#ifdef __KERNEL__
#ifndef __ASSEMBLY__
+#include <linux/config.h>
#include <linux/spinlock.h>
#include <linux/list.h>
#include <linux/wait.h>
#include <linux/numa.h>
#include <linux/init.h>
#include <linux/seqlock.h>
-#include <linux/nodemask.h>
#include <asm/atomic.h>
-#include <asm/page.h>
/* Free memory management - zoned buddy allocator. */
#ifndef CONFIG_FORCE_MAX_ZONEORDER
#else
#define MAX_ORDER CONFIG_FORCE_MAX_ZONEORDER
#endif
-#define MAX_ORDER_NR_PAGES (1 << (MAX_ORDER - 1))
struct free_area {
struct list_head free_list;
#define ZONE_PADDING(name)
#endif
-enum zone_stat_item {
- NR_ANON_PAGES, /* Mapped anonymous pages */
- NR_FILE_MAPPED, /* pagecache pages mapped into pagetables.
- only modified from process context */
- NR_FILE_PAGES,
- NR_SLAB, /* Pages used by slab allocator */
- NR_PAGETABLE, /* used for pagetables */
- NR_FILE_DIRTY,
- NR_WRITEBACK,
- NR_UNSTABLE_NFS, /* NFS unstable pages */
- NR_BOUNCE,
-#ifdef CONFIG_NUMA
- 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 */
-#endif
- NR_VM_ZONE_STAT_ITEMS };
-
struct per_cpu_pages {
int count; /* number of pages in the list */
int high; /* high watermark, emptying needed */
struct per_cpu_pageset {
struct per_cpu_pages pcp[2]; /* 0: hot. 1: cold */
-#ifdef CONFIG_SMP
- s8 stat_threshold;
- s8 vm_stat_diff[NR_VM_ZONE_STAT_ITEMS];
+#ifdef CONFIG_NUMA
+ unsigned long numa_hit; /* allocated in intended node */
+ unsigned long numa_miss; /* allocated in non intended node */
+ unsigned long numa_foreign; /* was intended here, hit elsewhere */
+ unsigned long interleave_hit; /* interleaver prefered this zone */
+ unsigned long local_node; /* allocation from local node */
+ unsigned long other_node; /* allocation from other node */
#endif
} ____cacheline_aligned_in_smp;
unsigned long lowmem_reserve[MAX_NR_ZONES];
#ifdef CONFIG_NUMA
- /*
- * zone reclaim becomes active if more unmapped pages exist.
- */
- unsigned long min_unmapped_ratio;
- unsigned long min_slab_pages;
struct per_cpu_pageset *pageset[NR_CPUS];
#else
struct per_cpu_pageset pageset[NR_CPUS];
/* A count of how many reclaimers are scanning this zone */
atomic_t reclaim_in_progress;
- /* Zone statistics */
- atomic_long_t vm_stat[NR_VM_ZONE_STAT_ITEMS];
+ /*
+ * timestamp (in jiffies) of the last zone reclaim that did not
+ * result in freeing of pages. This is used to avoid repeated scans
+ * if all memory in the zone is in use.
+ */
+ unsigned long last_unsuccessful_zone_reclaim;
/*
* prev_priority holds the scanning priority for this zone. It is
* under - it drives the swappiness decision: whether to unmap mapped
* pages.
*
- * Access to both this field is quite racy even on uniprocessor. But
+ * temp_priority is used to remember the scanning priority at which
+ * this zone was successfully refilled to free_pages == pages_high.
+ *
+ * Access to both these fields is quite racy even on uniprocessor. But
* it is expected to average out OK.
*/
+ int temp_priority;
int prev_priority;
/*
* wait_table -- the array holding the hash table
- * wait_table_hash_nr_entries -- the size of the hash table array
+ * wait_table_size -- the size of the hash table array
* wait_table_bits -- wait_table_size == (1 << wait_table_bits)
*
* The purpose of all these is to keep track of the people
* free_area_init_core() performs the initialization of them.
*/
wait_queue_head_t * wait_table;
- unsigned long wait_table_hash_nr_entries;
+ unsigned long wait_table_size;
unsigned long wait_table_bits;
/*
* Discontig memory support fields.
*/
struct pglist_data *zone_pgdat;
+ struct page *zone_mem_map;
/* zone_start_pfn == zone_start_paddr >> PAGE_SHIFT */
unsigned long zone_start_pfn;
unsigned long node_spanned_pages; /* total size of physical page
range, including holes */
int node_id;
+ struct pglist_data *pgdat_next;
wait_queue_head_t kswapd_wait;
struct task_struct *kswapd;
int kswapd_max_order;
#include <linux/memory_hotplug.h>
+extern struct pglist_data *pgdat_list;
+
void __get_zone_counts(unsigned long *active, unsigned long *inactive,
unsigned long *free, struct pglist_data *pgdat);
void get_zone_counts(unsigned long *active, unsigned long *inactive,
int zone_watermark_ok(struct zone *z, int order, unsigned long mark,
int classzone_idx, int alloc_flags);
-extern int init_currently_empty_zone(struct zone *zone, unsigned long start_pfn,
- unsigned long size);
-
#ifdef CONFIG_HAVE_MEMORY_PRESENT
void memory_present(int nid, unsigned long start, unsigned long end);
#else
*/
#define zone_idx(zone) ((zone) - (zone)->zone_pgdat->node_zones)
+/**
+ * for_each_pgdat - helper macro to iterate over all nodes
+ * @pgdat - pointer to a pg_data_t variable
+ *
+ * Meant to help with common loops of the form
+ * pgdat = pgdat_list;
+ * while(pgdat) {
+ * ...
+ * pgdat = pgdat->pgdat_next;
+ * }
+ */
+#define for_each_pgdat(pgdat) \
+ for (pgdat = pgdat_list; pgdat; pgdat = pgdat->pgdat_next)
+
+/*
+ * next_zone - helper magic for for_each_zone()
+ * Thanks to William Lee Irwin III for this piece of ingenuity.
+ */
+static inline struct zone *next_zone(struct zone *zone)
+{
+ pg_data_t *pgdat = zone->zone_pgdat;
+
+ if (zone < pgdat->node_zones + MAX_NR_ZONES - 1)
+ zone++;
+ else if (pgdat->pgdat_next) {
+ pgdat = pgdat->pgdat_next;
+ zone = pgdat->node_zones;
+ } else
+ zone = NULL;
+
+ return zone;
+}
+
+/**
+ * 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. This basically means for_each_zone() is an
+ * easier to read version of this piece of code:
+ *
+ * for (pgdat = pgdat_list; pgdat; pgdat = pgdat->node_next)
+ * for (i = 0; i < MAX_NR_ZONES; ++i) {
+ * struct zone * z = pgdat->node_zones + i;
+ * ...
+ * }
+ * }
+ */
+#define for_each_zone(zone) \
+ for (zone = pgdat_list->node_zones; zone; zone = next_zone(zone))
+
static inline int populated_zone(struct zone *zone)
{
return (!!zone->present_pages);
void __user *, size_t *, loff_t *);
int percpu_pagelist_fraction_sysctl_handler(struct ctl_table *, int, struct file *,
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 *);
-int sysctl_min_slab_ratio_sysctl_handler(struct ctl_table *, int,
- struct file *, void __user *, size_t *, loff_t *);
#include <linux/topology.h>
/* Returns the number of the current Node. */
#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_pgdat - helper macro to iterate over all 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))
-
#ifdef CONFIG_SPARSEMEM
#include <asm/sparsemem.h>
#endif
* 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.
*/
#define SECTION_HAS_MEM_MAP (1UL<<1)
#define SECTION_MAP_LAST_BIT (1UL<<2)
#define SECTION_MAP_MASK (~(SECTION_MAP_LAST_BIT-1))
-#define SECTION_NID_SHIFT 2
static inline struct page *__section_mem_map_addr(struct mem_section *section)
{
return __nr_to_section(pfn_to_section_nr(pfn));
}
+#define pfn_to_page(pfn) \
+({ \
+ unsigned long __pfn = (pfn); \
+ __section_mem_map_addr(__pfn_to_section(__pfn)) + __pfn; \
+})
+#define page_to_pfn(page) \
+({ \
+ page - __section_mem_map_addr(__nr_to_section( \
+ page_to_section(page))); \
+})
+
static inline int pfn_valid(unsigned long pfn)
{
if (pfn_to_section_nr(pfn) >= NR_MEM_SECTIONS)
#define sparse_index_init(_sec, _nid) do {} while (0)
#endif /* CONFIG_SPARSEMEM */
-#ifdef CONFIG_NODES_SPAN_OTHER_NODES
-#define early_pfn_in_nid(pfn, nid) (early_pfn_to_nid(pfn) == (nid))
-#else
-#define early_pfn_in_nid(pfn, nid) (1)
-#endif
-
#ifndef early_pfn_valid
#define early_pfn_valid(pfn) (1)
#endif