diff options
Diffstat (limited to 'include/linux/mmzone.h')
-rw-r--r-- | include/linux/mmzone.h | 1077 |
1 files changed, 753 insertions, 324 deletions
diff --git a/include/linux/mmzone.h b/include/linux/mmzone.h index 462f6873905a..5f74891556f3 100644 --- a/include/linux/mmzone.h +++ b/include/linux/mmzone.h @@ -20,13 +20,14 @@ #include <linux/atomic.h> #include <linux/mm_types.h> #include <linux/page-flags.h> +#include <linux/local_lock.h> #include <asm/page.h> /* Free memory management - zoned buddy allocator. */ -#ifndef CONFIG_FORCE_MAX_ZONEORDER +#ifndef CONFIG_ARCH_FORCE_MAX_ORDER #define MAX_ORDER 11 #else -#define MAX_ORDER CONFIG_FORCE_MAX_ZONEORDER +#define MAX_ORDER CONFIG_ARCH_FORCE_MAX_ORDER #endif #define MAX_ORDER_NR_PAGES (1 << (MAX_ORDER - 1)) @@ -53,10 +54,7 @@ enum migratetype { * * 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, #endif @@ -82,59 +80,33 @@ 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 (type = 0; type < MIGRATE_TYPES; type++) extern int page_group_by_mobility_disabled; -#define NR_MIGRATETYPE_BITS (PB_migrate_end - PB_migrate + 1) -#define MIGRATETYPE_MASK ((1UL << NR_MIGRATETYPE_BITS) - 1) +#define MIGRATETYPE_MASK ((1UL << PB_migratetype_bits) - 1) #define get_pageblock_migratetype(page) \ - get_pfnblock_flags_mask(page, page_to_pfn(page), \ - PB_migrate_end, MIGRATETYPE_MASK) + get_pfnblock_flags_mask(page, page_to_pfn(page), MIGRATETYPE_MASK) struct free_area { struct list_head free_list[MIGRATE_TYPES]; unsigned long nr_free; }; -/* Used for pages not on another list */ -static inline void add_to_free_area(struct page *page, struct free_area *area, - int migratetype) -{ - list_add(&page->lru, &area->free_list[migratetype]); - area->nr_free++; -} - -/* Used for pages not on another list */ -static inline void add_to_free_area_tail(struct page *page, struct free_area *area, - int migratetype) -{ - list_add_tail(&page->lru, &area->free_list[migratetype]); - area->nr_free++; -} - -#ifdef CONFIG_SHUFFLE_PAGE_ALLOCATOR -/* Used to preserve page allocation order entropy */ -void add_to_free_area_random(struct page *page, struct free_area *area, - int migratetype); -#else -static inline void add_to_free_area_random(struct page *page, - struct free_area *area, int migratetype) -{ - add_to_free_area(page, area, migratetype); -} -#endif - -/* Used for pages which are on another list */ -static inline void move_to_free_area(struct page *page, struct free_area *area, - int migratetype) -{ - list_move(&page->lru, &area->free_list[migratetype]); -} - static inline struct page *get_page_from_free_area(struct free_area *area, int migratetype) { @@ -142,15 +114,6 @@ static inline struct page *get_page_from_free_area(struct free_area *area, struct page, lru); } -static inline void del_page_from_free_area(struct page *page, - struct free_area *area) -{ - list_del(&page->lru); - __ClearPageBuddy(page); - set_page_private(page, 0); - area->nr_free--; -} - static inline bool free_area_empty(struct free_area *area, int migratetype) { return list_empty(&area->free_list[migratetype]); @@ -158,21 +121,6 @@ static inline bool free_area_empty(struct free_area *area, int migratetype) struct pglist_data; -/* - * zone->lock and the 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; -#else -#define ZONE_PADDING(name) -#endif - #ifdef CONFIG_NUMA enum numa_stat_item { NUMA_HIT, /* allocated in intended node */ @@ -181,10 +129,10 @@ enum numa_stat_item { NUMA_INTERLEAVE_HIT, /* interleaver preferred this zone */ NUMA_LOCAL, /* allocation from local node */ NUMA_OTHER, /* allocation from other node */ - NR_VM_NUMA_STAT_ITEMS + NR_VM_NUMA_EVENT_ITEMS }; #else -#define NR_VM_NUMA_STAT_ITEMS 0 +#define NR_VM_NUMA_EVENT_ITEMS 0 #endif enum zone_stat_item { @@ -198,8 +146,6 @@ enum zone_stat_item { NR_ZONE_UNEVICTABLE, NR_ZONE_WRITE_PENDING, /* Count of dirty, writeback and unstable pages */ NR_MLOCK, /* mlock()ed pages found and moved off LRU */ - NR_PAGETABLE, /* used for pagetables */ - NR_KERNEL_STACK_KB, /* measured in KiB */ /* Second 128 byte cacheline */ NR_BOUNCE, #if IS_ENABLED(CONFIG_ZSMALLOC) @@ -215,14 +161,20 @@ enum node_stat_item { NR_INACTIVE_FILE, /* " " " " " */ NR_ACTIVE_FILE, /* " " " " " */ NR_UNEVICTABLE, /* " " " " " */ - NR_SLAB_RECLAIMABLE, - NR_SLAB_UNRECLAIMABLE, + 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, - WORKINGSET_ACTIVATE, - WORKINGSET_RESTORE, + 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. @@ -237,16 +189,68 @@ enum node_stat_item { NR_FILE_THPS, NR_FILE_PMDMAPPED, NR_ANON_THPS, - NR_UNSTABLE_NFS, /* NFS unstable pages */ NR_VMSCAN_WRITE, NR_VMSCAN_IMMEDIATE, /* Prioritise for reclaim when writeback ends */ NR_DIRTIED, /* page dirtyings since bootup */ NR_WRITTEN, /* page writings since bootup */ + 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_PAGETABLE, /* used for pagetables */ + NR_SECONDARY_PAGETABLE, /* secondary pagetables, e.g. KVM pagetables */ +#ifdef CONFIG_SWAP + NR_SWAPCACHE, +#endif +#ifdef CONFIG_NUMA_BALANCING + PGPROMOTE_SUCCESS, /* promote successfully */ + PGPROMOTE_CANDIDATE, /* candidate pages to promote */ +#endif 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, * so it is important to keep the active lists LRU_ACTIVE higher in * the array than the corresponding inactive lists, and to keep @@ -268,6 +272,14 @@ 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++) @@ -282,18 +294,9 @@ static inline bool is_active_lru(enum lru_list lru) return (lru == LRU_ACTIVE_ANON || lru == LRU_ACTIVE_FILE); } -struct zone_reclaim_stat { - /* - * 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. - * - * The anon LRU stats live in [0], file LRU stats in [1] - */ - unsigned long recent_rotated[2]; - unsigned long recent_scanned[2]; -}; +#define WORKINGSET_ANON 0 +#define WORKINGSET_FILE 1 +#define ANON_AND_FILE 2 enum lruvec_flags { LRUVEC_CONGESTED, /* lruvec has many dirty pages @@ -301,15 +304,230 @@ enum lruvec_flags { */ }; +#endif /* !__GENERATING_BOUNDS_H */ + +/* + * Evictable pages 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 page is on one of lrugen->lists[]. Otherwise it stores 0. + * + * A page is added to the youngest generation on faulting. The aging needs to + * check the accessed bit at least twice before handing this page over to the + * eviction. The first check takes care of the accessed bit set on the initial + * fault; the second check makes sure this page 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 page is on one of lrugen->lists[] so that + * the aging needs not to worry about it. And it's set again when a page + * 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. + */ +#define MIN_NR_GENS 2U +#define MAX_NR_GENS 4U + +/* + * Each generation is divided into multiple tiers. A page accessed N times + * through file descriptors is in tier order_base_2(N). A page in the first tier + * (N=0,1) is marked by PG_referenced unless it was faulted in through page + * tables or read ahead. A page in any other tier (N>1) is marked by + * PG_referenced and PG_workingset. This implies a minimum of two tiers is + * supported without using additional bits 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 pages 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. + */ +#define MAX_NR_TIERS 4U + +#ifndef __GENERATING_BOUNDS_H + +struct lruvec; +struct page_vma_mapped_walk; + +#define LRU_GEN_MASK ((BIT(LRU_GEN_WIDTH) - 1) << LRU_GEN_PGOFF) +#define LRU_REFS_MASK ((BIT(LRU_REFS_WIDTH) - 1) << LRU_REFS_PGOFF) + +#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 as clean file pages + * can be evicted regardless of swap constraints. + * + * Normally anon and file min_seq are in sync. But if swapping is constrained, + * e.g., out of swap space, file min_seq is allowed to advance and leave anon + * min_seq behind. + * + * The number of pages in each generation is eventually consistent and therefore + * can be transiently negative when reset_batch_size() is pending. + */ +struct lru_gen_struct { + /* 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 lists[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]; + /* the first tier doesn't need protection, hence the minus one */ + unsigned long protected[NR_HIST_GENS][ANON_AND_FILE][MAX_NR_TIERS - 1]; + /* 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; +}; + +enum { + MM_LEAF_TOTAL, /* total leaf entries */ + MM_LEAF_OLD, /* old leaf entries */ + MM_LEAF_YOUNG, /* young leaf entries */ + MM_NONLEAF_TOTAL, /* total non-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 { + /* set to max_seq after each iteration */ + unsigned long seq; + /* where the current iteration continues (inclusive) */ + struct list_head *head; + /* where the last iteration ended (exclusive) */ + struct list_head *tail; + /* to wait for the last page table walker to finish */ + struct wait_queue_head wait; + /* Bloom filters flip after each iteration */ + unsigned long *filters[NR_BLOOM_FILTERS]; + /* the mm stats for debugging */ + unsigned long stats[NR_HIST_GENS][NR_MM_STATS]; + /* the number of concurrent page table walkers */ + int nr_walkers; +}; + +struct lru_gen_mm_walk { + /* the lruvec under reclaim */ + struct lruvec *lruvec; + /* unstable max_seq from lru_gen_struct */ + unsigned long max_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; + bool can_swap; + bool force_scan; +}; + +void lru_gen_init_lruvec(struct lruvec *lruvec); +void lru_gen_look_around(struct page_vma_mapped_walk *pvmw); + +#ifdef CONFIG_MEMCG +void lru_gen_init_memcg(struct mem_cgroup *memcg); +void lru_gen_exit_memcg(struct mem_cgroup *memcg); +#endif + +#else /* !CONFIG_LRU_GEN */ + +static inline void lru_gen_init_lruvec(struct lruvec *lruvec) +{ +} + +static inline void lru_gen_look_around(struct page_vma_mapped_walk *pvmw) +{ +} + +#ifdef CONFIG_MEMCG +static inline void lru_gen_init_memcg(struct mem_cgroup *memcg) +{ +} + +static inline void lru_gen_exit_memcg(struct mem_cgroup *memcg) +{ +} +#endif + +#endif /* CONFIG_LRU_GEN */ + struct lruvec { struct list_head lists[NR_LRU_LISTS]; - struct zone_reclaim_stat reclaim_stat; - /* Evictions & activations on the inactive file list */ - atomic_long_t inactive_age; + /* 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; + 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_struct lrugen; + /* to concurrently iterate lru_gen_mm_list */ + struct lru_gen_mm_state mm_state; +#endif #ifdef CONFIG_MEMCG struct pglist_data *pgdat; #endif @@ -329,32 +547,56 @@ enum zone_watermarks { WMARK_MIN, WMARK_LOW, WMARK_HIGH, + WMARK_PROMO, NR_WMARK }; +/* + * One per migratetype for each PAGE_ALLOC_COSTLY_ORDER. One additional list + * for THP which will usually be GFP_MOVABLE. Even if it is another type, + * it should not contribute to serious fragmentation causing THP allocation + * failures. + */ +#ifdef CONFIG_TRANSPARENT_HUGEPAGE +#define NR_PCP_THP 1 +#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) + #define min_wmark_pages(z) (z->_watermark[WMARK_MIN] + z->watermark_boost) #define low_wmark_pages(z) (z->_watermark[WMARK_LOW] + z->watermark_boost) #define high_wmark_pages(z) (z->_watermark[WMARK_HIGH] + z->watermark_boost) #define wmark_pages(z, i) (z->_watermark[i] + z->watermark_boost) +/* Fields and list protected by pagesets local_lock in page_alloc.c */ 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 batch; /* chunk size for buddy add/remove */ + short free_factor; /* batch scaling factor during free */ +#ifdef CONFIG_NUMA + short expire; /* When 0, remote pagesets are drained */ +#endif /* 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; - u16 vm_numa_stat_diff[NR_VM_NUMA_STAT_ITEMS]; -#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 }; @@ -375,26 +617,6 @@ enum zone_type { * 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. - * - * Some examples: - * - * - i386 and x86_64 have a fixed 16M ZONE_DMA and ZONE_DMA32 for the - * rest of the lower 4G. - * - * - arm only uses ZONE_DMA, the size, up to 4G, may vary depending on - * the specific device. - * - * - arm64 has a fixed 1G ZONE_DMA and ZONE_DMA32 for the rest of the - * lower 4G. - * - * - powerpc only uses ZONE_DMA, the size, up to 2G, may vary - * depending on the specific device. - * - * - s390 uses ZONE_DMA fixed to the lower 2G. - * - * - ia64 and riscv only use ZONE_DMA32. - * - * - parisc uses neither. */ #ifdef CONFIG_ZONE_DMA ZONE_DMA, @@ -419,6 +641,55 @@ 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, @@ -429,6 +700,8 @@ enum zone_type { #ifndef __GENERATING_BOUNDS_H +#define ASYNC_AND_SYNC 2 + struct zone { /* Read-mostly fields */ @@ -453,7 +726,14 @@ struct zone { int node; #endif struct pglist_data *zone_pgdat; - struct per_cpu_pageset __percpu *pageset; + struct per_cpu_pages __percpu *per_cpu_pageset; + struct per_cpu_zonestat __percpu *per_cpu_zonestats; + /* + * the high and batch values are copied to individual pagesets for + * faster access + */ + int pageset_high; + int pageset_batch; #ifndef CONFIG_SPARSEMEM /* @@ -475,11 +755,18 @@ 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 @@ -498,12 +785,18 @@ struct zone { * give them a chance of being in the same cacheline. * * Write access to present_pages at runtime should be protected by - * mem_hotplug_begin/end(). Any reader who can't tolerant drift of - * present_pages should get_online_mems() to get a stable value. + * 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; +#if defined(CONFIG_MEMORY_HOTPLUG) + unsigned long present_early_pages; +#endif +#ifdef CONFIG_CMA + unsigned long cma_pages; +#endif const char *name; @@ -524,7 +817,7 @@ struct zone { int initialized; /* Write-intensive fields used from the page allocator */ - ZONE_PADDING(_pad1_) + CACHELINE_PADDING(_pad1_); /* free areas of different sizes */ struct free_area free_area[MAX_ORDER]; @@ -536,7 +829,7 @@ struct zone { spinlock_t lock; /* Write-intensive fields used by compaction and vmstats. */ - ZONE_PADDING(_pad2_) + CACHELINE_PADDING(_pad2_); /* * When free pages are below this point, additional steps are taken @@ -548,8 +841,8 @@ struct zone { #if defined CONFIG_COMPACTION || defined CONFIG_CMA /* pfn where compaction free scanner should start */ unsigned long compact_cached_free_pfn; - /* pfn where async and sync compaction migration scanner should start */ - unsigned long compact_cached_migrate_pfn[2]; + /* 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 @@ -559,6 +852,7 @@ struct zone { * 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; @@ -572,10 +866,10 @@ struct zone { bool contiguous; - ZONE_PADDING(_pad3_) + CACHELINE_PADDING(_pad3_); /* Zone statistics */ atomic_long_t vm_stat[NR_VM_ZONE_STAT_ITEMS]; - atomic_long_t vm_numa_stat[NR_VM_NUMA_STAT_ITEMS]; + atomic_long_t vm_numa_event[NR_VM_NUMA_EVENT_ITEMS]; } ____cacheline_internodealigned_in_smp; enum pgdat_flags { @@ -593,6 +887,7 @@ enum zone_flags { ZONE_BOOSTED_WATERMARK, /* zone recently boosted watermarks. * Cleared when kswapd is woken. */ + ZONE_RECLAIM_ACTIVE, /* kswapd may be scanning the zone. */ }; static inline unsigned long zone_managed_pages(struct zone *zone) @@ -600,6 +895,15 @@ static inline unsigned long zone_managed_pages(struct zone *zone) return (unsigned long)atomic_long_read(&zone->managed_pages); } +static inline unsigned long zone_cma_pages(struct zone *zone) +{ +#ifdef CONFIG_CMA + return zone->cma_pages; +#else + return 0; +#endif +} + static inline unsigned long zone_end_pfn(const struct zone *zone) { return zone->zone_start_pfn + zone->spanned_pages; @@ -620,6 +924,88 @@ static inline bool zone_is_empty(struct zone *zone) return zone->spanned_pages == 0; } +#ifndef BUILD_VDSO32_64 +/* + * The zone field is never updated after free_area_init_core() + * sets it, so none of the operations on it need to be atomic. + */ + +/* 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) + +/* + * 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 page_zonenum(const struct page *page) +{ + ASSERT_EXCLUSIVE_BITS(page->flags, ZONES_MASK << ZONES_PGSHIFT); + return (page->flags >> ZONES_PGSHIFT) & ZONES_MASK; +} + +static inline enum zone_type folio_zonenum(const struct folio *folio) +{ + return page_zonenum(&folio->page); +} + +#ifdef CONFIG_ZONE_DEVICE +static inline bool is_zone_device_page(const struct page *page) +{ + return page_zonenum(page) == ZONE_DEVICE; +} +extern void memmap_init_zone_device(struct zone *, unsigned long, + unsigned long, struct dev_pagemap *); +#else +static inline bool is_zone_device_page(const struct page *page) +{ + return false; +} +#endif + +static inline bool folio_is_zone_device(const struct folio *folio) +{ + return is_zone_device_page(&folio->page); +} + +static inline bool is_zone_movable_page(const struct page *page) +{ + return page_zonenum(page) == ZONE_MOVABLE; +} +#endif + /* * Return true if [start_pfn, start_pfn + nr_pages) range has a non-empty * intersection with the given zone @@ -685,10 +1071,12 @@ struct zonelist { struct zoneref _zonerefs[MAX_ZONES_PER_ZONELIST + 1]; }; -#ifndef CONFIG_DISCONTIGMEM -/* The array of struct pages - for discontigmem use pgdat->lmem_map */ +/* + * 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; -#endif #ifdef CONFIG_TRANSPARENT_HUGEPAGE struct deferred_split { @@ -706,12 +1094,23 @@ struct deferred_split { * 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_PAGE_EXTENSION struct page_ext *node_page_ext; @@ -721,6 +1120,8 @@ typedef struct pglist_data { /* * 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 @@ -737,18 +1138,28 @@ typedef struct pglist_data { int node_id; wait_queue_head_t kswapd_wait; wait_queue_head_t pfmemalloc_wait; - struct task_struct *kswapd; /* Protected by - mem_hotplug_begin/end() */ + + /* 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_classzone_idx; + enum zone_type kswapd_highest_zoneidx; int kswapd_failures; /* Number of 'reclaimed == 0' runs */ #ifdef CONFIG_COMPACTION int kcompactd_max_order; - enum zone_type kcompactd_classzone_idx; + 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 @@ -765,8 +1176,7 @@ typedef struct pglist_data { #endif /* CONFIG_NUMA */ /* Write-intensive fields used by page reclaim */ - ZONE_PADDING(_pad1_) - spinlock_t lru_lock; + CACHELINE_PADDING(_pad1_); #ifdef CONFIG_DEFERRED_STRUCT_PAGE_INIT /* @@ -780,6 +1190,21 @@ typedef struct pglist_data { 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 stat time of current promote + * threshold adjustment period + */ + unsigned long nbp_th_nr_cand; +#endif /* Fields commonly accessed by the page reclaim scanner */ /* @@ -791,21 +1216,23 @@ typedef struct pglist_data { unsigned long flags; - ZONE_PADDING(_pad2_) +#ifdef CONFIG_LRU_GEN + /* kswap mm walk data */ + struct lru_gen_mm_walk mm_walk; +#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 } 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)) @@ -815,28 +1242,28 @@ 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> void build_all_zonelists(pg_data_t *pgdat); void wakeup_kswapd(struct zone *zone, gfp_t gfp_mask, int order, - enum zone_type classzone_idx); + enum zone_type highest_zoneidx); bool __zone_watermark_ok(struct zone *z, unsigned int order, unsigned long mark, - int classzone_idx, unsigned int alloc_flags, + int highest_zoneidx, unsigned int alloc_flags, long free_pages); bool zone_watermark_ok(struct zone *z, unsigned int order, - unsigned long mark, int classzone_idx, + unsigned long mark, int highest_zoneidx, unsigned int alloc_flags); bool zone_watermark_ok_safe(struct zone *z, unsigned int order, - unsigned long mark, int classzone_idx); -enum memmap_context { - MEMMAP_EARLY, - MEMMAP_HOTPLUG, + unsigned long mark, int highest_zoneidx); +/* + * 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 void init_currently_empty_zone(struct zone *zone, unsigned long start_pfn, unsigned long size); @@ -851,20 +1278,6 @@ static inline struct pglist_data *lruvec_pgdat(struct lruvec *lruvec) #endif } -extern unsigned long lruvec_lru_size(struct lruvec *lruvec, enum lru_list lru, int zone_idx); - -#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 - -#if defined(CONFIG_SPARSEMEM) -void memblocks_present(void); -#else -static inline void memblocks_present(void) {} -#endif - #ifdef CONFIG_HAVE_MEMORYLESS_NODES int local_memory_node(int node_id); #else @@ -876,6 +1289,18 @@ static inline int local_memory_node(int node_id) { return node_id; }; */ #define zone_idx(zone) ((zone) - (zone)->zone_pgdat->node_zones) +#ifdef CONFIG_ZONE_DEVICE +static inline bool zone_is_zone_device(struct zone *zone) +{ + return zone_idx(zone) == ZONE_DEVICE; +} +#else +static inline bool zone_is_zone_device(struct zone *zone) +{ + return false; +} +#endif + /* * Returns true if a zone has pages managed by the buddy allocator. * All the reclaim decisions have to use this function rather than @@ -914,22 +1339,11 @@ static inline void zone_set_nid(struct zone *zone, int nid) {} extern int movable_zone; -#ifdef CONFIG_HIGHMEM -static inline int zone_movable_is_highmem(void) -{ -#ifdef CONFIG_HAVE_MEMBLOCK_NODE_MAP - return movable_zone == ZONE_HIGHMEM; -#else - return (ZONE_MOVABLE - 1) == ZONE_HIGHMEM; -#endif -} -#endif - 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 @@ -939,51 +1353,58 @@ static inline int is_highmem_idx(enum zone_type idx) * 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) { -#ifdef CONFIG_HIGHMEM return is_highmem_idx(zone_idx(zone)); +} + +#ifdef CONFIG_ZONE_DMA +bool has_managed_dma(void); #else - return 0; -#endif +static inline bool has_managed_dma(void) +{ + return false; } +#endif /* 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 *); -int watermark_boost_factor_sysctl_handler(struct ctl_table *, int, - void __user *, size_t *, loff_t *); -int watermark_scale_factor_sysctl_handler(struct ctl_table *, int, - void __user *, size_t *, loff_t *); + +int min_free_kbytes_sysctl_handler(struct ctl_table *, int, void *, size_t *, + loff_t *); +int watermark_scale_factor_sysctl_handler(struct ctl_table *, int, void *, + size_t *, loff_t *); extern int sysctl_lowmem_reserve_ratio[MAX_NR_ZONES]; -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 lowmem_reserve_ratio_sysctl_handler(struct ctl_table *, int, void *, + size_t *, loff_t *); +int percpu_pagelist_high_fraction_sysctl_handler(struct ctl_table *, int, + void *, size_t *, loff_t *); int sysctl_min_unmapped_ratio_sysctl_handler(struct ctl_table *, int, - void __user *, size_t *, loff_t *); + void *, size_t *, loff_t *); int sysctl_min_slab_ratio_sysctl_handler(struct ctl_table *, int, - void __user *, size_t *, loff_t *); - -extern int numa_zonelist_order_handler(struct ctl_table *, int, - void __user *, size_t *, loff_t *); + void *, size_t *, loff_t *); +int numa_zonelist_order_handler(struct ctl_table *, int, + void *, size_t *, loff_t *); +extern int percpu_pagelist_high_fraction; extern char numa_zonelist_order[]; #define NUMA_ZONELIST_ORDER_LEN 16 -#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); @@ -991,7 +1412,7 @@ 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(); \ @@ -999,7 +1420,7 @@ 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. @@ -1038,15 +1459,18 @@ struct zoneref *__next_zones_zonelist(struct zoneref *z, /** * 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 + * @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 */ static __always_inline struct zoneref *next_zones_zonelist(struct zoneref *z, enum zone_type highest_zoneidx, @@ -1059,10 +1483,9 @@ static __always_inline struct zoneref *next_zones_zonelist(struct zoneref *z, /** * 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 - * @return - Zoneref pointer for the first suitable zone found (see below) + * @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 @@ -1072,6 +1495,8 @@ static __always_inline struct zoneref *next_zones_zonelist(struct zoneref *z, * 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, @@ -1083,11 +1508,11 @@ static inline struct zoneref *first_zones_zonelist(struct zonelist *zonelist, /** * 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->_zonerefs 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 @@ -1098,7 +1523,7 @@ static inline struct zoneref *first_zones_zonelist(struct zonelist *zonelist, z = next_zones_zonelist(++z, highidx, nodemask), \ zone = zonelist_zone(z)) -#define for_next_zone_zonelist_nodemask(zone, z, zlist, highidx, nodemask) \ +#define for_next_zone_zonelist_nodemask(zone, z, highidx, nodemask) \ for (zone = z->zone; \ zone; \ z = next_zones_zonelist(++z, highidx, nodemask), \ @@ -1107,27 +1532,40 @@ static inline struct zoneref *first_zones_zonelist(struct zonelist *zonelist, /** * 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) { - BUILD_BUG_ON(IS_ENABLED(CONFIG_NUMA)); - 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 (!z->zone) ? true : false; } + + +#ifdef CONFIG_SPARSEMEM +#include <asm/sparsemem.h> #endif #ifdef CONFIG_FLATMEM @@ -1137,8 +1575,6 @@ 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 */ @@ -1170,6 +1606,7 @@ static inline unsigned long section_nr_to_pfn(unsigned long sec) #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) @@ -1185,7 +1622,9 @@ static inline unsigned long section_nr_to_pfn(unsigned long sec) #define SUBSECTION_ALIGN_DOWN(pfn) ((pfn) & PAGE_SUBSECTION_MASK) struct mem_section_usage { +#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]; }; @@ -1247,15 +1686,17 @@ static inline unsigned long *section_to_usemap(struct mem_section *ms) static inline struct mem_section *__nr_to_section(unsigned long nr) { + unsigned long root = SECTION_NR_TO_ROOT(nr); + + if (unlikely(root >= NR_SECTION_ROOTS)) + return NULL; + #ifdef CONFIG_SPARSEMEM_EXTREME - if (!mem_section) + if (!mem_section || !mem_section[root]) return NULL; #endif - if (!mem_section[SECTION_NR_TO_ROOT(nr)]) - return NULL; - return &mem_section[SECTION_NR_TO_ROOT(nr)][nr & SECTION_ROOT_MASK]; + return &mem_section[root][nr & SECTION_ROOT_MASK]; } -extern unsigned long __section_nr(struct mem_section *ms); extern size_t mem_section_usage_size(void); /* @@ -1269,15 +1710,32 @@ extern size_t mem_section_usage_size(void); * (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. + * 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_IS_ONLINE (1UL<<2) -#define SECTION_IS_EARLY (1UL<<3) -#define SECTION_MAP_LAST_BIT (1UL<<4) -#define SECTION_MAP_MASK (~(SECTION_MAP_LAST_BIT-1)) -#define SECTION_NID_SHIFT 3 +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 + 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 +#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) { @@ -1316,6 +1774,20 @@ static inline int online_section(struct mem_section *section) return (section && (section->section_mem_map & SECTION_IS_ONLINE)); } +#ifdef CONFIG_ZONE_DEVICE +static inline int online_device_section(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(struct mem_section *section) +{ + return 0; +} +#endif + static inline int online_section_nr(unsigned long nr) { return online_section(__nr_to_section(nr)); @@ -1323,10 +1795,8 @@ static inline int online_section_nr(unsigned long nr) #ifdef CONFIG_MEMORY_HOTPLUG void online_mem_sections(unsigned long start_pfn, unsigned long end_pfn); -#ifdef CONFIG_MEMORY_HOTREMOVE void offline_mem_sections(unsigned long start_pfn, unsigned long end_pfn); #endif -#endif static inline struct mem_section *__pfn_to_section(unsigned long pfn) { @@ -1355,13 +1825,33 @@ static inline int pfn_section_valid(struct mem_section *ms, unsigned long pfn) #endif #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; + /* + * 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; - ms = __nr_to_section(pfn_to_section_nr(pfn)); + ms = __pfn_to_section(pfn); if (!valid_section(ms)) return 0; /* @@ -1372,11 +1862,11 @@ static inline int pfn_valid(unsigned long 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) @@ -1404,75 +1894,14 @@ static inline unsigned long next_present_section_nr(unsigned long section_nr) #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 pfn_present pfn_valid +#define pfn_in_present_section pfn_valid #define subsection_map_init(_pfn, _nr_pages) do {} while (0) #endif /* CONFIG_SPARSEMEM */ -/* - * During memory init memblocks map pfns to nids. The search is expensive and - * this caches recent lookups. The implementation of __early_pfn_to_nid - * may treat start/end as pfns or sections. - */ -struct mminit_pfnnid_cache { - unsigned long last_start; - unsigned long last_end; - int last_nid; -}; - -#ifndef early_pfn_valid -#define early_pfn_valid(pfn) (1) -#endif - -void memory_present(int nid, unsigned long start, unsigned long end); - -/* - * If it is possible to have holes within a MAX_ORDER_NR_PAGES, then we - * need to check pfn validity 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. - */ -#ifdef CONFIG_HOLES_IN_ZONE -#define pfn_valid_within(pfn) pfn_valid(pfn) -#else -#define pfn_valid_within(pfn) (1) -#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. This means that a struct page exists for this - * pfn. The caller cannot assume the page is fully initialized in general. - * Hotplugable pages might not have been onlined yet. pfn_to_online_page() - * will ensure the struct page is fully online and initialized. Special pages - * (e.g. ZONE_DEVICE) are never onlined and should be treated accordingly. - * - * 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. - */ -bool memmap_valid_within(unsigned long pfn, - struct page *page, struct zone *zone); -#else -static inline bool memmap_valid_within(unsigned long pfn, - struct page *page, struct zone *zone) -{ - return true; -} -#endif /* CONFIG_ARCH_HAS_HOLES_MEMORYMODEL */ - #endif /* !__GENERATING_BOUNDS.H */ #endif /* !__ASSEMBLY__ */ #endif /* _LINUX_MMZONE_H */ |