enum {
MIGRATE_UNMOVABLE,
- MIGRATE_RECLAIMABLE,
MIGRATE_MOVABLE,
+ MIGRATE_RECLAIMABLE,
MIGRATE_PCPTYPES, /* the number of types on the pcp lists */
- MIGRATE_RESERVE = MIGRATE_PCPTYPES,
+ MIGRATE_HIGHATOMIC = MIGRATE_PCPTYPES,
#ifdef CONFIG_CMA
/*
* MIGRATE_CMA migration type is designed to mimic the way
ZONE_HIGHMEM,
#endif
ZONE_MOVABLE,
+#ifdef CONFIG_ZONE_DEVICE
+ ZONE_DEVICE,
+#endif
__MAX_NR_ZONES
+
};
#ifndef __GENERATING_BOUNDS_H
/* zone watermarks, access with *_wmark_pages(zone) macros */
unsigned long watermark[NR_WMARK];
+ 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's tons of freeable ram
- * on the higher zones). This array is recalculated at runtime if the
- * sysctl_lowmem_reserve_ratio sysctl changes.
+ * 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];
const char *name;
- /*
- * Number of MIGRATE_RESERVE page block. To maintain for just
- * optimization. Protected by zone->lock.
- */
- int nr_migrate_reserve_block;
-
#ifdef CONFIG_MEMORY_ISOLATION
/*
* Number of isolated pageblock. It is used to solve incorrect
* [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().
- *
- * 1) The BITMAP fullzones tracks which zones in a zonelist have come
- * up short of free memory since the last time (last_fullzone_zap)
- * we zero'd fullzones.
- * 2) The array z_to_n[] maps each zone in the zonelist to its node
- * id, so that we can efficiently evaluate whether that node is
- * set in the current tasks mems_allowed.
- *
- * Both fullzones and z_to_n[] are one-to-one with the zonelist,
- * indexed by a zones offset in the zonelist zones[] array.
- *
- * The get_page_from_freelist() routine does two scans. During the
- * first scan, we skip zones whose corresponding bit in 'fullzones'
- * is set or whose corresponding node in current->mems_allowed (which
- * comes from cpusets) is not set. During the second scan, we bypass
- * this zonelist_cache, to ensure we look methodically at each zone.
- *
- * Once per second, we zero out (zap) fullzones, forcing us to
- * reconsider nodes that might have regained more free memory.
- * The field last_full_zap is the time we last zapped fullzones.
- *
- * This mechanism reduces the amount of time we waste repeatedly
- * reexaming zones for free memory when they just came up low on
- * memory momentarilly ago.
- *
- * The zonelist_cache struct members logically belong in struct
- * zonelist. However, the mempolicy zonelists constructed for
- * MPOL_BIND are intentionally variable length (and usually much
- * shorter). A general purpose mechanism for handling structs with
- * multiple variable length members is more mechanism than we want
- * here. We resort to some special case hackery instead.
- *
- * The MPOL_BIND zonelists don't need this zonelist_cache (in good
- * part because they are shorter), so we put the fixed length stuff
- * at the front of the zonelist struct, ending in a variable length
- * zones[], as is needed by MPOL_BIND.
- *
- * Then we put the optional zonelist cache on the end of the zonelist
- * struct. This optional stuff is found by a 'zlcache_ptr' pointer in
- * the fixed length portion at the front of the struct. This pointer
- * both enables us to find the zonelist cache, and in the case of
- * MPOL_BIND zonelists, (which will just set the zlcache_ptr to NULL)
- * to know that the zonelist cache is not there.
- *
- * The end result is that struct zonelists come in two flavors:
- * 1) The full, fixed length version, shown below, and
- * 2) The custom zonelists for MPOL_BIND.
- * The custom MPOL_BIND zonelists have a NULL zlcache_ptr and no zlcache.
- *
- * Even though there may be multiple CPU cores on a node modifying
- * fullzones or last_full_zap in the same zonelist_cache at the same
- * time, we don't lock it. This is just hint data - if it is wrong now
- * and then, the allocator will still function, perhaps a bit slower.
- */
-
-
-struct zonelist_cache {
- unsigned short z_to_n[MAX_ZONES_PER_ZONELIST]; /* zone->nid */
- DECLARE_BITMAP(fullzones, MAX_ZONES_PER_ZONELIST); /* zone full? */
- unsigned long last_full_zap; /* when last zap'd (jiffies) */
-};
#else
#define MAX_ZONELISTS 1
-struct zonelist_cache;
#endif
/*
* allocation, the other zones are fallback zones, in decreasing
* priority.
*
- * 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_node_idx() - Return the index of the node for an entry
*/
struct zonelist {
- struct zonelist_cache *zlcache_ptr; // NULL or &zlcache
struct zoneref _zonerefs[MAX_ZONES_PER_ZONELIST + 1];
-#ifdef CONFIG_NUMA
- struct zonelist_cache zlcache; // optional ...
-#endif
};
-#ifdef CONFIG_HAVE_MEMBLOCK_NODE_MAP
-struct node_active_region {
- unsigned long start_pfn;
- unsigned long end_pfn;
- int nid;
-};
-#endif /* CONFIG_HAVE_MEMBLOCK_NODE_MAP */
-
#ifndef CONFIG_DISCONTIGMEM
/* The array of struct pages - for discontigmem use pgdat->lmem_map */
extern struct page *mem_map;
/* Number of pages migrated during the rate limiting time interval */
unsigned long numabalancing_migrate_nr_pages;
#endif
+
+#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 */
} pg_data_t;
#define node_present_pages(nid) (NODE_DATA(nid)->node_present_pages)
return !pgdat->node_start_pfn && !pgdat->node_spanned_pages;
}
+static inline int zone_id(const struct zone *zone)
+{
+ struct pglist_data *pgdat = zone->zone_pgdat;
+
+ return zone - pgdat->node_zones;
+}
+
+#ifdef CONFIG_ZONE_DEVICE
+static inline bool is_dev_zone(const struct zone *zone)
+{
+ return zone_id(zone) == ZONE_DEVICE;
+}
+#else
+static inline bool is_dev_zone(const struct zone *zone)
+{
+ return false;
+}
+#endif
+
#include <linux/memory_hotplug.h>
extern struct mutex zonelists_mutex;
bool zone_watermark_ok(struct zone *z, unsigned int order,
unsigned long mark, int classzone_idx, int alloc_flags);
bool zone_watermark_ok_safe(struct zone *z, unsigned int order,
- unsigned long mark, int classzone_idx, int alloc_flags);
+ unsigned long mark, int classzone_idx);
enum memmap_context {
MEMMAP_EARLY,
MEMMAP_HOTPLUG,
};
extern int init_currently_empty_zone(struct zone *zone, unsigned long start_pfn,
- unsigned long size,
- enum memmap_context context);
+ unsigned long size);
extern void lruvec_init(struct lruvec *lruvec);
#define sparse_index_init(_sec, _nid) do {} while (0)
#endif /* CONFIG_SPARSEMEM */
-#ifdef CONFIG_NODES_SPAN_OTHER_NODES
-bool early_pfn_in_nid(unsigned long pfn, int nid);
-#else
-#define early_pfn_in_nid(pfn, nid) (1)
-#endif
+/*
+ * 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)
Code Review / kvmfornfv.git / blobdiff