#ifndef _LINUX_MMZONE_H
#define _LINUX_MMZONE_H
-#ifdef __KERNEL__
#ifndef __ASSEMBLY__
#ifndef __GENERATING_BOUNDS_H
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, /* " " " " " */
+#ifdef CONFIG_UNEVICTABLE_LRU
+ NR_UNEVICTABLE, /* " " " " " */
+ NR_MLOCK, /* mlock()ed pages found and moved off LRU */
+#else
+ NR_UNEVICTABLE = NR_ACTIVE_FILE, /* avoid compiler errors in dead code */
+ NR_MLOCK = NR_ACTIVE_FILE,
+#endif
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_UNSTABLE_NFS, /* NFS unstable pages */
NR_BOUNCE,
NR_VMSCAN_WRITE,
+ /* Second 128 byte cacheline */
+ NR_WRITEBACK_TEMP, /* Writeback using temporary buffers */
#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,
+#ifdef CONFIG_UNEVICTABLE_LRU
+ LRU_UNEVICTABLE,
+#else
+ LRU_UNEVICTABLE = LRU_ACTIVE_FILE, /* avoid compiler errors in dead code */
+#endif
+ 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)
+{
+#ifdef CONFIG_UNEVICTABLE_LRU
+ return (l == LRU_UNEVICTABLE);
+#else
+ return 0;
+#endif
+}
+
struct per_cpu_pages {
int count; /* number of pages in the list */
int high; /* high watermark, emptying needed */
#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];
+};
+
struct zone {
/* Fields commonly accessed by the page allocator */
unsigned long pages_min, pages_low, pages_high;
/* 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 {
+ struct list_head list;
+ unsigned long nr_scan;
+ } 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
struct bootmem_data *bdata;
#ifdef CONFIG_MEMORY_HOTPLUG
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) \
*
* 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
return &mem_section[SECTION_NR_TO_ROOT(nr)][nr & SECTION_ROOT_MASK];
}
extern int __section_nr(struct mem_section* ms);
+extern unsigned long usemap_size(void);
/*
* We use the lower bits of the mem_map pointer to store
#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
#endif /* !__GENERATING_BOUNDS.H */
#endif /* !__ASSEMBLY__ */
-#endif /* __KERNEL__ */
#endif /* _LINUX_MMZONE_H */