X-Git-Url: http://git.onelab.eu/?a=blobdiff_plain;f=include%2Flinux%2Fmmzone.h;h=b262f47961fbe8a439cc218cd62b20122c5ac957;hb=97bf2856c6014879bd04983a3e9dfcdac1e7fe85;hp=ebfc238cc243482d9baa9b7bb3bd92391d4f6479;hpb=76828883507a47dae78837ab5dec5a5b4513c667;p=linux-2.6.git diff --git a/include/linux/mmzone.h b/include/linux/mmzone.h index ebfc238cc..b262f4796 100644 --- a/include/linux/mmzone.h +++ b/include/linux/mmzone.h @@ -4,7 +4,6 @@ #ifdef __KERNEL__ #ifndef __ASSEMBLY__ -#include #include #include #include @@ -13,7 +12,9 @@ #include #include #include +#include #include +#include /* Free memory management - zoned buddy allocator. */ #ifndef CONFIG_FORCE_MAX_ZONEORDER @@ -21,6 +22,7 @@ #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; @@ -44,6 +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 */ @@ -53,13 +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; @@ -69,53 +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 + * 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 */ @@ -132,6 +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]; @@ -163,12 +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 @@ -180,13 +218,9 @@ struct zone { * under - it drives the swappiness decision: whether to unmap mapped * pages. * - * 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 + * Access to both this field is quite racy even on uniprocessor. But * it is expected to average out OK. */ - int temp_priority; int prev_priority; @@ -195,7 +229,7 @@ struct zone { /* * wait_table -- the array holding the hash table - * wait_table_size -- the size of the hash table array + * wait_table_hash_nr_entries -- 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 @@ -218,14 +252,13 @@ struct zone { * free_area_init_core() performs the initialization of them. */ wait_queue_head_t * wait_table; - unsigned long wait_table_size; + unsigned long wait_table_hash_nr_entries; 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; @@ -245,10 +278,9 @@ struct zone { /* * rarely used fields: */ - char *name; + const 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 @@ -256,21 +288,108 @@ struct zone { */ #define DEF_PRIORITY 12 +/* Maximum number of zones on a zonelist */ +#define MAX_ZONES_PER_ZONELIST (MAX_NUMNODES * MAX_NR_ZONES) + +#ifdef CONFIG_NUMA +/* + * 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 +struct zonelist_cache; +#endif + /* * One allocation request operates on a zonelist. A zonelist * is a list of zones, the first one is the 'goal' of the * allocation, the other zones are fallback zones, in decreasing * priority. * - * Right now a zonelist takes up less than a cacheline. We never - * modify it apart from boot-up, and only a few indices are used, - * so despite the zonelist table being relatively big, the cache - * footprint of this construct is very small. + * 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. */ + struct zonelist { - struct zone *zones[MAX_NUMNODES * MAX_NR_ZONES + 1]; // NULL delimited + struct zonelist_cache *zlcache_ptr; // NULL or &zlcache + struct zone *zones[MAX_ZONES_PER_ZONELIST + 1]; // NULL delimited +#ifdef CONFIG_NUMA + struct zonelist_cache zlcache; // optional ... +#endif }; +#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 @@ -286,7 +405,7 @@ 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; @@ -307,7 +426,6 @@ typedef struct pglist_data { 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; @@ -324,8 +442,6 @@ typedef struct pglist_data { #include -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, @@ -334,6 +450,13 @@ void build_all_zonelists(void); void wakeup_kswapd(struct zone *zone, int order); int zone_watermark_ok(struct zone *z, int order, unsigned long mark, int classzone_idx, int alloc_flags); +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); #ifdef CONFIG_HAVE_MEMORY_PRESENT void memory_present(int nid, unsigned long start, unsigned long end); @@ -350,68 +473,21 @@ unsigned long __init node_memmap_size_bytes(int, unsigned long, unsigned long); */ #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); } -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); } @@ -424,7 +500,11 @@ 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) @@ -434,7 +514,11 @@ 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) @@ -452,6 +536,10 @@ 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 /* Returns the number of the current Node. */ @@ -472,6 +560,30 @@ extern struct pglist_data contig_page_data; #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 #endif @@ -495,7 +607,8 @@ extern struct pglist_data contig_page_data; #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 @@ -535,6 +648,10 @@ struct mem_section { * 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. */ @@ -574,6 +691,7 @@ extern int __section_nr(struct mem_section* ms); #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) { @@ -602,17 +720,6 @@ static inline struct mem_section *__pfn_to_section(unsigned long pfn) 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) @@ -642,6 +749,12 @@ void sparse_init(void); #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