/* * 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/swap.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/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/memory_hotplug.h>#include <linux/nodemask.h>#include <linux/vmalloc.h>#include <linux/vmstat.h>#include <linux/mempolicy.h>#include <linux/memremap.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_ext.h>#include <linux/debugobjects.h>#include <linux/kmemleak.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/migrate.h>#include <linux/hugetlb.h>#include <linux/sched/rt.h>#include <linux/sched/mm.h>#include <linux/page_owner.h>#include <linux/kthread.h>#include <linux/memcontrol.h>#include <linux/ftrace.h>#include <linux/nmi.h> #include <asm/sections.h>#include <asm/tlbflush.h>#include <asm/div64.h>#include "internal.h" /* prevent >1 _updater_ of zone percpu pageset ->high and ->batch fields */static DEFINE_MUTEX(pcp_batch_high_lock);#define MIN_PERCPU_PAGELIST_FRACTION (8) #ifdef CONFIG_USE_PERCPU_NUMA_NODE_IDDEFINE_PER_CPU(int, numa_node);EXPORT_PER_CPU_SYMBOL(numa_node);#endif #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_);int _node_numa_mem_[MAX_NUMNODES];#endif /* work_structs for global per-cpu drains */DEFINE_MUTEX(pcpu_drain_mutex);DEFINE_PER_CPU(struct work_struct, pcpu_drain); #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); /* 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;unsigned long totalcma_pages __read_mostly; int percpu_pagelist_fraction;gfp_t gfp_allowed_mask __read_mostly = GFP_BOOT_MASK; /* * A cached value of the page's pageblock's migratetype, used when the page is * put on a pcplist. Used to avoid the pageblock migratetype lookup when * freeing from pcplists in most cases, at the cost of possibly becoming stale. * Also the migratetype set in the page does not necessarily match the pcplist * index, e.g. page might have MIGRATE_CMA set but be on a pcplist with any * other index - this ensures that it will be put on the correct CMA freelist. */static inline int get_pcppage_migratetype(struct page *page){ return page->index;} static inline void set_pcppage_migratetype(struct page *page, int migratetype){ page->index = migratetype;} #ifdef CONFIG_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_IO | __GFP_FS);} bool pm_suspended_storage(void){ if ((gfp_allowed_mask & (__GFP_IO | __GFP_FS)) == (__GFP_IO | __GFP_FS)) return false; return true;}#endif /* CONFIG_PM_SLEEP */ #ifdef CONFIG_HUGETLB_PAGE_SIZE_VARIABLEunsigned int pageblock_order __read_mostly;#endif static void __free_pages_ok(struct page *page, unsigned int order); /* * 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 */int sysctl_lowmem_reserve_ratio[MAX_NR_ZONES-1] = {#ifdef CONFIG_ZONE_DMA 256,#endif#ifdef CONFIG_ZONE_DMA32 256,#endif#ifdef CONFIG_HIGHMEM 32,#endif 32,}; EXPORT_SYMBOL(totalram_pages); static 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}; char * const migratetype_names[MIGRATE_TYPES] = { "Unmovable", "Movable", "Reclaimable", "HighAtomic",#ifdef CONFIG_CMA "CMA",#endif#ifdef CONFIG_MEMORY_ISOLATION "Isolate",#endif}; compound_page_dtor * const compound_page_dtors[] = { NULL, free_compound_page,#ifdef CONFIG_HUGETLB_PAGE free_huge_page,#endif#ifdef CONFIG_TRANSPARENT_HUGEPAGE free_transhuge_page,#endif}; int min_free_kbytes = 1024;int user_min_free_kbytes = -1;int watermark_scale_factor = 10; static unsigned long __meminitdata nr_kernel_pages;static unsigned long __meminitdata nr_all_pages;static unsigned long __meminitdata dma_reserve; #ifdef CONFIG_HAVE_MEMBLOCK_NODE_MAPstatic 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];static bool mirrored_kernelcore; /* 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 > 1int nr_node_ids __read_mostly = MAX_NUMNODES;int nr_online_nodes __read_mostly = 1;EXPORT_SYMBOL(nr_node_ids);EXPORT_SYMBOL(nr_online_nodes);#endif int page_group_by_mobility_disabled __read_mostly; #ifdef CONFIG_DEFERRED_STRUCT_PAGE_INITstatic inline void reset_deferred_meminit(pg_data_t *pgdat){ unsigned long max_initialise; unsigned long reserved_lowmem; /* * Initialise at least 2G of a node but also take into account that * two large system hashes that can take up 1GB for 0.25TB/node. */ max_initialise = max(2UL << (30 - PAGE_SHIFT), (pgdat->node_spanned_pages >> 8)); /* * Compensate the all the memblock reservations (e.g. crash kernel) * from the initial estimation to make sure we will initialize enough * memory to boot. */ reserved_lowmem = memblock_reserved_memory_within(pgdat->node_start_pfn, pgdat->node_start_pfn + max_initialise); max_initialise += reserved_lowmem; pgdat->static_init_size = min(max_initialise, pgdat->node_spanned_pages); pgdat->first_deferred_pfn = ULONG_MAX;} /* Returns true if the struct page for the pfn is uninitialised */static inline bool __meminit early_page_uninitialised(unsigned long pfn){ int nid = early_pfn_to_nid(pfn); if (node_online(nid) && pfn >= NODE_DATA(nid)->first_deferred_pfn) return true; return false;} /* * Returns false when the remaining initialisation should be deferred until * later in the boot cycle when it can be parallelised. */static inline bool update_defer_init(pg_data_t *pgdat, unsigned long pfn, unsigned long zone_end, unsigned long *nr_initialised){ /* Always populate low zones for address-contrained allocations */ if (zone_end < pgdat_end_pfn(pgdat)) return true; (*nr_initialised)++; if ((*nr_initialised > pgdat->static_init_size) && (pfn & (PAGES_PER_SECTION - 1)) == 0) { pgdat->first_deferred_pfn = pfn; return false; } return true;}#elsestatic inline void reset_deferred_meminit(pg_data_t *pgdat){} static inline bool early_page_uninitialised(unsigned long pfn){ return false;} static inline bool update_defer_init(pg_data_t *pgdat, unsigned long pfn, unsigned long zone_end, unsigned long *nr_initialised){ return true;}#endif /* Return a pointer to the bitmap storing bits affecting a block of pages */static inline unsigned long *get_pageblock_bitmap(struct page *page, unsigned long pfn){#ifdef CONFIG_SPARSEMEM return __pfn_to_section(pfn)->pageblock_flags;#else return page_zone(page)->pageblock_flags;#endif /* CONFIG_SPARSEMEM */} static inline int pfn_to_bitidx(struct page *page, unsigned long pfn){#ifdef CONFIG_SPARSEMEM pfn &= (PAGES_PER_SECTION-1); return (pfn >> pageblock_order) * NR_PAGEBLOCK_BITS;#else pfn = pfn - round_down(page_zone(page)->zone_start_pfn, pageblock_nr_pages); return (pfn >> pageblock_order) * NR_PAGEBLOCK_BITS;#endif /* CONFIG_SPARSEMEM */} /** * get_pfnblock_flags_mask - Return the requested group of flags for the pageblock_nr_pages block of pages * @page: The page within the block of interest * @pfn: The target page frame number * @end_bitidx: The last bit of interest to retrieve * @mask: mask of bits that the caller is interested in * * Return: pageblock_bits flags */static __always_inline unsigned long __get_pfnblock_flags_mask(struct page *page, unsigned long pfn, unsigned long end_bitidx, 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); word = bitmap[word_bitidx]; bitidx += end_bitidx; return (word >> (BITS_PER_LONG - bitidx - 1)) & mask;} unsigned long get_pfnblock_flags_mask(struct page *page, unsigned long pfn, unsigned long end_bitidx, unsigned long mask){ return __get_pfnblock_flags_mask(page, pfn, end_bitidx, mask);} static __always_inline int get_pfnblock_migratetype(struct page *page, unsigned long pfn){ return __get_pfnblock_flags_mask(page, pfn, PB_migrate_end, 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 * @end_bitidx: The last bit of interest * @mask: mask of bits that the caller is interested in */void set_pfnblock_flags_mask(struct page *page, unsigned long flags, unsigned long pfn, unsigned long end_bitidx, unsigned long mask){ unsigned long *bitmap; unsigned long bitidx, word_bitidx; unsigned long old_word, word; BUILD_BUG_ON(NR_PAGEBLOCK_BITS != 4); 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); bitidx += end_bitidx; mask <<= (BITS_PER_LONG - bitidx - 1); flags <<= (BITS_PER_LONG - bitidx - 1); word = READ_ONCE(bitmap[word_bitidx]); for (;;) { old_word = cmpxchg(&bitmap[word_bitidx], word, (word & ~mask) | flags); if (word == old_word) break; word = old_word; }} void set_pageblock_migratetype(struct page *page, int 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_DEBUG_VMstatic int page_outside_zone_boundaries(struct zone *zone, struct page *page){ int ret = 0; 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; if (!zone_spans_pfn(zone, pfn)) ret = 1; } 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;} Lines 1–500 of 7843. Load more
/* * 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/swap.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/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/memory_hotplug.h> #include <linux/nodemask.h> #include <linux/vmalloc.h> #include <linux/vmstat.h> #include <linux/mempolicy.h> #include <linux/memremap.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_ext.h> #include <linux/debugobjects.h> #include <linux/kmemleak.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/migrate.h> #include <linux/hugetlb.h> #include <linux/sched/rt.h> #include <linux/sched/mm.h> #include <linux/page_owner.h> #include <linux/kthread.h> #include <linux/memcontrol.h> #include <linux/ftrace.h> #include <linux/nmi.h> #include <asm/sections.h> #include <asm/tlbflush.h> #include <asm/div64.h> #include "internal.h" /* prevent >1 _updater_ of zone percpu pageset ->high and ->batch fields */ static DEFINE_MUTEX(pcp_batch_high_lock); #define MIN_PERCPU_PAGELIST_FRACTION (8) #ifdef CONFIG_USE_PERCPU_NUMA_NODE_ID DEFINE_PER_CPU(int, numa_node); EXPORT_PER_CPU_SYMBOL(numa_node); #endif #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_); int _node_numa_mem_[MAX_NUMNODES]; #endif /* work_structs for global per-cpu drains */ DEFINE_MUTEX(pcpu_drain_mutex); DEFINE_PER_CPU(struct work_struct, pcpu_drain); #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); /* 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; unsigned long totalcma_pages __read_mostly; int percpu_pagelist_fraction; gfp_t gfp_allowed_mask __read_mostly = GFP_BOOT_MASK; /* * A cached value of the page's pageblock's migratetype, used when the page is * put on a pcplist. Used to avoid the pageblock migratetype lookup when * freeing from pcplists in most cases, at the cost of possibly becoming stale. * Also the migratetype set in the page does not necessarily match the pcplist * index, e.g. page might have MIGRATE_CMA set but be on a pcplist with any * other index - this ensures that it will be put on the correct CMA freelist. */ static inline int get_pcppage_migratetype(struct page *page) { return page->index; } static inline void set_pcppage_migratetype(struct page *page, int migratetype) { page->index = migratetype; } #ifdef CONFIG_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_IO | __GFP_FS); } bool pm_suspended_storage(void) { if ((gfp_allowed_mask & (__GFP_IO | __GFP_FS)) == (__GFP_IO | __GFP_FS)) return false; return true; } #endif /* CONFIG_PM_SLEEP */ #ifdef CONFIG_HUGETLB_PAGE_SIZE_VARIABLE unsigned int pageblock_order __read_mostly; #endif static void __free_pages_ok(struct page *page, unsigned int order); /* * 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 */ int sysctl_lowmem_reserve_ratio[MAX_NR_ZONES-1] = { #ifdef CONFIG_ZONE_DMA 256, #endif #ifdef CONFIG_ZONE_DMA32 256, #endif #ifdef CONFIG_HIGHMEM 32, #endif 32, }; EXPORT_SYMBOL(totalram_pages); static 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 }; char * const migratetype_names[MIGRATE_TYPES] = { "Unmovable", "Movable", "Reclaimable", "HighAtomic", #ifdef CONFIG_CMA "CMA", #endif #ifdef CONFIG_MEMORY_ISOLATION "Isolate", #endif }; compound_page_dtor * const compound_page_dtors[] = { NULL, free_compound_page, #ifdef CONFIG_HUGETLB_PAGE free_huge_page, #endif #ifdef CONFIG_TRANSPARENT_HUGEPAGE free_transhuge_page, #endif }; int min_free_kbytes = 1024; int user_min_free_kbytes = -1; int watermark_scale_factor = 10; static unsigned long __meminitdata nr_kernel_pages; static unsigned long __meminitdata nr_all_pages; static unsigned long __meminitdata dma_reserve; #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]; static bool mirrored_kernelcore; /* 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; EXPORT_SYMBOL(nr_node_ids); EXPORT_SYMBOL(nr_online_nodes); #endif int page_group_by_mobility_disabled __read_mostly; #ifdef CONFIG_DEFERRED_STRUCT_PAGE_INIT static inline void reset_deferred_meminit(pg_data_t *pgdat) { unsigned long max_initialise; unsigned long reserved_lowmem; /* * Initialise at least 2G of a node but also take into account that * two large system hashes that can take up 1GB for 0.25TB/node. */ max_initialise = max(2UL << (30 - PAGE_SHIFT), (pgdat->node_spanned_pages >> 8)); /* * Compensate the all the memblock reservations (e.g. crash kernel) * from the initial estimation to make sure we will initialize enough * memory to boot. */ reserved_lowmem = memblock_reserved_memory_within(pgdat->node_start_pfn, pgdat->node_start_pfn + max_initialise); max_initialise += reserved_lowmem; pgdat->static_init_size = min(max_initialise, pgdat->node_spanned_pages); pgdat->first_deferred_pfn = ULONG_MAX; } /* Returns true if the struct page for the pfn is uninitialised */ static inline bool __meminit early_page_uninitialised(unsigned long pfn) { int nid = early_pfn_to_nid(pfn); if (node_online(nid) && pfn >= NODE_DATA(nid)->first_deferred_pfn) return true; return false; } /* * Returns false when the remaining initialisation should be deferred until * later in the boot cycle when it can be parallelised. */ static inline bool update_defer_init(pg_data_t *pgdat, unsigned long pfn, unsigned long zone_end, unsigned long *nr_initialised) { /* Always populate low zones for address-contrained allocations */ if (zone_end < pgdat_end_pfn(pgdat)) return true; (*nr_initialised)++; if ((*nr_initialised > pgdat->static_init_size) && (pfn & (PAGES_PER_SECTION - 1)) == 0) { pgdat->first_deferred_pfn = pfn; return false; } return true; } #else static inline void reset_deferred_meminit(pg_data_t *pgdat) { } static inline bool early_page_uninitialised(unsigned long pfn) { return false; } static inline bool update_defer_init(pg_data_t *pgdat, unsigned long pfn, unsigned long zone_end, unsigned long *nr_initialised) { return true; } #endif /* Return a pointer to the bitmap storing bits affecting a block of pages */ static inline unsigned long *get_pageblock_bitmap(struct page *page, unsigned long pfn) { #ifdef CONFIG_SPARSEMEM return __pfn_to_section(pfn)->pageblock_flags; #else return page_zone(page)->pageblock_flags; #endif /* CONFIG_SPARSEMEM */ } static inline int pfn_to_bitidx(struct page *page, unsigned long pfn) { #ifdef CONFIG_SPARSEMEM pfn &= (PAGES_PER_SECTION-1); return (pfn >> pageblock_order) * NR_PAGEBLOCK_BITS; #else pfn = pfn - round_down(page_zone(page)->zone_start_pfn, pageblock_nr_pages); return (pfn >> pageblock_order) * NR_PAGEBLOCK_BITS; #endif /* CONFIG_SPARSEMEM */ } /** * get_pfnblock_flags_mask - Return the requested group of flags for the pageblock_nr_pages block of pages * @page: The page within the block of interest * @pfn: The target page frame number * @end_bitidx: The last bit of interest to retrieve * @mask: mask of bits that the caller is interested in * * Return: pageblock_bits flags */ static __always_inline unsigned long __get_pfnblock_flags_mask(struct page *page, unsigned long pfn, unsigned long end_bitidx, 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); word = bitmap[word_bitidx]; bitidx += end_bitidx; return (word >> (BITS_PER_LONG - bitidx - 1)) & mask; } unsigned long get_pfnblock_flags_mask(struct page *page, unsigned long pfn, unsigned long end_bitidx, unsigned long mask) { return __get_pfnblock_flags_mask(page, pfn, end_bitidx, mask); } static __always_inline int get_pfnblock_migratetype(struct page *page, unsigned long pfn) { return __get_pfnblock_flags_mask(page, pfn, PB_migrate_end, 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 * @end_bitidx: The last bit of interest * @mask: mask of bits that the caller is interested in */ void set_pfnblock_flags_mask(struct page *page, unsigned long flags, unsigned long pfn, unsigned long end_bitidx, unsigned long mask) { unsigned long *bitmap; unsigned long bitidx, word_bitidx; unsigned long old_word, word; BUILD_BUG_ON(NR_PAGEBLOCK_BITS != 4); 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); bitidx += end_bitidx; mask <<= (BITS_PER_LONG - bitidx - 1); flags <<= (BITS_PER_LONG - bitidx - 1); word = READ_ONCE(bitmap[word_bitidx]); for (;;) { old_word = cmpxchg(&bitmap[word_bitidx], word, (word & ~mask) | flags); if (word == old_word) break; word = old_word; } } void set_pageblock_migratetype(struct page *page, int 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_DEBUG_VM static int page_outside_zone_boundaries(struct zone *zone, struct page *page) { int ret = 0; 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; if (!zone_spans_pfn(zone, pfn)) ret = 1; } 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; }