Viewing file:  mmzone.h (41.85 KB) -rw-r--r--
Select action/file-type:
 (+) |  (+) |  (+) | Code (+) | Session (+) |  (+) | SDB (+) |  (+) |  (+) |  (+) |  (+) |  (+) |
/* SPDX-License-Identifier: GPL-2.0 */
#ifndef _LINUX_MMZONE_H
#define _LINUX_MMZONE_H
#ifndef __ASSEMBLY__
#ifndef __GENERATING_BOUNDS_H
#include <linux/spinlock.h>
#include <linux/list.h>
#include <linux/wait.h>
#include <linux/bitops.h>
#include <linux/cache.h>
#include <linux/threads.h>
#include <linux/numa.h>
#include <linux/init.h>
#include <linux/seqlock.h>
#include <linux/nodemask.h>
#include <linux/pageblock-flags.h>
#include <linux/page-flags-layout.h>
#include <linux/atomic.h>
#include <linux/mm_types.h>
#include <linux/page-flags.h>
#include <asm/page.h>
/* Free memory management - zoned buddy allocator. */
#ifndef CONFIG_FORCE_MAX_ZONEORDER
#define MAX_ORDER 11
#else
#define MAX_ORDER CONFIG_FORCE_MAX_ZONEORDER
#endif
#define MAX_ORDER_NR_PAGES (1 << (MAX_ORDER - 1))
/*
* PAGE_ALLOC_COSTLY_ORDER is the order at which allocations are deemed
* costly to service. That is between allocation orders which should
* coalesce naturally under reasonable reclaim pressure and those which
* will not.
*/
#define PAGE_ALLOC_COSTLY_ORDER 3
enum migratetype {
MIGRATE_UNMOVABLE,
MIGRATE_MOVABLE,
MIGRATE_RECLAIMABLE,
MIGRATE_PCPTYPES, /* the number of types on the pcp lists */
MIGRATE_HIGHATOMIC = MIGRATE_PCPTYPES,
#ifdef CONFIG_CMA
/*
* MIGRATE_CMA migration type is designed to mimic the way
* ZONE_MOVABLE works. Only movable pages can be allocated
* from MIGRATE_CMA pageblocks and page allocator never
* implicitly change migration type of MIGRATE_CMA pageblock.
*
* The way to use it is to change migratetype of a range of
* pageblocks to MIGRATE_CMA which can be done by
* __free_pageblock_cma() function. What is important though
* is that a range of pageblocks must be aligned to
* MAX_ORDER_NR_PAGES should biggest page be bigger then
* a single pageblock.
*/
MIGRATE_CMA,
#endif
#ifdef CONFIG_MEMORY_ISOLATION
MIGRATE_ISOLATE, /* can't allocate from here */
#endif
MIGRATE_TYPES
};
/* In mm/page_alloc.c; keep in sync also with show_migration_types() there */
extern const char * const migratetype_names[MIGRATE_TYPES];
#ifdef CONFIG_CMA
# define is_migrate_cma(migratetype) unlikely((migratetype) == MIGRATE_CMA)
# define is_migrate_cma_page(_page) (get_pageblock_migratetype(_page) == MIGRATE_CMA)
#else
# define is_migrate_cma(migratetype) false
# define is_migrate_cma_page(_page) false
#endif
static inline bool is_migrate_movable(int mt)
{
return is_migrate_cma(mt) || mt == MIGRATE_MOVABLE;
}
#define for_each_migratetype_order(order, type) \
for (order = 0; order < MAX_ORDER; order++) \
for (type = 0; type < MIGRATE_TYPES; type++)
extern int page_group_by_mobility_disabled;
#define NR_MIGRATETYPE_BITS (PB_migrate_end - PB_migrate + 1)
#define MIGRATETYPE_MASK ((1UL << NR_MIGRATETYPE_BITS) - 1)
#define get_pageblock_migratetype(page) \
get_pfnblock_flags_mask(page, page_to_pfn(page), \
PB_migrate_end, MIGRATETYPE_MASK)
struct free_area {
struct list_head free_list[MIGRATE_TYPES];
unsigned long nr_free;
};
/* Used for pages not on another list */
static inline void add_to_free_area(struct page *page, struct free_area *area,
int migratetype)
{
list_add(&page->lru, &area->free_list[migratetype]);
area->nr_free++;
}
/* Used for pages not on another list */
static inline void add_to_free_area_tail(struct page *page, struct free_area *area,
int migratetype)
{
list_add_tail(&page->lru, &area->free_list[migratetype]);
area->nr_free++;
}
#ifdef CONFIG_SHUFFLE_PAGE_ALLOCATOR
/* Used to preserve page allocation order entropy */
void add_to_free_area_random(struct page *page, struct free_area *area,
int migratetype);
#else
static inline void add_to_free_area_random(struct page *page,
struct free_area *area, int migratetype)
{
add_to_free_area(page, area, migratetype);
}
#endif
/* Used for pages which are on another list */
static inline void move_to_free_area(struct page *page, struct free_area *area,
int migratetype)
{
list_move(&page->lru, &area->free_list[migratetype]);
}
static inline struct page *get_page_from_free_area(struct free_area *area,
int migratetype)
{
return list_first_entry_or_null(&area->free_list[migratetype],
struct page, lru);
}
static inline void del_page_from_free_area(struct page *page,
struct free_area *area)
{
list_del(&page->lru);
__ClearPageBuddy(page);
set_page_private(page, 0);
area->nr_free--;
}
static inline bool free_area_empty(struct free_area *area, int migratetype)
{
return list_empty(&area->free_list[migratetype]);
}
struct pglist_data;
/*
* zone->lock and the zone lru_lock are two of the hottest locks in the kernel.
* So add a wild amount of padding here to ensure that they fall into separate
* cachelines. There are very few zone structures in the machine, so space
* consumption is not a concern here.
*/
#if defined(CONFIG_SMP)
struct zone_padding {
char x[0];
} ____cacheline_internodealigned_in_smp;
#define ZONE_PADDING(name) struct zone_padding name;
#else
#define ZONE_PADDING(name)
#endif
#ifdef CONFIG_NUMA
enum numa_stat_item {
NUMA_HIT, /* allocated in intended node */
NUMA_MISS, /* allocated in non intended node */
NUMA_FOREIGN, /* was intended here, hit elsewhere */
NUMA_INTERLEAVE_HIT, /* interleaver preferred this zone */
NUMA_LOCAL, /* allocation from local node */
NUMA_OTHER, /* allocation from other node */
NR_VM_NUMA_STAT_ITEMS
};
#else
#define NR_VM_NUMA_STAT_ITEMS 0
#endif
enum zone_stat_item {
/* First 128 byte cacheline (assuming 64 bit words) */
NR_FREE_PAGES,
NR_ZONE_LRU_BASE, /* Used only for compaction and reclaim retry */
NR_ZONE_INACTIVE_ANON = NR_ZONE_LRU_BASE,
NR_ZONE_ACTIVE_ANON,
NR_ZONE_INACTIVE_FILE,
NR_ZONE_ACTIVE_FILE,
NR_ZONE_UNEVICTABLE,
NR_ZONE_WRITE_PENDING, /* Count of dirty, writeback and unstable pages */
NR_MLOCK, /* mlock()ed pages found and moved off LRU */
NR_PAGETABLE, /* used for pagetables */
NR_KERNEL_STACK_KB, /* measured in KiB */
/* Second 128 byte cacheline */
NR_BOUNCE,
#if IS_ENABLED(CONFIG_ZSMALLOC)
NR_ZSPAGES, /* allocated in zsmalloc */
#endif
NR_FREE_CMA_PAGES,
NR_VM_ZONE_STAT_ITEMS };
enum node_stat_item {
NR_LRU_BASE,
NR_INACTIVE_ANON = NR_LRU_BASE, /* must match order of LRU_[IN]ACTIVE */
NR_ACTIVE_ANON, /* " " " " " */
NR_INACTIVE_FILE, /* " " " " " */
NR_ACTIVE_FILE, /* " " " " " */
NR_UNEVICTABLE, /* " " " " " */
NR_SLAB_RECLAIMABLE,
NR_SLAB_UNRECLAIMABLE,
NR_ISOLATED_ANON, /* Temporary isolated pages from anon lru */
NR_ISOLATED_FILE, /* Temporary isolated pages from file lru */
WORKINGSET_NODES,
WORKINGSET_REFAULT,
WORKINGSET_ACTIVATE,
WORKINGSET_RESTORE,
WORKINGSET_NODERECLAIM,
NR_ANON_MAPPED, /* Mapped anonymous pages */
NR_FILE_MAPPED, /* pagecache pages mapped into pagetables.
only modified from process context */
NR_FILE_PAGES,
NR_FILE_DIRTY,
NR_WRITEBACK,
NR_WRITEBACK_TEMP, /* Writeback using temporary buffers */
NR_SHMEM, /* shmem pages (included tmpfs/GEM pages) */
NR_SHMEM_THPS,
NR_SHMEM_PMDMAPPED,
NR_FILE_THPS,
NR_FILE_PMDMAPPED,
NR_ANON_THPS,
NR_UNSTABLE_NFS, /* NFS unstable pages */
NR_VMSCAN_WRITE,
NR_VMSCAN_IMMEDIATE, /* Prioritise for reclaim when writeback ends */
NR_DIRTIED, /* page dirtyings since bootup */
NR_WRITTEN, /* page writings since bootup */
NR_KERNEL_MISC_RECLAIMABLE, /* reclaimable non-slab kernel pages */
NR_VM_NODE_STAT_ITEMS
};
/*
* We do arithmetic on the LRU lists in various places in the code,
* so it is important to keep the active lists LRU_ACTIVE higher in
* the array than the corresponding inactive lists, and to keep
* the *_FILE lists LRU_FILE higher than the corresponding _ANON lists.
*
* This has to be kept in sync with the statistics in zone_stat_item
* above and the descriptions in vmstat_text in mm/vmstat.c
*/
#define LRU_BASE 0
#define LRU_ACTIVE 1
#define LRU_FILE 2
enum lru_list {
LRU_INACTIVE_ANON = LRU_BASE,
LRU_ACTIVE_ANON = LRU_BASE + LRU_ACTIVE,
LRU_INACTIVE_FILE = LRU_BASE + LRU_FILE,
LRU_ACTIVE_FILE = LRU_BASE + LRU_FILE + LRU_ACTIVE,
LRU_UNEVICTABLE,
NR_LRU_LISTS
};
#define for_each_lru(lru) for (lru = 0; lru < NR_LRU_LISTS; lru++)
#define for_each_evictable_lru(lru) for (lru = 0; lru <= LRU_ACTIVE_FILE; lru++)
static inline int is_file_lru(enum lru_list lru)
{
return (lru == LRU_INACTIVE_FILE || lru == LRU_ACTIVE_FILE);
}
static inline int is_active_lru(enum lru_list lru)
{
return (lru == LRU_ACTIVE_ANON || lru == LRU_ACTIVE_FILE);
}
struct zone_reclaim_stat {
/*
* The pageout code in vmscan.c keeps track of how many of the
* mem/swap backed and file backed pages are referenced.
* The higher the rotated/scanned ratio, the more valuable
* that cache is.
*
* The anon LRU stats live in [0], file LRU stats in [1]
*/
unsigned long recent_rotated[2];
unsigned long recent_scanned[2];
};
struct lruvec {
struct list_head lists[NR_LRU_LISTS];
struct zone_reclaim_stat reclaim_stat;
/* Evictions & activations on the inactive file list */
atomic_long_t inactive_age;
/* Refaults at the time of last reclaim cycle */
unsigned long refaults;
#ifdef CONFIG_MEMCG
struct pglist_data *pgdat;
#endif
};
/* Isolate unmapped file */
#define ISOLATE_UNMAPPED ((__force isolate_mode_t)0x2)
/* Isolate for asynchronous migration */
#define ISOLATE_ASYNC_MIGRATE ((__force isolate_mode_t)0x4)
/* Isolate unevictable pages */
#define ISOLATE_UNEVICTABLE ((__force isolate_mode_t)0x8)
/* LRU Isolation modes. */
typedef unsigned __bitwise isolate_mode_t;
enum zone_watermarks {
WMARK_MIN,
WMARK_LOW,
WMARK_HIGH,
NR_WMARK
};
#define min_wmark_pages(z) (z->_watermark[WMARK_MIN] + z->watermark_boost)
#define low_wmark_pages(z) (z->_watermark[WMARK_LOW] + z->watermark_boost)
#define high_wmark_pages(z) (z->_watermark[WMARK_HIGH] + z->watermark_boost)
#define wmark_pages(z, i) (z->_watermark[i] + z->watermark_boost)
struct per_cpu_pages {
int count; /* number of pages in the list */
int high; /* high watermark, emptying needed */
int batch; /* chunk size for buddy add/remove */
/* Lists of pages, one per migrate type stored on the pcp-lists */
struct list_head lists[MIGRATE_PCPTYPES];
};
struct per_cpu_pageset {
struct per_cpu_pages pcp;
#ifdef CONFIG_NUMA
s8 expire;
u16 vm_numa_stat_diff[NR_VM_NUMA_STAT_ITEMS];
#endif
#ifdef CONFIG_SMP
s8 stat_threshold;
s8 vm_stat_diff[NR_VM_ZONE_STAT_ITEMS];
#endif
};
struct per_cpu_nodestat {
s8 stat_threshold;
s8 vm_node_stat_diff[NR_VM_NODE_STAT_ITEMS];
};
#endif /* !__GENERATING_BOUNDS.H */
enum zone_type {
#ifdef CONFIG_ZONE_DMA
/*
* ZONE_DMA is used when there are devices that are not able
* to do DMA to all of addressable memory (ZONE_NORMAL). Then we
* carve out the portion of memory that is needed for these devices.
* The range is arch specific.
*
* Some examples
*
* Architecture Limit
* ---------------------------
* parisc, ia64, sparc <4G
* s390, powerpc <2G
* arm Various
* alpha Unlimited or 0-16MB.
*
* i386, x86_64 and multiple other arches
* <16M.
*/
ZONE_DMA,
#endif
#ifdef CONFIG_ZONE_DMA32
/*
* x86_64 needs two ZONE_DMAs because it supports devices that are
* only able to do DMA to the lower 16M but also 32 bit devices that
* can only do DMA areas below 4G.
*/
ZONE_DMA32,
#endif
/*
* Normal addressable memory is in ZONE_NORMAL. DMA operations can be
* performed on pages in ZONE_NORMAL if the DMA devices support
* transfers to all addressable memory.
*/
ZONE_NORMAL,
#ifdef CONFIG_HIGHMEM
/*
* A memory area that is only addressable by the kernel through
* mapping portions into its own address space. This is for example
* used by i386 to allow the kernel to address the memory beyond
* 900MB. The kernel will set up special mappings (page
* table entries on i386) for each page that the kernel needs to
* access.
*/
ZONE_HIGHMEM,
#endif
ZONE_MOVABLE,
#ifdef CONFIG_ZONE_DEVICE
ZONE_DEVICE,
#endif
__MAX_NR_ZONES
};
#ifndef __GENERATING_BOUNDS_H
struct zone {
/* Read-mostly fields */
/* zone watermarks, access with *_wmark_pages(zone) macros */
unsigned long _watermark[NR_WMARK];
unsigned long watermark_boost;
unsigned long nr_reserved_highatomic;
/*
* We don't know if the memory that we're going to allocate will be
* freeable or/and it will be released eventually, so to avoid totally
* wasting several GB of ram we must reserve some of the lower zone
* memory (otherwise we risk to run OOM on the lower zones despite
* there being tons of freeable ram on the higher zones). This array is
* recalculated at runtime if the sysctl_lowmem_reserve_ratio sysctl
* changes.
*/
long lowmem_reserve[MAX_NR_ZONES];
#ifdef CONFIG_NUMA
int node;
#endif
struct pglist_data *zone_pgdat;
struct per_cpu_pageset __percpu *pageset;
#ifndef CONFIG_SPARSEMEM
/*
* Flags for a pageblock_nr_pages block. See pageblock-flags.h.
* In SPARSEMEM, this map is stored in struct mem_section
*/
unsigned long *pageblock_flags;
#endif /* CONFIG_SPARSEMEM */
/* zone_start_pfn == zone_start_paddr >> PAGE_SHIFT */
unsigned long zone_start_pfn;
/*
* spanned_pages is the total pages spanned by the zone, including
* holes, which is calculated as:
* spanned_pages = zone_end_pfn - zone_start_pfn;
*
* present_pages is physical pages existing within the zone, which
* is calculated as:
* present_pages = spanned_pages - absent_pages(pages in holes);
*
* managed_pages is present pages managed by the buddy system, which
* is calculated as (reserved_pages includes pages allocated by the
* bootmem allocator):
* managed_pages = present_pages - reserved_pages;
*
* So present_pages may be used by memory hotplug or memory power
* management logic to figure out unmanaged pages by checking
* (present_pages - managed_pages). And managed_pages should be used
* by page allocator and vm scanner to calculate all kinds of watermarks
* and thresholds.
*
* Locking rules:
*
* zone_start_pfn and spanned_pages are protected by span_seqlock.
* It is a seqlock because it has to be read outside of zone->lock,
* and it is done in the main allocator path. But, it is written
* quite infrequently.
*
* The span_seq lock is declared along with zone->lock because it is
* frequently read in proximity to zone->lock. It's good to
* give them a chance of being in the same cacheline.
*
* Write access to present_pages at runtime should be protected by
* mem_hotplug_begin/end(). Any reader who can't tolerant drift of
* present_pages should get_online_mems() to get a stable value.
*/
atomic_long_t managed_pages;
unsigned long spanned_pages;
unsigned long present_pages;
const char *name;
#ifdef CONFIG_MEMORY_ISOLATION
/*
* Number of isolated pageblock. It is used to solve incorrect
* freepage counting problem due to racy retrieving migratetype
* of pageblock. Protected by zone->lock.
*/
unsigned long nr_isolate_pageblock;
#endif
#ifdef CONFIG_MEMORY_HOTPLUG
/* see spanned/present_pages for more description */
seqlock_t span_seqlock;
#endif
int initialized;
/* Write-intensive fields used from the page allocator */
ZONE_PADDING(_pad1_)
/* free areas of different sizes */
struct free_area free_area[MAX_ORDER];
/* zone flags, see below */
unsigned long flags;
/* Primarily protects free_area */
spinlock_t lock;
/* Write-intensive fields used by compaction and vmstats. */
ZONE_PADDING(_pad2_)
/*
* When free pages are below this point, additional steps are taken
* when reading the number of free pages to avoid per-cpu counter
* drift allowing watermarks to be breached
*/
unsigned long percpu_drift_mark;
#if defined CONFIG_COMPACTION || defined CONFIG_CMA
/* pfn where compaction free scanner should start */
unsigned long compact_cached_free_pfn;
/* pfn where async and sync compaction migration scanner should start */
unsigned long compact_cached_migrate_pfn[2];
unsigned long compact_init_migrate_pfn;
unsigned long compact_init_free_pfn;
#endif
#ifdef CONFIG_COMPACTION
/*
* On compaction failure, 1<<compact_defer_shift compactions
* are skipped before trying again. The number attempted since
* last failure is tracked with compact_considered.
*/
unsigned int compact_considered;
unsigned int compact_defer_shift;
int compact_order_failed;
#endif
#if defined CONFIG_COMPACTION || defined CONFIG_CMA
/* Set to true when the PG_migrate_skip bits should be cleared */
bool compact_blockskip_flush;
#endif
bool contiguous;
ZONE_PADDING(_pad3_)
/* Zone statistics */
atomic_long_t vm_stat[NR_VM_ZONE_STAT_ITEMS];
atomic_long_t vm_numa_stat[NR_VM_NUMA_STAT_ITEMS];
} ____cacheline_internodealigned_in_smp;
enum pgdat_flags {
PGDAT_CONGESTED, /* pgdat has many dirty pages backed by
* a congested BDI
*/
PGDAT_DIRTY, /* reclaim scanning has recently found
* many dirty file pages at the tail
* of the LRU.
*/
PGDAT_WRITEBACK, /* reclaim scanning has recently found
* many pages under writeback
*/
PGDAT_RECLAIM_LOCKED, /* prevents concurrent reclaim */
};
enum zone_flags {
ZONE_BOOSTED_WATERMARK, /* zone recently boosted watermarks.
* Cleared when kswapd is woken.
*/
};
static inline unsigned long zone_managed_pages(struct zone *zone)
{
return (unsigned long)atomic_long_read(&zone->managed_pages);
}
static inline unsigned long zone_end_pfn(const struct zone *zone)
{
return zone->zone_start_pfn + zone->spanned_pages;
}
static inline bool zone_spans_pfn(const struct zone *zone, unsigned long pfn)
{
return zone->zone_start_pfn <= pfn && pfn < zone_end_pfn(zone);
}
static inline bool zone_is_initialized(struct zone *zone)
{
return zone->initialized;
}
static inline bool zone_is_empty(struct zone *zone)
{
return zone->spanned_pages == 0;
}
/*
* Return true if [start_pfn, start_pfn + nr_pages) range has a non-empty
* intersection with the given zone
*/
static inline bool zone_intersects(struct zone *zone,
unsigned long start_pfn, unsigned long nr_pages)
{
if (zone_is_empty(zone))
return false;
if (start_pfn >= zone_end_pfn(zone) ||
start_pfn + nr_pages <= zone->zone_start_pfn)
return false;
return true;
}
/*
* The "priority" of VM scanning is how much of the queues we will scan in one
* go. A value of 12 for DEF_PRIORITY implies that we will scan 1/4096th of the
* queues ("queue_length >> 12") during an aging round.
*/
#define DEF_PRIORITY 12
/* Maximum number of zones on a zonelist */
#define MAX_ZONES_PER_ZONELIST (MAX_NUMNODES * MAX_NR_ZONES)
enum {
ZONELIST_FALLBACK, /* zonelist with fallback */
#ifdef CONFIG_NUMA
/*
* The NUMA zonelists are doubled because we need zonelists that
* restrict the allocations to a single node for __GFP_THISNODE.
*/
ZONELIST_NOFALLBACK, /* zonelist without fallback (__GFP_THISNODE) */
#endif
MAX_ZONELISTS
};
/*
* This struct contains information about a zone in a zonelist. It is stored
* here to avoid dereferences into large structures and lookups of tables
*/
struct zoneref {
struct zone *zone; /* Pointer to actual zone */
int zone_idx; /* zone_idx(zoneref->zone) */
};
/*
* One allocation request operates on a zonelist. A zonelist
* is a list of zones, the first one is the 'goal' of the
* allocation, the other zones are fallback zones, in decreasing
* priority.
*
* To speed the reading of the zonelist, the zonerefs contain the zone index
* of the entry being read. Helper functions to access information given
* a struct zoneref are
*
* zonelist_zone() - Return the struct zone * for an entry in _zonerefs
* zonelist_zone_idx() - Return the index of the zone for an entry
* zonelist_node_idx() - Return the index of the node for an entry
*/
struct zonelist {
struct zoneref _zonerefs[MAX_ZONES_PER_ZONELIST + 1];
};
#ifndef CONFIG_DISCONTIGMEM
/* The array of struct pages - for discontigmem use pgdat->lmem_map */
extern struct page *mem_map;
#endif
#ifdef CONFIG_TRANSPARENT_HUGEPAGE
struct deferred_split {
spinlock_t split_queue_lock;
struct list_head split_queue;
unsigned long split_queue_len;
};
#endif
/*
* On NUMA machines, each NUMA node would have a pg_data_t to describe
* it's memory layout. On UMA machines there is a single pglist_data which
* describes the whole memory.
*
* Memory statistics and page replacement data structures are maintained on a
* per-zone basis.
*/
struct bootmem_data;
typedef struct pglist_data {
struct zone node_zones[MAX_NR_ZONES];
struct zonelist node_zonelists[MAX_ZONELISTS];
int nr_zones;
#ifdef CONFIG_FLAT_NODE_MEM_MAP /* means !SPARSEMEM */
struct page *node_mem_map;
#ifdef CONFIG_PAGE_EXTENSION
struct page_ext *node_page_ext;
#endif
#endif
#if defined(CONFIG_MEMORY_HOTPLUG) || defined(CONFIG_DEFERRED_STRUCT_PAGE_INIT)
/*
* Must be held any time you expect node_start_pfn,
* node_present_pages, node_spanned_pages or nr_zones to stay constant.
* Also synchronizes pgdat->first_deferred_pfn during deferred page
* init.
*
* pgdat_resize_lock() and pgdat_resize_unlock() are provided to
* manipulate node_size_lock without checking for CONFIG_MEMORY_HOTPLUG
* or CONFIG_DEFERRED_STRUCT_PAGE_INIT.
*
* Nests above zone->lock and zone->span_seqlock
*/
spinlock_t node_size_lock;
#endif
unsigned long node_start_pfn;
unsigned long node_present_pages; /* total number of physical pages */
unsigned long node_spanned_pages; /* total size of physical page
range, including holes */
int node_id;
wait_queue_head_t kswapd_wait;
wait_queue_head_t pfmemalloc_wait;
struct task_struct *kswapd; /* Protected by
mem_hotplug_begin/end() */
int kswapd_order;
enum zone_type kswapd_classzone_idx;
int kswapd_failures; /* Number of 'reclaimed == 0' runs */
#ifdef CONFIG_COMPACTION
int kcompactd_max_order;
enum zone_type kcompactd_classzone_idx;
wait_queue_head_t kcompactd_wait;
struct task_struct *kcompactd;
#endif
/*
* This is a per-node reserve of pages that are not available
* to userspace allocations.
*/
unsigned long totalreserve_pages;
#ifdef CONFIG_NUMA
/*
* zone reclaim becomes active if more unmapped pages exist.
*/
unsigned long min_unmapped_pages;
unsigned long min_slab_pages;
#endif /* CONFIG_NUMA */
/* Write-intensive fields used by page reclaim */
ZONE_PADDING(_pad1_)
spinlock_t lru_lock;
#ifdef CONFIG_DEFERRED_STRUCT_PAGE_INIT
/*
* If memory initialisation on large machines is deferred then this
* is the first PFN that needs to be initialised.
*/
unsigned long first_deferred_pfn;
#endif /* CONFIG_DEFERRED_STRUCT_PAGE_INIT */
#ifdef CONFIG_TRANSPARENT_HUGEPAGE
struct deferred_split deferred_split_queue;
#endif
/* Fields commonly accessed by the page reclaim scanner */
struct lruvec lruvec;
unsigned long flags;
ZONE_PADDING(_pad2_)
/* Per-node vmstats */
struct per_cpu_nodestat __percpu *per_cpu_nodestats;
atomic_long_t vm_stat[NR_VM_NODE_STAT_ITEMS];
} pg_data_t;
#define node_present_pages(nid) (NODE_DATA(nid)->node_present_pages)
#define node_spanned_pages(nid) (NODE_DATA(nid)->node_spanned_pages)
#ifdef CONFIG_FLAT_NODE_MEM_MAP
#define pgdat_page_nr(pgdat, pagenr) ((pgdat)->node_mem_map + (pagenr))
#else
#define pgdat_page_nr(pgdat, pagenr) pfn_to_page((pgdat)->node_start_pfn + (pagenr))
#endif
#define nid_page_nr(nid, pagenr) pgdat_page_nr(NODE_DATA(nid),(pagenr))
#define node_start_pfn(nid) (NODE_DATA(nid)->node_start_pfn)
#define node_end_pfn(nid) pgdat_end_pfn(NODE_DATA(nid))
static inline struct lruvec *node_lruvec(struct pglist_data *pgdat)
{
return &pgdat->lruvec;
}
static inline unsigned long pgdat_end_pfn(pg_data_t *pgdat)
{
return pgdat->node_start_pfn + pgdat->node_spanned_pages;
}
static inline bool pgdat_is_empty(pg_data_t *pgdat)
{
return !pgdat->node_start_pfn && !pgdat->node_spanned_pages;
}
#include <linux/memory_hotplug.h>
void build_all_zonelists(pg_data_t *pgdat);
void wakeup_kswapd(struct zone *zone, gfp_t gfp_mask, int order,
enum zone_type classzone_idx);
bool __zone_watermark_ok(struct zone *z, unsigned int order, unsigned long mark,
int classzone_idx, unsigned int alloc_flags,
long free_pages);
bool zone_watermark_ok(struct zone *z, unsigned int order,
unsigned long mark, int classzone_idx,
unsigned int alloc_flags);
bool zone_watermark_ok_safe(struct zone *z, unsigned int order,
unsigned long mark, int classzone_idx);
/*
* Memory initialization context, use to differentiate memory added by
* the platform statically or via memory hotplug interface.
*/
enum meminit_context {
MEMINIT_EARLY,
MEMINIT_HOTPLUG,
};
extern void init_currently_empty_zone(struct zone *zone, unsigned long start_pfn,
unsigned long size);
extern void lruvec_init(struct lruvec *lruvec);
static inline struct pglist_data *lruvec_pgdat(struct lruvec *lruvec)
{
#ifdef CONFIG_MEMCG
return lruvec->pgdat;
#else
return container_of(lruvec, struct pglist_data, lruvec);
#endif
}
extern unsigned long lruvec_lru_size(struct lruvec *lruvec, enum lru_list lru, int zone_idx);
#ifdef CONFIG_HAVE_MEMORY_PRESENT
void memory_present(int nid, unsigned long start, unsigned long end);
#else
static inline void memory_present(int nid, unsigned long start, unsigned long end) {}
#endif
#if defined(CONFIG_SPARSEMEM)
void memblocks_present(void);
#else
static inline void memblocks_present(void) {}
#endif
#ifdef CONFIG_HAVE_MEMORYLESS_NODES
int local_memory_node(int node_id);
#else
static inline int local_memory_node(int node_id) { return node_id; };
#endif
/*
* zone_idx() returns 0 for the ZONE_DMA zone, 1 for the ZONE_NORMAL zone, etc.
*/
#define zone_idx(zone) ((zone) - (zone)->zone_pgdat->node_zones)
/*
* Returns true if a zone has pages managed by the buddy allocator.
* All the reclaim decisions have to use this function rather than
* populated_zone(). If the whole zone is reserved then we can easily
* end up with populated_zone() && !managed_zone().
*/
static inline bool managed_zone(struct zone *zone)
{
return zone_managed_pages(zone);
}
/* Returns true if a zone has memory */
static inline bool populated_zone(struct zone *zone)
{
return zone->present_pages;
}
#ifdef CONFIG_NUMA
static inline int zone_to_nid(struct zone *zone)
{
return zone->node;
}
static inline void zone_set_nid(struct zone *zone, int nid)
{
zone->node = nid;
}
#else
static inline int zone_to_nid(struct zone *zone)
{
return 0;
}
static inline void zone_set_nid(struct zone *zone, int nid) {}
#endif
extern int movable_zone;
#ifdef CONFIG_HIGHMEM
static inline int zone_movable_is_highmem(void)
{
#ifdef CONFIG_HAVE_MEMBLOCK_NODE_MAP
return movable_zone == ZONE_HIGHMEM;
#else
return (ZONE_MOVABLE - 1) == ZONE_HIGHMEM;
#endif
}
#endif
static inline int is_highmem_idx(enum zone_type idx)
{
#ifdef CONFIG_HIGHMEM
return (idx == ZONE_HIGHMEM ||
(idx == ZONE_MOVABLE && zone_movable_is_highmem()));
#else
return 0;
#endif
}
#ifdef CONFIG_ZONE_DMA
bool has_managed_dma(void);
#else
static inline bool has_managed_dma(void)
{
return false;
}
#endif
/**
* is_highmem - helper function to quickly check if a struct zone is a
* highmem zone or not. This is an attempt to keep references
* to ZONE_{DMA/NORMAL/HIGHMEM/etc} in general code to a minimum.
* @zone - pointer to struct zone variable
*/
static inline int is_highmem(struct zone *zone)
{
#ifdef CONFIG_HIGHMEM
return is_highmem_idx(zone_idx(zone));
#else
return 0;
#endif
}
/* These two functions are used to setup the per zone pages min values */
struct ctl_table;
int min_free_kbytes_sysctl_handler(struct ctl_table *, int,
void __user *, size_t *, loff_t *);
int watermark_boost_factor_sysctl_handler(struct ctl_table *, int,
void __user *, size_t *, loff_t *);
int watermark_scale_factor_sysctl_handler(struct ctl_table *, int,
void __user *, size_t *, loff_t *);
extern int sysctl_lowmem_reserve_ratio[MAX_NR_ZONES];
int lowmem_reserve_ratio_sysctl_handler(struct ctl_table *, int,
void __user *, size_t *, loff_t *);
int percpu_pagelist_fraction_sysctl_handler(struct ctl_table *, int,
void __user *, size_t *, loff_t *);
int sysctl_min_unmapped_ratio_sysctl_handler(struct ctl_table *, int,
void __user *, size_t *, loff_t *);
int sysctl_min_slab_ratio_sysctl_handler(struct ctl_table *, int,
void __user *, size_t *, loff_t *);
extern int numa_zonelist_order_handler(struct ctl_table *, int,
void __user *, size_t *, loff_t *);
extern char numa_zonelist_order[];
#define NUMA_ZONELIST_ORDER_LEN 16
#ifndef CONFIG_NEED_MULTIPLE_NODES
extern struct pglist_data contig_page_data;
#define NODE_DATA(nid) (&contig_page_data)
#define NODE_MEM_MAP(nid) mem_map
#else /* CONFIG_NEED_MULTIPLE_NODES */
#include <asm/mmzone.h>
#endif /* !CONFIG_NEED_MULTIPLE_NODES */
extern struct pglist_data *first_online_pgdat(void);
extern struct pglist_data *next_online_pgdat(struct pglist_data *pgdat);
extern struct zone *next_zone(struct zone *zone);
/**
* for_each_online_pgdat - helper macro to iterate over all online nodes
* @pgdat - pointer to a pg_data_t variable
*/
#define for_each_online_pgdat(pgdat) \
for (pgdat = first_online_pgdat(); \
pgdat; \
pgdat = next_online_pgdat(pgdat))
/**
* for_each_zone - helper macro to iterate over all memory zones
* @zone - pointer to struct zone variable
*
* The user only needs to declare the zone variable, for_each_zone
* fills it in.
*/
#define for_each_zone(zone) \
for (zone = (first_online_pgdat())->node_zones; \
zone; \
zone = next_zone(zone))
#define for_each_populated_zone(zone) \
for (zone = (first_online_pgdat())->node_zones; \
zone; \
zone = next_zone(zone)) \
if (!populated_zone(zone)) \
; /* do nothing */ \
else
static inline struct zone *zonelist_zone(struct zoneref *zoneref)
{
return zoneref->zone;
}
static inline int zonelist_zone_idx(struct zoneref *zoneref)
{
return zoneref->zone_idx;
}
static inline int zonelist_node_idx(struct zoneref *zoneref)
{
return zone_to_nid(zoneref->zone);
}
struct zoneref *__next_zones_zonelist(struct zoneref *z,
enum zone_type highest_zoneidx,
nodemask_t *nodes);
/**
* next_zones_zonelist - Returns the next zone at or below highest_zoneidx within the allowed nodemask using a cursor within a zonelist as a starting point
* @z - The cursor used as a starting point for the search
* @highest_zoneidx - The zone index of the highest zone to return
* @nodes - An optional nodemask to filter the zonelist with
*
* This function returns the next zone at or below a given zone index that is
* within the allowed nodemask using a cursor as the starting point for the
* search. The zoneref returned is a cursor that represents the current zone
* being examined. It should be advanced by one before calling
* next_zones_zonelist again.
*/
static __always_inline struct zoneref *next_zones_zonelist(struct zoneref *z,
enum zone_type highest_zoneidx,
nodemask_t *nodes)
{
if (likely(!nodes && zonelist_zone_idx(z) <= highest_zoneidx))
return z;
return __next_zones_zonelist(z, highest_zoneidx, nodes);
}
/**
* first_zones_zonelist - Returns the first zone at or below highest_zoneidx within the allowed nodemask in a zonelist
* @zonelist - The zonelist to search for a suitable zone
* @highest_zoneidx - The zone index of the highest zone to return
* @nodes - An optional nodemask to filter the zonelist with
* @return - Zoneref pointer for the first suitable zone found (see below)
*
* This function returns the first zone at or below a given zone index that is
* within the allowed nodemask. The zoneref returned is a cursor that can be
* used to iterate the zonelist with next_zones_zonelist by advancing it by
* one before calling.
*
* When no eligible zone is found, zoneref->zone is NULL (zoneref itself is
* never NULL). This may happen either genuinely, or due to concurrent nodemask
* update due to cpuset modification.
*/
static inline struct zoneref *first_zones_zonelist(struct zonelist *zonelist,
enum zone_type highest_zoneidx,
nodemask_t *nodes)
{
return next_zones_zonelist(zonelist->_zonerefs,
highest_zoneidx, nodes);
}
/**
* for_each_zone_zonelist_nodemask - helper macro to iterate over valid zones in a zonelist at or below a given zone index and within a nodemask
* @zone - The current zone in the iterator
* @z - The current pointer within zonelist->zones being iterated
* @zlist - The zonelist being iterated
* @highidx - The zone index of the highest zone to return
* @nodemask - Nodemask allowed by the allocator
*
* This iterator iterates though all zones at or below a given zone index and
* within a given nodemask
*/
#define for_each_zone_zonelist_nodemask(zone, z, zlist, highidx, nodemask) \
for (z = first_zones_zonelist(zlist, highidx, nodemask), zone = zonelist_zone(z); \
zone; \
z = next_zones_zonelist(++z, highidx, nodemask), \
zone = zonelist_zone(z))
#define for_next_zone_zonelist_nodemask(zone, z, zlist, highidx, nodemask) \
for (zone = z->zone; \
zone; \
z = next_zones_zonelist(++z, highidx, nodemask), \
zone = zonelist_zone(z))
/**
* for_each_zone_zonelist - helper macro to iterate over valid zones in a zonelist at or below a given zone index
* @zone - The current zone in the iterator
* @z - The current pointer within zonelist->zones being iterated
* @zlist - The zonelist being iterated
* @highidx - The zone index of the highest zone to return
*
* This iterator iterates though all zones at or below a given zone index.
*/
#define for_each_zone_zonelist(zone, z, zlist, highidx) \
for_each_zone_zonelist_nodemask(zone, z, zlist, highidx, NULL)
#ifdef CONFIG_SPARSEMEM
#include <asm/sparsemem.h>
#endif
#if !defined(CONFIG_HAVE_ARCH_EARLY_PFN_TO_NID) && \
!defined(CONFIG_HAVE_MEMBLOCK_NODE_MAP)
static inline unsigned long early_pfn_to_nid(unsigned long pfn)
{
BUILD_BUG_ON(IS_ENABLED(CONFIG_NUMA));
return 0;
}
#endif
#ifdef CONFIG_FLATMEM
#define pfn_to_nid(pfn) (0)
#endif
#ifdef CONFIG_SPARSEMEM
/*
* SECTION_SHIFT #bits space required to store a section #
*
* PA_SECTION_SHIFT physical address to/from section number
* PFN_SECTION_SHIFT pfn to/from section number
*/
#define PA_SECTION_SHIFT (SECTION_SIZE_BITS)
#define PFN_SECTION_SHIFT (SECTION_SIZE_BITS - PAGE_SHIFT)
#define NR_MEM_SECTIONS (1UL << SECTIONS_SHIFT)
#define PAGES_PER_SECTION (1UL << PFN_SECTION_SHIFT)
#define PAGE_SECTION_MASK (~(PAGES_PER_SECTION-1))
#define SECTION_BLOCKFLAGS_BITS \
((1UL << (PFN_SECTION_SHIFT - pageblock_order)) * NR_PAGEBLOCK_BITS)
#if (MAX_ORDER - 1 + PAGE_SHIFT) > SECTION_SIZE_BITS
#error Allocator MAX_ORDER exceeds SECTION_SIZE
#endif
static inline unsigned long pfn_to_section_nr(unsigned long pfn)
{
return pfn >> PFN_SECTION_SHIFT;
}
static inline unsigned long section_nr_to_pfn(unsigned long sec)
{
return sec << PFN_SECTION_SHIFT;
}
#define SECTION_ALIGN_UP(pfn) (((pfn) + PAGES_PER_SECTION - 1) & PAGE_SECTION_MASK)
#define SECTION_ALIGN_DOWN(pfn) ((pfn) & PAGE_SECTION_MASK)
#define SUBSECTION_SHIFT 21
#define PFN_SUBSECTION_SHIFT (SUBSECTION_SHIFT - PAGE_SHIFT)
#define PAGES_PER_SUBSECTION (1UL << PFN_SUBSECTION_SHIFT)
#define PAGE_SUBSECTION_MASK (~(PAGES_PER_SUBSECTION-1))
#if SUBSECTION_SHIFT > SECTION_SIZE_BITS
#error Subsection size exceeds section size
#else
#define SUBSECTIONS_PER_SECTION (1UL << (SECTION_SIZE_BITS - SUBSECTION_SHIFT))
#endif
#define SUBSECTION_ALIGN_UP(pfn) ALIGN((pfn), PAGES_PER_SUBSECTION)
#define SUBSECTION_ALIGN_DOWN(pfn) ((pfn) & PAGE_SUBSECTION_MASK)
struct mem_section_usage {
DECLARE_BITMAP(subsection_map, SUBSECTIONS_PER_SECTION);
/* See declaration of similar field in struct zone */
unsigned long pageblock_flags[0];
};
void subsection_map_init(unsigned long pfn, unsigned long nr_pages);
struct page;
struct page_ext;
struct mem_section {
/*
* This is, logically, a pointer to an array of struct
* pages. However, it is stored with some other magic.
* (see sparse.c::sparse_init_one_section())
*
* Additionally during early boot we encode node id of
* the location of the section here to guide allocation.
* (see sparse.c::memory_present())
*
* Making it a UL at least makes someone do a cast
* before using it wrong.
*/
unsigned long section_mem_map;
struct mem_section_usage *usage;
#ifdef CONFIG_PAGE_EXTENSION
/*
* If SPARSEMEM, pgdat doesn't have page_ext pointer. We use
* section. (see page_ext.h about this.)
*/
struct page_ext *page_ext;
unsigned long pad;
#endif
/*
* WARNING: mem_section must be a power-of-2 in size for the
* calculation and use of SECTION_ROOT_MASK to make sense.
*/
};
#ifdef CONFIG_SPARSEMEM_EXTREME
#define SECTIONS_PER_ROOT (PAGE_SIZE / sizeof (struct mem_section))
#else
#define SECTIONS_PER_ROOT 1
#endif
#define SECTION_NR_TO_ROOT(sec) ((sec) / SECTIONS_PER_ROOT)
#define NR_SECTION_ROOTS DIV_ROUND_UP(NR_MEM_SECTIONS, SECTIONS_PER_ROOT)
#define SECTION_ROOT_MASK (SECTIONS_PER_ROOT - 1)
#ifdef CONFIG_SPARSEMEM_EXTREME
extern struct mem_section **mem_section;
#else
extern struct mem_section mem_section[NR_SECTION_ROOTS][SECTIONS_PER_ROOT];
#endif
static inline unsigned long *section_to_usemap(struct mem_section *ms)
{
return ms->usage->pageblock_flags;
}
static inline struct mem_section *__nr_to_section(unsigned long nr)
{
unsigned long root = SECTION_NR_TO_ROOT(nr);
if (unlikely(root >= NR_SECTION_ROOTS))
return NULL;
#ifdef CONFIG_SPARSEMEM_EXTREME
if (!mem_section || !mem_section[root])
return NULL;
#endif
return &mem_section[root][nr & SECTION_ROOT_MASK];
}
extern unsigned long __section_nr(struct mem_section *ms);
extern size_t mem_section_usage_size(void);
/*
* We use the lower bits of the mem_map pointer to store
* a little bit of information. The pointer is calculated
* as mem_map - section_nr_to_pfn(pnum). The result is
* aligned to the minimum alignment of the two values:
* 1. All mem_map arrays are page-aligned.
* 2. section_nr_to_pfn() always clears PFN_SECTION_SHIFT
* lowest bits. PFN_SECTION_SHIFT is arch-specific
* (equal SECTION_SIZE_BITS - PAGE_SHIFT), and the
* worst combination is powerpc with 256k pages,
* which results in PFN_SECTION_SHIFT equal 6.
* To sum it up, at least 6 bits are available.
*/
#define SECTION_MARKED_PRESENT (1UL<<0)
#define SECTION_HAS_MEM_MAP (1UL<<1)
#define SECTION_IS_ONLINE (1UL<<2)
#define SECTION_IS_EARLY (1UL<<3)
#define SECTION_MAP_LAST_BIT (1UL<<4)
#define SECTION_MAP_MASK (~(SECTION_MAP_LAST_BIT-1))
#define SECTION_NID_SHIFT 3
static inline struct page *__section_mem_map_addr(struct mem_section *section)
{
unsigned long map = section->section_mem_map;
map &= SECTION_MAP_MASK;
return (struct page *)map;
}
static inline int present_section(struct mem_section *section)
{
return (section && (section->section_mem_map & SECTION_MARKED_PRESENT));
}
static inline int present_section_nr(unsigned long nr)
{
return present_section(__nr_to_section(nr));
}
static inline int valid_section(struct mem_section *section)
{
return (section && (section->section_mem_map & SECTION_HAS_MEM_MAP));
}
static inline int early_section(struct mem_section *section)
{
return (section && (section->section_mem_map & SECTION_IS_EARLY));
}
static inline int valid_section_nr(unsigned long nr)
{
return valid_section(__nr_to_section(nr));
}
static inline int online_section(struct mem_section *section)
{
return (section && (section->section_mem_map & SECTION_IS_ONLINE));
}
static inline int online_section_nr(unsigned long nr)
{
return online_section(__nr_to_section(nr));
}
#ifdef CONFIG_MEMORY_HOTPLUG
void online_mem_sections(unsigned long start_pfn, unsigned long end_pfn);
#ifdef CONFIG_MEMORY_HOTREMOVE
void offline_mem_sections(unsigned long start_pfn, unsigned long end_pfn);
#endif
#endif
static inline struct mem_section *__pfn_to_section(unsigned long pfn)
{
return __nr_to_section(pfn_to_section_nr(pfn));
}
extern unsigned long __highest_present_section_nr;
static inline int subsection_map_index(unsigned long pfn)
{
return (pfn & ~(PAGE_SECTION_MASK)) / PAGES_PER_SUBSECTION;
}
#ifdef CONFIG_SPARSEMEM_VMEMMAP
static inline int pfn_section_valid(struct mem_section *ms, unsigned long pfn)
{
int idx = subsection_map_index(pfn);
return test_bit(idx, ms->usage->subsection_map);
}
#else
static inline int pfn_section_valid(struct mem_section *ms, unsigned long pfn)
{
return 1;
}
#endif
#ifndef CONFIG_HAVE_ARCH_PFN_VALID
static inline int pfn_valid(unsigned long pfn)
{
struct mem_section *ms;
if (pfn_to_section_nr(pfn) >= NR_MEM_SECTIONS)
return 0;
ms = __nr_to_section(pfn_to_section_nr(pfn));
if (!valid_section(ms))
return 0;
/*
* Traditionally early sections always returned pfn_valid() for
* the entire section-sized span.
*/
return early_section(ms) || pfn_section_valid(ms, pfn);
}
#endif
static inline int pfn_present(unsigned long pfn)
{
if (pfn_to_section_nr(pfn) >= NR_MEM_SECTIONS)
return 0;
return present_section(__nr_to_section(pfn_to_section_nr(pfn)));
}
/*
* These are _only_ used during initialisation, therefore they
* can use __initdata ... They could have names to indicate
* this restriction.
*/
#ifdef CONFIG_NUMA
#define pfn_to_nid(pfn) \
({ \
unsigned long __pfn_to_nid_pfn = (pfn); \
page_to_nid(pfn_to_page(__pfn_to_nid_pfn)); \
})
#else
#define pfn_to_nid(pfn) (0)
#endif
#define early_pfn_valid(pfn) pfn_valid(pfn)
void sparse_init(void);
#else
#define sparse_init() do {} while (0)
#define sparse_index_init(_sec, _nid) do {} while (0)
#define pfn_present pfn_valid
#define subsection_map_init(_pfn, _nr_pages) do {} while (0)
#endif /* CONFIG_SPARSEMEM */
/*
* During memory init memblocks map pfns to nids. The search is expensive and
* this caches recent lookups. The implementation of __early_pfn_to_nid
* may treat start/end as pfns or sections.
*/
struct mminit_pfnnid_cache {
unsigned long last_start;
unsigned long last_end;
int last_nid;
};
#ifndef early_pfn_valid
#define early_pfn_valid(pfn) (1)
#endif
void memory_present(int nid, unsigned long start, unsigned long end);
/*
* If it is possible to have holes within a MAX_ORDER_NR_PAGES, then we
* need to check pfn validity within that MAX_ORDER_NR_PAGES block.
* pfn_valid_within() should be used in this case; we optimise this away
* when we have no holes within a MAX_ORDER_NR_PAGES block.
*/
#ifdef CONFIG_HOLES_IN_ZONE
#define pfn_valid_within(pfn) pfn_valid(pfn)
#else
#define pfn_valid_within(pfn) (1)
#endif
#endif /* !__GENERATING_BOUNDS.H */
#endif /* !__ASSEMBLY__ */
#endif /* _LINUX_MMZONE_H */
|