diff options
Diffstat (limited to 'include')
51 files changed, 1064 insertions, 717 deletions
diff --git a/include/asm-generic/cacheflush.h b/include/asm-generic/cacheflush.h index f46258d1a080..84ec53ccc450 100644 --- a/include/asm-generic/cacheflush.h +++ b/include/asm-generic/cacheflush.h @@ -77,13 +77,6 @@ static inline void flush_icache_range(unsigned long start, unsigned long end) #define flush_icache_user_range flush_icache_range #endif -#ifndef flush_icache_page -static inline void flush_icache_page(struct vm_area_struct *vma, - struct page *page) -{ -} -#endif - #ifndef flush_icache_user_page static inline void flush_icache_user_page(struct vm_area_struct *vma, struct page *page, diff --git a/include/asm-generic/io.h b/include/asm-generic/io.h index 587e7e9b9a37..bac63e874c7b 100644 --- a/include/asm-generic/io.h +++ b/include/asm-generic/io.h @@ -1047,41 +1047,22 @@ static inline void iounmap(volatile void __iomem *addr) #elif defined(CONFIG_GENERIC_IOREMAP) #include <linux/pgtable.h> -/* - * Arch code can implement the following two hooks when using GENERIC_IOREMAP - * ioremap_allowed() return a bool, - * - true means continue to remap - * - false means skip remap and return directly - * iounmap_allowed() return a bool, - * - true means continue to vunmap - * - false means skip vunmap and return directly - */ -#ifndef ioremap_allowed -#define ioremap_allowed ioremap_allowed -static inline bool ioremap_allowed(phys_addr_t phys_addr, size_t size, - unsigned long prot) -{ - return true; -} -#endif - -#ifndef iounmap_allowed -#define iounmap_allowed iounmap_allowed -static inline bool iounmap_allowed(void *addr) -{ - return true; -} -#endif +void __iomem *generic_ioremap_prot(phys_addr_t phys_addr, size_t size, + pgprot_t prot); void __iomem *ioremap_prot(phys_addr_t phys_addr, size_t size, unsigned long prot); void iounmap(volatile void __iomem *addr); +void generic_iounmap(volatile void __iomem *addr); +#ifndef ioremap +#define ioremap ioremap static inline void __iomem *ioremap(phys_addr_t addr, size_t size) { /* _PAGE_IOREMAP needs to be supplied by the architecture */ return ioremap_prot(addr, size, _PAGE_IOREMAP); } +#endif #endif /* !CONFIG_MMU || CONFIG_GENERIC_IOREMAP */ #ifndef ioremap_wc diff --git a/include/asm-generic/iomap.h b/include/asm-generic/iomap.h index 08237ae8b840..196087a8126e 100644 --- a/include/asm-generic/iomap.h +++ b/include/asm-generic/iomap.h @@ -93,15 +93,15 @@ extern void __iomem *ioport_map(unsigned long port, unsigned int nr); extern void ioport_unmap(void __iomem *); #endif -#ifndef ARCH_HAS_IOREMAP_WC +#ifndef ioremap_wc #define ioremap_wc ioremap #endif -#ifndef ARCH_HAS_IOREMAP_WT +#ifndef ioremap_wt #define ioremap_wt ioremap #endif -#ifndef ARCH_HAS_IOREMAP_NP +#ifndef ioremap_np /* See the comment in asm-generic/io.h about ioremap_np(). */ #define ioremap_np ioremap_np static inline void __iomem *ioremap_np(phys_addr_t offset, size_t size) diff --git a/include/asm-generic/pgalloc.h b/include/asm-generic/pgalloc.h index a7cf825befae..c75d4a753849 100644 --- a/include/asm-generic/pgalloc.h +++ b/include/asm-generic/pgalloc.h @@ -8,7 +8,7 @@ #define GFP_PGTABLE_USER (GFP_PGTABLE_KERNEL | __GFP_ACCOUNT) /** - * __pte_alloc_one_kernel - allocate a page for PTE-level kernel page table + * __pte_alloc_one_kernel - allocate memory for a PTE-level kernel page table * @mm: the mm_struct of the current context * * This function is intended for architectures that need @@ -18,12 +18,17 @@ */ static inline pte_t *__pte_alloc_one_kernel(struct mm_struct *mm) { - return (pte_t *)__get_free_page(GFP_PGTABLE_KERNEL); + struct ptdesc *ptdesc = pagetable_alloc(GFP_PGTABLE_KERNEL & + ~__GFP_HIGHMEM, 0); + + if (!ptdesc) + return NULL; + return ptdesc_address(ptdesc); } #ifndef __HAVE_ARCH_PTE_ALLOC_ONE_KERNEL /** - * pte_alloc_one_kernel - allocate a page for PTE-level kernel page table + * pte_alloc_one_kernel - allocate memory for a PTE-level kernel page table * @mm: the mm_struct of the current context * * Return: pointer to the allocated memory or %NULL on error @@ -35,40 +40,40 @@ static inline pte_t *pte_alloc_one_kernel(struct mm_struct *mm) #endif /** - * pte_free_kernel - free PTE-level kernel page table page + * pte_free_kernel - free PTE-level kernel page table memory * @mm: the mm_struct of the current context * @pte: pointer to the memory containing the page table */ static inline void pte_free_kernel(struct mm_struct *mm, pte_t *pte) { - free_page((unsigned long)pte); + pagetable_free(virt_to_ptdesc(pte)); } /** - * __pte_alloc_one - allocate a page for PTE-level user page table + * __pte_alloc_one - allocate memory for a PTE-level user page table * @mm: the mm_struct of the current context * @gfp: GFP flags to use for the allocation * - * Allocates a page and runs the pgtable_pte_page_ctor(). + * Allocate memory for a page table and ptdesc and runs pagetable_pte_ctor(). * * This function is intended for architectures that need * anything beyond simple page allocation or must have custom GFP flags. * - * Return: `struct page` initialized as page table or %NULL on error + * Return: `struct page` referencing the ptdesc or %NULL on error */ static inline pgtable_t __pte_alloc_one(struct mm_struct *mm, gfp_t gfp) { - struct page *pte; + struct ptdesc *ptdesc; - pte = alloc_page(gfp); - if (!pte) + ptdesc = pagetable_alloc(gfp, 0); + if (!ptdesc) return NULL; - if (!pgtable_pte_page_ctor(pte)) { - __free_page(pte); + if (!pagetable_pte_ctor(ptdesc)) { + pagetable_free(ptdesc); return NULL; } - return pte; + return ptdesc_page(ptdesc); } #ifndef __HAVE_ARCH_PTE_ALLOC_ONE @@ -76,9 +81,9 @@ static inline pgtable_t __pte_alloc_one(struct mm_struct *mm, gfp_t gfp) * pte_alloc_one - allocate a page for PTE-level user page table * @mm: the mm_struct of the current context * - * Allocates a page and runs the pgtable_pte_page_ctor(). + * Allocate memory for a page table and ptdesc and runs pagetable_pte_ctor(). * - * Return: `struct page` initialized as page table or %NULL on error + * Return: `struct page` referencing the ptdesc or %NULL on error */ static inline pgtable_t pte_alloc_one(struct mm_struct *mm) { @@ -92,14 +97,16 @@ static inline pgtable_t pte_alloc_one(struct mm_struct *mm) */ /** - * pte_free - free PTE-level user page table page + * pte_free - free PTE-level user page table memory * @mm: the mm_struct of the current context - * @pte_page: the `struct page` representing the page table + * @pte_page: the `struct page` referencing the ptdesc */ static inline void pte_free(struct mm_struct *mm, struct page *pte_page) { - pgtable_pte_page_dtor(pte_page); - __free_page(pte_page); + struct ptdesc *ptdesc = page_ptdesc(pte_page); + + pagetable_pte_dtor(ptdesc); + pagetable_free(ptdesc); } @@ -107,10 +114,11 @@ static inline void pte_free(struct mm_struct *mm, struct page *pte_page) #ifndef __HAVE_ARCH_PMD_ALLOC_ONE /** - * pmd_alloc_one - allocate a page for PMD-level page table + * pmd_alloc_one - allocate memory for a PMD-level page table * @mm: the mm_struct of the current context * - * Allocates a page and runs the pgtable_pmd_page_ctor(). + * Allocate memory for a page table and ptdesc and runs pagetable_pmd_ctor(). + * * Allocations use %GFP_PGTABLE_USER in user context and * %GFP_PGTABLE_KERNEL in kernel context. * @@ -118,28 +126,30 @@ static inline void pte_free(struct mm_struct *mm, struct page *pte_page) */ static inline pmd_t *pmd_alloc_one(struct mm_struct *mm, unsigned long addr) { - struct page *page; + struct ptdesc *ptdesc; gfp_t gfp = GFP_PGTABLE_USER; if (mm == &init_mm) gfp = GFP_PGTABLE_KERNEL; - page = alloc_page(gfp); - if (!page) + ptdesc = pagetable_alloc(gfp, 0); + if (!ptdesc) return NULL; - if (!pgtable_pmd_page_ctor(page)) { - __free_page(page); + if (!pagetable_pmd_ctor(ptdesc)) { + pagetable_free(ptdesc); return NULL; } - return (pmd_t *)page_address(page); + return ptdesc_address(ptdesc); } #endif #ifndef __HAVE_ARCH_PMD_FREE static inline void pmd_free(struct mm_struct *mm, pmd_t *pmd) { + struct ptdesc *ptdesc = virt_to_ptdesc(pmd); + BUG_ON((unsigned long)pmd & (PAGE_SIZE-1)); - pgtable_pmd_page_dtor(virt_to_page(pmd)); - free_page((unsigned long)pmd); + pagetable_pmd_dtor(ptdesc); + pagetable_free(ptdesc); } #endif @@ -150,19 +160,25 @@ static inline void pmd_free(struct mm_struct *mm, pmd_t *pmd) static inline pud_t *__pud_alloc_one(struct mm_struct *mm, unsigned long addr) { gfp_t gfp = GFP_PGTABLE_USER; + struct ptdesc *ptdesc; if (mm == &init_mm) gfp = GFP_PGTABLE_KERNEL; - return (pud_t *)get_zeroed_page(gfp); + gfp &= ~__GFP_HIGHMEM; + + ptdesc = pagetable_alloc(gfp, 0); + if (!ptdesc) + return NULL; + return ptdesc_address(ptdesc); } #ifndef __HAVE_ARCH_PUD_ALLOC_ONE /** - * pud_alloc_one - allocate a page for PUD-level page table + * pud_alloc_one - allocate memory for a PUD-level page table * @mm: the mm_struct of the current context * - * Allocates a page using %GFP_PGTABLE_USER for user context and - * %GFP_PGTABLE_KERNEL for kernel context. + * Allocate memory for a page table using %GFP_PGTABLE_USER for user context + * and %GFP_PGTABLE_KERNEL for kernel context. * * Return: pointer to the allocated memory or %NULL on error */ @@ -175,7 +191,7 @@ 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) { BUG_ON((unsigned long)pud & (PAGE_SIZE-1)); - free_page((unsigned long)pud); + pagetable_free(virt_to_ptdesc(pud)); } #ifndef __HAVE_ARCH_PUD_FREE @@ -190,7 +206,7 @@ static inline void pud_free(struct mm_struct *mm, pud_t *pud) #ifndef __HAVE_ARCH_PGD_FREE static inline void pgd_free(struct mm_struct *mm, pgd_t *pgd) { - free_page((unsigned long)pgd); + pagetable_free(virt_to_ptdesc(pgd)); } #endif diff --git a/include/asm-generic/tlb.h b/include/asm-generic/tlb.h index b46617207c93..129a3a759976 100644 --- a/include/asm-generic/tlb.h +++ b/include/asm-generic/tlb.h @@ -456,7 +456,6 @@ static inline void tlb_flush_mmu_tlbonly(struct mmu_gather *tlb) return; tlb_flush(tlb); - mmu_notifier_invalidate_range(tlb->mm, tlb->start, tlb->end); __tlb_reset_range(tlb); } @@ -481,6 +480,17 @@ static inline void tlb_remove_page(struct mmu_gather *tlb, struct page *page) return tlb_remove_page_size(tlb, page, PAGE_SIZE); } +static inline void tlb_remove_ptdesc(struct mmu_gather *tlb, void *pt) +{ + tlb_remove_table(tlb, pt); +} + +/* Like tlb_remove_ptdesc, but for page-like page directories. */ +static inline void tlb_remove_page_ptdesc(struct mmu_gather *tlb, struct ptdesc *pt) +{ + tlb_remove_page(tlb, ptdesc_page(pt)); +} + static inline void tlb_change_page_size(struct mmu_gather *tlb, unsigned int page_size) { diff --git a/include/linux/backing-dev.h b/include/linux/backing-dev.h index fbad4fcd408e..1a97277f99b1 100644 --- a/include/linux/backing-dev.h +++ b/include/linux/backing-dev.h @@ -46,7 +46,6 @@ extern spinlock_t bdi_lock; extern struct list_head bdi_list; extern struct workqueue_struct *bdi_wq; -extern struct workqueue_struct *bdi_async_bio_wq; static inline bool wb_has_dirty_io(struct bdi_writeback *wb) { diff --git a/include/linux/bio.h b/include/linux/bio.h index 11984ed29cb8..e8767f165bad 100644 --- a/include/linux/bio.h +++ b/include/linux/bio.h @@ -253,6 +253,11 @@ static inline struct page *bio_first_page_all(struct bio *bio) return bio_first_bvec_all(bio)->bv_page; } +static inline struct folio *bio_first_folio_all(struct bio *bio) +{ + return page_folio(bio_first_page_all(bio)); +} + static inline struct bio_vec *bio_last_bvec_all(struct bio *bio) { WARN_ON_ONCE(bio_flagged(bio, BIO_CLONED)); diff --git a/include/linux/buffer_head.h b/include/linux/buffer_head.h index 6cb3e9af78c9..06566aee94ca 100644 --- a/include/linux/buffer_head.h +++ b/include/linux/buffer_head.h @@ -194,8 +194,6 @@ void buffer_check_dirty_writeback(struct folio *folio, void mark_buffer_dirty(struct buffer_head *bh); void mark_buffer_write_io_error(struct buffer_head *bh); void touch_buffer(struct buffer_head *bh); -void set_bh_page(struct buffer_head *bh, - struct page *page, unsigned long offset); void folio_set_bh(struct buffer_head *bh, struct folio *folio, unsigned long offset); bool try_to_free_buffers(struct folio *); @@ -288,7 +286,7 @@ int cont_write_begin(struct file *, struct address_space *, loff_t, unsigned, struct page **, void **, get_block_t *, loff_t *); int generic_cont_expand_simple(struct inode *inode, loff_t size); -int block_commit_write(struct page *page, unsigned from, unsigned to); +void block_commit_write(struct page *page, unsigned int from, unsigned int to); int block_page_mkwrite(struct vm_area_struct *vma, struct vm_fault *vmf, get_block_t get_block); /* Convert errno to return value from ->page_mkwrite() call */ diff --git a/include/linux/cacheflush.h b/include/linux/cacheflush.h index a6189d21f2ba..55f297b2c23f 100644 --- a/include/linux/cacheflush.h +++ b/include/linux/cacheflush.h @@ -7,14 +7,23 @@ struct folio; #if ARCH_IMPLEMENTS_FLUSH_DCACHE_PAGE -#ifndef ARCH_IMPLEMENTS_FLUSH_DCACHE_FOLIO +#ifndef flush_dcache_folio void flush_dcache_folio(struct folio *folio); #endif #else static inline void flush_dcache_folio(struct folio *folio) { } -#define ARCH_IMPLEMENTS_FLUSH_DCACHE_FOLIO 0 +#define flush_dcache_folio flush_dcache_folio #endif /* ARCH_IMPLEMENTS_FLUSH_DCACHE_PAGE */ +#ifndef flush_icache_pages +static inline void flush_icache_pages(struct vm_area_struct *vma, + struct page *page, unsigned int nr) +{ +} +#endif + +#define flush_icache_page(vma, page) flush_icache_pages(vma, page, 1) + #endif /* _LINUX_CACHEFLUSH_H */ diff --git a/include/linux/damon.h b/include/linux/damon.h index d5d4d19928e0..ae2664d1d5f1 100644 --- a/include/linux/damon.h +++ b/include/linux/damon.h @@ -226,16 +226,26 @@ struct damos_stat { * enum damos_filter_type - Type of memory for &struct damos_filter * @DAMOS_FILTER_TYPE_ANON: Anonymous pages. * @DAMOS_FILTER_TYPE_MEMCG: Specific memcg's pages. + * @DAMOS_FILTER_TYPE_ADDR: Address range. + * @DAMOS_FILTER_TYPE_TARGET: Data Access Monitoring target. * @NR_DAMOS_FILTER_TYPES: Number of filter types. * - * The support of each filter type is up to running &struct damon_operations. - * &enum DAMON_OPS_PADDR is supporting all filter types, while - * &enum DAMON_OPS_VADDR and &enum DAMON_OPS_FVADDR are not supporting any - * filter types. + * The anon pages type and memcg type filters are handled by underlying + * &struct damon_operations as a part of scheme action trying, and therefore + * accounted as 'tried'. In contrast, other types are handled by core layer + * before trying of the action and therefore not accounted as 'tried'. + * + * The support of the filters that handled by &struct damon_operations depend + * on the running &struct damon_operations. + * &enum DAMON_OPS_PADDR supports both anon pages type and memcg type filters, + * while &enum DAMON_OPS_VADDR and &enum DAMON_OPS_FVADDR don't support any of + * the two types. */ enum damos_filter_type { DAMOS_FILTER_TYPE_ANON, DAMOS_FILTER_TYPE_MEMCG, + DAMOS_FILTER_TYPE_ADDR, + DAMOS_FILTER_TYPE_TARGET, NR_DAMOS_FILTER_TYPES, }; @@ -244,18 +254,24 @@ enum damos_filter_type { * @type: Type of the page. * @matching: If the matching page should filtered out or in. * @memcg_id: Memcg id of the question if @type is DAMOS_FILTER_MEMCG. + * @addr_range: Address range if @type is DAMOS_FILTER_TYPE_ADDR. + * @target_idx: Index of the &struct damon_target of + * &damon_ctx->adaptive_targets if @type is + * DAMOS_FILTER_TYPE_TARGET. * @list: List head for siblings. * * Before applying the &damos->action to a memory region, DAMOS checks if each * page of the region matches to this and avoid applying the action if so. - * Note that the check support is up to &struct damon_operations - * implementation. + * Support of each filter type depends on the running &struct damon_operations + * and the type. Refer to &enum damos_filter_type for more detai. */ struct damos_filter { enum damos_filter_type type; bool matching; union { unsigned short memcg_id; + struct damon_addr_range addr_range; + int target_idx; }; struct list_head list; }; diff --git a/include/linux/dax.h b/include/linux/dax.h index 261944ec0887..22cd9902345d 100644 --- a/include/linux/dax.h +++ b/include/linux/dax.h @@ -241,10 +241,10 @@ void dax_flush(struct dax_device *dax_dev, void *addr, size_t size); ssize_t dax_iomap_rw(struct kiocb *iocb, struct iov_iter *iter, const struct iomap_ops *ops); -vm_fault_t dax_iomap_fault(struct vm_fault *vmf, enum page_entry_size pe_size, +vm_fault_t dax_iomap_fault(struct vm_fault *vmf, unsigned int order, pfn_t *pfnp, int *errp, const struct iomap_ops *ops); vm_fault_t dax_finish_sync_fault(struct vm_fault *vmf, - enum page_entry_size pe_size, pfn_t pfn); + unsigned int order, pfn_t pfn); int dax_delete_mapping_entry(struct address_space *mapping, pgoff_t index); int dax_invalidate_mapping_entry_sync(struct address_space *mapping, pgoff_t index); diff --git a/include/linux/frontswap.h b/include/linux/frontswap.h deleted file mode 100644 index eaa0ac5f9003..000000000000 --- a/include/linux/frontswap.h +++ /dev/null @@ -1,91 +0,0 @@ -/* SPDX-License-Identifier: GPL-2.0 */ -#ifndef _LINUX_FRONTSWAP_H -#define _LINUX_FRONTSWAP_H - -#include <linux/swap.h> -#include <linux/mm.h> -#include <linux/bitops.h> -#include <linux/jump_label.h> - -struct frontswap_ops { - void (*init)(unsigned); /* this swap type was just swapon'ed */ - int (*store)(unsigned, pgoff_t, struct page *); /* store a page */ - int (*load)(unsigned, pgoff_t, struct page *, bool *); /* load a page */ - void (*invalidate_page)(unsigned, pgoff_t); /* page no longer needed */ - void (*invalidate_area)(unsigned); /* swap type just swapoff'ed */ -}; - -int frontswap_register_ops(const struct frontswap_ops *ops); - -extern void frontswap_init(unsigned type, unsigned long *map); -extern int __frontswap_store(struct page *page); -extern int __frontswap_load(struct page *page); -extern void __frontswap_invalidate_page(unsigned, pgoff_t); -extern void __frontswap_invalidate_area(unsigned); - -#ifdef CONFIG_FRONTSWAP -extern struct static_key_false frontswap_enabled_key; - -static inline bool frontswap_enabled(void) -{ - return static_branch_unlikely(&frontswap_enabled_key); -} - -static inline void frontswap_map_set(struct swap_info_struct *p, - unsigned long *map) -{ - p->frontswap_map = map; -} - -static inline unsigned long *frontswap_map_get(struct swap_info_struct *p) -{ - return p->frontswap_map; -} -#else -/* all inline routines become no-ops and all externs are ignored */ - -static inline bool frontswap_enabled(void) -{ - return false; -} - -static inline void frontswap_map_set(struct swap_info_struct *p, - unsigned long *map) -{ -} - -static inline unsigned long *frontswap_map_get(struct swap_info_struct *p) -{ - return NULL; -} -#endif - -static inline int frontswap_store(struct page *page) -{ - if (frontswap_enabled()) - return __frontswap_store(page); - - return -1; -} - -static inline int frontswap_load(struct page *page) -{ - if (frontswap_enabled()) - return __frontswap_load(page); - - return -1; -} - -static inline void frontswap_invalidate_page(unsigned type, pgoff_t offset) -{ - if (frontswap_enabled()) - __frontswap_invalidate_page(type, offset); -} - -static inline void frontswap_invalidate_area(unsigned type) -{ - if (frontswap_enabled()) - __frontswap_invalidate_area(type); -} - -#endif /* _LINUX_FRONTSWAP_H */ diff --git a/include/linux/fs.h b/include/linux/fs.h index dda08d973639..c8ff4156a0a1 100644 --- a/include/linux/fs.h +++ b/include/linux/fs.h @@ -478,11 +478,11 @@ struct address_space { atomic_t nr_thps; #endif struct rb_root_cached i_mmap; - struct rw_semaphore i_mmap_rwsem; unsigned long nrpages; pgoff_t writeback_index; const struct address_space_operations *a_ops; unsigned long flags; + struct rw_semaphore i_mmap_rwsem; errseq_t wb_err; spinlock_t private_lock; struct list_head private_list; diff --git a/include/linux/highmem.h b/include/linux/highmem.h index 68da30625a6c..99c474de800d 100644 --- a/include/linux/highmem.h +++ b/include/linux/highmem.h @@ -439,6 +439,50 @@ static inline void memzero_page(struct page *page, size_t offset, size_t len) kunmap_local(addr); } +static inline void memcpy_from_folio(char *to, struct folio *folio, + size_t offset, size_t len) +{ + VM_BUG_ON(offset + len > folio_size(folio)); + + do { + const char *from = kmap_local_folio(folio, offset); + size_t chunk = len; + + if (folio_test_highmem(folio) && + chunk > PAGE_SIZE - offset_in_page(offset)) + chunk = PAGE_SIZE - offset_in_page(offset); + memcpy(to, from, chunk); + kunmap_local(from); + + from += chunk; + offset += chunk; + len -= chunk; + } while (len > 0); +} + +static inline void memcpy_to_folio(struct folio *folio, size_t offset, + const char *from, size_t len) +{ + VM_BUG_ON(offset + len > folio_size(folio)); + + do { + char *to = kmap_local_folio(folio, offset); + size_t chunk = len; + + if (folio_test_highmem(folio) && + chunk > PAGE_SIZE - offset_in_page(offset)) + chunk = PAGE_SIZE - offset_in_page(offset); + memcpy(to, from, chunk); + kunmap_local(to); + + from += chunk; + offset += chunk; + len -= chunk; + } while (len > 0); + + flush_dcache_folio(folio); +} + /** * memcpy_from_file_folio - Copy some bytes from a file folio. * @to: The destination buffer. diff --git a/include/linux/huge_mm.h b/include/linux/huge_mm.h index e718dbe928ba..fa0350b0812a 100644 --- a/include/linux/huge_mm.h +++ b/include/linux/huge_mm.h @@ -140,9 +140,7 @@ bool hugepage_vma_check(struct vm_area_struct *vma, unsigned long vm_flags, unsigned long thp_get_unmapped_area(struct file *filp, unsigned long addr, unsigned long len, unsigned long pgoff, unsigned long flags); -void prep_transhuge_page(struct page *page); -void free_transhuge_page(struct page *page); - +void folio_prep_large_rmappable(struct folio *folio); bool can_split_folio(struct folio *folio, int *pextra_pins); int split_huge_page_to_list(struct page *page, struct list_head *list); static inline int split_huge_page(struct page *page) @@ -282,7 +280,7 @@ static inline bool hugepage_vma_check(struct vm_area_struct *vma, return false; } -static inline void prep_transhuge_page(struct page *page) {} +static inline void folio_prep_large_rmappable(struct folio *folio) {} #define transparent_hugepage_flags 0UL diff --git a/include/linux/hugetlb.h b/include/linux/hugetlb.h index ca3c8e10f24a..5b2626063f4f 100644 --- a/include/linux/hugetlb.h +++ b/include/linux/hugetlb.h @@ -26,6 +26,8 @@ typedef struct { unsigned long pd; } hugepd_t; #define __hugepd(x) ((hugepd_t) { (x) }) #endif +void free_huge_folio(struct folio *folio); + #ifdef CONFIG_HUGETLB_PAGE #include <linux/mempolicy.h> @@ -131,10 +133,8 @@ int move_hugetlb_page_tables(struct vm_area_struct *vma, int copy_hugetlb_page_range(struct mm_struct *, struct mm_struct *, struct vm_area_struct *, struct vm_area_struct *); struct page *hugetlb_follow_page_mask(struct vm_area_struct *vma, - unsigned long address, unsigned int flags); -long follow_hugetlb_page(struct mm_struct *, struct vm_area_struct *, - struct page **, unsigned long *, unsigned long *, - long, unsigned int, int *); + unsigned long address, unsigned int flags, + unsigned int *page_mask); void unmap_hugepage_range(struct vm_area_struct *, unsigned long, unsigned long, struct page *, zap_flags_t); @@ -167,7 +167,6 @@ int get_huge_page_for_hwpoison(unsigned long pfn, int flags, bool *migratable_cleared); void folio_putback_active_hugetlb(struct folio *folio); void move_hugetlb_state(struct folio *old_folio, struct folio *new_folio, int reason); -void free_huge_page(struct page *page); void hugetlb_fix_reserve_counts(struct inode *inode); extern struct mutex *hugetlb_fault_mutex_table; u32 hugetlb_fault_mutex_hash(struct address_space *mapping, pgoff_t idx); @@ -297,21 +296,13 @@ static inline void adjust_range_if_pmd_sharing_possible( { } -static inline struct page *hugetlb_follow_page_mask(struct vm_area_struct *vma, - unsigned long address, unsigned int flags) +static inline struct page *hugetlb_follow_page_mask( + struct vm_area_struct *vma, unsigned long address, unsigned int flags, + unsigned int *page_mask) { BUILD_BUG(); /* should never be compiled in if !CONFIG_HUGETLB_PAGE*/ } -static inline long follow_hugetlb_page(struct mm_struct *mm, - struct vm_area_struct *vma, struct page **pages, - unsigned long *position, unsigned long *nr_pages, - long i, unsigned int flags, int *nonblocking) -{ - BUG(); - return 0; -} - static inline int copy_hugetlb_page_range(struct mm_struct *dst, struct mm_struct *src, struct vm_area_struct *dst_vma, @@ -851,11 +842,6 @@ static inline struct hstate *folio_hstate(struct folio *folio) return size_to_hstate(folio_size(folio)); } -static inline struct hstate *page_hstate(struct page *page) -{ - return folio_hstate(page_folio(page)); -} - static inline unsigned hstate_index_to_shift(unsigned index) { return hstates[index].order + PAGE_SHIFT; @@ -1007,6 +993,11 @@ void hugetlb_register_node(struct node *node); void hugetlb_unregister_node(struct node *node); #endif +/* + * Check if a given raw @page in a hugepage is HWPOISON. + */ +bool is_raw_hwpoison_page_in_hugepage(struct page *page); + #else /* CONFIG_HUGETLB_PAGE */ struct hstate {}; @@ -1067,11 +1058,6 @@ static inline struct hstate *folio_hstate(struct folio *folio) return NULL; } -static inline struct hstate *page_hstate(struct page *page) -{ - return NULL; -} - static inline struct hstate *size_to_hstate(unsigned long size) { return NULL; diff --git a/include/linux/ioremap.h b/include/linux/ioremap.h new file mode 100644 index 000000000000..f0e99fc7dd8b --- /dev/null +++ b/include/linux/ioremap.h @@ -0,0 +1,30 @@ +/* SPDX-License-Identifier: GPL-2.0 */ +#ifndef _LINUX_IOREMAP_H +#define _LINUX_IOREMAP_H + +#include <linux/kasan.h> +#include <asm/pgtable.h> + +#if defined(CONFIG_HAS_IOMEM) || defined(CONFIG_GENERIC_IOREMAP) +/* + * Ioremap often, but not always uses the generic vmalloc area. E.g on + * Power ARCH, it could have different ioremap space. + */ +#ifndef IOREMAP_START +#define IOREMAP_START VMALLOC_START +#define IOREMAP_END VMALLOC_END +#endif +static inline bool is_ioremap_addr(const void *x) +{ + unsigned long addr = (unsigned long)kasan_reset_tag(x); + + return addr >= IOREMAP_START && addr < IOREMAP_END; +} +#else +static inline bool is_ioremap_addr(const void *x) +{ + return false; +} +#endif + +#endif /* _LINUX_IOREMAP_H */ diff --git a/include/linux/kfence.h b/include/linux/kfence.h index 726857a4b680..401af4757514 100644 --- a/include/linux/kfence.h +++ b/include/linux/kfence.h @@ -59,15 +59,16 @@ static __always_inline bool is_kfence_address(const void *addr) } /** - * kfence_alloc_pool() - allocate the KFENCE pool via memblock + * kfence_alloc_pool_and_metadata() - allocate the KFENCE pool and KFENCE + * metadata via memblock */ -void __init kfence_alloc_pool(void); +void __init kfence_alloc_pool_and_metadata(void); /** * kfence_init() - perform KFENCE initialization at boot time * - * Requires that kfence_alloc_pool() was called before. This sets up the - * allocation gate timer, and requires that workqueues are available. + * Requires that kfence_alloc_pool_and_metadata() was called before. This sets + * up the allocation gate timer, and requires that workqueues are available. */ void __init kfence_init(void); @@ -223,7 +224,7 @@ bool __kfence_obj_info(struct kmem_obj_info *kpp, void *object, struct slab *sla #else /* CONFIG_KFENCE */ static inline bool is_kfence_address(const void *addr) { return false; } -static inline void kfence_alloc_pool(void) { } +static inline void kfence_alloc_pool_and_metadata(void) { } static inline void kfence_init(void) { } static inline void kfence_shutdown_cache(struct kmem_cache *s) { } static inline void *kfence_alloc(struct kmem_cache *s, size_t size, gfp_t flags) { return NULL; } diff --git a/include/linux/ksm.h b/include/linux/ksm.h index 899a314bc487..c2dd786a30e1 100644 --- a/include/linux/ksm.h +++ b/include/linux/ksm.h @@ -26,6 +26,22 @@ int ksm_disable(struct mm_struct *mm); int __ksm_enter(struct mm_struct *mm); void __ksm_exit(struct mm_struct *mm); +/* + * To identify zeropages that were mapped by KSM, we reuse the dirty bit + * in the PTE. If the PTE is dirty, the zeropage was mapped by KSM when + * deduplicating memory. + */ +#define is_ksm_zero_pte(pte) (is_zero_pfn(pte_pfn(pte)) && pte_dirty(pte)) + +extern unsigned long ksm_zero_pages; + +static inline void ksm_might_unmap_zero_page(struct mm_struct *mm, pte_t pte) +{ + if (is_ksm_zero_pte(pte)) { + ksm_zero_pages--; + mm->ksm_zero_pages--; + } +} static inline int ksm_fork(struct mm_struct *mm, struct mm_struct *oldmm) { @@ -95,6 +111,10 @@ static inline void ksm_exit(struct mm_struct *mm) { } +static inline void ksm_might_unmap_zero_page(struct mm_struct *mm, pte_t pte) +{ +} + #ifdef CONFIG_MEMORY_FAILURE static inline void collect_procs_ksm(struct page *page, struct list_head *to_kill, int force_early) diff --git a/include/linux/maple_tree.h b/include/linux/maple_tree.h index 295548cca8b3..e41c70ac7744 100644 --- a/include/linux/maple_tree.h +++ b/include/linux/maple_tree.h @@ -29,14 +29,12 @@ #define MAPLE_NODE_SLOTS 31 /* 256 bytes including ->parent */ #define MAPLE_RANGE64_SLOTS 16 /* 256 bytes */ #define MAPLE_ARANGE64_SLOTS 10 /* 240 bytes */ -#define MAPLE_ARANGE64_META_MAX 15 /* Out of range for metadata */ #define MAPLE_ALLOC_SLOTS (MAPLE_NODE_SLOTS - 1) #else /* 32bit sizes */ #define MAPLE_NODE_SLOTS 63 /* 256 bytes including ->parent */ #define MAPLE_RANGE64_SLOTS 32 /* 256 bytes */ #define MAPLE_ARANGE64_SLOTS 21 /* 240 bytes */ -#define MAPLE_ARANGE64_META_MAX 31 /* Out of range for metadata */ #define MAPLE_ALLOC_SLOTS (MAPLE_NODE_SLOTS - 2) #endif /* defined(CONFIG_64BIT) || defined(BUILD_VDSO32_64) */ @@ -184,13 +182,23 @@ enum maple_type { #ifdef CONFIG_LOCKDEP typedef struct lockdep_map *lockdep_map_p; -#define mt_lock_is_held(mt) lock_is_held(mt->ma_external_lock) +#define mt_lock_is_held(mt) \ + (!(mt)->ma_external_lock || lock_is_held((mt)->ma_external_lock)) + +#define mt_write_lock_is_held(mt) \ + (!(mt)->ma_external_lock || \ + lock_is_held_type((mt)->ma_external_lock, 0)) + #define mt_set_external_lock(mt, lock) \ (mt)->ma_external_lock = &(lock)->dep_map + +#define mt_on_stack(mt) (mt).ma_external_lock = NULL #else typedef struct { /* nothing */ } lockdep_map_p; -#define mt_lock_is_held(mt) 1 +#define mt_lock_is_held(mt) 1 +#define mt_write_lock_is_held(mt) 1 #define mt_set_external_lock(mt, lock) do { } while (0) +#define mt_on_stack(mt) do { } while (0) #endif /* @@ -212,8 +220,8 @@ struct maple_tree { spinlock_t ma_lock; lockdep_map_p ma_external_lock; }; - void __rcu *ma_root; unsigned int ma_flags; + void __rcu *ma_root; }; /** @@ -458,7 +466,7 @@ void *mas_find(struct ma_state *mas, unsigned long max); void *mas_find_range(struct ma_state *mas, unsigned long max); void *mas_find_rev(struct ma_state *mas, unsigned long min); void *mas_find_range_rev(struct ma_state *mas, unsigned long max); -int mas_preallocate(struct ma_state *mas, gfp_t gfp); +int mas_preallocate(struct ma_state *mas, void *entry, gfp_t gfp); bool mas_is_err(struct ma_state *mas); bool mas_nomem(struct ma_state *mas, gfp_t gfp); @@ -531,6 +539,22 @@ static inline void mas_reset(struct ma_state *mas) */ #define mas_for_each(__mas, __entry, __max) \ while (((__entry) = mas_find((__mas), (__max))) != NULL) +/** + * __mas_set_range() - Set up Maple Tree operation state to a sub-range of the + * current location. + * @mas: Maple Tree operation state. + * @start: New start of range in the Maple Tree. + * @last: New end of range in the Maple Tree. + * + * set the internal maple state values to a sub-range. + * Please use mas_set_range() if you do not know where you are in the tree. + */ +static inline void __mas_set_range(struct ma_state *mas, unsigned long start, + unsigned long last) +{ + mas->index = start; + mas->last = last; +} /** * mas_set_range() - Set up Maple Tree operation state for a different index. @@ -545,9 +569,8 @@ static inline void mas_reset(struct ma_state *mas) static inline void mas_set_range(struct ma_state *mas, unsigned long start, unsigned long last) { - mas->index = start; - mas->last = last; - mas->node = MAS_START; + __mas_set_range(mas, start, last); + mas->node = MAS_START; } /** @@ -662,10 +685,11 @@ void *mt_next(struct maple_tree *mt, unsigned long index, unsigned long max); * mt_for_each - Iterate over each entry starting at index until max. * @__tree: The Maple Tree * @__entry: The current entry - * @__index: The index to update to track the location in the tree + * @__index: The index to start the search from. Subsequently used as iterator. * @__max: The maximum limit for @index * - * Note: Will not return the zero entry. + * This iterator skips all entries, which resolve to a NULL pointer, + * e.g. entries which has been reserved with XA_ZERO_ENTRY. */ #define mt_for_each(__tree, __entry, __index, __max) \ for (__entry = mt_find(__tree, &(__index), __max); \ diff --git a/include/linux/memblock.h b/include/linux/memblock.h index f71ff9f0ec81..1c1072e3ca06 100644 --- a/include/linux/memblock.h +++ b/include/linux/memblock.h @@ -581,9 +581,7 @@ extern void *alloc_large_system_hash(const char *tablename, unsigned long high_limit); #define HASH_EARLY 0x00000001 /* Allocating during early boot? */ -#define HASH_SMALL 0x00000002 /* sub-page allocation allowed, min - * shift passed via *_hash_shift */ -#define HASH_ZERO 0x00000004 /* Zero allocated hash table */ +#define HASH_ZERO 0x00000002 /* Zero allocated hash table */ /* Only NUMA needs hash distribution. 64bit NUMA architectures have * sufficient vmalloc space. @@ -596,13 +594,11 @@ extern int hashdist; /* Distribute hashes across NUMA nodes? */ #endif #ifdef CONFIG_MEMTEST -extern phys_addr_t early_memtest_bad_size; /* Size of faulty ram found by memtest */ -extern bool early_memtest_done; /* Was early memtest done? */ -extern void early_memtest(phys_addr_t start, phys_addr_t end); +void early_memtest(phys_addr_t start, phys_addr_t end); +void memtest_report_meminfo(struct seq_file *m); #else -static inline void early_memtest(phys_addr_t start, phys_addr_t end) -{ -} +static inline void early_memtest(phys_addr_t start, phys_addr_t end) { } +static inline void memtest_report_meminfo(struct seq_file *m) { } #endif diff --git a/include/linux/memcontrol.h b/include/linux/memcontrol.h index dbf26bc89dd4..ab94ad4597d0 100644 --- a/include/linux/memcontrol.h +++ b/include/linux/memcontrol.h @@ -61,7 +61,6 @@ struct mem_cgroup_reclaim_cookie { #ifdef CONFIG_MEMCG #define MEM_CGROUP_ID_SHIFT 16 -#define MEM_CGROUP_ID_MAX USHRT_MAX struct mem_cgroup_id { int id; @@ -112,6 +111,9 @@ struct lruvec_stats { /* Aggregated (CPU and subtree) state */ long state[NR_VM_NODE_STAT_ITEMS]; + /* Non-hierarchical (CPU aggregated) state */ + long state_local[NR_VM_NODE_STAT_ITEMS]; + /* Pending child counts during tree propagation */ long state_pending[NR_VM_NODE_STAT_ITEMS]; }; @@ -588,7 +590,7 @@ static inline void mem_cgroup_protection(struct mem_cgroup *root, /* * There is no reclaim protection applied to a targeted reclaim. * We are special casing this specific case here because - * mem_cgroup_protected calculation is not robust enough to keep + * mem_cgroup_calculate_protection is not robust enough to keep * the protection invariant for calculated effective values for * parallel reclaimers with different reclaim target. This is * especially a problem for tail memcgs (as they have pages on LRU) @@ -866,8 +868,7 @@ static inline struct mem_cgroup *lruvec_memcg(struct lruvec *lruvec) * parent_mem_cgroup - find the accounting parent of a memcg * @memcg: memcg whose parent to find * - * Returns the parent memcg, or NULL if this is the root or the memory - * controller is in legacy no-hierarchy mode. + * Returns the parent memcg, or NULL if this is the root. */ static inline struct mem_cgroup *parent_mem_cgroup(struct mem_cgroup *memcg) { @@ -1025,14 +1026,12 @@ static inline unsigned long lruvec_page_state_local(struct lruvec *lruvec, { struct mem_cgroup_per_node *pn; long x = 0; - int cpu; if (mem_cgroup_disabled()) return node_page_state(lruvec_pgdat(lruvec), idx); pn = container_of(lruvec, struct mem_cgroup_per_node, lruvec); - for_each_possible_cpu(cpu) - x += per_cpu(pn->lruvec_stats_percpu->state[idx], cpu); + x = READ_ONCE(pn->lruvec_stats.state_local[idx]); #ifdef CONFIG_SMP if (x < 0) x = 0; @@ -1163,7 +1162,6 @@ unsigned long mem_cgroup_soft_limit_reclaim(pg_data_t *pgdat, int order, #else /* CONFIG_MEMCG */ #define MEM_CGROUP_ID_SHIFT 0 -#define MEM_CGROUP_ID_MAX 0 static inline struct mem_cgroup *folio_memcg(struct folio *folio) { @@ -1766,7 +1764,7 @@ 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); -struct obj_cgroup *get_obj_cgroup_from_page(struct page *page); +struct obj_cgroup *get_obj_cgroup_from_folio(struct folio *folio); 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); @@ -1850,7 +1848,7 @@ static inline void __memcg_kmem_uncharge_page(struct page *page, int order) { } -static inline struct obj_cgroup *get_obj_cgroup_from_page(struct page *page) +static inline struct obj_cgroup *get_obj_cgroup_from_folio(struct folio *folio) { return NULL; } diff --git a/include/linux/memory-tiers.h b/include/linux/memory-tiers.h index fc9647b1b4f9..437441cdf78f 100644 --- a/include/linux/memory-tiers.h +++ b/include/linux/memory-tiers.h @@ -33,7 +33,7 @@ struct memory_dev_type { #ifdef CONFIG_NUMA extern bool numa_demotion_enabled; struct memory_dev_type *alloc_memory_type(int adistance); -void destroy_memory_type(struct memory_dev_type *memtype); +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); #ifdef CONFIG_MIGRATION @@ -68,7 +68,7 @@ static inline struct memory_dev_type *alloc_memory_type(int adistance) return NULL; } -static inline void destroy_memory_type(struct memory_dev_type *memtype) +static inline void put_memory_type(struct memory_dev_type *memtype) { } diff --git a/include/linux/memory.h b/include/linux/memory.h index 31343566c221..f53cfdaaaa41 100644 --- a/include/linux/memory.h +++ b/include/linux/memory.h @@ -77,11 +77,7 @@ struct memory_block { */ struct zone *zone; struct device dev; - /* - * Number of vmemmap pages. These pages - * lay at the beginning of the memory block. - */ - unsigned long nr_vmemmap_pages; + struct vmem_altmap *altmap; struct memory_group *group; /* group (if any) for this block */ struct list_head group_next; /* next block inside memory group */ #if defined(CONFIG_MEMORY_FAILURE) && defined(CONFIG_MEMORY_HOTPLUG) @@ -147,7 +143,7 @@ static inline int hotplug_memory_notifier(notifier_fn_t fn, int pri) extern int register_memory_notifier(struct notifier_block *nb); extern void unregister_memory_notifier(struct notifier_block *nb); int create_memory_block_devices(unsigned long start, unsigned long size, - unsigned long vmemmap_pages, + struct vmem_altmap *altmap, struct memory_group *group); void remove_memory_block_devices(unsigned long start, unsigned long size); extern void memory_dev_init(void); diff --git a/include/linux/memory_hotplug.h b/include/linux/memory_hotplug.h index 013c69753c91..7d2076583494 100644 --- a/include/linux/memory_hotplug.h +++ b/include/linux/memory_hotplug.h @@ -97,6 +97,8 @@ typedef int __bitwise mhp_t; * To do so, we will use the beginning of the hot-added range to build * the page tables for the memmap array that describes the entire range. * Only selected architectures support it with SPARSE_VMEMMAP. + * This is only a hint, the core kernel can decide to not do this based on + * different alignment checks. */ #define MHP_MEMMAP_ON_MEMORY ((__force mhp_t)BIT(1)) /* @@ -354,7 +356,6 @@ extern struct zone *zone_for_pfn_range(int online_type, int nid, extern int arch_create_linear_mapping(int nid, u64 start, u64 size, struct mhp_params *params); void arch_remove_linear_mapping(u64 start, u64 size); -extern bool mhp_supports_memmap_on_memory(unsigned long size); #endif /* CONFIG_MEMORY_HOTPLUG */ #endif /* __LINUX_MEMORY_HOTPLUG_H */ diff --git a/include/linux/minmax.h b/include/linux/minmax.h index 396df1121bff..4f011eb6533d 100644 --- a/include/linux/minmax.h +++ b/include/linux/minmax.h @@ -3,6 +3,7 @@ #define _LINUX_MINMAX_H #include <linux/const.h> +#include <linux/types.h> /* * min()/max()/clamp() macros must accomplish three things: @@ -158,6 +159,32 @@ */ #define clamp_val(val, lo, hi) clamp_t(typeof(val), val, lo, hi) +static inline bool in_range64(u64 val, u64 start, u64 len) +{ + return (val - start) < len; +} + +static inline bool in_range32(u32 val, u32 start, u32 len) +{ + return (val - start) < len; +} + +/** + * in_range - Determine if a value lies within a range. + * @val: Value to test. + * @start: First value in range. + * @len: Number of values in range. + * + * This is more efficient than "if (start <= val && val < (start + len))". + * It also gives a different answer if @start + @len overflows the size of + * the type by a sufficient amount to encompass @val. Decide for yourself + * which behaviour you want, or prove that start + len never overflow. + * Do not blindly replace one form with the other. + */ +#define in_range(val, start, len) \ + ((sizeof(start) | sizeof(len) | sizeof(val)) <= sizeof(u32) ? \ + in_range32(val, start, len) : in_range64(val, start, len)) + /** * swap - swap values of @a and @b * @a: first value diff --git a/include/linux/mm.h b/include/linux/mm.h index 34f9dba17c1a..53efddc4d178 100644 --- a/include/linux/mm.h +++ b/include/linux/mm.h @@ -532,13 +532,6 @@ struct vm_fault { */ }; -/* page entry size for vm->huge_fault() */ -enum page_entry_size { - PE_SIZE_PTE = 0, - PE_SIZE_PMD, - PE_SIZE_PUD, -}; - /* * These are the virtual MM functions - opening of an area, closing and * unmapping it (needed to keep files on disk up-to-date etc), pointer @@ -562,8 +555,7 @@ struct vm_operations_struct { int (*mprotect)(struct vm_area_struct *vma, unsigned long start, unsigned long end, unsigned long newflags); vm_fault_t (*fault)(struct vm_fault *vmf); - vm_fault_t (*huge_fault)(struct vm_fault *vmf, - enum page_entry_size pe_size); + vm_fault_t (*huge_fault)(struct vm_fault *vmf, unsigned int order); vm_fault_t (*map_pages)(struct vm_fault *vmf, pgoff_t start_pgoff, pgoff_t end_pgoff); unsigned long (*pagesize)(struct vm_area_struct * area); @@ -679,6 +671,7 @@ static inline void vma_end_read(struct vm_area_struct *vma) rcu_read_unlock(); } +/* WARNING! Can only be used if mmap_lock is expected to be write-locked */ static bool __is_vma_write_locked(struct vm_area_struct *vma, int *mm_lock_seq) { mmap_assert_write_locked(vma->vm_mm); @@ -691,6 +684,11 @@ static bool __is_vma_write_locked(struct vm_area_struct *vma, int *mm_lock_seq) return (vma->vm_lock_seq == *mm_lock_seq); } +/* + * Begin writing to a VMA. + * Exclude concurrent readers under the per-VMA lock until the currently + * write-locked mmap_lock is dropped or downgraded. + */ static inline void vma_start_write(struct vm_area_struct *vma) { int mm_lock_seq; @@ -709,26 +707,17 @@ static inline void vma_start_write(struct vm_area_struct *vma) up_write(&vma->vm_lock->lock); } -static inline bool vma_try_start_write(struct vm_area_struct *vma) +static inline void vma_assert_write_locked(struct vm_area_struct *vma) { int mm_lock_seq; - if (__is_vma_write_locked(vma, &mm_lock_seq)) - return true; - - if (!down_write_trylock(&vma->vm_lock->lock)) - return false; - - WRITE_ONCE(vma->vm_lock_seq, mm_lock_seq); - up_write(&vma->vm_lock->lock); - return true; + VM_BUG_ON_VMA(!__is_vma_write_locked(vma, &mm_lock_seq), vma); } -static inline void vma_assert_write_locked(struct vm_area_struct *vma) +static inline void vma_assert_locked(struct vm_area_struct *vma) { - int mm_lock_seq; - - VM_BUG_ON_VMA(!__is_vma_write_locked(vma, &mm_lock_seq), vma); + if (!rwsem_is_locked(&vma->vm_lock->lock)) + vma_assert_write_locked(vma); } static inline void vma_mark_detached(struct vm_area_struct *vma, bool detached) @@ -739,6 +728,22 @@ static inline void vma_mark_detached(struct vm_area_struct *vma, bool detached) vma->detached = detached; } +static inline void release_fault_lock(struct vm_fault *vmf) +{ + if (vmf->flags & FAULT_FLAG_VMA_LOCK) + vma_end_read(vmf->vma); + else + mmap_read_unlock(vmf->vma->vm_mm); +} + +static inline void assert_fault_locked(struct vm_fault *vmf) +{ + if (vmf->flags & FAULT_FLAG_VMA_LOCK) + vma_assert_locked(vmf->vma); + else + mmap_assert_locked(vmf->vma->vm_mm); +} + struct vm_area_struct *lock_vma_under_rcu(struct mm_struct *mm, unsigned long address); @@ -748,25 +753,40 @@ static inline bool vma_start_read(struct vm_area_struct *vma) { return false; } static inline void vma_end_read(struct vm_area_struct *vma) {} static inline void vma_start_write(struct vm_area_struct *vma) {} -static inline bool vma_try_start_write(struct vm_area_struct *vma) - { return true; } -static inline void vma_assert_write_locked(struct vm_area_struct *vma) {} +static inline void vma_assert_write_locked(struct vm_area_struct *vma) + { mmap_assert_write_locked(vma->vm_mm); } static inline void vma_mark_detached(struct vm_area_struct *vma, bool detached) {} +static inline struct vm_area_struct *lock_vma_under_rcu(struct mm_struct *mm, + unsigned long address) +{ + return NULL; +} + +static inline void release_fault_lock(struct vm_fault *vmf) +{ + mmap_read_unlock(vmf->vma->vm_mm); +} + +static inline void assert_fault_locked(struct vm_fault *vmf) +{ + mmap_assert_locked(vmf->vma->vm_mm); +} + #endif /* CONFIG_PER_VMA_LOCK */ +extern const struct vm_operations_struct vma_dummy_vm_ops; + /* * WARNING: vma_init does not initialize vma->vm_lock. * Use vm_area_alloc()/vm_area_free() if vma needs locking. */ static inline void vma_init(struct vm_area_struct *vma, struct mm_struct *mm) { - static const struct vm_operations_struct dummy_vm_ops = {}; - memset(vma, 0, sizeof(*vma)); vma->vm_mm = mm; - vma->vm_ops = &dummy_vm_ops; + vma->vm_ops = &vma_dummy_vm_ops; INIT_LIST_HEAD(&vma->anon_vma_chain); vma_mark_detached(vma, false); vma_numab_state_init(vma); @@ -779,18 +799,22 @@ static inline void vm_flags_init(struct vm_area_struct *vma, ACCESS_PRIVATE(vma, __vm_flags) = flags; } -/* Use when VMA is part of the VMA tree and modifications need coordination */ +/* + * Use when VMA is part of the VMA tree and modifications need coordination + * Note: vm_flags_reset and vm_flags_reset_once do not lock the vma and + * it should be locked explicitly beforehand. + */ static inline void vm_flags_reset(struct vm_area_struct *vma, vm_flags_t flags) { - vma_start_write(vma); + vma_assert_write_locked(vma); vm_flags_init(vma, flags); } static inline void vm_flags_reset_once(struct vm_area_struct *vma, vm_flags_t flags) { - vma_start_write(vma); + vma_assert_write_locked(vma); WRITE_ONCE(ACCESS_PRIVATE(vma, __vm_flags), flags); } @@ -839,6 +863,31 @@ static inline bool vma_is_anonymous(struct vm_area_struct *vma) return !vma->vm_ops; } +/* + * Indicate if the VMA is a heap for the given task; for + * /proc/PID/maps that is the heap of the main task. + */ +static inline bool vma_is_initial_heap(const struct vm_area_struct *vma) +{ + return vma->vm_start <= vma->vm_mm->brk && + vma->vm_end >= vma->vm_mm->start_brk; +} + +/* + * Indicate if the VMA is a stack for the given task; for + * /proc/PID/maps that is the stack of the main task. + */ +static inline bool vma_is_initial_stack(const struct vm_area_struct *vma) +{ + /* + * We make no effort to guess what a given thread considers to be + * its "stack". It's not even well-defined for programs written + * languages like Go. + */ + return vma->vm_start <= vma->vm_mm->start_stack && + vma->vm_end >= vma->vm_mm->start_stack; +} + static inline bool vma_is_temporary_stack(struct vm_area_struct *vma) { int maybe_stack = vma->vm_flags & (VM_GROWSDOWN | VM_GROWSUP); @@ -976,7 +1025,7 @@ struct inode; * compound_order() can be called without holding a reference, which means * that niceties like page_folio() don't work. These callers should be * prepared to handle wild return values. For example, PG_head may be - * set before _folio_order is initialised, or this may be a tail page. + * set before the order is initialised, or this may be a tail page. * See compaction.c for some good examples. */ static inline unsigned int compound_order(struct page *page) @@ -985,7 +1034,7 @@ static inline unsigned int compound_order(struct page *page) if (!test_bit(PG_head, &folio->flags)) return 0; - return folio->_folio_order; + return folio->_flags_1 & 0xff; } /** @@ -1001,7 +1050,7 @@ static inline unsigned int folio_order(struct folio *folio) { if (!folio_test_large(folio)) return 0; - return folio->_folio_order; + return folio->_flags_1 & 0xff; } #include <linux/huge_mm.h> @@ -1072,11 +1121,6 @@ unsigned long vmalloc_to_pfn(const void *addr); * On nommu, vmalloc/vfree wrap through kmalloc/kfree directly, so there * is no special casing required. */ - -#ifndef is_ioremap_addr -#define is_ioremap_addr(x) is_vmalloc_addr(x) -#endif - #ifdef CONFIG_MMU extern bool is_vmalloc_addr(const void *x); extern int is_vmalloc_or_module_addr(const void *x); @@ -1220,33 +1264,6 @@ void folio_copy(struct folio *dst, struct folio *src); unsigned long nr_free_buffer_pages(void); -/* - * Compound pages have a destructor function. Provide a - * prototype for that function and accessor functions. - * These are _only_ valid on the head of a compound page. - */ -typedef void compound_page_dtor(struct page *); - -/* Keep the enum in sync with compound_page_dtors array in mm/page_alloc.c */ -enum compound_dtor_id { - NULL_COMPOUND_DTOR, - COMPOUND_PAGE_DTOR, -#ifdef CONFIG_HUGETLB_PAGE - HUGETLB_PAGE_DTOR, -#endif -#ifdef CONFIG_TRANSPARENT_HUGEPAGE - TRANSHUGE_PAGE_DTOR, -#endif - NR_COMPOUND_DTORS, -}; - -static inline void folio_set_compound_dtor(struct folio *folio, - enum compound_dtor_id compound_dtor) -{ - VM_BUG_ON_FOLIO(compound_dtor >= NR_COMPOUND_DTORS, folio); - folio->_folio_dtor = compound_dtor; -} - void destroy_large_folio(struct folio *folio); /* Returns the number of bytes in this potentially compound page. */ @@ -1282,8 +1299,6 @@ static inline unsigned long thp_size(struct page *page) return PAGE_SIZE << thp_order(page); } -void free_compound_page(struct page *page); - #ifdef CONFIG_MMU /* * Do pte_mkwrite, but only if the vma says VM_WRITE. We do this when @@ -1299,7 +1314,8 @@ static inline pte_t maybe_mkwrite(pte_t pte, struct vm_area_struct *vma) } vm_fault_t do_set_pmd(struct vm_fault *vmf, struct page *page); -void do_set_pte(struct vm_fault *vmf, struct page *page, unsigned long addr); +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); @@ -2006,7 +2022,7 @@ static inline long folio_nr_pages(struct folio *folio) #ifdef CONFIG_64BIT return folio->_folio_nr_pages; #else - return 1L << folio->_folio_order; + return 1L << (folio->_flags_1 & 0xff); #endif } @@ -2024,7 +2040,7 @@ static inline unsigned long compound_nr(struct page *page) #ifdef CONFIG_64BIT return folio->_folio_nr_pages; #else - return 1L << folio->_folio_order; + return 1L << (folio->_flags_1 & 0xff); #endif } @@ -2170,7 +2186,6 @@ static inline void *folio_address(const struct folio *folio) return page_address(&folio->page); } -extern void *page_rmapping(struct page *page); extern pgoff_t __page_file_index(struct page *page); /* @@ -2238,18 +2253,6 @@ extern void pagefault_out_of_memory(void); #define offset_in_folio(folio, p) ((unsigned long)(p) & (folio_size(folio) - 1)) /* - * Flags passed to show_mem() and show_free_areas() to suppress output in - * various contexts. - */ -#define SHOW_MEM_FILTER_NODES (0x0001u) /* disallowed nodes */ - -extern void __show_free_areas(unsigned int flags, nodemask_t *nodemask, int max_zone_idx); -static void __maybe_unused show_free_areas(unsigned int flags, nodemask_t *nodemask) -{ - __show_free_areas(flags, nodemask, MAX_NR_ZONES - 1); -} - -/* * Parameter block passed down to zap_pte_range in exceptional cases. */ struct zap_details { @@ -2317,9 +2320,9 @@ static inline void zap_vma_pages(struct vm_area_struct *vma) zap_page_range_single(vma, vma->vm_start, vma->vm_end - vma->vm_start, NULL); } -void unmap_vmas(struct mmu_gather *tlb, struct maple_tree *mt, +void unmap_vmas(struct mmu_gather *tlb, struct ma_state *mas, struct vm_area_struct *start_vma, unsigned long start, - unsigned long end, bool mm_wr_locked); + unsigned long end, unsigned long tree_end, bool mm_wr_locked); struct mmu_notifier_range; @@ -2766,42 +2769,93 @@ static inline pmd_t *pmd_alloc(struct mm_struct *mm, pud_t *pud, unsigned long a } #endif /* CONFIG_MMU */ +static inline struct ptdesc *virt_to_ptdesc(const void *x) +{ + return page_ptdesc(virt_to_page(x)); +} + +static inline void *ptdesc_to_virt(const struct ptdesc *pt) +{ + return page_to_virt(ptdesc_page(pt)); +} + +static inline void *ptdesc_address(const struct ptdesc *pt) +{ + return folio_address(ptdesc_folio(pt)); +} + +static inline bool pagetable_is_reserved(struct ptdesc *pt) +{ + return folio_test_reserved(ptdesc_folio(pt)); +} + +/** + * pagetable_alloc - Allocate pagetables + * @gfp: GFP flags + * @order: desired pagetable order + * + * pagetable_alloc allocates memory for page tables as well as a page table + * descriptor to describe that memory. + * + * Return: The ptdesc describing the allocated page tables. + */ +static inline struct ptdesc *pagetable_alloc(gfp_t gfp, unsigned int order) +{ + struct page *page = alloc_pages(gfp | __GFP_COMP, order); + + return page_ptdesc(page); +} + +/** + * pagetable_free - Free pagetables + * @pt: The page table descriptor + * + * pagetable_free frees the memory of all page tables described by a page + * table descriptor and the memory for the descriptor itself. + */ +static inline void pagetable_free(struct ptdesc *pt) +{ + struct page *page = ptdesc_page(pt); + + __free_pages(page, compound_order(page)); +} + #if USE_SPLIT_PTE_PTLOCKS #if ALLOC_SPLIT_PTLOCKS void __init ptlock_cache_init(void); -extern bool ptlock_alloc(struct page *page); -extern void ptlock_free(struct page *page); +bool ptlock_alloc(struct ptdesc *ptdesc); +void ptlock_free(struct ptdesc *ptdesc); -static inline spinlock_t *ptlock_ptr(struct page *page) +static inline spinlock_t *ptlock_ptr(struct ptdesc *ptdesc) { - return page->ptl; + return ptdesc->ptl; } #else /* ALLOC_SPLIT_PTLOCKS */ static inline void ptlock_cache_init(void) { } -static inline bool ptlock_alloc(struct page *page) +static inline bool ptlock_alloc(struct ptdesc *ptdesc) { return true; } -static inline void ptlock_free(struct page *page) +static inline void ptlock_free(struct ptdesc *ptdesc) { } -static inline spinlock_t *ptlock_ptr(struct page *page) +static inline spinlock_t *ptlock_ptr(struct ptdesc *ptdesc) { - return &page->ptl; + return &ptdesc->ptl; } #endif /* ALLOC_SPLIT_PTLOCKS */ static inline spinlock_t *pte_lockptr(struct mm_struct *mm, pmd_t *pmd) { - return ptlock_ptr(pmd_page(*pmd)); + return ptlock_ptr(page_ptdesc(pmd_page(*pmd))); } -static inline bool ptlock_init(struct page *page) +static inline bool ptlock_init(struct ptdesc *ptdesc) { /* * prep_new_page() initialize page->private (and therefore page->ptl) @@ -2810,10 +2864,10 @@ static inline bool ptlock_init(struct page *page) * It can happen if arch try to use slab for page table allocation: * slab code uses page->slab_cache, which share storage with page->ptl. */ - VM_BUG_ON_PAGE(*(unsigned long *)&page->ptl, page); - if (!ptlock_alloc(page)) + VM_BUG_ON_PAGE(*(unsigned long *)&ptdesc->ptl, ptdesc_page(ptdesc)); + if (!ptlock_alloc(ptdesc)) return false; - spin_lock_init(ptlock_ptr(page)); + spin_lock_init(ptlock_ptr(ptdesc)); return true; } @@ -2826,24 +2880,28 @@ static inline spinlock_t *pte_lockptr(struct mm_struct *mm, pmd_t *pmd) return &mm->page_table_lock; } static inline void ptlock_cache_init(void) {} -static inline bool ptlock_init(struct page *page) { return true; } -static inline void ptlock_free(struct page *page) {} +static inline bool ptlock_init(struct ptdesc *ptdesc) { return true; } +static inline void ptlock_free(struct ptdesc *ptdesc) {} #endif /* USE_SPLIT_PTE_PTLOCKS */ -static inline bool pgtable_pte_page_ctor(struct page *page) +static inline bool pagetable_pte_ctor(struct ptdesc *ptdesc) { - if (!ptlock_init(page)) + struct folio *folio = ptdesc_folio(ptdesc); + + if (!ptlock_init(ptdesc)) return false; - __SetPageTable(page); - inc_lruvec_page_state(page, NR_PAGETABLE); + __folio_set_pgtable(folio); + lruvec_stat_add_folio(folio, NR_PAGETABLE); return true; } -static inline void pgtable_pte_page_dtor(struct page *page) +static inline void pagetable_pte_dtor(struct ptdesc *ptdesc) { - ptlock_free(page); - __ClearPageTable(page); - dec_lruvec_page_state(page, NR_PAGETABLE); + struct folio *folio = ptdesc_folio(ptdesc); + + ptlock_free(ptdesc); + __folio_clear_pgtable(folio); + lruvec_stat_sub_folio(folio, NR_PAGETABLE); } pte_t *__pte_offset_map(pmd_t *pmd, unsigned long addr, pmd_t *pmdvalp); @@ -2892,28 +2950,33 @@ static inline struct page *pmd_pgtable_page(pmd_t *pmd) return virt_to_page((void *)((unsigned long) pmd & mask)); } +static inline struct ptdesc *pmd_ptdesc(pmd_t *pmd) +{ + return page_ptdesc(pmd_pgtable_page(pmd)); +} + static inline spinlock_t *pmd_lockptr(struct mm_struct *mm, pmd_t *pmd) { - return ptlock_ptr(pmd_pgtable_page(pmd)); + return ptlock_ptr(pmd_ptdesc(pmd)); } -static inline bool pmd_ptlock_init(struct page *page) +static inline bool pmd_ptlock_init(struct ptdesc *ptdesc) { #ifdef CONFIG_TRANSPARENT_HUGEPAGE - page->pmd_huge_pte = NULL; + ptdesc->pmd_huge_pte = NULL; #endif - return ptlock_init(page); + return ptlock_init(ptdesc); } -static inline void pmd_ptlock_free(struct page *page) +static inline void pmd_ptlock_free(struct ptdesc *ptdesc) { #ifdef CONFIG_TRANSPARENT_HUGEPAGE - VM_BUG_ON_PAGE(page->pmd_huge_pte, page); + VM_BUG_ON_PAGE(ptdesc->pmd_huge_pte, ptdesc_page(ptdesc)); #endif - ptlock_free(page); + ptlock_free(ptdesc); } -#define pmd_huge_pte(mm, pmd) (pmd_pgtable_page(pmd)->pmd_huge_pte) +#define pmd_huge_pte(mm, pmd) (pmd_ptdesc(pmd)->pmd_huge_pte) #else @@ -2922,8 +2985,8 @@ static inline spinlock_t *pmd_lockptr(struct mm_struct *mm, pmd_t *pmd) return &mm->page_table_lock; } -static inline bool pmd_ptlock_init(struct page *page) { return true; } -static inline void pmd_ptlock_free(struct page *page) {} +static inline bool pmd_ptlock_init(struct ptdesc *ptdesc) { return true; } +static inline void pmd_ptlock_free(struct ptdesc *ptdesc) {} #define pmd_huge_pte(mm, pmd) ((mm)->pmd_huge_pte) @@ -2936,20 +2999,24 @@ static inline spinlock_t *pmd_lock(struct mm_struct *mm, pmd_t *pmd) return ptl; } -static inline bool pgtable_pmd_page_ctor(struct page *page) +static inline bool pagetable_pmd_ctor(struct ptdesc *ptdesc) { - if (!pmd_ptlock_init(page)) + struct folio *folio = ptdesc_folio(ptdesc); + + if (!pmd_ptlock_init(ptdesc)) return false; - __SetPageTable(page); - inc_lruvec_page_state(page, NR_PAGETABLE); + __folio_set_pgtable(folio); + lruvec_stat_add_folio(folio, NR_PAGETABLE); return true; } -static inline void pgtable_pmd_page_dtor(struct page *page) +static inline void pagetable_pmd_dtor(struct ptdesc *ptdesc) { - pmd_ptlock_free(page); - __ClearPageTable(page); - dec_lruvec_page_state(page, NR_PAGETABLE); + struct folio *folio = ptdesc_folio(ptdesc); + + pmd_ptlock_free(ptdesc); + __folio_clear_pgtable(folio); + lruvec_stat_sub_folio(folio, NR_PAGETABLE); } /* @@ -3004,6 +3071,11 @@ static inline void mark_page_reserved(struct page *page) adjust_managed_page_count(page, -1); } +static inline void free_reserved_ptdesc(struct ptdesc *pt) +{ + free_reserved_page(ptdesc_page(pt)); +} + /* * Default method to free all the __init memory into the buddy system. * The freed pages will be poisoned with pattern "poison" if it's within @@ -3069,9 +3141,9 @@ extern void mem_init(void); extern void __init mmap_init(void); extern void __show_mem(unsigned int flags, nodemask_t *nodemask, int max_zone_idx); -static inline void show_mem(unsigned int flags, nodemask_t *nodemask) +static inline void show_mem(void) { - __show_mem(flags, nodemask, MAX_NR_ZONES - 1); + __show_mem(0, NULL, MAX_NR_ZONES - 1); } extern long si_mem_available(void); extern void si_meminfo(struct sysinfo * val); @@ -3509,8 +3581,8 @@ static inline bool debug_pagealloc_enabled(void) } /* - * For use in fast paths after init_debug_pagealloc() has run, or when a - * false negative result is not harmful when called too early. + * For use in fast paths after mem_debugging_and_hardening_init() has run, + * or when a false negative result is not harmful when called too early. */ static inline bool debug_pagealloc_enabled_static(void) { @@ -3665,13 +3737,32 @@ void vmemmap_free(unsigned long start, unsigned long end, struct vmem_altmap *altmap); #endif -#ifdef CONFIG_ARCH_WANT_OPTIMIZE_VMEMMAP -static inline bool vmemmap_can_optimize(struct vmem_altmap *altmap, - struct dev_pagemap *pgmap) +#define VMEMMAP_RESERVE_NR 2 +#ifdef CONFIG_ARCH_WANT_OPTIMIZE_DAX_VMEMMAP +static inline bool __vmemmap_can_optimize(struct vmem_altmap *altmap, + struct dev_pagemap *pgmap) { - return is_power_of_2(sizeof(struct page)) && - pgmap && (pgmap_vmemmap_nr(pgmap) > 1) && !altmap; + unsigned long nr_pages; + unsigned long nr_vmemmap_pages; + + if (!pgmap || !is_power_of_2(sizeof(struct page))) + return false; + + nr_pages = pgmap_vmemmap_nr(pgmap); + nr_vmemmap_pages = ((nr_pages * sizeof(struct page)) >> PAGE_SHIFT); + /* + * For vmemmap optimization with DAX we need minimum 2 vmemmap + * pages. See layout diagram in Documentation/mm/vmemmap_dedup.rst + */ + return !altmap && (nr_vmemmap_pages > VMEMMAP_RESERVE_NR); } +/* + * If we don't have an architecture override, use the generic rule + */ +#ifndef vmemmap_can_optimize +#define vmemmap_can_optimize __vmemmap_can_optimize +#endif + #else static inline bool vmemmap_can_optimize(struct vmem_altmap *altmap, struct dev_pagemap *pgmap) diff --git a/include/linux/mm_inline.h b/include/linux/mm_inline.h index 21d6c72bcc71..8148b30a9df1 100644 --- a/include/linux/mm_inline.h +++ b/include/linux/mm_inline.h @@ -523,6 +523,27 @@ static inline bool mm_tlb_flush_nested(struct mm_struct *mm) return atomic_read(&mm->tlb_flush_pending) > 1; } +#ifdef CONFIG_MMU +/* + * Computes the pte marker to copy from the given source entry into dst_vma. + * If no marker should be copied, returns 0. + * The caller should insert a new pte created with make_pte_marker(). + */ +static inline pte_marker copy_pte_marker( + swp_entry_t entry, struct vm_area_struct *dst_vma) +{ + pte_marker srcm = pte_marker_get(entry); + /* Always copy error entries. */ + pte_marker dstm = srcm & PTE_MARKER_POISONED; + + /* Only copy PTE markers if UFFD register matches. */ + if ((srcm & PTE_MARKER_UFFD_WP) && userfaultfd_wp(dst_vma)) + dstm |= PTE_MARKER_UFFD_WP; + + return dstm; +} +#endif + /* * If this pte is wr-protected by uffd-wp in any form, arm the special pte to * replace a none pte. NOTE! This should only be called when *pte is already diff --git a/include/linux/mm_types.h b/include/linux/mm_types.h index 7d30dc4ff0ff..36c5b43999e6 100644 --- a/include/linux/mm_types.h +++ b/include/linux/mm_types.h @@ -141,20 +141,6 @@ struct page { struct { /* Tail pages of compound page */ unsigned long compound_head; /* Bit zero is set */ }; - struct { /* Page table pages */ - unsigned long _pt_pad_1; /* compound_head */ - pgtable_t pmd_huge_pte; /* protected by page->ptl */ - unsigned long _pt_pad_2; /* mapping */ - union { - struct mm_struct *pt_mm; /* x86 pgds only */ - atomic_t pt_frag_refcount; /* powerpc */ - }; -#if ALLOC_SPLIT_PTLOCKS - spinlock_t *ptl; -#else - spinlock_t ptl; -#endif - }; struct { /* ZONE_DEVICE pages */ /** @pgmap: Points to the hosting device page map. */ struct dev_pagemap *pgmap; @@ -262,6 +248,14 @@ static inline struct page *encoded_page_ptr(struct encoded_page *page) return (struct page *)(~ENCODE_PAGE_BITS & (unsigned long)page); } +/* + * A swap entry has to fit into a "unsigned long", as the entry is hidden + * in the "index" field of the swapper address space. + */ +typedef struct { + unsigned long val; +} swp_entry_t; + /** * struct folio - Represents a contiguous set of bytes. * @flags: Identical to the page flags. @@ -272,14 +266,12 @@ static inline struct page *encoded_page_ptr(struct encoded_page *page) * @index: Offset within the file, in units of pages. For anonymous memory, * this is the index from the beginning of the mmap. * @private: Filesystem per-folio data (see folio_attach_private()). - * Used for swp_entry_t if folio_test_swapcache(). + * @swap: Used for swp_entry_t if folio_test_swapcache(). * @_mapcount: Do not access this member directly. Use folio_mapcount() to * find out how many times this folio is mapped by userspace. * @_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. - * @_folio_dtor: Which destructor to use for this folio. - * @_folio_order: Do not use directly, call folio_order(). * @_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(). @@ -317,7 +309,10 @@ struct folio { }; struct address_space *mapping; pgoff_t index; - void *private; + union { + void *private; + swp_entry_t swap; + }; atomic_t _mapcount; atomic_t _refcount; #ifdef CONFIG_MEMCG @@ -331,9 +326,8 @@ struct folio { struct { unsigned long _flags_1; unsigned long _head_1; + unsigned long _folio_avail; /* public: */ - unsigned char _folio_dtor; - unsigned char _folio_order; atomic_t _entire_mapcount; atomic_t _nr_pages_mapped; atomic_t _pincount; @@ -391,8 +385,89 @@ FOLIO_MATCH(compound_head, _head_1); offsetof(struct page, pg) + 2 * sizeof(struct page)) FOLIO_MATCH(flags, _flags_2); FOLIO_MATCH(compound_head, _head_2); +FOLIO_MATCH(flags, _flags_2a); +FOLIO_MATCH(compound_head, _head_2a); #undef FOLIO_MATCH +/** + * struct ptdesc - Memory descriptor for page tables. + * @__page_flags: Same as page flags. Unused for page tables. + * @pt_rcu_head: For freeing page table pages. + * @pt_list: List of used page tables. Used for s390 and x86. + * @_pt_pad_1: Padding that aliases with page's compound head. + * @pmd_huge_pte: Protected by ptdesc->ptl, used for THPs. + * @__page_mapping: Aliases with page->mapping. Unused for page tables. + * @pt_mm: Used for x86 pgds. + * @pt_frag_refcount: For fragmented page table tracking. Powerpc and s390 only. + * @_pt_pad_2: Padding to ensure proper alignment. + * @ptl: Lock for the page table. + * @__page_type: Same as page->page_type. Unused for page tables. + * @_refcount: Same as page refcount. Used for s390 page tables. + * @pt_memcg_data: Memcg data. Tracked for page tables here. + * + * This struct overlays struct page for now. Do not modify without a good + * understanding of the issues. + */ +struct ptdesc { + unsigned long __page_flags; + + union { + struct rcu_head pt_rcu_head; + struct list_head pt_list; + struct { + unsigned long _pt_pad_1; + pgtable_t pmd_huge_pte; + }; + }; + unsigned long __page_mapping; + + union { + struct mm_struct *pt_mm; + atomic_t pt_frag_refcount; + }; + + union { + unsigned long _pt_pad_2; +#if ALLOC_SPLIT_PTLOCKS + spinlock_t *ptl; +#else + spinlock_t ptl; +#endif + }; + unsigned int __page_type; + atomic_t _refcount; +#ifdef CONFIG_MEMCG + unsigned long pt_memcg_data; +#endif +}; + +#define TABLE_MATCH(pg, pt) \ + static_assert(offsetof(struct page, pg) == offsetof(struct ptdesc, pt)) +TABLE_MATCH(flags, __page_flags); +TABLE_MATCH(compound_head, pt_list); +TABLE_MATCH(compound_head, _pt_pad_1); +TABLE_MATCH(mapping, __page_mapping); +TABLE_MATCH(rcu_head, pt_rcu_head); +TABLE_MATCH(page_type, __page_type); +TABLE_MATCH(_refcount, _refcount); +#ifdef CONFIG_MEMCG +TABLE_MATCH(memcg_data, pt_memcg_data); +#endif +#undef TABLE_MATCH +static_assert(sizeof(struct ptdesc) <= sizeof(struct page)); + +#define ptdesc_page(pt) (_Generic((pt), \ + const struct ptdesc *: (const struct page *)(pt), \ + struct ptdesc *: (struct page *)(pt))) + +#define ptdesc_folio(pt) (_Generic((pt), \ + const struct ptdesc *: (const struct folio *)(pt), \ + struct ptdesc *: (struct folio *)(pt))) + +#define page_ptdesc(p) (_Generic((p), \ + const struct page *: (const struct ptdesc *)(p), \ + struct page *: (struct ptdesc *)(p))) + /* * Used for sizing the vmemmap region on some architectures */ @@ -812,7 +887,7 @@ struct mm_struct { #ifdef CONFIG_KSM /* * Represent how many pages of this process are involved in KSM - * merging. + * merging (not including ksm_zero_pages). */ unsigned long ksm_merging_pages; /* @@ -820,7 +895,12 @@ struct mm_struct { * including merged and not merged. */ unsigned long ksm_rmap_items; -#endif + /* + * Represent how many empty pages are merged with kernel zero + * pages when enabling KSM use_zero_pages. + */ + unsigned long ksm_zero_pages; +#endif /* CONFIG_KSM */ #ifdef CONFIG_LRU_GEN struct { /* this mm_struct is on lru_gen_mm_list */ @@ -1105,7 +1185,8 @@ enum vm_fault_reason { { VM_FAULT_RETRY, "RETRY" }, \ { VM_FAULT_FALLBACK, "FALLBACK" }, \ { VM_FAULT_DONE_COW, "DONE_COW" }, \ - { VM_FAULT_NEEDDSYNC, "NEEDDSYNC" } + { VM_FAULT_NEEDDSYNC, "NEEDDSYNC" }, \ + { VM_FAULT_COMPLETED, "COMPLETED" } struct vm_special_mapping { const char *name; /* The name, e.g. "[vdso]". */ @@ -1139,14 +1220,6 @@ enum tlb_flush_reason { NR_TLB_FLUSH_REASONS, }; - /* - * A swap entry has to fit into a "unsigned long", as the entry is hidden - * in the "index" field of the swapper address space. - */ -typedef struct { - unsigned long val; -} swp_entry_t; - /** * enum fault_flag - Fault flag definitions. * @FAULT_FLAG_WRITE: Fault was a write fault. diff --git a/include/linux/mm_types_task.h b/include/linux/mm_types_task.h index 5414b5c6a103..aa44fff8bb9d 100644 --- a/include/linux/mm_types_task.h +++ b/include/linux/mm_types_task.h @@ -52,8 +52,8 @@ struct tlbflush_unmap_batch { #ifdef CONFIG_ARCH_WANT_BATCHED_UNMAP_TLB_FLUSH /* * The arch code makes the following promise: generic code can modify a - * PTE, then call arch_tlbbatch_add_mm() (which internally provides all - * needed barriers), then call arch_tlbbatch_flush(), and the entries + * PTE, then call arch_tlbbatch_add_pending() (which internally provides + * all needed barriers), then call arch_tlbbatch_flush(), and the entries * will be flushed on all CPUs by the time that arch_tlbbatch_flush() * returns. */ diff --git a/include/linux/mmap_lock.h b/include/linux/mmap_lock.h index e05e167dbd16..8d38dcb6d044 100644 --- a/include/linux/mmap_lock.h +++ b/include/linux/mmap_lock.h @@ -73,6 +73,14 @@ static inline void mmap_assert_write_locked(struct mm_struct *mm) } #ifdef CONFIG_PER_VMA_LOCK +/* + * Drop all currently-held per-VMA locks. + * This is called from the mmap_lock implementation directly before releasing + * a write-locked mmap_lock (or downgrading it to read-locked). + * This should normally NOT be called manually from other places. + * If you want to call this manually anyway, keep in mind that this will release + * *all* VMA write locks, including ones from further up the stack. + */ static inline void vma_end_write_all(struct mm_struct *mm) { mmap_assert_write_locked(mm); @@ -118,16 +126,6 @@ static inline int mmap_write_lock_killable(struct mm_struct *mm) return ret; } -static inline bool mmap_write_trylock(struct mm_struct *mm) -{ - bool ret; - - __mmap_lock_trace_start_locking(mm, true); - ret = down_write_trylock(&mm->mmap_lock) != 0; - __mmap_lock_trace_acquire_returned(mm, true, ret); - return ret; -} - static inline void mmap_write_unlock(struct mm_struct *mm) { __mmap_lock_trace_released(mm, true); diff --git a/include/linux/mmu_notifier.h b/include/linux/mmu_notifier.h index 64a3e051c3c4..6e3c857606f1 100644 --- a/include/linux/mmu_notifier.h +++ b/include/linux/mmu_notifier.h @@ -187,27 +187,27 @@ struct mmu_notifier_ops { const struct mmu_notifier_range *range); /* - * invalidate_range() is either called between - * invalidate_range_start() and invalidate_range_end() when the - * VM has to free pages that where unmapped, but before the - * pages are actually freed, or outside of _start()/_end() when - * a (remote) TLB is necessary. + * arch_invalidate_secondary_tlbs() is used to manage a non-CPU TLB + * which shares page-tables with the CPU. The + * invalidate_range_start()/end() callbacks should not be implemented as + * invalidate_secondary_tlbs() already catches the points in time when + * an external TLB needs to be flushed. * - * If invalidate_range() is used to manage a non-CPU TLB with - * shared page-tables, it not necessary to implement the - * invalidate_range_start()/end() notifiers, as - * invalidate_range() already catches the points in time when an - * external TLB range needs to be flushed. For more in depth - * discussion on this see Documentation/mm/mmu_notifier.rst + * This requires arch_invalidate_secondary_tlbs() to be called while + * holding the ptl spin-lock and therefore this callback is not allowed + * to sleep. * - * Note that this function might be called with just a sub-range - * of what was passed to invalidate_range_start()/end(), if - * called between those functions. + * This is called by architecture code whenever invalidating a TLB + * entry. It is assumed that any secondary TLB has the same rules for + * when invalidations are required. If this is not the case architecture + * code will need to call this explicitly when required for secondary + * TLB invalidation. */ - void (*invalidate_range)(struct mmu_notifier *subscription, - struct mm_struct *mm, - unsigned long start, - unsigned long end); + void (*arch_invalidate_secondary_tlbs)( + struct mmu_notifier *subscription, + struct mm_struct *mm, + unsigned long start, + unsigned long end); /* * These callbacks are used with the get/put interface to manage the @@ -395,10 +395,9 @@ extern int __mmu_notifier_test_young(struct mm_struct *mm, extern void __mmu_notifier_change_pte(struct mm_struct *mm, unsigned long address, pte_t pte); extern int __mmu_notifier_invalidate_range_start(struct mmu_notifier_range *r); -extern void __mmu_notifier_invalidate_range_end(struct mmu_notifier_range *r, - bool only_end); -extern void __mmu_notifier_invalidate_range(struct mm_struct *mm, - unsigned long start, unsigned long end); +extern void __mmu_notifier_invalidate_range_end(struct mmu_notifier_range *r); +extern void __mmu_notifier_arch_invalidate_secondary_tlbs(struct mm_struct *mm, + unsigned long start, unsigned long end); extern bool mmu_notifier_range_update_to_read_only(const struct mmu_notifier_range *range); @@ -481,21 +480,14 @@ mmu_notifier_invalidate_range_end(struct mmu_notifier_range *range) might_sleep(); if (mm_has_notifiers(range->mm)) - __mmu_notifier_invalidate_range_end(range, false); -} - -static inline void -mmu_notifier_invalidate_range_only_end(struct mmu_notifier_range *range) -{ - if (mm_has_notifiers(range->mm)) - __mmu_notifier_invalidate_range_end(range, true); + __mmu_notifier_invalidate_range_end(range); } -static inline void mmu_notifier_invalidate_range(struct mm_struct *mm, - unsigned long start, unsigned long end) +static inline void mmu_notifier_arch_invalidate_secondary_tlbs(struct mm_struct *mm, + unsigned long start, unsigned long end) { if (mm_has_notifiers(mm)) - __mmu_notifier_invalidate_range(mm, start, end); + __mmu_notifier_arch_invalidate_secondary_tlbs(mm, start, end); } static inline void mmu_notifier_subscriptions_init(struct mm_struct *mm) @@ -582,45 +574,6 @@ static inline void mmu_notifier_range_init_owner( __young; \ }) -#define ptep_clear_flush_notify(__vma, __address, __ptep) \ -({ \ - unsigned long ___addr = __address & PAGE_MASK; \ - struct mm_struct *___mm = (__vma)->vm_mm; \ - pte_t ___pte; \ - \ - ___pte = ptep_clear_flush(__vma, __address, __ptep); \ - mmu_notifier_invalidate_range(___mm, ___addr, \ - ___addr + PAGE_SIZE); \ - \ - ___pte; \ -}) - -#define pmdp_huge_clear_flush_notify(__vma, __haddr, __pmd) \ -({ \ - unsigned long ___haddr = __haddr & HPAGE_PMD_MASK; \ - struct mm_struct *___mm = (__vma)->vm_mm; \ - pmd_t ___pmd; \ - \ - ___pmd = pmdp_huge_clear_flush(__vma, __haddr, __pmd); \ - mmu_notifier_invalidate_range(___mm, ___haddr, \ - ___haddr + HPAGE_PMD_SIZE); \ - \ - ___pmd; \ -}) - -#define pudp_huge_clear_flush_notify(__vma, __haddr, __pud) \ -({ \ - unsigned long ___haddr = __haddr & HPAGE_PUD_MASK; \ - struct mm_struct *___mm = (__vma)->vm_mm; \ - pud_t ___pud; \ - \ - ___pud = pudp_huge_clear_flush(__vma, __haddr, __pud); \ - mmu_notifier_invalidate_range(___mm, ___haddr, \ - ___haddr + HPAGE_PUD_SIZE); \ - \ - ___pud; \ -}) - /* * set_pte_at_notify() sets the pte _after_ running the notifier. * This is safe to start by updating the secondary MMUs, because the primary MMU @@ -711,12 +664,7 @@ void mmu_notifier_invalidate_range_end(struct mmu_notifier_range *range) { } -static inline void -mmu_notifier_invalidate_range_only_end(struct mmu_notifier_range *range) -{ -} - -static inline void mmu_notifier_invalidate_range(struct mm_struct *mm, +static inline void mmu_notifier_arch_invalidate_secondary_tlbs(struct mm_struct *mm, unsigned long start, unsigned long end) { } diff --git a/include/linux/mmzone.h b/include/linux/mmzone.h index 5e50b78d58ea..4106fbc5b4b3 100644 --- a/include/linux/mmzone.h +++ b/include/linux/mmzone.h @@ -676,7 +676,6 @@ 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) -/* Fields and list protected by pagesets local_lock in page_alloc.c */ struct per_cpu_pages { spinlock_t lock; /* Protects lists field */ int count; /* number of pages in the list */ diff --git a/include/linux/net_mm.h b/include/linux/net_mm.h deleted file mode 100644 index b298998bd5a0..000000000000 --- a/include/linux/net_mm.h +++ /dev/null @@ -1,17 +0,0 @@ -/* SPDX-License-Identifier: GPL-2.0-or-later */ -#ifdef CONFIG_MMU - -#ifdef CONFIG_INET -extern const struct vm_operations_struct tcp_vm_ops; -static inline bool vma_is_tcp(const struct vm_area_struct *vma) -{ - return vma->vm_ops == &tcp_vm_ops; -} -#else -static inline bool vma_is_tcp(const struct vm_area_struct *vma) -{ - return false; -} -#endif /* CONFIG_INET*/ - -#endif /* CONFIG_MMU */ diff --git a/include/linux/page-flags.h b/include/linux/page-flags.h index 92a2063a0a23..5c02720c53a5 100644 --- a/include/linux/page-flags.h +++ b/include/linux/page-flags.h @@ -99,13 +99,15 @@ */ enum pageflags { PG_locked, /* Page is locked. Don't touch. */ + PG_writeback, /* Page is under writeback */ PG_referenced, PG_uptodate, PG_dirty, PG_lru, + PG_head, /* Must be in bit 6 */ + PG_waiters, /* Page has waiters, check its waitqueue. Must be bit #7 and in the same byte as "PG_locked" */ PG_active, PG_workingset, - PG_waiters, /* Page has waiters, check its waitqueue. Must be bit #7 and in the same byte as "PG_locked" */ PG_error, PG_slab, PG_owner_priv_1, /* Owner use. If pagecache, fs may use*/ @@ -113,8 +115,6 @@ enum pageflags { PG_reserved, PG_private, /* If pagecache, has fs-private data */ PG_private_2, /* If pagecache, has fs aux data */ - PG_writeback, /* Page is under writeback */ - PG_head, /* A head page */ PG_mappedtodisk, /* Has blocks allocated on-disk */ PG_reclaim, /* To be reclaimed asap */ PG_swapbacked, /* Page is backed by RAM/swap */ @@ -171,15 +171,6 @@ enum pageflags { /* Remapped by swiotlb-xen. */ PG_xen_remapped = PG_owner_priv_1, -#ifdef CONFIG_MEMORY_FAILURE - /* - * Compound pages. Stored in first tail page's flags. - * Indicates that at least one subpage is hwpoisoned in the - * THP. - */ - PG_has_hwpoisoned = PG_error, -#endif - /* non-lru isolated movable page */ PG_isolated = PG_reclaim, @@ -190,6 +181,17 @@ enum pageflags { /* For self-hosted memmap pages */ PG_vmemmap_self_hosted = PG_owner_priv_1, #endif + + /* + * Flags only valid for compound pages. Stored in first tail page's + * flags word. Cannot use the first 8 flags or any flag marked as + * PF_ANY. + */ + + /* At least one page in this folio has the hwpoison flag set */ + PG_has_hwpoisoned = PG_error, + PG_hugetlb = PG_active, + PG_large_rmappable = PG_workingset, /* anon or file-backed */ }; #define PAGEFLAGS_MASK ((1UL << NR_PAGEFLAGS) - 1) @@ -806,13 +808,32 @@ static inline void ClearPageCompound(struct page *page) BUG_ON(!PageHead(page)); ClearPageHead(page); } +PAGEFLAG(LargeRmappable, large_rmappable, PF_SECOND) +#else +TESTPAGEFLAG_FALSE(LargeRmappable, large_rmappable) #endif #define PG_head_mask ((1UL << PG_head)) #ifdef CONFIG_HUGETLB_PAGE int PageHuge(struct page *page); -bool folio_test_hugetlb(struct folio *folio); +SETPAGEFLAG(HugeTLB, hugetlb, PF_SECOND) +CLEARPAGEFLAG(HugeTLB, hugetlb, PF_SECOND) + +/** + * folio_test_hugetlb - Determine if the folio belongs to hugetlbfs + * @folio: The folio to test. + * + * Context: Any context. Caller should have a reference on the folio to + * prevent it from being turned into a tail page. + * Return: True for hugetlbfs folios, false for anon folios or folios + * belonging to other filesystems. + */ +static inline bool folio_test_hugetlb(struct folio *folio) +{ + return folio_test_large(folio) && + test_bit(PG_hugetlb, folio_flags(folio, 1)); +} #else TESTPAGEFLAG_FALSE(Huge, hugetlb) #endif @@ -832,11 +853,6 @@ static inline int PageTransHuge(struct page *page) return PageHead(page); } -static inline bool folio_test_transhuge(struct folio *folio) -{ - return folio_test_head(folio); -} - /* * PageTransCompound returns true for both transparent huge pages * and hugetlbfs pages, so it should only be called when it's known @@ -908,6 +924,8 @@ static inline bool is_page_hwpoison(struct page *page) #define PageType(page, flag) \ ((page->page_type & (PAGE_TYPE_BASE | flag)) == PAGE_TYPE_BASE) +#define folio_test_type(folio, flag) \ + ((folio->page.page_type & (PAGE_TYPE_BASE | flag)) == PAGE_TYPE_BASE) static inline int page_type_has_type(unsigned int page_type) { @@ -919,27 +937,41 @@ static inline int page_has_type(struct page *page) return page_type_has_type(page->page_type); } -#define PAGE_TYPE_OPS(uname, lname) \ -static __always_inline int Page##uname(struct page *page) \ +#define PAGE_TYPE_OPS(uname, lname, fname) \ +static __always_inline int Page##uname(const struct page *page) \ { \ return PageType(page, PG_##lname); \ } \ +static __always_inline int folio_test_##fname(const struct folio *folio)\ +{ \ + return folio_test_type(folio, PG_##lname); \ +} \ static __always_inline void __SetPage##uname(struct page *page) \ { \ VM_BUG_ON_PAGE(!PageType(page, 0), page); \ page->page_type &= ~PG_##lname; \ } \ +static __always_inline void __folio_set_##fname(struct folio *folio) \ +{ \ + VM_BUG_ON_FOLIO(!folio_test_type(folio, 0), folio); \ + folio->page.page_type &= ~PG_##lname; \ +} \ static __always_inline void __ClearPage##uname(struct page *page) \ { \ VM_BUG_ON_PAGE(!Page##uname(page), page); \ page->page_type |= PG_##lname; \ -} +} \ +static __always_inline void __folio_clear_##fname(struct folio *folio) \ +{ \ + VM_BUG_ON_FOLIO(!folio_test_##fname(folio), folio); \ + folio->page.page_type |= PG_##lname; \ +} \ /* * PageBuddy() indicates that the page is free and in the buddy system * (see mm/page_alloc.c). */ -PAGE_TYPE_OPS(Buddy, buddy) +PAGE_TYPE_OPS(Buddy, buddy, buddy) /* * PageOffline() indicates that the page is logically offline although the @@ -963,7 +995,7 @@ PAGE_TYPE_OPS(Buddy, buddy) * pages should check PageOffline() and synchronize with such drivers using * page_offline_freeze()/page_offline_thaw(). */ -PAGE_TYPE_OPS(Offline, offline) +PAGE_TYPE_OPS(Offline, offline, offline) extern void page_offline_freeze(void); extern void page_offline_thaw(void); @@ -973,12 +1005,12 @@ extern void page_offline_end(void); /* * Marks pages in use as page tables. */ -PAGE_TYPE_OPS(Table, table) +PAGE_TYPE_OPS(Table, table, pgtable) /* * Marks guardpages used with debug_pagealloc. */ -PAGE_TYPE_OPS(Guard, guard) +PAGE_TYPE_OPS(Guard, guard, guard) extern bool is_free_buddy_page(struct page *page); @@ -1040,6 +1072,14 @@ static __always_inline void __ClearPageAnonExclusive(struct page *page) #define PAGE_FLAGS_CHECK_AT_PREP \ ((PAGEFLAGS_MASK & ~__PG_HWPOISON) | LRU_GEN_MASK | LRU_REFS_MASK) +/* + * Flags stored in the second page of a compound page. They may overlap + * the CHECK_AT_FREE flags above, so need to be cleared. + */ +#define PAGE_FLAGS_SECOND \ + (0xffUL /* order */ | 1UL << PG_has_hwpoisoned | \ + 1UL << PG_hugetlb | 1UL << PG_large_rmappable) + #define PAGE_FLAGS_PRIVATE \ (1UL << PG_private | 1UL << PG_private_2) /** diff --git a/include/linux/page_ext.h b/include/linux/page_ext.h index 67314f648aeb..be98564191e6 100644 --- a/include/linux/page_ext.h +++ b/include/linux/page_ext.h @@ -8,6 +8,7 @@ struct pglist_data; +#ifdef CONFIG_PAGE_EXTENSION /** * struct page_ext_operations - per page_ext client operations * @offset: Offset to the client's data within page_ext. Offset is returned to @@ -29,8 +30,6 @@ struct page_ext_operations { bool need_shared_flags; }; -#ifdef CONFIG_PAGE_EXTENSION - /* * The page_ext_flags users must set need_shared_flags to true. */ @@ -82,6 +81,12 @@ static inline void page_ext_init(void) extern struct page_ext *page_ext_get(struct page *page); extern void page_ext_put(struct page_ext *page_ext); +static inline void *page_ext_data(struct page_ext *page_ext, + struct page_ext_operations *ops) +{ + return (void *)(page_ext) + ops->offset; +} + static inline struct page_ext *page_ext_next(struct page_ext *curr) { void *next = curr; diff --git a/include/linux/page_idle.h b/include/linux/page_idle.h index 5cb7bd2078ec..d8f344840643 100644 --- a/include/linux/page_idle.h +++ b/include/linux/page_idle.h @@ -144,9 +144,4 @@ static inline void set_page_idle(struct page *page) { folio_set_idle(page_folio(page)); } - -static inline void clear_page_idle(struct page *page) -{ - folio_clear_idle(page_folio(page)); -} #endif /* _LINUX_MM_PAGE_IDLE_H */ diff --git a/include/linux/page_table_check.h b/include/linux/page_table_check.h index 01e16c7696ec..6722941c7cb8 100644 --- a/include/linux/page_table_check.h +++ b/include/linux/page_table_check.h @@ -14,18 +14,13 @@ extern struct static_key_true page_table_check_disabled; extern struct page_ext_operations page_table_check_ops; void __page_table_check_zero(struct page *page, unsigned int order); -void __page_table_check_pte_clear(struct mm_struct *mm, unsigned long addr, - pte_t pte); -void __page_table_check_pmd_clear(struct mm_struct *mm, unsigned long addr, - pmd_t pmd); -void __page_table_check_pud_clear(struct mm_struct *mm, unsigned long addr, - pud_t pud); -void __page_table_check_pte_set(struct mm_struct *mm, unsigned long addr, - pte_t *ptep, pte_t pte); -void __page_table_check_pmd_set(struct mm_struct *mm, unsigned long addr, - pmd_t *pmdp, pmd_t pmd); -void __page_table_check_pud_set(struct mm_struct *mm, unsigned long addr, - pud_t *pudp, pud_t pud); +void __page_table_check_pte_clear(struct mm_struct *mm, pte_t pte); +void __page_table_check_pmd_clear(struct mm_struct *mm, pmd_t pmd); +void __page_table_check_pud_clear(struct mm_struct *mm, pud_t pud); +void __page_table_check_ptes_set(struct mm_struct *mm, pte_t *ptep, pte_t pte, + unsigned int nr); +void __page_table_check_pmd_set(struct mm_struct *mm, pmd_t *pmdp, pmd_t pmd); +void __page_table_check_pud_set(struct mm_struct *mm, pud_t *pudp, pud_t pud); void __page_table_check_pte_clear_range(struct mm_struct *mm, unsigned long addr, pmd_t pmd); @@ -46,61 +41,55 @@ static inline void page_table_check_free(struct page *page, unsigned int order) __page_table_check_zero(page, order); } -static inline void page_table_check_pte_clear(struct mm_struct *mm, - unsigned long addr, pte_t pte) +static inline void page_table_check_pte_clear(struct mm_struct *mm, pte_t pte) { if (static_branch_likely(&page_table_check_disabled)) return; - __page_table_check_pte_clear(mm, addr, pte); + __page_table_check_pte_clear(mm, pte); } -static inline void page_table_check_pmd_clear(struct mm_struct *mm, - unsigned long addr, pmd_t pmd) +static inline void page_table_check_pmd_clear(struct mm_struct *mm, pmd_t pmd) { if (static_branch_likely(&page_table_check_disabled)) return; - __page_table_check_pmd_clear(mm, addr, pmd); + __page_table_check_pmd_clear(mm, pmd); } -static inline void page_table_check_pud_clear(struct mm_struct *mm, - unsigned long addr, pud_t pud) +static inline void page_table_check_pud_clear(struct mm_struct *mm, pud_t pud) { if (static_branch_likely(&page_table_check_disabled)) return; - __page_table_check_pud_clear(mm, addr, pud); + __page_table_check_pud_clear(mm, pud); } -static inline void page_table_check_pte_set(struct mm_struct *mm, - unsigned long addr, pte_t *ptep, - pte_t pte) +static inline void page_table_check_ptes_set(struct mm_struct *mm, + pte_t *ptep, pte_t pte, unsigned int nr) { if (static_branch_likely(&page_table_check_disabled)) return; - __page_table_check_pte_set(mm, addr, ptep, pte); + __page_table_check_ptes_set(mm, ptep, pte, nr); } -static inline void page_table_check_pmd_set(struct mm_struct *mm, - unsigned long addr, pmd_t *pmdp, +static inline void page_table_check_pmd_set(struct mm_struct *mm, pmd_t *pmdp, pmd_t pmd) { if (static_branch_likely(&page_table_check_disabled)) return; - __page_table_check_pmd_set(mm, addr, pmdp, pmd); + __page_table_check_pmd_set(mm, pmdp, pmd); } -static inline void page_table_check_pud_set(struct mm_struct *mm, - unsigned long addr, pud_t *pudp, +static inline void page_table_check_pud_set(struct mm_struct *mm, pud_t *pudp, pud_t pud) { if (static_branch_likely(&page_table_check_disabled)) return; - __page_table_check_pud_set(mm, addr, pudp, pud); + __page_table_check_pud_set(mm, pudp, pud); } static inline void page_table_check_pte_clear_range(struct mm_struct *mm, @@ -123,35 +112,29 @@ static inline void page_table_check_free(struct page *page, unsigned int order) { } -static inline void page_table_check_pte_clear(struct mm_struct *mm, - unsigned long addr, pte_t pte) +static inline void page_table_check_pte_clear(struct mm_struct *mm, pte_t pte) { } -static inline void page_table_check_pmd_clear(struct mm_struct *mm, - unsigned long addr, pmd_t pmd) +static inline void page_table_check_pmd_clear(struct mm_struct *mm, pmd_t pmd) { } -static inline void page_table_check_pud_clear(struct mm_struct *mm, - unsigned long addr, pud_t pud) +static inline void page_table_check_pud_clear(struct mm_struct *mm, pud_t pud) { } -static inline void page_table_check_pte_set(struct mm_struct *mm, - unsigned long addr, pte_t *ptep, - pte_t pte) +static inline void page_table_check_ptes_set(struct mm_struct *mm, + pte_t *ptep, pte_t pte, unsigned int nr) { } -static inline void page_table_check_pmd_set(struct mm_struct *mm, - unsigned long addr, pmd_t *pmdp, +static inline void page_table_check_pmd_set(struct mm_struct *mm, pmd_t *pmdp, pmd_t pmd) { } -static inline void page_table_check_pud_set(struct mm_struct *mm, - unsigned long addr, pud_t *pudp, +static inline void page_table_check_pud_set(struct mm_struct *mm, pud_t *pudp, pud_t pud) { } diff --git a/include/linux/pagemap.h b/include/linux/pagemap.h index d87840acbfb2..351c3b7f93a1 100644 --- a/include/linux/pagemap.h +++ b/include/linux/pagemap.h @@ -203,6 +203,7 @@ enum mapping_flags { /* writeback related tags are not used */ AS_NO_WRITEBACK_TAGS = 5, AS_LARGE_FOLIO_SUPPORT = 6, + AS_RELEASE_ALWAYS, /* Call ->release_folio(), even if no private data */ }; /** @@ -273,6 +274,21 @@ static inline int mapping_use_writeback_tags(struct address_space *mapping) return !test_bit(AS_NO_WRITEBACK_TAGS, &mapping->flags); } +static inline bool mapping_release_always(const struct address_space *mapping) +{ + return test_bit(AS_RELEASE_ALWAYS, &mapping->flags); +} + +static inline void mapping_set_release_always(struct address_space *mapping) +{ + set_bit(AS_RELEASE_ALWAYS, &mapping->flags); +} + +static inline void mapping_clear_release_always(struct address_space *mapping) +{ + clear_bit(AS_RELEASE_ALWAYS, &mapping->flags); +} + static inline gfp_t mapping_gfp_mask(struct address_space * mapping) { return mapping->gfp_mask; @@ -373,23 +389,31 @@ static inline struct address_space *folio_file_mapping(struct folio *folio) return folio->mapping; } -static inline struct address_space *page_file_mapping(struct page *page) -{ - return folio_file_mapping(page_folio(page)); -} - -/* - * For file cache pages, return the address_space, otherwise return NULL +/** + * folio_flush_mapping - Find the file mapping this folio belongs to. + * @folio: The folio. + * + * For folios which are in the page cache, return the mapping that this + * page belongs to. Anonymous folios return NULL, even if they're in + * the swap cache. Other kinds of folio also return NULL. + * + * This is ONLY used by architecture cache flushing code. If you aren't + * writing cache flushing code, you want either folio_mapping() or + * folio_file_mapping(). */ -static inline struct address_space *page_mapping_file(struct page *page) +static inline struct address_space *folio_flush_mapping(struct folio *folio) { - struct folio *folio = page_folio(page); - if (unlikely(folio_test_swapcache(folio))) return NULL; + return folio_mapping(folio); } +static inline struct address_space *page_file_mapping(struct page *page) +{ + return folio_file_mapping(page_folio(page)); +} + /** * folio_inode - Get the host inode for this folio. * @folio: The folio. @@ -960,8 +984,7 @@ static inline bool wake_page_match(struct wait_page_queue *wait_page, void __folio_lock(struct folio *folio); int __folio_lock_killable(struct folio *folio); -bool __folio_lock_or_retry(struct folio *folio, struct mm_struct *mm, - unsigned int flags); +vm_fault_t __folio_lock_or_retry(struct folio *folio, struct vm_fault *vmf); void unlock_page(struct page *page); void folio_unlock(struct folio *folio); @@ -1065,11 +1088,13 @@ static inline int folio_lock_killable(struct folio *folio) * Return value and mmap_lock implications depend on flags; see * __folio_lock_or_retry(). */ -static inline bool folio_lock_or_retry(struct folio *folio, - struct mm_struct *mm, unsigned int flags) +static inline vm_fault_t folio_lock_or_retry(struct folio *folio, + struct vm_fault *vmf) { might_sleep(); - return folio_trylock(folio) || __folio_lock_or_retry(folio, mm, flags); + if (!folio_trylock(folio)) + return __folio_lock_or_retry(folio, vmf); + return 0; } /* @@ -1104,11 +1129,6 @@ static inline void wait_on_page_locked(struct page *page) folio_wait_locked(page_folio(page)); } -static inline int wait_on_page_locked_killable(struct page *page) -{ - return folio_wait_locked_killable(page_folio(page)); -} - 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/pgtable.h b/include/linux/pgtable.h index 5063b482e34f..f49abcfe5eda 100644 --- a/include/linux/pgtable.h +++ b/include/linux/pgtable.h @@ -5,6 +5,9 @@ #include <linux/pfn.h> #include <asm/pgtable.h> +#define PMD_ORDER (PMD_SHIFT - PAGE_SHIFT) +#define PUD_ORDER (PUD_SHIFT - PAGE_SHIFT) + #ifndef __ASSEMBLY__ #ifdef CONFIG_MMU @@ -63,7 +66,6 @@ static inline unsigned long pte_index(unsigned long address) { return (address >> PAGE_SHIFT) & (PTRS_PER_PTE - 1); } -#define pte_index pte_index #ifndef pmd_index static inline unsigned long pmd_index(unsigned long address) @@ -99,7 +101,7 @@ static inline pte_t *pte_offset_kernel(pmd_t *pmd, unsigned long address) ((pte_t *)kmap_local_page(pmd_page(*(pmd))) + pte_index((address))) #define pte_unmap(pte) do { \ kunmap_local((pte)); \ - /* rcu_read_unlock() to be added later */ \ + rcu_read_unlock(); \ } while (0) #else static inline pte_t *__pte_map(pmd_t *pmd, unsigned long address) @@ -108,10 +110,12 @@ static inline pte_t *__pte_map(pmd_t *pmd, unsigned long address) } static inline void pte_unmap(pte_t *pte) { - /* rcu_read_unlock() to be added later */ + rcu_read_unlock(); } #endif +void pte_free_defer(struct mm_struct *mm, pgtable_t pgtable); + /* Find an entry in the second-level page table.. */ #ifndef pmd_offset static inline pmd_t *pmd_offset(pud_t *pud, unsigned long address) @@ -180,6 +184,60 @@ static inline int pmd_young(pmd_t pmd) } #endif +/* + * A facility to provide lazy MMU batching. This allows PTE updates and + * page invalidations to be delayed until a call to leave lazy MMU mode + * is issued. Some architectures may benefit from doing this, and it is + * beneficial for both shadow and direct mode hypervisors, which may batch + * the PTE updates which happen during this window. Note that using this + * interface requires that read hazards be removed from the code. A read + * hazard could result in the direct mode hypervisor case, since the actual + * write to the page tables may not yet have taken place, so reads though + * a raw PTE pointer after it has been modified are not guaranteed to be + * up to date. This mode can only be entered and left under the protection of + * the page table locks for all page tables which may be modified. In the UP + * case, this is required so that preemption is disabled, and in the SMP case, + * it must synchronize the delayed page table writes properly on other CPUs. + */ +#ifndef __HAVE_ARCH_ENTER_LAZY_MMU_MODE +#define arch_enter_lazy_mmu_mode() do {} while (0) +#define arch_leave_lazy_mmu_mode() do {} while (0) +#define arch_flush_lazy_mmu_mode() do {} while (0) +#endif + +#ifndef set_ptes +/** + * set_ptes - Map consecutive pages to a contiguous range of addresses. + * @mm: Address space to map the pages into. + * @addr: Address to map the first page at. + * @ptep: Page table pointer for the first entry. + * @pte: Page table entry for the first page. + * @nr: Number of pages to map. + * + * May be overridden by the architecture, or the architecture can define + * set_pte() and PFN_PTE_SHIFT. + * + * Context: The caller holds the page table lock. The pages all belong + * to the same folio. The PTEs are all in the same PMD. + */ +static inline void set_ptes(struct mm_struct *mm, unsigned long addr, + pte_t *ptep, pte_t pte, unsigned int nr) +{ + page_table_check_ptes_set(mm, ptep, pte, nr); + + arch_enter_lazy_mmu_mode(); + for (;;) { + set_pte(ptep, pte); + if (--nr == 0) + break; + ptep++; + pte = __pte(pte_val(pte) + (1UL << PFN_PTE_SHIFT)); + } + arch_leave_lazy_mmu_mode(); +} +#endif +#define set_pte_at(mm, addr, ptep, pte) set_ptes(mm, addr, ptep, pte, 1) + #ifndef __HAVE_ARCH_PTEP_SET_ACCESS_FLAGS extern int ptep_set_access_flags(struct vm_area_struct *vma, unsigned long address, pte_t *ptep, @@ -320,7 +378,7 @@ static inline pte_t ptep_get_and_clear(struct mm_struct *mm, { pte_t pte = ptep_get(ptep); pte_clear(mm, address, ptep); - page_table_check_pte_clear(mm, address, pte); + page_table_check_pte_clear(mm, pte); return pte; } #endif @@ -390,6 +448,7 @@ static inline pmd_t pmdp_get_lockless(pmd_t *pmdp) return pmd; } #define pmdp_get_lockless pmdp_get_lockless +#define pmdp_get_lockless_sync() tlb_remove_table_sync_one() #endif /* CONFIG_PGTABLE_LEVELS > 2 */ #endif /* CONFIG_GUP_GET_PXX_LOW_HIGH */ @@ -408,6 +467,9 @@ static inline pmd_t pmdp_get_lockless(pmd_t *pmdp) { return pmdp_get(pmdp); } +static inline void pmdp_get_lockless_sync(void) +{ +} #endif #ifdef CONFIG_TRANSPARENT_HUGEPAGE @@ -419,7 +481,7 @@ static inline pmd_t pmdp_huge_get_and_clear(struct mm_struct *mm, pmd_t pmd = *pmdp; pmd_clear(pmdp); - page_table_check_pmd_clear(mm, address, pmd); + page_table_check_pmd_clear(mm, pmd); return pmd; } @@ -432,7 +494,7 @@ static inline pud_t pudp_huge_get_and_clear(struct mm_struct *mm, pud_t pud = *pudp; pud_clear(pudp); - page_table_check_pud_clear(mm, address, pud); + page_table_check_pud_clear(mm, pud); return pud; } @@ -450,11 +512,11 @@ static inline pmd_t pmdp_huge_get_and_clear_full(struct vm_area_struct *vma, #endif #ifndef __HAVE_ARCH_PUDP_HUGE_GET_AND_CLEAR_FULL -static inline pud_t pudp_huge_get_and_clear_full(struct mm_struct *mm, +static inline pud_t pudp_huge_get_and_clear_full(struct vm_area_struct *vma, unsigned long address, pud_t *pudp, int full) { - return pudp_huge_get_and_clear(mm, address, pudp); + return pudp_huge_get_and_clear(vma->vm_mm, address, pudp); } #endif #endif /* CONFIG_TRANSPARENT_HUGEPAGE */ @@ -558,6 +620,7 @@ static inline void pmdp_set_wrprotect(struct mm_struct *mm, #endif #ifndef __HAVE_ARCH_PUDP_SET_WRPROTECT #ifdef CONFIG_HAVE_ARCH_TRANSPARENT_HUGEPAGE_PUD +#ifdef CONFIG_TRANSPARENT_HUGEPAGE static inline void pudp_set_wrprotect(struct mm_struct *mm, unsigned long address, pud_t *pudp) { @@ -571,6 +634,7 @@ static inline void pudp_set_wrprotect(struct mm_struct *mm, { BUILD_BUG(); } +#endif /* CONFIG_TRANSPARENT_HUGEPAGE */ #endif /* CONFIG_HAVE_ARCH_TRANSPARENT_HUGEPAGE_PUD */ #endif @@ -693,11 +757,14 @@ static inline int pmd_same(pmd_t pmd_a, pmd_t pmd_b) { return pmd_val(pmd_a) == pmd_val(pmd_b); } +#endif +#ifndef pud_same static inline int pud_same(pud_t pud_a, pud_t pud_b) { return pud_val(pud_a) == pud_val(pud_b); } +#define pud_same pud_same #endif #ifndef __HAVE_ARCH_P4D_SAME @@ -1041,27 +1108,6 @@ static inline pgprot_t pgprot_modify(pgprot_t oldprot, pgprot_t newprot) #endif /* - * A facility to provide lazy MMU batching. This allows PTE updates and - * page invalidations to be delayed until a call to leave lazy MMU mode - * is issued. Some architectures may benefit from doing this, and it is - * beneficial for both shadow and direct mode hypervisors, which may batch - * the PTE updates which happen during this window. Note that using this - * interface requires that read hazards be removed from the code. A read - * hazard could result in the direct mode hypervisor case, since the actual - * write to the page tables may not yet have taken place, so reads though - * a raw PTE pointer after it has been modified are not guaranteed to be - * up to date. This mode can only be entered and left under the protection of - * the page table locks for all page tables which may be modified. In the UP - * case, this is required so that preemption is disabled, and in the SMP case, - * it must synchronize the delayed page table writes properly on other CPUs. - */ -#ifndef __HAVE_ARCH_ENTER_LAZY_MMU_MODE -#define arch_enter_lazy_mmu_mode() do {} while (0) -#define arch_leave_lazy_mmu_mode() do {} while (0) -#define arch_flush_lazy_mmu_mode() do {} while (0) -#endif - -/* * A facility to provide batching of the reload of page tables and * other process state with the actual context switch code for * paravirtualized guests. By convention, only one of the batched @@ -1322,12 +1368,16 @@ static inline int pud_trans_unstable(pud_t *pud) #ifndef CONFIG_NUMA_BALANCING /* - * Technically a PTE can be PROTNONE even when not doing NUMA balancing but - * the only case the kernel cares is for NUMA balancing and is only ever set - * when the VMA is accessible. For PROT_NONE VMAs, the PTEs are not marked - * _PAGE_PROTNONE so by default, implement the helper as "always no". It - * is the responsibility of the caller to distinguish between PROT_NONE - * protections and NUMA hinting fault protections. + * In an inaccessible (PROT_NONE) VMA, pte_protnone() may indicate "yes". It is + * perfectly valid to indicate "no" in that case, which is why our default + * implementation defaults to "always no". + * + * In an accessible VMA, however, pte_protnone() reliably indicates PROT_NONE + * page protection due to NUMA hinting. NUMA hinting faults only apply in + * accessible VMAs. + * + * So, to reliably identify PROT_NONE PTEs that require a NUMA hinting fault, + * looking at the VMA accessibility is sufficient. */ static inline int pte_protnone(pte_t pte) { @@ -1499,6 +1549,9 @@ typedef unsigned int pgtbl_mod_mask; #define has_transparent_hugepage() IS_BUILTIN(CONFIG_TRANSPARENT_HUGEPAGE) #endif +#ifndef has_transparent_pud_hugepage +#define has_transparent_pud_hugepage() IS_BUILTIN(CONFIG_HAVE_ARCH_TRANSPARENT_HUGEPAGE_PUD) +#endif /* * On some architectures it depends on the mm if the p4d/pud or pmd * layer of the page table hierarchy is folded or not. diff --git a/include/linux/pid_namespace.h b/include/linux/pid_namespace.h index c758809d5bcf..f9f9931e02d6 100644 --- a/include/linux/pid_namespace.h +++ b/include/linux/pid_namespace.h @@ -17,18 +17,10 @@ struct fs_pin; #if defined(CONFIG_SYSCTL) && defined(CONFIG_MEMFD_CREATE) -/* - * sysctl for vm.memfd_noexec - * 0: memfd_create() without MFD_EXEC nor MFD_NOEXEC_SEAL - * acts like MFD_EXEC was set. - * 1: memfd_create() without MFD_EXEC nor MFD_NOEXEC_SEAL - * acts like MFD_NOEXEC_SEAL was set. - * 2: memfd_create() without MFD_NOEXEC_SEAL will be - * rejected. - */ -#define MEMFD_NOEXEC_SCOPE_EXEC 0 -#define MEMFD_NOEXEC_SCOPE_NOEXEC_SEAL 1 -#define MEMFD_NOEXEC_SCOPE_NOEXEC_ENFORCED 2 +/* modes for vm.memfd_noexec sysctl */ +#define MEMFD_NOEXEC_SCOPE_EXEC 0 /* MFD_EXEC implied if unset */ +#define MEMFD_NOEXEC_SCOPE_NOEXEC_SEAL 1 /* MFD_NOEXEC_SEAL implied if unset */ +#define MEMFD_NOEXEC_SCOPE_NOEXEC_ENFORCED 2 /* same as 1, except MFD_EXEC rejected */ #endif struct pid_namespace { @@ -47,7 +39,6 @@ struct pid_namespace { int reboot; /* group exit code if this pidns was rebooted */ struct ns_common ns; #if defined(CONFIG_SYSCTL) && defined(CONFIG_MEMFD_CREATE) - /* sysctl for vm.memfd_noexec */ int memfd_noexec_scope; #endif } __randomize_layout; @@ -64,6 +55,23 @@ static inline struct pid_namespace *get_pid_ns(struct pid_namespace *ns) return ns; } +#if defined(CONFIG_SYSCTL) && defined(CONFIG_MEMFD_CREATE) +static inline int pidns_memfd_noexec_scope(struct pid_namespace *ns) +{ + int scope = MEMFD_NOEXEC_SCOPE_EXEC; + + for (; ns; ns = ns->parent) + scope = max(scope, READ_ONCE(ns->memfd_noexec_scope)); + + return scope; +} +#else +static inline int pidns_memfd_noexec_scope(struct pid_namespace *ns) +{ + return 0; +} +#endif + extern struct pid_namespace *copy_pid_ns(unsigned long flags, struct user_namespace *user_ns, struct pid_namespace *ns); extern void zap_pid_ns_processes(struct pid_namespace *pid_ns); @@ -78,6 +86,11 @@ static inline struct pid_namespace *get_pid_ns(struct pid_namespace *ns) return ns; } +static inline int pidns_memfd_noexec_scope(struct pid_namespace *ns) +{ + return 0; +} + static inline struct pid_namespace *copy_pid_ns(unsigned long flags, struct user_namespace *user_ns, struct pid_namespace *ns) { diff --git a/include/linux/rmap.h b/include/linux/rmap.h index b87d01660412..a3825ce81102 100644 --- a/include/linux/rmap.h +++ b/include/linux/rmap.h @@ -198,6 +198,8 @@ void folio_add_new_anon_rmap(struct folio *, struct vm_area_struct *, unsigned long address); void page_add_file_rmap(struct page *, struct vm_area_struct *, bool compound); +void folio_add_file_rmap_range(struct folio *, struct page *, unsigned int nr, + struct vm_area_struct *, bool compound); void page_remove_rmap(struct page *, struct vm_area_struct *, bool compound); diff --git a/include/linux/secretmem.h b/include/linux/secretmem.h index 988528b5da43..35f3a4a8ceb1 100644 --- a/include/linux/secretmem.h +++ b/include/linux/secretmem.h @@ -6,24 +6,23 @@ extern const struct address_space_operations secretmem_aops; -static inline bool page_is_secretmem(struct page *page) +static inline bool folio_is_secretmem(struct folio *folio) { struct address_space *mapping; /* - * Using page_mapping() is quite slow because of the actual call - * instruction and repeated compound_head(page) inside the - * page_mapping() function. + * Using folio_mapping() is quite slow because of the actual call + * instruction. * We know that secretmem pages are not compound and LRU so we can * save a couple of cycles here. */ - if (PageCompound(page) || !PageLRU(page)) + if (folio_test_large(folio) || !folio_test_lru(folio)) return false; mapping = (struct address_space *) - ((unsigned long)page->mapping & ~PAGE_MAPPING_FLAGS); + ((unsigned long)folio->mapping & ~PAGE_MAPPING_FLAGS); - if (!mapping || mapping != page->mapping) + if (!mapping || mapping != folio->mapping) return false; return mapping->a_ops == &secretmem_aops; @@ -39,7 +38,7 @@ static inline bool vma_is_secretmem(struct vm_area_struct *vma) return false; } -static inline bool page_is_secretmem(struct page *page) +static inline bool folio_is_secretmem(struct folio *folio) { return false; } diff --git a/include/linux/swap.h b/include/linux/swap.h index 456546443f1f..493487ed7c38 100644 --- a/include/linux/swap.h +++ b/include/linux/swap.h @@ -302,10 +302,6 @@ struct swap_info_struct { struct file *swap_file; /* seldom referenced */ unsigned int old_block_size; /* seldom referenced */ struct completion comp; /* seldom referenced */ -#ifdef CONFIG_FRONTSWAP - unsigned long *frontswap_map; /* frontswap in-use, one bit per page */ - atomic_t frontswap_pages; /* frontswap pages in-use counter */ -#endif spinlock_t lock; /* * protect map scan related fields like * swap_map, lowest_bit, highest_bit, @@ -337,15 +333,13 @@ struct swap_info_struct { */ }; -static inline swp_entry_t folio_swap_entry(struct folio *folio) +static inline swp_entry_t page_swap_entry(struct page *page) { - swp_entry_t entry = { .val = page_private(&folio->page) }; - return entry; -} + struct folio *folio = page_folio(page); + swp_entry_t entry = folio->swap; -static inline void folio_set_swap_entry(struct folio *folio, swp_entry_t entry) -{ - folio->private = (void *)entry.val; + entry.val += folio_page_idx(folio, page); + return entry; } /* linux/mm/workingset.c */ @@ -630,11 +624,6 @@ static inline int mem_cgroup_swappiness(struct mem_cgroup *mem) } #endif -#ifdef CONFIG_ZSWAP -extern u64 zswap_pool_total_size; -extern atomic_t zswap_stored_pages; -#endif - #if defined(CONFIG_SWAP) && defined(CONFIG_MEMCG) && defined(CONFIG_BLK_CGROUP) void __folio_throttle_swaprate(struct folio *folio, gfp_t gfp); static inline void folio_throttle_swaprate(struct folio *folio, gfp_t gfp) diff --git a/include/linux/swapfile.h b/include/linux/swapfile.h index 7ed529a77c5b..99e3ed469e88 100644 --- a/include/linux/swapfile.h +++ b/include/linux/swapfile.h @@ -2,11 +2,6 @@ #ifndef _LINUX_SWAPFILE_H #define _LINUX_SWAPFILE_H -/* - * these were static in swapfile.c but frontswap.c needs them and we don't - * want to expose them to the dozens of source files that include swap.h - */ -extern struct swap_info_struct *swap_info[]; extern unsigned long generic_max_swapfile_size(void); unsigned long arch_max_swapfile_size(void); diff --git a/include/linux/swapops.h b/include/linux/swapops.h index 4c932cb45e0b..bff1e8d97de0 100644 --- a/include/linux/swapops.h +++ b/include/linux/swapops.h @@ -393,7 +393,12 @@ static inline bool is_migration_entry_dirty(swp_entry_t entry) typedef unsigned long pte_marker; #define PTE_MARKER_UFFD_WP BIT(0) -#define PTE_MARKER_SWAPIN_ERROR BIT(1) +/* + * "Poisoned" here is meant in the very general sense of "future accesses are + * invalid", instead of referring very specifically to hardware memory errors. + * This marker is meant to represent any of various different causes of this. + */ +#define PTE_MARKER_POISONED BIT(1) #define PTE_MARKER_MASK (BIT(2) - 1) static inline swp_entry_t make_pte_marker_entry(pte_marker marker) @@ -421,15 +426,15 @@ static inline pte_t make_pte_marker(pte_marker marker) return swp_entry_to_pte(make_pte_marker_entry(marker)); } -static inline swp_entry_t make_swapin_error_entry(void) +static inline swp_entry_t make_poisoned_swp_entry(void) { - return make_pte_marker_entry(PTE_MARKER_SWAPIN_ERROR); + return make_pte_marker_entry(PTE_MARKER_POISONED); } -static inline int is_swapin_error_entry(swp_entry_t entry) +static inline int is_poisoned_swp_entry(swp_entry_t entry) { return is_pte_marker_entry(entry) && - (pte_marker_get(entry) & PTE_MARKER_SWAPIN_ERROR); + (pte_marker_get(entry) & PTE_MARKER_POISONED); } /* diff --git a/include/linux/userfaultfd_k.h b/include/linux/userfaultfd_k.h index ac7b0c96d351..ac8c6854097c 100644 --- a/include/linux/userfaultfd_k.h +++ b/include/linux/userfaultfd_k.h @@ -46,6 +46,7 @@ enum mfill_atomic_mode { MFILL_ATOMIC_COPY, MFILL_ATOMIC_ZEROPAGE, MFILL_ATOMIC_CONTINUE, + MFILL_ATOMIC_POISON, NR_MFILL_ATOMIC_MODES, }; @@ -83,6 +84,9 @@ extern ssize_t mfill_atomic_zeropage(struct mm_struct *dst_mm, extern ssize_t mfill_atomic_continue(struct mm_struct *dst_mm, unsigned long dst_start, unsigned long len, atomic_t *mmap_changing, uffd_flags_t flags); +extern ssize_t mfill_atomic_poison(struct mm_struct *dst_mm, unsigned long start, + unsigned long len, atomic_t *mmap_changing, + uffd_flags_t flags); extern int mwriteprotect_range(struct mm_struct *dst_mm, unsigned long start, unsigned long len, bool enable_wp, atomic_t *mmap_changing); diff --git a/include/linux/zswap.h b/include/linux/zswap.h new file mode 100644 index 000000000000..2a60ce39cfde --- /dev/null +++ b/include/linux/zswap.h @@ -0,0 +1,37 @@ +/* SPDX-License-Identifier: GPL-2.0 */ +#ifndef _LINUX_ZSWAP_H +#define _LINUX_ZSWAP_H + +#include <linux/types.h> +#include <linux/mm_types.h> + +extern u64 zswap_pool_total_size; +extern atomic_t zswap_stored_pages; + +#ifdef CONFIG_ZSWAP + +bool zswap_store(struct folio *folio); +bool zswap_load(struct folio *folio); +void zswap_invalidate(int type, pgoff_t offset); +void zswap_swapon(int type); +void zswap_swapoff(int type); + +#else + +static inline bool zswap_store(struct folio *folio) +{ + return false; +} + +static inline bool zswap_load(struct folio *folio) +{ + return false; +} + +static inline void zswap_invalidate(int type, pgoff_t offset) {} +static inline void zswap_swapon(int type) {} +static inline void zswap_swapoff(int type) {} + +#endif + +#endif /* _LINUX_ZSWAP_H */ diff --git a/include/net/tcp.h b/include/net/tcp.h index 07b21d9a9620..91688d0dadcd 100644 --- a/include/net/tcp.h +++ b/include/net/tcp.h @@ -45,7 +45,6 @@ #include <linux/memcontrol.h> #include <linux/bpf-cgroup.h> #include <linux/siphash.h> -#include <linux/net_mm.h> extern struct inet_hashinfo tcp_hashinfo; diff --git a/include/trace/events/thp.h b/include/trace/events/thp.h index 202b3e3e67ff..f50048af5fcc 100644 --- a/include/trace/events/thp.h +++ b/include/trace/events/thp.h @@ -8,25 +8,34 @@ #include <linux/types.h> #include <linux/tracepoint.h> -TRACE_EVENT(hugepage_set_pmd, +DECLARE_EVENT_CLASS(hugepage_set, - TP_PROTO(unsigned long addr, unsigned long pmd), - TP_ARGS(addr, pmd), + TP_PROTO(unsigned long addr, unsigned long pte), + TP_ARGS(addr, pte), TP_STRUCT__entry( __field(unsigned long, addr) - __field(unsigned long, pmd) + __field(unsigned long, pte) ), TP_fast_assign( __entry->addr = addr; - __entry->pmd = pmd; + __entry->pte = pte; ), - TP_printk("Set pmd with 0x%lx with 0x%lx", __entry->addr, __entry->pmd) + TP_printk("Set page table entry with 0x%lx with 0x%lx", __entry->addr, __entry->pte) ); +DEFINE_EVENT(hugepage_set, hugepage_set_pmd, + TP_PROTO(unsigned long addr, unsigned long pmd), + TP_ARGS(addr, pmd) +); -TRACE_EVENT(hugepage_update, +DEFINE_EVENT(hugepage_set, hugepage_set_pud, + TP_PROTO(unsigned long addr, unsigned long pud), + TP_ARGS(addr, pud) +); + +DECLARE_EVENT_CLASS(hugepage_update, TP_PROTO(unsigned long addr, unsigned long pte, unsigned long clr, unsigned long set), TP_ARGS(addr, pte, clr, set), @@ -48,6 +57,16 @@ TRACE_EVENT(hugepage_update, TP_printk("hugepage update at addr 0x%lx and pte = 0x%lx clr = 0x%lx, set = 0x%lx", __entry->addr, __entry->pte, __entry->clr, __entry->set) ); +DEFINE_EVENT(hugepage_update, hugepage_update_pmd, + TP_PROTO(unsigned long addr, unsigned long pmd, unsigned long clr, unsigned long set), + TP_ARGS(addr, pmd, clr, set) +); + +DEFINE_EVENT(hugepage_update, hugepage_update_pud, + TP_PROTO(unsigned long addr, unsigned long pud, unsigned long clr, unsigned long set), + TP_ARGS(addr, pud, clr, set) +); + DECLARE_EVENT_CLASS(migration_pmd, TP_PROTO(unsigned long addr, unsigned long pmd), diff --git a/include/uapi/linux/userfaultfd.h b/include/uapi/linux/userfaultfd.h index 66dd4cd277bd..62151706c5a3 100644 --- a/include/uapi/linux/userfaultfd.h +++ b/include/uapi/linux/userfaultfd.h @@ -39,7 +39,8 @@ UFFD_FEATURE_MINOR_SHMEM | \ UFFD_FEATURE_EXACT_ADDRESS | \ UFFD_FEATURE_WP_HUGETLBFS_SHMEM | \ - UFFD_FEATURE_WP_UNPOPULATED) + UFFD_FEATURE_WP_UNPOPULATED | \ + UFFD_FEATURE_POISON) #define UFFD_API_IOCTLS \ ((__u64)1 << _UFFDIO_REGISTER | \ (__u64)1 << _UFFDIO_UNREGISTER | \ @@ -49,12 +50,14 @@ (__u64)1 << _UFFDIO_COPY | \ (__u64)1 << _UFFDIO_ZEROPAGE | \ (__u64)1 << _UFFDIO_WRITEPROTECT | \ - (__u64)1 << _UFFDIO_CONTINUE) + (__u64)1 << _UFFDIO_CONTINUE | \ + (__u64)1 << _UFFDIO_POISON) #define UFFD_API_RANGE_IOCTLS_BASIC \ ((__u64)1 << _UFFDIO_WAKE | \ (__u64)1 << _UFFDIO_COPY | \ + (__u64)1 << _UFFDIO_WRITEPROTECT | \ (__u64)1 << _UFFDIO_CONTINUE | \ - (__u64)1 << _UFFDIO_WRITEPROTECT) + (__u64)1 << _UFFDIO_POISON) /* * Valid ioctl command number range with this API is from 0x00 to @@ -71,6 +74,7 @@ #define _UFFDIO_ZEROPAGE (0x04) #define _UFFDIO_WRITEPROTECT (0x06) #define _UFFDIO_CONTINUE (0x07) +#define _UFFDIO_POISON (0x08) #define _UFFDIO_API (0x3F) /* userfaultfd ioctl ids */ @@ -91,6 +95,8 @@ struct uffdio_writeprotect) #define UFFDIO_CONTINUE _IOWR(UFFDIO, _UFFDIO_CONTINUE, \ struct uffdio_continue) +#define UFFDIO_POISON _IOWR(UFFDIO, _UFFDIO_POISON, \ + struct uffdio_poison) /* read() structure */ struct uffd_msg { @@ -225,6 +231,7 @@ struct uffdio_api { #define UFFD_FEATURE_EXACT_ADDRESS (1<<11) #define UFFD_FEATURE_WP_HUGETLBFS_SHMEM (1<<12) #define UFFD_FEATURE_WP_UNPOPULATED (1<<13) +#define UFFD_FEATURE_POISON (1<<14) __u64 features; __u64 ioctls; @@ -321,6 +328,18 @@ struct uffdio_continue { __s64 mapped; }; +struct uffdio_poison { + struct uffdio_range range; +#define UFFDIO_POISON_MODE_DONTWAKE ((__u64)1<<0) + __u64 mode; + + /* + * Fields below here are written by the ioctl and must be at the end: + * the copy_from_user will not read past here. + */ + __s64 updated; +}; + /* * Flags for the userfaultfd(2) system call itself. */ |