From b3fdf9398a16f01dc013967a4ab25e99c3f4fc12 Mon Sep 17 00:00:00 2001 From: Jane Chu Date: Mon, 16 May 2022 11:21:46 -0700 Subject: x86/mce: relocate set{clear}_mce_nospec() functions Relocate the twin mce functions to arch/x86/mm/pat/set_memory.c file where they belong. While at it, fixup a function name in a comment. Reviewed-by: Christoph Hellwig Reviewed-by: Dan Williams Signed-off-by: Jane Chu Acked-by: Borislav Petkov Cc: Stephen Rothwell [sfr: gate {set,clear}_mce_nospec() by CONFIG_X86_64] Link: https://lore.kernel.org/r/165272527328.90175.8336008202048685278.stgit@dwillia2-desk3.amr.corp.intel.com Signed-off-by: Dan Williams --- include/linux/set_memory.h | 8 ++++---- 1 file changed, 4 insertions(+), 4 deletions(-) (limited to 'include/linux') diff --git a/include/linux/set_memory.h b/include/linux/set_memory.h index f36be5166c19..683a6c3f7179 100644 --- a/include/linux/set_memory.h +++ b/include/linux/set_memory.h @@ -42,14 +42,14 @@ static inline bool can_set_direct_map(void) #endif #endif /* CONFIG_ARCH_HAS_SET_DIRECT_MAP */ -#ifndef set_mce_nospec +#ifdef CONFIG_X86_64 +int set_mce_nospec(unsigned long pfn, bool unmap); +int clear_mce_nospec(unsigned long pfn); +#else static inline int set_mce_nospec(unsigned long pfn, bool unmap) { return 0; } -#endif - -#ifndef clear_mce_nospec static inline int clear_mce_nospec(unsigned long pfn) { return 0; -- cgit v1.2.3 From 5898b43af954b83c4a4ee4ab85c4dbafa395822a Mon Sep 17 00:00:00 2001 From: Jane Chu Date: Mon, 16 May 2022 11:38:10 -0700 Subject: mce: fix set_mce_nospec to always unmap the whole page The set_memory_uc() approach doesn't work well in all cases. As Dan pointed out when "The VMM unmapped the bad page from guest physical space and passed the machine check to the guest." "The guest gets virtual #MC on an access to that page. When the guest tries to do set_memory_uc() and instructs cpa_flush() to do clean caches that results in taking another fault / exception perhaps because the VMM unmapped the page from the guest." Since the driver has special knowledge to handle NP or UC, mark the poisoned page with NP and let driver handle it when it comes down to repair. Please refer to discussions here for more details. https://lore.kernel.org/all/CAPcyv4hrXPb1tASBZUg-GgdVs0OOFKXMXLiHmktg_kFi7YBMyQ@mail.gmail.com/ Now since poisoned page is marked as not-present, in order to avoid writing to a not-present page and trigger kernel Oops, also fix pmem_do_write(). Fixes: 284ce4011ba6 ("x86/memory_failure: Introduce {set, clear}_mce_nospec()") Reviewed-by: Christoph Hellwig Reviewed-by: Dan Williams Signed-off-by: Jane Chu Acked-by: Tony Luck Link: https://lore.kernel.org/r/165272615484.103830.2563950688772226611.stgit@dwillia2-desk3.amr.corp.intel.com Signed-off-by: Dan Williams --- include/linux/set_memory.h | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-) (limited to 'include/linux') diff --git a/include/linux/set_memory.h b/include/linux/set_memory.h index 683a6c3f7179..369769ce7399 100644 --- a/include/linux/set_memory.h +++ b/include/linux/set_memory.h @@ -43,10 +43,10 @@ static inline bool can_set_direct_map(void) #endif /* CONFIG_ARCH_HAS_SET_DIRECT_MAP */ #ifdef CONFIG_X86_64 -int set_mce_nospec(unsigned long pfn, bool unmap); +int set_mce_nospec(unsigned long pfn); int clear_mce_nospec(unsigned long pfn); #else -static inline int set_mce_nospec(unsigned long pfn, bool unmap) +static inline int set_mce_nospec(unsigned long pfn) { return 0; } -- cgit v1.2.3 From e511c4a3d2a1f64aafc1f5df37a2ffcf7ef91b55 Mon Sep 17 00:00:00 2001 From: Jane Chu Date: Fri, 13 May 2022 15:10:58 -0700 Subject: dax: introduce DAX_RECOVERY_WRITE dax access mode Up till now, dax_direct_access() is used implicitly for normal access, but for the purpose of recovery write, dax range with poison is requested. To make the interface clear, introduce enum dax_access_mode { DAX_ACCESS, DAX_RECOVERY_WRITE, } where DAX_ACCESS is used for normal dax access, and DAX_RECOVERY_WRITE is used for dax recovery write. Suggested-by: Dan Williams Signed-off-by: Jane Chu Reviewed-by: Christoph Hellwig Cc: Mike Snitzer Reviewed-by: Vivek Goyal Link: https://lore.kernel.org/r/165247982851.52965.11024212198889762949.stgit@dwillia2-desk3.amr.corp.intel.com Signed-off-by: Dan Williams --- include/linux/dax.h | 9 +++++++-- include/linux/device-mapper.h | 4 +++- 2 files changed, 10 insertions(+), 3 deletions(-) (limited to 'include/linux') diff --git a/include/linux/dax.h b/include/linux/dax.h index 9fc5f99a0ae2..3f1339bce3c0 100644 --- a/include/linux/dax.h +++ b/include/linux/dax.h @@ -14,6 +14,11 @@ struct iomap_ops; struct iomap_iter; struct iomap; +enum dax_access_mode { + DAX_ACCESS, + DAX_RECOVERY_WRITE, +}; + struct dax_operations { /* * direct_access: translate a device-relative @@ -21,7 +26,7 @@ struct dax_operations { * number of pages available for DAX at that pfn. */ long (*direct_access)(struct dax_device *, pgoff_t, long, - void **, pfn_t *); + enum dax_access_mode, void **, pfn_t *); /* * Validate whether this device is usable as an fsdax backing * device. @@ -178,7 +183,7 @@ static inline void dax_read_unlock(int id) bool dax_alive(struct dax_device *dax_dev); void *dax_get_private(struct dax_device *dax_dev); long dax_direct_access(struct dax_device *dax_dev, pgoff_t pgoff, long nr_pages, - void **kaddr, pfn_t *pfn); + enum dax_access_mode mode, void **kaddr, pfn_t *pfn); size_t dax_copy_from_iter(struct dax_device *dax_dev, pgoff_t pgoff, void *addr, size_t bytes, struct iov_iter *i); size_t dax_copy_to_iter(struct dax_device *dax_dev, pgoff_t pgoff, void *addr, diff --git a/include/linux/device-mapper.h b/include/linux/device-mapper.h index c2a3758c4aaa..acdedda0d12b 100644 --- a/include/linux/device-mapper.h +++ b/include/linux/device-mapper.h @@ -20,6 +20,7 @@ struct dm_table; struct dm_report_zones_args; struct mapped_device; struct bio_vec; +enum dax_access_mode; /* * Type of table, mapped_device's mempool and request_queue @@ -146,7 +147,8 @@ typedef int (*dm_busy_fn) (struct dm_target *ti); * >= 0 : the number of bytes accessible at the address */ typedef long (*dm_dax_direct_access_fn) (struct dm_target *ti, pgoff_t pgoff, - long nr_pages, void **kaddr, pfn_t *pfn); + long nr_pages, enum dax_access_mode node, void **kaddr, + pfn_t *pfn); typedef int (*dm_dax_zero_page_range_fn)(struct dm_target *ti, pgoff_t pgoff, size_t nr_pages); -- cgit v1.2.3 From 047218ec904da19c45c4a70274fc3f818a1fcba1 Mon Sep 17 00:00:00 2001 From: Jane Chu Date: Fri, 22 Apr 2022 16:45:06 -0600 Subject: dax: add .recovery_write dax_operation Introduce dax_recovery_write() operation. The function is used to recover a dax range that contains poison. Typical use case is when a user process receives a SIGBUS with si_code BUS_MCEERR_AR indicating poison(s) in a dax range, in response, the user process issues a pwrite() to the page-aligned dax range, thus clears the poison and puts valid data in the range. Reviewed-by: Christoph Hellwig Signed-off-by: Jane Chu Link: https://lore.kernel.org/r/20220422224508.440670-6-jane.chu@oracle.com Signed-off-by: Dan Williams --- include/linux/dax.h | 13 +++++++++++++ include/linux/device-mapper.h | 9 +++++++++ 2 files changed, 22 insertions(+) (limited to 'include/linux') diff --git a/include/linux/dax.h b/include/linux/dax.h index 3f1339bce3c0..e7b81634c52a 100644 --- a/include/linux/dax.h +++ b/include/linux/dax.h @@ -35,6 +35,12 @@ struct dax_operations { sector_t, sector_t); /* zero_page_range: required operation. Zero page range */ int (*zero_page_range)(struct dax_device *, pgoff_t, size_t); + /* + * recovery_write: recover a poisoned range by DAX device driver + * capable of clearing poison. + */ + size_t (*recovery_write)(struct dax_device *dax_dev, pgoff_t pgoff, + void *addr, size_t bytes, struct iov_iter *iter); }; #if IS_ENABLED(CONFIG_DAX) @@ -45,6 +51,8 @@ void dax_write_cache(struct dax_device *dax_dev, bool wc); bool dax_write_cache_enabled(struct dax_device *dax_dev); bool dax_synchronous(struct dax_device *dax_dev); void set_dax_synchronous(struct dax_device *dax_dev); +size_t dax_recovery_write(struct dax_device *dax_dev, pgoff_t pgoff, + void *addr, size_t bytes, struct iov_iter *i); /* * Check if given mapping is supported by the file / underlying device. */ @@ -92,6 +100,11 @@ static inline bool daxdev_mapping_supported(struct vm_area_struct *vma, { return !(vma->vm_flags & VM_SYNC); } +static inline size_t dax_recovery_write(struct dax_device *dax_dev, + pgoff_t pgoff, void *addr, size_t bytes, struct iov_iter *i) +{ + return 0; +} #endif void set_dax_nocache(struct dax_device *dax_dev); diff --git a/include/linux/device-mapper.h b/include/linux/device-mapper.h index acdedda0d12b..47a01c7cffdf 100644 --- a/include/linux/device-mapper.h +++ b/include/linux/device-mapper.h @@ -152,6 +152,14 @@ typedef long (*dm_dax_direct_access_fn) (struct dm_target *ti, pgoff_t pgoff, typedef int (*dm_dax_zero_page_range_fn)(struct dm_target *ti, pgoff_t pgoff, size_t nr_pages); +/* + * Returns: + * != 0 : number of bytes transferred + * 0 : recovery write failed + */ +typedef size_t (*dm_dax_recovery_write_fn)(struct dm_target *ti, pgoff_t pgoff, + void *addr, size_t bytes, struct iov_iter *i); + void dm_error(const char *message); struct dm_dev { @@ -201,6 +209,7 @@ struct target_type { dm_io_hints_fn io_hints; dm_dax_direct_access_fn direct_access; dm_dax_zero_page_range_fn dax_zero_page_range; + dm_dax_recovery_write_fn dax_recovery_write; /* For internal device-mapper use. */ struct list_head list; -- cgit v1.2.3