diff options
Diffstat (limited to 'mm/internal.h')
| -rw-r--r-- | mm/internal.h | 974 |
1 files changed, 764 insertions, 210 deletions
diff --git a/mm/internal.h b/mm/internal.h index d1d4bf4e63c0..e430da900430 100644 --- a/mm/internal.h +++ b/mm/internal.h @@ -8,14 +8,64 @@ #define __MM_INTERNAL_H #include <linux/fs.h> +#include <linux/khugepaged.h> #include <linux/mm.h> +#include <linux/mm_inline.h> #include <linux/pagemap.h> +#include <linux/pagewalk.h> #include <linux/rmap.h> +#include <linux/swap.h> +#include <linux/leafops.h> +#include <linux/swap_cgroup.h> #include <linux/tracepoint-defs.h> +/* Internal core VMA manipulation functions. */ +#include "vma.h" + struct folio_batch; /* + * Maintains state across a page table move. The operation assumes both source + * and destination VMAs already exist and are specified by the user. + * + * Partial moves are permitted, but the old and new ranges must both reside + * within a VMA. + * + * mmap lock must be held in write and VMA write locks must be held on any VMA + * that is visible. + * + * Use the PAGETABLE_MOVE() macro to initialise this struct. + * + * The old_addr and new_addr fields are updated as the page table move is + * executed. + * + * NOTE: The page table move is affected by reading from [old_addr, old_end), + * and old_addr may be updated for better page table alignment, so len_in + * represents the length of the range being copied as specified by the user. + */ +struct pagetable_move_control { + struct vm_area_struct *old; /* Source VMA. */ + struct vm_area_struct *new; /* Destination VMA. */ + unsigned long old_addr; /* Address from which the move begins. */ + unsigned long old_end; /* Exclusive address at which old range ends. */ + unsigned long new_addr; /* Address to move page tables to. */ + unsigned long len_in; /* Bytes to remap specified by user. */ + + bool need_rmap_locks; /* Do rmap locks need to be taken? */ + bool for_stack; /* Is this an early temp stack being moved? */ +}; + +#define PAGETABLE_MOVE(name, old_, new_, old_addr_, new_addr_, len_) \ + struct pagetable_move_control name = { \ + .old = old_, \ + .new = new_, \ + .old_addr = old_addr_, \ + .old_end = (old_addr_) + (len_), \ + .new_addr = new_addr_, \ + .len_in = len_, \ + } + +/* * The set of flags that only affect watermark checking and reclaim * behaviour. This is used by the MM to obey the caller constraints * about IO, FS and watermark checking while ignoring placement @@ -40,7 +90,7 @@ struct folio_batch; * when we specify __GFP_NOWARN. */ #define WARN_ON_ONCE_GFP(cond, gfp) ({ \ - static bool __section(".data.once") __warned; \ + static bool __section(".data..once") __warned; \ int __ret_warn_once = !!(cond); \ \ if (unlikely(!(gfp & __GFP_NOWARN) && __ret_warn_once && !__warned)) { \ @@ -54,12 +104,12 @@ void page_writeback_init(void); /* * If a 16GB hugetlb folio were mapped by PTEs of all of its 4kB pages, - * its nr_pages_mapped would be 0x400000: choose the COMPOUND_MAPPED bit + * its nr_pages_mapped would be 0x400000: choose the ENTIRELY_MAPPED bit * above that range, instead of 2*(PMD_SIZE/PAGE_SIZE). Hugetlb currently * leaves nr_pages_mapped at 0, but avoid surprise if it participates later. */ -#define COMPOUND_MAPPED 0x800000 -#define FOLIO_PAGES_MAPPED (COMPOUND_MAPPED - 1) +#define ENTIRELY_MAPPED 0x800000 +#define FOLIO_PAGES_MAPPED (ENTIRELY_MAPPED - 1) /* * Flags passed to __show_mem() and show_free_areas() to suppress output in @@ -70,19 +120,292 @@ void page_writeback_init(void); /* * How many individual pages have an elevated _mapcount. Excludes * the folio's entire_mapcount. + * + * Don't use this function outside of debugging code. */ -static inline int folio_nr_pages_mapped(struct folio *folio) +static inline int folio_nr_pages_mapped(const struct folio *folio) { + if (IS_ENABLED(CONFIG_NO_PAGE_MAPCOUNT)) + return -1; return atomic_read(&folio->_nr_pages_mapped) & FOLIO_PAGES_MAPPED; } -static inline void *folio_raw_mapping(struct folio *folio) +/* + * Retrieve the first entry of a folio based on a provided entry within the + * folio. We cannot rely on folio->swap as there is no guarantee that it has + * been initialized. Used for calling arch_swap_restore() + */ +static inline swp_entry_t folio_swap(swp_entry_t entry, + const struct folio *folio) +{ + swp_entry_t swap = { + .val = ALIGN_DOWN(entry.val, folio_nr_pages(folio)), + }; + + return swap; +} + +static inline void *folio_raw_mapping(const struct folio *folio) { unsigned long mapping = (unsigned long)folio->mapping; - return (void *)(mapping & ~PAGE_MAPPING_FLAGS); + return (void *)(mapping & ~FOLIO_MAPPING_FLAGS); +} + +/* + * This is a file-backed mapping, and is about to be memory mapped - invoke its + * mmap hook and safely handle error conditions. On error, VMA hooks will be + * mutated. + * + * @file: File which backs the mapping. + * @vma: VMA which we are mapping. + * + * Returns: 0 if success, error otherwise. + */ +static inline int mmap_file(struct file *file, struct vm_area_struct *vma) +{ + int err = vfs_mmap(file, vma); + + if (likely(!err)) + return 0; + + /* + * OK, we tried to call the file hook for mmap(), but an error + * arose. The mapping is in an inconsistent state and we most not invoke + * any further hooks on it. + */ + vma->vm_ops = &vma_dummy_vm_ops; + + return err; +} + +/* + * If the VMA has a close hook then close it, and since closing it might leave + * it in an inconsistent state which makes the use of any hooks suspect, clear + * them down by installing dummy empty hooks. + */ +static inline void vma_close(struct vm_area_struct *vma) +{ + if (vma->vm_ops && vma->vm_ops->close) { + vma->vm_ops->close(vma); + + /* + * The mapping is in an inconsistent state, and no further hooks + * may be invoked upon it. + */ + vma->vm_ops = &vma_dummy_vm_ops; + } +} + +#ifdef CONFIG_MMU + +/* Flags for folio_pte_batch(). */ +typedef int __bitwise fpb_t; + +/* Compare PTEs respecting the dirty bit. */ +#define FPB_RESPECT_DIRTY ((__force fpb_t)BIT(0)) + +/* Compare PTEs respecting the soft-dirty bit. */ +#define FPB_RESPECT_SOFT_DIRTY ((__force fpb_t)BIT(1)) + +/* Compare PTEs respecting the writable bit. */ +#define FPB_RESPECT_WRITE ((__force fpb_t)BIT(2)) + +/* + * Merge PTE write bits: if any PTE in the batch is writable, modify the + * PTE at @ptentp to be writable. + */ +#define FPB_MERGE_WRITE ((__force fpb_t)BIT(3)) + +/* + * Merge PTE young and dirty bits: if any PTE in the batch is young or dirty, + * modify the PTE at @ptentp to be young or dirty, respectively. + */ +#define FPB_MERGE_YOUNG_DIRTY ((__force fpb_t)BIT(4)) + +static inline pte_t __pte_batch_clear_ignored(pte_t pte, fpb_t flags) +{ + if (!(flags & FPB_RESPECT_DIRTY)) + pte = pte_mkclean(pte); + if (likely(!(flags & FPB_RESPECT_SOFT_DIRTY))) + pte = pte_clear_soft_dirty(pte); + if (likely(!(flags & FPB_RESPECT_WRITE))) + pte = pte_wrprotect(pte); + return pte_mkold(pte); +} + +/** + * folio_pte_batch_flags - detect a PTE batch for a large folio + * @folio: The large folio to detect a PTE batch for. + * @vma: The VMA. Only relevant with FPB_MERGE_WRITE, otherwise can be NULL. + * @ptep: Page table pointer for the first entry. + * @ptentp: Pointer to a COPY of the first page table entry whose flags this + * function updates based on @flags if appropriate. + * @max_nr: The maximum number of table entries to consider. + * @flags: Flags to modify the PTE batch semantics. + * + * Detect a PTE batch: consecutive (present) PTEs that map consecutive + * pages of the same large folio in a single VMA and a single page table. + * + * All PTEs inside a PTE batch have the same PTE bits set, excluding the PFN, + * the accessed bit, writable bit, dirty bit (unless FPB_RESPECT_DIRTY is set) + * and soft-dirty bit (unless FPB_RESPECT_SOFT_DIRTY is set). + * + * @ptep must map any page of the folio. max_nr must be at least one and + * must be limited by the caller so scanning cannot exceed a single VMA and + * a single page table. + * + * Depending on the FPB_MERGE_* flags, the pte stored at @ptentp will + * be updated: it's crucial that a pointer to a COPY of the first + * page table entry, obtained through ptep_get(), is provided as @ptentp. + * + * This function will be inlined to optimize based on the input parameters; + * consider using folio_pte_batch() instead if applicable. + * + * Return: the number of table entries in the batch. + */ +static inline unsigned int folio_pte_batch_flags(struct folio *folio, + struct vm_area_struct *vma, pte_t *ptep, pte_t *ptentp, + unsigned int max_nr, fpb_t flags) +{ + bool any_writable = false, any_young = false, any_dirty = false; + pte_t expected_pte, pte = *ptentp; + unsigned int nr, cur_nr; + + VM_WARN_ON_FOLIO(!pte_present(pte), folio); + VM_WARN_ON_FOLIO(!folio_test_large(folio) || max_nr < 1, folio); + VM_WARN_ON_FOLIO(page_folio(pfn_to_page(pte_pfn(pte))) != folio, folio); + /* + * Ensure this is a pointer to a copy not a pointer into a page table. + * If this is a stack value, it won't be a valid virtual address, but + * that's fine because it also cannot be pointing into the page table. + */ + VM_WARN_ON(virt_addr_valid(ptentp) && PageTable(virt_to_page(ptentp))); + + /* Limit max_nr to the actual remaining PFNs in the folio we could batch. */ + max_nr = min_t(unsigned long, max_nr, + folio_pfn(folio) + folio_nr_pages(folio) - pte_pfn(pte)); + + nr = pte_batch_hint(ptep, pte); + expected_pte = __pte_batch_clear_ignored(pte_advance_pfn(pte, nr), flags); + ptep = ptep + nr; + + while (nr < max_nr) { + pte = ptep_get(ptep); + + if (!pte_same(__pte_batch_clear_ignored(pte, flags), expected_pte)) + break; + + if (flags & FPB_MERGE_WRITE) + any_writable |= pte_write(pte); + if (flags & FPB_MERGE_YOUNG_DIRTY) { + any_young |= pte_young(pte); + any_dirty |= pte_dirty(pte); + } + + cur_nr = pte_batch_hint(ptep, pte); + expected_pte = pte_advance_pfn(expected_pte, cur_nr); + ptep += cur_nr; + nr += cur_nr; + } + + if (any_writable) + *ptentp = pte_mkwrite(*ptentp, vma); + if (any_young) + *ptentp = pte_mkyoung(*ptentp); + if (any_dirty) + *ptentp = pte_mkdirty(*ptentp); + + return min(nr, max_nr); +} + +unsigned int folio_pte_batch(struct folio *folio, pte_t *ptep, pte_t pte, + unsigned int max_nr); + +/** + * pte_move_swp_offset - Move the swap entry offset field of a swap pte + * forward or backward by delta + * @pte: The initial pte state; must be a swap entry + * @delta: The direction and the offset we are moving; forward if delta + * is positive; backward if delta is negative + * + * Moves the swap offset, while maintaining all other fields, including + * swap type, and any swp pte bits. The resulting pte is returned. + */ +static inline pte_t pte_move_swp_offset(pte_t pte, long delta) +{ + const softleaf_t entry = softleaf_from_pte(pte); + pte_t new = __swp_entry_to_pte(__swp_entry(swp_type(entry), + (swp_offset(entry) + delta))); + + if (pte_swp_soft_dirty(pte)) + new = pte_swp_mksoft_dirty(new); + if (pte_swp_exclusive(pte)) + new = pte_swp_mkexclusive(new); + if (pte_swp_uffd_wp(pte)) + new = pte_swp_mkuffd_wp(new); + + return new; } + +/** + * pte_next_swp_offset - Increment the swap entry offset field of a swap pte. + * @pte: The initial pte state; must be a swap entry. + * + * Increments the swap offset, while maintaining all other fields, including + * swap type, and any swp pte bits. The resulting pte is returned. + */ +static inline pte_t pte_next_swp_offset(pte_t pte) +{ + return pte_move_swp_offset(pte, 1); +} + +/** + * swap_pte_batch - detect a PTE batch for a set of contiguous swap entries + * @start_ptep: Page table pointer for the first entry. + * @max_nr: The maximum number of table entries to consider. + * @pte: Page table entry for the first entry. + * + * Detect a batch of contiguous swap entries: consecutive (non-present) PTEs + * containing swap entries all with consecutive offsets and targeting the same + * swap type, all with matching swp pte bits. + * + * max_nr must be at least one and must be limited by the caller so scanning + * cannot exceed a single page table. + * + * Return: the number of table entries in the batch. + */ +static inline int swap_pte_batch(pte_t *start_ptep, int max_nr, pte_t pte) +{ + pte_t expected_pte = pte_next_swp_offset(pte); + const pte_t *end_ptep = start_ptep + max_nr; + const softleaf_t entry = softleaf_from_pte(pte); + pte_t *ptep = start_ptep + 1; + unsigned short cgroup_id; + + VM_WARN_ON(max_nr < 1); + VM_WARN_ON(!softleaf_is_swap(entry)); + + cgroup_id = lookup_swap_cgroup_id(entry); + while (ptep < end_ptep) { + softleaf_t entry; + + pte = ptep_get(ptep); + + if (!pte_same(pte, expected_pte)) + break; + entry = softleaf_from_pte(pte); + if (lookup_swap_cgroup_id(entry) != cgroup_id) + break; + expected_pte = pte_next_swp_offset(expected_pte); + ptep++; + } + + return ptep - start_ptep; +} +#endif /* CONFIG_MMU */ + void __acct_reclaim_writeback(pg_data_t *pgdat, struct folio *folio, int nr_throttled); static inline void acct_reclaim_writeback(struct folio *folio) @@ -103,6 +426,16 @@ static inline void wake_throttle_isolated(pg_data_t *pgdat) wake_up(wqh); } +vm_fault_t __vmf_anon_prepare(struct vm_fault *vmf); +static inline vm_fault_t vmf_anon_prepare(struct vm_fault *vmf) +{ + vm_fault_t ret = __vmf_anon_prepare(vmf); + + if (unlikely(ret & VM_FAULT_RETRY)) + vma_end_read(vmf->vma); + return ret; +} + vm_fault_t do_swap_page(struct vm_fault *vmf); void folio_rotate_reclaimable(struct folio *folio); bool __folio_end_writeback(struct folio *folio); @@ -119,9 +452,13 @@ void unmap_page_range(struct mmu_gather *tlb, struct vm_area_struct *vma, unsigned long addr, unsigned long end, struct zap_details *details); +void zap_page_range_single_batched(struct mmu_gather *tlb, + struct vm_area_struct *vma, unsigned long addr, + unsigned long size, struct zap_details *details); +int folio_unmap_invalidate(struct address_space *mapping, struct folio *folio, + gfp_t gfp); -void page_cache_ra_order(struct readahead_control *, struct file_ra_state *, - unsigned int order); +void page_cache_ra_order(struct readahead_control *, struct file_ra_state *); void force_page_cache_ra(struct readahead_control *, unsigned long nr); static inline void force_page_cache_readahead(struct address_space *mapping, struct file *file, pgoff_t index, unsigned long nr_to_read) @@ -138,7 +475,7 @@ void filemap_free_folio(struct address_space *mapping, struct folio *folio); int truncate_inode_folio(struct address_space *mapping, struct folio *folio); bool truncate_inode_partial_folio(struct folio *folio, loff_t start, loff_t end); -long invalidate_inode_page(struct page *page); +long mapping_evict_folio(struct address_space *mapping, struct folio *folio); unsigned long mapping_try_invalidate(struct address_space *mapping, pgoff_t start, pgoff_t end, unsigned long *nr_failed); @@ -198,11 +535,19 @@ extern unsigned long highest_memmap_pfn; /* * in mm/vmscan.c: */ -bool isolate_lru_page(struct page *page); bool folio_isolate_lru(struct folio *folio); -void putback_lru_page(struct page *page); void folio_putback_lru(struct folio *folio); extern void reclaim_throttle(pg_data_t *pgdat, enum vmscan_throttle_state reason); +#ifdef CONFIG_NUMA +int user_proactive_reclaim(char *buf, + struct mem_cgroup *memcg, pg_data_t *pgdat); +#else +static inline int user_proactive_reclaim(char *buf, + struct mem_cgroup *memcg, pg_data_t *pgdat) +{ + return 0; +} +#endif /* * in mm/rmap.c: @@ -220,6 +565,7 @@ extern char * const zone_names[MAX_NR_ZONES]; DECLARE_STATIC_KEY_MAYBE(CONFIG_DEBUG_VM, check_pages_enabled); extern int min_free_kbytes; +extern int defrag_mode; void setup_per_zone_wmarks(void); void calculate_min_free_kbytes(void); @@ -335,7 +681,7 @@ static inline bool page_is_buddy(struct page *page, struct page *buddy, * satisfies the following equation: * P = B & ~(1 << O) * - * Assumption: *_mem_map is contiguous at least up to MAX_ORDER + * Assumption: *_mem_map is contiguous at least up to MAX_PAGE_ORDER */ static inline unsigned long __find_buddy_pfn(unsigned long page_pfn, unsigned int order) @@ -385,6 +731,8 @@ static inline struct page *pageblock_pfn_to_page(unsigned long start_pfn, } void set_zone_contiguous(struct zone *zone); +bool pfn_range_intersects_zones(int nid, unsigned long start_pfn, + unsigned long nr_pages); static inline void clear_zone_contiguous(struct zone *zone) { @@ -396,7 +744,8 @@ extern void __putback_isolated_page(struct page *page, unsigned int order, int mt); extern void memblock_free_pages(struct page *page, unsigned long pfn, unsigned int order); -extern void __free_pages_core(struct page *page, unsigned int order); +extern void __free_pages_core(struct page *page, unsigned int order, + enum meminit_context context); /* * This will have no effect, other than possibly generating a warning, if the @@ -406,23 +755,59 @@ static inline void folio_set_order(struct folio *folio, unsigned int order) { if (WARN_ON_ONCE(!order || !folio_test_large(folio))) return; + VM_WARN_ON_ONCE(order > MAX_FOLIO_ORDER); folio->_flags_1 = (folio->_flags_1 & ~0xffUL) | order; -#ifdef CONFIG_64BIT - folio->_folio_nr_pages = 1U << order; +#ifdef NR_PAGES_IN_LARGE_FOLIO + folio->_nr_pages = 1U << order; #endif } -void folio_undo_large_rmappable(struct folio *folio); +bool __folio_unqueue_deferred_split(struct folio *folio); +static inline bool folio_unqueue_deferred_split(struct folio *folio) +{ + if (folio_order(folio) <= 1 || !folio_test_large_rmappable(folio)) + return false; + + /* + * At this point, there is no one trying to add the folio to + * deferred_list. If folio is not in deferred_list, it's safe + * to check without acquiring the split_queue_lock. + */ + if (data_race(list_empty(&folio->_deferred_list))) + return false; + + return __folio_unqueue_deferred_split(folio); +} + +static inline struct folio *page_rmappable_folio(struct page *page) +{ + struct folio *folio = (struct folio *)page; + + if (folio && folio_test_large(folio)) + folio_set_large_rmappable(folio); + return folio; +} static inline void prep_compound_head(struct page *page, unsigned int order) { struct folio *folio = (struct folio *)page; folio_set_order(folio, order); - atomic_set(&folio->_entire_mapcount, -1); - atomic_set(&folio->_nr_pages_mapped, 0); - atomic_set(&folio->_pincount, 0); + atomic_set(&folio->_large_mapcount, -1); + if (IS_ENABLED(CONFIG_PAGE_MAPCOUNT)) + atomic_set(&folio->_nr_pages_mapped, 0); + if (IS_ENABLED(CONFIG_MM_ID)) { + folio->_mm_ids = 0; + folio->_mm_id_mapcount[0] = -1; + folio->_mm_id_mapcount[1] = -1; + } + if (IS_ENABLED(CONFIG_64BIT) || order > 1) { + atomic_set(&folio->_pincount, 0); + atomic_set(&folio->_entire_mapcount, -1); + } + if (order > 1) + INIT_LIST_HEAD(&folio->_deferred_list); } static inline void prep_compound_tail(struct page *head, int tail_idx) @@ -434,14 +819,33 @@ static inline void prep_compound_tail(struct page *head, int tail_idx) set_page_private(p, 0); } -extern void prep_compound_page(struct page *page, unsigned int order); +void post_alloc_hook(struct page *page, unsigned int order, gfp_t gfp_flags); +extern bool free_pages_prepare(struct page *page, unsigned int order); -extern void post_alloc_hook(struct page *page, unsigned int order, - gfp_t gfp_flags); extern int user_min_free_kbytes; -extern void free_unref_page(struct page *page, unsigned int order); -extern void free_unref_page_list(struct list_head *list); +struct page *__alloc_frozen_pages_noprof(gfp_t, unsigned int order, int nid, + nodemask_t *); +#define __alloc_frozen_pages(...) \ + alloc_hooks(__alloc_frozen_pages_noprof(__VA_ARGS__)) +void free_frozen_pages(struct page *page, unsigned int order); +void free_unref_folios(struct folio_batch *fbatch); + +#ifdef CONFIG_NUMA +struct page *alloc_frozen_pages_noprof(gfp_t, unsigned int order); +#else +static inline struct page *alloc_frozen_pages_noprof(gfp_t gfp, unsigned int order) +{ + return __alloc_frozen_pages_noprof(gfp, order, numa_node_id(), NULL); +} +#endif + +#define alloc_frozen_pages(...) \ + alloc_hooks(alloc_frozen_pages_noprof(__VA_ARGS__)) + +struct page *alloc_frozen_pages_nolock_noprof(gfp_t gfp_flags, int nid, unsigned int order); +#define alloc_frozen_pages_nolock(...) \ + alloc_hooks(alloc_frozen_pages_nolock_noprof(__VA_ARGS__)) extern void zone_pcp_reset(struct zone *zone); extern void zone_pcp_disable(struct zone *zone); @@ -453,11 +857,8 @@ extern void *memmap_alloc(phys_addr_t size, phys_addr_t align, int nid, bool exact_nid); void memmap_init_range(unsigned long, int, unsigned long, unsigned long, - unsigned long, enum meminit_context, struct vmem_altmap *, int); - - -int split_free_page(struct page *free_page, - unsigned int order, unsigned long split_pfn_offset); + unsigned long, enum meminit_context, struct vmem_altmap *, int, + bool); #if defined CONFIG_COMPACTION || defined CONFIG_CMA @@ -472,7 +873,7 @@ int split_free_page(struct page *free_page, * completes when free_pfn <= migrate_pfn */ struct compact_control { - struct list_head freepages; /* List of free pages to migrate to */ + struct list_head freepages[NR_PAGE_ORDERS]; /* List of free pages to migrate to */ struct list_head migratepages; /* List of pages being migrated */ unsigned int nr_freepages; /* Number of isolated free pages */ unsigned int nr_migratepages; /* Number of pages to migrate */ @@ -527,81 +928,108 @@ int isolate_migratepages_range(struct compact_control *cc, unsigned long low_pfn, unsigned long end_pfn); -int __alloc_contig_migrate_range(struct compact_control *cc, - unsigned long start, unsigned long end); - /* Free whole pageblock and set its migration type to MIGRATE_CMA. */ void init_cma_reserved_pageblock(struct page *page); #endif /* CONFIG_COMPACTION || CONFIG_CMA */ +struct cma; + +#ifdef CONFIG_CMA +void *cma_reserve_early(struct cma *cma, unsigned long size); +void init_cma_pageblock(struct page *page); +#else +static inline void *cma_reserve_early(struct cma *cma, unsigned long size) +{ + return NULL; +} +static inline void init_cma_pageblock(struct page *page) +{ +} +#endif + + int find_suitable_fallback(struct free_area *area, unsigned int order, - int migratetype, bool only_stealable, bool *can_steal); + int migratetype, bool claimable); static inline bool free_area_empty(struct free_area *area, int migratetype) { return list_empty(&area->free_list[migratetype]); } -/* - * These three helpers classifies VMAs for virtual memory accounting. - */ +/* mm/util.c */ +struct anon_vma *folio_anon_vma(const struct folio *folio); -/* - * Executable code area - executable, not writable, not stack - */ -static inline bool is_exec_mapping(vm_flags_t flags) -{ - return (flags & (VM_EXEC | VM_WRITE | VM_STACK)) == VM_EXEC; -} +#ifdef CONFIG_MMU +void unmap_mapping_folio(struct folio *folio); +extern long populate_vma_page_range(struct vm_area_struct *vma, + unsigned long start, unsigned long end, int *locked); +extern long faultin_page_range(struct mm_struct *mm, unsigned long start, + unsigned long end, bool write, int *locked); +bool mlock_future_ok(const struct mm_struct *mm, vm_flags_t vm_flags, + unsigned long bytes); /* - * Stack area - automatically grows in one direction + * NOTE: This function can't tell whether the folio is "fully mapped" in the + * range. + * "fully mapped" means all the pages of folio is associated with the page + * table of range while this function just check whether the folio range is + * within the range [start, end). Function caller needs to do page table + * check if it cares about the page table association. * - * VM_GROWSUP / VM_GROWSDOWN VMAs are always private anonymous: - * do_mmap() forbids all other combinations. + * Typical usage (like mlock or madvise) is: + * Caller knows at least 1 page of folio is associated with page table of VMA + * and the range [start, end) is intersect with the VMA range. Caller wants + * to know whether the folio is fully associated with the range. It calls + * this function to check whether the folio is in the range first. Then checks + * the page table to know whether the folio is fully mapped to the range. */ -static inline bool is_stack_mapping(vm_flags_t flags) +static inline bool +folio_within_range(struct folio *folio, struct vm_area_struct *vma, + unsigned long start, unsigned long end) { - return (flags & VM_STACK) == VM_STACK; + pgoff_t pgoff, addr; + unsigned long vma_pglen = vma_pages(vma); + + VM_WARN_ON_FOLIO(folio_test_ksm(folio), folio); + if (start > end) + return false; + + if (start < vma->vm_start) + start = vma->vm_start; + + if (end > vma->vm_end) + end = vma->vm_end; + + pgoff = folio_pgoff(folio); + + /* if folio start address is not in vma range */ + if (!in_range(pgoff, vma->vm_pgoff, vma_pglen)) + return false; + + addr = vma->vm_start + ((pgoff - vma->vm_pgoff) << PAGE_SHIFT); + + return !(addr < start || end - addr < folio_size(folio)); } -/* - * Data area - private, writable, not stack - */ -static inline bool is_data_mapping(vm_flags_t flags) +static inline bool +folio_within_vma(struct folio *folio, struct vm_area_struct *vma) { - return (flags & (VM_WRITE | VM_SHARED | VM_STACK)) == VM_WRITE; + return folio_within_range(folio, vma, vma->vm_start, vma->vm_end); } -/* mm/util.c */ -struct anon_vma *folio_anon_vma(struct folio *folio); - -#ifdef CONFIG_MMU -void unmap_mapping_folio(struct folio *folio); -extern long populate_vma_page_range(struct vm_area_struct *vma, - unsigned long start, unsigned long end, int *locked); -extern long faultin_vma_page_range(struct vm_area_struct *vma, - unsigned long start, unsigned long end, - bool write, int *locked); -extern bool mlock_future_ok(struct mm_struct *mm, unsigned long flags, - unsigned long bytes); /* * mlock_vma_folio() and munlock_vma_folio(): * should be called with vma's mmap_lock held for read or write, * under page table lock for the pte/pmd being added or removed. * - * mlock is usually called at the end of page_add_*_rmap(), munlock at - * the end of page_remove_rmap(); but new anon folios are managed by + * mlock is usually called at the end of folio_add_*_rmap_*(), munlock at + * the end of folio_remove_rmap_*(); but new anon folios are managed by * folio_add_lru_vma() calling mlock_new_folio(). - * - * @compound is used to include pmd mappings of THPs, but filter out - * pte mappings of THPs, which cannot be consistently counted: a pte - * mapping of the THP head cannot be distinguished by the page alone. */ void mlock_folio(struct folio *folio); static inline void mlock_vma_folio(struct folio *folio, - struct vm_area_struct *vma, bool compound) + struct vm_area_struct *vma) { /* * The VM_SPECIAL check here serves two purposes. @@ -611,17 +1039,24 @@ static inline void mlock_vma_folio(struct folio *folio, * file->f_op->mmap() is using vm_insert_page(s), when VM_LOCKED may * still be set while VM_SPECIAL bits are added: so ignore it then. */ - if (unlikely((vma->vm_flags & (VM_LOCKED|VM_SPECIAL)) == VM_LOCKED) && - (compound || !folio_test_large(folio))) + if (unlikely((vma->vm_flags & (VM_LOCKED|VM_SPECIAL)) == VM_LOCKED)) mlock_folio(folio); } void munlock_folio(struct folio *folio); static inline void munlock_vma_folio(struct folio *folio, - struct vm_area_struct *vma, bool compound) + struct vm_area_struct *vma) { - if (unlikely(vma->vm_flags & VM_LOCKED) && - (compound || !folio_test_large(folio))) + /* + * munlock if the function is called. Ideally, we should only + * do munlock if any page of folio is unmapped from VMA and + * cause folio not fully mapped to VMA. + * + * But it's not easy to confirm that's the situation. So we + * always munlock the folio and page reclaim will correct it + * if it's wrong. + */ + if (unlikely(vma->vm_flags & VM_LOCKED)) munlock_folio(folio); } @@ -632,13 +1067,17 @@ void mlock_drain_remote(int cpu); extern pmd_t maybe_pmd_mkwrite(pmd_t pmd, struct vm_area_struct *vma); -/* - * Return the start of user virtual address at the specific offset within - * a vma. +/** + * vma_address - Find the virtual address a page range is mapped at + * @vma: The vma which maps this object. + * @pgoff: The page offset within its object. + * @nr_pages: The number of pages to consider. + * + * If any page in this range is mapped by this VMA, return the first address + * where any of these pages appear. Otherwise, return -EFAULT. */ -static inline unsigned long -vma_pgoff_address(pgoff_t pgoff, unsigned long nr_pages, - struct vm_area_struct *vma) +static inline unsigned long vma_address(const struct vm_area_struct *vma, + pgoff_t pgoff, unsigned long nr_pages) { unsigned long address; @@ -658,18 +1097,6 @@ vma_pgoff_address(pgoff_t pgoff, unsigned long nr_pages, } /* - * Return the start of user virtual address of a page within a vma. - * Returns -EFAULT if all of the page is outside the range of vma. - * If page is a compound head, the entire compound page is considered. - */ -static inline unsigned long -vma_address(struct page *page, struct vm_area_struct *vma) -{ - VM_BUG_ON_PAGE(PageKsm(page), page); /* KSM page->index unusable */ - return vma_pgoff_address(page_to_pgoff(page), compound_nr(page), vma); -} - -/* * Then at what user virtual address will none of the range be found in vma? * Assumes that vma_address() already returned a good starting address. */ @@ -729,6 +1156,8 @@ DECLARE_STATIC_KEY_TRUE(deferred_pages); bool __init deferred_grow_zone(struct zone *zone, unsigned int order); #endif /* CONFIG_DEFERRED_STRUCT_PAGE_INIT */ +void init_deferred_page(unsigned long pfn, int nid); + enum mminit_level { MMINIT_WARNING, MMINIT_VERIFY, @@ -773,9 +1202,13 @@ static inline void mminit_verify_zonelist(void) #define NODE_RECLAIM_SUCCESS 1 #ifdef CONFIG_NUMA +extern int node_reclaim_mode; + extern int node_reclaim(struct pglist_data *, gfp_t, unsigned int); extern int find_next_best_node(int node, nodemask_t *used_node_mask); #else +#define node_reclaim_mode 0 + static inline int node_reclaim(struct pglist_data *pgdat, gfp_t mask, unsigned int order) { @@ -787,17 +1220,40 @@ static inline int find_next_best_node(int node, nodemask_t *used_node_mask) } #endif +static inline bool node_reclaim_enabled(void) +{ + /* Is any node_reclaim_mode bit set? */ + return node_reclaim_mode & (RECLAIM_ZONE|RECLAIM_WRITE|RECLAIM_UNMAP); +} + /* * mm/memory-failure.c */ -extern int hwpoison_filter(struct page *p); +#ifdef CONFIG_MEMORY_FAILURE +int unmap_poisoned_folio(struct folio *folio, unsigned long pfn, bool must_kill); +void shake_folio(struct folio *folio); +typedef int hwpoison_filter_func_t(struct page *p); +void hwpoison_filter_register(hwpoison_filter_func_t *filter); +void hwpoison_filter_unregister(void); + +#define MAGIC_HWPOISON 0x48575053U /* HWPS */ +void SetPageHWPoisonTakenOff(struct page *page); +void ClearPageHWPoisonTakenOff(struct page *page); +bool take_page_off_buddy(struct page *page); +bool put_page_back_buddy(struct page *page); +struct task_struct *task_early_kill(struct task_struct *tsk, int force_early); +void add_to_kill_ksm(struct task_struct *tsk, const struct page *p, + struct vm_area_struct *vma, struct list_head *to_kill, + unsigned long ksm_addr); +unsigned long page_mapped_in_vma(const struct page *page, + struct vm_area_struct *vma); -extern u32 hwpoison_filter_dev_major; -extern u32 hwpoison_filter_dev_minor; -extern u64 hwpoison_filter_flags_mask; -extern u64 hwpoison_filter_flags_value; -extern u64 hwpoison_filter_memcg; -extern u32 hwpoison_filter_enable; +#else +static inline int unmap_poisoned_folio(struct folio *folio, unsigned long pfn, bool must_kill) +{ + return -EBUSY; +} +#endif extern unsigned long __must_check vm_mmap_pgoff(struct file *, unsigned long, unsigned long, unsigned long, @@ -842,6 +1298,7 @@ unsigned int reclaim_clean_pages_from_list(struct zone *zone, #define ALLOC_NOFRAGMENT 0x0 #endif #define ALLOC_HIGHATOMIC 0x200 /* Allows access to MIGRATE_HIGHATOMIC */ +#define ALLOC_TRYLOCK 0x400 /* Only use spin_trylock in allocation path */ #define ALLOC_KSWAPD 0x800 /* allow waking of kswapd, __GFP_KSWAPD_RECLAIM set */ /* Flags that allow allocations below the min watermark. */ @@ -874,26 +1331,16 @@ static inline void flush_tlb_batched_pending(struct mm_struct *mm) #endif /* CONFIG_ARCH_WANT_BATCHED_UNMAP_TLB_FLUSH */ extern const struct trace_print_flags pageflag_names[]; -extern const struct trace_print_flags pagetype_names[]; extern const struct trace_print_flags vmaflag_names[]; extern const struct trace_print_flags gfpflag_names[]; -static inline bool is_migrate_highatomic(enum migratetype migratetype) -{ - return migratetype == MIGRATE_HIGHATOMIC; -} - -static inline bool is_migrate_highatomic_page(struct page *page) -{ - return get_pageblock_migratetype(page) == MIGRATE_HIGHATOMIC; -} - void setup_zone_pageset(struct zone *zone); struct migration_target_control { int nid; /* preferred node id */ nodemask_t *nmask; gfp_t gfp_mask; + enum migrate_reason reason; }; /* @@ -908,7 +1355,8 @@ size_t splice_folio_into_pipe(struct pipe_inode_info *pipe, #ifdef CONFIG_MMU void __init vmalloc_init(void); int __must_check vmap_pages_range_noflush(unsigned long addr, unsigned long end, - pgprot_t prot, struct page **pages, unsigned int page_shift); + pgprot_t prot, struct page **pages, unsigned int page_shift, gfp_t gfp_mask); +unsigned int get_vm_area_page_order(struct vm_struct *vm); #else static inline void vmalloc_init(void) { @@ -916,7 +1364,7 @@ static inline void vmalloc_init(void) static inline int __must_check vmap_pages_range_noflush(unsigned long addr, unsigned long end, - pgprot_t prot, struct page **pages, unsigned int page_shift) + pgprot_t prot, struct page **pages, unsigned int page_shift, gfp_t gfp_mask) { return -EINVAL; } @@ -930,24 +1378,74 @@ void vunmap_range_noflush(unsigned long start, unsigned long end); void __vunmap_range_noflush(unsigned long start, unsigned long end); -int numa_migrate_prep(struct page *page, struct vm_area_struct *vma, - unsigned long addr, int page_nid, int *flags); +static inline bool vma_is_single_threaded_private(struct vm_area_struct *vma) +{ + if (vma->vm_flags & VM_SHARED) + return false; + + return atomic_read(&vma->vm_mm->mm_users) == 1; +} + +#ifdef CONFIG_NUMA_BALANCING +bool folio_can_map_prot_numa(struct folio *folio, struct vm_area_struct *vma, + bool is_private_single_threaded); + +#else +static inline bool folio_can_map_prot_numa(struct folio *folio, + struct vm_area_struct *vma, bool is_private_single_threaded) +{ + return false; +} +#endif + +int numa_migrate_check(struct folio *folio, struct vm_fault *vmf, + unsigned long addr, int *flags, bool writable, + int *last_cpupid); -void free_zone_device_page(struct page *page); -int migrate_device_coherent_page(struct page *page); +void free_zone_device_folio(struct folio *folio); +int migrate_device_coherent_folio(struct folio *folio); + +struct vm_struct *__get_vm_area_node(unsigned long size, + unsigned long align, unsigned long shift, + unsigned long vm_flags, unsigned long start, + unsigned long end, int node, gfp_t gfp_mask, + const void *caller); /* * mm/gup.c */ -struct folio *try_grab_folio(struct page *page, int refs, unsigned int flags); -int __must_check try_grab_page(struct page *page, unsigned int flags); +int __must_check try_grab_folio(struct folio *folio, int refs, + unsigned int flags); /* * mm/huge_memory.c */ -struct page *follow_trans_huge_pmd(struct vm_area_struct *vma, - unsigned long addr, pmd_t *pmd, - unsigned int flags); +void touch_pud(struct vm_area_struct *vma, unsigned long addr, + pud_t *pud, bool write); +bool touch_pmd(struct vm_area_struct *vma, unsigned long addr, + pmd_t *pmd, bool write); + +/* + * Parses a string with mem suffixes into its order. Useful to parse kernel + * parameters. + */ +static inline int get_order_from_str(const char *size_str, + unsigned long valid_orders) +{ + unsigned long size; + char *endptr; + int order; + + size = memparse(size_str, &endptr); + + if (!is_power_of_2(size)) + return -EINVAL; + order = get_order(size); + if (BIT(order) & ~valid_orders) + return -EINVAL; + + return order; +} enum { /* mark page accessed */ @@ -962,8 +1460,14 @@ enum { FOLL_FAST_ONLY = 1 << 20, /* allow unlocking the mmap lock */ FOLL_UNLOCKABLE = 1 << 21, + /* VMA lookup+checks compatible with MADV_POPULATE_(READ|WRITE) */ + FOLL_MADV_POPULATE = 1 << 22, }; +#define INTERNAL_GUP_FLAGS (FOLL_TOUCH | FOLL_TRIED | FOLL_REMOTE | FOLL_PIN | \ + FOLL_FAST_ONLY | FOLL_UNLOCKABLE | \ + FOLL_MADV_POPULATE) + /* * Indicates for which pages that are write-protected in the page table, * whether GUP has to trigger unsharing via FAULT_FLAG_UNSHARE such that the @@ -975,7 +1479,7 @@ enum { * * Ordinary GUP: Using the PT lock * * GUP-fast and fork(): mm->write_protect_seq * * GUP-fast and KSM or temporary unmapping (swap, migration): see - * page_try_share_anon_rmap() + * folio_try_share_anon_rmap_*() * * Must be called with the (sub)page that's actually referenced via the * page table entry, which might not necessarily be the head page for a @@ -1018,29 +1522,29 @@ static inline bool gup_must_unshare(struct vm_area_struct *vma, return is_cow_mapping(vma->vm_flags); } - /* Paired with a memory barrier in page_try_share_anon_rmap(). */ - if (IS_ENABLED(CONFIG_HAVE_FAST_GUP)) + /* Paired with a memory barrier in folio_try_share_anon_rmap_*(). */ + if (IS_ENABLED(CONFIG_HAVE_GUP_FAST)) smp_rmb(); /* - * During GUP-fast we might not get called on the head page for a - * hugetlb page that is mapped using cont-PTE, because GUP-fast does - * not work with the abstracted hugetlb PTEs that always point at the - * head page. For hugetlb, PageAnonExclusive only applies on the head - * page (as it cannot be partially COW-shared), so lookup the head page. - */ - if (unlikely(!PageHead(page) && PageHuge(page))) - page = compound_head(page); - - /* - * Note that PageKsm() pages cannot be exclusive, and consequently, + * Note that KSM pages cannot be exclusive, and consequently, * cannot get pinned. */ return !PageAnonExclusive(page); } extern bool mirrored_kernelcore; -extern bool memblock_has_mirror(void); +bool memblock_has_mirror(void); +void memblock_free_all(void); + +static __always_inline void vma_set_range(struct vm_area_struct *vma, + unsigned long start, unsigned long end, + pgoff_t pgoff) +{ + vma->vm_start = start; + vma->vm_end = end; + vma->vm_pgoff = pgoff; +} static inline bool vma_soft_dirty_enabled(struct vm_area_struct *vma) { @@ -1050,7 +1554,7 @@ static inline bool vma_soft_dirty_enabled(struct vm_area_struct *vma) * VM_SOFTDIRTY is defined as 0x0, then !(vm_flags & VM_SOFTDIRTY) * will be constantly true. */ - if (!IS_ENABLED(CONFIG_MEM_SOFT_DIRTY)) + if (!pgtable_supports_soft_dirty()) return false; /* @@ -1060,98 +1564,148 @@ static inline bool vma_soft_dirty_enabled(struct vm_area_struct *vma) return !(vma->vm_flags & VM_SOFTDIRTY); } -static inline void vma_iter_config(struct vma_iterator *vmi, - unsigned long index, unsigned long last) +static inline bool pmd_needs_soft_dirty_wp(struct vm_area_struct *vma, pmd_t pmd) { - MAS_BUG_ON(&vmi->mas, vmi->mas.node != MAS_START && - (vmi->mas.index > index || vmi->mas.last < index)); - __mas_set_range(&vmi->mas, index, last - 1); + return vma_soft_dirty_enabled(vma) && !pmd_soft_dirty(pmd); } -/* - * VMA Iterator functions shared between nommu and mmap - */ -static inline int vma_iter_prealloc(struct vma_iterator *vmi, - struct vm_area_struct *vma) +static inline bool pte_needs_soft_dirty_wp(struct vm_area_struct *vma, pte_t pte) { - return mas_preallocate(&vmi->mas, vma, GFP_KERNEL); + return vma_soft_dirty_enabled(vma) && !pte_soft_dirty(pte); } -static inline void vma_iter_clear(struct vma_iterator *vmi) +void __meminit __init_single_page(struct page *page, unsigned long pfn, + unsigned long zone, int nid); +void __meminit __init_page_from_nid(unsigned long pfn, int nid); + +/* shrinker related functions */ +unsigned long shrink_slab(gfp_t gfp_mask, int nid, struct mem_cgroup *memcg, + int priority); + +int shmem_add_to_page_cache(struct folio *folio, + struct address_space *mapping, + pgoff_t index, void *expected, gfp_t gfp); +int shmem_inode_acct_blocks(struct inode *inode, long pages); +bool shmem_recalc_inode(struct inode *inode, long alloced, long swapped); + +#ifdef CONFIG_SHRINKER_DEBUG +static inline __printf(2, 0) int shrinker_debugfs_name_alloc( + struct shrinker *shrinker, const char *fmt, va_list ap) { - mas_store_prealloc(&vmi->mas, NULL); + shrinker->name = kvasprintf_const(GFP_KERNEL, fmt, ap); + + return shrinker->name ? 0 : -ENOMEM; } -static inline int vma_iter_clear_gfp(struct vma_iterator *vmi, - unsigned long start, unsigned long end, gfp_t gfp) +static inline void shrinker_debugfs_name_free(struct shrinker *shrinker) { - __mas_set_range(&vmi->mas, start, end - 1); - mas_store_gfp(&vmi->mas, NULL, gfp); - if (unlikely(mas_is_err(&vmi->mas))) - return -ENOMEM; + kfree_const(shrinker->name); + shrinker->name = NULL; +} +extern int shrinker_debugfs_add(struct shrinker *shrinker); +extern struct dentry *shrinker_debugfs_detach(struct shrinker *shrinker, + int *debugfs_id); +extern void shrinker_debugfs_remove(struct dentry *debugfs_entry, + int debugfs_id); +#else /* CONFIG_SHRINKER_DEBUG */ +static inline int shrinker_debugfs_add(struct shrinker *shrinker) +{ return 0; } - -static inline struct vm_area_struct *vma_iter_load(struct vma_iterator *vmi) +static inline int shrinker_debugfs_name_alloc(struct shrinker *shrinker, + const char *fmt, va_list ap) +{ + return 0; +} +static inline void shrinker_debugfs_name_free(struct shrinker *shrinker) +{ +} +static inline struct dentry *shrinker_debugfs_detach(struct shrinker *shrinker, + int *debugfs_id) +{ + *debugfs_id = -1; + return NULL; +} +static inline void shrinker_debugfs_remove(struct dentry *debugfs_entry, + int debugfs_id) { - return mas_walk(&vmi->mas); } +#endif /* CONFIG_SHRINKER_DEBUG */ + +/* Only track the nodes of mappings with shadow entries */ +void workingset_update_node(struct xa_node *node); +extern struct list_lru shadow_nodes; +#define mapping_set_update(xas, mapping) do { \ + if (!dax_mapping(mapping) && !shmem_mapping(mapping)) { \ + xas_set_update(xas, workingset_update_node); \ + xas_set_lru(xas, &shadow_nodes); \ + } \ +} while (0) + +/* mremap.c */ +unsigned long move_page_tables(struct pagetable_move_control *pmc); -/* Store a VMA with preallocated memory */ -static inline void vma_iter_store(struct vma_iterator *vmi, - struct vm_area_struct *vma) +#ifdef CONFIG_UNACCEPTED_MEMORY +void accept_page(struct page *page); +#else /* CONFIG_UNACCEPTED_MEMORY */ +static inline void accept_page(struct page *page) +{ +} +#endif /* CONFIG_UNACCEPTED_MEMORY */ + +/* pagewalk.c */ +int walk_page_range_mm_unsafe(struct mm_struct *mm, unsigned long start, + unsigned long end, const struct mm_walk_ops *ops, + void *private); +int walk_page_range_vma_unsafe(struct vm_area_struct *vma, unsigned long start, + unsigned long end, const struct mm_walk_ops *ops, + void *private); +int walk_page_range_debug(struct mm_struct *mm, unsigned long start, + unsigned long end, const struct mm_walk_ops *ops, + pgd_t *pgd, void *private); + +/* pt_reclaim.c */ +bool try_get_and_clear_pmd(struct mm_struct *mm, pmd_t *pmd, pmd_t *pmdval); +void free_pte(struct mm_struct *mm, unsigned long addr, struct mmu_gather *tlb, + pmd_t pmdval); +void try_to_free_pte(struct mm_struct *mm, pmd_t *pmd, unsigned long addr, + struct mmu_gather *tlb); + +#ifdef CONFIG_PT_RECLAIM +bool reclaim_pt_is_enabled(unsigned long start, unsigned long end, + struct zap_details *details); +#else +static inline bool reclaim_pt_is_enabled(unsigned long start, unsigned long end, + struct zap_details *details) { + return false; +} +#endif /* CONFIG_PT_RECLAIM */ -#if defined(CONFIG_DEBUG_VM_MAPLE_TREE) - if (MAS_WARN_ON(&vmi->mas, vmi->mas.node != MAS_START && - vmi->mas.index > vma->vm_start)) { - pr_warn("%lx > %lx\n store vma %lx-%lx\n into slot %lx-%lx\n", - vmi->mas.index, vma->vm_start, vma->vm_start, - vma->vm_end, vmi->mas.index, vmi->mas.last); - } - if (MAS_WARN_ON(&vmi->mas, vmi->mas.node != MAS_START && - vmi->mas.last < vma->vm_start)) { - pr_warn("%lx < %lx\nstore vma %lx-%lx\ninto slot %lx-%lx\n", - vmi->mas.last, vma->vm_start, vma->vm_start, vma->vm_end, - vmi->mas.index, vmi->mas.last); - } -#endif +void dup_mm_exe_file(struct mm_struct *mm, struct mm_struct *oldmm); +int dup_mmap(struct mm_struct *mm, struct mm_struct *oldmm); + +void remap_pfn_range_prepare(struct vm_area_desc *desc, unsigned long pfn); +int remap_pfn_range_complete(struct vm_area_struct *vma, unsigned long addr, + unsigned long pfn, unsigned long size, pgprot_t pgprot); - if (vmi->mas.node != MAS_START && - ((vmi->mas.index > vma->vm_start) || (vmi->mas.last < vma->vm_start))) - vma_iter_invalidate(vmi); +static inline void io_remap_pfn_range_prepare(struct vm_area_desc *desc, + unsigned long orig_pfn, unsigned long size) +{ + const unsigned long pfn = io_remap_pfn_range_pfn(orig_pfn, size); - __mas_set_range(&vmi->mas, vma->vm_start, vma->vm_end - 1); - mas_store_prealloc(&vmi->mas, vma); + return remap_pfn_range_prepare(desc, pfn); } -static inline int vma_iter_store_gfp(struct vma_iterator *vmi, - struct vm_area_struct *vma, gfp_t gfp) +static inline int io_remap_pfn_range_complete(struct vm_area_struct *vma, + unsigned long addr, unsigned long orig_pfn, unsigned long size, + pgprot_t orig_prot) { - if (vmi->mas.node != MAS_START && - ((vmi->mas.index > vma->vm_start) || (vmi->mas.last < vma->vm_start))) - vma_iter_invalidate(vmi); - - __mas_set_range(&vmi->mas, vma->vm_start, vma->vm_end - 1); - mas_store_gfp(&vmi->mas, vma, gfp); - if (unlikely(mas_is_err(&vmi->mas))) - return -ENOMEM; + const unsigned long pfn = io_remap_pfn_range_pfn(orig_pfn, size); + const pgprot_t prot = pgprot_decrypted(orig_prot); - return 0; + return remap_pfn_range_complete(vma, addr, pfn, size, prot); } -/* - * VMA lock generalization - */ -struct vma_prepare { - struct vm_area_struct *vma; - struct vm_area_struct *adj_next; - struct file *file; - struct address_space *mapping; - struct anon_vma *anon_vma; - struct vm_area_struct *insert; - struct vm_area_struct *remove; - struct vm_area_struct *remove2; -}; #endif /* __MM_INTERNAL_H */ |