#ifndef _LINUX_MMZONE_H
#define _LINUX_MMZONE_H
-#ifdef __KERNEL__
#ifndef __ASSEMBLY__
#ifndef __GENERATING_BOUNDS_H
#include <linux/seqlock.h>
#include <linux/nodemask.h>
#include <linux/pageblock-flags.h>
-#include <linux/bounds.h>
+#include <generated/bounds.h>
#include <asm/atomic.h>
#include <asm/page.h>
#define MIGRATE_UNMOVABLE 0
#define MIGRATE_RECLAIMABLE 1
#define MIGRATE_MOVABLE 2
+#define MIGRATE_PCPTYPES 3 /* the number of types on the pcp lists */
#define MIGRATE_RESERVE 3
#define MIGRATE_ISOLATE 4 /* can't allocate from here */
#define MIGRATE_TYPES 5
static inline int get_pageblock_migratetype(struct page *page)
{
- if (unlikely(page_group_by_mobility_disabled))
- return MIGRATE_UNMOVABLE;
-
return get_pageblock_flags_group(page, PB_migrate, PB_migrate_end);
}
enum zone_stat_item {
/* First 128 byte cacheline (assuming 64 bit words) */
NR_FREE_PAGES,
- NR_INACTIVE,
- NR_ACTIVE,
+ 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_MLOCK, /* mlock()ed pages found and moved off LRU */
NR_ANON_PAGES, /* Mapped anonymous pages */
NR_FILE_MAPPED, /* pagecache pages mapped into pagetables.
only modified from process context */
NR_FILE_PAGES,
NR_FILE_DIRTY,
NR_WRITEBACK,
- /* Second 128 byte cacheline */
NR_SLAB_RECLAIMABLE,
NR_SLAB_UNRECLAIMABLE,
NR_PAGETABLE, /* used for pagetables */
+ NR_KERNEL_STACK,
+ /* Second 128 byte cacheline */
NR_UNSTABLE_NFS, /* NFS unstable pages */
NR_BOUNCE,
NR_VMSCAN_WRITE,
NR_WRITEBACK_TEMP, /* Writeback using temporary buffers */
+ NR_ISOLATED_ANON, /* Temporary isolated pages from anon lru */
+ NR_ISOLATED_FILE, /* Temporary isolated pages from file lru */
+ NR_SHMEM, /* shmem pages (included tmpfs/GEM pages) */
#ifdef CONFIG_NUMA
NUMA_HIT, /* allocated in intended node */
NUMA_MISS, /* allocated in non intended node */
#endif
NR_VM_ZONE_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(l) for (l = 0; l < NR_LRU_LISTS; l++)
+
+#define for_each_evictable_lru(l) for (l = 0; l <= LRU_ACTIVE_FILE; l++)
+
+static inline int is_file_lru(enum lru_list l)
+{
+ return (l == LRU_INACTIVE_FILE || l == LRU_ACTIVE_FILE);
+}
+
+static inline int is_active_lru(enum lru_list l)
+{
+ return (l == LRU_ACTIVE_ANON || l == LRU_ACTIVE_FILE);
+}
+
+static inline int is_unevictable_lru(enum lru_list l)
+{
+ return (l == LRU_UNEVICTABLE);
+}
+
+enum zone_watermarks {
+ WMARK_MIN,
+ WMARK_LOW,
+ WMARK_HIGH,
+ NR_WMARK
+};
+
+#define min_wmark_pages(z) (z->watermark[WMARK_MIN])
+#define low_wmark_pages(z) (z->watermark[WMARK_LOW])
+#define high_wmark_pages(z) (z->watermark[WMARK_HIGH])
+
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 */
- struct list_head list; /* the list of pages */
+
+ /* Lists of pages, one per migrate type stored on the pcp-lists */
+ struct list_head lists[MIGRATE_PCPTYPES];
};
struct per_cpu_pageset {
#error ZONES_SHIFT -- too many zones configured adjust calculation
#endif
+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 refeferenced.
+ * 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];
+
+ /*
+ * accumulated for batching
+ */
+ unsigned long nr_saved_scan[NR_LRU_LISTS];
+};
+
struct zone {
/* Fields commonly accessed by the page allocator */
- unsigned long pages_min, pages_low, pages_high;
+
+ /* zone watermarks, access with *_wmark_pages(zone) macros */
+ unsigned long watermark[NR_WMARK];
+
/*
* 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
/* Fields commonly accessed by the page reclaim scanner */
spinlock_t lru_lock;
- struct list_head active_list;
- struct list_head inactive_list;
- unsigned long nr_scan_active;
- unsigned long nr_scan_inactive;
+ struct zone_lru {
+ struct list_head list;
+ } lru[NR_LRU_LISTS];
+
+ struct zone_reclaim_stat reclaim_stat;
+
unsigned long pages_scanned; /* since last reclaim */
unsigned long flags; /* zone flags, see below */
*/
int prev_priority;
+ /*
+ * The target ratio of ACTIVE_ANON to INACTIVE_ANON pages on
+ * this zone's LRU. Maintained by the pageout code.
+ */
+ unsigned int inactive_ratio;
+
ZONE_PADDING(_pad2_)
/* Rarely used or read-mostly fields */
struct zone node_zones[MAX_NR_ZONES];
struct zonelist node_zonelists[MAX_ZONELISTS];
int nr_zones;
-#ifdef CONFIG_FLAT_NODE_MEM_MAP
+#ifdef CONFIG_FLAT_NODE_MEM_MAP /* means !SPARSEMEM */
struct page *node_mem_map;
+#ifdef CONFIG_CGROUP_MEM_RES_CTLR
+ struct page_cgroup *node_page_cgroup;
#endif
+#endif
+#ifndef CONFIG_NO_BOOTMEM
struct bootmem_data *bdata;
+#endif
#ifdef CONFIG_MEMORY_HOTPLUG
/*
* Must be held any time you expect node_start_pfn, node_present_pages
/* These two functions are used to setup the per zone pages min values */
struct ctl_table;
-struct file;
-int min_free_kbytes_sysctl_handler(struct ctl_table *, int, struct file *,
+int min_free_kbytes_sysctl_handler(struct ctl_table *, int,
void __user *, size_t *, loff_t *);
extern int sysctl_lowmem_reserve_ratio[MAX_NR_ZONES-1];
-int lowmem_reserve_ratio_sysctl_handler(struct ctl_table *, int, struct file *,
+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, struct file *,
+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,
- struct file *, void __user *, size_t *, loff_t *);
+ void __user *, size_t *, loff_t *);
int sysctl_min_slab_ratio_sysctl_handler(struct ctl_table *, int,
- struct file *, void __user *, size_t *, loff_t *);
+ void __user *, size_t *, loff_t *);
extern int numa_zonelist_order_handler(struct ctl_table *, int,
- struct file *, void __user *, size_t *, loff_t *);
+ void __user *, size_t *, loff_t *);
extern char numa_zonelist_order[];
#define NUMA_ZONELIST_ORDER_LEN 16 /* string buffer size */
-#include <linux/topology.h>
-/* Returns the number of the current Node. */
-#ifndef numa_node_id
-#define numa_node_id() (cpu_to_node(raw_smp_processor_id()))
-#endif
-
#ifndef CONFIG_NEED_MULTIPLE_NODES
extern struct pglist_data contig_page_data;
extern struct zone *next_zone(struct zone *zone);
/**
- * for_each_pgdat - helper macro to iterate over all nodes
+ * 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) \
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;
*
* 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 is used as the next starting
- * point for future calls to next_zones_zonelist().
+ * 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.
*/
struct zoneref *next_zones_zonelist(struct zoneref *z,
enum zone_type highest_zoneidx,
*
* 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. The cursor should
- * not be used by the caller as it does not match the value of the zone
- * returned.
+ * used to iterate the zonelist with next_zones_zonelist by advancing it by
+ * one before calling.
*/
static inline struct zoneref *first_zones_zonelist(struct zonelist *zonelist,
enum zone_type highest_zoneidx,
#define for_each_zone_zonelist_nodemask(zone, z, zlist, highidx, nodemask) \
for (z = first_zones_zonelist(zlist, highidx, nodemask, &zone); \
zone; \
- z = next_zones_zonelist(z, highidx, nodemask, &zone)) \
+ z = next_zones_zonelist(++z, highidx, nodemask, &zone)) \
/**
* for_each_zone_zonelist - helper macro to iterate over valid zones in a zonelist at or below a given zone index
#endif
struct page;
+struct page_cgroup;
struct mem_section {
/*
* This is, logically, a pointer to an array of struct
/* See declaration of similar field in struct zone */
unsigned long *pageblock_flags;
+#ifdef CONFIG_CGROUP_MEM_RES_CTLR
+ /*
+ * If !SPARSEMEM, pgdat doesn't have page_cgroup pointer. We use
+ * section. (see memcontrol.h/page_cgroup.h about this.)
+ */
+ struct page_cgroup *page_cgroup;
+ unsigned long pad;
+#endif
};
#ifdef CONFIG_SPARSEMEM_EXTREME
#endif /* CONFIG_SPARSEMEM */
#ifdef CONFIG_NODES_SPAN_OTHER_NODES
-#define early_pfn_in_nid(pfn, nid) (early_pfn_to_nid(pfn) == (nid))
+bool early_pfn_in_nid(unsigned long pfn, int nid);
#else
#define early_pfn_in_nid(pfn, nid) (1)
#endif
#define pfn_valid_within(pfn) (1)
#endif
+#ifdef CONFIG_ARCH_HAS_HOLES_MEMORYMODEL
+/*
+ * pfn_valid() is meant to be able to tell if a given PFN has valid memmap
+ * associated with it or not. In FLATMEM, it is expected that holes always
+ * have valid memmap as long as there is valid PFNs either side of the hole.
+ * In SPARSEMEM, it is assumed that a valid section has a memmap for the
+ * entire section.
+ *
+ * However, an ARM, and maybe other embedded architectures in the future
+ * free memmap backing holes to save memory on the assumption the memmap is
+ * never used. The page_zone linkages are then broken even though pfn_valid()
+ * returns true. A walker of the full memmap must then do this additional
+ * check to ensure the memmap they are looking at is sane by making sure
+ * the zone and PFN linkages are still valid. This is expensive, but walkers
+ * of the full memmap are extremely rare.
+ */
+int memmap_valid_within(unsigned long pfn,
+ struct page *page, struct zone *zone);
+#else
+static inline int memmap_valid_within(unsigned long pfn,
+ struct page *page, struct zone *zone)
+{
+ return 1;
+}
+#endif /* CONFIG_ARCH_HAS_HOLES_MEMORYMODEL */
+
#endif /* !__GENERATING_BOUNDS.H */
#endif /* !__ASSEMBLY__ */
-#endif /* __KERNEL__ */
#endif /* _LINUX_MMZONE_H */
Code Review / linux-2.6.git / blobdiff