diff options
Diffstat (limited to 'include/linux/mmzone.h')
| -rw-r--r-- | include/linux/mmzone.h | 2203 |
1 files changed, 1618 insertions, 585 deletions
diff --git a/include/linux/mmzone.h b/include/linux/mmzone.h index af4a3b77a8de..4398e027f450 100644 --- a/include/linux/mmzone.h +++ b/include/linux/mmzone.h @@ -1,3 +1,4 @@ +/* SPDX-License-Identifier: GPL-2.0 */ #ifndef _LINUX_MMZONE_H #define _LINUX_MMZONE_H @@ -6,6 +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> @@ -17,15 +19,39 @@ #include <linux/pageblock-flags.h> #include <linux/page-flags-layout.h> #include <linux/atomic.h> +#include <linux/mm_types.h> +#include <linux/page-flags.h> +#include <linux/local_lock.h> +#include <linux/zswap.h> #include <asm/page.h> /* Free memory management - zoned buddy allocator. */ -#ifndef CONFIG_FORCE_MAX_ZONEORDER -#define MAX_ORDER 11 +#ifndef CONFIG_ARCH_FORCE_MAX_ORDER +#define MAX_PAGE_ORDER 10 #else -#define MAX_ORDER CONFIG_FORCE_MAX_ZONEORDER +#define MAX_PAGE_ORDER CONFIG_ARCH_FORCE_MAX_ORDER +#endif +#define MAX_ORDER_NR_PAGES (1 << MAX_PAGE_ORDER) + +#define IS_MAX_ORDER_ALIGNED(pfn) IS_ALIGNED(pfn, MAX_ORDER_NR_PAGES) + +#define NR_PAGE_ORDERS (MAX_PAGE_ORDER + 1) + +/* Defines the order for the number of pages that have a migrate type. */ +#ifndef CONFIG_PAGE_BLOCK_MAX_ORDER +#define PAGE_BLOCK_MAX_ORDER MAX_PAGE_ORDER +#else +#define PAGE_BLOCK_MAX_ORDER CONFIG_PAGE_BLOCK_MAX_ORDER +#endif /* CONFIG_PAGE_BLOCK_MAX_ORDER */ + +/* + * The MAX_PAGE_ORDER, which defines the max order of pages to be allocated + * by the buddy allocator, has to be larger or equal to the PAGE_BLOCK_MAX_ORDER, + * which defines the order for the number of pages that can have a migrate type + */ +#if (PAGE_BLOCK_MAX_ORDER > MAX_PAGE_ORDER) +#error MAX_PAGE_ORDER must be >= PAGE_BLOCK_MAX_ORDER #endif -#define MAX_ORDER_NR_PAGES (1 << (MAX_ORDER - 1)) /* * PAGE_ALLOC_COSTLY_ORDER is the order at which allocations are deemed @@ -35,12 +61,12 @@ */ #define PAGE_ALLOC_COSTLY_ORDER 3 -enum { +enum migratetype { MIGRATE_UNMOVABLE, - MIGRATE_RECLAIMABLE, MIGRATE_MOVABLE, + MIGRATE_RECLAIMABLE, MIGRATE_PCPTYPES, /* the number of types on the pcp lists */ - MIGRATE_RESERVE = MIGRATE_PCPTYPES, + MIGRATE_HIGHATOMIC = MIGRATE_PCPTYPES, #ifdef CONFIG_CMA /* * MIGRATE_CMA migration type is designed to mimic the way @@ -50,12 +76,12 @@ enum { * * The way to use it is to change migratetype of a range of * pageblocks to MIGRATE_CMA which can be done by - * __free_pageblock_cma() function. What is important though - * is that a range of pageblocks must be aligned to - * MAX_ORDER_NR_PAGES should biggest page be bigger then - * a single pageblock. + * __free_pageblock_cma() function. */ MIGRATE_CMA, + __MIGRATE_TYPE_END = MIGRATE_CMA, +#else + __MIGRATE_TYPE_END = MIGRATE_HIGHATOMIC, #endif #ifdef CONFIG_MEMORY_ISOLATION MIGRATE_ISOLATE, /* can't allocate from here */ @@ -63,22 +89,51 @@ enum { MIGRATE_TYPES }; +/* In mm/page_alloc.c; keep in sync also with show_migration_types() there */ +extern const char * const migratetype_names[MIGRATE_TYPES]; + #ifdef CONFIG_CMA # define is_migrate_cma(migratetype) unlikely((migratetype) == MIGRATE_CMA) +# define is_migrate_cma_page(_page) (get_pageblock_migratetype(_page) == MIGRATE_CMA) +/* + * __dump_folio() in mm/debug.c passes a folio pointer to on-stack struct folio, + * so folio_pfn() cannot be used and pfn is needed. + */ +# define is_migrate_cma_folio(folio, pfn) \ + (get_pfnblock_migratetype(&folio->page, pfn) == MIGRATE_CMA) #else # define is_migrate_cma(migratetype) false +# define is_migrate_cma_page(_page) false +# define is_migrate_cma_folio(folio, pfn) false #endif +static inline bool is_migrate_movable(int mt) +{ + return is_migrate_cma(mt) || mt == MIGRATE_MOVABLE; +} + +/* + * Check whether a migratetype can be merged with another migratetype. + * + * It is only mergeable when it can fall back to other migratetypes for + * allocation. See fallbacks[MIGRATE_TYPES][3] in page_alloc.c. + */ +static inline bool migratetype_is_mergeable(int mt) +{ + return mt < MIGRATE_PCPTYPES; +} + #define for_each_migratetype_order(order, type) \ - for (order = 0; order < MAX_ORDER; order++) \ + for (order = 0; order < NR_PAGE_ORDERS; order++) \ for (type = 0; type < MIGRATE_TYPES; type++) extern int page_group_by_mobility_disabled; -static inline int get_pageblock_migratetype(struct page *page) -{ - return get_pageblock_flags_group(page, PB_migrate, PB_migrate_end); -} +#define get_pageblock_migratetype(page) \ + get_pfnblock_migratetype(page, page_to_pfn(page)) + +#define folio_migratetype(folio) \ + get_pageblock_migratetype(&folio->page) struct free_area { struct list_head free_list[MIGRATE_TYPES]; @@ -87,63 +142,163 @@ struct free_area { struct pglist_data; -/* - * zone->lock and zone->lru_lock are two of the hottest locks in the kernel. - * So add a wild amount of padding here to ensure that they fall into separate - * cachelines. There are very few zone structures in the machine, so space - * consumption is not a concern here. - */ -#if defined(CONFIG_SMP) -struct zone_padding { - char x[0]; -} ____cacheline_internodealigned_in_smp; -#define ZONE_PADDING(name) struct zone_padding name; +#ifdef CONFIG_NUMA +enum numa_stat_item { + 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 */ + NR_VM_NUMA_EVENT_ITEMS +}; #else -#define ZONE_PADDING(name) +#define NR_VM_NUMA_EVENT_ITEMS 0 #endif enum zone_stat_item { /* First 128 byte cacheline (assuming 64 bit words) */ NR_FREE_PAGES, + NR_FREE_PAGES_BLOCKS, + NR_ZONE_LRU_BASE, /* Used only for compaction and reclaim retry */ + NR_ZONE_INACTIVE_ANON = NR_ZONE_LRU_BASE, + NR_ZONE_ACTIVE_ANON, + NR_ZONE_INACTIVE_FILE, + NR_ZONE_ACTIVE_FILE, + NR_ZONE_UNEVICTABLE, + NR_ZONE_WRITE_PENDING, /* Count of dirty, writeback and unstable pages */ + NR_MLOCK, /* mlock()ed pages found and moved off LRU */ + /* Second 128 byte cacheline */ +#if IS_ENABLED(CONFIG_ZSMALLOC) + NR_ZSPAGES, /* allocated in zsmalloc */ +#endif + NR_FREE_CMA_PAGES, +#ifdef CONFIG_UNACCEPTED_MEMORY + NR_UNACCEPTED, +#endif + NR_VM_ZONE_STAT_ITEMS }; + +enum node_stat_item { NR_LRU_BASE, NR_INACTIVE_ANON = NR_LRU_BASE, /* must match order of LRU_[IN]ACTIVE */ NR_ACTIVE_ANON, /* " " " " " */ NR_INACTIVE_FILE, /* " " " " " */ NR_ACTIVE_FILE, /* " " " " " */ NR_UNEVICTABLE, /* " " " " " */ - NR_MLOCK, /* mlock()ed pages found and moved off LRU */ - NR_ANON_PAGES, /* Mapped anonymous pages */ + NR_SLAB_RECLAIMABLE_B, + NR_SLAB_UNRECLAIMABLE_B, + NR_ISOLATED_ANON, /* Temporary isolated pages from anon lru */ + NR_ISOLATED_FILE, /* Temporary isolated pages from file lru */ + WORKINGSET_NODES, + WORKINGSET_REFAULT_BASE, + WORKINGSET_REFAULT_ANON = WORKINGSET_REFAULT_BASE, + WORKINGSET_REFAULT_FILE, + WORKINGSET_ACTIVATE_BASE, + WORKINGSET_ACTIVATE_ANON = WORKINGSET_ACTIVATE_BASE, + WORKINGSET_ACTIVATE_FILE, + WORKINGSET_RESTORE_BASE, + WORKINGSET_RESTORE_ANON = WORKINGSET_RESTORE_BASE, + WORKINGSET_RESTORE_FILE, + WORKINGSET_NODERECLAIM, + NR_ANON_MAPPED, /* Mapped anonymous pages */ NR_FILE_MAPPED, /* pagecache pages mapped into pagetables. only modified from process context */ NR_FILE_PAGES, NR_FILE_DIRTY, NR_WRITEBACK, - 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_SHMEM, /* shmem pages (included tmpfs/GEM pages) */ + NR_SHMEM_THPS, + NR_SHMEM_PMDMAPPED, + NR_FILE_THPS, + NR_FILE_PMDMAPPED, + NR_ANON_THPS, NR_VMSCAN_WRITE, NR_VMSCAN_IMMEDIATE, /* Prioritise for reclaim when writeback ends */ - 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 */ - 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 */ + NR_THROTTLED_WRITTEN, /* NR_WRITTEN while reclaim throttled */ + NR_KERNEL_MISC_RECLAIMABLE, /* reclaimable non-slab kernel pages */ + NR_FOLL_PIN_ACQUIRED, /* via: pin_user_page(), gup flag: FOLL_PIN */ + NR_FOLL_PIN_RELEASED, /* pages returned via unpin_user_page() */ + NR_KERNEL_STACK_KB, /* measured in KiB */ +#if IS_ENABLED(CONFIG_SHADOW_CALL_STACK) + NR_KERNEL_SCS_KB, /* measured in KiB */ #endif - NR_ANON_TRANSPARENT_HUGEPAGES, - NR_FREE_CMA_PAGES, - NR_VM_ZONE_STAT_ITEMS }; + NR_PAGETABLE, /* used for pagetables */ + NR_SECONDARY_PAGETABLE, /* secondary pagetables, KVM & IOMMU */ +#ifdef CONFIG_IOMMU_SUPPORT + NR_IOMMU_PAGES, /* # of pages allocated by IOMMU */ +#endif +#ifdef CONFIG_SWAP + NR_SWAPCACHE, +#endif +#ifdef CONFIG_NUMA_BALANCING + PGPROMOTE_SUCCESS, /* promote successfully */ + /** + * Candidate pages for promotion based on hint fault latency. This + * counter is used to control the promotion rate and adjust the hot + * threshold. + */ + PGPROMOTE_CANDIDATE, + /** + * Not rate-limited (NRL) candidate pages for those can be promoted + * without considering hot threshold because of enough free pages in + * fast-tier node. These promotions bypass the regular hotness checks + * and do NOT influence the promotion rate-limiter or + * threshold-adjustment logic. + * This is for statistics/monitoring purposes. + */ + PGPROMOTE_CANDIDATE_NRL, +#endif + /* PGDEMOTE_*: pages demoted */ + PGDEMOTE_KSWAPD, + PGDEMOTE_DIRECT, + PGDEMOTE_KHUGEPAGED, + PGDEMOTE_PROACTIVE, +#ifdef CONFIG_HUGETLB_PAGE + NR_HUGETLB, +#endif + NR_BALLOON_PAGES, + NR_KERNEL_FILE_PAGES, + NR_VM_NODE_STAT_ITEMS +}; + +/* + * Returns true if the item should be printed in THPs (/proc/vmstat + * currently prints number of anon, file and shmem THPs. But the item + * is charged in pages). + */ +static __always_inline bool vmstat_item_print_in_thp(enum node_stat_item item) +{ + if (!IS_ENABLED(CONFIG_TRANSPARENT_HUGEPAGE)) + return false; + + return item == NR_ANON_THPS || + item == NR_FILE_THPS || + item == NR_SHMEM_THPS || + item == NR_SHMEM_PMDMAPPED || + item == NR_FILE_PMDMAPPED; +} + +/* + * Returns true if the value is measured in bytes (most vmstat values are + * measured in pages). This defines the API part, the internal representation + * might be different. + */ +static __always_inline bool vmstat_item_in_bytes(int idx) +{ + /* + * Global and per-node slab counters track slab pages. + * It's expected that changes are multiples of PAGE_SIZE. + * Internally values are stored in pages. + * + * Per-memcg and per-lruvec counters track memory, consumed + * by individual slab objects. These counters are actually + * byte-precise. + */ + return (idx == NR_SLAB_RECLAIMABLE_B || + idx == NR_SLAB_UNRECLAIMABLE_B); +} /* * We do arithmetic on the LRU lists in various places in the code, @@ -167,124 +322,480 @@ enum lru_list { NR_LRU_LISTS }; +enum vmscan_throttle_state { + VMSCAN_THROTTLE_WRITEBACK, + VMSCAN_THROTTLE_ISOLATED, + VMSCAN_THROTTLE_NOPROGRESS, + VMSCAN_THROTTLE_CONGESTED, + NR_VMSCAN_THROTTLE, +}; + #define for_each_lru(lru) for (lru = 0; lru < NR_LRU_LISTS; lru++) #define for_each_evictable_lru(lru) for (lru = 0; lru <= LRU_ACTIVE_FILE; lru++) -static inline int is_file_lru(enum lru_list lru) +static inline bool is_file_lru(enum lru_list lru) { return (lru == LRU_INACTIVE_FILE || lru == LRU_ACTIVE_FILE); } -static inline int is_active_lru(enum lru_list lru) +static inline bool is_active_lru(enum lru_list lru) { return (lru == LRU_ACTIVE_ANON || lru == LRU_ACTIVE_FILE); } -static inline int is_unevictable_lru(enum lru_list lru) -{ - return (lru == LRU_UNEVICTABLE); -} +#define WORKINGSET_ANON 0 +#define WORKINGSET_FILE 1 +#define ANON_AND_FILE 2 -struct zone_reclaim_stat { +enum lruvec_flags { /* - * The pageout code in vmscan.c keeps track of how many of the - * mem/swap backed and file backed pages are referenced. - * The higher the rotated/scanned ratio, the more valuable - * that cache is. + * An lruvec has many dirty pages backed by a congested BDI: + * 1. LRUVEC_CGROUP_CONGESTED is set by cgroup-level reclaim. + * It can be cleared by cgroup reclaim or kswapd. + * 2. LRUVEC_NODE_CONGESTED is set by kswapd node-level reclaim. + * It can only be cleared by kswapd. * - * The anon LRU stats live in [0], file LRU stats in [1] + * Essentially, kswapd can unthrottle an lruvec throttled by cgroup + * reclaim, but not vice versa. This only applies to the root cgroup. + * The goal is to prevent cgroup reclaim on the root cgroup (e.g. + * memory.reclaim) to unthrottle an unbalanced node (that was throttled + * by kswapd). */ - unsigned long recent_rotated[2]; - unsigned long recent_scanned[2]; + LRUVEC_CGROUP_CONGESTED, + LRUVEC_NODE_CONGESTED, +}; + +#endif /* !__GENERATING_BOUNDS_H */ + +/* + * Evictable folios are divided into multiple generations. The youngest and the + * oldest generation numbers, max_seq and min_seq, are monotonically increasing. + * 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 folio is on one of lrugen->folios[]. Otherwise it stores 0. + * + * After a folio is faulted in, the aging needs to check the accessed bit at + * least twice before handing this folio over to the eviction. The first check + * clears the accessed bit from the initial fault; the second check makes sure + * this folio hasn't been used since then. This process, AKA second chance, + * requires a minimum of two generations, hence MIN_NR_GENS. And to maintain ABI + * compatibility with the active/inactive LRU, e.g., /proc/vmstat, these two + * generations are considered active; the rest of generations, if they exist, + * are considered inactive. See lru_gen_is_active(). + * + * PG_active is always cleared while a folio is on one of lrugen->folios[] so + * that the sliding window needs not to worry about it. And it's set again when + * a folio considered active is isolated for non-reclaiming purposes, e.g., + * migration. See lru_gen_add_folio() and lru_gen_del_folio(). + * + * MAX_NR_GENS is set to 4 so that the multi-gen LRU can support twice the + * number of categories of the active/inactive LRU when keeping track of + * accesses through page tables. This requires order_base_2(MAX_NR_GENS+1) bits + * in folio->flags, masked by LRU_GEN_MASK. + */ +#define MIN_NR_GENS 2U +#define MAX_NR_GENS 4U + +/* + * Each generation is divided into multiple tiers. A folio accessed N times + * through file descriptors is in tier order_base_2(N). A folio in the first + * tier (N=0,1) is marked by PG_referenced unless it was faulted in through page + * tables or read ahead. A folio in the last tier (MAX_NR_TIERS-1) is marked by + * PG_workingset. A folio in any other tier (1<N<5) between the first and last + * is marked by additional bits of LRU_REFS_WIDTH in folio->flags. + * + * In contrast to moving across generations which requires the LRU lock, moving + * across tiers only involves atomic operations on folio->flags and therefore + * has a negligible cost in the buffered access path. In the eviction path, + * comparisons of refaulted/(evicted+protected) from the first tier and the rest + * infer whether folios accessed multiple times through file descriptors are + * statistically hot and thus worth protecting. + * + * MAX_NR_TIERS is set to 4 so that the multi-gen LRU can support twice the + * number of categories of the active/inactive LRU when keeping track of + * accesses through file descriptors. This uses MAX_NR_TIERS-2 spare bits in + * folio->flags, masked by LRU_REFS_MASK. + */ +#define MAX_NR_TIERS 4U + +#ifndef __GENERATING_BOUNDS_H + +#define LRU_GEN_MASK ((BIT(LRU_GEN_WIDTH) - 1) << LRU_GEN_PGOFF) +#define LRU_REFS_MASK ((BIT(LRU_REFS_WIDTH) - 1) << LRU_REFS_PGOFF) + +/* + * For folios accessed multiple times through file descriptors, + * lru_gen_inc_refs() sets additional bits of LRU_REFS_WIDTH in folio->flags + * after PG_referenced, then PG_workingset after LRU_REFS_WIDTH. After all its + * bits are set, i.e., LRU_REFS_FLAGS|BIT(PG_workingset), a folio is lazily + * promoted into the second oldest generation in the eviction path. And when + * folio_inc_gen() does that, it clears LRU_REFS_FLAGS so that + * lru_gen_inc_refs() can start over. Note that for this case, LRU_REFS_MASK is + * only valid when PG_referenced is set. + * + * For folios accessed multiple times through page tables, folio_update_gen() + * from a page table walk or lru_gen_set_refs() from a rmap walk sets + * PG_referenced after the accessed bit is cleared for the first time. + * Thereafter, those two paths set PG_workingset and promote folios to the + * youngest generation. Like folio_inc_gen(), folio_update_gen() also clears + * PG_referenced. Note that for this case, LRU_REFS_MASK is not used. + * + * For both cases above, after PG_workingset is set on a folio, it remains until + * this folio is either reclaimed, or "deactivated" by lru_gen_clear_refs(). It + * can be set again if lru_gen_test_recent() returns true upon a refault. + */ +#define LRU_REFS_FLAGS (LRU_REFS_MASK | BIT(PG_referenced)) + +struct lruvec; +struct page_vma_mapped_walk; + +#ifdef CONFIG_LRU_GEN + +enum { + LRU_GEN_ANON, + LRU_GEN_FILE, +}; + +enum { + LRU_GEN_CORE, + LRU_GEN_MM_WALK, + LRU_GEN_NONLEAF_YOUNG, + NR_LRU_GEN_CAPS +}; + +#define MIN_LRU_BATCH BITS_PER_LONG +#define MAX_LRU_BATCH (MIN_LRU_BATCH * 64) + +/* whether to keep historical stats from evicted generations */ +#ifdef CONFIG_LRU_GEN_STATS +#define NR_HIST_GENS MAX_NR_GENS +#else +#define NR_HIST_GENS 1U +#endif + +/* + * The youngest generation number is stored in max_seq for both anon and file + * types as they are aged on an equal footing. The oldest generation numbers are + * stored in min_seq[] separately for anon and file types so that they can be + * incremented independently. Ideally min_seq[] are kept in sync when both anon + * and file types are evictable. However, to adapt to situations like extreme + * swappiness, they are allowed to be out of sync by at most + * MAX_NR_GENS-MIN_NR_GENS-1. + * + * 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_folio { + /* the aging increments the youngest generation number */ + unsigned long max_seq; + /* the eviction increments the oldest generation numbers */ + unsigned long min_seq[ANON_AND_FILE]; + /* 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 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 */ + unsigned long avg_refaulted[ANON_AND_FILE][MAX_NR_TIERS]; + /* the exponential moving average of evicted+protected */ + unsigned long avg_total[ANON_AND_FILE][MAX_NR_TIERS]; + /* can only be modified under the LRU lock */ + unsigned long protected[NR_HIST_GENS][ANON_AND_FILE][MAX_NR_TIERS]; + /* can be modified without holding the LRU lock */ + atomic_long_t evicted[NR_HIST_GENS][ANON_AND_FILE][MAX_NR_TIERS]; + atomic_long_t refaulted[NR_HIST_GENS][ANON_AND_FILE][MAX_NR_TIERS]; + /* whether the multi-gen LRU is enabled */ + bool enabled; + /* 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; +}; + +enum { + MM_LEAF_TOTAL, /* total leaf entries */ + MM_LEAF_YOUNG, /* young leaf entries */ + MM_NONLEAF_FOUND, /* non-leaf entries found in Bloom filters */ + MM_NONLEAF_ADDED, /* non-leaf entries added to Bloom filters */ + NR_MM_STATS +}; + +/* double-buffering Bloom filters */ +#define NR_BLOOM_FILTERS 2 + +struct lru_gen_mm_state { + /* synced with max_seq after each iteration */ + unsigned long seq; + /* where the current iteration continues after */ + struct list_head *head; + /* where the last iteration ended before */ + struct list_head *tail; + /* 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]; +}; + +struct lru_gen_mm_walk { + /* the lruvec under reclaim */ + struct lruvec *lruvec; + /* max_seq from lru_gen_folio: can be out of date */ + unsigned long seq; + /* the next address within an mm to scan */ + unsigned long next_addr; + /* to batch promoted pages */ + int nr_pages[MAX_NR_GENS][ANON_AND_FILE][MAX_NR_ZONES]; + /* to batch the mm stats */ + int mm_stats[NR_MM_STATS]; + /* total batched items */ + int batched; + int swappiness; + bool force_scan; }; +/* + * 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 a 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 a 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 a 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 a 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 a memcg below low, which triggers + * MEMCG_LRU_TAIL; + * 3. The first attempt to reclaim a memcg offlined or below reclaimable size + * threshold, which triggers MEMCG_LRU_TAIL; + * 4. The second attempt to reclaim a memcg offlined or below reclaimable size + * threshold, which triggers MEMCG_LRU_YOUNG; + * 5. Attempting to reclaim a memcg below min, which triggers MEMCG_LRU_YOUNG; + * 6. Finishing the aging on the eviction path, which triggers MEMCG_LRU_YOUNG; + * 7. Offlining a memcg, which triggers MEMCG_LRU_OLD. + * + * Notes: + * 1. 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(). + * 2. There are only two valid generations: old (seq) and young (seq+1). + * MEMCG_NR_GENS is set to three so that when reading the generation counter + * locklessly, a stale value (seq-1) does not wraparound to young. + */ +#define MEMCG_NR_GENS 3 +#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_lruvec(struct lruvec *lruvec); +bool lru_gen_look_around(struct page_vma_mapped_walk *pvmw); + +void lru_gen_init_memcg(struct mem_cgroup *memcg); +void lru_gen_exit_memcg(struct mem_cgroup *memcg); +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 mem_cgroup *memcg, int nid); + +#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) +{ +} + +static inline bool lru_gen_look_around(struct page_vma_mapped_walk *pvmw) +{ + return false; +} + +static inline void lru_gen_init_memcg(struct mem_cgroup *memcg) +{ +} + +static inline void lru_gen_exit_memcg(struct mem_cgroup *memcg) +{ +} + +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 mem_cgroup *memcg, int nid) +{ +} + +#endif /* CONFIG_LRU_GEN */ + struct lruvec { - struct list_head lists[NR_LRU_LISTS]; - struct zone_reclaim_stat reclaim_stat; + struct list_head lists[NR_LRU_LISTS]; + /* per lruvec lru_lock for memcg */ + spinlock_t lru_lock; + /* + * These track the cost of reclaiming one LRU - file or anon - + * over the other. As the observed cost of reclaiming one LRU + * increases, the reclaim scan balance tips toward the other. + */ + unsigned long anon_cost; + unsigned long file_cost; + /* Non-resident age, driven by LRU movement */ + atomic_long_t nonresident_age; + /* Refaults at the time of last reclaim cycle */ + unsigned long refaults[ANON_AND_FILE]; + /* Various lruvec state flags (enum lruvec_flags) */ + unsigned long flags; +#ifdef CONFIG_LRU_GEN + /* evictable pages divided into generations */ + struct lru_gen_folio lrugen; +#ifdef CONFIG_LRU_GEN_WALKS_MMU + /* to concurrently iterate lru_gen_mm_list */ + struct lru_gen_mm_state mm_state; +#endif +#endif /* CONFIG_LRU_GEN */ #ifdef CONFIG_MEMCG - struct zone *zone; + struct pglist_data *pgdat; #endif + struct zswap_lruvec_state zswap_lruvec_state; }; -/* Mask used at gathering information at once (see memcontrol.c) */ -#define LRU_ALL_FILE (BIT(LRU_INACTIVE_FILE) | BIT(LRU_ACTIVE_FILE)) -#define LRU_ALL_ANON (BIT(LRU_INACTIVE_ANON) | BIT(LRU_ACTIVE_ANON)) -#define LRU_ALL ((1 << NR_LRU_LISTS) - 1) - -/* Isolate clean file */ -#define ISOLATE_CLEAN ((__force isolate_mode_t)0x1) -/* Isolate unmapped file */ -#define ISOLATE_UNMAPPED ((__force isolate_mode_t)0x2) /* Isolate for asynchronous migration */ #define ISOLATE_ASYNC_MIGRATE ((__force isolate_mode_t)0x4) /* Isolate unevictable pages */ #define ISOLATE_UNEVICTABLE ((__force isolate_mode_t)0x8) /* LRU Isolation modes. */ -typedef unsigned __bitwise__ isolate_mode_t; +typedef unsigned __bitwise isolate_mode_t; enum zone_watermarks { WMARK_MIN, WMARK_LOW, WMARK_HIGH, + WMARK_PROMO, NR_WMARK }; -#define min_wmark_pages(z) (z->watermark[WMARK_MIN]) -#define low_wmark_pages(z) (z->watermark[WMARK_LOW]) -#define high_wmark_pages(z) (z->watermark[WMARK_HIGH]) +/* + * One per migratetype for each PAGE_ALLOC_COSTLY_ORDER. Two additional lists + * are added for THP. One PCP list is used by GPF_MOVABLE, and the other PCP list + * is used by GFP_UNMOVABLE and GFP_RECLAIMABLE. + */ +#ifdef CONFIG_TRANSPARENT_HUGEPAGE +#define NR_PCP_THP 2 +#else +#define NR_PCP_THP 0 +#endif +#define NR_LOWORDER_PCP_LISTS (MIGRATE_PCPTYPES * (PAGE_ALLOC_COSTLY_ORDER + 1)) +#define NR_PCP_LISTS (NR_LOWORDER_PCP_LISTS + NR_PCP_THP) + +/* + * Flags used in pcp->flags field. + * + * PCPF_PREV_FREE_HIGH_ORDER: a high-order page is freed in the + * previous page freeing. To avoid to drain PCP for an accident + * high-order page freeing. + * + * PCPF_FREE_HIGH_BATCH: preserve "pcp->batch" pages in PCP before + * draining PCP for consecutive high-order pages freeing without + * allocation if data cache slice of CPU is large enough. To reduce + * zone lock contention and keep cache-hot pages reusing. + */ +#define PCPF_PREV_FREE_HIGH_ORDER BIT(0) +#define PCPF_FREE_HIGH_BATCH BIT(1) struct per_cpu_pages { + spinlock_t lock; /* Protects lists field */ int count; /* number of pages in the list */ int high; /* high watermark, emptying needed */ + int high_min; /* min high watermark */ + int high_max; /* max high watermark */ int batch; /* chunk size for buddy add/remove */ + u8 flags; /* protected by pcp->lock */ + u8 alloc_factor; /* batch scaling factor during allocate */ +#ifdef CONFIG_NUMA + u8 expire; /* When 0, remote pagesets are drained */ +#endif + short free_count; /* consecutive free count */ /* Lists of pages, one per migrate type stored on the pcp-lists */ - struct list_head lists[MIGRATE_PCPTYPES]; -}; + struct list_head lists[NR_PCP_LISTS]; +} ____cacheline_aligned_in_smp; -struct per_cpu_pageset { - struct per_cpu_pages pcp; -#ifdef CONFIG_NUMA - s8 expire; -#endif +struct per_cpu_zonestat { #ifdef CONFIG_SMP - s8 stat_threshold; s8 vm_stat_diff[NR_VM_ZONE_STAT_ITEMS]; + s8 stat_threshold; #endif +#ifdef CONFIG_NUMA + /* + * Low priority inaccurate counters that are only folded + * on demand. Use a large type to avoid the overhead of + * folding during refresh_cpu_vm_stats. + */ + unsigned long vm_numa_event[NR_VM_NUMA_EVENT_ITEMS]; +#endif +}; + +struct per_cpu_nodestat { + s8 stat_threshold; + s8 vm_node_stat_diff[NR_VM_NODE_STAT_ITEMS]; }; #endif /* !__GENERATING_BOUNDS.H */ enum zone_type { -#ifdef CONFIG_ZONE_DMA /* - * 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 - * arm Various - * alpha Unlimited or 0-16MB. - * - * i386, x86_64 and multiple other arches - * <16M. + * ZONE_DMA and ZONE_DMA32 are used when there are peripherals not able + * to DMA to all of the addressable memory (ZONE_NORMAL). + * On architectures where this area covers the whole 32 bit address + * space ZONE_DMA32 is used. ZONE_DMA is left for the ones with smaller + * DMA addressing constraints. This distinction is important as a 32bit + * DMA mask is assumed when ZONE_DMA32 is defined. Some 64-bit + * platforms may need both zones as they support peripherals with + * different DMA addressing limitations. */ +#ifdef CONFIG_ZONE_DMA ZONE_DMA, #endif #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 /* @@ -304,68 +815,101 @@ enum zone_type { */ ZONE_HIGHMEM, #endif + /* + * ZONE_MOVABLE is similar to ZONE_NORMAL, except that it contains + * movable pages with few exceptional cases described below. Main use + * cases for ZONE_MOVABLE are to make memory offlining/unplug more + * likely to succeed, and to locally limit unmovable allocations - e.g., + * to increase the number of THP/huge pages. Notable special cases are: + * + * 1. Pinned pages: (long-term) pinning of movable pages might + * essentially turn such pages unmovable. Therefore, we do not allow + * pinning long-term pages in ZONE_MOVABLE. When pages are pinned and + * faulted, they come from the right zone right away. However, it is + * still possible that address space already has pages in + * ZONE_MOVABLE at the time when pages are pinned (i.e. user has + * touches that memory before pinning). In such case we migrate them + * to a different zone. When migration fails - pinning fails. + * 2. memblock allocations: kernelcore/movablecore setups might create + * situations where ZONE_MOVABLE contains unmovable allocations + * after boot. Memory offlining and allocations fail early. + * 3. Memory holes: kernelcore/movablecore setups might create very rare + * situations where ZONE_MOVABLE contains memory holes after boot, + * for example, if we have sections that are only partially + * populated. Memory offlining and allocations fail early. + * 4. PG_hwpoison pages: while poisoned pages can be skipped during + * memory offlining, such pages cannot be allocated. + * 5. Unmovable PG_offline pages: in paravirtualized environments, + * hotplugged memory blocks might only partially be managed by the + * buddy (e.g., via XEN-balloon, Hyper-V balloon, virtio-mem). The + * parts not manged by the buddy are unmovable PG_offline pages. In + * some cases (virtio-mem), such pages can be skipped during + * memory offlining, however, cannot be moved/allocated. These + * techniques might use alloc_contig_range() to hide previously + * exposed pages from the buddy again (e.g., to implement some sort + * of memory unplug in virtio-mem). + * 6. ZERO_PAGE(0), kernelcore/movablecore setups might create + * situations where ZERO_PAGE(0) which is allocated differently + * on different platforms may end up in a movable zone. ZERO_PAGE(0) + * cannot be migrated. + * 7. Memory-hotplug: when using memmap_on_memory and onlining the + * memory to the MOVABLE zone, the vmemmap pages are also placed in + * such zone. Such pages cannot be really moved around as they are + * self-stored in the range, but they are treated as movable when + * the range they describe is about to be offlined. + * + * In general, no unmovable allocations that degrade memory offlining + * should end up in ZONE_MOVABLE. Allocators (like alloc_contig_range()) + * have to expect that migrating pages in ZONE_MOVABLE can fail (even + * if has_unmovable_pages() states that there are no unmovable pages, + * there can be false negatives). + */ ZONE_MOVABLE, +#ifdef CONFIG_ZONE_DEVICE + ZONE_DEVICE, +#endif __MAX_NR_ZONES + }; #ifndef __GENERATING_BOUNDS_H +#define ASYNC_AND_SYNC 2 + 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; + unsigned long _watermark[NR_WMARK]; + unsigned long watermark_boost; - /* - * 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 - * to run OOM on the lower zones despite there's tons of freeable ram - * 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]; + unsigned long nr_reserved_highatomic; + unsigned long nr_free_highatomic; /* - * This is a per-zone reserve of pages that should not be - * considered dirtyable memory. + * 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 to run OOM on the lower zones despite + * there being tons of freeable ram on the higher zones). This array is + * recalculated at runtime if the sysctl_lowmem_reserve_ratio sysctl + * changes. */ - unsigned long dirty_balance_reserve; + 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; #endif - struct per_cpu_pageset __percpu *pageset; + struct pglist_data *zone_pgdat; + struct per_cpu_pages __percpu *per_cpu_pageset; + struct per_cpu_zonestat __percpu *per_cpu_zonestats; /* - * free areas of different sizes + * the high and batch values are copied to individual pagesets for + * faster access */ - spinlock_t lock; - int all_unreclaimable; /* All pages pinned */ -#if defined CONFIG_COMPACTION || defined CONFIG_CMA - /* Set to true when the PG_migrate_skip bits should be cleared */ - bool compact_blockskip_flush; - - /* pfns where compaction scanners should start */ - unsigned long compact_cached_free_pfn; - unsigned long compact_cached_migrate_pfn; -#endif -#ifdef CONFIG_MEMORY_HOTPLUG - /* see spanned/present_pages for more description */ - seqlock_t span_seqlock; -#endif - struct free_area free_area[MAX_ORDER]; + int pageset_high_min; + int pageset_high_max; + int pageset_batch; #ifndef CONFIG_SPARSEMEM /* @@ -375,71 +919,6 @@ 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; - int compact_order_failed; -#endif - - ZONE_PADDING(_pad1_) - - /* Fields commonly accessed by the page reclaim scanner */ - spinlock_t lru_lock; - struct lruvec lruvec; - - unsigned long pages_scanned; /* since last reclaim */ - unsigned long flags; /* zone flags, see below */ - - /* Zone statistics */ - atomic_long_t vm_stat[NR_VM_ZONE_STAT_ITEMS]; - - /* - * The target ratio of ACTIVE_ANON to INACTIVE_ANON pages on - * this zone's LRU. Maintained by the pageout code. - */ - unsigned int inactive_ratio; - - - ZONE_PADDING(_pad2_) - /* Rarely used or read-mostly 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. - */ - wait_queue_head_t * wait_table; - unsigned long wait_table_hash_nr_entries; - unsigned long wait_table_bits; - - /* - * Discontig memory support fields. - */ - struct pglist_data *zone_pgdat; /* zone_start_pfn == zone_start_paddr >> PAGE_SHIFT */ unsigned long zone_start_pfn; @@ -452,11 +931,18 @@ struct zone { * is calculated as: * present_pages = spanned_pages - absent_pages(pages in holes); * + * present_early_pages is present pages existing within the zone + * located on memory available since early boot, excluding hotplugged + * memory. + * * managed_pages is present pages managed by the buddy system, which * is calculated as (reserved_pages includes pages allocated by the * bootmem allocator): * managed_pages = present_pages - reserved_pages; * + * cma pages is present pages that are assigned for CMA use + * (MIGRATE_CMA). + * * So present_pages may be used by memory hotplug or memory power * management logic to figure out unmanaged pages by checking * (present_pages - managed_pages). And managed_pages should be used @@ -475,79 +961,157 @@ struct zone { * give them a chance of being in the same cacheline. * * Write access to present_pages at runtime should be protected by - * lock_memory_hotplug()/unlock_memory_hotplug(). Any reader who can't - * tolerant drift of present_pages should hold memory hotplug lock to - * get a stable value. - * - * Read access to managed_pages should be safe because it's unsigned - * long. Write access to zone->managed_pages and totalram_pages are - * protected by managed_page_count_lock at runtime. Idealy only - * adjust_managed_page_count() should be used instead of directly - * touching zone->managed_pages and totalram_pages. + * mem_hotplug_begin/done(). Any reader who can't tolerant drift of + * present_pages should use get_online_mems() to get a stable value. */ + atomic_long_t managed_pages; unsigned long spanned_pages; unsigned long present_pages; - unsigned long managed_pages; +#if defined(CONFIG_MEMORY_HOTPLUG) + unsigned long present_early_pages; +#endif +#ifdef CONFIG_CMA + unsigned long cma_pages; +#endif + + const char *name; +#ifdef CONFIG_MEMORY_ISOLATION /* - * rarely used fields: + * Number of isolated pageblock. It is used to solve incorrect + * freepage counting problem due to racy retrieving migratetype + * of pageblock. Protected by zone->lock. */ - const char *name; + unsigned long nr_isolate_pageblock; +#endif + +#ifdef CONFIG_MEMORY_HOTPLUG + /* see spanned/present_pages for more description */ + seqlock_t span_seqlock; +#endif + + int initialized; + + /* Write-intensive fields used from the page allocator */ + CACHELINE_PADDING(_pad1_); + + /* free areas of different sizes */ + struct free_area free_area[NR_PAGE_ORDERS]; + +#ifdef CONFIG_UNACCEPTED_MEMORY + /* Pages to be accepted. All pages on the list are MAX_PAGE_ORDER */ + struct list_head unaccepted_pages; + + /* To be called once the last page in the zone is accepted */ + struct work_struct unaccepted_cleanup; +#endif + + /* zone flags, see below */ + unsigned long flags; + + /* Primarily protects free_area */ + spinlock_t lock; + + /* Pages to be freed when next trylock succeeds */ + struct llist_head trylock_free_pages; + + /* Write-intensive fields used by compaction and vmstats. */ + CACHELINE_PADDING(_pad2_); + + /* + * 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 compaction migration scanner should start */ + unsigned long compact_cached_migrate_pfn[ASYNC_AND_SYNC]; + unsigned long compact_init_migrate_pfn; + unsigned long compact_init_free_pfn; +#endif + +#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. + * compact_order_failed is the minimum compaction failed order. + */ + unsigned int compact_considered; + unsigned int compact_defer_shift; + int compact_order_failed; +#endif + +#if defined CONFIG_COMPACTION || defined CONFIG_CMA + /* Set to true when the PG_migrate_skip bits should be cleared */ + bool compact_blockskip_flush; +#endif + + bool contiguous; + + CACHELINE_PADDING(_pad3_); + /* Zone statistics */ + atomic_long_t vm_stat[NR_VM_ZONE_STAT_ITEMS]; + atomic_long_t vm_numa_event[NR_VM_NUMA_EVENT_ITEMS]; } ____cacheline_internodealigned_in_smp; -typedef enum { - 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_TAIL_LRU_DIRTY, /* reclaim scanning has recently found - * many dirty file pages at the tail - * of the LRU. - */ - ZONE_WRITEBACK, /* reclaim scanning has recently found +enum pgdat_flags { + PGDAT_WRITEBACK, /* reclaim scanning has recently found * many pages under writeback */ -} zone_flags_t; + PGDAT_RECLAIM_LOCKED, /* prevents concurrent reclaim */ +}; -static inline void zone_set_flag(struct zone *zone, zone_flags_t flag) -{ - set_bit(flag, &zone->flags); -} +enum zone_flags { + ZONE_BOOSTED_WATERMARK, /* zone recently boosted watermarks. + * Cleared when kswapd is woken. + */ + ZONE_RECLAIM_ACTIVE, /* kswapd may be scanning the zone. */ + ZONE_BELOW_HIGH, /* zone is below high watermark. */ +}; -static inline int zone_test_and_set_flag(struct zone *zone, zone_flags_t flag) +static inline unsigned long wmark_pages(const struct zone *z, + enum zone_watermarks w) { - return test_and_set_bit(flag, &zone->flags); + return z->_watermark[w] + z->watermark_boost; } -static inline void zone_clear_flag(struct zone *zone, zone_flags_t flag) +static inline unsigned long min_wmark_pages(const struct zone *z) { - clear_bit(flag, &zone->flags); + return wmark_pages(z, WMARK_MIN); } -static inline int zone_is_reclaim_congested(const struct zone *zone) +static inline unsigned long low_wmark_pages(const struct zone *z) { - return test_bit(ZONE_CONGESTED, &zone->flags); + return wmark_pages(z, WMARK_LOW); } -static inline int zone_is_reclaim_dirty(const struct zone *zone) +static inline unsigned long high_wmark_pages(const struct zone *z) { - return test_bit(ZONE_TAIL_LRU_DIRTY, &zone->flags); + return wmark_pages(z, WMARK_HIGH); } -static inline int zone_is_reclaim_writeback(const struct zone *zone) +static inline unsigned long promo_wmark_pages(const struct zone *z) { - return test_bit(ZONE_WRITEBACK, &zone->flags); + return wmark_pages(z, WMARK_PROMO); } -static inline int zone_is_reclaim_locked(const struct zone *zone) +static inline unsigned long zone_managed_pages(const struct zone *zone) { - return test_bit(ZONE_RECLAIM_LOCKED, &zone->flags); + return (unsigned long)atomic_long_read(&zone->managed_pages); } -static inline int zone_is_oom_locked(const struct zone *zone) +static inline unsigned long zone_cma_pages(struct zone *zone) { - return test_bit(ZONE_OOM_LOCKED, &zone->flags); +#ifdef CONFIG_CMA + return zone->cma_pages; +#else + return 0; +#endif } static inline unsigned long zone_end_pfn(const struct zone *zone) @@ -560,106 +1124,184 @@ static inline bool zone_spans_pfn(const struct zone *zone, unsigned long pfn) return zone->zone_start_pfn <= pfn && pfn < zone_end_pfn(zone); } -static inline bool zone_is_initialized(struct zone *zone) +static inline bool zone_is_initialized(const struct zone *zone) { - return !!zone->wait_table; + return zone->initialized; } -static inline bool zone_is_empty(struct zone *zone) +static inline bool zone_is_empty(const struct zone *zone) { return zone->spanned_pages == 0; } +#ifndef BUILD_VDSO32_64 /* - * 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 - * queues ("queue_length >> 12") during an aging round. + * The zone field is never updated after free_area_init_core() + * sets it, so none of the operations on it need to be atomic. */ -#define DEF_PRIORITY 12 -/* Maximum number of zones on a zonelist */ -#define MAX_ZONES_PER_ZONELIST (MAX_NUMNODES * MAX_NR_ZONES) +/* Page flags: | [SECTION] | [NODE] | ZONE | [LAST_CPUPID] | ... | FLAGS | */ +#define SECTIONS_PGOFF ((sizeof(unsigned long)*8) - SECTIONS_WIDTH) +#define NODES_PGOFF (SECTIONS_PGOFF - NODES_WIDTH) +#define ZONES_PGOFF (NODES_PGOFF - ZONES_WIDTH) +#define LAST_CPUPID_PGOFF (ZONES_PGOFF - LAST_CPUPID_WIDTH) +#define KASAN_TAG_PGOFF (LAST_CPUPID_PGOFF - KASAN_TAG_WIDTH) +#define LRU_GEN_PGOFF (KASAN_TAG_PGOFF - LRU_GEN_WIDTH) +#define LRU_REFS_PGOFF (LRU_GEN_PGOFF - LRU_REFS_WIDTH) -#ifdef CONFIG_NUMA +/* + * Define the bit shifts to access each section. For non-existent + * sections we define the shift as 0; that plus a 0 mask ensures + * the compiler will optimise away reference to them. + */ +#define SECTIONS_PGSHIFT (SECTIONS_PGOFF * (SECTIONS_WIDTH != 0)) +#define NODES_PGSHIFT (NODES_PGOFF * (NODES_WIDTH != 0)) +#define ZONES_PGSHIFT (ZONES_PGOFF * (ZONES_WIDTH != 0)) +#define LAST_CPUPID_PGSHIFT (LAST_CPUPID_PGOFF * (LAST_CPUPID_WIDTH != 0)) +#define KASAN_TAG_PGSHIFT (KASAN_TAG_PGOFF * (KASAN_TAG_WIDTH != 0)) + +/* NODE:ZONE or SECTION:ZONE is used to ID a zone for the buddy allocator */ +#ifdef NODE_NOT_IN_PAGE_FLAGS +#define ZONEID_SHIFT (SECTIONS_SHIFT + ZONES_SHIFT) +#define ZONEID_PGOFF ((SECTIONS_PGOFF < ZONES_PGOFF) ? \ + SECTIONS_PGOFF : ZONES_PGOFF) +#else +#define ZONEID_SHIFT (NODES_SHIFT + ZONES_SHIFT) +#define ZONEID_PGOFF ((NODES_PGOFF < ZONES_PGOFF) ? \ + NODES_PGOFF : ZONES_PGOFF) +#endif + +#define ZONEID_PGSHIFT (ZONEID_PGOFF * (ZONEID_SHIFT != 0)) + +#define ZONES_MASK ((1UL << ZONES_WIDTH) - 1) +#define NODES_MASK ((1UL << NODES_WIDTH) - 1) +#define SECTIONS_MASK ((1UL << SECTIONS_WIDTH) - 1) +#define LAST_CPUPID_MASK ((1UL << LAST_CPUPID_SHIFT) - 1) +#define KASAN_TAG_MASK ((1UL << KASAN_TAG_WIDTH) - 1) +#define ZONEID_MASK ((1UL << ZONEID_SHIFT) - 1) + +static inline enum zone_type memdesc_zonenum(memdesc_flags_t flags) +{ + ASSERT_EXCLUSIVE_BITS(flags.f, ZONES_MASK << ZONES_PGSHIFT); + return (flags.f >> ZONES_PGSHIFT) & ZONES_MASK; +} + +static inline enum zone_type page_zonenum(const struct page *page) +{ + return memdesc_zonenum(page->flags); +} + +static inline enum zone_type folio_zonenum(const struct folio *folio) +{ + return memdesc_zonenum(folio->flags); +} + +#ifdef CONFIG_ZONE_DEVICE +static inline bool memdesc_is_zone_device(memdesc_flags_t mdf) +{ + return memdesc_zonenum(mdf) == ZONE_DEVICE; +} + +static inline struct dev_pagemap *page_pgmap(const struct page *page) +{ + VM_WARN_ON_ONCE_PAGE(!memdesc_is_zone_device(page->flags), page); + return page_folio(page)->pgmap; +} /* - * The NUMA zonelists are doubled because we need zonelists that restrict the - * allocations to a single node for GFP_THISNODE. - * - * [0] : Zonelist with fallback - * [1] : No fallback (GFP_THISNODE) + * 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. */ -#define MAX_ZONELISTS 2 +static inline bool zone_device_pages_have_same_pgmap(const struct page *a, + const struct page *b) +{ + if (memdesc_is_zone_device(a->flags) != memdesc_is_zone_device(b->flags)) + return false; + if (!memdesc_is_zone_device(a->flags)) + return true; + return page_pgmap(a) == page_pgmap(b); +} + +extern void memmap_init_zone_device(struct zone *, unsigned long, + unsigned long, struct dev_pagemap *); +#else +static inline bool memdesc_is_zone_device(memdesc_flags_t mdf) +{ + return false; +} +static inline bool zone_device_pages_have_same_pgmap(const struct page *a, + const struct page *b) +{ + return true; +} +static inline struct dev_pagemap *page_pgmap(const struct page *page) +{ + return NULL; +} +#endif + +static inline bool is_zone_device_page(const struct page *page) +{ + return memdesc_is_zone_device(page->flags); +} + +static inline bool folio_is_zone_device(const struct folio *folio) +{ + return memdesc_is_zone_device(folio->flags); +} +static inline bool is_zone_movable_page(const struct page *page) +{ + return page_zonenum(page) == ZONE_MOVABLE; +} + +static inline bool folio_is_zone_movable(const struct folio *folio) +{ + return folio_zonenum(folio) == ZONE_MOVABLE; +} +#endif /* - * 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. + * Return true if [start_pfn, start_pfn + nr_pages) range has a non-empty + * intersection with the given zone */ +static inline bool zone_intersects(const struct zone *zone, + unsigned long start_pfn, unsigned long nr_pages) +{ + if (zone_is_empty(zone)) + return false; + if (start_pfn >= zone_end_pfn(zone) || + start_pfn + nr_pages <= zone->zone_start_pfn) + return false; + return true; +} -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 -#define MAX_ZONELISTS 1 -struct zonelist_cache; +/* + * 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 + * queues ("queue_length >> 12") during an aging round. + */ +#define DEF_PRIORITY 12 + +/* Maximum number of zones on a zonelist */ +#define MAX_ZONES_PER_ZONELIST (MAX_NUMNODES * MAX_NR_ZONES) + +enum { + ZONELIST_FALLBACK, /* zonelist with fallback */ +#ifdef CONFIG_NUMA + /* + * The NUMA zonelists are doubled because we need zonelists that + * restrict the allocations to a single node for __GFP_THISNODE. + */ + ZONELIST_NOFALLBACK, /* zonelist without fallback (__GFP_THISNODE) */ #endif + MAX_ZONELISTS +}; /* * This struct contains information about a zone in a zonelist. It is stored @@ -676,9 +1318,6 @@ struct zoneref { * allocation, the other zones are fallback zones, in decreasing * priority. * - * 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. - * * * To speed the reading of the zonelist, the zonerefs contain the zone index * of the entry being read. Helper functions to access information given * a struct zoneref are @@ -688,59 +1327,89 @@ struct zoneref { * zonelist_node_idx() - Return the index of the node for an entry */ struct zonelist { - struct zonelist_cache *zlcache_ptr; // NULL or &zlcache struct zoneref _zonerefs[MAX_ZONES_PER_ZONELIST + 1]; -#ifdef CONFIG_NUMA - struct zonelist_cache zlcache; // optional ... -#endif }; -#ifdef CONFIG_HAVE_MEMBLOCK_NODE_MAP -struct node_active_region { - unsigned long start_pfn; - unsigned long end_pfn; - int nid; +/* + * The array of struct pages for flatmem. + * It must be declared for SPARSEMEM as well because there are configurations + * that rely on that. + */ +extern struct page *mem_map; + +#ifdef CONFIG_TRANSPARENT_HUGEPAGE +struct deferred_split { + spinlock_t split_queue_lock; + struct list_head split_queue; + unsigned long split_queue_len; }; -#endif /* CONFIG_HAVE_MEMBLOCK_NODE_MAP */ +#endif -#ifndef CONFIG_DISCONTIGMEM -/* The array of struct pages - for discontigmem use pgdat->lmem_map */ -extern struct page *mem_map; +#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 /* - * The pg_data_t structure is used in machines with CONFIG_DISCONTIGMEM - * (mostly NUMA machines?) to denote a higher-level memory zone than the - * zone denotes. - * * On NUMA machines, each NUMA node would have a pg_data_t to describe - * it's memory layout. + * it's memory layout. On UMA machines there is a single pglist_data which + * describes the whole memory. * * Memory statistics and page replacement data structures are maintained on a * per-zone basis. */ -struct bootmem_data; typedef struct pglist_data { + /* + * node_zones contains just the zones for THIS node. Not all of the + * zones may be populated, but it is the full list. It is referenced by + * this node's node_zonelists as well as other node's node_zonelists. + */ struct zone node_zones[MAX_NR_ZONES]; + + /* + * node_zonelists contains references to all zones in all nodes. + * Generally the first zones will be references to this node's + * node_zones. + */ struct zonelist node_zonelists[MAX_ZONELISTS]; - int nr_zones; -#ifdef CONFIG_FLAT_NODE_MEM_MAP /* means !SPARSEMEM */ + + int nr_zones; /* number of populated zones in this node */ +#ifdef CONFIG_FLATMEM /* means !SPARSEMEM */ struct page *node_mem_map; -#ifdef CONFIG_MEMCG - struct page_cgroup *node_page_cgroup; -#endif +#ifdef CONFIG_PAGE_EXTENSION + struct page_ext *node_page_ext; #endif -#ifndef CONFIG_NO_BOOTMEM - struct bootmem_data *bdata; #endif -#ifdef CONFIG_MEMORY_HOTPLUG +#if defined(CONFIG_MEMORY_HOTPLUG) || defined(CONFIG_DEFERRED_STRUCT_PAGE_INIT) /* - * 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. + * Must be held any time you expect node_start_pfn, + * node_present_pages, node_spanned_pages or nr_zones to stay constant. + * Also synchronizes pgdat->first_deferred_pfn during deferred page + * init. * * pgdat_resize_lock() and pgdat_resize_unlock() are provided to - * manipulate node_size_lock without checking for CONFIG_MEMORY_HOTPLUG. + * manipulate node_size_lock without checking for CONFIG_MEMORY_HOTPLUG + * or CONFIG_DEFERRED_STRUCT_PAGE_INIT. * * Nests above zone->lock and zone->span_seqlock */ @@ -751,35 +1420,108 @@ typedef struct pglist_data { unsigned long node_spanned_pages; /* total size of physical page range, including holes */ int node_id; - nodemask_t reclaim_nodes; /* Nodes allowed to reclaim from */ wait_queue_head_t kswapd_wait; wait_queue_head_t pfmemalloc_wait; - struct task_struct *kswapd; /* Protected by lock_memory_hotplug() */ - int kswapd_max_order; - enum zone_type classzone_idx; + + /* workqueues for throttling reclaim for different reasons. */ + wait_queue_head_t reclaim_wait[NR_VMSCAN_THROTTLE]; + + atomic_t nr_writeback_throttled;/* nr of writeback-throttled tasks */ + unsigned long nr_reclaim_start; /* nr pages written while throttled + * when throttling started. */ +#ifdef CONFIG_MEMORY_HOTPLUG + struct mutex kswapd_lock; +#endif + struct task_struct *kswapd; /* Protected by kswapd_lock */ + int kswapd_order; + enum zone_type kswapd_highest_zoneidx; + + atomic_t kswapd_failures; /* Number of 'reclaimed == 0' runs */ + +#ifdef CONFIG_COMPACTION + int kcompactd_max_order; + enum zone_type kcompactd_highest_zoneidx; + wait_queue_head_t kcompactd_wait; + struct task_struct *kcompactd; + bool proactive_compact_trigger; +#endif + /* + * This is a per-node reserve of pages that are not available + * to userspace allocations. + */ + unsigned long totalreserve_pages; + +#ifdef CONFIG_NUMA + /* + * node reclaim becomes active if more unmapped pages exist. + */ + unsigned long min_unmapped_pages; + unsigned long min_slab_pages; +#endif /* CONFIG_NUMA */ + + /* Write-intensive fields used by page reclaim */ + CACHELINE_PADDING(_pad1_); + +#ifdef CONFIG_DEFERRED_STRUCT_PAGE_INIT + /* + * If memory initialisation on large machines is deferred then this + * is the first PFN that needs to be initialised. + */ + unsigned long first_deferred_pfn; +#endif /* CONFIG_DEFERRED_STRUCT_PAGE_INIT */ + +#ifdef CONFIG_TRANSPARENT_HUGEPAGE + struct deferred_split deferred_split_queue; +#endif + #ifdef CONFIG_NUMA_BALANCING + /* start time in ms of current promote rate limit period */ + unsigned int nbp_rl_start; + /* number of promote candidate pages at start time of current rate limit period */ + unsigned long nbp_rl_nr_cand; + /* promote threshold in ms */ + unsigned int nbp_threshold; + /* start time in ms of current promote threshold adjustment period */ + unsigned int nbp_th_start; + /* + * number of promote candidate pages at start time of current promote + * threshold adjustment period + */ + unsigned long nbp_th_nr_cand; +#endif + /* Fields commonly accessed by the page reclaim scanner */ + /* - * Lock serializing the per destination node AutoNUMA memory - * migration rate limiting data. + * NOTE: THIS IS UNUSED IF MEMCG IS ENABLED. + * + * Use mem_cgroup_lruvec() to look up lruvecs. */ - spinlock_t numabalancing_migrate_lock; + struct lruvec __lruvec; - /* Rate limiting time interval */ - unsigned long numabalancing_migrate_next_window; + unsigned long flags; - /* Number of pages migrated during the rate limiting time interval */ - unsigned long numabalancing_migrate_nr_pages; +#ifdef CONFIG_LRU_GEN + /* kswap mm walk data */ + struct lru_gen_mm_walk mm_walk; + /* lru_gen_folio list */ + struct lru_gen_memcg memcg_lru; +#endif + + CACHELINE_PADDING(_pad2_); + + /* Per-node vmstats */ + struct per_cpu_nodestat __percpu *per_cpu_nodestats; + atomic_long_t vm_stat[NR_VM_NODE_STAT_ITEMS]; +#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) #define node_spanned_pages(nid) (NODE_DATA(nid)->node_spanned_pages) -#ifdef CONFIG_FLAT_NODE_MEM_MAP -#define pgdat_page_nr(pgdat, pagenr) ((pgdat)->node_mem_map + (pagenr)) -#else -#define pgdat_page_nr(pgdat, pagenr) pfn_to_page((pgdat)->node_start_pfn + (pagenr)) -#endif -#define nid_page_nr(nid, pagenr) pgdat_page_nr(NODE_DATA(nid),(pagenr)) #define node_start_pfn(nid) (NODE_DATA(nid)->node_start_pfn) #define node_end_pfn(nid) pgdat_end_pfn(NODE_DATA(nid)) @@ -789,134 +1531,146 @@ static inline unsigned long pgdat_end_pfn(pg_data_t *pgdat) return pgdat->node_start_pfn + pgdat->node_spanned_pages; } -static inline bool pgdat_is_empty(pg_data_t *pgdat) -{ - return !pgdat->node_start_pfn && !pgdat->node_spanned_pages; -} - #include <linux/memory_hotplug.h> -extern struct mutex zonelists_mutex; -void build_all_zonelists(pg_data_t *pgdat, struct zone *zone); -void wakeup_kswapd(struct zone *zone, int order, enum zone_type classzone_idx); -bool zone_watermark_ok(struct zone *z, int order, unsigned long mark, - int classzone_idx, int alloc_flags); -bool zone_watermark_ok_safe(struct zone *z, int order, unsigned long mark, - int classzone_idx, int alloc_flags); -enum memmap_context { - MEMMAP_EARLY, - MEMMAP_HOTPLUG, +void build_all_zonelists(pg_data_t *pgdat); +void wakeup_kswapd(struct zone *zone, gfp_t gfp_mask, int order, + enum zone_type highest_zoneidx); +bool __zone_watermark_ok(struct zone *z, unsigned int order, unsigned long mark, + int highest_zoneidx, unsigned int alloc_flags, + long free_pages); +bool zone_watermark_ok(struct zone *z, unsigned int order, + unsigned long mark, int highest_zoneidx, + unsigned int alloc_flags); +/* + * Memory initialization context, use to differentiate memory added by + * the platform statically or via memory hotplug interface. + */ +enum meminit_context { + MEMINIT_EARLY, + MEMINIT_HOTPLUG, }; -extern int init_currently_empty_zone(struct zone *zone, unsigned long start_pfn, - unsigned long size, - enum memmap_context context); + +extern void init_currently_empty_zone(struct zone *zone, unsigned long start_pfn, + unsigned long size); extern void lruvec_init(struct lruvec *lruvec); -static inline struct zone *lruvec_zone(struct lruvec *lruvec) +static inline struct pglist_data *lruvec_pgdat(struct lruvec *lruvec) { #ifdef CONFIG_MEMCG - return lruvec->zone; + return lruvec->pgdat; #else - return container_of(lruvec, struct zone, lruvec); + return container_of(lruvec, struct pglist_data, __lruvec); #endif } -#ifdef CONFIG_HAVE_MEMORY_PRESENT -void memory_present(int nid, unsigned long start, unsigned long end); -#else -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 - /* * zone_idx() returns 0 for the ZONE_DMA zone, 1 for the ZONE_NORMAL zone, etc. */ #define zone_idx(zone) ((zone) - (zone)->zone_pgdat->node_zones) -static inline int populated_zone(struct zone *zone) +#ifdef CONFIG_ZONE_DEVICE +static inline bool zone_is_zone_device(const struct zone *zone) { - return (!!zone->present_pages); + return zone_idx(zone) == ZONE_DEVICE; } +#else +static inline bool zone_is_zone_device(const struct zone *zone) +{ + return false; +} +#endif -extern int movable_zone; +/* + * Returns true if a zone has pages managed by the buddy allocator. + * All the reclaim decisions have to use this function rather than + * populated_zone(). If the whole zone is reserved then we can easily + * end up with populated_zone() && !managed_zone(). + */ +static inline bool managed_zone(const struct zone *zone) +{ + return zone_managed_pages(zone); +} -static inline int zone_movable_is_highmem(void) +/* Returns true if a zone has memory */ +static inline bool populated_zone(const struct zone *zone) { -#if defined(CONFIG_HIGHMEM) && defined(CONFIG_HAVE_MEMBLOCK_NODE_MAP) - return movable_zone == ZONE_HIGHMEM; + return zone->present_pages; +} + +#ifdef CONFIG_NUMA +static inline int zone_to_nid(const struct zone *zone) +{ + return zone->node; +} + +static inline void zone_set_nid(struct zone *zone, int nid) +{ + zone->node = nid; +} #else +static inline int zone_to_nid(const struct zone *zone) +{ return 0; -#endif } +static inline void zone_set_nid(struct zone *zone, int nid) {} +#endif + +extern int movable_zone; + static inline int is_highmem_idx(enum zone_type idx) { #ifdef CONFIG_HIGHMEM return (idx == ZONE_HIGHMEM || - (idx == ZONE_MOVABLE && zone_movable_is_highmem())); + (idx == ZONE_MOVABLE && movable_zone == ZONE_HIGHMEM)); #else return 0; #endif } /** - * is_highmem - helper function to quickly check if a struct zone is a + * is_highmem - helper function to quickly check if a struct zone is a * highmem zone or not. This is an attempt to keep references * to ZONE_{DMA/NORMAL/HIGHMEM/etc} in general code to a minimum. - * @zone - pointer to struct zone variable + * @zone: pointer to struct zone variable + * Return: 1 for a highmem zone, 0 otherwise */ -static inline int is_highmem(struct zone *zone) +static inline int is_highmem(const struct zone *zone) { -#ifdef CONFIG_HIGHMEM - int zone_off = (char *)zone - (char *)zone->zone_pgdat->node_zones; - return zone_off == ZONE_HIGHMEM * sizeof(*zone) || - (zone_off == ZONE_MOVABLE * sizeof(*zone) && - zone_movable_is_highmem()); -#else - return 0; -#endif + return is_highmem_idx(zone_idx(zone)); } -/* These two functions are used to setup the per zone pages min values */ -struct ctl_table; -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, - void __user *, size_t *, loff_t *); -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, - void __user *, size_t *, loff_t *); -int sysctl_min_slab_ratio_sysctl_handler(struct ctl_table *, int, - void __user *, size_t *, loff_t *); +#ifdef CONFIG_ZONE_DMA +bool has_managed_dma(void); +#else +static inline bool has_managed_dma(void) +{ + return false; +} +#endif -extern int numa_zonelist_order_handler(struct ctl_table *, int, - void __user *, size_t *, loff_t *); -extern char numa_zonelist_order[]; -#define NUMA_ZONELIST_ORDER_LEN 16 /* string buffer size */ -#ifndef CONFIG_NEED_MULTIPLE_NODES +#ifndef CONFIG_NUMA extern struct pglist_data contig_page_data; -#define NODE_DATA(nid) (&contig_page_data) -#define NODE_MEM_MAP(nid) mem_map +static inline struct pglist_data *NODE_DATA(int nid) +{ + return &contig_page_data; +} -#else /* CONFIG_NEED_MULTIPLE_NODES */ +#else /* CONFIG_NUMA */ #include <asm/mmzone.h> -#endif /* !CONFIG_NEED_MULTIPLE_NODES */ +#endif /* !CONFIG_NUMA */ extern struct pglist_data *first_online_pgdat(void); extern struct pglist_data *next_online_pgdat(struct pglist_data *pgdat); @@ -924,7 +1678,7 @@ extern struct zone *next_zone(struct zone *zone); /** * for_each_online_pgdat - helper macro to iterate over all online nodes - * @pgdat - pointer to a pg_data_t variable + * @pgdat: pointer to a pg_data_t variable */ #define for_each_online_pgdat(pgdat) \ for (pgdat = first_online_pgdat(); \ @@ -932,7 +1686,7 @@ extern struct zone *next_zone(struct zone *zone); pgdat = next_online_pgdat(pgdat)) /** * for_each_zone - helper macro to iterate over all memory zones - * @zone - pointer to struct zone variable + * @zone: pointer to struct zone variable * * The user only needs to declare the zone variable, for_each_zone * fills it in. @@ -955,98 +1709,129 @@ static inline struct zone *zonelist_zone(struct zoneref *zoneref) return zoneref->zone; } -static inline int zonelist_zone_idx(struct zoneref *zoneref) +static inline int zonelist_zone_idx(const struct zoneref *zoneref) { return zoneref->zone_idx; } -static inline int zonelist_node_idx(struct zoneref *zoneref) +static inline int zonelist_node_idx(const struct zoneref *zoneref) { -#ifdef CONFIG_NUMA - /* zone_to_nid not available in this context */ - return zoneref->zone->node; -#else - return 0; -#endif /* CONFIG_NUMA */ + return zone_to_nid(zoneref->zone); } +struct zoneref *__next_zones_zonelist(struct zoneref *z, + enum zone_type highest_zoneidx, + nodemask_t *nodes); + /** * next_zones_zonelist - Returns the next zone at or below highest_zoneidx within the allowed nodemask using a cursor within a zonelist as a starting point - * @z - The cursor used as a starting point for the search - * @highest_zoneidx - The zone index of the highest zone to return - * @nodes - An optional nodemask to filter the zonelist with - * @zone - The first suitable zone found is returned via this parameter + * @z: The cursor used as a starting point for the search + * @highest_zoneidx: The zone index of the highest zone to return + * @nodes: An optional nodemask to filter the zonelist with * * This function returns the next zone at or below a given zone index that is * within the allowed nodemask using a cursor as the starting point for the * search. The zoneref returned is a cursor that represents the current zone * being examined. It should be advanced by one before calling * next_zones_zonelist again. + * + * Return: the next zone at or below highest_zoneidx within the allowed + * nodemask using a cursor within a zonelist as a starting point */ -struct zoneref *next_zones_zonelist(struct zoneref *z, +static __always_inline struct zoneref *next_zones_zonelist(struct zoneref *z, enum zone_type highest_zoneidx, - nodemask_t *nodes, - struct zone **zone); + nodemask_t *nodes) +{ + if (likely(!nodes && zonelist_zone_idx(z) <= highest_zoneidx)) + return z; + return __next_zones_zonelist(z, highest_zoneidx, nodes); +} /** * first_zones_zonelist - Returns the first zone at or below highest_zoneidx within the allowed nodemask in a zonelist - * @zonelist - The zonelist to search for a suitable zone - * @highest_zoneidx - The zone index of the highest zone to return - * @nodes - An optional nodemask to filter the zonelist with - * @zone - The first suitable zone found is returned via this parameter + * @zonelist: The zonelist to search for a suitable zone + * @highest_zoneidx: The zone index of the highest zone to return + * @nodes: An optional nodemask to filter the zonelist with * * This function returns the first zone at or below a given zone index that is * within the allowed nodemask. The zoneref returned is a cursor that can be * used to iterate the zonelist with next_zones_zonelist by advancing it by * one before calling. + * + * When no eligible zone is found, zoneref->zone is NULL (zoneref itself is + * never NULL). This may happen either genuinely, or due to concurrent nodemask + * update due to cpuset modification. + * + * Return: Zoneref pointer for the first suitable zone found */ static inline struct zoneref *first_zones_zonelist(struct zonelist *zonelist, enum zone_type highest_zoneidx, - nodemask_t *nodes, - struct zone **zone) + nodemask_t *nodes) { - return next_zones_zonelist(zonelist->_zonerefs, highest_zoneidx, nodes, - zone); + return next_zones_zonelist(zonelist->_zonerefs, + highest_zoneidx, nodes); } /** * for_each_zone_zonelist_nodemask - helper macro to iterate over valid zones in a zonelist at or below a given zone index and within a nodemask - * @zone - The current zone in the iterator - * @z - The current pointer within zonelist->zones being iterated - * @zlist - The zonelist being iterated - * @highidx - The zone index of the highest zone to return - * @nodemask - Nodemask allowed by the allocator + * @zone: The current zone in the iterator + * @z: The current pointer within zonelist->_zonerefs being iterated + * @zlist: The zonelist being iterated + * @highidx: The zone index of the highest zone to return + * @nodemask: Nodemask allowed by the allocator * * This iterator iterates though all zones at or below a given zone index and * within a given nodemask */ #define for_each_zone_zonelist_nodemask(zone, z, zlist, highidx, nodemask) \ - for (z = first_zones_zonelist(zlist, highidx, nodemask, &zone); \ + for (z = first_zones_zonelist(zlist, highidx, nodemask), zone = zonelist_zone(z); \ + zone; \ + z = next_zones_zonelist(++z, highidx, nodemask), \ + zone = zonelist_zone(z)) + +#define for_next_zone_zonelist_nodemask(zone, z, highidx, nodemask) \ + for (zone = zonelist_zone(z); \ zone; \ - z = next_zones_zonelist(++z, highidx, nodemask, &zone)) \ + z = next_zones_zonelist(++z, highidx, nodemask), \ + zone = zonelist_zone(z)) + /** * for_each_zone_zonelist - helper macro to iterate over valid zones in a zonelist at or below a given zone index - * @zone - The current zone in the iterator - * @z - The current pointer within zonelist->zones being iterated - * @zlist - The zonelist being iterated - * @highidx - The zone index of the highest zone to return + * @zone: The current zone in the iterator + * @z: The current pointer within zonelist->zones being iterated + * @zlist: The zonelist being iterated + * @highidx: The zone index of the highest zone to return * * This iterator iterates though all zones at or below a given zone index. */ #define for_each_zone_zonelist(zone, z, zlist, highidx) \ for_each_zone_zonelist_nodemask(zone, z, zlist, highidx, NULL) -#ifdef CONFIG_SPARSEMEM -#include <asm/sparsemem.h> -#endif - -#if !defined(CONFIG_HAVE_ARCH_EARLY_PFN_TO_NID) && \ - !defined(CONFIG_HAVE_MEMBLOCK_NODE_MAP) -static inline unsigned long early_pfn_to_nid(unsigned long pfn) +/* Whether the 'nodes' are all movable nodes */ +static inline bool movable_only_nodes(nodemask_t *nodes) { - return 0; + struct zonelist *zonelist; + struct zoneref *z; + int nid; + + if (nodes_empty(*nodes)) + return false; + + /* + * We can chose arbitrary node from the nodemask to get a + * zonelist as they are interlinked. We just need to find + * at least one zone that can satisfy kernel allocations. + */ + nid = first_node(*nodes); + zonelist = &NODE_DATA(nid)->node_zonelists[ZONELIST_FALLBACK]; + z = first_zones_zonelist(zonelist, ZONE_NORMAL, nodes); + return (!zonelist_zone(z)) ? true : false; } + + +#ifdef CONFIG_SPARSEMEM +#include <asm/sparsemem.h> #endif #ifdef CONFIG_FLATMEM @@ -1056,8 +1841,6 @@ static inline unsigned long early_pfn_to_nid(unsigned long pfn) #ifdef CONFIG_SPARSEMEM /* - * SECTION_SHIFT #bits space required to store a section # - * * PA_SECTION_SHIFT physical address to/from section number * PFN_SECTION_SHIFT pfn to/from section number */ @@ -1072,18 +1855,51 @@ static inline unsigned long early_pfn_to_nid(unsigned long pfn) #define SECTION_BLOCKFLAGS_BITS \ ((1UL << (PFN_SECTION_SHIFT - pageblock_order)) * NR_PAGEBLOCK_BITS) -#if (MAX_ORDER - 1 + PAGE_SHIFT) > SECTION_SIZE_BITS -#error Allocator MAX_ORDER exceeds SECTION_SIZE +#if (MAX_PAGE_ORDER + PAGE_SHIFT) > SECTION_SIZE_BITS +#error Allocator MAX_PAGE_ORDER exceeds SECTION_SIZE #endif -#define pfn_to_section_nr(pfn) ((pfn) >> PFN_SECTION_SHIFT) -#define section_nr_to_pfn(sec) ((sec) << PFN_SECTION_SHIFT) +static inline unsigned long pfn_to_section_nr(unsigned long pfn) +{ + return pfn >> PFN_SECTION_SHIFT; +} +static inline unsigned long section_nr_to_pfn(unsigned long sec) +{ + return sec << PFN_SECTION_SHIFT; +} #define SECTION_ALIGN_UP(pfn) (((pfn) + PAGES_PER_SECTION - 1) & PAGE_SECTION_MASK) #define SECTION_ALIGN_DOWN(pfn) ((pfn) & PAGE_SECTION_MASK) +#define SUBSECTION_SHIFT 21 +#define SUBSECTION_SIZE (1UL << SUBSECTION_SHIFT) + +#define PFN_SUBSECTION_SHIFT (SUBSECTION_SHIFT - PAGE_SHIFT) +#define PAGES_PER_SUBSECTION (1UL << PFN_SUBSECTION_SHIFT) +#define PAGE_SUBSECTION_MASK (~(PAGES_PER_SUBSECTION-1)) + +#if SUBSECTION_SHIFT > SECTION_SIZE_BITS +#error Subsection size exceeds section size +#else +#define SUBSECTIONS_PER_SECTION (1UL << (SECTION_SIZE_BITS - SUBSECTION_SHIFT)) +#endif + +#define SUBSECTION_ALIGN_UP(pfn) ALIGN((pfn), PAGES_PER_SUBSECTION) +#define SUBSECTION_ALIGN_DOWN(pfn) ((pfn) & PAGE_SUBSECTION_MASK) + +struct mem_section_usage { + struct rcu_head rcu; +#ifdef CONFIG_SPARSEMEM_VMEMMAP + DECLARE_BITMAP(subsection_map, SUBSECTIONS_PER_SECTION); +#endif + /* See declaration of similar field in struct zone */ + unsigned long pageblock_flags[0]; +}; + +void subsection_map_init(unsigned long pfn, unsigned long nr_pages); + struct page; -struct page_cgroup; +struct page_ext; struct mem_section { /* * This is, logically, a pointer to an array of struct @@ -1099,14 +1915,13 @@ struct mem_section { */ unsigned long section_mem_map; - /* See declaration of similar field in struct zone */ - unsigned long *pageblock_flags; -#ifdef CONFIG_MEMCG + struct mem_section_usage *usage; +#ifdef CONFIG_PAGE_EXTENSION /* - * If !SPARSEMEM, pgdat doesn't have page_cgroup pointer. We use - * section. (see memcontrol.h/page_cgroup.h about this.) + * If SPARSEMEM, pgdat doesn't have page_ext pointer. We use + * section. (see page_ext.h about this.) */ - struct page_cgroup *page_cgroup; + struct page_ext *page_ext; unsigned long pad; #endif /* @@ -1126,30 +1941,74 @@ struct mem_section { #define SECTION_ROOT_MASK (SECTIONS_PER_ROOT - 1) #ifdef CONFIG_SPARSEMEM_EXTREME -extern struct mem_section *mem_section[NR_SECTION_ROOTS]; +extern struct mem_section **mem_section; #else extern struct mem_section mem_section[NR_SECTION_ROOTS][SECTIONS_PER_ROOT]; #endif +static inline unsigned long *section_to_usemap(struct mem_section *ms) +{ + return ms->usage->pageblock_flags; +} + static inline struct mem_section *__nr_to_section(unsigned long nr) { - if (!mem_section[SECTION_NR_TO_ROOT(nr)]) + unsigned long root = SECTION_NR_TO_ROOT(nr); + + if (unlikely(root >= NR_SECTION_ROOTS)) + return NULL; + +#ifdef CONFIG_SPARSEMEM_EXTREME + if (!mem_section || !mem_section[root]) return NULL; - return &mem_section[SECTION_NR_TO_ROOT(nr)][nr & SECTION_ROOT_MASK]; +#endif + return &mem_section[root][nr & SECTION_ROOT_MASK]; } -extern int __section_nr(struct mem_section* ms); -extern unsigned long usemap_size(void); +extern size_t mem_section_usage_size(void); /* * We use the lower bits of the mem_map pointer to store - * a little bit of information. There should be at least - * 3 bits here due to 32-bit alignment. + * a little bit of information. The pointer is calculated + * as mem_map - section_nr_to_pfn(pnum). The result is + * aligned to the minimum alignment of the two values: + * 1. All mem_map arrays are page-aligned. + * 2. section_nr_to_pfn() always clears PFN_SECTION_SHIFT + * lowest bits. PFN_SECTION_SHIFT is arch-specific + * (equal SECTION_SIZE_BITS - PAGE_SHIFT), and the + * worst combination is powerpc with 256k pages, + * which results in PFN_SECTION_SHIFT equal 6. + * To sum it up, at least 6 bits are available on all architectures. + * However, we can exceed 6 bits on some other architectures except + * powerpc (e.g. 15 bits are available on x86_64, 13 bits are available + * with the worst case of 64K pages on arm64) if we make sure the + * exceeded bit is not applicable to powerpc. */ -#define SECTION_MARKED_PRESENT (1UL<<0) -#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 +enum { + SECTION_MARKED_PRESENT_BIT, + SECTION_HAS_MEM_MAP_BIT, + SECTION_IS_ONLINE_BIT, + SECTION_IS_EARLY_BIT, +#ifdef CONFIG_ZONE_DEVICE + SECTION_TAINT_ZONE_DEVICE_BIT, +#endif +#ifdef CONFIG_SPARSEMEM_VMEMMAP_PREINIT + SECTION_IS_VMEMMAP_PREINIT_BIT, +#endif + SECTION_MAP_LAST_BIT, +}; + +#define SECTION_MARKED_PRESENT BIT(SECTION_MARKED_PRESENT_BIT) +#define SECTION_HAS_MEM_MAP BIT(SECTION_HAS_MEM_MAP_BIT) +#define SECTION_IS_ONLINE BIT(SECTION_IS_ONLINE_BIT) +#define SECTION_IS_EARLY BIT(SECTION_IS_EARLY_BIT) +#ifdef CONFIG_ZONE_DEVICE +#define SECTION_TAINT_ZONE_DEVICE BIT(SECTION_TAINT_ZONE_DEVICE_BIT) +#endif +#ifdef CONFIG_SPARSEMEM_VMEMMAP_PREINIT +#define SECTION_IS_VMEMMAP_PREINIT BIT(SECTION_IS_VMEMMAP_PREINIT_BIT) +#endif +#define SECTION_MAP_MASK (~(BIT(SECTION_MAP_LAST_BIT) - 1)) +#define SECTION_NID_SHIFT SECTION_MAP_LAST_BIT static inline struct page *__section_mem_map_addr(struct mem_section *section) { @@ -1158,7 +2017,7 @@ static inline struct page *__section_mem_map_addr(struct mem_section *section) return (struct page *)map; } -static inline int present_section(struct mem_section *section) +static inline int present_section(const struct mem_section *section) { return (section && (section->section_mem_map & SECTION_MARKED_PRESENT)); } @@ -1168,37 +2027,249 @@ static inline int present_section_nr(unsigned long nr) return present_section(__nr_to_section(nr)); } -static inline int valid_section(struct mem_section *section) +static inline int valid_section(const struct mem_section *section) { return (section && (section->section_mem_map & SECTION_HAS_MEM_MAP)); } +static inline int early_section(const struct mem_section *section) +{ + return (section && (section->section_mem_map & SECTION_IS_EARLY)); +} + static inline int valid_section_nr(unsigned long nr) { return valid_section(__nr_to_section(nr)); } +static inline int online_section(const struct mem_section *section) +{ + return (section && (section->section_mem_map & SECTION_IS_ONLINE)); +} + +#ifdef CONFIG_ZONE_DEVICE +static inline int online_device_section(const struct mem_section *section) +{ + unsigned long flags = SECTION_IS_ONLINE | SECTION_TAINT_ZONE_DEVICE; + + return section && ((section->section_mem_map & flags) == flags); +} +#else +static inline int online_device_section(const struct mem_section *section) +{ + return 0; +} +#endif + +#ifdef CONFIG_SPARSEMEM_VMEMMAP_PREINIT +static inline int preinited_vmemmap_section(const struct mem_section *section) +{ + return (section && + (section->section_mem_map & SECTION_IS_VMEMMAP_PREINIT)); +} + +void sparse_vmemmap_init_nid_early(int nid); +void sparse_vmemmap_init_nid_late(int nid); + +#else +static inline int preinited_vmemmap_section(const struct mem_section *section) +{ + return 0; +} +static inline void sparse_vmemmap_init_nid_early(int nid) +{ +} + +static inline void sparse_vmemmap_init_nid_late(int nid) +{ +} +#endif + +static inline int online_section_nr(unsigned long nr) +{ + return online_section(__nr_to_section(nr)); +} + +#ifdef CONFIG_MEMORY_HOTPLUG +void online_mem_sections(unsigned long start_pfn, unsigned long end_pfn); +void offline_mem_sections(unsigned long start_pfn, unsigned long end_pfn); +#endif + static inline struct mem_section *__pfn_to_section(unsigned long pfn) { return __nr_to_section(pfn_to_section_nr(pfn)); } +extern unsigned long __highest_present_section_nr; + +static inline int subsection_map_index(unsigned long pfn) +{ + return (pfn & ~(PAGE_SECTION_MASK)) / PAGES_PER_SUBSECTION; +} + +#ifdef CONFIG_SPARSEMEM_VMEMMAP +static inline int pfn_section_valid(struct mem_section *ms, unsigned long pfn) +{ + int idx = subsection_map_index(pfn); + struct mem_section_usage *usage = READ_ONCE(ms->usage); + + return usage ? test_bit(idx, usage->subsection_map) : 0; +} + +static inline bool pfn_section_first_valid(struct mem_section *ms, unsigned long *pfn) +{ + struct mem_section_usage *usage = READ_ONCE(ms->usage); + int idx = subsection_map_index(*pfn); + unsigned long bit; + + if (!usage) + return false; + + if (test_bit(idx, usage->subsection_map)) + return true; + + /* Find the next subsection that exists */ + bit = find_next_bit(usage->subsection_map, SUBSECTIONS_PER_SECTION, idx); + if (bit == SUBSECTIONS_PER_SECTION) + return false; + + *pfn = (*pfn & PAGE_SECTION_MASK) + (bit * PAGES_PER_SUBSECTION); + return true; +} +#else +static inline int pfn_section_valid(struct mem_section *ms, unsigned long pfn) +{ + return 1; +} + +static inline bool pfn_section_first_valid(struct mem_section *ms, unsigned long *pfn) +{ + return true; +} +#endif + +void sparse_init_early_section(int nid, struct page *map, unsigned long pnum, + unsigned long flags); + #ifndef CONFIG_HAVE_ARCH_PFN_VALID +/** + * pfn_valid - check if there is a valid memory map entry for a PFN + * @pfn: the page frame number to check + * + * Check if there is a valid memory map entry aka struct page for the @pfn. + * Note, that availability of the memory map entry does not imply that + * there is actual usable memory at that @pfn. The struct page may + * represent a hole or an unusable page frame. + * + * Return: 1 for PFNs that have memory map entries and 0 otherwise + */ static inline int pfn_valid(unsigned long pfn) { + struct mem_section *ms; + int ret; + + /* + * Ensure the upper PAGE_SHIFT bits are clear in the + * pfn. Else it might lead to false positives when + * some of the upper bits are set, but the lower bits + * match a valid pfn. + */ + if (PHYS_PFN(PFN_PHYS(pfn)) != pfn) + return 0; + if (pfn_to_section_nr(pfn) >= NR_MEM_SECTIONS) return 0; - return valid_section(__nr_to_section(pfn_to_section_nr(pfn))); + ms = __pfn_to_section(pfn); + rcu_read_lock_sched(); + if (!valid_section(ms)) { + rcu_read_unlock_sched(); + return 0; + } + /* + * Traditionally early sections always returned pfn_valid() for + * the entire section-sized span. + */ + ret = early_section(ms) || pfn_section_valid(ms, pfn); + rcu_read_unlock_sched(); + + return ret; +} + +/* Returns end_pfn or higher if no valid PFN remaining in range */ +static inline unsigned long first_valid_pfn(unsigned long pfn, unsigned long end_pfn) +{ + unsigned long nr = pfn_to_section_nr(pfn); + + rcu_read_lock_sched(); + + while (nr <= __highest_present_section_nr && pfn < end_pfn) { + struct mem_section *ms = __pfn_to_section(pfn); + + if (valid_section(ms) && + (early_section(ms) || pfn_section_first_valid(ms, &pfn))) { + rcu_read_unlock_sched(); + return pfn; + } + + /* Nothing left in this section? Skip to next section */ + nr++; + pfn = section_nr_to_pfn(nr); + } + + rcu_read_unlock_sched(); + return end_pfn; } + +static inline unsigned long next_valid_pfn(unsigned long pfn, unsigned long end_pfn) +{ + pfn++; + + if (pfn >= end_pfn) + return end_pfn; + + /* + * Either every PFN within the section (or subsection for VMEMMAP) is + * valid, or none of them are. So there's no point repeating the check + * for every PFN; only call first_valid_pfn() again when crossing a + * (sub)section boundary (i.e. !(pfn & ~PAGE_{SUB,}SECTION_MASK)). + */ + if (pfn & ~(IS_ENABLED(CONFIG_SPARSEMEM_VMEMMAP) ? + PAGE_SUBSECTION_MASK : PAGE_SECTION_MASK)) + return pfn; + + return first_valid_pfn(pfn, end_pfn); +} + + +#define for_each_valid_pfn(_pfn, _start_pfn, _end_pfn) \ + for ((_pfn) = first_valid_pfn((_start_pfn), (_end_pfn)); \ + (_pfn) < (_end_pfn); \ + (_pfn) = next_valid_pfn((_pfn), (_end_pfn))) + #endif -static inline int pfn_present(unsigned long pfn) +static inline int pfn_in_present_section(unsigned long pfn) { if (pfn_to_section_nr(pfn) >= NR_MEM_SECTIONS) return 0; - return present_section(__nr_to_section(pfn_to_section_nr(pfn))); + return present_section(__pfn_to_section(pfn)); +} + +static inline unsigned long next_present_section_nr(unsigned long section_nr) +{ + while (++section_nr <= __highest_present_section_nr) { + if (present_section_nr(section_nr)) + return section_nr; + } + + return -1; } +#define for_each_present_section_nr(start, section_nr) \ + for (section_nr = next_present_section_nr(start - 1); \ + section_nr != -1; \ + section_nr = next_present_section_nr(section_nr)) + /* * These are _only_ used during initialisation, therefore they * can use __initdata ... They could have names to indicate @@ -1214,64 +2285,26 @@ static inline int pfn_present(unsigned long pfn) #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) +#define sparse_vmemmap_init_nid_early(_nid, _use) do {} while (0) +#define sparse_vmemmap_init_nid_late(_nid) do {} while (0) +#define pfn_in_present_section pfn_valid +#define subsection_map_init(_pfn, _nr_pages) do {} while (0) #endif /* CONFIG_SPARSEMEM */ -#ifdef CONFIG_NODES_SPAN_OTHER_NODES -bool early_pfn_in_nid(unsigned long pfn, int nid); -#else -#define early_pfn_in_nid(pfn, nid) (1) -#endif - -#ifndef early_pfn_valid -#define early_pfn_valid(pfn) (1) -#endif - -void memory_present(int nid, unsigned long start, unsigned long end); -unsigned long __init node_memmap_size_bytes(int, unsigned long, unsigned long); - /* - * If it is possible to have holes within a MAX_ORDER_NR_PAGES, then we - * need to check pfn validility within that MAX_ORDER_NR_PAGES block. - * pfn_valid_within() should be used in this case; we optimise this away - * when we have no holes within a MAX_ORDER_NR_PAGES block. + * Fallback case for when the architecture provides its own pfn_valid() but + * not a corresponding for_each_valid_pfn(). */ -#ifdef CONFIG_HOLES_IN_ZONE -#define pfn_valid_within(pfn) pfn_valid(pfn) -#else -#define pfn_valid_within(pfn) (1) +#ifndef for_each_valid_pfn +#define for_each_valid_pfn(_pfn, _start_pfn, _end_pfn) \ + for ((_pfn) = (_start_pfn); (_pfn) < (_end_pfn); (_pfn)++) \ + if (pfn_valid(_pfn)) #endif -#ifdef CONFIG_ARCH_HAS_HOLES_MEMORYMODEL -/* - * pfn_valid() is meant to be able to tell if a given PFN has valid memmap - * associated with it or not. In FLATMEM, it is expected that holes always - * have valid memmap as long as there is valid PFNs either side of the hole. - * In SPARSEMEM, it is assumed that a valid section has a memmap for the - * entire section. - * - * However, an ARM, and maybe other embedded architectures in the future - * free memmap backing holes to save memory on the assumption the memmap is - * never used. The page_zone linkages are then broken even though pfn_valid() - * returns true. A walker of the full memmap must then do this additional - * check to ensure the memmap they are looking at is sane by making sure - * the zone and PFN linkages are still valid. This is expensive, but walkers - * of the full memmap are extremely rare. - */ -int memmap_valid_within(unsigned long pfn, - struct page *page, struct zone *zone); -#else -static inline int memmap_valid_within(unsigned long pfn, - struct page *page, struct zone *zone) -{ - return 1; -} -#endif /* CONFIG_ARCH_HAS_HOLES_MEMORYMODEL */ - #endif /* !__GENERATING_BOUNDS.H */ #endif /* !__ASSEMBLY__ */ #endif /* _LINUX_MMZONE_H */ |