diff options
Diffstat (limited to 'mm/page_alloc.c')
| -rw-r--r-- | mm/page_alloc.c | 10165 |
1 files changed, 5730 insertions, 4435 deletions
diff --git a/mm/page_alloc.c b/mm/page_alloc.c index b100255dedda..822e05f1a964 100644 --- a/mm/page_alloc.c +++ b/mm/page_alloc.c @@ -1,3 +1,4 @@ +// SPDX-License-Identifier: GPL-2.0-only /* * linux/mm/page_alloc.c * @@ -16,64 +17,163 @@ #include <linux/stddef.h> #include <linux/mm.h> -#include <linux/swap.h> +#include <linux/highmem.h> #include <linux/interrupt.h> -#include <linux/pagemap.h> #include <linux/jiffies.h> -#include <linux/bootmem.h> -#include <linux/memblock.h> #include <linux/compiler.h> #include <linux/kernel.h> -#include <linux/kmemcheck.h> +#include <linux/kasan.h> +#include <linux/kmsan.h> #include <linux/module.h> #include <linux/suspend.h> -#include <linux/pagevec.h> -#include <linux/blkdev.h> -#include <linux/slab.h> #include <linux/ratelimit.h> #include <linux/oom.h> -#include <linux/notifier.h> #include <linux/topology.h> #include <linux/sysctl.h> #include <linux/cpu.h> #include <linux/cpuset.h> +#include <linux/pagevec.h> #include <linux/memory_hotplug.h> #include <linux/nodemask.h> -#include <linux/vmalloc.h> #include <linux/vmstat.h> -#include <linux/mempolicy.h> -#include <linux/stop_machine.h> -#include <linux/sort.h> -#include <linux/pfn.h> -#include <linux/backing-dev.h> #include <linux/fault-inject.h> -#include <linux/page-isolation.h> -#include <linux/page_cgroup.h> -#include <linux/debugobjects.h> -#include <linux/kmemleak.h> #include <linux/compaction.h> #include <trace/events/kmem.h> -#include <linux/ftrace_event.h> -#include <linux/memcontrol.h> +#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/page-debug-flags.h> -#include <linux/hugetlb.h> -#include <linux/sched/rt.h> - -#include <asm/sections.h> -#include <asm/tlbflush.h> +#include <linux/sched/mm.h> +#include <linux/page_owner.h> +#include <linux/page_table_check.h> +#include <linux/memcontrol.h> +#include <linux/ftrace.h> +#include <linux/lockdep.h> +#include <linux/psi.h> +#include <linux/khugepaged.h> +#include <linux/delayacct.h> +#include <linux/cacheinfo.h> +#include <linux/pgalloc_tag.h> #include <asm/div64.h> #include "internal.h" +#include "shuffle.h" +#include "page_reporting.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)) + +/* Free the page without taking locks. Rely on trylock only. */ +#define FPI_TRYLOCK ((__force fpi_t)BIT(2)) /* prevent >1 _updater_ of zone percpu pageset ->high and ->batch fields */ static DEFINE_MUTEX(pcp_batch_high_lock); +#define MIN_PERCPU_PAGELIST_HIGH_FRACTION (8) + +#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. + * Pass flags to a no-op inline function to typecheck and silence the unused + * variable warning. + */ +static inline void __pcp_trylock_noop(unsigned long *flags) { } +#define pcp_trylock_prepare(flags) __pcp_trylock_noop(&(flags)) +#define pcp_trylock_finish(flags) __pcp_trylock_noop(&(flags)) +#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_trylock(type, member, ptr) \ +({ \ + type *_ret; \ + pcpu_task_pin(); \ + _ret = this_cpu_ptr(ptr); \ + if (!spin_trylock(&_ret->member)) { \ + pcpu_task_unpin(); \ + _ret = NULL; \ + } \ + _ret; \ +}) + +#define pcpu_spin_unlock(member, ptr) \ +({ \ + spin_unlock(&ptr->member); \ + pcpu_task_unpin(); \ +}) + +/* struct per_cpu_pages specific helpers. */ +#define pcp_spin_trylock(ptr, UP_flags) \ +({ \ + struct per_cpu_pages *__ret; \ + pcp_trylock_prepare(UP_flags); \ + __ret = pcpu_spin_trylock(struct per_cpu_pages, lock, ptr); \ + if (!__ret) \ + pcp_trylock_finish(UP_flags); \ + __ret; \ +}) + +#define pcp_spin_unlock(ptr, UP_flags) \ +({ \ + pcpu_spin_unlock(lock, ptr); \ + pcp_trylock_finish(UP_flags); \ +}) #ifdef CONFIG_USE_PERCPU_NUMA_NODE_ID DEFINE_PER_CPU(int, numa_node); EXPORT_PER_CPU_SYMBOL(numa_node); #endif +DEFINE_STATIC_KEY_TRUE(vm_numa_stat_key); + #ifdef CONFIG_HAVE_MEMORYLESS_NODES /* * N.B., Do NOT reference the '_numa_mem_' per cpu variable directly. @@ -85,6 +185,13 @@ DEFINE_PER_CPU(int, _numa_mem_); /* Kernel "local memory" node */ EXPORT_PER_CPU_SYMBOL(_numa_mem_); #endif +static DEFINE_MUTEX(pcpu_drain_mutex); + +#ifdef CONFIG_GCC_PLUGIN_LATENT_ENTROPY +volatile unsigned long latent_entropy __latent_entropy; +EXPORT_SYMBOL(latent_entropy); +#endif + /* * Array of node states. */ @@ -96,72 +203,20 @@ nodemask_t node_states[NR_NODE_STATES] __read_mostly = { #ifdef CONFIG_HIGHMEM [N_HIGH_MEMORY] = { { [0] = 1UL } }, #endif -#ifdef CONFIG_MOVABLE_NODE [N_MEMORY] = { { [0] = 1UL } }, -#endif [N_CPU] = { { [0] = 1UL } }, #endif /* NUMA */ }; EXPORT_SYMBOL(node_states); -/* Protect totalram_pages and zone->managed_pages */ -static DEFINE_SPINLOCK(managed_page_count_lock); - -unsigned long totalram_pages __read_mostly; -unsigned long totalreserve_pages __read_mostly; -/* - * When calculating the number of globally allowed dirty pages, there - * is a certain number of per-zone reserves that should not be - * considered dirtyable memory. This is the sum of those reserves - * over all existing zones that contribute dirtyable memory. - */ -unsigned long dirty_balance_reserve __read_mostly; - -int percpu_pagelist_fraction; gfp_t gfp_allowed_mask __read_mostly = GFP_BOOT_MASK; -#ifdef CONFIG_PM_SLEEP -/* - * The following functions are used by the suspend/hibernate code to temporarily - * change gfp_allowed_mask in order to avoid using I/O during memory allocations - * while devices are suspended. To avoid races with the suspend/hibernate code, - * they should always be called with pm_mutex held (gfp_allowed_mask also should - * only be modified with pm_mutex held, unless the suspend/hibernate code is - * guaranteed not to run in parallel with that modification). - */ - -static gfp_t saved_gfp_mask; - -void pm_restore_gfp_mask(void) -{ - WARN_ON(!mutex_is_locked(&pm_mutex)); - if (saved_gfp_mask) { - gfp_allowed_mask = saved_gfp_mask; - saved_gfp_mask = 0; - } -} - -void pm_restrict_gfp_mask(void) -{ - WARN_ON(!mutex_is_locked(&pm_mutex)); - WARN_ON(saved_gfp_mask); - saved_gfp_mask = gfp_allowed_mask; - gfp_allowed_mask &= ~GFP_IOFS; -} - -bool pm_suspended_storage(void) -{ - if ((gfp_allowed_mask & GFP_IOFS) == GFP_IOFS) - return false; - return true; -} -#endif /* CONFIG_PM_SLEEP */ - #ifdef CONFIG_HUGETLB_PAGE_SIZE_VARIABLE -int pageblock_order __read_mostly; +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: @@ -169,27 +224,26 @@ static void __free_pages_ok(struct page *page, unsigned int order); * 1G machine -> (16M dma, 784M normal, 224M high) * NORMAL allocation will leave 784M/256 of ram reserved in the ZONE_DMA * HIGHMEM allocation will leave 224M/32 of ram reserved in ZONE_NORMAL - * HIGHMEM allocation will (224M+784M)/256 of ram reserved in ZONE_DMA + * HIGHMEM allocation will leave (224M+784M)/256 of ram reserved in ZONE_DMA * * TBD: should special case ZONE_DMA32 machines here - in those we normally * don't need any ZONE_NORMAL reservation */ -int sysctl_lowmem_reserve_ratio[MAX_NR_ZONES-1] = { +static int sysctl_lowmem_reserve_ratio[MAX_NR_ZONES] = { #ifdef CONFIG_ZONE_DMA - 256, + [ZONE_DMA] = 256, #endif #ifdef CONFIG_ZONE_DMA32 - 256, + [ZONE_DMA32] = 256, #endif + [ZONE_NORMAL] = 32, #ifdef CONFIG_HIGHMEM - 32, + [ZONE_HIGHMEM] = 0, #endif - 32, + [ZONE_MOVABLE] = 0, }; -EXPORT_SYMBOL(totalram_pages); - -static char * const zone_names[MAX_NR_ZONES] = { +char * const zone_names[MAX_NR_ZONES] = { #ifdef CONFIG_ZONE_DMA "DMA", #endif @@ -201,52 +255,329 @@ static char * const zone_names[MAX_NR_ZONES] = { "HighMem", #endif "Movable", +#ifdef CONFIG_ZONE_DEVICE + "Device", +#endif }; -int min_free_kbytes = 1024; -int user_min_free_kbytes; - -static unsigned long __meminitdata nr_kernel_pages; -static unsigned long __meminitdata nr_all_pages; -static unsigned long __meminitdata dma_reserve; +const char * const migratetype_names[MIGRATE_TYPES] = { + "Unmovable", + "Movable", + "Reclaimable", + "HighAtomic", +#ifdef CONFIG_CMA + "CMA", +#endif +#ifdef CONFIG_MEMORY_ISOLATION + "Isolate", +#endif +}; -#ifdef CONFIG_HAVE_MEMBLOCK_NODE_MAP -static unsigned long __meminitdata arch_zone_lowest_possible_pfn[MAX_NR_ZONES]; -static unsigned long __meminitdata arch_zone_highest_possible_pfn[MAX_NR_ZONES]; -static unsigned long __initdata required_kernelcore; -static unsigned long __initdata required_movablecore; -static unsigned long __meminitdata zone_movable_pfn[MAX_NUMNODES]; +int min_free_kbytes = 1024; +int user_min_free_kbytes = -1; +static int watermark_boost_factor __read_mostly = 15000; +static int watermark_scale_factor = 10; +int defrag_mode; /* movable_zone is the "real" zone pages in ZONE_MOVABLE are taken from */ int movable_zone; EXPORT_SYMBOL(movable_zone); -#endif /* CONFIG_HAVE_MEMBLOCK_NODE_MAP */ #if MAX_NUMNODES > 1 -int nr_node_ids __read_mostly = MAX_NUMNODES; -int nr_online_nodes __read_mostly = 1; +unsigned int nr_node_ids __read_mostly = MAX_NUMNODES; +unsigned int nr_online_nodes __read_mostly = 1; EXPORT_SYMBOL(nr_node_ids); EXPORT_SYMBOL(nr_online_nodes); #endif +static bool page_contains_unaccepted(struct page *page, unsigned int order); +static bool cond_accept_memory(struct zone *zone, unsigned int order, + int alloc_flags); +static bool __free_unaccepted(struct page *page); + int page_group_by_mobility_disabled __read_mostly; -void set_pageblock_migratetype(struct page *page, int migratetype) +#ifdef CONFIG_DEFERRED_STRUCT_PAGE_INIT +/* + * During boot we initialize deferred pages on-demand, as needed, but once + * page_alloc_init_late() has finished, the deferred pages are all initialized, + * and we can permanently disable that path. + */ +DEFINE_STATIC_KEY_TRUE(deferred_pages); + +static inline bool deferred_pages_enabled(void) +{ + return static_branch_unlikely(&deferred_pages); +} + +/* + * deferred_grow_zone() is __init, but it is called from + * get_page_from_freelist() during early boot until deferred_pages permanently + * disables this call. This is why we have refdata wrapper to avoid warning, + * and to ensure that the function body gets unloaded. + */ +static bool __ref +_deferred_grow_zone(struct zone *zone, unsigned int order) +{ + return deferred_grow_zone(zone, order); +} +#else +static inline bool deferred_pages_enabled(void) +{ + return false; +} + +static inline bool _deferred_grow_zone(struct zone *zone, unsigned int order) +{ + return false; +} +#endif /* CONFIG_DEFERRED_STRUCT_PAGE_INIT */ + +/* Return a pointer to the bitmap storing bits affecting a block of pages */ +static inline unsigned long *get_pageblock_bitmap(const struct page *page, + unsigned long pfn) +{ +#ifdef CONFIG_SPARSEMEM + return section_to_usemap(__pfn_to_section(pfn)); +#else + return page_zone(page)->pageblock_flags; +#endif /* CONFIG_SPARSEMEM */ +} + +static inline int pfn_to_bitidx(const struct page *page, unsigned long pfn) +{ +#ifdef CONFIG_SPARSEMEM + pfn &= (PAGES_PER_SECTION-1); +#else + pfn = pfn - pageblock_start_pfn(page_zone(page)->zone_start_pfn); +#endif /* CONFIG_SPARSEMEM */ + return (pfn >> pageblock_order) * NR_PAGEBLOCK_BITS; +} + +static __always_inline bool is_standalone_pb_bit(enum pageblock_bits pb_bit) +{ + return pb_bit >= PB_compact_skip && pb_bit < __NR_PAGEBLOCK_BITS; +} + +static __always_inline void +get_pfnblock_bitmap_bitidx(const struct page *page, unsigned long pfn, + unsigned long **bitmap_word, unsigned long *bitidx) +{ + unsigned long *bitmap; + unsigned long word_bitidx; + +#ifdef CONFIG_MEMORY_ISOLATION + BUILD_BUG_ON(NR_PAGEBLOCK_BITS != 8); +#else + BUILD_BUG_ON(NR_PAGEBLOCK_BITS != 4); +#endif + BUILD_BUG_ON(__MIGRATE_TYPE_END > MIGRATETYPE_MASK); + VM_BUG_ON_PAGE(!zone_spans_pfn(page_zone(page), pfn), page); + + bitmap = get_pageblock_bitmap(page, pfn); + *bitidx = pfn_to_bitidx(page, pfn); + word_bitidx = *bitidx / BITS_PER_LONG; + *bitidx &= (BITS_PER_LONG - 1); + *bitmap_word = &bitmap[word_bitidx]; +} + + +/** + * __get_pfnblock_flags_mask - Return the requested group of flags for + * a 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 + */ +static unsigned long __get_pfnblock_flags_mask(const struct page *page, + unsigned long pfn, + unsigned long mask) +{ + unsigned long *bitmap_word; + unsigned long bitidx; + unsigned long word; + + get_pfnblock_bitmap_bitidx(page, pfn, &bitmap_word, &bitidx); + /* + * This races, without locks, with set_pfnblock_migratetype(). Ensure + * a consistent read of the memory array, so that results, even though + * racy, are not corrupted. + */ + word = READ_ONCE(*bitmap_word); + return (word >> bitidx) & mask; +} + +/** + * get_pfnblock_bit - Check if a standalone bit of a pageblock is set + * @page: The page within the block of interest + * @pfn: The target page frame number + * @pb_bit: pageblock bit to check + * + * Return: true if the bit is set, otherwise false + */ +bool get_pfnblock_bit(const struct page *page, unsigned long pfn, + enum pageblock_bits pb_bit) +{ + unsigned long *bitmap_word; + unsigned long bitidx; + + if (WARN_ON_ONCE(!is_standalone_pb_bit(pb_bit))) + return false; + + get_pfnblock_bitmap_bitidx(page, pfn, &bitmap_word, &bitidx); + + return test_bit(bitidx + pb_bit, bitmap_word); +} + +/** + * get_pfnblock_migratetype - Return the migratetype of a pageblock + * @page: The page within the block of interest + * @pfn: The target page frame number + * + * Return: The migratetype of the pageblock + * + * Use get_pfnblock_migratetype() if caller already has both @page and @pfn + * to save a call to page_to_pfn(). + */ +__always_inline enum migratetype +get_pfnblock_migratetype(const struct page *page, unsigned long pfn) +{ + unsigned long mask = MIGRATETYPE_AND_ISO_MASK; + unsigned long flags; + + flags = __get_pfnblock_flags_mask(page, pfn, mask); + +#ifdef CONFIG_MEMORY_ISOLATION + if (flags & BIT(PB_migrate_isolate)) + return MIGRATE_ISOLATE; +#endif + return flags & MIGRATETYPE_MASK; +} + +/** + * __set_pfnblock_flags_mask - Set the requested group of flags for + * a pageblock_nr_pages block of pages + * @page: The page within the block of interest + * @pfn: The target page frame number + * @flags: The flags to set + * @mask: mask of bits that the caller is interested in + */ +static void __set_pfnblock_flags_mask(struct page *page, unsigned long pfn, + unsigned long flags, unsigned long mask) +{ + unsigned long *bitmap_word; + unsigned long bitidx; + unsigned long word; + + get_pfnblock_bitmap_bitidx(page, pfn, &bitmap_word, &bitidx); + + mask <<= bitidx; + flags <<= bitidx; + + word = READ_ONCE(*bitmap_word); + do { + } while (!try_cmpxchg(bitmap_word, &word, (word & ~mask) | flags)); +} + +/** + * set_pfnblock_bit - Set a standalone bit of a pageblock + * @page: The page within the block of interest + * @pfn: The target page frame number + * @pb_bit: pageblock bit to set + */ +void set_pfnblock_bit(const struct page *page, unsigned long pfn, + enum pageblock_bits pb_bit) +{ + unsigned long *bitmap_word; + unsigned long bitidx; + + if (WARN_ON_ONCE(!is_standalone_pb_bit(pb_bit))) + return; + + get_pfnblock_bitmap_bitidx(page, pfn, &bitmap_word, &bitidx); + + set_bit(bitidx + pb_bit, bitmap_word); +} + +/** + * clear_pfnblock_bit - Clear a standalone bit of a pageblock + * @page: The page within the block of interest + * @pfn: The target page frame number + * @pb_bit: pageblock bit to clear + */ +void clear_pfnblock_bit(const struct page *page, unsigned long pfn, + enum pageblock_bits pb_bit) { + unsigned long *bitmap_word; + unsigned long bitidx; + + if (WARN_ON_ONCE(!is_standalone_pb_bit(pb_bit))) + return; - if (unlikely(page_group_by_mobility_disabled)) + get_pfnblock_bitmap_bitidx(page, pfn, &bitmap_word, &bitidx); + + clear_bit(bitidx + pb_bit, bitmap_word); +} + +/** + * set_pageblock_migratetype - Set the migratetype of a pageblock + * @page: The page within the block of interest + * @migratetype: migratetype to set + */ +static void set_pageblock_migratetype(struct page *page, + enum migratetype migratetype) +{ + if (unlikely(page_group_by_mobility_disabled && + migratetype < MIGRATE_PCPTYPES)) migratetype = MIGRATE_UNMOVABLE; - set_pageblock_flags_group(page, (unsigned long)migratetype, - PB_migrate, PB_migrate_end); +#ifdef CONFIG_MEMORY_ISOLATION + if (migratetype == MIGRATE_ISOLATE) { + VM_WARN_ONCE(1, + "Use set_pageblock_isolate() for pageblock isolation"); + return; + } + VM_WARN_ONCE(get_pageblock_isolate(page), + "Use clear_pageblock_isolate() to unisolate pageblock"); + /* MIGRATETYPE_AND_ISO_MASK clears PB_migrate_isolate if it is set */ +#endif + __set_pfnblock_flags_mask(page, page_to_pfn(page), + (unsigned long)migratetype, + MIGRATETYPE_AND_ISO_MASK); } -bool oom_killer_disabled __read_mostly; +void __meminit init_pageblock_migratetype(struct page *page, + enum migratetype migratetype, + bool isolate) +{ + unsigned long flags; + + if (unlikely(page_group_by_mobility_disabled && + migratetype < MIGRATE_PCPTYPES)) + migratetype = MIGRATE_UNMOVABLE; + + flags = migratetype; + +#ifdef CONFIG_MEMORY_ISOLATION + if (migratetype == MIGRATE_ISOLATE) { + VM_WARN_ONCE( + 1, + "Set isolate=true to isolate pageblock with a migratetype"); + return; + } + if (isolate) + flags |= BIT(PB_migrate_isolate); +#endif + __set_pfnblock_flags_mask(page, page_to_pfn(page), flags, + MIGRATETYPE_AND_ISO_MASK); +} #ifdef CONFIG_DEBUG_VM static int page_outside_zone_boundaries(struct zone *zone, struct page *page) { - int ret = 0; + int ret; unsigned seq; unsigned long pfn = page_to_pfn(page); unsigned long sp, start_pfn; @@ -255,57 +586,42 @@ static int page_outside_zone_boundaries(struct zone *zone, struct page *page) seq = zone_span_seqbegin(zone); start_pfn = zone->zone_start_pfn; sp = zone->spanned_pages; - if (!zone_spans_pfn(zone, pfn)) - ret = 1; + ret = !zone_spans_pfn(zone, pfn); } while (zone_span_seqretry(zone, seq)); if (ret) - pr_err("page %lu outside zone [ %lu - %lu ]\n", - pfn, start_pfn, start_pfn + sp); + pr_err("page 0x%lx outside node %d zone %s [ 0x%lx - 0x%lx ]\n", + pfn, zone_to_nid(zone), zone->name, + start_pfn, start_pfn + sp); return ret; } -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; - - return 1; -} /* * Temporary debugging check for pages not lying within a given zone. */ -static int bad_range(struct zone *zone, struct page *page) +static bool __maybe_unused bad_range(struct zone *zone, struct page *page) { if (page_outside_zone_boundaries(zone, page)) - return 1; - if (!page_is_consistent(zone, page)) - return 1; + return true; + if (zone != page_zone(page)) + return true; - return 0; + return false; } #else -static inline int bad_range(struct zone *zone, struct page *page) +static inline bool __maybe_unused bad_range(struct zone *zone, struct page *page) { - return 0; + return false; } #endif -static void bad_page(struct page *page) +static void bad_page(struct page *page, const char *reason) { static unsigned long resume; static unsigned long nr_shown; static unsigned long nr_unshown; - /* Don't complain about poisoned pages */ - if (PageHWPoison(page)) { - page_mapcount_reset(page); /* remove PageBuddy */ - return; - } - /* * Allow a burst of 60 reports, then keep quiet for that minute; * or allow a steady drip of one report per second. @@ -316,7 +632,7 @@ static void bad_page(struct page *page) goto out; } if (nr_unshown) { - printk(KERN_ALERT + pr_alert( "BUG: Bad page state: %lu messages suppressed\n", nr_unshown); nr_unshown = 0; @@ -326,192 +642,276 @@ static void bad_page(struct page *page) if (nr_shown++ == 0) resume = jiffies + 60 * HZ; - printk(KERN_ALERT "BUG: Bad page state in process %s pfn:%05lx\n", + pr_alert("BUG: Bad page state in process %s pfn:%05lx\n", current->comm, page_to_pfn(page)); - dump_page(page); + dump_page(page, reason); print_modules(); dump_stack(); out: /* Leave bad fields for debug, except PageBuddy could make trouble */ - page_mapcount_reset(page); /* remove PageBuddy */ + if (PageBuddy(page)) + __ClearPageBuddy(page); add_taint(TAINT_BAD_PAGE, LOCKDEP_NOW_UNRELIABLE); } +static inline unsigned int order_to_pindex(int migratetype, int order) +{ + +#ifdef CONFIG_TRANSPARENT_HUGEPAGE + bool movable; + if (order > PAGE_ALLOC_COSTLY_ORDER) { + VM_BUG_ON(order != HPAGE_PMD_ORDER); + + movable = migratetype == MIGRATE_MOVABLE; + + return NR_LOWORDER_PCP_LISTS + movable; + } +#else + VM_BUG_ON(order > PAGE_ALLOC_COSTLY_ORDER); +#endif + + return (MIGRATE_PCPTYPES * order) + 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 = HPAGE_PMD_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 == HPAGE_PMD_ORDER) + return true; +#endif + return false; +} + /* * Higher-order pages are called "compound pages". They are structured thusly: * - * The first PAGE_SIZE page is called the "head page". - * - * The remaining PAGE_SIZE pages are called "tail pages". + * The first PAGE_SIZE page is called the "head page" and have PG_head set. * - * All pages have PG_compound set. All tail pages have their ->first_page - * pointing at the head page. + * The remaining PAGE_SIZE pages are called "tail pages". PageTail() is encoded + * in bit 0 of page->compound_head. The rest of bits is pointer to head page. * - * The first tail page's ->lru.next holds the address of the compound page's - * put_page() function. Its ->lru.prev holds the order of allocation. + * The first tail page's ->compound_order holds the order of allocation. * This usage means that zero-order pages may not be compound. */ -static void free_compound_page(struct page *page) -{ - __free_pages_ok(page, compound_order(page)); -} - -void prep_compound_page(struct page *page, unsigned long order) +void prep_compound_page(struct page *page, unsigned int order) { int i; int nr_pages = 1 << order; - set_compound_page_dtor(page, free_compound_page); - set_compound_order(page, order); __SetPageHead(page); - for (i = 1; i < nr_pages; i++) { - struct page *p = page + i; - __SetPageTail(p); - set_page_count(p, 0); - p->first_page = page; - } + for (i = 1; i < nr_pages; i++) + prep_compound_tail(page, i); + + prep_compound_head(page, order); } -/* update __split_huge_page_refcount if you change this function */ -static int destroy_compound_page(struct page *page, unsigned long order) +static inline void set_buddy_order(struct page *page, unsigned int order) { - int i; - int nr_pages = 1 << order; - int bad = 0; - - if (unlikely(compound_order(page) != order)) { - bad_page(page); - bad++; - } - - __ClearPageHead(page); - - for (i = 1; i < nr_pages; i++) { - struct page *p = page + i; + set_page_private(page, order); + __SetPageBuddy(page); +} - if (unlikely(!PageTail(p) || (p->first_page != page))) { - bad_page(page); - bad++; - } - __ClearPageTail(p); - } +#ifdef CONFIG_COMPACTION +static inline struct capture_control *task_capc(struct zone *zone) +{ + struct capture_control *capc = current->capture_control; - return bad; + return unlikely(capc) && + !(current->flags & PF_KTHREAD) && + !capc->page && + capc->cc->zone == zone ? capc : NULL; } -static inline void prep_zero_page(struct page *page, int order, gfp_t gfp_flags) +static inline bool +compaction_capture(struct capture_control *capc, struct page *page, + int order, int migratetype) { - int i; + if (!capc || order != capc->cc->order) + return false; + + /* Do not accidentally pollute CMA or isolated regions*/ + if (is_migrate_cma(migratetype) || + is_migrate_isolate(migratetype)) + return false; /* - * clear_highpage() will use KM_USER0, so it's a bug to use __GFP_ZERO - * and __GFP_HIGHMEM from hard or soft interrupt context. + * Do not let lower order allocations pollute a movable pageblock + * unless compaction is also requesting movable pages. + * This might let an unmovable request use a reclaimable pageblock + * and vice-versa but no more than normal fallback logic which can + * have trouble finding a high-order free page. */ - VM_BUG_ON((gfp_flags & __GFP_HIGHMEM) && in_interrupt()); - for (i = 0; i < (1 << order); i++) - clear_highpage(page + i); -} + if (order < pageblock_order && migratetype == MIGRATE_MOVABLE && + capc->cc->migratetype != MIGRATE_MOVABLE) + return false; + + if (migratetype != capc->cc->migratetype) + trace_mm_page_alloc_extfrag(page, capc->cc->order, order, + capc->cc->migratetype, migratetype); -#ifdef CONFIG_DEBUG_PAGEALLOC -unsigned int _debug_guardpage_minorder; + capc->page = page; + return true; +} -static int __init debug_guardpage_minorder_setup(char *buf) +#else +static inline struct capture_control *task_capc(struct zone *zone) { - unsigned long res; + return NULL; +} - if (kstrtoul(buf, 10, &res) < 0 || res > MAX_ORDER / 2) { - printk(KERN_ERR "Bad debug_guardpage_minorder value\n"); - return 0; - } - _debug_guardpage_minorder = res; - printk(KERN_INFO "Setting debug_guardpage_minorder to %lu\n", res); - return 0; +static inline bool +compaction_capture(struct capture_control *capc, struct page *page, + int order, int migratetype) +{ + return false; } -__setup("debug_guardpage_minorder=", debug_guardpage_minorder_setup); +#endif /* CONFIG_COMPACTION */ -static inline void set_page_guard_flag(struct page *page) +static inline void account_freepages(struct zone *zone, int nr_pages, + int migratetype) { - __set_bit(PAGE_DEBUG_FLAG_GUARD, &page->debug_flags); + lockdep_assert_held(&zone->lock); + + if (is_migrate_isolate(migratetype)) + return; + + __mod_zone_page_state(zone, NR_FREE_PAGES, nr_pages); + + if (is_migrate_cma(migratetype)) + __mod_zone_page_state(zone, NR_FREE_CMA_PAGES, nr_pages); + else if (migratetype == MIGRATE_HIGHATOMIC) + WRITE_ONCE(zone->nr_free_highatomic, + zone->nr_free_highatomic + nr_pages); } -static inline void clear_page_guard_flag(struct page *page) +/* 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, + bool tail) { - __clear_bit(PAGE_DEBUG_FLAG_GUARD, &page->debug_flags); + struct free_area *area = &zone->free_area[order]; + int nr_pages = 1 << order; + + VM_WARN_ONCE(get_pageblock_migratetype(page) != migratetype, + "page type is %d, passed migratetype is %d (nr=%d)\n", + get_pageblock_migratetype(page), migratetype, nr_pages); + + if (tail) + list_add_tail(&page->buddy_list, &area->free_list[migratetype]); + else + list_add(&page->buddy_list, &area->free_list[migratetype]); + area->nr_free++; + + if (order >= pageblock_order && !is_migrate_isolate(migratetype)) + __mod_zone_page_state(zone, NR_FREE_PAGES_BLOCKS, nr_pages); } -#else -static inline void set_page_guard_flag(struct page *page) { } -static inline void clear_page_guard_flag(struct page *page) { } -#endif -static inline void set_page_order(struct page *page, int order) +/* + * 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 old_mt, int new_mt) { - set_page_private(page, order); - __SetPageBuddy(page); + struct free_area *area = &zone->free_area[order]; + int nr_pages = 1 << order; + + /* Free page moving can fail, so it happens before the type update */ + VM_WARN_ONCE(get_pageblock_migratetype(page) != old_mt, + "page type is %d, passed migratetype is %d (nr=%d)\n", + get_pageblock_migratetype(page), old_mt, nr_pages); + + list_move_tail(&page->buddy_list, &area->free_list[new_mt]); + + account_freepages(zone, -nr_pages, old_mt); + account_freepages(zone, nr_pages, new_mt); + + if (order >= pageblock_order && + is_migrate_isolate(old_mt) != is_migrate_isolate(new_mt)) { + if (!is_migrate_isolate(old_mt)) + nr_pages = -nr_pages; + __mod_zone_page_state(zone, NR_FREE_PAGES_BLOCKS, nr_pages); + } } -static inline void rmv_page_order(struct page *page) +static inline void __del_page_from_free_list(struct page *page, struct zone *zone, + unsigned int order, int migratetype) { + int nr_pages = 1 << order; + + VM_WARN_ONCE(get_pageblock_migratetype(page) != migratetype, + "page type is %d, passed migratetype is %d (nr=%d)\n", + get_pageblock_migratetype(page), migratetype, nr_pages); + + /* clear reported state and update reported page count */ + if (page_reported(page)) + __ClearPageReported(page); + + list_del(&page->buddy_list); __ClearPageBuddy(page); set_page_private(page, 0); + zone->free_area[order].nr_free--; + + if (order >= pageblock_order && !is_migrate_isolate(migratetype)) + __mod_zone_page_state(zone, NR_FREE_PAGES_BLOCKS, -nr_pages); } -/* - * Locate the struct page for both the matching buddy in our - * pair (buddy1) and the combined O(n+1) page they form (page). - * - * 1) Any buddy B1 will have an order O twin B2 which satisfies - * the following equation: - * B2 = B1 ^ (1 << O) - * For example, if the starting buddy (buddy2) is #8 its order - * 1 buddy is #10: - * B2 = 8 ^ (1 << 1) = 8 ^ 2 = 10 - * - * 2) Any buddy B will have an order O+1 parent P which - * satisfies the following equation: - * P = B & ~(1 << O) - * - * Assumption: *_mem_map is contiguous at least up to MAX_ORDER - */ -static inline unsigned long -__find_buddy_index(unsigned long page_idx, unsigned int order) +static inline void del_page_from_free_list(struct page *page, struct zone *zone, + unsigned int order, int migratetype) +{ + __del_page_from_free_list(page, zone, order, migratetype); + account_freepages(zone, -(1 << order), migratetype); +} + +static inline struct page *get_page_from_free_area(struct free_area *area, + int migratetype) { - return page_idx ^ (1 << order); + return list_first_entry_or_null(&area->free_list[migratetype], + struct page, buddy_list); } /* - * This function checks whether a page is free && is the buddy - * we can do coalesce a page and its buddy if - * (a) the buddy is not in a hole && - * (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 ->_mapcount -2. - * Setting, clearing, and testing _mapcount -2 is serialized by zone->lock. - * - * For recording page's order, we use page_private(page). + * If this is less than the 2nd largest possible page, check if the buddy + * of the next-higher order is free. If it is, it's possible + * that pages are being freed that will coalesce soon. In case, + * that is happening, add the free page to the tail of the list + * so it's less likely to be used soon and more likely to be merged + * as a 2-level higher order page */ -static inline int page_is_buddy(struct page *page, struct page *buddy, - int order) +static inline bool +buddy_merge_likely(unsigned long pfn, unsigned long buddy_pfn, + struct page *page, unsigned int order) { - if (!pfn_valid_within(page_to_pfn(buddy))) - return 0; + unsigned long higher_page_pfn; + struct page *higher_page; - if (page_zone_id(page) != page_zone_id(buddy)) - return 0; + if (order >= MAX_PAGE_ORDER - 1) + return false; - if (page_is_guard(buddy) && page_order(buddy) == order) { - VM_BUG_ON(page_count(buddy) != 0); - return 1; - } + higher_page_pfn = buddy_pfn & pfn; + higher_page = page + (higher_page_pfn - pfn); - if (PageBuddy(buddy) && page_order(buddy) == order) { - VM_BUG_ON(page_count(buddy) != 0); - return 1; - } - return 0; + return find_buddy_page_pfn(higher_page, higher_page_pfn, order + 1, + NULL) != NULL; } /* @@ -527,8 +927,8 @@ static inline int page_is_buddy(struct page *page, struct page *buddy, * as necessary, plus some accounting needed to play nicely with other * parts of the VM system. * At each level, we keep a list of pages, which are heads of continuous - * free pages of length of (1 << order) and marked with _mapcount -2. Page's - * order is recorded in page_private(page) field. + * free pages of length of (1 << order) and marked with PageBuddy. + * Page's order is recorded in page_private(page) field. * So when we are allocating or freeing one, we can derive the state of the * other. That is, if we allocate a small block, and both were * free, the remainder of the region must be split into blocks. @@ -539,252 +939,738 @@ static inline int page_is_buddy(struct page *page, struct page *buddy, */ 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) { - unsigned long page_idx; - unsigned long combined_idx; - unsigned long uninitialized_var(buddy_idx); + struct capture_control *capc = task_capc(zone); + unsigned long buddy_pfn = 0; + unsigned long combined_pfn; struct page *buddy; + bool to_tail; VM_BUG_ON(!zone_is_initialized(zone)); + VM_BUG_ON_PAGE(page->flags.f & PAGE_FLAGS_CHECK_AT_PREP, page); + + VM_BUG_ON(migratetype == -1); + VM_BUG_ON_PAGE(pfn & ((1 << order) - 1), page); + VM_BUG_ON_PAGE(bad_range(zone, page), page); + + account_freepages(zone, 1 << order, migratetype); - if (unlikely(PageCompound(page))) - if (unlikely(destroy_compound_page(page, order))) + while (order < MAX_PAGE_ORDER) { + int buddy_mt = migratetype; + + if (compaction_capture(capc, page, order, migratetype)) { + account_freepages(zone, -(1 << order), migratetype); return; + } - VM_BUG_ON(migratetype == -1); + buddy = find_buddy_page_pfn(page, pfn, order, &buddy_pfn); + if (!buddy) + goto done_merging; - page_idx = page_to_pfn(page) & ((1 << MAX_ORDER) - 1); + 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. + */ + buddy_mt = get_pfnblock_migratetype(buddy, buddy_pfn); - VM_BUG_ON(page_idx & ((1 << order) - 1)); - VM_BUG_ON(bad_range(zone, page)); + if (migratetype != buddy_mt && + (!migratetype_is_mergeable(migratetype) || + !migratetype_is_mergeable(buddy_mt))) + goto done_merging; + } - while (order < MAX_ORDER-1) { - buddy_idx = __find_buddy_index(page_idx, order); - buddy = page + (buddy_idx - page_idx); - if (!page_is_buddy(page, buddy, order)) - break; /* * Our buddy is free or it is CONFIG_DEBUG_PAGEALLOC guard page, * merge with it and move up one order. */ - if (page_is_guard(buddy)) { - clear_page_guard_flag(buddy); - set_page_private(page, 0); - __mod_zone_freepage_state(zone, 1 << order, - migratetype); - } else { - list_del(&buddy->lru); - zone->free_area[order].nr_free--; - rmv_page_order(buddy); + if (page_is_guard(buddy)) + clear_page_guard(zone, buddy, order); + else + __del_page_from_free_list(buddy, zone, order, buddy_mt); + + if (unlikely(buddy_mt != migratetype)) { + /* + * Match buddy type. This ensures that an + * expand() down the line puts the sub-blocks + * on the right freelists. + */ + set_pageblock_migratetype(buddy, migratetype); } - combined_idx = buddy_idx & page_idx; - page = page + (combined_idx - page_idx); - page_idx = combined_idx; + + combined_pfn = buddy_pfn & pfn; + page = page + (combined_pfn - pfn); + pfn = combined_pfn; order++; } - set_page_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(page_to_pfn(buddy))) { - struct page *higher_page, *higher_buddy; - combined_idx = buddy_idx & page_idx; - higher_page = page + (combined_idx - page_idx); - buddy_idx = __find_buddy_index(combined_idx, order + 1); - higher_buddy = higher_page + (buddy_idx - combined_idx); - if (page_is_buddy(higher_page, higher_buddy, order + 1)) { - list_add_tail(&page->lru, - &zone->free_area[order].free_list[migratetype]); - goto out; - } +done_merging: + set_buddy_order(page, order); + + 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); + + __add_to_free_list(page, zone, order, migratetype, to_tail); + + /* Notify page reporting subsystem of freed page */ + if (!(fpi_flags & FPI_SKIP_REPORT_NOTIFY)) + page_reporting_notify_free(order); +} + +/* + * 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 + * check if necessary. + */ +static inline bool page_expected_state(struct page *page, + unsigned long check_flags) +{ + if (unlikely(atomic_read(&page->_mapcount) != -1)) + return false; + + if (unlikely((unsigned long)page->mapping | + page_ref_count(page) | +#ifdef CONFIG_MEMCG + page->memcg_data | +#endif + page_pool_page_is_pp(page) | + (page->flags.f & check_flags))) + return false; + + return true; +} + +static const char *page_bad_reason(struct page *page, unsigned long flags) +{ + const char *bad_reason = NULL; + + 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.f & 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->memcg_data)) + bad_reason = "page still charged to cgroup"; +#endif + if (unlikely(page_pool_page_is_pp(page))) + bad_reason = "page_pool leak"; + return bad_reason; +} - list_add(&page->lru, &zone->free_area[order].free_list[migratetype]); -out: - zone->free_area[order].nr_free++; +static inline bool free_page_is_bad(struct page *page) +{ + if (likely(page_expected_state(page, PAGE_FLAGS_CHECK_AT_FREE))) + return false; + + /* Something has gone sideways, find it */ + bad_page(page, page_bad_reason(page, PAGE_FLAGS_CHECK_AT_FREE)); + return true; } -static inline int free_pages_check(struct page *page) +static inline bool is_check_pages_enabled(void) { - if (unlikely(page_mapcount(page) | - (page->mapping != NULL) | - (atomic_read(&page->_count) != 0) | - (page->flags & PAGE_FLAGS_CHECK_AT_FREE) | - (mem_cgroup_bad_page_check(page)))) { - bad_page(page); - return 1; + return static_branch_unlikely(&check_pages_enabled); +} + +static int free_tail_page_prepare(struct page *head_page, struct page *page) +{ + struct folio *folio = (struct folio *)head_page; + int ret = 1; + + /* + * We rely page->lru.next never has bit 0 set, unless the page + * is PageTail(). Let's make sure that's true even for poisoned ->lru. + */ + BUILD_BUG_ON((unsigned long)LIST_POISON1 & 1); + + if (!is_check_pages_enabled()) { + ret = 0; + goto out; } - page_nid_reset_last(page); - if (page->flags & PAGE_FLAGS_CHECK_AT_PREP) - page->flags &= ~PAGE_FLAGS_CHECK_AT_PREP; - return 0; + switch (page - head_page) { + case 1: + /* the first tail page: these may be in place of ->mapping */ + if (unlikely(folio_large_mapcount(folio))) { + bad_page(page, "nonzero large_mapcount"); + goto out; + } + if (IS_ENABLED(CONFIG_PAGE_MAPCOUNT) && + unlikely(atomic_read(&folio->_nr_pages_mapped))) { + bad_page(page, "nonzero nr_pages_mapped"); + goto out; + } + if (IS_ENABLED(CONFIG_MM_ID)) { + if (unlikely(folio->_mm_id_mapcount[0] != -1)) { + bad_page(page, "nonzero mm mapcount 0"); + goto out; + } + if (unlikely(folio->_mm_id_mapcount[1] != -1)) { + bad_page(page, "nonzero mm mapcount 1"); + goto out; + } + } + if (IS_ENABLED(CONFIG_64BIT)) { + if (unlikely(atomic_read(&folio->_entire_mapcount) + 1)) { + bad_page(page, "nonzero entire_mapcount"); + goto out; + } + if (unlikely(atomic_read(&folio->_pincount))) { + bad_page(page, "nonzero pincount"); + goto out; + } + } + break; + case 2: + /* the second tail page: deferred_list overlaps ->mapping */ + if (unlikely(!list_empty(&folio->_deferred_list))) { + bad_page(page, "on deferred list"); + goto out; + } + if (!IS_ENABLED(CONFIG_64BIT)) { + if (unlikely(atomic_read(&folio->_entire_mapcount) + 1)) { + bad_page(page, "nonzero entire_mapcount"); + goto out; + } + if (unlikely(atomic_read(&folio->_pincount))) { + bad_page(page, "nonzero pincount"); + goto out; + } + } + break; + case 3: + /* the third tail page: hugetlb specifics overlap ->mappings */ + if (IS_ENABLED(CONFIG_HUGETLB_PAGE)) + break; + fallthrough; + default: + if (page->mapping != TAIL_MAPPING) { + bad_page(page, "corrupted mapping in tail page"); + goto out; + } + break; + } + if (unlikely(!PageTail(page))) { + bad_page(page, "PageTail not set"); + goto out; + } + if (unlikely(compound_head(page) != head_page)) { + bad_page(page, "compound_head not consistent"); + goto out; + } + ret = 0; +out: + page->mapping = NULL; + clear_compound_head(page); + return ret; } /* - * Frees a number of pages from the PCP lists - * Assumes all pages on list are in same zone, and of same order. - * count is the number of pages to free. + * Skip KASAN memory poisoning when either: + * + * 1. For generic KASAN: deferred memory initialization has not yet completed. + * Tag-based KASAN modes skip pages freed via deferred memory initialization + * using page tags instead (see below). + * 2. For tag-based KASAN modes: the page has a match-all KASAN tag, indicating + * that error detection is disabled for accesses via the page address. * - * If the zone was previously in an "all pages pinned" state then look to - * see if this freeing clears that state. + * Pages will have match-all tags in the following circumstances: * - * And clear the zone's pages_scanned counter, to hold off the "all pages are - * pinned" detection logic. + * 1. Pages are being initialized for the first time, including during deferred + * memory init; see the call to page_kasan_tag_reset in __init_single_page. + * 2. The allocation was not unpoisoned due to __GFP_SKIP_KASAN, with the + * exception of pages unpoisoned by kasan_unpoison_vmalloc. + * 3. The allocation was excluded from being checked due to sampling, + * see the call to kasan_unpoison_pages. + * + * 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 void free_pcppages_bulk(struct zone *zone, int count, - struct per_cpu_pages *pcp) +static inline bool should_skip_kasan_poison(struct page *page) { - int migratetype = 0; - int batch_free = 0; - int to_free = count; + if (IS_ENABLED(CONFIG_KASAN_GENERIC)) + return deferred_pages_enabled(); - spin_lock(&zone->lock); - zone->all_unreclaimable = 0; - zone->pages_scanned = 0; + return page_kasan_tag(page) == KASAN_TAG_KERNEL; +} - while (to_free) { - struct page *page; - struct list_head *list; +static void kernel_init_pages(struct page *page, int numpages) +{ + int i; - /* - * 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 - */ - do { - batch_free++; - if (++migratetype == MIGRATE_PCPTYPES) - migratetype = 0; - list = &pcp->lists[migratetype]; - } while (list_empty(list)); + /* s390's use of memset() could override KASAN redzones. */ + kasan_disable_current(); + for (i = 0; i < numpages; i++) + clear_highpage_kasan_tagged(page + i); + kasan_enable_current(); +} - /* This is the only non-empty list. Free them all. */ - if (batch_free == MIGRATE_PCPTYPES) - batch_free = to_free; +#ifdef CONFIG_MEM_ALLOC_PROFILING - do { - int mt; /* migratetype of the to-be-freed page */ +/* Should be called only if mem_alloc_profiling_enabled() */ +void __clear_page_tag_ref(struct page *page) +{ + union pgtag_ref_handle handle; + union codetag_ref ref; - page = list_entry(list->prev, struct page, lru); - /* must delete as __free_one_page list manipulates */ - list_del(&page->lru); - mt = get_freepage_migratetype(page); - /* MIGRATE_MOVABLE list may include MIGRATE_RESERVEs */ - __free_one_page(page, zone, 0, mt); - trace_mm_page_pcpu_drain(page, 0, mt); - if (likely(!is_migrate_isolate_page(page))) { - __mod_zone_page_state(zone, NR_FREE_PAGES, 1); - if (is_migrate_cma(mt)) - __mod_zone_page_state(zone, NR_FREE_CMA_PAGES, 1); - } - } while (--to_free && --batch_free && !list_empty(list)); + if (get_page_tag_ref(page, &ref, &handle)) { + set_codetag_empty(&ref); + update_page_tag_ref(handle, &ref); + put_page_tag_ref(handle); } - spin_unlock(&zone->lock); } -static void free_one_page(struct zone *zone, struct page *page, int order, - int migratetype) +/* Should be called only if mem_alloc_profiling_enabled() */ +static noinline +void __pgalloc_tag_add(struct page *page, struct task_struct *task, + unsigned int nr) { - spin_lock(&zone->lock); - zone->all_unreclaimable = 0; - zone->pages_scanned = 0; + union pgtag_ref_handle handle; + union codetag_ref ref; - __free_one_page(page, zone, order, migratetype); - if (unlikely(!is_migrate_isolate(migratetype))) - __mod_zone_freepage_state(zone, 1 << order, migratetype); - spin_unlock(&zone->lock); + if (get_page_tag_ref(page, &ref, &handle)) { + alloc_tag_add(&ref, task->alloc_tag, PAGE_SIZE * nr); + update_page_tag_ref(handle, &ref); + put_page_tag_ref(handle); + } } -static bool free_pages_prepare(struct page *page, unsigned int order) +static inline void pgalloc_tag_add(struct page *page, struct task_struct *task, + unsigned int nr) +{ + if (mem_alloc_profiling_enabled()) + __pgalloc_tag_add(page, task, nr); +} + +/* Should be called only if mem_alloc_profiling_enabled() */ +static noinline +void __pgalloc_tag_sub(struct page *page, unsigned int nr) +{ + union pgtag_ref_handle handle; + union codetag_ref ref; + + if (get_page_tag_ref(page, &ref, &handle)) { + alloc_tag_sub(&ref, PAGE_SIZE * nr); + update_page_tag_ref(handle, &ref); + put_page_tag_ref(handle); + } +} + +static inline void pgalloc_tag_sub(struct page *page, unsigned int nr) +{ + if (mem_alloc_profiling_enabled()) + __pgalloc_tag_sub(page, nr); +} + +/* When tag is not NULL, assuming mem_alloc_profiling_enabled */ +static inline void pgalloc_tag_sub_pages(struct alloc_tag *tag, unsigned int nr) +{ + if (tag) + this_cpu_sub(tag->counters->bytes, PAGE_SIZE * nr); +} + +#else /* CONFIG_MEM_ALLOC_PROFILING */ + +static inline void pgalloc_tag_add(struct page *page, struct task_struct *task, + unsigned int nr) {} +static inline void pgalloc_tag_sub(struct page *page, unsigned int nr) {} +static inline void pgalloc_tag_sub_pages(struct alloc_tag *tag, unsigned int nr) {} + +#endif /* CONFIG_MEM_ALLOC_PROFILING */ + +__always_inline bool free_pages_prepare(struct page *page, + unsigned int order) { - int i; int bad = 0; + bool skip_kasan_poison = should_skip_kasan_poison(page); + bool init = want_init_on_free(); + bool compound = PageCompound(page); + struct folio *folio = page_folio(page); + + VM_BUG_ON_PAGE(PageTail(page), page); trace_mm_page_free(page, order); - kmemcheck_free_shadow(page, order); + kmsan_free_page(page, order); + + if (memcg_kmem_online() && PageMemcgKmem(page)) + __memcg_kmem_uncharge_page(page, order); - if (PageAnon(page)) - page->mapping = NULL; - for (i = 0; i < (1 << order); i++) - bad += free_pages_check(page + i); - if (bad) + /* + * In rare cases, when truncation or holepunching raced with + * munlock after VM_LOCKED was cleared, Mlocked may still be + * found set here. This does not indicate a problem, unless + * "unevictable_pgs_cleared" appears worryingly large. + */ + if (unlikely(folio_test_mlocked(folio))) { + long nr_pages = folio_nr_pages(folio); + + __folio_clear_mlocked(folio); + zone_stat_mod_folio(folio, NR_MLOCK, -nr_pages); + count_vm_events(UNEVICTABLE_PGCLEARED, nr_pages); + } + + if (unlikely(PageHWPoison(page)) && !order) { + /* Do not let hwpoison pages hit pcplists/buddy */ + reset_page_owner(page, order); + page_table_check_free(page, order); + pgalloc_tag_sub(page, 1 << order); + + /* + * The page is isolated and accounted for. + * Mark the codetag as empty to avoid accounting error + * when the page is freed by unpoison_memory(). + */ + clear_page_tag_ref(page); return false; + } + + VM_BUG_ON_PAGE(compound && compound_order(page) != order, page); + + /* + * Check tail pages before head page information is cleared to + * avoid checking PageCompound for order-0 pages. + */ + if (unlikely(order)) { + int i; + + if (compound) { + page[1].flags.f &= ~PAGE_FLAGS_SECOND; +#ifdef NR_PAGES_IN_LARGE_FOLIO + folio->_nr_pages = 0; +#endif + } + for (i = 1; i < (1 << order); i++) { + if (compound) + bad += free_tail_page_prepare(page, page + i); + if (is_check_pages_enabled()) { + if (free_page_is_bad(page + i)) { + bad++; + continue; + } + } + (page + i)->flags.f &= ~PAGE_FLAGS_CHECK_AT_PREP; + } + } + if (folio_test_anon(folio)) { + mod_mthp_stat(order, MTHP_STAT_NR_ANON, -1); + folio->mapping = NULL; + } + if (unlikely(page_has_type(page))) + /* Reset the page_type (which overlays _mapcount) */ + page->page_type = UINT_MAX; + + if (is_check_pages_enabled()) { + if (free_page_is_bad(page)) + bad++; + if (bad) + return false; + } + + page_cpupid_reset_last(page); + page->flags.f &= ~PAGE_FLAGS_CHECK_AT_PREP; + reset_page_owner(page, order); + page_table_check_free(page, order); + pgalloc_tag_sub(page, 1 << order); if (!PageHighMem(page)) { - debug_check_no_locks_freed(page_address(page),PAGE_SIZE<<order); + debug_check_no_locks_freed(page_address(page), + PAGE_SIZE << order); debug_check_no_obj_freed(page_address(page), PAGE_SIZE << order); } + + 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 (!skip_kasan_poison) { + 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 + * happen after this. + */ arch_free_page(page, order); - kernel_map_pages(page, 1 << order, 0); + + debug_pagealloc_unmap_pages(page, 1 << order); return true; } -static void __free_pages_ok(struct page *page, unsigned int order) +/* + * Frees a number of pages from the PCP lists + * Assumes all pages on list are in same zone. + * count is the number of pages to free. + */ +static void free_pcppages_bulk(struct zone *zone, int count, + struct per_cpu_pages *pcp, + int pindex) { unsigned long flags; - int migratetype; + unsigned int order; + struct page *page; - if (!free_pages_prepare(page, order)) - return; + /* + * Ensure proper count is passed which otherwise would stuck in the + * below while (list_empty(list)) loop. + */ + count = min(pcp->count, count); + + /* Ensure requested pindex is drained first. */ + pindex = pindex - 1; + + spin_lock_irqsave(&zone->lock, flags); + + while (count > 0) { + struct list_head *list; + int nr_pages; + + /* Remove pages from lists in a round-robin fashion. */ + do { + if (++pindex > NR_PCP_LISTS - 1) + pindex = 0; + list = &pcp->lists[pindex]; + } while (list_empty(list)); + + order = pindex_to_order(pindex); + nr_pages = 1 << order; + do { + unsigned long pfn; + int mt; + + page = list_last_entry(list, struct page, pcp_list); + pfn = page_to_pfn(page); + mt = get_pfnblock_migratetype(page, pfn); + + /* must delete to avoid corrupting pcp list */ + list_del(&page->pcp_list); + count -= nr_pages; + pcp->count -= nr_pages; + + __free_one_page(page, pfn, zone, order, mt, FPI_NONE); + trace_mm_page_pcpu_drain(page, order, mt); + } while (count > 0 && !list_empty(list)); + } + + spin_unlock_irqrestore(&zone->lock, flags); +} + +/* Split a multi-block free page into its individual pageblocks. */ +static void split_large_buddy(struct zone *zone, struct page *page, + unsigned long pfn, int order, fpi_t fpi) +{ + unsigned long end = pfn + (1 << order); + + VM_WARN_ON_ONCE(!IS_ALIGNED(pfn, 1 << order)); + /* Caller removed page from freelist, buddy info cleared! */ + VM_WARN_ON_ONCE(PageBuddy(page)); + + if (order > pageblock_order) + order = pageblock_order; + + do { + int mt = get_pfnblock_migratetype(page, pfn); + + __free_one_page(page, pfn, zone, order, mt, fpi); + pfn += 1 << order; + if (pfn == end) + break; + page = pfn_to_page(pfn); + } while (1); +} + +static void add_page_to_zone_llist(struct zone *zone, struct page *page, + unsigned int order) +{ + /* Remember the order */ + page->private = order; + /* Add the page to the free list */ + llist_add(&page->pcp_llist, &zone->trylock_free_pages); +} + +static void free_one_page(struct zone *zone, struct page *page, + unsigned long pfn, unsigned int order, + fpi_t fpi_flags) +{ + struct llist_head *llhead; + unsigned long flags; + + if (unlikely(fpi_flags & FPI_TRYLOCK)) { + if (!spin_trylock_irqsave(&zone->lock, flags)) { + add_page_to_zone_llist(zone, page, order); + return; + } + } else { + spin_lock_irqsave(&zone->lock, flags); + } + + /* The lock succeeded. Process deferred pages. */ + llhead = &zone->trylock_free_pages; + if (unlikely(!llist_empty(llhead) && !(fpi_flags & FPI_TRYLOCK))) { + struct llist_node *llnode; + struct page *p, *tmp; + + llnode = llist_del_all(llhead); + llist_for_each_entry_safe(p, tmp, llnode, pcp_llist) { + unsigned int p_order = p->private; + + split_large_buddy(zone, p, page_to_pfn(p), p_order, fpi_flags); + __count_vm_events(PGFREE, 1 << p_order); + } + } + split_large_buddy(zone, page, pfn, order, fpi_flags); + spin_unlock_irqrestore(&zone->lock, flags); - local_irq_save(flags); __count_vm_events(PGFREE, 1 << order); - migratetype = get_pageblock_migratetype(page); - set_freepage_migratetype(page, migratetype); - free_one_page(page_zone(page), page, order, migratetype); - local_irq_restore(flags); } -void __init __free_pages_bootmem(struct page *page, unsigned int order) +static void __free_pages_ok(struct page *page, unsigned int order, + fpi_t fpi_flags) +{ + unsigned long pfn = page_to_pfn(page); + struct zone *zone = page_zone(page); + + if (free_pages_prepare(page, order)) + free_one_page(zone, page, pfn, order, fpi_flags); +} + +void __meminit __free_pages_core(struct page *page, unsigned int order, + enum meminit_context context) { unsigned int nr_pages = 1 << order; + struct page *p = page; unsigned int loop; - prefetchw(page); - for (loop = 0; loop < nr_pages; loop++) { - struct page *p = &page[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. + * + * Note that hotplugged memory pages are initialized to PageOffline(). + * Pages freed from memblock might be marked as reserved. + */ + if (IS_ENABLED(CONFIG_MEMORY_HOTPLUG) && + unlikely(context == MEMINIT_HOTPLUG)) { + for (loop = 0; loop < nr_pages; loop++, p++) { + VM_WARN_ON_ONCE(PageReserved(p)); + __ClearPageOffline(p); + set_page_count(p, 0); + } + + adjust_managed_page_count(page, nr_pages); + } else { + for (loop = 0; loop < nr_pages; loop++, p++) { + __ClearPageReserved(p); + set_page_count(p, 0); + } + + /* memblock adjusts totalram_pages() manually. */ + atomic_long_add(nr_pages, &page_zone(page)->managed_pages); + } + + if (page_contains_unaccepted(page, order)) { + if (order == MAX_PAGE_ORDER && __free_unaccepted(page)) + return; - if (loop + 1 < nr_pages) - prefetchw(p + 1); - __ClearPageReserved(p); - set_page_count(p, 0); + accept_memory(page_to_phys(page), PAGE_SIZE << order); } - page_zone(page)->managed_pages += 1 << order; - 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); } -#ifdef CONFIG_CMA -/* Free whole pageblock and set it's migration type to MIGRATE_CMA. */ -void __init init_cma_reserved_pageblock(struct page *page) +/* + * 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. + * + * Return struct page pointer of start_pfn, or NULL if checks were not passed. + * + * It's possible on some configurations to have a setup like node0 node1 node0 + * i.e. it's possible that all pages within a zones range of pages do not + * belong to a single zone. We assume that a border between node0 and node1 + * can occur within a single pageblock, but not a node0 node1 node0 + * interleaving within a single pageblock. It is therefore sufficient to check + * the first and last page of a pageblock and avoid checking each individual + * page in a pageblock. + * + * Note: the function may return non-NULL struct page even for a page block + * which contains a memory hole (i.e. there is no physical memory for a subset + * of the pfn range). For example, if the pageblock order is MAX_PAGE_ORDER, which + * will fall into 2 sub-sections, and the end pfn of the pageblock may be hole + * even though the start pfn is online and valid. This should be safe most of + * the time because struct pages are still initialized via init_unavailable_range() + * and pfn walkers shouldn't touch any physical memory range for which they do + * not recognize any specific metadata in struct pages. + */ +struct page *__pageblock_pfn_to_page(unsigned long start_pfn, + unsigned long end_pfn, struct zone *zone) { - unsigned i = pageblock_nr_pages; - struct page *p = page; + struct page *start_page; + struct page *end_page; - do { - __ClearPageReserved(p); - set_page_count(p, 0); - } while (++p, --i); + /* end_pfn is one past the range we are checking */ + end_pfn--; + + if (!pfn_valid(end_pfn)) + return NULL; + + start_page = pfn_to_online_page(start_pfn); + if (!start_page) + return NULL; + + if (page_zone(start_page) != zone) + return NULL; + + end_page = pfn_to_page(end_pfn); - set_page_refcounted(page); - set_pageblock_migratetype(page, MIGRATE_CMA); - __free_pages(page, pageblock_order); - adjust_managed_page_count(page, pageblock_nr_pages); + /* This gives a shorter code than deriving page_zone(end_page) */ + if (page_zone_id(start_page) != page_zone_id(end_page)) + return NULL; + + return start_page; } -#endif /* * The order of subdivision here is critical for the IO subsystem. @@ -800,106 +1686,212 @@ 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) +static inline unsigned int expand(struct zone *zone, struct page *page, int low, + int high, int migratetype) { - unsigned long size = 1 << high; + unsigned int size = 1 << high; + unsigned int nr_added = 0; while (high > low) { - area--; high--; size >>= 1; - VM_BUG_ON(bad_range(zone, &page[size])); + VM_BUG_ON_PAGE(bad_range(zone, &page[size]), &page[size]); -#ifdef CONFIG_DEBUG_PAGEALLOC - if (high < debug_guardpage_minorder()) { - /* - * Mark as guard pages (or page), that will allow to - * merge back to allocator when buddy will be freed. - * Corresponding page table entries will not be touched, - * pages will stay not present in virtual address space - */ - INIT_LIST_HEAD(&page[size].lru); - set_page_guard_flag(&page[size]); - set_page_private(&page[size], high); - /* Guard pages are not available for any usage */ - __mod_zone_freepage_state(zone, -(1 << high), - migratetype); + /* + * Mark as guard pages (or page), that will allow to + * merge back to allocator when buddy will be freed. + * Corresponding page table entries will not be touched, + * pages will stay not present in virtual address space + */ + if (set_page_guard(zone, &page[size], high)) continue; - } -#endif - list_add(&page[size].lru, &area->free_list[migratetype]); - area->nr_free++; - set_page_order(&page[size], high); + + __add_to_free_list(&page[size], zone, high, migratetype, false); + set_buddy_order(&page[size], high); + nr_added += size; } + + return nr_added; +} + +static __always_inline void page_del_and_expand(struct zone *zone, + struct page *page, int low, + int high, int migratetype) +{ + int nr_pages = 1 << high; + + __del_page_from_free_list(page, zone, high, migratetype); + nr_pages -= expand(zone, page, low, high, migratetype); + account_freepages(zone, -nr_pages, migratetype); +} + +static void check_new_page_bad(struct page *page) +{ + if (unlikely(PageHWPoison(page))) { + /* Don't complain about hwpoisoned pages */ + if (PageBuddy(page)) + __ClearPageBuddy(page); + return; + } + + bad_page(page, + page_bad_reason(page, PAGE_FLAGS_CHECK_AT_PREP)); } /* * This page is about to be returned from the page allocator */ -static inline int check_new_page(struct page *page) -{ - if (unlikely(page_mapcount(page) | - (page->mapping != NULL) | - (atomic_read(&page->_count) != 0) | - (page->flags & PAGE_FLAGS_CHECK_AT_PREP) | - (mem_cgroup_bad_page_check(page)))) { - bad_page(page); - return 1; - } - return 0; +static bool check_new_page(struct page *page) +{ + if (likely(page_expected_state(page, + PAGE_FLAGS_CHECK_AT_PREP|__PG_HWPOISON))) + return false; + + check_new_page_bad(page); + return true; } -static int prep_new_page(struct page *page, int order, gfp_t gfp_flags) +static inline bool check_new_pages(struct page *page, unsigned int order) { - int i; + if (is_check_pages_enabled()) { + for (int i = 0; i < (1 << order); i++) { + struct page *p = page + i; - for (i = 0; i < (1 << order); i++) { - struct page *p = page + i; - if (unlikely(check_new_page(p))) - return 1; + if (check_new_page(p)) + return true; + } } + return false; +} + +static inline bool should_skip_kasan_unpoison(gfp_t flags) +{ + /* Don't skip if a software KASAN mode is enabled. */ + if (IS_ENABLED(CONFIG_KASAN_GENERIC) || + IS_ENABLED(CONFIG_KASAN_SW_TAGS)) + return false; + + /* Skip, if hardware tag-based KASAN is not enabled. */ + if (!kasan_hw_tags_enabled()) + return true; + + /* + * With hardware tag-based KASAN enabled, skip if this has been + * requested via __GFP_SKIP_KASAN. + */ + return flags & __GFP_SKIP_KASAN; +} + +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 zero_tags = init && (gfp_flags & __GFP_ZEROTAGS); + int i; + set_page_private(page, 0); - set_page_refcounted(page); arch_alloc_page(page, order); - kernel_map_pages(page, 1 << order, 1); + debug_pagealloc_map_pages(page, 1 << order); - if (gfp_flags & __GFP_ZERO) - prep_zero_page(page, order, gfp_flags); + /* + * 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 (zero_tags) + init = !tag_clear_highpages(page, 1 << order); + + if (!should_skip_kasan_unpoison(gfp_flags) && + kasan_unpoison_pages(page, order, init)) { + /* Take note that memory was initialized by KASAN. */ + if (kasan_has_integrated_init()) + init = false; + } else { + /* + * If memory tags have not been set by KASAN, reset the page + * tags to 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, initialize it now. */ + if (init) + kernel_init_pages(page, 1 << order); + + set_page_owner(page, order, gfp_flags); + page_table_check_alloc(page, order); + pgalloc_tag_add(page, current, 1 << order); +} + +static void prep_new_page(struct page *page, unsigned int order, gfp_t gfp_flags, + unsigned int alloc_flags) +{ + post_alloc_hook(page, order, gfp_flags); if (order && (gfp_flags & __GFP_COMP)) prep_compound_page(page, order); - return 0; + /* + * page is set pfmemalloc when ALLOC_NO_WATERMARKS was necessary to + * allocate the page. The expectation is that the caller is taking + * steps that will free more memory. The caller should avoid the page + * being used for !PFMEMALLOC purposes. + */ + if (alloc_flags & ALLOC_NO_WATERMARKS) + set_page_pfmemalloc(page); + else + clear_page_pfmemalloc(page); } /* * Go through the free lists for the given migratetype and remove * the smallest available page from the freelists */ -static inline +static __always_inline struct page *__rmqueue_smallest(struct zone *zone, unsigned int order, int migratetype) { unsigned int current_order; - struct free_area * area; + struct free_area *area; struct page *page; /* Find a page of the appropriate size in the preferred list */ - for (current_order = order; current_order < MAX_ORDER; ++current_order) { + for (current_order = order; current_order < NR_PAGE_ORDERS; ++current_order) { area = &(zone->free_area[current_order]); - if (list_empty(&area->free_list[migratetype])) + page = get_page_from_free_area(area, migratetype); + if (!page) continue; - page = list_entry(area->free_list[migratetype].next, - struct page, lru); - list_del(&page->lru); - rmv_page_order(page); - area->nr_free--; - expand(zone, page, order, current_order, area, migratetype); + page_del_and_expand(zone, page, order, current_order, + migratetype); + trace_mm_page_alloc_zone_locked(page, order, migratetype, + pcp_allowed_order(order) && + migratetype < MIGRATE_PCPTYPES); return page; } @@ -910,92 +1902,251 @@ 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] = { - [MIGRATE_UNMOVABLE] = { MIGRATE_RECLAIMABLE, MIGRATE_MOVABLE, MIGRATE_RESERVE }, - [MIGRATE_RECLAIMABLE] = { MIGRATE_UNMOVABLE, MIGRATE_MOVABLE, MIGRATE_RESERVE }, +static int fallbacks[MIGRATE_PCPTYPES][MIGRATE_PCPTYPES - 1] = { + [MIGRATE_UNMOVABLE] = { MIGRATE_RECLAIMABLE, MIGRATE_MOVABLE }, + [MIGRATE_MOVABLE] = { MIGRATE_RECLAIMABLE, MIGRATE_UNMOVABLE }, + [MIGRATE_RECLAIMABLE] = { MIGRATE_UNMOVABLE, MIGRATE_MOVABLE }, +}; + #ifdef CONFIG_CMA - [MIGRATE_MOVABLE] = { MIGRATE_CMA, MIGRATE_RECLAIMABLE, MIGRATE_UNMOVABLE, MIGRATE_RESERVE }, - [MIGRATE_CMA] = { MIGRATE_RESERVE }, /* Never used */ +static __always_inline struct page *__rmqueue_cma_fallback(struct zone *zone, + unsigned int order) +{ + return __rmqueue_smallest(zone, order, MIGRATE_CMA); +} #else - [MIGRATE_MOVABLE] = { MIGRATE_RECLAIMABLE, MIGRATE_UNMOVABLE, MIGRATE_RESERVE }, -#endif - [MIGRATE_RESERVE] = { MIGRATE_RESERVE }, /* Never used */ -#ifdef CONFIG_MEMORY_ISOLATION - [MIGRATE_ISOLATE] = { MIGRATE_RESERVE }, /* Never used */ +static inline struct page *__rmqueue_cma_fallback(struct zone *zone, + unsigned int order) { return NULL; } #endif -}; /* - * Move the free pages in a range to the free lists 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() + * Move all free pages of a block to new type's freelist. Caller needs to + * change the block type. */ -int move_freepages(struct zone *zone, - struct page *start_page, struct page *end_page, - int migratetype) +static int __move_freepages_block(struct zone *zone, unsigned long start_pfn, + int old_mt, int new_mt) { struct page *page; - unsigned long order; + unsigned long pfn, end_pfn; + unsigned int order; int pages_moved = 0; -#ifndef CONFIG_HOLES_IN_ZONE - /* - * page_zone is not safe to call in this context when - * CONFIG_HOLES_IN_ZONE is set. This bug check is probably redundant - * anyway as we check zone boundaries in move_freepages_block(). - * Remove at a later date when no bug reports exist related to - * grouping pages by mobility - */ - BUG_ON(page_zone(start_page) != page_zone(end_page)); -#endif - - for (page = start_page; page <= end_page;) { - /* Make sure we are not inadvertently changing nodes */ - VM_BUG_ON(page_to_nid(page) != zone_to_nid(zone)); - - if (!pfn_valid_within(page_to_pfn(page))) { - page++; - continue; - } + VM_WARN_ON(start_pfn & (pageblock_nr_pages - 1)); + end_pfn = pageblock_end_pfn(start_pfn); + for (pfn = start_pfn; pfn < end_pfn;) { + page = pfn_to_page(pfn); if (!PageBuddy(page)) { - page++; + pfn++; continue; } - order = page_order(page); - list_move(&page->lru, - &zone->free_area[order].free_list[migratetype]); - set_freepage_migratetype(page, migratetype); - page += 1 << order; + /* Make sure we are not inadvertently changing nodes */ + VM_BUG_ON_PAGE(page_to_nid(page) != zone_to_nid(zone), page); + VM_BUG_ON_PAGE(page_zone(page) != zone, page); + + order = buddy_order(page); + + move_to_free_list(page, zone, order, old_mt, new_mt); + + pfn += 1 << order; pages_moved += 1 << order; } return pages_moved; } -int move_freepages_block(struct zone *zone, struct page *page, - int migratetype) +static bool prep_move_freepages_block(struct zone *zone, struct page *page, + unsigned long *start_pfn, + int *num_free, int *num_movable) { - unsigned long start_pfn, end_pfn; - struct page *start_page, *end_page; + unsigned long pfn, start, end; - 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 = pageblock_start_pfn(pfn); + end = pageblock_end_pfn(pfn); - /* Do not cross zone boundaries */ - if (!zone_spans_pfn(zone, start_pfn)) - start_page = page; - if (!zone_spans_pfn(zone, end_pfn)) - return 0; + /* + * The caller only has the lock for @zone, don't touch ranges + * that straddle into other zones. While we could move part of + * the range that's inside the zone, this call is usually + * accompanied by other operations such as migratetype updates + * which also should be locked. + */ + if (!zone_spans_pfn(zone, start)) + return false; + if (!zone_spans_pfn(zone, end - 1)) + return false; + + *start_pfn = start; + + if (num_free) { + *num_free = 0; + *num_movable = 0; + for (pfn = start; pfn < end;) { + page = pfn_to_page(pfn); + if (PageBuddy(page)) { + int nr = 1 << buddy_order(page); + + *num_free += nr; + pfn += nr; + continue; + } + /* + * We assume that pages that could be isolated for + * migration are movable. But we don't actually try + * isolating, as that would be expensive. + */ + if (PageLRU(page) || page_has_movable_ops(page)) + (*num_movable)++; + pfn++; + } + } - return move_freepages(zone, start_page, end_page, migratetype); + return true; } +static int move_freepages_block(struct zone *zone, struct page *page, + int old_mt, int new_mt) +{ + unsigned long start_pfn; + int res; + + if (!prep_move_freepages_block(zone, page, &start_pfn, NULL, NULL)) + return -1; + + res = __move_freepages_block(zone, start_pfn, old_mt, new_mt); + set_pageblock_migratetype(pfn_to_page(start_pfn), new_mt); + + return res; + +} + +#ifdef CONFIG_MEMORY_ISOLATION +/* Look for a buddy that straddles start_pfn */ +static unsigned long find_large_buddy(unsigned long start_pfn) +{ + /* + * If start_pfn is not an order-0 PageBuddy, next PageBuddy containing + * start_pfn has minimal order of __ffs(start_pfn) + 1. Start checking + * the order with __ffs(start_pfn). If start_pfn is order-0 PageBuddy, + * the starting order does not matter. + */ + int order = start_pfn ? __ffs(start_pfn) : MAX_PAGE_ORDER; + struct page *page; + unsigned long pfn = start_pfn; + + while (!PageBuddy(page = pfn_to_page(pfn))) { + /* Nothing found */ + if (++order > MAX_PAGE_ORDER) + return start_pfn; + pfn &= ~0UL << order; + } + + /* + * Found a preceding buddy, but does it straddle? + */ + if (pfn + (1 << buddy_order(page)) > start_pfn) + return pfn; + + /* Nothing found */ + return start_pfn; +} + +static inline void toggle_pageblock_isolate(struct page *page, bool isolate) +{ + if (isolate) + set_pageblock_isolate(page); + else + clear_pageblock_isolate(page); +} + +/** + * __move_freepages_block_isolate - move free pages in block for page isolation + * @zone: the zone + * @page: the pageblock page + * @isolate: to isolate the given pageblock or unisolate it + * + * This is similar to move_freepages_block(), but handles the special + * case encountered in page isolation, where the block of interest + * might be part of a larger buddy spanning multiple pageblocks. + * + * Unlike the regular page allocator path, which moves pages while + * stealing buddies off the freelist, page isolation is interested in + * arbitrary pfn ranges that may have overlapping buddies on both ends. + * + * This function handles that. Straddling buddies are split into + * individual pageblocks. Only the block of interest is moved. + * + * Returns %true if pages could be moved, %false otherwise. + */ +static bool __move_freepages_block_isolate(struct zone *zone, + struct page *page, bool isolate) +{ + unsigned long start_pfn, buddy_pfn; + int from_mt; + int to_mt; + struct page *buddy; + + if (isolate == get_pageblock_isolate(page)) { + VM_WARN_ONCE(1, "%s a pageblock that is already in that state", + isolate ? "Isolate" : "Unisolate"); + return false; + } + + if (!prep_move_freepages_block(zone, page, &start_pfn, NULL, NULL)) + return false; + + /* No splits needed if buddies can't span multiple blocks */ + if (pageblock_order == MAX_PAGE_ORDER) + goto move; + + buddy_pfn = find_large_buddy(start_pfn); + buddy = pfn_to_page(buddy_pfn); + /* We're a part of a larger buddy */ + if (PageBuddy(buddy) && buddy_order(buddy) > pageblock_order) { + int order = buddy_order(buddy); + + del_page_from_free_list(buddy, zone, order, + get_pfnblock_migratetype(buddy, buddy_pfn)); + toggle_pageblock_isolate(page, isolate); + split_large_buddy(zone, buddy, buddy_pfn, order, FPI_NONE); + return true; + } + +move: + /* Use MIGRATETYPE_MASK to get non-isolate migratetype */ + if (isolate) { + from_mt = __get_pfnblock_flags_mask(page, page_to_pfn(page), + MIGRATETYPE_MASK); + to_mt = MIGRATE_ISOLATE; + } else { + from_mt = MIGRATE_ISOLATE; + to_mt = __get_pfnblock_flags_mask(page, page_to_pfn(page), + MIGRATETYPE_MASK); + } + + __move_freepages_block(zone, start_pfn, from_mt, to_mt); + toggle_pageblock_isolate(pfn_to_page(start_pfn), isolate); + + return true; +} + +bool pageblock_isolate_and_move_free_pages(struct zone *zone, struct page *page) +{ + return __move_freepages_block_isolate(zone, page, true); +} + +bool pageblock_unisolate_and_move_free_pages(struct zone *zone, struct page *page) +{ + return __move_freepages_block_isolate(zone, page, false); +} + +#endif /* CONFIG_MEMORY_ISOLATION */ + static void change_pageblock_range(struct page *pageblock_page, int start_order, int migratetype) { @@ -1007,79 +2158,243 @@ static void change_pageblock_range(struct page *pageblock_page, } } -/* Remove an element from the buddy allocator from the fallback list */ -static inline struct page * -__rmqueue_fallback(struct zone *zone, int order, int start_migratetype) +static inline bool boost_watermark(struct zone *zone) { - struct free_area * area; - int current_order; - struct page *page; - int migratetype, i; + unsigned long max_boost; - /* Find the largest possible block of pages in the other list */ - for (current_order = MAX_ORDER-1; current_order >= order; - --current_order) { - for (i = 0;; i++) { - migratetype = fallbacks[start_migratetype][i]; + if (!watermark_boost_factor) + 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; - /* MIGRATE_RESERVE handled later if necessary */ - if (migratetype == MIGRATE_RESERVE) - break; + max_boost = mult_frac(zone->_watermark[WMARK_HIGH], + watermark_boost_factor, 10000); - area = &(zone->free_area[current_order]); - if (list_empty(&area->free_list[migratetype])) - continue; + /* + * high watermark may be uninitialised if fragmentation occurs + * very early in boot so do not boost. We do not fall + * through and boost by pageblock_nr_pages as failing + * allocations that early means that reclaim is not going + * to help and it may even be impossible to reclaim the + * boosted watermark resulting in a hang. + */ + if (!max_boost) + return false; - page = list_entry(area->free_list[migratetype].next, - struct page, lru); - area->nr_free--; + max_boost = max(pageblock_nr_pages, max_boost); - /* - * If breaking a large block of pages, move all free - * pages to the preferred allocation list. If falling - * back for a reclaimable kernel allocation, be more - * aggressive about taking ownership of free pages - * - * On the other hand, never change migration - * type of MIGRATE_CMA pageblocks nor move CMA - * pages on different free lists. We don't - * want unmovable pages to be allocated from - * MIGRATE_CMA areas. - */ - if (!is_migrate_cma(migratetype) && - (current_order >= pageblock_order / 2 || - start_migratetype == MIGRATE_RECLAIMABLE || - page_group_by_mobility_disabled)) { - int pages; - pages = move_freepages_block(zone, page, - start_migratetype); - - /* Claim the whole block if over half of it is free */ - if (pages >= (1 << (pageblock_order-1)) || - page_group_by_mobility_disabled) - set_pageblock_migratetype(page, - start_migratetype); - - migratetype = start_migratetype; - } + zone->watermark_boost = min(zone->watermark_boost + pageblock_nr_pages, + max_boost); - /* Remove the page from the freelists */ - list_del(&page->lru); - rmv_page_order(page); + return true; +} - /* Take ownership for orders >= pageblock_order */ - if (current_order >= pageblock_order && - !is_migrate_cma(migratetype)) - change_pageblock_range(page, current_order, - start_migratetype); +/* + * When we are falling back to another migratetype during allocation, should we + * try to claim an entire block to satisfy further allocations, instead of + * polluting multiple pageblocks? + */ +static bool should_try_claim_block(unsigned int order, int start_mt) +{ + /* + * Leaving this order check is intended, although there is + * relaxed order check in next check. The reason is that + * we can actually claim the whole pageblock if this condition met, + * but, below check doesn't guarantee it and that is just heuristic + * so could be changed anytime. + */ + if (order >= pageblock_order) + return true; - expand(zone, page, order, current_order, area, - is_migrate_cma(migratetype) - ? migratetype : start_migratetype); + /* + * Above a certain threshold, always try to claim, as it's likely there + * will be more free pages in the pageblock. + */ + if (order >= pageblock_order / 2) + return true; - trace_mm_page_alloc_extfrag(page, order, current_order, - start_migratetype, migratetype); + /* + * Unmovable/reclaimable allocations would cause permanent + * fragmentations if they fell back to allocating from a movable block + * (polluting it), so we try to claim the whole block regardless of the + * allocation size. Later movable allocations can always steal from this + * block, which is less problematic. + */ + if (start_mt == MIGRATE_RECLAIMABLE || start_mt == MIGRATE_UNMOVABLE) + return true; + + if (page_group_by_mobility_disabled) + return true; + + /* + * Movable pages won't cause permanent fragmentation, so when you alloc + * small pages, we just need to temporarily steal unmovable or + * reclaimable pages that are closest to the request size. After a + * while, memory compaction may occur to form large contiguous pages, + * and the next movable allocation may not need to steal. + */ + return false; +} + +/* + * Check whether there is a suitable fallback freepage with requested order. + * If claimable is true, this function returns fallback_mt only if + * we would do this whole-block claiming. This would help to reduce + * fragmentation due to mixed migratetype pages in one pageblock. + */ +int find_suitable_fallback(struct free_area *area, unsigned int order, + int migratetype, bool claimable) +{ + int i; + + if (claimable && !should_try_claim_block(order, migratetype)) + return -2; + + if (area->nr_free == 0) + return -1; + + for (i = 0; i < MIGRATE_PCPTYPES - 1 ; i++) { + int fallback_mt = fallbacks[migratetype][i]; + + if (!free_area_empty(area, fallback_mt)) + return fallback_mt; + } + + return -1; +} + +/* + * This function implements actual block claiming behaviour. If order is large + * enough, we can claim the whole pageblock for the requested migratetype. If + * not, we check the pageblock for constituent pages; if at least half of the + * pages are free or compatible, we can still claim the whole block, so pages + * freed in the future will be put on the correct free list. + */ +static struct page * +try_to_claim_block(struct zone *zone, struct page *page, + int current_order, int order, int start_type, + int block_type, unsigned int alloc_flags) +{ + int free_pages, movable_pages, alike_pages; + unsigned long start_pfn; + + /* Take ownership for orders >= pageblock_order */ + if (current_order >= pageblock_order) { + unsigned int nr_added; + + del_page_from_free_list(page, zone, current_order, block_type); + change_pageblock_range(page, current_order, start_type); + nr_added = expand(zone, page, order, current_order, start_type); + account_freepages(zone, nr_added, start_type); + return page; + } + + /* + * Boost watermarks to increase reclaim pressure to reduce the + * likelihood of future fallbacks. Wake kswapd now as the node + * may be balanced overall and kswapd will not wake naturally. + */ + if (boost_watermark(zone) && (alloc_flags & ALLOC_KSWAPD)) + set_bit(ZONE_BOOSTED_WATERMARK, &zone->flags); + + /* moving whole block can fail due to zone boundary conditions */ + if (!prep_move_freepages_block(zone, page, &start_pfn, &free_pages, + &movable_pages)) + return NULL; + + /* + * Determine how many pages are compatible with our allocation. + * For movable allocation, it's the number of movable pages which + * we just obtained. For other types it's a bit more tricky. + */ + if (start_type == MIGRATE_MOVABLE) { + alike_pages = movable_pages; + } else { + /* + * If we are falling back a RECLAIMABLE or UNMOVABLE allocation + * to MOVABLE pageblock, consider all non-movable pages as + * compatible. If it's UNMOVABLE falling back to RECLAIMABLE or + * vice versa, be conservative since we can't distinguish the + * exact migratetype of non-movable pages. + */ + if (block_type == MIGRATE_MOVABLE) + alike_pages = pageblock_nr_pages + - (free_pages + movable_pages); + else + alike_pages = 0; + } + /* + * If a sufficient number of pages in the block are either free or of + * compatible migratability as our allocation, claim the whole block. + */ + if (free_pages + alike_pages >= (1 << (pageblock_order-1)) || + page_group_by_mobility_disabled) { + __move_freepages_block(zone, start_pfn, block_type, start_type); + set_pageblock_migratetype(pfn_to_page(start_pfn), start_type); + return __rmqueue_smallest(zone, order, start_type); + } + + return NULL; +} + +/* + * Try to allocate from some fallback migratetype by claiming the entire block, + * i.e. converting it to the allocation's start migratetype. + * + * The use of signed ints for order and current_order is a deliberate + * deviation from the rest of this file, to make the for loop + * condition simpler. + */ +static __always_inline struct page * +__rmqueue_claim(struct zone *zone, int order, int start_migratetype, + unsigned int alloc_flags) +{ + struct free_area *area; + int current_order; + int min_order = order; + struct page *page; + int fallback_mt; + + /* + * Do not steal pages from freelists belonging to other pageblocks + * i.e. orders < pageblock_order. If there are no local zones free, + * the zonelists will be reiterated without ALLOC_NOFRAGMENT. + */ + if (order < pageblock_order && alloc_flags & ALLOC_NOFRAGMENT) + min_order = pageblock_order; + + /* + * Find the largest available free page in the other list. This roughly + * approximates finding the pageblock with the most free pages, which + * would be too costly to do exactly. + */ + for (current_order = MAX_PAGE_ORDER; current_order >= min_order; + --current_order) { + area = &(zone->free_area[current_order]); + fallback_mt = find_suitable_fallback(area, current_order, + start_migratetype, true); + + /* No block in that order */ + if (fallback_mt == -1) + continue; + + /* Advanced into orders too low to claim, abort */ + if (fallback_mt == -2) + break; + page = get_page_from_free_area(area, fallback_mt); + page = try_to_claim_block(zone, page, current_order, order, + start_migratetype, fallback_mt, + alloc_flags); + if (page) { + trace_mm_page_alloc_extfrag(page, order, current_order, + start_migratetype, fallback_mt); return page; } } @@ -1088,33 +2403,108 @@ __rmqueue_fallback(struct zone *zone, int order, int start_migratetype) } /* - * Do the hard work of removing an element from the buddy allocator. - * Call me with the zone->lock already held. + * Try to steal a single page from some fallback migratetype. Leave the rest of + * the block as its current migratetype, potentially causing fragmentation. */ -static struct page *__rmqueue(struct zone *zone, unsigned int order, - int migratetype) +static __always_inline struct page * +__rmqueue_steal(struct zone *zone, int order, int start_migratetype) { + struct free_area *area; + int current_order; struct page *page; + int fallback_mt; -retry_reserve: - page = __rmqueue_smallest(zone, order, migratetype); + for (current_order = order; current_order < NR_PAGE_ORDERS; current_order++) { + area = &(zone->free_area[current_order]); + fallback_mt = find_suitable_fallback(area, current_order, + start_migratetype, false); + if (fallback_mt == -1) + continue; + + page = get_page_from_free_area(area, fallback_mt); + page_del_and_expand(zone, page, order, current_order, fallback_mt); + trace_mm_page_alloc_extfrag(page, order, current_order, + start_migratetype, fallback_mt); + return page; + } - if (unlikely(!page) && migratetype != MIGRATE_RESERVE) { - page = __rmqueue_fallback(zone, order, migratetype); + return NULL; +} +enum rmqueue_mode { + RMQUEUE_NORMAL, + RMQUEUE_CMA, + RMQUEUE_CLAIM, + RMQUEUE_STEAL, +}; + +/* + * Do the hard work of removing an element from the buddy allocator. + * Call me with the zone->lock already held. + */ +static __always_inline struct page * +__rmqueue(struct zone *zone, unsigned int order, int migratetype, + unsigned int alloc_flags, enum rmqueue_mode *mode) +{ + struct page *page; + + if (IS_ENABLED(CONFIG_CMA)) { /* - * Use MIGRATE_RESERVE rather than fail an allocation. goto - * is used because __rmqueue_smallest is an inline function - * and we want just one call site + * 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 (!page) { - migratetype = MIGRATE_RESERVE; - goto retry_reserve; + 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; } } - trace_mm_page_alloc_zone_locked(page, order, migratetype); - return page; + /* + * First try the freelists of the requested migratetype, then try + * fallbacks modes with increasing levels of fragmentation risk. + * + * The fallback logic is expensive and rmqueue_bulk() calls in + * a loop with the zone->lock held, meaning the freelists are + * not subject to any outside changes. Remember in *mode where + * we found pay dirt, to save us the search on the next call. + */ + switch (*mode) { + case RMQUEUE_NORMAL: + page = __rmqueue_smallest(zone, order, migratetype); + if (page) + return page; + fallthrough; + case RMQUEUE_CMA: + if (alloc_flags & ALLOC_CMA) { + page = __rmqueue_cma_fallback(zone, order); + if (page) { + *mode = RMQUEUE_CMA; + return page; + } + } + fallthrough; + case RMQUEUE_CLAIM: + page = __rmqueue_claim(zone, order, migratetype, alloc_flags); + if (page) { + /* Replenished preferred freelist, back to normal mode. */ + *mode = RMQUEUE_NORMAL; + return page; + } + fallthrough; + case RMQUEUE_STEAL: + if (!(alloc_flags & ALLOC_NOFRAGMENT)) { + page = __rmqueue_steal(zone, order, migratetype); + if (page) { + *mode = RMQUEUE_STEAL; + return page; + } + } + } + return NULL; } /* @@ -1124,251 +2514,567 @@ retry_reserve: */ static int rmqueue_bulk(struct zone *zone, unsigned int order, unsigned long count, struct list_head *list, - int migratetype, int cold) + int migratetype, unsigned int alloc_flags) { - int mt = migratetype, i; + enum rmqueue_mode rmqm = RMQUEUE_NORMAL; + unsigned long flags; + int i; - spin_lock(&zone->lock); + if (unlikely(alloc_flags & ALLOC_TRYLOCK)) { + if (!spin_trylock_irqsave(&zone->lock, flags)) + return 0; + } else { + spin_lock_irqsave(&zone->lock, flags); + } for (i = 0; i < count; ++i) { - struct page *page = __rmqueue(zone, order, migratetype); + struct page *page = __rmqueue(zone, order, migratetype, + alloc_flags, &rmqm); if (unlikely(page == NULL)) break; /* - * Split buddy pages returned by expand() are received here - * in physical page order. The page is added to the callers and - * list and the list head then moves forward. From the callers - * perspective, the linked list is ordered by page number in - * some conditions. This is useful for IO devices that can - * merge IO requests if the physical pages are ordered - * properly. + * Split buddy pages returned by expand() are received here in + * physical page order. The page is added to the tail of + * caller's list. From the callers perspective, the linked list + * is ordered by page number under some conditions. This is + * useful for IO devices that can forward direction from the + * head, thus also in the physical page order. This is useful + * for IO devices that can merge IO requests if the physical + * pages are ordered properly. */ - if (likely(cold == 0)) - list_add(&page->lru, list); - else - list_add_tail(&page->lru, list); - if (IS_ENABLED(CONFIG_CMA)) { - mt = get_pageblock_migratetype(page); - if (!is_migrate_cma(mt) && !is_migrate_isolate(mt)) - mt = migratetype; - } - set_freepage_migratetype(page, mt); - list = &page->lru; - if (is_migrate_cma(mt)) - __mod_zone_page_state(zone, NR_FREE_CMA_PAGES, - -(1 << order)); - } - __mod_zone_page_state(zone, NR_FREE_PAGES, -(i << order)); - spin_unlock(&zone->lock); + list_add_tail(&page->pcp_list, list); + } + spin_unlock_irqrestore(&zone->lock, flags); + return i; } +/* + * Called from the vmstat counter updater to decay the PCP high. + * Return whether there are addition works to do. + */ +bool decay_pcp_high(struct zone *zone, struct per_cpu_pages *pcp) +{ + int high_min, to_drain, to_drain_batched, batch; + bool todo = false; + + high_min = READ_ONCE(pcp->high_min); + batch = READ_ONCE(pcp->batch); + /* + * Decrease pcp->high periodically to try to free possible + * idle PCP pages. And, avoid to free too many pages to + * control latency. This caps pcp->high decrement too. + */ + if (pcp->high > high_min) { + pcp->high = max3(pcp->count - (batch << CONFIG_PCP_BATCH_SCALE_MAX), + pcp->high - (pcp->high >> 3), high_min); + if (pcp->high > high_min) + todo = true; + } + + to_drain = pcp->count - pcp->high; + while (to_drain > 0) { + to_drain_batched = min(to_drain, batch); + spin_lock(&pcp->lock); + free_pcppages_bulk(zone, to_drain_batched, pcp, 0); + spin_unlock(&pcp->lock); + todo = true; + + to_drain -= to_drain_batched; + } + + return todo; +} + #ifdef CONFIG_NUMA /* * 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; - unsigned long batch; + int to_drain, batch; - local_irq_save(flags); - batch = ACCESS_ONCE(pcp->batch); - if (pcp->count >= batch) - to_drain = batch; - else - to_drain = pcp->count; + batch = READ_ONCE(pcp->batch); + to_drain = min(pcp->count, batch); if (to_drain > 0) { - free_pcppages_bulk(zone, to_drain, pcp); - pcp->count -= to_drain; + spin_lock(&pcp->lock); + free_pcppages_bulk(zone, to_drain, pcp, 0); + spin_unlock(&pcp->lock); } - local_irq_restore(flags); } #endif /* - * Drain pages of 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. + * Drain pcplists of the indicated processor and zone. + */ +static void drain_pages_zone(unsigned int cpu, struct zone *zone) +{ + struct per_cpu_pages *pcp = per_cpu_ptr(zone->per_cpu_pageset, cpu); + int count; + + do { + spin_lock(&pcp->lock); + count = pcp->count; + if (count) { + int to_drain = min(count, + pcp->batch << CONFIG_PCP_BATCH_SCALE_MAX); + + free_pcppages_bulk(zone, to_drain, pcp, 0); + count -= to_drain; + } + spin_unlock(&pcp->lock); + } while (count); +} + +/* + * Drain pcplists of all zones on the indicated processor. */ static void drain_pages(unsigned int cpu) { - unsigned long flags; struct zone *zone; for_each_populated_zone(zone) { - struct per_cpu_pageset *pset; - struct per_cpu_pages *pcp; - - local_irq_save(flags); - pset = per_cpu_ptr(zone->pageset, cpu); - - pcp = &pset->pcp; - if (pcp->count) { - free_pcppages_bulk(zone, pcp->count, pcp); - pcp->count = 0; - } - local_irq_restore(flags); + drain_pages_zone(cpu, zone); } } /* * Spill all of this CPU's per-cpu pages back into the buddy allocator. */ -void drain_local_pages(void *arg) +void drain_local_pages(struct zone *zone) { - drain_pages(smp_processor_id()); + int cpu = smp_processor_id(); + + if (zone) + drain_pages_zone(cpu, zone); + else + drain_pages(cpu); } /* - * Spill all the per-cpu pages from all CPUs back into the buddy allocator. + * The implementation of drain_all_pages(), exposing an extra parameter to + * drain on all cpus. * - * Note that this code is protected against sending an IPI to an offline - * CPU but does not guarantee sending an IPI to newly hotplugged CPUs: - * on_each_cpu_mask() blocks hotplug and won't talk to offlined CPUs but - * nothing keeps CPUs from showing up after we populated the cpumask and - * before the call to on_each_cpu_mask(). + * 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(void) +static void __drain_all_pages(struct zone *zone, bool force_all_cpus) { int cpu; - struct per_cpu_pageset *pcp; - struct zone *zone; /* - * 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; /* + * 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. + */ + if (unlikely(!mutex_trylock(&pcpu_drain_mutex))) { + if (!zone) + return; + mutex_lock(&pcpu_drain_mutex); + } + + /* * We don't care about racing with CPU hotplug event * as offline notification will cause the notified * cpu to drain that CPU pcps and on_each_cpu_mask * disables preemption as part of its processing */ for_each_online_cpu(cpu) { + struct per_cpu_pages *pcp; + struct zone *z; bool has_pcps = false; - for_each_populated_zone(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; - break; + } else { + for_each_populated_zone(z) { + pcp = per_cpu_ptr(z->per_cpu_pageset, cpu); + if (pcp->count) { + has_pcps = true; + break; + } } } + if (has_pcps) cpumask_set_cpu(cpu, &cpus_with_pcps); else cpumask_clear_cpu(cpu, &cpus_with_pcps); } - on_each_cpu_mask(&cpus_with_pcps, drain_local_pages, NULL, 1); + + for_each_cpu(cpu, &cpus_with_pcps) { + if (zone) + drain_pages_zone(cpu, zone); + else + drain_pages(cpu); + } + + mutex_unlock(&pcpu_drain_mutex); } -#ifdef CONFIG_HIBERNATION +/* + * 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); +} -void mark_free_pages(struct zone *zone) +static int nr_pcp_free(struct per_cpu_pages *pcp, int batch, int high, bool free_high) { - unsigned long pfn, max_zone_pfn; - unsigned long flags; - int order, t; - struct list_head *curr; + int min_nr_free, max_nr_free; - if (!zone->spanned_pages) - return; + /* Free as much as possible if batch freeing high-order pages. */ + if (unlikely(free_high)) + return min(pcp->count, batch << CONFIG_PCP_BATCH_SCALE_MAX); - spin_lock_irqsave(&zone->lock, flags); + /* Check for PCP disabled or boot pageset */ + if (unlikely(high < batch)) + return 1; - max_zone_pfn = zone_end_pfn(zone); - for (pfn = zone->zone_start_pfn; pfn < max_zone_pfn; pfn++) - if (pfn_valid(pfn)) { - struct page *page = pfn_to_page(pfn); + /* Leave at least pcp->batch pages on the list */ + min_nr_free = batch; + max_nr_free = high - batch; - if (!swsusp_page_is_forbidden(page)) - swsusp_unset_page_free(page); - } + /* + * Increase the batch number to the number of the consecutive + * freed pages to reduce zone lock contention. + */ + batch = clamp_t(int, pcp->free_count, min_nr_free, max_nr_free); + + return batch; +} + +static int nr_pcp_high(struct per_cpu_pages *pcp, struct zone *zone, + int batch, bool free_high) +{ + int high, high_min, high_max; + + high_min = READ_ONCE(pcp->high_min); + high_max = READ_ONCE(pcp->high_max); + high = pcp->high = clamp(pcp->high, high_min, high_max); + + if (unlikely(!high)) + return 0; + + if (unlikely(free_high)) { + pcp->high = max(high - (batch << CONFIG_PCP_BATCH_SCALE_MAX), + high_min); + return 0; + } - for_each_migratetype_order(order, t) { - list_for_each(curr, &zone->free_area[order].free_list[t]) { - unsigned long i; + /* + * If reclaim is active, limit the number of pages that can be + * stored on pcp lists + */ + if (test_bit(ZONE_RECLAIM_ACTIVE, &zone->flags)) { + int free_count = max_t(int, pcp->free_count, batch); + + pcp->high = max(high - free_count, high_min); + return min(batch << 2, pcp->high); + } + + if (high_min == high_max) + return high; + + if (test_bit(ZONE_BELOW_HIGH, &zone->flags)) { + int free_count = max_t(int, pcp->free_count, batch); + + pcp->high = max(high - free_count, high_min); + high = max(pcp->count, high_min); + } else if (pcp->count >= high) { + int need_high = pcp->free_count + batch; + + /* pcp->high should be large enough to hold batch freed pages */ + if (pcp->high < need_high) + pcp->high = clamp(need_high, high_min, high_max); + } + + return high; +} + +/* + * Tune pcp alloc factor and adjust count & free_count. Free pages to bring the + * pcp's watermarks below high. + * + * May return a freed pcp, if during page freeing the pcp spinlock cannot be + * reacquired. Return true if pcp is locked, false otherwise. + */ +static bool free_frozen_page_commit(struct zone *zone, + struct per_cpu_pages *pcp, struct page *page, int migratetype, + unsigned int order, fpi_t fpi_flags, unsigned long *UP_flags) +{ + int high, batch; + int to_free, to_free_batched; + int pindex; + int cpu = smp_processor_id(); + int ret = true; + bool free_high = false; + + /* + * On freeing, reduce the number of pages that are batch allocated. + * See nr_pcp_alloc() where alloc_factor is increased for subsequent + * allocations. + */ + pcp->alloc_factor >>= 1; + __count_vm_events(PGFREE, 1 << order); + pindex = order_to_pindex(migratetype, order); + list_add(&page->pcp_list, &pcp->lists[pindex]); + pcp->count += 1 << order; - pfn = page_to_pfn(list_entry(curr, struct page, lru)); - for (i = 0; i < (1UL << order); i++) - swsusp_set_page_free(pfn_to_page(pfn + i)); + batch = READ_ONCE(pcp->batch); + /* + * 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. + */ + if (order && order <= PAGE_ALLOC_COSTLY_ORDER) { + free_high = (pcp->free_count >= (batch + pcp->high_min / 2) && + (pcp->flags & PCPF_PREV_FREE_HIGH_ORDER) && + (!(pcp->flags & PCPF_FREE_HIGH_BATCH) || + pcp->count >= batch)); + pcp->flags |= PCPF_PREV_FREE_HIGH_ORDER; + } else if (pcp->flags & PCPF_PREV_FREE_HIGH_ORDER) { + pcp->flags &= ~PCPF_PREV_FREE_HIGH_ORDER; + } + if (pcp->free_count < (batch << CONFIG_PCP_BATCH_SCALE_MAX)) + pcp->free_count += (1 << order); + + if (unlikely(fpi_flags & FPI_TRYLOCK)) { + /* + * Do not attempt to take a zone lock. Let pcp->count get + * over high mark temporarily. + */ + return true; + } + + high = nr_pcp_high(pcp, zone, batch, free_high); + if (pcp->count < high) + return true; + + to_free = nr_pcp_free(pcp, batch, high, free_high); + while (to_free > 0 && pcp->count > 0) { + to_free_batched = min(to_free, batch); + free_pcppages_bulk(zone, to_free_batched, pcp, pindex); + to_free -= to_free_batched; + + if (to_free == 0 || pcp->count == 0) + break; + + pcp_spin_unlock(pcp, *UP_flags); + + pcp = pcp_spin_trylock(zone->per_cpu_pageset, *UP_flags); + if (!pcp) { + ret = false; + break; + } + + /* + * Check if this thread has been migrated to a different CPU. + * If that is the case, give up and indicate that the pcp is + * returned in an unlocked state. + */ + if (smp_processor_id() != cpu) { + pcp_spin_unlock(pcp, *UP_flags); + ret = false; + break; } } - spin_unlock_irqrestore(&zone->lock, flags); + + if (test_bit(ZONE_BELOW_HIGH, &zone->flags) && + zone_watermark_ok(zone, 0, high_wmark_pages(zone), + ZONE_MOVABLE, 0)) { + struct pglist_data *pgdat = zone->zone_pgdat; + clear_bit(ZONE_BELOW_HIGH, &zone->flags); + + /* + * Assume that memory pressure on this node is gone and may be + * in a reclaimable state. If a memory fallback node exists, + * direct reclaim may not have been triggered, causing a + * 'hopeless node' to stay in that state for a while. Let + * kswapd work again by resetting kswapd_failures. + */ + if (atomic_read(&pgdat->kswapd_failures) >= MAX_RECLAIM_RETRIES && + next_memory_node(pgdat->node_id) < MAX_NUMNODES) + atomic_set(&pgdat->kswapd_failures, 0); + } + return ret; } -#endif /* CONFIG_PM */ /* - * Free a 0-order page - * cold == 1 ? free a cold page : free a hot page + * Free a pcp page */ -void free_hot_cold_page(struct page *page, int cold) +static void __free_frozen_pages(struct page *page, unsigned int order, + fpi_t fpi_flags) { - struct zone *zone = page_zone(page); + unsigned long UP_flags; struct per_cpu_pages *pcp; - unsigned long flags; + struct zone *zone; + unsigned long pfn = page_to_pfn(page); int migratetype; - if (!free_pages_prepare(page, 0)) + if (!pcp_allowed_order(order)) { + __free_pages_ok(page, order, fpi_flags); return; + } - migratetype = get_pageblock_migratetype(page); - set_freepage_migratetype(page, migratetype); - local_irq_save(flags); - __count_vm_event(PGFREE); + if (!free_pages_prepare(page, order)) + return; /* * We only track unmovable, reclaimable and movable on pcp lists. - * Free ISOLATE pages back to the allocator because they are being - * offlined but treat RESERVE as movable pages so we can get those - * areas back if necessary. Otherwise, we may have to free + * Place ISOLATE pages on the isolated list because they are being + * offlined but treat HIGHATOMIC and CMA 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) { + zone = page_zone(page); + migratetype = get_pfnblock_migratetype(page, pfn); + if (unlikely(migratetype >= MIGRATE_PCPTYPES)) { if (unlikely(is_migrate_isolate(migratetype))) { - free_one_page(zone, page, 0, migratetype); - goto out; + free_one_page(zone, page, pfn, order, fpi_flags); + return; } migratetype = MIGRATE_MOVABLE; } - pcp = &this_cpu_ptr(zone->pageset)->pcp; - if (cold) - list_add_tail(&page->lru, &pcp->lists[migratetype]); - else - list_add(&page->lru, &pcp->lists[migratetype]); - pcp->count++; - if (pcp->count >= pcp->high) { - unsigned long batch = ACCESS_ONCE(pcp->batch); - free_pcppages_bulk(zone, batch, pcp); - pcp->count -= batch; + if (unlikely((fpi_flags & FPI_TRYLOCK) && IS_ENABLED(CONFIG_PREEMPT_RT) + && (in_nmi() || in_hardirq()))) { + add_page_to_zone_llist(zone, page, order); + return; } + pcp = pcp_spin_trylock(zone->per_cpu_pageset, UP_flags); + if (pcp) { + if (!free_frozen_page_commit(zone, pcp, page, migratetype, + order, fpi_flags, &UP_flags)) + return; + pcp_spin_unlock(pcp, UP_flags); + } else { + free_one_page(zone, page, pfn, order, fpi_flags); + } +} -out: - local_irq_restore(flags); +void free_frozen_pages(struct page *page, unsigned int order) +{ + __free_frozen_pages(page, order, FPI_NONE); } /* - * Free a list of 0-order pages + * Free a batch of folios */ -void free_hot_cold_page_list(struct list_head *list, int cold) +void free_unref_folios(struct folio_batch *folios) { - struct page *page, *next; + unsigned long UP_flags; + struct per_cpu_pages *pcp = NULL; + struct zone *locked_zone = NULL; + int i, j; - list_for_each_entry_safe(page, next, list, lru) { - trace_mm_page_free_batched(page, cold); - free_hot_cold_page(page, cold); + /* Prepare folios for freeing */ + for (i = 0, j = 0; i < folios->nr; i++) { + struct folio *folio = folios->folios[i]; + unsigned long pfn = folio_pfn(folio); + unsigned int order = folio_order(folio); + + if (!free_pages_prepare(&folio->page, order)) + continue; + /* + * Free orders not handled on the PCP directly to the + * allocator. + */ + if (!pcp_allowed_order(order)) { + free_one_page(folio_zone(folio), &folio->page, + pfn, order, FPI_NONE); + continue; + } + folio->private = (void *)(unsigned long)order; + if (j != i) + folios->folios[j] = folio; + j++; } + folios->nr = j; + + for (i = 0; i < folios->nr; i++) { + struct folio *folio = folios->folios[i]; + struct zone *zone = folio_zone(folio); + unsigned long pfn = folio_pfn(folio); + unsigned int order = (unsigned long)folio->private; + int migratetype; + + folio->private = NULL; + migratetype = get_pfnblock_migratetype(&folio->page, pfn); + + /* Different zone requires a different pcp lock */ + if (zone != locked_zone || + is_migrate_isolate(migratetype)) { + if (pcp) { + pcp_spin_unlock(pcp, UP_flags); + locked_zone = NULL; + pcp = NULL; + } + + /* + * Free isolated pages directly to the + * allocator, see comment in free_frozen_pages. + */ + if (is_migrate_isolate(migratetype)) { + free_one_page(zone, &folio->page, pfn, + order, FPI_NONE); + continue; + } + + /* + * trylock is necessary as folios may be getting freed + * from IRQ or SoftIRQ context after an IO completion. + */ + pcp = pcp_spin_trylock(zone->per_cpu_pageset, UP_flags); + if (unlikely(!pcp)) { + free_one_page(zone, &folio->page, pfn, + order, FPI_NONE); + continue; + } + locked_zone = zone; + } + + /* + * Non-isolated types over MIGRATE_PCPTYPES get added + * to the MIGRATE_MOVABLE pcp list. + */ + if (unlikely(migratetype >= MIGRATE_PCPTYPES)) + migratetype = MIGRATE_MOVABLE; + + trace_mm_page_free_batched(&folio->page); + if (!free_frozen_page_commit(zone, pcp, &folio->page, + migratetype, order, FPI_NONE, &UP_flags)) { + pcp = NULL; + locked_zone = NULL; + } + } + + if (pcp) + pcp_spin_unlock(pcp, UP_flags); + folio_batch_reinit(folios); } /* @@ -1383,736 +3089,957 @@ void split_page(struct page *page, unsigned int order) { int i; - VM_BUG_ON(PageCompound(page)); - VM_BUG_ON(!page_count(page)); - -#ifdef CONFIG_KMEMCHECK - /* - * Split shadow pages too, because free(page[0]) would - * otherwise free the whole shadow. - */ - if (kmemcheck_page_is_tracked(page)) - split_page(virt_to_page(page[0].shadow), order); -#endif + VM_BUG_ON_PAGE(PageCompound(page), page); + VM_BUG_ON_PAGE(!page_count(page), page); for (i = 1; i < (1 << order); i++) set_page_refcounted(page + i); + split_page_owner(page, order, 0); + pgalloc_tag_split(page_folio(page), order, 0); + split_page_memcg(page, order); } EXPORT_SYMBOL_GPL(split_page); -static int __isolate_free_page(struct page *page, unsigned int order) +int __isolate_free_page(struct page *page, unsigned int 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)) { - /* Obey watermarks as if the page was being allocated */ - watermark = low_wmark_pages(zone) + (1 << order); - if (!zone_watermark_ok(zone, 0, watermark, 0, 0)) + 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 + * watermark, because we already know our high-order page + * exists. + */ + watermark = zone->_watermark[WMARK_MIN] + (1UL << order); + if (!zone_watermark_ok(zone, 0, watermark, 0, ALLOC_CMA)) return 0; - - __mod_zone_freepage_state(zone, -(1UL << order), mt); } - /* Remove page from free list */ - list_del(&page->lru); - zone->free_area[order].nr_free--; - rmv_page_order(page); + del_page_from_free_list(page, zone, order, mt); - /* Set the pageblock if the isolated page is at least a pageblock */ + /* + * Set the pageblock if the isolated page is at least half of a + * pageblock + */ if (order >= pageblock_order - 1) { 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)) - set_pageblock_migratetype(page, - MIGRATE_MOVABLE); + /* + * Only change normal pageblocks (i.e., they can merge + * with others) + */ + if (migratetype_is_mergeable(mt)) + move_freepages_block(zone, page, mt, + MIGRATE_MOVABLE); } } return 1UL << order; } -/* - * Similar to split_page except the page is already free. As this is only - * being used for migration, the migratetype of the block also changes. - * As this is called with interrupts disabled, the caller is responsible - * for calling arch_alloc_page() and kernel_map_page() after interrupts - * are enabled. +/** + * __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 * - * Note: this is probably too low level an operation for use in drivers. - * Please consult with lkml before using this in your driver. + * 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. */ -int split_free_page(struct page *page) +void __putback_isolated_page(struct page *page, unsigned int order, int mt) { - unsigned int order; - int nr_pages; - - order = page_order(page); + struct zone *zone = page_zone(page); - nr_pages = __isolate_free_page(page, order); - if (!nr_pages) - return 0; + /* zone lock should be held when this function is called */ + lockdep_assert_held(&zone->lock); - /* Split into individual pages */ - set_page_refcounted(page); - split_page(page, order); - return nr_pages; + /* 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); } /* - * Really, prep_compound_page() should be called from __rmqueue_bulk(). But - * we cheat by calling it from here, in the order > 0 path. Saves a branch - * or two. + * Update NUMA hit/miss statistics */ -static inline -struct page *buffered_rmqueue(struct zone *preferred_zone, - struct zone *zone, int order, gfp_t gfp_flags, - int migratetype) +static inline void zone_statistics(struct zone *preferred_zone, struct zone *z, + long nr_account) { - unsigned long flags; - struct page *page; - int cold = !!(gfp_flags & __GFP_COLD); +#ifdef CONFIG_NUMA + enum numa_stat_item local_stat = NUMA_LOCAL; -again: - if (likely(order == 0)) { - struct per_cpu_pages *pcp; - struct list_head *list; + /* skip numa counters update if numa stats is disabled */ + if (!static_branch_likely(&vm_numa_stat_key)) + return; - local_irq_save(flags); - pcp = &this_cpu_ptr(zone->pageset)->pcp; - list = &pcp->lists[migratetype]; - if (list_empty(list)) { - pcp->count += rmqueue_bulk(zone, 0, - pcp->batch, list, - migratetype, cold); - if (unlikely(list_empty(list))) - goto failed; + if (zone_to_nid(z) != numa_node_id()) + local_stat = NUMA_OTHER; + + if (zone_to_nid(z) == zone_to_nid(preferred_zone)) + __count_numa_events(z, NUMA_HIT, nr_account); + else { + __count_numa_events(z, NUMA_MISS, nr_account); + __count_numa_events(preferred_zone, NUMA_FOREIGN, nr_account); + } + __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; + if (unlikely(alloc_flags & ALLOC_TRYLOCK)) { + if (!spin_trylock_irqsave(&zone->lock, flags)) + return NULL; + } else { + spin_lock_irqsave(&zone->lock, flags); } + if (alloc_flags & ALLOC_HIGHATOMIC) + page = __rmqueue_smallest(zone, order, MIGRATE_HIGHATOMIC); + if (!page) { + enum rmqueue_mode rmqm = RMQUEUE_NORMAL; - if (cold) - page = list_entry(list->prev, struct page, lru); - else - page = list_entry(list->next, struct page, lru); + page = __rmqueue(zone, order, migratetype, alloc_flags, &rmqm); - list_del(&page->lru); - pcp->count--; - } else { - if (unlikely(gfp_flags & __GFP_NOFAIL)) { /* - * __GFP_NOFAIL is not to be used in new code. - * - * All __GFP_NOFAIL callers should be fixed so that they - * properly detect and handle allocation failures. - * - * We most definitely don't want callers attempting to - * allocate greater than order-1 page units with - * __GFP_NOFAIL. + * If the allocation fails, allow OOM handling and + * order-0 (atomic) allocs access to HIGHATOMIC + * reserves as failing now is worse than failing a + * high-order atomic allocation in the future. */ - WARN_ON_ONCE(order > 1); + if (!page && (alloc_flags & (ALLOC_OOM|ALLOC_NON_BLOCK))) + page = __rmqueue_smallest(zone, order, MIGRATE_HIGHATOMIC); + + if (!page) { + spin_unlock_irqrestore(&zone->lock, flags); + return NULL; + } } - spin_lock_irqsave(&zone->lock, flags); - page = __rmqueue(zone, order, migratetype); - spin_unlock(&zone->lock); - if (!page) - goto failed; - __mod_zone_freepage_state(zone, -(1 << order), - get_pageblock_migratetype(page)); - } + spin_unlock_irqrestore(&zone->lock, flags); + } while (check_new_pages(page, order)); - __count_zone_vm_events(PGALLOC, zone, 1 << order); - zone_statistics(preferred_zone, zone, gfp_flags); - local_irq_restore(flags); + __count_zid_vm_events(PGALLOC, page_zonenum(page), 1 << order); + zone_statistics(preferred_zone, zone, 1); - VM_BUG_ON(bad_range(zone, page)); - if (prep_new_page(page, order, gfp_flags)) - goto again; return page; - -failed: - local_irq_restore(flags); - return NULL; } -#ifdef CONFIG_FAIL_PAGE_ALLOC +static int nr_pcp_alloc(struct per_cpu_pages *pcp, struct zone *zone, int order) +{ + int high, base_batch, batch, max_nr_alloc; + int high_max, high_min; -static struct { - struct fault_attr attr; + base_batch = READ_ONCE(pcp->batch); + high_min = READ_ONCE(pcp->high_min); + high_max = READ_ONCE(pcp->high_max); + high = pcp->high = clamp(pcp->high, high_min, high_max); - u32 ignore_gfp_highmem; - u32 ignore_gfp_wait; - u32 min_order; -} fail_page_alloc = { - .attr = FAULT_ATTR_INITIALIZER, - .ignore_gfp_wait = 1, - .ignore_gfp_highmem = 1, - .min_order = 1, -}; + /* Check for PCP disabled or boot pageset */ + if (unlikely(high < base_batch)) + return 1; -static int __init setup_fail_page_alloc(char *str) -{ - return setup_fault_attr(&fail_page_alloc.attr, str); -} -__setup("fail_page_alloc=", setup_fail_page_alloc); + if (order) + batch = base_batch; + else + batch = (base_batch << pcp->alloc_factor); -static bool should_fail_alloc_page(gfp_t gfp_mask, unsigned int order) -{ - if (order < fail_page_alloc.min_order) - return false; - if (gfp_mask & __GFP_NOFAIL) - return false; - if (fail_page_alloc.ignore_gfp_highmem && (gfp_mask & __GFP_HIGHMEM)) - return false; - if (fail_page_alloc.ignore_gfp_wait && (gfp_mask & __GFP_WAIT)) - return false; + /* + * If we had larger pcp->high, we could avoid to allocate from + * zone. + */ + if (high_min != high_max && !test_bit(ZONE_BELOW_HIGH, &zone->flags)) + high = pcp->high = min(high + batch, high_max); - return should_fail(&fail_page_alloc.attr, 1 << order); -} + if (!order) { + max_nr_alloc = max(high - pcp->count - base_batch, base_batch); + /* + * Double the number of pages allocated each time there is + * subsequent allocation of order-0 pages without any freeing. + */ + if (batch <= max_nr_alloc && + pcp->alloc_factor < CONFIG_PCP_BATCH_SCALE_MAX) + pcp->alloc_factor++; + batch = min(batch, max_nr_alloc); + } -#ifdef CONFIG_FAULT_INJECTION_DEBUG_FS + /* + * 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); -static int __init fail_page_alloc_debugfs(void) + return batch; +} + +/* Remove page from the per-cpu list, caller must protect the list */ +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) { - umode_t mode = S_IFREG | S_IRUSR | S_IWUSR; - struct dentry *dir; + struct page *page; - dir = fault_create_debugfs_attr("fail_page_alloc", NULL, - &fail_page_alloc.attr); - if (IS_ERR(dir)) - return PTR_ERR(dir); + do { + if (list_empty(list)) { + int batch = nr_pcp_alloc(pcp, zone, order); + int alloced; - if (!debugfs_create_bool("ignore-gfp-wait", mode, dir, - &fail_page_alloc.ignore_gfp_wait)) - goto fail; - if (!debugfs_create_bool("ignore-gfp-highmem", mode, dir, - &fail_page_alloc.ignore_gfp_highmem)) - goto fail; - if (!debugfs_create_u32("min-order", mode, dir, - &fail_page_alloc.min_order)) - goto fail; + alloced = rmqueue_bulk(zone, order, + batch, list, + migratetype, alloc_flags); - return 0; -fail: - debugfs_remove_recursive(dir); + pcp->count += alloced << order; + if (unlikely(list_empty(list))) + return NULL; + } - return -ENOMEM; -} + page = list_first_entry(list, struct page, pcp_list); + list_del(&page->pcp_list); + pcp->count -= 1 << order; + } while (check_new_pages(page, order)); -late_initcall(fail_page_alloc_debugfs); + return page; +} -#endif /* CONFIG_FAULT_INJECTION_DEBUG_FS */ +/* Lock and remove page from the per-cpu list */ +static struct page *rmqueue_pcplist(struct zone *preferred_zone, + 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 UP_flags; -#else /* CONFIG_FAIL_PAGE_ALLOC */ + /* spin_trylock may fail due to a parallel drain or IRQ reentrancy. */ + pcp = pcp_spin_trylock(zone->per_cpu_pageset, UP_flags); + if (!pcp) + return NULL; -static inline bool should_fail_alloc_page(gfp_t gfp_mask, unsigned int order) -{ - return false; + /* + * 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_count >>= 1; + list = &pcp->lists[order_to_pindex(migratetype, order)]; + page = __rmqueue_pcplist(zone, order, migratetype, alloc_flags, pcp, list); + pcp_spin_unlock(pcp, UP_flags); + if (page) { + __count_zid_vm_events(PGALLOC, page_zonenum(page), 1 << order); + zone_statistics(preferred_zone, zone, 1); + } + return page; } -#endif /* CONFIG_FAIL_PAGE_ALLOC */ +/* + * Allocate a page from the given zone. + * Use pcplists for THP or "cheap" high-order allocations. + */ /* - * Return true if free pages are above 'mark'. This takes into account the order - * of the allocation. + * Do not instrument rmqueue() with KMSAN. This function may call + * __msan_poison_alloca() through a call to set_pfnblock_migratetype(). + * If __msan_poison_alloca() attempts to allocate pages for the stack depot, it + * may call rmqueue() again, which will result in a deadlock. */ -static bool __zone_watermark_ok(struct zone *z, int order, unsigned long mark, - int classzone_idx, int alloc_flags, long free_pages) +__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) { - /* free_pages my go negative - that's OK */ - long min = mark; - long lowmem_reserve = z->lowmem_reserve[classzone_idx]; - int o; - long free_cma = 0; - - free_pages -= (1 << order) - 1; - if (alloc_flags & ALLOC_HIGH) - min -= min / 2; - if (alloc_flags & ALLOC_HARDER) - 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_cma = zone_page_state(z, NR_FREE_CMA_PAGES); -#endif + struct page *page; - if (free_pages - free_cma <= min + lowmem_reserve) - return false; - for (o = 0; o < order; o++) { - /* At the next order, this order's pages become unavailable */ - free_pages -= z->free_area[o].nr_free << o; + if (likely(pcp_allowed_order(order))) { + page = rmqueue_pcplist(preferred_zone, zone, order, + migratetype, alloc_flags); + if (likely(page)) + goto out; + } - /* Require fewer higher order pages to be free */ - min >>= 1; + page = rmqueue_buddy(preferred_zone, zone, order, alloc_flags, + migratetype); - if (free_pages <= min) - return false; +out: + /* Separate test+clear to avoid unnecessary atomics */ + if ((alloc_flags & ALLOC_KSWAPD) && + unlikely(test_bit(ZONE_BOOSTED_WATERMARK, &zone->flags))) { + clear_bit(ZONE_BOOSTED_WATERMARK, &zone->flags); + wakeup_kswapd(zone, 0, 0, zone_idx(zone)); } - return true; -} -bool zone_watermark_ok(struct zone *z, int order, unsigned long mark, - int classzone_idx, int alloc_flags) -{ - return __zone_watermark_ok(z, order, mark, classzone_idx, alloc_flags, - zone_page_state(z, NR_FREE_PAGES)); + VM_BUG_ON_PAGE(page && bad_range(zone, page), page); + return page; } -bool zone_watermark_ok_safe(struct zone *z, int order, unsigned long mark, - int classzone_idx, int alloc_flags) +/* + * Reserve the pageblock(s) surrounding an allocation request for + * exclusive use of high-order atomic allocations if there are no + * empty page blocks that contain a page with a suitable order + */ +static void reserve_highatomic_pageblock(struct page *page, int order, + struct zone *zone) { - long free_pages = zone_page_state(z, NR_FREE_PAGES); + int mt; + unsigned long max_managed, flags; + + /* + * The number reserved as: minimum is 1 pageblock, maximum is + * roughly 1% of a zone. But if 1% of a zone falls below a + * pageblock size, then don't reserve any pageblocks. + * Check is race-prone but harmless. + */ + if ((zone_managed_pages(zone) / 100) < pageblock_nr_pages) + return; + max_managed = ALIGN((zone_managed_pages(zone) / 100), pageblock_nr_pages); + if (zone->nr_reserved_highatomic >= max_managed) + return; + + spin_lock_irqsave(&zone->lock, flags); + + /* Recheck the nr_reserved_highatomic limit under the lock */ + if (zone->nr_reserved_highatomic >= max_managed) + goto out_unlock; - if (z->percpu_drift_mark && free_pages < z->percpu_drift_mark) - free_pages = zone_page_state_snapshot(z, NR_FREE_PAGES); + /* Yoink! */ + mt = get_pageblock_migratetype(page); + /* Only reserve normal pageblocks (i.e., they can merge with others) */ + if (!migratetype_is_mergeable(mt)) + goto out_unlock; + + if (order < pageblock_order) { + if (move_freepages_block(zone, page, mt, MIGRATE_HIGHATOMIC) == -1) + goto out_unlock; + zone->nr_reserved_highatomic += pageblock_nr_pages; + } else { + change_pageblock_range(page, order, MIGRATE_HIGHATOMIC); + zone->nr_reserved_highatomic += 1 << order; + } - return __zone_watermark_ok(z, order, mark, classzone_idx, alloc_flags, - free_pages); +out_unlock: + spin_unlock_irqrestore(&zone->lock, flags); } -#ifdef CONFIG_NUMA /* - * zlc_setup - Setup for "zonelist cache". Uses cached zone data to - * skip over zones that are not allowed by the cpuset, or that have - * been recently (in last second) found to be nearly full. See further - * comments in mmzone.h. Reduces cache footprint of zonelist scans - * that have to skip over a lot of full or unallowed zones. - * - * If the zonelist cache is present in the passed in zonelist, then - * returns a pointer to the allowed node mask (either the current - * tasks mems_allowed, or node_states[N_MEMORY].) - * - * If the zonelist cache is not available for this zonelist, does - * nothing and returns NULL. + * Used when an allocation is about to fail under memory pressure. This + * potentially hurts the reliability of high-order allocations when under + * intense memory pressure but failed atomic allocations should be easier + * to recover from than an OOM. * - * If the fullzones BITMAP in the zonelist cache is stale (more than - * a second since last zap'd) then we zap it out (clear its bits.) - * - * We hold off even calling zlc_setup, until after we've checked the - * first zone in the zonelist, on the theory that most allocations will - * be satisfied from that first zone, so best to examine that zone as - * quickly as we can. + * If @force is true, try to unreserve pageblocks even though highatomic + * pageblock is exhausted. */ -static nodemask_t *zlc_setup(struct zonelist *zonelist, int alloc_flags) +static bool unreserve_highatomic_pageblock(const struct alloc_context *ac, + bool force) { - struct zonelist_cache *zlc; /* cached zonelist speedup info */ - nodemask_t *allowednodes; /* zonelist_cache approximation */ + struct zonelist *zonelist = ac->zonelist; + unsigned long flags; + struct zoneref *z; + struct zone *zone; + struct page *page; + int order; + int ret; - zlc = zonelist->zlcache_ptr; - if (!zlc) - return NULL; + for_each_zone_zonelist_nodemask(zone, z, zonelist, ac->highest_zoneidx, + ac->nodemask) { + /* + * Preserve at least one pageblock unless memory pressure + * is really high. + */ + if (!force && zone->nr_reserved_highatomic <= + pageblock_nr_pages) + continue; + + spin_lock_irqsave(&zone->lock, flags); + for (order = 0; order < NR_PAGE_ORDERS; order++) { + struct free_area *area = &(zone->free_area[order]); + unsigned long size; + + page = get_page_from_free_area(area, MIGRATE_HIGHATOMIC); + if (!page) + continue; + + size = max(pageblock_nr_pages, 1UL << order); + /* + * It should never happen but changes to + * locking could inadvertently allow a per-cpu + * drain to add pages to MIGRATE_HIGHATOMIC + * while unreserving so be safe and watch for + * underflows. + */ + if (WARN_ON_ONCE(size > zone->nr_reserved_highatomic)) + size = zone->nr_reserved_highatomic; + zone->nr_reserved_highatomic -= size; - if (time_after(jiffies, zlc->last_full_zap + HZ)) { - bitmap_zero(zlc->fullzones, MAX_ZONES_PER_ZONELIST); - zlc->last_full_zap = jiffies; + /* + * Convert to ac->migratetype and avoid the normal + * pageblock stealing heuristics. Minimally, the caller + * is doing the work and needs the pages. More + * importantly, if the block was always converted to + * MIGRATE_UNMOVABLE or another type then the number + * of pageblocks that cannot be completely freed + * may increase. + */ + if (order < pageblock_order) + ret = move_freepages_block(zone, page, + MIGRATE_HIGHATOMIC, + ac->migratetype); + else { + move_to_free_list(page, zone, order, + MIGRATE_HIGHATOMIC, + ac->migratetype); + change_pageblock_range(page, order, + ac->migratetype); + ret = 1; + } + /* + * Reserving the block(s) already succeeded, + * so this should not fail on zone boundaries. + */ + WARN_ON_ONCE(ret == -1); + if (ret > 0) { + spin_unlock_irqrestore(&zone->lock, flags); + return ret; + } + } + spin_unlock_irqrestore(&zone->lock, flags); } - allowednodes = !in_interrupt() && (alloc_flags & ALLOC_CPUSET) ? - &cpuset_current_mems_allowed : - &node_states[N_MEMORY]; - return allowednodes; + return false; } -/* - * Given 'z' scanning a zonelist, run a couple of quick checks to see - * if it is worth looking at further for free memory: - * 1) Check that the zone isn't thought to be full (doesn't have its - * bit set in the zonelist_cache fullzones BITMAP). - * 2) Check that the zones node (obtained from the zonelist_cache - * z_to_n[] mapping) is allowed in the passed in allowednodes mask. - * Return true (non-zero) if zone is worth looking at further, or - * else return false (zero) if it is not. - * - * This check -ignores- the distinction between various watermarks, - * such as GFP_HIGH, GFP_ATOMIC, PF_MEMALLOC, ... If a zone is - * found to be full for any variation of these watermarks, it will - * be considered full for up to one second by all requests, unless - * we are so low on memory on all allowed nodes that we are forced - * into the second scan of the zonelist. - * - * In the second scan we ignore this zonelist cache and exactly - * apply the watermarks to all zones, even it is slower to do so. - * We are low on memory in the second scan, and should leave no stone - * unturned looking for a free page. - */ -static int zlc_zone_worth_trying(struct zonelist *zonelist, struct zoneref *z, - nodemask_t *allowednodes) +static inline long __zone_watermark_unusable_free(struct zone *z, + unsigned int order, unsigned int alloc_flags) { - struct zonelist_cache *zlc; /* cached zonelist speedup info */ - int i; /* index of *z in zonelist zones */ - int n; /* node that zone *z is on */ + long unusable_free = (1 << order) - 1; - zlc = zonelist->zlcache_ptr; - if (!zlc) - return 1; + /* + * If the caller does not have rights to reserves below the min + * watermark then subtract the free pages reserved for highatomic. + */ + if (likely(!(alloc_flags & ALLOC_RESERVES))) + unusable_free += READ_ONCE(z->nr_free_highatomic); - i = z - zonelist->_zonerefs; - n = zlc->z_to_n[i]; +#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 - /* This zone is worth trying if it is allowed but not full */ - return node_isset(n, *allowednodes) && !test_bit(i, zlc->fullzones); + return unusable_free; } /* - * Given 'z' scanning a zonelist, set the corresponding bit in - * zlc->fullzones, so that subsequent attempts to allocate a page - * from that zone don't waste time re-examining it. + * 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 + * one free page of a suitable size. Checking now avoids taking the zone lock + * to check in the allocation paths if no pages are free. */ -static void zlc_mark_zone_full(struct zonelist *zonelist, struct zoneref *z) +bool __zone_watermark_ok(struct zone *z, unsigned int order, unsigned long mark, + int highest_zoneidx, unsigned int alloc_flags, + long free_pages) { - struct zonelist_cache *zlc; /* cached zonelist speedup info */ - int i; /* index of *z in zonelist zones */ + long min = mark; + int o; - zlc = zonelist->zlcache_ptr; - if (!zlc) - return; + /* free_pages may go negative - that's OK */ + free_pages -= __zone_watermark_unusable_free(z, order, alloc_flags); - i = z - zonelist->_zonerefs; + if (unlikely(alloc_flags & ALLOC_RESERVES)) { + /* + * __GFP_HIGH allows access to 50% of the min reserve as well + * as OOM. + */ + if (alloc_flags & ALLOC_MIN_RESERVE) { + min -= min / 2; - set_bit(i, zlc->fullzones); -} + /* + * Non-blocking allocations (e.g. GFP_ATOMIC) can + * access more reserves than just __GFP_HIGH. Other + * non-blocking allocations requests such as GFP_NOWAIT + * or (GFP_KERNEL & ~__GFP_DIRECT_RECLAIM) do not get + * access to the min reserve. + */ + if (alloc_flags & ALLOC_NON_BLOCK) + min -= min / 4; + } -/* - * clear all zones full, called after direct reclaim makes progress so that - * a zone that was recently full is not skipped over for up to a second - */ -static void zlc_clear_zones_full(struct zonelist *zonelist) -{ - struct zonelist_cache *zlc; /* cached zonelist speedup info */ + /* + * OOM victims can try even harder than the normal reserve + * users on the grounds that it's definitely going to be in + * the exit path shortly and free memory. Any allocation it + * makes during the free path will be small and short-lived. + */ + if (alloc_flags & ALLOC_OOM) + min -= min / 2; + } - zlc = zonelist->zlcache_ptr; - if (!zlc) - return; + /* + * 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[highest_zoneidx]) + return false; - bitmap_zero(zlc->fullzones, MAX_ZONES_PER_ZONELIST); + /* If this is an order-0 request then the watermark is fine */ + if (!order) + return true; + + /* For a high-order request, check at least one suitable page is free */ + for (o = order; o < NR_PAGE_ORDERS; o++) { + struct free_area *area = &z->free_area[o]; + int mt; + + if (!area->nr_free) + continue; + + for (mt = 0; mt < MIGRATE_PCPTYPES; mt++) { + if (!free_area_empty(area, mt)) + return true; + } + +#ifdef CONFIG_CMA + if ((alloc_flags & ALLOC_CMA) && + !free_area_empty(area, MIGRATE_CMA)) { + return true; + } +#endif + if ((alloc_flags & (ALLOC_HIGHATOMIC|ALLOC_OOM)) && + !free_area_empty(area, MIGRATE_HIGHATOMIC)) { + return true; + } + } + return false; } -static bool zone_allows_reclaim(struct zone *local_zone, struct zone *zone) +bool zone_watermark_ok(struct zone *z, unsigned int order, unsigned long mark, + int highest_zoneidx, unsigned int alloc_flags) { - return node_isset(local_zone->node, zone->zone_pgdat->reclaim_nodes); + return __zone_watermark_ok(z, order, mark, highest_zoneidx, alloc_flags, + zone_page_state(z, NR_FREE_PAGES)); } -static void __paginginit init_zone_allows_reclaim(int nid) +static inline bool zone_watermark_fast(struct zone *z, unsigned int order, + unsigned long mark, int highest_zoneidx, + unsigned int alloc_flags, gfp_t gfp_mask) { - int i; + long free_pages; - for_each_online_node(i) - if (node_distance(nid, i) <= RECLAIM_DISTANCE) - node_set(i, NODE_DATA(nid)->reclaim_nodes); - else - zone_reclaim_mode = 1; -} + free_pages = zone_page_state(z, NR_FREE_PAGES); -#else /* CONFIG_NUMA */ + /* + * Fast check for order-0 only. If this fails then the reserves + * need to be calculated. + */ + if (!order) { + long usable_free; + long reserved; -static nodemask_t *zlc_setup(struct zonelist *zonelist, int alloc_flags) -{ - return NULL; -} + usable_free = free_pages; + reserved = __zone_watermark_unusable_free(z, 0, alloc_flags); -static int zlc_zone_worth_trying(struct zonelist *zonelist, struct zoneref *z, - nodemask_t *allowednodes) -{ - return 1; -} + /* reserved may over estimate high-atomic reserves. */ + usable_free -= min(usable_free, reserved); + if (usable_free > mark + z->lowmem_reserve[highest_zoneidx]) + return true; + } -static void zlc_mark_zone_full(struct zonelist *zonelist, struct zoneref *z) -{ + if (__zone_watermark_ok(z, order, mark, highest_zoneidx, alloc_flags, + free_pages)) + return true; + + /* + * Ignore watermark boosting for __GFP_HIGH 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 && (alloc_flags & ALLOC_MIN_RESERVE) && 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 false; } -static void zlc_clear_zones_full(struct zonelist *zonelist) +#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)) <= + node_reclaim_distance; } - +#else /* CONFIG_NUMA */ static bool zone_allows_reclaim(struct zone *local_zone, struct zone *zone) { return true; } +#endif /* CONFIG_NUMA */ -static inline void init_zone_allows_reclaim(int nid) +/* + * The restriction on ZONE_DMA32 as being a suitable zone to use to avoid + * fragmentation is subtle. If the preferred zone was HIGHMEM then + * premature use of a lower zone may cause lowmem pressure problems that + * are worse than fragmentation. If the next zone is ZONE_DMA then it is + * probably too small. It only makes sense to spread allocations to avoid + * fragmentation between the Normal and DMA32 zones. + */ +static inline unsigned int +alloc_flags_nofragment(struct zone *zone, gfp_t gfp_mask) { + unsigned int alloc_flags; + + /* + * __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); + + if (defrag_mode) { + alloc_flags |= ALLOC_NOFRAGMENT; + return alloc_flags; + } + +#ifdef CONFIG_ZONE_DMA32 + if (!zone) + return alloc_flags; + + if (zone_idx(zone) != ZONE_NORMAL) + return alloc_flags; + + /* + * If ZONE_DMA32 exists, assume it is the one after ZONE_NORMAL and + * the pointer is within zone->zone_pgdat->node_zones[]. Also assume + * on UMA that if Normal is populated then so is DMA32. + */ + BUILD_BUG_ON(ZONE_NORMAL - ZONE_DMA32 != 1); + if (nr_online_nodes > 1 && !populated_zone(--zone)) + return alloc_flags; + + alloc_flags |= ALLOC_NOFRAGMENT; +#endif /* CONFIG_ZONE_DMA32 */ + 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; } -#endif /* CONFIG_NUMA */ /* * get_page_from_freelist goes through the zonelist trying to allocate * a page. */ static struct page * -get_page_from_freelist(gfp_t gfp_mask, nodemask_t *nodemask, unsigned int order, - struct zonelist *zonelist, int high_zoneidx, int alloc_flags, - struct zone *preferred_zone, int migratetype) +get_page_from_freelist(gfp_t gfp_mask, unsigned int order, int alloc_flags, + const struct alloc_context *ac) { struct zoneref *z; - struct page *page = NULL; - int classzone_idx; struct zone *zone; - nodemask_t *allowednodes = NULL;/* zonelist_cache approximation */ - int zlc_active = 0; /* set if using zonelist_cache */ - int did_zlc_setup = 0; /* just call zlc_setup() one time */ + struct pglist_data *last_pgdat = NULL; + bool last_pgdat_dirty_ok = false; + bool no_fallback; + bool skip_kswapd_nodes = nr_online_nodes > 1; + bool skipped_kswapd_nodes = false; - classzone_idx = zone_idx(preferred_zone); -zonelist_scan: +retry: /* * Scan zonelist, looking for a zone with enough free. - * See also cpuset_zone_allowed() comment in kernel/cpuset.c. + * See also cpuset_current_node_allowed() comment in kernel/cgroup/cpuset.c. */ - for_each_zone_zonelist_nodemask(zone, z, zonelist, - high_zoneidx, nodemask) { - if (IS_ENABLED(CONFIG_NUMA) && zlc_active && - !zlc_zone_worth_trying(zonelist, z, allowednodes)) - continue; - if ((alloc_flags & ALLOC_CPUSET) && - !cpuset_zone_allowed_softwall(zone, gfp_mask)) + no_fallback = alloc_flags & ALLOC_NOFRAGMENT; + z = ac->preferred_zoneref; + for_next_zone_zonelist_nodemask(zone, z, ac->highest_zoneidx, + ac->nodemask) { + struct page *page; + unsigned long mark; + + if (cpusets_enabled() && + (alloc_flags & ALLOC_CPUSET) && + !__cpuset_zone_allowed(zone, gfp_mask)) continue; /* * When allocating a page cache page for writing, we - * want to get it from a zone that is within its dirty - * limit, such that no single zone holds more than its + * want to get it from a node that is within its dirty + * limit, such that no single node holds more than its * proportional share of globally allowed dirty pages. - * The dirty limits take into account the zone's + * The dirty limits take into account the node's * lowmem reserves and high watermark so that kswapd * should be able to balance it without having to * write pages from its LRU list. * - * This may look like it could increase pressure on - * lower zones by failing allocations in higher zones - * before they are full. But the pages that do spill - * over are limited as the lower zones are protected - * by this very same mechanism. It should not become - * a practical burden to them. - * * XXX: For now, allow allocations to potentially - * exceed the per-zone dirty limit in the slowpath - * (ALLOC_WMARK_LOW unset) before going into reclaim, + * exceed the per-node dirty limit in the slowpath + * (spread_dirty_pages unset) before going into reclaim, * which is important when on a NUMA setup the allowed - * zones are together not big enough to reach the + * nodes are together not big enough to reach the * global limit. The proper fix for these situations - * will require awareness of zones in the + * will require awareness of nodes in the * dirty-throttling and the flusher threads. */ - if ((alloc_flags & ALLOC_WMARK_LOW) && - (gfp_mask & __GFP_WRITE) && !zone_dirty_ok(zone)) - goto this_zone_full; + if (ac->spread_dirty_pages) { + if (last_pgdat != zone->zone_pgdat) { + last_pgdat = zone->zone_pgdat; + last_pgdat_dirty_ok = node_dirty_ok(zone->zone_pgdat); + } - BUILD_BUG_ON(ALLOC_NO_WATERMARKS < NR_WMARK); - if (!(alloc_flags & ALLOC_NO_WATERMARKS)) { - unsigned long mark; - int ret; + if (!last_pgdat_dirty_ok) + continue; + } - mark = zone->watermark[alloc_flags & ALLOC_WMARK_MASK]; - if (zone_watermark_ok(zone, order, mark, - classzone_idx, alloc_flags)) - goto try_this_zone; + if (no_fallback && !defrag_mode && nr_online_nodes > 1 && + zone != zonelist_zone(ac->preferred_zoneref)) { + int local_nid; - if (IS_ENABLED(CONFIG_NUMA) && - !did_zlc_setup && nr_online_nodes > 1) { - /* - * we do zlc_setup if there are multiple nodes - * and before considering the first zone allowed - * by the cpuset. - */ - allowednodes = zlc_setup(zonelist, alloc_flags); - zlc_active = 1; - did_zlc_setup = 1; + /* + * If moving to a remote node, retry but allow + * fragmenting fallbacks. Locality is more important + * than fragmentation avoidance. + */ + local_nid = zonelist_node_idx(ac->preferred_zoneref); + if (zone_to_nid(zone) != local_nid) { + alloc_flags &= ~ALLOC_NOFRAGMENT; + goto retry; } + } - if (zone_reclaim_mode == 0 || - !zone_allows_reclaim(preferred_zone, zone)) - goto this_zone_full; + /* + * If kswapd is already active on a node, keep looking + * for other nodes that might be idle. This can happen + * if another process has NUMA bindings and is causing + * kswapd wakeups on only some nodes. Avoid accidental + * "node_reclaim_mode"-like behavior in this case. + */ + if (skip_kswapd_nodes && + !waitqueue_active(&zone->zone_pgdat->kswapd_wait)) { + skipped_kswapd_nodes = true; + continue; + } + + cond_accept_memory(zone, order, alloc_flags); + + /* + * Detect whether the number of free pages is below high + * watermark. If so, we will decrease pcp->high and free + * PCP pages in free path to reduce the possibility of + * premature page reclaiming. Detection is done here to + * avoid to do that in hotter free path. + */ + if (test_bit(ZONE_BELOW_HIGH, &zone->flags)) + goto check_alloc_wmark; + + mark = high_wmark_pages(zone); + if (zone_watermark_fast(zone, order, mark, + ac->highest_zoneidx, alloc_flags, + gfp_mask)) + goto try_this_zone; + else + set_bit(ZONE_BELOW_HIGH, &zone->flags); + +check_alloc_wmark: + mark = wmark_pages(zone, alloc_flags & ALLOC_WMARK_MASK); + if (!zone_watermark_fast(zone, order, mark, + ac->highest_zoneidx, alloc_flags, + gfp_mask)) { + int ret; + + if (cond_accept_memory(zone, order, alloc_flags)) + goto try_this_zone; /* - * As we may have just activated ZLC, check if the first - * eligible zone has failed zone_reclaim recently. + * Watermark failed for this zone, but see if we can + * grow this zone if it contains deferred pages. */ - if (IS_ENABLED(CONFIG_NUMA) && zlc_active && - !zlc_zone_worth_trying(zonelist, z, allowednodes)) + if (deferred_pages_enabled()) { + if (_deferred_grow_zone(zone, order)) + goto try_this_zone; + } + /* Checked here to keep the fast path fast */ + BUILD_BUG_ON(ALLOC_NO_WATERMARKS < NR_WMARK); + if (alloc_flags & ALLOC_NO_WATERMARKS) + goto try_this_zone; + + if (!node_reclaim_enabled() || + !zone_allows_reclaim(zonelist_zone(ac->preferred_zoneref), zone)) continue; - ret = zone_reclaim(zone, gfp_mask, order); + ret = node_reclaim(zone->zone_pgdat, gfp_mask, order); switch (ret) { - case ZONE_RECLAIM_NOSCAN: + case NODE_RECLAIM_NOSCAN: /* did not scan */ continue; - case ZONE_RECLAIM_FULL: + case NODE_RECLAIM_FULL: /* scanned but unreclaimable */ continue; default: /* did we reclaim enough */ if (zone_watermark_ok(zone, order, mark, - classzone_idx, alloc_flags)) + ac->highest_zoneidx, alloc_flags)) goto try_this_zone; - /* - * Failed to reclaim enough to meet watermark. - * Only mark the zone full if checking the min - * watermark or if we failed to reclaim just - * 1<<order pages or else the page allocator - * fastpath will prematurely mark zones full - * when the watermark is between the low and - * min watermarks. - */ - if (((alloc_flags & ALLOC_WMARK_MASK) == ALLOC_WMARK_MIN) || - ret == ZONE_RECLAIM_SOME) - goto this_zone_full; - continue; } } try_this_zone: - page = buffered_rmqueue(preferred_zone, zone, order, - gfp_mask, migratetype); - if (page) - break; -this_zone_full: - if (IS_ENABLED(CONFIG_NUMA)) - zlc_mark_zone_full(zonelist, z); - } + page = rmqueue(zonelist_zone(ac->preferred_zoneref), zone, order, + gfp_mask, alloc_flags, ac->migratetype); + if (page) { + prep_new_page(page, order, gfp_mask, alloc_flags); - if (unlikely(IS_ENABLED(CONFIG_NUMA) && page == NULL && zlc_active)) { - /* Disable zlc cache for second zonelist scan */ - zlc_active = 0; - goto zonelist_scan; - } + /* + * If this is a high-order atomic allocation then check + * if the pageblock should be reserved for the future + */ + if (unlikely(alloc_flags & ALLOC_HIGHATOMIC)) + reserve_highatomic_pageblock(page, order, zone); - if (page) - /* - * page->pfmemalloc is set when ALLOC_NO_WATERMARKS was - * necessary to allocate the page. The expectation is - * that the caller is taking steps that will free more - * memory. The caller should avoid the page being used - * for !PFMEMALLOC purposes. - */ - page->pfmemalloc = !!(alloc_flags & ALLOC_NO_WATERMARKS); + return page; + } else { + if (cond_accept_memory(zone, order, alloc_flags)) + goto try_this_zone; - return page; -} + /* Try again if zone has deferred pages */ + if (deferred_pages_enabled()) { + if (_deferred_grow_zone(zone, order)) + goto try_this_zone; + } + } + } -/* - * Large machines with many possible nodes should not always dump per-node - * meminfo in irq context. - */ -static inline bool should_suppress_show_mem(void) -{ - bool ret = false; + /* + * If we skipped over nodes with active kswapds and found no + * idle nodes, retry and place anywhere the watermarks permit. + */ + if (skip_kswapd_nodes && skipped_kswapd_nodes) { + skip_kswapd_nodes = false; + goto retry; + } -#if NODES_SHIFT > 8 - ret = in_interrupt(); -#endif - return ret; -} + /* + * It's possible on a UMA machine to get through all zones that are + * fragmented. If avoiding fragmentation, reset and try again. + */ + if (no_fallback && !defrag_mode) { + alloc_flags &= ~ALLOC_NOFRAGMENT; + goto retry; + } -static DEFINE_RATELIMIT_STATE(nopage_rs, - DEFAULT_RATELIMIT_INTERVAL, - DEFAULT_RATELIMIT_BURST); + return NULL; +} -void warn_alloc_failed(gfp_t gfp_mask, int order, const char *fmt, ...) +static void warn_alloc_show_mem(gfp_t gfp_mask, nodemask_t *nodemask) { unsigned int filter = SHOW_MEM_FILTER_NODES; - if ((gfp_mask & __GFP_NOWARN) || !__ratelimit(&nopage_rs) || - debug_guardpage_minorder() > 0) - return; - - /* - * Walking all memory to count page types is very expensive and should - * be inhibited in non-blockable contexts. - */ - if (!(gfp_mask & __GFP_WAIT)) - filter |= SHOW_MEM_FILTER_PAGE_COUNT; - /* * This documents exceptions given to allocations in certain * contexts that are allowed to allocate outside current's set * of allowed nodes. */ if (!(gfp_mask & __GFP_NOMEMALLOC)) - if (test_thread_flag(TIF_MEMDIE) || + if (tsk_is_oom_victim(current) || (current->flags & (PF_MEMALLOC | PF_EXITING))) filter &= ~SHOW_MEM_FILTER_NODES; - if (in_interrupt() || !(gfp_mask & __GFP_WAIT)) + if (!in_task() || !(gfp_mask & __GFP_DIRECT_RECLAIM)) filter &= ~SHOW_MEM_FILTER_NODES; - if (fmt) { - struct va_format vaf; - va_list args; - - va_start(args, fmt); - - vaf.fmt = fmt; - vaf.va = &args; + __show_mem(filter, nodemask, gfp_zone(gfp_mask)); + mem_cgroup_show_protected_memory(NULL); +} - pr_warn("%pV", &vaf); +void warn_alloc(gfp_t gfp_mask, nodemask_t *nodemask, const char *fmt, ...) +{ + struct va_format vaf; + va_list args; + static DEFINE_RATELIMIT_STATE(nopage_rs, 10*HZ, 1); - va_end(args); - } + if ((gfp_mask & __GFP_NOWARN) || + !__ratelimit(&nopage_rs) || + ((gfp_mask & __GFP_DMA) && !has_managed_dma())) + return; - pr_warn("%s: page allocation failure: order:%d, mode:0x%x\n", - current->comm, order, gfp_mask); + va_start(args, fmt); + vaf.fmt = fmt; + vaf.va = &args; + pr_warn("%s: %pV, mode:%#x(%pGg), nodemask=%*pbl", + current->comm, &vaf, gfp_mask, &gfp_mask, + nodemask_pr_args(nodemask)); + va_end(args); + cpuset_print_current_mems_allowed(); + pr_cont("\n"); dump_stack(); - if (!should_suppress_show_mem()) - show_mem(filter); + warn_alloc_show_mem(gfp_mask, nodemask); } -static inline int -should_alloc_retry(gfp_t gfp_mask, unsigned int order, - unsigned long did_some_progress, - unsigned long pages_reclaimed) +static inline struct page * +__alloc_pages_cpuset_fallback(gfp_t gfp_mask, unsigned int order, + unsigned int alloc_flags, + const struct alloc_context *ac) { - /* Do not loop if specifically requested */ - if (gfp_mask & __GFP_NORETRY) - return 0; - - /* Always retry if specifically requested */ - if (gfp_mask & __GFP_NOFAIL) - return 1; - - /* - * Suspend converts GFP_KERNEL to __GFP_WAIT which can prevent reclaim - * making forward progress without invoking OOM. Suspend also disables - * storage devices so kswapd will not help. Bail if we are suspending. - */ - if (!did_some_progress && pm_suspended_storage()) - return 0; - - /* - * In this implementation, order <= PAGE_ALLOC_COSTLY_ORDER - * means __GFP_NOFAIL, but that may not be true in other - * implementations. - */ - if (order <= PAGE_ALLOC_COSTLY_ORDER) - return 1; + struct page *page; + page = get_page_from_freelist(gfp_mask, order, + alloc_flags|ALLOC_CPUSET, ac); /* - * For order > PAGE_ALLOC_COSTLY_ORDER, if __GFP_REPEAT is - * specified, then we retry until we no longer reclaim any pages - * (above), or we've reclaimed an order of pages at least as - * large as the allocation's order. In both cases, if the - * allocation still fails, we stop retrying. + * fallback to ignore cpuset restriction if our nodes + * are depleted */ - if (gfp_mask & __GFP_REPEAT && pages_reclaimed < (1 << order)) - return 1; - - return 0; + if (!page) + page = get_page_from_freelist(gfp_mask, order, + alloc_flags, ac); + return page; } static inline struct page * __alloc_pages_may_oom(gfp_t gfp_mask, unsigned int order, - struct zonelist *zonelist, enum zone_type high_zoneidx, - nodemask_t *nodemask, struct zone *preferred_zone, - int migratetype) -{ + const struct alloc_context *ac, unsigned long *did_some_progress) +{ + struct oom_control oc = { + .zonelist = ac->zonelist, + .nodemask = ac->nodemask, + .memcg = NULL, + .gfp_mask = gfp_mask, + .order = order, + }; struct page *page; - /* Acquire the OOM killer lock for the zones in zonelist */ - if (!try_set_zonelist_oom(zonelist, gfp_mask)) { + *did_some_progress = 0; + + /* + * Acquire the oom lock. If that fails, somebody else is + * making progress for us. + */ + if (!mutex_trylock(&oom_lock)) { + *did_some_progress = 1; schedule_timeout_uninterruptible(1); return NULL; } @@ -2120,139 +4047,338 @@ __alloc_pages_may_oom(gfp_t gfp_mask, unsigned int order, /* * Go through the zonelist yet one more time, keep very high watermark * here, this is only to catch a parallel oom killing, we must fail if - * we're still under heavy pressure. + * we're still under heavy pressure. But make sure that this reclaim + * attempt shall not depend on __GFP_DIRECT_RECLAIM && !__GFP_NORETRY + * allocation which will never fail due to oom_lock already held. */ - page = get_page_from_freelist(gfp_mask|__GFP_HARDWALL, nodemask, - order, zonelist, high_zoneidx, - ALLOC_WMARK_HIGH|ALLOC_CPUSET, - preferred_zone, migratetype); + page = get_page_from_freelist((gfp_mask | __GFP_HARDWALL) & + ~__GFP_DIRECT_RECLAIM, order, + ALLOC_WMARK_HIGH|ALLOC_CPUSET, ac); if (page) goto out; - if (!(gfp_mask & __GFP_NOFAIL)) { - /* The OOM killer will not help higher order allocs */ - if (order > PAGE_ALLOC_COSTLY_ORDER) - goto out; - /* The OOM killer does not needlessly kill tasks for lowmem */ - if (high_zoneidx < ZONE_NORMAL) - goto out; + /* Coredumps can quickly deplete all memory reserves */ + if (current->flags & PF_DUMPCORE) + goto out; + /* The OOM killer will not help higher order allocs */ + if (order > PAGE_ALLOC_COSTLY_ORDER) + goto out; + /* + * We have already exhausted all our reclaim opportunities without any + * 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 | __GFP_THISNODE)) + goto out; + /* The OOM killer does not needlessly kill tasks for lowmem */ + if (ac->highest_zoneidx < ZONE_NORMAL) + goto out; + if (pm_suspended_storage()) + goto out; + /* + * XXX: GFP_NOFS allocations should rather fail than rely on + * other request to make a forward progress. + * We are in an unfortunate situation where out_of_memory cannot + * do much for this context but let's try it to at least get + * access to memory reserved if the current task is killed (see + * out_of_memory). Once filesystems are ready to handle allocation + * failures more gracefully we should just bail out here. + */ + + /* Exhausted what can be done so it's blame time */ + if (out_of_memory(&oc) || + WARN_ON_ONCE_GFP(gfp_mask & __GFP_NOFAIL, gfp_mask)) { + *did_some_progress = 1; + /* - * GFP_THISNODE contains __GFP_NORETRY and we never hit this. - * Sanity check for bare calls of __GFP_THISNODE, not real OOM. - * The caller should handle page allocation failure by itself if - * it specifies __GFP_THISNODE. - * Note: Hugepage uses it but will hit PAGE_ALLOC_COSTLY_ORDER. + * Help non-failing allocations by giving them access to memory + * reserves */ - if (gfp_mask & __GFP_THISNODE) - goto out; + if (gfp_mask & __GFP_NOFAIL) + page = __alloc_pages_cpuset_fallback(gfp_mask, order, + ALLOC_NO_WATERMARKS, ac); } - /* Exhausted what can be done so it's blamo time */ - out_of_memory(zonelist, gfp_mask, order, nodemask, false); - out: - clear_zonelist_oom(zonelist, gfp_mask); + mutex_unlock(&oom_lock); return page; } +/* + * 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 + #ifdef CONFIG_COMPACTION /* Try memory compaction for high-order allocations before reclaim */ static struct page * __alloc_pages_direct_compact(gfp_t gfp_mask, unsigned int order, - struct zonelist *zonelist, enum zone_type high_zoneidx, - nodemask_t *nodemask, int alloc_flags, struct zone *preferred_zone, - int migratetype, bool sync_migration, - bool *contended_compaction, bool *deferred_compaction, - unsigned long *did_some_progress) + unsigned int alloc_flags, const struct alloc_context *ac, + enum compact_priority prio, enum compact_result *compact_result) { + struct page *page = NULL; + unsigned long pflags; + unsigned int noreclaim_flag; + if (!order) return NULL; - if (compaction_deferred(preferred_zone, order)) { - *deferred_compaction = true; + psi_memstall_enter(&pflags); + delayacct_compact_start(); + noreclaim_flag = memalloc_noreclaim_save(); + + *compact_result = try_to_compact_pages(gfp_mask, order, alloc_flags, ac, + prio, &page); + + 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 + */ + count_vm_event(COMPACTSTALL); + + /* Prep a captured page if available */ + if (page) + prep_new_page(page, order, gfp_mask, alloc_flags); + + /* Try get a page from the freelist if available */ + if (!page) + page = get_page_from_freelist(gfp_mask, order, alloc_flags, ac); + + if (page) { + struct zone *zone = page_zone(page); + + zone->compact_blockskip_flush = false; + compaction_defer_reset(zone, order, true); + count_vm_event(COMPACTSUCCESS); + return page; } - current->flags |= PF_MEMALLOC; - *did_some_progress = try_to_compact_pages(zonelist, order, gfp_mask, - nodemask, sync_migration, - contended_compaction); - current->flags &= ~PF_MEMALLOC; + /* + * It's bad if compaction run occurs and fails. The most likely reason + * is that pages exist, but not enough to satisfy watermarks. + */ + count_vm_event(COMPACTFAIL); - if (*did_some_progress != COMPACT_SKIPPED) { - struct page *page; + cond_resched(); + + return NULL; +} - /* Page migration frees to the PCP lists but we want merging */ - drain_pages(get_cpu()); - put_cpu(); +static inline bool +should_compact_retry(struct alloc_context *ac, int order, int alloc_flags, + enum compact_result compact_result, + enum compact_priority *compact_priority, + int *compaction_retries) +{ + int max_retries = MAX_COMPACT_RETRIES; + int min_priority; + bool ret = false; + int retries = *compaction_retries; + enum compact_priority priority = *compact_priority; - page = get_page_from_freelist(gfp_mask, nodemask, - order, zonelist, high_zoneidx, - alloc_flags & ~ALLOC_NO_WATERMARKS, - preferred_zone, migratetype); - if (page) { - preferred_zone->compact_blockskip_flush = false; - preferred_zone->compact_considered = 0; - preferred_zone->compact_defer_shift = 0; - if (order >= preferred_zone->compact_order_failed) - preferred_zone->compact_order_failed = order + 1; - count_vm_event(COMPACTSUCCESS); - return page; - } + if (!order) + return false; - /* - * It's bad if compaction run occurs and fails. - * The most likely reason is that pages exist, - * but not enough to satisfy watermarks. - */ - count_vm_event(COMPACTFAIL); + if (fatal_signal_pending(current)) + return false; + + /* + * Compaction was skipped due to a lack of free order-0 + * migration targets. Continue if reclaim can help. + */ + if (compact_result == COMPACT_SKIPPED) { + ret = compaction_zonelist_suitable(ac, order, alloc_flags); + goto out; + } + /* + * Compaction managed to coalesce some page blocks, but the + * allocation failed presumably due to a race. Retry some. + */ + if (compact_result == COMPACT_SUCCESS) { /* - * As async compaction considers a subset of pageblocks, only - * defer if the failure was a sync compaction failure. + * !costly requests are much more important than + * __GFP_RETRY_MAYFAIL costly ones because they are de + * facto nofail and invoke OOM killer to move on while + * costly can fail and users are ready to cope with + * that. 1/4 retries is rather arbitrary but we would + * need much more detailed feedback from compaction to + * make a better decision. */ - if (sync_migration) - defer_compaction(preferred_zone, order); + if (order > PAGE_ALLOC_COSTLY_ORDER) + max_retries /= 4; - cond_resched(); + if (++(*compaction_retries) <= max_retries) { + ret = true; + goto out; + } } - return NULL; + /* + * Compaction failed. Retry with increasing priority. + */ + min_priority = (order > PAGE_ALLOC_COSTLY_ORDER) ? + MIN_COMPACT_COSTLY_PRIORITY : MIN_COMPACT_PRIORITY; + + if (*compact_priority > min_priority) { + (*compact_priority)--; + *compaction_retries = 0; + ret = true; + } +out: + trace_compact_retry(order, priority, compact_result, retries, max_retries, ret); + return ret; } #else static inline struct page * __alloc_pages_direct_compact(gfp_t gfp_mask, unsigned int order, - struct zonelist *zonelist, enum zone_type high_zoneidx, - nodemask_t *nodemask, int alloc_flags, struct zone *preferred_zone, - int migratetype, bool sync_migration, - bool *contended_compaction, bool *deferred_compaction, - unsigned long *did_some_progress) + unsigned int alloc_flags, const struct alloc_context *ac, + enum compact_priority prio, enum compact_result *compact_result) { + *compact_result = COMPACT_SKIPPED; return NULL; } + +static inline bool +should_compact_retry(struct alloc_context *ac, int order, int alloc_flags, + enum compact_result compact_result, + enum compact_priority *compact_priority, + int *compaction_retries) +{ + struct zone *zone; + struct zoneref *z; + + if (!order || order > PAGE_ALLOC_COSTLY_ORDER) + return false; + + /* + * There are setups with compaction disabled which would prefer to loop + * inside the allocator rather than hit the oom killer prematurely. + * 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->highest_zoneidx, ac->nodemask) { + if (zone_watermark_ok(zone, 0, min_wmark_pages(zone), + ac->highest_zoneidx, alloc_flags)) + return true; + } + return false; +} #endif /* CONFIG_COMPACTION */ +#ifdef CONFIG_LOCKDEP +static struct lockdep_map __fs_reclaim_map = + STATIC_LOCKDEP_MAP_INIT("fs_reclaim", &__fs_reclaim_map); + +static bool __need_reclaim(gfp_t gfp_mask) +{ + /* no reclaim without waiting on it */ + if (!(gfp_mask & __GFP_DIRECT_RECLAIM)) + return false; + + /* this guy won't enter reclaim */ + if (current->flags & PF_MEMALLOC) + return false; + + if (gfp_mask & __GFP_NOLOCKDEP) + return false; + + return true; +} + +void __fs_reclaim_acquire(unsigned long ip) +{ + lock_acquire_exclusive(&__fs_reclaim_map, 0, 0, NULL, ip); +} + +void __fs_reclaim_release(unsigned long ip) +{ + lock_release(&__fs_reclaim_map, ip); +} + +void fs_reclaim_acquire(gfp_t gfp_mask) +{ + 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) +{ + 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 -__perform_reclaim(gfp_t gfp_mask, unsigned int order, struct zonelist *zonelist, - nodemask_t *nodemask) +static unsigned long +__perform_reclaim(gfp_t gfp_mask, unsigned int order, + const struct alloc_context *ac) { - struct reclaim_state reclaim_state; - int progress; + unsigned int noreclaim_flag; + unsigned long progress; cond_resched(); /* We now go into synchronous reclaim */ cpuset_memory_pressure_bump(); - current->flags |= PF_MEMALLOC; - lockdep_set_current_reclaim_state(gfp_mask); - reclaim_state.reclaimed_slab = 0; - current->reclaim_state = &reclaim_state; + fs_reclaim_acquire(gfp_mask); + noreclaim_flag = memalloc_noreclaim_save(); - progress = try_to_free_pages(zonelist, order, gfp_mask, nodemask); + progress = try_to_free_pages(ac->zonelist, order, gfp_mask, + ac->nodemask); - current->reclaim_state = NULL; - lockdep_clear_current_reclaim_state(); - current->flags &= ~PF_MEMALLOC; + memalloc_noreclaim_restore(noreclaim_flag); + fs_reclaim_release(gfp_mask); cond_resched(); @@ -2262,508 +4388,993 @@ __perform_reclaim(gfp_t gfp_mask, unsigned int order, struct zonelist *zonelist, /* The really slow allocator path where we enter direct reclaim */ static inline struct page * __alloc_pages_direct_reclaim(gfp_t gfp_mask, unsigned int order, - struct zonelist *zonelist, enum zone_type high_zoneidx, - nodemask_t *nodemask, int alloc_flags, struct zone *preferred_zone, - int migratetype, unsigned long *did_some_progress) + unsigned int alloc_flags, const struct alloc_context *ac, + unsigned long *did_some_progress) { struct page *page = NULL; + unsigned long pflags; bool drained = false; - *did_some_progress = __perform_reclaim(gfp_mask, order, zonelist, - nodemask); + psi_memstall_enter(&pflags); + *did_some_progress = __perform_reclaim(gfp_mask, order, ac); if (unlikely(!(*did_some_progress))) - return NULL; - - /* After successful reclaim, reconsider all zones for allocation */ - if (IS_ENABLED(CONFIG_NUMA)) - zlc_clear_zones_full(zonelist); + goto out; retry: - page = get_page_from_freelist(gfp_mask, nodemask, order, - zonelist, high_zoneidx, - alloc_flags & ~ALLOC_NO_WATERMARKS, - preferred_zone, migratetype); + page = get_page_from_freelist(gfp_mask, order, alloc_flags, ac); /* * If an allocation failed after direct reclaim, it could be because - * pages are pinned on the per-cpu lists. Drain them and try again + * pages are pinned on the per-cpu lists or in high alloc reserves. + * Shrink them and try again */ if (!page && !drained) { - drain_all_pages(); + unreserve_highatomic_pageblock(ac, false); + drain_all_pages(NULL); drained = true; goto retry; } +out: + psi_memstall_leave(&pflags); return page; } -/* - * This is called in the allocator slow-path if the allocation request is of - * sufficient urgency to ignore watermarks and take other desperate measures - */ -static inline struct page * -__alloc_pages_high_priority(gfp_t gfp_mask, unsigned int order, - struct zonelist *zonelist, enum zone_type high_zoneidx, - nodemask_t *nodemask, struct zone *preferred_zone, - int migratetype) -{ - struct page *page; - - do { - page = get_page_from_freelist(gfp_mask, nodemask, order, - zonelist, high_zoneidx, ALLOC_NO_WATERMARKS, - preferred_zone, migratetype); - - if (!page && gfp_mask & __GFP_NOFAIL) - wait_iff_congested(preferred_zone, BLK_RW_ASYNC, HZ/50); - } while (!page && (gfp_mask & __GFP_NOFAIL)); - - return page; -} - -static inline -void wake_all_kswapd(unsigned int order, struct zonelist *zonelist, - enum zone_type high_zoneidx, - enum zone_type classzone_idx) +static void wake_all_kswapds(unsigned int order, gfp_t gfp_mask, + const struct alloc_context *ac) { struct zoneref *z; struct zone *zone; + pg_data_t *last_pgdat = NULL; + enum zone_type highest_zoneidx = ac->highest_zoneidx; + unsigned int reclaim_order; + + if (defrag_mode) + reclaim_order = max(order, pageblock_order); + else + reclaim_order = order; - for_each_zone_zonelist(zone, z, zonelist, high_zoneidx) - wakeup_kswapd(zone, order, classzone_idx); + for_each_zone_zonelist_nodemask(zone, z, ac->zonelist, highest_zoneidx, + ac->nodemask) { + if (!managed_zone(zone)) + continue; + if (last_pgdat == zone->zone_pgdat) + continue; + wakeup_kswapd(zone, gfp_mask, reclaim_order, highest_zoneidx); + last_pgdat = zone->zone_pgdat; + } } -static inline int -gfp_to_alloc_flags(gfp_t gfp_mask) +static inline unsigned int +gfp_to_alloc_flags(gfp_t gfp_mask, unsigned int order) { - int alloc_flags = ALLOC_WMARK_MIN | ALLOC_CPUSET; - const gfp_t wait = gfp_mask & __GFP_WAIT; + unsigned int alloc_flags = ALLOC_WMARK_MIN | ALLOC_CPUSET; - /* __GFP_HIGH is assumed to be the same as ALLOC_HIGH to save a branch. */ - BUILD_BUG_ON(__GFP_HIGH != (__force gfp_t) ALLOC_HIGH); + /* + * __GFP_HIGH is assumed to be the same as ALLOC_MIN_RESERVE + * 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_MIN_RESERVE); + BUILD_BUG_ON(__GFP_KSWAPD_RECLAIM != (__force gfp_t) ALLOC_KSWAPD); /* * The caller may dip into page reserves a bit more if the caller * cannot run direct reclaim, or if the caller has realtime scheduling * policy or is asking for __GFP_HIGH memory. GFP_ATOMIC requests will - * set both ALLOC_HARDER (!wait) and ALLOC_HIGH (__GFP_HIGH). + * set both ALLOC_NON_BLOCK and ALLOC_MIN_RESERVE(__GFP_HIGH). */ - alloc_flags |= (__force int) (gfp_mask & __GFP_HIGH); + alloc_flags |= (__force int) + (gfp_mask & (__GFP_HIGH | __GFP_KSWAPD_RECLAIM)); - if (!wait) { + if (!(gfp_mask & __GFP_DIRECT_RECLAIM)) { /* - * Not worth trying to allocate harder for - * __GFP_NOMEMALLOC even if it can't schedule. + * Not worth trying to allocate harder for __GFP_NOMEMALLOC even + * if it can't schedule. */ - if (!(gfp_mask & __GFP_NOMEMALLOC)) - alloc_flags |= ALLOC_HARDER; + if (!(gfp_mask & __GFP_NOMEMALLOC)) { + alloc_flags |= ALLOC_NON_BLOCK; + + if (order > 0 && (alloc_flags & ALLOC_MIN_RESERVE)) + alloc_flags |= ALLOC_HIGHATOMIC; + } + /* - * Ignore cpuset if GFP_ATOMIC (!wait) rather than fail alloc. - * See also cpuset_zone_allowed() comment in kernel/cpuset.c. + * Ignore cpuset mems for non-blocking __GFP_HIGH (probably + * GFP_ATOMIC) rather than fail, see the comment for + * cpuset_current_node_allowed(). */ - alloc_flags &= ~ALLOC_CPUSET; - } else if (unlikely(rt_task(current)) && !in_interrupt()) - alloc_flags |= ALLOC_HARDER; - - if (likely(!(gfp_mask & __GFP_NOMEMALLOC))) { - if (gfp_mask & __GFP_MEMALLOC) - alloc_flags |= ALLOC_NO_WATERMARKS; - else if (in_serving_softirq() && (current->flags & PF_MEMALLOC)) - alloc_flags |= ALLOC_NO_WATERMARKS; - else if (!in_interrupt() && - ((current->flags & PF_MEMALLOC) || - unlikely(test_thread_flag(TIF_MEMDIE)))) - alloc_flags |= ALLOC_NO_WATERMARKS; - } -#ifdef CONFIG_CMA - if (allocflags_to_migratetype(gfp_mask) == MIGRATE_MOVABLE) - alloc_flags |= ALLOC_CMA; -#endif + if (alloc_flags & ALLOC_MIN_RESERVE) + alloc_flags &= ~ALLOC_CPUSET; + } else if (unlikely(rt_or_dl_task(current)) && in_task()) + alloc_flags |= ALLOC_MIN_RESERVE; + + alloc_flags = gfp_to_alloc_flags_cma(gfp_mask, alloc_flags); + + if (defrag_mode) + alloc_flags |= ALLOC_NOFRAGMENT; + return alloc_flags; } +static bool oom_reserves_allowed(struct task_struct *tsk) +{ + if (!tsk_is_oom_victim(tsk)) + return false; + + /* + * !MMU doesn't have oom reaper so give access to memory reserves + * only to the thread with TIF_MEMDIE set + */ + if (!IS_ENABLED(CONFIG_MMU) && !test_thread_flag(TIF_MEMDIE)) + return false; + + return true; +} + +/* + * Distinguish requests which really need access to full memory + * reserves from oom victims which can live with a portion of it + */ +static inline int __gfp_pfmemalloc_flags(gfp_t gfp_mask) +{ + if (unlikely(gfp_mask & __GFP_NOMEMALLOC)) + return 0; + if (gfp_mask & __GFP_MEMALLOC) + return ALLOC_NO_WATERMARKS; + if (in_serving_softirq() && (current->flags & PF_MEMALLOC)) + return ALLOC_NO_WATERMARKS; + if (!in_interrupt()) { + if (current->flags & PF_MEMALLOC) + return ALLOC_NO_WATERMARKS; + else if (oom_reserves_allowed(current)) + return ALLOC_OOM; + } + + return 0; +} + bool gfp_pfmemalloc_allowed(gfp_t gfp_mask) { - return !!(gfp_to_alloc_flags(gfp_mask) & ALLOC_NO_WATERMARKS); + return !!__gfp_pfmemalloc_flags(gfp_mask); +} + +/* + * Checks whether it makes sense to retry the reclaim to make a forward progress + * for the given allocation request. + * + * We give up when we either have tried MAX_RECLAIM_RETRIES in a row + * without success, or when we couldn't even meet the watermark if we + * reclaimed all remaining pages on the LRU lists. + * + * Returns true if a retry is viable or false to enter the oom path. + */ +static inline bool +should_reclaim_retry(gfp_t gfp_mask, unsigned order, + struct alloc_context *ac, int alloc_flags, + bool did_some_progress, int *no_progress_loops) +{ + struct zone *zone; + struct zoneref *z; + bool ret = false; + + /* + * Costly allocations might have made a progress but this doesn't mean + * their order will become available due to high fragmentation so + * always increment the no progress counter for them + */ + if (did_some_progress && order <= PAGE_ALLOC_COSTLY_ORDER) + *no_progress_loops = 0; + else + (*no_progress_loops)++; + + if (*no_progress_loops > MAX_RECLAIM_RETRIES) + goto out; + + + /* + * Keep reclaiming pages while there is a chance this will lead + * somewhere. If none of the target zones can satisfy our allocation + * 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->highest_zoneidx, ac->nodemask) { + unsigned long available; + unsigned long reclaimable; + unsigned long min_wmark = min_wmark_pages(zone); + bool wmark; + + if (cpusets_enabled() && + (alloc_flags & ALLOC_CPUSET) && + !__cpuset_zone_allowed(zone, gfp_mask)) + continue; + + available = reclaimable = zone_reclaimable_pages(zone); + available += zone_page_state_snapshot(zone, NR_FREE_PAGES); + + /* + * Would the allocation succeed if we reclaimed all + * reclaimable pages? + */ + wmark = __zone_watermark_ok(zone, order, min_wmark, + ac->highest_zoneidx, alloc_flags, available); + trace_reclaim_retry_zone(z, order, reclaimable, + available, min_wmark, *no_progress_loops, wmark); + if (wmark) { + ret = true; + break; + } + } + + /* + * Memory allocation/reclaim might be called from a WQ context and the + * current implementation of the WQ concurrency control doesn't + * recognize that a particular WQ is congested if the worker thread is + * looping without ever sleeping. Therefore we have to do a short sleep + * here rather than calling cond_resched(). + */ + if (current->flags & PF_WQ_WORKER) + schedule_timeout_uninterruptible(1); + else + cond_resched(); +out: + /* Before OOM, exhaust highatomic_reserve */ + if (!ret) + return unreserve_highatomic_pageblock(ac, true); + + return ret; +} + +static inline bool +check_retry_cpuset(int cpuset_mems_cookie, struct alloc_context *ac) +{ + /* + * It's possible that cpuset's mems_allowed and the nodemask from + * mempolicy don't intersect. This should be normally dealt with by + * policy_nodemask(), but it's possible to race with cpuset update in + * such a way the check therein was true, and then it became false + * before we got our cpuset_mems_cookie here. + * This assumes that for all allocations, ac->nodemask can come only + * from MPOL_BIND mempolicy (whose documented semantics is to be ignored + * when it does not intersect with the cpuset restrictions) or the + * caller can deal with a violated nodemask. + */ + if (cpusets_enabled() && ac->nodemask && + !cpuset_nodemask_valid_mems_allowed(ac->nodemask)) { + ac->nodemask = NULL; + return true; + } + + /* + * When updating a task's mems_allowed or mempolicy nodemask, it is + * possible to race with parallel threads in such a way that our + * allocation can fail while the mask is being updated. If we are about + * to fail, check if the cpuset changed during allocation and if so, + * retry. + */ + if (read_mems_allowed_retry(cpuset_mems_cookie)) + return true; + + return false; } static inline struct page * __alloc_pages_slowpath(gfp_t gfp_mask, unsigned int order, - struct zonelist *zonelist, enum zone_type high_zoneidx, - nodemask_t *nodemask, struct zone *preferred_zone, - int migratetype) + struct alloc_context *ac) { - const gfp_t wait = gfp_mask & __GFP_WAIT; + bool can_direct_reclaim = gfp_mask & __GFP_DIRECT_RECLAIM; + bool can_compact = gfp_compaction_allowed(gfp_mask); + bool nofail = gfp_mask & __GFP_NOFAIL; + const bool costly_order = order > PAGE_ALLOC_COSTLY_ORDER; struct page *page = NULL; - int alloc_flags; - unsigned long pages_reclaimed = 0; + unsigned int alloc_flags; unsigned long did_some_progress; - bool sync_migration = false; - bool deferred_compaction = false; - bool contended_compaction = false; + enum compact_priority compact_priority; + enum compact_result compact_result; + int compaction_retries; + int no_progress_loops; + unsigned int cpuset_mems_cookie; + unsigned int zonelist_iter_cookie; + int reserve_flags; + + if (unlikely(nofail)) { + /* + * Also we don't support __GFP_NOFAIL without __GFP_DIRECT_RECLAIM, + * otherwise, we may result in lockup. + */ + WARN_ON_ONCE(!can_direct_reclaim); + /* + * PF_MEMALLOC request from this context is rather bizarre + * because we cannot reclaim anything and only can loop waiting + * for somebody to do a work for us. + */ + WARN_ON_ONCE(current->flags & PF_MEMALLOC); + } + +restart: + compaction_retries = 0; + no_progress_loops = 0; + compact_result = COMPACT_SKIPPED; + compact_priority = DEF_COMPACT_PRIORITY; + cpuset_mems_cookie = read_mems_allowed_begin(); + zonelist_iter_cookie = zonelist_iter_begin(); /* - * In the slowpath, we sanity check order to avoid ever trying to - * reclaim >= MAX_ORDER areas which will never succeed. Callers may - * be using allocators in order of preference for an area that is - * too large. + * The fast path uses conservative alloc_flags to succeed only until + * kswapd needs to be woken up, and to avoid the cost of setting up + * alloc_flags precisely. So we do that now. */ - if (order >= MAX_ORDER) { - WARN_ON_ONCE(!(gfp_mask & __GFP_NOWARN)); - return NULL; - } + alloc_flags = gfp_to_alloc_flags(gfp_mask, order); /* - * GFP_THISNODE (meaning __GFP_THISNODE, __GFP_NORETRY and - * __GFP_NOWARN set) should not cause reclaim since the subsystem - * (f.e. slab) using GFP_THISNODE may choose to trigger reclaim - * using a larger set of nodes after it has established that the - * allowed per node queues are empty and that nodes are - * over allocated. - */ - if (IS_ENABLED(CONFIG_NUMA) && - (gfp_mask & GFP_THISNODE) == GFP_THISNODE) + * We need to recalculate the starting point for the zonelist iterator + * because we might have used different nodemask in the fast path, or + * there was a cpuset modification and we are retrying - otherwise we + * could end up iterating over non-eligible zones endlessly. + */ + ac->preferred_zoneref = first_zones_zonelist(ac->zonelist, + ac->highest_zoneidx, ac->nodemask); + if (!zonelist_zone(ac->preferred_zoneref)) goto nopage; -restart: - if (!(gfp_mask & __GFP_NO_KSWAPD)) - wake_all_kswapd(order, zonelist, high_zoneidx, - zone_idx(preferred_zone)); - /* - * OK, we're below the kswapd watermark and have kicked background - * reclaim. Now things get more complex, so set up alloc_flags according - * to how we want to proceed. + * 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. */ - alloc_flags = gfp_to_alloc_flags(gfp_mask); + if (cpusets_insane_config() && (gfp_mask & __GFP_HARDWALL)) { + struct zoneref *z = first_zones_zonelist(ac->zonelist, + ac->highest_zoneidx, + &cpuset_current_mems_allowed); + if (!zonelist_zone(z)) + goto nopage; + } + + if (alloc_flags & ALLOC_KSWAPD) + wake_all_kswapds(order, gfp_mask, ac); /* - * Find the true preferred zone if the allocation is unconstrained by - * cpusets. - */ - if (!(alloc_flags & ALLOC_CPUSET) && !nodemask) - first_zones_zonelist(zonelist, high_zoneidx, NULL, - &preferred_zone); - -rebalance: - /* This is the last chance, in general, before the goto nopage. */ - page = get_page_from_freelist(gfp_mask, nodemask, order, zonelist, - high_zoneidx, alloc_flags & ~ALLOC_NO_WATERMARKS, - preferred_zone, migratetype); + * The adjusted alloc_flags might result in immediate success, so try + * that first + */ + page = get_page_from_freelist(gfp_mask, order, alloc_flags, ac); if (page) goto got_pg; - /* Allocate without watermarks if the context allows */ - if (alloc_flags & ALLOC_NO_WATERMARKS) { + /* + * For costly allocations, try direct compaction first, as it's likely + * that we have enough base pages and don't need to reclaim. For non- + * movable high-order allocations, do that as well, as compaction will + * try prevent permanent fragmentation by migrating from blocks of the + * same migratetype. + * Don't try this for allocations that are allowed to ignore + * watermarks, as the ALLOC_NO_WATERMARKS attempt didn't yet happen. + */ + if (can_direct_reclaim && can_compact && + (costly_order || + (order > 0 && ac->migratetype != MIGRATE_MOVABLE)) + && !gfp_pfmemalloc_allowed(gfp_mask)) { + page = __alloc_pages_direct_compact(gfp_mask, order, + alloc_flags, ac, + INIT_COMPACT_PRIORITY, + &compact_result); + if (page) + goto got_pg; + /* - * Ignore mempolicies if ALLOC_NO_WATERMARKS on the grounds - * the allocation is high priority and these type of - * allocations are system rather than user orientated + * Checks for costly allocations with __GFP_NORETRY, which + * includes some THP page fault allocations */ - zonelist = node_zonelist(numa_node_id(), gfp_mask); + if (costly_order && (gfp_mask & __GFP_NORETRY)) { + /* + * If allocating entire pageblock(s) and compaction + * failed because all zones are below low watermarks + * or is prohibited because it recently failed at this + * order, fail immediately unless the allocator has + * requested compaction and reclaim retry. + * + * Reclaim is + * - potentially very expensive because zones are far + * below their low watermarks or this is part of very + * bursty high order allocations, + * - not guaranteed to help because isolate_freepages() + * may not iterate over freed pages as part of its + * linear scan, and + * - unlikely to make entire pageblocks free on its + * own. + */ + if (compact_result == COMPACT_SKIPPED || + compact_result == COMPACT_DEFERRED) + goto nopage; - page = __alloc_pages_high_priority(gfp_mask, order, - zonelist, high_zoneidx, nodemask, - preferred_zone, migratetype); - if (page) { - goto got_pg; + /* + * Looks like reclaim/compaction is worth trying, but + * sync compaction could be very expensive, so keep + * using async compaction. + */ + compact_priority = INIT_COMPACT_PRIORITY; } } - /* Atomic allocations - we can't balance anything */ - if (!wait) +retry: + /* + * Deal with possible cpuset update races or zonelist updates to avoid + * infinite retries. + */ + if (check_retry_cpuset(cpuset_mems_cookie, ac) || + check_retry_zonelist(zonelist_iter_cookie)) + goto restart; + + /* Ensure kswapd doesn't accidentally go to sleep as long as we loop */ + if (alloc_flags & ALLOC_KSWAPD) + wake_all_kswapds(order, gfp_mask, ac); + + reserve_flags = __gfp_pfmemalloc_flags(gfp_mask); + if (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 + * ignored. These allocations are high priority and system rather than + * user oriented. + */ + if (!(alloc_flags & ALLOC_CPUSET) || reserve_flags) { + ac->nodemask = NULL; + ac->preferred_zoneref = first_zones_zonelist(ac->zonelist, + ac->highest_zoneidx, ac->nodemask); + } + + /* Attempt with potentially adjusted zonelist and alloc_flags */ + page = get_page_from_freelist(gfp_mask, order, alloc_flags, ac); + if (page) + goto got_pg; + + /* Caller is not willing to reclaim, we can't balance anything */ + if (!can_direct_reclaim) goto nopage; /* Avoid recursion of direct reclaim */ if (current->flags & PF_MEMALLOC) goto nopage; - /* Avoid allocations with no watermarks from looping endlessly */ - if (test_thread_flag(TIF_MEMDIE) && !(gfp_mask & __GFP_NOFAIL)) - goto nopage; + /* Try direct reclaim and then allocating */ + page = __alloc_pages_direct_reclaim(gfp_mask, order, alloc_flags, ac, + &did_some_progress); + if (page) + goto got_pg; - /* - * Try direct compaction. The first pass is asynchronous. Subsequent - * attempts after direct reclaim are synchronous - */ - page = __alloc_pages_direct_compact(gfp_mask, order, - zonelist, high_zoneidx, - nodemask, - alloc_flags, preferred_zone, - migratetype, sync_migration, - &contended_compaction, - &deferred_compaction, - &did_some_progress); + /* Try direct compaction and then allocating */ + page = __alloc_pages_direct_compact(gfp_mask, order, alloc_flags, ac, + compact_priority, &compact_result); if (page) goto got_pg; - sync_migration = true; + + /* Do not loop if specifically requested */ + if (gfp_mask & __GFP_NORETRY) + goto nopage; /* - * If compaction is deferred for high-order allocations, it is because - * sync compaction recently failed. In this is the case and the caller - * requested a movable allocation that does not heavily disrupt the - * system then fail the allocation instead of entering direct reclaim. + * Do not retry costly high order allocations unless they are + * __GFP_RETRY_MAYFAIL and we can compact */ - if ((deferred_compaction || contended_compaction) && - (gfp_mask & __GFP_NO_KSWAPD)) + if (costly_order && (!can_compact || + !(gfp_mask & __GFP_RETRY_MAYFAIL))) goto nopage; - /* Try direct reclaim and then allocating */ - page = __alloc_pages_direct_reclaim(gfp_mask, order, - zonelist, high_zoneidx, - nodemask, - alloc_flags, preferred_zone, - migratetype, &did_some_progress); - if (page) - goto got_pg; + if (should_reclaim_retry(gfp_mask, order, ac, alloc_flags, + did_some_progress > 0, &no_progress_loops)) + goto retry; /* - * If we failed to make any progress reclaiming, then we are - * running out of options and have to consider going OOM + * It doesn't make any sense to retry for the compaction if the order-0 + * reclaim is not able to make any progress because the current + * implementation of the compaction depends on the sufficient amount + * of free memory (see __compaction_suitable) */ - if (!did_some_progress) { - if ((gfp_mask & __GFP_FS) && !(gfp_mask & __GFP_NORETRY)) { - if (oom_killer_disabled) - goto nopage; - /* Coredumps can quickly deplete all memory reserves */ - if ((current->flags & PF_DUMPCORE) && - !(gfp_mask & __GFP_NOFAIL)) - goto nopage; - page = __alloc_pages_may_oom(gfp_mask, order, - zonelist, high_zoneidx, - nodemask, preferred_zone, - migratetype); - if (page) - goto got_pg; + if (did_some_progress > 0 && can_compact && + should_compact_retry(ac, order, alloc_flags, + compact_result, &compact_priority, + &compaction_retries)) + goto retry; - if (!(gfp_mask & __GFP_NOFAIL)) { - /* - * The oom killer is not called for high-order - * allocations that may fail, so if no progress - * is being made, there are no other options and - * retrying is unlikely to help. - */ - if (order > PAGE_ALLOC_COSTLY_ORDER) - goto nopage; - /* - * The oom killer is not called for lowmem - * allocations to prevent needlessly killing - * innocent tasks. - */ - if (high_zoneidx < ZONE_NORMAL) - goto nopage; - } + /* Reclaim/compaction failed to prevent the fallback */ + if (defrag_mode && (alloc_flags & ALLOC_NOFRAGMENT)) { + alloc_flags &= ~ALLOC_NOFRAGMENT; + goto retry; + } - goto restart; - } + /* + * 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); + if (page) + goto got_pg; + + /* Avoid allocations with no watermarks from looping endlessly */ + if (tsk_is_oom_victim(current) && + (alloc_flags & ALLOC_OOM || + (gfp_mask & __GFP_NOMEMALLOC))) + goto nopage; + + /* Retry as long as the OOM killer is making progress */ + if (did_some_progress) { + no_progress_loops = 0; + goto retry; } - /* Check if we should retry the allocation */ - pages_reclaimed += did_some_progress; - if (should_alloc_retry(gfp_mask, order, did_some_progress, - pages_reclaimed)) { - /* Wait for some write requests to complete then retry */ - wait_iff_congested(preferred_zone, BLK_RW_ASYNC, HZ/50); - goto rebalance; - } else { +nopage: + /* + * 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 + * we always retry + */ + if (unlikely(nofail)) { /* - * High-order allocations do not necessarily loop after - * direct reclaim and reclaim/compaction depends on compaction - * being called after reclaim so call directly if necessary + * Lacking direct_reclaim we can't do anything to reclaim memory, + * we disregard these unreasonable nofail requests and still + * return NULL */ - page = __alloc_pages_direct_compact(gfp_mask, order, - zonelist, high_zoneidx, - nodemask, - alloc_flags, preferred_zone, - migratetype, sync_migration, - &contended_compaction, - &deferred_compaction, - &did_some_progress); + if (!can_direct_reclaim) + goto fail; + + /* + * Help non-failing allocations by giving some access to memory + * reserves normally used for high priority non-blocking + * allocations but do not use ALLOC_NO_WATERMARKS because this + * could deplete whole memory reserves which would just make + * the situation worse. + */ + page = __alloc_pages_cpuset_fallback(gfp_mask, order, ALLOC_MIN_RESERVE, ac); if (page) goto got_pg; - } -nopage: - warn_alloc_failed(gfp_mask, order, NULL); - return page; + cond_resched(); + goto retry; + } +fail: + warn_alloc(gfp_mask, ac->nodemask, + "page allocation failure: order:%u", order); got_pg: - if (kmemcheck_enabled) - kmemcheck_pagealloc_alloc(page, order, gfp_mask); - return page; } -/* - * This is the 'heart' of the zoned buddy allocator. - */ -struct page * -__alloc_pages_nodemask(gfp_t gfp_mask, unsigned int order, - struct zonelist *zonelist, nodemask_t *nodemask) +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_gfp, + unsigned int *alloc_flags) { - enum zone_type high_zoneidx = gfp_zone(gfp_mask); - struct zone *preferred_zone; - struct page *page = NULL; - int migratetype = allocflags_to_migratetype(gfp_mask); - unsigned int cpuset_mems_cookie; - int alloc_flags = ALLOC_WMARK_LOW|ALLOC_CPUSET; - struct mem_cgroup *memcg = NULL; + ac->highest_zoneidx = gfp_zone(gfp_mask); + ac->zonelist = node_zonelist(preferred_nid, gfp_mask); + ac->nodemask = nodemask; + ac->migratetype = gfp_migratetype(gfp_mask); + + if (cpusets_enabled()) { + *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; + } - gfp_mask &= gfp_allowed_mask; + might_alloc(gfp_mask); - lockdep_trace_alloc(gfp_mask); + /* + * Don't invoke should_fail logic, since it may call + * get_random_u32() and printk() which need to spin_lock. + */ + if (!(*alloc_flags & ALLOC_TRYLOCK) && + should_fail_alloc_page(gfp_mask, order)) + return false; - might_sleep_if(gfp_mask & __GFP_WAIT); + *alloc_flags = gfp_to_alloc_flags_cma(gfp_mask, *alloc_flags); - if (should_fail_alloc_page(gfp_mask, order)) - return NULL; + /* Dirty zone balancing only done in the fast path */ + ac->spread_dirty_pages = (gfp_mask & __GFP_WRITE); /* - * Check the zones suitable for the gfp_mask contain at least one - * valid zone. It's possible to have an empty zonelist as a result - * of GFP_THISNODE and a memoryless node + * The preferred zone is used for statistics but crucially it is + * also used as the starting point for the zonelist iterator. It + * may get reset for allocations that ignore memory policies. */ - if (unlikely(!zonelist->_zonerefs->zone)) - return NULL; + ac->preferred_zoneref = first_zones_zonelist(ac->zonelist, + ac->highest_zoneidx, ac->nodemask); + + return true; +} + +/* + * __alloc_pages_bulk - Allocate a number of order-0 pages to an array + * @gfp: GFP flags for the allocation + * @preferred_nid: The preferred NUMA node ID to allocate from + * @nodemask: Set of nodes to allocate from, may be NULL + * @nr_pages: The number of pages desired in the array + * @page_array: Array to store the pages + * + * This is a batched version of the page allocator that attempts to allocate + * @nr_pages quickly. Pages are added to @page_array. + * + * Note that only the elements in @page_array that were cleared to %NULL on + * entry are populated with newly allocated pages. @nr_pages is the maximum + * number of pages that will be stored in the array. + * + * Returns the number of pages in @page_array, including ones already + * allocated on entry. This can be less than the number requested in @nr_pages, + * but all empty slots are filled from the beginning. I.e., if all slots in + * @page_array were set to %NULL on entry, the slots from 0 to the return value + * - 1 will be filled. + */ +unsigned long alloc_pages_bulk_noprof(gfp_t gfp, int preferred_nid, + nodemask_t *nodemask, int nr_pages, + struct page **page_array) +{ + struct page *page; + unsigned long 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; /* - * Will only have any effect when __GFP_KMEMCG is set. This is - * verified in the (always inline) callee + * Skip populated array elements to determine if any pages need + * to be allocated before disabling IRQs. */ - if (!memcg_kmem_newpage_charge(gfp_mask, &memcg, order)) - return NULL; + while (nr_populated < nr_pages && page_array[nr_populated]) + nr_populated++; -retry_cpuset: - cpuset_mems_cookie = get_mems_allowed(); + /* No pages requested? */ + if (unlikely(nr_pages <= 0)) + goto out; - /* The preferred zone is used for statistics later */ - first_zones_zonelist(zonelist, high_zoneidx, - nodemask ? : &cpuset_current_mems_allowed, - &preferred_zone); - if (!preferred_zone) + /* Already populated array? */ + if (unlikely(nr_pages - nr_populated == 0)) goto out; -#ifdef CONFIG_CMA - if (allocflags_to_migratetype(gfp_mask) == MIGRATE_MOVABLE) - alloc_flags |= ALLOC_CMA; + /* Bulk allocator does not support memcg accounting. */ + if (memcg_kmem_online() && (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 - /* First allocation attempt */ - page = get_page_from_freelist(gfp_mask|__GFP_HARDWALL, nodemask, order, - zonelist, high_zoneidx, alloc_flags, - preferred_zone, migratetype); - if (unlikely(!page)) { - /* - * Runtime PM, block IO and its error handling path - * can deadlock because I/O on the device might not - * complete. - */ - gfp_mask = memalloc_noio_flags(gfp_mask); - page = __alloc_pages_slowpath(gfp_mask, order, - zonelist, high_zoneidx, nodemask, - preferred_zone, migratetype); - } - trace_mm_page_alloc(page, order, gfp_mask, migratetype); + /* 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. */ + z = ac.preferred_zoneref; + for_next_zone_zonelist_nodemask(zone, z, ac.highest_zoneidx, ac.nodemask) { + unsigned long mark; + + if (cpusets_enabled() && (alloc_flags & ALLOC_CPUSET) && + !__cpuset_zone_allowed(zone, gfp)) { + continue; + } + + if (nr_online_nodes > 1 && zone != zonelist_zone(ac.preferred_zoneref) && + zone_to_nid(zone) != zonelist_node_idx(ac.preferred_zoneref)) { + goto failed; + } + + cond_accept_memory(zone, 0, alloc_flags); +retry_this_zone: + mark = wmark_pages(zone, alloc_flags & ALLOC_WMARK_MASK) + nr_pages; + if (zone_watermark_fast(zone, 0, mark, + zonelist_zone_idx(ac.preferred_zoneref), + alloc_flags, gfp)) { + break; + } + + if (cond_accept_memory(zone, 0, alloc_flags)) + goto retry_this_zone; + + /* Try again if zone has deferred pages */ + if (deferred_pages_enabled()) { + if (_deferred_grow_zone(zone, 0)) + goto retry_this_zone; + } + } -out: /* - * When updating a task's mems_allowed, it is possible to race with - * parallel threads in such a way that an allocation can fail while - * the mask is being updated. If a page allocation is about to fail, - * check if the cpuset changed during allocation and if so, retry. + * If there are no allowed local zones that meets the watermarks then + * try to allocate a single page and reclaim if necessary. */ - if (unlikely(!put_mems_allowed(cpuset_mems_cookie) && !page)) - goto retry_cpuset; + if (unlikely(!zone)) + goto failed; - memcg_kmem_commit_charge(page, memcg, order); + /* spin_trylock may fail due to a parallel drain or IRQ reentrancy. */ + pcp = pcp_spin_trylock(zone->per_cpu_pageset, UP_flags); + if (!pcp) + goto failed; - return page; + /* 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[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(pcp, UP_flags); + goto failed; + } + break; + } + nr_account++; + + prep_new_page(page, 0, gfp, 0); + set_page_refcounted(page); + page_array[nr_populated++] = page; + } + + pcp_spin_unlock(pcp, UP_flags); + + __count_zid_vm_events(PGALLOC, zone_idx(zone), nr_account); + zone_statistics(zonelist_zone(ac.preferred_zoneref), zone, nr_account); + +out: + return nr_populated; + +failed: + page = __alloc_pages_noprof(gfp, 0, preferred_nid, nodemask); + if (page) + page_array[nr_populated++] = page; + goto out; } -EXPORT_SYMBOL(__alloc_pages_nodemask); +EXPORT_SYMBOL_GPL(alloc_pages_bulk_noprof); /* - * Common helper functions. + * This is the 'heart' of the zoned buddy allocator. */ -unsigned long __get_free_pages(gfp_t gfp_mask, unsigned int order) +struct page *__alloc_frozen_pages_noprof(gfp_t gfp, unsigned int order, + int preferred_nid, nodemask_t *nodemask) { struct page *page; + unsigned int alloc_flags = ALLOC_WMARK_LOW; + 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 (WARN_ON_ONCE_GFP(order > MAX_PAGE_ORDER, gfp)) + return NULL; + gfp &= gfp_allowed_mask; /* - * __get_free_pages() returns a 32-bit address, which cannot represent - * a highmem page + * 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. */ - VM_BUG_ON((gfp_mask & __GFP_HIGHMEM) != 0); + gfp = current_gfp_context(gfp); + alloc_gfp = gfp; + if (!prepare_alloc_pages(gfp, order, preferred_nid, nodemask, &ac, + &alloc_gfp, &alloc_flags)) + return NULL; + + /* + * Forbid the first pass from falling back to types that fragment + * memory until all local zones are considered. + */ + alloc_flags |= alloc_flags_nofragment(zonelist_zone(ac.preferred_zoneref), gfp); + + /* First allocation attempt */ + page = get_page_from_freelist(alloc_gfp, order, alloc_flags, &ac); + if (likely(page)) + goto out; - page = alloc_pages(gfp_mask, order); + 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. + */ + ac.nodemask = nodemask; + + page = __alloc_pages_slowpath(alloc_gfp, order, &ac); + +out: + if (memcg_kmem_online() && (gfp & __GFP_ACCOUNT) && page && + unlikely(__memcg_kmem_charge_page(page, gfp, order) != 0)) { + free_frozen_pages(page, order); + page = NULL; + } + + trace_mm_page_alloc(page, order, alloc_gfp, ac.migratetype); + kmsan_alloc_page(page, order, alloc_gfp); + + return page; +} +EXPORT_SYMBOL(__alloc_frozen_pages_noprof); + +struct page *__alloc_pages_noprof(gfp_t gfp, unsigned int order, + int preferred_nid, nodemask_t *nodemask) +{ + struct page *page; + + page = __alloc_frozen_pages_noprof(gfp, order, preferred_nid, nodemask); + if (page) + set_page_refcounted(page); + return page; +} +EXPORT_SYMBOL(__alloc_pages_noprof); + +struct folio *__folio_alloc_noprof(gfp_t gfp, unsigned int order, int preferred_nid, + nodemask_t *nodemask) +{ + struct page *page = __alloc_pages_noprof(gfp | __GFP_COMP, order, + preferred_nid, nodemask); + return page_rmappable_folio(page); +} +EXPORT_SYMBOL(__folio_alloc_noprof); + +/* + * Common helper functions. Never use with __GFP_HIGHMEM because the returned + * address cannot represent highmem pages. Use alloc_pages and then kmap if + * you need to access high mem. + */ +unsigned long get_free_pages_noprof(gfp_t gfp_mask, unsigned int order) +{ + struct page *page; + + page = alloc_pages_noprof(gfp_mask & ~__GFP_HIGHMEM, order); if (!page) return 0; return (unsigned long) page_address(page); } -EXPORT_SYMBOL(__get_free_pages); +EXPORT_SYMBOL(get_free_pages_noprof); -unsigned long get_zeroed_page(gfp_t gfp_mask) +unsigned long get_zeroed_page_noprof(gfp_t gfp_mask) { - return __get_free_pages(gfp_mask | __GFP_ZERO, 0); + return get_free_pages_noprof(gfp_mask | __GFP_ZERO, 0); } -EXPORT_SYMBOL(get_zeroed_page); +EXPORT_SYMBOL(get_zeroed_page_noprof); -void __free_pages(struct page *page, unsigned int order) +static void ___free_pages(struct page *page, unsigned int order, + fpi_t fpi_flags) { - if (put_page_testzero(page)) { - if (order == 0) - free_hot_cold_page(page, 0); - else - __free_pages_ok(page, order); + /* get PageHead before we drop reference */ + int head = PageHead(page); + /* get alloc tag in case the page is released by others */ + struct alloc_tag *tag = pgalloc_tag_get(page); + + if (put_page_testzero(page)) + __free_frozen_pages(page, order, fpi_flags); + else if (!head) { + pgalloc_tag_sub_pages(tag, (1 << order) - 1); + while (order-- > 0) { + /* + * The "tail" pages of this non-compound high-order + * page will have no code tags, so to avoid warnings + * mark them as empty. + */ + clear_page_tag_ref(page + (1 << order)); + __free_frozen_pages(page + (1 << order), order, + fpi_flags); + } } } -EXPORT_SYMBOL(__free_pages); - -void free_pages(unsigned long addr, unsigned int 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 (addr != 0) { - VM_BUG_ON(!virt_addr_valid((void *)addr)); - __free_pages(virt_to_page((void *)addr), order); - } + ___free_pages(page, order, FPI_NONE); } - -EXPORT_SYMBOL(free_pages); +EXPORT_SYMBOL(__free_pages); /* - * __free_memcg_kmem_pages and free_memcg_kmem_pages will free - * pages allocated with __GFP_KMEMCG. - * - * Those pages are accounted to a particular memcg, embedded in the - * corresponding page_cgroup. To avoid adding a hit in the allocator to search - * for that information only to find out that it is NULL for users who have no - * interest in that whatsoever, we provide these functions. - * - * The caller knows better which flags it relies on. + * Can be called while holding raw_spin_lock or from IRQ and NMI for any + * page type (not only those that came from alloc_pages_nolock) */ -void __free_memcg_kmem_pages(struct page *page, unsigned int order) +void free_pages_nolock(struct page *page, unsigned int order) { - memcg_kmem_uncharge_pages(page, order); - __free_pages(page, order); + ___free_pages(page, order, FPI_TRYLOCK); } -void free_memcg_kmem_pages(unsigned long addr, unsigned int order) +/** + * free_pages - Free pages allocated with __get_free_pages(). + * @addr: The virtual address tied to a page returned from __get_free_pages(). + * @order: The order of the allocation. + * + * This function behaves the same as __free_pages(). Use this function + * to free pages when you only have a valid virtual address. If you have + * the page, call __free_pages() instead. + */ +void free_pages(unsigned long addr, unsigned int order) { if (addr != 0) { VM_BUG_ON(!virt_addr_valid((void *)addr)); - __free_memcg_kmem_pages(virt_to_page((void *)addr), order); + __free_pages(virt_to_page((void *)addr), order); } } -static void *make_alloc_exact(unsigned long addr, unsigned order, size_t size) +EXPORT_SYMBOL(free_pages); + +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); - - split_page(virt_to_page((void *)addr), order); - while (used < alloc_end) { - free_page(used); - used += PAGE_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_owner(page, order, 0); + pgalloc_tag_split(page_folio(page), order, 0); + split_page_memcg(page, 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; } @@ -2771,47 +5382,56 @@ static void *make_alloc_exact(unsigned long addr, unsigned order, size_t size) /** * alloc_pages_exact - allocate an exact number physically-contiguous pages. * @size: the number of bytes to allocate - * @gfp_mask: GFP flags for the allocation + * @gfp_mask: GFP flags for the allocation, must not contain __GFP_COMP * * This function is similar to alloc_pages(), except that it allocates the * minimum number of pages to satisfy the request. alloc_pages() can only * allocate memory in power-of-two pages. * - * This function is also limited by MAX_ORDER. + * This function is also limited by MAX_PAGE_ORDER. * * Memory allocated by this function must be released by free_pages_exact(). + * + * Return: pointer to the allocated area or %NULL in case of error. */ -void *alloc_pages_exact(size_t size, gfp_t gfp_mask) +void *alloc_pages_exact_noprof(size_t size, gfp_t gfp_mask) { unsigned int order = get_order(size); unsigned long addr; - addr = __get_free_pages(gfp_mask, order); + if (WARN_ON_ONCE(gfp_mask & (__GFP_COMP | __GFP_HIGHMEM))) + gfp_mask &= ~(__GFP_COMP | __GFP_HIGHMEM); + + addr = get_free_pages_noprof(gfp_mask, order); return make_alloc_exact(addr, order, size); } -EXPORT_SYMBOL(alloc_pages_exact); +EXPORT_SYMBOL(alloc_pages_exact_noprof); /** * alloc_pages_exact_nid - allocate an exact number of physically-contiguous * pages on a node. * @nid: the preferred node ID where memory should be allocated * @size: the number of bytes to allocate - * @gfp_mask: GFP flags for the allocation + * @gfp_mask: GFP flags for the allocation, must not contain __GFP_COMP * * Like alloc_pages_exact(), but try to allocate on node nid first before falling * back. - * Note this is not alloc_pages_exact_node() which allocates on a specific node, - * but is not exact. + * + * Return: pointer to the allocated area or %NULL in case of error. */ -void *alloc_pages_exact_nid(int nid, size_t size, gfp_t gfp_mask) +void * __meminit alloc_pages_exact_nid_noprof(int nid, size_t size, gfp_t gfp_mask) { - unsigned order = get_order(size); - struct page *p = alloc_pages_node(nid, gfp_mask, order); + unsigned int order = get_order(size); + struct page *p; + + if (WARN_ON_ONCE(gfp_mask & (__GFP_COMP | __GFP_HIGHMEM))) + gfp_mask &= ~(__GFP_COMP | __GFP_HIGHMEM); + + p = alloc_pages_node_noprof(nid, gfp_mask, order); if (!p) return NULL; return make_alloc_exact((unsigned long)page_address(p), order, size); } -EXPORT_SYMBOL(alloc_pages_exact_nid); /** * free_pages_exact - release memory allocated via alloc_pages_exact() @@ -2836,10 +5456,13 @@ EXPORT_SYMBOL(free_pages_exact); * nr_free_zone_pages - count number of pages beyond high watermark * @offset: The zone index of the highest zone * - * nr_free_zone_pages() counts the number of counts pages which are beyond the + * nr_free_zone_pages() counts the number of pages which are beyond the * high watermark within all zones at or below a given zone index. For each * zone, the number of pages is calculated as: - * managed_pages - high_pages + * + * nr_free_zone_pages = managed_pages - high_pages + * + * Return: number of pages beyond high watermark. */ static unsigned long nr_free_zone_pages(int offset) { @@ -2852,7 +5475,7 @@ static unsigned long nr_free_zone_pages(int offset) struct zonelist *zonelist = node_zonelist(numa_node_id(), GFP_KERNEL); for_each_zone_zonelist(zone, z, zonelist, offset) { - unsigned long size = zone->managed_pages; + unsigned long size = zone_managed_pages(zone); unsigned long high = high_wmark_pages(zone); if (size > high) sum += size - high; @@ -2866,6 +5489,9 @@ static unsigned long nr_free_zone_pages(int offset) * * nr_free_buffer_pages() counts the number of pages which are beyond the high * watermark within ZONE_DMA and ZONE_NORMAL. + * + * Return: number of pages beyond high watermark within ZONE_DMA and + * ZONE_NORMAL. */ unsigned long nr_free_buffer_pages(void) { @@ -2873,275 +5499,6 @@ 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. - */ -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)) - printk("Node %d ", zone_to_nid(zone)); -} - -void si_meminfo(struct sysinfo *val) -{ - val->totalram = totalram_pages; - val->sharedram = 0; - val->freeram = global_page_state(NR_FREE_PAGES); - val->bufferram = nr_blockdev_pages(); - val->totalhigh = totalhigh_pages; - val->freehigh = nr_free_highpages(); - val->mem_unit = PAGE_SIZE; -} - -EXPORT_SYMBOL(si_meminfo); - -#ifdef CONFIG_NUMA -void si_meminfo_node(struct sysinfo *val, int nid) -{ - int zone_type; /* needs to be signed */ - unsigned long managed_pages = 0; - pg_data_t *pgdat = NODE_DATA(nid); - - for (zone_type = 0; zone_type < MAX_NR_ZONES; zone_type++) - managed_pages += pgdat->node_zones[zone_type].managed_pages; - val->totalram = managed_pages; - val->freeram = node_page_state(nid, NR_FREE_PAGES); -#ifdef CONFIG_HIGHMEM - val->totalhigh = pgdat->node_zones[ZONE_HIGHMEM].managed_pages; - val->freehigh = zone_page_state(&pgdat->node_zones[ZONE_HIGHMEM], - NR_FREE_PAGES); -#else - val->totalhigh = 0; - val->freehigh = 0; -#endif - val->mem_unit = PAGE_SIZE; -} -#endif - -/* - * Determine whether the node should be displayed or not, depending on whether - * SHOW_MEM_FILTER_NODES was passed to show_free_areas(). - */ -bool skip_free_areas_node(unsigned int flags, int nid) -{ - bool ret = false; - unsigned int cpuset_mems_cookie; - - if (!(flags & SHOW_MEM_FILTER_NODES)) - goto out; - - do { - cpuset_mems_cookie = get_mems_allowed(); - ret = !node_isset(nid, cpuset_current_mems_allowed); - } while (!put_mems_allowed(cpuset_mems_cookie)); -out: - return ret; -} - -#define K(x) ((x) << (PAGE_SHIFT-10)) - -static void show_migration_types(unsigned char type) -{ - static const char types[MIGRATE_TYPES] = { - [MIGRATE_UNMOVABLE] = 'U', - [MIGRATE_RECLAIMABLE] = 'E', - [MIGRATE_MOVABLE] = 'M', - [MIGRATE_RESERVE] = 'R', -#ifdef CONFIG_CMA - [MIGRATE_CMA] = 'C', -#endif -#ifdef CONFIG_MEMORY_ISOLATION - [MIGRATE_ISOLATE] = 'I', -#endif - }; - char tmp[MIGRATE_TYPES + 1]; - char *p = tmp; - int i; - - for (i = 0; i < MIGRATE_TYPES; i++) { - if (type & (1 << i)) - *p++ = types[i]; - } - - *p = '\0'; - printk("(%s) ", tmp); -} - -/* - * Show free area list (used inside shift_scroll-lock stuff) - * We also calculate the percentage fragmentation. We do this by counting the - * memory on each free list with the exception of the first item on the list. - * Suppresses nodes that are not allowed by current's cpuset if - * SHOW_MEM_FILTER_NODES is passed. - */ -void show_free_areas(unsigned int filter) -{ - int cpu; - struct zone *zone; - - for_each_populated_zone(zone) { - if (skip_free_areas_node(filter, zone_to_nid(zone))) - continue; - show_node(zone); - printk("%s per-cpu:\n", zone->name); - - for_each_online_cpu(cpu) { - struct per_cpu_pageset *pageset; - - pageset = per_cpu_ptr(zone->pageset, cpu); - - printk("CPU %4d: hi:%5d, btch:%4d usd:%4d\n", - cpu, pageset->pcp.high, - pageset->pcp.batch, pageset->pcp.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" - " free:%lu slab_reclaimable:%lu slab_unreclaimable:%lu\n" - " mapped:%lu shmem:%lu pagetables:%lu bounce:%lu\n" - " free_cma:%lu\n", - global_page_state(NR_ACTIVE_ANON), - global_page_state(NR_INACTIVE_ANON), - global_page_state(NR_ISOLATED_ANON), - global_page_state(NR_ACTIVE_FILE), - global_page_state(NR_INACTIVE_FILE), - global_page_state(NR_ISOLATED_FILE), - global_page_state(NR_UNEVICTABLE), - global_page_state(NR_FILE_DIRTY), - global_page_state(NR_WRITEBACK), - global_page_state(NR_UNSTABLE_NFS), - global_page_state(NR_FREE_PAGES), - global_page_state(NR_SLAB_RECLAIMABLE), - global_page_state(NR_SLAB_UNRECLAIMABLE), - global_page_state(NR_FILE_MAPPED), - global_page_state(NR_SHMEM), - global_page_state(NR_PAGETABLE), - global_page_state(NR_BOUNCE), - global_page_state(NR_FREE_CMA_PAGES)); - - for_each_populated_zone(zone) { - int i; - - if (skip_free_areas_node(filter, zone_to_nid(zone))) - continue; - show_node(zone); - printk("%s" - " free:%lukB" - " min:%lukB" - " low:%lukB" - " high:%lukB" - " active_anon:%lukB" - " inactive_anon:%lukB" - " active_file:%lukB" - " inactive_file:%lukB" - " unevictable:%lukB" - " isolated(anon):%lukB" - " isolated(file):%lukB" - " present:%lukB" - " managed:%lukB" - " mlocked:%lukB" - " dirty:%lukB" - " writeback:%lukB" - " mapped:%lukB" - " shmem:%lukB" - " slab_reclaimable:%lukB" - " slab_unreclaimable:%lukB" - " kernel_stack:%lukB" - " pagetables:%lukB" - " unstable:%lukB" - " bounce:%lukB" - " free_cma:%lukB" - " writeback_tmp:%lukB" - " pages_scanned:%lu" - " all_unreclaimable? %s" - "\n", - zone->name, - K(zone_page_state(zone, NR_FREE_PAGES)), - K(min_wmark_pages(zone)), - K(low_wmark_pages(zone)), - K(high_wmark_pages(zone)), - K(zone_page_state(zone, NR_ACTIVE_ANON)), - K(zone_page_state(zone, NR_INACTIVE_ANON)), - K(zone_page_state(zone, NR_ACTIVE_FILE)), - K(zone_page_state(zone, NR_INACTIVE_FILE)), - K(zone_page_state(zone, NR_UNEVICTABLE)), - K(zone_page_state(zone, NR_ISOLATED_ANON)), - K(zone_page_state(zone, NR_ISOLATED_FILE)), - K(zone->present_pages), - K(zone->managed_pages), - K(zone_page_state(zone, NR_MLOCK)), - K(zone_page_state(zone, NR_FILE_DIRTY)), - K(zone_page_state(zone, NR_WRITEBACK)), - K(zone_page_state(zone, NR_FILE_MAPPED)), - K(zone_page_state(zone, NR_SHMEM)), - K(zone_page_state(zone, NR_SLAB_RECLAIMABLE)), - K(zone_page_state(zone, NR_SLAB_UNRECLAIMABLE)), - zone_page_state(zone, NR_KERNEL_STACK) * - THREAD_SIZE / 1024, - K(zone_page_state(zone, NR_PAGETABLE)), - K(zone_page_state(zone, NR_UNSTABLE_NFS)), - K(zone_page_state(zone, NR_BOUNCE)), - K(zone_page_state(zone, NR_FREE_CMA_PAGES)), - K(zone_page_state(zone, NR_WRITEBACK_TEMP)), - zone->pages_scanned, - (zone->all_unreclaimable ? "yes" : "no") - ); - printk("lowmem_reserve[]:"); - for (i = 0; i < MAX_NR_ZONES; i++) - printk(" %lu", zone->lowmem_reserve[i]); - printk("\n"); - } - - for_each_populated_zone(zone) { - unsigned long nr[MAX_ORDER], flags, order, total = 0; - unsigned char types[MAX_ORDER]; - - if (skip_free_areas_node(filter, zone_to_nid(zone))) - continue; - show_node(zone); - printk("%s: ", zone->name); - - spin_lock_irqsave(&zone->lock, flags); - for (order = 0; order < MAX_ORDER; order++) { - struct free_area *area = &zone->free_area[order]; - int type; - - nr[order] = area->nr_free; - total += nr[order] << order; - - types[order] = 0; - for (type = 0; type < MIGRATE_TYPES; type++) { - if (!list_empty(&area->free_list[type])) - types[order] |= 1 << type; - } - } - spin_unlock_irqrestore(&zone->lock, flags); - for (order = 0; order < MAX_ORDER; order++) { - printk("%lu*%lukB ", nr[order], K(1UL) << order); - if (nr[order]) - show_migration_types(types[order]); - } - printk("= %lukB\n", K(total)); - } - - hugetlb_show_meminfo(); - - printk("%ld total pagecache pages\n", global_page_state(NR_FILE_PAGES)); - - show_swap_cache_info(); -} - static void zoneref_set_zone(struct zone *zone, struct zoneref *zoneref) { zoneref->zone = zone; @@ -3153,18 +5510,17 @@ static void zoneref_set_zone(struct zone *zone, struct zoneref *zoneref) * * Add all populated zones of a node to the zonelist. */ -static int build_zonelists_node(pg_data_t *pgdat, struct zonelist *zonelist, - int nr_zones) +static int build_zonerefs_node(pg_data_t *pgdat, struct zoneref *zonerefs) { struct zone *zone; enum zone_type zone_type = MAX_NR_ZONES; + int nr_zones = 0; do { zone_type--; zone = pgdat->node_zones + zone_type; if (populated_zone(zone)) { - zoneref_set_zone(zone, - &zonelist->_zonerefs[nr_zones++]); + zoneref_set_zone(zone, &zonerefs[nr_zones++]); check_highest_zone(zone_type); } } while (zone_type); @@ -3172,120 +5528,36 @@ static int build_zonelists_node(pg_data_t *pgdat, struct zonelist *zonelist, return nr_zones; } - -/* - * zonelist_order: - * 0 = automatic detection of better ordering. - * 1 = order by ([node] distance, -zonetype) - * 2 = order by (-zonetype, [node] distance) - * - * If not NUMA, ZONELIST_ORDER_ZONE and ZONELIST_ORDER_NODE will create - * the same zonelist. So only NUMA can configure this param. - */ -#define ZONELIST_ORDER_DEFAULT 0 -#define ZONELIST_ORDER_NODE 1 -#define ZONELIST_ORDER_ZONE 2 - -/* zonelist order in the kernel. - * set_zonelist_order() will set this to NODE or ZONE. - */ -static int current_zonelist_order = ZONELIST_ORDER_DEFAULT; -static char zonelist_order_name[3][8] = {"Default", "Node", "Zone"}; - - #ifdef CONFIG_NUMA -/* The value user specified ....changed by config */ -static int user_zonelist_order = ZONELIST_ORDER_DEFAULT; -/* string for sysctl */ -#define NUMA_ZONELIST_ORDER_LEN 16 -char numa_zonelist_order[16] = "default"; - -/* - * interface for configure zonelist ordering. - * command line option "numa_zonelist_order" - * = "[dD]efault - default, automatic configuration. - * = "[nN]ode - order by node locality, then by zone within node - * = "[zZ]one - order by zone, then by locality within zone - */ static int __parse_numa_zonelist_order(char *s) { - if (*s == 'd' || *s == 'D') { - user_zonelist_order = ZONELIST_ORDER_DEFAULT; - } else if (*s == 'n' || *s == 'N') { - user_zonelist_order = ZONELIST_ORDER_NODE; - } else if (*s == 'z' || *s == 'Z') { - user_zonelist_order = ZONELIST_ORDER_ZONE; - } else { - printk(KERN_WARNING - "Ignoring invalid numa_zonelist_order value: " - "%s\n", s); + /* + * 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 + */ + if (!(*s == 'd' || *s == 'D' || *s == 'n' || *s == 'N')) { + pr_warn("Ignoring unsupported numa_zonelist_order value: %s\n", s); return -EINVAL; } return 0; } -static __init int setup_numa_zonelist_order(char *s) -{ - int ret; - - if (!s) - return 0; - - ret = __parse_numa_zonelist_order(s); - if (ret == 0) - strlcpy(numa_zonelist_order, s, NUMA_ZONELIST_ORDER_LEN); - - return ret; -} -early_param("numa_zonelist_order", setup_numa_zonelist_order); - +static char numa_zonelist_order[] = "Node"; +#define NUMA_ZONELIST_ORDER_LEN 16 /* * sysctl handler for numa_zonelist_order */ -int numa_zonelist_order_handler(ctl_table *table, int write, - void __user *buffer, size_t *length, - loff_t *ppos) +static int numa_zonelist_order_handler(const struct ctl_table *table, int write, + void *buffer, size_t *length, loff_t *ppos) { - char saved_string[NUMA_ZONELIST_ORDER_LEN]; - int ret; - static DEFINE_MUTEX(zl_order_mutex); - - mutex_lock(&zl_order_mutex); - if (write) { - if (strlen((char *)table->data) >= NUMA_ZONELIST_ORDER_LEN) { - ret = -EINVAL; - goto out; - } - strcpy(saved_string, (char *)table->data); - } - ret = proc_dostring(table, write, buffer, length, ppos); - if (ret) - goto out; - if (write) { - int oldval = user_zonelist_order; - - ret = __parse_numa_zonelist_order((char *)table->data); - if (ret) { - /* - * bogus value. restore saved string - */ - strncpy((char *)table->data, saved_string, - NUMA_ZONELIST_ORDER_LEN); - user_zonelist_order = oldval; - } else if (oldval != user_zonelist_order) { - mutex_lock(&zonelists_mutex); - build_all_zonelists(NULL, NULL); - mutex_unlock(&zonelists_mutex); - } - } -out: - mutex_unlock(&zl_order_mutex); - 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]; /** @@ -3300,17 +5572,20 @@ static int node_load[MAX_NUMNODES]; * from each node to each node in the system), and should also prefer nodes * with no CPUs, since presumably they'll have very little allocation pressure * on them otherwise. - * It returns -1 if no node is found. + * + * 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)) { + /* + * Use the local node if we haven't already, but for memoryless local + * node, we should skip it and fall back to other nodes. + */ + if (!node_isset(node, *used_node_mask) && node_state(node, N_MEMORY)) { node_set(node, *used_node_mask); return node; } @@ -3328,12 +5603,11 @@ 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) { @@ -3354,161 +5628,53 @@ static int find_next_best_node(int node, nodemask_t *used_node_mask) * This results in maximum locality--normal zone overflows into local * DMA zone, if any--but risks exhausting DMA zone. */ -static void build_zonelists_in_node_order(pg_data_t *pgdat, int node) +static void build_zonelists_in_node_order(pg_data_t *pgdat, int *node_order, + unsigned nr_nodes) { - int j; - struct zonelist *zonelist; - - zonelist = &pgdat->node_zonelists[0]; - for (j = 0; zonelist->_zonerefs[j].zone != NULL; j++) - ; - j = build_zonelists_node(NODE_DATA(node), zonelist, j); - zonelist->_zonerefs[j].zone = NULL; - zonelist->_zonerefs[j].zone_idx = 0; -} - -/* - * Build gfp_thisnode zonelists - */ -static void build_thisnode_zonelists(pg_data_t *pgdat) -{ - int j; - struct zonelist *zonelist; + struct zoneref *zonerefs; + int i; - zonelist = &pgdat->node_zonelists[1]; - j = build_zonelists_node(pgdat, zonelist, 0); - zonelist->_zonerefs[j].zone = NULL; - zonelist->_zonerefs[j].zone_idx = 0; -} + zonerefs = pgdat->node_zonelists[ZONELIST_FALLBACK]._zonerefs; -/* - * Build zonelists ordered by zone and nodes within zones. - * This results in conserving DMA zone[s] until all Normal memory is - * exhausted, but results in overflowing to remote node while memory - * may still exist in local DMA zone. - */ -static int node_order[MAX_NUMNODES]; + for (i = 0; i < nr_nodes; i++) { + int nr_zones; -static void build_zonelists_in_zone_order(pg_data_t *pgdat, int nr_nodes) -{ - int pos, j, node; - int zone_type; /* needs to be signed */ - struct zone *z; - struct zonelist *zonelist; + pg_data_t *node = NODE_DATA(node_order[i]); - zonelist = &pgdat->node_zonelists[0]; - pos = 0; - for (zone_type = MAX_NR_ZONES - 1; zone_type >= 0; zone_type--) { - for (j = 0; j < nr_nodes; j++) { - node = node_order[j]; - z = &NODE_DATA(node)->node_zones[zone_type]; - if (populated_zone(z)) { - zoneref_set_zone(z, - &zonelist->_zonerefs[pos++]); - check_highest_zone(zone_type); - } - } + nr_zones = build_zonerefs_node(node, zonerefs); + zonerefs += nr_zones; } - zonelist->_zonerefs[pos].zone = NULL; - zonelist->_zonerefs[pos].zone_idx = 0; + zonerefs->zone = NULL; + zonerefs->zone_idx = 0; } -static int default_zonelist_order(void) +/* + * Build __GFP_THISNODE zonelists + */ +static void build_thisnode_zonelists(pg_data_t *pgdat) { - int nid, zone_type; - unsigned long low_kmem_size,total_size; - struct zone *z; - int average_size; - /* - * ZONE_DMA and ZONE_DMA32 can be very small area in the system. - * If they are really small and used heavily, the system can fall - * into OOM very easily. - * This function detect ZONE_DMA/DMA32 size and configures zone order. - */ - /* Is there ZONE_NORMAL ? (ex. ppc has only DMA zone..) */ - low_kmem_size = 0; - total_size = 0; - for_each_online_node(nid) { - for (zone_type = 0; zone_type < MAX_NR_ZONES; zone_type++) { - z = &NODE_DATA(nid)->node_zones[zone_type]; - if (populated_zone(z)) { - if (zone_type < ZONE_NORMAL) - low_kmem_size += z->managed_pages; - total_size += z->managed_pages; - } else if (zone_type == ZONE_NORMAL) { - /* - * If any node has only lowmem, then node order - * is preferred to allow kernel allocations - * locally; otherwise, they can easily infringe - * on other nodes when there is an abundance of - * lowmem available to allocate from. - */ - return ZONELIST_ORDER_NODE; - } - } - } - if (!low_kmem_size || /* there are no DMA area. */ - low_kmem_size > total_size/2) /* DMA/DMA32 is big. */ - return ZONELIST_ORDER_NODE; - /* - * look into each node's config. - * If there is a node whose DMA/DMA32 memory is very big area on - * local memory, NODE_ORDER may be suitable. - */ - average_size = total_size / - (nodes_weight(node_states[N_MEMORY]) + 1); - for_each_online_node(nid) { - low_kmem_size = 0; - total_size = 0; - for (zone_type = 0; zone_type < MAX_NR_ZONES; zone_type++) { - z = &NODE_DATA(nid)->node_zones[zone_type]; - if (populated_zone(z)) { - if (zone_type < ZONE_NORMAL) - low_kmem_size += z->present_pages; - total_size += z->present_pages; - } - } - if (low_kmem_size && - total_size > average_size && /* ignore small node */ - low_kmem_size > total_size * 70/100) - return ZONELIST_ORDER_NODE; - } - return ZONELIST_ORDER_ZONE; -} + struct zoneref *zonerefs; + int nr_zones; -static void set_zonelist_order(void) -{ - if (user_zonelist_order == ZONELIST_ORDER_DEFAULT) - current_zonelist_order = default_zonelist_order(); - else - current_zonelist_order = user_zonelist_order; + zonerefs = pgdat->node_zonelists[ZONELIST_NOFALLBACK]._zonerefs; + nr_zones = build_zonerefs_node(pgdat, zonerefs); + zonerefs += nr_zones; + zonerefs->zone = NULL; + zonerefs->zone_idx = 0; } static void build_zonelists(pg_data_t *pgdat) { - int j, node, load; - enum zone_type i; - nodemask_t used_mask; + static int node_order[MAX_NUMNODES]; + int node, nr_nodes = 0; + nodemask_t used_mask = NODE_MASK_NONE; int local_node, prev_node; - struct zonelist *zonelist; - int order = current_zonelist_order; - - /* initialize zonelists */ - for (i = 0; i < MAX_ZONELISTS; i++) { - zonelist = pgdat->node_zonelists + i; - zonelist->_zonerefs[0].zone = NULL; - zonelist->_zonerefs[0].zone_idx = 0; - } /* 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)); - j = 0; - while ((node = find_next_best_node(local_node, &used_mask)) >= 0) { /* * We don't want to pressure a particular node. @@ -3517,36 +5683,18 @@ 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--; - if (order == ZONELIST_ORDER_NODE) - build_zonelists_in_node_order(pgdat, node); - else - node_order[j++] = node; /* remember order */ - } - - if (order == ZONELIST_ORDER_ZONE) { - /* calculate node order -- i.e., DMA last! */ - build_zonelists_in_zone_order(pgdat, j); } + build_zonelists_in_node_order(pgdat, node_order, nr_nodes); build_thisnode_zonelists(pgdat); -} - -/* Construct the zonelist performance cache - see further mmzone.h */ -static void build_zonelist_cache(pg_data_t *pgdat) -{ - struct zonelist *zonelist; - struct zonelist_cache *zlc; - struct zoneref *z; - - zonelist = &pgdat->node_zonelists[0]; - zonelist->zlcache_ptr = zlc = &zonelist->zlcache; - bitmap_zero(zlc->fullzones, MAX_ZONES_PER_ZONELIST); - for (z = zonelist->_zonerefs; z->zone; z++) - zlc->z_to_n[z - zonelist->_zonerefs] = zonelist_node_idx(z); + 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 @@ -3558,61 +5706,30 @@ static void build_zonelist_cache(pg_data_t *pgdat) */ int local_memory_node(int node) { - struct zone *zone; + struct zoneref *z; - (void)first_zones_zonelist(node_zonelist(node, GFP_KERNEL), + z = first_zones_zonelist(node_zonelist(node, GFP_KERNEL), gfp_zone(GFP_KERNEL), - NULL, - &zone); - return zone->node; + NULL); + return zonelist_node_idx(z); } #endif +static void setup_min_unmapped_ratio(void); +static void setup_min_slab_ratio(void); #else /* CONFIG_NUMA */ -static void set_zonelist_order(void) -{ - current_zonelist_order = ZONELIST_ORDER_ZONE; -} - static void build_zonelists(pg_data_t *pgdat) { - int node, local_node; - enum zone_type j; - struct zonelist *zonelist; + struct zoneref *zonerefs; + int nr_zones; - local_node = pgdat->node_id; - - zonelist = &pgdat->node_zonelists[0]; - j = build_zonelists_node(pgdat, zonelist, 0); + zonerefs = pgdat->node_zonelists[ZONELIST_FALLBACK]._zonerefs; + nr_zones = build_zonerefs_node(pgdat, zonerefs); + zonerefs += nr_zones; - /* - * Now we build the zonelist so that it contains the zones - * of all the other nodes. - * We don't want to pressure a particular node, so when - * building the zones for node N, we make sure that the - * zones coming right after the local ones are those from - * node N+1 (modulo N) - */ - for (node = local_node + 1; node < MAX_NUMNODES; node++) { - if (!node_online(node)) - continue; - j = build_zonelists_node(NODE_DATA(node), zonelist, j); - } - for (node = 0; node < local_node; node++) { - if (!node_online(node)) - continue; - j = build_zonelists_node(NODE_DATA(node), zonelist, j); - } - - zonelist->_zonerefs[j].zone = NULL; - zonelist->_zonerefs[j].zone_idx = 0; -} - -/* non-NUMA variant of zonelist performance cache - just NULL zlcache_ptr */ -static void build_zonelist_cache(pg_data_t *pgdat) -{ - pgdat->node_zonelists[0].zlcache_ptr = NULL; + zonerefs->zone = NULL; + zonerefs->zone_idx = 0; } #endif /* CONFIG_NUMA */ @@ -3632,39 +5749,79 @@ static void build_zonelist_cache(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 setup_zone_pageset(struct zone *zone); +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); -/* - * Global mutex to protect against size modification of zonelists - * as well as to serialize pageset setup for the new populated zone. - */ -DEFINE_MUTEX(zonelists_mutex); - -/* return values int ....just for stop_machine() */ -static int __build_all_zonelists(void *data) +static void __build_all_zonelists(void *data) { int nid; - int cpu; + int __maybe_unused cpu; pg_data_t *self = data; + unsigned long flags; + + /* + * The zonelist_update_seq must be acquired with irqsave because the + * reader can be invoked from IRQ with GFP_ATOMIC. + */ + write_seqlock_irqsave(&zonelist_update_seq, flags); + /* + * Also disable synchronous printk() to prevent any printk() from + * trying to hold port->lock, for + * tty_insert_flip_string_and_push_buffer() on other CPU might be + * calling kmalloc(GFP_ATOMIC | __GFP_NOWARN) with port->lock held. + */ + printk_deferred_enter(); #ifdef CONFIG_NUMA memset(node_load, 0, sizeof(node_load)); #endif + /* + * This node is hotadded and no memory is yet present. So just + * building zonelists is fine - no need to touch other nodes. + */ if (self && !node_online(self->node_id)) { build_zonelists(self); - build_zonelist_cache(self); - } + } else { + /* + * All possible nodes have pgdat preallocated + * in free_area_init + */ + for_each_node(nid) { + pg_data_t *pgdat = NODE_DATA(nid); - for_each_online_node(nid) { - pg_data_t *pgdat = NODE_DATA(nid); + build_zonelists(pgdat); + } - build_zonelists(pgdat); - build_zonelist_cache(pgdat); +#ifdef CONFIG_HAVE_MEMORYLESS_NODES + /* + * We now know the "local memory node" for each node-- + * i.e., the node of the first zone in the generic zonelist. + * Set up numa_mem percpu variable for on-line cpus. During + * boot, only the boot cpu should be on-line; we'll init the + * secondary cpus' numa_mem as they come on-line. During + * node/memory hotplug, we'll fixup all on-line cpus. + */ + for_each_online_cpu(cpu) + set_cpu_numa_mem(cpu, local_memory_node(cpu_to_node(cpu))); +#endif } + printk_deferred_exit(); + write_sequnlock_irqrestore(&zonelist_update_seq, flags); +} + +static noinline void __init +build_all_zonelists_init(void) +{ + int cpu; + + __build_all_zonelists(NULL); + /* * Initialize the boot_pagesets that are going to be used * for bootstrapping processors. The real pagesets for @@ -3678,49 +5835,31 @@ static int __build_all_zonelists(void *data) * needs the percpu allocator in order to allocate its pagesets * (a chicken-egg dilemma). */ - for_each_possible_cpu(cpu) { - setup_pageset(&per_cpu(boot_pageset, cpu), 0); - -#ifdef CONFIG_HAVE_MEMORYLESS_NODES - /* - * We now know the "local memory node" for each node-- - * i.e., the node of the first zone in the generic zonelist. - * Set up numa_mem percpu variable for on-line cpus. During - * boot, only the boot cpu should be on-line; we'll init the - * secondary cpus' numa_mem as they come on-line. During - * node/memory hotplug, we'll fixup all on-line cpus. - */ - if (cpu_online(cpu)) - set_cpu_numa_mem(cpu, local_memory_node(cpu_to_node(cpu))); -#endif - } + for_each_possible_cpu(cpu) + per_cpu_pages_init(&per_cpu(boot_pageset, cpu), &per_cpu(boot_zonestats, cpu)); - return 0; + mminit_verify_zonelist(); + cpuset_init_current_mems_allowed(); } /* - * Called with zonelists_mutex held always * unless system_state == SYSTEM_BOOTING. + * + * __ref due to call of __init annotated helper build_all_zonelists_init + * [protected by SYSTEM_BOOTING]. */ -void __ref build_all_zonelists(pg_data_t *pgdat, struct zone *zone) +void __ref build_all_zonelists(pg_data_t *pgdat) { - set_zonelist_order(); + unsigned long vm_total_pages; if (system_state == SYSTEM_BOOTING) { - __build_all_zonelists(NULL); - mminit_verify_zonelist(); - cpuset_init_current_mems_allowed(); + build_all_zonelists_init(); } else { -#ifdef CONFIG_MEMORY_HOTPLUG - if (zone) - setup_zone_pageset(zone); -#endif - /* we have to stop all cpus to guarantee there is no user - of zonelist */ - stop_machine(__build_all_zonelists, pgdat, NULL); + __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 @@ -3733,278 +5872,29 @@ void __ref build_all_zonelists(pg_data_t *pgdat, struct zone *zone) else page_group_by_mobility_disabled = 0; - printk("Built %i zonelists in %s order, mobility grouping %s. " - "Total pages: %ld\n", - nr_online_nodes, - zonelist_order_name[current_zonelist_order], - page_group_by_mobility_disabled ? "off" : "on", - vm_total_pages); + pr_info("Built %u zonelists, mobility grouping %s. Total pages: %ld\n", + nr_online_nodes, + str_off_on(page_group_by_mobility_disabled), + vm_total_pages); #ifdef CONFIG_NUMA - printk("Policy zone: %s\n", zone_names[policy_zone]); -#endif -} - -/* - * Helper functions to size the waitqueue hash table. - * Essentially these want to choose hash table sizes sufficiently - * large so that collisions trying to wait on pages are rare. - * But in fact, the number of active page waitqueues on typical - * systems is ridiculously low, less than 200. So this is even - * conservative, even though it seems large. - * - * The constant PAGES_PER_WAITQUEUE specifies the ratio of pages to - * waitqueues, i.e. the size of the waitq table given the number of pages. - */ -#define PAGES_PER_WAITQUEUE 256 - -#ifndef CONFIG_MEMORY_HOTPLUG -static inline unsigned long wait_table_hash_nr_entries(unsigned long pages) -{ - unsigned long size = 1; - - pages /= PAGES_PER_WAITQUEUE; - - while (size < pages) - size <<= 1; - - /* - * Once we have dozens or even hundreds of threads sleeping - * on IO we've got bigger problems than wait queue collision. - * Limit the size of the wait table to a reasonable size. - */ - size = min(size, 4096UL); - - return max(size, 4UL); -} -#else -/* - * A zone's size might be changed by hot-add, so it is not possible to determine - * a suitable size for its wait_table. So we use the maximum size now. - * - * The max wait table size = 4096 x sizeof(wait_queue_head_t). ie: - * - * i386 (preemption config) : 4096 x 16 = 64Kbyte. - * ia64, x86-64 (no preemption): 4096 x 20 = 80Kbyte. - * ia64, x86-64 (preemption) : 4096 x 24 = 96Kbyte. - * - * The maximum entries are prepared when a zone's memory is (512K + 256) pages - * or more by the traditional way. (See above). It equals: - * - * i386, x86-64, powerpc(4K page size) : = ( 2G + 1M)byte. - * ia64(16K page size) : = ( 8G + 4M)byte. - * powerpc (64K page size) : = (32G +16M)byte. - */ -static inline unsigned long wait_table_hash_nr_entries(unsigned long pages) -{ - return 4096UL; -} + pr_info("Policy zone: %s\n", zone_names[policy_zone]); #endif - -/* - * This is an integer logarithm so that shifts can be used later - * to extract the more random high bits from the multiplicative - * hash function before the remainder is taken. - */ -static inline unsigned long wait_table_bits(unsigned long size) -{ - return ffz(~size); -} - -#define LONG_ALIGN(x) (((x)+(sizeof(long))-1)&~((sizeof(long))-1)) - -/* - * Check if a pageblock contains reserved pages - */ -static int pageblock_is_reserved(unsigned long start_pfn, unsigned long end_pfn) -{ - unsigned long pfn; - - for (pfn = start_pfn; pfn < end_pfn; pfn++) { - if (!pfn_valid_within(pfn) || PageReserved(pfn_to_page(pfn))) - return 1; - } - return 0; } -/* - * Mark a number of pageblocks as MIGRATE_RESERVE. The number - * of blocks reserved is based on min_wmark_pages(zone). The memory within - * the reserve will tend to store contiguous free pages. Setting min_free_kbytes - * higher will lead to a bigger reserve which will get freed as contiguous - * blocks as reclaim kicks in - */ -static void setup_zone_migrate_reserve(struct zone *zone) -{ - unsigned long start_pfn, pfn, end_pfn, block_end_pfn; - struct page *page; - unsigned long block_migratetype; - int reserve; - - /* - * Get the start pfn, end pfn and the number of blocks to reserve - * We have to be careful to be aligned to pageblock_nr_pages to - * make sure that we always check pfn_valid for the first page in - * the block. - */ - start_pfn = zone->zone_start_pfn; - end_pfn = zone_end_pfn(zone); - start_pfn = roundup(start_pfn, pageblock_nr_pages); - reserve = roundup(min_wmark_pages(zone), pageblock_nr_pages) >> - pageblock_order; - - /* - * Reserve blocks are generally in place to help high-order atomic - * allocations that are short-lived. A min_free_kbytes value that - * would result in more than 2 reserve blocks for atomic allocations - * is assumed to be in place to help anti-fragmentation for the - * future allocation of hugepages at runtime. - */ - reserve = min(2, reserve); - - for (pfn = start_pfn; pfn < end_pfn; pfn += pageblock_nr_pages) { - if (!pfn_valid(pfn)) - continue; - page = pfn_to_page(pfn); - - /* Watch out for overlapping nodes */ - if (page_to_nid(page) != zone_to_nid(zone)) - continue; - - block_migratetype = get_pageblock_migratetype(page); - - /* Only test what is necessary when the reserves are not met */ - if (reserve > 0) { - /* - * Blocks with reserved pages will never free, skip - * them. - */ - block_end_pfn = min(pfn + pageblock_nr_pages, end_pfn); - if (pageblock_is_reserved(pfn, block_end_pfn)) - continue; - - /* If this block is reserved, account for it */ - if (block_migratetype == MIGRATE_RESERVE) { - reserve--; - continue; - } - - /* Suitable for reserving if this block is movable */ - if (block_migratetype == MIGRATE_MOVABLE) { - set_pageblock_migratetype(page, - MIGRATE_RESERVE); - move_freepages_block(zone, page, - MIGRATE_RESERVE); - reserve--; - continue; - } - } - - /* - * If the reserve is met and this is a previous reserved block, - * take it back - */ - if (block_migratetype == MIGRATE_RESERVE) { - set_pageblock_migratetype(page, MIGRATE_MOVABLE); - move_freepages_block(zone, page, MIGRATE_MOVABLE); - } - } -} - -/* - * Initially all pages are reserved - free ones are freed - * up by free_all_bootmem() once the early boot process is - * done. Non-atomic initialization, single-pass. - */ -void __meminit memmap_init_zone(unsigned long size, int nid, unsigned long zone, - unsigned long start_pfn, enum memmap_context context) -{ - struct page *page; - unsigned long end_pfn = start_pfn + size; - unsigned long pfn; - struct zone *z; - - if (highest_memmap_pfn < end_pfn - 1) - highest_memmap_pfn = end_pfn - 1; - - z = &NODE_DATA(nid)->node_zones[zone]; - for (pfn = start_pfn; pfn < end_pfn; pfn++) { - /* - * 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)) - continue; - if (!early_pfn_in_nid(pfn, nid)) - continue; - } - page = pfn_to_page(pfn); - set_page_links(page, zone, nid, pfn); - mminit_verify_page_links(page, zone, nid, pfn); - init_page_count(page); - page_mapcount_reset(page); - page_nid_reset_last(page); - 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. Later some blocks near - * the start are marked MIGRATE_RESERVE by - * setup_zone_migrate_reserve() - * - * 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. - */ - if ((z->zone_start_pfn <= pfn) - && (pfn < zone_end_pfn(z)) - && !(pfn & (pageblock_nr_pages - 1))) - set_pageblock_migratetype(page, MIGRATE_MOVABLE); - - INIT_LIST_HEAD(&page->lru); -#ifdef WANT_PAGE_VIRTUAL - /* The shift won't overflow because ZONE_NORMAL is below 4G. */ - if (!is_highmem_idx(zone)) - set_page_address(page, __va(pfn << PAGE_SHIFT)); -#endif - } -} - -static void __meminit zone_init_free_lists(struct zone *zone) -{ - int order, t; - for_each_migratetype_order(order, t) { - INIT_LIST_HEAD(&zone->free_area[order].free_list[t]); - zone->free_area[order].nr_free = 0; - } -} - -#ifndef __HAVE_ARCH_MEMMAP_INIT -#define memmap_init(size, nid, zone, start_pfn) \ - memmap_init_zone((size), (nid), (zone), (start_pfn), MEMMAP_EARLY) -#endif - -static int __meminit zone_batchsize(struct zone *zone) +static int zone_batchsize(struct zone *zone) { #ifdef CONFIG_MMU int batch; /* - * The per-cpu-pages pools are set to around 1000th of the - * size of the zone. But no more than 1/2 of a meg. - * - * OK, so we don't know how big the cache is. So guess. + * The number of pages to batch allocate is either ~0.025% + * of the zone or 256KB, whichever is smaller. The batch + * size is striking a balance between allocation latency + * and zone lock contention. */ - batch = zone->managed_pages / 1024; - if (batch * PAGE_SIZE > 512 * 1024) - batch = (512 * 1024) / PAGE_SIZE; - batch /= 4; /* We effectively *= 4 below */ - if (batch < 1) - batch = 1; + batch = min(zone_managed_pages(zone) >> 12, SZ_256K / PAGE_SIZE); + if (batch <= 1) + return 1; /* * Clamp the batch to a 2^n - 1 value. Having a power @@ -4038,1202 +5928,274 @@ static int __meminit zone_batchsize(struct zone *zone) #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. - * - * Any new users of pcp->batch and pcp->high should ensure they can cope with - * those fields changing asynchronously (acording the the above rule). - * - * mutex_is_locked(&pcp_batch_high_lock) required when calling this function - * outside of boot time (or some other assurance that no concurrent updaters - * exist). - */ -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; -} - -/* a companion to pageset_set_high() */ -static void pageset_set_batch(struct per_cpu_pageset *p, unsigned long batch) -{ - pageset_update(&p->pcp, 6 * batch, max(1UL, 1 * batch)); -} - -static void pageset_init(struct per_cpu_pageset *p) -{ - struct per_cpu_pages *pcp; - int migratetype; - - memset(p, 0, sizeof(*p)); - - pcp = &p->pcp; - pcp->count = 0; - for (migratetype = 0; migratetype < MIGRATE_PCPTYPES; migratetype++) - INIT_LIST_HEAD(&pcp->lists[migratetype]); -} - -static void setup_pageset(struct per_cpu_pageset *p, unsigned long batch) +static int percpu_pagelist_high_fraction; +static int zone_highsize(struct zone *zone, int batch, int cpu_online, + int high_fraction) { - pageset_init(p); - pageset_set_batch(p, batch); -} - -/* - * pageset_set_high() sets the high water mark for hot per_cpu_pagelist - * to the value high for the pageset p. - */ -static void pageset_set_high(struct per_cpu_pageset *p, - unsigned long high) -{ - unsigned long batch = max(1UL, high / 4); - if ((high / 4) > (PAGE_SHIFT * 8)) - batch = PAGE_SHIFT * 8; - - pageset_update(&p->pcp, high, batch); -} - -static void __meminit pageset_set_high_and_batch(struct zone *zone, - struct per_cpu_pageset *pcp) -{ - if (percpu_pagelist_fraction) - pageset_set_high(pcp, - (zone->managed_pages / - percpu_pagelist_fraction)); - else - pageset_set_batch(pcp, zone_batchsize(zone)); -} - -static void __meminit zone_pageset_init(struct zone *zone, int cpu) -{ - struct per_cpu_pageset *pcp = per_cpu_ptr(zone->pageset, cpu); - - pageset_init(pcp); - pageset_set_high_and_batch(zone, pcp); -} - -static 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); -} - -/* - * Allocate per cpu pagesets and initialize them. - * Before this call only boot pagesets were available. - */ -void __init setup_per_cpu_pageset(void) -{ - struct zone *zone; - - for_each_populated_zone(zone) - setup_zone_pageset(zone); -} - -static noinline __init_refok -int zone_wait_table_init(struct zone *zone, unsigned long zone_size_pages) -{ - int i; - struct pglist_data *pgdat = zone->zone_pgdat; - size_t alloc_size; +#ifdef CONFIG_MMU + int high; + int nr_split_cpus; + unsigned long total_pages; - /* - * The per-page waitqueue mechanism uses hashed waitqueues - * per zone. - */ - zone->wait_table_hash_nr_entries = - wait_table_hash_nr_entries(zone_size_pages); - zone->wait_table_bits = - wait_table_bits(zone->wait_table_hash_nr_entries); - alloc_size = zone->wait_table_hash_nr_entries - * sizeof(wait_queue_head_t); - - if (!slab_is_available()) { - zone->wait_table = (wait_queue_head_t *) - alloc_bootmem_node_nopanic(pgdat, alloc_size); + if (!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 { /* - * This case means that a zone whose size was 0 gets new memory - * via memory hot-add. - * But it may be the case that a new node was hot-added. In - * this case vmalloc() will not be able to use this new node's - * memory - this wait_table must be initialized to use this new - * node itself as well. - * To use this new node's memory, further consideration will be - * necessary. + * If percpu_pagelist_high_fraction is configured, the high + * value is based on a fraction of the managed pages in the + * zone. */ - zone->wait_table = vmalloc(alloc_size); + total_pages = zone_managed_pages(zone) / high_fraction; } - if (!zone->wait_table) - return -ENOMEM; - for(i = 0; i < zone->wait_table_hash_nr_entries; ++i) - init_waitqueue_head(zone->wait_table + i); - - return 0; -} - -static __meminit void zone_pcp_init(struct zone *zone) -{ /* - * per cpu subsystem is not up at this point. The following code - * relies on the ability of the linker to provide the - * offset of a (static) per cpu variable into the per cpu area. + * 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 the high value + * across all online CPUs to mitigate the risk that reclaim is triggered + * prematurely due to pages stored on pcp lists. */ - zone->pageset = &boot_pageset; - - if (zone->present_pages) - printk(KERN_DEBUG " %s zone: %lu pages, LIFO batch:%u\n", - zone->name, zone->present_pages, - zone_batchsize(zone)); -} + 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; -int __meminit init_currently_empty_zone(struct zone *zone, - unsigned long zone_start_pfn, - unsigned long size, - enum memmap_context context) -{ - struct pglist_data *pgdat = zone->zone_pgdat; - int ret; - ret = zone_wait_table_init(zone, size); - if (ret) - return ret; - pgdat->nr_zones = zone_idx(zone) + 1; - - zone->zone_start_pfn = zone_start_pfn; - - mminit_dprintk(MMINIT_TRACE, "memmap_init", - "Initialising map node %d zone %lu pfns %lu -> %lu\n", - pgdat->node_id, - (unsigned long)zone_idx(zone), - zone_start_pfn, (zone_start_pfn + size)); - - zone_init_free_lists(zone); - - return 0; -} - -#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. - * Architectures may implement their own version but if add_active_range() - * was used and there are no special requirements, this is a convenient - * alternative - */ -int __meminit __early_pfn_to_nid(unsigned long pfn) -{ - unsigned long start_pfn, end_pfn; - int i, nid; /* - * NOTE: The following SMP-unsafe globals are only used early in boot - * when the kernel is running single-threaded. + * Ensure high is at least batch*4. The multiple is based on the + * historical relationship between high and batch. */ - static unsigned long __meminitdata last_start_pfn, last_end_pfn; - static int __meminitdata last_nid; - - if (last_start_pfn <= pfn && pfn < last_end_pfn) - return last_nid; - - for_each_mem_pfn_range(i, MAX_NUMNODES, &start_pfn, &end_pfn, &nid) - if (start_pfn <= pfn && pfn < end_pfn) { - last_start_pfn = start_pfn; - last_end_pfn = end_pfn; - last_nid = nid; - return nid; - } - /* This is a memory hole */ - return -1; -} -#endif /* CONFIG_HAVE_ARCH_EARLY_PFN_TO_NID */ + high = max(high, batch << 2); -int __meminit early_pfn_to_nid(unsigned long pfn) -{ - int nid; - - nid = __early_pfn_to_nid(pfn); - if (nid >= 0) - return nid; - /* just returns 0 */ + return high; +#else return 0; -} - -#ifdef CONFIG_NODES_SPAN_OTHER_NODES -bool __meminit early_pfn_in_nid(unsigned long pfn, int node) -{ - int nid; - - nid = __early_pfn_to_nid(pfn); - if (nid >= 0 && nid != node) - return false; - return true; -} #endif - -/** - * free_bootmem_with_active_regions - Call free_bootmem_node 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 free_bootmem_node - * - * If an architecture guarantees that all ranges registered with - * add_active_ranges() contain no holes and may be freed, this - * this function may be used instead of calling free_bootmem() 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) - free_bootmem_node(NODE_DATA(this_nid), - PFN_PHYS(start_pfn), - (end_pfn - start_pfn) << PAGE_SHIFT); - } } -/** - * 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. +/* + * 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. * - * If an architecture guarantees that all ranges registered with - * add_active_ranges() 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. - * @start_pfn: Passed by reference. On return, it will have the node start_pfn. - * @end_pfn: Passed by reference. On return, it will have the node end_pfn. + * 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, pcp->high_min and pcp->high_max + * 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. * - * It returns the start and end page frame of a node based on information - * provided by an arch calling add_active_range(). If called for a node - * with no available memory, a warning is printed and the start and end - * PFNs will be 0. + * mutex_is_locked(&pcp_batch_high_lock) required when calling this function + * outside of boot time (or some other assurance that no concurrent updaters + * exist). */ -void __meminit get_pfn_range_for_nid(unsigned int nid, - unsigned long *start_pfn, unsigned long *end_pfn) +static void pageset_update(struct per_cpu_pages *pcp, unsigned long high_min, + unsigned long high_max, unsigned long batch) { - unsigned long this_start_pfn, this_end_pfn; - int i; - - *start_pfn = -1UL; - *end_pfn = 0; - - for_each_mem_pfn_range(i, nid, &this_start_pfn, &this_end_pfn, NULL) { - *start_pfn = min(*start_pfn, this_start_pfn); - *end_pfn = max(*end_pfn, this_end_pfn); - } - - if (*start_pfn == -1UL) - *start_pfn = 0; + WRITE_ONCE(pcp->batch, batch); + WRITE_ONCE(pcp->high_min, high_min); + WRITE_ONCE(pcp->high_max, high_max); } -/* - * This finds a zone that can be used for ZONE_MOVABLE pages. The - * assumption is made that zones within a node are ordered in monotonic - * increasing memory addresses so that the "highest" populated zone is used - */ -static void __init find_usable_zone_for_movable(void) +static void per_cpu_pages_init(struct per_cpu_pages *pcp, struct per_cpu_zonestat *pzstats) { - int zone_index; - for (zone_index = MAX_NR_ZONES - 1; zone_index >= 0; zone_index--) { - if (zone_index == ZONE_MOVABLE) - continue; + int pindex; - if (arch_zone_highest_possible_pfn[zone_index] > - arch_zone_lowest_possible_pfn[zone_index]) - break; - } + memset(pcp, 0, sizeof(*pcp)); + memset(pzstats, 0, sizeof(*pzstats)); + + spin_lock_init(&pcp->lock); + for (pindex = 0; pindex < NR_PCP_LISTS; pindex++) + INIT_LIST_HEAD(&pcp->lists[pindex]); - VM_BUG_ON(zone_index == -1); - movable_zone = zone_index; + /* + * 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_min = BOOT_PAGESET_HIGH; + pcp->high_max = BOOT_PAGESET_HIGH; + pcp->batch = BOOT_PAGESET_BATCH; } -/* - * The zone ranges provided by the architecture do not include ZONE_MOVABLE - * because it is sized independent of architecture. Unlike the other zones, - * the starting point for ZONE_MOVABLE is not fixed. It may be different - * in each node depending on the size of each node and how evenly kernelcore - * is distributed. This helper function adjusts the zone ranges - * provided by the architecture for a given node by using the end of the - * highest usable zone for ZONE_MOVABLE. This preserves the assumption that - * zones within a node are in order of monotonic increases memory addresses - */ -static void __meminit adjust_zone_range_for_zone_movable(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) +static void __zone_set_pageset_high_and_batch(struct zone *zone, unsigned long high_min, + unsigned long high_max, unsigned long batch) { - /* Only adjust if ZONE_MOVABLE is on this node */ - if (zone_movable_pfn[nid]) { - /* Size ZONE_MOVABLE */ - if (zone_type == ZONE_MOVABLE) { - *zone_start_pfn = zone_movable_pfn[nid]; - *zone_end_pfn = min(node_end_pfn, - arch_zone_highest_possible_pfn[movable_zone]); - - /* Adjust for ZONE_MOVABLE starting within this range */ - } else if (*zone_start_pfn < zone_movable_pfn[nid] && - *zone_end_pfn > zone_movable_pfn[nid]) { - *zone_end_pfn = zone_movable_pfn[nid]; + struct per_cpu_pages *pcp; + int cpu; - /* Check if this whole range is within ZONE_MOVABLE */ - } else if (*zone_start_pfn >= zone_movable_pfn[nid]) - *zone_start_pfn = *zone_end_pfn; + for_each_possible_cpu(cpu) { + pcp = per_cpu_ptr(zone->per_cpu_pageset, cpu); + pageset_update(pcp, high_min, high_max, batch); } } /* - * Return the number of pages a zone spans in a node, including holes - * present_pages = zone_spanned_pages_in_node() - zone_absent_pages_in_node() - */ -static unsigned long __meminit zone_spanned_pages_in_node(int nid, - unsigned long zone_type, - unsigned long node_start_pfn, - unsigned long node_end_pfn, - unsigned long *ignored) -{ - unsigned long zone_start_pfn, zone_end_pfn; - - /* Get the start and end of the zone */ - zone_start_pfn = arch_zone_lowest_possible_pfn[zone_type]; - zone_end_pfn = arch_zone_highest_possible_pfn[zone_type]; - adjust_zone_range_for_zone_movable(nid, zone_type, - node_start_pfn, node_end_pfn, - &zone_start_pfn, &zone_end_pfn); - - /* Check that this node has pages within the zone's required range */ - if (zone_end_pfn < node_start_pfn || zone_start_pfn > node_end_pfn) - return 0; - - /* Move the zone boundaries inside the node if necessary */ - zone_end_pfn = min(zone_end_pfn, node_end_pfn); - zone_start_pfn = max(zone_start_pfn, node_start_pfn); - - /* Return the spanned pages */ - return zone_end_pfn - zone_start_pfn; -} - -/* - * Return the number of holes in a range on a node. If nid is MAX_NUMNODES, - * then all holes in the requested range will be accounted for. + * Calculate and set new high and batch values for all per-cpu pagesets of a + * zone based on the zone's size. */ -unsigned long __meminit __absent_pages_in_range(int nid, - unsigned long range_start_pfn, - unsigned long range_end_pfn) +static void zone_set_pageset_high_and_batch(struct zone *zone, int cpu_online) { - unsigned long nr_absent = range_end_pfn - range_start_pfn; - unsigned long start_pfn, end_pfn; - int i; + int new_high_min, new_high_max, new_batch; - for_each_mem_pfn_range(i, nid, &start_pfn, &end_pfn, NULL) { - start_pfn = clamp(start_pfn, range_start_pfn, range_end_pfn); - end_pfn = clamp(end_pfn, range_start_pfn, range_end_pfn); - nr_absent -= end_pfn - start_pfn; + new_batch = zone_batchsize(zone); + if (percpu_pagelist_high_fraction) { + new_high_min = zone_highsize(zone, new_batch, cpu_online, + percpu_pagelist_high_fraction); + /* + * PCP high is tuned manually, disable auto-tuning via + * setting high_min and high_max to the manual value. + */ + new_high_max = new_high_min; + } else { + new_high_min = zone_highsize(zone, new_batch, cpu_online, 0); + new_high_max = zone_highsize(zone, new_batch, cpu_online, + MIN_PERCPU_PAGELIST_HIGH_FRACTION); } - return nr_absent; -} -/** - * absent_pages_in_range - Return number of page frames in holes within a range - * @start_pfn: The start PFN to start searching for holes - * @end_pfn: The end PFN to stop searching for holes - * - * It returns the number of pages frames in memory holes within a range. - */ -unsigned long __init absent_pages_in_range(unsigned long start_pfn, - unsigned long end_pfn) -{ - return __absent_pages_in_range(MAX_NUMNODES, start_pfn, end_pfn); -} - -/* Return the number of page frames in holes in a zone on a node */ -static unsigned long __meminit 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 zone_low = arch_zone_lowest_possible_pfn[zone_type]; - unsigned long zone_high = arch_zone_highest_possible_pfn[zone_type]; - unsigned long zone_start_pfn, zone_end_pfn; - - zone_start_pfn = clamp(node_start_pfn, zone_low, zone_high); - zone_end_pfn = clamp(node_end_pfn, zone_low, zone_high); + if (zone->pageset_high_min == new_high_min && + zone->pageset_high_max == new_high_max && + zone->pageset_batch == new_batch) + return; - adjust_zone_range_for_zone_movable(nid, zone_type, - node_start_pfn, node_end_pfn, - &zone_start_pfn, &zone_end_pfn); - return __absent_pages_in_range(nid, zone_start_pfn, zone_end_pfn); -} + zone->pageset_high_min = new_high_min; + zone->pageset_high_max = new_high_max; + zone->pageset_batch = new_batch; -#else /* CONFIG_HAVE_MEMBLOCK_NODE_MAP */ -static inline unsigned long __meminit zone_spanned_pages_in_node(int nid, - unsigned long zone_type, - unsigned long node_start_pfn, - unsigned long node_end_pfn, - unsigned long *zones_size) -{ - return zones_size[zone_type]; + __zone_set_pageset_high_and_batch(zone, new_high_min, new_high_max, + new_batch); } -static inline unsigned long __meminit 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) +void __meminit setup_zone_pageset(struct zone *zone) { - if (!zholes_size) - return 0; - - return zholes_size[zone_type]; -} + int cpu; -#endif /* CONFIG_HAVE_MEMBLOCK_NODE_MAP */ + /* Size may be 0 on !SMP && !NUMA */ + if (sizeof(struct per_cpu_zonestat) > 0) + zone->per_cpu_zonestats = alloc_percpu(struct per_cpu_zonestat); -static void __meminit 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 realtotalpages, totalpages = 0; - enum zone_type i; + 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; - for (i = 0; i < MAX_NR_ZONES; i++) - totalpages += zone_spanned_pages_in_node(pgdat->node_id, i, - node_start_pfn, - node_end_pfn, - zones_size); - pgdat->node_spanned_pages = totalpages; + pcp = per_cpu_ptr(zone->per_cpu_pageset, cpu); + pzstats = per_cpu_ptr(zone->per_cpu_zonestats, cpu); + per_cpu_pages_init(pcp, pzstats); + } - realtotalpages = totalpages; - for (i = 0; i < MAX_NR_ZONES; i++) - realtotalpages -= - zone_absent_pages_in_node(pgdat->node_id, i, - node_start_pfn, node_end_pfn, - zholes_size); - pgdat->node_present_pages = realtotalpages; - printk(KERN_DEBUG "On node %d totalpages: %lu\n", pgdat->node_id, - realtotalpages); + zone_set_pageset_high_and_batch(zone, 0); } -#ifndef CONFIG_SPARSEMEM /* - * Calculate the size of the zone->blockflags rounded to an unsigned long - * Start by making sure zonesize is a multiple of pageblock_order by rounding - * up. Then use 1 NR_PAGEBLOCK_BITS worth of bits per pageblock, finally - * round what is now in bits to nearest long in bits, then return it in - * bytes. + * The zone indicated has a new number of managed_pages; batch sizes and percpu + * page high values need to be recalculated. */ -static unsigned long __init usemap_size(unsigned long zone_start_pfn, unsigned long zonesize) -{ - unsigned long usemapsize; - - zonesize += zone_start_pfn & (pageblock_nr_pages-1); - usemapsize = roundup(zonesize, pageblock_nr_pages); - usemapsize = usemapsize >> pageblock_order; - usemapsize *= NR_PAGEBLOCK_BITS; - usemapsize = roundup(usemapsize, 8 * sizeof(unsigned long)); - - return usemapsize / 8; -} - -static void __init setup_usemap(struct pglist_data *pgdat, - struct zone *zone, - unsigned long zone_start_pfn, - unsigned long zonesize) +static void zone_pcp_update(struct zone *zone, int cpu_online) { - unsigned long usemapsize = usemap_size(zone_start_pfn, zonesize); - zone->pageblock_flags = NULL; - if (usemapsize) - zone->pageblock_flags = alloc_bootmem_node_nopanic(pgdat, - usemapsize); + mutex_lock(&pcp_batch_high_lock); + zone_set_pageset_high_and_batch(zone, cpu_online); + mutex_unlock(&pcp_batch_high_lock); } -#else -static inline void setup_usemap(struct pglist_data *pgdat, struct zone *zone, - unsigned long zone_start_pfn, unsigned long zonesize) {} -#endif /* CONFIG_SPARSEMEM */ -#ifdef CONFIG_HUGETLB_PAGE_SIZE_VARIABLE - -/* Initialise the number of pages represented by NR_PAGEBLOCK_BITS */ -void __init set_pageblock_order(void) +static void zone_pcp_update_cacheinfo(struct zone *zone, unsigned int cpu) { - unsigned int order; - - /* Check that pageblock_nr_pages has not already been setup */ - if (pageblock_order) - return; - - if (HPAGE_SHIFT > PAGE_SHIFT) - order = HUGETLB_PAGE_ORDER; - else - order = MAX_ORDER - 1; + struct per_cpu_pages *pcp; + struct cpu_cacheinfo *cci; + pcp = per_cpu_ptr(zone->per_cpu_pageset, cpu); + cci = get_cpu_cacheinfo(cpu); /* - * Assume the largest contiguous order of interest is a huge page. - * This value may be variable depending on boot parameters on IA64 and - * powerpc. + * If data cache slice of CPU is large enough, "pcp->batch" + * pages can be preserved in PCP before draining PCP for + * consecutive high-order pages freeing without allocation. + * This can reduce zone lock contention without hurting + * cache-hot pages sharing. */ - pageblock_order = order; + spin_lock(&pcp->lock); + if ((cci->per_cpu_data_slice_size >> PAGE_SHIFT) > 3 * pcp->batch) + pcp->flags |= PCPF_FREE_HIGH_BATCH; + else + pcp->flags &= ~PCPF_FREE_HIGH_BATCH; + spin_unlock(&pcp->lock); } -#else /* CONFIG_HUGETLB_PAGE_SIZE_VARIABLE */ -/* - * When CONFIG_HUGETLB_PAGE_SIZE_VARIABLE is not set, set_pageblock_order() - * is unused as pageblock_order is set at compile-time. See - * include/linux/pageblock-flags.h for the values of pageblock_order based on - * the kernel config - */ -void __init set_pageblock_order(void) +void setup_pcp_cacheinfo(unsigned int cpu) { -} - -#endif /* CONFIG_HUGETLB_PAGE_SIZE_VARIABLE */ - -static unsigned long __paginginit calc_memmap_size(unsigned long spanned_pages, - unsigned long present_pages) -{ - unsigned long pages = spanned_pages; - - /* - * Provide a more accurate estimation if there are holes within - * the zone and SPARSEMEM is in use. If there are holes within the - * zone, each populated memory region may cost us one or two extra - * memmap pages due to alignment because memmap pages for each - * populated regions may not naturally algined on page boundary. - * So the (present_pages >> 4) heuristic is a tradeoff for that. - */ - if (spanned_pages > present_pages + (present_pages >> 4) && - IS_ENABLED(CONFIG_SPARSEMEM)) - pages = present_pages; + struct zone *zone; - return PAGE_ALIGN(pages * sizeof(struct page)) >> PAGE_SHIFT; + for_each_populated_zone(zone) + zone_pcp_update_cacheinfo(zone, cpu); } /* - * Set up the zone data structures: - * - mark all pages reserved - * - mark all memory queues empty - * - clear the memory bitmaps - * - * NOTE: pgdat should get zeroed by caller. + * Allocate per cpu pagesets and initialize them. + * Before this call only boot pagesets were available. */ -static void __paginginit free_area_init_core(struct pglist_data *pgdat, - unsigned long node_start_pfn, unsigned long node_end_pfn, - unsigned long *zones_size, unsigned long *zholes_size) +void __init setup_per_cpu_pageset(void) { - enum zone_type j; - int nid = pgdat->node_id; - unsigned long zone_start_pfn = pgdat->node_start_pfn; - int ret; - - pgdat_resize_init(pgdat); -#ifdef CONFIG_NUMA_BALANCING - spin_lock_init(&pgdat->numabalancing_migrate_lock); - pgdat->numabalancing_migrate_nr_pages = 0; - pgdat->numabalancing_migrate_next_window = jiffies; -#endif - init_waitqueue_head(&pgdat->kswapd_wait); - init_waitqueue_head(&pgdat->pfmemalloc_wait); - pgdat_page_cgroup_init(pgdat); - - for (j = 0; j < MAX_NR_ZONES; j++) { - struct zone *zone = pgdat->node_zones + j; - unsigned long size, realsize, freesize, memmap_pages; - - size = zone_spanned_pages_in_node(nid, j, node_start_pfn, - node_end_pfn, zones_size); - realsize = freesize = size - zone_absent_pages_in_node(nid, j, - node_start_pfn, - node_end_pfn, - zholes_size); - - /* - * Adjust freesize so that it accounts for how much memory - * is used by this zone for memmap. This affects the watermark - * and per-cpu initialisations - */ - memmap_pages = calc_memmap_size(size, realsize); - 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); - } else - printk(KERN_WARNING - " %s zone: %lu 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); - } + struct pglist_data *pgdat; + struct zone *zone; + int __maybe_unused cpu; - if (!is_highmem_idx(j)) - nr_kernel_pages += freesize; - /* Charge for highmem memmap if there are enough kernel pages */ - else if (nr_kernel_pages > memmap_pages * 2) - nr_kernel_pages -= memmap_pages; - nr_all_pages += freesize; + for_each_populated_zone(zone) + setup_zone_pageset(zone); - zone->spanned_pages = size; - zone->present_pages = realsize; - /* - * Set an approximate value for lowmem here, it will be adjusted - * when the bootmem allocator frees pages into the buddy system. - * And all highmem pages will be managed by the buddy system. - */ - zone->managed_pages = is_highmem_idx(j) ? realsize : freesize; #ifdef CONFIG_NUMA - zone->node = nid; - zone->min_unmapped_pages = (freesize*sysctl_min_unmapped_ratio) - / 100; - zone->min_slab_pages = (freesize * sysctl_min_slab_ratio) / 100; -#endif - zone->name = zone_names[j]; - spin_lock_init(&zone->lock); - spin_lock_init(&zone->lru_lock); - zone_seqlock_init(zone); - zone->zone_pgdat = pgdat; - - zone_pcp_init(zone); - lruvec_init(&zone->lruvec); - if (!size) - continue; - - set_pageblock_order(); - setup_usemap(pgdat, zone, zone_start_pfn, size); - ret = init_currently_empty_zone(zone, zone_start_pfn, - size, MEMMAP_EARLY); - BUG_ON(ret); - memmap_init(size, nid, j, zone_start_pfn); - zone_start_pfn += size; - } -} - -static void __init_refok alloc_node_mem_map(struct pglist_data *pgdat) -{ - /* Skip empty nodes */ - if (!pgdat->node_spanned_pages) - return; - -#ifdef CONFIG_FLAT_NODE_MEM_MAP - /* ia64 gets its own node_mem_map, before this, without bootmem */ - if (!pgdat->node_mem_map) { - unsigned long size, start, end; - struct page *map; - - /* - * The zone's endpoints aren't required to be MAX_ORDER - * aligned but the node_mem_map endpoints must be in order - * for the buddy allocator to function correctly. - */ - start = pgdat->node_start_pfn & ~(MAX_ORDER_NR_PAGES - 1); - end = pgdat_end_pfn(pgdat); - end = ALIGN(end, MAX_ORDER_NR_PAGES); - size = (end - start) * sizeof(struct page); - map = alloc_remap(pgdat->node_id, size); - if (!map) - map = alloc_bootmem_node_nopanic(pgdat, size); - pgdat->node_mem_map = map + (pgdat->node_start_pfn - start); - } -#ifndef CONFIG_NEED_MULTIPLE_NODES /* - * With no DISCONTIG, the global mem_map is just set as node 0's + * 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. */ - if (pgdat == NODE_DATA(0)) { - mem_map = NODE_DATA(0)->node_mem_map; -#ifdef CONFIG_HAVE_MEMBLOCK_NODE_MAP - if (page_to_pfn(mem_map) != pgdat->node_start_pfn) - mem_map -= (pgdat->node_start_pfn - ARCH_PFN_OFFSET); -#endif /* CONFIG_HAVE_MEMBLOCK_NODE_MAP */ + 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 -#endif /* CONFIG_FLAT_NODE_MEM_MAP */ -} - -void __paginginit free_area_init_node(int nid, unsigned long *zones_size, - unsigned long node_start_pfn, unsigned long *zholes_size) -{ - 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->classzone_idx); - - pgdat->node_id = nid; - pgdat->node_start_pfn = node_start_pfn; - init_zone_allows_reclaim(nid); -#ifdef CONFIG_HAVE_MEMBLOCK_NODE_MAP - get_pfn_range_for_nid(nid, &start_pfn, &end_pfn); -#endif - calculate_node_totalpages(pgdat, start_pfn, end_pfn, - zones_size, zholes_size); - - alloc_node_mem_map(pgdat); -#ifdef CONFIG_FLAT_NODE_MEM_MAP - printk(KERN_DEBUG "free_area_init_node: node %d, pgdat %08lx, node_mem_map %08lx\n", - nid, (unsigned long)pgdat, - (unsigned long)pgdat->node_mem_map); -#endif - - free_area_init_core(pgdat, start_pfn, end_pfn, - zones_size, zholes_size); -} - -#ifdef CONFIG_HAVE_MEMBLOCK_NODE_MAP - -#if MAX_NUMNODES > 1 -/* - * Figure out the number of possible node ids. - */ -void __init setup_nr_node_ids(void) -{ - unsigned int node; - unsigned int highest = 0; - - for_each_node_mask(node, node_possible_map) - highest = node; - nr_node_ids = highest + 1; -} -#endif - -/** - * node_map_pfn_alignment - determine the maximum internode alignment - * - * This function should be called after node map is populated and sorted. - * It calculates the maximum power of two alignment which can distinguish - * all the nodes. - * - * For example, if all nodes are 1GiB and aligned to 1GiB, the return value - * would indicate 1GiB alignment with (1 << (30 - PAGE_SHIFT)). If the - * nodes are shifted by 256MiB, 256MiB. Note that if only the last node is - * shifted, 1GiB is enough and this function will indicate so. - * - * This is used to test whether pfn -> nid mapping of the chosen memory - * model has fine enough granularity to avoid incorrect mapping for the - * populated node map. - * - * Returns the determined alignment in pfn's. 0 if there is no alignment - * requirement (single node). - */ -unsigned long __init node_map_pfn_alignment(void) -{ - unsigned long accl_mask = 0, last_end = 0; - unsigned long start, end, mask; - int last_nid = -1; - int i, nid; - - for_each_mem_pfn_range(i, MAX_NUMNODES, &start, &end, &nid) { - if (!start || last_nid < 0 || last_nid == nid) { - last_nid = nid; - last_end = end; - continue; - } - - /* - * Start with a mask granular enough to pin-point to the - * start pfn and tick off bits one-by-one until it becomes - * too coarse to separate the current node from the last. - */ - mask = ~((1 << __ffs(start)) - 1); - while (mask && last_end <= (start & (mask << 1))) - mask <<= 1; - - /* accumulate all internode masks */ - accl_mask |= mask; - } - - /* convert mask to number of pages */ - 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) { - printk(KERN_WARNING - "Could not find start_pfn for node %d\n", nid); - return 0; - } - return min_pfn; + for_each_online_pgdat(pgdat) + pgdat->per_cpu_nodestats = + alloc_percpu(struct per_cpu_nodestat); } -/** - * find_min_pfn_with_active_regions - Find the minimum PFN registered - * - * It returns the minimum PFN based on information provided via - * add_active_range(). - */ -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. - * Populate N_MEMORY for calculating usable_nodes. - */ -static unsigned long __init early_calculate_totalpages(void) -{ - unsigned long totalpages = 0; - unsigned long start_pfn, end_pfn; - int i, nid; - - for_each_mem_pfn_range(i, MAX_NUMNODES, &start_pfn, &end_pfn, &nid) { - unsigned long pages = end_pfn - start_pfn; - - totalpages += pages; - if (pages) - node_set_state(nid, N_MEMORY); - } - return totalpages; -} - -/* - * Find the PFN the Movable zone begins in each node. Kernel memory - * is spread evenly between nodes as long as the nodes have enough - * memory. When they don't, some nodes will have more kernelcore than - * others - */ -static void __init find_zone_movable_pfns_for_nodes(void) +__meminit void zone_pcp_init(struct zone *zone) { - int i, nid; - unsigned long usable_startpfn; - unsigned long kernelcore_node, kernelcore_remaining; - /* save the state before borrow the nodemask */ - nodemask_t saved_node_state = node_states[N_MEMORY]; - unsigned long totalpages = early_calculate_totalpages(); - int usable_nodes = nodes_weight(node_states[N_MEMORY]); - - /* - * If movablecore was specified, calculate what size of - * kernelcore that corresponds so that memory usable for - * any allocation type is evenly spread. If both kernelcore - * and movablecore are specified, then the value of kernelcore - * will be used for required_kernelcore if it's greater than - * what movablecore would have allowed. - */ - if (required_movablecore) { - unsigned long corepages; - - /* - * Round-up so that ZONE_MOVABLE is at least as large as what - * was requested by the user - */ - required_movablecore = - roundup(required_movablecore, MAX_ORDER_NR_PAGES); - corepages = totalpages - required_movablecore; - - required_kernelcore = max(required_kernelcore, corepages); - } - - /* If kernelcore was not specified, there is no ZONE_MOVABLE */ - if (!required_kernelcore) - goto out; - - /* usable_startpfn is the lowest possible pfn ZONE_MOVABLE can be at */ - find_usable_zone_for_movable(); - usable_startpfn = arch_zone_lowest_possible_pfn[movable_zone]; - -restart: - /* Spread kernelcore memory as evenly as possible throughout nodes */ - kernelcore_node = required_kernelcore / usable_nodes; - for_each_node_state(nid, N_MEMORY) { - unsigned long start_pfn, end_pfn; - - /* - * Recalculate kernelcore_node if the division per node - * now exceeds what is necessary to satisfy the requested - * amount of memory for the kernel - */ - if (required_kernelcore < kernelcore_node) - kernelcore_node = required_kernelcore / usable_nodes; - - /* - * As the map is walked, we track how much memory is usable - * by the kernel using kernelcore_remaining. When it is - * 0, the rest of the node is usable by ZONE_MOVABLE - */ - kernelcore_remaining = kernelcore_node; - - /* Go through each range of PFNs within this node */ - for_each_mem_pfn_range(i, nid, &start_pfn, &end_pfn, NULL) { - unsigned long size_pages; - - start_pfn = max(start_pfn, zone_movable_pfn[nid]); - if (start_pfn >= end_pfn) - continue; - - /* Account for what is only usable for kernelcore */ - if (start_pfn < usable_startpfn) { - unsigned long kernel_pages; - kernel_pages = min(end_pfn, usable_startpfn) - - start_pfn; - - kernelcore_remaining -= min(kernel_pages, - kernelcore_remaining); - required_kernelcore -= min(kernel_pages, - required_kernelcore); - - /* Continue if range is now fully accounted */ - if (end_pfn <= usable_startpfn) { - - /* - * Push zone_movable_pfn to the end so - * that if we have to rebalance - * kernelcore across nodes, we will - * not double account here - */ - zone_movable_pfn[nid] = end_pfn; - continue; - } - start_pfn = usable_startpfn; - } - - /* - * The usable PFN range for ZONE_MOVABLE is from - * start_pfn->end_pfn. Calculate size_pages as the - * number of pages used as kernelcore - */ - size_pages = end_pfn - start_pfn; - if (size_pages > kernelcore_remaining) - size_pages = kernelcore_remaining; - zone_movable_pfn[nid] = start_pfn + size_pages; - - /* - * Some kernelcore has been met, update counts and - * break if the kernelcore for this node has been - * satisified - */ - required_kernelcore -= min(required_kernelcore, - size_pages); - kernelcore_remaining -= size_pages; - if (!kernelcore_remaining) - break; - } - } - /* - * If there is still required_kernelcore, we do another pass with one - * less node in the count. This will push zone_movable_pfn[nid] further - * along on the nodes that still have memory until kernelcore is - * satisified + * per cpu subsystem is not up at this point. The following code + * relies on the ability of the linker to provide the + * offset of a (static) per cpu variable into the per cpu area. */ - usable_nodes--; - if (usable_nodes && required_kernelcore > usable_nodes) - goto restart; - - /* Align start of ZONE_MOVABLE on all nids to MAX_ORDER_NR_PAGES */ - for (nid = 0; nid < MAX_NUMNODES; nid++) - zone_movable_pfn[nid] = - roundup(zone_movable_pfn[nid], MAX_ORDER_NR_PAGES); - -out: - /* restore the node_state */ - node_states[N_MEMORY] = saved_node_state; -} - -/* Any regular or high memory on that node ? */ -static void check_for_memory(pg_data_t *pgdat, int nid) -{ - enum zone_type zone_type; - - if (N_MEMORY == N_NORMAL_MEMORY) - return; + zone->per_cpu_pageset = &boot_pageset; + zone->per_cpu_zonestats = &boot_zonestats; + zone->pageset_high_min = BOOT_PAGESET_HIGH; + zone->pageset_high_max = BOOT_PAGESET_HIGH; + zone->pageset_batch = BOOT_PAGESET_BATCH; - for (zone_type = 0; zone_type <= ZONE_MOVABLE - 1; zone_type++) { - struct zone *zone = &pgdat->node_zones[zone_type]; - if (zone->present_pages) { - node_set_state(nid, N_HIGH_MEMORY); - if (N_NORMAL_MEMORY != N_HIGH_MEMORY && - zone_type <= ZONE_NORMAL) - node_set_state(nid, N_NORMAL_MEMORY); - break; - } - } + if (populated_zone(zone)) + pr_debug(" %s zone: %lu pages, LIFO batch:%u\n", zone->name, + zone->present_pages, zone_batchsize(zone)); } -/** - * free_area_init_nodes - 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. - * Using the page ranges provided by add_active_range(), the size of each - * zone in each node and their holes is calculated. If the maximum PFN - * between two adjacent zones match, it is assumed that the zone is empty. - * For example, if arch_max_dma_pfn == arch_max_dma32_pfn, it is assumed - * that arch_max_dma32_pfn has no pages. It is also assumed that a zone - * 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) -{ - unsigned long start_pfn, end_pfn; - int i, nid; - - /* Record where the zone boundaries are */ - memset(arch_zone_lowest_possible_pfn, 0, - sizeof(arch_zone_lowest_possible_pfn)); - memset(arch_zone_highest_possible_pfn, 0, - sizeof(arch_zone_highest_possible_pfn)); - arch_zone_lowest_possible_pfn[0] = find_min_pfn_with_active_regions(); - arch_zone_highest_possible_pfn[0] = max_zone_pfn[0]; - for (i = 1; i < MAX_NR_ZONES; i++) { - if (i == ZONE_MOVABLE) - continue; - arch_zone_lowest_possible_pfn[i] = - arch_zone_highest_possible_pfn[i-1]; - arch_zone_highest_possible_pfn[i] = - max(max_zone_pfn[i], arch_zone_lowest_possible_pfn[i]); - } - arch_zone_lowest_possible_pfn[ZONE_MOVABLE] = 0; - arch_zone_highest_possible_pfn[ZONE_MOVABLE] = 0; - - /* Find the PFNs that ZONE_MOVABLE begins at in each node */ - memset(zone_movable_pfn, 0, sizeof(zone_movable_pfn)); - find_zone_movable_pfns_for_nodes(); - - /* Print out the zone ranges */ - printk("Zone ranges:\n"); - for (i = 0; i < MAX_NR_ZONES; i++) { - if (i == ZONE_MOVABLE) - continue; - printk(KERN_CONT " %-8s ", zone_names[i]); - if (arch_zone_lowest_possible_pfn[i] == - arch_zone_highest_possible_pfn[i]) - printk(KERN_CONT "empty\n"); - else - printk(KERN_CONT "[mem %0#10lx-%0#10lx]\n", - arch_zone_lowest_possible_pfn[i] << PAGE_SHIFT, - (arch_zone_highest_possible_pfn[i] - << PAGE_SHIFT) - 1); - } - - /* Print out the PFNs ZONE_MOVABLE begins at in each node */ - printk("Movable zone start for each node\n"); - for (i = 0; i < MAX_NUMNODES; i++) { - if (zone_movable_pfn[i]) - printk(" Node %d: %#010lx\n", i, - zone_movable_pfn[i] << PAGE_SHIFT); - } - - /* Print out the early node map */ - printk("Early memory node ranges\n"); - for_each_mem_pfn_range(i, MAX_NUMNODES, &start_pfn, &end_pfn, &nid) - printk(" node %3d: [mem %#010lx-%#010lx]\n", nid, - start_pfn << PAGE_SHIFT, (end_pfn << PAGE_SHIFT) - 1); - - /* Initialise every node */ - mminit_verify_pageflags_layout(); - setup_nr_node_ids(); - 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); - - /* Any memory on that node */ - if (pgdat->node_present_pages) - node_set_state(nid, N_MEMORY); - check_for_memory(pgdat, nid); - } -} - -static int __init cmdline_parse_core(char *p, unsigned long *core) -{ - unsigned long long coremem; - if (!p) - return -EINVAL; - - coremem = memparse(p, &p); - *core = coremem >> PAGE_SHIFT; - - /* Paranoid check that UL is enough for the coremem value */ - WARN_ON((coremem >> PAGE_SHIFT) > ULONG_MAX); - - return 0; -} - -/* - * kernelcore=size sets the amount of memory for use for allocations that - * cannot be reclaimed or migrated. - */ -static int __init cmdline_parse_kernelcore(char *p) -{ - return cmdline_parse_core(p, &required_kernelcore); -} - -/* - * movablecore=size sets the amount of memory for use for allocations that - * can be reclaimed or migrated. - */ -static int __init cmdline_parse_movablecore(char *p) -{ - return cmdline_parse_core(p, &required_movablecore); -} - -early_param("kernelcore", cmdline_parse_kernelcore); -early_param("movablecore", cmdline_parse_movablecore); - -#endif /* CONFIG_HAVE_MEMBLOCK_NODE_MAP */ +static void setup_per_zone_lowmem_reserve(void); void adjust_managed_page_count(struct page *page, long count) { - spin_lock(&managed_page_count_lock); - page_zone(page)->managed_pages += count; - totalram_pages += count; -#ifdef CONFIG_HIGHMEM - if (PageHighMem(page)) - totalhigh_pages += count; -#endif - spin_unlock(&managed_page_count_lock); + atomic_long_add(count, &page_zone(page)->managed_pages); + totalram_pages_add(count); + setup_per_zone_lowmem_reserve(); } EXPORT_SYMBOL(adjust_managed_page_count); -unsigned long free_reserved_area(void *start, void *end, int poison, char *s) +unsigned long free_reserved_area(void *start, void *end, int poison, const char *s) { void *pos; unsigned long pages = 0; @@ -5241,138 +6203,97 @@ unsigned long free_reserved_area(void *start, void *end, int poison, char *s) start = (void *)PAGE_ALIGN((unsigned long)start); end = (void *)((unsigned long)end & PAGE_MASK); for (pos = start; pos < end; pos += PAGE_SIZE, pages++) { + struct page *page = virt_to_page(pos); + void *direct_map_addr; + + /* + * 'direct_map_addr' might be different from 'pos' + * because some architectures' virt_to_page() + * work with aliases. Getting the direct map + * address ensures that we get a _writeable_ + * 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(pos, poison, PAGE_SIZE); - free_reserved_page(virt_to_page(pos)); + memset(direct_map_addr, poison, PAGE_SIZE); + + free_reserved_page(page); } if (pages && s) - pr_info("Freeing %s memory: %ldK (%p - %p)\n", - s, pages << (PAGE_SHIFT - 10), start, end); + pr_info("Freeing %s memory: %ldK\n", s, K(pages)); return pages; } -EXPORT_SYMBOL(free_reserved_area); -#ifdef CONFIG_HIGHMEM -void free_highmem_page(struct page *page) +void free_reserved_page(struct page *page) { - __free_reserved_page(page); - totalram_pages++; - page_zone(page)->managed_pages++; - totalhigh_pages++; + clear_page_tag_ref(page); + ClearPageReserved(page); + init_page_count(page); + __free_page(page); + adjust_managed_page_count(page, 1); } -#endif - +EXPORT_SYMBOL(free_reserved_page); -void __init mem_init_print_info(const char *str) +static int page_alloc_cpu_dead(unsigned int cpu) { - unsigned long physpages, codesize, datasize, rosize, bss_size; - unsigned long init_code_size, init_data_size; + struct zone *zone; - physpages = get_num_physpages(); - codesize = _etext - _stext; - datasize = _edata - _sdata; - rosize = __end_rodata - __start_rodata; - bss_size = __bss_stop - __bss_start; - init_data_size = __init_end - __init_begin; - init_code_size = _einittext - _sinittext; + lru_add_drain_cpu(cpu); + mlock_drain_remote(cpu); + drain_pages(cpu); /* - * Detect special cases and adjust section sizes accordingly: - * 1) .init.* may be embedded into .data sections - * 2) .init.text.* may be out of [__init_begin, __init_end], - * please refer to arch/tile/kernel/vmlinux.lds.S. - * 3) .rodata.* may be embedded into .text or .data sections. - */ -#define adj_init_size(start, end, size, pos, adj) \ - if (start <= pos && pos < end && size > adj) \ - size -= adj; - - adj_init_size(__init_begin, __init_end, init_data_size, - _sinittext, init_code_size); - adj_init_size(_stext, _etext, codesize, _sinittext, init_code_size); - adj_init_size(_sdata, _edata, datasize, __init_begin, init_data_size); - adj_init_size(_stext, _etext, codesize, __start_rodata, rosize); - adj_init_size(_sdata, _edata, datasize, __start_rodata, rosize); - -#undef adj_init_size - - printk("Memory: %luK/%luK available " - "(%luK kernel code, %luK rwdata, %luK rodata, " - "%luK init, %luK bss, %luK reserved" -#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) << (PAGE_SHIFT-10), -#ifdef CONFIG_HIGHMEM - totalhigh_pages << (PAGE_SHIFT-10), -#endif - str ? ", " : "", str ? str : ""); -} + * Spill the event counters of the dead processor + * into the current processors event counters. + * This artificially elevates the count of the current + * processor. + */ + vm_events_fold_cpu(cpu); -/** - * set_dma_reserve - set the specified number of pages reserved in the first zone - * @new_dma_reserve: The number of pages to mark reserved - * - * The per-cpu batchsize and zone watermarks are determined by present_pages. - * In the DMA zone, a significant percentage may be consumed by kernel image - * and other unfreeable allocations which can skew the watermarks badly. This - * function may optionally be used to account for unfreeable pages in the - * first zone (e.g., ZONE_DMA). The effect will be lower watermarks and - * smaller per-cpu batchsize. - */ -void __init set_dma_reserve(unsigned long new_dma_reserve) -{ - dma_reserve = new_dma_reserve; -} + /* + * Zero the differential counters of the dead processor + * so that the vm statistics are consistent. + * + * This is only okay since the processor is dead and cannot + * race with what we are doing. + */ + cpu_vm_stats_fold(cpu); -void __init free_area_init(unsigned long *zones_size) -{ - free_area_init_node(0, zones_size, - __pa(PAGE_OFFSET) >> PAGE_SHIFT, NULL); + for_each_populated_zone(zone) + zone_pcp_update(zone, 0); + + return 0; } -static int page_alloc_cpu_notify(struct notifier_block *self, - unsigned long action, void *hcpu) +static int page_alloc_cpu_online(unsigned int cpu) { - int cpu = (unsigned long)hcpu; - - if (action == CPU_DEAD || action == CPU_DEAD_FROZEN) { - lru_add_drain_cpu(cpu); - drain_pages(cpu); - - /* - * Spill the event counters of the dead processor - * into the current processors event counters. - * This artificially elevates the count of the current - * processor. - */ - vm_events_fold_cpu(cpu); + struct zone *zone; - /* - * Zero the differential counters of the dead processor - * so that the vm statistics are consistent. - * - * This is only okay since the processor is dead and cannot - * race with what we are doing. - */ - refresh_cpu_vm_stats(cpu); - } - return NOTIFY_OK; + for_each_populated_zone(zone) + zone_pcp_update(zone, 1); + return 0; } -void __init page_alloc_init(void) +void __init page_alloc_init_cpuhp(void) { - hotcpu_notifier(page_alloc_cpu_notify, 0); + int ret; + + ret = cpuhp_setup_state_nocalls(CPUHP_PAGE_ALLOC, + "mm/page_alloc:pcp", + page_alloc_cpu_online, + page_alloc_cpu_dead); + WARN_ON(ret < 0); } /* - * calculate_totalreserve_pages - called when sysctl_lower_zone_reserve_ratio + * calculate_totalreserve_pages - called when sysctl_lowmem_reserve_ratio * or min_free_kbytes changes. */ static void calculate_totalreserve_pages(void) @@ -5382,69 +6303,86 @@ static void calculate_totalreserve_pages(void) enum zone_type i, j; for_each_online_pgdat(pgdat) { + + pgdat->totalreserve_pages = 0; + for (i = 0; i < MAX_NR_ZONES; i++) { struct zone *zone = pgdat->node_zones + i; - unsigned long max = 0; + long max = 0; + unsigned long managed_pages = zone_managed_pages(zone); - /* Find valid and maximum lowmem_reserve in the zone */ - for (j = i; j < MAX_NR_ZONES; j++) { - if (zone->lowmem_reserve[j] > max) - max = zone->lowmem_reserve[j]; - } + /* + * lowmem_reserve[j] is monotonically non-decreasing + * in j for a given zone (see + * setup_per_zone_lowmem_reserve()). The maximum + * valid reserve lives at the highest index with a + * non-zero value, so scan backwards and stop at the + * first hit. + */ + for (j = MAX_NR_ZONES - 1; j > i; j--) { + if (!zone->lowmem_reserve[j]) + continue; + max = zone->lowmem_reserve[j]; + break; + } /* we treat the high watermark as reserved pages. */ max += high_wmark_pages(zone); - if (max > zone->managed_pages) - max = zone->managed_pages; + max = min_t(unsigned long, max, managed_pages); + + pgdat->totalreserve_pages += max; + reserve_pages += max; - /* - * Lowmem reserves are not available to - * GFP_HIGHUSER page cache allocations and - * kswapd tries to balance zones to their high - * watermark. As a result, neither should be - * regarded as dirtyable memory, to prevent a - * situation where reclaim has to clean pages - * in order to balance the zones. - */ - zone->dirty_balance_reserve = max; } } - dirty_balance_reserve = reserve_pages; totalreserve_pages = reserve_pages; + trace_mm_calculate_totalreserve_pages(totalreserve_pages); } /* * setup_per_zone_lowmem_reserve - called whenever - * sysctl_lower_zone_reserve_ratio changes. Ensures that each zone + * sysctl_lowmem_reserve_ratio changes. Ensures that each zone * has a correct pages reserved value, so an adequate number of * pages are left in the zone after a successful __alloc_pages(). */ static void setup_per_zone_lowmem_reserve(void) { struct pglist_data *pgdat; - enum zone_type j, idx; - + enum zone_type i, j; + /* + * For a given zone node_zones[i], lowmem_reserve[j] (j > i) + * represents how many pages in zone i must effectively be kept + * in reserve when deciding whether an allocation class that is + * allowed to allocate from zones up to j may fall back into + * zone i. + * + * As j increases, the allocation class can use a strictly larger + * set of fallback zones and therefore must not be allowed to + * deplete low zones more aggressively than a less flexible one. + * As a result, lowmem_reserve[j] is required to be monotonically + * non-decreasing in j for each zone i. Callers such as + * calculate_totalreserve_pages() rely on this monotonicity when + * selecting the maximum reserve entry. + */ 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->lowmem_reserve[j] = 0; - - idx = j; - while (idx) { - struct zone *lower_zone; - - idx--; - - if (sysctl_lowmem_reserve_ratio[idx] < 1) - sysctl_lowmem_reserve_ratio[idx] = 1; - - lower_zone = pgdat->node_zones + idx; - lower_zone->lowmem_reserve[j] = managed_pages / - sysctl_lowmem_reserve_ratio[idx]; - managed_pages += lower_zone->managed_pages; + 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; + + for (j = i + 1; j < MAX_NR_ZONES; j++) { + struct zone *upper_zone = &pgdat->node_zones[j]; + + managed_pages += zone_managed_pages(upper_zone); + + if (clear) + zone->lowmem_reserve[j] = 0; + else + zone->lowmem_reserve[j] = managed_pages / ratio; + trace_mm_setup_per_zone_lowmem_reserve(zone, upper_zone, + zone->lowmem_reserve[j]); } } } @@ -5460,45 +6398,56 @@ static void __setup_per_zone_wmarks(void) struct zone *zone; unsigned long flags; - /* Calculate total number of !ZONE_HIGHMEM pages */ + /* Calculate total number of !ZONE_HIGHMEM and !ZONE_MOVABLE pages */ for_each_zone(zone) { - if (!is_highmem(zone)) - lowmem_pages += zone->managed_pages; + if (!is_highmem(zone) && zone_idx(zone) != ZONE_MOVABLE) + lowmem_pages += zone_managed_pages(zone); } for_each_zone(zone) { u64 tmp; spin_lock_irqsave(&zone->lock, flags); - tmp = (u64)pages_min * zone->managed_pages; - do_div(tmp, lowmem_pages); - if (is_highmem(zone)) { + tmp = (u64)pages_min * zone_managed_pages(zone); + tmp = div64_ul(tmp, lowmem_pages); + if (is_highmem(zone) || zone_idx(zone) == ZONE_MOVABLE) { /* * __GFP_HIGH and PF_MEMALLOC allocations usually don't - * need highmem pages, so cap pages_min to a small - * value here. + * need highmem and movable zones pages, so cap pages_min + * to a small value here. * * The WMARK_HIGH-WMARK_LOW and (WMARK_LOW-WMARK_MIN) - * deltas controls asynch page reclaim, and so should - * not be capped for highmem. + * deltas control async page reclaim, and so should + * not be capped for highmem and movable zones. */ unsigned long min_pages; - min_pages = zone->managed_pages / 1024; + min_pages = zone_managed_pages(zone) / 1024; min_pages = clamp(min_pages, SWAP_CLUSTER_MAX, 128UL); - zone->watermark[WMARK_MIN] = min_pages; + zone->_watermark[WMARK_MIN] = min_pages; } else { /* * If it's a lowmem zone, reserve a number of pages * proportionate to the zone's size. */ - zone->watermark[WMARK_MIN] = tmp; + zone->_watermark[WMARK_MIN] = tmp; } - zone->watermark[WMARK_LOW] = min_wmark_pages(zone) + (tmp >> 2); - zone->watermark[WMARK_HIGH] = min_wmark_pages(zone) + (tmp >> 1); + /* + * Set the kswapd watermarks distance according to the + * scale factor in proportion to available memory, but + * ensure a minimum size on small systems. + */ + tmp = max_t(u64, tmp >> 2, + mult_frac(zone_managed_pages(zone), + watermark_scale_factor, 10000)); + + 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; + trace_mm_setup_per_zone_wmarks(zone); - setup_zone_migrate_reserve(zone); spin_unlock_irqrestore(&zone->lock, flags); } @@ -5515,62 +6464,29 @@ static void __setup_per_zone_wmarks(void) */ void setup_per_zone_wmarks(void) { - mutex_lock(&zonelists_mutex); - __setup_per_zone_wmarks(); - mutex_unlock(&zonelists_mutex); -} - -/* - * The inactive anon list should be small enough that the VM never has to - * do too much work, but large enough that each inactive page has a chance - * to be referenced again before it is swapped out. - * - * The inactive_anon ratio is the target ratio of ACTIVE_ANON to - * INACTIVE_ANON pages on this zone's LRU, maintained by the - * pageout code. A zone->inactive_ratio of 3 means 3:1 or 25% of - * the anonymous pages are kept on the inactive list. - * - * total target max - * memory ratio inactive anon - * ------------------------------------- - * 10MB 1 5MB - * 100MB 1 50MB - * 1GB 3 250MB - * 10GB 10 0.9GB - * 100GB 31 3GB - * 1TB 101 10GB - * 10TB 320 32GB - */ -static void __meminit calculate_zone_inactive_ratio(struct zone *zone) -{ - unsigned int gb, ratio; - - /* Zone size in gigabytes */ - gb = zone->managed_pages >> (30 - PAGE_SHIFT); - if (gb) - ratio = int_sqrt(10 * gb); - else - ratio = 1; - - zone->inactive_ratio = ratio; -} - -static void __meminit setup_per_zone_inactive_ratio(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) - calculate_zone_inactive_ratio(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: + * min_free_kbytes = 4 * sqrt(lowmem_kbytes), for better accuracy: * min_free_kbytes = sqrt(lowmem_kbytes * 16) * * which yields @@ -5587,7 +6503,7 @@ static void __meminit setup_per_zone_inactive_ratio(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; @@ -5595,33 +6511,46 @@ 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(); - setup_per_zone_inactive_ratio(); + +#ifdef CONFIG_NUMA + setup_min_unmapped_ratio(); + setup_min_slab_ratio(); +#endif + + khugepaged_min_free_kbytes_update(); + return 0; } -module_init(init_per_zone_wmark_min) +postcore_initcall(init_per_zone_wmark_min) /* - * min_free_kbytes_sysctl_handler - just a wrapper around proc_dointvec() so + * min_free_kbytes_sysctl_handler - just a wrapper around proc_dointvec() so * that we can call two helper functions whenever min_free_kbytes * changes. */ -int min_free_kbytes_sysctl_handler(ctl_table *table, int write, - void __user *buffer, size_t *length, loff_t *ppos) +static int min_free_kbytes_sysctl_handler(const struct ctl_table *table, int write, + void *buffer, size_t *length, loff_t *ppos) { - proc_dointvec(table, write, buffer, length, ppos); + int rc; + + rc = proc_dointvec_minmax(table, write, buffer, length, ppos); + if (rc) + return rc; + if (write) { user_min_free_kbytes = min_free_kbytes; setup_per_zone_wmarks(); @@ -5629,36 +6558,74 @@ int min_free_kbytes_sysctl_handler(ctl_table *table, int write, return 0; } +static int watermark_scale_factor_sysctl_handler(const struct ctl_table *table, int write, + void *buffer, size_t *length, loff_t *ppos) +{ + int rc; + + rc = proc_dointvec_minmax(table, write, buffer, length, ppos); + if (rc) + return rc; + + if (write) + setup_per_zone_wmarks(); + + return 0; +} + #ifdef CONFIG_NUMA -int sysctl_min_unmapped_ratio_sysctl_handler(ctl_table *table, int write, - void __user *buffer, size_t *length, loff_t *ppos) +static void setup_min_unmapped_ratio(void) { + pg_data_t *pgdat; struct zone *zone; + + for_each_online_pgdat(pgdat) + pgdat->min_unmapped_pages = 0; + + for_each_zone(zone) + zone->zone_pgdat->min_unmapped_pages += (zone_managed_pages(zone) * + sysctl_min_unmapped_ratio) / 100; +} + + +static int sysctl_min_unmapped_ratio_sysctl_handler(const struct ctl_table *table, int write, + void *buffer, size_t *length, loff_t *ppos) +{ int rc; rc = proc_dointvec_minmax(table, write, buffer, length, ppos); if (rc) return rc; - for_each_zone(zone) - zone->min_unmapped_pages = (zone->managed_pages * - sysctl_min_unmapped_ratio) / 100; + setup_min_unmapped_ratio(); + return 0; } -int sysctl_min_slab_ratio_sysctl_handler(ctl_table *table, int write, - void __user *buffer, size_t *length, loff_t *ppos) +static void setup_min_slab_ratio(void) { + pg_data_t *pgdat; struct zone *zone; + + for_each_online_pgdat(pgdat) + pgdat->min_slab_pages = 0; + + for_each_zone(zone) + zone->zone_pgdat->min_slab_pages += (zone_managed_pages(zone) * + sysctl_min_slab_ratio) / 100; +} + +static int sysctl_min_slab_ratio_sysctl_handler(const struct ctl_table *table, int write, + void *buffer, size_t *length, loff_t *ppos) +{ int rc; rc = proc_dointvec_minmax(table, write, buffer, length, ppos); if (rc) return rc; - for_each_zone(zone) - zone->min_slab_pages = (zone->managed_pages * - sysctl_min_slab_ratio) / 100; + setup_min_slab_ratio(); + return 0; } #endif @@ -5672,337 +6639,157 @@ int sysctl_min_slab_ratio_sysctl_handler(ctl_table *table, int write, * minimum watermarks. The lowmem reserve ratio can only make sense * if in function of the boot time zone sizes. */ -int lowmem_reserve_ratio_sysctl_handler(ctl_table *table, int write, - void __user *buffer, size_t *length, loff_t *ppos) +static int lowmem_reserve_ratio_sysctl_handler(const struct ctl_table *table, + int write, void *buffer, size_t *length, loff_t *ppos) { + int i; + proc_dointvec_minmax(table, write, buffer, length, ppos); + + for (i = 0; i < MAX_NR_ZONES; i++) { + if (sysctl_lowmem_reserve_ratio[i] < 1) + sysctl_lowmem_reserve_ratio[i] = 0; + } + 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 pagelist - * can have before it gets flushed back to buddy allocator. + * 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(ctl_table *table, int write, - void __user *buffer, size_t *length, loff_t *ppos) +static int percpu_pagelist_high_fraction_sysctl_handler(const struct ctl_table *table, + int write, void *buffer, size_t *length, loff_t *ppos) { struct zone *zone; - unsigned int cpu; + int old_percpu_pagelist_high_fraction; int ret; - ret = proc_dointvec_minmax(table, write, buffer, length, ppos); - if (!write || (ret < 0)) - return ret; - mutex_lock(&pcp_batch_high_lock); - for_each_populated_zone(zone) { - unsigned long high; - high = zone->managed_pages / percpu_pagelist_fraction; - for_each_possible_cpu(cpu) - pageset_set_high(per_cpu_ptr(zone->pageset, cpu), - high); - } - mutex_unlock(&pcp_batch_high_lock); - return 0; -} - -int hashdist = HASHDIST_DEFAULT; + old_percpu_pagelist_high_fraction = percpu_pagelist_high_fraction; -#ifdef CONFIG_NUMA -static int __init set_hashdist(char *str) -{ - if (!str) - return 0; - hashdist = simple_strtoul(str, &str, 0); - return 1; -} -__setup("hashdist=", set_hashdist); -#endif - -/* - * allocate a large system hash table from bootmem - * - it is assumed that the hash table must contain an exact power-of-2 - * quantity of entries - * - limit is the number of hash buckets, not the total allocation size - */ -void *__init alloc_large_system_hash(const char *tablename, - unsigned long bucketsize, - unsigned long numentries, - int scale, - int flags, - unsigned int *_hash_shift, - unsigned int *_hash_mask, - unsigned long low_limit, - unsigned long high_limit) -{ - unsigned long long max = high_limit; - unsigned long log2qty, size; - void *table = NULL; - - /* allow the kernel cmdline to have a say */ - if (!numentries) { - /* round applicable memory size up to nearest megabyte */ - numentries = nr_kernel_pages; - numentries += (1UL << (20 - PAGE_SHIFT)) - 1; - numentries >>= 20 - PAGE_SHIFT; - numentries <<= 20 - PAGE_SHIFT; - - /* limit to 1 bucket per 2^scale bytes of low memory */ - if (scale > PAGE_SHIFT) - numentries >>= (scale - PAGE_SHIFT); - else - numentries <<= (PAGE_SHIFT - scale); - - /* Make sure we've got at least a 0-order allocation.. */ - if (unlikely(flags & HASH_SMALL)) { - /* Makes no sense without HASH_EARLY */ - WARN_ON(!(flags & HASH_EARLY)); - if (!(numentries >> *_hash_shift)) { - numentries = 1UL << *_hash_shift; - BUG_ON(!numentries); - } - } else if (unlikely((numentries * bucketsize) < PAGE_SIZE)) - numentries = PAGE_SIZE / bucketsize; - } - numentries = roundup_pow_of_two(numentries); + ret = proc_dointvec_minmax(table, write, buffer, length, ppos); + if (!write || ret < 0) + goto out; - /* limit allocation size to 1/16 total memory by default */ - if (max == 0) { - max = ((unsigned long long)nr_all_pages << PAGE_SHIFT) >> 4; - do_div(max, bucketsize); + /* Sanity checking to avoid pcp imbalance */ + 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; } - max = min(max, 0x80000000ULL); - - if (numentries < low_limit) - numentries = low_limit; - if (numentries > max) - numentries = max; - - log2qty = ilog2(numentries); - - do { - size = bucketsize << log2qty; - if (flags & HASH_EARLY) - table = alloc_bootmem_nopanic(size); - else if (hashdist) - table = __vmalloc(size, GFP_ATOMIC, PAGE_KERNEL); - else { - /* - * If bucketsize is not a power-of-two, we may free - * some pages at the end of hash table which - * alloc_pages_exact() automatically does - */ - if (get_order(size) < MAX_ORDER) { - table = alloc_pages_exact(size, GFP_ATOMIC); - kmemleak_alloc(table, size, 1, GFP_ATOMIC); - } - } - } while (!table && size > PAGE_SIZE && --log2qty); - - if (!table) - panic("Failed to allocate %s hash table\n", tablename); - - printk(KERN_INFO "%s hash table entries: %ld (order: %d, %lu bytes)\n", - tablename, - (1UL << log2qty), - ilog2(size) - PAGE_SHIFT, - size); - - if (_hash_shift) - *_hash_shift = log2qty; - if (_hash_mask) - *_hash_mask = (1 << log2qty) - 1; - - return table; -} -/* Return a pointer to the bitmap storing bits affecting a block of pages */ -static inline unsigned long *get_pageblock_bitmap(struct zone *zone, - unsigned long pfn) -{ -#ifdef CONFIG_SPARSEMEM - return __pfn_to_section(pfn)->pageblock_flags; -#else - return zone->pageblock_flags; -#endif /* CONFIG_SPARSEMEM */ -} + /* No change? */ + if (percpu_pagelist_high_fraction == old_percpu_pagelist_high_fraction) + goto out; -static inline int pfn_to_bitidx(struct zone *zone, unsigned long pfn) -{ -#ifdef CONFIG_SPARSEMEM - pfn &= (PAGES_PER_SECTION-1); - return (pfn >> pageblock_order) * NR_PAGEBLOCK_BITS; -#else - pfn = pfn - round_down(zone->zone_start_pfn, pageblock_nr_pages); - return (pfn >> pageblock_order) * NR_PAGEBLOCK_BITS; -#endif /* CONFIG_SPARSEMEM */ + for_each_populated_zone(zone) + zone_set_pageset_high_and_batch(zone, 0); +out: + mutex_unlock(&pcp_batch_high_lock); + return ret; } -/** - * get_pageblock_flags_group - Return the requested group of flags for the pageblock_nr_pages block of pages - * @page: The page within the block of interest - * @start_bitidx: The first bit of interest to retrieve - * @end_bitidx: The last bit of interest - * returns pageblock_bits flags - */ -unsigned long get_pageblock_flags_group(struct page *page, - int start_bitidx, int end_bitidx) -{ - struct zone *zone; - unsigned long *bitmap; - unsigned long pfn, bitidx; - unsigned long flags = 0; - unsigned long value = 1; - - zone = page_zone(page); - pfn = page_to_pfn(page); - bitmap = get_pageblock_bitmap(zone, pfn); - bitidx = pfn_to_bitidx(zone, pfn); - - for (; start_bitidx <= end_bitidx; start_bitidx++, value <<= 1) - if (test_bit(bitidx + start_bitidx, bitmap)) - flags |= value; - - return flags; -} +static const struct ctl_table page_alloc_sysctl_table[] = { + { + .procname = "min_free_kbytes", + .data = &min_free_kbytes, + .maxlen = sizeof(min_free_kbytes), + .mode = 0644, + .proc_handler = min_free_kbytes_sysctl_handler, + .extra1 = SYSCTL_ZERO, + }, + { + .procname = "watermark_boost_factor", + .data = &watermark_boost_factor, + .maxlen = sizeof(watermark_boost_factor), + .mode = 0644, + .proc_handler = proc_dointvec_minmax, + .extra1 = SYSCTL_ZERO, + }, + { + .procname = "watermark_scale_factor", + .data = &watermark_scale_factor, + .maxlen = sizeof(watermark_scale_factor), + .mode = 0644, + .proc_handler = watermark_scale_factor_sysctl_handler, + .extra1 = SYSCTL_ONE, + .extra2 = SYSCTL_THREE_THOUSAND, + }, + { + .procname = "defrag_mode", + .data = &defrag_mode, + .maxlen = sizeof(defrag_mode), + .mode = 0644, + .proc_handler = proc_dointvec_minmax, + .extra1 = SYSCTL_ZERO, + .extra2 = SYSCTL_ONE, + }, + { + .procname = "percpu_pagelist_high_fraction", + .data = &percpu_pagelist_high_fraction, + .maxlen = sizeof(percpu_pagelist_high_fraction), + .mode = 0644, + .proc_handler = percpu_pagelist_high_fraction_sysctl_handler, + .extra1 = SYSCTL_ZERO, + }, + { + .procname = "lowmem_reserve_ratio", + .data = &sysctl_lowmem_reserve_ratio, + .maxlen = sizeof(sysctl_lowmem_reserve_ratio), + .mode = 0644, + .proc_handler = lowmem_reserve_ratio_sysctl_handler, + }, +#ifdef CONFIG_NUMA + { + .procname = "numa_zonelist_order", + .data = &numa_zonelist_order, + .maxlen = NUMA_ZONELIST_ORDER_LEN, + .mode = 0644, + .proc_handler = numa_zonelist_order_handler, + }, + { + .procname = "min_unmapped_ratio", + .data = &sysctl_min_unmapped_ratio, + .maxlen = sizeof(sysctl_min_unmapped_ratio), + .mode = 0644, + .proc_handler = sysctl_min_unmapped_ratio_sysctl_handler, + .extra1 = SYSCTL_ZERO, + .extra2 = SYSCTL_ONE_HUNDRED, + }, + { + .procname = "min_slab_ratio", + .data = &sysctl_min_slab_ratio, + .maxlen = sizeof(sysctl_min_slab_ratio), + .mode = 0644, + .proc_handler = sysctl_min_slab_ratio_sysctl_handler, + .extra1 = SYSCTL_ZERO, + .extra2 = SYSCTL_ONE_HUNDRED, + }, +#endif +}; -/** - * set_pageblock_flags_group - Set the requested group of flags for a pageblock_nr_pages block of pages - * @page: The page within the block of interest - * @start_bitidx: The first bit of interest - * @end_bitidx: The last bit of interest - * @flags: The flags to set - */ -void set_pageblock_flags_group(struct page *page, unsigned long flags, - int start_bitidx, int end_bitidx) +void __init page_alloc_sysctl_init(void) { - struct zone *zone; - unsigned long *bitmap; - unsigned long pfn, bitidx; - unsigned long value = 1; - - zone = page_zone(page); - pfn = page_to_pfn(page); - bitmap = get_pageblock_bitmap(zone, pfn); - bitidx = pfn_to_bitidx(zone, pfn); - VM_BUG_ON(!zone_spans_pfn(zone, pfn)); - - for (; start_bitidx <= end_bitidx; start_bitidx++, value <<= 1) - if (flags & value) - __set_bit(bitidx + start_bitidx, bitmap); - else - __clear_bit(bitidx + start_bitidx, bitmap); + register_sysctl_init("vm", page_alloc_sysctl_table); } -/* - * This function checks whether pageblock includes unmovable pages or not. - * If @count is not zero, it is okay to include less @count unmovable pages - * - * PageLRU check wihtout isolation or lru_lock could race so that - * MIGRATE_MOVABLE block might include unmovable pages. It means you can't - * expect this function should be exact. - */ -bool has_unmovable_pages(struct zone *zone, struct page *page, int count, - bool skip_hwpoisoned_pages) +#ifdef CONFIG_CONTIG_ALLOC +/* Usage: See admin-guide/dynamic-debug-howto.rst */ +static void alloc_contig_dump_pages(struct list_head *page_list) { - unsigned long pfn, iter, found; - int mt; + DEFINE_DYNAMIC_DEBUG_METADATA(descriptor, "migrate failure"); - /* - * For avoiding noise data, lru_add_drain_all() should be called - * If ZONE_MOVABLE, the zone never contains unmovable pages - */ - if (zone_idx(zone) == ZONE_MOVABLE) - return false; - mt = get_pageblock_migratetype(page); - if (mt == MIGRATE_MOVABLE || is_migrate_cma(mt)) - return false; - - pfn = page_to_pfn(page); - for (found = 0, iter = 0; iter < pageblock_nr_pages; iter++) { - unsigned long check = pfn + iter; - - if (!pfn_valid_within(check)) - continue; - - page = pfn_to_page(check); - /* - * 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->_count is zero at all time. - */ - if (!atomic_read(&page->_count)) { - 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 (skip_hwpoisoned_pages && PageHWPoison(page)) - continue; + if (DYNAMIC_DEBUG_BRANCH(descriptor)) { + struct page *page; - if (!PageLRU(page)) - found++; - /* - * If there are RECLAIMABLE pages, we need to check it. - * But now, memory offline itself doesn't call shrink_slab() - * 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. - */ - if (found > count) - return true; + dump_stack(); + list_for_each_entry(page, page_list, lru) + dump_page(page, "migration failure"); } - return false; -} - -bool is_pageblock_removable_nolock(struct page *page) -{ - struct zone *zone; - unsigned long pfn; - - /* - * We have to be careful here because we are iterating over memory - * sections which are not zone aware so we might end up outside of - * the zone but still within the section. - * We have to take care about the node as well. If the node is offline - * its NODE_DATA will be NULL - see page_zone. - */ - if (!node_online(page_to_nid(page))) - return false; - - zone = page_zone(page); - pfn = page_to_pfn(page); - if (!zone_spans_pfn(zone, pfn)) - return false; - - return !has_unmovable_pages(zone, page, 0, true); -} - -#ifdef CONFIG_CMA - -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) -{ - return ALIGN(pfn, max_t(unsigned long, MAX_ORDER_NR_PAGES, - pageblock_nr_pages)); } /* [start, end) must belong to a single zone. */ @@ -6010,12 +6797,17 @@ static 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 = cc->gfp_mask, + .reason = MR_CONTIG_RANGE, + }; - migrate_prep(); + lru_cache_disable(); while (pfn < end || !list_empty(&cc->migratepages)) { if (fatal_signal_pending(current)) { @@ -6025,15 +6817,13 @@ static int __alloc_contig_migrate_range(struct compact_control *cc, if (list_empty(&cc->migratepages)) { cc->nr_migratepages = 0; - pfn = isolate_migratepages_range(cc->zone, cc, - pfn, end, true); - 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; } @@ -6041,13 +6831,84 @@ 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, - 0, MIGRATE_SYNC, MR_CMA); + 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; } + + return (ret < 0) ? ret : 0; +} + +static void split_free_pages(struct list_head *list, gfp_t gfp_mask) +{ + int order; + + for (order = 0; order < NR_PAGE_ORDERS; order++) { + struct page *page, *next; + int nr_pages = 1 << order; + + list_for_each_entry_safe(page, next, &list[order], lru) { + int i; + + post_alloc_hook(page, order, gfp_mask); + set_page_refcounted(page); + if (!order) + continue; + + split_page(page, order); + + /* Add all subpages to the order-0 head, in sequence. */ + list_del(&page->lru); + for (i = 0; i < nr_pages; i++) + list_add_tail(&page[i].lru, &list[0]); + } + } +} + +static int __alloc_contig_verify_gfp_mask(gfp_t gfp_mask, gfp_t *gfp_cc_mask) +{ + const gfp_t reclaim_mask = __GFP_IO | __GFP_FS | __GFP_RECLAIM; + const gfp_t action_mask = __GFP_COMP | __GFP_RETRY_MAYFAIL | __GFP_NOWARN | + __GFP_ZERO | __GFP_ZEROTAGS | __GFP_SKIP_ZERO; + const gfp_t cc_action_mask = __GFP_RETRY_MAYFAIL | __GFP_NOWARN; + + /* + * We are given the range to allocate; node, mobility and placement + * hints are irrelevant at this point. We'll simply ignore them. + */ + gfp_mask &= ~(GFP_ZONEMASK | __GFP_RECLAIMABLE | __GFP_WRITE | + __GFP_HARDWALL | __GFP_THISNODE | __GFP_MOVABLE); + + /* + * We only support most reclaim flags (but not NOFAIL/NORETRY), and + * selected action flags. + */ + if (gfp_mask & ~(reclaim_mask | action_mask)) + return -EINVAL; + + /* + * Flags to control page compaction/migration/reclaim, to free up our + * page range. Migratable pages are movable, __GFP_MOVABLE is implied + * for them. + * + * Traditionally we always had __GFP_RETRY_MAYFAIL set, keep doing that + * to not degrade callers. + */ + *gfp_cc_mask = (gfp_mask & (reclaim_mask | cc_action_mask)) | + __GFP_MOVABLE | __GFP_RETRY_MAYFAIL; return 0; } @@ -6055,49 +6916,64 @@ 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 - * #MIGRATE_MOVABLE or #MIGRATE_CMA). All pageblocks - * in range must have the same migratetype and it must - * be either of the two. + * @alloc_flags: allocation information + * @gfp_mask: GFP mask. Node/zone/placement hints are ignored; only some + * action and reclaim modifiers are supported. Reclaim modifiers + * control allocation behavior during compaction/migration/reclaim. * - * The PFN range does not have to be pageblock or MAX_ORDER_NR_PAGES - * aligned, however it's the caller's responsibility to guarantee that - * we are the only thread that changes migrate type of pageblocks the - * pages fall in. + * The PFN range does not have to be pageblock aligned. The PFN range must + * belong to a single zone. * - * 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 + * be modified by others. * - * Returns zero on success or negative error code. On success all + * Return: zero on success or negative error code. On success all * pages which PFN is in [start, end) are allocated for the caller and * need to be freed with free_contig_range(). */ -int alloc_contig_range(unsigned long start, unsigned long end, - unsigned migratetype) +int alloc_contig_range_noprof(unsigned long start, unsigned long end, + acr_flags_t alloc_flags, gfp_t gfp_mask) { + const unsigned int order = ilog2(end - start); unsigned long outer_start, outer_end; - int ret = 0, order; + int ret = 0; struct compact_control cc = { .nr_migratepages = 0, .order = -1, .zone = page_zone(pfn_to_page(start)), - .sync = true, + .mode = MIGRATE_SYNC, .ignore_skip_hint = true, + .no_set_skip_hint = true, + .alloc_contig = true, }; INIT_LIST_HEAD(&cc.migratepages); + enum pb_isolate_mode mode = (alloc_flags & ACR_FLAGS_CMA) ? + PB_ISOLATE_MODE_CMA_ALLOC : + PB_ISOLATE_MODE_OTHER; + + /* + * In contrast to the buddy, we allow for orders here that exceed + * MAX_PAGE_ORDER, so we must manually make sure that we are not + * exceeding the maximum folio order. + */ + if (WARN_ON_ONCE((gfp_mask & __GFP_COMP) && order > MAX_FOLIO_ORDER)) + return -EINVAL; + + gfp_mask = current_gfp_context(gfp_mask); + if (__alloc_contig_verify_gfp_mask(gfp_mask, (gfp_t *)&cc.gfp_mask)) + return -EINVAL; /* * What we do here is we mark all pageblocks in range as * MIGRATE_ISOLATE. Because pageblock and max order pages may * 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 @@ -6110,18 +6986,39 @@ 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, - false); + ret = start_isolate_page_range(start, end, mode); if (ret) - return ret; + goto done; + + drain_all_pages(cc.zone); + /* + * In case of -EBUSY, we'd like to know which page causes problem. + * So, just fall through. test_pages_isolated() has a tracepoint + * which will report the busy page. + * + * It is possible that busy pages could become available before + * the call to test_pages_isolated, and the range will actually be + * allocated. So, if we fall through be sure to clear ret so that + * -EBUSY is not accidentally used or returned to caller. + */ ret = __alloc_contig_migrate_range(&cc, start, end); + if (ret && ret != -EBUSY) + goto done; + + /* + * When in-use hugetlb pages are migrated, they may simply be released + * back into the free hugepage pool instead of being returned to the + * buddy system. After the migration of in-use huge pages is completed, + * we will invoke replace_free_hugepage_folios() to ensure that these + * hugepages are properly released to the buddy system. + */ + ret = replace_free_hugepage_folios(start, end); if (ret) goto done; /* - * Pages from [start, end) are within a 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 @@ -6136,29 +7033,14 @@ int alloc_contig_range(unsigned long start, unsigned long end, * We don't have to hold zone->lock here because the pages are * isolated thus they won't get removed from buddy. */ - - lru_add_drain_all(); - drain_all_pages(); - - order = 0; - outer_start = start; - while (!PageBuddy(pfn_to_page(outer_start))) { - if (++order >= MAX_ORDER) { - ret = -EBUSY; - goto done; - } - outer_start &= ~0UL << order; - } + outer_start = find_large_buddy(start); /* Make sure the range is really isolated. */ - if (test_pages_isolated(outer_start, end, false)) { - pr_warn("alloc_contig_range test_pages_isolated(%lx, %lx) failed\n", - outer_start, end); + if (test_pages_isolated(outer_start, end, mode)) { ret = -EBUSY; goto done; } - /* Grab isolated pages from freelists. */ outer_end = isolate_freepages_range(&cc, outer_start, end); if (!outer_end) { @@ -6166,21 +7048,147 @@ int alloc_contig_range(unsigned long start, unsigned long end, goto done; } - /* Free head and tail (if any) */ - if (start != outer_start) - free_contig_range(outer_start, start - outer_start); - if (end != outer_end) - free_contig_range(end, outer_end - end); + if (!(gfp_mask & __GFP_COMP)) { + split_free_pages(cc.freepages, gfp_mask); + /* Free head and tail (if any) */ + if (start != outer_start) + free_contig_range(outer_start, start - outer_start); + if (end != outer_end) + free_contig_range(end, outer_end - end); + } else if (start == outer_start && end == outer_end && is_power_of_2(end - start)) { + struct page *head = pfn_to_page(start); + + check_new_pages(head, order); + prep_new_page(head, order, gfp_mask, 0); + set_page_refcounted(head); + } else { + ret = -EINVAL; + WARN(true, "PFN range: requested [%lu, %lu), allocated [%lu, %lu)\n", + start, end, outer_start, outer_end); + } done: - undo_isolate_page_range(pfn_max_align_down(start), - pfn_max_align_up(end), migratetype); + undo_isolate_page_range(start, end); return ret; } +EXPORT_SYMBOL(alloc_contig_range_noprof); + +static int __alloc_contig_pages(unsigned long start_pfn, + unsigned long nr_pages, gfp_t gfp_mask) +{ + unsigned long end_pfn = start_pfn + nr_pages; + + return alloc_contig_range_noprof(start_pfn, end_pfn, ACR_FLAGS_NONE, + gfp_mask); +} + +static bool pfn_range_valid_contig(struct zone *z, unsigned long start_pfn, + unsigned long nr_pages) +{ + unsigned long i, end_pfn = start_pfn + nr_pages; + struct page *page; + + for (i = start_pfn; i < end_pfn; i++) { + page = pfn_to_online_page(i); + if (!page) + return false; + + if (page_zone(page) != z) + return false; + + if (PageReserved(page)) + return false; + + if (PageHuge(page)) + return false; + } + return true; +} -void free_contig_range(unsigned long pfn, unsigned nr_pages) +static bool zone_spans_last_pfn(const struct zone *zone, + unsigned long start_pfn, unsigned long nr_pages) { - unsigned int count = 0; + unsigned long last_pfn = start_pfn + nr_pages - 1; + + return zone_spans_pfn(zone, last_pfn); +} + +/** + * alloc_contig_pages() -- tries to find and allocate contiguous range of pages + * @nr_pages: Number of contiguous pages to allocate + * @gfp_mask: GFP mask. Node/zone/placement hints limit the search; only some + * action and reclaim modifiers are supported. Reclaim modifiers + * control allocation behavior during compaction/migration/reclaim. + * @nid: Target node + * @nodemask: Mask for other possible nodes + * + * This routine is a wrapper around alloc_contig_range(). It scans over zones + * on an applicable zonelist to find a contiguous pfn range which can then be + * tried for allocation with alloc_contig_range(). This routine is intended + * 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 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. + * + * Return: pointer to contiguous pages on success, or NULL if not successful. + */ +struct page *alloc_contig_pages_noprof(unsigned long nr_pages, gfp_t gfp_mask, + int nid, nodemask_t *nodemask) +{ + unsigned long ret, pfn, flags; + struct zonelist *zonelist; + struct zone *zone; + struct zoneref *z; + + zonelist = node_zonelist(nid, gfp_mask); + for_each_zone_zonelist_nodemask(zone, z, zonelist, + gfp_zone(gfp_mask), nodemask) { + spin_lock_irqsave(&zone->lock, flags); + + pfn = ALIGN(zone->zone_start_pfn, nr_pages); + while (zone_spans_last_pfn(zone, pfn, nr_pages)) { + if (pfn_range_valid_contig(zone, pfn, nr_pages)) { + /* + * We release the zone lock here because + * alloc_contig_range() will also lock the zone + * at some point. If there's an allocation + * spinning on this lock, it may win the race + * and cause alloc_contig_range() to fail... + */ + spin_unlock_irqrestore(&zone->lock, flags); + ret = __alloc_contig_pages(pfn, nr_pages, + gfp_mask); + if (!ret) + return pfn_to_page(pfn); + spin_lock_irqsave(&zone->lock, flags); + } + pfn += nr_pages; + } + spin_unlock_irqrestore(&zone->lock, flags); + } + return NULL; +} +#endif /* CONFIG_CONTIG_ALLOC */ + +void free_contig_range(unsigned long pfn, unsigned long nr_pages) +{ + unsigned long count = 0; + struct folio *folio = pfn_folio(pfn); + + if (folio_test_large(folio)) { + int expected = folio_nr_pages(folio); + + if (nr_pages == expected) + folio_put(folio); + else + WARN(true, "PFN %lu: nr_pages %lu != expected %d\n", + pfn, nr_pages, expected); + return; + } for (; nr_pages--; pfn++) { struct page *page = pfn_to_page(pfn); @@ -6188,71 +7196,73 @@ void free_contig_range(unsigned long pfn, unsigned 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); } -#endif +EXPORT_SYMBOL(free_contig_range); -#ifdef CONFIG_MEMORY_HOTPLUG /* - * 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) { - unsigned cpu; mutex_lock(&pcp_batch_high_lock); - for_each_possible_cpu(cpu) - pageset_set_high_and_batch(zone, - per_cpu_ptr(zone->pageset, cpu)); + __zone_set_pageset_high_and_batch(zone, 0, 0, 1); + __drain_all_pages(zone, true); +} + +void zone_pcp_enable(struct zone *zone) +{ + __zone_set_pageset_high_and_batch(zone, zone->pageset_high_min, + zone->pageset_high_max, zone->pageset_batch); mutex_unlock(&pcp_batch_high_lock); } -#endif 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 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. + * + * Returns the number of managed (non-PageOffline()) pages in the range: the + * number of pages for which memory offlining code must adjust managed page + * counters using adjust_managed_page_count(). */ -void -__offline_isolated_pages(unsigned long start_pfn, unsigned long end_pfn) +unsigned long __offline_isolated_pages(unsigned long start_pfn, + unsigned long end_pfn) { + unsigned long already_offline = 0, flags; + unsigned long pfn = start_pfn; struct page *page; struct zone *zone; - int order, i; - unsigned long pfn; - unsigned long flags; - /* find the first valid pfn */ - for (pfn = start_pfn; pfn < end_pfn; pfn++) - if (pfn_valid(pfn)) - break; - if (pfn == end_pfn) - return; + unsigned int order; + + 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 @@ -6260,130 +7270,415 @@ __offline_isolated_pages(unsigned long start_pfn, unsigned long end_pfn) */ if (unlikely(!PageBuddy(page) && PageHWPoison(page))) { pfn++; - SetPageReserved(page); + 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)); + already_offline++; + pfn++; continue; } BUG_ON(page_count(page)); BUG_ON(!PageBuddy(page)); - order = page_order(page); -#ifdef CONFIG_DEBUG_VM - printk(KERN_INFO "remove from free list %lx %d %lx\n", - pfn, 1 << order, end_pfn); -#endif - list_del(&page->lru); - rmv_page_order(page); - zone->free_area[order].nr_free--; -#ifdef CONFIG_HIGHMEM - if (PageHighMem(page)) - totalhigh_pages -= 1 << order; -#endif - for (i = 0; i < (1 << order); i++) - SetPageReserved((page+i)); + VM_WARN_ON(get_pageblock_migratetype(page) != MIGRATE_ISOLATE); + order = buddy_order(page); + del_page_from_free_list(page, zone, order, MIGRATE_ISOLATE); pfn += (1 << order); } spin_unlock_irqrestore(&zone->lock, flags); + + return end_pfn - start_pfn - already_offline; } #endif +/* + * This function returns a stable result only if called under zone lock. + */ +bool is_free_buddy_page(const struct page *page) +{ + unsigned long pfn = page_to_pfn(page); + unsigned int order; + + for (order = 0; order < NR_PAGE_ORDERS; order++) { + const struct page *head = page - (pfn & ((1 << order) - 1)); + + if (PageBuddy(head) && + buddy_order_unsafe(head) >= order) + break; + } + + return order <= MAX_PAGE_ORDER; +} +EXPORT_SYMBOL(is_free_buddy_page); + #ifdef CONFIG_MEMORY_FAILURE -bool is_free_buddy_page(struct page *page) +static inline void add_to_free_list(struct page *page, struct zone *zone, + unsigned int order, int migratetype, + bool tail) +{ + __add_to_free_list(page, zone, order, migratetype, tail); + account_freepages(zone, 1 << order, migratetype); +} + +/* + * Break down a higher-order page in sub-pages, and keep our target out of + * buddy allocator. + */ +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; + + while (high > low) { + high--; + size >>= 1; + + if (target >= &page[size]) { + current_buddy = page; + page = page + size; + } else { + current_buddy = page + size; + } + + if (set_page_guard(zone, current_buddy, high)) + continue; + + add_to_free_list(current_buddy, zone, high, migratetype, false); + set_buddy_order(current_buddy, high); + } +} + +/* + * 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; - int order; + unsigned int order; + bool ret = false; spin_lock_irqsave(&zone->lock, flags); - for (order = 0; order < MAX_ORDER; order++) { + for (order = 0; order < NR_PAGE_ORDERS; order++) { struct page *page_head = page - (pfn & ((1 << order) - 1)); - - if (PageBuddy(page_head) && page_order(page_head) >= order) + 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, + migratetype); + break_down_buddy_pages(zone, page_head, page, 0, + page_order, migratetype); + SetPageHWPoisonTakenOff(page); + 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 flags; + bool ret = false; + + spin_lock_irqsave(&zone->lock, flags); + if (put_page_testzero(page)) { + unsigned long pfn = page_to_pfn(page); + int migratetype = get_pfnblock_migratetype(page, pfn); + + ClearPageHWPoisonTakenOff(page); + __free_one_page(page, pfn, zone, 0, migratetype, FPI_NONE); + if (TestClearPageHWPoison(page)) { + ret = true; + } + } + spin_unlock_irqrestore(&zone->lock, flags); - return order < MAX_ORDER; + return ret; } #endif -static const struct trace_print_flags pageflag_names[] = { - {1UL << PG_locked, "locked" }, - {1UL << PG_error, "error" }, - {1UL << PG_referenced, "referenced" }, - {1UL << PG_uptodate, "uptodate" }, - {1UL << PG_dirty, "dirty" }, - {1UL << PG_lru, "lru" }, - {1UL << PG_active, "active" }, - {1UL << PG_slab, "slab" }, - {1UL << PG_owner_priv_1, "owner_priv_1" }, - {1UL << PG_arch_1, "arch_1" }, - {1UL << PG_reserved, "reserved" }, - {1UL << PG_private, "private" }, - {1UL << PG_private_2, "private_2" }, - {1UL << PG_writeback, "writeback" }, -#ifdef CONFIG_PAGEFLAGS_EXTENDED - {1UL << PG_head, "head" }, - {1UL << PG_tail, "tail" }, -#else - {1UL << PG_compound, "compound" }, -#endif - {1UL << PG_swapcache, "swapcache" }, - {1UL << PG_mappedtodisk, "mappedtodisk" }, - {1UL << PG_reclaim, "reclaim" }, - {1UL << PG_swapbacked, "swapbacked" }, - {1UL << PG_unevictable, "unevictable" }, -#ifdef CONFIG_MMU - {1UL << PG_mlocked, "mlocked" }, -#endif -#ifdef CONFIG_ARCH_USES_PG_UNCACHED - {1UL << PG_uncached, "uncached" }, -#endif -#ifdef CONFIG_MEMORY_FAILURE - {1UL << PG_hwpoison, "hwpoison" }, -#endif -#ifdef CONFIG_TRANSPARENT_HUGEPAGE - {1UL << PG_compound_lock, "compound_lock" }, -#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 */ + +#ifdef CONFIG_UNACCEPTED_MEMORY + +static bool lazy_accept = true; -static void dump_page_flags(unsigned long flags) +static int __init accept_memory_parse(char *p) { - const char *delim = ""; - unsigned long mask; - int i; + if (!strcmp(p, "lazy")) { + lazy_accept = true; + return 0; + } else if (!strcmp(p, "eager")) { + lazy_accept = false; + return 0; + } else { + return -EINVAL; + } +} +early_param("accept_memory", accept_memory_parse); - BUILD_BUG_ON(ARRAY_SIZE(pageflag_names) != __NR_PAGEFLAGS); +static bool page_contains_unaccepted(struct page *page, unsigned int order) +{ + phys_addr_t start = page_to_phys(page); - printk(KERN_ALERT "page flags: %#lx(", flags); + return range_contains_unaccepted_memory(start, PAGE_SIZE << order); +} - /* remove zone id */ - flags &= (1UL << NR_PAGEFLAGS) - 1; +static void __accept_page(struct zone *zone, unsigned long *flags, + struct page *page) +{ + list_del(&page->lru); + account_freepages(zone, -MAX_ORDER_NR_PAGES, MIGRATE_MOVABLE); + __mod_zone_page_state(zone, NR_UNACCEPTED, -MAX_ORDER_NR_PAGES); + __ClearPageUnaccepted(page); + spin_unlock_irqrestore(&zone->lock, *flags); - for (i = 0; i < ARRAY_SIZE(pageflag_names) && flags; i++) { + accept_memory(page_to_phys(page), PAGE_SIZE << MAX_PAGE_ORDER); - mask = pageflag_names[i].mask; - if ((flags & mask) != mask) - continue; + __free_pages_ok(page, MAX_PAGE_ORDER, FPI_TO_TAIL); +} + +void accept_page(struct page *page) +{ + struct zone *zone = page_zone(page); + unsigned long flags; + + spin_lock_irqsave(&zone->lock, flags); + if (!PageUnaccepted(page)) { + spin_unlock_irqrestore(&zone->lock, flags); + return; + } + + /* Unlocks zone->lock */ + __accept_page(zone, &flags, page); +} + +static bool try_to_accept_memory_one(struct zone *zone) +{ + unsigned long flags; + struct page *page; - flags &= ~mask; - printk("%s%s", delim, pageflag_names[i].name); - delim = "|"; + spin_lock_irqsave(&zone->lock, flags); + page = list_first_entry_or_null(&zone->unaccepted_pages, + struct page, lru); + if (!page) { + spin_unlock_irqrestore(&zone->lock, flags); + return false; } - /* check for left over flags */ - if (flags) - printk("%s%#lx", delim, flags); + /* Unlocks zone->lock */ + __accept_page(zone, &flags, page); - printk(")\n"); + return true; } -void dump_page(struct page *page) +static bool cond_accept_memory(struct zone *zone, unsigned int order, + int alloc_flags) { - printk(KERN_ALERT - "page:%p count:%d mapcount:%d mapping:%p index:%#lx\n", - page, atomic_read(&page->_count), page_mapcount(page), - page->mapping, page->index); - dump_page_flags(page->flags); - mem_cgroup_print_bad_page(page); + long to_accept, wmark; + bool ret = false; + + if (list_empty(&zone->unaccepted_pages)) + return false; + + /* Bailout, since try_to_accept_memory_one() needs to take a lock */ + if (alloc_flags & ALLOC_TRYLOCK) + return false; + + wmark = promo_wmark_pages(zone); + + /* + * Watermarks have not been initialized yet. + * + * Accepting one MAX_ORDER page to ensure progress. + */ + if (!wmark) + return try_to_accept_memory_one(zone); + + /* How much to accept to get to promo watermark? */ + to_accept = wmark - + (zone_page_state(zone, NR_FREE_PAGES) - + __zone_watermark_unusable_free(zone, order, 0) - + zone_page_state(zone, NR_UNACCEPTED)); + + while (to_accept > 0) { + if (!try_to_accept_memory_one(zone)) + break; + ret = true; + to_accept -= MAX_ORDER_NR_PAGES; + } + + return ret; +} + +static bool __free_unaccepted(struct page *page) +{ + struct zone *zone = page_zone(page); + unsigned long flags; + + if (!lazy_accept) + return false; + + spin_lock_irqsave(&zone->lock, flags); + list_add_tail(&page->lru, &zone->unaccepted_pages); + account_freepages(zone, MAX_ORDER_NR_PAGES, MIGRATE_MOVABLE); + __mod_zone_page_state(zone, NR_UNACCEPTED, MAX_ORDER_NR_PAGES); + __SetPageUnaccepted(page); + spin_unlock_irqrestore(&zone->lock, flags); + + return true; +} + +#else + +static bool page_contains_unaccepted(struct page *page, unsigned int order) +{ + return false; +} + +static bool cond_accept_memory(struct zone *zone, unsigned int order, + int alloc_flags) +{ + return false; +} + +static bool __free_unaccepted(struct page *page) +{ + BUILD_BUG(); + return false; +} + +#endif /* CONFIG_UNACCEPTED_MEMORY */ + +struct page *alloc_frozen_pages_nolock_noprof(gfp_t gfp_flags, int nid, unsigned int order) +{ + /* + * Do not specify __GFP_DIRECT_RECLAIM, since direct claim is not allowed. + * Do not specify __GFP_KSWAPD_RECLAIM either, since wake up of kswapd + * is not safe in arbitrary context. + * + * These two are the conditions for gfpflags_allow_spinning() being true. + * + * Specify __GFP_NOWARN since failing alloc_pages_nolock() is not a reason + * to warn. Also warn would trigger printk() which is unsafe from + * various contexts. We cannot use printk_deferred_enter() to mitigate, + * since the running context is unknown. + * + * Specify __GFP_ZERO to make sure that call to kmsan_alloc_page() below + * is safe in any context. Also zeroing the page is mandatory for + * BPF use cases. + * + * Though __GFP_NOMEMALLOC is not checked in the code path below, + * specify it here to highlight that alloc_pages_nolock() + * doesn't want to deplete reserves. + */ + gfp_t alloc_gfp = __GFP_NOWARN | __GFP_ZERO | __GFP_NOMEMALLOC | __GFP_COMP + | gfp_flags; + unsigned int alloc_flags = ALLOC_TRYLOCK; + struct alloc_context ac = { }; + struct page *page; + + VM_WARN_ON_ONCE(gfp_flags & ~__GFP_ACCOUNT); + /* + * In PREEMPT_RT spin_trylock() will call raw_spin_lock() which is + * unsafe in NMI. If spin_trylock() is called from hard IRQ the current + * task may be waiting for one rt_spin_lock, but rt_spin_trylock() will + * mark the task as the owner of another rt_spin_lock which will + * confuse PI logic, so return immediately if called form hard IRQ or + * NMI. + * + * Note, irqs_disabled() case is ok. This function can be called + * from raw_spin_lock_irqsave region. + */ + if (IS_ENABLED(CONFIG_PREEMPT_RT) && (in_nmi() || in_hardirq())) + return NULL; + if (!pcp_allowed_order(order)) + return NULL; + + /* Bailout, since _deferred_grow_zone() needs to take a lock */ + if (deferred_pages_enabled()) + return NULL; + + if (nid == NUMA_NO_NODE) + nid = numa_node_id(); + + prepare_alloc_pages(alloc_gfp, order, nid, NULL, &ac, + &alloc_gfp, &alloc_flags); + + /* + * Best effort allocation from percpu free list. + * If it's empty attempt to spin_trylock zone->lock. + */ + page = get_page_from_freelist(alloc_gfp, order, alloc_flags, &ac); + + /* Unlike regular alloc_pages() there is no __alloc_pages_slowpath(). */ + + if (memcg_kmem_online() && page && (gfp_flags & __GFP_ACCOUNT) && + unlikely(__memcg_kmem_charge_page(page, alloc_gfp, order) != 0)) { + __free_frozen_pages(page, order, FPI_TRYLOCK); + page = NULL; + } + trace_mm_page_alloc(page, order, alloc_gfp, ac.migratetype); + kmsan_alloc_page(page, order, alloc_gfp); + return page; +} +/** + * alloc_pages_nolock - opportunistic reentrant allocation from any context + * @gfp_flags: GFP flags. Only __GFP_ACCOUNT allowed. + * @nid: node to allocate from + * @order: allocation order size + * + * Allocates pages of a given order from the given node. This is safe to + * call from any context (from atomic, NMI, and also reentrant + * allocator -> tracepoint -> alloc_pages_nolock_noprof). + * Allocation is best effort and to be expected to fail easily so nobody should + * rely on the success. Failures are not reported via warn_alloc(). + * See always fail conditions below. + * + * Return: allocated page or NULL on failure. NULL does not mean EBUSY or EAGAIN. + * It means ENOMEM. There is no reason to call it again and expect !NULL. + */ +struct page *alloc_pages_nolock_noprof(gfp_t gfp_flags, int nid, unsigned int order) +{ + struct page *page; + + page = alloc_frozen_pages_nolock_noprof(gfp_flags, nid, order); + if (page) + set_page_refcounted(page); + return page; } +EXPORT_SYMBOL_GPL(alloc_pages_nolock_noprof); |