1 files changed, 121 insertions, 57 deletions

diff --git a/include/linux/mmzone.h b/include/linux/mmzone.h
index d6120fa6911..59855b8718a 100644
--- a/include/linux/mmzone.h
+++ b/include/linux/mmzone.h
@@ -46,6 +46,29 @@ struct zone_padding {
 #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_RECLAIMABLE,
+        NR_SLAB_UNRECLAIMABLE,
+        NR_PAGETABLE,   /* used for pagetables */
+        NR_FILE_DIRTY,
+        NR_WRITEBACK,
+        NR_UNSTABLE_NFS,        /* NFS unstable pages */
+        NR_BOUNCE,
+        NR_VMSCAN_WRITE,
+#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 */
@@ -55,13 +78,9 @@ struct per_cpu_pages {
 
 struct per_cpu_pageset {
         struct per_cpu_pages pcp[2];    /* 0: hot.  1: cold */
-#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 */
+#ifdef CONFIG_SMP
+        s8 stat_threshold;
+        s8 vm_stat_diff[NR_VM_ZONE_STAT_ITEMS];
 #endif
 } ____cacheline_aligned_in_smp;
 
@@ -71,53 +90,68 @@ struct per_cpu_pageset {
 #define zone_pcp(__z, __cpu) (&(__z)->pageset[(__cpu)])
 #endif
 
-#define ZONE_DMA                0
-#define ZONE_DMA32              1
-#define ZONE_NORMAL             2
-#define ZONE_HIGHMEM            3
-
-#define MAX_NR_ZONES            4       /* Sync this with ZONES_SHIFT */
-#define ZONES_SHIFT             2       /* ceil(log2(MAX_NR_ZONES)) */
-
+enum zone_type {
+        /*
+         * ZONE_DMA is used when there are devices that are not able
+         * to do DMA to all of addressable memory (ZONE_NORMAL). Then we
+         * carve out the portion of memory that is needed for these devices.
+         * The range is arch specific.
+         *
+         * Some examples
+         *
+         * Architecture         Limit
+         * ---------------------------
+         * parisc, ia64, sparc  <4G
+         * s390                 <2G
+         * arm26                <48M
+         * arm                  Various
+         * alpha                Unlimited or 0-16MB.
+         *
+         * i386, x86_64 and multiple other arches
+         *                      <16M.
+         */
+        ZONE_DMA,
+#ifdef CONFIG_ZONE_DMA32
+        /*
+         * x86_64 needs two ZONE_DMAs because it supports devices that are
+         * only able to do DMA to the lower 16M but also 32 bit devices that
+         * can only do DMA areas below 4G.
+         */
+        ZONE_DMA32,
+#endif
+        /*
+         * Normal addressable memory is in ZONE_NORMAL. DMA operations can be
+         * performed on pages in ZONE_NORMAL if the DMA devices support
+         * transfers to all addressable memory.
+         */
+        ZONE_NORMAL,
+#ifdef CONFIG_HIGHMEM
+        /*
+         * A memory area that is only addressable by the kernel through
+         * mapping portions into its own address space. This is for example
+         * used by i386 to allow the kernel to address the memory beyond
+         * 900MB. The kernel will set up special mappings (page
+         * table entries on i386) for each page that the kernel needs to
+         * access.
+         */
+        ZONE_HIGHMEM,
+#endif
+        MAX_NR_ZONES
+};
 
 /*
  * When a memory allocation must conform to specific limitations (such
  * as being suitable for DMA) the caller will pass in hints to the
  * allocator in the gfp_mask, in the zone modifier bits.  These bits
  * are used to select a priority ordered list of memory zones which
- * match the requested limits.  GFP_ZONEMASK defines which bits within
- * the gfp_mask should be considered as zone modifiers.  Each valid
- * combination of the zone modifier bits has a corresponding list
- * of zones (in node_zonelists).  Thus for two zone modifiers there
- * will be a maximum of 4 (2 ** 2) zonelists, for 3 modifiers there will
- * be 8 (2 ** 3) zonelists.  GFP_ZONETYPES defines the number of possible
- * combinations of zone modifiers in "zone modifier space".
- *
- * As an optimisation any zone modifier bits which are only valid when
- * no other zone modifier bits are set (loners) should be placed in
- * the highest order bits of this field.  This allows us to reduce the
- * extent of the zonelists thus saving space.  For example in the case
- * of three zone modifier bits, we could require up to eight zonelists.
- * If the left most zone modifier is a "loner" then the highest valid
- * zonelist would be four allowing us to allocate only five zonelists.
- * Use the first form for GFP_ZONETYPES when the left most bit is not
- * a "loner", otherwise use the second.
- *
- * NOTE! Make sure this matches the zones in <linux/gfp.h>
+ * match the requested limits. See gfp_zone() in include/linux/gfp.h
  */
-#define GFP_ZONEMASK    0x07
-/* #define GFP_ZONETYPES       (GFP_ZONEMASK + 1) */           /* Non-loner */
-#define GFP_ZONETYPES  ((GFP_ZONEMASK + 1) / 2 + 1)            /* Loner */
 
-/*
- * On machines where it is needed (eg PCs) we divide physical memory
- * into multiple physical zones. On a 32bit PC we have 4 zones:
- *
- * ZONE_DMA       < 16 MB       ISA DMA capable memory
- * ZONE_DMA32        0 MB       Empty
- * ZONE_NORMAL  16-896 MB       direct mapped by the kernel
- * ZONE_HIGHMEM  > 896 MB       only page cache and user processes
- */
+#if !defined(CONFIG_ZONE_DMA32) && !defined(CONFIG_HIGHMEM)
+#define ZONES_SHIFT 1
+#else
+#define ZONES_SHIFT 2
+#endif
 
 struct zone {
         /* Fields commonly accessed by the page allocator */
@@ -134,6 +168,12 @@ struct zone {
         unsigned long           lowmem_reserve[MAX_NR_ZONES];
 
 #ifdef CONFIG_NUMA
+        int node;
+        /*
+         * zone reclaim becomes active if more unmapped pages exist.
+         */
+        unsigned long           min_unmapped_pages;
+        unsigned long           min_slab_pages;
         struct per_cpu_pageset  *pageset[NR_CPUS];
 #else
         struct per_cpu_pageset  pageset[NR_CPUS];
@@ -165,12 +205,8 @@ struct zone {
         /* A count of how many reclaimers are scanning this zone */
         atomic_t                reclaim_in_progress;
 
-        /*
-         * 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;
+        /* Zone statistics */
+        atomic_long_t           vm_stat[NR_VM_ZONE_STAT_ITEMS];
 
         /*
          * prev_priority holds the scanning priority for this zone.  It is
@@ -249,7 +285,6 @@ struct zone {
         char                    *name;
 } ____cacheline_internodealigned_in_smp;
 
-
 /*
  * 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
@@ -272,6 +307,18 @@ struct zonelist {
         struct zone *zones[MAX_NUMNODES * MAX_NR_ZONES + 1]; // NULL delimited
 };
 
+#ifdef CONFIG_ARCH_POPULATES_NODE_MAP
+struct node_active_region {
+        unsigned long start_pfn;
+        unsigned long end_pfn;
+        int nid;
+};
+#endif /* CONFIG_ARCH_POPULATES_NODE_MAP */
+
+#ifndef CONFIG_DISCONTIGMEM
+/* The array of struct pages - for discontigmem use pgdat->lmem_map */
+extern struct page *mem_map;
+#endif
 
 /*
  * The pg_data_t structure is used in machines with CONFIG_DISCONTIGMEM
@@ -287,7 +334,7 @@ struct zonelist {
 struct bootmem_data;
 typedef struct pglist_data {
         struct zone node_zones[MAX_NR_ZONES];
-        struct zonelist node_zonelists[GFP_ZONETYPES];
+        struct zonelist node_zonelists[MAX_NR_ZONES];
         int nr_zones;
 #ifdef CONFIG_FLAT_NODE_MEM_MAP
         struct page *node_mem_map;
@@ -356,12 +403,16 @@ static inline int populated_zone(struct zone *zone)
         return (!!zone->present_pages);
 }
 
-static inline int is_highmem_idx(int idx)
+static inline int is_highmem_idx(enum zone_type idx)
 {
+#ifdef CONFIG_HIGHMEM
         return (idx == ZONE_HIGHMEM);
+#else
+        return 0;
+#endif
 }
 
-static inline int is_normal_idx(int idx)
+static inline int is_normal_idx(enum zone_type idx)
 {
         return (idx == ZONE_NORMAL);
 }
@@ -374,7 +425,11 @@ static inline int is_normal_idx(int idx)
  */
 static inline int is_highmem(struct zone *zone)
 {
+#ifdef CONFIG_HIGHMEM
         return zone == zone->zone_pgdat->node_zones + ZONE_HIGHMEM;
+#else
+        return 0;
+#endif
 }
 
 static inline int is_normal(struct zone *zone)
@@ -384,7 +439,11 @@ static inline int is_normal(struct zone *zone)
 
 static inline int is_dma32(struct zone *zone)
 {
+#ifdef CONFIG_ZONE_DMA32
         return zone == zone->zone_pgdat->node_zones + ZONE_DMA32;
+#else
+        return 0;
+#endif
 }
 
 static inline int is_dma(struct zone *zone)
@@ -402,6 +461,10 @@ int lowmem_reserve_ratio_sysctl_handler(struct ctl_table *, int, struct file *,
                                         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. */
@@ -469,7 +532,8 @@ extern struct zone *next_zone(struct zone *zone);
 
 #endif
 
-#ifndef CONFIG_HAVE_ARCH_EARLY_PFN_TO_NID
+#if !defined(CONFIG_HAVE_ARCH_EARLY_PFN_TO_NID) && \
+        !defined(CONFIG_ARCH_POPULATES_NODE_MAP)
 #define early_pfn_to_nid(nid)  (0UL)
 #endif