From 9fad9d560af5c654bb38e0b07ee54a4e9acdc5cd Mon Sep 17 00:00:00 2001 From: Justin Stitt Date: Wed, 8 May 2024 17:22:51 +0000 Subject: scsi: sr: Fix unintentional arithmetic wraparound Running syzkaller with the newly reintroduced signed integer overflow sanitizer produces this report: [ 65.194362] ------------[ cut here ]------------ [ 65.197752] UBSAN: signed-integer-overflow in ../drivers/scsi/sr_ioctl.c:436:9 [ 65.203607] -2147483648 * 177 cannot be represented in type 'int' [ 65.207911] CPU: 2 PID: 10416 Comm: syz-executor.1 Not tainted 6.8.0-rc2-00035-gb3ef86b5a957 #1 [ 65.213585] Hardware name: QEMU Standard PC (i440FX + PIIX, 1996), BIOS 1.16.3-debian-1.16.3-2 04/01/2014 [ 65.219923] Call Trace: [ 65.221556] [ 65.223029] dump_stack_lvl+0x93/0xd0 [ 65.225573] handle_overflow+0x171/0x1b0 [ 65.228219] sr_select_speed+0xeb/0xf0 [ 65.230786] ? __pm_runtime_resume+0xe6/0x130 [ 65.233606] sr_block_ioctl+0x15d/0x1d0 ... Historically, the signed integer overflow sanitizer did not work in the kernel due to its interaction with `-fwrapv` but this has since been changed [1] in the newest version of Clang. It was re-enabled in the kernel with Commit 557f8c582a9b ("ubsan: Reintroduce signed overflow sanitizer"). Firstly, let's change the type of "speed" to unsigned long as sr_select_speed()'s only caller passes in an unsigned long anyways. $ git grep '\.select_speed' | drivers/scsi/sr.c: .select_speed = sr_select_speed, ... | static int cdrom_ioctl_select_speed(struct cdrom_device_info *cdi, | unsigned long arg) | { | ... | return cdi->ops->select_speed(cdi, arg); | } Next, let's add an extra check to make sure we don't exceed 0xffff/177 (350) since 0xffff is the max speed. This has two benefits: 1) we deal with integer overflow before it happens and 2) we properly respect the max speed of 0xffff. There are some "magic" numbers here but I did not want to change more than what was necessary. Link: https://github.com/llvm/llvm-project/pull/82432 [1] Closes: https://github.com/KSPP/linux/issues/357 Cc: linux-hardening@vger.kernel.org Signed-off-by: Justin Stitt Link: https://lore.kernel.org/r/20240508-b4-b4-sio-sr_select_speed-v2-1-00b68f724290@google.com Reviewed-by: Kees Cook Signed-off-by: Martin K. Petersen --- include/linux/cdrom.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/cdrom.h b/include/linux/cdrom.h index 98c6fd0b39b6..fdfb61ccf55a 100644 --- a/include/linux/cdrom.h +++ b/include/linux/cdrom.h @@ -77,7 +77,7 @@ struct cdrom_device_ops { unsigned int clearing, int slot); int (*tray_move) (struct cdrom_device_info *, int); int (*lock_door) (struct cdrom_device_info *, int); - int (*select_speed) (struct cdrom_device_info *, int); + int (*select_speed) (struct cdrom_device_info *, unsigned long); int (*get_last_session) (struct cdrom_device_info *, struct cdrom_multisession *); int (*get_mcn) (struct cdrom_device_info *, -- cgit v1.2.3 From db003a28e03f95f2bcb63f037a2078b8870b1ecd Mon Sep 17 00:00:00 2001 From: Christian Brauner Date: Tue, 28 May 2024 14:33:20 +0200 Subject: netfs: fix kernel doc for nets_wait_for_outstanding_io() The @inode parameter wasn't documented leading to new doc build warnings. Fixes: f89ea63f1c65 ("netfs, 9p: Fix race between umount and async request completion") Link: https://lore.kernel.org/r/20240528133050.7e09d78e@canb.auug.org.au Signed-off-by: Christian Brauner --- include/linux/netfs.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/netfs.h b/include/linux/netfs.h index 3ca3906bb8da..5d0288938cc2 100644 --- a/include/linux/netfs.h +++ b/include/linux/netfs.h @@ -521,7 +521,7 @@ static inline struct fscache_cookie *netfs_i_cookie(struct netfs_inode *ctx) /** * netfs_wait_for_outstanding_io - Wait for outstanding I/O to complete - * @ctx: The netfs inode to wait on + * @inode: The netfs inode to wait on * * Wait for outstanding I/O requests of any type to complete. This is intended * to be called from inode eviction routines. This makes sure that any -- cgit v1.2.3 From 89e8a2366e3bce584b6c01549d5019c5cda1205e Mon Sep 17 00:00:00 2001 From: Lu Baolu Date: Tue, 28 May 2024 12:25:28 +0800 Subject: iommu: Return right value in iommu_sva_bind_device() iommu_sva_bind_device() should return either a sva bond handle or an ERR_PTR value in error cases. Existing drivers (idxd and uacce) only check the return value with IS_ERR(). This could potentially lead to a kernel NULL pointer dereference issue if the function returns NULL instead of an error pointer. In reality, this doesn't cause any problems because iommu_sva_bind_device() only returns NULL when the kernel is not configured with CONFIG_IOMMU_SVA. In this case, iommu_dev_enable_feature(dev, IOMMU_DEV_FEAT_SVA) will return an error, and the device drivers won't call iommu_sva_bind_device() at all. Fixes: 26b25a2b98e4 ("iommu: Bind process address spaces to devices") Signed-off-by: Lu Baolu Reviewed-by: Jean-Philippe Brucker Reviewed-by: Kevin Tian Reviewed-by: Vasant Hegde Link: https://lore.kernel.org/r/20240528042528.71396-1-baolu.lu@linux.intel.com Signed-off-by: Joerg Roedel --- include/linux/iommu.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/iommu.h b/include/linux/iommu.h index 7bc8dff7cf6d..17b3f36ad843 100644 --- a/include/linux/iommu.h +++ b/include/linux/iommu.h @@ -1533,7 +1533,7 @@ struct iommu_domain *iommu_sva_domain_alloc(struct device *dev, static inline struct iommu_sva * iommu_sva_bind_device(struct device *dev, struct mm_struct *mm) { - return NULL; + return ERR_PTR(-ENODEV); } static inline void iommu_sva_unbind_device(struct iommu_sva *handle) -- cgit v1.2.3 From c9d52fb313d3719d69a040f4ca78a3e2e95fba21 Mon Sep 17 00:00:00 2001 From: Dan Williams Date: Thu, 30 May 2024 18:04:24 -0700 Subject: PCI: Revert the cfg_access_lock lockdep mechanism While the experiment did reveal that there are additional places that are missing the lock during secondary bus reset, one of the places that needs to take cfg_access_lock (pci_bus_lock()) is not prepared for lockdep annotation. Specifically, pci_bus_lock() takes pci_dev_lock() recursively and is currently dependent on the fact that the device_lock() is marked lockdep_set_novalidate_class(&dev->mutex). Otherwise, without that annotation, pci_bus_lock() would need to use something like a new pci_dev_lock_nested() helper, a scheme to track a PCI device's depth in the topology, and a hope that the depth of a PCI tree never exceeds the max value for a lockdep subclass. The alternative to ripping out the lockdep coverage would be to deploy a dynamic lock key for every PCI device. Unfortunately, there is evidence that increasing the number of keys that lockdep needs to track to be per-PCI-device is prohibitively expensive for something like the cfg_access_lock. The main motivation for adding the annotation in the first place was to catch unlocked secondary bus resets, not necessarily catch lock ordering problems between cfg_access_lock and other locks. Solve that narrower problem with follow-on patches, and just due to targeted revert for now. Link: https://lore.kernel.org/r/171711746402.1628941.14575335981264103013.stgit@dwillia2-xfh.jf.intel.com Fixes: 7e89efc6e9e4 ("PCI: Lock upstream bridge for pci_reset_function()") Reported-by: Imre Deak Closes: https://intel-gfx-ci.01.org/tree/drm-tip/Patchwork_134186v1/shard-dg2-1/igt@device_reset@unbind-reset-rebind.html Signed-off-by: Dan Williams Signed-off-by: Bjorn Helgaas Tested-by: Hans de Goede Tested-by: Kalle Valo Reviewed-by: Dave Jiang Cc: Jani Saarinen --- drivers/pci/access.c | 4 ---- drivers/pci/pci.c | 1 - drivers/pci/probe.c | 3 --- include/linux/lockdep.h | 5 ----- include/linux/pci.h | 2 -- 5 files changed, 15 deletions(-) (limited to 'include/linux') diff --git a/drivers/pci/access.c b/drivers/pci/access.c index 30f031de9cfe..b123da16b63b 100644 --- a/drivers/pci/access.c +++ b/drivers/pci/access.c @@ -289,8 +289,6 @@ void pci_cfg_access_lock(struct pci_dev *dev) { might_sleep(); - lock_map_acquire(&dev->cfg_access_lock); - raw_spin_lock_irq(&pci_lock); if (dev->block_cfg_access) pci_wait_cfg(dev); @@ -345,8 +343,6 @@ void pci_cfg_access_unlock(struct pci_dev *dev) raw_spin_unlock_irqrestore(&pci_lock, flags); wake_up_all(&pci_cfg_wait); - - lock_map_release(&dev->cfg_access_lock); } EXPORT_SYMBOL_GPL(pci_cfg_access_unlock); diff --git a/drivers/pci/pci.c b/drivers/pci/pci.c index 59e0949fb079..35fb1f17a589 100644 --- a/drivers/pci/pci.c +++ b/drivers/pci/pci.c @@ -4883,7 +4883,6 @@ void __weak pcibios_reset_secondary_bus(struct pci_dev *dev) */ int pci_bridge_secondary_bus_reset(struct pci_dev *dev) { - lock_map_assert_held(&dev->cfg_access_lock); pcibios_reset_secondary_bus(dev); return pci_bridge_wait_for_secondary_bus(dev, "bus reset"); diff --git a/drivers/pci/probe.c b/drivers/pci/probe.c index 8e696e547565..5fbabb4e3425 100644 --- a/drivers/pci/probe.c +++ b/drivers/pci/probe.c @@ -2546,9 +2546,6 @@ void pci_device_add(struct pci_dev *dev, struct pci_bus *bus) dev->dev.dma_mask = &dev->dma_mask; dev->dev.dma_parms = &dev->dma_parms; dev->dev.coherent_dma_mask = 0xffffffffull; - lockdep_register_key(&dev->cfg_access_key); - lockdep_init_map(&dev->cfg_access_lock, dev_name(&dev->dev), - &dev->cfg_access_key, 0); dma_set_max_seg_size(&dev->dev, 65536); dma_set_seg_boundary(&dev->dev, 0xffffffff); diff --git a/include/linux/lockdep.h b/include/linux/lockdep.h index 5e51b0de4c4b..08b0d1d9d78b 100644 --- a/include/linux/lockdep.h +++ b/include/linux/lockdep.h @@ -297,9 +297,6 @@ extern void lock_unpin_lock(struct lockdep_map *lock, struct pin_cookie); .wait_type_inner = _wait_type, \ .lock_type = LD_LOCK_WAIT_OVERRIDE, } -#define lock_map_assert_held(l) \ - lockdep_assert(lock_is_held(l) != LOCK_STATE_NOT_HELD) - #else /* !CONFIG_LOCKDEP */ static inline void lockdep_init_task(struct task_struct *task) @@ -391,8 +388,6 @@ extern int lockdep_is_held(const void *); #define DEFINE_WAIT_OVERRIDE_MAP(_name, _wait_type) \ struct lockdep_map __maybe_unused _name = {} -#define lock_map_assert_held(l) do { (void)(l); } while (0) - #endif /* !LOCKDEP */ #ifdef CONFIG_PROVE_LOCKING diff --git a/include/linux/pci.h b/include/linux/pci.h index fb004fd4e889..cafc5ab1cbcb 100644 --- a/include/linux/pci.h +++ b/include/linux/pci.h @@ -413,8 +413,6 @@ struct pci_dev { struct resource driver_exclusive_resource; /* driver exclusive resource ranges */ bool match_driver; /* Skip attaching driver */ - struct lock_class_key cfg_access_key; - struct lockdep_map cfg_access_lock; unsigned int transparent:1; /* Subtractive decode bridge */ unsigned int io_window:1; /* Bridge has I/O window */ -- cgit v1.2.3 From f92a59f6d12e31ead999fee9585471b95a8ae8a3 Mon Sep 17 00:00:00 2001 From: Carlos Llamas Date: Wed, 15 May 2024 13:37:10 +0000 Subject: locking/atomic: scripts: fix ${atomic}_sub_and_test() kerneldoc For ${atomic}_sub_and_test() the @i parameter is the value to subtract, not add. Fix the typo in the kerneldoc template and generate the headers with this update. Fixes: ad8110706f38 ("locking/atomic: scripts: generate kerneldoc comments") Suggested-by: Mark Rutland Signed-off-by: Carlos Llamas Signed-off-by: Peter Zijlstra (Intel) Acked-by: Mark Rutland Reviewed-by: Kees Cook Cc: stable@vger.kernel.org Link: https://lkml.kernel.org/r/20240515133844.3502360-1-cmllamas@google.com --- include/linux/atomic/atomic-arch-fallback.h | 6 +++--- include/linux/atomic/atomic-instrumented.h | 8 ++++---- include/linux/atomic/atomic-long.h | 4 ++-- scripts/atomic/kerneldoc/sub_and_test | 2 +- 4 files changed, 10 insertions(+), 10 deletions(-) (limited to 'include/linux') diff --git a/include/linux/atomic/atomic-arch-fallback.h b/include/linux/atomic/atomic-arch-fallback.h index 956bcba5dbf2..2f9d36b72bd8 100644 --- a/include/linux/atomic/atomic-arch-fallback.h +++ b/include/linux/atomic/atomic-arch-fallback.h @@ -2242,7 +2242,7 @@ raw_atomic_try_cmpxchg_relaxed(atomic_t *v, int *old, int new) /** * raw_atomic_sub_and_test() - atomic subtract and test if zero with full ordering - * @i: int value to add + * @i: int value to subtract * @v: pointer to atomic_t * * Atomically updates @v to (@v - @i) with full ordering. @@ -4368,7 +4368,7 @@ raw_atomic64_try_cmpxchg_relaxed(atomic64_t *v, s64 *old, s64 new) /** * raw_atomic64_sub_and_test() - atomic subtract and test if zero with full ordering - * @i: s64 value to add + * @i: s64 value to subtract * @v: pointer to atomic64_t * * Atomically updates @v to (@v - @i) with full ordering. @@ -4690,4 +4690,4 @@ raw_atomic64_dec_if_positive(atomic64_t *v) } #endif /* _LINUX_ATOMIC_FALLBACK_H */ -// 14850c0b0db20c62fdc78ccd1d42b98b88d76331 +// b565db590afeeff0d7c9485ccbca5bb6e155749f diff --git a/include/linux/atomic/atomic-instrumented.h b/include/linux/atomic/atomic-instrumented.h index debd487fe971..9409a6ddf3e0 100644 --- a/include/linux/atomic/atomic-instrumented.h +++ b/include/linux/atomic/atomic-instrumented.h @@ -1349,7 +1349,7 @@ atomic_try_cmpxchg_relaxed(atomic_t *v, int *old, int new) /** * atomic_sub_and_test() - atomic subtract and test if zero with full ordering - * @i: int value to add + * @i: int value to subtract * @v: pointer to atomic_t * * Atomically updates @v to (@v - @i) with full ordering. @@ -2927,7 +2927,7 @@ atomic64_try_cmpxchg_relaxed(atomic64_t *v, s64 *old, s64 new) /** * atomic64_sub_and_test() - atomic subtract and test if zero with full ordering - * @i: s64 value to add + * @i: s64 value to subtract * @v: pointer to atomic64_t * * Atomically updates @v to (@v - @i) with full ordering. @@ -4505,7 +4505,7 @@ atomic_long_try_cmpxchg_relaxed(atomic_long_t *v, long *old, long new) /** * atomic_long_sub_and_test() - atomic subtract and test if zero with full ordering - * @i: long value to add + * @i: long value to subtract * @v: pointer to atomic_long_t * * Atomically updates @v to (@v - @i) with full ordering. @@ -5050,4 +5050,4 @@ atomic_long_dec_if_positive(atomic_long_t *v) #endif /* _LINUX_ATOMIC_INSTRUMENTED_H */ -// ce5b65e0f1f8a276268b667194581d24bed219d4 +// 8829b337928e9508259079d32581775ececd415b diff --git a/include/linux/atomic/atomic-long.h b/include/linux/atomic/atomic-long.h index 3ef844b3ab8a..f86b29d90877 100644 --- a/include/linux/atomic/atomic-long.h +++ b/include/linux/atomic/atomic-long.h @@ -1535,7 +1535,7 @@ raw_atomic_long_try_cmpxchg_relaxed(atomic_long_t *v, long *old, long new) /** * raw_atomic_long_sub_and_test() - atomic subtract and test if zero with full ordering - * @i: long value to add + * @i: long value to subtract * @v: pointer to atomic_long_t * * Atomically updates @v to (@v - @i) with full ordering. @@ -1809,4 +1809,4 @@ raw_atomic_long_dec_if_positive(atomic_long_t *v) } #endif /* _LINUX_ATOMIC_LONG_H */ -// 1c4a26fc77f345342953770ebe3c4d08e7ce2f9a +// eadf183c3600b8b92b91839dd3be6bcc560c752d diff --git a/scripts/atomic/kerneldoc/sub_and_test b/scripts/atomic/kerneldoc/sub_and_test index d3760f7749d4..96615e50836b 100644 --- a/scripts/atomic/kerneldoc/sub_and_test +++ b/scripts/atomic/kerneldoc/sub_and_test @@ -1,7 +1,7 @@ cat < Date: Thu, 23 May 2024 10:36:39 +0800 Subject: mm: drop the 'anon_' prefix for swap-out mTHP counters The mTHP swap related counters: 'anon_swpout' and 'anon_swpout_fallback' are confusing with an 'anon_' prefix, since the shmem can swap out non-anonymous pages. So drop the 'anon_' prefix to keep consistent with the old swap counter names. This is needed in 6.10-rcX to avoid having an inconsistent ABI out in the field. Link: https://lkml.kernel.org/r/7a8989c13299920d7589007a30065c3e2c19f0e0.1716431702.git.baolin.wang@linux.alibaba.com Fixes: d0f048ac39f6 ("mm: add per-order mTHP anon_swpout and anon_swpout_fallback counters") Fixes: 42248b9d34ea ("mm: add docs for per-order mTHP counters and transhuge_page ABI") Signed-off-by: Baolin Wang Suggested-by: "Huang, Ying" Acked-by: Barry Song Cc: David Hildenbrand Cc: Lance Yang Cc: Matthew Wilcox (Oracle) Cc: Ryan Roberts Cc: Zi Yan Signed-off-by: Andrew Morton --- Documentation/admin-guide/mm/transhuge.rst | 4 ++-- include/linux/huge_mm.h | 4 ++-- mm/huge_memory.c | 8 ++++---- mm/page_io.c | 2 +- mm/vmscan.c | 2 +- 5 files changed, 10 insertions(+), 10 deletions(-) (limited to 'include/linux') diff --git a/Documentation/admin-guide/mm/transhuge.rst b/Documentation/admin-guide/mm/transhuge.rst index 076443cc10a6..d414d3f5592a 100644 --- a/Documentation/admin-guide/mm/transhuge.rst +++ b/Documentation/admin-guide/mm/transhuge.rst @@ -467,11 +467,11 @@ anon_fault_fallback_charge instead falls back to using huge pages with lower orders or small pages even though the allocation was successful. -anon_swpout +swpout is incremented every time a huge page is swapped out in one piece without splitting. -anon_swpout_fallback +swpout_fallback is incremented if a huge page has to be split before swapout. Usually because failed to allocate some continuous swap space for the huge page. diff --git a/include/linux/huge_mm.h b/include/linux/huge_mm.h index c8d3ec116e29..8c72d3786583 100644 --- a/include/linux/huge_mm.h +++ b/include/linux/huge_mm.h @@ -269,8 +269,8 @@ enum mthp_stat_item { MTHP_STAT_ANON_FAULT_ALLOC, MTHP_STAT_ANON_FAULT_FALLBACK, MTHP_STAT_ANON_FAULT_FALLBACK_CHARGE, - MTHP_STAT_ANON_SWPOUT, - MTHP_STAT_ANON_SWPOUT_FALLBACK, + MTHP_STAT_SWPOUT, + MTHP_STAT_SWPOUT_FALLBACK, __MTHP_STAT_COUNT }; diff --git a/mm/huge_memory.c b/mm/huge_memory.c index 317de2afd371..89932fd0f62e 100644 --- a/mm/huge_memory.c +++ b/mm/huge_memory.c @@ -558,15 +558,15 @@ static struct kobj_attribute _name##_attr = __ATTR_RO(_name) DEFINE_MTHP_STAT_ATTR(anon_fault_alloc, MTHP_STAT_ANON_FAULT_ALLOC); DEFINE_MTHP_STAT_ATTR(anon_fault_fallback, MTHP_STAT_ANON_FAULT_FALLBACK); DEFINE_MTHP_STAT_ATTR(anon_fault_fallback_charge, MTHP_STAT_ANON_FAULT_FALLBACK_CHARGE); -DEFINE_MTHP_STAT_ATTR(anon_swpout, MTHP_STAT_ANON_SWPOUT); -DEFINE_MTHP_STAT_ATTR(anon_swpout_fallback, MTHP_STAT_ANON_SWPOUT_FALLBACK); +DEFINE_MTHP_STAT_ATTR(swpout, MTHP_STAT_SWPOUT); +DEFINE_MTHP_STAT_ATTR(swpout_fallback, MTHP_STAT_SWPOUT_FALLBACK); static struct attribute *stats_attrs[] = { &anon_fault_alloc_attr.attr, &anon_fault_fallback_attr.attr, &anon_fault_fallback_charge_attr.attr, - &anon_swpout_attr.attr, - &anon_swpout_fallback_attr.attr, + &swpout_attr.attr, + &swpout_fallback_attr.attr, NULL, }; diff --git a/mm/page_io.c b/mm/page_io.c index 46c603dddf04..0a150c240bf4 100644 --- a/mm/page_io.c +++ b/mm/page_io.c @@ -217,7 +217,7 @@ static inline void count_swpout_vm_event(struct folio *folio) count_memcg_folio_events(folio, THP_SWPOUT, 1); count_vm_event(THP_SWPOUT); } - count_mthp_stat(folio_order(folio), MTHP_STAT_ANON_SWPOUT); + count_mthp_stat(folio_order(folio), MTHP_STAT_SWPOUT); #endif count_vm_events(PSWPOUT, folio_nr_pages(folio)); } diff --git a/mm/vmscan.c b/mm/vmscan.c index d55e8d07ffc4..2e34de9cd0d4 100644 --- a/mm/vmscan.c +++ b/mm/vmscan.c @@ -1227,7 +1227,7 @@ retry: THP_SWPOUT_FALLBACK, 1); count_vm_event(THP_SWPOUT_FALLBACK); } - count_mthp_stat(order, MTHP_STAT_ANON_SWPOUT_FALLBACK); + count_mthp_stat(order, MTHP_STAT_SWPOUT_FALLBACK); #endif if (!add_to_swap(folio)) goto activate_locked_split; -- cgit v1.2.3 From 94d46bf17916965e918bd2f3d2eec057f7c5578d Mon Sep 17 00:00:00 2001 From: Barry Song Date: Fri, 24 May 2024 08:50:48 +1200 Subject: mm: huge_mm: fix undefined reference to `mthp_stats' for CONFIG_SYSFS=n if CONFIG_SYSFS is not enabled in config, we get the below error, All errors (new ones prefixed by >>): s390-linux-ld: mm/memory.o: in function `count_mthp_stat': >> include/linux/huge_mm.h:285:(.text+0x191c): undefined reference to `mthp_stats' s390-linux-ld: mm/huge_memory.o:(.rodata+0x10): undefined reference to `mthp_stats' vim +285 include/linux/huge_mm.h 279 280 static inline void count_mthp_stat(int order, enum mthp_stat_item item) 281 { 282 if (order <= 0 || order > PMD_ORDER) 283 return; 284 > 285 this_cpu_inc(mthp_stats.stats[order][item]); 286 } 287 Link: https://lkml.kernel.org/r/20240523210045.40444-1-21cnbao@gmail.com Fixes: ec33687c6749 ("mm: add per-order mTHP anon_fault_alloc and anon_fault_fallback counters") Reported-by: kernel test robot Closes: https://lore.kernel.org/oe-kbuild-all/202405231728.tCAogiSI-lkp@intel.com/ Signed-off-by: Barry Song Tested-by: Yujie Liu Signed-off-by: Andrew Morton --- include/linux/huge_mm.h | 6 ++++++ 1 file changed, 6 insertions(+) (limited to 'include/linux') diff --git a/include/linux/huge_mm.h b/include/linux/huge_mm.h index 8c72d3786583..2aa986a5cd1b 100644 --- a/include/linux/huge_mm.h +++ b/include/linux/huge_mm.h @@ -278,6 +278,7 @@ struct mthp_stat { unsigned long stats[ilog2(MAX_PTRS_PER_PTE) + 1][__MTHP_STAT_COUNT]; }; +#ifdef CONFIG_SYSFS DECLARE_PER_CPU(struct mthp_stat, mthp_stats); static inline void count_mthp_stat(int order, enum mthp_stat_item item) @@ -287,6 +288,11 @@ static inline void count_mthp_stat(int order, enum mthp_stat_item item) this_cpu_inc(mthp_stats.stats[order][item]); } +#else +static inline void count_mthp_stat(int order, enum mthp_stat_item item) +{ +} +#endif #define transparent_hugepage_use_zero_page() \ (transparent_hugepage_flags & \ -- cgit v1.2.3 From c2dc78b86e0821ecf9a9d0c35dba2618279a5bb6 Mon Sep 17 00:00:00 2001 From: Chengming Zhou Date: Tue, 28 May 2024 13:15:22 +0800 Subject: mm/ksm: fix ksm_zero_pages accounting We normally ksm_zero_pages++ in ksmd when page is merged with zero page, but ksm_zero_pages-- is done from page tables side, where there is no any accessing protection of ksm_zero_pages. So we can read very exceptional value of ksm_zero_pages in rare cases, such as -1, which is very confusing to users. Fix it by changing to use atomic_long_t, and the same case with the mm->ksm_zero_pages. Link: https://lkml.kernel.org/r/20240528-b4-ksm-counters-v3-2-34bb358fdc13@linux.dev Fixes: e2942062e01d ("ksm: count all zero pages placed by KSM") Fixes: 6080d19f0704 ("ksm: add ksm zero pages for each process") Signed-off-by: Chengming Zhou Acked-by: David Hildenbrand Cc: Andrea Arcangeli Cc: Hugh Dickins Cc: Ran Xiaokai Cc: Stefan Roesch Cc: xu xin Cc: Yang Yang Cc: Signed-off-by: Andrew Morton --- fs/proc/base.c | 2 +- include/linux/ksm.h | 17 ++++++++++++++--- include/linux/mm_types.h | 2 +- mm/ksm.c | 11 +++++------ 4 files changed, 21 insertions(+), 11 deletions(-) (limited to 'include/linux') diff --git a/fs/proc/base.c b/fs/proc/base.c index 18550c071d71..72a1acd03675 100644 --- a/fs/proc/base.c +++ b/fs/proc/base.c @@ -3214,7 +3214,7 @@ static int proc_pid_ksm_stat(struct seq_file *m, struct pid_namespace *ns, mm = get_task_mm(task); if (mm) { seq_printf(m, "ksm_rmap_items %lu\n", mm->ksm_rmap_items); - seq_printf(m, "ksm_zero_pages %lu\n", mm->ksm_zero_pages); + seq_printf(m, "ksm_zero_pages %ld\n", mm_ksm_zero_pages(mm)); seq_printf(m, "ksm_merging_pages %lu\n", mm->ksm_merging_pages); seq_printf(m, "ksm_process_profit %ld\n", ksm_process_profit(mm)); mmput(mm); diff --git a/include/linux/ksm.h b/include/linux/ksm.h index 52c63a9c5a9c..11690dacd986 100644 --- a/include/linux/ksm.h +++ b/include/linux/ksm.h @@ -33,16 +33,27 @@ void __ksm_exit(struct mm_struct *mm); */ #define is_ksm_zero_pte(pte) (is_zero_pfn(pte_pfn(pte)) && pte_dirty(pte)) -extern unsigned long ksm_zero_pages; +extern atomic_long_t ksm_zero_pages; + +static inline void ksm_map_zero_page(struct mm_struct *mm) +{ + atomic_long_inc(&ksm_zero_pages); + atomic_long_inc(&mm->ksm_zero_pages); +} static inline void ksm_might_unmap_zero_page(struct mm_struct *mm, pte_t pte) { if (is_ksm_zero_pte(pte)) { - ksm_zero_pages--; - mm->ksm_zero_pages--; + atomic_long_dec(&ksm_zero_pages); + atomic_long_dec(&mm->ksm_zero_pages); } } +static inline long mm_ksm_zero_pages(struct mm_struct *mm) +{ + return atomic_long_read(&mm->ksm_zero_pages); +} + static inline int ksm_fork(struct mm_struct *mm, struct mm_struct *oldmm) { if (test_bit(MMF_VM_MERGEABLE, &oldmm->flags)) diff --git a/include/linux/mm_types.h b/include/linux/mm_types.h index 24323c7d0bd4..af3a0256fa93 100644 --- a/include/linux/mm_types.h +++ b/include/linux/mm_types.h @@ -985,7 +985,7 @@ struct mm_struct { * Represent how many empty pages are merged with kernel zero * pages when enabling KSM use_zero_pages. */ - unsigned long ksm_zero_pages; + atomic_long_t ksm_zero_pages; #endif /* CONFIG_KSM */ #ifdef CONFIG_LRU_GEN_WALKS_MMU struct { diff --git a/mm/ksm.c b/mm/ksm.c index 9e99cb12d330..34c4820e0d3d 100644 --- a/mm/ksm.c +++ b/mm/ksm.c @@ -296,7 +296,7 @@ static bool ksm_use_zero_pages __read_mostly; static bool ksm_smart_scan = true; /* The number of zero pages which is placed by KSM */ -unsigned long ksm_zero_pages; +atomic_long_t ksm_zero_pages = ATOMIC_LONG_INIT(0); /* The number of pages that have been skipped due to "smart scanning" */ static unsigned long ksm_pages_skipped; @@ -1429,8 +1429,7 @@ static int replace_page(struct vm_area_struct *vma, struct page *page, * the dirty bit in zero page's PTE is set. */ newpte = pte_mkdirty(pte_mkspecial(pfn_pte(page_to_pfn(kpage), vma->vm_page_prot))); - ksm_zero_pages++; - mm->ksm_zero_pages++; + ksm_map_zero_page(mm); /* * We're replacing an anonymous page with a zero page, which is * not anonymous. We need to do proper accounting otherwise we @@ -3374,7 +3373,7 @@ static void wait_while_offlining(void) #ifdef CONFIG_PROC_FS long ksm_process_profit(struct mm_struct *mm) { - return (long)(mm->ksm_merging_pages + mm->ksm_zero_pages) * PAGE_SIZE - + return (long)(mm->ksm_merging_pages + mm_ksm_zero_pages(mm)) * PAGE_SIZE - mm->ksm_rmap_items * sizeof(struct ksm_rmap_item); } #endif /* CONFIG_PROC_FS */ @@ -3663,7 +3662,7 @@ KSM_ATTR_RO(pages_skipped); static ssize_t ksm_zero_pages_show(struct kobject *kobj, struct kobj_attribute *attr, char *buf) { - return sysfs_emit(buf, "%ld\n", ksm_zero_pages); + return sysfs_emit(buf, "%ld\n", atomic_long_read(&ksm_zero_pages)); } KSM_ATTR_RO(ksm_zero_pages); @@ -3672,7 +3671,7 @@ static ssize_t general_profit_show(struct kobject *kobj, { long general_profit; - general_profit = (ksm_pages_sharing + ksm_zero_pages) * PAGE_SIZE - + general_profit = (ksm_pages_sharing + atomic_long_read(&ksm_zero_pages)) * PAGE_SIZE - ksm_rmap_items * sizeof(struct ksm_rmap_item); return sysfs_emit(buf, "%ld\n", general_profit); -- cgit v1.2.3 From 144ba8580bcb82b2686c3d1a043299d844b9a682 Mon Sep 17 00:00:00 2001 From: Kory Maincent Date: Mon, 10 Jun 2024 10:34:26 +0200 Subject: net: pse-pd: Use EOPNOTSUPP error code instead of ENOTSUPP ENOTSUPP is not a SUSV4 error code, prefer EOPNOTSUPP as reported by checkpatch script. Fixes: 18ff0bcda6d1 ("ethtool: add interface to interact with Ethernet Power Equipment") Reviewed-by: Andrew Lunn Acked-by: Oleksij Rempel Signed-off-by: Kory Maincent Link: https://lore.kernel.org/r/20240610083426.740660-1-kory.maincent@bootlin.com Signed-off-by: Jakub Kicinski --- include/linux/pse-pd/pse.h | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-) (limited to 'include/linux') diff --git a/include/linux/pse-pd/pse.h b/include/linux/pse-pd/pse.h index 6d07c95dabb9..6eec24ffa866 100644 --- a/include/linux/pse-pd/pse.h +++ b/include/linux/pse-pd/pse.h @@ -167,14 +167,14 @@ static inline int pse_ethtool_get_status(struct pse_control *psec, struct netlink_ext_ack *extack, struct pse_control_status *status) { - return -ENOTSUPP; + return -EOPNOTSUPP; } static inline int pse_ethtool_set_config(struct pse_control *psec, struct netlink_ext_ack *extack, const struct pse_control_config *config) { - return -ENOTSUPP; + return -EOPNOTSUPP; } static inline bool pse_has_podl(struct pse_control *psec) -- cgit v1.2.3