// SPDX-License-Identifier: GPL-2.0-only/* * linux/mm/page_alloc.c * * Manages the free list, the system allocates free pages here. * Note that kmalloc() lives in slab.c * * Copyright (C) 1991, 1992, 1993, 1994 Linus Torvalds * Swap reorganised 29.12.95, Stephen Tweedie * Support of BIGMEM added by Gerhard Wichert, Siemens AG, July 1999 * Reshaped it to be a zoned allocator, Ingo Molnar, Red Hat, 1999 * Discontiguous memory support, Kanoj Sarcar, SGI, Nov 1999 * Zone balancing, Kanoj Sarcar, SGI, Jan 2000 * Per cpu hot/cold page lists, bulk allocation, Martin J. Bligh, Sept 2002 * (lots of bits borrowed from Ingo Molnar & Andrew Morton) */ #include <linux/stddef.h>#include <linux/mm.h>#include <linux/highmem.h>#include <linux/interrupt.h>#include <linux/jiffies.h>#include <linux/compiler.h>#include <linux/kernel.h>#include <linux/kasan.h>#include <linux/kmsan.h>#include <linux/module.h>#include <linux/suspend.h>#include <linux/ratelimit.h>#include <linux/oom.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/vmstat.h>#include <linux/fault-inject.h>#include <linux/compaction.h>#include <trace/events/kmem.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/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)) /* 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. */#define pcp_trylock_prepare(flags) do { } while (0)#define pcp_trylock_finish(flag) do { } while (0)#else /* UP spin_trylock always succeeds so disable IRQs to prevent re-entrancy. */#define pcp_trylock_prepare(flags) local_irq_save(flags)#define pcp_trylock_finish(flags) local_irq_restore(flags)#endif /* * Locking a pcp requires a PCP lookup followed by a spinlock. To avoid * a migration causing the wrong PCP to be locked and remote memory being * potentially allocated, pin the task to the CPU for the lookup+lock. * preempt_disable is used on !RT because it is faster than migrate_disable. * migrate_disable is used on RT because otherwise RT spinlock usage is * interfered with and a high priority task cannot preempt the allocator. */#ifndef CONFIG_PREEMPT_RT#define pcpu_task_pin() preempt_disable()#define pcpu_task_unpin() preempt_enable()#else#define pcpu_task_pin() migrate_disable()#define pcpu_task_unpin() migrate_enable()#endif /* * Generic helper to lookup and a per-cpu variable with an embedded spinlock. * Return value should be used with equivalent unlock helper. */#define pcpu_spin_lock(type, member, ptr) \({ \ type *_ret; \ pcpu_task_pin(); \ _ret = this_cpu_ptr(ptr); \ spin_lock(&_ret->member); \ _ret; \}) #define pcpu_spin_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_lock(ptr) \ pcpu_spin_lock(struct per_cpu_pages, lock, ptr) #define pcp_spin_trylock(ptr) \ pcpu_spin_trylock(struct per_cpu_pages, lock, ptr) #define pcp_spin_unlock(ptr) \ pcpu_spin_unlock(lock, ptr) #ifdef CONFIG_USE_PERCPU_NUMA_NODE_IDDEFINE_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. * It will not be defined when CONFIG_HAVE_MEMORYLESS_NODES is not defined. * Use the accessor functions set_numa_mem(), numa_mem_id() and cpu_to_mem() * defined in <linux/topology.h>. */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_ENTROPYvolatile unsigned long latent_entropy __latent_entropy;EXPORT_SYMBOL(latent_entropy);#endif /* * Array of node states. */nodemask_t node_states[NR_NODE_STATES] __read_mostly = { [N_POSSIBLE] = NODE_MASK_ALL, [N_ONLINE] = { { [0] = 1UL } },#ifndef CONFIG_NUMA [N_NORMAL_MEMORY] = { { [0] = 1UL } },#ifdef CONFIG_HIGHMEM [N_HIGH_MEMORY] = { { [0] = 1UL } },#endif [N_MEMORY] = { { [0] = 1UL } }, [N_CPU] = { { [0] = 1UL } },#endif /* NUMA */};EXPORT_SYMBOL(node_states); gfp_t gfp_allowed_mask __read_mostly = GFP_BOOT_MASK; #ifdef CONFIG_HUGETLB_PAGE_SIZE_VARIABLEunsigned int pageblock_order __read_mostly;#endif static void __free_pages_ok(struct page *page, unsigned int order, fpi_t fpi_flags); /* * results with 256, 32 in the lowmem_reserve sysctl: * 1G machine -> (16M dma, 800M-16M normal, 1G-800M high) * 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 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 */static int sysctl_lowmem_reserve_ratio[MAX_NR_ZONES] = {#ifdef CONFIG_ZONE_DMA [ZONE_DMA] = 256,#endif#ifdef CONFIG_ZONE_DMA32 [ZONE_DMA32] = 256,#endif [ZONE_NORMAL] = 32,#ifdef CONFIG_HIGHMEM [ZONE_HIGHMEM] = 0,#endif [ZONE_MOVABLE] = 0,}; char * const zone_names[MAX_NR_ZONES] = {#ifdef CONFIG_ZONE_DMA "DMA",#endif#ifdef CONFIG_ZONE_DMA32 "DMA32",#endif "Normal",#ifdef CONFIG_HIGHMEM "HighMem",#endif "Movable",#ifdef CONFIG_ZONE_DEVICE "Device",#endif}; const char * const migratetype_names[MIGRATE_TYPES] = { "Unmovable", "Movable", "Reclaimable", "HighAtomic",#ifdef CONFIG_CMA "CMA",#endif#ifdef CONFIG_MEMORY_ISOLATION "Isolate",#endif}; 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; /* movable_zone is the "real" zone pages in ZONE_MOVABLE are taken from */int movable_zone;EXPORT_SYMBOL(movable_zone); #if MAX_NUMNODES > 1unsigned 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);static bool __free_unaccepted(struct page *page); int page_group_by_mobility_disabled __read_mostly; #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);}#elsestatic 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;} /** * get_pfnblock_flags_mask - Return the requested group of flags for the pageblock_nr_pages block of pages * @page: The page within the block of interest * @pfn: The target page frame number * @mask: mask of bits that the caller is interested in * * Return: pageblock_bits flags */unsigned long get_pfnblock_flags_mask(const struct page *page, unsigned long pfn, unsigned long mask){ unsigned long *bitmap; unsigned long bitidx, word_bitidx; unsigned long word; bitmap = get_pageblock_bitmap(page, pfn); bitidx = pfn_to_bitidx(page, pfn); word_bitidx = bitidx / BITS_PER_LONG; bitidx &= (BITS_PER_LONG-1); /* * This races, without locks, with set_pfnblock_flags_mask(). Ensure * a consistent read of the memory array, so that results, even though * racy, are not corrupted. */ word = READ_ONCE(bitmap[word_bitidx]); return (word >> bitidx) & mask;} static __always_inline int get_pfnblock_migratetype(const struct page *page, unsigned long pfn){ return get_pfnblock_flags_mask(page, pfn, 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 * @flags: The flags to set * @pfn: The target page frame number * @mask: mask of bits that the caller is interested in */void set_pfnblock_flags_mask(struct page *page, unsigned long flags, unsigned long pfn, unsigned long mask){ unsigned long *bitmap; unsigned long bitidx, word_bitidx; unsigned long word; BUILD_BUG_ON(NR_PAGEBLOCK_BITS != 4); BUILD_BUG_ON(MIGRATE_TYPES > (1 << PB_migratetype_bits)); bitmap = get_pageblock_bitmap(page, pfn); bitidx = pfn_to_bitidx(page, pfn); word_bitidx = bitidx / BITS_PER_LONG; bitidx &= (BITS_PER_LONG-1); VM_BUG_ON_PAGE(!zone_spans_pfn(page_zone(page), pfn), page); mask <<= bitidx; flags <<= bitidx; word = READ_ONCE(bitmap[word_bitidx]); do { } while (!try_cmpxchg(&bitmap[word_bitidx], &word, (word & ~mask) | flags));} void set_pageblock_migratetype(struct page *page, int migratetype){ if (unlikely(page_group_by_mobility_disabled && migratetype < MIGRATE_PCPTYPES)) migratetype = MIGRATE_UNMOVABLE; set_pfnblock_flags_mask(page, (unsigned long)migratetype, page_to_pfn(page), MIGRATETYPE_MASK);} #ifdef CONFIG_DEBUG_VMstatic int page_outside_zone_boundaries(struct zone *zone, struct page *page){ int ret; unsigned seq; unsigned long pfn = page_to_pfn(page); unsigned long sp, start_pfn; do { seq = zone_span_seqbegin(zone); start_pfn = zone->zone_start_pfn; sp = zone->spanned_pages; ret = !zone_spans_pfn(zone, pfn); } while (zone_span_seqretry(zone, seq)); if (ret) 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;} /* * Temporary debugging check for pages not lying within a given zone. */static bool __maybe_unused bad_range(struct zone *zone, struct page *page){ if (page_outside_zone_boundaries(zone, page)) return true; if (zone != page_zone(page)) return true; return false;}#elsestatic inline bool __maybe_unused bad_range(struct zone *zone, struct page *page){ return false;}#endif static void bad_page(struct page *page, const char *reason){ static unsigned long resume; static unsigned long nr_shown; static unsigned long nr_unshown; /* * Allow a burst of 60 reports, then keep quiet for that minute; * or allow a steady drip of one report per second. */ if (nr_shown == 60) { if (time_before(jiffies, resume)) { nr_unshown++; goto out; } if (nr_unshown) { pr_alert( "BUG: Bad page state: %lu messages suppressed\n", nr_unshown); nr_unshown = 0; } nr_shown = 0; } if (nr_shown++ == 0) resume = jiffies + 60 * HZ; pr_alert("BUG: Bad page state in process %s pfn:%05lx\n", current->comm, page_to_pfn(page)); dump_page(page, reason); print_modules();Lines 1–500 of 7030. Load more
// SPDX-License-Identifier: GPL-2.0-only /* * linux/mm/page_alloc.c * * Manages the free list, the system allocates free pages here. * Note that kmalloc() lives in slab.c * * Copyright (C) 1991, 1992, 1993, 1994 Linus Torvalds * Swap reorganised 29.12.95, Stephen Tweedie * Support of BIGMEM added by Gerhard Wichert, Siemens AG, July 1999 * Reshaped it to be a zoned allocator, Ingo Molnar, Red Hat, 1999 * Discontiguous memory support, Kanoj Sarcar, SGI, Nov 1999 * Zone balancing, Kanoj Sarcar, SGI, Jan 2000 * Per cpu hot/cold page lists, bulk allocation, Martin J. Bligh, Sept 2002 * (lots of bits borrowed from Ingo Molnar & Andrew Morton) */ #include <linux/stddef.h> #include <linux/mm.h> #include <linux/highmem.h> #include <linux/interrupt.h> #include <linux/jiffies.h> #include <linux/compiler.h> #include <linux/kernel.h> #include <linux/kasan.h> #include <linux/kmsan.h> #include <linux/module.h> #include <linux/suspend.h> #include <linux/ratelimit.h> #include <linux/oom.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/vmstat.h> #include <linux/fault-inject.h> #include <linux/compaction.h> #include <trace/events/kmem.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/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)) /* 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. */ #define pcp_trylock_prepare(flags) do { } while (0) #define pcp_trylock_finish(flag) do { } while (0) #else /* UP spin_trylock always succeeds so disable IRQs to prevent re-entrancy. */ #define pcp_trylock_prepare(flags) local_irq_save(flags) #define pcp_trylock_finish(flags) local_irq_restore(flags) #endif /* * Locking a pcp requires a PCP lookup followed by a spinlock. To avoid * a migration causing the wrong PCP to be locked and remote memory being * potentially allocated, pin the task to the CPU for the lookup+lock. * preempt_disable is used on !RT because it is faster than migrate_disable. * migrate_disable is used on RT because otherwise RT spinlock usage is * interfered with and a high priority task cannot preempt the allocator. */ #ifndef CONFIG_PREEMPT_RT #define pcpu_task_pin() preempt_disable() #define pcpu_task_unpin() preempt_enable() #else #define pcpu_task_pin() migrate_disable() #define pcpu_task_unpin() migrate_enable() #endif /* * Generic helper to lookup and a per-cpu variable with an embedded spinlock. * Return value should be used with equivalent unlock helper. */ #define pcpu_spin_lock(type, member, ptr) \ ({ \ type *_ret; \ pcpu_task_pin(); \ _ret = this_cpu_ptr(ptr); \ spin_lock(&_ret->member); \ _ret; \ }) #define pcpu_spin_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_lock(ptr) \ pcpu_spin_lock(struct per_cpu_pages, lock, ptr) #define pcp_spin_trylock(ptr) \ pcpu_spin_trylock(struct per_cpu_pages, lock, ptr) #define pcp_spin_unlock(ptr) \ pcpu_spin_unlock(lock, ptr) #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. * It will not be defined when CONFIG_HAVE_MEMORYLESS_NODES is not defined. * Use the accessor functions set_numa_mem(), numa_mem_id() and cpu_to_mem() * defined in <linux/topology.h>. */ 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. */ nodemask_t node_states[NR_NODE_STATES] __read_mostly = { [N_POSSIBLE] = NODE_MASK_ALL, [N_ONLINE] = { { [0] = 1UL } }, #ifndef CONFIG_NUMA [N_NORMAL_MEMORY] = { { [0] = 1UL } }, #ifdef CONFIG_HIGHMEM [N_HIGH_MEMORY] = { { [0] = 1UL } }, #endif [N_MEMORY] = { { [0] = 1UL } }, [N_CPU] = { { [0] = 1UL } }, #endif /* NUMA */ }; EXPORT_SYMBOL(node_states); gfp_t gfp_allowed_mask __read_mostly = GFP_BOOT_MASK; #ifdef CONFIG_HUGETLB_PAGE_SIZE_VARIABLE unsigned int pageblock_order __read_mostly; #endif static void __free_pages_ok(struct page *page, unsigned int order, fpi_t fpi_flags); /* * results with 256, 32 in the lowmem_reserve sysctl: * 1G machine -> (16M dma, 800M-16M normal, 1G-800M high) * 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 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 */ static int sysctl_lowmem_reserve_ratio[MAX_NR_ZONES] = { #ifdef CONFIG_ZONE_DMA [ZONE_DMA] = 256, #endif #ifdef CONFIG_ZONE_DMA32 [ZONE_DMA32] = 256, #endif [ZONE_NORMAL] = 32, #ifdef CONFIG_HIGHMEM [ZONE_HIGHMEM] = 0, #endif [ZONE_MOVABLE] = 0, }; char * const zone_names[MAX_NR_ZONES] = { #ifdef CONFIG_ZONE_DMA "DMA", #endif #ifdef CONFIG_ZONE_DMA32 "DMA32", #endif "Normal", #ifdef CONFIG_HIGHMEM "HighMem", #endif "Movable", #ifdef CONFIG_ZONE_DEVICE "Device", #endif }; const char * const migratetype_names[MIGRATE_TYPES] = { "Unmovable", "Movable", "Reclaimable", "HighAtomic", #ifdef CONFIG_CMA "CMA", #endif #ifdef CONFIG_MEMORY_ISOLATION "Isolate", #endif }; 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; /* movable_zone is the "real" zone pages in ZONE_MOVABLE are taken from */ int movable_zone; EXPORT_SYMBOL(movable_zone); #if MAX_NUMNODES > 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); static bool __free_unaccepted(struct page *page); int page_group_by_mobility_disabled __read_mostly; #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; } /** * get_pfnblock_flags_mask - Return the requested group of flags for the pageblock_nr_pages block of pages * @page: The page within the block of interest * @pfn: The target page frame number * @mask: mask of bits that the caller is interested in * * Return: pageblock_bits flags */ unsigned long get_pfnblock_flags_mask(const struct page *page, unsigned long pfn, unsigned long mask) { unsigned long *bitmap; unsigned long bitidx, word_bitidx; unsigned long word; bitmap = get_pageblock_bitmap(page, pfn); bitidx = pfn_to_bitidx(page, pfn); word_bitidx = bitidx / BITS_PER_LONG; bitidx &= (BITS_PER_LONG-1); /* * This races, without locks, with set_pfnblock_flags_mask(). Ensure * a consistent read of the memory array, so that results, even though * racy, are not corrupted. */ word = READ_ONCE(bitmap[word_bitidx]); return (word >> bitidx) & mask; } static __always_inline int get_pfnblock_migratetype(const struct page *page, unsigned long pfn) { return get_pfnblock_flags_mask(page, pfn, 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 * @flags: The flags to set * @pfn: The target page frame number * @mask: mask of bits that the caller is interested in */ void set_pfnblock_flags_mask(struct page *page, unsigned long flags, unsigned long pfn, unsigned long mask) { unsigned long *bitmap; unsigned long bitidx, word_bitidx; unsigned long word; BUILD_BUG_ON(NR_PAGEBLOCK_BITS != 4); BUILD_BUG_ON(MIGRATE_TYPES > (1 << PB_migratetype_bits)); bitmap = get_pageblock_bitmap(page, pfn); bitidx = pfn_to_bitidx(page, pfn); word_bitidx = bitidx / BITS_PER_LONG; bitidx &= (BITS_PER_LONG-1); VM_BUG_ON_PAGE(!zone_spans_pfn(page_zone(page), pfn), page); mask <<= bitidx; flags <<= bitidx; word = READ_ONCE(bitmap[word_bitidx]); do { } while (!try_cmpxchg(&bitmap[word_bitidx], &word, (word & ~mask) | flags)); } void set_pageblock_migratetype(struct page *page, int migratetype) { if (unlikely(page_group_by_mobility_disabled && migratetype < MIGRATE_PCPTYPES)) migratetype = MIGRATE_UNMOVABLE; set_pfnblock_flags_mask(page, (unsigned long)migratetype, page_to_pfn(page), MIGRATETYPE_MASK); } #ifdef CONFIG_DEBUG_VM static int page_outside_zone_boundaries(struct zone *zone, struct page *page) { int ret; unsigned seq; unsigned long pfn = page_to_pfn(page); unsigned long sp, start_pfn; do { seq = zone_span_seqbegin(zone); start_pfn = zone->zone_start_pfn; sp = zone->spanned_pages; ret = !zone_spans_pfn(zone, pfn); } while (zone_span_seqretry(zone, seq)); if (ret) 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; } /* * Temporary debugging check for pages not lying within a given zone. */ static bool __maybe_unused bad_range(struct zone *zone, struct page *page) { if (page_outside_zone_boundaries(zone, page)) return true; if (zone != page_zone(page)) return true; return false; } #else static inline bool __maybe_unused bad_range(struct zone *zone, struct page *page) { return false; } #endif static void bad_page(struct page *page, const char *reason) { static unsigned long resume; static unsigned long nr_shown; static unsigned long nr_unshown; /* * Allow a burst of 60 reports, then keep quiet for that minute; * or allow a steady drip of one report per second. */ if (nr_shown == 60) { if (time_before(jiffies, resume)) { nr_unshown++; goto out; } if (nr_unshown) { pr_alert( "BUG: Bad page state: %lu messages suppressed\n", nr_unshown); nr_unshown = 0; } nr_shown = 0; } if (nr_shown++ == 0) resume = jiffies + 60 * HZ; pr_alert("BUG: Bad page state in process %s pfn:%05lx\n", current->comm, page_to_pfn(page)); dump_page(page, reason); print_modules();