From 9bff9479e143d4d0497fa408396c5fc3d7786f04 Mon Sep 17 00:00:00 2001 From: Qiuxu Zhuo Date: Fri, 11 Jun 2021 10:01:18 -0700 Subject: [PATCH 001/342] EDAC/skx_common: Add new ADXL components for 2-level memory [ Upstream commit 2f4348e5a86198704368a699a7c4cdeb21d569f5 ] Some Intel servers may configure memory in 2 levels, using fast "near" memory (e.g. DDR) as a cache for larger, slower, "far" memory (e.g. 3D X-point). In these configurations the BIOS ADXL address translation for an address in a 2-level memory range will provide details of both the "near" and far components. Current exported ADXL components are only for 1-level memory system or for 2nd level memory of 2-level memory system. So add new ADXL components for 1st level memory of 2-level memory system to fully support 2-level memory system and the detection of memory error source(1st level memory or 2nd level memory). Signed-off-by: Qiuxu Zhuo Signed-off-by: Tony Luck Link: https://lore.kernel.org/r/20210611170123.1057025-2-tony.luck@intel.com Stable-dep-of: 123b15863550 ("EDAC, i10nm: make skx_common.o a separate module") Signed-off-by: Sasha Levin --- drivers/edac/skx_common.c | 67 ++++++++++++++++++++++++++++++++------- drivers/edac/skx_common.h | 11 +++++++ 2 files changed, 67 insertions(+), 11 deletions(-) diff --git a/drivers/edac/skx_common.c b/drivers/edac/skx_common.c index 2b4ce8e5ac2f..300bfd8383e1 100644 --- a/drivers/edac/skx_common.c +++ b/drivers/edac/skx_common.c @@ -23,10 +23,13 @@ #include "skx_common.h" static const char * const component_names[] = { - [INDEX_SOCKET] = "ProcessorSocketId", - [INDEX_MEMCTRL] = "MemoryControllerId", - [INDEX_CHANNEL] = "ChannelId", - [INDEX_DIMM] = "DimmSlotId", + [INDEX_SOCKET] = "ProcessorSocketId", + [INDEX_MEMCTRL] = "MemoryControllerId", + [INDEX_CHANNEL] = "ChannelId", + [INDEX_DIMM] = "DimmSlotId", + [INDEX_NM_MEMCTRL] = "NmMemoryControllerId", + [INDEX_NM_CHANNEL] = "NmChannelId", + [INDEX_NM_DIMM] = "NmDimmSlotId", }; static int component_indices[ARRAY_SIZE(component_names)]; @@ -34,12 +37,14 @@ static int adxl_component_count; static const char * const *adxl_component_names; static u64 *adxl_values; static char *adxl_msg; +static unsigned long adxl_nm_bitmap; static char skx_msg[MSG_SIZE]; static skx_decode_f skx_decode; static skx_show_retry_log_f skx_show_retry_rd_err_log; static u64 skx_tolm, skx_tohm; static LIST_HEAD(dev_edac_list); +static bool skx_mem_cfg_2lm; int __init skx_adxl_get(void) { @@ -56,14 +61,25 @@ int __init skx_adxl_get(void) for (j = 0; names[j]; j++) { if (!strcmp(component_names[i], names[j])) { component_indices[i] = j; + + if (i >= INDEX_NM_FIRST) + adxl_nm_bitmap |= 1 << i; + break; } } - if (!names[j]) + if (!names[j] && i < INDEX_NM_FIRST) goto err; } + if (skx_mem_cfg_2lm) { + if (!adxl_nm_bitmap) + skx_printk(KERN_NOTICE, "Not enough ADXL components for 2-level memory.\n"); + else + edac_dbg(2, "adxl_nm_bitmap: 0x%lx\n", adxl_nm_bitmap); + } + adxl_component_names = names; while (*names++) adxl_component_count++; @@ -99,7 +115,7 @@ void __exit skx_adxl_put(void) kfree(adxl_msg); } -static bool skx_adxl_decode(struct decoded_addr *res) +static bool skx_adxl_decode(struct decoded_addr *res, bool error_in_1st_level_mem) { struct skx_dev *d; int i, len = 0; @@ -116,11 +132,20 @@ static bool skx_adxl_decode(struct decoded_addr *res) } res->socket = (int)adxl_values[component_indices[INDEX_SOCKET]]; - res->imc = (int)adxl_values[component_indices[INDEX_MEMCTRL]]; - res->channel = (int)adxl_values[component_indices[INDEX_CHANNEL]]; - res->dimm = (int)adxl_values[component_indices[INDEX_DIMM]]; + if (error_in_1st_level_mem) { + res->imc = (adxl_nm_bitmap & BIT_NM_MEMCTRL) ? + (int)adxl_values[component_indices[INDEX_NM_MEMCTRL]] : -1; + res->channel = (adxl_nm_bitmap & BIT_NM_CHANNEL) ? + (int)adxl_values[component_indices[INDEX_NM_CHANNEL]] : -1; + res->dimm = (adxl_nm_bitmap & BIT_NM_DIMM) ? + (int)adxl_values[component_indices[INDEX_NM_DIMM]] : -1; + } else { + res->imc = (int)adxl_values[component_indices[INDEX_MEMCTRL]]; + res->channel = (int)adxl_values[component_indices[INDEX_CHANNEL]]; + res->dimm = (int)adxl_values[component_indices[INDEX_DIMM]]; + } - if (res->imc > NUM_IMC - 1) { + if (res->imc > NUM_IMC - 1 || res->imc < 0) { skx_printk(KERN_ERR, "Bad imc %d\n", res->imc); return false; } @@ -151,6 +176,11 @@ static bool skx_adxl_decode(struct decoded_addr *res) return true; } +void skx_set_mem_cfg(bool mem_cfg_2lm) +{ + skx_mem_cfg_2lm = mem_cfg_2lm; +} + void skx_set_decode(skx_decode_f decode, skx_show_retry_log_f show_retry_log) { skx_decode = decode; @@ -565,6 +595,21 @@ static void skx_mce_output_error(struct mem_ctl_info *mci, optype, skx_msg); } +static bool skx_error_in_1st_level_mem(const struct mce *m) +{ + u32 errcode; + + if (!skx_mem_cfg_2lm) + return false; + + errcode = GET_BITFIELD(m->status, 0, 15); + + if ((errcode & 0xef80) != 0x280) + return false; + + return true; +} + int skx_mce_check_error(struct notifier_block *nb, unsigned long val, void *data) { @@ -584,7 +629,7 @@ int skx_mce_check_error(struct notifier_block *nb, unsigned long val, res.addr = mce->addr; if (adxl_component_count) { - if (!skx_adxl_decode(&res)) + if (!skx_adxl_decode(&res, skx_error_in_1st_level_mem(mce))) return NOTIFY_DONE; } else if (!skx_decode || !skx_decode(&res)) { return NOTIFY_DONE; diff --git a/drivers/edac/skx_common.h b/drivers/edac/skx_common.h index 78f8c1de0b71..9773bd8e0532 100644 --- a/drivers/edac/skx_common.h +++ b/drivers/edac/skx_common.h @@ -9,6 +9,8 @@ #ifndef _SKX_COMM_EDAC_H #define _SKX_COMM_EDAC_H +#include + #define MSG_SIZE 1024 /* @@ -90,9 +92,17 @@ enum { INDEX_MEMCTRL, INDEX_CHANNEL, INDEX_DIMM, + INDEX_NM_FIRST, + INDEX_NM_MEMCTRL = INDEX_NM_FIRST, + INDEX_NM_CHANNEL, + INDEX_NM_DIMM, INDEX_MAX }; +#define BIT_NM_MEMCTRL BIT_ULL(INDEX_NM_MEMCTRL) +#define BIT_NM_CHANNEL BIT_ULL(INDEX_NM_CHANNEL) +#define BIT_NM_DIMM BIT_ULL(INDEX_NM_DIMM) + struct decoded_addr { struct skx_dev *dev; u64 addr; @@ -127,6 +137,7 @@ typedef void (*skx_show_retry_log_f)(struct decoded_addr *res, char *msg, int le int __init skx_adxl_get(void); void __exit skx_adxl_put(void); void skx_set_decode(skx_decode_f decode, skx_show_retry_log_f show_retry_log); +void skx_set_mem_cfg(bool mem_cfg_2lm); int skx_get_src_id(struct skx_dev *d, int off, u8 *id); int skx_get_node_id(struct skx_dev *d, u8 *id); From 3070e81609169b316e3e3f226456950238338d43 Mon Sep 17 00:00:00 2001 From: Arnd Bergmann Date: Wed, 29 May 2024 11:51:11 +0200 Subject: [PATCH 002/342] EDAC, i10nm: make skx_common.o a separate module [ Upstream commit 123b158635505c89ed0d3ef45c5845ff9030a466 ] Commit 598afa050403 ("kbuild: warn objects shared among multiple modules") was added to track down cases where the same object is linked into multiple modules. This can cause serious problems if some modules are builtin while others are not. That test triggers this warning: scripts/Makefile.build:236: drivers/edac/Makefile: skx_common.o is added to multiple modules: i10nm_edac skx_edac Make this a separate module instead. [Tony: Added more background details to commit message] Fixes: d4dc89d069aa ("EDAC, i10nm: Add a driver for Intel 10nm server processors") Signed-off-by: Arnd Bergmann Signed-off-by: Tony Luck Link: https://lore.kernel.org/all/20240529095132.1929397-1-arnd@kernel.org/ Signed-off-by: Sasha Levin --- drivers/edac/Makefile | 10 ++++++---- drivers/edac/skx_common.c | 21 +++++++++++++++++++-- drivers/edac/skx_common.h | 4 ++-- 3 files changed, 27 insertions(+), 8 deletions(-) diff --git a/drivers/edac/Makefile b/drivers/edac/Makefile index 3a849168780d..eec69c885c1d 100644 --- a/drivers/edac/Makefile +++ b/drivers/edac/Makefile @@ -58,11 +58,13 @@ obj-$(CONFIG_EDAC_MPC85XX) += mpc85xx_edac_mod.o layerscape_edac_mod-y := fsl_ddr_edac.o layerscape_edac.o obj-$(CONFIG_EDAC_LAYERSCAPE) += layerscape_edac_mod.o -skx_edac-y := skx_common.o skx_base.o -obj-$(CONFIG_EDAC_SKX) += skx_edac.o +skx_edac_common-y := skx_common.o -i10nm_edac-y := skx_common.o i10nm_base.o -obj-$(CONFIG_EDAC_I10NM) += i10nm_edac.o +skx_edac-y := skx_base.o +obj-$(CONFIG_EDAC_SKX) += skx_edac.o skx_edac_common.o + +i10nm_edac-y := i10nm_base.o +obj-$(CONFIG_EDAC_I10NM) += i10nm_edac.o skx_edac_common.o obj-$(CONFIG_EDAC_MV64X60) += mv64x60_edac.o obj-$(CONFIG_EDAC_CELL) += cell_edac.o diff --git a/drivers/edac/skx_common.c b/drivers/edac/skx_common.c index 300bfd8383e1..b585cbe3eff9 100644 --- a/drivers/edac/skx_common.c +++ b/drivers/edac/skx_common.c @@ -46,7 +46,7 @@ static u64 skx_tolm, skx_tohm; static LIST_HEAD(dev_edac_list); static bool skx_mem_cfg_2lm; -int __init skx_adxl_get(void) +int skx_adxl_get(void) { const char * const *names; int i, j; @@ -108,12 +108,14 @@ int __init skx_adxl_get(void) return -ENODEV; } +EXPORT_SYMBOL_GPL(skx_adxl_get); -void __exit skx_adxl_put(void) +void skx_adxl_put(void) { kfree(adxl_values); kfree(adxl_msg); } +EXPORT_SYMBOL_GPL(skx_adxl_put); static bool skx_adxl_decode(struct decoded_addr *res, bool error_in_1st_level_mem) { @@ -180,12 +182,14 @@ void skx_set_mem_cfg(bool mem_cfg_2lm) { skx_mem_cfg_2lm = mem_cfg_2lm; } +EXPORT_SYMBOL_GPL(skx_set_mem_cfg); void skx_set_decode(skx_decode_f decode, skx_show_retry_log_f show_retry_log) { skx_decode = decode; skx_show_retry_rd_err_log = show_retry_log; } +EXPORT_SYMBOL_GPL(skx_set_decode); int skx_get_src_id(struct skx_dev *d, int off, u8 *id) { @@ -199,6 +203,7 @@ int skx_get_src_id(struct skx_dev *d, int off, u8 *id) *id = GET_BITFIELD(reg, 12, 14); return 0; } +EXPORT_SYMBOL_GPL(skx_get_src_id); int skx_get_node_id(struct skx_dev *d, u8 *id) { @@ -212,6 +217,7 @@ int skx_get_node_id(struct skx_dev *d, u8 *id) *id = GET_BITFIELD(reg, 0, 2); return 0; } +EXPORT_SYMBOL_GPL(skx_get_node_id); static int get_width(u32 mtr) { @@ -277,6 +283,7 @@ int skx_get_all_bus_mappings(struct res_config *cfg, struct list_head **list) *list = &dev_edac_list; return ndev; } +EXPORT_SYMBOL_GPL(skx_get_all_bus_mappings); int skx_get_hi_lo(unsigned int did, int off[], u64 *tolm, u64 *tohm) { @@ -316,6 +323,7 @@ int skx_get_hi_lo(unsigned int did, int off[], u64 *tolm, u64 *tohm) pci_dev_put(pdev); return -ENODEV; } +EXPORT_SYMBOL_GPL(skx_get_hi_lo); static int skx_get_dimm_attr(u32 reg, int lobit, int hibit, int add, int minval, int maxval, const char *name) @@ -369,6 +377,7 @@ int skx_get_dimm_info(u32 mtr, u32 mcmtr, u32 amap, struct dimm_info *dimm, return 1; } +EXPORT_SYMBOL_GPL(skx_get_dimm_info); int skx_get_nvdimm_info(struct dimm_info *dimm, struct skx_imc *imc, int chan, int dimmno, const char *mod_str) @@ -417,6 +426,7 @@ int skx_get_nvdimm_info(struct dimm_info *dimm, struct skx_imc *imc, return (size == 0 || size == ~0ull) ? 0 : 1; } +EXPORT_SYMBOL_GPL(skx_get_nvdimm_info); int skx_register_mci(struct skx_imc *imc, struct pci_dev *pdev, const char *ctl_name, const char *mod_str, @@ -484,6 +494,7 @@ int skx_register_mci(struct skx_imc *imc, struct pci_dev *pdev, imc->mci = NULL; return rc; } +EXPORT_SYMBOL_GPL(skx_register_mci); static void skx_unregister_mci(struct skx_imc *imc) { @@ -663,6 +674,7 @@ int skx_mce_check_error(struct notifier_block *nb, unsigned long val, mce->kflags |= MCE_HANDLED_EDAC; return NOTIFY_DONE; } +EXPORT_SYMBOL_GPL(skx_mce_check_error); void skx_remove(void) { @@ -698,3 +710,8 @@ void skx_remove(void) kfree(d); } } +EXPORT_SYMBOL_GPL(skx_remove); + +MODULE_LICENSE("GPL v2"); +MODULE_AUTHOR("Tony Luck"); +MODULE_DESCRIPTION("MC Driver for Intel server processors"); diff --git a/drivers/edac/skx_common.h b/drivers/edac/skx_common.h index 9773bd8e0532..b93c33ac8e60 100644 --- a/drivers/edac/skx_common.h +++ b/drivers/edac/skx_common.h @@ -134,8 +134,8 @@ typedef int (*get_dimm_config_f)(struct mem_ctl_info *mci); typedef bool (*skx_decode_f)(struct decoded_addr *res); typedef void (*skx_show_retry_log_f)(struct decoded_addr *res, char *msg, int len); -int __init skx_adxl_get(void); -void __exit skx_adxl_put(void); +int skx_adxl_get(void); +void skx_adxl_put(void); void skx_set_decode(skx_decode_f decode, skx_show_retry_log_f show_retry_log); void skx_set_mem_cfg(bool mem_cfg_2lm); From c0748b7684a96fc61900a53ec96f9cec4a0c702e Mon Sep 17 00:00:00 2001 From: Tzung-Bi Shih Date: Tue, 11 Jun 2024 11:31:10 +0000 Subject: [PATCH 003/342] platform/chrome: cros_ec_debugfs: fix wrong EC message version [ Upstream commit c2a28647bbb4e0894e8824362410f72b06ac57a4 ] ec_read_version_supported() uses ec_params_get_cmd_versions_v1 but it wrongly uses message version 0. Fix it. Fixes: e86264595225 ("mfd: cros_ec: add debugfs, console log file") Reviewed-by: Guenter Roeck Link: https://lore.kernel.org/r/20240611113110.16955-1-tzungbi@kernel.org Signed-off-by: Tzung-Bi Shih Signed-off-by: Sasha Levin --- drivers/platform/chrome/cros_ec_debugfs.c | 1 + 1 file changed, 1 insertion(+) diff --git a/drivers/platform/chrome/cros_ec_debugfs.c b/drivers/platform/chrome/cros_ec_debugfs.c index 0dbceee87a4b..2928c3cb3785 100644 --- a/drivers/platform/chrome/cros_ec_debugfs.c +++ b/drivers/platform/chrome/cros_ec_debugfs.c @@ -326,6 +326,7 @@ static int ec_read_version_supported(struct cros_ec_dev *ec) if (!msg) return 0; + msg->version = 1; msg->command = EC_CMD_GET_CMD_VERSIONS + ec->cmd_offset; msg->outsize = sizeof(*params); msg->insize = sizeof(*response); From 97795f23a8ab9bceeb51f91fa09cbe24998e1fe2 Mon Sep 17 00:00:00 2001 From: Chao Yu Date: Fri, 7 Jun 2024 22:23:04 +0800 Subject: [PATCH 004/342] hfsplus: fix to avoid false alarm of circular locking MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit [ Upstream commit be4edd1642ee205ed7bbf66edc0453b1be1fb8d7 ] Syzbot report potential ABBA deadlock as below: loop0: detected capacity change from 0 to 1024 ====================================================== WARNING: possible circular locking dependency detected 6.9.0-syzkaller-10323-g8f6a15f095a6 #0 Not tainted ------------------------------------------------------ syz-executor171/5344 is trying to acquire lock: ffff88807cb980b0 (&tree->tree_lock){+.+.}-{3:3}, at: hfsplus_file_truncate+0x811/0xb50 fs/hfsplus/extents.c:595 but task is already holding lock: ffff88807a930108 (&HFSPLUS_I(inode)->extents_lock){+.+.}-{3:3}, at: hfsplus_file_truncate+0x2da/0xb50 fs/hfsplus/extents.c:576 which lock already depends on the new lock. the existing dependency chain (in reverse order) is: -> #1 (&HFSPLUS_I(inode)->extents_lock){+.+.}-{3:3}: lock_acquire+0x1ed/0x550 kernel/locking/lockdep.c:5754 __mutex_lock_common kernel/locking/mutex.c:608 [inline] __mutex_lock+0x136/0xd70 kernel/locking/mutex.c:752 hfsplus_file_extend+0x21b/0x1b70 fs/hfsplus/extents.c:457 hfsplus_bmap_reserve+0x105/0x4e0 fs/hfsplus/btree.c:358 hfsplus_rename_cat+0x1d0/0x1050 fs/hfsplus/catalog.c:456 hfsplus_rename+0x12e/0x1c0 fs/hfsplus/dir.c:552 vfs_rename+0xbdb/0xf00 fs/namei.c:4887 do_renameat2+0xd94/0x13f0 fs/namei.c:5044 __do_sys_rename fs/namei.c:5091 [inline] __se_sys_rename fs/namei.c:5089 [inline] __x64_sys_rename+0x86/0xa0 fs/namei.c:5089 do_syscall_x64 arch/x86/entry/common.c:52 [inline] do_syscall_64+0xf5/0x240 arch/x86/entry/common.c:83 entry_SYSCALL_64_after_hwframe+0x77/0x7f -> #0 (&tree->tree_lock){+.+.}-{3:3}: check_prev_add kernel/locking/lockdep.c:3134 [inline] check_prevs_add kernel/locking/lockdep.c:3253 [inline] validate_chain+0x18cb/0x58e0 kernel/locking/lockdep.c:3869 __lock_acquire+0x1346/0x1fd0 kernel/locking/lockdep.c:5137 lock_acquire+0x1ed/0x550 kernel/locking/lockdep.c:5754 __mutex_lock_common kernel/locking/mutex.c:608 [inline] __mutex_lock+0x136/0xd70 kernel/locking/mutex.c:752 hfsplus_file_truncate+0x811/0xb50 fs/hfsplus/extents.c:595 hfsplus_setattr+0x1ce/0x280 fs/hfsplus/inode.c:265 notify_change+0xb9d/0xe70 fs/attr.c:497 do_truncate+0x220/0x310 fs/open.c:65 handle_truncate fs/namei.c:3308 [inline] do_open fs/namei.c:3654 [inline] path_openat+0x2a3d/0x3280 fs/namei.c:3807 do_filp_open+0x235/0x490 fs/namei.c:3834 do_sys_openat2+0x13e/0x1d0 fs/open.c:1406 do_sys_open fs/open.c:1421 [inline] __do_sys_creat fs/open.c:1497 [inline] __se_sys_creat fs/open.c:1491 [inline] __x64_sys_creat+0x123/0x170 fs/open.c:1491 do_syscall_x64 arch/x86/entry/common.c:52 [inline] do_syscall_64+0xf5/0x240 arch/x86/entry/common.c:83 entry_SYSCALL_64_after_hwframe+0x77/0x7f other info that might help us debug this: Possible unsafe locking scenario: CPU0 CPU1 ---- ---- lock(&HFSPLUS_I(inode)->extents_lock); lock(&tree->tree_lock); lock(&HFSPLUS_I(inode)->extents_lock); lock(&tree->tree_lock); This is a false alarm as tree_lock mutex are different, one is from sbi->cat_tree, and another is from sbi->ext_tree: Thread A Thread B - hfsplus_rename - hfsplus_rename_cat - hfs_find_init - mutext_lock(cat_tree->tree_lock) - hfsplus_setattr - hfsplus_file_truncate - mutex_lock(hip->extents_lock) - hfs_find_init - mutext_lock(ext_tree->tree_lock) - hfs_bmap_reserve - hfsplus_file_extend - mutex_lock(hip->extents_lock) So, let's call mutex_lock_nested for tree_lock mutex lock, and pass correct lock class for it. Fixes: 31651c607151 ("hfsplus: avoid deadlock on file truncation") Reported-by: syzbot+6030b3b1b9bf70e538c4@syzkaller.appspotmail.com Closes: https://lore.kernel.org/linux-fsdevel/000000000000e37a4005ef129563@google.com Cc: Ernesto A. Fernández Signed-off-by: Chao Yu Link: https://lore.kernel.org/r/20240607142304.455441-1-chao@kernel.org Signed-off-by: Christian Brauner Signed-off-by: Sasha Levin --- fs/hfsplus/bfind.c | 15 ++------------- fs/hfsplus/extents.c | 9 ++++++--- fs/hfsplus/hfsplus_fs.h | 21 +++++++++++++++++++++ 3 files changed, 29 insertions(+), 16 deletions(-) diff --git a/fs/hfsplus/bfind.c b/fs/hfsplus/bfind.c index ca2ba8c9f82e..901e83d65d20 100644 --- a/fs/hfsplus/bfind.c +++ b/fs/hfsplus/bfind.c @@ -25,19 +25,8 @@ int hfs_find_init(struct hfs_btree *tree, struct hfs_find_data *fd) fd->key = ptr + tree->max_key_len + 2; hfs_dbg(BNODE_REFS, "find_init: %d (%p)\n", tree->cnid, __builtin_return_address(0)); - switch (tree->cnid) { - case HFSPLUS_CAT_CNID: - mutex_lock_nested(&tree->tree_lock, CATALOG_BTREE_MUTEX); - break; - case HFSPLUS_EXT_CNID: - mutex_lock_nested(&tree->tree_lock, EXTENTS_BTREE_MUTEX); - break; - case HFSPLUS_ATTR_CNID: - mutex_lock_nested(&tree->tree_lock, ATTR_BTREE_MUTEX); - break; - default: - BUG(); - } + mutex_lock_nested(&tree->tree_lock, + hfsplus_btree_lock_class(tree)); return 0; } diff --git a/fs/hfsplus/extents.c b/fs/hfsplus/extents.c index 7054a542689f..c95a2f0ed4a7 100644 --- a/fs/hfsplus/extents.c +++ b/fs/hfsplus/extents.c @@ -430,7 +430,8 @@ int hfsplus_free_fork(struct super_block *sb, u32 cnid, hfsplus_free_extents(sb, ext_entry, total_blocks - start, total_blocks); total_blocks = start; - mutex_lock(&fd.tree->tree_lock); + mutex_lock_nested(&fd.tree->tree_lock, + hfsplus_btree_lock_class(fd.tree)); } while (total_blocks > blocks); hfs_find_exit(&fd); @@ -592,7 +593,8 @@ void hfsplus_file_truncate(struct inode *inode) alloc_cnt, alloc_cnt - blk_cnt); hfsplus_dump_extent(hip->first_extents); hip->first_blocks = blk_cnt; - mutex_lock(&fd.tree->tree_lock); + mutex_lock_nested(&fd.tree->tree_lock, + hfsplus_btree_lock_class(fd.tree)); break; } res = __hfsplus_ext_cache_extent(&fd, inode, alloc_cnt); @@ -606,7 +608,8 @@ void hfsplus_file_truncate(struct inode *inode) hfsplus_free_extents(sb, hip->cached_extents, alloc_cnt - start, alloc_cnt - blk_cnt); hfsplus_dump_extent(hip->cached_extents); - mutex_lock(&fd.tree->tree_lock); + mutex_lock_nested(&fd.tree->tree_lock, + hfsplus_btree_lock_class(fd.tree)); if (blk_cnt > start) { hip->extent_state |= HFSPLUS_EXT_DIRTY; break; diff --git a/fs/hfsplus/hfsplus_fs.h b/fs/hfsplus/hfsplus_fs.h index c438680ef9f7..bfbe88e804eb 100644 --- a/fs/hfsplus/hfsplus_fs.h +++ b/fs/hfsplus/hfsplus_fs.h @@ -557,6 +557,27 @@ static inline __be32 __hfsp_ut2mt(time64_t ut) return cpu_to_be32(lower_32_bits(ut) + HFSPLUS_UTC_OFFSET); } +static inline enum hfsplus_btree_mutex_classes +hfsplus_btree_lock_class(struct hfs_btree *tree) +{ + enum hfsplus_btree_mutex_classes class; + + switch (tree->cnid) { + case HFSPLUS_CAT_CNID: + class = CATALOG_BTREE_MUTEX; + break; + case HFSPLUS_EXT_CNID: + class = EXTENTS_BTREE_MUTEX; + break; + case HFSPLUS_ATTR_CNID: + class = ATTR_BTREE_MUTEX; + break; + default: + BUG(); + } + return class; +} + /* compatibility */ #define hfsp_mt2ut(t) (struct timespec64){ .tv_sec = __hfsp_mt2ut(t) } #define hfsp_ut2mt(t) __hfsp_ut2mt((t).tv_sec) From e2fdf7b79f08e05934efccbc74158803aa5d14ef Mon Sep 17 00:00:00 2001 From: =?UTF-8?q?Ilpo=20J=C3=A4rvinen?= Date: Mon, 27 May 2024 15:55:35 +0300 Subject: [PATCH 005/342] x86/of: Return consistent error type from x86_of_pci_irq_enable() MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit [ Upstream commit ec0b4c4d45cf7cf9a6c9626a494a89cb1ae7c645 ] x86_of_pci_irq_enable() returns PCIBIOS_* code received from pci_read_config_byte() directly and also -EINVAL which are not compatible error types. x86_of_pci_irq_enable() is used as (*pcibios_enable_irq) function which should not return PCIBIOS_* codes. Convert the PCIBIOS_* return code from pci_read_config_byte() into normal errno using pcibios_err_to_errno(). Fixes: 96e0a0797eba ("x86: dtb: Add support for PCI devices backed by dtb nodes") Signed-off-by: Ilpo Järvinen Signed-off-by: Borislav Petkov (AMD) Link: https://lore.kernel.org/r/20240527125538.13620-1-ilpo.jarvinen@linux.intel.com Signed-off-by: Sasha Levin --- arch/x86/kernel/devicetree.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/arch/x86/kernel/devicetree.c b/arch/x86/kernel/devicetree.c index ddffd80f5c52..2d654fdf001d 100644 --- a/arch/x86/kernel/devicetree.c +++ b/arch/x86/kernel/devicetree.c @@ -92,7 +92,7 @@ static int x86_of_pci_irq_enable(struct pci_dev *dev) ret = pci_read_config_byte(dev, PCI_INTERRUPT_PIN, &pin); if (ret) - return ret; + return pcibios_err_to_errno(ret); if (!pin) return 0; From c995bea85e2e5ae98ea81a99841f9f7d621fd031 Mon Sep 17 00:00:00 2001 From: =?UTF-8?q?Ilpo=20J=C3=A4rvinen?= Date: Mon, 27 May 2024 15:55:36 +0300 Subject: [PATCH 006/342] x86/pci/intel_mid_pci: Fix PCIBIOS_* return code handling MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit [ Upstream commit 724852059e97c48557151b3aa4af424614819752 ] intel_mid_pci_irq_enable() uses pci_read_config_byte() that returns PCIBIOS_* codes. The error handling, however, assumes the codes are normal errnos because it checks for < 0. intel_mid_pci_irq_enable() also returns the PCIBIOS_* code back to the caller but the function is used as the (*pcibios_enable_irq) function which should return normal errnos. Convert the error check to plain non-zero check which works for PCIBIOS_* return codes and convert the PCIBIOS_* return code using pcibios_err_to_errno() into normal errno before returning it. Fixes: 5b395e2be6c4 ("x86/platform/intel-mid: Make IRQ allocation a bit more flexible") Signed-off-by: Ilpo Järvinen Signed-off-by: Borislav Petkov (AMD) Reviewed-by: Andy Shevchenko Link: https://lore.kernel.org/r/20240527125538.13620-2-ilpo.jarvinen@linux.intel.com Signed-off-by: Sasha Levin --- arch/x86/pci/intel_mid_pci.c | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-) diff --git a/arch/x86/pci/intel_mid_pci.c b/arch/x86/pci/intel_mid_pci.c index 24ca4ee2802f..3399dcdd526c 100644 --- a/arch/x86/pci/intel_mid_pci.c +++ b/arch/x86/pci/intel_mid_pci.c @@ -223,9 +223,9 @@ static int intel_mid_pci_irq_enable(struct pci_dev *dev) return 0; ret = pci_read_config_byte(dev, PCI_INTERRUPT_LINE, &gsi); - if (ret < 0) { + if (ret) { dev_warn(&dev->dev, "Failed to read interrupt line: %d\n", ret); - return ret; + return pcibios_err_to_errno(ret); } switch (intel_mid_identify_cpu()) { From 010441f08347406c57de626278cee027e20580ef Mon Sep 17 00:00:00 2001 From: =?UTF-8?q?Ilpo=20J=C3=A4rvinen?= Date: Mon, 27 May 2024 15:55:37 +0300 Subject: [PATCH 007/342] x86/pci/xen: Fix PCIBIOS_* return code handling MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit [ Upstream commit e9d7b435dfaec58432f4106aaa632bf39f52ce9f ] xen_pcifront_enable_irq() uses pci_read_config_byte() that returns PCIBIOS_* codes. The error handling, however, assumes the codes are normal errnos because it checks for < 0. xen_pcifront_enable_irq() also returns the PCIBIOS_* code back to the caller but the function is used as the (*pcibios_enable_irq) function which should return normal errnos. Convert the error check to plain non-zero check which works for PCIBIOS_* return codes and convert the PCIBIOS_* return code using pcibios_err_to_errno() into normal errno before returning it. Fixes: 3f2a230caf21 ("xen: handled remapped IRQs when enabling a pcifront PCI device.") Signed-off-by: Ilpo Järvinen Signed-off-by: Borislav Petkov (AMD) Reviewed-by: Juergen Gross Link: https://lore.kernel.org/r/20240527125538.13620-3-ilpo.jarvinen@linux.intel.com Signed-off-by: Sasha Levin --- arch/x86/pci/xen.c | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-) diff --git a/arch/x86/pci/xen.c b/arch/x86/pci/xen.c index 326d6d173733..cbe9ab42cbeb 100644 --- a/arch/x86/pci/xen.c +++ b/arch/x86/pci/xen.c @@ -37,10 +37,10 @@ static int xen_pcifront_enable_irq(struct pci_dev *dev) u8 gsi; rc = pci_read_config_byte(dev, PCI_INTERRUPT_LINE, &gsi); - if (rc < 0) { + if (rc) { dev_warn(&dev->dev, "Xen PCI: failed to read interrupt line: %d\n", rc); - return rc; + return pcibios_err_to_errno(rc); } /* In PV DomU the Xen PCI backend puts the PIRQ in the interrupt line.*/ pirq = gsi; From 685976438b640897236604d8423b7a62ba28ce9a Mon Sep 17 00:00:00 2001 From: =?UTF-8?q?Ilpo=20J=C3=A4rvinen?= Date: Mon, 27 May 2024 15:55:38 +0300 Subject: [PATCH 008/342] x86/platform/iosf_mbi: Convert PCIBIOS_* return codes to errnos MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit [ Upstream commit 7821fa101eab529521aa4b724bf708149d70820c ] iosf_mbi_pci_{read,write}_mdr() use pci_{read,write}_config_dword() that return PCIBIOS_* codes but functions also return -ENODEV which are not compatible error codes. As neither of the functions are related to PCI read/write functions, they should return normal errnos. Convert PCIBIOS_* returns code using pcibios_err_to_errno() into normal errno before returning it. Fixes: 46184415368a ("arch: x86: New MailBox support driver for Intel SOC's") Signed-off-by: Ilpo Järvinen Signed-off-by: Borislav Petkov (AMD) Link: https://lore.kernel.org/r/20240527125538.13620-4-ilpo.jarvinen@linux.intel.com Signed-off-by: Sasha Levin --- arch/x86/platform/intel/iosf_mbi.c | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-) diff --git a/arch/x86/platform/intel/iosf_mbi.c b/arch/x86/platform/intel/iosf_mbi.c index 526f70f27c1c..70a1c3877f8e 100644 --- a/arch/x86/platform/intel/iosf_mbi.c +++ b/arch/x86/platform/intel/iosf_mbi.c @@ -62,7 +62,7 @@ static int iosf_mbi_pci_read_mdr(u32 mcrx, u32 mcr, u32 *mdr) fail_read: dev_err(&mbi_pdev->dev, "PCI config access failed with %d\n", result); - return result; + return pcibios_err_to_errno(result); } static int iosf_mbi_pci_write_mdr(u32 mcrx, u32 mcr, u32 mdr) @@ -91,7 +91,7 @@ static int iosf_mbi_pci_write_mdr(u32 mcrx, u32 mcr, u32 mdr) fail_write: dev_err(&mbi_pdev->dev, "PCI config access failed with %d\n", result); - return result; + return pcibios_err_to_errno(result); } int iosf_mbi_read(u8 port, u8 opcode, u32 offset, u32 *mdr) From d8571b9a83d140e0998bfd3bb28021ce07a56459 Mon Sep 17 00:00:00 2001 From: Wayne Tung Date: Mon, 1 Jul 2024 15:32:52 +0800 Subject: [PATCH 009/342] hwmon: (adt7475) Fix default duty on fan is disabled [ Upstream commit 39b24cced70fdc336dbc0070f8b3bde61d8513a8 ] According to the comments on fan is disabled, we change to manual mode and set the duty cycle to 0. For setting the duty cycle part, the register is wrong. Fix it. Fixes: 1c301fc5394f ("hwmon: Add a driver for the ADT7475 hardware monitoring chip") Signed-off-by: Wayne Tung Link: https://lore.kernel.org/r/20240701073252.317397-1-chineweff@gmail.com Signed-off-by: Guenter Roeck Signed-off-by: Sasha Levin --- drivers/hwmon/adt7475.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/drivers/hwmon/adt7475.c b/drivers/hwmon/adt7475.c index 22e314725def..b4c0f01f52c4 100644 --- a/drivers/hwmon/adt7475.c +++ b/drivers/hwmon/adt7475.c @@ -1770,7 +1770,7 @@ static void adt7475_read_pwm(struct i2c_client *client, int index) data->pwm[CONTROL][index] &= ~0xE0; data->pwm[CONTROL][index] |= (7 << 5); - i2c_smbus_write_byte_data(client, PWM_CONFIG_REG(index), + i2c_smbus_write_byte_data(client, PWM_REG(index), data->pwm[INPUT][index]); i2c_smbus_write_byte_data(client, PWM_CONFIG_REG(index), From ae8bd075a92166dc32cdb68bd5f8f1b32d7846a1 Mon Sep 17 00:00:00 2001 From: =?UTF-8?q?Uwe=20Kleine-K=C3=B6nig?= Date: Wed, 3 Jul 2024 13:00:06 +0200 Subject: [PATCH 010/342] pwm: stm32: Always do lazy disabling MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit [ Upstream commit 7346e7a058a2c9aa9ff1cc699c7bf18a402d9f84 ] When the state changes from enabled to disabled, polarity, duty_cycle and period are not configured in hardware and TIM_CCER_CCxE is just cleared. However if the state changes from one disabled state to another, all parameters are written to hardware because the early exit from stm32_pwm_apply() is only taken if the pwm is currently enabled. This yields surprises like: Applying { .period = 1, .duty_cycle = 0, .enabled = false } succeeds if the pwm is initially on, but fails if it's already off because 1 is a too small period. Update the check for lazy disable to always exit early if the target state is disabled, no matter what is currently configured. Fixes: 7edf7369205b ("pwm: Add driver for STM32 plaftorm") Signed-off-by: Uwe Kleine-König Link: https://lore.kernel.org/r/20240703110010.672654-2-u.kleine-koenig@baylibre.com Signed-off-by: Uwe Kleine-König Signed-off-by: Sasha Levin --- drivers/pwm/pwm-stm32.c | 5 +++-- 1 file changed, 3 insertions(+), 2 deletions(-) diff --git a/drivers/pwm/pwm-stm32.c b/drivers/pwm/pwm-stm32.c index 3e5f1b622af8..7146b3f6755b 100644 --- a/drivers/pwm/pwm-stm32.c +++ b/drivers/pwm/pwm-stm32.c @@ -452,8 +452,9 @@ static int stm32_pwm_apply(struct pwm_chip *chip, struct pwm_device *pwm, enabled = pwm->state.enabled; - if (enabled && !state->enabled) { - stm32_pwm_disable(priv, pwm->hwpwm); + if (!state->enabled) { + if (enabled) + stm32_pwm_disable(priv, pwm->hwpwm); return 0; } From 15770a1476920c05abfa021e031f882d50d06d33 Mon Sep 17 00:00:00 2001 From: Guenter Roeck Date: Sat, 13 Jul 2024 14:26:19 -0700 Subject: [PATCH 011/342] hwmon: (max6697) Fix underflow when writing limit attributes [ Upstream commit cbf7467828cd4ec7ceac7a8b5b5ddb2f69f07b0e ] Using DIV_ROUND_CLOSEST() on an unbound value can result in underflows. Indeed, module test scripts report: temp1_max: Suspected underflow: [min=0, read 255000, written -9223372036854775808] temp1_crit: Suspected underflow: [min=0, read 255000, written -9223372036854775808] Fix by introducing an extra set of clamping. Fixes: 5372d2d71c46 ("hwmon: Driver for Maxim MAX6697 and compatibles") Reviewed-by: Tzung-Bi Shih Signed-off-by: Guenter Roeck Signed-off-by: Sasha Levin --- drivers/hwmon/max6697.c | 1 + 1 file changed, 1 insertion(+) diff --git a/drivers/hwmon/max6697.c b/drivers/hwmon/max6697.c index fc3241101178..3fa2a3b3c995 100644 --- a/drivers/hwmon/max6697.c +++ b/drivers/hwmon/max6697.c @@ -312,6 +312,7 @@ static ssize_t temp_store(struct device *dev, return ret; mutex_lock(&data->update_lock); + temp = clamp_val(temp, -1000000, 1000000); /* prevent underflow */ temp = DIV_ROUND_CLOSEST(temp, 1000) + data->temp_offset; temp = clamp_val(temp, 0, data->type == max6581 ? 255 : 127); data->temp[nr][index] = temp; From d3e6b30c9cf5d923f0c007d609bc0ae2911030a0 Mon Sep 17 00:00:00 2001 From: Guenter Roeck Date: Sat, 13 Jul 2024 12:03:53 -0700 Subject: [PATCH 012/342] hwmon: (max6697) Fix swapped temp{1,8} critical alarms [ Upstream commit 1ea3fd1eb9869fcdcbc9c68f9728bfc47b9503f1 ] The critical alarm bit for the local temperature sensor (temp1) is in bit 7 of register 0x45 (not bit 6), and the critical alarm bit for remote temperature sensor 7 (temp8) is in bit 6 (not bit 7). This only affects MAX6581 since all other chips supported by this driver do not support those critical alarms. Fixes: 5372d2d71c46 ("hwmon: Driver for Maxim MAX6697 and compatibles") Reviewed-by: Tzung-Bi Shih Signed-off-by: Guenter Roeck Signed-off-by: Sasha Levin --- drivers/hwmon/max6697.c | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-) diff --git a/drivers/hwmon/max6697.c b/drivers/hwmon/max6697.c index 3fa2a3b3c995..7508d67c3dfb 100644 --- a/drivers/hwmon/max6697.c +++ b/drivers/hwmon/max6697.c @@ -430,14 +430,14 @@ static SENSOR_DEVICE_ATTR_RO(temp6_max_alarm, alarm, 20); static SENSOR_DEVICE_ATTR_RO(temp7_max_alarm, alarm, 21); static SENSOR_DEVICE_ATTR_RO(temp8_max_alarm, alarm, 23); -static SENSOR_DEVICE_ATTR_RO(temp1_crit_alarm, alarm, 14); +static SENSOR_DEVICE_ATTR_RO(temp1_crit_alarm, alarm, 15); static SENSOR_DEVICE_ATTR_RO(temp2_crit_alarm, alarm, 8); static SENSOR_DEVICE_ATTR_RO(temp3_crit_alarm, alarm, 9); static SENSOR_DEVICE_ATTR_RO(temp4_crit_alarm, alarm, 10); static SENSOR_DEVICE_ATTR_RO(temp5_crit_alarm, alarm, 11); static SENSOR_DEVICE_ATTR_RO(temp6_crit_alarm, alarm, 12); static SENSOR_DEVICE_ATTR_RO(temp7_crit_alarm, alarm, 13); -static SENSOR_DEVICE_ATTR_RO(temp8_crit_alarm, alarm, 15); +static SENSOR_DEVICE_ATTR_RO(temp8_crit_alarm, alarm, 14); static SENSOR_DEVICE_ATTR_RO(temp2_fault, alarm, 1); static SENSOR_DEVICE_ATTR_RO(temp3_fault, alarm, 2); From 39f4cb508ebf47efef6795f3a8135a384e283539 Mon Sep 17 00:00:00 2001 From: Dmitry Baryshkov Date: Wed, 1 May 2024 19:19:32 +0300 Subject: [PATCH 013/342] arm64: dts: qcom: sdm845: add power-domain to UFS PHY [ Upstream commit fd39ae8b9bc10419b1e4b849cdbc6755a967ade1 ] The UFS PHY is powered on via the UFS_PHY_GDSC power domain. Add corresponding power-domain the the PHY node. Fixes: cc16687fbd74 ("arm64: dts: qcom: sdm845: add UFS controller") Signed-off-by: Dmitry Baryshkov Reviewed-by: Konrad Dybcio Link: https://lore.kernel.org/r/20240501-qcom-phy-fixes-v1-6-f1fd15c33fb3@linaro.org Signed-off-by: Bjorn Andersson Signed-off-by: Sasha Levin --- arch/arm64/boot/dts/qcom/sdm845.dtsi | 2 ++ 1 file changed, 2 insertions(+) diff --git a/arch/arm64/boot/dts/qcom/sdm845.dtsi b/arch/arm64/boot/dts/qcom/sdm845.dtsi index b00f6d8bc8ba..da48ae60155a 100644 --- a/arch/arm64/boot/dts/qcom/sdm845.dtsi +++ b/arch/arm64/boot/dts/qcom/sdm845.dtsi @@ -2125,6 +2125,8 @@ ufs_mem_phy: phy@1d87000 { clocks = <&gcc GCC_UFS_MEM_CLKREF_CLK>, <&gcc GCC_UFS_PHY_PHY_AUX_CLK>; + power-domains = <&gcc UFS_PHY_GDSC>; + resets = <&ufs_mem_hc 0>; reset-names = "ufsphy"; status = "disabled"; From eedd9fd986415b3cc62b96876ad5d41d3ed56127 Mon Sep 17 00:00:00 2001 From: Stephen Boyd Date: Thu, 9 May 2024 11:41:28 -0700 Subject: [PATCH 014/342] soc: qcom: rpmh-rsc: Ensure irqs aren't disabled by rpmh_rsc_send_data() callers [ Upstream commit e43111f52b9ec5c2d700f89a1d61c8d10dc2d9e9 ] Dan pointed out that Smatch is concerned about this code because it uses spin_lock_irqsave() and then calls wait_event_lock_irq() which enables irqs before going to sleep. The comment above the function says it should be called with interrupts enabled, but we simply hope that's true without really confirming that. Let's add a might_sleep() here to confirm that interrupts and preemption aren't disabled. Once we do that, we can change the lock to be non-saving, spin_lock_irq(), to clarify that we don't expect irqs to be disabled. If irqs are disabled by callers they're going to be enabled anyway in the wait_event_lock_irq() call which would be bad. This should make Smatch happier and find bad callers faster with the might_sleep(). We can drop the WARN_ON() in the caller because we have the might_sleep() now, simplifying the code. Reported-by: Dan Carpenter Closes: https://lore.kernel.org/r/911181ed-c430-4592-ad26-4dc948834e08@moroto.mountain Fixes: 2bc20f3c8487 ("soc: qcom: rpmh-rsc: Sleep waiting for tcs slots to be free") Cc: Douglas Anderson Signed-off-by: Stephen Boyd Reviewed-by: Douglas Anderson Link: https://lore.kernel.org/r/20240509184129.3924422-1-swboyd@chromium.org Signed-off-by: Bjorn Andersson Signed-off-by: Sasha Levin --- drivers/soc/qcom/rpmh-rsc.c | 7 ++++--- drivers/soc/qcom/rpmh.c | 1 - 2 files changed, 4 insertions(+), 4 deletions(-) diff --git a/drivers/soc/qcom/rpmh-rsc.c b/drivers/soc/qcom/rpmh-rsc.c index a297911afe57..26e6dd860b5d 100644 --- a/drivers/soc/qcom/rpmh-rsc.c +++ b/drivers/soc/qcom/rpmh-rsc.c @@ -629,13 +629,14 @@ int rpmh_rsc_send_data(struct rsc_drv *drv, const struct tcs_request *msg) { struct tcs_group *tcs; int tcs_id; - unsigned long flags; + + might_sleep(); tcs = get_tcs_for_msg(drv, msg); if (IS_ERR(tcs)) return PTR_ERR(tcs); - spin_lock_irqsave(&drv->lock, flags); + spin_lock_irq(&drv->lock); /* Wait forever for a free tcs. It better be there eventually! */ wait_event_lock_irq(drv->tcs_wait, @@ -654,7 +655,7 @@ int rpmh_rsc_send_data(struct rsc_drv *drv, const struct tcs_request *msg) write_tcs_reg_sync(drv, RSC_DRV_CMD_WAIT_FOR_CMPL, tcs_id, 0); enable_tcs_irq(drv, tcs_id, true); } - spin_unlock_irqrestore(&drv->lock, flags); + spin_unlock_irq(&drv->lock); /* * These two can be done after the lock is released because: diff --git a/drivers/soc/qcom/rpmh.c b/drivers/soc/qcom/rpmh.c index b61e183ede69..707e176ed4ed 100644 --- a/drivers/soc/qcom/rpmh.c +++ b/drivers/soc/qcom/rpmh.c @@ -193,7 +193,6 @@ static int __rpmh_write(const struct device *dev, enum rpmh_state state, rpm_msg->msg.state = state; if (state == RPMH_ACTIVE_ONLY_STATE) { - WARN_ON(irqs_disabled()); ret = rpmh_rsc_send_data(ctrlr_to_drv(ctrlr), &rpm_msg->msg); } else { /* Clean up our call by spoofing tx_done */ From a584e5d3f7d909769a03f6b63d301f39accb1e6e Mon Sep 17 00:00:00 2001 From: Dmitry Baryshkov Date: Mon, 8 Apr 2024 03:04:31 +0300 Subject: [PATCH 015/342] arm64: dts: qcom: msm8996: specify UFS core_clk frequencies [ Upstream commit 02f838b7f8cdfb7a96b7f08e7f6716f230bdecba ] Follow the example of other platforms and specify core_clk frequencies in the frequency table in addition to the core_clk_src frequencies. The driver should be setting the leaf frequency instead of some interim clock freq. Suggested-by: Nitin Rawat Fixes: 57fc67ef0d35 ("arm64: dts: qcom: msm8996: Add ufs related nodes") Reviewed-by: Konrad Dybcio Reviewed-by: Manivannan Sadhasivam Signed-off-by: Dmitry Baryshkov Link: https://lore.kernel.org/r/20240408-msm8996-fix-ufs-v4-1-ee1a28bf8579@linaro.org Signed-off-by: Bjorn Andersson Signed-off-by: Sasha Levin --- arch/arm64/boot/dts/qcom/msm8996.dtsi | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/arch/arm64/boot/dts/qcom/msm8996.dtsi b/arch/arm64/boot/dts/qcom/msm8996.dtsi index e990e727cc0f..118fd1e47d5c 100644 --- a/arch/arm64/boot/dts/qcom/msm8996.dtsi +++ b/arch/arm64/boot/dts/qcom/msm8996.dtsi @@ -927,7 +927,7 @@ ufshc: ufshc@624000 { <&gcc GCC_UFS_RX_SYMBOL_0_CLK>; freq-table-hz = <100000000 200000000>, - <0 0>, + <100000000 200000000>, <0 0>, <0 0>, <0 0>, From eab05737ee22216250fe20d27f5a596da5ea6eb7 Mon Sep 17 00:00:00 2001 From: Dmitry Baryshkov Date: Sat, 22 Jun 2024 01:03:40 +0300 Subject: [PATCH 016/342] soc: qcom: pdr: protect locator_addr with the main mutex [ Upstream commit 107924c14e3ddd85119ca43c26a4ee1056fa9b84 ] If the service locator server is restarted fast enough, the PDR can rewrite locator_addr fields concurrently. Protect them by placing modification of those fields under the main pdr->lock. Fixes: fbe639b44a82 ("soc: qcom: Introduce Protection Domain Restart helpers") Tested-by: Neil Armstrong # on SM8550-QRD Tested-by: Steev Klimaszewski Tested-by: Alexey Minnekhanov Signed-off-by: Dmitry Baryshkov Link: https://lore.kernel.org/r/20240622-qcom-pd-mapper-v9-1-a84ee3591c8e@linaro.org Signed-off-by: Bjorn Andersson Signed-off-by: Sasha Levin --- drivers/soc/qcom/pdr_interface.c | 6 ++++-- 1 file changed, 4 insertions(+), 2 deletions(-) diff --git a/drivers/soc/qcom/pdr_interface.c b/drivers/soc/qcom/pdr_interface.c index 205cc96823b7..373725b6d544 100644 --- a/drivers/soc/qcom/pdr_interface.c +++ b/drivers/soc/qcom/pdr_interface.c @@ -76,12 +76,12 @@ static int pdr_locator_new_server(struct qmi_handle *qmi, locator_hdl); struct pdr_service *pds; + mutex_lock(&pdr->lock); /* Create a local client port for QMI communication */ pdr->locator_addr.sq_family = AF_QIPCRTR; pdr->locator_addr.sq_node = svc->node; pdr->locator_addr.sq_port = svc->port; - mutex_lock(&pdr->lock); pdr->locator_init_complete = true; mutex_unlock(&pdr->lock); @@ -104,10 +104,10 @@ static void pdr_locator_del_server(struct qmi_handle *qmi, mutex_lock(&pdr->lock); pdr->locator_init_complete = false; - mutex_unlock(&pdr->lock); pdr->locator_addr.sq_node = 0; pdr->locator_addr.sq_port = 0; + mutex_unlock(&pdr->lock); } static struct qmi_ops pdr_locator_ops = { @@ -366,12 +366,14 @@ static int pdr_get_domain_list(struct servreg_get_domain_list_req *req, if (ret < 0) return ret; + mutex_lock(&pdr->lock); ret = qmi_send_request(&pdr->locator_hdl, &pdr->locator_addr, &txn, SERVREG_GET_DOMAIN_LIST_REQ, SERVREG_GET_DOMAIN_LIST_REQ_MAX_LEN, servreg_get_domain_list_req_ei, req); + mutex_unlock(&pdr->lock); if (ret < 0) { qmi_txn_cancel(&txn); return ret; From 5cc525351b0ca5f436366ff145e9de0459e615ce Mon Sep 17 00:00:00 2001 From: Dmitry Baryshkov Date: Sat, 22 Jun 2024 01:03:41 +0300 Subject: [PATCH 017/342] soc: qcom: pdr: fix parsing of domains lists [ Upstream commit 57f20d51f35780f240ecf39d81cda23612800a92 ] While parsing the domains list, start offsets from 0 rather than from domains_read. The domains_read is equal to the total count of the domains we have seen, while the domains list in the message starts from offset 0. Fixes: fbe639b44a82 ("soc: qcom: Introduce Protection Domain Restart helpers") Tested-by: Steev Klimaszewski Tested-by: Alexey Minnekhanov Reviewed-by: Chris Lew Tested-by: Neil Armstrong # on SM8550-QRD Signed-off-by: Dmitry Baryshkov Link: https://lore.kernel.org/r/20240622-qcom-pd-mapper-v9-2-a84ee3591c8e@linaro.org Signed-off-by: Bjorn Andersson Signed-off-by: Sasha Levin --- drivers/soc/qcom/pdr_interface.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/drivers/soc/qcom/pdr_interface.c b/drivers/soc/qcom/pdr_interface.c index 373725b6d544..6e3cbd822663 100644 --- a/drivers/soc/qcom/pdr_interface.c +++ b/drivers/soc/qcom/pdr_interface.c @@ -418,7 +418,7 @@ static int pdr_locate_service(struct pdr_handle *pdr, struct pdr_service *pds) if (ret < 0) goto out; - for (i = domains_read; i < resp->domain_list_len; i++) { + for (i = 0; i < resp->domain_list_len; i++) { entry = &resp->domain_list[i]; if (strnlen(entry->name, sizeof(entry->name)) == sizeof(entry->name)) From 31a9a0958b157b4fd1e4d3c55fa6eec498a45b81 Mon Sep 17 00:00:00 2001 From: Jonas Karlman Date: Sat, 15 Jun 2024 17:03:52 +0000 Subject: [PATCH 018/342] arm64: dts: rockchip: Increase VOP clk rate on RK3328 [ Upstream commit 0f2ddb128fa20f8441d903285632f2c69e90fae1 ] The VOP on RK3328 needs to run at a higher rate in order to produce a proper 3840x2160 signal. Change to use 300MHz for VIO clk and 400MHz for VOP clk, same rates used by vendor 4.4 kernel. Fixes: 52e02d377a72 ("arm64: dts: rockchip: add core dtsi file for RK3328 SoCs") Signed-off-by: Jonas Karlman Link: https://lore.kernel.org/r/20240615170417.3134517-2-jonas@kwiboo.se Signed-off-by: Heiko Stuebner Signed-off-by: Sasha Levin --- arch/arm64/boot/dts/rockchip/rk3328.dtsi | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-) diff --git a/arch/arm64/boot/dts/rockchip/rk3328.dtsi b/arch/arm64/boot/dts/rockchip/rk3328.dtsi index 10df6636a6b6..3c6398e98f76 100644 --- a/arch/arm64/boot/dts/rockchip/rk3328.dtsi +++ b/arch/arm64/boot/dts/rockchip/rk3328.dtsi @@ -811,8 +811,8 @@ cru: clock-controller@ff440000 { <0>, <24000000>, <24000000>, <24000000>, <15000000>, <15000000>, - <100000000>, <100000000>, - <100000000>, <100000000>, + <300000000>, <100000000>, + <400000000>, <100000000>, <50000000>, <100000000>, <100000000>, <100000000>, <50000000>, <50000000>, From bbfa9a71ae4afd393afc31e106c977cfc87a2304 Mon Sep 17 00:00:00 2001 From: Marco Felsch Date: Tue, 26 Jul 2022 15:05:20 +0200 Subject: [PATCH 019/342] ARM: dts: imx6qdl-kontron-samx6i: move phy reset into phy-node [ Upstream commit 5694eed98cca5c164ebb5b831b65b4c9eee4b2d5 ] Add ethernet-phy node so we can drop the deprecated fec phy-reset-gpios property. The reset-assert-us value is taken from the existing logic since the fec driver will add an 1ms assert delay per default if phy-reset-gpios is used and phy-reset-duration is not specified. Signed-off-by: Marco Felsch Signed-off-by: Shawn Guo Stable-dep-of: edfea889a049 ("ARM: dts: imx6qdl-kontron-samx6i: fix PHY reset") Signed-off-by: Sasha Levin --- arch/arm/boot/dts/imx6qdl-kontron-samx6i.dtsi | 14 +++++++++++++- 1 file changed, 13 insertions(+), 1 deletion(-) diff --git a/arch/arm/boot/dts/imx6qdl-kontron-samx6i.dtsi b/arch/arm/boot/dts/imx6qdl-kontron-samx6i.dtsi index 37d94aa45a8b..e2b7bfddedcd 100644 --- a/arch/arm/boot/dts/imx6qdl-kontron-samx6i.dtsi +++ b/arch/arm/boot/dts/imx6qdl-kontron-samx6i.dtsi @@ -260,7 +260,19 @@ &fec { pinctrl-names = "default"; pinctrl-0 = <&pinctrl_enet>; phy-mode = "rgmii"; - phy-reset-gpios = <&gpio1 25 GPIO_ACTIVE_LOW>; + phy-handle = <ðphy>; + + mdio { + #address-cells = <1>; + #size-cells = <0>; + + ethphy: ethernet-phy@1 { + compatible = "ethernet-phy-ieee802.3-c22"; + reg = <1>; + reset-gpios = <&gpio1 25 GPIO_ACTIVE_LOW>; + reset-assert-us = <1000>; + }; + }; }; &i2c_intern { From efd89b5db5be106c7f59de8867008944a72920f1 Mon Sep 17 00:00:00 2001 From: Michael Walle Date: Mon, 17 Jun 2024 11:13:30 +0200 Subject: [PATCH 020/342] ARM: dts: imx6qdl-kontron-samx6i: fix PHY reset [ Upstream commit edfea889a049abe80f0d55c0365bf60fbade272f ] The PHY reset line is connected to both the SoC (GPIO1_25) and the CPLD. We must not use the GPIO1_25 as it will drive against the output buffer of the CPLD. Instead there is another GPIO (GPIO2_01), an input to the CPLD, which will tell the CPLD to assert the PHY reset line. Fixes: 2a51f9dae13d ("ARM: dts: imx6qdl-kontron-samx6i: Add iMX6-based Kontron SMARC-sAMX6i module") Fixes: 5694eed98cca ("ARM: dts: imx6qdl-kontron-samx6i: move phy reset into phy-node") Signed-off-by: Michael Walle Signed-off-by: Shawn Guo Signed-off-by: Sasha Levin --- arch/arm/boot/dts/imx6qdl-kontron-samx6i.dtsi | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-) diff --git a/arch/arm/boot/dts/imx6qdl-kontron-samx6i.dtsi b/arch/arm/boot/dts/imx6qdl-kontron-samx6i.dtsi index e2b7bfddedcd..cf001c251fe3 100644 --- a/arch/arm/boot/dts/imx6qdl-kontron-samx6i.dtsi +++ b/arch/arm/boot/dts/imx6qdl-kontron-samx6i.dtsi @@ -269,7 +269,7 @@ mdio { ethphy: ethernet-phy@1 { compatible = "ethernet-phy-ieee802.3-c22"; reg = <1>; - reset-gpios = <&gpio1 25 GPIO_ACTIVE_LOW>; + reset-gpios = <&gpio2 1 GPIO_ACTIVE_LOW>; reset-assert-us = <1000>; }; }; @@ -512,7 +512,7 @@ MX6QDL_PAD_RGMII_RX_CTL__RGMII_RX_CTL 0x1b0b0 MX6QDL_PAD_ENET_MDIO__ENET_MDIO 0x1b0b0 MX6QDL_PAD_ENET_MDC__ENET_MDC 0x1b0b0 MX6QDL_PAD_ENET_REF_CLK__ENET_TX_CLK 0x1b0b0 - MX6QDL_PAD_ENET_CRS_DV__GPIO1_IO25 0x1b0b0 /* RST_GBE0_PHY# */ + MX6QDL_PAD_NANDF_D1__GPIO2_IO01 0x1b0b0 /* RST_GBE0_PHY# */ >; }; From c79a7cad4115b47257643f0df54b65d0e2e24dd4 Mon Sep 17 00:00:00 2001 From: Michael Walle Date: Mon, 17 Jun 2024 11:13:31 +0200 Subject: [PATCH 021/342] ARM: dts: imx6qdl-kontron-samx6i: fix board reset [ Upstream commit b972d6b3b46345023aee56a95df8e2c137aa4ee4 ] On i.MX6 the board is reset by the watchdog. But in turn to do a complete board reset, we have to assert the WDOG_B output which is routed also to the CPLD which then do a complete power-cycle of the board. Fixes: 2125212785c9 ("ARM: dts: imx6qdl-kontron-samx6i: add Kontron SMARC SoM Support") Signed-off-by: Michael Walle Signed-off-by: Shawn Guo Signed-off-by: Sasha Levin --- arch/arm/boot/dts/imx6qdl-kontron-samx6i.dtsi | 1 + 1 file changed, 1 insertion(+) diff --git a/arch/arm/boot/dts/imx6qdl-kontron-samx6i.dtsi b/arch/arm/boot/dts/imx6qdl-kontron-samx6i.dtsi index cf001c251fe3..8eda848e9f0e 100644 --- a/arch/arm/boot/dts/imx6qdl-kontron-samx6i.dtsi +++ b/arch/arm/boot/dts/imx6qdl-kontron-samx6i.dtsi @@ -813,5 +813,6 @@ &wdog1 { /* CPLD is feeded by watchdog (hardwired) */ pinctrl-names = "default"; pinctrl-0 = <&pinctrl_wdog1>; + fsl,ext-reset-output; status = "okay"; }; From a992c88fbb8c93757713feba749fd6613d79d829 Mon Sep 17 00:00:00 2001 From: Michael Walle Date: Mon, 17 Jun 2024 11:13:33 +0200 Subject: [PATCH 022/342] ARM: dts: imx6qdl-kontron-samx6i: fix SPI0 chip selects [ Upstream commit 74e1c956a68a65d642447d852e95b3fbb69bebaa ] There is a comment in the imx6q variant dtsi claiming that these modules will have one more chip select than the imx6dl variant. This is wrong. Ordinary GPIOs are used for chip selects and both variants of the module share the very same PCB and both have this GPIO routed to the SPI0_CS1# pin of the SMARC connector. Fix it by moving the third chip select description to the common dtsi. Fixes: 2125212785c9 ("ARM: dts: imx6qdl-kontron-samx6i: add Kontron SMARC SoM Support") Signed-off-by: Michael Walle Signed-off-by: Shawn Guo Signed-off-by: Sasha Levin --- arch/arm/boot/dts/imx6q-kontron-samx6i.dtsi | 23 ------------------- arch/arm/boot/dts/imx6qdl-kontron-samx6i.dtsi | 5 +++- 2 files changed, 4 insertions(+), 24 deletions(-) diff --git a/arch/arm/boot/dts/imx6q-kontron-samx6i.dtsi b/arch/arm/boot/dts/imx6q-kontron-samx6i.dtsi index 4d6a0c3e8455..ff062f4fd726 100644 --- a/arch/arm/boot/dts/imx6q-kontron-samx6i.dtsi +++ b/arch/arm/boot/dts/imx6q-kontron-samx6i.dtsi @@ -5,31 +5,8 @@ #include "imx6q.dtsi" #include "imx6qdl-kontron-samx6i.dtsi" -#include / { model = "Kontron SMARC sAMX6i Quad/Dual"; compatible = "kontron,imx6q-samx6i", "fsl,imx6q"; }; - -/* Quad/Dual SoMs have 3 chip-select signals */ -&ecspi4 { - cs-gpios = <&gpio3 24 GPIO_ACTIVE_LOW>, - <&gpio3 29 GPIO_ACTIVE_LOW>, - <&gpio3 25 GPIO_ACTIVE_LOW>; -}; - -&pinctrl_ecspi4 { - fsl,pins = < - MX6QDL_PAD_EIM_D21__ECSPI4_SCLK 0x100b1 - MX6QDL_PAD_EIM_D28__ECSPI4_MOSI 0x100b1 - MX6QDL_PAD_EIM_D22__ECSPI4_MISO 0x100b1 - - /* SPI4_IMX_CS2# - connected to internal flash */ - MX6QDL_PAD_EIM_D24__GPIO3_IO24 0x1b0b0 - /* SPI4_IMX_CS0# - connected to SMARC SPI0_CS0# */ - MX6QDL_PAD_EIM_D29__GPIO3_IO29 0x1b0b0 - /* SPI4_CS3# - connected to SMARC SPI0_CS1# */ - MX6QDL_PAD_EIM_D25__GPIO3_IO25 0x1b0b0 - >; -}; diff --git a/arch/arm/boot/dts/imx6qdl-kontron-samx6i.dtsi b/arch/arm/boot/dts/imx6qdl-kontron-samx6i.dtsi index 8eda848e9f0e..115084500c37 100644 --- a/arch/arm/boot/dts/imx6qdl-kontron-samx6i.dtsi +++ b/arch/arm/boot/dts/imx6qdl-kontron-samx6i.dtsi @@ -244,7 +244,8 @@ &ecspi4 { pinctrl-names = "default"; pinctrl-0 = <&pinctrl_ecspi4>; cs-gpios = <&gpio3 24 GPIO_ACTIVE_LOW>, - <&gpio3 29 GPIO_ACTIVE_LOW>; + <&gpio3 29 GPIO_ACTIVE_LOW>, + <&gpio3 25 GPIO_ACTIVE_LOW>; status = "okay"; /* default boot source: workaround #1 for errata ERR006282 */ @@ -460,6 +461,8 @@ MX6QDL_PAD_EIM_D22__ECSPI4_MISO 0x100b1 MX6QDL_PAD_EIM_D24__GPIO3_IO24 0x1b0b0 /* SPI_IMX_CS0# - connected to SMARC SPI0_CS0# */ MX6QDL_PAD_EIM_D29__GPIO3_IO29 0x1b0b0 + /* SPI4_CS3# - connected to SMARC SPI0_CS1# */ + MX6QDL_PAD_EIM_D25__GPIO3_IO25 0x1b0b0 >; }; From b1e9396ac410ad4c15f738a2ad2aa993ff96229f Mon Sep 17 00:00:00 2001 From: Michael Walle Date: Mon, 17 Jun 2024 11:13:38 +0200 Subject: [PATCH 023/342] ARM: dts: imx6qdl-kontron-samx6i: fix PCIe reset polarity [ Upstream commit df35c6e9027cf9affe699e632a48082ab1bbba4c ] The PCIe reset line is active low. Fix it. Fixes: 2a51f9dae13d ("ARM: dts: imx6qdl-kontron-samx6i: Add iMX6-based Kontron SMARC-sAMX6i module") Signed-off-by: Michael Walle Signed-off-by: Shawn Guo Signed-off-by: Sasha Levin --- arch/arm/boot/dts/imx6qdl-kontron-samx6i.dtsi | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/arch/arm/boot/dts/imx6qdl-kontron-samx6i.dtsi b/arch/arm/boot/dts/imx6qdl-kontron-samx6i.dtsi index 115084500c37..9ec1519e1719 100644 --- a/arch/arm/boot/dts/imx6qdl-kontron-samx6i.dtsi +++ b/arch/arm/boot/dts/imx6qdl-kontron-samx6i.dtsi @@ -728,7 +728,7 @@ &pcie { pinctrl-names = "default"; pinctrl-0 = <&pinctrl_pcie>; wake-up-gpio = <&gpio6 18 GPIO_ACTIVE_HIGH>; - reset-gpio = <&gpio3 13 GPIO_ACTIVE_HIGH>; + reset-gpio = <&gpio3 13 GPIO_ACTIVE_LOW>; }; /* LCD_BKLT_PWM */ From be5ca4064751858371d00121afaed5140e5ad38d Mon Sep 17 00:00:00 2001 From: Chen-Yu Tsai Date: Fri, 12 Apr 2024 15:56:12 +0800 Subject: [PATCH 024/342] arm64: dts: mediatek: mt8183-kukui: Drop bogus output-enable property [ Upstream commit e9a9055fdcdc1e5a27cef118c5b4f09cdd2fa28e ] The "output-enable" property is set on uart1's RTS pin. This is bogus because the hardware does not actually have a controllable output buffer. Secondly, the implementation incorrectly treats this property as a request to switch the pin to GPIO output. This does not fit the intended semantic of "output-enable" and it does not have any affect either because the pin is muxed to the UART function, not the GPIO function. Drop the property. Fixes: cd894e274b74 ("arm64: dts: mt8183: Add krane-sku176 board") Signed-off-by: Chen-Yu Tsai Link: https://lore.kernel.org/r/20240412075613.1200048-1-wenst@chromium.org Signed-off-by: AngeloGioacchino Del Regno Signed-off-by: Sasha Levin --- arch/arm64/boot/dts/mediatek/mt8183-kukui.dtsi | 2 -- 1 file changed, 2 deletions(-) diff --git a/arch/arm64/boot/dts/mediatek/mt8183-kukui.dtsi b/arch/arm64/boot/dts/mediatek/mt8183-kukui.dtsi index a4f860bb4a84..ad8b11267c7d 100644 --- a/arch/arm64/boot/dts/mediatek/mt8183-kukui.dtsi +++ b/arch/arm64/boot/dts/mediatek/mt8183-kukui.dtsi @@ -628,7 +628,6 @@ pins_tx { }; pins_rts { pinmux = ; - output-enable; }; pins_cts { pinmux = ; @@ -647,7 +646,6 @@ pins_tx { }; pins_rts { pinmux = ; - output-enable; }; pins_cts { pinmux = ; From 4745535fce11f688c00e4dea2fae0b51373e20ac Mon Sep 17 00:00:00 2001 From: =?UTF-8?q?Rafa=C5=82=20Mi=C5=82ecki?= Date: Tue, 4 Jun 2024 09:49:16 +0200 Subject: [PATCH 025/342] arm64: dts: mediatek: mt7622: fix "emmc" pinctrl mux MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit [ Upstream commit aebba1030a5766cdf894ed4ab0cac7aed5aee9c1 ] Value "emmc_rst" is a group name and should be part of the "groups" property. This fixes: arch/arm64/boot/dts/mediatek/mt7622-rfb1.dtb: pinctrl@10211000: emmc-pins-default:mux:function: ['emmc', 'emmc_rst'] is too long from schema $id: http://devicetree.org/schemas/pinctrl/mediatek,mt7622-pinctrl.yaml# arch/arm64/boot/dts/mediatek/mt7622-bananapi-bpi-r64.dtb: pinctrl@10211000: emmc-pins-default:mux:function: ['emmc', 'emmc_rst'] is too long from schema $id: http://devicetree.org/schemas/pinctrl/mediatek,mt7622-pinctrl.yaml# Fixes: 3725ba3f5574 ("arm64: dts: mt7622: add pinctrl related device nodes") Fixes: 0b6286dd96c0 ("arm64: dts: mt7622: add bananapi BPI-R64 board") Signed-off-by: Rafał Miłecki Reviewed-by: AngeloGioacchino Del Regno Link: https://lore.kernel.org/r/20240604074916.7929-1-zajec5@gmail.com Signed-off-by: AngeloGioacchino Del Regno Signed-off-by: Sasha Levin --- arch/arm64/boot/dts/mediatek/mt7622-bananapi-bpi-r64.dts | 4 ++-- arch/arm64/boot/dts/mediatek/mt7622-rfb1.dts | 4 ++-- 2 files changed, 4 insertions(+), 4 deletions(-) diff --git a/arch/arm64/boot/dts/mediatek/mt7622-bananapi-bpi-r64.dts b/arch/arm64/boot/dts/mediatek/mt7622-bananapi-bpi-r64.dts index 778174a7d649..46e412b436ed 100644 --- a/arch/arm64/boot/dts/mediatek/mt7622-bananapi-bpi-r64.dts +++ b/arch/arm64/boot/dts/mediatek/mt7622-bananapi-bpi-r64.dts @@ -285,8 +285,8 @@ asm_sel { /* eMMC is shared pin with parallel NAND */ emmc_pins_default: emmc-pins-default { mux { - function = "emmc", "emmc_rst"; - groups = "emmc"; + function = "emmc"; + groups = "emmc", "emmc_rst"; }; /* "NDL0","NDL1","NDL2","NDL3","NDL4","NDL5","NDL6","NDL7", diff --git a/arch/arm64/boot/dts/mediatek/mt7622-rfb1.dts b/arch/arm64/boot/dts/mediatek/mt7622-rfb1.dts index 810575de6670..5dd993496a5c 100644 --- a/arch/arm64/boot/dts/mediatek/mt7622-rfb1.dts +++ b/arch/arm64/boot/dts/mediatek/mt7622-rfb1.dts @@ -249,8 +249,8 @@ &pio { /* eMMC is shared pin with parallel NAND */ emmc_pins_default: emmc-pins-default { mux { - function = "emmc", "emmc_rst"; - groups = "emmc"; + function = "emmc"; + groups = "emmc", "emmc_rst"; }; /* "NDL0","NDL1","NDL2","NDL3","NDL4","NDL5","NDL6","NDL7", From e04654f42577a2733e6cdc5e5c4490bfc1d77188 Mon Sep 17 00:00:00 2001 From: Jerome Brunet Date: Wed, 26 Jun 2024 17:27:30 +0200 Subject: [PATCH 026/342] arm64: dts: amlogic: gx: correct hdmi clocks [ Upstream commit 0602ba0dcd0e76067a0b7543e92b2de3fb231073 ] The clocks provided to HDMI tx are not consistent between gx and g12: * gx receives the peripheral clock as 'isfr' while g12 receives it as 'iahb' * g12 gets the HDMI system clock as 'isfr' but gx does not even get it. It surely needs that clock since the driver is directly poking around the clock controller's registers for that clock. Align gx SoCs with g12 and provide: * the HDMI peripheral clock as 'iahb' * the HDMI system clock as 'isfr' Fixes: 6939db7e0dbf ("ARM64: dts: meson-gx: Add support for HDMI output") Signed-off-by: Jerome Brunet Link: https://lore.kernel.org/r/20240626152733.1350376-2-jbrunet@baylibre.com Signed-off-by: Neil Armstrong Signed-off-by: Sasha Levin --- arch/arm64/boot/dts/amlogic/meson-gxbb.dtsi | 4 ++-- arch/arm64/boot/dts/amlogic/meson-gxl.dtsi | 4 ++-- 2 files changed, 4 insertions(+), 4 deletions(-) diff --git a/arch/arm64/boot/dts/amlogic/meson-gxbb.dtsi b/arch/arm64/boot/dts/amlogic/meson-gxbb.dtsi index 7c029f552a23..256c46771db7 100644 --- a/arch/arm64/boot/dts/amlogic/meson-gxbb.dtsi +++ b/arch/arm64/boot/dts/amlogic/meson-gxbb.dtsi @@ -311,8 +311,8 @@ &hdmi_tx { <&reset RESET_HDMI_SYSTEM_RESET>, <&reset RESET_HDMI_TX>; reset-names = "hdmitx_apb", "hdmitx", "hdmitx_phy"; - clocks = <&clkc CLKID_HDMI_PCLK>, - <&clkc CLKID_CLK81>, + clocks = <&clkc CLKID_HDMI>, + <&clkc CLKID_HDMI_PCLK>, <&clkc CLKID_GCLK_VENCI_INT0>; clock-names = "isfr", "iahb", "venci"; }; diff --git a/arch/arm64/boot/dts/amlogic/meson-gxl.dtsi b/arch/arm64/boot/dts/amlogic/meson-gxl.dtsi index 350022935052..a689bd14ece9 100644 --- a/arch/arm64/boot/dts/amlogic/meson-gxl.dtsi +++ b/arch/arm64/boot/dts/amlogic/meson-gxl.dtsi @@ -323,8 +323,8 @@ &hdmi_tx { <&reset RESET_HDMI_SYSTEM_RESET>, <&reset RESET_HDMI_TX>; reset-names = "hdmitx_apb", "hdmitx", "hdmitx_phy"; - clocks = <&clkc CLKID_HDMI_PCLK>, - <&clkc CLKID_CLK81>, + clocks = <&clkc CLKID_HDMI>, + <&clkc CLKID_HDMI_PCLK>, <&clkc CLKID_GCLK_VENCI_INT0>; clock-names = "isfr", "iahb", "venci"; }; From 4a49ce2d63d5f4d87c56664a9807d91bbd75e88f Mon Sep 17 00:00:00 2001 From: Eero Tamminen Date: Mon, 24 Jun 2024 17:49:01 +0300 Subject: [PATCH 027/342] m68k: atari: Fix TT bootup freeze / unexpected (SCU) interrupt messages MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit [ Upstream commit f70065a9fd988983b2c693631b801f25a615fc04 ] Avoid freeze on Atari TT / MegaSTe boot with continuous messages of: unexpected interrupt from 112 Which was due to VBL interrupt being enabled in SCU sys mask, but there being no handler for that any more. (Bug and fix were first verified on real Atari TT HW by Christian, this patch later on in Hatari emulator.) Fixes: 1fa0b29f3a43f9dd ("fbdev: Kill Atari vblank cursor blinking") Reported-by: Nicolas Pomarède Closes: https://listengine.tuxfamily.org/lists.tuxfamily.org/hatari-devel/2024/06/msg00016.html Closes: https://lore.kernel.org/all/9aa793d7-82ed-4fbd-bce5-60810d8a9119@helsinkinet.fi Tested-by: Christian Zietz Signed-off-by: Eero Tamminen Reviewed-by: Michael Schmitz Reviewed-by: Geert Uytterhoeven Link: https://lore.kernel.org/20240624144901.5236-1-oak@helsinkinet.fi Signed-off-by: Geert Uytterhoeven Signed-off-by: Sasha Levin --- arch/m68k/atari/ataints.c | 6 +----- 1 file changed, 1 insertion(+), 5 deletions(-) diff --git a/arch/m68k/atari/ataints.c b/arch/m68k/atari/ataints.c index 56f02ea2c248..715d1e0d973e 100644 --- a/arch/m68k/atari/ataints.c +++ b/arch/m68k/atari/ataints.c @@ -302,11 +302,7 @@ void __init atari_init_IRQ(void) if (ATARIHW_PRESENT(SCU)) { /* init the SCU if present */ - tt_scu.sys_mask = 0x10; /* enable VBL (for the cursor) and - * disable HSYNC interrupts (who - * needs them?) MFP and SCC are - * enabled in VME mask - */ + tt_scu.sys_mask = 0x0; /* disable all interrupts */ tt_scu.vme_mask = 0x60; /* enable MFP and SCC ints */ } else { /* If no SCU and no Hades, the HSYNC interrupt needs to be From ba1d2ecfcf1b959819794a4c3012e144e7903127 Mon Sep 17 00:00:00 2001 From: Chen Ni Date: Tue, 2 Jul 2024 11:10:10 +0800 Subject: [PATCH 028/342] x86/xen: Convert comma to semicolon [ Upstream commit 349d271416c61f82b853336509b1d0dc04c1fcbb ] Replace a comma between expression statements by a semicolon. Fixes: 8310b77b48c5 ("Xen/gnttab: handle p2m update errors on a per-slot basis") Signed-off-by: Chen Ni Reviewed-by: Juergen Gross Link: https://lore.kernel.org/r/20240702031010.1411875-1-nichen@iscas.ac.cn Signed-off-by: Juergen Gross Signed-off-by: Sasha Levin --- arch/x86/xen/p2m.c | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-) diff --git a/arch/x86/xen/p2m.c b/arch/x86/xen/p2m.c index e809f1446846..bfa972f7e874 100644 --- a/arch/x86/xen/p2m.c +++ b/arch/x86/xen/p2m.c @@ -736,7 +736,7 @@ int set_foreign_p2m_mapping(struct gnttab_map_grant_ref *map_ops, * immediate unmapping. */ map_ops[i].status = GNTST_general_error; - unmap[0].host_addr = map_ops[i].host_addr, + unmap[0].host_addr = map_ops[i].host_addr; unmap[0].handle = map_ops[i].handle; map_ops[i].handle = ~0; if (map_ops[i].flags & GNTMAP_device_map) @@ -746,7 +746,7 @@ int set_foreign_p2m_mapping(struct gnttab_map_grant_ref *map_ops, if (kmap_ops) { kmap_ops[i].status = GNTST_general_error; - unmap[1].host_addr = kmap_ops[i].host_addr, + unmap[1].host_addr = kmap_ops[i].host_addr; unmap[1].handle = kmap_ops[i].handle; kmap_ops[i].handle = ~0; if (kmap_ops[i].flags & GNTMAP_device_map) From 3ae2ec97d8e988b91b77c243095b9abcc4de39d5 Mon Sep 17 00:00:00 2001 From: Thorsten Blum Date: Tue, 2 Jul 2024 05:41:17 +0200 Subject: [PATCH 029/342] m68k: cmpxchg: Fix return value for default case in __arch_xchg() [ Upstream commit 21b9e722ad28c19c2bc83f18f540b3dbd89bf762 ] The return value of __invalid_xchg_size() is assigned to tmp instead of the return variable x. Assign it to x instead. Fixes: 2501cf768e4009a0 ("m68k: Fix xchg/cmpxchg to fail to link if given an inappropriate pointer") Signed-off-by: Thorsten Blum Reviewed-by: Geert Uytterhoeven Link: https://lore.kernel.org/20240702034116.140234-2-thorsten.blum@toblux.com Signed-off-by: Geert Uytterhoeven Signed-off-by: Sasha Levin --- arch/m68k/include/asm/cmpxchg.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/arch/m68k/include/asm/cmpxchg.h b/arch/m68k/include/asm/cmpxchg.h index 3a3bdcfcd375..2035b30d7951 100644 --- a/arch/m68k/include/asm/cmpxchg.h +++ b/arch/m68k/include/asm/cmpxchg.h @@ -33,7 +33,7 @@ static inline unsigned long __xchg(unsigned long x, volatile void * ptr, int siz x = tmp; break; default: - tmp = __invalid_xchg_size(x, ptr, size); + x = __invalid_xchg_size(x, ptr, size); break; } From 7b7d06a310e218ac4f853144350574756b3abfba Mon Sep 17 00:00:00 2001 From: Arnd Bergmann Date: Wed, 11 Sep 2019 16:43:59 +0200 Subject: [PATCH 030/342] ARM: pxa: spitz: use gpio descriptors for audio [ Upstream commit 726d8c965bae2d7468445d990849e281dca8cbf7 ] The audio driver should not use a hardwired gpio number from the header. Change it to use a lookup table. Acked-by: Mark Brown Cc: alsa-devel@alsa-project.org Reviewed-by: Linus Walleij Signed-off-by: Arnd Bergmann Stable-dep-of: 78ab3d352f29 ("ARM: spitz: fix GPIO assignment for backlight") Signed-off-by: Sasha Levin --- arch/arm/mach-pxa/spitz.c | 33 ++++++++++- arch/arm/mach-pxa/{include/mach => }/spitz.h | 2 +- arch/arm/mach-pxa/spitz_pm.c | 2 +- sound/soc/pxa/spitz.c | 58 ++++++++------------ 4 files changed, 57 insertions(+), 38 deletions(-) rename arch/arm/mach-pxa/{include/mach => }/spitz.h (99%) diff --git a/arch/arm/mach-pxa/spitz.c b/arch/arm/mach-pxa/spitz.c index 264de0bc97d6..8f880dbc05fd 100644 --- a/arch/arm/mach-pxa/spitz.c +++ b/arch/arm/mach-pxa/spitz.c @@ -43,7 +43,7 @@ #include #include #include -#include +#include "spitz.h" #include "sharpsl_pm.h" #include @@ -954,11 +954,42 @@ static void __init spitz_i2c_init(void) static inline void spitz_i2c_init(void) {} #endif +static struct gpiod_lookup_table spitz_audio_gpio_table = { + .dev_id = "spitz-audio", + .table = { + GPIO_LOOKUP("sharp-scoop.0", SPITZ_GPIO_MUTE_L - SPITZ_SCP_GPIO_BASE, + "mute-l", GPIO_ACTIVE_HIGH), + GPIO_LOOKUP("sharp-scoop.0", SPITZ_GPIO_MUTE_R - SPITZ_SCP_GPIO_BASE, + "mute-r", GPIO_ACTIVE_HIGH), + GPIO_LOOKUP("sharp-scoop.1", SPITZ_GPIO_MIC_BIAS - SPITZ_SCP2_GPIO_BASE, + "mic", GPIO_ACTIVE_HIGH), + { }, + }, +}; + +static struct gpiod_lookup_table akita_audio_gpio_table = { + .dev_id = "spitz-audio", + .table = { + GPIO_LOOKUP("sharp-scoop.0", SPITZ_GPIO_MUTE_L - SPITZ_SCP_GPIO_BASE, + "mute-l", GPIO_ACTIVE_HIGH), + GPIO_LOOKUP("sharp-scoop.0", SPITZ_GPIO_MUTE_R - SPITZ_SCP_GPIO_BASE, + "mute-r", GPIO_ACTIVE_HIGH), + GPIO_LOOKUP("i2c-max7310", AKITA_GPIO_MIC_BIAS - AKITA_IOEXP_GPIO_BASE, + "mic", GPIO_ACTIVE_HIGH), + { }, + }, +}; + /****************************************************************************** * Audio devices ******************************************************************************/ static inline void spitz_audio_init(void) { + if (machine_is_akita()) + gpiod_add_lookup_table(&akita_audio_gpio_table); + else + gpiod_add_lookup_table(&spitz_audio_gpio_table); + platform_device_register_simple("spitz-audio", -1, NULL, 0); } diff --git a/arch/arm/mach-pxa/include/mach/spitz.h b/arch/arm/mach-pxa/spitz.h similarity index 99% rename from arch/arm/mach-pxa/include/mach/spitz.h rename to arch/arm/mach-pxa/spitz.h index 04828d8918aa..f97e3ebd762d 100644 --- a/arch/arm/mach-pxa/include/mach/spitz.h +++ b/arch/arm/mach-pxa/spitz.h @@ -11,7 +11,7 @@ #define __ASM_ARCH_SPITZ_H 1 #endif -#include "irqs.h" /* PXA_NR_BUILTIN_GPIO, PXA_GPIO_TO_IRQ */ +#include /* PXA_NR_BUILTIN_GPIO, PXA_GPIO_TO_IRQ */ #include /* Spitz/Akita GPIOs */ diff --git a/arch/arm/mach-pxa/spitz_pm.c b/arch/arm/mach-pxa/spitz_pm.c index 25a1f8c5a738..6167f96d7b41 100644 --- a/arch/arm/mach-pxa/spitz_pm.c +++ b/arch/arm/mach-pxa/spitz_pm.c @@ -20,7 +20,7 @@ #include #include -#include +#include "spitz.h" #include "pxa27x.h" #include "sharpsl_pm.h" diff --git a/sound/soc/pxa/spitz.c b/sound/soc/pxa/spitz.c index 7c1384a869ca..44303b6eb228 100644 --- a/sound/soc/pxa/spitz.c +++ b/sound/soc/pxa/spitz.c @@ -14,13 +14,12 @@ #include #include #include -#include +#include #include #include #include #include -#include #include "../codecs/wm8750.h" #include "pxa2xx-i2s.h" @@ -37,7 +36,7 @@ static int spitz_jack_func; static int spitz_spk_func; -static int spitz_mic_gpio; +static struct gpio_desc *gpiod_mic, *gpiod_mute_l, *gpiod_mute_r; static void spitz_ext_control(struct snd_soc_dapm_context *dapm) { @@ -56,8 +55,8 @@ static void spitz_ext_control(struct snd_soc_dapm_context *dapm) snd_soc_dapm_disable_pin_unlocked(dapm, "Mic Jack"); snd_soc_dapm_disable_pin_unlocked(dapm, "Line Jack"); snd_soc_dapm_enable_pin_unlocked(dapm, "Headphone Jack"); - gpio_set_value(SPITZ_GPIO_MUTE_L, 1); - gpio_set_value(SPITZ_GPIO_MUTE_R, 1); + gpiod_set_value(gpiod_mute_l, 1); + gpiod_set_value(gpiod_mute_r, 1); break; case SPITZ_MIC: /* enable mic jack and bias, mute hp */ @@ -65,8 +64,8 @@ static void spitz_ext_control(struct snd_soc_dapm_context *dapm) snd_soc_dapm_disable_pin_unlocked(dapm, "Headset Jack"); snd_soc_dapm_disable_pin_unlocked(dapm, "Line Jack"); snd_soc_dapm_enable_pin_unlocked(dapm, "Mic Jack"); - gpio_set_value(SPITZ_GPIO_MUTE_L, 0); - gpio_set_value(SPITZ_GPIO_MUTE_R, 0); + gpiod_set_value(gpiod_mute_l, 0); + gpiod_set_value(gpiod_mute_r, 0); break; case SPITZ_LINE: /* enable line jack, disable mic bias and mute hp */ @@ -74,8 +73,8 @@ static void spitz_ext_control(struct snd_soc_dapm_context *dapm) snd_soc_dapm_disable_pin_unlocked(dapm, "Headset Jack"); snd_soc_dapm_disable_pin_unlocked(dapm, "Mic Jack"); snd_soc_dapm_enable_pin_unlocked(dapm, "Line Jack"); - gpio_set_value(SPITZ_GPIO_MUTE_L, 0); - gpio_set_value(SPITZ_GPIO_MUTE_R, 0); + gpiod_set_value(gpiod_mute_l, 0); + gpiod_set_value(gpiod_mute_r, 0); break; case SPITZ_HEADSET: /* enable and unmute headset jack enable mic bias, mute L hp */ @@ -83,8 +82,8 @@ static void spitz_ext_control(struct snd_soc_dapm_context *dapm) snd_soc_dapm_enable_pin_unlocked(dapm, "Mic Jack"); snd_soc_dapm_disable_pin_unlocked(dapm, "Line Jack"); snd_soc_dapm_enable_pin_unlocked(dapm, "Headset Jack"); - gpio_set_value(SPITZ_GPIO_MUTE_L, 0); - gpio_set_value(SPITZ_GPIO_MUTE_R, 1); + gpiod_set_value(gpiod_mute_l, 0); + gpiod_set_value(gpiod_mute_r, 1); break; case SPITZ_HP_OFF: @@ -93,8 +92,8 @@ static void spitz_ext_control(struct snd_soc_dapm_context *dapm) snd_soc_dapm_disable_pin_unlocked(dapm, "Headset Jack"); snd_soc_dapm_disable_pin_unlocked(dapm, "Mic Jack"); snd_soc_dapm_disable_pin_unlocked(dapm, "Line Jack"); - gpio_set_value(SPITZ_GPIO_MUTE_L, 0); - gpio_set_value(SPITZ_GPIO_MUTE_R, 0); + gpiod_set_value(gpiod_mute_l, 0); + gpiod_set_value(gpiod_mute_r, 0); break; } @@ -199,7 +198,7 @@ static int spitz_set_spk(struct snd_kcontrol *kcontrol, static int spitz_mic_bias(struct snd_soc_dapm_widget *w, struct snd_kcontrol *k, int event) { - gpio_set_value_cansleep(spitz_mic_gpio, SND_SOC_DAPM_EVENT_ON(event)); + gpiod_set_value_cansleep(gpiod_mic, SND_SOC_DAPM_EVENT_ON(event)); return 0; } @@ -287,39 +286,28 @@ static int spitz_probe(struct platform_device *pdev) struct snd_soc_card *card = &snd_soc_spitz; int ret; - if (machine_is_akita()) - spitz_mic_gpio = AKITA_GPIO_MIC_BIAS; - else - spitz_mic_gpio = SPITZ_GPIO_MIC_BIAS; - - ret = gpio_request(spitz_mic_gpio, "MIC GPIO"); - if (ret) - goto err1; - - ret = gpio_direction_output(spitz_mic_gpio, 0); - if (ret) - goto err2; + gpiod_mic = devm_gpiod_get(&pdev->dev, "mic", GPIOD_OUT_LOW); + if (IS_ERR(gpiod_mic)) + return PTR_ERR(gpiod_mic); + gpiod_mute_l = devm_gpiod_get(&pdev->dev, "mute-l", GPIOD_OUT_LOW); + if (IS_ERR(gpiod_mute_l)) + return PTR_ERR(gpiod_mute_l); + gpiod_mute_r = devm_gpiod_get(&pdev->dev, "mute-r", GPIOD_OUT_LOW); + if (IS_ERR(gpiod_mute_r)) + return PTR_ERR(gpiod_mute_r); card->dev = &pdev->dev; ret = devm_snd_soc_register_card(&pdev->dev, card); - if (ret) { + if (ret) dev_err(&pdev->dev, "snd_soc_register_card() failed: %d\n", ret); - goto err2; - } - return 0; - -err2: - gpio_free(spitz_mic_gpio); -err1: return ret; } static int spitz_remove(struct platform_device *pdev) { - gpio_free(spitz_mic_gpio); return 0; } From 6f3cb1fd6b4263fb194904cef2fc59738003bdd8 Mon Sep 17 00:00:00 2001 From: Dmitry Torokhov Date: Fri, 28 Jun 2024 11:08:41 -0700 Subject: [PATCH 031/342] ARM: spitz: fix GPIO assignment for backlight [ Upstream commit 78ab3d352f2982bf3f7e506bfbaba7afee1ed8a9 ] GPIOs controlling backlight on Spitz and Akita are coming from GPIO expanders, not the pxa27xx-gpio block, correct it. Additionally GPIO lookup tables operate with pin numbers rather than legacy GPIO numbers, fix that as well. Use raw numbers instead of legacy GPIO names to avoid confusion. Fixes: ee0c8e494cc3 ("backlight: corgi: Convert to use GPIO descriptors") Reviewed-by: Linus Walleij Signed-off-by: Dmitry Torokhov Link: https://lore.kernel.org/r/20240628180852.1738922-2-dmitry.torokhov@gmail.com Signed-off-by: Arnd Bergmann Signed-off-by: Sasha Levin --- arch/arm/mach-pxa/spitz.c | 30 ++++++++++-------------------- 1 file changed, 10 insertions(+), 20 deletions(-) diff --git a/arch/arm/mach-pxa/spitz.c b/arch/arm/mach-pxa/spitz.c index 8f880dbc05fd..9bdc20706d18 100644 --- a/arch/arm/mach-pxa/spitz.c +++ b/arch/arm/mach-pxa/spitz.c @@ -516,10 +516,8 @@ static struct pxa2xx_spi_chip spitz_ads7846_chip = { static struct gpiod_lookup_table spitz_lcdcon_gpio_table = { .dev_id = "spi2.1", .table = { - GPIO_LOOKUP("gpio-pxa", SPITZ_GPIO_BACKLIGHT_CONT, - "BL_CONT", GPIO_ACTIVE_LOW), - GPIO_LOOKUP("gpio-pxa", SPITZ_GPIO_BACKLIGHT_ON, - "BL_ON", GPIO_ACTIVE_HIGH), + GPIO_LOOKUP("sharp-scoop.1", 6, "BL_CONT", GPIO_ACTIVE_LOW), + GPIO_LOOKUP("sharp-scoop.1", 7, "BL_ON", GPIO_ACTIVE_HIGH), { }, }, }; @@ -527,10 +525,8 @@ static struct gpiod_lookup_table spitz_lcdcon_gpio_table = { static struct gpiod_lookup_table akita_lcdcon_gpio_table = { .dev_id = "spi2.1", .table = { - GPIO_LOOKUP("gpio-pxa", AKITA_GPIO_BACKLIGHT_CONT, - "BL_CONT", GPIO_ACTIVE_LOW), - GPIO_LOOKUP("gpio-pxa", AKITA_GPIO_BACKLIGHT_ON, - "BL_ON", GPIO_ACTIVE_HIGH), + GPIO_LOOKUP("i2c-max7310", 3, "BL_ON", GPIO_ACTIVE_HIGH), + GPIO_LOOKUP("i2c-max7310", 4, "BL_CONT", GPIO_ACTIVE_LOW), { }, }, }; @@ -957,12 +953,9 @@ static inline void spitz_i2c_init(void) {} static struct gpiod_lookup_table spitz_audio_gpio_table = { .dev_id = "spitz-audio", .table = { - GPIO_LOOKUP("sharp-scoop.0", SPITZ_GPIO_MUTE_L - SPITZ_SCP_GPIO_BASE, - "mute-l", GPIO_ACTIVE_HIGH), - GPIO_LOOKUP("sharp-scoop.0", SPITZ_GPIO_MUTE_R - SPITZ_SCP_GPIO_BASE, - "mute-r", GPIO_ACTIVE_HIGH), - GPIO_LOOKUP("sharp-scoop.1", SPITZ_GPIO_MIC_BIAS - SPITZ_SCP2_GPIO_BASE, - "mic", GPIO_ACTIVE_HIGH), + GPIO_LOOKUP("sharp-scoop.0", 3, "mute-l", GPIO_ACTIVE_HIGH), + GPIO_LOOKUP("sharp-scoop.0", 4, "mute-r", GPIO_ACTIVE_HIGH), + GPIO_LOOKUP("sharp-scoop.1", 8, "mic", GPIO_ACTIVE_HIGH), { }, }, }; @@ -970,12 +963,9 @@ static struct gpiod_lookup_table spitz_audio_gpio_table = { static struct gpiod_lookup_table akita_audio_gpio_table = { .dev_id = "spitz-audio", .table = { - GPIO_LOOKUP("sharp-scoop.0", SPITZ_GPIO_MUTE_L - SPITZ_SCP_GPIO_BASE, - "mute-l", GPIO_ACTIVE_HIGH), - GPIO_LOOKUP("sharp-scoop.0", SPITZ_GPIO_MUTE_R - SPITZ_SCP_GPIO_BASE, - "mute-r", GPIO_ACTIVE_HIGH), - GPIO_LOOKUP("i2c-max7310", AKITA_GPIO_MIC_BIAS - AKITA_IOEXP_GPIO_BASE, - "mic", GPIO_ACTIVE_HIGH), + GPIO_LOOKUP("sharp-scoop.0", 3, "mute-l", GPIO_ACTIVE_HIGH), + GPIO_LOOKUP("sharp-scoop.0", 4, "mute-r", GPIO_ACTIVE_HIGH), + GPIO_LOOKUP("i2c-max7310", 2, "mic", GPIO_ACTIVE_HIGH), { }, }, }; From 085dc942897c3c59185a0e075df6e17be507851a Mon Sep 17 00:00:00 2001 From: =?UTF-8?q?Marek=20Beh=C3=BAn?= Date: Mon, 15 Jul 2024 13:59:11 +0200 Subject: [PATCH 032/342] firmware: turris-mox-rwtm: Fix checking return value of wait_for_completion_timeout() MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit [ Upstream commit 8467cfe821ac3526f7598682ad5f90689fa8cc49 ] The wait_for_completion_timeout() function returns 0 if timed out, and a positive value if completed. Fix the usage of this function. Fixes: 389711b37493 ("firmware: Add Turris Mox rWTM firmware driver") Fixes: 2eab59cf0d20 ("firmware: turris-mox-rwtm: fail probing when firmware does not support hwrng") Signed-off-by: Marek Behún Reviewed-by: Ilpo Järvinen Reviewed-by: Andy Shevchenko Signed-off-by: Arnd Bergmann Signed-off-by: Sasha Levin --- drivers/firmware/turris-mox-rwtm.c | 15 ++++++--------- 1 file changed, 6 insertions(+), 9 deletions(-) diff --git a/drivers/firmware/turris-mox-rwtm.c b/drivers/firmware/turris-mox-rwtm.c index 0bef988580ad..32c94c306b23 100644 --- a/drivers/firmware/turris-mox-rwtm.c +++ b/drivers/firmware/turris-mox-rwtm.c @@ -199,9 +199,8 @@ static int mox_get_board_info(struct mox_rwtm *rwtm) if (ret < 0) return ret; - ret = wait_for_completion_timeout(&rwtm->cmd_done, HZ / 2); - if (ret < 0) - return ret; + if (!wait_for_completion_timeout(&rwtm->cmd_done, HZ / 2)) + return -ETIMEDOUT; ret = mox_get_status(MBOX_CMD_BOARD_INFO, reply->retval); if (ret == -ENODATA) { @@ -235,9 +234,8 @@ static int mox_get_board_info(struct mox_rwtm *rwtm) if (ret < 0) return ret; - ret = wait_for_completion_timeout(&rwtm->cmd_done, HZ / 2); - if (ret < 0) - return ret; + if (!wait_for_completion_timeout(&rwtm->cmd_done, HZ / 2)) + return -ETIMEDOUT; ret = mox_get_status(MBOX_CMD_ECDSA_PUB_KEY, reply->retval); if (ret == -ENODATA) { @@ -274,9 +272,8 @@ static int check_get_random_support(struct mox_rwtm *rwtm) if (ret < 0) return ret; - ret = wait_for_completion_timeout(&rwtm->cmd_done, HZ / 2); - if (ret < 0) - return ret; + if (!wait_for_completion_timeout(&rwtm->cmd_done, HZ / 2)) + return -ETIMEDOUT; return mox_get_status(MBOX_CMD_GET_RANDOM, rwtm->reply.retval); } From 1eb5751e2369b46af2f561664a417f5d013a046d Mon Sep 17 00:00:00 2001 From: =?UTF-8?q?Marek=20Beh=C3=BAn?= Date: Mon, 15 Jul 2024 13:59:12 +0200 Subject: [PATCH 033/342] firmware: turris-mox-rwtm: Initialize completion before mailbox MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit [ Upstream commit 49e24c80d3c81c43e2a56101449e1eea32fcf292 ] Initialize the completion before the mailbox channel is requested. Fixes: 389711b37493 ("firmware: Add Turris Mox rWTM firmware driver") Signed-off-by: Marek Behún Reviewed-by: Andy Shevchenko Signed-off-by: Arnd Bergmann Signed-off-by: Sasha Levin --- drivers/firmware/turris-mox-rwtm.c | 3 +-- 1 file changed, 1 insertion(+), 2 deletions(-) diff --git a/drivers/firmware/turris-mox-rwtm.c b/drivers/firmware/turris-mox-rwtm.c index 32c94c306b23..dcb717254c79 100644 --- a/drivers/firmware/turris-mox-rwtm.c +++ b/drivers/firmware/turris-mox-rwtm.c @@ -496,6 +496,7 @@ static int turris_mox_rwtm_probe(struct platform_device *pdev) platform_set_drvdata(pdev, rwtm); mutex_init(&rwtm->busy); + init_completion(&rwtm->cmd_done); rwtm->mbox_client.dev = dev; rwtm->mbox_client.rx_callback = mox_rwtm_rx_callback; @@ -509,8 +510,6 @@ static int turris_mox_rwtm_probe(struct platform_device *pdev) goto remove_files; } - init_completion(&rwtm->cmd_done); - ret = mox_get_board_info(rwtm); if (ret < 0) dev_warn(dev, "Cannot read board information: %i\n", ret); From 1302433dc6641490caa387ac927e05df6e7cdf40 Mon Sep 17 00:00:00 2001 From: Samasth Norway Ananda Date: Thu, 9 May 2024 16:10:37 -0700 Subject: [PATCH 034/342] wifi: brcmsmac: LCN PHY code is used for BCM4313 2G-only device [ Upstream commit c636fa85feb450ca414a10010ed05361a73c93a6 ] The band_idx variable in the function wlc_lcnphy_tx_iqlo_cal() will never be set to 1 as BCM4313 is the only device for which the LCN PHY code is used. This is a 2G-only device. Fixes: 5b435de0d786 ("net: wireless: add brcm80211 drivers") Signed-off-by: Samasth Norway Ananda Acked-by: Arend van Spriel Signed-off-by: Kalle Valo Link: https://msgid.link/20240509231037.2014109-1-samasth.norway.ananda@oracle.com Signed-off-by: Sasha Levin --- .../broadcom/brcm80211/brcmsmac/phy/phy_lcn.c | 18 +++++++++--------- 1 file changed, 9 insertions(+), 9 deletions(-) diff --git a/drivers/net/wireless/broadcom/brcm80211/brcmsmac/phy/phy_lcn.c b/drivers/net/wireless/broadcom/brcm80211/brcmsmac/phy/phy_lcn.c index 7717eb85a1db..47c0e8e429e5 100644 --- a/drivers/net/wireless/broadcom/brcm80211/brcmsmac/phy/phy_lcn.c +++ b/drivers/net/wireless/broadcom/brcm80211/brcmsmac/phy/phy_lcn.c @@ -2567,7 +2567,6 @@ wlc_lcnphy_tx_iqlo_cal(struct brcms_phy *pi, struct lcnphy_txgains cal_gains, temp_gains; u16 hash; - u8 band_idx; int j; u16 ncorr_override[5]; u16 syst_coeffs[] = { 0x0000, 0x0000, 0x0000, 0x0000, 0x0000, 0x0000, @@ -2599,6 +2598,9 @@ wlc_lcnphy_tx_iqlo_cal(struct brcms_phy *pi, u16 *values_to_save; struct brcms_phy_lcnphy *pi_lcn = pi->u.pi_lcnphy; + if (WARN_ON(CHSPEC_IS5G(pi->radio_chanspec))) + return; + values_to_save = kmalloc_array(20, sizeof(u16), GFP_ATOMIC); if (NULL == values_to_save) return; @@ -2662,20 +2664,18 @@ wlc_lcnphy_tx_iqlo_cal(struct brcms_phy *pi, hash = (target_gains->gm_gain << 8) | (target_gains->pga_gain << 4) | (target_gains->pad_gain); - band_idx = (CHSPEC_IS5G(pi->radio_chanspec) ? 1 : 0); - cal_gains = *target_gains; memset(ncorr_override, 0, sizeof(ncorr_override)); - for (j = 0; j < iqcal_gainparams_numgains_lcnphy[band_idx]; j++) { - if (hash == tbl_iqcal_gainparams_lcnphy[band_idx][j][0]) { + for (j = 0; j < iqcal_gainparams_numgains_lcnphy[0]; j++) { + if (hash == tbl_iqcal_gainparams_lcnphy[0][j][0]) { cal_gains.gm_gain = - tbl_iqcal_gainparams_lcnphy[band_idx][j][1]; + tbl_iqcal_gainparams_lcnphy[0][j][1]; cal_gains.pga_gain = - tbl_iqcal_gainparams_lcnphy[band_idx][j][2]; + tbl_iqcal_gainparams_lcnphy[0][j][2]; cal_gains.pad_gain = - tbl_iqcal_gainparams_lcnphy[band_idx][j][3]; + tbl_iqcal_gainparams_lcnphy[0][j][3]; memcpy(ncorr_override, - &tbl_iqcal_gainparams_lcnphy[band_idx][j][3], + &tbl_iqcal_gainparams_lcnphy[0][j][3], sizeof(ncorr_override)); break; } From 2f5738bdd6f6c1e7320fd03ac06e061964a31444 Mon Sep 17 00:00:00 2001 From: Geliang Tang Date: Fri, 17 May 2024 14:21:46 +0800 Subject: [PATCH 035/342] selftests/bpf: Fix prog numbers in test_sockmap [ Upstream commit 6c8d7598dfed759bf1d9d0322b4c2b42eb7252d8 ] bpf_prog5 and bpf_prog7 are removed from progs/test_sockmap_kern.h in commit d79a32129b21 ("bpf: Selftests, remove prints from sockmap tests"), now there are only 9 progs in it, not 11: SEC("sk_skb1") int bpf_prog1(struct __sk_buff *skb) SEC("sk_skb2") int bpf_prog2(struct __sk_buff *skb) SEC("sk_skb3") int bpf_prog3(struct __sk_buff *skb) SEC("sockops") int bpf_sockmap(struct bpf_sock_ops *skops) SEC("sk_msg1") int bpf_prog4(struct sk_msg_md *msg) SEC("sk_msg2") int bpf_prog6(struct sk_msg_md *msg) SEC("sk_msg3") int bpf_prog8(struct sk_msg_md *msg) SEC("sk_msg4") int bpf_prog9(struct sk_msg_md *msg) SEC("sk_msg5") int bpf_prog10(struct sk_msg_md *msg) This patch updates the array sizes of prog_fd[], prog_attach_type[] and prog_type[] from 11 to 9 accordingly. Fixes: d79a32129b21 ("bpf: Selftests, remove prints from sockmap tests") Signed-off-by: Geliang Tang Signed-off-by: Andrii Nakryiko Link: https://lore.kernel.org/bpf/9c10d9f974f07fcb354a43a8eca67acb2fafc587.1715926605.git.tanggeliang@kylinos.cn Signed-off-by: Sasha Levin --- tools/testing/selftests/bpf/test_sockmap.c | 6 +----- 1 file changed, 1 insertion(+), 5 deletions(-) diff --git a/tools/testing/selftests/bpf/test_sockmap.c b/tools/testing/selftests/bpf/test_sockmap.c index 85d57633c8b6..daf848258410 100644 --- a/tools/testing/selftests/bpf/test_sockmap.c +++ b/tools/testing/selftests/bpf/test_sockmap.c @@ -65,7 +65,7 @@ int passed; int failed; int map_fd[9]; struct bpf_map *maps[9]; -int prog_fd[11]; +int prog_fd[9]; int txmsg_pass; int txmsg_redir; @@ -1708,8 +1708,6 @@ int prog_attach_type[] = { BPF_SK_MSG_VERDICT, BPF_SK_MSG_VERDICT, BPF_SK_MSG_VERDICT, - BPF_SK_MSG_VERDICT, - BPF_SK_MSG_VERDICT, }; int prog_type[] = { @@ -1722,8 +1720,6 @@ int prog_type[] = { BPF_PROG_TYPE_SK_MSG, BPF_PROG_TYPE_SK_MSG, BPF_PROG_TYPE_SK_MSG, - BPF_PROG_TYPE_SK_MSG, - BPF_PROG_TYPE_SK_MSG, }; static int populate_progs(char *bpf_file) From 8d0d50a8b73816ecb7839b2df3b7d317c24b79e4 Mon Sep 17 00:00:00 2001 From: Hagar Hemdan Date: Sat, 18 May 2024 13:04:39 +0000 Subject: [PATCH 036/342] net: esp: cleanup esp_output_tail_tcp() in case of unsupported ESPINTCP [ Upstream commit 96f887a612e4cda89efc3f54bc10c1997e3ab0e9 ] xmit() functions should consume skb or return error codes in error paths. When the configuration "CONFIG_INET_ESPINTCP" is not set, the implementation of the function "esp_output_tail_tcp" violates this rule. The function frees the skb and returns the error code. This change removes the kfree_skb from both functions, for both esp4 and esp6. WARN_ON is added because esp_output_tail_tcp() should never be called if CONFIG_INET_ESPINTCP is not set. This bug was discovered and resolved using Coverity Static Analysis Security Testing (SAST) by Synopsys, Inc. Fixes: e27cca96cd68 ("xfrm: add espintcp (RFC 8229)") Signed-off-by: Hagar Hemdan Signed-off-by: Steffen Klassert Signed-off-by: Sasha Levin --- net/ipv4/esp4.c | 3 +-- net/ipv6/esp6.c | 3 +-- 2 files changed, 2 insertions(+), 4 deletions(-) diff --git a/net/ipv4/esp4.c b/net/ipv4/esp4.c index 412a3c153cad..adfefcd88bbc 100644 --- a/net/ipv4/esp4.c +++ b/net/ipv4/esp4.c @@ -239,8 +239,7 @@ static int esp_output_tail_tcp(struct xfrm_state *x, struct sk_buff *skb) #else static int esp_output_tail_tcp(struct xfrm_state *x, struct sk_buff *skb) { - kfree_skb(skb); - + WARN_ON(1); return -EOPNOTSUPP; } #endif diff --git a/net/ipv6/esp6.c b/net/ipv6/esp6.c index fddc811bbde1..39154531d455 100644 --- a/net/ipv6/esp6.c +++ b/net/ipv6/esp6.c @@ -255,8 +255,7 @@ static int esp_output_tail_tcp(struct xfrm_state *x, struct sk_buff *skb) #else static int esp_output_tail_tcp(struct xfrm_state *x, struct sk_buff *skb) { - kfree_skb(skb); - + WARN_ON(1); return -EOPNOTSUPP; } #endif From 15c2ec7c284dfbaac2cdac92cb8b484be0d0eaa8 Mon Sep 17 00:00:00 2001 From: Stefan Raspl Date: Mon, 9 Aug 2021 10:10:14 +0200 Subject: [PATCH 037/342] net/smc: Allow SMC-D 1MB DMB allocations [ Upstream commit 67161779a9ea926fccee8de047ae66cbd3482b91 ] Commit a3fe3d01bd0d7 ("net/smc: introduce sg-logic for RMBs") introduced a restriction for RMB allocations as used by SMC-R. However, SMC-D does not use scatter-gather lists to back its DMBs, yet it was limited by this restriction, still. This patch exempts SMC, but limits allocations to the maximum RMB/DMB size respectively. Signed-off-by: Stefan Raspl Signed-off-by: Guvenc Gulce Signed-off-by: David S. Miller Stable-dep-of: 3ac14b9dfbd3 ("net/smc: set rmb's SG_MAX_SINGLE_ALLOC limitation only when CONFIG_ARCH_NO_SG_CHAIN is defined") Signed-off-by: Sasha Levin --- net/smc/smc_core.c | 31 ++++++++++++++++--------------- 1 file changed, 16 insertions(+), 15 deletions(-) diff --git a/net/smc/smc_core.c b/net/smc/smc_core.c index ab9ecdd1af0a..701bfc2bab23 100644 --- a/net/smc/smc_core.c +++ b/net/smc/smc_core.c @@ -1375,21 +1375,30 @@ int smc_conn_create(struct smc_sock *smc, struct smc_init_info *ini) return rc; } -/* convert the RMB size into the compressed notation - minimum 16K. +#define SMCD_DMBE_SIZES 6 /* 0 -> 16KB, 1 -> 32KB, .. 6 -> 1MB */ +#define SMCR_RMBE_SIZES 5 /* 0 -> 16KB, 1 -> 32KB, .. 5 -> 512KB */ + +/* convert the RMB size into the compressed notation (minimum 16K, see + * SMCD/R_DMBE_SIZES. * In contrast to plain ilog2, this rounds towards the next power of 2, * so the socket application gets at least its desired sndbuf / rcvbuf size. */ -static u8 smc_compress_bufsize(int size) +static u8 smc_compress_bufsize(int size, bool is_smcd, bool is_rmb) { + const unsigned int max_scat = SG_MAX_SINGLE_ALLOC * PAGE_SIZE; u8 compressed; if (size <= SMC_BUF_MIN_SIZE) return 0; - size = (size - 1) >> 14; - compressed = ilog2(size) + 1; - if (compressed >= SMC_RMBE_SIZES) - compressed = SMC_RMBE_SIZES - 1; + size = (size - 1) >> 14; /* convert to 16K multiple */ + compressed = min_t(u8, ilog2(size) + 1, + is_smcd ? SMCD_DMBE_SIZES : SMCR_RMBE_SIZES); + + if (!is_smcd && is_rmb) + /* RMBs are backed by & limited to max size of scatterlists */ + compressed = min_t(u8, compressed, ilog2(max_scat >> 14)); + return compressed; } @@ -1608,17 +1617,12 @@ static int smcr_buf_map_usable_links(struct smc_link_group *lgr, return rc; } -#define SMCD_DMBE_SIZES 6 /* 0 -> 16KB, 1 -> 32KB, .. 6 -> 1MB */ - static struct smc_buf_desc *smcd_new_buf_create(struct smc_link_group *lgr, bool is_dmb, int bufsize) { struct smc_buf_desc *buf_desc; int rc; - if (smc_compress_bufsize(bufsize) > SMCD_DMBE_SIZES) - return ERR_PTR(-EAGAIN); - /* try to alloc a new DMB */ buf_desc = kzalloc(sizeof(*buf_desc), GFP_KERNEL); if (!buf_desc) @@ -1666,9 +1670,8 @@ static int __smc_buf_create(struct smc_sock *smc, bool is_smcd, bool is_rmb) /* use socket send buffer size (w/o overhead) as start value */ sk_buf_size = smc->sk.sk_sndbuf / 2; - for (bufsize_short = smc_compress_bufsize(sk_buf_size); + for (bufsize_short = smc_compress_bufsize(sk_buf_size, is_smcd, is_rmb); bufsize_short >= 0; bufsize_short--) { - if (is_rmb) { lock = &lgr->rmbs_lock; buf_list = &lgr->rmbs[bufsize_short]; @@ -1677,8 +1680,6 @@ static int __smc_buf_create(struct smc_sock *smc, bool is_smcd, bool is_rmb) buf_list = &lgr->sndbufs[bufsize_short]; } bufsize = smc_uncompress_bufsize(bufsize_short); - if ((1 << get_order(bufsize)) > SG_MAX_SINGLE_ALLOC) - continue; /* check for reusable slot in the link group */ buf_desc = smc_buf_get_slot(bufsize_short, lock, buf_list); From 249adb30cbc78cd88e2d1f4db168a0ac79fc3f68 Mon Sep 17 00:00:00 2001 From: Guangguan Wang Date: Mon, 3 Jun 2024 11:00:18 +0800 Subject: [PATCH 038/342] net/smc: set rmb's SG_MAX_SINGLE_ALLOC limitation only when CONFIG_ARCH_NO_SG_CHAIN is defined [ Upstream commit 3ac14b9dfbd345e891d48d89f6c2fa519848f0f4 ] SG_MAX_SINGLE_ALLOC is used to limit maximum number of entries that will be allocated in one piece of scatterlist. When the entries of scatterlist exceeds SG_MAX_SINGLE_ALLOC, sg chain will be used. From commit 7c703e54cc71 ("arch: switch the default on ARCH_HAS_SG_CHAIN"), we can know that the macro CONFIG_ARCH_NO_SG_CHAIN is used to identify whether sg chain is supported. So, SMC-R's rmb buffer should be limited by SG_MAX_SINGLE_ALLOC only when the macro CONFIG_ARCH_NO_SG_CHAIN is defined. Fixes: a3fe3d01bd0d ("net/smc: introduce sg-logic for RMBs") Signed-off-by: Guangguan Wang Co-developed-by: Wen Gu Signed-off-by: Wen Gu Signed-off-by: David S. Miller Signed-off-by: Sasha Levin --- net/smc/smc_core.c | 5 +++-- 1 file changed, 3 insertions(+), 2 deletions(-) diff --git a/net/smc/smc_core.c b/net/smc/smc_core.c index 701bfc2bab23..0e9d22e9c760 100644 --- a/net/smc/smc_core.c +++ b/net/smc/smc_core.c @@ -1385,7 +1385,6 @@ int smc_conn_create(struct smc_sock *smc, struct smc_init_info *ini) */ static u8 smc_compress_bufsize(int size, bool is_smcd, bool is_rmb) { - const unsigned int max_scat = SG_MAX_SINGLE_ALLOC * PAGE_SIZE; u8 compressed; if (size <= SMC_BUF_MIN_SIZE) @@ -1395,9 +1394,11 @@ static u8 smc_compress_bufsize(int size, bool is_smcd, bool is_rmb) compressed = min_t(u8, ilog2(size) + 1, is_smcd ? SMCD_DMBE_SIZES : SMCR_RMBE_SIZES); +#ifdef CONFIG_ARCH_NO_SG_CHAIN if (!is_smcd && is_rmb) /* RMBs are backed by & limited to max size of scatterlists */ - compressed = min_t(u8, compressed, ilog2(max_scat >> 14)); + compressed = min_t(u8, compressed, ilog2((SG_MAX_SINGLE_ALLOC * PAGE_SIZE) >> 14)); +#endif return compressed; } From ada0c319253a6aad4f82dd2c29bf15d8feecbcf8 Mon Sep 17 00:00:00 2001 From: Geliang Tang Date: Thu, 23 May 2024 14:50:03 +0800 Subject: [PATCH 039/342] selftests/bpf: Check length of recv in test_sockmap [ Upstream commit de1b5ea789dc28066cc8dc634b6825bd6148f38b ] The value of recv in msg_loop may be negative, like EWOULDBLOCK, so it's necessary to check if it is positive before accumulating it to bytes_recvd. Fixes: 16962b2404ac ("bpf: sockmap, add selftests") Signed-off-by: Geliang Tang Signed-off-by: Daniel Borkmann Tested-by: Jakub Sitnicki Acked-by: John Fastabend Link: https://lore.kernel.org/bpf/5172563f7c7b2a2e953cef02e89fc34664a7b190.1716446893.git.tanggeliang@kylinos.cn Signed-off-by: Sasha Levin --- tools/testing/selftests/bpf/test_sockmap.c | 3 ++- 1 file changed, 2 insertions(+), 1 deletion(-) diff --git a/tools/testing/selftests/bpf/test_sockmap.c b/tools/testing/selftests/bpf/test_sockmap.c index daf848258410..61be5993416e 100644 --- a/tools/testing/selftests/bpf/test_sockmap.c +++ b/tools/testing/selftests/bpf/test_sockmap.c @@ -663,7 +663,8 @@ static int msg_loop(int fd, int iov_count, int iov_length, int cnt, } } - s->bytes_recvd += recv; + if (recv > 0) + s->bytes_recvd += recv; if (data) { int chunk_sz = opt->sendpage ? From 22ae17a267f4812861f0c644186c3421ff97dbfc Mon Sep 17 00:00:00 2001 From: Ido Schimmel Date: Thu, 6 Jun 2024 16:49:41 +0200 Subject: [PATCH 040/342] lib: objagg: Fix general protection fault [ Upstream commit b4a3a89fffcdf09702b1f161b914e52abca1894d ] The library supports aggregation of objects into other objects only if the parent object does not have a parent itself. That is, nesting is not supported. Aggregation happens in two cases: Without and with hints, where hints are a pre-computed recommendation on how to aggregate the provided objects. Nesting is not possible in the first case due to a check that prevents it, but in the second case there is no check because the assumption is that nesting cannot happen when creating objects based on hints. The violation of this assumption leads to various warnings and eventually to a general protection fault [1]. Before fixing the root cause, error out when nesting happens and warn. [1] general protection fault, probably for non-canonical address 0xdead000000000d90: 0000 [#1] PREEMPT SMP PTI CPU: 1 PID: 1083 Comm: kworker/1:9 Tainted: G W 6.9.0-rc6-custom-gd9b4f1cca7fb #7 Hardware name: Mellanox Technologies Ltd. MSN3700/VMOD0005, BIOS 5.11 01/06/2019 Workqueue: mlxsw_core mlxsw_sp_acl_tcam_vregion_rehash_work RIP: 0010:mlxsw_sp_acl_erp_bf_insert+0x25/0x80 [...] Call Trace: mlxsw_sp_acl_atcam_entry_add+0x256/0x3c0 mlxsw_sp_acl_tcam_entry_create+0x5e/0xa0 mlxsw_sp_acl_tcam_vchunk_migrate_one+0x16b/0x270 mlxsw_sp_acl_tcam_vregion_rehash_work+0xbe/0x510 process_one_work+0x151/0x370 worker_thread+0x2cb/0x3e0 kthread+0xd0/0x100 ret_from_fork+0x34/0x50 ret_from_fork_asm+0x1a/0x30 Fixes: 9069a3817d82 ("lib: objagg: implement optimization hints assembly and use hints for object creation") Reported-by: Alexander Zubkov Signed-off-by: Ido Schimmel Reviewed-by: Amit Cohen Tested-by: Alexander Zubkov Signed-off-by: Petr Machata Reviewed-by: Simon Horman Signed-off-by: David S. Miller Signed-off-by: Sasha Levin --- lib/objagg.c | 3 +++ 1 file changed, 3 insertions(+) diff --git a/lib/objagg.c b/lib/objagg.c index 5e1676ccdadd..73d711602573 100644 --- a/lib/objagg.c +++ b/lib/objagg.c @@ -167,6 +167,9 @@ static int objagg_obj_parent_assign(struct objagg *objagg, { void *delta_priv; + if (WARN_ON(!objagg_obj_is_root(parent))) + return -EINVAL; + delta_priv = objagg->ops->delta_create(objagg->priv, parent->obj, objagg_obj->obj); if (IS_ERR(delta_priv)) From 36a9996e020dd5aa325e0ecc55eb2328288ea6bb Mon Sep 17 00:00:00 2001 From: Ido Schimmel Date: Thu, 6 Jun 2024 16:49:42 +0200 Subject: [PATCH 041/342] mlxsw: spectrum_acl_erp: Fix object nesting warning [ Upstream commit 97d833ceb27dc19f8777d63f90be4a27b5daeedf ] ACLs in Spectrum-2 and newer ASICs can reside in the algorithmic TCAM (A-TCAM) or in the ordinary circuit TCAM (C-TCAM). The former can contain more ACLs (i.e., tc filters), but the number of masks in each region (i.e., tc chain) is limited. In order to mitigate the effects of the above limitation, the device allows filters to share a single mask if their masks only differ in up to 8 consecutive bits. For example, dst_ip/25 can be represented using dst_ip/24 with a delta of 1 bit. The C-TCAM does not have a limit on the number of masks being used (and therefore does not support mask aggregation), but can contain a limited number of filters. The driver uses the "objagg" library to perform the mask aggregation by passing it objects that consist of the filter's mask and whether the filter is to be inserted into the A-TCAM or the C-TCAM since filters in different TCAMs cannot share a mask. The set of created objects is dependent on the insertion order of the filters and is not necessarily optimal. Therefore, the driver will periodically ask the library to compute a more optimal set ("hints") by looking at all the existing objects. When the library asks the driver whether two objects can be aggregated the driver only compares the provided masks and ignores the A-TCAM / C-TCAM indication. This is the right thing to do since the goal is to move as many filters as possible to the A-TCAM. The driver also forbids two identical masks from being aggregated since this can only happen if one was intentionally put in the C-TCAM to avoid a conflict in the A-TCAM. The above can result in the following set of hints: H1: {mask X, A-TCAM} -> H2: {mask Y, A-TCAM} // X is Y + delta H3: {mask Y, C-TCAM} -> H4: {mask Z, A-TCAM} // Y is Z + delta After getting the hints from the library the driver will start migrating filters from one region to another while consulting the computed hints and instructing the device to perform a lookup in both regions during the transition. Assuming a filter with mask X is being migrated into the A-TCAM in the new region, the hints lookup will return H1. Since H2 is the parent of H1, the library will try to find the object associated with it and create it if necessary in which case another hints lookup (recursive) will be performed. This hints lookup for {mask Y, A-TCAM} will either return H2 or H3 since the driver passes the library an object comparison function that ignores the A-TCAM / C-TCAM indication. This can eventually lead to nested objects which are not supported by the library [1]. Fix by removing the object comparison function from both the driver and the library as the driver was the only user. That way the lookup will only return exact matches. I do not have a reliable reproducer that can reproduce the issue in a timely manner, but before the fix the issue would reproduce in several minutes and with the fix it does not reproduce in over an hour. Note that the current usefulness of the hints is limited because they include the C-TCAM indication and represent aggregation that cannot actually happen. This will be addressed in net-next. [1] WARNING: CPU: 0 PID: 153 at lib/objagg.c:170 objagg_obj_parent_assign+0xb5/0xd0 Modules linked in: CPU: 0 PID: 153 Comm: kworker/0:18 Not tainted 6.9.0-rc6-custom-g70fbc2c1c38b #42 Hardware name: Mellanox Technologies Ltd. MSN3700C/VMOD0008, BIOS 5.11 10/10/2018 Workqueue: mlxsw_core mlxsw_sp_acl_tcam_vregion_rehash_work RIP: 0010:objagg_obj_parent_assign+0xb5/0xd0 [...] Call Trace: __objagg_obj_get+0x2bb/0x580 objagg_obj_get+0xe/0x80 mlxsw_sp_acl_erp_mask_get+0xb5/0xf0 mlxsw_sp_acl_atcam_entry_add+0xe8/0x3c0 mlxsw_sp_acl_tcam_entry_create+0x5e/0xa0 mlxsw_sp_acl_tcam_vchunk_migrate_one+0x16b/0x270 mlxsw_sp_acl_tcam_vregion_rehash_work+0xbe/0x510 process_one_work+0x151/0x370 Fixes: 9069a3817d82 ("lib: objagg: implement optimization hints assembly and use hints for object creation") Signed-off-by: Ido Schimmel Reviewed-by: Amit Cohen Tested-by: Alexander Zubkov Signed-off-by: Petr Machata Reviewed-by: Simon Horman Signed-off-by: David S. Miller Signed-off-by: Sasha Levin --- .../ethernet/mellanox/mlxsw/spectrum_acl_erp.c | 13 ------------- include/linux/objagg.h | 1 - lib/objagg.c | 15 --------------- 3 files changed, 29 deletions(-) diff --git a/drivers/net/ethernet/mellanox/mlxsw/spectrum_acl_erp.c b/drivers/net/ethernet/mellanox/mlxsw/spectrum_acl_erp.c index d231f4d2888b..9eee229303cc 100644 --- a/drivers/net/ethernet/mellanox/mlxsw/spectrum_acl_erp.c +++ b/drivers/net/ethernet/mellanox/mlxsw/spectrum_acl_erp.c @@ -1217,18 +1217,6 @@ static bool mlxsw_sp_acl_erp_delta_check(void *priv, const void *parent_obj, return err ? false : true; } -static int mlxsw_sp_acl_erp_hints_obj_cmp(const void *obj1, const void *obj2) -{ - const struct mlxsw_sp_acl_erp_key *key1 = obj1; - const struct mlxsw_sp_acl_erp_key *key2 = obj2; - - /* For hints purposes, two objects are considered equal - * in case the masks are the same. Does not matter what - * the "ctcam" value is. - */ - return memcmp(key1->mask, key2->mask, sizeof(key1->mask)); -} - static void *mlxsw_sp_acl_erp_delta_create(void *priv, void *parent_obj, void *obj) { @@ -1308,7 +1296,6 @@ static void mlxsw_sp_acl_erp_root_destroy(void *priv, void *root_priv) static const struct objagg_ops mlxsw_sp_acl_erp_objagg_ops = { .obj_size = sizeof(struct mlxsw_sp_acl_erp_key), .delta_check = mlxsw_sp_acl_erp_delta_check, - .hints_obj_cmp = mlxsw_sp_acl_erp_hints_obj_cmp, .delta_create = mlxsw_sp_acl_erp_delta_create, .delta_destroy = mlxsw_sp_acl_erp_delta_destroy, .root_create = mlxsw_sp_acl_erp_root_create, diff --git a/include/linux/objagg.h b/include/linux/objagg.h index 78021777df46..6df5b887dc54 100644 --- a/include/linux/objagg.h +++ b/include/linux/objagg.h @@ -8,7 +8,6 @@ struct objagg_ops { size_t obj_size; bool (*delta_check)(void *priv, const void *parent_obj, const void *obj); - int (*hints_obj_cmp)(const void *obj1, const void *obj2); void * (*delta_create)(void *priv, void *parent_obj, void *obj); void (*delta_destroy)(void *priv, void *delta_priv); void * (*root_create)(void *priv, void *obj, unsigned int root_id); diff --git a/lib/objagg.c b/lib/objagg.c index 73d711602573..57bde522f249 100644 --- a/lib/objagg.c +++ b/lib/objagg.c @@ -909,20 +909,6 @@ static const struct objagg_opt_algo *objagg_opt_algos[] = { [OBJAGG_OPT_ALGO_SIMPLE_GREEDY] = &objagg_opt_simple_greedy, }; -static int objagg_hints_obj_cmp(struct rhashtable_compare_arg *arg, - const void *obj) -{ - struct rhashtable *ht = arg->ht; - struct objagg_hints *objagg_hints = - container_of(ht, struct objagg_hints, node_ht); - const struct objagg_ops *ops = objagg_hints->ops; - const char *ptr = obj; - - ptr += ht->p.key_offset; - return ops->hints_obj_cmp ? ops->hints_obj_cmp(ptr, arg->key) : - memcmp(ptr, arg->key, ht->p.key_len); -} - /** * objagg_hints_get - obtains hints instance * @objagg: objagg instance @@ -961,7 +947,6 @@ struct objagg_hints *objagg_hints_get(struct objagg *objagg, offsetof(struct objagg_hints_node, obj); objagg_hints->ht_params.head_offset = offsetof(struct objagg_hints_node, ht_node); - objagg_hints->ht_params.obj_cmpfn = objagg_hints_obj_cmp; err = rhashtable_init(&objagg_hints->node_ht, &objagg_hints->ht_params); if (err) From aa98eb0740510e61926f6526ab1cbf933839e1e0 Mon Sep 17 00:00:00 2001 From: Amit Cohen Date: Thu, 6 Jan 2022 18:06:48 +0200 Subject: [PATCH 042/342] mlxsw: spectrum_acl_bloom_filter: Make mlxsw_sp_acl_bf_key_encode() more flexible [ Upstream commit 5d5c3ba9e4121b7738d10be3825f4d9a5a1d80ef ] Spectrum-4 will calculate hash function for bloom filter differently from the existing ASICs. One of the changes is related to the way that the chunks will be build - without padding. As preparation for support of Spectrum-4 bloom filter, make mlxsw_sp_acl_bf_key_encode() more flexible, so it will be able to use it for Spectrum-4 as well. Signed-off-by: Amit Cohen Reviewed-by: Petr Machata Signed-off-by: Ido Schimmel Signed-off-by: Jakub Kicinski Stable-dep-of: 75d8d7a63065 ("mlxsw: spectrum_acl: Fix ACL scale regression and firmware errors") Signed-off-by: Sasha Levin --- .../mlxsw/spectrum_acl_bloom_filter.c | 36 +++++++++++++------ 1 file changed, 25 insertions(+), 11 deletions(-) diff --git a/drivers/net/ethernet/mellanox/mlxsw/spectrum_acl_bloom_filter.c b/drivers/net/ethernet/mellanox/mlxsw/spectrum_acl_bloom_filter.c index 2e8b17e3b935..2d2e29c20277 100644 --- a/drivers/net/ethernet/mellanox/mlxsw/spectrum_acl_bloom_filter.c +++ b/drivers/net/ethernet/mellanox/mlxsw/spectrum_acl_bloom_filter.c @@ -116,9 +116,10 @@ static u16 mlxsw_sp_acl_bf_crc(const u8 *buffer, size_t len) } static void -mlxsw_sp_acl_bf_key_encode(struct mlxsw_sp_acl_atcam_region *aregion, - struct mlxsw_sp_acl_atcam_entry *aentry, - char *output, u8 *len) +__mlxsw_sp_acl_bf_key_encode(struct mlxsw_sp_acl_atcam_region *aregion, + struct mlxsw_sp_acl_atcam_entry *aentry, + char *output, u8 *len, u8 max_chunks, u8 pad_bytes, + u8 key_offset, u8 chunk_key_len, u8 chunk_len) { struct mlxsw_afk_key_info *key_info = aregion->region->key_info; u8 chunk_index, chunk_count, block_count; @@ -129,17 +130,30 @@ mlxsw_sp_acl_bf_key_encode(struct mlxsw_sp_acl_atcam_region *aregion, chunk_count = 1 + ((block_count - 1) >> 2); erp_region_id = cpu_to_be16(aentry->ht_key.erp_id | (aregion->region->id << 4)); - for (chunk_index = MLXSW_BLOOM_KEY_CHUNKS - chunk_count; - chunk_index < MLXSW_BLOOM_KEY_CHUNKS; chunk_index++) { - memset(chunk, 0, MLXSW_BLOOM_CHUNK_PAD_BYTES); - memcpy(chunk + MLXSW_BLOOM_CHUNK_PAD_BYTES, &erp_region_id, + for (chunk_index = max_chunks - chunk_count; chunk_index < max_chunks; + chunk_index++) { + memset(chunk, 0, pad_bytes); + memcpy(chunk + pad_bytes, &erp_region_id, sizeof(erp_region_id)); - memcpy(chunk + MLXSW_BLOOM_CHUNK_KEY_OFFSET, + memcpy(chunk + key_offset, &aentry->enc_key[chunk_key_offsets[chunk_index]], - MLXSW_BLOOM_CHUNK_KEY_BYTES); - chunk += MLXSW_BLOOM_KEY_CHUNK_BYTES; + chunk_key_len); + chunk += chunk_len; } - *len = chunk_count * MLXSW_BLOOM_KEY_CHUNK_BYTES; + *len = chunk_count * chunk_len; +} + +static void +mlxsw_sp_acl_bf_key_encode(struct mlxsw_sp_acl_atcam_region *aregion, + struct mlxsw_sp_acl_atcam_entry *aentry, + char *output, u8 *len) +{ + __mlxsw_sp_acl_bf_key_encode(aregion, aentry, output, len, + MLXSW_BLOOM_KEY_CHUNKS, + MLXSW_BLOOM_CHUNK_PAD_BYTES, + MLXSW_BLOOM_CHUNK_KEY_OFFSET, + MLXSW_BLOOM_CHUNK_KEY_BYTES, + MLXSW_BLOOM_KEY_CHUNK_BYTES); } static unsigned int From dae1ab70406e58657626c3449d3822739e1454f4 Mon Sep 17 00:00:00 2001 From: Ido Schimmel Date: Thu, 6 Jun 2024 16:49:43 +0200 Subject: [PATCH 043/342] mlxsw: spectrum_acl: Fix ACL scale regression and firmware errors [ Upstream commit 75d8d7a63065b18df9555dbaab0b42d4c6f20943 ] ACLs that reside in the algorithmic TCAM (A-TCAM) in Spectrum-2 and newer ASICs can share the same mask if their masks only differ in up to 8 consecutive bits. For example, consider the following filters: # tc filter add dev swp1 ingress pref 1 proto ip flower dst_ip 192.0.2.0/24 action drop # tc filter add dev swp1 ingress pref 1 proto ip flower dst_ip 198.51.100.128/25 action drop The second filter can use the same mask as the first (dst_ip/24) with a delta of 1 bit. However, the above only works because the two filters have different values in the common unmasked part (dst_ip/24). When entries have the same value in the common unmasked part they create undesired collisions in the device since many entries now have the same key. This leads to firmware errors such as [1] and to a reduced scale. Fix by adjusting the hash table key to only include the value in the common unmasked part. That is, without including the delta bits. That way the driver will detect the collision during filter insertion and spill the filter into the circuit TCAM (C-TCAM). Add a test case that fails without the fix and adjust existing cases that check C-TCAM spillage according to the above limitation. [1] mlxsw_spectrum2 0000:06:00.0: EMAD reg access failed (tid=3379b18a00003394,reg_id=3027(ptce3),type=write,status=8(resource not available)) Fixes: c22291f7cf45 ("mlxsw: spectrum: acl: Implement delta for ERP") Reported-by: Alexander Zubkov Signed-off-by: Ido Schimmel Reviewed-by: Amit Cohen Tested-by: Alexander Zubkov Signed-off-by: Petr Machata Reviewed-by: Simon Horman Signed-off-by: David S. Miller Signed-off-by: Sasha Levin --- .../mellanox/mlxsw/spectrum_acl_atcam.c | 18 +++--- .../mlxsw/spectrum_acl_bloom_filter.c | 2 +- .../mellanox/mlxsw/spectrum_acl_tcam.h | 9 +-- .../drivers/net/mlxsw/spectrum-2/tc_flower.sh | 55 +++++++++++++++++-- 4 files changed, 63 insertions(+), 21 deletions(-) diff --git a/drivers/net/ethernet/mellanox/mlxsw/spectrum_acl_atcam.c b/drivers/net/ethernet/mellanox/mlxsw/spectrum_acl_atcam.c index 4b713832fdd5..f5c0a4214c4e 100644 --- a/drivers/net/ethernet/mellanox/mlxsw/spectrum_acl_atcam.c +++ b/drivers/net/ethernet/mellanox/mlxsw/spectrum_acl_atcam.c @@ -391,7 +391,8 @@ mlxsw_sp_acl_atcam_region_entry_insert(struct mlxsw_sp *mlxsw_sp, if (err) return err; - lkey_id = aregion->ops->lkey_id_get(aregion, aentry->enc_key, erp_id); + lkey_id = aregion->ops->lkey_id_get(aregion, aentry->ht_key.enc_key, + erp_id); if (IS_ERR(lkey_id)) return PTR_ERR(lkey_id); aentry->lkey_id = lkey_id; @@ -399,7 +400,7 @@ mlxsw_sp_acl_atcam_region_entry_insert(struct mlxsw_sp *mlxsw_sp, kvdl_index = mlxsw_afa_block_first_kvdl_index(rulei->act_block); mlxsw_reg_ptce3_pack(ptce3_pl, true, MLXSW_REG_PTCE3_OP_WRITE_WRITE, priority, region->tcam_region_info, - aentry->enc_key, erp_id, + aentry->ht_key.enc_key, erp_id, aentry->delta_info.start, aentry->delta_info.mask, aentry->delta_info.value, @@ -428,7 +429,7 @@ mlxsw_sp_acl_atcam_region_entry_remove(struct mlxsw_sp *mlxsw_sp, mlxsw_reg_ptce3_pack(ptce3_pl, false, MLXSW_REG_PTCE3_OP_WRITE_WRITE, 0, region->tcam_region_info, - aentry->enc_key, erp_id, + aentry->ht_key.enc_key, erp_id, aentry->delta_info.start, aentry->delta_info.mask, aentry->delta_info.value, @@ -457,7 +458,7 @@ mlxsw_sp_acl_atcam_region_entry_action_replace(struct mlxsw_sp *mlxsw_sp, kvdl_index = mlxsw_afa_block_first_kvdl_index(rulei->act_block); mlxsw_reg_ptce3_pack(ptce3_pl, true, MLXSW_REG_PTCE3_OP_WRITE_UPDATE, priority, region->tcam_region_info, - aentry->enc_key, erp_id, + aentry->ht_key.enc_key, erp_id, aentry->delta_info.start, aentry->delta_info.mask, aentry->delta_info.value, @@ -480,15 +481,13 @@ __mlxsw_sp_acl_atcam_entry_add(struct mlxsw_sp *mlxsw_sp, int err; mlxsw_afk_encode(afk, region->key_info, &rulei->values, - aentry->ht_key.full_enc_key, mask); + aentry->ht_key.enc_key, mask); erp_mask = mlxsw_sp_acl_erp_mask_get(aregion, mask, false); if (IS_ERR(erp_mask)) return PTR_ERR(erp_mask); aentry->erp_mask = erp_mask; aentry->ht_key.erp_id = mlxsw_sp_acl_erp_mask_erp_id(erp_mask); - memcpy(aentry->enc_key, aentry->ht_key.full_enc_key, - sizeof(aentry->enc_key)); /* Compute all needed delta information and clear the delta bits * from the encrypted key. @@ -497,9 +496,8 @@ __mlxsw_sp_acl_atcam_entry_add(struct mlxsw_sp *mlxsw_sp, aentry->delta_info.start = mlxsw_sp_acl_erp_delta_start(delta); aentry->delta_info.mask = mlxsw_sp_acl_erp_delta_mask(delta); aentry->delta_info.value = - mlxsw_sp_acl_erp_delta_value(delta, - aentry->ht_key.full_enc_key); - mlxsw_sp_acl_erp_delta_clear(delta, aentry->enc_key); + mlxsw_sp_acl_erp_delta_value(delta, aentry->ht_key.enc_key); + mlxsw_sp_acl_erp_delta_clear(delta, aentry->ht_key.enc_key); /* Add rule to the list of A-TCAM rules, assuming this * rule is intended to A-TCAM. In case this rule does diff --git a/drivers/net/ethernet/mellanox/mlxsw/spectrum_acl_bloom_filter.c b/drivers/net/ethernet/mellanox/mlxsw/spectrum_acl_bloom_filter.c index 2d2e29c20277..3ab87db83b7f 100644 --- a/drivers/net/ethernet/mellanox/mlxsw/spectrum_acl_bloom_filter.c +++ b/drivers/net/ethernet/mellanox/mlxsw/spectrum_acl_bloom_filter.c @@ -136,7 +136,7 @@ __mlxsw_sp_acl_bf_key_encode(struct mlxsw_sp_acl_atcam_region *aregion, memcpy(chunk + pad_bytes, &erp_region_id, sizeof(erp_region_id)); memcpy(chunk + key_offset, - &aentry->enc_key[chunk_key_offsets[chunk_index]], + &aentry->ht_key.enc_key[chunk_key_offsets[chunk_index]], chunk_key_len); chunk += chunk_len; } diff --git a/drivers/net/ethernet/mellanox/mlxsw/spectrum_acl_tcam.h b/drivers/net/ethernet/mellanox/mlxsw/spectrum_acl_tcam.h index a41df10ade9b..f28c47ae5488 100644 --- a/drivers/net/ethernet/mellanox/mlxsw/spectrum_acl_tcam.h +++ b/drivers/net/ethernet/mellanox/mlxsw/spectrum_acl_tcam.h @@ -171,9 +171,9 @@ struct mlxsw_sp_acl_atcam_region { }; struct mlxsw_sp_acl_atcam_entry_ht_key { - char full_enc_key[MLXSW_REG_PTCEX_FLEX_KEY_BLOCKS_LEN]; /* Encoded - * key. - */ + char enc_key[MLXSW_REG_PTCEX_FLEX_KEY_BLOCKS_LEN]; /* Encoded key, minus + * delta bits. + */ u8 erp_id; }; @@ -185,9 +185,6 @@ struct mlxsw_sp_acl_atcam_entry { struct rhash_head ht_node; struct list_head list; /* Member in entries_list */ struct mlxsw_sp_acl_atcam_entry_ht_key ht_key; - char enc_key[MLXSW_REG_PTCEX_FLEX_KEY_BLOCKS_LEN]; /* Encoded key, - * minus delta bits. - */ struct { u16 start; u8 mask; diff --git a/tools/testing/selftests/drivers/net/mlxsw/spectrum-2/tc_flower.sh b/tools/testing/selftests/drivers/net/mlxsw/spectrum-2/tc_flower.sh index 616d3581419c..21d0f419cc6d 100755 --- a/tools/testing/selftests/drivers/net/mlxsw/spectrum-2/tc_flower.sh +++ b/tools/testing/selftests/drivers/net/mlxsw/spectrum-2/tc_flower.sh @@ -11,7 +11,7 @@ ALL_TESTS="single_mask_test identical_filters_test two_masks_test \ multiple_masks_test ctcam_edge_cases_test delta_simple_test \ delta_two_masks_one_key_test delta_simple_rehash_test \ bloom_simple_test bloom_complex_test bloom_delta_test \ - max_erp_entries_test max_group_size_test" + max_erp_entries_test max_group_size_test collision_test" NUM_NETIFS=2 source $lib_dir/lib.sh source $lib_dir/tc_common.sh @@ -457,7 +457,7 @@ delta_two_masks_one_key_test() { # If 2 keys are the same and only differ in mask in a way that # they belong under the same ERP (second is delta of the first), - # there should be no C-TCAM spill. + # there should be C-TCAM spill. RET=0 @@ -474,8 +474,8 @@ delta_two_masks_one_key_test() tp_record "mlxsw:*" "tc filter add dev $h2 ingress protocol ip \ pref 2 handle 102 flower $tcflags dst_ip 192.0.2.2 \ action drop" - tp_check_hits "mlxsw:mlxsw_sp_acl_atcam_entry_add_ctcam_spill" 0 - check_err $? "incorrect C-TCAM spill while inserting the second rule" + tp_check_hits "mlxsw:mlxsw_sp_acl_atcam_entry_add_ctcam_spill" 1 + check_err $? "C-TCAM spill did not happen while inserting the second rule" $MZ $h1 -c 1 -p 64 -a $h1mac -b $h2mac -A 192.0.2.1 -B 192.0.2.2 \ -t ip -q @@ -1087,6 +1087,53 @@ max_group_size_test() log_test "max ACL group size test ($tcflags). max size $max_size" } +collision_test() +{ + # Filters cannot share an eRP if in the common unmasked part (i.e., + # without the delta bits) they have the same values. If the driver does + # not prevent such configuration (by spilling into the C-TCAM), then + # multiple entries will be present in the device with the same key, + # leading to collisions and a reduced scale. + # + # Create such a scenario and make sure all the filters are successfully + # added. + + RET=0 + + local ret + + if [[ "$tcflags" != "skip_sw" ]]; then + return 0; + fi + + # Add a single dst_ip/24 filter and multiple dst_ip/32 filters that all + # have the same values in the common unmasked part (dst_ip/24). + + tc filter add dev $h2 ingress pref 1 proto ipv4 handle 101 \ + flower $tcflags dst_ip 198.51.100.0/24 \ + action drop + + for i in {0..255}; do + tc filter add dev $h2 ingress pref 2 proto ipv4 \ + handle $((102 + i)) \ + flower $tcflags dst_ip 198.51.100.${i}/32 \ + action drop + ret=$? + [[ $ret -ne 0 ]] && break + done + + check_err $ret "failed to add all the filters" + + for i in {255..0}; do + tc filter del dev $h2 ingress pref 2 proto ipv4 \ + handle $((102 + i)) flower + done + + tc filter del dev $h2 ingress pref 1 proto ipv4 handle 101 flower + + log_test "collision test ($tcflags)" +} + setup_prepare() { h1=${NETIFS[p1]} From 2aa1739334d037446827ec9703bb9ac6582cec00 Mon Sep 17 00:00:00 2001 From: Carl Huang Date: Fri, 11 Dec 2020 19:35:46 +0200 Subject: [PATCH 044/342] ath11k: dp: stop rx pktlog before suspend [ Upstream commit 840c36fa727aea13a2401a5d1d33b722b79df5af ] Stop dp rx pktlog when entering suspend and reap the mon_status buffer to keep it empty. During resume restart the reap timer. Tested-on: QCA6390 hw2.0 PCI WLAN.HST.1.0.1-01740-QCAHSTSWPLZ_V2_TO_X86-1 Signed-off-by: Carl Huang Signed-off-by: Kalle Valo Link: https://lore.kernel.org/r/1607708150-21066-7-git-send-email-kvalo@codeaurora.org Stable-dep-of: d2b0ca38d362 ("wifi: ath11k: fix wrong handling of CCMP256 and GCMP ciphers") Signed-off-by: Sasha Levin --- drivers/net/wireless/ath/ath11k/dp.h | 1 + drivers/net/wireless/ath/ath11k/dp_rx.c | 48 +++++++++++++++++++++++++ drivers/net/wireless/ath/ath11k/dp_rx.h | 3 ++ drivers/net/wireless/ath/ath11k/mac.c | 4 +++ 4 files changed, 56 insertions(+) diff --git a/drivers/net/wireless/ath/ath11k/dp.h b/drivers/net/wireless/ath/ath11k/dp.h index c4972233149f..89dc3ab2e2fb 100644 --- a/drivers/net/wireless/ath/ath11k/dp.h +++ b/drivers/net/wireless/ath/ath11k/dp.h @@ -40,6 +40,7 @@ struct dp_rx_tid { #define DP_REO_DESC_FREE_THRESHOLD 64 #define DP_REO_DESC_FREE_TIMEOUT_MS 1000 +#define DP_MON_PURGE_TIMEOUT_MS 100 #define DP_MON_SERVICE_BUDGET 128 struct dp_reo_cache_flush_elem { diff --git a/drivers/net/wireless/ath/ath11k/dp_rx.c b/drivers/net/wireless/ath/ath11k/dp_rx.c index a50325f4634b..a83b5edea66b 100644 --- a/drivers/net/wireless/ath/ath11k/dp_rx.c +++ b/drivers/net/wireless/ath/ath11k/dp_rx.c @@ -274,6 +274,28 @@ static void ath11k_dp_service_mon_ring(struct timer_list *t) msecs_to_jiffies(ATH11K_MON_TIMER_INTERVAL)); } +static int ath11k_dp_purge_mon_ring(struct ath11k_base *ab) +{ + int i, reaped = 0; + unsigned long timeout = jiffies + msecs_to_jiffies(DP_MON_PURGE_TIMEOUT_MS); + + do { + for (i = 0; i < ab->hw_params.num_rxmda_per_pdev; i++) + reaped += ath11k_dp_rx_process_mon_rings(ab, i, + NULL, + DP_MON_SERVICE_BUDGET); + + /* nothing more to reap */ + if (reaped < DP_MON_SERVICE_BUDGET) + return 0; + + } while (time_before(jiffies, timeout)); + + ath11k_warn(ab, "dp mon ring purge timeout"); + + return -ETIMEDOUT; +} + /* Returns number of Rx buffers replenished */ int ath11k_dp_rxbufs_replenish(struct ath11k_base *ab, int mac_id, struct dp_rxdma_ring *rx_ring, @@ -5065,3 +5087,29 @@ int ath11k_dp_rx_pdev_mon_detach(struct ath11k *ar) ath11k_dp_mon_link_free(ar); return 0; } + +int ath11k_dp_rx_pktlog_start(struct ath11k_base *ab) +{ + /* start reap timer */ + mod_timer(&ab->mon_reap_timer, + jiffies + msecs_to_jiffies(ATH11K_MON_TIMER_INTERVAL)); + + return 0; +} + +int ath11k_dp_rx_pktlog_stop(struct ath11k_base *ab, bool stop_timer) +{ + int ret; + + if (stop_timer) + del_timer_sync(&ab->mon_reap_timer); + + /* reap all the monitor related rings */ + ret = ath11k_dp_purge_mon_ring(ab); + if (ret) { + ath11k_warn(ab, "failed to purge dp mon ring: %d\n", ret); + return ret; + } + + return 0; +} diff --git a/drivers/net/wireless/ath/ath11k/dp_rx.h b/drivers/net/wireless/ath/ath11k/dp_rx.h index 6986752fc4b6..623da3bf9dc8 100644 --- a/drivers/net/wireless/ath/ath11k/dp_rx.h +++ b/drivers/net/wireless/ath/ath11k/dp_rx.h @@ -92,4 +92,7 @@ int ath11k_dp_rx_pdev_mon_detach(struct ath11k *ar); int ath11k_dp_rx_pdev_mon_attach(struct ath11k *ar); int ath11k_peer_rx_frag_setup(struct ath11k *ar, const u8 *peer_mac, int vdev_id); +int ath11k_dp_rx_pktlog_start(struct ath11k_base *ab); +int ath11k_dp_rx_pktlog_stop(struct ath11k_base *ab, bool stop_timer); + #endif /* ATH11K_DP_RX_H */ diff --git a/drivers/net/wireless/ath/ath11k/mac.c b/drivers/net/wireless/ath/ath11k/mac.c index 3170c54c97b7..835e181d22cb 100644 --- a/drivers/net/wireless/ath/ath11k/mac.c +++ b/drivers/net/wireless/ath/ath11k/mac.c @@ -4149,6 +4149,10 @@ static int ath11k_mac_config_mon_status_default(struct ath11k *ar, bool enable) &tlv_filter); } + if (enable && !ar->ab->hw_params.rxdma1_enable) + mod_timer(&ar->ab->mon_reap_timer, jiffies + + msecs_to_jiffies(ATH11K_MON_TIMER_INTERVAL)); + return ret; } From 4055275ca3e0ca1bdbd76315f7f941640677c681 Mon Sep 17 00:00:00 2001 From: Baochen Qiang Date: Tue, 11 Jun 2024 09:42:34 +0300 Subject: [PATCH 045/342] wifi: ath11k: fix wrong handling of CCMP256 and GCMP ciphers [ Upstream commit d2b0ca38d362ebf16ca79cd7f309d5bb8b581deb ] Currently for CCMP256, GCMP128 and GCMP256 ciphers, in ath11k_install_key() IEEE80211_KEY_FLAG_GENERATE_IV_MGMT is not set. And in ath11k_mac_mgmt_tx_wmi() a length of IEEE80211_CCMP_MIC_LEN is reserved for all ciphers. This results in unexpected management frame drop in case either of above 3 ciphers is used. The reason is, without IEEE80211_KEY_FLAG_GENERATE_IV_MGMT set, mac80211 will not generate CCMP/GCMP headers in frame for ath11k. Also MIC length reserved is wrong. Such frame is dropped later by hardware: ath11k_pci 0000:5a:00.0: mac tx mgmt frame, buf id 0 ath11k_pci 0000:5a:00.0: mgmt tx compl ev pdev_id 1, desc_id 0, status 1 From user point of view, we have observed very low throughput due to this issue: action frames are all dropped so ADDBA response from DUT never reaches AP. AP can not use aggregation thus throughput is low. Fix this by setting IEEE80211_KEY_FLAG_GENERATE_IV_MGMT flag and by reserving proper MIC length for those ciphers. Tested-on: WCN6855 hw2.0 PCI WLAN.HSP.1.1-03125-QCAHSPSWPL_V1_V2_SILICONZ_LITE-3.6510.30 Tested-on: QCN9074 hw1.0 PCI WLAN.HK.2.7.0.1-01744-QCAHKSWPL_SILICONZ-1 Fixes: d5c65159f289 ("ath11k: driver for Qualcomm IEEE 802.11ax devices") Reported-by: Yaroslav Isakov Tested-by: Yaroslav Isakov Closes: https://lore.kernel.org/all/CADS+iDX5=JtJr0apAtAQ02WWBxgOFEv8G063vuGYwDTC8AVZaw@mail.gmail.com Signed-off-by: Baochen Qiang Acked-by: Jeff Johnson Signed-off-by: Kalle Valo Link: https://msgid.link/20240605014826.22498-1-quic_bqiang@quicinc.com Signed-off-by: Sasha Levin --- drivers/net/wireless/ath/ath11k/dp_rx.c | 3 +-- drivers/net/wireless/ath/ath11k/dp_rx.h | 3 +++ drivers/net/wireless/ath/ath11k/mac.c | 15 +++++++++++---- 3 files changed, 15 insertions(+), 6 deletions(-) diff --git a/drivers/net/wireless/ath/ath11k/dp_rx.c b/drivers/net/wireless/ath/ath11k/dp_rx.c index a83b5edea66b..6c4b84282e44 100644 --- a/drivers/net/wireless/ath/ath11k/dp_rx.c +++ b/drivers/net/wireless/ath/ath11k/dp_rx.c @@ -1852,8 +1852,7 @@ static void ath11k_dp_rx_h_csum_offload(struct sk_buff *msdu) CHECKSUM_NONE : CHECKSUM_UNNECESSARY; } -static int ath11k_dp_rx_crypto_mic_len(struct ath11k *ar, - enum hal_encrypt_type enctype) +int ath11k_dp_rx_crypto_mic_len(struct ath11k *ar, enum hal_encrypt_type enctype) { switch (enctype) { case HAL_ENCRYPT_TYPE_OPEN: diff --git a/drivers/net/wireless/ath/ath11k/dp_rx.h b/drivers/net/wireless/ath/ath11k/dp_rx.h index 623da3bf9dc8..c322e30caa96 100644 --- a/drivers/net/wireless/ath/ath11k/dp_rx.h +++ b/drivers/net/wireless/ath/ath11k/dp_rx.h @@ -1,6 +1,7 @@ /* SPDX-License-Identifier: BSD-3-Clause-Clear */ /* * Copyright (c) 2018-2019 The Linux Foundation. All rights reserved. + * Copyright (c) 2024 Qualcomm Innovation Center, Inc. All rights reserved. */ #ifndef ATH11K_DP_RX_H #define ATH11K_DP_RX_H @@ -95,4 +96,6 @@ int ath11k_peer_rx_frag_setup(struct ath11k *ar, const u8 *peer_mac, int vdev_id int ath11k_dp_rx_pktlog_start(struct ath11k_base *ab); int ath11k_dp_rx_pktlog_stop(struct ath11k_base *ab, bool stop_timer); +int ath11k_dp_rx_crypto_mic_len(struct ath11k *ar, enum hal_encrypt_type enctype); + #endif /* ATH11K_DP_RX_H */ diff --git a/drivers/net/wireless/ath/ath11k/mac.c b/drivers/net/wireless/ath/ath11k/mac.c index 835e181d22cb..b66b6a7072d8 100644 --- a/drivers/net/wireless/ath/ath11k/mac.c +++ b/drivers/net/wireless/ath/ath11k/mac.c @@ -2410,6 +2410,7 @@ static int ath11k_install_key(struct ath11k_vif *arvif, switch (key->cipher) { case WLAN_CIPHER_SUITE_CCMP: + case WLAN_CIPHER_SUITE_CCMP_256: arg.key_cipher = WMI_CIPHER_AES_CCM; /* TODO: Re-check if flag is valid */ key->flags |= IEEE80211_KEY_FLAG_GENERATE_IV_MGMT; @@ -2419,12 +2420,10 @@ static int ath11k_install_key(struct ath11k_vif *arvif, arg.key_txmic_len = 8; arg.key_rxmic_len = 8; break; - case WLAN_CIPHER_SUITE_CCMP_256: - arg.key_cipher = WMI_CIPHER_AES_CCM; - break; case WLAN_CIPHER_SUITE_GCMP: case WLAN_CIPHER_SUITE_GCMP_256: arg.key_cipher = WMI_CIPHER_AES_GCM; + key->flags |= IEEE80211_KEY_FLAG_GENERATE_IV_MGMT; break; default: ath11k_warn(ar->ab, "cipher %d is not supported\n", key->cipher); @@ -3946,7 +3945,10 @@ static int ath11k_mac_mgmt_tx_wmi(struct ath11k *ar, struct ath11k_vif *arvif, { struct ath11k_base *ab = ar->ab; struct ieee80211_hdr *hdr = (struct ieee80211_hdr *)skb->data; + struct ath11k_skb_cb *skb_cb = ATH11K_SKB_CB(skb); struct ieee80211_tx_info *info; + enum hal_encrypt_type enctype; + unsigned int mic_len; dma_addr_t paddr; int buf_id; int ret; @@ -3966,7 +3968,12 @@ static int ath11k_mac_mgmt_tx_wmi(struct ath11k *ar, struct ath11k_vif *arvif, ieee80211_is_deauth(hdr->frame_control) || ieee80211_is_disassoc(hdr->frame_control)) && ieee80211_has_protected(hdr->frame_control)) { - skb_put(skb, IEEE80211_CCMP_MIC_LEN); + if (!(skb_cb->flags & ATH11K_SKB_CIPHER_SET)) + ath11k_warn(ab, "WMI management tx frame without ATH11K_SKB_CIPHER_SET"); + + enctype = ath11k_dp_tx_get_encrypt_type(skb_cb->cipher); + mic_len = ath11k_dp_rx_crypto_mic_len(ar, enctype); + skb_put(skb, mic_len); } } From 72e470089fc4e692c38fe8f1eaceba9bcc981353 Mon Sep 17 00:00:00 2001 From: Baochen Qiang Date: Thu, 6 Jun 2024 10:06:52 +0800 Subject: [PATCH 046/342] wifi: cfg80211: fix typo in cfg80211_calculate_bitrate_he() [ Upstream commit 9ee0d44f055276fe2802b2f65058e920853f4f99 ] rates_996 is mistakenly written as rates_969, fix it. Fixes: c4cbaf7973a7 ("cfg80211: Add support for HE") Signed-off-by: Baochen Qiang Link: https://msgid.link/20240606020653.33205-2-quic_bqiang@quicinc.com Signed-off-by: Johannes Berg Signed-off-by: Sasha Levin --- net/wireless/util.c | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-) diff --git a/net/wireless/util.c b/net/wireless/util.c index 4b32e85c2d9a..0d5b1c18d62f 100644 --- a/net/wireless/util.c +++ b/net/wireless/util.c @@ -1334,7 +1334,7 @@ static u32 cfg80211_calculate_bitrate_he(struct rate_info *rate) 2048, /* 1.000000... */ }; u32 rates_160M[3] = { 960777777, 907400000, 816666666 }; - u32 rates_969[3] = { 480388888, 453700000, 408333333 }; + u32 rates_996[3] = { 480388888, 453700000, 408333333 }; u32 rates_484[3] = { 229411111, 216666666, 195000000 }; u32 rates_242[3] = { 114711111, 108333333, 97500000 }; u32 rates_106[3] = { 40000000, 37777777, 34000000 }; @@ -1359,7 +1359,7 @@ static u32 cfg80211_calculate_bitrate_he(struct rate_info *rate) else if (rate->bw == RATE_INFO_BW_80 || (rate->bw == RATE_INFO_BW_HE_RU && rate->he_ru_alloc == NL80211_RATE_INFO_HE_RU_ALLOC_996)) - result = rates_969[rate->he_gi]; + result = rates_996[rate->he_gi]; else if (rate->bw == RATE_INFO_BW_40 || (rate->bw == RATE_INFO_BW_HE_RU && rate->he_ru_alloc == NL80211_RATE_INFO_HE_RU_ALLOC_484)) From 2e201b3d162c6c49417c438ffb30b58c9f85769f Mon Sep 17 00:00:00 2001 From: Baochen Qiang Date: Thu, 6 Jun 2024 10:06:53 +0800 Subject: [PATCH 047/342] wifi: cfg80211: handle 2x996 RU allocation in cfg80211_calculate_bitrate_he() [ Upstream commit bcbd771cd5d68c0c52567556097d75f9fc4e7cd6 ] Currently NL80211_RATE_INFO_HE_RU_ALLOC_2x996 is not handled in cfg80211_calculate_bitrate_he(), leading to below warning: kernel: invalid HE MCS: bw:6, ru:6 kernel: WARNING: CPU: 0 PID: 2312 at net/wireless/util.c:1501 cfg80211_calculate_bitrate_he+0x22b/0x270 [cfg80211] Fix it by handling 2x996 RU allocation in the same way as 160 MHz bandwidth. Fixes: c4cbaf7973a7 ("cfg80211: Add support for HE") Signed-off-by: Baochen Qiang Link: https://msgid.link/20240606020653.33205-3-quic_bqiang@quicinc.com Signed-off-by: Johannes Berg Signed-off-by: Sasha Levin --- net/wireless/util.c | 4 +++- 1 file changed, 3 insertions(+), 1 deletion(-) diff --git a/net/wireless/util.c b/net/wireless/util.c index 0d5b1c18d62f..37719fc39f64 100644 --- a/net/wireless/util.c +++ b/net/wireless/util.c @@ -1354,7 +1354,9 @@ static u32 cfg80211_calculate_bitrate_he(struct rate_info *rate) if (WARN_ON_ONCE(rate->nss < 1 || rate->nss > 8)) return 0; - if (rate->bw == RATE_INFO_BW_160) + if (rate->bw == RATE_INFO_BW_160 || + (rate->bw == RATE_INFO_BW_HE_RU && + rate->he_ru_alloc == NL80211_RATE_INFO_HE_RU_ALLOC_2x996)) result = rates_160M[rate->he_gi]; else if (rate->bw == RATE_INFO_BW_80 || (rate->bw == RATE_INFO_BW_HE_RU && From 29254059a1f897d56777f0670809cc6eeef61ff3 Mon Sep 17 00:00:00 2001 From: =?UTF-8?q?Cs=C3=B3k=C3=A1s=20Bence?= Date: Mon, 12 Feb 2024 16:37:17 +0100 Subject: [PATCH 048/342] net: fec: Refactor: #define magic constants MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit [ Upstream commit ff049886671ccd4e624a30ec464cb20e4c39a313 ] Add defines for bits of ECR, RCR control registers, TX watermark etc. Signed-off-by: Csókás Bence Reviewed-by: Andrew Lunn Link: https://lore.kernel.org/r/20240212153717.10023-1-csokas.bence@prolan.hu Signed-off-by: Jakub Kicinski Stable-dep-of: c32fe1986f27 ("net: fec: Fix FEC_ECR_EN1588 being cleared on link-down") Signed-off-by: Sasha Levin --- drivers/net/ethernet/freescale/fec_main.c | 46 +++++++++++++++-------- 1 file changed, 30 insertions(+), 16 deletions(-) diff --git a/drivers/net/ethernet/freescale/fec_main.c b/drivers/net/ethernet/freescale/fec_main.c index adb76db66031..269c6365ec09 100644 --- a/drivers/net/ethernet/freescale/fec_main.c +++ b/drivers/net/ethernet/freescale/fec_main.c @@ -220,8 +220,8 @@ MODULE_PARM_DESC(macaddr, "FEC Ethernet MAC address"); #define PKT_MINBUF_SIZE 64 /* FEC receive acceleration */ -#define FEC_RACC_IPDIS (1 << 1) -#define FEC_RACC_PRODIS (1 << 2) +#define FEC_RACC_IPDIS BIT(1) +#define FEC_RACC_PRODIS BIT(2) #define FEC_RACC_SHIFT16 BIT(7) #define FEC_RACC_OPTIONS (FEC_RACC_IPDIS | FEC_RACC_PRODIS) @@ -253,8 +253,23 @@ MODULE_PARM_DESC(macaddr, "FEC Ethernet MAC address"); #define FEC_MMFR_TA (2 << 16) #define FEC_MMFR_DATA(v) (v & 0xffff) /* FEC ECR bits definition */ -#define FEC_ECR_MAGICEN (1 << 2) -#define FEC_ECR_SLEEP (1 << 3) +#define FEC_ECR_RESET BIT(0) +#define FEC_ECR_ETHEREN BIT(1) +#define FEC_ECR_MAGICEN BIT(2) +#define FEC_ECR_SLEEP BIT(3) +#define FEC_ECR_EN1588 BIT(4) +#define FEC_ECR_BYTESWP BIT(8) +/* FEC RCR bits definition */ +#define FEC_RCR_LOOP BIT(0) +#define FEC_RCR_HALFDPX BIT(1) +#define FEC_RCR_MII BIT(2) +#define FEC_RCR_PROMISC BIT(3) +#define FEC_RCR_BC_REJ BIT(4) +#define FEC_RCR_FLOWCTL BIT(5) +#define FEC_RCR_RMII BIT(8) +#define FEC_RCR_10BASET BIT(9) +/* TX WMARK bits */ +#define FEC_TXWMRK_STRFWD BIT(8) #define FEC_MII_TIMEOUT 30000 /* us */ @@ -949,7 +964,7 @@ fec_restart(struct net_device *ndev) u32 val; u32 temp_mac[2]; u32 rcntl = OPT_FRAME_SIZE | 0x04; - u32 ecntl = 0x2; /* ETHEREN */ + u32 ecntl = FEC_ECR_ETHEREN; /* Whack a reset. We should wait for this. * For i.MX6SX SOC, enet use AXI bus, we use disable MAC @@ -1025,18 +1040,18 @@ fec_restart(struct net_device *ndev) fep->phy_interface == PHY_INTERFACE_MODE_RGMII_TXID) rcntl |= (1 << 6); else if (fep->phy_interface == PHY_INTERFACE_MODE_RMII) - rcntl |= (1 << 8); + rcntl |= FEC_RCR_RMII; else - rcntl &= ~(1 << 8); + rcntl &= ~FEC_RCR_RMII; /* 1G, 100M or 10M */ if (ndev->phydev) { if (ndev->phydev->speed == SPEED_1000) ecntl |= (1 << 5); else if (ndev->phydev->speed == SPEED_100) - rcntl &= ~(1 << 9); + rcntl &= ~FEC_RCR_10BASET; else - rcntl |= (1 << 9); + rcntl |= FEC_RCR_10BASET; } } else { #ifdef FEC_MIIGSK_ENR @@ -1095,13 +1110,13 @@ fec_restart(struct net_device *ndev) if (fep->quirks & FEC_QUIRK_ENET_MAC) { /* enable ENET endian swap */ - ecntl |= (1 << 8); + ecntl |= FEC_ECR_BYTESWP; /* enable ENET store and forward mode */ - writel(1 << 8, fep->hwp + FEC_X_WMRK); + writel(FEC_TXWMRK_STRFWD, fep->hwp + FEC_X_WMRK); } if (fep->bufdesc_ex) - ecntl |= (1 << 4); + ecntl |= FEC_ECR_EN1588; #ifndef CONFIG_M5272 /* Enable the MIB statistic event counters */ @@ -1148,7 +1163,7 @@ static void fec_stop(struct net_device *ndev) { struct fec_enet_private *fep = netdev_priv(ndev); - u32 rmii_mode = readl(fep->hwp + FEC_R_CNTRL) & (1 << 8); + u32 rmii_mode = readl(fep->hwp + FEC_R_CNTRL) & FEC_RCR_RMII; u32 val; /* We cannot expect a graceful transmit stop without link !!! */ @@ -1167,7 +1182,7 @@ fec_stop(struct net_device *ndev) if (fep->quirks & FEC_QUIRK_HAS_AVB) { writel(0, fep->hwp + FEC_ECNTRL); } else { - writel(1, fep->hwp + FEC_ECNTRL); + writel(FEC_ECR_RESET, fep->hwp + FEC_ECNTRL); udelay(10); } writel(FEC_DEFAULT_IMASK, fep->hwp + FEC_IMASK); @@ -1183,12 +1198,11 @@ fec_stop(struct net_device *ndev) /* We have to keep ENET enabled to have MII interrupt stay working */ if (fep->quirks & FEC_QUIRK_ENET_MAC && !(fep->wol_flag & FEC_WOL_FLAG_SLEEP_ON)) { - writel(2, fep->hwp + FEC_ECNTRL); + writel(FEC_ECR_ETHEREN, fep->hwp + FEC_ECNTRL); writel(rmii_mode, fep->hwp + FEC_R_CNTRL); } } - static void fec_timeout(struct net_device *ndev, unsigned int txqueue) { From 2912a0d136ee2abc7168c60200dc804b755fdddd Mon Sep 17 00:00:00 2001 From: =?UTF-8?q?Cs=C3=B3k=C3=A1s=2C=20Bence?= Date: Wed, 19 Jun 2024 14:31:11 +0200 Subject: [PATCH 049/342] net: fec: Fix FEC_ECR_EN1588 being cleared on link-down MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit [ Upstream commit c32fe1986f27cac329767d3497986e306cad1d5e ] FEC_ECR_EN1588 bit gets cleared after MAC reset in `fec_stop()`, which makes all 1588 functionality shut down, and all the extended registers disappear, on link-down, making the adapter fall back to compatibility "dumb mode". However, some functionality needs to be retained (e.g. PPS) even without link. Fixes: 6605b730c061 ("FEC: Add time stamping code and a PTP hardware clock") Cc: Richard Cochran Reviewed-by: Andrew Lunn Link: https://lore.kernel.org/netdev/5fa9fadc-a89d-467a-aae9-c65469ff5fe1@lunn.ch/ Signed-off-by: Csókás, Bence Reviewed-by: Wei Fang Signed-off-by: David S. Miller Signed-off-by: Sasha Levin --- drivers/net/ethernet/freescale/fec_main.c | 6 ++++++ 1 file changed, 6 insertions(+) diff --git a/drivers/net/ethernet/freescale/fec_main.c b/drivers/net/ethernet/freescale/fec_main.c index 269c6365ec09..a591ca0b3778 100644 --- a/drivers/net/ethernet/freescale/fec_main.c +++ b/drivers/net/ethernet/freescale/fec_main.c @@ -1201,6 +1201,12 @@ fec_stop(struct net_device *ndev) writel(FEC_ECR_ETHEREN, fep->hwp + FEC_ECNTRL); writel(rmii_mode, fep->hwp + FEC_R_CNTRL); } + + if (fep->bufdesc_ex) { + val = readl(fep->hwp + FEC_ECNTRL); + val |= FEC_ECR_EN1588; + writel(val, fep->hwp + FEC_ECNTRL); + } } static void From 0d08015beedbb9e387fcf84c9c6aeff627775a4e Mon Sep 17 00:00:00 2001 From: Ismael Luceno Date: Thu, 23 May 2024 18:54:44 +0200 Subject: [PATCH 050/342] ipvs: Avoid unnecessary calls to skb_is_gso_sctp [ Upstream commit 53796b03295cf7ab1fc8600016fa6dfbf4a494a0 ] In the context of the SCTP SNAT/DNAT handler, these calls can only return true. Fixes: e10d3ba4d434 ("ipvs: Fix checksumming on GSO of SCTP packets") Signed-off-by: Ismael Luceno Acked-by: Julian Anastasov Acked-by: Simon Horman Signed-off-by: Pablo Neira Ayuso Signed-off-by: Sasha Levin --- net/netfilter/ipvs/ip_vs_proto_sctp.c | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-) diff --git a/net/netfilter/ipvs/ip_vs_proto_sctp.c b/net/netfilter/ipvs/ip_vs_proto_sctp.c index 1e689c714127..83e452916403 100644 --- a/net/netfilter/ipvs/ip_vs_proto_sctp.c +++ b/net/netfilter/ipvs/ip_vs_proto_sctp.c @@ -126,7 +126,7 @@ sctp_snat_handler(struct sk_buff *skb, struct ip_vs_protocol *pp, if (sctph->source != cp->vport || payload_csum || skb->ip_summed == CHECKSUM_PARTIAL) { sctph->source = cp->vport; - if (!skb_is_gso(skb) || !skb_is_gso_sctp(skb)) + if (!skb_is_gso(skb)) sctp_nat_csum(skb, sctph, sctphoff); } else { skb->ip_summed = CHECKSUM_UNNECESSARY; @@ -175,7 +175,7 @@ sctp_dnat_handler(struct sk_buff *skb, struct ip_vs_protocol *pp, (skb->ip_summed == CHECKSUM_PARTIAL && !(skb_dst(skb)->dev->features & NETIF_F_SCTP_CRC))) { sctph->dest = cp->dport; - if (!skb_is_gso(skb) || !skb_is_gso_sctp(skb)) + if (!skb_is_gso(skb)) sctp_nat_csum(skb, sctph, sctphoff); } else if (skb->ip_summed != CHECKSUM_PARTIAL) { skb->ip_summed = CHECKSUM_UNNECESSARY; From d4f4188ecfe58d73c108d43693823557785cde06 Mon Sep 17 00:00:00 2001 From: Pablo Neira Ayuso Date: Mon, 3 Jun 2024 20:16:59 +0200 Subject: [PATCH 051/342] netfilter: nf_tables: rise cap on SELinux secmark context [ Upstream commit e29630247be24c3987e2b048f8e152771b32d38b ] secmark context is artificially limited 256 bytes, rise it to 4Kbytes. Fixes: fb961945457f ("netfilter: nf_tables: add SECMARK support") Signed-off-by: Pablo Neira Ayuso Signed-off-by: Sasha Levin --- include/uapi/linux/netfilter/nf_tables.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/include/uapi/linux/netfilter/nf_tables.h b/include/uapi/linux/netfilter/nf_tables.h index f93ffb1b6739..40d900537093 100644 --- a/include/uapi/linux/netfilter/nf_tables.h +++ b/include/uapi/linux/netfilter/nf_tables.h @@ -1284,7 +1284,7 @@ enum nft_secmark_attributes { #define NFTA_SECMARK_MAX (__NFTA_SECMARK_MAX - 1) /* Max security context length */ -#define NFT_SECMARK_CTX_MAXLEN 256 +#define NFT_SECMARK_CTX_MAXLEN 4096 /** * enum nft_reject_types - nf_tables reject expression reject types From a497a6b72b294a6bdeb54daa2dfcb53337fc4629 Mon Sep 17 00:00:00 2001 From: Adrian Hunter Date: Mon, 24 Jun 2024 23:10:57 +0300 Subject: [PATCH 052/342] perf/x86/intel/pt: Fix pt_topa_entry_for_page() address calculation [ Upstream commit 3520b251dcae2b4a27b95cd6f745c54fd658bda5 ] Currently, perf allocates an array of page pointers which is limited in size by MAX_PAGE_ORDER. That in turn limits the maximum Intel PT buffer size to 2GiB. Should that limitation be lifted, the Intel PT driver can support larger sizes, except for one calculation in pt_topa_entry_for_page(), which is limited to 32-bits. Fix pt_topa_entry_for_page() address calculation by adding a cast. Fixes: 39152ee51b77 ("perf/x86/intel/pt: Get rid of reverse lookup table for ToPA") Signed-off-by: Adrian Hunter Signed-off-by: Peter Zijlstra (Intel) Link: https://lore.kernel.org/r/20240624201101.60186-4-adrian.hunter@intel.com Signed-off-by: Sasha Levin --- arch/x86/events/intel/pt.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/arch/x86/events/intel/pt.c b/arch/x86/events/intel/pt.c index 5667b8b994e3..d97d34b4669b 100644 --- a/arch/x86/events/intel/pt.c +++ b/arch/x86/events/intel/pt.c @@ -973,7 +973,7 @@ pt_topa_entry_for_page(struct pt_buffer *buf, unsigned int pg) * order allocations, there shouldn't be many of these. */ list_for_each_entry(topa, &buf->tables, list) { - if (topa->offset + topa->size > pg << PAGE_SHIFT) + if (topa->offset + topa->size > (unsigned long)pg << PAGE_SHIFT) goto found; } From a2450206c092c310f109ca77fa288625dff38898 Mon Sep 17 00:00:00 2001 From: Adrian Hunter Date: Mon, 24 Jun 2024 23:10:58 +0300 Subject: [PATCH 053/342] perf: Fix perf_aux_size() for greater-than 32-bit size [ Upstream commit 3df94a5b1078dfe2b0c03f027d018800faf44c82 ] perf_buffer->aux_nr_pages uses a 32-bit type, so a cast is needed to calculate a 64-bit size. Fixes: 45bfb2e50471 ("perf: Add AUX area to ring buffer for raw data streams") Signed-off-by: Adrian Hunter Signed-off-by: Peter Zijlstra (Intel) Link: https://lore.kernel.org/r/20240624201101.60186-5-adrian.hunter@intel.com Signed-off-by: Sasha Levin --- kernel/events/internal.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/kernel/events/internal.h b/kernel/events/internal.h index aa23ffdaf819..8e63cc2bd4f7 100644 --- a/kernel/events/internal.h +++ b/kernel/events/internal.h @@ -128,7 +128,7 @@ static inline unsigned long perf_data_size(struct perf_buffer *rb) static inline unsigned long perf_aux_size(struct perf_buffer *rb) { - return rb->aux_nr_pages << PAGE_SHIFT; + return (unsigned long)rb->aux_nr_pages << PAGE_SHIFT; } #define __DEFINE_OUTPUT_COPY_BODY(advance_buf, memcpy_func, ...) \ From 7f132aca18208837a86cd51ba254b901ad73e154 Mon Sep 17 00:00:00 2001 From: Adrian Hunter Date: Mon, 24 Jun 2024 23:10:59 +0300 Subject: [PATCH 054/342] perf: Prevent passing zero nr_pages to rb_alloc_aux() [ Upstream commit dbc48c8f41c208082cfa95e973560134489e3309 ] nr_pages is unsigned long but gets passed to rb_alloc_aux() as an int, and is stored as an int. Only power-of-2 values are accepted, so if nr_pages is a 64_bit value, it will be passed to rb_alloc_aux() as zero. That is not ideal because: 1. the value is incorrect 2. rb_alloc_aux() is at risk of misbehaving, although it manages to return -ENOMEM in that case, it is a result of passing zero to get_order() even though the get_order() result is documented to be undefined in that case. Fix by simply validating the maximum supported value in the first place. Use -ENOMEM error code for consistency with the current error code that is returned in that case. Fixes: 45bfb2e50471 ("perf: Add AUX area to ring buffer for raw data streams") Signed-off-by: Adrian Hunter Signed-off-by: Peter Zijlstra (Intel) Link: https://lore.kernel.org/r/20240624201101.60186-6-adrian.hunter@intel.com Signed-off-by: Sasha Levin --- kernel/events/core.c | 2 ++ 1 file changed, 2 insertions(+) diff --git a/kernel/events/core.c b/kernel/events/core.c index 3a191bec69ac..b60325cc8604 100644 --- a/kernel/events/core.c +++ b/kernel/events/core.c @@ -6239,6 +6239,8 @@ static int perf_mmap(struct file *file, struct vm_area_struct *vma) return -EINVAL; nr_pages = vma_size / PAGE_SIZE; + if (nr_pages > INT_MAX) + return -ENOMEM; mutex_lock(&event->mmap_mutex); ret = -EINVAL; From b33dd45086401c231616f88ec5d827f825ebe35d Mon Sep 17 00:00:00 2001 From: Shai Malin Date: Mon, 13 Sep 2021 10:50:24 +0300 Subject: [PATCH 055/342] qed: Improve the stack space of filter_config() [ Upstream commit f55e36d5ab76c3097ff36ecea60b91c6b0d80fc8 ] As it was reported and discussed in: https://lore.kernel.org/lkml/CAHk-=whF9F89vsfH8E9TGc0tZA-yhzi2Di8wOtquNB5vRkFX5w@mail.gmail.com/ This patch improves the stack space of qede_config_rx_mode() by splitting filter_config() to 3 functions and removing the union qed_filter_type_params. Reported-by: Naresh Kamboju Signed-off-by: Ariel Elior Signed-off-by: Shai Malin Signed-off-by: David S. Miller Stable-dep-of: b5d14b0c6716 ("wifi: virt_wifi: avoid reporting connection success with wrong SSID") Signed-off-by: Sasha Levin --- drivers/net/ethernet/qlogic/qed/qed_l2.c | 23 ++------- .../net/ethernet/qlogic/qede/qede_filter.c | 47 ++++++++----------- include/linux/qed/qed_eth_if.h | 21 ++++----- 3 files changed, 30 insertions(+), 61 deletions(-) diff --git a/drivers/net/ethernet/qlogic/qed/qed_l2.c b/drivers/net/ethernet/qlogic/qed/qed_l2.c index 0157bcd2efff..198022bc1f94 100644 --- a/drivers/net/ethernet/qlogic/qed/qed_l2.c +++ b/drivers/net/ethernet/qlogic/qed/qed_l2.c @@ -2762,25 +2762,6 @@ static int qed_configure_filter_mcast(struct qed_dev *cdev, return qed_filter_mcast_cmd(cdev, &mcast, QED_SPQ_MODE_CB, NULL); } -static int qed_configure_filter(struct qed_dev *cdev, - struct qed_filter_params *params) -{ - enum qed_filter_rx_mode_type accept_flags; - - switch (params->type) { - case QED_FILTER_TYPE_UCAST: - return qed_configure_filter_ucast(cdev, ¶ms->filter.ucast); - case QED_FILTER_TYPE_MCAST: - return qed_configure_filter_mcast(cdev, ¶ms->filter.mcast); - case QED_FILTER_TYPE_RX_MODE: - accept_flags = params->filter.accept_flags; - return qed_configure_filter_rx_mode(cdev, accept_flags); - default: - DP_NOTICE(cdev, "Unknown filter type %d\n", (int)params->type); - return -EINVAL; - } -} - static int qed_configure_arfs_searcher(struct qed_dev *cdev, enum qed_filter_config_mode mode) { @@ -2903,7 +2884,9 @@ static const struct qed_eth_ops qed_eth_ops_pass = { .q_rx_stop = &qed_stop_rxq, .q_tx_start = &qed_start_txq, .q_tx_stop = &qed_stop_txq, - .filter_config = &qed_configure_filter, + .filter_config_rx_mode = &qed_configure_filter_rx_mode, + .filter_config_ucast = &qed_configure_filter_ucast, + .filter_config_mcast = &qed_configure_filter_mcast, .fastpath_stop = &qed_fastpath_stop, .eth_cqe_completion = &qed_fp_cqe_completion, .get_vport_stats = &qed_get_vport_stats, diff --git a/drivers/net/ethernet/qlogic/qede/qede_filter.c b/drivers/net/ethernet/qlogic/qede/qede_filter.c index 5f4962d90022..f4385466418c 100644 --- a/drivers/net/ethernet/qlogic/qede/qede_filter.c +++ b/drivers/net/ethernet/qlogic/qede/qede_filter.c @@ -619,30 +619,28 @@ static int qede_set_ucast_rx_mac(struct qede_dev *edev, enum qed_filter_xcast_params_type opcode, unsigned char mac[ETH_ALEN]) { - struct qed_filter_params filter_cmd; + struct qed_filter_ucast_params ucast; - memset(&filter_cmd, 0, sizeof(filter_cmd)); - filter_cmd.type = QED_FILTER_TYPE_UCAST; - filter_cmd.filter.ucast.type = opcode; - filter_cmd.filter.ucast.mac_valid = 1; - ether_addr_copy(filter_cmd.filter.ucast.mac, mac); + memset(&ucast, 0, sizeof(ucast)); + ucast.type = opcode; + ucast.mac_valid = 1; + ether_addr_copy(ucast.mac, mac); - return edev->ops->filter_config(edev->cdev, &filter_cmd); + return edev->ops->filter_config_ucast(edev->cdev, &ucast); } static int qede_set_ucast_rx_vlan(struct qede_dev *edev, enum qed_filter_xcast_params_type opcode, u16 vid) { - struct qed_filter_params filter_cmd; + struct qed_filter_ucast_params ucast; - memset(&filter_cmd, 0, sizeof(filter_cmd)); - filter_cmd.type = QED_FILTER_TYPE_UCAST; - filter_cmd.filter.ucast.type = opcode; - filter_cmd.filter.ucast.vlan_valid = 1; - filter_cmd.filter.ucast.vlan = vid; + memset(&ucast, 0, sizeof(ucast)); + ucast.type = opcode; + ucast.vlan_valid = 1; + ucast.vlan = vid; - return edev->ops->filter_config(edev->cdev, &filter_cmd); + return edev->ops->filter_config_ucast(edev->cdev, &ucast); } static int qede_config_accept_any_vlan(struct qede_dev *edev, bool action) @@ -1057,18 +1055,17 @@ static int qede_set_mcast_rx_mac(struct qede_dev *edev, enum qed_filter_xcast_params_type opcode, unsigned char *mac, int num_macs) { - struct qed_filter_params filter_cmd; + struct qed_filter_mcast_params mcast; int i; - memset(&filter_cmd, 0, sizeof(filter_cmd)); - filter_cmd.type = QED_FILTER_TYPE_MCAST; - filter_cmd.filter.mcast.type = opcode; - filter_cmd.filter.mcast.num = num_macs; + memset(&mcast, 0, sizeof(mcast)); + mcast.type = opcode; + mcast.num = num_macs; for (i = 0; i < num_macs; i++, mac += ETH_ALEN) - ether_addr_copy(filter_cmd.filter.mcast.mac[i], mac); + ether_addr_copy(mcast.mac[i], mac); - return edev->ops->filter_config(edev->cdev, &filter_cmd); + return edev->ops->filter_config_mcast(edev->cdev, &mcast); } int qede_set_mac_addr(struct net_device *ndev, void *p) @@ -1194,7 +1191,6 @@ void qede_config_rx_mode(struct net_device *ndev) { enum qed_filter_rx_mode_type accept_flags; struct qede_dev *edev = netdev_priv(ndev); - struct qed_filter_params rx_mode; unsigned char *uc_macs, *temp; struct netdev_hw_addr *ha; int rc, uc_count; @@ -1220,10 +1216,6 @@ void qede_config_rx_mode(struct net_device *ndev) netif_addr_unlock_bh(ndev); - /* Configure the struct for the Rx mode */ - memset(&rx_mode, 0, sizeof(struct qed_filter_params)); - rx_mode.type = QED_FILTER_TYPE_RX_MODE; - /* Remove all previous unicast secondary macs and multicast macs * (configure / leave the primary mac) */ @@ -1271,8 +1263,7 @@ void qede_config_rx_mode(struct net_device *ndev) qede_config_accept_any_vlan(edev, false); } - rx_mode.filter.accept_flags = accept_flags; - edev->ops->filter_config(edev->cdev, &rx_mode); + edev->ops->filter_config_rx_mode(edev->cdev, accept_flags); out: kfree(uc_macs); } diff --git a/include/linux/qed/qed_eth_if.h b/include/linux/qed/qed_eth_if.h index 812a4d751163..4df0bf0a0864 100644 --- a/include/linux/qed/qed_eth_if.h +++ b/include/linux/qed/qed_eth_if.h @@ -145,12 +145,6 @@ struct qed_filter_mcast_params { unsigned char mac[64][ETH_ALEN]; }; -union qed_filter_type_params { - enum qed_filter_rx_mode_type accept_flags; - struct qed_filter_ucast_params ucast; - struct qed_filter_mcast_params mcast; -}; - enum qed_filter_type { QED_FILTER_TYPE_UCAST, QED_FILTER_TYPE_MCAST, @@ -158,11 +152,6 @@ enum qed_filter_type { QED_MAX_FILTER_TYPES, }; -struct qed_filter_params { - enum qed_filter_type type; - union qed_filter_type_params filter; -}; - struct qed_tunn_params { u16 vxlan_port; u8 update_vxlan_port; @@ -314,8 +303,14 @@ struct qed_eth_ops { int (*q_tx_stop)(struct qed_dev *cdev, u8 rss_id, void *handle); - int (*filter_config)(struct qed_dev *cdev, - struct qed_filter_params *params); + int (*filter_config_rx_mode)(struct qed_dev *cdev, + enum qed_filter_rx_mode_type type); + + int (*filter_config_ucast)(struct qed_dev *cdev, + struct qed_filter_ucast_params *params); + + int (*filter_config_mcast)(struct qed_dev *cdev, + struct qed_filter_mcast_params *params); int (*fastpath_stop)(struct qed_dev *cdev); From 05c4488a0e446c6ccde9f22b573950665e1cd414 Mon Sep 17 00:00:00 2001 From: En-Wei Wu Date: Fri, 5 Jul 2024 10:37:56 +0800 Subject: [PATCH 056/342] wifi: virt_wifi: avoid reporting connection success with wrong SSID [ Upstream commit b5d14b0c6716fad7f0c94ac6e1d6f60a49f985c7 ] When user issues a connection with a different SSID than the one virt_wifi has advertised, the __cfg80211_connect_result() will trigger the warning: WARN_ON(bss_not_found). The issue is because the connection code in virt_wifi does not check the SSID from user space (it only checks the BSSID), and virt_wifi will call cfg80211_connect_result() with WLAN_STATUS_SUCCESS even if the SSID is different from the one virt_wifi has advertised. Eventually cfg80211 won't be able to find the cfg80211_bss and generate the warning. Fixed it by checking the SSID (from user space) in the connection code. Fixes: c7cdba31ed8b ("mac80211-next: rtnetlink wifi simulation device") Reported-by: syzbot+d6eb9cee2885ec06f5e3@syzkaller.appspotmail.com Signed-off-by: En-Wei Wu Link: https://patch.msgid.link/20240705023756.10954-1-en-wei.wu@canonical.com Signed-off-by: Johannes Berg Signed-off-by: Sasha Levin --- drivers/net/wireless/virt_wifi.c | 19 ++++++++++++++++--- 1 file changed, 16 insertions(+), 3 deletions(-) diff --git a/drivers/net/wireless/virt_wifi.c b/drivers/net/wireless/virt_wifi.c index 514f2c1124b6..ec730bc44adc 100644 --- a/drivers/net/wireless/virt_wifi.c +++ b/drivers/net/wireless/virt_wifi.c @@ -136,6 +136,8 @@ static struct ieee80211_supported_band band_5ghz = { /* Assigned at module init. Guaranteed locally-administered and unicast. */ static u8 fake_router_bssid[ETH_ALEN] __ro_after_init = {}; +#define VIRT_WIFI_SSID "VirtWifi" + static void virt_wifi_inform_bss(struct wiphy *wiphy) { u64 tsf = div_u64(ktime_get_boottime_ns(), 1000); @@ -146,8 +148,8 @@ static void virt_wifi_inform_bss(struct wiphy *wiphy) u8 ssid[8]; } __packed ssid = { .tag = WLAN_EID_SSID, - .len = 8, - .ssid = "VirtWifi", + .len = strlen(VIRT_WIFI_SSID), + .ssid = VIRT_WIFI_SSID, }; informed_bss = cfg80211_inform_bss(wiphy, &channel_5ghz, @@ -213,6 +215,8 @@ struct virt_wifi_netdev_priv { struct net_device *upperdev; u32 tx_packets; u32 tx_failed; + u32 connect_requested_ssid_len; + u8 connect_requested_ssid[IEEE80211_MAX_SSID_LEN]; u8 connect_requested_bss[ETH_ALEN]; bool is_up; bool is_connected; @@ -229,6 +233,12 @@ static int virt_wifi_connect(struct wiphy *wiphy, struct net_device *netdev, if (priv->being_deleted || !priv->is_up) return -EBUSY; + if (!sme->ssid) + return -EINVAL; + + priv->connect_requested_ssid_len = sme->ssid_len; + memcpy(priv->connect_requested_ssid, sme->ssid, sme->ssid_len); + could_schedule = schedule_delayed_work(&priv->connect, HZ * 2); if (!could_schedule) return -EBUSY; @@ -252,12 +262,15 @@ static void virt_wifi_connect_complete(struct work_struct *work) container_of(work, struct virt_wifi_netdev_priv, connect.work); u8 *requested_bss = priv->connect_requested_bss; bool right_addr = ether_addr_equal(requested_bss, fake_router_bssid); + bool right_ssid = priv->connect_requested_ssid_len == strlen(VIRT_WIFI_SSID) && + !memcmp(priv->connect_requested_ssid, VIRT_WIFI_SSID, + priv->connect_requested_ssid_len); u16 status = WLAN_STATUS_SUCCESS; if (is_zero_ether_addr(requested_bss)) requested_bss = NULL; - if (!priv->is_up || (requested_bss && !right_addr)) + if (!priv->is_up || (requested_bss && !right_addr) || !right_ssid) status = WLAN_STATUS_UNSPECIFIED_FAILURE; else priv->is_connected = true; From f851ff5c6e0e4de5ae75d81aea1dea6a117c94ff Mon Sep 17 00:00:00 2001 From: Gaosheng Cui Date: Sat, 6 Jul 2024 14:50:08 +0800 Subject: [PATCH 057/342] gss_krb5: Fix the error handling path for crypto_sync_skcipher_setkey [ Upstream commit a3123341dc358952ce2bf8067fbdfb7eaadf71bb ] If we fail to call crypto_sync_skcipher_setkey, we should free the memory allocation for cipher, replace err_return with err_free_cipher to free the memory of cipher. Fixes: 4891f2d008e4 ("gss_krb5: import functionality to derive keys into the kernel") Signed-off-by: Gaosheng Cui Reviewed-by: Simon Horman Signed-off-by: Chuck Lever Signed-off-by: Sasha Levin --- net/sunrpc/auth_gss/gss_krb5_keys.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/net/sunrpc/auth_gss/gss_krb5_keys.c b/net/sunrpc/auth_gss/gss_krb5_keys.c index 726c076950c0..fc4639687c0f 100644 --- a/net/sunrpc/auth_gss/gss_krb5_keys.c +++ b/net/sunrpc/auth_gss/gss_krb5_keys.c @@ -161,7 +161,7 @@ u32 krb5_derive_key(const struct gss_krb5_enctype *gk5e, if (IS_ERR(cipher)) goto err_return; if (crypto_sync_skcipher_setkey(cipher, inkey->data, inkey->len)) - goto err_return; + goto err_free_cipher; /* allocate and set up buffers */ From be53b70fc08198fa090a4d26e8a7c7c641de8aea Mon Sep 17 00:00:00 2001 From: Johannes Berg Date: Tue, 9 Jul 2024 08:34:09 +0200 Subject: [PATCH 058/342] wifi: virt_wifi: don't use strlen() in const context [ Upstream commit 6e909f489191b365364e9d636dec33b5dfd4e5eb ] Looks like not all compilers allow strlen(constant) as a constant, so don't do that. Instead, revert back to defining the length as the first submission had it. Fixes: b5d14b0c6716 ("wifi: virt_wifi: avoid reporting connection success with wrong SSID") Reported-by: kernel test robot Closes: https://lore.kernel.org/oe-kbuild-all/202407090934.NnR1TUbW-lkp@intel.com/ Closes: https://lore.kernel.org/oe-kbuild-all/202407090944.mpwLHGt9-lkp@intel.com/ Signed-off-by: Johannes Berg Signed-off-by: Sasha Levin --- drivers/net/wireless/virt_wifi.c | 5 +++-- 1 file changed, 3 insertions(+), 2 deletions(-) diff --git a/drivers/net/wireless/virt_wifi.c b/drivers/net/wireless/virt_wifi.c index ec730bc44adc..dd6675436bda 100644 --- a/drivers/net/wireless/virt_wifi.c +++ b/drivers/net/wireless/virt_wifi.c @@ -137,6 +137,7 @@ static struct ieee80211_supported_band band_5ghz = { static u8 fake_router_bssid[ETH_ALEN] __ro_after_init = {}; #define VIRT_WIFI_SSID "VirtWifi" +#define VIRT_WIFI_SSID_LEN 8 static void virt_wifi_inform_bss(struct wiphy *wiphy) { @@ -148,7 +149,7 @@ static void virt_wifi_inform_bss(struct wiphy *wiphy) u8 ssid[8]; } __packed ssid = { .tag = WLAN_EID_SSID, - .len = strlen(VIRT_WIFI_SSID), + .len = VIRT_WIFI_SSID_LEN, .ssid = VIRT_WIFI_SSID, }; @@ -262,7 +263,7 @@ static void virt_wifi_connect_complete(struct work_struct *work) container_of(work, struct virt_wifi_netdev_priv, connect.work); u8 *requested_bss = priv->connect_requested_bss; bool right_addr = ether_addr_equal(requested_bss, fake_router_bssid); - bool right_ssid = priv->connect_requested_ssid_len == strlen(VIRT_WIFI_SSID) && + bool right_ssid = priv->connect_requested_ssid_len == VIRT_WIFI_SSID_LEN && !memcmp(priv->connect_requested_ssid, VIRT_WIFI_SSID, priv->connect_requested_ssid_len); u16 status = WLAN_STATUS_SUCCESS; From 1ccb1399bd513a139b5220a4caa24469ac977997 Mon Sep 17 00:00:00 2001 From: Geliang Tang Date: Tue, 9 Jul 2024 17:16:19 +0800 Subject: [PATCH 059/342] selftests/bpf: Close fd in error path in drop_on_reuseport [ Upstream commit adae187ebedcd95d02f045bc37dfecfd5b29434b ] In the error path when update_lookup_map() fails in drop_on_reuseport in prog_tests/sk_lookup.c, "server1", the fd of server 1, should be closed. This patch fixes this by using "goto close_srv1" lable instead of "detach" to close "server1" in this case. Fixes: 0ab5539f8584 ("selftests/bpf: Tests for BPF_SK_LOOKUP attach point") Acked-by: Eduard Zingerman Signed-off-by: Geliang Tang Link: https://lore.kernel.org/r/86aed33b4b0ea3f04497c757845cff7e8e621a2d.1720515893.git.tanggeliang@kylinos.cn Signed-off-by: Martin KaFai Lau Signed-off-by: Sasha Levin --- tools/testing/selftests/bpf/prog_tests/sk_lookup.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/tools/testing/selftests/bpf/prog_tests/sk_lookup.c b/tools/testing/selftests/bpf/prog_tests/sk_lookup.c index b4c9f4a96ae4..95a1d3ee55a7 100644 --- a/tools/testing/selftests/bpf/prog_tests/sk_lookup.c +++ b/tools/testing/selftests/bpf/prog_tests/sk_lookup.c @@ -964,7 +964,7 @@ static void drop_on_reuseport(const struct test *t) err = update_lookup_map(t->sock_map, SERVER_A, server1); if (err) - goto detach; + goto close_srv1; /* second server on destination address we should never reach */ server2 = make_server(t->sotype, t->connect_to.ip, t->connect_to.port, From 28c8fce2078a4a38b2231181f4ddccf62aa27479 Mon Sep 17 00:00:00 2001 From: Alan Maguire Date: Thu, 11 Jul 2024 19:23:21 +0100 Subject: [PATCH 060/342] bpf: annotate BTF show functions with __printf [ Upstream commit b3470da314fd8018ee237e382000c4154a942420 ] -Werror=suggest-attribute=format warns about two functions in kernel/bpf/btf.c [1]; add __printf() annotations to silence these warnings since for CONFIG_WERROR=y they will trigger build failures. [1] https://lore.kernel.org/bpf/a8b20c72-6631-4404-9e1f-0410642d7d20@gmail.com/ Fixes: 31d0bc81637d ("bpf: Move to generic BTF show support, apply it to seq files/strings") Reported-by: Mirsad Todorovac Signed-off-by: Alan Maguire Tested-by: Mirsad Todorovac Link: https://lore.kernel.org/r/20240711182321.963667-1-alan.maguire@oracle.com Signed-off-by: Alexei Starovoitov Signed-off-by: Sasha Levin --- kernel/bpf/btf.c | 8 ++++---- 1 file changed, 4 insertions(+), 4 deletions(-) diff --git a/kernel/bpf/btf.c b/kernel/bpf/btf.c index 06c028bdb8d4..326feb230170 100644 --- a/kernel/bpf/btf.c +++ b/kernel/bpf/btf.c @@ -5344,8 +5344,8 @@ static void btf_type_show(const struct btf *btf, u32 type_id, void *obj, btf_type_ops(t)->show(btf, t, type_id, obj, 0, show); } -static void btf_seq_show(struct btf_show *show, const char *fmt, - va_list args) +__printf(2, 0) static void btf_seq_show(struct btf_show *show, const char *fmt, + va_list args) { seq_vprintf((struct seq_file *)show->target, fmt, args); } @@ -5378,8 +5378,8 @@ struct btf_show_snprintf { int len; /* length we would have written */ }; -static void btf_snprintf_show(struct btf_show *show, const char *fmt, - va_list args) +__printf(2, 0) static void btf_snprintf_show(struct btf_show *show, const char *fmt, + va_list args) { struct btf_show_snprintf *ssnprintf = (struct btf_show_snprintf *)show; int len; From 6ce46045f9b90d952602e2c0b8886cfadf860bf1 Mon Sep 17 00:00:00 2001 From: Alexey Kodanev Date: Mon, 8 Jul 2024 10:50:08 +0000 Subject: [PATCH 061/342] bna: adjust 'name' buf size of bna_tcb and bna_ccb structures [ Upstream commit c9741a03dc8e491e57b95fba0058ab46b7e506da ] To have enough space to write all possible sprintf() args. Currently 'name' size is 16, but the first '%s' specifier may already need at least 16 characters, since 'bnad->netdev->name' is used there. For '%d' specifiers, assume that they require: * 1 char for 'tx_id + tx_info->tcb[i]->id' sum, BNAD_MAX_TXQ_PER_TX is 8 * 2 chars for 'rx_id + rx_info->rx_ctrl[i].ccb->id', BNAD_MAX_RXP_PER_RX is 16 And replace sprintf with snprintf. Detected using the static analysis tool - Svace. Fixes: 8b230ed8ec96 ("bna: Brocade 10Gb Ethernet device driver") Signed-off-by: Alexey Kodanev Reviewed-by: Simon Horman Signed-off-by: David S. Miller Signed-off-by: Sasha Levin --- drivers/net/ethernet/brocade/bna/bna_types.h | 2 +- drivers/net/ethernet/brocade/bna/bnad.c | 11 ++++++----- 2 files changed, 7 insertions(+), 6 deletions(-) diff --git a/drivers/net/ethernet/brocade/bna/bna_types.h b/drivers/net/ethernet/brocade/bna/bna_types.h index 666b6922e24d..ebf54d74c2bb 100644 --- a/drivers/net/ethernet/brocade/bna/bna_types.h +++ b/drivers/net/ethernet/brocade/bna/bna_types.h @@ -410,7 +410,7 @@ struct bna_ib { /* Tx object */ /* Tx datapath control structure */ -#define BNA_Q_NAME_SIZE 16 +#define BNA_Q_NAME_SIZE (IFNAMSIZ + 6) struct bna_tcb { /* Fast path */ void **sw_qpt; diff --git a/drivers/net/ethernet/brocade/bna/bnad.c b/drivers/net/ethernet/brocade/bna/bnad.c index 7e4e831d720f..9ccfb038ffc7 100644 --- a/drivers/net/ethernet/brocade/bna/bnad.c +++ b/drivers/net/ethernet/brocade/bna/bnad.c @@ -1535,8 +1535,9 @@ bnad_tx_msix_register(struct bnad *bnad, struct bnad_tx_info *tx_info, for (i = 0; i < num_txqs; i++) { vector_num = tx_info->tcb[i]->intr_vector; - sprintf(tx_info->tcb[i]->name, "%s TXQ %d", bnad->netdev->name, - tx_id + tx_info->tcb[i]->id); + snprintf(tx_info->tcb[i]->name, BNA_Q_NAME_SIZE, "%s TXQ %d", + bnad->netdev->name, + tx_id + tx_info->tcb[i]->id); err = request_irq(bnad->msix_table[vector_num].vector, (irq_handler_t)bnad_msix_tx, 0, tx_info->tcb[i]->name, @@ -1586,9 +1587,9 @@ bnad_rx_msix_register(struct bnad *bnad, struct bnad_rx_info *rx_info, for (i = 0; i < num_rxps; i++) { vector_num = rx_info->rx_ctrl[i].ccb->intr_vector; - sprintf(rx_info->rx_ctrl[i].ccb->name, "%s CQ %d", - bnad->netdev->name, - rx_id + rx_info->rx_ctrl[i].ccb->id); + snprintf(rx_info->rx_ctrl[i].ccb->name, BNA_Q_NAME_SIZE, + "%s CQ %d", bnad->netdev->name, + rx_id + rx_info->rx_ctrl[i].ccb->id); err = request_irq(bnad->msix_table[vector_num].vector, (irq_handler_t)bnad_msix_rx, 0, rx_info->rx_ctrl[i].ccb->name, From 859bc763747c9012ed58f5c61b89daef6cebe165 Mon Sep 17 00:00:00 2001 From: Alan Maguire Date: Fri, 12 Jul 2024 10:28:59 +0100 Subject: [PATCH 062/342] bpf: Eliminate remaining "make W=1" warnings in kernel/bpf/btf.o MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit [ Upstream commit 2454075f8e2915cebbe52a1195631bc7efe2b7e1 ] As reported by Mirsad [1] we still see format warnings in kernel/bpf/btf.o at W=1 warning level: CC kernel/bpf/btf.o ./kernel/bpf/btf.c: In function ‘btf_type_seq_show_flags’: ./kernel/bpf/btf.c:7553:21: warning: assignment left-hand side might be a candidate for a format attribute [-Wsuggest-attribute=format] 7553 | sseq.showfn = btf_seq_show; | ^ ./kernel/bpf/btf.c: In function ‘btf_type_snprintf_show’: ./kernel/bpf/btf.c:7604:31: warning: assignment left-hand side might be a candidate for a format attribute [-Wsuggest-attribute=format] 7604 | ssnprintf.show.showfn = btf_snprintf_show; | ^ Combined with CONFIG_WERROR=y these can halt the build. The fix (annotating the structure field with __printf()) suggested by Mirsad resolves these. Apologies I missed this last time. No other W=1 warnings were observed in kernel/bpf after this fix. [1] https://lore.kernel.org/bpf/92c9d047-f058-400c-9c7d-81d4dc1ef71b@gmail.com/ Fixes: b3470da314fd ("bpf: annotate BTF show functions with __printf") Reported-by: Mirsad Todorovac Suggested-by: Mirsad Todorovac Signed-off-by: Alan Maguire Signed-off-by: Daniel Borkmann Link: https://lore.kernel.org/bpf/20240712092859.1390960-1-alan.maguire@oracle.com Signed-off-by: Sasha Levin --- kernel/bpf/btf.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/kernel/bpf/btf.c b/kernel/bpf/btf.c index 326feb230170..cfbb038d150c 100644 --- a/kernel/bpf/btf.c +++ b/kernel/bpf/btf.c @@ -340,7 +340,7 @@ static const char *btf_type_str(const struct btf_type *t) struct btf_show { u64 flags; void *target; /* target of show operation (seq file, buffer) */ - void (*showfn)(struct btf_show *show, const char *fmt, va_list args); + __printf(2, 0) void (*showfn)(struct btf_show *show, const char *fmt, va_list args); const struct btf *btf; /* below are used during iteration */ struct { From 96178b12c8818a26df9797180f42d28aafa51b69 Mon Sep 17 00:00:00 2001 From: Amit Cohen Date: Thu, 11 Jul 2024 17:27:02 +0200 Subject: [PATCH 063/342] selftests: forwarding: devlink_lib: Wait for udev events after reloading [ Upstream commit f67a90a0c8f5b3d0acc18f10650d90fec44775f9 ] Lately, an additional locking was added by commit c0a40097f0bc ("drivers: core: synchronize really_probe() and dev_uevent()"). The locking protects dev_uevent() calling. This function is used to send messages from the kernel to user space. Uevent messages notify user space about changes in device states, such as when a device is added, removed, or changed. These messages are used by udev (or other similar user-space tools) to apply device-specific rules. After reloading devlink instance, udev events should be processed. This locking causes a short delay of udev events handling. One example for useful udev rule is renaming ports. 'forwading.config' can be configured to use names after udev rules are applied. Some tests run devlink_reload() and immediately use the updated names. This worked before the above mentioned commit was pushed, but now the delay of uevent messages causes that devlink_reload() returns before udev events are handled and tests fail. Adjust devlink_reload() to not assume that udev events are already processed when devlink reload is done, instead, wait for udev events to ensure they are processed before returning from the function. Without this patch: TESTS='rif_mac_profile' ./resource_scale.sh TEST: 'rif_mac_profile' 4 [ OK ] sysctl: cannot stat /proc/sys/net/ipv6/conf/swp1/disable_ipv6: No such file or directory sysctl: cannot stat /proc/sys/net/ipv6/conf/swp1/disable_ipv6: No such file or directory sysctl: cannot stat /proc/sys/net/ipv6/conf/swp2/disable_ipv6: No such file or directory sysctl: cannot stat /proc/sys/net/ipv6/conf/swp2/disable_ipv6: No such file or directory Cannot find device "swp1" Cannot find device "swp2" TEST: setup_wait_dev (: Interface swp1 does not come up.) [FAIL] With this patch: $ TESTS='rif_mac_profile' ./resource_scale.sh TEST: 'rif_mac_profile' 4 [ OK ] TEST: 'rif_mac_profile' overflow 5 [ OK ] This is relevant not only for this test. Fixes: bc7cbb1e9f4c ("selftests: forwarding: Add devlink_lib.sh") Signed-off-by: Amit Cohen Reviewed-by: Ido Schimmel Signed-off-by: Petr Machata Link: https://patch.msgid.link/89367666e04b38a8993027f1526801ca327ab96a.1720709333.git.petrm@nvidia.com Signed-off-by: Jakub Kicinski Signed-off-by: Sasha Levin --- tools/testing/selftests/net/forwarding/devlink_lib.sh | 2 ++ 1 file changed, 2 insertions(+) diff --git a/tools/testing/selftests/net/forwarding/devlink_lib.sh b/tools/testing/selftests/net/forwarding/devlink_lib.sh index 9c12c4fd3afc..6edfd207e324 100644 --- a/tools/testing/selftests/net/forwarding/devlink_lib.sh +++ b/tools/testing/selftests/net/forwarding/devlink_lib.sh @@ -113,6 +113,8 @@ devlink_reload() still_pending=$(devlink resource show "$DEVLINK_DEV" | \ grep -c "size_new") check_err $still_pending "Failed reload - There are still unset sizes" + + udevadm settle } declare -A DEVLINK_ORIG From be9d08ff102df3ac4f66e826ea935cf3af63a4bd Mon Sep 17 00:00:00 2001 From: Taehee Yoo Date: Fri, 12 Jul 2024 09:51:16 +0000 Subject: [PATCH 064/342] xdp: fix invalid wait context of page_pool_destroy() [ Upstream commit 59a931c5b732ca5fc2ca727f5a72aeabaafa85ec ] If the driver uses a page pool, it creates a page pool with page_pool_create(). The reference count of page pool is 1 as default. A page pool will be destroyed only when a reference count reaches 0. page_pool_destroy() is used to destroy page pool, it decreases a reference count. When a page pool is destroyed, ->disconnect() is called, which is mem_allocator_disconnect(). This function internally acquires mutex_lock(). If the driver uses XDP, it registers a memory model with xdp_rxq_info_reg_mem_model(). The xdp_rxq_info_reg_mem_model() internally increases a page pool reference count if a memory model is a page pool. Now the reference count is 2. To destroy a page pool, the driver should call both page_pool_destroy() and xdp_unreg_mem_model(). The xdp_unreg_mem_model() internally calls page_pool_destroy(). Only page_pool_destroy() decreases a reference count. If a driver calls page_pool_destroy() then xdp_unreg_mem_model(), we will face an invalid wait context warning. Because xdp_unreg_mem_model() calls page_pool_destroy() with rcu_read_lock(). The page_pool_destroy() internally acquires mutex_lock(). Splat looks like: ============================= [ BUG: Invalid wait context ] 6.10.0-rc6+ #4 Tainted: G W ----------------------------- ethtool/1806 is trying to lock: ffffffff90387b90 (mem_id_lock){+.+.}-{4:4}, at: mem_allocator_disconnect+0x73/0x150 other info that might help us debug this: context-{5:5} 3 locks held by ethtool/1806: stack backtrace: CPU: 0 PID: 1806 Comm: ethtool Tainted: G W 6.10.0-rc6+ #4 f916f41f172891c800f2fed Hardware name: ASUS System Product Name/PRIME Z690-P D4, BIOS 0603 11/01/2021 Call Trace: dump_stack_lvl+0x7e/0xc0 __lock_acquire+0x1681/0x4de0 ? _printk+0x64/0xe0 ? __pfx_mark_lock.part.0+0x10/0x10 ? __pfx___lock_acquire+0x10/0x10 lock_acquire+0x1b3/0x580 ? mem_allocator_disconnect+0x73/0x150 ? __wake_up_klogd.part.0+0x16/0xc0 ? __pfx_lock_acquire+0x10/0x10 ? dump_stack_lvl+0x91/0xc0 __mutex_lock+0x15c/0x1690 ? mem_allocator_disconnect+0x73/0x150 ? __pfx_prb_read_valid+0x10/0x10 ? mem_allocator_disconnect+0x73/0x150 ? __pfx_llist_add_batch+0x10/0x10 ? console_unlock+0x193/0x1b0 ? lockdep_hardirqs_on+0xbe/0x140 ? __pfx___mutex_lock+0x10/0x10 ? tick_nohz_tick_stopped+0x16/0x90 ? __irq_work_queue_local+0x1e5/0x330 ? irq_work_queue+0x39/0x50 ? __wake_up_klogd.part.0+0x79/0xc0 ? mem_allocator_disconnect+0x73/0x150 mem_allocator_disconnect+0x73/0x150 ? __pfx_mem_allocator_disconnect+0x10/0x10 ? mark_held_locks+0xa5/0xf0 ? rcu_is_watching+0x11/0xb0 page_pool_release+0x36e/0x6d0 page_pool_destroy+0xd7/0x440 xdp_unreg_mem_model+0x1a7/0x2a0 ? __pfx_xdp_unreg_mem_model+0x10/0x10 ? kfree+0x125/0x370 ? bnxt_free_ring.isra.0+0x2eb/0x500 ? bnxt_free_mem+0x5ac/0x2500 xdp_rxq_info_unreg+0x4a/0xd0 bnxt_free_mem+0x1356/0x2500 bnxt_close_nic+0xf0/0x3b0 ? __pfx_bnxt_close_nic+0x10/0x10 ? ethnl_parse_bit+0x2c6/0x6d0 ? __pfx___nla_validate_parse+0x10/0x10 ? __pfx_ethnl_parse_bit+0x10/0x10 bnxt_set_features+0x2a8/0x3e0 __netdev_update_features+0x4dc/0x1370 ? ethnl_parse_bitset+0x4ff/0x750 ? __pfx_ethnl_parse_bitset+0x10/0x10 ? __pfx___netdev_update_features+0x10/0x10 ? mark_held_locks+0xa5/0xf0 ? _raw_spin_unlock_irqrestore+0x42/0x70 ? __pm_runtime_resume+0x7d/0x110 ethnl_set_features+0x32d/0xa20 To fix this problem, it uses rhashtable_lookup_fast() instead of rhashtable_lookup() with rcu_read_lock(). Using xa without rcu_read_lock() here is safe. xa is freed by __xdp_mem_allocator_rcu_free() and this is called by call_rcu() of mem_xa_remove(). The mem_xa_remove() is called by page_pool_destroy() if a reference count reaches 0. The xa is already protected by the reference count mechanism well in the control plane. So removing rcu_read_lock() for page_pool_destroy() is safe. Fixes: c3f812cea0d7 ("page_pool: do not release pool until inflight == 0.") Signed-off-by: Taehee Yoo Reviewed-by: Jakub Kicinski Link: https://patch.msgid.link/20240712095116.3801586-1-ap420073@gmail.com Signed-off-by: Jakub Kicinski Signed-off-by: Sasha Levin --- net/core/xdp.c | 4 +--- 1 file changed, 1 insertion(+), 3 deletions(-) diff --git a/net/core/xdp.c b/net/core/xdp.c index fd98d6059007..b2ad644df21f 100644 --- a/net/core/xdp.c +++ b/net/core/xdp.c @@ -124,10 +124,8 @@ void xdp_unreg_mem_model(struct xdp_mem_info *mem) return; if (type == MEM_TYPE_PAGE_POOL) { - rcu_read_lock(); - xa = rhashtable_lookup(mem_id_ht, &id, mem_id_rht_params); + xa = rhashtable_lookup_fast(mem_id_ht, &id, mem_id_rht_params); page_pool_destroy(xa->page_pool); - rcu_read_unlock(); } } EXPORT_SYMBOL_GPL(xdp_unreg_mem_model); From fb20da833874ed7a447fa08f4e4d52bb18cdcaca Mon Sep 17 00:00:00 2001 From: Douglas Anderson Date: Fri, 17 May 2024 14:36:37 -0700 Subject: [PATCH 065/342] drm/panel: boe-tv101wum-nl6: If prepare fails, disable GPIO before regulators [ Upstream commit 587c48f622374e5d47b1d515c6006a4df4dee882 ] The enable GPIO should clearly be set low before turning off regulators. That matches both the inverse order that things were enabled and also the order in unprepare(). Fixes: a869b9db7adf ("drm/panel: support for boe tv101wum-nl6 wuxga dsi video mode panel") Signed-off-by: Douglas Anderson Reviewed-by: Dmitry Baryshkov Reviewed-by: Linus Walleij Link: https://lore.kernel.org/r/20240517143643.2.Ieac346cd0f1606948ba39ceea06b55359fe972b6@changeid Signed-off-by: Neil Armstrong Link: https://patchwork.freedesktop.org/patch/msgid/20240517143643.2.Ieac346cd0f1606948ba39ceea06b55359fe972b6@changeid Signed-off-by: Sasha Levin --- drivers/gpu/drm/panel/panel-boe-tv101wum-nl6.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/drivers/gpu/drm/panel/panel-boe-tv101wum-nl6.c b/drivers/gpu/drm/panel/panel-boe-tv101wum-nl6.c index 9e518213a54f..c448be3d01d1 100644 --- a/drivers/gpu/drm/panel/panel-boe-tv101wum-nl6.c +++ b/drivers/gpu/drm/panel/panel-boe-tv101wum-nl6.c @@ -574,13 +574,13 @@ static int boe_panel_prepare(struct drm_panel *panel) return 0; poweroff: + gpiod_set_value(boe->enable_gpio, 0); regulator_disable(boe->avee); poweroffavdd: regulator_disable(boe->avdd); poweroff1v8: usleep_range(5000, 7000); regulator_disable(boe->pp1800); - gpiod_set_value(boe->enable_gpio, 0); return ret; } From 7aaa368c684cca1151a26c3cb649f1ca07a40ea7 Mon Sep 17 00:00:00 2001 From: Douglas Anderson Date: Fri, 17 May 2024 14:36:38 -0700 Subject: [PATCH 066/342] drm/panel: boe-tv101wum-nl6: Check for errors on the NOP in prepare() [ Upstream commit 6320b9199dd99622668649c234d4e8a99e44a9c8 ] The mipi_dsi_dcs_nop() function returns an error but we weren't checking it in boe_panel_prepare(). Add a check. This is highly unlikely to matter in practice. If the NOP failed then likely later MIPI commands would fail too. Found by code inspection. Fixes: 812562b8d881 ("drm/panel: boe-tv101wum-nl6: Fine tune the panel power sequence") Signed-off-by: Douglas Anderson Reviewed-by: AngeloGioacchino Del Regno Reviewed-by: Dmitry Baryshkov Reviewed-by: Linus Walleij Link: https://lore.kernel.org/r/20240517143643.3.Ibffbaa5b4999ac0e55f43bf353144433b099d727@changeid Signed-off-by: Neil Armstrong Link: https://patchwork.freedesktop.org/patch/msgid/20240517143643.3.Ibffbaa5b4999ac0e55f43bf353144433b099d727@changeid Signed-off-by: Sasha Levin --- drivers/gpu/drm/panel/panel-boe-tv101wum-nl6.c | 6 +++++- 1 file changed, 5 insertions(+), 1 deletion(-) diff --git a/drivers/gpu/drm/panel/panel-boe-tv101wum-nl6.c b/drivers/gpu/drm/panel/panel-boe-tv101wum-nl6.c index c448be3d01d1..0a2d5f461aee 100644 --- a/drivers/gpu/drm/panel/panel-boe-tv101wum-nl6.c +++ b/drivers/gpu/drm/panel/panel-boe-tv101wum-nl6.c @@ -553,7 +553,11 @@ static int boe_panel_prepare(struct drm_panel *panel) usleep_range(5000, 10000); if (boe->desc->lp11_before_reset) { - mipi_dsi_dcs_nop(boe->dsi); + ret = mipi_dsi_dcs_nop(boe->dsi); + if (ret < 0) { + dev_err(&boe->dsi->dev, "Failed to send NOP: %d\n", ret); + goto poweroff; + } usleep_range(1000, 2000); } gpiod_set_value(boe->enable_gpio, 1); From bcc963f591b9a445e4b6ef7fdc9829719b1bcd08 Mon Sep 17 00:00:00 2001 From: Zheng Yejian Date: Thu, 9 May 2024 20:44:14 +0800 Subject: [PATCH 067/342] media: dvb-usb: Fix unexpected infinite loop in dvb_usb_read_remote_control() [ Upstream commit 2052138b7da52ad5ccaf74f736d00f39a1c9198c ] Infinite log printing occurs during fuzz test: rc rc1: DViCO FusionHDTV DVB-T USB (LGZ201) as ... ... dvb-usb: schedule remote query interval to 100 msecs. dvb-usb: DViCO FusionHDTV DVB-T USB (LGZ201) successfully initialized ... dvb-usb: bulk message failed: -22 (1/0) dvb-usb: bulk message failed: -22 (1/0) dvb-usb: bulk message failed: -22 (1/0) ... dvb-usb: bulk message failed: -22 (1/0) Looking into the codes, there is a loop in dvb_usb_read_remote_control(), that is in rc_core_dvb_usb_remote_init() create a work that will call dvb_usb_read_remote_control(), and this work will reschedule itself at 'rc_interval' intervals to recursively call dvb_usb_read_remote_control(), see following code snippet: rc_core_dvb_usb_remote_init() { ... INIT_DELAYED_WORK(&d->rc_query_work, dvb_usb_read_remote_control); schedule_delayed_work(&d->rc_query_work, msecs_to_jiffies(rc_interval)); ... } dvb_usb_read_remote_control() { ... err = d->props.rc.core.rc_query(d); if (err) err(...) // Did not return even if query failed schedule_delayed_work(&d->rc_query_work, msecs_to_jiffies(rc_interval)); } When the infinite log printing occurs, the query callback 'd->props.rc.core.rc_query' is cxusb_rc_query(). And the log is due to the failure of finding a valid 'generic_bulk_ctrl_endpoint' in usb_bulk_msg(), see following code snippet: cxusb_rc_query() { cxusb_ctrl_msg() { dvb_usb_generic_rw() { ret = usb_bulk_msg(d->udev, usb_sndbulkpipe(d->udev, d->props.generic_bulk_ctrl_endpoint),...); if (ret) err("bulk message failed: %d (%d/%d)",ret,wlen,actlen); ... } ... } By analyzing the corresponding USB descriptor, it shows that the bNumEndpoints is 0 in its interface descriptor, but the 'generic_bulk_ctrl_endpoint' is 1, that means user don't configure a valid endpoint for 'generic_bulk_ctrl_endpoint', therefore this 'invalid' USB device should be rejected before it calls into dvb_usb_read_remote_control(). To fix it, we need to add endpoint check for 'generic_bulk_ctrl_endpoint'. And as Sean suggested, the same check and clear halts should be done for 'generic_bulk_ctrl_endpoint_response'. So introduce dvb_usb_check_bulk_endpoint() to do it for both of them. Fixes: 4d43e13f723e ("V4L/DVB (4643): Multi-input patch for DVB-USB device") Signed-off-by: Zheng Yejian Signed-off-by: Sean Young Signed-off-by: Hans Verkuil Signed-off-by: Sasha Levin --- drivers/media/usb/dvb-usb/dvb-usb-init.c | 35 +++++++++++++++++++++--- 1 file changed, 31 insertions(+), 4 deletions(-) diff --git a/drivers/media/usb/dvb-usb/dvb-usb-init.c b/drivers/media/usb/dvb-usb/dvb-usb-init.c index 58eea8ab5477..6cf6d08cc4ec 100644 --- a/drivers/media/usb/dvb-usb/dvb-usb-init.c +++ b/drivers/media/usb/dvb-usb/dvb-usb-init.c @@ -23,11 +23,40 @@ static int dvb_usb_force_pid_filter_usage; module_param_named(force_pid_filter_usage, dvb_usb_force_pid_filter_usage, int, 0444); MODULE_PARM_DESC(force_pid_filter_usage, "force all dvb-usb-devices to use a PID filter, if any (default: 0)."); +static int dvb_usb_check_bulk_endpoint(struct dvb_usb_device *d, u8 endpoint) +{ + if (endpoint) { + int ret; + + ret = usb_pipe_type_check(d->udev, usb_sndbulkpipe(d->udev, endpoint)); + if (ret) + return ret; + ret = usb_pipe_type_check(d->udev, usb_rcvbulkpipe(d->udev, endpoint)); + if (ret) + return ret; + } + return 0; +} + +static void dvb_usb_clear_halt(struct dvb_usb_device *d, u8 endpoint) +{ + if (endpoint) { + usb_clear_halt(d->udev, usb_sndbulkpipe(d->udev, endpoint)); + usb_clear_halt(d->udev, usb_rcvbulkpipe(d->udev, endpoint)); + } +} + static int dvb_usb_adapter_init(struct dvb_usb_device *d, short *adapter_nrs) { struct dvb_usb_adapter *adap; int ret, n, o; + ret = dvb_usb_check_bulk_endpoint(d, d->props.generic_bulk_ctrl_endpoint); + if (ret) + return ret; + ret = dvb_usb_check_bulk_endpoint(d, d->props.generic_bulk_ctrl_endpoint_response); + if (ret) + return ret; for (n = 0; n < d->props.num_adapters; n++) { adap = &d->adapter[n]; adap->dev = d; @@ -103,10 +132,8 @@ static int dvb_usb_adapter_init(struct dvb_usb_device *d, short *adapter_nrs) * when reloading the driver w/o replugging the device * sometimes a timeout occurs, this helps */ - if (d->props.generic_bulk_ctrl_endpoint != 0) { - usb_clear_halt(d->udev, usb_sndbulkpipe(d->udev, d->props.generic_bulk_ctrl_endpoint)); - usb_clear_halt(d->udev, usb_rcvbulkpipe(d->udev, d->props.generic_bulk_ctrl_endpoint)); - } + dvb_usb_clear_halt(d, d->props.generic_bulk_ctrl_endpoint); + dvb_usb_clear_halt(d, d->props.generic_bulk_ctrl_endpoint_response); return 0; From f3968b3d3cfb8d9d430ab31d18d4553bea206a96 Mon Sep 17 00:00:00 2001 From: Ricardo Ribalda Date: Mon, 6 May 2024 21:10:27 +0000 Subject: [PATCH 068/342] media: imon: Fix race getting ictx->lock [ Upstream commit 24147897507cd3a7d63745d1518a638bf4132238 ] Lets fix a race between mutex_is_lock() and mutex_lock(). <-mutex is not locked if (!mutex_is_locked(&ictx->lock)) { unlock = true; <- mutex is locked externaly mutex_lock(&ictx->lock); } Let's use mutex_trylock() that does mutex_is_lock() and mutex_lock() atomically. Fix the following cocci warning: drivers/media/rc/imon.c:1167:1-7: preceding lock on line 1153 Fixes: 23ef710e1a6c ("[media] imon: add conditional locking in change_protocol") Signed-off-by: Ricardo Ribalda Signed-off-by: Sean Young Signed-off-by: Hans Verkuil Signed-off-by: Sasha Levin --- drivers/media/rc/imon.c | 5 +---- 1 file changed, 1 insertion(+), 4 deletions(-) diff --git a/drivers/media/rc/imon.c b/drivers/media/rc/imon.c index 253a1d1a840a..cd4995e74b97 100644 --- a/drivers/media/rc/imon.c +++ b/drivers/media/rc/imon.c @@ -1153,10 +1153,7 @@ static int imon_ir_change_protocol(struct rc_dev *rc, u64 *rc_proto) memcpy(ictx->usb_tx_buf, &ir_proto_packet, sizeof(ir_proto_packet)); - if (!mutex_is_locked(&ictx->lock)) { - unlock = true; - mutex_lock(&ictx->lock); - } + unlock = mutex_trylock(&ictx->lock); retval = send_packet(ictx); if (retval) From e470e95616bf3fd328ec39552d18935406819f0e Mon Sep 17 00:00:00 2001 From: Aleksandr Burakov Date: Fri, 16 Feb 2024 15:40:06 +0300 Subject: [PATCH 069/342] saa7134: Unchecked i2c_transfer function result fixed [ Upstream commit 9d8683b3fd93f0e378f24dc3d9604e5d7d3e0a17 ] Return value of function 'i2c_transfer' is not checked that may cause undefined behaviour. Found by Linux Verification Center (linuxtesting.org) with SVACE. Fixes: 2cf36ac44730 ("[PATCH] v4l: 656: added support for the following cards") Signed-off-by: Aleksandr Burakov Signed-off-by: Hans Verkuil Signed-off-by: Sasha Levin --- drivers/media/pci/saa7134/saa7134-dvb.c | 8 ++++++-- 1 file changed, 6 insertions(+), 2 deletions(-) diff --git a/drivers/media/pci/saa7134/saa7134-dvb.c b/drivers/media/pci/saa7134/saa7134-dvb.c index f359cd5c006a..c786b83a69d2 100644 --- a/drivers/media/pci/saa7134/saa7134-dvb.c +++ b/drivers/media/pci/saa7134/saa7134-dvb.c @@ -466,7 +466,9 @@ static int philips_europa_tuner_sleep(struct dvb_frontend *fe) /* switch the board to analog mode */ if (fe->ops.i2c_gate_ctrl) fe->ops.i2c_gate_ctrl(fe, 1); - i2c_transfer(&dev->i2c_adap, &analog_msg, 1); + if (i2c_transfer(&dev->i2c_adap, &analog_msg, 1) != 1) + return -EIO; + return 0; } @@ -1018,7 +1020,9 @@ static int md8800_set_voltage2(struct dvb_frontend *fe, else wbuf[1] = rbuf & 0xef; msg[0].len = 2; - i2c_transfer(&dev->i2c_adap, msg, 1); + if (i2c_transfer(&dev->i2c_adap, msg, 1) != 1) + return -EIO; + return 0; } From 115d814d6acd4badb8b8f670b13e44884523fd50 Mon Sep 17 00:00:00 2001 From: Ricardo Ribalda Date: Wed, 23 Dec 2020 14:35:21 +0100 Subject: [PATCH 070/342] media: uvcvideo: Allow entity-defined get_info and get_cur [ Upstream commit 65900c581d014499f0f8ceabfc02c652e9a88771 ] Allows controls to get their properties and current value from an entity-defined function instead of via a query to the USB device. Signed-off-by: Ricardo Ribalda Signed-off-by: Laurent Pinchart Signed-off-by: Mauro Carvalho Chehab Stable-dep-of: 86419686e66d ("media: uvcvideo: Override default flags") Signed-off-by: Sasha Levin --- drivers/media/usb/uvc/uvc_ctrl.c | 22 ++++++++++++++++++---- drivers/media/usb/uvc/uvcvideo.h | 5 +++++ 2 files changed, 23 insertions(+), 4 deletions(-) diff --git a/drivers/media/usb/uvc/uvc_ctrl.c b/drivers/media/usb/uvc/uvc_ctrl.c index 5e0acabed37a..e1a98c95b785 100644 --- a/drivers/media/usb/uvc/uvc_ctrl.c +++ b/drivers/media/usb/uvc/uvc_ctrl.c @@ -1002,10 +1002,20 @@ static int __uvc_ctrl_get(struct uvc_video_chain *chain, return -EACCES; if (!ctrl->loaded) { - ret = uvc_query_ctrl(chain->dev, UVC_GET_CUR, ctrl->entity->id, - chain->dev->intfnum, ctrl->info.selector, + if (ctrl->entity->get_cur) { + ret = ctrl->entity->get_cur(chain->dev, + ctrl->entity, + ctrl->info.selector, uvc_ctrl_data(ctrl, UVC_CTRL_DATA_CURRENT), ctrl->info.size); + } else { + ret = uvc_query_ctrl(chain->dev, UVC_GET_CUR, + ctrl->entity->id, + chain->dev->intfnum, + ctrl->info.selector, + uvc_ctrl_data(ctrl, UVC_CTRL_DATA_CURRENT), + ctrl->info.size); + } if (ret < 0) return ret; @@ -1718,8 +1728,12 @@ static int uvc_ctrl_get_flags(struct uvc_device *dev, if (data == NULL) return -ENOMEM; - ret = uvc_query_ctrl(dev, UVC_GET_INFO, ctrl->entity->id, dev->intfnum, - info->selector, data, 1); + if (ctrl->entity->get_info) + ret = ctrl->entity->get_info(dev, ctrl->entity, + ctrl->info.selector, data); + else + ret = uvc_query_ctrl(dev, UVC_GET_INFO, ctrl->entity->id, + dev->intfnum, info->selector, data, 1); if (!ret) info->flags |= (data[0] & UVC_CONTROL_CAP_GET ? UVC_CTRL_FLAG_GET_CUR : 0) diff --git a/drivers/media/usb/uvc/uvcvideo.h b/drivers/media/usb/uvc/uvcvideo.h index c75990c0957e..c3241cf5f7b4 100644 --- a/drivers/media/usb/uvc/uvcvideo.h +++ b/drivers/media/usb/uvc/uvcvideo.h @@ -354,6 +354,11 @@ struct uvc_entity { u8 bNrInPins; u8 *baSourceID; + int (*get_info)(struct uvc_device *dev, struct uvc_entity *entity, + u8 cs, u8 *caps); + int (*get_cur)(struct uvc_device *dev, struct uvc_entity *entity, + u8 cs, void *data, u16 size); + unsigned int ncontrols; struct uvc_control *controls; }; From 9459f33175624e84cd0abdb3d25a571360a72cff Mon Sep 17 00:00:00 2001 From: Daniel Schaefer Date: Sun, 2 Jun 2024 14:50:53 +0800 Subject: [PATCH 071/342] media: uvcvideo: Override default flags [ Upstream commit 86419686e66da5b90a07fb8a40ab138fe97189b5 ] When the UVC device has a control that is readonly it doesn't set the SET_CUR flag. For example the privacy control has SET_CUR flag set in the defaults in the `uvc_ctrls` variable. Even if the device does not have it set, it's not cleared by uvc_ctrl_get_flags(). Originally written with assignment in commit 859086ae3636 ("media: uvcvideo: Apply flags from device to actual properties"). But changed to |= in commit 0dc68cabdb62 ("media: uvcvideo: Prevent setting unavailable flags"). It would not clear the default flags. With this patch applied the correct flags are reported to user space. Tested with: ``` > v4l2-ctl --list-ctrls | grep privacy privacy 0x009a0910 (bool) : default=0 value=0 flags=read-only ``` Signed-off-by: Daniel Schaefer Fixes: 0dc68cabdb62 ("media: uvcvideo: Prevent setting unavailable flags") Reviewed-by: Ricardo Ribalda Reviewed-by: Laurent Pinchart Link: https://lore.kernel.org/r/20240602065053.36850-1-dhs@frame.work Signed-off-by: Laurent Pinchart Signed-off-by: Sasha Levin --- drivers/media/usb/uvc/uvc_ctrl.c | 9 ++++++++- 1 file changed, 8 insertions(+), 1 deletion(-) diff --git a/drivers/media/usb/uvc/uvc_ctrl.c b/drivers/media/usb/uvc/uvc_ctrl.c index e1a98c95b785..c89f582bd532 100644 --- a/drivers/media/usb/uvc/uvc_ctrl.c +++ b/drivers/media/usb/uvc/uvc_ctrl.c @@ -1734,7 +1734,13 @@ static int uvc_ctrl_get_flags(struct uvc_device *dev, else ret = uvc_query_ctrl(dev, UVC_GET_INFO, ctrl->entity->id, dev->intfnum, info->selector, data, 1); - if (!ret) + + if (!ret) { + info->flags &= ~(UVC_CTRL_FLAG_GET_CUR | + UVC_CTRL_FLAG_SET_CUR | + UVC_CTRL_FLAG_AUTO_UPDATE | + UVC_CTRL_FLAG_ASYNCHRONOUS); + info->flags |= (data[0] & UVC_CONTROL_CAP_GET ? UVC_CTRL_FLAG_GET_CUR : 0) | (data[0] & UVC_CONTROL_CAP_SET ? @@ -1743,6 +1749,7 @@ static int uvc_ctrl_get_flags(struct uvc_device *dev, UVC_CTRL_FLAG_AUTO_UPDATE : 0) | (data[0] & UVC_CONTROL_CAP_ASYNCHRONOUS ? UVC_CTRL_FLAG_ASYNCHRONOUS : 0); + } kfree(data); return ret; From 3944484005d66cb660be273e1e3cab809508ef7a Mon Sep 17 00:00:00 2001 From: Laurent Pinchart Date: Sun, 5 May 2024 20:22:27 +0300 Subject: [PATCH 072/342] media: renesas: vsp1: Fix _irqsave and _irq mix [ Upstream commit 57edbbcf5258c378a9b9d0c80d33b03a010b22c8 ] The histogram support mixes _irqsave and _irq, causing the following smatch warning: drivers/media/platform/renesas/vsp1/vsp1_histo.c:153 histo_stop_streaming() warn: mixing irqsave and irq The histo_stop_streaming() calls spin_lock_irqsave() followed by wait_event_lock_irq(). The former hints that interrupts may be disabled by the caller, while the latter reenables interrupts unconditionally. This doesn't cause any real bug, as the function is always called with interrupts enabled, but the pattern is still incorrect. Fix the problem by using spin_lock_irq() instead of spin_lock_irqsave() in histo_stop_streaming(). While at it, switch to spin_lock_irq() and spin_lock() as appropriate elsewhere. Fixes: 99362e32332b ("[media] v4l: vsp1: Add histogram support") Reported-by: Dan Carpenter Closes: https://lore.kernel.org/linux-renesas-soc/164d74ff-312c-468f-be64-afa7182cd2f4@moroto.mountain/ Reviewed-by: Kieran Bingham Signed-off-by: Laurent Pinchart Signed-off-by: Sasha Levin --- drivers/media/platform/vsp1/vsp1_histo.c | 20 ++++++++------------ 1 file changed, 8 insertions(+), 12 deletions(-) diff --git a/drivers/media/platform/vsp1/vsp1_histo.c b/drivers/media/platform/vsp1/vsp1_histo.c index a91e142bcb94..37df7d2d4639 100644 --- a/drivers/media/platform/vsp1/vsp1_histo.c +++ b/drivers/media/platform/vsp1/vsp1_histo.c @@ -36,9 +36,8 @@ struct vsp1_histogram_buffer * vsp1_histogram_buffer_get(struct vsp1_histogram *histo) { struct vsp1_histogram_buffer *buf = NULL; - unsigned long flags; - spin_lock_irqsave(&histo->irqlock, flags); + spin_lock(&histo->irqlock); if (list_empty(&histo->irqqueue)) goto done; @@ -49,7 +48,7 @@ vsp1_histogram_buffer_get(struct vsp1_histogram *histo) histo->readout = true; done: - spin_unlock_irqrestore(&histo->irqlock, flags); + spin_unlock(&histo->irqlock); return buf; } @@ -58,7 +57,6 @@ void vsp1_histogram_buffer_complete(struct vsp1_histogram *histo, size_t size) { struct vsp1_pipeline *pipe = histo->entity.pipe; - unsigned long flags; /* * The pipeline pointer is guaranteed to be valid as this function is @@ -70,10 +68,10 @@ void vsp1_histogram_buffer_complete(struct vsp1_histogram *histo, vb2_set_plane_payload(&buf->buf.vb2_buf, 0, size); vb2_buffer_done(&buf->buf.vb2_buf, VB2_BUF_STATE_DONE); - spin_lock_irqsave(&histo->irqlock, flags); + spin_lock(&histo->irqlock); histo->readout = false; wake_up(&histo->wait_queue); - spin_unlock_irqrestore(&histo->irqlock, flags); + spin_unlock(&histo->irqlock); } /* ----------------------------------------------------------------------------- @@ -124,11 +122,10 @@ static void histo_buffer_queue(struct vb2_buffer *vb) struct vb2_v4l2_buffer *vbuf = to_vb2_v4l2_buffer(vb); struct vsp1_histogram *histo = vb2_get_drv_priv(vb->vb2_queue); struct vsp1_histogram_buffer *buf = to_vsp1_histogram_buffer(vbuf); - unsigned long flags; - spin_lock_irqsave(&histo->irqlock, flags); + spin_lock_irq(&histo->irqlock); list_add_tail(&buf->queue, &histo->irqqueue); - spin_unlock_irqrestore(&histo->irqlock, flags); + spin_unlock_irq(&histo->irqlock); } static int histo_start_streaming(struct vb2_queue *vq, unsigned int count) @@ -140,9 +137,8 @@ static void histo_stop_streaming(struct vb2_queue *vq) { struct vsp1_histogram *histo = vb2_get_drv_priv(vq); struct vsp1_histogram_buffer *buffer; - unsigned long flags; - spin_lock_irqsave(&histo->irqlock, flags); + spin_lock_irq(&histo->irqlock); /* Remove all buffers from the IRQ queue. */ list_for_each_entry(buffer, &histo->irqqueue, queue) @@ -152,7 +148,7 @@ static void histo_stop_streaming(struct vb2_queue *vq) /* Wait for the buffer being read out (if any) to complete. */ wait_event_lock_irq(histo->wait_queue, !histo->readout, histo->irqlock); - spin_unlock_irqrestore(&histo->irqlock, flags); + spin_unlock_irq(&histo->irqlock); } static const struct vb2_ops histo_video_queue_qops = { From 3c9071a8710574dcdf2908c1fece65d0ac5fa182 Mon Sep 17 00:00:00 2001 From: Laurent Pinchart Date: Sun, 19 Nov 2023 03:11:51 +0200 Subject: [PATCH 073/342] media: renesas: vsp1: Store RPF partition configuration per RPF instance [ Upstream commit a213bc09b1025c771ee722ee341af1d84375db8a ] The vsp1_partition structure stores the RPF partition configuration in a single field for all RPF instances, while each RPF can have its own configuration. Fix it by storing the configuration separately for each RPF instance. Signed-off-by: Laurent Pinchart Fixes: ab45e8585182 ("media: v4l: vsp1: Allow entities to participate in the partition algorithm") Reviewed-by: Jacopo Mondi Signed-off-by: Sasha Levin --- drivers/media/platform/vsp1/vsp1_pipe.h | 2 +- drivers/media/platform/vsp1/vsp1_rpf.c | 8 +++++--- 2 files changed, 6 insertions(+), 4 deletions(-) diff --git a/drivers/media/platform/vsp1/vsp1_pipe.h b/drivers/media/platform/vsp1/vsp1_pipe.h index ae646c9ef337..15daf35bda21 100644 --- a/drivers/media/platform/vsp1/vsp1_pipe.h +++ b/drivers/media/platform/vsp1/vsp1_pipe.h @@ -73,7 +73,7 @@ struct vsp1_partition_window { * @wpf: The WPF partition window configuration */ struct vsp1_partition { - struct vsp1_partition_window rpf; + struct vsp1_partition_window rpf[VSP1_MAX_RPF]; struct vsp1_partition_window uds_sink; struct vsp1_partition_window uds_source; struct vsp1_partition_window sru; diff --git a/drivers/media/platform/vsp1/vsp1_rpf.c b/drivers/media/platform/vsp1/vsp1_rpf.c index 75083cb234fe..996a3058d5b7 100644 --- a/drivers/media/platform/vsp1/vsp1_rpf.c +++ b/drivers/media/platform/vsp1/vsp1_rpf.c @@ -271,8 +271,8 @@ static void rpf_configure_partition(struct vsp1_entity *entity, * 'width' need to be adjusted. */ if (pipe->partitions > 1) { - crop.width = pipe->partition->rpf.width; - crop.left += pipe->partition->rpf.left; + crop.width = pipe->partition->rpf[rpf->entity.index].width; + crop.left += pipe->partition->rpf[rpf->entity.index].left; } if (pipe->interlaced) { @@ -327,7 +327,9 @@ static void rpf_partition(struct vsp1_entity *entity, unsigned int partition_idx, struct vsp1_partition_window *window) { - partition->rpf = *window; + struct vsp1_rwpf *rpf = to_rwpf(&entity->subdev); + + partition->rpf[rpf->entity.index] = *window; } static const struct vsp1_entity_operations rpf_entity_ops = { From 09c1583f0e10c918855d6e7540a79461a353e5d6 Mon Sep 17 00:00:00 2001 From: Hans de Goede Date: Sat, 4 May 2024 18:25:33 +0200 Subject: [PATCH 074/342] leds: trigger: Unregister sysfs attributes before calling deactivate() MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit [ Upstream commit c0dc9adf9474ecb7106e60e5472577375aedaed3 ] Triggers which have trigger specific sysfs attributes typically store related data in trigger-data allocated by the activate() callback and freed by the deactivate() callback. Calling device_remove_groups() after calling deactivate() leaves a window where the sysfs attributes show/store functions could be called after deactivation and then operate on the just freed trigger-data. Move the device_remove_groups() call to before deactivate() to close this race window. This also makes the deactivation path properly do things in reverse order of the activation path which calls the activate() callback before calling device_add_groups(). Fixes: a7e7a3156300 ("leds: triggers: add device attribute support") Cc: Uwe Kleine-König Signed-off-by: Hans de Goede Acked-by: Uwe Kleine-König Link: https://lore.kernel.org/r/20240504162533.76780-1-hdegoede@redhat.com Signed-off-by: Lee Jones Signed-off-by: Sasha Levin --- drivers/leds/led-triggers.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/drivers/leds/led-triggers.c b/drivers/leds/led-triggers.c index 4e7b78a84149..cbe70f38cb57 100644 --- a/drivers/leds/led-triggers.c +++ b/drivers/leds/led-triggers.c @@ -177,9 +177,9 @@ int led_trigger_set(struct led_classdev *led_cdev, struct led_trigger *trig) flags); cancel_work_sync(&led_cdev->set_brightness_work); led_stop_software_blink(led_cdev); + device_remove_groups(led_cdev->dev, led_cdev->trigger->groups); if (led_cdev->trigger->deactivate) led_cdev->trigger->deactivate(led_cdev); - device_remove_groups(led_cdev->dev, led_cdev->trigger->groups); led_cdev->trigger = NULL; led_cdev->trigger_data = NULL; led_cdev->activated = false; From 6ef4f1e98154d9938b4161f56c94013b55b9dacf Mon Sep 17 00:00:00 2001 From: Namhyung Kim Date: Fri, 21 Jun 2024 10:05:25 -0700 Subject: [PATCH 075/342] perf report: Fix condition in sort__sym_cmp() [ Upstream commit cb39d05e67dc24985ff9f5150e71040fa4d60ab8 ] It's expected that both hist entries are in the same hists when comparing two. But the current code in the function checks one without dso sort key and other with the key. This would make the condition true in any case. I guess the intention of the original commit was to add '!' for the right side too. But as it should be the same, let's just remove it. Fixes: 69849fc5d2119 ("perf hists: Move sort__has_dso into struct perf_hpp_list") Reviewed-by: Kan Liang Signed-off-by: Namhyung Kim Link: https://lore.kernel.org/r/20240621170528.608772-2-namhyung@kernel.org Signed-off-by: Sasha Levin --- tools/perf/util/sort.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/tools/perf/util/sort.c b/tools/perf/util/sort.c index 42806102010b..bbebb1e51b88 100644 --- a/tools/perf/util/sort.c +++ b/tools/perf/util/sort.c @@ -272,7 +272,7 @@ sort__sym_cmp(struct hist_entry *left, struct hist_entry *right) * comparing symbol address alone is not enough since it's a * relative address within a dso. */ - if (!hists__has(left->hists, dso) || hists__has(right->hists, dso)) { + if (!hists__has(left->hists, dso)) { ret = sort__dso_cmp(left, right); if (ret != 0) return ret; From cd105977b1f8abfd988a8f22ead7f4c5ce25f3b4 Mon Sep 17 00:00:00 2001 From: Lucas Stach Date: Fri, 21 Jun 2024 19:11:06 +0200 Subject: [PATCH 076/342] drm/etnaviv: fix DMA direction handling for cached RW buffers [ Upstream commit 58979ad6330a70450ed78837be3095107d022ea9 ] The dma sync operation needs to be done with DMA_BIDIRECTIONAL when the BO is prepared for both read and write operations. Fixes: a8c21a5451d8 ("drm/etnaviv: add initial etnaviv DRM driver") Signed-off-by: Lucas Stach Reviewed-by: Philipp Zabel Reviewed-by: Christian Gmeiner Signed-off-by: Sasha Levin --- drivers/gpu/drm/etnaviv/etnaviv_gem.c | 6 ++++-- 1 file changed, 4 insertions(+), 2 deletions(-) diff --git a/drivers/gpu/drm/etnaviv/etnaviv_gem.c b/drivers/gpu/drm/etnaviv/etnaviv_gem.c index 424474041c94..aa372982335e 100644 --- a/drivers/gpu/drm/etnaviv/etnaviv_gem.c +++ b/drivers/gpu/drm/etnaviv/etnaviv_gem.c @@ -364,9 +364,11 @@ static void *etnaviv_gem_vmap_impl(struct etnaviv_gem_object *obj) static inline enum dma_data_direction etnaviv_op_to_dma_dir(u32 op) { - if (op & ETNA_PREP_READ) + op &= ETNA_PREP_READ | ETNA_PREP_WRITE; + + if (op == ETNA_PREP_READ) return DMA_FROM_DEVICE; - else if (op & ETNA_PREP_WRITE) + else if (op == ETNA_PREP_WRITE) return DMA_TO_DEVICE; else return DMA_BIDIRECTIONAL; From 4e87f592a46bb804d8f833da6ce702ae4b55053f Mon Sep 17 00:00:00 2001 From: Chen Ni Date: Fri, 21 Jun 2024 15:10:31 +0800 Subject: [PATCH 077/342] drm/qxl: Add check for drm_cvt_mode [ Upstream commit 7bd09a2db0f617377027a2bb0b9179e6959edff3 ] Add check for the return value of drm_cvt_mode() and return the error if it fails in order to avoid NULL pointer dereference. Fixes: 1b043677d4be ("drm/qxl: add qxl_add_mode helper function") Signed-off-by: Chen Ni Reviewed-by: Heng Qi Signed-off-by: Maxime Ripard Link: https://patchwork.freedesktop.org/patch/msgid/20240621071031.1987974-1-nichen@iscas.ac.cn Signed-off-by: Sasha Levin --- drivers/gpu/drm/qxl/qxl_display.c | 3 +++ 1 file changed, 3 insertions(+) diff --git a/drivers/gpu/drm/qxl/qxl_display.c b/drivers/gpu/drm/qxl/qxl_display.c index f22a1b776f4b..3ffa721d777b 100644 --- a/drivers/gpu/drm/qxl/qxl_display.c +++ b/drivers/gpu/drm/qxl/qxl_display.c @@ -232,6 +232,9 @@ static int qxl_add_mode(struct drm_connector *connector, return 0; mode = drm_cvt_mode(dev, width, height, 60, false, false, false); + if (!mode) + return 0; + if (preferred) mode->type |= DRM_MODE_TYPE_PREFERRED; mode->hdisplay = width; From c9106ad5ea2af671e584b94bbe6bd282c54b9ba5 Mon Sep 17 00:00:00 2001 From: Luca Ceresoli Date: Tue, 25 Jun 2024 10:34:38 +0200 Subject: [PATCH 078/342] Revert "leds: led-core: Fix refcount leak in of_led_get()" MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit [ Upstream commit 940b27161afc6ec53fc66245a4fb3518394cdc92 ] This reverts commit da1afe8e6099980fe1e2fd7436dca284af9d3f29. Commit 699a8c7c4bd3 ("leds: Add of_led_get() and led_put()"), introduced in 5.5, added of_led_get() and led_put() but missed a put_device() in led_put(), thus creating a leak in case the consumer device is removed. Arguably device removal was not very popular, so this went apparently unnoticed until 2022. In January 2023 two different patches got merged to fix the same bug: - commit da1afe8e6099 ("leds: led-core: Fix refcount leak in of_led_get()") - commit 445110941eb9 ("leds: led-class: Add missing put_device() to led_put()") They fix the bug in two different ways, which creates no patch conflicts, and both were merged in v6.2. The result is that now there is one more put_device() than get_device()s, instead of one less. Arguably device removal is not very popular yet, so this apparently hasn't been noticed as well up to now. But it blew up here while I'm working with device tree overlay insertion and removal. The symptom is an apparently unrelated list of oopses on device removal, with reasons: kernfs: can not remove 'uevent', no directory kernfs: can not remove 'brightness', no directory kernfs: can not remove 'max_brightness', no directory ... Here sysfs fails removing attribute files, which is because the device name changed and so the sysfs path. This is because the device name string got corrupted, which is because it got freed too early and its memory reused. Different symptoms could appear in different use cases. Fix by removing one of the two fixes. The choice was to remove commit da1afe8e6099 because: * it is calling put_device() inside of_led_get() just after getting the device, thus it is basically not refcounting the LED device at all during its entire lifetime * it does not add a corresponding put_device() in led_get(), so it fixes only the OF case The other fix (445110941eb9) is adding the put_device() in led_put() so it covers the entire lifetime, and it works even in the non-DT case. Fixes: da1afe8e6099 ("leds: led-core: Fix refcount leak in of_led_get()") Co-developed-by: Hervé Codina Signed-off-by: Hervé Codina Signed-off-by: Luca Ceresoli Link: https://lore.kernel.org/r/20240625-led-class-device-leak-v2-1-75fdccf47421@bootlin.com Signed-off-by: Lee Jones Signed-off-by: Sasha Levin --- drivers/leds/led-class.c | 1 - 1 file changed, 1 deletion(-) diff --git a/drivers/leds/led-class.c b/drivers/leds/led-class.c index fcb9eee3b609..e28a4bb71603 100644 --- a/drivers/leds/led-class.c +++ b/drivers/leds/led-class.c @@ -236,7 +236,6 @@ struct led_classdev *of_led_get(struct device_node *np, int index) led_dev = class_find_device_by_of_node(leds_class, led_node); of_node_put(led_node); - put_device(led_dev); if (!led_dev) return ERR_PTR(-EPROBE_DEFER); From 5ed0496e383cb6de120e56991385dce70bbb87c1 Mon Sep 17 00:00:00 2001 From: "Luis Henriques (SUSE)" Date: Wed, 15 May 2024 09:28:57 +0100 Subject: [PATCH 079/342] ext4: fix infinite loop when replaying fast_commit [ Upstream commit 907c3fe532253a6ef4eb9c4d67efb71fab58c706 ] When doing fast_commit replay an infinite loop may occur due to an uninitialized extent_status struct. ext4_ext_determine_insert_hole() does not detect the replay and calls ext4_es_find_extent_range(), which will return immediately without initializing the 'es' variable. Because 'es' contains garbage, an integer overflow may happen causing an infinite loop in this function, easily reproducible using fstest generic/039. This commit fixes this issue by unconditionally initializing the structure in function ext4_es_find_extent_range(). Thanks to Zhang Yi, for figuring out the real problem! Fixes: 8016e29f4362 ("ext4: fast commit recovery path") Signed-off-by: Luis Henriques (SUSE) Reviewed-by: Zhang Yi Link: https://patch.msgid.link/20240515082857.32730-1-luis.henriques@linux.dev Signed-off-by: Theodore Ts'o Signed-off-by: Sasha Levin --- fs/ext4/extents_status.c | 2 ++ 1 file changed, 2 insertions(+) diff --git a/fs/ext4/extents_status.c b/fs/ext4/extents_status.c index f37e62546745..be3b3ccbf70b 100644 --- a/fs/ext4/extents_status.c +++ b/fs/ext4/extents_status.c @@ -312,6 +312,8 @@ void ext4_es_find_extent_range(struct inode *inode, ext4_lblk_t lblk, ext4_lblk_t end, struct extent_status *es) { + es->es_lblk = es->es_len = es->es_pblk = 0; + if (EXT4_SB(inode->i_sb)->s_mount_state & EXT4_FC_REPLAY) return; From 72ac78ec1a354d8e2fa27db7729449e04cf19b57 Mon Sep 17 00:00:00 2001 From: Dikshita Agarwal Date: Wed, 10 Jan 2024 11:42:14 +0530 Subject: [PATCH 080/342] media: venus: flush all buffers in output plane streamoff [ Upstream commit e750a4b1224142bd8dd057b0d5adf8a5608b7e77 ] For scenarios, when source change is followed by VIDIOC_STREAMOFF on output plane, driver should discard any queued OUTPUT buffers, which are not decoded or dequeued. Flush with HFI_FLUSH_INPUT does not have any actual impact. So, fix it, by invoking HFI_FLUSH_ALL, which will flush all queued buffers. Fixes: 85872f861d4c ("media: venus: Mark last capture buffer") Signed-off-by: Dikshita Agarwal Tested-by: Nathan Hebert Reviewed-by: Bryan O'Donoghue Signed-off-by: Stanimir Varbanov Signed-off-by: Hans Verkuil Signed-off-by: Sasha Levin --- drivers/media/platform/qcom/venus/vdec.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/drivers/media/platform/qcom/venus/vdec.c b/drivers/media/platform/qcom/venus/vdec.c index c437a929a545..b6edfa812bb7 100644 --- a/drivers/media/platform/qcom/venus/vdec.c +++ b/drivers/media/platform/qcom/venus/vdec.c @@ -1142,7 +1142,7 @@ static int vdec_stop_output(struct venus_inst *inst) break; case VENUS_DEC_STATE_INIT: case VENUS_DEC_STATE_CAPTURE_SETUP: - ret = hfi_session_flush(inst, HFI_FLUSH_INPUT, true); + ret = hfi_session_flush(inst, HFI_FLUSH_ALL, true); break; default: break; From cf9141d2f778246c7d26801d93b779a6e34b73ff Mon Sep 17 00:00:00 2001 From: Javier Carrasco Date: Wed, 26 Jun 2024 21:37:03 +0200 Subject: [PATCH 081/342] mfd: omap-usb-tll: Use struct_size to allocate tll [ Upstream commit 40176714c818b0b6a2ca8213cdb7654fbd49b742 ] Commit 16c2004d9e4d ("mfd: omap-usb-tll: Allocate driver data at once") changed the memory allocation of 'tll' to consolidate it into a single allocation, introducing an incorrect size calculation. In particular, the allocation for the array of pointers was converted into a single-pointer allocation. The memory allocation used to occur in two steps: tll = devm_kzalloc(dev, sizeof(struct usbtll_omap), GFP_KERNEL); tll->ch_clk = devm_kzalloc(dev, sizeof(struct clk *) * tll->nch, GFP_KERNEL); And it turned that into the following allocation: tll = devm_kzalloc(dev, sizeof(*tll) + sizeof(tll->ch_clk[nch]), GFP_KERNEL); sizeof(tll->ch_clk[nch]) returns the size of a single pointer instead of the expected nch pointers. This bug went unnoticed because the allocation size was small enough to fit within the minimum size of a memory allocation for this particular case [1]. The complete allocation can still be done at once with the struct_size macro, which comes in handy for structures with a trailing flexible array. Fix the memory allocation to obtain the original size again. Link: https://lore.kernel.org/all/202406261121.2FFD65647@keescook/ [1] Fixes: 16c2004d9e4d ("mfd: omap-usb-tll: Allocate driver data at once") Reviewed-by: Kees Cook Signed-off-by: Javier Carrasco Fixes: commit 16c2004d9e4d ("mfd: omap-usb-tll: Allocate driver data at once") Link: https://lore.kernel.org/r/20240626-omap-usb-tll-counted_by-v2-1-4bedf20d1b51@gmail.com Signed-off-by: Lee Jones Signed-off-by: Sasha Levin --- drivers/mfd/omap-usb-tll.c | 3 +-- 1 file changed, 1 insertion(+), 2 deletions(-) diff --git a/drivers/mfd/omap-usb-tll.c b/drivers/mfd/omap-usb-tll.c index 16fad79c73f1..99ca0dfa127b 100644 --- a/drivers/mfd/omap-usb-tll.c +++ b/drivers/mfd/omap-usb-tll.c @@ -237,8 +237,7 @@ static int usbtll_omap_probe(struct platform_device *pdev) break; } - tll = devm_kzalloc(dev, sizeof(*tll) + sizeof(tll->ch_clk[nch]), - GFP_KERNEL); + tll = devm_kzalloc(dev, struct_size(tll, ch_clk, nch), GFP_KERNEL); if (!tll) { pm_runtime_put_sync(dev); pm_runtime_disable(dev); From 974294806bafacae0c312263f1f2a19f4840aae3 Mon Sep 17 00:00:00 2001 From: Chuck Lever Date: Mon, 19 Apr 2021 14:03:00 -0400 Subject: [PATCH 082/342] xprtrdma: Rename frwr_release_mr() [ Upstream commit f912af77e2c1ba25bd40534668b10da5b20f686a ] Clean up: To be consistent with other functions in this source file, follow the naming convention of putting the object being acted upon before the action itself. Signed-off-by: Chuck Lever Signed-off-by: Trond Myklebust Stable-dep-of: acd9f2dd23c6 ("xprtrdma: Fix rpcrdma_reqs_reset()") Signed-off-by: Sasha Levin --- net/sunrpc/xprtrdma/frwr_ops.c | 6 +++--- net/sunrpc/xprtrdma/verbs.c | 4 ++-- net/sunrpc/xprtrdma/xprt_rdma.h | 2 +- 3 files changed, 6 insertions(+), 6 deletions(-) diff --git a/net/sunrpc/xprtrdma/frwr_ops.c b/net/sunrpc/xprtrdma/frwr_ops.c index bf3627dce552..177099f6ae18 100644 --- a/net/sunrpc/xprtrdma/frwr_ops.c +++ b/net/sunrpc/xprtrdma/frwr_ops.c @@ -50,11 +50,11 @@ #endif /** - * frwr_release_mr - Destroy one MR + * frwr_mr_release - Destroy one MR * @mr: MR allocated by frwr_mr_init * */ -void frwr_release_mr(struct rpcrdma_mr *mr) +void frwr_mr_release(struct rpcrdma_mr *mr) { int rc; @@ -83,7 +83,7 @@ static void frwr_mr_recycle(struct rpcrdma_mr *mr) r_xprt->rx_stats.mrs_recycled++; spin_unlock(&r_xprt->rx_buf.rb_lock); - frwr_release_mr(mr); + frwr_mr_release(mr); } /* frwr_reset - Place MRs back on the free list diff --git a/net/sunrpc/xprtrdma/verbs.c b/net/sunrpc/xprtrdma/verbs.c index 9e9df38b29f7..167f0d99b858 100644 --- a/net/sunrpc/xprtrdma/verbs.c +++ b/net/sunrpc/xprtrdma/verbs.c @@ -1100,7 +1100,7 @@ void rpcrdma_req_destroy(struct rpcrdma_req *req) list_del(&mr->mr_all); spin_unlock(&buf->rb_lock); - frwr_release_mr(mr); + frwr_mr_release(mr); } rpcrdma_regbuf_free(req->rl_recvbuf); @@ -1131,7 +1131,7 @@ static void rpcrdma_mrs_destroy(struct rpcrdma_xprt *r_xprt) list_del(&mr->mr_all); spin_unlock(&buf->rb_lock); - frwr_release_mr(mr); + frwr_mr_release(mr); spin_lock(&buf->rb_lock); } diff --git a/net/sunrpc/xprtrdma/xprt_rdma.h b/net/sunrpc/xprtrdma/xprt_rdma.h index 702f0344523c..73c8ab89456b 100644 --- a/net/sunrpc/xprtrdma/xprt_rdma.h +++ b/net/sunrpc/xprtrdma/xprt_rdma.h @@ -520,7 +520,7 @@ rpcrdma_data_dir(bool writing) void frwr_reset(struct rpcrdma_req *req); int frwr_query_device(struct rpcrdma_ep *ep, const struct ib_device *device); int frwr_mr_init(struct rpcrdma_xprt *r_xprt, struct rpcrdma_mr *mr); -void frwr_release_mr(struct rpcrdma_mr *mr); +void frwr_mr_release(struct rpcrdma_mr *mr); struct rpcrdma_mr_seg *frwr_map(struct rpcrdma_xprt *r_xprt, struct rpcrdma_mr_seg *seg, int nsegs, bool writing, __be32 xid, From 84edcf61bd41cad91e9b3e464a43f2e4cac04e02 Mon Sep 17 00:00:00 2001 From: Chuck Lever Date: Tue, 4 Jun 2024 15:45:23 -0400 Subject: [PATCH 083/342] xprtrdma: Fix rpcrdma_reqs_reset() [ Upstream commit acd9f2dd23c632568156217aac7a05f5a0313152 ] Avoid FastReg operations getting MW_BIND_ERR after a reconnect. rpcrdma_reqs_reset() is called on transport tear-down to get each rpcrdma_req back into a clean state. MRs on req->rl_registered are waiting for a FastReg, are already registered, or are waiting for invalidation. If the transport is being torn down when reqs_reset() is called, the matching LocalInv might never be posted. That leaves these MR registered /and/ on req->rl_free_mrs, where they can be re-used for the next connection. Since xprtrdma does not keep specific track of the MR state, it's not possible to know what state these MRs are in, so the only safe thing to do is release them immediately. Fixes: 5de55ce951a1 ("xprtrdma: Release in-flight MRs on disconnect") Signed-off-by: Chuck Lever Signed-off-by: Anna Schumaker Signed-off-by: Sasha Levin --- net/sunrpc/xprtrdma/frwr_ops.c | 3 ++- net/sunrpc/xprtrdma/verbs.c | 16 +++++++++++++++- 2 files changed, 17 insertions(+), 2 deletions(-) diff --git a/net/sunrpc/xprtrdma/frwr_ops.c b/net/sunrpc/xprtrdma/frwr_ops.c index 177099f6ae18..2035d748d923 100644 --- a/net/sunrpc/xprtrdma/frwr_ops.c +++ b/net/sunrpc/xprtrdma/frwr_ops.c @@ -86,7 +86,8 @@ static void frwr_mr_recycle(struct rpcrdma_mr *mr) frwr_mr_release(mr); } -/* frwr_reset - Place MRs back on the free list +/** + * frwr_reset - Place MRs back on @req's free list * @req: request to reset * * Used after a failed marshal. For FRWR, this means the MRs diff --git a/net/sunrpc/xprtrdma/verbs.c b/net/sunrpc/xprtrdma/verbs.c index 167f0d99b858..9262c94a13c1 100644 --- a/net/sunrpc/xprtrdma/verbs.c +++ b/net/sunrpc/xprtrdma/verbs.c @@ -932,6 +932,8 @@ static int rpcrdma_reqs_setup(struct rpcrdma_xprt *r_xprt) static void rpcrdma_req_reset(struct rpcrdma_req *req) { + struct rpcrdma_mr *mr; + /* Credits are valid for only one connection */ req->rl_slot.rq_cong = 0; @@ -941,7 +943,19 @@ static void rpcrdma_req_reset(struct rpcrdma_req *req) rpcrdma_regbuf_dma_unmap(req->rl_sendbuf); rpcrdma_regbuf_dma_unmap(req->rl_recvbuf); - frwr_reset(req); + /* The verbs consumer can't know the state of an MR on the + * req->rl_registered list unless a successful completion + * has occurred, so they cannot be re-used. + */ + while ((mr = rpcrdma_mr_pop(&req->rl_registered))) { + struct rpcrdma_buffer *buf = &mr->mr_xprt->rx_buf; + + spin_lock(&buf->rb_lock); + list_del(&mr->mr_all); + spin_unlock(&buf->rb_lock); + + frwr_mr_release(mr); + } } /* ASSUMPTION: the rb_allreqs list is stable for the duration, From 91c22df7013847f3f88d1e3f79637c4074548c90 Mon Sep 17 00:00:00 2001 From: NeilBrown Date: Wed, 19 Jun 2024 11:05:13 +1000 Subject: [PATCH 084/342] SUNRPC: avoid soft lockup when transmitting UDP to reachable server. [ Upstream commit 6258cf25d5e3155c3219ab5a79b970eef7996356 ] Prior to the commit identified below, call_transmit_status() would handle -EPERM and other errors related to an unreachable server by falling through to call_status() which added a 3-second delay and handled the failure as a timeout. Since that commit, call_transmit_status() falls through to handle_bind(). For UDP this moves straight on to handle_connect() and handle_transmit() so we immediately retransmit - and likely get the same error. This results in an indefinite loop in __rpc_execute() which triggers a soft-lockup warning. For the errors that indicate an unreachable server, call_transmit_status() should fall back to call_status() as it did before. This cannot cause the thundering herd that the previous patch was avoiding, as the call_status() will insert a delay. Fixes: ed7dc973bd91 ("SUNRPC: Prevent thundering herd when the socket is not connected") Signed-off-by: NeilBrown Signed-off-by: Anna Schumaker Signed-off-by: Sasha Levin --- net/sunrpc/clnt.c | 3 ++- 1 file changed, 2 insertions(+), 1 deletion(-) diff --git a/net/sunrpc/clnt.c b/net/sunrpc/clnt.c index 196a3b11d150..86397f9c4bc8 100644 --- a/net/sunrpc/clnt.c +++ b/net/sunrpc/clnt.c @@ -2188,12 +2188,13 @@ call_transmit_status(struct rpc_task *task) task->tk_action = call_transmit; task->tk_status = 0; break; - case -ECONNREFUSED: case -EHOSTDOWN: case -ENETDOWN: case -EHOSTUNREACH: case -ENETUNREACH: case -EPERM: + break; + case -ECONNREFUSED: if (RPC_IS_SOFTCONN(task)) { if (!task->tk_msg.rpc_proc->p_proc) trace_xprt_ping(task->tk_xprt, From 3d096f2a99eb88148ef84ee0370699054a87f7d6 Mon Sep 17 00:00:00 2001 From: Jan Kara Date: Thu, 13 Jun 2024 17:02:34 +0200 Subject: [PATCH 085/342] ext4: avoid writing unitialized memory to disk in EA inodes [ Upstream commit 65121eff3e4c8c90f8126debf3c369228691c591 ] If the extended attribute size is not a multiple of block size, the last block in the EA inode will have uninitialized tail which will get written to disk. We will never expose the data to userspace but still this is not a good practice so just zero out the tail of the block as it isn't going to cause a noticeable performance overhead. Fixes: e50e5129f384 ("ext4: xattr-in-inode support") Reported-by: syzbot+9c1fe13fcb51574b249b@syzkaller.appspotmail.com Reported-by: Hugh Dickins Signed-off-by: Jan Kara Link: https://patch.msgid.link/20240613150234.25176-1-jack@suse.cz Signed-off-by: Theodore Ts'o Signed-off-by: Sasha Levin --- fs/ext4/xattr.c | 6 ++++++ 1 file changed, 6 insertions(+) diff --git a/fs/ext4/xattr.c b/fs/ext4/xattr.c index 2dcb7d2bb85e..b91a1d1099d5 100644 --- a/fs/ext4/xattr.c +++ b/fs/ext4/xattr.c @@ -1377,6 +1377,12 @@ static int ext4_xattr_inode_write(handle_t *handle, struct inode *ea_inode, goto out; memcpy(bh->b_data, buf, csize); + /* + * Zero out block tail to avoid writing uninitialized memory + * to disk. + */ + if (csize < blocksize) + memset(bh->b_data + csize, 0, blocksize - csize); set_buffer_uptodate(bh); ext4_handle_dirty_metadata(handle, ea_inode, bh); From 8f1dc3f33f2aee4186ca54a161f4eb2fca9280a4 Mon Sep 17 00:00:00 2001 From: Andreas Larsson Date: Wed, 10 Jul 2024 11:41:53 +0200 Subject: [PATCH 086/342] sparc64: Fix incorrect function signature and add prototype for prom_cif_init MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit [ Upstream commit a6c3ea1ec96307dbfbb2f16d96c674c5cc80f445 ] Remove the unused cif_stack argument and add a protype in oplib_64.h Commit ef3e035c3a9b ("sparc64: Fix register corruption in top-most kernel stack frame during boot.") removed the cif_stack argument to prom_cif init in the declaration at the caller site and the usage of it within prom_cif_init, but not in the function signature of the function itself. This also fixes the following warning: arch/sparc/prom/p1275.c:52:6: warning: no previous prototype for ‘prom_cif_init’ Fixes: ef3e035c3a9b ("sparc64: Fix register corruption in top-most kernel stack frame during boot.") Link: https://lore.kernel.org/r/20240710094155.458731-3-andreas@gaisler.com Signed-off-by: Andreas Larsson Signed-off-by: Sasha Levin --- arch/sparc/include/asm/oplib_64.h | 1 + arch/sparc/prom/init_64.c | 3 --- arch/sparc/prom/p1275.c | 2 +- 3 files changed, 2 insertions(+), 4 deletions(-) diff --git a/arch/sparc/include/asm/oplib_64.h b/arch/sparc/include/asm/oplib_64.h index a67abebd4359..1b86d02a8455 100644 --- a/arch/sparc/include/asm/oplib_64.h +++ b/arch/sparc/include/asm/oplib_64.h @@ -247,6 +247,7 @@ void prom_sun4v_guest_soft_state(void); int prom_ihandle2path(int handle, char *buffer, int bufsize); /* Client interface level routines. */ +void prom_cif_init(void *cif_handler); void p1275_cmd_direct(unsigned long *); #endif /* !(__SPARC64_OPLIB_H) */ diff --git a/arch/sparc/prom/init_64.c b/arch/sparc/prom/init_64.c index 103aa9104318..f7b8a1a865b8 100644 --- a/arch/sparc/prom/init_64.c +++ b/arch/sparc/prom/init_64.c @@ -26,9 +26,6 @@ phandle prom_chosen_node; * routines in the prom library. * It gets passed the pointer to the PROM vector. */ - -extern void prom_cif_init(void *); - void __init prom_init(void *cif_handler) { phandle node; diff --git a/arch/sparc/prom/p1275.c b/arch/sparc/prom/p1275.c index 889aa602f8d8..51c3f984bbf7 100644 --- a/arch/sparc/prom/p1275.c +++ b/arch/sparc/prom/p1275.c @@ -49,7 +49,7 @@ void p1275_cmd_direct(unsigned long *args) local_irq_restore(flags); } -void prom_cif_init(void *cif_handler, void *cif_stack) +void prom_cif_init(void *cif_handler) { p1275buf.prom_cif_handler = (void (*)(long *))cif_handler; } From 8105318210a41a219584227bf9bf35e99043f5cd Mon Sep 17 00:00:00 2001 From: Benjamin Coddington Date: Thu, 11 Jul 2024 13:21:00 -0400 Subject: [PATCH 087/342] SUNRPC: Fixup gss_status tracepoint error output [ Upstream commit b9fae9f06d84ffab0f3f9118f3a96bbcdc528bf6 ] The GSS routine errors are values, not flags. Fixes: 0c77668ddb4e ("SUNRPC: Introduce trace points in rpc_auth_gss.ko") Signed-off-by: Benjamin Coddington Reviewed-by: Chuck Lever Signed-off-by: Anna Schumaker Signed-off-by: Sasha Levin --- include/trace/events/rpcgss.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/include/trace/events/rpcgss.h b/include/trace/events/rpcgss.h index ffdbe6f85da8..9c8cb69c7911 100644 --- a/include/trace/events/rpcgss.h +++ b/include/trace/events/rpcgss.h @@ -52,7 +52,7 @@ TRACE_DEFINE_ENUM(GSS_S_UNSEQ_TOKEN); TRACE_DEFINE_ENUM(GSS_S_GAP_TOKEN); #define show_gss_status(x) \ - __print_flags(x, "|", \ + __print_symbolic(x, \ { GSS_S_BAD_MECH, "GSS_S_BAD_MECH" }, \ { GSS_S_BAD_NAME, "GSS_S_BAD_NAME" }, \ { GSS_S_BAD_NAMETYPE, "GSS_S_BAD_NAMETYPE" }, \ From 3d1c4bf57db8ac67755fec7763cf456614e95c50 Mon Sep 17 00:00:00 2001 From: =?UTF-8?q?Ilpo=20J=C3=A4rvinen?= Date: Tue, 7 May 2024 13:25:16 +0300 Subject: [PATCH 088/342] PCI: Fix resource double counting on remove & rescan MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit [ Upstream commit 903534fa7d30214d8ba840ab1cd9e917e0c88e41 ] pbus_size_mem() keeps the size of the optional resources in children_add_size. When calculating the PCI bridge window size, calculate_memsize() lower bounds size by old_size before adding children_add_size and performing the window size alignment. This results in double counting for the resources in children_add_size because old_size may be based on the previous size of the bridge window after it has already included children_add_size (that is, size1 in pbus_size_mem() from an earlier invocation of that function). As a result, on repeated remove of the bus & rescan cycles the resource size keeps increasing when children_add_size is non-zero as can be seen from this extract: iomem0: 23fffd00000-23fffdfffff : PCI Bus 0000:03 # 1MiB iomem1: 20000000000-200001fffff : PCI Bus 0000:03 # 2MiB iomem2: 20000000000-200002fffff : PCI Bus 0000:03 # 3MiB iomem3: 20000000000-200003fffff : PCI Bus 0000:03 # 4MiB iomem4: 20000000000-200004fffff : PCI Bus 0000:03 # 5MiB Solve the double counting by moving old_size check later in calculate_memsize() so that children_add_size is already accounted for. After the patch, the bridge window retains its size as expected: iomem0: 23fffd00000-23fffdfffff : PCI Bus 0000:03 # 1MiB iomem1: 20000000000-200000fffff : PCI Bus 0000:03 # 1MiB iomem2: 20000000000-200000fffff : PCI Bus 0000:03 # 1MiB Fixes: a4ac9fea016f ("PCI : Calculate right add_size") Link: https://lore.kernel.org/r/20240507102523.57320-2-ilpo.jarvinen@linux.intel.com Tested-by: Lidong Wang Signed-off-by: Ilpo Järvinen Signed-off-by: Bjorn Helgaas Reviewed-by: Mika Westerberg Signed-off-by: Sasha Levin --- drivers/pci/setup-bus.c | 6 ++---- 1 file changed, 2 insertions(+), 4 deletions(-) diff --git a/drivers/pci/setup-bus.c b/drivers/pci/setup-bus.c index 16d291e10627..a159bfdfa251 100644 --- a/drivers/pci/setup-bus.c +++ b/drivers/pci/setup-bus.c @@ -824,11 +824,9 @@ static resource_size_t calculate_memsize(resource_size_t size, size = min_size; if (old_size == 1) old_size = 0; - if (size < old_size) - size = old_size; - size = ALIGN(max(size, add_size) + children_add_size, align); - return size; + size = max(size, add_size) + children_add_size; + return ALIGN(max(size, old_size), align); } resource_size_t __weak pcibios_window_alignment(struct pci_bus *bus, From 2be7e24056d7863340e4bf07d53e533700ee1a78 Mon Sep 17 00:00:00 2001 From: James Clark Date: Wed, 29 May 2024 14:36:26 +0100 Subject: [PATCH 089/342] coresight: Fix ref leak when of_coresight_parse_endpoint() fails [ Upstream commit 7fcb9cb2fe47294e16067c3cfd25332c8662a115 ] of_graph_get_next_endpoint() releases the reference to the previous endpoint on each iteration, but when parsing fails the loop exits early meaning the last reference is never dropped. Fix it by dropping the refcount in the exit condition. Fixes: d375b356e687 ("coresight: Fix support for sparsely populated ports") Signed-off-by: James Clark Reported-by: Laurent Pinchart Reviewed-by: Laurent Pinchart Signed-off-by: Suzuki K Poulose Link: https://lore.kernel.org/r/20240529133626.90080-1-james.clark@arm.com Signed-off-by: Sasha Levin --- drivers/hwtracing/coresight/coresight-platform.c | 4 +++- 1 file changed, 3 insertions(+), 1 deletion(-) diff --git a/drivers/hwtracing/coresight/coresight-platform.c b/drivers/hwtracing/coresight/coresight-platform.c index c594f45319fc..dfb8022c4da1 100644 --- a/drivers/hwtracing/coresight/coresight-platform.c +++ b/drivers/hwtracing/coresight/coresight-platform.c @@ -323,8 +323,10 @@ static int of_get_coresight_platform_data(struct device *dev, continue; ret = of_coresight_parse_endpoint(dev, ep, pdata); - if (ret) + if (ret) { + of_node_put(ep); return ret; + } } return 0; From 26b6512d5d209ce688a7b285bb04e596524f784f Mon Sep 17 00:00:00 2001 From: Andrei Lalaev Date: Mon, 17 Jun 2024 20:30:18 +0200 Subject: [PATCH 090/342] Input: qt1050 - handle CHIP_ID reading error [ Upstream commit 866a5c7e2781cf1b019072288f1f5c64186dcb63 ] If the device is missing, we get the following error: qt1050 3-0041: ID -1340767592 not supported Let's handle this situation and print more informative error when reading of CHIP_ID fails: qt1050 3-0041: Failed to read chip ID: -6 Fixes: cbebf5addec1 ("Input: qt1050 - add Microchip AT42QT1050 support") Signed-off-by: Andrei Lalaev Reviewed-by: Marco Felsch Link: https://lore.kernel.org/r/20240617183018.916234-1-andrey.lalaev@gmail.com Signed-off-by: Dmitry Torokhov Signed-off-by: Sasha Levin --- drivers/input/keyboard/qt1050.c | 7 ++++++- 1 file changed, 6 insertions(+), 1 deletion(-) diff --git a/drivers/input/keyboard/qt1050.c b/drivers/input/keyboard/qt1050.c index 403060d05c3b..7193a4198e21 100644 --- a/drivers/input/keyboard/qt1050.c +++ b/drivers/input/keyboard/qt1050.c @@ -226,7 +226,12 @@ static bool qt1050_identify(struct qt1050_priv *ts) int err; /* Read Chip ID */ - regmap_read(ts->regmap, QT1050_CHIP_ID, &val); + err = regmap_read(ts->regmap, QT1050_CHIP_ID, &val); + if (err) { + dev_err(&ts->client->dev, "Failed to read chip ID: %d\n", err); + return false; + } + if (val != QT1050_CHIP_ID_VER) { dev_err(&ts->client->dev, "ID %d not supported\n", val); return false; From 6bf3cf61f35a67c5a18ba12fab0400f429c06f7b Mon Sep 17 00:00:00 2001 From: Leon Romanovsky Date: Sun, 16 Jun 2024 19:16:33 +0300 Subject: [PATCH 091/342] RDMA/mlx4: Fix truncated output warning in mad.c MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit [ Upstream commit 0d2e6992fc956e3308cd5376c18567def4cb3967 ] Increase size of the name array to avoid truncated output warning. drivers/infiniband/hw/mlx4/mad.c: In function ‘mlx4_ib_alloc_demux_ctx’: drivers/infiniband/hw/mlx4/mad.c:2197:47: error: ‘%d’ directive output may be truncated writing between 1 and 11 bytes into a region of size 4 [-Werror=format-truncation=] 2197 | snprintf(name, sizeof(name), "mlx4_ibt%d", port); | ^~ drivers/infiniband/hw/mlx4/mad.c:2197:38: note: directive argument in the range [-2147483645, 2147483647] 2197 | snprintf(name, sizeof(name), "mlx4_ibt%d", port); | ^~~~~~~~~~~~ drivers/infiniband/hw/mlx4/mad.c:2197:9: note: ‘snprintf’ output between 10 and 20 bytes into a destination of size 12 2197 | snprintf(name, sizeof(name), "mlx4_ibt%d", port); | ^~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~ drivers/infiniband/hw/mlx4/mad.c:2205:48: error: ‘%d’ directive output may be truncated writing between 1 and 11 bytes into a region of size 3 [-Werror=format-truncation=] 2205 | snprintf(name, sizeof(name), "mlx4_ibwi%d", port); | ^~ drivers/infiniband/hw/mlx4/mad.c:2205:38: note: directive argument in the range [-2147483645, 2147483647] 2205 | snprintf(name, sizeof(name), "mlx4_ibwi%d", port); | ^~~~~~~~~~~~~ drivers/infiniband/hw/mlx4/mad.c:2205:9: note: ‘snprintf’ output between 11 and 21 bytes into a destination of size 12 2205 | snprintf(name, sizeof(name), "mlx4_ibwi%d", port); | ^~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~ drivers/infiniband/hw/mlx4/mad.c:2213:48: error: ‘%d’ directive output may be truncated writing between 1 and 11 bytes into a region of size 3 [-Werror=format-truncation=] 2213 | snprintf(name, sizeof(name), "mlx4_ibud%d", port); | ^~ drivers/infiniband/hw/mlx4/mad.c:2213:38: note: directive argument in the range [-2147483645, 2147483647] 2213 | snprintf(name, sizeof(name), "mlx4_ibud%d", port); | ^~~~~~~~~~~~~ drivers/infiniband/hw/mlx4/mad.c:2213:9: note: ‘snprintf’ output between 11 and 21 bytes into a destination of size 12 2213 | snprintf(name, sizeof(name), "mlx4_ibud%d", port); | ^~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~ cc1: all warnings being treated as errors make[6]: *** [scripts/Makefile.build:244: drivers/infiniband/hw/mlx4/mad.o] Error 1 Fixes: fc06573dfaf8 ("IB/mlx4: Initialize SR-IOV IB support for slaves in master context") Link: https://lore.kernel.org/r/f3798b3ce9a410257d7e1ec7c9e285f1352e256a.1718554569.git.leon@kernel.org Signed-off-by: Leon Romanovsky Signed-off-by: Jason Gunthorpe Signed-off-by: Sasha Levin --- drivers/infiniband/hw/mlx4/mad.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/drivers/infiniband/hw/mlx4/mad.c b/drivers/infiniband/hw/mlx4/mad.c index 8bd16474708f..44ea25e82549 100644 --- a/drivers/infiniband/hw/mlx4/mad.c +++ b/drivers/infiniband/hw/mlx4/mad.c @@ -2155,7 +2155,7 @@ static int mlx4_ib_alloc_demux_ctx(struct mlx4_ib_dev *dev, struct mlx4_ib_demux_ctx *ctx, int port) { - char name[12]; + char name[21]; int ret = 0; int i; From 506e71b0e10d7ca9e8f5ee9e64d1afa9decc8f72 Mon Sep 17 00:00:00 2001 From: Leon Romanovsky Date: Sun, 16 Jun 2024 19:17:30 +0300 Subject: [PATCH 092/342] RDMA/mlx4: Fix truncated output warning in alias_GUID.c MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit [ Upstream commit 5953e0647cec703ef436ead37fed48943507b433 ] drivers/infiniband/hw/mlx4/alias_GUID.c: In function ‘mlx4_ib_init_alias_guid_service’: drivers/infiniband/hw/mlx4/alias_GUID.c:878:74: error: ‘%d’ directive output may be truncated writing between 1 and 11 bytes into a region of size 5 [-Werror=format-truncation=] 878 | snprintf(alias_wq_name, sizeof alias_wq_name, "alias_guid%d", i); | ^~ drivers/infiniband/hw/mlx4/alias_GUID.c:878:63: note: directive argument in the range [-2147483641, 2147483646] 878 | snprintf(alias_wq_name, sizeof alias_wq_name, "alias_guid%d", i); | ^~~~~~~~~~~~~~ drivers/infiniband/hw/mlx4/alias_GUID.c:878:17: note: ‘snprintf’ output between 12 and 22 bytes into a destination of size 15 878 | snprintf(alias_wq_name, sizeof alias_wq_name, "alias_guid%d", i); | ^~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~ cc1: all warnings being treated as errors Fixes: a0c64a17aba8 ("mlx4: Add alias_guid mechanism") Link: https://lore.kernel.org/r/1951c9500109ca7e36dcd523f8a5f2d0d2a608d1.1718554641.git.leon@kernel.org Signed-off-by: Leon Romanovsky Signed-off-by: Jason Gunthorpe Signed-off-by: Sasha Levin --- drivers/infiniband/hw/mlx4/alias_GUID.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/drivers/infiniband/hw/mlx4/alias_GUID.c b/drivers/infiniband/hw/mlx4/alias_GUID.c index cca414ecfcd5..05420e189ca9 100644 --- a/drivers/infiniband/hw/mlx4/alias_GUID.c +++ b/drivers/infiniband/hw/mlx4/alias_GUID.c @@ -832,7 +832,7 @@ void mlx4_ib_destroy_alias_guid_service(struct mlx4_ib_dev *dev) int mlx4_ib_init_alias_guid_service(struct mlx4_ib_dev *dev) { - char alias_wq_name[15]; + char alias_wq_name[22]; int ret = 0; int i, j; union ib_gid gid; From 771f129bed4d88545418c0ecb5134302a9c8d278 Mon Sep 17 00:00:00 2001 From: Honggang LI Date: Mon, 24 Jun 2024 10:03:48 +0800 Subject: [PATCH 093/342] RDMA/rxe: Don't set BTH_ACK_MASK for UC or UD QPs [ Upstream commit 4adcaf969d77d3d3aa3871bbadc196258a38aec6 ] BTH_ACK_MASK bit is used to indicate that an acknowledge (for this packet) should be scheduled by the responder. Both UC and UD QPs are unacknowledged, so don't set BTH_ACK_MASK for UC or UD QPs. Fixes: 8700e3e7c485 ("Soft RoCE driver") Signed-off-by: Honggang LI Link: https://lore.kernel.org/r/20240624020348.494338-1-honggangli@163.com Reviewed-by: Zhu Yanjun Signed-off-by: Leon Romanovsky Signed-off-by: Jason Gunthorpe Signed-off-by: Sasha Levin --- drivers/infiniband/sw/rxe/rxe_req.c | 7 ++++--- 1 file changed, 4 insertions(+), 3 deletions(-) diff --git a/drivers/infiniband/sw/rxe/rxe_req.c b/drivers/infiniband/sw/rxe/rxe_req.c index 69238f856c67..a034aa8fc5ca 100644 --- a/drivers/infiniband/sw/rxe/rxe_req.c +++ b/drivers/infiniband/sw/rxe/rxe_req.c @@ -362,7 +362,7 @@ static struct sk_buff *init_req_packet(struct rxe_qp *qp, int solicited; u16 pkey; u32 qp_num; - int ack_req; + int ack_req = 0; /* length from start of bth to end of icrc */ paylen = rxe_opcode[opcode].length + payload + pad + RXE_ICRC_SIZE; @@ -396,8 +396,9 @@ static struct sk_buff *init_req_packet(struct rxe_qp *qp, qp_num = (pkt->mask & RXE_DETH_MASK) ? ibwr->wr.ud.remote_qpn : qp->attr.dest_qp_num; - ack_req = ((pkt->mask & RXE_END_MASK) || - (qp->req.noack_pkts++ > RXE_MAX_PKT_PER_ACK)); + if (qp_type(qp) != IB_QPT_UD && qp_type(qp) != IB_QPT_UC) + ack_req = ((pkt->mask & RXE_END_MASK) || + (qp->req.noack_pkts++ > RXE_MAX_PKT_PER_ACK)); if (ack_req) qp->req.noack_pkts = 0; From ab2114f6ffc8290c4f5d37531d440c3751b51ead Mon Sep 17 00:00:00 2001 From: Chen Ni Date: Fri, 28 Jun 2024 16:05:34 +0800 Subject: [PATCH 094/342] ASoC: max98088: Check for clk_prepare_enable() error [ Upstream commit 1a70579723fde3624a72dfea6e79e55be6e36659 ] clk_prepare_enable() may fail, so we should better check its return value and propagate it in the case of error. Fixes: 62a7fc32a628 ("ASoC: max98088: Add master clock handling") Signed-off-by: Chen Ni Link: https://patch.msgid.link/20240628080534.843815-1-nichen@iscas.ac.cn Signed-off-by: Mark Brown Signed-off-by: Sasha Levin --- sound/soc/codecs/max98088.c | 10 +++++++--- 1 file changed, 7 insertions(+), 3 deletions(-) diff --git a/sound/soc/codecs/max98088.c b/sound/soc/codecs/max98088.c index f8e49e45ce33..a71fbfddc29a 100644 --- a/sound/soc/codecs/max98088.c +++ b/sound/soc/codecs/max98088.c @@ -1319,6 +1319,7 @@ static int max98088_set_bias_level(struct snd_soc_component *component, enum snd_soc_bias_level level) { struct max98088_priv *max98088 = snd_soc_component_get_drvdata(component); + int ret; switch (level) { case SND_SOC_BIAS_ON: @@ -1334,10 +1335,13 @@ static int max98088_set_bias_level(struct snd_soc_component *component, */ if (!IS_ERR(max98088->mclk)) { if (snd_soc_component_get_bias_level(component) == - SND_SOC_BIAS_ON) + SND_SOC_BIAS_ON) { clk_disable_unprepare(max98088->mclk); - else - clk_prepare_enable(max98088->mclk); + } else { + ret = clk_prepare_enable(max98088->mclk); + if (ret) + return ret; + } } break; From 695d70c60bdbab9d5aa35cc9b933ff11c1d391a6 Mon Sep 17 00:00:00 2001 From: Arnd Bergmann Date: Wed, 29 May 2024 11:50:39 +0200 Subject: [PATCH 095/342] mtd: make mtd_test.c a separate module [ Upstream commit a5cf054d325e6f362e82fe6d124a1871a4af8174 ] This file gets linked into nine different modules, which causes a warning: scripts/Makefile.build:236: drivers/mtd/tests/Makefile: mtd_test.o is added to multiple modules: mtd_nandbiterrs mtd_oobtest mtd_pagetest mtd_readtest mtd_speedtest mtd_stresstest mtd_subpagetest mtd_torturetest Make it a separate module instead. Fixes: a995c792280d ("mtd: tests: rename sources in order to link a helper object") Signed-off-by: Arnd Bergmann Signed-off-by: Miquel Raynal Link: https://lore.kernel.org/linux-mtd/20240529095049.1915393-1-arnd@kernel.org Signed-off-by: Sasha Levin --- drivers/mtd/tests/Makefile | 34 +++++++++++++++++----------------- drivers/mtd/tests/mtd_test.c | 9 +++++++++ 2 files changed, 26 insertions(+), 17 deletions(-) diff --git a/drivers/mtd/tests/Makefile b/drivers/mtd/tests/Makefile index 5de0378f90db..7dae831ee8b6 100644 --- a/drivers/mtd/tests/Makefile +++ b/drivers/mtd/tests/Makefile @@ -1,19 +1,19 @@ # SPDX-License-Identifier: GPL-2.0 -obj-$(CONFIG_MTD_TESTS) += mtd_oobtest.o -obj-$(CONFIG_MTD_TESTS) += mtd_pagetest.o -obj-$(CONFIG_MTD_TESTS) += mtd_readtest.o -obj-$(CONFIG_MTD_TESTS) += mtd_speedtest.o -obj-$(CONFIG_MTD_TESTS) += mtd_stresstest.o -obj-$(CONFIG_MTD_TESTS) += mtd_subpagetest.o -obj-$(CONFIG_MTD_TESTS) += mtd_torturetest.o -obj-$(CONFIG_MTD_TESTS) += mtd_nandecctest.o -obj-$(CONFIG_MTD_TESTS) += mtd_nandbiterrs.o +obj-$(CONFIG_MTD_TESTS) += mtd_oobtest.o mtd_test.o +obj-$(CONFIG_MTD_TESTS) += mtd_pagetest.o mtd_test.o +obj-$(CONFIG_MTD_TESTS) += mtd_readtest.o mtd_test.o +obj-$(CONFIG_MTD_TESTS) += mtd_speedtest.o mtd_test.o +obj-$(CONFIG_MTD_TESTS) += mtd_stresstest.o mtd_test.o +obj-$(CONFIG_MTD_TESTS) += mtd_subpagetest.o mtd_test.o +obj-$(CONFIG_MTD_TESTS) += mtd_torturetest.o mtd_test.o +obj-$(CONFIG_MTD_TESTS) += mtd_nandecctest.o mtd_test.o +obj-$(CONFIG_MTD_TESTS) += mtd_nandbiterrs.o mtd_test.o -mtd_oobtest-objs := oobtest.o mtd_test.o -mtd_pagetest-objs := pagetest.o mtd_test.o -mtd_readtest-objs := readtest.o mtd_test.o -mtd_speedtest-objs := speedtest.o mtd_test.o -mtd_stresstest-objs := stresstest.o mtd_test.o -mtd_subpagetest-objs := subpagetest.o mtd_test.o -mtd_torturetest-objs := torturetest.o mtd_test.o -mtd_nandbiterrs-objs := nandbiterrs.o mtd_test.o +mtd_oobtest-objs := oobtest.o +mtd_pagetest-objs := pagetest.o +mtd_readtest-objs := readtest.o +mtd_speedtest-objs := speedtest.o +mtd_stresstest-objs := stresstest.o +mtd_subpagetest-objs := subpagetest.o +mtd_torturetest-objs := torturetest.o +mtd_nandbiterrs-objs := nandbiterrs.o diff --git a/drivers/mtd/tests/mtd_test.c b/drivers/mtd/tests/mtd_test.c index c84250beffdc..f391e0300cdc 100644 --- a/drivers/mtd/tests/mtd_test.c +++ b/drivers/mtd/tests/mtd_test.c @@ -25,6 +25,7 @@ int mtdtest_erase_eraseblock(struct mtd_info *mtd, unsigned int ebnum) return 0; } +EXPORT_SYMBOL_GPL(mtdtest_erase_eraseblock); static int is_block_bad(struct mtd_info *mtd, unsigned int ebnum) { @@ -57,6 +58,7 @@ int mtdtest_scan_for_bad_eraseblocks(struct mtd_info *mtd, unsigned char *bbt, return 0; } +EXPORT_SYMBOL_GPL(mtdtest_scan_for_bad_eraseblocks); int mtdtest_erase_good_eraseblocks(struct mtd_info *mtd, unsigned char *bbt, unsigned int eb, int ebcnt) @@ -75,6 +77,7 @@ int mtdtest_erase_good_eraseblocks(struct mtd_info *mtd, unsigned char *bbt, return 0; } +EXPORT_SYMBOL_GPL(mtdtest_erase_good_eraseblocks); int mtdtest_read(struct mtd_info *mtd, loff_t addr, size_t size, void *buf) { @@ -92,6 +95,7 @@ int mtdtest_read(struct mtd_info *mtd, loff_t addr, size_t size, void *buf) return err; } +EXPORT_SYMBOL_GPL(mtdtest_read); int mtdtest_write(struct mtd_info *mtd, loff_t addr, size_t size, const void *buf) @@ -107,3 +111,8 @@ int mtdtest_write(struct mtd_info *mtd, loff_t addr, size_t size, return err; } +EXPORT_SYMBOL_GPL(mtdtest_write); + +MODULE_LICENSE("GPL"); +MODULE_DESCRIPTION("MTD function test helpers"); +MODULE_AUTHOR("Akinobu Mita"); From 37a484f771edf278bf32d477c55cb5e9e71f74a6 Mon Sep 17 00:00:00 2001 From: Leon Romanovsky Date: Mon, 24 Jun 2024 16:24:32 +0300 Subject: [PATCH 096/342] RDMA/device: Return error earlier if port in not valid [ Upstream commit 917918f57a7b139c043e78c502876f2c286f4f0a ] There is no need to allocate port data if port provided is not valid. Fixes: c2261dd76b54 ("RDMA/device: Add ib_device_set_netdev() as an alternative to get_netdev") Link: https://lore.kernel.org/r/022047a8b16988fc88d4426da50bf60a4833311b.1719235449.git.leon@kernel.org Signed-off-by: Leon Romanovsky Signed-off-by: Sasha Levin --- drivers/infiniband/core/device.c | 6 +++--- 1 file changed, 3 insertions(+), 3 deletions(-) diff --git a/drivers/infiniband/core/device.c b/drivers/infiniband/core/device.c index 94c3bad72cc5..3848fe0449a4 100644 --- a/drivers/infiniband/core/device.c +++ b/drivers/infiniband/core/device.c @@ -2106,6 +2106,9 @@ int ib_device_set_netdev(struct ib_device *ib_dev, struct net_device *ndev, unsigned long flags; int ret; + if (!rdma_is_port_valid(ib_dev, port)) + return -EINVAL; + /* * Drivers wish to call this before ib_register_driver, so we have to * setup the port data early. @@ -2114,9 +2117,6 @@ int ib_device_set_netdev(struct ib_device *ib_dev, struct net_device *ndev, if (ret) return ret; - if (!rdma_is_port_valid(ib_dev, port)) - return -EINVAL; - pdata = &ib_dev->port_data[port]; spin_lock_irqsave(&pdata->netdev_lock, flags); old_ndev = rcu_dereference_protected( From 3009d371a2ef90a7bf2afca2863112b328c1a42e Mon Sep 17 00:00:00 2001 From: Dmitry Torokhov Date: Thu, 6 Jun 2024 23:02:48 -0700 Subject: [PATCH 097/342] Input: elan_i2c - do not leave interrupt disabled on suspend failure [ Upstream commit 5f82c1e04721e7cd98e604eb4e58f0724d8e5a65 ] Make sure interrupts are not left disabled when we fail to suspend the touch controller. Fixes: 6696777c6506 ("Input: add driver for Elan I2C/SMbus touchpad") Link: https://lore.kernel.org/r/ZmKiiL-1wzKrhqBj@google.com Signed-off-by: Dmitry Torokhov Signed-off-by: Sasha Levin --- drivers/input/mouse/elan_i2c_core.c | 2 ++ 1 file changed, 2 insertions(+) diff --git a/drivers/input/mouse/elan_i2c_core.c b/drivers/input/mouse/elan_i2c_core.c index 6f59c8b245f2..14c2c66414f4 100644 --- a/drivers/input/mouse/elan_i2c_core.c +++ b/drivers/input/mouse/elan_i2c_core.c @@ -1340,6 +1340,8 @@ static int __maybe_unused elan_suspend(struct device *dev) } err: + if (ret) + enable_irq(client->irq); mutex_unlock(&data->sysfs_mutex); return ret; } From 38a7e4b8bfeaf3a00b5e2c42e4861a37734d2f4f Mon Sep 17 00:00:00 2001 From: Dominique Martinet Date: Fri, 5 Jul 2024 16:48:30 +0900 Subject: [PATCH 098/342] MIPS: Octeron: remove source file executable bit [ Upstream commit 89c7f5078935872cf47a713a645affb5037be694 ] This does not matter the least, but there is no other .[ch] file in the repo that is executable, so clean this up. Fixes: 29b83a64df3b ("MIPS: Octeon: Add PCIe link status check") Signed-off-by: Dominique Martinet Signed-off-by: Thomas Bogendoerfer Signed-off-by: Sasha Levin --- arch/mips/pci/pcie-octeon.c | 0 1 file changed, 0 insertions(+), 0 deletions(-) mode change 100755 => 100644 arch/mips/pci/pcie-octeon.c diff --git a/arch/mips/pci/pcie-octeon.c b/arch/mips/pci/pcie-octeon.c old mode 100755 new mode 100644 From 445ffbccd05a30cf25b0b84399b1777aed794ef6 Mon Sep 17 00:00:00 2001 From: Michael Ellerman Date: Thu, 9 May 2024 22:12:47 +1000 Subject: [PATCH 099/342] powerpc/xmon: Fix disassembly CPU feature checks [ Upstream commit 14196e47c5ffe32af7ed5a51c9e421c5ea5bccce ] In the xmon disassembly code there are several CPU feature checks to determine what dialects should be passed to the disassembler. The dialect controls which instructions the disassembler will recognise. Unfortunately the checks are incorrect, because instead of passing a single CPU feature they are passing a mask of feature bits. For example the code: if (cpu_has_feature(CPU_FTRS_POWER5)) dialect |= PPC_OPCODE_POWER5; Is trying to check if the system is running on a Power5 CPU. But CPU_FTRS_POWER5 is a mask of *all* the feature bits that are enabled on a Power5. In practice the test will always return true for any 64-bit CPU, because at least one bit in the mask will be present in the CPU_FTRS_ALWAYS mask. Similarly for all the other checks against CPU_FTRS_xx masks. Rather than trying to match the disassembly behaviour exactly to the current CPU, just differentiate between 32-bit and 64-bit, and Altivec, VSX and HTM. That will cause some instructions to be shown in disassembly even on a CPU that doesn't support them, but that's OK, objdump -d output has the same behaviour, and if anything it's less confusing than some instructions not being disassembled. Fixes: 897f112bb42e ("[POWERPC] Import updated version of ppc disassembly code for xmon") Signed-off-by: Michael Ellerman Link: https://msgid.link/20240509121248.270878-2-mpe@ellerman.id.au Signed-off-by: Sasha Levin --- arch/powerpc/xmon/ppc-dis.c | 33 +++++++++++---------------------- 1 file changed, 11 insertions(+), 22 deletions(-) diff --git a/arch/powerpc/xmon/ppc-dis.c b/arch/powerpc/xmon/ppc-dis.c index 75fa98221d48..af105e1bc3fc 100644 --- a/arch/powerpc/xmon/ppc-dis.c +++ b/arch/powerpc/xmon/ppc-dis.c @@ -122,32 +122,21 @@ int print_insn_powerpc (unsigned long insn, unsigned long memaddr) bool insn_is_short; ppc_cpu_t dialect; - dialect = PPC_OPCODE_PPC | PPC_OPCODE_COMMON - | PPC_OPCODE_64 | PPC_OPCODE_POWER4 | PPC_OPCODE_ALTIVEC; + dialect = PPC_OPCODE_PPC | PPC_OPCODE_COMMON; - if (cpu_has_feature(CPU_FTRS_POWER5)) - dialect |= PPC_OPCODE_POWER5; + if (IS_ENABLED(CONFIG_PPC64)) + dialect |= PPC_OPCODE_64 | PPC_OPCODE_POWER4 | PPC_OPCODE_CELL | + PPC_OPCODE_POWER5 | PPC_OPCODE_POWER6 | PPC_OPCODE_POWER7 | PPC_OPCODE_POWER8 | + PPC_OPCODE_POWER9; - if (cpu_has_feature(CPU_FTRS_CELL)) - dialect |= (PPC_OPCODE_CELL | PPC_OPCODE_ALTIVEC); + if (cpu_has_feature(CPU_FTR_TM)) + dialect |= PPC_OPCODE_HTM; - if (cpu_has_feature(CPU_FTRS_POWER6)) - dialect |= (PPC_OPCODE_POWER5 | PPC_OPCODE_POWER6 | PPC_OPCODE_ALTIVEC); + if (cpu_has_feature(CPU_FTR_ALTIVEC)) + dialect |= PPC_OPCODE_ALTIVEC | PPC_OPCODE_ALTIVEC2; - if (cpu_has_feature(CPU_FTRS_POWER7)) - dialect |= (PPC_OPCODE_POWER5 | PPC_OPCODE_POWER6 | PPC_OPCODE_POWER7 - | PPC_OPCODE_ALTIVEC | PPC_OPCODE_VSX); - - if (cpu_has_feature(CPU_FTRS_POWER8)) - dialect |= (PPC_OPCODE_POWER5 | PPC_OPCODE_POWER6 | PPC_OPCODE_POWER7 - | PPC_OPCODE_POWER8 | PPC_OPCODE_HTM - | PPC_OPCODE_ALTIVEC | PPC_OPCODE_ALTIVEC2 | PPC_OPCODE_VSX); - - if (cpu_has_feature(CPU_FTRS_POWER9)) - dialect |= (PPC_OPCODE_POWER5 | PPC_OPCODE_POWER6 | PPC_OPCODE_POWER7 - | PPC_OPCODE_POWER8 | PPC_OPCODE_POWER9 | PPC_OPCODE_HTM - | PPC_OPCODE_ALTIVEC | PPC_OPCODE_ALTIVEC2 - | PPC_OPCODE_VSX | PPC_OPCODE_VSX3); + if (cpu_has_feature(CPU_FTR_VSX)) + dialect |= PPC_OPCODE_VSX | PPC_OPCODE_VSX3; /* Get the major opcode of the insn. */ opcode = NULL; From 29723ad94817da1a8b9ff607cbc254c3ebe8caaa Mon Sep 17 00:00:00 2001 From: Nick Bowler Date: Wed, 10 Jul 2024 23:54:17 -0400 Subject: [PATCH 100/342] macintosh/therm_windtunnel: fix module unload. [ Upstream commit fd748e177194ebcbbaf98df75152a30e08230cc6 ] The of_device_unregister call in therm_windtunnel's module_exit procedure does not fully reverse the effects of of_platform_device_create in the module_init prodedure. Once you unload this module, it is impossible to load it ever again since only the first of_platform_device_create call on the fan node succeeds. This driver predates first git commit, and it turns out back then of_platform_device_create worked differently than it does today. So this is actually an old regression. The appropriate function to undo of_platform_device_create now appears to be of_platform_device_destroy, and switching to use this makes it possible to unload and load the module as expected. Signed-off-by: Nick Bowler Fixes: c6e126de43e7 ("of: Keep track of populated platform devices") Signed-off-by: Michael Ellerman Link: https://msgid.link/20240711035428.16696-1-nbowler@draconx.ca Signed-off-by: Sasha Levin --- drivers/macintosh/therm_windtunnel.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/drivers/macintosh/therm_windtunnel.c b/drivers/macintosh/therm_windtunnel.c index f55f6adf5e5f..49805eb4d145 100644 --- a/drivers/macintosh/therm_windtunnel.c +++ b/drivers/macintosh/therm_windtunnel.c @@ -549,7 +549,7 @@ g4fan_exit( void ) platform_driver_unregister( &therm_of_driver ); if( x.of_dev ) - of_device_unregister( x.of_dev ); + of_platform_device_destroy(&x.of_dev->dev, NULL); } module_init(g4fan_init); From edc2dee07ab4ae2188b9780c453a64032162a5a0 Mon Sep 17 00:00:00 2001 From: Chengchang Tang Date: Wed, 10 Jul 2024 21:37:01 +0800 Subject: [PATCH 101/342] RDMA/hns: Fix missing pagesize and alignment check in FRMR [ Upstream commit d387d4b54eb84208bd4ca13572e106851d0a0819 ] The offset requires 128B alignment and the page size ranges from 4K to 128M. Fixes: 68a997c5d28c ("RDMA/hns: Add FRMR support for hip08") Signed-off-by: Chengchang Tang Signed-off-by: Junxian Huang Link: https://lore.kernel.org/r/20240710133705.896445-5-huangjunxian6@hisilicon.com Signed-off-by: Leon Romanovsky Signed-off-by: Sasha Levin --- drivers/infiniband/hw/hns/hns_roce_device.h | 4 ++++ drivers/infiniband/hw/hns/hns_roce_mr.c | 5 +++++ 2 files changed, 9 insertions(+) diff --git a/drivers/infiniband/hw/hns/hns_roce_device.h b/drivers/infiniband/hw/hns/hns_roce_device.h index fe54e09eeccd..72a41f34ecfd 100644 --- a/drivers/infiniband/hw/hns/hns_roce_device.h +++ b/drivers/infiniband/hw/hns/hns_roce_device.h @@ -98,6 +98,7 @@ #define MR_TYPE_DMA 0x03 #define HNS_ROCE_FRMR_MAX_PA 512 +#define HNS_ROCE_FRMR_ALIGN_SIZE 128 #define PKEY_ID 0xffff #define GUID_LEN 8 @@ -267,6 +268,9 @@ enum { #define HNS_HW_PAGE_SHIFT 12 #define HNS_HW_PAGE_SIZE (1 << HNS_HW_PAGE_SHIFT) +#define HNS_HW_MAX_PAGE_SHIFT 27 +#define HNS_HW_MAX_PAGE_SIZE (1 << HNS_HW_MAX_PAGE_SHIFT) + struct hns_roce_uar { u64 pfn; unsigned long index; diff --git a/drivers/infiniband/hw/hns/hns_roce_mr.c b/drivers/infiniband/hw/hns/hns_roce_mr.c index c038ed7d9496..7e93c9b4a33f 100644 --- a/drivers/infiniband/hw/hns/hns_roce_mr.c +++ b/drivers/infiniband/hw/hns/hns_roce_mr.c @@ -486,6 +486,11 @@ int hns_roce_map_mr_sg(struct ib_mr *ibmr, struct scatterlist *sg, int sg_nents, struct hns_roce_mtr *mtr = &mr->pbl_mtr; int ret, sg_num = 0; + if (!IS_ALIGNED(*sg_offset, HNS_ROCE_FRMR_ALIGN_SIZE) || + ibmr->page_size < HNS_HW_PAGE_SIZE || + ibmr->page_size > HNS_HW_MAX_PAGE_SIZE) + return sg_num; + mr->npages = 0; mr->page_list = kvcalloc(mr->pbl_mtr.hem_cfg.buf_pg_count, sizeof(dma_addr_t), GFP_KERNEL); From 9118c408ee0956b996cd48a44c586d2b50e17990 Mon Sep 17 00:00:00 2001 From: Jack Wang Date: Wed, 10 Jul 2024 14:21:02 +0200 Subject: [PATCH 102/342] bnxt_re: Fix imm_data endianness [ Upstream commit 95b087f87b780daafad1dbb2c84e81b729d5d33f ] When map a device between servers with MLX and BCM RoCE nics, RTRS server complain about unknown imm type, and can't map the device, After more debug, it seems bnxt_re wrongly handle the imm_data, this patch fixed the compat issue with MLX for us. In off list discussion, Selvin confirmed HW is working in little endian format and all data needs to be converted to LE while providing. This patch fix the endianness for imm_data Fixes: 1ac5a4047975 ("RDMA/bnxt_re: Add bnxt_re RoCE driver") Signed-off-by: Jack Wang Link: https://lore.kernel.org/r/20240710122102.37569-1-jinpu.wang@ionos.com Acked-by: Selvin Xavier Signed-off-by: Leon Romanovsky Signed-off-by: Sasha Levin --- drivers/infiniband/hw/bnxt_re/ib_verbs.c | 8 ++++---- drivers/infiniband/hw/bnxt_re/qplib_fp.h | 6 +++--- 2 files changed, 7 insertions(+), 7 deletions(-) diff --git a/drivers/infiniband/hw/bnxt_re/ib_verbs.c b/drivers/infiniband/hw/bnxt_re/ib_verbs.c index a0d7777acb6d..f16e0b2c7895 100644 --- a/drivers/infiniband/hw/bnxt_re/ib_verbs.c +++ b/drivers/infiniband/hw/bnxt_re/ib_verbs.c @@ -2357,7 +2357,7 @@ static int bnxt_re_build_send_wqe(struct bnxt_re_qp *qp, break; case IB_WR_SEND_WITH_IMM: wqe->type = BNXT_QPLIB_SWQE_TYPE_SEND_WITH_IMM; - wqe->send.imm_data = wr->ex.imm_data; + wqe->send.imm_data = be32_to_cpu(wr->ex.imm_data); break; case IB_WR_SEND_WITH_INV: wqe->type = BNXT_QPLIB_SWQE_TYPE_SEND_WITH_INV; @@ -2387,7 +2387,7 @@ static int bnxt_re_build_rdma_wqe(const struct ib_send_wr *wr, break; case IB_WR_RDMA_WRITE_WITH_IMM: wqe->type = BNXT_QPLIB_SWQE_TYPE_RDMA_WRITE_WITH_IMM; - wqe->rdma.imm_data = wr->ex.imm_data; + wqe->rdma.imm_data = be32_to_cpu(wr->ex.imm_data); break; case IB_WR_RDMA_READ: wqe->type = BNXT_QPLIB_SWQE_TYPE_RDMA_READ; @@ -3334,7 +3334,7 @@ static void bnxt_re_process_res_shadow_qp_wc(struct bnxt_re_qp *gsi_sqp, wc->byte_len = orig_cqe->length; wc->qp = &gsi_qp->ib_qp; - wc->ex.imm_data = orig_cqe->immdata; + wc->ex.imm_data = cpu_to_be32(le32_to_cpu(orig_cqe->immdata)); wc->src_qp = orig_cqe->src_qp; memcpy(wc->smac, orig_cqe->smac, ETH_ALEN); if (bnxt_re_is_vlan_pkt(orig_cqe, &vlan_id, &sl)) { @@ -3474,7 +3474,7 @@ int bnxt_re_poll_cq(struct ib_cq *ib_cq, int num_entries, struct ib_wc *wc) continue; } wc->qp = &qp->ib_qp; - wc->ex.imm_data = cqe->immdata; + wc->ex.imm_data = cpu_to_be32(le32_to_cpu(cqe->immdata)); wc->src_qp = cqe->src_qp; memcpy(wc->smac, cqe->smac, ETH_ALEN); wc->port_num = 1; diff --git a/drivers/infiniband/hw/bnxt_re/qplib_fp.h b/drivers/infiniband/hw/bnxt_re/qplib_fp.h index 667f93d90045..f112f013df7d 100644 --- a/drivers/infiniband/hw/bnxt_re/qplib_fp.h +++ b/drivers/infiniband/hw/bnxt_re/qplib_fp.h @@ -162,7 +162,7 @@ struct bnxt_qplib_swqe { /* Send, with imm, inval key */ struct { union { - __be32 imm_data; + u32 imm_data; u32 inv_key; }; u32 q_key; @@ -180,7 +180,7 @@ struct bnxt_qplib_swqe { /* RDMA write, with imm, read */ struct { union { - __be32 imm_data; + u32 imm_data; u32 inv_key; }; u64 remote_va; @@ -372,7 +372,7 @@ struct bnxt_qplib_cqe { u16 cfa_meta; u64 wr_id; union { - __be32 immdata; + __le32 immdata; u32 invrkey; }; u64 qp_handle; From eb4ca1a97e08ff5b920664ba292e576257e2d184 Mon Sep 17 00:00:00 2001 From: Pablo Neira Ayuso Date: Sat, 13 Jul 2024 16:47:38 +0200 Subject: [PATCH 103/342] netfilter: ctnetlink: use helper function to calculate expect ID [ Upstream commit 782161895eb4ac45cf7cfa8db375bd4766cb8299 ] Delete expectation path is missing a call to the nf_expect_get_id() helper function to calculate the expectation ID, otherwise LSB of the expectation object address is leaked to userspace. Fixes: 3c79107631db ("netfilter: ctnetlink: don't use conntrack/expect object addresses as id") Reported-by: zdi-disclosures@trendmicro.com Signed-off-by: Pablo Neira Ayuso Signed-off-by: Sasha Levin --- net/netfilter/nf_conntrack_netlink.c | 3 ++- 1 file changed, 2 insertions(+), 1 deletion(-) diff --git a/net/netfilter/nf_conntrack_netlink.c b/net/netfilter/nf_conntrack_netlink.c index ceb7c988edef..b55e87143c2c 100644 --- a/net/netfilter/nf_conntrack_netlink.c +++ b/net/netfilter/nf_conntrack_netlink.c @@ -3413,7 +3413,8 @@ static int ctnetlink_del_expect(struct net *net, struct sock *ctnl, if (cda[CTA_EXPECT_ID]) { __be32 id = nla_get_be32(cda[CTA_EXPECT_ID]); - if (ntohl(id) != (u32)(unsigned long)exp) { + + if (id != nf_expect_get_id(exp)) { nf_ct_expect_put(exp); return -ENOENT; } From ef6af29942616dcfb342d9c61909c3d2f5efd5ce Mon Sep 17 00:00:00 2001 From: Martin Willi Date: Wed, 17 Jul 2024 11:08:19 +0200 Subject: [PATCH 104/342] net: dsa: mv88e6xxx: Limit chip-wide frame size config to CPU ports [ Upstream commit 66b6095c264e1b4e0a441c6329861806504e06c6 ] Marvell chips not supporting per-port jumbo frame size configurations use a chip-wide frame size configuration. In the commit referenced with the Fixes tag, the setting is applied just for the last port changing its MTU. While configuring CPU ports accounts for tagger overhead, user ports do not. When setting the MTU for a user port, the chip-wide setting is reduced to not include the tagger overhead, resulting in an potentially insufficient maximum frame size for the CPU port. Specifically, sending full-size frames from the CPU port on a MV88E6097 having a user port MTU of 1500 bytes results in dropped frames. As, by design, the CPU port MTU is adjusted for any user port change, apply the chip-wide setting only for CPU ports. Fixes: 1baf0fac10fb ("net: dsa: mv88e6xxx: Use chip-wide max frame size for MTU") Suggested-by: Vladimir Oltean Signed-off-by: Martin Willi Reviewed-by: Vladimir Oltean Signed-off-by: Paolo Abeni Signed-off-by: Sasha Levin --- drivers/net/dsa/mv88e6xxx/chip.c | 3 ++- 1 file changed, 2 insertions(+), 1 deletion(-) diff --git a/drivers/net/dsa/mv88e6xxx/chip.c b/drivers/net/dsa/mv88e6xxx/chip.c index 6a1ae774cfe9..c7f93329ae75 100644 --- a/drivers/net/dsa/mv88e6xxx/chip.c +++ b/drivers/net/dsa/mv88e6xxx/chip.c @@ -2774,7 +2774,8 @@ static int mv88e6xxx_change_mtu(struct dsa_switch *ds, int port, int new_mtu) mv88e6xxx_reg_lock(chip); if (chip->info->ops->port_set_jumbo_size) ret = chip->info->ops->port_set_jumbo_size(chip, port, new_mtu); - else if (chip->info->ops->set_max_frame_size) + else if (chip->info->ops->set_max_frame_size && + dsa_is_cpu_port(ds, port)) ret = chip->info->ops->set_max_frame_size(chip, new_mtu); mv88e6xxx_reg_unlock(chip); From 01c0341e9846fb6422e2a6a088b868aa5525ccd5 Mon Sep 17 00:00:00 2001 From: Martin Willi Date: Wed, 17 Jul 2024 11:08:20 +0200 Subject: [PATCH 105/342] net: dsa: b53: Limit chip-wide jumbo frame config to CPU ports [ Upstream commit c5118072e228e7e4385fc5ac46b2e31cf6c4f2d3 ] Broadcom switches supported by the b53 driver use a chip-wide jumbo frame configuration. In the commit referenced with the Fixes tag, the setting is applied just for the last port changing its MTU. While configuring CPU ports accounts for tagger overhead, user ports do not. When setting the MTU for a user port, the chip-wide setting is reduced to not include the tagger overhead, resulting in an potentially insufficient chip-wide maximum frame size for the CPU port. As, by design, the CPU port MTU is adjusted for any user port change, apply the chip-wide setting only for CPU ports. This aligns the driver to the behavior of other switch drivers. Fixes: 6ae5834b983a ("net: dsa: b53: add MTU configuration support") Suggested-by: Vladimir Oltean Signed-off-by: Martin Willi Reviewed-by: Vladimir Oltean Signed-off-by: Paolo Abeni Signed-off-by: Sasha Levin --- drivers/net/dsa/b53/b53_common.c | 3 +++ 1 file changed, 3 insertions(+) diff --git a/drivers/net/dsa/b53/b53_common.c b/drivers/net/dsa/b53/b53_common.c index d3b37cebcfde..2bf07a398054 100644 --- a/drivers/net/dsa/b53/b53_common.c +++ b/drivers/net/dsa/b53/b53_common.c @@ -2180,6 +2180,9 @@ static int b53_change_mtu(struct dsa_switch *ds, int port, int mtu) if (is5325(dev) || is5365(dev)) return -EOPNOTSUPP; + if (!dsa_is_cpu_port(ds, port)) + return 0; + enable_jumbo = (mtu >= JMS_MIN_SIZE); allow_10_100 = (dev->chip_id == BCM583XX_DEVICE_ID); From 53f2d5bce177245b18d09d25dd803e34b6810e6f Mon Sep 17 00:00:00 2001 From: Dmitry Yashin Date: Wed, 15 May 2024 17:16:32 +0500 Subject: [PATCH 106/342] pinctrl: rockchip: update rk3308 iomux routes [ Upstream commit a8f2548548584549ea29d43431781d67c4afa42b ] Some of the rk3308 iomux routes in rk3308_mux_route_data belong to the rk3308b SoC. Remove them and correct i2c3 routes. Fixes: 7825aeb7b208 ("pinctrl: rockchip: add rk3308 SoC support") Signed-off-by: Dmitry Yashin Reviewed-by: Heiko Stuebner Link: https://lore.kernel.org/r/20240515121634.23945-2-dmt.yashin@gmail.com Signed-off-by: Linus Walleij Signed-off-by: Sasha Levin --- drivers/pinctrl/pinctrl-rockchip.c | 17 ++--------------- 1 file changed, 2 insertions(+), 15 deletions(-) diff --git a/drivers/pinctrl/pinctrl-rockchip.c b/drivers/pinctrl/pinctrl-rockchip.c index 02b41f1bafe7..e0f22ce219ee 100644 --- a/drivers/pinctrl/pinctrl-rockchip.c +++ b/drivers/pinctrl/pinctrl-rockchip.c @@ -720,9 +720,8 @@ static struct rockchip_mux_route_data rk3308_mux_route_data[] = { RK_MUXROUTE_SAME(0, RK_PC3, 1, 0x314, BIT(16 + 0) | BIT(0)), /* rtc_clk */ RK_MUXROUTE_SAME(1, RK_PC6, 2, 0x314, BIT(16 + 2) | BIT(16 + 3)), /* uart2_rxm0 */ RK_MUXROUTE_SAME(4, RK_PD2, 2, 0x314, BIT(16 + 2) | BIT(16 + 3) | BIT(2)), /* uart2_rxm1 */ - RK_MUXROUTE_SAME(0, RK_PB7, 2, 0x608, BIT(16 + 8) | BIT(16 + 9)), /* i2c3_sdam0 */ - RK_MUXROUTE_SAME(3, RK_PB4, 2, 0x608, BIT(16 + 8) | BIT(16 + 9) | BIT(8)), /* i2c3_sdam1 */ - RK_MUXROUTE_SAME(2, RK_PA0, 3, 0x608, BIT(16 + 8) | BIT(16 + 9) | BIT(9)), /* i2c3_sdam2 */ + RK_MUXROUTE_SAME(0, RK_PB7, 2, 0x314, BIT(16 + 4)), /* i2c3_sdam0 */ + RK_MUXROUTE_SAME(3, RK_PB4, 2, 0x314, BIT(16 + 4) | BIT(4)), /* i2c3_sdam1 */ RK_MUXROUTE_SAME(1, RK_PA3, 2, 0x308, BIT(16 + 3)), /* i2s-8ch-1-sclktxm0 */ RK_MUXROUTE_SAME(1, RK_PA4, 2, 0x308, BIT(16 + 3)), /* i2s-8ch-1-sclkrxm0 */ RK_MUXROUTE_SAME(1, RK_PB5, 2, 0x308, BIT(16 + 3) | BIT(3)), /* i2s-8ch-1-sclktxm1 */ @@ -731,18 +730,6 @@ static struct rockchip_mux_route_data rk3308_mux_route_data[] = { RK_MUXROUTE_SAME(1, RK_PB6, 4, 0x308, BIT(16 + 12) | BIT(16 + 13) | BIT(12)), /* pdm-clkm1 */ RK_MUXROUTE_SAME(2, RK_PA6, 2, 0x308, BIT(16 + 12) | BIT(16 + 13) | BIT(13)), /* pdm-clkm2 */ RK_MUXROUTE_SAME(2, RK_PA4, 3, 0x600, BIT(16 + 2) | BIT(2)), /* pdm-clkm-m2 */ - RK_MUXROUTE_SAME(3, RK_PB2, 3, 0x314, BIT(16 + 9)), /* spi1_miso */ - RK_MUXROUTE_SAME(2, RK_PA4, 2, 0x314, BIT(16 + 9) | BIT(9)), /* spi1_miso_m1 */ - RK_MUXROUTE_SAME(0, RK_PB3, 3, 0x314, BIT(16 + 10) | BIT(16 + 11)), /* owire_m0 */ - RK_MUXROUTE_SAME(1, RK_PC6, 7, 0x314, BIT(16 + 10) | BIT(16 + 11) | BIT(10)), /* owire_m1 */ - RK_MUXROUTE_SAME(2, RK_PA2, 5, 0x314, BIT(16 + 10) | BIT(16 + 11) | BIT(11)), /* owire_m2 */ - RK_MUXROUTE_SAME(0, RK_PB3, 2, 0x314, BIT(16 + 12) | BIT(16 + 13)), /* can_rxd_m0 */ - RK_MUXROUTE_SAME(1, RK_PC6, 5, 0x314, BIT(16 + 12) | BIT(16 + 13) | BIT(12)), /* can_rxd_m1 */ - RK_MUXROUTE_SAME(2, RK_PA2, 4, 0x314, BIT(16 + 12) | BIT(16 + 13) | BIT(13)), /* can_rxd_m2 */ - RK_MUXROUTE_SAME(1, RK_PC4, 3, 0x314, BIT(16 + 14)), /* mac_rxd0_m0 */ - RK_MUXROUTE_SAME(4, RK_PA2, 2, 0x314, BIT(16 + 14) | BIT(14)), /* mac_rxd0_m1 */ - RK_MUXROUTE_SAME(3, RK_PB4, 4, 0x314, BIT(16 + 15)), /* uart3_rx */ - RK_MUXROUTE_SAME(0, RK_PC1, 3, 0x314, BIT(16 + 15) | BIT(15)), /* uart3_rx_m1 */ }; static struct rockchip_mux_route_data rk3328_mux_route_data[] = { From 8c3bef7ca88a855c337e78c3b296adbdfabb3a45 Mon Sep 17 00:00:00 2001 From: Yang Yingliang Date: Thu, 6 Jun 2024 10:37:02 +0800 Subject: [PATCH 107/342] pinctrl: core: fix possible memory leak when pinctrl_enable() fails [ Upstream commit ae1cf4759972c5fe665ee4c5e0c29de66fe3cf4a ] In devm_pinctrl_register(), if pinctrl_enable() fails in pinctrl_register(), the "pctldev" has not been added to dev resources, so devm_pinctrl_dev_release() can not be called, it leads memory leak. Introduce pinctrl_uninit_controller(), call it in the error path to free memory. Fixes: 5038a66dad01 ("pinctrl: core: delete incorrect free in pinctrl_enable()") Signed-off-by: Yang Yingliang Reviewed-by: Dan Carpenter Link: https://lore.kernel.org/r/20240606023704.3931561-2-yangyingliang@huawei.com Signed-off-by: Linus Walleij Signed-off-by: Sasha Levin --- drivers/pinctrl/core.c | 12 +++++++++++- 1 file changed, 11 insertions(+), 1 deletion(-) diff --git a/drivers/pinctrl/core.c b/drivers/pinctrl/core.c index 3d44d6f48cc4..8152d24e128a 100644 --- a/drivers/pinctrl/core.c +++ b/drivers/pinctrl/core.c @@ -2039,6 +2039,14 @@ pinctrl_init_controller(struct pinctrl_desc *pctldesc, struct device *dev, return ERR_PTR(ret); } +static void pinctrl_uninit_controller(struct pinctrl_dev *pctldev, struct pinctrl_desc *pctldesc) +{ + pinctrl_free_pindescs(pctldev, pctldesc->pins, + pctldesc->npins); + mutex_destroy(&pctldev->mutex); + kfree(pctldev); +} + static int pinctrl_claim_hogs(struct pinctrl_dev *pctldev) { pctldev->p = create_pinctrl(pctldev->dev, pctldev); @@ -2119,8 +2127,10 @@ struct pinctrl_dev *pinctrl_register(struct pinctrl_desc *pctldesc, return pctldev; error = pinctrl_enable(pctldev); - if (error) + if (error) { + pinctrl_uninit_controller(pctldev, pctldesc); return ERR_PTR(error); + } return pctldev; } From 15014206f90db2cea5b84b5fbdb63bbc64cd1ba4 Mon Sep 17 00:00:00 2001 From: Yang Yingliang Date: Thu, 6 Jun 2024 10:37:03 +0800 Subject: [PATCH 108/342] pinctrl: single: fix possible memory leak when pinctrl_enable() fails [ Upstream commit 8f773bfbdd428819328a2d185976cfc6ae811cd3 ] This driver calls pinctrl_register_and_init() which is not devm_ managed, it will leads memory leak if pinctrl_enable() fails. Replace it with devm_pinctrl_register_and_init(). And call pcs_free_resources() if pinctrl_enable() fails. Fixes: 5038a66dad01 ("pinctrl: core: delete incorrect free in pinctrl_enable()") Signed-off-by: Yang Yingliang Reviewed-by: Dan Carpenter Link: https://lore.kernel.org/r/20240606023704.3931561-3-yangyingliang@huawei.com Signed-off-by: Linus Walleij Signed-off-by: Sasha Levin --- drivers/pinctrl/pinctrl-single.c | 7 ++++--- 1 file changed, 4 insertions(+), 3 deletions(-) diff --git a/drivers/pinctrl/pinctrl-single.c b/drivers/pinctrl/pinctrl-single.c index 22e471933b37..4860c4dd853f 100644 --- a/drivers/pinctrl/pinctrl-single.c +++ b/drivers/pinctrl/pinctrl-single.c @@ -1332,7 +1332,6 @@ static void pcs_irq_free(struct pcs_device *pcs) static void pcs_free_resources(struct pcs_device *pcs) { pcs_irq_free(pcs); - pinctrl_unregister(pcs->pctl); #if IS_BUILTIN(CONFIG_PINCTRL_SINGLE) if (pcs->missing_nr_pinctrl_cells) @@ -1889,7 +1888,7 @@ static int pcs_probe(struct platform_device *pdev) if (ret < 0) goto free; - ret = pinctrl_register_and_init(&pcs->desc, pcs->dev, pcs, &pcs->pctl); + ret = devm_pinctrl_register_and_init(pcs->dev, &pcs->desc, pcs, &pcs->pctl); if (ret) { dev_err(pcs->dev, "could not register single pinctrl driver\n"); goto free; @@ -1922,8 +1921,10 @@ static int pcs_probe(struct platform_device *pdev) dev_info(pcs->dev, "%i pins, size %u\n", pcs->desc.npins, pcs->size); - return pinctrl_enable(pcs->pctl); + if (pinctrl_enable(pcs->pctl)) + goto free; + return 0; free: pcs_free_resources(pcs); From 73303a4a8fd7f7661372a1cbd4d7c40436c62f2d Mon Sep 17 00:00:00 2001 From: =?UTF-8?q?Uwe=20Kleine-K=C3=B6nig?= Date: Mon, 9 Oct 2023 10:38:39 +0200 Subject: [PATCH 109/342] pinctrl: ti: ti-iodelay: Drop if block with always false condition MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit [ Upstream commit 88b3f108502bc45e6ebd005702add46759f3f45a ] ti_iodelay_remove() is only called after ti_iodelay_probe() completed successfully. In this case platform_set_drvdata() was called with a non-NULL argument and so platform_get_drvdata() won't return NULL. Simplify by removing the if block with the always false condition. Signed-off-by: Uwe Kleine-König Link: https://lore.kernel.org/r/20231009083856.222030-4-u.kleine-koenig@pengutronix.de Signed-off-by: Linus Walleij Stable-dep-of: 9b401f4a7170 ("pinctrl: ti: ti-iodelay: fix possible memory leak when pinctrl_enable() fails") Signed-off-by: Sasha Levin --- drivers/pinctrl/ti/pinctrl-ti-iodelay.c | 3 --- 1 file changed, 3 deletions(-) diff --git a/drivers/pinctrl/ti/pinctrl-ti-iodelay.c b/drivers/pinctrl/ti/pinctrl-ti-iodelay.c index cfb924228d87..60d94c1fc6a6 100644 --- a/drivers/pinctrl/ti/pinctrl-ti-iodelay.c +++ b/drivers/pinctrl/ti/pinctrl-ti-iodelay.c @@ -906,9 +906,6 @@ static int ti_iodelay_remove(struct platform_device *pdev) { struct ti_iodelay_device *iod = platform_get_drvdata(pdev); - if (!iod) - return 0; - if (iod->pctl) pinctrl_unregister(iod->pctl); From d2de7746e5e95ecd862f129f21d237bdce9fb27a Mon Sep 17 00:00:00 2001 From: Yang Yingliang Date: Thu, 6 Jun 2024 10:37:04 +0800 Subject: [PATCH 110/342] pinctrl: ti: ti-iodelay: fix possible memory leak when pinctrl_enable() fails [ Upstream commit 9b401f4a7170125365160c9af267a41ff6b39001 ] This driver calls pinctrl_register_and_init() which is not devm_ managed, it will leads memory leak if pinctrl_enable() fails. Replace it with devm_pinctrl_register_and_init(). And add missing of_node_put() in the error path. Fixes: 5038a66dad01 ("pinctrl: core: delete incorrect free in pinctrl_enable()") Signed-off-by: Yang Yingliang Reviewed-by: Dan Carpenter Link: https://lore.kernel.org/r/20240606023704.3931561-4-yangyingliang@huawei.com Signed-off-by: Linus Walleij Signed-off-by: Sasha Levin --- drivers/pinctrl/ti/pinctrl-ti-iodelay.c | 11 ++++++----- 1 file changed, 6 insertions(+), 5 deletions(-) diff --git a/drivers/pinctrl/ti/pinctrl-ti-iodelay.c b/drivers/pinctrl/ti/pinctrl-ti-iodelay.c index 60d94c1fc6a6..6e1b067fb72e 100644 --- a/drivers/pinctrl/ti/pinctrl-ti-iodelay.c +++ b/drivers/pinctrl/ti/pinctrl-ti-iodelay.c @@ -881,7 +881,7 @@ static int ti_iodelay_probe(struct platform_device *pdev) iod->desc.name = dev_name(dev); iod->desc.owner = THIS_MODULE; - ret = pinctrl_register_and_init(&iod->desc, dev, iod, &iod->pctl); + ret = devm_pinctrl_register_and_init(dev, &iod->desc, iod, &iod->pctl); if (ret) { dev_err(dev, "Failed to register pinctrl\n"); goto exit_out; @@ -889,7 +889,11 @@ static int ti_iodelay_probe(struct platform_device *pdev) platform_set_drvdata(pdev, iod); - return pinctrl_enable(iod->pctl); + ret = pinctrl_enable(iod->pctl); + if (ret) + goto exit_out; + + return 0; exit_out: of_node_put(np); @@ -906,9 +910,6 @@ static int ti_iodelay_remove(struct platform_device *pdev) { struct ti_iodelay_device *iod = platform_get_drvdata(pdev); - if (iod->pctl) - pinctrl_unregister(iod->pctl); - ti_iodelay_pinconf_deinit_dev(iod); /* Expect other allocations to be freed by devm */ From 21a15d52bc2249b917196a4de83c2a3c781d52a3 Mon Sep 17 00:00:00 2001 From: Peng Fan Date: Sat, 4 May 2024 21:20:16 +0800 Subject: [PATCH 111/342] pinctrl: freescale: mxs: Fix refcount of child [ Upstream commit 7f500f2011c0bbb6e1cacab74b4c99222e60248e ] of_get_next_child() will increase refcount of the returned node, need use of_node_put() on it when done. Per current implementation, 'child' will be override by for_each_child_of_node(np, child), so use of_get_child_count to avoid refcount leakage. Fixes: 17723111e64f ("pinctrl: add pinctrl-mxs support") Signed-off-by: Peng Fan Link: https://lore.kernel.org/20240504-pinctrl-cleanup-v2-18-26c5f2dc1181@nxp.com Signed-off-by: Linus Walleij Signed-off-by: Sasha Levin --- drivers/pinctrl/freescale/pinctrl-mxs.c | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-) diff --git a/drivers/pinctrl/freescale/pinctrl-mxs.c b/drivers/pinctrl/freescale/pinctrl-mxs.c index 735cedd0958a..5b0fcf15f280 100644 --- a/drivers/pinctrl/freescale/pinctrl-mxs.c +++ b/drivers/pinctrl/freescale/pinctrl-mxs.c @@ -405,8 +405,8 @@ static int mxs_pinctrl_probe_dt(struct platform_device *pdev, int ret; u32 val; - child = of_get_next_child(np, NULL); - if (!child) { + val = of_get_child_count(np); + if (val == 0) { dev_err(&pdev->dev, "no group is defined\n"); return -ENOENT; } From 3c6fa67023bcf6cc84c7b948db824693dc96c745 Mon Sep 17 00:00:00 2001 From: David Hildenbrand Date: Fri, 7 Jun 2024 14:23:52 +0200 Subject: [PATCH 112/342] fs/proc/task_mmu: indicate PM_FILE for PMD-mapped file THP [ Upstream commit 3f9f022e975d930709848a86a1c79775b0585202 ] Patch series "fs/proc: move page_mapcount() to fs/proc/internal.h". With all other page_mapcount() users in the tree gone, move page_mapcount() to fs/proc/internal.h, rename it and extend the documentation to prevent future (ab)use. ... of course, I find some issues while working on that code that I sort first ;) We'll now only end up calling page_mapcount() [now folio_precise_page_mapcount()] on pages mapped via present page table entries. Except for /proc/kpagecount, that still does questionable things, but we'll leave that legacy interface as is for now. Did a quick sanity check. Likely we would want some better selfestest for /proc/$/pagemap + smaps. I'll see if I can find some time to write some more. This patch (of 6): Looks like we never taught pagemap_pmd_range() about the existence of PMD-mapped file THPs. Seems to date back to the times when we first added support for non-anon THPs in the form of shmem THP. Link: https://lkml.kernel.org/r/20240607122357.115423-1-david@redhat.com Link: https://lkml.kernel.org/r/20240607122357.115423-2-david@redhat.com Signed-off-by: David Hildenbrand Fixes: 800d8c63b2e9 ("shmem: add huge pages support") Acked-by: Kirill A. Shutemov Reviewed-by: Lance Yang Reviewed-by: Oscar Salvador Cc: David Hildenbrand Cc: Jonathan Corbet Cc: Alexey Dobriyan Signed-off-by: Andrew Morton Signed-off-by: Sasha Levin --- fs/proc/task_mmu.c | 2 ++ 1 file changed, 2 insertions(+) diff --git a/fs/proc/task_mmu.c b/fs/proc/task_mmu.c index 39b1038076c3..97023c0dca60 100644 --- a/fs/proc/task_mmu.c +++ b/fs/proc/task_mmu.c @@ -1468,6 +1468,8 @@ static int pagemap_pmd_range(pmd_t *pmdp, unsigned long addr, unsigned long end, } #endif + if (page && !PageAnon(page)) + flags |= PM_FILE; if (page && !migration && page_mapcount(page) == 1) flags |= PM_MMAP_EXCLUSIVE; From 9d6571b1c4b62dc0e03e7ca03e3dd88c1e786e88 Mon Sep 17 00:00:00 2001 From: Alex Shi Date: Tue, 15 Dec 2020 20:45:27 -0800 Subject: [PATCH 113/342] fs/nilfs2: remove some unused macros to tame gcc [ Upstream commit e7920b3e9d9f5470d5ff7d883e72a47addc0a137 ] There some macros are unused and cause gcc warning. Remove them. fs/nilfs2/segment.c:137:0: warning: macro "nilfs_cnt32_gt" is not used [-Wunused-macros] fs/nilfs2/segment.c:144:0: warning: macro "nilfs_cnt32_le" is not used [-Wunused-macros] fs/nilfs2/segment.c:143:0: warning: macro "nilfs_cnt32_lt" is not used [-Wunused-macros] Link: https://lkml.kernel.org/r/1607552733-24292-1-git-send-email-konishi.ryusuke@gmail.com Signed-off-by: Ryusuke Konishi Signed-off-by: Alex Shi Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds Stable-dep-of: 0f3819e8c483 ("nilfs2: avoid undefined behavior in nilfs_cnt32_ge macro") Signed-off-by: Sasha Levin --- fs/nilfs2/segment.c | 5 ----- 1 file changed, 5 deletions(-) diff --git a/fs/nilfs2/segment.c b/fs/nilfs2/segment.c index 02407c524382..1f7ae5f36bde 100644 --- a/fs/nilfs2/segment.c +++ b/fs/nilfs2/segment.c @@ -134,14 +134,9 @@ static void nilfs_segctor_do_flush(struct nilfs_sc_info *, int); static void nilfs_segctor_do_immediate_flush(struct nilfs_sc_info *); static void nilfs_dispose_list(struct the_nilfs *, struct list_head *, int); -#define nilfs_cnt32_gt(a, b) \ - (typecheck(__u32, a) && typecheck(__u32, b) && \ - ((__s32)(b) - (__s32)(a) < 0)) #define nilfs_cnt32_ge(a, b) \ (typecheck(__u32, a) && typecheck(__u32, b) && \ ((__s32)(a) - (__s32)(b) >= 0)) -#define nilfs_cnt32_lt(a, b) nilfs_cnt32_gt(b, a) -#define nilfs_cnt32_le(a, b) nilfs_cnt32_ge(b, a) static int nilfs_prepare_segment_lock(struct super_block *sb, struct nilfs_transaction_info *ti) From 84ffa27eb04ca312e3cc2f5399eb5ac492b58bfc Mon Sep 17 00:00:00 2001 From: Ryusuke Konishi Date: Wed, 3 Jul 2024 03:35:12 +0900 Subject: [PATCH 114/342] nilfs2: avoid undefined behavior in nilfs_cnt32_ge macro [ Upstream commit 0f3819e8c483771a59cf9d3190cd68a7a990083c ] According to the C standard 3.4.3p3, the result of signed integer overflow is undefined. The macro nilfs_cnt32_ge(), which compares two sequence numbers, uses signed integer subtraction that can overflow, and therefore the result of the calculation may differ from what is expected due to undefined behavior in different environments. Similar to an earlier change to the jiffies-related comparison macros in commit 5a581b367b5d ("jiffies: Avoid undefined behavior from signed overflow"), avoid this potential issue by changing the definition of the macro to perform the subtraction as unsigned integers, then cast the result to a signed integer for comparison. Link: https://lkml.kernel.org/r/20130727225828.GA11864@linux.vnet.ibm.com Link: https://lkml.kernel.org/r/20240702183512.6390-1-konishi.ryusuke@gmail.com Fixes: 9ff05123e3bf ("nilfs2: segment constructor") Signed-off-by: Ryusuke Konishi Signed-off-by: Andrew Morton Signed-off-by: Sasha Levin --- fs/nilfs2/segment.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/fs/nilfs2/segment.c b/fs/nilfs2/segment.c index 1f7ae5f36bde..d9f92df15a84 100644 --- a/fs/nilfs2/segment.c +++ b/fs/nilfs2/segment.c @@ -136,7 +136,7 @@ static void nilfs_dispose_list(struct the_nilfs *, struct list_head *, int); #define nilfs_cnt32_ge(a, b) \ (typecheck(__u32, a) && typecheck(__u32, b) && \ - ((__s32)(a) - (__s32)(b) >= 0)) + ((__s32)((a) - (b)) >= 0)) static int nilfs_prepare_segment_lock(struct super_block *sb, struct nilfs_transaction_info *ti) From 14083dc69ba6eaf376e581ce773d218abfbae76d Mon Sep 17 00:00:00 2001 From: =?UTF-8?q?Cs=C3=B3k=C3=A1s=2C=20Bence?= Date: Wed, 19 Jun 2024 16:04:52 +0200 Subject: [PATCH 115/342] rtc: interface: Add RTC offset to alarm after fix-up MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit [ Upstream commit 463927a8902a9f22c3633960119410f57d4c8920 ] `rtc_add_offset()` is called by `__rtc_read_time()` and `__rtc_read_alarm()` to add the RTC's offset to the raw read-outs from the device drivers. However, in the latter case, a fix-up algorithm is run if the RTC device does not report a full `struct rtc_time` alarm value. In that case, the offset was forgot to be added. Fixes: fd6792bb022e ("rtc: fix alarm read and set offset") Signed-off-by: Csókás, Bence Link: https://lore.kernel.org/r/20240619140451.2800578-1-csokas.bence@prolan.hu Signed-off-by: Alexandre Belloni Signed-off-by: Sasha Levin --- drivers/rtc/interface.c | 9 +++++---- 1 file changed, 5 insertions(+), 4 deletions(-) diff --git a/drivers/rtc/interface.c b/drivers/rtc/interface.c index 146056858135..154ea5ae2c0c 100644 --- a/drivers/rtc/interface.c +++ b/drivers/rtc/interface.c @@ -274,10 +274,9 @@ int __rtc_read_alarm(struct rtc_device *rtc, struct rtc_wkalrm *alarm) return err; /* full-function RTCs won't have such missing fields */ - if (rtc_valid_tm(&alarm->time) == 0) { - rtc_add_offset(rtc, &alarm->time); - return 0; - } + err = rtc_valid_tm(&alarm->time); + if (!err) + goto done; /* get the "after" timestamp, to detect wrapped fields */ err = rtc_read_time(rtc, &now); @@ -379,6 +378,8 @@ int __rtc_read_alarm(struct rtc_device *rtc, struct rtc_wkalrm *alarm) if (err) dev_warn(&rtc->dev, "invalid alarm value: %ptR\n", &alarm->time); + else + rtc_add_offset(rtc, &alarm->time); return err; } From f2c2c4cc5af7525ac3fdd723fd284533f7b3f073 Mon Sep 17 00:00:00 2001 From: Krzysztof Kozlowski Date: Tue, 2 Jul 2024 16:52:48 +0200 Subject: [PATCH 116/342] dt-bindings: thermal: correct thermal zone node name limit commit 97e32381d0fc6c2602a767b0c46e15eb2b75971d upstream. Linux kernel uses thermal zone node name during registering thermal zones and has a hard-coded limit of 20 characters, including terminating NUL byte. The bindings expect node names to finish with '-thermal' which is eight bytes long, thus we have only 11 characters for the reset of the node name (thus 10 for the pattern after leading fixed character). Reported-by: Rob Herring Closes: https://lore.kernel.org/all/CAL_JsqKogbT_4DPd1n94xqeHaU_J8ve5K09WOyVsRX3jxxUW3w@mail.gmail.com/ Fixes: 1202a442a31f ("dt-bindings: thermal: Add yaml bindings for thermal zones") Cc: stable@vger.kernel.org Signed-off-by: Krzysztof Kozlowski Link: https://lore.kernel.org/r/20240702145248.47184-1-krzysztof.kozlowski@linaro.org Signed-off-by: Daniel Lezcano Signed-off-by: Greg Kroah-Hartman --- Documentation/devicetree/bindings/thermal/thermal-zones.yaml | 5 ++++- 1 file changed, 4 insertions(+), 1 deletion(-) diff --git a/Documentation/devicetree/bindings/thermal/thermal-zones.yaml b/Documentation/devicetree/bindings/thermal/thermal-zones.yaml index 1b3954aa71c1..af946e3da82a 100644 --- a/Documentation/devicetree/bindings/thermal/thermal-zones.yaml +++ b/Documentation/devicetree/bindings/thermal/thermal-zones.yaml @@ -49,7 +49,10 @@ properties: to take when the temperature crosses those thresholds. patternProperties: - "^[a-zA-Z][a-zA-Z0-9\\-]{1,12}-thermal$": + # Node name is limited in size due to Linux kernel requirements - 19 + # characters in total (see THERMAL_NAME_LENGTH, including terminating NUL + # byte): + "^[a-zA-Z][a-zA-Z0-9\\-]{1,10}-thermal$": type: object description: Each thermal zone node contains information about how frequently it From 9ef7190228145f959d9bc0ddca40ecf76bb413b0 Mon Sep 17 00:00:00 2001 From: Yu Liao Date: Thu, 11 Jul 2024 20:48:43 +0800 Subject: [PATCH 117/342] tick/broadcast: Make takeover of broadcast hrtimer reliable commit f7d43dd206e7e18c182f200e67a8db8c209907fa upstream. Running the LTP hotplug stress test on a aarch64 machine results in rcu_sched stall warnings when the broadcast hrtimer was owned by the un-plugged CPU. The issue is the following: CPU1 (owns the broadcast hrtimer) CPU2 tick_broadcast_enter() // shutdown local timer device broadcast_shutdown_local() ... tick_broadcast_exit() clockevents_switch_state(dev, CLOCK_EVT_STATE_ONESHOT) // timer device is not programmed cpumask_set_cpu(cpu, tick_broadcast_force_mask) initiates offlining of CPU1 take_cpu_down() /* * CPU1 shuts down and does not * send broadcast IPI anymore */ takedown_cpu() hotplug_cpu__broadcast_tick_pull() // move broadcast hrtimer to this CPU clockevents_program_event() bc_set_next() hrtimer_start() /* * timer device is not programmed * because only the first expiring * timer will trigger clockevent * device reprogramming */ What happens is that CPU2 exits broadcast mode with force bit set, then the local timer device is not reprogrammed and CPU2 expects to receive the expired event by the broadcast IPI. But this does not happen because CPU1 is offlined by CPU2. CPU switches the clockevent device to ONESHOT state, but does not reprogram the device. The subsequent reprogramming of the hrtimer broadcast device does not program the clockevent device of CPU2 either because the pending expiry time is already in the past and the CPU expects the event to be delivered. As a consequence all CPUs which wait for a broadcast event to be delivered are stuck forever. Fix this issue by reprogramming the local timer device if the broadcast force bit of the CPU is set so that the broadcast hrtimer is delivered. [ tglx: Massage comment and change log. Add Fixes tag ] Fixes: 989dcb645ca7 ("tick: Handle broadcast wakeup of multiple cpus") Signed-off-by: Yu Liao Signed-off-by: Thomas Gleixner Cc: stable@vger.kernel.org Link: https://lore.kernel.org/r/20240711124843.64167-1-liaoyu15@huawei.com Signed-off-by: Greg Kroah-Hartman --- kernel/time/tick-broadcast.c | 23 +++++++++++++++++++++++ 1 file changed, 23 insertions(+) diff --git a/kernel/time/tick-broadcast.c b/kernel/time/tick-broadcast.c index a9530e866e5f..792ef33ba487 100644 --- a/kernel/time/tick-broadcast.c +++ b/kernel/time/tick-broadcast.c @@ -944,6 +944,7 @@ void tick_broadcast_switch_to_oneshot(void) #ifdef CONFIG_HOTPLUG_CPU void hotplug_cpu__broadcast_tick_pull(int deadcpu) { + struct tick_device *td = this_cpu_ptr(&tick_cpu_device); struct clock_event_device *bc; unsigned long flags; @@ -951,6 +952,28 @@ void hotplug_cpu__broadcast_tick_pull(int deadcpu) bc = tick_broadcast_device.evtdev; if (bc && broadcast_needs_cpu(bc, deadcpu)) { + /* + * If the broadcast force bit of the current CPU is set, + * then the current CPU has not yet reprogrammed the local + * timer device to avoid a ping-pong race. See + * ___tick_broadcast_oneshot_control(). + * + * If the broadcast device is hrtimer based then + * programming the broadcast event below does not have any + * effect because the local clockevent device is not + * running and not programmed because the broadcast event + * is not earlier than the pending event of the local clock + * event device. As a consequence all CPUs waiting for a + * broadcast event are stuck forever. + * + * Detect this condition and reprogram the cpu local timer + * device to avoid the starvation. + */ + if (tick_check_broadcast_expired()) { + cpumask_clear_cpu(smp_processor_id(), tick_broadcast_force_mask); + tick_program_event(td->evtdev->next_event, 1); + } + /* This moves the broadcast assignment to this CPU: */ clockevents_program_event(bc, bc->next_event, 1); } From 7e36a3c701b486d47d163f2ed8142223006e42f5 Mon Sep 17 00:00:00 2001 From: Breno Leitao Date: Fri, 12 Jul 2024 07:34:15 -0700 Subject: [PATCH 118/342] net: netconsole: Disable target before netpoll cleanup commit 97d9fba9a812cada5484667a46e14a4c976ca330 upstream. Currently, netconsole cleans up the netpoll structure before disabling the target. This approach can lead to race conditions, as message senders (write_ext_msg() and write_msg()) check if the target is enabled before using netpoll. The sender can validate that the target is enabled, but, the netpoll might be de-allocated already, causing undesired behaviours. This patch reverses the order of operations: 1. Disable the target 2. Clean up the netpoll structure This change eliminates the potential race condition, ensuring that no messages are sent through a partially cleaned-up netpoll structure. Fixes: 2382b15bcc39 ("netconsole: take care of NETDEV_UNREGISTER event") Cc: stable@vger.kernel.org Signed-off-by: Breno Leitao Reviewed-by: Eric Dumazet Link: https://patch.msgid.link/20240712143415.1141039-1-leitao@debian.org Signed-off-by: Jakub Kicinski Signed-off-by: Greg Kroah-Hartman --- drivers/net/netconsole.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/drivers/net/netconsole.c b/drivers/net/netconsole.c index 92001f7af380..924370e53003 100644 --- a/drivers/net/netconsole.c +++ b/drivers/net/netconsole.c @@ -715,6 +715,7 @@ static int netconsole_netdev_event(struct notifier_block *this, /* rtnl_lock already held * we might sleep in __netpoll_cleanup() */ + nt->enabled = false; spin_unlock_irqrestore(&target_list_lock, flags); __netpoll_cleanup(&nt->np); @@ -722,7 +723,6 @@ static int netconsole_netdev_event(struct notifier_block *this, spin_lock_irqsave(&target_list_lock, flags); dev_put(nt->np.dev); nt->np.dev = NULL; - nt->enabled = false; stopped = true; netconsole_target_put(nt); goto restart; From 83e2dfadcb6258fe3111c8a8ec9cf34465e55e64 Mon Sep 17 00:00:00 2001 From: Chengen Du Date: Sat, 13 Jul 2024 19:47:35 +0800 Subject: [PATCH 119/342] af_packet: Handle outgoing VLAN packets without hardware offloading commit 79eecf631c14e7f4057186570ac20e2cfac3802e upstream. The issue initially stems from libpcap. The ethertype will be overwritten as the VLAN TPID if the network interface lacks hardware VLAN offloading. In the outbound packet path, if hardware VLAN offloading is unavailable, the VLAN tag is inserted into the payload but then cleared from the sk_buff struct. Consequently, this can lead to a false negative when checking for the presence of a VLAN tag, causing the packet sniffing outcome to lack VLAN tag information (i.e., TCI-TPID). As a result, the packet capturing tool may be unable to parse packets as expected. The TCI-TPID is missing because the prb_fill_vlan_info() function does not modify the tp_vlan_tci/tp_vlan_tpid values, as the information is in the payload and not in the sk_buff struct. The skb_vlan_tag_present() function only checks vlan_all in the sk_buff struct. In cooked mode, the L2 header is stripped, preventing the packet capturing tool from determining the correct TCI-TPID value. Additionally, the protocol in SLL is incorrect, which means the packet capturing tool cannot parse the L3 header correctly. Link: https://github.com/the-tcpdump-group/libpcap/issues/1105 Link: https://lore.kernel.org/netdev/20240520070348.26725-1-chengen.du@canonical.com/T/#u Fixes: 393e52e33c6c ("packet: deliver VLAN TCI to userspace") Cc: stable@vger.kernel.org Signed-off-by: Chengen Du Reviewed-by: Willem de Bruijn Link: https://patch.msgid.link/20240713114735.62360-1-chengen.du@canonical.com Signed-off-by: Jakub Kicinski Signed-off-by: Greg Kroah-Hartman --- net/packet/af_packet.c | 86 +++++++++++++++++++++++++++++++++++++++++- 1 file changed, 84 insertions(+), 2 deletions(-) diff --git a/net/packet/af_packet.c b/net/packet/af_packet.c index 9bec88fe3505..ce3e20bcde4a 100644 --- a/net/packet/af_packet.c +++ b/net/packet/af_packet.c @@ -503,6 +503,61 @@ static void *packet_current_frame(struct packet_sock *po, return packet_lookup_frame(po, rb, rb->head, status); } +static u16 vlan_get_tci(struct sk_buff *skb, struct net_device *dev) +{ + u8 *skb_orig_data = skb->data; + int skb_orig_len = skb->len; + struct vlan_hdr vhdr, *vh; + unsigned int header_len; + + if (!dev) + return 0; + + /* In the SOCK_DGRAM scenario, skb data starts at the network + * protocol, which is after the VLAN headers. The outer VLAN + * header is at the hard_header_len offset in non-variable + * length link layer headers. If it's a VLAN device, the + * min_header_len should be used to exclude the VLAN header + * size. + */ + if (dev->min_header_len == dev->hard_header_len) + header_len = dev->hard_header_len; + else if (is_vlan_dev(dev)) + header_len = dev->min_header_len; + else + return 0; + + skb_push(skb, skb->data - skb_mac_header(skb)); + vh = skb_header_pointer(skb, header_len, sizeof(vhdr), &vhdr); + if (skb_orig_data != skb->data) { + skb->data = skb_orig_data; + skb->len = skb_orig_len; + } + if (unlikely(!vh)) + return 0; + + return ntohs(vh->h_vlan_TCI); +} + +static __be16 vlan_get_protocol_dgram(struct sk_buff *skb) +{ + __be16 proto = skb->protocol; + + if (unlikely(eth_type_vlan(proto))) { + u8 *skb_orig_data = skb->data; + int skb_orig_len = skb->len; + + skb_push(skb, skb->data - skb_mac_header(skb)); + proto = __vlan_get_protocol(skb, proto, NULL); + if (skb_orig_data != skb->data) { + skb->data = skb_orig_data; + skb->len = skb_orig_len; + } + } + + return proto; +} + static void prb_del_retire_blk_timer(struct tpacket_kbdq_core *pkc) { del_timer_sync(&pkc->retire_blk_timer); @@ -972,10 +1027,16 @@ static void prb_clear_rxhash(struct tpacket_kbdq_core *pkc, static void prb_fill_vlan_info(struct tpacket_kbdq_core *pkc, struct tpacket3_hdr *ppd) { + struct packet_sock *po = container_of(pkc, struct packet_sock, rx_ring.prb_bdqc); + if (skb_vlan_tag_present(pkc->skb)) { ppd->hv1.tp_vlan_tci = skb_vlan_tag_get(pkc->skb); ppd->hv1.tp_vlan_tpid = ntohs(pkc->skb->vlan_proto); ppd->tp_status = TP_STATUS_VLAN_VALID | TP_STATUS_VLAN_TPID_VALID; + } else if (unlikely(po->sk.sk_type == SOCK_DGRAM && eth_type_vlan(pkc->skb->protocol))) { + ppd->hv1.tp_vlan_tci = vlan_get_tci(pkc->skb, pkc->skb->dev); + ppd->hv1.tp_vlan_tpid = ntohs(pkc->skb->protocol); + ppd->tp_status = TP_STATUS_VLAN_VALID | TP_STATUS_VLAN_TPID_VALID; } else { ppd->hv1.tp_vlan_tci = 0; ppd->hv1.tp_vlan_tpid = 0; @@ -2390,6 +2451,10 @@ static int tpacket_rcv(struct sk_buff *skb, struct net_device *dev, h.h2->tp_vlan_tci = skb_vlan_tag_get(skb); h.h2->tp_vlan_tpid = ntohs(skb->vlan_proto); status |= TP_STATUS_VLAN_VALID | TP_STATUS_VLAN_TPID_VALID; + } else if (unlikely(sk->sk_type == SOCK_DGRAM && eth_type_vlan(skb->protocol))) { + h.h2->tp_vlan_tci = vlan_get_tci(skb, skb->dev); + h.h2->tp_vlan_tpid = ntohs(skb->protocol); + status |= TP_STATUS_VLAN_VALID | TP_STATUS_VLAN_TPID_VALID; } else { h.h2->tp_vlan_tci = 0; h.h2->tp_vlan_tpid = 0; @@ -2419,7 +2484,8 @@ static int tpacket_rcv(struct sk_buff *skb, struct net_device *dev, sll->sll_halen = dev_parse_header(skb, sll->sll_addr); sll->sll_family = AF_PACKET; sll->sll_hatype = dev->type; - sll->sll_protocol = skb->protocol; + sll->sll_protocol = (sk->sk_type == SOCK_DGRAM) ? + vlan_get_protocol_dgram(skb) : skb->protocol; sll->sll_pkttype = skb->pkt_type; if (unlikely(packet_sock_flag(po, PACKET_SOCK_ORIGDEV))) sll->sll_ifindex = orig_dev->ifindex; @@ -3451,7 +3517,8 @@ static int packet_recvmsg(struct socket *sock, struct msghdr *msg, size_t len, /* Original length was stored in sockaddr_ll fields */ origlen = PACKET_SKB_CB(skb)->sa.origlen; sll->sll_family = AF_PACKET; - sll->sll_protocol = skb->protocol; + sll->sll_protocol = (sock->type == SOCK_DGRAM) ? + vlan_get_protocol_dgram(skb) : skb->protocol; } sock_recv_ts_and_drops(msg, sk, skb); @@ -3506,6 +3573,21 @@ static int packet_recvmsg(struct socket *sock, struct msghdr *msg, size_t len, aux.tp_vlan_tci = skb_vlan_tag_get(skb); aux.tp_vlan_tpid = ntohs(skb->vlan_proto); aux.tp_status |= TP_STATUS_VLAN_VALID | TP_STATUS_VLAN_TPID_VALID; + } else if (unlikely(sock->type == SOCK_DGRAM && eth_type_vlan(skb->protocol))) { + struct sockaddr_ll *sll = &PACKET_SKB_CB(skb)->sa.ll; + struct net_device *dev; + + rcu_read_lock(); + dev = dev_get_by_index_rcu(sock_net(sk), sll->sll_ifindex); + if (dev) { + aux.tp_vlan_tci = vlan_get_tci(skb, dev); + aux.tp_vlan_tpid = ntohs(skb->protocol); + aux.tp_status |= TP_STATUS_VLAN_VALID | TP_STATUS_VLAN_TPID_VALID; + } else { + aux.tp_vlan_tci = 0; + aux.tp_vlan_tpid = 0; + } + rcu_read_unlock(); } else { aux.tp_vlan_tci = 0; aux.tp_vlan_tpid = 0; From 5c5b02d48946084bbb3cc5d8c7ac64eba9d01362 Mon Sep 17 00:00:00 2001 From: Nicolas Dichtel Date: Wed, 10 Jul 2024 10:14:29 +0200 Subject: [PATCH 120/342] ipv6: take care of scope when choosing the src addr commit abb9a68d2c64dd9b128ae1f2e635e4d805e7ce64 upstream. When the source address is selected, the scope must be checked. For example, if a loopback address is assigned to the vrf device, it must not be chosen for packets sent outside. CC: stable@vger.kernel.org Fixes: afbac6010aec ("net: ipv6: Address selection needs to consider L3 domains") Signed-off-by: Nicolas Dichtel Reviewed-by: David Ahern Link: https://patch.msgid.link/20240710081521.3809742-4-nicolas.dichtel@6wind.com Signed-off-by: Jakub Kicinski Signed-off-by: Greg Kroah-Hartman --- net/ipv6/addrconf.c | 3 ++- 1 file changed, 2 insertions(+), 1 deletion(-) diff --git a/net/ipv6/addrconf.c b/net/ipv6/addrconf.c index ac09d4543f3e..455bb4668407 100644 --- a/net/ipv6/addrconf.c +++ b/net/ipv6/addrconf.c @@ -1822,7 +1822,8 @@ int ipv6_dev_get_saddr(struct net *net, const struct net_device *dst_dev, master, &dst, scores, hiscore_idx); - if (scores[hiscore_idx].ifa) + if (scores[hiscore_idx].ifa && + scores[hiscore_idx].scopedist >= 0) goto out; } From cf0c713c6946413b712c2311c6666d11a73ae4c2 Mon Sep 17 00:00:00 2001 From: Tejun Heo Date: Tue, 25 Jun 2024 15:29:58 -1000 Subject: [PATCH 121/342] sched/fair: set_load_weight() must also call reweight_task() for SCHED_IDLE tasks commit d329605287020c3d1c3b0dadc63d8208e7251382 upstream. When a task's weight is being changed, set_load_weight() is called with @update_load set. As weight changes aren't trivial for the fair class, set_load_weight() calls fair.c::reweight_task() for fair class tasks. However, set_load_weight() first tests task_has_idle_policy() on entry and skips calling reweight_task() for SCHED_IDLE tasks. This is buggy as SCHED_IDLE tasks are just fair tasks with a very low weight and they would incorrectly skip load, vlag and position updates. Fix it by updating reweight_task() to take struct load_weight as idle weight can't be expressed with prio and making set_load_weight() call reweight_task() for SCHED_IDLE tasks too when @update_load is set. Fixes: 9059393e4ec1 ("sched/fair: Use reweight_entity() for set_user_nice()") Suggested-by: Peter Zijlstra (Intel) Signed-off-by: Tejun Heo Signed-off-by: Peter Zijlstra (Intel) Cc: stable@vger.kernel.org # v4.15+ Link: http://lkml.kernel.org/r/20240624102331.GI31592@noisy.programming.kicks-ass.net Signed-off-by: Greg Kroah-Hartman --- kernel/sched/core.c | 23 ++++++++++------------- kernel/sched/fair.c | 7 +++---- kernel/sched/sched.h | 2 +- 3 files changed, 14 insertions(+), 18 deletions(-) diff --git a/kernel/sched/core.c b/kernel/sched/core.c index 40f40f359c5d..29d8fc3a7bbd 100644 --- a/kernel/sched/core.c +++ b/kernel/sched/core.c @@ -848,27 +848,24 @@ static void set_load_weight(struct task_struct *p) { bool update_load = !(READ_ONCE(p->state) & TASK_NEW); int prio = p->static_prio - MAX_RT_PRIO; - struct load_weight *load = &p->se.load; + struct load_weight lw; - /* - * SCHED_IDLE tasks get minimal weight: - */ if (task_has_idle_policy(p)) { - load->weight = scale_load(WEIGHT_IDLEPRIO); - load->inv_weight = WMULT_IDLEPRIO; - return; + lw.weight = scale_load(WEIGHT_IDLEPRIO); + lw.inv_weight = WMULT_IDLEPRIO; + } else { + lw.weight = scale_load(sched_prio_to_weight[prio]); + lw.inv_weight = sched_prio_to_wmult[prio]; } /* * SCHED_OTHER tasks have to update their load when changing their * weight */ - if (update_load && p->sched_class == &fair_sched_class) { - reweight_task(p, prio); - } else { - load->weight = scale_load(sched_prio_to_weight[prio]); - load->inv_weight = sched_prio_to_wmult[prio]; - } + if (update_load && p->sched_class == &fair_sched_class) + reweight_task(p, &lw); + else + p->se.load = lw; } #ifdef CONFIG_UCLAMP_TASK diff --git a/kernel/sched/fair.c b/kernel/sched/fair.c index 73a89fbd81be..376f5c6a933d 100644 --- a/kernel/sched/fair.c +++ b/kernel/sched/fair.c @@ -3119,15 +3119,14 @@ static void reweight_entity(struct cfs_rq *cfs_rq, struct sched_entity *se, } -void reweight_task(struct task_struct *p, int prio) +void reweight_task(struct task_struct *p, const struct load_weight *lw) { struct sched_entity *se = &p->se; struct cfs_rq *cfs_rq = cfs_rq_of(se); struct load_weight *load = &se->load; - unsigned long weight = scale_load(sched_prio_to_weight[prio]); - reweight_entity(cfs_rq, se, weight); - load->inv_weight = sched_prio_to_wmult[prio]; + reweight_entity(cfs_rq, se, lw->weight); + load->inv_weight = lw->inv_weight; } #ifdef CONFIG_FAIR_GROUP_SCHED diff --git a/kernel/sched/sched.h b/kernel/sched/sched.h index 8de07aba8bdd..df6cf8aa59f8 100644 --- a/kernel/sched/sched.h +++ b/kernel/sched/sched.h @@ -1938,7 +1938,7 @@ extern void init_sched_dl_class(void); extern void init_sched_rt_class(void); extern void init_sched_fair_class(void); -extern void reweight_task(struct task_struct *p, int prio); +extern void reweight_task(struct task_struct *p, const struct load_weight *lw); extern void resched_curr(struct rq *rq); extern void resched_cpu(int cpu); From e65cccfae729e1abc265ed689d49692897b787de Mon Sep 17 00:00:00 2001 From: Joe Hattori Date: Thu, 27 Jun 2024 15:31:09 +0900 Subject: [PATCH 122/342] char: tpm: Fix possible memory leak in tpm_bios_measurements_open() commit 5d8e2971e817bb64225fc0b6327a78752f58a9aa upstream. In tpm_bios_measurements_open(), get_device() is called on the device embedded in struct tpm_chip. In the error path, however, put_device() is not called. This results in a reference count leak, which prevents the device from being properly released. This commit makes sure to call put_device() when the seq_open() call fails. Cc: stable@vger.kernel.org # +v4.18 Fixes: 9b01b5356629 ("tpm: Move shared eventlog functions to common.c") Signed-off-by: Joe Hattori Signed-off-by: Jarkko Sakkinen Signed-off-by: Greg Kroah-Hartman --- drivers/char/tpm/eventlog/common.c | 2 ++ 1 file changed, 2 insertions(+) diff --git a/drivers/char/tpm/eventlog/common.c b/drivers/char/tpm/eventlog/common.c index 8512ec76d526..4a6186f9f889 100644 --- a/drivers/char/tpm/eventlog/common.c +++ b/drivers/char/tpm/eventlog/common.c @@ -47,6 +47,8 @@ static int tpm_bios_measurements_open(struct inode *inode, if (!err) { seq = file->private_data; seq->private = chip; + } else { + put_device(&chip->dev); } return err; From 4c9d235630d35db762b85a4149bbb0be9d504c36 Mon Sep 17 00:00:00 2001 From: Dikshita Agarwal Date: Thu, 9 May 2024 10:44:29 +0530 Subject: [PATCH 123/342] media: venus: fix use after free in vdec_close commit a0157b5aa34eb43ec4c5510f9c260bbb03be937e upstream. There appears to be a possible use after free with vdec_close(). The firmware will add buffer release work to the work queue through HFI callbacks as a normal part of decoding. Randomly closing the decoder device from userspace during normal decoding can incur a read after free for inst. Fix it by cancelling the work in vdec_close. Cc: stable@vger.kernel.org Fixes: af2c3834c8ca ("[media] media: venus: adding core part and helper functions") Signed-off-by: Dikshita Agarwal Acked-by: Vikash Garodia Signed-off-by: Stanimir Varbanov Signed-off-by: Hans Verkuil Signed-off-by: Greg Kroah-Hartman --- drivers/media/platform/qcom/venus/vdec.c | 1 + 1 file changed, 1 insertion(+) diff --git a/drivers/media/platform/qcom/venus/vdec.c b/drivers/media/platform/qcom/venus/vdec.c index b6edfa812bb7..d91030a134c0 100644 --- a/drivers/media/platform/qcom/venus/vdec.c +++ b/drivers/media/platform/qcom/venus/vdec.c @@ -1587,6 +1587,7 @@ static int vdec_close(struct file *file) vdec_pm_get(inst); + cancel_work_sync(&inst->delayed_process_work); v4l2_m2m_ctx_release(inst->m2m_ctx); v4l2_m2m_release(inst->m2m_dev); vdec_ctrl_deinit(inst); From 10f7163bfb5f8b4e0c9c05a939f20b8540e33c65 Mon Sep 17 00:00:00 2001 From: Chao Yu Date: Sun, 16 Jun 2024 09:38:41 +0800 Subject: [PATCH 124/342] hfs: fix to initialize fields of hfs_inode_info after hfs_alloc_inode() commit 26a2ed107929a855155429b11e1293b83e6b2a8b upstream. Syzbot reports uninitialized value access issue as below: loop0: detected capacity change from 0 to 64 ===================================================== BUG: KMSAN: uninit-value in hfs_revalidate_dentry+0x307/0x3f0 fs/hfs/sysdep.c:30 hfs_revalidate_dentry+0x307/0x3f0 fs/hfs/sysdep.c:30 d_revalidate fs/namei.c:862 [inline] lookup_fast+0x89e/0x8e0 fs/namei.c:1649 walk_component fs/namei.c:2001 [inline] link_path_walk+0x817/0x1480 fs/namei.c:2332 path_lookupat+0xd9/0x6f0 fs/namei.c:2485 filename_lookup+0x22e/0x740 fs/namei.c:2515 user_path_at_empty+0x8b/0x390 fs/namei.c:2924 user_path_at include/linux/namei.h:57 [inline] do_mount fs/namespace.c:3689 [inline] __do_sys_mount fs/namespace.c:3898 [inline] __se_sys_mount+0x66b/0x810 fs/namespace.c:3875 __x64_sys_mount+0xe4/0x140 fs/namespace.c:3875 do_syscall_x64 arch/x86/entry/common.c:52 [inline] do_syscall_64+0xcf/0x1e0 arch/x86/entry/common.c:83 entry_SYSCALL_64_after_hwframe+0x63/0x6b BUG: KMSAN: uninit-value in hfs_ext_read_extent fs/hfs/extent.c:196 [inline] BUG: KMSAN: uninit-value in hfs_get_block+0x92d/0x1620 fs/hfs/extent.c:366 hfs_ext_read_extent fs/hfs/extent.c:196 [inline] hfs_get_block+0x92d/0x1620 fs/hfs/extent.c:366 block_read_full_folio+0x4ff/0x11b0 fs/buffer.c:2271 hfs_read_folio+0x55/0x60 fs/hfs/inode.c:39 filemap_read_folio+0x148/0x4f0 mm/filemap.c:2426 do_read_cache_folio+0x7c8/0xd90 mm/filemap.c:3553 do_read_cache_page mm/filemap.c:3595 [inline] read_cache_page+0xfb/0x2f0 mm/filemap.c:3604 read_mapping_page include/linux/pagemap.h:755 [inline] hfs_btree_open+0x928/0x1ae0 fs/hfs/btree.c:78 hfs_mdb_get+0x260c/0x3000 fs/hfs/mdb.c:204 hfs_fill_super+0x1fb1/0x2790 fs/hfs/super.c:406 mount_bdev+0x628/0x920 fs/super.c:1359 hfs_mount+0xcd/0xe0 fs/hfs/super.c:456 legacy_get_tree+0x167/0x2e0 fs/fs_context.c:610 vfs_get_tree+0xdc/0x5d0 fs/super.c:1489 do_new_mount+0x7a9/0x16f0 fs/namespace.c:3145 path_mount+0xf98/0x26a0 fs/namespace.c:3475 do_mount fs/namespace.c:3488 [inline] __do_sys_mount fs/namespace.c:3697 [inline] __se_sys_mount+0x919/0x9e0 fs/namespace.c:3674 __ia32_sys_mount+0x15b/0x1b0 fs/namespace.c:3674 do_syscall_32_irqs_on arch/x86/entry/common.c:112 [inline] __do_fast_syscall_32+0xa2/0x100 arch/x86/entry/common.c:178 do_fast_syscall_32+0x37/0x80 arch/x86/entry/common.c:203 do_SYSENTER_32+0x1f/0x30 arch/x86/entry/common.c:246 entry_SYSENTER_compat_after_hwframe+0x70/0x82 Uninit was created at: __alloc_pages+0x9a6/0xe00 mm/page_alloc.c:4590 __alloc_pages_node include/linux/gfp.h:238 [inline] alloc_pages_node include/linux/gfp.h:261 [inline] alloc_slab_page mm/slub.c:2190 [inline] allocate_slab mm/slub.c:2354 [inline] new_slab+0x2d7/0x1400 mm/slub.c:2407 ___slab_alloc+0x16b5/0x3970 mm/slub.c:3540 __slab_alloc mm/slub.c:3625 [inline] __slab_alloc_node mm/slub.c:3678 [inline] slab_alloc_node mm/slub.c:3850 [inline] kmem_cache_alloc_lru+0x64d/0xb30 mm/slub.c:3879 alloc_inode_sb include/linux/fs.h:3018 [inline] hfs_alloc_inode+0x5a/0xc0 fs/hfs/super.c:165 alloc_inode+0x83/0x440 fs/inode.c:260 new_inode_pseudo fs/inode.c:1005 [inline] new_inode+0x38/0x4f0 fs/inode.c:1031 hfs_new_inode+0x61/0x1010 fs/hfs/inode.c:186 hfs_mkdir+0x54/0x250 fs/hfs/dir.c:228 vfs_mkdir+0x49a/0x700 fs/namei.c:4126 do_mkdirat+0x529/0x810 fs/namei.c:4149 __do_sys_mkdirat fs/namei.c:4164 [inline] __se_sys_mkdirat fs/namei.c:4162 [inline] __x64_sys_mkdirat+0xc8/0x120 fs/namei.c:4162 do_syscall_x64 arch/x86/entry/common.c:52 [inline] do_syscall_64+0xcf/0x1e0 arch/x86/entry/common.c:83 entry_SYSCALL_64_after_hwframe+0x63/0x6b It missed to initialize .tz_secondswest, .cached_start and .cached_blocks fields in struct hfs_inode_info after hfs_alloc_inode(), fix it. Cc: stable@vger.kernel.org Reported-by: syzbot+3ae6be33a50b5aae4dab@syzkaller.appspotmail.com Closes: https://lore.kernel.org/linux-fsdevel/0000000000005ad04005ee48897f@google.com Signed-off-by: Chao Yu Link: https://lore.kernel.org/r/20240616013841.2217-1-chao@kernel.org Signed-off-by: Christian Brauner Signed-off-by: Greg Kroah-Hartman --- fs/hfs/inode.c | 3 +++ 1 file changed, 3 insertions(+) diff --git a/fs/hfs/inode.c b/fs/hfs/inode.c index 6fbde990e056..3d59cdb31278 100644 --- a/fs/hfs/inode.c +++ b/fs/hfs/inode.c @@ -200,6 +200,7 @@ struct inode *hfs_new_inode(struct inode *dir, const struct qstr *name, umode_t HFS_I(inode)->flags = 0; HFS_I(inode)->rsrc_inode = NULL; HFS_I(inode)->fs_blocks = 0; + HFS_I(inode)->tz_secondswest = sys_tz.tz_minuteswest * 60; if (S_ISDIR(mode)) { inode->i_size = 2; HFS_SB(sb)->folder_count++; @@ -275,6 +276,8 @@ void hfs_inode_read_fork(struct inode *inode, struct hfs_extent *ext, for (count = 0, i = 0; i < 3; i++) count += be16_to_cpu(ext[i].count); HFS_I(inode)->first_blocks = count; + HFS_I(inode)->cached_start = 0; + HFS_I(inode)->cached_blocks = 0; inode->i_size = HFS_I(inode)->phys_size = log_size; HFS_I(inode)->fs_blocks = (log_size + sb->s_blocksize - 1) >> sb->s_blocksize_bits; From 86f4ca8b3b6e5e3441ec0716b0e82a45782395a1 Mon Sep 17 00:00:00 2001 From: Jan Kara Date: Mon, 24 Jun 2024 17:12:56 +0200 Subject: [PATCH 125/342] ext2: Verify bitmap and itable block numbers before using them commit 322a6aff03937aa1ece33b4e46c298eafaf9ac41 upstream. Verify bitmap block numbers and inode table blocks are sane before using them for checking bits in the block bitmap. CC: stable@vger.kernel.org Signed-off-by: Jan Kara Signed-off-by: Greg Kroah-Hartman --- fs/ext2/balloc.c | 11 +++++++++-- 1 file changed, 9 insertions(+), 2 deletions(-) diff --git a/fs/ext2/balloc.c b/fs/ext2/balloc.c index c17ccc19b938..9bf086821eb3 100644 --- a/fs/ext2/balloc.c +++ b/fs/ext2/balloc.c @@ -79,26 +79,33 @@ static int ext2_valid_block_bitmap(struct super_block *sb, ext2_grpblk_t next_zero_bit; ext2_fsblk_t bitmap_blk; ext2_fsblk_t group_first_block; + ext2_grpblk_t max_bit; group_first_block = ext2_group_first_block_no(sb, block_group); + max_bit = ext2_group_last_block_no(sb, block_group) - group_first_block; /* check whether block bitmap block number is set */ bitmap_blk = le32_to_cpu(desc->bg_block_bitmap); offset = bitmap_blk - group_first_block; - if (!ext2_test_bit(offset, bh->b_data)) + if (offset < 0 || offset > max_bit || + !ext2_test_bit(offset, bh->b_data)) /* bad block bitmap */ goto err_out; /* check whether the inode bitmap block number is set */ bitmap_blk = le32_to_cpu(desc->bg_inode_bitmap); offset = bitmap_blk - group_first_block; - if (!ext2_test_bit(offset, bh->b_data)) + if (offset < 0 || offset > max_bit || + !ext2_test_bit(offset, bh->b_data)) /* bad block bitmap */ goto err_out; /* check whether the inode table block number is set */ bitmap_blk = le32_to_cpu(desc->bg_inode_table); offset = bitmap_blk - group_first_block; + if (offset < 0 || offset > max_bit || + offset + EXT2_SB(sb)->s_itb_per_group - 1 > max_bit) + goto err_out; next_zero_bit = ext2_find_next_zero_bit(bh->b_data, offset + EXT2_SB(sb)->s_itb_per_group, offset); From b6ac46a00188cde50ffba233e6efb366354a1de5 Mon Sep 17 00:00:00 2001 From: Ma Ke Date: Tue, 9 Jul 2024 19:33:11 +0800 Subject: [PATCH 126/342] drm/gma500: fix null pointer dereference in cdv_intel_lvds_get_modes commit cb520c3f366c77e8d69e4e2e2781a8ce48d98e79 upstream. In cdv_intel_lvds_get_modes(), the return value of drm_mode_duplicate() is assigned to mode, which will lead to a NULL pointer dereference on failure of drm_mode_duplicate(). Add a check to avoid npd. Cc: stable@vger.kernel.org Fixes: 6a227d5fd6c4 ("gma500: Add support for Cedarview") Signed-off-by: Ma Ke Signed-off-by: Patrik Jakobsson Link: https://patchwork.freedesktop.org/patch/msgid/20240709113311.37168-1-make24@iscas.ac.cn Signed-off-by: Greg Kroah-Hartman --- drivers/gpu/drm/gma500/cdv_intel_lvds.c | 3 +++ 1 file changed, 3 insertions(+) diff --git a/drivers/gpu/drm/gma500/cdv_intel_lvds.c b/drivers/gpu/drm/gma500/cdv_intel_lvds.c index eaaf4efec217..b13c34fa29ed 100644 --- a/drivers/gpu/drm/gma500/cdv_intel_lvds.c +++ b/drivers/gpu/drm/gma500/cdv_intel_lvds.c @@ -310,6 +310,9 @@ static int cdv_intel_lvds_get_modes(struct drm_connector *connector) if (mode_dev->panel_fixed_mode != NULL) { struct drm_display_mode *mode = drm_mode_duplicate(dev, mode_dev->panel_fixed_mode); + if (!mode) + return 0; + drm_mode_probed_add(connector, mode); return 1; } From 6735d02ead7dd3adf74eb8b70aebd09e0ce78ec9 Mon Sep 17 00:00:00 2001 From: Ma Ke Date: Tue, 9 Jul 2024 17:20:11 +0800 Subject: [PATCH 127/342] drm/gma500: fix null pointer dereference in psb_intel_lvds_get_modes commit 2df7aac81070987b0f052985856aa325a38debf6 upstream. In psb_intel_lvds_get_modes(), the return value of drm_mode_duplicate() is assigned to mode, which will lead to a possible NULL pointer dereference on failure of drm_mode_duplicate(). Add a check to avoid npd. Cc: stable@vger.kernel.org Fixes: 89c78134cc54 ("gma500: Add Poulsbo support") Signed-off-by: Ma Ke Signed-off-by: Patrik Jakobsson Link: https://patchwork.freedesktop.org/patch/msgid/20240709092011.3204970-1-make24@iscas.ac.cn Signed-off-by: Greg Kroah-Hartman --- drivers/gpu/drm/gma500/psb_intel_lvds.c | 3 +++ 1 file changed, 3 insertions(+) diff --git a/drivers/gpu/drm/gma500/psb_intel_lvds.c b/drivers/gpu/drm/gma500/psb_intel_lvds.c index 063c66bb946d..889964efe62d 100644 --- a/drivers/gpu/drm/gma500/psb_intel_lvds.c +++ b/drivers/gpu/drm/gma500/psb_intel_lvds.c @@ -508,6 +508,9 @@ static int psb_intel_lvds_get_modes(struct drm_connector *connector) if (mode_dev->panel_fixed_mode != NULL) { struct drm_display_mode *mode = drm_mode_duplicate(dev, mode_dev->panel_fixed_mode); + if (!mode) + return 0; + drm_mode_probed_add(connector, mode); return 1; } From 748e9ad7c0c238b3246548d53740dee75d85544f Mon Sep 17 00:00:00 2001 From: Shreyas Deodhar Date: Wed, 10 Jul 2024 22:40:54 +0530 Subject: [PATCH 128/342] scsi: qla2xxx: Fix optrom version displayed in FDMI commit 348744f27a35e087acc9378bf53537fbfb072775 upstream. Bios version was popluated for FDMI response. Systems with EFI would show optrom version as 0. EFI version is populated here and BIOS version is already displayed under FDMI_HBA_BOOT_BIOS_NAME. Cc: stable@vger.kernel.org Signed-off-by: Shreyas Deodhar Signed-off-by: Nilesh Javali Link: https://lore.kernel.org/r/20240710171057.35066-9-njavali@marvell.com Reviewed-by: Himanshu Madhani Signed-off-by: Martin K. Petersen Signed-off-by: Greg Kroah-Hartman --- drivers/scsi/qla2xxx/qla_gs.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/drivers/scsi/qla2xxx/qla_gs.c b/drivers/scsi/qla2xxx/qla_gs.c index d9ac17dbad78..b08a92d346f5 100644 --- a/drivers/scsi/qla2xxx/qla_gs.c +++ b/drivers/scsi/qla2xxx/qla_gs.c @@ -1708,7 +1708,7 @@ qla2x00_hba_attributes(scsi_qla_host_t *vha, void *entries, eiter->type = cpu_to_be16(FDMI_HBA_OPTION_ROM_VERSION); alen = scnprintf( eiter->a.orom_version, sizeof(eiter->a.orom_version), - "%d.%02d", ha->bios_revision[1], ha->bios_revision[0]); + "%d.%02d", ha->efi_revision[1], ha->efi_revision[0]); alen += FDMI_ATTR_ALIGNMENT(alen); alen += FDMI_ATTR_TYPELEN(eiter); eiter->len = cpu_to_be16(alen); From 9ce89824ff04d261fc855e0ca6e6025251d9fa40 Mon Sep 17 00:00:00 2001 From: Sung Joon Kim Date: Mon, 8 Jul 2024 19:29:49 -0400 Subject: [PATCH 129/342] drm/amd/display: Check for NULL pointer commit 4ab68e168ae1695f7c04fae98930740aaf7c50fa upstream. [why & how] Need to make sure plane_state is initialized before accessing its members. Cc: Mario Limonciello Cc: Alex Deucher Cc: stable@vger.kernel.org Reviewed-by: Xi (Alex) Liu Signed-off-by: Sung Joon Kim Signed-off-by: Aurabindo Pillai Signed-off-by: Alex Deucher (cherry picked from commit 295d91cbc700651782a60572f83c24861607b648) Signed-off-by: Greg Kroah-Hartman --- drivers/gpu/drm/amd/display/dc/core/dc_surface.c | 3 ++- 1 file changed, 2 insertions(+), 1 deletion(-) diff --git a/drivers/gpu/drm/amd/display/dc/core/dc_surface.c b/drivers/gpu/drm/amd/display/dc/core/dc_surface.c index 3d7d27435f15..98391ba103d6 100644 --- a/drivers/gpu/drm/amd/display/dc/core/dc_surface.c +++ b/drivers/gpu/drm/amd/display/dc/core/dc_surface.c @@ -154,7 +154,8 @@ const struct dc_plane_status *dc_plane_get_status( if (pipe_ctx->plane_state != plane_state) continue; - pipe_ctx->plane_state->status.is_flip_pending = false; + if (pipe_ctx->plane_state) + pipe_ctx->plane_state->status.is_flip_pending = false; break; } From eb46367187a446fea41897a42d78a32b5f8e49a3 Mon Sep 17 00:00:00 2001 From: Pierre Gondois Date: Wed, 6 Dec 2023 10:00:43 +0100 Subject: [PATCH 130/342] sched/fair: Use all little CPUs for CPU-bound workloads commit 3af7524b14198f5159a86692d57a9f28ec9375ce upstream. Running N CPU-bound tasks on an N CPUs platform: - with asymmetric CPU capacity - not being a DynamIq system (i.e. having a PKG level sched domain without the SD_SHARE_PKG_RESOURCES flag set) .. might result in a task placement where two tasks run on a big CPU and none on a little CPU. This placement could be more optimal by using all CPUs. Testing platform: Juno-r2: - 2 big CPUs (1-2), maximum capacity of 1024 - 4 little CPUs (0,3-5), maximum capacity of 383 Testing workload ([1]): Spawn 6 CPU-bound tasks. During the first 100ms (step 1), each tasks is affine to a CPU, except for: - one little CPU which is left idle. - one big CPU which has 2 tasks affine. After the 100ms (step 2), remove the cpumask affinity. Behavior before the patch: During step 2, the load balancer running from the idle CPU tags sched domains as: - little CPUs: 'group_has_spare'. Cf. group_has_capacity() and group_is_overloaded(), 3 CPU-bound tasks run on a 4 CPUs sched-domain, and the idle CPU provides enough spare capacity regarding the imbalance_pct - big CPUs: 'group_overloaded'. Indeed, 3 tasks run on a 2 CPUs sched-domain, so the following path is used: group_is_overloaded() \-if (sgs->sum_nr_running <= sgs->group_weight) return true; The following path which would change the migration type to 'migrate_task' is not taken: calculate_imbalance() \-if (env->idle != CPU_NOT_IDLE && env->imbalance == 0) as the local group has some spare capacity, so the imbalance is not 0. The migration type requested is 'migrate_util' and the busiest runqueue is the big CPU's runqueue having 2 tasks (each having a utilization of 512). The idle little CPU cannot pull one of these task as its capacity is too small for the task. The following path is used: detach_tasks() \-case migrate_util: \-if (util > env->imbalance) goto next; After the patch: As the number of failed balancing attempts grows (with 'nr_balance_failed'), progressively make it easier to migrate a big task to the idling little CPU. A similar mechanism is used for the 'migrate_load' migration type. Improvement: Running the testing workload [1] with the step 2 representing a ~10s load for a big CPU: Before patch: ~19.3s After patch: ~18s (-6.7%) Similar issue reported at: https://lore.kernel.org/lkml/20230716014125.139577-1-qyousef@layalina.io/ Suggested-by: Vincent Guittot Signed-off-by: Pierre Gondois Signed-off-by: Ingo Molnar Reviewed-by: Vincent Guittot Reviewed-by: Dietmar Eggemann Acked-by: Qais Yousef Link: https://lore.kernel.org/r/20231206090043.634697-1-pierre.gondois@arm.com Signed-off-by: Greg Kroah-Hartman --- kernel/sched/fair.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/kernel/sched/fair.c b/kernel/sched/fair.c index 376f5c6a933d..a6a755aec32b 100644 --- a/kernel/sched/fair.c +++ b/kernel/sched/fair.c @@ -7950,7 +7950,7 @@ static int detach_tasks(struct lb_env *env) case migrate_util: util = task_util_est(p); - if (util > env->imbalance) + if (shr_bound(util, env->sd->nr_balance_failed) > env->imbalance) goto next; env->imbalance -= util; From 973155ca67fef3038d5d752f7076c45a010e1b43 Mon Sep 17 00:00:00 2001 From: Fedor Pchelkin Date: Thu, 1 Feb 2024 17:24:48 +0300 Subject: [PATCH 131/342] apparmor: use kvfree_sensitive to free data->data commit 2bc73505a5cd2a18a7a542022722f136c19e3b87 upstream. Inside unpack_profile() data->data is allocated using kvmemdup() so it should be freed with the corresponding kvfree_sensitive(). Also add missing data->data release for rhashtable insertion failure path in unpack_profile(). Found by Linux Verification Center (linuxtesting.org). Fixes: e025be0f26d5 ("apparmor: support querying extended trusted helper extra data") Cc: stable@vger.kernel.org Signed-off-by: Fedor Pchelkin Signed-off-by: John Johansen Signed-off-by: Greg Kroah-Hartman --- security/apparmor/policy.c | 2 +- security/apparmor/policy_unpack.c | 1 + 2 files changed, 2 insertions(+), 1 deletion(-) diff --git a/security/apparmor/policy.c b/security/apparmor/policy.c index fcf22577f606..e59bdb750ef0 100644 --- a/security/apparmor/policy.c +++ b/security/apparmor/policy.c @@ -187,7 +187,7 @@ static void aa_free_data(void *ptr, void *arg) { struct aa_data *data = ptr; - kfree_sensitive(data->data); + kvfree_sensitive(data->data, data->size); kfree_sensitive(data->key); kfree_sensitive(data); } diff --git a/security/apparmor/policy_unpack.c b/security/apparmor/policy_unpack.c index 6c2a536173b5..93fcafdaa548 100644 --- a/security/apparmor/policy_unpack.c +++ b/security/apparmor/policy_unpack.c @@ -915,6 +915,7 @@ static struct aa_profile *unpack_profile(struct aa_ext *e, char **ns_name) if (rhashtable_insert_fast(profile->data, &data->head, profile->data->p)) { + kvfree_sensitive(data->data, data->size); kfree_sensitive(data->key); kfree_sensitive(data); info = "failed to insert data to table"; From 1fd27cc6f0a540f97d29bd695521a3bb57d02f33 Mon Sep 17 00:00:00 2001 From: Frederic Weisbecker Date: Fri, 21 Jun 2024 11:15:58 +0200 Subject: [PATCH 132/342] task_work: s/task_work_cancel()/task_work_cancel_func()/ commit 68cbd415dd4b9c5b9df69f0f091879e56bf5907a upstream. A proper task_work_cancel() API that actually cancels a callback and not *any* callback pointing to a given function is going to be needed for perf events event freeing. Do the appropriate rename to prepare for that. Signed-off-by: Frederic Weisbecker Signed-off-by: Peter Zijlstra (Intel) Cc: stable@vger.kernel.org Link: https://lore.kernel.org/r/20240621091601.18227-2-frederic@kernel.org Signed-off-by: Greg Kroah-Hartman --- include/linux/task_work.h | 2 +- kernel/irq/manage.c | 2 +- kernel/task_work.c | 10 +++++----- security/keys/keyctl.c | 2 +- 4 files changed, 8 insertions(+), 8 deletions(-) diff --git a/include/linux/task_work.h b/include/linux/task_work.h index 5b8a93f288bb..da581770b89d 100644 --- a/include/linux/task_work.h +++ b/include/linux/task_work.h @@ -24,7 +24,7 @@ int task_work_add(struct task_struct *task, struct callback_head *twork, struct callback_head *task_work_cancel_match(struct task_struct *task, bool (*match)(struct callback_head *, void *data), void *data); -struct callback_head *task_work_cancel(struct task_struct *, task_work_func_t); +struct callback_head *task_work_cancel_func(struct task_struct *, task_work_func_t); void task_work_run(void); static inline void exit_task_work(struct task_struct *task) diff --git a/kernel/irq/manage.c b/kernel/irq/manage.c index 0159925054fa..c7f4f948f17e 100644 --- a/kernel/irq/manage.c +++ b/kernel/irq/manage.c @@ -1230,7 +1230,7 @@ static int irq_thread(void *data) * synchronize_hardirq(). So neither IRQTF_RUNTHREAD nor the * oneshot mask bit can be set. */ - task_work_cancel(current, irq_thread_dtor); + task_work_cancel_func(current, irq_thread_dtor); return 0; } diff --git a/kernel/task_work.c b/kernel/task_work.c index e9316198c64b..6ab445aebcea 100644 --- a/kernel/task_work.c +++ b/kernel/task_work.c @@ -101,9 +101,9 @@ static bool task_work_func_match(struct callback_head *cb, void *data) } /** - * task_work_cancel - cancel a pending work added by task_work_add() - * @task: the task which should execute the work - * @func: identifies the work to remove + * task_work_cancel_func - cancel a pending work matching a function added by task_work_add() + * @task: the task which should execute the func's work + * @func: identifies the func to match with a work to remove * * Find the last queued pending work with ->func == @func and remove * it from queue. @@ -112,7 +112,7 @@ static bool task_work_func_match(struct callback_head *cb, void *data) * The found work or NULL if not found. */ struct callback_head * -task_work_cancel(struct task_struct *task, task_work_func_t func) +task_work_cancel_func(struct task_struct *task, task_work_func_t func) { return task_work_cancel_match(task, task_work_func_match, func); } @@ -149,7 +149,7 @@ void task_work_run(void) if (!work) break; /* - * Synchronize with task_work_cancel(). It can not remove + * Synchronize with task_work_cancel_match(). It can not remove * the first entry == work, cmpxchg(task_works) must fail. * But it can remove another entry from the ->next list. */ diff --git a/security/keys/keyctl.c b/security/keys/keyctl.c index e3ffaf5ad639..c283474ecea5 100644 --- a/security/keys/keyctl.c +++ b/security/keys/keyctl.c @@ -1694,7 +1694,7 @@ long keyctl_session_to_parent(void) goto unlock; /* cancel an already pending keyring replacement */ - oldwork = task_work_cancel(parent, key_change_session_keyring); + oldwork = task_work_cancel_func(parent, key_change_session_keyring); /* the replacement session keyring is applied just prior to userspace * restarting */ From 5c59cb8dd95430dde203c353166926f746f51b09 Mon Sep 17 00:00:00 2001 From: Frederic Weisbecker Date: Fri, 21 Jun 2024 11:15:59 +0200 Subject: [PATCH 133/342] task_work: Introduce task_work_cancel() again commit f409530e4db9dd11b88cb7703c97c8f326ff6566 upstream. Re-introduce task_work_cancel(), this time to cancel an actual callback and not *any* callback pointing to a given function. This is going to be needed for perf events event freeing. Signed-off-by: Frederic Weisbecker Signed-off-by: Peter Zijlstra (Intel) Cc: stable@vger.kernel.org Link: https://lore.kernel.org/r/20240621091601.18227-3-frederic@kernel.org Signed-off-by: Greg Kroah-Hartman --- include/linux/task_work.h | 1 + kernel/task_work.c | 24 ++++++++++++++++++++++++ 2 files changed, 25 insertions(+) diff --git a/include/linux/task_work.h b/include/linux/task_work.h index da581770b89d..ad9432313627 100644 --- a/include/linux/task_work.h +++ b/include/linux/task_work.h @@ -25,6 +25,7 @@ int task_work_add(struct task_struct *task, struct callback_head *twork, struct callback_head *task_work_cancel_match(struct task_struct *task, bool (*match)(struct callback_head *, void *data), void *data); struct callback_head *task_work_cancel_func(struct task_struct *, task_work_func_t); +bool task_work_cancel(struct task_struct *task, struct callback_head *cb); void task_work_run(void); static inline void exit_task_work(struct task_struct *task) diff --git a/kernel/task_work.c b/kernel/task_work.c index 6ab445aebcea..6138e13dce3d 100644 --- a/kernel/task_work.c +++ b/kernel/task_work.c @@ -117,6 +117,30 @@ task_work_cancel_func(struct task_struct *task, task_work_func_t func) return task_work_cancel_match(task, task_work_func_match, func); } +static bool task_work_match(struct callback_head *cb, void *data) +{ + return cb == data; +} + +/** + * task_work_cancel - cancel a pending work added by task_work_add() + * @task: the task which should execute the work + * @cb: the callback to remove if queued + * + * Remove a callback from a task's queue if queued. + * + * RETURNS: + * True if the callback was queued and got cancelled, false otherwise. + */ +bool task_work_cancel(struct task_struct *task, struct callback_head *cb) +{ + struct callback_head *ret; + + ret = task_work_cancel_match(task, task_work_match, cb); + + return ret == cb; +} + /** * task_work_run - execute the works added by task_work_add() * From 2199e157a465aaf98294d3932797ecd7fce942d5 Mon Sep 17 00:00:00 2001 From: Jan Kara Date: Mon, 17 Jun 2024 17:41:52 +0200 Subject: [PATCH 134/342] udf: Avoid using corrupted block bitmap buffer commit a90d4471146de21745980cba51ce88e7926bcc4f upstream. When the filesystem block bitmap is corrupted, we detect the corruption while loading the bitmap and fail the allocation with error. However the next allocation from the same bitmap will notice the bitmap buffer is already loaded and tries to allocate from the bitmap with mixed results (depending on the exact nature of the bitmap corruption). Fix the problem by using BH_verified bit to indicate whether the bitmap is valid or not. Reported-by: syzbot+5f682cd029581f9edfd1@syzkaller.appspotmail.com CC: stable@vger.kernel.org Link: https://patch.msgid.link/20240617154201.29512-2-jack@suse.cz Fixes: 1e0d4adf17e7 ("udf: Check consistency of Space Bitmap Descriptor") Signed-off-by: Jan Kara Signed-off-by: Greg Kroah-Hartman --- fs/udf/balloc.c | 15 +++++++++++++-- fs/udf/super.c | 3 ++- 2 files changed, 15 insertions(+), 3 deletions(-) diff --git a/fs/udf/balloc.c b/fs/udf/balloc.c index f416b7fe092f..c4c18eeacb60 100644 --- a/fs/udf/balloc.c +++ b/fs/udf/balloc.c @@ -68,8 +68,12 @@ static int read_block_bitmap(struct super_block *sb, } for (i = 0; i < count; i++) - if (udf_test_bit(i + off, bh->b_data)) + if (udf_test_bit(i + off, bh->b_data)) { + bitmap->s_block_bitmap[bitmap_nr] = + ERR_PTR(-EFSCORRUPTED); + brelse(bh); return -EFSCORRUPTED; + } return 0; } @@ -85,8 +89,15 @@ static int __load_block_bitmap(struct super_block *sb, block_group, nr_groups); } - if (bitmap->s_block_bitmap[block_group]) + if (bitmap->s_block_bitmap[block_group]) { + /* + * The bitmap failed verification in the past. No point in + * trying again. + */ + if (IS_ERR(bitmap->s_block_bitmap[block_group])) + return PTR_ERR(bitmap->s_block_bitmap[block_group]); return block_group; + } retval = read_block_bitmap(sb, bitmap, block_group, block_group); if (retval < 0) diff --git a/fs/udf/super.c b/fs/udf/super.c index 4af9ce34ee80..1939678f0b62 100644 --- a/fs/udf/super.c +++ b/fs/udf/super.c @@ -266,7 +266,8 @@ static void udf_sb_free_bitmap(struct udf_bitmap *bitmap) int nr_groups = bitmap->s_nr_groups; for (i = 0; i < nr_groups; i++) - brelse(bitmap->s_block_bitmap[i]); + if (!IS_ERR_OR_NULL(bitmap->s_block_bitmap[i])) + brelse(bitmap->s_block_bitmap[i]); kvfree(bitmap); } From 38463947850ccdd0a97338046ff3cac6b482d6c9 Mon Sep 17 00:00:00 2001 From: Paolo Pisati Date: Sat, 1 Jun 2024 17:32:54 +0200 Subject: [PATCH 135/342] m68k: amiga: Turn off Warp1260 interrupts during boot commit 1d8491d3e726984343dd8c3cdbe2f2b47cfdd928 upstream. On an Amiga 1200 equipped with a Warp1260 accelerator, an interrupt storm coming from the accelerator board causes the machine to crash in local_irq_enable() or auto_irq_enable(). Disabling interrupts for the Warp1260 in amiga_parse_bootinfo() fixes the problem. Link: https://lore.kernel.org/r/ZkjwzVwYeQtyAPrL@amaterasu.local Cc: stable Signed-off-by: Paolo Pisati Reviewed-by: Michael Schmitz Reviewed-by: Geert Uytterhoeven Link: https://lore.kernel.org/r/20240601153254.186225-1-p.pisati@gmail.com Signed-off-by: Geert Uytterhoeven Signed-off-by: Greg Kroah-Hartman --- arch/m68k/amiga/config.c | 9 +++++++++ include/uapi/linux/zorro_ids.h | 3 +++ 2 files changed, 12 insertions(+) diff --git a/arch/m68k/amiga/config.c b/arch/m68k/amiga/config.c index bee9f240f35d..c92c1e559da0 100644 --- a/arch/m68k/amiga/config.c +++ b/arch/m68k/amiga/config.c @@ -179,6 +179,15 @@ int __init amiga_parse_bootinfo(const struct bi_record *record) dev->slotsize = be16_to_cpu(cd->cd_SlotSize); dev->boardaddr = be32_to_cpu(cd->cd_BoardAddr); dev->boardsize = be32_to_cpu(cd->cd_BoardSize); + + /* CS-LAB Warp 1260 workaround */ + if (be16_to_cpu(dev->rom.er_Manufacturer) == ZORRO_MANUF(ZORRO_PROD_CSLAB_WARP_1260) && + dev->rom.er_Product == ZORRO_PROD(ZORRO_PROD_CSLAB_WARP_1260)) { + + /* turn off all interrupts */ + pr_info("Warp 1260 card detected: applying interrupt storm workaround\n"); + *(uint32_t *)(dev->boardaddr + 0x1000) = 0xfff; + } } else pr_warn("amiga_parse_bootinfo: too many AutoConfig devices\n"); #endif /* CONFIG_ZORRO */ diff --git a/include/uapi/linux/zorro_ids.h b/include/uapi/linux/zorro_ids.h index 6e574d7b7d79..393f2ee9c042 100644 --- a/include/uapi/linux/zorro_ids.h +++ b/include/uapi/linux/zorro_ids.h @@ -449,6 +449,9 @@ #define ZORRO_PROD_VMC_ISDN_BLASTER_Z2 ZORRO_ID(VMC, 0x01, 0) #define ZORRO_PROD_VMC_HYPERCOM_4 ZORRO_ID(VMC, 0x02, 0) +#define ZORRO_MANUF_CSLAB 0x1400 +#define ZORRO_PROD_CSLAB_WARP_1260 ZORRO_ID(CSLAB, 0x65, 0) + #define ZORRO_MANUF_INFORMATION 0x157C #define ZORRO_PROD_INFORMATION_ISDN_ENGINE_I ZORRO_ID(INFORMATION, 0x64, 0) From 42d420517072028fb0eb852c358056b7717ba5aa Mon Sep 17 00:00:00 2001 From: Baokun Li Date: Tue, 2 Jul 2024 21:23:48 +0800 Subject: [PATCH 136/342] ext4: check dot and dotdot of dx_root before making dir indexed commit 50ea741def587a64e08879ce6c6a30131f7111e7 upstream. Syzbot reports a issue as follows: ============================================ BUG: unable to handle page fault for address: ffffed11022e24fe PGD 23ffee067 P4D 23ffee067 PUD 0 Oops: Oops: 0000 [#1] PREEMPT SMP KASAN PTI CPU: 0 PID: 5079 Comm: syz-executor306 Not tainted 6.10.0-rc5-g55027e689933 #0 Call Trace: make_indexed_dir+0xdaf/0x13c0 fs/ext4/namei.c:2341 ext4_add_entry+0x222a/0x25d0 fs/ext4/namei.c:2451 ext4_rename fs/ext4/namei.c:3936 [inline] ext4_rename2+0x26e5/0x4370 fs/ext4/namei.c:4214 [...] ============================================ The immediate cause of this problem is that there is only one valid dentry for the block to be split during do_split, so split==0 results in out of bounds accesses to the map triggering the issue. do_split unsigned split dx_make_map count = 1 split = count/2 = 0; continued = hash2 == map[split - 1].hash; ---> map[4294967295] The maximum length of a filename is 255 and the minimum block size is 1024, so it is always guaranteed that the number of entries is greater than or equal to 2 when do_split() is called. But syzbot's crafted image has no dot and dotdot in dir, and the dentry distribution in dirblock is as follows: bus dentry1 hole dentry2 free |xx--|xx-------------|...............|xx-------------|...............| 0 12 (8+248)=256 268 256 524 (8+256)=264 788 236 1024 So when renaming dentry1 increases its name_len length by 1, neither hole nor free is sufficient to hold the new dentry, and make_indexed_dir() is called. In make_indexed_dir() it is assumed that the first two entries of the dirblock must be dot and dotdot, so bus and dentry1 are left in dx_root because they are treated as dot and dotdot, and only dentry2 is moved to the new leaf block. That's why count is equal to 1. Therefore add the ext4_check_dx_root() helper function to add more sanity checks to dot and dotdot before starting the conversion to avoid the above issue. Reported-by: syzbot+ae688d469e36fb5138d0@syzkaller.appspotmail.com Closes: https://syzkaller.appspot.com/bug?extid=ae688d469e36fb5138d0 Fixes: ac27a0ec112a ("[PATCH] ext4: initial copy of files from ext3") Cc: stable@kernel.org Signed-off-by: Baokun Li Reviewed-by: Jan Kara Link: https://patch.msgid.link/20240702132349.2600605-2-libaokun@huaweicloud.com Signed-off-by: Theodore Ts'o Signed-off-by: Greg Kroah-Hartman --- fs/ext4/namei.c | 56 ++++++++++++++++++++++++++++++++++++++++++++----- 1 file changed, 51 insertions(+), 5 deletions(-) diff --git a/fs/ext4/namei.c b/fs/ext4/namei.c index af0801593abb..16676c4920e9 100644 --- a/fs/ext4/namei.c +++ b/fs/ext4/namei.c @@ -2098,6 +2098,52 @@ static int add_dirent_to_buf(handle_t *handle, struct ext4_filename *fname, return err ? err : err2; } +static bool ext4_check_dx_root(struct inode *dir, struct dx_root *root) +{ + struct fake_dirent *fde; + const char *error_msg; + unsigned int rlen; + unsigned int blocksize = dir->i_sb->s_blocksize; + char *blockend = (char *)root + dir->i_sb->s_blocksize; + + fde = &root->dot; + if (unlikely(fde->name_len != 1)) { + error_msg = "invalid name_len for '.'"; + goto corrupted; + } + if (unlikely(strncmp(root->dot_name, ".", fde->name_len))) { + error_msg = "invalid name for '.'"; + goto corrupted; + } + rlen = ext4_rec_len_from_disk(fde->rec_len, blocksize); + if (unlikely((char *)fde + rlen >= blockend)) { + error_msg = "invalid rec_len for '.'"; + goto corrupted; + } + + fde = &root->dotdot; + if (unlikely(fde->name_len != 2)) { + error_msg = "invalid name_len for '..'"; + goto corrupted; + } + if (unlikely(strncmp(root->dotdot_name, "..", fde->name_len))) { + error_msg = "invalid name for '..'"; + goto corrupted; + } + rlen = ext4_rec_len_from_disk(fde->rec_len, blocksize); + if (unlikely((char *)fde + rlen >= blockend)) { + error_msg = "invalid rec_len for '..'"; + goto corrupted; + } + + return true; + +corrupted: + EXT4_ERROR_INODE(dir, "Corrupt dir, %s, running e2fsck is recommended", + error_msg); + return false; +} + /* * This converts a one block unindexed directory to a 3 block indexed * directory, and adds the dentry to the indexed directory. @@ -2131,17 +2177,17 @@ static int make_indexed_dir(handle_t *handle, struct ext4_filename *fname, brelse(bh); return retval; } + root = (struct dx_root *) bh->b_data; + if (!ext4_check_dx_root(dir, root)) { + brelse(bh); + return -EFSCORRUPTED; + } /* The 0th block becomes the root, move the dirents out */ fde = &root->dotdot; de = (struct ext4_dir_entry_2 *)((char *)fde + ext4_rec_len_from_disk(fde->rec_len, blocksize)); - if ((char *) de >= (((char *) root) + blocksize)) { - EXT4_ERROR_INODE(dir, "invalid rec_len for '..'"); - brelse(bh); - return -EFSCORRUPTED; - } len = ((char *) root) + (blocksize - csum_size) - (char *) de; /* Allocate new block for the 0th block's dirents */ From de2a011a13a46468a6e8259db58b1b62071fe136 Mon Sep 17 00:00:00 2001 From: Baokun Li Date: Tue, 2 Jul 2024 21:23:49 +0800 Subject: [PATCH 137/342] ext4: make sure the first directory block is not a hole commit f9ca51596bbfd0f9c386dd1c613c394c78d9e5e6 upstream. The syzbot constructs a directory that has no dirblock but is non-inline, i.e. the first directory block is a hole. And no errors are reported when creating files in this directory in the following flow. ext4_mknod ... ext4_add_entry // Read block 0 ext4_read_dirblock(dir, block, DIRENT) bh = ext4_bread(NULL, inode, block, 0) if (!bh && (type == INDEX || type == DIRENT_HTREE)) // The first directory block is a hole // But type == DIRENT, so no error is reported. After that, we get a directory block without '.' and '..' but with a valid dentry. This may cause some code that relies on dot or dotdot (such as make_indexed_dir()) to crash. Therefore when ext4_read_dirblock() finds that the first directory block is a hole report that the filesystem is corrupted and return an error to avoid loading corrupted data from disk causing something bad. Reported-by: syzbot+ae688d469e36fb5138d0@syzkaller.appspotmail.com Closes: https://syzkaller.appspot.com/bug?extid=ae688d469e36fb5138d0 Fixes: 4e19d6b65fb4 ("ext4: allow directory holes") Cc: stable@kernel.org Signed-off-by: Baokun Li Reviewed-by: Jan Kara Link: https://patch.msgid.link/20240702132349.2600605-3-libaokun@huaweicloud.com Signed-off-by: Theodore Ts'o Signed-off-by: Greg Kroah-Hartman --- fs/ext4/namei.c | 17 ++++++----------- 1 file changed, 6 insertions(+), 11 deletions(-) diff --git a/fs/ext4/namei.c b/fs/ext4/namei.c index 16676c4920e9..bf312f94c3bf 100644 --- a/fs/ext4/namei.c +++ b/fs/ext4/namei.c @@ -145,10 +145,11 @@ static struct buffer_head *__ext4_read_dirblock(struct inode *inode, return bh; } - if (!bh && (type == INDEX || type == DIRENT_HTREE)) { + /* The first directory block must not be a hole. */ + if (!bh && (type == INDEX || type == DIRENT_HTREE || block == 0)) { ext4_error_inode(inode, func, line, block, - "Directory hole found for htree %s block", - (type == INDEX) ? "index" : "leaf"); + "Directory hole found for htree %s block %u", + (type == INDEX) ? "index" : "leaf", block); return ERR_PTR(-EFSCORRUPTED); } if (!bh) @@ -2977,10 +2978,7 @@ bool ext4_empty_dir(struct inode *inode) EXT4_ERROR_INODE(inode, "invalid size"); return false; } - /* The first directory block must not be a hole, - * so treat it as DIRENT_HTREE - */ - bh = ext4_read_dirblock(inode, 0, DIRENT_HTREE); + bh = ext4_read_dirblock(inode, 0, EITHER); if (IS_ERR(bh)) return false; @@ -3611,10 +3609,7 @@ static struct buffer_head *ext4_get_first_dir_block(handle_t *handle, struct ext4_dir_entry_2 *de; unsigned int offset; - /* The first directory block must not be a hole, so - * treat it as DIRENT_HTREE - */ - bh = ext4_read_dirblock(inode, 0, DIRENT_HTREE); + bh = ext4_read_dirblock(inode, 0, EITHER); if (IS_ERR(bh)) { *retval = PTR_ERR(bh); return NULL; From 35f8c9ac0cd3d128dd6b1068ed02a650b2f7f327 Mon Sep 17 00:00:00 2001 From: Rafael Beims Date: Fri, 10 May 2024 13:04:58 +0200 Subject: [PATCH 138/342] wifi: mwifiex: Fix interface type change commit a17b9f590f6ec2b9f1b12b1db3bf1d181de6b272 upstream. When changing the interface type we also need to update the bss_num, the driver private data is searched based on a unique (bss_type, bss_num) tuple, therefore every time bss_type changes, bss_num must also change. This fixes for example an issue in which, after the mode changed, a wireless scan on the changed interface would not finish, leading to repeated -EBUSY messages to userspace when other scan requests were sent. Fixes: c606008b7062 ("mwifiex: Properly initialize private structure on interface type changes") Cc: stable@vger.kernel.org Signed-off-by: Rafael Beims Signed-off-by: Francesco Dolcini Signed-off-by: Kalle Valo Link: https://msgid.link/20240510110458.15475-1-francesco@dolcini.it Signed-off-by: Greg Kroah-Hartman --- drivers/net/wireless/marvell/mwifiex/cfg80211.c | 2 ++ 1 file changed, 2 insertions(+) diff --git a/drivers/net/wireless/marvell/mwifiex/cfg80211.c b/drivers/net/wireless/marvell/mwifiex/cfg80211.c index e1196c565a62..03ba8ed995bf 100644 --- a/drivers/net/wireless/marvell/mwifiex/cfg80211.c +++ b/drivers/net/wireless/marvell/mwifiex/cfg80211.c @@ -930,6 +930,8 @@ mwifiex_init_new_priv_params(struct mwifiex_private *priv, return -EOPNOTSUPP; } + priv->bss_num = mwifiex_get_unused_bss_num(adapter, priv->bss_type); + spin_lock_irqsave(&adapter->main_proc_lock, flags); adapter->main_locked = false; spin_unlock_irqrestore(&adapter->main_proc_lock, flags); From 6d5223be13f22511740a63567c997c78591f4af6 Mon Sep 17 00:00:00 2001 From: =?UTF-8?q?Ilpo=20J=C3=A4rvinen?= Date: Mon, 27 May 2024 16:27:00 +0300 Subject: [PATCH 139/342] leds: ss4200: Convert PCIBIOS_* return codes to errnos MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit commit ce068e83976140badb19c7f1307926b4b562fac4 upstream. ich7_lpc_probe() uses pci_read_config_dword() that returns PCIBIOS_* codes. The error handling code assumes incorrectly it's a normal errno and checks for < 0. The return code is returned from the probe function as is but probe functions should return normal errnos. Remove < 0 from the check and convert PCIBIOS_* returns code using pcibios_err_to_errno() into normal errno before returning it. Fixes: a328e95b82c1 ("leds: LED driver for Intel NAS SS4200 series (v5)") Cc: Signed-off-by: Ilpo Järvinen Link: https://lore.kernel.org/r/20240527132700.14260-1-ilpo.jarvinen@linux.intel.com Signed-off-by: Lee Jones Signed-off-by: Greg Kroah-Hartman --- drivers/leds/leds-ss4200.c | 7 +++++-- 1 file changed, 5 insertions(+), 2 deletions(-) diff --git a/drivers/leds/leds-ss4200.c b/drivers/leds/leds-ss4200.c index 245de443fe9c..833bb721a8e0 100644 --- a/drivers/leds/leds-ss4200.c +++ b/drivers/leds/leds-ss4200.c @@ -356,8 +356,10 @@ static int ich7_lpc_probe(struct pci_dev *dev, nas_gpio_pci_dev = dev; status = pci_read_config_dword(dev, PMBASE, &g_pm_io_base); - if (status) + if (status) { + status = pcibios_err_to_errno(status); goto out; + } g_pm_io_base &= 0x00000ff80; status = pci_read_config_dword(dev, GPIO_CTRL, &gc); @@ -369,8 +371,9 @@ static int ich7_lpc_probe(struct pci_dev *dev, } status = pci_read_config_dword(dev, GPIO_BASE, &nas_gpio_io_base); - if (0 > status) { + if (status) { dev_info(&dev->dev, "Unable to read GPIOBASE.\n"); + status = pcibios_err_to_errno(status); goto out; } dev_dbg(&dev->dev, ": GPIOBASE = 0x%08x\n", nas_gpio_io_base); From cdbcb4e9f69b66cbfbfc59e6168aea84b715a440 Mon Sep 17 00:00:00 2001 From: Jan Kara Date: Mon, 24 Jun 2024 19:01:17 +0200 Subject: [PATCH 140/342] jbd2: make jbd2_journal_get_max_txn_bufs() internal commit 4aa99c71e42ad60178c1154ec24e3df9c684fb67 upstream. There's no reason to have jbd2_journal_get_max_txn_bufs() public function. Currently all users are internal and can use journal->j_max_transaction_buffers instead. This saves some unnecessary recomputations of the limit as a bonus which becomes important as this function gets more complex in the following patch. CC: stable@vger.kernel.org Signed-off-by: Jan Kara Reviewed-by: Zhang Yi Link: https://patch.msgid.link/20240624170127.3253-1-jack@suse.cz Signed-off-by: Theodore Ts'o Signed-off-by: Greg Kroah-Hartman --- fs/jbd2/commit.c | 2 +- fs/jbd2/journal.c | 5 +++++ include/linux/jbd2.h | 5 ----- 3 files changed, 6 insertions(+), 6 deletions(-) diff --git a/fs/jbd2/commit.c b/fs/jbd2/commit.c index db137671a41f..7d548821854e 100644 --- a/fs/jbd2/commit.c +++ b/fs/jbd2/commit.c @@ -813,7 +813,7 @@ void jbd2_journal_commit_transaction(journal_t *journal) if (first_block < journal->j_tail) freed += journal->j_last - journal->j_first; /* Update tail only if we free significant amount of space */ - if (freed < jbd2_journal_get_max_txn_bufs(journal)) + if (freed < journal->j_max_transaction_buffers) update_tail = 0; } J_ASSERT(commit_transaction->t_state == T_COMMIT); diff --git a/fs/jbd2/journal.c b/fs/jbd2/journal.c index effd837b8c1f..4ae4b85ea187 100644 --- a/fs/jbd2/journal.c +++ b/fs/jbd2/journal.c @@ -1481,6 +1481,11 @@ static void journal_fail_superblock(journal_t *journal) journal->j_sb_buffer = NULL; } +static int jbd2_journal_get_max_txn_bufs(journal_t *journal) +{ + return (journal->j_total_len - journal->j_fc_wbufsize) / 4; +} + /* * Given a journal_t structure, initialise the various fields for * startup of a new journaling session. We use this both when creating diff --git a/include/linux/jbd2.h b/include/linux/jbd2.h index 578ff196b3ce..80f573d1b3b8 100644 --- a/include/linux/jbd2.h +++ b/include/linux/jbd2.h @@ -1626,11 +1626,6 @@ int jbd2_wait_inode_data(journal_t *journal, struct jbd2_inode *jinode); int jbd2_fc_wait_bufs(journal_t *journal, int num_blks); int jbd2_fc_release_bufs(journal_t *journal); -static inline int jbd2_journal_get_max_txn_bufs(journal_t *journal) -{ - return (journal->j_total_len - journal->j_fc_wbufsize) / 4; -} - /* * is_journal_abort * From 9d289ce917f847305fe98b8cd9463a61ec5e4f4b Mon Sep 17 00:00:00 2001 From: Sean Christopherson Date: Fri, 7 Jun 2024 10:26:06 -0700 Subject: [PATCH 141/342] KVM: VMX: Split out the non-virtualization part of vmx_interrupt_blocked() commit 322a569c4b4188a0da2812f9e952780ce09b74ba upstream. Move the non-VMX chunk of the "interrupt blocked" checks to a separate helper so that KVM can reuse the code to detect if interrupts are blocked for L2, e.g. to determine if a virtual interrupt _for L2_ is a valid wake event. If L1 disables HLT-exiting for L2, nested APICv is enabled, and L2 HLTs, then L2 virtual interrupts are valid wake events, but if and only if interrupts are unblocked for L2. Cc: stable@vger.kernel.org Link: https://lore.kernel.org/r/20240607172609.3205077-4-seanjc@google.com Signed-off-by: Sean Christopherson Signed-off-by: Greg Kroah-Hartman --- arch/x86/kvm/vmx/vmx.c | 11 ++++++++--- arch/x86/kvm/vmx/vmx.h | 1 + 2 files changed, 9 insertions(+), 3 deletions(-) diff --git a/arch/x86/kvm/vmx/vmx.c b/arch/x86/kvm/vmx/vmx.c index 3e9bb9ae836d..b29be51b72b4 100644 --- a/arch/x86/kvm/vmx/vmx.c +++ b/arch/x86/kvm/vmx/vmx.c @@ -4738,14 +4738,19 @@ static int vmx_nmi_allowed(struct kvm_vcpu *vcpu, bool for_injection) return !vmx_nmi_blocked(vcpu); } +bool __vmx_interrupt_blocked(struct kvm_vcpu *vcpu) +{ + return !(vmx_get_rflags(vcpu) & X86_EFLAGS_IF) || + (vmcs_read32(GUEST_INTERRUPTIBILITY_INFO) & + (GUEST_INTR_STATE_STI | GUEST_INTR_STATE_MOV_SS)); +} + bool vmx_interrupt_blocked(struct kvm_vcpu *vcpu) { if (is_guest_mode(vcpu) && nested_exit_on_intr(vcpu)) return false; - return !(vmx_get_rflags(vcpu) & X86_EFLAGS_IF) || - (vmcs_read32(GUEST_INTERRUPTIBILITY_INFO) & - (GUEST_INTR_STATE_STI | GUEST_INTR_STATE_MOV_SS)); + return __vmx_interrupt_blocked(vcpu); } static int vmx_interrupt_allowed(struct kvm_vcpu *vcpu, bool for_injection) diff --git a/arch/x86/kvm/vmx/vmx.h b/arch/x86/kvm/vmx/vmx.h index ed4b6da83aa8..811d7ef4638b 100644 --- a/arch/x86/kvm/vmx/vmx.h +++ b/arch/x86/kvm/vmx/vmx.h @@ -359,6 +359,7 @@ bool vmx_guest_inject_ac(struct kvm_vcpu *vcpu); void update_exception_bitmap(struct kvm_vcpu *vcpu); void vmx_update_msr_bitmap(struct kvm_vcpu *vcpu); bool vmx_nmi_blocked(struct kvm_vcpu *vcpu); +bool __vmx_interrupt_blocked(struct kvm_vcpu *vcpu); bool vmx_interrupt_blocked(struct kvm_vcpu *vcpu); bool vmx_get_nmi_mask(struct kvm_vcpu *vcpu); void vmx_set_nmi_mask(struct kvm_vcpu *vcpu, bool masked); From 43aab4483daa1a210b327392f5e0a55bea8f3614 Mon Sep 17 00:00:00 2001 From: Alan Stern Date: Thu, 6 Jun 2024 09:57:55 -0400 Subject: [PATCH 142/342] tools/memory-model: Fix bug in lock.cat commit 4c830eef806679dc243e191f962c488dd9d00708 upstream. Andrea reported that the following innocuous litmus test: C T {} P0(spinlock_t *x) { int r0; spin_lock(x); spin_unlock(x); r0 = spin_is_locked(x); } gives rise to a nonsensical empty result with no executions: $ herd7 -conf linux-kernel.cfg T.litmus Test T Required States 0 Ok Witnesses Positive: 0 Negative: 0 Condition forall (true) Observation T Never 0 0 Time T 0.00 Hash=6fa204e139ddddf2cb6fa963bad117c0 The problem is caused by a bug in the lock.cat part of the LKMM. Its computation of the rf relation for RU (read-unlocked) events is faulty; it implicitly assumes that every RU event must read from either a UL (unlock) event in another thread or from the lock's initial state. Neither is true in the litmus test above, so the computation yields no possible executions. The lock.cat code tries to make up for this deficiency by allowing RU events outside of critical sections to read from the last po-previous UL event. But it does this incorrectly, trying to keep these rfi links separate from the rfe links that might also be needed, and passing only the latter to herd7's cross() macro. The problem is fixed by merging the two sets of possible rf links for RU events and using them all in the call to cross(). Signed-off-by: Alan Stern Reported-by: Andrea Parri Closes: https://lore.kernel.org/linux-arch/ZlC0IkzpQdeGj+a3@andrea/ Tested-by: Andrea Parri Acked-by: Andrea Parri Fixes: 15553dcbca06 ("tools/memory-model: Add model support for spin_is_locked()") CC: Signed-off-by: Paul E. McKenney Signed-off-by: Greg Kroah-Hartman --- tools/memory-model/lock.cat | 20 ++++++++++---------- 1 file changed, 10 insertions(+), 10 deletions(-) diff --git a/tools/memory-model/lock.cat b/tools/memory-model/lock.cat index 6b52f365d73a..9f3b5b38221b 100644 --- a/tools/memory-model/lock.cat +++ b/tools/memory-model/lock.cat @@ -102,19 +102,19 @@ let rf-lf = rfe-lf | rfi-lf * within one of the lock's critical sections returns False. *) -(* rfi for RU events: an RU may read from the last po-previous UL *) -let rfi-ru = ([UL] ; po-loc ; [RU]) \ ([UL] ; po-loc ; [LKW] ; po-loc) - -(* rfe for RU events: an RU may read from an external UL or the initial write *) -let all-possible-rfe-ru = - let possible-rfe-ru r = +(* + * rf for RU events: an RU may read from an external UL or the initial write, + * or from the last po-previous UL + *) +let all-possible-rf-ru = + let possible-rf-ru r = let pair-to-relation p = p ++ 0 - in map pair-to-relation (((UL | IW) * {r}) & loc & ext) - in map possible-rfe-ru RU + in map pair-to-relation ((((UL | IW) * {r}) & loc & ext) | + (((UL * {r}) & po-loc) \ ([UL] ; po-loc ; [LKW] ; po-loc))) + in map possible-rf-ru RU (* Generate all rf relations for RU events *) -with rfe-ru from cross(all-possible-rfe-ru) -let rf-ru = rfe-ru | rfi-ru +with rf-ru from cross(all-possible-rf-ru) (* Final rf relation *) let rf = rf | rf-lf | rf-ru From af1d27f88ec908bf85058ee1a8368a42469ad395 Mon Sep 17 00:00:00 2001 From: =?UTF-8?q?Ilpo=20J=C3=A4rvinen?= Date: Mon, 27 May 2024 16:26:15 +0300 Subject: [PATCH 143/342] hwrng: amd - Convert PCIBIOS_* return codes to errnos MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit commit 14cba6ace79627a57fb9058582b03f0ed3832390 upstream. amd_rng_mod_init() uses pci_read_config_dword() that returns PCIBIOS_* codes. The return code is then returned as is but amd_rng_mod_init() is a module_init() function that should return normal errnos. Convert PCIBIOS_* returns code using pcibios_err_to_errno() into normal errno before returning it. Fixes: 96d63c0297cc ("[PATCH] Add AMD HW RNG driver") Cc: stable@vger.kernel.org Signed-off-by: Ilpo Järvinen Signed-off-by: Herbert Xu Signed-off-by: Greg Kroah-Hartman --- drivers/char/hw_random/amd-rng.c | 4 +++- 1 file changed, 3 insertions(+), 1 deletion(-) diff --git a/drivers/char/hw_random/amd-rng.c b/drivers/char/hw_random/amd-rng.c index db3dd467194c..3f3fdf6ee3d5 100644 --- a/drivers/char/hw_random/amd-rng.c +++ b/drivers/char/hw_random/amd-rng.c @@ -142,8 +142,10 @@ static int __init mod_init(void) found: err = pci_read_config_dword(pdev, 0x58, &pmbase); - if (err) + if (err) { + err = pcibios_err_to_errno(err); goto put_dev; + } pmbase &= 0x0000FF00; if (pmbase == 0) { From e5bae95306f75014cb07594bef56ac4cd4c3110b Mon Sep 17 00:00:00 2001 From: Wei Liu Date: Mon, 1 Jul 2024 20:26:05 +0000 Subject: [PATCH 144/342] PCI: hv: Return zero, not garbage, when reading PCI_INTERRUPT_PIN MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit commit fea93a3e5d5e6a09eb153866d2ce60ea3287a70d upstream. The intent of the code snippet is to always return 0 for both PCI_INTERRUPT_LINE and PCI_INTERRUPT_PIN. The check misses PCI_INTERRUPT_PIN. This patch fixes that. This is discovered by this call in VFIO: pci_read_config_byte(vdev->pdev, PCI_INTERRUPT_PIN, &pin); The old code does not set *val to 0 because it misses the check for PCI_INTERRUPT_PIN. Garbage is returned in that case. Fixes: 4daace0d8ce8 ("PCI: hv: Add paravirtual PCI front-end for Microsoft Hyper-V VMs") Link: https://lore.kernel.org/linux-pci/20240701202606.129606-1-wei.liu@kernel.org Signed-off-by: Wei Liu Signed-off-by: Krzysztof Wilczyński Reviewed-by: Michael Kelley Cc: stable@kernel.org Signed-off-by: Greg Kroah-Hartman --- drivers/pci/controller/pci-hyperv.c | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-) diff --git a/drivers/pci/controller/pci-hyperv.c b/drivers/pci/controller/pci-hyperv.c index 2d6c77dcc815..d0b3ec237385 100644 --- a/drivers/pci/controller/pci-hyperv.c +++ b/drivers/pci/controller/pci-hyperv.c @@ -680,8 +680,8 @@ static void _hv_pcifront_read_config(struct hv_pci_dev *hpdev, int where, PCI_CAPABILITY_LIST) { /* ROM BARs are unimplemented */ *val = 0; - } else if (where >= PCI_INTERRUPT_LINE && where + size <= - PCI_INTERRUPT_PIN) { + } else if ((where >= PCI_INTERRUPT_LINE && where + size <= PCI_INTERRUPT_PIN) || + (where >= PCI_INTERRUPT_PIN && where + size <= PCI_MIN_GNT)) { /* * Interrupt Line and Interrupt PIN are hard-wired to zero * because this front-end only supports message-signaled From ac2459460ce794bd79931ffd9af36055207bb69f Mon Sep 17 00:00:00 2001 From: Manivannan Sadhasivam Date: Tue, 16 Apr 2024 11:12:35 +0530 Subject: [PATCH 145/342] PCI: rockchip: Use GPIOD_OUT_LOW flag while requesting ep_gpio MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit commit 840b7a5edf88fe678c60dee88a135647c0ea4375 upstream. Rockchip platforms use 'GPIO_ACTIVE_HIGH' flag in the devicetree definition for ep_gpio. This means, whatever the logical value set by the driver for the ep_gpio, physical line will output the same logic level. For instance, gpiod_set_value_cansleep(rockchip->ep_gpio, 0); --> Level low gpiod_set_value_cansleep(rockchip->ep_gpio, 1); --> Level high But while requesting the ep_gpio, GPIOD_OUT_HIGH flag is currently used. Now, this also causes the physical line to output 'high' creating trouble for endpoint devices during host reboot. When host reboot happens, the ep_gpio will initially output 'low' due to the GPIO getting reset to its POR value. Then during host controller probe, it will output 'high' due to GPIOD_OUT_HIGH flag. Then during rockchip_pcie_host_init_port(), it will first output 'low' and then 'high' indicating the completion of controller initialization. On the endpoint side, each output 'low' of ep_gpio is accounted for PERST# assert and 'high' for PERST# deassert. With the above mentioned flow during host reboot, endpoint will witness below state changes for PERST#: (1) PERST# assert - GPIO POR state (2) PERST# deassert - GPIOD_OUT_HIGH while requesting GPIO (3) PERST# assert - rockchip_pcie_host_init_port() (4) PERST# deassert - rockchip_pcie_host_init_port() Now the time interval between (2) and (3) is very short as both happen during the driver probe(), and this results in a race in the endpoint. Because, before completing the PERST# deassertion in (2), endpoint got another PERST# assert in (3). A proper way to fix this issue is to change the GPIOD_OUT_HIGH flag in (2) to GPIOD_OUT_LOW. Because the usual convention is to request the GPIO with a state corresponding to its 'initial/default' value and let the driver change the state of the GPIO when required. As per that, the ep_gpio should be requested with GPIOD_OUT_LOW as it corresponds to the POR value of '0' (PERST# assert in the endpoint). Then the driver can change the state of the ep_gpio later in rockchip_pcie_host_init_port() as per the initialization sequence. This fixes the firmware crash issue in Qcom based modems connected to Rockpro64 based board. Fixes: e77f847df54c ("PCI: rockchip: Add Rockchip PCIe controller support") Closes: https://lore.kernel.org/mhi/20240402045647.GG2933@thinkpad/ Link: https://lore.kernel.org/linux-pci/20240416-pci-rockchip-perst-fix-v1-1-4800b1d4d954@linaro.org Reported-by: Slark Xiao Signed-off-by: Manivannan Sadhasivam Signed-off-by: Krzysztof Wilczyński Signed-off-by: Bjorn Helgaas Reviewed-by: Niklas Cassel Cc: stable@vger.kernel.org # v4.9 Signed-off-by: Greg Kroah-Hartman --- drivers/pci/controller/pcie-rockchip.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/drivers/pci/controller/pcie-rockchip.c b/drivers/pci/controller/pcie-rockchip.c index 1aa84035a8bc..bdce1ba7c1bc 100644 --- a/drivers/pci/controller/pcie-rockchip.c +++ b/drivers/pci/controller/pcie-rockchip.c @@ -120,7 +120,7 @@ int rockchip_pcie_parse_dt(struct rockchip_pcie *rockchip) if (rockchip->is_rc) { rockchip->ep_gpio = devm_gpiod_get_optional(dev, "ep", - GPIOD_OUT_HIGH); + GPIOD_OUT_LOW); if (IS_ERR(rockchip->ep_gpio)) return dev_err_probe(dev, PTR_ERR(rockchip->ep_gpio), "failed to get ep GPIO\n"); From 388ee7a4d33045933553542aec4530d859db7c29 Mon Sep 17 00:00:00 2001 From: Carlos Llamas Date: Thu, 11 Jul 2024 20:14:51 +0000 Subject: [PATCH 146/342] binder: fix hang of unregistered readers MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit commit 31643d84b8c3d9c846aa0e20bc033e46c68c7e7d upstream. With the introduction of binder_available_for_proc_work_ilocked() in commit 1b77e9dcc3da ("ANDROID: binder: remove proc waitqueue") a binder thread can only "wait_for_proc_work" after its thread->looper has been marked as BINDER_LOOPER_STATE_{ENTERED|REGISTERED}. This means an unregistered reader risks waiting indefinitely for work since it never gets added to the proc->waiting_threads. If there are no further references to its waitqueue either the task will hang. The same applies to readers using the (e)poll interface. I couldn't find the rationale behind this restriction. So this patch restores the previous behavior of allowing unregistered threads to "wait_for_proc_work". Note that an error message for this scenario, which had previously become unreachable, is now re-enabled. Fixes: 1b77e9dcc3da ("ANDROID: binder: remove proc waitqueue") Cc: stable@vger.kernel.org Cc: Martijn Coenen Cc: Arve Hjønnevåg Signed-off-by: Carlos Llamas Link: https://lore.kernel.org/r/20240711201452.2017543-1-cmllamas@google.com Signed-off-by: Greg Kroah-Hartman --- drivers/android/binder.c | 4 +--- 1 file changed, 1 insertion(+), 3 deletions(-) diff --git a/drivers/android/binder.c b/drivers/android/binder.c index 6631a65f632b..cd3de4ec1767 100644 --- a/drivers/android/binder.c +++ b/drivers/android/binder.c @@ -928,9 +928,7 @@ static bool binder_has_work(struct binder_thread *thread, bool do_proc_work) static bool binder_available_for_proc_work_ilocked(struct binder_thread *thread) { return !thread->transaction_stack && - binder_worklist_empty_ilocked(&thread->todo) && - (thread->looper & (BINDER_LOOPER_STATE_ENTERED | - BINDER_LOOPER_STATE_REGISTERED)); + binder_worklist_empty_ilocked(&thread->todo); } static void binder_wakeup_poll_threads_ilocked(struct binder_proc *proc, From a44f88f7576bc1916d8d6293f5c62fbe7cbe03e0 Mon Sep 17 00:00:00 2001 From: tuhaowen Date: Mon, 8 Jul 2024 16:04:30 +0800 Subject: [PATCH 147/342] dev/parport: fix the array out-of-bounds risk commit ab11dac93d2d568d151b1918d7b84c2d02bacbd5 upstream. Fixed array out-of-bounds issues caused by sprintf by replacing it with snprintf for safer data copying, ensuring the destination buffer is not overflowed. Below is the stack trace I encountered during the actual issue: [ 66.575408s] [pid:5118,cpu4,QThread,4]Kernel panic - not syncing: stack-protector: Kernel stack is corrupted in: do_hardware_base_addr+0xcc/0xd0 [parport] [ 66.575408s] [pid:5118,cpu4,QThread,5]CPU: 4 PID: 5118 Comm: QThread Tainted: G S W O 5.10.97-arm64-desktop #7100.57021.2 [ 66.575439s] [pid:5118,cpu4,QThread,6]TGID: 5087 Comm: EFileApp [ 66.575439s] [pid:5118,cpu4,QThread,7]Hardware name: HUAWEI HUAWEI QingYun PGUX-W515x-B081/SP1PANGUXM, BIOS 1.00.07 04/29/2024 [ 66.575439s] [pid:5118,cpu4,QThread,8]Call trace: [ 66.575469s] [pid:5118,cpu4,QThread,9] dump_backtrace+0x0/0x1c0 [ 66.575469s] [pid:5118,cpu4,QThread,0] show_stack+0x14/0x20 [ 66.575469s] [pid:5118,cpu4,QThread,1] dump_stack+0xd4/0x10c [ 66.575500s] [pid:5118,cpu4,QThread,2] panic+0x1d8/0x3bc [ 66.575500s] [pid:5118,cpu4,QThread,3] __stack_chk_fail+0x2c/0x38 [ 66.575500s] [pid:5118,cpu4,QThread,4] do_hardware_base_addr+0xcc/0xd0 [parport] Signed-off-by: tuhaowen Cc: stable Link: https://lore.kernel.org/r/20240708080430.8221-1-tuhaowen@uniontech.com Signed-off-by: Greg Kroah-Hartman --- drivers/parport/procfs.c | 24 ++++++++++++------------ 1 file changed, 12 insertions(+), 12 deletions(-) diff --git a/drivers/parport/procfs.c b/drivers/parport/procfs.c index d740eba3c099..8400a379186e 100644 --- a/drivers/parport/procfs.c +++ b/drivers/parport/procfs.c @@ -51,12 +51,12 @@ static int do_active_device(struct ctl_table *table, int write, for (dev = port->devices; dev ; dev = dev->next) { if(dev == port->cad) { - len += sprintf(buffer, "%s\n", dev->name); + len += snprintf(buffer, sizeof(buffer), "%s\n", dev->name); } } if(!len) { - len += sprintf(buffer, "%s\n", "none"); + len += snprintf(buffer, sizeof(buffer), "%s\n", "none"); } if (len > *lenp) @@ -87,19 +87,19 @@ static int do_autoprobe(struct ctl_table *table, int write, } if ((str = info->class_name) != NULL) - len += sprintf (buffer + len, "CLASS:%s;\n", str); + len += snprintf (buffer + len, sizeof(buffer) - len, "CLASS:%s;\n", str); if ((str = info->model) != NULL) - len += sprintf (buffer + len, "MODEL:%s;\n", str); + len += snprintf (buffer + len, sizeof(buffer) - len, "MODEL:%s;\n", str); if ((str = info->mfr) != NULL) - len += sprintf (buffer + len, "MANUFACTURER:%s;\n", str); + len += snprintf (buffer + len, sizeof(buffer) - len, "MANUFACTURER:%s;\n", str); if ((str = info->description) != NULL) - len += sprintf (buffer + len, "DESCRIPTION:%s;\n", str); + len += snprintf (buffer + len, sizeof(buffer) - len, "DESCRIPTION:%s;\n", str); if ((str = info->cmdset) != NULL) - len += sprintf (buffer + len, "COMMAND SET:%s;\n", str); + len += snprintf (buffer + len, sizeof(buffer) - len, "COMMAND SET:%s;\n", str); if (len > *lenp) len = *lenp; @@ -117,7 +117,7 @@ static int do_hardware_base_addr(struct ctl_table *table, int write, void *result, size_t *lenp, loff_t *ppos) { struct parport *port = (struct parport *)table->extra1; - char buffer[20]; + char buffer[64]; int len = 0; if (*ppos) { @@ -128,7 +128,7 @@ static int do_hardware_base_addr(struct ctl_table *table, int write, if (write) /* permissions prevent this anyway */ return -EACCES; - len += sprintf (buffer, "%lu\t%lu\n", port->base, port->base_hi); + len += snprintf (buffer, sizeof(buffer), "%lu\t%lu\n", port->base, port->base_hi); if (len > *lenp) len = *lenp; @@ -155,7 +155,7 @@ static int do_hardware_irq(struct ctl_table *table, int write, if (write) /* permissions prevent this anyway */ return -EACCES; - len += sprintf (buffer, "%d\n", port->irq); + len += snprintf (buffer, sizeof(buffer), "%d\n", port->irq); if (len > *lenp) len = *lenp; @@ -182,7 +182,7 @@ static int do_hardware_dma(struct ctl_table *table, int write, if (write) /* permissions prevent this anyway */ return -EACCES; - len += sprintf (buffer, "%d\n", port->dma); + len += snprintf (buffer, sizeof(buffer), "%d\n", port->dma); if (len > *lenp) len = *lenp; @@ -213,7 +213,7 @@ static int do_hardware_modes(struct ctl_table *table, int write, #define printmode(x) \ do { \ if (port->modes & PARPORT_MODE_##x) \ - len += sprintf(buffer + len, "%s%s", f++ ? "," : "", #x); \ + len += snprintf(buffer + len, sizeof(buffer) - len, "%s%s", f++ ? "," : "", #x); \ } while (0) int f = 0; printmode(PCSPP); From b848b40794bac3851fec079ab7696380d2e05b71 Mon Sep 17 00:00:00 2001 From: Saurav Kashyap Date: Wed, 10 Jul 2024 22:40:50 +0530 Subject: [PATCH 148/342] scsi: qla2xxx: Return ENOBUFS if sg_cnt is more than one for ELS cmds commit ce2065c4cc4f05635413f63f6dc038d7d4842e31 upstream. Firmware only supports single DSDs in ELS Pass-through IOCB (0x53h), sg cnt is decided by the SCSI ML. User is not aware of the cause of an acutal error. Return the appropriate return code that will be decoded by API and application and proper error message will be displayed to user. Fixes: 6e98016ca077 ("[SCSI] qla2xxx: Re-organized BSG interface specific code.") Cc: stable@vger.kernel.org Signed-off-by: Saurav Kashyap Signed-off-by: Nilesh Javali Link: https://lore.kernel.org/r/20240710171057.35066-5-njavali@marvell.com Reviewed-by: Himanshu Madhani Signed-off-by: Martin K. Petersen Signed-off-by: Greg Kroah-Hartman --- drivers/scsi/qla2xxx/qla_bsg.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/drivers/scsi/qla2xxx/qla_bsg.c b/drivers/scsi/qla2xxx/qla_bsg.c index 804cac4c3476..d415e816ad0e 100644 --- a/drivers/scsi/qla2xxx/qla_bsg.c +++ b/drivers/scsi/qla2xxx/qla_bsg.c @@ -306,7 +306,7 @@ qla2x00_process_els(struct bsg_job *bsg_job) "request_sg_cnt=%x reply_sg_cnt=%x.\n", bsg_job->request_payload.sg_cnt, bsg_job->reply_payload.sg_cnt); - rval = -EPERM; + rval = -ENOBUFS; goto done; } From 54bc4e88447e385c4d4ffa85d93e0dce628fcfa6 Mon Sep 17 00:00:00 2001 From: Chao Yu Date: Tue, 4 Jun 2024 15:56:36 +0800 Subject: [PATCH 149/342] f2fs: fix to don't dirty inode for readonly filesystem commit 192b8fb8d1c8ca3c87366ebbef599fa80bb626b8 upstream. syzbot reports f2fs bug as below: kernel BUG at fs/f2fs/inode.c:933! RIP: 0010:f2fs_evict_inode+0x1576/0x1590 fs/f2fs/inode.c:933 Call Trace: evict+0x2a4/0x620 fs/inode.c:664 dispose_list fs/inode.c:697 [inline] evict_inodes+0x5f8/0x690 fs/inode.c:747 generic_shutdown_super+0x9d/0x2c0 fs/super.c:675 kill_block_super+0x44/0x90 fs/super.c:1667 kill_f2fs_super+0x303/0x3b0 fs/f2fs/super.c:4894 deactivate_locked_super+0xc1/0x130 fs/super.c:484 cleanup_mnt+0x426/0x4c0 fs/namespace.c:1256 task_work_run+0x24a/0x300 kernel/task_work.c:180 ptrace_notify+0x2cd/0x380 kernel/signal.c:2399 ptrace_report_syscall include/linux/ptrace.h:411 [inline] ptrace_report_syscall_exit include/linux/ptrace.h:473 [inline] syscall_exit_work kernel/entry/common.c:251 [inline] syscall_exit_to_user_mode_prepare kernel/entry/common.c:278 [inline] __syscall_exit_to_user_mode_work kernel/entry/common.c:283 [inline] syscall_exit_to_user_mode+0x15c/0x280 kernel/entry/common.c:296 do_syscall_64+0x50/0x110 arch/x86/entry/common.c:88 entry_SYSCALL_64_after_hwframe+0x63/0x6b The root cause is: - do_sys_open - f2fs_lookup - __f2fs_find_entry - f2fs_i_depth_write - f2fs_mark_inode_dirty_sync - f2fs_dirty_inode - set_inode_flag(inode, FI_DIRTY_INODE) - umount - kill_f2fs_super - kill_block_super - generic_shutdown_super - sync_filesystem : sb is readonly, skip sync_filesystem() - evict_inodes - iput - f2fs_evict_inode - f2fs_bug_on(sbi, is_inode_flag_set(inode, FI_DIRTY_INODE)) : trigger kernel panic When we try to repair i_current_depth in readonly filesystem, let's skip dirty inode to avoid panic in later f2fs_evict_inode(). Cc: stable@vger.kernel.org Reported-by: syzbot+31e4659a3fe953aec2f4@syzkaller.appspotmail.com Closes: https://lore.kernel.org/linux-f2fs-devel/000000000000e890bc0609a55cff@google.com Signed-off-by: Chao Yu Signed-off-by: Jaegeuk Kim Signed-off-by: Greg Kroah-Hartman --- fs/f2fs/inode.c | 3 +++ 1 file changed, 3 insertions(+) diff --git a/fs/f2fs/inode.c b/fs/f2fs/inode.c index 724760353bcd..b23e6a848e9b 100644 --- a/fs/f2fs/inode.c +++ b/fs/f2fs/inode.c @@ -23,6 +23,9 @@ void f2fs_mark_inode_dirty_sync(struct inode *inode, bool sync) if (is_inode_flag_set(inode, FI_NEW_INODE)) return; + if (f2fs_readonly(F2FS_I_SB(inode)->sb)) + return; + if (f2fs_inode_dirtied(inode, sync)) return; From ae99754cd86bfbdba582b150032620c6803c621c Mon Sep 17 00:00:00 2001 From: Bastien Curutchet Date: Thu, 18 Jul 2024 13:55:34 +0200 Subject: [PATCH 150/342] clk: davinci: da8xx-cfgchip: Initialize clk_init_data before use commit a83b22754e351f13fb46596c85f667dc33da71ec upstream. The flag attribute of the struct clk_init_data isn't initialized before the devm_clk_hw_register() call. This can lead to unexpected behavior during registration. Initialize the entire clk_init_data to zero at declaration. Cc: stable@vger.kernel.org Fixes: 58e1e2d2cd89 ("clk: davinci: cfgchip: Add TI DA8XX USB PHY clocks") Signed-off-by: Bastien Curutchet Reviewed-by: David Lechner Link: https://lore.kernel.org/r/20240718115534.41513-1-bastien.curutchet@bootlin.com Signed-off-by: Stephen Boyd Signed-off-by: Greg Kroah-Hartman --- drivers/clk/davinci/da8xx-cfgchip.c | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-) diff --git a/drivers/clk/davinci/da8xx-cfgchip.c b/drivers/clk/davinci/da8xx-cfgchip.c index 77d18276bfe8..90d96ee4a58b 100644 --- a/drivers/clk/davinci/da8xx-cfgchip.c +++ b/drivers/clk/davinci/da8xx-cfgchip.c @@ -505,7 +505,7 @@ da8xx_cfgchip_register_usb0_clk48(struct device *dev, const char * const parent_names[] = { "usb_refclkin", "pll0_auxclk" }; struct clk *fck_clk; struct da8xx_usb0_clk48 *usb0; - struct clk_init_data init; + struct clk_init_data init = {}; int ret; fck_clk = devm_clk_get(dev, "fck"); @@ -580,7 +580,7 @@ da8xx_cfgchip_register_usb1_clk48(struct device *dev, { const char * const parent_names[] = { "usb0_clk48", "usb_refclkin" }; struct da8xx_usb1_clk48 *usb1; - struct clk_init_data init; + struct clk_init_data init = {}; int ret; usb1 = devm_kzalloc(dev, sizeof(*usb1), GFP_KERNEL); From bed9580165d5c2cc4c3fc9d49eadac5212db70ee Mon Sep 17 00:00:00 2001 From: Fedor Pchelkin Date: Thu, 29 Feb 2024 23:42:36 +0300 Subject: [PATCH 151/342] ubi: eba: properly rollback inside self_check_eba commit 745d9f4a31defec731119ee8aad8ba9f2536dd9a upstream. In case of a memory allocation failure in the volumes loop we can only process the already allocated scan_eba and fm_eba array elements on the error path - others are still uninitialized. Found by Linux Verification Center (linuxtesting.org). Fixes: 00abf3041590 ("UBI: Add self_check_eba()") Cc: stable@vger.kernel.org Signed-off-by: Fedor Pchelkin Reviewed-by: Zhihao Cheng Signed-off-by: Richard Weinberger Signed-off-by: Greg Kroah-Hartman --- drivers/mtd/ubi/eba.c | 3 ++- 1 file changed, 2 insertions(+), 1 deletion(-) diff --git a/drivers/mtd/ubi/eba.c b/drivers/mtd/ubi/eba.c index b4cdf2351cac..d33deb84b6ec 100644 --- a/drivers/mtd/ubi/eba.c +++ b/drivers/mtd/ubi/eba.c @@ -1560,6 +1560,7 @@ int self_check_eba(struct ubi_device *ubi, struct ubi_attach_info *ai_fastmap, GFP_KERNEL); if (!fm_eba[i]) { ret = -ENOMEM; + kfree(scan_eba[i]); goto out_free; } @@ -1595,7 +1596,7 @@ int self_check_eba(struct ubi_device *ubi, struct ubi_attach_info *ai_fastmap, } out_free: - for (i = 0; i < num_volumes; i++) { + while (--i >= 0) { if (!ubi->volumes[i]) continue; From 0730ea85027071ef0897ed50e6702e5c90ea7cfc Mon Sep 17 00:00:00 2001 From: Ross Lagerwall Date: Wed, 17 Jul 2024 17:20:16 +0100 Subject: [PATCH 152/342] decompress_bunzip2: fix rare decompression failure commit bf6acd5d16057d7accbbb1bf7dc6d8c56eeb4ecc upstream. The decompression code parses a huffman tree and counts the number of symbols for a given bit length. In rare cases, there may be >= 256 symbols with a given bit length, causing the unsigned char to overflow. This causes a decompression failure later when the code tries and fails to find the bit length for a given symbol. Since the maximum number of symbols is 258, use unsigned short instead. Link: https://lkml.kernel.org/r/20240717162016.1514077-1-ross.lagerwall@citrix.com Fixes: bc22c17e12c1 ("bzip2/lzma: library support for gzip, bzip2 and lzma decompression") Signed-off-by: Ross Lagerwall Cc: Alain Knaff Cc: "H. Peter Anvin" Cc: Signed-off-by: Andrew Morton Signed-off-by: Greg Kroah-Hartman --- lib/decompress_bunzip2.c | 3 ++- 1 file changed, 2 insertions(+), 1 deletion(-) diff --git a/lib/decompress_bunzip2.c b/lib/decompress_bunzip2.c index c72c865032fa..0cc292256fd3 100644 --- a/lib/decompress_bunzip2.c +++ b/lib/decompress_bunzip2.c @@ -232,7 +232,8 @@ static int INIT get_next_block(struct bunzip_data *bd) RUNB) */ symCount = symTotal+2; for (j = 0; j < groupCount; j++) { - unsigned char length[MAX_SYMBOLS], temp[MAX_HUFCODE_BITS+1]; + unsigned char length[MAX_SYMBOLS]; + unsigned short temp[MAX_HUFCODE_BITS+1]; int minLen, maxLen, pp; /* Read Huffman code lengths for each symbol. They're stored in a way similar to mtf; record a starting From 41dd9636414bef6dc9ce8f8d84be3424e2952f3d Mon Sep 17 00:00:00 2001 From: Nathan Chancellor Date: Fri, 26 Jul 2024 11:05:00 -0700 Subject: [PATCH 153/342] kbuild: Fix '-S -c' in x86 stack protector scripts commit 3415b10a03945b0da4a635e146750dfe5ce0f448 upstream. After a recent change in clang to stop consuming all instances of '-S' and '-c' [1], the stack protector scripts break due to the kernel's use of -Werror=unused-command-line-argument to catch cases where flags are not being properly consumed by the compiler driver: $ echo | clang -o - -x c - -S -c -Werror=unused-command-line-argument clang: error: argument unused during compilation: '-c' [-Werror,-Wunused-command-line-argument] This results in CONFIG_STACKPROTECTOR getting disabled because CONFIG_CC_HAS_SANE_STACKPROTECTOR is no longer set. '-c' and '-S' both instruct the compiler to stop at different stages of the pipeline ('-S' after compiling, '-c' after assembling), so having them present together in the same command makes little sense. In this case, the test wants to stop before assembling because it is looking at the textual assembly output of the compiler for either '%fs' or '%gs', so remove '-c' from the list of arguments to resolve the error. All versions of GCC continue to work after this change, along with versions of clang that do or do not contain the change mentioned above. Cc: stable@vger.kernel.org Fixes: 4f7fd4d7a791 ("[PATCH] Add the -fstack-protector option to the CFLAGS") Fixes: 60a5317ff0f4 ("x86: implement x86_32 stack protector") Link: https://github.com/llvm/llvm-project/commit/6461e537815f7fa68cef06842505353cf5600e9c [1] Signed-off-by: Nathan Chancellor Signed-off-by: Masahiro Yamada Signed-off-by: Greg Kroah-Hartman --- scripts/gcc-x86_32-has-stack-protector.sh | 2 +- scripts/gcc-x86_64-has-stack-protector.sh | 2 +- 2 files changed, 2 insertions(+), 2 deletions(-) diff --git a/scripts/gcc-x86_32-has-stack-protector.sh b/scripts/gcc-x86_32-has-stack-protector.sh index 825c75c5b715..9459ca4f0f11 100755 --- a/scripts/gcc-x86_32-has-stack-protector.sh +++ b/scripts/gcc-x86_32-has-stack-protector.sh @@ -5,4 +5,4 @@ # -mstack-protector-guard-reg, added by # https://gcc.gnu.org/bugzilla/show_bug.cgi?id=81708 -echo "int foo(void) { char X[200]; return 3; }" | $* -S -x c -c -m32 -O0 -fstack-protector -mstack-protector-guard-reg=fs -mstack-protector-guard-symbol=__stack_chk_guard - -o - 2> /dev/null | grep -q "%fs" +echo "int foo(void) { char X[200]; return 3; }" | $* -S -x c -m32 -O0 -fstack-protector -mstack-protector-guard-reg=fs -mstack-protector-guard-symbol=__stack_chk_guard - -o - 2> /dev/null | grep -q "%fs" diff --git a/scripts/gcc-x86_64-has-stack-protector.sh b/scripts/gcc-x86_64-has-stack-protector.sh index 75e4e22b986a..f680bb01aeeb 100755 --- a/scripts/gcc-x86_64-has-stack-protector.sh +++ b/scripts/gcc-x86_64-has-stack-protector.sh @@ -1,4 +1,4 @@ #!/bin/sh # SPDX-License-Identifier: GPL-2.0 -echo "int foo(void) { char X[200]; return 3; }" | $* -S -x c -c -m64 -O0 -mcmodel=kernel -fno-PIE -fstack-protector - -o - 2> /dev/null | grep -q "%gs" +echo "int foo(void) { char X[200]; return 3; }" | $* -S -x c -m64 -O0 -mcmodel=kernel -fno-PIE -fstack-protector - -o - 2> /dev/null | grep -q "%gs" From 648d5490460d38436640da0812bf7f6351c150d2 Mon Sep 17 00:00:00 2001 From: Zijun Hu Date: Thu, 30 May 2024 21:14:37 +0800 Subject: [PATCH 154/342] kobject_uevent: Fix OOB access within zap_modalias_env() commit dd6e9894b451e7c85cceb8e9dc5432679a70e7dc upstream. zap_modalias_env() wrongly calculates size of memory block to move, so will cause OOB memory access issue if variable MODALIAS is not the last one within its @env parameter, fixed by correcting size to memmove. Fixes: 9b3fa47d4a76 ("kobject: fix suppressing modalias in uevents delivered over netlink") Cc: stable@vger.kernel.org Signed-off-by: Zijun Hu Reviewed-by: Lk Sii Link: https://lore.kernel.org/r/1717074877-11352-1-git-send-email-quic_zijuhu@quicinc.com Signed-off-by: Greg Kroah-Hartman --- lib/kobject_uevent.c | 17 ++++++++++++++++- 1 file changed, 16 insertions(+), 1 deletion(-) diff --git a/lib/kobject_uevent.c b/lib/kobject_uevent.c index c87d5b6a8a55..38716b2eb671 100644 --- a/lib/kobject_uevent.c +++ b/lib/kobject_uevent.c @@ -432,8 +432,23 @@ static void zap_modalias_env(struct kobj_uevent_env *env) len = strlen(env->envp[i]) + 1; if (i != env->envp_idx - 1) { + /* @env->envp[] contains pointers to @env->buf[] + * with @env->buflen chars, and we are removing + * variable MODALIAS here pointed by @env->envp[i] + * with length @len as shown below: + * + * 0 @env->buf[] @env->buflen + * --------------------------------------------- + * ^ ^ ^ ^ + * | |-> @len <-| target block | + * @env->envp[0] @env->envp[i] @env->envp[i + 1] + * + * so the "target block" indicated above is moved + * backward by @len, and its right size is + * @env->buflen - (@env->envp[i + 1] - @env->envp[0]). + */ memmove(env->envp[i], env->envp[i + 1], - env->buflen - len); + env->buflen - (env->envp[i + 1] - env->envp[0])); for (j = i; j < env->envp_idx - 1; j++) env->envp[j] = env->envp[j + 1] - len; From d4d814159f535865c4f263262fcd41d5013c862d Mon Sep 17 00:00:00 2001 From: Zijun Hu Date: Tue, 2 Jul 2024 22:51:50 +0800 Subject: [PATCH 155/342] devres: Fix devm_krealloc() wasting memory commit c884e3249f753dcef7a2b2023541ac1dc46b318e upstream. Driver API devm_krealloc() calls alloc_dr() with wrong argument @total_new_size, so causes more memory to be allocated than required fix this memory waste by using @new_size as the argument for alloc_dr(). Fixes: f82485722e5d ("devres: provide devm_krealloc()") Cc: stable@vger.kernel.org Signed-off-by: Zijun Hu Link: https://lore.kernel.org/r/1719931914-19035-2-git-send-email-quic_zijuhu@quicinc.com Signed-off-by: Greg Kroah-Hartman --- drivers/base/devres.c | 5 ++++- 1 file changed, 4 insertions(+), 1 deletion(-) diff --git a/drivers/base/devres.c b/drivers/base/devres.c index 586e9a75c840..452541ce0dc8 100644 --- a/drivers/base/devres.c +++ b/drivers/base/devres.c @@ -901,9 +901,12 @@ void *devm_krealloc(struct device *dev, void *ptr, size_t new_size, gfp_t gfp) /* * Otherwise: allocate new, larger chunk. We need to allocate before * taking the lock as most probably the caller uses GFP_KERNEL. + * alloc_dr() will call check_dr_size() to reserve extra memory + * for struct devres automatically, so size @new_size user request + * is delivered to it directly as devm_kmalloc() does. */ new_dr = alloc_dr(devm_kmalloc_release, - total_new_size, gfp, dev_to_node(dev)); + new_size, gfp, dev_to_node(dev)); if (!new_dr) return NULL; From 2fcd485289c858d78e7119ca40577bc5c9efbc71 Mon Sep 17 00:00:00 2001 From: Joy Chakraborty Date: Wed, 12 Jun 2024 08:36:35 +0000 Subject: [PATCH 156/342] rtc: cmos: Fix return value of nvmem callbacks commit 1c184baccf0d5e2ef4cc1562261d0e48508a1c2b upstream. Read/write callbacks registered with nvmem core expect 0 to be returned on success and a negative value to be returned on failure. cmos_nvram_read()/cmos_nvram_write() currently return the number of bytes read or written, fix to return 0 on success and -EIO incase number of bytes requested was not read or written. Fixes: 8b5b7958fd1c ("rtc: cmos: use generic nvmem") Cc: stable@vger.kernel.org Signed-off-by: Joy Chakraborty Reviewed-by: Dan Carpenter Link: https://lore.kernel.org/r/20240612083635.1253039-1-joychakr@google.com Signed-off-by: Alexandre Belloni Signed-off-by: Greg Kroah-Hartman --- drivers/rtc/rtc-cmos.c | 10 ++++------ 1 file changed, 4 insertions(+), 6 deletions(-) diff --git a/drivers/rtc/rtc-cmos.c b/drivers/rtc/rtc-cmos.c index 2c4ccab6e462..a55a1cff2ef0 100644 --- a/drivers/rtc/rtc-cmos.c +++ b/drivers/rtc/rtc-cmos.c @@ -649,11 +649,10 @@ static int cmos_nvram_read(void *priv, unsigned int off, void *val, size_t count) { unsigned char *buf = val; - int retval; off += NVRAM_OFFSET; spin_lock_irq(&rtc_lock); - for (retval = 0; count; count--, off++, retval++) { + for (; count; count--, off++) { if (off < 128) *buf++ = CMOS_READ(off); else if (can_bank2) @@ -663,7 +662,7 @@ static int cmos_nvram_read(void *priv, unsigned int off, void *val, } spin_unlock_irq(&rtc_lock); - return retval; + return count ? -EIO : 0; } static int cmos_nvram_write(void *priv, unsigned int off, void *val, @@ -671,7 +670,6 @@ static int cmos_nvram_write(void *priv, unsigned int off, void *val, { struct cmos_rtc *cmos = priv; unsigned char *buf = val; - int retval; /* NOTE: on at least PCs and Ataris, the boot firmware uses a * checksum on part of the NVRAM data. That's currently ignored @@ -680,7 +678,7 @@ static int cmos_nvram_write(void *priv, unsigned int off, void *val, */ off += NVRAM_OFFSET; spin_lock_irq(&rtc_lock); - for (retval = 0; count; count--, off++, retval++) { + for (; count; count--, off++) { /* don't trash RTC registers */ if (off == cmos->day_alrm || off == cmos->mon_alrm @@ -695,7 +693,7 @@ static int cmos_nvram_write(void *priv, unsigned int off, void *val, } spin_unlock_irq(&rtc_lock); - return retval; + return count ? -EIO : 0; } /*----------------------------------------------------------------*/ From e5ed6a26ffdec0c91cf0b6138afbd675c00ad5fc Mon Sep 17 00:00:00 2001 From: Manish Rangankar Date: Wed, 10 Jul 2024 22:40:53 +0530 Subject: [PATCH 157/342] scsi: qla2xxx: During vport delete send async logout explicitly commit 76f480d7c717368f29a3870f7d64471ce0ff8fb2 upstream. During vport delete, it is observed that during unload we hit a crash because of stale entries in outstanding command array. For all these stale I/O entries, eh_abort was issued and aborted (fast_fail_io = 2009h) but I/Os could not complete while vport delete is in process of deleting. BUG: kernel NULL pointer dereference, address: 000000000000001c #PF: supervisor read access in kernel mode #PF: error_code(0x0000) - not-present page PGD 0 P4D 0 Oops: 0000 [#1] PREEMPT SMP NOPTI Workqueue: qla2xxx_wq qla_do_work [qla2xxx] RIP: 0010:dma_direct_unmap_sg+0x51/0x1e0 RSP: 0018:ffffa1e1e150fc68 EFLAGS: 00010046 RAX: 0000000000000000 RBX: 0000000000000021 RCX: 0000000000000001 RDX: 0000000000000021 RSI: 0000000000000000 RDI: ffff8ce208a7a0d0 RBP: ffff8ce208a7a0d0 R08: 0000000000000000 R09: ffff8ce378aac9c8 R10: ffff8ce378aac8a0 R11: ffffa1e1e150f9d8 R12: 0000000000000000 R13: 0000000000000000 R14: ffff8ce378aac9c8 R15: 0000000000000000 FS: 0000000000000000(0000) GS:ffff8d217f000000(0000) knlGS:0000000000000000 CS: 0010 DS: 0000 ES: 0000 CR0: 0000000080050033 CR2: 000000000000001c CR3: 0000002089acc000 CR4: 0000000000350ee0 Call Trace: qla2xxx_qpair_sp_free_dma+0x417/0x4e0 ? qla2xxx_qpair_sp_compl+0x10d/0x1a0 ? qla2x00_status_entry+0x768/0x2830 ? newidle_balance+0x2f0/0x430 ? dequeue_entity+0x100/0x3c0 ? qla24xx_process_response_queue+0x6a1/0x19e0 ? __schedule+0x2d5/0x1140 ? qla_do_work+0x47/0x60 ? process_one_work+0x267/0x440 ? process_one_work+0x440/0x440 ? worker_thread+0x2d/0x3d0 ? process_one_work+0x440/0x440 ? kthread+0x156/0x180 ? set_kthread_struct+0x50/0x50 ? ret_from_fork+0x22/0x30 Send out async logout explicitly for all the ports during vport delete. Cc: stable@vger.kernel.org Signed-off-by: Manish Rangankar Signed-off-by: Nilesh Javali Link: https://lore.kernel.org/r/20240710171057.35066-8-njavali@marvell.com Reviewed-by: Himanshu Madhani Signed-off-by: Martin K. Petersen Signed-off-by: Greg Kroah-Hartman --- drivers/scsi/qla2xxx/qla_mid.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/drivers/scsi/qla2xxx/qla_mid.c b/drivers/scsi/qla2xxx/qla_mid.c index c7caf322f445..b98c390b4b27 100644 --- a/drivers/scsi/qla2xxx/qla_mid.c +++ b/drivers/scsi/qla2xxx/qla_mid.c @@ -164,7 +164,7 @@ qla24xx_disable_vp(scsi_qla_host_t *vha) atomic_set(&vha->loop_state, LOOP_DOWN); atomic_set(&vha->loop_down_timer, LOOP_DOWN_TIME); list_for_each_entry(fcport, &vha->vp_fcports, list) - fcport->logout_on_delete = 0; + fcport->logout_on_delete = 1; qla2x00_mark_all_devices_lost(vha); From 87db8d7b7520e99de71791260989f06f9c94953d Mon Sep 17 00:00:00 2001 From: Shreyas Deodhar Date: Wed, 10 Jul 2024 22:40:49 +0530 Subject: [PATCH 158/342] scsi: qla2xxx: Fix for possible memory corruption commit c03d740152f78e86945a75b2ad541bf972fab92a upstream. Init Control Block is dereferenced incorrectly. Correctly dereference ICB Cc: stable@vger.kernel.org Signed-off-by: Shreyas Deodhar Signed-off-by: Nilesh Javali Link: https://lore.kernel.org/r/20240710171057.35066-4-njavali@marvell.com Reviewed-by: Himanshu Madhani Signed-off-by: Martin K. Petersen Signed-off-by: Greg Kroah-Hartman --- drivers/scsi/qla2xxx/qla_os.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/drivers/scsi/qla2xxx/qla_os.c b/drivers/scsi/qla2xxx/qla_os.c index 0930bf996cd3..945b9b5e0971 100644 --- a/drivers/scsi/qla2xxx/qla_os.c +++ b/drivers/scsi/qla2xxx/qla_os.c @@ -4453,7 +4453,7 @@ static void qla2x00_number_of_exch(scsi_qla_host_t *vha, u32 *ret_cnt, u16 max_cnt) { u32 temp; - struct init_cb_81xx *icb = (struct init_cb_81xx *)&vha->hw->init_cb; + struct init_cb_81xx *icb = (struct init_cb_81xx *)vha->hw->init_cb; *ret_cnt = FW_DEF_EXCHANGES_CNT; if (max_cnt > vha->hw->max_exchg) From b0c39dcbd8a53c6d7e4d52aa77c7a2b89d94b000 Mon Sep 17 00:00:00 2001 From: Quinn Tran Date: Wed, 10 Jul 2024 22:40:51 +0530 Subject: [PATCH 159/342] scsi: qla2xxx: Fix flash read failure commit 29e222085d8907ccff18ecd931bdd4c6b1f11b92 upstream. Link up failure is observed as a result of flash read failure. Current code does not check flash read return code where it relies on FW checksum to detect the problem. Add check of flash read failure to detect the problem sooner. Reported-by: kernel test robot Reported-by: Dan Carpenter Closes: https://lore.kernel.org/all/202406210815.rPDRDMBi-lkp@intel.com/ Cc: stable@vger.kernel.org Signed-off-by: Quinn Tran Signed-off-by: Nilesh Javali Link: https://lore.kernel.org/r/20240710171057.35066-6-njavali@marvell.com Reviewed-by: Himanshu Madhani Signed-off-by: Martin K. Petersen Signed-off-by: Greg Kroah-Hartman --- drivers/scsi/qla2xxx/qla_init.c | 63 +++++++++++++++---- drivers/scsi/qla2xxx/qla_sup.c | 108 ++++++++++++++++++++++---------- 2 files changed, 125 insertions(+), 46 deletions(-) diff --git a/drivers/scsi/qla2xxx/qla_init.c b/drivers/scsi/qla2xxx/qla_init.c index 8d54f6099802..affb3bc39006 100644 --- a/drivers/scsi/qla2xxx/qla_init.c +++ b/drivers/scsi/qla2xxx/qla_init.c @@ -7696,15 +7696,21 @@ qla28xx_get_aux_images( struct qla27xx_image_status pri_aux_image_status, sec_aux_image_status; bool valid_pri_image = false, valid_sec_image = false; bool active_pri_image = false, active_sec_image = false; + int rc; if (!ha->flt_region_aux_img_status_pri) { ql_dbg(ql_dbg_init, vha, 0x018a, "Primary aux image not addressed\n"); goto check_sec_image; } - qla24xx_read_flash_data(vha, (uint32_t *)&pri_aux_image_status, + rc = qla24xx_read_flash_data(vha, (uint32_t *)&pri_aux_image_status, ha->flt_region_aux_img_status_pri, sizeof(pri_aux_image_status) >> 2); + if (rc) { + ql_log(ql_log_info, vha, 0x01a1, + "Unable to read Primary aux image(%x).\n", rc); + goto check_sec_image; + } qla27xx_print_image(vha, "Primary aux image", &pri_aux_image_status); if (qla28xx_check_aux_image_status_signature(&pri_aux_image_status)) { @@ -7735,9 +7741,15 @@ qla28xx_get_aux_images( goto check_valid_image; } - qla24xx_read_flash_data(vha, (uint32_t *)&sec_aux_image_status, + rc = qla24xx_read_flash_data(vha, (uint32_t *)&sec_aux_image_status, ha->flt_region_aux_img_status_sec, sizeof(sec_aux_image_status) >> 2); + if (rc) { + ql_log(ql_log_info, vha, 0x01a2, + "Unable to read Secondary aux image(%x).\n", rc); + goto check_valid_image; + } + qla27xx_print_image(vha, "Secondary aux image", &sec_aux_image_status); if (qla28xx_check_aux_image_status_signature(&sec_aux_image_status)) { @@ -7794,6 +7806,7 @@ qla27xx_get_active_image(struct scsi_qla_host *vha, struct qla27xx_image_status pri_image_status, sec_image_status; bool valid_pri_image = false, valid_sec_image = false; bool active_pri_image = false, active_sec_image = false; + int rc; if (!ha->flt_region_img_status_pri) { ql_dbg(ql_dbg_init, vha, 0x018a, "Primary image not addressed\n"); @@ -7835,8 +7848,14 @@ qla27xx_get_active_image(struct scsi_qla_host *vha, goto check_valid_image; } - qla24xx_read_flash_data(vha, (uint32_t *)(&sec_image_status), + rc = qla24xx_read_flash_data(vha, (uint32_t *)(&sec_image_status), ha->flt_region_img_status_sec, sizeof(sec_image_status) >> 2); + if (rc) { + ql_log(ql_log_info, vha, 0x01a3, + "Unable to read Secondary image status(%x).\n", rc); + goto check_valid_image; + } + qla27xx_print_image(vha, "Secondary image", &sec_image_status); if (qla27xx_check_image_status_signature(&sec_image_status)) { @@ -7908,11 +7927,10 @@ qla24xx_load_risc_flash(scsi_qla_host_t *vha, uint32_t *srisc_addr, "FW: Loading firmware from flash (%x).\n", faddr); dcode = (uint32_t *)req->ring; - qla24xx_read_flash_data(vha, dcode, faddr, 8); - if (qla24xx_risc_firmware_invalid(dcode)) { + rval = qla24xx_read_flash_data(vha, dcode, faddr, 8); + if (rval || qla24xx_risc_firmware_invalid(dcode)) { ql_log(ql_log_fatal, vha, 0x008c, - "Unable to verify the integrity of flash firmware " - "image.\n"); + "Unable to verify the integrity of flash firmware image (rval %x).\n", rval); ql_log(ql_log_fatal, vha, 0x008d, "Firmware data: %08x %08x %08x %08x.\n", dcode[0], dcode[1], dcode[2], dcode[3]); @@ -7926,7 +7944,12 @@ qla24xx_load_risc_flash(scsi_qla_host_t *vha, uint32_t *srisc_addr, for (j = 0; j < segments; j++) { ql_dbg(ql_dbg_init, vha, 0x008d, "-> Loading segment %u...\n", j); - qla24xx_read_flash_data(vha, dcode, faddr, 10); + rval = qla24xx_read_flash_data(vha, dcode, faddr, 10); + if (rval) { + ql_log(ql_log_fatal, vha, 0x016a, + "-> Unable to read segment addr + size .\n"); + return QLA_FUNCTION_FAILED; + } risc_addr = be32_to_cpu((__force __be32)dcode[2]); risc_size = be32_to_cpu((__force __be32)dcode[3]); if (!*srisc_addr) { @@ -7942,7 +7965,13 @@ qla24xx_load_risc_flash(scsi_qla_host_t *vha, uint32_t *srisc_addr, ql_dbg(ql_dbg_init, vha, 0x008e, "-> Loading fragment %u: %#x <- %#x (%#lx dwords)...\n", fragment, risc_addr, faddr, dlen); - qla24xx_read_flash_data(vha, dcode, faddr, dlen); + rval = qla24xx_read_flash_data(vha, dcode, faddr, dlen); + if (rval) { + ql_log(ql_log_fatal, vha, 0x016b, + "-> Unable to read fragment(faddr %#x dlen %#lx).\n", + faddr, dlen); + return QLA_FUNCTION_FAILED; + } for (i = 0; i < dlen; i++) dcode[i] = swab32(dcode[i]); @@ -7972,7 +8001,14 @@ qla24xx_load_risc_flash(scsi_qla_host_t *vha, uint32_t *srisc_addr, fwdt->length = 0; dcode = (uint32_t *)req->ring; - qla24xx_read_flash_data(vha, dcode, faddr, 7); + + rval = qla24xx_read_flash_data(vha, dcode, faddr, 7); + if (rval) { + ql_log(ql_log_fatal, vha, 0x016c, + "-> Unable to read template size.\n"); + goto failed; + } + risc_size = be32_to_cpu((__force __be32)dcode[2]); ql_dbg(ql_dbg_init, vha, 0x0161, "-> fwdt%u template array at %#x (%#x dwords)\n", @@ -7998,11 +8034,12 @@ qla24xx_load_risc_flash(scsi_qla_host_t *vha, uint32_t *srisc_addr, } dcode = fwdt->template; - qla24xx_read_flash_data(vha, dcode, faddr, risc_size); + rval = qla24xx_read_flash_data(vha, dcode, faddr, risc_size); - if (!qla27xx_fwdt_template_valid(dcode)) { + if (rval || !qla27xx_fwdt_template_valid(dcode)) { ql_log(ql_log_warn, vha, 0x0165, - "-> fwdt%u failed template validate\n", j); + "-> fwdt%u failed template validate (rval %x)\n", + j, rval); goto failed; } diff --git a/drivers/scsi/qla2xxx/qla_sup.c b/drivers/scsi/qla2xxx/qla_sup.c index 0fa9c529fca1..c55135f1463e 100644 --- a/drivers/scsi/qla2xxx/qla_sup.c +++ b/drivers/scsi/qla2xxx/qla_sup.c @@ -555,6 +555,7 @@ qla2xxx_find_flt_start(scsi_qla_host_t *vha, uint32_t *start) struct qla_flt_location *fltl = (void *)req->ring; uint32_t *dcode = (uint32_t *)req->ring; uint8_t *buf = (void *)req->ring, *bcode, last_image; + int rc; /* * FLT-location structure resides after the last PCI region. @@ -584,14 +585,24 @@ qla2xxx_find_flt_start(scsi_qla_host_t *vha, uint32_t *start) pcihdr = 0; do { /* Verify PCI expansion ROM header. */ - qla24xx_read_flash_data(vha, dcode, pcihdr >> 2, 0x20); + rc = qla24xx_read_flash_data(vha, dcode, pcihdr >> 2, 0x20); + if (rc) { + ql_log(ql_log_info, vha, 0x016d, + "Unable to read PCI Expansion Rom Header (%x).\n", rc); + return QLA_FUNCTION_FAILED; + } bcode = buf + (pcihdr % 4); if (bcode[0x0] != 0x55 || bcode[0x1] != 0xaa) goto end; /* Locate PCI data structure. */ pcids = pcihdr + ((bcode[0x19] << 8) | bcode[0x18]); - qla24xx_read_flash_data(vha, dcode, pcids >> 2, 0x20); + rc = qla24xx_read_flash_data(vha, dcode, pcids >> 2, 0x20); + if (rc) { + ql_log(ql_log_info, vha, 0x0179, + "Unable to read PCI Data Structure (%x).\n", rc); + return QLA_FUNCTION_FAILED; + } bcode = buf + (pcihdr % 4); /* Validate signature of PCI data structure. */ @@ -606,7 +617,12 @@ qla2xxx_find_flt_start(scsi_qla_host_t *vha, uint32_t *start) } while (!last_image); /* Now verify FLT-location structure. */ - qla24xx_read_flash_data(vha, dcode, pcihdr >> 2, sizeof(*fltl) >> 2); + rc = qla24xx_read_flash_data(vha, dcode, pcihdr >> 2, sizeof(*fltl) >> 2); + if (rc) { + ql_log(ql_log_info, vha, 0x017a, + "Unable to read FLT (%x).\n", rc); + return QLA_FUNCTION_FAILED; + } if (memcmp(fltl->sig, "QFLT", 4)) goto end; @@ -2605,13 +2621,18 @@ qla24xx_read_optrom_data(struct scsi_qla_host *vha, void *buf, uint32_t offset, uint32_t length) { struct qla_hw_data *ha = vha->hw; + int rc; /* Suspend HBA. */ scsi_block_requests(vha->host); set_bit(MBX_UPDATE_FLASH_ACTIVE, &ha->mbx_cmd_flags); /* Go with read. */ - qla24xx_read_flash_data(vha, buf, offset >> 2, length >> 2); + rc = qla24xx_read_flash_data(vha, buf, offset >> 2, length >> 2); + if (rc) { + ql_log(ql_log_info, vha, 0x01a0, + "Unable to perform optrom read(%x).\n", rc); + } /* Resume HBA. */ clear_bit(MBX_UPDATE_FLASH_ACTIVE, &ha->mbx_cmd_flags); @@ -3412,7 +3433,7 @@ qla24xx_get_flash_version(scsi_qla_host_t *vha, void *mbuf) struct active_regions active_regions = { }; if (IS_P3P_TYPE(ha)) - return ret; + return QLA_SUCCESS; if (!mbuf) return QLA_FUNCTION_FAILED; @@ -3432,20 +3453,31 @@ qla24xx_get_flash_version(scsi_qla_host_t *vha, void *mbuf) do { /* Verify PCI expansion ROM header. */ - qla24xx_read_flash_data(vha, dcode, pcihdr >> 2, 0x20); + ret = qla24xx_read_flash_data(vha, dcode, pcihdr >> 2, 0x20); + if (ret) { + ql_log(ql_log_info, vha, 0x017d, + "Unable to read PCI EXP Rom Header(%x).\n", ret); + return QLA_FUNCTION_FAILED; + } + bcode = mbuf + (pcihdr % 4); if (memcmp(bcode, "\x55\xaa", 2)) { /* No signature */ ql_log(ql_log_fatal, vha, 0x0059, "No matching ROM signature.\n"); - ret = QLA_FUNCTION_FAILED; - break; + return QLA_FUNCTION_FAILED; } /* Locate PCI data structure. */ pcids = pcihdr + ((bcode[0x19] << 8) | bcode[0x18]); - qla24xx_read_flash_data(vha, dcode, pcids >> 2, 0x20); + ret = qla24xx_read_flash_data(vha, dcode, pcids >> 2, 0x20); + if (ret) { + ql_log(ql_log_info, vha, 0x018e, + "Unable to read PCI Data Structure (%x).\n", ret); + return QLA_FUNCTION_FAILED; + } + bcode = mbuf + (pcihdr % 4); /* Validate signature of PCI data structure. */ @@ -3454,8 +3486,7 @@ qla24xx_get_flash_version(scsi_qla_host_t *vha, void *mbuf) ql_log(ql_log_fatal, vha, 0x005a, "PCI data struct not found pcir_adr=%x.\n", pcids); ql_dump_buffer(ql_dbg_init, vha, 0x0059, dcode, 32); - ret = QLA_FUNCTION_FAILED; - break; + return QLA_FUNCTION_FAILED; } /* Read version */ @@ -3507,20 +3538,26 @@ qla24xx_get_flash_version(scsi_qla_host_t *vha, void *mbuf) faddr = ha->flt_region_fw_sec; } - qla24xx_read_flash_data(vha, dcode, faddr, 8); - if (qla24xx_risc_firmware_invalid(dcode)) { - ql_log(ql_log_warn, vha, 0x005f, - "Unrecognized fw revision at %x.\n", - ha->flt_region_fw * 4); - ql_dump_buffer(ql_dbg_init, vha, 0x005f, dcode, 32); + ret = qla24xx_read_flash_data(vha, dcode, faddr, 8); + if (ret) { + ql_log(ql_log_info, vha, 0x019e, + "Unable to read FW version (%x).\n", ret); + return ret; } else { - for (i = 0; i < 4; i++) - ha->fw_revision[i] = + if (qla24xx_risc_firmware_invalid(dcode)) { + ql_log(ql_log_warn, vha, 0x005f, + "Unrecognized fw revision at %x.\n", + ha->flt_region_fw * 4); + ql_dump_buffer(ql_dbg_init, vha, 0x005f, dcode, 32); + } else { + for (i = 0; i < 4; i++) + ha->fw_revision[i] = be32_to_cpu((__force __be32)dcode[4+i]); - ql_dbg(ql_dbg_init, vha, 0x0060, - "Firmware revision (flash) %u.%u.%u (%x).\n", - ha->fw_revision[0], ha->fw_revision[1], - ha->fw_revision[2], ha->fw_revision[3]); + ql_dbg(ql_dbg_init, vha, 0x0060, + "Firmware revision (flash) %u.%u.%u (%x).\n", + ha->fw_revision[0], ha->fw_revision[1], + ha->fw_revision[2], ha->fw_revision[3]); + } } /* Check for golden firmware and get version if available */ @@ -3531,18 +3568,23 @@ qla24xx_get_flash_version(scsi_qla_host_t *vha, void *mbuf) memset(ha->gold_fw_version, 0, sizeof(ha->gold_fw_version)); faddr = ha->flt_region_gold_fw; - qla24xx_read_flash_data(vha, dcode, ha->flt_region_gold_fw, 8); - if (qla24xx_risc_firmware_invalid(dcode)) { - ql_log(ql_log_warn, vha, 0x0056, - "Unrecognized golden fw at %#x.\n", faddr); - ql_dump_buffer(ql_dbg_init, vha, 0x0056, dcode, 32); + ret = qla24xx_read_flash_data(vha, dcode, ha->flt_region_gold_fw, 8); + if (ret) { + ql_log(ql_log_info, vha, 0x019f, + "Unable to read Gold FW version (%x).\n", ret); return ret; + } else { + if (qla24xx_risc_firmware_invalid(dcode)) { + ql_log(ql_log_warn, vha, 0x0056, + "Unrecognized golden fw at %#x.\n", faddr); + ql_dump_buffer(ql_dbg_init, vha, 0x0056, dcode, 32); + return QLA_FUNCTION_FAILED; + } + + for (i = 0; i < 4; i++) + ha->gold_fw_version[i] = + be32_to_cpu((__force __be32)dcode[4+i]); } - - for (i = 0; i < 4; i++) - ha->gold_fw_version[i] = - be32_to_cpu((__force __be32)dcode[4+i]); - return ret; } From 57ba7563712227647f82a92547e82c96cd350553 Mon Sep 17 00:00:00 2001 From: Shreyas Deodhar Date: Wed, 10 Jul 2024 22:40:52 +0530 Subject: [PATCH 160/342] scsi: qla2xxx: Complete command early within lock commit 4475afa2646d3fec176fc4d011d3879b26cb26e3 upstream. A crash was observed while performing NPIV and FW reset, BUG: kernel NULL pointer dereference, address: 000000000000001c #PF: supervisor read access in kernel mode #PF: error_code(0x0000) - not-present page PGD 0 P4D 0 Oops: 0000 1 PREEMPT_RT SMP NOPTI RIP: 0010:dma_direct_unmap_sg+0x51/0x1e0 RSP: 0018:ffffc90026f47b88 EFLAGS: 00010246 RAX: 0000000000000000 RBX: 0000000000000021 RCX: 0000000000000002 RDX: 0000000000000021 RSI: 0000000000000000 RDI: ffff8881041130d0 RBP: ffff8881041130d0 R08: 0000000000000000 R09: 0000000000000034 R10: ffffc90026f47c48 R11: 0000000000000031 R12: 0000000000000000 R13: 0000000000000000 R14: ffff8881565e4a20 R15: 0000000000000000 FS: 00007f4c69ed3d00(0000) GS:ffff889faac80000(0000) knlGS:0000000000000000 CS: 0010 DS: 0000 ES: 0000 CR0: 0000000080050033 CR2: 000000000000001c CR3: 0000000288a50002 CR4: 00000000007706e0 DR0: 0000000000000000 DR1: 0000000000000000 DR2: 0000000000000000 DR3: 0000000000000000 DR6: 00000000fffe0ff0 DR7: 0000000000000400 PKRU: 55555554 Call Trace: ? __die_body+0x1a/0x60 ? page_fault_oops+0x16f/0x4a0 ? do_user_addr_fault+0x174/0x7f0 ? exc_page_fault+0x69/0x1a0 ? asm_exc_page_fault+0x22/0x30 ? dma_direct_unmap_sg+0x51/0x1e0 ? preempt_count_sub+0x96/0xe0 qla2xxx_qpair_sp_free_dma+0x29f/0x3b0 [qla2xxx] qla2xxx_qpair_sp_compl+0x60/0x80 [qla2xxx] __qla2x00_abort_all_cmds+0xa2/0x450 [qla2xxx] The command completion was done early while aborting the commands in driver unload path but outside lock to avoid the WARN_ON condition of performing dma_free_attr within the lock. However this caused race condition while command completion via multiple paths causing system crash. Hence complete the command early in unload path but within the lock to avoid race condition. Fixes: 0367076b0817 ("scsi: qla2xxx: Perform lockless command completion in abort path") Cc: stable@vger.kernel.org Signed-off-by: Shreyas Deodhar Signed-off-by: Nilesh Javali Link: https://lore.kernel.org/r/20240710171057.35066-7-njavali@marvell.com Reviewed-by: Himanshu Madhani Signed-off-by: Martin K. Petersen Signed-off-by: Greg Kroah-Hartman --- drivers/scsi/qla2xxx/qla_os.c | 5 ----- 1 file changed, 5 deletions(-) diff --git a/drivers/scsi/qla2xxx/qla_os.c b/drivers/scsi/qla2xxx/qla_os.c index 945b9b5e0971..00b971d1c419 100644 --- a/drivers/scsi/qla2xxx/qla_os.c +++ b/drivers/scsi/qla2xxx/qla_os.c @@ -1752,14 +1752,9 @@ __qla2x00_abort_all_cmds(struct qla_qpair *qp, int res) for (cnt = 1; cnt < req->num_outstanding_cmds; cnt++) { sp = req->outstanding_cmds[cnt]; if (sp) { - /* - * perform lockless completion during driver unload - */ if (qla2x00_chip_is_down(vha)) { req->outstanding_cmds[cnt] = NULL; - spin_unlock_irqrestore(qp->qp_lock_ptr, flags); sp->done(sp, res); - spin_lock_irqsave(qp->qp_lock_ptr, flags); continue; } From a3ab508a4853a9f5ae25a7816a4889f09938f63c Mon Sep 17 00:00:00 2001 From: Nilesh Javali Date: Wed, 10 Jul 2024 22:40:48 +0530 Subject: [PATCH 161/342] scsi: qla2xxx: validate nvme_local_port correctly commit eb1d4ce2609584eeb7694866f34d4b213caa3af9 upstream. The driver load failed with error message, qla2xxx [0000:04:00.0]-ffff:0: register_localport failed: ret=ffffffef and with a kernel crash, BUG: unable to handle kernel NULL pointer dereference at 0000000000000070 Workqueue: events_unbound qla_register_fcport_fn [qla2xxx] RIP: 0010:nvme_fc_register_remoteport+0x16/0x430 [nvme_fc] RSP: 0018:ffffaaa040eb3d98 EFLAGS: 00010282 RAX: 0000000000000000 RBX: ffff9dfb46b78c00 RCX: 0000000000000000 RDX: ffff9dfb46b78da8 RSI: ffffaaa040eb3e08 RDI: 0000000000000000 RBP: ffff9dfb612a0a58 R08: ffffffffaf1d6270 R09: 3a34303a30303030 R10: 34303a303030305b R11: 2078787832616c71 R12: ffff9dfb46b78dd4 R13: ffff9dfb46b78c24 R14: ffff9dfb41525300 R15: ffff9dfb46b78da8 FS: 0000000000000000(0000) GS:ffff9dfc67c00000(0000) knlGS:0000000000000000 CS: 0010 DS: 0000 ES: 0000 CR0: 0000000080050033 CR2: 0000000000000070 CR3: 000000018da10004 CR4: 00000000000206f0 Call Trace: qla_nvme_register_remote+0xeb/0x1f0 [qla2xxx] ? qla2x00_dfs_create_rport+0x231/0x270 [qla2xxx] qla2x00_update_fcport+0x2a1/0x3c0 [qla2xxx] qla_register_fcport_fn+0x54/0xc0 [qla2xxx] Exit the qla_nvme_register_remote() function when qla_nvme_register_hba() fails and correctly validate nvme_local_port. Cc: stable@vger.kernel.org Signed-off-by: Nilesh Javali Link: https://lore.kernel.org/r/20240710171057.35066-3-njavali@marvell.com Reviewed-by: Himanshu Madhani Signed-off-by: Martin K. Petersen Signed-off-by: Greg Kroah-Hartman --- drivers/scsi/qla2xxx/qla_nvme.c | 5 ++++- 1 file changed, 4 insertions(+), 1 deletion(-) diff --git a/drivers/scsi/qla2xxx/qla_nvme.c b/drivers/scsi/qla2xxx/qla_nvme.c index 6dad7787f20d..28a5b40e0f32 100644 --- a/drivers/scsi/qla2xxx/qla_nvme.c +++ b/drivers/scsi/qla2xxx/qla_nvme.c @@ -27,7 +27,10 @@ int qla_nvme_register_remote(struct scsi_qla_host *vha, struct fc_port *fcport) return 0; } - if (!vha->nvme_local_port && qla_nvme_register_hba(vha)) + if (qla_nvme_register_hba(vha)) + return 0; + + if (!vha->nvme_local_port) return 0; if (!(fcport->nvme_prli_service_param & From 3b8e1b7d26d65a35fbad8e398e8e35ca561f8fd2 Mon Sep 17 00:00:00 2001 From: Marco Cavenati Date: Mon, 24 Jun 2024 23:10:55 +0300 Subject: [PATCH 162/342] perf/x86/intel/pt: Fix topa_entry base length commit 5638bd722a44bbe97c1a7b3fae5b9efddb3e70ff upstream. topa_entry->base needs to store a pfn. It obviously needs to be large enough to store the largest possible x86 pfn which is MAXPHYADDR-PAGE_SIZE (52-12). So it is 4 bits too small. Increase the size of topa_entry->base from 36 bits to 40 bits. Note, systems where physical addresses can be 256TiB or more are affected. [ Adrian: Amend commit message as suggested by Dave Hansen ] Fixes: 52ca9ced3f70 ("perf/x86/intel/pt: Add Intel PT PMU driver") Signed-off-by: Marco Cavenati Signed-off-by: Adrian Hunter Signed-off-by: Peter Zijlstra (Intel) Reviewed-by: Adrian Hunter Cc: stable@vger.kernel.org Link: https://lore.kernel.org/r/20240624201101.60186-2-adrian.hunter@intel.com Signed-off-by: Greg Kroah-Hartman --- arch/x86/events/intel/pt.h | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-) diff --git a/arch/x86/events/intel/pt.h b/arch/x86/events/intel/pt.h index 96906a62aacd..f5e46c04c145 100644 --- a/arch/x86/events/intel/pt.h +++ b/arch/x86/events/intel/pt.h @@ -33,8 +33,8 @@ struct topa_entry { u64 rsvd2 : 1; u64 size : 4; u64 rsvd3 : 2; - u64 base : 36; - u64 rsvd4 : 16; + u64 base : 40; + u64 rsvd4 : 12; }; /* TSC to Core Crystal Clock Ratio */ From a49321257f62df5ca4a905c69ff7fb40d1f90209 Mon Sep 17 00:00:00 2001 From: Adrian Hunter Date: Mon, 24 Jun 2024 23:10:56 +0300 Subject: [PATCH 163/342] perf/x86/intel/pt: Fix a topa_entry base address calculation commit ad97196379d0b8cb24ef3d5006978a6554e6467f upstream. topa_entry->base is a bit-field. Bit-fields are not promoted to a 64-bit type, even if the underlying type is 64-bit, and so, if necessary, must be cast to a larger type when calculations are done. Fix a topa_entry->base address calculation by adding a cast. Without the cast, the address was limited to 36-bits i.e. 64GiB. The address calculation is used on systems that do not support Multiple Entry ToPA (only Broadwell), and affects physical addresses on or above 64GiB. Instead of writing to the correct address, the address comprising the first 36 bits would be written to. Intel PT snapshot and sampling modes are not affected. Fixes: 52ca9ced3f70 ("perf/x86/intel/pt: Add Intel PT PMU driver") Reported-by: Dave Hansen Signed-off-by: Adrian Hunter Signed-off-by: Peter Zijlstra (Intel) Cc: stable@vger.kernel.org Link: https://lore.kernel.org/r/20240624201101.60186-3-adrian.hunter@intel.com Signed-off-by: Greg Kroah-Hartman --- arch/x86/events/intel/pt.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/arch/x86/events/intel/pt.c b/arch/x86/events/intel/pt.c index d97d34b4669b..da7e8c2b5347 100644 --- a/arch/x86/events/intel/pt.c +++ b/arch/x86/events/intel/pt.c @@ -861,7 +861,7 @@ static void pt_update_head(struct pt *pt) */ static void *pt_buffer_region(struct pt_buffer *buf) { - return phys_to_virt(TOPA_ENTRY(buf->cur, buf->cur_idx)->base << TOPA_SHIFT); + return phys_to_virt((phys_addr_t)TOPA_ENTRY(buf->cur, buf->cur_idx)->base << TOPA_SHIFT); } /** From 9cba1ec637f304b6a820fdf21b80f8222341b3d1 Mon Sep 17 00:00:00 2001 From: Joy Chakraborty Date: Wed, 12 Jun 2024 08:08:31 +0000 Subject: [PATCH 164/342] rtc: isl1208: Fix return value of nvmem callbacks commit 70f1ae5f0e7f44edf842444044615da7b59838c1 upstream. Read/write callbacks registered with nvmem core expect 0 to be returned on success and a negative value to be returned on failure. isl1208_nvmem_read()/isl1208_nvmem_write() currently return the number of bytes read/written on success, fix to return 0 on success and negative on failure. Fixes: c3544f6f51ed ("rtc: isl1208: Add new style nvmem support to driver") Cc: stable@vger.kernel.org Signed-off-by: Joy Chakraborty Link: https://lore.kernel.org/r/20240612080831.1227131-1-joychakr@google.com Signed-off-by: Alexandre Belloni Signed-off-by: Greg Kroah-Hartman --- drivers/rtc/rtc-isl1208.c | 11 ++++------- 1 file changed, 4 insertions(+), 7 deletions(-) diff --git a/drivers/rtc/rtc-isl1208.c b/drivers/rtc/rtc-isl1208.c index ebb691fa48a6..cba0dfe21a15 100644 --- a/drivers/rtc/rtc-isl1208.c +++ b/drivers/rtc/rtc-isl1208.c @@ -743,14 +743,13 @@ static int isl1208_nvmem_read(void *priv, unsigned int off, void *buf, { struct isl1208_state *isl1208 = priv; struct i2c_client *client = to_i2c_client(isl1208->rtc->dev.parent); - int ret; /* nvmem sanitizes offset/count for us, but count==0 is possible */ if (!count) return count; - ret = isl1208_i2c_read_regs(client, ISL1208_REG_USR1 + off, buf, + + return isl1208_i2c_read_regs(client, ISL1208_REG_USR1 + off, buf, count); - return ret == 0 ? count : ret; } static int isl1208_nvmem_write(void *priv, unsigned int off, void *buf, @@ -758,15 +757,13 @@ static int isl1208_nvmem_write(void *priv, unsigned int off, void *buf, { struct isl1208_state *isl1208 = priv; struct i2c_client *client = to_i2c_client(isl1208->rtc->dev.parent); - int ret; /* nvmem sanitizes off/count for us, but count==0 is possible */ if (!count) return count; - ret = isl1208_i2c_set_regs(client, ISL1208_REG_USR1 + off, buf, - count); - return ret == 0 ? count : ret; + return isl1208_i2c_set_regs(client, ISL1208_REG_USR1 + off, buf, + count); } static const struct nvmem_config isl1208_nvmem_config = { From 19f108b3d1cafab159078a26ac93a64cab47258b Mon Sep 17 00:00:00 2001 From: Thomas Gleixner Date: Thu, 11 Jul 2024 22:25:21 +0200 Subject: [PATCH 165/342] watchdog/perf: properly initialize the turbo mode timestamp and rearm counter commit f944ffcbc2e1c759764850261670586ddf3bdabb upstream. For systems on which the performance counter can expire early due to turbo modes the watchdog handler has a safety net in place which validates that since the last watchdog event there has at least 4/5th of the watchdog period elapsed. This works reliably only after the first watchdog event because the per CPU variable which holds the timestamp of the last event is never initialized. So a first spurious event will validate against a timestamp of 0 which results in a delta which is likely to be way over the 4/5 threshold of the period. As this might happen before the first watchdog hrtimer event increments the watchdog counter, this can lead to false positives. Fix this by initializing the timestamp before enabling the hardware event. Reset the rearm counter as well, as that might be non zero after the watchdog was disabled and reenabled. Link: https://lkml.kernel.org/r/87frsfu15a.ffs@tglx Fixes: 7edaeb6841df ("kernel/watchdog: Prevent false positives with turbo modes") Signed-off-by: Thomas Gleixner Cc: Arjan van de Ven Cc: Peter Zijlstra Cc: Signed-off-by: Andrew Morton Signed-off-by: Greg Kroah-Hartman --- kernel/watchdog_hld.c | 11 ++++++++--- 1 file changed, 8 insertions(+), 3 deletions(-) diff --git a/kernel/watchdog_hld.c b/kernel/watchdog_hld.c index 1e8a49dc956e..8ba4b269ab89 100644 --- a/kernel/watchdog_hld.c +++ b/kernel/watchdog_hld.c @@ -91,11 +91,15 @@ static bool watchdog_check_timestamp(void) __this_cpu_write(last_timestamp, now); return true; } -#else -static inline bool watchdog_check_timestamp(void) + +static void watchdog_init_timestamp(void) { - return true; + __this_cpu_write(nmi_rearmed, 0); + __this_cpu_write(last_timestamp, ktime_get_mono_fast_ns()); } +#else +static inline bool watchdog_check_timestamp(void) { return true; } +static inline void watchdog_init_timestamp(void) { } #endif static struct perf_event_attr wd_hw_attr = { @@ -196,6 +200,7 @@ void hardlockup_detector_perf_enable(void) if (!atomic_fetch_inc(&watchdog_cpus)) pr_info("Enabled. Permanently consumes one hw-PMU counter.\n"); + watchdog_init_timestamp(); perf_event_enable(this_cpu_read(watchdog_ev)); } From 9667d46f8a7778932c7cdd3391e1ba8a47c3095d Mon Sep 17 00:00:00 2001 From: Jiaxun Yang Date: Fri, 14 Jun 2024 16:40:15 +0100 Subject: [PATCH 166/342] platform: mips: cpu_hwmon: Disable driver on unsupported hardware commit f4d430db17b4ef4e9c3c352a04b2fe3c93011978 upstream. cpu_hwmon is unsupported on CPUs without loongson_chiptemp register and csr. Cc: stable@vger.kernel.org Signed-off-by: Jiaxun Yang Signed-off-by: Thomas Bogendoerfer Signed-off-by: Greg Kroah-Hartman --- drivers/platform/mips/cpu_hwmon.c | 3 +++ 1 file changed, 3 insertions(+) diff --git a/drivers/platform/mips/cpu_hwmon.c b/drivers/platform/mips/cpu_hwmon.c index d8c5f9195f85..2ac2f31090f9 100644 --- a/drivers/platform/mips/cpu_hwmon.c +++ b/drivers/platform/mips/cpu_hwmon.c @@ -139,6 +139,9 @@ static int __init loongson_hwmon_init(void) csr_temp_enable = csr_readl(LOONGSON_CSR_FEATURES) & LOONGSON_CSRF_TEMP; + if (!csr_temp_enable && !loongson_chiptemp[0]) + return -ENODEV; + nr_packages = loongson_sysconf.nr_cpus / loongson_sysconf.cores_per_package; From 94ee7ff99b87435ec63211f632918dc7f44dac79 Mon Sep 17 00:00:00 2001 From: Bart Van Assche Date: Wed, 5 Jun 2024 08:51:01 -0600 Subject: [PATCH 167/342] RDMA/iwcm: Fix a use-after-free related to destroying CM IDs commit aee2424246f9f1dadc33faa78990c1e2eb7826e4 upstream. iw_conn_req_handler() associates a new struct rdma_id_private (conn_id) with an existing struct iw_cm_id (cm_id) as follows: conn_id->cm_id.iw = cm_id; cm_id->context = conn_id; cm_id->cm_handler = cma_iw_handler; rdma_destroy_id() frees both the cm_id and the struct rdma_id_private. Make sure that cm_work_handler() does not trigger a use-after-free by only freeing of the struct rdma_id_private after all pending work has finished. Cc: stable@vger.kernel.org Fixes: 59c68ac31e15 ("iw_cm: free cm_id resources on the last deref") Reviewed-by: Zhu Yanjun Tested-by: Shin'ichiro Kawasaki Signed-off-by: Bart Van Assche Link: https://lore.kernel.org/r/20240605145117.397751-6-bvanassche@acm.org Signed-off-by: Leon Romanovsky Signed-off-by: Greg Kroah-Hartman --- drivers/infiniband/core/iwcm.c | 11 +++++++---- 1 file changed, 7 insertions(+), 4 deletions(-) diff --git a/drivers/infiniband/core/iwcm.c b/drivers/infiniband/core/iwcm.c index 75b6da00065a..7a6747850aea 100644 --- a/drivers/infiniband/core/iwcm.c +++ b/drivers/infiniband/core/iwcm.c @@ -370,8 +370,10 @@ EXPORT_SYMBOL(iw_cm_disconnect); * * Clean up all resources associated with the connection and release * the initial reference taken by iw_create_cm_id. + * + * Returns true if and only if the last cm_id_priv reference has been dropped. */ -static void destroy_cm_id(struct iw_cm_id *cm_id) +static bool destroy_cm_id(struct iw_cm_id *cm_id) { struct iwcm_id_private *cm_id_priv; struct ib_qp *qp; @@ -441,7 +443,7 @@ static void destroy_cm_id(struct iw_cm_id *cm_id) iwpm_remove_mapping(&cm_id->local_addr, RDMA_NL_IWCM); } - (void)iwcm_deref_id(cm_id_priv); + return iwcm_deref_id(cm_id_priv); } /* @@ -452,7 +454,8 @@ static void destroy_cm_id(struct iw_cm_id *cm_id) */ void iw_destroy_cm_id(struct iw_cm_id *cm_id) { - destroy_cm_id(cm_id); + if (!destroy_cm_id(cm_id)) + flush_workqueue(iwcm_wq); } EXPORT_SYMBOL(iw_destroy_cm_id); @@ -1036,7 +1039,7 @@ static void cm_work_handler(struct work_struct *_work) if (!test_bit(IWCM_F_DROP_EVENTS, &cm_id_priv->flags)) { ret = process_event(cm_id_priv, &levent); if (ret) - destroy_cm_id(&cm_id_priv->id); + WARN_ON_ONCE(destroy_cm_id(&cm_id_priv->id)); } else pr_debug("dropping event %d\n", levent.event); if (iwcm_deref_id(cm_id_priv)) From 24933a55bfaf142f943b57d0b1ce8e2f5a32bae9 Mon Sep 17 00:00:00 2001 From: Michael Ellerman Date: Mon, 20 May 2024 16:26:47 +1000 Subject: [PATCH 168/342] selftests/sigaltstack: Fix ppc64 GCC build MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit commit 17c743b9da9e0d073ff19fd5313f521744514939 upstream. Building the sigaltstack test with GCC on 64-bit powerpc errors with: gcc -Wall sas.c -o /home/michael/linux/.build/kselftest/sigaltstack/sas In file included from sas.c:23: current_stack_pointer.h:22:2: error: #error "implement current_stack_pointer equivalent" 22 | #error "implement current_stack_pointer equivalent" | ^~~~~ sas.c: In function ‘my_usr1’: sas.c:50:13: error: ‘sp’ undeclared (first use in this function); did you mean ‘p’? 50 | if (sp < (unsigned long)sstack || | ^~ This happens because GCC doesn't define __ppc__ for 64-bit builds, only 32-bit builds. Instead use __powerpc__ to detect powerpc builds, which is defined by clang and GCC for 64-bit and 32-bit builds. Fixes: 05107edc9101 ("selftests: sigaltstack: fix -Wuninitialized") Cc: stable@vger.kernel.org # v6.3+ Signed-off-by: Michael Ellerman Link: https://msgid.link/20240520062647.688667-1-mpe@ellerman.id.au Signed-off-by: Greg Kroah-Hartman --- tools/testing/selftests/sigaltstack/current_stack_pointer.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/tools/testing/selftests/sigaltstack/current_stack_pointer.h b/tools/testing/selftests/sigaltstack/current_stack_pointer.h index ea9bdf3a90b1..09da8f1011ce 100644 --- a/tools/testing/selftests/sigaltstack/current_stack_pointer.h +++ b/tools/testing/selftests/sigaltstack/current_stack_pointer.h @@ -8,7 +8,7 @@ register unsigned long sp asm("sp"); register unsigned long sp asm("esp"); #elif __loongarch64 register unsigned long sp asm("$sp"); -#elif __ppc__ +#elif __powerpc__ register unsigned long sp asm("r1"); #elif __s390x__ register unsigned long sp asm("%15"); From 4e8f70d3cc5ebe74cd2884fbde8b2f1478c26463 Mon Sep 17 00:00:00 2001 From: Ilya Dryomov Date: Tue, 23 Jul 2024 18:08:08 +0200 Subject: [PATCH 169/342] rbd: don't assume rbd_is_lock_owner() for exclusive mappings commit 3ceccb14f5576e02b81cc8b105ab81f224bd87f6 upstream. Expanding on the previous commit, assuming that rbd_is_lock_owner() always returns true (i.e. that we are either in RBD_LOCK_STATE_LOCKED or RBD_LOCK_STATE_QUIESCING) if the mapping is exclusive is wrong too. In case ceph_cls_set_cookie() fails, the lock would be temporarily released even if the mapping is exclusive, meaning that we can end up even in RBD_LOCK_STATE_UNLOCKED. IOW, exclusive mappings are really "just" about disabling automatic lock transitions (as documented in the man page), not about grabbing the lock and holding on to it whatever it takes. Cc: stable@vger.kernel.org Fixes: 637cd060537d ("rbd: new exclusive lock wait/wake code") Signed-off-by: Ilya Dryomov Reviewed-by: Dongsheng Yang Signed-off-by: Greg Kroah-Hartman --- drivers/block/rbd.c | 5 ----- 1 file changed, 5 deletions(-) diff --git a/drivers/block/rbd.c b/drivers/block/rbd.c index 5b102d333a41..f693deafb002 100644 --- a/drivers/block/rbd.c +++ b/drivers/block/rbd.c @@ -6660,11 +6660,6 @@ static int rbd_add_acquire_lock(struct rbd_device *rbd_dev) if (ret) return ret; - /* - * The lock may have been released by now, unless automatic lock - * transitions are disabled. - */ - rbd_assert(!rbd_dev->opts->exclusive || rbd_is_lock_owner(rbd_dev)); return 0; } From 636163de03cc6922995851071f7e1f607dc5073a Mon Sep 17 00:00:00 2001 From: Jiaxun Yang Date: Sun, 16 Jun 2024 18:54:24 +0100 Subject: [PATCH 170/342] MIPS: ip30: ip30-console: Add missing include MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit commit 8de4ed75bd14ed197119ac509c6902a8561e0c1c upstream. Include linux/processor.h to fix build error: arch/mips/sgi-ip30/ip30-console.c: In function ‘prom_putchar’: arch/mips/sgi-ip30/ip30-console.c:21:17: error: implicit declaration of function ‘cpu_relax’ [-Werror=implicit-function-declaration] 21 | cpu_relax(); Cc: stable@vger.kernel.org Signed-off-by: Jiaxun Yang Signed-off-by: Thomas Bogendoerfer Signed-off-by: Greg Kroah-Hartman --- arch/mips/sgi-ip30/ip30-console.c | 1 + 1 file changed, 1 insertion(+) diff --git a/arch/mips/sgi-ip30/ip30-console.c b/arch/mips/sgi-ip30/ip30-console.c index b91f8c4fdc78..a087b7ebe129 100644 --- a/arch/mips/sgi-ip30/ip30-console.c +++ b/arch/mips/sgi-ip30/ip30-console.c @@ -1,6 +1,7 @@ // SPDX-License-Identifier: GPL-2.0 #include +#include #include From 77411a2d22524104813f6278f595593db165212c Mon Sep 17 00:00:00 2001 From: Jiaxun Yang Date: Fri, 14 Jun 2024 16:40:18 +0100 Subject: [PATCH 171/342] MIPS: Loongson64: env: Hook up Loongsson-2K commit 77543269ff23c75bebfb8e6e9a1177b350908ea7 upstream. Somehow those enablement bits were left over when we were adding initial Loongson-2K support. Set up basic information and select proper builtin DTB for Loongson-2K. Cc: stable@vger.kernel.org Signed-off-by: Jiaxun Yang Signed-off-by: Thomas Bogendoerfer Signed-off-by: Greg Kroah-Hartman --- arch/mips/include/asm/mach-loongson64/boot_param.h | 2 ++ arch/mips/loongson64/env.c | 8 ++++++++ 2 files changed, 10 insertions(+) diff --git a/arch/mips/include/asm/mach-loongson64/boot_param.h b/arch/mips/include/asm/mach-loongson64/boot_param.h index afc92b7a61c6..deafd177f095 100644 --- a/arch/mips/include/asm/mach-loongson64/boot_param.h +++ b/arch/mips/include/asm/mach-loongson64/boot_param.h @@ -38,12 +38,14 @@ enum loongson_cpu_type { Legacy_1B = 0x5, Legacy_2G = 0x6, Legacy_2H = 0x7, + Legacy_2K = 0x8, Loongson_1A = 0x100, Loongson_1B = 0x101, Loongson_2E = 0x200, Loongson_2F = 0x201, Loongson_2G = 0x202, Loongson_2H = 0x203, + Loongson_2K = 0x204, Loongson_3A = 0x300, Loongson_3B = 0x301 }; diff --git a/arch/mips/loongson64/env.c b/arch/mips/loongson64/env.c index 134cb8e9efc2..c9db6c496138 100644 --- a/arch/mips/loongson64/env.c +++ b/arch/mips/loongson64/env.c @@ -65,6 +65,12 @@ void __init prom_init_env(void) cpu_clock_freq = ecpu->cpu_clock_freq; loongson_sysconf.cputype = ecpu->cputype; switch (ecpu->cputype) { + case Legacy_2K: + case Loongson_2K: + smp_group[0] = 0x900000001fe11000; + loongson_sysconf.cores_per_node = 2; + loongson_sysconf.cores_per_package = 2; + break; case Legacy_3A: case Loongson_3A: loongson_sysconf.cores_per_node = 4; @@ -213,6 +219,8 @@ void __init prom_init_env(void) default: break; } + } else if ((read_c0_prid() & PRID_IMP_MASK) == PRID_IMP_LOONGSON_64R) { + loongson_fdt_blob = __dtb_loongson64_2core_2k1000_begin; } else if ((read_c0_prid() & PRID_IMP_MASK) == PRID_IMP_LOONGSON_64G) { if (loongson_sysconf.bridgetype == LS7A) loongson_fdt_blob = __dtb_loongson64g_4core_ls7a_begin; From 76b62f30350875e087c338abf94f32247c600044 Mon Sep 17 00:00:00 2001 From: Dragan Simic Date: Mon, 17 Jun 2024 22:17:48 +0200 Subject: [PATCH 172/342] drm/panfrost: Mark simple_ondemand governor as softdep commit 80f4e62730a91572b7fdc657f7bb747e107ae308 upstream. Panfrost DRM driver uses devfreq to perform DVFS, while using simple_ondemand devfreq governor by default. This causes driver initialization to fail on boot when simple_ondemand governor isn't built into the kernel statically, as a result of the missing module dependency and, consequently, the required governor module not being included in the initial ramdisk. Thus, let's mark simple_ondemand governor as a softdep for Panfrost, to have its kernel module included in the initial ramdisk. This is a rather longstanding issue that has forced distributions to build devfreq governors statically into their kernels, [1][2] or has forced users to introduce some unnecessary workarounds. [3] For future reference, not having support for the simple_ondemand governor in the initial ramdisk produces errors in the kernel log similar to these below, which were taken from a Pine64 RockPro64: panfrost ff9a0000.gpu: [drm:panfrost_devfreq_init [panfrost]] *ERROR* Couldn't initialize GPU devfreq panfrost ff9a0000.gpu: Fatal error during GPU init panfrost: probe of ff9a0000.gpu failed with error -22 Having simple_ondemand marked as a softdep for Panfrost may not resolve this issue for all Linux distributions. In particular, it will remain unresolved for the distributions whose utilities for the initial ramdisk generation do not handle the available softdep information [4] properly yet. However, some Linux distributions already handle softdeps properly while generating their initial ramdisks, [5] and this is a prerequisite step in the right direction for the distributions that don't handle them properly yet. [1] https://gitlab.manjaro.org/manjaro-arm/packages/core/linux/-/blob/linux61/config?ref_type=heads#L8180 [2] https://salsa.debian.org/kernel-team/linux/-/merge_requests/1066 [3] https://forum.pine64.org/showthread.php?tid=15458 [4] https://git.kernel.org/pub/scm/utils/kernel/kmod/kmod.git/commit/?id=49d8e0b59052999de577ab732b719cfbeb89504d [5] https://github.com/archlinux/mkinitcpio/commit/97ac4d37aae084a050be512f6d8f4489054668ad Cc: Diederik de Haas Cc: Furkan Kardame Cc: stable@vger.kernel.org Fixes: f3ba91228e8e ("drm/panfrost: Add initial panfrost driver") Signed-off-by: Dragan Simic Reviewed-by: Steven Price Reviewed-by: Boris Brezillon Signed-off-by: Steven Price Link: https://patchwork.freedesktop.org/patch/msgid/4e1e00422a14db4e2a80870afb704405da16fd1b.1718655077.git.dsimic@manjaro.org Signed-off-by: Greg Kroah-Hartman --- drivers/gpu/drm/panfrost/panfrost_drv.c | 1 + 1 file changed, 1 insertion(+) diff --git a/drivers/gpu/drm/panfrost/panfrost_drv.c b/drivers/gpu/drm/panfrost/panfrost_drv.c index 4af25c0b6570..ba098b4dee2e 100644 --- a/drivers/gpu/drm/panfrost/panfrost_drv.c +++ b/drivers/gpu/drm/panfrost/panfrost_drv.c @@ -681,3 +681,4 @@ module_platform_driver(panfrost_driver); MODULE_AUTHOR("Panfrost Project Developers"); MODULE_DESCRIPTION("Panfrost DRM Driver"); MODULE_LICENSE("GPL v2"); +MODULE_SOFTDEP("pre: governor_simpleondemand"); From 52d8d27fd6d3ce9bdec18e2c3c35471a031357ec Mon Sep 17 00:00:00 2001 From: Ilya Dryomov Date: Tue, 23 Jul 2024 17:54:39 +0200 Subject: [PATCH 173/342] rbd: rename RBD_LOCK_STATE_RELEASING and releasing_wait commit f5c466a0fdb2d9f3650d2e3911b0735f17ba00cf upstream. ... to RBD_LOCK_STATE_QUIESCING and quiescing_wait to recognize that this state and the associated completion are backing rbd_quiesce_lock(), which isn't specific to releasing the lock. While exclusive lock does get quiesced before it's released, it also gets quiesced before an attempt to update the cookie is made and there the lock is not released as long as ceph_cls_set_cookie() succeeds. Signed-off-by: Ilya Dryomov Reviewed-by: Dongsheng Yang Signed-off-by: Greg Kroah-Hartman --- drivers/block/rbd.c | 20 ++++++++++---------- 1 file changed, 10 insertions(+), 10 deletions(-) diff --git a/drivers/block/rbd.c b/drivers/block/rbd.c index f693deafb002..11c133fe3028 100644 --- a/drivers/block/rbd.c +++ b/drivers/block/rbd.c @@ -362,7 +362,7 @@ enum rbd_watch_state { enum rbd_lock_state { RBD_LOCK_STATE_UNLOCKED, RBD_LOCK_STATE_LOCKED, - RBD_LOCK_STATE_RELEASING, + RBD_LOCK_STATE_QUIESCING, }; /* WatchNotify::ClientId */ @@ -422,7 +422,7 @@ struct rbd_device { struct list_head running_list; struct completion acquire_wait; int acquire_err; - struct completion releasing_wait; + struct completion quiescing_wait; spinlock_t object_map_lock; u8 *object_map; @@ -525,7 +525,7 @@ static bool __rbd_is_lock_owner(struct rbd_device *rbd_dev) lockdep_assert_held(&rbd_dev->lock_rwsem); return rbd_dev->lock_state == RBD_LOCK_STATE_LOCKED || - rbd_dev->lock_state == RBD_LOCK_STATE_RELEASING; + rbd_dev->lock_state == RBD_LOCK_STATE_QUIESCING; } static bool rbd_is_lock_owner(struct rbd_device *rbd_dev) @@ -3523,12 +3523,12 @@ static void rbd_lock_del_request(struct rbd_img_request *img_req) spin_lock(&rbd_dev->lock_lists_lock); if (!list_empty(&img_req->lock_item)) { list_del_init(&img_req->lock_item); - need_wakeup = (rbd_dev->lock_state == RBD_LOCK_STATE_RELEASING && + need_wakeup = (rbd_dev->lock_state == RBD_LOCK_STATE_QUIESCING && list_empty(&rbd_dev->running_list)); } spin_unlock(&rbd_dev->lock_lists_lock); if (need_wakeup) - complete(&rbd_dev->releasing_wait); + complete(&rbd_dev->quiescing_wait); } static int rbd_img_exclusive_lock(struct rbd_img_request *img_req) @@ -4237,16 +4237,16 @@ static bool rbd_quiesce_lock(struct rbd_device *rbd_dev) /* * Ensure that all in-flight IO is flushed. */ - rbd_dev->lock_state = RBD_LOCK_STATE_RELEASING; - rbd_assert(!completion_done(&rbd_dev->releasing_wait)); + rbd_dev->lock_state = RBD_LOCK_STATE_QUIESCING; + rbd_assert(!completion_done(&rbd_dev->quiescing_wait)); if (list_empty(&rbd_dev->running_list)) return true; up_write(&rbd_dev->lock_rwsem); - wait_for_completion(&rbd_dev->releasing_wait); + wait_for_completion(&rbd_dev->quiescing_wait); down_write(&rbd_dev->lock_rwsem); - if (rbd_dev->lock_state != RBD_LOCK_STATE_RELEASING) + if (rbd_dev->lock_state != RBD_LOCK_STATE_QUIESCING) return false; rbd_assert(list_empty(&rbd_dev->running_list)); @@ -5455,7 +5455,7 @@ static struct rbd_device *__rbd_dev_create(struct rbd_spec *spec) INIT_LIST_HEAD(&rbd_dev->acquiring_list); INIT_LIST_HEAD(&rbd_dev->running_list); init_completion(&rbd_dev->acquire_wait); - init_completion(&rbd_dev->releasing_wait); + init_completion(&rbd_dev->quiescing_wait); spin_lock_init(&rbd_dev->object_map_lock); From 1fccae3fd7ae2c5fd82a010057588b31c232d2d0 Mon Sep 17 00:00:00 2001 From: Ilya Dryomov Date: Tue, 23 Jul 2024 18:07:59 +0200 Subject: [PATCH 174/342] rbd: don't assume RBD_LOCK_STATE_LOCKED for exclusive mappings commit 2237ceb71f89837ac47c5dce2aaa2c2b3a337a3c upstream. Every time a watch is reestablished after getting lost, we need to update the cookie which involves quiescing exclusive lock. For this, we transition from RBD_LOCK_STATE_LOCKED to RBD_LOCK_STATE_QUIESCING roughly for the duration of rbd_reacquire_lock() call. If the mapping is exclusive and I/O happens to arrive in this time window, it's failed with EROFS (later translated to EIO) based on the wrong assumption in rbd_img_exclusive_lock() -- "lock got released?" check there stopped making sense with commit a2b1da09793d ("rbd: lock should be quiesced on reacquire"). To make it worse, any such I/O is added to the acquiring list before EROFS is returned and this sets up for violating rbd_lock_del_request() precondition that the request is either on the running list or not on any list at all -- see commit ded080c86b3f ("rbd: don't move requests to the running list on errors"). rbd_lock_del_request() ends up processing these requests as if they were on the running list which screws up quiescing_wait completion counter and ultimately leads to rbd_assert(!completion_done(&rbd_dev->quiescing_wait)); being triggered on the next watch error. Cc: stable@vger.kernel.org # 06ef84c4e9c4: rbd: rename RBD_LOCK_STATE_RELEASING and releasing_wait Cc: stable@vger.kernel.org Fixes: 637cd060537d ("rbd: new exclusive lock wait/wake code") Signed-off-by: Ilya Dryomov Reviewed-by: Dongsheng Yang Signed-off-by: Greg Kroah-Hartman --- drivers/block/rbd.c | 10 +++++----- 1 file changed, 5 insertions(+), 5 deletions(-) diff --git a/drivers/block/rbd.c b/drivers/block/rbd.c index 11c133fe3028..0ceef7bcfe8e 100644 --- a/drivers/block/rbd.c +++ b/drivers/block/rbd.c @@ -3522,6 +3522,7 @@ static void rbd_lock_del_request(struct rbd_img_request *img_req) lockdep_assert_held(&rbd_dev->lock_rwsem); spin_lock(&rbd_dev->lock_lists_lock); if (!list_empty(&img_req->lock_item)) { + rbd_assert(!list_empty(&rbd_dev->running_list)); list_del_init(&img_req->lock_item); need_wakeup = (rbd_dev->lock_state == RBD_LOCK_STATE_QUIESCING && list_empty(&rbd_dev->running_list)); @@ -3541,11 +3542,6 @@ static int rbd_img_exclusive_lock(struct rbd_img_request *img_req) if (rbd_lock_add_request(img_req)) return 1; - if (rbd_dev->opts->exclusive) { - WARN_ON(1); /* lock got released? */ - return -EROFS; - } - /* * Note the use of mod_delayed_work() in rbd_acquire_lock() * and cancel_delayed_work() in wake_lock_waiters(). @@ -4657,6 +4653,10 @@ static void rbd_reacquire_lock(struct rbd_device *rbd_dev) rbd_warn(rbd_dev, "failed to update lock cookie: %d", ret); + if (rbd_dev->opts->exclusive) + rbd_warn(rbd_dev, + "temporarily releasing lock on exclusive mapping"); + /* * Lock cookie cannot be updated on older OSDs, so do * a manual release and queue an acquire. From 4d3eb40ccd1b0f0e654a07063983a97041091ea3 Mon Sep 17 00:00:00 2001 From: Hilda Wu Date: Mon, 17 Jun 2024 17:05:18 +0800 Subject: [PATCH 175/342] Bluetooth: btusb: Add RTL8852BE device 0489:e125 to device tables commit 295ef07a9dae6182ad4b689aa8c6a7dbba21474c upstream. Add the support ID 0489:e125 to usb_device_id table for Realtek RTL8852B chip. The device info from /sys/kernel/debug/usb/devices as below. T: Bus=01 Lev=01 Prnt=01 Port=07 Cnt=03 Dev#= 5 Spd=12 MxCh= 0 D: Ver= 1.00 Cls=e0(wlcon) Sub=01 Prot=01 MxPS=64 #Cfgs= 1 P: Vendor=0489 ProdID=e125 Rev= 0.00 S: Manufacturer=Realtek S: Product=Bluetooth Radio S: SerialNumber=00e04c000001 C:* #Ifs= 2 Cfg#= 1 Atr=e0 MxPwr=500mA I:* If#= 0 Alt= 0 #EPs= 3 Cls=e0(wlcon) Sub=01 Prot=01 Driver=btusb E: Ad=81(I) Atr=03(Int.) MxPS= 16 Ivl=1ms E: Ad=02(O) Atr=02(Bulk) MxPS= 64 Ivl=0ms E: Ad=82(I) Atr=02(Bulk) MxPS= 64 Ivl=0ms I:* If#= 1 Alt= 0 #EPs= 2 Cls=e0(wlcon) Sub=01 Prot=01 Driver=btusb E: Ad=03(O) Atr=01(Isoc) MxPS= 0 Ivl=1ms E: Ad=83(I) Atr=01(Isoc) MxPS= 0 Ivl=1ms I: If#= 1 Alt= 1 #EPs= 2 Cls=e0(wlcon) Sub=01 Prot=01 Driver=btusb E: Ad=03(O) Atr=01(Isoc) MxPS= 9 Ivl=1ms E: Ad=83(I) Atr=01(Isoc) MxPS= 9 Ivl=1ms I: If#= 1 Alt= 2 #EPs= 2 Cls=e0(wlcon) Sub=01 Prot=01 Driver=btusb E: Ad=03(O) Atr=01(Isoc) MxPS= 17 Ivl=1ms E: Ad=83(I) Atr=01(Isoc) MxPS= 17 Ivl=1ms I: If#= 1 Alt= 3 #EPs= 2 Cls=e0(wlcon) Sub=01 Prot=01 Driver=btusb E: Ad=03(O) Atr=01(Isoc) MxPS= 25 Ivl=1ms E: Ad=83(I) Atr=01(Isoc) MxPS= 25 Ivl=1ms I: If#= 1 Alt= 4 #EPs= 2 Cls=e0(wlcon) Sub=01 Prot=01 Driver=btusb E: Ad=03(O) Atr=01(Isoc) MxPS= 33 Ivl=1ms E: Ad=83(I) Atr=01(Isoc) MxPS= 33 Ivl=1ms I: If#= 1 Alt= 5 #EPs= 2 Cls=e0(wlcon) Sub=01 Prot=01 Driver=btusb E: Ad=03(O) Atr=01(Isoc) MxPS= 49 Ivl=1ms E: Ad=83(I) Atr=01(Isoc) MxPS= 49 Ivl=1ms Signed-off-by: Hilda Wu Signed-off-by: Luiz Augusto von Dentz Signed-off-by: Erpeng Xu Signed-off-by: Greg Kroah-Hartman --- drivers/bluetooth/btusb.c | 2 ++ 1 file changed, 2 insertions(+) diff --git a/drivers/bluetooth/btusb.c b/drivers/bluetooth/btusb.c index b2836e8efefd..536c7f7be226 100644 --- a/drivers/bluetooth/btusb.c +++ b/drivers/bluetooth/btusb.c @@ -428,6 +428,8 @@ static const struct usb_device_id blacklist_table[] = { BTUSB_WIDEBAND_SPEECH }, { USB_DEVICE(0x13d3, 0x3571), .driver_info = BTUSB_REALTEK | BTUSB_WIDEBAND_SPEECH }, + { USB_DEVICE(0x0489, 0xe125), .driver_info = BTUSB_REALTEK | + BTUSB_WIDEBAND_SPEECH }, /* Realtek Bluetooth devices */ { USB_VENDOR_AND_INTERFACE_INFO(0x0bda, 0xe0, 0x01, 0x01), From 9fa8eca2598aad978b4434868355aa922a10dac9 Mon Sep 17 00:00:00 2001 From: WangYuli Date: Sat, 22 Jun 2024 12:09:59 +0800 Subject: [PATCH 176/342] Bluetooth: btusb: Add Realtek RTL8852BE support ID 0x13d3:0x3591 commit 473a89b4ed7fd52a419340f7c540d5c8fc96fc75 upstream. Add the support ID(0x13d3, 0x3591) to usb_device_id table for Realtek RTL8852BE. The device table is as follows: T: Bus=01 Lev=02 Prnt=03 Port=00 Cnt=01 Dev#= 5 Spd=12 MxCh= 0 D: Ver= 1.00 Cls=e0(wlcon) Sub=01 Prot=01 MxPS=64 #Cfgs= 1 P: Vendor=13d3 ProdID=3591 Rev= 0.00 S: Manufacturer=Realtek S: Product=Bluetooth Radio S: SerialNumber=00e04c000001 C:* #Ifs= 2 Cfg#= 1 Atr=e0 MxPwr=500mA I:* If#= 0 Alt= 0 #EPs= 3 Cls=e0(wlcon) Sub=01 Prot=01 Driver=btusb E: Ad=81(I) Atr=03(Int.) MxPS= 16 Ivl=1ms E: Ad=02(O) Atr=02(Bulk) MxPS= 64 Ivl=0ms E: Ad=82(I) Atr=02(Bulk) MxPS= 64 Ivl=0ms I:* If#= 1 Alt= 0 #EPs= 2 Cls=e0(wlcon) Sub=01 Prot=01 Driver=btusb E: Ad=03(O) Atr=01(Isoc) MxPS= 0 Ivl=1ms E: Ad=83(I) Atr=01(Isoc) MxPS= 0 Ivl=1ms I: If#= 1 Alt= 1 #EPs= 2 Cls=e0(wlcon) Sub=01 Prot=01 Driver=btusb E: Ad=03(O) Atr=01(Isoc) MxPS= 9 Ivl=1ms E: Ad=83(I) Atr=01(Isoc) MxPS= 9 Ivl=1ms I: If#= 1 Alt= 2 #EPs= 2 Cls=e0(wlcon) Sub=01 Prot=01 Driver=btusb E: Ad=03(O) Atr=01(Isoc) MxPS= 17 Ivl=1ms E: Ad=83(I) Atr=01(Isoc) MxPS= 17 Ivl=1ms I: If#= 1 Alt= 3 #EPs= 2 Cls=e0(wlcon) Sub=01 Prot=01 Driver=btusb E: Ad=03(O) Atr=01(Isoc) MxPS= 25 Ivl=1ms E: Ad=83(I) Atr=01(Isoc) MxPS= 25 Ivl=1ms I: If#= 1 Alt= 4 #EPs= 2 Cls=e0(wlcon) Sub=01 Prot=01 Driver=btusb E: Ad=03(O) Atr=01(Isoc) MxPS= 33 Ivl=1ms E: Ad=83(I) Atr=01(Isoc) MxPS= 33 Ivl=1ms I: If#= 1 Alt= 5 #EPs= 2 Cls=e0(wlcon) Sub=01 Prot=01 Driver=btusb E: Ad=03(O) Atr=01(Isoc) MxPS= 49 Ivl=1ms E: Ad=83(I) Atr=01(Isoc) MxPS= 49 Ivl=1ms Cc: stable@vger.kernel.org Signed-off-by: Wentao Guan Signed-off-by: WangYuli Signed-off-by: Luiz Augusto von Dentz Signed-off-by: Erpeng Xu Signed-off-by: Greg Kroah-Hartman --- drivers/bluetooth/btusb.c | 2 ++ 1 file changed, 2 insertions(+) diff --git a/drivers/bluetooth/btusb.c b/drivers/bluetooth/btusb.c index 536c7f7be226..b0d97c9ffd26 100644 --- a/drivers/bluetooth/btusb.c +++ b/drivers/bluetooth/btusb.c @@ -428,6 +428,8 @@ static const struct usb_device_id blacklist_table[] = { BTUSB_WIDEBAND_SPEECH }, { USB_DEVICE(0x13d3, 0x3571), .driver_info = BTUSB_REALTEK | BTUSB_WIDEBAND_SPEECH }, + { USB_DEVICE(0x13d3, 0x3591), .driver_info = BTUSB_REALTEK | + BTUSB_WIDEBAND_SPEECH }, { USB_DEVICE(0x0489, 0xe125), .driver_info = BTUSB_REALTEK | BTUSB_WIDEBAND_SPEECH }, From 5f0a6800b8aec1b453c7fe4c44fcaac5ffe9d52e Mon Sep 17 00:00:00 2001 From: Ryusuke Konishi Date: Thu, 25 Jul 2024 14:20:07 +0900 Subject: [PATCH 177/342] nilfs2: handle inconsistent state in nilfs_btnode_create_block() commit 4811f7af6090e8f5a398fbdd766f903ef6c0d787 upstream. Syzbot reported that a buffer state inconsistency was detected in nilfs_btnode_create_block(), triggering a kernel bug. It is not appropriate to treat this inconsistency as a bug; it can occur if the argument block address (the buffer index of the newly created block) is a virtual block number and has been reallocated due to corruption of the bitmap used to manage its allocation state. So, modify nilfs_btnode_create_block() and its callers to treat it as a possible filesystem error, rather than triggering a kernel bug. Link: https://lkml.kernel.org/r/20240725052007.4562-1-konishi.ryusuke@gmail.com Fixes: a60be987d45d ("nilfs2: B-tree node cache") Signed-off-by: Ryusuke Konishi Reported-by: syzbot+89cc4f2324ed37988b60@syzkaller.appspotmail.com Closes: https://syzkaller.appspot.com/bug?extid=89cc4f2324ed37988b60 Cc: Signed-off-by: Andrew Morton Signed-off-by: Greg Kroah-Hartman --- fs/nilfs2/btnode.c | 25 ++++++++++++++++++++----- fs/nilfs2/btree.c | 4 ++-- 2 files changed, 22 insertions(+), 7 deletions(-) diff --git a/fs/nilfs2/btnode.c b/fs/nilfs2/btnode.c index 1776121677e2..28a726553318 100644 --- a/fs/nilfs2/btnode.c +++ b/fs/nilfs2/btnode.c @@ -51,12 +51,21 @@ nilfs_btnode_create_block(struct address_space *btnc, __u64 blocknr) bh = nilfs_grab_buffer(inode, btnc, blocknr, BIT(BH_NILFS_Node)); if (unlikely(!bh)) - return NULL; + return ERR_PTR(-ENOMEM); if (unlikely(buffer_mapped(bh) || buffer_uptodate(bh) || buffer_dirty(bh))) { - brelse(bh); - BUG(); + /* + * The block buffer at the specified new address was already + * in use. This can happen if it is a virtual block number + * and has been reallocated due to corruption of the bitmap + * used to manage its allocation state (if not, the buffer + * clearing of an abandoned b-tree node is missing somewhere). + */ + nilfs_error(inode->i_sb, + "state inconsistency probably due to duplicate use of b-tree node block address %llu (ino=%lu)", + (unsigned long long)blocknr, inode->i_ino); + goto failed; } memset(bh->b_data, 0, i_blocksize(inode)); bh->b_bdev = inode->i_sb->s_bdev; @@ -67,6 +76,12 @@ nilfs_btnode_create_block(struct address_space *btnc, __u64 blocknr) unlock_page(bh->b_page); put_page(bh->b_page); return bh; + +failed: + unlock_page(bh->b_page); + put_page(bh->b_page); + brelse(bh); + return ERR_PTR(-EIO); } int nilfs_btnode_submit_block(struct address_space *btnc, __u64 blocknr, @@ -217,8 +232,8 @@ int nilfs_btnode_prepare_change_key(struct address_space *btnc, } nbh = nilfs_btnode_create_block(btnc, newkey); - if (!nbh) - return -ENOMEM; + if (IS_ERR(nbh)) + return PTR_ERR(nbh); BUG_ON(nbh == obh); ctxt->newbh = nbh; diff --git a/fs/nilfs2/btree.c b/fs/nilfs2/btree.c index 4905b7cd7bf3..a426e4e2acda 100644 --- a/fs/nilfs2/btree.c +++ b/fs/nilfs2/btree.c @@ -63,8 +63,8 @@ static int nilfs_btree_get_new_block(const struct nilfs_bmap *btree, struct buffer_head *bh; bh = nilfs_btnode_create_block(btnc, ptr); - if (!bh) - return -ENOMEM; + if (IS_ERR(bh)) + return PTR_ERR(bh); set_buffer_nilfs_volatile(bh); *bhp = bh; From b839175c06daede0127f5f547a55adf330ad090e Mon Sep 17 00:00:00 2001 From: Pavel Begunkov Date: Wed, 10 Jul 2024 18:58:17 +0100 Subject: [PATCH 178/342] io_uring/io-wq: limit retrying worker initialisation commit 0453aad676ff99787124b9b3af4a5f59fbe808e2 upstream. If io-wq worker creation fails, we retry it by queueing up a task_work. tasK_work is needed because it should be done from the user process context. The problem is that retries are not limited, and if queueing a task_work is the reason for the failure, we might get into an infinite loop. It doesn't seem to happen now but it would with the following patch executing task_work in the freezer's loop. For now, arbitrarily limit the number of attempts to create a worker. Cc: stable@vger.kernel.org Fixes: 3146cba99aa28 ("io-wq: make worker creation resilient against signals") Reported-by: Julian Orth Signed-off-by: Pavel Begunkov Link: https://lore.kernel.org/r/8280436925db88448c7c85c6656edee1a43029ea.1720634146.git.asml.silence@gmail.com Signed-off-by: Jens Axboe Signed-off-by: Greg Kroah-Hartman --- io_uring/io-wq.c | 10 +++++++--- 1 file changed, 7 insertions(+), 3 deletions(-) diff --git a/io_uring/io-wq.c b/io_uring/io-wq.c index fe8594a0396c..c5d249f5d214 100644 --- a/io_uring/io-wq.c +++ b/io_uring/io-wq.c @@ -19,6 +19,7 @@ #include "io-wq.h" #define WORKER_IDLE_TIMEOUT (5 * HZ) +#define WORKER_INIT_LIMIT 3 enum { IO_WORKER_F_UP = 1, /* up and active */ @@ -54,6 +55,7 @@ struct io_worker { unsigned long create_state; struct callback_head create_work; int create_index; + int init_retries; union { struct rcu_head rcu; @@ -732,7 +734,7 @@ static bool io_wq_work_match_all(struct io_wq_work *work, void *data) return true; } -static inline bool io_should_retry_thread(long err) +static inline bool io_should_retry_thread(struct io_worker *worker, long err) { /* * Prevent perpetual task_work retry, if the task (or its group) is @@ -740,6 +742,8 @@ static inline bool io_should_retry_thread(long err) */ if (fatal_signal_pending(current)) return false; + if (worker->init_retries++ >= WORKER_INIT_LIMIT) + return false; switch (err) { case -EAGAIN: @@ -766,7 +770,7 @@ static void create_worker_cont(struct callback_head *cb) io_init_new_worker(wqe, worker, tsk); io_worker_release(worker); return; - } else if (!io_should_retry_thread(PTR_ERR(tsk))) { + } else if (!io_should_retry_thread(worker, PTR_ERR(tsk))) { struct io_wqe_acct *acct = io_wqe_get_acct(worker); atomic_dec(&acct->nr_running); @@ -831,7 +835,7 @@ static bool create_io_worker(struct io_wq *wq, struct io_wqe *wqe, int index) tsk = create_io_thread(io_wqe_worker, worker, wqe->node); if (!IS_ERR(tsk)) { io_init_new_worker(wqe, worker, tsk); - } else if (!io_should_retry_thread(PTR_ERR(tsk))) { + } else if (!io_should_retry_thread(worker, PTR_ERR(tsk))) { kfree(worker); goto fail; } else { From 65dba3c9ce750d449758b3488c722d55dcfe1600 Mon Sep 17 00:00:00 2001 From: Pavel Begunkov Date: Wed, 10 Jul 2024 18:58:18 +0100 Subject: [PATCH 179/342] kernel: rerun task_work while freezing in get_signal() commit 943ad0b62e3c21f324c4884caa6cb4a871bca05c upstream. io_uring can asynchronously add a task_work while the task is getting freezed. TIF_NOTIFY_SIGNAL will prevent the task from sleeping in do_freezer_trap(), and since the get_signal()'s relock loop doesn't retry task_work, the task will spin there not being able to sleep until the freezing is cancelled / the task is killed / etc. Run task_works in the freezer path. Keep the patch small and simple so it can be easily back ported, but we might need to do some cleaning after and look if there are other places with similar problems. Cc: stable@vger.kernel.org Link: https://github.com/systemd/systemd/issues/33626 Fixes: 12db8b690010c ("entry: Add support for TIF_NOTIFY_SIGNAL") Reported-by: Julian Orth Acked-by: Oleg Nesterov Acked-by: Tejun Heo Signed-off-by: Pavel Begunkov Link: https://lore.kernel.org/r/89ed3a52933370deaaf61a0a620a6ac91f1e754d.1720634146.git.asml.silence@gmail.com Signed-off-by: Jens Axboe Signed-off-by: Greg Kroah-Hartman --- include/linux/sched/signal.h | 6 ++++++ kernel/signal.c | 8 ++++++++ 2 files changed, 14 insertions(+) diff --git a/include/linux/sched/signal.h b/include/linux/sched/signal.h index 2c634010cc7b..5e4194e12a7d 100644 --- a/include/linux/sched/signal.h +++ b/include/linux/sched/signal.h @@ -348,6 +348,12 @@ extern void sigqueue_free(struct sigqueue *); extern int send_sigqueue(struct sigqueue *, struct pid *, enum pid_type); extern int do_sigaction(int, struct k_sigaction *, struct k_sigaction *); +static inline void clear_notify_signal(void) +{ + clear_thread_flag(TIF_NOTIFY_SIGNAL); + smp_mb__after_atomic(); +} + static inline int restart_syscall(void) { set_tsk_thread_flag(current, TIF_SIGPENDING); diff --git a/kernel/signal.c b/kernel/signal.c index e487c4660921..bfc1da526ebb 100644 --- a/kernel/signal.c +++ b/kernel/signal.c @@ -2464,6 +2464,14 @@ static void do_freezer_trap(void) spin_unlock_irq(¤t->sighand->siglock); cgroup_enter_frozen(); freezable_schedule(); + + /* + * We could've been woken by task_work, run it to clear + * TIF_NOTIFY_SIGNAL. The caller will retry if necessary. + */ + clear_notify_signal(); + if (unlikely(READ_ONCE(current->task_works))) + task_work_run(); } static int ptrace_signal(int signr, kernel_siginfo_t *info) From f0ad62559f05e36d08309d80d0a86155193bb16e Mon Sep 17 00:00:00 2001 From: Arnd Bergmann Date: Tue, 28 May 2024 14:11:48 +0200 Subject: [PATCH 180/342] kdb: address -Wformat-security warnings [ Upstream commit 70867efacf4370b6c7cdfc7a5b11300e9ef7de64 ] When -Wformat-security is not disabled, using a string pointer as a format causes a warning: kernel/debug/kdb/kdb_io.c: In function 'kdb_read': kernel/debug/kdb/kdb_io.c:365:36: error: format not a string literal and no format arguments [-Werror=format-security] 365 | kdb_printf(kdb_prompt_str); | ^~~~~~~~~~~~~~ kernel/debug/kdb/kdb_io.c: In function 'kdb_getstr': kernel/debug/kdb/kdb_io.c:456:20: error: format not a string literal and no format arguments [-Werror=format-security] 456 | kdb_printf(kdb_prompt_str); | ^~~~~~~~~~~~~~ Use an explcit "%s" format instead. Signed-off-by: Arnd Bergmann Fixes: 5d5314d6795f ("kdb: core for kgdb back end (1 of 2)") Reviewed-by: Douglas Anderson Link: https://lore.kernel.org/r/20240528121154.3662553-1-arnd@kernel.org Signed-off-by: Daniel Thompson Signed-off-by: Sasha Levin --- kernel/debug/kdb/kdb_io.c | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-) diff --git a/kernel/debug/kdb/kdb_io.c b/kernel/debug/kdb/kdb_io.c index a3b4b55d2e2e..a4256e558a70 100644 --- a/kernel/debug/kdb/kdb_io.c +++ b/kernel/debug/kdb/kdb_io.c @@ -358,7 +358,7 @@ static char *kdb_read(char *buffer, size_t bufsize) if (i >= dtab_count) kdb_printf("..."); kdb_printf("\n"); - kdb_printf(kdb_prompt_str); + kdb_printf("%s", kdb_prompt_str); kdb_printf("%s", buffer); if (cp != lastchar) kdb_position_cursor(kdb_prompt_str, buffer, cp); @@ -450,7 +450,7 @@ char *kdb_getstr(char *buffer, size_t bufsize, const char *prompt) { if (prompt && kdb_prompt_str != prompt) strscpy(kdb_prompt_str, prompt, CMD_BUFLEN); - kdb_printf(kdb_prompt_str); + kdb_printf("%s", kdb_prompt_str); kdb_nextline = 1; /* Prompt and input resets line number */ return kdb_read(buffer, bufsize); } From 1c089efe763df98f54cb14e9410c5440f7db8443 Mon Sep 17 00:00:00 2001 From: Douglas Anderson Date: Tue, 28 May 2024 07:11:48 -0700 Subject: [PATCH 181/342] kdb: Use the passed prompt in kdb_position_cursor() [ Upstream commit e2e821095949cde46256034975a90f88626a2a73 ] The function kdb_position_cursor() takes in a "prompt" parameter but never uses it. This doesn't _really_ matter since all current callers of the function pass the same value and it's a global variable, but it's a bit ugly. Let's clean it up. Found by code inspection. This patch is expected to functionally be a no-op. Fixes: 09b35989421d ("kdb: Use format-strings rather than '\0' injection in kdb_read()") Signed-off-by: Douglas Anderson Link: https://lore.kernel.org/r/20240528071144.1.I0feb49839c6b6f4f2c4bf34764f5e95de3f55a66@changeid Signed-off-by: Daniel Thompson Signed-off-by: Sasha Levin --- kernel/debug/kdb/kdb_io.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/kernel/debug/kdb/kdb_io.c b/kernel/debug/kdb/kdb_io.c index a4256e558a70..b28b8a5ef638 100644 --- a/kernel/debug/kdb/kdb_io.c +++ b/kernel/debug/kdb/kdb_io.c @@ -194,7 +194,7 @@ char kdb_getchar(void) */ static void kdb_position_cursor(char *prompt, char *buffer, char *cp) { - kdb_printf("\r%s", kdb_prompt_str); + kdb_printf("\r%s", prompt); if (cp > buffer) kdb_printf("%.*s", (int)(cp - buffer), buffer); } From 538a27c8048f081a5ddd286f886eb986fbbc7f80 Mon Sep 17 00:00:00 2001 From: Jeongjun Park Date: Thu, 30 May 2024 22:28:09 +0900 Subject: [PATCH 182/342] jfs: Fix array-index-out-of-bounds in diFree [ Upstream commit f73f969b2eb39ad8056f6c7f3a295fa2f85e313a ] Reported-by: syzbot+241c815bda521982cb49@syzkaller.appspotmail.com Fixes: 1da177e4c3f4 ("Linux-2.6.12-rc2") Signed-off-by: Jeongjun Park Signed-off-by: Dave Kleikamp Signed-off-by: Sasha Levin --- fs/jfs/jfs_imap.c | 5 ++++- 1 file changed, 4 insertions(+), 1 deletion(-) diff --git a/fs/jfs/jfs_imap.c b/fs/jfs/jfs_imap.c index b0965f3ef186..36ed75682064 100644 --- a/fs/jfs/jfs_imap.c +++ b/fs/jfs/jfs_imap.c @@ -292,7 +292,7 @@ int diSync(struct inode *ipimap) int diRead(struct inode *ip) { struct jfs_sb_info *sbi = JFS_SBI(ip->i_sb); - int iagno, ino, extno, rc; + int iagno, ino, extno, rc, agno; struct inode *ipimap; struct dinode *dp; struct iag *iagp; @@ -341,8 +341,11 @@ int diRead(struct inode *ip) /* get the ag for the iag */ agstart = le64_to_cpu(iagp->agstart); + agno = BLKTOAG(agstart, JFS_SBI(ip->i_sb)); release_metapage(mp); + if (agno >= MAXAG || agno < 0) + return -EIO; rel_inode = (ino & (INOSPERPAGE - 1)); pageno = blkno >> sbi->l2nbperpage; From 721190921a87f035d9a2b79bdab4ed3e83e0f6a2 Mon Sep 17 00:00:00 2001 From: Johannes Berg Date: Wed, 17 Apr 2024 10:27:45 +0200 Subject: [PATCH 183/342] um: time-travel: fix time-travel-start option [ Upstream commit 7d0a8a490aa3a2a82de8826aaf1dfa38575cb77a ] We need to have the = as part of the option so that the value can be parsed properly. Also document that it must be given in nanoseconds, not seconds. Fixes: 065038706f77 ("um: Support time travel mode") Link: https://patch.msgid.link/20240417102744.14b9a9d4eba0.Ib22e9136513126b2099d932650f55f193120cd97@changeid Signed-off-by: Johannes Berg Signed-off-by: Sasha Levin --- arch/um/kernel/time.c | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-) diff --git a/arch/um/kernel/time.c b/arch/um/kernel/time.c index 8dafc3f2add4..9a0fcafafd00 100644 --- a/arch/um/kernel/time.c +++ b/arch/um/kernel/time.c @@ -756,9 +756,9 @@ int setup_time_travel_start(char *str) return 1; } -__setup("time-travel-start", setup_time_travel_start); +__setup("time-travel-start=", setup_time_travel_start); __uml_help(setup_time_travel_start, -"time-travel-start=\n" +"time-travel-start=\n" "Configure the UML instance's wall clock to start at this value rather than\n" "the host's wall clock at the time of UML boot.\n"); #endif From ff2387553f6aedb657ad3b77be92b3489e30b4c2 Mon Sep 17 00:00:00 2001 From: Sheng Yong Date: Mon, 8 Jul 2024 20:04:07 +0800 Subject: [PATCH 184/342] f2fs: fix start segno of large section [ Upstream commit 8c409989678e92e4a737e7cd2bb04f3efb81071a ] get_ckpt_valid_blocks() checks valid ckpt blocks in current section. It counts all vblocks from the first to the last segment in the large section. However, START_SEGNO() is used to get the first segno in an SIT block. This patch fixes that to get the correct start segno. Fixes: 61461fc921b7 ("f2fs: fix to avoid touching checkpointed data in get_victim()") Signed-off-by: Sheng Yong Reviewed-by: Chao Yu Signed-off-by: Jaegeuk Kim Signed-off-by: Sasha Levin --- fs/f2fs/segment.h | 3 ++- 1 file changed, 2 insertions(+), 1 deletion(-) diff --git a/fs/f2fs/segment.h b/fs/f2fs/segment.h index 979296b835b5..665e0e186687 100644 --- a/fs/f2fs/segment.h +++ b/fs/f2fs/segment.h @@ -371,7 +371,8 @@ static inline unsigned int get_ckpt_valid_blocks(struct f2fs_sb_info *sbi, unsigned int segno, bool use_section) { if (use_section && __is_large_section(sbi)) { - unsigned int start_segno = START_SEGNO(segno); + unsigned int secno = GET_SEC_FROM_SEG(sbi, segno); + unsigned int start_segno = GET_SEG_FROM_SEC(sbi, secno); unsigned int blocks = 0; int i; From 641b7a8920f44967184921ce5707eb180ee2cfdf Mon Sep 17 00:00:00 2001 From: Andrii Nakryiko Date: Fri, 12 Jul 2024 15:44:42 -0700 Subject: [PATCH 185/342] libbpf: Fix no-args func prototype BTF dumping syntax [ Upstream commit 189f1a976e426011e6a5588f1d3ceedf71fe2965 ] For all these years libbpf's BTF dumper has been emitting not strictly valid syntax for function prototypes that have no input arguments. Instead of `int (*blah)()` we should emit `int (*blah)(void)`. This is not normally a problem, but it manifests when we get kfuncs in vmlinux.h that have no input arguments. Due to compiler internal specifics, we get no BTF information for such kfuncs, if they are not declared with proper `(void)`. The fix is trivial. We also need to adjust a few ancient tests that happily assumed `()` is correct. Fixes: 351131b51c7a ("libbpf: add btf_dump API for BTF-to-C conversion") Reported-by: Tejun Heo Signed-off-by: Andrii Nakryiko Signed-off-by: Daniel Borkmann Acked-by: Stanislav Fomichev Link: https://lore.kernel.org/bpf/20240712224442.282823-1-andrii@kernel.org Signed-off-by: Sasha Levin --- tools/lib/bpf/btf_dump.c | 8 +++++--- .../selftests/bpf/progs/btf_dump_test_case_multidim.c | 4 ++-- .../selftests/bpf/progs/btf_dump_test_case_syntax.c | 4 ++-- 3 files changed, 9 insertions(+), 7 deletions(-) diff --git a/tools/lib/bpf/btf_dump.c b/tools/lib/bpf/btf_dump.c index 61aa2c47fbd5..2342aec3c5a3 100644 --- a/tools/lib/bpf/btf_dump.c +++ b/tools/lib/bpf/btf_dump.c @@ -1426,10 +1426,12 @@ static void btf_dump_emit_type_chain(struct btf_dump *d, * Clang for BPF target generates func_proto with no * args as a func_proto with a single void arg (e.g., * `int (*f)(void)` vs just `int (*f)()`). We are - * going to pretend there are no args for such case. + * going to emit valid empty args (void) syntax for + * such case. Similarly and conveniently, valid + * no args case can be special-cased here as well. */ - if (vlen == 1 && p->type == 0) { - btf_dump_printf(d, ")"); + if (vlen == 0 || (vlen == 1 && p->type == 0)) { + btf_dump_printf(d, "void)"); return; } diff --git a/tools/testing/selftests/bpf/progs/btf_dump_test_case_multidim.c b/tools/testing/selftests/bpf/progs/btf_dump_test_case_multidim.c index ba97165bdb28..a657651eba52 100644 --- a/tools/testing/selftests/bpf/progs/btf_dump_test_case_multidim.c +++ b/tools/testing/selftests/bpf/progs/btf_dump_test_case_multidim.c @@ -14,9 +14,9 @@ typedef int *ptr_arr_t[6]; typedef int *ptr_multiarr_t[7][8][9][10]; -typedef int * (*fn_ptr_arr_t[11])(); +typedef int * (*fn_ptr_arr_t[11])(void); -typedef int * (*fn_ptr_multiarr_t[12][13])(); +typedef int * (*fn_ptr_multiarr_t[12][13])(void); struct root_struct { arr_t _1; diff --git a/tools/testing/selftests/bpf/progs/btf_dump_test_case_syntax.c b/tools/testing/selftests/bpf/progs/btf_dump_test_case_syntax.c index fe43556e1a61..956b24ce8145 100644 --- a/tools/testing/selftests/bpf/progs/btf_dump_test_case_syntax.c +++ b/tools/testing/selftests/bpf/progs/btf_dump_test_case_syntax.c @@ -67,7 +67,7 @@ typedef void (*printf_fn_t)(const char *, ...); * `int -> char *` function and returns pointer to a char. Equivalent: * typedef char * (*fn_input_t)(int); * typedef char * (*fn_output_outer_t)(fn_input_t); - * typedef const fn_output_outer_t (* fn_output_inner_t)(); + * typedef const fn_output_outer_t (* fn_output_inner_t)(void); * typedef const fn_output_inner_t fn_ptr_arr2_t[5]; */ /* ----- START-EXPECTED-OUTPUT ----- */ @@ -94,7 +94,7 @@ typedef void (* (*signal_t)(int, void (*)(int)))(int); typedef char * (*fn_ptr_arr1_t[10])(int **); -typedef char * (* (* const fn_ptr_arr2_t[5])())(char * (*)(int)); +typedef char * (* (* const fn_ptr_arr2_t[5])(void))(char * (*)(int)); struct struct_w_typedefs { int_t a; From 257193083e8f43907e99ea633820fc2b3bcd24c7 Mon Sep 17 00:00:00 2001 From: Lance Richardson Date: Thu, 18 Jul 2024 14:38:24 +0000 Subject: [PATCH 186/342] dma: fix call order in dmam_free_coherent [ Upstream commit 28e8b7406d3a1f5329a03aa25a43aa28e087cb20 ] dmam_free_coherent() frees a DMA allocation, which makes the freed vaddr available for reuse, then calls devres_destroy() to remove and free the data structure used to track the DMA allocation. Between the two calls, it is possible for a concurrent task to make an allocation with the same vaddr and add it to the devres list. If this happens, there will be two entries in the devres list with the same vaddr and devres_destroy() can free the wrong entry, triggering the WARN_ON() in dmam_match. Fix by destroying the devres entry before freeing the DMA allocation. Tested: kokonut //net/encryption http://sponge2/b9145fe6-0f72-4325-ac2f-a84d81075b03 Fixes: 9ac7849e35f7 ("devres: device resource management") Signed-off-by: Lance Richardson Signed-off-by: Christoph Hellwig Signed-off-by: Sasha Levin --- kernel/dma/mapping.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/kernel/dma/mapping.c b/kernel/dma/mapping.c index 51bb8fa8eb89..453c0fbe87ff 100644 --- a/kernel/dma/mapping.c +++ b/kernel/dma/mapping.c @@ -60,8 +60,8 @@ void dmam_free_coherent(struct device *dev, size_t size, void *vaddr, { struct dma_devres match_data = { size, vaddr, dma_handle }; - dma_free_coherent(dev, size, vaddr, dma_handle); WARN_ON(devres_destroy(dev, dmam_release, dmam_match, &match_data)); + dma_free_coherent(dev, size, vaddr, dma_handle); } EXPORT_SYMBOL(dmam_free_coherent); From f62a9cc0c2f746827aea6b9b7ade2761a451b31e Mon Sep 17 00:00:00 2001 From: Gregory CLEMENT Date: Mon, 22 Jul 2024 15:15:39 +0200 Subject: [PATCH 187/342] MIPS: SMP-CPS: Fix address for GCR_ACCESS register for CM3 and later [ Upstream commit a263e5f309f32301e1f3ad113293f4e68a82a646 ] When the CM block migrated from CM2.5 to CM3.0, the address offset for the Global CSR Access Privilege register was modified. We saw this in the "MIPS64 I6500 Multiprocessing System Programmer's Guide," it is stated that "the Global CSR Access Privilege register is located at offset 0x0120" in section 5.4. It is at least the same for I6400. This fix allows to use the VP cores in SMP mode if the reset values were modified by the bootloader. Based on the work of Vladimir Kondratiev and the feedback from Jiaxun Yang . Fixes: 197e89e0984a ("MIPS: mips-cm: Implement mips_cm_revision") Signed-off-by: Gregory CLEMENT Reviewed-by: Jiaxun Yang Signed-off-by: Thomas Bogendoerfer Signed-off-by: Sasha Levin --- arch/mips/include/asm/mips-cm.h | 4 ++++ arch/mips/kernel/smp-cps.c | 5 ++++- 2 files changed, 8 insertions(+), 1 deletion(-) diff --git a/arch/mips/include/asm/mips-cm.h b/arch/mips/include/asm/mips-cm.h index 23c67c0871b1..696b40beb774 100644 --- a/arch/mips/include/asm/mips-cm.h +++ b/arch/mips/include/asm/mips-cm.h @@ -228,6 +228,10 @@ GCR_ACCESSOR_RO(32, 0x0d0, gic_status) GCR_ACCESSOR_RO(32, 0x0f0, cpc_status) #define CM_GCR_CPC_STATUS_EX BIT(0) +/* GCR_ACCESS - Controls core/IOCU access to GCRs */ +GCR_ACCESSOR_RW(32, 0x120, access_cm3) +#define CM_GCR_ACCESS_ACCESSEN GENMASK(7, 0) + /* GCR_L2_CONFIG - Indicates L2 cache configuration when Config5.L2C=1 */ GCR_ACCESSOR_RW(32, 0x130, l2_config) #define CM_GCR_L2_CONFIG_BYPASS BIT(20) diff --git a/arch/mips/kernel/smp-cps.c b/arch/mips/kernel/smp-cps.c index f659adb681bc..02ae0b29e688 100644 --- a/arch/mips/kernel/smp-cps.c +++ b/arch/mips/kernel/smp-cps.c @@ -229,7 +229,10 @@ static void boot_core(unsigned int core, unsigned int vpe_id) write_gcr_co_reset_ext_base(CM_GCR_Cx_RESET_EXT_BASE_UEB); /* Ensure the core can access the GCRs */ - set_gcr_access(1 << core); + if (mips_cm_revision() < CM_REV_CM3) + set_gcr_access(1 << core); + else + set_gcr_access_cm3(1 << core); if (mips_cpc_present()) { /* Reset the core */ From 3bf09eab401eb48b6a66cca4dfe6d67ef64ba86f Mon Sep 17 00:00:00 2001 From: Ido Schimmel Date: Thu, 18 Jul 2024 15:34:07 +0300 Subject: [PATCH 188/342] ipv4: Fix incorrect source address in Record Route option [ Upstream commit cc73bbab4b1fb8a4f53a24645871dafa5f81266a ] The Record Route IP option records the addresses of the routers that routed the packet. In the case of forwarded packets, the kernel performs a route lookup via fib_lookup() and fills in the preferred source address of the matched route. The lookup is performed with the DS field of the forwarded packet, but using the RT_TOS() macro which only masks one of the two ECN bits. If the packet is ECT(0) or CE, the matched route might be different than the route via which the packet was forwarded as the input path masks both of the ECN bits, resulting in the wrong address being filled in the Record Route option. Fix by masking both of the ECN bits. Fixes: 8e36360ae876 ("ipv4: Remove route key identity dependencies in ip_rt_get_source().") Signed-off-by: Ido Schimmel Reviewed-by: Guillaume Nault Link: https://patch.msgid.link/20240718123407.434778-1-idosch@nvidia.com Signed-off-by: Paolo Abeni Signed-off-by: Sasha Levin --- net/ipv4/route.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/net/ipv4/route.c b/net/ipv4/route.c index b3b49d8b386d..1eb1e4316ed6 100644 --- a/net/ipv4/route.c +++ b/net/ipv4/route.c @@ -1302,7 +1302,7 @@ void ip_rt_get_source(u8 *addr, struct sk_buff *skb, struct rtable *rt) struct flowi4 fl4 = { .daddr = iph->daddr, .saddr = iph->saddr, - .flowi4_tos = RT_TOS(iph->tos), + .flowi4_tos = iph->tos & IPTOS_RT_MASK, .flowi4_oif = rt->dst.dev->ifindex, .flowi4_iif = skb->dev->ifindex, .flowi4_mark = skb->mark, From c8ae5939f40e4a67cd3aed47e147684e36aa68a4 Mon Sep 17 00:00:00 2001 From: Johannes Berg Date: Fri, 19 Jul 2024 09:41:18 -0700 Subject: [PATCH 189/342] net: bonding: correctly annotate RCU in bond_should_notify_peers() [ Upstream commit 3ba359c0cd6eb5ea772125a7aededb4a2d516684 ] RCU use in bond_should_notify_peers() looks wrong, since it does rcu_dereference(), leaves the critical section, and uses the pointer after that. Luckily, it's called either inside a nested RCU critical section or with the RTNL held. Annotate it with rcu_dereference_rtnl() instead, and remove the inner RCU critical section. Fixes: 4cb4f97b7e36 ("bonding: rebuild the lock use for bond_mii_monitor()") Reviewed-by: Jiri Pirko Signed-off-by: Johannes Berg Acked-by: Jay Vosburgh Link: https://patch.msgid.link/20240719094119.35c62455087d.I68eb9c0f02545b364b79a59f2110f2cf5682a8e2@changeid Signed-off-by: Paolo Abeni Signed-off-by: Sasha Levin --- drivers/net/bonding/bond_main.c | 7 ++----- 1 file changed, 2 insertions(+), 5 deletions(-) diff --git a/drivers/net/bonding/bond_main.c b/drivers/net/bonding/bond_main.c index 50fabba04248..c07b9bac1a6a 100644 --- a/drivers/net/bonding/bond_main.c +++ b/drivers/net/bonding/bond_main.c @@ -1052,13 +1052,10 @@ static struct slave *bond_find_best_slave(struct bonding *bond) return bestslave; } +/* must be called in RCU critical section or with RTNL held */ static bool bond_should_notify_peers(struct bonding *bond) { - struct slave *slave; - - rcu_read_lock(); - slave = rcu_dereference(bond->curr_active_slave); - rcu_read_unlock(); + struct slave *slave = rcu_dereference_rtnl(bond->curr_active_slave); if (!slave || !bond->send_peer_notif || bond->send_peer_notif % From cf791b98fe0ca825dcd989a53248fd8cedb78c3f Mon Sep 17 00:00:00 2001 From: Florian Westphal Date: Fri, 19 Jul 2024 13:19:26 +0200 Subject: [PATCH 190/342] netfilter: nft_set_pipapo_avx2: disable softinterrupts [ Upstream commit a16909ae9982e931841c456061cb57fbaec9c59e ] We need to disable softinterrupts, else we get following problem: 1. pipapo_avx2 called from process context; fpu usable 2. preempt_disable() called, pcpu scratchmap in use 3. softirq handles rx or tx, we re-enter pipapo_avx2 4. fpu busy, fallback to generic non-avx version 5. fallback reuses scratch map and index, which are in use by the preempted process Handle this same way as generic version by first disabling softinterrupts while the scratchmap is in use. Fixes: f0b3d338064e ("netfilter: nft_set_pipapo_avx2: Add irq_fpu_usable() check, fallback to non-AVX2 version") Cc: Stefano Brivio Signed-off-by: Florian Westphal Reviewed-by: Stefano Brivio Signed-off-by: Pablo Neira Ayuso Signed-off-by: Sasha Levin --- net/netfilter/nft_set_pipapo_avx2.c | 12 ++++++++++-- 1 file changed, 10 insertions(+), 2 deletions(-) diff --git a/net/netfilter/nft_set_pipapo_avx2.c b/net/netfilter/nft_set_pipapo_avx2.c index 60fb8bc0fdcc..13c7e22c9384 100644 --- a/net/netfilter/nft_set_pipapo_avx2.c +++ b/net/netfilter/nft_set_pipapo_avx2.c @@ -1129,8 +1129,14 @@ bool nft_pipapo_avx2_lookup(const struct net *net, const struct nft_set *set, bool map_index; int i, ret = 0; - if (unlikely(!irq_fpu_usable())) - return nft_pipapo_lookup(net, set, key, ext); + local_bh_disable(); + + if (unlikely(!irq_fpu_usable())) { + bool fallback_res = nft_pipapo_lookup(net, set, key, ext); + + local_bh_enable(); + return fallback_res; + } m = rcu_dereference(priv->match); @@ -1140,6 +1146,7 @@ bool nft_pipapo_avx2_lookup(const struct net *net, const struct nft_set *set, scratch = *raw_cpu_ptr(m->scratch); if (unlikely(!scratch)) { kernel_fpu_end(); + local_bh_enable(); return false; } @@ -1220,6 +1227,7 @@ bool nft_pipapo_avx2_lookup(const struct net *net, const struct nft_set *set, if (i % 2) scratch->map_index = !map_index; kernel_fpu_end(); + local_bh_enable(); return ret >= 0; } From aa38bf74899de07cf70b50cd17f8ad45fb6654c8 Mon Sep 17 00:00:00 2001 From: Shigeru Yoshida Date: Tue, 16 Jul 2024 11:09:05 +0900 Subject: [PATCH 191/342] tipc: Return non-zero value from tipc_udp_addr2str() on error [ Upstream commit fa96c6baef1b5385e2f0c0677b32b3839e716076 ] tipc_udp_addr2str() should return non-zero value if the UDP media address is invalid. Otherwise, a buffer overflow access can occur in tipc_media_addr_printf(). Fix this by returning 1 on an invalid UDP media address. Fixes: d0f91938bede ("tipc: add ip/udp media type") Signed-off-by: Shigeru Yoshida Reviewed-by: Tung Nguyen Signed-off-by: David S. Miller Signed-off-by: Sasha Levin --- net/tipc/udp_media.c | 5 ++++- 1 file changed, 4 insertions(+), 1 deletion(-) diff --git a/net/tipc/udp_media.c b/net/tipc/udp_media.c index 3e47501f024f..ec6d7730b852 100644 --- a/net/tipc/udp_media.c +++ b/net/tipc/udp_media.c @@ -129,8 +129,11 @@ static int tipc_udp_addr2str(struct tipc_media_addr *a, char *buf, int size) snprintf(buf, size, "%pI4:%u", &ua->ipv4, ntohs(ua->port)); else if (ntohs(ua->proto) == ETH_P_IPV6) snprintf(buf, size, "%pI6:%u", &ua->ipv6, ntohs(ua->port)); - else + else { pr_err("Invalid UDP media address\n"); + return 1; + } + return 0; } From dc2a655437c47c53373c4b6970ecaf2aa32d07cd Mon Sep 17 00:00:00 2001 From: Simon Horman Date: Tue, 23 Jul 2024 14:29:27 +0100 Subject: [PATCH 192/342] net: stmmac: Correct byte order of perfect_match [ Upstream commit e9dbebae2e3c338122716914fe105458f41e3a4a ] The perfect_match parameter of the update_vlan_hash operation is __le16, and is correctly converted from host byte-order in the lone caller, stmmac_vlan_update(). However, the implementations of this caller, dwxgmac2_update_vlan_hash() and dwxgmac2_update_vlan_hash(), both treat this parameter as host byte order, using the following pattern: u32 value = ... ... writel(value | perfect_match, ...); This is not correct because both: 1) value is host byte order; and 2) writel expects a host byte order value as it's first argument I believe that this will break on big endian systems. And I expect it has gone unnoticed by only being exercised on little endian systems. The approach taken by this patch is to update the callback, and it's caller to simply use a host byte order value. Flagged by Sparse. Compile tested only. Fixes: c7ab0b8088d7 ("net: stmmac: Fallback to VLAN Perfect filtering if HASH is not available") Signed-off-by: Simon Horman Reviewed-by: Maxime Chevallier Signed-off-by: David S. Miller Signed-off-by: Sasha Levin --- drivers/net/ethernet/stmicro/stmmac/dwmac4_core.c | 2 +- drivers/net/ethernet/stmicro/stmmac/dwxgmac2_core.c | 2 +- drivers/net/ethernet/stmicro/stmmac/hwif.h | 2 +- drivers/net/ethernet/stmicro/stmmac/stmmac_main.c | 4 ++-- 4 files changed, 5 insertions(+), 5 deletions(-) diff --git a/drivers/net/ethernet/stmicro/stmmac/dwmac4_core.c b/drivers/net/ethernet/stmicro/stmmac/dwmac4_core.c index 5c6073d95f02..c315e0605baa 100644 --- a/drivers/net/ethernet/stmicro/stmmac/dwmac4_core.c +++ b/drivers/net/ethernet/stmicro/stmmac/dwmac4_core.c @@ -938,7 +938,7 @@ static void dwmac4_set_mac_loopback(void __iomem *ioaddr, bool enable) } static void dwmac4_update_vlan_hash(struct mac_device_info *hw, u32 hash, - __le16 perfect_match, bool is_double) + u16 perfect_match, bool is_double) { void __iomem *ioaddr = hw->pcsr; u32 value; diff --git a/drivers/net/ethernet/stmicro/stmmac/dwxgmac2_core.c b/drivers/net/ethernet/stmicro/stmmac/dwxgmac2_core.c index 86f70ea9a520..357762ce23ff 100644 --- a/drivers/net/ethernet/stmicro/stmmac/dwxgmac2_core.c +++ b/drivers/net/ethernet/stmicro/stmmac/dwxgmac2_core.c @@ -581,7 +581,7 @@ static int dwxgmac2_rss_configure(struct mac_device_info *hw, } static void dwxgmac2_update_vlan_hash(struct mac_device_info *hw, u32 hash, - __le16 perfect_match, bool is_double) + u16 perfect_match, bool is_double) { void __iomem *ioaddr = hw->pcsr; diff --git a/drivers/net/ethernet/stmicro/stmmac/hwif.h b/drivers/net/ethernet/stmicro/stmmac/hwif.h index 8b7ec2457eba..d7ea2fd944ee 100644 --- a/drivers/net/ethernet/stmicro/stmmac/hwif.h +++ b/drivers/net/ethernet/stmicro/stmmac/hwif.h @@ -368,7 +368,7 @@ struct stmmac_ops { struct stmmac_rss *cfg, u32 num_rxq); /* VLAN */ void (*update_vlan_hash)(struct mac_device_info *hw, u32 hash, - __le16 perfect_match, bool is_double); + u16 perfect_match, bool is_double); void (*enable_vlan)(struct mac_device_info *hw, u32 type); int (*add_hw_vlan_rx_fltr)(struct net_device *dev, struct mac_device_info *hw, diff --git a/drivers/net/ethernet/stmicro/stmmac/stmmac_main.c b/drivers/net/ethernet/stmicro/stmmac/stmmac_main.c index 8416a186cd7f..b8581a711514 100644 --- a/drivers/net/ethernet/stmicro/stmmac/stmmac_main.c +++ b/drivers/net/ethernet/stmicro/stmmac/stmmac_main.c @@ -4660,7 +4660,7 @@ static u32 stmmac_vid_crc32_le(__le16 vid_le) static int stmmac_vlan_update(struct stmmac_priv *priv, bool is_double) { u32 crc, hash = 0; - __le16 pmatch = 0; + u16 pmatch = 0; int count = 0; u16 vid = 0; @@ -4675,7 +4675,7 @@ static int stmmac_vlan_update(struct stmmac_priv *priv, bool is_double) if (count > 2) /* VID = 0 always passes filter */ return -EOPNOTSUPP; - pmatch = cpu_to_le16(vid); + pmatch = vid; hash = 0; } From 5cc4d71dda2dd4f1520f40e634a527022e48ccd8 Mon Sep 17 00:00:00 2001 From: Petr Machata Date: Tue, 23 Jul 2024 18:04:16 +0200 Subject: [PATCH 193/342] net: nexthop: Initialize all fields in dumped nexthops [ Upstream commit 6d745cd0e9720282cd291d36b9db528aea18add2 ] struct nexthop_grp contains two reserved fields that are not initialized by nla_put_nh_group(), and carry garbage. This can be observed e.g. with strace (edited for clarity): # ip nexthop add id 1 dev lo # ip nexthop add id 101 group 1 # strace -e recvmsg ip nexthop get id 101 ... recvmsg(... [{nla_len=12, nla_type=NHA_GROUP}, [{id=1, weight=0, resvd1=0x69, resvd2=0x67}]] ...) = 52 The fields are reserved and therefore not currently used. But as they are, they leak kernel memory, and the fact they are not just zero complicates repurposing of the fields for new ends. Initialize the full structure. Fixes: 430a049190de ("nexthop: Add support for nexthop groups") Signed-off-by: Petr Machata Reviewed-by: Ido Schimmel Reviewed-by: Eric Dumazet Signed-off-by: David S. Miller Signed-off-by: Sasha Levin --- net/ipv4/nexthop.c | 7 ++++--- 1 file changed, 4 insertions(+), 3 deletions(-) diff --git a/net/ipv4/nexthop.c b/net/ipv4/nexthop.c index 7a0102a4b1de..a508fd94b8be 100644 --- a/net/ipv4/nexthop.c +++ b/net/ipv4/nexthop.c @@ -210,9 +210,10 @@ static int nla_put_nh_group(struct sk_buff *skb, struct nh_group *nhg) p = nla_data(nla); for (i = 0; i < nhg->num_nh; ++i) { - p->id = nhg->nh_entries[i].nh->id; - p->weight = nhg->nh_entries[i].weight - 1; - p += 1; + *p++ = (struct nexthop_grp) { + .id = nhg->nh_entries[i].nh->id, + .weight = nhg->nh_entries[i].weight - 1, + }; } return 0; From dda518dea60d556a2d171c0122ca7d9fdb7d473a Mon Sep 17 00:00:00 2001 From: Fred Li Date: Fri, 19 Jul 2024 10:46:53 +0800 Subject: [PATCH 194/342] bpf: Fix a segment issue when downgrading gso_size [ Upstream commit fa5ef655615a01533035c6139248c5b33aa27028 ] Linearize the skb when downgrading gso_size because it may trigger a BUG_ON() later when the skb is segmented as described in [1,2]. Fixes: 2be7e212d5419 ("bpf: add bpf_skb_adjust_room helper") Signed-off-by: Fred Li Signed-off-by: Daniel Borkmann Reviewed-by: Willem de Bruijn Acked-by: Daniel Borkmann Link: https://lore.kernel.org/all/20240626065555.35460-2-dracodingfly@gmail.com [1] Link: https://lore.kernel.org/all/668d5cf1ec330_1c18c32947@willemb.c.googlers.com.notmuch [2] Link: https://lore.kernel.org/bpf/20240719024653.77006-1-dracodingfly@gmail.com Signed-off-by: Sasha Levin --- net/core/filter.c | 15 +++++++++++---- 1 file changed, 11 insertions(+), 4 deletions(-) diff --git a/net/core/filter.c b/net/core/filter.c index a3101cdfd47b..99fdd8afeeda 100644 --- a/net/core/filter.c +++ b/net/core/filter.c @@ -3535,13 +3535,20 @@ static int bpf_skb_net_grow(struct sk_buff *skb, u32 off, u32 len_diff, if (skb_is_gso(skb)) { struct skb_shared_info *shinfo = skb_shinfo(skb); - /* Due to header grow, MSS needs to be downgraded. */ - if (!(flags & BPF_F_ADJ_ROOM_FIXED_GSO)) - skb_decrease_gso_size(shinfo, len_diff); - /* Header must be checked, and gso_segs recomputed. */ shinfo->gso_type |= gso_type; shinfo->gso_segs = 0; + + /* Due to header growth, MSS needs to be downgraded. + * There is a BUG_ON() when segmenting the frag_list with + * head_frag true, so linearize the skb after downgrading + * the MSS. + */ + if (!(flags & BPF_F_ADJ_ROOM_FIXED_GSO)) { + skb_decrease_gso_size(shinfo, len_diff); + if (shinfo->frag_list) + return skb_linearize(skb); + } } return 0; From 9460ac3dd1ae033bc2b021a458fb535a0c36ddb2 Mon Sep 17 00:00:00 2001 From: Dan Carpenter Date: Wed, 24 Jul 2024 11:08:18 -0500 Subject: [PATCH 195/342] mISDN: Fix a use after free in hfcmulti_tx() [ Upstream commit 61ab751451f5ebd0b98e02276a44e23a10110402 ] Don't dereference *sp after calling dev_kfree_skb(*sp). Fixes: af69fb3a8ffa ("Add mISDN HFC multiport driver") Signed-off-by: Dan Carpenter Reviewed-by: Simon Horman Link: https://patch.msgid.link/8be65f5a-c2dd-4ba0-8a10-bfe5980b8cfb@stanley.mountain Signed-off-by: Jakub Kicinski Signed-off-by: Sasha Levin --- drivers/isdn/hardware/mISDN/hfcmulti.c | 7 ++++--- 1 file changed, 4 insertions(+), 3 deletions(-) diff --git a/drivers/isdn/hardware/mISDN/hfcmulti.c b/drivers/isdn/hardware/mISDN/hfcmulti.c index 4c5b6772562d..a0697d64aab3 100644 --- a/drivers/isdn/hardware/mISDN/hfcmulti.c +++ b/drivers/isdn/hardware/mISDN/hfcmulti.c @@ -1931,7 +1931,7 @@ hfcmulti_dtmf(struct hfc_multi *hc) static void hfcmulti_tx(struct hfc_multi *hc, int ch) { - int i, ii, temp, len = 0; + int i, ii, temp, tmp_len, len = 0; int Zspace, z1, z2; /* must be int for calculation */ int Fspace, f1, f2; u_char *d; @@ -2152,14 +2152,15 @@ hfcmulti_tx(struct hfc_multi *hc, int ch) HFC_wait_nodebug(hc); } + tmp_len = (*sp)->len; dev_kfree_skb(*sp); /* check for next frame */ if (bch && get_next_bframe(bch)) { - len = (*sp)->len; + len = tmp_len; goto next_frame; } if (dch && get_next_dframe(dch)) { - len = (*sp)->len; + len = tmp_len; goto next_frame; } From 347dcb84a4874b5fb375092c08d8cc4069b94f81 Mon Sep 17 00:00:00 2001 From: Xiao Liang Date: Sat, 2 Sep 2023 08:48:38 +0800 Subject: [PATCH 196/342] apparmor: Fix null pointer deref when receiving skb during sock creation [ Upstream commit fce09ea314505a52f2436397608fa0a5d0934fb1 ] The panic below is observed when receiving ICMP packets with secmark set while an ICMP raw socket is being created. SK_CTX(sk)->label is updated in apparmor_socket_post_create(), but the packet is delivered to the socket before that, causing the null pointer dereference. Drop the packet if label context is not set. BUG: kernel NULL pointer dereference, address: 000000000000004c #PF: supervisor read access in kernel mode #PF: error_code(0x0000) - not-present page PGD 0 P4D 0 Oops: 0000 [#1] PREEMPT SMP NOPTI CPU: 0 PID: 407 Comm: a.out Not tainted 6.4.12-arch1-1 #1 3e6fa2753a2d75925c34ecb78e22e85a65d083df Hardware name: VMware, Inc. VMware Virtual Platform/440BX Desktop Reference Platform, BIOS 6.00 05/28/2020 RIP: 0010:aa_label_next_confined+0xb/0x40 Code: 00 00 48 89 ef e8 d5 25 0c 00 e9 66 ff ff ff 90 90 90 90 90 90 90 90 90 90 90 90 90 90 90 90 66 0f 1f 00 0f 1f 44 00 00 89 f0 <8b> 77 4c 39 c6 7e 1f 48 63 d0 48 8d 14 d7 eb 0b 83 c0 01 48 83 c2 RSP: 0018:ffffa92940003b08 EFLAGS: 00010246 RAX: 0000000000000000 RBX: 0000000000000000 RCX: 000000000000000e RDX: ffffa92940003be8 RSI: 0000000000000000 RDI: 0000000000000000 RBP: ffff8b57471e7800 R08: ffff8b574c642400 R09: 0000000000000002 R10: ffffffffbd820eeb R11: ffffffffbeb7ff00 R12: ffff8b574c642400 R13: 0000000000000001 R14: 0000000000000001 R15: 0000000000000000 FS: 00007fb092ea7640(0000) GS:ffff8b577bc00000(0000) knlGS:0000000000000000 CS: 0010 DS: 0000 ES: 0000 CR0: 0000000080050033 CR2: 000000000000004c CR3: 00000001020f2005 CR4: 00000000007706f0 PKRU: 55555554 Call Trace: ? __die+0x23/0x70 ? page_fault_oops+0x171/0x4e0 ? exc_page_fault+0x7f/0x180 ? asm_exc_page_fault+0x26/0x30 ? aa_label_next_confined+0xb/0x40 apparmor_secmark_check+0xec/0x330 security_sock_rcv_skb+0x35/0x50 sk_filter_trim_cap+0x47/0x250 sock_queue_rcv_skb_reason+0x20/0x60 raw_rcv+0x13c/0x210 raw_local_deliver+0x1f3/0x250 ip_protocol_deliver_rcu+0x4f/0x2f0 ip_local_deliver_finish+0x76/0xa0 __netif_receive_skb_one_core+0x89/0xa0 netif_receive_skb+0x119/0x170 ? __netdev_alloc_skb+0x3d/0x140 vmxnet3_rq_rx_complete+0xb23/0x1010 [vmxnet3 56a84f9c97178c57a43a24ec073b45a9d6f01f3a] vmxnet3_poll_rx_only+0x36/0xb0 [vmxnet3 56a84f9c97178c57a43a24ec073b45a9d6f01f3a] __napi_poll+0x28/0x1b0 net_rx_action+0x2a4/0x380 __do_softirq+0xd1/0x2c8 __irq_exit_rcu+0xbb/0xf0 common_interrupt+0x86/0xa0 asm_common_interrupt+0x26/0x40 RIP: 0010:apparmor_socket_post_create+0xb/0x200 Code: 08 48 85 ff 75 a1 eb b1 0f 1f 80 00 00 00 00 90 90 90 90 90 90 90 90 90 90 90 90 90 90 90 90 f3 0f 1e fa 0f 1f 44 00 00 41 54 <55> 48 89 fd 53 45 85 c0 0f 84 b2 00 00 00 48 8b 1d 80 56 3f 02 48 RSP: 0018:ffffa92940ce7e50 EFLAGS: 00000286 RAX: ffffffffbc756440 RBX: 0000000000000000 RCX: 0000000000000001 RDX: 0000000000000003 RSI: 0000000000000002 RDI: ffff8b574eaab740 RBP: 0000000000000001 R08: 0000000000000000 R09: 0000000000000000 R10: ffff8b57444cec70 R11: 0000000000000000 R12: 0000000000000003 R13: 0000000000000002 R14: ffff8b574eaab740 R15: ffffffffbd8e4748 ? __pfx_apparmor_socket_post_create+0x10/0x10 security_socket_post_create+0x4b/0x80 __sock_create+0x176/0x1f0 __sys_socket+0x89/0x100 __x64_sys_socket+0x17/0x20 do_syscall_64+0x5d/0x90 ? do_syscall_64+0x6c/0x90 ? do_syscall_64+0x6c/0x90 ? do_syscall_64+0x6c/0x90 entry_SYSCALL_64_after_hwframe+0x72/0xdc Fixes: ab9f2115081a ("apparmor: Allow filtering based on secmark policy") Signed-off-by: Xiao Liang Signed-off-by: John Johansen Signed-off-by: Sasha Levin --- security/apparmor/lsm.c | 7 +++++++ 1 file changed, 7 insertions(+) diff --git a/security/apparmor/lsm.c b/security/apparmor/lsm.c index 052f1b920e43..37aa1650c74e 100644 --- a/security/apparmor/lsm.c +++ b/security/apparmor/lsm.c @@ -1048,6 +1048,13 @@ static int apparmor_socket_sock_rcv_skb(struct sock *sk, struct sk_buff *skb) if (!skb->secmark) return 0; + /* + * If reach here before socket_post_create hook is called, in which + * case label is null, drop the packet. + */ + if (!ctx->label) + return -EACCES; + return apparmor_secmark_check(ctx->label, OP_RECVMSG, AA_MAY_RECEIVE, skb->secmark, sk); } From ea72a8881007b6924c11cb9a3ecb67946478e121 Mon Sep 17 00:00:00 2001 From: Al Viro Date: Thu, 30 May 2024 23:54:55 -0400 Subject: [PATCH 197/342] powerpc: fix a file leak in kvm_vcpu_ioctl_enable_cap() [ Upstream commit b4cf5fc01ce83e5c0bcf3dbb9f929428646b9098 ] missing fdput() on one of the failure exits Fixes: eacc56bb9de3e # v5.2 Signed-off-by: Al Viro Signed-off-by: Sasha Levin --- arch/powerpc/kvm/powerpc.c | 4 +++- 1 file changed, 3 insertions(+), 1 deletion(-) diff --git a/arch/powerpc/kvm/powerpc.c b/arch/powerpc/kvm/powerpc.c index ef8077a739b8..0f5ebec660a7 100644 --- a/arch/powerpc/kvm/powerpc.c +++ b/arch/powerpc/kvm/powerpc.c @@ -1956,8 +1956,10 @@ static int kvm_vcpu_ioctl_enable_cap(struct kvm_vcpu *vcpu, break; r = -ENXIO; - if (!xive_enabled()) + if (!xive_enabled()) { + fdput(f); break; + } r = -EPERM; dev = kvm_device_from_filp(f.file); From 3ff431695351b4b705f4a23b7fa1b219a2160cb5 Mon Sep 17 00:00:00 2001 From: Al Viro Date: Thu, 30 May 2024 23:58:26 -0400 Subject: [PATCH 198/342] lirc: rc_dev_get_from_fd(): fix file leak [ Upstream commit bba1f6758a9ec90c1adac5dcf78f8a15f1bad65b ] missing fdput() on a failure exit Fixes: 6a9d552483d50 "media: rc: bpf attach/detach requires write permission" # v6.9 Signed-off-by: Al Viro Signed-off-by: Sasha Levin --- drivers/media/rc/lirc_dev.c | 4 +++- 1 file changed, 3 insertions(+), 1 deletion(-) diff --git a/drivers/media/rc/lirc_dev.c b/drivers/media/rc/lirc_dev.c index 14243ce03b46..c59601487334 100644 --- a/drivers/media/rc/lirc_dev.c +++ b/drivers/media/rc/lirc_dev.c @@ -840,8 +840,10 @@ struct rc_dev *rc_dev_get_from_fd(int fd, bool write) return ERR_PTR(-EINVAL); } - if (write && !(f.file->f_mode & FMODE_WRITE)) + if (write && !(f.file->f_mode & FMODE_WRITE)) { + fdput(f); return ERR_PTR(-EPERM); + } fh = f.file->private_data; dev = fh->rc; From eb1b7575fe52f76d10cc014d11b308a5203adf5f Mon Sep 17 00:00:00 2001 From: Pierre-Louis Bossart Date: Mon, 22 Jul 2024 10:30:02 +0200 Subject: [PATCH 199/342] ASoC: Intel: use soc_intel_is_byt_cr() only when IOSF_MBI is reachable MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit [ Upstream commit 9931f7d5d251882a147cc5811060097df43e79f5 ] the Intel kbuild bot reports a link failure when IOSF_MBI is built-in but the Merrifield driver is configured as a module. The soc-intel-quirks.h is included for Merrifield platforms, but IOSF_MBI is not selected for that platform. ld.lld: error: undefined symbol: iosf_mbi_read >>> referenced by atom.c >>> sound/soc/sof/intel/atom.o:(atom_machine_select) in archive vmlinux.a This patch forces the use of the fallback static inline when IOSF_MBI is not reachable. Fixes: 536cfd2f375d ("ASoC: Intel: use common helpers to detect CPUs") Reported-by: kernel test robot Closes: https://lore.kernel.org/oe-kbuild-all/202407160704.zpdhJ8da-lkp@intel.com/ Suggested-by: Takashi Iwai Signed-off-by: Pierre-Louis Bossart Reviewed-by: Péter Ujfalusi Reviewed-by: Bard Liao Link: https://patch.msgid.link/20240722083002.10800-1-pierre-louis.bossart@linux.intel.com Signed-off-by: Mark Brown Signed-off-by: Sasha Levin --- sound/soc/intel/common/soc-intel-quirks.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/sound/soc/intel/common/soc-intel-quirks.h b/sound/soc/intel/common/soc-intel-quirks.h index de4e550c5b34..42bd51456b94 100644 --- a/sound/soc/intel/common/soc-intel-quirks.h +++ b/sound/soc/intel/common/soc-intel-quirks.h @@ -11,7 +11,7 @@ #include -#if IS_ENABLED(CONFIG_X86) +#if IS_REACHABLE(CONFIG_IOSF_MBI) #include #include From b59013d264b6a8e73cff5cd4ddbc45dc2cab8b95 Mon Sep 17 00:00:00 2001 From: ethanwu Date: Thu, 11 Jul 2024 14:47:56 +0800 Subject: [PATCH 200/342] ceph: fix incorrect kmalloc size of pagevec mempool [ Upstream commit 03230edb0bd831662a7c08b6fef66b2a9a817774 ] The kmalloc size of pagevec mempool is incorrectly calculated. It misses the size of page pointer and only accounts the number for the array. Fixes: a0102bda5bc0 ("ceph: move sb->wb_pagevec_pool to be a global mempool") Signed-off-by: ethanwu Reviewed-by: Xiubo Li Signed-off-by: Ilya Dryomov Signed-off-by: Sasha Levin --- fs/ceph/super.c | 3 ++- 1 file changed, 2 insertions(+), 1 deletion(-) diff --git a/fs/ceph/super.c b/fs/ceph/super.c index f2aff97348bc..4e09d8e06647 100644 --- a/fs/ceph/super.c +++ b/fs/ceph/super.c @@ -783,7 +783,8 @@ static int __init init_caches(void) if (!ceph_mds_request_cachep) goto bad_mds_req; - ceph_wb_pagevec_pool = mempool_create_kmalloc_pool(10, CEPH_MAX_WRITE_SIZE >> PAGE_SHIFT); + ceph_wb_pagevec_pool = mempool_create_kmalloc_pool(10, + (CEPH_MAX_WRITE_SIZE >> PAGE_SHIFT) * sizeof(struct page *)); if (!ceph_wb_pagevec_pool) goto bad_pagevec_pool; From ce90f30157ebd44b83dc3526760067157897517a Mon Sep 17 00:00:00 2001 From: Jens Axboe Date: Fri, 29 Oct 2021 14:32:44 -0600 Subject: [PATCH 201/342] nvme: split command copy into a helper [ Upstream commit 3233b94cf842984ea7e208d5be1ad2f2af02d495 ] We'll need it for batched submit as well. Since we now have a copy helper, get rid of the nvme_submit_cmd() wrapper. Reviewed-by: Chaitanya Kulkarni Reviewed-by: Hannes Reinecke Reviewed-by: Max Gurtovoy Reviewed-by: Christoph Hellwig Signed-off-by: Jens Axboe Stable-dep-of: c31fad147038 ("nvme-pci: add missing condition check for existence of mapped data") Signed-off-by: Sasha Levin --- drivers/nvme/host/pci.c | 26 ++++++++++++-------------- 1 file changed, 12 insertions(+), 14 deletions(-) diff --git a/drivers/nvme/host/pci.c b/drivers/nvme/host/pci.c index a7131f4752e2..1436aee1f861 100644 --- a/drivers/nvme/host/pci.c +++ b/drivers/nvme/host/pci.c @@ -486,22 +486,13 @@ static inline void nvme_write_sq_db(struct nvme_queue *nvmeq, bool write_sq) nvmeq->last_sq_tail = nvmeq->sq_tail; } -/** - * nvme_submit_cmd() - Copy a command into a queue and ring the doorbell - * @nvmeq: The queue to use - * @cmd: The command to send - * @write_sq: whether to write to the SQ doorbell - */ -static void nvme_submit_cmd(struct nvme_queue *nvmeq, struct nvme_command *cmd, - bool write_sq) +static inline void nvme_sq_copy_cmd(struct nvme_queue *nvmeq, + struct nvme_command *cmd) { - spin_lock(&nvmeq->sq_lock); memcpy(nvmeq->sq_cmds + (nvmeq->sq_tail << nvmeq->sqes), - cmd, sizeof(*cmd)); + absolute_pointer(cmd), sizeof(*cmd)); if (++nvmeq->sq_tail == nvmeq->q_depth) nvmeq->sq_tail = 0; - nvme_write_sq_db(nvmeq, write_sq); - spin_unlock(&nvmeq->sq_lock); } static void nvme_commit_rqs(struct blk_mq_hw_ctx *hctx) @@ -945,7 +936,10 @@ static blk_status_t nvme_queue_rq(struct blk_mq_hw_ctx *hctx, } blk_mq_start_request(req); - nvme_submit_cmd(nvmeq, cmnd, bd->last); + spin_lock(&nvmeq->sq_lock); + nvme_sq_copy_cmd(nvmeq, &iod->cmd); + nvme_write_sq_db(nvmeq, bd->last); + spin_unlock(&nvmeq->sq_lock); return BLK_STS_OK; out_unmap_data: nvme_unmap_data(dev, req); @@ -1120,7 +1114,11 @@ static void nvme_pci_submit_async_event(struct nvme_ctrl *ctrl) memset(&c, 0, sizeof(c)); c.common.opcode = nvme_admin_async_event; c.common.command_id = NVME_AQ_BLK_MQ_DEPTH; - nvme_submit_cmd(nvmeq, &c, true); + + spin_lock(&nvmeq->sq_lock); + nvme_sq_copy_cmd(nvmeq, &c); + nvme_write_sq_db(nvmeq, true); + spin_unlock(&nvmeq->sq_lock); } static int adapter_delete_queue(struct nvme_dev *dev, u8 opcode, u16 id) From be23ae63080e0bf9e246ab20207200bca6585eba Mon Sep 17 00:00:00 2001 From: Leon Romanovsky Date: Wed, 24 Jul 2024 13:31:14 +0300 Subject: [PATCH 202/342] nvme-pci: add missing condition check for existence of mapped data [ Upstream commit c31fad1470389666ac7169fe43aa65bf5b7e2cfd ] nvme_map_data() is called when request has physical segments, hence the nvme_unmap_data() should have same condition to avoid dereference. Fixes: 4aedb705437f ("nvme-pci: split metadata handling from nvme_map_data / nvme_unmap_data") Signed-off-by: Leon Romanovsky Reviewed-by: Christoph Hellwig Reviewed-by: Nitesh Shetty Signed-off-by: Keith Busch Signed-off-by: Sasha Levin --- drivers/nvme/host/pci.c | 3 ++- 1 file changed, 2 insertions(+), 1 deletion(-) diff --git a/drivers/nvme/host/pci.c b/drivers/nvme/host/pci.c index 1436aee1f861..4a4b7aa74835 100644 --- a/drivers/nvme/host/pci.c +++ b/drivers/nvme/host/pci.c @@ -942,7 +942,8 @@ static blk_status_t nvme_queue_rq(struct blk_mq_hw_ctx *hctx, spin_unlock(&nvmeq->sq_lock); return BLK_STS_OK; out_unmap_data: - nvme_unmap_data(dev, req); + if (blk_rq_nr_phys_segments(req)) + nvme_unmap_data(dev, req); out_free_cmd: nvme_cleanup_cmd(req); return ret; From d28869a145cff53c9e6af7a68e67847d3fccb811 Mon Sep 17 00:00:00 2001 From: "Seth Forshee (DigitalOcean)" Date: Wed, 24 Jul 2024 09:53:59 -0500 Subject: [PATCH 203/342] fs: don't allow non-init s_user_ns for filesystems without FS_USERNS_MOUNT [ Upstream commit e1c5ae59c0f22f7fe5c07fb5513a29e4aad868c9 ] Christian noticed that it is possible for a privileged user to mount most filesystems with a non-initial user namespace in sb->s_user_ns. When fsopen() is called in a non-init namespace the caller's namespace is recorded in fs_context->user_ns. If the returned file descriptor is then passed to a process priviliged in init_user_ns, that process can call fsconfig(fd_fs, FSCONFIG_CMD_CREATE), creating a new superblock with sb->s_user_ns set to the namespace of the process which called fsopen(). This is problematic. We cannot assume that any filesystem which does not set FS_USERNS_MOUNT has been written with a non-initial s_user_ns in mind, increasing the risk for bugs and security issues. Prevent this by returning EPERM from sget_fc() when FS_USERNS_MOUNT is not set for the filesystem and a non-initial user namespace will be used. sget() does not need to be updated as it always uses the user namespace of the current context, or the initial user namespace if SB_SUBMOUNT is set. Fixes: cb50b348c71f ("convenience helpers: vfs_get_super() and sget_fc()") Reported-by: Christian Brauner Signed-off-by: Seth Forshee (DigitalOcean) Link: https://lore.kernel.org/r/20240724-s_user_ns-fix-v1-1-895d07c94701@kernel.org Reviewed-by: Alexander Mikhalitsyn Signed-off-by: Christian Brauner Signed-off-by: Sasha Levin --- fs/super.c | 11 +++++++++++ 1 file changed, 11 insertions(+) diff --git a/fs/super.c b/fs/super.c index f9795e72e3bf..282aa36901eb 100644 --- a/fs/super.c +++ b/fs/super.c @@ -518,6 +518,17 @@ struct super_block *sget_fc(struct fs_context *fc, struct user_namespace *user_ns = fc->global ? &init_user_ns : fc->user_ns; int err; + /* + * Never allow s_user_ns != &init_user_ns when FS_USERNS_MOUNT is + * not set, as the filesystem is likely unprepared to handle it. + * This can happen when fsconfig() is called from init_user_ns with + * an fs_fd opened in another user namespace. + */ + if (user_ns != &init_user_ns && !(fc->fs_type->fs_flags & FS_USERNS_MOUNT)) { + errorfc(fc, "VFS: Mounting from non-initial user namespace is not allowed"); + return ERR_PTR(-EPERM); + } + retry: spin_lock(&sb_lock); if (test) { From 2fa82af6fd04cdc3b0e9f7e40bd7773c4a3cd739 Mon Sep 17 00:00:00 2001 From: Esben Haabendal Date: Thu, 30 May 2024 16:46:37 +0200 Subject: [PATCH 204/342] powerpc/configs: Update defconfig with now user-visible CONFIG_FSL_IFC commit 45547a0a93d85f704b49788cde2e1d9ab9cd363b upstream. With CONFIG_FSL_IFC now being user-visible, and thus changed from a select to depends in CONFIG_MTD_NAND_FSL_IFC, the dependencies needs to be selected in defconfigs. Depends-on: 9ba0cae3cac0 ("memory: fsl_ifc: Make FSL_IFC config visible and selectable") Signed-off-by: Esben Haabendal Reviewed-by: Krzysztof Kozlowski Signed-off-by: Michael Ellerman Link: https://msgid.link/20240530-fsl-ifc-config-v3-2-1fd2c3d233dd@geanix.com Signed-off-by: Greg Kroah-Hartman --- arch/powerpc/configs/85xx-hw.config | 2 ++ 1 file changed, 2 insertions(+) diff --git a/arch/powerpc/configs/85xx-hw.config b/arch/powerpc/configs/85xx-hw.config index 524db76f47b7..8aff83217397 100644 --- a/arch/powerpc/configs/85xx-hw.config +++ b/arch/powerpc/configs/85xx-hw.config @@ -24,6 +24,7 @@ CONFIG_FS_ENET=y CONFIG_FSL_CORENET_CF=y CONFIG_FSL_DMA=y CONFIG_FSL_HV_MANAGER=y +CONFIG_FSL_IFC=y CONFIG_FSL_PQ_MDIO=y CONFIG_FSL_RIO=y CONFIG_FSL_XGMAC_MDIO=y @@ -58,6 +59,7 @@ CONFIG_INPUT_FF_MEMLESS=m CONFIG_MARVELL_PHY=y CONFIG_MDIO_BUS_MUX_GPIO=y CONFIG_MDIO_BUS_MUX_MMIOREG=y +CONFIG_MEMORY=y CONFIG_MMC_SDHCI_OF_ESDHC=y CONFIG_MMC_SDHCI_PLTFM=y CONFIG_MMC_SDHCI=y From 997d3c9cbed656ed1ef6f36e8818f0a4ce1f75cc Mon Sep 17 00:00:00 2001 From: Miklos Szeredi Date: Wed, 4 Aug 2021 13:22:58 +0200 Subject: [PATCH 205/342] fuse: name fs_context consistently [ Upstream commit 84c215075b5723ab946708a6c74c26bd3c51114c ] Naming convention under fs/fuse/: struct fuse_conn *fc; struct fs_context *fsc; Signed-off-by: Miklos Szeredi Stable-dep-of: 525bd65aa759 ("fuse: verify {g,u}id mount options correctly") Signed-off-by: Sasha Levin --- fs/fuse/control.c | 10 ++++---- fs/fuse/inode.c | 60 ++++++++++++++++++++++----------------------- fs/fuse/virtio_fs.c | 12 ++++----- 3 files changed, 41 insertions(+), 41 deletions(-) diff --git a/fs/fuse/control.c b/fs/fuse/control.c index 24b4d9db231d..79f01d09c78c 100644 --- a/fs/fuse/control.c +++ b/fs/fuse/control.c @@ -328,7 +328,7 @@ void fuse_ctl_remove_conn(struct fuse_conn *fc) drop_nlink(d_inode(fuse_control_sb->s_root)); } -static int fuse_ctl_fill_super(struct super_block *sb, struct fs_context *fctx) +static int fuse_ctl_fill_super(struct super_block *sb, struct fs_context *fsc) { static const struct tree_descr empty_descr = {""}; struct fuse_conn *fc; @@ -354,18 +354,18 @@ static int fuse_ctl_fill_super(struct super_block *sb, struct fs_context *fctx) return 0; } -static int fuse_ctl_get_tree(struct fs_context *fc) +static int fuse_ctl_get_tree(struct fs_context *fsc) { - return get_tree_single(fc, fuse_ctl_fill_super); + return get_tree_single(fsc, fuse_ctl_fill_super); } static const struct fs_context_operations fuse_ctl_context_ops = { .get_tree = fuse_ctl_get_tree, }; -static int fuse_ctl_init_fs_context(struct fs_context *fc) +static int fuse_ctl_init_fs_context(struct fs_context *fsc) { - fc->ops = &fuse_ctl_context_ops; + fsc->ops = &fuse_ctl_context_ops; return 0; } diff --git a/fs/fuse/inode.c b/fs/fuse/inode.c index 4a7ebccd359e..5f9b2dc59135 100644 --- a/fs/fuse/inode.c +++ b/fs/fuse/inode.c @@ -141,12 +141,12 @@ static void fuse_evict_inode(struct inode *inode) } } -static int fuse_reconfigure(struct fs_context *fc) +static int fuse_reconfigure(struct fs_context *fsc) { - struct super_block *sb = fc->root->d_sb; + struct super_block *sb = fsc->root->d_sb; sync_filesystem(sb); - if (fc->sb_flags & SB_MANDLOCK) + if (fsc->sb_flags & SB_MANDLOCK) return -EINVAL; return 0; @@ -535,38 +535,38 @@ static const struct fs_parameter_spec fuse_fs_parameters[] = { {} }; -static int fuse_parse_param(struct fs_context *fc, struct fs_parameter *param) +static int fuse_parse_param(struct fs_context *fsc, struct fs_parameter *param) { struct fs_parse_result result; - struct fuse_fs_context *ctx = fc->fs_private; + struct fuse_fs_context *ctx = fsc->fs_private; int opt; - if (fc->purpose == FS_CONTEXT_FOR_RECONFIGURE) { + if (fsc->purpose == FS_CONTEXT_FOR_RECONFIGURE) { /* * Ignore options coming from mount(MS_REMOUNT) for backward * compatibility. */ - if (fc->oldapi) + if (fsc->oldapi) return 0; - return invalfc(fc, "No changes allowed in reconfigure"); + return invalfc(fsc, "No changes allowed in reconfigure"); } - opt = fs_parse(fc, fuse_fs_parameters, param, &result); + opt = fs_parse(fsc, fuse_fs_parameters, param, &result); if (opt < 0) return opt; switch (opt) { case OPT_SOURCE: - if (fc->source) - return invalfc(fc, "Multiple sources specified"); - fc->source = param->string; + if (fsc->source) + return invalfc(fsc, "Multiple sources specified"); + fsc->source = param->string; param->string = NULL; break; case OPT_SUBTYPE: if (ctx->subtype) - return invalfc(fc, "Multiple subtypes specified"); + return invalfc(fsc, "Multiple subtypes specified"); ctx->subtype = param->string; param->string = NULL; return 0; @@ -578,22 +578,22 @@ static int fuse_parse_param(struct fs_context *fc, struct fs_parameter *param) case OPT_ROOTMODE: if (!fuse_valid_type(result.uint_32)) - return invalfc(fc, "Invalid rootmode"); + return invalfc(fsc, "Invalid rootmode"); ctx->rootmode = result.uint_32; ctx->rootmode_present = true; break; case OPT_USER_ID: - ctx->user_id = make_kuid(fc->user_ns, result.uint_32); + ctx->user_id = make_kuid(fsc->user_ns, result.uint_32); if (!uid_valid(ctx->user_id)) - return invalfc(fc, "Invalid user_id"); + return invalfc(fsc, "Invalid user_id"); ctx->user_id_present = true; break; case OPT_GROUP_ID: - ctx->group_id = make_kgid(fc->user_ns, result.uint_32); + ctx->group_id = make_kgid(fsc->user_ns, result.uint_32); if (!gid_valid(ctx->group_id)) - return invalfc(fc, "Invalid group_id"); + return invalfc(fsc, "Invalid group_id"); ctx->group_id_present = true; break; @@ -611,7 +611,7 @@ static int fuse_parse_param(struct fs_context *fc, struct fs_parameter *param) case OPT_BLKSIZE: if (!ctx->is_bdev) - return invalfc(fc, "blksize only supported for fuseblk"); + return invalfc(fsc, "blksize only supported for fuseblk"); ctx->blksize = result.uint_32; break; @@ -622,9 +622,9 @@ static int fuse_parse_param(struct fs_context *fc, struct fs_parameter *param) return 0; } -static void fuse_free_fc(struct fs_context *fc) +static void fuse_free_fsc(struct fs_context *fsc) { - struct fuse_fs_context *ctx = fc->fs_private; + struct fuse_fs_context *ctx = fsc->fs_private; if (ctx) { kfree(ctx->subtype); @@ -1486,9 +1486,9 @@ static int fuse_fill_super(struct super_block *sb, struct fs_context *fsc) return err; } -static int fuse_get_tree(struct fs_context *fc) +static int fuse_get_tree(struct fs_context *fsc) { - struct fuse_fs_context *ctx = fc->fs_private; + struct fuse_fs_context *ctx = fsc->fs_private; if (!ctx->fd_present || !ctx->rootmode_present || !ctx->user_id_present || !ctx->group_id_present) @@ -1496,14 +1496,14 @@ static int fuse_get_tree(struct fs_context *fc) #ifdef CONFIG_BLOCK if (ctx->is_bdev) - return get_tree_bdev(fc, fuse_fill_super); + return get_tree_bdev(fsc, fuse_fill_super); #endif - return get_tree_nodev(fc, fuse_fill_super); + return get_tree_nodev(fsc, fuse_fill_super); } static const struct fs_context_operations fuse_context_ops = { - .free = fuse_free_fc, + .free = fuse_free_fsc, .parse_param = fuse_parse_param, .reconfigure = fuse_reconfigure, .get_tree = fuse_get_tree, @@ -1512,7 +1512,7 @@ static const struct fs_context_operations fuse_context_ops = { /* * Set up the filesystem mount context. */ -static int fuse_init_fs_context(struct fs_context *fc) +static int fuse_init_fs_context(struct fs_context *fsc) { struct fuse_fs_context *ctx; @@ -1525,14 +1525,14 @@ static int fuse_init_fs_context(struct fs_context *fc) ctx->legacy_opts_show = true; #ifdef CONFIG_BLOCK - if (fc->fs_type == &fuseblk_fs_type) { + if (fsc->fs_type == &fuseblk_fs_type) { ctx->is_bdev = true; ctx->destroy = true; } #endif - fc->fs_private = ctx; - fc->ops = &fuse_context_ops; + fsc->fs_private = ctx; + fsc->ops = &fuse_context_ops; return 0; } diff --git a/fs/fuse/virtio_fs.c b/fs/fuse/virtio_fs.c index faadc80485e7..7d4655022afc 100644 --- a/fs/fuse/virtio_fs.c +++ b/fs/fuse/virtio_fs.c @@ -97,14 +97,14 @@ static const struct fs_parameter_spec virtio_fs_parameters[] = { {} }; -static int virtio_fs_parse_param(struct fs_context *fc, +static int virtio_fs_parse_param(struct fs_context *fsc, struct fs_parameter *param) { struct fs_parse_result result; - struct fuse_fs_context *ctx = fc->fs_private; + struct fuse_fs_context *ctx = fsc->fs_private; int opt; - opt = fs_parse(fc, virtio_fs_parameters, param, &result); + opt = fs_parse(fsc, virtio_fs_parameters, param, &result); if (opt < 0) return opt; @@ -119,9 +119,9 @@ static int virtio_fs_parse_param(struct fs_context *fc, return 0; } -static void virtio_fs_free_fc(struct fs_context *fc) +static void virtio_fs_free_fsc(struct fs_context *fsc) { - struct fuse_fs_context *ctx = fc->fs_private; + struct fuse_fs_context *ctx = fsc->fs_private; kfree(ctx); } @@ -1500,7 +1500,7 @@ static int virtio_fs_get_tree(struct fs_context *fsc) } static const struct fs_context_operations virtio_fs_context_ops = { - .free = virtio_fs_free_fc, + .free = virtio_fs_free_fsc, .parse_param = virtio_fs_parse_param, .get_tree = virtio_fs_get_tree, }; From 88f053a1dd34c9e41c1c65e55375fe5217437fbf Mon Sep 17 00:00:00 2001 From: Eric Sandeen Date: Tue, 2 Jul 2024 17:22:41 -0500 Subject: [PATCH 206/342] fuse: verify {g,u}id mount options correctly [ Upstream commit 525bd65aa759ec320af1dc06e114ed69733e9e23 ] As was done in 0200679fc795 ("tmpfs: verify {g,u}id mount options correctly") we need to validate that the requested uid and/or gid is representable in the filesystem's idmapping. Cribbing from the above commit log, The contract for {g,u}id mount options and {g,u}id values in general set from userspace has always been that they are translated according to the caller's idmapping. In so far, fuse has been doing the correct thing. But since fuse is mountable in unprivileged contexts it is also necessary to verify that the resulting {k,g}uid is representable in the namespace of the superblock. Fixes: c30da2e981a7 ("fuse: convert to use the new mount API") Cc: stable@vger.kernel.org # 5.4+ Signed-off-by: Eric Sandeen Link: https://lore.kernel.org/r/8f07d45d-c806-484d-a2e3-7a2199df1cd2@redhat.com Reviewed-by: Christian Brauner Reviewed-by: Josef Bacik Signed-off-by: Christian Brauner Signed-off-by: Sasha Levin --- fs/fuse/inode.c | 24 ++++++++++++++++++++---- 1 file changed, 20 insertions(+), 4 deletions(-) diff --git a/fs/fuse/inode.c b/fs/fuse/inode.c index 5f9b2dc59135..a5d1eb0bc521 100644 --- a/fs/fuse/inode.c +++ b/fs/fuse/inode.c @@ -540,6 +540,8 @@ static int fuse_parse_param(struct fs_context *fsc, struct fs_parameter *param) struct fs_parse_result result; struct fuse_fs_context *ctx = fsc->fs_private; int opt; + kuid_t kuid; + kgid_t kgid; if (fsc->purpose == FS_CONTEXT_FOR_RECONFIGURE) { /* @@ -584,16 +586,30 @@ static int fuse_parse_param(struct fs_context *fsc, struct fs_parameter *param) break; case OPT_USER_ID: - ctx->user_id = make_kuid(fsc->user_ns, result.uint_32); - if (!uid_valid(ctx->user_id)) + kuid = make_kuid(fsc->user_ns, result.uint_32); + if (!uid_valid(kuid)) return invalfc(fsc, "Invalid user_id"); + /* + * The requested uid must be representable in the + * filesystem's idmapping. + */ + if (!kuid_has_mapping(fsc->user_ns, kuid)) + return invalfc(fsc, "Invalid user_id"); + ctx->user_id = kuid; ctx->user_id_present = true; break; case OPT_GROUP_ID: - ctx->group_id = make_kgid(fsc->user_ns, result.uint_32); - if (!gid_valid(ctx->group_id)) + kgid = make_kgid(fsc->user_ns, result.uint_32);; + if (!gid_valid(kgid)) return invalfc(fsc, "Invalid group_id"); + /* + * The requested gid must be representable in the + * filesystem's idmapping. + */ + if (!kgid_has_mapping(fsc->user_ns, kgid)) + return invalfc(fsc, "Invalid group_id"); + ctx->group_id = kgid; ctx->group_id_present = true; break; From b2591c89a6e2858796111138c38fcb6851aa1955 Mon Sep 17 00:00:00 2001 From: =?UTF-8?q?Thomas=20Wei=C3=9Fschuh?= Date: Tue, 2 Apr 2024 23:10:34 +0200 Subject: [PATCH 207/342] sysctl: always initialize i_uid/i_gid MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit [ Upstream commit 98ca62ba9e2be5863c7d069f84f7166b45a5b2f4 ] Always initialize i_uid/i_gid inside the sysfs core so set_ownership() can safely skip setting them. Commit 5ec27ec735ba ("fs/proc/proc_sysctl.c: fix the default values of i_uid/i_gid on /proc/sys inodes.") added defaults for i_uid/i_gid when set_ownership() was not implemented. It also missed adjusting net_ctl_set_ownership() to use the same default values in case the computation of a better value failed. Fixes: 5ec27ec735ba ("fs/proc/proc_sysctl.c: fix the default values of i_uid/i_gid on /proc/sys inodes.") Cc: stable@vger.kernel.org Signed-off-by: Thomas Weißschuh Signed-off-by: Joel Granados Signed-off-by: Sasha Levin --- fs/proc/proc_sysctl.c | 6 ++---- 1 file changed, 2 insertions(+), 4 deletions(-) diff --git a/fs/proc/proc_sysctl.c b/fs/proc/proc_sysctl.c index aff9593feb73..f5c967735335 100644 --- a/fs/proc/proc_sysctl.c +++ b/fs/proc/proc_sysctl.c @@ -471,12 +471,10 @@ static struct inode *proc_sys_make_inode(struct super_block *sb, make_empty_dir_inode(inode); } + inode->i_uid = GLOBAL_ROOT_UID; + inode->i_gid = GLOBAL_ROOT_GID; if (root->set_ownership) root->set_ownership(head, table, &inode->i_uid, &inode->i_gid); - else { - inode->i_uid = GLOBAL_ROOT_UID; - inode->i_gid = GLOBAL_ROOT_GID; - } return inode; } From 4b6d9a0fe743956596c91c7f4eed59b3c67af368 Mon Sep 17 00:00:00 2001 From: Zhang Yi Date: Fri, 17 May 2024 20:39:56 +0800 Subject: [PATCH 208/342] ext4: factor out a common helper to query extent map [ Upstream commit 8e4e5cdf2fdeb99445a468b6b6436ad79b9ecb30 ] Factor out a new common helper ext4_map_query_blocks() from the ext4_da_map_blocks(), it query and return the extent map status on the inode's extent path, no logic changes. Signed-off-by: Zhang Yi Reviewed-by: Jan Kara Reviewed-by: Ritesh Harjani (IBM) Link: https://patch.msgid.link/20240517124005.347221-2-yi.zhang@huaweicloud.com Signed-off-by: Theodore Ts'o Stable-dep-of: 0ea6560abb3b ("ext4: check the extent status again before inserting delalloc block") Signed-off-by: Sasha Levin --- fs/ext4/inode.c | 57 +++++++++++++++++++++++++++---------------------- 1 file changed, 32 insertions(+), 25 deletions(-) diff --git a/fs/ext4/inode.c b/fs/ext4/inode.c index 8b48ed351c4b..a252c84edac8 100644 --- a/fs/ext4/inode.c +++ b/fs/ext4/inode.c @@ -484,6 +484,35 @@ static void ext4_map_blocks_es_recheck(handle_t *handle, } #endif /* ES_AGGRESSIVE_TEST */ +static int ext4_map_query_blocks(handle_t *handle, struct inode *inode, + struct ext4_map_blocks *map) +{ + unsigned int status; + int retval; + + if (ext4_test_inode_flag(inode, EXT4_INODE_EXTENTS)) + retval = ext4_ext_map_blocks(handle, inode, map, 0); + else + retval = ext4_ind_map_blocks(handle, inode, map, 0); + + if (retval <= 0) + return retval; + + if (unlikely(retval != map->m_len)) { + ext4_warning(inode->i_sb, + "ES len assertion failed for inode " + "%lu: retval %d != map->m_len %d", + inode->i_ino, retval, map->m_len); + WARN_ON(1); + } + + status = map->m_flags & EXT4_MAP_UNWRITTEN ? + EXTENT_STATUS_UNWRITTEN : EXTENT_STATUS_WRITTEN; + ext4_es_insert_extent(inode, map->m_lblk, map->m_len, + map->m_pblk, status); + return retval; +} + /* * The ext4_map_blocks() function tries to look up the requested blocks, * and returns if the blocks are already mapped. @@ -1767,33 +1796,11 @@ static int ext4_da_map_blocks(struct inode *inode, sector_t iblock, down_read(&EXT4_I(inode)->i_data_sem); if (ext4_has_inline_data(inode)) retval = 0; - else if (ext4_test_inode_flag(inode, EXT4_INODE_EXTENTS)) - retval = ext4_ext_map_blocks(NULL, inode, map, 0); else - retval = ext4_ind_map_blocks(NULL, inode, map, 0); - if (retval < 0) { - up_read(&EXT4_I(inode)->i_data_sem); - return retval; - } - if (retval > 0) { - unsigned int status; - - if (unlikely(retval != map->m_len)) { - ext4_warning(inode->i_sb, - "ES len assertion failed for inode " - "%lu: retval %d != map->m_len %d", - inode->i_ino, retval, map->m_len); - WARN_ON(1); - } - - status = map->m_flags & EXT4_MAP_UNWRITTEN ? - EXTENT_STATUS_UNWRITTEN : EXTENT_STATUS_WRITTEN; - ext4_es_insert_extent(inode, map->m_lblk, map->m_len, - map->m_pblk, status); - up_read(&EXT4_I(inode)->i_data_sem); - return retval; - } + retval = ext4_map_query_blocks(NULL, inode, map); up_read(&EXT4_I(inode)->i_data_sem); + if (retval) + return retval; add_delayed: down_write(&EXT4_I(inode)->i_data_sem); From 58b07286aef1556e8c667a9d53815dbaffc06178 Mon Sep 17 00:00:00 2001 From: Zhang Yi Date: Fri, 17 May 2024 20:39:57 +0800 Subject: [PATCH 209/342] ext4: check the extent status again before inserting delalloc block [ Upstream commit 0ea6560abb3bac1ffcfa4bf6b2c4d344fdc27b3c ] ext4_da_map_blocks looks up for any extent entry in the extent status tree (w/o i_data_sem) and then the looks up for any ondisk extent mapping (with i_data_sem in read mode). If it finds a hole in the extent status tree or if it couldn't find any entry at all, it then takes the i_data_sem in write mode to add a da entry into the extent status tree. This can actually race with page mkwrite & fallocate path. Note that this is ok between 1. ext4 buffered-write path v/s ext4_page_mkwrite(), because of the folio lock 2. ext4 buffered write path v/s ext4 fallocate because of the inode lock. But this can race between ext4_page_mkwrite() & ext4 fallocate path ext4_page_mkwrite() ext4_fallocate() block_page_mkwrite() ext4_da_map_blocks() //find hole in extent status tree ext4_alloc_file_blocks() ext4_map_blocks() //allocate block and unwritten extent ext4_insert_delayed_block() ext4_da_reserve_space() //reserve one more block ext4_es_insert_delayed_block() //drop unwritten extent and add delayed extent by mistake Then, the delalloc extent is wrong until writeback and the extra reserved block can't be released any more and it triggers below warning: EXT4-fs (pmem2): Inode 13 (00000000bbbd4d23): i_reserved_data_blocks(1) not cleared! Fix the problem by looking up extent status tree again while the i_data_sem is held in write mode. If it still can't find any entry, then we insert a new da entry into the extent status tree. Cc: stable@vger.kernel.org Signed-off-by: Zhang Yi Reviewed-by: Jan Kara Link: https://patch.msgid.link/20240517124005.347221-3-yi.zhang@huaweicloud.com Signed-off-by: Theodore Ts'o Signed-off-by: Sasha Levin --- fs/ext4/inode.c | 21 +++++++++++++++++++++ 1 file changed, 21 insertions(+) diff --git a/fs/ext4/inode.c b/fs/ext4/inode.c index a252c84edac8..6e9323a56d28 100644 --- a/fs/ext4/inode.c +++ b/fs/ext4/inode.c @@ -1760,6 +1760,7 @@ static int ext4_da_map_blocks(struct inode *inode, sector_t iblock, if (ext4_es_is_hole(&es)) goto add_delayed; +found: /* * Delayed extent could be allocated by fallocate. * So we need to check it. @@ -1804,6 +1805,26 @@ static int ext4_da_map_blocks(struct inode *inode, sector_t iblock, add_delayed: down_write(&EXT4_I(inode)->i_data_sem); + /* + * Page fault path (ext4_page_mkwrite does not take i_rwsem) + * and fallocate path (no folio lock) can race. Make sure we + * lookup the extent status tree here again while i_data_sem + * is held in write mode, before inserting a new da entry in + * the extent status tree. + */ + if (ext4_es_lookup_extent(inode, iblock, NULL, &es)) { + if (!ext4_es_is_hole(&es)) { + up_write(&EXT4_I(inode)->i_data_sem); + goto found; + } + } else if (!ext4_has_inline_data(inode)) { + retval = ext4_map_query_blocks(NULL, inode, map); + if (retval) { + up_write(&EXT4_I(inode)->i_data_sem); + return retval; + } + } + retval = ext4_insert_delayed_block(inode, map->m_lblk); up_write(&EXT4_I(inode)->i_data_sem); if (retval) From 79ec4cde1d8a6128382aa9d94a5ec83cbc4b3708 Mon Sep 17 00:00:00 2001 From: Michael Tretter Date: Wed, 25 Aug 2021 17:03:10 +0200 Subject: [PATCH 210/342] soc: xilinx: move PM_INIT_FINALIZE to zynqmp_pm_domains driver [ Upstream commit 7fd890b89dea55eb5866640eb8befad26d558161 ] PM_INIT_FINALIZE tells the PMU FW that Linux is able to handle the power management nodes that are provided by the PMU FW. Nodes that are not requested are shut down after this call. Calling PM_INIT_FINALIZE from the zynqmp_power driver is wrong. The PM node request mechanism is implemented in the zynqmp_pm_domains driver, which must also call PM_INIT_FINALIZE. Due to the behavior of the PMU FW, all devices must be powered up before PM_INIT_FINALIZE is called, because otherwise the devices might misbehave. Calling PM_INIT_FINALIZE from the sync_state device callback ensures that all users probed successfully before the PMU FW is allowed to power off unused domains. Signed-off-by: Michael Tretter Acked-by: Michal Simek Acked-by: Rajan Vaja Link: https://lore.kernel.org/r/20210825150313.4033156-2-m.tretter@pengutronix.de Signed-off-by: Michal Simek Stable-dep-of: 9b003e14801c ("drivers: soc: xilinx: check return status of get_api_version()") Signed-off-by: Sasha Levin --- drivers/soc/xilinx/zynqmp_pm_domains.c | 16 ++++++++++++++++ drivers/soc/xilinx/zynqmp_power.c | 1 - 2 files changed, 16 insertions(+), 1 deletion(-) diff --git a/drivers/soc/xilinx/zynqmp_pm_domains.c b/drivers/soc/xilinx/zynqmp_pm_domains.c index 226d343f0a6a..81e8e10f1092 100644 --- a/drivers/soc/xilinx/zynqmp_pm_domains.c +++ b/drivers/soc/xilinx/zynqmp_pm_domains.c @@ -152,11 +152,17 @@ static int zynqmp_gpd_power_off(struct generic_pm_domain *domain) static int zynqmp_gpd_attach_dev(struct generic_pm_domain *domain, struct device *dev) { + struct device_link *link; int ret; struct zynqmp_pm_domain *pd; pd = container_of(domain, struct zynqmp_pm_domain, gpd); + link = device_link_add(dev, &domain->dev, DL_FLAG_SYNC_STATE_ONLY); + if (!link) + dev_dbg(&domain->dev, "failed to create device link for %s\n", + dev_name(dev)); + /* If this is not the first device to attach there is nothing to do */ if (domain->device_count) return 0; @@ -299,9 +305,19 @@ static int zynqmp_gpd_remove(struct platform_device *pdev) return 0; } +static void zynqmp_gpd_sync_state(struct device *dev) +{ + int ret; + + ret = zynqmp_pm_init_finalize(); + if (ret) + dev_warn(dev, "failed to release power management to firmware\n"); +} + static struct platform_driver zynqmp_power_domain_driver = { .driver = { .name = "zynqmp_power_controller", + .sync_state = zynqmp_gpd_sync_state, }, .probe = zynqmp_gpd_probe, .remove = zynqmp_gpd_remove, diff --git a/drivers/soc/xilinx/zynqmp_power.c b/drivers/soc/xilinx/zynqmp_power.c index c556623dae02..f8c301984d4f 100644 --- a/drivers/soc/xilinx/zynqmp_power.c +++ b/drivers/soc/xilinx/zynqmp_power.c @@ -178,7 +178,6 @@ static int zynqmp_pm_probe(struct platform_device *pdev) u32 pm_api_version; struct mbox_client *client; - zynqmp_pm_init_finalize(); zynqmp_pm_get_api_version(&pm_api_version); /* Check PM API version number */ From 6bb9cc6e25942b13ebe1e2241b3c5b6317031793 Mon Sep 17 00:00:00 2001 From: Jay Buddhabhatti Date: Wed, 15 May 2024 04:23:45 -0700 Subject: [PATCH 211/342] drivers: soc: xilinx: check return status of get_api_version() [ Upstream commit 9b003e14801cf85a8cebeddc87bc9fc77100fdce ] Currently return status is not getting checked for get_api_version and because of that for x86 arch we are getting below smatch error. CC drivers/soc/xilinx/zynqmp_power.o drivers/soc/xilinx/zynqmp_power.c: In function 'zynqmp_pm_probe': drivers/soc/xilinx/zynqmp_power.c:295:12: warning: 'pm_api_version' is used uninitialized [-Wuninitialized] 295 | if (pm_api_version < ZYNQMP_PM_VERSION) | ^ CHECK drivers/soc/xilinx/zynqmp_power.c drivers/soc/xilinx/zynqmp_power.c:295 zynqmp_pm_probe() error: uninitialized symbol 'pm_api_version'. So, check return status of pm_get_api_version and return error in case of failure to avoid checking uninitialized pm_api_version variable. Fixes: b9b3a8be28b3 ("firmware: xilinx: Remove eemi ops for get_api_version") Signed-off-by: Jay Buddhabhatti Cc: stable@vger.kernel.org Link: https://lore.kernel.org/r/20240515112345.24673-1-jay.buddhabhatti@amd.com Signed-off-by: Michal Simek Signed-off-by: Sasha Levin --- drivers/soc/xilinx/zynqmp_power.c | 4 +++- 1 file changed, 3 insertions(+), 1 deletion(-) diff --git a/drivers/soc/xilinx/zynqmp_power.c b/drivers/soc/xilinx/zynqmp_power.c index f8c301984d4f..2653d29ba829 100644 --- a/drivers/soc/xilinx/zynqmp_power.c +++ b/drivers/soc/xilinx/zynqmp_power.c @@ -178,7 +178,9 @@ static int zynqmp_pm_probe(struct platform_device *pdev) u32 pm_api_version; struct mbox_client *client; - zynqmp_pm_get_api_version(&pm_api_version); + ret = zynqmp_pm_get_api_version(&pm_api_version); + if (ret) + return ret; /* Check PM API version number */ if (pm_api_version < ZYNQMP_PM_VERSION) From 81484ab2858b2a929499d4baa79336e74954f82e Mon Sep 17 00:00:00 2001 From: Andy Shevchenko Date: Thu, 1 Apr 2021 20:10:30 +0300 Subject: [PATCH 212/342] driver core: Cast to (void *) with __force for __percpu pointer [ Upstream commit d7aa44f5a1f86cb40659eef06035d8d92604b9d5 ] Sparse is not happy: drivers/base/devres.c:1230:9: warning: cast removes address space '__percpu' of expression Use __force attribute to make it happy. Signed-off-by: Andy Shevchenko Link: https://lore.kernel.org/r/20210401171030.60527-1-andriy.shevchenko@linux.intel.com Signed-off-by: Greg Kroah-Hartman Stable-dep-of: bd50a974097b ("devres: Fix memory leakage caused by driver API devm_free_percpu()") Signed-off-by: Sasha Levin --- drivers/base/devres.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/drivers/base/devres.c b/drivers/base/devres.c index 452541ce0dc8..a1508eeb8ebd 100644 --- a/drivers/base/devres.c +++ b/drivers/base/devres.c @@ -1231,6 +1231,6 @@ EXPORT_SYMBOL_GPL(__devm_alloc_percpu); void devm_free_percpu(struct device *dev, void __percpu *pdata) { WARN_ON(devres_destroy(dev, devm_percpu_release, devm_percpu_match, - (void *)pdata)); + (__force void *)pdata)); } EXPORT_SYMBOL_GPL(devm_free_percpu); From ef56dcdca8f2a53abc3a83d388b8336447533d85 Mon Sep 17 00:00:00 2001 From: Zijun Hu Date: Tue, 2 Jul 2024 22:51:51 +0800 Subject: [PATCH 213/342] devres: Fix memory leakage caused by driver API devm_free_percpu() [ Upstream commit bd50a974097bb82d52a458bd3ee39fb723129a0c ] It will cause memory leakage when use driver API devm_free_percpu() to free memory allocated by devm_alloc_percpu(), fixed by using devres_release() instead of devres_destroy() within devm_free_percpu(). Fixes: ff86aae3b411 ("devres: add devm_alloc_percpu()") Cc: stable@vger.kernel.org Signed-off-by: Zijun Hu Link: https://lore.kernel.org/r/1719931914-19035-3-git-send-email-quic_zijuhu@quicinc.com Signed-off-by: Greg Kroah-Hartman Signed-off-by: Sasha Levin --- drivers/base/devres.c | 6 +++++- 1 file changed, 5 insertions(+), 1 deletion(-) diff --git a/drivers/base/devres.c b/drivers/base/devres.c index a1508eeb8ebd..8a74008c13c4 100644 --- a/drivers/base/devres.c +++ b/drivers/base/devres.c @@ -1230,7 +1230,11 @@ EXPORT_SYMBOL_GPL(__devm_alloc_percpu); */ void devm_free_percpu(struct device *dev, void __percpu *pdata) { - WARN_ON(devres_destroy(dev, devm_percpu_release, devm_percpu_match, + /* + * Use devres_release() to prevent memory leakage as + * devm_free_pages() does. + */ + WARN_ON(devres_release(dev, devm_percpu_release, devm_percpu_match, (__force void *)pdata)); } EXPORT_SYMBOL_GPL(devm_free_percpu); From 652e7b4d730067934b544e4d74cd574813045e37 Mon Sep 17 00:00:00 2001 From: Marc Zyngier Date: Tue, 1 Feb 2022 12:02:59 +0000 Subject: [PATCH 214/342] genirq: Allow the PM device to originate from irq domain [ Upstream commit 1f8863bfb5ca500ea1c7669b16b1931ba27fce20 ] As a preparation to moving the reference to the device used for runtime power management, add a new 'dev' field to the irqdomain structure for that exact purpose. The irq_chip_pm_{get,put}() helpers are made aware of the dual location via a new private helper. No functional change intended. Signed-off-by: Marc Zyngier Reviewed-by: Geert Uytterhoeven Tested-by: Geert Uytterhoeven Tested-by: Tony Lindgren Acked-by: Bartosz Golaszewski Link: https://lore.kernel.org/r/20220201120310.878267-2-maz@kernel.org Stable-dep-of: 33b1c47d1fc0 ("irqchip/imx-irqsteer: Handle runtime power management correctly") Signed-off-by: Sasha Levin --- include/linux/irqdomain.h | 10 ++++++++++ kernel/irq/chip.c | 23 ++++++++++++++++++----- 2 files changed, 28 insertions(+), 5 deletions(-) diff --git a/include/linux/irqdomain.h b/include/linux/irqdomain.h index 9b9743f7538c..60f53eadfa42 100644 --- a/include/linux/irqdomain.h +++ b/include/linux/irqdomain.h @@ -149,6 +149,8 @@ struct irq_domain_chip_generic; * @gc: Pointer to a list of generic chips. There is a helper function for * setting up one or more generic chips for interrupt controllers * drivers using the generic chip library which uses this pointer. + * @dev: Pointer to a device that the domain represent, and that will be + * used for power management purposes. * @parent: Pointer to parent irq_domain to support hierarchy irq_domains * @debugfs_file: dentry for the domain debugfs file * @@ -171,6 +173,7 @@ struct irq_domain { struct fwnode_handle *fwnode; enum irq_domain_bus_token bus_token; struct irq_domain_chip_generic *gc; + struct device *dev; #ifdef CONFIG_IRQ_DOMAIN_HIERARCHY struct irq_domain *parent; #endif @@ -227,6 +230,13 @@ static inline struct device_node *irq_domain_get_of_node(struct irq_domain *d) return to_of_node(d->fwnode); } +static inline void irq_domain_set_pm_device(struct irq_domain *d, + struct device *dev) +{ + if (d) + d->dev = dev; +} + #ifdef CONFIG_IRQ_DOMAIN struct fwnode_handle *__irq_domain_alloc_fwnode(unsigned int type, int id, const char *name, phys_addr_t *pa); diff --git a/kernel/irq/chip.c b/kernel/irq/chip.c index e7d284261d45..b8aa9e22105f 100644 --- a/kernel/irq/chip.c +++ b/kernel/irq/chip.c @@ -1586,6 +1586,17 @@ int irq_chip_compose_msi_msg(struct irq_data *data, struct msi_msg *msg) return 0; } +static struct device *irq_get_parent_device(struct irq_data *data) +{ + if (data->chip->parent_device) + return data->chip->parent_device; + + if (data->domain) + return data->domain->dev; + + return NULL; +} + /** * irq_chip_pm_get - Enable power for an IRQ chip * @data: Pointer to interrupt specific data @@ -1595,12 +1606,13 @@ int irq_chip_compose_msi_msg(struct irq_data *data, struct msi_msg *msg) */ int irq_chip_pm_get(struct irq_data *data) { + struct device *dev = irq_get_parent_device(data); int retval; - if (IS_ENABLED(CONFIG_PM) && data->chip->parent_device) { - retval = pm_runtime_get_sync(data->chip->parent_device); + if (IS_ENABLED(CONFIG_PM) && dev) { + retval = pm_runtime_get_sync(dev); if (retval < 0) { - pm_runtime_put_noidle(data->chip->parent_device); + pm_runtime_put_noidle(dev); return retval; } } @@ -1618,10 +1630,11 @@ int irq_chip_pm_get(struct irq_data *data) */ int irq_chip_pm_put(struct irq_data *data) { + struct device *dev = irq_get_parent_device(data); int retval = 0; - if (IS_ENABLED(CONFIG_PM) && data->chip->parent_device) - retval = pm_runtime_put(data->chip->parent_device); + if (IS_ENABLED(CONFIG_PM) && dev) + retval = pm_runtime_put(dev); return (retval < 0) ? retval : 0; } From 06a93b720351d7fc5b11f39fd4a91bc9197e79ee Mon Sep 17 00:00:00 2001 From: Lucas Stach Date: Wed, 6 Apr 2022 18:37:00 +0200 Subject: [PATCH 215/342] irqchip/imx-irqsteer: Constify irq_chip struct [ Upstream commit e9a50f12e579a48e124ac5adb93dafc35f0a46b8 ] The imx_irqsteer_irq_chip struct is constant data. Signed-off-by: Lucas Stach Signed-off-by: Marc Zyngier Link: https://lore.kernel.org/r/20220406163701.1277930-1-l.stach@pengutronix.de Stable-dep-of: 33b1c47d1fc0 ("irqchip/imx-irqsteer: Handle runtime power management correctly") Signed-off-by: Sasha Levin --- drivers/irqchip/irq-imx-irqsteer.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/drivers/irqchip/irq-imx-irqsteer.c b/drivers/irqchip/irq-imx-irqsteer.c index 1edf7692a790..c9998b46414c 100644 --- a/drivers/irqchip/irq-imx-irqsteer.c +++ b/drivers/irqchip/irq-imx-irqsteer.c @@ -70,7 +70,7 @@ static void imx_irqsteer_irq_mask(struct irq_data *d) raw_spin_unlock_irqrestore(&data->lock, flags); } -static struct irq_chip imx_irqsteer_irq_chip = { +static const struct irq_chip imx_irqsteer_irq_chip = { .name = "irqsteer", .irq_mask = imx_irqsteer_irq_mask, .irq_unmask = imx_irqsteer_irq_unmask, From 0548b54d0a26a60e159f0d550b09987630fb8846 Mon Sep 17 00:00:00 2001 From: Lucas Stach Date: Wed, 6 Apr 2022 18:37:01 +0200 Subject: [PATCH 216/342] irqchip/imx-irqsteer: Add runtime PM support [ Upstream commit 4730d2233311d86cad9dc510318d1b40e4b53cf2 ] There are now SoCs that integrate the irqsteer controller within a separate power domain. In order to allow this domain to be powered down when not needed, add runtime PM support to the driver. Signed-off-by: Lucas Stach Signed-off-by: Marc Zyngier Link: https://lore.kernel.org/r/20220406163701.1277930-2-l.stach@pengutronix.de Stable-dep-of: 33b1c47d1fc0 ("irqchip/imx-irqsteer: Handle runtime power management correctly") Signed-off-by: Sasha Levin --- drivers/irqchip/irq-imx-irqsteer.c | 14 +++++++++++--- 1 file changed, 11 insertions(+), 3 deletions(-) diff --git a/drivers/irqchip/irq-imx-irqsteer.c b/drivers/irqchip/irq-imx-irqsteer.c index c9998b46414c..b1ecdb08c618 100644 --- a/drivers/irqchip/irq-imx-irqsteer.c +++ b/drivers/irqchip/irq-imx-irqsteer.c @@ -12,6 +12,7 @@ #include #include #include +#include #include #define CTRL_STRIDE_OFF(_t, _r) (_t * 4 * _r) @@ -178,7 +179,7 @@ static int imx_irqsteer_probe(struct platform_device *pdev) data->irq_count = DIV_ROUND_UP(irqs_num, 64); data->reg_num = irqs_num / 32; - if (IS_ENABLED(CONFIG_PM_SLEEP)) { + if (IS_ENABLED(CONFIG_PM)) { data->saved_reg = devm_kzalloc(&pdev->dev, sizeof(u32) * data->reg_num, GFP_KERNEL); @@ -202,6 +203,7 @@ static int imx_irqsteer_probe(struct platform_device *pdev) ret = -ENOMEM; goto out; } + irq_domain_set_pm_device(data->domain, &pdev->dev); if (!data->irq_count || data->irq_count > CHAN_MAX_OUTPUT_INT) { ret = -EINVAL; @@ -222,6 +224,9 @@ static int imx_irqsteer_probe(struct platform_device *pdev) platform_set_drvdata(pdev, data); + pm_runtime_set_active(&pdev->dev); + pm_runtime_enable(&pdev->dev); + return 0; out: clk_disable_unprepare(data->ipg_clk); @@ -244,7 +249,7 @@ static int imx_irqsteer_remove(struct platform_device *pdev) return 0; } -#ifdef CONFIG_PM_SLEEP +#ifdef CONFIG_PM static void imx_irqsteer_save_regs(struct irqsteer_data *data) { int i; @@ -291,7 +296,10 @@ static int imx_irqsteer_resume(struct device *dev) #endif static const struct dev_pm_ops imx_irqsteer_pm_ops = { - SET_NOIRQ_SYSTEM_SLEEP_PM_OPS(imx_irqsteer_suspend, imx_irqsteer_resume) + SET_NOIRQ_SYSTEM_SLEEP_PM_OPS(pm_runtime_force_suspend, + pm_runtime_force_resume) + SET_RUNTIME_PM_OPS(imx_irqsteer_suspend, + imx_irqsteer_resume, NULL) }; static const struct of_device_id imx_irqsteer_dt_ids[] = { From 3a2884a44e5cda192df1b28e9925661f79f599a1 Mon Sep 17 00:00:00 2001 From: Shenwei Wang Date: Wed, 3 Jul 2024 11:32:50 -0500 Subject: [PATCH 217/342] irqchip/imx-irqsteer: Handle runtime power management correctly [ Upstream commit 33b1c47d1fc0b5f06a393bb915db85baacba18ea ] The power domain is automatically activated from clk_prepare(). However, on certain platforms like i.MX8QM and i.MX8QXP, the power-on handling invokes sleeping functions, which triggers the 'scheduling while atomic' bug in the context switch path during device probing: BUG: scheduling while atomic: kworker/u13:1/48/0x00000002 Call trace: __schedule_bug+0x54/0x6c __schedule+0x7f0/0xa94 schedule+0x5c/0xc4 schedule_preempt_disabled+0x24/0x40 __mutex_lock.constprop.0+0x2c0/0x540 __mutex_lock_slowpath+0x14/0x20 mutex_lock+0x48/0x54 clk_prepare_lock+0x44/0xa0 clk_prepare+0x20/0x44 imx_irqsteer_resume+0x28/0xe0 pm_generic_runtime_resume+0x2c/0x44 __genpd_runtime_resume+0x30/0x80 genpd_runtime_resume+0xc8/0x2c0 __rpm_callback+0x48/0x1d8 rpm_callback+0x6c/0x78 rpm_resume+0x490/0x6b4 __pm_runtime_resume+0x50/0x94 irq_chip_pm_get+0x2c/0xa0 __irq_do_set_handler+0x178/0x24c irq_set_chained_handler_and_data+0x60/0xa4 mxc_gpio_probe+0x160/0x4b0 Cure this by implementing the irq_bus_lock/sync_unlock() interrupt chip callbacks and handle power management in them as they are invoked from non-atomic context. [ tglx: Rewrote change log, added Fixes tag ] Fixes: 0136afa08967 ("irqchip: Add driver for imx-irqsteer controller") Signed-off-by: Shenwei Wang Signed-off-by: Thomas Gleixner Cc: stable@vger.kernel.org Link: https://lore.kernel.org/r/20240703163250.47887-1-shenwei.wang@nxp.com Signed-off-by: Sasha Levin --- drivers/irqchip/irq-imx-irqsteer.c | 24 +++++++++++++++++++++--- 1 file changed, 21 insertions(+), 3 deletions(-) diff --git a/drivers/irqchip/irq-imx-irqsteer.c b/drivers/irqchip/irq-imx-irqsteer.c index b1ecdb08c618..4bdcefa44f11 100644 --- a/drivers/irqchip/irq-imx-irqsteer.c +++ b/drivers/irqchip/irq-imx-irqsteer.c @@ -35,6 +35,7 @@ struct irqsteer_data { int channel; struct irq_domain *domain; u32 *saved_reg; + struct device *dev; }; static int imx_irqsteer_get_reg_index(struct irqsteer_data *data, @@ -71,10 +72,26 @@ static void imx_irqsteer_irq_mask(struct irq_data *d) raw_spin_unlock_irqrestore(&data->lock, flags); } +static void imx_irqsteer_irq_bus_lock(struct irq_data *d) +{ + struct irqsteer_data *data = d->chip_data; + + pm_runtime_get_sync(data->dev); +} + +static void imx_irqsteer_irq_bus_sync_unlock(struct irq_data *d) +{ + struct irqsteer_data *data = d->chip_data; + + pm_runtime_put_autosuspend(data->dev); +} + static const struct irq_chip imx_irqsteer_irq_chip = { - .name = "irqsteer", - .irq_mask = imx_irqsteer_irq_mask, - .irq_unmask = imx_irqsteer_irq_unmask, + .name = "irqsteer", + .irq_mask = imx_irqsteer_irq_mask, + .irq_unmask = imx_irqsteer_irq_unmask, + .irq_bus_lock = imx_irqsteer_irq_bus_lock, + .irq_bus_sync_unlock = imx_irqsteer_irq_bus_sync_unlock, }; static int imx_irqsteer_irq_map(struct irq_domain *h, unsigned int irq, @@ -152,6 +169,7 @@ static int imx_irqsteer_probe(struct platform_device *pdev) if (!data) return -ENOMEM; + data->dev = &pdev->dev; data->regs = devm_platform_ioremap_resource(pdev, 0); if (IS_ERR(data->regs)) { dev_err(&pdev->dev, "failed to initialize reg\n"); From a4ed3286a5c64d046bb3f37ee9b4748c2a3925c8 Mon Sep 17 00:00:00 2001 From: Peng Fan Date: Sat, 6 Mar 2021 19:24:24 +0800 Subject: [PATCH 218/342] remoteproc: imx_rproc: ignore mapping vdev regions [ Upstream commit 8f2d8961640f0346cbe892273c3260a0d30c1931 ] vdev regions are vdev0vring0, vdev0vring1, vdevbuffer and similar. They are handled by remoteproc common code, no need to map in imx rproc driver. Signed-off-by: Peng Fan Reviewed-by: Mathieu Poirier Link: https://lore.kernel.org/r/1615029865-23312-10-git-send-email-peng.fan@oss.nxp.com Signed-off-by: Bjorn Andersson Stable-dep-of: 2fa26ca8b786 ("remoteproc: imx_rproc: Skip over memory region when node value is NULL") Signed-off-by: Sasha Levin --- drivers/remoteproc/imx_rproc.c | 3 +++ 1 file changed, 3 insertions(+) diff --git a/drivers/remoteproc/imx_rproc.c b/drivers/remoteproc/imx_rproc.c index 8957ed271d20..6e233f628920 100644 --- a/drivers/remoteproc/imx_rproc.c +++ b/drivers/remoteproc/imx_rproc.c @@ -287,6 +287,9 @@ static int imx_rproc_addr_init(struct imx_rproc *priv, struct resource res; node = of_parse_phandle(np, "memory-region", a); + /* Not map vdev region */ + if (!strcmp(node->name, "vdev")) + continue; err = of_address_to_resource(node, 0, &res); if (err) { dev_err(dev, "unable to resolve memory region\n"); From 5991ef8e7a9012d81f17b1d291e7105ae925fd2d Mon Sep 17 00:00:00 2001 From: Dong Aisheng Date: Fri, 10 Sep 2021 17:06:19 +0800 Subject: [PATCH 219/342] remoteproc: imx_rproc: Fix ignoring mapping vdev regions [ Upstream commit afe670e23af91d8a74a8d7049f6e0984bbf6ea11 ] vdev regions are typically named vdev0buffer, vdev0ring0, vdev0ring1 and etc. Change to strncmp to cover them all. Fixes: 8f2d8961640f ("remoteproc: imx_rproc: ignore mapping vdev regions") Reviewed-and-tested-by: Peng Fan Signed-off-by: Dong Aisheng Signed-off-by: Peng Fan Cc: stable Link: https://lore.kernel.org/r/20210910090621.3073540-5-peng.fan@oss.nxp.com Signed-off-by: Mathieu Poirier Signed-off-by: Bjorn Andersson Stable-dep-of: 2fa26ca8b786 ("remoteproc: imx_rproc: Skip over memory region when node value is NULL") Signed-off-by: Sasha Levin --- drivers/remoteproc/imx_rproc.c | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-) diff --git a/drivers/remoteproc/imx_rproc.c b/drivers/remoteproc/imx_rproc.c index 6e233f628920..517d1b573328 100644 --- a/drivers/remoteproc/imx_rproc.c +++ b/drivers/remoteproc/imx_rproc.c @@ -287,8 +287,8 @@ static int imx_rproc_addr_init(struct imx_rproc *priv, struct resource res; node = of_parse_phandle(np, "memory-region", a); - /* Not map vdev region */ - if (!strcmp(node->name, "vdev")) + /* Not map vdevbuffer, vdevring region */ + if (!strncmp(node->name, "vdev", strlen("vdev"))) continue; err = of_address_to_resource(node, 0, &res); if (err) { From 6b50462b473fdccdc0dfad73001147e40ff19a66 Mon Sep 17 00:00:00 2001 From: Aleksandr Mishin Date: Thu, 6 Jun 2024 10:52:04 +0300 Subject: [PATCH 220/342] remoteproc: imx_rproc: Skip over memory region when node value is NULL [ Upstream commit 2fa26ca8b786888673689ccc9da6094150939982 ] In imx_rproc_addr_init() "nph = of_count_phandle_with_args()" just counts number of phandles. But phandles may be empty. So of_parse_phandle() in the parsing loop (0 < a < nph) may return NULL which is later dereferenced. Adjust this issue by adding NULL-return check. Found by Linux Verification Center (linuxtesting.org) with SVACE. Fixes: a0ff4aa6f010 ("remoteproc: imx_rproc: add a NXP/Freescale imx_rproc driver") Signed-off-by: Aleksandr Mishin Reviewed-by: Peng Fan Cc: stable@vger.kernel.org Link: https://lore.kernel.org/r/20240606075204.12354-1-amishin@t-argos.ru [Fixed title to fit within the prescribed 70-75 charcters] Signed-off-by: Mathieu Poirier Signed-off-by: Sasha Levin --- drivers/remoteproc/imx_rproc.c | 2 ++ 1 file changed, 2 insertions(+) diff --git a/drivers/remoteproc/imx_rproc.c b/drivers/remoteproc/imx_rproc.c index 517d1b573328..373fce8b9106 100644 --- a/drivers/remoteproc/imx_rproc.c +++ b/drivers/remoteproc/imx_rproc.c @@ -287,6 +287,8 @@ static int imx_rproc_addr_init(struct imx_rproc *priv, struct resource res; node = of_parse_phandle(np, "memory-region", a); + if (!node) + continue; /* Not map vdevbuffer, vdevring region */ if (!strncmp(node->name, "vdev", strlen("vdev"))) continue; From 906372e753c5027a1dc88743843b6aa2ad1aaecf Mon Sep 17 00:00:00 2001 From: Danilo Krummrich Date: Thu, 18 Jul 2024 18:58:46 +0200 Subject: [PATCH 221/342] drm/nouveau: prime: fix refcount underflow MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit [ Upstream commit a9bf3efc33f1fbf88787a277f7349459283c9b95 ] Calling nouveau_bo_ref() on a nouveau_bo without initializing it (and hence the backing ttm_bo) leads to a refcount underflow. Instead of calling nouveau_bo_ref() in the unwind path of drm_gem_object_init(), clean things up manually. Fixes: ab9ccb96a6e6 ("drm/nouveau: use prime helpers") Reviewed-by: Ben Skeggs Reviewed-by: Christian König Signed-off-by: Danilo Krummrich Link: https://patchwork.freedesktop.org/patch/msgid/20240718165959.3983-2-dakr@kernel.org (cherry picked from commit 1b93f3e89d03cfc576636e195466a0d728ad8de5) Signed-off-by: Danilo Krummrich Signed-off-by: Sasha Levin --- drivers/gpu/drm/nouveau/nouveau_prime.c | 3 ++- 1 file changed, 2 insertions(+), 1 deletion(-) diff --git a/drivers/gpu/drm/nouveau/nouveau_prime.c b/drivers/gpu/drm/nouveau/nouveau_prime.c index f08bda533bd9..65874a48dc80 100644 --- a/drivers/gpu/drm/nouveau/nouveau_prime.c +++ b/drivers/gpu/drm/nouveau/nouveau_prime.c @@ -81,7 +81,8 @@ struct drm_gem_object *nouveau_gem_prime_import_sg_table(struct drm_device *dev, * to the caller, instead of a normal nouveau_bo ttm reference. */ ret = drm_gem_object_init(dev, &nvbo->bo.base, size); if (ret) { - nouveau_bo_ref(NULL, &nvbo); + drm_gem_object_release(&nvbo->bo.base); + kfree(nvbo); obj = ERR_PTR(-ENOMEM); goto unlock; } From b17eeed7cd098dcb059e0456e6af3ea955cf6eb2 Mon Sep 17 00:00:00 2001 From: Ian Forbes Date: Fri, 19 Jul 2024 11:36:27 -0500 Subject: [PATCH 222/342] drm/vmwgfx: Fix overlay when using Screen Targets [ Upstream commit cb372a505a994cb39aa75acfb8b3bcf94787cf94 ] This code was never updated to support Screen Targets. Fixes a bug where Xv playback displays a green screen instead of actual video contents when 3D acceleration is disabled in the guest. Fixes: c8261a961ece ("vmwgfx: Major KMS refactoring / cleanup in preparation of screen targets") Reported-by: Doug Brown Closes: https://lore.kernel.org/all/bd9cb3c7-90e8-435d-bc28-0e38fee58977@schmorgal.com Signed-off-by: Ian Forbes Tested-by: Doug Brown Signed-off-by: Zack Rusin Link: https://patchwork.freedesktop.org/patch/msgid/20240719163627.20888-1-ian.forbes@broadcom.com Signed-off-by: Sasha Levin --- drivers/gpu/drm/vmwgfx/vmwgfx_overlay.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/drivers/gpu/drm/vmwgfx/vmwgfx_overlay.c b/drivers/gpu/drm/vmwgfx/vmwgfx_overlay.c index cd7ed1650d60..7aa1d9218ea6 100644 --- a/drivers/gpu/drm/vmwgfx/vmwgfx_overlay.c +++ b/drivers/gpu/drm/vmwgfx/vmwgfx_overlay.c @@ -98,7 +98,7 @@ static int vmw_overlay_send_put(struct vmw_private *dev_priv, { struct vmw_escape_video_flush *flush; size_t fifo_size; - bool have_so = (dev_priv->active_display_unit == vmw_du_screen_object); + bool have_so = (dev_priv->active_display_unit != vmw_du_legacy); int i, num_items; SVGAGuestPtr ptr; From 7c03ab555eb1ba26c77fd7c25bdf44a0ac23edee Mon Sep 17 00:00:00 2001 From: Eric Dumazet Date: Thu, 25 Jul 2024 09:27:45 +0000 Subject: [PATCH 223/342] sched: act_ct: take care of padding in struct zones_ht_key [ Upstream commit 2191a54f63225b548fd8346be3611c3219a24738 ] Blamed commit increased lookup key size from 2 bytes to 16 bytes, because zones_ht_key got a struct net pointer. Make sure rhashtable_lookup() is not using the padding bytes which are not initialized. BUG: KMSAN: uninit-value in rht_ptr_rcu include/linux/rhashtable.h:376 [inline] BUG: KMSAN: uninit-value in __rhashtable_lookup include/linux/rhashtable.h:607 [inline] BUG: KMSAN: uninit-value in rhashtable_lookup include/linux/rhashtable.h:646 [inline] BUG: KMSAN: uninit-value in rhashtable_lookup_fast include/linux/rhashtable.h:672 [inline] BUG: KMSAN: uninit-value in tcf_ct_flow_table_get+0x611/0x2260 net/sched/act_ct.c:329 rht_ptr_rcu include/linux/rhashtable.h:376 [inline] __rhashtable_lookup include/linux/rhashtable.h:607 [inline] rhashtable_lookup include/linux/rhashtable.h:646 [inline] rhashtable_lookup_fast include/linux/rhashtable.h:672 [inline] tcf_ct_flow_table_get+0x611/0x2260 net/sched/act_ct.c:329 tcf_ct_init+0xa67/0x2890 net/sched/act_ct.c:1408 tcf_action_init_1+0x6cc/0xb30 net/sched/act_api.c:1425 tcf_action_init+0x458/0xf00 net/sched/act_api.c:1488 tcf_action_add net/sched/act_api.c:2061 [inline] tc_ctl_action+0x4be/0x19d0 net/sched/act_api.c:2118 rtnetlink_rcv_msg+0x12fc/0x1410 net/core/rtnetlink.c:6647 netlink_rcv_skb+0x375/0x650 net/netlink/af_netlink.c:2550 rtnetlink_rcv+0x34/0x40 net/core/rtnetlink.c:6665 netlink_unicast_kernel net/netlink/af_netlink.c:1331 [inline] netlink_unicast+0xf52/0x1260 net/netlink/af_netlink.c:1357 netlink_sendmsg+0x10da/0x11e0 net/netlink/af_netlink.c:1901 sock_sendmsg_nosec net/socket.c:730 [inline] __sock_sendmsg+0x30f/0x380 net/socket.c:745 ____sys_sendmsg+0x877/0xb60 net/socket.c:2597 ___sys_sendmsg+0x28d/0x3c0 net/socket.c:2651 __sys_sendmsg net/socket.c:2680 [inline] __do_sys_sendmsg net/socket.c:2689 [inline] __se_sys_sendmsg net/socket.c:2687 [inline] __x64_sys_sendmsg+0x307/0x4a0 net/socket.c:2687 x64_sys_call+0x2dd6/0x3c10 arch/x86/include/generated/asm/syscalls_64.h:47 do_syscall_x64 arch/x86/entry/common.c:52 [inline] do_syscall_64+0xcd/0x1e0 arch/x86/entry/common.c:83 entry_SYSCALL_64_after_hwframe+0x77/0x7f Local variable key created at: tcf_ct_flow_table_get+0x4a/0x2260 net/sched/act_ct.c:324 tcf_ct_init+0xa67/0x2890 net/sched/act_ct.c:1408 Fixes: 88c67aeb1407 ("sched: act_ct: add netns into the key of tcf_ct_flow_table") Reported-by: syzbot+1b5e4e187cc586d05ea0@syzkaller.appspotmail.com Signed-off-by: Eric Dumazet Cc: Xin Long Reviewed-by: Simon Horman Reviewed-by: Xin Long Signed-off-by: David S. Miller Signed-off-by: Sasha Levin --- net/sched/act_ct.c | 4 +++- 1 file changed, 3 insertions(+), 1 deletion(-) diff --git a/net/sched/act_ct.c b/net/sched/act_ct.c index a59a8ad38721..4ea7a81707f3 100644 --- a/net/sched/act_ct.c +++ b/net/sched/act_ct.c @@ -41,6 +41,8 @@ static DEFINE_MUTEX(zones_mutex); struct zones_ht_key { struct net *net; u16 zone; + /* Note : pad[] must be the last field. */ + u8 pad[]; }; struct tcf_ct_flow_table { @@ -57,7 +59,7 @@ struct tcf_ct_flow_table { static const struct rhashtable_params zones_params = { .head_offset = offsetof(struct tcf_ct_flow_table, node), .key_offset = offsetof(struct tcf_ct_flow_table, key), - .key_len = sizeof_field(struct tcf_ct_flow_table, key), + .key_len = offsetof(struct zones_ht_key, pad), .automatic_shrinking = true, }; From c65f72eec60a34ace031426e04e9aff8e5f04895 Mon Sep 17 00:00:00 2001 From: Alexandra Winter Date: Mon, 29 Jul 2024 14:28:16 +0200 Subject: [PATCH 224/342] net/iucv: fix use after free in iucv_sock_close() [ Upstream commit f558120cd709682b739207b48cf7479fd9568431 ] iucv_sever_path() is called from process context and from bh context. iucv->path is used as indicator whether somebody else is taking care of severing the path (or it is already removed / never existed). This needs to be done with atomic compare and swap, otherwise there is a small window where iucv_sock_close() will try to work with a path that has already been severed and freed by iucv_callback_connrej() called by iucv_tasklet_fn(). Example: [452744.123844] Call Trace: [452744.123845] ([<0000001e87f03880>] 0x1e87f03880) [452744.123966] [<00000000d593001e>] iucv_path_sever+0x96/0x138 [452744.124330] [<000003ff801ddbca>] iucv_sever_path+0xc2/0xd0 [af_iucv] [452744.124336] [<000003ff801e01b6>] iucv_sock_close+0xa6/0x310 [af_iucv] [452744.124341] [<000003ff801e08cc>] iucv_sock_release+0x3c/0xd0 [af_iucv] [452744.124345] [<00000000d574794e>] __sock_release+0x5e/0xe8 [452744.124815] [<00000000d5747a0c>] sock_close+0x34/0x48 [452744.124820] [<00000000d5421642>] __fput+0xba/0x268 [452744.124826] [<00000000d51b382c>] task_work_run+0xbc/0xf0 [452744.124832] [<00000000d5145710>] do_notify_resume+0x88/0x90 [452744.124841] [<00000000d5978096>] system_call+0xe2/0x2c8 [452744.125319] Last Breaking-Event-Address: [452744.125321] [<00000000d5930018>] iucv_path_sever+0x90/0x138 [452744.125324] [452744.125325] Kernel panic - not syncing: Fatal exception in interrupt Note that bh_lock_sock() is not serializing the tasklet context against process context, because the check for sock_owned_by_user() and corresponding handling is missing. Ideas for a future clean-up patch: A) Correct usage of bh_lock_sock() in tasklet context, as described in Link: https://lore.kernel.org/netdev/1280155406.2899.407.camel@edumazet-laptop/ Re-enqueue, if needed. This may require adding return values to the tasklet functions and thus changes to all users of iucv. B) Change iucv tasklet into worker and use only lock_sock() in af_iucv. Fixes: 7d316b945352 ("af_iucv: remove IUCV-pathes completely") Reviewed-by: Halil Pasic Signed-off-by: Alexandra Winter Link: https://patch.msgid.link/20240729122818.947756-1-wintera@linux.ibm.com Signed-off-by: Paolo Abeni Signed-off-by: Sasha Levin --- net/iucv/af_iucv.c | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-) diff --git a/net/iucv/af_iucv.c b/net/iucv/af_iucv.c index 7c73faa5336c..3d0424e4ae6c 100644 --- a/net/iucv/af_iucv.c +++ b/net/iucv/af_iucv.c @@ -359,8 +359,8 @@ static void iucv_sever_path(struct sock *sk, int with_user_data) struct iucv_sock *iucv = iucv_sk(sk); struct iucv_path *path = iucv->path; - if (iucv->path) { - iucv->path = NULL; + /* Whoever resets the path pointer, must sever and free it. */ + if (xchg(&iucv->path, NULL)) { if (with_user_data) { low_nmcpy(user_data, iucv->src_name); high_nmcpy(user_data, iucv->dst_name); From 8e97cc828d5fc38c5fbb61396f6e53f9f435fb08 Mon Sep 17 00:00:00 2001 From: Shahar Shitrit Date: Tue, 30 Jul 2024 09:16:37 +0300 Subject: [PATCH 225/342] net/mlx5e: Add a check for the return value from mlx5_port_set_eth_ptys [ Upstream commit 3f8e82a020a5c22f9b791f4ac499b8e18007fbda ] Since the documentation for mlx5_toggle_port_link states that it should only be used after setting the port register, we add a check for the return value from mlx5_port_set_eth_ptys to ensure the register was successfully set before calling it. Fixes: 667daedaecd1 ("net/mlx5e: Toggle link only after modifying port parameters") Signed-off-by: Shahar Shitrit Reviewed-by: Carolina Jubran Signed-off-by: Tariq Toukan Reviewed-by: Wojciech Drewek Link: https://patch.msgid.link/20240730061638.1831002-9-tariqt@nvidia.com Signed-off-by: Jakub Kicinski Signed-off-by: Sasha Levin --- drivers/net/ethernet/mellanox/mlx5/core/en_ethtool.c | 7 ++++++- 1 file changed, 6 insertions(+), 1 deletion(-) diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en_ethtool.c b/drivers/net/ethernet/mellanox/mlx5/core/en_ethtool.c index d3817dd07e3d..1fdb42899a9f 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/en_ethtool.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/en_ethtool.c @@ -1155,7 +1155,12 @@ int mlx5e_ethtool_set_link_ksettings(struct mlx5e_priv *priv, if (!an_changes && link_modes == eproto.admin) goto out; - mlx5_port_set_eth_ptys(mdev, an_disable, link_modes, ext); + err = mlx5_port_set_eth_ptys(mdev, an_disable, link_modes, ext); + if (err) { + netdev_err(priv->netdev, "%s: failed to set ptys reg: %d\n", __func__, err); + goto out; + } + mlx5_toggle_port_link(mdev); out: From 7d72f519510949f61c4652d22886ed1fe172e00c Mon Sep 17 00:00:00 2001 From: =?UTF-8?q?Maciej=20=C5=BBenczykowski?= Date: Mon, 29 Jul 2024 17:17:48 -0700 Subject: [PATCH 226/342] ipv6: fix ndisc_is_useropt() handling for PIO MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit [ Upstream commit a46c68debf3be3a477a69ccbf0a1d050df841676 ] The current logic only works if the PIO is between two other ND user options. This fixes it so that the PIO can also be either before or after other ND user options (for example the first or last option in the RA). side note: there's actually Android tests verifying a portion of the old broken behaviour, so: https://android-review.googlesource.com/c/kernel/tests/+/3196704 fixes those up. Cc: Jen Linkova Cc: Lorenzo Colitti Cc: Patrick Rohr Cc: David Ahern Cc: YOSHIFUJI Hideaki / 吉藤英明 Cc: Jakub Kicinski Signed-off-by: Maciej Żenczykowski Fixes: 048c796beb6e ("ipv6: adjust ndisc_is_useropt() to also return true for PIO") Link: https://patch.msgid.link/20240730001748.147636-1-maze@google.com Signed-off-by: Paolo Abeni Signed-off-by: Sasha Levin --- net/ipv6/ndisc.c | 34 ++++++++++++++++++---------------- 1 file changed, 18 insertions(+), 16 deletions(-) diff --git a/net/ipv6/ndisc.c b/net/ipv6/ndisc.c index 14251347c4a5..4f46b0a2e568 100644 --- a/net/ipv6/ndisc.c +++ b/net/ipv6/ndisc.c @@ -226,6 +226,7 @@ struct ndisc_options *ndisc_parse_options(const struct net_device *dev, return NULL; memset(ndopts, 0, sizeof(*ndopts)); while (opt_len) { + bool unknown = false; int l; if (opt_len < sizeof(struct nd_opt_hdr)) return NULL; @@ -261,22 +262,23 @@ struct ndisc_options *ndisc_parse_options(const struct net_device *dev, break; #endif default: - if (ndisc_is_useropt(dev, nd_opt)) { - ndopts->nd_useropts_end = nd_opt; - if (!ndopts->nd_useropts) - ndopts->nd_useropts = nd_opt; - } else { - /* - * Unknown options must be silently ignored, - * to accommodate future extension to the - * protocol. - */ - ND_PRINTK(2, notice, - "%s: ignored unsupported option; type=%d, len=%d\n", - __func__, - nd_opt->nd_opt_type, - nd_opt->nd_opt_len); - } + unknown = true; + } + if (ndisc_is_useropt(dev, nd_opt)) { + ndopts->nd_useropts_end = nd_opt; + if (!ndopts->nd_useropts) + ndopts->nd_useropts = nd_opt; + } else if (unknown) { + /* + * Unknown options must be silently ignored, + * to accommodate future extension to the + * protocol. + */ + ND_PRINTK(2, notice, + "%s: ignored unsupported option; type=%d, len=%d\n", + __func__, + nd_opt->nd_opt_type, + nd_opt->nd_opt_len); } next_opt: opt_len -= l; From 59be4a167782d68e21068a761b90b01fadc09146 Mon Sep 17 00:00:00 2001 From: Zhe Qiao Date: Wed, 31 Jul 2024 16:45:47 +0800 Subject: [PATCH 227/342] riscv/mm: Add handling for VM_FAULT_SIGSEGV in mm_fault_error() [ Upstream commit 0c710050c47d45eb77b28c271cddefc5c785cb40 ] Handle VM_FAULT_SIGSEGV in the page fault path so that we correctly kill the process and we don't BUG() the kernel. Fixes: 07037db5d479 ("RISC-V: Paging and MMU") Signed-off-by: Zhe Qiao Reviewed-by: Alexandre Ghiti Link: https://lore.kernel.org/r/20240731084547.85380-1-qiaozhe@iscas.ac.cn Signed-off-by: Palmer Dabbelt Signed-off-by: Sasha Levin --- arch/riscv/mm/fault.c | 17 +++++++++-------- 1 file changed, 9 insertions(+), 8 deletions(-) diff --git a/arch/riscv/mm/fault.c b/arch/riscv/mm/fault.c index 54b12943cc7b..9bed32089197 100644 --- a/arch/riscv/mm/fault.c +++ b/arch/riscv/mm/fault.c @@ -39,26 +39,27 @@ static inline void no_context(struct pt_regs *regs, unsigned long addr) static inline void mm_fault_error(struct pt_regs *regs, unsigned long addr, vm_fault_t fault) { + if (!user_mode(regs)) { + no_context(regs, addr); + return; + } + if (fault & VM_FAULT_OOM) { /* * We ran out of memory, call the OOM killer, and return the userspace * (which will retry the fault, or kill us if we got oom-killed). */ - if (!user_mode(regs)) { - no_context(regs, addr); - return; - } pagefault_out_of_memory(); return; } else if (fault & VM_FAULT_SIGBUS) { /* Kernel mode? Handle exceptions or die */ - if (!user_mode(regs)) { - no_context(regs, addr); - return; - } do_trap(regs, SIGBUS, BUS_ADRERR, addr); return; + } else if (fault & VM_FAULT_SIGSEGV) { + do_trap(regs, SIGSEGV, SEGV_MAPERR, addr); + return; } + BUG(); } From b12a67976b12f1b365be66fffff62c150591b79d Mon Sep 17 00:00:00 2001 From: Patryk Duda Date: Tue, 30 Jul 2024 10:44:25 +0000 Subject: [PATCH 228/342] platform/chrome: cros_ec_proto: Lock device when updating MKBP version commit df615907f1bf907260af01ccb904d0e9304b5278 upstream. The cros_ec_get_host_command_version_mask() function requires that the caller must have ec_dev->lock mutex before calling it. This requirement was not met and as a result it was possible that two commands were sent to the device at the same time. The problem was observed while using UART backend which doesn't use any additional locks, unlike SPI backend which locks the controller until response is received. Fixes: f74c7557ed0d ("platform/chrome: cros_ec_proto: Update version on GET_NEXT_EVENT failure") Cc: stable@vger.kernel.org Signed-off-by: Patryk Duda Link: https://lore.kernel.org/r/20240730104425.607083-1-patrykd@google.com Signed-off-by: Tzung-Bi Shih Signed-off-by: Greg Kroah-Hartman --- drivers/platform/chrome/cros_ec_proto.c | 2 ++ 1 file changed, 2 insertions(+) diff --git a/drivers/platform/chrome/cros_ec_proto.c b/drivers/platform/chrome/cros_ec_proto.c index 8ffbf92ec1e0..39c41aeb57e4 100644 --- a/drivers/platform/chrome/cros_ec_proto.c +++ b/drivers/platform/chrome/cros_ec_proto.c @@ -780,9 +780,11 @@ int cros_ec_get_next_event(struct cros_ec_device *ec_dev, if (ret == -ENOPROTOOPT) { dev_dbg(ec_dev->dev, "GET_NEXT_EVENT returned invalid version error.\n"); + mutex_lock(&ec_dev->lock); ret = cros_ec_get_host_command_version_mask(ec_dev, EC_CMD_GET_NEXT_EVENT, &ver_mask); + mutex_unlock(&ec_dev->lock); if (ret < 0 || ver_mask == 0) /* * Do not change the MKBP supported version if we can't From e4b2b0306b6bf6b5e481aa75b3c781188c8e3b4f Mon Sep 17 00:00:00 2001 From: Tatsunosuke Tobita Date: Tue, 9 Jul 2024 14:57:28 +0900 Subject: [PATCH 229/342] HID: wacom: Modify pen IDs commit f0d17d696dfce77c9abc830e4ac2d677890a2dad upstream. The pen ID, 0x80842, was not the correct ID for wacom driver to treat. The ID was corrected to 0x8842. Also, 0x4200 was not the expected ID used on any Wacom device. Therefore, 0x4200 was removed. Signed-off-by: Tatsunosuke Tobita Signed-off-by: Tatsunosuke Tobita Fixes: bfdc750c4cb2 ("HID: wacom: add three styli to wacom_intuos_get_tool_type") Cc: stable@kernel.org #6.2 Reviewed-by: Ping Cheng Link: https://patch.msgid.link/20240709055729.17158-1-tatsunosuke.wacom@gmail.com Signed-off-by: Benjamin Tissoires Signed-off-by: Greg Kroah-Hartman --- drivers/hid/wacom_wac.c | 3 +-- 1 file changed, 1 insertion(+), 2 deletions(-) diff --git a/drivers/hid/wacom_wac.c b/drivers/hid/wacom_wac.c index c454768ffb49..f6ee287a892c 100644 --- a/drivers/hid/wacom_wac.c +++ b/drivers/hid/wacom_wac.c @@ -714,13 +714,12 @@ static int wacom_intuos_get_tool_type(int tool_id) case 0x8e2: /* IntuosHT2 pen */ case 0x022: case 0x200: /* Pro Pen 3 */ - case 0x04200: /* Pro Pen 3 */ case 0x10842: /* MobileStudio Pro Pro Pen slim */ case 0x14802: /* Intuos4/5 13HD/24HD Classic Pen */ case 0x16802: /* Cintiq 13HD Pro Pen */ case 0x18802: /* DTH2242 Pen */ case 0x10802: /* Intuos4/5 13HD/24HD General Pen */ - case 0x80842: /* Intuos Pro and Cintiq Pro 3D Pen */ + case 0x8842: /* Intuos Pro and Cintiq Pro 3D Pen */ tool_type = BTN_TOOL_PEN; break; From 08775b3d6ed117cf4518754ec7300ee42b6a5368 Mon Sep 17 00:00:00 2001 From: Al Viro Date: Thu, 1 Aug 2024 15:22:22 -0400 Subject: [PATCH 230/342] protect the fetch of ->fd[fd] in do_dup2() from mispredictions commit 8aa37bde1a7b645816cda8b80df4753ecf172bf1 upstream. both callers have verified that fd is not greater than ->max_fds; however, misprediction might end up with tofree = fdt->fd[fd]; being speculatively executed. That's wrong for the same reasons why it's wrong in close_fd()/file_close_fd_locked(); the same solution applies - array_index_nospec(fd, fdt->max_fds) could differ from fd only in case of speculative execution on mispredicted path. Cc: stable@vger.kernel.org Signed-off-by: Al Viro Signed-off-by: Greg Kroah-Hartman --- fs/file.c | 1 + 1 file changed, 1 insertion(+) diff --git a/fs/file.c b/fs/file.c index 913f7d897d2f..105a084b7924 100644 --- a/fs/file.c +++ b/fs/file.c @@ -1057,6 +1057,7 @@ __releases(&files->file_lock) * tables and this condition does not arise without those. */ fdt = files_fdtable(files); + fd = array_index_nospec(fd, fdt->max_fds); tofree = fdt->fd[fd]; if (!tofree && fd_is_open(fd, fdt)) goto Ebusy; From 7b745257ff392d4846dc6842704fb9d9507331bd Mon Sep 17 00:00:00 2001 From: Takashi Iwai Date: Wed, 31 Jul 2024 16:19:41 +0200 Subject: [PATCH 231/342] ALSA: usb-audio: Correct surround channels in UAC1 channel map commit b7b7e1ab7619deb3b299b5e5c619c3e6f183a12d upstream. USB-audio driver puts SNDRV_CHMAP_SL and _SR as left and right surround channels for UAC1 channel map, respectively. But they should have been SNDRV_CHMAP_RL and _RR; the current value *_SL and _SR are rather "side" channels, not "surround". I guess I took those mistakenly when I read the spec mentioning "surround left". This patch corrects those entries to be the right channels. Suggested-by: Sylvain BERTRAND Closes: https://lore.kernel.orgZ/qIyJD8lhd8hFhlC@freedom Fixes: 04324ccc75f9 ("ALSA: usb-audio: add channel map support") Cc: Link: https://patch.msgid.link/20240731142018.24750-1-tiwai@suse.de Signed-off-by: Takashi Iwai Signed-off-by: Greg Kroah-Hartman --- sound/usb/stream.c | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-) diff --git a/sound/usb/stream.c b/sound/usb/stream.c index f51e901a9689..0c77f244e5d6 100644 --- a/sound/usb/stream.c +++ b/sound/usb/stream.c @@ -245,8 +245,8 @@ static struct snd_pcm_chmap_elem *convert_chmap(int channels, unsigned int bits, SNDRV_CHMAP_FR, /* right front */ SNDRV_CHMAP_FC, /* center front */ SNDRV_CHMAP_LFE, /* LFE */ - SNDRV_CHMAP_SL, /* left surround */ - SNDRV_CHMAP_SR, /* right surround */ + SNDRV_CHMAP_RL, /* left surround */ + SNDRV_CHMAP_RR, /* right surround */ SNDRV_CHMAP_FLC, /* left of center */ SNDRV_CHMAP_FRC, /* right of center */ SNDRV_CHMAP_RC, /* surround */ From 8b0a5709ac6e40152ce9a1d3be69ae41b427a514 Mon Sep 17 00:00:00 2001 From: Mavroudis Chatzilazaridis Date: Sun, 28 Jul 2024 12:36:04 +0000 Subject: [PATCH 232/342] ALSA: hda/realtek: Add quirk for Acer Aspire E5-574G commit 3c0b6f924e1259ade38587ea719b693f6f6f2f3e upstream. ALC255_FIXUP_ACER_LIMIT_INT_MIC_BOOST fixes combo jack detection and limits the internal microphone boost that causes clipping on this model. Signed-off-by: Mavroudis Chatzilazaridis Cc: Link: https://patch.msgid.link/20240728123601.144017-1-mavchatz@protonmail.com Signed-off-by: Takashi Iwai Signed-off-by: Greg Kroah-Hartman --- sound/pci/hda/patch_realtek.c | 1 + 1 file changed, 1 insertion(+) diff --git a/sound/pci/hda/patch_realtek.c b/sound/pci/hda/patch_realtek.c index 28dbe8cbbffd..e8e9cfb4a935 100644 --- a/sound/pci/hda/patch_realtek.c +++ b/sound/pci/hda/patch_realtek.c @@ -8893,6 +8893,7 @@ static const struct snd_pci_quirk alc269_fixup_tbl[] = { SND_PCI_QUIRK(0x1025, 0x079b, "Acer Aspire V5-573G", ALC282_FIXUP_ASPIRE_V5_PINS), SND_PCI_QUIRK(0x1025, 0x080d, "Acer Aspire V5-122P", ALC269_FIXUP_ASPIRE_HEADSET_MIC), SND_PCI_QUIRK(0x1025, 0x0840, "Acer Aspire E1", ALC269VB_FIXUP_ASPIRE_E1_COEF), + SND_PCI_QUIRK(0x1025, 0x100c, "Acer Aspire E5-574G", ALC255_FIXUP_ACER_LIMIT_INT_MIC_BOOST), SND_PCI_QUIRK(0x1025, 0x101c, "Acer Veriton N2510G", ALC269_FIXUP_LIFEBOOK), SND_PCI_QUIRK(0x1025, 0x102b, "Acer Aspire C24-860", ALC286_FIXUP_ACER_AIO_MIC_NO_PRESENCE), SND_PCI_QUIRK(0x1025, 0x1065, "Acer Aspire C20-820", ALC269VC_FIXUP_ACER_HEADSET_MIC), From 646e9e907138f26608c4ae4828f1856d9b2d4f75 Mon Sep 17 00:00:00 2001 From: Ma Ke Date: Thu, 25 Jul 2024 10:29:42 +0800 Subject: [PATCH 233/342] net: usb: sr9700: fix uninitialized variable use in sr_mdio_read commit 08f3a5c38087d1569e982a121aad1e6acbf145ce upstream. It could lead to error happen because the variable res is not updated if the call to sr_share_read_word returns an error. In this particular case error code was returned and res stayed uninitialized. Same issue also applies to sr_read_reg. This can be avoided by checking the return value of sr_share_read_word and sr_read_reg, and propagating the error if the read operation failed. Found by code review. Cc: stable@vger.kernel.org Fixes: c9b37458e956 ("USB2NET : SR9700 : One chip USB 1.1 USB2NET SR9700Device Driver Support") Signed-off-by: Ma Ke Reviewed-by: Shigeru Yoshida Reviewed-by: Hariprasad Kelam Signed-off-by: David S. Miller Signed-off-by: Greg Kroah-Hartman --- drivers/net/usb/sr9700.c | 11 +++++++++-- 1 file changed, 9 insertions(+), 2 deletions(-) diff --git a/drivers/net/usb/sr9700.c b/drivers/net/usb/sr9700.c index 3fac642bec77..8d2e3daf03cf 100644 --- a/drivers/net/usb/sr9700.c +++ b/drivers/net/usb/sr9700.c @@ -178,6 +178,7 @@ static int sr_mdio_read(struct net_device *netdev, int phy_id, int loc) struct usbnet *dev = netdev_priv(netdev); __le16 res; int rc = 0; + int err; if (phy_id) { netdev_dbg(netdev, "Only internal phy supported\n"); @@ -188,11 +189,17 @@ static int sr_mdio_read(struct net_device *netdev, int phy_id, int loc) if (loc == MII_BMSR) { u8 value; - sr_read_reg(dev, SR_NSR, &value); + err = sr_read_reg(dev, SR_NSR, &value); + if (err < 0) + return err; + if (value & NSR_LINKST) rc = 1; } - sr_share_read_word(dev, 1, loc, &res); + err = sr_share_read_word(dev, 1, loc, &res); + if (err < 0) + return err; + if (rc == 1) res = le16_to_cpu(res) | BMSR_LSTATUS; else From 3deac6f6860da921a583c48d70b32e98ad07cb90 Mon Sep 17 00:00:00 2001 From: Heiner Kallweit Date: Tue, 30 Jul 2024 21:51:52 +0200 Subject: [PATCH 234/342] r8169: don't increment tx_dropped in case of NETDEV_TX_BUSY commit d516b187a9cc2e842030dd005be2735db3e8f395 upstream. The skb isn't consumed in case of NETDEV_TX_BUSY, therefore don't increment the tx_dropped counter. Fixes: 188f4af04618 ("r8169: use NETDEV_TX_{BUSY/OK}") Cc: stable@vger.kernel.org Suggested-by: Jakub Kicinski Signed-off-by: Heiner Kallweit Reviewed-by: Wojciech Drewek Link: https://patch.msgid.link/bbba9c48-8bac-4932-9aa1-d2ed63bc9433@gmail.com Signed-off-by: Jakub Kicinski Signed-off-by: Greg Kroah-Hartman --- drivers/net/ethernet/realtek/r8169_main.c | 8 ++------ 1 file changed, 2 insertions(+), 6 deletions(-) diff --git a/drivers/net/ethernet/realtek/r8169_main.c b/drivers/net/ethernet/realtek/r8169_main.c index d24eb5ee152a..4c588fc43eb9 100644 --- a/drivers/net/ethernet/realtek/r8169_main.c +++ b/drivers/net/ethernet/realtek/r8169_main.c @@ -4288,7 +4288,8 @@ static netdev_tx_t rtl8169_start_xmit(struct sk_buff *skb, if (unlikely(!rtl_tx_slots_avail(tp))) { if (net_ratelimit()) netdev_err(dev, "BUG! Tx Ring full when queue awake!\n"); - goto err_stop_0; + netif_stop_queue(dev); + return NETDEV_TX_BUSY; } opts[1] = rtl8169_tx_vlan_tag(skb); @@ -4361,11 +4362,6 @@ static netdev_tx_t rtl8169_start_xmit(struct sk_buff *skb, dev_kfree_skb_any(skb); dev->stats.tx_dropped++; return NETDEV_TX_OK; - -err_stop_0: - netif_stop_queue(dev); - dev->stats.tx_dropped++; - return NETDEV_TX_BUSY; } static unsigned int rtl_last_frag_len(struct sk_buff *skb) From e93fa44f07149843b39f1ea63d72ec1253783df6 Mon Sep 17 00:00:00 2001 From: Paolo Abeni Date: Wed, 31 Jul 2024 12:10:15 +0200 Subject: [PATCH 235/342] mptcp: fix duplicate data handling commit 68cc924729ffcfe90d0383177192030a9aeb2ee4 upstream. When a subflow receives and discards duplicate data, the mptcp stack assumes that the consumed offset inside the current skb is zero. With multiple subflows receiving data simultaneously such assertion does not held true. As a result the subflow-level copied_seq will be incorrectly increased and later on the same subflow will observe a bad mapping, leading to subflow reset. Address the issue taking into account the skb consumed offset in mptcp_subflow_discard_data(). Fixes: 04e4cd4f7ca4 ("mptcp: cleanup mptcp_subflow_discard_data()") Cc: stable@vger.kernel.org Link: https://github.com/multipath-tcp/mptcp_net-next/issues/501 Signed-off-by: Paolo Abeni Reviewed-by: Mat Martineau Signed-off-by: Matthieu Baerts (NGI0) Signed-off-by: Paolo Abeni Signed-off-by: Greg Kroah-Hartman --- net/mptcp/subflow.c | 16 ++++++++++++---- 1 file changed, 12 insertions(+), 4 deletions(-) diff --git a/net/mptcp/subflow.c b/net/mptcp/subflow.c index 276fe9f44df7..823a92b21c6c 100644 --- a/net/mptcp/subflow.c +++ b/net/mptcp/subflow.c @@ -863,14 +863,22 @@ static void mptcp_subflow_discard_data(struct sock *ssk, struct sk_buff *skb, { struct mptcp_subflow_context *subflow = mptcp_subflow_ctx(ssk); bool fin = TCP_SKB_CB(skb)->tcp_flags & TCPHDR_FIN; - u32 incr; + struct tcp_sock *tp = tcp_sk(ssk); + u32 offset, incr, avail_len; - incr = limit >= skb->len ? skb->len + fin : limit; + offset = tp->copied_seq - TCP_SKB_CB(skb)->seq; + if (WARN_ON_ONCE(offset > skb->len)) + goto out; - pr_debug("discarding=%d len=%d seq=%d", incr, skb->len, - subflow->map_subflow_seq); + avail_len = skb->len - offset; + incr = limit >= avail_len ? avail_len + fin : limit; + + pr_debug("discarding=%d len=%d offset=%d seq=%d", incr, skb->len, + offset, subflow->map_subflow_seq); MPTCP_INC_STATS(sock_net(ssk), MPTCP_MIB_DUPDATA); tcp_sk(ssk)->copied_seq += incr; + +out: if (!before(tcp_sk(ssk)->copied_seq, TCP_SKB_CB(skb)->end_seq)) sk_eat_skb(ssk, skb); if (mptcp_subflow_get_map_offset(subflow) >= subflow->map_data_len) From 12fa9934332dc5e232b9a1373d414d607fb3a6ca Mon Sep 17 00:00:00 2001 From: Alexander Maltsev Date: Wed, 17 Apr 2024 18:51:41 +0500 Subject: [PATCH 236/342] netfilter: ipset: Add list flush to cancel_gc [ Upstream commit c1193d9bbbd379defe9be3c6de566de684de8a6f ] Flushing list in cancel_gc drops references to other lists right away, without waiting for RCU to destroy list. Fixes race when referenced ipsets can't be destroyed while referring list is scheduled for destroy. Fixes: 97f7cf1cd80e ("netfilter: ipset: fix performance regression in swap operation") Signed-off-by: Alexander Maltsev Acked-by: Jozsef Kadlecsik Signed-off-by: Pablo Neira Ayuso Signed-off-by: Sasha Levin --- net/netfilter/ipset/ip_set_list_set.c | 3 +++ 1 file changed, 3 insertions(+) diff --git a/net/netfilter/ipset/ip_set_list_set.c b/net/netfilter/ipset/ip_set_list_set.c index e839c356bcb5..902ff2f3bc72 100644 --- a/net/netfilter/ipset/ip_set_list_set.c +++ b/net/netfilter/ipset/ip_set_list_set.c @@ -547,6 +547,9 @@ list_set_cancel_gc(struct ip_set *set) if (SET_WITH_TIMEOUT(set)) del_timer_sync(&map->gc); + + /* Flush list to drop references to other ipsets */ + list_set_flush(set); } static const struct ip_set_type_variant set_variant = { From c476c5c7bb8d8f6fbd2bf8d62cd188d1fcd95e1a Mon Sep 17 00:00:00 2001 From: Marc Zyngier Date: Wed, 9 Feb 2022 16:25:59 +0000 Subject: [PATCH 237/342] genirq: Allow irq_chip registration functions to take a const irq_chip [ Upstream commit 393e1280f765661cf39785e967676a4e57324126 ] In order to let a const irqchip be fed to the irqchip layer, adjust the various prototypes. An extra cast in irq_set_chip()() is required to avoid a warning. Signed-off-by: Marc Zyngier Acked-by: Linus Walleij Link: https://lore.kernel.org/r/20220209162607.1118325-3-maz@kernel.org Signed-off-by: Sasha Levin --- include/linux/irq.h | 7 ++++--- kernel/irq/chip.c | 9 +++------ 2 files changed, 7 insertions(+), 9 deletions(-) diff --git a/include/linux/irq.h b/include/linux/irq.h index b89a8ac83d1b..eb7af809e6e5 100644 --- a/include/linux/irq.h +++ b/include/linux/irq.h @@ -708,10 +708,11 @@ extern struct irq_chip no_irq_chip; extern struct irq_chip dummy_irq_chip; extern void -irq_set_chip_and_handler_name(unsigned int irq, struct irq_chip *chip, +irq_set_chip_and_handler_name(unsigned int irq, const struct irq_chip *chip, irq_flow_handler_t handle, const char *name); -static inline void irq_set_chip_and_handler(unsigned int irq, struct irq_chip *chip, +static inline void irq_set_chip_and_handler(unsigned int irq, + const struct irq_chip *chip, irq_flow_handler_t handle) { irq_set_chip_and_handler_name(irq, chip, handle, NULL); @@ -801,7 +802,7 @@ static inline void irq_set_percpu_devid_flags(unsigned int irq) } /* Set/get chip/data for an IRQ: */ -extern int irq_set_chip(unsigned int irq, struct irq_chip *chip); +extern int irq_set_chip(unsigned int irq, const struct irq_chip *chip); extern int irq_set_handler_data(unsigned int irq, void *data); extern int irq_set_chip_data(unsigned int irq, void *data); extern int irq_set_irq_type(unsigned int irq, unsigned int type); diff --git a/kernel/irq/chip.c b/kernel/irq/chip.c index b8aa9e22105f..09b91aebb90b 100644 --- a/kernel/irq/chip.c +++ b/kernel/irq/chip.c @@ -38,7 +38,7 @@ struct irqaction chained_action = { * @irq: irq number * @chip: pointer to irq chip description structure */ -int irq_set_chip(unsigned int irq, struct irq_chip *chip) +int irq_set_chip(unsigned int irq, const struct irq_chip *chip) { unsigned long flags; struct irq_desc *desc = irq_get_desc_lock(irq, &flags, 0); @@ -46,10 +46,7 @@ int irq_set_chip(unsigned int irq, struct irq_chip *chip) if (!desc) return -EINVAL; - if (!chip) - chip = &no_irq_chip; - - desc->irq_data.chip = chip; + desc->irq_data.chip = (struct irq_chip *)(chip ?: &no_irq_chip); irq_put_desc_unlock(desc, flags); /* * For !CONFIG_SPARSE_IRQ make the irq show up in @@ -1102,7 +1099,7 @@ irq_set_chained_handler_and_data(unsigned int irq, irq_flow_handler_t handle, EXPORT_SYMBOL_GPL(irq_set_chained_handler_and_data); void -irq_set_chip_and_handler_name(unsigned int irq, struct irq_chip *chip, +irq_set_chip_and_handler_name(unsigned int irq, const struct irq_chip *chip, irq_flow_handler_t handle, const char *name) { irq_set_chip(irq, chip); From 75880302cf3a2758fd5edd2974690f18ca0fa0b0 Mon Sep 17 00:00:00 2001 From: Yipeng Zou Date: Tue, 30 Jul 2024 09:44:00 +0800 Subject: [PATCH 238/342] irqchip/mbigen: Fix mbigen node address layout [ Upstream commit 6be6cba9c4371d27f78d900ccfe34bb880d9ee20 ] The mbigen interrupt chip has its per node registers located in a contiguous region of page sized chunks. The code maps them into virtual address space as a contiguous region and determines the address of a node by using the node ID as index. mbigen chip |-----------------|------------|--------------| mgn_node_0 mgn_node_1 ... mgn_node_i |--------------| |--------------| |----------------------| [0x0000, 0x0x0FFF] [0x1000, 0x1FFF] [i*0x1000, (i+1)*0x1000 - 1] This works correctly up to 10 nodes, but then fails because the 11th's array slot is used for the MGN_CLEAR registers. mbigen chip |-----------|--------|--------|---------------|--------| mgn_node_0 mgn_node_1 ... mgn_clear_register ... mgn_node_i |-----------------| [0xA000, 0xAFFF] Skip the MGN_CLEAR register space when calculating the offset for node IDs greater than or equal to ten. Fixes: a6c2f87b8820 ("irqchip/mbigen: Implement the mbigen irq chip operation functions") Signed-off-by: Yipeng Zou Signed-off-by: Thomas Gleixner Link: https://lore.kernel.org/all/20240730014400.1751530-1-zouyipeng@huawei.com Signed-off-by: Sasha Levin --- drivers/irqchip/irq-mbigen.c | 20 ++++++++++++++++---- 1 file changed, 16 insertions(+), 4 deletions(-) diff --git a/drivers/irqchip/irq-mbigen.c b/drivers/irqchip/irq-mbigen.c index ff7627b57772..192950e9909b 100644 --- a/drivers/irqchip/irq-mbigen.c +++ b/drivers/irqchip/irq-mbigen.c @@ -64,6 +64,20 @@ struct mbigen_device { void __iomem *base; }; +static inline unsigned int get_mbigen_node_offset(unsigned int nid) +{ + unsigned int offset = nid * MBIGEN_NODE_OFFSET; + + /* + * To avoid touched clear register in unexpected way, we need to directly + * skip clear register when access to more than 10 mbigen nodes. + */ + if (nid >= (REG_MBIGEN_CLEAR_OFFSET / MBIGEN_NODE_OFFSET)) + offset += MBIGEN_NODE_OFFSET; + + return offset; +} + static inline unsigned int get_mbigen_vec_reg(irq_hw_number_t hwirq) { unsigned int nid, pin; @@ -72,8 +86,7 @@ static inline unsigned int get_mbigen_vec_reg(irq_hw_number_t hwirq) nid = hwirq / IRQS_PER_MBIGEN_NODE + 1; pin = hwirq % IRQS_PER_MBIGEN_NODE; - return pin * 4 + nid * MBIGEN_NODE_OFFSET - + REG_MBIGEN_VEC_OFFSET; + return pin * 4 + get_mbigen_node_offset(nid) + REG_MBIGEN_VEC_OFFSET; } static inline void get_mbigen_type_reg(irq_hw_number_t hwirq, @@ -88,8 +101,7 @@ static inline void get_mbigen_type_reg(irq_hw_number_t hwirq, *mask = 1 << (irq_ofst % 32); ofst = irq_ofst / 32 * 4; - *addr = ofst + nid * MBIGEN_NODE_OFFSET - + REG_MBIGEN_TYPE_OFFSET; + *addr = ofst + get_mbigen_node_offset(nid) + REG_MBIGEN_TYPE_OFFSET; } static inline void get_mbigen_clear_reg(irq_hw_number_t hwirq, From d00c9b4bbc442d99e1dafbdfdab848bc1ead73f6 Mon Sep 17 00:00:00 2001 From: Peter Zijlstra Date: Wed, 31 Jul 2024 18:31:05 +0200 Subject: [PATCH 239/342] x86/mm: Fix pti_clone_pgtable() alignment assumption [ Upstream commit 41e71dbb0e0a0fe214545fe64af031303a08524c ] Guenter reported dodgy crashes on an i386-nosmp build using GCC-11 that had the form of endless traps until entry stack exhaust and then #DF from the stack guard. It turned out that pti_clone_pgtable() had alignment assumptions on the start address, notably it hard assumes start is PMD aligned. This is true on x86_64, but very much not true on i386. These assumptions can cause the end condition to malfunction, leading to a 'short' clone. Guess what happens when the user mapping has a short copy of the entry text? Use the correct increment form for addr to avoid alignment assumptions. Fixes: 16a3fe634f6a ("x86/mm/pti: Clone kernel-image on PTE level for 32 bit") Reported-by: Guenter Roeck Tested-by: Guenter Roeck Suggested-by: Thomas Gleixner Signed-off-by: Peter Zijlstra (Intel) Link: https://lkml.kernel.org/r/20240731163105.GG33588@noisy.programming.kicks-ass.net Signed-off-by: Sasha Levin --- arch/x86/mm/pti.c | 6 +++--- 1 file changed, 3 insertions(+), 3 deletions(-) diff --git a/arch/x86/mm/pti.c b/arch/x86/mm/pti.c index 1aab92930569..59c13fdb8da0 100644 --- a/arch/x86/mm/pti.c +++ b/arch/x86/mm/pti.c @@ -374,14 +374,14 @@ pti_clone_pgtable(unsigned long start, unsigned long end, */ *target_pmd = *pmd; - addr += PMD_SIZE; + addr = round_up(addr + 1, PMD_SIZE); } else if (level == PTI_CLONE_PTE) { /* Walk the page-table down to the pte level */ pte = pte_offset_kernel(pmd, addr); if (pte_none(*pte)) { - addr += PAGE_SIZE; + addr = round_up(addr + 1, PAGE_SIZE); continue; } @@ -401,7 +401,7 @@ pti_clone_pgtable(unsigned long start, unsigned long end, /* Clone the PTE */ *target_pte = *pte; - addr += PAGE_SIZE; + addr = round_up(addr + 1, PAGE_SIZE); } else { BUG(); From ba4e59f34c648148fbf7532de9d3053d6f04ba92 Mon Sep 17 00:00:00 2001 From: Peter Zijlstra Date: Thu, 1 Aug 2024 12:42:25 +0200 Subject: [PATCH 240/342] x86/mm: Fix pti_clone_entry_text() for i386 [ Upstream commit 3db03fb4995ef85fc41e86262ead7b4852f4bcf0 ] While x86_64 has PMD aligned text sections, i386 does not have this luxery. Notably ALIGN_ENTRY_TEXT_END is empty and _etext has PAGE alignment. This means that text on i386 can be page granular at the tail end, which in turn means that the PTI text clones should consistently account for this. Make pti_clone_entry_text() consistent with pti_clone_kernel_text(). Fixes: 16a3fe634f6a ("x86/mm/pti: Clone kernel-image on PTE level for 32 bit") Signed-off-by: Peter Zijlstra (Intel) Signed-off-by: Sasha Levin --- arch/x86/mm/pti.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/arch/x86/mm/pti.c b/arch/x86/mm/pti.c index 59c13fdb8da0..50e31d14351b 100644 --- a/arch/x86/mm/pti.c +++ b/arch/x86/mm/pti.c @@ -497,7 +497,7 @@ static void pti_clone_entry_text(void) { pti_clone_pgtable((unsigned long) __entry_text_start, (unsigned long) __entry_text_end, - PTI_CLONE_PMD); + PTI_LEVEL_KERNEL_IMAGE); } /* From 17a93a820196da74b30938ba87eeb182f70cf247 Mon Sep 17 00:00:00 2001 From: Xin Long Date: Tue, 21 Dec 2021 16:40:30 -0500 Subject: [PATCH 241/342] sctp: move hlist_node and hashent out of sctp_ep_common [ Upstream commit 3d3b2f57d4447e6e9f4096ad01d0e4129f7bc7e9 ] Struct sctp_ep_common is included in both asoc and ep, but hlist_node and hashent are only needed by ep after asoc_hashtable was dropped by Commit b5eff7128366 ("sctp: drop the old assoc hashtable of sctp"). So it is better to move hlist_node and hashent from sctp_ep_common to sctp_endpoint, and it saves some space for each asoc. Signed-off-by: Xin Long Signed-off-by: David S. Miller Stable-dep-of: 9ab0faa7f9ff ("sctp: Fix null-ptr-deref in reuseport_add_sock().") Signed-off-by: Sasha Levin --- include/net/sctp/sctp.h | 4 ++-- include/net/sctp/structs.h | 8 ++++---- net/sctp/input.c | 27 ++++++++++----------------- net/sctp/proc.c | 10 ++++------ net/sctp/socket.c | 6 +++--- 5 files changed, 23 insertions(+), 32 deletions(-) diff --git a/include/net/sctp/sctp.h b/include/net/sctp/sctp.h index 33475d061823..6d89a7f3f6a4 100644 --- a/include/net/sctp/sctp.h +++ b/include/net/sctp/sctp.h @@ -506,8 +506,8 @@ static inline int sctp_ep_hashfn(struct net *net, __u16 lport) return (net_hash_mix(net) + lport) & (sctp_ep_hashsize - 1); } -#define sctp_for_each_hentry(epb, head) \ - hlist_for_each_entry(epb, head, node) +#define sctp_for_each_hentry(ep, head) \ + hlist_for_each_entry(ep, head, node) /* Is a socket of this style? */ #define sctp_style(sk, style) __sctp_style((sk), (SCTP_SOCKET_##style)) diff --git a/include/net/sctp/structs.h b/include/net/sctp/structs.h index be59e8df0bff..108eb62cdc2c 100644 --- a/include/net/sctp/structs.h +++ b/include/net/sctp/structs.h @@ -1218,10 +1218,6 @@ enum sctp_endpoint_type { */ struct sctp_ep_common { - /* Fields to help us manage our entries in the hash tables. */ - struct hlist_node node; - int hashent; - /* Runtime type information. What kind of endpoint is this? */ enum sctp_endpoint_type type; @@ -1273,6 +1269,10 @@ struct sctp_endpoint { /* Common substructure for endpoint and association. */ struct sctp_ep_common base; + /* Fields to help us manage our entries in the hash tables. */ + struct hlist_node node; + int hashent; + /* Associations: A list of current associations and mappings * to the data consumers for each association. This * may be in the form of a hash table or other diff --git a/net/sctp/input.c b/net/sctp/input.c index 8f3aab6a4458..17df756418ea 100644 --- a/net/sctp/input.c +++ b/net/sctp/input.c @@ -723,23 +723,21 @@ static int __sctp_hash_endpoint(struct sctp_endpoint *ep) struct sock *sk = ep->base.sk; struct net *net = sock_net(sk); struct sctp_hashbucket *head; - struct sctp_ep_common *epb; - epb = &ep->base; - epb->hashent = sctp_ep_hashfn(net, epb->bind_addr.port); - head = &sctp_ep_hashtable[epb->hashent]; + ep->hashent = sctp_ep_hashfn(net, ep->base.bind_addr.port); + head = &sctp_ep_hashtable[ep->hashent]; if (sk->sk_reuseport) { bool any = sctp_is_ep_boundall(sk); - struct sctp_ep_common *epb2; + struct sctp_endpoint *ep2; struct list_head *list; int cnt = 0, err = 1; list_for_each(list, &ep->base.bind_addr.address_list) cnt++; - sctp_for_each_hentry(epb2, &head->chain) { - struct sock *sk2 = epb2->sk; + sctp_for_each_hentry(ep2, &head->chain) { + struct sock *sk2 = ep2->base.sk; if (!net_eq(sock_net(sk2), net) || sk2 == sk || !uid_eq(sock_i_uid(sk2), sock_i_uid(sk)) || @@ -766,7 +764,7 @@ static int __sctp_hash_endpoint(struct sctp_endpoint *ep) } write_lock(&head->lock); - hlist_add_head(&epb->node, &head->chain); + hlist_add_head(&ep->node, &head->chain); write_unlock(&head->lock); return 0; } @@ -788,19 +786,16 @@ static void __sctp_unhash_endpoint(struct sctp_endpoint *ep) { struct sock *sk = ep->base.sk; struct sctp_hashbucket *head; - struct sctp_ep_common *epb; - epb = &ep->base; + ep->hashent = sctp_ep_hashfn(sock_net(sk), ep->base.bind_addr.port); - epb->hashent = sctp_ep_hashfn(sock_net(sk), epb->bind_addr.port); - - head = &sctp_ep_hashtable[epb->hashent]; + head = &sctp_ep_hashtable[ep->hashent]; if (rcu_access_pointer(sk->sk_reuseport_cb)) reuseport_detach_sock(sk); write_lock(&head->lock); - hlist_del_init(&epb->node); + hlist_del_init(&ep->node); write_unlock(&head->lock); } @@ -833,7 +828,6 @@ static struct sctp_endpoint *__sctp_rcv_lookup_endpoint( const union sctp_addr *paddr) { struct sctp_hashbucket *head; - struct sctp_ep_common *epb; struct sctp_endpoint *ep; struct sock *sk; __be16 lport; @@ -843,8 +837,7 @@ static struct sctp_endpoint *__sctp_rcv_lookup_endpoint( hash = sctp_ep_hashfn(net, ntohs(lport)); head = &sctp_ep_hashtable[hash]; read_lock(&head->lock); - sctp_for_each_hentry(epb, &head->chain) { - ep = sctp_ep(epb); + sctp_for_each_hentry(ep, &head->chain) { if (sctp_endpoint_is_match(ep, net, laddr)) goto hit; } diff --git a/net/sctp/proc.c b/net/sctp/proc.c index 963b94517ec2..ec00ee75d59a 100644 --- a/net/sctp/proc.c +++ b/net/sctp/proc.c @@ -161,7 +161,6 @@ static void *sctp_eps_seq_next(struct seq_file *seq, void *v, loff_t *pos) static int sctp_eps_seq_show(struct seq_file *seq, void *v) { struct sctp_hashbucket *head; - struct sctp_ep_common *epb; struct sctp_endpoint *ep; struct sock *sk; int hash = *(loff_t *)v; @@ -171,18 +170,17 @@ static int sctp_eps_seq_show(struct seq_file *seq, void *v) head = &sctp_ep_hashtable[hash]; read_lock_bh(&head->lock); - sctp_for_each_hentry(epb, &head->chain) { - ep = sctp_ep(epb); - sk = epb->sk; + sctp_for_each_hentry(ep, &head->chain) { + sk = ep->base.sk; if (!net_eq(sock_net(sk), seq_file_net(seq))) continue; seq_printf(seq, "%8pK %8pK %-3d %-3d %-4d %-5d %5u %5lu ", ep, sk, sctp_sk(sk)->type, sk->sk_state, hash, - epb->bind_addr.port, + ep->base.bind_addr.port, from_kuid_munged(seq_user_ns(seq), sock_i_uid(sk)), sock_i_ino(sk)); - sctp_seq_dump_local_addrs(seq, epb); + sctp_seq_dump_local_addrs(seq, &ep->base); seq_printf(seq, "\n"); } read_unlock_bh(&head->lock); diff --git a/net/sctp/socket.c b/net/sctp/socket.c index 79cf4cda2cf6..5053d813e91c 100644 --- a/net/sctp/socket.c +++ b/net/sctp/socket.c @@ -5193,14 +5193,14 @@ int sctp_for_each_endpoint(int (*cb)(struct sctp_endpoint *, void *), void *p) { int err = 0; int hash = 0; - struct sctp_ep_common *epb; + struct sctp_endpoint *ep; struct sctp_hashbucket *head; for (head = sctp_ep_hashtable; hash < sctp_ep_hashsize; hash++, head++) { read_lock_bh(&head->lock); - sctp_for_each_hentry(epb, &head->chain) { - err = cb(sctp_ep(epb), p); + sctp_for_each_hentry(ep, &head->chain) { + err = cb(ep, p); if (err) break; } From 52319d9d2f522ed939af31af70f8c3a0f0f67e6c Mon Sep 17 00:00:00 2001 From: Kuniyuki Iwashima Date: Wed, 31 Jul 2024 16:46:24 -0700 Subject: [PATCH 242/342] sctp: Fix null-ptr-deref in reuseport_add_sock(). [ Upstream commit 9ab0faa7f9ffe31296dbb9bbe6f76c72c14eea18 ] syzbot reported a null-ptr-deref while accessing sk2->sk_reuseport_cb in reuseport_add_sock(). [0] The repro first creates a listener with SO_REUSEPORT. Then, it creates another listener on the same port and concurrently closes the first listener. The second listen() calls reuseport_add_sock() with the first listener as sk2, where sk2->sk_reuseport_cb is not expected to be cleared concurrently, but the close() does clear it by reuseport_detach_sock(). The problem is SCTP does not properly synchronise reuseport_alloc(), reuseport_add_sock(), and reuseport_detach_sock(). The caller of reuseport_alloc() and reuseport_{add,detach}_sock() must provide synchronisation for sockets that are classified into the same reuseport group. Otherwise, such sockets form multiple identical reuseport groups, and all groups except one would be silently dead. 1. Two sockets call listen() concurrently 2. No socket in the same group found in sctp_ep_hashtable[] 3. Two sockets call reuseport_alloc() and form two reuseport groups 4. Only one group hit first in __sctp_rcv_lookup_endpoint() receives incoming packets Also, the reported null-ptr-deref could occur. TCP/UDP guarantees that would not happen by holding the hash bucket lock. Let's apply the locking strategy to __sctp_hash_endpoint() and __sctp_unhash_endpoint(). [0]: Oops: general protection fault, probably for non-canonical address 0xdffffc0000000002: 0000 [#1] PREEMPT SMP KASAN PTI KASAN: null-ptr-deref in range [0x0000000000000010-0x0000000000000017] CPU: 1 UID: 0 PID: 10230 Comm: syz-executor119 Not tainted 6.10.0-syzkaller-12585-g301927d2d2eb #0 Hardware name: Google Google Compute Engine/Google Compute Engine, BIOS Google 06/27/2024 RIP: 0010:reuseport_add_sock+0x27e/0x5e0 net/core/sock_reuseport.c:350 Code: 00 0f b7 5d 00 bf 01 00 00 00 89 de e8 1b a4 ff f7 83 fb 01 0f 85 a3 01 00 00 e8 6d a0 ff f7 49 8d 7e 12 48 89 f8 48 c1 e8 03 <42> 0f b6 04 28 84 c0 0f 85 4b 02 00 00 41 0f b7 5e 12 49 8d 7e 14 RSP: 0018:ffffc9000b947c98 EFLAGS: 00010202 RAX: 0000000000000002 RBX: ffff8880252ddf98 RCX: ffff888079478000 RDX: 0000000000000000 RSI: 0000000000000001 RDI: 0000000000000012 RBP: 0000000000000001 R08: ffffffff8993e18d R09: 1ffffffff1fef385 R10: dffffc0000000000 R11: fffffbfff1fef386 R12: ffff8880252ddac0 R13: dffffc0000000000 R14: 0000000000000000 R15: 0000000000000000 FS: 00007f24e45b96c0(0000) GS:ffff8880b9300000(0000) knlGS:0000000000000000 CS: 0010 DS: 0000 ES: 0000 CR0: 0000000080050033 CR2: 00007ffcced5f7b8 CR3: 00000000241be000 CR4: 00000000003506f0 DR0: 0000000000000000 DR1: 0000000000000000 DR2: 0000000000000000 DR3: 0000000000000000 DR6: 00000000fffe0ff0 DR7: 0000000000000400 Call Trace: __sctp_hash_endpoint net/sctp/input.c:762 [inline] sctp_hash_endpoint+0x52a/0x600 net/sctp/input.c:790 sctp_listen_start net/sctp/socket.c:8570 [inline] sctp_inet_listen+0x767/0xa20 net/sctp/socket.c:8625 __sys_listen_socket net/socket.c:1883 [inline] __sys_listen+0x1b7/0x230 net/socket.c:1894 __do_sys_listen net/socket.c:1902 [inline] __se_sys_listen net/socket.c:1900 [inline] __x64_sys_listen+0x5a/0x70 net/socket.c:1900 do_syscall_x64 arch/x86/entry/common.c:52 [inline] do_syscall_64+0xf3/0x230 arch/x86/entry/common.c:83 entry_SYSCALL_64_after_hwframe+0x77/0x7f RIP: 0033:0x7f24e46039b9 Code: 28 00 00 00 75 05 48 83 c4 28 c3 e8 91 1a 00 00 90 48 89 f8 48 89 f7 48 89 d6 48 89 ca 4d 89 c2 4d 89 c8 4c 8b 4c 24 08 0f 05 <48> 3d 01 f0 ff ff 73 01 c3 48 c7 c1 b0 ff ff ff f7 d8 64 89 01 48 RSP: 002b:00007f24e45b9228 EFLAGS: 00000246 ORIG_RAX: 0000000000000032 RAX: ffffffffffffffda RBX: 00007f24e468e428 RCX: 00007f24e46039b9 RDX: 00007f24e46039b9 RSI: 0000000000000003 RDI: 0000000000000004 RBP: 00007f24e468e420 R08: 00007f24e45b96c0 R09: 00007f24e45b96c0 R10: 00007f24e45b96c0 R11: 0000000000000246 R12: 00007f24e468e42c R13: 00007f24e465a5dc R14: 0020000000000001 R15: 00007ffcced5f7d8 Modules linked in: Fixes: 6ba845740267 ("sctp: process sk_reuseport in sctp_get_port_local") Reported-by: syzbot+e6979a5d2f10ecb700e4@syzkaller.appspotmail.com Closes: https://syzkaller.appspot.com/bug?extid=e6979a5d2f10ecb700e4 Tested-by: syzbot+e6979a5d2f10ecb700e4@syzkaller.appspotmail.com Signed-off-by: Kuniyuki Iwashima Acked-by: Xin Long Link: https://patch.msgid.link/20240731234624.94055-1-kuniyu@amazon.com Signed-off-by: Jakub Kicinski Signed-off-by: Sasha Levin --- net/sctp/input.c | 19 +++++++++++-------- 1 file changed, 11 insertions(+), 8 deletions(-) diff --git a/net/sctp/input.c b/net/sctp/input.c index 17df756418ea..8fe1a74f0618 100644 --- a/net/sctp/input.c +++ b/net/sctp/input.c @@ -723,15 +723,19 @@ static int __sctp_hash_endpoint(struct sctp_endpoint *ep) struct sock *sk = ep->base.sk; struct net *net = sock_net(sk); struct sctp_hashbucket *head; + int err = 0; ep->hashent = sctp_ep_hashfn(net, ep->base.bind_addr.port); head = &sctp_ep_hashtable[ep->hashent]; + write_lock(&head->lock); if (sk->sk_reuseport) { bool any = sctp_is_ep_boundall(sk); struct sctp_endpoint *ep2; struct list_head *list; - int cnt = 0, err = 1; + int cnt = 0; + + err = 1; list_for_each(list, &ep->base.bind_addr.address_list) cnt++; @@ -749,24 +753,24 @@ static int __sctp_hash_endpoint(struct sctp_endpoint *ep) if (!err) { err = reuseport_add_sock(sk, sk2, any); if (err) - return err; + goto out; break; } else if (err < 0) { - return err; + goto out; } } if (err) { err = reuseport_alloc(sk, any); if (err) - return err; + goto out; } } - write_lock(&head->lock); hlist_add_head(&ep->node, &head->chain); +out: write_unlock(&head->lock); - return 0; + return err; } /* Add an endpoint to the hash. Local BH-safe. */ @@ -791,10 +795,9 @@ static void __sctp_unhash_endpoint(struct sctp_endpoint *ep) head = &sctp_ep_hashtable[ep->hashent]; + write_lock(&head->lock); if (rcu_access_pointer(sk->sk_reuseport_cb)) reuseport_detach_sock(sk); - - write_lock(&head->lock); hlist_del_init(&ep->node); write_unlock(&head->lock); } From e87f52225e04a7001bf55bbd7a330fa4252327b5 Mon Sep 17 00:00:00 2001 From: Daniele Palmas Date: Thu, 1 Aug 2024 15:55:12 +0200 Subject: [PATCH 243/342] net: usb: qmi_wwan: fix memory leak for not ip packets MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit [ Upstream commit 7ab107544b777c3bd7feb9fe447367d8edd5b202 ] Free the unused skb when not ip packets arrive. Fixes: c6adf77953bc ("net: usb: qmi_wwan: add qmap mux protocol support") Signed-off-by: Daniele Palmas Acked-by: Bjørn Mork Signed-off-by: David S. Miller Signed-off-by: Sasha Levin --- drivers/net/usb/qmi_wwan.c | 1 + 1 file changed, 1 insertion(+) diff --git a/drivers/net/usb/qmi_wwan.c b/drivers/net/usb/qmi_wwan.c index d2a8238e144a..47cc54a64b56 100644 --- a/drivers/net/usb/qmi_wwan.c +++ b/drivers/net/usb/qmi_wwan.c @@ -216,6 +216,7 @@ static int qmimux_rx_fixup(struct usbnet *dev, struct sk_buff *skb) break; default: /* not ip - do not know what to do */ + kfree_skb(skbn); goto skip; } From 085fb116c4ad22691fc048c0667ccf053b1a7a90 Mon Sep 17 00:00:00 2001 From: Eric Dumazet Date: Mon, 5 Aug 2024 08:58:21 +0000 Subject: [PATCH 244/342] net: linkwatch: use system_unbound_wq [ Upstream commit 3e7917c0cdad835a5121520fc5686d954b7a61ab ] linkwatch_event() grabs possibly very contended RTNL mutex. system_wq is not suitable for such work. Inspired by many noisy syzbot reports. 3 locks held by kworker/0:7/5266: #0: ffff888015480948 ((wq_completion)events){+.+.}-{0:0}, at: process_one_work kernel/workqueue.c:3206 [inline] #0: ffff888015480948 ((wq_completion)events){+.+.}-{0:0}, at: process_scheduled_works+0x90a/0x1830 kernel/workqueue.c:3312 #1: ffffc90003f6fd00 ((linkwatch_work).work){+.+.}-{0:0}, at: process_one_work kernel/workqueue.c:3207 [inline] , at: process_scheduled_works+0x945/0x1830 kernel/workqueue.c:3312 #2: ffffffff8fa6f208 (rtnl_mutex){+.+.}-{3:3}, at: linkwatch_event+0xe/0x60 net/core/link_watch.c:276 Reported-by: syzbot Fixes: 1da177e4c3f4 ("Linux-2.6.12-rc2") Signed-off-by: Eric Dumazet Reviewed-by: Kuniyuki Iwashima Link: https://patch.msgid.link/20240805085821.1616528-1-edumazet@google.com Signed-off-by: Jakub Kicinski Signed-off-by: Sasha Levin --- net/core/link_watch.c | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-) diff --git a/net/core/link_watch.c b/net/core/link_watch.c index 1a455847da54..0311d4d309e1 100644 --- a/net/core/link_watch.c +++ b/net/core/link_watch.c @@ -138,9 +138,9 @@ static void linkwatch_schedule_work(int urgent) * override the existing timer. */ if (test_bit(LW_URGENT, &linkwatch_flags)) - mod_delayed_work(system_wq, &linkwatch_work, 0); + mod_delayed_work(system_unbound_wq, &linkwatch_work, 0); else - schedule_delayed_work(&linkwatch_work, delay); + queue_delayed_work(system_unbound_wq, &linkwatch_work, delay); } From 01150020c0719e1e37b1c068cb3446b8028a599f Mon Sep 17 00:00:00 2001 From: Dmitry Antipov Date: Wed, 31 Jul 2024 12:19:36 +0300 Subject: [PATCH 245/342] Bluetooth: l2cap: always unlock channel in l2cap_conless_channel() [ Upstream commit c531e63871c0b50c8c4e62c048535a08886fba3e ] Add missing call to 'l2cap_chan_unlock()' on receive error handling path in 'l2cap_conless_channel()'. Fixes: a24cce144b98 ("Bluetooth: Fix reference counting of global L2CAP channels") Reported-by: syzbot+45ac74737e866894acb0@syzkaller.appspotmail.com Closes: https://syzkaller.appspot.com/bug?extid=45ac74737e866894acb0 Signed-off-by: Dmitry Antipov Signed-off-by: Luiz Augusto von Dentz Signed-off-by: Sasha Levin --- net/bluetooth/l2cap_core.c | 1 + 1 file changed, 1 insertion(+) diff --git a/net/bluetooth/l2cap_core.c b/net/bluetooth/l2cap_core.c index 9cc034e6074c..23fc03f7bf31 100644 --- a/net/bluetooth/l2cap_core.c +++ b/net/bluetooth/l2cap_core.c @@ -7762,6 +7762,7 @@ static void l2cap_conless_channel(struct l2cap_conn *conn, __le16 psm, bt_cb(skb)->l2cap.psm = psm; if (!chan->ops->recv(chan, skb)) { + l2cap_chan_unlock(chan); l2cap_chan_put(chan); return; } From b7b8d9f5e679af60c94251fd6728dde34be69a71 Mon Sep 17 00:00:00 2001 From: Joe Hattori Date: Tue, 6 Aug 2024 10:13:27 +0900 Subject: [PATCH 246/342] net: dsa: bcm_sf2: Fix a possible memory leak in bcm_sf2_mdio_register() [ Upstream commit e3862093ee93fcfbdadcb7957f5f8974fffa806a ] bcm_sf2_mdio_register() calls of_phy_find_device() and then phy_device_remove() in a loop to remove existing PHY devices. of_phy_find_device() eventually calls bus_find_device(), which calls get_device() on the returned struct device * to increment the refcount. The current implementation does not decrement the refcount, which causes memory leak. This commit adds the missing phy_device_free() call to decrement the refcount via put_device() to balance the refcount. Fixes: 771089c2a485 ("net: dsa: bcm_sf2: Ensure that MDIO diversion is used") Signed-off-by: Joe Hattori Tested-by: Florian Fainelli Reviewed-by: Florian Fainelli Link: https://patch.msgid.link/20240806011327.3817861-1-joe@pf.is.s.u-tokyo.ac.jp Signed-off-by: Jakub Kicinski Signed-off-by: Sasha Levin --- drivers/net/dsa/bcm_sf2.c | 4 +++- 1 file changed, 3 insertions(+), 1 deletion(-) diff --git a/drivers/net/dsa/bcm_sf2.c b/drivers/net/dsa/bcm_sf2.c index a5849663f65c..d0f94a5fae5a 100644 --- a/drivers/net/dsa/bcm_sf2.c +++ b/drivers/net/dsa/bcm_sf2.c @@ -558,8 +558,10 @@ static int bcm_sf2_mdio_register(struct dsa_switch *ds) of_remove_property(child, prop); phydev = of_phy_find_device(child); - if (phydev) + if (phydev) { phy_device_remove(phydev); + phy_device_free(phydev); + } } err = mdiobus_register(priv->slave_mii_bus); From 865948628a42ef6b661fe3f204620bab1f7a6414 Mon Sep 17 00:00:00 2001 From: James Chapman Date: Tue, 6 Aug 2024 17:06:26 +0100 Subject: [PATCH 247/342] l2tp: fix lockdep splat [ Upstream commit 86a41ea9fd79ddb6145cb8ebf5aeafceabca6f7d ] When l2tp tunnels use a socket provided by userspace, we can hit lockdep splats like the below when data is transmitted through another (unrelated) userspace socket which then gets routed over l2tp. This issue was previously discussed here: https://lore.kernel.org/netdev/87sfialu2n.fsf@cloudflare.com/ The solution is to have lockdep treat socket locks of l2tp tunnel sockets separately than those of standard INET sockets. To do so, use a different lockdep subclass where lock nesting is possible. ============================================ WARNING: possible recursive locking detected 6.10.0+ #34 Not tainted -------------------------------------------- iperf3/771 is trying to acquire lock: ffff8881027601d8 (slock-AF_INET/1){+.-.}-{2:2}, at: l2tp_xmit_skb+0x243/0x9d0 but task is already holding lock: ffff888102650d98 (slock-AF_INET/1){+.-.}-{2:2}, at: tcp_v4_rcv+0x1848/0x1e10 other info that might help us debug this: Possible unsafe locking scenario: CPU0 ---- lock(slock-AF_INET/1); lock(slock-AF_INET/1); *** DEADLOCK *** May be due to missing lock nesting notation 10 locks held by iperf3/771: #0: ffff888102650258 (sk_lock-AF_INET){+.+.}-{0:0}, at: tcp_sendmsg+0x1a/0x40 #1: ffffffff822ac220 (rcu_read_lock){....}-{1:2}, at: __ip_queue_xmit+0x4b/0xbc0 #2: ffffffff822ac220 (rcu_read_lock){....}-{1:2}, at: ip_finish_output2+0x17a/0x1130 #3: ffffffff822ac220 (rcu_read_lock){....}-{1:2}, at: process_backlog+0x28b/0x9f0 #4: ffffffff822ac220 (rcu_read_lock){....}-{1:2}, at: ip_local_deliver_finish+0xf9/0x260 #5: ffff888102650d98 (slock-AF_INET/1){+.-.}-{2:2}, at: tcp_v4_rcv+0x1848/0x1e10 #6: ffffffff822ac220 (rcu_read_lock){....}-{1:2}, at: __ip_queue_xmit+0x4b/0xbc0 #7: ffffffff822ac220 (rcu_read_lock){....}-{1:2}, at: ip_finish_output2+0x17a/0x1130 #8: ffffffff822ac1e0 (rcu_read_lock_bh){....}-{1:2}, at: __dev_queue_xmit+0xcc/0x1450 #9: ffff888101f33258 (dev->qdisc_tx_busylock ?: &qdisc_tx_busylock#2){+...}-{2:2}, at: __dev_queue_xmit+0x513/0x1450 stack backtrace: CPU: 2 UID: 0 PID: 771 Comm: iperf3 Not tainted 6.10.0+ #34 Hardware name: QEMU Standard PC (i440FX + PIIX, 1996), BIOS 1.15.0-1 04/01/2014 Call Trace: dump_stack_lvl+0x69/0xa0 dump_stack+0xc/0x20 __lock_acquire+0x135d/0x2600 ? srso_alias_return_thunk+0x5/0xfbef5 lock_acquire+0xc4/0x2a0 ? l2tp_xmit_skb+0x243/0x9d0 ? __skb_checksum+0xa3/0x540 _raw_spin_lock_nested+0x35/0x50 ? l2tp_xmit_skb+0x243/0x9d0 l2tp_xmit_skb+0x243/0x9d0 l2tp_eth_dev_xmit+0x3c/0xc0 dev_hard_start_xmit+0x11e/0x420 sch_direct_xmit+0xc3/0x640 __dev_queue_xmit+0x61c/0x1450 ? ip_finish_output2+0xf4c/0x1130 ip_finish_output2+0x6b6/0x1130 ? srso_alias_return_thunk+0x5/0xfbef5 ? __ip_finish_output+0x217/0x380 ? srso_alias_return_thunk+0x5/0xfbef5 __ip_finish_output+0x217/0x380 ip_output+0x99/0x120 __ip_queue_xmit+0xae4/0xbc0 ? srso_alias_return_thunk+0x5/0xfbef5 ? srso_alias_return_thunk+0x5/0xfbef5 ? tcp_options_write.constprop.0+0xcb/0x3e0 ip_queue_xmit+0x34/0x40 __tcp_transmit_skb+0x1625/0x1890 __tcp_send_ack+0x1b8/0x340 tcp_send_ack+0x23/0x30 __tcp_ack_snd_check+0xa8/0x530 ? srso_alias_return_thunk+0x5/0xfbef5 tcp_rcv_established+0x412/0xd70 tcp_v4_do_rcv+0x299/0x420 tcp_v4_rcv+0x1991/0x1e10 ip_protocol_deliver_rcu+0x50/0x220 ip_local_deliver_finish+0x158/0x260 ip_local_deliver+0xc8/0xe0 ip_rcv+0xe5/0x1d0 ? __pfx_ip_rcv+0x10/0x10 __netif_receive_skb_one_core+0xce/0xe0 ? process_backlog+0x28b/0x9f0 __netif_receive_skb+0x34/0xd0 ? process_backlog+0x28b/0x9f0 process_backlog+0x2cb/0x9f0 __napi_poll.constprop.0+0x61/0x280 net_rx_action+0x332/0x670 ? srso_alias_return_thunk+0x5/0xfbef5 ? find_held_lock+0x2b/0x80 ? srso_alias_return_thunk+0x5/0xfbef5 ? srso_alias_return_thunk+0x5/0xfbef5 handle_softirqs+0xda/0x480 ? __dev_queue_xmit+0xa2c/0x1450 do_softirq+0xa1/0xd0 __local_bh_enable_ip+0xc8/0xe0 ? __dev_queue_xmit+0xa2c/0x1450 __dev_queue_xmit+0xa48/0x1450 ? ip_finish_output2+0xf4c/0x1130 ip_finish_output2+0x6b6/0x1130 ? srso_alias_return_thunk+0x5/0xfbef5 ? __ip_finish_output+0x217/0x380 ? srso_alias_return_thunk+0x5/0xfbef5 __ip_finish_output+0x217/0x380 ip_output+0x99/0x120 __ip_queue_xmit+0xae4/0xbc0 ? srso_alias_return_thunk+0x5/0xfbef5 ? srso_alias_return_thunk+0x5/0xfbef5 ? tcp_options_write.constprop.0+0xcb/0x3e0 ip_queue_xmit+0x34/0x40 __tcp_transmit_skb+0x1625/0x1890 tcp_write_xmit+0x766/0x2fb0 ? __entry_text_end+0x102ba9/0x102bad ? srso_alias_return_thunk+0x5/0xfbef5 ? __might_fault+0x74/0xc0 ? srso_alias_return_thunk+0x5/0xfbef5 __tcp_push_pending_frames+0x56/0x190 tcp_push+0x117/0x310 tcp_sendmsg_locked+0x14c1/0x1740 tcp_sendmsg+0x28/0x40 inet_sendmsg+0x5d/0x90 sock_write_iter+0x242/0x2b0 vfs_write+0x68d/0x800 ? __pfx_sock_write_iter+0x10/0x10 ksys_write+0xc8/0xf0 __x64_sys_write+0x3d/0x50 x64_sys_call+0xfaf/0x1f50 do_syscall_64+0x6d/0x140 entry_SYSCALL_64_after_hwframe+0x76/0x7e RIP: 0033:0x7f4d143af992 Code: c3 8b 07 85 c0 75 24 49 89 fb 48 89 f0 48 89 d7 48 89 ce 4c 89 c2 4d 89 ca 4c 8b 44 24 08 4c 8b 4c 24 10 4c 89 5c 24 08 0f 05 e9 01 cc ff ff 41 54 b8 02 00 00 0 RSP: 002b:00007ffd65032058 EFLAGS: 00000246 ORIG_RAX: 0000000000000001 RAX: ffffffffffffffda RBX: 0000000000000001 RCX: 00007f4d143af992 RDX: 0000000000000025 RSI: 00007f4d143f3bcc RDI: 0000000000000005 RBP: 00007f4d143f2b28 R08: 0000000000000000 R09: 0000000000000000 R10: 0000000000000000 R11: 0000000000000246 R12: 00007f4d143f3bcc R13: 0000000000000005 R14: 0000000000000000 R15: 00007ffd650323f0 Fixes: 0b2c59720e65 ("l2tp: close all race conditions in l2tp_tunnel_register()") Suggested-by: Eric Dumazet Reported-by: syzbot+6acef9e0a4d1f46c83d4@syzkaller.appspotmail.com Closes: https://syzkaller.appspot.com/bug?extid=6acef9e0a4d1f46c83d4 CC: gnault@redhat.com CC: cong.wang@bytedance.com Signed-off-by: James Chapman Signed-off-by: Tom Parkin Link: https://patch.msgid.link/20240806160626.1248317-1-jchapman@katalix.com Signed-off-by: Jakub Kicinski Signed-off-by: Sasha Levin --- net/l2tp/l2tp_core.c | 15 +++++++++++++-- 1 file changed, 13 insertions(+), 2 deletions(-) diff --git a/net/l2tp/l2tp_core.c b/net/l2tp/l2tp_core.c index a4b793d1b7d7..b6dcfca740c1 100644 --- a/net/l2tp/l2tp_core.c +++ b/net/l2tp/l2tp_core.c @@ -88,6 +88,11 @@ /* Default trace flags */ #define L2TP_DEFAULT_DEBUG_FLAGS 0 +#define L2TP_DEPTH_NESTING 2 +#if L2TP_DEPTH_NESTING == SINGLE_DEPTH_NESTING +#error "L2TP requires its own lockdep subclass" +#endif + /* Private data stored for received packets in the skb. */ struct l2tp_skb_cb { @@ -1041,7 +1046,13 @@ static int l2tp_xmit_core(struct l2tp_session *session, struct sk_buff *skb, uns IPCB(skb)->flags &= ~(IPSKB_XFRM_TUNNEL_SIZE | IPSKB_XFRM_TRANSFORMED | IPSKB_REROUTED); nf_reset_ct(skb); - bh_lock_sock_nested(sk); + /* L2TP uses its own lockdep subclass to avoid lockdep splats caused by + * nested socket calls on the same lockdep socket class. This can + * happen when data from a user socket is routed over l2tp, which uses + * another userspace socket. + */ + spin_lock_nested(&sk->sk_lock.slock, L2TP_DEPTH_NESTING); + if (sock_owned_by_user(sk)) { kfree_skb(skb); ret = NET_XMIT_DROP; @@ -1093,7 +1104,7 @@ static int l2tp_xmit_core(struct l2tp_session *session, struct sk_buff *skb, uns ret = l2tp_xmit_queue(tunnel, skb, &inet->cork.fl); out_unlock: - bh_unlock_sock(sk); + spin_unlock(&sk->sk_lock.slock); return ret; } From adc491f3e73d852d2b7f9ec9f11668bb1442d6ee Mon Sep 17 00:00:00 2001 From: =?UTF-8?q?Cs=C3=B3k=C3=A1s=2C=20Bence?= Date: Wed, 7 Aug 2024 10:09:56 +0200 Subject: [PATCH 248/342] net: fec: Stop PPS on driver remove MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit [ Upstream commit 8fee6d5ad5fa18c270eedb2a2cdf58dbadefb94b ] PPS was not stopped in `fec_ptp_stop()`, called when the adapter was removed. Consequentially, you couldn't safely reload the driver with the PPS signal on. Fixes: 32cba57ba74b ("net: fec: introduce fec_ptp_stop and use in probe fail path") Reviewed-by: Fabio Estevam Link: https://lore.kernel.org/netdev/CAOMZO5BzcZR8PwKKwBssQq_wAGzVgf1ffwe_nhpQJjviTdxy-w@mail.gmail.com/T/#m01dcb810bfc451a492140f6797ca77443d0cb79f Signed-off-by: Csókás, Bence Reviewed-by: Andrew Lunn Reviewed-by: Frank Li Link: https://patch.msgid.link/20240807080956.2556602-1-csokas.bence@prolan.hu Signed-off-by: Jakub Kicinski Signed-off-by: Sasha Levin --- drivers/net/ethernet/freescale/fec_ptp.c | 3 +++ 1 file changed, 3 insertions(+) diff --git a/drivers/net/ethernet/freescale/fec_ptp.c b/drivers/net/ethernet/freescale/fec_ptp.c index 780fbb3e1ed0..84e0855069a8 100644 --- a/drivers/net/ethernet/freescale/fec_ptp.c +++ b/drivers/net/ethernet/freescale/fec_ptp.c @@ -640,6 +640,9 @@ void fec_ptp_stop(struct platform_device *pdev) struct net_device *ndev = platform_get_drvdata(pdev); struct fec_enet_private *fep = netdev_priv(ndev); + if (fep->pps_enable) + fec_ptp_enable_pps(fep, 0); + cancel_delayed_work_sync(&fep->time_keep); if (fep->ptp_clock) ptp_clock_unregister(fep->ptp_clock); From 464d242868a8604d77cd1a1ea2f3f3f86cb265b6 Mon Sep 17 00:00:00 2001 From: "Paul E. McKenney" Date: Fri, 5 Apr 2024 12:02:11 -0700 Subject: [PATCH 249/342] rcutorture: Fix rcu_torture_fwd_cb_cr() data race [ Upstream commit 6040072f4774a575fa67b912efe7722874be337b ] On powerpc systems, spinlock acquisition does not order prior stores against later loads. This means that this statement: rfcp->rfc_next = NULL; Can be reordered to follow this statement: WRITE_ONCE(*rfcpp, rfcp); Which is then a data race with rcu_torture_fwd_prog_cr(), specifically, this statement: rfcpn = READ_ONCE(rfcp->rfc_next) KCSAN located this data race, which represents a real failure on powerpc. Signed-off-by: Paul E. McKenney Acked-by: Marco Elver Cc: Andrey Konovalov Cc: Signed-off-by: Sasha Levin --- kernel/rcu/rcutorture.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/kernel/rcu/rcutorture.c b/kernel/rcu/rcutorture.c index 9f505688291e..5c4bdbe76df0 100644 --- a/kernel/rcu/rcutorture.c +++ b/kernel/rcu/rcutorture.c @@ -1867,7 +1867,7 @@ static void rcu_torture_fwd_cb_cr(struct rcu_head *rhp) spin_lock_irqsave(&rfp->rcu_fwd_lock, flags); rfcpp = rfp->rcu_fwd_cb_tail; rfp->rcu_fwd_cb_tail = &rfcp->rfc_next; - WRITE_ONCE(*rfcpp, rfcp); + smp_store_release(rfcpp, rfcp); WRITE_ONCE(rfp->n_launders_cb, rfp->n_launders_cb + 1); i = ((jiffies - rfp->rcu_fwd_startat) / (HZ / FWD_CBS_HIST_DIV)); if (i >= ARRAY_SIZE(rfp->n_launders_hist)) From 5ccf99545c7132187849db9f3ff1b2c8f8be851b Mon Sep 17 00:00:00 2001 From: Li Nan Date: Wed, 8 May 2024 17:20:53 +0800 Subject: [PATCH 250/342] md: do not delete safemode_timer in mddev_suspend [ Upstream commit a8768a134518e406d41799a3594aeb74e0889cf7 ] The deletion of safemode_timer in mddev_suspend() is redundant and potentially harmful now. If timer is about to be woken up but gets deleted, 'in_sync' will remain 0 until the next write, causing array to stay in the 'active' state instead of transitioning to 'clean'. Commit 0d9f4f135eb6 ("MD: Add del_timer_sync to mddev_suspend (fix nasty panic))" introduced this deletion for dm, because if timer fired after dm is destroyed, the resource which the timer depends on might have been freed. However, commit 0dd84b319352 ("md: call __md_stop_writes in md_stop") added __md_stop_writes() to md_stop(), which is called before freeing resource. Timer is deleted in __md_stop_writes(), and the origin issue is resolved. Therefore, delete safemode_timer can be removed safely now. Signed-off-by: Li Nan Reviewed-by: Yu Kuai Signed-off-by: Song Liu Link: https://lore.kernel.org/r/20240508092053.1447930-1-linan666@huaweicloud.com Signed-off-by: Sasha Levin --- drivers/md/md.c | 1 - 1 file changed, 1 deletion(-) diff --git a/drivers/md/md.c b/drivers/md/md.c index 67ceab4573be..f1f029243e0c 100644 --- a/drivers/md/md.c +++ b/drivers/md/md.c @@ -524,7 +524,6 @@ void mddev_suspend(struct mddev *mddev) clear_bit_unlock(MD_ALLOW_SB_UPDATE, &mddev->flags); wait_event(mddev->sb_wait, !test_bit(MD_UPDATING_SB, &mddev->flags)); - del_timer_sync(&mddev->safemode_timer); /* restrict memory reclaim I/O during raid array is suspend */ mddev->noio_flag = memalloc_noio_save(); } From c384dd4f1fb3b14a2fd199360701cc163ea88705 Mon Sep 17 00:00:00 2001 From: Yu Kuai Date: Tue, 11 Jun 2024 21:22:51 +0800 Subject: [PATCH 251/342] md/raid5: avoid BUG_ON() while continue reshape after reassembling [ Upstream commit 305a5170dc5cf3d395bb4c4e9239bca6d0b54b49 ] Currently, mdadm support --revert-reshape to abort the reshape while reassembling, as the test 07revert-grow. However, following BUG_ON() can be triggerred by the test: kernel BUG at drivers/md/raid5.c:6278! invalid opcode: 0000 [#1] PREEMPT SMP PTI irq event stamp: 158985 CPU: 6 PID: 891 Comm: md0_reshape Not tainted 6.9.0-03335-g7592a0b0049a #94 RIP: 0010:reshape_request+0x3f1/0xe60 Call Trace: raid5_sync_request+0x43d/0x550 md_do_sync+0xb7a/0x2110 md_thread+0x294/0x2b0 kthread+0x147/0x1c0 ret_from_fork+0x59/0x70 ret_from_fork_asm+0x1a/0x30 Root cause is that --revert-reshape update the raid_disks from 5 to 4, while reshape position is still set, and after reassembling the array, reshape position will be read from super block, then during reshape the checking of 'writepos' that is caculated by old reshape position will fail. Fix this panic the easy way first, by converting the BUG_ON() to WARN_ON(), and stop the reshape if checkings fail. Noted that mdadm must fix --revert-shape as well, and probably md/raid should enhance metadata validation as well, however this means reassemble will fail and there must be user tools to fix the wrong metadata. Signed-off-by: Yu Kuai Signed-off-by: Song Liu Link: https://lore.kernel.org/r/20240611132251.1967786-13-yukuai1@huaweicloud.com Signed-off-by: Sasha Levin --- drivers/md/raid5.c | 20 +++++++++++++------- 1 file changed, 13 insertions(+), 7 deletions(-) diff --git a/drivers/md/raid5.c b/drivers/md/raid5.c index 66167c4c7bc9..7cdc6f20f504 100644 --- a/drivers/md/raid5.c +++ b/drivers/md/raid5.c @@ -6005,7 +6005,9 @@ static sector_t reshape_request(struct mddev *mddev, sector_t sector_nr, int *sk safepos = conf->reshape_safe; sector_div(safepos, data_disks); if (mddev->reshape_backwards) { - BUG_ON(writepos < reshape_sectors); + if (WARN_ON(writepos < reshape_sectors)) + return MaxSector; + writepos -= reshape_sectors; readpos += reshape_sectors; safepos += reshape_sectors; @@ -6023,14 +6025,18 @@ static sector_t reshape_request(struct mddev *mddev, sector_t sector_nr, int *sk * to set 'stripe_addr' which is where we will write to. */ if (mddev->reshape_backwards) { - BUG_ON(conf->reshape_progress == 0); + if (WARN_ON(conf->reshape_progress == 0)) + return MaxSector; + stripe_addr = writepos; - BUG_ON((mddev->dev_sectors & - ~((sector_t)reshape_sectors - 1)) - - reshape_sectors - stripe_addr - != sector_nr); + if (WARN_ON((mddev->dev_sectors & + ~((sector_t)reshape_sectors - 1)) - + reshape_sectors - stripe_addr != sector_nr)) + return MaxSector; } else { - BUG_ON(writepos != sector_nr + reshape_sectors); + if (WARN_ON(writepos != sector_nr + reshape_sectors)) + return MaxSector; + stripe_addr = sector_nr; } From 64ac0c02352b44cda6ac29013bfdd16dc9a8e1ac Mon Sep 17 00:00:00 2001 From: =?UTF-8?q?Niklas=20S=C3=B6derlund?= Date: Tue, 2 Jul 2024 21:02:30 +0200 Subject: [PATCH 252/342] clocksource/drivers/sh_cmt: Address race condition for clock events MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit [ Upstream commit db19d3aa77612983a02bd223b3f273f896b243cf ] There is a race condition in the CMT interrupt handler. In the interrupt handler the driver sets a driver private flag, FLAG_IRQCONTEXT. This flag is used to indicate any call to set_next_event() should not be directly propagated to the device, but instead cached. This is done as the interrupt handler itself reprograms the device when needed before it completes and this avoids this operation to take place twice. It is unclear why this design was chosen, my suspicion is to allow the struct clock_event_device.event_handler callback, which is called while the FLAG_IRQCONTEXT is set, can update the next event without having to write to the device twice. Unfortunately there is a race between when the FLAG_IRQCONTEXT flag is set and later cleared where the interrupt handler have already started to write the next event to the device. If set_next_event() is called in this window the value is only cached in the driver but not written. This leads to the board to misbehave, or worse lockup and produce a splat. rcu: INFO: rcu_preempt detected stalls on CPUs/tasks: rcu: 0-...!: (0 ticks this GP) idle=f5e0/0/0x0 softirq=519/519 fqs=0 (false positive?) rcu: (detected by 1, t=6502 jiffies, g=-595, q=77 ncpus=2) Sending NMI from CPU 1 to CPUs 0: NMI backtrace for cpu 0 CPU: 0 PID: 0 Comm: swapper/0 Not tainted 6.10.0-rc5-arm64-renesas-00019-g74a6f86eaf1c-dirty #20 Hardware name: Renesas Salvator-X 2nd version board based on r8a77965 (DT) pstate: 60000005 (nZCv daif -PAN -UAO -TCO -DIT -SSBS BTYPE=--) pc : tick_check_broadcast_expired+0xc/0x40 lr : cpu_idle_poll.isra.0+0x8c/0x168 sp : ffff800081c63d70 x29: ffff800081c63d70 x28: 00000000580000c8 x27: 00000000bfee5610 x26: 0000000000000027 x25: 0000000000000000 x24: 0000000000000000 x23: ffff00007fbb9100 x22: ffff8000818f1008 x21: ffff8000800ef07c x20: ffff800081c79ec0 x19: ffff800081c70c28 x18: 0000000000000000 x17: 0000000000000000 x16: 0000000000000000 x15: 0000ffffc2c717d8 x14: 0000000000000000 x13: ffff000009c18080 x12: ffff8000825f7fc0 x11: 0000000000000000 x10: ffff8000818f3cd4 x9 : 0000000000000028 x8 : ffff800081c79ec0 x7 : ffff800081c73000 x6 : 0000000000000000 x5 : 0000000000000000 x4 : ffff7ffffe286000 x3 : 0000000000000000 x2 : ffff7ffffe286000 x1 : ffff800082972900 x0 : ffff8000818f1008 Call trace: tick_check_broadcast_expired+0xc/0x40 do_idle+0x9c/0x280 cpu_startup_entry+0x34/0x40 kernel_init+0x0/0x11c do_one_initcall+0x0/0x260 __primary_switched+0x80/0x88 rcu: rcu_preempt kthread timer wakeup didn't happen for 6501 jiffies! g-595 f0x0 RCU_GP_WAIT_FQS(5) ->state=0x402 rcu: Possible timer handling issue on cpu=0 timer-softirq=262 rcu: rcu_preempt kthread starved for 6502 jiffies! g-595 f0x0 RCU_GP_WAIT_FQS(5) ->state=0x402 ->cpu=0 rcu: Unless rcu_preempt kthread gets sufficient CPU time, OOM is now expected behavior. rcu: RCU grace-period kthread stack dump: task:rcu_preempt state:I stack:0 pid:15 tgid:15 ppid:2 flags:0x00000008 Call trace: __switch_to+0xbc/0x100 __schedule+0x358/0xbe0 schedule+0x48/0x148 schedule_timeout+0xc4/0x138 rcu_gp_fqs_loop+0x12c/0x764 rcu_gp_kthread+0x208/0x298 kthread+0x10c/0x110 ret_from_fork+0x10/0x20 The design have been part of the driver since it was first merged in early 2009. It becomes increasingly harder to trigger the issue the older kernel version one tries. It only takes a few boots on v6.10-rc5, while hundreds of boots are needed to trigger it on v5.10. Close the race condition by using the CMT channel lock for the two competing sections. The channel lock was added to the driver after its initial design. Signed-off-by: Niklas Söderlund Link: https://lore.kernel.org/r/20240702190230.3825292-1-niklas.soderlund+renesas@ragnatech.se Signed-off-by: Daniel Lezcano Signed-off-by: Sasha Levin --- drivers/clocksource/sh_cmt.c | 13 ++++++++++++- 1 file changed, 12 insertions(+), 1 deletion(-) diff --git a/drivers/clocksource/sh_cmt.c b/drivers/clocksource/sh_cmt.c index 66e4872ab34f..26dbf01d2ec5 100644 --- a/drivers/clocksource/sh_cmt.c +++ b/drivers/clocksource/sh_cmt.c @@ -530,6 +530,7 @@ static void sh_cmt_set_next(struct sh_cmt_channel *ch, unsigned long delta) static irqreturn_t sh_cmt_interrupt(int irq, void *dev_id) { struct sh_cmt_channel *ch = dev_id; + unsigned long flags; /* clear flags */ sh_cmt_write_cmcsr(ch, sh_cmt_read_cmcsr(ch) & @@ -560,6 +561,8 @@ static irqreturn_t sh_cmt_interrupt(int irq, void *dev_id) ch->flags &= ~FLAG_SKIPEVENT; + raw_spin_lock_irqsave(&ch->lock, flags); + if (ch->flags & FLAG_REPROGRAM) { ch->flags &= ~FLAG_REPROGRAM; sh_cmt_clock_event_program_verify(ch, 1); @@ -572,6 +575,8 @@ static irqreturn_t sh_cmt_interrupt(int irq, void *dev_id) ch->flags &= ~FLAG_IRQCONTEXT; + raw_spin_unlock_irqrestore(&ch->lock, flags); + return IRQ_HANDLED; } @@ -770,12 +775,18 @@ static int sh_cmt_clock_event_next(unsigned long delta, struct clock_event_device *ced) { struct sh_cmt_channel *ch = ced_to_sh_cmt(ced); + unsigned long flags; BUG_ON(!clockevent_state_oneshot(ced)); + + raw_spin_lock_irqsave(&ch->lock, flags); + if (likely(ch->flags & FLAG_IRQCONTEXT)) ch->next_match_value = delta - 1; else - sh_cmt_set_next(ch, delta - 1); + __sh_cmt_set_next(ch, delta - 1); + + raw_spin_unlock_irqrestore(&ch->lock, flags); return 0; } From 85d8fe79a3cebeebc807056e108c0e1d1e9f0026 Mon Sep 17 00:00:00 2001 From: =?UTF-8?q?Thomas=20Wei=C3=9Fschuh?= Date: Sun, 9 Jun 2024 09:27:16 +0200 Subject: [PATCH 253/342] ACPI: battery: create alarm sysfs attribute atomically MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit [ Upstream commit a231eed10ed5a290129fda36ad7bcc263c53ff7d ] Let the power supply core register the attribute. This ensures that the attribute is created before the device is announced to userspace, avoid a race condition. Signed-off-by: Thomas Weißschuh Signed-off-by: Rafael J. Wysocki Signed-off-by: Sasha Levin --- drivers/acpi/battery.c | 16 ++++++++++++---- 1 file changed, 12 insertions(+), 4 deletions(-) diff --git a/drivers/acpi/battery.c b/drivers/acpi/battery.c index 8b43efe97da5..2e1462b8929c 100644 --- a/drivers/acpi/battery.c +++ b/drivers/acpi/battery.c @@ -670,12 +670,18 @@ static ssize_t acpi_battery_alarm_store(struct device *dev, return count; } -static const struct device_attribute alarm_attr = { +static struct device_attribute alarm_attr = { .attr = {.name = "alarm", .mode = 0644}, .show = acpi_battery_alarm_show, .store = acpi_battery_alarm_store, }; +static struct attribute *acpi_battery_attrs[] = { + &alarm_attr.attr, + NULL +}; +ATTRIBUTE_GROUPS(acpi_battery); + /* * The Battery Hooking API * @@ -812,7 +818,10 @@ static void __exit battery_hook_exit(void) static int sysfs_add_battery(struct acpi_battery *battery) { - struct power_supply_config psy_cfg = { .drv_data = battery, }; + struct power_supply_config psy_cfg = { + .drv_data = battery, + .attr_grp = acpi_battery_groups, + }; bool full_cap_broken = false; if (!ACPI_BATTERY_CAPACITY_VALID(battery->full_charge_capacity) && @@ -857,7 +866,7 @@ static int sysfs_add_battery(struct acpi_battery *battery) return result; } battery_hook_add_battery(battery); - return device_create_file(&battery->bat->dev, &alarm_attr); + return 0; } static void sysfs_remove_battery(struct acpi_battery *battery) @@ -868,7 +877,6 @@ static void sysfs_remove_battery(struct acpi_battery *battery) return; } battery_hook_remove_battery(battery); - device_remove_file(&battery->bat->dev, &alarm_attr); power_supply_unregister(battery->bat); battery->bat = NULL; mutex_unlock(&battery->sysfs_lock); From 8e665ccc52623889a811b75671b8f25a0bee3b6f Mon Sep 17 00:00:00 2001 From: =?UTF-8?q?Thomas=20Wei=C3=9Fschuh?= Date: Sun, 9 Jun 2024 13:13:28 +0200 Subject: [PATCH 254/342] ACPI: SBS: manage alarm sysfs attribute through psy core MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit [ Upstream commit 6bad28cfc30988a845fb3f59a99f4b8a4ce8fe95 ] Let the power supply core register the attribute. This ensures that the attribute is created before the device is announced to userspace, avoiding a race condition. Signed-off-by: Thomas Weißschuh Signed-off-by: Rafael J. Wysocki Signed-off-by: Sasha Levin --- drivers/acpi/sbs.c | 23 ++++++++++++----------- 1 file changed, 12 insertions(+), 11 deletions(-) diff --git a/drivers/acpi/sbs.c b/drivers/acpi/sbs.c index e6d9f4de2800..54396cb8930a 100644 --- a/drivers/acpi/sbs.c +++ b/drivers/acpi/sbs.c @@ -77,7 +77,6 @@ struct acpi_battery { u16 spec; u8 id; u8 present:1; - u8 have_sysfs_alarm:1; }; #define to_acpi_battery(x) power_supply_get_drvdata(x) @@ -462,12 +461,18 @@ static ssize_t acpi_battery_alarm_store(struct device *dev, return count; } -static const struct device_attribute alarm_attr = { +static struct device_attribute alarm_attr = { .attr = {.name = "alarm", .mode = 0644}, .show = acpi_battery_alarm_show, .store = acpi_battery_alarm_store, }; +static struct attribute *acpi_battery_attrs[] = { + &alarm_attr.attr, + NULL +}; +ATTRIBUTE_GROUPS(acpi_battery); + /* -------------------------------------------------------------------------- Driver Interface -------------------------------------------------------------------------- */ @@ -509,7 +514,10 @@ static int acpi_battery_read(struct acpi_battery *battery) static int acpi_battery_add(struct acpi_sbs *sbs, int id) { struct acpi_battery *battery = &sbs->battery[id]; - struct power_supply_config psy_cfg = { .drv_data = battery, }; + struct power_supply_config psy_cfg = { + .drv_data = battery, + .attr_grp = acpi_battery_groups, + }; int result; battery->id = id; @@ -539,10 +547,6 @@ static int acpi_battery_add(struct acpi_sbs *sbs, int id) goto end; } - result = device_create_file(&battery->bat->dev, &alarm_attr); - if (result) - goto end; - battery->have_sysfs_alarm = 1; end: printk(KERN_INFO PREFIX "%s [%s]: Battery Slot [%s] (battery %s)\n", ACPI_SBS_DEVICE_NAME, acpi_device_bid(sbs->device), @@ -554,11 +558,8 @@ static void acpi_battery_remove(struct acpi_sbs *sbs, int id) { struct acpi_battery *battery = &sbs->battery[id]; - if (battery->bat) { - if (battery->have_sysfs_alarm) - device_remove_file(&battery->bat->dev, &alarm_attr); + if (battery->bat) power_supply_unregister(battery->bat); - } } static int acpi_charger_add(struct acpi_sbs *sbs) From 55985e3aa15a2292d91c794e8839057a32d03cb8 Mon Sep 17 00:00:00 2001 From: Yonghong Song Date: Wed, 5 Jun 2024 13:12:03 -0700 Subject: [PATCH 255/342] selftests/bpf: Fix send_signal test with nested CONFIG_PARAVIRT [ Upstream commit 7015843afcaf68c132784c89528dfddc0005e483 ] Alexei reported that send_signal test may fail with nested CONFIG_PARAVIRT configs. In this particular case, the base VM is AMD with 166 cpus, and I run selftests with regular qemu on top of that and indeed send_signal test failed. I also tried with an Intel box with 80 cpus and there is no issue. The main qemu command line includes: -enable-kvm -smp 16 -cpu host The failure log looks like: $ ./test_progs -t send_signal [ 48.501588] watchdog: BUG: soft lockup - CPU#9 stuck for 26s! [test_progs:2225] [ 48.503622] Modules linked in: bpf_testmod(O) [ 48.503622] CPU: 9 PID: 2225 Comm: test_progs Tainted: G O 6.9.0-08561-g2c1713a8f1c9-dirty #69 [ 48.507629] Hardware name: QEMU Standard PC (i440FX + PIIX, 1996), BIOS rel-1.15.0-0-g2dd4b9b3f840-prebuilt.qemu.org 04/01/2014 [ 48.511635] RIP: 0010:handle_softirqs+0x71/0x290 [ 48.511635] Code: [...] 10 0a 00 00 00 31 c0 65 66 89 05 d5 f4 fa 7e fb bb ff ff ff ff <49> c7 c2 cb [ 48.518527] RSP: 0018:ffffc90000310fa0 EFLAGS: 00000246 [ 48.519579] RAX: 0000000000000000 RBX: 00000000ffffffff RCX: 00000000000006e0 [ 48.522526] RDX: 0000000000000006 RSI: ffff88810791ae80 RDI: 0000000000000000 [ 48.523587] RBP: ffffc90000fabc88 R08: 00000005a0af4f7f R09: 0000000000000000 [ 48.525525] R10: 0000000561d2f29c R11: 0000000000006534 R12: 0000000000000280 [ 48.528525] R13: 0000000000000000 R14: 0000000000000000 R15: 0000000000000000 [ 48.528525] FS: 00007f2f2885cd00(0000) GS:ffff888237c40000(0000) knlGS:0000000000000000 [ 48.531600] CS: 0010 DS: 0000 ES: 0000 CR0: 0000000080050033 [ 48.535520] CR2: 00007f2f287059f0 CR3: 0000000106a28002 CR4: 00000000003706f0 [ 48.537538] Call Trace: [ 48.537538] [ 48.537538] ? watchdog_timer_fn+0x1cd/0x250 [ 48.539590] ? lockup_detector_update_enable+0x50/0x50 [ 48.539590] ? __hrtimer_run_queues+0xff/0x280 [ 48.542520] ? hrtimer_interrupt+0x103/0x230 [ 48.544524] ? __sysvec_apic_timer_interrupt+0x4f/0x140 [ 48.545522] ? sysvec_apic_timer_interrupt+0x3a/0x90 [ 48.547612] ? asm_sysvec_apic_timer_interrupt+0x1a/0x20 [ 48.547612] ? handle_softirqs+0x71/0x290 [ 48.547612] irq_exit_rcu+0x63/0x80 [ 48.551585] sysvec_apic_timer_interrupt+0x75/0x90 [ 48.552521] [ 48.553529] [ 48.553529] asm_sysvec_apic_timer_interrupt+0x1a/0x20 [ 48.555609] RIP: 0010:finish_task_switch.isra.0+0x90/0x260 [ 48.556526] Code: [...] 9f 58 0a 00 00 48 85 db 0f 85 89 01 00 00 4c 89 ff e8 53 d9 bd 00 fb 66 90 <4d> 85 ed 74 [ 48.562524] RSP: 0018:ffffc90000fabd38 EFLAGS: 00000282 [ 48.563589] RAX: 0000000000000000 RBX: 0000000000000000 RCX: ffffffff83385620 [ 48.563589] RDX: ffff888237c73ae4 RSI: 0000000000000000 RDI: ffff888237c6fd00 [ 48.568521] RBP: ffffc90000fabd68 R08: 0000000000000000 R09: 0000000000000000 [ 48.569528] R10: 0000000000000001 R11: 0000000000000000 R12: ffff8881009d0000 [ 48.573525] R13: ffff8881024e5400 R14: ffff88810791ae80 R15: ffff888237c6fd00 [ 48.575614] ? finish_task_switch.isra.0+0x8d/0x260 [ 48.576523] __schedule+0x364/0xac0 [ 48.577535] schedule+0x2e/0x110 [ 48.578555] pipe_read+0x301/0x400 [ 48.579589] ? destroy_sched_domains_rcu+0x30/0x30 [ 48.579589] vfs_read+0x2b3/0x2f0 [ 48.579589] ksys_read+0x8b/0xc0 [ 48.583590] do_syscall_64+0x3d/0xc0 [ 48.583590] entry_SYSCALL_64_after_hwframe+0x4b/0x53 [ 48.586525] RIP: 0033:0x7f2f28703fa1 [ 48.587592] Code: [...] 00 00 00 0f 1f 44 00 00 f3 0f 1e fa 80 3d c5 23 14 00 00 74 13 31 c0 0f 05 <48> 3d 00 f0 [ 48.593534] RSP: 002b:00007ffd90f8cf88 EFLAGS: 00000246 ORIG_RAX: 0000000000000000 [ 48.595589] RAX: ffffffffffffffda RBX: 00007ffd90f8d5e8 RCX: 00007f2f28703fa1 [ 48.595589] RDX: 0000000000000001 RSI: 00007ffd90f8cfb0 RDI: 0000000000000006 [ 48.599592] RBP: 00007ffd90f8d2f0 R08: 0000000000000064 R09: 0000000000000000 [ 48.602527] R10: 0000000000000000 R11: 0000000000000246 R12: 0000000000000000 [ 48.603589] R13: 00007ffd90f8d608 R14: 00007f2f288d8000 R15: 0000000000f6bdb0 [ 48.605527] In the test, two processes are communicating through pipe. Further debugging with strace found that the above splat is triggered as read() syscall could not receive the data even if the corresponding write() syscall in another process successfully wrote data into the pipe. The failed subtest is "send_signal_perf". The corresponding perf event has sample_period 1 and config PERF_COUNT_SW_CPU_CLOCK. sample_period 1 means every overflow event will trigger a call to the BPF program. So I suspect this may overwhelm the system. So I increased the sample_period to 100,000 and the test passed. The sample_period 10,000 still has the test failed. In other parts of selftest, e.g., [1], sample_freq is used instead. So I decided to use sample_freq = 1,000 since the test can pass as well. [1] https://lore.kernel.org/bpf/20240604070700.3032142-1-song@kernel.org/ Reported-by: Alexei Starovoitov Signed-off-by: Yonghong Song Signed-off-by: Daniel Borkmann Link: https://lore.kernel.org/bpf/20240605201203.2603846-1-yonghong.song@linux.dev Signed-off-by: Sasha Levin --- tools/testing/selftests/bpf/prog_tests/send_signal.c | 3 ++- 1 file changed, 2 insertions(+), 1 deletion(-) diff --git a/tools/testing/selftests/bpf/prog_tests/send_signal.c b/tools/testing/selftests/bpf/prog_tests/send_signal.c index 75b72c751772..0b6349070824 100644 --- a/tools/testing/selftests/bpf/prog_tests/send_signal.c +++ b/tools/testing/selftests/bpf/prog_tests/send_signal.c @@ -155,7 +155,8 @@ static void test_send_signal_tracepoint(bool signal_thread) static void test_send_signal_perf(bool signal_thread) { struct perf_event_attr attr = { - .sample_period = 1, + .freq = 1, + .sample_freq = 1000, .type = PERF_TYPE_SOFTWARE, .config = PERF_COUNT_SW_CPU_CLOCK, }; From 65b982b9af547040256a73badf02c9ebe08df613 Mon Sep 17 00:00:00 2001 From: FUJITA Tomonori Date: Mon, 24 Jun 2024 08:55:01 +0900 Subject: [PATCH 256/342] PCI: Add Edimax Vendor ID to pci_ids.h [ Upstream commit eee5528890d54b22b46f833002355a5ee94c3bb4 ] Add the Edimax Vendor ID (0x1432) for an ethernet driver for Tehuti Networks TN40xx chips. This ID can be used for Realtek 8180 and Ralink rt28xx wireless drivers. Signed-off-by: FUJITA Tomonori Acked-by: Bjorn Helgaas Link: https://patch.msgid.link/20240623235507.108147-2-fujita.tomonori@gmail.com Signed-off-by: Jakub Kicinski Signed-off-by: Sasha Levin --- include/linux/pci_ids.h | 2 ++ 1 file changed, 2 insertions(+) diff --git a/include/linux/pci_ids.h b/include/linux/pci_ids.h index 80744a7b5e33..b2418bfda4a9 100644 --- a/include/linux/pci_ids.h +++ b/include/linux/pci_ids.h @@ -2137,6 +2137,8 @@ #define PCI_VENDOR_ID_CHELSIO 0x1425 +#define PCI_VENDOR_ID_EDIMAX 0x1432 + #define PCI_VENDOR_ID_ADLINK 0x144a #define PCI_VENDOR_ID_SAMSUNG 0x144d From 934f815345c09c290a9b9a9cfdddc203ec2117e8 Mon Sep 17 00:00:00 2001 From: Roman Smirnov Date: Thu, 20 Jun 2024 10:24:13 +0300 Subject: [PATCH 257/342] udf: prevent integer overflow in udf_bitmap_free_blocks() [ Upstream commit 56e69e59751d20993f243fb7dd6991c4e522424c ] An overflow may occur if the function is called with the last block and an offset greater than zero. It is necessary to add a check to avoid this. Found by Linux Verification Center (linuxtesting.org) with Svace. [JK: Make test cover also unalloc table freeing] Link: https://patch.msgid.link/20240620072413.7448-1-r.smirnov@omp.ru Suggested-by: Jan Kara Signed-off-by: Roman Smirnov Signed-off-by: Jan Kara Signed-off-by: Sasha Levin --- fs/udf/balloc.c | 36 +++++++++++++----------------------- 1 file changed, 13 insertions(+), 23 deletions(-) diff --git a/fs/udf/balloc.c b/fs/udf/balloc.c index c4c18eeacb60..aa73ab1b50a5 100644 --- a/fs/udf/balloc.c +++ b/fs/udf/balloc.c @@ -22,6 +22,7 @@ #include "udfdecl.h" #include +#include #include "udf_i.h" #include "udf_sb.h" @@ -144,7 +145,6 @@ static void udf_bitmap_free_blocks(struct super_block *sb, { struct udf_sb_info *sbi = UDF_SB(sb); struct buffer_head *bh = NULL; - struct udf_part_map *partmap; unsigned long block; unsigned long block_group; unsigned long bit; @@ -153,19 +153,9 @@ static void udf_bitmap_free_blocks(struct super_block *sb, unsigned long overflow; mutex_lock(&sbi->s_alloc_mutex); - partmap = &sbi->s_partmaps[bloc->partitionReferenceNum]; - if (bloc->logicalBlockNum + count < count || - (bloc->logicalBlockNum + count) > partmap->s_partition_len) { - udf_debug("%u < %d || %u + %u > %u\n", - bloc->logicalBlockNum, 0, - bloc->logicalBlockNum, count, - partmap->s_partition_len); - goto error_return; - } - + /* We make sure this cannot overflow when mounting the filesystem */ block = bloc->logicalBlockNum + offset + (sizeof(struct spaceBitmapDesc) << 3); - do { overflow = 0; block_group = block >> (sb->s_blocksize_bits + 3); @@ -395,7 +385,6 @@ static void udf_table_free_blocks(struct super_block *sb, uint32_t count) { struct udf_sb_info *sbi = UDF_SB(sb); - struct udf_part_map *partmap; uint32_t start, end; uint32_t elen; struct kernel_lb_addr eloc; @@ -404,16 +393,6 @@ static void udf_table_free_blocks(struct super_block *sb, struct udf_inode_info *iinfo; mutex_lock(&sbi->s_alloc_mutex); - partmap = &sbi->s_partmaps[bloc->partitionReferenceNum]; - if (bloc->logicalBlockNum + count < count || - (bloc->logicalBlockNum + count) > partmap->s_partition_len) { - udf_debug("%u < %d || %u + %u > %u\n", - bloc->logicalBlockNum, 0, - bloc->logicalBlockNum, count, - partmap->s_partition_len); - goto error_return; - } - iinfo = UDF_I(table); udf_add_free_space(sb, sbi->s_partition, count); @@ -688,6 +667,17 @@ void udf_free_blocks(struct super_block *sb, struct inode *inode, { uint16_t partition = bloc->partitionReferenceNum; struct udf_part_map *map = &UDF_SB(sb)->s_partmaps[partition]; + uint32_t blk; + + if (check_add_overflow(bloc->logicalBlockNum, offset, &blk) || + check_add_overflow(blk, count, &blk) || + bloc->logicalBlockNum + count > map->s_partition_len) { + udf_debug("Invalid request to free blocks: (%d, %u), off %u, " + "len %u, partition len %u\n", + partition, bloc->logicalBlockNum, offset, count, + map->s_partition_len); + return; + } if (map->s_partition_flags & UDF_PART_FLAG_UNALLOC_BITMAP) { udf_bitmap_free_blocks(sb, map->s_uspace.s_bitmap, From 29ce18d7672f0370cfcdee67b0aa940cc27ea26d Mon Sep 17 00:00:00 2001 From: Johannes Berg Date: Thu, 27 Jun 2024 10:44:11 +0200 Subject: [PATCH 258/342] wifi: nl80211: don't give key data to userspace [ Upstream commit a7e5793035792cc46a1a4b0a783655ffa897dfe9 ] When a key is requested by userspace, there's really no need to include the key data, the sequence counter is really what userspace needs in this case. The fact that it's included is just a historic quirk. Remove the key data. Reviewed-by: Miriam Rachel Korenblit Link: https://patch.msgid.link/20240627104411.b6a4f097e4ea.I7e6cc976cb9e8a80ef25a3351330f313373b4578@changeid Signed-off-by: Johannes Berg Signed-off-by: Sasha Levin --- net/wireless/nl80211.c | 10 ++-------- 1 file changed, 2 insertions(+), 8 deletions(-) diff --git a/net/wireless/nl80211.c b/net/wireless/nl80211.c index 846e40dc00bb..f9ad7de710cb 100644 --- a/net/wireless/nl80211.c +++ b/net/wireless/nl80211.c @@ -3968,10 +3968,7 @@ static void get_key_callback(void *c, struct key_params *params) struct nlattr *key; struct get_key_cookie *cookie = c; - if ((params->key && - nla_put(cookie->msg, NL80211_ATTR_KEY_DATA, - params->key_len, params->key)) || - (params->seq && + if ((params->seq && nla_put(cookie->msg, NL80211_ATTR_KEY_SEQ, params->seq_len, params->seq)) || (params->cipher && @@ -3983,10 +3980,7 @@ static void get_key_callback(void *c, struct key_params *params) if (!key) goto nla_put_failure; - if ((params->key && - nla_put(cookie->msg, NL80211_KEY_DATA, - params->key_len, params->key)) || - (params->seq && + if ((params->seq && nla_put(cookie->msg, NL80211_KEY_SEQ, params->seq_len, params->seq)) || (params->cipher && From 1d4e65fa623941a1b176f018053975d7fe24ee6d Mon Sep 17 00:00:00 2001 From: Filipe Manana Date: Wed, 3 Jul 2024 15:40:59 +0100 Subject: [PATCH 259/342] btrfs: fix bitmap leak when loading free space cache on duplicate entry [ Upstream commit 320d8dc612660da84c3b70a28658bb38069e5a9a ] If we failed to link a free space entry because there's already a conflicting entry for the same offset, we free the free space entry but we don't free the associated bitmap that we had just allocated before. Fix that by freeing the bitmap before freeing the entry. Reviewed-by: Johannes Thumshirn Signed-off-by: Filipe Manana Reviewed-by: David Sterba Signed-off-by: David Sterba Signed-off-by: Sasha Levin --- fs/btrfs/free-space-cache.c | 1 + 1 file changed, 1 insertion(+) diff --git a/fs/btrfs/free-space-cache.c b/fs/btrfs/free-space-cache.c index 4989c60b1df9..af52c9e005b3 100644 --- a/fs/btrfs/free-space-cache.c +++ b/fs/btrfs/free-space-cache.c @@ -798,6 +798,7 @@ static int __load_free_space_cache(struct btrfs_root *root, struct inode *inode, spin_unlock(&ctl->tree_lock); btrfs_err(fs_info, "Duplicate entries in free space cache, dumping"); + kmem_cache_free(btrfs_free_space_bitmap_cachep, e->bitmap); kmem_cache_free(btrfs_free_space_cachep, e); goto free_cache; } From d81c1eeb333d84b3012a91c0500189dc1d71e46c Mon Sep 17 00:00:00 2001 From: Ma Jun Date: Sat, 11 May 2024 15:48:02 +0800 Subject: [PATCH 260/342] drm/amdgpu: Fix the null pointer dereference to ras_manager [ Upstream commit 4c11d30c95576937c6c35e6f29884761f2dddb43 ] Check ras_manager before using it Signed-off-by: Ma Jun Reviewed-by: Lijo Lazar Signed-off-by: Alex Deucher Signed-off-by: Sasha Levin --- drivers/gpu/drm/amd/amdgpu/amdgpu_ras.c | 7 +++++-- 1 file changed, 5 insertions(+), 2 deletions(-) diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_ras.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_ras.c index e971d2b9e3c0..56f10679a26d 100644 --- a/drivers/gpu/drm/amd/amdgpu/amdgpu_ras.c +++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_ras.c @@ -1351,12 +1351,15 @@ static void amdgpu_ras_interrupt_process_handler(struct work_struct *work) int amdgpu_ras_interrupt_dispatch(struct amdgpu_device *adev, struct ras_dispatch_if *info) { - struct ras_manager *obj = amdgpu_ras_find_obj(adev, &info->head); - struct ras_ih_data *data = &obj->ih_data; + struct ras_manager *obj; + struct ras_ih_data *data; + obj = amdgpu_ras_find_obj(adev, &info->head); if (!obj) return -EINVAL; + data = &obj->ih_data; + if (data->inuse == 0) return 0; From c1749313f35b98e2e655479f037db37f19756622 Mon Sep 17 00:00:00 2001 From: Ma Jun Date: Thu, 9 May 2024 15:51:35 +0800 Subject: [PATCH 261/342] drm/amdgpu/pm: Fix the null pointer dereference in apply_state_adjust_rules [ Upstream commit d19fb10085a49b77578314f69fff21562f7cd054 ] Check the pointer value to fix potential null pointer dereference Acked-by: Yang Wang Signed-off-by: Ma Jun Signed-off-by: Alex Deucher Signed-off-by: Sasha Levin --- .../gpu/drm/amd/pm/powerplay/hwmgr/smu7_hwmgr.c | 7 +++++-- .../gpu/drm/amd/pm/powerplay/hwmgr/smu8_hwmgr.c | 14 ++++++++------ .../gpu/drm/amd/pm/powerplay/hwmgr/vega10_hwmgr.c | 7 +++++-- 3 files changed, 18 insertions(+), 10 deletions(-) diff --git a/drivers/gpu/drm/amd/pm/powerplay/hwmgr/smu7_hwmgr.c b/drivers/gpu/drm/amd/pm/powerplay/hwmgr/smu7_hwmgr.c index 7931528bc864..5e72b7555eda 100644 --- a/drivers/gpu/drm/amd/pm/powerplay/hwmgr/smu7_hwmgr.c +++ b/drivers/gpu/drm/amd/pm/powerplay/hwmgr/smu7_hwmgr.c @@ -2983,8 +2983,7 @@ static int smu7_apply_state_adjust_rules(struct pp_hwmgr *hwmgr, const struct pp_power_state *current_ps) { struct amdgpu_device *adev = hwmgr->adev; - struct smu7_power_state *smu7_ps = - cast_phw_smu7_power_state(&request_ps->hardware); + struct smu7_power_state *smu7_ps; uint32_t sclk; uint32_t mclk; struct PP_Clocks minimum_clocks = {0}; @@ -2998,6 +2997,10 @@ static int smu7_apply_state_adjust_rules(struct pp_hwmgr *hwmgr, int32_t count; int32_t stable_pstate_sclk = 0, stable_pstate_mclk = 0; + smu7_ps = cast_phw_smu7_power_state(&request_ps->hardware); + if (!smu7_ps) + return -EINVAL; + data->battery_state = (PP_StateUILabel_Battery == request_ps->classification.ui_label); diff --git a/drivers/gpu/drm/amd/pm/powerplay/hwmgr/smu8_hwmgr.c b/drivers/gpu/drm/amd/pm/powerplay/hwmgr/smu8_hwmgr.c index 35ed47ebaf09..35d0ff57a596 100644 --- a/drivers/gpu/drm/amd/pm/powerplay/hwmgr/smu8_hwmgr.c +++ b/drivers/gpu/drm/amd/pm/powerplay/hwmgr/smu8_hwmgr.c @@ -1051,16 +1051,18 @@ static int smu8_apply_state_adjust_rules(struct pp_hwmgr *hwmgr, struct pp_power_state *prequest_ps, const struct pp_power_state *pcurrent_ps) { - struct smu8_power_state *smu8_ps = - cast_smu8_power_state(&prequest_ps->hardware); - - const struct smu8_power_state *smu8_current_ps = - cast_const_smu8_power_state(&pcurrent_ps->hardware); - + struct smu8_power_state *smu8_ps; + const struct smu8_power_state *smu8_current_ps; struct smu8_hwmgr *data = hwmgr->backend; struct PP_Clocks clocks = {0, 0, 0, 0}; bool force_high; + smu8_ps = cast_smu8_power_state(&prequest_ps->hardware); + smu8_current_ps = cast_const_smu8_power_state(&pcurrent_ps->hardware); + + if (!smu8_ps || !smu8_current_ps) + return -EINVAL; + smu8_ps->need_dfs_bypass = true; data->battery_state = (PP_StateUILabel_Battery == prequest_ps->classification.ui_label); diff --git a/drivers/gpu/drm/amd/pm/powerplay/hwmgr/vega10_hwmgr.c b/drivers/gpu/drm/amd/pm/powerplay/hwmgr/vega10_hwmgr.c index 4dc27ec4d012..10678b519995 100644 --- a/drivers/gpu/drm/amd/pm/powerplay/hwmgr/vega10_hwmgr.c +++ b/drivers/gpu/drm/amd/pm/powerplay/hwmgr/vega10_hwmgr.c @@ -3232,8 +3232,7 @@ static int vega10_apply_state_adjust_rules(struct pp_hwmgr *hwmgr, const struct pp_power_state *current_ps) { struct amdgpu_device *adev = hwmgr->adev; - struct vega10_power_state *vega10_ps = - cast_phw_vega10_power_state(&request_ps->hardware); + struct vega10_power_state *vega10_ps; uint32_t sclk; uint32_t mclk; struct PP_Clocks minimum_clocks = {0}; @@ -3251,6 +3250,10 @@ static int vega10_apply_state_adjust_rules(struct pp_hwmgr *hwmgr, uint32_t stable_pstate_sclk = 0, stable_pstate_mclk = 0; uint32_t latency; + vega10_ps = cast_phw_vega10_power_state(&request_ps->hardware); + if (!vega10_ps) + return -EINVAL; + data->battery_state = (PP_StateUILabel_Battery == request_ps->classification.ui_label); From de305abd36eba9198021d9e53b53786468b9d4b7 Mon Sep 17 00:00:00 2001 From: Ricardo Ribalda Date: Sat, 23 Mar 2024 10:48:03 +0000 Subject: [PATCH 262/342] media: uvcvideo: Ignore empty TS packets [ Upstream commit 5cd7c25f6f0576073b3d03bc4cfb1e8ca63a1195 ] Some SunplusIT cameras took a borderline interpretation of the UVC 1.5 standard, and fill the PTS and SCR fields with invalid data if the package does not contain data. "STC must be captured when the first video data of a video frame is put on the USB bus." Some SunplusIT devices send, e.g., buffer: 0xa7755c00 len 000012 header:0x8c stc 00000000 sof 0000 pts 00000000 buffer: 0xa7755c00 len 000012 header:0x8c stc 00000000 sof 0000 pts 00000000 buffer: 0xa7755c00 len 000668 header:0x8c stc 73779dba sof 070c pts 7376d37a While the UVC specification meant that the first two packets shouldn't have had the SCR bit set in the header. This borderline/buggy interpretation has been implemented in a variety of devices, from directly SunplusIT and from other OEMs that rebrand SunplusIT products. So quirking based on VID:PID will be problematic. All the affected modules have the following extension unit: VideoControl Interface Descriptor: guidExtensionCode {82066163-7050-ab49-b8cc-b3855e8d221d} But the vendor plans to use that GUID in the future and fix the bug, this means that we should use heuristic to figure out the broken packets. This patch takes care of this. lsusb of one of the affected cameras: Bus 001 Device 003: ID 1bcf:2a01 Sunplus Innovation Technology Inc. Device Descriptor: bLength 18 bDescriptorType 1 bcdUSB 2.01 bDeviceClass 239 Miscellaneous Device bDeviceSubClass 2 ? bDeviceProtocol 1 Interface Association bMaxPacketSize0 64 idVendor 0x1bcf Sunplus Innovation Technology Inc. idProduct 0x2a01 bcdDevice 0.02 iManufacturer 1 SunplusIT Inc iProduct 2 HanChen Wise Camera iSerial 3 01.00.00 bNumConfigurations 1 Tested-by: HungNien Chen Reviewed-by: Sergey Senozhatsky Reviewed-by: Laurent Pinchart Signed-off-by: Ricardo Ribalda Reviewed-by: Tomasz Figa Link: https://lore.kernel.org/r/20240323-resend-hwtimestamp-v10-2-b08e590d97c7@chromium.org Signed-off-by: Laurent Pinchart Signed-off-by: Sasha Levin --- drivers/media/usb/uvc/uvc_video.c | 31 ++++++++++++++++++++++++++++++- 1 file changed, 30 insertions(+), 1 deletion(-) diff --git a/drivers/media/usb/uvc/uvc_video.c b/drivers/media/usb/uvc/uvc_video.c index 03dfe96bceba..9a4c730943a9 100644 --- a/drivers/media/usb/uvc/uvc_video.c +++ b/drivers/media/usb/uvc/uvc_video.c @@ -468,6 +468,7 @@ uvc_video_clock_decode(struct uvc_streaming *stream, struct uvc_buffer *buf, ktime_t time; u16 host_sof; u16 dev_sof; + u32 dev_stc; switch (data[1] & (UVC_STREAM_PTS | UVC_STREAM_SCR)) { case UVC_STREAM_PTS | UVC_STREAM_SCR: @@ -512,6 +513,34 @@ uvc_video_clock_decode(struct uvc_streaming *stream, struct uvc_buffer *buf, if (dev_sof == stream->clock.last_sof) return; + dev_stc = get_unaligned_le32(&data[header_size - 6]); + + /* + * STC (Source Time Clock) is the clock used by the camera. The UVC 1.5 + * standard states that it "must be captured when the first video data + * of a video frame is put on the USB bus". This is generally understood + * as requiring devices to clear the payload header's SCR bit before + * the first packet containing video data. + * + * Most vendors follow that interpretation, but some (namely SunplusIT + * on some devices) always set the `UVC_STREAM_SCR` bit, fill the SCR + * field with 0's,and expect that the driver only processes the SCR if + * there is data in the packet. + * + * Ignore all the hardware timestamp information if we haven't received + * any data for this frame yet, the packet contains no data, and both + * STC and SOF are zero. This heuristics should be safe on compliant + * devices. This should be safe with compliant devices, as in the very + * unlikely case where a UVC 1.1 device would send timing information + * only before the first packet containing data, and both STC and SOF + * happen to be zero for a particular frame, we would only miss one + * clock sample from many and the clock recovery algorithm wouldn't + * suffer from this condition. + */ + if (buf && buf->bytesused == 0 && len == header_size && + dev_stc == 0 && dev_sof == 0) + return; + stream->clock.last_sof = dev_sof; host_sof = usb_get_current_frame_number(stream->dev->udev); @@ -549,7 +578,7 @@ uvc_video_clock_decode(struct uvc_streaming *stream, struct uvc_buffer *buf, spin_lock_irqsave(&stream->clock.lock, flags); sample = &stream->clock.samples[stream->clock.head]; - sample->dev_stc = get_unaligned_le32(&data[header_size - 6]); + sample->dev_stc = dev_stc; sample->dev_sof = dev_sof; sample->host_sof = host_sof; sample->host_time = time; From e48a901ce65fc2f3edca4c90bfe3ab7706a3f6b7 Mon Sep 17 00:00:00 2001 From: Michal Pecio Date: Sun, 14 Apr 2024 19:00:40 +0200 Subject: [PATCH 263/342] media: uvcvideo: Fix the bandwdith quirk on USB 3.x [ Upstream commit 9e3d55fbd160b3ca376599a68b4cddfdc67d4153 ] The bandwidth fixup quirk doesn't know that SuperSpeed exists and has the same 8 service intervals per millisecond as High Speed, hence its calculations are wrong. Assume that all speeds from HS up use 8 intervals per millisecond. No further changes are needed, updated code has been confirmed to work with all speeds from FS to SS. Signed-off-by: Michal Pecio Reviewed-by: Ricardo Ribalda Reviewed-by: Laurent Pinchart Link: https://lore.kernel.org/r/20240414190040.2255a0bc@foxbook Signed-off-by: Laurent Pinchart Signed-off-by: Sasha Levin --- drivers/media/usb/uvc/uvc_video.c | 6 +++--- 1 file changed, 3 insertions(+), 3 deletions(-) diff --git a/drivers/media/usb/uvc/uvc_video.c b/drivers/media/usb/uvc/uvc_video.c index 9a4c730943a9..288f097e2e6f 100644 --- a/drivers/media/usb/uvc/uvc_video.c +++ b/drivers/media/usb/uvc/uvc_video.c @@ -207,13 +207,13 @@ static void uvc_fixup_video_ctrl(struct uvc_streaming *stream, /* Compute a bandwidth estimation by multiplying the frame * size by the number of video frames per second, divide the * result by the number of USB frames (or micro-frames for - * high-speed devices) per second and add the UVC header size - * (assumed to be 12 bytes long). + * high- and super-speed devices) per second and add the UVC + * header size (assumed to be 12 bytes long). */ bandwidth = frame->wWidth * frame->wHeight / 8 * format->bpp; bandwidth *= 10000000 / interval + 1; bandwidth /= 1000; - if (stream->dev->udev->speed == USB_SPEED_HIGH) + if (stream->dev->udev->speed >= USB_SPEED_HIGH) bandwidth /= 8; bandwidth += 12; From 1a6b4240b0b900e451f7f4b44a256b67d7f6cb3f Mon Sep 17 00:00:00 2001 From: Kemeng Shi Date: Tue, 14 May 2024 19:24:30 +0800 Subject: [PATCH 264/342] jbd2: avoid memleak in jbd2_journal_write_metadata_buffer [ Upstream commit cc102aa24638b90e04364d64e4f58a1fa91a1976 ] The new_bh is from alloc_buffer_head, we should call free_buffer_head to free it in error case. Signed-off-by: Kemeng Shi Reviewed-by: Zhang Yi Reviewed-by: Jan Kara Link: https://patch.msgid.link/20240514112438.1269037-2-shikemeng@huaweicloud.com Signed-off-by: Theodore Ts'o Signed-off-by: Sasha Levin --- fs/jbd2/journal.c | 1 + 1 file changed, 1 insertion(+) diff --git a/fs/jbd2/journal.c b/fs/jbd2/journal.c index 4ae4b85ea187..205e6c7c2fd0 100644 --- a/fs/jbd2/journal.c +++ b/fs/jbd2/journal.c @@ -412,6 +412,7 @@ int jbd2_journal_write_metadata_buffer(transaction_t *transaction, tmp = jbd2_alloc(bh_in->b_size, GFP_NOFS); if (!tmp) { brelse(new_bh); + free_buffer_head(new_bh); return -ENOMEM; } spin_lock(&jh_in->b_state_lock); From a3e52a4c22c846858a6875e1c280030a3849e148 Mon Sep 17 00:00:00 2001 From: Peter Oberparleiter Date: Thu, 20 Jun 2024 14:20:27 +0200 Subject: [PATCH 265/342] s390/sclp: Prevent release of buffer in I/O [ Upstream commit bf365071ea92b9579d5a272679b74052a5643e35 ] When a task waiting for completion of a Store Data operation is interrupted, an attempt is made to halt this operation. If this attempt fails due to a hardware or firmware problem, there is a chance that the SCLP facility might store data into buffers referenced by the original operation at a later time. Handle this situation by not releasing the referenced data buffers if the halt attempt fails. For current use cases, this might result in a leak of few pages of memory in case of a rare hardware/firmware malfunction. Reviewed-by: Heiko Carstens Signed-off-by: Peter Oberparleiter Signed-off-by: Alexander Gordeev Signed-off-by: Sasha Levin --- drivers/s390/char/sclp_sd.c | 10 ++++++++-- 1 file changed, 8 insertions(+), 2 deletions(-) diff --git a/drivers/s390/char/sclp_sd.c b/drivers/s390/char/sclp_sd.c index 1e244f78f192..64581433c334 100644 --- a/drivers/s390/char/sclp_sd.c +++ b/drivers/s390/char/sclp_sd.c @@ -319,8 +319,14 @@ static int sclp_sd_store_data(struct sclp_sd_data *result, u8 di) &esize); if (rc) { /* Cancel running request if interrupted */ - if (rc == -ERESTARTSYS) - sclp_sd_sync(page, SD_EQ_HALT, di, 0, 0, NULL, NULL); + if (rc == -ERESTARTSYS) { + if (sclp_sd_sync(page, SD_EQ_HALT, di, 0, 0, NULL, NULL)) { + pr_warn("Could not stop Store Data request - leaking at least %zu bytes\n", + (size_t)dsize * PAGE_SIZE); + data = NULL; + asce = 0; + } + } vfree(data); goto out; } From 3b2b169fadd89c5f3ab8abf94e0dda83d84026db Mon Sep 17 00:00:00 2001 From: Benjamin Coddington Date: Wed, 17 Jul 2024 10:49:33 -0400 Subject: [PATCH 266/342] SUNRPC: Fix a race to wake a sync task [ Upstream commit ed0172af5d6fc07d1b40ca82f5ca3979300369f7 ] We've observed NFS clients with sync tasks sleeping in __rpc_execute waiting on RPC_TASK_QUEUED that have not responded to a wake-up from rpc_make_runnable(). I suspect this problem usually goes unnoticed, because on a busy client the task will eventually be re-awoken by another task completion or xprt event. However, if the state manager is draining the slot table, a sync task missing a wake-up can result in a hung client. We've been able to prove that the waker in rpc_make_runnable() successfully calls wake_up_bit() (ie- there's no race to tk_runstate), but the wake_up_bit() call fails to wake the waiter. I suspect the waker is missing the load of the bit's wait_queue_head, so waitqueue_active() is false. There are some very helpful comments about this problem above wake_up_bit(), prepare_to_wait(), and waitqueue_active(). Fix this by inserting smp_mb__after_atomic() before the wake_up_bit(), which pairs with prepare_to_wait() calling set_current_state(). Signed-off-by: Benjamin Coddington Reviewed-by: Jeff Layton Signed-off-by: Anna Schumaker Signed-off-by: Sasha Levin --- net/sunrpc/sched.c | 4 +++- 1 file changed, 3 insertions(+), 1 deletion(-) diff --git a/net/sunrpc/sched.c b/net/sunrpc/sched.c index a4c9d410eb8d..f4b1b7fee2c0 100644 --- a/net/sunrpc/sched.c +++ b/net/sunrpc/sched.c @@ -348,8 +348,10 @@ static void rpc_make_runnable(struct workqueue_struct *wq, if (RPC_IS_ASYNC(task)) { INIT_WORK(&task->u.tk_work, rpc_async_schedule); queue_work(wq, &task->u.tk_work); - } else + } else { + smp_mb__after_atomic(); wake_up_bit(&task->tk_runstate, RPC_TASK_QUEUED); + } } /* From 1d21d4175054413d7fc8eefbd071c2b133c2afe5 Mon Sep 17 00:00:00 2001 From: Zheng Zucheng Date: Fri, 26 Jul 2024 02:32:35 +0000 Subject: [PATCH 267/342] sched/cputime: Fix mul_u64_u64_div_u64() precision for cputime commit 77baa5bafcbe1b2a15ef9c37232c21279c95481c upstream. In extreme test scenarios: the 14th field utime in /proc/xx/stat is greater than sum_exec_runtime, utime = 18446744073709518790 ns, rtime = 135989749728000 ns In cputime_adjust() process, stime is greater than rtime due to mul_u64_u64_div_u64() precision problem. before call mul_u64_u64_div_u64(), stime = 175136586720000, rtime = 135989749728000, utime = 1416780000. after call mul_u64_u64_div_u64(), stime = 135989949653530 unsigned reversion occurs because rtime is less than stime. utime = rtime - stime = 135989749728000 - 135989949653530 = -199925530 = (u64)18446744073709518790 Trigger condition: 1). User task run in kernel mode most of time 2). ARM64 architecture 3). TICK_CPU_ACCOUNTING=y CONFIG_VIRT_CPU_ACCOUNTING_NATIVE is not set Fix mul_u64_u64_div_u64() conversion precision by reset stime to rtime Fixes: 3dc167ba5729 ("sched/cputime: Improve cputime_adjust()") Signed-off-by: Zheng Zucheng Signed-off-by: Peter Zijlstra (Intel) Cc: Link: https://lkml.kernel.org/r/20240726023235.217771-1-zhengzucheng@huawei.com Signed-off-by: Greg Kroah-Hartman --- kernel/sched/cputime.c | 6 ++++++ 1 file changed, 6 insertions(+) diff --git a/kernel/sched/cputime.c b/kernel/sched/cputime.c index ca0eef7d3852..f03b3af2fb79 100644 --- a/kernel/sched/cputime.c +++ b/kernel/sched/cputime.c @@ -579,6 +579,12 @@ void cputime_adjust(struct task_cputime *curr, struct prev_cputime *prev, } stime = mul_u64_u64_div_u64(stime, rtime, stime + utime); + /* + * Because mul_u64_u64_div_u64() can approximate on some + * achitectures; enforce the constraint that: a*b/(b+c) <= a. + */ + if (unlikely(stime > rtime)) + stime = rtime; update: /* From 69299a4282a3ed5b5a2db72bec8447581ce3270a Mon Sep 17 00:00:00 2001 From: Kemeng Shi Date: Sat, 3 Jun 2023 23:03:11 +0800 Subject: [PATCH 268/342] ext4: fix wrong unit use in ext4_mb_find_by_goal [ Upstream commit 99c515e3a860576ba90c11acbc1d6488dfca6463 ] We need start in block unit while fe_start is in cluster unit. Use ext4_grp_offs_to_block helper to convert fe_start to get start in block unit. Signed-off-by: Kemeng Shi Reviewed-by: Ojaswin Mujoo Link: https://lore.kernel.org/r/20230603150327.3596033-4-shikemeng@huaweicloud.com Signed-off-by: Theodore Ts'o Signed-off-by: Sasha Levin --- fs/ext4/mballoc.c | 3 +-- 1 file changed, 1 insertion(+), 2 deletions(-) diff --git a/fs/ext4/mballoc.c b/fs/ext4/mballoc.c index 87378d08a414..bc5db22df9fe 100644 --- a/fs/ext4/mballoc.c +++ b/fs/ext4/mballoc.c @@ -1927,8 +1927,7 @@ int ext4_mb_find_by_goal(struct ext4_allocation_context *ac, if (max >= ac->ac_g_ex.fe_len && ac->ac_g_ex.fe_len == sbi->s_stripe) { ext4_fsblk_t start; - start = ext4_group_first_block_no(ac->ac_sb, e4b->bd_group) + - ex.fe_start; + start = ext4_grp_offs_to_block(ac->ac_sb, &ex); /* use do_div to get remainder (would be 64-bit modulo) */ if (do_div(start, sbi->s_stripe) == 0) { ac->ac_found++; From 5b9ae6bb33601677ed7e07da5c40e042b400e3f9 Mon Sep 17 00:00:00 2001 From: James Morse Date: Fri, 9 Aug 2024 11:17:27 +0100 Subject: [PATCH 269/342] arm64: cpufeature: Force HWCAP to be based on the sysreg visible to user-space [ Upstream commit 237405ebef580a7352a52129b2465c117145eafa ] arm64 advertises hardware features to user-space via HWCAPs, and by emulating access to the CPUs id registers. The cpufeature code has a sanitised system-wide view of an id register, and a sanitised user-space view of an id register, where some features use their 'safe' value instead of the hardware value. It is currently possible for a HWCAP to be advertised where the user-space view of the id register does not show the feature as supported. Erratum workaround need to remove both the HWCAP, and the feature from the user-space view of the id register. This involves duplicating the code, and spreading it over cpufeature.c and cpu_errata.c. Make the HWCAP code use the user-space view of id registers. This ensures the values never diverge, and allows erratum workaround to remove HWCAP by modifying the user-space view of the id register. Signed-off-by: James Morse Reviewed-by: Suzuki K Poulose Link: https://lore.kernel.org/r/20220909165938.3931307-2-james.morse@arm.com Signed-off-by: Catalin Marinas [ Mark: fixup lack of 'width' parameter ] Signed-off-by: Mark Rutland Signed-off-by: Sasha Levin --- arch/arm64/kernel/cpufeature.c | 40 ++++++++++++++++++++++++++-------- 1 file changed, 31 insertions(+), 9 deletions(-) diff --git a/arch/arm64/kernel/cpufeature.c b/arch/arm64/kernel/cpufeature.c index 1f0a2deafd64..11a42fcf94bf 100644 --- a/arch/arm64/kernel/cpufeature.c +++ b/arch/arm64/kernel/cpufeature.c @@ -1196,17 +1196,39 @@ feature_matches(u64 reg, const struct arm64_cpu_capabilities *entry) return val >= entry->min_field_value; } +static u64 +read_scoped_sysreg(const struct arm64_cpu_capabilities *entry, int scope) +{ + WARN_ON(scope == SCOPE_LOCAL_CPU && preemptible()); + if (scope == SCOPE_SYSTEM) + return read_sanitised_ftr_reg(entry->sys_reg); + else + return __read_sysreg_by_encoding(entry->sys_reg); +} + +static bool +has_user_cpuid_feature(const struct arm64_cpu_capabilities *entry, int scope) +{ + int mask; + struct arm64_ftr_reg *regp; + u64 val = read_scoped_sysreg(entry, scope); + + regp = get_arm64_ftr_reg(entry->sys_reg); + if (!regp) + return false; + + mask = cpuid_feature_extract_unsigned_field(regp->user_mask, + entry->field_pos); + if (!mask) + return false; + + return feature_matches(val, entry); +} + static bool has_cpuid_feature(const struct arm64_cpu_capabilities *entry, int scope) { - u64 val; - - WARN_ON(scope == SCOPE_LOCAL_CPU && preemptible()); - if (scope == SCOPE_SYSTEM) - val = read_sanitised_ftr_reg(entry->sys_reg); - else - val = __read_sysreg_by_encoding(entry->sys_reg); - + u64 val = read_scoped_sysreg(entry, scope); return feature_matches(val, entry); } @@ -2172,7 +2194,7 @@ static const struct arm64_cpu_capabilities arm64_features[] = { }; #define HWCAP_CPUID_MATCH(reg, field, s, min_value) \ - .matches = has_cpuid_feature, \ + .matches = has_user_cpuid_feature, \ .sys_reg = reg, \ .field_pos = field, \ .sign = s, \ From 55920e407a7ee0acb50c6c7b97f584abe3d18e33 Mon Sep 17 00:00:00 2001 From: Besar Wicaksono Date: Fri, 9 Aug 2024 11:17:28 +0100 Subject: [PATCH 270/342] arm64: Add Neoverse-V2 part [ Upstream commit f4d9d9dcc70b96b5e5d7801bd5fbf8491b07b13d ] Add the part number and MIDR for Neoverse-V2 Signed-off-by: Besar Wicaksono Reviewed-by: James Clark Link: https://lore.kernel.org/r/20240109192310.16234-2-bwicaksono@nvidia.com Signed-off-by: Will Deacon [ Mark: trivial backport ] Signed-off-by: Mark Rutland Signed-off-by: Sasha Levin --- arch/arm64/include/asm/cputype.h | 2 ++ 1 file changed, 2 insertions(+) diff --git a/arch/arm64/include/asm/cputype.h b/arch/arm64/include/asm/cputype.h index c2a1ccd5fd46..b772159a84b9 100644 --- a/arch/arm64/include/asm/cputype.h +++ b/arch/arm64/include/asm/cputype.h @@ -84,6 +84,7 @@ #define ARM_CPU_PART_CORTEX_X2 0xD48 #define ARM_CPU_PART_NEOVERSE_N2 0xD49 #define ARM_CPU_PART_CORTEX_A78C 0xD4B +#define ARM_CPU_PART_NEOVERSE_V2 0xD4F #define APM_CPU_PART_POTENZA 0x000 @@ -136,6 +137,7 @@ #define MIDR_CORTEX_X2 MIDR_CPU_MODEL(ARM_CPU_IMP_ARM, ARM_CPU_PART_CORTEX_X2) #define MIDR_NEOVERSE_N2 MIDR_CPU_MODEL(ARM_CPU_IMP_ARM, ARM_CPU_PART_NEOVERSE_N2) #define MIDR_CORTEX_A78C MIDR_CPU_MODEL(ARM_CPU_IMP_ARM, ARM_CPU_PART_CORTEX_A78C) +#define MIDR_NEOVERSE_V2 MIDR_CPU_MODEL(ARM_CPU_IMP_ARM, ARM_CPU_PART_NEOVERSE_V2) #define MIDR_THUNDERX MIDR_CPU_MODEL(ARM_CPU_IMP_CAVIUM, CAVIUM_CPU_PART_THUNDERX) #define MIDR_THUNDERX_81XX MIDR_CPU_MODEL(ARM_CPU_IMP_CAVIUM, CAVIUM_CPU_PART_THUNDERX_81XX) #define MIDR_THUNDERX_83XX MIDR_CPU_MODEL(ARM_CPU_IMP_CAVIUM, CAVIUM_CPU_PART_THUNDERX_83XX) From c46b7570c9d515ea8a0f18c902f1d99a3ac8b570 Mon Sep 17 00:00:00 2001 From: Mark Rutland Date: Fri, 9 Aug 2024 11:17:29 +0100 Subject: [PATCH 271/342] arm64: cputype: Add Cortex-X4 definitions [ Upstream commit 02a0a04676fa7796d9cbc9eb5ca120aaa194d2dd ] Add cputype definitions for Cortex-X4. These will be used for errata detection in subsequent patches. These values can be found in Table B-249 ("MIDR_EL1 bit descriptions") in issue 0002-05 of the Cortex-X4 TRM, which can be found at: https://developer.arm.com/documentation/102484/0002/?lang=en Signed-off-by: Mark Rutland Cc: Catalin Marinas Cc: James Morse Cc: Will Deacon Link: https://lore.kernel.org/r/20240508081400.235362-3-mark.rutland@arm.com Signed-off-by: Will Deacon [ Mark: fix conflict (dealt with upstream via a later merge) ] Signed-off-by: Mark Rutland Signed-off-by: Sasha Levin --- arch/arm64/include/asm/cputype.h | 2 ++ 1 file changed, 2 insertions(+) diff --git a/arch/arm64/include/asm/cputype.h b/arch/arm64/include/asm/cputype.h index b772159a84b9..a6d1276751dc 100644 --- a/arch/arm64/include/asm/cputype.h +++ b/arch/arm64/include/asm/cputype.h @@ -85,6 +85,7 @@ #define ARM_CPU_PART_NEOVERSE_N2 0xD49 #define ARM_CPU_PART_CORTEX_A78C 0xD4B #define ARM_CPU_PART_NEOVERSE_V2 0xD4F +#define ARM_CPU_PART_CORTEX_X4 0xD82 #define APM_CPU_PART_POTENZA 0x000 @@ -138,6 +139,7 @@ #define MIDR_NEOVERSE_N2 MIDR_CPU_MODEL(ARM_CPU_IMP_ARM, ARM_CPU_PART_NEOVERSE_N2) #define MIDR_CORTEX_A78C MIDR_CPU_MODEL(ARM_CPU_IMP_ARM, ARM_CPU_PART_CORTEX_A78C) #define MIDR_NEOVERSE_V2 MIDR_CPU_MODEL(ARM_CPU_IMP_ARM, ARM_CPU_PART_NEOVERSE_V2) +#define MIDR_CORTEX_X4 MIDR_CPU_MODEL(ARM_CPU_IMP_ARM, ARM_CPU_PART_CORTEX_X4) #define MIDR_THUNDERX MIDR_CPU_MODEL(ARM_CPU_IMP_CAVIUM, CAVIUM_CPU_PART_THUNDERX) #define MIDR_THUNDERX_81XX MIDR_CPU_MODEL(ARM_CPU_IMP_CAVIUM, CAVIUM_CPU_PART_THUNDERX_81XX) #define MIDR_THUNDERX_83XX MIDR_CPU_MODEL(ARM_CPU_IMP_CAVIUM, CAVIUM_CPU_PART_THUNDERX_83XX) From d8029a49c8af1792c4565baf0c3624f39c54ddfc Mon Sep 17 00:00:00 2001 From: Mark Rutland Date: Fri, 9 Aug 2024 11:17:30 +0100 Subject: [PATCH 272/342] arm64: cputype: Add Neoverse-V3 definitions [ Upstream commit 0ce85db6c2141b7ffb95709d76fc55a27ff3cdc1 ] Add cputype definitions for Neoverse-V3. These will be used for errata detection in subsequent patches. These values can be found in Table B-249 ("MIDR_EL1 bit descriptions") in issue 0001-04 of the Neoverse-V3 TRM, which can be found at: https://developer.arm.com/documentation/107734/0001/?lang=en Signed-off-by: Mark Rutland Cc: Catalin Marinas Cc: James Morse Cc: Will Deacon Link: https://lore.kernel.org/r/20240508081400.235362-4-mark.rutland@arm.com Signed-off-by: Will Deacon [ Mark: trivial backport ] Signed-off-by: Mark Rutland Signed-off-by: Sasha Levin --- arch/arm64/include/asm/cputype.h | 2 ++ 1 file changed, 2 insertions(+) diff --git a/arch/arm64/include/asm/cputype.h b/arch/arm64/include/asm/cputype.h index a6d1276751dc..b2887995e575 100644 --- a/arch/arm64/include/asm/cputype.h +++ b/arch/arm64/include/asm/cputype.h @@ -86,6 +86,7 @@ #define ARM_CPU_PART_CORTEX_A78C 0xD4B #define ARM_CPU_PART_NEOVERSE_V2 0xD4F #define ARM_CPU_PART_CORTEX_X4 0xD82 +#define ARM_CPU_PART_NEOVERSE_V3 0xD84 #define APM_CPU_PART_POTENZA 0x000 @@ -140,6 +141,7 @@ #define MIDR_CORTEX_A78C MIDR_CPU_MODEL(ARM_CPU_IMP_ARM, ARM_CPU_PART_CORTEX_A78C) #define MIDR_NEOVERSE_V2 MIDR_CPU_MODEL(ARM_CPU_IMP_ARM, ARM_CPU_PART_NEOVERSE_V2) #define MIDR_CORTEX_X4 MIDR_CPU_MODEL(ARM_CPU_IMP_ARM, ARM_CPU_PART_CORTEX_X4) +#define MIDR_NEOVERSE_V3 MIDR_CPU_MODEL(ARM_CPU_IMP_ARM, ARM_CPU_PART_NEOVERSE_V3) #define MIDR_THUNDERX MIDR_CPU_MODEL(ARM_CPU_IMP_CAVIUM, CAVIUM_CPU_PART_THUNDERX) #define MIDR_THUNDERX_81XX MIDR_CPU_MODEL(ARM_CPU_IMP_CAVIUM, CAVIUM_CPU_PART_THUNDERX_81XX) #define MIDR_THUNDERX_83XX MIDR_CPU_MODEL(ARM_CPU_IMP_CAVIUM, CAVIUM_CPU_PART_THUNDERX_83XX) From 9f7ba007824900638f6cc1367d7c063a07fae93f Mon Sep 17 00:00:00 2001 From: Mark Rutland Date: Fri, 9 Aug 2024 11:17:31 +0100 Subject: [PATCH 273/342] arm64: errata: Add workaround for Arm errata 3194386 and 3312417 [ Upstream commit 7187bb7d0b5c7dfa18ca82e9e5c75e13861b1d88 ] Cortex-X4 and Neoverse-V3 suffer from errata whereby an MSR to the SSBS special-purpose register does not affect subsequent speculative instructions, permitting speculative store bypassing for a window of time. This is described in their Software Developer Errata Notice (SDEN) documents: * Cortex-X4 SDEN v8.0, erratum 3194386: https://developer.arm.com/documentation/SDEN-2432808/0800/ * Neoverse-V3 SDEN v6.0, erratum 3312417: https://developer.arm.com/documentation/SDEN-2891958/0600/ To workaround these errata, it is necessary to place a speculation barrier (SB) after MSR to the SSBS special-purpose register. This patch adds the requisite SB after writes to SSBS within the kernel, and hides the presence of SSBS from EL0 such that userspace software which cares about SSBS will manipulate this via prctl(PR_GET_SPECULATION_CTRL, ...). Signed-off-by: Mark Rutland Cc: Catalin Marinas Cc: James Morse Cc: Will Deacon Link: https://lore.kernel.org/r/20240508081400.235362-5-mark.rutland@arm.com Signed-off-by: Will Deacon [ Mark: fix conflicts & renames, drop unneeded cpucaps.h, fold in user_feature_fixup() ] Signed-off-by: Mark Rutland Signed-off-by: Sasha Levin --- Documentation/arm64/silicon-errata.rst | 4 +++ arch/arm64/Kconfig | 41 ++++++++++++++++++++++++++ arch/arm64/include/asm/cpucaps.h | 3 +- arch/arm64/kernel/cpu_errata.c | 19 ++++++++++++ arch/arm64/kernel/cpufeature.c | 12 ++++++++ arch/arm64/kernel/proton-pack.c | 12 ++++++++ 6 files changed, 90 insertions(+), 1 deletion(-) diff --git a/Documentation/arm64/silicon-errata.rst b/Documentation/arm64/silicon-errata.rst index 10a26d44ef4a..0ecb714b2c42 100644 --- a/Documentation/arm64/silicon-errata.rst +++ b/Documentation/arm64/silicon-errata.rst @@ -98,12 +98,16 @@ stable kernels. +----------------+-----------------+-----------------+-----------------------------+ | ARM | Cortex-A510 | #2457168 | ARM64_ERRATUM_2457168 | +----------------+-----------------+-----------------+-----------------------------+ +| ARM | Cortex-X4 | #3194386 | ARM64_ERRATUM_3194386 | ++----------------+-----------------+-----------------+-----------------------------+ | ARM | Neoverse-N1 | #1188873,1418040| ARM64_ERRATUM_1418040 | +----------------+-----------------+-----------------+-----------------------------+ | ARM | Neoverse-N1 | #1349291 | N/A | +----------------+-----------------+-----------------+-----------------------------+ | ARM | Neoverse-N1 | #1542419 | ARM64_ERRATUM_1542419 | +----------------+-----------------+-----------------+-----------------------------+ +| ARM | Neoverse-V3 | #3312417 | ARM64_ERRATUM_3312417 | ++----------------+-----------------+-----------------+-----------------------------+ | ARM | MMU-500 | #841119,826419 | N/A | +----------------+-----------------+-----------------+-----------------------------+ +----------------+-----------------+-----------------+-----------------------------+ diff --git a/arch/arm64/Kconfig b/arch/arm64/Kconfig index 13cf137da999..0d59e8ab27c8 100644 --- a/arch/arm64/Kconfig +++ b/arch/arm64/Kconfig @@ -691,6 +691,47 @@ config ARM64_ERRATUM_2457168 If unsure, say Y. +config ARM64_WORKAROUND_SPECULATIVE_SSBS + bool + +config ARM64_ERRATUM_3194386 + bool "Cortex-X4: 3194386: workaround for MSR SSBS not self-synchronizing" + select ARM64_WORKAROUND_SPECULATIVE_SSBS + default y + help + This option adds the workaround for ARM Cortex-X4 erratum 3194386. + + On affected cores "MSR SSBS, #0" instructions may not affect + subsequent speculative instructions, which may permit unexepected + speculative store bypassing. + + Work around this problem by placing a speculation barrier after + kernel changes to SSBS. The presence of the SSBS special-purpose + register is hidden from hwcaps and EL0 reads of ID_AA64PFR1_EL1, such + that userspace will use the PR_SPEC_STORE_BYPASS prctl to change + SSBS. + + If unsure, say Y. + +config ARM64_ERRATUM_3312417 + bool "Neoverse-V3: 3312417: workaround for MSR SSBS not self-synchronizing" + select ARM64_WORKAROUND_SPECULATIVE_SSBS + default y + help + This option adds the workaround for ARM Neoverse-V3 erratum 3312417. + + On affected cores "MSR SSBS, #0" instructions may not affect + subsequent speculative instructions, which may permit unexepected + speculative store bypassing. + + Work around this problem by placing a speculation barrier after + kernel changes to SSBS. The presence of the SSBS special-purpose + register is hidden from hwcaps and EL0 reads of ID_AA64PFR1_EL1, such + that userspace will use the PR_SPEC_STORE_BYPASS prctl to change + SSBS. + + If unsure, say Y. + config CAVIUM_ERRATUM_22375 bool "Cavium erratum 22375, 24313" default y diff --git a/arch/arm64/include/asm/cpucaps.h b/arch/arm64/include/asm/cpucaps.h index d2080a41f6e6..931c88182fb8 100644 --- a/arch/arm64/include/asm/cpucaps.h +++ b/arch/arm64/include/asm/cpucaps.h @@ -69,7 +69,8 @@ #define ARM64_SPECTRE_BHB 59 #define ARM64_WORKAROUND_2457168 60 #define ARM64_WORKAROUND_1742098 61 +#define ARM64_WORKAROUND_SPECULATIVE_SSBS 62 -#define ARM64_NCAPS 62 +#define ARM64_NCAPS 63 #endif /* __ASM_CPUCAPS_H */ diff --git a/arch/arm64/kernel/cpu_errata.c b/arch/arm64/kernel/cpu_errata.c index 5d6f19bc628c..3eabd809aee4 100644 --- a/arch/arm64/kernel/cpu_errata.c +++ b/arch/arm64/kernel/cpu_errata.c @@ -364,6 +364,18 @@ static struct midr_range broken_aarch32_aes[] = { }; #endif +#ifdef CONFIG_ARM64_WORKAROUND_SPECULATIVE_SSBS +static const struct midr_range erratum_spec_ssbs_list[] = { +#ifdef CONFIG_ARM64_ERRATUM_3194386 + MIDR_ALL_VERSIONS(MIDR_CORTEX_X4), +#endif +#ifdef CONFIG_ARM64_ERRATUM_3312417 + MIDR_ALL_VERSIONS(MIDR_NEOVERSE_V3), +#endif + {} +}; +#endif + const struct arm64_cpu_capabilities arm64_errata[] = { #ifdef CONFIG_ARM64_WORKAROUND_CLEAN_CACHE { @@ -570,6 +582,13 @@ const struct arm64_cpu_capabilities arm64_errata[] = { CAP_MIDR_RANGE_LIST(broken_aarch32_aes), .type = ARM64_CPUCAP_LOCAL_CPU_ERRATUM, }, +#endif +#ifdef CONFIG_ARM64_WORKAROUND_SPECULATIVE_SSBS + { + .desc = "ARM errata 3194386, 3312417", + .capability = ARM64_WORKAROUND_SPECULATIVE_SSBS, + ERRATA_MIDR_RANGE_LIST(erratum_spec_ssbs_list), + }, #endif { } diff --git a/arch/arm64/kernel/cpufeature.c b/arch/arm64/kernel/cpufeature.c index 11a42fcf94bf..dc92fd590f2f 100644 --- a/arch/arm64/kernel/cpufeature.c +++ b/arch/arm64/kernel/cpufeature.c @@ -1753,6 +1753,17 @@ static void cpu_enable_mte(struct arm64_cpu_capabilities const *cap) } #endif /* CONFIG_ARM64_MTE */ +static void user_feature_fixup(void) +{ + if (cpus_have_cap(ARM64_WORKAROUND_SPECULATIVE_SSBS)) { + struct arm64_ftr_reg *regp; + + regp = get_arm64_ftr_reg(SYS_ID_AA64PFR1_EL1); + if (regp) + regp->user_mask &= ~GENMASK(7, 4); /* SSBS */ + } +} + static void elf_hwcap_fixup(void) { #ifdef CONFIG_ARM64_ERRATUM_1742098 @@ -2764,6 +2775,7 @@ void __init setup_cpu_features(void) u32 cwg; setup_system_capabilities(); + user_feature_fixup(); setup_elf_hwcaps(arm64_elf_hwcaps); if (system_supports_32bit_el0()) { diff --git a/arch/arm64/kernel/proton-pack.c b/arch/arm64/kernel/proton-pack.c index 9c0e9d9eed6e..b40310e0bdb9 100644 --- a/arch/arm64/kernel/proton-pack.c +++ b/arch/arm64/kernel/proton-pack.c @@ -574,6 +574,18 @@ static enum mitigation_state spectre_v4_enable_hw_mitigation(void) /* SCTLR_EL1.DSSBS was initialised to 0 during boot */ asm volatile(SET_PSTATE_SSBS(0)); + + /* + * SSBS is self-synchronizing and is intended to affect subsequent + * speculative instructions, but some CPUs can speculate with a stale + * value of SSBS. + * + * Mitigate this with an unconditional speculation barrier, as CPUs + * could mis-speculate branches and bypass a conditional barrier. + */ + if (IS_ENABLED(CONFIG_ARM64_WORKAROUND_SPECULATIVE_SSBS)) + spec_bar(); + return SPECTRE_MITIGATED; } From b8d683f5b5386d0d5736cf31fc42d3fa0001da63 Mon Sep 17 00:00:00 2001 From: Mark Rutland Date: Fri, 9 Aug 2024 11:17:32 +0100 Subject: [PATCH 274/342] arm64: cputype: Add Cortex-X3 definitions [ Upstream commit be5a6f238700f38b534456608588723fba96c5ab ] Add cputype definitions for Cortex-X3. These will be used for errata detection in subsequent patches. These values can be found in Table A-263 ("MIDR_EL1 bit descriptions") in issue 07 of the Cortex-X3 TRM, which can be found at: https://developer.arm.com/documentation/101593/0102/?lang=en Signed-off-by: Mark Rutland Cc: James Morse Cc: Will Deacon Link: https://lore.kernel.org/r/20240603111812.1514101-2-mark.rutland@arm.com Signed-off-by: Catalin Marinas [ Mark: trivial backport ] Signed-off-by: Mark Rutland Signed-off-by: Sasha Levin --- arch/arm64/include/asm/cputype.h | 2 ++ 1 file changed, 2 insertions(+) diff --git a/arch/arm64/include/asm/cputype.h b/arch/arm64/include/asm/cputype.h index b2887995e575..e8ceddaba7a0 100644 --- a/arch/arm64/include/asm/cputype.h +++ b/arch/arm64/include/asm/cputype.h @@ -84,6 +84,7 @@ #define ARM_CPU_PART_CORTEX_X2 0xD48 #define ARM_CPU_PART_NEOVERSE_N2 0xD49 #define ARM_CPU_PART_CORTEX_A78C 0xD4B +#define ARM_CPU_PART_CORTEX_X3 0xD4E #define ARM_CPU_PART_NEOVERSE_V2 0xD4F #define ARM_CPU_PART_CORTEX_X4 0xD82 #define ARM_CPU_PART_NEOVERSE_V3 0xD84 @@ -139,6 +140,7 @@ #define MIDR_CORTEX_X2 MIDR_CPU_MODEL(ARM_CPU_IMP_ARM, ARM_CPU_PART_CORTEX_X2) #define MIDR_NEOVERSE_N2 MIDR_CPU_MODEL(ARM_CPU_IMP_ARM, ARM_CPU_PART_NEOVERSE_N2) #define MIDR_CORTEX_A78C MIDR_CPU_MODEL(ARM_CPU_IMP_ARM, ARM_CPU_PART_CORTEX_A78C) +#define MIDR_CORTEX_X3 MIDR_CPU_MODEL(ARM_CPU_IMP_ARM, ARM_CPU_PART_CORTEX_X3) #define MIDR_NEOVERSE_V2 MIDR_CPU_MODEL(ARM_CPU_IMP_ARM, ARM_CPU_PART_NEOVERSE_V2) #define MIDR_CORTEX_X4 MIDR_CPU_MODEL(ARM_CPU_IMP_ARM, ARM_CPU_PART_CORTEX_X4) #define MIDR_NEOVERSE_V3 MIDR_CPU_MODEL(ARM_CPU_IMP_ARM, ARM_CPU_PART_NEOVERSE_V3) From 77741cdc254d58e40c2e99fb60fbbad15a97f533 Mon Sep 17 00:00:00 2001 From: Mark Rutland Date: Fri, 9 Aug 2024 11:17:33 +0100 Subject: [PATCH 275/342] arm64: cputype: Add Cortex-A720 definitions [ Upstream commit add332c40328cf06fe35e4b3cde8ec315c4629e5 ] Add cputype definitions for Cortex-A720. These will be used for errata detection in subsequent patches. These values can be found in Table A-186 ("MIDR_EL1 bit descriptions") in issue 0002-05 of the Cortex-A720 TRM, which can be found at: https://developer.arm.com/documentation/102530/0002/?lang=en Signed-off-by: Mark Rutland Cc: James Morse Cc: Will Deacon Link: https://lore.kernel.org/r/20240603111812.1514101-3-mark.rutland@arm.com Signed-off-by: Catalin Marinas [ Mark: trivial backport ] Signed-off-by: Mark Rutland Signed-off-by: Sasha Levin --- arch/arm64/include/asm/cputype.h | 2 ++ 1 file changed, 2 insertions(+) diff --git a/arch/arm64/include/asm/cputype.h b/arch/arm64/include/asm/cputype.h index e8ceddaba7a0..4f08438344e2 100644 --- a/arch/arm64/include/asm/cputype.h +++ b/arch/arm64/include/asm/cputype.h @@ -86,6 +86,7 @@ #define ARM_CPU_PART_CORTEX_A78C 0xD4B #define ARM_CPU_PART_CORTEX_X3 0xD4E #define ARM_CPU_PART_NEOVERSE_V2 0xD4F +#define ARM_CPU_PART_CORTEX_A720 0xD81 #define ARM_CPU_PART_CORTEX_X4 0xD82 #define ARM_CPU_PART_NEOVERSE_V3 0xD84 @@ -142,6 +143,7 @@ #define MIDR_CORTEX_A78C MIDR_CPU_MODEL(ARM_CPU_IMP_ARM, ARM_CPU_PART_CORTEX_A78C) #define MIDR_CORTEX_X3 MIDR_CPU_MODEL(ARM_CPU_IMP_ARM, ARM_CPU_PART_CORTEX_X3) #define MIDR_NEOVERSE_V2 MIDR_CPU_MODEL(ARM_CPU_IMP_ARM, ARM_CPU_PART_NEOVERSE_V2) +#define MIDR_CORTEX_A720 MIDR_CPU_MODEL(ARM_CPU_IMP_ARM, ARM_CPU_PART_CORTEX_A720) #define MIDR_CORTEX_X4 MIDR_CPU_MODEL(ARM_CPU_IMP_ARM, ARM_CPU_PART_CORTEX_X4) #define MIDR_NEOVERSE_V3 MIDR_CPU_MODEL(ARM_CPU_IMP_ARM, ARM_CPU_PART_NEOVERSE_V3) #define MIDR_THUNDERX MIDR_CPU_MODEL(ARM_CPU_IMP_CAVIUM, CAVIUM_CPU_PART_THUNDERX) From 17ff37fe453f379f8c104abcb3126791eb1cc703 Mon Sep 17 00:00:00 2001 From: Mark Rutland Date: Fri, 9 Aug 2024 11:17:34 +0100 Subject: [PATCH 276/342] arm64: cputype: Add Cortex-X925 definitions [ Upstream commit fd2ff5f0b320f418288e7a1f919f648fbc8a0dfc ] Add cputype definitions for Cortex-X925. These will be used for errata detection in subsequent patches. These values can be found in Table A-285 ("MIDR_EL1 bit descriptions") in issue 0001-05 of the Cortex-X925 TRM, which can be found at: https://developer.arm.com/documentation/102807/0001/?lang=en Signed-off-by: Mark Rutland Cc: James Morse Cc: Will Deacon Link: https://lore.kernel.org/r/20240603111812.1514101-4-mark.rutland@arm.com Signed-off-by: Catalin Marinas [ Mark: trivial backport ] Signed-off-by: Mark Rutland Signed-off-by: Sasha Levin --- arch/arm64/include/asm/cputype.h | 2 ++ 1 file changed, 2 insertions(+) diff --git a/arch/arm64/include/asm/cputype.h b/arch/arm64/include/asm/cputype.h index 4f08438344e2..35162c15ed6c 100644 --- a/arch/arm64/include/asm/cputype.h +++ b/arch/arm64/include/asm/cputype.h @@ -89,6 +89,7 @@ #define ARM_CPU_PART_CORTEX_A720 0xD81 #define ARM_CPU_PART_CORTEX_X4 0xD82 #define ARM_CPU_PART_NEOVERSE_V3 0xD84 +#define ARM_CPU_PART_CORTEX_X925 0xD85 #define APM_CPU_PART_POTENZA 0x000 @@ -146,6 +147,7 @@ #define MIDR_CORTEX_A720 MIDR_CPU_MODEL(ARM_CPU_IMP_ARM, ARM_CPU_PART_CORTEX_A720) #define MIDR_CORTEX_X4 MIDR_CPU_MODEL(ARM_CPU_IMP_ARM, ARM_CPU_PART_CORTEX_X4) #define MIDR_NEOVERSE_V3 MIDR_CPU_MODEL(ARM_CPU_IMP_ARM, ARM_CPU_PART_NEOVERSE_V3) +#define MIDR_CORTEX_X925 MIDR_CPU_MODEL(ARM_CPU_IMP_ARM, ARM_CPU_PART_CORTEX_X925) #define MIDR_THUNDERX MIDR_CPU_MODEL(ARM_CPU_IMP_CAVIUM, CAVIUM_CPU_PART_THUNDERX) #define MIDR_THUNDERX_81XX MIDR_CPU_MODEL(ARM_CPU_IMP_CAVIUM, CAVIUM_CPU_PART_THUNDERX_81XX) #define MIDR_THUNDERX_83XX MIDR_CPU_MODEL(ARM_CPU_IMP_CAVIUM, CAVIUM_CPU_PART_THUNDERX_83XX) From bf0d247dfbda15060347aa120dc94019dfedc6b1 Mon Sep 17 00:00:00 2001 From: Mark Rutland Date: Fri, 9 Aug 2024 11:17:35 +0100 Subject: [PATCH 277/342] arm64: errata: Unify speculative SSBS errata logic [ Upstream commit ec768766608092087dfb5c1fc45a16a6f524dee2 ] Cortex-X4 erratum 3194386 and Neoverse-V3 erratum 3312417 are identical, with duplicate Kconfig text and some unsightly ifdeffery. While we try to share code behind CONFIG_ARM64_WORKAROUND_SPECULATIVE_SSBS, having separate options results in a fair amount of boilerplate code, and this will only get worse as we expand the set of affected CPUs. To reduce this boilerplate, unify the two behind a common Kconfig option. This removes the duplicate text and Kconfig logic, and removes the need for the intermediate ARM64_WORKAROUND_SPECULATIVE_SSBS option. The set of affected CPUs is described as a list so that this can easily be extended. I've used ARM64_ERRATUM_3194386 (matching the Neoverse-V3 erratum ID) as the common option, matching the way we use ARM64_ERRATUM_1319367 to cover Cortex-A57 erratum 1319537 and Cortex-A72 erratum 1319367. Signed-off-by: Mark Rutland Cc: James Morse Cc: Will Deacon Link: https://lore.kernel.org/r/20240603111812.1514101-5-mark.rutland@arm.com Signed-off-by: Catalin Marinas [ Mark: fix conflicts & renames, drop unneeded cpucaps.h ] Signed-off-by: Mark Rutland Signed-off-by: Sasha Levin --- Documentation/arm64/silicon-errata.rst | 2 +- arch/arm64/Kconfig | 28 ++++---------------------- arch/arm64/kernel/cpu_errata.c | 8 ++------ arch/arm64/kernel/proton-pack.c | 2 +- 4 files changed, 8 insertions(+), 32 deletions(-) diff --git a/Documentation/arm64/silicon-errata.rst b/Documentation/arm64/silicon-errata.rst index 0ecb714b2c42..2f50eb0fce34 100644 --- a/Documentation/arm64/silicon-errata.rst +++ b/Documentation/arm64/silicon-errata.rst @@ -106,7 +106,7 @@ stable kernels. +----------------+-----------------+-----------------+-----------------------------+ | ARM | Neoverse-N1 | #1542419 | ARM64_ERRATUM_1542419 | +----------------+-----------------+-----------------+-----------------------------+ -| ARM | Neoverse-V3 | #3312417 | ARM64_ERRATUM_3312417 | +| ARM | Neoverse-V3 | #3312417 | ARM64_ERRATUM_3194386 | +----------------+-----------------+-----------------+-----------------------------+ | ARM | MMU-500 | #841119,826419 | N/A | +----------------+-----------------+-----------------+-----------------------------+ diff --git a/arch/arm64/Kconfig b/arch/arm64/Kconfig index 0d59e8ab27c8..4ed94e8d84c7 100644 --- a/arch/arm64/Kconfig +++ b/arch/arm64/Kconfig @@ -691,34 +691,14 @@ config ARM64_ERRATUM_2457168 If unsure, say Y. -config ARM64_WORKAROUND_SPECULATIVE_SSBS - bool - config ARM64_ERRATUM_3194386 - bool "Cortex-X4: 3194386: workaround for MSR SSBS not self-synchronizing" - select ARM64_WORKAROUND_SPECULATIVE_SSBS + bool "Cortex-X4/Neoverse-V3: workaround for MSR SSBS not self-synchronizing" default y help - This option adds the workaround for ARM Cortex-X4 erratum 3194386. + This option adds the workaround for the following errata: - On affected cores "MSR SSBS, #0" instructions may not affect - subsequent speculative instructions, which may permit unexepected - speculative store bypassing. - - Work around this problem by placing a speculation barrier after - kernel changes to SSBS. The presence of the SSBS special-purpose - register is hidden from hwcaps and EL0 reads of ID_AA64PFR1_EL1, such - that userspace will use the PR_SPEC_STORE_BYPASS prctl to change - SSBS. - - If unsure, say Y. - -config ARM64_ERRATUM_3312417 - bool "Neoverse-V3: 3312417: workaround for MSR SSBS not self-synchronizing" - select ARM64_WORKAROUND_SPECULATIVE_SSBS - default y - help - This option adds the workaround for ARM Neoverse-V3 erratum 3312417. + * ARM Cortex-X4 erratum 3194386 + * ARM Neoverse-V3 erratum 3312417 On affected cores "MSR SSBS, #0" instructions may not affect subsequent speculative instructions, which may permit unexepected diff --git a/arch/arm64/kernel/cpu_errata.c b/arch/arm64/kernel/cpu_errata.c index 3eabd809aee4..4dc465d285d5 100644 --- a/arch/arm64/kernel/cpu_errata.c +++ b/arch/arm64/kernel/cpu_errata.c @@ -364,14 +364,10 @@ static struct midr_range broken_aarch32_aes[] = { }; #endif -#ifdef CONFIG_ARM64_WORKAROUND_SPECULATIVE_SSBS -static const struct midr_range erratum_spec_ssbs_list[] = { #ifdef CONFIG_ARM64_ERRATUM_3194386 +static const struct midr_range erratum_spec_ssbs_list[] = { MIDR_ALL_VERSIONS(MIDR_CORTEX_X4), -#endif -#ifdef CONFIG_ARM64_ERRATUM_3312417 MIDR_ALL_VERSIONS(MIDR_NEOVERSE_V3), -#endif {} }; #endif @@ -583,7 +579,7 @@ const struct arm64_cpu_capabilities arm64_errata[] = { .type = ARM64_CPUCAP_LOCAL_CPU_ERRATUM, }, #endif -#ifdef CONFIG_ARM64_WORKAROUND_SPECULATIVE_SSBS +#ifdef CONFIG_ARM64_ERRATUM_3194386 { .desc = "ARM errata 3194386, 3312417", .capability = ARM64_WORKAROUND_SPECULATIVE_SSBS, diff --git a/arch/arm64/kernel/proton-pack.c b/arch/arm64/kernel/proton-pack.c index b40310e0bdb9..90337910c3f5 100644 --- a/arch/arm64/kernel/proton-pack.c +++ b/arch/arm64/kernel/proton-pack.c @@ -583,7 +583,7 @@ static enum mitigation_state spectre_v4_enable_hw_mitigation(void) * Mitigate this with an unconditional speculation barrier, as CPUs * could mis-speculate branches and bypass a conditional barrier. */ - if (IS_ENABLED(CONFIG_ARM64_WORKAROUND_SPECULATIVE_SSBS)) + if (IS_ENABLED(CONFIG_ARM64_ERRATUM_3194386)) spec_bar(); return SPECTRE_MITIGATED; From 4a500d4bdcec631a76ba5780b0e0864767ee6df0 Mon Sep 17 00:00:00 2001 From: Mark Rutland Date: Fri, 9 Aug 2024 11:17:36 +0100 Subject: [PATCH 278/342] arm64: errata: Expand speculative SSBS workaround [ Upstream commit 75b3c43eab594bfbd8184ec8ee1a6b820950819a ] A number of Arm Ltd CPUs suffer from errata whereby an MSR to the SSBS special-purpose register does not affect subsequent speculative instructions, permitting speculative store bypassing for a window of time. We worked around this for Cortex-X4 and Neoverse-V3, in commit: 7187bb7d0b5c7dfa ("arm64: errata: Add workaround for Arm errata 3194386 and 3312417") ... as per their Software Developer Errata Notice (SDEN) documents: * Cortex-X4 SDEN v8.0, erratum 3194386: https://developer.arm.com/documentation/SDEN-2432808/0800/ * Neoverse-V3 SDEN v6.0, erratum 3312417: https://developer.arm.com/documentation/SDEN-2891958/0600/ Since then, similar errata have been published for a number of other Arm Ltd CPUs, for which the mitigation is the same. This is described in their respective SDEN documents: * Cortex-A710 SDEN v19.0, errataum 3324338 https://developer.arm.com/documentation/SDEN-1775101/1900/?lang=en * Cortex-A720 SDEN v11.0, erratum 3456091 https://developer.arm.com/documentation/SDEN-2439421/1100/?lang=en * Cortex-X2 SDEN v19.0, erratum 3324338 https://developer.arm.com/documentation/SDEN-1775100/1900/?lang=en * Cortex-X3 SDEN v14.0, erratum 3324335 https://developer.arm.com/documentation/SDEN-2055130/1400/?lang=en * Cortex-X925 SDEN v8.0, erratum 3324334 https://developer.arm.com/documentation/109108/800/?lang=en * Neoverse-N2 SDEN v17.0, erratum 3324339 https://developer.arm.com/documentation/SDEN-1982442/1700/?lang=en * Neoverse-V2 SDEN v9.0, erratum 3324336 https://developer.arm.com/documentation/SDEN-2332927/900/?lang=en Note that due to shared design lineage, some CPUs share the same erratum number. Add these to the existing mitigation under CONFIG_ARM64_ERRATUM_3194386. As listing all of the erratum IDs in the runtime description would be unwieldy, this is reduced to: "SSBS not fully self-synchronizing" ... matching the description of the errata in all of the SDENs. Signed-off-by: Mark Rutland Cc: James Morse Cc: Will Deacon Link: https://lore.kernel.org/r/20240603111812.1514101-6-mark.rutland@arm.com Signed-off-by: Catalin Marinas [ Mark: fix conflicts and renames ] Signed-off-by: Mark Rutland Signed-off-by: Sasha Levin --- Documentation/arm64/silicon-errata.rst | 14 ++++++++++++++ arch/arm64/Kconfig | 9 ++++++++- arch/arm64/kernel/cpu_errata.c | 9 ++++++++- 3 files changed, 30 insertions(+), 2 deletions(-) diff --git a/Documentation/arm64/silicon-errata.rst b/Documentation/arm64/silicon-errata.rst index 2f50eb0fce34..748f9cc5877b 100644 --- a/Documentation/arm64/silicon-errata.rst +++ b/Documentation/arm64/silicon-errata.rst @@ -98,14 +98,28 @@ stable kernels. +----------------+-----------------+-----------------+-----------------------------+ | ARM | Cortex-A510 | #2457168 | ARM64_ERRATUM_2457168 | +----------------+-----------------+-----------------+-----------------------------+ +| ARM | Cortex-A710 | #3324338 | ARM64_ERRATUM_3194386 | ++----------------+-----------------+-----------------+-----------------------------+ +| ARM | Cortex-A720 | #3456091 | ARM64_ERRATUM_3194386 | ++----------------+-----------------+-----------------+-----------------------------+ +| ARM | Cortex-X2 | #3324338 | ARM64_ERRATUM_3194386 | ++----------------+-----------------+-----------------+-----------------------------+ +| ARM | Cortex-X3 | #3324335 | ARM64_ERRATUM_3194386 | ++----------------+-----------------+-----------------+-----------------------------+ | ARM | Cortex-X4 | #3194386 | ARM64_ERRATUM_3194386 | +----------------+-----------------+-----------------+-----------------------------+ +| ARM | Cortex-X925 | #3324334 | ARM64_ERRATUM_3194386 | ++----------------+-----------------+-----------------+-----------------------------+ | ARM | Neoverse-N1 | #1188873,1418040| ARM64_ERRATUM_1418040 | +----------------+-----------------+-----------------+-----------------------------+ | ARM | Neoverse-N1 | #1349291 | N/A | +----------------+-----------------+-----------------+-----------------------------+ | ARM | Neoverse-N1 | #1542419 | ARM64_ERRATUM_1542419 | +----------------+-----------------+-----------------+-----------------------------+ +| ARM | Neoverse-N2 | #3324339 | ARM64_ERRATUM_3194386 | ++----------------+-----------------+-----------------+-----------------------------+ +| ARM | Neoverse-V2 | #3324336 | ARM64_ERRATUM_3194386 | ++----------------+-----------------+-----------------+-----------------------------+ | ARM | Neoverse-V3 | #3312417 | ARM64_ERRATUM_3194386 | +----------------+-----------------+-----------------+-----------------------------+ | ARM | MMU-500 | #841119,826419 | N/A | diff --git a/arch/arm64/Kconfig b/arch/arm64/Kconfig index 4ed94e8d84c7..3662cb8aa44d 100644 --- a/arch/arm64/Kconfig +++ b/arch/arm64/Kconfig @@ -692,12 +692,19 @@ config ARM64_ERRATUM_2457168 If unsure, say Y. config ARM64_ERRATUM_3194386 - bool "Cortex-X4/Neoverse-V3: workaround for MSR SSBS not self-synchronizing" + bool "Cortex-{A720,X4,X925}/Neoverse-V3: workaround for MSR SSBS not self-synchronizing" default y help This option adds the workaround for the following errata: + * ARM Cortex-A710 erratam 3324338 + * ARM Cortex-A720 erratum 3456091 + * ARM Cortex-X2 erratum 3324338 + * ARM Cortex-X3 erratum 3324335 * ARM Cortex-X4 erratum 3194386 + * ARM Cortex-X925 erratum 3324334 + * ARM Neoverse N2 erratum 3324339 + * ARM Neoverse V2 erratum 3324336 * ARM Neoverse-V3 erratum 3312417 On affected cores "MSR SSBS, #0" instructions may not affect diff --git a/arch/arm64/kernel/cpu_errata.c b/arch/arm64/kernel/cpu_errata.c index 4dc465d285d5..000c61ee5a1e 100644 --- a/arch/arm64/kernel/cpu_errata.c +++ b/arch/arm64/kernel/cpu_errata.c @@ -366,8 +366,15 @@ static struct midr_range broken_aarch32_aes[] = { #ifdef CONFIG_ARM64_ERRATUM_3194386 static const struct midr_range erratum_spec_ssbs_list[] = { + MIDR_ALL_VERSIONS(MIDR_CORTEX_A710), + MIDR_ALL_VERSIONS(MIDR_CORTEX_A720), + MIDR_ALL_VERSIONS(MIDR_CORTEX_X2), + MIDR_ALL_VERSIONS(MIDR_CORTEX_X3), MIDR_ALL_VERSIONS(MIDR_CORTEX_X4), + MIDR_ALL_VERSIONS(MIDR_CORTEX_X925), + MIDR_ALL_VERSIONS(MIDR_NEOVERSE_N2), MIDR_ALL_VERSIONS(MIDR_NEOVERSE_V3), + MIDR_ALL_VERSIONS(MIDR_NEOVERSE_V2), {} }; #endif @@ -581,7 +588,7 @@ const struct arm64_cpu_capabilities arm64_errata[] = { #endif #ifdef CONFIG_ARM64_ERRATUM_3194386 { - .desc = "ARM errata 3194386, 3312417", + .desc = "SSBS not fully self-synchronizing", .capability = ARM64_WORKAROUND_SPECULATIVE_SSBS, ERRATA_MIDR_RANGE_LIST(erratum_spec_ssbs_list), }, From bdae104b0949216ba8d4f2f1c11788a6526c0fc0 Mon Sep 17 00:00:00 2001 From: Mark Rutland Date: Fri, 9 Aug 2024 11:17:37 +0100 Subject: [PATCH 279/342] arm64: cputype: Add Cortex-X1C definitions [ Upstream commit 58d245e03c324d083a0ec3b9ab8ebd46ec9848d7 ] Add cputype definitions for Cortex-X1C. These will be used for errata detection in subsequent patches. These values can be found in the Cortex-X1C TRM: https://developer.arm.com/documentation/101968/0002/ ... in section B2.107 ("MIDR_EL1, Main ID Register, EL1"). Signed-off-by: Mark Rutland Cc: James Morse Cc: Will Deacon Reviewed-by: Anshuman Khandual Link: https://lore.kernel.org/r/20240801101803.1982459-2-mark.rutland@arm.com Signed-off-by: Catalin Marinas [ Mark: trivial backport ] Signed-off-by: Mark Rutland Signed-off-by: Sasha Levin --- arch/arm64/include/asm/cputype.h | 2 ++ 1 file changed, 2 insertions(+) diff --git a/arch/arm64/include/asm/cputype.h b/arch/arm64/include/asm/cputype.h index 35162c15ed6c..8dccfd205269 100644 --- a/arch/arm64/include/asm/cputype.h +++ b/arch/arm64/include/asm/cputype.h @@ -84,6 +84,7 @@ #define ARM_CPU_PART_CORTEX_X2 0xD48 #define ARM_CPU_PART_NEOVERSE_N2 0xD49 #define ARM_CPU_PART_CORTEX_A78C 0xD4B +#define ARM_CPU_PART_CORTEX_X1C 0xD4C #define ARM_CPU_PART_CORTEX_X3 0xD4E #define ARM_CPU_PART_NEOVERSE_V2 0xD4F #define ARM_CPU_PART_CORTEX_A720 0xD81 @@ -142,6 +143,7 @@ #define MIDR_CORTEX_X2 MIDR_CPU_MODEL(ARM_CPU_IMP_ARM, ARM_CPU_PART_CORTEX_X2) #define MIDR_NEOVERSE_N2 MIDR_CPU_MODEL(ARM_CPU_IMP_ARM, ARM_CPU_PART_NEOVERSE_N2) #define MIDR_CORTEX_A78C MIDR_CPU_MODEL(ARM_CPU_IMP_ARM, ARM_CPU_PART_CORTEX_A78C) +#define MIDR_CORTEX_X1C MIDR_CPU_MODEL(ARM_CPU_IMP_ARM, ARM_CPU_PART_CORTEX_X1C) #define MIDR_CORTEX_X3 MIDR_CPU_MODEL(ARM_CPU_IMP_ARM, ARM_CPU_PART_CORTEX_X3) #define MIDR_NEOVERSE_V2 MIDR_CPU_MODEL(ARM_CPU_IMP_ARM, ARM_CPU_PART_NEOVERSE_V2) #define MIDR_CORTEX_A720 MIDR_CPU_MODEL(ARM_CPU_IMP_ARM, ARM_CPU_PART_CORTEX_A720) From f261c5d8d0f8d813125a2e245a91f761f77c067d Mon Sep 17 00:00:00 2001 From: Mark Rutland Date: Fri, 9 Aug 2024 11:17:38 +0100 Subject: [PATCH 280/342] arm64: cputype: Add Cortex-A725 definitions [ Upstream commit 9ef54a384526911095db465e77acc1cb5266b32c ] Add cputype definitions for Cortex-A725. These will be used for errata detection in subsequent patches. These values can be found in the Cortex-A725 TRM: https://developer.arm.com/documentation/107652/0001/ ... in table A-247 ("MIDR_EL1 bit descriptions"). Signed-off-by: Mark Rutland Cc: James Morse Cc: Will Deacon Reviewed-by: Anshuman Khandual Link: https://lore.kernel.org/r/20240801101803.1982459-3-mark.rutland@arm.com Signed-off-by: Catalin Marinas [ Mark: trivial backport ] Signed-off-by: Mark Rutland Signed-off-by: Sasha Levin --- arch/arm64/include/asm/cputype.h | 2 ++ 1 file changed, 2 insertions(+) diff --git a/arch/arm64/include/asm/cputype.h b/arch/arm64/include/asm/cputype.h index 8dccfd205269..91890e9fcb6c 100644 --- a/arch/arm64/include/asm/cputype.h +++ b/arch/arm64/include/asm/cputype.h @@ -91,6 +91,7 @@ #define ARM_CPU_PART_CORTEX_X4 0xD82 #define ARM_CPU_PART_NEOVERSE_V3 0xD84 #define ARM_CPU_PART_CORTEX_X925 0xD85 +#define ARM_CPU_PART_CORTEX_A725 0xD87 #define APM_CPU_PART_POTENZA 0x000 @@ -150,6 +151,7 @@ #define MIDR_CORTEX_X4 MIDR_CPU_MODEL(ARM_CPU_IMP_ARM, ARM_CPU_PART_CORTEX_X4) #define MIDR_NEOVERSE_V3 MIDR_CPU_MODEL(ARM_CPU_IMP_ARM, ARM_CPU_PART_NEOVERSE_V3) #define MIDR_CORTEX_X925 MIDR_CPU_MODEL(ARM_CPU_IMP_ARM, ARM_CPU_PART_CORTEX_X925) +#define MIDR_CORTEX_A725 MIDR_CPU_MODEL(ARM_CPU_IMP_ARM, ARM_CPU_PART_CORTEX_A725) #define MIDR_THUNDERX MIDR_CPU_MODEL(ARM_CPU_IMP_CAVIUM, CAVIUM_CPU_PART_THUNDERX) #define MIDR_THUNDERX_81XX MIDR_CPU_MODEL(ARM_CPU_IMP_CAVIUM, CAVIUM_CPU_PART_THUNDERX_81XX) #define MIDR_THUNDERX_83XX MIDR_CPU_MODEL(ARM_CPU_IMP_CAVIUM, CAVIUM_CPU_PART_THUNDERX_83XX) From 706f18a8fa4317ccffea53098faac8b1efe6f427 Mon Sep 17 00:00:00 2001 From: Mark Rutland Date: Fri, 9 Aug 2024 11:17:39 +0100 Subject: [PATCH 281/342] arm64: errata: Expand speculative SSBS workaround (again) [ Upstream commit adeec61a4723fd3e39da68db4cc4d924e6d7f641 ] A number of Arm Ltd CPUs suffer from errata whereby an MSR to the SSBS special-purpose register does not affect subsequent speculative instructions, permitting speculative store bypassing for a window of time. We worked around this for a number of CPUs in commits: * 7187bb7d0b5c7dfa ("arm64: errata: Add workaround for Arm errata 3194386 and 3312417") * 75b3c43eab594bfb ("arm64: errata: Expand speculative SSBS workaround") Since then, similar errata have been published for a number of other Arm Ltd CPUs, for which the same mitigation is sufficient. This is described in their respective Software Developer Errata Notice (SDEN) documents: * Cortex-A76 (MP052) SDEN v31.0, erratum 3324349 https://developer.arm.com/documentation/SDEN-885749/3100/ * Cortex-A77 (MP074) SDEN v19.0, erratum 3324348 https://developer.arm.com/documentation/SDEN-1152370/1900/ * Cortex-A78 (MP102) SDEN v21.0, erratum 3324344 https://developer.arm.com/documentation/SDEN-1401784/2100/ * Cortex-A78C (MP138) SDEN v16.0, erratum 3324346 https://developer.arm.com/documentation/SDEN-1707916/1600/ * Cortex-A78C (MP154) SDEN v10.0, erratum 3324347 https://developer.arm.com/documentation/SDEN-2004089/1000/ * Cortex-A725 (MP190) SDEN v5.0, erratum 3456106 https://developer.arm.com/documentation/SDEN-2832921/0500/ * Cortex-X1 (MP077) SDEN v21.0, erratum 3324344 https://developer.arm.com/documentation/SDEN-1401782/2100/ * Cortex-X1C (MP136) SDEN v16.0, erratum 3324346 https://developer.arm.com/documentation/SDEN-1707914/1600/ * Neoverse-N1 (MP050) SDEN v32.0, erratum 3324349 https://developer.arm.com/documentation/SDEN-885747/3200/ * Neoverse-V1 (MP076) SDEN v19.0, erratum 3324341 https://developer.arm.com/documentation/SDEN-1401781/1900/ Note that due to the manner in which Arm develops IP and tracks errata, some CPUs share a common erratum number and some CPUs have multiple erratum numbers for the same HW issue. On parts without SB, it is necessary to use ISB for the workaround. The spec_bar() macro used in the mitigation will expand to a "DSB SY; ISB" sequence in this case, which is sufficient on all affected parts. Enable the existing mitigation by adding the relevant MIDRs to erratum_spec_ssbs_list. The list is sorted alphanumerically (involving moving Neoverse-V3 after Neoverse-V2) so that this is easy to audit and potentially extend again in future. The Kconfig text is also updated to clarify the set of affected parts and the mitigation. Signed-off-by: Mark Rutland Cc: James Morse Cc: Will Deacon Reviewed-by: Anshuman Khandual Acked-by: Will Deacon Link: https://lore.kernel.org/r/20240801101803.1982459-4-mark.rutland@arm.com Signed-off-by: Catalin Marinas [ Mark: fix conflicts in silicon-errata.rst ] Signed-off-by: Mark Rutland Signed-off-by: Sasha Levin --- Documentation/arm64/silicon-errata.rst | 18 ++++++++++++++++++ arch/arm64/Kconfig | 22 ++++++++++++++++------ arch/arm64/kernel/cpu_errata.c | 11 ++++++++++- 3 files changed, 44 insertions(+), 7 deletions(-) diff --git a/Documentation/arm64/silicon-errata.rst b/Documentation/arm64/silicon-errata.rst index 748f9cc5877b..14eef7e93614 100644 --- a/Documentation/arm64/silicon-errata.rst +++ b/Documentation/arm64/silicon-errata.rst @@ -94,14 +94,28 @@ stable kernels. +----------------+-----------------+-----------------+-----------------------------+ | ARM | Cortex-A76 | #1463225 | ARM64_ERRATUM_1463225 | +----------------+-----------------+-----------------+-----------------------------+ +| ARM | Cortex-A76 | #3324349 | ARM64_ERRATUM_3194386 | ++----------------+-----------------+-----------------+-----------------------------+ | ARM | Cortex-A77 | #1508412 | ARM64_ERRATUM_1508412 | +----------------+-----------------+-----------------+-----------------------------+ +| ARM | Cortex-A77 | #3324348 | ARM64_ERRATUM_3194386 | ++----------------+-----------------+-----------------+-----------------------------+ +| ARM | Cortex-A78 | #3324344 | ARM64_ERRATUM_3194386 | ++----------------+-----------------+-----------------+-----------------------------+ +| ARM | Cortex-A78C | #3324346,3324347| ARM64_ERRATUM_3194386 | ++----------------+-----------------+-----------------+-----------------------------+ | ARM | Cortex-A510 | #2457168 | ARM64_ERRATUM_2457168 | +----------------+-----------------+-----------------+-----------------------------+ | ARM | Cortex-A710 | #3324338 | ARM64_ERRATUM_3194386 | +----------------+-----------------+-----------------+-----------------------------+ | ARM | Cortex-A720 | #3456091 | ARM64_ERRATUM_3194386 | +----------------+-----------------+-----------------+-----------------------------+ +| ARM | Cortex-A725 | #3456106 | ARM64_ERRATUM_3194386 | ++----------------+-----------------+-----------------+-----------------------------+ +| ARM | Cortex-X1 | #3324344 | ARM64_ERRATUM_3194386 | ++----------------+-----------------+-----------------+-----------------------------+ +| ARM | Cortex-X1C | #3324346 | ARM64_ERRATUM_3194386 | ++----------------+-----------------+-----------------+-----------------------------+ | ARM | Cortex-X2 | #3324338 | ARM64_ERRATUM_3194386 | +----------------+-----------------+-----------------+-----------------------------+ | ARM | Cortex-X3 | #3324335 | ARM64_ERRATUM_3194386 | @@ -116,8 +130,12 @@ stable kernels. +----------------+-----------------+-----------------+-----------------------------+ | ARM | Neoverse-N1 | #1542419 | ARM64_ERRATUM_1542419 | +----------------+-----------------+-----------------+-----------------------------+ +| ARM | Neoverse-N1 | #3324349 | ARM64_ERRATUM_3194386 | ++----------------+-----------------+-----------------+-----------------------------+ | ARM | Neoverse-N2 | #3324339 | ARM64_ERRATUM_3194386 | +----------------+-----------------+-----------------+-----------------------------+ +| ARM | Neoverse-V1 | #3324341 | ARM64_ERRATUM_3194386 | ++----------------+-----------------+-----------------+-----------------------------+ | ARM | Neoverse-V2 | #3324336 | ARM64_ERRATUM_3194386 | +----------------+-----------------+-----------------+-----------------------------+ | ARM | Neoverse-V3 | #3312417 | ARM64_ERRATUM_3194386 | diff --git a/arch/arm64/Kconfig b/arch/arm64/Kconfig index 3662cb8aa44d..9fdf8b036428 100644 --- a/arch/arm64/Kconfig +++ b/arch/arm64/Kconfig @@ -692,18 +692,28 @@ config ARM64_ERRATUM_2457168 If unsure, say Y. config ARM64_ERRATUM_3194386 - bool "Cortex-{A720,X4,X925}/Neoverse-V3: workaround for MSR SSBS not self-synchronizing" + bool "Cortex-*/Neoverse-*: workaround for MSR SSBS not self-synchronizing" default y help This option adds the workaround for the following errata: + * ARM Cortex-A76 erratum 3324349 + * ARM Cortex-A77 erratum 3324348 + * ARM Cortex-A78 erratum 3324344 + * ARM Cortex-A78C erratum 3324346 + * ARM Cortex-A78C erratum 3324347 * ARM Cortex-A710 erratam 3324338 * ARM Cortex-A720 erratum 3456091 + * ARM Cortex-A725 erratum 3456106 + * ARM Cortex-X1 erratum 3324344 + * ARM Cortex-X1C erratum 3324346 * ARM Cortex-X2 erratum 3324338 * ARM Cortex-X3 erratum 3324335 * ARM Cortex-X4 erratum 3194386 * ARM Cortex-X925 erratum 3324334 + * ARM Neoverse-N1 erratum 3324349 * ARM Neoverse N2 erratum 3324339 + * ARM Neoverse-V1 erratum 3324341 * ARM Neoverse V2 erratum 3324336 * ARM Neoverse-V3 erratum 3312417 @@ -711,11 +721,11 @@ config ARM64_ERRATUM_3194386 subsequent speculative instructions, which may permit unexepected speculative store bypassing. - Work around this problem by placing a speculation barrier after - kernel changes to SSBS. The presence of the SSBS special-purpose - register is hidden from hwcaps and EL0 reads of ID_AA64PFR1_EL1, such - that userspace will use the PR_SPEC_STORE_BYPASS prctl to change - SSBS. + Work around this problem by placing a Speculation Barrier (SB) or + Instruction Synchronization Barrier (ISB) after kernel changes to + SSBS. The presence of the SSBS special-purpose register is hidden + from hwcaps and EL0 reads of ID_AA64PFR1_EL1, such that userspace + will use the PR_SPEC_STORE_BYPASS prctl to change SSBS. If unsure, say Y. diff --git a/arch/arm64/kernel/cpu_errata.c b/arch/arm64/kernel/cpu_errata.c index 000c61ee5a1e..6e63dc8f0e8c 100644 --- a/arch/arm64/kernel/cpu_errata.c +++ b/arch/arm64/kernel/cpu_errata.c @@ -366,15 +366,24 @@ static struct midr_range broken_aarch32_aes[] = { #ifdef CONFIG_ARM64_ERRATUM_3194386 static const struct midr_range erratum_spec_ssbs_list[] = { + MIDR_ALL_VERSIONS(MIDR_CORTEX_A76), + MIDR_ALL_VERSIONS(MIDR_CORTEX_A77), + MIDR_ALL_VERSIONS(MIDR_CORTEX_A78), + MIDR_ALL_VERSIONS(MIDR_CORTEX_A78C), MIDR_ALL_VERSIONS(MIDR_CORTEX_A710), MIDR_ALL_VERSIONS(MIDR_CORTEX_A720), + MIDR_ALL_VERSIONS(MIDR_CORTEX_A725), + MIDR_ALL_VERSIONS(MIDR_CORTEX_X1), + MIDR_ALL_VERSIONS(MIDR_CORTEX_X1C), MIDR_ALL_VERSIONS(MIDR_CORTEX_X2), MIDR_ALL_VERSIONS(MIDR_CORTEX_X3), MIDR_ALL_VERSIONS(MIDR_CORTEX_X4), MIDR_ALL_VERSIONS(MIDR_CORTEX_X925), + MIDR_ALL_VERSIONS(MIDR_NEOVERSE_N1), MIDR_ALL_VERSIONS(MIDR_NEOVERSE_N2), - MIDR_ALL_VERSIONS(MIDR_NEOVERSE_V3), + MIDR_ALL_VERSIONS(MIDR_NEOVERSE_V1), MIDR_ALL_VERSIONS(MIDR_NEOVERSE_V2), + MIDR_ALL_VERSIONS(MIDR_NEOVERSE_V3), {} }; #endif From 5605992ad425c86d4266204d306f437b7bb12528 Mon Sep 17 00:00:00 2001 From: Guenter Roeck Date: Mon, 10 Jan 2022 09:28:56 -0800 Subject: [PATCH 282/342] i2c: smbus: Improve handling of stuck alerts [ Upstream commit 37c526f00bc1c4f847fc800085f8f009d2e11be6 ] The following messages were observed while testing alert functionality on systems with multiple I2C devices on a single bus if alert was active on more than one chip. smbus_alert 3-000c: SMBALERT# from dev 0x0c, flag 0 smbus_alert 3-000c: no driver alert()! and: smbus_alert 3-000c: SMBALERT# from dev 0x28, flag 0 Once it starts, this message repeats forever at high rate. There is no device at any of the reported addresses. Analysis shows that this is seen if multiple devices have the alert pin active. Apparently some devices do not support SMBus arbitration correctly. They keep sending address bits after detecting an address collision and handle the collision not at all or too late. Specifically, address 0x0c is seen with ADT7461A at address 0x4c and ADM1021 at address 0x18 if alert is active on both chips. Address 0x28 is seen with ADT7483 at address 0x2a and ADT7461 at address 0x4c if alert is active on both chips. Once the system is in bad state (alert is set by more than one chip), it often only recovers by power cycling. To reduce the impact of this problem, abort the endless loop in smbus_alert() if the same address is read more than once and not handled by a driver. Fixes: b5527a7766f0 ("i2c: Add SMBus alert support") Signed-off-by: Guenter Roeck [wsa: it also fixed an interrupt storm in one of my experiments] Tested-by: Wolfram Sang [wsa: rebased, moved a comment as well, improved the 'invalid' value] Signed-off-by: Wolfram Sang Signed-off-by: Sasha Levin --- drivers/i2c/i2c-smbus.c | 32 +++++++++++++++++++++++++------- 1 file changed, 25 insertions(+), 7 deletions(-) diff --git a/drivers/i2c/i2c-smbus.c b/drivers/i2c/i2c-smbus.c index d3d06e3b4f3b..dcbc4b29aa72 100644 --- a/drivers/i2c/i2c-smbus.c +++ b/drivers/i2c/i2c-smbus.c @@ -34,6 +34,7 @@ static int smbus_do_alert(struct device *dev, void *addrp) struct i2c_client *client = i2c_verify_client(dev); struct alert_data *data = addrp; struct i2c_driver *driver; + int ret; if (!client || client->addr != data->addr) return 0; @@ -47,16 +48,21 @@ static int smbus_do_alert(struct device *dev, void *addrp) device_lock(dev); if (client->dev.driver) { driver = to_i2c_driver(client->dev.driver); - if (driver->alert) + if (driver->alert) { + /* Stop iterating after we find the device */ driver->alert(client, data->type, data->data); - else + ret = -EBUSY; + } else { dev_warn(&client->dev, "no driver alert()!\n"); - } else + ret = -EOPNOTSUPP; + } + } else { dev_dbg(&client->dev, "alert with no driver\n"); + ret = -ENODEV; + } device_unlock(dev); - /* Stop iterating after we find the device */ - return -EBUSY; + return ret; } /* @@ -67,6 +73,7 @@ static irqreturn_t smbus_alert(int irq, void *d) { struct i2c_smbus_alert *alert = d; struct i2c_client *ara; + unsigned short prev_addr = I2C_CLIENT_END; /* Not a valid address */ ara = alert->ara; @@ -94,8 +101,19 @@ static irqreturn_t smbus_alert(int irq, void *d) data.addr, data.data); /* Notify driver for the device which issued the alert */ - device_for_each_child(&ara->adapter->dev, &data, - smbus_do_alert); + status = device_for_each_child(&ara->adapter->dev, &data, + smbus_do_alert); + /* + * If we read the same address more than once, and the alert + * was not handled by a driver, it won't do any good to repeat + * the loop because it will never terminate. + * Bail out in this case. + * Note: This assumes that a driver with alert handler handles + * the alert properly and clears it if necessary. + */ + if (data.addr == prev_addr && status != -EBUSY) + break; + prev_addr = data.addr; } return IRQ_HANDLED; From 56f106d2c47676f4bb0c6a449ccc7afa40d8d411 Mon Sep 17 00:00:00 2001 From: Krzysztof Kozlowski Date: Fri, 26 Jul 2024 16:10:44 +0200 Subject: [PATCH 283/342] ASoC: codecs: wsa881x: Correct Soundwire ports mask [ Upstream commit eb11c3bb64ad0a05aeacdb01039863aa2aa3614b ] Device has up to WSA881X_MAX_SWR_PORTS number of ports and the array assigned to prop.sink_dpn_prop has 0..WSA881X_MAX_SWR_PORTS-1 elements. On the other hand, GENMASK(high, low) creates an inclusive mask between , so we need the mask from 0 up to WSA881X_MAX_SWR_PORTS-1. Theoretically, too wide mask could cause an out of bounds read in sdw_get_slave_dpn_prop() in stream.c, however only in the case of buggy driver, e.g. adding incorrect number of ports via sdw_stream_add_slave(). Fixes: a0aab9e1404a ("ASoC: codecs: add wsa881x amplifier support") Signed-off-by: Krzysztof Kozlowski Link: https://patch.msgid.link/20240726-asoc-wcd-wsa-swr-ports-genmask-v1-4-d4d7a8b56f05@linaro.org Signed-off-by: Mark Brown Signed-off-by: Sasha Levin --- sound/soc/codecs/wsa881x.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/sound/soc/codecs/wsa881x.c b/sound/soc/codecs/wsa881x.c index 9f66f6dc2c67..77012979e131 100644 --- a/sound/soc/codecs/wsa881x.c +++ b/sound/soc/codecs/wsa881x.c @@ -1120,7 +1120,7 @@ static int wsa881x_probe(struct sdw_slave *pdev, wsa881x->sconfig.frame_rate = 48000; wsa881x->sconfig.direction = SDW_DATA_DIR_RX; wsa881x->sconfig.type = SDW_STREAM_PDM; - pdev->prop.sink_ports = GENMASK(WSA881X_MAX_SWR_PORTS, 0); + pdev->prop.sink_ports = GENMASK(WSA881X_MAX_SWR_PORTS - 1, 0); pdev->prop.sink_dpn_prop = wsa_sink_dpn_prop; pdev->prop.scp_int1_mask = SDW_SCP_INT1_BUS_CLASH | SDW_SCP_INT1_PARITY; gpiod_direction_output(wsa881x->sd_n, 1); From 455769ebb60fe7bc6d9f370b30913341f1c031ff Mon Sep 17 00:00:00 2001 From: Guenter Roeck Date: Tue, 30 Jul 2024 07:19:41 -0700 Subject: [PATCH 284/342] i2c: smbus: Send alert notifications to all devices if source not found [ Upstream commit f6c29f710c1ff2590109f83be3e212b86c01e0f3 ] If a SMBus alert is received and the originating device is not found, the reason may be that the address reported on the SMBus alert address is corrupted, for example because multiple devices asserted alert and do not correctly implement SMBus arbitration. If this happens, call alert handlers on all devices connected to the given I2C bus, in the hope that this cleans up the situation. This change reliably fixed the problem on a system with multiple devices on a single bus. Example log where the device on address 0x18 (ADM1021) and on address 0x4c (ADT7461A) both had the alert line asserted: smbus_alert 3-000c: SMBALERT# from dev 0x0c, flag 0 smbus_alert 3-000c: no driver alert()! smbus_alert 3-000c: SMBALERT# from dev 0x0c, flag 0 smbus_alert 3-000c: no driver alert()! lm90 3-0018: temp1 out of range, please check! lm90 3-0018: Disabling ALERT# lm90 3-0029: Everything OK lm90 3-002a: Everything OK lm90 3-004c: temp1 out of range, please check! lm90 3-004c: temp2 out of range, please check! lm90 3-004c: Disabling ALERT# Fixes: b5527a7766f0 ("i2c: Add SMBus alert support") Signed-off-by: Guenter Roeck [wsa: fixed a typo in the commit message] Signed-off-by: Wolfram Sang Signed-off-by: Sasha Levin --- drivers/i2c/i2c-smbus.c | 38 +++++++++++++++++++++++++++++++++++--- 1 file changed, 35 insertions(+), 3 deletions(-) diff --git a/drivers/i2c/i2c-smbus.c b/drivers/i2c/i2c-smbus.c index dcbc4b29aa72..44582cf29e16 100644 --- a/drivers/i2c/i2c-smbus.c +++ b/drivers/i2c/i2c-smbus.c @@ -65,6 +65,32 @@ static int smbus_do_alert(struct device *dev, void *addrp) return ret; } +/* Same as above, but call back all drivers with alert handler */ + +static int smbus_do_alert_force(struct device *dev, void *addrp) +{ + struct i2c_client *client = i2c_verify_client(dev); + struct alert_data *data = addrp; + struct i2c_driver *driver; + + if (!client || (client->flags & I2C_CLIENT_TEN)) + return 0; + + /* + * Drivers should either disable alerts, or provide at least + * a minimal handler. Lock so the driver won't change. + */ + device_lock(dev); + if (client->dev.driver) { + driver = to_i2c_driver(client->dev.driver); + if (driver->alert) + driver->alert(client, data->type, data->data); + } + device_unlock(dev); + + return 0; +} + /* * The alert IRQ handler needs to hand work off to a task which can issue * SMBus calls, because those sleeping calls can't be made in IRQ context. @@ -106,13 +132,19 @@ static irqreturn_t smbus_alert(int irq, void *d) /* * If we read the same address more than once, and the alert * was not handled by a driver, it won't do any good to repeat - * the loop because it will never terminate. - * Bail out in this case. + * the loop because it will never terminate. Try again, this + * time calling the alert handlers of all devices connected to + * the bus, and abort the loop afterwards. If this helps, we + * are all set. If it doesn't, there is nothing else we can do, + * so we might as well abort the loop. * Note: This assumes that a driver with alert handler handles * the alert properly and clears it if necessary. */ - if (data.addr == prev_addr && status != -EBUSY) + if (data.addr == prev_addr && status != -EBUSY) { + device_for_each_child(&ara->adapter->dev, &data, + smbus_do_alert_force); break; + } prev_addr = data.addr; } From 9ddd5e7835c66c64cd007d9300a2fe7ab64ea554 Mon Sep 17 00:00:00 2001 From: Menglong Dong Date: Mon, 5 Aug 2024 14:01:21 +0900 Subject: [PATCH 285/342] bpf: kprobe: remove unused declaring of bpf_kprobe_override [ Upstream commit 0e8b53979ac86eddb3fd76264025a70071a25574 ] After the commit 66665ad2f102 ("tracing/kprobe: bpf: Compare instruction pointer with original one"), "bpf_kprobe_override" is not used anywhere anymore, and we can remove it now. Link: https://lore.kernel.org/all/20240710085939.11520-1-dongml2@chinatelecom.cn/ Fixes: 66665ad2f102 ("tracing/kprobe: bpf: Compare instruction pointer with original one") Signed-off-by: Menglong Dong Acked-by: Jiri Olsa Signed-off-by: Masami Hiramatsu (Google) Signed-off-by: Sasha Levin --- include/linux/trace_events.h | 1 - 1 file changed, 1 deletion(-) diff --git a/include/linux/trace_events.h b/include/linux/trace_events.h index dbf0993153d3..64af1e11ea13 100644 --- a/include/linux/trace_events.h +++ b/include/linux/trace_events.h @@ -729,7 +729,6 @@ do { \ struct perf_event; DECLARE_PER_CPU(struct pt_regs, perf_trace_regs); -DECLARE_PER_CPU(int, bpf_kprobe_override); extern int perf_trace_init(struct perf_event *event); extern void perf_trace_destroy(struct perf_event *event); From c6ba514732e99679e59c5aa69606a138076169d6 Mon Sep 17 00:00:00 2001 From: "Masami Hiramatsu (Google)" Date: Fri, 2 Aug 2024 22:53:15 +0900 Subject: [PATCH 286/342] kprobes: Fix to check symbol prefixes correctly [ Upstream commit 8c8acb8f26cbde665b233dd1b9bbcbb9b86822dc ] Since str_has_prefix() takes the prefix as the 2nd argument and the string as the first, is_cfi_preamble_symbol() always fails to check the prefix. Fix the function parameter order so that it correctly check the prefix. Link: https://lore.kernel.org/all/172260679559.362040.7360872132937227206.stgit@devnote2/ Fixes: de02f2ac5d8c ("kprobes: Prohibit probing on CFI preamble symbol") Signed-off-by: Masami Hiramatsu (Google) Signed-off-by: Sasha Levin --- kernel/kprobes.c | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-) diff --git a/kernel/kprobes.c b/kernel/kprobes.c index dba6541c0fc3..c8e62458d323 100644 --- a/kernel/kprobes.c +++ b/kernel/kprobes.c @@ -1632,8 +1632,8 @@ static bool is_cfi_preamble_symbol(unsigned long addr) if (lookup_symbol_name(addr, symbuf)) return false; - return str_has_prefix("__cfi_", symbuf) || - str_has_prefix("__pfx_", symbuf); + return str_has_prefix(symbuf, "__cfi_") || + str_has_prefix(symbuf, "__pfx_"); } static int check_kprobe_address_safe(struct kprobe *p, From c9c11ece5ad9f2afe3524b2c8e174af6379f83ae Mon Sep 17 00:00:00 2001 From: Stefan Wahren Date: Sun, 4 Aug 2024 13:36:11 +0200 Subject: [PATCH 287/342] spi: spi-fsl-lpspi: Fix scldiv calculation [ Upstream commit 730bbfaf7d4890bd99e637db7767dc68cfeb24e7 ] The effective SPI clock frequency should never exceed speed_hz otherwise this might result in undefined behavior of the SPI device. Currently the scldiv calculation could violate this constraint. For the example parameters perclk_rate = 24 MHz and speed_hz = 7 MHz, the function fsl_lpspi_set_bitrate will determine perscale = 0 and scldiv = 1, which is a effective SPI clock of 8 MHz. So fix this by rounding up the quotient of perclk_rate and speed_hz. While this never change within the loop, we can pull this out. Fixes: 5314987de5e5 ("spi: imx: add lpspi bus driver") Signed-off-by: Stefan Wahren Link: https://patch.msgid.link/20240804113611.83613-1-wahrenst@gmx.net Signed-off-by: Mark Brown Signed-off-by: Sasha Levin --- drivers/spi/spi-fsl-lpspi.c | 6 ++++-- 1 file changed, 4 insertions(+), 2 deletions(-) diff --git a/drivers/spi/spi-fsl-lpspi.c b/drivers/spi/spi-fsl-lpspi.c index c5ff6e8c45be..c21d7959dcd2 100644 --- a/drivers/spi/spi-fsl-lpspi.c +++ b/drivers/spi/spi-fsl-lpspi.c @@ -297,7 +297,7 @@ static void fsl_lpspi_set_watermark(struct fsl_lpspi_data *fsl_lpspi) static int fsl_lpspi_set_bitrate(struct fsl_lpspi_data *fsl_lpspi) { struct lpspi_config config = fsl_lpspi->config; - unsigned int perclk_rate, scldiv; + unsigned int perclk_rate, scldiv, div; u8 prescale; perclk_rate = clk_get_rate(fsl_lpspi->clk_per); @@ -308,8 +308,10 @@ static int fsl_lpspi_set_bitrate(struct fsl_lpspi_data *fsl_lpspi) return -EINVAL; } + div = DIV_ROUND_UP(perclk_rate, config.speed_hz); + for (prescale = 0; prescale < 8; prescale++) { - scldiv = perclk_rate / config.speed_hz / (1 << prescale) - 2; + scldiv = div / (1 << prescale) - 2; if (scldiv < 256) { fsl_lpspi->config.prescale = prescale; break; From 44e11ae8f942cfdd6bce821251261afee5d105da Mon Sep 17 00:00:00 2001 From: Takashi Iwai Date: Thu, 8 Aug 2024 10:18:01 +0200 Subject: [PATCH 288/342] ALSA: usb-audio: Re-add ScratchAmp quirk entries [ Upstream commit 03898691d42e0170e7d00f07cbe21ce0e9f3a8fa ] At the code refactoring of USB-audio quirk handling, I assumed that the quirk entries of Stanton ScratchAmp devices were only about the device name, and moved them completely into the rename table. But it seems that the device requires the quirk entry so that it's probed by the driver itself. This re-adds back the quirk entries of ScratchAmp, but in a minimalistic manner. Fixes: 5436f59bc5bc ("ALSA: usb-audio: Move device rename and profile quirks to an internal table") Link: https://patch.msgid.link/20240808081803.22300-1-tiwai@suse.de Signed-off-by: Takashi Iwai Signed-off-by: Sasha Levin --- sound/usb/quirks-table.h | 4 ++++ 1 file changed, 4 insertions(+) diff --git a/sound/usb/quirks-table.h b/sound/usb/quirks-table.h index 97fe2fadcafb..8f2fb2ac7af6 100644 --- a/sound/usb/quirks-table.h +++ b/sound/usb/quirks-table.h @@ -2573,6 +2573,10 @@ YAMAHA_DEVICE(0x7010, "UB99"), } }, +/* Stanton ScratchAmp */ +{ USB_DEVICE(0x103d, 0x0100) }, +{ USB_DEVICE(0x103d, 0x0101) }, + /* Novation EMS devices */ { USB_DEVICE_VENDOR_SPEC(0x1235, 0x0001), From 5291d4f73452c91e8a11f71207617e3e234d418e Mon Sep 17 00:00:00 2001 From: Ma Ke Date: Fri, 2 Aug 2024 12:47:36 +0800 Subject: [PATCH 289/342] drm/client: fix null pointer dereference in drm_client_modeset_probe commit 113fd6372a5bb3689aba8ef5b8a265ed1529a78f upstream. In drm_client_modeset_probe(), the return value of drm_mode_duplicate() is assigned to modeset->mode, which will lead to a possible NULL pointer dereference on failure of drm_mode_duplicate(). Add a check to avoid npd. Cc: stable@vger.kernel.org Fixes: cf13909aee05 ("drm/fb-helper: Move out modeset config code") Signed-off-by: Ma Ke Reviewed-by: Thomas Zimmermann Signed-off-by: Thomas Zimmermann Link: https://patchwork.freedesktop.org/patch/msgid/20240802044736.1570345-1-make24@iscas.ac.cn Signed-off-by: Greg Kroah-Hartman --- drivers/gpu/drm/drm_client_modeset.c | 5 +++++ 1 file changed, 5 insertions(+) diff --git a/drivers/gpu/drm/drm_client_modeset.c b/drivers/gpu/drm/drm_client_modeset.c index 7872a04e9a72..3884fab01110 100644 --- a/drivers/gpu/drm/drm_client_modeset.c +++ b/drivers/gpu/drm/drm_client_modeset.c @@ -866,6 +866,11 @@ int drm_client_modeset_probe(struct drm_client_dev *client, unsigned int width, kfree(modeset->mode); modeset->mode = drm_mode_duplicate(dev, mode); + if (!modeset->mode) { + ret = -ENOMEM; + break; + } + drm_connector_get(connector); modeset->connectors[modeset->num_connectors++] = connector; modeset->x = offset->x; From e7e7d2b180d8f297cea6db43ea72402fd33e1a29 Mon Sep 17 00:00:00 2001 From: Takashi Iwai Date: Mon, 5 Aug 2024 15:01:28 +0200 Subject: [PATCH 290/342] ALSA: line6: Fix racy access to midibuf commit 15b7a03205b31bc5623378c190d22b7ff60026f1 upstream. There can be concurrent accesses to line6 midibuf from both the URB completion callback and the rawmidi API access. This could be a cause of KMSAN warning triggered by syzkaller below (so put as reported-by here). This patch protects the midibuf call of the former code path with a spinlock for avoiding the possible races. Reported-by: syzbot+78eccfb8b3c9a85fc6c5@syzkaller.appspotmail.com Closes: https://lore.kernel.org/00000000000000949c061df288c5@google.com Cc: Link: https://patch.msgid.link/20240805130129.10872-1-tiwai@suse.de Signed-off-by: Takashi Iwai Signed-off-by: Greg Kroah-Hartman --- sound/usb/line6/driver.c | 5 +++++ 1 file changed, 5 insertions(+) diff --git a/sound/usb/line6/driver.c b/sound/usb/line6/driver.c index f4437015d43a..9df49a880b75 100644 --- a/sound/usb/line6/driver.c +++ b/sound/usb/line6/driver.c @@ -286,12 +286,14 @@ static void line6_data_received(struct urb *urb) { struct usb_line6 *line6 = (struct usb_line6 *)urb->context; struct midi_buffer *mb = &line6->line6midi->midibuf_in; + unsigned long flags; int done; if (urb->status == -ESHUTDOWN) return; if (line6->properties->capabilities & LINE6_CAP_CONTROL_MIDI) { + spin_lock_irqsave(&line6->line6midi->lock, flags); done = line6_midibuf_write(mb, urb->transfer_buffer, urb->actual_length); @@ -300,12 +302,15 @@ static void line6_data_received(struct urb *urb) dev_dbg(line6->ifcdev, "%d %d buffer overflow - message skipped\n", done, urb->actual_length); } + spin_unlock_irqrestore(&line6->line6midi->lock, flags); for (;;) { + spin_lock_irqsave(&line6->line6midi->lock, flags); done = line6_midibuf_read(mb, line6->buffer_message, LINE6_MIDI_MESSAGE_MAXLEN, LINE6_MIDIBUF_READ_RX); + spin_unlock_irqrestore(&line6->line6midi->lock, flags); if (done <= 0) break; From c7c1ca6e258d885f883b4e077c04e60fca69c144 Mon Sep 17 00:00:00 2001 From: Steven 'Steve' Kendall Date: Tue, 6 Aug 2024 00:08:24 +0000 Subject: [PATCH 291/342] ALSA: hda: Add HP MP9 G4 Retail System AMS to force connect list commit 7e1e206b99f4b3345aeb49d94584a420b7887f1d upstream. In recent HP UEFI firmware (likely v2.15 and above, tested on 2.27), these pins are incorrectly set for HDMI/DP audio. Tested on HP MP9 G4 Retail System AMS. Tested audio with two monitors connected via DisplayPort. Link: https://forum.manjaro.org/t/intel-cannon-lake-pch-cavs-conexant-cx20632-no-sound-at-hdmi-or-displayport/133494 Link: https://bbs.archlinux.org/viewtopic.php?id=270523 Signed-off-by: Steven 'Steve' Kendall Cc: Link: https://patch.msgid.link/20240806-hdmi-audio-hp-wrongpins-v2-1-d9eb4ad41043@chromium.org Signed-off-by: Takashi Iwai Signed-off-by: Greg Kroah-Hartman --- sound/pci/hda/patch_hdmi.c | 1 + 1 file changed, 1 insertion(+) diff --git a/sound/pci/hda/patch_hdmi.c b/sound/pci/hda/patch_hdmi.c index 0d1c6c4c1ee6..d928cc45a61a 100644 --- a/sound/pci/hda/patch_hdmi.c +++ b/sound/pci/hda/patch_hdmi.c @@ -1963,6 +1963,7 @@ static int hdmi_add_cvt(struct hda_codec *codec, hda_nid_t cvt_nid) } static const struct snd_pci_quirk force_connect_list[] = { + SND_PCI_QUIRK(0x103c, 0x83ef, "HP MP9 G4 Retail System AMS", 1), SND_PCI_QUIRK(0x103c, 0x870f, "HP", 1), SND_PCI_QUIRK(0x103c, 0x871a, "HP", 1), SND_PCI_QUIRK(0x103c, 0x8711, "HP", 1), From d993cb25efb18e30bceee398647ffef7b307b5f0 Mon Sep 17 00:00:00 2001 From: Takashi Iwai Date: Tue, 6 Aug 2024 08:49:16 +0200 Subject: [PATCH 292/342] ALSA: hda/hdmi: Yet more pin fix for HP EliteDesk 800 G4 commit 176fd1511dd9086ab4fa9323cb232177c6235288 upstream. HP EliteDesk 800 G4 (PCI SSID 103c:83e2) is another Kabylake machine where BIOS misses the HDMI pin initializations. Add the quirk entry. Cc: Link: https://patch.msgid.link/20240806064918.11132-1-tiwai@suse.de Signed-off-by: Takashi Iwai Signed-off-by: Greg Kroah-Hartman --- sound/pci/hda/patch_hdmi.c | 1 + 1 file changed, 1 insertion(+) diff --git a/sound/pci/hda/patch_hdmi.c b/sound/pci/hda/patch_hdmi.c index d928cc45a61a..0ffab5541de8 100644 --- a/sound/pci/hda/patch_hdmi.c +++ b/sound/pci/hda/patch_hdmi.c @@ -1963,6 +1963,7 @@ static int hdmi_add_cvt(struct hda_codec *codec, hda_nid_t cvt_nid) } static const struct snd_pci_quirk force_connect_list[] = { + SND_PCI_QUIRK(0x103c, 0x83e2, "HP EliteDesk 800 G4", 1), SND_PCI_QUIRK(0x103c, 0x83ef, "HP MP9 G4 Retail System AMS", 1), SND_PCI_QUIRK(0x103c, 0x870f, "HP", 1), SND_PCI_QUIRK(0x103c, 0x871a, "HP", 1), From 4dacdb9720aaab10b6be121eae55820174d97174 Mon Sep 17 00:00:00 2001 From: Oliver Neukum Date: Tue, 9 Jul 2024 13:38:41 +0200 Subject: [PATCH 293/342] usb: vhci-hcd: Do not drop references before new references are gained commit afdcfd3d6fcdeca2735ca8d994c5f2d24a368f0a upstream. At a few places the driver carries stale pointers to references that can still be used. Make sure that does not happen. This strictly speaking closes ZDI-CAN-22273, though there may be similar races in the driver. Signed-off-by: Oliver Neukum Cc: stable Acked-by: Shuah Khan Link: https://lore.kernel.org/r/20240709113851.14691-1-oneukum@suse.com Signed-off-by: Greg Kroah-Hartman --- drivers/usb/usbip/vhci_hcd.c | 9 ++++++--- 1 file changed, 6 insertions(+), 3 deletions(-) diff --git a/drivers/usb/usbip/vhci_hcd.c b/drivers/usb/usbip/vhci_hcd.c index b07b2925ff78..affcb928771d 100644 --- a/drivers/usb/usbip/vhci_hcd.c +++ b/drivers/usb/usbip/vhci_hcd.c @@ -745,6 +745,7 @@ static int vhci_urb_enqueue(struct usb_hcd *hcd, struct urb *urb, gfp_t mem_flag * */ if (usb_pipedevice(urb->pipe) == 0) { + struct usb_device *old; __u8 type = usb_pipetype(urb->pipe); struct usb_ctrlrequest *ctrlreq = (struct usb_ctrlrequest *) urb->setup_packet; @@ -755,14 +756,15 @@ static int vhci_urb_enqueue(struct usb_hcd *hcd, struct urb *urb, gfp_t mem_flag goto no_need_xmit; } + old = vdev->udev; switch (ctrlreq->bRequest) { case USB_REQ_SET_ADDRESS: /* set_address may come when a device is reset */ dev_info(dev, "SetAddress Request (%d) to port %d\n", ctrlreq->wValue, vdev->rhport); - usb_put_dev(vdev->udev); vdev->udev = usb_get_dev(urb->dev); + usb_put_dev(old); spin_lock(&vdev->ud.lock); vdev->ud.status = VDEV_ST_USED; @@ -781,8 +783,8 @@ static int vhci_urb_enqueue(struct usb_hcd *hcd, struct urb *urb, gfp_t mem_flag usbip_dbg_vhci_hc( "Not yet?:Get_Descriptor to device 0 (get max pipe size)\n"); - usb_put_dev(vdev->udev); vdev->udev = usb_get_dev(urb->dev); + usb_put_dev(old); goto out; default: @@ -1095,6 +1097,7 @@ static void vhci_shutdown_connection(struct usbip_device *ud) static void vhci_device_reset(struct usbip_device *ud) { struct vhci_device *vdev = container_of(ud, struct vhci_device, ud); + struct usb_device *old = vdev->udev; unsigned long flags; spin_lock_irqsave(&ud->lock, flags); @@ -1102,8 +1105,8 @@ static void vhci_device_reset(struct usbip_device *ud) vdev->speed = 0; vdev->devid = 0; - usb_put_dev(vdev->udev); vdev->udev = NULL; + usb_put_dev(old); if (ud->tcp_socket) { sockfd_put(ud->tcp_socket); From f1205a5aad682aeb94f8a26f073815bdf8fbf183 Mon Sep 17 00:00:00 2001 From: =?UTF-8?q?Marek=20Marczykowski-G=C3=B3recki?= Date: Mon, 15 Jul 2024 12:44:53 +0200 Subject: [PATCH 294/342] USB: serial: debug: do not echo input by default MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit commit 00af4f3dda1461ec90d892edc10bec6d3c50c554 upstream. This driver is intended as a "client" end of the console connection. When connected to a host it's supposed to receive debug logs, and possibly allow to interact with whatever debug console is available there. Feeding messages back, depending on a configuration may cause log messages be executed as shell commands (which can be really bad if one is unlucky, imagine a log message like "prevented running `rm -rf /home`"). In case of Xen, it exposes sysrq-like debug interface, and feeding it its own logs will pretty quickly hit 'R' for "instant reboot". Contrary to a classic serial console, the USB one cannot be configured ahead of time, as the device shows up only when target OS is up. And at the time device is opened to execute relevant ioctl, it's already too late, especially when logs start flowing shortly after device is initialized. Avoid the issue by changing default to no echo for this type of devices. Signed-off-by: Marek Marczykowski-Górecki [ johan: amend summary; disable also ECHONL ] Cc: stable@vger.kernel.org Signed-off-by: Johan Hovold Signed-off-by: Greg Kroah-Hartman --- drivers/usb/serial/usb_debug.c | 7 +++++++ 1 file changed, 7 insertions(+) diff --git a/drivers/usb/serial/usb_debug.c b/drivers/usb/serial/usb_debug.c index aaf4813e4971..406cb326e812 100644 --- a/drivers/usb/serial/usb_debug.c +++ b/drivers/usb/serial/usb_debug.c @@ -69,6 +69,11 @@ static void usb_debug_process_read_urb(struct urb *urb) usb_serial_generic_process_read_urb(urb); } +static void usb_debug_init_termios(struct tty_struct *tty) +{ + tty->termios.c_lflag &= ~(ECHO | ECHONL); +} + static struct usb_serial_driver debug_device = { .driver = { .owner = THIS_MODULE, @@ -78,6 +83,7 @@ static struct usb_serial_driver debug_device = { .num_ports = 1, .bulk_out_size = USB_DEBUG_MAX_PACKET_SIZE, .break_ctl = usb_debug_break_ctl, + .init_termios = usb_debug_init_termios, .process_read_urb = usb_debug_process_read_urb, }; @@ -89,6 +95,7 @@ static struct usb_serial_driver dbc_device = { .id_table = dbc_id_table, .num_ports = 1, .break_ctl = usb_debug_break_ctl, + .init_termios = usb_debug_init_termios, .process_read_urb = usb_debug_process_read_urb, }; From 7cc9ebcfe58be22f18056ad8bc6272d120bdcb3e Mon Sep 17 00:00:00 2001 From: Chris Wulff Date: Wed, 24 Jul 2024 21:04:20 -0400 Subject: [PATCH 295/342] usb: gadget: core: Check for unset descriptor commit 973a57891608a98e894db2887f278777f564de18 upstream. Make sure the descriptor has been set before looking at maxpacket. This fixes a null pointer panic in this case. This may happen if the gadget doesn't properly set up the endpoint for the current speed, or the gadget descriptors are malformed and the descriptor for the speed/endpoint are not found. No current gadget driver is known to have this problem, but this may cause a hard-to-find bug during development of new gadgets. Fixes: 54f83b8c8ea9 ("USB: gadget: Reject endpoints with 0 maxpacket value") Cc: stable@vger.kernel.org Signed-off-by: Chris Wulff Link: https://lore.kernel.org/r/20240725010419.314430-2-crwulff@gmail.com Signed-off-by: Greg Kroah-Hartman --- drivers/usb/gadget/udc/core.c | 10 ++++------ 1 file changed, 4 insertions(+), 6 deletions(-) diff --git a/drivers/usb/gadget/udc/core.c b/drivers/usb/gadget/udc/core.c index e80aa717c8b5..dd2fafc5b0c3 100644 --- a/drivers/usb/gadget/udc/core.c +++ b/drivers/usb/gadget/udc/core.c @@ -99,12 +99,10 @@ int usb_ep_enable(struct usb_ep *ep) goto out; /* UDC drivers can't handle endpoints with maxpacket size 0 */ - if (usb_endpoint_maxp(ep->desc) == 0) { - /* - * We should log an error message here, but we can't call - * dev_err() because there's no way to find the gadget - * given only ep. - */ + if (!ep->desc || usb_endpoint_maxp(ep->desc) == 0) { + WARN_ONCE(1, "%s: ep%d (%s) has %s\n", __func__, ep->address, ep->name, + (!ep->desc) ? "NULL descriptor" : "maxpacket 0"); + ret = -EINVAL; goto out; } From ef1b208ca813155d5c982aedb5e8847d276aef4c Mon Sep 17 00:00:00 2001 From: Prashanth K Date: Tue, 30 Jul 2024 18:27:54 +0530 Subject: [PATCH 296/342] usb: gadget: u_serial: Set start_delayed during suspend commit 5a444bea37e2759549ef72bfe83d1c8712e76b3d upstream. Upstream commit aba3a8d01d62 ("usb: gadget: u_serial: add suspend resume callbacks") added started_delayed flag, so that new ports which are opened after USB suspend can start IO while resuming. But if the port was already opened, and gadget suspend kicks in afterwards, start_delayed will never be set. This causes resume to bail out before calling gs_start_io(). Fix this by setting start_delayed during suspend. Fixes: aba3a8d01d62 ("usb: gadget: u_serial: add suspend resume callbacks") Cc: stable@vger.kernel.org Signed-off-by: Prashanth K Link: https://lore.kernel.org/r/20240730125754.576326-1-quic_prashk@quicinc.com Signed-off-by: Greg Kroah-Hartman --- drivers/usb/gadget/function/u_serial.c | 1 + 1 file changed, 1 insertion(+) diff --git a/drivers/usb/gadget/function/u_serial.c b/drivers/usb/gadget/function/u_serial.c index a717b53847a8..03ad1ed83c92 100644 --- a/drivers/usb/gadget/function/u_serial.c +++ b/drivers/usb/gadget/function/u_serial.c @@ -1438,6 +1438,7 @@ void gserial_suspend(struct gserial *gser) spin_lock(&port->port_lock); spin_unlock(&serial_port_lock); port->suspended = true; + port->start_delayed = true; spin_unlock_irqrestore(&port->port_lock, flags); } EXPORT_SYMBOL_GPL(gserial_suspend); From 005c318981bc84bbc79621550d3c0e4de92fa2fe Mon Sep 17 00:00:00 2001 From: Vamshi Gajjela Date: Wed, 24 Jul 2024 19:21:26 +0530 Subject: [PATCH 297/342] scsi: ufs: core: Fix hba->last_dme_cmd_tstamp timestamp updating logic commit ab9fd06cb8f0db0854291833fc40c789e43a361f upstream. The ufshcd_add_delay_before_dme_cmd() always introduces a delay of MIN_DELAY_BEFORE_DME_CMDS_US between DME commands even when it's not required. The delay is added when the UFS host controller supplies the quirk UFSHCD_QUIRK_DELAY_BEFORE_DME_CMDS. Fix the logic to update hba->last_dme_cmd_tstamp to ensure subsequent DME commands have the correct delay in the range of 0 to MIN_DELAY_BEFORE_DME_CMDS_US. Update the timestamp at the end of the function to ensure it captures the latest time after any necessary delay has been applied. Signed-off-by: Vamshi Gajjela Link: https://lore.kernel.org/r/20240724135126.1786126-1-vamshigajjela@google.com Fixes: cad2e03d8607 ("ufs: add support to allow non standard behaviours (quirks)") Cc: stable@vger.kernel.org Reviewed-by: Bart Van Assche Signed-off-by: Martin K. Petersen Signed-off-by: Greg Kroah-Hartman --- drivers/scsi/ufs/ufshcd.c | 11 ++++++++--- 1 file changed, 8 insertions(+), 3 deletions(-) diff --git a/drivers/scsi/ufs/ufshcd.c b/drivers/scsi/ufs/ufshcd.c index 0b0230b46f28..a4c70fbc809f 100644 --- a/drivers/scsi/ufs/ufshcd.c +++ b/drivers/scsi/ufs/ufshcd.c @@ -3653,11 +3653,16 @@ static inline void ufshcd_add_delay_before_dme_cmd(struct ufs_hba *hba) min_sleep_time_us = MIN_DELAY_BEFORE_DME_CMDS_US - delta; else - return; /* no more delay required */ + min_sleep_time_us = 0; /* no more delay required */ } - /* allow sleep for extra 50us if needed */ - usleep_range(min_sleep_time_us, min_sleep_time_us + 50); + if (min_sleep_time_us > 0) { + /* allow sleep for extra 50us if needed */ + usleep_range(min_sleep_time_us, min_sleep_time_us + 50); + } + + /* update the last_dme_cmd_tstamp */ + hba->last_dme_cmd_tstamp = ktime_get(); } /** From 668c6c4a7e9e9f081c06b70f30104fb7013437ed Mon Sep 17 00:00:00 2001 From: Thomas Gleixner Date: Wed, 31 Jul 2024 12:23:51 +0200 Subject: [PATCH 298/342] tick/broadcast: Move per CPU pointer access into the atomic section commit 6881e75237a84093d0986f56223db3724619f26e upstream. The recent fix for making the take over of the broadcast timer more reliable retrieves a per CPU pointer in preemptible context. This went unnoticed as compilers hoist the access into the non-preemptible region where the pointer is actually used. But of course it's valid that the compiler keeps it at the place where the code puts it which rightfully triggers: BUG: using smp_processor_id() in preemptible [00000000] code: caller is hotplug_cpu__broadcast_tick_pull+0x1c/0xc0 Move it to the actual usage site which is in a non-preemptible region. Fixes: f7d43dd206e7 ("tick/broadcast: Make takeover of broadcast hrtimer reliable") Reported-by: David Wang <00107082@163.com> Signed-off-by: Thomas Gleixner Tested-by: Yu Liao Cc: stable@vger.kernel.org Link: https://lore.kernel.org/all/87ttg56ers.ffs@tglx Signed-off-by: Greg Kroah-Hartman --- kernel/time/tick-broadcast.c | 3 ++- 1 file changed, 2 insertions(+), 1 deletion(-) diff --git a/kernel/time/tick-broadcast.c b/kernel/time/tick-broadcast.c index 792ef33ba487..dc3838c00d6c 100644 --- a/kernel/time/tick-broadcast.c +++ b/kernel/time/tick-broadcast.c @@ -944,7 +944,6 @@ void tick_broadcast_switch_to_oneshot(void) #ifdef CONFIG_HOTPLUG_CPU void hotplug_cpu__broadcast_tick_pull(int deadcpu) { - struct tick_device *td = this_cpu_ptr(&tick_cpu_device); struct clock_event_device *bc; unsigned long flags; @@ -970,6 +969,8 @@ void hotplug_cpu__broadcast_tick_pull(int deadcpu) * device to avoid the starvation. */ if (tick_check_broadcast_expired()) { + struct tick_device *td = this_cpu_ptr(&tick_cpu_device); + cpumask_clear_cpu(smp_processor_id(), tick_broadcast_force_mask); tick_program_event(td->evtdev->next_event, 1); } From dc335b92e5f1c92f0d9904afff5bc0d9cc112a4c Mon Sep 17 00:00:00 2001 From: Justin Stitt Date: Fri, 17 May 2024 20:22:44 +0000 Subject: [PATCH 299/342] ntp: Clamp maxerror and esterror to operating range [ Upstream commit 87d571d6fb77ec342a985afa8744bb9bb75b3622 ] Using syzkaller alongside the newly reintroduced signed integer overflow sanitizer spits out this report: UBSAN: signed-integer-overflow in ../kernel/time/ntp.c:461:16 9223372036854775807 + 500 cannot be represented in type 'long' Call Trace: handle_overflow+0x171/0x1b0 second_overflow+0x2d6/0x500 accumulate_nsecs_to_secs+0x60/0x160 timekeeping_advance+0x1fe/0x890 update_wall_time+0x10/0x30 time_maxerror is unconditionally incremented and the result is checked against NTP_PHASE_LIMIT, but the increment itself can overflow, resulting in wrap-around to negative space. Before commit eea83d896e31 ("ntp: NTP4 user space bits update") the user supplied value was sanity checked to be in the operating range. That change removed the sanity check and relied on clamping in handle_overflow() which does not work correctly when the user supplied value is in the overflow zone of the '+ 500' operation. The operation requires CAP_SYS_TIME and the side effect of the overflow is NTP getting out of sync. Miroslav confirmed that the input value should be clamped to the operating range and the same applies to time_esterror. The latter is not used by the kernel, but the value still should be in the operating range as it was before the sanity check got removed. Clamp them to the operating range. [ tglx: Changed it to clamping and included time_esterror ] Fixes: eea83d896e31 ("ntp: NTP4 user space bits update") Signed-off-by: Justin Stitt Signed-off-by: Thomas Gleixner Cc: Miroslav Lichvar Link: https://lore.kernel.org/all/20240517-b4-sio-ntp-usec-v2-1-d539180f2b79@google.com Closes: https://github.com/KSPP/linux/issues/354 Signed-off-by: Sasha Levin [ cast things to long long to fix compiler warnings - gregkh ] Signed-off-by: Greg Kroah-Hartman --- kernel/time/ntp.c | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-) diff --git a/kernel/time/ntp.c b/kernel/time/ntp.c index 069ca78fb0bf..f447787a7394 100644 --- a/kernel/time/ntp.c +++ b/kernel/time/ntp.c @@ -679,10 +679,10 @@ static inline void process_adjtimex_modes(const struct __kernel_timex *txc, } if (txc->modes & ADJ_MAXERROR) - time_maxerror = txc->maxerror; + time_maxerror = clamp(txc->maxerror, (long long)0, (long long)NTP_PHASE_LIMIT); if (txc->modes & ADJ_ESTERROR) - time_esterror = txc->esterror; + time_esterror = clamp(txc->esterror, (long long)0, (long long)NTP_PHASE_LIMIT); if (txc->modes & ADJ_TIMECONST) { time_constant = txc->constant; From f098e8fc7227166206256c18d56ab622039108b1 Mon Sep 17 00:00:00 2001 From: Dan Williams Date: Fri, 12 Jul 2024 12:42:09 -0700 Subject: [PATCH 300/342] driver core: Fix uevent_show() vs driver detach race commit 15fffc6a5624b13b428bb1c6e9088e32a55eb82c upstream. uevent_show() wants to de-reference dev->driver->name. There is no clean way for a device attribute to de-reference dev->driver unless that attribute is defined via (struct device_driver).dev_groups. Instead, the anti-pattern of taking the device_lock() in the attribute handler risks deadlocks with code paths that remove device attributes while holding the lock. This deadlock is typically invisible to lockdep given the device_lock() is marked lockdep_set_novalidate_class(), but some subsystems allocate a local lockdep key for @dev->mutex to reveal reports of the form: ====================================================== WARNING: possible circular locking dependency detected 6.10.0-rc7+ #275 Tainted: G OE N ------------------------------------------------------ modprobe/2374 is trying to acquire lock: ffff8c2270070de0 (kn->active#6){++++}-{0:0}, at: __kernfs_remove+0xde/0x220 but task is already holding lock: ffff8c22016e88f8 (&cxl_root_key){+.+.}-{3:3}, at: device_release_driver_internal+0x39/0x210 which lock already depends on the new lock. the existing dependency chain (in reverse order) is: -> #1 (&cxl_root_key){+.+.}-{3:3}: __mutex_lock+0x99/0xc30 uevent_show+0xac/0x130 dev_attr_show+0x18/0x40 sysfs_kf_seq_show+0xac/0xf0 seq_read_iter+0x110/0x450 vfs_read+0x25b/0x340 ksys_read+0x67/0xf0 do_syscall_64+0x75/0x190 entry_SYSCALL_64_after_hwframe+0x76/0x7e -> #0 (kn->active#6){++++}-{0:0}: __lock_acquire+0x121a/0x1fa0 lock_acquire+0xd6/0x2e0 kernfs_drain+0x1e9/0x200 __kernfs_remove+0xde/0x220 kernfs_remove_by_name_ns+0x5e/0xa0 device_del+0x168/0x410 device_unregister+0x13/0x60 devres_release_all+0xb8/0x110 device_unbind_cleanup+0xe/0x70 device_release_driver_internal+0x1c7/0x210 driver_detach+0x47/0x90 bus_remove_driver+0x6c/0xf0 cxl_acpi_exit+0xc/0x11 [cxl_acpi] __do_sys_delete_module.isra.0+0x181/0x260 do_syscall_64+0x75/0x190 entry_SYSCALL_64_after_hwframe+0x76/0x7e The observation though is that driver objects are typically much longer lived than device objects. It is reasonable to perform lockless de-reference of a @driver pointer even if it is racing detach from a device. Given the infrequency of driver unregistration, use synchronize_rcu() in module_remove_driver() to close any potential races. It is potentially overkill to suffer synchronize_rcu() just to handle the rare module removal racing uevent_show() event. Thanks to Tetsuo Handa for the debug analysis of the syzbot report [1]. Fixes: c0a40097f0bc ("drivers: core: synchronize really_probe() and dev_uevent()") Reported-by: syzbot+4762dd74e32532cda5ff@syzkaller.appspotmail.com Reported-by: Tetsuo Handa Closes: http://lore.kernel.org/5aa5558f-90a4-4864-b1b1-5d6784c5607d@I-love.SAKURA.ne.jp [1] Link: http://lore.kernel.org/669073b8ea479_5fffa294c1@dwillia2-xfh.jf.intel.com.notmuch Cc: stable@vger.kernel.org Cc: Ashish Sangwan Cc: Namjae Jeon Cc: Dirk Behme Cc: Greg Kroah-Hartman Cc: Rafael J. Wysocki Signed-off-by: Dan Williams Link: https://lore.kernel.org/r/172081332794.577428.9738802016494057132.stgit@dwillia2-xfh.jf.intel.com Signed-off-by: Greg Kroah-Hartman --- drivers/base/core.c | 13 ++++++++----- drivers/base/module.c | 4 ++++ 2 files changed, 12 insertions(+), 5 deletions(-) diff --git a/drivers/base/core.c b/drivers/base/core.c index b13a60de5a86..b81fd39226ca 100644 --- a/drivers/base/core.c +++ b/drivers/base/core.c @@ -25,6 +25,7 @@ #include #include #include +#include #include #include #include @@ -1909,6 +1910,7 @@ static int dev_uevent(struct kset *kset, struct kobject *kobj, struct kobj_uevent_env *env) { struct device *dev = kobj_to_dev(kobj); + struct device_driver *driver; int retval = 0; /* add device node properties if present */ @@ -1937,8 +1939,12 @@ static int dev_uevent(struct kset *kset, struct kobject *kobj, if (dev->type && dev->type->name) add_uevent_var(env, "DEVTYPE=%s", dev->type->name); - if (dev->driver) - add_uevent_var(env, "DRIVER=%s", dev->driver->name); + /* Synchronize with module_remove_driver() */ + rcu_read_lock(); + driver = READ_ONCE(dev->driver); + if (driver) + add_uevent_var(env, "DRIVER=%s", driver->name); + rcu_read_unlock(); /* Add common DT information about the device */ of_device_uevent(dev, env); @@ -2008,11 +2014,8 @@ static ssize_t uevent_show(struct device *dev, struct device_attribute *attr, if (!env) return -ENOMEM; - /* Synchronize with really_probe() */ - device_lock(dev); /* let the kset specific function add its keys */ retval = kset->uevent_ops->uevent(kset, &dev->kobj, env); - device_unlock(dev); if (retval) goto out; diff --git a/drivers/base/module.c b/drivers/base/module.c index 46ad4d636731..851cc5367c04 100644 --- a/drivers/base/module.c +++ b/drivers/base/module.c @@ -7,6 +7,7 @@ #include #include #include +#include #include "base.h" static char *make_driver_name(struct device_driver *drv) @@ -77,6 +78,9 @@ void module_remove_driver(struct device_driver *drv) if (!drv) return; + /* Synchronize with dev_uevent() */ + synchronize_rcu(); + sysfs_remove_link(&drv->p->kobj, "module"); if (drv->owner) From f3405f4997b0233719afdec7289593f9e2ac9fd0 Mon Sep 17 00:00:00 2001 From: Justin Stitt Date: Fri, 17 May 2024 00:47:10 +0000 Subject: [PATCH 301/342] ntp: Safeguard against time_constant overflow commit 06c03c8edce333b9ad9c6b207d93d3a5ae7c10c0 upstream. Using syzkaller with the recently reintroduced signed integer overflow sanitizer produces this UBSAN report: UBSAN: signed-integer-overflow in ../kernel/time/ntp.c:738:18 9223372036854775806 + 4 cannot be represented in type 'long' Call Trace: handle_overflow+0x171/0x1b0 __do_adjtimex+0x1236/0x1440 do_adjtimex+0x2be/0x740 The user supplied time_constant value is incremented by four and then clamped to the operating range. Before commit eea83d896e31 ("ntp: NTP4 user space bits update") the user supplied value was sanity checked to be in the operating range. That change removed the sanity check and relied on clamping after incrementing which does not work correctly when the user supplied value is in the overflow zone of the '+ 4' operation. The operation requires CAP_SYS_TIME and the side effect of the overflow is NTP getting out of sync. Similar to the fixups for time_maxerror and time_esterror, clamp the user space supplied value to the operating range. [ tglx: Switch to clamping ] Fixes: eea83d896e31 ("ntp: NTP4 user space bits update") Signed-off-by: Justin Stitt Signed-off-by: Thomas Gleixner Cc: Miroslav Lichvar Cc: stable@vger.kernel.org Link: https://lore.kernel.org/all/20240517-b4-sio-ntp-c-v2-1-f3a80096f36f@google.com Closes: https://github.com/KSPP/linux/issues/352 Signed-off-by: Greg Kroah-Hartman --- kernel/time/ntp.c | 5 ++--- 1 file changed, 2 insertions(+), 3 deletions(-) diff --git a/kernel/time/ntp.c b/kernel/time/ntp.c index f447787a7394..02d96c007673 100644 --- a/kernel/time/ntp.c +++ b/kernel/time/ntp.c @@ -685,11 +685,10 @@ static inline void process_adjtimex_modes(const struct __kernel_timex *txc, time_esterror = clamp(txc->esterror, (long long)0, (long long)NTP_PHASE_LIMIT); if (txc->modes & ADJ_TIMECONST) { - time_constant = txc->constant; + time_constant = clamp(txc->constant, (long long)0, (long long)MAXTC); if (!(time_status & STA_NANO)) time_constant += 4; - time_constant = min(time_constant, (long)MAXTC); - time_constant = max(time_constant, 0l); + time_constant = clamp(time_constant, (long)0, (long)MAXTC); } if (txc->modes & ADJ_TAI && From 8f209716ea5ec9d954d8f328583245b49d5fd151 Mon Sep 17 00:00:00 2001 From: Sreekanth Reddy Date: Thu, 3 Mar 2022 19:32:03 +0530 Subject: [PATCH 302/342] scsi: mpt3sas: Remove scsi_dma_map() error messages [ Upstream commit 0c25422d34b4726b2707d5f38560943155a91b80 ] When scsi_dma_map() fails by returning a sges_left value less than zero, the amount of logging produced can be extremely high. In a recent end-user environment, 1200 messages per second were being sent to the log buffer. This eventually overwhelmed the system and it stalled. These error messages are not needed. Remove them. Link: https://lore.kernel.org/r/20220303140203.12642-1-sreekanth.reddy@broadcom.com Suggested-by: Christoph Hellwig Signed-off-by: Sreekanth Reddy Signed-off-by: Martin K. Petersen Stable-dep-of: 82dbb57ac8d0 ("scsi: mpt3sas: Avoid IOMMU page faults on REPORT ZONES") Signed-off-by: Sasha Levin --- drivers/scsi/mpt3sas/mpt3sas_base.c | 18 +++--------------- 1 file changed, 3 insertions(+), 15 deletions(-) diff --git a/drivers/scsi/mpt3sas/mpt3sas_base.c b/drivers/scsi/mpt3sas/mpt3sas_base.c index 2803b475dae6..de4ec552799d 100644 --- a/drivers/scsi/mpt3sas/mpt3sas_base.c +++ b/drivers/scsi/mpt3sas/mpt3sas_base.c @@ -2431,12 +2431,8 @@ _base_check_pcie_native_sgl(struct MPT3SAS_ADAPTER *ioc, /* Get the SG list pointer and info. */ sges_left = scsi_dma_map(scmd); - if (sges_left < 0) { - sdev_printk(KERN_ERR, scmd->device, - "scsi_dma_map failed: request for %d bytes!\n", - scsi_bufflen(scmd)); + if (sges_left < 0) return 1; - } /* Check if we need to build a native SG list. */ if (base_is_prp_possible(ioc, pcie_device, @@ -2543,12 +2539,8 @@ _base_build_sg_scmd(struct MPT3SAS_ADAPTER *ioc, sg_scmd = scsi_sglist(scmd); sges_left = scsi_dma_map(scmd); - if (sges_left < 0) { - sdev_printk(KERN_ERR, scmd->device, - "scsi_dma_map failed: request for %d bytes!\n", - scsi_bufflen(scmd)); + if (sges_left < 0) return -ENOMEM; - } sg_local = &mpi_request->SGL; sges_in_segment = ioc->max_sges_in_main_message; @@ -2691,12 +2683,8 @@ _base_build_sg_scmd_ieee(struct MPT3SAS_ADAPTER *ioc, sg_scmd = scsi_sglist(scmd); sges_left = scsi_dma_map(scmd); - if (sges_left < 0) { - sdev_printk(KERN_ERR, scmd->device, - "scsi_dma_map failed: request for %d bytes!\n", - scsi_bufflen(scmd)); + if (sges_left < 0) return -ENOMEM; - } sg_local = &mpi_request->SGL; sges_in_segment = (ioc->request_sz - From 5f1aa8ce6452cefa5e56dad4ecd888f1d8f35f05 Mon Sep 17 00:00:00 2001 From: Damien Le Moal Date: Fri, 19 Jul 2024 16:39:12 +0900 Subject: [PATCH 303/342] scsi: mpt3sas: Avoid IOMMU page faults on REPORT ZONES [ Upstream commit 82dbb57ac8d06dfe8227ba9ab11a49de2b475ae5 ] Some firmware versions of the 9600 series SAS HBA byte-swap the REPORT ZONES command reply buffer from ATA-ZAC devices by directly accessing the buffer in the host memory. This does not respect the default command DMA direction and causes IOMMU page faults on architectures with an IOMMU enforcing write-only mappings for DMA_FROM_DEVICE DMA driection (e.g. AMD hosts). scsi 18:0:0:0: Direct-Access-ZBC ATA WDC WSH722020AL W870 PQ: 0 ANSI: 6 scsi 18:0:0:0: SATA: handle(0x0027), sas_addr(0x300062b2083e7c40), phy(0), device_name(0x5000cca29dc35e11) scsi 18:0:0:0: enclosure logical id (0x300062b208097c40), slot(0) scsi 18:0:0:0: enclosure level(0x0000), connector name( C0.0) scsi 18:0:0:0: atapi(n), ncq(y), asyn_notify(n), smart(y), fua(y), sw_preserve(y) scsi 18:0:0:0: qdepth(32), tagged(1), scsi_level(7), cmd_que(1) sd 18:0:0:0: Attached scsi generic sg2 type 20 sd 18:0:0:0: [sdc] Host-managed zoned block device mpt3sas 0000:41:00.0: AMD-Vi: Event logged [IO_PAGE_FAULT domain=0x0021 address=0xfff9b200 flags=0x0050] mpt3sas 0000:41:00.0: AMD-Vi: Event logged [IO_PAGE_FAULT domain=0x0021 address=0xfff9b300 flags=0x0050] mpt3sas_cm0: mpt3sas_ctl_pre_reset_handler: Releasing the trace buffer due to adapter reset. mpt3sas_cm0 fault info from func: mpt3sas_base_make_ioc_ready mpt3sas_cm0: fault_state(0x2666)! mpt3sas_cm0: sending diag reset !! mpt3sas_cm0: diag reset: SUCCESS sd 18:0:0:0: [sdc] REPORT ZONES start lba 0 failed sd 18:0:0:0: [sdc] REPORT ZONES: Result: hostbyte=DID_RESET driverbyte=DRIVER_OK sd 18:0:0:0: [sdc] 0 4096-byte logical blocks: (0 B/0 B) Avoid such issue by always mapping the buffer of REPORT ZONES commands using DMA_BIDIRECTIONAL (read+write IOMMU mapping). This is done by introducing the helper function _base_scsi_dma_map() and using this helper in _base_build_sg_scmd() and _base_build_sg_scmd_ieee() instead of calling directly scsi_dma_map(). Fixes: 471ef9d4e498 ("mpt3sas: Build MPI SGL LIST on GEN2 HBAs and IEEE SGL LIST on GEN3 HBAs") Cc: stable@vger.kernel.org Signed-off-by: Damien Le Moal Link: https://lore.kernel.org/r/20240719073913.179559-3-dlemoal@kernel.org Reviewed-by: Christoph Hellwig Reviewed-by: Johannes Thumshirn Signed-off-by: Martin K. Petersen Signed-off-by: Sasha Levin --- drivers/scsi/mpt3sas/mpt3sas_base.c | 20 ++++++++++++++++++-- 1 file changed, 18 insertions(+), 2 deletions(-) diff --git a/drivers/scsi/mpt3sas/mpt3sas_base.c b/drivers/scsi/mpt3sas/mpt3sas_base.c index de4ec552799d..53528711dac1 100644 --- a/drivers/scsi/mpt3sas/mpt3sas_base.c +++ b/drivers/scsi/mpt3sas/mpt3sas_base.c @@ -2492,6 +2492,22 @@ _base_build_zero_len_sge_ieee(struct MPT3SAS_ADAPTER *ioc, void *paddr) _base_add_sg_single_ieee(paddr, sgl_flags, 0, 0, -1); } +static inline int _base_scsi_dma_map(struct scsi_cmnd *cmd) +{ + /* + * Some firmware versions byte-swap the REPORT ZONES command reply from + * ATA-ZAC devices by directly accessing in the host buffer. This does + * not respect the default command DMA direction and causes IOMMU page + * faults on some architectures with an IOMMU enforcing write mappings + * (e.g. AMD hosts). Avoid such issue by making the report zones buffer + * mapping bi-directional. + */ + if (cmd->cmnd[0] == ZBC_IN && cmd->cmnd[1] == ZI_REPORT_ZONES) + cmd->sc_data_direction = DMA_BIDIRECTIONAL; + + return scsi_dma_map(cmd); +} + /** * _base_build_sg_scmd - main sg creation routine * pcie_device is unused here! @@ -2538,7 +2554,7 @@ _base_build_sg_scmd(struct MPT3SAS_ADAPTER *ioc, sgl_flags = sgl_flags << MPI2_SGE_FLAGS_SHIFT; sg_scmd = scsi_sglist(scmd); - sges_left = scsi_dma_map(scmd); + sges_left = _base_scsi_dma_map(scmd); if (sges_left < 0) return -ENOMEM; @@ -2682,7 +2698,7 @@ _base_build_sg_scmd_ieee(struct MPT3SAS_ADAPTER *ioc, } sg_scmd = scsi_sglist(scmd); - sges_left = scsi_dma_map(scmd); + sges_left = _base_scsi_dma_map(scmd); if (sges_left < 0) return -ENOMEM; From 7dddf560e2381eb3e1d6fcc890cd082dbf255ee1 Mon Sep 17 00:00:00 2001 From: Qianggui Song Date: Fri, 25 Feb 2022 13:52:04 +0800 Subject: [PATCH 304/342] irqchip/meson-gpio: support more than 8 channels gpio irq [ Upstream commit cc311074f681443266ed9f5969a5b5a0e833c5bc ] Current meson gpio irqchip driver only support 8 channels for gpio irq line, later chips may have more then 8 channels, so need to modify code to support more. Signed-off-by: Qianggui Song Signed-off-by: Marc Zyngier Link: https://lore.kernel.org/r/20220225055207.1048-3-qianggui.song@amlogic.com Stable-dep-of: f872d4af79fe ("irqchip/meson-gpio: Convert meson_gpio_irq_controller::lock to 'raw_spinlock_t'") Signed-off-by: Sasha Levin --- drivers/irqchip/irq-meson-gpio.c | 21 ++++++++++++--------- 1 file changed, 12 insertions(+), 9 deletions(-) diff --git a/drivers/irqchip/irq-meson-gpio.c b/drivers/irqchip/irq-meson-gpio.c index e50676ce2ec8..89dab14406e6 100644 --- a/drivers/irqchip/irq-meson-gpio.c +++ b/drivers/irqchip/irq-meson-gpio.c @@ -16,7 +16,7 @@ #include #include -#define NUM_CHANNEL 8 +#define MAX_NUM_CHANNEL 64 #define MAX_INPUT_MUX 256 #define REG_EDGE_POL 0x00 @@ -60,6 +60,7 @@ struct irq_ctl_ops { struct meson_gpio_irq_params { unsigned int nr_hwirq; + unsigned int nr_channels; bool support_edge_both; unsigned int edge_both_offset; unsigned int edge_single_offset; @@ -81,6 +82,7 @@ struct meson_gpio_irq_params { .edge_single_offset = 0, \ .pol_low_offset = 16, \ .pin_sel_mask = 0xff, \ + .nr_channels = 8, \ #define INIT_MESON_A1_COMMON_DATA(irqs) \ INIT_MESON_COMMON(irqs, meson_a1_gpio_irq_init, \ @@ -90,6 +92,7 @@ struct meson_gpio_irq_params { .edge_single_offset = 8, \ .pol_low_offset = 0, \ .pin_sel_mask = 0x7f, \ + .nr_channels = 8, \ static const struct meson_gpio_irq_params meson8_params = { INIT_MESON8_COMMON_DATA(134) @@ -136,8 +139,8 @@ static const struct of_device_id meson_irq_gpio_matches[] = { struct meson_gpio_irq_controller { const struct meson_gpio_irq_params *params; void __iomem *base; - u32 channel_irqs[NUM_CHANNEL]; - DECLARE_BITMAP(channel_map, NUM_CHANNEL); + u32 channel_irqs[MAX_NUM_CHANNEL]; + DECLARE_BITMAP(channel_map, MAX_NUM_CHANNEL); spinlock_t lock; }; @@ -207,8 +210,8 @@ meson_gpio_irq_request_channel(struct meson_gpio_irq_controller *ctl, spin_lock_irqsave(&ctl->lock, flags); /* Find a free channel */ - idx = find_first_zero_bit(ctl->channel_map, NUM_CHANNEL); - if (idx >= NUM_CHANNEL) { + idx = find_first_zero_bit(ctl->channel_map, ctl->params->nr_channels); + if (idx >= ctl->params->nr_channels) { spin_unlock_irqrestore(&ctl->lock, flags); pr_err("No channel available\n"); return -ENOSPC; @@ -451,10 +454,10 @@ static int __init meson_gpio_irq_parse_dt(struct device_node *node, ret = of_property_read_variable_u32_array(node, "amlogic,channel-interrupts", ctl->channel_irqs, - NUM_CHANNEL, - NUM_CHANNEL); + ctl->params->nr_channels, + ctl->params->nr_channels); if (ret < 0) { - pr_err("can't get %d channel interrupts\n", NUM_CHANNEL); + pr_err("can't get %d channel interrupts\n", ctl->params->nr_channels); return ret; } @@ -509,7 +512,7 @@ static int __init meson_gpio_irq_of_init(struct device_node *node, } pr_info("%d to %d gpio interrupt mux initialized\n", - ctl->params->nr_hwirq, NUM_CHANNEL); + ctl->params->nr_hwirq, ctl->params->nr_channels); return 0; From 227d455e6cec2404fec6b4e3a8c6a37c4120d187 Mon Sep 17 00:00:00 2001 From: Arseniy Krasnov Date: Mon, 29 Jul 2024 16:18:50 +0300 Subject: [PATCH 305/342] irqchip/meson-gpio: Convert meson_gpio_irq_controller::lock to 'raw_spinlock_t' [ Upstream commit f872d4af79fe8c71ae291ce8875b477e1669a6c7 ] This lock is acquired under irq_desc::lock with interrupts disabled. When PREEMPT_RT is enabled, 'spinlock_t' becomes preemptible, which results in invalid lock acquire context; [ BUG: Invalid wait context ] swapper/0/1 is trying to lock: ffff0000008fed30 (&ctl->lock){....}-{3:3}, at: meson_gpio_irq_update_bits0 other info that might help us debug this: context-{5:5} 3 locks held by swapper/0/1: #0: ffff0000003cd0f8 (&dev->mutex){....}-{4:4}, at: __driver_attach+0x90c #1: ffff000004714650 (&desc->request_mutex){+.+.}-{4:4}, at: __setup_irq0 #2: ffff0000047144c8 (&irq_desc_lock_class){-.-.}-{2:2}, at: __setup_irq0 stack backtrace: CPU: 1 PID: 1 Comm: swapper/0 Not tainted 6.9.9-sdkernel #1 Call trace: _raw_spin_lock_irqsave+0x60/0x88 meson_gpio_irq_update_bits+0x34/0x70 meson8_gpio_irq_set_type+0x78/0xc4 meson_gpio_irq_set_type+0x30/0x60 __irq_set_trigger+0x60/0x180 __setup_irq+0x30c/0x6e0 request_threaded_irq+0xec/0x1a4 Fixes: 215f4cc0fb20 ("irqchip/meson: Add support for gpio interrupt controller") Signed-off-by: Arseniy Krasnov Signed-off-by: Thomas Gleixner Cc: stable@vger.kernel.org Link: https://lore.kernel.org/all/20240729131850.3015508-1-avkrasnov@salutedevices.com Signed-off-by: Sasha Levin --- drivers/irqchip/irq-meson-gpio.c | 14 +++++++------- 1 file changed, 7 insertions(+), 7 deletions(-) diff --git a/drivers/irqchip/irq-meson-gpio.c b/drivers/irqchip/irq-meson-gpio.c index 89dab14406e6..6a3d18d5ba2f 100644 --- a/drivers/irqchip/irq-meson-gpio.c +++ b/drivers/irqchip/irq-meson-gpio.c @@ -141,7 +141,7 @@ struct meson_gpio_irq_controller { void __iomem *base; u32 channel_irqs[MAX_NUM_CHANNEL]; DECLARE_BITMAP(channel_map, MAX_NUM_CHANNEL); - spinlock_t lock; + raw_spinlock_t lock; }; static void meson_gpio_irq_update_bits(struct meson_gpio_irq_controller *ctl, @@ -150,14 +150,14 @@ static void meson_gpio_irq_update_bits(struct meson_gpio_irq_controller *ctl, unsigned long flags; u32 tmp; - spin_lock_irqsave(&ctl->lock, flags); + raw_spin_lock_irqsave(&ctl->lock, flags); tmp = readl_relaxed(ctl->base + reg); tmp &= ~mask; tmp |= val; writel_relaxed(tmp, ctl->base + reg); - spin_unlock_irqrestore(&ctl->lock, flags); + raw_spin_unlock_irqrestore(&ctl->lock, flags); } static void meson_gpio_irq_init_dummy(struct meson_gpio_irq_controller *ctl) @@ -207,12 +207,12 @@ meson_gpio_irq_request_channel(struct meson_gpio_irq_controller *ctl, unsigned long flags; unsigned int idx; - spin_lock_irqsave(&ctl->lock, flags); + raw_spin_lock_irqsave(&ctl->lock, flags); /* Find a free channel */ idx = find_first_zero_bit(ctl->channel_map, ctl->params->nr_channels); if (idx >= ctl->params->nr_channels) { - spin_unlock_irqrestore(&ctl->lock, flags); + raw_spin_unlock_irqrestore(&ctl->lock, flags); pr_err("No channel available\n"); return -ENOSPC; } @@ -220,7 +220,7 @@ meson_gpio_irq_request_channel(struct meson_gpio_irq_controller *ctl, /* Mark the channel as used */ set_bit(idx, ctl->channel_map); - spin_unlock_irqrestore(&ctl->lock, flags); + raw_spin_unlock_irqrestore(&ctl->lock, flags); /* * Setup the mux of the channel to route the signal of the pad @@ -488,7 +488,7 @@ static int __init meson_gpio_irq_of_init(struct device_node *node, if (!ctl) return -ENOMEM; - spin_lock_init(&ctl->lock); + raw_spin_lock_init(&ctl->lock); ctl->base = of_iomap(node, 0); if (!ctl->base) { From 52b138f1021113e593ee6ad258ce08fe90693a9e Mon Sep 17 00:00:00 2001 From: George Kennedy Date: Wed, 17 Jul 2024 07:24:38 -0500 Subject: [PATCH 306/342] serial: core: check uartclk for zero to avoid divide by zero commit 6eabce6608d6f3440f4c03aa3d3ef50a47a3d193 upstream. Calling ioctl TIOCSSERIAL with an invalid baud_base can result in uartclk being zero, which will result in a divide by zero error in uart_get_divisor(). The check for uartclk being zero in uart_set_info() needs to be done before other settings are made as subsequent calls to ioctl TIOCSSERIAL for the same port would be impacted if the uartclk check was done where uartclk gets set. Oops: divide error: 0000 PREEMPT SMP KASAN PTI RIP: 0010:uart_get_divisor (drivers/tty/serial/serial_core.c:580) Call Trace: serial8250_get_divisor (drivers/tty/serial/8250/8250_port.c:2576 drivers/tty/serial/8250/8250_port.c:2589) serial8250_do_set_termios (drivers/tty/serial/8250/8250_port.c:502 drivers/tty/serial/8250/8250_port.c:2741) serial8250_set_termios (drivers/tty/serial/8250/8250_port.c:2862) uart_change_line_settings (./include/linux/spinlock.h:376 ./include/linux/serial_core.h:608 drivers/tty/serial/serial_core.c:222) uart_port_startup (drivers/tty/serial/serial_core.c:342) uart_startup (drivers/tty/serial/serial_core.c:368) uart_set_info (drivers/tty/serial/serial_core.c:1034) uart_set_info_user (drivers/tty/serial/serial_core.c:1059) tty_set_serial (drivers/tty/tty_io.c:2637) tty_ioctl (drivers/tty/tty_io.c:2647 drivers/tty/tty_io.c:2791) __x64_sys_ioctl (fs/ioctl.c:52 fs/ioctl.c:907 fs/ioctl.c:893 fs/ioctl.c:893) do_syscall_64 (arch/x86/entry/common.c:52 (discriminator 1) arch/x86/entry/common.c:83 (discriminator 1)) entry_SYSCALL_64_after_hwframe (arch/x86/entry/entry_64.S:130) Reported-by: syzkaller Cc: stable@vger.kernel.org Signed-off-by: George Kennedy Rule: add Link: https://lore.kernel.org/stable/1721148848-9784-1-git-send-email-george.kennedy%40oracle.com Link: https://lore.kernel.org/r/1721219078-3209-1-git-send-email-george.kennedy@oracle.com Signed-off-by: Greg Kroah-Hartman --- drivers/tty/serial/serial_core.c | 8 ++++++++ 1 file changed, 8 insertions(+) diff --git a/drivers/tty/serial/serial_core.c b/drivers/tty/serial/serial_core.c index 10b8785b9982..c7adcf97e2a3 100644 --- a/drivers/tty/serial/serial_core.c +++ b/drivers/tty/serial/serial_core.c @@ -862,6 +862,14 @@ static int uart_set_info(struct tty_struct *tty, struct tty_port *port, new_flags = (__force upf_t)new_info->flags; old_custom_divisor = uport->custom_divisor; + if (!(uport->flags & UPF_FIXED_PORT)) { + unsigned int uartclk = new_info->baud_base * 16; + /* check needs to be done here before other settings made */ + if (uartclk == 0) { + retval = -EINVAL; + goto exit; + } + } if (!capable(CAP_SYS_ADMIN)) { retval = -EPERM; if (change_irq || change_port || From db959cdfe67b9f15dc6f1fb4b65f02261e6092c7 Mon Sep 17 00:00:00 2001 From: Radhey Shyam Pandey Date: Fri, 9 Aug 2024 12:32:24 +0530 Subject: [PATCH 307/342] irqchip/xilinx: Fix shift out of bounds commit d73f0f49daa84176c3beee1606e73c7ffb6af8b2 upstream. The device tree property 'xlnx,kind-of-intr' is sanity checked that the bitmask contains only set bits which are in the range of the number of interrupts supported by the controller. The check is done by shifting the mask right by the number of supported interrupts and checking the result for zero. The data type of the mask is u32 and the number of supported interrupts is up to 32. In case of 32 interrupts the shift is out of bounds, resulting in a mismatch warning. The out of bounds condition is also reported by UBSAN: UBSAN: shift-out-of-bounds in irq-xilinx-intc.c:332:22 shift exponent 32 is too large for 32-bit type 'unsigned int' Fix it by promoting the mask to u64 for the test. Fixes: d50466c90724 ("microblaze: intc: Refactor DT sanity check") Signed-off-by: Radhey Shyam Pandey Signed-off-by: Thomas Gleixner Cc: stable@vger.kernel.org Link: https://lore.kernel.org/all/1723186944-3571957-1-git-send-email-radhey.shyam.pandey@amd.com Signed-off-by: Greg Kroah-Hartman --- drivers/irqchip/irq-xilinx-intc.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/drivers/irqchip/irq-xilinx-intc.c b/drivers/irqchip/irq-xilinx-intc.c index 8cd1bfc73057..b48c3fb4b35e 100644 --- a/drivers/irqchip/irq-xilinx-intc.c +++ b/drivers/irqchip/irq-xilinx-intc.c @@ -201,7 +201,7 @@ static int __init xilinx_intc_of_init(struct device_node *intc, irqc->intr_mask = 0; } - if (irqc->intr_mask >> irqc->nr_irq) + if ((u64)irqc->intr_mask >> irqc->nr_irq) pr_warn("irq-xilinx: mismatch in kind-of-intr param\n"); pr_info("irq-xilinx: %pOF: num_irq=%d, edge=0x%x\n", From a26bcfeea300fa38bbdaa0715f647e606e44a0ee Mon Sep 17 00:00:00 2001 From: Shay Drory Date: Tue, 6 Aug 2024 10:20:44 +0300 Subject: [PATCH 308/342] genirq/irqdesc: Honor caller provided affinity in alloc_desc() commit edbbaae42a56f9a2b39c52ef2504dfb3fb0a7858 upstream. Currently, whenever a caller is providing an affinity hint for an interrupt, the allocation code uses it to calculate the node and copies the cpumask into irq_desc::affinity. If the affinity for the interrupt is not marked 'managed' then the startup of the interrupt ignores irq_desc::affinity and uses the system default affinity mask. Prevent this by setting the IRQD_AFFINITY_SET flag for the interrupt in the allocator, which causes irq_setup_affinity() to use irq_desc::affinity on interrupt startup if the mask contains an online CPU. [ tglx: Massaged changelog ] Fixes: 45ddcecbfa94 ("genirq: Use affinity hint in irqdesc allocation") Signed-off-by: Shay Drory Signed-off-by: Thomas Gleixner Cc: Link: https://lore.kernel.org/all/20240806072044.837827-1-shayd@nvidia.com Signed-off-by: Greg Kroah-Hartman --- kernel/irq/irqdesc.c | 1 + 1 file changed, 1 insertion(+) diff --git a/kernel/irq/irqdesc.c b/kernel/irq/irqdesc.c index 6c009a033c73..68183511226a 100644 --- a/kernel/irq/irqdesc.c +++ b/kernel/irq/irqdesc.c @@ -491,6 +491,7 @@ static int alloc_descs(unsigned int start, unsigned int cnt, int node, flags = IRQD_AFFINITY_MANAGED | IRQD_MANAGED_SHUTDOWN; } + flags |= IRQD_AFFINITY_SET; mask = &affinity->mask; node = cpu_to_node(cpumask_first(mask)); affinity++; From 51e8360d94b44360ab39171fef17fdc42347813f Mon Sep 17 00:00:00 2001 From: Hans de Goede Date: Wed, 17 Jul 2024 22:03:32 +0200 Subject: [PATCH 309/342] power: supply: axp288_charger: Fix constant_charge_voltage writes commit b34ce4a59cfe9cd0d6f870e6408e8ec88a964585 upstream. info->max_cv is in millivolts, divide the microvolt value being written to constant_charge_voltage by 1000 *before* clamping it to info->max_cv. Before this fix the code always tried to set constant_charge_voltage to max_cv / 1000 = 4 millivolt, which ends up in setting it to 4.1V which is the lowest supported value. Fixes: 843735b788a4 ("power: axp288_charger: axp288 charger driver") Cc: stable@vger.kernel.org Signed-off-by: Hans de Goede Link: https://lore.kernel.org/r/20240717200333.56669-1-hdegoede@redhat.com Signed-off-by: Sebastian Reichel Signed-off-by: Greg Kroah-Hartman --- drivers/power/supply/axp288_charger.c | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-) diff --git a/drivers/power/supply/axp288_charger.c b/drivers/power/supply/axp288_charger.c index f65bf7b295c5..a65357094147 100644 --- a/drivers/power/supply/axp288_charger.c +++ b/drivers/power/supply/axp288_charger.c @@ -371,8 +371,8 @@ static int axp288_charger_usb_set_property(struct power_supply *psy, dev_warn(&info->pdev->dev, "set charge current failed\n"); break; case POWER_SUPPLY_PROP_CONSTANT_CHARGE_VOLTAGE: - scaled_val = min(val->intval, info->max_cv); - scaled_val = DIV_ROUND_CLOSEST(scaled_val, 1000); + scaled_val = DIV_ROUND_CLOSEST(val->intval, 1000); + scaled_val = min(scaled_val, info->max_cv); ret = axp288_charger_set_cv(info, scaled_val); if (ret < 0) dev_warn(&info->pdev->dev, "set charge voltage failed\n"); From ca2ea2dec107b742f4b21eb8f85e5d8256afe9fa Mon Sep 17 00:00:00 2001 From: Hans de Goede Date: Wed, 17 Jul 2024 22:03:33 +0200 Subject: [PATCH 310/342] power: supply: axp288_charger: Round constant_charge_voltage writes down commit 81af7f2342d162e24ac820c10e68684d9f927663 upstream. Round constant_charge_voltage writes down to the first supported lower value, rather then rounding them up to the first supported higher value. This fixes e.g. writing 4250000 resulting in a value of 4350000 which might be dangerous, instead writing 4250000 will now result in a safe 4200000 value. Fixes: 843735b788a4 ("power: axp288_charger: axp288 charger driver") Cc: stable@vger.kernel.org Signed-off-by: Hans de Goede Link: https://lore.kernel.org/r/20240717200333.56669-2-hdegoede@redhat.com Signed-off-by: Sebastian Reichel Signed-off-by: Greg Kroah-Hartman --- drivers/power/supply/axp288_charger.c | 20 ++++++++++---------- 1 file changed, 10 insertions(+), 10 deletions(-) diff --git a/drivers/power/supply/axp288_charger.c b/drivers/power/supply/axp288_charger.c index a65357094147..c4f1a2bac333 100644 --- a/drivers/power/supply/axp288_charger.c +++ b/drivers/power/supply/axp288_charger.c @@ -168,18 +168,18 @@ static inline int axp288_charger_set_cv(struct axp288_chrg_info *info, int cv) u8 reg_val; int ret; - if (cv <= CV_4100MV) { - reg_val = CHRG_CCCV_CV_4100MV; - cv = CV_4100MV; - } else if (cv <= CV_4150MV) { - reg_val = CHRG_CCCV_CV_4150MV; - cv = CV_4150MV; - } else if (cv <= CV_4200MV) { - reg_val = CHRG_CCCV_CV_4200MV; - cv = CV_4200MV; - } else { + if (cv >= CV_4350MV) { reg_val = CHRG_CCCV_CV_4350MV; cv = CV_4350MV; + } else if (cv >= CV_4200MV) { + reg_val = CHRG_CCCV_CV_4200MV; + cv = CV_4200MV; + } else if (cv >= CV_4150MV) { + reg_val = CHRG_CCCV_CV_4150MV; + cv = CV_4150MV; + } else { + reg_val = CHRG_CCCV_CV_4100MV; + cv = CV_4100MV; } reg_val = reg_val << CHRG_CCCV_CV_BIT_POS; From eb223bf01e688dfe37e813c8988ee11c8c9f8d0a Mon Sep 17 00:00:00 2001 From: Tze-nan Wu Date: Mon, 5 Aug 2024 13:59:22 +0800 Subject: [PATCH 311/342] tracing: Fix overflow in get_free_elt() commit bcf86c01ca4676316557dd482c8416ece8c2e143 upstream. "tracing_map->next_elt" in get_free_elt() is at risk of overflowing. Once it overflows, new elements can still be inserted into the tracing_map even though the maximum number of elements (`max_elts`) has been reached. Continuing to insert elements after the overflow could result in the tracing_map containing "tracing_map->max_size" elements, leaving no empty entries. If any attempt is made to insert an element into a full tracing_map using `__tracing_map_insert()`, it will cause an infinite loop with preemption disabled, leading to a CPU hang problem. Fix this by preventing any further increments to "tracing_map->next_elt" once it reaches "tracing_map->max_elt". Cc: stable@vger.kernel.org Cc: Masami Hiramatsu Fixes: 08d43a5fa063e ("tracing: Add lock-free tracing_map") Co-developed-by: Cheng-Jui Wang Link: https://lore.kernel.org/20240805055922.6277-1-Tze-nan.Wu@mediatek.com Signed-off-by: Cheng-Jui Wang Signed-off-by: Tze-nan Wu Signed-off-by: Steven Rostedt (Google) Signed-off-by: Greg Kroah-Hartman --- kernel/trace/tracing_map.c | 6 +++--- 1 file changed, 3 insertions(+), 3 deletions(-) diff --git a/kernel/trace/tracing_map.c b/kernel/trace/tracing_map.c index d47641f9740b..e6cc8d5ab1a4 100644 --- a/kernel/trace/tracing_map.c +++ b/kernel/trace/tracing_map.c @@ -454,7 +454,7 @@ static struct tracing_map_elt *get_free_elt(struct tracing_map *map) struct tracing_map_elt *elt = NULL; int idx; - idx = atomic_inc_return(&map->next_elt); + idx = atomic_fetch_add_unless(&map->next_elt, 1, map->max_elts); if (idx < map->max_elts) { elt = *(TRACING_MAP_ELT(map->elts, idx)); if (map->ops && map->ops->elt_init) @@ -699,7 +699,7 @@ void tracing_map_clear(struct tracing_map *map) { unsigned int i; - atomic_set(&map->next_elt, -1); + atomic_set(&map->next_elt, 0); atomic64_set(&map->hits, 0); atomic64_set(&map->drops, 0); @@ -783,7 +783,7 @@ struct tracing_map *tracing_map_create(unsigned int map_bits, map->map_bits = map_bits; map->max_elts = (1 << map_bits); - atomic_set(&map->next_elt, -1); + atomic_set(&map->next_elt, 0); map->map_size = (1 << (map_bits + 1)); map->ops = ops; From ab8b397d5997d8c37610252528edc54bebf9f6d3 Mon Sep 17 00:00:00 2001 From: Waiman Long Date: Tue, 6 Aug 2024 13:46:47 -0400 Subject: [PATCH 312/342] padata: Fix possible divide-by-0 panic in padata_mt_helper() commit 6d45e1c948a8b7ed6ceddb14319af69424db730c upstream. We are hit with a not easily reproducible divide-by-0 panic in padata.c at bootup time. [ 10.017908] Oops: divide error: 0000 1 PREEMPT SMP NOPTI [ 10.017908] CPU: 26 PID: 2627 Comm: kworker/u1666:1 Not tainted 6.10.0-15.el10.x86_64 #1 [ 10.017908] Hardware name: Lenovo ThinkSystem SR950 [7X12CTO1WW]/[7X12CTO1WW], BIOS [PSE140J-2.30] 07/20/2021 [ 10.017908] Workqueue: events_unbound padata_mt_helper [ 10.017908] RIP: 0010:padata_mt_helper+0x39/0xb0 : [ 10.017963] Call Trace: [ 10.017968] [ 10.018004] ? padata_mt_helper+0x39/0xb0 [ 10.018084] process_one_work+0x174/0x330 [ 10.018093] worker_thread+0x266/0x3a0 [ 10.018111] kthread+0xcf/0x100 [ 10.018124] ret_from_fork+0x31/0x50 [ 10.018138] ret_from_fork_asm+0x1a/0x30 [ 10.018147] Looking at the padata_mt_helper() function, the only way a divide-by-0 panic can happen is when ps->chunk_size is 0. The way that chunk_size is initialized in padata_do_multithreaded(), chunk_size can be 0 when the min_chunk in the passed-in padata_mt_job structure is 0. Fix this divide-by-0 panic by making sure that chunk_size will be at least 1 no matter what the input parameters are. Link: https://lkml.kernel.org/r/20240806174647.1050398-1-longman@redhat.com Fixes: 004ed42638f4 ("padata: add basic support for multithreaded jobs") Signed-off-by: Waiman Long Cc: Daniel Jordan Cc: Steffen Klassert Cc: Waiman Long Cc: Signed-off-by: Andrew Morton Signed-off-by: Greg Kroah-Hartman --- kernel/padata.c | 7 +++++++ 1 file changed, 7 insertions(+) diff --git a/kernel/padata.c b/kernel/padata.c index 471ccbc44541..2a514cf8379b 100644 --- a/kernel/padata.c +++ b/kernel/padata.c @@ -521,6 +521,13 @@ void __init padata_do_multithreaded(struct padata_mt_job *job) ps.chunk_size = max(ps.chunk_size, job->min_chunk); ps.chunk_size = roundup(ps.chunk_size, job->align); + /* + * chunk_size can be 0 if the caller sets min_chunk to 0. So force it + * to at least 1 to prevent divide-by-0 panic in padata_mt_helper().` + */ + if (!ps.chunk_size) + ps.chunk_size = 1U; + list_for_each_entry(pw, &works, pw_list) queue_work(system_unbound_wq, &pw->pw_work); From 450b6b22acdaac67a18eaf5ed498421ffcf10051 Mon Sep 17 00:00:00 2001 From: Andi Kleen Date: Wed, 7 Aug 2024 17:02:44 -0700 Subject: [PATCH 313/342] x86/mtrr: Check if fixed MTRRs exist before saving them commit 919f18f961c03d6694aa726c514184f2311a4614 upstream. MTRRs have an obsolete fixed variant for fine grained caching control of the 640K-1MB region that uses separate MSRs. This fixed variant has a separate capability bit in the MTRR capability MSR. So far all x86 CPUs which support MTRR have this separate bit set, so it went unnoticed that mtrr_save_state() does not check the capability bit before accessing the fixed MTRR MSRs. Though on a CPU that does not support the fixed MTRR capability this results in a #GP. The #GP itself is harmless because the RDMSR fault is handled gracefully, but results in a WARN_ON(). Add the missing capability check to prevent this. Fixes: 2b1f6278d77c ("[PATCH] x86: Save the MTRRs of the BSP before booting an AP") Signed-off-by: Andi Kleen Signed-off-by: Thomas Gleixner Cc: stable@vger.kernel.org Link: https://lore.kernel.org/all/20240808000244.946864-1-ak@linux.intel.com Signed-off-by: Greg Kroah-Hartman --- arch/x86/kernel/cpu/mtrr/mtrr.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/arch/x86/kernel/cpu/mtrr/mtrr.c b/arch/x86/kernel/cpu/mtrr/mtrr.c index 5f436cb4f7c4..9d5313118660 100644 --- a/arch/x86/kernel/cpu/mtrr/mtrr.c +++ b/arch/x86/kernel/cpu/mtrr/mtrr.c @@ -817,7 +817,7 @@ void mtrr_save_state(void) { int first_cpu; - if (!mtrr_enabled()) + if (!mtrr_enabled() || !mtrr_state.have_fixed) return; first_cpu = cpumask_first(cpu_online_mask); From fd65cf86ca3c3db49e56488fd66f75212124071c Mon Sep 17 00:00:00 2001 From: Lucas Stach Date: Mon, 18 Mar 2024 21:39:23 +0100 Subject: [PATCH 314/342] drm/bridge: analogix_dp: properly handle zero sized AUX transactions commit e82290a2e0e8ec5e836ecad1ca025021b3855c2d upstream. Address only transactions without any data are valid and should not be flagged as short transactions. Simply return the message size when no transaction errors occured. CC: stable@vger.kernel.org Signed-off-by: Lucas Stach Reviewed-by: Robert Foss Signed-off-by: Robert Foss Link: https://patchwork.freedesktop.org/patch/msgid/20240318203925.2837689-1-l.stach@pengutronix.de Signed-off-by: Greg Kroah-Hartman --- drivers/gpu/drm/bridge/analogix/analogix_dp_reg.c | 5 +---- 1 file changed, 1 insertion(+), 4 deletions(-) diff --git a/drivers/gpu/drm/bridge/analogix/analogix_dp_reg.c b/drivers/gpu/drm/bridge/analogix/analogix_dp_reg.c index cab3f5c4e2fc..37c62794e213 100644 --- a/drivers/gpu/drm/bridge/analogix/analogix_dp_reg.c +++ b/drivers/gpu/drm/bridge/analogix/analogix_dp_reg.c @@ -1115,7 +1115,6 @@ ssize_t analogix_dp_transfer(struct analogix_dp_device *dp, u32 status_reg; u8 *buffer = msg->buffer; unsigned int i; - int num_transferred = 0; int ret; /* Buffer size of AUX CH is 16 bytes */ @@ -1167,7 +1166,6 @@ ssize_t analogix_dp_transfer(struct analogix_dp_device *dp, reg = buffer[i]; writel(reg, dp->reg_base + ANALOGIX_DP_BUF_DATA_0 + 4 * i); - num_transferred++; } } @@ -1215,7 +1213,6 @@ ssize_t analogix_dp_transfer(struct analogix_dp_device *dp, reg = readl(dp->reg_base + ANALOGIX_DP_BUF_DATA_0 + 4 * i); buffer[i] = (unsigned char)reg; - num_transferred++; } } @@ -1232,7 +1229,7 @@ ssize_t analogix_dp_transfer(struct analogix_dp_device *dp, (msg->request & ~DP_AUX_I2C_MOT) == DP_AUX_NATIVE_READ) msg->reply = DP_AUX_NATIVE_REPLY_ACK; - return num_transferred > 0 ? num_transferred : -EBUSY; + return msg->size; aux_error: /* if aux err happen, reset aux */ From 32b133fb7833996b4f01230bde4718cb4950a85c Mon Sep 17 00:00:00 2001 From: Thomas Zimmermann Date: Mon, 13 May 2024 14:51:06 +0200 Subject: [PATCH 315/342] drm/mgag200: Set DDC timeout in milliseconds commit ecde5db1598aecab54cc392282c15114f526f05f upstream. Compute the i2c timeout in jiffies from a value in milliseconds. The original values of 2 jiffies equals 2 milliseconds if HZ has been configured to a value of 1000. This corresponds to 2.2 milliseconds used by most other DRM drivers. Update mgag200 accordingly. Signed-off-by: Thomas Zimmermann Reviewed-by: Jocelyn Falempe Fixes: 414c45310625 ("mgag200: initial g200se driver (v2)") Cc: Dave Airlie Cc: Maarten Lankhorst Cc: Maxime Ripard Cc: Thomas Zimmermann Cc: Jocelyn Falempe Cc: dri-devel@lists.freedesktop.org Cc: # v3.5+ Link: https://patchwork.freedesktop.org/patch/msgid/20240513125620.6337-2-tzimmermann@suse.de Signed-off-by: Greg Kroah-Hartman --- drivers/gpu/drm/mgag200/mgag200_i2c.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/drivers/gpu/drm/mgag200/mgag200_i2c.c b/drivers/gpu/drm/mgag200/mgag200_i2c.c index 09731e614e46..40cda2468332 100644 --- a/drivers/gpu/drm/mgag200/mgag200_i2c.c +++ b/drivers/gpu/drm/mgag200/mgag200_i2c.c @@ -134,7 +134,7 @@ struct mga_i2c_chan *mgag200_i2c_create(struct drm_device *dev) i2c->adapter.algo_data = &i2c->bit; i2c->bit.udelay = 10; - i2c->bit.timeout = 2; + i2c->bit.timeout = usecs_to_jiffies(2200); i2c->bit.data = i2c; i2c->bit.setsda = mga_gpio_setsda; i2c->bit.setscl = mga_gpio_setscl; From 381cad7a0873c09dbae81137716ee3387a15148e Mon Sep 17 00:00:00 2001 From: "Matthieu Baerts (NGI0)" Date: Fri, 9 Aug 2024 12:54:13 +0200 Subject: [PATCH 316/342] mptcp: sched: check both directions for backup commit b6a66e521a2032f7fcba2af5a9bcbaeaa19b7ca3 upstream. The 'mptcp_subflow_context' structure has two items related to the backup flags: - 'backup': the subflow has been marked as backup by the other peer - 'request_bkup': the backup flag has been set by the host Before this patch, the scheduler was only looking at the 'backup' flag. That can make sense in some cases, but it looks like that's not what we wanted for the general use, because either the path-manager was setting both of them when sending an MP_PRIO, or the receiver was duplicating the 'backup' flag in the subflow request. Note that the use of these two flags in the path-manager are going to be fixed in the next commits, but this change here is needed not to modify the behaviour. Fixes: f296234c98a8 ("mptcp: Add handling of incoming MP_JOIN requests") Cc: stable@vger.kernel.org Reviewed-by: Mat Martineau Signed-off-by: Matthieu Baerts (NGI0) Signed-off-by: Paolo Abeni [ Conflicts in protocol.c, because the context has changed in commit 3ce0852c86b9 ("mptcp: enforce HoL-blocking estimation") and in commit 33d41c9cd74c ("mptcp: more accurate timeout"), which are not in this version. This commit is unrelated to this modification. Note that the tracepoint is not in this version, see commit e10a98920976 ("mptcp: add tracepoint in mptcp_subflow_get_send"). ] Signed-off-by: Matthieu Baerts (NGI0) Signed-off-by: Greg Kroah-Hartman --- net/mptcp/protocol.c | 10 ++++++---- 1 file changed, 6 insertions(+), 4 deletions(-) diff --git a/net/mptcp/protocol.c b/net/mptcp/protocol.c index a36493bbf895..a343b3077458 100644 --- a/net/mptcp/protocol.c +++ b/net/mptcp/protocol.c @@ -1124,11 +1124,13 @@ static struct sock *mptcp_subflow_get_send(struct mptcp_sock *msk, send_info[i].ratio = -1; } mptcp_for_each_subflow(msk, subflow) { + bool backup = subflow->backup || subflow->request_bkup; + ssk = mptcp_subflow_tcp_sock(subflow); if (!mptcp_subflow_active(subflow)) continue; - nr_active += !subflow->backup; + nr_active += !backup; *sndbuf = max(tcp_sk(ssk)->snd_wnd, *sndbuf); if (!sk_stream_memory_free(subflow->tcp_sock)) continue; @@ -1139,9 +1141,9 @@ static struct sock *mptcp_subflow_get_send(struct mptcp_sock *msk, ratio = div_u64((u64)READ_ONCE(ssk->sk_wmem_queued) << 32, pace); - if (ratio < send_info[subflow->backup].ratio) { - send_info[subflow->backup].ssk = ssk; - send_info[subflow->backup].ratio = ratio; + if (ratio < send_info[backup].ratio) { + send_info[backup].ssk = ssk; + send_info[backup].ratio = ratio; } } From 1008f2bcbc8e461c1df3aebba30ac4f616ebe570 Mon Sep 17 00:00:00 2001 From: "Matthieu Baerts (NGI0)" Date: Fri, 9 Aug 2024 12:54:31 +0200 Subject: [PATCH 317/342] mptcp: distinguish rcv vs sent backup flag in requests commit efd340bf3d7779a3a8ec954d8ec0fb8a10f24982 upstream. When sending an MP_JOIN + SYN + ACK, it is possible to mark the subflow as 'backup' by setting the flag with the same name. Before this patch, the backup was set if the other peer set it in its MP_JOIN + SYN request. It is not correct: the backup flag should be set in the MPJ+SYN+ACK only if the host asks for it, and not mirroring what was done by the other peer. It is then required to have a dedicated bit for each direction, similar to what is done in the subflow context. Fixes: f296234c98a8 ("mptcp: Add handling of incoming MP_JOIN requests") Cc: stable@vger.kernel.org Reviewed-by: Mat Martineau Signed-off-by: Matthieu Baerts (NGI0) Signed-off-by: Paolo Abeni [ Conflicts in subflow.c, because the context has changed in commit 4cf86ae84c71 ("mptcp: strict local address ID selection"), and in commit 967d3c27127e ("mptcp: fix data races on remote_id"), which are not in this version. These commits are unrelated to this modification. Same in protocol.h, with commit bab6b88e0560 ("mptcp: add allow_join_id0 in mptcp_out_options"). ] Signed-off-by: Matthieu Baerts (NGI0) Signed-off-by: Greg Kroah-Hartman --- net/mptcp/options.c | 2 +- net/mptcp/protocol.h | 3 ++- net/mptcp/subflow.c | 1 + 3 files changed, 4 insertions(+), 2 deletions(-) diff --git a/net/mptcp/options.c b/net/mptcp/options.c index c389d7e47135..f7a91266d5a9 100644 --- a/net/mptcp/options.c +++ b/net/mptcp/options.c @@ -708,7 +708,7 @@ bool mptcp_synack_options(const struct request_sock *req, unsigned int *size, return true; } else if (subflow_req->mp_join) { opts->suboptions = OPTION_MPTCP_MPJ_SYNACK; - opts->backup = subflow_req->backup; + opts->backup = subflow_req->request_bkup; opts->join_id = subflow_req->local_id; opts->thmac = subflow_req->thmac; opts->nonce = subflow_req->local_nonce; diff --git a/net/mptcp/protocol.h b/net/mptcp/protocol.h index 3e5af8397434..b5978bb4022f 100644 --- a/net/mptcp/protocol.h +++ b/net/mptcp/protocol.h @@ -261,7 +261,8 @@ struct mptcp_subflow_request_sock { struct tcp_request_sock sk; u16 mp_capable : 1, mp_join : 1, - backup : 1; + backup : 1, + request_bkup : 1; u8 local_id; u8 remote_id; u64 local_key; diff --git a/net/mptcp/subflow.c b/net/mptcp/subflow.c index 823a92b21c6c..a59c731d7fed 100644 --- a/net/mptcp/subflow.c +++ b/net/mptcp/subflow.c @@ -1395,6 +1395,7 @@ static void subflow_ulp_clone(const struct request_sock *req, new_ctx->mp_join = 1; new_ctx->fully_established = 1; new_ctx->backup = subflow_req->backup; + new_ctx->request_bkup = subflow_req->request_bkup; new_ctx->local_id = subflow_req->local_id; new_ctx->remote_id = subflow_req->remote_id; new_ctx->token = subflow_req->token; From 96f3c8a85021e48a00c0be6221bfc6fe2c8d0a5e Mon Sep 17 00:00:00 2001 From: Paolo Abeni Date: Fri, 9 Aug 2024 12:54:50 +0200 Subject: [PATCH 318/342] mptcp: fix NL PM announced address accounting commit 4b317e0eb287bd30a1b329513531157c25e8b692 upstream. Currently the per connection announced address counter is never decreased. As a consequence, after connection establishment, if the NL PM deletes an endpoint and adds a new/different one, no additional subflow is created for the new endpoint even if the current limits allow that. Address the issue properly updating the signaled address counter every time the NL PM removes such addresses. Fixes: 01cacb00b35c ("mptcp: add netlink-based PM") Cc: stable@vger.kernel.org Signed-off-by: Paolo Abeni Reviewed-by: Matthieu Baerts (NGI0) Signed-off-by: Matthieu Baerts (NGI0) Signed-off-by: David S. Miller [ Conflicts in pm_netlink.c, because the commit 06faa2271034 ("mptcp: remove multi addresses and subflows in PM") is not in this version. Only the modification in mptcp_pm_remove_anno_addr() is then needed. ] Signed-off-by: Matthieu Baerts (NGI0) Signed-off-by: Greg Kroah-Hartman --- net/mptcp/pm_netlink.c | 1 + 1 file changed, 1 insertion(+) diff --git a/net/mptcp/pm_netlink.c b/net/mptcp/pm_netlink.c index 452c7e21befd..7f4d84f5189b 100644 --- a/net/mptcp/pm_netlink.c +++ b/net/mptcp/pm_netlink.c @@ -759,6 +759,7 @@ static bool mptcp_pm_remove_anno_addr(struct mptcp_sock *msk, ret = remove_anno_list_by_saddr(msk, addr); if (ret || force) { spin_lock_bh(&msk->pm.lock); + msk->pm.add_addr_signaled -= ret; mptcp_pm_remove_addr(msk, addr->id); spin_unlock_bh(&msk->pm.lock); } From 9b9a64ef9a1adba5983bd70ac3b8b4ba64f66821 Mon Sep 17 00:00:00 2001 From: "Matthieu Baerts (NGI0)" Date: Fri, 9 Aug 2024 12:55:15 +0200 Subject: [PATCH 319/342] mptcp: mib: count MPJ with backup flag commit 4dde0d72ccec500c60c798e036b852e013d6e124 upstream. Without such counters, it is difficult to easily debug issues with MPJ not having the backup flags on production servers. This is not strictly a fix, but it eases to validate the following patches without requiring to take packet traces, to query ongoing connections with Netlink with admin permissions, or to guess by looking at the behaviour of the packet scheduler. Also, the modification is self contained, isolated, well controlled, and the increments are done just after others, there from the beginning. It looks then safe, and helpful to backport this. Fixes: 4596a2c1b7f5 ("mptcp: allow creating non-backup subflows") Cc: stable@vger.kernel.org Reviewed-by: Mat Martineau Signed-off-by: Matthieu Baerts (NGI0) Signed-off-by: Paolo Abeni [ Conflicts in subflow.c because the context has changed in commit b3ea6b272d79 ("mptcp: consolidate initial ack seq generation") and commit 5bc56388c74f ("mptcp: add port number check for MP_JOIN") which are not in this version. These commits are unrelated to this modification. ] Signed-off-by: Matthieu Baerts (NGI0) Signed-off-by: Greg Kroah-Hartman --- net/mptcp/mib.c | 2 ++ net/mptcp/mib.h | 2 ++ net/mptcp/subflow.c | 6 ++++++ 3 files changed, 10 insertions(+) diff --git a/net/mptcp/mib.c b/net/mptcp/mib.c index b921cbdd9aaa..f4034e000f3e 100644 --- a/net/mptcp/mib.c +++ b/net/mptcp/mib.c @@ -16,7 +16,9 @@ static const struct snmp_mib mptcp_snmp_list[] = { SNMP_MIB_ITEM("MPTCPRetrans", MPTCP_MIB_RETRANSSEGS), SNMP_MIB_ITEM("MPJoinNoTokenFound", MPTCP_MIB_JOINNOTOKEN), SNMP_MIB_ITEM("MPJoinSynRx", MPTCP_MIB_JOINSYNRX), + SNMP_MIB_ITEM("MPJoinSynBackupRx", MPTCP_MIB_JOINSYNBACKUPRX), SNMP_MIB_ITEM("MPJoinSynAckRx", MPTCP_MIB_JOINSYNACKRX), + SNMP_MIB_ITEM("MPJoinSynAckBackupRx", MPTCP_MIB_JOINSYNACKBACKUPRX), SNMP_MIB_ITEM("MPJoinSynAckHMacFailure", MPTCP_MIB_JOINSYNACKMAC), SNMP_MIB_ITEM("MPJoinAckRx", MPTCP_MIB_JOINACKRX), SNMP_MIB_ITEM("MPJoinAckHMacFailure", MPTCP_MIB_JOINACKMAC), diff --git a/net/mptcp/mib.h b/net/mptcp/mib.h index 47bcecce1106..a9f43ff00b3c 100644 --- a/net/mptcp/mib.h +++ b/net/mptcp/mib.h @@ -9,7 +9,9 @@ enum linux_mptcp_mib_field { MPTCP_MIB_RETRANSSEGS, /* Segments retransmitted at the MPTCP-level */ MPTCP_MIB_JOINNOTOKEN, /* Received MP_JOIN but the token was not found */ MPTCP_MIB_JOINSYNRX, /* Received a SYN + MP_JOIN */ + MPTCP_MIB_JOINSYNBACKUPRX, /* Received a SYN + MP_JOIN + backup flag */ MPTCP_MIB_JOINSYNACKRX, /* Received a SYN/ACK + MP_JOIN */ + MPTCP_MIB_JOINSYNACKBACKUPRX, /* Received a SYN/ACK + MP_JOIN + backup flag */ MPTCP_MIB_JOINSYNACKMAC, /* HMAC was wrong on SYN/ACK + MP_JOIN */ MPTCP_MIB_JOINACKRX, /* Received an ACK + MP_JOIN */ MPTCP_MIB_JOINACKMAC, /* HMAC was wrong on ACK + MP_JOIN */ diff --git a/net/mptcp/subflow.c b/net/mptcp/subflow.c index a59c731d7fed..f4067484727e 100644 --- a/net/mptcp/subflow.c +++ b/net/mptcp/subflow.c @@ -135,6 +135,9 @@ static void subflow_init_req(struct request_sock *req, return; } else if (mp_opt.mp_join) { SUBFLOW_REQ_INC_STATS(req, MPTCP_MIB_JOINSYNRX); + + if (mp_opt.backup) + SUBFLOW_REQ_INC_STATS(req, MPTCP_MIB_JOINSYNBACKUPRX); } if (mp_opt.mp_capable && listener->request_mptcp) { @@ -347,6 +350,9 @@ static void subflow_finish_connect(struct sock *sk, const struct sk_buff *skb) subflow->mp_join = 1; MPTCP_INC_STATS(sock_net(sk), MPTCP_MIB_JOINSYNACKRX); + + if (subflow->backup) + MPTCP_INC_STATS(sock_net(sk), MPTCP_MIB_JOINSYNACKBACKUPRX); } else if (mptcp_check_fallback(sk)) { fallback: mptcp_rcv_space_init(mptcp_sk(parent), sk); From 44165604dd6e62de432198af4b428a910b97edaa Mon Sep 17 00:00:00 2001 From: Geliang Tang Date: Fri, 9 Aug 2024 12:55:39 +0200 Subject: [PATCH 320/342] mptcp: export local_address commit dc886bce753cc2cf3c88ec5c7a6880a4e17d65ba upstream. Rename local_address() with "mptcp_" prefix and export it in protocol.h. This function will be re-used in the common PM code (pm.c) in the following commit. Signed-off-by: Geliang Tang Reviewed-by: Matthieu Baerts Signed-off-by: Matthieu Baerts Reviewed-by: Larysa Zaremba Signed-off-by: Jakub Kicinski Stable-dep-of: 6834097fc38c ("mptcp: pm: fix backup support in signal endpoints") [ Conflicts in pm_netlink.c and protocol.h, because the context has changed in commit 4638de5aefe5 ("mptcp: handle local addrs announced by userspace PMs") which is not in this version. This commit is unrelated to this modification. Also some parts using 'local_address' are not in this version, that's OK, we don't need to do anything with them. ] Signed-off-by: Matthieu Baerts (NGI0) Signed-off-by: Greg Kroah-Hartman --- net/mptcp/pm_netlink.c | 9 ++++----- net/mptcp/protocol.h | 1 + 2 files changed, 5 insertions(+), 5 deletions(-) diff --git a/net/mptcp/pm_netlink.c b/net/mptcp/pm_netlink.c index 7f4d84f5189b..6a0079d42dc4 100644 --- a/net/mptcp/pm_netlink.c +++ b/net/mptcp/pm_netlink.c @@ -84,8 +84,7 @@ static bool address_zero(const struct mptcp_addr_info *addr) return addresses_equal(addr, &zero, false); } -static void local_address(const struct sock_common *skc, - struct mptcp_addr_info *addr) +void mptcp_local_address(const struct sock_common *skc, struct mptcp_addr_info *addr) { addr->port = 0; addr->family = skc->skc_family; @@ -120,7 +119,7 @@ static bool lookup_subflow_by_saddr(const struct list_head *list, list_for_each_entry(subflow, list, node) { skc = (struct sock_common *)mptcp_subflow_tcp_sock(subflow); - local_address(skc, &cur); + mptcp_local_address(skc, &cur); if (addresses_equal(&cur, saddr, false)) return true; } @@ -533,8 +532,8 @@ int mptcp_pm_nl_get_local_id(struct mptcp_sock *msk, struct sock_common *skc) /* The 0 ID mapping is defined by the first subflow, copied into the msk * addr */ - local_address((struct sock_common *)msk, &msk_local); - local_address((struct sock_common *)skc, &skc_local); + mptcp_local_address((struct sock_common *)msk, &msk_local); + mptcp_local_address((struct sock_common *)skc, &skc_local); if (addresses_equal(&msk_local, &skc_local, false)) return 0; diff --git a/net/mptcp/protocol.h b/net/mptcp/protocol.h index b5978bb4022f..ddfc7bde8c90 100644 --- a/net/mptcp/protocol.h +++ b/net/mptcp/protocol.h @@ -372,6 +372,7 @@ void __mptcp_close_ssk(struct sock *sk, struct sock *ssk, struct mptcp_subflow_context *subflow, long timeout); void mptcp_subflow_reset(struct sock *ssk); +void mptcp_local_address(const struct sock_common *skc, struct mptcp_addr_info *addr); /* called with sk socket lock held */ int __mptcp_subflow_connect(struct sock *sk, const struct mptcp_addr_info *loc, From 3f84b37abb8f3a62fa0ebba6b9b50b9f2fdd1a23 Mon Sep 17 00:00:00 2001 From: "Matthieu Baerts (NGI0)" Date: Fri, 9 Aug 2024 12:55:40 +0200 Subject: [PATCH 321/342] mptcp: pm: fix backup support in signal endpoints commit 6834097fc38c5416701c793da94558cea49c0a1f upstream. There was a support for signal endpoints, but only when the endpoint's flag was changed during a connection. If an endpoint with the signal and backup was already present, the MP_JOIN reply was not containing the backup flag as expected. That's confusing to have this inconsistent behaviour. On the other hand, the infrastructure to set the backup flag in the SYN + ACK + MP_JOIN was already there, it was just never set before. Now when requesting the local ID from the path-manager, the backup status is also requested. Note that when the userspace PM is used, the backup flag can be set if the local address was already used before with a backup flag, e.g. if the address was announced with the 'backup' flag, or a subflow was created with the 'backup' flag. Fixes: 4596a2c1b7f5 ("mptcp: allow creating non-backup subflows") Cc: stable@vger.kernel.org Closes: https://github.com/multipath-tcp/mptcp_net-next/issues/507 Reviewed-by: Mat Martineau Signed-off-by: Matthieu Baerts (NGI0) Signed-off-by: Paolo Abeni [ Conflicts in pm_userspace.c because the context has changed in commit 1e07938e29c5 ("net: mptcp: rename netlink handlers to mptcp_pm_nl__{doit,dumpit}") which is not in this version. This commit is unrelated to this modification. Conflicts in protocol.h because the context has changed in commit 9ae7846c4b6b ("mptcp: dump addrs in userspace pm list") which is not in this version. This commit is unrelated to this modification. Conflicts in pm.c because the context has changed in commit f40be0db0b76 ("mptcp: unify pm get_flags_and_ifindex_by_id") and commit 71b7dec27f34 ("mptcp: less aggressive retransmission strategy") which are not in this version. These commits are unrelated to this modification. Conflicts in subflow.c, because the commit 4cf86ae84c71 ("mptcp: strict local address ID selection") is not in this version. It is then not needed to modify the subflow_chk_local_id() helper, which is not in this version. Also, in this version, there is no pm_userspace.c, because this PM has been added in v5.19, which also causes conflicts in protocol.h, and pm_netlink.c. Plus the code in pm.c can be simplified, as there is no userspace PM. And the code in pm_netlink.c needs to use addresses_equal() instead of mptcp_addresses_equal(), see commit 4638de5aefe5 ("mptcp: handle local addrs announced by userspace PMs"). The code in pm_netlink.c also needs to be adapted because the pm_nl_get_pernet_from_msk() helper is not in this version, introduced later in commit c682bf536cf4 ("mptcp: add pm_nl_pernet helpers"), and also because the 'flags' are in mptcp_addr_info structure, see commit daa83ab03954 ("mptcp: move flags and ifindex out of mptcp_addr_info"). ] Signed-off-by: Matthieu Baerts (NGI0) Signed-off-by: Matthieu Baerts (NGI0) Signed-off-by: Greg Kroah-Hartman --- net/mptcp/pm.c | 9 +++++++++ net/mptcp/pm_netlink.c | 20 ++++++++++++++++++++ net/mptcp/protocol.h | 2 ++ net/mptcp/subflow.c | 1 + 4 files changed, 32 insertions(+) diff --git a/net/mptcp/pm.c b/net/mptcp/pm.c index e19e1525ecbb..1f310abbf1ed 100644 --- a/net/mptcp/pm.c +++ b/net/mptcp/pm.c @@ -225,6 +225,15 @@ int mptcp_pm_get_local_id(struct mptcp_sock *msk, struct sock_common *skc) return mptcp_pm_nl_get_local_id(msk, skc); } +bool mptcp_pm_is_backup(struct mptcp_sock *msk, struct sock_common *skc) +{ + struct mptcp_addr_info skc_local; + + mptcp_local_address((struct sock_common *)skc, &skc_local); + + return mptcp_pm_nl_is_backup(msk, &skc_local); +} + void mptcp_pm_data_init(struct mptcp_sock *msk) { msk->pm.add_addr_signaled = 0; diff --git a/net/mptcp/pm_netlink.c b/net/mptcp/pm_netlink.c index 6a0079d42dc4..ca57d856d5df 100644 --- a/net/mptcp/pm_netlink.c +++ b/net/mptcp/pm_netlink.c @@ -568,6 +568,26 @@ int mptcp_pm_nl_get_local_id(struct mptcp_sock *msk, struct sock_common *skc) return ret; } +bool mptcp_pm_nl_is_backup(struct mptcp_sock *msk, struct mptcp_addr_info *skc) +{ + struct mptcp_pm_addr_entry *entry; + struct pm_nl_pernet *pernet; + bool backup = false; + + pernet = net_generic(sock_net((struct sock *)msk), pm_nl_pernet_id); + + rcu_read_lock(); + list_for_each_entry_rcu(entry, &pernet->local_addr_list, list) { + if (addresses_equal(&entry->addr, skc, entry->addr.port)) { + backup = !!(entry->addr.flags & MPTCP_PM_ADDR_FLAG_BACKUP); + break; + } + } + rcu_read_unlock(); + + return backup; +} + void mptcp_pm_nl_data_init(struct mptcp_sock *msk) { struct mptcp_pm_data *pm = &msk->pm; diff --git a/net/mptcp/protocol.h b/net/mptcp/protocol.h index ddfc7bde8c90..4348bccb982f 100644 --- a/net/mptcp/protocol.h +++ b/net/mptcp/protocol.h @@ -481,6 +481,7 @@ bool mptcp_pm_add_addr_signal(struct mptcp_sock *msk, unsigned int remaining, bool mptcp_pm_rm_addr_signal(struct mptcp_sock *msk, unsigned int remaining, u8 *rm_id); int mptcp_pm_get_local_id(struct mptcp_sock *msk, struct sock_common *skc); +bool mptcp_pm_is_backup(struct mptcp_sock *msk, struct sock_common *skc); void __init mptcp_pm_nl_init(void); void mptcp_pm_nl_data_init(struct mptcp_sock *msk); @@ -490,6 +491,7 @@ void mptcp_pm_nl_add_addr_received(struct mptcp_sock *msk); void mptcp_pm_nl_rm_addr_received(struct mptcp_sock *msk); void mptcp_pm_nl_rm_subflow_received(struct mptcp_sock *msk, u8 rm_id); int mptcp_pm_nl_get_local_id(struct mptcp_sock *msk, struct sock_common *skc); +bool mptcp_pm_nl_is_backup(struct mptcp_sock *msk, struct mptcp_addr_info *skc); static inline struct mptcp_ext *mptcp_get_ext(struct sk_buff *skb) { diff --git a/net/mptcp/subflow.c b/net/mptcp/subflow.c index f4067484727e..ba86cb06d6d8 100644 --- a/net/mptcp/subflow.c +++ b/net/mptcp/subflow.c @@ -80,6 +80,7 @@ static struct mptcp_sock *subflow_token_join_request(struct request_sock *req, return NULL; } subflow_req->local_id = local_id; + subflow_req->request_bkup = mptcp_pm_is_backup(msk, (struct sock_common *)req); get_random_bytes(&subflow_req->local_nonce, sizeof(u32)); From 5b9f49cc86bd3ffdd4ad5a3a2ba4782b75ed6a5a Mon Sep 17 00:00:00 2001 From: Gabriel Krisman Bertazi Date: Thu, 25 Jul 2024 11:32:27 -0400 Subject: [PATCH 322/342] samples: Add fs error monitoring example [ Upstream commit 5451093081db6ca1a708d149e11cfd219800bc4c ] Introduce an example of a FAN_FS_ERROR fanotify user to track filesystem errors. Link: https://lore.kernel.org/r/20211025192746.66445-31-krisman@collabora.com Reviewed-by: Amir Goldstein Reviewed-by: Jan Kara Signed-off-by: Gabriel Krisman Bertazi Signed-off-by: Jan Kara [ cel: adjusted to squelch a missing file warning on v5.10.y ] Signed-off-by: Chuck Lever Signed-off-by: Greg Kroah-Hartman --- samples/Kconfig | 8 ++ samples/Makefile | 1 + samples/fanotify/Makefile | 5 ++ samples/fanotify/fs-monitor.c | 142 ++++++++++++++++++++++++++++++++++ 4 files changed, 156 insertions(+) create mode 100644 samples/fanotify/Makefile create mode 100644 samples/fanotify/fs-monitor.c diff --git a/samples/Kconfig b/samples/Kconfig index e76cdfc50e25..cecd311ff321 100644 --- a/samples/Kconfig +++ b/samples/Kconfig @@ -120,6 +120,14 @@ config SAMPLE_CONNECTOR with it. See also Documentation/driver-api/connector.rst +config SAMPLE_FANOTIFY_ERROR + bool "Build fanotify error monitoring sample" + depends on FANOTIFY + help + When enabled, this builds an example code that uses the + FAN_FS_ERROR fanotify mechanism to monitor filesystem + errors. + config SAMPLE_HIDRAW bool "hidraw sample" depends on CC_CAN_LINK && HEADERS_INSTALL diff --git a/samples/Makefile b/samples/Makefile index c3392a595e4b..93e2d64bc9a7 100644 --- a/samples/Makefile +++ b/samples/Makefile @@ -5,6 +5,7 @@ subdir-$(CONFIG_SAMPLE_AUXDISPLAY) += auxdisplay subdir-$(CONFIG_SAMPLE_ANDROID_BINDERFS) += binderfs obj-$(CONFIG_SAMPLE_CONFIGFS) += configfs/ obj-$(CONFIG_SAMPLE_CONNECTOR) += connector/ +obj-$(CONFIG_SAMPLE_FANOTIFY_ERROR) += fanotify/ subdir-$(CONFIG_SAMPLE_HIDRAW) += hidraw obj-$(CONFIG_SAMPLE_HW_BREAKPOINT) += hw_breakpoint/ obj-$(CONFIG_SAMPLE_KDB) += kdb/ diff --git a/samples/fanotify/Makefile b/samples/fanotify/Makefile new file mode 100644 index 000000000000..e20db1bdde3b --- /dev/null +++ b/samples/fanotify/Makefile @@ -0,0 +1,5 @@ +# SPDX-License-Identifier: GPL-2.0-only +userprogs-always-y += fs-monitor + +userccflags += -I usr/include -Wall + diff --git a/samples/fanotify/fs-monitor.c b/samples/fanotify/fs-monitor.c new file mode 100644 index 000000000000..a0e44cd31e6f --- /dev/null +++ b/samples/fanotify/fs-monitor.c @@ -0,0 +1,142 @@ +// SPDX-License-Identifier: GPL-2.0 +/* + * Copyright 2021, Collabora Ltd. + */ + +#define _GNU_SOURCE +#include +#include +#include +#include +#include +#include +#include +#include +#include + +#ifndef FAN_FS_ERROR +#define FAN_FS_ERROR 0x00008000 +#define FAN_EVENT_INFO_TYPE_ERROR 5 + +struct fanotify_event_info_error { + struct fanotify_event_info_header hdr; + __s32 error; + __u32 error_count; +}; +#endif + +#ifndef FILEID_INO32_GEN +#define FILEID_INO32_GEN 1 +#endif + +#ifndef FILEID_INVALID +#define FILEID_INVALID 0xff +#endif + +static void print_fh(struct file_handle *fh) +{ + int i; + uint32_t *h = (uint32_t *) fh->f_handle; + + printf("\tfh: "); + for (i = 0; i < fh->handle_bytes; i++) + printf("%hhx", fh->f_handle[i]); + printf("\n"); + + printf("\tdecoded fh: "); + if (fh->handle_type == FILEID_INO32_GEN) + printf("inode=%u gen=%u\n", h[0], h[1]); + else if (fh->handle_type == FILEID_INVALID && !fh->handle_bytes) + printf("Type %d (Superblock error)\n", fh->handle_type); + else + printf("Type %d (Unknown)\n", fh->handle_type); + +} + +static void handle_notifications(char *buffer, int len) +{ + struct fanotify_event_metadata *event = + (struct fanotify_event_metadata *) buffer; + struct fanotify_event_info_header *info; + struct fanotify_event_info_error *err; + struct fanotify_event_info_fid *fid; + int off; + + for (; FAN_EVENT_OK(event, len); event = FAN_EVENT_NEXT(event, len)) { + + if (event->mask != FAN_FS_ERROR) { + printf("unexpected FAN MARK: %llx\n", event->mask); + goto next_event; + } + + if (event->fd != FAN_NOFD) { + printf("Unexpected fd (!= FAN_NOFD)\n"); + goto next_event; + } + + printf("FAN_FS_ERROR (len=%d)\n", event->event_len); + + for (off = sizeof(*event) ; off < event->event_len; + off += info->len) { + info = (struct fanotify_event_info_header *) + ((char *) event + off); + + switch (info->info_type) { + case FAN_EVENT_INFO_TYPE_ERROR: + err = (struct fanotify_event_info_error *) info; + + printf("\tGeneric Error Record: len=%d\n", + err->hdr.len); + printf("\terror: %d\n", err->error); + printf("\terror_count: %d\n", err->error_count); + break; + + case FAN_EVENT_INFO_TYPE_FID: + fid = (struct fanotify_event_info_fid *) info; + + printf("\tfsid: %x%x\n", + fid->fsid.val[0], fid->fsid.val[1]); + print_fh((struct file_handle *) &fid->handle); + break; + + default: + printf("\tUnknown info type=%d len=%d:\n", + info->info_type, info->len); + } + } +next_event: + printf("---\n\n"); + } +} + +int main(int argc, char **argv) +{ + int fd; + + char buffer[BUFSIZ]; + + if (argc < 2) { + printf("Missing path argument\n"); + return 1; + } + + fd = fanotify_init(FAN_CLASS_NOTIF|FAN_REPORT_FID, O_RDONLY); + if (fd < 0) + errx(1, "fanotify_init"); + + if (fanotify_mark(fd, FAN_MARK_ADD|FAN_MARK_FILESYSTEM, + FAN_FS_ERROR, AT_FDCWD, argv[1])) { + errx(1, "fanotify_mark"); + } + + while (1) { + int n = read(fd, buffer, BUFSIZ); + + if (n < 0) + errx(1, "read"); + + handle_notifications(buffer, n); + } + + return 0; +} From 9bdf0624bdbc7bfcdc3dc191fe0049ddd9a792cf Mon Sep 17 00:00:00 2001 From: Gabriel Krisman Bertazi Date: Thu, 25 Jul 2024 11:32:28 -0400 Subject: [PATCH 323/342] samples: Make fs-monitor depend on libc and headers [ Upstream commit 8fc70b3a142f97f7859bf052151df896933d2586 ] Prevent build errors when headers or libc are not available, such as on kernel build bots, like the below: samples/fanotify/fs-monitor.c:7:10: fatal error: errno.h: No such file or directory 7 | #include | ^~~~~~~~~ Link: https://lore.kernel.org/r/87fsslasgz.fsf@collabora.com Suggested-by: Guenter Roeck Tested-by: Guenter Roeck Signed-off-by: Gabriel Krisman Bertazi Signed-off-by: Jan Kara Signed-off-by: Chuck Lever Signed-off-by: Greg Kroah-Hartman --- samples/Kconfig | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/samples/Kconfig b/samples/Kconfig index cecd311ff321..a98e89992a18 100644 --- a/samples/Kconfig +++ b/samples/Kconfig @@ -122,7 +122,7 @@ config SAMPLE_CONNECTOR config SAMPLE_FANOTIFY_ERROR bool "Build fanotify error monitoring sample" - depends on FANOTIFY + depends on FANOTIFY && CC_CAN_LINK && HEADERS_INSTALL help When enabled, this builds an example code that uses the FAN_FS_ERROR fanotify mechanism to monitor filesystem From 329eae03d0f963cfd77ef2469e177e2c17b235f3 Mon Sep 17 00:00:00 2001 From: Linus Torvalds Date: Thu, 25 Jul 2024 11:32:29 -0400 Subject: [PATCH 324/342] Add gitignore file for samples/fanotify/ subdirectory [ Upstream commit c107fb9b4f8338375b3e865c3d2c1d98ccb3a95a ] Commit 5451093081db ("samples: Add fs error monitoring example") added a new sample program, but didn't teach git to ignore the new generated files, causing unnecessary noise from 'git status' after a full build. Add the 'fs-monitor' sample executable to the .gitignore for this subdirectory to silence it all again. Signed-off-by: Linus Torvalds Signed-off-by: Chuck Lever Signed-off-by: Greg Kroah-Hartman --- samples/fanotify/.gitignore | 1 + 1 file changed, 1 insertion(+) create mode 100644 samples/fanotify/.gitignore diff --git a/samples/fanotify/.gitignore b/samples/fanotify/.gitignore new file mode 100644 index 000000000000..d74593e8b2de --- /dev/null +++ b/samples/fanotify/.gitignore @@ -0,0 +1 @@ +fs-monitor From 7e62564d5e43f34f260db311cb6d1528d6189f6e Mon Sep 17 00:00:00 2001 From: Jari Ruusu Date: Fri, 26 Jul 2024 09:53:18 +0000 Subject: [PATCH 325/342] Fix gcc 4.9 build issue in 5.10.y Some older systems still compile kernels with old gcc version. These warnings and errors show up when compiling with gcc 4.9.2 error: "__GCC4_has_attribute___uninitialized__" is not defined [-Werror=undef] Upstream won't need this because newer kernels are not compilable with gcc 4.9. Subject: gcc-4.9 warning/error fix for 5.10.223-rc1 Fixes: fd7eea27a3ae ("Compiler Attributes: Add __uninitialized macro") Signed-off-by: Jari Ruusu Signed-off-by: Greg Kroah-Hartman --- include/linux/compiler_attributes.h | 1 + 1 file changed, 1 insertion(+) diff --git a/include/linux/compiler_attributes.h b/include/linux/compiler_attributes.h index 3982c2dc541e..a3b85459959e 100644 --- a/include/linux/compiler_attributes.h +++ b/include/linux/compiler_attributes.h @@ -37,6 +37,7 @@ # define __GCC4_has_attribute___nonstring__ 0 # define __GCC4_has_attribute___no_sanitize_address__ (__GNUC_MINOR__ >= 8) # define __GCC4_has_attribute___no_sanitize_undefined__ (__GNUC_MINOR__ >= 9) +# define __GCC4_has_attribute___uninitialized__ 0 # define __GCC4_has_attribute___fallthrough__ 0 # define __GCC4_has_attribute___warning__ 1 #endif From c52f9e1a9eb40f13993142c331a6cfd334d4b91d Mon Sep 17 00:00:00 2001 From: Lukas Wunner Date: Tue, 30 Jul 2024 12:26:55 +0200 Subject: [PATCH 326/342] PCI/DPC: Fix use-after-free on concurrent DPC and hot-removal MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit commit 11a1f4bc47362700fcbde717292158873fb847ed upstream. Keith reports a use-after-free when a DPC event occurs concurrently to hot-removal of the same portion of the hierarchy: The dpc_handler() awaits readiness of the secondary bus below the Downstream Port where the DPC event occurred. To do so, it polls the config space of the first child device on the secondary bus. If that child device is concurrently removed, accesses to its struct pci_dev cause the kernel to oops. That's because pci_bridge_wait_for_secondary_bus() neglects to hold a reference on the child device. Before v6.3, the function was only called on resume from system sleep or on runtime resume. Holding a reference wasn't necessary back then because the pciehp IRQ thread could never run concurrently. (On resume from system sleep, IRQs are not enabled until after the resume_noirq phase. And runtime resume is always awaited before a PCI device is removed.) However starting with v6.3, pci_bridge_wait_for_secondary_bus() is also called on a DPC event. Commit 53b54ad074de ("PCI/DPC: Await readiness of secondary bus after reset"), which introduced that, failed to appreciate that pci_bridge_wait_for_secondary_bus() now needs to hold a reference on the child device because dpc_handler() and pciehp may indeed run concurrently. The commit was backported to v5.10+ stable kernels, so that's the oldest one affected. Add the missing reference acquisition. Abridged stack trace: BUG: unable to handle page fault for address: 00000000091400c0 CPU: 15 PID: 2464 Comm: irq/53-pcie-dpc 6.9.0 RIP: pci_bus_read_config_dword+0x17/0x50 pci_dev_wait() pci_bridge_wait_for_secondary_bus() dpc_reset_link() pcie_do_recovery() dpc_handler() Fixes: 53b54ad074de ("PCI/DPC: Await readiness of secondary bus after reset") Closes: https://lore.kernel.org/r/20240612181625.3604512-3-kbusch@meta.com/ Link: https://lore.kernel.org/linux-pci/8e4bcd4116fd94f592f2bf2749f168099c480ddf.1718707743.git.lukas@wunner.de Reported-by: Keith Busch Tested-by: Keith Busch Signed-off-by: Lukas Wunner Signed-off-by: Krzysztof Wilczyński Reviewed-by: Keith Busch Reviewed-by: Mika Westerberg Cc: stable@vger.kernel.org # v5.10+ Signed-off-by: Greg Kroah-Hartman --- drivers/pci/pci.c | 19 ++++++++++++------- 1 file changed, 12 insertions(+), 7 deletions(-) diff --git a/drivers/pci/pci.c b/drivers/pci/pci.c index 530ced8f7abd..09d5fa637b98 100644 --- a/drivers/pci/pci.c +++ b/drivers/pci/pci.c @@ -4817,7 +4817,7 @@ int pci_bridge_wait_for_secondary_bus(struct pci_dev *dev, char *reset_type, int timeout) { struct pci_dev *child; - int delay; + int delay, ret = 0; if (pci_dev_is_disconnected(dev)) return 0; @@ -4845,8 +4845,8 @@ int pci_bridge_wait_for_secondary_bus(struct pci_dev *dev, char *reset_type, return 0; } - child = list_first_entry(&dev->subordinate->devices, struct pci_dev, - bus_list); + child = pci_dev_get(list_first_entry(&dev->subordinate->devices, + struct pci_dev, bus_list)); up_read(&pci_bus_sem); /* @@ -4856,7 +4856,7 @@ int pci_bridge_wait_for_secondary_bus(struct pci_dev *dev, char *reset_type, if (!pci_is_pcie(dev)) { pci_dbg(dev, "waiting %d ms for secondary bus\n", 1000 + delay); msleep(1000 + delay); - return 0; + goto put_child; } /* @@ -4877,7 +4877,7 @@ int pci_bridge_wait_for_secondary_bus(struct pci_dev *dev, char *reset_type, * until the timeout expires. */ if (!pcie_downstream_port(dev)) - return 0; + goto put_child; if (pcie_get_speed_cap(dev) <= PCIE_SPEED_5_0GT) { pci_dbg(dev, "waiting %d ms for downstream link\n", delay); @@ -4888,11 +4888,16 @@ int pci_bridge_wait_for_secondary_bus(struct pci_dev *dev, char *reset_type, if (!pcie_wait_for_link_delay(dev, true, delay)) { /* Did not train, no need to wait any further */ pci_info(dev, "Data Link Layer Link Active not set in 1000 msec\n"); - return -ENOTTY; + ret = -ENOTTY; + goto put_child; } } - return pci_dev_wait(child, reset_type, timeout - delay); + ret = pci_dev_wait(child, reset_type, timeout - delay); + +put_child: + pci_dev_put(child); + return ret; } void pci_reset_secondary_bus(struct pci_dev *dev) From 191fc44395240130a4487c5270cc040ec2f01213 Mon Sep 17 00:00:00 2001 From: Pablo Neira Ayuso Date: Mon, 12 Aug 2024 12:27:39 +0200 Subject: [PATCH 327/342] netfilter: nf_tables: set element extended ACK reporting support commit b53c116642502b0c85ecef78bff4f826a7dd4145 upstream. Report the element that causes problems via netlink extended ACK for set element commands. Signed-off-by: Pablo Neira Ayuso Signed-off-by: Greg Kroah-Hartman --- net/netfilter/nf_tables_api.c | 13 +++++++++---- 1 file changed, 9 insertions(+), 4 deletions(-) diff --git a/net/netfilter/nf_tables_api.c b/net/netfilter/nf_tables_api.c index f4bbddfbbc24..0bc92edb7827 100644 --- a/net/netfilter/nf_tables_api.c +++ b/net/netfilter/nf_tables_api.c @@ -5354,8 +5354,10 @@ static int nf_tables_getsetelem(struct net *net, struct sock *nlsk, nla_for_each_nested(attr, nla[NFTA_SET_ELEM_LIST_ELEMENTS], rem) { err = nft_get_set_elem(&ctx, set, attr); - if (err < 0) + if (err < 0) { + NL_SET_BAD_ATTR(extack, attr); break; + } } return err; @@ -5848,8 +5850,10 @@ static int nf_tables_newsetelem(struct net *net, struct sock *nlsk, nla_for_each_nested(attr, nla[NFTA_SET_ELEM_LIST_ELEMENTS], rem) { err = nft_add_set_elem(&ctx, set, attr, nlh->nlmsg_flags); - if (err < 0) + if (err < 0) { + NL_SET_BAD_ATTR(extack, attr); return err; + } } if (nft_net->validate_state == NFT_VALIDATE_DO) @@ -6058,9 +6062,10 @@ static int nf_tables_delsetelem(struct net *net, struct sock *nlsk, nla_for_each_nested(attr, nla[NFTA_SET_ELEM_LIST_ELEMENTS], rem) { err = nft_del_setelem(&ctx, set, attr); - if (err < 0) + if (err < 0) { + NL_SET_BAD_ATTR(extack, attr); break; - + } set->ndeact++; } return err; From 7b17de2a71e56c10335b565cc7ad238e6d984379 Mon Sep 17 00:00:00 2001 From: Pablo Neira Ayuso Date: Mon, 12 Aug 2024 12:27:40 +0200 Subject: [PATCH 328/342] netfilter: nf_tables: use timestamp to check for set element timeout commit 7395dfacfff65e9938ac0889dafa1ab01e987d15 upstream Add a timestamp field at the beginning of the transaction, store it in the nftables per-netns area. Update set backend .insert, .deactivate and sync gc path to use the timestamp, this avoids that an element expires while control plane transaction is still unfinished. .lookup and .update, which are used from packet path, still use the current time to check if the element has expired. And .get path and dump also since this runs lockless under rcu read size lock. Then, there is async gc which also needs to check the current time since it runs asynchronously from a workqueue. [ NB: rbtree GC updates has been excluded because GC is asynchronous. ] Fixes: c3e1b005ed1c ("netfilter: nf_tables: add set element timeout support") Signed-off-by: Pablo Neira Ayuso Signed-off-by: Greg Kroah-Hartman --- include/net/netfilter/nf_tables.h | 21 +++++++++++++++++++-- net/netfilter/nf_tables_api.c | 1 + net/netfilter/nft_set_hash.c | 8 +++++++- net/netfilter/nft_set_pipapo.c | 18 +++++++++++------- net/netfilter/nft_set_rbtree.c | 6 ++++-- 5 files changed, 42 insertions(+), 12 deletions(-) diff --git a/include/net/netfilter/nf_tables.h b/include/net/netfilter/nf_tables.h index 2b99ee1303d9..dd7c310e7216 100644 --- a/include/net/netfilter/nf_tables.h +++ b/include/net/netfilter/nf_tables.h @@ -13,6 +13,7 @@ #include #include #include +#include #define NFT_MAX_HOOKS (NF_INET_INGRESS + 1) @@ -686,10 +687,16 @@ static inline struct nft_expr *nft_set_ext_expr(const struct nft_set_ext *ext) return nft_set_ext(ext, NFT_SET_EXT_EXPR); } -static inline bool nft_set_elem_expired(const struct nft_set_ext *ext) +static inline bool __nft_set_elem_expired(const struct nft_set_ext *ext, + u64 tstamp) { return nft_set_ext_exists(ext, NFT_SET_EXT_EXPIRATION) && - time_is_before_eq_jiffies64(*nft_set_ext_expiration(ext)); + time_after_eq64(tstamp, *nft_set_ext_expiration(ext)); +} + +static inline bool nft_set_elem_expired(const struct nft_set_ext *ext) +{ + return __nft_set_elem_expired(ext, get_jiffies_64()); } static inline struct nft_set_ext *nft_set_elem_ext(const struct nft_set *set, @@ -1580,9 +1587,19 @@ struct nftables_pernet { struct list_head module_list; struct list_head notify_list; struct mutex commit_mutex; + u64 tstamp; unsigned int base_seq; u8 validate_state; unsigned int gc_seq; }; +extern unsigned int nf_tables_net_id; + +static inline u64 nft_net_tstamp(const struct net *net) +{ + struct nftables_pernet *nft_net = net_generic(net, nf_tables_net_id); + + return nft_net->tstamp; +} + #endif /* _NET_NF_TABLES_H */ diff --git a/net/netfilter/nf_tables_api.c b/net/netfilter/nf_tables_api.c index 0bc92edb7827..bf4c455474a6 100644 --- a/net/netfilter/nf_tables_api.c +++ b/net/netfilter/nf_tables_api.c @@ -9034,6 +9034,7 @@ static bool nf_tables_valid_genid(struct net *net, u32 genid) bool genid_ok; mutex_lock(&nft_net->commit_mutex); + nft_net->tstamp = get_jiffies_64(); genid_ok = genid == 0 || nft_net->base_seq == genid; if (!genid_ok) diff --git a/net/netfilter/nft_set_hash.c b/net/netfilter/nft_set_hash.c index f0a9ad1c4ea4..2499d25a5c85 100644 --- a/net/netfilter/nft_set_hash.c +++ b/net/netfilter/nft_set_hash.c @@ -38,6 +38,7 @@ struct nft_rhash_cmp_arg { const struct nft_set *set; const u32 *key; u8 genmask; + u64 tstamp; }; static inline u32 nft_rhash_key(const void *data, u32 len, u32 seed) @@ -64,7 +65,7 @@ static inline int nft_rhash_cmp(struct rhashtable_compare_arg *arg, return 1; if (nft_set_elem_is_dead(&he->ext)) return 1; - if (nft_set_elem_expired(&he->ext)) + if (__nft_set_elem_expired(&he->ext, x->tstamp)) return 1; if (!nft_set_elem_active(&he->ext, x->genmask)) return 1; @@ -88,6 +89,7 @@ static bool nft_rhash_lookup(const struct net *net, const struct nft_set *set, .genmask = nft_genmask_cur(net), .set = set, .key = key, + .tstamp = get_jiffies_64(), }; he = rhashtable_lookup(&priv->ht, &arg, nft_rhash_params); @@ -106,6 +108,7 @@ static void *nft_rhash_get(const struct net *net, const struct nft_set *set, .genmask = nft_genmask_cur(net), .set = set, .key = elem->key.val.data, + .tstamp = get_jiffies_64(), }; he = rhashtable_lookup(&priv->ht, &arg, nft_rhash_params); @@ -129,6 +132,7 @@ static bool nft_rhash_update(struct nft_set *set, const u32 *key, .genmask = NFT_GENMASK_ANY, .set = set, .key = key, + .tstamp = get_jiffies_64(), }; he = rhashtable_lookup(&priv->ht, &arg, nft_rhash_params); @@ -172,6 +176,7 @@ static int nft_rhash_insert(const struct net *net, const struct nft_set *set, .genmask = nft_genmask_next(net), .set = set, .key = elem->key.val.data, + .tstamp = nft_net_tstamp(net), }; struct nft_rhash_elem *prev; @@ -214,6 +219,7 @@ static void *nft_rhash_deactivate(const struct net *net, .genmask = nft_genmask_next(net), .set = set, .key = elem->key.val.data, + .tstamp = nft_net_tstamp(net), }; rcu_read_lock(); diff --git a/net/netfilter/nft_set_pipapo.c b/net/netfilter/nft_set_pipapo.c index 5a8521abd8f5..9e0269e85017 100644 --- a/net/netfilter/nft_set_pipapo.c +++ b/net/netfilter/nft_set_pipapo.c @@ -504,6 +504,7 @@ bool nft_pipapo_lookup(const struct net *net, const struct nft_set *set, * @set: nftables API set representation * @data: Key data to be matched against existing elements * @genmask: If set, check that element is active in given genmask + * @tstamp: timestamp to check for expired elements * * This is essentially the same as the lookup function, except that it matches * key data against the uncommitted copy and doesn't use preallocated maps for @@ -513,7 +514,8 @@ bool nft_pipapo_lookup(const struct net *net, const struct nft_set *set, */ static struct nft_pipapo_elem *pipapo_get(const struct net *net, const struct nft_set *set, - const u8 *data, u8 genmask) + const u8 *data, u8 genmask, + u64 tstamp) { struct nft_pipapo_elem *ret = ERR_PTR(-ENOENT); struct nft_pipapo *priv = nft_set_priv(set); @@ -566,7 +568,7 @@ static struct nft_pipapo_elem *pipapo_get(const struct net *net, goto out; if (last) { - if (nft_set_elem_expired(&f->mt[b].e->ext)) + if (__nft_set_elem_expired(&f->mt[b].e->ext, tstamp)) goto next_match; if ((genmask && !nft_set_elem_active(&f->mt[b].e->ext, genmask))) @@ -603,7 +605,7 @@ static void *nft_pipapo_get(const struct net *net, const struct nft_set *set, const struct nft_set_elem *elem, unsigned int flags) { return pipapo_get(net, set, (const u8 *)elem->key.val.data, - nft_genmask_cur(net)); + nft_genmask_cur(net), get_jiffies_64()); } /** @@ -1197,6 +1199,7 @@ static int nft_pipapo_insert(const struct net *net, const struct nft_set *set, struct nft_pipapo *priv = nft_set_priv(set); struct nft_pipapo_match *m = priv->clone; u8 genmask = nft_genmask_next(net); + u64 tstamp = nft_net_tstamp(net); struct nft_pipapo_field *f; const u8 *start_p, *end_p; int i, bsize_max, err = 0; @@ -1206,7 +1209,7 @@ static int nft_pipapo_insert(const struct net *net, const struct nft_set *set, else end = start; - dup = pipapo_get(net, set, start, genmask); + dup = pipapo_get(net, set, start, genmask, tstamp); if (!IS_ERR(dup)) { /* Check if we already have the same exact entry */ const struct nft_data *dup_key, *dup_end; @@ -1228,7 +1231,7 @@ static int nft_pipapo_insert(const struct net *net, const struct nft_set *set, if (PTR_ERR(dup) == -ENOENT) { /* Look for partially overlapping entries */ - dup = pipapo_get(net, set, end, nft_genmask_next(net)); + dup = pipapo_get(net, set, end, nft_genmask_next(net), tstamp); } if (PTR_ERR(dup) != -ENOENT) { @@ -1580,6 +1583,7 @@ static void pipapo_gc(const struct nft_set *_set, struct nft_pipapo_match *m) struct nft_set *set = (struct nft_set *) _set; struct nft_pipapo *priv = nft_set_priv(set); struct net *net = read_pnet(&set->net); + u64 tstamp = nft_net_tstamp(net); int rules_f0, first_rule = 0; struct nft_trans_gc *gc; @@ -1613,7 +1617,7 @@ static void pipapo_gc(const struct nft_set *_set, struct nft_pipapo_match *m) /* synchronous gc never fails, there is no need to set on * NFT_SET_ELEM_DEAD_BIT. */ - if (nft_set_elem_expired(&e->ext)) { + if (__nft_set_elem_expired(&e->ext, tstamp)) { priv->dirty = true; gc = nft_trans_gc_queue_sync(gc, GFP_ATOMIC); @@ -1772,7 +1776,7 @@ static void *pipapo_deactivate(const struct net *net, const struct nft_set *set, { struct nft_pipapo_elem *e; - e = pipapo_get(net, set, data, nft_genmask_next(net)); + e = pipapo_get(net, set, data, nft_genmask_next(net), nft_net_tstamp(net)); if (IS_ERR(e)) return NULL; diff --git a/net/netfilter/nft_set_rbtree.c b/net/netfilter/nft_set_rbtree.c index 18c0d163dc76..bbced30113e4 100644 --- a/net/netfilter/nft_set_rbtree.c +++ b/net/netfilter/nft_set_rbtree.c @@ -316,6 +316,7 @@ static int __nft_rbtree_insert(const struct net *net, const struct nft_set *set, struct nft_rbtree *priv = nft_set_priv(set); u8 cur_genmask = nft_genmask_cur(net); u8 genmask = nft_genmask_next(net); + u64 tstamp = nft_net_tstamp(net); int d; /* Descend the tree to search for an existing element greater than the @@ -363,7 +364,7 @@ static int __nft_rbtree_insert(const struct net *net, const struct nft_set *set, /* perform garbage collection to avoid bogus overlap reports * but skip new elements in this transaction. */ - if (nft_set_elem_expired(&rbe->ext) && + if (__nft_set_elem_expired(&rbe->ext, tstamp) && nft_set_elem_active(&rbe->ext, cur_genmask)) { const struct nft_rbtree_elem *removed_end; @@ -550,6 +551,7 @@ static void *nft_rbtree_deactivate(const struct net *net, const struct rb_node *parent = priv->root.rb_node; struct nft_rbtree_elem *rbe, *this = elem->priv; u8 genmask = nft_genmask_next(net); + u64 tstamp = nft_net_tstamp(net); int d; while (parent != NULL) { @@ -570,7 +572,7 @@ static void *nft_rbtree_deactivate(const struct net *net, nft_rbtree_interval_end(this)) { parent = parent->rb_right; continue; - } else if (nft_set_elem_expired(&rbe->ext)) { + } else if (__nft_set_elem_expired(&rbe->ext, tstamp)) { break; } else if (!nft_set_elem_active(&rbe->ext, genmask)) { parent = parent->rb_left; From d5f87c11114b5a6293cd44d94132bb8784c124b6 Mon Sep 17 00:00:00 2001 From: Pablo Neira Ayuso Date: Mon, 12 Aug 2024 12:27:41 +0200 Subject: [PATCH 329/342] netfilter: nf_tables: allow clone callbacks to sleep commit fa23e0d4b756d25829e124d6b670a4c6bbd4bf7e upstream. Sven Auhagen reports transaction failures with following error: ./main.nft:13:1-26: Error: Could not process rule: Cannot allocate memory percpu: allocation failed, size=16 align=8 atomic=1, atomic alloc failed, no space left This points to failing pcpu allocation with GFP_ATOMIC flag. However, transactions happen from user context and are allowed to sleep. One case where we can call into percpu allocator with GFP_ATOMIC is nft_counter expression. Normally this happens from control plane, so this could use GFP_KERNEL instead. But one use case, element insertion from packet path, needs to use GFP_ATOMIC allocations (nft_dynset expression). At this time, .clone callbacks always use GFP_ATOMIC for this reason. Add gfp_t argument to the .clone function and pass GFP_KERNEL or GFP_ATOMIC flag depending on context, this allows all clone memory allocations to sleep for the normal (transaction) case. Cc: Sven Auhagen Signed-off-by: Florian Westphal Signed-off-by: Pablo Neira Ayuso Signed-off-by: Greg Kroah-Hartman --- include/net/netfilter/nf_tables.h | 4 ++-- net/netfilter/nf_tables_api.c | 8 ++++---- net/netfilter/nft_connlimit.c | 2 +- net/netfilter/nft_counter.c | 4 ++-- net/netfilter/nft_dynset.c | 2 +- 5 files changed, 10 insertions(+), 10 deletions(-) diff --git a/include/net/netfilter/nf_tables.h b/include/net/netfilter/nf_tables.h index dd7c310e7216..3cc25a5faa23 100644 --- a/include/net/netfilter/nf_tables.h +++ b/include/net/netfilter/nf_tables.h @@ -786,7 +786,7 @@ struct nft_expr_ops { struct nft_regs *regs, const struct nft_pktinfo *pkt); int (*clone)(struct nft_expr *dst, - const struct nft_expr *src); + const struct nft_expr *src, gfp_t gfp); unsigned int size; int (*init)(const struct nft_ctx *ctx, @@ -837,7 +837,7 @@ static inline void *nft_expr_priv(const struct nft_expr *expr) return (void *)expr->data; } -int nft_expr_clone(struct nft_expr *dst, struct nft_expr *src); +int nft_expr_clone(struct nft_expr *dst, struct nft_expr *src, gfp_t gfp); void nft_expr_destroy(const struct nft_ctx *ctx, struct nft_expr *expr); int nft_expr_dump(struct sk_buff *skb, unsigned int attr, const struct nft_expr *expr); diff --git a/net/netfilter/nf_tables_api.c b/net/netfilter/nf_tables_api.c index bf4c455474a6..2b5e9efe86dd 100644 --- a/net/netfilter/nf_tables_api.c +++ b/net/netfilter/nf_tables_api.c @@ -2968,13 +2968,13 @@ static struct nft_expr *nft_expr_init(const struct nft_ctx *ctx, return ERR_PTR(err); } -int nft_expr_clone(struct nft_expr *dst, struct nft_expr *src) +int nft_expr_clone(struct nft_expr *dst, struct nft_expr *src, gfp_t gfp) { int err; if (src->ops->clone) { dst->ops = src->ops; - err = src->ops->clone(dst, src); + err = src->ops->clone(dst, src, gfp); if (err < 0) return err; } else { @@ -5524,7 +5524,7 @@ static int nft_set_elem_expr_setup(struct nft_ctx *ctx, if (expr == NULL) return 0; - err = nft_expr_clone(elem_expr, expr); + err = nft_expr_clone(elem_expr, expr, GFP_KERNEL); if (err < 0) return -ENOMEM; @@ -5632,7 +5632,7 @@ static int nft_add_set_elem(struct nft_ctx *ctx, struct nft_set *set, if (!expr) return -ENOMEM; - err = nft_expr_clone(expr, set->expr); + err = nft_expr_clone(expr, set->expr, GFP_KERNEL); if (err < 0) goto err_set_elem_expr; } diff --git a/net/netfilter/nft_connlimit.c b/net/netfilter/nft_connlimit.c index 7d0761fad37e..091457e5c260 100644 --- a/net/netfilter/nft_connlimit.c +++ b/net/netfilter/nft_connlimit.c @@ -195,7 +195,7 @@ static void nft_connlimit_destroy(const struct nft_ctx *ctx, nft_connlimit_do_destroy(ctx, priv); } -static int nft_connlimit_clone(struct nft_expr *dst, const struct nft_expr *src) +static int nft_connlimit_clone(struct nft_expr *dst, const struct nft_expr *src, gfp_t gfp) { struct nft_connlimit *priv_dst = nft_expr_priv(dst); struct nft_connlimit *priv_src = nft_expr_priv(src); diff --git a/net/netfilter/nft_counter.c b/net/netfilter/nft_counter.c index 85ed461ec24e..75fa6fcd6cd6 100644 --- a/net/netfilter/nft_counter.c +++ b/net/netfilter/nft_counter.c @@ -224,7 +224,7 @@ static void nft_counter_destroy(const struct nft_ctx *ctx, nft_counter_do_destroy(priv); } -static int nft_counter_clone(struct nft_expr *dst, const struct nft_expr *src) +static int nft_counter_clone(struct nft_expr *dst, const struct nft_expr *src, gfp_t gfp) { struct nft_counter_percpu_priv *priv = nft_expr_priv(src); struct nft_counter_percpu_priv *priv_clone = nft_expr_priv(dst); @@ -234,7 +234,7 @@ static int nft_counter_clone(struct nft_expr *dst, const struct nft_expr *src) nft_counter_fetch(priv, &total); - cpu_stats = alloc_percpu_gfp(struct nft_counter, GFP_ATOMIC); + cpu_stats = alloc_percpu_gfp(struct nft_counter, gfp); if (cpu_stats == NULL) return -ENOMEM; diff --git a/net/netfilter/nft_dynset.c b/net/netfilter/nft_dynset.c index 408b7f5faa5e..9461293182e8 100644 --- a/net/netfilter/nft_dynset.c +++ b/net/netfilter/nft_dynset.c @@ -48,7 +48,7 @@ static void *nft_dynset_new(struct nft_set *set, const struct nft_expr *expr, ext = nft_set_elem_ext(set, elem); if (priv->expr != NULL && - nft_expr_clone(nft_set_ext_expr(ext), priv->expr) < 0) + nft_expr_clone(nft_set_ext_expr(ext), priv->expr, GFP_ATOMIC) < 0) goto err2; return elem; From 31c35f9f89ef585f1edb53e17ac73a0ca4a9712b Mon Sep 17 00:00:00 2001 From: Florian Westphal Date: Mon, 12 Aug 2024 12:27:42 +0200 Subject: [PATCH 330/342] netfilter: nf_tables: prefer nft_chain_validate MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit commit cff3bd012a9512ac5ed858d38e6ed65f6391008c upstream. nft_chain_validate already performs loop detection because a cycle will result in a call stack overflow (ctx->level >= NFT_JUMP_STACK_SIZE). It also follows maps via ->validate callback in nft_lookup, so there appears no reason to iterate the maps again. nf_tables_check_loops() and all its helper functions can be removed. This improves ruleset load time significantly, from 23s down to 12s. This also fixes a crash bug. Old loop detection code can result in unbounded recursion: BUG: TASK stack guard page was hit at .... Oops: stack guard page: 0000 [#1] PREEMPT SMP KASAN CPU: 4 PID: 1539 Comm: nft Not tainted 6.10.0-rc5+ #1 [..] with a suitable ruleset during validation of register stores. I can't see any actual reason to attempt to check for this from nft_validate_register_store(), at this point the transaction is still in progress, so we don't have a full picture of the rule graph. For nf-next it might make sense to either remove it or make this depend on table->validate_state in case we could catch an error earlier (for improved error reporting to userspace). Fixes: 20a69341f2d0 ("netfilter: nf_tables: add netlink set API") Signed-off-by: Florian Westphal Signed-off-by: Pablo Neira Ayuso Signed-off-by: Greg Kroah-Hartman --- net/netfilter/nf_tables_api.c | 127 ++++------------------------------ 1 file changed, 13 insertions(+), 114 deletions(-) diff --git a/net/netfilter/nf_tables_api.c b/net/netfilter/nf_tables_api.c index 2b5e9efe86dd..249c30c47cbd 100644 --- a/net/netfilter/nf_tables_api.c +++ b/net/netfilter/nf_tables_api.c @@ -3349,6 +3349,15 @@ static void nf_tables_rule_release(const struct nft_ctx *ctx, struct nft_rule *r nf_tables_rule_destroy(ctx, rule); } +/** nft_chain_validate - loop detection and hook validation + * + * @ctx: context containing call depth and base chain + * @chain: chain to validate + * + * Walk through the rules of the given chain and chase all jumps/gotos + * and set lookups until either the jump limit is hit or all reachable + * chains have been validated. + */ int nft_chain_validate(const struct nft_ctx *ctx, const struct nft_chain *chain) { struct nft_expr *expr, *last; @@ -3367,6 +3376,9 @@ int nft_chain_validate(const struct nft_ctx *ctx, const struct nft_chain *chain) if (!expr->ops->validate) continue; + /* This may call nft_chain_validate() recursively, + * callers that do so must increment ctx->level. + */ err = expr->ops->validate(ctx, expr, &data); if (err < 0) return err; @@ -9087,119 +9099,6 @@ int nft_chain_validate_hooks(const struct nft_chain *chain, } EXPORT_SYMBOL_GPL(nft_chain_validate_hooks); -/* - * Loop detection - walk through the ruleset beginning at the destination chain - * of a new jump until either the source chain is reached (loop) or all - * reachable chains have been traversed. - * - * The loop check is performed whenever a new jump verdict is added to an - * expression or verdict map or a verdict map is bound to a new chain. - */ - -static int nf_tables_check_loops(const struct nft_ctx *ctx, - const struct nft_chain *chain); - -static int nft_check_loops(const struct nft_ctx *ctx, - const struct nft_set_ext *ext) -{ - const struct nft_data *data; - int ret; - - data = nft_set_ext_data(ext); - switch (data->verdict.code) { - case NFT_JUMP: - case NFT_GOTO: - ret = nf_tables_check_loops(ctx, data->verdict.chain); - break; - default: - ret = 0; - break; - } - - return ret; -} - -static int nf_tables_loop_check_setelem(const struct nft_ctx *ctx, - struct nft_set *set, - const struct nft_set_iter *iter, - struct nft_set_elem *elem) -{ - const struct nft_set_ext *ext = nft_set_elem_ext(set, elem->priv); - - if (nft_set_ext_exists(ext, NFT_SET_EXT_FLAGS) && - *nft_set_ext_flags(ext) & NFT_SET_ELEM_INTERVAL_END) - return 0; - - return nft_check_loops(ctx, ext); -} - -static int nf_tables_check_loops(const struct nft_ctx *ctx, - const struct nft_chain *chain) -{ - const struct nft_rule *rule; - const struct nft_expr *expr, *last; - struct nft_set *set; - struct nft_set_binding *binding; - struct nft_set_iter iter; - - if (ctx->chain == chain) - return -ELOOP; - - list_for_each_entry(rule, &chain->rules, list) { - nft_rule_for_each_expr(expr, last, rule) { - struct nft_immediate_expr *priv; - const struct nft_data *data; - int err; - - if (strcmp(expr->ops->type->name, "immediate")) - continue; - - priv = nft_expr_priv(expr); - if (priv->dreg != NFT_REG_VERDICT) - continue; - - data = &priv->data; - switch (data->verdict.code) { - case NFT_JUMP: - case NFT_GOTO: - err = nf_tables_check_loops(ctx, - data->verdict.chain); - if (err < 0) - return err; - break; - default: - break; - } - } - } - - list_for_each_entry(set, &ctx->table->sets, list) { - if (!nft_is_active_next(ctx->net, set)) - continue; - if (!(set->flags & NFT_SET_MAP) || - set->dtype != NFT_DATA_VERDICT) - continue; - - list_for_each_entry(binding, &set->bindings, list) { - if (!(binding->flags & NFT_SET_MAP) || - binding->chain != chain) - continue; - - iter.genmask = nft_genmask_next(ctx->net); - iter.skip = 0; - iter.count = 0; - iter.err = 0; - iter.fn = nf_tables_loop_check_setelem; - - set->ops->walk(ctx, set, &iter); - if (iter.err < 0) - return iter.err; - } - } - - return 0; -} - /** * nft_parse_u32_check - fetch u32 attribute and check for maximum value * @@ -9335,7 +9234,7 @@ static int nft_validate_register_store(const struct nft_ctx *ctx, if (data != NULL && (data->verdict.code == NFT_GOTO || data->verdict.code == NFT_JUMP)) { - err = nf_tables_check_loops(ctx, data->verdict.chain); + err = nft_chain_validate(ctx, data->verdict.chain); if (err < 0) return err; } From 50111a8098fb9ade621eeff82228a997d42732ab Mon Sep 17 00:00:00 2001 From: Andi Shyti Date: Fri, 2 Aug 2024 10:38:50 +0200 Subject: [PATCH 331/342] drm/i915/gem: Fix Virtual Memory mapping boundaries calculation commit 8bdd9ef7e9b1b2a73e394712b72b22055e0e26c3 upstream. Calculating the size of the mapped area as the lesser value between the requested size and the actual size does not consider the partial mapping offset. This can cause page fault access. Fix the calculation of the starting and ending addresses, the total size is now deduced from the difference between the end and start addresses. Additionally, the calculations have been rewritten in a clearer and more understandable form. Fixes: c58305af1835 ("drm/i915: Use remap_io_mapping() to prefault all PTE in a single pass") Reported-by: Jann Horn Co-developed-by: Chris Wilson Signed-off-by: Chris Wilson Signed-off-by: Andi Shyti Cc: Joonas Lahtinen Cc: Matthew Auld Cc: Rodrigo Vivi Cc: # v4.9+ Reviewed-by: Jann Horn Reviewed-by: Jonathan Cavitt [Joonas: Add Requires: tag] Requires: 60a2066c5005 ("drm/i915/gem: Adjust vma offset for framebuffer mmap offset") Signed-off-by: Joonas Lahtinen Link: https://patchwork.freedesktop.org/patch/msgid/20240802083850.103694-3-andi.shyti@linux.intel.com (cherry picked from commit 97b6784753da06d9d40232328efc5c5367e53417) Signed-off-by: Joonas Lahtinen Signed-off-by: Greg Kroah-Hartman --- drivers/gpu/drm/i915/gem/i915_gem_mman.c | 53 +++++++++++++++++++++--- 1 file changed, 47 insertions(+), 6 deletions(-) diff --git a/drivers/gpu/drm/i915/gem/i915_gem_mman.c b/drivers/gpu/drm/i915/gem/i915_gem_mman.c index 01a88b03bc6d..0021b039b72b 100644 --- a/drivers/gpu/drm/i915/gem/i915_gem_mman.c +++ b/drivers/gpu/drm/i915/gem/i915_gem_mman.c @@ -273,6 +273,41 @@ static vm_fault_t vm_fault_cpu(struct vm_fault *vmf) return i915_error_to_vmf_fault(err); } +static void set_address_limits(struct vm_area_struct *area, + struct i915_vma *vma, + unsigned long obj_offset, + unsigned long *start_vaddr, + unsigned long *end_vaddr) +{ + unsigned long vm_start, vm_end, vma_size; /* user's memory parameters */ + long start, end; /* memory boundaries */ + + /* + * Let's move into the ">> PAGE_SHIFT" + * domain to be sure not to lose bits + */ + vm_start = area->vm_start >> PAGE_SHIFT; + vm_end = area->vm_end >> PAGE_SHIFT; + vma_size = vma->size >> PAGE_SHIFT; + + /* + * Calculate the memory boundaries by considering the offset + * provided by the user during memory mapping and the offset + * provided for the partial mapping. + */ + start = vm_start; + start -= obj_offset; + start += vma->ggtt_view.partial.offset; + end = start + vma_size; + + start = max_t(long, start, vm_start); + end = min_t(long, end, vm_end); + + /* Let's move back into the "<< PAGE_SHIFT" domain */ + *start_vaddr = (unsigned long)start << PAGE_SHIFT; + *end_vaddr = (unsigned long)end << PAGE_SHIFT; +} + static vm_fault_t vm_fault_gtt(struct vm_fault *vmf) { #define MIN_CHUNK_PAGES (SZ_1M >> PAGE_SHIFT) @@ -285,14 +320,18 @@ static vm_fault_t vm_fault_gtt(struct vm_fault *vmf) struct i915_ggtt *ggtt = &i915->ggtt; bool write = area->vm_flags & VM_WRITE; struct i915_gem_ww_ctx ww; + unsigned long obj_offset; + unsigned long start, end; /* memory boundaries */ intel_wakeref_t wakeref; struct i915_vma *vma; pgoff_t page_offset; + unsigned long pfn; int srcu; int ret; - /* We don't use vmf->pgoff since that has the fake offset */ + obj_offset = area->vm_pgoff - drm_vma_node_start(&mmo->vma_node); page_offset = (vmf->address - area->vm_start) >> PAGE_SHIFT; + page_offset += obj_offset; trace_i915_gem_object_fault(obj, page_offset, true, write); @@ -363,12 +402,14 @@ static vm_fault_t vm_fault_gtt(struct vm_fault *vmf) if (ret) goto err_unpin; + set_address_limits(area, vma, obj_offset, &start, &end); + + pfn = (ggtt->gmadr.start + i915_ggtt_offset(vma)) >> PAGE_SHIFT; + pfn += (start - area->vm_start) >> PAGE_SHIFT; + pfn += obj_offset - vma->ggtt_view.partial.offset; + /* Finally, remap it using the new GTT offset */ - ret = remap_io_mapping(area, - area->vm_start + (vma->ggtt_view.partial.offset << PAGE_SHIFT), - (ggtt->gmadr.start + vma->node.start) >> PAGE_SHIFT, - min_t(u64, vma->size, area->vm_end - area->vm_start), - &ggtt->iomap); + ret = remap_io_mapping(area, start, pfn, end - start, &ggtt->iomap); if (ret) goto err_fence; From fb6675db04c4b79883373edc578d5df7bbc84848 Mon Sep 17 00:00:00 2001 From: Mahesh Salgaonkar Date: Wed, 10 Apr 2024 10:00:06 +0530 Subject: [PATCH 332/342] powerpc: Avoid nmi_enter/nmi_exit in real mode interrupt. commit 0db880fc865ffb522141ced4bfa66c12ab1fbb70 upstream. nmi_enter()/nmi_exit() touches per cpu variables which can lead to kernel crash when invoked during real mode interrupt handling (e.g. early HMI/MCE interrupt handler) if percpu allocation comes from vmalloc area. Early HMI/MCE handlers are called through DEFINE_INTERRUPT_HANDLER_NMI() wrapper which invokes nmi_enter/nmi_exit calls. We don't see any issue when percpu allocation is from the embedded first chunk. However with CONFIG_NEED_PER_CPU_PAGE_FIRST_CHUNK enabled there are chances where percpu allocation can come from the vmalloc area. With kernel command line "percpu_alloc=page" we can force percpu allocation to come from vmalloc area and can see kernel crash in machine_check_early: [ 1.215714] NIP [c000000000e49eb4] rcu_nmi_enter+0x24/0x110 [ 1.215717] LR [c0000000000461a0] machine_check_early+0xf0/0x2c0 [ 1.215719] --- interrupt: 200 [ 1.215720] [c000000fffd73180] [0000000000000000] 0x0 (unreliable) [ 1.215722] [c000000fffd731b0] [0000000000000000] 0x0 [ 1.215724] [c000000fffd73210] [c000000000008364] machine_check_early_common+0x134/0x1f8 Fix this by avoiding use of nmi_enter()/nmi_exit() in real mode if percpu first chunk is not embedded. Reviewed-by: Christophe Leroy Tested-by: Shirisha Ganta Signed-off-by: Mahesh Salgaonkar Signed-off-by: Michael Ellerman Link: https://msgid.link/20240410043006.81577-1-mahesh@linux.ibm.com [ Conflicts in arch/powerpc/include/asm/interrupt.h because machine_check_early() and machine_check_exception() has been refactored. ] Signed-off-by: Jinjie Ruan Signed-off-by: Greg Kroah-Hartman --- arch/powerpc/include/asm/percpu.h | 10 ++++++++++ arch/powerpc/kernel/mce.c | 14 +++++++++++--- arch/powerpc/kernel/setup_64.c | 2 ++ arch/powerpc/kernel/traps.c | 8 +++++++- 4 files changed, 30 insertions(+), 4 deletions(-) diff --git a/arch/powerpc/include/asm/percpu.h b/arch/powerpc/include/asm/percpu.h index 8e5b7d0b851c..634970ce13c6 100644 --- a/arch/powerpc/include/asm/percpu.h +++ b/arch/powerpc/include/asm/percpu.h @@ -15,6 +15,16 @@ #endif /* CONFIG_SMP */ #endif /* __powerpc64__ */ +#if defined(CONFIG_NEED_PER_CPU_PAGE_FIRST_CHUNK) && defined(CONFIG_SMP) +#include +DECLARE_STATIC_KEY_FALSE(__percpu_first_chunk_is_paged); + +#define percpu_first_chunk_is_paged \ + (static_key_enabled(&__percpu_first_chunk_is_paged.key)) +#else +#define percpu_first_chunk_is_paged false +#endif /* CONFIG_PPC64 && CONFIG_SMP */ + #include #include diff --git a/arch/powerpc/kernel/mce.c b/arch/powerpc/kernel/mce.c index 63702c0badb9..259343040e1b 100644 --- a/arch/powerpc/kernel/mce.c +++ b/arch/powerpc/kernel/mce.c @@ -594,8 +594,15 @@ long notrace machine_check_early(struct pt_regs *regs) u8 ftrace_enabled = this_cpu_get_ftrace_enabled(); this_cpu_set_ftrace_enabled(0); - /* Do not use nmi_enter/exit for pseries hpte guest */ - if (radix_enabled() || !firmware_has_feature(FW_FEATURE_LPAR)) + /* + * Do not use nmi_enter/exit for pseries hpte guest + * + * Likewise, do not use it in real mode if percpu first chunk is not + * embedded. With CONFIG_NEED_PER_CPU_PAGE_FIRST_CHUNK enabled there + * are chances where percpu allocation can come from vmalloc area. + */ + if ((radix_enabled() || !firmware_has_feature(FW_FEATURE_LPAR)) && + !percpu_first_chunk_is_paged) nmi_enter(); hv_nmi_check_nonrecoverable(regs); @@ -606,7 +613,8 @@ long notrace machine_check_early(struct pt_regs *regs) if (ppc_md.machine_check_early) handled = ppc_md.machine_check_early(regs); - if (radix_enabled() || !firmware_has_feature(FW_FEATURE_LPAR)) + if ((radix_enabled() || !firmware_has_feature(FW_FEATURE_LPAR)) && + !percpu_first_chunk_is_paged) nmi_exit(); this_cpu_set_ftrace_enabled(ftrace_enabled); diff --git a/arch/powerpc/kernel/setup_64.c b/arch/powerpc/kernel/setup_64.c index 3f8426bccd16..899d87de0165 100644 --- a/arch/powerpc/kernel/setup_64.c +++ b/arch/powerpc/kernel/setup_64.c @@ -824,6 +824,7 @@ static int pcpu_cpu_distance(unsigned int from, unsigned int to) unsigned long __per_cpu_offset[NR_CPUS] __read_mostly; EXPORT_SYMBOL(__per_cpu_offset); +DEFINE_STATIC_KEY_FALSE(__percpu_first_chunk_is_paged); static void __init pcpu_populate_pte(unsigned long addr) { @@ -903,6 +904,7 @@ void __init setup_per_cpu_areas(void) if (rc < 0) panic("cannot initialize percpu area (err=%d)", rc); + static_key_enable(&__percpu_first_chunk_is_paged.key); delta = (unsigned long)pcpu_base_addr - (unsigned long)__per_cpu_start; for_each_possible_cpu(cpu) { __per_cpu_offset[cpu] = delta + pcpu_unit_offsets[cpu]; diff --git a/arch/powerpc/kernel/traps.c b/arch/powerpc/kernel/traps.c index b0e87dce2b9a..b4d108bef814 100644 --- a/arch/powerpc/kernel/traps.c +++ b/arch/powerpc/kernel/traps.c @@ -835,8 +835,14 @@ void machine_check_exception(struct pt_regs *regs) * This is silly. The BOOK3S_64 should just call a different function * rather than expecting semantics to magically change. Something * like 'non_nmi_machine_check_exception()', perhaps? + * + * Do not use nmi_enter/exit in real mode if percpu first chunk is + * not embedded. With CONFIG_NEED_PER_CPU_PAGE_FIRST_CHUNK enabled + * there are chances where percpu allocation can come from + * vmalloc area. */ - const bool nmi = !IS_ENABLED(CONFIG_PPC_BOOK3S_64); + const bool nmi = !IS_ENABLED(CONFIG_PPC_BOOK3S_64) && + !percpu_first_chunk_is_paged; if (nmi) nmi_enter(); From ec54634f91232fada8f3a96a94531e54d8f5bb5e Mon Sep 17 00:00:00 2001 From: Amit Daniel Kachhap Date: Thu, 3 Nov 2022 13:52:32 +0530 Subject: [PATCH 333/342] arm64: cpufeature: Fix the visibility of compat hwcaps commit 85f1506337f0c79a4955edfeee86a18628e3735f upstream. Commit 237405ebef58 ("arm64: cpufeature: Force HWCAP to be based on the sysreg visible to user-space") forced the hwcaps to use sanitised user-space view of the id registers. However, the ID register structures used to select few compat cpufeatures (vfp, crc32, ...) are masked and hence such hwcaps do not appear in /proc/cpuinfo anymore for PER_LINUX32 personality. Add the ID register structures explicitly and set the relevant entry as visible. As these ID registers are now of type visible so make them available in 64-bit userspace by making necessary changes in register emulation logic and documentation. While at it, update the comment for structure ftr_generic_32bits[] which lists the ID register that use it. Fixes: 237405ebef58 ("arm64: cpufeature: Force HWCAP to be based on the sysreg visible to user-space") Cc: Suzuki K Poulose Reviewed-by: James Morse Signed-off-by: Amit Daniel Kachhap Link: https://lore.kernel.org/r/20221103082232.19189-1-amit.kachhap@arm.com Signed-off-by: Catalin Marinas Signed-off-by: Greg Kroah-Hartman --- Documentation/arm64/cpu-feature-registers.rst | 38 ++++++++++++++++- arch/arm64/kernel/cpufeature.c | 42 +++++++++++++++---- 2 files changed, 70 insertions(+), 10 deletions(-) diff --git a/Documentation/arm64/cpu-feature-registers.rst b/Documentation/arm64/cpu-feature-registers.rst index 749ae970c319..8aaa5d13d3cc 100644 --- a/Documentation/arm64/cpu-feature-registers.rst +++ b/Documentation/arm64/cpu-feature-registers.rst @@ -92,7 +92,7 @@ operation if the source belongs to the supported system register space. The infrastructure emulates only the following system register space:: - Op0=3, Op1=0, CRn=0, CRm=0,4,5,6,7 + Op0=3, Op1=0, CRn=0, CRm=0,2,3,4,5,6,7 (See Table C5-6 'System instruction encodings for non-Debug System register accesses' in ARMv8 ARM DDI 0487A.h, for the list of @@ -291,6 +291,42 @@ infrastructure: | RPRES | [7-4] | y | +------------------------------+---------+---------+ + 10) MVFR0_EL1 - AArch32 Media and VFP Feature Register 0 + + +------------------------------+---------+---------+ + | Name | bits | visible | + +------------------------------+---------+---------+ + | FPDP | [11-8] | y | + +------------------------------+---------+---------+ + + 11) MVFR1_EL1 - AArch32 Media and VFP Feature Register 1 + + +------------------------------+---------+---------+ + | Name | bits | visible | + +------------------------------+---------+---------+ + | SIMDFMAC | [31-28] | y | + +------------------------------+---------+---------+ + | SIMDSP | [19-16] | y | + +------------------------------+---------+---------+ + | SIMDInt | [15-12] | y | + +------------------------------+---------+---------+ + | SIMDLS | [11-8] | y | + +------------------------------+---------+---------+ + + 12) ID_ISAR5_EL1 - AArch32 Instruction Set Attribute Register 5 + + +------------------------------+---------+---------+ + | Name | bits | visible | + +------------------------------+---------+---------+ + | CRC32 | [19-16] | y | + +------------------------------+---------+---------+ + | SHA2 | [15-12] | y | + +------------------------------+---------+---------+ + | SHA1 | [11-8] | y | + +------------------------------+---------+---------+ + | AES | [7-4] | y | + +------------------------------+---------+---------+ + Appendix I: Example ------------------- diff --git a/arch/arm64/kernel/cpufeature.c b/arch/arm64/kernel/cpufeature.c index dc92fd590f2f..2dc269b865de 100644 --- a/arch/arm64/kernel/cpufeature.c +++ b/arch/arm64/kernel/cpufeature.c @@ -399,6 +399,30 @@ static const struct arm64_ftr_bits ftr_id_aa64dfr0[] = { ARM64_FTR_END, }; +static const struct arm64_ftr_bits ftr_mvfr0[] = { + ARM64_FTR_BITS(FTR_HIDDEN, FTR_STRICT, FTR_LOWER_SAFE, MVFR0_FPROUND_SHIFT, 4, 0), + ARM64_FTR_BITS(FTR_HIDDEN, FTR_STRICT, FTR_LOWER_SAFE, MVFR0_FPSHVEC_SHIFT, 4, 0), + ARM64_FTR_BITS(FTR_HIDDEN, FTR_STRICT, FTR_LOWER_SAFE, MVFR0_FPSQRT_SHIFT, 4, 0), + ARM64_FTR_BITS(FTR_HIDDEN, FTR_STRICT, FTR_LOWER_SAFE, MVFR0_FPDIVIDE_SHIFT, 4, 0), + ARM64_FTR_BITS(FTR_HIDDEN, FTR_STRICT, FTR_LOWER_SAFE, MVFR0_FPTRAP_SHIFT, 4, 0), + ARM64_FTR_BITS(FTR_VISIBLE, FTR_STRICT, FTR_LOWER_SAFE, MVFR0_FPDP_SHIFT, 4, 0), + ARM64_FTR_BITS(FTR_HIDDEN, FTR_STRICT, FTR_LOWER_SAFE, MVFR0_FPSP_SHIFT, 4, 0), + ARM64_FTR_BITS(FTR_HIDDEN, FTR_STRICT, FTR_LOWER_SAFE, MVFR0_SIMD_SHIFT, 4, 0), + ARM64_FTR_END, +}; + +static const struct arm64_ftr_bits ftr_mvfr1[] = { + ARM64_FTR_BITS(FTR_VISIBLE, FTR_STRICT, FTR_LOWER_SAFE, MVFR1_SIMDFMAC_SHIFT, 4, 0), + ARM64_FTR_BITS(FTR_HIDDEN, FTR_STRICT, FTR_LOWER_SAFE, MVFR1_FPHP_SHIFT, 4, 0), + ARM64_FTR_BITS(FTR_HIDDEN, FTR_STRICT, FTR_LOWER_SAFE, MVFR1_SIMDHP_SHIFT, 4, 0), + ARM64_FTR_BITS(FTR_VISIBLE, FTR_STRICT, FTR_LOWER_SAFE, MVFR1_SIMDSP_SHIFT, 4, 0), + ARM64_FTR_BITS(FTR_VISIBLE, FTR_STRICT, FTR_LOWER_SAFE, MVFR1_SIMDINT_SHIFT, 4, 0), + ARM64_FTR_BITS(FTR_VISIBLE, FTR_STRICT, FTR_LOWER_SAFE, MVFR1_SIMDLS_SHIFT, 4, 0), + ARM64_FTR_BITS(FTR_HIDDEN, FTR_STRICT, FTR_LOWER_SAFE, MVFR1_FPDNAN_SHIFT, 4, 0), + ARM64_FTR_BITS(FTR_HIDDEN, FTR_STRICT, FTR_LOWER_SAFE, MVFR1_FPFTZ_SHIFT, 4, 0), + ARM64_FTR_END, +}; + static const struct arm64_ftr_bits ftr_mvfr2[] = { ARM64_FTR_BITS(FTR_HIDDEN, FTR_STRICT, FTR_LOWER_SAFE, MVFR2_FPMISC_SHIFT, 4, 0), ARM64_FTR_BITS(FTR_HIDDEN, FTR_STRICT, FTR_LOWER_SAFE, MVFR2_SIMDMISC_SHIFT, 4, 0), @@ -424,10 +448,10 @@ static const struct arm64_ftr_bits ftr_id_isar0[] = { static const struct arm64_ftr_bits ftr_id_isar5[] = { ARM64_FTR_BITS(FTR_HIDDEN, FTR_STRICT, FTR_LOWER_SAFE, ID_ISAR5_RDM_SHIFT, 4, 0), - ARM64_FTR_BITS(FTR_HIDDEN, FTR_STRICT, FTR_LOWER_SAFE, ID_ISAR5_CRC32_SHIFT, 4, 0), - ARM64_FTR_BITS(FTR_HIDDEN, FTR_STRICT, FTR_LOWER_SAFE, ID_ISAR5_SHA2_SHIFT, 4, 0), - ARM64_FTR_BITS(FTR_HIDDEN, FTR_STRICT, FTR_LOWER_SAFE, ID_ISAR5_SHA1_SHIFT, 4, 0), - ARM64_FTR_BITS(FTR_HIDDEN, FTR_STRICT, FTR_LOWER_SAFE, ID_ISAR5_AES_SHIFT, 4, 0), + ARM64_FTR_BITS(FTR_VISIBLE, FTR_STRICT, FTR_LOWER_SAFE, ID_ISAR5_CRC32_SHIFT, 4, 0), + ARM64_FTR_BITS(FTR_VISIBLE, FTR_STRICT, FTR_LOWER_SAFE, ID_ISAR5_SHA2_SHIFT, 4, 0), + ARM64_FTR_BITS(FTR_VISIBLE, FTR_STRICT, FTR_LOWER_SAFE, ID_ISAR5_SHA1_SHIFT, 4, 0), + ARM64_FTR_BITS(FTR_VISIBLE, FTR_STRICT, FTR_LOWER_SAFE, ID_ISAR5_AES_SHIFT, 4, 0), ARM64_FTR_BITS(FTR_HIDDEN, FTR_STRICT, FTR_LOWER_SAFE, ID_ISAR5_SEVL_SHIFT, 4, 0), ARM64_FTR_END, }; @@ -534,7 +558,7 @@ static const struct arm64_ftr_bits ftr_zcr[] = { * Common ftr bits for a 32bit register with all hidden, strict * attributes, with 4bit feature fields and a default safe value of * 0. Covers the following 32bit registers: - * id_isar[1-4], id_mmfr[1-3], id_pfr1, mvfr[0-1] + * id_isar[1-3], id_mmfr[1-3] */ static const struct arm64_ftr_bits ftr_generic_32bits[] = { ARM64_FTR_BITS(FTR_HIDDEN, FTR_STRICT, FTR_LOWER_SAFE, 28, 4, 0), @@ -590,8 +614,8 @@ static const struct __ftr_reg_entry { ARM64_FTR_REG(SYS_ID_ISAR6_EL1, ftr_id_isar6), /* Op1 = 0, CRn = 0, CRm = 3 */ - ARM64_FTR_REG(SYS_MVFR0_EL1, ftr_generic_32bits), - ARM64_FTR_REG(SYS_MVFR1_EL1, ftr_generic_32bits), + ARM64_FTR_REG(SYS_MVFR0_EL1, ftr_mvfr0), + ARM64_FTR_REG(SYS_MVFR1_EL1, ftr_mvfr1), ARM64_FTR_REG(SYS_MVFR2_EL1, ftr_mvfr2), ARM64_FTR_REG(SYS_ID_PFR2_EL1, ftr_id_pfr2), ARM64_FTR_REG(SYS_ID_DFR1_EL1, ftr_id_dfr1), @@ -2814,7 +2838,7 @@ static void __maybe_unused cpu_enable_cnp(struct arm64_cpu_capabilities const *c /* * We emulate only the following system register space. - * Op0 = 0x3, CRn = 0x0, Op1 = 0x0, CRm = [0, 4 - 7] + * Op0 = 0x3, CRn = 0x0, Op1 = 0x0, CRm = [0, 2 - 7] * See Table C5-6 System instruction encodings for System register accesses, * ARMv8 ARM(ARM DDI 0487A.f) for more details. */ @@ -2824,7 +2848,7 @@ static inline bool __attribute_const__ is_emulated(u32 id) sys_reg_CRn(id) == 0x0 && sys_reg_Op1(id) == 0x0 && (sys_reg_CRm(id) == 0 || - ((sys_reg_CRm(id) >= 4) && (sys_reg_CRm(id) <= 7)))); + ((sys_reg_CRm(id) >= 2) && (sys_reg_CRm(id) <= 7)))); } /* From d39e0f582b43f1e00ff398375af762edabfc34e2 Mon Sep 17 00:00:00 2001 From: Yunke Cao Date: Thu, 7 Jul 2022 10:53:31 +0200 Subject: [PATCH 334/342] media: uvcvideo: Use entity get_cur in uvc_ctrl_set commit 5f36851c36b30f713f588ed2b60aa7b4512e2c76 upstream. Entity controls should get_cur using an entity-defined function instead of via a query. Fix this in uvc_ctrl_set. Fixes: 65900c581d01 ("media: uvcvideo: Allow entity-defined get_info and get_cur") Signed-off-by: Yunke Cao Reviewed-by: Ricardo Ribalda Signed-off-by: Laurent Pinchart Signed-off-by: Mauro Carvalho Chehab Signed-off-by: Greg Kroah-Hartman --- drivers/media/usb/uvc/uvc_ctrl.c | 83 ++++++++++++++++++-------------- 1 file changed, 46 insertions(+), 37 deletions(-) diff --git a/drivers/media/usb/uvc/uvc_ctrl.c b/drivers/media/usb/uvc/uvc_ctrl.c index c89f582bd532..dc8d790eb911 100644 --- a/drivers/media/usb/uvc/uvc_ctrl.c +++ b/drivers/media/usb/uvc/uvc_ctrl.c @@ -992,35 +992,55 @@ static s32 __uvc_ctrl_get_value(struct uvc_control_mapping *mapping, return value; } +static int __uvc_ctrl_load_cur(struct uvc_video_chain *chain, + struct uvc_control *ctrl) +{ + u8 *data; + int ret; + + if (ctrl->loaded) + return 0; + + data = uvc_ctrl_data(ctrl, UVC_CTRL_DATA_CURRENT); + + if ((ctrl->info.flags & UVC_CTRL_FLAG_GET_CUR) == 0) { + memset(data, 0, ctrl->info.size); + ctrl->loaded = 1; + + return 0; + } + + if (ctrl->entity->get_cur) + ret = ctrl->entity->get_cur(chain->dev, ctrl->entity, + ctrl->info.selector, data, + ctrl->info.size); + else + ret = uvc_query_ctrl(chain->dev, UVC_GET_CUR, + ctrl->entity->id, chain->dev->intfnum, + ctrl->info.selector, data, + ctrl->info.size); + + if (ret < 0) + return ret; + + ctrl->loaded = 1; + + return ret; +} + static int __uvc_ctrl_get(struct uvc_video_chain *chain, - struct uvc_control *ctrl, struct uvc_control_mapping *mapping, - s32 *value) + struct uvc_control *ctrl, + struct uvc_control_mapping *mapping, + s32 *value) { int ret; if ((ctrl->info.flags & UVC_CTRL_FLAG_GET_CUR) == 0) return -EACCES; - if (!ctrl->loaded) { - if (ctrl->entity->get_cur) { - ret = ctrl->entity->get_cur(chain->dev, - ctrl->entity, - ctrl->info.selector, - uvc_ctrl_data(ctrl, UVC_CTRL_DATA_CURRENT), - ctrl->info.size); - } else { - ret = uvc_query_ctrl(chain->dev, UVC_GET_CUR, - ctrl->entity->id, - chain->dev->intfnum, - ctrl->info.selector, - uvc_ctrl_data(ctrl, UVC_CTRL_DATA_CURRENT), - ctrl->info.size); - } - if (ret < 0) - return ret; - - ctrl->loaded = 1; - } + ret = __uvc_ctrl_load_cur(chain, ctrl); + if (ret < 0) + return ret; *value = __uvc_ctrl_get_value(mapping, uvc_ctrl_data(ctrl, UVC_CTRL_DATA_CURRENT)); @@ -1675,21 +1695,10 @@ int uvc_ctrl_set(struct uvc_fh *handle, * needs to be loaded from the device to perform the read-modify-write * operation. */ - if (!ctrl->loaded && (ctrl->info.size * 8) != mapping->size) { - if ((ctrl->info.flags & UVC_CTRL_FLAG_GET_CUR) == 0) { - memset(uvc_ctrl_data(ctrl, UVC_CTRL_DATA_CURRENT), - 0, ctrl->info.size); - } else { - ret = uvc_query_ctrl(chain->dev, UVC_GET_CUR, - ctrl->entity->id, chain->dev->intfnum, - ctrl->info.selector, - uvc_ctrl_data(ctrl, UVC_CTRL_DATA_CURRENT), - ctrl->info.size); - if (ret < 0) - return ret; - } - - ctrl->loaded = 1; + if ((ctrl->info.size * 8) != mapping->size) { + ret = __uvc_ctrl_load_cur(chain, ctrl); + if (ret < 0) + return ret; } /* Backup the current value in case we need to rollback later. */ From 15469d46ba34559bfe7e3de6659115778c624759 Mon Sep 17 00:00:00 2001 From: Kees Cook Date: Thu, 8 Aug 2024 11:39:08 -0700 Subject: [PATCH 335/342] exec: Fix ToCToU between perm check and set-uid/gid usage commit f50733b45d865f91db90919f8311e2127ce5a0cb upstream. When opening a file for exec via do_filp_open(), permission checking is done against the file's metadata at that moment, and on success, a file pointer is passed back. Much later in the execve() code path, the file metadata (specifically mode, uid, and gid) is used to determine if/how to set the uid and gid. However, those values may have changed since the permissions check, meaning the execution may gain unintended privileges. For example, if a file could change permissions from executable and not set-id: ---------x 1 root root 16048 Aug 7 13:16 target to set-id and non-executable: ---S------ 1 root root 16048 Aug 7 13:16 target it is possible to gain root privileges when execution should have been disallowed. While this race condition is rare in real-world scenarios, it has been observed (and proven exploitable) when package managers are updating the setuid bits of installed programs. Such files start with being world-executable but then are adjusted to be group-exec with a set-uid bit. For example, "chmod o-x,u+s target" makes "target" executable only by uid "root" and gid "cdrom", while also becoming setuid-root: -rwxr-xr-x 1 root cdrom 16048 Aug 7 13:16 target becomes: -rwsr-xr-- 1 root cdrom 16048 Aug 7 13:16 target But racing the chmod means users without group "cdrom" membership can get the permission to execute "target" just before the chmod, and when the chmod finishes, the exec reaches brpm_fill_uid(), and performs the setuid to root, violating the expressed authorization of "only cdrom group members can setuid to root". Re-check that we still have execute permissions in case the metadata has changed. It would be better to keep a copy from the perm-check time, but until we can do that refactoring, the least-bad option is to do a full inode_permission() call (under inode lock). It is understood that this is safe against dead-locks, but hardly optimal. Reported-by: Marco Vanotti Tested-by: Marco Vanotti Suggested-by: Linus Torvalds Cc: stable@vger.kernel.org Cc: Eric Biederman Cc: Alexander Viro Cc: Christian Brauner Signed-off-by: Kees Cook Signed-off-by: Greg Kroah-Hartman --- fs/exec.c | 8 +++++++- 1 file changed, 7 insertions(+), 1 deletion(-) diff --git a/fs/exec.c b/fs/exec.c index d5c8f085235b..6a4bbe58d3c0 100644 --- a/fs/exec.c +++ b/fs/exec.c @@ -1588,6 +1588,7 @@ static void bprm_fill_uid(struct linux_binprm *bprm, struct file *file) unsigned int mode; kuid_t uid; kgid_t gid; + int err; if (!mnt_may_suid(file->f_path.mnt)) return; @@ -1603,12 +1604,17 @@ static void bprm_fill_uid(struct linux_binprm *bprm, struct file *file) /* Be careful if suid/sgid is set */ inode_lock(inode); - /* reload atomically mode/uid/gid now that lock held */ + /* Atomically reload and check mode/uid/gid now that lock held. */ mode = inode->i_mode; uid = inode->i_uid; gid = inode->i_gid; + err = inode_permission(inode, MAY_EXEC); inode_unlock(inode); + /* Did the exec bit vanish out from under us? Give up. */ + if (err) + return; + /* We ignore suid/sgid if there are no mappings for them in the ns */ if (!kuid_has_mapping(bprm->cred->user_ns, uid) || !kgid_has_mapping(bprm->cred->user_ns, gid)) From b21ea49e6e69b43ff9eabf067d40b68e7852fe0e Mon Sep 17 00:00:00 2001 From: WangYuli Date: Mon, 15 Jul 2024 17:31:44 +0800 Subject: [PATCH 336/342] nvme/pci: Add APST quirk for Lenovo N60z laptop commit ab091ec536cb7b271983c0c063b17f62f3591583 upstream. There is a hardware power-saving problem with the Lenovo N60z board. When turn it on and leave it for 10 hours, there is a 20% chance that a nvme disk will not wake up until reboot. Link: https://lore.kernel.org/all/2B5581C46AC6E335+9c7a81f1-05fb-4fd0-9fbb-108757c21628@uniontech.com Signed-off-by: hmy Signed-off-by: Wentao Guan Signed-off-by: WangYuli Signed-off-by: Keith Busch Signed-off-by: Greg Kroah-Hartman --- drivers/nvme/host/pci.c | 7 +++++++ 1 file changed, 7 insertions(+) diff --git a/drivers/nvme/host/pci.c b/drivers/nvme/host/pci.c index 4a4b7aa74835..78cac4220e03 100644 --- a/drivers/nvme/host/pci.c +++ b/drivers/nvme/host/pci.c @@ -2846,6 +2846,13 @@ static unsigned long check_vendor_combination_bug(struct pci_dev *pdev) return NVME_QUIRK_SIMPLE_SUSPEND; } + /* + * NVMe SSD drops off the PCIe bus after system idle + * for 10 hours on a Lenovo N60z board. + */ + if (dmi_match(DMI_BOARD_NAME, "LXKT-ZXEG-N6")) + return NVME_QUIRK_NO_APST; + return 0; } From 06e9e6ac59fed629c343e627302f528b54a78079 Mon Sep 17 00:00:00 2001 From: Cai Huoqing Date: Mon, 2 Aug 2021 09:37:17 +0800 Subject: [PATCH 337/342] vdpa: Make use of PFN_PHYS/PFN_UP/PFN_DOWN helper macro [ Upstream commit 729ce5a5bd6fda5eb2322a39db2287f1f26f92f3 ] it's a nice refactor to make use of PFN_PHYS/PFN_UP/PFN_DOWN helper macro Signed-off-by: Cai Huoqing Link: https://lore.kernel.org/r/20210802013717.851-1-caihuoqing@baidu.com Acked-by: Jason Wang Signed-off-by: Michael S. Tsirkin Stable-dep-of: 0823dc64586b ("vhost-vdpa: switch to use vmf_insert_pfn() in the fault handler") Signed-off-by: Sasha Levin --- drivers/vhost/vdpa.c | 24 ++++++++++++------------ 1 file changed, 12 insertions(+), 12 deletions(-) diff --git a/drivers/vhost/vdpa.c b/drivers/vhost/vdpa.c index 04578aa87e4d..f48047a1027a 100644 --- a/drivers/vhost/vdpa.c +++ b/drivers/vhost/vdpa.c @@ -519,15 +519,15 @@ static void vhost_vdpa_iotlb_unmap(struct vhost_vdpa *v, u64 start, u64 last) unsigned long pfn, pinned; while ((map = vhost_iotlb_itree_first(iotlb, start, last)) != NULL) { - pinned = map->size >> PAGE_SHIFT; - for (pfn = map->addr >> PAGE_SHIFT; + pinned = PFN_DOWN(map->size); + for (pfn = PFN_DOWN(map->addr); pinned > 0; pfn++, pinned--) { page = pfn_to_page(pfn); if (map->perm & VHOST_ACCESS_WO) set_page_dirty_lock(page); unpin_user_page(page); } - atomic64_sub(map->size >> PAGE_SHIFT, &dev->mm->pinned_vm); + atomic64_sub(PFN_DOWN(map->size), &dev->mm->pinned_vm); vhost_iotlb_map_free(iotlb, map); } } @@ -589,7 +589,7 @@ static int vhost_vdpa_map(struct vhost_vdpa *v, if (r) vhost_iotlb_del_range(dev->iotlb, iova, iova + size - 1); else - atomic64_add(size >> PAGE_SHIFT, &dev->mm->pinned_vm); + atomic64_add(PFN_DOWN(size), &dev->mm->pinned_vm); return r; } @@ -643,7 +643,7 @@ static int vhost_vdpa_process_iotlb_update(struct vhost_vdpa *v, if (msg->perm & VHOST_ACCESS_WO) gup_flags |= FOLL_WRITE; - npages = PAGE_ALIGN(msg->size + (iova & ~PAGE_MASK)) >> PAGE_SHIFT; + npages = PFN_UP(msg->size + (iova & ~PAGE_MASK)); if (!npages) { ret = -EINVAL; goto free; @@ -651,7 +651,7 @@ static int vhost_vdpa_process_iotlb_update(struct vhost_vdpa *v, mmap_read_lock(dev->mm); - lock_limit = rlimit(RLIMIT_MEMLOCK) >> PAGE_SHIFT; + lock_limit = PFN_DOWN(rlimit(RLIMIT_MEMLOCK)); if (npages + atomic64_read(&dev->mm->pinned_vm) > lock_limit) { ret = -ENOMEM; goto unlock; @@ -685,9 +685,9 @@ static int vhost_vdpa_process_iotlb_update(struct vhost_vdpa *v, if (last_pfn && (this_pfn != last_pfn + 1)) { /* Pin a contiguous chunk of memory */ - csize = (last_pfn - map_pfn + 1) << PAGE_SHIFT; + csize = PFN_PHYS(last_pfn - map_pfn + 1); ret = vhost_vdpa_map(v, iova, csize, - map_pfn << PAGE_SHIFT, + PFN_PHYS(map_pfn), msg->perm); if (ret) { /* @@ -711,13 +711,13 @@ static int vhost_vdpa_process_iotlb_update(struct vhost_vdpa *v, last_pfn = this_pfn; } - cur_base += pinned << PAGE_SHIFT; + cur_base += PFN_PHYS(pinned); npages -= pinned; } /* Pin the rest chunk */ - ret = vhost_vdpa_map(v, iova, (last_pfn - map_pfn + 1) << PAGE_SHIFT, - map_pfn << PAGE_SHIFT, msg->perm); + ret = vhost_vdpa_map(v, iova, PFN_PHYS(last_pfn - map_pfn + 1), + PFN_PHYS(map_pfn), msg->perm); out: if (ret) { if (nchunks) { @@ -961,7 +961,7 @@ static vm_fault_t vhost_vdpa_fault(struct vm_fault *vmf) vma->vm_page_prot = pgprot_noncached(vma->vm_page_prot); if (remap_pfn_range(vma, vmf->address & PAGE_MASK, - notify.addr >> PAGE_SHIFT, PAGE_SIZE, + PFN_DOWN(notify.addr), PAGE_SIZE, vma->vm_page_prot)) return VM_FAULT_SIGBUS; From a563f1243092518271e804b8c481fc1254c145bd Mon Sep 17 00:00:00 2001 From: Jason Wang Date: Mon, 1 Jul 2024 11:31:59 +0800 Subject: [PATCH 338/342] vhost-vdpa: switch to use vmf_insert_pfn() in the fault handler [ Upstream commit 0823dc64586ba5ea13a7d200a5d33e4c5fa45950 ] remap_pfn_page() should not be called in the fault handler as it may change the vma->flags which may trigger lockdep warning since the vma write lock is not held. Actually there's no need to modify the vma->flags as it has been set in the mmap(). So this patch switches to use vmf_insert_pfn() instead. Reported-by: Dragos Tatulea Tested-by: Dragos Tatulea Fixes: ddd89d0a059d ("vhost_vdpa: support doorbell mapping via mmap") Cc: stable@vger.kernel.org Signed-off-by: Jason Wang Message-Id: <20240701033159.18133-1-jasowang@redhat.com> Signed-off-by: Michael S. Tsirkin Reviewed-by: Michal Kubiak Signed-off-by: Sasha Levin --- drivers/vhost/vdpa.c | 8 +------- 1 file changed, 1 insertion(+), 7 deletions(-) diff --git a/drivers/vhost/vdpa.c b/drivers/vhost/vdpa.c index f48047a1027a..c9f585db1553 100644 --- a/drivers/vhost/vdpa.c +++ b/drivers/vhost/vdpa.c @@ -959,13 +959,7 @@ static vm_fault_t vhost_vdpa_fault(struct vm_fault *vmf) notify = ops->get_vq_notification(vdpa, index); - vma->vm_page_prot = pgprot_noncached(vma->vm_page_prot); - if (remap_pfn_range(vma, vmf->address & PAGE_MASK, - PFN_DOWN(notify.addr), PAGE_SIZE, - vma->vm_page_prot)) - return VM_FAULT_SIGBUS; - - return VM_FAULT_NOPAGE; + return vmf_insert_pfn(vma, vmf->address & PAGE_MASK, PFN_DOWN(notify.addr)); } static const struct vm_operations_struct vhost_vdpa_vm_ops = { From 80ac0cc9c0bef984e29637b1efa93d7214b42f53 Mon Sep 17 00:00:00 2001 From: Eric Dumazet Date: Sat, 15 Jun 2024 16:08:00 +0000 Subject: [PATCH 339/342] wifi: cfg80211: restrict NL80211_ATTR_TXQ_QUANTUM values [ Upstream commit d1cba2ea8121e7fdbe1328cea782876b1dd80993 ] syzbot is able to trigger softlockups, setting NL80211_ATTR_TXQ_QUANTUM to 2^31. We had a similar issue in sch_fq, fixed with commit d9e15a273306 ("pkt_sched: fq: do not accept silly TCA_FQ_QUANTUM") watchdog: BUG: soft lockup - CPU#1 stuck for 26s! [kworker/1:0:24] Modules linked in: irq event stamp: 131135 hardirqs last enabled at (131134): [] __exit_to_kernel_mode arch/arm64/kernel/entry-common.c:85 [inline] hardirqs last enabled at (131134): [] exit_to_kernel_mode+0xdc/0x10c arch/arm64/kernel/entry-common.c:95 hardirqs last disabled at (131135): [] __el1_irq arch/arm64/kernel/entry-common.c:533 [inline] hardirqs last disabled at (131135): [] el1_interrupt+0x24/0x68 arch/arm64/kernel/entry-common.c:551 softirqs last enabled at (125892): [] neigh_hh_init net/core/neighbour.c:1538 [inline] softirqs last enabled at (125892): [] neigh_resolve_output+0x268/0x658 net/core/neighbour.c:1553 softirqs last disabled at (125896): [] local_bh_disable+0x10/0x34 include/linux/bottom_half.h:19 CPU: 1 PID: 24 Comm: kworker/1:0 Not tainted 6.9.0-rc7-syzkaller-gfda5695d692c #0 Hardware name: Google Google Compute Engine/Google Compute Engine, BIOS Google 03/27/2024 Workqueue: mld mld_ifc_work pstate: 80400005 (Nzcv daif +PAN -UAO -TCO -DIT -SSBS BTYPE=--) pc : __list_del include/linux/list.h:195 [inline] pc : __list_del_entry include/linux/list.h:218 [inline] pc : list_move_tail include/linux/list.h:310 [inline] pc : fq_tin_dequeue include/net/fq_impl.h:112 [inline] pc : ieee80211_tx_dequeue+0x6b8/0x3b4c net/mac80211/tx.c:3854 lr : __list_del_entry include/linux/list.h:218 [inline] lr : list_move_tail include/linux/list.h:310 [inline] lr : fq_tin_dequeue include/net/fq_impl.h:112 [inline] lr : ieee80211_tx_dequeue+0x67c/0x3b4c net/mac80211/tx.c:3854 sp : ffff800093d36700 x29: ffff800093d36a60 x28: ffff800093d36960 x27: dfff800000000000 x26: ffff0000d800ad50 x25: ffff0000d800abe0 x24: ffff0000d800abf0 x23: ffff0000e0032468 x22: ffff0000e00324d4 x21: ffff0000d800abf0 x20: ffff0000d800abf8 x19: ffff0000d800abf0 x18: ffff800093d363c0 x17: 000000000000d476 x16: ffff8000805519dc x15: ffff7000127a6cc8 x14: 1ffff000127a6cc8 x13: 0000000000000004 x12: ffffffffffffffff x11: ffff7000127a6cc8 x10: 0000000000ff0100 x9 : 0000000000000000 x8 : 0000000000000000 x7 : 0000000000000000 x6 : 0000000000000000 x5 : ffff80009287aa08 x4 : 0000000000000008 x3 : ffff80008034c7fc x2 : ffff0000e0032468 x1 : 00000000da0e46b8 x0 : ffff0000e0032470 Call trace: __list_del include/linux/list.h:195 [inline] __list_del_entry include/linux/list.h:218 [inline] list_move_tail include/linux/list.h:310 [inline] fq_tin_dequeue include/net/fq_impl.h:112 [inline] ieee80211_tx_dequeue+0x6b8/0x3b4c net/mac80211/tx.c:3854 wake_tx_push_queue net/mac80211/util.c:294 [inline] ieee80211_handle_wake_tx_queue+0x118/0x274 net/mac80211/util.c:315 drv_wake_tx_queue net/mac80211/driver-ops.h:1350 [inline] schedule_and_wake_txq net/mac80211/driver-ops.h:1357 [inline] ieee80211_queue_skb+0x18e8/0x2244 net/mac80211/tx.c:1664 ieee80211_tx+0x260/0x400 net/mac80211/tx.c:1966 ieee80211_xmit+0x278/0x354 net/mac80211/tx.c:2062 __ieee80211_subif_start_xmit+0xab8/0x122c net/mac80211/tx.c:4338 ieee80211_subif_start_xmit+0xe0/0x438 net/mac80211/tx.c:4532 __netdev_start_xmit include/linux/netdevice.h:4903 [inline] netdev_start_xmit include/linux/netdevice.h:4917 [inline] xmit_one net/core/dev.c:3531 [inline] dev_hard_start_xmit+0x27c/0x938 net/core/dev.c:3547 __dev_queue_xmit+0x1678/0x33fc net/core/dev.c:4341 dev_queue_xmit include/linux/netdevice.h:3091 [inline] neigh_resolve_output+0x558/0x658 net/core/neighbour.c:1563 neigh_output include/net/neighbour.h:542 [inline] ip6_finish_output2+0x104c/0x1ee8 net/ipv6/ip6_output.c:137 ip6_finish_output+0x428/0x7a0 net/ipv6/ip6_output.c:222 NF_HOOK_COND include/linux/netfilter.h:303 [inline] ip6_output+0x270/0x594 net/ipv6/ip6_output.c:243 dst_output include/net/dst.h:450 [inline] NF_HOOK+0x160/0x4f0 include/linux/netfilter.h:314 mld_sendpack+0x7b4/0x10f4 net/ipv6/mcast.c:1818 mld_send_cr net/ipv6/mcast.c:2119 [inline] mld_ifc_work+0x840/0xd0c net/ipv6/mcast.c:2650 process_one_work+0x7b8/0x15d4 kernel/workqueue.c:3267 process_scheduled_works kernel/workqueue.c:3348 [inline] worker_thread+0x938/0xef4 kernel/workqueue.c:3429 kthread+0x288/0x310 kernel/kthread.c:388 ret_from_fork+0x10/0x20 arch/arm64/kernel/entry.S:860 Fixes: 52539ca89f36 ("cfg80211: Expose TXQ stats and parameters to userspace") Signed-off-by: Eric Dumazet Link: https://patch.msgid.link/20240615160800.250667-1-edumazet@google.com Signed-off-by: Johannes Berg Signed-off-by: Sasha Levin Signed-off-by: Greg Kroah-Hartman --- net/wireless/nl80211.c | 6 +++++- 1 file changed, 5 insertions(+), 1 deletion(-) diff --git a/net/wireless/nl80211.c b/net/wireless/nl80211.c index f9ad7de710cb..9a6bbf24b0f7 100644 --- a/net/wireless/nl80211.c +++ b/net/wireless/nl80211.c @@ -403,6 +403,10 @@ nl80211_unsol_bcast_probe_resp_policy[NL80211_UNSOL_BCAST_PROBE_RESP_ATTR_MAX + .len = IEEE80211_MAX_DATA_LEN } }; +static struct netlink_range_validation q_range = { + .max = INT_MAX, +}; + static const struct nla_policy nl80211_policy[NUM_NL80211_ATTR] = { [0] = { .strict_start_type = NL80211_ATTR_HE_OBSS_PD }, [NL80211_ATTR_WIPHY] = { .type = NLA_U32 }, @@ -685,7 +689,7 @@ static const struct nla_policy nl80211_policy[NUM_NL80211_ATTR] = { [NL80211_ATTR_TXQ_LIMIT] = { .type = NLA_U32 }, [NL80211_ATTR_TXQ_MEMORY_LIMIT] = { .type = NLA_U32 }, - [NL80211_ATTR_TXQ_QUANTUM] = { .type = NLA_U32 }, + [NL80211_ATTR_TXQ_QUANTUM] = NLA_POLICY_FULL_RANGE(NLA_U32, &q_range), [NL80211_ATTR_HE_CAPABILITY] = NLA_POLICY_RANGE(NLA_BINARY, NL80211_HE_MIN_CAPABILITY_LEN, From e1ee1c4198c7a1fc5f3c23f472152b0e7fd76c08 Mon Sep 17 00:00:00 2001 From: Michael Walle Date: Mon, 17 Jun 2024 11:13:29 +0200 Subject: [PATCH 340/342] ARM: dts: imx6qdl-kontron-samx6i: fix phy-mode commit 0df3c7d7a73d75153090637392c0b73a63cdc24a upstream. The i.MX6 cannot add any RGMII delays. The PHY has to add both the RX and TX delays on the RGMII interface. Fix the interface mode. While at it, use the new phy-connection-type property name. Fixes: 5694eed98cca ("ARM: dts: imx6qdl-kontron-samx6i: move phy reset into phy-node") Signed-off-by: Michael Walle Signed-off-by: Shawn Guo Signed-off-by: Greg Kroah-Hartman --- arch/arm/boot/dts/imx6qdl-kontron-samx6i.dtsi | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/arch/arm/boot/dts/imx6qdl-kontron-samx6i.dtsi b/arch/arm/boot/dts/imx6qdl-kontron-samx6i.dtsi index 9ec1519e1719..2d1cc67628b4 100644 --- a/arch/arm/boot/dts/imx6qdl-kontron-samx6i.dtsi +++ b/arch/arm/boot/dts/imx6qdl-kontron-samx6i.dtsi @@ -260,7 +260,7 @@ smarc_flash: flash@0 { &fec { pinctrl-names = "default"; pinctrl-0 = <&pinctrl_enet>; - phy-mode = "rgmii"; + phy-connection-type = "rgmii-id"; phy-handle = <ðphy>; mdio { From 2de18b5cc38e83428316d6d6d05a702208fb299b Mon Sep 17 00:00:00 2001 From: Sean Young Date: Thu, 8 Aug 2024 10:35:19 +0200 Subject: [PATCH 341/342] media: Revert "media: dvb-usb: Fix unexpected infinite loop in dvb_usb_read_remote_control()" commit 0c84bde4f37ba27d50e4c70ecacd33fe4a57030d upstream. This reverts commit 2052138b7da52ad5ccaf74f736d00f39a1c9198c. This breaks the TeVii s480 dual DVB-S2 S660. The device has a bulk in endpoint but no corresponding out endpoint, so the device does not pass the "has both receive and send bulk endpoint" test. Seemingly this device does not use dvb_usb_generic_rw() so I have tried removing the generic_bulk_ctrl_endpoint entry, but this resulted in different problems. As we have no explanation yet, revert. $ dmesg | grep -i -e dvb -e dw21 -e usb\ 4 [ 0.999122] usb 1-1: new high-speed USB device number 2 using ehci-pci [ 1.023123] usb 4-1: new high-speed USB device number 2 using ehci-pci [ 1.130247] usb 1-1: New USB device found, idVendor=9022, idProduct=d482, +bcdDevice= 0.01 [ 1.130257] usb 1-1: New USB device strings: Mfr=0, Product=0, SerialNumber=0 [ 1.152323] usb 4-1: New USB device found, idVendor=9022, idProduct=d481, +bcdDevice= 0.01 [ 1.152329] usb 4-1: New USB device strings: Mfr=0, Product=0, SerialNumber=0 [ 6.701033] dvb-usb: found a 'TeVii S480.2 USB' in cold state, will try to +load a firmware [ 6.701178] dvb-usb: downloading firmware from file 'dvb-usb-s660.fw' [ 6.701179] dw2102: start downloading DW210X firmware [ 6.703715] dvb-usb: found a 'Microsoft Xbox One Digital TV Tuner' in cold +state, will try to load a firmware [ 6.703974] dvb-usb: downloading firmware from file 'dvb-usb-dib0700-1.20.fw' [ 6.756432] usb 1-1: USB disconnect, device number 2 [ 6.862119] dvb-usb: found a 'TeVii S480.2 USB' in warm state. [ 6.862194] dvb-usb: TeVii S480.2 USB error while loading driver (-22) [ 6.862209] dvb-usb: found a 'TeVii S480.1 USB' in cold state, will try to +load a firmware [ 6.862244] dvb-usb: downloading firmware from file 'dvb-usb-s660.fw' [ 6.862245] dw2102: start downloading DW210X firmware [ 6.914811] usb 4-1: USB disconnect, device number 2 [ 7.014131] dvb-usb: found a 'TeVii S480.1 USB' in warm state. [ 7.014487] dvb-usb: TeVii S480.1 USB error while loading driver (-22) [ 7.014538] usbcore: registered new interface driver dw2102 Closes: https://lore.kernel.org/stable/20240801165146.38991f60@mir/ Fixes: 2052138b7da5 ("media: dvb-usb: Fix unexpected infinite loop in dvb_usb_read_remote_control()") Reported-by: Stefan Lippers-Hollmann Cc: stable@vger.kernel.org Signed-off-by: Sean Young Signed-off-by: Mauro Carvalho Chehab Signed-off-by: Greg Kroah-Hartman --- drivers/media/usb/dvb-usb/dvb-usb-init.c | 35 +++--------------------- 1 file changed, 4 insertions(+), 31 deletions(-) diff --git a/drivers/media/usb/dvb-usb/dvb-usb-init.c b/drivers/media/usb/dvb-usb/dvb-usb-init.c index 6cf6d08cc4ec..58eea8ab5477 100644 --- a/drivers/media/usb/dvb-usb/dvb-usb-init.c +++ b/drivers/media/usb/dvb-usb/dvb-usb-init.c @@ -23,40 +23,11 @@ static int dvb_usb_force_pid_filter_usage; module_param_named(force_pid_filter_usage, dvb_usb_force_pid_filter_usage, int, 0444); MODULE_PARM_DESC(force_pid_filter_usage, "force all dvb-usb-devices to use a PID filter, if any (default: 0)."); -static int dvb_usb_check_bulk_endpoint(struct dvb_usb_device *d, u8 endpoint) -{ - if (endpoint) { - int ret; - - ret = usb_pipe_type_check(d->udev, usb_sndbulkpipe(d->udev, endpoint)); - if (ret) - return ret; - ret = usb_pipe_type_check(d->udev, usb_rcvbulkpipe(d->udev, endpoint)); - if (ret) - return ret; - } - return 0; -} - -static void dvb_usb_clear_halt(struct dvb_usb_device *d, u8 endpoint) -{ - if (endpoint) { - usb_clear_halt(d->udev, usb_sndbulkpipe(d->udev, endpoint)); - usb_clear_halt(d->udev, usb_rcvbulkpipe(d->udev, endpoint)); - } -} - static int dvb_usb_adapter_init(struct dvb_usb_device *d, short *adapter_nrs) { struct dvb_usb_adapter *adap; int ret, n, o; - ret = dvb_usb_check_bulk_endpoint(d, d->props.generic_bulk_ctrl_endpoint); - if (ret) - return ret; - ret = dvb_usb_check_bulk_endpoint(d, d->props.generic_bulk_ctrl_endpoint_response); - if (ret) - return ret; for (n = 0; n < d->props.num_adapters; n++) { adap = &d->adapter[n]; adap->dev = d; @@ -132,8 +103,10 @@ static int dvb_usb_adapter_init(struct dvb_usb_device *d, short *adapter_nrs) * when reloading the driver w/o replugging the device * sometimes a timeout occurs, this helps */ - dvb_usb_clear_halt(d, d->props.generic_bulk_ctrl_endpoint); - dvb_usb_clear_halt(d, d->props.generic_bulk_ctrl_endpoint_response); + if (d->props.generic_bulk_ctrl_endpoint != 0) { + usb_clear_halt(d->udev, usb_sndbulkpipe(d->udev, d->props.generic_bulk_ctrl_endpoint)); + usb_clear_halt(d->udev, usb_rcvbulkpipe(d->udev, d->props.generic_bulk_ctrl_endpoint)); + } return 0; From b2add7c50b5bf51a401424ad00792b130a73c2c5 Mon Sep 17 00:00:00 2001 From: Greg Kroah-Hartman Date: Mon, 19 Aug 2024 05:41:24 +0200 Subject: [PATCH 342/342] Linux 5.10.224 Link: https://lore.kernel.org/r/20240815131919.196120297@linuxfoundation.org Tested-by: Pavel Machek (CIP) Tested-by: Florian Fainelli Link: https://lore.kernel.org/r/20240816101509.001640500@linuxfoundation.org Tested-by: Mark Brown Tested-by: Pavel Machek (CIP) Tested-by: Florian Fainelli Link: https://lore.kernel.org/r/20240817074737.217182940@linuxfoundation.org Tested-by: Jon Hunter Tested-by: Pavel Machek (CIP) Signed-off-by: Greg Kroah-Hartman --- Makefile | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/Makefile b/Makefile index 91c79c64f5a3..38351794f6c9 100644 --- a/Makefile +++ b/Makefile @@ -1,7 +1,7 @@ # SPDX-License-Identifier: GPL-2.0 VERSION = 5 PATCHLEVEL = 10 -SUBLEVEL = 223 +SUBLEVEL = 224 EXTRAVERSION = NAME = Dare mighty things