#define GFP_RECLAIM_MASK (__GFP_RECLAIM|__GFP_HIGH|__GFP_IO|__GFP_FS|\
__GFP_NOWARN|__GFP_RETRY_MAYFAIL|__GFP_NOFAIL|\
__GFP_NORETRY|__GFP_MEMALLOC|__GFP_NOMEMALLOC|\
- __GFP_ATOMIC|__GFP_NOLOCKDEP)
+ __GFP_NOLOCKDEP)
/* The GFP flags allowed during early boot */
#define GFP_BOOT_MASK (__GFP_BITS_MASK & ~(__GFP_RECLAIM|__GFP_IO|__GFP_FS))
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 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 ENTIRELY_MAPPED 0x800000
+#define FOLIO_PAGES_MAPPED (ENTIRELY_MAPPED - 1)
+
+/*
+ * Flags passed to __show_mem() and show_free_areas() to suppress output in
+ * various contexts.
+ */
+#define SHOW_MEM_FILTER_NODES (0x0001u) /* disallowed nodes */
+
+/*
+ * How many individual pages have an elevated _mapcount. Excludes
+ * the folio's entire_mapcount.
+ */
+static inline int folio_nr_pages_mapped(struct folio *folio)
+{
+ return atomic_read(&folio->_nr_pages_mapped) & FOLIO_PAGES_MAPPED;
+}
+
static inline void *folio_raw_mapping(struct folio *folio)
{
unsigned long mapping = (unsigned long)folio->mapping;
return (void *)(mapping & ~PAGE_MAPPING_FLAGS);
}
+#ifdef CONFIG_MMU
+
+/* Flags for folio_pte_batch(). */
+typedef int __bitwise fpb_t;
+
+/* Compare PTEs after pte_mkclean(), ignoring the dirty bit. */
+#define FPB_IGNORE_DIRTY ((__force fpb_t)BIT(0))
+
+/* Compare PTEs after pte_clear_soft_dirty(), ignoring the soft-dirty bit. */
+#define FPB_IGNORE_SOFT_DIRTY ((__force fpb_t)BIT(1))
+
+static inline pte_t __pte_batch_clear_ignored(pte_t pte, fpb_t flags)
+{
+ if (flags & FPB_IGNORE_DIRTY)
+ pte = pte_mkclean(pte);
+ if (likely(flags & FPB_IGNORE_SOFT_DIRTY))
+ pte = pte_clear_soft_dirty(pte);
+ return pte_wrprotect(pte_mkold(pte));
+}
+
+/**
+ * folio_pte_batch - detect a PTE batch for a large folio
+ * @folio: The large folio to detect a PTE batch for.
+ * @addr: The user virtual address the first page is mapped at.
+ * @start_ptep: Page table pointer for the first entry.
+ * @pte: Page table entry for the first page.
+ * @max_nr: The maximum number of table entries to consider.
+ * @flags: Flags to modify the PTE batch semantics.
+ * @any_writable: Optional pointer to indicate whether any entry except the
+ * first one is writable.
+ *
+ * Detect a PTE batch: consecutive (present) PTEs that map consecutive
+ * pages of the same large folio.
+ *
+ * All PTEs inside a PTE batch have the same PTE bits set, excluding the PFN,
+ * the accessed bit, writable bit, dirty bit (with FPB_IGNORE_DIRTY) and
+ * soft-dirty bit (with FPB_IGNORE_SOFT_DIRTY).
+ *
+ * start_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 page table.
+ *
+ * Return: the number of table entries in the batch.
+ */
+static inline int folio_pte_batch(struct folio *folio, unsigned long addr,
+ pte_t *start_ptep, pte_t pte, int max_nr, fpb_t flags,
+ bool *any_writable)
+{
+ unsigned long folio_end_pfn = folio_pfn(folio) + folio_nr_pages(folio);
+ const pte_t *end_ptep = start_ptep + max_nr;
+ pte_t expected_pte, *ptep;
+ bool writable;
+ int nr;
+
+ if (any_writable)
+ *any_writable = false;
+
+ 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);
+
+ nr = pte_batch_hint(start_ptep, pte);
+ expected_pte = __pte_batch_clear_ignored(pte_advance_pfn(pte, nr), flags);
+ ptep = start_ptep + nr;
+
+ while (ptep < end_ptep) {
+ pte = ptep_get(ptep);
+ if (any_writable)
+ writable = !!pte_write(pte);
+ pte = __pte_batch_clear_ignored(pte, flags);
+
+ if (!pte_same(pte, expected_pte))
+ break;
+
+ /*
+ * Stop immediately once we reached the end of the folio. In
+ * corner cases the next PFN might fall into a different
+ * folio.
+ */
+ if (pte_pfn(pte) >= folio_end_pfn)
+ break;
+
+ if (any_writable)
+ *any_writable |= writable;
+
+ nr = pte_batch_hint(ptep, pte);
+ expected_pte = pte_advance_pfn(expected_pte, nr);
+ ptep += nr;
+ }
+
+ return min(ptep - start_ptep, max_nr);
+}
+#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)
wake_up(wqh);
}
+vm_fault_t vmf_anon_prepare(struct vm_fault *vmf);
vm_fault_t do_swap_page(struct vm_fault *vmf);
void folio_rotate_reclaimable(struct folio *folio);
bool __folio_end_writeback(struct folio *folio);
void deactivate_file_folio(struct folio *folio);
+void folio_activate(struct folio *folio);
-void free_pgtables(struct mmu_gather *tlb, struct vm_area_struct *start_vma,
- unsigned long floor, unsigned long ceiling);
+void free_pgtables(struct mmu_gather *tlb, struct ma_state *mas,
+ struct vm_area_struct *start_vma, unsigned long floor,
+ unsigned long ceiling, bool mm_wr_locked);
void pmd_install(struct mm_struct *mm, pmd_t *pmd, pgtable_t *pte);
struct zap_details;
force_page_cache_ra(&ractl, nr_to_read);
}
-unsigned find_lock_entries(struct address_space *mapping, pgoff_t start,
+unsigned find_lock_entries(struct address_space *mapping, pgoff_t *start,
pgoff_t end, struct folio_batch *fbatch, pgoff_t *indices);
-unsigned find_get_entries(struct address_space *mapping, pgoff_t start,
+unsigned find_get_entries(struct address_space *mapping, pgoff_t *start,
pgoff_t end, struct folio_batch *fbatch, pgoff_t *indices);
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);
-unsigned long invalidate_mapping_pagevec(struct address_space *mapping,
- pgoff_t start, pgoff_t end, unsigned long *nr_pagevec);
+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);
/**
* folio_evictable - Test whether a folio is evictable.
return ret;
}
-static inline bool page_evictable(struct page *page)
-{
- bool ret;
-
- /* Prevent address_space of inode and swap cache from being freed */
- rcu_read_lock();
- ret = !mapping_unevictable(page_mapping(page)) && !PageMlocked(page);
- rcu_read_unlock();
- return ret;
-}
-
/*
* Turn a non-refcounted page (->_refcount == 0) into refcounted with
* a count of one.
set_page_count(page, 1);
}
+/*
+ * Return true if a folio needs ->release_folio() calling upon it.
+ */
+static inline bool folio_needs_release(struct folio *folio)
+{
+ struct address_space *mapping = folio_mapping(folio);
+
+ return folio_has_private(folio) ||
+ (mapping && mapping_release_always(mapping));
+}
+
extern unsigned long highest_memmap_pfn;
/*
*/
#define MAX_RECLAIM_RETRIES 16
-/*
- * in mm/early_ioremap.c
- */
-pgprot_t __init early_memremap_pgprot_adjust(resource_size_t phys_addr,
- unsigned long size, pgprot_t prot);
-
/*
* in mm/vmscan.c:
*/
-int isolate_lru_page(struct page *page);
-int folio_isolate_lru(struct folio *folio);
+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);
/*
* in mm/rmap.c:
*/
-extern pmd_t *mm_find_pmd(struct mm_struct *mm, unsigned long address);
+pmd_t *mm_find_pmd(struct mm_struct *mm, unsigned long address);
/*
* in mm/page_alloc.c
*/
+#define K(x) ((x) << (PAGE_SHIFT-10))
+
+extern char * const zone_names[MAX_NR_ZONES];
+
+/* perform sanity checks on struct pages being allocated or freed */
+DECLARE_STATIC_KEY_MAYBE(CONFIG_DEBUG_VM, check_pages_enabled);
+
+extern int min_free_kbytes;
+
+void setup_per_zone_wmarks(void);
+void calculate_min_free_kbytes(void);
+int __meminit init_per_zone_wmark_min(void);
+void page_alloc_sysctl_init(void);
/*
* Structure for holding the mostly immutable allocation parameters passed
* 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)
return __pageblock_pfn_to_page(start_pfn, end_pfn, zone);
}
+void set_zone_contiguous(struct zone *zone);
+
+static inline void clear_zone_contiguous(struct zone *zone)
+{
+ zone->contiguous = false;
+}
+
extern int __isolate_free_page(struct page *page, unsigned int order);
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);
+
+/*
+ * This will have no effect, other than possibly generating a warning, if the
+ * caller passes in a non-large folio.
+ */
+static inline void folio_set_order(struct folio *folio, unsigned int order)
+{
+ if (WARN_ON_ONCE(!order || !folio_test_large(folio)))
+ return;
+
+ folio->_flags_1 = (folio->_flags_1 & ~0xffUL) | order;
+#ifdef CONFIG_64BIT
+ folio->_folio_nr_pages = 1U << order;
+#endif
+}
+
+void folio_undo_large_rmappable(struct folio *folio);
+
+static inline struct folio *page_rmappable_folio(struct page *page)
+{
+ struct folio *folio = (struct folio *)page;
+
+ folio_prep_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);
+}
+
+static inline void prep_compound_tail(struct page *head, int tail_idx)
+{
+ struct page *p = head + tail_idx;
+
+ p->mapping = TAIL_MAPPING;
+ set_compound_head(p, head);
+ set_page_private(p, 0);
+}
+
extern void prep_compound_page(struct page *page, unsigned int order);
+
extern 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 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);
+void free_unref_page(struct page *page, unsigned int order);
+void free_unref_folios(struct folio_batch *fbatch);
-extern void zone_pcp_update(struct zone *zone, int cpu_online);
extern void zone_pcp_reset(struct zone *zone);
extern void zone_pcp_disable(struct zone *zone);
extern void zone_pcp_enable(struct zone *zone);
+extern void zone_pcp_init(struct zone *zone);
extern void *memmap_alloc(phys_addr_t size, phys_addr_t align,
phys_addr_t min_addr,
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);
* 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 */
bool proactive_compaction; /* kcompactd proactive compaction */
bool whole_zone; /* Whole zone should/has been scanned */
bool contended; /* Signal lock contention */
- bool rescan; /* Rescanning the same pageblock */
+ bool finish_pageblock; /* Scan the remainder of a pageblock. Used
+ * when there are potentially transient
+ * isolation or migration failures to
+ * ensure forward progress.
+ */
bool alloc_contig; /* alloc_contig_range allocation */
};
unsigned long low_pfn, unsigned long end_pfn);
int __alloc_contig_migrate_range(struct compact_control *cc,
- unsigned long start, unsigned long end);
-#endif
+ unsigned long start, unsigned long end,
+ int migratetype);
+
+/* Free whole pageblock and set its migration type to MIGRATE_CMA. */
+void init_cma_reserved_pageblock(struct page *page);
+
+#endif /* CONFIG_COMPACTION || CONFIG_CMA */
+
int find_suitable_fallback(struct free_area *area, unsigned int order,
int migratetype, bool only_stealable, bool *can_steal);
+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.
*/
}
/*
- * Stack area - automatically grows in one direction
+ * Stack area (including shadow stacks)
*
* VM_GROWSUP / VM_GROWSDOWN VMAs are always private anonymous:
* do_mmap() forbids all other combinations.
*/
static inline bool is_stack_mapping(vm_flags_t flags)
{
- return (flags & VM_STACK) == VM_STACK;
+ return ((flags & VM_STACK) == VM_STACK) || (flags & VM_SHADOW_STACK);
}
/*
}
/* mm/util.c */
-void __vma_link_list(struct mm_struct *mm, struct vm_area_struct *vma,
- struct vm_area_struct *prev);
-void __vma_unlink_list(struct mm_struct *mm, struct vm_area_struct *vma);
struct anon_vma *folio_anon_vma(struct folio *folio);
#ifdef CONFIG_MMU
extern long faultin_vma_page_range(struct vm_area_struct *vma,
unsigned long start, unsigned long end,
bool write, int *locked);
-extern int mlock_future_check(struct mm_struct *mm, unsigned long flags,
- unsigned long len);
+extern bool mlock_future_ok(struct mm_struct *mm, unsigned long flags,
+ unsigned long bytes);
+
+/*
+ * 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.
+ *
+ * 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
+folio_within_range(struct folio *folio, struct vm_area_struct *vma,
+ unsigned long start, unsigned long end)
+{
+ 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));
+}
+
+static inline bool
+folio_within_vma(struct folio *folio, struct vm_area_struct *vma)
+{
+ return folio_within_range(folio, vma, vma->vm_start, vma->vm_end);
+}
+
/*
- * mlock_vma_page() and munlock_vma_page():
+ * 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
- * pages are managed by lru_cache_add_inactive_or_unevictable()
- * calling mlock_new_page().
- *
- * @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.
+ * 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().
*/
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.
* 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);
}
-static inline void mlock_vma_page(struct page *page,
- struct vm_area_struct *vma, bool compound)
+void munlock_folio(struct folio *folio);
+static inline void munlock_vma_folio(struct folio *folio,
+ struct vm_area_struct *vma)
{
- mlock_vma_folio(page_folio(page), vma, compound);
+ /*
+ * 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);
}
-void munlock_page(struct page *page);
-static inline void munlock_vma_page(struct page *page,
- struct vm_area_struct *vma, bool compound)
-{
- if (unlikely(vma->vm_flags & VM_LOCKED) &&
- (compound || !PageTransCompound(page)))
- munlock_page(page);
-}
-void mlock_new_page(struct page *page);
-bool need_mlock_page_drain(int cpu);
-void mlock_page_drain_local(void);
-void mlock_page_drain_remote(int cpu);
+void mlock_new_folio(struct folio *folio);
+bool need_mlock_drain(int cpu);
+void mlock_drain_local(void);
+void mlock_drain_remote(int cpu);
extern pmd_t maybe_pmd_mkwrite(pmd_t pmd, struct vm_area_struct *vma);
if (fault_flag_allow_retry_first(flags) &&
!(flags & FAULT_FLAG_RETRY_NOWAIT)) {
fpin = get_file(vmf->vma->vm_file);
- mmap_read_unlock(vmf->vma->vm_mm);
+ release_fault_lock(vmf);
}
return fpin;
}
#else /* !CONFIG_MMU */
static inline void unmap_mapping_folio(struct folio *folio) { }
-static inline void mlock_vma_page(struct page *page,
- struct vm_area_struct *vma, bool compound) { }
-static inline void munlock_vma_page(struct page *page,
- struct vm_area_struct *vma, bool compound) { }
-static inline void mlock_new_page(struct page *page) { }
-static inline bool need_mlock_page_drain(int cpu) { return false; }
-static inline void mlock_page_drain_local(void) { }
-static inline void mlock_page_drain_remote(int cpu) { }
+static inline void mlock_new_folio(struct folio *folio) { }
+static inline bool need_mlock_drain(int cpu) { return false; }
+static inline void mlock_drain_local(void) { }
+static inline void mlock_drain_remote(int cpu) { }
static inline void vunmap_range_noflush(unsigned long start, unsigned long end)
{
}
#endif /* !CONFIG_MMU */
-/*
- * Return the mem_map entry representing the 'offset' subpage within
- * the maximally aligned gigantic page 'base'. Handle any discontiguity
- * in the mem_map at MAX_ORDER_NR_PAGES boundaries.
- */
-static inline struct page *mem_map_offset(struct page *base, int offset)
-{
- if (unlikely(offset >= MAX_ORDER_NR_PAGES))
- return nth_page(base, offset);
- return base + offset;
-}
+/* Memory initialisation debug and verification */
+#ifdef CONFIG_DEFERRED_STRUCT_PAGE_INIT
+DECLARE_STATIC_KEY_TRUE(deferred_pages);
-/*
- * Iterator over all subpages within the maximally aligned gigantic
- * page 'base'. Handle any discontiguity in the mem_map.
- */
-static inline struct page *mem_map_next(struct page *iter,
- struct page *base, int offset)
-{
- if (unlikely((offset & (MAX_ORDER_NR_PAGES - 1)) == 0)) {
- unsigned long pfn = page_to_pfn(base) + offset;
- if (!pfn_valid(pfn))
- return NULL;
- return pfn_to_page(pfn);
- }
- return iter + 1;
-}
+bool __init deferred_grow_zone(struct zone *zone, unsigned int order);
+#endif /* CONFIG_DEFERRED_STRUCT_PAGE_INIT */
-/* Memory initialisation debug and verification */
enum mminit_level {
MMINIT_WARNING,
MMINIT_VERIFY,
extern u64 hwpoison_filter_memcg;
extern u32 hwpoison_filter_enable;
-#ifdef CONFIG_MEMORY_FAILURE
-void clear_hwpoisoned_pages(struct page *memmap, int nr_pages);
-#else
-static inline void clear_hwpoisoned_pages(struct page *memmap, int nr_pages)
-{
-}
-#endif
-
extern unsigned long __must_check vm_mmap_pgoff(struct file *, unsigned long,
unsigned long, unsigned long,
unsigned long, unsigned long);
extern void set_pageblock_order(void);
+unsigned long reclaim_pages(struct list_head *folio_list, bool ignore_references);
unsigned int reclaim_clean_pages_from_list(struct zone *zone,
- struct list_head *page_list);
+ struct list_head *folio_list);
/* The ALLOC_WMARK bits are used as an index to zone->watermark */
#define ALLOC_WMARK_MIN WMARK_MIN
#define ALLOC_WMARK_LOW WMARK_LOW
#define ALLOC_OOM ALLOC_NO_WATERMARKS
#endif
-#define ALLOC_HARDER 0x10 /* try to alloc harder */
-#define ALLOC_HIGH 0x20 /* __GFP_HIGH set */
+#define ALLOC_NON_BLOCK 0x10 /* Caller cannot block. Allow access
+ * to 25% of the min watermark or
+ * 62.5% if __GFP_HIGH is set.
+ */
+#define ALLOC_MIN_RESERVE 0x20 /* __GFP_HIGH set. Allow access to 50%
+ * of the min watermark.
+ */
#define ALLOC_CPUSET 0x40 /* check for correct cpuset */
#define ALLOC_CMA 0x80 /* allow allocations from CMA areas */
#ifdef CONFIG_ZONE_DMA32
#else
#define ALLOC_NOFRAGMENT 0x0
#endif
+#define ALLOC_HIGHATOMIC 0x200 /* Allows access to MIGRATE_HIGHATOMIC */
#define ALLOC_KSWAPD 0x800 /* allow waking of kswapd, __GFP_KSWAPD_RECLAIM set */
+/* Flags that allow allocations below the min watermark. */
+#define ALLOC_RESERVES (ALLOC_NON_BLOCK|ALLOC_MIN_RESERVE|ALLOC_HIGHATOMIC|ALLOC_OOM)
+
enum ttu_flags;
struct tlbflush_unmap_batch;
#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[];
gfp_t gfp_mask;
};
+/*
+ * mm/filemap.c
+ */
+size_t splice_folio_into_pipe(struct pipe_inode_info *pipe,
+ struct folio *folio, loff_t fpos, size_t size);
+
/*
* mm/vmalloc.c
*/
#ifdef CONFIG_MMU
-int vmap_pages_range_noflush(unsigned long addr, unsigned long end,
+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);
#else
+static inline void vmalloc_init(void)
+{
+}
+
static inline
-int vmap_pages_range_noflush(unsigned long addr, unsigned long end,
+int __must_check vmap_pages_range_noflush(unsigned long addr, unsigned long end,
pgprot_t prot, struct page **pages, unsigned int page_shift)
{
return -EINVAL;
}
#endif
+int __must_check __vmap_pages_range_noflush(unsigned long addr,
+ unsigned long end, pgprot_t prot,
+ struct page **pages, unsigned int page_shift);
+
void vunmap_range_noflush(unsigned long start, unsigned long end);
-int numa_migrate_prep(struct page *page, struct vm_area_struct *vma,
+void __vunmap_range_noflush(unsigned long start, unsigned long end);
+
+int numa_migrate_prep(struct folio *folio, struct vm_area_struct *vma,
unsigned long addr, int page_nid, int *flags);
void free_zone_device_page(struct page *page);
* 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);
+
+/*
+ * mm/huge_memory.c
+ */
+struct page *follow_trans_huge_pmd(struct vm_area_struct *vma,
+ unsigned long addr, pmd_t *pmd,
+ unsigned int flags);
+
+/*
+ * mm/mmap.c
+ */
+struct vm_area_struct *vma_merge_extend(struct vma_iterator *vmi,
+ struct vm_area_struct *vma,
+ unsigned long delta);
+
+enum {
+ /* mark page accessed */
+ FOLL_TOUCH = 1 << 16,
+ /* a retry, previous pass started an IO */
+ FOLL_TRIED = 1 << 17,
+ /* we are working on non-current tsk/mm */
+ FOLL_REMOTE = 1 << 18,
+ /* pages must be released via unpin_user_page */
+ FOLL_PIN = 1 << 19,
+ /* gup_fast: prevent fall-back to slow gup */
+ FOLL_FAST_ONLY = 1 << 20,
+ /* allow unlocking the mmap lock */
+ FOLL_UNLOCKABLE = 1 << 21,
+};
+
+#define INTERNAL_GUP_FLAGS (FOLL_TOUCH | FOLL_TRIED | FOLL_REMOTE | FOLL_PIN | \
+ FOLL_FAST_ONLY | FOLL_UNLOCKABLE)
+
+/*
+ * 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
+ * GUP pin will remain consistent with the pages mapped into the page tables
+ * of the MM.
+ *
+ * Temporary unmapping of PageAnonExclusive() pages or clearing of
+ * PageAnonExclusive() has to protect against concurrent GUP:
+ * * Ordinary GUP: Using the PT lock
+ * * GUP-fast and fork(): mm->write_protect_seq
+ * * GUP-fast and KSM or temporary unmapping (swap, migration): see
+ * 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
+ * PTE-mapped THP.
+ *
+ * If the vma is NULL, we're coming from the GUP-fast path and might have
+ * to fallback to the slow path just to lookup the vma.
+ */
+static inline bool gup_must_unshare(struct vm_area_struct *vma,
+ unsigned int flags, struct page *page)
+{
+ /*
+ * FOLL_WRITE is implicitly handled correctly as the page table entry
+ * has to be writable -- and if it references (part of) an anonymous
+ * folio, that part is required to be marked exclusive.
+ */
+ if ((flags & (FOLL_WRITE | FOLL_PIN)) != FOLL_PIN)
+ return false;
+ /*
+ * Note: PageAnon(page) is stable until the page is actually getting
+ * freed.
+ */
+ if (!PageAnon(page)) {
+ /*
+ * We only care about R/O long-term pining: R/O short-term
+ * pinning does not have the semantics to observe successive
+ * changes through the process page tables.
+ */
+ if (!(flags & FOLL_LONGTERM))
+ return false;
+
+ /* We really need the vma ... */
+ if (!vma)
+ return true;
+
+ /*
+ * ... because we only care about writable private ("COW")
+ * mappings where we have to break COW early.
+ */
+ return is_cow_mapping(vma->vm_flags);
+ }
+
+ /* Paired with a memory barrier in folio_try_share_anon_rmap_*(). */
+ if (IS_ENABLED(CONFIG_HAVE_FAST_GUP))
+ 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);
-DECLARE_PER_CPU(struct per_cpu_nodestat, boot_nodestats);
+ /*
+ * Note that PageKsm() pages cannot be exclusive, and consequently,
+ * cannot get pinned.
+ */
+ return !PageAnonExclusive(page);
+}
extern bool mirrored_kernelcore;
+extern bool memblock_has_mirror(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)
{
return !(vma->vm_flags & VM_SOFTDIRTY);
}
+static inline void vma_iter_config(struct vma_iterator *vmi,
+ unsigned long index, unsigned long last)
+{
+ __mas_set_range(&vmi->mas, index, last - 1);
+}
+
+/*
+ * VMA Iterator functions shared between nommu and mmap
+ */
+static inline int vma_iter_prealloc(struct vma_iterator *vmi,
+ struct vm_area_struct *vma)
+{
+ return mas_preallocate(&vmi->mas, vma, GFP_KERNEL);
+}
+
+static inline void vma_iter_clear(struct vma_iterator *vmi)
+{
+ mas_store_prealloc(&vmi->mas, NULL);
+}
+
+static inline struct vm_area_struct *vma_iter_load(struct vma_iterator *vmi)
+{
+ return mas_walk(&vmi->mas);
+}
+
+/* Store a VMA with preallocated memory */
+static inline void vma_iter_store(struct vma_iterator *vmi,
+ struct vm_area_struct *vma)
+{
+
+#if defined(CONFIG_DEBUG_VM_MAPLE_TREE)
+ if (MAS_WARN_ON(&vmi->mas, vmi->mas.status != ma_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.status != ma_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
+
+ if (vmi->mas.status != ma_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_prealloc(&vmi->mas, vma);
+}
+
+static inline int vma_iter_store_gfp(struct vma_iterator *vmi,
+ struct vm_area_struct *vma, gfp_t gfp)
+{
+ if (vmi->mas.status != ma_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;
+
+ return 0;
+}
+
+/*
+ * 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;
+};
+
+void __meminit __init_single_page(struct page *page, unsigned long pfn,
+ unsigned long zone, int nid);
+
+/* shrinker related functions */
+unsigned long shrink_slab(gfp_t gfp_mask, int nid, struct mem_cgroup *memcg,
+ int priority);
+
+#ifdef CONFIG_SHRINKER_DEBUG
+static inline __printf(2, 0) int shrinker_debugfs_name_alloc(
+ struct shrinker *shrinker, const char *fmt, va_list ap)
+{
+ shrinker->name = kvasprintf_const(GFP_KERNEL, fmt, ap);
+
+ return shrinker->name ? 0 : -ENOMEM;
+}
+
+static inline void shrinker_debugfs_name_free(struct shrinker *shrinker)
+{
+ 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 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)
+{
+}
+#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;
+
#endif /* __MM_INTERNAL_H */