diff options
Diffstat (limited to 'mm/page_alloc.c')
| -rw-r--r-- | mm/page_alloc.c | 2518 |
1 files changed, 1492 insertions, 1026 deletions
diff --git a/mm/page_alloc.c b/mm/page_alloc.c index 14d39f34d336..2ef3c07266b3 100644 --- a/mm/page_alloc.c +++ b/mm/page_alloc.c @@ -54,6 +54,7 @@ #include <linux/khugepaged.h> #include <linux/delayacct.h> #include <linux/cacheinfo.h> +#include <linux/pgalloc_tag.h> #include <asm/div64.h> #include "internal.h" #include "shuffle.h" @@ -87,6 +88,9 @@ typedef int __bitwise fpi_t; */ #define FPI_TO_TAIL ((__force fpi_t)BIT(1)) +/* Free the page without taking locks. Rely on trylock only. */ +#define FPI_TRYLOCK ((__force fpi_t)BIT(2)) + /* prevent >1 _updater_ of zone percpu pageset ->high and ->batch fields */ static DEFINE_MUTEX(pcp_batch_high_lock); #define MIN_PERCPU_PAGELIST_HIGH_FRACTION (8) @@ -206,24 +210,6 @@ EXPORT_SYMBOL(node_states); gfp_t gfp_allowed_mask __read_mostly = GFP_BOOT_MASK; -/* - * A cached value of the page's pageblock's migratetype, used when the page is - * put on a pcplist. Used to avoid the pageblock migratetype lookup when - * freeing from pcplists in most cases, at the cost of possibly becoming stale. - * Also the migratetype set in the page does not necessarily match the pcplist - * index, e.g. page might have MIGRATE_CMA set but be on a pcplist with any - * other index - this ensures that it will be put on the correct CMA freelist. - */ -static inline int get_pcppage_migratetype(struct page *page) -{ - return page->index; -} - -static inline void set_pcppage_migratetype(struct page *page, int migratetype) -{ - page->index = migratetype; -} - #ifdef CONFIG_HUGETLB_PAGE_SIZE_VARIABLE unsigned int pageblock_order __read_mostly; #endif @@ -290,6 +276,7 @@ int min_free_kbytes = 1024; int user_min_free_kbytes = -1; static int watermark_boost_factor __read_mostly = 15000; static int watermark_scale_factor = 10; +int defrag_mode; /* movable_zone is the "real" zone pages in ZONE_MOVABLE are taken from */ int movable_zone; @@ -303,9 +290,8 @@ EXPORT_SYMBOL(nr_online_nodes); #endif static bool page_contains_unaccepted(struct page *page, unsigned int order); -static void accept_page(struct page *page, unsigned int order); -static bool try_to_accept_memory(struct zone *zone, unsigned int order); -static inline bool has_unaccepted_memory(void); +static bool cond_accept_memory(struct zone *zone, unsigned int order, + int alloc_flags); static bool __free_unaccepted(struct page *page); int page_group_by_mobility_disabled __read_mostly; @@ -332,13 +318,18 @@ static inline bool deferred_pages_enabled(void) static bool __ref _deferred_grow_zone(struct zone *zone, unsigned int order) { - return deferred_grow_zone(zone, order); + return deferred_grow_zone(zone, order); } #else static inline bool deferred_pages_enabled(void) { return false; } + +static inline bool _deferred_grow_zone(struct zone *zone, unsigned int order) +{ + return false; +} #endif /* CONFIG_DEFERRED_STRUCT_PAGE_INIT */ /* Return a pointer to the bitmap storing bits affecting a block of pages */ @@ -515,16 +506,22 @@ static void bad_page(struct page *page, const char *reason) dump_stack(); out: /* Leave bad fields for debug, except PageBuddy could make trouble */ - page_mapcount_reset(page); /* remove PageBuddy */ + if (PageBuddy(page)) + __ClearPageBuddy(page); add_taint(TAINT_BAD_PAGE, LOCKDEP_NOW_UNRELIABLE); } static inline unsigned int order_to_pindex(int migratetype, int order) { + #ifdef CONFIG_TRANSPARENT_HUGEPAGE + bool movable; if (order > PAGE_ALLOC_COSTLY_ORDER) { - VM_BUG_ON(order != pageblock_order); - return NR_LOWORDER_PCP_LISTS; + VM_BUG_ON(order != HPAGE_PMD_ORDER); + + movable = migratetype == MIGRATE_MOVABLE; + + return NR_LOWORDER_PCP_LISTS + movable; } #else VM_BUG_ON(order > PAGE_ALLOC_COSTLY_ORDER); @@ -538,8 +535,8 @@ static inline int pindex_to_order(unsigned int pindex) int order = pindex / MIGRATE_PCPTYPES; #ifdef CONFIG_TRANSPARENT_HUGEPAGE - if (pindex == NR_LOWORDER_PCP_LISTS) - order = pageblock_order; + if (pindex >= NR_LOWORDER_PCP_LISTS) + order = HPAGE_PMD_ORDER; #else VM_BUG_ON(order > PAGE_ALLOC_COSTLY_ORDER); #endif @@ -552,20 +549,12 @@ static inline bool pcp_allowed_order(unsigned int order) if (order <= PAGE_ALLOC_COSTLY_ORDER) return true; #ifdef CONFIG_TRANSPARENT_HUGEPAGE - if (order == pageblock_order) + if (order == HPAGE_PMD_ORDER) return true; #endif return false; } -static inline void free_the_page(struct page *page, unsigned int order) -{ - if (pcp_allowed_order(order)) /* Via pcp? */ - free_unref_page(page, order); - else - __free_pages_ok(page, order, FPI_NONE); -} - /* * Higher-order pages are called "compound pages". They are structured thusly: * @@ -590,20 +579,6 @@ void prep_compound_page(struct page *page, unsigned int order) prep_compound_head(page, order); } -void destroy_large_folio(struct folio *folio) -{ - if (folio_test_hugetlb(folio)) { - free_huge_folio(folio); - return; - } - - if (folio_test_large_rmappable(folio)) - folio_undo_large_rmappable(folio); - - mem_cgroup_uncharge(folio); - free_the_page(&folio->page, folio_order(folio)); -} - static inline void set_buddy_order(struct page *page, unsigned int order) { set_page_private(page, order); @@ -634,14 +609,20 @@ compaction_capture(struct capture_control *capc, struct page *page, return false; /* - * Do not let lower order allocations pollute a movable pageblock. + * Do not let lower order allocations pollute a movable pageblock + * unless compaction is also requesting movable pages. * This might let an unmovable request use a reclaimable pageblock * and vice-versa but no more than normal fallback logic which can * have trouble finding a high-order free page. */ - if (order < pageblock_order && migratetype == MIGRATE_MOVABLE) + if (order < pageblock_order && migratetype == MIGRATE_MOVABLE && + capc->cc->migratetype != MIGRATE_MOVABLE) return false; + if (migratetype != capc->cc->migratetype) + trace_mm_page_alloc_extfrag(page, capc->cc->order, order, + capc->cc->migratetype, migratetype); + capc->page = page; return true; } @@ -660,24 +641,43 @@ compaction_capture(struct capture_control *capc, struct page *page, } #endif /* CONFIG_COMPACTION */ -/* Used for pages not on another list */ -static inline void add_to_free_list(struct page *page, struct zone *zone, - unsigned int order, int migratetype) +static inline void account_freepages(struct zone *zone, int nr_pages, + int migratetype) { - struct free_area *area = &zone->free_area[order]; + lockdep_assert_held(&zone->lock); - list_add(&page->buddy_list, &area->free_list[migratetype]); - area->nr_free++; + if (is_migrate_isolate(migratetype)) + return; + + __mod_zone_page_state(zone, NR_FREE_PAGES, nr_pages); + + if (is_migrate_cma(migratetype)) + __mod_zone_page_state(zone, NR_FREE_CMA_PAGES, nr_pages); + else if (is_migrate_highatomic(migratetype)) + WRITE_ONCE(zone->nr_free_highatomic, + zone->nr_free_highatomic + nr_pages); } /* Used for pages not on another list */ -static inline void add_to_free_list_tail(struct page *page, struct zone *zone, - unsigned int order, int migratetype) +static inline void __add_to_free_list(struct page *page, struct zone *zone, + unsigned int order, int migratetype, + bool tail) { struct free_area *area = &zone->free_area[order]; + int nr_pages = 1 << order; + + VM_WARN_ONCE(get_pageblock_migratetype(page) != migratetype, + "page type is %lu, passed migratetype is %d (nr=%d)\n", + get_pageblock_migratetype(page), migratetype, nr_pages); - list_add_tail(&page->buddy_list, &area->free_list[migratetype]); + if (tail) + list_add_tail(&page->buddy_list, &area->free_list[migratetype]); + else + list_add(&page->buddy_list, &area->free_list[migratetype]); area->nr_free++; + + if (order >= pageblock_order && !is_migrate_isolate(migratetype)) + __mod_zone_page_state(zone, NR_FREE_PAGES_BLOCKS, nr_pages); } /* @@ -686,16 +686,38 @@ static inline void add_to_free_list_tail(struct page *page, struct zone *zone, * allocation again (e.g., optimization for memory onlining). */ static inline void move_to_free_list(struct page *page, struct zone *zone, - unsigned int order, int migratetype) + unsigned int order, int old_mt, int new_mt) { struct free_area *area = &zone->free_area[order]; + int nr_pages = 1 << order; + + /* Free page moving can fail, so it happens before the type update */ + VM_WARN_ONCE(get_pageblock_migratetype(page) != old_mt, + "page type is %lu, passed migratetype is %d (nr=%d)\n", + get_pageblock_migratetype(page), old_mt, nr_pages); - list_move_tail(&page->buddy_list, &area->free_list[migratetype]); + list_move_tail(&page->buddy_list, &area->free_list[new_mt]); + + account_freepages(zone, -nr_pages, old_mt); + account_freepages(zone, nr_pages, new_mt); + + if (order >= pageblock_order && + is_migrate_isolate(old_mt) != is_migrate_isolate(new_mt)) { + if (!is_migrate_isolate(old_mt)) + nr_pages = -nr_pages; + __mod_zone_page_state(zone, NR_FREE_PAGES_BLOCKS, nr_pages); + } } -static inline void del_page_from_free_list(struct page *page, struct zone *zone, - unsigned int order) +static inline void __del_page_from_free_list(struct page *page, struct zone *zone, + unsigned int order, int migratetype) { + int nr_pages = 1 << order; + + VM_WARN_ONCE(get_pageblock_migratetype(page) != migratetype, + "page type is %lu, passed migratetype is %d (nr=%d)\n", + get_pageblock_migratetype(page), migratetype, nr_pages); + /* clear reported state and update reported page count */ if (page_reported(page)) __ClearPageReported(page); @@ -704,6 +726,16 @@ static inline void del_page_from_free_list(struct page *page, struct zone *zone, __ClearPageBuddy(page); set_page_private(page, 0); zone->free_area[order].nr_free--; + + if (order >= pageblock_order && !is_migrate_isolate(migratetype)) + __mod_zone_page_state(zone, NR_FREE_PAGES_BLOCKS, -nr_pages); +} + +static inline void del_page_from_free_list(struct page *page, struct zone *zone, + unsigned int order, int migratetype) +{ + __del_page_from_free_list(page, zone, order, migratetype); + account_freepages(zone, -(1 << order), migratetype); } static inline struct page *get_page_from_free_area(struct free_area *area, @@ -714,12 +746,12 @@ static inline struct page *get_page_from_free_area(struct free_area *area, } /* - * If this is not the largest possible page, check if the buddy - * of the next-highest order is free. If it is, it's possible + * If this is less than the 2nd largest possible page, check if the buddy + * of the next-higher order is free. If it is, it's possible * that pages are being freed that will coalesce soon. In case, * that is happening, add the free page to the tail of the list * so it's less likely to be used soon and more likely to be merged - * as a higher order page + * as a 2-level higher order page */ static inline bool buddy_merge_likely(unsigned long pfn, unsigned long buddy_pfn, @@ -777,16 +809,16 @@ static inline void __free_one_page(struct page *page, VM_BUG_ON_PAGE(page->flags & PAGE_FLAGS_CHECK_AT_PREP, page); VM_BUG_ON(migratetype == -1); - if (likely(!is_migrate_isolate(migratetype))) - __mod_zone_freepage_state(zone, 1 << order, migratetype); - VM_BUG_ON_PAGE(pfn & ((1 << order) - 1), page); VM_BUG_ON_PAGE(bad_range(zone, page), page); + account_freepages(zone, 1 << order, migratetype); + while (order < MAX_PAGE_ORDER) { + int buddy_mt = migratetype; + if (compaction_capture(capc, page, order, migratetype)) { - __mod_zone_freepage_state(zone, -(1 << order), - migratetype); + account_freepages(zone, -(1 << order), migratetype); return; } @@ -801,11 +833,11 @@ static inline void __free_one_page(struct page *page, * pageblock isolation could cause incorrect freepage or CMA * accounting or HIGHATOMIC accounting. */ - int buddy_mt = get_pfnblock_migratetype(buddy, buddy_pfn); + buddy_mt = get_pfnblock_migratetype(buddy, buddy_pfn); - if (migratetype != buddy_mt - && (!migratetype_is_mergeable(migratetype) || - !migratetype_is_mergeable(buddy_mt))) + if (migratetype != buddy_mt && + (!migratetype_is_mergeable(migratetype) || + !migratetype_is_mergeable(buddy_mt))) goto done_merging; } @@ -814,9 +846,19 @@ static inline void __free_one_page(struct page *page, * merge with it and move up one order. */ if (page_is_guard(buddy)) - clear_page_guard(zone, buddy, order, migratetype); + clear_page_guard(zone, buddy, order); else - del_page_from_free_list(buddy, zone, order); + __del_page_from_free_list(buddy, zone, order, buddy_mt); + + if (unlikely(buddy_mt != migratetype)) { + /* + * Match buddy type. This ensures that an + * expand() down the line puts the sub-blocks + * on the right freelists. + */ + set_pageblock_migratetype(buddy, migratetype); + } + combined_pfn = buddy_pfn & pfn; page = page + (combined_pfn - pfn); pfn = combined_pfn; @@ -833,74 +875,13 @@ done_merging: else to_tail = buddy_merge_likely(pfn, buddy_pfn, page, order); - if (to_tail) - add_to_free_list_tail(page, zone, order, migratetype); - else - add_to_free_list(page, zone, order, migratetype); + __add_to_free_list(page, zone, order, migratetype, to_tail); /* Notify page reporting subsystem of freed page */ if (!(fpi_flags & FPI_SKIP_REPORT_NOTIFY)) page_reporting_notify_free(order); } -/** - * split_free_page() -- split a free page at split_pfn_offset - * @free_page: the original free page - * @order: the order of the page - * @split_pfn_offset: split offset within the page - * - * Return -ENOENT if the free page is changed, otherwise 0 - * - * It is used when the free page crosses two pageblocks with different migratetypes - * at split_pfn_offset within the page. The split free page will be put into - * separate migratetype lists afterwards. Otherwise, the function achieves - * nothing. - */ -int split_free_page(struct page *free_page, - unsigned int order, unsigned long split_pfn_offset) -{ - struct zone *zone = page_zone(free_page); - unsigned long free_page_pfn = page_to_pfn(free_page); - unsigned long pfn; - unsigned long flags; - int free_page_order; - int mt; - int ret = 0; - - if (split_pfn_offset == 0) - return ret; - - spin_lock_irqsave(&zone->lock, flags); - - if (!PageBuddy(free_page) || buddy_order(free_page) != order) { - ret = -ENOENT; - goto out; - } - - mt = get_pfnblock_migratetype(free_page, free_page_pfn); - if (likely(!is_migrate_isolate(mt))) - __mod_zone_freepage_state(zone, -(1UL << order), mt); - - del_page_from_free_list(free_page, zone, order); - for (pfn = free_page_pfn; - pfn < free_page_pfn + (1UL << order);) { - int mt = get_pfnblock_migratetype(pfn_to_page(pfn), pfn); - - free_page_order = min_t(unsigned int, - pfn ? __ffs(pfn) : order, - __fls(split_pfn_offset)); - __free_one_page(pfn_to_page(pfn), pfn, zone, free_page_order, - mt, FPI_NONE); - pfn += 1UL << free_page_order; - split_pfn_offset -= (1UL << free_page_order); - /* we have done the first part, now switch to second part */ - if (split_pfn_offset == 0) - split_pfn_offset = (1UL << order) - (pfn - free_page_pfn); - } -out: - spin_unlock_irqrestore(&zone->lock, flags); - return ret; -} /* * A bad page could be due to a number of fields. Instead of multiple branches, * try and check multiple fields with one check. The caller must do a detailed @@ -917,9 +898,7 @@ static inline bool page_expected_state(struct page *page, #ifdef CONFIG_MEMCG page->memcg_data | #endif -#ifdef CONFIG_PAGE_POOL - ((page->pp_magic & ~0x3UL) == PP_SIGNATURE) | -#endif + page_pool_page_is_pp(page) | (page->flags & check_flags))) return false; @@ -946,26 +925,18 @@ static const char *page_bad_reason(struct page *page, unsigned long flags) if (unlikely(page->memcg_data)) bad_reason = "page still charged to cgroup"; #endif -#ifdef CONFIG_PAGE_POOL - if (unlikely((page->pp_magic & ~0x3UL) == PP_SIGNATURE)) + if (unlikely(page_pool_page_is_pp(page))) bad_reason = "page_pool leak"; -#endif return bad_reason; } -static void free_page_is_bad_report(struct page *page) -{ - bad_page(page, - page_bad_reason(page, PAGE_FLAGS_CHECK_AT_FREE)); -} - static inline bool free_page_is_bad(struct page *page) { if (likely(page_expected_state(page, PAGE_FLAGS_CHECK_AT_FREE))) return false; /* Something has gone sideways, find it */ - free_page_is_bad_report(page); + bad_page(page, page_bad_reason(page, PAGE_FLAGS_CHECK_AT_FREE)); return true; } @@ -992,25 +963,58 @@ static int free_tail_page_prepare(struct page *head_page, struct page *page) switch (page - head_page) { case 1: /* the first tail page: these may be in place of ->mapping */ - if (unlikely(folio_entire_mapcount(folio))) { - bad_page(page, "nonzero entire_mapcount"); + if (unlikely(folio_large_mapcount(folio))) { + bad_page(page, "nonzero large_mapcount"); goto out; } - if (unlikely(atomic_read(&folio->_nr_pages_mapped))) { + if (IS_ENABLED(CONFIG_PAGE_MAPCOUNT) && + unlikely(atomic_read(&folio->_nr_pages_mapped))) { bad_page(page, "nonzero nr_pages_mapped"); goto out; } - if (unlikely(atomic_read(&folio->_pincount))) { - bad_page(page, "nonzero pincount"); - goto out; + if (IS_ENABLED(CONFIG_MM_ID)) { + if (unlikely(folio->_mm_id_mapcount[0] != -1)) { + bad_page(page, "nonzero mm mapcount 0"); + goto out; + } + if (unlikely(folio->_mm_id_mapcount[1] != -1)) { + bad_page(page, "nonzero mm mapcount 1"); + goto out; + } + } + if (IS_ENABLED(CONFIG_64BIT)) { + if (unlikely(atomic_read(&folio->_entire_mapcount) + 1)) { + bad_page(page, "nonzero entire_mapcount"); + goto out; + } + if (unlikely(atomic_read(&folio->_pincount))) { + bad_page(page, "nonzero pincount"); + goto out; + } } break; case 2: - /* - * the second tail page: ->mapping is - * deferred_list.next -- ignore value. - */ + /* the second tail page: deferred_list overlaps ->mapping */ + if (unlikely(!list_empty(&folio->_deferred_list))) { + bad_page(page, "on deferred list"); + goto out; + } + if (!IS_ENABLED(CONFIG_64BIT)) { + if (unlikely(atomic_read(&folio->_entire_mapcount) + 1)) { + bad_page(page, "nonzero entire_mapcount"); + goto out; + } + if (unlikely(atomic_read(&folio->_pincount))) { + bad_page(page, "nonzero pincount"); + goto out; + } + } break; + case 3: + /* the third tail page: hugetlb specifics overlap ->mappings */ + if (IS_ENABLED(CONFIG_HUGETLB_PAGE)) + break; + fallthrough; default: if (page->mapping != TAIL_MAPPING) { bad_page(page, "corrupted mapping in tail page"); @@ -1081,6 +1085,79 @@ static void kernel_init_pages(struct page *page, int numpages) kasan_enable_current(); } +#ifdef CONFIG_MEM_ALLOC_PROFILING + +/* Should be called only if mem_alloc_profiling_enabled() */ +void __clear_page_tag_ref(struct page *page) +{ + union pgtag_ref_handle handle; + union codetag_ref ref; + + if (get_page_tag_ref(page, &ref, &handle)) { + set_codetag_empty(&ref); + update_page_tag_ref(handle, &ref); + put_page_tag_ref(handle); + } +} + +/* Should be called only if mem_alloc_profiling_enabled() */ +static noinline +void __pgalloc_tag_add(struct page *page, struct task_struct *task, + unsigned int nr) +{ + union pgtag_ref_handle handle; + union codetag_ref ref; + + if (get_page_tag_ref(page, &ref, &handle)) { + alloc_tag_add(&ref, task->alloc_tag, PAGE_SIZE * nr); + update_page_tag_ref(handle, &ref); + put_page_tag_ref(handle); + } +} + +static inline void pgalloc_tag_add(struct page *page, struct task_struct *task, + unsigned int nr) +{ + if (mem_alloc_profiling_enabled()) + __pgalloc_tag_add(page, task, nr); +} + +/* Should be called only if mem_alloc_profiling_enabled() */ +static noinline +void __pgalloc_tag_sub(struct page *page, unsigned int nr) +{ + union pgtag_ref_handle handle; + union codetag_ref ref; + + if (get_page_tag_ref(page, &ref, &handle)) { + alloc_tag_sub(&ref, PAGE_SIZE * nr); + update_page_tag_ref(handle, &ref); + put_page_tag_ref(handle); + } +} + +static inline void pgalloc_tag_sub(struct page *page, unsigned int nr) +{ + if (mem_alloc_profiling_enabled()) + __pgalloc_tag_sub(page, nr); +} + +/* When tag is not NULL, assuming mem_alloc_profiling_enabled */ +static inline void pgalloc_tag_sub_pages(struct alloc_tag *tag, unsigned int nr) +{ + if (tag) + this_cpu_sub(tag->counters->bytes, PAGE_SIZE * nr); +} + +#else /* CONFIG_MEM_ALLOC_PROFILING */ + +static inline void pgalloc_tag_add(struct page *page, struct task_struct *task, + unsigned int nr) {} +static inline void pgalloc_tag_sub(struct page *page, unsigned int nr) {} +static inline void pgalloc_tag_sub_pages(struct alloc_tag *tag, unsigned int nr) {} + +#endif /* CONFIG_MEM_ALLOC_PROFILING */ + __always_inline bool free_pages_prepare(struct page *page, unsigned int order) { @@ -1088,6 +1165,7 @@ __always_inline bool free_pages_prepare(struct page *page, bool skip_kasan_poison = should_skip_kasan_poison(page); bool init = want_init_on_free(); bool compound = PageCompound(page); + struct folio *folio = page_folio(page); VM_BUG_ON_PAGE(PageTail(page), page); @@ -1097,10 +1175,32 @@ __always_inline bool free_pages_prepare(struct page *page, if (memcg_kmem_online() && PageMemcgKmem(page)) __memcg_kmem_uncharge_page(page, order); + /* + * In rare cases, when truncation or holepunching raced with + * munlock after VM_LOCKED was cleared, Mlocked may still be + * found set here. This does not indicate a problem, unless + * "unevictable_pgs_cleared" appears worryingly large. + */ + if (unlikely(folio_test_mlocked(folio))) { + long nr_pages = folio_nr_pages(folio); + + __folio_clear_mlocked(folio); + zone_stat_mod_folio(folio, NR_MLOCK, -nr_pages); + count_vm_events(UNEVICTABLE_PGCLEARED, nr_pages); + } + if (unlikely(PageHWPoison(page)) && !order) { /* Do not let hwpoison pages hit pcplists/buddy */ reset_page_owner(page, order); page_table_check_free(page, order); + pgalloc_tag_sub(page, 1 << order); + + /* + * The page is isolated and accounted for. + * Mark the codetag as empty to avoid accounting error + * when the page is freed by unpoison_memory(). + */ + clear_page_tag_ref(page); return false; } @@ -1113,8 +1213,12 @@ __always_inline bool free_pages_prepare(struct page *page, if (unlikely(order)) { int i; - if (compound) + if (compound) { page[1].flags &= ~PAGE_FLAGS_SECOND; +#ifdef NR_PAGES_IN_LARGE_FOLIO + folio->_nr_pages = 0; +#endif + } for (i = 1; i < (1 << order); i++) { if (compound) bad += free_tail_page_prepare(page, page + i); @@ -1127,8 +1231,11 @@ __always_inline bool free_pages_prepare(struct page *page, (page + i)->flags &= ~PAGE_FLAGS_CHECK_AT_PREP; } } - if (PageMappingFlags(page)) + if (PageMappingFlags(page)) { + if (PageAnon(page)) + mod_mthp_stat(order, MTHP_STAT_NR_ANON, -1); page->mapping = NULL; + } if (is_check_pages_enabled()) { if (free_page_is_bad(page)) bad++; @@ -1140,6 +1247,7 @@ __always_inline bool free_pages_prepare(struct page *page, page->flags &= ~PAGE_FLAGS_CHECK_AT_PREP; reset_page_owner(page, order); page_table_check_free(page, order); + pgalloc_tag_sub(page, 1 << order); if (!PageHighMem(page)) { debug_check_no_locks_freed(page_address(page), @@ -1191,7 +1299,6 @@ static void free_pcppages_bulk(struct zone *zone, int count, { unsigned long flags; unsigned int order; - bool isolated_pageblocks; struct page *page; /* @@ -1204,7 +1311,6 @@ static void free_pcppages_bulk(struct zone *zone, int count, pindex = pindex - 1; spin_lock_irqsave(&zone->lock, flags); - isolated_pageblocks = has_isolate_pageblock(zone); while (count > 0) { struct list_head *list; @@ -1220,23 +1326,19 @@ static void free_pcppages_bulk(struct zone *zone, int count, order = pindex_to_order(pindex); nr_pages = 1 << order; do { + unsigned long pfn; int mt; page = list_last_entry(list, struct page, pcp_list); - mt = get_pcppage_migratetype(page); + pfn = page_to_pfn(page); + mt = get_pfnblock_migratetype(page, pfn); /* must delete to avoid corrupting pcp list */ list_del(&page->pcp_list); count -= nr_pages; pcp->count -= nr_pages; - /* MIGRATE_ISOLATE page should not go to pcplists */ - VM_BUG_ON_PAGE(is_migrate_isolate(mt), page); - /* Pageblock could have been isolated meanwhile */ - if (unlikely(isolated_pageblocks)) - mt = get_pageblock_migratetype(page); - - __free_one_page(page, page_to_pfn(page), zone, order, mt, FPI_NONE); + __free_one_page(page, pfn, zone, order, mt, FPI_NONE); trace_mm_page_pcpu_drain(page, order, mt); } while (count > 0 && !list_empty(list)); } @@ -1244,45 +1346,87 @@ static void free_pcppages_bulk(struct zone *zone, int count, spin_unlock_irqrestore(&zone->lock, flags); } -static void free_one_page(struct zone *zone, - struct page *page, unsigned long pfn, - unsigned int order, - int migratetype, fpi_t fpi_flags) +/* Split a multi-block free page into its individual pageblocks. */ +static void split_large_buddy(struct zone *zone, struct page *page, + unsigned long pfn, int order, fpi_t fpi) +{ + unsigned long end = pfn + (1 << order); + + VM_WARN_ON_ONCE(!IS_ALIGNED(pfn, 1 << order)); + /* Caller removed page from freelist, buddy info cleared! */ + VM_WARN_ON_ONCE(PageBuddy(page)); + + if (order > pageblock_order) + order = pageblock_order; + + do { + int mt = get_pfnblock_migratetype(page, pfn); + + __free_one_page(page, pfn, zone, order, mt, fpi); + pfn += 1 << order; + if (pfn == end) + break; + page = pfn_to_page(pfn); + } while (1); +} + +static void add_page_to_zone_llist(struct zone *zone, struct page *page, + unsigned int order) +{ + /* Remember the order */ + page->order = order; + /* Add the page to the free list */ + llist_add(&page->pcp_llist, &zone->trylock_free_pages); +} + +static void free_one_page(struct zone *zone, struct page *page, + unsigned long pfn, unsigned int order, + fpi_t fpi_flags) { + struct llist_head *llhead; unsigned long flags; - spin_lock_irqsave(&zone->lock, flags); - if (unlikely(has_isolate_pageblock(zone) || - is_migrate_isolate(migratetype))) { - migratetype = get_pfnblock_migratetype(page, pfn); + if (unlikely(fpi_flags & FPI_TRYLOCK)) { + if (!spin_trylock_irqsave(&zone->lock, flags)) { + add_page_to_zone_llist(zone, page, order); + return; + } + } else { + spin_lock_irqsave(&zone->lock, flags); } - __free_one_page(page, pfn, zone, order, migratetype, fpi_flags); + + /* The lock succeeded. Process deferred pages. */ + llhead = &zone->trylock_free_pages; + if (unlikely(!llist_empty(llhead) && !(fpi_flags & FPI_TRYLOCK))) { + struct llist_node *llnode; + struct page *p, *tmp; + + llnode = llist_del_all(llhead); + llist_for_each_entry_safe(p, tmp, llnode, pcp_llist) { + unsigned int p_order = p->order; + + split_large_buddy(zone, p, page_to_pfn(p), p_order, fpi_flags); + __count_vm_events(PGFREE, 1 << p_order); + } + } + split_large_buddy(zone, page, pfn, order, fpi_flags); spin_unlock_irqrestore(&zone->lock, flags); + + __count_vm_events(PGFREE, 1 << order); } static void __free_pages_ok(struct page *page, unsigned int order, fpi_t fpi_flags) { - int migratetype; unsigned long pfn = page_to_pfn(page); struct zone *zone = page_zone(page); - if (!free_pages_prepare(page, order)) - return; - - /* - * Calling get_pfnblock_migratetype() without spin_lock_irqsave() here - * is used to avoid calling get_pfnblock_migratetype() under the lock. - * This will reduce the lock holding time. - */ - migratetype = get_pfnblock_migratetype(page, pfn); - - free_one_page(zone, page, pfn, order, migratetype, fpi_flags); - - __count_vm_events(PGFREE, 1 << order); + if (free_pages_prepare(page, order)) + free_one_page(zone, page, pfn, order, fpi_flags); } -void __free_pages_core(struct page *page, unsigned int order) +void __meminit __free_pages_core(struct page *page, unsigned int order, + enum meminit_context context) { unsigned int nr_pages = 1 << order; struct page *p = page; @@ -1292,23 +1436,34 @@ void __free_pages_core(struct page *page, unsigned int order) * When initializing the memmap, __init_single_page() sets the refcount * of all pages to 1 ("allocated"/"not free"). We have to set the * refcount of all involved pages to 0. + * + * Note that hotplugged memory pages are initialized to PageOffline(). + * Pages freed from memblock might be marked as reserved. */ - prefetchw(p); - for (loop = 0; loop < (nr_pages - 1); loop++, p++) { - prefetchw(p + 1); - __ClearPageReserved(p); - set_page_count(p, 0); - } - __ClearPageReserved(p); - set_page_count(p, 0); + if (IS_ENABLED(CONFIG_MEMORY_HOTPLUG) && + unlikely(context == MEMINIT_HOTPLUG)) { + for (loop = 0; loop < nr_pages; loop++, p++) { + VM_WARN_ON_ONCE(PageReserved(p)); + __ClearPageOffline(p); + set_page_count(p, 0); + } + + adjust_managed_page_count(page, nr_pages); + } else { + for (loop = 0; loop < nr_pages; loop++, p++) { + __ClearPageReserved(p); + set_page_count(p, 0); + } - atomic_long_add(nr_pages, &page_zone(page)->managed_pages); + /* memblock adjusts totalram_pages() manually. */ + atomic_long_add(nr_pages, &page_zone(page)->managed_pages); + } if (page_contains_unaccepted(page, order)) { if (order == MAX_PAGE_ORDER && __free_unaccepted(page)) return; - accept_page(page, order); + accept_memory(page_to_phys(page), PAGE_SIZE << order); } /* @@ -1384,10 +1539,11 @@ struct page *__pageblock_pfn_to_page(unsigned long start_pfn, * * -- nyc */ -static inline void expand(struct zone *zone, struct page *page, - int low, int high, int migratetype) +static inline unsigned int expand(struct zone *zone, struct page *page, int low, + int high, int migratetype) { - unsigned long size = 1 << high; + unsigned int size = 1 << high; + unsigned int nr_added = 0; while (high > low) { high--; @@ -1400,19 +1556,34 @@ static inline void expand(struct zone *zone, struct page *page, * Corresponding page table entries will not be touched, * pages will stay not present in virtual address space */ - if (set_page_guard(zone, &page[size], high, migratetype)) + if (set_page_guard(zone, &page[size], high)) continue; - add_to_free_list(&page[size], zone, high, migratetype); + __add_to_free_list(&page[size], zone, high, migratetype, false); set_buddy_order(&page[size], high); + nr_added += size; } + + return nr_added; +} + +static __always_inline void page_del_and_expand(struct zone *zone, + struct page *page, int low, + int high, int migratetype) +{ + int nr_pages = 1 << high; + + __del_page_from_free_list(page, zone, high, migratetype); + nr_pages -= expand(zone, page, low, high, migratetype); + account_freepages(zone, -nr_pages, migratetype); } static void check_new_page_bad(struct page *page) { - if (unlikely(page->flags & __PG_HWPOISON)) { + if (unlikely(PageHWPoison(page))) { /* Don't complain about hwpoisoned pages */ - page_mapcount_reset(page); /* remove PageBuddy */ + if (PageBuddy(page)) + __ClearPageBuddy(page); return; } @@ -1484,7 +1655,6 @@ inline void post_alloc_hook(struct page *page, unsigned int order, int i; set_page_private(page, 0); - set_page_refcounted(page); arch_alloc_page(page, order); debug_pagealloc_map_pages(page, 1 << order); @@ -1533,6 +1703,7 @@ inline void post_alloc_hook(struct page *page, unsigned int order, set_page_owner(page, order, gfp_flags); page_table_check_alloc(page, order); + pgalloc_tag_add(page, current, 1 << order); } static void prep_new_page(struct page *page, unsigned int order, gfp_t gfp_flags, @@ -1573,9 +1744,9 @@ struct page *__rmqueue_smallest(struct zone *zone, unsigned int order, page = get_page_from_free_area(area, migratetype); if (!page) continue; - del_page_from_free_list(page, zone, current_order); - expand(zone, page, order, current_order, migratetype); - set_pcppage_migratetype(page, migratetype); + + page_del_and_expand(zone, page, order, current_order, + migratetype); trace_mm_page_alloc_zone_locked(page, order, migratetype, pcp_allowed_order(order) && migratetype < MIGRATE_PCPTYPES); @@ -1592,7 +1763,7 @@ struct page *__rmqueue_smallest(struct zone *zone, unsigned int order, * * The other migratetypes do not have fallbacks. */ -static int fallbacks[MIGRATE_TYPES][MIGRATE_PCPTYPES - 1] = { +static int fallbacks[MIGRATE_PCPTYPES][MIGRATE_PCPTYPES - 1] = { [MIGRATE_UNMOVABLE] = { MIGRATE_RECLAIMABLE, MIGRATE_MOVABLE }, [MIGRATE_MOVABLE] = { MIGRATE_RECLAIMABLE, MIGRATE_UNMOVABLE }, [MIGRATE_RECLAIMABLE] = { MIGRATE_UNMOVABLE, MIGRATE_MOVABLE }, @@ -1610,30 +1781,23 @@ static inline struct page *__rmqueue_cma_fallback(struct zone *zone, #endif /* - * Move the free pages in a range to the freelist tail of the requested type. - * Note that start_page and end_pages are not aligned on a pageblock - * boundary. If alignment is required, use move_freepages_block() + * Change the type of a block and move all its free pages to that + * type's freelist. */ -static int move_freepages(struct zone *zone, - unsigned long start_pfn, unsigned long end_pfn, - int migratetype, int *num_movable) +static int __move_freepages_block(struct zone *zone, unsigned long start_pfn, + int old_mt, int new_mt) { struct page *page; - unsigned long pfn; + unsigned long pfn, end_pfn; unsigned int order; int pages_moved = 0; - for (pfn = start_pfn; pfn <= end_pfn;) { + VM_WARN_ON(start_pfn & (pageblock_nr_pages - 1)); + end_pfn = pageblock_end_pfn(start_pfn); + + for (pfn = start_pfn; pfn < end_pfn;) { page = pfn_to_page(pfn); if (!PageBuddy(page)) { - /* - * We assume that pages that could be isolated for - * migration are movable. But we don't actually try - * isolating, as that would be expensive. - */ - if (num_movable && - (PageLRU(page) || __PageMovable(page))) - (*num_movable)++; pfn++; continue; } @@ -1643,78 +1807,175 @@ static int move_freepages(struct zone *zone, VM_BUG_ON_PAGE(page_zone(page) != zone, page); order = buddy_order(page); - move_to_free_list(page, zone, order, migratetype); + + move_to_free_list(page, zone, order, old_mt, new_mt); + pfn += 1 << order; pages_moved += 1 << order; } + set_pageblock_migratetype(pfn_to_page(start_pfn), new_mt); + return pages_moved; } -int move_freepages_block(struct zone *zone, struct page *page, - int migratetype, int *num_movable) +static bool prep_move_freepages_block(struct zone *zone, struct page *page, + unsigned long *start_pfn, + int *num_free, int *num_movable) { - unsigned long start_pfn, end_pfn, pfn; + unsigned long pfn, start, end; + + pfn = page_to_pfn(page); + start = pageblock_start_pfn(pfn); + end = pageblock_end_pfn(pfn); + + /* + * The caller only has the lock for @zone, don't touch ranges + * that straddle into other zones. While we could move part of + * the range that's inside the zone, this call is usually + * accompanied by other operations such as migratetype updates + * which also should be locked. + */ + if (!zone_spans_pfn(zone, start)) + return false; + if (!zone_spans_pfn(zone, end - 1)) + return false; + + *start_pfn = start; - if (num_movable) + if (num_free) { + *num_free = 0; *num_movable = 0; + for (pfn = start; pfn < end;) { + page = pfn_to_page(pfn); + if (PageBuddy(page)) { + int nr = 1 << buddy_order(page); - pfn = page_to_pfn(page); - start_pfn = pageblock_start_pfn(pfn); - end_pfn = pageblock_end_pfn(pfn) - 1; + *num_free += nr; + pfn += nr; + continue; + } + /* + * We assume that pages that could be isolated for + * migration are movable. But we don't actually try + * isolating, as that would be expensive. + */ + if (PageLRU(page) || __PageMovable(page)) + (*num_movable)++; + pfn++; + } + } - /* Do not cross zone boundaries */ - if (!zone_spans_pfn(zone, start_pfn)) - start_pfn = pfn; - if (!zone_spans_pfn(zone, end_pfn)) - return 0; + return true; +} - return move_freepages(zone, start_pfn, end_pfn, migratetype, - num_movable); +static int move_freepages_block(struct zone *zone, struct page *page, + int old_mt, int new_mt) +{ + unsigned long start_pfn; + + if (!prep_move_freepages_block(zone, page, &start_pfn, NULL, NULL)) + return -1; + + return __move_freepages_block(zone, start_pfn, old_mt, new_mt); } -static void change_pageblock_range(struct page *pageblock_page, - int start_order, int migratetype) +#ifdef CONFIG_MEMORY_ISOLATION +/* Look for a buddy that straddles start_pfn */ +static unsigned long find_large_buddy(unsigned long start_pfn) { - int nr_pageblocks = 1 << (start_order - pageblock_order); + int order = 0; + struct page *page; + unsigned long pfn = start_pfn; - while (nr_pageblocks--) { - set_pageblock_migratetype(pageblock_page, migratetype); - pageblock_page += pageblock_nr_pages; + while (!PageBuddy(page = pfn_to_page(pfn))) { + /* Nothing found */ + if (++order > MAX_PAGE_ORDER) + return start_pfn; + pfn &= ~0UL << order; } + + /* + * Found a preceding buddy, but does it straddle? + */ + if (pfn + (1 << buddy_order(page)) > start_pfn) + return pfn; + + /* Nothing found */ + return start_pfn; } -/* - * When we are falling back to another migratetype during allocation, try to - * steal extra free pages from the same pageblocks to satisfy further - * allocations, instead of polluting multiple pageblocks. +/** + * move_freepages_block_isolate - move free pages in block for page isolation + * @zone: the zone + * @page: the pageblock page + * @migratetype: migratetype to set on the pageblock * - * If we are stealing a relatively large buddy page, it is likely there will - * be more free pages in the pageblock, so try to steal them all. For - * reclaimable and unmovable allocations, we steal regardless of page size, - * as fragmentation caused by those allocations polluting movable pageblocks - * is worse than movable allocations stealing from unmovable and reclaimable - * pageblocks. + * This is similar to move_freepages_block(), but handles the special + * case encountered in page isolation, where the block of interest + * might be part of a larger buddy spanning multiple pageblocks. + * + * Unlike the regular page allocator path, which moves pages while + * stealing buddies off the freelist, page isolation is interested in + * arbitrary pfn ranges that may have overlapping buddies on both ends. + * + * This function handles that. Straddling buddies are split into + * individual pageblocks. Only the block of interest is moved. + * + * Returns %true if pages could be moved, %false otherwise. */ -static bool can_steal_fallback(unsigned int order, int start_mt) +bool move_freepages_block_isolate(struct zone *zone, struct page *page, + int migratetype) { - /* - * Leaving this order check is intended, although there is - * relaxed order check in next check. The reason is that - * we can actually steal whole pageblock if this condition met, - * but, below check doesn't guarantee it and that is just heuristic - * so could be changed anytime. - */ - if (order >= pageblock_order) + unsigned long start_pfn, pfn; + + if (!prep_move_freepages_block(zone, page, &start_pfn, NULL, NULL)) + return false; + + /* No splits needed if buddies can't span multiple blocks */ + if (pageblock_order == MAX_PAGE_ORDER) + goto move; + + /* We're a tail block in a larger buddy */ + pfn = find_large_buddy(start_pfn); + if (pfn != start_pfn) { + struct page *buddy = pfn_to_page(pfn); + int order = buddy_order(buddy); + + del_page_from_free_list(buddy, zone, order, + get_pfnblock_migratetype(buddy, pfn)); + set_pageblock_migratetype(page, migratetype); + split_large_buddy(zone, buddy, pfn, order, FPI_NONE); return true; + } - if (order >= pageblock_order / 2 || - start_mt == MIGRATE_RECLAIMABLE || - start_mt == MIGRATE_UNMOVABLE || - page_group_by_mobility_disabled) + /* We're the starting block of a larger buddy */ + if (PageBuddy(page) && buddy_order(page) > pageblock_order) { + int order = buddy_order(page); + + del_page_from_free_list(page, zone, order, + get_pfnblock_migratetype(page, pfn)); + set_pageblock_migratetype(page, migratetype); + split_large_buddy(zone, page, pfn, order, FPI_NONE); return true; + } +move: + __move_freepages_block(zone, start_pfn, + get_pfnblock_migratetype(page, start_pfn), + migratetype); + return true; +} +#endif /* CONFIG_MEMORY_ISOLATION */ - return false; +static void change_pageblock_range(struct page *pageblock_page, + int start_order, int migratetype) +{ + int nr_pageblocks = 1 << (start_order - pageblock_order); + + while (nr_pageblocks--) { + set_pageblock_migratetype(pageblock_page, migratetype); + pageblock_page += pageblock_nr_pages; + } } static inline bool boost_watermark(struct zone *zone) @@ -1755,33 +2016,103 @@ static inline bool boost_watermark(struct zone *zone) } /* - * This function implements actual steal behaviour. If order is large enough, - * we can steal whole pageblock. If not, we first move freepages in this - * pageblock to our migratetype and determine how many already-allocated pages - * are there in the pageblock with a compatible migratetype. If at least half - * of pages are free or compatible, we can change migratetype of the pageblock - * itself, so pages freed in the future will be put on the correct free list. + * When we are falling back to another migratetype during allocation, should we + * try to claim an entire block to satisfy further allocations, instead of + * polluting multiple pageblocks? */ -static void steal_suitable_fallback(struct zone *zone, struct page *page, - unsigned int alloc_flags, int start_type, bool whole_block) +static bool should_try_claim_block(unsigned int order, int start_mt) { - unsigned int current_order = buddy_order(page); - int free_pages, movable_pages, alike_pages; - int old_block_type; + /* + * Leaving this order check is intended, although there is + * relaxed order check in next check. The reason is that + * we can actually claim the whole pageblock if this condition met, + * but, below check doesn't guarantee it and that is just heuristic + * so could be changed anytime. + */ + if (order >= pageblock_order) + return true; - old_block_type = get_pageblock_migratetype(page); + /* + * Above a certain threshold, always try to claim, as it's likely there + * will be more free pages in the pageblock. + */ + if (order >= pageblock_order / 2) + return true; /* - * This can happen due to races and we want to prevent broken - * highatomic accounting. + * Unmovable/reclaimable allocations would cause permanent + * fragmentations if they fell back to allocating from a movable block + * (polluting it), so we try to claim the whole block regardless of the + * allocation size. Later movable allocations can always steal from this + * block, which is less problematic. */ - if (is_migrate_highatomic(old_block_type)) - goto single_page; + if (start_mt == MIGRATE_RECLAIMABLE || start_mt == MIGRATE_UNMOVABLE) + return true; + + if (page_group_by_mobility_disabled) + return true; + + /* + * Movable pages won't cause permanent fragmentation, so when you alloc + * small pages, we just need to temporarily steal unmovable or + * reclaimable pages that are closest to the request size. After a + * while, memory compaction may occur to form large contiguous pages, + * and the next movable allocation may not need to steal. + */ + return false; +} + +/* + * Check whether there is a suitable fallback freepage with requested order. + * If claimable is true, this function returns fallback_mt only if + * we would do this whole-block claiming. This would help to reduce + * fragmentation due to mixed migratetype pages in one pageblock. + */ +int find_suitable_fallback(struct free_area *area, unsigned int order, + int migratetype, bool claimable) +{ + int i; + + if (claimable && !should_try_claim_block(order, migratetype)) + return -2; + + if (area->nr_free == 0) + return -1; + + for (i = 0; i < MIGRATE_PCPTYPES - 1 ; i++) { + int fallback_mt = fallbacks[migratetype][i]; + + if (!free_area_empty(area, fallback_mt)) + return fallback_mt; + } + + return -1; +} + +/* + * This function implements actual block claiming behaviour. If order is large + * enough, we can claim the whole pageblock for the requested migratetype. If + * not, we check the pageblock for constituent pages; if at least half of the + * pages are free or compatible, we can still claim the whole block, so pages + * freed in the future will be put on the correct free list. + */ +static struct page * +try_to_claim_block(struct zone *zone, struct page *page, + int current_order, int order, int start_type, + int block_type, unsigned int alloc_flags) +{ + int free_pages, movable_pages, alike_pages; + unsigned long start_pfn; /* Take ownership for orders >= pageblock_order */ if (current_order >= pageblock_order) { + unsigned int nr_added; + + del_page_from_free_list(page, zone, current_order, block_type); change_pageblock_range(page, current_order, start_type); - goto single_page; + nr_added = expand(zone, page, order, current_order, start_type); + account_freepages(zone, nr_added, start_type); + return page; } /* @@ -1792,15 +2123,10 @@ static void steal_suitable_fallback(struct zone *zone, struct page *page, if (boost_watermark(zone) && (alloc_flags & ALLOC_KSWAPD)) set_bit(ZONE_BOOSTED_WATERMARK, &zone->flags); - /* We are not allowed to try stealing from the whole block */ - if (!whole_block) - goto single_page; - - free_pages = move_freepages_block(zone, page, start_type, - &movable_pages); /* moving whole block can fail due to zone boundary conditions */ - if (!free_pages) - goto single_page; + if (!prep_move_freepages_block(zone, page, &start_pfn, &free_pages, + &movable_pages)) + return NULL; /* * Determine how many pages are compatible with our allocation. @@ -1817,7 +2143,7 @@ static void steal_suitable_fallback(struct zone *zone, struct page *page, * vice versa, be conservative since we can't distinguish the * exact migratetype of non-movable pages. */ - if (old_block_type == MIGRATE_MOVABLE) + if (block_type == MIGRATE_MOVABLE) alike_pages = pageblock_nr_pages - (free_pages + movable_pages); else @@ -1828,182 +2154,24 @@ static void steal_suitable_fallback(struct zone *zone, struct page *page, * compatible migratability as our allocation, claim the whole block. */ if (free_pages + alike_pages >= (1 << (pageblock_order-1)) || - page_group_by_mobility_disabled) - set_pageblock_migratetype(page, start_type); - - return; - -single_page: - move_to_free_list(page, zone, current_order, start_type); -} - -/* - * Check whether there is a suitable fallback freepage with requested order. - * If only_stealable is true, this function returns fallback_mt only if - * we can steal other freepages all together. This would help to reduce - * fragmentation due to mixed migratetype pages in one pageblock. - */ -int find_suitable_fallback(struct free_area *area, unsigned int order, - int migratetype, bool only_stealable, bool *can_steal) -{ - int i; - int fallback_mt; - - if (area->nr_free == 0) - return -1; - - *can_steal = false; - for (i = 0; i < MIGRATE_PCPTYPES - 1 ; i++) { - fallback_mt = fallbacks[migratetype][i]; - if (free_area_empty(area, fallback_mt)) - continue; - - if (can_steal_fallback(order, migratetype)) - *can_steal = true; - - if (!only_stealable) - return fallback_mt; - - if (*can_steal) - return fallback_mt; - } - - return -1; -} - -/* - * Reserve a pageblock for exclusive use of high-order atomic allocations if - * there are no empty page blocks that contain a page with a suitable order - */ -static void reserve_highatomic_pageblock(struct page *page, struct zone *zone) -{ - int mt; - unsigned long max_managed, flags; - - /* - * The number reserved as: minimum is 1 pageblock, maximum is - * roughly 1% of a zone. But if 1% of a zone falls below a - * pageblock size, then don't reserve any pageblocks. - * Check is race-prone but harmless. - */ - if ((zone_managed_pages(zone) / 100) < pageblock_nr_pages) - return; - max_managed = ALIGN((zone_managed_pages(zone) / 100), pageblock_nr_pages); - if (zone->nr_reserved_highatomic >= max_managed) - return; - - spin_lock_irqsave(&zone->lock, flags); - - /* Recheck the nr_reserved_highatomic limit under the lock */ - if (zone->nr_reserved_highatomic >= max_managed) - goto out_unlock; - - /* Yoink! */ - mt = get_pageblock_migratetype(page); - /* Only reserve normal pageblocks (i.e., they can merge with others) */ - if (migratetype_is_mergeable(mt)) { - zone->nr_reserved_highatomic += pageblock_nr_pages; - set_pageblock_migratetype(page, MIGRATE_HIGHATOMIC); - move_freepages_block(zone, page, MIGRATE_HIGHATOMIC, NULL); + page_group_by_mobility_disabled) { + __move_freepages_block(zone, start_pfn, block_type, start_type); + return __rmqueue_smallest(zone, order, start_type); } -out_unlock: - spin_unlock_irqrestore(&zone->lock, flags); -} - -/* - * Used when an allocation is about to fail under memory pressure. This - * potentially hurts the reliability of high-order allocations when under - * intense memory pressure but failed atomic allocations should be easier - * to recover from than an OOM. - * - * If @force is true, try to unreserve a pageblock even though highatomic - * pageblock is exhausted. - */ -static bool unreserve_highatomic_pageblock(const struct alloc_context *ac, - bool force) -{ - struct zonelist *zonelist = ac->zonelist; - unsigned long flags; - struct zoneref *z; - struct zone *zone; - struct page *page; - int order; - bool ret; - - for_each_zone_zonelist_nodemask(zone, z, zonelist, ac->highest_zoneidx, - ac->nodemask) { - /* - * Preserve at least one pageblock unless memory pressure - * is really high. - */ - if (!force && zone->nr_reserved_highatomic <= - pageblock_nr_pages) - continue; - - spin_lock_irqsave(&zone->lock, flags); - for (order = 0; order < NR_PAGE_ORDERS; order++) { - struct free_area *area = &(zone->free_area[order]); - - page = get_page_from_free_area(area, MIGRATE_HIGHATOMIC); - if (!page) - continue; - - /* - * In page freeing path, migratetype change is racy so - * we can counter several free pages in a pageblock - * in this loop although we changed the pageblock type - * from highatomic to ac->migratetype. So we should - * adjust the count once. - */ - if (is_migrate_highatomic_page(page)) { - /* - * It should never happen but changes to - * locking could inadvertently allow a per-cpu - * drain to add pages to MIGRATE_HIGHATOMIC - * while unreserving so be safe and watch for - * underflows. - */ - zone->nr_reserved_highatomic -= min( - pageblock_nr_pages, - zone->nr_reserved_highatomic); - } - - /* - * Convert to ac->migratetype and avoid the normal - * pageblock stealing heuristics. Minimally, the caller - * is doing the work and needs the pages. More - * importantly, if the block was always converted to - * MIGRATE_UNMOVABLE or another type then the number - * of pageblocks that cannot be completely freed - * may increase. - */ - set_pageblock_migratetype(page, ac->migratetype); - ret = move_freepages_block(zone, page, ac->migratetype, - NULL); - if (ret) { - spin_unlock_irqrestore(&zone->lock, flags); - return ret; - } - } - spin_unlock_irqrestore(&zone->lock, flags); - } - - return false; + return NULL; } /* - * Try finding a free buddy page on the fallback list and put it on the free - * list of requested migratetype, possibly along with other pages from the same - * block, depending on fragmentation avoidance heuristics. Returns true if - * fallback was found so that __rmqueue_smallest() can grab it. + * Try to allocate from some fallback migratetype by claiming the entire block, + * i.e. converting it to the allocation's start migratetype. * * The use of signed ints for order and current_order is a deliberate * deviation from the rest of this file, to make the for loop * condition simpler. */ -static __always_inline bool -__rmqueue_fallback(struct zone *zone, int order, int start_migratetype, +static __always_inline struct page * +__rmqueue_claim(struct zone *zone, int order, int start_migratetype, unsigned int alloc_flags) { struct free_area *area; @@ -2011,7 +2179,6 @@ __rmqueue_fallback(struct zone *zone, int order, int start_migratetype, int min_order = order; struct page *page; int fallback_mt; - bool can_steal; /* * Do not steal pages from freelists belonging to other pageblocks @@ -2030,62 +2197,73 @@ __rmqueue_fallback(struct zone *zone, int order, int start_migratetype, --current_order) { area = &(zone->free_area[current_order]); fallback_mt = find_suitable_fallback(area, current_order, - start_migratetype, false, &can_steal); + start_migratetype, true); + + /* No block in that order */ if (fallback_mt == -1) continue; - /* - * We cannot steal all free pages from the pageblock and the - * requested migratetype is movable. In that case it's better to - * steal and split the smallest available page instead of the - * largest available page, because even if the next movable - * allocation falls back into a different pageblock than this - * one, it won't cause permanent fragmentation. - */ - if (!can_steal && start_migratetype == MIGRATE_MOVABLE - && current_order > order) - goto find_smallest; + /* Advanced into orders too low to claim, abort */ + if (fallback_mt == -2) + break; - goto do_steal; + page = get_page_from_free_area(area, fallback_mt); + page = try_to_claim_block(zone, page, current_order, order, + start_migratetype, fallback_mt, + alloc_flags); + if (page) { + trace_mm_page_alloc_extfrag(page, order, current_order, + start_migratetype, fallback_mt); + return page; + } } - return false; + return NULL; +} + +/* + * Try to steal a single page from some fallback migratetype. Leave the rest of + * the block as its current migratetype, potentially causing fragmentation. + */ +static __always_inline struct page * +__rmqueue_steal(struct zone *zone, int order, int start_migratetype) +{ + struct free_area *area; + int current_order; + struct page *page; + int fallback_mt; -find_smallest: for (current_order = order; current_order < NR_PAGE_ORDERS; current_order++) { area = &(zone->free_area[current_order]); fallback_mt = find_suitable_fallback(area, current_order, - start_migratetype, false, &can_steal); - if (fallback_mt != -1) - break; - } - - /* - * This should not happen - we already found a suitable fallback - * when looking for the largest page. - */ - VM_BUG_ON(current_order > MAX_PAGE_ORDER); - -do_steal: - page = get_page_from_free_area(area, fallback_mt); - - steal_suitable_fallback(zone, page, alloc_flags, start_migratetype, - can_steal); - - trace_mm_page_alloc_extfrag(page, order, current_order, - start_migratetype, fallback_mt); + start_migratetype, false); + if (fallback_mt == -1) + continue; - return true; + page = get_page_from_free_area(area, fallback_mt); + page_del_and_expand(zone, page, order, current_order, fallback_mt); + trace_mm_page_alloc_extfrag(page, order, current_order, + start_migratetype, fallback_mt); + return page; + } + return NULL; } +enum rmqueue_mode { + RMQUEUE_NORMAL, + RMQUEUE_CMA, + RMQUEUE_CLAIM, + RMQUEUE_STEAL, +}; + /* * Do the hard work of removing an element from the buddy allocator. * Call me with the zone->lock already held. */ static __always_inline struct page * __rmqueue(struct zone *zone, unsigned int order, int migratetype, - unsigned int alloc_flags) + unsigned int alloc_flags, enum rmqueue_mode *mode) { struct page *page; @@ -2103,17 +2281,49 @@ __rmqueue(struct zone *zone, unsigned int order, int migratetype, return page; } } -retry: - page = __rmqueue_smallest(zone, order, migratetype); - if (unlikely(!page)) { - if (alloc_flags & ALLOC_CMA) - page = __rmqueue_cma_fallback(zone, order); - if (!page && __rmqueue_fallback(zone, order, migratetype, - alloc_flags)) - goto retry; + /* + * First try the freelists of the requested migratetype, then try + * fallbacks modes with increasing levels of fragmentation risk. + * + * The fallback logic is expensive and rmqueue_bulk() calls in + * a loop with the zone->lock held, meaning the freelists are + * not subject to any outside changes. Remember in *mode where + * we found pay dirt, to save us the search on the next call. + */ + switch (*mode) { + case RMQUEUE_NORMAL: + page = __rmqueue_smallest(zone, order, migratetype); + if (page) + return page; + fallthrough; + case RMQUEUE_CMA: + if (alloc_flags & ALLOC_CMA) { + page = __rmqueue_cma_fallback(zone, order); + if (page) { + *mode = RMQUEUE_CMA; + return page; + } + } + fallthrough; + case RMQUEUE_CLAIM: + page = __rmqueue_claim(zone, order, migratetype, alloc_flags); + if (page) { + /* Replenished preferred freelist, back to normal mode. */ + *mode = RMQUEUE_NORMAL; + return page; + } + fallthrough; + case RMQUEUE_STEAL: + if (!(alloc_flags & ALLOC_NOFRAGMENT)) { + page = __rmqueue_steal(zone, order, migratetype); + if (page) { + *mode = RMQUEUE_STEAL; + return page; + } + } } - return page; + return NULL; } /* @@ -2125,13 +2335,19 @@ static int rmqueue_bulk(struct zone *zone, unsigned int order, unsigned long count, struct list_head *list, int migratetype, unsigned int alloc_flags) { + enum rmqueue_mode rmqm = RMQUEUE_NORMAL; unsigned long flags; int i; - spin_lock_irqsave(&zone->lock, flags); + if (unlikely(alloc_flags & ALLOC_TRYLOCK)) { + if (!spin_trylock_irqsave(&zone->lock, flags)) + return 0; + } else { + spin_lock_irqsave(&zone->lock, flags); + } for (i = 0; i < count; ++i) { struct page *page = __rmqueue(zone, order, migratetype, - alloc_flags); + alloc_flags, &rmqm); if (unlikely(page == NULL)) break; @@ -2146,12 +2362,7 @@ static int rmqueue_bulk(struct zone *zone, unsigned int order, * pages are ordered properly. */ list_add_tail(&page->pcp_list, list); - if (is_migrate_cma(get_pcppage_migratetype(page))) - __mod_zone_page_state(zone, NR_FREE_CMA_PAGES, - -(1 << order)); } - - __mod_zone_page_state(zone, NR_FREE_PAGES, -(i << order)); spin_unlock_irqrestore(&zone->lock, flags); return i; @@ -2216,14 +2427,21 @@ void drain_zone_pages(struct zone *zone, struct per_cpu_pages *pcp) */ static void drain_pages_zone(unsigned int cpu, struct zone *zone) { - struct per_cpu_pages *pcp; + struct per_cpu_pages *pcp = per_cpu_ptr(zone->per_cpu_pageset, cpu); + int count; - pcp = per_cpu_ptr(zone->per_cpu_pageset, cpu); - if (pcp->count) { + do { spin_lock(&pcp->lock); - free_pcppages_bulk(zone, pcp->count, pcp, 0); + count = pcp->count; + if (count) { + int to_drain = min(count, + pcp->batch << CONFIG_PCP_BATCH_SCALE_MAX); + + free_pcppages_bulk(zone, to_drain, pcp, 0); + count -= to_drain; + } spin_unlock(&pcp->lock); - } + } while (count); } /* @@ -2339,19 +2557,6 @@ void drain_all_pages(struct zone *zone) __drain_all_pages(zone, false); } -static bool free_unref_page_prepare(struct page *page, unsigned long pfn, - unsigned int order) -{ - int migratetype; - - if (!free_pages_prepare(page, order)) - return false; - - migratetype = get_pfnblock_migratetype(page, pfn); - set_pcppage_migratetype(page, migratetype); - return true; -} - static int nr_pcp_free(struct per_cpu_pages *pcp, int batch, int high, bool free_high) { int min_nr_free, max_nr_free; @@ -2425,9 +2630,9 @@ static int nr_pcp_high(struct per_cpu_pages *pcp, struct zone *zone, return high; } -static void free_unref_page_commit(struct zone *zone, struct per_cpu_pages *pcp, - struct page *page, int migratetype, - unsigned int order) +static void free_frozen_page_commit(struct zone *zone, + struct per_cpu_pages *pcp, struct page *page, int migratetype, + unsigned int order, fpi_t fpi_flags) { int high, batch; int pindex; @@ -2452,16 +2657,24 @@ static void free_unref_page_commit(struct zone *zone, struct per_cpu_pages *pcp, * stops will be drained from vmstat refresh context. */ if (order && order <= PAGE_ALLOC_COSTLY_ORDER) { - free_high = (pcp->free_count >= batch && + free_high = (pcp->free_count >= (batch + pcp->high_min / 2) && (pcp->flags & PCPF_PREV_FREE_HIGH_ORDER) && (!(pcp->flags & PCPF_FREE_HIGH_BATCH) || - pcp->count >= READ_ONCE(batch))); + pcp->count >= batch)); pcp->flags |= PCPF_PREV_FREE_HIGH_ORDER; } else if (pcp->flags & PCPF_PREV_FREE_HIGH_ORDER) { pcp->flags &= ~PCPF_PREV_FREE_HIGH_ORDER; } if (pcp->free_count < (batch << CONFIG_PCP_BATCH_SCALE_MAX)) pcp->free_count += (1 << order); + + if (unlikely(fpi_flags & FPI_TRYLOCK)) { + /* + * Do not attempt to take a zone lock. Let pcp->count get + * over high mark temporarily. + */ + return; + } high = nr_pcp_high(pcp, zone, batch, free_high); if (pcp->count >= high) { free_pcppages_bulk(zone, nr_pcp_free(pcp, batch, high, free_high), @@ -2476,15 +2689,21 @@ static void free_unref_page_commit(struct zone *zone, struct per_cpu_pages *pcp, /* * Free a pcp page */ -void free_unref_page(struct page *page, unsigned int order) +static void __free_frozen_pages(struct page *page, unsigned int order, + fpi_t fpi_flags) { unsigned long __maybe_unused UP_flags; struct per_cpu_pages *pcp; struct zone *zone; unsigned long pfn = page_to_pfn(page); - int migratetype, pcpmigratetype; + int migratetype; - if (!free_unref_page_prepare(page, pfn, order)) + if (!pcp_allowed_order(order)) { + __free_pages_ok(page, order, fpi_flags); + return; + } + + if (!free_pages_prepare(page, order)) return; /* @@ -2494,27 +2713,37 @@ void free_unref_page(struct page *page, unsigned int order) * get those areas back if necessary. Otherwise, we may have to free * excessively into the page allocator */ - migratetype = pcpmigratetype = get_pcppage_migratetype(page); + zone = page_zone(page); + migratetype = get_pfnblock_migratetype(page, pfn); if (unlikely(migratetype >= MIGRATE_PCPTYPES)) { if (unlikely(is_migrate_isolate(migratetype))) { - free_one_page(page_zone(page), page, pfn, order, migratetype, FPI_NONE); + free_one_page(zone, page, pfn, order, fpi_flags); return; } - pcpmigratetype = MIGRATE_MOVABLE; + migratetype = MIGRATE_MOVABLE; } - zone = page_zone(page); + if (unlikely((fpi_flags & FPI_TRYLOCK) && IS_ENABLED(CONFIG_PREEMPT_RT) + && (in_nmi() || in_hardirq()))) { + add_page_to_zone_llist(zone, page, order); + return; + } pcp_trylock_prepare(UP_flags); pcp = pcp_spin_trylock(zone->per_cpu_pageset); if (pcp) { - free_unref_page_commit(zone, pcp, page, pcpmigratetype, order); + free_frozen_page_commit(zone, pcp, page, migratetype, order, fpi_flags); pcp_spin_unlock(pcp); } else { - free_one_page(zone, page, pfn, order, migratetype, FPI_NONE); + free_one_page(zone, page, pfn, order, fpi_flags); } pcp_trylock_finish(UP_flags); } +void free_frozen_pages(struct page *page, unsigned int order) +{ + __free_frozen_pages(page, order, FPI_NONE); +} + /* * Free a batch of folios */ @@ -2523,7 +2752,7 @@ void free_unref_folios(struct folio_batch *folios) unsigned long __maybe_unused UP_flags; struct per_cpu_pages *pcp = NULL; struct zone *locked_zone = NULL; - int i, j, migratetype; + int i, j; /* Prepare folios for freeing */ for (i = 0, j = 0; i < folios->nr; i++) { @@ -2531,20 +2760,15 @@ void free_unref_folios(struct folio_batch *folios) unsigned long pfn = folio_pfn(folio); unsigned int order = folio_order(folio); - if (order > 0 && folio_test_large_rmappable(folio)) - folio_undo_large_rmappable(folio); - if (!free_unref_page_prepare(&folio->page, pfn, order)) + if (!free_pages_prepare(&folio->page, order)) continue; - /* - * Free isolated folios and orders not handled on the PCP - * directly to the allocator, see comment in free_unref_page. + * Free orders not handled on the PCP directly to the + * allocator. */ - migratetype = get_pcppage_migratetype(&folio->page); - if (!pcp_allowed_order(order) || - is_migrate_isolate(migratetype)) { - free_one_page(folio_zone(folio), &folio->page, pfn, - order, migratetype, FPI_NONE); + if (!pcp_allowed_order(order)) { + free_one_page(folio_zone(folio), &folio->page, + pfn, order, FPI_NONE); continue; } folio->private = (void *)(unsigned long)order; @@ -2557,16 +2781,31 @@ void free_unref_folios(struct folio_batch *folios) for (i = 0; i < folios->nr; i++) { struct folio *folio = folios->folios[i]; struct zone *zone = folio_zone(folio); + unsigned long pfn = folio_pfn(folio); unsigned int order = (unsigned long)folio->private; + int migratetype; folio->private = NULL; - migratetype = get_pcppage_migratetype(&folio->page); + migratetype = get_pfnblock_migratetype(&folio->page, pfn); /* Different zone requires a different pcp lock */ - if (zone != locked_zone) { + if (zone != locked_zone || + is_migrate_isolate(migratetype)) { if (pcp) { pcp_spin_unlock(pcp); pcp_trylock_finish(UP_flags); + locked_zone = NULL; + pcp = NULL; + } + + /* + * Free isolated pages directly to the + * allocator, see comment in free_frozen_pages. + */ + if (is_migrate_isolate(migratetype)) { + free_one_page(zone, &folio->page, pfn, + order, FPI_NONE); + continue; } /* @@ -2577,10 +2816,8 @@ void free_unref_folios(struct folio_batch *folios) pcp = pcp_spin_trylock(zone->per_cpu_pageset); if (unlikely(!pcp)) { pcp_trylock_finish(UP_flags); - free_one_page(zone, &folio->page, - folio_pfn(folio), order, - migratetype, FPI_NONE); - locked_zone = NULL; + free_one_page(zone, &folio->page, pfn, + order, FPI_NONE); continue; } locked_zone = zone; @@ -2594,8 +2831,8 @@ void free_unref_folios(struct folio_batch *folios) migratetype = MIGRATE_MOVABLE; trace_mm_page_free_batched(&folio->page); - free_unref_page_commit(zone, pcp, &folio->page, migratetype, - order); + free_frozen_page_commit(zone, pcp, &folio->page, migratetype, + order, FPI_NONE); } if (pcp) { @@ -2623,7 +2860,8 @@ void split_page(struct page *page, unsigned int order) for (i = 1; i < (1 << order); i++) set_page_refcounted(page + i); split_page_owner(page, order, 0); - split_page_memcg(page, order, 0); + pgalloc_tag_split(page_folio(page), order, 0); + split_page_memcg(page, order); } EXPORT_SYMBOL_GPL(split_page); @@ -2643,11 +2881,9 @@ int __isolate_free_page(struct page *page, unsigned int order) watermark = zone->_watermark[WMARK_MIN] + (1UL << order); if (!zone_watermark_ok(zone, 0, watermark, 0, ALLOC_CMA)) return 0; - - __mod_zone_freepage_state(zone, -(1UL << order), mt); } - del_page_from_free_list(page, zone, order); + del_page_from_free_list(page, zone, order, mt); /* * Set the pageblock if the isolated page is at least half of a @@ -2662,8 +2898,8 @@ int __isolate_free_page(struct page *page, unsigned int order) * with others) */ if (migratetype_is_mergeable(mt)) - set_pageblock_migratetype(page, - MIGRATE_MOVABLE); + move_freepages_block(zone, page, mt, + MIGRATE_MOVABLE); } } @@ -2727,19 +2963,26 @@ struct page *rmqueue_buddy(struct zone *preferred_zone, struct zone *zone, do { page = NULL; - spin_lock_irqsave(&zone->lock, flags); + if (unlikely(alloc_flags & ALLOC_TRYLOCK)) { + if (!spin_trylock_irqsave(&zone->lock, flags)) + return NULL; + } else { + spin_lock_irqsave(&zone->lock, flags); + } if (alloc_flags & ALLOC_HIGHATOMIC) page = __rmqueue_smallest(zone, order, MIGRATE_HIGHATOMIC); if (!page) { - page = __rmqueue(zone, order, migratetype, alloc_flags); + enum rmqueue_mode rmqm = RMQUEUE_NORMAL; + + page = __rmqueue(zone, order, migratetype, alloc_flags, &rmqm); /* - * If the allocation fails, allow OOM handling access - * to HIGHATOMIC reserves as failing now is worse than - * failing a high-order atomic allocation in the - * future. + * If the allocation fails, allow OOM handling and + * order-0 (atomic) allocs access to HIGHATOMIC + * reserves as failing now is worse than failing a + * high-order atomic allocation in the future. */ - if (!page && (alloc_flags & ALLOC_OOM)) + if (!page && (alloc_flags & (ALLOC_OOM|ALLOC_NON_BLOCK))) page = __rmqueue_smallest(zone, order, MIGRATE_HIGHATOMIC); if (!page) { @@ -2747,8 +2990,6 @@ struct page *rmqueue_buddy(struct zone *preferred_zone, struct zone *zone, return NULL; } } - __mod_zone_freepage_state(zone, -(1 << order), - get_pcppage_migratetype(page)); spin_unlock_irqrestore(&zone->lock, flags); } while (check_new_pages(page, order)); @@ -2895,12 +3136,6 @@ struct page *rmqueue(struct zone *preferred_zone, { struct page *page; - /* - * We most definitely don't want callers attempting to - * allocate greater than order-1 page units with __GFP_NOFAIL. - */ - WARN_ON_ONCE((gfp_flags & __GFP_NOFAIL) && (order > 1)); - if (likely(pcp_allowed_order(order))) { page = rmqueue_pcplist(preferred_zone, zone, order, migratetype, alloc_flags); @@ -2923,11 +3158,141 @@ out: return page; } -noinline bool should_fail_alloc_page(gfp_t gfp_mask, unsigned int order) +/* + * Reserve the pageblock(s) surrounding an allocation request for + * exclusive use of high-order atomic allocations if there are no + * empty page blocks that contain a page with a suitable order + */ +static void reserve_highatomic_pageblock(struct page *page, int order, + struct zone *zone) { - return __should_fail_alloc_page(gfp_mask, order); + int mt; + unsigned long max_managed, flags; + + /* + * The number reserved as: minimum is 1 pageblock, maximum is + * roughly 1% of a zone. But if 1% of a zone falls below a + * pageblock size, then don't reserve any pageblocks. + * Check is race-prone but harmless. + */ + if ((zone_managed_pages(zone) / 100) < pageblock_nr_pages) + return; + max_managed = ALIGN((zone_managed_pages(zone) / 100), pageblock_nr_pages); + if (zone->nr_reserved_highatomic >= max_managed) + return; + + spin_lock_irqsave(&zone->lock, flags); + + /* Recheck the nr_reserved_highatomic limit under the lock */ + if (zone->nr_reserved_highatomic >= max_managed) + goto out_unlock; + + /* Yoink! */ + mt = get_pageblock_migratetype(page); + /* Only reserve normal pageblocks (i.e., they can merge with others) */ + if (!migratetype_is_mergeable(mt)) + goto out_unlock; + + if (order < pageblock_order) { + if (move_freepages_block(zone, page, mt, MIGRATE_HIGHATOMIC) == -1) + goto out_unlock; + zone->nr_reserved_highatomic += pageblock_nr_pages; + } else { + change_pageblock_range(page, order, MIGRATE_HIGHATOMIC); + zone->nr_reserved_highatomic += 1 << order; + } + +out_unlock: + spin_unlock_irqrestore(&zone->lock, flags); +} + +/* + * Used when an allocation is about to fail under memory pressure. This + * potentially hurts the reliability of high-order allocations when under + * intense memory pressure but failed atomic allocations should be easier + * to recover from than an OOM. + * + * If @force is true, try to unreserve pageblocks even though highatomic + * pageblock is exhausted. + */ +static bool unreserve_highatomic_pageblock(const struct alloc_context *ac, + bool force) +{ + struct zonelist *zonelist = ac->zonelist; + unsigned long flags; + struct zoneref *z; + struct zone *zone; + struct page *page; + int order; + int ret; + + for_each_zone_zonelist_nodemask(zone, z, zonelist, ac->highest_zoneidx, + ac->nodemask) { + /* + * Preserve at least one pageblock unless memory pressure + * is really high. + */ + if (!force && zone->nr_reserved_highatomic <= + pageblock_nr_pages) + continue; + + spin_lock_irqsave(&zone->lock, flags); + for (order = 0; order < NR_PAGE_ORDERS; order++) { + struct free_area *area = &(zone->free_area[order]); + unsigned long size; + + page = get_page_from_free_area(area, MIGRATE_HIGHATOMIC); + if (!page) + continue; + + size = max(pageblock_nr_pages, 1UL << order); + /* + * It should never happen but changes to + * locking could inadvertently allow a per-cpu + * drain to add pages to MIGRATE_HIGHATOMIC + * while unreserving so be safe and watch for + * underflows. + */ + if (WARN_ON_ONCE(size > zone->nr_reserved_highatomic)) + size = zone->nr_reserved_highatomic; + zone->nr_reserved_highatomic -= size; + + /* + * Convert to ac->migratetype and avoid the normal + * pageblock stealing heuristics. Minimally, the caller + * is doing the work and needs the pages. More + * importantly, if the block was always converted to + * MIGRATE_UNMOVABLE or another type then the number + * of pageblocks that cannot be completely freed + * may increase. + */ + if (order < pageblock_order) + ret = move_freepages_block(zone, page, + MIGRATE_HIGHATOMIC, + ac->migratetype); + else { + move_to_free_list(page, zone, order, + MIGRATE_HIGHATOMIC, + ac->migratetype); + change_pageblock_range(page, order, + ac->migratetype); + ret = 1; + } + /* + * Reserving the block(s) already succeeded, + * so this should not fail on zone boundaries. + */ + WARN_ON_ONCE(ret == -1); + if (ret > 0) { + spin_unlock_irqrestore(&zone->lock, flags); + return ret; + } + } + spin_unlock_irqrestore(&zone->lock, flags); + } + + return false; } -ALLOW_ERROR_INJECTION(should_fail_alloc_page, TRUE); static inline long __zone_watermark_unusable_free(struct zone *z, unsigned int order, unsigned int alloc_flags) @@ -2936,20 +3301,16 @@ static inline long __zone_watermark_unusable_free(struct zone *z, /* * If the caller does not have rights to reserves below the min - * watermark then subtract the high-atomic reserves. This will - * over-estimate the size of the atomic reserve but it avoids a search. + * watermark then subtract the free pages reserved for highatomic. */ if (likely(!(alloc_flags & ALLOC_RESERVES))) - unusable_free += z->nr_reserved_highatomic; + unusable_free += READ_ONCE(z->nr_free_highatomic); #ifdef CONFIG_CMA /* If allocation can't use CMA areas don't use free CMA pages */ if (!(alloc_flags & ALLOC_CMA)) unusable_free += zone_page_state(z, NR_FREE_CMA_PAGES); #endif -#ifdef CONFIG_UNACCEPTED_MEMORY - unusable_free += zone_page_state(z, NR_UNACCEPTED); -#endif return unusable_free; } @@ -3090,18 +3451,6 @@ static inline bool zone_watermark_fast(struct zone *z, unsigned int order, return false; } -bool zone_watermark_ok_safe(struct zone *z, unsigned int order, - unsigned long mark, int highest_zoneidx) -{ - long free_pages = zone_page_state(z, NR_FREE_PAGES); - - if (z->percpu_drift_mark && free_pages < z->percpu_drift_mark) - free_pages = zone_page_state_snapshot(z, NR_FREE_PAGES); - - return __zone_watermark_ok(z, order, mark, highest_zoneidx, 0, - free_pages); -} - #ifdef CONFIG_NUMA int __read_mostly node_reclaim_distance = RECLAIM_DISTANCE; @@ -3136,6 +3485,11 @@ alloc_flags_nofragment(struct zone *zone, gfp_t gfp_mask) */ alloc_flags = (__force int) (gfp_mask & __GFP_KSWAPD_RECLAIM); + if (defrag_mode) { + alloc_flags |= ALLOC_NOFRAGMENT; + return alloc_flags; + } + #ifdef CONFIG_ZONE_DMA32 if (!zone) return alloc_flags; @@ -3185,7 +3539,7 @@ get_page_from_freelist(gfp_t gfp_mask, unsigned int order, int alloc_flags, retry: /* * Scan zonelist, looking for a zone with enough free. - * See also cpuset_node_allowed() comment in kernel/cgroup/cpuset.c. + * See also cpuset_current_node_allowed() comment in kernel/cgroup/cpuset.c. */ no_fallback = alloc_flags & ALLOC_NOFRAGMENT; z = ac->preferred_zoneref; @@ -3227,8 +3581,8 @@ retry: continue; } - if (no_fallback && nr_online_nodes > 1 && - zone != ac->preferred_zoneref->zone) { + if (no_fallback && !defrag_mode && nr_online_nodes > 1 && + zone != zonelist_zone(ac->preferred_zoneref)) { int local_nid; /* @@ -3236,13 +3590,15 @@ retry: * fragmenting fallbacks. Locality is more important * than fragmentation avoidance. */ - local_nid = zone_to_nid(ac->preferred_zoneref->zone); + local_nid = zonelist_node_idx(ac->preferred_zoneref); if (zone_to_nid(zone) != local_nid) { alloc_flags &= ~ALLOC_NOFRAGMENT; goto retry; } } + cond_accept_memory(zone, order, alloc_flags); + /* * Detect whether the number of free pages is below high * watermark. If so, we will decrease pcp->high and free @@ -3268,12 +3624,9 @@ check_alloc_wmark: gfp_mask)) { int ret; - if (has_unaccepted_memory()) { - if (try_to_accept_memory(zone, order)) - goto try_this_zone; - } + if (cond_accept_memory(zone, order, alloc_flags)) + goto try_this_zone; -#ifdef CONFIG_DEFERRED_STRUCT_PAGE_INIT /* * Watermark failed for this zone, but see if we can * grow this zone if it contains deferred pages. @@ -3282,14 +3635,13 @@ check_alloc_wmark: if (_deferred_grow_zone(zone, order)) goto try_this_zone; } -#endif /* Checked here to keep the fast path fast */ BUILD_BUG_ON(ALLOC_NO_WATERMARKS < NR_WMARK); if (alloc_flags & ALLOC_NO_WATERMARKS) goto try_this_zone; if (!node_reclaim_enabled() || - !zone_allows_reclaim(ac->preferred_zoneref->zone, zone)) + !zone_allows_reclaim(zonelist_zone(ac->preferred_zoneref), zone)) continue; ret = node_reclaim(zone->zone_pgdat, gfp_mask, order); @@ -3311,7 +3663,7 @@ check_alloc_wmark: } try_this_zone: - page = rmqueue(ac->preferred_zoneref->zone, zone, order, + page = rmqueue(zonelist_zone(ac->preferred_zoneref), zone, order, gfp_mask, alloc_flags, ac->migratetype); if (page) { prep_new_page(page, order, gfp_mask, alloc_flags); @@ -3321,22 +3673,18 @@ try_this_zone: * if the pageblock should be reserved for the future */ if (unlikely(alloc_flags & ALLOC_HIGHATOMIC)) - reserve_highatomic_pageblock(page, zone); + reserve_highatomic_pageblock(page, order, zone); return page; } else { - if (has_unaccepted_memory()) { - if (try_to_accept_memory(zone, order)) - goto try_this_zone; - } + if (cond_accept_memory(zone, order, alloc_flags)) + goto try_this_zone; -#ifdef CONFIG_DEFERRED_STRUCT_PAGE_INIT /* Try again if zone has deferred pages */ if (deferred_pages_enabled()) { if (_deferred_grow_zone(zone, order)) goto try_this_zone; } -#endif } } @@ -3344,7 +3692,7 @@ try_this_zone: * It's possible on a UMA machine to get through all zones that are * fragmented. If avoiding fragmentation, reset and try again. */ - if (no_fallback) { + if (no_fallback && !defrag_mode) { alloc_flags &= ~ALLOC_NOFRAGMENT; goto retry; } @@ -3412,7 +3760,6 @@ __alloc_pages_cpuset_fallback(gfp_t gfp_mask, unsigned int order, if (!page) page = get_page_from_freelist(gfp_mask, order, alloc_flags, ac); - return page; } @@ -3824,15 +4171,21 @@ static void wake_all_kswapds(unsigned int order, gfp_t gfp_mask, struct zone *zone; pg_data_t *last_pgdat = NULL; enum zone_type highest_zoneidx = ac->highest_zoneidx; + unsigned int reclaim_order; + + if (defrag_mode) + reclaim_order = max(order, pageblock_order); + else + reclaim_order = order; for_each_zone_zonelist_nodemask(zone, z, ac->zonelist, highest_zoneidx, ac->nodemask) { if (!managed_zone(zone)) continue; - if (last_pgdat != zone->zone_pgdat) { - wakeup_kswapd(zone, gfp_mask, order, highest_zoneidx); - last_pgdat = zone->zone_pgdat; - } + if (last_pgdat == zone->zone_pgdat) + continue; + wakeup_kswapd(zone, gfp_mask, reclaim_order, highest_zoneidx); + last_pgdat = zone->zone_pgdat; } } @@ -3873,15 +4226,18 @@ gfp_to_alloc_flags(gfp_t gfp_mask, unsigned int order) /* * Ignore cpuset mems for non-blocking __GFP_HIGH (probably * GFP_ATOMIC) rather than fail, see the comment for - * cpuset_node_allowed(). + * cpuset_current_node_allowed(). */ if (alloc_flags & ALLOC_MIN_RESERVE) alloc_flags &= ~ALLOC_CPUSET; - } else if (unlikely(rt_task(current)) && in_task()) + } else if (unlikely(rt_or_dl_task(current)) && in_task()) alloc_flags |= ALLOC_MIN_RESERVE; alloc_flags = gfp_to_alloc_flags_cma(gfp_mask, alloc_flags); + if (defrag_mode) + alloc_flags |= ALLOC_NOFRAGMENT; + return alloc_flags; } @@ -3973,6 +4329,11 @@ should_reclaim_retry(gfp_t gfp_mask, unsigned order, unsigned long min_wmark = min_wmark_pages(zone); bool wmark; + if (cpusets_enabled() && + (alloc_flags & ALLOC_CPUSET) && + !__cpuset_zone_allowed(zone, gfp_mask)) + continue; + available = reclaimable = zone_reclaimable_pages(zone); available += zone_page_state_snapshot(zone, NR_FREE_PAGES); @@ -4048,6 +4409,7 @@ __alloc_pages_slowpath(gfp_t gfp_mask, unsigned int order, { bool can_direct_reclaim = gfp_mask & __GFP_DIRECT_RECLAIM; bool can_compact = gfp_compaction_allowed(gfp_mask); + bool nofail = gfp_mask & __GFP_NOFAIL; const bool costly_order = order > PAGE_ALLOC_COSTLY_ORDER; struct page *page = NULL; unsigned int alloc_flags; @@ -4060,9 +4422,29 @@ __alloc_pages_slowpath(gfp_t gfp_mask, unsigned int order, unsigned int zonelist_iter_cookie; int reserve_flags; + if (unlikely(nofail)) { + /* + * We most definitely don't want callers attempting to + * allocate greater than order-1 page units with __GFP_NOFAIL. + */ + WARN_ON_ONCE(order > 1); + /* + * Also we don't support __GFP_NOFAIL without __GFP_DIRECT_RECLAIM, + * otherwise, we may result in lockup. + */ + WARN_ON_ONCE(!can_direct_reclaim); + /* + * PF_MEMALLOC request from this context is rather bizarre + * because we cannot reclaim anything and only can loop waiting + * for somebody to do a work for us. + */ + WARN_ON_ONCE(current->flags & PF_MEMALLOC); + } + restart: compaction_retries = 0; no_progress_loops = 0; + compact_result = COMPACT_SKIPPED; compact_priority = DEF_COMPACT_PRIORITY; cpuset_mems_cookie = read_mems_allowed_begin(); zonelist_iter_cookie = zonelist_iter_begin(); @@ -4082,7 +4464,7 @@ restart: */ ac->preferred_zoneref = first_zones_zonelist(ac->zonelist, ac->highest_zoneidx, ac->nodemask); - if (!ac->preferred_zoneref->zone) + if (!zonelist_zone(ac->preferred_zoneref)) goto nopage; /* @@ -4094,7 +4476,7 @@ restart: struct zoneref *z = first_zones_zonelist(ac->zonelist, ac->highest_zoneidx, &cpuset_current_mems_allowed); - if (!z->zone) + if (!zonelist_zone(z)) goto nopage; } @@ -4165,6 +4547,14 @@ restart: } retry: + /* + * Deal with possible cpuset update races or zonelist updates to avoid + * infinite retries. + */ + if (check_retry_cpuset(cpuset_mems_cookie, ac) || + check_retry_zonelist(zonelist_iter_cookie)) + goto restart; + /* Ensure kswapd doesn't accidentally go to sleep as long as we loop */ if (alloc_flags & ALLOC_KSWAPD) wake_all_kswapds(order, gfp_mask, ac); @@ -4238,6 +4628,11 @@ retry: &compaction_retries)) goto retry; + /* Reclaim/compaction failed to prevent the fallback */ + if (defrag_mode && (alloc_flags & ALLOC_NOFRAGMENT)) { + alloc_flags &= ~ALLOC_NOFRAGMENT; + goto retry; + } /* * Deal with possible cpuset update races or zonelist updates to avoid @@ -4277,30 +4672,16 @@ nopage: * Make sure that __GFP_NOFAIL request doesn't leak out and make sure * we always retry */ - if (gfp_mask & __GFP_NOFAIL) { + if (unlikely(nofail)) { /* - * All existing users of the __GFP_NOFAIL are blockable, so warn - * of any new users that actually require GFP_NOWAIT + * Lacking direct_reclaim we can't do anything to reclaim memory, + * we disregard these unreasonable nofail requests and still + * return NULL */ - if (WARN_ON_ONCE_GFP(!can_direct_reclaim, gfp_mask)) + if (!can_direct_reclaim) goto fail; /* - * PF_MEMALLOC request from this context is rather bizarre - * because we cannot reclaim anything and only can loop waiting - * for somebody to do a work for us - */ - WARN_ON_ONCE_GFP(current->flags & PF_MEMALLOC, gfp_mask); - - /* - * non failing costly orders are a hard requirement which we - * are not prepared for much so let's warn about these users - * so that we can identify them and convert them to something - * else. - */ - WARN_ON_ONCE_GFP(costly_order, gfp_mask); - - /* * Help non-failing allocations by giving some access to memory * reserves normally used for high priority non-blocking * allocations but do not use ALLOC_NO_WATERMARKS because this @@ -4345,7 +4726,12 @@ static inline bool prepare_alloc_pages(gfp_t gfp_mask, unsigned int order, might_alloc(gfp_mask); - if (should_fail_alloc_page(gfp_mask, order)) + /* + * Don't invoke should_fail logic, since it may call + * get_random_u32() and printk() which need to spin_lock. + */ + if (!(*alloc_flags & ALLOC_TRYLOCK) && + should_fail_alloc_page(gfp_mask, order)) return false; *alloc_flags = gfp_to_alloc_flags_cma(gfp_mask, *alloc_flags); @@ -4365,28 +4751,23 @@ static inline bool prepare_alloc_pages(gfp_t gfp_mask, unsigned int order, } /* - * __alloc_pages_bulk - Allocate a number of order-0 pages to a list or array + * __alloc_pages_bulk - Allocate a number of order-0 pages to an array * @gfp: GFP flags for the allocation * @preferred_nid: The preferred NUMA node ID to allocate from * @nodemask: Set of nodes to allocate from, may be NULL - * @nr_pages: The number of pages desired on the list or array - * @page_list: Optional list to store the allocated pages - * @page_array: Optional array to store the pages + * @nr_pages: The number of pages desired in the array + * @page_array: Array to store the pages * * This is a batched version of the page allocator that attempts to - * allocate nr_pages quickly. Pages are added to page_list if page_list - * is not NULL, otherwise it is assumed that the page_array is valid. + * allocate nr_pages quickly. Pages are added to the page_array. * - * For lists, nr_pages is the number of pages that should be allocated. - * - * For arrays, only NULL elements are populated with pages and nr_pages + * Note that only NULL elements are populated with pages and nr_pages * is the maximum number of pages that will be stored in the array. * - * Returns the number of pages on the list or array. + * Returns the number of pages in the array. */ -unsigned long __alloc_pages_bulk(gfp_t gfp, int preferred_nid, +unsigned long alloc_pages_bulk_noprof(gfp_t gfp, int preferred_nid, nodemask_t *nodemask, int nr_pages, - struct list_head *page_list, struct page **page_array) { struct page *page; @@ -4404,7 +4785,7 @@ unsigned long __alloc_pages_bulk(gfp_t gfp, int preferred_nid, * Skip populated array elements to determine if any pages need * to be allocated before disabling IRQs. */ - while (page_array && nr_populated < nr_pages && page_array[nr_populated]) + while (nr_populated < nr_pages && page_array[nr_populated]) nr_populated++; /* No pages requested? */ @@ -4412,7 +4793,7 @@ unsigned long __alloc_pages_bulk(gfp_t gfp, int preferred_nid, goto out; /* Already populated array? */ - if (unlikely(page_array && nr_pages - nr_populated == 0)) + if (unlikely(nr_pages - nr_populated == 0)) goto out; /* Bulk allocator does not support memcg accounting. */ @@ -4443,7 +4824,8 @@ unsigned long __alloc_pages_bulk(gfp_t gfp, int preferred_nid, gfp = alloc_gfp; /* Find an allowed local zone that meets the low watermark. */ - for_each_zone_zonelist_nodemask(zone, z, ac.zonelist, ac.highest_zoneidx, ac.nodemask) { + z = ac.preferred_zoneref; + for_next_zone_zonelist_nodemask(zone, z, ac.highest_zoneidx, ac.nodemask) { unsigned long mark; if (cpusets_enabled() && (alloc_flags & ALLOC_CPUSET) && @@ -4451,17 +4833,28 @@ unsigned long __alloc_pages_bulk(gfp_t gfp, int preferred_nid, continue; } - if (nr_online_nodes > 1 && zone != ac.preferred_zoneref->zone && - zone_to_nid(zone) != zone_to_nid(ac.preferred_zoneref->zone)) { + if (nr_online_nodes > 1 && zone != zonelist_zone(ac.preferred_zoneref) && + zone_to_nid(zone) != zonelist_node_idx(ac.preferred_zoneref)) { goto failed; } + cond_accept_memory(zone, 0, alloc_flags); +retry_this_zone: mark = wmark_pages(zone, alloc_flags & ALLOC_WMARK_MASK) + nr_pages; if (zone_watermark_fast(zone, 0, mark, zonelist_zone_idx(ac.preferred_zoneref), alloc_flags, gfp)) { break; } + + if (cond_accept_memory(zone, 0, alloc_flags)) + goto retry_this_zone; + + /* Try again if zone has deferred pages */ + if (deferred_pages_enabled()) { + if (_deferred_grow_zone(zone, 0)) + goto retry_this_zone; + } } /* @@ -4482,7 +4875,7 @@ unsigned long __alloc_pages_bulk(gfp_t gfp, int preferred_nid, while (nr_populated < nr_pages) { /* Skip existing pages */ - if (page_array && page_array[nr_populated]) { + if (page_array[nr_populated]) { nr_populated++; continue; } @@ -4500,18 +4893,15 @@ unsigned long __alloc_pages_bulk(gfp_t gfp, int preferred_nid, nr_account++; prep_new_page(page, 0, gfp, 0); - if (page_list) - list_add(&page->lru, page_list); - else - page_array[nr_populated] = page; - nr_populated++; + set_page_refcounted(page); + page_array[nr_populated++] = page; } pcp_spin_unlock(pcp); pcp_trylock_finish(UP_flags); __count_zid_vm_events(PGALLOC, zone_idx(zone), nr_account); - zone_statistics(ac.preferred_zoneref->zone, zone, nr_account); + zone_statistics(zonelist_zone(ac.preferred_zoneref), zone, nr_account); out: return nr_populated; @@ -4520,24 +4910,18 @@ failed_irq: pcp_trylock_finish(UP_flags); failed: - page = __alloc_pages(gfp, 0, preferred_nid, nodemask); - if (page) { - if (page_list) - list_add(&page->lru, page_list); - else - page_array[nr_populated] = page; - nr_populated++; - } - + page = __alloc_pages_noprof(gfp, 0, preferred_nid, nodemask); + if (page) + page_array[nr_populated++] = page; goto out; } -EXPORT_SYMBOL_GPL(__alloc_pages_bulk); +EXPORT_SYMBOL_GPL(alloc_pages_bulk_noprof); /* * This is the 'heart' of the zoned buddy allocator. */ -struct page *__alloc_pages(gfp_t gfp, unsigned int order, int preferred_nid, - nodemask_t *nodemask) +struct page *__alloc_frozen_pages_noprof(gfp_t gfp, unsigned int order, + int preferred_nid, nodemask_t *nodemask) { struct page *page; unsigned int alloc_flags = ALLOC_WMARK_LOW; @@ -4569,7 +4953,7 @@ struct page *__alloc_pages(gfp_t gfp, unsigned int order, int preferred_nid, * Forbid the first pass from falling back to types that fragment * memory until all local zones are considered. */ - alloc_flags |= alloc_flags_nofragment(ac.preferred_zoneref->zone, gfp); + alloc_flags |= alloc_flags_nofragment(zonelist_zone(ac.preferred_zoneref), gfp); /* First allocation attempt */ page = get_page_from_freelist(alloc_gfp, order, alloc_flags, &ac); @@ -4590,7 +4974,7 @@ struct page *__alloc_pages(gfp_t gfp, unsigned int order, int preferred_nid, out: if (memcg_kmem_online() && (gfp & __GFP_ACCOUNT) && page && unlikely(__memcg_kmem_charge_page(page, gfp, order) != 0)) { - __free_pages(page, order); + free_frozen_pages(page, order); page = NULL; } @@ -4599,43 +4983,56 @@ out: return page; } -EXPORT_SYMBOL(__alloc_pages); +EXPORT_SYMBOL(__alloc_frozen_pages_noprof); + +struct page *__alloc_pages_noprof(gfp_t gfp, unsigned int order, + int preferred_nid, nodemask_t *nodemask) +{ + struct page *page; + + page = __alloc_frozen_pages_noprof(gfp, order, preferred_nid, nodemask); + if (page) + set_page_refcounted(page); + return page; +} +EXPORT_SYMBOL(__alloc_pages_noprof); -struct folio *__folio_alloc(gfp_t gfp, unsigned int order, int preferred_nid, +struct folio *__folio_alloc_noprof(gfp_t gfp, unsigned int order, int preferred_nid, nodemask_t *nodemask) { - struct page *page = __alloc_pages(gfp | __GFP_COMP, order, + struct page *page = __alloc_pages_noprof(gfp | __GFP_COMP, order, preferred_nid, nodemask); return page_rmappable_folio(page); } -EXPORT_SYMBOL(__folio_alloc); +EXPORT_SYMBOL(__folio_alloc_noprof); /* * Common helper functions. Never use with __GFP_HIGHMEM because the returned * address cannot represent highmem pages. Use alloc_pages and then kmap if * you need to access high mem. */ -unsigned long __get_free_pages(gfp_t gfp_mask, unsigned int order) +unsigned long get_free_pages_noprof(gfp_t gfp_mask, unsigned int order) { struct page *page; - page = alloc_pages(gfp_mask & ~__GFP_HIGHMEM, order); + page = alloc_pages_noprof(gfp_mask & ~__GFP_HIGHMEM, order); if (!page) return 0; return (unsigned long) page_address(page); } -EXPORT_SYMBOL(__get_free_pages); +EXPORT_SYMBOL(get_free_pages_noprof); -unsigned long get_zeroed_page(gfp_t gfp_mask) +unsigned long get_zeroed_page_noprof(gfp_t gfp_mask) { - return __get_free_page(gfp_mask | __GFP_ZERO); + return get_free_pages_noprof(gfp_mask | __GFP_ZERO, 0); } -EXPORT_SYMBOL(get_zeroed_page); +EXPORT_SYMBOL(get_zeroed_page_noprof); /** - * __free_pages - Free pages allocated with alloc_pages(). + * ___free_pages - Free pages allocated with alloc_pages(). * @page: The page pointer returned from alloc_pages(). * @order: The order of the allocation. + * @fpi_flags: Free Page Internal flags. * * This function can free multi-page allocations that are not compound * pages. It does not check that the @order passed in matches that of @@ -4652,164 +5049,47 @@ EXPORT_SYMBOL(get_zeroed_page); * Context: May be called in interrupt context or while holding a normal * spinlock, but not in NMI context or while holding a raw spinlock. */ -void __free_pages(struct page *page, unsigned int order) +static void ___free_pages(struct page *page, unsigned int order, + fpi_t fpi_flags) { /* get PageHead before we drop reference */ int head = PageHead(page); + /* get alloc tag in case the page is released by others */ + struct alloc_tag *tag = pgalloc_tag_get(page); if (put_page_testzero(page)) - free_the_page(page, order); - else if (!head) + __free_frozen_pages(page, order, fpi_flags); + else if (!head) { + pgalloc_tag_sub_pages(tag, (1 << order) - 1); while (order-- > 0) - free_the_page(page + (1 << order), order); + __free_frozen_pages(page + (1 << order), order, + fpi_flags); + } } -EXPORT_SYMBOL(__free_pages); - -void free_pages(unsigned long addr, unsigned int order) +void __free_pages(struct page *page, unsigned int order) { - if (addr != 0) { - VM_BUG_ON(!virt_addr_valid((void *)addr)); - __free_pages(virt_to_page((void *)addr), order); - } + ___free_pages(page, order, FPI_NONE); } - -EXPORT_SYMBOL(free_pages); +EXPORT_SYMBOL(__free_pages); /* - * Page Fragment: - * An arbitrary-length arbitrary-offset area of memory which resides - * within a 0 or higher order page. Multiple fragments within that page - * are individually refcounted, in the page's reference counter. - * - * The page_frag functions below provide a simple allocation framework for - * page fragments. This is used by the network stack and network device - * drivers to provide a backing region of memory for use as either an - * sk_buff->head, or to be used in the "frags" portion of skb_shared_info. + * Can be called while holding raw_spin_lock or from IRQ and NMI for any + * page type (not only those that came from alloc_pages_nolock) */ -static struct page *__page_frag_cache_refill(struct page_frag_cache *nc, - gfp_t gfp_mask) -{ - struct page *page = NULL; - gfp_t gfp = gfp_mask; - -#if (PAGE_SIZE < PAGE_FRAG_CACHE_MAX_SIZE) - gfp_mask = (gfp_mask & ~__GFP_DIRECT_RECLAIM) | __GFP_COMP | - __GFP_NOWARN | __GFP_NORETRY | __GFP_NOMEMALLOC; - page = alloc_pages_node(NUMA_NO_NODE, gfp_mask, - PAGE_FRAG_CACHE_MAX_ORDER); - nc->size = page ? PAGE_FRAG_CACHE_MAX_SIZE : PAGE_SIZE; -#endif - if (unlikely(!page)) - page = alloc_pages_node(NUMA_NO_NODE, gfp, 0); - - nc->va = page ? page_address(page) : NULL; - - return page; -} - -void page_frag_cache_drain(struct page_frag_cache *nc) -{ - if (!nc->va) - return; - - __page_frag_cache_drain(virt_to_head_page(nc->va), nc->pagecnt_bias); - nc->va = NULL; -} -EXPORT_SYMBOL(page_frag_cache_drain); - -void __page_frag_cache_drain(struct page *page, unsigned int count) +void free_pages_nolock(struct page *page, unsigned int order) { - VM_BUG_ON_PAGE(page_ref_count(page) == 0, page); - - if (page_ref_sub_and_test(page, count)) - free_the_page(page, compound_order(page)); + ___free_pages(page, order, FPI_TRYLOCK); } -EXPORT_SYMBOL(__page_frag_cache_drain); -void *__page_frag_alloc_align(struct page_frag_cache *nc, - unsigned int fragsz, gfp_t gfp_mask, - unsigned int align_mask) +void free_pages(unsigned long addr, unsigned int order) { - unsigned int size = PAGE_SIZE; - struct page *page; - int offset; - - if (unlikely(!nc->va)) { -refill: - page = __page_frag_cache_refill(nc, gfp_mask); - if (!page) - return NULL; - -#if (PAGE_SIZE < PAGE_FRAG_CACHE_MAX_SIZE) - /* if size can vary use size else just use PAGE_SIZE */ - size = nc->size; -#endif - /* Even if we own the page, we do not use atomic_set(). - * This would break get_page_unless_zero() users. - */ - page_ref_add(page, PAGE_FRAG_CACHE_MAX_SIZE); - - /* reset page count bias and offset to start of new frag */ - nc->pfmemalloc = page_is_pfmemalloc(page); - nc->pagecnt_bias = PAGE_FRAG_CACHE_MAX_SIZE + 1; - nc->offset = size; - } - - offset = nc->offset - fragsz; - if (unlikely(offset < 0)) { - page = virt_to_page(nc->va); - - if (!page_ref_sub_and_test(page, nc->pagecnt_bias)) - goto refill; - - if (unlikely(nc->pfmemalloc)) { - free_the_page(page, compound_order(page)); - goto refill; - } - -#if (PAGE_SIZE < PAGE_FRAG_CACHE_MAX_SIZE) - /* if size can vary use size else just use PAGE_SIZE */ - size = nc->size; -#endif - /* OK, page count is 0, we can safely set it */ - set_page_count(page, PAGE_FRAG_CACHE_MAX_SIZE + 1); - - /* reset page count bias and offset to start of new frag */ - nc->pagecnt_bias = PAGE_FRAG_CACHE_MAX_SIZE + 1; - offset = size - fragsz; - if (unlikely(offset < 0)) { - /* - * The caller is trying to allocate a fragment - * with fragsz > PAGE_SIZE but the cache isn't big - * enough to satisfy the request, this may - * happen in low memory conditions. - * We don't release the cache page because - * it could make memory pressure worse - * so we simply return NULL here. - */ - return NULL; - } + if (addr != 0) { + VM_BUG_ON(!virt_addr_valid((void *)addr)); + __free_pages(virt_to_page((void *)addr), order); } - - nc->pagecnt_bias--; - offset &= align_mask; - nc->offset = offset; - - return nc->va + offset; } -EXPORT_SYMBOL(__page_frag_alloc_align); - -/* - * Frees a page fragment allocated out of either a compound or order 0 page. - */ -void page_frag_free(void *addr) -{ - struct page *page = virt_to_head_page(addr); - if (unlikely(put_page_testzero(page))) - free_the_page(page, compound_order(page)); -} -EXPORT_SYMBOL(page_frag_free); +EXPORT_SYMBOL(free_pages); static void *make_alloc_exact(unsigned long addr, unsigned int order, size_t size) @@ -4820,7 +5100,8 @@ static void *make_alloc_exact(unsigned long addr, unsigned int order, struct page *last = page + nr; split_page_owner(page, order, 0); - split_page_memcg(page, order, 0); + pgalloc_tag_split(page_folio(page), order, 0); + split_page_memcg(page, order); while (page < --last) set_page_refcounted(last); @@ -4846,7 +5127,7 @@ static void *make_alloc_exact(unsigned long addr, unsigned int order, * * Return: pointer to the allocated area or %NULL in case of error. */ -void *alloc_pages_exact(size_t size, gfp_t gfp_mask) +void *alloc_pages_exact_noprof(size_t size, gfp_t gfp_mask) { unsigned int order = get_order(size); unsigned long addr; @@ -4854,10 +5135,10 @@ void *alloc_pages_exact(size_t size, gfp_t gfp_mask) if (WARN_ON_ONCE(gfp_mask & (__GFP_COMP | __GFP_HIGHMEM))) gfp_mask &= ~(__GFP_COMP | __GFP_HIGHMEM); - addr = __get_free_pages(gfp_mask, order); + addr = get_free_pages_noprof(gfp_mask, order); return make_alloc_exact(addr, order, size); } -EXPORT_SYMBOL(alloc_pages_exact); +EXPORT_SYMBOL(alloc_pages_exact_noprof); /** * alloc_pages_exact_nid - allocate an exact number of physically-contiguous @@ -4871,7 +5152,7 @@ EXPORT_SYMBOL(alloc_pages_exact); * * Return: pointer to the allocated area or %NULL in case of error. */ -void * __meminit alloc_pages_exact_nid(int nid, size_t size, gfp_t gfp_mask) +void * __meminit alloc_pages_exact_nid_noprof(int nid, size_t size, gfp_t gfp_mask) { unsigned int order = get_order(size); struct page *p; @@ -4879,7 +5160,7 @@ void * __meminit alloc_pages_exact_nid(int nid, size_t size, gfp_t gfp_mask) if (WARN_ON_ONCE(gfp_mask & (__GFP_COMP | __GFP_HIGHMEM))) gfp_mask &= ~(__GFP_COMP | __GFP_HIGHMEM); - p = alloc_pages_node(nid, gfp_mask, order); + p = alloc_pages_node_noprof(nid, gfp_mask, order); if (!p) return NULL; return make_alloc_exact((unsigned long)page_address(p), order, size); @@ -5002,7 +5283,7 @@ static char numa_zonelist_order[] = "Node"; /* * sysctl handler for numa_zonelist_order */ -static int numa_zonelist_order_handler(struct ctl_table *table, int write, +static int numa_zonelist_order_handler(const struct ctl_table *table, int write, void *buffer, size_t *length, loff_t *ppos) { if (write) @@ -5101,7 +5382,7 @@ static void build_zonelists_in_node_order(pg_data_t *pgdat, int *node_order, } /* - * Build gfp_thisnode zonelists + * Build __GFP_THISNODE zonelists */ static void build_thisnode_zonelists(pg_data_t *pgdat) { @@ -5115,13 +5396,6 @@ static void build_thisnode_zonelists(pg_data_t *pgdat) zonerefs->zone_idx = 0; } -/* - * Build zonelists ordered by zone and nodes within zones. - * This results in conserving DMA zone[s] until all Normal memory is - * exhausted, but results in overflowing to remote node while memory - * may still exist in local DMA zone. - */ - static void build_zonelists(pg_data_t *pgdat) { static int node_order[MAX_NUMNODES]; @@ -5170,7 +5444,7 @@ int local_memory_node(int node) z = first_zones_zonelist(node_zonelist(node, GFP_KERNEL), gfp_zone(GFP_KERNEL), NULL); - return zone_to_nid(z->zone); + return zonelist_node_idx(z); } #endif @@ -5180,37 +5454,13 @@ static void setup_min_slab_ratio(void); static void build_zonelists(pg_data_t *pgdat) { - int node, local_node; struct zoneref *zonerefs; int nr_zones; - local_node = pgdat->node_id; - zonerefs = pgdat->node_zonelists[ZONELIST_FALLBACK]._zonerefs; nr_zones = build_zonerefs_node(pgdat, zonerefs); zonerefs += nr_zones; - /* - * Now we build the zonelist so that it contains the zones - * of all the other nodes. - * We don't want to pressure a particular node, so when - * building the zones for node N, we make sure that the - * zones coming right after the local ones are those from - * node N+1 (modulo N) - */ - for (node = local_node + 1; node < MAX_NUMNODES; node++) { - if (!node_online(node)) - continue; - nr_zones = build_zonerefs_node(NODE_DATA(node), zonerefs); - zonerefs += nr_zones; - } - for (node = 0; node < local_node; node++) { - if (!node_online(node)) - continue; - nr_zones = build_zonerefs_node(NODE_DATA(node), zonerefs); - zonerefs += nr_zones; - } - zonerefs->zone = NULL; zonerefs->zone_idx = 0; } @@ -5357,7 +5607,7 @@ void __ref build_all_zonelists(pg_data_t *pgdat) pr_info("Built %u zonelists, mobility grouping %s. Total pages: %ld\n", nr_online_nodes, - page_group_by_mobility_disabled ? "off" : "on", + str_off_on(page_group_by_mobility_disabled), vm_total_pages); #ifdef CONFIG_NUMA pr_info("Policy zone: %s\n", zone_names[policy_zone]); @@ -5670,14 +5920,13 @@ __meminit void zone_pcp_init(struct zone *zone) zone->present_pages, zone_batchsize(zone)); } +static void setup_per_zone_lowmem_reserve(void); + void adjust_managed_page_count(struct page *page, long count) { atomic_long_add(count, &page_zone(page)->managed_pages); totalram_pages_add(count); -#ifdef CONFIG_HIGHMEM - if (PageHighMem(page)) - totalhigh_pages_add(count); -#endif + setup_per_zone_lowmem_reserve(); } EXPORT_SYMBOL(adjust_managed_page_count); @@ -5717,6 +5966,16 @@ unsigned long free_reserved_area(void *start, void *end, int poison, const char return pages; } +void free_reserved_page(struct page *page) +{ + clear_page_tag_ref(page); + ClearPageReserved(page); + init_page_count(page); + __free_page(page); + adjust_managed_page_count(page, 1); +} +EXPORT_SYMBOL(free_reserved_page); + static int page_alloc_cpu_dead(unsigned int cpu) { struct zone *zone; @@ -5805,6 +6064,7 @@ static void calculate_totalreserve_pages(void) } } totalreserve_pages = reserve_pages; + trace_mm_calculate_totalreserve_pages(totalreserve_pages); } /* @@ -5834,6 +6094,8 @@ static void setup_per_zone_lowmem_reserve(void) zone->lowmem_reserve[j] = 0; else zone->lowmem_reserve[j] = managed_pages / ratio; + trace_mm_setup_per_zone_lowmem_reserve(zone, upper_zone, + zone->lowmem_reserve[j]); } } } @@ -5897,6 +6159,7 @@ static void __setup_per_zone_wmarks(void) zone->_watermark[WMARK_LOW] = min_wmark_pages(zone) + tmp; zone->_watermark[WMARK_HIGH] = low_wmark_pages(zone) + tmp; zone->_watermark[WMARK_PROMO] = high_wmark_pages(zone) + tmp; + trace_mm_setup_per_zone_wmarks(zone); spin_unlock_irqrestore(&zone->lock, flags); } @@ -5992,7 +6255,7 @@ postcore_initcall(init_per_zone_wmark_min) * that we can call two helper functions whenever min_free_kbytes * changes. */ -static int min_free_kbytes_sysctl_handler(struct ctl_table *table, int write, +static int min_free_kbytes_sysctl_handler(const struct ctl_table *table, int write, void *buffer, size_t *length, loff_t *ppos) { int rc; @@ -6008,7 +6271,7 @@ static int min_free_kbytes_sysctl_handler(struct ctl_table *table, int write, return 0; } -static int watermark_scale_factor_sysctl_handler(struct ctl_table *table, int write, +static int watermark_scale_factor_sysctl_handler(const struct ctl_table *table, int write, void *buffer, size_t *length, loff_t *ppos) { int rc; @@ -6038,7 +6301,7 @@ static void setup_min_unmapped_ratio(void) } -static int sysctl_min_unmapped_ratio_sysctl_handler(struct ctl_table *table, int write, +static int sysctl_min_unmapped_ratio_sysctl_handler(const struct ctl_table *table, int write, void *buffer, size_t *length, loff_t *ppos) { int rc; @@ -6065,7 +6328,7 @@ static void setup_min_slab_ratio(void) sysctl_min_slab_ratio) / 100; } -static int sysctl_min_slab_ratio_sysctl_handler(struct ctl_table *table, int write, +static int sysctl_min_slab_ratio_sysctl_handler(const struct ctl_table *table, int write, void *buffer, size_t *length, loff_t *ppos) { int rc; @@ -6089,7 +6352,7 @@ static int sysctl_min_slab_ratio_sysctl_handler(struct ctl_table *table, int wri * minimum watermarks. The lowmem reserve ratio can only make sense * if in function of the boot time zone sizes. */ -static int lowmem_reserve_ratio_sysctl_handler(struct ctl_table *table, +static int lowmem_reserve_ratio_sysctl_handler(const struct ctl_table *table, int write, void *buffer, size_t *length, loff_t *ppos) { int i; @@ -6110,7 +6373,7 @@ static int lowmem_reserve_ratio_sysctl_handler(struct ctl_table *table, * cpu. It is the fraction of total pages in each zone that a hot per cpu * pagelist can have before it gets flushed back to buddy allocator. */ -static int percpu_pagelist_high_fraction_sysctl_handler(struct ctl_table *table, +static int percpu_pagelist_high_fraction_sysctl_handler(const struct ctl_table *table, int write, void *buffer, size_t *length, loff_t *ppos) { struct zone *zone; @@ -6143,7 +6406,7 @@ out: return ret; } -static struct ctl_table page_alloc_sysctl_table[] = { +static const struct ctl_table page_alloc_sysctl_table[] = { { .procname = "min_free_kbytes", .data = &min_free_kbytes, @@ -6170,6 +6433,15 @@ static struct ctl_table page_alloc_sysctl_table[] = { .extra2 = SYSCTL_THREE_THOUSAND, }, { + .procname = "defrag_mode", + .data = &defrag_mode, + .maxlen = sizeof(defrag_mode), + .mode = 0644, + .proc_handler = proc_dointvec_minmax, + .extra1 = SYSCTL_ZERO, + .extra2 = SYSCTL_ONE, + }, + { .procname = "percpu_pagelist_high_fraction", .data = &percpu_pagelist_high_fraction, .maxlen = sizeof(percpu_pagelist_high_fraction), @@ -6211,7 +6483,6 @@ static struct ctl_table page_alloc_sysctl_table[] = { .extra2 = SYSCTL_ONE_HUNDRED, }, #endif - {} }; void __init page_alloc_sysctl_init(void) @@ -6239,9 +6510,8 @@ static void alloc_contig_dump_pages(struct list_head *page_list) * @migratetype: using migratetype to filter the type of migration in * trace_mm_alloc_contig_migrate_range_info. */ -int __alloc_contig_migrate_range(struct compact_control *cc, - unsigned long start, unsigned long end, - int migratetype) +static int __alloc_contig_migrate_range(struct compact_control *cc, + unsigned long start, unsigned long end, int migratetype) { /* This function is based on compact_zone() from compaction.c. */ unsigned int nr_reclaimed; @@ -6250,7 +6520,8 @@ int __alloc_contig_migrate_range(struct compact_control *cc, int ret = 0; struct migration_target_control mtc = { .nid = zone_to_nid(cc->zone), - .gfp_mask = GFP_USER | __GFP_MOVABLE | __GFP_RETRY_MAYFAIL, + .gfp_mask = cc->gfp_mask, + .reason = MR_CONTIG_RANGE, }; struct page *page; unsigned long total_mapped = 0; @@ -6283,8 +6554,12 @@ int __alloc_contig_migrate_range(struct compact_control *cc, if (trace_mm_alloc_contig_migrate_range_info_enabled()) { total_reclaimed += nr_reclaimed; - list_for_each_entry(page, &cc->migratepages, lru) - total_mapped += page_mapcount(page); + list_for_each_entry(page, &cc->migratepages, lru) { + struct folio *folio = page_folio(page); + + total_mapped += folio_mapped(folio) * + folio_nr_pages(folio); + } } ret = migrate_pages(&cc->migratepages, alloc_migration_target, @@ -6315,6 +6590,66 @@ int __alloc_contig_migrate_range(struct compact_control *cc, return (ret < 0) ? ret : 0; } +static void split_free_pages(struct list_head *list, gfp_t gfp_mask) +{ + int order; + + for (order = 0; order < NR_PAGE_ORDERS; order++) { + struct page *page, *next; + int nr_pages = 1 << order; + + list_for_each_entry_safe(page, next, &list[order], lru) { + int i; + + post_alloc_hook(page, order, gfp_mask); + set_page_refcounted(page); + if (!order) + continue; + + split_page(page, order); + + /* Add all subpages to the order-0 head, in sequence. */ + list_del(&page->lru); + for (i = 0; i < nr_pages; i++) + list_add_tail(&page[i].lru, &list[0]); + } + } +} + +static int __alloc_contig_verify_gfp_mask(gfp_t gfp_mask, gfp_t *gfp_cc_mask) +{ + const gfp_t reclaim_mask = __GFP_IO | __GFP_FS | __GFP_RECLAIM; + const gfp_t action_mask = __GFP_COMP | __GFP_RETRY_MAYFAIL | __GFP_NOWARN | + __GFP_ZERO | __GFP_ZEROTAGS | __GFP_SKIP_ZERO; + const gfp_t cc_action_mask = __GFP_RETRY_MAYFAIL | __GFP_NOWARN; + + /* + * We are given the range to allocate; node, mobility and placement + * hints are irrelevant at this point. We'll simply ignore them. + */ + gfp_mask &= ~(GFP_ZONEMASK | __GFP_RECLAIMABLE | __GFP_WRITE | + __GFP_HARDWALL | __GFP_THISNODE | __GFP_MOVABLE); + + /* + * We only support most reclaim flags (but not NOFAIL/NORETRY), and + * selected action flags. + */ + if (gfp_mask & ~(reclaim_mask | action_mask)) + return -EINVAL; + + /* + * Flags to control page compaction/migration/reclaim, to free up our + * page range. Migratable pages are movable, __GFP_MOVABLE is implied + * for them. + * + * Traditionally we always had __GFP_RETRY_MAYFAIL set, keep doing that + * to not degrade callers. + */ + *gfp_cc_mask = (gfp_mask & (reclaim_mask | cc_action_mask)) | + __GFP_MOVABLE | __GFP_RETRY_MAYFAIL; + return 0; +} + /** * alloc_contig_range() -- tries to allocate given range of pages * @start: start PFN to allocate @@ -6323,7 +6658,9 @@ int __alloc_contig_migrate_range(struct compact_control *cc, * #MIGRATE_MOVABLE or #MIGRATE_CMA). All pageblocks * in range must have the same migratetype and it must * be either of the two. - * @gfp_mask: GFP mask to use during compaction + * @gfp_mask: GFP mask. Node/zone/placement hints are ignored; only some + * action and reclaim modifiers are supported. Reclaim modifiers + * control allocation behavior during compaction/migration/reclaim. * * The PFN range does not have to be pageblock aligned. The PFN range must * belong to a single zone. @@ -6336,11 +6673,10 @@ int __alloc_contig_migrate_range(struct compact_control *cc, * pages which PFN is in [start, end) are allocated for the caller and * need to be freed with free_contig_range(). */ -int alloc_contig_range(unsigned long start, unsigned long end, +int alloc_contig_range_noprof(unsigned long start, unsigned long end, unsigned migratetype, gfp_t gfp_mask) { unsigned long outer_start, outer_end; - int order; int ret = 0; struct compact_control cc = { @@ -6350,11 +6686,14 @@ int alloc_contig_range(unsigned long start, unsigned long end, .mode = MIGRATE_SYNC, .ignore_skip_hint = true, .no_set_skip_hint = true, - .gfp_mask = current_gfp_context(gfp_mask), .alloc_contig = true, }; INIT_LIST_HEAD(&cc.migratepages); + gfp_mask = current_gfp_context(gfp_mask); + if (__alloc_contig_verify_gfp_mask(gfp_mask, (gfp_t *)&cc.gfp_mask)) + return -EINVAL; + /* * What we do here is we mark all pageblocks in range as * MIGRATE_ISOLATE. Because pageblock and max order pages may @@ -6376,7 +6715,7 @@ int alloc_contig_range(unsigned long start, unsigned long end, * put back to page allocator so that buddy can use them. */ - ret = start_isolate_page_range(start, end, migratetype, 0, gfp_mask); + ret = start_isolate_page_range(start, end, migratetype, 0); if (ret) goto done; @@ -6395,7 +6734,17 @@ int alloc_contig_range(unsigned long start, unsigned long end, ret = __alloc_contig_migrate_range(&cc, start, end, migratetype); if (ret && ret != -EBUSY) goto done; - ret = 0; + + /* + * When in-use hugetlb pages are migrated, they may simply be released + * back into the free hugepage pool instead of being returned to the + * buddy system. After the migration of in-use huge pages is completed, + * we will invoke replace_free_hugepage_folios() to ensure that these + * hugepages are properly released to the buddy system. + */ + ret = replace_free_hugepage_folios(start, end); + if (ret) + goto done; /* * Pages from [start, end) are within a pageblock_nr_pages @@ -6413,29 +6762,7 @@ int alloc_contig_range(unsigned long start, unsigned long end, * We don't have to hold zone->lock here because the pages are * isolated thus they won't get removed from buddy. */ - - order = 0; - outer_start = start; - while (!PageBuddy(pfn_to_page(outer_start))) { - if (++order > MAX_PAGE_ORDER) { - outer_start = start; - break; - } - outer_start &= ~0UL << order; - } - - if (outer_start != start) { - order = buddy_order(pfn_to_page(outer_start)); - - /* - * outer_start page could be small order buddy page and - * it doesn't include start page. Adjust outer_start - * in this case to report failed page properly - * on tracepoint in test_pages_isolated() - */ - if (outer_start + (1UL << order) <= start) - outer_start = start; - } + outer_start = find_large_buddy(start); /* Make sure the range is really isolated. */ if (test_pages_isolated(outer_start, end, 0)) { @@ -6450,25 +6777,39 @@ int alloc_contig_range(unsigned long start, unsigned long end, goto done; } - /* Free head and tail (if any) */ - if (start != outer_start) - free_contig_range(outer_start, start - outer_start); - if (end != outer_end) - free_contig_range(end, outer_end - end); + if (!(gfp_mask & __GFP_COMP)) { + split_free_pages(cc.freepages, gfp_mask); + /* Free head and tail (if any) */ + if (start != outer_start) + free_contig_range(outer_start, start - outer_start); + if (end != outer_end) + free_contig_range(end, outer_end - end); + } else if (start == outer_start && end == outer_end && is_power_of_2(end - start)) { + struct page *head = pfn_to_page(start); + int order = ilog2(end - start); + + check_new_pages(head, order); + prep_new_page(head, order, gfp_mask, 0); + set_page_refcounted(head); + } else { + ret = -EINVAL; + WARN(true, "PFN range: requested [%lu, %lu), allocated [%lu, %lu)\n", + start, end, outer_start, outer_end); + } done: undo_isolate_page_range(start, end, migratetype); return ret; } -EXPORT_SYMBOL(alloc_contig_range); +EXPORT_SYMBOL(alloc_contig_range_noprof); static int __alloc_contig_pages(unsigned long start_pfn, unsigned long nr_pages, gfp_t gfp_mask) { unsigned long end_pfn = start_pfn + nr_pages; - return alloc_contig_range(start_pfn, end_pfn, MIGRATE_MOVABLE, - gfp_mask); + return alloc_contig_range_noprof(start_pfn, end_pfn, MIGRATE_MOVABLE, + gfp_mask); } static bool pfn_range_valid_contig(struct zone *z, unsigned long start_pfn, @@ -6505,7 +6846,9 @@ static bool zone_spans_last_pfn(const struct zone *zone, /** * alloc_contig_pages() -- tries to find and allocate contiguous range of pages * @nr_pages: Number of contiguous pages to allocate - * @gfp_mask: GFP mask to limit search and used during compaction + * @gfp_mask: GFP mask. Node/zone/placement hints limit the search; only some + * action and reclaim modifiers are supported. Reclaim modifiers + * control allocation behavior during compaction/migration/reclaim. * @nid: Target node * @nodemask: Mask for other possible nodes * @@ -6523,8 +6866,8 @@ static bool zone_spans_last_pfn(const struct zone *zone, * * Return: pointer to contiguous pages on success, or NULL if not successful. */ -struct page *alloc_contig_pages(unsigned long nr_pages, gfp_t gfp_mask, - int nid, nodemask_t *nodemask) +struct page *alloc_contig_pages_noprof(unsigned long nr_pages, gfp_t gfp_mask, + int nid, nodemask_t *nodemask) { unsigned long ret, pfn, flags; struct zonelist *zonelist; @@ -6564,6 +6907,18 @@ struct page *alloc_contig_pages(unsigned long nr_pages, gfp_t gfp_mask, void free_contig_range(unsigned long pfn, unsigned long nr_pages) { unsigned long count = 0; + struct folio *folio = pfn_folio(pfn); + + if (folio_test_large(folio)) { + int expected = folio_nr_pages(folio); + + if (nr_pages == expected) + folio_put(folio); + else + WARN(true, "PFN %lu: nr_pages %lu != expected %d\n", + pfn, nr_pages, expected); + return; + } for (; nr_pages--; pfn++) { struct page *page = pfn_to_page(pfn); @@ -6620,14 +6975,19 @@ void zone_pcp_reset(struct zone *zone) /* * All pages in the range must be in a single zone, must not contain holes, * must span full sections, and must be isolated before calling this function. + * + * Returns the number of managed (non-PageOffline()) pages in the range: the + * number of pages for which memory offlining code must adjust managed page + * counters using adjust_managed_page_count(). */ -void __offline_isolated_pages(unsigned long start_pfn, unsigned long end_pfn) +unsigned long __offline_isolated_pages(unsigned long start_pfn, + unsigned long end_pfn) { + unsigned long already_offline = 0, flags; unsigned long pfn = start_pfn; struct page *page; struct zone *zone; unsigned int order; - unsigned long flags; offline_mem_sections(pfn, end_pfn); zone = page_zone(pfn_to_page(pfn)); @@ -6649,33 +7009,37 @@ void __offline_isolated_pages(unsigned long start_pfn, unsigned long end_pfn) if (PageOffline(page)) { BUG_ON(page_count(page)); BUG_ON(PageBuddy(page)); + already_offline++; pfn++; continue; } BUG_ON(page_count(page)); BUG_ON(!PageBuddy(page)); + VM_WARN_ON(get_pageblock_migratetype(page) != MIGRATE_ISOLATE); order = buddy_order(page); - del_page_from_free_list(page, zone, order); + del_page_from_free_list(page, zone, order, MIGRATE_ISOLATE); pfn += (1 << order); } spin_unlock_irqrestore(&zone->lock, flags); + + return end_pfn - start_pfn - already_offline; } #endif /* * This function returns a stable result only if called under zone lock. */ -bool is_free_buddy_page(struct page *page) +bool is_free_buddy_page(const struct page *page) { unsigned long pfn = page_to_pfn(page); unsigned int order; for (order = 0; order < NR_PAGE_ORDERS; order++) { - struct page *page_head = page - (pfn & ((1 << order) - 1)); + const struct page *head = page - (pfn & ((1 << order) - 1)); - if (PageBuddy(page_head) && - buddy_order_unsafe(page_head) >= order) + if (PageBuddy(head) && + buddy_order_unsafe(head) >= order) break; } @@ -6684,6 +7048,14 @@ bool is_free_buddy_page(struct page *page) EXPORT_SYMBOL(is_free_buddy_page); #ifdef CONFIG_MEMORY_FAILURE +static inline void add_to_free_list(struct page *page, struct zone *zone, + unsigned int order, int migratetype, + bool tail) +{ + __add_to_free_list(page, zone, order, migratetype, tail); + account_freepages(zone, 1 << order, migratetype); +} + /* * Break down a higher-order page in sub-pages, and keep our target out of * buddy allocator. @@ -6706,10 +7078,10 @@ static void break_down_buddy_pages(struct zone *zone, struct page *page, current_buddy = page + size; } - if (set_page_guard(zone, current_buddy, high, migratetype)) + if (set_page_guard(zone, current_buddy, high)) continue; - add_to_free_list(current_buddy, zone, high, migratetype); + add_to_free_list(current_buddy, zone, high, migratetype, false); set_buddy_order(current_buddy, high); } } @@ -6735,12 +7107,11 @@ bool take_page_off_buddy(struct page *page) int migratetype = get_pfnblock_migratetype(page_head, pfn_head); - del_page_from_free_list(page_head, zone, page_order); + del_page_from_free_list(page_head, zone, page_order, + migratetype); break_down_buddy_pages(zone, page_head, page, 0, page_order, migratetype); SetPageHWPoisonTakenOff(page); - if (!is_migrate_isolate(migratetype)) - __mod_zone_freepage_state(zone, -1, migratetype); ret = true; break; } @@ -6757,13 +7128,14 @@ bool take_page_off_buddy(struct page *page) bool put_page_back_buddy(struct page *page) { struct zone *zone = page_zone(page); - unsigned long pfn = page_to_pfn(page); unsigned long flags; - int migratetype = get_pfnblock_migratetype(page, pfn); bool ret = false; spin_lock_irqsave(&zone->lock, flags); if (put_page_testzero(page)) { + unsigned long pfn = page_to_pfn(page); + int migratetype = get_pfnblock_migratetype(page, pfn); + ClearPageHWPoisonTakenOff(page); __free_one_page(page, pfn, zone, 0, migratetype, FPI_NONE); if (TestClearPageHWPoison(page)) { @@ -6793,9 +7165,6 @@ bool has_managed_dma(void) #ifdef CONFIG_UNACCEPTED_MEMORY -/* Counts number of zones with unaccepted pages. */ -static DEFINE_STATIC_KEY_FALSE(zones_with_unaccepted_pages); - static bool lazy_accept = true; static int __init accept_memory_parse(char *p) @@ -6815,26 +7184,43 @@ early_param("accept_memory", accept_memory_parse); static bool page_contains_unaccepted(struct page *page, unsigned int order) { phys_addr_t start = page_to_phys(page); - phys_addr_t end = start + (PAGE_SIZE << order); - return range_contains_unaccepted_memory(start, end); + return range_contains_unaccepted_memory(start, PAGE_SIZE << order); } -static void accept_page(struct page *page, unsigned int order) +static void __accept_page(struct zone *zone, unsigned long *flags, + struct page *page) { - phys_addr_t start = page_to_phys(page); + list_del(&page->lru); + account_freepages(zone, -MAX_ORDER_NR_PAGES, MIGRATE_MOVABLE); + __mod_zone_page_state(zone, NR_UNACCEPTED, -MAX_ORDER_NR_PAGES); + __ClearPageUnaccepted(page); + spin_unlock_irqrestore(&zone->lock, *flags); - accept_memory(start, start + (PAGE_SIZE << order)); + accept_memory(page_to_phys(page), PAGE_SIZE << MAX_PAGE_ORDER); + + __free_pages_ok(page, MAX_PAGE_ORDER, FPI_TO_TAIL); +} + +void accept_page(struct page *page) +{ + struct zone *zone = page_zone(page); + unsigned long flags; + + spin_lock_irqsave(&zone->lock, flags); + if (!PageUnaccepted(page)) { + spin_unlock_irqrestore(&zone->lock, flags); + return; + } + + /* Unlocks zone->lock */ + __accept_page(zone, &flags, page); } static bool try_to_accept_memory_one(struct zone *zone) { unsigned long flags; struct page *page; - bool last; - - if (list_empty(&zone->unaccepted_pages)) - return false; spin_lock_irqsave(&zone->lock, flags); page = list_first_entry_or_null(&zone->unaccepted_pages, @@ -6844,68 +7230,66 @@ static bool try_to_accept_memory_one(struct zone *zone) return false; } - list_del(&page->lru); - last = list_empty(&zone->unaccepted_pages); + /* Unlocks zone->lock */ + __accept_page(zone, &flags, page); - __mod_zone_freepage_state(zone, -MAX_ORDER_NR_PAGES, MIGRATE_MOVABLE); - __mod_zone_page_state(zone, NR_UNACCEPTED, -MAX_ORDER_NR_PAGES); - spin_unlock_irqrestore(&zone->lock, flags); + return true; +} - accept_page(page, MAX_PAGE_ORDER); +static bool cond_accept_memory(struct zone *zone, unsigned int order, + int alloc_flags) +{ + long to_accept, wmark; + bool ret = false; - __free_pages_ok(page, MAX_PAGE_ORDER, FPI_TO_TAIL); + if (list_empty(&zone->unaccepted_pages)) + return false; - if (last) - static_branch_dec(&zones_with_unaccepted_pages); + /* Bailout, since try_to_accept_memory_one() needs to take a lock */ + if (alloc_flags & ALLOC_TRYLOCK) + return false; - return true; -} + wmark = promo_wmark_pages(zone); -static bool try_to_accept_memory(struct zone *zone, unsigned int order) -{ - long to_accept; - int ret = false; + /* + * Watermarks have not been initialized yet. + * + * Accepting one MAX_ORDER page to ensure progress. + */ + if (!wmark) + return try_to_accept_memory_one(zone); - /* How much to accept to get to high watermark? */ - to_accept = high_wmark_pages(zone) - + /* How much to accept to get to promo watermark? */ + to_accept = wmark - (zone_page_state(zone, NR_FREE_PAGES) - - __zone_watermark_unusable_free(zone, order, 0)); + __zone_watermark_unusable_free(zone, order, 0) - + zone_page_state(zone, NR_UNACCEPTED)); - /* Accept at least one page */ - do { + while (to_accept > 0) { if (!try_to_accept_memory_one(zone)) break; ret = true; to_accept -= MAX_ORDER_NR_PAGES; - } while (to_accept > 0); + } return ret; } -static inline bool has_unaccepted_memory(void) -{ - return static_branch_unlikely(&zones_with_unaccepted_pages); -} - static bool __free_unaccepted(struct page *page) { struct zone *zone = page_zone(page); unsigned long flags; - bool first = false; if (!lazy_accept) return false; spin_lock_irqsave(&zone->lock, flags); - first = list_empty(&zone->unaccepted_pages); list_add_tail(&page->lru, &zone->unaccepted_pages); - __mod_zone_freepage_state(zone, MAX_ORDER_NR_PAGES, MIGRATE_MOVABLE); + account_freepages(zone, MAX_ORDER_NR_PAGES, MIGRATE_MOVABLE); __mod_zone_page_state(zone, NR_UNACCEPTED, MAX_ORDER_NR_PAGES); + __SetPageUnaccepted(page); spin_unlock_irqrestore(&zone->lock, flags); - if (first) - static_branch_inc(&zones_with_unaccepted_pages); - return true; } @@ -6916,16 +7300,8 @@ static bool page_contains_unaccepted(struct page *page, unsigned int order) return false; } -static void accept_page(struct page *page, unsigned int order) -{ -} - -static bool try_to_accept_memory(struct zone *zone, unsigned int order) -{ - return false; -} - -static inline bool has_unaccepted_memory(void) +static bool cond_accept_memory(struct zone *zone, unsigned int order, + int alloc_flags) { return false; } @@ -6937,3 +7313,93 @@ static bool __free_unaccepted(struct page *page) } #endif /* CONFIG_UNACCEPTED_MEMORY */ + +/** + * alloc_pages_nolock - opportunistic reentrant allocation from any context + * @nid: node to allocate from + * @order: allocation order size + * + * Allocates pages of a given order from the given node. This is safe to + * call from any context (from atomic, NMI, and also reentrant + * allocator -> tracepoint -> alloc_pages_nolock_noprof). + * Allocation is best effort and to be expected to fail easily so nobody should + * rely on the success. Failures are not reported via warn_alloc(). + * See always fail conditions below. + * + * Return: allocated page or NULL on failure. NULL does not mean EBUSY or EAGAIN. + * It means ENOMEM. There is no reason to call it again and expect !NULL. + */ +struct page *alloc_pages_nolock_noprof(int nid, unsigned int order) +{ + /* + * Do not specify __GFP_DIRECT_RECLAIM, since direct claim is not allowed. + * Do not specify __GFP_KSWAPD_RECLAIM either, since wake up of kswapd + * is not safe in arbitrary context. + * + * These two are the conditions for gfpflags_allow_spinning() being true. + * + * Specify __GFP_NOWARN since failing alloc_pages_nolock() is not a reason + * to warn. Also warn would trigger printk() which is unsafe from + * various contexts. We cannot use printk_deferred_enter() to mitigate, + * since the running context is unknown. + * + * Specify __GFP_ZERO to make sure that call to kmsan_alloc_page() below + * is safe in any context. Also zeroing the page is mandatory for + * BPF use cases. + * + * Though __GFP_NOMEMALLOC is not checked in the code path below, + * specify it here to highlight that alloc_pages_nolock() + * doesn't want to deplete reserves. + */ + gfp_t alloc_gfp = __GFP_NOWARN | __GFP_ZERO | __GFP_NOMEMALLOC + | __GFP_ACCOUNT; + unsigned int alloc_flags = ALLOC_TRYLOCK; + struct alloc_context ac = { }; + struct page *page; + + /* + * In PREEMPT_RT spin_trylock() will call raw_spin_lock() which is + * unsafe in NMI. If spin_trylock() is called from hard IRQ the current + * task may be waiting for one rt_spin_lock, but rt_spin_trylock() will + * mark the task as the owner of another rt_spin_lock which will + * confuse PI logic, so return immediately if called form hard IRQ or + * NMI. + * + * Note, irqs_disabled() case is ok. This function can be called + * from raw_spin_lock_irqsave region. + */ + if (IS_ENABLED(CONFIG_PREEMPT_RT) && (in_nmi() || in_hardirq())) + return NULL; + if (!pcp_allowed_order(order)) + return NULL; + + /* Bailout, since _deferred_grow_zone() needs to take a lock */ + if (deferred_pages_enabled()) + return NULL; + + if (nid == NUMA_NO_NODE) + nid = numa_node_id(); + + prepare_alloc_pages(alloc_gfp, order, nid, NULL, &ac, + &alloc_gfp, &alloc_flags); + + /* + * Best effort allocation from percpu free list. + * If it's empty attempt to spin_trylock zone->lock. + */ + page = get_page_from_freelist(alloc_gfp, order, alloc_flags, &ac); + + /* Unlike regular alloc_pages() there is no __alloc_pages_slowpath(). */ + + if (page) + set_page_refcounted(page); + + if (memcg_kmem_online() && page && + unlikely(__memcg_kmem_charge_page(page, alloc_gfp, order) != 0)) { + free_pages_nolock(page, order); + page = NULL; + } + trace_mm_page_alloc(page, order, alloc_gfp, ac.migratetype); + kmsan_alloc_page(page, order, alloc_gfp); + return page; +} |