diff options
Diffstat (limited to 'include/linux/mmzone.h')
| -rw-r--r-- | include/linux/mmzone.h | 210 |
1 files changed, 176 insertions, 34 deletions
diff --git a/include/linux/mmzone.h b/include/linux/mmzone.h index 5f74891556f3..a4889c9d4055 100644 --- a/include/linux/mmzone.h +++ b/include/linux/mmzone.h @@ -7,6 +7,7 @@ #include <linux/spinlock.h> #include <linux/list.h> +#include <linux/list_nulls.h> #include <linux/wait.h> #include <linux/bitops.h> #include <linux/cache.h> @@ -25,11 +26,13 @@ /* Free memory management - zoned buddy allocator. */ #ifndef CONFIG_ARCH_FORCE_MAX_ORDER -#define MAX_ORDER 11 +#define MAX_ORDER 10 #else #define MAX_ORDER CONFIG_ARCH_FORCE_MAX_ORDER #endif -#define MAX_ORDER_NR_PAGES (1 << (MAX_ORDER - 1)) +#define MAX_ORDER_NR_PAGES (1 << MAX_ORDER) + +#define IS_MAX_ORDER_ALIGNED(pfn) IS_ALIGNED(pfn, MAX_ORDER_NR_PAGES) /* * PAGE_ALLOC_COSTLY_ORDER is the order at which allocations are deemed @@ -92,7 +95,7 @@ static inline bool migratetype_is_mergeable(int mt) } #define for_each_migratetype_order(order, type) \ - for (order = 0; order < MAX_ORDER; order++) \ + for (order = 0; order <= MAX_ORDER; order++) \ for (type = 0; type < MIGRATE_TYPES; type++) extern int page_group_by_mobility_disabled; @@ -107,18 +110,6 @@ struct free_area { unsigned long nr_free; }; -static inline struct page *get_page_from_free_area(struct free_area *area, - int migratetype) -{ - return list_first_entry_or_null(&area->free_list[migratetype], - struct page, lru); -} - -static inline bool free_area_empty(struct free_area *area, int migratetype) -{ - return list_empty(&area->free_list[migratetype]); -} - struct pglist_data; #ifdef CONFIG_NUMA @@ -312,7 +303,7 @@ enum lruvec_flags { * They form a sliding window of a variable size [MIN_NR_GENS, MAX_NR_GENS]. An * offset within MAX_NR_GENS, i.e., gen, indexes the LRU list of the * corresponding generation. The gen counter in folio->flags stores gen+1 while - * a page is on one of lrugen->lists[]. Otherwise it stores 0. + * a page is on one of lrugen->folios[]. Otherwise it stores 0. * * A page is added to the youngest generation on faulting. The aging needs to * check the accessed bit at least twice before handing this page over to the @@ -324,8 +315,8 @@ enum lruvec_flags { * rest of generations, if they exist, are considered inactive. See * lru_gen_is_active(). * - * PG_active is always cleared while a page is on one of lrugen->lists[] so that - * the aging needs not to worry about it. And it's set again when a page + * PG_active is always cleared while a page is on one of lrugen->folios[] so + * that the aging needs not to worry about it. And it's set again when a page * considered active is isolated for non-reclaiming purposes, e.g., migration. * See lru_gen_add_folio() and lru_gen_del_folio(). * @@ -404,7 +395,7 @@ enum { * The number of pages in each generation is eventually consistent and therefore * can be transiently negative when reset_batch_size() is pending. */ -struct lru_gen_struct { +struct lru_gen_folio { /* the aging increments the youngest generation number */ unsigned long max_seq; /* the eviction increments the oldest generation numbers */ @@ -412,7 +403,7 @@ struct lru_gen_struct { /* the birth time of each generation in jiffies */ unsigned long timestamps[MAX_NR_GENS]; /* the multi-gen LRU lists, lazily sorted on eviction */ - struct list_head lists[MAX_NR_GENS][ANON_AND_FILE][MAX_NR_ZONES]; + struct list_head folios[MAX_NR_GENS][ANON_AND_FILE][MAX_NR_ZONES]; /* the multi-gen LRU sizes, eventually consistent */ long nr_pages[MAX_NR_GENS][ANON_AND_FILE][MAX_NR_ZONES]; /* the exponential moving average of refaulted */ @@ -426,6 +417,14 @@ struct lru_gen_struct { atomic_long_t refaulted[NR_HIST_GENS][ANON_AND_FILE][MAX_NR_TIERS]; /* whether the multi-gen LRU is enabled */ bool enabled; +#ifdef CONFIG_MEMCG + /* the memcg generation this lru_gen_folio belongs to */ + u8 gen; + /* the list segment this lru_gen_folio belongs to */ + u8 seg; + /* per-node lru_gen_folio list for global reclaim */ + struct hlist_nulls_node list; +#endif }; enum { @@ -444,24 +443,20 @@ enum { struct lru_gen_mm_state { /* set to max_seq after each iteration */ unsigned long seq; - /* where the current iteration continues (inclusive) */ + /* where the current iteration continues after */ struct list_head *head; - /* where the last iteration ended (exclusive) */ + /* where the last iteration ended before */ struct list_head *tail; - /* to wait for the last page table walker to finish */ - struct wait_queue_head wait; /* Bloom filters flip after each iteration */ unsigned long *filters[NR_BLOOM_FILTERS]; /* the mm stats for debugging */ unsigned long stats[NR_HIST_GENS][NR_MM_STATS]; - /* the number of concurrent page table walkers */ - int nr_walkers; }; struct lru_gen_mm_walk { /* the lruvec under reclaim */ struct lruvec *lruvec; - /* unstable max_seq from lru_gen_struct */ + /* unstable max_seq from lru_gen_folio */ unsigned long max_seq; /* the next address within an mm to scan */ unsigned long next_addr; @@ -479,12 +474,87 @@ void lru_gen_init_lruvec(struct lruvec *lruvec); void lru_gen_look_around(struct page_vma_mapped_walk *pvmw); #ifdef CONFIG_MEMCG + +/* + * For each node, memcgs are divided into two generations: the old and the + * young. For each generation, memcgs are randomly sharded into multiple bins + * to improve scalability. For each bin, the hlist_nulls is virtually divided + * into three segments: the head, the tail and the default. + * + * An onlining memcg is added to the tail of a random bin in the old generation. + * The eviction starts at the head of a random bin in the old generation. The + * per-node memcg generation counter, whose reminder (mod MEMCG_NR_GENS) indexes + * the old generation, is incremented when all its bins become empty. + * + * There are four operations: + * 1. MEMCG_LRU_HEAD, which moves an memcg to the head of a random bin in its + * current generation (old or young) and updates its "seg" to "head"; + * 2. MEMCG_LRU_TAIL, which moves an memcg to the tail of a random bin in its + * current generation (old or young) and updates its "seg" to "tail"; + * 3. MEMCG_LRU_OLD, which moves an memcg to the head of a random bin in the old + * generation, updates its "gen" to "old" and resets its "seg" to "default"; + * 4. MEMCG_LRU_YOUNG, which moves an memcg to the tail of a random bin in the + * young generation, updates its "gen" to "young" and resets its "seg" to + * "default". + * + * The events that trigger the above operations are: + * 1. Exceeding the soft limit, which triggers MEMCG_LRU_HEAD; + * 2. The first attempt to reclaim an memcg below low, which triggers + * MEMCG_LRU_TAIL; + * 3. The first attempt to reclaim an memcg below reclaimable size threshold, + * which triggers MEMCG_LRU_TAIL; + * 4. The second attempt to reclaim an memcg below reclaimable size threshold, + * which triggers MEMCG_LRU_YOUNG; + * 5. Attempting to reclaim an memcg below min, which triggers MEMCG_LRU_YOUNG; + * 6. Finishing the aging on the eviction path, which triggers MEMCG_LRU_YOUNG; + * 7. Offlining an memcg, which triggers MEMCG_LRU_OLD. + * + * Note that memcg LRU only applies to global reclaim, and the round-robin + * incrementing of their max_seq counters ensures the eventual fairness to all + * eligible memcgs. For memcg reclaim, it still relies on mem_cgroup_iter(). + */ +#define MEMCG_NR_GENS 2 +#define MEMCG_NR_BINS 8 + +struct lru_gen_memcg { + /* the per-node memcg generation counter */ + unsigned long seq; + /* each memcg has one lru_gen_folio per node */ + unsigned long nr_memcgs[MEMCG_NR_GENS]; + /* per-node lru_gen_folio list for global reclaim */ + struct hlist_nulls_head fifo[MEMCG_NR_GENS][MEMCG_NR_BINS]; + /* protects the above */ + spinlock_t lock; +}; + +void lru_gen_init_pgdat(struct pglist_data *pgdat); + void lru_gen_init_memcg(struct mem_cgroup *memcg); void lru_gen_exit_memcg(struct mem_cgroup *memcg); -#endif +void lru_gen_online_memcg(struct mem_cgroup *memcg); +void lru_gen_offline_memcg(struct mem_cgroup *memcg); +void lru_gen_release_memcg(struct mem_cgroup *memcg); +void lru_gen_soft_reclaim(struct lruvec *lruvec); + +#else /* !CONFIG_MEMCG */ + +#define MEMCG_NR_GENS 1 + +struct lru_gen_memcg { +}; + +static inline void lru_gen_init_pgdat(struct pglist_data *pgdat) +{ +} + +#endif /* CONFIG_MEMCG */ #else /* !CONFIG_LRU_GEN */ +static inline void lru_gen_init_pgdat(struct pglist_data *pgdat) +{ +} + static inline void lru_gen_init_lruvec(struct lruvec *lruvec) { } @@ -494,6 +564,7 @@ static inline void lru_gen_look_around(struct page_vma_mapped_walk *pvmw) } #ifdef CONFIG_MEMCG + static inline void lru_gen_init_memcg(struct mem_cgroup *memcg) { } @@ -501,7 +572,24 @@ static inline void lru_gen_init_memcg(struct mem_cgroup *memcg) static inline void lru_gen_exit_memcg(struct mem_cgroup *memcg) { } -#endif + +static inline void lru_gen_online_memcg(struct mem_cgroup *memcg) +{ +} + +static inline void lru_gen_offline_memcg(struct mem_cgroup *memcg) +{ +} + +static inline void lru_gen_release_memcg(struct mem_cgroup *memcg) +{ +} + +static inline void lru_gen_soft_reclaim(struct lruvec *lruvec) +{ +} + +#endif /* CONFIG_MEMCG */ #endif /* CONFIG_LRU_GEN */ @@ -524,7 +612,7 @@ struct lruvec { unsigned long flags; #ifdef CONFIG_LRU_GEN /* evictable pages divided into generations */ - struct lru_gen_struct lrugen; + struct lru_gen_folio lrugen; /* to concurrently iterate lru_gen_mm_list */ struct lru_gen_mm_state mm_state; #endif @@ -820,7 +908,7 @@ struct zone { CACHELINE_PADDING(_pad1_); /* free areas of different sizes */ - struct free_area free_area[MAX_ORDER]; + struct free_area free_area[MAX_ORDER + 1]; /* zone flags, see below */ unsigned long flags; @@ -986,6 +1074,25 @@ static inline bool is_zone_device_page(const struct page *page) { return page_zonenum(page) == ZONE_DEVICE; } + +/* + * Consecutive zone device pages should not be merged into the same sgl + * or bvec segment with other types of pages or if they belong to different + * pgmaps. Otherwise getting the pgmap of a given segment is not possible + * without scanning the entire segment. This helper returns true either if + * both pages are not zone device pages or both pages are zone device pages + * with the same pgmap. + */ +static inline bool zone_device_pages_have_same_pgmap(const struct page *a, + const struct page *b) +{ + if (is_zone_device_page(a) != is_zone_device_page(b)) + return false; + if (!is_zone_device_page(a)) + return true; + return a->pgmap == b->pgmap; +} + extern void memmap_init_zone_device(struct zone *, unsigned long, unsigned long, struct dev_pagemap *); #else @@ -993,6 +1100,11 @@ static inline bool is_zone_device_page(const struct page *page) { return false; } +static inline bool zone_device_pages_have_same_pgmap(const struct page *a, + const struct page *b) +{ + return true; +} #endif static inline bool folio_is_zone_device(const struct folio *folio) @@ -1086,6 +1198,31 @@ struct deferred_split { }; #endif +#ifdef CONFIG_MEMORY_FAILURE +/* + * Per NUMA node memory failure handling statistics. + */ +struct memory_failure_stats { + /* + * Number of raw pages poisoned. + * Cases not accounted: memory outside kernel control, offline page, + * arch-specific memory_failure (SGX), hwpoison_filter() filtered + * error events, and unpoison actions from hwpoison_unpoison. + */ + unsigned long total; + /* + * Recovery results of poisoned raw pages handled by memory_failure, + * in sync with mf_result. + * total = ignored + failed + delayed + recovered. + * total * PAGE_SIZE * #nodes = /proc/meminfo/HardwareCorrupted. + */ + unsigned long ignored; + unsigned long failed; + unsigned long delayed; + unsigned long recovered; +}; +#endif + /* * On NUMA machines, each NUMA node would have a pg_data_t to describe * it's memory layout. On UMA machines there is a single pglist_data which @@ -1200,7 +1337,7 @@ typedef struct pglist_data { /* start time in ms of current promote threshold adjustment period */ unsigned int nbp_th_start; /* - * number of promote candidate pages at stat time of current promote + * number of promote candidate pages at start time of current promote * threshold adjustment period */ unsigned long nbp_th_nr_cand; @@ -1218,7 +1355,9 @@ typedef struct pglist_data { #ifdef CONFIG_LRU_GEN /* kswap mm walk data */ - struct lru_gen_mm_walk mm_walk; + struct lru_gen_mm_walk mm_walk; + /* lru_gen_folio list */ + struct lru_gen_memcg memcg_lru; #endif CACHELINE_PADDING(_pad2_); @@ -1229,6 +1368,9 @@ typedef struct pglist_data { #ifdef CONFIG_NUMA struct memory_tier __rcu *memtier; #endif +#ifdef CONFIG_MEMORY_FAILURE + struct memory_failure_stats mf_stats; +#endif } pg_data_t; #define node_present_pages(nid) (NODE_DATA(nid)->node_present_pages) @@ -1589,7 +1731,7 @@ static inline bool movable_only_nodes(nodemask_t *nodes) #define SECTION_BLOCKFLAGS_BITS \ ((1UL << (PFN_SECTION_SHIFT - pageblock_order)) * NR_PAGEBLOCK_BITS) -#if (MAX_ORDER - 1 + PAGE_SHIFT) > SECTION_SIZE_BITS +#if (MAX_ORDER + PAGE_SHIFT) > SECTION_SIZE_BITS #error Allocator MAX_ORDER exceeds SECTION_SIZE #endif |