diff options
Diffstat (limited to 'include/linux/mmzone.h')
| -rw-r--r-- | include/linux/mmzone.h | 107 |
1 files changed, 64 insertions, 43 deletions
diff --git a/include/linux/mmzone.h b/include/linux/mmzone.h index 889598537370..39c24ebe9cfd 100644 --- a/include/linux/mmzone.h +++ b/include/linux/mmzone.h @@ -15,7 +15,7 @@ #include <linux/seqlock.h> #include <linux/nodemask.h> #include <linux/pageblock-flags.h> -#include <linux/bounds.h> +#include <generated/bounds.h> #include <asm/atomic.h> #include <asm/page.h> @@ -38,6 +38,7 @@ #define MIGRATE_UNMOVABLE 0 #define MIGRATE_RECLAIMABLE 1 #define MIGRATE_MOVABLE 2 +#define MIGRATE_PCPTYPES 3 /* the number of types on the pcp lists */ #define MIGRATE_RESERVE 3 #define MIGRATE_ISOLATE 4 /* can't allocate from here */ #define MIGRATE_TYPES 5 @@ -94,11 +95,17 @@ enum zone_stat_item { NR_SLAB_RECLAIMABLE, NR_SLAB_UNRECLAIMABLE, NR_PAGETABLE, /* used for pagetables */ + NR_KERNEL_STACK, + /* Second 128 byte cacheline */ NR_UNSTABLE_NFS, /* NFS unstable pages */ NR_BOUNCE, NR_VMSCAN_WRITE, - /* Second 128 byte cacheline */ NR_WRITEBACK_TEMP, /* Writeback using temporary buffers */ + NR_ISOLATED_ANON, /* Temporary isolated pages from anon lru */ + NR_ISOLATED_FILE, /* Temporary isolated pages from file lru */ + NR_SHMEM, /* shmem pages (included tmpfs/GEM pages) */ + NR_DIRTIED, /* page dirtyings since bootup */ + NR_WRITTEN, /* page writings since bootup */ #ifdef CONFIG_NUMA NUMA_HIT, /* allocated in intended node */ NUMA_MISS, /* allocated in non intended node */ @@ -165,7 +172,9 @@ struct per_cpu_pages { int count; /* number of pages in the list */ int high; /* high watermark, emptying needed */ int batch; /* chunk size for buddy add/remove */ - struct list_head list; /* the list of pages */ + + /* Lists of pages, one per migrate type stored on the pcp-lists */ + struct list_head lists[MIGRATE_PCPTYPES]; }; struct per_cpu_pageset { @@ -177,13 +186,7 @@ struct per_cpu_pageset { s8 stat_threshold; s8 vm_stat_diff[NR_VM_ZONE_STAT_ITEMS]; #endif -} ____cacheline_aligned_in_smp; - -#ifdef CONFIG_NUMA -#define zone_pcp(__z, __cpu) ((__z)->pageset[(__cpu)]) -#else -#define zone_pcp(__z, __cpu) (&(__z)->pageset[(__cpu)]) -#endif +}; #endif /* !__GENERATING_BOUNDS.H */ @@ -269,6 +272,11 @@ struct zone_reclaim_stat { */ unsigned long recent_rotated[2]; unsigned long recent_scanned[2]; + + /* + * accumulated for batching + */ + unsigned long nr_saved_scan[NR_LRU_LISTS]; }; struct zone { @@ -278,6 +286,13 @@ struct zone { unsigned long watermark[NR_WMARK]; /* + * When free pages are below this point, additional steps are taken + * when reading the number of free pages to avoid per-cpu counter + * drift allowing watermarks to be breached + */ + unsigned long percpu_drift_mark; + + /* * We don't know if the memory that we're going to allocate will be freeable * or/and it will be released eventually, so to avoid totally wasting several * GB of ram we must reserve some of the lower zone memory (otherwise we risk @@ -294,14 +309,13 @@ struct zone { */ 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]; #endif + struct per_cpu_pageset __percpu *pageset; /* * free areas of different sizes */ spinlock_t lock; + int all_unreclaimable; /* All pages pinned */ #ifdef CONFIG_MEMORY_HOTPLUG /* see spanned/present_pages for more description */ seqlock_t span_seqlock; @@ -316,6 +330,15 @@ struct zone { unsigned long *pageblock_flags; #endif /* CONFIG_SPARSEMEM */ +#ifdef CONFIG_COMPACTION + /* + * On compaction failure, 1<<compact_defer_shift compactions + * are skipped before trying again. The number attempted since + * last failure is tracked with compact_considered. + */ + unsigned int compact_considered; + unsigned int compact_defer_shift; +#endif ZONE_PADDING(_pad1_) @@ -323,7 +346,6 @@ struct zone { spinlock_t lru_lock; struct zone_lru { struct list_head list; - unsigned long nr_saved_scan; /* accumulated for batching */ } lru[NR_LRU_LISTS]; struct zone_reclaim_stat reclaim_stat; @@ -335,21 +357,6 @@ struct zone { 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 - * target at the previous try_to_free_pages() or balance_pgdat() - * invokation. - * - * We use prev_priority as a measure of how much stress page reclaim is - * under - it drives the swappiness decision: whether to unmap mapped - * pages. - * - * Access to both this field is quite racy even on uniprocessor. But - * it is expected to average out OK. - */ - int prev_priority; - - /* * The target ratio of ACTIVE_ANON to INACTIVE_ANON pages on * this zone's LRU. Maintained by the pageout code. */ @@ -414,9 +421,11 @@ struct zone { } ____cacheline_internodealigned_in_smp; typedef enum { - ZONE_ALL_UNRECLAIMABLE, /* all pages pinned */ ZONE_RECLAIM_LOCKED, /* prevents concurrent reclaim */ ZONE_OOM_LOCKED, /* zone is in OOM killer zonelist */ + ZONE_CONGESTED, /* zone has many dirty pages backed by + * a congested BDI + */ } zone_flags_t; static inline void zone_set_flag(struct zone *zone, zone_flags_t flag) @@ -434,9 +443,9 @@ static inline void zone_clear_flag(struct zone *zone, zone_flags_t flag) clear_bit(flag, &zone->flags); } -static inline int zone_is_all_unreclaimable(const struct zone *zone) +static inline int zone_is_reclaim_congested(const struct zone *zone) { - return test_bit(ZONE_ALL_UNRECLAIMABLE, &zone->flags); + return test_bit(ZONE_CONGESTED, &zone->flags); } static inline int zone_is_reclaim_locked(const struct zone *zone) @@ -449,6 +458,12 @@ static inline int zone_is_oom_locked(const struct zone *zone) return test_bit(ZONE_OOM_LOCKED, &zone->flags); } +#ifdef CONFIG_SMP +unsigned long zone_nr_free_pages(struct zone *zone); +#else +#define zone_nr_free_pages(zone) zone_page_state(zone, NR_FREE_PAGES) +#endif /* CONFIG_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 @@ -609,7 +624,9 @@ typedef struct pglist_data { struct page_cgroup *node_page_cgroup; #endif #endif +#ifndef CONFIG_NO_BOOTMEM struct bootmem_data *bdata; +#endif #ifdef CONFIG_MEMORY_HOTPLUG /* * Must be held any time you expect node_start_pfn, node_present_pages @@ -641,9 +658,8 @@ typedef struct pglist_data { #include <linux/memory_hotplug.h> -void get_zone_counts(unsigned long *active, unsigned long *inactive, - unsigned long *free); -void build_all_zonelists(void); +extern struct mutex zonelists_mutex; +void build_all_zonelists(void *data); 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); @@ -661,6 +677,12 @@ void memory_present(int nid, unsigned long start, unsigned long end); static inline void memory_present(int nid, unsigned long start, unsigned long end) {} #endif +#ifdef CONFIG_HAVE_MEMORYLESS_NODES +int local_memory_node(int node_id); +#else +static inline int local_memory_node(int node_id) { return node_id; }; +#endif + #ifdef CONFIG_NEED_NODE_MEMMAP_SIZE unsigned long __init node_memmap_size_bytes(int, unsigned long, unsigned long); #endif @@ -744,21 +766,20 @@ static inline int is_dma(struct zone *zone) /* These two functions are used to setup the per zone pages min values */ struct ctl_table; -struct file; -int min_free_kbytes_sysctl_handler(struct ctl_table *, int, struct file *, +int min_free_kbytes_sysctl_handler(struct ctl_table *, int, void __user *, size_t *, loff_t *); extern int sysctl_lowmem_reserve_ratio[MAX_NR_ZONES-1]; -int lowmem_reserve_ratio_sysctl_handler(struct ctl_table *, int, struct file *, +int lowmem_reserve_ratio_sysctl_handler(struct ctl_table *, int, void __user *, size_t *, loff_t *); -int percpu_pagelist_fraction_sysctl_handler(struct ctl_table *, int, struct file *, +int percpu_pagelist_fraction_sysctl_handler(struct ctl_table *, int, 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 *); + 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 *); + void __user *, size_t *, loff_t *); extern int numa_zonelist_order_handler(struct ctl_table *, int, - struct file *, void __user *, size_t *, loff_t *); + void __user *, size_t *, loff_t *); extern char numa_zonelist_order[]; #define NUMA_ZONELIST_ORDER_LEN 16 /* string buffer size */ @@ -973,7 +994,7 @@ struct mem_section { #endif #define SECTION_NR_TO_ROOT(sec) ((sec) / SECTIONS_PER_ROOT) -#define NR_SECTION_ROOTS (NR_MEM_SECTIONS / SECTIONS_PER_ROOT) +#define NR_SECTION_ROOTS DIV_ROUND_UP(NR_MEM_SECTIONS, SECTIONS_PER_ROOT) #define SECTION_ROOT_MASK (SECTIONS_PER_ROOT - 1) #ifdef CONFIG_SPARSEMEM_EXTREME |