#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>
#endif
#define MAX_ORDER_NR_PAGES (1 << (MAX_ORDER - 1))
+/*
+ * PAGE_ALLOC_COSTLY_ORDER is the order at which allocations are deemed
+ * costly to service. That is between allocation orders which should
+ * coelesce naturally under reasonable reclaim pressure and those which
+ * will not.
+ */
+#define PAGE_ALLOC_COSTLY_ORDER 3
+
+#define MIGRATE_UNMOVABLE 0
+#define MIGRATE_RECLAIMABLE 1
+#define MIGRATE_MOVABLE 2
+#define MIGRATE_RESERVE 3
+#define MIGRATE_TYPES 4
+
+#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;
};
#endif
enum zone_stat_item {
+ /* First 128 byte cacheline (assuming 64 bit words) */
+ NR_FREE_PAGES,
+ NR_INACTIVE,
+ NR_ACTIVE,
NR_ANON_PAGES, /* Mapped anonymous pages */
NR_FILE_MAPPED, /* pagecache pages mapped into pagetables.
only modified from process context */
NR_FILE_PAGES,
- NR_SLAB_RECLAIMABLE,
- NR_SLAB_UNRECLAIMABLE,
- NR_PAGETABLE, /* used for pagetables */
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,
struct per_cpu_pageset {
struct per_cpu_pages pcp[2]; /* 0: hot. 1: cold */
+#ifdef CONFIG_NUMA
+ s8 expire;
+#endif
#ifdef CONFIG_SMP
s8 stat_threshold;
s8 vm_stat_diff[NR_VM_ZONE_STAT_ITEMS];
#endif
enum zone_type {
+#ifdef CONFIG_ZONE_DMA
/*
* ZONE_DMA is used when there are devices that are not able
* to do DMA to all of addressable memory (ZONE_NORMAL). Then we
* ---------------------------
* parisc, ia64, sparc <4G
* s390 <2G
- * arm26 <48M
* arm Various
* alpha Unlimited or 0-16MB.
*
* <16M.
*/
ZONE_DMA,
+#endif
#ifdef CONFIG_ZONE_DMA32
/*
* x86_64 needs two ZONE_DMAs because it supports devices that are
*/
ZONE_HIGHMEM,
#endif
+ ZONE_MOVABLE,
MAX_NR_ZONES
};
* match the requested limits. See gfp_zone() in include/linux/gfp.h
*/
-#if !defined(CONFIG_ZONE_DMA32) && !defined(CONFIG_HIGHMEM)
+/*
+ * Count the active zones. Note that the use of defined(X) outside
+ * #if and family is not necessarily defined so ensure we cannot use
+ * it later. Use __ZONE_COUNT to work out how many shift bits we need.
+ */
+#define __ZONE_COUNT ( \
+ defined(CONFIG_ZONE_DMA) \
+ + defined(CONFIG_ZONE_DMA32) \
+ + 1 \
+ + defined(CONFIG_HIGHMEM) \
+ + 1 \
+)
+#if __ZONE_COUNT < 2
+#define ZONES_SHIFT 0
+#elif __ZONE_COUNT <= 2
#define ZONES_SHIFT 1
-#else
+#elif __ZONE_COUNT <= 4
#define ZONES_SHIFT 2
+#else
+#error ZONES_SHIFT -- too many zones configured adjust calculation
#endif
+#undef __ZONE_COUNT
struct zone {
/* Fields commonly accessed by the page allocator */
- unsigned long free_pages;
unsigned long pages_min, pages_low, pages_high;
/*
* We don't know if the memory that we're going to allocate will be freeable
#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_)
struct list_head inactive_list;
unsigned long nr_scan_active;
unsigned long nr_scan_inactive;
- unsigned long nr_active;
- unsigned long nr_inactive;
unsigned long pages_scanned; /* since last reclaim */
int all_unreclaimable; /* All pages pinned */
#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 .. MAX_NR_ZONES -1] : Zonelists with fallback
+ * [MAZ_NR_ZONES ... MAZ_ZONELISTS -1] : No fallback (GFP_THISNODE)
+ */
+#define MAX_ZONELISTS (2 * MAX_NR_ZONES)
+
+
/*
* 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 MAX_NR_ZONES
struct zonelist_cache;
#endif
#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;
#include <linux/memory_hotplug.h>
-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,
unsigned long *free);
void build_all_zonelists(void);
return (!!zone->present_pages);
}
+extern int movable_zone;
+
+static inline int zone_movable_is_highmem(void)
+{
+#if defined(CONFIG_HIGHMEM) && defined(CONFIG_ARCH_POPULATES_NODE_MAP)
+ return movable_zone == ZONE_HIGHMEM;
+#else
+ return 0;
+#endif
+}
+
static inline int is_highmem_idx(enum zone_type idx)
{
#ifdef CONFIG_HIGHMEM
- return (idx == ZONE_HIGHMEM);
+ return (idx == ZONE_HIGHMEM ||
+ (idx == ZONE_MOVABLE && zone_movable_is_highmem()));
#else
return 0;
#endif
static inline int is_highmem(struct zone *zone)
{
#ifdef CONFIG_HIGHMEM
- return zone == zone->zone_pgdat->node_zones + ZONE_HIGHMEM;
+ int zone_idx = zone - zone->zone_pgdat->node_zones;
+ return zone_idx == ZONE_HIGHMEM ||
+ (zone_idx == ZONE_MOVABLE && zone_movable_is_highmem());
#else
return 0;
#endif
static inline int is_dma(struct zone *zone)
{
+#ifdef CONFIG_ZONE_DMA
return zone == zone->zone_pgdat->node_zones + ZONE_DMA;
+#else
+ return 0;
+#endif
}
/* These two functions are used to setup the per zone pages min values */
int sysctl_min_slab_ratio_sysctl_handler(struct ctl_table *, int,
struct file *, void __user *, size_t *, loff_t *);
+extern int numa_zonelist_order_handler(struct ctl_table *, int,
+ struct file *, 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 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
void memory_present(int nid, unsigned long start, unsigned long end);
unsigned long __init node_memmap_size_bytes(int, unsigned long, unsigned long);
+/*
+ * If it is possible to have holes within a MAX_ORDER_NR_PAGES, then we
+ * need to check pfn validility within that MAX_ORDER_NR_PAGES block.
+ * pfn_valid_within() should be used in this case; we optimise this away
+ * when we have no holes within a MAX_ORDER_NR_PAGES block.
+ */
+#ifdef CONFIG_HOLES_IN_ZONE
+#define pfn_valid_within(pfn) pfn_valid(pfn)
+#else
+#define pfn_valid_within(pfn) (1)
+#endif
+
#endif /* !__ASSEMBLY__ */
#endif /* __KERNEL__ */
#endif /* _LINUX_MMZONE_H */