diff options
Diffstat (limited to 'include')
43 files changed, 837 insertions, 344 deletions
diff --git a/include/asm-generic/bitops/instrumented-lock.h b/include/asm-generic/bitops/instrumented-lock.h index eb64bd4f11f3..542d3727ee4e 100644 --- a/include/asm-generic/bitops/instrumented-lock.h +++ b/include/asm-generic/bitops/instrumented-lock.h @@ -58,27 +58,25 @@ static inline bool test_and_set_bit_lock(long nr, volatile unsigned long *addr) return arch_test_and_set_bit_lock(nr, addr); } -#if defined(arch_clear_bit_unlock_is_negative_byte) /** - * clear_bit_unlock_is_negative_byte - Clear a bit in memory and test if bottom - * byte is negative, for unlock. - * @nr: the bit to clear - * @addr: the address to start counting from + * xor_unlock_is_negative_byte - XOR a single byte in memory and test if + * it is negative, for unlock. + * @mask: Change the bits which are set in this mask. + * @addr: The address of the word containing the byte to change. * + * Changes some of bits 0-6 in the word pointed to by @addr. * This operation is atomic and provides release barrier semantics. + * Used to optimise some folio operations which are commonly paired + * with an unlock or end of writeback. Bit 7 is used as PG_waiters to + * indicate whether anybody is waiting for the unlock. * - * This is a bit of a one-trick-pony for the filemap code, which clears - * PG_locked and tests PG_waiters, + * Return: Whether the top bit of the byte is set. */ -static inline bool -clear_bit_unlock_is_negative_byte(long nr, volatile unsigned long *addr) +static inline bool xor_unlock_is_negative_byte(unsigned long mask, + volatile unsigned long *addr) { kcsan_release(); - instrument_atomic_write(addr + BIT_WORD(nr), sizeof(long)); - return arch_clear_bit_unlock_is_negative_byte(nr, addr); + instrument_atomic_write(addr, sizeof(long)); + return arch_xor_unlock_is_negative_byte(mask, addr); } -/* Let everybody know we have it. */ -#define clear_bit_unlock_is_negative_byte clear_bit_unlock_is_negative_byte -#endif - #endif /* _ASM_GENERIC_BITOPS_INSTRUMENTED_LOCK_H */ diff --git a/include/asm-generic/bitops/lock.h b/include/asm-generic/bitops/lock.h index 40913516e654..14d4ec8c5152 100644 --- a/include/asm-generic/bitops/lock.h +++ b/include/asm-generic/bitops/lock.h @@ -66,27 +66,15 @@ arch___clear_bit_unlock(unsigned int nr, volatile unsigned long *p) raw_atomic_long_set_release((atomic_long_t *)p, old); } -/** - * arch_clear_bit_unlock_is_negative_byte - Clear a bit in memory and test if bottom - * byte is negative, for unlock. - * @nr: the bit to clear - * @addr: the address to start counting from - * - * This is a bit of a one-trick-pony for the filemap code, which clears - * PG_locked and tests PG_waiters, - */ -#ifndef arch_clear_bit_unlock_is_negative_byte -static inline bool arch_clear_bit_unlock_is_negative_byte(unsigned int nr, - volatile unsigned long *p) +#ifndef arch_xor_unlock_is_negative_byte +static inline bool arch_xor_unlock_is_negative_byte(unsigned long mask, + volatile unsigned long *p) { long old; - unsigned long mask = BIT_MASK(nr); - p += BIT_WORD(nr); - old = raw_atomic_long_fetch_andnot_release(mask, (atomic_long_t *)p); + old = raw_atomic_long_fetch_xor_release(mask, (atomic_long_t *)p); return !!(old & BIT(7)); } -#define arch_clear_bit_unlock_is_negative_byte arch_clear_bit_unlock_is_negative_byte #endif #include <asm-generic/bitops/instrumented-lock.h> diff --git a/include/asm-generic/pgalloc.h b/include/asm-generic/pgalloc.h index c75d4a753849..879e5f8aa5e9 100644 --- a/include/asm-generic/pgalloc.h +++ b/include/asm-generic/pgalloc.h @@ -169,6 +169,8 @@ static inline pud_t *__pud_alloc_one(struct mm_struct *mm, unsigned long addr) ptdesc = pagetable_alloc(gfp, 0); if (!ptdesc) return NULL; + + pagetable_pud_ctor(ptdesc); return ptdesc_address(ptdesc); } @@ -190,8 +192,11 @@ static inline pud_t *pud_alloc_one(struct mm_struct *mm, unsigned long addr) static inline void __pud_free(struct mm_struct *mm, pud_t *pud) { + struct ptdesc *ptdesc = virt_to_ptdesc(pud); + BUG_ON((unsigned long)pud & (PAGE_SIZE-1)); - pagetable_free(virt_to_ptdesc(pud)); + pagetable_pud_dtor(ptdesc); + pagetable_free(ptdesc); } #ifndef __HAVE_ARCH_PUD_FREE diff --git a/include/linux/bootmem_info.h b/include/linux/bootmem_info.h index e1a3c9c9754c..cffa38a73618 100644 --- a/include/linux/bootmem_info.h +++ b/include/linux/bootmem_info.h @@ -60,7 +60,7 @@ static inline void get_page_bootmem(unsigned long info, struct page *page, static inline void free_bootmem_page(struct page *page) { - kmemleak_free_part(page_to_virt(page), PAGE_SIZE); + kmemleak_free_part_phys(PFN_PHYS(page_to_pfn(page)), PAGE_SIZE); free_reserved_page(page); } #endif diff --git a/include/linux/buffer_head.h b/include/linux/buffer_head.h index 44e9de51eedf..5f23ee599889 100644 --- a/include/linux/buffer_head.h +++ b/include/linux/buffer_head.h @@ -198,13 +198,11 @@ void touch_buffer(struct buffer_head *bh); void folio_set_bh(struct buffer_head *bh, struct folio *folio, unsigned long offset); struct buffer_head *folio_alloc_buffers(struct folio *folio, unsigned long size, - bool retry); + gfp_t gfp); struct buffer_head *alloc_page_buffers(struct page *page, unsigned long size, bool retry); -void create_empty_buffers(struct page *, unsigned long, - unsigned long b_state); -void folio_create_empty_buffers(struct folio *folio, unsigned long blocksize, - unsigned long b_state); +struct buffer_head *create_empty_buffers(struct folio *folio, + unsigned long blocksize, unsigned long b_state); void end_buffer_read_sync(struct buffer_head *bh, int uptodate); void end_buffer_write_sync(struct buffer_head *bh, int uptodate); void end_buffer_async_write(struct buffer_head *bh, int uptodate); @@ -227,8 +225,8 @@ void __wait_on_buffer(struct buffer_head *); wait_queue_head_t *bh_waitq_head(struct buffer_head *bh); struct buffer_head *__find_get_block(struct block_device *bdev, sector_t block, unsigned size); -struct buffer_head *__getblk_gfp(struct block_device *bdev, sector_t block, - unsigned size, gfp_t gfp); +struct buffer_head *bdev_getblk(struct block_device *bdev, sector_t block, + unsigned size, gfp_t gfp); void __brelse(struct buffer_head *); void __bforget(struct buffer_head *); void __breadahead(struct block_device *, sector_t block, unsigned int size); @@ -338,17 +336,38 @@ sb_breadahead(struct super_block *sb, sector_t block) __breadahead(sb->s_bdev, block, sb->s_blocksize); } -static inline struct buffer_head * -sb_getblk(struct super_block *sb, sector_t block) +static inline struct buffer_head *getblk_unmovable(struct block_device *bdev, + sector_t block, unsigned size) { - return __getblk_gfp(sb->s_bdev, block, sb->s_blocksize, __GFP_MOVABLE); + gfp_t gfp; + + gfp = mapping_gfp_constraint(bdev->bd_inode->i_mapping, ~__GFP_FS); + gfp |= __GFP_NOFAIL; + + return bdev_getblk(bdev, block, size, gfp); } +static inline struct buffer_head *__getblk(struct block_device *bdev, + sector_t block, unsigned size) +{ + gfp_t gfp; -static inline struct buffer_head * -sb_getblk_gfp(struct super_block *sb, sector_t block, gfp_t gfp) + gfp = mapping_gfp_constraint(bdev->bd_inode->i_mapping, ~__GFP_FS); + gfp |= __GFP_MOVABLE | __GFP_NOFAIL; + + return bdev_getblk(bdev, block, size, gfp); +} + +static inline struct buffer_head *sb_getblk(struct super_block *sb, + sector_t block) { - return __getblk_gfp(sb->s_bdev, block, sb->s_blocksize, gfp); + return __getblk(sb->s_bdev, block, sb->s_blocksize); +} + +static inline struct buffer_head *sb_getblk_gfp(struct super_block *sb, + sector_t block, gfp_t gfp) +{ + return bdev_getblk(sb->s_bdev, block, sb->s_blocksize, gfp); } static inline struct buffer_head * @@ -385,20 +404,6 @@ static inline void lock_buffer(struct buffer_head *bh) __lock_buffer(bh); } -static inline struct buffer_head *getblk_unmovable(struct block_device *bdev, - sector_t block, - unsigned size) -{ - return __getblk_gfp(bdev, block, size, 0); -} - -static inline struct buffer_head *__getblk(struct block_device *bdev, - sector_t block, - unsigned size) -{ - return __getblk_gfp(bdev, block, size, __GFP_MOVABLE); -} - static inline void bh_readahead(struct buffer_head *bh, blk_opf_t op_flags) { if (!buffer_uptodate(bh) && trylock_buffer(bh)) { @@ -450,6 +455,28 @@ __bread(struct block_device *bdev, sector_t block, unsigned size) return __bread_gfp(bdev, block, size, __GFP_MOVABLE); } +/** + * get_nth_bh - Get a reference on the n'th buffer after this one. + * @bh: The buffer to start counting from. + * @count: How many buffers to skip. + * + * This is primarily useful for finding the nth buffer in a folio; in + * that case you pass the head buffer and the byte offset in the folio + * divided by the block size. It can be used for other purposes, but + * it will wrap at the end of the folio rather than returning NULL or + * proceeding to the next folio for you. + * + * Return: The requested buffer with an elevated refcount. + */ +static inline __must_check +struct buffer_head *get_nth_bh(struct buffer_head *bh, unsigned int count) +{ + while (count--) + bh = bh->b_this_page; + get_bh(bh); + return bh; +} + bool block_dirty_folio(struct address_space *mapping, struct folio *folio); #ifdef CONFIG_BUFFER_HEAD diff --git a/include/linux/cacheinfo.h b/include/linux/cacheinfo.h index a5cfd44fab45..d504eb4b49ab 100644 --- a/include/linux/cacheinfo.h +++ b/include/linux/cacheinfo.h @@ -73,6 +73,7 @@ struct cacheinfo { struct cpu_cacheinfo { struct cacheinfo *info_list; + unsigned int per_cpu_data_slice_size; unsigned int num_levels; unsigned int num_leaves; bool cpu_map_populated; diff --git a/include/linux/cgroup-defs.h b/include/linux/cgroup-defs.h index 265da00a1a8b..4a6b6b77ccb6 100644 --- a/include/linux/cgroup-defs.h +++ b/include/linux/cgroup-defs.h @@ -115,6 +115,11 @@ enum { * Enable recursive subtree protection */ CGRP_ROOT_MEMORY_RECURSIVE_PROT = (1 << 18), + + /* + * Enable hugetlb accounting for the memory controller. + */ + CGRP_ROOT_MEMORY_HUGETLB_ACCOUNTING = (1 << 19), }; /* cftype->flags */ diff --git a/include/linux/damon.h b/include/linux/damon.h index ae2664d1d5f1..ab2f17d9926b 100644 --- a/include/linux/damon.h +++ b/include/linux/damon.h @@ -40,9 +40,24 @@ struct damon_addr_range { * @ar: The address range of the region. * @sampling_addr: Address of the sample for the next access check. * @nr_accesses: Access frequency of this region. + * @nr_accesses_bp: @nr_accesses in basis point (0.01%) that updated for + * each sampling interval. * @list: List head for siblings. * @age: Age of this region. * + * @nr_accesses is reset to zero for every &damon_attrs->aggr_interval and be + * increased for every &damon_attrs->sample_interval if an access to the region + * during the last sampling interval is found. The update of this field should + * not be done with direct access but with the helper function, + * damon_update_region_access_rate(). + * + * @nr_accesses_bp is another representation of @nr_accesses in basis point + * (1 in 10,000) that updated for every &damon_attrs->sample_interval in a + * manner similar to moving sum. By the algorithm, this value becomes + * @nr_accesses * 10000 for every &struct damon_attrs->aggr_interval. This can + * be used when the aggregation interval is too huge and therefore cannot wait + * for it before getting the access monitoring results. + * * @age is initially zero, increased for each aggregation interval, and reset * to zero again if the access frequency is significantly changed. If two * regions are merged into a new region, both @nr_accesses and @age of the new @@ -52,6 +67,7 @@ struct damon_region { struct damon_addr_range ar; unsigned long sampling_addr; unsigned int nr_accesses; + unsigned int nr_accesses_bp; struct list_head list; unsigned int age; @@ -298,24 +314,24 @@ struct damos_access_pattern { * struct damos - Represents a Data Access Monitoring-based Operation Scheme. * @pattern: Access pattern of target regions. * @action: &damo_action to be applied to the target regions. + * @apply_interval_us: The time between applying the @action. * @quota: Control the aggressiveness of this scheme. * @wmarks: Watermarks for automated (in)activation of this scheme. * @filters: Additional set of &struct damos_filter for &action. * @stat: Statistics of this scheme. * @list: List head for siblings. * - * For each aggregation interval, DAMON finds regions which fit in the + * For each @apply_interval_us, DAMON finds regions which fit in the * &pattern and applies &action to those. To avoid consuming too much * CPU time or IO resources for the &action, "a is used. * + * If @apply_interval_us is zero, &damon_attrs->aggr_interval is used instead. + * * To do the work only when needed, schemes can be activated for specific * system situations using &wmarks. If all schemes that registered to the * monitoring context are inactive, DAMON stops monitoring either, and just * repeatedly checks the watermarks. * - * If all schemes that registered to a &struct damon_ctx are inactive, DAMON - * stops monitoring and just repeatedly checks the watermarks. - * * Before applying the &action to a memory region, &struct damon_operations * implementation could check pages of the region and skip &action to respect * &filters @@ -327,6 +343,14 @@ struct damos_access_pattern { struct damos { struct damos_access_pattern pattern; enum damos_action action; + unsigned long apply_interval_us; +/* private: internal use only */ + /* + * number of sample intervals that should be passed before applying + * @action + */ + unsigned long next_apply_sis; +/* public: */ struct damos_quota quota; struct damos_watermarks wmarks; struct list_head filters; @@ -472,13 +496,14 @@ struct damon_callback { * regions. * * For each @sample_interval, DAMON checks whether each region is accessed or - * not. It aggregates and keeps the access information (number of accesses to - * each region) for @aggr_interval time. DAMON also checks whether the target - * memory regions need update (e.g., by ``mmap()`` calls from the application, - * in case of virtual memory monitoring) and applies the changes for each - * @ops_update_interval. All time intervals are in micro-seconds. - * Please refer to &struct damon_operations and &struct damon_callback for more - * detail. + * not during the last @sample_interval. If such access is found, DAMON + * aggregates the information by increasing &damon_region->nr_accesses for + * @aggr_interval time. For each @aggr_interval, the count is reset. DAMON + * also checks whether the target memory regions need update (e.g., by + * ``mmap()`` calls from the application, in case of virtual memory monitoring) + * and applies the changes for each @ops_update_interval. All time intervals + * are in micro-seconds. Please refer to &struct damon_operations and &struct + * damon_callback for more detail. */ struct damon_attrs { unsigned long sample_interval; @@ -522,8 +547,18 @@ struct damon_ctx { struct damon_attrs attrs; /* private: internal use only */ - struct timespec64 last_aggregation; - struct timespec64 last_ops_update; + /* number of sample intervals that passed since this context started */ + unsigned long passed_sample_intervals; + /* + * number of sample intervals that should be passed before next + * aggregation + */ + unsigned long next_aggregation_sis; + /* + * number of sample intervals that should be passed before next ops + * update + */ + unsigned long next_ops_update_sis; /* public: */ struct task_struct *kdamond; @@ -608,6 +643,8 @@ void damon_add_region(struct damon_region *r, struct damon_target *t); void damon_destroy_region(struct damon_region *r, struct damon_target *t); int damon_set_regions(struct damon_target *t, struct damon_addr_range *ranges, unsigned int nr_ranges); +void damon_update_region_access_rate(struct damon_region *r, bool accessed, + struct damon_attrs *attrs); struct damos_filter *damos_new_filter(enum damos_filter_type type, bool matching); @@ -615,7 +652,9 @@ void damos_add_filter(struct damos *s, struct damos_filter *f); void damos_destroy_filter(struct damos_filter *f); struct damos *damon_new_scheme(struct damos_access_pattern *pattern, - enum damos_action action, struct damos_quota *quota, + enum damos_action action, + unsigned long apply_interval_us, + struct damos_quota *quota, struct damos_watermarks *wmarks); void damon_add_scheme(struct damon_ctx *ctx, struct damos *s); void damon_destroy_scheme(struct damos *s); @@ -642,6 +681,13 @@ static inline bool damon_target_has_pid(const struct damon_ctx *ctx) return ctx->ops.id == DAMON_OPS_VADDR || ctx->ops.id == DAMON_OPS_FVADDR; } +static inline unsigned int damon_max_nr_accesses(const struct damon_attrs *attrs) +{ + /* {aggr,sample}_interval are unsigned long, hence could overflow */ + return min(attrs->aggr_interval / attrs->sample_interval, + (unsigned long)UINT_MAX); +} + int damon_start(struct damon_ctx **ctxs, int nr_ctxs, bool exclusive); int damon_stop(struct damon_ctx **ctxs, int nr_ctxs); diff --git a/include/linux/dax.h b/include/linux/dax.h index 22cd9902345d..b463502b16e1 100644 --- a/include/linux/dax.h +++ b/include/linux/dax.h @@ -159,8 +159,8 @@ int dax_writeback_mapping_range(struct address_space *mapping, struct page *dax_layout_busy_page(struct address_space *mapping); struct page *dax_layout_busy_page_range(struct address_space *mapping, loff_t start, loff_t end); -dax_entry_t dax_lock_page(struct page *page); -void dax_unlock_page(struct page *page, dax_entry_t cookie); +dax_entry_t dax_lock_folio(struct folio *folio); +void dax_unlock_folio(struct folio *folio, dax_entry_t cookie); dax_entry_t dax_lock_mapping_entry(struct address_space *mapping, unsigned long index, struct page **page); void dax_unlock_mapping_entry(struct address_space *mapping, @@ -182,14 +182,14 @@ static inline int dax_writeback_mapping_range(struct address_space *mapping, return -EOPNOTSUPP; } -static inline dax_entry_t dax_lock_page(struct page *page) +static inline dax_entry_t dax_lock_folio(struct folio *folio) { - if (IS_DAX(page->mapping->host)) + if (IS_DAX(folio->mapping->host)) return ~0UL; return 0; } -static inline void dax_unlock_page(struct page *page, dax_entry_t cookie) +static inline void dax_unlock_folio(struct folio *folio, dax_entry_t cookie) { } diff --git a/include/linux/fs.h b/include/linux/fs.h index c27c324ba58a..98b7a7a8c42e 100644 --- a/include/linux/fs.h +++ b/include/linux/fs.h @@ -454,7 +454,7 @@ extern const struct address_space_operations empty_aops; * It is also used to block modification of page cache contents through * memory mappings. * @gfp_mask: Memory allocation flags to use for allocating pages. - * @i_mmap_writable: Number of VM_SHARED mappings. + * @i_mmap_writable: Number of VM_SHARED, VM_MAYWRITE mappings. * @nr_thps: Number of THPs in the pagecache (non-shmem only). * @i_mmap: Tree of private and shared mappings. * @i_mmap_rwsem: Protects @i_mmap and @i_mmap_writable. @@ -557,7 +557,7 @@ static inline int mapping_mapped(struct address_space *mapping) /* * Might pages of this file have been modified in userspace? - * Note that i_mmap_writable counts all VM_SHARED vmas: do_mmap + * Note that i_mmap_writable counts all VM_SHARED, VM_MAYWRITE vmas: do_mmap * marks vma as VM_SHARED if it is shared, and the file was opened for * writing i.e. vma may be mprotected writable even if now readonly. * @@ -1270,7 +1270,7 @@ struct super_block { const struct dentry_operations *s_d_op; /* default d_op for dentries */ - struct shrinker s_shrink; /* per-sb shrinker handle */ + struct shrinker *s_shrink; /* per-sb shrinker handle */ /* Number of inodes with nlink == 0 but still referenced */ atomic_long_t s_remove_count; diff --git a/include/linux/gfp.h b/include/linux/gfp.h index 665f06675c83..de292a007138 100644 --- a/include/linux/gfp.h +++ b/include/linux/gfp.h @@ -8,6 +8,7 @@ #include <linux/topology.h> struct vm_area_struct; +struct mempolicy; /* Convert GFP flags to their corresponding migrate type */ #define GFP_MOVABLE_MASK (__GFP_RECLAIMABLE|__GFP_MOVABLE) @@ -262,7 +263,9 @@ static inline struct page *alloc_pages_node(int nid, gfp_t gfp_mask, #ifdef CONFIG_NUMA struct page *alloc_pages(gfp_t gfp, unsigned int order); -struct folio *folio_alloc(gfp_t gfp, unsigned order); +struct page *alloc_pages_mpol(gfp_t gfp, unsigned int order, + struct mempolicy *mpol, pgoff_t ilx, int nid); +struct folio *folio_alloc(gfp_t gfp, unsigned int order); struct folio *vma_alloc_folio(gfp_t gfp, int order, struct vm_area_struct *vma, unsigned long addr, bool hugepage); #else @@ -270,6 +273,11 @@ static inline struct page *alloc_pages(gfp_t gfp_mask, unsigned int order) { return alloc_pages_node(numa_node_id(), gfp_mask, order); } +static inline struct page *alloc_pages_mpol(gfp_t gfp, unsigned int order, + struct mempolicy *mpol, pgoff_t ilx, int nid) +{ + return alloc_pages(gfp, order); +} static inline struct folio *folio_alloc(gfp_t gfp, unsigned int order) { return __folio_alloc_node(gfp, order, numa_node_id()); @@ -320,11 +328,13 @@ extern void page_frag_free(void *addr); #define free_page(addr) free_pages((addr), 0) void page_alloc_init_cpuhp(void); +int decay_pcp_high(struct zone *zone, struct per_cpu_pages *pcp); void drain_zone_pages(struct zone *zone, struct per_cpu_pages *pcp); void drain_all_pages(struct zone *zone); void drain_local_pages(struct zone *zone); void page_alloc_init_late(void); +void setup_pcp_cacheinfo(void); /* * gfp_allowed_mask is set to GFP_BOOT_MASK during early boot to restrict what diff --git a/include/linux/hugetlb.h b/include/linux/hugetlb.h index 47d25a5e1933..d3acecc5db4b 100644 --- a/include/linux/hugetlb.h +++ b/include/linux/hugetlb.h @@ -30,7 +30,7 @@ void free_huge_folio(struct folio *folio); #ifdef CONFIG_HUGETLB_PAGE -#include <linux/mempolicy.h> +#include <linux/pagemap.h> #include <linux/shm.h> #include <asm/tlbflush.h> @@ -280,6 +280,7 @@ long hugetlb_change_protection(struct vm_area_struct *vma, unsigned long cp_flags); bool is_hugetlb_entry_migration(pte_t pte); +bool is_hugetlb_entry_hwpoisoned(pte_t pte); void hugetlb_unshare_all_pmds(struct vm_area_struct *vma); #else /* !CONFIG_HUGETLB_PAGE */ @@ -544,7 +545,6 @@ static inline struct hugetlbfs_sb_info *HUGETLBFS_SB(struct super_block *sb) } struct hugetlbfs_inode_info { - struct shared_policy policy; struct inode vfs_inode; unsigned int seals; }; @@ -748,8 +748,6 @@ struct folio *alloc_hugetlb_folio(struct vm_area_struct *vma, unsigned long addr, int avoid_reserve); struct folio *alloc_hugetlb_folio_nodemask(struct hstate *h, int preferred_nid, nodemask_t *nmask, gfp_t gfp_mask); -struct folio *alloc_hugetlb_folio_vma(struct hstate *h, struct vm_area_struct *vma, - unsigned long address); int hugetlb_add_to_page_cache(struct folio *folio, struct address_space *mapping, pgoff_t idx); void restore_reserve_on_error(struct hstate *h, struct vm_area_struct *vma, @@ -844,6 +842,12 @@ static inline unsigned int blocks_per_huge_page(struct hstate *h) return huge_page_size(h) / 512; } +static inline struct folio *filemap_lock_hugetlb_folio(struct hstate *h, + struct address_space *mapping, pgoff_t idx) +{ + return filemap_lock_folio(mapping, idx << huge_page_order(h)); +} + #include <asm/hugetlb.h> #ifndef is_hugepage_only_range @@ -1040,6 +1044,12 @@ static inline struct hugepage_subpool *hugetlb_folio_subpool(struct folio *folio return NULL; } +static inline struct folio *filemap_lock_hugetlb_folio(struct hstate *h, + struct address_space *mapping, pgoff_t idx) +{ + return NULL; +} + static inline int isolate_or_dissolve_huge_page(struct page *page, struct list_head *list) { @@ -1060,13 +1070,6 @@ alloc_hugetlb_folio_nodemask(struct hstate *h, int preferred_nid, return NULL; } -static inline struct folio *alloc_hugetlb_folio_vma(struct hstate *h, - struct vm_area_struct *vma, - unsigned long address) -{ - return NULL; -} - static inline int __alloc_bootmem_huge_page(struct hstate *h) { return 0; diff --git a/include/linux/hugetlb_cgroup.h b/include/linux/hugetlb_cgroup.h index 3d82d91f49ac..e5d64b8b59c2 100644 --- a/include/linux/hugetlb_cgroup.h +++ b/include/linux/hugetlb_cgroup.h @@ -22,13 +22,6 @@ struct resv_map; struct file_region; #ifdef CONFIG_CGROUP_HUGETLB -/* - * Minimum page order trackable by hugetlb cgroup. - * At least 3 pages are necessary for all the tracking information. - * The second tail page contains all of the hugetlb-specific fields. - */ -#define HUGETLB_CGROUP_MIN_ORDER order_base_2(__NR_USED_SUBPAGE) - enum hugetlb_memory_event { HUGETLB_MAX, HUGETLB_NR_MEMORY_EVENTS, @@ -68,8 +61,6 @@ static inline struct hugetlb_cgroup * __hugetlb_cgroup_from_folio(struct folio *folio, bool rsvd) { VM_BUG_ON_FOLIO(!folio_test_hugetlb(folio), folio); - if (folio_order(folio) < HUGETLB_CGROUP_MIN_ORDER) - return NULL; if (rsvd) return folio->_hugetlb_cgroup_rsvd; else @@ -91,8 +82,6 @@ static inline void __set_hugetlb_cgroup(struct folio *folio, struct hugetlb_cgroup *h_cg, bool rsvd) { VM_BUG_ON_FOLIO(!folio_test_hugetlb(folio), folio); - if (folio_order(folio) < HUGETLB_CGROUP_MIN_ORDER) - return; if (rsvd) folio->_hugetlb_cgroup_rsvd = h_cg; else diff --git a/include/linux/jbd2.h b/include/linux/jbd2.h index 52772c826c86..6dcbb4eb80fb 100644 --- a/include/linux/jbd2.h +++ b/include/linux/jbd2.h @@ -886,7 +886,7 @@ struct journal_s * Journal head shrinker, reclaim buffer's journal head which * has been written back. */ - struct shrinker j_shrinker; + struct shrinker *j_shrinker; /** * @j_checkpoint_jh_count: diff --git a/include/linux/memblock.h b/include/linux/memblock.h index 1c1072e3ca06..ae3bde302f70 100644 --- a/include/linux/memblock.h +++ b/include/linux/memblock.h @@ -40,6 +40,8 @@ extern unsigned long long max_possible_pfn; * via a driver, and never indicated in the firmware-provided memory map as * system RAM. This corresponds to IORESOURCE_SYSRAM_DRIVER_MANAGED in the * kernel resource tree. + * @MEMBLOCK_RSRV_NOINIT: memory region for which struct pages are + * not initialized (only for reserved regions). */ enum memblock_flags { MEMBLOCK_NONE = 0x0, /* No special request */ @@ -47,6 +49,7 @@ enum memblock_flags { MEMBLOCK_MIRROR = 0x2, /* mirrored region */ MEMBLOCK_NOMAP = 0x4, /* don't add to kernel direct mapping */ MEMBLOCK_DRIVER_MANAGED = 0x8, /* always detected via a driver */ + MEMBLOCK_RSRV_NOINIT = 0x10, /* don't initialize struct pages */ }; /** @@ -125,6 +128,7 @@ int memblock_clear_hotplug(phys_addr_t base, phys_addr_t size); int memblock_mark_mirror(phys_addr_t base, phys_addr_t size); int memblock_mark_nomap(phys_addr_t base, phys_addr_t size); int memblock_clear_nomap(phys_addr_t base, phys_addr_t size); +int memblock_reserved_mark_noinit(phys_addr_t base, phys_addr_t size); void memblock_free_all(void); void memblock_free(void *ptr, size_t size); @@ -259,6 +263,11 @@ static inline bool memblock_is_nomap(struct memblock_region *m) return m->flags & MEMBLOCK_NOMAP; } +static inline bool memblock_is_reserved_noinit(struct memblock_region *m) +{ + return m->flags & MEMBLOCK_RSRV_NOINIT; +} + static inline bool memblock_is_driver_managed(struct memblock_region *m) { return m->flags & MEMBLOCK_DRIVER_MANAGED; diff --git a/include/linux/memcontrol.h b/include/linux/memcontrol.h index e4e24da16d2c..7bdcf3020d7a 100644 --- a/include/linux/memcontrol.h +++ b/include/linux/memcontrol.h @@ -21,6 +21,7 @@ #include <linux/vmstat.h> #include <linux/writeback.h> #include <linux/page-flags.h> +#include <linux/shrinker.h> struct mem_cgroup; struct obj_cgroup; @@ -88,17 +89,6 @@ struct mem_cgroup_reclaim_iter { unsigned int generation; }; -/* - * Bitmap and deferred work of shrinker::id corresponding to memcg-aware - * shrinkers, which have elements charged to this memcg. - */ -struct shrinker_info { - struct rcu_head rcu; - atomic_long_t *nr_deferred; - unsigned long *map; - int map_nr_max; -}; - struct lruvec_stats_percpu { /* Local (CPU and cgroup) state */ long state[NR_VM_NODE_STAT_ITEMS]; @@ -153,7 +143,7 @@ struct mem_cgroup_threshold_ary { /* Size of entries[] */ unsigned int size; /* Array of thresholds */ - struct mem_cgroup_threshold entries[]; + struct mem_cgroup_threshold entries[] __counted_by(size); }; struct mem_cgroup_thresholds { @@ -299,7 +289,13 @@ struct mem_cgroup { #ifdef CONFIG_MEMCG_KMEM int kmemcg_id; - struct obj_cgroup __rcu *objcg; + /* + * memcg->objcg is wiped out as a part of the objcg repaprenting + * process. memcg->orig_objcg preserves a pointer (and a reference) + * to the original objcg until the end of live of memcg. + */ + struct obj_cgroup __rcu *objcg; + struct obj_cgroup *orig_objcg; /* list of inherited objcgs, protected by objcg_lock */ struct list_head objcg_list; #endif @@ -662,6 +658,8 @@ static inline bool mem_cgroup_below_min(struct mem_cgroup *target, page_counter_read(&memcg->memory); } +void mem_cgroup_commit_charge(struct folio *folio, struct mem_cgroup *memcg); + int __mem_cgroup_charge(struct folio *folio, struct mm_struct *mm, gfp_t gfp); /** @@ -686,6 +684,9 @@ static inline int mem_cgroup_charge(struct folio *folio, struct mm_struct *mm, return __mem_cgroup_charge(folio, mm, gfp); } +int mem_cgroup_hugetlb_try_charge(struct mem_cgroup *memcg, gfp_t gfp, + long nr_pages); + int mem_cgroup_swapin_charge_folio(struct folio *folio, struct mm_struct *mm, gfp_t gfp, swp_entry_t entry); void mem_cgroup_swapin_uncharge_swap(swp_entry_t entry); @@ -713,6 +714,10 @@ static inline void mem_cgroup_uncharge_list(struct list_head *page_list) __mem_cgroup_uncharge_list(page_list); } +void mem_cgroup_cancel_charge(struct mem_cgroup *memcg, unsigned int nr_pages); + +void mem_cgroup_replace_folio(struct folio *old, struct folio *new); + void mem_cgroup_migrate(struct folio *old, struct folio *new); /** @@ -769,6 +774,8 @@ struct mem_cgroup *mem_cgroup_from_task(struct task_struct *p); struct mem_cgroup *get_mem_cgroup_from_mm(struct mm_struct *mm); +struct mem_cgroup *get_mem_cgroup_from_current(void); + struct lruvec *folio_lruvec_lock(struct folio *folio); struct lruvec *folio_lruvec_lock_irq(struct folio *folio); struct lruvec *folio_lruvec_lock_irqsave(struct folio *folio, @@ -1080,15 +1087,6 @@ static inline void count_memcg_events(struct mem_cgroup *memcg, local_irq_restore(flags); } -static inline void count_memcg_page_event(struct page *page, - enum vm_event_item idx) -{ - struct mem_cgroup *memcg = page_memcg(page); - - if (memcg) - count_memcg_events(memcg, idx, 1); -} - static inline void count_memcg_folio_events(struct folio *folio, enum vm_event_item idx, unsigned long nr) { @@ -1249,12 +1247,23 @@ static inline bool mem_cgroup_below_min(struct mem_cgroup *target, return false; } +static inline void mem_cgroup_commit_charge(struct folio *folio, + struct mem_cgroup *memcg) +{ +} + static inline int mem_cgroup_charge(struct folio *folio, struct mm_struct *mm, gfp_t gfp) { return 0; } +static inline int mem_cgroup_hugetlb_try_charge(struct mem_cgroup *memcg, + gfp_t gfp, long nr_pages) +{ + return 0; +} + static inline int mem_cgroup_swapin_charge_folio(struct folio *folio, struct mm_struct *mm, gfp_t gfp, swp_entry_t entry) { @@ -1273,6 +1282,16 @@ static inline void mem_cgroup_uncharge_list(struct list_head *page_list) { } +static inline void mem_cgroup_cancel_charge(struct mem_cgroup *memcg, + unsigned int nr_pages) +{ +} + +static inline void mem_cgroup_replace_folio(struct folio *old, + struct folio *new) +{ +} + static inline void mem_cgroup_migrate(struct folio *old, struct folio *new) { } @@ -1310,6 +1329,11 @@ static inline struct mem_cgroup *get_mem_cgroup_from_mm(struct mm_struct *mm) return NULL; } +static inline struct mem_cgroup *get_mem_cgroup_from_current(void) +{ + return NULL; +} + static inline struct mem_cgroup *mem_cgroup_from_css(struct cgroup_subsys_state *css) { @@ -1565,11 +1589,6 @@ static inline void __count_memcg_events(struct mem_cgroup *memcg, { } -static inline void count_memcg_page_event(struct page *page, - int idx) -{ -} - static inline void count_memcg_folio_events(struct folio *folio, enum vm_event_item idx, unsigned long nr) { @@ -1763,9 +1782,27 @@ bool mem_cgroup_kmem_disabled(void); int __memcg_kmem_charge_page(struct page *page, gfp_t gfp, int order); void __memcg_kmem_uncharge_page(struct page *page, int order); -struct obj_cgroup *get_obj_cgroup_from_current(void); +/* + * The returned objcg pointer is safe to use without additional + * protection within a scope. The scope is defined either by + * the current task (similar to the "current" global variable) + * or by set_active_memcg() pair. + * Please, use obj_cgroup_get() to get a reference if the pointer + * needs to be used outside of the local scope. + */ +struct obj_cgroup *current_obj_cgroup(void); struct obj_cgroup *get_obj_cgroup_from_folio(struct folio *folio); +static inline struct obj_cgroup *get_obj_cgroup_from_current(void) +{ + struct obj_cgroup *objcg = current_obj_cgroup(); + + if (objcg) + obj_cgroup_get(objcg); + + return objcg; +} + int obj_cgroup_charge(struct obj_cgroup *objcg, gfp_t gfp, size_t size); void obj_cgroup_uncharge(struct obj_cgroup *objcg, size_t size); diff --git a/include/linux/memory-tiers.h b/include/linux/memory-tiers.h index 437441cdf78f..1e39d27bee41 100644 --- a/include/linux/memory-tiers.h +++ b/include/linux/memory-tiers.h @@ -6,6 +6,7 @@ #include <linux/nodemask.h> #include <linux/kref.h> #include <linux/mmzone.h> +#include <linux/notifier.h> /* * Each tier cover a abstrace distance chunk size of 128 */ @@ -22,7 +23,9 @@ struct memory_tier; struct memory_dev_type { /* list of memory types that are part of same tier as this type */ - struct list_head tier_sibiling; + struct list_head tier_sibling; + /* list of memory types that are managed by one driver */ + struct list_head list; /* abstract distance for this specific memory type */ int adistance; /* Nodes of same abstract distance */ @@ -30,12 +33,21 @@ struct memory_dev_type { struct kref kref; }; +struct node_hmem_attrs; + #ifdef CONFIG_NUMA extern bool numa_demotion_enabled; +extern struct memory_dev_type *default_dram_type; struct memory_dev_type *alloc_memory_type(int adistance); void put_memory_type(struct memory_dev_type *memtype); void init_node_memory_type(int node, struct memory_dev_type *default_type); void clear_node_memory_type(int node, struct memory_dev_type *memtype); +int register_mt_adistance_algorithm(struct notifier_block *nb); +int unregister_mt_adistance_algorithm(struct notifier_block *nb); +int mt_calc_adistance(int node, int *adist); +int mt_set_default_dram_perf(int nid, struct node_hmem_attrs *perf, + const char *source); +int mt_perf_to_adistance(struct node_hmem_attrs *perf, int *adist); #ifdef CONFIG_MIGRATION int next_demotion_node(int node); void node_get_allowed_targets(pg_data_t *pgdat, nodemask_t *targets); @@ -60,6 +72,7 @@ static inline bool node_is_toptier(int node) #else #define numa_demotion_enabled false +#define default_dram_type NULL /* * CONFIG_NUMA implementation returns non NULL error. */ @@ -97,5 +110,31 @@ static inline bool node_is_toptier(int node) { return true; } + +static inline int register_mt_adistance_algorithm(struct notifier_block *nb) +{ + return 0; +} + +static inline int unregister_mt_adistance_algorithm(struct notifier_block *nb) +{ + return 0; +} + +static inline int mt_calc_adistance(int node, int *adist) +{ + return NOTIFY_DONE; +} + +static inline int mt_set_default_dram_perf(int nid, struct node_hmem_attrs *perf, + const char *source) +{ + return -EIO; +} + +static inline int mt_perf_to_adistance(struct node_hmem_attrs *perf, int *adist) +{ + return -EIO; +} #endif /* CONFIG_NUMA */ #endif /* _LINUX_MEMORY_TIERS_H */ diff --git a/include/linux/mempolicy.h b/include/linux/mempolicy.h index d232de7cdc56..931b118336f4 100644 --- a/include/linux/mempolicy.h +++ b/include/linux/mempolicy.h @@ -17,6 +17,8 @@ struct mm_struct; +#define NO_INTERLEAVE_INDEX (-1UL) /* use task il_prev for interleaving */ + #ifdef CONFIG_NUMA /* @@ -89,8 +91,6 @@ static inline struct mempolicy *mpol_dup(struct mempolicy *pol) return pol; } -#define vma_policy(vma) ((vma)->vm_policy) - static inline void mpol_get(struct mempolicy *pol) { if (pol) @@ -107,35 +107,30 @@ static inline bool mpol_equal(struct mempolicy *a, struct mempolicy *b) /* * Tree of shared policies for a shared memory region. - * Maintain the policies in a pseudo mm that contains vmas. The vmas - * carry the policy. As a special twist the pseudo mm is indexed in pages, not - * bytes, so that we can work with shared memory segments bigger than - * unsigned long. */ - -struct sp_node { - struct rb_node nd; - unsigned long start, end; - struct mempolicy *policy; -}; - struct shared_policy { struct rb_root root; rwlock_t lock; }; +struct sp_node { + struct rb_node nd; + pgoff_t start, end; + struct mempolicy *policy; +}; int vma_dup_policy(struct vm_area_struct *src, struct vm_area_struct *dst); void mpol_shared_policy_init(struct shared_policy *sp, struct mempolicy *mpol); -int mpol_set_shared_policy(struct shared_policy *info, - struct vm_area_struct *vma, - struct mempolicy *new); -void mpol_free_shared_policy(struct shared_policy *p); +int mpol_set_shared_policy(struct shared_policy *sp, + struct vm_area_struct *vma, struct mempolicy *mpol); +void mpol_free_shared_policy(struct shared_policy *sp); struct mempolicy *mpol_shared_policy_lookup(struct shared_policy *sp, - unsigned long idx); + pgoff_t idx); struct mempolicy *get_task_policy(struct task_struct *p); struct mempolicy *__get_vma_policy(struct vm_area_struct *vma, - unsigned long addr); + unsigned long addr, pgoff_t *ilx); +struct mempolicy *get_vma_policy(struct vm_area_struct *vma, + unsigned long addr, int order, pgoff_t *ilx); bool vma_policy_mof(struct vm_area_struct *vma); extern void numa_default_policy(void); @@ -149,8 +144,6 @@ extern int huge_node(struct vm_area_struct *vma, extern bool init_nodemask_of_mempolicy(nodemask_t *mask); extern bool mempolicy_in_oom_domain(struct task_struct *tsk, const nodemask_t *mask); -extern nodemask_t *policy_nodemask(gfp_t gfp, struct mempolicy *policy); - extern unsigned int mempolicy_slab_node(void); extern enum zone_type policy_zone; @@ -174,7 +167,7 @@ extern void mpol_to_str(char *buffer, int maxlen, struct mempolicy *pol); /* Check if a vma is migratable */ extern bool vma_migratable(struct vm_area_struct *vma); -extern int mpol_misplaced(struct page *, struct vm_area_struct *, unsigned long); +int mpol_misplaced(struct folio *, struct vm_area_struct *, unsigned long); extern void mpol_put_task_policy(struct task_struct *); static inline bool mpol_is_preferred_many(struct mempolicy *pol) @@ -188,12 +181,17 @@ extern bool apply_policy_zone(struct mempolicy *policy, enum zone_type zone); struct mempolicy {}; +static inline struct mempolicy *get_task_policy(struct task_struct *p) +{ + return NULL; +} + static inline bool mpol_equal(struct mempolicy *a, struct mempolicy *b) { return true; } -static inline void mpol_put(struct mempolicy *p) +static inline void mpol_put(struct mempolicy *pol) { } @@ -212,17 +210,22 @@ static inline void mpol_shared_policy_init(struct shared_policy *sp, { } -static inline void mpol_free_shared_policy(struct shared_policy *p) +static inline void mpol_free_shared_policy(struct shared_policy *sp) { } static inline struct mempolicy * -mpol_shared_policy_lookup(struct shared_policy *sp, unsigned long idx) +mpol_shared_policy_lookup(struct shared_policy *sp, pgoff_t idx) { return NULL; } -#define vma_policy(vma) NULL +static inline struct mempolicy *get_vma_policy(struct vm_area_struct *vma, + unsigned long addr, int order, pgoff_t *ilx) +{ + *ilx = 0; + return NULL; +} static inline int vma_dup_policy(struct vm_area_struct *src, struct vm_area_struct *dst) @@ -278,7 +281,8 @@ static inline int mpol_parse_str(char *str, struct mempolicy **mpol) } #endif -static inline int mpol_misplaced(struct page *page, struct vm_area_struct *vma, +static inline int mpol_misplaced(struct folio *folio, + struct vm_area_struct *vma, unsigned long address) { return -1; /* no node preference */ diff --git a/include/linux/migrate.h b/include/linux/migrate.h index 711dd9412561..2ce13e8a309b 100644 --- a/include/linux/migrate.h +++ b/include/linux/migrate.h @@ -142,10 +142,10 @@ const struct movable_operations *page_movable_ops(struct page *page) } #ifdef CONFIG_NUMA_BALANCING -int migrate_misplaced_page(struct page *page, struct vm_area_struct *vma, +int migrate_misplaced_folio(struct folio *folio, struct vm_area_struct *vma, int node); #else -static inline int migrate_misplaced_page(struct page *page, +static inline int migrate_misplaced_folio(struct folio *folio, struct vm_area_struct *vma, int node) { return -EAGAIN; /* can't migrate now */ diff --git a/include/linux/mm.h b/include/linux/mm.h index ba896e946651..418d26608ece 100644 --- a/include/linux/mm.h +++ b/include/linux/mm.h @@ -617,7 +617,7 @@ struct vm_operations_struct { * policy. */ struct mempolicy *(*get_policy)(struct vm_area_struct *vma, - unsigned long addr); + unsigned long addr, pgoff_t *ilx); #endif /* * Called by vm_normal_page() for special PTEs to find the @@ -935,6 +935,17 @@ static inline bool vma_is_accessible(struct vm_area_struct *vma) return vma->vm_flags & VM_ACCESS_FLAGS; } +static inline bool is_shared_maywrite(vm_flags_t vm_flags) +{ + return (vm_flags & (VM_SHARED | VM_MAYWRITE)) == + (VM_SHARED | VM_MAYWRITE); +} + +static inline bool vma_is_shared_maywrite(struct vm_area_struct *vma) +{ + return is_shared_maywrite(vma->vm_flags); +} + static inline struct vm_area_struct *vma_find(struct vma_iterator *vmi, unsigned long max) { @@ -1335,7 +1346,6 @@ void set_pte_range(struct vm_fault *vmf, struct folio *folio, struct page *page, unsigned int nr, unsigned long addr); vm_fault_t finish_fault(struct vm_fault *vmf); -vm_fault_t finish_mkwrite_fault(struct vm_fault *vmf); #endif /* @@ -1684,26 +1694,26 @@ static inline bool __cpupid_match_pid(pid_t task_pid, int cpupid) #define cpupid_match_pid(task, cpupid) __cpupid_match_pid(task->pid, cpupid) #ifdef LAST_CPUPID_NOT_IN_PAGE_FLAGS -static inline int page_cpupid_xchg_last(struct page *page, int cpupid) +static inline int folio_xchg_last_cpupid(struct folio *folio, int cpupid) { - return xchg(&page->_last_cpupid, cpupid & LAST_CPUPID_MASK); + return xchg(&folio->_last_cpupid, cpupid & LAST_CPUPID_MASK); } -static inline int page_cpupid_last(struct page *page) +static inline int folio_last_cpupid(struct folio *folio) { - return page->_last_cpupid; + return folio->_last_cpupid; } static inline void page_cpupid_reset_last(struct page *page) { page->_last_cpupid = -1 & LAST_CPUPID_MASK; } #else -static inline int page_cpupid_last(struct page *page) +static inline int folio_last_cpupid(struct folio *folio) { - return (page->flags >> LAST_CPUPID_PGSHIFT) & LAST_CPUPID_MASK; + return (folio->flags >> LAST_CPUPID_PGSHIFT) & LAST_CPUPID_MASK; } -extern int page_cpupid_xchg_last(struct page *page, int cpupid); +int folio_xchg_last_cpupid(struct folio *folio, int cpupid); static inline void page_cpupid_reset_last(struct page *page) { @@ -1711,11 +1721,12 @@ static inline void page_cpupid_reset_last(struct page *page) } #endif /* LAST_CPUPID_NOT_IN_PAGE_FLAGS */ -static inline int xchg_page_access_time(struct page *page, int time) +static inline int folio_xchg_access_time(struct folio *folio, int time) { int last_time; - last_time = page_cpupid_xchg_last(page, time >> PAGE_ACCESS_TIME_BUCKETS); + last_time = folio_xchg_last_cpupid(folio, + time >> PAGE_ACCESS_TIME_BUCKETS); return last_time << PAGE_ACCESS_TIME_BUCKETS; } @@ -1729,19 +1740,19 @@ static inline void vma_set_access_pid_bit(struct vm_area_struct *vma) } } #else /* !CONFIG_NUMA_BALANCING */ -static inline int page_cpupid_xchg_last(struct page *page, int cpupid) +static inline int folio_xchg_last_cpupid(struct folio *folio, int cpupid) { - return page_to_nid(page); /* XXX */ + return folio_nid(folio); /* XXX */ } -static inline int xchg_page_access_time(struct page *page, int time) +static inline int folio_xchg_access_time(struct folio *folio, int time) { return 0; } -static inline int page_cpupid_last(struct page *page) +static inline int folio_last_cpupid(struct folio *folio) { - return page_to_nid(page); /* XXX */ + return folio_nid(folio); /* XXX */ } static inline int cpupid_to_nid(int cpupid) @@ -2325,6 +2336,8 @@ struct folio *vm_normal_folio(struct vm_area_struct *vma, unsigned long addr, pte_t pte); struct page *vm_normal_page(struct vm_area_struct *vma, unsigned long addr, pte_t pte); +struct folio *vm_normal_folio_pmd(struct vm_area_struct *vma, + unsigned long addr, pmd_t pmd); struct page *vm_normal_page_pmd(struct vm_area_struct *vma, unsigned long addr, pmd_t pmd); @@ -2411,8 +2424,6 @@ extern int access_process_vm(struct task_struct *tsk, unsigned long addr, void *buf, int len, unsigned int gup_flags); extern int access_remote_vm(struct mm_struct *mm, unsigned long addr, void *buf, int len, unsigned int gup_flags); -extern int __access_remote_vm(struct mm_struct *mm, unsigned long addr, - void *buf, int len, unsigned int gup_flags); long get_user_pages_remote(struct mm_struct *mm, unsigned long start, unsigned long nr_pages, @@ -2423,6 +2434,9 @@ long pin_user_pages_remote(struct mm_struct *mm, unsigned int gup_flags, struct page **pages, int *locked); +/* + * Retrieves a single page alongside its VMA. Does not support FOLL_NOWAIT. + */ static inline struct page *get_user_page_vma_remote(struct mm_struct *mm, unsigned long addr, int gup_flags, @@ -2430,12 +2444,15 @@ static inline struct page *get_user_page_vma_remote(struct mm_struct *mm, { struct page *page; struct vm_area_struct *vma; - int got = get_user_pages_remote(mm, addr, 1, gup_flags, &page, NULL); + int got; + + if (WARN_ON_ONCE(unlikely(gup_flags & FOLL_NOWAIT))) + return ERR_PTR(-EINVAL); + + got = get_user_pages_remote(mm, addr, 1, gup_flags, &page, NULL); if (got < 0) return ERR_PTR(got); - if (got == 0) - return NULL; vma = vma_lookup(mm, addr); if (WARN_ON_ONCE(!vma)) { @@ -2478,7 +2495,7 @@ int get_cmdline(struct task_struct *task, char *buffer, int buflen); extern unsigned long move_page_tables(struct vm_area_struct *vma, unsigned long old_addr, struct vm_area_struct *new_vma, unsigned long new_addr, unsigned long len, - bool need_rmap_locks); + bool need_rmap_locks, bool for_stack); /* * Flags used by change_protection(). For now we make it a bitmap so @@ -2626,14 +2643,6 @@ static inline void setmax_mm_hiwater_rss(unsigned long *maxrss, *maxrss = hiwater_rss; } -#if defined(SPLIT_RSS_COUNTING) -void sync_mm_rss(struct mm_struct *mm); -#else -static inline void sync_mm_rss(struct mm_struct *mm) -{ -} -#endif - #ifndef CONFIG_ARCH_HAS_PTE_SPECIAL static inline int pte_special(pte_t pte) { @@ -3055,6 +3064,22 @@ static inline spinlock_t *pud_lock(struct mm_struct *mm, pud_t *pud) return ptl; } +static inline void pagetable_pud_ctor(struct ptdesc *ptdesc) +{ + struct folio *folio = ptdesc_folio(ptdesc); + + __folio_set_pgtable(folio); + lruvec_stat_add_folio(folio, NR_PAGETABLE); +} + +static inline void pagetable_pud_dtor(struct ptdesc *ptdesc) +{ + struct folio *folio = ptdesc_folio(ptdesc); + + __folio_clear_pgtable(folio); + lruvec_stat_sub_folio(folio, NR_PAGETABLE); +} + extern void __init pagecache_init(void); extern void free_initmem(void); @@ -3219,22 +3244,73 @@ extern int vma_expand(struct vma_iterator *vmi, struct vm_area_struct *vma, struct vm_area_struct *next); extern int vma_shrink(struct vma_iterator *vmi, struct vm_area_struct *vma, unsigned long start, unsigned long end, pgoff_t pgoff); -extern struct vm_area_struct *vma_merge(struct vma_iterator *vmi, - struct mm_struct *, struct vm_area_struct *prev, unsigned long addr, - unsigned long end, unsigned long vm_flags, struct anon_vma *, - struct file *, pgoff_t, struct mempolicy *, struct vm_userfaultfd_ctx, - struct anon_vma_name *); extern struct anon_vma *find_mergeable_anon_vma(struct vm_area_struct *); -extern int __split_vma(struct vma_iterator *vmi, struct vm_area_struct *, - unsigned long addr, int new_below); -extern int split_vma(struct vma_iterator *vmi, struct vm_area_struct *, - unsigned long addr, int new_below); extern int insert_vm_struct(struct mm_struct *, struct vm_area_struct *); extern void unlink_file_vma(struct vm_area_struct *); extern struct vm_area_struct *copy_vma(struct vm_area_struct **, unsigned long addr, unsigned long len, pgoff_t pgoff, bool *need_rmap_locks); extern void exit_mmap(struct mm_struct *); +struct vm_area_struct *vma_modify(struct vma_iterator *vmi, + struct vm_area_struct *prev, + struct vm_area_struct *vma, + unsigned long start, unsigned long end, + unsigned long vm_flags, + struct mempolicy *policy, + struct vm_userfaultfd_ctx uffd_ctx, + struct anon_vma_name *anon_name); + +/* We are about to modify the VMA's flags. */ +static inline struct vm_area_struct +*vma_modify_flags(struct vma_iterator *vmi, + struct vm_area_struct *prev, + struct vm_area_struct *vma, + unsigned long start, unsigned long end, + unsigned long new_flags) +{ + return vma_modify(vmi, prev, vma, start, end, new_flags, + vma_policy(vma), vma->vm_userfaultfd_ctx, + anon_vma_name(vma)); +} + +/* We are about to modify the VMA's flags and/or anon_name. */ +static inline struct vm_area_struct +*vma_modify_flags_name(struct vma_iterator *vmi, + struct vm_area_struct *prev, + struct vm_area_struct *vma, + unsigned long start, + unsigned long end, + unsigned long new_flags, + struct anon_vma_name *new_name) +{ + return vma_modify(vmi, prev, vma, start, end, new_flags, + vma_policy(vma), vma->vm_userfaultfd_ctx, new_name); +} + +/* We are about to modify the VMA's memory policy. */ +static inline struct vm_area_struct +*vma_modify_policy(struct vma_iterator *vmi, + struct vm_area_struct *prev, + struct vm_area_struct *vma, + unsigned long start, unsigned long end, + struct mempolicy *new_pol) +{ + return vma_modify(vmi, prev, vma, start, end, vma->vm_flags, + new_pol, vma->vm_userfaultfd_ctx, anon_vma_name(vma)); +} + +/* We are about to modify the VMA's flags and/or uffd context. */ +static inline struct vm_area_struct +*vma_modify_flags_uffd(struct vma_iterator *vmi, + struct vm_area_struct *prev, + struct vm_area_struct *vma, + unsigned long start, unsigned long end, + unsigned long new_flags, + struct vm_userfaultfd_ctx new_ctx) +{ + return vma_modify(vmi, prev, vma, start, end, new_flags, + vma_policy(vma), new_ctx, anon_vma_name(vma)); +} static inline int check_data_rlimit(unsigned long rlim, unsigned long new, @@ -3997,25 +4073,26 @@ static inline void mem_dump_obj(void *object) {} #endif /** - * seal_check_future_write - Check for F_SEAL_FUTURE_WRITE flag and handle it + * seal_check_write - Check for F_SEAL_WRITE or F_SEAL_FUTURE_WRITE flags and + * handle them. * @seals: the seals to check * @vma: the vma to operate on * - * Check whether F_SEAL_FUTURE_WRITE is set; if so, do proper check/handling on - * the vma flags. Return 0 if check pass, or <0 for errors. + * Check whether F_SEAL_WRITE or F_SEAL_FUTURE_WRITE are set; if so, do proper + * check/handling on the vma flags. Return 0 if check pass, or <0 for errors. */ -static inline int seal_check_future_write(int seals, struct vm_area_struct *vma) +static inline int seal_check_write(int seals, struct vm_area_struct *vma) { - if (seals & F_SEAL_FUTURE_WRITE) { + if (seals & (F_SEAL_WRITE | F_SEAL_FUTURE_WRITE)) { /* * New PROT_WRITE and MAP_SHARED mmaps are not allowed when - * "future write" seal active. + * write seals are active. */ if ((vma->vm_flags & VM_SHARED) && (vma->vm_flags & VM_WRITE)) return -EPERM; /* - * Since an F_SEAL_FUTURE_WRITE sealed memfd can be mapped as + * Since an F_SEAL_[FUTURE_]WRITE sealed memfd can be mapped as * MAP_SHARED and read-only, take care to not allow mprotect to * revert protections on such mappings. Do this only for shared * mappings. For private mappings, don't need to mask @@ -4059,4 +4136,11 @@ static inline void accept_memory(phys_addr_t start, phys_addr_t end) #endif +static inline bool pfn_is_unaccepted_memory(unsigned long pfn) +{ + phys_addr_t paddr = pfn << PAGE_SHIFT; + + return range_contains_unaccepted_memory(paddr, paddr + PAGE_SIZE); +} + #endif /* _LINUX_MM_H */ diff --git a/include/linux/mm_inline.h b/include/linux/mm_inline.h index 8148b30a9df1..9ae7def16cb2 100644 --- a/include/linux/mm_inline.h +++ b/include/linux/mm_inline.h @@ -4,6 +4,7 @@ #include <linux/atomic.h> #include <linux/huge_mm.h> +#include <linux/mm_types.h> #include <linux/swap.h> #include <linux/string.h> #include <linux/userfaultfd_k.h> @@ -352,15 +353,6 @@ void lruvec_del_folio(struct lruvec *lruvec, struct folio *folio) } #ifdef CONFIG_ANON_VMA_NAME -/* - * mmap_lock should be read-locked when calling anon_vma_name(). Caller should - * either keep holding the lock while using the returned pointer or it should - * raise anon_vma_name refcount before releasing the lock. - */ -extern struct anon_vma_name *anon_vma_name(struct vm_area_struct *vma); -extern struct anon_vma_name *anon_vma_name_alloc(const char *name); -extern void anon_vma_name_free(struct kref *kref); - /* mmap_lock should be read-locked */ static inline void anon_vma_name_get(struct anon_vma_name *anon_name) { @@ -415,16 +407,6 @@ static inline bool anon_vma_name_eq(struct anon_vma_name *anon_name1, } #else /* CONFIG_ANON_VMA_NAME */ -static inline struct anon_vma_name *anon_vma_name(struct vm_area_struct *vma) -{ - return NULL; -} - -static inline struct anon_vma_name *anon_vma_name_alloc(const char *name) -{ - return NULL; -} - static inline void anon_vma_name_get(struct anon_vma_name *anon_name) {} static inline void anon_vma_name_put(struct anon_vma_name *anon_name) {} static inline void dup_anon_vma_name(struct vm_area_struct *orig_vma, diff --git a/include/linux/mm_types.h b/include/linux/mm_types.h index 4be8e310b189..957ce38768b2 100644 --- a/include/linux/mm_types.h +++ b/include/linux/mm_types.h @@ -188,6 +188,10 @@ struct page { not kmapped, ie. highmem) */ #endif /* WANT_PAGE_VIRTUAL */ +#ifdef LAST_CPUPID_NOT_IN_PAGE_FLAGS + int _last_cpupid; +#endif + #ifdef CONFIG_KMSAN /* * KMSAN metadata for this page: @@ -199,10 +203,6 @@ struct page { struct page *kmsan_shadow; struct page *kmsan_origin; #endif - -#ifdef LAST_CPUPID_NOT_IN_PAGE_FLAGS - int _last_cpupid; -#endif } _struct_page_alignment; /* @@ -261,6 +261,8 @@ typedef struct { * @_refcount: Do not access this member directly. Use folio_ref_count() * to find how many references there are to this folio. * @memcg_data: Memory Control Group data. + * @virtual: Virtual address in the kernel direct map. + * @_last_cpupid: IDs of last CPU and last process that accessed the folio. * @_entire_mapcount: Do not use directly, call folio_entire_mapcount(). * @_nr_pages_mapped: Do not use directly, call folio_mapcount(). * @_pincount: Do not use directly, call folio_maybe_dma_pinned(). @@ -307,6 +309,12 @@ struct folio { #ifdef CONFIG_MEMCG unsigned long memcg_data; #endif +#if defined(WANT_PAGE_VIRTUAL) + void *virtual; +#endif +#ifdef LAST_CPUPID_NOT_IN_PAGE_FLAGS + int _last_cpupid; +#endif /* private: the union with struct page is transitional */ }; struct page page; @@ -362,6 +370,12 @@ FOLIO_MATCH(_refcount, _refcount); #ifdef CONFIG_MEMCG FOLIO_MATCH(memcg_data, memcg_data); #endif +#if defined(WANT_PAGE_VIRTUAL) +FOLIO_MATCH(virtual, virtual); +#endif +#ifdef LAST_CPUPID_NOT_IN_PAGE_FLAGS +FOLIO_MATCH(_last_cpupid, _last_cpupid); +#endif #undef FOLIO_MATCH #define FOLIO_MATCH(pg, fl) \ static_assert(offsetof(struct folio, fl) == \ @@ -535,6 +549,27 @@ struct anon_vma_name { char name[]; }; +#ifdef CONFIG_ANON_VMA_NAME +/* + * mmap_lock should be read-locked when calling anon_vma_name(). Caller should + * either keep holding the lock while using the returned pointer or it should + * raise anon_vma_name refcount before releasing the lock. + */ +struct anon_vma_name *anon_vma_name(struct vm_area_struct *vma); +struct anon_vma_name *anon_vma_name_alloc(const char *name); +void anon_vma_name_free(struct kref *kref); +#else /* CONFIG_ANON_VMA_NAME */ +static inline struct anon_vma_name *anon_vma_name(struct vm_area_struct *vma) +{ + return NULL; +} + +static inline struct anon_vma_name *anon_vma_name_alloc(const char *name) +{ + return NULL; +} +#endif + struct vma_lock { struct rw_semaphore lock; }; @@ -678,6 +713,12 @@ struct vm_area_struct { struct vm_userfaultfd_ctx vm_userfaultfd_ctx; } __randomize_layout; +#ifdef CONFIG_NUMA +#define vma_policy(vma) ((vma)->vm_policy) +#else +#define vma_policy(vma) NULL +#endif + #ifdef CONFIG_SCHED_MM_CID struct mm_cid { u64 time; diff --git a/include/linux/mmu_notifier.h b/include/linux/mmu_notifier.h index 6e3c857606f1..f349e08a9dfe 100644 --- a/include/linux/mmu_notifier.h +++ b/include/linux/mmu_notifier.h @@ -459,7 +459,14 @@ mmu_notifier_invalidate_range_start(struct mmu_notifier_range *range) lock_map_release(&__mmu_notifier_invalidate_range_start_map); } -static inline int +/* + * This version of mmu_notifier_invalidate_range_start() avoids blocking, but it + * can return an error if a notifier can't proceed without blocking, in which + * case you're not allowed to modify PTEs in the specified range. + * + * This is mainly intended for OOM handling. + */ +static inline int __must_check mmu_notifier_invalidate_range_start_nonblock(struct mmu_notifier_range *range) { int ret = 0; diff --git a/include/linux/mmzone.h b/include/linux/mmzone.h index 4106fbc5b4b3..3c25226beeed 100644 --- a/include/linux/mmzone.h +++ b/include/linux/mmzone.h @@ -639,8 +639,6 @@ struct lruvec { #endif }; -/* Isolate unmapped pages */ -#define ISOLATE_UNMAPPED ((__force isolate_mode_t)0x2) /* Isolate for asynchronous migration */ #define ISOLATE_ASYNC_MIGRATE ((__force isolate_mode_t)0x4) /* Isolate unevictable pages */ @@ -676,15 +674,34 @@ enum zone_watermarks { #define high_wmark_pages(z) (z->_watermark[WMARK_HIGH] + z->watermark_boost) #define wmark_pages(z, i) (z->_watermark[i] + z->watermark_boost) +/* + * Flags used in pcp->flags field. + * + * PCPF_PREV_FREE_HIGH_ORDER: a high-order page is freed in the + * previous page freeing. To avoid to drain PCP for an accident + * high-order page freeing. + * + * PCPF_FREE_HIGH_BATCH: preserve "pcp->batch" pages in PCP before + * draining PCP for consecutive high-order pages freeing without + * allocation if data cache slice of CPU is large enough. To reduce + * zone lock contention and keep cache-hot pages reusing. + */ +#define PCPF_PREV_FREE_HIGH_ORDER BIT(0) +#define PCPF_FREE_HIGH_BATCH BIT(1) + struct per_cpu_pages { spinlock_t lock; /* Protects lists field */ int count; /* number of pages in the list */ int high; /* high watermark, emptying needed */ + int high_min; /* min high watermark */ + int high_max; /* max high watermark */ int batch; /* chunk size for buddy add/remove */ - short free_factor; /* batch scaling factor during free */ + u8 flags; /* protected by pcp->lock */ + u8 alloc_factor; /* batch scaling factor during allocate */ #ifdef CONFIG_NUMA - short expire; /* When 0, remote pagesets are drained */ + u8 expire; /* When 0, remote pagesets are drained */ #endif + short free_count; /* consecutive free count */ /* Lists of pages, one per migrate type stored on the pcp-lists */ struct list_head lists[NR_PCP_LISTS]; @@ -837,7 +854,8 @@ struct zone { * the high and batch values are copied to individual pagesets for * faster access */ - int pageset_high; + int pageset_high_min; + int pageset_high_max; int pageset_batch; #ifndef CONFIG_SPARSEMEM @@ -998,6 +1016,7 @@ enum zone_flags { * Cleared when kswapd is woken. */ ZONE_RECLAIM_ACTIVE, /* kswapd may be scanning the zone. */ + ZONE_BELOW_HIGH, /* zone is below high watermark. */ }; static inline unsigned long zone_managed_pages(struct zone *zone) diff --git a/include/linux/page-flags.h b/include/linux/page-flags.h index 5c02720c53a5..a88e64acebfe 100644 --- a/include/linux/page-flags.h +++ b/include/linux/page-flags.h @@ -693,6 +693,25 @@ TESTPAGEFLAG_FALSE(Ksm, ksm) u64 stable_page_flags(struct page *page); /** + * folio_xor_flags_has_waiters - Change some folio flags. + * @folio: The folio. + * @mask: Bits set in this word will be changed. + * + * This must only be used for flags which are changed with the folio + * lock held. For example, it is unsafe to use for PG_dirty as that + * can be set without the folio lock held. It can also only be used + * on flags which are in the range 0-6 as some of the implementations + * only affect those bits. + * + * Return: Whether there are tasks waiting on the folio. + */ +static inline bool folio_xor_flags_has_waiters(struct folio *folio, + unsigned long mask) +{ + return xor_unlock_is_negative_byte(mask, folio_flags(folio, 0)); +} + +/** * folio_test_uptodate - Is this folio up to date? * @folio: The folio. * diff --git a/include/linux/pagemap.h b/include/linux/pagemap.h index 351c3b7f93a1..bcc1ea44b4e8 100644 --- a/include/linux/pagemap.h +++ b/include/linux/pagemap.h @@ -789,9 +789,6 @@ static inline pgoff_t folio_next_index(struct folio *folio) */ static inline struct page *folio_file_page(struct folio *folio, pgoff_t index) { - /* HugeTLBfs indexes the page cache in units of hpage_size */ - if (folio_test_hugetlb(folio)) - return &folio->page; return folio_page(folio, index & (folio_nr_pages(folio) - 1)); } @@ -807,9 +804,6 @@ static inline struct page *folio_file_page(struct folio *folio, pgoff_t index) */ static inline bool folio_contains(struct folio *folio, pgoff_t index) { - /* HugeTLBfs indexes the page cache in units of hpage_size */ - if (folio_test_hugetlb(folio)) - return folio->index == index; return index - folio_index(folio) < folio_nr_pages(folio); } @@ -867,10 +861,9 @@ static inline struct folio *read_mapping_folio(struct address_space *mapping, } /* - * Get index of the page within radix-tree (but not for hugetlb pages). - * (TODO: remove once hugetlb pages will have ->index in PAGE_SIZE) + * Get the offset in PAGE_SIZE (even for hugetlb pages). */ -static inline pgoff_t page_to_index(struct page *page) +static inline pgoff_t page_to_pgoff(struct page *page) { struct page *head; @@ -885,19 +878,6 @@ static inline pgoff_t page_to_index(struct page *page) return head->index + page - head; } -extern pgoff_t hugetlb_basepage_index(struct page *page); - -/* - * Get the offset in PAGE_SIZE (even for hugetlb pages). - * (TODO: hugetlb pages should have ->index in PAGE_SIZE) - */ -static inline pgoff_t page_to_pgoff(struct page *page) -{ - if (unlikely(PageHuge(page))) - return hugetlb_basepage_index(page); - return page_to_index(page); -} - /* * Return byte-offset into filesystem object for page. */ @@ -934,24 +914,16 @@ static inline loff_t folio_file_pos(struct folio *folio) /* * Get the offset in PAGE_SIZE (even for hugetlb folios). - * (TODO: hugetlb folios should have ->index in PAGE_SIZE) */ static inline pgoff_t folio_pgoff(struct folio *folio) { - if (unlikely(folio_test_hugetlb(folio))) - return hugetlb_basepage_index(&folio->page); return folio->index; } -extern pgoff_t linear_hugepage_index(struct vm_area_struct *vma, - unsigned long address); - static inline pgoff_t linear_page_index(struct vm_area_struct *vma, unsigned long address) { pgoff_t pgoff; - if (unlikely(is_vm_hugetlb_page(vma))) - return linear_hugepage_index(vma, address); pgoff = (address - vma->vm_start) >> PAGE_SHIFT; pgoff += vma->vm_pgoff; return pgoff; @@ -1129,6 +1101,7 @@ static inline void wait_on_page_locked(struct page *page) folio_wait_locked(page_folio(page)); } +void folio_end_read(struct folio *folio, bool success); void wait_on_page_writeback(struct page *page); void folio_wait_writeback(struct folio *folio); int folio_wait_writeback_killable(struct folio *folio); diff --git a/include/linux/percpu_counter.h b/include/linux/percpu_counter.h index d01351b1526f..3a44dd1e33d2 100644 --- a/include/linux/percpu_counter.h +++ b/include/linux/percpu_counter.h @@ -57,6 +57,8 @@ void percpu_counter_add_batch(struct percpu_counter *fbc, s64 amount, s32 batch); s64 __percpu_counter_sum(struct percpu_counter *fbc); int __percpu_counter_compare(struct percpu_counter *fbc, s64 rhs, s32 batch); +bool __percpu_counter_limited_add(struct percpu_counter *fbc, s64 limit, + s64 amount, s32 batch); void percpu_counter_sync(struct percpu_counter *fbc); static inline int percpu_counter_compare(struct percpu_counter *fbc, s64 rhs) @@ -69,6 +71,13 @@ static inline void percpu_counter_add(struct percpu_counter *fbc, s64 amount) percpu_counter_add_batch(fbc, amount, percpu_counter_batch); } +static inline bool +percpu_counter_limited_add(struct percpu_counter *fbc, s64 limit, s64 amount) +{ + return __percpu_counter_limited_add(fbc, limit, amount, + percpu_counter_batch); +} + /* * With percpu_counter_add_local() and percpu_counter_sub_local(), counts * are accumulated in local per cpu counter and not in fbc->count until @@ -185,6 +194,27 @@ percpu_counter_add(struct percpu_counter *fbc, s64 amount) local_irq_restore(flags); } +static inline bool +percpu_counter_limited_add(struct percpu_counter *fbc, s64 limit, s64 amount) +{ + unsigned long flags; + bool good = false; + s64 count; + + if (amount == 0) + return true; + + local_irq_save(flags); + count = fbc->count + amount; + if ((amount > 0 && count <= limit) || + (amount < 0 && count >= limit)) { + fbc->count = count; + good = true; + } + local_irq_restore(flags); + return good; +} + /* non-SMP percpu_counter_add_local is the same with percpu_counter_add */ static inline void percpu_counter_add_local(struct percpu_counter *fbc, s64 amount) diff --git a/include/linux/rmap.h b/include/linux/rmap.h index 51cc21ebb568..b26fe858fd44 100644 --- a/include/linux/rmap.h +++ b/include/linux/rmap.h @@ -189,7 +189,7 @@ typedef int __bitwise rmap_t; /* * rmap interfaces called when adding or removing pte of page */ -void page_move_anon_rmap(struct page *, struct vm_area_struct *); +void folio_move_anon_rmap(struct folio *, struct vm_area_struct *); void page_add_anon_rmap(struct page *, struct vm_area_struct *, unsigned long address, rmap_t flags); void page_add_new_anon_rmap(struct page *, struct vm_area_struct *, @@ -203,7 +203,7 @@ void folio_add_file_rmap_range(struct folio *, struct page *, unsigned int nr, void page_remove_rmap(struct page *, struct vm_area_struct *, bool compound); -void hugepage_add_anon_rmap(struct page *, struct vm_area_struct *, +void hugepage_add_anon_rmap(struct folio *, struct vm_area_struct *, unsigned long address, rmap_t flags); void hugepage_add_new_anon_rmap(struct folio *, struct vm_area_struct *, unsigned long address); diff --git a/include/linux/sched.h b/include/linux/sched.h index 12ec109ce8c9..b49ca40f6335 100644 --- a/include/linux/sched.h +++ b/include/linux/sched.h @@ -1448,6 +1448,10 @@ struct task_struct { struct mem_cgroup *active_memcg; #endif +#ifdef CONFIG_MEMCG_KMEM + struct obj_cgroup *objcg; +#endif + #ifdef CONFIG_BLK_CGROUP struct gendisk *throttle_disk; #endif diff --git a/include/linux/sched/coredump.h b/include/linux/sched/coredump.h index 0ee96ea7a0e9..02f5090ffea2 100644 --- a/include/linux/sched/coredump.h +++ b/include/linux/sched/coredump.h @@ -71,6 +71,7 @@ static inline int get_dumpable(struct mm_struct *mm) #define MMF_UNSTABLE 22 /* mm is unstable for copy_from_user */ #define MMF_HUGE_ZERO_PAGE 23 /* mm has ever used the global huge zero page */ #define MMF_DISABLE_THP 24 /* disable THP for all VMAs */ +#define MMF_DISABLE_THP_MASK (1 << MMF_DISABLE_THP) #define MMF_OOM_REAP_QUEUED 25 /* mm was queued for oom_reaper */ #define MMF_MULTIPROCESS 26 /* mm is shared between processes */ /* @@ -85,10 +86,22 @@ static inline int get_dumpable(struct mm_struct *mm) #define MMF_HAS_MDWE 28 #define MMF_HAS_MDWE_MASK (1 << MMF_HAS_MDWE) -#define MMF_DISABLE_THP_MASK (1 << MMF_DISABLE_THP) + +#define MMF_HAS_MDWE_NO_INHERIT 29 + +#define MMF_VM_MERGE_ANY 30 +#define MMF_VM_MERGE_ANY_MASK (1 << MMF_VM_MERGE_ANY) #define MMF_INIT_MASK (MMF_DUMPABLE_MASK | MMF_DUMP_FILTER_MASK |\ - MMF_DISABLE_THP_MASK | MMF_HAS_MDWE_MASK) + MMF_DISABLE_THP_MASK | MMF_HAS_MDWE_MASK |\ + MMF_VM_MERGE_ANY_MASK) + +static inline unsigned long mmf_init_flags(unsigned long flags) +{ + if (flags & (1UL << MMF_HAS_MDWE_NO_INHERIT)) + flags &= ~((1UL << MMF_HAS_MDWE) | + (1UL << MMF_HAS_MDWE_NO_INHERIT)); + return flags & MMF_INIT_MASK; +} -#define MMF_VM_MERGE_ANY 29 #endif /* _LINUX_SCHED_COREDUMP_H */ diff --git a/include/linux/sched/mm.h b/include/linux/sched/mm.h index 8d89c8c4fac1..9a19f1b42f64 100644 --- a/include/linux/sched/mm.h +++ b/include/linux/sched/mm.h @@ -403,6 +403,10 @@ DECLARE_PER_CPU(struct mem_cgroup *, int_active_memcg); * __GFP_ACCOUNT allocations till the end of the scope will be charged to the * given memcg. * + * Please, make sure that caller has a reference to the passed memcg structure, + * so its lifetime is guaranteed to exceed the scope between two + * set_active_memcg() calls. + * * NOTE: This function can nest. Users must save the return value and * reset the previous value after their own charging scope is over. */ diff --git a/include/linux/sched/numa_balancing.h b/include/linux/sched/numa_balancing.h index b69afb8630db..52b22c5c396d 100644 --- a/include/linux/sched/numa_balancing.h +++ b/include/linux/sched/numa_balancing.h @@ -30,8 +30,8 @@ extern void task_numa_fault(int last_node, int node, int pages, int flags); extern pid_t task_numa_group_id(struct task_struct *p); extern void set_numabalancing_state(bool enabled); extern void task_numa_free(struct task_struct *p, bool final); -extern bool should_numa_migrate_memory(struct task_struct *p, struct page *page, - int src_nid, int dst_cpu); +bool should_numa_migrate_memory(struct task_struct *p, struct folio *folio, + int src_nid, int dst_cpu); #else static inline void task_numa_fault(int last_node, int node, int pages, int flags) @@ -48,7 +48,7 @@ static inline void task_numa_free(struct task_struct *p, bool final) { } static inline bool should_numa_migrate_memory(struct task_struct *p, - struct page *page, int src_nid, int dst_cpu) + struct folio *folio, int src_nid, int dst_cpu) { return true; } diff --git a/include/linux/shmem_fs.h b/include/linux/shmem_fs.h index 6b0c626620f5..2caa6b86106a 100644 --- a/include/linux/shmem_fs.h +++ b/include/linux/shmem_fs.h @@ -23,18 +23,22 @@ struct shmem_inode_info { unsigned long flags; unsigned long alloced; /* data pages alloced to file */ unsigned long swapped; /* subtotal assigned to swap */ - pgoff_t fallocend; /* highest fallocate endindex */ - struct list_head shrinklist; /* shrinkable hpage inodes */ - struct list_head swaplist; /* chain of maybes on swap */ + union { + struct offset_ctx dir_offsets; /* stable directory offsets */ + struct { + struct list_head shrinklist; /* shrinkable hpage inodes */ + struct list_head swaplist; /* chain of maybes on swap */ + }; + }; + struct timespec64 i_crtime; /* file creation time */ struct shared_policy policy; /* NUMA memory alloc policy */ struct simple_xattrs xattrs; /* list of xattrs */ + pgoff_t fallocend; /* highest fallocate endindex */ + unsigned int fsflags; /* for FS_IOC_[SG]ETFLAGS */ atomic_t stop_eviction; /* hold when working on inode */ - struct timespec64 i_crtime; /* file creation time */ - unsigned int fsflags; /* flags for FS_IOC_[SG]ETFLAGS */ #ifdef CONFIG_TMPFS_QUOTA struct dquot *i_dquot[MAXQUOTAS]; #endif - struct offset_ctx dir_offsets; /* stable entry offsets */ struct inode vfs_inode; }; diff --git a/include/linux/shrinker.h b/include/linux/shrinker.h index 224293b2dd06..1a00be90d93a 100644 --- a/include/linux/shrinker.h +++ b/include/linux/shrinker.h @@ -4,6 +4,25 @@ #include <linux/atomic.h> #include <linux/types.h> +#include <linux/refcount.h> +#include <linux/completion.h> + +#define SHRINKER_UNIT_BITS BITS_PER_LONG + +/* + * Bitmap and deferred work of shrinker::id corresponding to memcg-aware + * shrinkers, which have elements charged to the memcg. + */ +struct shrinker_info_unit { + atomic_long_t nr_deferred[SHRINKER_UNIT_BITS]; + DECLARE_BITMAP(map, SHRINKER_UNIT_BITS); +}; + +struct shrinker_info { + struct rcu_head rcu; + int map_nr_max; + struct shrinker_info_unit *unit[]; +}; /* * This struct is used to pass information from page reclaim to the shrinkers. @@ -70,6 +89,19 @@ struct shrinker { int seeks; /* seeks to recreate an obj */ unsigned flags; + /* + * The reference count of this shrinker. Registered shrinker have an + * initial refcount of 1, then the lookup operations are now allowed + * to use it via shrinker_try_get(). Later in the unregistration step, + * the initial refcount will be discarded, and will free the shrinker + * asynchronously via RCU after its refcount reaches 0. + */ + refcount_t refcount; + struct completion done; /* use to wait for refcount to reach 0 */ + struct rcu_head rcu; + + void *private_data; + /* These are for internal use */ struct list_head list; #ifdef CONFIG_MEMCG @@ -86,48 +118,39 @@ struct shrinker { }; #define DEFAULT_SEEKS 2 /* A good number if you don't know better. */ -/* Flags */ -#define SHRINKER_REGISTERED (1 << 0) -#define SHRINKER_NUMA_AWARE (1 << 1) -#define SHRINKER_MEMCG_AWARE (1 << 2) +/* Internal flags */ +#define SHRINKER_REGISTERED BIT(0) +#define SHRINKER_ALLOCATED BIT(1) + +/* Flags for users to use */ +#define SHRINKER_NUMA_AWARE BIT(2) +#define SHRINKER_MEMCG_AWARE BIT(3) /* * It just makes sense when the shrinker is also MEMCG_AWARE for now, * non-MEMCG_AWARE shrinker should not have this flag set. */ -#define SHRINKER_NONSLAB (1 << 3) +#define SHRINKER_NONSLAB BIT(4) -extern int __printf(2, 3) prealloc_shrinker(struct shrinker *shrinker, - const char *fmt, ...); -extern void register_shrinker_prepared(struct shrinker *shrinker); -extern int __printf(2, 3) register_shrinker(struct shrinker *shrinker, - const char *fmt, ...); -extern void unregister_shrinker(struct shrinker *shrinker); -extern void free_prealloced_shrinker(struct shrinker *shrinker); -extern void synchronize_shrinkers(void); +__printf(2, 3) +struct shrinker *shrinker_alloc(unsigned int flags, const char *fmt, ...); +void shrinker_register(struct shrinker *shrinker); +void shrinker_free(struct shrinker *shrinker); -#ifdef CONFIG_SHRINKER_DEBUG -extern int shrinker_debugfs_add(struct shrinker *shrinker); -extern struct dentry *shrinker_debugfs_detach(struct shrinker *shrinker, - int *debugfs_id); -extern void shrinker_debugfs_remove(struct dentry *debugfs_entry, - int debugfs_id); -extern int __printf(2, 3) shrinker_debugfs_rename(struct shrinker *shrinker, - const char *fmt, ...); -#else /* CONFIG_SHRINKER_DEBUG */ -static inline int shrinker_debugfs_add(struct shrinker *shrinker) -{ - return 0; -} -static inline struct dentry *shrinker_debugfs_detach(struct shrinker *shrinker, - int *debugfs_id) +static inline bool shrinker_try_get(struct shrinker *shrinker) { - *debugfs_id = -1; - return NULL; + return refcount_inc_not_zero(&shrinker->refcount); } -static inline void shrinker_debugfs_remove(struct dentry *debugfs_entry, - int debugfs_id) + +static inline void shrinker_put(struct shrinker *shrinker) { + if (refcount_dec_and_test(&shrinker->refcount)) + complete(&shrinker->done); } + +#ifdef CONFIG_SHRINKER_DEBUG +extern int __printf(2, 3) shrinker_debugfs_rename(struct shrinker *shrinker, + const char *fmt, ...); +#else /* CONFIG_SHRINKER_DEBUG */ static inline __printf(2, 3) int shrinker_debugfs_rename(struct shrinker *shrinker, const char *fmt, ...) { diff --git a/include/linux/userfaultfd_k.h b/include/linux/userfaultfd_k.h index ac8c6854097c..f2dc19f40d05 100644 --- a/include/linux/userfaultfd_k.h +++ b/include/linux/userfaultfd_k.h @@ -161,11 +161,22 @@ static inline bool userfaultfd_armed(struct vm_area_struct *vma) } static inline bool vma_can_userfault(struct vm_area_struct *vma, - unsigned long vm_flags) + unsigned long vm_flags, + bool wp_async) { + vm_flags &= __VM_UFFD_FLAGS; + if ((vm_flags & VM_UFFD_MINOR) && (!is_vm_hugetlb_page(vma) && !vma_is_shmem(vma))) return false; + + /* + * If wp async enabled, and WP is the only mode enabled, allow any + * memory type. + */ + if (wp_async && (vm_flags == VM_UFFD_WP)) + return true; + #ifndef CONFIG_PTE_MARKER_UFFD_WP /* * If user requested uffd-wp but not enabled pte markers for @@ -175,6 +186,8 @@ static inline bool vma_can_userfault(struct vm_area_struct *vma, if ((vm_flags & VM_UFFD_WP) && !vma_is_anonymous(vma)) return false; #endif + + /* By default, allow any of anon|shmem|hugetlb */ return vma_is_anonymous(vma) || is_vm_hugetlb_page(vma) || vma_is_shmem(vma); } @@ -197,6 +210,7 @@ extern int userfaultfd_unmap_prep(struct vm_area_struct *vma, extern void userfaultfd_unmap_complete(struct mm_struct *mm, struct list_head *uf); extern bool userfaultfd_wp_unpopulated(struct vm_area_struct *vma); +extern bool userfaultfd_wp_async(struct vm_area_struct *vma); #else /* CONFIG_USERFAULTFD */ @@ -207,6 +221,13 @@ static inline vm_fault_t handle_userfault(struct vm_fault *vmf, return VM_FAULT_SIGBUS; } +static inline long uffd_wp_range(struct vm_area_struct *vma, + unsigned long start, unsigned long len, + bool enable_wp) +{ + return false; +} + static inline bool is_mergeable_vm_userfaultfd_ctx(struct vm_area_struct *vma, struct vm_userfaultfd_ctx vm_ctx) { @@ -297,6 +318,11 @@ static inline bool userfaultfd_wp_unpopulated(struct vm_area_struct *vma) return false; } +static inline bool userfaultfd_wp_async(struct vm_area_struct *vma) +{ + return false; +} + #endif /* CONFIG_USERFAULTFD */ static inline bool userfaultfd_wp_use_markers(struct vm_area_struct *vma) diff --git a/include/linux/wait.h b/include/linux/wait.h index 5ec7739400f4..3473b663176f 100644 --- a/include/linux/wait.h +++ b/include/linux/wait.h @@ -19,10 +19,9 @@ int default_wake_function(struct wait_queue_entry *wq_entry, unsigned mode, int /* wait_queue_entry::flags */ #define WQ_FLAG_EXCLUSIVE 0x01 #define WQ_FLAG_WOKEN 0x02 -#define WQ_FLAG_BOOKMARK 0x04 -#define WQ_FLAG_CUSTOM 0x08 -#define WQ_FLAG_DONE 0x10 -#define WQ_FLAG_PRIORITY 0x20 +#define WQ_FLAG_CUSTOM 0x04 +#define WQ_FLAG_DONE 0x08 +#define WQ_FLAG_PRIORITY 0x10 /* * A single wait-queue entry structure: @@ -212,8 +211,6 @@ __remove_wait_queue(struct wait_queue_head *wq_head, struct wait_queue_entry *wq int __wake_up(struct wait_queue_head *wq_head, unsigned int mode, int nr, void *key); void __wake_up_on_current_cpu(struct wait_queue_head *wq_head, unsigned int mode, void *key); void __wake_up_locked_key(struct wait_queue_head *wq_head, unsigned int mode, void *key); -void __wake_up_locked_key_bookmark(struct wait_queue_head *wq_head, - unsigned int mode, void *key, wait_queue_entry_t *bookmark); void __wake_up_sync_key(struct wait_queue_head *wq_head, unsigned int mode, void *key); void __wake_up_locked_sync_key(struct wait_queue_head *wq_head, unsigned int mode, void *key); void __wake_up_locked(struct wait_queue_head *wq_head, unsigned int mode, int nr); diff --git a/include/trace/events/damon.h b/include/trace/events/damon.h index c79f1d4c39af..23200aabccac 100644 --- a/include/trace/events/damon.h +++ b/include/trace/events/damon.h @@ -9,12 +9,51 @@ #include <linux/types.h> #include <linux/tracepoint.h> +TRACE_EVENT_CONDITION(damos_before_apply, + + TP_PROTO(unsigned int context_idx, unsigned int scheme_idx, + unsigned int target_idx, struct damon_region *r, + unsigned int nr_regions, bool do_trace), + + TP_ARGS(context_idx, target_idx, scheme_idx, r, nr_regions, do_trace), + + TP_CONDITION(do_trace), + + TP_STRUCT__entry( + __field(unsigned int, context_idx) + __field(unsigned int, scheme_idx) + __field(unsigned long, target_idx) + __field(unsigned long, start) + __field(unsigned long, end) + __field(unsigned int, nr_accesses) + __field(unsigned int, age) + __field(unsigned int, nr_regions) + ), + + TP_fast_assign( + __entry->context_idx = context_idx; + __entry->scheme_idx = scheme_idx; + __entry->target_idx = target_idx; + __entry->start = r->ar.start; + __entry->end = r->ar.end; + __entry->nr_accesses = r->nr_accesses_bp / 10000; + __entry->age = r->age; + __entry->nr_regions = nr_regions; + ), + + TP_printk("ctx_idx=%u scheme_idx=%u target_idx=%lu nr_regions=%u %lu-%lu: %u %u", + __entry->context_idx, __entry->scheme_idx, + __entry->target_idx, __entry->nr_regions, + __entry->start, __entry->end, + __entry->nr_accesses, __entry->age) +); + TRACE_EVENT(damon_aggregated, - TP_PROTO(struct damon_target *t, unsigned int target_id, - struct damon_region *r, unsigned int nr_regions), + TP_PROTO(unsigned int target_id, struct damon_region *r, + unsigned int nr_regions), - TP_ARGS(t, target_id, r, nr_regions), + TP_ARGS(target_id, r, nr_regions), TP_STRUCT__entry( __field(unsigned long, target_id) diff --git a/include/trace/events/migrate.h b/include/trace/events/migrate.h index 061b5128f335..0190ef725b43 100644 --- a/include/trace/events/migrate.h +++ b/include/trace/events/migrate.h @@ -49,10 +49,11 @@ TRACE_EVENT(mm_migrate_pages, TP_PROTO(unsigned long succeeded, unsigned long failed, unsigned long thp_succeeded, unsigned long thp_failed, - unsigned long thp_split, enum migrate_mode mode, int reason), + unsigned long thp_split, unsigned long large_folio_split, + enum migrate_mode mode, int reason), TP_ARGS(succeeded, failed, thp_succeeded, thp_failed, - thp_split, mode, reason), + thp_split, large_folio_split, mode, reason), TP_STRUCT__entry( __field( unsigned long, succeeded) @@ -60,26 +61,29 @@ TRACE_EVENT(mm_migrate_pages, __field( unsigned long, thp_succeeded) __field( unsigned long, thp_failed) __field( unsigned long, thp_split) + __field( unsigned long, large_folio_split) __field( enum migrate_mode, mode) __field( int, reason) ), TP_fast_assign( - __entry->succeeded = succeeded; - __entry->failed = failed; - __entry->thp_succeeded = thp_succeeded; - __entry->thp_failed = thp_failed; - __entry->thp_split = thp_split; - __entry->mode = mode; - __entry->reason = reason; + __entry->succeeded = succeeded; + __entry->failed = failed; + __entry->thp_succeeded = thp_succeeded; + __entry->thp_failed = thp_failed; + __entry->thp_split = thp_split; + __entry->large_folio_split = large_folio_split; + __entry->mode = mode; + __entry->reason = reason; ), - TP_printk("nr_succeeded=%lu nr_failed=%lu nr_thp_succeeded=%lu nr_thp_failed=%lu nr_thp_split=%lu mode=%s reason=%s", + TP_printk("nr_succeeded=%lu nr_failed=%lu nr_thp_succeeded=%lu nr_thp_failed=%lu nr_thp_split=%lu nr_split=%lu mode=%s reason=%s", __entry->succeeded, __entry->failed, __entry->thp_succeeded, __entry->thp_failed, __entry->thp_split, + __entry->large_folio_split, __print_symbolic(__entry->mode, MIGRATE_MODE), __print_symbolic(__entry->reason, MIGRATE_REASON)) ); diff --git a/include/trace/events/vmscan.h b/include/trace/events/vmscan.h index d2123dd960d5..1a488c30afa5 100644 --- a/include/trace/events/vmscan.h +++ b/include/trace/events/vmscan.h @@ -285,10 +285,9 @@ TRACE_EVENT(mm_vmscan_lru_isolate, unsigned long nr_scanned, unsigned long nr_skipped, unsigned long nr_taken, - isolate_mode_t isolate_mode, int lru), - TP_ARGS(highest_zoneidx, order, nr_requested, nr_scanned, nr_skipped, nr_taken, isolate_mode, lru), + TP_ARGS(highest_zoneidx, order, nr_requested, nr_scanned, nr_skipped, nr_taken, lru), TP_STRUCT__entry( __field(int, highest_zoneidx) @@ -297,7 +296,6 @@ TRACE_EVENT(mm_vmscan_lru_isolate, __field(unsigned long, nr_scanned) __field(unsigned long, nr_skipped) __field(unsigned long, nr_taken) - __field(unsigned int, isolate_mode) __field(int, lru) ), @@ -308,7 +306,6 @@ TRACE_EVENT(mm_vmscan_lru_isolate, __entry->nr_scanned = nr_scanned; __entry->nr_skipped = nr_skipped; __entry->nr_taken = nr_taken; - __entry->isolate_mode = (__force unsigned int)isolate_mode; __entry->lru = lru; ), @@ -316,8 +313,7 @@ TRACE_EVENT(mm_vmscan_lru_isolate, * classzone is previous name of the highest_zoneidx. * Reason not to change it is the ABI requirement of the tracepoint. */ - TP_printk("isolate_mode=%d classzone=%d order=%d nr_requested=%lu nr_scanned=%lu nr_skipped=%lu nr_taken=%lu lru=%s", - __entry->isolate_mode, + TP_printk("classzone=%d order=%d nr_requested=%lu nr_scanned=%lu nr_skipped=%lu nr_taken=%lu lru=%s", __entry->highest_zoneidx, __entry->order, __entry->nr_requested, diff --git a/include/uapi/linux/fs.h b/include/uapi/linux/fs.h index b7b56871029c..da43810b7485 100644 --- a/include/uapi/linux/fs.h +++ b/include/uapi/linux/fs.h @@ -305,4 +305,63 @@ typedef int __bitwise __kernel_rwf_t; #define RWF_SUPPORTED (RWF_HIPRI | RWF_DSYNC | RWF_SYNC | RWF_NOWAIT |\ RWF_APPEND) +/* Pagemap ioctl */ +#define PAGEMAP_SCAN _IOWR('f', 16, struct pm_scan_arg) + +/* Bitmasks provided in pm_scan_args masks and reported in page_region.categories. */ +#define PAGE_IS_WPALLOWED (1 << 0) +#define PAGE_IS_WRITTEN (1 << 1) +#define PAGE_IS_FILE (1 << 2) +#define PAGE_IS_PRESENT (1 << 3) +#define PAGE_IS_SWAPPED (1 << 4) +#define PAGE_IS_PFNZERO (1 << 5) +#define PAGE_IS_HUGE (1 << 6) + +/* + * struct page_region - Page region with flags + * @start: Start of the region + * @end: End of the region (exclusive) + * @categories: PAGE_IS_* category bitmask for the region + */ +struct page_region { + __u64 start; + __u64 end; + __u64 categories; +}; + +/* Flags for PAGEMAP_SCAN ioctl */ +#define PM_SCAN_WP_MATCHING (1 << 0) /* Write protect the pages matched. */ +#define PM_SCAN_CHECK_WPASYNC (1 << 1) /* Abort the scan when a non-WP-enabled page is found. */ + +/* + * struct pm_scan_arg - Pagemap ioctl argument + * @size: Size of the structure + * @flags: Flags for the IOCTL + * @start: Starting address of the region + * @end: Ending address of the region + * @walk_end Address where the scan stopped (written by kernel). + * walk_end == end (address tags cleared) informs that the scan completed on entire range. + * @vec: Address of page_region struct array for output + * @vec_len: Length of the page_region struct array + * @max_pages: Optional limit for number of returned pages (0 = disabled) + * @category_inverted: PAGE_IS_* categories which values match if 0 instead of 1 + * @category_mask: Skip pages for which any category doesn't match + * @category_anyof_mask: Skip pages for which no category matches + * @return_mask: PAGE_IS_* categories that are to be reported in `page_region`s returned + */ +struct pm_scan_arg { + __u64 size; + __u64 flags; + __u64 start; + __u64 end; + __u64 walk_end; + __u64 vec; + __u64 vec_len; + __u64 max_pages; + __u64 category_inverted; + __u64 category_mask; + __u64 category_anyof_mask; + __u64 return_mask; +}; + #endif /* _UAPI_LINUX_FS_H */ diff --git a/include/uapi/linux/mempolicy.h b/include/uapi/linux/mempolicy.h index 046d0ccba4cd..a8963f7ef4c2 100644 --- a/include/uapi/linux/mempolicy.h +++ b/include/uapi/linux/mempolicy.h @@ -48,7 +48,7 @@ enum { #define MPOL_MF_MOVE (1<<1) /* Move pages owned by this process to conform to policy */ #define MPOL_MF_MOVE_ALL (1<<2) /* Move every page to conform to policy */ -#define MPOL_MF_LAZY (1<<3) /* Modifies '_MOVE: lazy migrate on fault */ +#define MPOL_MF_LAZY (1<<3) /* UNSUPPORTED FLAG: Lazy migrate on fault */ #define MPOL_MF_INTERNAL (1<<4) /* Internal flags start here */ #define MPOL_MF_VALID (MPOL_MF_STRICT | \ diff --git a/include/uapi/linux/prctl.h b/include/uapi/linux/prctl.h index 3c36aeade991..370ed14b1ae0 100644 --- a/include/uapi/linux/prctl.h +++ b/include/uapi/linux/prctl.h @@ -283,7 +283,8 @@ struct prctl_mm_map { /* Memory deny write / execute */ #define PR_SET_MDWE 65 -# define PR_MDWE_REFUSE_EXEC_GAIN 1 +# define PR_MDWE_REFUSE_EXEC_GAIN (1UL << 0) +# define PR_MDWE_NO_INHERIT (1UL << 1) #define PR_GET_MDWE 66 diff --git a/include/uapi/linux/userfaultfd.h b/include/uapi/linux/userfaultfd.h index 62151706c5a3..0dbc81015018 100644 --- a/include/uapi/linux/userfaultfd.h +++ b/include/uapi/linux/userfaultfd.h @@ -40,7 +40,8 @@ UFFD_FEATURE_EXACT_ADDRESS | \ UFFD_FEATURE_WP_HUGETLBFS_SHMEM | \ UFFD_FEATURE_WP_UNPOPULATED | \ - UFFD_FEATURE_POISON) + UFFD_FEATURE_POISON | \ + UFFD_FEATURE_WP_ASYNC) #define UFFD_API_IOCTLS \ ((__u64)1 << _UFFDIO_REGISTER | \ (__u64)1 << _UFFDIO_UNREGISTER | \ @@ -216,6 +217,11 @@ struct uffdio_api { * (i.e. empty ptes). This will be the default behavior for shmem * & hugetlbfs, so this flag only affects anonymous memory behavior * when userfault write-protection mode is registered. + * + * UFFD_FEATURE_WP_ASYNC indicates that userfaultfd write-protection + * asynchronous mode is supported in which the write fault is + * automatically resolved and write-protection is un-set. + * It implies UFFD_FEATURE_WP_UNPOPULATED. */ #define UFFD_FEATURE_PAGEFAULT_FLAG_WP (1<<0) #define UFFD_FEATURE_EVENT_FORK (1<<1) @@ -232,6 +238,7 @@ struct uffdio_api { #define UFFD_FEATURE_WP_HUGETLBFS_SHMEM (1<<12) #define UFFD_FEATURE_WP_UNPOPULATED (1<<13) #define UFFD_FEATURE_POISON (1<<14) +#define UFFD_FEATURE_WP_ASYNC (1<<15) __u64 features; __u64 ioctls; |