#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 <asm/atomic.h>
#include <asm/page.h>
*/
#define PAGE_ALLOC_COSTLY_ORDER 3
+#define MIGRATE_UNMOVABLE 0
+#define MIGRATE_RECLAIMABLE 1
+#define MIGRATE_MOVABLE 2
+#define MIGRATE_RESERVE 3
+#define MIGRATE_ISOLATE 4 /* can't allocate from here */
+#define MIGRATE_TYPES 5
+
+#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;
+
+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);
+}
+
struct free_area {
- struct list_head free_list;
+ struct list_head free_list[MIGRATE_TYPES];
unsigned long nr_free;
};
};
struct per_cpu_pageset {
- struct per_cpu_pages pcp[2]; /* 0: hot. 1: cold */
+ struct per_cpu_pages pcp;
#ifdef CONFIG_NUMA
s8 expire;
#endif
#endif
struct free_area free_area[MAX_ORDER];
+#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_PADDING(_pad1_)
unsigned long nr_scan_active;
unsigned long nr_scan_inactive;
unsigned long pages_scanned; /* since last reclaim */
- int all_unreclaimable; /* All pages pinned */
-
- /* A count of how many reclaimers are scanning this zone */
- atomic_t reclaim_in_progress;
+ unsigned long flags; /* zone flags, see below */
/* Zone statistics */
atomic_long_t vm_stat[NR_VM_ZONE_STAT_ITEMS];
const char *name;
} ____cacheline_internodealigned_in_smp;
+typedef enum {
+ ZONE_ALL_UNRECLAIMABLE, /* all pages pinned */
+ ZONE_RECLAIM_LOCKED, /* prevents concurrent reclaim */
+ ZONE_OOM_LOCKED, /* zone is in OOM killer zonelist */
+} zone_flags_t;
+
+static inline void zone_set_flag(struct zone *zone, zone_flags_t flag)
+{
+ set_bit(flag, &zone->flags);
+}
+
+static inline int zone_test_and_set_flag(struct zone *zone, zone_flags_t flag)
+{
+ return test_and_set_bit(flag, &zone->flags);
+}
+
+static inline void zone_clear_flag(struct zone *zone, zone_flags_t flag)
+{
+ clear_bit(flag, &zone->flags);
+}
+
+static inline int zone_is_all_unreclaimable(const struct zone *zone)
+{
+ return test_bit(ZONE_ALL_UNRECLAIMABLE, &zone->flags);
+}
+
+static inline int zone_is_reclaim_locked(const struct zone *zone)
+{
+ return test_bit(ZONE_RECLAIM_LOCKED, &zone->flags);
+}
+
+static inline int zone_is_oom_locked(const struct zone *zone)
+{
+ return test_bit(ZONE_OOM_LOCKED, &zone->flags);
+}
+
/*
* 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
#define MAX_ZONES_PER_ZONELIST (MAX_NUMNODES * MAX_NR_ZONES)
#ifdef CONFIG_NUMA
+
+/*
+ * The NUMA zonelists are doubled becausse we need zonelists that restrict the
+ * allocations to a single node for GFP_THISNODE.
+ *
+ * [0] : Zonelist with fallback
+ * [1] : No fallback (GFP_THISNODE)
+ */
+#define MAX_ZONELISTS 2
+
+
/*
* We cache key information from each zonelist for smaller cache
* footprint when scanning for free pages in get_page_from_freelist().
unsigned long last_full_zap; /* when last zap'd (jiffies) */
};
#else
+#define MAX_ZONELISTS 1
struct zonelist_cache;
#endif
+/*
+ * 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
*
* If zlcache_ptr is not NULL, then it is just the address of zlcache,
* as explained above. If zlcache_ptr is NULL, there is no zlcache.
+ * *
+ * 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 zonelist_cache *zlcache_ptr; // NULL or &zlcache
- struct zone *zones[MAX_ZONES_PER_ZONELIST + 1]; // NULL delimited
+ struct zoneref _zonerefs[MAX_ZONES_PER_ZONELIST + 1];
#ifdef CONFIG_NUMA
struct zonelist_cache zlcache; // optional ...
#endif
};
-#ifdef CONFIG_NUMA
-/*
- * Only custom zonelists like MPOL_BIND need to be filtered as part of
- * policies. As described in the comment for struct zonelist_cache, these
- * zonelists will not have a zlcache so zlcache_ptr will not be set. Use
- * that to determine if the zonelists needs to be filtered or not.
- */
-static inline int alloc_should_filter_zonelist(struct zonelist *zonelist)
-{
- return !zonelist->zlcache_ptr;
-}
-#else
-static inline int alloc_should_filter_zonelist(struct zonelist *zonelist)
-{
- return 0;
-}
-#endif /* CONFIG_NUMA */
-
#ifdef CONFIG_ARCH_POPULATES_NODE_MAP
struct node_active_region {
unsigned long start_pfn;
struct bootmem_data;
typedef struct pglist_data {
struct zone node_zones[MAX_NR_ZONES];
- struct zonelist node_zonelists[MAX_NR_ZONES];
+ struct zonelist node_zonelists[MAX_ZONELISTS];
int nr_zones;
#ifdef CONFIG_FLAT_NODE_MEM_MAP
struct page *node_mem_map;
static inline int is_highmem(struct zone *zone)
{
#ifdef CONFIG_HIGHMEM
- int zone_idx = zone - zone->zone_pgdat->node_zones;
- return zone_idx == ZONE_HIGHMEM ||
- (zone_idx == ZONE_MOVABLE && zone_movable_is_highmem());
+ int zone_off = (char *)zone - (char *)zone->zone_pgdat->node_zones;
+ return zone_off == ZONE_HIGHMEM * sizeof(*zone) ||
+ (zone_off == ZONE_MOVABLE * sizeof(*zone) &&
+ zone_movable_is_highmem());
#else
return 0;
#endif
extern struct pglist_data contig_page_data;
#define NODE_DATA(nid) (&contig_page_data)
#define NODE_MEM_MAP(nid) mem_map
-#define MAX_NODES_SHIFT 1
#else /* CONFIG_NEED_MULTIPLE_NODES */
zone; \
zone = next_zone(zone))
+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)
+{
+#ifdef CONFIG_NUMA
+ /* zone_to_nid not available in this context */
+ return zoneref->zone->node;
+#else
+ return 0;
+#endif /* CONFIG_NUMA */
+}
+
+static inline void zoneref_set_zone(struct zone *zone, struct zoneref *zoneref)
+{
+ zoneref->zone = zone;
+ zoneref->zone_idx = zone_idx(zone);
+}
+
+/* Returns the first zone at or below highest_zoneidx in a zonelist */
+static inline struct zoneref *first_zones_zonelist(struct zonelist *zonelist,
+ enum zone_type highest_zoneidx)
+{
+ struct zoneref *z;
+
+ /* Find the first suitable zone to use for the allocation */
+ z = zonelist->_zonerefs;
+ while (zonelist_zone_idx(z) > highest_zoneidx)
+ z++;
+
+ return z;
+}
+
+/* Returns the next zone at or below highest_zoneidx in a zonelist */
+static inline struct zoneref *next_zones_zonelist(struct zoneref *z,
+ enum zone_type highest_zoneidx)
+{
+ /* Find the next suitable zone to use for the allocation */
+ while (zonelist_zone_idx(z) > highest_zoneidx)
+ z++;
+
+ return 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 (z = first_zones_zonelist(zlist, highidx), \
+ zone = zonelist_zone(z++); \
+ zone; \
+ z = next_zones_zonelist(z, highidx), \
+ zone = zonelist_zone(z++))
+
#ifdef CONFIG_SPARSEMEM
#include <asm/sparsemem.h>
#endif
#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
* before using it wrong.
*/
unsigned long section_mem_map;
+
+ /* See declaration of similar field in struct zone */
+ unsigned long *pageblock_flags;
};
#ifdef CONFIG_SPARSEMEM_EXTREME
return (struct page *)map;
}
-static inline int valid_section(struct mem_section *section)
+static inline int present_section(struct mem_section *section)
{
return (section && (section->section_mem_map & SECTION_MARKED_PRESENT));
}
-static inline int section_has_mem_map(struct mem_section *section)
+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));
}
return valid_section(__nr_to_section(pfn_to_section_nr(pfn)));
}
+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
git.samba.org / sfrench / cifs-2.6.git / blobdiff