X-Git-Url: http://ftp.safe.ca/?a=blobdiff_plain;f=include%2Flinux%2Fmmzone.h;h=e06683e2bea39fb61fc02803aff1e5fcee2ce7fd;hb=1399ff54741b3aa0aaf5097b8559fa30277ebe61;hp=6c90461ed99fd5707c178d3b4fbf922b367b55b0;hpb=29751f6991e845f7d002a6ae520bf996b38c8dcd;p=safe%2Fjmp%2Flinux-2.6 diff --git a/include/linux/mmzone.h b/include/linux/mmzone.h index 6c90461..e06683e 100644 --- a/include/linux/mmzone.h +++ b/include/linux/mmzone.h @@ -4,7 +4,6 @@ #ifdef __KERNEL__ #ifndef __ASSEMBLY__ -#include #include #include #include @@ -12,7 +11,10 @@ #include #include #include +#include +#include #include +#include /* Free memory management - zoned buddy allocator. */ #ifndef CONFIG_FORCE_MAX_ZONEORDER @@ -20,6 +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; @@ -37,15 +40,37 @@ struct pglist_data; #if defined(CONFIG_SMP) struct zone_padding { char x[0]; -} ____cacheline_maxaligned_in_smp; +} ____cacheline_internodealigned_in_smp; #define ZONE_PADDING(name) struct zone_padding name; #else #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 low; /* low watermark, refill needed */ int high; /* high watermark, emptying needed */ int batch; /* chunk size for buddy add/remove */ struct list_head list; /* the list of pages */ @@ -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; @@ -69,50 +90,68 @@ struct per_cpu_pageset { #define zone_pcp(__z, __cpu) (&(__z)->pageset[(__cpu)]) #endif -#define ZONE_DMA 0 -#define ZONE_NORMAL 1 -#define ZONE_HIGHMEM 2 - -#define MAX_NR_ZONES 3 /* 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". - */ -#define GFP_ZONEMASK 0x03 -/* - * 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 when the left most bit is not a "loner", otherwise - * use the second. + * match the requested limits. See gfp_zone() in include/linux/gfp.h */ -/* #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 PC we have 3 zones: - * - * ZONE_DMA < 16 MB ISA DMA capable memory - * 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 */ @@ -129,6 +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]; @@ -137,6 +182,10 @@ struct zone { * free areas of different sizes */ spinlock_t lock; +#ifdef CONFIG_MEMORY_HOTPLUG + /* see spanned/present_pages for more description */ + seqlock_t span_seqlock; +#endif struct free_area free_area[MAX_ORDER]; @@ -153,14 +202,12 @@ struct zone { unsigned long pages_scanned; /* since last reclaim */ int all_unreclaimable; /* All pages pinned */ - /* - * Does the allocator try to reclaim pages from the zone as soon - * as it fails a watermark_ok() in __alloc_pages? - */ - int reclaim_pages; /* 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]; + /* * prev_priority holds the scanning priority for this zone. It is * defined as the scanning priority at which we achieved our reclaim @@ -171,13 +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; @@ -186,7 +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 @@ -209,17 +252,26 @@ 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; + /* + * zone_start_pfn, spanned_pages and present_pages are all + * protected by span_seqlock. It is a seqlock because it has + * to be read outside of zone->lock, and it is done in the main + * allocator path. But, it is written quite infrequently. + * + * The lock is declared along with zone->lock because it is + * frequently read in proximity to zone->lock. It's good to + * give them a chance of being in the same cacheline. + */ unsigned long spanned_pages; /* total size, including holes */ unsigned long present_pages; /* amount of memory (excluding holes) */ @@ -227,8 +279,7 @@ struct zone { * rarely used fields: */ char *name; -} ____cacheline_maxaligned_in_smp; - +} ____cacheline_internodealigned_in_smp; /* * The "priority" of VM scanning is how much of the queues we will scan in one @@ -252,6 +303,18 @@ 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 @@ -267,18 +330,27 @@ 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; #endif struct bootmem_data *bdata; +#ifdef CONFIG_MEMORY_HOTPLUG + /* + * Must be held any time you expect node_start_pfn, node_present_pages + * or node_spanned_pages stay constant. Holding this will also + * guarantee that any pfn_valid() stays that way. + * + * Nests above zone->lock and zone->size_seqlock. + */ + spinlock_t node_size_lock; +#endif unsigned long node_start_pfn; unsigned long node_present_pages; /* total number of physical pages */ 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; @@ -293,7 +365,7 @@ typedef struct pglist_data { #endif #define nid_page_nr(nid, pagenr) pgdat_page_nr(NODE_DATA(nid),(pagenr)) -extern struct pglist_data *pgdat_list; +#include void __get_zone_counts(unsigned long *active, unsigned long *inactive, unsigned long *free, struct pglist_data *pgdat); @@ -302,7 +374,10 @@ void get_zone_counts(unsigned long *active, unsigned long *inactive, 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 alloc_type, int can_try_harder, int gfp_high); + 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); @@ -319,66 +394,25 @@ 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) +static inline int populated_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; + return (!!zone->present_pages); } -/** - * 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 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); } + /** * is_highmem - helper function to quickly check if a struct zone is a * highmem zone or not. This is an attempt to keep references @@ -387,7 +421,11 @@ 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) @@ -395,6 +433,20 @@ static inline int is_normal(struct zone *zone) return zone == zone->zone_pgdat->node_zones + ZONE_NORMAL; } +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) +{ + return zone == zone->zone_pgdat->node_zones + ZONE_DMA; +} + /* These two functions are used to setup the per zone pages min values */ struct ctl_table; struct file; @@ -403,10 +455,18 @@ int min_free_kbytes_sysctl_handler(struct ctl_table *, int, struct file *, extern int sysctl_lowmem_reserve_ratio[MAX_NR_ZONES-1]; 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. */ +#ifndef numa_node_id #define numa_node_id() (cpu_to_node(raw_smp_processor_id())) +#endif #ifndef CONFIG_NEED_MULTIPLE_NODES @@ -414,7 +474,6 @@ extern struct pglist_data contig_page_data; #define NODE_DATA(nid) (&contig_page_data) #define NODE_MEM_MAP(nid) mem_map #define MAX_NODES_SHIFT 1 -#define pfn_to_nid(pfn) (0) #else /* CONFIG_NEED_MULTIPLE_NODES */ @@ -422,16 +481,40 @@ 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 -#if BITS_PER_LONG == 32 || defined(ARCH_HAS_ATOMIC_UNSIGNED) +#if BITS_PER_LONG == 32 /* - * with 32 bit page->flags field, we reserve 8 bits for node/zone info. - * there are 3 zones (2 bits) and this leaves 8-2=6 bits for nodes. + * with 32 bit page->flags field, we reserve 9 bits for node/zone info. + * there are 4 zones (3 bits) and this leaves 9-3=6 bits for nodes. */ -#define FLAGS_RESERVED 8 +#define FLAGS_RESERVED 9 #elif BITS_PER_LONG == 64 /* @@ -445,10 +528,15 @@ 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 +#ifdef CONFIG_FLATMEM +#define pfn_to_nid(pfn) (0) +#endif + #define pfn_to_section_nr(pfn) ((pfn) >> PFN_SECTION_SHIFT) #define section_nr_to_pfn(sec) ((sec) << PFN_SECTION_SHIFT) @@ -481,18 +569,39 @@ 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. */ unsigned long section_mem_map; }; -extern struct mem_section mem_section[NR_MEM_SECTIONS]; +#ifdef CONFIG_SPARSEMEM_EXTREME +#define SECTIONS_PER_ROOT (PAGE_SIZE / sizeof (struct mem_section)) +#else +#define SECTIONS_PER_ROOT 1 +#endif + +#define SECTION_NR_TO_ROOT(sec) ((sec) / SECTIONS_PER_ROOT) +#define NR_SECTION_ROOTS (NR_MEM_SECTIONS / SECTIONS_PER_ROOT) +#define SECTION_ROOT_MASK (SECTIONS_PER_ROOT - 1) + +#ifdef CONFIG_SPARSEMEM_EXTREME +extern struct mem_section *mem_section[NR_SECTION_ROOTS]; +#else +extern struct mem_section mem_section[NR_SECTION_ROOTS][SECTIONS_PER_ROOT]; +#endif static inline struct mem_section *__nr_to_section(unsigned long nr) { - return &mem_section[nr]; + if (!mem_section[SECTION_NR_TO_ROOT(nr)]) + return NULL; + return &mem_section[SECTION_NR_TO_ROOT(nr)][nr & SECTION_ROOT_MASK]; } +extern int __section_nr(struct mem_section* ms); /* * We use the lower bits of the mem_map pointer to store @@ -503,6 +612,7 @@ static inline struct mem_section *__nr_to_section(unsigned long nr) #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) { @@ -513,12 +623,12 @@ static inline struct page *__section_mem_map_addr(struct mem_section *section) static inline int valid_section(struct mem_section *section) { - return (section->section_mem_map & SECTION_MARKED_PRESENT); + return (section && (section->section_mem_map & SECTION_MARKED_PRESENT)); } static inline int section_has_mem_map(struct mem_section *section) { - return (section->section_mem_map & SECTION_HAS_MEM_MAP); + return (section && (section->section_mem_map & SECTION_HAS_MEM_MAP)); } static inline int valid_section_nr(unsigned long nr) @@ -526,27 +636,11 @@ static inline int valid_section_nr(unsigned long nr) return valid_section(__nr_to_section(nr)); } -/* - * Given a kernel address, find the home node of the underlying memory. - */ -#define kvaddr_to_nid(kaddr) pfn_to_nid(__pa(kaddr) >> PAGE_SHIFT) - 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) @@ -560,18 +654,20 @@ static inline int pfn_valid(unsigned long pfn) * this restriction. */ #ifdef CONFIG_NUMA -#define pfn_to_nid early_pfn_to_nid -#endif - -#define pfn_to_pgdat(pfn) \ +#define pfn_to_nid(pfn) \ ({ \ - NODE_DATA(pfn_to_nid(pfn)); \ + unsigned long __pfn_to_nid_pfn = (pfn); \ + page_to_nid(pfn_to_page(__pfn_to_nid_pfn)); \ }) +#else +#define pfn_to_nid(pfn) (0) +#endif #define early_pfn_valid(pfn) pfn_valid(pfn) void sparse_init(void); #else #define sparse_init() do {} while (0) +#define sparse_index_init(_sec, _nid) do {} while (0) #endif /* CONFIG_SPARSEMEM */ #ifdef CONFIG_NODES_SPAN_OTHER_NODES