Merge ra.kernel.org:/pub/scm/linux/kernel/git/davem/net

MAINTAINERS

@@ -9074,7 +9074,7 @@ S:	Maintained
 F:	drivers/usb/mtu3/
 
 MEGACHIPS STDPXXXX-GE-B850V3-FW LVDS/DP++ BRIDGES
-M:	Peter Senna Tschudin <peter.senna@collabora.com>
+M:	Peter Senna Tschudin <peter.senna@gmail.com>
 M:	Martin Donnelly <martin.donnelly@ge.com>
 M:	Martyn Welch <martyn.welch@collabora.co.uk>
 S:	Maintained

Makefile

@@ -2,7 +2,7 @@
 VERSION = 4
 PATCHLEVEL = 18
 SUBLEVEL = 0
-EXTRAVERSION = -rc5
+EXTRAVERSION = -rc6
 NAME = Merciless Moray
 
 # *DOCUMENTATION*

arch/alpha/kernel/osf_sys.c

@@ -1180,13 +1180,10 @@ SYSCALL_DEFINE2(osf_getrusage, int, who, struct rusage32 __user *, ru)
 SYSCALL_DEFINE4(osf_wait4, pid_t, pid, int __user *, ustatus, int, options,
 		struct rusage32 __user *, ur)
 {
-	unsigned int status = 0;
 	struct rusage r;
-	long err = kernel_wait4(pid, &status, options, &r);
+	long err = kernel_wait4(pid, ustatus, options, &r);
 	if (err <= 0)
 		return err;
-	if (put_user(status, ustatus))
-		return -EFAULT;
 	if (!ur)
 		return err;
 	if (put_tv_to_tv32(&ur->ru_utime, &r.ru_utime))

arch/arm/boot/dts/imx6qdl-zii-rdu2.dtsi

@@ -692,7 +692,7 @@ switch: switch@0 {
 			dsa,member = <0 0>;
 			eeprom-length = <512>;
 			interrupt-parent = <&gpio6>;
-			interrupts = <3 IRQ_TYPE_EDGE_FALLING>;
+			interrupts = <3 IRQ_TYPE_LEVEL_LOW>;
 			interrupt-controller;
 			#interrupt-cells = <2>;
 

arch/arm/boot/dts/omap4-droid4-xt894.dts

@@ -159,13 +159,7 @@ soundcard {
 
 		dais = <&mcbsp2_port>, <&mcbsp3_port>;
 	};
-};
 
-&dss {
-	status = "okay";
-};
-
-&gpio6 {
 	pwm8: dmtimer-pwm-8 {
 		pinctrl-names = "default";
 		pinctrl-0 = <&vibrator_direction_pin>;
@@ -192,7 +186,10 @@ vibrator {
 		pwm-names = "enable", "direction";
 		direction-duty-cycle-ns = <10000000>;
 	};
+};
 
+&dss {
+	status = "okay";
 };
 
 &dsi1 {

arch/ia64/kernel/perfmon.c

@@ -2278,17 +2278,15 @@ pfm_smpl_buffer_alloc(struct task_struct *task, struct file *filp, pfm_context_t
 	DPRINT(("smpl_buf @%p\n", smpl_buf));
 
 	/* allocate vma */
-	vma = kmem_cache_zalloc(vm_area_cachep, GFP_KERNEL);
+	vma = vm_area_alloc(mm);
 	if (!vma) {
 		DPRINT(("Cannot allocate vma\n"));
 		goto error_kmem;
 	}
-	INIT_LIST_HEAD(&vma->anon_vma_chain);
 
 	/*
 	 * partially initialize the vma for the sampling buffer
 	 */
-	vma->vm_mm	     = mm;
 	vma->vm_file	     = get_file(filp);
 	vma->vm_flags	     = VM_READ|VM_MAYREAD|VM_DONTEXPAND|VM_DONTDUMP;
 	vma->vm_page_prot    = PAGE_READONLY; /* XXX may need to change */
@@ -2346,7 +2344,7 @@ pfm_smpl_buffer_alloc(struct task_struct *task, struct file *filp, pfm_context_t
 	return 0;
 
 error:
-	kmem_cache_free(vm_area_cachep, vma);
+	vm_area_free(vma);
 error_kmem:
 	pfm_rvfree(smpl_buf, size);
 

arch/ia64/mm/init.c

@@ -114,10 +114,8 @@ ia64_init_addr_space (void)
 	 * the problem.  When the process attempts to write to the register backing store
 	 * for the first time, it will get a SEGFAULT in this case.
 	 */
-	vma = kmem_cache_zalloc(vm_area_cachep, GFP_KERNEL);
+	vma = vm_area_alloc(current->mm);
 	if (vma) {
-		INIT_LIST_HEAD(&vma->anon_vma_chain);
-		vma->vm_mm = current->mm;
 		vma->vm_start = current->thread.rbs_bot & PAGE_MASK;
 		vma->vm_end = vma->vm_start + PAGE_SIZE;
 		vma->vm_flags = VM_DATA_DEFAULT_FLAGS|VM_GROWSUP|VM_ACCOUNT;
@@ -125,7 +123,7 @@ ia64_init_addr_space (void)
 		down_write(&current->mm->mmap_sem);
 		if (insert_vm_struct(current->mm, vma)) {
 			up_write(&current->mm->mmap_sem);
-			kmem_cache_free(vm_area_cachep, vma);
+			vm_area_free(vma);
 			return;
 		}
 		up_write(&current->mm->mmap_sem);
@@ -133,10 +131,8 @@ ia64_init_addr_space (void)
 
 	/* map NaT-page at address zero to speed up speculative dereferencing of NULL: */
 	if (!(current->personality & MMAP_PAGE_ZERO)) {
-		vma = kmem_cache_zalloc(vm_area_cachep, GFP_KERNEL);
+		vma = vm_area_alloc(current->mm);
 		if (vma) {
-			INIT_LIST_HEAD(&vma->anon_vma_chain);
-			vma->vm_mm = current->mm;
 			vma->vm_end = PAGE_SIZE;
 			vma->vm_page_prot = __pgprot(pgprot_val(PAGE_READONLY) | _PAGE_MA_NAT);
 			vma->vm_flags = VM_READ | VM_MAYREAD | VM_IO |
@@ -144,7 +140,7 @@ ia64_init_addr_space (void)
 			down_write(&current->mm->mmap_sem);
 			if (insert_vm_struct(current->mm, vma)) {
 				up_write(&current->mm->mmap_sem);
-				kmem_cache_free(vm_area_cachep, vma);
+				vm_area_free(vma);
 				return;
 			}
 			up_write(&current->mm->mmap_sem);

arch/mips/ath79/common.c

@@ -58,7 +58,7 @@ EXPORT_SYMBOL_GPL(ath79_ddr_ctrl_init);
 
 void ath79_ddr_wb_flush(u32 reg)
 {
-	void __iomem *flush_reg = ath79_ddr_wb_flush_base + reg;
+	void __iomem *flush_reg = ath79_ddr_wb_flush_base + (reg * 4);
 
 	/* Flush the DDR write buffer. */
 	__raw_writel(0x1, flush_reg);

arch/mips/pci/pci.c

@@ -54,5 +54,5 @@ void pci_resource_to_user(const struct pci_dev *dev, int bar,
 	phys_addr_t size = resource_size(rsrc);
 
 	*start = fixup_bigphys_addr(rsrc->start, size);
-	*end = rsrc->start + size;
+	*end = rsrc->start + size - 1;
 }

arch/powerpc/Makefile

@@ -243,6 +243,7 @@ endif
 cpu-as-$(CONFIG_4xx)		+= -Wa,-m405
 cpu-as-$(CONFIG_ALTIVEC)	+= $(call as-option,-Wa$(comma)-maltivec)
 cpu-as-$(CONFIG_E200)		+= -Wa,-me200
+cpu-as-$(CONFIG_E500)		+= -Wa,-me500
 cpu-as-$(CONFIG_PPC_BOOK3S_64)	+= -Wa,-mpower4
 cpu-as-$(CONFIG_PPC_E500MC)	+= $(call as-option,-Wa$(comma)-me500mc)
 

arch/powerpc/include/asm/mmu_context.h

@@ -35,9 +35,9 @@ extern struct mm_iommu_table_group_mem_t *mm_iommu_lookup_rm(
 extern struct mm_iommu_table_group_mem_t *mm_iommu_find(struct mm_struct *mm,
 		unsigned long ua, unsigned long entries);
 extern long mm_iommu_ua_to_hpa(struct mm_iommu_table_group_mem_t *mem,
-		unsigned long ua, unsigned long *hpa);
+		unsigned long ua, unsigned int pageshift, unsigned long *hpa);
 extern long mm_iommu_ua_to_hpa_rm(struct mm_iommu_table_group_mem_t *mem,
-		unsigned long ua, unsigned long *hpa);
+		unsigned long ua, unsigned int pageshift, unsigned long *hpa);
 extern long mm_iommu_mapped_inc(struct mm_iommu_table_group_mem_t *mem);
 extern void mm_iommu_mapped_dec(struct mm_iommu_table_group_mem_t *mem);
 #endif

arch/powerpc/kernel/idle_book3s.S

@@ -144,7 +144,9 @@ power9_restore_additional_sprs:
 	mtspr	SPRN_MMCR1, r4
 
 	ld	r3, STOP_MMCR2(r13)
+	ld	r4, PACA_SPRG_VDSO(r13)
 	mtspr	SPRN_MMCR2, r3
+	mtspr	SPRN_SPRG3, r4
 	blr
 
 /*

arch/powerpc/kvm/book3s_64_vio.c

@@ -449,7 +449,7 @@ long kvmppc_tce_iommu_do_map(struct kvm *kvm, struct iommu_table *tbl,
 		/* This only handles v2 IOMMU type, v1 is handled via ioctl() */
 		return H_TOO_HARD;
 
-	if (WARN_ON_ONCE(mm_iommu_ua_to_hpa(mem, ua, &hpa)))
+	if (WARN_ON_ONCE(mm_iommu_ua_to_hpa(mem, ua, tbl->it_page_shift, &hpa)))
 		return H_HARDWARE;
 
 	if (mm_iommu_mapped_inc(mem))

arch/powerpc/kvm/book3s_64_vio_hv.c

@@ -279,7 +279,8 @@ static long kvmppc_rm_tce_iommu_do_map(struct kvm *kvm, struct iommu_table *tbl,
 	if (!mem)
 		return H_TOO_HARD;
 
-	if (WARN_ON_ONCE_RM(mm_iommu_ua_to_hpa_rm(mem, ua, &hpa)))
+	if (WARN_ON_ONCE_RM(mm_iommu_ua_to_hpa_rm(mem, ua, tbl->it_page_shift,
+			&hpa)))
 		return H_HARDWARE;
 
 	pua = (void *) vmalloc_to_phys(pua);
@@ -469,7 +470,8 @@ long kvmppc_rm_h_put_tce_indirect(struct kvm_vcpu *vcpu,
 
 		mem = mm_iommu_lookup_rm(vcpu->kvm->mm, ua, IOMMU_PAGE_SIZE_4K);
 		if (mem)
-			prereg = mm_iommu_ua_to_hpa_rm(mem, ua, &tces) == 0;
+			prereg = mm_iommu_ua_to_hpa_rm(mem, ua,
+					IOMMU_PAGE_SHIFT_4K, &tces) == 0;
 	}
 
 	if (!prereg) {

arch/powerpc/mm/mmu_context_iommu.c

@@ -19,6 +19,7 @@
 #include <linux/hugetlb.h>
 #include <linux/swap.h>
 #include <asm/mmu_context.h>
+#include <asm/pte-walk.h>
 
 static DEFINE_MUTEX(mem_list_mutex);
 
@@ -27,6 +28,7 @@ struct mm_iommu_table_group_mem_t {
 	struct rcu_head rcu;
 	unsigned long used;
 	atomic64_t mapped;
+	unsigned int pageshift;
 	u64 ua;			/* userspace address */
 	u64 entries;		/* number of entries in hpas[] */
 	u64 *hpas;		/* vmalloc'ed */
@@ -125,6 +127,8 @@ long mm_iommu_get(struct mm_struct *mm, unsigned long ua, unsigned long entries,
 {
 	struct mm_iommu_table_group_mem_t *mem;
 	long i, j, ret = 0, locked_entries = 0;
+	unsigned int pageshift;
+	unsigned long flags;
 	struct page *page = NULL;
 
 	mutex_lock(&mem_list_mutex);
@@ -159,6 +163,12 @@ long mm_iommu_get(struct mm_struct *mm, unsigned long ua, unsigned long entries,
 		goto unlock_exit;
 	}
 
+	/*
+	 * For a starting point for a maximum page size calculation
+	 * we use @ua and @entries natural alignment to allow IOMMU pages
+	 * smaller than huge pages but still bigger than PAGE_SIZE.
+	 */
+	mem->pageshift = __ffs(ua | (entries << PAGE_SHIFT));
 	mem->hpas = vzalloc(array_size(entries, sizeof(mem->hpas[0])));
 	if (!mem->hpas) {
 		kfree(mem);
@@ -199,6 +209,23 @@ long mm_iommu_get(struct mm_struct *mm, unsigned long ua, unsigned long entries,
 			}
 		}
 populate:
+		pageshift = PAGE_SHIFT;
+		if (PageCompound(page)) {
+			pte_t *pte;
+			struct page *head = compound_head(page);
+			unsigned int compshift = compound_order(head);
+
+			local_irq_save(flags); /* disables as well */
+			pte = find_linux_pte(mm->pgd, ua, NULL, &pageshift);
+			local_irq_restore(flags);
+
+			/* Double check it is still the same pinned page */
+			if (pte && pte_page(*pte) == head &&
+					pageshift == compshift)
+				pageshift = max_t(unsigned int, pageshift,
+						PAGE_SHIFT);
+		}
+		mem->pageshift = min(mem->pageshift, pageshift);
 		mem->hpas[i] = page_to_pfn(page) << PAGE_SHIFT;
 	}
 
@@ -349,7 +376,7 @@ struct mm_iommu_table_group_mem_t *mm_iommu_find(struct mm_struct *mm,
 EXPORT_SYMBOL_GPL(mm_iommu_find);
 
 long mm_iommu_ua_to_hpa(struct mm_iommu_table_group_mem_t *mem,
-		unsigned long ua, unsigned long *hpa)
+		unsigned long ua, unsigned int pageshift, unsigned long *hpa)
 {
 	const long entry = (ua - mem->ua) >> PAGE_SHIFT;
 	u64 *va = &mem->hpas[entry];
@@ -357,6 +384,9 @@ long mm_iommu_ua_to_hpa(struct mm_iommu_table_group_mem_t *mem,
 	if (entry >= mem->entries)
 		return -EFAULT;
 
+	if (pageshift > mem->pageshift)
+		return -EFAULT;
+
 	*hpa = *va | (ua & ~PAGE_MASK);
 
 	return 0;
@@ -364,7 +394,7 @@ long mm_iommu_ua_to_hpa(struct mm_iommu_table_group_mem_t *mem,
 EXPORT_SYMBOL_GPL(mm_iommu_ua_to_hpa);
 
 long mm_iommu_ua_to_hpa_rm(struct mm_iommu_table_group_mem_t *mem,
-		unsigned long ua, unsigned long *hpa)
+		unsigned long ua, unsigned int pageshift, unsigned long *hpa)
 {
 	const long entry = (ua - mem->ua) >> PAGE_SHIFT;
 	void *va = &mem->hpas[entry];
@@ -373,6 +403,9 @@ long mm_iommu_ua_to_hpa_rm(struct mm_iommu_table_group_mem_t *mem,
 	if (entry >= mem->entries)
 		return -EFAULT;
 
+	if (pageshift > mem->pageshift)
+		return -EFAULT;
+
 	pa = (void *) vmalloc_to_phys(va);
 	if (!pa)
 		return -EFAULT;

arch/powerpc/net/bpf_jit_comp64.c

@@ -286,6 +286,7 @@ static int bpf_jit_build_body(struct bpf_prog *fp, u32 *image,
 		u64 imm64;
 		u8 *func;
 		u32 true_cond;
+		u32 tmp_idx;
 
 		/*
 		 * addrs[] maps a BPF bytecode address into a real offset from
@@ -637,11 +638,7 @@ static int bpf_jit_build_body(struct bpf_prog *fp, u32 *image,
 		case BPF_STX | BPF_XADD | BPF_W:
 			/* Get EA into TMP_REG_1 */
 			PPC_ADDI(b2p[TMP_REG_1], dst_reg, off);
-			/* error if EA is not word-aligned */
+			tmp_idx = ctx->idx * 4;
-			PPC_ANDI(b2p[TMP_REG_2], b2p[TMP_REG_1], 0x03);
-			PPC_BCC_SHORT(COND_EQ, (ctx->idx * 4) + 12);
-			PPC_LI(b2p[BPF_REG_0], 0);
-			PPC_JMP(exit_addr);
 			/* load value from memory into TMP_REG_2 */
 			PPC_BPF_LWARX(b2p[TMP_REG_2], 0, b2p[TMP_REG_1], 0);
 			/* add value from src_reg into this */
@@ -649,32 +646,16 @@ static int bpf_jit_build_body(struct bpf_prog *fp, u32 *image,
 			/* store result back */
 			PPC_BPF_STWCX(b2p[TMP_REG_2], 0, b2p[TMP_REG_1]);
 			/* we're done if this succeeded */
-			PPC_BCC_SHORT(COND_EQ, (ctx->idx * 4) + (7*4));
+			PPC_BCC_SHORT(COND_NE, tmp_idx);
-			/* otherwise, let's try once more */
-			PPC_BPF_LWARX(b2p[TMP_REG_2], 0, b2p[TMP_REG_1], 0);
-			PPC_ADD(b2p[TMP_REG_2], b2p[TMP_REG_2], src_reg);
-			PPC_BPF_STWCX(b2p[TMP_REG_2], 0, b2p[TMP_REG_1]);
-			/* exit if the store was not successful */
-			PPC_LI(b2p[BPF_REG_0], 0);
-			PPC_BCC(COND_NE, exit_addr);
 			break;
 		/* *(u64 *)(dst + off) += src */
 		case BPF_STX | BPF_XADD | BPF_DW:
 			PPC_ADDI(b2p[TMP_REG_1], dst_reg, off);
-			/* error if EA is not doubleword-aligned */
+			tmp_idx = ctx->idx * 4;
-			PPC_ANDI(b2p[TMP_REG_2], b2p[TMP_REG_1], 0x07);
-			PPC_BCC_SHORT(COND_EQ, (ctx->idx * 4) + (3*4));
-			PPC_LI(b2p[BPF_REG_0], 0);
-			PPC_JMP(exit_addr);
 			PPC_BPF_LDARX(b2p[TMP_REG_2], 0, b2p[TMP_REG_1], 0);
 			PPC_ADD(b2p[TMP_REG_2], b2p[TMP_REG_2], src_reg);
 			PPC_BPF_STDCX(b2p[TMP_REG_2], 0, b2p[TMP_REG_1]);
-			PPC_BCC_SHORT(COND_EQ, (ctx->idx * 4) + (7*4));
+			PPC_BCC_SHORT(COND_NE, tmp_idx);
-			PPC_BPF_LDARX(b2p[TMP_REG_2], 0, b2p[TMP_REG_1], 0);
-			PPC_ADD(b2p[TMP_REG_2], b2p[TMP_REG_2], src_reg);
-			PPC_BPF_STDCX(b2p[TMP_REG_2], 0, b2p[TMP_REG_1]);
-			PPC_LI(b2p[BPF_REG_0], 0);
-			PPC_BCC(COND_NE, exit_addr);
 			break;
 
 		/*

arch/powerpc/xmon/xmon.c

@@ -2734,7 +2734,7 @@ generic_inst_dump(unsigned long adr, long count, int praddr,
 {
 	int nr, dotted;
 	unsigned long first_adr;
-	unsigned long inst, last_inst = 0;
+	unsigned int inst, last_inst = 0;
 	unsigned char val[4];
 
 	dotted = 0;
@@ -2758,7 +2758,7 @@ generic_inst_dump(unsigned long adr, long count, int praddr,
 		dotted = 0;
 		last_inst = inst;
 		if (praddr)
-			printf(REG"  %.8lx", adr, inst);
+			printf(REG"  %.8x", adr, inst);
 		printf("\t");
 		dump_func(inst, adr);
 		printf("\n");

arch/s390/Kconfig

@@ -140,7 +140,7 @@ config S390
 	select HAVE_FUNCTION_GRAPH_TRACER
 	select HAVE_FUNCTION_TRACER
 	select HAVE_FUTEX_CMPXCHG if FUTEX
-	select HAVE_GCC_PLUGINS
+	select HAVE_GCC_PLUGINS if BROKEN
 	select HAVE_KERNEL_BZIP2
 	select HAVE_KERNEL_GZIP
 	select HAVE_KERNEL_LZ4

arch/x86/Kconfig

@@ -63,7 +63,7 @@ config X86
 	select ARCH_HAS_PTE_SPECIAL
 	select ARCH_HAS_REFCOUNT
 	select ARCH_HAS_UACCESS_FLUSHCACHE	if X86_64
-	select ARCH_HAS_UACCESS_MCSAFE		if X86_64
+	select ARCH_HAS_UACCESS_MCSAFE		if X86_64 && X86_MCE
 	select ARCH_HAS_SET_MEMORY
 	select ARCH_HAS_SG_CHAIN
 	select ARCH_HAS_STRICT_KERNEL_RWX

arch/x86/events/intel/ds.c

@@ -408,9 +408,11 @@ static int alloc_bts_buffer(int cpu)
 	ds->bts_buffer_base = (unsigned long) cea;
 	ds_update_cea(cea, buffer, BTS_BUFFER_SIZE, PAGE_KERNEL);
 	ds->bts_index = ds->bts_buffer_base;
-	max = BTS_RECORD_SIZE * (BTS_BUFFER_SIZE / BTS_RECORD_SIZE);
+	max = BTS_BUFFER_SIZE / BTS_RECORD_SIZE;
-	ds->bts_absolute_maximum = ds->bts_buffer_base + max;
+	ds->bts_absolute_maximum = ds->bts_buffer_base +
-	ds->bts_interrupt_threshold = ds->bts_absolute_maximum - (max / 16);
+					max * BTS_RECORD_SIZE;
+	ds->bts_interrupt_threshold = ds->bts_absolute_maximum -
+					(max / 16) * BTS_RECORD_SIZE;
 	return 0;
 }
 

arch/x86/include/asm/apm.h

@@ -7,8 +7,6 @@
 #ifndef _ASM_X86_MACH_DEFAULT_APM_H
 #define _ASM_X86_MACH_DEFAULT_APM_H
 
-#include <asm/nospec-branch.h>
-
 #ifdef APM_ZERO_SEGS
 #	define APM_DO_ZERO_SEGS \
 		"pushl %%ds\n\t" \
@@ -34,7 +32,6 @@ static inline void apm_bios_call_asm(u32 func, u32 ebx_in, u32 ecx_in,
 	 * N.B. We do NOT need a cld after the BIOS call
 	 * because we always save and restore the flags.
 	 */
-	firmware_restrict_branch_speculation_start();
 	__asm__ __volatile__(APM_DO_ZERO_SEGS
 		"pushl %%edi\n\t"
 		"pushl %%ebp\n\t"
@@ -47,7 +44,6 @@ static inline void apm_bios_call_asm(u32 func, u32 ebx_in, u32 ecx_in,
 		  "=S" (*esi)
 		: "a" (func), "b" (ebx_in), "c" (ecx_in)
 		: "memory", "cc");
-	firmware_restrict_branch_speculation_end();
 }
 
 static inline bool apm_bios_call_simple_asm(u32 func, u32 ebx_in,
@@ -60,7 +56,6 @@ static inline bool apm_bios_call_simple_asm(u32 func, u32 ebx_in,
 	 * N.B. We do NOT need a cld after the BIOS call
 	 * because we always save and restore the flags.
 	 */
-	firmware_restrict_branch_speculation_start();
 	__asm__ __volatile__(APM_DO_ZERO_SEGS
 		"pushl %%edi\n\t"
 		"pushl %%ebp\n\t"
@@ -73,7 +68,6 @@ static inline bool apm_bios_call_simple_asm(u32 func, u32 ebx_in,
 		  "=S" (si)
 		: "a" (func), "b" (ebx_in), "c" (ecx_in)
 		: "memory", "cc");
-	firmware_restrict_branch_speculation_end();
 	return error;
 }
 

arch/x86/include/asm/uaccess_64.h

@@ -52,7 +52,12 @@ copy_to_user_mcsafe(void *to, const void *from, unsigned len)
 	unsigned long ret;
 
 	__uaccess_begin();
-	ret = memcpy_mcsafe(to, from, len);
+	/*
+	 * Note, __memcpy_mcsafe() is explicitly used since it can
+	 * handle exceptions / faults.  memcpy_mcsafe() may fall back to
+	 * memcpy() which lacks this handling.
+	 */
+	ret = __memcpy_mcsafe(to, from, len);
 	__uaccess_end();
 	return ret;
 }

arch/x86/kernel/apm_32.c

@@ -240,6 +240,7 @@
 #include <asm/olpc.h>
 #include <asm/paravirt.h>
 #include <asm/reboot.h>
+#include <asm/nospec-branch.h>
 
 #if defined(CONFIG_APM_DISPLAY_BLANK) && defined(CONFIG_VT)
 extern int (*console_blank_hook)(int);
@@ -614,11 +615,13 @@ static long __apm_bios_call(void *_call)
 	gdt[0x40 / 8] = bad_bios_desc;
 
 	apm_irq_save(flags);
+	firmware_restrict_branch_speculation_start();
 	APM_DO_SAVE_SEGS;
 	apm_bios_call_asm(call->func, call->ebx, call->ecx,
 			  &call->eax, &call->ebx, &call->ecx, &call->edx,
 			  &call->esi);
 	APM_DO_RESTORE_SEGS;
+	firmware_restrict_branch_speculation_end();
 	apm_irq_restore(flags);
 	gdt[0x40 / 8] = save_desc_40;
 	put_cpu();
@@ -690,10 +693,12 @@ static long __apm_bios_call_simple(void *_call)
 	gdt[0x40 / 8] = bad_bios_desc;
 
 	apm_irq_save(flags);
+	firmware_restrict_branch_speculation_start();
 	APM_DO_SAVE_SEGS;
 	error = apm_bios_call_simple_asm(call->func, call->ebx, call->ecx,
 					 &call->eax);
 	APM_DO_RESTORE_SEGS;
+	firmware_restrict_branch_speculation_end();
 	apm_irq_restore(flags);
 	gdt[0x40 / 8] = save_desc_40;
 	put_cpu();

arch/x86/kernel/cpu/mcheck/mce.c

@@ -2165,9 +2165,6 @@ static ssize_t store_int_with_restart(struct device *s,
 	if (check_interval == old_check_interval)
 		return ret;
 
-	if (check_interval < 1)
-		check_interval = 1;
-
 	mutex_lock(&mce_sysfs_mutex);
 	mce_restart();
 	mutex_unlock(&mce_sysfs_mutex);

drivers/gpu/drm/drm_lease.c

@@ -553,24 +553,13 @@ int drm_mode_create_lease_ioctl(struct drm_device *dev,
 
 	/* Clone the lessor file to create a new file for us */
 	DRM_DEBUG_LEASE("Allocating lease file\n");
-	path_get(&lessor_file->f_path);
+	lessee_file = filp_clone_open(lessor_file);
-	lessee_file = alloc_file(&lessor_file->f_path,
-				 lessor_file->f_mode,
-				 fops_get(lessor_file->f_inode->i_fop));
-
 	if (IS_ERR(lessee_file)) {
 		ret = PTR_ERR(lessee_file);
 		goto out_lessee;
 	}
 
-	/* Initialize the new file for DRM */
-	DRM_DEBUG_LEASE("Initializing the file with %p\n", lessee_file->f_op->open);
-	ret = lessee_file->f_op->open(lessee_file->f_inode, lessee_file);
-	if (ret)
-		goto out_lessee_file;
-
 	lessee_priv = lessee_file->private_data;
-
 	/* Change the file to a master one */
 	drm_master_put(&lessee_priv->master);
 	lessee_priv->master = lessee;
@@ -588,9 +577,6 @@ int drm_mode_create_lease_ioctl(struct drm_device *dev,
 	DRM_DEBUG_LEASE("drm_mode_create_lease_ioctl succeeded\n");
 	return 0;
 
-out_lessee_file:
-	fput(lessee_file);
-
 out_lessee:
 	drm_master_put(&lessee);
 

drivers/misc/cxl/api.c

@@ -103,15 +103,15 @@ static struct file *cxl_getfile(const char *name,
 	d_instantiate(path.dentry, inode);
 
 	file = alloc_file(&path, OPEN_FMODE(flags), fops);
-	if (IS_ERR(file))
+	if (IS_ERR(file)) {
-		goto err_dput;
+		path_put(&path);
+		goto err_fs;
+	}
 	file->f_flags = flags & (O_ACCMODE | O_NONBLOCK);
 	file->private_data = priv;
 
 	return file;
 
-err_dput:
-	path_put(&path);
 err_inode:
 	iput(inode);
 err_fs:

drivers/net/bonding/bond_options.c

@@ -743,16 +743,21 @@ const struct bond_option *bond_opt_get(unsigned int option)
 static int bond_option_mode_set(struct bonding *bond,
 				const struct bond_opt_value *newval)
 {
-	if (!bond_mode_uses_arp(newval->value) && bond->params.arp_interval) {
+	if (!bond_mode_uses_arp(newval->value)) {
+		if (bond->params.arp_interval) {
 			netdev_dbg(bond->dev, "%s mode is incompatible with arp monitoring, start mii monitoring\n",
 				   newval->string);
 			/* disable arp monitoring */
 			bond->params.arp_interval = 0;
+		}
+
+		if (!bond->params.miimon) {
 			/* set miimon to default value */
 			bond->params.miimon = BOND_DEFAULT_MIIMON;
 			netdev_dbg(bond->dev, "Setting MII monitoring interval to %d\n",
 				   bond->params.miimon);
 		}
+	}
 
 	if (newval->value == BOND_MODE_ALB)
 		bond->params.tlb_dynamic_lb = 1;

drivers/net/can/m_can/m_can.c

@@ -634,10 +634,12 @@ static int m_can_clk_start(struct m_can_priv *priv)
 	int err;
 
 	err = pm_runtime_get_sync(priv->device);
-	if (err)
+	if (err < 0) {
 		pm_runtime_put_noidle(priv->device);
-
 		return err;
+	}
+
+	return 0;
 }
 
 static void m_can_clk_stop(struct m_can_priv *priv)
@@ -1109,7 +1111,8 @@ static void m_can_chip_config(struct net_device *dev)
 
 	} else {
 	/* Version 3.1.x or 3.2.x */
-		cccr &= ~(CCCR_TEST | CCCR_MON | CCCR_BRSE | CCCR_FDOE);
+		cccr &= ~(CCCR_TEST | CCCR_MON | CCCR_BRSE | CCCR_FDOE |
+			  CCCR_NISO);
 
 		/* Only 3.2.x has NISO Bit implemented */
 		if (priv->can.ctrlmode & CAN_CTRLMODE_FD_NON_ISO)
@@ -1642,8 +1645,6 @@ static int m_can_plat_probe(struct platform_device *pdev)
 	priv->can.clock.freq = clk_get_rate(cclk);
 	priv->mram_base = mram_addr;
 
-	m_can_of_parse_mram(priv, mram_config_vals);
-
 	platform_set_drvdata(pdev, dev);
 	SET_NETDEV_DEV(dev, &pdev->dev);
 
@@ -1666,6 +1667,8 @@ static int m_can_plat_probe(struct platform_device *pdev)
 		goto clk_disable;
 	}
 
+	m_can_of_parse_mram(priv, mram_config_vals);
+
 	devm_can_led_init(dev);
 
 	of_can_transceiver(dev);
@@ -1687,8 +1690,6 @@ static int m_can_plat_probe(struct platform_device *pdev)
 	return ret;
 }
 
-/* TODO: runtime PM with power down or sleep mode  */
-
 static __maybe_unused int m_can_suspend(struct device *dev)
 {
 	struct net_device *ndev = dev_get_drvdata(dev);
@@ -1715,8 +1716,6 @@ static __maybe_unused int m_can_resume(struct device *dev)
 
 	pinctrl_pm_select_default_state(dev);
 
-	m_can_init_ram(priv);
-
 	priv->can.state = CAN_STATE_ERROR_ACTIVE;
 
 	if (netif_running(ndev)) {
@@ -1726,6 +1725,7 @@ static __maybe_unused int m_can_resume(struct device *dev)
 		if (ret)
 			return ret;
 
+		m_can_init_ram(priv);
 		m_can_start(ndev);
 		netif_device_attach(ndev);
 		netif_start_queue(ndev);

drivers/net/can/mscan/mpc5xxx_can.c

@@ -86,6 +86,11 @@ static u32 mpc52xx_can_get_clock(struct platform_device *ofdev,
 		return 0;
 	}
 	cdm = of_iomap(np_cdm, 0);
+	if (!cdm) {
+		of_node_put(np_cdm);
+		dev_err(&ofdev->dev, "can't map clock node!\n");
+		return 0;
+	}
 
 	if (in_8(&cdm->ipb_clk_sel) & 0x1)
 		freq *= 2;

drivers/net/can/peak_canfd/peak_pciefd_main.c

@@ -58,6 +58,10 @@ MODULE_LICENSE("GPL v2");
 #define PCIEFD_REG_SYS_VER1		0x0040	/* version reg #1 */
 #define PCIEFD_REG_SYS_VER2		0x0044	/* version reg #2 */
 
+#define PCIEFD_FW_VERSION(x, y, z)	(((u32)(x) << 24) | \
+					 ((u32)(y) << 16) | \
+					 ((u32)(z) << 8))
+
 /* System Control Registers Bits */
 #define PCIEFD_SYS_CTL_TS_RST		0x00000001	/* timestamp clock */
 #define PCIEFD_SYS_CTL_CLK_EN		0x00000002	/* system clock */
@@ -782,6 +786,21 @@ static int peak_pciefd_probe(struct pci_dev *pdev,
 		 "%ux CAN-FD PCAN-PCIe FPGA v%u.%u.%u:\n", can_count,
 		 hw_ver_major, hw_ver_minor, hw_ver_sub);
 
+#ifdef CONFIG_ARCH_DMA_ADDR_T_64BIT
+	/* FW < v3.3.0 DMA logic doesn't handle correctly the mix of 32-bit and
+	 * 64-bit logical addresses: this workaround forces usage of 32-bit
+	 * DMA addresses only when such a fw is detected.
+	 */
+	if (PCIEFD_FW_VERSION(hw_ver_major, hw_ver_minor, hw_ver_sub) <
+	    PCIEFD_FW_VERSION(3, 3, 0)) {
+		err = dma_set_mask_and_coherent(&pdev->dev, DMA_BIT_MASK(32));
+		if (err)
+			dev_warn(&pdev->dev,
+				 "warning: can't set DMA mask %llxh (err %d)\n",
+				 DMA_BIT_MASK(32), err);
+	}
+#endif
+
 	/* stop system clock */
 	pciefd_sys_writereg(pciefd, PCIEFD_SYS_CTL_CLK_EN,
 			    PCIEFD_REG_SYS_CTL_CLR);

drivers/net/can/xilinx_can.c

@@ -2,6 +2,7 @@
  *
  * Copyright (C) 2012 - 2014 Xilinx, Inc.
  * Copyright (C) 2009 PetaLogix. All rights reserved.
+ * Copyright (C) 2017 Sandvik Mining and Construction Oy
  *
  * Description:
  * This driver is developed for Axi CAN IP and for Zynq CANPS Controller.
@@ -25,8 +26,10 @@
 #include <linux/module.h>
 #include <linux/netdevice.h>
 #include <linux/of.h>
+#include <linux/of_device.h>
 #include <linux/platform_device.h>
 #include <linux/skbuff.h>
+#include <linux/spinlock.h>
 #include <linux/string.h>
 #include <linux/types.h>
 #include <linux/can/dev.h>
@@ -101,7 +104,7 @@ enum xcan_reg {
 #define XCAN_INTR_ALL		(XCAN_IXR_TXOK_MASK | XCAN_IXR_BSOFF_MASK |\
 				 XCAN_IXR_WKUP_MASK | XCAN_IXR_SLP_MASK | \
 				 XCAN_IXR_RXNEMP_MASK | XCAN_IXR_ERROR_MASK | \
-				 XCAN_IXR_ARBLST_MASK | XCAN_IXR_RXOK_MASK)
+				 XCAN_IXR_RXOFLW_MASK | XCAN_IXR_ARBLST_MASK)
 
 /* CAN register bit shift - XCAN_<REG>_<BIT>_SHIFT */
 #define XCAN_BTR_SJW_SHIFT		7  /* Synchronous jump width */
@@ -118,6 +121,7 @@ enum xcan_reg {
 /**
  * struct xcan_priv - This definition define CAN driver instance
  * @can:			CAN private data structure.
+ * @tx_lock:			Lock for synchronizing TX interrupt handling
  * @tx_head:			Tx CAN packets ready to send on the queue
  * @tx_tail:			Tx CAN packets successfully sended on the queue
  * @tx_max:			Maximum number packets the driver can send
@@ -132,6 +136,7 @@ enum xcan_reg {
  */
 struct xcan_priv {
 	struct can_priv can;
+	spinlock_t tx_lock;
 	unsigned int tx_head;
 	unsigned int tx_tail;
 	unsigned int tx_max;
@@ -159,6 +164,11 @@ static const struct can_bittiming_const xcan_bittiming_const = {
 	.brp_inc = 1,
 };
 
+#define XCAN_CAP_WATERMARK	0x0001
+struct xcan_devtype_data {
+	unsigned int caps;
+};
+
 /**
  * xcan_write_reg_le - Write a value to the device register little endian
  * @priv:	Driver private data structure
@@ -238,6 +248,10 @@ static int set_reset_mode(struct net_device *ndev)
 		usleep_range(500, 10000);
 	}
 
+	/* reset clears FIFOs */
+	priv->tx_head = 0;
+	priv->tx_tail = 0;
+
 	return 0;
 }
 
@@ -392,6 +406,7 @@ static int xcan_start_xmit(struct sk_buff *skb, struct net_device *ndev)
 	struct net_device_stats *stats = &ndev->stats;
 	struct can_frame *cf = (struct can_frame *)skb->data;
 	u32 id, dlc, data[2] = {0, 0};
+	unsigned long flags;
 
 	if (can_dropped_invalid_skb(ndev, skb))
 		return NETDEV_TX_OK;
@@ -439,6 +454,9 @@ static int xcan_start_xmit(struct sk_buff *skb, struct net_device *ndev)
 		data[1] = be32_to_cpup((__be32 *)(cf->data + 4));
 
 	can_put_echo_skb(skb, ndev, priv->tx_head % priv->tx_max);
+
+	spin_lock_irqsave(&priv->tx_lock, flags);
+
 	priv->tx_head++;
 
 	/* Write the Frame to Xilinx CAN TX FIFO */
@@ -454,10 +472,16 @@ static int xcan_start_xmit(struct sk_buff *skb, struct net_device *ndev)
 		stats->tx_bytes += cf->can_dlc;
 	}
 
+	/* Clear TX-FIFO-empty interrupt for xcan_tx_interrupt() */
+	if (priv->tx_max > 1)
+		priv->write_reg(priv, XCAN_ICR_OFFSET, XCAN_IXR_TXFEMP_MASK);
+
 	/* Check if the TX buffer is full */
 	if ((priv->tx_head - priv->tx_tail) == priv->tx_max)
 		netif_stop_queue(ndev);
 
+	spin_unlock_irqrestore(&priv->tx_lock, flags);
+
 	return NETDEV_TX_OK;
 }
 
@@ -529,6 +553,123 @@ static int xcan_rx(struct net_device *ndev)
 	return 1;
 }
 
+/**
+ * xcan_current_error_state - Get current error state from HW
+ * @ndev:	Pointer to net_device structure
+ *
+ * Checks the current CAN error state from the HW. Note that this
+ * only checks for ERROR_PASSIVE and ERROR_WARNING.
+ *
+ * Return:
+ * ERROR_PASSIVE or ERROR_WARNING if either is active, ERROR_ACTIVE
+ * otherwise.
+ */
+static enum can_state xcan_current_error_state(struct net_device *ndev)
+{
+	struct xcan_priv *priv = netdev_priv(ndev);
+	u32 status = priv->read_reg(priv, XCAN_SR_OFFSET);
+
+	if ((status & XCAN_SR_ESTAT_MASK) == XCAN_SR_ESTAT_MASK)
+		return CAN_STATE_ERROR_PASSIVE;
+	else if (status & XCAN_SR_ERRWRN_MASK)
+		return CAN_STATE_ERROR_WARNING;
+	else
+		return CAN_STATE_ERROR_ACTIVE;
+}
+
+/**
+ * xcan_set_error_state - Set new CAN error state
+ * @ndev:	Pointer to net_device structure
+ * @new_state:	The new CAN state to be set
+ * @cf:		Error frame to be populated or NULL
+ *
+ * Set new CAN error state for the device, updating statistics and
+ * populating the error frame if given.
+ */
+static void xcan_set_error_state(struct net_device *ndev,
+				 enum can_state new_state,
+				 struct can_frame *cf)
+{
+	struct xcan_priv *priv = netdev_priv(ndev);
+	u32 ecr = priv->read_reg(priv, XCAN_ECR_OFFSET);
+	u32 txerr = ecr & XCAN_ECR_TEC_MASK;
+	u32 rxerr = (ecr & XCAN_ECR_REC_MASK) >> XCAN_ESR_REC_SHIFT;
+
+	priv->can.state = new_state;
+
+	if (cf) {
+		cf->can_id |= CAN_ERR_CRTL;
+		cf->data[6] = txerr;
+		cf->data[7] = rxerr;
+	}
+
+	switch (new_state) {
+	case CAN_STATE_ERROR_PASSIVE:
+		priv->can.can_stats.error_passive++;
+		if (cf)
+			cf->data[1] = (rxerr > 127) ?
+					CAN_ERR_CRTL_RX_PASSIVE :
+					CAN_ERR_CRTL_TX_PASSIVE;
+		break;
+	case CAN_STATE_ERROR_WARNING:
+		priv->can.can_stats.error_warning++;
+		if (cf)
+			cf->data[1] |= (txerr > rxerr) ?
+					CAN_ERR_CRTL_TX_WARNING :
+					CAN_ERR_CRTL_RX_WARNING;
+		break;
+	case CAN_STATE_ERROR_ACTIVE:
+		if (cf)
+			cf->data[1] |= CAN_ERR_CRTL_ACTIVE;
+		break;
+	default:
+		/* non-ERROR states are handled elsewhere */
+		WARN_ON(1);
+		break;
+	}
+}
+
+/**
+ * xcan_update_error_state_after_rxtx - Update CAN error state after RX/TX
+ * @ndev:	Pointer to net_device structure
+ *
+ * If the device is in a ERROR-WARNING or ERROR-PASSIVE state, check if
+ * the performed RX/TX has caused it to drop to a lesser state and set
+ * the interface state accordingly.
+ */
+static void xcan_update_error_state_after_rxtx(struct net_device *ndev)
+{
+	struct xcan_priv *priv = netdev_priv(ndev);
+	enum can_state old_state = priv->can.state;
+	enum can_state new_state;
+
+	/* changing error state due to successful frame RX/TX can only
+	 * occur from these states
+	 */
+	if (old_state != CAN_STATE_ERROR_WARNING &&
+	    old_state != CAN_STATE_ERROR_PASSIVE)
+		return;
+
+	new_state = xcan_current_error_state(ndev);
+
+	if (new_state != old_state) {
+		struct sk_buff *skb;
+		struct can_frame *cf;
+
+		skb = alloc_can_err_skb(ndev, &cf);
+
+		xcan_set_error_state(ndev, new_state, skb ? cf : NULL);
+
+		if (skb) {
+			struct net_device_stats *stats = &ndev->stats;
+
+			stats->rx_packets++;
+			stats->rx_bytes += cf->can_dlc;
+			netif_rx(skb);
+		}
+	}
+}
+
 /**
  * xcan_err_interrupt - error frame Isr
  * @ndev:	net_device pointer
@@ -544,16 +685,12 @@ static void xcan_err_interrupt(struct net_device *ndev, u32 isr)
 	struct net_device_stats *stats = &ndev->stats;
 	struct can_frame *cf;
 	struct sk_buff *skb;
-	u32 err_status, status, txerr = 0, rxerr = 0;
+	u32 err_status;
 
 	skb = alloc_can_err_skb(ndev, &cf);
 
 	err_status = priv->read_reg(priv, XCAN_ESR_OFFSET);
 	priv->write_reg(priv, XCAN_ESR_OFFSET, err_status);
-	txerr = priv->read_reg(priv, XCAN_ECR_OFFSET) & XCAN_ECR_TEC_MASK;
-	rxerr = ((priv->read_reg(priv, XCAN_ECR_OFFSET) &
-			XCAN_ECR_REC_MASK) >> XCAN_ESR_REC_SHIFT);
-	status = priv->read_reg(priv, XCAN_SR_OFFSET);
 
 	if (isr & XCAN_IXR_BSOFF_MASK) {
 		priv->can.state = CAN_STATE_BUS_OFF;
@@ -563,28 +700,10 @@ static void xcan_err_interrupt(struct net_device *ndev, u32 isr)
 		can_bus_off(ndev);
 		if (skb)
 			cf->can_id |= CAN_ERR_BUSOFF;
-	} else if ((status & XCAN_SR_ESTAT_MASK) == XCAN_SR_ESTAT_MASK) {
+	} else {
-		priv->can.state = CAN_STATE_ERROR_PASSIVE;
+		enum can_state new_state = xcan_current_error_state(ndev);
-		priv->can.can_stats.error_passive++;
+
-		if (skb) {
+		xcan_set_error_state(ndev, new_state, skb ? cf : NULL);
-			cf->can_id |= CAN_ERR_CRTL;
-			cf->data[1] = (rxerr > 127) ?
-					CAN_ERR_CRTL_RX_PASSIVE :
-					CAN_ERR_CRTL_TX_PASSIVE;
-			cf->data[6] = txerr;
-			cf->data[7] = rxerr;
-		}
-	} else if (status & XCAN_SR_ERRWRN_MASK) {
-		priv->can.state = CAN_STATE_ERROR_WARNING;
-		priv->can.can_stats.error_warning++;
-		if (skb) {
-			cf->can_id |= CAN_ERR_CRTL;
-			cf->data[1] |= (txerr > rxerr) ?
-					CAN_ERR_CRTL_TX_WARNING :
-					CAN_ERR_CRTL_RX_WARNING;
-			cf->data[6] = txerr;
-			cf->data[7] = rxerr;
-		}
 	}
 
 	/* Check for Arbitration lost interrupt */
@@ -600,7 +719,6 @@ static void xcan_err_interrupt(struct net_device *ndev, u32 isr)
 	if (isr & XCAN_IXR_RXOFLW_MASK) {
 		stats->rx_over_errors++;
 		stats->rx_errors++;
-		priv->write_reg(priv, XCAN_SRR_OFFSET, XCAN_SRR_RESET_MASK);
 		if (skb) {
 			cf->can_id |= CAN_ERR_CRTL;
 			cf->data[1] |= CAN_ERR_CRTL_RX_OVERFLOW;
@@ -709,26 +827,20 @@ static int xcan_rx_poll(struct napi_struct *napi, int quota)
 
 	isr = priv->read_reg(priv, XCAN_ISR_OFFSET);
 	while ((isr & XCAN_IXR_RXNEMP_MASK) && (work_done < quota)) {
-		if (isr & XCAN_IXR_RXOK_MASK) {
-			priv->write_reg(priv, XCAN_ICR_OFFSET,
-				XCAN_IXR_RXOK_MASK);
 		work_done += xcan_rx(ndev);
-		} else {
-			priv->write_reg(priv, XCAN_ICR_OFFSET,
-				XCAN_IXR_RXNEMP_MASK);
-			break;
-		}
 		priv->write_reg(priv, XCAN_ICR_OFFSET, XCAN_IXR_RXNEMP_MASK);
 		isr = priv->read_reg(priv, XCAN_ISR_OFFSET);
 	}
 
-	if (work_done)
+	if (work_done) {
 		can_led_event(ndev, CAN_LED_EVENT_RX);
+		xcan_update_error_state_after_rxtx(ndev);
+	}
 
 	if (work_done < quota) {
 		napi_complete_done(napi, work_done);
 		ier = priv->read_reg(priv, XCAN_IER_OFFSET);
-		ier |= (XCAN_IXR_RXOK_MASK | XCAN_IXR_RXNEMP_MASK);
+		ier |= XCAN_IXR_RXNEMP_MASK;
 		priv->write_reg(priv, XCAN_IER_OFFSET, ier);
 	}
 	return work_done;
@@ -743,18 +855,71 @@ static void xcan_tx_interrupt(struct net_device *ndev, u32 isr)
 {
 	struct xcan_priv *priv = netdev_priv(ndev);
 	struct net_device_stats *stats = &ndev->stats;
+	unsigned int frames_in_fifo;
+	int frames_sent = 1; /* TXOK => at least 1 frame was sent */
+	unsigned long flags;
+	int retries = 0;
 
-	while ((priv->tx_head - priv->tx_tail > 0) &&
+	/* Synchronize with xmit as we need to know the exact number
-			(isr & XCAN_IXR_TXOK_MASK)) {
+	 * of frames in the FIFO to stay in sync due to the TXFEMP
+	 * handling.
+	 * This also prevents a race between netif_wake_queue() and
+	 * netif_stop_queue().
+	 */
+	spin_lock_irqsave(&priv->tx_lock, flags);
+
+	frames_in_fifo = priv->tx_head - priv->tx_tail;
+
+	if (WARN_ON_ONCE(frames_in_fifo == 0)) {
+		/* clear TXOK anyway to avoid getting back here */
 		priv->write_reg(priv, XCAN_ICR_OFFSET, XCAN_IXR_TXOK_MASK);
+		spin_unlock_irqrestore(&priv->tx_lock, flags);
+		return;
+	}
+
+	/* Check if 2 frames were sent (TXOK only means that at least 1
+	 * frame was sent).
+	 */
+	if (frames_in_fifo > 1) {
+		WARN_ON(frames_in_fifo > priv->tx_max);
+
+		/* Synchronize TXOK and isr so that after the loop:
+		 * (1) isr variable is up-to-date at least up to TXOK clear
+		 *     time. This avoids us clearing a TXOK of a second frame
+		 *     but not noticing that the FIFO is now empty and thus
+		 *     marking only a single frame as sent.
+		 * (2) No TXOK is left. Having one could mean leaving a
+		 *     stray TXOK as we might process the associated frame
+		 *     via TXFEMP handling as we read TXFEMP *after* TXOK
+		 *     clear to satisfy (1).
+		 */
+		while ((isr & XCAN_IXR_TXOK_MASK) && !WARN_ON(++retries == 100)) {
+			priv->write_reg(priv, XCAN_ICR_OFFSET, XCAN_IXR_TXOK_MASK);
+			isr = priv->read_reg(priv, XCAN_ISR_OFFSET);
+		}
+
+		if (isr & XCAN_IXR_TXFEMP_MASK) {
+			/* nothing in FIFO anymore */
+			frames_sent = frames_in_fifo;
+		}
+	} else {
+		/* single frame in fifo, just clear TXOK */
+		priv->write_reg(priv, XCAN_ICR_OFFSET, XCAN_IXR_TXOK_MASK);
+	}
+
+	while (frames_sent--) {
 		can_get_echo_skb(ndev, priv->tx_tail %
 					priv->tx_max);
 		priv->tx_tail++;
 		stats->tx_packets++;
-		isr = priv->read_reg(priv, XCAN_ISR_OFFSET);
 	}
-	can_led_event(ndev, CAN_LED_EVENT_TX);
+
 	netif_wake_queue(ndev);
+
+	spin_unlock_irqrestore(&priv->tx_lock, flags);
+
+	can_led_event(ndev, CAN_LED_EVENT_TX);
+	xcan_update_error_state_after_rxtx(ndev);
 }
 
 /**
@@ -773,6 +938,7 @@ static irqreturn_t xcan_interrupt(int irq, void *dev_id)
 	struct net_device *ndev = (struct net_device *)dev_id;
 	struct xcan_priv *priv = netdev_priv(ndev);
 	u32 isr, ier;
+	u32 isr_errors;
 
 	/* Get the interrupt status from Xilinx CAN */
 	isr = priv->read_reg(priv, XCAN_ISR_OFFSET);
@@ -791,18 +957,17 @@ static irqreturn_t xcan_interrupt(int irq, void *dev_id)
 		xcan_tx_interrupt(ndev, isr);
 
 	/* Check for the type of error interrupt and Processing it */
-	if (isr & (XCAN_IXR_ERROR_MASK | XCAN_IXR_RXOFLW_MASK |
+	isr_errors = isr & (XCAN_IXR_ERROR_MASK | XCAN_IXR_RXOFLW_MASK |
-			XCAN_IXR_BSOFF_MASK | XCAN_IXR_ARBLST_MASK)) {
+			    XCAN_IXR_BSOFF_MASK | XCAN_IXR_ARBLST_MASK);
-		priv->write_reg(priv, XCAN_ICR_OFFSET, (XCAN_IXR_ERROR_MASK |
+	if (isr_errors) {
-				XCAN_IXR_RXOFLW_MASK | XCAN_IXR_BSOFF_MASK |
+		priv->write_reg(priv, XCAN_ICR_OFFSET, isr_errors);
-				XCAN_IXR_ARBLST_MASK));
 		xcan_err_interrupt(ndev, isr);
 	}
 
 	/* Check for the type of receive interrupt and Processing it */
-	if (isr & (XCAN_IXR_RXNEMP_MASK | XCAN_IXR_RXOK_MASK)) {
+	if (isr & XCAN_IXR_RXNEMP_MASK) {
 		ier = priv->read_reg(priv, XCAN_IER_OFFSET);
-		ier &= ~(XCAN_IXR_RXNEMP_MASK | XCAN_IXR_RXOK_MASK);
+		ier &= ~XCAN_IXR_RXNEMP_MASK;
 		priv->write_reg(priv, XCAN_IER_OFFSET, ier);
 		napi_schedule(&priv->napi);
 	}
@@ -819,13 +984,9 @@ static irqreturn_t xcan_interrupt(int irq, void *dev_id)
 static void xcan_chip_stop(struct net_device *ndev)
 {
 	struct xcan_priv *priv = netdev_priv(ndev);
-	u32 ier;
 
 	/* Disable interrupts and leave the can in configuration mode */
-	ier = priv->read_reg(priv, XCAN_IER_OFFSET);
+	set_reset_mode(ndev);
-	ier &= ~XCAN_INTR_ALL;
-	priv->write_reg(priv, XCAN_IER_OFFSET, ier);
-	priv->write_reg(priv, XCAN_SRR_OFFSET, XCAN_SRR_RESET_MASK);
 	priv->can.state = CAN_STATE_STOPPED;
 }
 
@@ -958,10 +1119,15 @@ static const struct net_device_ops xcan_netdev_ops = {
  */
 static int __maybe_unused xcan_suspend(struct device *dev)
 {
-	if (!device_may_wakeup(dev))
+	struct net_device *ndev = dev_get_drvdata(dev);
-		return pm_runtime_force_suspend(dev);
 
-	return 0;
+	if (netif_running(ndev)) {
+		netif_stop_queue(ndev);
+		netif_device_detach(ndev);
+		xcan_chip_stop(ndev);
+	}
+
+	return pm_runtime_force_suspend(dev);
 }
 
 /**
@@ -973,11 +1139,27 @@ static int __maybe_unused xcan_suspend(struct device *dev)
  */
 static int __maybe_unused xcan_resume(struct device *dev)
 {
-	if (!device_may_wakeup(dev))
+	struct net_device *ndev = dev_get_drvdata(dev);
-		return pm_runtime_force_resume(dev);
+	int ret;
+
+	ret = pm_runtime_force_resume(dev);
+	if (ret) {
+		dev_err(dev, "pm_runtime_force_resume failed on resume\n");
+		return ret;
+	}
+
+	if (netif_running(ndev)) {
+		ret = xcan_chip_start(ndev);
+		if (ret) {
+			dev_err(dev, "xcan_chip_start failed on resume\n");
+			return ret;
+		}
+
+		netif_device_attach(ndev);
+		netif_start_queue(ndev);
+	}
 
 	return 0;
-
 }
 
 /**
@@ -992,14 +1174,6 @@ static int __maybe_unused xcan_runtime_suspend(struct device *dev)
 	struct net_device *ndev = dev_get_drvdata(dev);
 	struct xcan_priv *priv = netdev_priv(ndev);
 
-	if (netif_running(ndev)) {
-		netif_stop_queue(ndev);
-		netif_device_detach(ndev);
-	}
-
-	priv->write_reg(priv, XCAN_MSR_OFFSET, XCAN_MSR_SLEEP_MASK);
-	priv->can.state = CAN_STATE_SLEEPING;
-
 	clk_disable_unprepare(priv->bus_clk);
 	clk_disable_unprepare(priv->can_clk);
 
@@ -1018,7 +1192,6 @@ static int __maybe_unused xcan_runtime_resume(struct device *dev)
 	struct net_device *ndev = dev_get_drvdata(dev);
 	struct xcan_priv *priv = netdev_priv(ndev);
 	int ret;
-	u32 isr, status;
 
 	ret = clk_prepare_enable(priv->bus_clk);
 	if (ret) {
@@ -1032,27 +1205,6 @@ static int __maybe_unused xcan_runtime_resume(struct device *dev)
 		return ret;
 	}
 
-	priv->write_reg(priv, XCAN_SRR_OFFSET, XCAN_SRR_RESET_MASK);
-	isr = priv->read_reg(priv, XCAN_ISR_OFFSET);
-	status = priv->read_reg(priv, XCAN_SR_OFFSET);
-
-	if (netif_running(ndev)) {
-		if (isr & XCAN_IXR_BSOFF_MASK) {
-			priv->can.state = CAN_STATE_BUS_OFF;
-			priv->write_reg(priv, XCAN_SRR_OFFSET,
-					XCAN_SRR_RESET_MASK);
-		} else if ((status & XCAN_SR_ESTAT_MASK) ==
-					XCAN_SR_ESTAT_MASK) {
-			priv->can.state = CAN_STATE_ERROR_PASSIVE;
-		} else if (status & XCAN_SR_ERRWRN_MASK) {
-			priv->can.state = CAN_STATE_ERROR_WARNING;
-		} else {
-			priv->can.state = CAN_STATE_ERROR_ACTIVE;
-		}
-		netif_device_attach(ndev);
-		netif_start_queue(ndev);
-	}
-
 	return 0;
 }
 
@@ -1061,6 +1213,18 @@ static const struct dev_pm_ops xcan_dev_pm_ops = {
 	SET_RUNTIME_PM_OPS(xcan_runtime_suspend, xcan_runtime_resume, NULL)
 };
 
+static const struct xcan_devtype_data xcan_zynq_data = {
+	.caps = XCAN_CAP_WATERMARK,
+};
+
+/* Match table for OF platform binding */
+static const struct of_device_id xcan_of_match[] = {
+	{ .compatible = "xlnx,zynq-can-1.0", .data = &xcan_zynq_data },
+	{ .compatible = "xlnx,axi-can-1.00.a", },
+	{ /* end of list */ },
+};
+MODULE_DEVICE_TABLE(of, xcan_of_match);
+
 /**
  * xcan_probe - Platform registration call
  * @pdev:	Handle to the platform device structure
@@ -1075,8 +1239,10 @@ static int xcan_probe(struct platform_device *pdev)
 	struct resource *res; /* IO mem resources */
 	struct net_device *ndev;
 	struct xcan_priv *priv;
+	const struct of_device_id *of_id;
+	int caps = 0;
 	void __iomem *addr;
-	int ret, rx_max, tx_max;
+	int ret, rx_max, tx_max, tx_fifo_depth;
 
 	/* Get the virtual base address for the device */
 	res = platform_get_resource(pdev, IORESOURCE_MEM, 0);
@@ -1086,7 +1252,8 @@ static int xcan_probe(struct platform_device *pdev)
 		goto err;
 	}
 
-	ret = of_property_read_u32(pdev->dev.of_node, "tx-fifo-depth", &tx_max);
+	ret = of_property_read_u32(pdev->dev.of_node, "tx-fifo-depth",
+				   &tx_fifo_depth);
 	if (ret < 0)
 		goto err;
 
@@ -1094,6 +1261,30 @@ static int xcan_probe(struct platform_device *pdev)
 	if (ret < 0)
 		goto err;
 
+	of_id = of_match_device(xcan_of_match, &pdev->dev);
+	if (of_id) {
+		const struct xcan_devtype_data *devtype_data = of_id->data;
+
+		if (devtype_data)
+			caps = devtype_data->caps;
+	}
+
+	/* There is no way to directly figure out how many frames have been
+	 * sent when the TXOK interrupt is processed. If watermark programming
+	 * is supported, we can have 2 frames in the FIFO and use TXFEMP
+	 * to determine if 1 or 2 frames have been sent.
+	 * Theoretically we should be able to use TXFWMEMP to determine up
+	 * to 3 frames, but it seems that after putting a second frame in the
+	 * FIFO, with watermark at 2 frames, it can happen that TXFWMEMP (less
+	 * than 2 frames in FIFO) is set anyway with no TXOK (a frame was
+	 * sent), which is not a sensible state - possibly TXFWMEMP is not
+	 * completely synchronized with the rest of the bits?
+	 */
+	if (caps & XCAN_CAP_WATERMARK)
+		tx_max = min(tx_fifo_depth, 2);
+	else
+		tx_max = 1;
+
 	/* Create a CAN device instance */
 	ndev = alloc_candev(sizeof(struct xcan_priv), tx_max);
 	if (!ndev)
@@ -1108,6 +1299,7 @@ static int xcan_probe(struct platform_device *pdev)
 					CAN_CTRLMODE_BERR_REPORTING;
 	priv->reg_base = addr;
 	priv->tx_max = tx_max;
+	spin_lock_init(&priv->tx_lock);
 
 	/* Get IRQ for the device */
 	ndev->irq = platform_get_irq(pdev, 0);
@@ -1172,9 +1364,9 @@ static int xcan_probe(struct platform_device *pdev)
 
 	pm_runtime_put(&pdev->dev);
 
-	netdev_dbg(ndev, "reg_base=0x%p irq=%d clock=%d, tx fifo depth:%d\n",
+	netdev_dbg(ndev, "reg_base=0x%p irq=%d clock=%d, tx fifo depth: actual %d, using %d\n",
 			priv->reg_base, ndev->irq, priv->can.clock.freq,
-			priv->tx_max);
+			tx_fifo_depth, priv->tx_max);
 
 	return 0;
 
@@ -1208,14 +1400,6 @@ static int xcan_remove(struct platform_device *pdev)
 	return 0;
 }
 
-/* Match table for OF platform binding */
-static const struct of_device_id xcan_of_match[] = {
-	{ .compatible = "xlnx,zynq-can-1.0", },
-	{ .compatible = "xlnx,axi-can-1.00.a", },
-	{ /* end of list */ },
-};
-MODULE_DEVICE_TABLE(of, xcan_of_match);
-
 static struct platform_driver xcan_driver = {
 	.probe = xcan_probe,
 	.remove	= xcan_remove,

drivers/net/dsa/mv88e6xxx/chip.c

@@ -343,6 +343,7 @@ static const struct irq_domain_ops mv88e6xxx_g1_irq_domain_ops = {
 	.xlate	= irq_domain_xlate_twocell,
 };
 
+/* To be called with reg_lock held */
 static void mv88e6xxx_g1_irq_free_common(struct mv88e6xxx_chip *chip)
 {
 	int irq, virq;
@@ -362,9 +363,15 @@ static void mv88e6xxx_g1_irq_free_common(struct mv88e6xxx_chip *chip)
 
 static void mv88e6xxx_g1_irq_free(struct mv88e6xxx_chip *chip)
 {
-	mv88e6xxx_g1_irq_free_common(chip);
+	/*
-
+	 * free_irq must be called without reg_lock taken because the irq
+	 * handler takes this lock, too.
+	 */
 	free_irq(chip->irq, chip);
+
+	mutex_lock(&chip->reg_lock);
+	mv88e6xxx_g1_irq_free_common(chip);
+	mutex_unlock(&chip->reg_lock);
 }
 
 static int mv88e6xxx_g1_irq_setup_common(struct mv88e6xxx_chip *chip)
@@ -469,10 +476,12 @@ static int mv88e6xxx_irq_poll_setup(struct mv88e6xxx_chip *chip)
 
 static void mv88e6xxx_irq_poll_free(struct mv88e6xxx_chip *chip)
 {
-	mv88e6xxx_g1_irq_free_common(chip);
-
 	kthread_cancel_delayed_work_sync(&chip->irq_poll_work);
 	kthread_destroy_worker(chip->kworker);
+
+	mutex_lock(&chip->reg_lock);
+	mv88e6xxx_g1_irq_free_common(chip);
+	mutex_unlock(&chip->reg_lock);
 }
 
 int mv88e6xxx_wait(struct mv88e6xxx_chip *chip, int addr, int reg, u16 mask)
@@ -4523,12 +4532,10 @@ static int mv88e6xxx_probe(struct mdio_device *mdiodev)
 	if (chip->info->g2_irqs > 0)
 		mv88e6xxx_g2_irq_free(chip);
 out_g1_irq:
-	mutex_lock(&chip->reg_lock);
 	if (chip->irq > 0)
 		mv88e6xxx_g1_irq_free(chip);
 	else
 		mv88e6xxx_irq_poll_free(chip);
-	mutex_unlock(&chip->reg_lock);
 out:
 	if (pdata)
 		dev_put(pdata->netdev);
@@ -4556,12 +4563,10 @@ static void mv88e6xxx_remove(struct mdio_device *mdiodev)
 	if (chip->info->g2_irqs > 0)
 		mv88e6xxx_g2_irq_free(chip);
 
-	mutex_lock(&chip->reg_lock);
 	if (chip->irq > 0)
 		mv88e6xxx_g1_irq_free(chip);
 	else
 		mv88e6xxx_irq_poll_free(chip);
-	mutex_unlock(&chip->reg_lock);
 }
 
 static const struct of_device_id mv88e6xxx_of_match[] = {

drivers/net/ethernet/3com/Kconfig

@@ -32,7 +32,7 @@ config EL3
 
 config 3C515
 	tristate "3c515 ISA \"Fast EtherLink\""
-	depends on ISA && ISA_DMA_API
+	depends on ISA && ISA_DMA_API && !PPC32
 	---help---
 	  If you have a 3Com ISA EtherLink XL "Corkscrew" 3c515 Fast Ethernet
 	  network card, say Y here.

drivers/net/ethernet/amd/Kconfig

@@ -44,7 +44,7 @@ config AMD8111_ETH
 
 config LANCE
 	tristate "AMD LANCE and PCnet (AT1500 and NE2100) support"
-	depends on ISA && ISA_DMA_API && !ARM
+	depends on ISA && ISA_DMA_API && !ARM && !PPC32
 	---help---
 	  If you have a network (Ethernet) card of this type, say Y here.
 	  Some LinkSys cards are of this type.
@@ -138,7 +138,7 @@ config PCMCIA_NMCLAN
 
 config NI65
 	tristate "NI6510 support"
-	depends on ISA && ISA_DMA_API && !ARM
+	depends on ISA && ISA_DMA_API && !ARM && !PPC32
 	---help---
 	  If you have a network (Ethernet) card of this type, say Y here.
 

drivers/net/ethernet/atheros/atl1c/atl1c_main.c

@@ -1686,6 +1686,7 @@ static struct sk_buff *atl1c_alloc_skb(struct atl1c_adapter *adapter)
 	skb = build_skb(page_address(page) + adapter->rx_page_offset,
 			adapter->rx_frag_size);
 	if (likely(skb)) {
+		skb_reserve(skb, NET_SKB_PAD);
 		adapter->rx_page_offset += adapter->rx_frag_size;
 		if (adapter->rx_page_offset >= PAGE_SIZE)
 			adapter->rx_page = NULL;

drivers/net/ethernet/broadcom/bnx2x/bnx2x_ethtool.c

@@ -3388,14 +3388,18 @@ static int bnx2x_set_rss_flags(struct bnx2x *bp, struct ethtool_rxnfc *info)
 			DP(BNX2X_MSG_ETHTOOL,
 			   "rss re-configured, UDP 4-tupple %s\n",
 			   udp_rss_requested ? "enabled" : "disabled");
-			return bnx2x_rss(bp, &bp->rss_conf_obj, false, true);
+			if (bp->state == BNX2X_STATE_OPEN)
+				return bnx2x_rss(bp, &bp->rss_conf_obj, false,
+						 true);
 		} else if ((info->flow_type == UDP_V6_FLOW) &&
 			   (bp->rss_conf_obj.udp_rss_v6 != udp_rss_requested)) {
 			bp->rss_conf_obj.udp_rss_v6 = udp_rss_requested;
 			DP(BNX2X_MSG_ETHTOOL,
 			   "rss re-configured, UDP 4-tupple %s\n",
 			   udp_rss_requested ? "enabled" : "disabled");
-			return bnx2x_rss(bp, &bp->rss_conf_obj, false, true);
+			if (bp->state == BNX2X_STATE_OPEN)
+				return bnx2x_rss(bp, &bp->rss_conf_obj, false,
+						 true);
 		}
 		return 0;
 
@@ -3509,7 +3513,10 @@ static int bnx2x_set_rxfh(struct net_device *dev, const u32 *indir,
 		bp->rss_conf_obj.ind_table[i] = indir[i] + bp->fp->cl_id;
 	}
 
+	if (bp->state == BNX2X_STATE_OPEN)
 		return bnx2x_config_rss_eth(bp, false);
+
+	return 0;
 }
 
 /**

drivers/net/ethernet/cirrus/Kconfig

@@ -19,6 +19,7 @@ if NET_VENDOR_CIRRUS
 config CS89x0
 	tristate "CS89x0 support"
 	depends on ISA || EISA || ARM
+	depends on !PPC32
 	---help---
 	  Support for CS89x0 chipset based Ethernet cards. If you have a
 	  network (Ethernet) card of this type, say Y and read the file

drivers/net/ethernet/huawei/hinic/hinic_tx.c

@@ -229,6 +229,7 @@ netdev_tx_t hinic_xmit_frame(struct sk_buff *skb, struct net_device *netdev)
 		txq->txq_stats.tx_busy++;
 		u64_stats_update_end(&txq->txq_stats.syncp);
 		err = NETDEV_TX_BUSY;
+		wqe_size = 0;
 		goto flush_skbs;
 	}
 

drivers/net/ethernet/mellanox/mlx4/resource_tracker.c

@@ -2958,7 +2958,7 @@ int mlx4_RST2INIT_QP_wrapper(struct mlx4_dev *dev, int slave,
 	u32 srqn = qp_get_srqn(qpc) & 0xffffff;
 	int use_srq = (qp_get_srqn(qpc) >> 24) & 1;
 	struct res_srq *srq;
-	int local_qpn = be32_to_cpu(qpc->local_qpn) & 0xffffff;
+	int local_qpn = vhcr->in_modifier & 0xffffff;
 
 	err = adjust_qp_sched_queue(dev, slave, qpc, inbox);
 	if (err)

drivers/net/ethernet/mellanox/mlx5/core/alloc.c

@@ -123,7 +123,7 @@ int mlx5_frag_buf_alloc_node(struct mlx5_core_dev *dev, int size,
 	int i;
 
 	buf->size = size;
-	buf->npages = 1 << get_order(size);
+	buf->npages = DIV_ROUND_UP(size, PAGE_SIZE);
 	buf->page_shift = PAGE_SHIFT;
 	buf->frags = kcalloc(buf->npages, sizeof(struct mlx5_buf_list),
 			     GFP_KERNEL);

drivers/net/ethernet/mellanox/mlx5/core/en_arfs.c

@@ -381,14 +381,14 @@ static void arfs_may_expire_flow(struct mlx5e_priv *priv)
 	HLIST_HEAD(del_list);
 	spin_lock_bh(&priv->fs.arfs.arfs_lock);
 	mlx5e_for_each_arfs_rule(arfs_rule, htmp, priv->fs.arfs.arfs_tables, i, j) {
-		if (quota++ > MLX5E_ARFS_EXPIRY_QUOTA)
-			break;
 		if (!work_pending(&arfs_rule->arfs_work) &&
 		    rps_may_expire_flow(priv->netdev,
 					arfs_rule->rxq, arfs_rule->flow_id,
 					arfs_rule->filter_id)) {
 			hlist_del_init(&arfs_rule->hlist);
 			hlist_add_head(&arfs_rule->hlist, &del_list);
+			if (quota++ > MLX5E_ARFS_EXPIRY_QUOTA)
+				break;
 		}
 	}
 	spin_unlock_bh(&priv->fs.arfs.arfs_lock);
@@ -711,6 +711,9 @@ int mlx5e_rx_flow_steer(struct net_device *dev, const struct sk_buff *skb,
 	    skb->protocol != htons(ETH_P_IPV6))
 		return -EPROTONOSUPPORT;
 
+	if (skb->encapsulation)
+		return -EPROTONOSUPPORT;
+
 	arfs_t = arfs_get_table(arfs, arfs_get_ip_proto(skb), skb->protocol);
 	if (!arfs_t)
 		return -EPROTONOSUPPORT;

drivers/net/ethernet/mellanox/mlx5/core/en_dcbnl.c

@@ -275,7 +275,8 @@ int mlx5e_dcbnl_ieee_setets_core(struct mlx5e_priv *priv, struct ieee_ets *ets)
 }
 
 static int mlx5e_dbcnl_validate_ets(struct net_device *netdev,
-				    struct ieee_ets *ets)
+				    struct ieee_ets *ets,
+				    bool zero_sum_allowed)
 {
 	bool have_ets_tc = false;
 	int bw_sum = 0;
@@ -300,6 +301,7 @@ static int mlx5e_dbcnl_validate_ets(struct net_device *netdev,
 	}
 
 	if (have_ets_tc && bw_sum != 100) {
+		if (bw_sum || (!bw_sum && !zero_sum_allowed))
 			netdev_err(netdev,
 				   "Failed to validate ETS: BW sum is illegal\n");
 		return -EINVAL;
@@ -316,7 +318,7 @@ static int mlx5e_dcbnl_ieee_setets(struct net_device *netdev,
 	if (!MLX5_CAP_GEN(priv->mdev, ets))
 		return -EOPNOTSUPP;
 
-	err = mlx5e_dbcnl_validate_ets(netdev, ets);
+	err = mlx5e_dbcnl_validate_ets(netdev, ets, false);
 	if (err)
 		return err;
 
@@ -642,12 +644,9 @@ static u8 mlx5e_dcbnl_setall(struct net_device *netdev)
 			  ets.prio_tc[i]);
 	}
 
-	err = mlx5e_dbcnl_validate_ets(netdev, &ets);
+	err = mlx5e_dbcnl_validate_ets(netdev, &ets, true);
-	if (err) {
+	if (err)
-		netdev_err(netdev,
-			   "%s, Failed to validate ETS: %d\n", __func__, err);
 		goto out;
-	}
 
 	err = mlx5e_dcbnl_ieee_setets_core(priv, &ets);
 	if (err) {

drivers/net/ethernet/mellanox/mlx5/core/en_tc.c

@@ -2004,6 +2004,10 @@ static bool actions_match_supported(struct mlx5e_priv *priv,
 	else
 		actions = flow->nic_attr->action;
 
+	if (flow->flags & MLX5E_TC_FLOW_EGRESS &&
+	    !(actions & MLX5_FLOW_CONTEXT_ACTION_DECAP))
+		return false;
+
 	if (actions & MLX5_FLOW_CONTEXT_ACTION_MOD_HDR)
 		return modify_header_match_supported(&parse_attr->spec, exts);
 

drivers/net/ethernet/mellanox/mlx5/core/eswitch.c

@@ -2216,6 +2216,6 @@ int mlx5_eswitch_get_vport_stats(struct mlx5_eswitch *esw,
 
 u8 mlx5_eswitch_mode(struct mlx5_eswitch *esw)
 {
-	return esw->mode;
+	return ESW_ALLOWED(esw) ? esw->mode : SRIOV_NONE;
 }
 EXPORT_SYMBOL_GPL(mlx5_eswitch_mode);

drivers/net/ethernet/mellanox/mlx5/core/fs_core.c

@@ -1889,7 +1889,7 @@ mlx5_add_flow_rules(struct mlx5_flow_table *ft,
 	if (flow_act->action == MLX5_FLOW_CONTEXT_ACTION_FWD_NEXT_PRIO) {
 		if (!fwd_next_prio_supported(ft))
 			return ERR_PTR(-EOPNOTSUPP);
-		if (dest)
+		if (dest_num)
 			return ERR_PTR(-EINVAL);
 		mutex_lock(&root->chain_lock);
 		next_ft = find_next_chained_ft(prio);

drivers/net/ethernet/mellanox/mlx5/core/lib/clock.c

@@ -488,6 +488,7 @@ void mlx5_pps_event(struct mlx5_core_dev *mdev,
 void mlx5_init_clock(struct mlx5_core_dev *mdev)
 {
 	struct mlx5_clock *clock = &mdev->clock;
+	u64 overflow_cycles;
 	u64 ns;
 	u64 frac = 0;
 	u32 dev_freq;
@@ -511,10 +512,17 @@ void mlx5_init_clock(struct mlx5_core_dev *mdev)
 
 	/* Calculate period in seconds to call the overflow watchdog - to make
 	 * sure counter is checked at least once every wrap around.
+	 * The period is calculated as the minimum between max HW cycles count
+	 * (The clock source mask) and max amount of cycles that can be
+	 * multiplied by clock multiplier where the result doesn't exceed
+	 * 64bits.
 	 */
-	ns = cyclecounter_cyc2ns(&clock->cycles, clock->cycles.mask,
+	overflow_cycles = div64_u64(~0ULL >> 1, clock->cycles.mult);
+	overflow_cycles = min(overflow_cycles, clock->cycles.mask >> 1);
+
+	ns = cyclecounter_cyc2ns(&clock->cycles, overflow_cycles,
 				 frac, &frac);
-	do_div(ns, NSEC_PER_SEC / 2 / HZ);
+	do_div(ns, NSEC_PER_SEC / HZ);
 	clock->overflow_period = ns;
 
 	mdev->clock_info_page = alloc_page(GFP_KERNEL);

drivers/net/ethernet/mellanox/mlx5/core/wq.c

@@ -113,34 +113,44 @@ int mlx5_wq_cyc_create(struct mlx5_core_dev *mdev, struct mlx5_wq_param *param,
 	return err;
 }
 
-static void mlx5e_qp_set_frag_buf(struct mlx5_frag_buf *buf,
+static void mlx5_qp_set_frag_buf(struct mlx5_frag_buf *buf,
 				 struct mlx5_wq_qp *qp)
 {
+	struct mlx5_frag_buf_ctrl *sq_fbc;
 	struct mlx5_frag_buf *rqb, *sqb;
 
 	rqb  = &qp->rq.fbc.frag_buf;
 	*rqb = *buf;
 	rqb->size   = mlx5_wq_cyc_get_byte_size(&qp->rq);
-	rqb->npages = 1 << get_order(rqb->size);
+	rqb->npages = DIV_ROUND_UP(rqb->size, PAGE_SIZE);
 
-	sqb = &qp->sq.fbc.frag_buf;
+	sq_fbc = &qp->sq.fbc;
+	sqb    = &sq_fbc->frag_buf;
 	*sqb   = *buf;
-	sqb->size   = mlx5_wq_cyc_get_byte_size(&qp->rq);
+	sqb->size   = mlx5_wq_cyc_get_byte_size(&qp->sq);
-	sqb->npages = 1 << get_order(sqb->size);
+	sqb->npages = DIV_ROUND_UP(sqb->size, PAGE_SIZE);
 	sqb->frags += rqb->npages; /* first part is for the rq */
+	if (sq_fbc->strides_offset)
+		sqb->frags--;
 }
 
 int mlx5_wq_qp_create(struct mlx5_core_dev *mdev, struct mlx5_wq_param *param,
 		      void *qpc, struct mlx5_wq_qp *wq,
 		      struct mlx5_wq_ctrl *wq_ctrl)
 {
+	u32 sq_strides_offset;
 	int err;
 
 	mlx5_fill_fbc(MLX5_GET(qpc, qpc, log_rq_stride) + 4,
 		      MLX5_GET(qpc, qpc, log_rq_size),
 		      &wq->rq.fbc);
-	mlx5_fill_fbc(ilog2(MLX5_SEND_WQE_BB),
+
+	sq_strides_offset =
+		((wq->rq.fbc.frag_sz_m1 + 1) % PAGE_SIZE) / MLX5_SEND_WQE_BB;
+
+	mlx5_fill_fbc_offset(ilog2(MLX5_SEND_WQE_BB),
 			     MLX5_GET(qpc, qpc, log_sq_size),
+			     sq_strides_offset,
 			     &wq->sq.fbc);
 
 	err = mlx5_db_alloc_node(mdev, &wq_ctrl->db, param->db_numa_node);
@@ -156,7 +166,7 @@ int mlx5_wq_qp_create(struct mlx5_core_dev *mdev, struct mlx5_wq_param *param,
 		goto err_db_free;
 	}
 
-	mlx5e_qp_set_frag_buf(&wq_ctrl->buf, wq);
+	mlx5_qp_set_frag_buf(&wq_ctrl->buf, wq);
 
 	wq->rq.db  = &wq_ctrl->db.db[MLX5_RCV_DBR];
 	wq->sq.db  = &wq_ctrl->db.db[MLX5_SND_DBR];

drivers/net/ethernet/netronome/nfp/flower/tunnel_conf.c

@@ -317,7 +317,7 @@ nfp_tun_write_neigh(struct net_device *netdev, struct nfp_app *app,
 	payload.dst_ipv4 = flow->daddr;
 
 	/* If entry has expired send dst IP with all other fields 0. */
-	if (!(neigh->nud_state & NUD_VALID)) {
+	if (!(neigh->nud_state & NUD_VALID) || neigh->dead) {
 		nfp_tun_del_route_from_cache(app, payload.dst_ipv4);
 		/* Trigger ARP to verify invalid neighbour state. */
 		neigh_event_send(neigh, NULL);

drivers/net/ethernet/qlogic/qed/qed_l2.c

@@ -665,7 +665,7 @@ qed_sp_update_mcast_bin(struct qed_hwfn *p_hwfn,
 
 	p_ramrod->common.update_approx_mcast_flg = 1;
 	for (i = 0; i < ETH_MULTICAST_MAC_BINS_IN_REGS; i++) {
-		u32 *p_bins = (u32 *)p_params->bins;
+		u32 *p_bins = p_params->bins;
 
 		p_ramrod->approx_mcast.bins[i] = cpu_to_le32(p_bins[i]);
 	}
@@ -1476,8 +1476,8 @@ qed_sp_eth_filter_mcast(struct qed_hwfn *p_hwfn,
 			enum spq_mode comp_mode,
 			struct qed_spq_comp_cb *p_comp_data)
 {
-	unsigned long bins[ETH_MULTICAST_MAC_BINS_IN_REGS];
 	struct vport_update_ramrod_data *p_ramrod = NULL;
+	u32 bins[ETH_MULTICAST_MAC_BINS_IN_REGS];
 	struct qed_spq_entry *p_ent = NULL;
 	struct qed_sp_init_data init_data;
 	u8 abs_vport_id = 0;
@@ -1513,26 +1513,25 @@ qed_sp_eth_filter_mcast(struct qed_hwfn *p_hwfn,
 	/* explicitly clear out the entire vector */
 	memset(&p_ramrod->approx_mcast.bins, 0,
 	       sizeof(p_ramrod->approx_mcast.bins));
-	memset(bins, 0, sizeof(unsigned long) *
+	memset(bins, 0, sizeof(bins));
-	       ETH_MULTICAST_MAC_BINS_IN_REGS);
 	/* filter ADD op is explicit set op and it removes
 	 *  any existing filters for the vport
 	 */
 	if (p_filter_cmd->opcode == QED_FILTER_ADD) {
 		for (i = 0; i < p_filter_cmd->num_mc_addrs; i++) {
-			u32 bit;
+			u32 bit, nbits;
 
 			bit = qed_mcast_bin_from_mac(p_filter_cmd->mac[i]);
-			__set_bit(bit, bins);
+			nbits = sizeof(u32) * BITS_PER_BYTE;
+			bins[bit / nbits] |= 1 << (bit % nbits);
 		}
 
 		/* Convert to correct endianity */
 		for (i = 0; i < ETH_MULTICAST_MAC_BINS_IN_REGS; i++) {
 			struct vport_update_ramrod_mcast *p_ramrod_bins;
-			u32 *p_bins = (u32 *)bins;
 
 			p_ramrod_bins = &p_ramrod->approx_mcast;
-			p_ramrod_bins->bins[i] = cpu_to_le32(p_bins[i]);
+			p_ramrod_bins->bins[i] = cpu_to_le32(bins[i]);
 		}
 	}
 

drivers/net/ethernet/qlogic/qed/qed_l2.h

@@ -215,7 +215,7 @@ struct qed_sp_vport_update_params {
 	u8				anti_spoofing_en;
 	u8				update_accept_any_vlan_flg;
 	u8				accept_any_vlan;
-	unsigned long			bins[8];
+	u32				bins[8];
 	struct qed_rss_params		*rss_params;
 	struct qed_filter_accept_flags	accept_flags;
 	struct qed_sge_tpa_params	*sge_tpa_params;

drivers/net/ethernet/qlogic/qed/qed_mcp.c

@@ -1211,6 +1211,7 @@ static void qed_mcp_handle_link_change(struct qed_hwfn *p_hwfn,
 		break;
 	default:
 		p_link->speed = 0;
+		p_link->link_up = 0;
 	}
 
 	if (p_link->link_up && p_link->speed)
@@ -1308,8 +1309,14 @@ int qed_mcp_set_link(struct qed_hwfn *p_hwfn, struct qed_ptt *p_ptt, bool b_up)
 	phy_cfg.pause |= (params->pause.forced_tx) ? ETH_PAUSE_TX : 0;
 	phy_cfg.adv_speed = params->speed.advertised_speeds;
 	phy_cfg.loopback_mode = params->loopback_mode;
-	if (p_hwfn->mcp_info->capabilities & FW_MB_PARAM_FEATURE_SUPPORT_EEE) {
+
-		if (params->eee.enable)
+	/* There are MFWs that share this capability regardless of whether
+	 * this is feasible or not. And given that at the very least adv_caps
+	 * would be set internally by qed, we want to make sure LFA would
+	 * still work.
+	 */
+	if ((p_hwfn->mcp_info->capabilities &
+	     FW_MB_PARAM_FEATURE_SUPPORT_EEE) && params->eee.enable) {
 		phy_cfg.eee_cfg |= EEE_CFG_EEE_ENABLED;
 		if (params->eee.tx_lpi_enable)
 			phy_cfg.eee_cfg |= EEE_CFG_TX_LPI;

drivers/net/ethernet/qlogic/qed/qed_sriov.c

@@ -2831,7 +2831,7 @@ qed_iov_vp_update_mcast_bin_param(struct qed_hwfn *p_hwfn,
 
 	p_data->update_approx_mcast_flg = 1;
 	memcpy(p_data->bins, p_mcast_tlv->bins,
-	       sizeof(unsigned long) * ETH_MULTICAST_MAC_BINS_IN_REGS);
+	       sizeof(u32) * ETH_MULTICAST_MAC_BINS_IN_REGS);
 	*tlvs_mask |= 1 << QED_IOV_VP_UPDATE_MCAST;
 }
 

drivers/net/ethernet/qlogic/qed/qed_vf.c

@@ -1126,7 +1126,7 @@ int qed_vf_pf_vport_update(struct qed_hwfn *p_hwfn,
 		resp_size += sizeof(struct pfvf_def_resp_tlv);
 
 		memcpy(p_mcast_tlv->bins, p_params->bins,
-		       sizeof(unsigned long) * ETH_MULTICAST_MAC_BINS_IN_REGS);
+		       sizeof(u32) * ETH_MULTICAST_MAC_BINS_IN_REGS);
 	}
 
 	update_rx = p_params->accept_flags.update_rx_mode_config;
@@ -1272,7 +1272,7 @@ void qed_vf_pf_filter_mcast(struct qed_hwfn *p_hwfn,
 			u32 bit;
 
 			bit = qed_mcast_bin_from_mac(p_filter_cmd->mac[i]);
-			__set_bit(bit, sp_params.bins);
+			sp_params.bins[bit / 32] |= 1 << (bit % 32);
 		}
 	}
 

drivers/net/ethernet/qlogic/qed/qed_vf.h

@@ -392,7 +392,12 @@ struct vfpf_vport_update_mcast_bin_tlv {
 	struct channel_tlv tl;
 	u8 padding[4];
 
-	u64 bins[8];
+	/* There are only 256 approx bins, and in HSI they're divided into
+	 * 32-bit values. As old VFs used to set-bit to the values on its side,
+	 * the upper half of the array is never expected to contain any data.
+	 */
+	u64 bins[4];
+	u64 obsolete_bins[4];
 };
 
 struct vfpf_vport_update_accept_param_tlv {

drivers/net/ethernet/realtek/r8169.c

@@ -7396,8 +7396,7 @@ static int rtl_init_one(struct pci_dev *pdev, const struct pci_device_id *ent)
 		return rc;
 	}
 
-	/* override BIOS settings, use userspace tools to enable WOL */
+	tp->saved_wolopts = __rtl8169_get_wol(tp);
-	__rtl8169_set_wol(tp, 0);
 
 	mutex_init(&tp->wk.mutex);
 	u64_stats_init(&tp->rx_stats.syncp);

drivers/net/ethernet/xilinx/xilinx_axienet_mdio.c

@@ -218,6 +218,7 @@ int axienet_mdio_setup(struct axienet_local *lp, struct device_node *np)
 	ret = of_mdiobus_register(bus, np1);
 	if (ret) {
 		mdiobus_free(bus);
+		lp->mii_bus = NULL;
 		return ret;
 	}
 	return 0;

drivers/net/phy/phy.c

@@ -519,7 +519,7 @@ static int phy_start_aneg_priv(struct phy_device *phydev, bool sync)
 	 * negotiation may already be done and aneg interrupt may not be
 	 * generated.
 	 */
-	if (phy_interrupt_is_valid(phydev) && (phydev->state == PHY_AN)) {
+	if (phydev->irq != PHY_POLL && phydev->state == PHY_AN) {
 		err = phy_aneg_done(phydev);
 		if (err > 0) {
 			trigger = true;

drivers/net/usb/qmi_wwan.c

@@ -1246,7 +1246,7 @@ static const struct usb_device_id products[] = {
 	{QMI_FIXED_INTF(0x413c, 0x81b3, 8)},	/* Dell Wireless 5809e Gobi(TM) 4G LTE Mobile Broadband Card (rev3) */
 	{QMI_FIXED_INTF(0x413c, 0x81b6, 8)},	/* Dell Wireless 5811e */
 	{QMI_FIXED_INTF(0x413c, 0x81b6, 10)},	/* Dell Wireless 5811e */
-	{QMI_FIXED_INTF(0x413c, 0x81d7, 1)},	/* Dell Wireless 5821e */
+	{QMI_FIXED_INTF(0x413c, 0x81d7, 0)},	/* Dell Wireless 5821e */
 	{QMI_FIXED_INTF(0x03f0, 0x4e1d, 8)},	/* HP lt4111 LTE/EV-DO/HSPA+ Gobi 4G Module */
 	{QMI_FIXED_INTF(0x03f0, 0x9d1d, 1)},	/* HP lt4120 Snapdragon X5 LTE */
 	{QMI_FIXED_INTF(0x22de, 0x9061, 3)},	/* WeTelecom WPD-600N */

drivers/nvme/host/core.c

@@ -100,6 +100,22 @@ static struct class *nvme_subsys_class;
 static void nvme_ns_remove(struct nvme_ns *ns);
 static int nvme_revalidate_disk(struct gendisk *disk);
 static void nvme_put_subsystem(struct nvme_subsystem *subsys);
+static void nvme_remove_invalid_namespaces(struct nvme_ctrl *ctrl,
+					   unsigned nsid);
+
+static void nvme_set_queue_dying(struct nvme_ns *ns)
+{
+	/*
+	 * Revalidating a dead namespace sets capacity to 0. This will end
+	 * buffered writers dirtying pages that can't be synced.
+	 */
+	if (!ns->disk || test_and_set_bit(NVME_NS_DEAD, &ns->flags))
+		return;
+	revalidate_disk(ns->disk);
+	blk_set_queue_dying(ns->queue);
+	/* Forcibly unquiesce queues to avoid blocking dispatch */
+	blk_mq_unquiesce_queue(ns->queue);
+}
 
 static void nvme_queue_scan(struct nvme_ctrl *ctrl)
 {
@@ -1044,14 +1060,17 @@ EXPORT_SYMBOL_GPL(nvme_set_queue_count);
 
 static void nvme_enable_aen(struct nvme_ctrl *ctrl)
 {
-	u32 result;
+	u32 result, supported_aens = ctrl->oaes & NVME_AEN_SUPPORTED;
 	int status;
 
-	status = nvme_set_features(ctrl, NVME_FEAT_ASYNC_EVENT,
+	if (!supported_aens)
-			ctrl->oaes & NVME_AEN_SUPPORTED, NULL, 0, &result);
+		return;
+
+	status = nvme_set_features(ctrl, NVME_FEAT_ASYNC_EVENT, supported_aens,
+			NULL, 0, &result);
 	if (status)
 		dev_warn(ctrl->device, "Failed to configure AEN (cfg %x)\n",
-			 ctrl->oaes & NVME_AEN_SUPPORTED);
+			 supported_aens);
 }
 
 static int nvme_submit_io(struct nvme_ns *ns, struct nvme_user_io __user *uio)
@@ -1151,19 +1170,15 @@ static u32 nvme_passthru_start(struct nvme_ctrl *ctrl, struct nvme_ns *ns,
 
 static void nvme_update_formats(struct nvme_ctrl *ctrl)
 {
-	struct nvme_ns *ns, *next;
+	struct nvme_ns *ns;
-	LIST_HEAD(rm_list);
 
-	down_write(&ctrl->namespaces_rwsem);
+	down_read(&ctrl->namespaces_rwsem);
-	list_for_each_entry(ns, &ctrl->namespaces, list) {
+	list_for_each_entry(ns, &ctrl->namespaces, list)
-		if (ns->disk && nvme_revalidate_disk(ns->disk)) {
+		if (ns->disk && nvme_revalidate_disk(ns->disk))
-			list_move_tail(&ns->list, &rm_list);
+			nvme_set_queue_dying(ns);
-		}
+	up_read(&ctrl->namespaces_rwsem);
-	}
-	up_write(&ctrl->namespaces_rwsem);
 
-	list_for_each_entry_safe(ns, next, &rm_list, list)
+	nvme_remove_invalid_namespaces(ctrl, NVME_NSID_ALL);
-		nvme_ns_remove(ns);
 }
 
 static void nvme_passthru_end(struct nvme_ctrl *ctrl, u32 effects)
@@ -1218,7 +1233,7 @@ static int nvme_user_cmd(struct nvme_ctrl *ctrl, struct nvme_ns *ns,
 	effects = nvme_passthru_start(ctrl, ns, cmd.opcode);
 	status = nvme_submit_user_cmd(ns ? ns->queue : ctrl->admin_q, &c,
 			(void __user *)(uintptr_t)cmd.addr, cmd.data_len,
-			(void __user *)(uintptr_t)cmd.metadata, cmd.metadata,
+			(void __user *)(uintptr_t)cmd.metadata, cmd.metadata_len,
 			0, &cmd.result, timeout);
 	nvme_passthru_end(ctrl, effects);
 
@@ -3138,7 +3153,7 @@ static void nvme_remove_invalid_namespaces(struct nvme_ctrl *ctrl,
 
 	down_write(&ctrl->namespaces_rwsem);
 	list_for_each_entry_safe(ns, next, &ctrl->namespaces, list) {
-		if (ns->head->ns_id > nsid)
+		if (ns->head->ns_id > nsid || test_bit(NVME_NS_DEAD, &ns->flags))
 			list_move_tail(&ns->list, &rm_list);
 	}
 	up_write(&ctrl->namespaces_rwsem);
@@ -3542,19 +3557,9 @@ void nvme_kill_queues(struct nvme_ctrl *ctrl)
 	if (ctrl->admin_q)
 		blk_mq_unquiesce_queue(ctrl->admin_q);
 
-	list_for_each_entry(ns, &ctrl->namespaces, list) {
+	list_for_each_entry(ns, &ctrl->namespaces, list)
-		/*
+		nvme_set_queue_dying(ns);
-		 * Revalidating a dead namespace sets capacity to 0. This will
-		 * end buffered writers dirtying pages that can't be synced.
-		 */
-		if (!ns->disk || test_and_set_bit(NVME_NS_DEAD, &ns->flags))
-			continue;
-		revalidate_disk(ns->disk);
-		blk_set_queue_dying(ns->queue);
 
-		/* Forcibly unquiesce queues to avoid blocking dispatch */
-		blk_mq_unquiesce_queue(ns->queue);
-	}
 	up_read(&ctrl->namespaces_rwsem);
 }
 EXPORT_SYMBOL_GPL(nvme_kill_queues);

drivers/nvme/host/pci.c

@@ -2556,11 +2556,6 @@ static int nvme_probe(struct pci_dev *pdev, const struct pci_device_id *id)
 
 	quirks |= check_vendor_combination_bug(pdev);
 
-	result = nvme_init_ctrl(&dev->ctrl, &pdev->dev, &nvme_pci_ctrl_ops,
-			quirks);
-	if (result)
-		goto release_pools;
-
 	/*
 	 * Double check that our mempool alloc size will cover the biggest
 	 * command we support.
@@ -2578,6 +2573,11 @@ static int nvme_probe(struct pci_dev *pdev, const struct pci_device_id *id)
 		goto release_pools;
 	}
 
+	result = nvme_init_ctrl(&dev->ctrl, &pdev->dev, &nvme_pci_ctrl_ops,
+			quirks);
+	if (result)
+		goto release_mempool;
+
 	dev_info(dev->ctrl.device, "pci function %s\n", dev_name(&pdev->dev));
 
 	nvme_get_ctrl(&dev->ctrl);
@@ -2585,6 +2585,8 @@ static int nvme_probe(struct pci_dev *pdev, const struct pci_device_id *id)
 
 	return 0;
 
+ release_mempool:
+	mempool_destroy(dev->iod_mempool);
  release_pools:
 	nvme_release_prp_pools(dev);
  unmap:

drivers/scsi/cxlflash/ocxl_hw.c

@@ -134,15 +134,14 @@ static struct file *ocxlflash_getfile(struct device *dev, const char *name,
 		rc = PTR_ERR(file);
 		dev_err(dev, "%s: alloc_file failed rc=%d\n",
 			__func__, rc);
-		goto err5;
+		path_put(&path);
+		goto err3;
 	}
 
 	file->f_flags = flags & (O_ACCMODE | O_NONBLOCK);
 	file->private_data = priv;
 out:
 	return file;
-err5:
-	path_put(&path);
 err4:
 	iput(inode);
 err3:

drivers/soc/imx/gpc.c

@@ -27,9 +27,16 @@
 #define GPC_PGC_SW2ISO_SHIFT	0x8
 #define GPC_PGC_SW_SHIFT	0x0
 
+#define GPC_PGC_PCI_PDN		0x200
+#define GPC_PGC_PCI_SR		0x20c
+
 #define GPC_PGC_GPU_PDN		0x260
 #define GPC_PGC_GPU_PUPSCR	0x264
 #define GPC_PGC_GPU_PDNSCR	0x268
+#define GPC_PGC_GPU_SR		0x26c
+
+#define GPC_PGC_DISP_PDN	0x240
+#define GPC_PGC_DISP_SR		0x24c
 
 #define GPU_VPU_PUP_REQ		BIT(1)
 #define GPU_VPU_PDN_REQ		BIT(0)
@@ -318,10 +325,24 @@ static const struct of_device_id imx_gpc_dt_ids[] = {
 	{ }
 };
 
+static const struct regmap_range yes_ranges[] = {
+	regmap_reg_range(GPC_CNTR, GPC_CNTR),
+	regmap_reg_range(GPC_PGC_PCI_PDN, GPC_PGC_PCI_SR),
+	regmap_reg_range(GPC_PGC_GPU_PDN, GPC_PGC_GPU_SR),
+	regmap_reg_range(GPC_PGC_DISP_PDN, GPC_PGC_DISP_SR),
+};
+
+static const struct regmap_access_table access_table = {
+	.yes_ranges	= yes_ranges,
+	.n_yes_ranges	= ARRAY_SIZE(yes_ranges),
+};
+
 static const struct regmap_config imx_gpc_regmap_config = {
 	.reg_bits = 32,
 	.val_bits = 32,
 	.reg_stride = 4,
+	.rd_table = &access_table,
+	.wr_table = &access_table,
 	.max_register = 0x2ac,
 };
 

drivers/staging/media/omap4iss/iss_video.c

@@ -11,7 +11,6 @@
  * (at your option) any later version.
  */
 
-#include <asm/cacheflush.h>
 #include <linux/clk.h>
 #include <linux/mm.h>
 #include <linux/pagemap.h>
@@ -24,6 +23,8 @@
 #include <media/v4l2-ioctl.h>
 #include <media/v4l2-mc.h>
 
+#include <asm/cacheflush.h>
+
 #include "iss_video.h"
 #include "iss.h"
 

drivers/vfio/vfio_iommu_spapr_tce.c

@@ -457,17 +457,17 @@ static void tce_iommu_unuse_page(struct tce_container *container,
 }
 
 static int tce_iommu_prereg_ua_to_hpa(struct tce_container *container,
-		unsigned long tce, unsigned long size,
+		unsigned long tce, unsigned long shift,
 		unsigned long *phpa, struct mm_iommu_table_group_mem_t **pmem)
 {
 	long ret = 0;
 	struct mm_iommu_table_group_mem_t *mem;
 
-	mem = mm_iommu_lookup(container->mm, tce, size);
+	mem = mm_iommu_lookup(container->mm, tce, 1ULL << shift);
 	if (!mem)
 		return -EINVAL;
 
-	ret = mm_iommu_ua_to_hpa(mem, tce, phpa);
+	ret = mm_iommu_ua_to_hpa(mem, tce, shift, phpa);
 	if (ret)
 		return -EINVAL;
 
@@ -487,7 +487,7 @@ static void tce_iommu_unuse_page_v2(struct tce_container *container,
 	if (!pua)
 		return;
 
-	ret = tce_iommu_prereg_ua_to_hpa(container, *pua, IOMMU_PAGE_SIZE(tbl),
+	ret = tce_iommu_prereg_ua_to_hpa(container, *pua, tbl->it_page_shift,
 			&hpa, &mem);
 	if (ret)
 		pr_debug("%s: tce %lx at #%lx was not cached, ret=%d\n",
@@ -611,7 +611,7 @@ static long tce_iommu_build_v2(struct tce_container *container,
 				entry + i);
 
 		ret = tce_iommu_prereg_ua_to_hpa(container,
-				tce, IOMMU_PAGE_SIZE(tbl), &hpa, &mem);
+				tce, tbl->it_page_shift, &hpa, &mem);
 		if (ret)
 			break;
 

fs/aio.c

@@ -1896,6 +1896,11 @@ SYSCALL_DEFINE5(io_getevents, aio_context_t, ctx_id,
 	return ret;
 }
 
+struct __aio_sigset {
+	const sigset_t __user	*sigmask;
+	size_t		sigsetsize;
+};
+
 SYSCALL_DEFINE6(io_pgetevents,
 		aio_context_t, ctx_id,
 		long, min_nr,

fs/btrfs/extent_io.c

@@ -4238,8 +4238,9 @@ int try_release_extent_mapping(struct page *page, gfp_t mask)
 	struct extent_map *em;
 	u64 start = page_offset(page);
 	u64 end = start + PAGE_SIZE - 1;
-	struct extent_io_tree *tree = &BTRFS_I(page->mapping->host)->io_tree;
+	struct btrfs_inode *btrfs_inode = BTRFS_I(page->mapping->host);
-	struct extent_map_tree *map = &BTRFS_I(page->mapping->host)->extent_tree;
+	struct extent_io_tree *tree = &btrfs_inode->io_tree;
+	struct extent_map_tree *map = &btrfs_inode->extent_tree;
 
 	if (gfpflags_allow_blocking(mask) &&
 	    page->mapping->host->i_size > SZ_16M) {
@@ -4262,6 +4263,8 @@ int try_release_extent_mapping(struct page *page, gfp_t mask)
 					    extent_map_end(em) - 1,
 					    EXTENT_LOCKED | EXTENT_WRITEBACK,
 					    0, NULL)) {
+				set_bit(BTRFS_INODE_NEEDS_FULL_SYNC,
+					&btrfs_inode->runtime_flags);
 				remove_extent_mapping(map, em);
 				/* once for the rb tree */
 				free_extent_map(em);

fs/exec.c

@@ -290,7 +290,7 @@ static int __bprm_mm_init(struct linux_binprm *bprm)
 	struct vm_area_struct *vma = NULL;
 	struct mm_struct *mm = bprm->mm;
 
-	bprm->vma = vma = kmem_cache_zalloc(vm_area_cachep, GFP_KERNEL);
+	bprm->vma = vma = vm_area_alloc(mm);
 	if (!vma)
 		return -ENOMEM;
 
@@ -298,7 +298,6 @@ static int __bprm_mm_init(struct linux_binprm *bprm)
 		err = -EINTR;
 		goto err_free;
 	}
-	vma->vm_mm = mm;
 
 	/*
 	 * Place the stack at the largest stack address the architecture
@@ -311,7 +310,6 @@ static int __bprm_mm_init(struct linux_binprm *bprm)
 	vma->vm_start = vma->vm_end - PAGE_SIZE;
 	vma->vm_flags = VM_SOFTDIRTY | VM_STACK_FLAGS | VM_STACK_INCOMPLETE_SETUP;
 	vma->vm_page_prot = vm_get_page_prot(vma->vm_flags);
-	INIT_LIST_HEAD(&vma->anon_vma_chain);
 
 	err = insert_vm_struct(mm, vma);
 	if (err)
@@ -326,7 +324,7 @@ static int __bprm_mm_init(struct linux_binprm *bprm)
 	up_write(&mm->mmap_sem);
 err_free:
 	bprm->vma = NULL;
-	kmem_cache_free(vm_area_cachep, vma);
+	vm_area_free(vma);
 	return err;
 }
 

fs/fat/inode.c

@@ -707,13 +707,21 @@ static void fat_set_state(struct super_block *sb,
 	brelse(bh);
 }
 
+static void fat_reset_iocharset(struct fat_mount_options *opts)
+{
+	if (opts->iocharset != fat_default_iocharset) {
+		/* Note: opts->iocharset can be NULL here */
+		kfree(opts->iocharset);
+		opts->iocharset = fat_default_iocharset;
+	}
+}
+
 static void delayed_free(struct rcu_head *p)
 {
 	struct msdos_sb_info *sbi = container_of(p, struct msdos_sb_info, rcu);
 	unload_nls(sbi->nls_disk);
 	unload_nls(sbi->nls_io);
-	if (sbi->options.iocharset != fat_default_iocharset)
+	fat_reset_iocharset(&sbi->options);
-		kfree(sbi->options.iocharset);
 	kfree(sbi);
 }
 
@@ -1132,7 +1140,7 @@ static int parse_options(struct super_block *sb, char *options, int is_vfat,
 	opts->fs_fmask = opts->fs_dmask = current_umask();
 	opts->allow_utime = -1;
 	opts->codepage = fat_default_codepage;
-	opts->iocharset = fat_default_iocharset;
+	fat_reset_iocharset(opts);
 	if (is_vfat) {
 		opts->shortname = VFAT_SFN_DISPLAY_WINNT|VFAT_SFN_CREATE_WIN95;
 		opts->rodir = 0;
@@ -1289,8 +1297,7 @@ static int parse_options(struct super_block *sb, char *options, int is_vfat,
 
 		/* vfat specific */
 		case Opt_charset:
-			if (opts->iocharset != fat_default_iocharset)
+			fat_reset_iocharset(opts);
-				kfree(opts->iocharset);
 			iocharset = match_strdup(&args[0]);
 			if (!iocharset)
 				return -ENOMEM;
@@ -1881,8 +1888,7 @@ int fat_fill_super(struct super_block *sb, void *data, int silent, int isvfat,
 		iput(fat_inode);
 	unload_nls(sbi->nls_io);
 	unload_nls(sbi->nls_disk);
-	if (sbi->options.iocharset != fat_default_iocharset)
+	fat_reset_iocharset(&sbi->options);
-		kfree(sbi->options.iocharset);
 	sb->s_fs_info = NULL;
 	kfree(sbi);
 	return error;

fs/internal.h

@@ -127,7 +127,6 @@ int do_fchownat(int dfd, const char __user *filename, uid_t user, gid_t group,
 
 extern int open_check_o_direct(struct file *f);
 extern int vfs_open(const struct path *, struct file *, const struct cred *);
-extern struct file *filp_clone_open(struct file *);
 
 /*
  * inode.c

include/linux/bpfilter.h

@@ -5,10 +5,10 @@
 #include <uapi/linux/bpfilter.h>
 
 struct sock;
-int bpfilter_ip_set_sockopt(struct sock *sk, int optname, char *optval,
+int bpfilter_ip_set_sockopt(struct sock *sk, int optname, char __user *optval,
 			    unsigned int optlen);
-int bpfilter_ip_get_sockopt(struct sock *sk, int optname, char *optval,
+int bpfilter_ip_get_sockopt(struct sock *sk, int optname, char __user *optval,
-			    int *optlen);
+			    int __user *optlen);
 extern int (*bpfilter_process_sockopt)(struct sock *sk, int optname,
 				       char __user *optval,
 				       unsigned int optlen, bool is_set);

include/linux/fs.h

@@ -2420,6 +2420,7 @@ extern struct file *filp_open(const char *, int, umode_t);
 extern struct file *file_open_root(struct dentry *, struct vfsmount *,
 				   const char *, int, umode_t);
 extern struct file * dentry_open(const struct path *, int, const struct cred *);
+extern struct file *filp_clone_open(struct file *);
 extern int filp_close(struct file *, fl_owner_t id);
 
 extern struct filename *getname_flags(const char __user *, int, int *);

include/linux/mlx5/driver.h

@@ -363,6 +363,7 @@ struct mlx5_frag_buf_ctrl {
 	struct mlx5_frag_buf	frag_buf;
 	u32			sz_m1;
 	u32			frag_sz_m1;
+	u32			strides_offset;
 	u8			log_sz;
 	u8			log_stride;
 	u8			log_frag_strides;
@@ -991,7 +992,8 @@ static inline u32 mlx5_base_mkey(const u32 key)
 	return key & 0xffffff00u;
 }
 
-static inline void mlx5_fill_fbc(u8 log_stride, u8 log_sz,
+static inline void mlx5_fill_fbc_offset(u8 log_stride, u8 log_sz,
+					u32 strides_offset,
 					struct mlx5_frag_buf_ctrl *fbc)
 {
 	fbc->log_stride = log_stride;
@@ -999,6 +1001,13 @@ static inline void mlx5_fill_fbc(u8 log_stride, u8 log_sz,
 	fbc->sz_m1	= (1 << fbc->log_sz) - 1;
 	fbc->log_frag_strides = PAGE_SHIFT - fbc->log_stride;
 	fbc->frag_sz_m1	= (1 << fbc->log_frag_strides) - 1;
+	fbc->strides_offset = strides_offset;
+}
+
+static inline void mlx5_fill_fbc(u8 log_stride, u8 log_sz,
+				 struct mlx5_frag_buf_ctrl *fbc)
+{
+	mlx5_fill_fbc_offset(log_stride, log_sz, 0, fbc);
 }
 
 static inline void mlx5_core_init_cq_frag_buf(struct mlx5_frag_buf_ctrl *fbc,
@@ -1012,7 +1021,10 @@ static inline void mlx5_core_init_cq_frag_buf(struct mlx5_frag_buf_ctrl *fbc,
 static inline void *mlx5_frag_buf_get_wqe(struct mlx5_frag_buf_ctrl *fbc,
 					  u32 ix)
 {
-	unsigned int frag = (ix >> fbc->log_frag_strides);
+	unsigned int frag;
+
+	ix  += fbc->strides_offset;
+	frag = ix >> fbc->log_frag_strides;
 
 	return fbc->frag_buf.frags[frag].buf +
 		((fbc->frag_sz_m1 & ix) << fbc->log_stride);

include/linux/mm.h

@@ -155,7 +155,9 @@ extern int overcommit_kbytes_handler(struct ctl_table *, int, void __user *,
  * mmap() functions).
  */
 
-extern struct kmem_cache *vm_area_cachep;
+struct vm_area_struct *vm_area_alloc(struct mm_struct *);
+struct vm_area_struct *vm_area_dup(struct vm_area_struct *);
+void vm_area_free(struct vm_area_struct *);
 
 #ifndef CONFIG_MMU
 extern struct rb_root nommu_region_tree;

include/linux/sched/task.h

@@ -75,7 +75,7 @@ extern long _do_fork(unsigned long, unsigned long, unsigned long, int __user *,
 extern long do_fork(unsigned long, unsigned long, unsigned long, int __user *, int __user *);
 struct task_struct *fork_idle(int);
 extern pid_t kernel_thread(int (*fn)(void *), void *arg, unsigned long flags);
-extern long kernel_wait4(pid_t, int *, int, struct rusage *);
+extern long kernel_wait4(pid_t, int __user *, int, struct rusage *);
 
 extern void free_task(struct task_struct *tsk);
 

include/linux/syscalls.h

@@ -11,6 +11,7 @@
 #ifndef _LINUX_SYSCALLS_H
 #define _LINUX_SYSCALLS_H
 
+struct __aio_sigset;
 struct epoll_event;
 struct iattr;
 struct inode;

include/net/cfg80211.h

@@ -5937,10 +5937,11 @@ void cfg80211_mgmt_tx_status(struct wireless_dev *wdev, u64 cookie,
 /**
  * cfg80211_rx_control_port - notification about a received control port frame
  * @dev: The device the frame matched to
- * @buf: control port frame
+ * @skb: The skbuf with the control port frame.  It is assumed that the skbuf
- * @len: length of the frame data
+ *	is 802.3 formatted (with 802.3 header).  The skb can be non-linear.
- * @addr: The peer from which the frame was received
+ *	This function does not take ownership of the skb, so the caller is
- * @proto: frame protocol, typically PAE or Pre-authentication
+ *	responsible for any cleanup.  The caller must also ensure that
+ *	skb->protocol is set appropriately.
  * @unencrypted: Whether the frame was received unencrypted
  *
  * This function is used to inform userspace about a received control port
@@ -5953,8 +5954,7 @@ void cfg80211_mgmt_tx_status(struct wireless_dev *wdev, u64 cookie,
  * Return: %true if the frame was passed to userspace
  */
 bool cfg80211_rx_control_port(struct net_device *dev,
-			      const u8 *buf, size_t len,
+			      struct sk_buff *skb, bool unencrypted);
-			      const u8 *addr, u16 proto, bool unencrypted);
 
 /**
  * cfg80211_cqm_rssi_notify - connection quality monitoring rssi event

include/net/ip6_fib.h

@@ -281,6 +281,11 @@ static inline void fib6_info_hold(struct fib6_info *f6i)
 	atomic_inc(&f6i->fib6_ref);
 }
 
+static inline bool fib6_info_hold_safe(struct fib6_info *f6i)
+{
+	return atomic_inc_not_zero(&f6i->fib6_ref);
+}
+
 static inline void fib6_info_release(struct fib6_info *f6i)
 {
 	if (f6i && atomic_dec_and_test(&f6i->fib6_ref))

include/net/netfilter/nf_tables.h

@@ -150,6 +150,7 @@ static inline void nft_data_debug(const struct nft_data *data)
  *	@portid: netlink portID of the original message
  *	@seq: netlink sequence number
  *	@family: protocol family
+ *	@level: depth of the chains
  *	@report: notify via unicast netlink message
  */
 struct nft_ctx {
@@ -160,6 +161,7 @@ struct nft_ctx {
 	u32				portid;
 	u32				seq;
 	u8				family;
+	u8				level;
 	bool				report;
 };
 
@@ -865,7 +867,6 @@ enum nft_chain_flags {
  *	@table: table that this chain belongs to
  *	@handle: chain handle
  *	@use: number of jump references to this chain
- *	@level: length of longest path to this chain
  *	@flags: bitmask of enum nft_chain_flags
  *	@name: name of the chain
  */
@@ -878,7 +879,6 @@ struct nft_chain {
 	struct nft_table		*table;
 	u64				handle;
 	u32				use;
-	u16				level;
 	u8				flags:6,
 					genmask:2;
 	char				*name;
@@ -1124,7 +1124,6 @@ struct nft_flowtable {
 	u32				genmask:2,
 					use:30;
 	u64				handle;
-	char				*dev_name[NFT_FLOWTABLE_DEVICE_MAX];
 	/* runtime data below here */
 	struct nf_hook_ops		*ops ____cacheline_aligned;
 	struct nf_flowtable		data;

include/net/tcp.h

@@ -342,6 +342,7 @@ ssize_t tcp_splice_read(struct socket *sk, loff_t *ppos,
 			struct pipe_inode_info *pipe, size_t len,
 			unsigned int flags);
 
+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)
 {
@@ -540,6 +541,7 @@ void tcp_send_fin(struct sock *sk);
 void tcp_send_active_reset(struct sock *sk, gfp_t priority);
 int tcp_send_synack(struct sock *);
 void tcp_push_one(struct sock *, unsigned int mss_now);
+void __tcp_send_ack(struct sock *sk, u32 rcv_nxt);
 void tcp_send_ack(struct sock *sk);
 void tcp_send_delayed_ack(struct sock *sk);
 void tcp_send_loss_probe(struct sock *sk);
@@ -839,6 +841,11 @@ static inline void bpf_compute_data_end_sk_skb(struct sk_buff *skb)
  * as TCP moves IP6CB into a different location in skb->cb[]
  */
 static inline int tcp_v6_iif(const struct sk_buff *skb)
+{
+	return TCP_SKB_CB(skb)->header.h6.iif;
+}
+
+static inline int tcp_v6_iif_l3_slave(const struct sk_buff *skb)
 {
 	bool l3_slave = ipv6_l3mdev_skb(TCP_SKB_CB(skb)->header.h6.flags);
 

include/uapi/linux/aio_abi.h

@@ -29,7 +29,6 @@
 
 #include <linux/types.h>
 #include <linux/fs.h>
-#include <linux/signal.h>
 #include <asm/byteorder.h>
 
 typedef __kernel_ulong_t aio_context_t;
@@ -110,10 +109,5 @@ struct iocb {
 #undef IFBIG
 #undef IFLITTLE
 
-struct __aio_sigset {
-	const sigset_t __user	*sigmask;
-	size_t		sigsetsize;
-};
-
 #endif /* __LINUX__AIO_ABI_H */
 

include/uapi/linux/btf.h

@@ -76,7 +76,7 @@ struct btf_type {
  */
 #define BTF_INT_ENCODING(VAL)	(((VAL) & 0x0f000000) >> 24)
 #define BTF_INT_OFFSET(VAL)	(((VAL  & 0x00ff0000)) >> 16)
-#define BTF_INT_BITS(VAL)	((VAL)  & 0x0000ffff)
+#define BTF_INT_BITS(VAL)	((VAL)  & 0x000000ff)
 
 /* Attributes stored in the BTF_INT_ENCODING */
 #define BTF_INT_SIGNED	(1 << 0)

kernel/bpf/btf.c

@@ -450,7 +450,7 @@ static const struct btf_type *btf_type_by_id(const struct btf *btf, u32 type_id)
  */
 static bool btf_type_int_is_regular(const struct btf_type *t)
 {
-	u16 nr_bits, nr_bytes;
+	u8 nr_bits, nr_bytes;
 	u32 int_data;
 
 	int_data = btf_type_int(t);
@@ -993,12 +993,16 @@ static void btf_int_bits_seq_show(const struct btf *btf,
 {
 	u16 left_shift_bits, right_shift_bits;
 	u32 int_data = btf_type_int(t);
-	u16 nr_bits = BTF_INT_BITS(int_data);
+	u8 nr_bits = BTF_INT_BITS(int_data);
-	u16 total_bits_offset;
+	u8 total_bits_offset;
-	u16 nr_copy_bytes;
+	u8 nr_copy_bytes;
-	u16 nr_copy_bits;
+	u8 nr_copy_bits;
 	u64 print_num;
 
+	/*
+	 * bits_offset is at most 7.
+	 * BTF_INT_OFFSET() cannot exceed 64 bits.
+	 */
 	total_bits_offset = bits_offset + BTF_INT_OFFSET(int_data);
 	data += BITS_ROUNDDOWN_BYTES(total_bits_offset);
 	bits_offset = BITS_PER_BYTE_MASKED(total_bits_offset);
@@ -1028,7 +1032,7 @@ static void btf_int_seq_show(const struct btf *btf, const struct btf_type *t,
 	u32 int_data = btf_type_int(t);
 	u8 encoding = BTF_INT_ENCODING(int_data);
 	bool sign = encoding & BTF_INT_SIGNED;
-	u32 nr_bits = BTF_INT_BITS(int_data);
+	u8 nr_bits = BTF_INT_BITS(int_data);
 
 	if (bits_offset || BTF_INT_OFFSET(int_data) ||
 	    BITS_PER_BYTE_MASKED(nr_bits)) {

kernel/fork.c

@@ -303,11 +303,38 @@ struct kmem_cache *files_cachep;
 struct kmem_cache *fs_cachep;
 
 /* SLAB cache for vm_area_struct structures */
-struct kmem_cache *vm_area_cachep;
+static struct kmem_cache *vm_area_cachep;
 
 /* SLAB cache for mm_struct structures (tsk->mm) */
 static struct kmem_cache *mm_cachep;
 
+struct vm_area_struct *vm_area_alloc(struct mm_struct *mm)
+{
+	struct vm_area_struct *vma = kmem_cache_zalloc(vm_area_cachep, GFP_KERNEL);
+
+	if (vma) {
+		vma->vm_mm = mm;
+		INIT_LIST_HEAD(&vma->anon_vma_chain);
+	}
+	return vma;
+}
+
+struct vm_area_struct *vm_area_dup(struct vm_area_struct *orig)
+{
+	struct vm_area_struct *new = kmem_cache_alloc(vm_area_cachep, GFP_KERNEL);
+
+	if (new) {
+		*new = *orig;
+		INIT_LIST_HEAD(&new->anon_vma_chain);
+	}
+	return new;
+}
+
+void vm_area_free(struct vm_area_struct *vma)
+{
+	kmem_cache_free(vm_area_cachep, vma);
+}
+
 static void account_kernel_stack(struct task_struct *tsk, int account)
 {
 	void *stack = task_stack_page(tsk);
@@ -455,11 +482,9 @@ static __latent_entropy int dup_mmap(struct mm_struct *mm,
 				goto fail_nomem;
 			charge = len;
 		}
-		tmp = kmem_cache_alloc(vm_area_cachep, GFP_KERNEL);
+		tmp = vm_area_dup(mpnt);
 		if (!tmp)
 			goto fail_nomem;
-		*tmp = *mpnt;
-		INIT_LIST_HEAD(&tmp->anon_vma_chain);
 		retval = vma_dup_policy(mpnt, tmp);
 		if (retval)
 			goto fail_nomem_policy;
@@ -539,7 +564,7 @@ static __latent_entropy int dup_mmap(struct mm_struct *mm,
 fail_nomem_anon_vma_fork:
 	mpol_put(vma_policy(tmp));
 fail_nomem_policy:
-	kmem_cache_free(vm_area_cachep, tmp);
+	vm_area_free(tmp);
 fail_nomem:
 	retval = -ENOMEM;
 	vm_unacct_memory(charge);

kernel/sched/deadline.c

@@ -2290,8 +2290,17 @@ 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);
 
-	if (!task_on_rq_queued(p))
+	if (!task_on_rq_queued(p)) {
+		/*
+		 * Inactive timer is armed. However, p is leaving DEADLINE and
+		 * might migrate away from this rq while continuing to run on
+		 * some other class. We need to remove its contribution from
+		 * this rq running_bw now, or sub_rq_bw (below) will complain.
+		 */
+		if (p->dl.dl_non_contending)
+			sub_running_bw(&p->dl, &rq->dl);
 		sub_rq_bw(&p->dl, &rq->dl);
+	}
 
 	/*
 	 * We cannot use inactive_task_timer() to invoke sub_running_bw()

kernel/stop_machine.c

@@ -270,7 +270,11 @@ static int cpu_stop_queue_two_works(int cpu1, struct cpu_stop_work *work1,
 		goto retry;
 	}
 
+	if (!err) {
+		preempt_disable();
 		wake_up_q(&wakeq);
+		preempt_enable();
+	}
 
 	return err;
 }

lib/iov_iter.c

@@ -596,15 +596,70 @@ static unsigned long memcpy_mcsafe_to_page(struct page *page, size_t offset,
 	return ret;
 }
 
+static size_t copy_pipe_to_iter_mcsafe(const void *addr, size_t bytes,
+				struct iov_iter *i)
+{
+	struct pipe_inode_info *pipe = i->pipe;
+	size_t n, off, xfer = 0;
+	int idx;
+
+	if (!sanity(i))
+		return 0;
+
+	bytes = n = push_pipe(i, bytes, &idx, &off);
+	if (unlikely(!n))
+		return 0;
+	for ( ; n; idx = next_idx(idx, pipe), off = 0) {
+		size_t chunk = min_t(size_t, n, PAGE_SIZE - off);
+		unsigned long rem;
+
+		rem = memcpy_mcsafe_to_page(pipe->bufs[idx].page, off, addr,
+				chunk);
+		i->idx = idx;
+		i->iov_offset = off + chunk - rem;
+		xfer += chunk - rem;
+		if (rem)
+			break;
+		n -= chunk;
+		addr += chunk;
+	}
+	i->count -= xfer;
+	return xfer;
+}
+
+/**
+ * _copy_to_iter_mcsafe - copy to user with source-read error exception handling
+ * @addr: source kernel address
+ * @bytes: total transfer length
+ * @iter: destination iterator
+ *
+ * The pmem driver arranges for filesystem-dax to use this facility via
+ * dax_copy_to_iter() for protecting read/write to persistent memory.
+ * Unless / until an architecture can guarantee identical performance
+ * between _copy_to_iter_mcsafe() and _copy_to_iter() it would be a
+ * performance regression to switch more users to the mcsafe version.
+ *
+ * Otherwise, the main differences between this and typical _copy_to_iter().
+ *
+ * * Typical tail/residue handling after a fault retries the copy
+ *   byte-by-byte until the fault happens again. Re-triggering machine
+ *   checks is potentially fatal so the implementation uses source
+ *   alignment and poison alignment assumptions to avoid re-triggering
+ *   hardware exceptions.
+ *
+ * * ITER_KVEC, ITER_PIPE, and ITER_BVEC can return short copies.
+ *   Compare to copy_to_iter() where only ITER_IOVEC attempts might return
+ *   a short copy.
+ *
+ * See MCSAFE_TEST for self-test.
+ */
 size_t _copy_to_iter_mcsafe(const void *addr, size_t bytes, struct iov_iter *i)
 {
 	const char *from = addr;
 	unsigned long rem, curr_addr, s_addr = (unsigned long) addr;
 
-	if (unlikely(i->type & ITER_PIPE)) {
+	if (unlikely(i->type & ITER_PIPE))
-		WARN_ON(1);
+		return copy_pipe_to_iter_mcsafe(addr, bytes, i);
-		return 0;
-	}
 	if (iter_is_iovec(i))
 		might_fault();
 	iterate_and_advance(i, bytes, v,
@@ -701,6 +756,20 @@ size_t _copy_from_iter_nocache(void *addr, size_t bytes, struct iov_iter *i)
 EXPORT_SYMBOL(_copy_from_iter_nocache);
 
 #ifdef CONFIG_ARCH_HAS_UACCESS_FLUSHCACHE
+/**
+ * _copy_from_iter_flushcache - write destination through cpu cache
+ * @addr: destination kernel address
+ * @bytes: total transfer length
+ * @iter: source iterator
+ *
+ * The pmem driver arranges for filesystem-dax to use this facility via
+ * dax_copy_from_iter() for ensuring that writes to persistent memory
+ * are flushed through the CPU cache. It is differentiated from
+ * _copy_from_iter_nocache() in that guarantees all data is flushed for
+ * all iterator types. The _copy_from_iter_nocache() only attempts to
+ * bypass the cache for the ITER_IOVEC case, and on some archs may use
+ * instructions that strand dirty-data in the cache.
+ */
 size_t _copy_from_iter_flushcache(void *addr, size_t bytes, struct iov_iter *i)
 {
 	char *to = addr;

mm/huge_memory.c

@@ -2084,6 +2084,8 @@ static void __split_huge_pmd_locked(struct vm_area_struct *vma, pmd_t *pmd,
 		if (vma_is_dax(vma))
 			return;
 		page = pmd_page(_pmd);
+		if (!PageDirty(page) && pmd_dirty(_pmd))
+			set_page_dirty(page);
 		if (!PageReferenced(page) && pmd_young(_pmd))
 			SetPageReferenced(page);
 		page_remove_rmap(page, true);

mm/memblock.c

@@ -20,6 +20,7 @@
 #include <linux/kmemleak.h>
 #include <linux/seq_file.h>
 #include <linux/memblock.h>
+#include <linux/bootmem.h>
 
 #include <asm/sections.h>
 #include <linux/io.h>
@@ -1225,6 +1226,7 @@ phys_addr_t __init memblock_alloc_try_nid(phys_addr_t size, phys_addr_t align, i
 	return memblock_alloc_base(size, align, MEMBLOCK_ALLOC_ACCESSIBLE);
 }
 
+#if defined(CONFIG_NO_BOOTMEM)
 /**
  * memblock_virt_alloc_internal - allocate boot memory block
  * @size: size of memory block to be allocated in bytes
@@ -1432,6 +1434,7 @@ void * __init memblock_virt_alloc_try_nid(
 	      (u64)max_addr);
 	return NULL;
 }
+#endif
 
 /**
  * __memblock_free_early - free boot memory block

mm/memcontrol.c

@@ -850,7 +850,7 @@ static void invalidate_reclaim_iterators(struct mem_cgroup *dead_memcg)
 	int nid;
 	int i;
 
-	while ((memcg = parent_mem_cgroup(memcg))) {
+	for (; memcg; memcg = parent_mem_cgroup(memcg)) {
 		for_each_node(nid) {
 			mz = mem_cgroup_nodeinfo(memcg, nid);
 			for (i = 0; i <= DEF_PRIORITY; i++) {

mm/mmap.c

@@ -182,7 +182,7 @@ static struct vm_area_struct *remove_vma(struct vm_area_struct *vma)
 	if (vma->vm_file)
 		fput(vma->vm_file);
 	mpol_put(vma_policy(vma));
-	kmem_cache_free(vm_area_cachep, vma);
+	vm_area_free(vma);
 	return next;
 }
 
@@ -911,7 +911,7 @@ int __vma_adjust(struct vm_area_struct *vma, unsigned long start,
 			anon_vma_merge(vma, next);
 		mm->map_count--;
 		mpol_put(vma_policy(next));
-		kmem_cache_free(vm_area_cachep, next);
+		vm_area_free(next);
 		/*
 		 * In mprotect's case 6 (see comments on vma_merge),
 		 * we must remove another next too. It would clutter
@@ -1729,19 +1729,17 @@ unsigned long mmap_region(struct file *file, unsigned long addr,
 	 * specific mapper. the address has already been validated, but
 	 * not unmapped, but the maps are removed from the list.
 	 */
-	vma = kmem_cache_zalloc(vm_area_cachep, GFP_KERNEL);
+	vma = vm_area_alloc(mm);
 	if (!vma) {
 		error = -ENOMEM;
 		goto unacct_error;
 	}
 
-	vma->vm_mm = mm;
 	vma->vm_start = addr;
 	vma->vm_end = addr + len;
 	vma->vm_flags = vm_flags;
 	vma->vm_page_prot = vm_get_page_prot(vm_flags);
 	vma->vm_pgoff = pgoff;
-	INIT_LIST_HEAD(&vma->anon_vma_chain);
 
 	if (file) {
 		if (vm_flags & VM_DENYWRITE) {
@@ -1832,7 +1830,7 @@ unsigned long mmap_region(struct file *file, unsigned long addr,
 	if (vm_flags & VM_DENYWRITE)
 		allow_write_access(file);
 free_vma:
-	kmem_cache_free(vm_area_cachep, vma);
+	vm_area_free(vma);
 unacct_error:
 	if (charged)
 		vm_unacct_memory(charged);
@@ -2620,15 +2618,10 @@ int __split_vma(struct mm_struct *mm, struct vm_area_struct *vma,
 			return err;
 	}
 
-	new = kmem_cache_alloc(vm_area_cachep, GFP_KERNEL);
+	new = vm_area_dup(vma);
 	if (!new)
 		return -ENOMEM;
 
-	/* most fields are the same, copy all, and then fixup */
-	*new = *vma;
-
-	INIT_LIST_HEAD(&new->anon_vma_chain);
-
 	if (new_below)
 		new->vm_end = addr;
 	else {
@@ -2669,7 +2662,7 @@ int __split_vma(struct mm_struct *mm, struct vm_area_struct *vma,
  out_free_mpol:
 	mpol_put(vma_policy(new));
  out_free_vma:
-	kmem_cache_free(vm_area_cachep, new);
+	vm_area_free(new);
 	return err;
 }
 
@@ -2984,14 +2977,12 @@ static int do_brk_flags(unsigned long addr, unsigned long len, unsigned long fla
 	/*
 	 * create a vma struct for an anonymous mapping
 	 */
-	vma = kmem_cache_zalloc(vm_area_cachep, GFP_KERNEL);
+	vma = vm_area_alloc(mm);
 	if (!vma) {
 		vm_unacct_memory(len >> PAGE_SHIFT);
 		return -ENOMEM;
 	}
 
-	INIT_LIST_HEAD(&vma->anon_vma_chain);
-	vma->vm_mm = mm;
 	vma->vm_start = addr;
 	vma->vm_end = addr + len;
 	vma->vm_pgoff = pgoff;
@@ -3202,16 +3193,14 @@ struct vm_area_struct *copy_vma(struct vm_area_struct **vmap,
 		}
 		*need_rmap_locks = (new_vma->vm_pgoff <= vma->vm_pgoff);
 	} else {
-		new_vma = kmem_cache_alloc(vm_area_cachep, GFP_KERNEL);
+		new_vma = vm_area_dup(vma);
 		if (!new_vma)
 			goto out;
-		*new_vma = *vma;
 		new_vma->vm_start = addr;
 		new_vma->vm_end = addr + len;
 		new_vma->vm_pgoff = pgoff;
 		if (vma_dup_policy(vma, new_vma))
 			goto out_free_vma;
-		INIT_LIST_HEAD(&new_vma->anon_vma_chain);
 		if (anon_vma_clone(new_vma, vma))
 			goto out_free_mempol;
 		if (new_vma->vm_file)
@@ -3226,7 +3215,7 @@ struct vm_area_struct *copy_vma(struct vm_area_struct **vmap,
 out_free_mempol:
 	mpol_put(vma_policy(new_vma));
 out_free_vma:
-	kmem_cache_free(vm_area_cachep, new_vma);
+	vm_area_free(new_vma);
 out:
 	return NULL;
 }
@@ -3350,12 +3339,10 @@ static struct vm_area_struct *__install_special_mapping(
 	int ret;
 	struct vm_area_struct *vma;
 
-	vma = kmem_cache_zalloc(vm_area_cachep, GFP_KERNEL);
+	vma = vm_area_alloc(mm);
 	if (unlikely(vma == NULL))
 		return ERR_PTR(-ENOMEM);
 
-	INIT_LIST_HEAD(&vma->anon_vma_chain);
-	vma->vm_mm = mm;
 	vma->vm_start = addr;
 	vma->vm_end = addr + len;
 
@@ -3376,7 +3363,7 @@ static struct vm_area_struct *__install_special_mapping(
 	return vma;
 
 out:
-	kmem_cache_free(vm_area_cachep, vma);
+	vm_area_free(vma);
 	return ERR_PTR(ret);
 }
 

mm/nommu.c

@@ -769,7 +769,7 @@ static void delete_vma(struct mm_struct *mm, struct vm_area_struct *vma)
 	if (vma->vm_file)
 		fput(vma->vm_file);
 	put_nommu_region(vma->vm_region);
-	kmem_cache_free(vm_area_cachep, vma);
+	vm_area_free(vma);
 }
 
 /*
@@ -1204,7 +1204,7 @@ unsigned long do_mmap(struct file *file,
 	if (!region)
 		goto error_getting_region;
 
-	vma = kmem_cache_zalloc(vm_area_cachep, GFP_KERNEL);
+	vma = vm_area_alloc(current->mm);
 	if (!vma)
 		goto error_getting_vma;
 
@@ -1212,7 +1212,6 @@ unsigned long do_mmap(struct file *file,
 	region->vm_flags = vm_flags;
 	region->vm_pgoff = pgoff;
 
-	INIT_LIST_HEAD(&vma->anon_vma_chain);
 	vma->vm_flags = vm_flags;
 	vma->vm_pgoff = pgoff;
 
@@ -1368,7 +1367,7 @@ unsigned long do_mmap(struct file *file,
 	kmem_cache_free(vm_region_jar, region);
 	if (vma->vm_file)
 		fput(vma->vm_file);
-	kmem_cache_free(vm_area_cachep, vma);
+	vm_area_free(vma);
 	return ret;
 
 sharing_violation:
@@ -1469,14 +1468,13 @@ int split_vma(struct mm_struct *mm, struct vm_area_struct *vma,
 	if (!region)
 		return -ENOMEM;
 
-	new = kmem_cache_alloc(vm_area_cachep, GFP_KERNEL);
+	new = vm_area_dup(vma);
 	if (!new) {
 		kmem_cache_free(vm_region_jar, region);
 		return -ENOMEM;
 	}
 
 	/* most fields are the same, copy all, and then fixup */
-	*new = *vma;
 	*region = *vma->vm_region;
 	new->vm_region = region;
 

net/caif/caif_dev.c

@@ -131,8 +131,10 @@ static void caif_flow_cb(struct sk_buff *skb)
 	caifd = caif_get(skb->dev);
 
 	WARN_ON(caifd == NULL);
-	if (caifd == NULL)
+	if (!caifd) {
+		rcu_read_unlock();
 		return;
+	}
 
 	caifd_hold(caifd);
 	rcu_read_unlock();

net/core/page_pool.c

@@ -269,7 +269,7 @@ static void __page_pool_empty_ring(struct page_pool *pool)
 	struct page *page;
 
 	/* Empty recycle ring */
-	while ((page = ptr_ring_consume(&pool->ring))) {
+	while ((page = ptr_ring_consume_bh(&pool->ring))) {
 		/* Verify the refcnt invariant of cached pages */
 		if (!(page_ref_count(page) == 1))
 			pr_crit("%s() page_pool refcnt %d violation\n",

net/core/skbuff.c

@@ -3720,6 +3720,7 @@ struct sk_buff *skb_segment(struct sk_buff *head_skb,
 				net_warn_ratelimited(
 					"skb_segment: too many frags: %u %u\n",
 					pos, mss);
+				err = -EINVAL;
 				goto err;
 			}
 
@@ -3753,11 +3754,10 @@ struct sk_buff *skb_segment(struct sk_buff *head_skb,
 
 perform_csum_check:
 		if (!csum) {
-			if (skb_has_shared_frag(nskb)) {
+			if (skb_has_shared_frag(nskb) &&
-				err = __skb_linearize(nskb);
+			    __skb_linearize(nskb))
-				if (err)
 				goto err;
-			}
+
 			if (!nskb->remcsum_offload)
 				nskb->ip_summed = CHECKSUM_NONE;
 			SKB_GSO_CB(nskb)->csum =

net/core/sock.c

@@ -2316,9 +2316,9 @@ int sk_alloc_sg(struct sock *sk, int len, struct scatterlist *sg,
 		pfrag->offset += use;
 
 		sge = sg + sg_curr - 1;
-		if (sg_curr > first_coalesce && sg_page(sg) == pfrag->page &&
+		if (sg_curr > first_coalesce && sg_page(sge) == pfrag->page &&
-		    sg->offset + sg->length == orig_offset) {
+		    sge->offset + sge->length == orig_offset) {
-			sg->length += use;
+			sge->length += use;
 		} else {
 			sge = sg + sg_curr;
 			sg_unmark_end(sge);

net/ipv4/igmp.c

@@ -1200,8 +1200,7 @@ static void igmpv3_del_delrec(struct in_device *in_dev, struct ip_mc_list *im)
 	spin_lock_bh(&im->lock);
 	if (pmc) {
 		im->interface = pmc->interface;
-		im->sfmode = pmc->sfmode;
+		if (im->sfmode == MCAST_INCLUDE) {
-		if (pmc->sfmode == MCAST_INCLUDE) {
 			im->tomb = pmc->tomb;
 			im->sources = pmc->sources;
 			for (psf = im->sources; psf; psf = psf->sf_next)

net/ipv4/ip_output.c

@@ -524,6 +524,8 @@ static void ip_copy_metadata(struct sk_buff *to, struct sk_buff *from)
 	to->dev = from->dev;
 	to->mark = from->mark;
 
+	skb_copy_hash(to, from);
+
 	/* Copy the flags to each fragment. */
 	IPCB(to)->flags = IPCB(from)->flags;
 

net/ipv4/ip_sockglue.c

@@ -150,15 +150,18 @@ static void ip_cmsg_recv_dstaddr(struct msghdr *msg, struct sk_buff *skb)
 {
 	struct sockaddr_in sin;
 	const struct iphdr *iph = ip_hdr(skb);
-	__be16 *ports = (__be16 *)skb_transport_header(skb);
+	__be16 *ports;
+	int end;
 
-	if (skb_transport_offset(skb) + 4 > (int)skb->len)
+	end = skb_transport_offset(skb) + 4;
+	if (end > 0 && !pskb_may_pull(skb, end))
 		return;
 
 	/* All current transport protocols have the port numbers in the
 	 * first four bytes of the transport header and this function is
 	 * written with this assumption in mind.
 	 */
+	ports = (__be16 *)skb_transport_header(skb);
 
 	sin.sin_family = AF_INET;
 	sin.sin_addr.s_addr = iph->daddr;

net/ipv4/tcp_dctcp.c

@@ -129,24 +129,14 @@ static void dctcp_ce_state_0_to_1(struct sock *sk)
 	struct dctcp *ca = inet_csk_ca(sk);
 	struct tcp_sock *tp = tcp_sk(sk);
 
-	/* State has changed from CE=0 to CE=1 and delayed
+	if (!ca->ce_state) {
-	 * ACK has not sent yet.
+		/* State has changed from CE=0 to CE=1, force an immediate
+		 * ACK to reflect the new CE state. If an ACK was delayed,
+		 * send that first to reflect the prior CE state.
 		 */
-	if (!ca->ce_state &&
+		if (inet_csk(sk)->icsk_ack.pending & ICSK_ACK_TIMER)
-	    inet_csk(sk)->icsk_ack.pending & ICSK_ACK_TIMER) {
+			__tcp_send_ack(sk, ca->prior_rcv_nxt);
-		u32 tmp_rcv_nxt;
+		tcp_enter_quickack_mode(sk, 1);
-
-		/* Save current rcv_nxt. */
-		tmp_rcv_nxt = tp->rcv_nxt;
-
-		/* Generate previous ack with CE=0. */
-		tp->ecn_flags &= ~TCP_ECN_DEMAND_CWR;
-		tp->rcv_nxt = ca->prior_rcv_nxt;
-
-		tcp_send_ack(sk);
-
-		/* Recover current rcv_nxt. */
-		tp->rcv_nxt = tmp_rcv_nxt;
 	}
 
 	ca->prior_rcv_nxt = tp->rcv_nxt;
@@ -160,24 +150,14 @@ static void dctcp_ce_state_1_to_0(struct sock *sk)
 	struct dctcp *ca = inet_csk_ca(sk);
 	struct tcp_sock *tp = tcp_sk(sk);
 
-	/* State has changed from CE=1 to CE=0 and delayed
+	if (ca->ce_state) {
-	 * ACK has not sent yet.
+		/* State has changed from CE=1 to CE=0, force an immediate
+		 * ACK to reflect the new CE state. If an ACK was delayed,
+		 * send that first to reflect the prior CE state.
 		 */
-	if (ca->ce_state &&
+		if (inet_csk(sk)->icsk_ack.pending & ICSK_ACK_TIMER)
-	    inet_csk(sk)->icsk_ack.pending & ICSK_ACK_TIMER) {
+			__tcp_send_ack(sk, ca->prior_rcv_nxt);
-		u32 tmp_rcv_nxt;
+		tcp_enter_quickack_mode(sk, 1);
-
-		/* Save current rcv_nxt. */
-		tmp_rcv_nxt = tp->rcv_nxt;
-
-		/* Generate previous ack with CE=1. */
-		tp->ecn_flags |= TCP_ECN_DEMAND_CWR;
-		tp->rcv_nxt = ca->prior_rcv_nxt;
-
-		tcp_send_ack(sk);
-
-		/* Recover current rcv_nxt. */
-		tp->rcv_nxt = tmp_rcv_nxt;
 	}
 
 	ca->prior_rcv_nxt = tp->rcv_nxt;

net/ipv4/tcp_input.c

@@ -216,7 +216,7 @@ static void tcp_incr_quickack(struct sock *sk, unsigned int max_quickacks)
 		icsk->icsk_ack.quick = quickacks;
 }
 
-static void tcp_enter_quickack_mode(struct sock *sk, unsigned int max_quickacks)
+void tcp_enter_quickack_mode(struct sock *sk, unsigned int max_quickacks)
 {
 	struct inet_connection_sock *icsk = inet_csk(sk);
 
@@ -224,6 +224,7 @@ static void tcp_enter_quickack_mode(struct sock *sk, unsigned int max_quickacks)
 	icsk->icsk_ack.pingpong = 0;
 	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.
@@ -4366,6 +4367,23 @@ static bool tcp_try_coalesce(struct sock *sk,
 	return true;
 }
 
+static bool tcp_ooo_try_coalesce(struct sock *sk,
+			     struct sk_buff *to,
+			     struct sk_buff *from,
+			     bool *fragstolen)
+{
+	bool res = tcp_try_coalesce(sk, to, from, fragstolen);
+
+	/* In case tcp_drop() is called later, update to->gso_segs */
+	if (res) {
+		u32 gso_segs = max_t(u16, 1, skb_shinfo(to)->gso_segs) +
+			       max_t(u16, 1, skb_shinfo(from)->gso_segs);
+
+		skb_shinfo(to)->gso_segs = min_t(u32, gso_segs, 0xFFFF);
+	}
+	return res;
+}
+
 static void tcp_drop(struct sock *sk, struct sk_buff *skb)
 {
 	sk_drops_add(sk, skb);
@@ -4489,7 +4507,7 @@ static void tcp_data_queue_ofo(struct sock *sk, struct sk_buff *skb)
 	/* In the typical case, we are adding an skb to the end of the list.
 	 * Use of ooo_last_skb avoids the O(Log(N)) rbtree lookup.
 	 */
-	if (tcp_try_coalesce(sk, tp->ooo_last_skb,
+	if (tcp_ooo_try_coalesce(sk, tp->ooo_last_skb,
 				 skb, &fragstolen)) {
 coalesce_done:
 		tcp_grow_window(sk, skb);
@@ -4518,7 +4536,7 @@ static void tcp_data_queue_ofo(struct sock *sk, struct sk_buff *skb)
 				/* All the bits are present. Drop. */
 				NET_INC_STATS(sock_net(sk),
 					      LINUX_MIB_TCPOFOMERGE);
-				__kfree_skb(skb);
+				tcp_drop(sk, skb);
 				skb = NULL;
 				tcp_dsack_set(sk, seq, end_seq);
 				goto add_sack;
@@ -4537,10 +4555,10 @@ static void tcp_data_queue_ofo(struct sock *sk, struct sk_buff *skb)
 						 TCP_SKB_CB(skb1)->end_seq);
 				NET_INC_STATS(sock_net(sk),
 					      LINUX_MIB_TCPOFOMERGE);
-				__kfree_skb(skb1);
+				tcp_drop(sk, skb1);
 				goto merge_right;
 			}
-		} else if (tcp_try_coalesce(sk, skb1,
+		} else if (tcp_ooo_try_coalesce(sk, skb1,
 						skb, &fragstolen)) {
 			goto coalesce_done;
 		}
@@ -4924,6 +4942,7 @@ tcp_collapse(struct sock *sk, struct sk_buff_head *list, struct rb_root *root,
 static void tcp_collapse_ofo_queue(struct sock *sk)
 {
 	struct tcp_sock *tp = tcp_sk(sk);
+	u32 range_truesize, sum_tiny = 0;
 	struct sk_buff *skb, *head;
 	u32 start, end;
 
@@ -4935,6 +4954,7 @@ static void tcp_collapse_ofo_queue(struct sock *sk)
 	}
 	start = TCP_SKB_CB(skb)->seq;
 	end = TCP_SKB_CB(skb)->end_seq;
+	range_truesize = skb->truesize;
 
 	for (head = skb;;) {
 		skb = skb_rb_next(skb);
@@ -4945,11 +4965,20 @@ static void tcp_collapse_ofo_queue(struct sock *sk)
 		if (!skb ||
 		    after(TCP_SKB_CB(skb)->seq, end) ||
 		    before(TCP_SKB_CB(skb)->end_seq, start)) {
+			/* Do not attempt collapsing tiny skbs */
+			if (range_truesize != head->truesize ||
+			    end - start >= SKB_WITH_OVERHEAD(SK_MEM_QUANTUM)) {
 				tcp_collapse(sk, NULL, &tp->out_of_order_queue,
 					     head, skb, start, end);
+			} else {
+				sum_tiny += range_truesize;
+				if (sum_tiny > sk->sk_rcvbuf >> 3)
+					return;
+			}
 			goto new_range;
 		}
 
+		range_truesize += skb->truesize;
 		if (unlikely(before(TCP_SKB_CB(skb)->seq, start)))
 			start = TCP_SKB_CB(skb)->seq;
 		if (after(TCP_SKB_CB(skb)->end_seq, end))
@@ -4964,6 +4993,7 @@ static void tcp_collapse_ofo_queue(struct sock *sk)
  * 2) not add too big latencies if thousands of packets sit there.
  *    (But if application shrinks SO_RCVBUF, we could still end up
  *     freeing whole queue here)
+ * 3) Drop at least 12.5 % of sk_rcvbuf to avoid malicious attacks.
  *
  * Return true if queue has shrunk.
  */
@@ -4971,20 +5001,26 @@ static bool tcp_prune_ofo_queue(struct sock *sk)
 {
 	struct tcp_sock *tp = tcp_sk(sk);
 	struct rb_node *node, *prev;
+	int goal;
 
 	if (RB_EMPTY_ROOT(&tp->out_of_order_queue))
 		return false;
 
 	NET_INC_STATS(sock_net(sk), LINUX_MIB_OFOPRUNED);
+	goal = sk->sk_rcvbuf >> 3;
 	node = &tp->ooo_last_skb->rbnode;
 	do {
 		prev = rb_prev(node);
 		rb_erase(node, &tp->out_of_order_queue);
+		goal -= rb_to_skb(node)->truesize;
 		tcp_drop(sk, rb_to_skb(node));
+		if (!prev || goal <= 0) {
 			sk_mem_reclaim(sk);
 			if (atomic_read(&sk->sk_rmem_alloc) <= sk->sk_rcvbuf &&
 			    !tcp_under_memory_pressure(sk))
 				break;
+			goal = sk->sk_rcvbuf >> 3;
+		}
 		node = prev;
 	} while (node);
 	tp->ooo_last_skb = rb_to_skb(prev);
@@ -5019,6 +5055,9 @@ static int tcp_prune_queue(struct sock *sk)
 	else if (tcp_under_memory_pressure(sk))
 		tp->rcv_ssthresh = min(tp->rcv_ssthresh, 4U * tp->advmss);
 
+	if (atomic_read(&sk->sk_rmem_alloc) <= sk->sk_rcvbuf)
+		return 0;
+
 	tcp_collapse_ofo_queue(sk);
 	if (!skb_queue_empty(&sk->sk_receive_queue))
 		tcp_collapse(sk, &sk->sk_receive_queue, NULL,