diff options
Diffstat (limited to '')
| -rw-r--r-- | mm/page_alloc.c | 4634 |
1 files changed, 2791 insertions, 1843 deletions
diff --git a/mm/page_alloc.c b/mm/page_alloc.c index 3c4eb750a199..218b28ee49ed 100644 --- a/mm/page_alloc.c +++ b/mm/page_alloc.c @@ -19,6 +19,7 @@ #include <linux/mm.h> #include <linux/highmem.h> #include <linux/swap.h> +#include <linux/swapops.h> #include <linux/interrupt.h> #include <linux/pagemap.h> #include <linux/jiffies.h> @@ -26,6 +27,7 @@ #include <linux/compiler.h> #include <linux/kernel.h> #include <linux/kasan.h> +#include <linux/kmsan.h> #include <linux/module.h> #include <linux/suspend.h> #include <linux/pagevec.h> @@ -57,28 +59,165 @@ #include <trace/events/oom.h> #include <linux/prefetch.h> #include <linux/mm_inline.h> +#include <linux/mmu_notifier.h> #include <linux/migrate.h> #include <linux/hugetlb.h> #include <linux/sched/rt.h> #include <linux/sched/mm.h> #include <linux/page_owner.h> +#include <linux/page_table_check.h> #include <linux/kthread.h> #include <linux/memcontrol.h> #include <linux/ftrace.h> #include <linux/lockdep.h> #include <linux/nmi.h> #include <linux/psi.h> - +#include <linux/padata.h> +#include <linux/khugepaged.h> +#include <linux/buffer_head.h> +#include <linux/delayacct.h> #include <asm/sections.h> #include <asm/tlbflush.h> #include <asm/div64.h> #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; + +/* No special request */ +#define FPI_NONE ((__force fpi_t)0) + +/* + * Skip free page reporting notification for the (possibly merged) page. + * This does not hinder free page reporting from grabbing the page, + * reporting it and marking it "reported" - it only skips notifying + * the free page reporting infrastructure about a newly freed page. For + * example, used when temporarily pulling a page from a freelist and + * putting it back unmodified. + */ +#define FPI_SKIP_REPORT_NOTIFY ((__force fpi_t)BIT(0)) + +/* + * Place the (possibly merged) page to the tail of the freelist. Will ignore + * page shuffling (relevant code - e.g., memory onlining - is expected to + * shuffle the whole zone). + * + * Note: No code should rely on this flag for correctness - it's purely + * to allow for optimizations when handing back either fresh pages + * (memory onlining) or untouched pages (page isolation, free page + * reporting). + */ +#define FPI_TO_TAIL ((__force fpi_t)BIT(1)) + +/* + * Don't poison memory with KASAN (only for the tag-based modes). + * During boot, all non-reserved memblock memory is exposed to page_alloc. + * Poisoning all that memory lengthens boot time, especially on systems with + * large amount of RAM. This flag is used to skip that poisoning. + * This is only done for the tag-based KASAN modes, as those are able to + * detect memory corruptions with the memory tags assigned by default. + * All memory allocated normally after boot gets poisoned as usual. + */ +#define FPI_SKIP_KASAN_POISON ((__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_FRACTION (8) +#define MIN_PERCPU_PAGELIST_HIGH_FRACTION (8) +#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); @@ -95,16 +234,9 @@ DEFINE_STATIC_KEY_TRUE(vm_numa_stat_key); */ DEFINE_PER_CPU(int, _numa_mem_); /* Kernel "local memory" node */ EXPORT_PER_CPU_SYMBOL(_numa_mem_); -int _node_numa_mem_[MAX_NUMNODES]; #endif -/* work_structs for global per-cpu drains */ -struct pcpu_drain { - struct zone *zone; - struct work_struct work; -}; -DEFINE_MUTEX(pcpu_drain_mutex); -DEFINE_PER_CPU(struct pcpu_drain, pcpu_drain); +static DEFINE_MUTEX(pcpu_drain_mutex); #ifdef CONFIG_GCC_PLUGIN_LATENT_ENTROPY volatile unsigned long latent_entropy __latent_entropy; @@ -133,55 +265,28 @@ EXPORT_SYMBOL(_totalram_pages); unsigned long totalreserve_pages __read_mostly; unsigned long totalcma_pages __read_mostly; -int percpu_pagelist_fraction; +int percpu_pagelist_high_fraction; gfp_t gfp_allowed_mask __read_mostly = GFP_BOOT_MASK; -#ifdef CONFIG_INIT_ON_ALLOC_DEFAULT_ON -DEFINE_STATIC_KEY_TRUE(init_on_alloc); -#else -DEFINE_STATIC_KEY_FALSE(init_on_alloc); -#endif +DEFINE_STATIC_KEY_MAYBE(CONFIG_INIT_ON_ALLOC_DEFAULT_ON, init_on_alloc); EXPORT_SYMBOL(init_on_alloc); -#ifdef CONFIG_INIT_ON_FREE_DEFAULT_ON -DEFINE_STATIC_KEY_TRUE(init_on_free); -#else -DEFINE_STATIC_KEY_FALSE(init_on_free); -#endif +DEFINE_STATIC_KEY_MAYBE(CONFIG_INIT_ON_FREE_DEFAULT_ON, init_on_free); EXPORT_SYMBOL(init_on_free); +static bool _init_on_alloc_enabled_early __read_mostly + = IS_ENABLED(CONFIG_INIT_ON_ALLOC_DEFAULT_ON); static int __init early_init_on_alloc(char *buf) { - int ret; - bool bool_result; - if (!buf) - return -EINVAL; - ret = kstrtobool(buf, &bool_result); - if (bool_result && page_poisoning_enabled()) - pr_info("mem auto-init: CONFIG_PAGE_POISONING is on, will take precedence over init_on_alloc\n"); - if (bool_result) - static_branch_enable(&init_on_alloc); - else - static_branch_disable(&init_on_alloc); - return ret; + return kstrtobool(buf, &_init_on_alloc_enabled_early); } early_param("init_on_alloc", early_init_on_alloc); +static bool _init_on_free_enabled_early __read_mostly + = IS_ENABLED(CONFIG_INIT_ON_FREE_DEFAULT_ON); static int __init early_init_on_free(char *buf) { - int ret; - bool bool_result; - - if (!buf) - return -EINVAL; - ret = kstrtobool(buf, &bool_result); - if (bool_result && page_poisoning_enabled()) - pr_info("mem auto-init: CONFIG_PAGE_POISONING is on, will take precedence over init_on_free\n"); - if (bool_result) - static_branch_enable(&init_on_free); - else - static_branch_disable(&init_on_free); - return ret; + return kstrtobool(buf, &_init_on_free_enabled_early); } early_param("init_on_free", early_init_on_free); @@ -245,7 +350,8 @@ bool pm_suspended_storage(void) unsigned int pageblock_order __read_mostly; #endif -static void __free_pages_ok(struct page *page, unsigned int order); +static void __free_pages_ok(struct page *page, unsigned int order, + fpi_t fpi_flags); /* * results with 256, 32 in the lowmem_reserve sysctl: @@ -302,40 +408,26 @@ const char * const migratetype_names[MIGRATE_TYPES] = { #endif }; -compound_page_dtor * const compound_page_dtors[] = { - NULL, - free_compound_page, +compound_page_dtor * const compound_page_dtors[NR_COMPOUND_DTORS] = { + [NULL_COMPOUND_DTOR] = NULL, + [COMPOUND_PAGE_DTOR] = free_compound_page, #ifdef CONFIG_HUGETLB_PAGE - free_huge_page, + [HUGETLB_PAGE_DTOR] = free_huge_page, #endif #ifdef CONFIG_TRANSPARENT_HUGEPAGE - free_transhuge_page, + [TRANSHUGE_PAGE_DTOR] = free_transhuge_page, #endif }; int min_free_kbytes = 1024; int user_min_free_kbytes = -1; -#ifdef CONFIG_DISCONTIGMEM -/* - * DiscontigMem defines memory ranges as separate pg_data_t even if the ranges - * are not on separate NUMA nodes. Functionally this works but with - * watermark_boost_factor, it can reclaim prematurely as the ranges can be - * quite small. By default, do not boost watermarks on discontigmem as in - * many cases very high-order allocations like THP are likely to be - * unsupported and the premature reclaim offsets the advantage of long-term - * fragmentation avoidance. - */ -int watermark_boost_factor __read_mostly; -#else int watermark_boost_factor __read_mostly = 15000; -#endif int watermark_scale_factor = 10; static unsigned long nr_kernel_pages __initdata; static unsigned long nr_all_pages __initdata; static unsigned long dma_reserve __initdata; -#ifdef CONFIG_HAVE_MEMBLOCK_NODE_MAP static unsigned long arch_zone_lowest_possible_pfn[MAX_NR_ZONES] __initdata; static unsigned long arch_zone_highest_possible_pfn[MAX_NR_ZONES] __initdata; static unsigned long required_kernelcore __initdata; @@ -343,12 +435,11 @@ 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; EXPORT_SYMBOL(movable_zone); -#endif /* CONFIG_HAVE_MEMBLOCK_NODE_MAP */ #if MAX_NUMNODES > 1 unsigned int nr_node_ids __read_mostly = MAX_NUMNODES; @@ -367,23 +458,9 @@ int page_group_by_mobility_disabled __read_mostly; */ static DEFINE_STATIC_KEY_TRUE(deferred_pages); -/* - * Calling kasan_free_pages() only after deferred memory initialization - * has completed. Poisoning pages during deferred memory init will greatly - * lengthen the process and cause problem in large memory systems as the - * deferred pages initialization is done with interrupt disabled. - * - * Assuming that there will be no reference to those newly initialized - * pages before they are ever allocated, this should have no effect on - * KASAN memory tracking as the poison will be properly inserted at page - * allocation time. The only corner case is when pages are allocated by - * on-demand allocation and then freed again before the deferred pages - * initialization is done, but this is not likely to happen. - */ -static inline void kasan_free_nondeferred_pages(struct page *page, int order) +static inline bool deferred_pages_enabled(void) { - if (!static_branch_unlikely(&deferred_pages)) - kasan_free_pages(page, order); + return static_branch_unlikely(&deferred_pages); } /* Returns true if the struct page for the pfn is uninitialised */ @@ -406,6 +483,8 @@ defer_init(int nid, unsigned long pfn, unsigned long end_pfn) { static unsigned long prev_end_pfn, nr_initialised; + if (early_page_ext_enabled()) + return false; /* * prev_end_pfn static that contains the end of previous zone * No need to protect because called very early in boot before smp_init. @@ -419,6 +498,8 @@ defer_init(int nid, unsigned long pfn, unsigned long end_pfn) if (end_pfn < pgdat_end_pfn(NODE_DATA(nid))) return false; + if (NODE_DATA(nid)->first_deferred_pfn != ULONG_MAX) + return true; /* * We start only with one section of pages, more pages are added as * needed until the rest of deferred pages are initialized. @@ -432,7 +513,10 @@ defer_init(int nid, unsigned long pfn, unsigned long end_pfn) return false; } #else -#define kasan_free_nondeferred_pages(p, o) kasan_free_pages(p, o) +static inline bool deferred_pages_enabled(void) +{ + return false; +} static inline bool early_page_uninitialised(unsigned long pfn) { @@ -446,7 +530,7 @@ static inline bool defer_init(int nid, unsigned long pfn, unsigned long end_pfn) #endif /* Return a pointer to the bitmap storing bits affecting a block of pages */ -static inline unsigned long *get_pageblock_bitmap(struct page *page, +static inline unsigned long *get_pageblock_bitmap(const struct page *page, unsigned long pfn) { #ifdef CONFIG_SPARSEMEM @@ -456,29 +540,19 @@ static inline unsigned long *get_pageblock_bitmap(struct page *page, #endif /* CONFIG_SPARSEMEM */ } -static inline int pfn_to_bitidx(struct page *page, unsigned long pfn) +static inline int pfn_to_bitidx(const struct page *page, unsigned long pfn) { #ifdef CONFIG_SPARSEMEM pfn &= (PAGES_PER_SECTION-1); - return (pfn >> pageblock_order) * NR_PAGEBLOCK_BITS; #else - pfn = pfn - round_down(page_zone(page)->zone_start_pfn, pageblock_nr_pages); - return (pfn >> pageblock_order) * NR_PAGEBLOCK_BITS; + pfn = pfn - pageblock_start_pfn(page_zone(page)->zone_start_pfn); #endif /* CONFIG_SPARSEMEM */ + return (pfn >> pageblock_order) * NR_PAGEBLOCK_BITS; } -/** - * get_pfnblock_flags_mask - Return the requested group of flags for the pageblock_nr_pages block of pages - * @page: The page within the block of interest - * @pfn: The target page frame number - * @end_bitidx: The last bit of interest to retrieve - * @mask: mask of bits that the caller is interested in - * - * Return: pageblock_bits flags - */ -static __always_inline unsigned long __get_pfnblock_flags_mask(struct page *page, +static __always_inline +unsigned long __get_pfnblock_flags_mask(const struct page *page, unsigned long pfn, - unsigned long end_bitidx, unsigned long mask) { unsigned long *bitmap; @@ -489,22 +563,33 @@ static __always_inline unsigned long __get_pfnblock_flags_mask(struct page *page bitidx = pfn_to_bitidx(page, pfn); word_bitidx = bitidx / BITS_PER_LONG; bitidx &= (BITS_PER_LONG-1); - - word = bitmap[word_bitidx]; - bitidx += end_bitidx; - return (word >> (BITS_PER_LONG - bitidx - 1)) & mask; + /* + * 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; } -unsigned long get_pfnblock_flags_mask(struct page *page, unsigned long pfn, - unsigned long end_bitidx, - unsigned long mask) +/** + * get_pfnblock_flags_mask - Return the requested group of flags for the pageblock_nr_pages block of pages + * @page: The page within the block of interest + * @pfn: The target page frame number + * @mask: mask of bits that the caller is interested in + * + * Return: pageblock_bits flags + */ +unsigned long get_pfnblock_flags_mask(const struct page *page, + unsigned long pfn, unsigned long mask) { - return __get_pfnblock_flags_mask(page, pfn, end_bitidx, mask); + return __get_pfnblock_flags_mask(page, pfn, mask); } -static __always_inline int get_pfnblock_migratetype(struct page *page, unsigned long pfn) +static __always_inline int get_pfnblock_migratetype(const struct page *page, + unsigned long pfn) { - return __get_pfnblock_flags_mask(page, pfn, PB_migrate_end, MIGRATETYPE_MASK); + return __get_pfnblock_flags_mask(page, pfn, MIGRATETYPE_MASK); } /** @@ -512,17 +597,15 @@ static __always_inline int get_pfnblock_migratetype(struct page *page, unsigned * @page: The page within the block of interest * @flags: The flags to set * @pfn: The target page frame number - * @end_bitidx: The last bit of interest * @mask: mask of bits that the caller is interested in */ void set_pfnblock_flags_mask(struct page *page, unsigned long flags, unsigned long pfn, - unsigned long end_bitidx, unsigned long mask) { 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)); @@ -534,17 +617,12 @@ void set_pfnblock_flags_mask(struct page *page, unsigned long flags, VM_BUG_ON_PAGE(!zone_spans_pfn(page_zone(page), pfn), page); - bitidx += end_bitidx; - mask <<= (BITS_PER_LONG - bitidx - 1); - flags <<= (BITS_PER_LONG - bitidx - 1); + mask <<= bitidx; + 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) @@ -553,8 +631,8 @@ void set_pageblock_migratetype(struct page *page, int migratetype) migratetype < MIGRATE_PCPTYPES)) migratetype = MIGRATE_UNMOVABLE; - set_pageblock_flags_group(page, (unsigned long)migratetype, - PB_migrate, PB_migrate_end); + set_pfnblock_flags_mask(page, (unsigned long)migratetype, + page_to_pfn(page), MIGRATETYPE_MASK); } #ifdef CONFIG_DEBUG_VM @@ -583,8 +661,6 @@ static int page_outside_zone_boundaries(struct zone *zone, struct page *page) static int page_is_consistent(struct zone *zone, struct page *page) { - if (!pfn_valid_within(page_to_pfn(page))) - return 0; if (zone != page_zone(page)) return 0; @@ -609,8 +685,7 @@ static inline int __maybe_unused bad_range(struct zone *zone, struct page *page) } #endif -static void bad_page(struct page *page, const char *reason, - unsigned long bad_flags) +static void bad_page(struct page *page, const char *reason) { static unsigned long resume; static unsigned long nr_shown; @@ -638,12 +713,7 @@ static void bad_page(struct page *page, const char *reason, pr_alert("BUG: Bad page state in process %s pfn:%05lx\n", current->comm, page_to_pfn(page)); - __dump_page(page, reason); - bad_flags &= page->flags; - if (bad_flags) - pr_alert("bad because of flags: %#lx(%pGp)\n", - bad_flags, &bad_flags); - dump_page_owner(page); + dump_page(page, reason); print_modules(); dump_stack(); @@ -653,6 +723,55 @@ out: add_taint(TAINT_BAD_PAGE, LOCKDEP_NOW_UNRELIABLE); } +static inline unsigned int order_to_pindex(int migratetype, int order) +{ + int base = order; + +#ifdef CONFIG_TRANSPARENT_HUGEPAGE + if (order > PAGE_ALLOC_COSTLY_ORDER) { + VM_BUG_ON(order != pageblock_order); + return NR_LOWORDER_PCP_LISTS; + } +#else + VM_BUG_ON(order > PAGE_ALLOC_COSTLY_ORDER); +#endif + + return (MIGRATE_PCPTYPES * base) + migratetype; +} + +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; +#else + VM_BUG_ON(order > PAGE_ALLOC_COSTLY_ORDER); +#endif + + return order; +} + +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) + 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: * @@ -670,8 +789,25 @@ out: void free_compound_page(struct page *page) { - mem_cgroup_uncharge(page); - __free_pages_ok(page, compound_order(page)); + mem_cgroup_uncharge(page_folio(page)); + free_the_page(page, compound_order(page)); +} + +static void prep_compound_head(struct page *page, unsigned int order) +{ + set_compound_page_dtor(page, COMPOUND_PAGE_DTOR); + set_compound_order(page, order); + atomic_set(compound_mapcount_ptr(page), -1); + atomic_set(compound_pincount_ptr(page), 0); +} + +static void prep_compound_tail(struct page *head, int tail_idx) +{ + struct page *p = head + tail_idx; + + p->mapping = TAIL_MAPPING; + set_compound_head(p, head); + set_page_private(p, 0); } void prep_compound_page(struct page *page, unsigned int order) @@ -679,16 +815,19 @@ void prep_compound_page(struct page *page, unsigned int order) int i; int nr_pages = 1 << order; - set_compound_page_dtor(page, COMPOUND_PAGE_DTOR); - set_compound_order(page, order); __SetPageHead(page); - for (i = 1; i < nr_pages; i++) { - struct page *p = page + i; - set_page_count(p, 0); - p->mapping = TAIL_MAPPING; - set_compound_head(p, page); - } - atomic_set(compound_mapcount_ptr(page), -1); + for (i = 1; i < nr_pages; i++) + prep_compound_tail(page, i); + + 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 @@ -708,19 +847,6 @@ static int __init early_debug_pagealloc(char *buf) } early_param("debug_pagealloc", early_debug_pagealloc); -void init_debug_pagealloc(void) -{ - if (!debug_pagealloc_enabled()) - return; - - static_branch_enable(&_debug_pagealloc_enabled); - - if (!debug_guardpage_minorder()) - return; - - static_branch_enable(&_debug_guardpage_enabled); -} - static int __init debug_guardpage_minorder_setup(char *buf) { unsigned long res; @@ -745,10 +871,11 @@ 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); + if (!is_migrate_isolate(migratetype)) + __mod_zone_freepage_state(zone, -(1 << order), migratetype); return true; } @@ -772,51 +899,68 @@ static inline void clear_page_guard(struct zone *zone, struct page *page, unsigned int order, int migratetype) {} #endif -static inline void set_page_order(struct page *page, unsigned int order) -{ - set_page_private(page, 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). + * Enable static keys related to various memory debugging and hardening options. + * Some override others, and depend on early params that are evaluated in the + * order of appearance. So we need to first gather the full picture of what was + * enabled, and then make decisions. */ -static inline int page_is_buddy(struct page *page, struct page *buddy, - unsigned int order) +void __init init_mem_debugging_and_hardening(void) { - if (page_is_guard(buddy) && page_order(buddy) == order) { - if (page_zone_id(page) != page_zone_id(buddy)) - return 0; + bool page_poisoning_requested = false; - VM_BUG_ON_PAGE(page_count(buddy) != 0, buddy); +#ifdef CONFIG_PAGE_POISONING + /* + * Page poisoning is debug page alloc for some arches. If + * either of those options are enabled, enable poisoning. + */ + if (page_poisoning_enabled() || + (!IS_ENABLED(CONFIG_ARCH_SUPPORTS_DEBUG_PAGEALLOC) && + debug_pagealloc_enabled())) { + static_branch_enable(&_page_poisoning_enabled); + page_poisoning_requested = true; + } +#endif - return 1; + if ((_init_on_alloc_enabled_early || _init_on_free_enabled_early) && + page_poisoning_requested) { + pr_info("mem auto-init: CONFIG_PAGE_POISONING is on, " + "will take precedence over init_on_alloc and init_on_free\n"); + _init_on_alloc_enabled_early = false; + _init_on_free_enabled_early = false; } - if (PageBuddy(buddy) && page_order(buddy) == order) { - /* - * 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 0; + if (_init_on_alloc_enabled_early) + static_branch_enable(&init_on_alloc); + else + static_branch_disable(&init_on_alloc); - VM_BUG_ON_PAGE(page_count(buddy) != 0, buddy); + if (_init_on_free_enabled_early) + static_branch_enable(&init_on_free); + else + static_branch_disable(&init_on_free); - return 1; - } - return 0; + if (IS_ENABLED(CONFIG_KMSAN) && + (_init_on_alloc_enabled_early || _init_on_free_enabled_early)) + pr_info("mem auto-init: please make sure init_on_alloc and init_on_free are disabled when running KMSAN\n"); + +#ifdef CONFIG_DEBUG_PAGEALLOC + if (!debug_pagealloc_enabled()) + return; + + static_branch_enable(&_debug_pagealloc_enabled); + + if (!debug_guardpage_minorder()) + return; + + static_branch_enable(&_debug_guardpage_enabled); +#endif +} + +static inline void set_buddy_order(struct page *page, unsigned int order) +{ + set_page_private(page, order); + __SetPageBuddy(page); } #ifdef CONFIG_COMPACTION @@ -824,11 +968,10 @@ static inline struct capture_control *task_capc(struct zone *zone) { struct capture_control *capc = current->capture_control; - return capc && + return unlikely(capc) && !(current->flags & PF_KTHREAD) && !capc->page && - capc->cc->zone == zone && - capc->cc->direct_compaction ? capc : NULL; + capc->cc->zone == zone ? capc : NULL; } static inline bool @@ -844,7 +987,7 @@ compaction_capture(struct capture_control *capc, struct page *page, return false; /* - * Do not let lower order allocations polluate a movable pageblock. + * Do not let lower order allocations pollute a movable pageblock. * 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. @@ -870,6 +1013,77 @@ 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) +{ + struct free_area *area = &zone->free_area[order]; + + list_add(&page->buddy_list, &area->free_list[migratetype]); + area->nr_free++; +} + +/* 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) +{ + struct free_area *area = &zone->free_area[order]; + + list_add_tail(&page->buddy_list, &area->free_list[migratetype]); + area->nr_free++; +} + +/* + * Used for pages which are on another list. Move the pages to the tail + * of the list - so the moved pages won't immediately be considered for + * 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) +{ + struct free_area *area = &zone->free_area[order]; + + list_move_tail(&page->buddy_list, &area->free_list[migratetype]); +} + +static inline void del_page_from_free_list(struct page *page, struct zone *zone, + unsigned int order) +{ + /* clear reported state and update reported page count */ + if (page_reported(page)) + __ClearPageReported(page); + + list_del(&page->buddy_list); + __ClearPageBuddy(page); + set_page_private(page, 0); + zone->free_area[order].nr_free--; +} + +/* + * 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 + * 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 + */ +static inline bool +buddy_merge_likely(unsigned long pfn, unsigned long buddy_pfn, + struct page *page, unsigned int order) +{ + unsigned long higher_page_pfn; + struct page *higher_page; + + if (order >= MAX_ORDER - 2) + return false; + + higher_page_pfn = buddy_pfn & pfn; + higher_page = page + (higher_page_pfn - pfn); + + return find_buddy_page_pfn(higher_page, higher_page_pfn, order + 1, + NULL) != NULL; +} + /* * Freeing function for a buddy system allocator. * @@ -897,15 +1111,13 @@ compaction_capture(struct capture_control *capc, struct page *page, static inline void __free_one_page(struct page *page, unsigned long pfn, struct zone *zone, unsigned int order, - int migratetype) + int migratetype, fpi_t fpi_flags) { + struct capture_control *capc = task_capc(zone); + unsigned long buddy_pfn = 0; unsigned long combined_pfn; - unsigned long uninitialized_var(buddy_pfn); struct page *buddy; - unsigned int max_order; - struct capture_control *capc = task_capc(zone); - - max_order = min_t(unsigned int, MAX_ORDER, pageblock_order + 1); + bool to_tail; VM_BUG_ON(!zone_is_initialized(zone)); VM_BUG_ON_PAGE(page->flags & PAGE_FLAGS_CHECK_AT_PREP, page); @@ -917,20 +1129,32 @@ 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 - 1) { + 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 (!pfn_valid_within(buddy_pfn)) - goto done_merging; - 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. @@ -938,71 +1162,91 @@ continue_merging: if (page_is_guard(buddy)) clear_page_guard(zone, buddy, order, migratetype); else - del_page_from_free_area(buddy, &zone->free_area[order]); + del_page_from_free_list(buddy, zone, order); combined_pfn = buddy_pfn & pfn; page = page + (combined_pfn - pfn); pfn = combined_pfn; order++; } - if (max_order < MAX_ORDER) { - /* If we are here, it means order is >= pageblock_order. - * We want to prevent merge between freepages on isolate - * pageblock and normal pageblock. Without this, pageblock - * isolation could cause incorrect freepage or CMA accounting. - * - * We don't want to hit this code for the more frequent - * low-order merging. - */ - if (unlikely(has_isolate_pageblock(zone))) { - int buddy_mt; - - buddy_pfn = __find_buddy_pfn(pfn, order); - buddy = page + (buddy_pfn - pfn); - buddy_mt = get_pageblock_migratetype(buddy); - - if (migratetype != buddy_mt - && (is_migrate_isolate(migratetype) || - is_migrate_isolate(buddy_mt))) - goto done_merging; - } - max_order++; - goto continue_merging; - } done_merging: - set_page_order(page, order); + set_buddy_order(page, order); - /* - * 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 - * 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 - */ - if ((order < MAX_ORDER-2) && pfn_valid_within(buddy_pfn) - && !is_shuffle_order(order)) { - struct page *higher_page, *higher_buddy; - 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); - if (pfn_valid_within(buddy_pfn) && - page_is_buddy(higher_page, higher_buddy, order + 1)) { - add_to_free_area_tail(page, &zone->free_area[order], - migratetype); - return; - } - } + if (fpi_flags & FPI_TO_TAIL) + to_tail = true; + else if (is_shuffle_order(order)) + to_tail = shuffle_pick_tail(); + else + to_tail = buddy_merge_likely(pfn, buddy_pfn, page, order); - if (is_shuffle_order(order)) - add_to_free_area_random(page, &zone->free_area[order], - migratetype); + if (to_tail) + add_to_free_list_tail(page, zone, order, migratetype); else - add_to_free_area(page, &zone->free_area[order], migratetype); + add_to_free_list(page, zone, order, migratetype); + /* 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_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 @@ -1017,7 +1261,7 @@ static inline bool page_expected_state(struct page *page, if (unlikely((unsigned long)page->mapping | page_ref_count(page) | #ifdef CONFIG_MEMCG - (unsigned long)page->mem_cgroup | + page->memcg_data | #endif (page->flags & check_flags))) return false; @@ -1025,13 +1269,9 @@ static inline bool page_expected_state(struct page *page, return true; } -static void free_pages_check_bad(struct page *page) +static const char *page_bad_reason(struct page *page, unsigned long flags) { - const char *bad_reason; - unsigned long bad_flags; - - bad_reason = NULL; - bad_flags = 0; + const char *bad_reason = NULL; if (unlikely(atomic_read(&page->_mapcount) != -1)) bad_reason = "nonzero mapcount"; @@ -1039,25 +1279,33 @@ static void free_pages_check_bad(struct page *page) bad_reason = "non-NULL mapping"; if (unlikely(page_ref_count(page) != 0)) bad_reason = "nonzero _refcount"; - if (unlikely(page->flags & PAGE_FLAGS_CHECK_AT_FREE)) { - bad_reason = "PAGE_FLAGS_CHECK_AT_FREE flag(s) set"; - bad_flags = PAGE_FLAGS_CHECK_AT_FREE; + if (unlikely(page->flags & flags)) { + if (flags == PAGE_FLAGS_CHECK_AT_PREP) + bad_reason = "PAGE_FLAGS_CHECK_AT_PREP flag(s) set"; + else + bad_reason = "PAGE_FLAGS_CHECK_AT_FREE flag(s) set"; } #ifdef CONFIG_MEMCG - if (unlikely(page->mem_cgroup)) + if (unlikely(page->memcg_data)) bad_reason = "page still charged to cgroup"; #endif - bad_page(page, bad_reason, bad_flags); + return bad_reason; } -static inline int free_pages_check(struct page *page) +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 0; + return false; /* Something has gone sideways, find it */ - free_pages_check_bad(page); - return 1; + free_page_is_bad_report(page); + return true; } static int free_tail_pages_check(struct page *head_page, struct page *page) @@ -1078,7 +1326,7 @@ static int free_tail_pages_check(struct page *head_page, struct page *page) case 1: /* the first tail page: ->mapping may be compound_mapcount() */ if (unlikely(compound_mapcount(page))) { - bad_page(page, "nonzero compound_mapcount", 0); + bad_page(page, "nonzero compound_mapcount"); goto out; } break; @@ -1090,17 +1338,17 @@ static int free_tail_pages_check(struct page *head_page, struct page *page) break; default: if (page->mapping != TAIL_MAPPING) { - bad_page(page, "corrupted mapping in tail page", 0); + bad_page(page, "corrupted mapping in tail page"); goto out; } break; } if (unlikely(!PageTail(page))) { - bad_page(page, "PageTail not set", 0); + bad_page(page, "PageTail not set"); goto out; } if (unlikely(compound_head(page) != head_page)) { - bad_page(page, "compound_head not consistent", 0); + bad_page(page, "compound_head not consistent"); goto out; } ret = 0; @@ -1110,22 +1358,68 @@ out: return ret; } -static void kernel_init_free_pages(struct page *page, int numpages) +/* + * Skip KASAN memory poisoning when either: + * + * 1. Deferred memory initialization has not yet completed, + * see the explanation below. + * 2. Skipping poisoning is requested via FPI_SKIP_KASAN_POISON, + * see the comment next to it. + * 3. Skipping poisoning is requested via __GFP_SKIP_KASAN_POISON, + * see the comment next to it. + * + * Poisoning pages during deferred memory init will greatly lengthen the + * process and cause problem in large memory systems as the deferred pages + * initialization is done with interrupt disabled. + * + * Assuming that there will be no reference to those newly initialized + * pages before they are ever allocated, this should have no effect on + * KASAN memory tracking as the poison will be properly inserted at page + * allocation time. The only corner case is when pages are allocated by + * on-demand allocation and then freed again before the deferred pages + * initialization is done, but this is not likely to happen. + */ +static inline bool should_skip_kasan_poison(struct page *page, fpi_t fpi_flags) +{ + return deferred_pages_enabled() || + (!IS_ENABLED(CONFIG_KASAN_GENERIC) && + (fpi_flags & FPI_SKIP_KASAN_POISON)) || + PageSkipKASanPoison(page); +} + +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++) - clear_highpage(page + i); + clear_highpage_kasan_tagged(page + i); + kasan_enable_current(); } static __always_inline bool free_pages_prepare(struct page *page, - unsigned int order, bool check_free) + unsigned int order, bool check_free, fpi_t fpi_flags) { int bad = 0; + bool init = want_init_on_free(); VM_BUG_ON_PAGE(PageTail(page), page); trace_mm_page_free(page, order); + kmsan_free_page(page, order); + + if (unlikely(PageHWPoison(page)) && !order) { + /* + * Do not let hwpoison pages hit pcplists/buddy + * Untie memcg state and reset page's owner + */ + if (memcg_kmem_enabled() && PageMemcgKmem(page)) + __memcg_kmem_uncharge_page(page, order); + reset_page_owner(page, order); + page_table_check_free(page, order); + return false; + } /* * Check tail pages before head page information is cleared to @@ -1137,12 +1431,14 @@ static __always_inline bool free_pages_prepare(struct page *page, VM_BUG_ON_PAGE(compound && compound_order(page) != order, page); - if (compound) + if (compound) { ClearPageDoubleMap(page); + ClearPageHasHWPoisoned(page); + } for (i = 1; i < (1 << order); i++) { if (compound) bad += free_tail_pages_check(page, page + i); - if (unlikely(free_pages_check(page + i))) { + if (unlikely(free_page_is_bad(page + i))) { bad++; continue; } @@ -1151,16 +1447,17 @@ static __always_inline bool free_pages_prepare(struct page *page, } if (PageMappingFlags(page)) page->mapping = NULL; - if (memcg_kmem_enabled() && PageKmemcg(page)) - __memcg_kmem_uncharge(page, order); - if (check_free) - bad += free_pages_check(page); + if (memcg_kmem_enabled() && PageMemcgKmem(page)) + __memcg_kmem_uncharge_page(page, order); + if (check_free && free_page_is_bad(page)) + bad++; if (bad) return false; page_cpupid_reset_last(page); page->flags &= ~PAGE_FLAGS_CHECK_AT_PREP; reset_page_owner(page, order); + page_table_check_free(page, order); if (!PageHighMem(page)) { debug_check_no_locks_freed(page_address(page), @@ -1168,10 +1465,27 @@ static __always_inline bool free_pages_prepare(struct page *page, debug_check_no_obj_freed(page_address(page), PAGE_SIZE << order); } - if (want_init_on_free()) - kernel_init_free_pages(page, 1 << order); - kernel_poison_pages(page, 1 << order, 0); + kernel_poison_pages(page, 1 << order); + + /* + * As memory initialization might be integrated into KASAN, + * KASAN poisoning and memory initialization code must be + * kept together to avoid discrepancies in behavior. + * + * With hardware tag-based KASAN, memory tags must be set before the + * page becomes unavailable via debug_pagealloc or arch_free_page. + */ + if (!should_skip_kasan_poison(page, fpi_flags)) { + kasan_poison_pages(page, order, init); + + /* Memory is already initialized if KASAN did it internally. */ + if (kasan_has_integrated_init()) + init = false; + } + if (init) + kernel_init_pages(page, 1 << order); + /* * arch_free_page() can make the page's contents inaccessible. s390 * does this. So nothing which can access the page's contents should @@ -1179,10 +1493,7 @@ static __always_inline bool free_pages_prepare(struct page *page, */ arch_free_page(page, order); - if (debug_pagealloc_enabled_static()) - kernel_map_pages(page, 1 << order, 0); - - kasan_free_nondeferred_pages(page, order); + debug_pagealloc_unmap_pages(page, 1 << order); return true; } @@ -1193,15 +1504,16 @@ static __always_inline bool free_pages_prepare(struct page *page, * to pcp lists. With debug_pagealloc also enabled, they are also rechecked when * moved from pcp lists to free lists. */ -static bool free_pcp_prepare(struct page *page) +static bool free_pcp_prepare(struct page *page, unsigned int order) { - return free_pages_prepare(page, 0, true); + return free_pages_prepare(page, order, true, FPI_NONE); } +/* return true if this page has an inappropriate state */ static bool bulkfree_pcp_prepare(struct page *page) { if (debug_pagealloc_enabled_static()) - return free_pages_check(page); + return free_page_is_bad(page); else return false; } @@ -1212,129 +1524,110 @@ static bool bulkfree_pcp_prepare(struct page *page) * debug_pagealloc enabled, they are checked also immediately when being freed * to the pcp lists. */ -static bool free_pcp_prepare(struct page *page) +static bool free_pcp_prepare(struct page *page, unsigned int order) { if (debug_pagealloc_enabled_static()) - return free_pages_prepare(page, 0, true); + return free_pages_prepare(page, order, true, FPI_NONE); else - return free_pages_prepare(page, 0, false); + return free_pages_prepare(page, order, false, FPI_NONE); } static bool bulkfree_pcp_prepare(struct page *page) { - return free_pages_check(page); + return free_page_is_bad(page); } #endif /* CONFIG_DEBUG_VM */ -static inline void prefetch_buddy(struct page *page) -{ - unsigned long pfn = page_to_pfn(page); - unsigned long buddy_pfn = __find_buddy_pfn(pfn, 0); - struct page *buddy = page + (buddy_pfn - pfn); - - prefetch(buddy); -} - /* * Frees a number of pages from the PCP lists - * Assumes all pages on list are in same zone, and of same order. + * Assumes all pages on list are in same zone. * count is the number of pages to free. - * - * If the zone was previously in an "all pages pinned" state then look to - * see if this freeing clears that state. - * - * And clear the zone's pages_scanned counter, to hold off the "all pages are - * pinned" detection logic. */ static void free_pcppages_bulk(struct zone *zone, int count, - struct per_cpu_pages *pcp) + struct per_cpu_pages *pcp, + int pindex) { - int migratetype = 0; - int batch_free = 0; - int prefetch_nr = 0; + int min_pindex = 0; + int max_pindex = NR_PCP_LISTS - 1; + unsigned int order; bool isolated_pageblocks; - struct page *page, *tmp; - LIST_HEAD(head); + struct page *page; + + /* + * Ensure proper count is passed which otherwise would stuck in the + * below while (list_empty(list)) loop. + */ + count = min(pcp->count, count); - while (count) { + /* Ensure requested pindex is drained first. */ + pindex = pindex - 1; + + /* Caller must hold IRQ-safe pcp->lock so IRQs are disabled. */ + spin_lock(&zone->lock); + isolated_pageblocks = has_isolate_pageblock(zone); + + while (count > 0) { struct list_head *list; + int nr_pages; - /* - * Remove pages from lists in a round-robin fashion. A - * batch_free count is maintained that is incremented when an - * empty list is encountered. This is so more pages are freed - * off fuller lists instead of spinning excessively around empty - * lists - */ + /* Remove pages from lists in a round-robin fashion. */ do { - batch_free++; - if (++migratetype == MIGRATE_PCPTYPES) - migratetype = 0; - list = &pcp->lists[migratetype]; - } while (list_empty(list)); + if (++pindex > max_pindex) + pindex = min_pindex; + list = &pcp->lists[pindex]; + if (!list_empty(list)) + break; - /* This is the only non-empty list. Free them all. */ - if (batch_free == MIGRATE_PCPTYPES) - batch_free = count; + if (pindex == max_pindex) + max_pindex--; + if (pindex == min_pindex) + min_pindex++; + } while (1); + order = pindex_to_order(pindex); + nr_pages = 1 << order; do { - page = list_last_entry(list, struct page, lru); + int mt; + + 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); - pcp->count--; + list_del(&page->pcp_list); + count -= nr_pages; + pcp->count -= nr_pages; if (bulkfree_pcp_prepare(page)) continue; - list_add_tail(&page->lru, &head); + /* 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); - /* - * We are going to put the page back to the global - * pool, prefetch its buddy to speed up later access - * under zone->lock. It is believed the overhead of - * an additional test and calculating buddy_pfn here - * can be offset by reduced memory latency later. To - * avoid excessive prefetching due to large count, only - * prefetch buddy for the first pcp->batch nr of pages. - */ - if (prefetch_nr++ < pcp->batch) - prefetch_buddy(page); - } while (--count && --batch_free && !list_empty(list)); + __free_one_page(page, page_to_pfn(page), zone, order, mt, FPI_NONE); + trace_mm_page_pcpu_drain(page, order, mt); + } while (count > 0 && !list_empty(list)); } - spin_lock(&zone->lock); - isolated_pageblocks = has_isolate_pageblock(zone); - - /* - * Use safe version since after __free_one_page(), - * page->lru.next will not point to original list. - */ - list_for_each_entry_safe(page, tmp, &head, lru) { - int mt = get_pcppage_migratetype(page); - /* 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, 0, mt); - trace_mm_page_pcpu_drain(page, 0, mt); - } spin_unlock(&zone->lock); } static void free_one_page(struct zone *zone, struct page *page, unsigned long pfn, unsigned int order, - int migratetype) + int migratetype, fpi_t fpi_flags) { - spin_lock(&zone->lock); + 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); } - __free_one_page(page, pfn, zone, order, migratetype); - spin_unlock(&zone->lock); + __free_one_page(page, pfn, zone, order, migratetype, fpi_flags); + spin_unlock_irqrestore(&zone->lock, flags); } static void __meminit __init_single_page(struct page *page, unsigned long pfn, @@ -1370,7 +1663,7 @@ static void __meminit init_reserved_page(unsigned long pfn) for (zid = 0; zid < MAX_NR_ZONES; zid++) { struct zone *zone = &pgdat->node_zones[zid]; - if (pfn >= zone->zone_start_pfn && pfn < zone_end_pfn(zone)) + if (zone_spans_pfn(zone, pfn)) break; } __init_single_page(pfn_to_page(pfn), pfn, zid, nid); @@ -1411,20 +1704,28 @@ void __meminit reserve_bootmem_region(phys_addr_t start, phys_addr_t end) } } -static void __free_pages_ok(struct page *page, unsigned int order) +static void __free_pages_ok(struct page *page, unsigned int order, + fpi_t fpi_flags) { unsigned long flags; int migratetype; unsigned long pfn = page_to_pfn(page); + struct zone *zone = page_zone(page); - if (!free_pages_prepare(page, order, true)) + if (!free_pages_prepare(page, order, true, fpi_flags)) return; migratetype = get_pfnblock_migratetype(page, pfn); - local_irq_save(flags); + + spin_lock_irqsave(&zone->lock, flags); + if (unlikely(has_isolate_pageblock(zone) || + is_migrate_isolate(migratetype))) { + migratetype = get_pfnblock_migratetype(page, pfn); + } + __free_one_page(page, pfn, zone, order, migratetype, fpi_flags); + spin_unlock_irqrestore(&zone->lock, flags); + __count_vm_events(PGFREE, 1 << order); - free_one_page(page_zone(page), page, pfn, order, migratetype); - local_irq_restore(flags); } void __free_pages_core(struct page *page, unsigned int order) @@ -1433,6 +1734,11 @@ void __free_pages_core(struct page *page, unsigned int order) struct page *p = page; unsigned int loop; + /* + * 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. + */ prefetchw(p); for (loop = 0; loop < (nr_pages - 1); loop++, p++) { prefetchw(p + 1); @@ -1443,64 +1749,82 @@ void __free_pages_core(struct page *page, unsigned int order) set_page_count(p, 0); atomic_long_add(nr_pages, &page_zone(page)->managed_pages); - set_page_refcounted(page); - __free_pages(page, order); + + /* + * Bypass PCP and place fresh pages right to the tail, primarily + * relevant for memory onlining. + */ + __free_pages_ok(page, order, FPI_TO_TAIL | FPI_SKIP_KASAN_POISON); } -#if defined(CONFIG_HAVE_ARCH_EARLY_PFN_TO_NID) || \ - defined(CONFIG_HAVE_MEMBLOCK_NODE_MAP) +#ifdef CONFIG_NUMA + +/* + * During memory init memblocks map pfns to nids. The search is expensive and + * this caches recent lookups. The implementation of __early_pfn_to_nid + * treats start/end as pfns. + */ +struct mminit_pfnnid_cache { + unsigned long last_start; + unsigned long last_end; + int last_nid; +}; static struct mminit_pfnnid_cache early_pfnnid_cache __meminitdata; -int __meminit early_pfn_to_nid(unsigned long pfn) +/* + * Required by SPARSEMEM. Given a PFN, return what node the PFN is on. + */ +static int __meminit __early_pfn_to_nid(unsigned long pfn, + struct mminit_pfnnid_cache *state) { - static DEFINE_SPINLOCK(early_pfn_lock); + unsigned long start_pfn, end_pfn; int nid; - spin_lock(&early_pfn_lock); - nid = __early_pfn_to_nid(pfn, &early_pfnnid_cache); - if (nid < 0) - nid = first_online_node; - spin_unlock(&early_pfn_lock); + if (state->last_start <= pfn && pfn < state->last_end) + return state->last_nid; + + nid = memblock_search_pfn_nid(pfn, &start_pfn, &end_pfn); + if (nid != NUMA_NO_NODE) { + state->last_start = start_pfn; + state->last_end = end_pfn; + state->last_nid = nid; + } return nid; } -#endif -#ifdef CONFIG_NODES_SPAN_OTHER_NODES -/* Only safe to use early in boot when initialisation is single-threaded */ -static inline bool __meminit early_pfn_in_nid(unsigned long pfn, int node) +int __meminit early_pfn_to_nid(unsigned long pfn) { + static DEFINE_SPINLOCK(early_pfn_lock); int nid; + spin_lock(&early_pfn_lock); nid = __early_pfn_to_nid(pfn, &early_pfnnid_cache); - if (nid >= 0 && nid != node) - return false; - return true; -} + if (nid < 0) + nid = first_online_node; + spin_unlock(&early_pfn_lock); -#else -static inline bool __meminit early_pfn_in_nid(unsigned long pfn, int node) -{ - return true; + return nid; } -#endif - +#endif /* CONFIG_NUMA */ void __init memblock_free_pages(struct page *page, unsigned long pfn, unsigned int order) { if (early_page_uninitialised(pfn)) return; + if (!kmsan_memblock_free_pages(page, order)) { + /* KMSAN will take care of these pages. */ + return; + } __free_pages_core(page, order); } /* * Check that the whole (or subset of) a pageblock given by the interval of * [start_pfn, end_pfn) is valid and within the same zone, before scanning it - * with the migration of free compaction scanner. The scanners then need to - * use only pfn_valid_within() check for arches that allow holes within - * pageblocks. + * with the migration of free compaction scanner. * * Return struct page pointer of start_pfn, or NULL if checks were not passed. * @@ -1545,7 +1869,7 @@ void set_zone_contiguous(struct zone *zone) unsigned long block_start_pfn = zone->zone_start_pfn; unsigned long block_end_pfn; - block_end_pfn = ALIGN(block_start_pfn + 1, pageblock_nr_pages); + block_end_pfn = pageblock_end_pfn(block_start_pfn); for (; block_start_pfn < zone_end_pfn(zone); block_start_pfn = block_end_pfn, block_end_pfn += pageblock_nr_pages) { @@ -1555,6 +1879,7 @@ void set_zone_contiguous(struct zone *zone) if (!__pageblock_pfn_to_page(block_start_pfn, block_end_pfn, zone)) return; + cond_resched(); } /* We confirm that there is no hole */ @@ -1579,15 +1904,14 @@ static void __init deferred_free_range(unsigned long pfn, page = pfn_to_page(pfn); /* Free a large naturally-aligned chunk if possible */ - if (nr_pages == pageblock_nr_pages && - (pfn & (pageblock_nr_pages - 1)) == 0) { + if (nr_pages == pageblock_nr_pages && pageblock_aligned(pfn)) { set_pageblock_migratetype(page, MIGRATE_MOVABLE); __free_pages_core(page, pageblock_order); return; } for (i = 0; i < nr_pages; i++, page++, pfn++) { - if ((pfn & (pageblock_nr_pages - 1)) == 0) + if (pageblock_aligned(pfn)) set_pageblock_migratetype(page, MIGRATE_MOVABLE); __free_pages_core(page, 0); } @@ -1606,18 +1930,12 @@ static inline void __init pgdat_init_report_one_done(void) /* * Returns true if page needs to be initialized or freed to buddy allocator. * - * First we check if pfn is valid on architectures where it is possible to have - * holes within pageblock_nr_pages. On systems where it is not possible, this - * function is optimized out. - * - * Then, we check if a current large page is valid by only checking the validity + * We check if a current large page is valid by only checking the validity * of the head pfn. */ static inline bool __init deferred_pfn_valid(unsigned long pfn) { - if (!pfn_valid_within(pfn)) - return false; - if (!(pfn & (pageblock_nr_pages - 1)) && !pfn_valid(pfn)) + if (pageblock_aligned(pfn) && !pfn_valid(pfn)) return false; return true; } @@ -1629,17 +1947,15 @@ static inline bool __init deferred_pfn_valid(unsigned long pfn) static void __init deferred_free_pages(unsigned long pfn, unsigned long end_pfn) { - unsigned long nr_pgmask = pageblock_nr_pages - 1; unsigned long nr_free = 0; for (; pfn < end_pfn; pfn++) { if (!deferred_pfn_valid(pfn)) { deferred_free_range(pfn - nr_free, nr_free); nr_free = 0; - } else if (!(pfn & nr_pgmask)) { + } else if (pageblock_aligned(pfn)) { deferred_free_range(pfn - nr_free, nr_free); nr_free = 1; - touch_nmi_watchdog(); } else { nr_free++; } @@ -1657,7 +1973,6 @@ static unsigned long __init deferred_init_pages(struct zone *zone, unsigned long pfn, unsigned long end_pfn) { - unsigned long nr_pgmask = pageblock_nr_pages - 1; int nid = zone_to_nid(zone); unsigned long nr_pages = 0; int zid = zone_idx(zone); @@ -1667,9 +1982,8 @@ static unsigned long __init deferred_init_pages(struct zone *zone, if (!deferred_pfn_valid(pfn)) { page = NULL; continue; - } else if (!page || !(pfn & nr_pgmask)) { + } else if (!page || pageblock_aligned(pfn)) { page = pfn_to_page(pfn); - touch_nmi_watchdog(); } else { page++; } @@ -1763,16 +2077,43 @@ deferred_init_maxorder(u64 *i, struct zone *zone, unsigned long *start_pfn, return nr_pages; } +static void __init +deferred_init_memmap_chunk(unsigned long start_pfn, unsigned long end_pfn, + void *arg) +{ + unsigned long spfn, epfn; + struct zone *zone = arg; + u64 i; + + deferred_init_mem_pfn_range_in_zone(&i, zone, &spfn, &epfn, start_pfn); + + /* + * Initialize and free pages in MAX_ORDER sized increments so that we + * can avoid introducing any issues with the buddy allocator. + */ + while (spfn < end_pfn) { + deferred_init_maxorder(&i, zone, &spfn, &epfn); + cond_resched(); + } +} + +/* An arch may override for more concurrency. */ +__weak int __init +deferred_page_init_max_threads(const struct cpumask *node_cpumask) +{ + return 1; +} + /* Initialise remaining memory on a node */ static int __init deferred_init_memmap(void *data) { pg_data_t *pgdat = data; const struct cpumask *cpumask = cpumask_of_node(pgdat->node_id); - unsigned long spfn = 0, epfn = 0, nr_pages = 0; + unsigned long spfn = 0, epfn = 0; unsigned long first_init_pfn, flags; unsigned long start = jiffies; struct zone *zone; - int zid; + int zid, max_threads; u64 i; /* Bind memory initialisation thread to a local node if possible */ @@ -1792,6 +2133,13 @@ static int __init deferred_init_memmap(void *data) BUG_ON(pgdat->first_deferred_pfn > pgdat_end_pfn(pgdat)); pgdat->first_deferred_pfn = ULONG_MAX; + /* + * Once we unlock here, the zone cannot be grown anymore, thus if an + * interrupt thread must allocate this early in boot, zone must be + * pre-grown prior to start of deferred page initialization. + */ + pgdat_resize_unlock(pgdat, &flags); + /* Only the highest zone is deferred so find it */ for (zid = 0; zid < MAX_NR_ZONES; zid++) { zone = pgdat->node_zones + zid; @@ -1804,21 +2152,30 @@ static int __init deferred_init_memmap(void *data) first_init_pfn)) goto zone_empty; - /* - * Initialize and free pages in MAX_ORDER sized increments so - * that we can avoid introducing any issues with the buddy - * allocator. - */ - while (spfn < epfn) - nr_pages += deferred_init_maxorder(&i, zone, &spfn, &epfn); -zone_empty: - pgdat_resize_unlock(pgdat, &flags); + max_threads = deferred_page_init_max_threads(cpumask); + while (spfn < epfn) { + unsigned long epfn_align = ALIGN(epfn, PAGES_PER_SECTION); + struct padata_mt_job job = { + .thread_fn = deferred_init_memmap_chunk, + .fn_arg = zone, + .start = spfn, + .size = epfn_align - spfn, + .align = PAGES_PER_SECTION, + .min_chunk = PAGES_PER_SECTION, + .max_threads = max_threads, + }; + + padata_do_multithreaded(&job); + deferred_init_mem_pfn_range_in_zone(&i, zone, &spfn, &epfn, + epfn_align); + } +zone_empty: /* Sanity check that the next zone really is unpopulated */ WARN_ON(++zid < MAX_NR_ZONES && populated_zone(++zone)); - pr_info("node %d initialised, %lu pages in %ums\n", - pgdat->node_id, nr_pages, jiffies_to_msecs(jiffies - start)); + pr_info("node %d deferred pages initialised in %ums\n", + pgdat->node_id, jiffies_to_msecs(jiffies - start)); pgdat_init_report_one_done(); return 0; @@ -1856,17 +2213,6 @@ deferred_grow_zone(struct zone *zone, unsigned int order) pgdat_resize_lock(pgdat, &flags); /* - * If deferred pages have been initialized while we were waiting for - * the lock, return true, as the zone was grown. The caller will retry - * this zone. We won't return to this function since the caller also - * has this static branch. - */ - if (!static_branch_unlikely(&deferred_pages)) { - pgdat_resize_unlock(pgdat, &flags); - return true; - } - - /* * If someone grew this zone while we were waiting for spinlock, return * true, as there might be enough pages already. */ @@ -1894,6 +2240,7 @@ deferred_grow_zone(struct zone *zone, unsigned int order) first_deferred_pfn = spfn; nr_pages += deferred_init_maxorder(&i, zone, &spfn, &epfn); + touch_nmi_watchdog(); /* We should only stop along section boundaries */ if ((first_deferred_pfn ^ spfn) < PAGES_PER_SECTION) @@ -1941,14 +2288,6 @@ void __init page_alloc_init_late(void) wait_for_completion(&pgdat_init_all_done_comp); /* - * The number of managed pages has changed due to the initialisation - * so the pcpu batch and high limits needs to be updated or the limits - * will be artificially small. - */ - for_each_populated_zone(zone) - zone_pcp_update(zone); - - /* * We initialized the rest of the deferred pages. Permanently disable * on-demand struct page initialization. */ @@ -1958,6 +2297,8 @@ void __init page_alloc_init_late(void) files_maxfiles_init(); #endif + buffer_init(); + /* Discard memblock private memory */ memblock_discard(); @@ -1981,21 +2322,11 @@ void __init init_cma_reserved_pageblock(struct page *page) } while (++p, --i); set_pageblock_migratetype(page, MIGRATE_CMA); - - if (pageblock_order >= MAX_ORDER) { - i = pageblock_nr_pages; - p = page; - do { - set_page_refcounted(p); - __free_pages(p, MAX_ORDER - 1); - p += MAX_ORDER_NR_PAGES; - } while (i -= MAX_ORDER_NR_PAGES); - } else { - set_page_refcounted(page); - __free_pages(page, pageblock_order); - } + set_page_refcounted(page); + __free_pages(page, pageblock_order); adjust_managed_page_count(page, pageblock_nr_pages); + page_zone(page)->cma_pages += pageblock_nr_pages; } #endif @@ -2014,13 +2345,11 @@ void __init init_cma_reserved_pageblock(struct page *page) * -- nyc */ static inline void expand(struct zone *zone, struct page *page, - int low, int high, struct free_area *area, - int migratetype) + int low, int high, int migratetype) { unsigned long size = 1 << high; while (high > low) { - area--; high--; size >>= 1; VM_BUG_ON_PAGE(bad_range(zone, &page[size]), &page[size]); @@ -2034,38 +2363,21 @@ static inline void expand(struct zone *zone, struct page *page, if (set_page_guard(zone, &page[size], high, migratetype)) continue; - add_to_free_area(&page[size], area, migratetype); - set_page_order(&page[size], high); + add_to_free_list(&page[size], zone, high, migratetype); + set_buddy_order(&page[size], high); } } static void check_new_page_bad(struct page *page) { - const char *bad_reason = NULL; - unsigned long bad_flags = 0; - - if (unlikely(atomic_read(&page->_mapcount) != -1)) - bad_reason = "nonzero mapcount"; - if (unlikely(page->mapping != NULL)) - bad_reason = "non-NULL mapping"; - if (unlikely(page_ref_count(page) != 0)) - bad_reason = "nonzero _refcount"; if (unlikely(page->flags & __PG_HWPOISON)) { - bad_reason = "HWPoisoned (hardware-corrupted)"; - bad_flags = __PG_HWPOISON; /* Don't complain about hwpoisoned pages */ page_mapcount_reset(page); /* remove PageBuddy */ return; } - if (unlikely(page->flags & PAGE_FLAGS_CHECK_AT_PREP)) { - bad_reason = "PAGE_FLAGS_CHECK_AT_PREP flag set"; - bad_flags = PAGE_FLAGS_CHECK_AT_PREP; - } -#ifdef CONFIG_MEMCG - if (unlikely(page->mem_cgroup)) - bad_reason = "page still charged to cgroup"; -#endif - bad_page(page, bad_reason, bad_flags); + + bad_page(page, + page_bad_reason(page, PAGE_FLAGS_CHECK_AT_PREP)); } /* @@ -2081,10 +2393,17 @@ static inline int check_new_page(struct page *page) return 1; } -static inline bool free_pages_prezeroed(void) +static bool check_new_pages(struct page *page, unsigned int order) { - return (IS_ENABLED(CONFIG_PAGE_POISONING_ZERO) && - page_poisoning_enabled()) || want_init_on_free(); + int i; + for (i = 0; i < (1 << order); i++) { + struct page *p = page + i; + + if (unlikely(check_new_page(p))) + return true; + } + + return false; } #ifdef CONFIG_DEBUG_VM @@ -2093,17 +2412,17 @@ static inline bool free_pages_prezeroed(void) * being allocated from pcp lists. With debug_pagealloc also enabled, they are * also checked when pcp lists are refilled from the free lists. */ -static inline bool check_pcp_refill(struct page *page) +static inline bool check_pcp_refill(struct page *page, unsigned int order) { if (debug_pagealloc_enabled_static()) - return check_new_page(page); + return check_new_pages(page, order); else return false; } -static inline bool check_new_pcp(struct page *page) +static inline bool check_new_pcp(struct page *page, unsigned int order) { - return check_new_page(page); + return check_new_pages(page, order); } #else /* @@ -2111,44 +2430,107 @@ static inline bool check_new_pcp(struct page *page) * when pcp lists are being refilled from the free lists. With debug_pagealloc * enabled, they are also checked when being allocated from the pcp lists. */ -static inline bool check_pcp_refill(struct page *page) +static inline bool check_pcp_refill(struct page *page, unsigned int order) { - return check_new_page(page); + return check_new_pages(page, order); } -static inline bool check_new_pcp(struct page *page) +static inline bool check_new_pcp(struct page *page, unsigned int order) { if (debug_pagealloc_enabled_static()) - return check_new_page(page); + return check_new_pages(page, order); else return false; } #endif /* CONFIG_DEBUG_VM */ -static bool check_new_pages(struct page *page, unsigned int order) +static inline bool should_skip_kasan_unpoison(gfp_t flags) { - int i; - for (i = 0; i < (1 << order); i++) { - struct page *p = page + i; + /* Don't skip if a software KASAN mode is enabled. */ + if (IS_ENABLED(CONFIG_KASAN_GENERIC) || + IS_ENABLED(CONFIG_KASAN_SW_TAGS)) + return false; - if (unlikely(check_new_page(p))) - return true; - } + /* Skip, if hardware tag-based KASAN is not enabled. */ + if (!kasan_hw_tags_enabled()) + return true; - return false; + /* + * With hardware tag-based KASAN enabled, skip if this has been + * requested via __GFP_SKIP_KASAN_UNPOISON. + */ + return flags & __GFP_SKIP_KASAN_UNPOISON; +} + +static inline bool should_skip_init(gfp_t flags) +{ + /* Don't skip, if hardware tag-based KASAN is not enabled. */ + if (!kasan_hw_tags_enabled()) + return false; + + /* For hardware tag-based KASAN, skip if requested. */ + return (flags & __GFP_SKIP_ZERO); } inline void post_alloc_hook(struct page *page, unsigned int order, gfp_t gfp_flags) { + 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); arch_alloc_page(page, order); - if (debug_pagealloc_enabled_static()) - kernel_map_pages(page, 1 << order, 1); - kasan_alloc_pages(page, order); - kernel_poison_pages(page, 1 << order, 1); + debug_pagealloc_map_pages(page, 1 << order); + + /* + * Page unpoisoning must happen before memory initialization. + * Otherwise, the poison pattern will be overwritten for __GFP_ZERO + * allocations and the page unpoisoning code will complain. + */ + kernel_unpoison_pages(page, 1 << order); + + /* + * As memory initialization might be integrated into KASAN, + * KASAN unpoisoning and memory initializion code must be + * kept together to avoid discrepancies in behavior. + */ + + /* + * If memory tags should be zeroed (which happens only when memory + * should be initialized as well). + */ + if (init_tags) { + /* Initialize both memory and tags. */ + for (i = 0; i != 1 << order; ++i) + tag_clear_highpage(page + i); + + /* Note that memory is already initialized by the loop above. */ + init = false; + } + 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_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); + set_page_owner(page, order, gfp_flags); + page_table_check_alloc(page, order); } static void prep_new_page(struct page *page, unsigned int order, gfp_t gfp_flags, @@ -2156,9 +2538,6 @@ static void prep_new_page(struct page *page, unsigned int order, gfp_t gfp_flags { post_alloc_hook(page, order, gfp_flags); - if (!free_pages_prezeroed() && want_init_on_alloc(gfp_flags)) - kernel_init_free_pages(page, 1 << order); - if (order && (gfp_flags & __GFP_COMP)) prep_compound_page(page, order); @@ -2192,9 +2571,12 @@ 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_area(page, area); - expand(zone, page, order, current_order, area, migratetype); + 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; } @@ -2205,17 +2587,13 @@ struct page *__rmqueue_smallest(struct zone *zone, unsigned int order, /* * This array describes the order lists are fallen back to when * the free lists for the desirable migrate type are depleted + * + * The other migratetypes do not have fallbacks. */ -static int fallbacks[MIGRATE_TYPES][4] = { +static int fallbacks[MIGRATE_TYPES][3] = { [MIGRATE_UNMOVABLE] = { MIGRATE_RECLAIMABLE, MIGRATE_MOVABLE, MIGRATE_TYPES }, [MIGRATE_MOVABLE] = { MIGRATE_RECLAIMABLE, MIGRATE_UNMOVABLE, MIGRATE_TYPES }, [MIGRATE_RECLAIMABLE] = { MIGRATE_UNMOVABLE, MIGRATE_MOVABLE, MIGRATE_TYPES }, -#ifdef CONFIG_CMA - [MIGRATE_CMA] = { MIGRATE_TYPES }, /* Never used */ -#endif -#ifdef CONFIG_MEMORY_ISOLATION - [MIGRATE_ISOLATE] = { MIGRATE_TYPES }, /* Never used */ -#endif }; #ifdef CONFIG_CMA @@ -2230,24 +2608,21 @@ static inline struct page *__rmqueue_cma_fallback(struct zone *zone, #endif /* - * Move the free pages in a range to the free lists of the requested type. + * 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() */ static int move_freepages(struct zone *zone, - struct page *start_page, struct page *end_page, + unsigned long start_pfn, unsigned long end_pfn, int migratetype, int *num_movable) { struct page *page; + unsigned long pfn; unsigned int order; int pages_moved = 0; - for (page = start_page; page <= end_page;) { - if (!pfn_valid_within(page_to_pfn(page))) { - page++; - continue; - } - + for (pfn = start_pfn; pfn <= end_pfn;) { + page = pfn_to_page(pfn); if (!PageBuddy(page)) { /* * We assume that pages that could be isolated for @@ -2257,8 +2632,7 @@ static int move_freepages(struct zone *zone, if (num_movable && (PageLRU(page) || __PageMovable(page))) (*num_movable)++; - - page++; + pfn++; continue; } @@ -2266,9 +2640,9 @@ static int move_freepages(struct zone *zone, VM_BUG_ON_PAGE(page_to_nid(page) != zone_to_nid(zone), page); VM_BUG_ON_PAGE(page_zone(page) != zone, page); - order = page_order(page); - move_to_free_area(page, &zone->free_area[order], migratetype); - page += 1 << order; + order = buddy_order(page); + move_to_free_list(page, zone, order, migratetype); + pfn += 1 << order; pages_moved += 1 << order; } @@ -2278,25 +2652,22 @@ static int move_freepages(struct zone *zone, int move_freepages_block(struct zone *zone, struct page *page, int migratetype, int *num_movable) { - unsigned long start_pfn, end_pfn; - struct page *start_page, *end_page; + unsigned long start_pfn, end_pfn, pfn; if (num_movable) *num_movable = 0; - start_pfn = page_to_pfn(page); - start_pfn = start_pfn & ~(pageblock_nr_pages-1); - start_page = pfn_to_page(start_pfn); - end_page = start_page + pageblock_nr_pages - 1; - end_pfn = start_pfn + pageblock_nr_pages - 1; + pfn = page_to_pfn(page); + start_pfn = pageblock_start_pfn(pfn); + end_pfn = pageblock_end_pfn(pfn) - 1; /* Do not cross zone boundaries */ if (!zone_spans_pfn(zone, start_pfn)) - start_page = page; + start_pfn = pfn; if (!zone_spans_pfn(zone, end_pfn)) return 0; - return move_freepages(zone, start_page, end_page, migratetype, + return move_freepages(zone, start_pfn, end_pfn, migratetype, num_movable); } @@ -2344,12 +2715,20 @@ static bool can_steal_fallback(unsigned int order, int start_mt) return false; } -static inline void boost_watermark(struct zone *zone) +static inline bool boost_watermark(struct zone *zone) { unsigned long max_boost; if (!watermark_boost_factor) - return; + return false; + /* + * Don't bother in zones that are unlikely to produce results. + * On small machines, including kdump capture kernels running + * in a small area, boosting the watermark can cause an out of + * memory situation immediately. + */ + if ((pageblock_nr_pages * 4) > zone_managed_pages(zone)) + return false; max_boost = mult_frac(zone->_watermark[WMARK_HIGH], watermark_boost_factor, 10000); @@ -2363,12 +2742,14 @@ static inline void boost_watermark(struct zone *zone) * boosted watermark resulting in a hang. */ if (!max_boost) - return; + return false; max_boost = max(pageblock_nr_pages, max_boost); zone->watermark_boost = min(zone->watermark_boost + pageblock_nr_pages, max_boost); + + return true; } /* @@ -2382,8 +2763,7 @@ static inline void boost_watermark(struct zone *zone) static void steal_suitable_fallback(struct zone *zone, struct page *page, unsigned int alloc_flags, int start_type, bool whole_block) { - unsigned int current_order = page_order(page); - struct free_area *area; + unsigned int current_order = buddy_order(page); int free_pages, movable_pages, alike_pages; int old_block_type; @@ -2407,8 +2787,7 @@ static void steal_suitable_fallback(struct zone *zone, struct page *page, * likelihood of future fallbacks. Wake kswapd now as the node * may be balanced overall and kswapd will not wake naturally. */ - boost_watermark(zone); - if (alloc_flags & ALLOC_KSWAPD) + 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 */ @@ -2454,8 +2833,7 @@ static void steal_suitable_fallback(struct zone *zone, struct page *page, return; single_page: - area = &zone->free_area[current_order]; - move_to_free_area(page, area, start_type); + move_to_free_list(page, zone, current_order, start_type); } /* @@ -2521,8 +2899,8 @@ static void reserve_highatomic_pageblock(struct page *page, struct zone *zone, /* Yoink! */ mt = get_pageblock_migratetype(page); - if (!is_migrate_highatomic(mt) && !is_migrate_isolate(mt) - && !is_migrate_cma(mt)) { + /* 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); @@ -2552,7 +2930,7 @@ static bool unreserve_highatomic_pageblock(const struct alloc_context *ac, int order; bool ret; - for_each_zone_zonelist_nodemask(zone, z, zonelist, ac->high_zoneidx, + for_each_zone_zonelist_nodemask(zone, z, zonelist, ac->highest_zoneidx, ac->nodemask) { /* * Preserve at least one pageblock unless memory pressure @@ -2573,7 +2951,7 @@ static bool unreserve_highatomic_pageblock(const struct alloc_context *ac, /* * In page freeing path, migratetype change is racy so * we can counter several free pages in a pageblock - * in this loop althoug we changed the pageblock type + * in this loop although we changed the pageblock type * from highatomic to ac->migratetype. So we should * adjust the count once. */ @@ -2639,7 +3017,7 @@ __rmqueue_fallback(struct zone *zone, int order, int start_migratetype, * i.e. orders < pageblock_order. If there are no local zones free, * the zonelists will be reiterated without ALLOC_NOFRAGMENT. */ - if (alloc_flags & ALLOC_NOFRAGMENT) + if (order < pageblock_order && alloc_flags & ALLOC_NOFRAGMENT) min_order = pageblock_order; /* @@ -2711,18 +3089,30 @@ __rmqueue(struct zone *zone, unsigned int order, int migratetype, { struct page *page; + if (IS_ENABLED(CONFIG_CMA)) { + /* + * Balance movable allocations between regular and CMA areas by + * allocating from CMA when over half of the zone's free memory + * is in the CMA area. + */ + if (alloc_flags & ALLOC_CMA && + zone_page_state(zone, NR_FREE_CMA_PAGES) > + zone_page_state(zone, NR_FREE_PAGES) / 2) { + page = __rmqueue_cma_fallback(zone, order); + if (page) + return page; + } + } retry: page = __rmqueue_smallest(zone, order, migratetype); if (unlikely(!page)) { - if (migratetype == MIGRATE_MOVABLE) + if (alloc_flags & ALLOC_CMA) page = __rmqueue_cma_fallback(zone, order); if (!page && __rmqueue_fallback(zone, order, migratetype, alloc_flags)) goto retry; } - - trace_mm_page_alloc_zone_locked(page, order, migratetype); return page; } @@ -2735,8 +3125,9 @@ static int rmqueue_bulk(struct zone *zone, unsigned int order, unsigned long count, struct list_head *list, int migratetype, unsigned int alloc_flags) { - int i, alloced = 0; + int i, allocated = 0; + /* 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, @@ -2744,7 +3135,7 @@ static int rmqueue_bulk(struct zone *zone, unsigned int order, if (unlikely(page == NULL)) break; - if (unlikely(check_pcp_refill(page))) + if (unlikely(check_pcp_refill(page, order))) continue; /* @@ -2757,8 +3148,8 @@ 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); - alloced++; + 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, -(1 << order)); @@ -2767,12 +3158,12 @@ static int rmqueue_bulk(struct zone *zone, unsigned int order, /* * i pages were removed from the buddy list even if some leak due * to check_pcp_refill failing so adjust NR_FREE_PAGES based - * on i. Do not confuse with 'alloced' which is the number of + * on i. Do not confuse with 'allocated' which is the number of * pages added to the pcp list. */ __mod_zone_page_state(zone, NR_FREE_PAGES, -(i << order)); spin_unlock(&zone->lock); - return alloced; + return allocated; } #ifdef CONFIG_NUMA @@ -2780,52 +3171,48 @@ 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_irq_save(flags); batch = READ_ONCE(pcp->batch); to_drain = min(pcp->count, batch); - if (to_drain > 0) - free_pcppages_bulk(zone, to_drain, pcp); - local_irq_restore(flags); + 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); + 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_pageset *pset; struct per_cpu_pages *pcp; - local_irq_save(flags); - pset = per_cpu_ptr(zone->pageset, cpu); + pcp = per_cpu_ptr(zone->per_cpu_pageset, cpu); + if (pcp->count) { + unsigned long flags; - pcp = &pset->pcp; - if (pcp->count) - free_pcppages_bulk(zone, pcp->count, pcp); - local_irq_restore(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) { @@ -2838,9 +3225,6 @@ 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) { @@ -2852,49 +3236,27 @@ 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 allright but we also have to make sure to not move to - * a different one. - */ - preempt_disable(); - drain_local_pages(drain->zone); - preempt_enable(); -} - /* - * 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. + * The implementation of drain_all_pages(), exposing an extra parameter to + * drain on all cpus. * - * Note that this can be extremely slow as the draining happens in a workqueue. + * drain_all_pages() is optimized to only execute on cpus where pcplists are + * not empty. The check for non-emptiness can however race with a free to + * pcplist that has not yet increased the pcp->count from 0 to 1. Callers + * that need the guarantee that every CPU has drained can disable the + * optimizing racy check. */ -void drain_all_pages(struct zone *zone) +static void __drain_all_pages(struct zone *zone, bool force_all_cpus) { int cpu; /* - * Allocate in the BSS so we wont require allocation in + * Allocate in the BSS so we won't require allocation in * direct reclaim path for CONFIG_CPUMASK_OFFSTACK=y */ 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. @@ -2912,18 +3274,24 @@ void drain_all_pages(struct zone *zone) * disables preemption as part of its processing */ for_each_online_cpu(cpu) { - struct per_cpu_pageset *pcp; + struct per_cpu_pages *pcp; struct zone *z; bool has_pcps = false; - if (zone) { - pcp = per_cpu_ptr(zone->pageset, cpu); - if (pcp->pcp.count) + if (force_all_cpus) { + /* + * The pcp.count check is racy, some callers need a + * guarantee that no cpu is missed. + */ + has_pcps = true; + } else if (zone) { + pcp = per_cpu_ptr(zone->per_cpu_pageset, cpu); + if (pcp->count) has_pcps = true; } else { for_each_populated_zone(z) { - pcp = per_cpu_ptr(z->pageset, cpu); - if (pcp->pcp.count) { + pcp = per_cpu_ptr(z->per_cpu_pageset, cpu); + if (pcp->count) { has_pcps = true; break; } @@ -2937,18 +3305,25 @@ void drain_all_pages(struct zone *zone) } 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); } +/* + * 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. + */ +void drain_all_pages(struct zone *zone) +{ + __drain_all_pages(zone, false); +} + #ifdef CONFIG_HIBERNATION /* @@ -2987,7 +3362,7 @@ 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); @@ -3004,11 +3379,12 @@ void mark_free_pages(struct zone *zone) } #endif /* CONFIG_PM */ -static bool free_unref_page_prepare(struct page *page, unsigned long pfn) +static bool free_unref_page_prepare(struct page *page, unsigned long pfn, + unsigned int order) { int migratetype; - if (!free_pcp_prepare(page)) + if (!free_pcp_prepare(page, order)) return false; migratetype = get_pfnblock_migratetype(page, pfn); @@ -3016,53 +3392,123 @@ static bool free_unref_page_prepare(struct page *page, unsigned long pfn) return true; } -static void free_unref_page_commit(struct page *page, unsigned long pfn) +static int nr_pcp_free(struct per_cpu_pages *pcp, int high, int batch, + bool free_high) { - struct zone *zone = page_zone(page); + int min_nr_free, max_nr_free; + + /* Free everything if batch freeing high-order pages. */ + if (unlikely(free_high)) + return pcp->count; + + /* Check for PCP disabled or boot pageset */ + if (unlikely(high < batch)) + return 1; + + /* Leave at least pcp->batch pages on the list */ + min_nr_free = batch; + max_nr_free = high - batch; + + /* + * Double the number of pages freed each time there is subsequent + * freeing of pages without any allocation. + */ + batch <<= pcp->free_factor; + if (batch < max_nr_free) + pcp->free_factor++; + batch = clamp(batch, min_nr_free, max_nr_free); + + return batch; +} + +static int nr_pcp_high(struct per_cpu_pages *pcp, struct zone *zone, + bool free_high) +{ + int high = READ_ONCE(pcp->high); + + if (unlikely(!high || free_high)) + return 0; + + if (!test_bit(ZONE_RECLAIM_ACTIVE, &zone->flags)) + return high; + + /* + * If reclaim is active, limit the number of pages that can be + * stored on pcp lists + */ + return min(READ_ONCE(pcp->batch) << 2, high); +} + +static void free_unref_page_commit(struct zone *zone, struct per_cpu_pages *pcp, + struct page *page, int migratetype, + unsigned int order) +{ + int high; + int pindex; + bool free_high; + + __count_vm_events(PGFREE, 1 << order); + pindex = order_to_pindex(migratetype, order); + list_add(&page->pcp_list, &pcp->lists[pindex]); + pcp->count += 1 << order; + + /* + * As high-order pages other than THP's stored on PCP can contribute + * to fragmentation, limit the number stored when PCP is heavily + * freeing without allocation. The remainder after bulk freeing + * stops will be drained from vmstat refresh context. + */ + free_high = (pcp->free_factor && order && order <= PAGE_ALLOC_COSTLY_ORDER); + + high = nr_pcp_high(pcp, zone, free_high); + if (pcp->count >= high) { + int batch = READ_ONCE(pcp->batch); + + free_pcppages_bulk(zone, nr_pcp_free(pcp, high, batch, free_high), pcp, pindex); + } +} + +/* + * Free a pcp page + */ +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; - migratetype = get_pcppage_migratetype(page); - __count_vm_event(PGFREE); + if (!free_unref_page_prepare(page, pfn, order)) + return; /* * We only track unmovable, reclaimable and movable on pcp lists. - * Free ISOLATE pages back to the allocator because they are being + * Place ISOLATE pages on the isolated list because they are being * offlined but treat HIGHATOMIC as movable pages so we can get those * areas back if necessary. Otherwise, we may have to free * excessively into the page allocator */ - if (migratetype >= MIGRATE_PCPTYPES) { + migratetype = get_pcppage_migratetype(page); + if (unlikely(migratetype >= MIGRATE_PCPTYPES)) { if (unlikely(is_migrate_isolate(migratetype))) { - free_one_page(zone, page, pfn, 0, migratetype); + free_one_page(page_zone(page), page, pfn, order, migratetype, FPI_NONE); return; } migratetype = MIGRATE_MOVABLE; } - pcp = &this_cpu_ptr(zone->pageset)->pcp; - list_add(&page->lru, &pcp->lists[migratetype]); - pcp->count++; - if (pcp->count >= pcp->high) { - unsigned long batch = READ_ONCE(pcp->batch); - free_pcppages_bulk(zone, batch, pcp); + 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); } -} - -/* - * Free a 0-order page - */ -void free_unref_page(struct page *page) -{ - unsigned long flags; - unsigned long pfn = page_to_pfn(page); - - if (!free_unref_page_prepare(page, pfn)) - return; - - local_irq_save(flags); - free_unref_page_commit(page, pfn); - local_irq_restore(flags); + pcp_trylock_finish(UP_flags); } /* @@ -3071,36 +3517,68 @@ void free_unref_page(struct page *page) void free_unref_page_list(struct list_head *list) { struct page *page, *next; - unsigned long flags, pfn; + struct per_cpu_pages *pcp = NULL; + struct zone *locked_zone = NULL; + unsigned long flags; int batch_count = 0; + int migratetype; /* Prepare pages for freeing */ list_for_each_entry_safe(page, next, list, lru) { - pfn = page_to_pfn(page); - if (!free_unref_page_prepare(page, pfn)) + unsigned long pfn = page_to_pfn(page); + if (!free_unref_page_prepare(page, pfn, 0)) { list_del(&page->lru); - set_page_private(page, pfn); + continue; + } + + /* + * Free isolated pages directly to the allocator, see + * comment in free_unref_page. + */ + migratetype = get_pcppage_migratetype(page); + if (unlikely(is_migrate_isolate(migratetype))) { + list_del(&page->lru); + free_one_page(page_zone(page), page, pfn, 0, migratetype, FPI_NONE); + continue; + } } - local_irq_save(flags); list_for_each_entry_safe(page, next, list, lru) { - unsigned long pfn = page_private(page); + 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. + */ + migratetype = get_pcppage_migratetype(page); + if (unlikely(migratetype >= MIGRATE_PCPTYPES)) + migratetype = MIGRATE_MOVABLE; - set_page_private(page, 0); trace_mm_page_free_batched(page); - free_unref_page_commit(page, pfn); + 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_irq_restore(flags); + pcp_spin_unlock_irqrestore(pcp, flags); batch_count = 0; - local_irq_save(flags); + pcp = pcp_spin_lock_irqsave(locked_zone->per_cpu_pageset, flags); } } - local_irq_restore(flags); + + if (pcp) + pcp_spin_unlock_irqrestore(pcp, flags); } /* @@ -3120,23 +3598,18 @@ 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); + split_page_owner(page, 1 << order); + split_page_memcg(page, 1 << order); } EXPORT_SYMBOL_GPL(split_page); int __isolate_free_page(struct page *page, unsigned int order) { - struct free_area *area = &page_zone(page)->free_area[order]; - unsigned long watermark; - struct zone *zone; - int mt; - - BUG_ON(!PageBuddy(page)); - - zone = page_zone(page); - mt = get_pageblock_migratetype(page); + struct zone *zone = page_zone(page); + int mt = get_pageblock_migratetype(page); if (!is_migrate_isolate(mt)) { + unsigned long watermark; /* * Obey watermarks as if the page was being allocated. We can * emulate a high-order watermark check with a raised order-0 @@ -3150,9 +3623,7 @@ int __isolate_free_page(struct page *page, unsigned int order) __mod_zone_freepage_state(zone, -(1UL << order), mt); } - /* Remove page from free list */ - - del_page_from_free_area(page, area); + del_page_from_free_list(page, zone, order); /* * Set the pageblock if the isolated page is at least half of a @@ -3162,23 +3633,45 @@ int __isolate_free_page(struct page *page, unsigned int order) struct page *endpage = page + (1 << order) - 1; for (; page < endpage; page += pageblock_nr_pages) { int mt = get_pageblock_migratetype(page); - if (!is_migrate_isolate(mt) && !is_migrate_cma(mt) - && !is_migrate_highatomic(mt)) + /* + * Only change normal pageblocks (i.e., they can merge + * with others) + */ + if (migratetype_is_mergeable(mt)) set_pageblock_migratetype(page, MIGRATE_MOVABLE); } } - return 1UL << order; } +/** + * __putback_isolated_page - Return a now-isolated page back where we got it + * @page: Page that was isolated + * @order: Order of the isolated page + * @mt: The page's pageblock's migratetype + * + * This function is meant to return a page pulled from the free lists via + * __isolate_free_page back to the free lists they were pulled from. + */ +void __putback_isolated_page(struct page *page, unsigned int order, int mt) +{ + struct zone *zone = page_zone(page); + + /* zone lock should be held when this function is called */ + lockdep_assert_held(&zone->lock); + + /* Return isolated page to tail of freelist. */ + __free_one_page(page, page_to_pfn(page), zone, order, mt, + FPI_SKIP_REPORT_NOTIFY | FPI_TO_TAIL); +} + /* * Update NUMA hit/miss statistics - * - * Must be called with interrupts disabled. */ -static inline void zone_statistics(struct zone *preferred_zone, struct zone *z) +static inline void zone_statistics(struct zone *preferred_zone, struct zone *z, + long nr_account) { #ifdef CONFIG_NUMA enum numa_stat_item local_stat = NUMA_LOCAL; @@ -3191,17 +3684,56 @@ static inline void zone_statistics(struct zone *preferred_zone, struct zone *z) local_stat = NUMA_OTHER; if (zone_to_nid(z) == zone_to_nid(preferred_zone)) - __inc_numa_state(z, NUMA_HIT); + __count_numa_events(z, NUMA_HIT, nr_account); else { - __inc_numa_state(z, NUMA_MISS); - __inc_numa_state(preferred_zone, NUMA_FOREIGN); + __count_numa_events(z, NUMA_MISS, nr_account); + __count_numa_events(preferred_zone, NUMA_FOREIGN, nr_account); } - __inc_numa_state(z, local_stat); + __count_numa_events(z, local_stat, nr_account); #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 struct page *__rmqueue_pcplist(struct zone *zone, int migratetype, +static inline +struct page *__rmqueue_pcplist(struct zone *zone, unsigned int order, + int migratetype, unsigned int alloc_flags, struct per_cpu_pages *pcp, struct list_head *list) @@ -3210,101 +3742,126 @@ static struct page *__rmqueue_pcplist(struct zone *zone, int migratetype, do { if (list_empty(list)) { - pcp->count += rmqueue_bulk(zone, 0, - pcp->batch, list, + int batch = READ_ONCE(pcp->batch); + int alloced; + + /* + * Scale batch relative to order if batch implies + * free pages can be stored on the PCP. Batch can + * be 1 for small zones or for boot pagesets which + * should never store free pages as the pages may + * belong to arbitrary zones. + */ + if (batch > 1) + batch = max(batch >> order, 2); + alloced = rmqueue_bulk(zone, order, + batch, list, migratetype, alloc_flags); + + pcp->count += alloced << order; if (unlikely(list_empty(list))) return NULL; } - page = list_first_entry(list, struct page, lru); - list_del(&page->lru); - pcp->count--; - } while (check_new_pcp(page)); + page = list_first_entry(list, struct page, pcp_list); + list_del(&page->pcp_list); + pcp->count -= 1 << order; + } while (check_new_pcp(page, order)); return page; } /* Lock and remove page from the per-cpu list */ static struct page *rmqueue_pcplist(struct zone *preferred_zone, - struct zone *zone, gfp_t gfp_flags, + struct zone *zone, unsigned int order, int migratetype, unsigned int alloc_flags) { struct per_cpu_pages *pcp; struct list_head *list; struct page *page; unsigned long flags; + unsigned long __maybe_unused UP_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; + } - local_irq_save(flags); - pcp = &this_cpu_ptr(zone->pageset)->pcp; - list = &pcp->lists[migratetype]; - page = __rmqueue_pcplist(zone, migratetype, alloc_flags, pcp, list); + /* + * On allocation, reduce the number of pages that are batch freed. + * See nr_pcp_free() where free_factor is increased for subsequent + * frees. + */ + pcp->free_factor >>= 1; + list = &pcp->lists[order_to_pindex(migratetype, order)]; + page = __rmqueue_pcplist(zone, order, migratetype, alloc_flags, pcp, list); + 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); + __count_zid_vm_events(PGALLOC, page_zonenum(page), 1 << order); + zone_statistics(preferred_zone, zone, 1); } - local_irq_restore(flags); return page; } /* - * Allocate a page from the given zone. Use pcplists for order-0 allocations. + * Allocate a page from the given zone. + * Use pcplists for THP or "cheap" high-order allocations. + */ + +/* + * Do not instrument rmqueue() with KMSAN. This function may call + * __msan_poison_alloca() through a call to set_pfnblock_flags_mask(). + * If __msan_poison_alloca() attempts to allocate pages for the stack depot, it + * may call rmqueue() again, which will result in a deadlock. */ +__no_sanitize_memory static inline struct page *rmqueue(struct zone *preferred_zone, struct zone *zone, unsigned int order, gfp_t gfp_flags, unsigned int alloc_flags, int migratetype) { - unsigned long flags; struct page *page; - if (likely(order == 0)) { - page = rmqueue_pcplist(preferred_zone, zone, gfp_flags, - migratetype, alloc_flags); - 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)); - spin_lock_irqsave(&zone->lock, flags); - do { - page = NULL; - if (alloc_flags & ALLOC_HARDER) { - page = __rmqueue_smallest(zone, order, MIGRATE_HIGHATOMIC); - if (page) - trace_mm_page_alloc_zone_locked(page, order, migratetype); + if (likely(pcp_allowed_order(order))) { + /* + * MIGRATE_MOVABLE pcplist could have the pages on CMA area and + * we need to skip it when CMA area isn't allowed. + */ + if (!IS_ENABLED(CONFIG_CMA) || alloc_flags & ALLOC_CMA || + migratetype != MIGRATE_MOVABLE) { + page = rmqueue_pcplist(preferred_zone, zone, order, + migratetype, alloc_flags); + if (likely(page)) + goto out; } - if (!page) - page = __rmqueue(zone, order, migratetype, alloc_flags); - } while (page && check_new_pages(page, order)); - spin_unlock(&zone->lock); - if (!page) - goto failed; - __mod_zone_freepage_state(zone, -(1 << order), - get_pcppage_migratetype(page)); + } - __count_zid_vm_events(PGALLOC, page_zonenum(page), 1 << order); - zone_statistics(preferred_zone, zone); - local_irq_restore(flags); + 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: - local_irq_restore(flags); - return NULL; } #ifdef CONFIG_FAIL_PAGE_ALLOC @@ -3340,6 +3897,9 @@ 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); } @@ -3375,12 +3935,35 @@ static inline bool __should_fail_alloc_page(gfp_t gfp_mask, unsigned int order) #endif /* CONFIG_FAIL_PAGE_ALLOC */ -static noinline bool should_fail_alloc_page(gfp_t gfp_mask, unsigned int order) +noinline bool should_fail_alloc_page(gfp_t gfp_mask, unsigned int order) { return __should_fail_alloc_page(gfp_mask, order); } 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) +{ + const bool alloc_harder = (alloc_flags & (ALLOC_HARDER|ALLOC_OOM)); + long unusable_free = (1 << order) - 1; + + /* + * If the caller does not have rights to ALLOC_HARDER then subtract + * the high-atomic reserves. This will over-estimate the size of the + * atomic reserve but it avoids a search. + */ + if (likely(!alloc_harder)) + unusable_free += z->nr_reserved_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 + + return unusable_free; +} + /* * Return true if free base pages are above 'mark'. For high-order checks it * will return true of the order-0 watermark is reached and there is at least @@ -3388,7 +3971,7 @@ ALLOW_ERROR_INJECTION(should_fail_alloc_page, TRUE); * to check in the allocation paths if no pages are free. */ bool __zone_watermark_ok(struct zone *z, unsigned int order, unsigned long mark, - int classzone_idx, unsigned int alloc_flags, + int highest_zoneidx, unsigned int alloc_flags, long free_pages) { long min = mark; @@ -3396,19 +3979,12 @@ bool __zone_watermark_ok(struct zone *z, unsigned int order, unsigned long mark, const bool alloc_harder = (alloc_flags & (ALLOC_HARDER|ALLOC_OOM)); /* free_pages may go negative - that's OK */ - free_pages -= (1 << order) - 1; + free_pages -= __zone_watermark_unusable_free(z, order, alloc_flags); if (alloc_flags & ALLOC_HIGH) min -= min / 2; - /* - * If the caller does not have rights to ALLOC_HARDER then subtract - * the high-atomic reserves. This will over-estimate the size of the - * atomic reserve but it avoids a search. - */ - if (likely(!alloc_harder)) { - free_pages -= z->nr_reserved_highatomic; - } else { + if (unlikely(alloc_harder)) { /* * OOM victims can try even harder than normal ALLOC_HARDER * users on the grounds that it's definitely going to be in @@ -3421,19 +3997,12 @@ bool __zone_watermark_ok(struct zone *z, unsigned int order, unsigned long mark, min -= min / 4; } - -#ifdef CONFIG_CMA - /* If allocation can't use CMA areas don't use free CMA pages */ - if (!(alloc_flags & ALLOC_CMA)) - free_pages -= zone_page_state(z, NR_FREE_CMA_PAGES); -#endif - /* * Check watermarks for an order-0 allocation request. If these * are not met, then a high-order request also cannot go ahead * even if a suitable page happened to be free. */ - if (free_pages <= min + z->lowmem_reserve[classzone_idx]) + if (free_pages <= min + z->lowmem_reserve[highest_zoneidx]) return false; /* If this is an order-0 request then the watermark is fine */ @@ -3459,59 +4028,78 @@ bool __zone_watermark_ok(struct zone *z, unsigned int order, unsigned long mark, return true; } #endif - if (alloc_harder && - !list_empty(&area->free_list[MIGRATE_HIGHATOMIC])) + if (alloc_harder && !free_area_empty(area, MIGRATE_HIGHATOMIC)) return true; } return false; } bool zone_watermark_ok(struct zone *z, unsigned int order, unsigned long mark, - int classzone_idx, unsigned int alloc_flags) + int highest_zoneidx, unsigned int alloc_flags) { - return __zone_watermark_ok(z, order, mark, classzone_idx, alloc_flags, + return __zone_watermark_ok(z, order, mark, highest_zoneidx, alloc_flags, zone_page_state(z, NR_FREE_PAGES)); } static inline bool zone_watermark_fast(struct zone *z, unsigned int order, - unsigned long mark, int classzone_idx, unsigned int alloc_flags) + unsigned long mark, int highest_zoneidx, + unsigned int alloc_flags, gfp_t gfp_mask) { - long free_pages = zone_page_state(z, NR_FREE_PAGES); - long cma_pages = 0; + long free_pages; -#ifdef CONFIG_CMA - /* If allocation can't use CMA areas don't use free CMA pages */ - if (!(alloc_flags & ALLOC_CMA)) - cma_pages = zone_page_state(z, NR_FREE_CMA_PAGES); -#endif + free_pages = zone_page_state(z, NR_FREE_PAGES); /* * Fast check for order-0 only. If this fails then the reserves - * need to be calculated. There is a corner case where the check - * passes but only the high-order atomic reserve are free. If - * the caller is !atomic then it'll uselessly search the free - * list. That corner case is then slower but it is harmless. + * need to be calculated. */ - if (!order && (free_pages - cma_pages) > mark + z->lowmem_reserve[classzone_idx]) + if (!order) { + long usable_free; + long reserved; + + usable_free = free_pages; + reserved = __zone_watermark_unusable_free(z, 0, alloc_flags); + + /* reserved may over estimate high-atomic reserves. */ + usable_free -= min(usable_free, reserved); + if (usable_free > mark + z->lowmem_reserve[highest_zoneidx]) + return true; + } + + if (__zone_watermark_ok(z, order, mark, highest_zoneidx, alloc_flags, + free_pages)) return true; + /* + * Ignore watermark boosting for GFP_ATOMIC order-0 allocations + * when checking the min watermark. The min watermark is the + * point where boosting is ignored so that kswapd is woken up + * when below the low watermark. + */ + if (unlikely(!order && (gfp_mask & __GFP_ATOMIC) && z->watermark_boost + && ((alloc_flags & ALLOC_WMARK_MASK) == WMARK_MIN))) { + mark = z->_watermark[WMARK_MIN]; + return __zone_watermark_ok(z, order, mark, highest_zoneidx, + alloc_flags, free_pages); + } - return __zone_watermark_ok(z, order, mark, classzone_idx, alloc_flags, - free_pages); + return false; } bool zone_watermark_ok_safe(struct zone *z, unsigned int order, - unsigned long mark, int classzone_idx) + 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, classzone_idx, 0, + return __zone_watermark_ok(z, order, mark, highest_zoneidx, 0, free_pages); } #ifdef CONFIG_NUMA +int __read_mostly node_reclaim_distance = RECLAIM_DISTANCE; + static bool zone_allows_reclaim(struct zone *local_zone, struct zone *zone) { return node_distance(zone_to_nid(local_zone), zone_to_nid(zone)) <= @@ -3535,10 +4123,13 @@ static bool zone_allows_reclaim(struct zone *local_zone, struct zone *zone) static inline unsigned int alloc_flags_nofragment(struct zone *zone, gfp_t gfp_mask) { - unsigned int alloc_flags = 0; + unsigned int alloc_flags; - if (gfp_mask & __GFP_KSWAPD_RECLAIM) - alloc_flags |= ALLOC_KSWAPD; + /* + * __GFP_KSWAPD_RECLAIM is assumed to be the same as ALLOC_KSWAPD + * to save a branch. + */ + alloc_flags = (__force int) (gfp_mask & __GFP_KSWAPD_RECLAIM); #ifdef CONFIG_ZONE_DMA32 if (!zone) @@ -3561,6 +4152,17 @@ alloc_flags_nofragment(struct zone *zone, gfp_t gfp_mask) return alloc_flags; } +/* Must be called after current_gfp_context() which can change gfp_mask */ +static inline unsigned int gfp_to_alloc_flags_cma(gfp_t gfp_mask, + unsigned int alloc_flags) +{ +#ifdef CONFIG_CMA + if (gfp_migratetype(gfp_mask) == MIGRATE_MOVABLE) + alloc_flags |= ALLOC_CMA; +#endif + return alloc_flags; +} + /* * get_page_from_freelist goes through the zonelist trying to allocate * a page. @@ -3571,18 +4173,19 @@ 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; - for_next_zone_zonelist_nodemask(zone, z, ac->zonelist, ac->high_zoneidx, - ac->nodemask) { + for_next_zone_zonelist_nodemask(zone, z, ac->highest_zoneidx, + ac->nodemask) { struct page *page; unsigned long mark; @@ -3610,13 +4213,13 @@ 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 && @@ -3637,7 +4240,8 @@ retry: mark = wmark_pages(zone, alloc_flags & ALLOC_WMARK_MASK); if (!zone_watermark_fast(zone, order, mark, - ac_classzone_idx(ac), alloc_flags)) { + ac->highest_zoneidx, alloc_flags, + gfp_mask)) { int ret; #ifdef CONFIG_DEFERRED_STRUCT_PAGE_INIT @@ -3655,7 +4259,7 @@ retry: if (alloc_flags & ALLOC_NO_WATERMARKS) goto try_this_zone; - if (node_reclaim_mode == 0 || + if (!node_reclaim_enabled() || !zone_allows_reclaim(ac->preferred_zoneref->zone, zone)) continue; @@ -3670,7 +4274,7 @@ retry: default: /* did we reclaim enough */ if (zone_watermark_ok(zone, order, mark, - ac_classzone_idx(ac), alloc_flags)) + ac->highest_zoneidx, alloc_flags)) goto try_this_zone; continue; @@ -3727,10 +4331,10 @@ static void warn_alloc_show_mem(gfp_t gfp_mask, nodemask_t *nodemask) if (tsk_is_oom_victim(current) || (current->flags & (PF_MEMALLOC | PF_EXITING))) filter &= ~SHOW_MEM_FILTER_NODES; - if (in_interrupt() || !(gfp_mask & __GFP_DIRECT_RECLAIM)) + if (!in_task() || !(gfp_mask & __GFP_DIRECT_RECLAIM)) filter &= ~SHOW_MEM_FILTER_NODES; - show_mem(filter, nodemask); + __show_mem(filter, nodemask, gfp_zone(gfp_mask)); } void warn_alloc(gfp_t gfp_mask, nodemask_t *nodemask, const char *fmt, ...) @@ -3739,7 +4343,9 @@ void warn_alloc(gfp_t gfp_mask, nodemask_t *nodemask, const char *fmt, ...) va_list args; static DEFINE_RATELIMIT_STATE(nopage_rs, 10*HZ, 1); - if ((gfp_mask & __GFP_NOWARN) || !__ratelimit(&nopage_rs)) + if ((gfp_mask & __GFP_NOWARN) || + !__ratelimit(&nopage_rs) || + ((gfp_mask & __GFP_DMA) && !has_managed_dma())) return; va_start(args, fmt); @@ -3825,11 +4431,13 @@ __alloc_pages_may_oom(gfp_t gfp_mask, unsigned int order, * success so it is time to admit defeat. We will skip the OOM killer * because it is very likely that the caller has a more reasonable * fallback than shooting a random task. + * + * The OOM killer may not free memory on a specific node. */ - if (gfp_mask & __GFP_RETRY_MAYFAIL) + if (gfp_mask & (__GFP_RETRY_MAYFAIL | __GFP_THISNODE)) goto out; /* The OOM killer does not needlessly kill tasks for lowmem */ - if (ac->high_zoneidx < ZONE_NORMAL) + if (ac->highest_zoneidx < ZONE_NORMAL) goto out; if (pm_suspended_storage()) goto out; @@ -3843,12 +4451,9 @@ __alloc_pages_may_oom(gfp_t gfp_mask, unsigned int order, * failures more gracefully we should just bail out here. */ - /* The OOM killer may not free memory on a specific node */ - if (gfp_mask & __GFP_THISNODE) - goto out; - /* 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; /* @@ -3865,7 +4470,7 @@ out: } /* - * Maximum number of compaction retries wit a progress before OOM + * Maximum number of compaction retries with a progress before OOM * killer is consider as the only way to move forward. */ #define MAX_COMPACT_RETRIES 16 @@ -3885,6 +4490,7 @@ __alloc_pages_direct_compact(gfp_t gfp_mask, unsigned int order, return NULL; psi_memstall_enter(&pflags); + delayacct_compact_start(); noreclaim_flag = memalloc_noreclaim_save(); *compact_result = try_to_compact_pages(gfp_mask, order, alloc_flags, ac, @@ -3892,7 +4498,10 @@ __alloc_pages_direct_compact(gfp_t gfp_mask, unsigned int order, memalloc_noreclaim_restore(noreclaim_flag); psi_memstall_leave(&pflags); + delayacct_compact_end(); + if (*compact_result == COMPACT_SKIPPED) + return NULL; /* * At least in one zone compaction wasn't deferred or skipped, so let's * count a compaction stall @@ -3942,6 +4551,9 @@ should_compact_retry(struct alloc_context *ac, int order, int alloc_flags, if (!order) return false; + if (fatal_signal_pending(current)) + return false; + if (compaction_made_progress(compact_result)) (*compaction_retries)++; @@ -4032,10 +4644,10 @@ should_compact_retry(struct alloc_context *ac, unsigned int order, int alloc_fla * Let's give them a good hope and keep retrying while the order-0 * watermarks are OK. */ - for_each_zone_zonelist_nodemask(zone, z, ac->zonelist, ac->high_zoneidx, - ac->nodemask) { + for_each_zone_zonelist_nodemask(zone, z, ac->zonelist, + ac->highest_zoneidx, ac->nodemask) { if (zone_watermark_ok(zone, 0, min_wmark_pages(zone), - ac_classzone_idx(ac), alloc_flags)) + ac->highest_zoneidx, alloc_flags)) return true; } return false; @@ -4046,10 +4658,8 @@ should_compact_retry(struct alloc_context *ac, unsigned int order, int alloc_fla static struct lockdep_map __fs_reclaim_map = STATIC_LOCKDEP_MAP_INIT("fs_reclaim", &__fs_reclaim_map); -static bool __need_fs_reclaim(gfp_t gfp_mask) +static bool __need_reclaim(gfp_t gfp_mask) { - gfp_mask = current_gfp_context(gfp_mask); - /* no reclaim without waiting on it */ if (!(gfp_mask & __GFP_DIRECT_RECLAIM)) return false; @@ -4058,55 +4668,87 @@ static bool __need_fs_reclaim(gfp_t gfp_mask) if (current->flags & PF_MEMALLOC) return false; - /* We're only interested __GFP_FS allocations for now */ - if (!(gfp_mask & __GFP_FS)) - return false; - if (gfp_mask & __GFP_NOLOCKDEP) return false; return true; } -void __fs_reclaim_acquire(void) +void __fs_reclaim_acquire(unsigned long ip) { - lock_map_acquire(&__fs_reclaim_map); + lock_acquire_exclusive(&__fs_reclaim_map, 0, 0, NULL, ip); } -void __fs_reclaim_release(void) +void __fs_reclaim_release(unsigned long ip) { - lock_map_release(&__fs_reclaim_map); + lock_release(&__fs_reclaim_map, ip); } void fs_reclaim_acquire(gfp_t gfp_mask) { - if (__need_fs_reclaim(gfp_mask)) - __fs_reclaim_acquire(); + gfp_mask = current_gfp_context(gfp_mask); + + if (__need_reclaim(gfp_mask)) { + if (gfp_mask & __GFP_FS) + __fs_reclaim_acquire(_RET_IP_); + +#ifdef CONFIG_MMU_NOTIFIER + lock_map_acquire(&__mmu_notifier_invalidate_range_start_map); + lock_map_release(&__mmu_notifier_invalidate_range_start_map); +#endif + + } } EXPORT_SYMBOL_GPL(fs_reclaim_acquire); void fs_reclaim_release(gfp_t gfp_mask) { - if (__need_fs_reclaim(gfp_mask)) - __fs_reclaim_release(); + gfp_mask = current_gfp_context(gfp_mask); + + if (__need_reclaim(gfp_mask)) { + if (gfp_mask & __GFP_FS) + __fs_reclaim_release(_RET_IP_); + } } EXPORT_SYMBOL_GPL(fs_reclaim_release); #endif +/* + * Zonelists may change due to hotplug during allocation. Detect when zonelists + * have been rebuilt so allocation retries. Reader side does not lock and + * retries the allocation if zonelist changes. Writer side is protected by the + * embedded spin_lock. + */ +static DEFINE_SEQLOCK(zonelist_update_seq); + +static unsigned int zonelist_iter_begin(void) +{ + if (IS_ENABLED(CONFIG_MEMORY_HOTREMOVE)) + return read_seqbegin(&zonelist_update_seq); + + return 0; +} + +static unsigned int check_retry_zonelist(unsigned int seq) +{ + if (IS_ENABLED(CONFIG_MEMORY_HOTREMOVE)) + return read_seqretry(&zonelist_update_seq, seq); + + return seq; +} + /* Perform direct synchronous page reclaim */ -static int +static unsigned long __perform_reclaim(gfp_t gfp_mask, unsigned int order, const struct alloc_context *ac) { - int progress; unsigned int noreclaim_flag; - unsigned long pflags; + unsigned long progress; cond_resched(); /* We now go into synchronous reclaim */ cpuset_memory_pressure_bump(); - psi_memstall_enter(&pflags); fs_reclaim_acquire(gfp_mask); noreclaim_flag = memalloc_noreclaim_save(); @@ -4115,7 +4757,6 @@ __perform_reclaim(gfp_t gfp_mask, unsigned int order, memalloc_noreclaim_restore(noreclaim_flag); fs_reclaim_release(gfp_mask); - psi_memstall_leave(&pflags); cond_resched(); @@ -4129,11 +4770,13 @@ __alloc_pages_direct_reclaim(gfp_t gfp_mask, unsigned int order, unsigned long *did_some_progress) { struct page *page = NULL; + unsigned long pflags; bool drained = false; + psi_memstall_enter(&pflags); *did_some_progress = __perform_reclaim(gfp_mask, order, ac); if (unlikely(!(*did_some_progress))) - return NULL; + goto out; retry: page = get_page_from_freelist(gfp_mask, order, alloc_flags, ac); @@ -4141,7 +4784,7 @@ retry: /* * If an allocation failed after direct reclaim, it could be because * pages are pinned on the per-cpu lists or in high alloc reserves. - * Shrink them them and try again + * Shrink them and try again */ if (!page && !drained) { unreserve_highatomic_pageblock(ac, false); @@ -4149,6 +4792,8 @@ retry: drained = true; goto retry; } +out: + psi_memstall_leave(&pflags); return page; } @@ -4159,13 +4804,16 @@ static void wake_all_kswapds(unsigned int order, gfp_t gfp_mask, struct zoneref *z; struct zone *zone; pg_data_t *last_pgdat = NULL; - enum zone_type high_zoneidx = ac->high_zoneidx; + enum zone_type highest_zoneidx = ac->highest_zoneidx; - for_each_zone_zonelist_nodemask(zone, z, ac->zonelist, high_zoneidx, + for_each_zone_zonelist_nodemask(zone, z, ac->zonelist, highest_zoneidx, ac->nodemask) { - if (last_pgdat != zone->zone_pgdat) - wakeup_kswapd(zone, gfp_mask, order, high_zoneidx); - 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; + } } } @@ -4174,8 +4822,13 @@ gfp_to_alloc_flags(gfp_t gfp_mask) { unsigned int alloc_flags = ALLOC_WMARK_MIN | ALLOC_CPUSET; - /* __GFP_HIGH is assumed to be the same as ALLOC_HIGH to save a branch. */ + /* + * __GFP_HIGH is assumed to be the same as ALLOC_HIGH + * and __GFP_KSWAPD_RECLAIM is assumed to be the same as ALLOC_KSWAPD + * to save two branches. + */ BUILD_BUG_ON(__GFP_HIGH != (__force gfp_t) ALLOC_HIGH); + BUILD_BUG_ON(__GFP_KSWAPD_RECLAIM != (__force gfp_t) ALLOC_KSWAPD); /* * The caller may dip into page reserves a bit more if the caller @@ -4183,7 +4836,8 @@ gfp_to_alloc_flags(gfp_t gfp_mask) * policy or is asking for __GFP_HIGH memory. GFP_ATOMIC requests will * set both ALLOC_HARDER (__GFP_ATOMIC) and ALLOC_HIGH (__GFP_HIGH). */ - alloc_flags |= (__force int) (gfp_mask & __GFP_HIGH); + alloc_flags |= (__force int) + (gfp_mask & (__GFP_HIGH | __GFP_KSWAPD_RECLAIM)); if (gfp_mask & __GFP_ATOMIC) { /* @@ -4197,16 +4851,11 @@ gfp_to_alloc_flags(gfp_t gfp_mask) * comment for __cpuset_node_allowed(). */ alloc_flags &= ~ALLOC_CPUSET; - } else if (unlikely(rt_task(current)) && !in_interrupt()) + } else if (unlikely(rt_task(current)) && in_task()) alloc_flags |= ALLOC_HARDER; - if (gfp_mask & __GFP_KSWAPD_RECLAIM) - alloc_flags |= ALLOC_KSWAPD; + alloc_flags = gfp_to_alloc_flags_cma(gfp_mask, alloc_flags); -#ifdef CONFIG_CMA - if (gfpflags_to_migratetype(gfp_mask) == MIGRATE_MOVABLE) - alloc_flags |= ALLOC_CMA; -#endif return alloc_flags; } @@ -4296,8 +4945,8 @@ should_reclaim_retry(gfp_t gfp_mask, unsigned order, * request even if all reclaimable pages are considered then we are * screwed and have to go OOM. */ - for_each_zone_zonelist_nodemask(zone, z, ac->zonelist, ac->high_zoneidx, - ac->nodemask) { + for_each_zone_zonelist_nodemask(zone, z, ac->zonelist, + ac->highest_zoneidx, ac->nodemask) { unsigned long available; unsigned long reclaimable; unsigned long min_wmark = min_wmark_pages(zone); @@ -4311,34 +4960,15 @@ should_reclaim_retry(gfp_t gfp_mask, unsigned order, * reclaimable pages? */ wmark = __zone_watermark_ok(zone, order, min_wmark, - ac_classzone_idx(ac), alloc_flags, available); + ac->highest_zoneidx, alloc_flags, available); trace_reclaim_retry_zone(z, order, reclaimable, available, min_wmark, *no_progress_loops, wmark); if (wmark) { - /* - * If we didn't make any progress and have a lot of - * dirty + writeback pages then we should wait for - * an IO to complete to slow down the reclaim and - * prevent from pre mature OOM - */ - if (!did_some_progress) { - unsigned long write_pending; - - write_pending = zone_page_state_snapshot(zone, - NR_ZONE_WRITE_PENDING); - - if (2 * write_pending > reclaimable) { - congestion_wait(BLK_RW_ASYNC, HZ/10); - return true; - } - } - ret = true; - goto out; + break; } } -out: /* * Memory allocation/reclaim might be called from a WQ context and the * current implementation of the WQ concurrency control doesn't @@ -4400,6 +5030,7 @@ __alloc_pages_slowpath(gfp_t gfp_mask, unsigned int order, int compaction_retries; int no_progress_loops; unsigned int cpuset_mems_cookie; + unsigned int zonelist_iter_cookie; int reserve_flags; /* @@ -4410,11 +5041,12 @@ __alloc_pages_slowpath(gfp_t gfp_mask, unsigned int order, (__GFP_ATOMIC|__GFP_DIRECT_RECLAIM))) gfp_mask &= ~__GFP_ATOMIC; -retry_cpuset: +restart: compaction_retries = 0; no_progress_loops = 0; compact_priority = DEF_COMPACT_PRIORITY; cpuset_mems_cookie = read_mems_allowed_begin(); + zonelist_iter_cookie = zonelist_iter_begin(); /* * The fast path uses conservative alloc_flags to succeed only until @@ -4430,10 +5062,23 @@ retry_cpuset: * could end up iterating over non-eligible zones endlessly. */ ac->preferred_zoneref = first_zones_zonelist(ac->zonelist, - ac->high_zoneidx, ac->nodemask); + ac->highest_zoneidx, ac->nodemask); if (!ac->preferred_zoneref->zone) goto nopage; + /* + * Check for insane configurations where the cpuset doesn't contain + * any suitable zone to satisfy the request - e.g. non-movable + * GFP_HIGHUSER allocations from MOVABLE nodes only. + */ + if (cpusets_insane_config() && (gfp_mask & __GFP_HARDWALL)) { + struct zoneref *z = first_zones_zonelist(ac->zonelist, + ac->highest_zoneidx, + &cpuset_current_mems_allowed); + if (!z->zone) + goto nopage; + } + if (alloc_flags & ALLOC_KSWAPD) wake_all_kswapds(order, gfp_mask, ac); @@ -4507,7 +5152,8 @@ retry: reserve_flags = __gfp_pfmemalloc_flags(gfp_mask); if (reserve_flags) - alloc_flags = reserve_flags; + alloc_flags = gfp_to_alloc_flags_cma(gfp_mask, reserve_flags) | + (alloc_flags & ALLOC_KSWAPD); /* * Reset the nodemask and zonelist iterators if memory policies can be @@ -4517,7 +5163,7 @@ retry: if (!(alloc_flags & ALLOC_CPUSET) || reserve_flags) { ac->nodemask = NULL; ac->preferred_zoneref = first_zones_zonelist(ac->zonelist, - ac->high_zoneidx, ac->nodemask); + ac->highest_zoneidx, ac->nodemask); } /* Attempt with potentially adjusted zonelist and alloc_flags */ @@ -4573,9 +5219,13 @@ retry: goto retry; - /* Deal with possible cpuset update races before we start OOM killing */ - if (check_retry_cpuset(cpuset_mems_cookie, ac)) - goto retry_cpuset; + /* + * Deal with possible cpuset update races or zonelist updates to avoid + * a unnecessary OOM kill. + */ + if (check_retry_cpuset(cpuset_mems_cookie, ac) || + check_retry_zonelist(zonelist_iter_cookie)) + goto restart; /* Reclaim has failed us, start killing things */ page = __alloc_pages_may_oom(gfp_mask, order, ac, &did_some_progress); @@ -4584,7 +5234,7 @@ retry: /* Avoid allocations with no watermarks from looping endlessly */ if (tsk_is_oom_victim(current) && - (alloc_flags == ALLOC_OOM || + (alloc_flags & ALLOC_OOM || (gfp_mask & __GFP_NOMEMALLOC))) goto nopage; @@ -4595,9 +5245,13 @@ retry: } nopage: - /* Deal with possible cpuset update races before we fail */ - if (check_retry_cpuset(cpuset_mems_cookie, ac)) - goto retry_cpuset; + /* + * Deal with possible cpuset update races or zonelist updates to avoid + * a unnecessary OOM kill. + */ + if (check_retry_cpuset(cpuset_mems_cookie, ac) || + check_retry_zonelist(zonelist_iter_cookie)) + goto restart; /* * Make sure that __GFP_NOFAIL request doesn't leak out and make sure @@ -4608,7 +5262,7 @@ 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; /* @@ -4616,7 +5270,7 @@ 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 @@ -4624,7 +5278,7 @@ 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(costly_order, gfp_mask); /* * Help non-failing allocations by giving them access to memory @@ -4648,39 +5302,33 @@ got_pg: static inline bool prepare_alloc_pages(gfp_t gfp_mask, unsigned int order, int preferred_nid, nodemask_t *nodemask, - struct alloc_context *ac, gfp_t *alloc_mask, + struct alloc_context *ac, gfp_t *alloc_gfp, unsigned int *alloc_flags) { - ac->high_zoneidx = gfp_zone(gfp_mask); + ac->highest_zoneidx = gfp_zone(gfp_mask); ac->zonelist = node_zonelist(preferred_nid, gfp_mask); ac->nodemask = nodemask; - ac->migratetype = gfpflags_to_migratetype(gfp_mask); + ac->migratetype = gfp_migratetype(gfp_mask); if (cpusets_enabled()) { - *alloc_mask |= __GFP_HARDWALL; - if (!ac->nodemask) + *alloc_gfp |= __GFP_HARDWALL; + /* + * When we are in the interrupt context, it is irrelevant + * to the current task context. It means that any node ok. + */ + if (in_task() && !ac->nodemask) ac->nodemask = &cpuset_current_mems_allowed; else *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; - if (IS_ENABLED(CONFIG_CMA) && ac->migratetype == MIGRATE_MOVABLE) - *alloc_flags |= ALLOC_CMA; + *alloc_flags = gfp_to_alloc_flags_cma(gfp_mask, *alloc_flags); - return true; -} - -/* Determine whether to spread dirty pages and what the first usable zone */ -static inline void finalise_ac(gfp_t gfp_mask, struct alloc_context *ac) -{ /* Dirty zone balancing only done in the fast path */ ac->spread_dirty_pages = (gfp_mask & __GFP_WRITE); @@ -4690,78 +5338,260 @@ static inline void finalise_ac(gfp_t gfp_mask, struct alloc_context *ac) * may get reset for allocations that ignore memory policies. */ ac->preferred_zoneref = first_zones_zonelist(ac->zonelist, - ac->high_zoneidx, ac->nodemask); + ac->highest_zoneidx, ac->nodemask); + + return true; } /* + * __alloc_pages_bulk - Allocate a number of order-0 pages to a list or 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 + * + * 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. + * + * 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 + * is the maximum number of pages that will be stored in the array. + * + * Returns the number of pages on the list or array. + */ +unsigned long __alloc_pages_bulk(gfp_t gfp, int preferred_nid, + nodemask_t *nodemask, int nr_pages, + struct list_head *page_list, + struct page **page_array) +{ + struct page *page; + unsigned long flags; + unsigned long __maybe_unused UP_flags; + struct zone *zone; + struct zoneref *z; + struct per_cpu_pages *pcp; + struct list_head *pcp_list; + struct alloc_context ac; + gfp_t alloc_gfp; + unsigned int alloc_flags = ALLOC_WMARK_LOW; + int nr_populated = 0, nr_account = 0; + + /* + * 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]) + nr_populated++; + + /* No pages requested? */ + if (unlikely(nr_pages <= 0)) + goto out; + + /* Already populated array? */ + if (unlikely(page_array && nr_pages - nr_populated == 0)) + goto out; + + /* Bulk allocator does not support memcg accounting. */ + if (memcg_kmem_enabled() && (gfp & __GFP_ACCOUNT)) + goto failed; + + /* Use the single page allocator for one page. */ + if (nr_pages - nr_populated == 1) + goto failed; + +#ifdef CONFIG_PAGE_OWNER + /* + * PAGE_OWNER may recurse into the allocator to allocate space to + * save the stack with pagesets.lock held. Releasing/reacquiring + * removes much of the performance benefit of bulk allocation so + * force the caller to allocate one page at a time as it'll have + * similar performance to added complexity to the bulk allocator. + */ + if (static_branch_unlikely(&page_owner_inited)) + goto failed; +#endif + + /* May set ALLOC_NOFRAGMENT, fragmentation will return 1 page. */ + gfp &= gfp_allowed_mask; + alloc_gfp = gfp; + if (!prepare_alloc_pages(gfp, 0, preferred_nid, nodemask, &ac, &alloc_gfp, &alloc_flags)) + goto out; + 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) { + unsigned long mark; + + if (cpusets_enabled() && (alloc_flags & ALLOC_CPUSET) && + !__cpuset_zone_allowed(zone, gfp)) { + continue; + } + + if (nr_online_nodes > 1 && zone != ac.preferred_zoneref->zone && + zone_to_nid(zone) != zone_to_nid(ac.preferred_zoneref->zone)) { + goto failed; + } + + 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 there are no allowed local zones that meets the watermarks then + * try to allocate a single page and reclaim if necessary. + */ + 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 */ + pcp_list = &pcp->lists[order_to_pindex(ac.migratetype, 0)]; + while (nr_populated < nr_pages) { + + /* Skip existing pages */ + if (page_array && page_array[nr_populated]) { + nr_populated++; + continue; + } + + page = __rmqueue_pcplist(zone, 0, ac.migratetype, alloc_flags, + pcp, pcp_list); + if (unlikely(!page)) { + /* Try and allocate at least one page */ + if (!nr_account) { + pcp_spin_unlock_irqrestore(pcp, flags); + goto failed_irq; + } + break; + } + 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++; + } + + 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); + +out: + return nr_populated; + +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++; + } + + goto out; +} +EXPORT_SYMBOL_GPL(__alloc_pages_bulk); + +/* * This is the 'heart' of the zoned buddy allocator. */ -struct page * -__alloc_pages_nodemask(gfp_t gfp_mask, unsigned int order, int preferred_nid, +struct page *__alloc_pages(gfp_t gfp, unsigned int order, int preferred_nid, nodemask_t *nodemask) { struct page *page; unsigned int alloc_flags = ALLOC_WMARK_LOW; - gfp_t alloc_mask; /* The gfp_t that was actually used for allocation */ + gfp_t alloc_gfp; /* The gfp_t that was actually used for allocation */ struct alloc_context ac = { }; /* * 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_mask & __GFP_NOWARN)); + if (WARN_ON_ONCE_GFP(order >= MAX_ORDER, gfp)) return NULL; - } - gfp_mask &= gfp_allowed_mask; - alloc_mask = gfp_mask; - if (!prepare_alloc_pages(gfp_mask, order, preferred_nid, nodemask, &ac, &alloc_mask, &alloc_flags)) + gfp &= gfp_allowed_mask; + /* + * Apply scoped allocation constraints. This is mainly about GFP_NOFS + * resp. GFP_NOIO which has to be inherited for all allocation requests + * from a particular context which has been marked by + * memalloc_no{fs,io}_{save,restore}. And PF_MEMALLOC_PIN which ensures + * movable zones are not used during allocation. + */ + gfp = current_gfp_context(gfp); + alloc_gfp = gfp; + if (!prepare_alloc_pages(gfp, order, preferred_nid, nodemask, &ac, + &alloc_gfp, &alloc_flags)) return NULL; - finalise_ac(gfp_mask, &ac); - /* * 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_mask); + alloc_flags |= alloc_flags_nofragment(ac.preferred_zoneref->zone, gfp); /* First allocation attempt */ - page = get_page_from_freelist(alloc_mask, order, alloc_flags, &ac); + page = get_page_from_freelist(alloc_gfp, order, alloc_flags, &ac); if (likely(page)) goto out; - /* - * Apply scoped allocation constraints. This is mainly about GFP_NOFS - * resp. GFP_NOIO which has to be inherited for all allocation requests - * from a particular context which has been marked by - * memalloc_no{fs,io}_{save,restore}. - */ - alloc_mask = current_gfp_context(gfp_mask); + alloc_gfp = gfp; ac.spread_dirty_pages = false; /* * Restore the original nodemask if it was potentially replaced with * &cpuset_current_mems_allowed to optimize the fast-path attempt. */ - if (unlikely(ac.nodemask != nodemask)) - ac.nodemask = nodemask; + ac.nodemask = nodemask; - page = __alloc_pages_slowpath(alloc_mask, order, &ac); + page = __alloc_pages_slowpath(alloc_gfp, order, &ac); out: - if (memcg_kmem_enabled() && (gfp_mask & __GFP_ACCOUNT) && page && - unlikely(__memcg_kmem_charge(page, gfp_mask, order) != 0)) { + if (memcg_kmem_enabled() && (gfp & __GFP_ACCOUNT) && page && + unlikely(__memcg_kmem_charge_page(page, gfp, order) != 0)) { __free_pages(page, order); page = NULL; } - trace_mm_page_alloc(page, order, alloc_mask, ac.migratetype); + trace_mm_page_alloc(page, order, alloc_gfp, ac.migratetype); + kmsan_alloc_page(page, order, alloc_gfp); return page; } -EXPORT_SYMBOL(__alloc_pages_nodemask); +EXPORT_SYMBOL(__alloc_pages); + +struct folio *__folio_alloc(gfp_t gfp, unsigned int order, int preferred_nid, + nodemask_t *nodemask) +{ + struct page *page = __alloc_pages(gfp | __GFP_COMP, order, + preferred_nid, nodemask); + + if (page && order > 1) + prep_transhuge_page(page); + return (struct folio *)page; +} +EXPORT_SYMBOL(__folio_alloc); /* * Common helper functions. Never use with __GFP_HIGHMEM because the returned @@ -4785,18 +5615,33 @@ unsigned long get_zeroed_page(gfp_t gfp_mask) } EXPORT_SYMBOL(get_zeroed_page); -static inline void free_the_page(struct page *page, unsigned int order) -{ - if (order == 0) /* Via pcp? */ - free_unref_page(page); - else - __free_pages_ok(page, order); -} - +/** + * __free_pages - Free pages allocated with alloc_pages(). + * @page: The page pointer returned from alloc_pages(). + * @order: The order of the allocation. + * + * This function can free multi-page allocations that are not compound + * pages. It does not check that the @order passed in matches that of + * the allocation, so it is easy to leak memory. Freeing more memory + * than was allocated will probably emit a warning. + * + * If the last reference to this page is speculative, it will be released + * by put_page() which only frees the first page of a non-compound + * allocation. To prevent the remaining pages from being leaked, we free + * the subsequent pages here. If you want to use the page's reference + * count to decide when to free the allocation, you should allocate a + * compound page, and use put_page() instead of __free_pages(). + * + * 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) { if (put_page_testzero(page)) free_the_page(page, order); + else if (!PageHead(page)) + while (order-- > 0) + free_the_page(page + (1 << order), order); } EXPORT_SYMBOL(__free_pages); @@ -4851,8 +5696,9 @@ void __page_frag_cache_drain(struct page *page, unsigned int count) } EXPORT_SYMBOL(__page_frag_cache_drain); -void *page_frag_alloc(struct page_frag_cache *nc, - unsigned int fragsz, gfp_t gfp_mask) +void *page_frag_alloc_align(struct page_frag_cache *nc, + unsigned int fragsz, gfp_t gfp_mask, + unsigned int align_mask) { unsigned int size = PAGE_SIZE; struct page *page; @@ -4886,6 +5732,11 @@ refill: 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; @@ -4896,14 +5747,27 @@ refill: /* 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; + } } nc->pagecnt_bias--; + offset &= align_mask; nc->offset = offset; return nc->va + offset; } -EXPORT_SYMBOL(page_frag_alloc); +EXPORT_SYMBOL(page_frag_alloc_align); /* * Frees a page fragment allocated out of either a compound or order 0 page. @@ -4921,14 +5785,18 @@ static void *make_alloc_exact(unsigned long addr, unsigned int order, size_t size) { if (addr) { - unsigned long alloc_end = addr + (PAGE_SIZE << order); - unsigned long used = addr + PAGE_ALIGN(size); + unsigned long nr = DIV_ROUND_UP(size, PAGE_SIZE); + struct page *page = virt_to_page((void *)addr); + struct page *last = page + nr; - split_page(virt_to_page((void *)addr), order); - while (used < alloc_end) { - free_page(used); - used += PAGE_SIZE; - } + split_page_owner(page, 1 << order); + split_page_memcg(page, 1 << order); + while (page < --last) + set_page_refcounted(last); + + last = page + (1UL << order); + for (page += nr; page < last; page++) + __free_pages_ok(page, 0, FPI_TO_TAIL); } return (void *)addr; } @@ -4953,8 +5821,8 @@ void *alloc_pages_exact(size_t size, gfp_t gfp_mask) unsigned int order = get_order(size); unsigned long addr; - if (WARN_ON_ONCE(gfp_mask & __GFP_COMP)) - gfp_mask &= ~__GFP_COMP; + if (WARN_ON_ONCE(gfp_mask & (__GFP_COMP | __GFP_HIGHMEM))) + gfp_mask &= ~(__GFP_COMP | __GFP_HIGHMEM); addr = __get_free_pages(gfp_mask, order); return make_alloc_exact(addr, order, size); @@ -4978,8 +5846,8 @@ void * __meminit alloc_pages_exact_nid(int nid, size_t size, gfp_t gfp_mask) unsigned int order = get_order(size); struct page *p; - if (WARN_ON_ONCE(gfp_mask & __GFP_COMP)) - gfp_mask &= ~__GFP_COMP; + if (WARN_ON_ONCE(gfp_mask & (__GFP_COMP | __GFP_HIGHMEM))) + gfp_mask &= ~(__GFP_COMP | __GFP_HIGHMEM); p = alloc_pages_node(nid, gfp_mask, order); if (!p) @@ -5053,19 +5921,6 @@ unsigned long nr_free_buffer_pages(void) } EXPORT_SYMBOL_GPL(nr_free_buffer_pages); -/** - * nr_free_pagecache_pages - count number of pages beyond high watermark - * - * nr_free_pagecache_pages() counts the number of pages which are beyond the - * high watermark within all zones. - * - * Return: number of pages beyond high watermark within all zones. - */ -unsigned long nr_free_pagecache_pages(void) -{ - return nr_free_zone_pages(gfp_zone(GFP_HIGHUSER_MOVABLE)); -} - static inline void show_node(struct zone *zone) { if (IS_ENABLED(CONFIG_NUMA)) @@ -5090,14 +5945,14 @@ 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); @@ -5108,8 +5963,8 @@ long si_mem_available(void) * items that are in use, and cannot be freed. Cap this estimate at the * low watermark. */ - reclaimable = global_node_page_state(NR_SLAB_RECLAIMABLE) + - global_node_page_state(NR_KERNEL_MISC_RECLAIMABLE); + reclaimable = global_node_page_state_pages(NR_SLAB_RECLAIMABLE_B) + + global_node_page_state(NR_KERNEL_MISC_RECLAIMABLE); available += reclaimable - min(reclaimable / 2, wmark_low); if (available < 0) @@ -5213,6 +6068,15 @@ static void show_migration_types(unsigned char type) printk(KERN_CONT "(%s) ", tmp); } +static bool node_has_managed_zones(pg_data_t *pgdat, int max_zone_idx) +{ + int zone_idx; + for (zone_idx = 0; zone_idx <= max_zone_idx; zone_idx++) + if (zone_managed_pages(pgdat->node_zones + zone_idx)) + return true; + return false; +} + /* * Show free area list (used inside shift_scroll-lock stuff) * We also calculate the percentage fragmentation. We do this by counting the @@ -5222,26 +6086,30 @@ static void show_migration_types(unsigned char type) * SHOW_MEM_FILTER_NODES: suppress nodes that are not allowed by current's * cpuset. */ -void show_free_areas(unsigned int filter, nodemask_t *nodemask) +void __show_free_areas(unsigned int filter, nodemask_t *nodemask, int max_zone_idx) { unsigned long free_pcp = 0; - int cpu; + int cpu, nid; struct zone *zone; pg_data_t *pgdat; for_each_populated_zone(zone) { + if (zone_idx(zone) > max_zone_idx) + continue; if (show_mem_node_skip(filter, zone_to_nid(zone), nodemask)) continue; for_each_online_cpu(cpu) - free_pcp += per_cpu_ptr(zone->pageset, cpu)->pcp.count; + free_pcp += per_cpu_ptr(zone->per_cpu_pageset, cpu)->count; } printk("active_anon:%lu inactive_anon:%lu isolated_anon:%lu\n" " active_file:%lu inactive_file:%lu isolated_file:%lu\n" - " unevictable:%lu dirty:%lu writeback:%lu unstable:%lu\n" + " unevictable:%lu dirty:%lu writeback:%lu\n" " slab_reclaimable:%lu slab_unreclaimable:%lu\n" - " mapped:%lu shmem:%lu pagetables:%lu bounce:%lu\n" + " mapped:%lu shmem:%lu pagetables:%lu\n" + " sec_pagetables:%lu bounce:%lu\n" + " kernel_misc_reclaimable:%lu\n" " free:%lu free_pcp:%lu free_cma:%lu\n", global_node_page_state(NR_ACTIVE_ANON), global_node_page_state(NR_INACTIVE_ANON), @@ -5252,13 +6120,14 @@ void show_free_areas(unsigned int filter, nodemask_t *nodemask) global_node_page_state(NR_UNEVICTABLE), global_node_page_state(NR_FILE_DIRTY), global_node_page_state(NR_WRITEBACK), - global_node_page_state(NR_UNSTABLE_NFS), - global_node_page_state(NR_SLAB_RECLAIMABLE), - global_node_page_state(NR_SLAB_UNRECLAIMABLE), + global_node_page_state_pages(NR_SLAB_RECLAIMABLE_B), + global_node_page_state_pages(NR_SLAB_UNRECLAIMABLE_B), global_node_page_state(NR_FILE_MAPPED), global_node_page_state(NR_SHMEM), - global_zone_page_state(NR_PAGETABLE), + global_node_page_state(NR_PAGETABLE), + global_node_page_state(NR_SECONDARY_PAGETABLE), global_zone_page_state(NR_BOUNCE), + global_node_page_state(NR_KERNEL_MISC_RECLAIMABLE), global_zone_page_state(NR_FREE_PAGES), free_pcp, global_zone_page_state(NR_FREE_CMA_PAGES)); @@ -5266,6 +6135,8 @@ void show_free_areas(unsigned int filter, nodemask_t *nodemask) for_each_online_pgdat(pgdat) { if (show_mem_node_skip(filter, pgdat->node_id, nodemask)) continue; + if (!node_has_managed_zones(pgdat, max_zone_idx)) + continue; printk("Node %d" " active_anon:%lukB" @@ -5285,7 +6156,12 @@ void show_free_areas(unsigned int filter, nodemask_t *nodemask) " anon_thp: %lukB" #endif " writeback_tmp:%lukB" - " unstable:%lukB" + " kernel_stack:%lukB" +#ifdef CONFIG_SHADOW_CALL_STACK + " shadow_call_stack:%lukB" +#endif + " pagetables:%lukB" + " sec_pagetables:%lukB" " all_unreclaimable? %s" "\n", pgdat->node_id, @@ -5301,13 +6177,17 @@ void show_free_areas(unsigned int filter, nodemask_t *nodemask) K(node_page_state(pgdat, NR_WRITEBACK)), K(node_page_state(pgdat, NR_SHMEM)), #ifdef CONFIG_TRANSPARENT_HUGEPAGE - K(node_page_state(pgdat, NR_SHMEM_THPS) * HPAGE_PMD_NR), - K(node_page_state(pgdat, NR_SHMEM_PMDMAPPED) - * HPAGE_PMD_NR), - K(node_page_state(pgdat, NR_ANON_THPS) * HPAGE_PMD_NR), + K(node_page_state(pgdat, NR_SHMEM_THPS)), + K(node_page_state(pgdat, NR_SHMEM_PMDMAPPED)), + K(node_page_state(pgdat, NR_ANON_THPS)), #endif K(node_page_state(pgdat, NR_WRITEBACK_TEMP)), - K(node_page_state(pgdat, NR_UNSTABLE_NFS)), + node_page_state(pgdat, NR_KERNEL_STACK_KB), +#ifdef CONFIG_SHADOW_CALL_STACK + node_page_state(pgdat, NR_KERNEL_SCS_KB), +#endif + K(node_page_state(pgdat, NR_PAGETABLE)), + K(node_page_state(pgdat, NR_SECONDARY_PAGETABLE)), pgdat->kswapd_failures >= MAX_RECLAIM_RETRIES ? "yes" : "no"); } @@ -5315,17 +6195,20 @@ void show_free_areas(unsigned int filter, nodemask_t *nodemask) for_each_populated_zone(zone) { int i; + if (zone_idx(zone) > max_zone_idx) + continue; if (show_mem_node_skip(filter, zone_to_nid(zone), nodemask)) continue; free_pcp = 0; for_each_online_cpu(cpu) - free_pcp += per_cpu_ptr(zone->pageset, cpu)->pcp.count; + free_pcp += per_cpu_ptr(zone->per_cpu_pageset, cpu)->count; show_node(zone); printk(KERN_CONT "%s" " free:%lukB" + " boost:%lukB" " min:%lukB" " low:%lukB" " high:%lukB" @@ -5339,8 +6222,6 @@ void show_free_areas(unsigned int filter, nodemask_t *nodemask) " present:%lukB" " managed:%lukB" " mlocked:%lukB" - " kernel_stack:%lukB" - " pagetables:%lukB" " bounce:%lukB" " free_pcp:%lukB" " local_pcp:%ukB" @@ -5348,6 +6229,7 @@ void show_free_areas(unsigned int filter, nodemask_t *nodemask) "\n", zone->name, K(zone_page_state(zone, NR_FREE_PAGES)), + K(zone->watermark_boost), K(min_wmark_pages(zone)), K(low_wmark_pages(zone)), K(high_wmark_pages(zone)), @@ -5361,11 +6243,9 @@ void show_free_areas(unsigned int filter, nodemask_t *nodemask) K(zone->present_pages), K(zone_managed_pages(zone)), K(zone_page_state(zone, NR_MLOCK)), - zone_page_state(zone, NR_KERNEL_STACK_KB), - K(zone_page_state(zone, NR_PAGETABLE)), K(zone_page_state(zone, NR_BOUNCE)), K(free_pcp), - K(this_cpu_read(zone->pageset->pcp.count)), + K(this_cpu_read(zone->per_cpu_pageset->count)), K(zone_page_state(zone, NR_FREE_CMA_PAGES))); printk("lowmem_reserve[]:"); for (i = 0; i < MAX_NR_ZONES; i++) @@ -5378,6 +6258,8 @@ void show_free_areas(unsigned int filter, nodemask_t *nodemask) unsigned long nr[MAX_ORDER], flags, total = 0; unsigned char types[MAX_ORDER]; + if (zone_idx(zone) > max_zone_idx) + continue; if (show_mem_node_skip(filter, zone_to_nid(zone), nodemask)) continue; show_node(zone); @@ -5407,7 +6289,11 @@ 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)); @@ -5434,7 +6320,7 @@ 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); } @@ -5448,7 +6334,7 @@ static int build_zonerefs_node(pg_data_t *pgdat, struct zoneref *zonerefs) static int __parse_numa_zonelist_order(char *s) { /* - * We used to support different zonlists modes but they turned + * We used to support different zonelists modes but they turned * out to be just not useful. Let's keep the warning in place * if somebody still use the cmd line parameter so that we do * not fail it silently @@ -5460,40 +6346,20 @@ static int __parse_numa_zonelist_order(char *s) return 0; } -static __init int setup_numa_zonelist_order(char *s) -{ - if (!s) - return 0; - - return __parse_numa_zonelist_order(s); -} -early_param("numa_zonelist_order", setup_numa_zonelist_order); - char numa_zonelist_order[] = "Node"; /* * sysctl handler for numa_zonelist_order */ int numa_zonelist_order_handler(struct ctl_table *table, int write, - void __user *buffer, size_t *length, - loff_t *ppos) + void *buffer, size_t *length, loff_t *ppos) { - char *str; - int ret; - - if (!write) - return proc_dostring(table, write, buffer, length, ppos); - str = memdup_user_nul(buffer, 16); - if (IS_ERR(str)) - return PTR_ERR(str); - - ret = __parse_numa_zonelist_order(str); - kfree(str); - return ret; + if (write) + return __parse_numa_zonelist_order(buffer); + return proc_dostring(table, write, buffer, length, ppos); } -#define MAX_NODE_LOAD (nr_online_nodes) static int node_load[MAX_NUMNODES]; /** @@ -5511,12 +6377,11 @@ static int node_load[MAX_NUMNODES]; * * Return: node id of the found node or %NUMA_NO_NODE if no node is found. */ -static int find_next_best_node(int node, nodemask_t *used_node_mask) +int find_next_best_node(int node, nodemask_t *used_node_mask) { int n, val; int min_val = INT_MAX; int best_node = NUMA_NO_NODE; - const struct cpumask *tmp = cpumask_of_node(0); /* Use the local node if we haven't already */ if (!node_isset(node, *used_node_mask)) { @@ -5537,12 +6402,11 @@ static int find_next_best_node(int node, nodemask_t *used_node_mask) val += (n < node); /* Give preference to headless and unused nodes */ - tmp = cpumask_of_node(n); - if (!cpumask_empty(tmp)) + if (!cpumask_empty(cpumask_of_node(n))) 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) { @@ -5608,15 +6472,13 @@ 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; - nodemask_t used_mask; + 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; - nodes_clear(used_mask); memset(node_order, 0, sizeof(node_order)); while ((node = find_next_best_node(local_node, &used_mask)) >= 0) { @@ -5627,15 +6489,18 @@ 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); build_thisnode_zonelists(pgdat); + pr_info("Fallback order for Node %d: ", local_node); + for (node = 0; node < nr_nodes; node++) + pr_cont("%d ", node_order[node]); + pr_cont("\n"); } #ifdef CONFIG_HAVE_MEMORYLESS_NODES @@ -5714,8 +6579,12 @@ static void build_zonelists(pg_data_t *pgdat) * not check if the processor is online before following the pageset pointer. * Other parts of the kernel may not check if the zone is available. */ -static void setup_pageset(struct per_cpu_pageset *p, unsigned long batch); -static DEFINE_PER_CPU(struct per_cpu_pageset, boot_pageset); +static void per_cpu_pages_init(struct per_cpu_pages *pcp, struct per_cpu_zonestat *pzstats); +/* These effectively disable the pcplists in the boot pageset completely */ +#define BOOT_PAGESET_HIGH 0 +#define BOOT_PAGESET_BATCH 1 +static DEFINE_PER_CPU(struct per_cpu_pages, boot_pageset); +static DEFINE_PER_CPU(struct per_cpu_zonestat, boot_zonestats); static DEFINE_PER_CPU(struct per_cpu_nodestat, boot_nodestats); static void __build_all_zonelists(void *data) @@ -5723,9 +6592,8 @@ static void __build_all_zonelists(void *data) int nid; int __maybe_unused cpu; pg_data_t *self = data; - static DEFINE_SPINLOCK(lock); - spin_lock(&lock); + write_seqlock(&zonelist_update_seq); #ifdef CONFIG_NUMA memset(node_load, 0, sizeof(node_load)); @@ -5738,7 +6606,11 @@ static void __build_all_zonelists(void *data) if (self && !node_online(self->node_id)) { build_zonelists(self); } else { - for_each_online_node(nid) { + /* + * All possible nodes have pgdat preallocated + * in free_area_init + */ + for_each_node(nid) { pg_data_t *pgdat = NODE_DATA(nid); build_zonelists(pgdat); @@ -5758,7 +6630,7 @@ static void __build_all_zonelists(void *data) #endif } - spin_unlock(&lock); + write_sequnlock(&zonelist_update_seq); } static noinline void __init @@ -5782,7 +6654,7 @@ build_all_zonelists_init(void) * (a chicken-egg dilemma). */ for_each_possible_cpu(cpu) - setup_pageset(&per_cpu(boot_pageset, cpu), 0); + per_cpu_pages_init(&per_cpu(boot_pageset, cpu), &per_cpu(boot_zonestats, cpu)); mminit_verify_zonelist(); cpuset_init_current_mems_allowed(); @@ -5796,13 +6668,16 @@ build_all_zonelists_init(void) */ void __ref build_all_zonelists(pg_data_t *pgdat) { + unsigned long vm_total_pages; + if (system_state == SYSTEM_BOOTING) { build_all_zonelists_init(); } else { __build_all_zonelists(pgdat); /* cpuset refresh routine should be here */ } - vm_total_pages = nr_free_pagecache_pages(); + /* Get the number of free pages beyond high watermark in all zones. */ + vm_total_pages = nr_free_zone_pages(gfp_zone(GFP_HIGHUSER_MOVABLE)); /* * Disable grouping by mobility if the number of pages in the * system is too low to allow the mechanism to work. It would be @@ -5828,12 +6703,11 @@ void __ref build_all_zonelists(pg_data_t *pgdat) static bool __meminit overlap_memmap_init(unsigned long zone, unsigned long *pfn) { -#ifdef CONFIG_HAVE_MEMBLOCK_NODE_MAP static struct memblock_region *r; if (mirrored_kernelcore && zone == ZONE_MOVABLE) { if (!r || *pfn >= memblock_region_memory_end_pfn(r)) { - for_each_memblock(memory, r) { + for_each_mem_region(r) { if (*pfn < memblock_region_memory_end_pfn(r)) break; } @@ -5844,35 +6718,22 @@ overlap_memmap_init(unsigned long zone, unsigned long *pfn) return true; } } -#endif return false; } -#ifdef CONFIG_SPARSEMEM -/* Skip PFNs that belong to non-present sections */ -static inline __meminit unsigned long next_pfn(unsigned long pfn) -{ - const unsigned long section_nr = pfn_to_section_nr(++pfn); - - if (present_section_nr(section_nr)) - return pfn; - return section_nr_to_pfn(next_present_section_nr(section_nr)); -} -#else -static inline __meminit unsigned long next_pfn(unsigned long pfn) -{ - return pfn++; -} -#endif - /* * Initially all pages are reserved - free ones are freed * up by memblock_free_all() once the early boot process is * done. Non-atomic initialization, single-pass. + * + * All aligned pageblocks are initialized to the specified migratetype + * (usually MIGRATE_MOVABLE). Besides setting the migratetype, no related + * zone stats (e.g., nr_isolate_pageblock) are touched. */ -void __meminit memmap_init_zone(unsigned long size, int nid, unsigned long zone, - unsigned long start_pfn, enum memmap_context context, - struct vmem_altmap *altmap) +void __meminit memmap_init_range(unsigned long size, int nid, unsigned long zone, + unsigned long start_pfn, unsigned long zone_end_pfn, + enum meminit_context context, + struct vmem_altmap *altmap, int migratetype) { unsigned long pfn, end_pfn = start_pfn + size; struct page *page; @@ -5903,40 +6764,25 @@ void __meminit memmap_init_zone(unsigned long size, int nid, unsigned long zone, * There can be holes in boot-time mem_map[]s handed to this * function. They do not exist on hotplugged memory. */ - if (context == MEMMAP_EARLY) { - if (!early_pfn_valid(pfn)) { - pfn = next_pfn(pfn); - continue; - } - if (!early_pfn_in_nid(pfn, nid)) { - pfn++; - continue; - } + if (context == MEMINIT_EARLY) { if (overlap_memmap_init(zone, &pfn)) continue; - if (defer_init(nid, pfn, end_pfn)) + if (defer_init(nid, pfn, zone_end_pfn)) break; } page = pfn_to_page(pfn); __init_single_page(page, pfn, zone, nid); - if (context == MEMMAP_HOTPLUG) + if (context == MEMINIT_HOTPLUG) __SetPageReserved(page); /* - * Mark the block movable so that blocks are reserved for - * movable at startup. This will force kernel allocations - * to reserve their blocks rather than leaking throughout - * the address space during boot when many long-lived - * kernel allocations are made. - * - * bitmap is created for zone's valid pfn range. but memmap - * can be created for invalid pages (for alignment) - * check here not to call set_pageblock_migratetype() against - * pfn out of zone. + * Usually, we want to mark the pageblock MIGRATE_MOVABLE, + * such that unmovable allocations won't be scattered all + * over the place during system boot. */ - if (!(pfn & (pageblock_nr_pages - 1))) { - set_pageblock_migratetype(page, MIGRATE_MOVABLE); + if (pageblock_aligned(pfn)) { + set_pageblock_migratetype(page, migratetype); cond_resched(); } pfn++; @@ -5944,6 +6790,98 @@ void __meminit memmap_init_zone(unsigned long size, int nid, unsigned long zone, } #ifdef CONFIG_ZONE_DEVICE +static void __ref __init_zone_device_page(struct page *page, unsigned long pfn, + unsigned long zone_idx, int nid, + struct dev_pagemap *pgmap) +{ + + __init_single_page(page, pfn, zone_idx, nid); + + /* + * Mark page reserved as it will need to wait for onlining + * phase for it to be fully associated with a zone. + * + * We can use the non-atomic __set_bit operation for setting + * the flag as we are still initializing the pages. + */ + __SetPageReserved(page); + + /* + * ZONE_DEVICE pages union ->lru with a ->pgmap back pointer + * and zone_device_data. It is a bug if a ZONE_DEVICE page is + * ever freed or placed on a driver-private list. + */ + page->pgmap = pgmap; + page->zone_device_data = NULL; + + /* + * Mark the block movable so that blocks are reserved for + * movable at startup. This will force kernel allocations + * to reserve their blocks rather than leaking throughout + * the address space during boot when many long-lived + * kernel allocations are made. + * + * Please note that MEMINIT_HOTPLUG path doesn't clear memmap + * because this is done early in section_activate() + */ + if (pageblock_aligned(pfn)) { + set_pageblock_migratetype(page, MIGRATE_MOVABLE); + cond_resched(); + } + + /* + * ZONE_DEVICE pages are released directly to the driver page allocator + * which will set the page count to 1 when allocating the page. + */ + if (pgmap->type == MEMORY_DEVICE_PRIVATE || + pgmap->type == MEMORY_DEVICE_COHERENT) + set_page_count(page, 0); +} + +/* + * 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, + struct dev_pagemap *pgmap, + unsigned long nr_pages) +{ + unsigned long pfn, end_pfn = head_pfn + nr_pages; + unsigned int order = pgmap->vmemmap_shift; + + __SetPageHead(head); + for (pfn = head_pfn + 1; pfn < end_pfn; pfn++) { + struct page *page = pfn_to_page(pfn); + + __init_zone_device_page(page, pfn, zone_idx, nid, pgmap); + prep_compound_tail(head, pfn - head_pfn); + set_page_count(page, 0); + + /* + * The first tail page stores compound_mapcount_ptr() and + * compound_order() and the second tail page stores + * compound_pincount_ptr(). Call prep_compound_head() after + * the first and second tail pages have been initialized to + * not have the data overwritten. + */ + if (pfn == head_pfn + 2) + prep_compound_head(head, order); + } +} + void __ref memmap_init_zone_device(struct zone *zone, unsigned long start_pfn, unsigned long nr_pages, @@ -5952,15 +6890,16 @@ void __ref memmap_init_zone_device(struct zone *zone, unsigned long pfn, end_pfn = start_pfn + nr_pages; struct pglist_data *pgdat = zone->zone_pgdat; struct vmem_altmap *altmap = pgmap_altmap(pgmap); + unsigned int pfns_per_compound = pgmap_vmemmap_nr(pgmap); unsigned long zone_idx = zone_idx(zone); unsigned long start = jiffies; int nid = pgdat->node_id; - if (WARN_ON_ONCE(!pgmap || zone_idx(zone) != ZONE_DEVICE)) + if (WARN_ON_ONCE(!pgmap || zone_idx != ZONE_DEVICE)) return; /* - * The call to memmap_init_zone should have already taken care + * The call to memmap_init should have already taken care * of the pages reserved for the memmap, so we can just jump to * the end of that region and start processing the device pages. */ @@ -5969,47 +6908,16 @@ void __ref memmap_init_zone_device(struct zone *zone, nr_pages = end_pfn - start_pfn; } - for (pfn = start_pfn; pfn < end_pfn; pfn++) { + for (pfn = start_pfn; pfn < end_pfn; pfn += pfns_per_compound) { struct page *page = pfn_to_page(pfn); - __init_single_page(page, pfn, zone_idx, nid); - - /* - * Mark page reserved as it will need to wait for onlining - * phase for it to be fully associated with a zone. - * - * We can use the non-atomic __set_bit operation for setting - * the flag as we are still initializing the pages. - */ - __SetPageReserved(page); + __init_zone_device_page(page, pfn, zone_idx, nid, pgmap); - /* - * ZONE_DEVICE pages union ->lru with a ->pgmap back pointer - * and zone_device_data. It is a bug if a ZONE_DEVICE page is - * ever freed or placed on a driver-private list. - */ - page->pgmap = pgmap; - page->zone_device_data = NULL; + if (pfns_per_compound == 1) + continue; - /* - * Mark the block movable so that blocks are reserved for - * movable at startup. This will force kernel allocations - * to reserve their blocks rather than leaking throughout - * the address space during boot when many long-lived - * kernel allocations are made. - * - * bitmap is created for zone's valid pfn range. but memmap - * can be created for invalid pages (for alignment) - * check here not to call set_pageblock_migratetype() against - * pfn out of zone. - * - * Please note that MEMMAP_HOTPLUG path doesn't clear memmap - * because this is done early in section_activate() - */ - if (!(pfn & (pageblock_nr_pages - 1))) { - set_pageblock_migratetype(page, MIGRATE_MOVABLE); - cond_resched(); - } + memmap_init_compound(page, pfn, zone_idx, nid, pgmap, + compound_nr_pages(altmap, pfns_per_compound)); } pr_info("%s initialised %lu pages in %ums\n", __func__, @@ -6026,10 +6934,129 @@ static void __meminit zone_init_free_lists(struct zone *zone) } } -void __meminit __weak memmap_init(unsigned long size, int nid, - unsigned long zone, unsigned long start_pfn) +/* + * Only struct pages that correspond to ranges defined by memblock.memory + * are zeroed and initialized by going through __init_single_page() during + * memmap_init_zone_range(). + * + * But, there could be struct pages that correspond to holes in + * memblock.memory. This can happen because of the following reasons: + * - physical memory bank size is not necessarily the exact multiple of the + * arbitrary section size + * - early reserved memory may not be listed in memblock.memory + * - memory layouts defined with memmap= kernel parameter may not align + * nicely with memmap sections + * + * Explicitly initialize those struct pages so that: + * - PG_Reserved is set + * - zone and node links point to zone and node that span the page if the + * hole is in the middle of a zone + * - zone and node links point to adjacent zone/node if the hole falls on + * the zone boundary; the pages in such holes will be prepended to the + * zone/node above the hole except for the trailing pages in the last + * section that will be appended to the zone/node below. + */ +static void __init init_unavailable_range(unsigned long spfn, + unsigned long epfn, + int zone, int node) +{ + unsigned long pfn; + u64 pgcnt = 0; + + for (pfn = spfn; pfn < epfn; pfn++) { + if (!pfn_valid(pageblock_start_pfn(pfn))) { + pfn = pageblock_end_pfn(pfn) - 1; + continue; + } + __init_single_page(pfn_to_page(pfn), pfn, zone, node); + __SetPageReserved(pfn_to_page(pfn)); + pgcnt++; + } + + if (pgcnt) + pr_info("On node %d, zone %s: %lld pages in unavailable ranges", + node, zone_names[zone], pgcnt); +} + +static void __init memmap_init_zone_range(struct zone *zone, + unsigned long start_pfn, + unsigned long end_pfn, + unsigned long *hole_pfn) +{ + unsigned long zone_start_pfn = zone->zone_start_pfn; + unsigned long zone_end_pfn = zone_start_pfn + zone->spanned_pages; + int nid = zone_to_nid(zone), zone_id = zone_idx(zone); + + start_pfn = clamp(start_pfn, zone_start_pfn, zone_end_pfn); + end_pfn = clamp(end_pfn, zone_start_pfn, zone_end_pfn); + + if (start_pfn >= end_pfn) + return; + + memmap_init_range(end_pfn - start_pfn, nid, zone_id, start_pfn, + zone_end_pfn, MEMINIT_EARLY, NULL, MIGRATE_MOVABLE); + + if (*hole_pfn < start_pfn) + init_unavailable_range(*hole_pfn, start_pfn, zone_id, nid); + + *hole_pfn = end_pfn; +} + +static void __init memmap_init(void) +{ + unsigned long start_pfn, end_pfn; + unsigned long hole_pfn = 0; + int i, j, zone_id = 0, nid; + + for_each_mem_pfn_range(i, MAX_NUMNODES, &start_pfn, &end_pfn, &nid) { + struct pglist_data *node = NODE_DATA(nid); + + for (j = 0; j < MAX_NR_ZONES; j++) { + struct zone *zone = node->node_zones + j; + + if (!populated_zone(zone)) + continue; + + memmap_init_zone_range(zone, start_pfn, end_pfn, + &hole_pfn); + zone_id = j; + } + } + +#ifdef CONFIG_SPARSEMEM + /* + * Initialize the memory map for hole in the range [memory_end, + * section_end]. + * Append the pages in this hole to the highest zone in the last + * node. + * The call to init_unavailable_range() is outside the ifdef to + * silence the compiler warining about zone_id set but not used; + * for FLATMEM it is a nop anyway + */ + end_pfn = round_up(end_pfn, PAGES_PER_SECTION); + if (hole_pfn < end_pfn) +#endif + init_unavailable_range(hole_pfn, end_pfn, zone_id, nid); +} + +void __init *memmap_alloc(phys_addr_t size, phys_addr_t align, + phys_addr_t min_addr, int nid, bool exact_nid) { - memmap_init_zone(size, nid, zone, start_pfn, MEMMAP_EARLY, NULL); + void *ptr; + + if (exact_nid) + ptr = memblock_alloc_exact_nid_raw(size, align, min_addr, + MEMBLOCK_ALLOC_ACCESSIBLE, + nid); + else + ptr = memblock_alloc_try_nid_raw(size, align, min_addr, + MEMBLOCK_ALLOC_ACCESSIBLE, + nid); + + if (ptr && size > 0) + page_init_poison(ptr, size); + + return ptr; } static int zone_batchsize(struct zone *zone) @@ -6038,13 +7065,12 @@ static int zone_batchsize(struct zone *zone) int batch; /* - * The per-cpu-pages pools are set to around 1000th of the - * size of the zone. + * The number of pages to batch allocate is either ~0.1% + * of the zone or 1MB, whichever is smaller. The batch + * size is striking a balance between allocation latency + * and zone lock contention. */ - batch = zone_managed_pages(zone) / 1024; - /* But no more than a meg. */ - if (batch * PAGE_SIZE > 1024 * 1024) - batch = (1024 * 1024) / PAGE_SIZE; + batch = min(zone_managed_pages(zone) >> 10, SZ_1M / PAGE_SIZE); batch /= 4; /* We effectively *= 4 below */ if (batch < 1) batch = 1; @@ -6081,14 +7107,65 @@ static int zone_batchsize(struct zone *zone) #endif } +static int zone_highsize(struct zone *zone, int batch, int cpu_online) +{ +#ifdef CONFIG_MMU + int high; + int nr_split_cpus; + unsigned long total_pages; + + if (!percpu_pagelist_high_fraction) { + /* + * By default, the high value of the pcp is based on the zone + * low watermark so that if they are full then background + * reclaim will not be started prematurely. + */ + total_pages = low_wmark_pages(zone); + } else { + /* + * If percpu_pagelist_high_fraction is configured, the high + * value is based on a fraction of the managed pages in the + * zone. + */ + total_pages = zone_managed_pages(zone) / percpu_pagelist_high_fraction; + } + + /* + * Split the high value across all online CPUs local to the zone. Note + * that early in boot that CPUs may not be online yet and that during + * CPU hotplug that the cpumask is not yet updated when a CPU is being + * onlined. For memory nodes that have no CPUs, split pcp->high across + * all online CPUs to mitigate the risk that reclaim is triggered + * prematurely due to pages stored on pcp lists. + */ + nr_split_cpus = cpumask_weight(cpumask_of_node(zone_to_nid(zone))) + cpu_online; + if (!nr_split_cpus) + nr_split_cpus = num_online_cpus(); + high = total_pages / nr_split_cpus; + + /* + * Ensure high is at least batch*4. The multiple is based on the + * historical relationship between high and batch. + */ + high = max(high, batch << 2); + + return high; +#else + return 0; +#endif +} + /* - * pcp->high and pcp->batch values are related and dependent on one another: - * ->batch must never be higher then ->high. - * The following function updates them in a safe manner without read side - * locking. + * pcp->high and pcp->batch values are related and generally batch is lower + * than high. They are also related to pcp->count such that count is lower + * than high, and as soon as it reaches high, the pcplist is flushed. * - * Any new users of pcp->batch and pcp->high should ensure they can cope with - * those fields changing asynchronously (acording the the above rule). + * However, guaranteeing these relations at all times would require e.g. write + * barriers here but also careful usage of read barriers at the read side, and + * thus be prone to error and bad for performance. Thus the update only prevents + * store tearing. Any new users of pcp->batch and pcp->high should ensure they + * can cope with those fields changing asynchronously, and fully trust only the + * pcp->count field on the local CPU with interrupts disabled. * * mutex_is_locked(&pcp_batch_high_lock) required when calling this function * outside of boot time (or some other assurance that no concurrent updaters @@ -6097,80 +7174,95 @@ static int zone_batchsize(struct zone *zone) static void pageset_update(struct per_cpu_pages *pcp, unsigned long high, unsigned long batch) { - /* start with a fail safe value for batch */ - pcp->batch = 1; - smp_wmb(); - - /* Update high, then batch, in order */ - pcp->high = high; - smp_wmb(); - - pcp->batch = batch; + WRITE_ONCE(pcp->batch, batch); + WRITE_ONCE(pcp->high, high); } -/* a companion to pageset_set_high() */ -static void pageset_set_batch(struct per_cpu_pageset *p, unsigned long batch) +static void per_cpu_pages_init(struct per_cpu_pages *pcp, struct per_cpu_zonestat *pzstats) { - pageset_update(&p->pcp, 6 * batch, max(1UL, 1 * batch)); -} + int pindex; -static void pageset_init(struct per_cpu_pageset *p) -{ - struct per_cpu_pages *pcp; - int migratetype; + memset(pcp, 0, sizeof(*pcp)); + memset(pzstats, 0, sizeof(*pzstats)); - memset(p, 0, sizeof(*p)); + spin_lock_init(&pcp->lock); + for (pindex = 0; pindex < NR_PCP_LISTS; pindex++) + INIT_LIST_HEAD(&pcp->lists[pindex]); - pcp = &p->pcp; - for (migratetype = 0; migratetype < MIGRATE_PCPTYPES; migratetype++) - INIT_LIST_HEAD(&pcp->lists[migratetype]); + /* + * Set batch and high values safe for a boot pageset. A true percpu + * pageset's initialization will update them subsequently. Here we don't + * need to be as careful as pageset_update() as nobody can access the + * pageset yet. + */ + pcp->high = BOOT_PAGESET_HIGH; + pcp->batch = BOOT_PAGESET_BATCH; + pcp->free_factor = 0; } -static void setup_pageset(struct per_cpu_pageset *p, unsigned long batch) +static void __zone_set_pageset_high_and_batch(struct zone *zone, unsigned long high, + unsigned long batch) { - pageset_init(p); - pageset_set_batch(p, batch); + struct per_cpu_pages *pcp; + int cpu; + + for_each_possible_cpu(cpu) { + pcp = per_cpu_ptr(zone->per_cpu_pageset, cpu); + pageset_update(pcp, high, batch); + } } /* - * pageset_set_high() sets the high water mark for hot per_cpu_pagelist - * to the value high for the pageset p. + * Calculate and set new high and batch values for all per-cpu pagesets of a + * zone based on the zone's size. */ -static void pageset_set_high(struct per_cpu_pageset *p, - unsigned long high) +static void zone_set_pageset_high_and_batch(struct zone *zone, int cpu_online) { - unsigned long batch = max(1UL, high / 4); - if ((high / 4) > (PAGE_SHIFT * 8)) - batch = PAGE_SHIFT * 8; + int new_high, new_batch; - pageset_update(&p->pcp, high, batch); -} + new_batch = max(1, zone_batchsize(zone)); + new_high = zone_highsize(zone, new_batch, cpu_online); -static void pageset_set_high_and_batch(struct zone *zone, - struct per_cpu_pageset *pcp) -{ - if (percpu_pagelist_fraction) - pageset_set_high(pcp, - (zone_managed_pages(zone) / - percpu_pagelist_fraction)); - else - pageset_set_batch(pcp, zone_batchsize(zone)); -} + if (zone->pageset_high == new_high && + zone->pageset_batch == new_batch) + return; -static void __meminit zone_pageset_init(struct zone *zone, int cpu) -{ - struct per_cpu_pageset *pcp = per_cpu_ptr(zone->pageset, cpu); + zone->pageset_high = new_high; + zone->pageset_batch = new_batch; - pageset_init(pcp); - pageset_set_high_and_batch(zone, pcp); + __zone_set_pageset_high_and_batch(zone, new_high, new_batch); } void __meminit setup_zone_pageset(struct zone *zone) { int cpu; - zone->pageset = alloc_percpu(struct per_cpu_pageset); - for_each_possible_cpu(cpu) - zone_pageset_init(zone, cpu); + + /* Size may be 0 on !SMP && !NUMA */ + if (sizeof(struct per_cpu_zonestat) > 0) + zone->per_cpu_zonestats = alloc_percpu(struct per_cpu_zonestat); + + zone->per_cpu_pageset = alloc_percpu(struct per_cpu_pages); + for_each_possible_cpu(cpu) { + struct per_cpu_pages *pcp; + struct per_cpu_zonestat *pzstats; + + pcp = per_cpu_ptr(zone->per_cpu_pageset, cpu); + pzstats = per_cpu_ptr(zone->per_cpu_zonestats, cpu); + per_cpu_pages_init(pcp, pzstats); + } + + zone_set_pageset_high_and_batch(zone, 0); +} + +/* + * The zone indicated has a new number of managed_pages; batch sizes and percpu + * page high values need to be recalculated. + */ +static void zone_pcp_update(struct zone *zone, int cpu_online) +{ + mutex_lock(&pcp_batch_high_lock); + zone_set_pageset_high_and_batch(zone, cpu_online); + mutex_unlock(&pcp_batch_high_lock); } /* @@ -6181,10 +7273,25 @@ void __init setup_per_cpu_pageset(void) { struct pglist_data *pgdat; struct zone *zone; + int __maybe_unused cpu; for_each_populated_zone(zone) setup_zone_pageset(zone); +#ifdef CONFIG_NUMA + /* + * Unpopulated zones continue using the boot pagesets. + * The numa stats for these pagesets need to be reset. + * Otherwise, they will end up skewing the stats of + * the nodes these zones are associated with. + */ + for_each_possible_cpu(cpu) { + struct per_cpu_zonestat *pzstats = &per_cpu(boot_zonestats, cpu); + memset(pzstats->vm_numa_event, 0, + sizeof(pzstats->vm_numa_event)); + } +#endif + for_each_online_pgdat(pgdat) pgdat->per_cpu_nodestats = alloc_percpu(struct per_cpu_nodestat); @@ -6197,12 +7304,14 @@ static __meminit void zone_pcp_init(struct zone *zone) * relies on the ability of the linker to provide the * offset of a (static) per cpu variable into the per cpu area. */ - zone->pageset = &boot_pageset; + zone->per_cpu_pageset = &boot_pageset; + zone->per_cpu_zonestats = &boot_zonestats; + zone->pageset_high = BOOT_PAGESET_HIGH; + zone->pageset_batch = BOOT_PAGESET_BATCH; if (populated_zone(zone)) - printk(KERN_DEBUG " %s zone: %lu pages, LIFO batch:%u\n", - zone->name, zone->present_pages, - zone_batchsize(zone)); + pr_debug(" %s zone: %lu pages, LIFO batch:%u\n", zone->name, + zone->present_pages, zone_batchsize(zone)); } void __meminit init_currently_empty_zone(struct zone *zone, @@ -6227,73 +7336,6 @@ void __meminit init_currently_empty_zone(struct zone *zone, zone->initialized = 1; } -#ifdef CONFIG_HAVE_MEMBLOCK_NODE_MAP -#ifndef CONFIG_HAVE_ARCH_EARLY_PFN_TO_NID - -/* - * Required by SPARSEMEM. Given a PFN, return what node the PFN is on. - */ -int __meminit __early_pfn_to_nid(unsigned long pfn, - struct mminit_pfnnid_cache *state) -{ - unsigned long start_pfn, end_pfn; - int nid; - - if (state->last_start <= pfn && pfn < state->last_end) - return state->last_nid; - - nid = memblock_search_pfn_nid(pfn, &start_pfn, &end_pfn); - if (nid != NUMA_NO_NODE) { - state->last_start = start_pfn; - state->last_end = end_pfn; - state->last_nid = nid; - } - - return nid; -} -#endif /* CONFIG_HAVE_ARCH_EARLY_PFN_TO_NID */ - -/** - * free_bootmem_with_active_regions - Call memblock_free_early_nid for each active range - * @nid: The node to free memory on. If MAX_NUMNODES, all nodes are freed. - * @max_low_pfn: The highest PFN that will be passed to memblock_free_early_nid - * - * If an architecture guarantees that all ranges registered contain no holes - * and may be freed, this this function may be used instead of calling - * memblock_free_early_nid() manually. - */ -void __init free_bootmem_with_active_regions(int nid, unsigned long max_low_pfn) -{ - unsigned long start_pfn, end_pfn; - int i, this_nid; - - for_each_mem_pfn_range(i, nid, &start_pfn, &end_pfn, &this_nid) { - start_pfn = min(start_pfn, max_low_pfn); - end_pfn = min(end_pfn, max_low_pfn); - - if (start_pfn < end_pfn) - memblock_free_early_nid(PFN_PHYS(start_pfn), - (end_pfn - start_pfn) << PAGE_SHIFT, - this_nid); - } -} - -/** - * sparse_memory_present_with_active_regions - Call memory_present for each active range - * @nid: The node to call memory_present for. If MAX_NUMNODES, all nodes will be used. - * - * If an architecture guarantees that all ranges registered contain no holes and may - * be freed, this function may be used instead of calling memory_present() manually. - */ -void __init sparse_memory_present_with_active_regions(int nid) -{ - unsigned long start_pfn, end_pfn; - int i, this_nid; - - for_each_mem_pfn_range(i, nid, &start_pfn, &end_pfn, &this_nid) - memory_present(this_nid, start_pfn, end_pfn); -} - /** * get_pfn_range_for_nid - Return the start and end page frames for a node * @nid: The nid to return the range for. If MAX_NUMNODES, the min and max PFN are returned. @@ -6390,8 +7432,7 @@ static unsigned long __init zone_spanned_pages_in_node(int nid, unsigned long node_start_pfn, unsigned long node_end_pfn, unsigned long *zone_start_pfn, - unsigned long *zone_end_pfn, - unsigned long *ignored) + unsigned long *zone_end_pfn) { unsigned long zone_low = arch_zone_lowest_possible_pfn[zone_type]; unsigned long zone_high = arch_zone_highest_possible_pfn[zone_type]; @@ -6455,8 +7496,7 @@ unsigned long __init absent_pages_in_range(unsigned long start_pfn, static unsigned long __init zone_absent_pages_in_node(int nid, unsigned long zone_type, unsigned long node_start_pfn, - unsigned long node_end_pfn, - unsigned long *ignored) + unsigned long node_end_pfn) { unsigned long zone_low = arch_zone_lowest_possible_pfn[zone_type]; unsigned long zone_high = arch_zone_highest_possible_pfn[zone_type]; @@ -6484,7 +7524,7 @@ static unsigned long __init zone_absent_pages_in_node(int nid, unsigned long start_pfn, end_pfn; struct memblock_region *r; - for_each_memblock(memory, r) { + for_each_mem_region(r) { start_pfn = clamp(memblock_region_memory_base_pfn(r), zone_start_pfn, zone_end_pfn); end_pfn = clamp(memblock_region_memory_end_pfn(r), @@ -6503,45 +7543,9 @@ static unsigned long __init zone_absent_pages_in_node(int nid, return nr_absent; } -#else /* CONFIG_HAVE_MEMBLOCK_NODE_MAP */ -static inline unsigned long __init zone_spanned_pages_in_node(int nid, - unsigned long zone_type, - unsigned long node_start_pfn, - unsigned long node_end_pfn, - unsigned long *zone_start_pfn, - unsigned long *zone_end_pfn, - unsigned long *zones_size) -{ - unsigned int zone; - - *zone_start_pfn = node_start_pfn; - for (zone = 0; zone < zone_type; zone++) - *zone_start_pfn += zones_size[zone]; - - *zone_end_pfn = *zone_start_pfn + zones_size[zone_type]; - - return zones_size[zone_type]; -} - -static inline unsigned long __init zone_absent_pages_in_node(int nid, - unsigned long zone_type, - unsigned long node_start_pfn, - unsigned long node_end_pfn, - unsigned long *zholes_size) -{ - if (!zholes_size) - return 0; - - return zholes_size[zone_type]; -} - -#endif /* CONFIG_HAVE_MEMBLOCK_NODE_MAP */ - static void __init calculate_node_totalpages(struct pglist_data *pgdat, unsigned long node_start_pfn, - unsigned long node_end_pfn, - unsigned long *zones_size, - unsigned long *zholes_size) + unsigned long node_end_pfn) { unsigned long realtotalpages = 0, totalpages = 0; enum zone_type i; @@ -6549,23 +7553,30 @@ static void __init calculate_node_totalpages(struct pglist_data *pgdat, for (i = 0; i < MAX_NR_ZONES; i++) { struct zone *zone = pgdat->node_zones + i; unsigned long zone_start_pfn, zone_end_pfn; + unsigned long spanned, absent; unsigned long size, real_size; - size = zone_spanned_pages_in_node(pgdat->node_id, i, - node_start_pfn, - node_end_pfn, - &zone_start_pfn, - &zone_end_pfn, - zones_size); - real_size = size - zone_absent_pages_in_node(pgdat->node_id, i, - node_start_pfn, node_end_pfn, - zholes_size); + spanned = zone_spanned_pages_in_node(pgdat->node_id, i, + node_start_pfn, + node_end_pfn, + &zone_start_pfn, + &zone_end_pfn); + absent = zone_absent_pages_in_node(pgdat->node_id, i, + node_start_pfn, + node_end_pfn); + + size = spanned; + real_size = size - absent; + if (size) zone->zone_start_pfn = zone_start_pfn; else zone->zone_start_pfn = 0; zone->spanned_pages = size; zone->present_pages = real_size; +#if defined(CONFIG_MEMORY_HOTPLUG) + zone->present_early_pages = real_size; +#endif totalpages += size; realtotalpages += real_size; @@ -6573,8 +7584,7 @@ static void __init calculate_node_totalpages(struct pglist_data *pgdat, pgdat->node_spanned_pages = totalpages; pgdat->node_present_pages = realtotalpages; - printk(KERN_DEBUG "On node %d totalpages: %lu\n", pgdat->node_id, - realtotalpages); + pr_debug("On node %d totalpages: %lu\n", pgdat->node_id, realtotalpages); } #ifndef CONFIG_SPARSEMEM @@ -6598,25 +7608,22 @@ static unsigned long __init usemap_size(unsigned long zone_start_pfn, unsigned l return usemapsize / 8; } -static void __ref setup_usemap(struct pglist_data *pgdat, - struct zone *zone, - unsigned long zone_start_pfn, - unsigned long zonesize) +static void __ref setup_usemap(struct zone *zone) { - unsigned long usemapsize = usemap_size(zone_start_pfn, zonesize); + unsigned long usemapsize = usemap_size(zone->zone_start_pfn, + zone->spanned_pages); zone->pageblock_flags = NULL; if (usemapsize) { zone->pageblock_flags = memblock_alloc_node(usemapsize, SMP_CACHE_BYTES, - pgdat->node_id); + zone_to_nid(zone)); if (!zone->pageblock_flags) panic("Failed to allocate %ld bytes for zone %s pageblock flags on node %d\n", - usemapsize, zone->name, pgdat->node_id); + usemapsize, zone->name, zone_to_nid(zone)); } } #else -static inline void setup_usemap(struct pglist_data *pgdat, struct zone *zone, - unsigned long zone_start_pfn, unsigned long zonesize) {} +static inline void setup_usemap(struct zone *zone) {} #endif /* CONFIG_SPARSEMEM */ #ifdef CONFIG_HUGETLB_PAGE_SIZE_VARIABLE @@ -6624,16 +7631,15 @@ static inline void setup_usemap(struct pglist_data *pgdat, struct zone *zone, /* Initialise the number of pages represented by NR_PAGEBLOCK_BITS */ void __init set_pageblock_order(void) { - unsigned int order; + unsigned int order = MAX_ORDER - 1; /* Check that pageblock_nr_pages has not already been setup */ if (pageblock_order) return; - if (HPAGE_SHIFT > PAGE_SHIFT) + /* Don't let pageblocks exceed the maximum allocation granularity. */ + if (HPAGE_SHIFT > PAGE_SHIFT && HUGETLB_PAGE_ORDER < order) order = HUGETLB_PAGE_ORDER; - else - order = MAX_ORDER - 1; /* * Assume the largest contiguous order of interest is a huge page. @@ -6700,7 +7706,10 @@ static void pgdat_init_kcompactd(struct pglist_data *pgdat) {} static void __meminit pgdat_init_internals(struct pglist_data *pgdat) { + int i; + pgdat_resize_init(pgdat); + pgdat_kswapd_lock_init(pgdat); pgdat_init_split_queue(pgdat); pgdat_init_kcompactd(pgdat); @@ -6708,8 +7717,10 @@ static void __meminit pgdat_init_internals(struct pglist_data *pgdat) init_waitqueue_head(&pgdat->kswapd_wait); init_waitqueue_head(&pgdat->pfmemalloc_wait); + for (i = 0; i < NR_VMSCAN_THROTTLE; i++) + init_waitqueue_head(&pgdat->reclaim_wait[i]); + pgdat_page_ext_init(pgdat); - spin_lock_init(&pgdat->lru_lock); lruvec_init(&pgdat->__lruvec); } @@ -6733,12 +7744,33 @@ static void __meminit zone_init_internals(struct zone *zone, enum zone_type idx, * NOTE: this function is only called during memory hotplug */ #ifdef CONFIG_MEMORY_HOTPLUG -void __ref free_area_init_core_hotplug(int nid) +void __ref free_area_init_core_hotplug(struct pglist_data *pgdat) { + int nid = pgdat->node_id; enum zone_type z; - pg_data_t *pgdat = NODE_DATA(nid); + int cpu; pgdat_init_internals(pgdat); + + if (pgdat->per_cpu_nodestats == &boot_nodestats) + pgdat->per_cpu_nodestats = alloc_percpu(struct per_cpu_nodestat); + + /* + * Reset the nr_zones, order and highest_zoneidx before reuse. + * Note that kswapd will init kswapd_highest_zoneidx properly + * when it starts in the near future. + */ + pgdat->nr_zones = 0; + pgdat->kswapd_order = 0; + pgdat->kswapd_highest_zoneidx = 0; + pgdat->node_start_pfn = 0; + for_each_online_cpu(cpu) { + struct per_cpu_nodestat *p; + + p = per_cpu_ptr(pgdat->per_cpu_nodestats, cpu); + memset(p, 0, sizeof(*p)); + } + for (z = 0; z < MAX_NR_ZONES; z++) zone_init_internals(&pgdat->node_zones[z], z, nid, 0); } @@ -6764,7 +7796,6 @@ static void __init free_area_init_core(struct pglist_data *pgdat) for (j = 0; j < MAX_NR_ZONES; j++) { struct zone *zone = pgdat->node_zones + j; unsigned long size, freesize, memmap_pages; - unsigned long zone_start_pfn = zone->zone_start_pfn; size = zone->spanned_pages; freesize = zone->present_pages; @@ -6779,19 +7810,17 @@ static void __init free_area_init_core(struct pglist_data *pgdat) if (freesize >= memmap_pages) { freesize -= memmap_pages; if (memmap_pages) - printk(KERN_DEBUG - " %s zone: %lu pages used for memmap\n", - zone_names[j], memmap_pages); + pr_debug(" %s zone: %lu pages used for memmap\n", + zone_names[j], memmap_pages); } else - pr_warn(" %s zone: %lu pages exceeds freesize %lu\n", + pr_warn(" %s zone: %lu memmap pages exceeds freesize %lu\n", zone_names[j], memmap_pages, freesize); } /* Account for reserved pages */ if (j == 0 && freesize > dma_reserve) { freesize -= dma_reserve; - printk(KERN_DEBUG " %s zone: %lu pages reserved\n", - zone_names[0], dma_reserve); + pr_debug(" %s zone: %lu pages reserved\n", zone_names[0], dma_reserve); } if (!is_highmem_idx(j)) @@ -6812,14 +7841,13 @@ static void __init free_area_init_core(struct pglist_data *pgdat) continue; set_pageblock_order(); - setup_usemap(pgdat, zone, zone_start_pfn, size); - init_currently_empty_zone(zone, zone_start_pfn, size); - memmap_init(size, nid, j, zone_start_pfn); + setup_usemap(zone); + init_currently_empty_zone(zone, zone->zone_start_pfn, size); } } -#ifdef CONFIG_FLAT_NODE_MEM_MAP -static void __ref alloc_node_mem_map(struct pglist_data *pgdat) +#ifdef CONFIG_FLATMEM +static void __init alloc_node_mem_map(struct pglist_data *pgdat) { unsigned long __maybe_unused start = 0; unsigned long __maybe_unused offset = 0; @@ -6843,8 +7871,8 @@ static void __ref alloc_node_mem_map(struct pglist_data *pgdat) end = pgdat_end_pfn(pgdat); end = ALIGN(end, MAX_ORDER_NR_PAGES); size = (end - start) * sizeof(struct page); - map = memblock_alloc_node(size, SMP_CACHE_BYTES, - pgdat->node_id); + map = memmap_alloc(size, SMP_CACHE_BYTES, MEMBLOCK_LOW_LIMIT, + pgdat->node_id, false); if (!map) panic("Failed to allocate %ld bytes for node %d memory map\n", size, pgdat->node_id); @@ -6853,22 +7881,20 @@ static void __ref alloc_node_mem_map(struct pglist_data *pgdat) pr_debug("%s: node %d, pgdat %08lx, node_mem_map %08lx\n", __func__, pgdat->node_id, (unsigned long)pgdat, (unsigned long)pgdat->node_mem_map); -#ifndef CONFIG_NEED_MULTIPLE_NODES +#ifndef CONFIG_NUMA /* * With no DISCONTIG, the global mem_map is just set as node 0's */ if (pgdat == NODE_DATA(0)) { mem_map = NODE_DATA(0)->node_mem_map; -#if defined(CONFIG_HAVE_MEMBLOCK_NODE_MAP) || defined(CONFIG_FLATMEM) if (page_to_pfn(mem_map) != pgdat->node_start_pfn) mem_map -= offset; -#endif /* CONFIG_HAVE_MEMBLOCK_NODE_MAP */ } #endif } #else -static void __ref alloc_node_mem_map(struct pglist_data *pgdat) { } -#endif /* CONFIG_FLAT_NODE_MEM_MAP */ +static inline void alloc_node_mem_map(struct pglist_data *pgdat) { } +#endif /* CONFIG_FLATMEM */ #ifdef CONFIG_DEFERRED_STRUCT_PAGE_INIT static inline void pgdat_set_deferred_range(pg_data_t *pgdat) @@ -6879,30 +7905,30 @@ static inline void pgdat_set_deferred_range(pg_data_t *pgdat) static inline void pgdat_set_deferred_range(pg_data_t *pgdat) {} #endif -void __init free_area_init_node(int nid, unsigned long *zones_size, - unsigned long node_start_pfn, - unsigned long *zholes_size) +static void __init free_area_init_node(int nid) { pg_data_t *pgdat = NODE_DATA(nid); unsigned long start_pfn = 0; unsigned long end_pfn = 0; /* pg_data_t should be reset to zero when it's allocated */ - WARN_ON(pgdat->nr_zones || pgdat->kswapd_classzone_idx); + WARN_ON(pgdat->nr_zones || pgdat->kswapd_highest_zoneidx); + + get_pfn_range_for_nid(nid, &start_pfn, &end_pfn); pgdat->node_id = nid; - pgdat->node_start_pfn = node_start_pfn; + pgdat->node_start_pfn = start_pfn; pgdat->per_cpu_nodestats = NULL; -#ifdef CONFIG_HAVE_MEMBLOCK_NODE_MAP - get_pfn_range_for_nid(nid, &start_pfn, &end_pfn); - pr_info("Initmem setup node %d [mem %#018Lx-%#018Lx]\n", nid, - (u64)start_pfn << PAGE_SHIFT, - end_pfn ? ((u64)end_pfn << PAGE_SHIFT) - 1 : 0); -#else - start_pfn = node_start_pfn; -#endif - calculate_node_totalpages(pgdat, start_pfn, end_pfn, - zones_size, zholes_size); + + if (start_pfn != end_pfn) { + pr_info("Initmem setup node %d [mem %#018Lx-%#018Lx]\n", nid, + (u64)start_pfn << PAGE_SHIFT, + end_pfn ? ((u64)end_pfn << PAGE_SHIFT) - 1 : 0); + } else { + pr_info("Initmem setup node %d as memoryless\n", nid); + } + + calculate_node_totalpages(pgdat, start_pfn, end_pfn); alloc_node_mem_map(pgdat); pgdat_set_deferred_range(pgdat); @@ -6910,90 +7936,10 @@ void __init free_area_init_node(int nid, unsigned long *zones_size, free_area_init_core(pgdat); } -#if !defined(CONFIG_FLAT_NODE_MEM_MAP) -/* - * Initialize all valid struct pages in the range [spfn, epfn) and mark them - * PageReserved(). Return the number of struct pages that were initialized. - */ -static u64 __init init_unavailable_range(unsigned long spfn, unsigned long epfn) -{ - unsigned long pfn; - u64 pgcnt = 0; - - for (pfn = spfn; pfn < epfn; pfn++) { - if (!pfn_valid(ALIGN_DOWN(pfn, pageblock_nr_pages))) { - pfn = ALIGN_DOWN(pfn, pageblock_nr_pages) - + pageblock_nr_pages - 1; - continue; - } - /* - * Use a fake node/zone (0) for now. Some of these pages - * (in memblock.reserved but not in memblock.memory) will - * get re-initialized via reserve_bootmem_region() later. - */ - __init_single_page(pfn_to_page(pfn), pfn, 0, 0); - __SetPageReserved(pfn_to_page(pfn)); - pgcnt++; - } - - return pgcnt; -} - -/* - * Only struct pages that are backed by physical memory are zeroed and - * initialized by going through __init_single_page(). But, there are some - * struct pages which are reserved in memblock allocator and their fields - * may be accessed (for example page_to_pfn() on some configuration accesses - * flags). We must explicitly initialize those struct pages. - * - * This function also addresses a similar issue where struct pages are left - * uninitialized because the physical address range is not covered by - * memblock.memory or memblock.reserved. That could happen when memblock - * layout is manually configured via memmap=, or when the highest physical - * address (max_pfn) does not end on a section boundary. - */ -static void __init init_unavailable_mem(void) -{ - phys_addr_t start, end; - u64 i, pgcnt; - phys_addr_t next = 0; - - /* - * Loop through unavailable ranges not covered by memblock.memory. - */ - pgcnt = 0; - for_each_mem_range(i, &memblock.memory, NULL, - NUMA_NO_NODE, MEMBLOCK_NONE, &start, &end, NULL) { - if (next < start) - pgcnt += init_unavailable_range(PFN_DOWN(next), - PFN_UP(start)); - next = end; - } - - /* - * Early sections always have a fully populated memmap for the whole - * section - see pfn_valid(). If the last section has holes at the - * end and that section is marked "online", the memmap will be - * considered initialized. Make sure that memmap has a well defined - * state. - */ - pgcnt += init_unavailable_range(PFN_DOWN(next), - round_up(max_pfn, PAGES_PER_SECTION)); - - /* - * Struct pages that do not have backing memory. This could be because - * firmware is using some of this memory, or for some other reasons. - */ - if (pgcnt) - pr_info("Zeroed struct page in unavailable ranges: %lld pages", pgcnt); -} -#else -static inline void __init init_unavailable_mem(void) +static void __init free_area_init_memoryless_node(int nid) { + free_area_init_node(nid); } -#endif /* !CONFIG_FLAT_NODE_MEM_MAP */ - -#ifdef CONFIG_HAVE_MEMBLOCK_NODE_MAP #if MAX_NUMNODES > 1 /* @@ -7058,35 +8004,6 @@ unsigned long __init node_map_pfn_alignment(void) return ~accl_mask + 1; } -/* Find the lowest pfn for a node */ -static unsigned long __init find_min_pfn_for_node(int nid) -{ - unsigned long min_pfn = ULONG_MAX; - unsigned long start_pfn; - int i; - - for_each_mem_pfn_range(i, nid, &start_pfn, NULL, NULL) - min_pfn = min(min_pfn, start_pfn); - - if (min_pfn == ULONG_MAX) { - pr_warn("Could not find start_pfn for node %d\n", nid); - return 0; - } - - return min_pfn; -} - -/** - * find_min_pfn_with_active_regions - Find the minimum PFN registered - * - * Return: the minimum PFN based on information provided via - * memblock_set_node(). - */ -unsigned long __init find_min_pfn_with_active_regions(void) -{ - return find_min_pfn_for_node(MAX_NUMNODES); -} - /* * early_calculate_totalpages() * Sum pages in active regions for movable zone. @@ -7133,11 +8050,11 @@ static void __init find_zone_movable_pfns_for_nodes(void) * options. */ if (movable_node_is_enabled()) { - for_each_memblock(memory, r) { + for_each_mem_region(r) { if (!memblock_is_hotpluggable(r)) continue; - nid = r->nid; + nid = memblock_get_region_node(r); usable_startpfn = PFN_DOWN(r->base); zone_movable_pfn[nid] = zone_movable_pfn[nid] ? @@ -7154,15 +8071,15 @@ static void __init find_zone_movable_pfns_for_nodes(void) if (mirrored_kernelcore) { bool mem_below_4gb_not_mirrored = false; - for_each_memblock(memory, r) { + for_each_mem_region(r) { if (memblock_is_mirror(r)) continue; - nid = r->nid; + nid = memblock_get_region_node(r); 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; } @@ -7173,7 +8090,7 @@ static void __init find_zone_movable_pfns_for_nodes(void) } if (mem_below_4gb_not_mirrored) - pr_warn("This configuration results in unmirrored kernel memory."); + pr_warn("This configuration results in unmirrored kernel memory.\n"); goto out2; } @@ -7312,10 +8229,17 @@ restart: out2: /* Align start of ZONE_MOVABLE on all nids to MAX_ORDER_NR_PAGES */ - for (nid = 0; nid < MAX_NUMNODES; nid++) + for (nid = 0; nid < MAX_NUMNODES; nid++) { + unsigned long start_pfn, end_pfn; + zone_movable_pfn[nid] = roundup(zone_movable_pfn[nid], MAX_ORDER_NR_PAGES); + get_pfn_range_for_nid(nid, &start_pfn, &end_pfn); + if (zone_movable_pfn[nid] >= end_pfn) + zone_movable_pfn[nid] = 0; + } + out: /* restore the node_state */ node_states[N_MEMORY] = saved_node_state; @@ -7338,8 +8262,17 @@ static void check_for_memory(pg_data_t *pgdat, int nid) } } +/* + * Some architectures, e.g. ARC may have ZONE_HIGHMEM below ZONE_NORMAL. For + * such cases we allow max_zone_pfn sorted in the descending order + */ +bool __weak arch_has_descending_max_zone_pfns(void) +{ + return false; +} + /** - * free_area_init_nodes - Initialise all pg_data_t and zone data + * free_area_init - Initialise all pg_data_t and zone data * @max_zone_pfn: an array of max PFNs for each zone * * This will call free_area_init_node() for each active node in the system. @@ -7351,10 +8284,11 @@ static void check_for_memory(pg_data_t *pgdat, int nid) * starts where the previous one ended. For example, ZONE_DMA32 starts * at arch_max_dma_pfn. */ -void __init free_area_init_nodes(unsigned long *max_zone_pfn) +void __init free_area_init(unsigned long *max_zone_pfn) { unsigned long start_pfn, end_pfn; - int i, nid; + int i, nid, zone; + bool descending; /* Record where the zone boundaries are */ memset(arch_zone_lowest_possible_pfn, 0, @@ -7362,15 +8296,21 @@ void __init free_area_init_nodes(unsigned long *max_zone_pfn) memset(arch_zone_highest_possible_pfn, 0, sizeof(arch_zone_highest_possible_pfn)); - start_pfn = find_min_pfn_with_active_regions(); + start_pfn = PHYS_PFN(memblock_start_of_DRAM()); + descending = arch_has_descending_max_zone_pfns(); for (i = 0; i < MAX_NR_ZONES; i++) { - if (i == ZONE_MOVABLE) + if (descending) + zone = MAX_NR_ZONES - i - 1; + else + zone = i; + + if (zone == ZONE_MOVABLE) continue; - end_pfn = max(max_zone_pfn[i], start_pfn); - arch_zone_lowest_possible_pfn[i] = start_pfn; - arch_zone_highest_possible_pfn[i] = end_pfn; + end_pfn = max(max_zone_pfn[zone], start_pfn); + arch_zone_lowest_possible_pfn[zone] = start_pfn; + arch_zone_highest_possible_pfn[zone] = end_pfn; start_pfn = end_pfn; } @@ -7420,17 +8360,45 @@ void __init free_area_init_nodes(unsigned long *max_zone_pfn) /* Initialise every node */ mminit_verify_pageflags_layout(); setup_nr_node_ids(); - init_unavailable_mem(); - for_each_online_node(nid) { - pg_data_t *pgdat = NODE_DATA(nid); - free_area_init_node(nid, NULL, - find_min_pfn_for_node(nid), NULL); + for_each_node(nid) { + pg_data_t *pgdat; + + if (!node_online(nid)) { + pr_info("Initializing node %d as memoryless\n", nid); + + /* Allocator not initialized yet */ + pgdat = arch_alloc_nodedata(nid); + if (!pgdat) { + pr_err("Cannot allocate %zuB for node %d.\n", + sizeof(*pgdat), nid); + continue; + } + arch_refresh_nodedata(nid, pgdat); + free_area_init_memoryless_node(nid); + + /* + * We do not want to confuse userspace by sysfs + * files/directories for node without any memory + * attached to it, so this node is not marked as + * N_MEMORY and not marked online so that no sysfs + * hierarchy will be created via register_one_node for + * it. The pgdat will get fully initialized by + * hotadd_init_pgdat() when memory is hotplugged into + * this node. + */ + continue; + } + + pgdat = NODE_DATA(nid); + free_area_init_node(nid); /* Any memory on that node */ if (pgdat->node_present_pages) node_set_state(nid, N_MEMORY); check_for_memory(pgdat, nid); } + + memmap_init(); } static int __init cmdline_parse_core(char *p, unsigned long *core, @@ -7489,8 +8457,6 @@ static int __init cmdline_parse_movablecore(char *p) early_param("kernelcore", cmdline_parse_kernelcore); early_param("movablecore", cmdline_parse_movablecore); -#endif /* CONFIG_HAVE_MEMBLOCK_NODE_MAP */ - void adjust_managed_page_count(struct page *page, long count) { atomic_long_add(count, &page_zone(page)->managed_pages); @@ -7521,6 +8487,11 @@ unsigned long free_reserved_area(void *start, void *end, int poison, const char * alias for the memset(). */ direct_map_addr = page_address(page); + /* + * Perform a kasan-unchecked memset() since this memory + * has not been initialized. + */ + direct_map_addr = kasan_reset_tag(direct_map_addr); if ((unsigned int)poison <= 0xFF) memset(direct_map_addr, poison, PAGE_SIZE); @@ -7528,24 +8499,12 @@ unsigned long free_reserved_area(void *start, void *end, int poison, const char } if (pages && s) - pr_info("Freeing %s memory: %ldK\n", - s, pages << (PAGE_SHIFT - 10)); + pr_info("Freeing %s memory: %ldK\n", s, K(pages)); return pages; } -#ifdef CONFIG_HIGHMEM -void free_highmem_page(struct page *page) -{ - __free_reserved_page(page); - totalram_pages_inc(); - atomic_long_inc(&page_zone(page)->managed_pages); - totalhigh_pages_inc(); -} -#endif - - -void __init mem_init_print_info(const char *str) +void __init mem_init_print_info(void) { unsigned long physpages, codesize, datasize, rosize, bss_size; unsigned long init_code_size, init_data_size; @@ -7567,7 +8526,7 @@ void __init mem_init_print_info(const char *str) */ #define adj_init_size(start, end, size, pos, adj) \ do { \ - if (start <= pos && pos < end && size > adj) \ + if (&start[0] <= &pos[0] && &pos[0] < &end[0] && size > adj) \ size -= adj; \ } while (0) @@ -7584,17 +8543,16 @@ void __init mem_init_print_info(const char *str) #ifdef CONFIG_HIGHMEM ", %luK highmem" #endif - "%s%s)\n", - nr_free_pages() << (PAGE_SHIFT - 10), - physpages << (PAGE_SHIFT - 10), - codesize >> 10, datasize >> 10, rosize >> 10, - (init_data_size + init_code_size) >> 10, bss_size >> 10, - (physpages - totalram_pages() - totalcma_pages) << (PAGE_SHIFT - 10), - totalcma_pages << (PAGE_SHIFT - 10), + ")\n", + K(nr_free_pages()), K(physpages), + codesize / SZ_1K, datasize / SZ_1K, rosize / SZ_1K, + (init_data_size + init_code_size) / SZ_1K, bss_size / SZ_1K, + K(physpages - totalram_pages() - totalcma_pages), + K(totalcma_pages) #ifdef CONFIG_HIGHMEM - totalhigh_pages() << (PAGE_SHIFT - 10), + , K(totalhigh_pages()) #endif - str ? ", " : "", str ? str : ""); + ); } /** @@ -7613,17 +8571,12 @@ void __init set_dma_reserve(unsigned long new_dma_reserve) dma_reserve = new_dma_reserve; } -void __init free_area_init(unsigned long *zones_size) -{ - init_unavailable_mem(); - free_area_init_node(0, zones_size, - __pa(PAGE_OFFSET) >> PAGE_SHIFT, NULL); -} - static int page_alloc_cpu_dead(unsigned int cpu) { + struct zone *zone; lru_add_drain_cpu(cpu); + mlock_page_drain_remote(cpu); drain_pages(cpu); /* @@ -7642,6 +8595,19 @@ static int page_alloc_cpu_dead(unsigned int cpu) * race with what we are doing. */ cpu_vm_stats_fold(cpu); + + for_each_populated_zone(zone) + zone_pcp_update(zone, 0); + + return 0; +} + +static int page_alloc_cpu_online(unsigned int cpu) +{ + struct zone *zone; + + for_each_populated_zone(zone) + zone_pcp_update(zone, 1); return 0; } @@ -7667,8 +8633,9 @@ void __init page_alloc_init(void) hashdist = 0; #endif - ret = cpuhp_setup_state_nocalls(CPUHP_PAGE_ALLOC_DEAD, - "mm/page_alloc:dead", NULL, + ret = cpuhp_setup_state_nocalls(CPUHP_PAGE_ALLOC, + "mm/page_alloc:pcp", + page_alloc_cpu_online, page_alloc_cpu_dead); WARN_ON(ret < 0); } @@ -7721,30 +8688,24 @@ static void calculate_totalreserve_pages(void) static void setup_per_zone_lowmem_reserve(void) { struct pglist_data *pgdat; - enum zone_type j, idx; + enum zone_type i, j; for_each_online_pgdat(pgdat) { - for (j = 0; j < MAX_NR_ZONES; j++) { - struct zone *zone = pgdat->node_zones + j; - unsigned long managed_pages = zone_managed_pages(zone); + for (i = 0; i < MAX_NR_ZONES - 1; i++) { + struct zone *zone = &pgdat->node_zones[i]; + int ratio = sysctl_lowmem_reserve_ratio[i]; + bool clear = !ratio || !zone_managed_pages(zone); + unsigned long managed_pages = 0; - zone->lowmem_reserve[j] = 0; + for (j = i + 1; j < MAX_NR_ZONES; j++) { + struct zone *upper_zone = &pgdat->node_zones[j]; - idx = j; - while (idx) { - struct zone *lower_zone; + managed_pages += zone_managed_pages(upper_zone); - idx--; - lower_zone = pgdat->node_zones + idx; - - if (sysctl_lowmem_reserve_ratio[idx] < 1) { - sysctl_lowmem_reserve_ratio[idx] = 0; - lower_zone->lowmem_reserve[j] = 0; - } else { - lower_zone->lowmem_reserve[j] = - managed_pages / sysctl_lowmem_reserve_ratio[idx]; - } - managed_pages += zone_managed_pages(lower_zone); + if (clear) + zone->lowmem_reserve[j] = 0; + else + zone->lowmem_reserve[j] = managed_pages / ratio; } } } @@ -7804,9 +8765,10 @@ static void __setup_per_zone_wmarks(void) mult_frac(zone_managed_pages(zone), watermark_scale_factor, 10000)); - zone->_watermark[WMARK_LOW] = min_wmark_pages(zone) + tmp; - zone->_watermark[WMARK_HIGH] = min_wmark_pages(zone) + tmp * 2; zone->watermark_boost = 0; + 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; spin_unlock_irqrestore(&zone->lock, flags); } @@ -7824,18 +8786,26 @@ static void __setup_per_zone_wmarks(void) */ void setup_per_zone_wmarks(void) { + struct zone *zone; static DEFINE_SPINLOCK(lock); spin_lock(&lock); __setup_per_zone_wmarks(); spin_unlock(&lock); + + /* + * The watermark size have changed so update the pcpu batch + * and high limits or the limits may be inappropriate. + */ + for_each_zone(zone) + zone_pcp_update(zone, 0); } /* * Initialise min_free_kbytes. * * For small machines we want it small (128k min). For large machines - * we want it large (64MB max). But it is not linear, because network + * we want it large (256MB max). But it is not linear, because network * bandwidth does not increase linearly with machine size. We use * * min_free_kbytes = 4 * sqrt(lowmem_kbytes), for better accuracy: @@ -7855,7 +8825,7 @@ void setup_per_zone_wmarks(void) * 8192MB: 11584k * 16384MB: 16384k */ -int __meminit init_per_zone_wmark_min(void) +void calculate_min_free_kbytes(void) { unsigned long lowmem_kbytes; int new_min_free_kbytes; @@ -7863,16 +8833,17 @@ int __meminit init_per_zone_wmark_min(void) lowmem_kbytes = nr_free_buffer_pages() * (PAGE_SIZE >> 10); new_min_free_kbytes = int_sqrt(lowmem_kbytes * 16); - if (new_min_free_kbytes > user_min_free_kbytes) { - min_free_kbytes = new_min_free_kbytes; - if (min_free_kbytes < 128) - min_free_kbytes = 128; - if (min_free_kbytes > 65536) - min_free_kbytes = 65536; - } else { + if (new_min_free_kbytes > user_min_free_kbytes) + min_free_kbytes = clamp(new_min_free_kbytes, 128, 262144); + else pr_warn("min_free_kbytes is not updated to %d because user defined value %d is preferred\n", new_min_free_kbytes, user_min_free_kbytes); - } + +} + +int __meminit init_per_zone_wmark_min(void) +{ + calculate_min_free_kbytes(); setup_per_zone_wmarks(); refresh_zone_stat_thresholds(); setup_per_zone_lowmem_reserve(); @@ -7882,9 +8853,11 @@ int __meminit init_per_zone_wmark_min(void) setup_min_slab_ratio(); #endif + khugepaged_min_free_kbytes_update(); + return 0; } -core_initcall(init_per_zone_wmark_min) +postcore_initcall(init_per_zone_wmark_min) /* * min_free_kbytes_sysctl_handler - just a wrapper around proc_dointvec() so @@ -7892,7 +8865,7 @@ core_initcall(init_per_zone_wmark_min) * changes. */ int min_free_kbytes_sysctl_handler(struct ctl_table *table, int write, - void __user *buffer, size_t *length, loff_t *ppos) + void *buffer, size_t *length, loff_t *ppos) { int rc; @@ -7907,20 +8880,8 @@ int min_free_kbytes_sysctl_handler(struct ctl_table *table, int write, return 0; } -int watermark_boost_factor_sysctl_handler(struct ctl_table *table, int write, - void __user *buffer, size_t *length, loff_t *ppos) -{ - int rc; - - rc = proc_dointvec_minmax(table, write, buffer, length, ppos); - if (rc) - return rc; - - return 0; -} - int watermark_scale_factor_sysctl_handler(struct ctl_table *table, int write, - void __user *buffer, size_t *length, loff_t *ppos) + void *buffer, size_t *length, loff_t *ppos) { int rc; @@ -7950,7 +8911,7 @@ static void setup_min_unmapped_ratio(void) int sysctl_min_unmapped_ratio_sysctl_handler(struct ctl_table *table, int write, - void __user *buffer, size_t *length, loff_t *ppos) + void *buffer, size_t *length, loff_t *ppos) { int rc; @@ -7977,7 +8938,7 @@ static void setup_min_slab_ratio(void) } int sysctl_min_slab_ratio_sysctl_handler(struct ctl_table *table, int write, - void __user *buffer, size_t *length, loff_t *ppos) + void *buffer, size_t *length, loff_t *ppos) { int rc; @@ -8001,55 +8962,54 @@ int sysctl_min_slab_ratio_sysctl_handler(struct ctl_table *table, int write, * if in function of the boot time zone sizes. */ int lowmem_reserve_ratio_sysctl_handler(struct ctl_table *table, int write, - void __user *buffer, size_t *length, loff_t *ppos) + void *buffer, size_t *length, loff_t *ppos) { + int i; + proc_dointvec_minmax(table, write, buffer, length, ppos); - setup_per_zone_lowmem_reserve(); - return 0; -} -static void __zone_pcp_update(struct zone *zone) -{ - unsigned int cpu; + for (i = 0; i < MAX_NR_ZONES; i++) { + if (sysctl_lowmem_reserve_ratio[i] < 1) + sysctl_lowmem_reserve_ratio[i] = 0; + } - for_each_possible_cpu(cpu) - pageset_set_high_and_batch(zone, - per_cpu_ptr(zone->pageset, cpu)); + setup_per_zone_lowmem_reserve(); + return 0; } /* - * percpu_pagelist_fraction - changes the pcp->high for each zone on each - * cpu. It is the fraction of total pages in each zone that a hot per cpu + * percpu_pagelist_high_fraction - changes the pcp->high for each zone on each + * 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. */ -int percpu_pagelist_fraction_sysctl_handler(struct ctl_table *table, int write, - void __user *buffer, size_t *length, loff_t *ppos) +int percpu_pagelist_high_fraction_sysctl_handler(struct ctl_table *table, + int write, void *buffer, size_t *length, loff_t *ppos) { struct zone *zone; - int old_percpu_pagelist_fraction; + int old_percpu_pagelist_high_fraction; int ret; mutex_lock(&pcp_batch_high_lock); - old_percpu_pagelist_fraction = percpu_pagelist_fraction; + old_percpu_pagelist_high_fraction = percpu_pagelist_high_fraction; ret = proc_dointvec_minmax(table, write, buffer, length, ppos); if (!write || ret < 0) goto out; /* Sanity checking to avoid pcp imbalance */ - if (percpu_pagelist_fraction && - percpu_pagelist_fraction < MIN_PERCPU_PAGELIST_FRACTION) { - percpu_pagelist_fraction = old_percpu_pagelist_fraction; + if (percpu_pagelist_high_fraction && + percpu_pagelist_high_fraction < MIN_PERCPU_PAGELIST_HIGH_FRACTION) { + percpu_pagelist_high_fraction = old_percpu_pagelist_high_fraction; ret = -EINVAL; goto out; } /* No change? */ - if (percpu_pagelist_fraction == old_percpu_pagelist_fraction) + if (percpu_pagelist_high_fraction == old_percpu_pagelist_high_fraction) goto out; for_each_populated_zone(zone) - __zone_pcp_update(zone); + zone_set_pageset_high_and_batch(zone, 0); out: mutex_unlock(&pcp_batch_high_lock); return ret; @@ -8099,9 +9059,10 @@ void *__init alloc_large_system_hash(const char *tablename, { unsigned long long max = high_limit; unsigned long log2qty, size; - void *table = NULL; + void *table; gfp_t gfp_flags; bool virt; + bool huge; /* allow the kernel cmdline to have a say */ if (!numentries) { @@ -8110,8 +9071,8 @@ void *__init alloc_large_system_hash(const char *tablename, numentries -= arch_reserved_kernel_pages(); /* It isn't necessary when PAGE_SIZE >= 1MB */ - if (PAGE_SHIFT < 20) - numentries = round_up(numentries, (1<<20)/PAGE_SIZE); + if (PAGE_SIZE < SZ_1M) + numentries = round_up(numentries, SZ_1M / PAGE_SIZE); #if __BITS_PER_LONG > 32 if (!high_limit) { @@ -8167,8 +9128,10 @@ 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, PAGE_KERNEL); + table = vmalloc_huge(size, gfp_flags); virt = true; + if (table) + huge = is_vm_area_hugepages(table); } else { /* * If bucketsize is not a power-of-two, we may free @@ -8185,7 +9148,7 @@ void *__init alloc_large_system_hash(const char *tablename, pr_info("%s hash table entries: %ld (order: %d, %lu bytes, %s)\n", tablename, 1UL << log2qty, ilog2(size) - PAGE_SHIFT, size, - virt ? "vmalloc" : "linear"); + virt ? (huge ? "vmalloc hugepage" : "vmalloc") : "linear"); if (_hash_shift) *_hash_shift = log2qty; @@ -8195,143 +9158,43 @@ 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 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) +#ifdef CONFIG_CONTIG_ALLOC +#if defined(CONFIG_DYNAMIC_DEBUG) || \ + (defined(CONFIG_DYNAMIC_DEBUG_CORE) && defined(DYNAMIC_DEBUG_MODULE)) +/* Usage: See admin-guide/dynamic-debug-howto.rst */ +static void alloc_contig_dump_pages(struct list_head *page_list) { - unsigned long iter = 0; - unsigned long pfn = page_to_pfn(page); - - /* - * TODO we could make this much more efficient by not checking every - * page in the range if we know all of them are in MOVABLE_ZONE and - * that the movable zone guarantees that pages are migratable but - * the later is not the case right now unfortunatelly. E.g. movablecore - * can still lead to having bootmem allocations in zone_movable. - */ - - 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; iter++) { - if (!pfn_valid_within(pfn + iter)) - continue; - - page = pfn_to_page(pfn + iter); - - 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. - * We need not scan over tail pages because we don't - * handle each tail page individually in migration. - */ - if (PageHuge(page)) { - struct page *head = compound_head(page); - unsigned int skip_pages; - - if (!hugepage_migration_supported(page_hstate(head))) - return page; - - skip_pages = compound_nr(head) - (page - head); - iter += skip_pages - 1; - continue; - } + DEFINE_DYNAMIC_DEBUG_METADATA(descriptor, "migrate failure"); - /* - * 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 << page_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; - - if (__PageMovable(page) || PageLRU(page)) - continue; + if (DYNAMIC_DEBUG_BRANCH(descriptor)) { + struct page *page; - /* - * 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. - */ - /* - * If the page is not RAM, page_count()should be 0. - * we don't need more check. This is an _used_ not-movable page. - * - * The problematic thing here is PG_reserved pages. PG_reserved - * is set to both of a memory hole page and a _used_ kernel - * page at boot. - */ - return page; + dump_stack(); + list_for_each_entry(page, page_list, lru) + dump_page(page, "migration failure"); } - return NULL; -} - -#ifdef CONFIG_CONTIG_ALLOC -static unsigned long pfn_max_align_down(unsigned long pfn) -{ - return pfn & ~(max_t(unsigned long, MAX_ORDER_NR_PAGES, - pageblock_nr_pages) - 1); } - -static unsigned long pfn_max_align_up(unsigned long pfn) +#else +static inline void alloc_contig_dump_pages(struct list_head *page_list) { - return ALIGN(pfn, max_t(unsigned long, MAX_ORDER_NR_PAGES, - pageblock_nr_pages)); } +#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. */ - unsigned long nr_reclaimed; + unsigned int nr_reclaimed; unsigned long pfn = start; unsigned int tries = 0; int ret = 0; + struct migration_target_control mtc = { + .nid = zone_to_nid(cc->zone), + .gfp_mask = GFP_USER | __GFP_MOVABLE | __GFP_RETRY_MAYFAIL, + }; - migrate_prep(); + lru_cache_disable(); while (pfn < end || !list_empty(&cc->migratepages)) { if (fatal_signal_pending(current)) { @@ -8341,14 +9204,13 @@ static int __alloc_contig_migrate_range(struct compact_control *cc, if (list_empty(&cc->migratepages)) { cc->nr_migratepages = 0; - pfn = isolate_migratepages_range(cc, pfn, end); - if (!pfn) { - ret = -EINTR; + ret = isolate_migratepages_range(cc, pfn, end); + if (ret && ret != -EAGAIN) break; - } + pfn = cc->migrate_pfn; tries = 0; } else if (++tries == 5) { - ret = ret < 0 ? ret : -EBUSY; + ret = -EBUSY; break; } @@ -8356,10 +9218,21 @@ static int __alloc_contig_migrate_range(struct compact_control *cc, &cc->migratepages); cc->nr_migratepages -= nr_reclaimed; - ret = migrate_pages(&cc->migratepages, alloc_migrate_target, - NULL, 0, cc->mode, MR_CONTIG_RANGE); + ret = migrate_pages(&cc->migratepages, alloc_migration_target, + NULL, (unsigned long)&mtc, cc->mode, MR_CONTIG_RANGE, NULL); + + /* + * On -ENOMEM, migrate_pages() bails out right away. It is pointless + * to retry again over this error, so do the same here. + */ + if (ret == -ENOMEM) + break; } + + lru_cache_enable(); if (ret < 0) { + if (!(cc->gfp_mask & __GFP_NOWARN) && ret == -EBUSY) + alloc_contig_dump_pages(&cc->migratepages); putback_movable_pages(&cc->migratepages); return ret; } @@ -8370,14 +9243,14 @@ static int __alloc_contig_migrate_range(struct compact_control *cc, * alloc_contig_range() -- tries to allocate given range of pages * @start: start PFN to allocate * @end: one-past-the-last PFN to allocate - * @migratetype: migratetype of the underlaying pageblocks (either + * @migratetype: migratetype of the underlying pageblocks (either * #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 * - * 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 @@ -8391,7 +9264,7 @@ 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 = { @@ -8402,6 +9275,7 @@ int alloc_contig_range(unsigned long start, unsigned long end, .ignore_skip_hint = true, .no_set_skip_hint = true, .gfp_mask = current_gfp_context(gfp_mask), + .alloc_contig = true, }; INIT_LIST_HEAD(&cc.migratepages); @@ -8409,14 +9283,11 @@ 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 @@ -8429,10 +9300,11 @@ 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); - if (ret < 0) - return ret; + ret = start_isolate_page_range(start, end, migratetype, 0, gfp_mask); + if (ret) + goto done; + + drain_all_pages(cc.zone); /* * In case of -EBUSY, we'd like to know which page causes problem. @@ -8447,10 +9319,10 @@ int alloc_contig_range(unsigned long start, unsigned long end, ret = __alloc_contig_migrate_range(&cc, start, end); if (ret && ret != -EBUSY) goto done; - ret =0; + 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 @@ -8466,8 +9338,6 @@ int alloc_contig_range(unsigned long start, unsigned long end, * isolated thus they won't get removed from buddy. */ - lru_add_drain_all(); - order = 0; outer_start = start; while (!PageBuddy(pfn_to_page(outer_start))) { @@ -8479,7 +9349,7 @@ int alloc_contig_range(unsigned long start, unsigned long end, } if (outer_start != start) { - order = page_order(pfn_to_page(outer_start)); + order = buddy_order(pfn_to_page(outer_start)); /* * outer_start page could be small order buddy page and @@ -8493,8 +9363,6 @@ int alloc_contig_range(unsigned long start, unsigned long end, /* Make sure the range is really isolated. */ if (test_pages_isolated(outer_start, end, 0)) { - pr_info_ratelimited("%s: [%lx, %lx) PFNs busy\n", - __func__, outer_start, end); ret = -EBUSY; goto done; } @@ -8513,10 +9381,10 @@ 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); static int __alloc_contig_pages(unsigned long start_pfn, unsigned long nr_pages, gfp_t gfp_mask) @@ -8543,12 +9411,6 @@ static bool pfn_range_valid_contig(struct zone *z, unsigned long start_pfn, if (PageReserved(page)) return false; - - if (page_count(page) > 0) - return false; - - if (PageHuge(page)) - return false; } return true; } @@ -8574,8 +9436,8 @@ static bool zone_spans_last_pfn(const struct zone *zone, * for allocation requests which can not be fulfilled with the buddy allocator. * * The allocated memory is always aligned to a page boundary. If nr_pages is a - * power of two then the alignment is guaranteed to be to the given nr_pages - * (e.g. 1GB request would be aligned to 1GB). + * power of two, then allocated range is also guaranteed to be aligned to same + * nr_pages (e.g. 1GB request would be aligned to 1GB). * * Allocated pages can be freed with free_contig_range() or by manually calling * __free_page() on each allocated page. @@ -8620,9 +9482,9 @@ struct page *alloc_contig_pages(unsigned long nr_pages, gfp_t gfp_mask, } #endif /* CONFIG_CONTIG_ALLOC */ -void free_contig_range(unsigned long pfn, unsigned int nr_pages) +void free_contig_range(unsigned long pfn, unsigned long nr_pages) { - unsigned int count = 0; + unsigned long count = 0; for (; nr_pages--; pfn++) { struct page *page = pfn_to_page(pfn); @@ -8630,70 +9492,67 @@ void free_contig_range(unsigned long pfn, unsigned int nr_pages) count += page_count(page) != 1; __free_page(page); } - WARN(count != 0, "%d pages are still in use!\n", count); + WARN(count != 0, "%lu pages are still in use!\n", count); } +EXPORT_SYMBOL(free_contig_range); /* - * The zone indicated has a new number of managed_pages; batch sizes and percpu - * page high values need to be recalulated. + * Effectively disable pcplists for the zone by setting the high limit to 0 + * and draining all cpus. A concurrent page freeing on another CPU that's about + * to put the page on pcplist will either finish before the drain and the page + * will be drained, or observe the new high limit and skip the pcplist. + * + * Must be paired with a call to zone_pcp_enable(). */ -void __meminit zone_pcp_update(struct zone *zone) +void zone_pcp_disable(struct zone *zone) { mutex_lock(&pcp_batch_high_lock); - __zone_pcp_update(zone); + __zone_set_pageset_high_and_batch(zone, 0, 1); + __drain_all_pages(zone, true); +} + +void zone_pcp_enable(struct zone *zone) +{ + __zone_set_pageset_high_and_batch(zone, zone->pageset_high, zone->pageset_batch); mutex_unlock(&pcp_batch_high_lock); } void zone_pcp_reset(struct zone *zone) { - unsigned long flags; int cpu; - struct per_cpu_pageset *pset; + struct per_cpu_zonestat *pzstats; - /* avoid races with drain_pages() */ - local_irq_save(flags); - if (zone->pageset != &boot_pageset) { + if (zone->per_cpu_pageset != &boot_pageset) { for_each_online_cpu(cpu) { - pset = per_cpu_ptr(zone->pageset, cpu); - drain_zonestat(zone, pset); + pzstats = per_cpu_ptr(zone->per_cpu_zonestats, cpu); + drain_zonestat(zone, pzstats); + } + free_percpu(zone->per_cpu_pageset); + zone->per_cpu_pageset = &boot_pageset; + if (zone->per_cpu_zonestats != &boot_zonestats) { + free_percpu(zone->per_cpu_zonestats); + zone->per_cpu_zonestats = &boot_zonestats; } - free_percpu(zone->pageset); - zone->pageset = &boot_pageset; } - local_irq_restore(flags); } #ifdef CONFIG_MEMORY_HOTREMOVE /* - * All pages in the range must be in a single zone and isolated - * before calling this. + * 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. */ -unsigned long -__offline_isolated_pages(unsigned long start_pfn, unsigned long end_pfn) +void __offline_isolated_pages(unsigned long start_pfn, unsigned long end_pfn) { + unsigned long pfn = start_pfn; struct page *page; struct zone *zone; unsigned int order; - unsigned long pfn; unsigned long flags; - unsigned long offlined_pages = 0; - - /* find the first valid pfn */ - for (pfn = start_pfn; pfn < end_pfn; pfn++) - if (pfn_valid(pfn)) - break; - if (pfn == end_pfn) - return offlined_pages; offline_mem_sections(pfn, end_pfn); zone = page_zone(pfn_to_page(pfn)); spin_lock_irqsave(&zone->lock, flags); - pfn = start_pfn; while (pfn < end_pfn) { - if (!pfn_valid(pfn)) { - pfn++; - continue; - } page = pfn_to_page(pfn); /* * The HWPoisoned page may be not in buddy system, and @@ -8701,68 +9560,157 @@ __offline_isolated_pages(unsigned long start_pfn, unsigned long end_pfn) */ if (unlikely(!PageBuddy(page) && PageHWPoison(page))) { pfn++; - offlined_pages++; + continue; + } + /* + * At this point all remaining PageOffline() pages have a + * reference count of 0 and can simply be skipped. + */ + if (PageOffline(page)) { + BUG_ON(page_count(page)); + BUG_ON(PageBuddy(page)); + pfn++; continue; } BUG_ON(page_count(page)); BUG_ON(!PageBuddy(page)); - order = page_order(page); - offlined_pages += 1 << order; - del_page_from_free_area(page, &zone->free_area[order]); + order = buddy_order(page); + del_page_from_free_list(page, zone, order); pfn += (1 << order); } spin_unlock_irqrestore(&zone->lock, flags); - - return offlined_pages; } #endif +/* + * This function returns a stable result only if called under zone lock. + */ bool is_free_buddy_page(struct page *page) { - struct zone *zone = page_zone(page); unsigned long pfn = page_to_pfn(page); - unsigned long flags; unsigned int order; - spin_lock_irqsave(&zone->lock, flags); for (order = 0; order < MAX_ORDER; order++) { struct page *page_head = page - (pfn & ((1 << order) - 1)); - if (PageBuddy(page_head) && page_order(page_head) >= order) + if (PageBuddy(page_head) && + buddy_order_unsafe(page_head) >= order) break; } - spin_unlock_irqrestore(&zone->lock, flags); return order < MAX_ORDER; } +EXPORT_SYMBOL(is_free_buddy_page); #ifdef CONFIG_MEMORY_FAILURE /* - * Set PG_hwpoison flag if a given page is confirmed to be a free page. This - * test is performed under the zone lock to prevent a race against page - * allocation. + * Break down a higher-order page in sub-pages, and keep our target out of + * buddy allocator. */ -bool set_hwpoison_free_buddy_page(struct page *page) +static void break_down_buddy_pages(struct zone *zone, struct page *page, + struct page *target, int low, int high, + int migratetype) +{ + unsigned long size = 1 << high; + struct page *current_buddy, *next_page; + + while (high > low) { + high--; + size >>= 1; + + if (target >= &page[size]) { + next_page = page + size; + current_buddy = page; + } else { + next_page = page; + current_buddy = page + size; + } + + if (set_page_guard(zone, current_buddy, high, migratetype)) + continue; + + if (current_buddy != target) { + add_to_free_list(current_buddy, zone, high, migratetype); + set_buddy_order(current_buddy, high); + page = next_page; + } + } +} + +/* + * Take a page that will be marked as poisoned off the buddy allocator. + */ +bool take_page_off_buddy(struct page *page) { struct zone *zone = page_zone(page); unsigned long pfn = page_to_pfn(page); unsigned long flags; unsigned int order; - bool hwpoisoned = false; + bool ret = false; spin_lock_irqsave(&zone->lock, flags); for (order = 0; order < MAX_ORDER; order++) { struct page *page_head = page - (pfn & ((1 << order) - 1)); - - if (PageBuddy(page_head) && page_order(page_head) >= order) { - if (!TestSetPageHWPoison(page)) - hwpoisoned = true; + int page_order = buddy_order(page_head); + + if (PageBuddy(page_head) && page_order >= order) { + unsigned long pfn_head = page_to_pfn(page_head); + int migratetype = get_pfnblock_migratetype(page_head, + pfn_head); + + del_page_from_free_list(page_head, zone, page_order); + 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; + } + if (page_count(page_head) > 0) break; + } + spin_unlock_irqrestore(&zone->lock, flags); + return ret; +} + +/* + * Cancel takeoff done by take_page_off_buddy(). + */ +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)) { + ClearPageHWPoisonTakenOff(page); + __free_one_page(page, pfn, zone, 0, migratetype, FPI_NONE); + if (TestClearPageHWPoison(page)) { + ret = true; } } spin_unlock_irqrestore(&zone->lock, flags); - return hwpoisoned; + return ret; } #endif + +#ifdef CONFIG_ZONE_DMA +bool has_managed_dma(void) +{ + struct pglist_data *pgdat; + + for_each_online_pgdat(pgdat) { + struct zone *zone = &pgdat->node_zones[ZONE_DMA]; + + if (managed_zone(zone)) + return true; + } + return false; +} +#endif /* CONFIG_ZONE_DMA */ |