diff --git a/include/linux/mmzone.h b/include/linux/mmzone.h index 559e659288fcfaedb16b96e5e484fd3e2500dbe6..ed0876bb902c03bb4bb2a5e35e7c6d40862b8f84 100644 --- a/include/linux/mmzone.h +++ b/include/linux/mmzone.h @@ -324,18 +324,11 @@ enum zone_type { #ifndef __GENERATING_BOUNDS_H struct zone { - /* Fields commonly accessed by the page allocator */ + /* Read-mostly fields */ /* zone watermarks, access with *_wmark_pages(zone) macros */ 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 @@ -344,41 +337,26 @@ struct zone { * on the higher zones). This array is recalculated at runtime if the * sysctl_lowmem_reserve_ratio sysctl changes. */ - unsigned long lowmem_reserve[MAX_NR_ZONES]; - - /* - * This is a per-zone reserve of pages that should not be - * considered dirtyable memory. - */ - unsigned long dirty_balance_reserve; + long lowmem_reserve[MAX_NR_ZONES]; #ifdef CONFIG_NUMA int node; +#endif + /* - * zone reclaim becomes active if more unmapped pages exist. + * The target ratio of ACTIVE_ANON to INACTIVE_ANON pages on + * this zone's LRU. Maintained by the pageout code. */ - unsigned long min_unmapped_pages; - unsigned long min_slab_pages; -#endif + unsigned int inactive_ratio; + + struct pglist_data *zone_pgdat; struct per_cpu_pageset __percpu *pageset; + /* - * free areas of different sizes + * This is a per-zone reserve of pages that should not be + * considered dirtyable memory. */ - spinlock_t lock; -#if defined CONFIG_COMPACTION || defined CONFIG_CMA - /* Set to true when the PG_migrate_skip bits should be cleared */ - bool compact_blockskip_flush; - - /* pfn where compaction free scanner should start */ - unsigned long compact_cached_free_pfn; - /* pfn where async and sync compaction migration scanner should start */ - unsigned long compact_cached_migrate_pfn[2]; -#endif -#ifdef CONFIG_MEMORY_HOTPLUG - /* see spanned/present_pages for more description */ - seqlock_t span_seqlock; -#endif - struct free_area free_area[MAX_ORDER]; + unsigned long dirty_balance_reserve; #ifndef CONFIG_SPARSEMEM /* @@ -388,74 +366,14 @@ struct zone { unsigned long *pageblock_flags; #endif /* CONFIG_SPARSEMEM */ -#ifdef CONFIG_COMPACTION - /* - * On compaction failure, 1<> PAGE_SHIFT */ unsigned long zone_start_pfn; @@ -500,9 +418,11 @@ struct zone { * adjust_managed_page_count() should be used instead of directly * touching zone->managed_pages and totalram_pages. */ + unsigned long managed_pages; unsigned long spanned_pages; unsigned long present_pages; - unsigned long managed_pages; + + const char *name; /* * Number of MIGRATE_RESEVE page block. To maintain for just @@ -510,10 +430,95 @@ struct zone { */ int nr_migrate_reserve_block; +#ifdef CONFIG_MEMORY_HOTPLUG + /* see spanned/present_pages for more description */ + seqlock_t span_seqlock; +#endif + /* - * rarely used fields: + * wait_table -- the array holding the hash table + * 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 + * waiting for a page to become available and make them + * runnable again when possible. The trouble is that this + * consumes a lot of space, especially when so few things + * wait on pages at a given time. So instead of using + * per-page waitqueues, we use a waitqueue hash table. + * + * The bucket discipline is to sleep on the same queue when + * colliding and wake all in that wait queue when removing. + * When something wakes, it must check to be sure its page is + * truly available, a la thundering herd. The cost of a + * collision is great, but given the expected load of the + * table, they should be so rare as to be outweighed by the + * benefits from the saved space. + * + * __wait_on_page_locked() and unlock_page() in mm/filemap.c, are the + * primary users of these fields, and in mm/page_alloc.c + * free_area_init_core() performs the initialization of them. */ - const char *name; + wait_queue_head_t *wait_table; + unsigned long wait_table_hash_nr_entries; + unsigned long wait_table_bits; + + ZONE_PADDING(_pad1_) + + /* Write-intensive fields used from the page allocator */ + spinlock_t lock; + + /* free areas of different sizes */ + struct free_area free_area[MAX_ORDER]; + + /* zone flags, see below */ + unsigned long flags; + + ZONE_PADDING(_pad2_) + + /* Write-intensive fields used by page reclaim */ + + /* Fields commonly accessed by the page reclaim scanner */ + spinlock_t lru_lock; + unsigned long pages_scanned; /* since last reclaim */ + struct lruvec lruvec; + + /* Evictions & activations on the inactive file list */ + atomic_long_t inactive_age; + + /* + * 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; + +#if defined CONFIG_COMPACTION || defined CONFIG_CMA + /* pfn where compaction free scanner should start */ + unsigned long compact_cached_free_pfn; + /* pfn where async and sync compaction migration scanner should start */ + unsigned long compact_cached_migrate_pfn[2]; +#endif + +#ifdef CONFIG_COMPACTION + /* + * On compaction failure, 1<lowmem_reserve[classzone_idx]; int o; long free_cma = 0; @@ -1723,7 +1722,7 @@ static bool __zone_watermark_ok(struct zone *z, unsigned int order, free_cma = zone_page_state(z, NR_FREE_CMA_PAGES); #endif - if (free_pages - free_cma <= min + lowmem_reserve) + if (free_pages - free_cma <= min + z->lowmem_reserve[classzone_idx]) return false; for (o = 0; o < order; o++) { /* At the next order, this order's pages become unavailable */ @@ -3254,7 +3253,7 @@ void show_free_areas(unsigned int filter) ); printk("lowmem_reserve[]:"); for (i = 0; i < MAX_NR_ZONES; i++) - printk(" %lu", zone->lowmem_reserve[i]); + printk(" %ld", zone->lowmem_reserve[i]); printk("\n"); } @@ -5575,7 +5574,7 @@ static void calculate_totalreserve_pages(void) for_each_online_pgdat(pgdat) { for (i = 0; i < MAX_NR_ZONES; i++) { struct zone *zone = pgdat->node_zones + i; - unsigned long max = 0; + long max = 0; /* Find valid and maximum lowmem_reserve in the zone */ for (j = i; j < MAX_NR_ZONES; j++) { diff --git a/mm/vmstat.c b/mm/vmstat.c index b37bd49bfd55e206e0845535bc42e7817502ce3b..8267f77d1875dec6287f7a3edb6d9fe2e9e04619 100644 --- a/mm/vmstat.c +++ b/mm/vmstat.c @@ -1077,10 +1077,10 @@ static void zoneinfo_show_print(struct seq_file *m, pg_data_t *pgdat, zone_page_state(zone, i)); seq_printf(m, - "\n protection: (%lu", + "\n protection: (%ld", zone->lowmem_reserve[0]); for (i = 1; i < ARRAY_SIZE(zone->lowmem_reserve); i++) - seq_printf(m, ", %lu", zone->lowmem_reserve[i]); + seq_printf(m, ", %ld", zone->lowmem_reserve[i]); seq_printf(m, ")" "\n pagesets");