diff options
Diffstat (limited to 'mm/page_alloc.c')
| -rw-r--r-- | mm/page_alloc.c | 875 |
1 files changed, 432 insertions, 443 deletions
diff --git a/mm/page_alloc.c b/mm/page_alloc.c index 6e5b4488a0c5..e5486d47406e 100644 --- a/mm/page_alloc.c +++ b/mm/page_alloc.c @@ -81,6 +81,7 @@ #include "internal.h" #include "shuffle.h" #include "page_reporting.h" +#include "swap.h" /* Free Page Internal flags: for internal, non-pcp variants of free_pages(). */ typedef int __bitwise fpi_t; @@ -125,13 +126,97 @@ typedef int __bitwise fpi_t; static DEFINE_MUTEX(pcp_batch_high_lock); #define MIN_PERCPU_PAGELIST_HIGH_FRACTION (8) -struct pagesets { - local_lock_t lock; -}; -static DEFINE_PER_CPU(struct pagesets, pagesets) = { - .lock = INIT_LOCAL_LOCK(lock), -}; +#if defined(CONFIG_SMP) || defined(CONFIG_PREEMPT_RT) +/* + * On SMP, spin_trylock is sufficient protection. + * On PREEMPT_RT, spin_trylock is equivalent on both SMP and UP. + */ +#define pcp_trylock_prepare(flags) do { } while (0) +#define pcp_trylock_finish(flag) do { } while (0) +#else + +/* UP spin_trylock always succeeds so disable IRQs to prevent re-entrancy. */ +#define pcp_trylock_prepare(flags) local_irq_save(flags) +#define pcp_trylock_finish(flags) local_irq_restore(flags) +#endif + +/* + * Locking a pcp requires a PCP lookup followed by a spinlock. To avoid + * a migration causing the wrong PCP to be locked and remote memory being + * potentially allocated, pin the task to the CPU for the lookup+lock. + * preempt_disable is used on !RT because it is faster than migrate_disable. + * migrate_disable is used on RT because otherwise RT spinlock usage is + * interfered with and a high priority task cannot preempt the allocator. + */ +#ifndef CONFIG_PREEMPT_RT +#define pcpu_task_pin() preempt_disable() +#define pcpu_task_unpin() preempt_enable() +#else +#define pcpu_task_pin() migrate_disable() +#define pcpu_task_unpin() migrate_enable() +#endif +/* + * Generic helper to lookup and a per-cpu variable with an embedded spinlock. + * Return value should be used with equivalent unlock helper. + */ +#define pcpu_spin_lock(type, member, ptr) \ +({ \ + type *_ret; \ + pcpu_task_pin(); \ + _ret = this_cpu_ptr(ptr); \ + spin_lock(&_ret->member); \ + _ret; \ +}) + +#define pcpu_spin_lock_irqsave(type, member, ptr, flags) \ +({ \ + type *_ret; \ + pcpu_task_pin(); \ + _ret = this_cpu_ptr(ptr); \ + spin_lock_irqsave(&_ret->member, flags); \ + _ret; \ +}) + +#define pcpu_spin_trylock_irqsave(type, member, ptr, flags) \ +({ \ + type *_ret; \ + pcpu_task_pin(); \ + _ret = this_cpu_ptr(ptr); \ + if (!spin_trylock_irqsave(&_ret->member, flags)) { \ + pcpu_task_unpin(); \ + _ret = NULL; \ + } \ + _ret; \ +}) + +#define pcpu_spin_unlock(member, ptr) \ +({ \ + spin_unlock(&ptr->member); \ + pcpu_task_unpin(); \ +}) + +#define pcpu_spin_unlock_irqrestore(member, ptr, flags) \ +({ \ + spin_unlock_irqrestore(&ptr->member, flags); \ + pcpu_task_unpin(); \ +}) + +/* struct per_cpu_pages specific helpers. */ +#define pcp_spin_lock(ptr) \ + pcpu_spin_lock(struct per_cpu_pages, lock, ptr) + +#define pcp_spin_lock_irqsave(ptr, flags) \ + pcpu_spin_lock_irqsave(struct per_cpu_pages, lock, ptr, flags) + +#define pcp_spin_trylock_irqsave(ptr, flags) \ + pcpu_spin_trylock_irqsave(struct per_cpu_pages, lock, ptr, flags) + +#define pcp_spin_unlock(ptr) \ + pcpu_spin_unlock(lock, ptr) + +#define pcp_spin_unlock_irqrestore(ptr, flags) \ + pcpu_spin_unlock_irqrestore(lock, ptr, flags) #ifdef CONFIG_USE_PERCPU_NUMA_NODE_ID DEFINE_PER_CPU(int, numa_node); EXPORT_PER_CPU_SYMBOL(numa_node); @@ -150,13 +235,7 @@ DEFINE_PER_CPU(int, _numa_mem_); /* Kernel "local memory" node */ EXPORT_PER_CPU_SYMBOL(_numa_mem_); #endif -/* work_structs for global per-cpu drains */ -struct pcpu_drain { - struct zone *zone; - struct work_struct work; -}; static DEFINE_MUTEX(pcpu_drain_mutex); -static DEFINE_PER_CPU(struct pcpu_drain, pcpu_drain); #ifdef CONFIG_GCC_PLUGIN_LATENT_ENTROPY volatile unsigned long latent_entropy __latent_entropy; @@ -355,7 +434,7 @@ static unsigned long required_kernelcore_percent __initdata; static unsigned long required_movablecore __initdata; static unsigned long required_movablecore_percent __initdata; static unsigned long zone_movable_pfn[MAX_NUMNODES] __initdata; -static bool mirrored_kernelcore __meminitdata; +bool mirrored_kernelcore __initdata_memblock; /* movable_zone is the "real" zone pages in ZONE_MOVABLE are taken from */ int movable_zone; @@ -481,8 +560,12 @@ unsigned long __get_pfnblock_flags_mask(const struct page *page, bitidx = pfn_to_bitidx(page, pfn); word_bitidx = bitidx / BITS_PER_LONG; bitidx &= (BITS_PER_LONG-1); - - word = bitmap[word_bitidx]; + /* + * This races, without locks, with set_pfnblock_flags_mask(). Ensure + * a consistent read of the memory array, so that results, even though + * racy, are not corrupted. + */ + word = READ_ONCE(bitmap[word_bitidx]); return (word >> bitidx) & mask; } @@ -519,7 +602,7 @@ void set_pfnblock_flags_mask(struct page *page, unsigned long flags, { unsigned long *bitmap; unsigned long bitidx, word_bitidx; - unsigned long old_word, word; + unsigned long word; BUILD_BUG_ON(NR_PAGEBLOCK_BITS != 4); BUILD_BUG_ON(MIGRATE_TYPES > (1 << PB_migratetype_bits)); @@ -535,12 +618,8 @@ void set_pfnblock_flags_mask(struct page *page, unsigned long flags, flags <<= bitidx; word = READ_ONCE(bitmap[word_bitidx]); - for (;;) { - old_word = cmpxchg(&bitmap[word_bitidx], word, (word & ~mask) | flags); - if (word == old_word) - break; - word = old_word; - } + do { + } while (!try_cmpxchg(&bitmap[word_bitidx], &word, (word & ~mask) | flags)); } void set_pageblock_migratetype(struct page *page, int migratetype) @@ -648,7 +727,7 @@ static inline unsigned int order_to_pindex(int migratetype, int order) #ifdef CONFIG_TRANSPARENT_HUGEPAGE if (order > PAGE_ALLOC_COSTLY_ORDER) { VM_BUG_ON(order != pageblock_order); - base = PAGE_ALLOC_COSTLY_ORDER + 1; + return NR_LOWORDER_PCP_LISTS; } #else VM_BUG_ON(order > PAGE_ALLOC_COSTLY_ORDER); @@ -662,7 +741,7 @@ static inline int pindex_to_order(unsigned int pindex) int order = pindex / MIGRATE_PCPTYPES; #ifdef CONFIG_TRANSPARENT_HUGEPAGE - if (order > PAGE_ALLOC_COSTLY_ORDER) + if (pindex == NR_LOWORDER_PCP_LISTS) order = pageblock_order; #else VM_BUG_ON(order > PAGE_ALLOC_COSTLY_ORDER); @@ -739,6 +818,14 @@ void prep_compound_page(struct page *page, unsigned int order) prep_compound_head(page, order); } +void destroy_large_folio(struct folio *folio) +{ + enum compound_dtor_id dtor = folio_page(folio, 1)->compound_dtor; + + VM_BUG_ON_FOLIO(dtor >= NR_COMPOUND_DTORS, folio); + compound_page_dtors[dtor](&folio->page); +} + #ifdef CONFIG_DEBUG_PAGEALLOC unsigned int _debug_guardpage_minorder; @@ -780,7 +867,7 @@ static inline bool set_page_guard(struct zone *zone, struct page *page, return false; __SetPageGuard(page); - INIT_LIST_HEAD(&page->lru); + INIT_LIST_HEAD(&page->buddy_list); set_page_private(page, order); /* Guard pages are not available for any usage */ __mod_zone_freepage_state(zone, -(1 << order), migratetype); @@ -867,40 +954,6 @@ static inline void set_buddy_order(struct page *page, unsigned int order) __SetPageBuddy(page); } -/* - * This function checks whether a page is free && is the buddy - * we can coalesce a page and its buddy if - * (a) the buddy is not in a hole (check before calling!) && - * (b) the buddy is in the buddy system && - * (c) a page and its buddy have the same order && - * (d) a page and its buddy are in the same zone. - * - * For recording whether a page is in the buddy system, we set PageBuddy. - * Setting, clearing, and testing PageBuddy is serialized by zone->lock. - * - * For recording page's order, we use page_private(page). - */ -static inline bool page_is_buddy(struct page *page, struct page *buddy, - unsigned int order) -{ - if (!page_is_guard(buddy) && !PageBuddy(buddy)) - return false; - - if (buddy_order(buddy) != order) - return false; - - /* - * zone check is done late to avoid uselessly calculating - * zone/node ids for pages that could never merge. - */ - if (page_zone_id(page) != page_zone_id(buddy)) - return false; - - VM_BUG_ON_PAGE(page_count(buddy) != 0, buddy); - - return true; -} - #ifdef CONFIG_COMPACTION static inline struct capture_control *task_capc(struct zone *zone) { @@ -957,7 +1010,7 @@ static inline void add_to_free_list(struct page *page, struct zone *zone, { struct free_area *area = &zone->free_area[order]; - list_add(&page->lru, &area->free_list[migratetype]); + list_add(&page->buddy_list, &area->free_list[migratetype]); area->nr_free++; } @@ -967,7 +1020,7 @@ static inline void add_to_free_list_tail(struct page *page, struct zone *zone, { struct free_area *area = &zone->free_area[order]; - list_add_tail(&page->lru, &area->free_list[migratetype]); + list_add_tail(&page->buddy_list, &area->free_list[migratetype]); area->nr_free++; } @@ -981,7 +1034,7 @@ static inline void move_to_free_list(struct page *page, struct zone *zone, { struct free_area *area = &zone->free_area[order]; - list_move_tail(&page->lru, &area->free_list[migratetype]); + list_move_tail(&page->buddy_list, &area->free_list[migratetype]); } static inline void del_page_from_free_list(struct page *page, struct zone *zone, @@ -991,7 +1044,7 @@ static inline void del_page_from_free_list(struct page *page, struct zone *zone, if (page_reported(page)) __ClearPageReported(page); - list_del(&page->lru); + list_del(&page->buddy_list); __ClearPageBuddy(page); set_page_private(page, 0); zone->free_area[order].nr_free--; @@ -1009,18 +1062,17 @@ static inline bool buddy_merge_likely(unsigned long pfn, unsigned long buddy_pfn, struct page *page, unsigned int order) { - struct page *higher_page, *higher_buddy; - unsigned long combined_pfn; + unsigned long higher_page_pfn; + struct page *higher_page; if (order >= MAX_ORDER - 2) return false; - combined_pfn = buddy_pfn & pfn; - higher_page = page + (combined_pfn - pfn); - buddy_pfn = __find_buddy_pfn(combined_pfn, order + 1); - higher_buddy = higher_page + (buddy_pfn - combined_pfn); + higher_page_pfn = buddy_pfn & pfn; + higher_page = page + (higher_page_pfn - pfn); - return page_is_buddy(higher_page, higher_buddy, order + 1); + return find_buddy_page_pfn(higher_page, higher_page_pfn, order + 1, + NULL) != NULL; } /* @@ -1053,7 +1105,6 @@ static inline void __free_one_page(struct page *page, int migratetype, fpi_t fpi_flags) { struct capture_control *capc = task_capc(zone); - unsigned int max_order = pageblock_order; unsigned long buddy_pfn; unsigned long combined_pfn; struct page *buddy; @@ -1069,18 +1120,32 @@ static inline void __free_one_page(struct page *page, VM_BUG_ON_PAGE(pfn & ((1 << order) - 1), page); VM_BUG_ON_PAGE(bad_range(zone, page), page); -continue_merging: - while (order < max_order) { + while (order < MAX_ORDER - 1) { if (compaction_capture(capc, page, order, migratetype)) { __mod_zone_freepage_state(zone, -(1 << order), migratetype); return; } - buddy_pfn = __find_buddy_pfn(pfn, order); - buddy = page + (buddy_pfn - pfn); - if (!page_is_buddy(page, buddy, order)) + buddy = find_buddy_page_pfn(page, pfn, order, &buddy_pfn); + if (!buddy) goto done_merging; + + if (unlikely(order >= pageblock_order)) { + /* + * We want to prevent merge between freepages on pageblock + * without fallbacks and normal pageblock. Without this, + * pageblock isolation could cause incorrect freepage or CMA + * accounting or HIGHATOMIC accounting. + */ + int buddy_mt = get_pageblock_migratetype(buddy); + + if (migratetype != buddy_mt + && (!migratetype_is_mergeable(migratetype) || + !migratetype_is_mergeable(buddy_mt))) + goto done_merging; + } + /* * Our buddy is free or it is CONFIG_DEBUG_PAGEALLOC guard page, * merge with it and move up one order. @@ -1094,32 +1159,6 @@ continue_merging: pfn = combined_pfn; order++; } - if (order < MAX_ORDER - 1) { - /* If we are here, it means order is >= pageblock_order. - * We want to prevent merge between freepages on pageblock - * without fallbacks and normal pageblock. Without this, - * pageblock isolation could cause incorrect freepage or CMA - * accounting or HIGHATOMIC accounting. - * - * We don't want to hit this code for the more frequent - * low-order merging. - */ - int buddy_mt; - - buddy_pfn = __find_buddy_pfn(pfn, order); - buddy = page + (buddy_pfn - pfn); - - if (!page_is_buddy(page, buddy, order)) - goto done_merging; - buddy_mt = get_pageblock_migratetype(buddy); - - if (migratetype != buddy_mt - && (!migratetype_is_mergeable(migratetype) || - !migratetype_is_mergeable(buddy_mt))) - goto done_merging; - max_order = order + 1; - goto continue_merging; - } done_merging: set_buddy_order(page, order); @@ -1141,6 +1180,64 @@ done_merging: 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_pageblock_migratetype(free_page); + 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 @@ -1281,18 +1378,14 @@ static inline bool should_skip_kasan_poison(struct page *page, fpi_t fpi_flags) PageSkipKASanPoison(page); } -static void kernel_init_free_pages(struct page *page, int numpages) +static void kernel_init_pages(struct page *page, int numpages) { int i; /* s390's use of memset() could override KASAN redzones. */ kasan_disable_current(); - for (i = 0; i < numpages; i++) { - u8 tag = page_kasan_tag(page + i); - page_kasan_tag_reset(page + i); - clear_highpage(page + i); - page_kasan_tag_set(page + i, tag); - } + for (i = 0; i < numpages; i++) + clear_highpage_kasan_tagged(page + i); kasan_enable_current(); } @@ -1381,7 +1474,7 @@ static __always_inline bool free_pages_prepare(struct page *page, init = false; } if (init) - kernel_init_free_pages(page, 1 << order); + kernel_init_pages(page, 1 << order); /* * arch_free_page() can make the page's contents inaccessible. s390 @@ -1458,10 +1551,7 @@ static void free_pcppages_bulk(struct zone *zone, int count, /* Ensure requested pindex is drained first. */ pindex = pindex - 1; - /* - * local_lock_irq held so equivalent to spin_lock_irqsave for - * both PREEMPT_RT and non-PREEMPT_RT configurations. - */ + /* Caller must hold IRQ-safe pcp->lock so IRQs are disabled. */ spin_lock(&zone->lock); isolated_pageblocks = has_isolate_pageblock(zone); @@ -1489,11 +1579,11 @@ static void free_pcppages_bulk(struct zone *zone, int count, do { int mt; - page = list_last_entry(list, struct page, lru); + page = list_last_entry(list, struct page, pcp_list); mt = get_pcppage_migratetype(page); /* must delete to avoid corrupting pcp list */ - list_del(&page->lru); + list_del(&page->pcp_list); count -= nr_pages; pcp->count -= nr_pages; @@ -2346,7 +2436,7 @@ static inline bool check_new_pcp(struct page *page, unsigned int order) } #endif /* CONFIG_DEBUG_VM */ -static inline bool should_skip_kasan_unpoison(gfp_t flags, bool init_tags) +static inline bool should_skip_kasan_unpoison(gfp_t flags) { /* Don't skip if a software KASAN mode is enabled. */ if (IS_ENABLED(CONFIG_KASAN_GENERIC) || @@ -2358,12 +2448,10 @@ static inline bool should_skip_kasan_unpoison(gfp_t flags, bool init_tags) return true; /* - * With hardware tag-based KASAN enabled, skip if either: - * - * 1. Memory tags have already been cleared via tag_clear_highpage(). - * 2. Skipping has been requested via __GFP_SKIP_KASAN_UNPOISON. + * With hardware tag-based KASAN enabled, skip if this has been + * requested via __GFP_SKIP_KASAN_UNPOISON. */ - return init_tags || (flags & __GFP_SKIP_KASAN_UNPOISON); + return flags & __GFP_SKIP_KASAN_UNPOISON; } static inline bool should_skip_init(gfp_t flags) @@ -2382,6 +2470,7 @@ inline void post_alloc_hook(struct page *page, unsigned int order, bool init = !want_init_on_free() && want_init_on_alloc(gfp_flags) && !should_skip_init(gfp_flags); bool init_tags = init && (gfp_flags & __GFP_ZEROTAGS); + int i; set_page_private(page, 0); set_page_refcounted(page); @@ -2407,8 +2496,6 @@ inline void post_alloc_hook(struct page *page, unsigned int order, * should be initialized as well). */ if (init_tags) { - int i; - /* Initialize both memory and tags. */ for (i = 0; i != 1 << order; ++i) tag_clear_highpage(page + i); @@ -2416,17 +2503,21 @@ inline void post_alloc_hook(struct page *page, unsigned int order, /* Note that memory is already initialized by the loop above. */ init = false; } - if (!should_skip_kasan_unpoison(gfp_flags, init_tags)) { + if (!should_skip_kasan_unpoison(gfp_flags)) { /* Unpoison shadow memory or set memory tags. */ kasan_unpoison_pages(page, order, init); /* Note that memory is already initialized by KASAN. */ if (kasan_has_integrated_init()) init = false; + } else { + /* Ensure page_address() dereferencing does not fault. */ + for (i = 0; i != 1 << order; ++i) + page_kasan_tag_reset(page + i); } /* If memory is still not initialized, do it now. */ if (init) - kernel_init_free_pages(page, 1 << order); + kernel_init_pages(page, 1 << order); /* Propagate __GFP_SKIP_KASAN_POISON to page flags. */ if (kasan_hw_tags_enabled() && (gfp_flags & __GFP_SKIP_KASAN_POISON)) SetPageSkipKASanPoison(page); @@ -2476,6 +2567,9 @@ struct page *__rmqueue_smallest(struct zone *zone, unsigned int order, del_page_from_free_list(page, zone, current_order); expand(zone, page, order, current_order, migratetype); set_pcppage_migratetype(page, migratetype); + trace_mm_page_alloc_zone_locked(page, order, migratetype, + pcp_allowed_order(order) && + migratetype < MIGRATE_PCPTYPES); return page; } @@ -2999,7 +3093,7 @@ __rmqueue(struct zone *zone, unsigned int order, int migratetype, zone_page_state(zone, NR_FREE_PAGES) / 2) { page = __rmqueue_cma_fallback(zone, order); if (page) - goto out; + return page; } } retry: @@ -3012,9 +3106,6 @@ retry: alloc_flags)) goto retry; } -out: - if (page) - trace_mm_page_alloc_zone_locked(page, order, migratetype); return page; } @@ -3029,10 +3120,7 @@ static int rmqueue_bulk(struct zone *zone, unsigned int order, { int i, allocated = 0; - /* - * local_lock_irq held so equivalent to spin_lock_irqsave for - * both PREEMPT_RT and non-PREEMPT_RT configurations. - */ + /* Caller must hold IRQ-safe pcp->lock so IRQs are disabled. */ spin_lock(&zone->lock); for (i = 0; i < count; ++i) { struct page *page = __rmqueue(zone, order, migratetype, @@ -3053,7 +3141,7 @@ static int rmqueue_bulk(struct zone *zone, unsigned int order, * for IO devices that can merge IO requests if the physical * pages are ordered properly. */ - list_add_tail(&page->lru, list); + list_add_tail(&page->pcp_list, list); allocated++; if (is_migrate_cma(get_pcppage_migratetype(page))) __mod_zone_page_state(zone, NR_FREE_CMA_PAGES, @@ -3076,51 +3164,48 @@ static int rmqueue_bulk(struct zone *zone, unsigned int order, * Called from the vmstat counter updater to drain pagesets of this * currently executing processor on remote nodes after they have * expired. - * - * Note that this function must be called with the thread pinned to - * a single processor. */ void drain_zone_pages(struct zone *zone, struct per_cpu_pages *pcp) { - unsigned long flags; int to_drain, batch; - local_lock_irqsave(&pagesets.lock, flags); batch = READ_ONCE(pcp->batch); to_drain = min(pcp->count, batch); - if (to_drain > 0) + if (to_drain > 0) { + unsigned long flags; + + /* + * free_pcppages_bulk expects IRQs disabled for zone->lock + * so even though pcp->lock is not intended to be IRQ-safe, + * it's needed in this context. + */ + spin_lock_irqsave(&pcp->lock, flags); free_pcppages_bulk(zone, to_drain, pcp, 0); - local_unlock_irqrestore(&pagesets.lock, flags); + spin_unlock_irqrestore(&pcp->lock, flags); + } } #endif /* * Drain pcplists of the indicated processor and zone. - * - * The processor must either be the current processor and the - * thread pinned to the current processor or a processor that - * is not online. */ static void drain_pages_zone(unsigned int cpu, struct zone *zone) { - unsigned long flags; struct per_cpu_pages *pcp; - local_lock_irqsave(&pagesets.lock, flags); - pcp = per_cpu_ptr(zone->per_cpu_pageset, cpu); - if (pcp->count) - free_pcppages_bulk(zone, pcp->count, pcp, 0); + if (pcp->count) { + unsigned long flags; - local_unlock_irqrestore(&pagesets.lock, flags); + /* See drain_zone_pages on why this is disabling IRQs */ + spin_lock_irqsave(&pcp->lock, flags); + free_pcppages_bulk(zone, pcp->count, pcp, 0); + spin_unlock_irqrestore(&pcp->lock, flags); + } } /* * Drain pcplists of all zones on the indicated processor. - * - * The processor must either be the current processor and the - * thread pinned to the current processor or a processor that - * is not online. */ static void drain_pages(unsigned int cpu) { @@ -3133,9 +3218,6 @@ static void drain_pages(unsigned int cpu) /* * Spill all of this CPU's per-cpu pages back into the buddy allocator. - * - * The CPU has to be pinned. When zone parameter is non-NULL, spill just - * the single zone's pages. */ void drain_local_pages(struct zone *zone) { @@ -3147,24 +3229,6 @@ void drain_local_pages(struct zone *zone) drain_pages(cpu); } -static void drain_local_pages_wq(struct work_struct *work) -{ - struct pcpu_drain *drain; - - drain = container_of(work, struct pcpu_drain, work); - - /* - * drain_all_pages doesn't use proper cpu hotplug protection so - * we can race with cpu offline when the WQ can move this from - * a cpu pinned worker to an unbound one. We can operate on a different - * cpu which is alright but we also have to make sure to not move to - * a different one. - */ - migrate_disable(); - drain_local_pages(drain->zone); - migrate_enable(); -} - /* * The implementation of drain_all_pages(), exposing an extra parameter to * drain on all cpus. @@ -3186,13 +3250,6 @@ static void __drain_all_pages(struct zone *zone, bool force_all_cpus) static cpumask_t cpus_with_pcps; /* - * Make sure nobody triggers this path before mm_percpu_wq is fully - * initialized. - */ - if (WARN_ON_ONCE(!mm_percpu_wq)) - return; - - /* * Do not drain if one is already in progress unless it's specific to * a zone. Such callers are primarily CMA and memory hotplug and need * the drain to be complete when the call returns. @@ -3241,14 +3298,11 @@ static void __drain_all_pages(struct zone *zone, bool force_all_cpus) } for_each_cpu(cpu, &cpus_with_pcps) { - struct pcpu_drain *drain = per_cpu_ptr(&pcpu_drain, cpu); - - drain->zone = zone; - INIT_WORK(&drain->work, drain_local_pages_wq); - queue_work_on(cpu, mm_percpu_wq, &drain->work); + if (zone) + drain_pages_zone(cpu, zone); + else + drain_pages(cpu); } - for_each_cpu(cpu, &cpus_with_pcps) - flush_work(&per_cpu_ptr(&pcpu_drain, cpu)->work); mutex_unlock(&pcpu_drain_mutex); } @@ -3257,8 +3311,6 @@ static void __drain_all_pages(struct zone *zone, bool force_all_cpus) * Spill all the per-cpu pages from all CPUs back into the buddy allocator. * * When zone parameter is non-NULL, spill just the single zone's pages. - * - * Note that this can be extremely slow as the draining happens in a workqueue. */ void drain_all_pages(struct zone *zone) { @@ -3303,7 +3355,7 @@ void mark_free_pages(struct zone *zone) for_each_migratetype_order(order, t) { list_for_each_entry(page, - &zone->free_area[order].free_list[t], lru) { + &zone->free_area[order].free_list[t], buddy_list) { unsigned long i; pfn = page_to_pfn(page); @@ -3380,19 +3432,17 @@ static int nr_pcp_high(struct per_cpu_pages *pcp, struct zone *zone, return min(READ_ONCE(pcp->batch) << 2, high); } -static void free_unref_page_commit(struct page *page, int migratetype, +static void free_unref_page_commit(struct zone *zone, struct per_cpu_pages *pcp, + struct page *page, int migratetype, unsigned int order) { - struct zone *zone = page_zone(page); - struct per_cpu_pages *pcp; int high; int pindex; bool free_high; __count_vm_event(PGFREE); - pcp = this_cpu_ptr(zone->per_cpu_pageset); pindex = order_to_pindex(migratetype, order); - list_add(&page->lru, &pcp->lists[pindex]); + list_add(&page->pcp_list, &pcp->lists[pindex]); pcp->count += 1 << order; /* @@ -3417,6 +3467,9 @@ static void free_unref_page_commit(struct page *page, int migratetype, void free_unref_page(struct page *page, unsigned int order) { unsigned long flags; + unsigned long __maybe_unused UP_flags; + struct per_cpu_pages *pcp; + struct zone *zone; unsigned long pfn = page_to_pfn(page); int migratetype; @@ -3439,9 +3492,16 @@ void free_unref_page(struct page *page, unsigned int order) migratetype = MIGRATE_MOVABLE; } - local_lock_irqsave(&pagesets.lock, flags); - free_unref_page_commit(page, migratetype, order); - local_unlock_irqrestore(&pagesets.lock, flags); + zone = page_zone(page); + pcp_trylock_prepare(UP_flags); + pcp = pcp_spin_trylock_irqsave(zone->per_cpu_pageset, flags); + if (pcp) { + free_unref_page_commit(zone, pcp, page, migratetype, order); + pcp_spin_unlock_irqrestore(pcp, flags); + } else { + free_one_page(zone, page, pfn, order, migratetype, FPI_NONE); + } + pcp_trylock_finish(UP_flags); } /* @@ -3450,6 +3510,8 @@ void free_unref_page(struct page *page, unsigned int order) void free_unref_page_list(struct list_head *list) { struct page *page, *next; + struct per_cpu_pages *pcp = NULL; + struct zone *locked_zone = NULL; unsigned long flags; int batch_count = 0; int migratetype; @@ -3474,8 +3536,18 @@ void free_unref_page_list(struct list_head *list) } } - local_lock_irqsave(&pagesets.lock, flags); list_for_each_entry_safe(page, next, list, lru) { + struct zone *zone = page_zone(page); + + /* Different zone, different pcp lock. */ + if (zone != locked_zone) { + if (pcp) + pcp_spin_unlock_irqrestore(pcp, flags); + + locked_zone = zone; + pcp = pcp_spin_lock_irqsave(locked_zone->per_cpu_pageset, flags); + } + /* * Non-isolated types over MIGRATE_PCPTYPES get added * to the MIGRATE_MOVABLE pcp list. @@ -3485,19 +3557,21 @@ void free_unref_page_list(struct list_head *list) migratetype = MIGRATE_MOVABLE; trace_mm_page_free_batched(page); - free_unref_page_commit(page, migratetype, 0); + free_unref_page_commit(zone, pcp, page, migratetype, 0); /* * Guard against excessive IRQ disabled times when we get * a large list of pages to free. */ if (++batch_count == SWAP_CLUSTER_MAX) { - local_unlock_irqrestore(&pagesets.lock, flags); + pcp_spin_unlock_irqrestore(pcp, flags); batch_count = 0; - local_lock_irqsave(&pagesets.lock, flags); + pcp = pcp_spin_lock_irqsave(locked_zone->per_cpu_pageset, flags); } } - local_unlock_irqrestore(&pagesets.lock, flags); + + if (pcp) + pcp_spin_unlock_irqrestore(pcp, flags); } /* @@ -3622,6 +3696,43 @@ static inline void zone_statistics(struct zone *preferred_zone, struct zone *z, #endif } +static __always_inline +struct page *rmqueue_buddy(struct zone *preferred_zone, struct zone *zone, + unsigned int order, unsigned int alloc_flags, + int migratetype) +{ + struct page *page; + unsigned long flags; + + do { + page = NULL; + spin_lock_irqsave(&zone->lock, flags); + /* + * order-0 request can reach here when the pcplist is skipped + * due to non-CMA allocation context. HIGHATOMIC area is + * reserved for high-order atomic allocation, so order-0 + * request should skip it. + */ + if (order > 0 && alloc_flags & ALLOC_HARDER) + page = __rmqueue_smallest(zone, order, MIGRATE_HIGHATOMIC); + if (!page) { + page = __rmqueue(zone, order, migratetype, alloc_flags); + if (!page) { + spin_unlock_irqrestore(&zone->lock, flags); + 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)); + + __count_zid_vm_events(PGALLOC, page_zonenum(page), 1 << order); + zone_statistics(preferred_zone, zone, 1); + + return page; +} + /* Remove page from the per-cpu list, caller must protect the list */ static inline struct page *__rmqueue_pcplist(struct zone *zone, unsigned int order, @@ -3655,8 +3766,8 @@ struct page *__rmqueue_pcplist(struct zone *zone, unsigned int order, return NULL; } - page = list_first_entry(list, struct page, lru); - list_del(&page->lru); + page = list_first_entry(list, struct page, pcp_list); + list_del(&page->pcp_list); pcp->count -= 1 << order; } while (check_new_pcp(page, order)); @@ -3673,19 +3784,29 @@ static struct page *rmqueue_pcplist(struct zone *preferred_zone, struct list_head *list; struct page *page; unsigned long flags; + unsigned long __maybe_unused UP_flags; - local_lock_irqsave(&pagesets.lock, flags); + /* + * spin_trylock may fail due to a parallel drain. In the future, the + * trylock will also protect against IRQ reentrancy. + */ + pcp_trylock_prepare(UP_flags); + pcp = pcp_spin_trylock_irqsave(zone->per_cpu_pageset, flags); + if (!pcp) { + pcp_trylock_finish(UP_flags); + return NULL; + } /* * On allocation, reduce the number of pages that are batch freed. * See nr_pcp_free() where free_factor is increased for subsequent * frees. */ - pcp = this_cpu_ptr(zone->per_cpu_pageset); pcp->free_factor >>= 1; list = &pcp->lists[order_to_pindex(migratetype, order)]; page = __rmqueue_pcplist(zone, order, migratetype, alloc_flags, pcp, list); - local_unlock_irqrestore(&pagesets.lock, flags); + pcp_spin_unlock_irqrestore(pcp, flags); + pcp_trylock_finish(UP_flags); if (page) { __count_zid_vm_events(PGALLOC, page_zonenum(page), 1); zone_statistics(preferred_zone, zone, 1); @@ -3702,9 +3823,14 @@ struct page *rmqueue(struct zone *preferred_zone, gfp_t gfp_flags, unsigned int alloc_flags, int migratetype) { - unsigned long flags; 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))) { /* * MIGRATE_MOVABLE pcplist could have the pages on CMA area and @@ -3714,56 +3840,23 @@ struct page *rmqueue(struct zone *preferred_zone, migratetype != MIGRATE_MOVABLE) { page = rmqueue_pcplist(preferred_zone, zone, order, gfp_flags, migratetype, alloc_flags); - goto out; + if (likely(page)) + goto out; } } - /* - * 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)); - - do { - page = NULL; - spin_lock_irqsave(&zone->lock, flags); - /* - * order-0 request can reach here when the pcplist is skipped - * due to non-CMA allocation context. HIGHATOMIC area is - * reserved for high-order atomic allocation, so order-0 - * request should skip it. - */ - if (order > 0 && alloc_flags & ALLOC_HARDER) { - page = __rmqueue_smallest(zone, order, MIGRATE_HIGHATOMIC); - if (page) - trace_mm_page_alloc_zone_locked(page, order, migratetype); - } - if (!page) { - page = __rmqueue(zone, order, migratetype, alloc_flags); - if (!page) - goto failed; - } - __mod_zone_freepage_state(zone, -(1 << order), - get_pcppage_migratetype(page)); - spin_unlock_irqrestore(&zone->lock, flags); - } while (check_new_pages(page, order)); - - __count_zid_vm_events(PGALLOC, page_zonenum(page), 1 << order); - zone_statistics(preferred_zone, zone, 1); + page = rmqueue_buddy(preferred_zone, zone, order, alloc_flags, + migratetype); out: /* Separate test+clear to avoid unnecessary atomics */ - if (test_bit(ZONE_BOOSTED_WATERMARK, &zone->flags)) { + if (unlikely(test_bit(ZONE_BOOSTED_WATERMARK, &zone->flags))) { clear_bit(ZONE_BOOSTED_WATERMARK, &zone->flags); wakeup_kswapd(zone, 0, 0, zone_idx(zone)); } VM_BUG_ON_PAGE(page && bad_range(zone, page), page); return page; - -failed: - spin_unlock_irqrestore(&zone->lock, flags); - return NULL; } #ifdef CONFIG_FAIL_PAGE_ALLOC @@ -3799,6 +3892,9 @@ static bool __should_fail_alloc_page(gfp_t gfp_mask, unsigned int order) (gfp_mask & __GFP_DIRECT_RECLAIM)) return false; + if (gfp_mask & __GFP_NOWARN) + fail_page_alloc.attr.no_warn = true; + return should_fail(&fail_page_alloc.attr, 1 << order); } @@ -3953,11 +4049,15 @@ static inline bool zone_watermark_fast(struct zone *z, unsigned int order, * need to be calculated. */ if (!order) { - long fast_free; + long usable_free; + long reserved; + + usable_free = free_pages; + reserved = __zone_watermark_unusable_free(z, 0, alloc_flags); - fast_free = free_pages; - fast_free -= __zone_watermark_unusable_free(z, 0, alloc_flags); - if (fast_free > mark + z->lowmem_reserve[highest_zoneidx]) + /* reserved may over estimate high-atomic reserves. */ + usable_free -= min(usable_free, reserved); + if (usable_free > mark + z->lowmem_reserve[highest_zoneidx]) return true; } @@ -4068,13 +4168,14 @@ get_page_from_freelist(gfp_t gfp_mask, unsigned int order, int alloc_flags, { struct zoneref *z; struct zone *zone; - struct pglist_data *last_pgdat_dirty_limit = NULL; + struct pglist_data *last_pgdat = NULL; + bool last_pgdat_dirty_ok = false; bool no_fallback; retry: /* * Scan zonelist, looking for a zone with enough free. - * See also __cpuset_node_allowed() comment in kernel/cpuset.c. + * See also __cpuset_node_allowed() comment in kernel/cgroup/cpuset.c. */ no_fallback = alloc_flags & ALLOC_NOFRAGMENT; z = ac->preferred_zoneref; @@ -4107,13 +4208,13 @@ retry: * dirty-throttling and the flusher threads. */ if (ac->spread_dirty_pages) { - if (last_pgdat_dirty_limit == zone->zone_pgdat) - continue; + if (last_pgdat != zone->zone_pgdat) { + last_pgdat = zone->zone_pgdat; + last_pgdat_dirty_ok = node_dirty_ok(zone->zone_pgdat); + } - if (!node_dirty_ok(zone->zone_pgdat)) { - last_pgdat_dirty_limit = zone->zone_pgdat; + if (!last_pgdat_dirty_ok) continue; - } } if (no_fallback && nr_online_nodes > 1 && @@ -4346,7 +4447,8 @@ __alloc_pages_may_oom(gfp_t gfp_mask, unsigned int order, */ /* Exhausted what can be done so it's blame time */ - if (out_of_memory(&oc) || WARN_ON_ONCE(gfp_mask & __GFP_NOFAIL)) { + if (out_of_memory(&oc) || + WARN_ON_ONCE_GFP(gfp_mask & __GFP_NOFAIL, gfp_mask)) { *did_some_progress = 1; /* @@ -4677,9 +4779,12 @@ static void wake_all_kswapds(unsigned int order, gfp_t gfp_mask, for_each_zone_zonelist_nodemask(zone, z, ac->zonelist, highest_zoneidx, ac->nodemask) { - if (last_pgdat != zone->zone_pgdat) + if (!managed_zone(zone)) + continue; + if (last_pgdat != zone->zone_pgdat) { wakeup_kswapd(zone, gfp_mask, order, highest_zoneidx); - last_pgdat = zone->zone_pgdat; + last_pgdat = zone->zone_pgdat; + } } } @@ -5117,7 +5222,7 @@ nopage: * All existing users of the __GFP_NOFAIL are blockable, so warn * of any new users that actually require GFP_NOWAIT */ - if (WARN_ON_ONCE(!can_direct_reclaim)) + if (WARN_ON_ONCE_GFP(!can_direct_reclaim, gfp_mask)) goto fail; /* @@ -5125,7 +5230,7 @@ nopage: * 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); + WARN_ON_ONCE_GFP(current->flags & PF_MEMALLOC, gfp_mask); /* * non failing costly orders are a hard requirement which we @@ -5133,7 +5238,7 @@ nopage: * so that we can identify them and convert them to something * else. */ - WARN_ON_ONCE(order > PAGE_ALLOC_COSTLY_ORDER); + WARN_ON_ONCE_GFP(order > PAGE_ALLOC_COSTLY_ORDER, gfp_mask); /* * Help non-failing allocations by giving them access to memory @@ -5177,10 +5282,7 @@ static inline bool prepare_alloc_pages(gfp_t gfp_mask, unsigned int order, *alloc_flags |= ALLOC_CPUSET; } - fs_reclaim_acquire(gfp_mask); - fs_reclaim_release(gfp_mask); - - might_sleep_if(gfp_mask & __GFP_DIRECT_RECLAIM); + might_alloc(gfp_mask); if (should_fail_alloc_page(gfp_mask, order)) return false; @@ -5228,6 +5330,7 @@ unsigned long __alloc_pages_bulk(gfp_t gfp, int preferred_nid, { struct page *page; unsigned long flags; + unsigned long __maybe_unused UP_flags; struct zone *zone; struct zoneref *z; struct per_cpu_pages *pcp; @@ -5308,11 +5411,14 @@ unsigned long __alloc_pages_bulk(gfp_t gfp, int preferred_nid, if (unlikely(!zone)) goto failed; + /* Is a parallel drain in progress? */ + pcp_trylock_prepare(UP_flags); + pcp = pcp_spin_trylock_irqsave(zone->per_cpu_pageset, flags); + if (!pcp) + goto failed_irq; + /* Attempt the batch allocation */ - local_lock_irqsave(&pagesets.lock, flags); - pcp = this_cpu_ptr(zone->per_cpu_pageset); pcp_list = &pcp->lists[order_to_pindex(ac.migratetype, 0)]; - while (nr_populated < nr_pages) { /* Skip existing pages */ @@ -5324,9 +5430,11 @@ unsigned long __alloc_pages_bulk(gfp_t gfp, int preferred_nid, page = __rmqueue_pcplist(zone, 0, ac.migratetype, alloc_flags, pcp, pcp_list); if (unlikely(!page)) { - /* Try and get at least one page */ - if (!nr_populated) + /* Try and allocate at least one page */ + if (!nr_account) { + pcp_spin_unlock_irqrestore(pcp, flags); goto failed_irq; + } break; } nr_account++; @@ -5339,7 +5447,8 @@ unsigned long __alloc_pages_bulk(gfp_t gfp, int preferred_nid, nr_populated++; } - local_unlock_irqrestore(&pagesets.lock, flags); + pcp_spin_unlock_irqrestore(pcp, flags); + pcp_trylock_finish(UP_flags); __count_zid_vm_events(PGALLOC, zone_idx(zone), nr_account); zone_statistics(ac.preferred_zoneref->zone, zone, nr_account); @@ -5348,7 +5457,7 @@ out: return nr_populated; failed_irq: - local_unlock_irqrestore(&pagesets.lock, flags); + pcp_trylock_finish(UP_flags); failed: page = __alloc_pages(gfp, 0, preferred_nid, nodemask); @@ -5379,10 +5488,8 @@ struct page *__alloc_pages(gfp_t gfp, unsigned int order, int preferred_nid, * There are several places where we assume that the order value is sane * so bail out early if the request is out of bound. */ - if (unlikely(order >= MAX_ORDER)) { - WARN_ON_ONCE(!(gfp & __GFP_NOWARN)); + if (WARN_ON_ONCE_GFP(order >= MAX_ORDER, gfp)) return NULL; - } gfp &= gfp_allowed_mask; /* @@ -5781,14 +5888,14 @@ long si_mem_available(void) /* * Estimate the amount of memory available for userspace allocations, - * without causing swapping. + * without causing swapping or OOM. */ available = global_zone_page_state(NR_FREE_PAGES) - totalreserve_pages; /* * Not all the page cache can be freed, otherwise the system will - * start swapping. Assume at least half of the page cache, or the - * low watermark worth of cache, needs to stay. + * start swapping or thrashing. Assume at least half of the page + * cache, or the low watermark worth of cache, needs to stay. */ pagecache = pages[LRU_ACTIVE_FILE] + pages[LRU_INACTIVE_FILE]; pagecache -= min(pagecache / 2, wmark_low); @@ -5916,7 +6023,7 @@ static void show_migration_types(unsigned char type) void show_free_areas(unsigned int filter, nodemask_t *nodemask) { unsigned long free_pcp = 0; - int cpu; + int cpu, nid; struct zone *zone; pg_data_t *pgdat; @@ -6104,7 +6211,11 @@ void show_free_areas(unsigned int filter, nodemask_t *nodemask) printk(KERN_CONT "= %lukB\n", K(total)); } - hugetlb_show_meminfo(); + for_each_online_node(nid) { + if (show_mem_node_skip(filter, nid, nodemask)) + continue; + hugetlb_show_meminfo_node(nid); + } printk("%ld total pagecache pages\n", global_node_page_state(NR_FILE_PAGES)); @@ -6131,7 +6242,7 @@ static int build_zonerefs_node(pg_data_t *pgdat, struct zoneref *zonerefs) do { zone_type--; zone = pgdat->node_zones + zone_type; - if (managed_zone(zone)) { + if (populated_zone(zone)) { zoneref_set_zone(zone, &zonerefs[nr_zones++]); check_highest_zone(zone_type); } @@ -6171,7 +6282,6 @@ int numa_zonelist_order_handler(struct ctl_table *table, int write, } -#define MAX_NODE_LOAD (nr_online_nodes) static int node_load[MAX_NUMNODES]; /** @@ -6218,7 +6328,7 @@ int find_next_best_node(int node, nodemask_t *used_node_mask) val += PENALTY_FOR_NODE_WITH_CPUS; /* Slight preference for less loaded node */ - val *= (MAX_NODE_LOAD*MAX_NUMNODES); + val *= MAX_NUMNODES; val += node_load[n]; if (val < min_val) { @@ -6284,13 +6394,12 @@ static void build_thisnode_zonelists(pg_data_t *pgdat) static void build_zonelists(pg_data_t *pgdat) { static int node_order[MAX_NUMNODES]; - int node, load, nr_nodes = 0; + int node, nr_nodes = 0; nodemask_t used_mask = NODE_MASK_NONE; int local_node, prev_node; /* NUMA-aware ordering of nodes */ local_node = pgdat->node_id; - load = nr_online_nodes; prev_node = local_node; memset(node_order, 0, sizeof(node_order)); @@ -6302,11 +6411,10 @@ static void build_zonelists(pg_data_t *pgdat) */ if (node_distance(local_node, node) != node_distance(local_node, prev_node)) - node_load[node] += load; + node_load[node] += 1; node_order[nr_nodes++] = node; prev_node = node; - load--; } build_zonelists_in_node_order(pgdat, node_order, nr_nodes); @@ -6645,6 +6753,21 @@ static void __ref __init_zone_device_page(struct page *page, unsigned long pfn, } } +/* + * With compound page geometry and when struct pages are stored in ram most + * tail pages are reused. Consequently, the amount of unique struct pages to + * initialize is a lot smaller that the total amount of struct pages being + * mapped. This is a paired / mild layering violation with explicit knowledge + * of how the sparse_vmemmap internals handle compound pages in the lack + * of an altmap. See vmemmap_populate_compound_pages(). + */ +static inline unsigned long compound_nr_pages(struct vmem_altmap *altmap, + unsigned long nr_pages) +{ + return is_power_of_2(sizeof(struct page)) && + !altmap ? 2 * (PAGE_SIZE / sizeof(struct page)) : nr_pages; +} + static void __ref memmap_init_compound(struct page *head, unsigned long head_pfn, unsigned long zone_idx, int nid, @@ -6709,7 +6832,7 @@ void __ref memmap_init_zone_device(struct zone *zone, continue; memmap_init_compound(page, pfn, zone_idx, nid, pgmap, - pfns_per_compound); + compound_nr_pages(altmap, pfns_per_compound)); } pr_info("%s initialised %lu pages in %ums\n", __func__, @@ -6978,6 +7101,7 @@ static void per_cpu_pages_init(struct per_cpu_pages *pcp, struct per_cpu_zonesta memset(pcp, 0, sizeof(*pcp)); memset(pzstats, 0, sizeof(*pzstats)); + spin_lock_init(&pcp->lock); for (pindex = 0; pindex < NR_PCP_LISTS; pindex++) INIT_LIST_HEAD(&pcp->lists[pindex]); @@ -7870,7 +7994,7 @@ static void __init find_zone_movable_pfns_for_nodes(void) usable_startpfn = memblock_region_memory_base_pfn(r); - if (usable_startpfn < 0x100000) { + if (usable_startpfn < PHYS_PFN(SZ_4G)) { mem_below_4gb_not_mirrored = true; continue; } @@ -8919,7 +9043,7 @@ void *__init alloc_large_system_hash(const char *tablename, table = memblock_alloc_raw(size, SMP_CACHE_BYTES); } else if (get_order(size) >= MAX_ORDER || hashdist) { - table = __vmalloc(size, gfp_flags); + table = vmalloc_huge(size, gfp_flags); virt = true; if (table) huge = is_vm_area_hugepages(table); @@ -8949,136 +9073,7 @@ void *__init alloc_large_system_hash(const char *tablename, return table; } -/* - * This function checks whether pageblock includes unmovable pages or not. - * - * PageLRU check without isolation or lru_lock could race so that - * MIGRATE_MOVABLE block might include unmovable pages. And __PageMovable - * check without lock_page also may miss some movable non-lru pages at - * race condition. So you can't expect this function should be exact. - * - * Returns a page without holding a reference. If the caller wants to - * dereference that page (e.g., dumping), it has to make sure that it - * cannot get removed (e.g., via memory unplug) concurrently. - * - */ -struct page *has_unmovable_pages(struct zone *zone, struct page *page, - int migratetype, int flags) -{ - unsigned long iter = 0; - unsigned long pfn = page_to_pfn(page); - unsigned long offset = pfn % pageblock_nr_pages; - - if (is_migrate_cma_page(page)) { - /* - * CMA allocations (alloc_contig_range) really need to mark - * isolate CMA pageblocks even when they are not movable in fact - * so consider them movable here. - */ - if (is_migrate_cma(migratetype)) - return NULL; - - return page; - } - - for (; iter < pageblock_nr_pages - offset; iter++) { - page = pfn_to_page(pfn + iter); - - /* - * Both, bootmem allocations and memory holes are marked - * PG_reserved and are unmovable. We can even have unmovable - * allocations inside ZONE_MOVABLE, for example when - * specifying "movablecore". - */ - if (PageReserved(page)) - return page; - - /* - * If the zone is movable and we have ruled out all reserved - * pages then it should be reasonably safe to assume the rest - * is movable. - */ - if (zone_idx(zone) == ZONE_MOVABLE) - continue; - - /* - * Hugepages are not in LRU lists, but they're movable. - * THPs are on the LRU, but need to be counted as #small pages. - * We need not scan over tail pages because we don't - * handle each tail page individually in migration. - */ - if (PageHuge(page) || PageTransCompound(page)) { - struct page *head = compound_head(page); - unsigned int skip_pages; - - if (PageHuge(page)) { - if (!hugepage_migration_supported(page_hstate(head))) - return page; - } else if (!PageLRU(head) && !__PageMovable(head)) { - return page; - } - - skip_pages = compound_nr(head) - (page - head); - iter += skip_pages - 1; - continue; - } - - /* - * We can't use page_count without pin a page - * because another CPU can free compound page. - * This check already skips compound tails of THP - * because their page->_refcount is zero at all time. - */ - if (!page_ref_count(page)) { - if (PageBuddy(page)) - iter += (1 << buddy_order(page)) - 1; - continue; - } - - /* - * The HWPoisoned page may be not in buddy system, and - * page_count() is not 0. - */ - if ((flags & MEMORY_OFFLINE) && PageHWPoison(page)) - continue; - - /* - * We treat all PageOffline() pages as movable when offlining - * to give drivers a chance to decrement their reference count - * in MEM_GOING_OFFLINE in order to indicate that these pages - * can be offlined as there are no direct references anymore. - * For actually unmovable PageOffline() where the driver does - * not support this, we will fail later when trying to actually - * move these pages that still have a reference count > 0. - * (false negatives in this function only) - */ - if ((flags & MEMORY_OFFLINE) && PageOffline(page)) - continue; - - if (__PageMovable(page) || PageLRU(page)) - continue; - - /* - * If there are RECLAIMABLE pages, we need to check - * it. But now, memory offline itself doesn't call - * shrink_node_slabs() and it still to be fixed. - */ - return page; - } - return NULL; -} - #ifdef CONFIG_CONTIG_ALLOC -static unsigned long pfn_max_align_down(unsigned long pfn) -{ - return ALIGN_DOWN(pfn, MAX_ORDER_NR_PAGES); -} - -static unsigned long pfn_max_align_up(unsigned long pfn) -{ - return ALIGN(pfn, MAX_ORDER_NR_PAGES); -} - #if defined(CONFIG_DYNAMIC_DEBUG) || \ (defined(CONFIG_DYNAMIC_DEBUG_CORE) && defined(DYNAMIC_DEBUG_MODULE)) /* Usage: See admin-guide/dynamic-debug-howto.rst */ @@ -9101,7 +9096,7 @@ static inline void alloc_contig_dump_pages(struct list_head *page_list) #endif /* [start, end) must belong to a single zone. */ -static int __alloc_contig_migrate_range(struct compact_control *cc, +int __alloc_contig_migrate_range(struct compact_control *cc, unsigned long start, unsigned long end) { /* This function is based on compact_zone() from compaction.c. */ @@ -9151,7 +9146,7 @@ static int __alloc_contig_migrate_range(struct compact_control *cc, lru_cache_enable(); if (ret < 0) { - if (ret == -EBUSY) + if (!(cc->gfp_mask & __GFP_NOWARN) && ret == -EBUSY) alloc_contig_dump_pages(&cc->migratepages); putback_movable_pages(&cc->migratepages); return ret; @@ -9169,8 +9164,8 @@ static int __alloc_contig_migrate_range(struct compact_control *cc, * be either of the two. * @gfp_mask: GFP mask to use during compaction * - * The PFN range does not have to be pageblock or MAX_ORDER_NR_PAGES - * aligned. The PFN range must belong to a single zone. + * The PFN range does not have to be pageblock aligned. The PFN range must + * belong to a single zone. * * The first thing this routine does is attempt to MIGRATE_ISOLATE all * pageblocks in the range. Once isolated, the pageblocks should not @@ -9184,7 +9179,7 @@ int alloc_contig_range(unsigned long start, unsigned long end, unsigned migratetype, gfp_t gfp_mask) { unsigned long outer_start, outer_end; - unsigned int order; + int order; int ret = 0; struct compact_control cc = { @@ -9203,14 +9198,11 @@ int alloc_contig_range(unsigned long start, unsigned long end, * What we do here is we mark all pageblocks in range as * MIGRATE_ISOLATE. Because pageblock and max order pages may * have different sizes, and due to the way page allocator - * work, we align the range to biggest of the two pages so - * that page allocator won't try to merge buddies from - * different pageblocks and change MIGRATE_ISOLATE to some - * other migration type. + * work, start_isolate_page_range() has special handlings for this. * * Once the pageblocks are marked as MIGRATE_ISOLATE, we * migrate the pages from an unaligned range (ie. pages that - * we are interested in). This will put all the pages in + * we are interested in). This will put all the pages in * range back to page allocator as MIGRATE_ISOLATE. * * When this is done, we take the pages in range from page @@ -9223,10 +9215,9 @@ 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(pfn_max_align_down(start), - pfn_max_align_up(end), migratetype, 0); + ret = start_isolate_page_range(start, end, migratetype, 0, gfp_mask); if (ret) - return ret; + goto done; drain_all_pages(cc.zone); @@ -9246,7 +9237,7 @@ int alloc_contig_range(unsigned long start, unsigned long end, ret = 0; /* - * Pages from [start, end) are within a MAX_ORDER_NR_PAGES + * Pages from [start, end) are within a pageblock_nr_pages * aligned blocks that are marked as MIGRATE_ISOLATE. What's * more, all pages in [start, end) are free in page allocator. * What we are going to do is to allocate all pages from @@ -9305,8 +9296,7 @@ int alloc_contig_range(unsigned long start, unsigned long end, free_contig_range(end, outer_end - end); done: - undo_isolate_page_range(pfn_max_align_down(start), - pfn_max_align_up(end), migratetype); + undo_isolate_page_range(start, end, migratetype); return ret; } EXPORT_SYMBOL(alloc_contig_range); @@ -9625,7 +9615,6 @@ bool put_page_back_buddy(struct page *page) ClearPageHWPoisonTakenOff(page); __free_one_page(page, pfn, zone, 0, migratetype, FPI_NONE); if (TestClearPageHWPoison(page)) { - num_poisoned_pages_dec(); ret = true; } } |