diff options
Diffstat (limited to 'kernel/mm/page_alloc.c')
| -rw-r--r-- | kernel/mm/page_alloc.c | 1573 |
1 files changed, 924 insertions, 649 deletions
diff --git a/kernel/mm/page_alloc.c b/kernel/mm/page_alloc.c index 41bd90d60..d002418fc 100644 --- a/kernel/mm/page_alloc.c +++ b/kernel/mm/page_alloc.c @@ -62,6 +62,7 @@ #include <linux/sched/rt.h> #include <linux/locallock.h> #include <linux/page_owner.h> +#include <linux/kthread.h> #include <asm/sections.h> #include <asm/tlbflush.h> @@ -125,6 +126,24 @@ unsigned long dirty_balance_reserve __read_mostly; int percpu_pagelist_fraction; gfp_t gfp_allowed_mask __read_mostly = GFP_BOOT_MASK; +/* + * A cached value of the page's pageblock's migratetype, used when the page is + * put on a pcplist. Used to avoid the pageblock migratetype lookup when + * freeing from pcplists in most cases, at the cost of possibly becoming stale. + * Also the migratetype set in the page does not necessarily match the pcplist + * index, e.g. page might have MIGRATE_CMA set but be on a pcplist with any + * other index - this ensures that it will be put on the correct CMA freelist. + */ +static inline int get_pcppage_migratetype(struct page *page) +{ + return page->index; +} + +static inline void set_pcppage_migratetype(struct page *page, int migratetype) +{ + page->index = migratetype; +} + #ifdef CONFIG_PM_SLEEP /* * The following functions are used by the suspend/hibernate code to temporarily @@ -151,19 +170,19 @@ void pm_restrict_gfp_mask(void) WARN_ON(!mutex_is_locked(&pm_mutex)); WARN_ON(saved_gfp_mask); saved_gfp_mask = gfp_allowed_mask; - gfp_allowed_mask &= ~GFP_IOFS; + gfp_allowed_mask &= ~(__GFP_IO | __GFP_FS); } bool pm_suspended_storage(void) { - if ((gfp_allowed_mask & GFP_IOFS) == GFP_IOFS) + if ((gfp_allowed_mask & (__GFP_IO | __GFP_FS)) == (__GFP_IO | __GFP_FS)) return false; return true; } #endif /* CONFIG_PM_SLEEP */ #ifdef CONFIG_HUGETLB_PAGE_SIZE_VARIABLE -int pageblock_order __read_mostly; +unsigned int pageblock_order __read_mostly; #endif static void __free_pages_ok(struct page *page, unsigned int order); @@ -206,6 +225,18 @@ static char * const zone_names[MAX_NR_ZONES] = { "HighMem", #endif "Movable", +#ifdef CONFIG_ZONE_DEVICE + "Device", +#endif +}; + +static void free_compound_page(struct page *page); +compound_page_dtor * const compound_page_dtors[] = { + NULL, + free_compound_page, +#ifdef CONFIG_HUGETLB_PAGE + free_huge_page, +#endif }; int min_free_kbytes = 1024; @@ -248,6 +279,75 @@ static DEFINE_LOCAL_IRQ_LOCK(pa_lock); int page_group_by_mobility_disabled __read_mostly; +#ifdef CONFIG_DEFERRED_STRUCT_PAGE_INIT +static inline void reset_deferred_meminit(pg_data_t *pgdat) +{ + pgdat->first_deferred_pfn = ULONG_MAX; +} + +/* Returns true if the struct page for the pfn is uninitialised */ +static inline bool __meminit early_page_uninitialised(unsigned long pfn) +{ + if (pfn >= NODE_DATA(early_pfn_to_nid(pfn))->first_deferred_pfn) + return true; + + return false; +} + +static inline bool early_page_nid_uninitialised(unsigned long pfn, int nid) +{ + if (pfn >= NODE_DATA(nid)->first_deferred_pfn) + return true; + + return false; +} + +/* + * Returns false when the remaining initialisation should be deferred until + * later in the boot cycle when it can be parallelised. + */ +static inline bool update_defer_init(pg_data_t *pgdat, + unsigned long pfn, unsigned long zone_end, + unsigned long *nr_initialised) +{ + /* Always populate low zones for address-contrained allocations */ + if (zone_end < pgdat_end_pfn(pgdat)) + return true; + + /* Initialise at least 2G of the highest zone */ + (*nr_initialised)++; + if (*nr_initialised > (2UL << (30 - PAGE_SHIFT)) && + (pfn & (PAGES_PER_SECTION - 1)) == 0) { + pgdat->first_deferred_pfn = pfn; + return false; + } + + return true; +} +#else +static inline void reset_deferred_meminit(pg_data_t *pgdat) +{ +} + +static inline bool early_page_uninitialised(unsigned long pfn) +{ + return false; +} + +static inline bool early_page_nid_uninitialised(unsigned long pfn, int nid) +{ + return false; +} + +static inline bool update_defer_init(pg_data_t *pgdat, + unsigned long pfn, unsigned long zone_end, + unsigned long *nr_initialised) +{ + return true; +} +#endif + + void set_pageblock_migratetype(struct page *page, int migratetype) { if (unlikely(page_group_by_mobility_disabled && @@ -358,15 +458,15 @@ out: /* * Higher-order pages are called "compound pages". They are structured thusly: * - * The first PAGE_SIZE page is called the "head page". + * The first PAGE_SIZE page is called the "head page" and have PG_head set. * - * The remaining PAGE_SIZE pages are called "tail pages". + * The remaining PAGE_SIZE pages are called "tail pages". PageTail() is encoded + * in bit 0 of page->compound_head. The rest of bits is pointer to head page. * - * All pages have PG_compound set. All tail pages have their ->first_page - * pointing at the head page. + * The first tail page's ->compound_dtor holds the offset in array of compound + * page destructors. See compound_page_dtors. * - * The first tail page's ->lru.next holds the address of the compound page's - * put_page() function. Its ->lru.prev holds the order of allocation. + * The first tail page's ->compound_order holds the order of allocation. * This usage means that zero-order pages may not be compound. */ @@ -375,38 +475,21 @@ static void free_compound_page(struct page *page) __free_pages_ok(page, compound_order(page)); } -void prep_compound_page(struct page *page, unsigned long order) +void prep_compound_page(struct page *page, unsigned int order) { int i; int nr_pages = 1 << order; - set_compound_page_dtor(page, free_compound_page); + set_compound_page_dtor(page, COMPOUND_PAGE_DTOR); set_compound_order(page, order); __SetPageHead(page); for (i = 1; i < nr_pages; i++) { struct page *p = page + i; set_page_count(p, 0); - p->first_page = page; - /* Make sure p->first_page is always valid for PageTail() */ - smp_wmb(); - __SetPageTail(p); + set_compound_head(p, page); } } -static inline void prep_zero_page(struct page *page, unsigned int order, - gfp_t gfp_flags) -{ - int i; - - /* - * clear_highpage() will use KM_USER0, so it's a bug to use __GFP_ZERO - * and __GFP_HIGHMEM from hard or soft interrupt context. - */ - VM_BUG_ON((gfp_flags & __GFP_HIGHMEM) && in_interrupt()); - for (i = 0; i < (1 << order); i++) - clear_highpage(page + i); -} - #ifdef CONFIG_DEBUG_PAGEALLOC unsigned int _debug_guardpage_minorder; bool _debug_pagealloc_enabled __read_mostly; @@ -592,7 +675,7 @@ static inline void __free_one_page(struct page *page, unsigned long combined_idx; unsigned long uninitialized_var(buddy_idx); struct page *buddy; - int max_order = MAX_ORDER; + unsigned int max_order = MAX_ORDER; VM_BUG_ON(!zone_is_initialized(zone)); VM_BUG_ON_PAGE(page->flags & PAGE_FLAGS_CHECK_AT_PREP, page); @@ -605,7 +688,7 @@ static inline void __free_one_page(struct page *page, * pageblock. Without this, pageblock isolation * could cause incorrect freepage accounting. */ - max_order = min(MAX_ORDER, pageblock_order + 1); + max_order = min_t(unsigned int, MAX_ORDER, pageblock_order + 1); } else { __mod_zone_freepage_state(zone, 1 << order, migratetype); } @@ -724,11 +807,13 @@ static void free_pcppages_bulk(struct zone *zone, int count, /* must delete as __free_one_page list manipulates */ list_del(&page->lru); - mt = get_freepage_migratetype(page); + mt = get_pcppage_migratetype(page); + /* MIGRATE_ISOLATE page should not go to pcplists */ + VM_BUG_ON_PAGE(is_migrate_isolate(mt), page); + /* Pageblock could have been isolated meanwhile */ if (unlikely(has_isolate_pageblock(zone))) mt = get_pageblock_migratetype(page); - /* MIGRATE_MOVABLE list may include MIGRATE_RESERVEs */ __free_one_page(page, page_to_pfn(page), zone, 0, mt); trace_mm_page_pcpu_drain(page, 0, mt); to_free--; @@ -775,6 +860,7 @@ static void isolate_pcp_pages(int to_free, struct per_cpu_pages *src, do { page = list_last_entry(list, struct page, lru); list_del(&page->lru); + list_add(&page->lru, dst); } while (--to_free && --batch_free && !list_empty(list)); } @@ -803,17 +889,103 @@ static void free_one_page(struct zone *zone, static int free_tail_pages_check(struct page *head_page, struct page *page) { - if (!IS_ENABLED(CONFIG_DEBUG_VM)) - return 0; + int ret = 1; + + /* + * We rely page->lru.next never has bit 0 set, unless the page + * is PageTail(). Let's make sure that's true even for poisoned ->lru. + */ + BUILD_BUG_ON((unsigned long)LIST_POISON1 & 1); + + if (!IS_ENABLED(CONFIG_DEBUG_VM)) { + ret = 0; + goto out; + } if (unlikely(!PageTail(page))) { bad_page(page, "PageTail not set", 0); - return 1; + goto out; } - if (unlikely(page->first_page != head_page)) { - bad_page(page, "first_page not consistent", 0); - return 1; + if (unlikely(compound_head(page) != head_page)) { + bad_page(page, "compound_head not consistent", 0); + goto out; + } + ret = 0; +out: + clear_compound_head(page); + return ret; +} + +static void __meminit __init_single_page(struct page *page, unsigned long pfn, + unsigned long zone, int nid) +{ + set_page_links(page, zone, nid, pfn); + init_page_count(page); + page_mapcount_reset(page); + page_cpupid_reset_last(page); + + INIT_LIST_HEAD(&page->lru); +#ifdef WANT_PAGE_VIRTUAL + /* The shift won't overflow because ZONE_NORMAL is below 4G. */ + if (!is_highmem_idx(zone)) + set_page_address(page, __va(pfn << PAGE_SHIFT)); +#endif +} + +static void __meminit __init_single_pfn(unsigned long pfn, unsigned long zone, + int nid) +{ + return __init_single_page(pfn_to_page(pfn), pfn, zone, nid); +} + +#ifdef CONFIG_DEFERRED_STRUCT_PAGE_INIT +static void init_reserved_page(unsigned long pfn) +{ + pg_data_t *pgdat; + int nid, zid; + + if (!early_page_uninitialised(pfn)) + return; + + nid = early_pfn_to_nid(pfn); + pgdat = NODE_DATA(nid); + + for (zid = 0; zid < MAX_NR_ZONES; zid++) { + struct zone *zone = &pgdat->node_zones[zid]; + + if (pfn >= zone->zone_start_pfn && pfn < zone_end_pfn(zone)) + break; + } + __init_single_pfn(pfn, zid, nid); +} +#else +static inline void init_reserved_page(unsigned long pfn) +{ +} +#endif /* CONFIG_DEFERRED_STRUCT_PAGE_INIT */ + +/* + * Initialised pages do not have PageReserved set. This function is + * called for each range allocated by the bootmem allocator and + * marks the pages PageReserved. The remaining valid pages are later + * sent to the buddy page allocator. + */ +void __meminit reserve_bootmem_region(unsigned long start, unsigned long end) +{ + unsigned long start_pfn = PFN_DOWN(start); + unsigned long end_pfn = PFN_UP(end); + + for (; start_pfn < end_pfn; start_pfn++) { + if (pfn_valid(start_pfn)) { + struct page *page = pfn_to_page(start_pfn); + + init_reserved_page(start_pfn); + + /* Avoid false-positive PageTail() */ + INIT_LIST_HEAD(&page->lru); + + SetPageReserved(page); + } } - return 0; } static bool free_pages_prepare(struct page *page, unsigned int order) @@ -865,12 +1037,12 @@ static void __free_pages_ok(struct page *page, unsigned int order) migratetype = get_pfnblock_migratetype(page, pfn); local_lock_irqsave(pa_lock, flags); __count_vm_events(PGFREE, 1 << order); - set_freepage_migratetype(page, migratetype); free_one_page(page_zone(page), page, pfn, order, migratetype); local_unlock_irqrestore(pa_lock, flags); } -void __init __free_pages_bootmem(struct page *page, unsigned int order) +static void __init __free_pages_boot_core(struct page *page, + unsigned long pfn, unsigned int order) { unsigned int nr_pages = 1 << order; struct page *p = page; @@ -890,6 +1062,235 @@ void __init __free_pages_bootmem(struct page *page, unsigned int order) __free_pages(page, order); } +#if defined(CONFIG_HAVE_ARCH_EARLY_PFN_TO_NID) || \ + defined(CONFIG_HAVE_MEMBLOCK_NODE_MAP) + +static struct mminit_pfnnid_cache early_pfnnid_cache __meminitdata; + +int __meminit early_pfn_to_nid(unsigned long pfn) +{ + static DEFINE_SPINLOCK(early_pfn_lock); + int nid; + + spin_lock(&early_pfn_lock); + nid = __early_pfn_to_nid(pfn, &early_pfnnid_cache); + if (nid < 0) + nid = 0; + spin_unlock(&early_pfn_lock); + + return nid; +} +#endif + +#ifdef CONFIG_NODES_SPAN_OTHER_NODES +static inline bool __meminit meminit_pfn_in_nid(unsigned long pfn, int node, + struct mminit_pfnnid_cache *state) +{ + int nid; + + nid = __early_pfn_to_nid(pfn, state); + if (nid >= 0 && nid != node) + return false; + return true; +} + +/* Only safe to use early in boot when initialisation is single-threaded */ +static inline bool __meminit early_pfn_in_nid(unsigned long pfn, int node) +{ + return meminit_pfn_in_nid(pfn, node, &early_pfnnid_cache); +} + +#else + +static inline bool __meminit early_pfn_in_nid(unsigned long pfn, int node) +{ + return true; +} +static inline bool __meminit meminit_pfn_in_nid(unsigned long pfn, int node, + struct mminit_pfnnid_cache *state) +{ + return true; +} +#endif + + +void __init __free_pages_bootmem(struct page *page, unsigned long pfn, + unsigned int order) +{ + if (early_page_uninitialised(pfn)) + return; + return __free_pages_boot_core(page, pfn, order); +} + +#ifdef CONFIG_DEFERRED_STRUCT_PAGE_INIT +static void __init deferred_free_range(struct page *page, + unsigned long pfn, int nr_pages) +{ + int i; + + if (!page) + return; + + /* Free a large naturally-aligned chunk if possible */ + if (nr_pages == MAX_ORDER_NR_PAGES && + (pfn & (MAX_ORDER_NR_PAGES-1)) == 0) { + set_pageblock_migratetype(page, MIGRATE_MOVABLE); + __free_pages_boot_core(page, pfn, MAX_ORDER-1); + return; + } + + for (i = 0; i < nr_pages; i++, page++, pfn++) + __free_pages_boot_core(page, pfn, 0); +} + +/* Completion tracking for deferred_init_memmap() threads */ +static atomic_t pgdat_init_n_undone __initdata; +static __initdata DECLARE_COMPLETION(pgdat_init_all_done_comp); + +static inline void __init pgdat_init_report_one_done(void) +{ + if (atomic_dec_and_test(&pgdat_init_n_undone)) + complete(&pgdat_init_all_done_comp); +} + +/* Initialise remaining memory on a node */ +static int __init deferred_init_memmap(void *data) +{ + pg_data_t *pgdat = data; + int nid = pgdat->node_id; + struct mminit_pfnnid_cache nid_init_state = { }; + unsigned long start = jiffies; + unsigned long nr_pages = 0; + unsigned long walk_start, walk_end; + int i, zid; + struct zone *zone; + unsigned long first_init_pfn = pgdat->first_deferred_pfn; + const struct cpumask *cpumask = cpumask_of_node(pgdat->node_id); + + if (first_init_pfn == ULONG_MAX) { + pgdat_init_report_one_done(); + return 0; + } + + /* Bind memory initialisation thread to a local node if possible */ + if (!cpumask_empty(cpumask)) + set_cpus_allowed_ptr(current, cpumask); + + /* Sanity check boundaries */ + BUG_ON(pgdat->first_deferred_pfn < pgdat->node_start_pfn); + BUG_ON(pgdat->first_deferred_pfn > pgdat_end_pfn(pgdat)); + pgdat->first_deferred_pfn = ULONG_MAX; + + /* Only the highest zone is deferred so find it */ + for (zid = 0; zid < MAX_NR_ZONES; zid++) { + zone = pgdat->node_zones + zid; + if (first_init_pfn < zone_end_pfn(zone)) + break; + } + + for_each_mem_pfn_range(i, nid, &walk_start, &walk_end, NULL) { + unsigned long pfn, end_pfn; + struct page *page = NULL; + struct page *free_base_page = NULL; + unsigned long free_base_pfn = 0; + int nr_to_free = 0; + + end_pfn = min(walk_end, zone_end_pfn(zone)); + pfn = first_init_pfn; + if (pfn < walk_start) + pfn = walk_start; + if (pfn < zone->zone_start_pfn) + pfn = zone->zone_start_pfn; + + for (; pfn < end_pfn; pfn++) { + if (!pfn_valid_within(pfn)) + goto free_range; + + /* + * Ensure pfn_valid is checked every + * MAX_ORDER_NR_PAGES for memory holes + */ + if ((pfn & (MAX_ORDER_NR_PAGES - 1)) == 0) { + if (!pfn_valid(pfn)) { + page = NULL; + goto free_range; + } + } + + if (!meminit_pfn_in_nid(pfn, nid, &nid_init_state)) { + page = NULL; + goto free_range; + } + + /* Minimise pfn page lookups and scheduler checks */ + if (page && (pfn & (MAX_ORDER_NR_PAGES - 1)) != 0) { + page++; + } else { + nr_pages += nr_to_free; + deferred_free_range(free_base_page, + free_base_pfn, nr_to_free); + free_base_page = NULL; + free_base_pfn = nr_to_free = 0; + + page = pfn_to_page(pfn); + cond_resched(); + } + + if (page->flags) { + VM_BUG_ON(page_zone(page) != zone); + goto free_range; + } + + __init_single_page(page, pfn, zid, nid); + if (!free_base_page) { + free_base_page = page; + free_base_pfn = pfn; + nr_to_free = 0; + } + nr_to_free++; + + /* Where possible, batch up pages for a single free */ + continue; +free_range: + /* Free the current block of pages to allocator */ + nr_pages += nr_to_free; + deferred_free_range(free_base_page, free_base_pfn, + nr_to_free); + free_base_page = NULL; + free_base_pfn = nr_to_free = 0; + } + + first_init_pfn = max(end_pfn, first_init_pfn); + } + + /* Sanity check that the next zone really is unpopulated */ + WARN_ON(++zid < MAX_NR_ZONES && populated_zone(++zone)); + + pr_info("node %d initialised, %lu pages in %ums\n", nid, nr_pages, + jiffies_to_msecs(jiffies - start)); + + pgdat_init_report_one_done(); + return 0; +} + +void __init page_alloc_init_late(void) +{ + int nid; + + /* There will be num_node_state(N_MEMORY) threads */ + atomic_set(&pgdat_init_n_undone, num_node_state(N_MEMORY)); + for_each_node_state(nid, N_MEMORY) { + kthread_run(deferred_init_memmap, NODE_DATA(nid), "pgdatinit%d", nid); + } + + /* Block until all are initialised */ + wait_for_completion(&pgdat_init_all_done_comp); + + /* Reinit limits that are based on free pages after the kernel is up */ + files_maxfiles_init(); +} +#endif /* CONFIG_DEFERRED_STRUCT_PAGE_INIT */ + #ifdef CONFIG_CMA /* Free whole pageblock and set its migration type to MIGRATE_CMA. */ void __init init_cma_reserved_pageblock(struct page *page) @@ -979,6 +1380,10 @@ static inline int check_new_page(struct page *page) bad_reason = "non-NULL mapping"; if (unlikely(atomic_read(&page->_count) != 0)) bad_reason = "nonzero _count"; + if (unlikely(page->flags & __PG_HWPOISON)) { + bad_reason = "HWPoisoned (hardware-corrupted)"; + bad_flags = __PG_HWPOISON; + } if (unlikely(page->flags & PAGE_FLAGS_CHECK_AT_PREP)) { bad_reason = "PAGE_FLAGS_CHECK_AT_PREP flag set"; bad_flags = PAGE_FLAGS_CHECK_AT_PREP; @@ -1013,7 +1418,8 @@ static int prep_new_page(struct page *page, unsigned int order, gfp_t gfp_flags, kasan_alloc_pages(page, order); if (gfp_flags & __GFP_ZERO) - prep_zero_page(page, order, gfp_flags); + for (i = 0; i < (1 << order); i++) + clear_highpage(page + i); if (order && (gfp_flags & __GFP_COMP)) prep_compound_page(page, order); @@ -1058,7 +1464,7 @@ struct page *__rmqueue_smallest(struct zone *zone, unsigned int order, rmv_page_order(page); area->nr_free--; expand(zone, page, order, current_order, area, migratetype); - set_freepage_migratetype(page, migratetype); + set_pcppage_migratetype(page, migratetype); return page; } @@ -1071,15 +1477,14 @@ struct page *__rmqueue_smallest(struct zone *zone, unsigned int order, * the free lists for the desirable migrate type are depleted */ static int fallbacks[MIGRATE_TYPES][4] = { - [MIGRATE_UNMOVABLE] = { MIGRATE_RECLAIMABLE, MIGRATE_MOVABLE, MIGRATE_RESERVE }, - [MIGRATE_RECLAIMABLE] = { MIGRATE_UNMOVABLE, MIGRATE_MOVABLE, MIGRATE_RESERVE }, - [MIGRATE_MOVABLE] = { MIGRATE_RECLAIMABLE, MIGRATE_UNMOVABLE, MIGRATE_RESERVE }, + [MIGRATE_UNMOVABLE] = { MIGRATE_RECLAIMABLE, MIGRATE_MOVABLE, MIGRATE_TYPES }, + [MIGRATE_RECLAIMABLE] = { MIGRATE_UNMOVABLE, MIGRATE_MOVABLE, MIGRATE_TYPES }, + [MIGRATE_MOVABLE] = { MIGRATE_RECLAIMABLE, MIGRATE_UNMOVABLE, MIGRATE_TYPES }, #ifdef CONFIG_CMA - [MIGRATE_CMA] = { MIGRATE_RESERVE }, /* Never used */ + [MIGRATE_CMA] = { MIGRATE_TYPES }, /* Never used */ #endif - [MIGRATE_RESERVE] = { MIGRATE_RESERVE }, /* Never used */ #ifdef CONFIG_MEMORY_ISOLATION - [MIGRATE_ISOLATE] = { MIGRATE_RESERVE }, /* Never used */ + [MIGRATE_ISOLATE] = { MIGRATE_TYPES }, /* Never used */ #endif }; @@ -1104,7 +1509,7 @@ int move_freepages(struct zone *zone, int migratetype) { struct page *page; - unsigned long order; + unsigned int order; int pages_moved = 0; #ifndef CONFIG_HOLES_IN_ZONE @@ -1135,7 +1540,6 @@ int move_freepages(struct zone *zone, order = page_order(page); list_move(&page->lru, &zone->free_area[order].free_list[migratetype]); - set_freepage_migratetype(page, migratetype); page += 1 << order; pages_moved += 1 << order; } @@ -1218,7 +1622,7 @@ static bool can_steal_fallback(unsigned int order, int start_mt) static void steal_suitable_fallback(struct zone *zone, struct page *page, int start_type) { - int current_order = page_order(page); + unsigned int current_order = page_order(page); int pages; /* Take ownership for orders >= pageblock_order */ @@ -1253,7 +1657,7 @@ int find_suitable_fallback(struct free_area *area, unsigned int order, *can_steal = false; for (i = 0;; i++) { fallback_mt = fallbacks[migratetype][i]; - if (fallback_mt == MIGRATE_RESERVE) + if (fallback_mt == MIGRATE_TYPES) break; if (list_empty(&area->free_list[fallback_mt])) @@ -1272,6 +1676,101 @@ int find_suitable_fallback(struct free_area *area, unsigned int order, return -1; } +/* + * Reserve a pageblock for exclusive use of high-order atomic allocations if + * there are no empty page blocks that contain a page with a suitable order + */ +static void reserve_highatomic_pageblock(struct page *page, struct zone *zone, + unsigned int alloc_order) +{ + int mt; + unsigned long max_managed, flags; + + /* + * Limit the number reserved to 1 pageblock or roughly 1% of a zone. + * Check is race-prone but harmless. + */ + max_managed = (zone->managed_pages / 100) + pageblock_nr_pages; + if (zone->nr_reserved_highatomic >= max_managed) + return; + + spin_lock_irqsave(&zone->lock, flags); + + /* Recheck the nr_reserved_highatomic limit under the lock */ + if (zone->nr_reserved_highatomic >= max_managed) + goto out_unlock; + + /* Yoink! */ + mt = get_pageblock_migratetype(page); + if (mt != MIGRATE_HIGHATOMIC && + !is_migrate_isolate(mt) && !is_migrate_cma(mt)) { + zone->nr_reserved_highatomic += pageblock_nr_pages; + set_pageblock_migratetype(page, MIGRATE_HIGHATOMIC); + move_freepages_block(zone, page, MIGRATE_HIGHATOMIC); + } + +out_unlock: + spin_unlock_irqrestore(&zone->lock, flags); +} + +/* + * Used when an allocation is about to fail under memory pressure. This + * potentially hurts the reliability of high-order allocations when under + * intense memory pressure but failed atomic allocations should be easier + * to recover from than an OOM. + */ +static void unreserve_highatomic_pageblock(const struct alloc_context *ac) +{ + struct zonelist *zonelist = ac->zonelist; + unsigned long flags; + struct zoneref *z; + struct zone *zone; + struct page *page; + int order; + + for_each_zone_zonelist_nodemask(zone, z, zonelist, ac->high_zoneidx, + ac->nodemask) { + /* Preserve at least one pageblock */ + if (zone->nr_reserved_highatomic <= pageblock_nr_pages) + continue; + + spin_lock_irqsave(&zone->lock, flags); + for (order = 0; order < MAX_ORDER; order++) { + struct free_area *area = &(zone->free_area[order]); + + if (list_empty(&area->free_list[MIGRATE_HIGHATOMIC])) + continue; + + page = list_entry(area->free_list[MIGRATE_HIGHATOMIC].next, + struct page, lru); + + /* + * It should never happen but changes to locking could + * inadvertently allow a per-cpu drain to add pages + * to MIGRATE_HIGHATOMIC while unreserving so be safe + * and watch for underflows. + */ + zone->nr_reserved_highatomic -= min(pageblock_nr_pages, + zone->nr_reserved_highatomic); + + /* + * Convert to ac->migratetype and avoid the normal + * pageblock stealing heuristics. Minimally, the caller + * is doing the work and needs the pages. More + * importantly, if the block was always converted to + * MIGRATE_UNMOVABLE or another type then the number + * of pageblocks that cannot be completely freed + * may increase. + */ + set_pageblock_migratetype(page, ac->migratetype); + move_freepages_block(zone, page, ac->migratetype); + spin_unlock_irqrestore(&zone->lock, flags); + return; + } + spin_unlock_irqrestore(&zone->lock, flags); + } +} + /* Remove an element from the buddy allocator from the fallback list */ static inline struct page * __rmqueue_fallback(struct zone *zone, unsigned int order, int start_migratetype) @@ -1305,14 +1804,13 @@ __rmqueue_fallback(struct zone *zone, unsigned int order, int start_migratetype) expand(zone, page, order, current_order, area, start_migratetype); /* - * The freepage_migratetype may differ from pageblock's + * The pcppage_migratetype may differ from pageblock's * migratetype depending on the decisions in - * try_to_steal_freepages(). This is OK as long as it - * does not differ for MIGRATE_CMA pageblocks. For CMA - * we need to make sure unallocated pages flushed from - * pcp lists are returned to the correct freelist. + * find_suitable_fallback(). This is OK as long as it does not + * differ for MIGRATE_CMA pageblocks. Those can be used as + * fallback only via special __rmqueue_cma_fallback() function */ - set_freepage_migratetype(page, start_migratetype); + set_pcppage_migratetype(page, start_migratetype); trace_mm_page_alloc_extfrag(page, order, current_order, start_migratetype, fallback_mt); @@ -1328,29 +1826,17 @@ __rmqueue_fallback(struct zone *zone, unsigned int order, int start_migratetype) * Call me with the zone->lock already held. */ static struct page *__rmqueue(struct zone *zone, unsigned int order, - int migratetype) + int migratetype, gfp_t gfp_flags) { struct page *page; -retry_reserve: page = __rmqueue_smallest(zone, order, migratetype); - - if (unlikely(!page) && migratetype != MIGRATE_RESERVE) { + if (unlikely(!page)) { if (migratetype == MIGRATE_MOVABLE) page = __rmqueue_cma_fallback(zone, order); if (!page) page = __rmqueue_fallback(zone, order, migratetype); - - /* - * Use MIGRATE_RESERVE rather than fail an allocation. goto - * is used because __rmqueue_smallest is an inline function - * and we want just one call site - */ - if (!page) { - migratetype = MIGRATE_RESERVE; - goto retry_reserve; - } } trace_mm_page_alloc_zone_locked(page, order, migratetype); @@ -1370,7 +1856,7 @@ static int rmqueue_bulk(struct zone *zone, unsigned int order, spin_lock(&zone->lock); for (i = 0; i < count; ++i) { - struct page *page = __rmqueue(zone, order, migratetype); + struct page *page = __rmqueue(zone, order, migratetype, 0); if (unlikely(page == NULL)) break; @@ -1388,7 +1874,7 @@ static int rmqueue_bulk(struct zone *zone, unsigned int order, else list_add_tail(&page->lru, list); list = &page->lru; - if (is_migrate_cma(get_freepage_migratetype(page))) + if (is_migrate_cma(get_pcppage_migratetype(page))) __mod_zone_page_state(zone, NR_FREE_CMA_PAGES, -(1 << order)); } @@ -1601,7 +2087,7 @@ void free_hot_cold_page(struct page *page, bool cold) return; migratetype = get_pfnblock_migratetype(page, pfn); - set_freepage_migratetype(page, migratetype); + set_pcppage_migratetype(page, migratetype); local_lock_irqsave(pa_lock, flags); __count_vm_event(PGFREE); @@ -1665,6 +2151,7 @@ void free_hot_cold_page_list(struct list_head *list, bool cold) void split_page(struct page *page, unsigned int order) { int i; + gfp_t gfp_mask; VM_BUG_ON_PAGE(PageCompound(page), page); VM_BUG_ON_PAGE(!page_count(page), page); @@ -1678,10 +2165,11 @@ void split_page(struct page *page, unsigned int order) split_page(virt_to_page(page[0].shadow), order); #endif - set_page_owner(page, 0, 0); + gfp_mask = get_page_owner_gfp(page); + set_page_owner(page, 0, gfp_mask); for (i = 1; i < (1 << order); i++) { set_page_refcounted(page + i); - set_page_owner(page + i, 0, 0); + set_page_owner(page + i, 0, gfp_mask); } } EXPORT_SYMBOL_GPL(split_page); @@ -1711,6 +2199,8 @@ int __isolate_free_page(struct page *page, unsigned int order) zone->free_area[order].nr_free--; rmv_page_order(page); + set_page_owner(page, order, __GFP_MOVABLE); + /* Set the pageblock if the isolated page is at least a pageblock */ if (order >= pageblock_order - 1) { struct page *endpage = page + (1 << order) - 1; @@ -1722,7 +2212,7 @@ int __isolate_free_page(struct page *page, unsigned int order) } } - set_page_owner(page, order, 0); + return 1UL << order; } @@ -1759,7 +2249,7 @@ int split_free_page(struct page *page) static inline struct page *buffered_rmqueue(struct zone *preferred_zone, struct zone *zone, unsigned int order, - gfp_t gfp_flags, int migratetype) + gfp_t gfp_flags, int alloc_flags, int migratetype) { unsigned long flags; struct page *page; @@ -1802,13 +2292,21 @@ struct page *buffered_rmqueue(struct zone *preferred_zone, WARN_ON_ONCE(order > 1); } local_spin_lock_irqsave(pa_lock, &zone->lock, flags); - page = __rmqueue(zone, order, migratetype); + + page = NULL; + if (alloc_flags & ALLOC_HARDER) { + page = __rmqueue_smallest(zone, order, MIGRATE_HIGHATOMIC); + if (page) + trace_mm_page_alloc_zone_locked(page, order, migratetype); + } + if (!page) + page = __rmqueue(zone, order, migratetype, gfp_flags); if (!page) { spin_unlock(&zone->lock); goto failed; } __mod_zone_freepage_state(zone, -(1 << order), - get_freepage_migratetype(page)); + get_pcppage_migratetype(page)); spin_unlock(&zone->lock); } @@ -1834,13 +2332,13 @@ failed: static struct { struct fault_attr attr; - u32 ignore_gfp_highmem; - u32 ignore_gfp_wait; + bool ignore_gfp_highmem; + bool ignore_gfp_reclaim; u32 min_order; } fail_page_alloc = { .attr = FAULT_ATTR_INITIALIZER, - .ignore_gfp_wait = 1, - .ignore_gfp_highmem = 1, + .ignore_gfp_reclaim = true, + .ignore_gfp_highmem = true, .min_order = 1, }; @@ -1858,7 +2356,8 @@ static bool should_fail_alloc_page(gfp_t gfp_mask, unsigned int order) return false; if (fail_page_alloc.ignore_gfp_highmem && (gfp_mask & __GFP_HIGHMEM)) return false; - if (fail_page_alloc.ignore_gfp_wait && (gfp_mask & __GFP_WAIT)) + if (fail_page_alloc.ignore_gfp_reclaim && + (gfp_mask & __GFP_DIRECT_RECLAIM)) return false; return should_fail(&fail_page_alloc.attr, 1 << order); @@ -1877,7 +2376,7 @@ static int __init fail_page_alloc_debugfs(void) return PTR_ERR(dir); if (!debugfs_create_bool("ignore-gfp-wait", mode, dir, - &fail_page_alloc.ignore_gfp_wait)) + &fail_page_alloc.ignore_gfp_reclaim)) goto fail; if (!debugfs_create_bool("ignore-gfp-highmem", mode, dir, &fail_page_alloc.ignore_gfp_highmem)) @@ -1907,42 +2406,77 @@ static inline bool should_fail_alloc_page(gfp_t gfp_mask, unsigned int order) #endif /* CONFIG_FAIL_PAGE_ALLOC */ /* - * Return true if free pages are above 'mark'. This takes into account the order - * of the allocation. + * Return true if free base pages are above 'mark'. For high-order checks it + * will return true of the order-0 watermark is reached and there is at least + * one free page of a suitable size. Checking now avoids taking the zone lock + * to check in the allocation paths if no pages are free. */ static bool __zone_watermark_ok(struct zone *z, unsigned int order, unsigned long mark, int classzone_idx, int alloc_flags, long free_pages) { - /* free_pages may go negative - that's OK */ long min = mark; int o; - long free_cma = 0; + const int alloc_harder = (alloc_flags & ALLOC_HARDER); + /* free_pages may go negative - that's OK */ free_pages -= (1 << order) - 1; + if (alloc_flags & ALLOC_HIGH) min -= min / 2; - if (alloc_flags & ALLOC_HARDER) + + /* + * If the caller does not have rights to ALLOC_HARDER then subtract + * the high-atomic reserves. This will over-estimate the size of the + * atomic reserve but it avoids a search. + */ + if (likely(!alloc_harder)) + free_pages -= z->nr_reserved_highatomic; + else min -= min / 4; + #ifdef CONFIG_CMA /* If allocation can't use CMA areas don't use free CMA pages */ if (!(alloc_flags & ALLOC_CMA)) - free_cma = zone_page_state(z, NR_FREE_CMA_PAGES); + free_pages -= zone_page_state(z, NR_FREE_CMA_PAGES); #endif - if (free_pages - free_cma <= min + z->lowmem_reserve[classzone_idx]) + /* + * Check watermarks for an order-0 allocation request. If these + * are not met, then a high-order request also cannot go ahead + * even if a suitable page happened to be free. + */ + if (free_pages <= min + z->lowmem_reserve[classzone_idx]) return false; - for (o = 0; o < order; o++) { - /* At the next order, this order's pages become unavailable */ - free_pages -= z->free_area[o].nr_free << o; - /* Require fewer higher order pages to be free */ - min >>= 1; + /* If this is an order-0 request then the watermark is fine */ + if (!order) + return true; + + /* For a high-order request, check at least one suitable page is free */ + for (o = order; o < MAX_ORDER; o++) { + struct free_area *area = &z->free_area[o]; + int mt; + + if (!area->nr_free) + continue; + + if (alloc_harder) + return true; + + for (mt = 0; mt < MIGRATE_PCPTYPES; mt++) { + if (!list_empty(&area->free_list[mt])) + return true; + } - if (free_pages <= min) - return false; +#ifdef CONFIG_CMA + if ((alloc_flags & ALLOC_CMA) && + !list_empty(&area->free_list[MIGRATE_CMA])) { + return true; + } +#endif } - return true; + return false; } bool zone_watermark_ok(struct zone *z, unsigned int order, unsigned long mark, @@ -1953,134 +2487,18 @@ bool zone_watermark_ok(struct zone *z, unsigned int order, unsigned long mark, } bool zone_watermark_ok_safe(struct zone *z, unsigned int order, - unsigned long mark, int classzone_idx, int alloc_flags) + unsigned long mark, int classzone_idx) { long free_pages = zone_page_state(z, NR_FREE_PAGES); if (z->percpu_drift_mark && free_pages < z->percpu_drift_mark) free_pages = zone_page_state_snapshot(z, NR_FREE_PAGES); - return __zone_watermark_ok(z, order, mark, classzone_idx, alloc_flags, + return __zone_watermark_ok(z, order, mark, classzone_idx, 0, free_pages); } #ifdef CONFIG_NUMA -/* - * zlc_setup - Setup for "zonelist cache". Uses cached zone data to - * skip over zones that are not allowed by the cpuset, or that have - * been recently (in last second) found to be nearly full. See further - * comments in mmzone.h. Reduces cache footprint of zonelist scans - * that have to skip over a lot of full or unallowed zones. - * - * If the zonelist cache is present in the passed zonelist, then - * returns a pointer to the allowed node mask (either the current - * tasks mems_allowed, or node_states[N_MEMORY].) - * - * If the zonelist cache is not available for this zonelist, does - * nothing and returns NULL. - * - * If the fullzones BITMAP in the zonelist cache is stale (more than - * a second since last zap'd) then we zap it out (clear its bits.) - * - * We hold off even calling zlc_setup, until after we've checked the - * first zone in the zonelist, on the theory that most allocations will - * be satisfied from that first zone, so best to examine that zone as - * quickly as we can. - */ -static nodemask_t *zlc_setup(struct zonelist *zonelist, int alloc_flags) -{ - struct zonelist_cache *zlc; /* cached zonelist speedup info */ - nodemask_t *allowednodes; /* zonelist_cache approximation */ - - zlc = zonelist->zlcache_ptr; - if (!zlc) - return NULL; - - if (time_after(jiffies, zlc->last_full_zap + HZ)) { - bitmap_zero(zlc->fullzones, MAX_ZONES_PER_ZONELIST); - zlc->last_full_zap = jiffies; - } - - allowednodes = !in_interrupt() && (alloc_flags & ALLOC_CPUSET) ? - &cpuset_current_mems_allowed : - &node_states[N_MEMORY]; - return allowednodes; -} - -/* - * Given 'z' scanning a zonelist, run a couple of quick checks to see - * if it is worth looking at further for free memory: - * 1) Check that the zone isn't thought to be full (doesn't have its - * bit set in the zonelist_cache fullzones BITMAP). - * 2) Check that the zones node (obtained from the zonelist_cache - * z_to_n[] mapping) is allowed in the passed in allowednodes mask. - * Return true (non-zero) if zone is worth looking at further, or - * else return false (zero) if it is not. - * - * This check -ignores- the distinction between various watermarks, - * such as GFP_HIGH, GFP_ATOMIC, PF_MEMALLOC, ... If a zone is - * found to be full for any variation of these watermarks, it will - * be considered full for up to one second by all requests, unless - * we are so low on memory on all allowed nodes that we are forced - * into the second scan of the zonelist. - * - * In the second scan we ignore this zonelist cache and exactly - * apply the watermarks to all zones, even it is slower to do so. - * We are low on memory in the second scan, and should leave no stone - * unturned looking for a free page. - */ -static int zlc_zone_worth_trying(struct zonelist *zonelist, struct zoneref *z, - nodemask_t *allowednodes) -{ - struct zonelist_cache *zlc; /* cached zonelist speedup info */ - int i; /* index of *z in zonelist zones */ - int n; /* node that zone *z is on */ - - zlc = zonelist->zlcache_ptr; - if (!zlc) - return 1; - - i = z - zonelist->_zonerefs; - n = zlc->z_to_n[i]; - - /* This zone is worth trying if it is allowed but not full */ - return node_isset(n, *allowednodes) && !test_bit(i, zlc->fullzones); -} - -/* - * Given 'z' scanning a zonelist, set the corresponding bit in - * zlc->fullzones, so that subsequent attempts to allocate a page - * from that zone don't waste time re-examining it. - */ -static void zlc_mark_zone_full(struct zonelist *zonelist, struct zoneref *z) -{ - struct zonelist_cache *zlc; /* cached zonelist speedup info */ - int i; /* index of *z in zonelist zones */ - - zlc = zonelist->zlcache_ptr; - if (!zlc) - return; - - i = z - zonelist->_zonerefs; - - set_bit(i, zlc->fullzones); -} - -/* - * clear all zones full, called after direct reclaim makes progress so that - * a zone that was recently full is not skipped over for up to a second - */ -static void zlc_clear_zones_full(struct zonelist *zonelist) -{ - struct zonelist_cache *zlc; /* cached zonelist speedup info */ - - zlc = zonelist->zlcache_ptr; - if (!zlc) - return; - - bitmap_zero(zlc->fullzones, MAX_ZONES_PER_ZONELIST); -} - static bool zone_local(struct zone *local_zone, struct zone *zone) { return local_zone->node == zone->node; @@ -2091,28 +2509,7 @@ static bool zone_allows_reclaim(struct zone *local_zone, struct zone *zone) return node_distance(zone_to_nid(local_zone), zone_to_nid(zone)) < RECLAIM_DISTANCE; } - #else /* CONFIG_NUMA */ - -static nodemask_t *zlc_setup(struct zonelist *zonelist, int alloc_flags) -{ - return NULL; -} - -static int zlc_zone_worth_trying(struct zonelist *zonelist, struct zoneref *z, - nodemask_t *allowednodes) -{ - return 1; -} - -static void zlc_mark_zone_full(struct zonelist *zonelist, struct zoneref *z) -{ -} - -static void zlc_clear_zones_full(struct zonelist *zonelist) -{ -} - static bool zone_local(struct zone *local_zone, struct zone *zone) { return true; @@ -2122,7 +2519,6 @@ static bool zone_allows_reclaim(struct zone *local_zone, struct zone *zone) { return true; } - #endif /* CONFIG_NUMA */ static void reset_alloc_batches(struct zone *preferred_zone) @@ -2149,11 +2545,6 @@ get_page_from_freelist(gfp_t gfp_mask, unsigned int order, int alloc_flags, struct zoneref *z; struct page *page = NULL; struct zone *zone; - nodemask_t *allowednodes = NULL;/* zonelist_cache approximation */ - int zlc_active = 0; /* set if using zonelist_cache */ - int did_zlc_setup = 0; /* just call zlc_setup() one time */ - bool consider_zone_dirty = (alloc_flags & ALLOC_WMARK_LOW) && - (gfp_mask & __GFP_WRITE); int nr_fair_skipped = 0; bool zonelist_rescan; @@ -2168,9 +2559,6 @@ zonelist_scan: ac->nodemask) { unsigned long mark; - if (IS_ENABLED(CONFIG_NUMA) && zlc_active && - !zlc_zone_worth_trying(zonelist, z, allowednodes)) - continue; if (cpusets_enabled() && (alloc_flags & ALLOC_CPUSET) && !cpuset_zone_allowed(zone, gfp_mask)) @@ -2208,14 +2596,14 @@ zonelist_scan: * * XXX: For now, allow allocations to potentially * exceed the per-zone dirty limit in the slowpath - * (ALLOC_WMARK_LOW unset) before going into reclaim, + * (spread_dirty_pages unset) before going into reclaim, * which is important when on a NUMA setup the allowed * zones are together not big enough to reach the * global limit. The proper fix for these situations * will require awareness of zones in the * dirty-throttling and the flusher threads. */ - if (consider_zone_dirty && !zone_dirty_ok(zone)) + if (ac->spread_dirty_pages && !zone_dirty_ok(zone)) continue; mark = zone->watermark[alloc_flags & ALLOC_WMARK_MASK]; @@ -2228,28 +2616,8 @@ zonelist_scan: if (alloc_flags & ALLOC_NO_WATERMARKS) goto try_this_zone; - if (IS_ENABLED(CONFIG_NUMA) && - !did_zlc_setup && nr_online_nodes > 1) { - /* - * we do zlc_setup if there are multiple nodes - * and before considering the first zone allowed - * by the cpuset. - */ - allowednodes = zlc_setup(zonelist, alloc_flags); - zlc_active = 1; - did_zlc_setup = 1; - } - if (zone_reclaim_mode == 0 || !zone_allows_reclaim(ac->preferred_zone, zone)) - goto this_zone_full; - - /* - * As we may have just activated ZLC, check if the first - * eligible zone has failed zone_reclaim recently. - */ - if (IS_ENABLED(CONFIG_NUMA) && zlc_active && - !zlc_zone_worth_trying(zonelist, z, allowednodes)) continue; ret = zone_reclaim(zone, gfp_mask, order); @@ -2266,34 +2634,26 @@ zonelist_scan: ac->classzone_idx, alloc_flags)) goto try_this_zone; - /* - * Failed to reclaim enough to meet watermark. - * Only mark the zone full if checking the min - * watermark or if we failed to reclaim just - * 1<<order pages or else the page allocator - * fastpath will prematurely mark zones full - * when the watermark is between the low and - * min watermarks. - */ - if (((alloc_flags & ALLOC_WMARK_MASK) == ALLOC_WMARK_MIN) || - ret == ZONE_RECLAIM_SOME) - goto this_zone_full; - continue; } } try_this_zone: page = buffered_rmqueue(ac->preferred_zone, zone, order, - gfp_mask, ac->migratetype); + gfp_mask, alloc_flags, ac->migratetype); if (page) { if (prep_new_page(page, order, gfp_mask, alloc_flags)) goto try_this_zone; + + /* + * If this is a high-order atomic allocation then check + * if the pageblock should be reserved for the future + */ + if (unlikely(order && (alloc_flags & ALLOC_HARDER))) + reserve_highatomic_pageblock(page, zone, order); + return page; } -this_zone_full: - if (IS_ENABLED(CONFIG_NUMA) && zlc_active) - zlc_mark_zone_full(zonelist, z); } /* @@ -2314,12 +2674,6 @@ this_zone_full: zonelist_rescan = true; } - if (unlikely(IS_ENABLED(CONFIG_NUMA) && zlc_active)) { - /* Disable zlc cache for second zonelist scan */ - zlc_active = 0; - zonelist_rescan = true; - } - if (zonelist_rescan) goto zonelist_scan; @@ -2344,7 +2698,7 @@ static DEFINE_RATELIMIT_STATE(nopage_rs, DEFAULT_RATELIMIT_INTERVAL, DEFAULT_RATELIMIT_BURST); -void warn_alloc_failed(gfp_t gfp_mask, int order, const char *fmt, ...) +void warn_alloc_failed(gfp_t gfp_mask, unsigned int order, const char *fmt, ...) { unsigned int filter = SHOW_MEM_FILTER_NODES; @@ -2361,7 +2715,7 @@ void warn_alloc_failed(gfp_t gfp_mask, int order, const char *fmt, ...) if (test_thread_flag(TIF_MEMDIE) || (current->flags & (PF_MEMALLOC | PF_EXITING))) filter &= ~SHOW_MEM_FILTER_NODES; - if (in_interrupt() || !(gfp_mask & __GFP_WAIT)) + if (in_interrupt() || !(gfp_mask & __GFP_DIRECT_RECLAIM)) filter &= ~SHOW_MEM_FILTER_NODES; if (fmt) { @@ -2378,7 +2732,7 @@ void warn_alloc_failed(gfp_t gfp_mask, int order, const char *fmt, ...) va_end(args); } - pr_warn("%s: page allocation failure: order:%d, mode:0x%x\n", + pr_warn("%s: page allocation failure: order:%u, mode:0x%x\n", current->comm, order, gfp_mask); dump_stack(); @@ -2386,61 +2740,25 @@ void warn_alloc_failed(gfp_t gfp_mask, int order, const char *fmt, ...) show_mem(filter); } -static inline int -should_alloc_retry(gfp_t gfp_mask, unsigned int order, - unsigned long did_some_progress, - unsigned long pages_reclaimed) -{ - /* Do not loop if specifically requested */ - if (gfp_mask & __GFP_NORETRY) - return 0; - - /* Always retry if specifically requested */ - if (gfp_mask & __GFP_NOFAIL) - return 1; - - /* - * Suspend converts GFP_KERNEL to __GFP_WAIT which can prevent reclaim - * making forward progress without invoking OOM. Suspend also disables - * storage devices so kswapd will not help. Bail if we are suspending. - */ - if (!did_some_progress && pm_suspended_storage()) - return 0; - - /* - * In this implementation, order <= PAGE_ALLOC_COSTLY_ORDER - * means __GFP_NOFAIL, but that may not be true in other - * implementations. - */ - if (order <= PAGE_ALLOC_COSTLY_ORDER) - return 1; - - /* - * For order > PAGE_ALLOC_COSTLY_ORDER, if __GFP_REPEAT is - * specified, then we retry until we no longer reclaim any pages - * (above), or we've reclaimed an order of pages at least as - * large as the allocation's order. In both cases, if the - * allocation still fails, we stop retrying. - */ - if (gfp_mask & __GFP_REPEAT && pages_reclaimed < (1 << order)) - return 1; - - return 0; -} - static inline struct page * __alloc_pages_may_oom(gfp_t gfp_mask, unsigned int order, const struct alloc_context *ac, unsigned long *did_some_progress) { + struct oom_control oc = { + .zonelist = ac->zonelist, + .nodemask = ac->nodemask, + .gfp_mask = gfp_mask, + .order = order, + }; struct page *page; *did_some_progress = 0; /* - * Acquire the per-zone oom lock for each zone. If that - * fails, somebody else is making progress for us. + * Acquire the oom lock. If that fails, somebody else is + * making progress for us. */ - if (!oom_zonelist_trylock(ac->zonelist, gfp_mask)) { + if (!mutex_trylock(&oom_lock)) { *did_some_progress = 1; schedule_timeout_uninterruptible(1); return NULL; @@ -2466,26 +2784,27 @@ __alloc_pages_may_oom(gfp_t gfp_mask, unsigned int order, /* The OOM killer does not needlessly kill tasks for lowmem */ if (ac->high_zoneidx < ZONE_NORMAL) goto out; - /* The OOM killer does not compensate for light reclaim */ + /* The OOM killer does not compensate for IO-less reclaim */ if (!(gfp_mask & __GFP_FS)) { /* * XXX: Page reclaim didn't yield anything, * and the OOM killer can't be invoked, but - * keep looping as per should_alloc_retry(). + * keep looping as per tradition. */ *did_some_progress = 1; goto out; } + if (pm_suspended_storage()) + goto out; /* The OOM killer may not free memory on a specific node */ if (gfp_mask & __GFP_THISNODE) goto out; } /* Exhausted what can be done so it's blamo time */ - if (out_of_memory(ac->zonelist, gfp_mask, order, ac->nodemask, false) - || WARN_ON_ONCE(gfp_mask & __GFP_NOFAIL)) + if (out_of_memory(&oc) || WARN_ON_ONCE(gfp_mask & __GFP_NOFAIL)) *did_some_progress = 1; out: - oom_zonelist_unlock(ac->zonelist, gfp_mask); + mutex_unlock(&oom_lock); return page; } @@ -2599,19 +2918,17 @@ __alloc_pages_direct_reclaim(gfp_t gfp_mask, unsigned int order, if (unlikely(!(*did_some_progress))) return NULL; - /* After successful reclaim, reconsider all zones for allocation */ - if (IS_ENABLED(CONFIG_NUMA)) - zlc_clear_zones_full(ac->zonelist); - retry: page = get_page_from_freelist(gfp_mask, order, alloc_flags & ~ALLOC_NO_WATERMARKS, ac); /* * If an allocation failed after direct reclaim, it could be because - * pages are pinned on the per-cpu lists. Drain them and try again + * pages are pinned on the per-cpu lists or in high alloc reserves. + * Shrink them them and try again */ if (!page && !drained) { + unreserve_highatomic_pageblock(ac); drain_all_pages(NULL); drained = true; goto retry; @@ -2656,7 +2973,6 @@ static inline int gfp_to_alloc_flags(gfp_t gfp_mask) { int alloc_flags = ALLOC_WMARK_MIN | ALLOC_CPUSET; - const bool atomic = !(gfp_mask & (__GFP_WAIT | __GFP_NO_KSWAPD)); /* __GFP_HIGH is assumed to be the same as ALLOC_HIGH to save a branch. */ BUILD_BUG_ON(__GFP_HIGH != (__force gfp_t) ALLOC_HIGH); @@ -2665,11 +2981,11 @@ gfp_to_alloc_flags(gfp_t gfp_mask) * The caller may dip into page reserves a bit more if the caller * cannot run direct reclaim, or if the caller has realtime scheduling * policy or is asking for __GFP_HIGH memory. GFP_ATOMIC requests will - * set both ALLOC_HARDER (atomic == true) and ALLOC_HIGH (__GFP_HIGH). + * set both ALLOC_HARDER (__GFP_ATOMIC) and ALLOC_HIGH (__GFP_HIGH). */ alloc_flags |= (__force int) (gfp_mask & __GFP_HIGH); - if (atomic) { + if (gfp_mask & __GFP_ATOMIC) { /* * Not worth trying to allocate harder for __GFP_NOMEMALLOC even * if it can't schedule. @@ -2706,11 +3022,16 @@ bool gfp_pfmemalloc_allowed(gfp_t gfp_mask) return !!(gfp_to_alloc_flags(gfp_mask) & ALLOC_NO_WATERMARKS); } +static inline bool is_thp_gfp_mask(gfp_t gfp_mask) +{ + return (gfp_mask & (GFP_TRANSHUGE | __GFP_KSWAPD_RECLAIM)) == GFP_TRANSHUGE; +} + static inline struct page * __alloc_pages_slowpath(gfp_t gfp_mask, unsigned int order, struct alloc_context *ac) { - const gfp_t wait = gfp_mask & __GFP_WAIT; + bool can_direct_reclaim = gfp_mask & __GFP_DIRECT_RECLAIM; struct page *page = NULL; int alloc_flags; unsigned long pages_reclaimed = 0; @@ -2731,15 +3052,23 @@ __alloc_pages_slowpath(gfp_t gfp_mask, unsigned int order, } /* + * We also sanity check to catch abuse of atomic reserves being used by + * callers that are not in atomic context. + */ + if (WARN_ON_ONCE((gfp_mask & (__GFP_ATOMIC|__GFP_DIRECT_RECLAIM)) == + (__GFP_ATOMIC|__GFP_DIRECT_RECLAIM))) + gfp_mask &= ~__GFP_ATOMIC; + + /* * If this allocation cannot block and it is for a specific node, then * fail early. There's no need to wakeup kswapd or retry for a * speculative node-specific allocation. */ - if (IS_ENABLED(CONFIG_NUMA) && (gfp_mask & __GFP_THISNODE) && !wait) + if (IS_ENABLED(CONFIG_NUMA) && (gfp_mask & __GFP_THISNODE) && !can_direct_reclaim) goto nopage; retry: - if (!(gfp_mask & __GFP_NO_KSWAPD)) + if (gfp_mask & __GFP_KSWAPD_RECLAIM) wake_all_kswapds(order, ac); /* @@ -2782,8 +3111,8 @@ retry: } } - /* Atomic allocations - we can't balance anything */ - if (!wait) { + /* Caller is not willing to reclaim, we can't balance anything */ + if (!can_direct_reclaim) { /* * All existing users of the deprecated __GFP_NOFAIL are * blockable, so warn of any new users that actually allow this @@ -2813,7 +3142,7 @@ retry: goto got_pg; /* Checks for THP-specific high-order allocations */ - if ((gfp_mask & GFP_TRANSHUGE) == GFP_TRANSHUGE) { + if (is_thp_gfp_mask(gfp_mask)) { /* * If compaction is deferred for high-order allocations, it is * because sync compaction recently failed. If this is the case @@ -2848,8 +3177,7 @@ retry: * fault, so use asynchronous memory compaction for THP unless it is * khugepaged trying to collapse. */ - if ((gfp_mask & GFP_TRANSHUGE) != GFP_TRANSHUGE || - (current->flags & PF_KTHREAD)) + if (!is_thp_gfp_mask(gfp_mask) || (current->flags & PF_KTHREAD)) migration_mode = MIGRATE_SYNC_LIGHT; /* Try direct reclaim and then allocating */ @@ -2858,40 +3186,40 @@ retry: if (page) goto got_pg; - /* Check if we should retry the allocation */ + /* Do not loop if specifically requested */ + if (gfp_mask & __GFP_NORETRY) + goto noretry; + + /* Keep reclaiming pages as long as there is reasonable progress */ pages_reclaimed += did_some_progress; - if (should_alloc_retry(gfp_mask, order, did_some_progress, - pages_reclaimed)) { - /* - * If we fail to make progress by freeing individual - * pages, but the allocation wants us to keep going, - * start OOM killing tasks. - */ - if (!did_some_progress) { - page = __alloc_pages_may_oom(gfp_mask, order, ac, - &did_some_progress); - if (page) - goto got_pg; - if (!did_some_progress) - goto nopage; - } + if ((did_some_progress && order <= PAGE_ALLOC_COSTLY_ORDER) || + ((gfp_mask & __GFP_REPEAT) && pages_reclaimed < (1 << order))) { /* Wait for some write requests to complete then retry */ wait_iff_congested(ac->preferred_zone, BLK_RW_ASYNC, HZ/50); goto retry; - } else { - /* - * High-order allocations do not necessarily loop after - * direct reclaim and reclaim/compaction depends on compaction - * being called after reclaim so call directly if necessary - */ - page = __alloc_pages_direct_compact(gfp_mask, order, - alloc_flags, ac, migration_mode, - &contended_compaction, - &deferred_compaction); - if (page) - goto got_pg; } + /* Reclaim has failed us, start killing things */ + page = __alloc_pages_may_oom(gfp_mask, order, ac, &did_some_progress); + if (page) + goto got_pg; + + /* Retry as long as the OOM killer is making progress */ + if (did_some_progress) + goto retry; + +noretry: + /* + * High-order allocations do not necessarily loop after + * direct reclaim and reclaim/compaction depends on compaction + * being called after reclaim so call directly if necessary + */ + page = __alloc_pages_direct_compact(gfp_mask, order, alloc_flags, + ac, migration_mode, + &contended_compaction, + &deferred_compaction); + if (page) + goto got_pg; nopage: warn_alloc_failed(gfp_mask, order, NULL); got_pg: @@ -2920,7 +3248,7 @@ __alloc_pages_nodemask(gfp_t gfp_mask, unsigned int order, lockdep_trace_alloc(gfp_mask); - might_sleep_if(gfp_mask & __GFP_WAIT); + might_sleep_if(gfp_mask & __GFP_DIRECT_RECLAIM); if (should_fail_alloc_page(gfp_mask, order)) return NULL; @@ -2941,6 +3269,10 @@ retry_cpuset: /* We set it here, as __alloc_pages_slowpath might have changed it */ ac.zonelist = zonelist; + + /* Dirty zone balancing only done in the fast path */ + ac.spread_dirty_pages = (gfp_mask & __GFP_WRITE); + /* The preferred zone is used for statistics later */ preferred_zoneref = first_zones_zonelist(ac.zonelist, ac.high_zoneidx, ac.nodemask ? : &cpuset_current_mems_allowed, @@ -2959,6 +3291,7 @@ retry_cpuset: * complete. */ alloc_mask = memalloc_noio_flags(gfp_mask); + ac.spread_dirty_pages = false; page = __alloc_pages_slowpath(alloc_mask, order, &ac); } @@ -3031,6 +3364,104 @@ void free_pages(unsigned long addr, unsigned int order) EXPORT_SYMBOL(free_pages); /* + * Page Fragment: + * An arbitrary-length arbitrary-offset area of memory which resides + * within a 0 or higher order page. Multiple fragments within that page + * are individually refcounted, in the page's reference counter. + * + * The page_frag functions below provide a simple allocation framework for + * page fragments. This is used by the network stack and network device + * drivers to provide a backing region of memory for use as either an + * sk_buff->head, or to be used in the "frags" portion of skb_shared_info. + */ +static struct page *__page_frag_refill(struct page_frag_cache *nc, + gfp_t gfp_mask) +{ + struct page *page = NULL; + gfp_t gfp = gfp_mask; + +#if (PAGE_SIZE < PAGE_FRAG_CACHE_MAX_SIZE) + gfp_mask |= __GFP_COMP | __GFP_NOWARN | __GFP_NORETRY | + __GFP_NOMEMALLOC; + page = alloc_pages_node(NUMA_NO_NODE, gfp_mask, + PAGE_FRAG_CACHE_MAX_ORDER); + nc->size = page ? PAGE_FRAG_CACHE_MAX_SIZE : PAGE_SIZE; +#endif + if (unlikely(!page)) + page = alloc_pages_node(NUMA_NO_NODE, gfp, 0); + + nc->va = page ? page_address(page) : NULL; + + return page; +} + +void *__alloc_page_frag(struct page_frag_cache *nc, + unsigned int fragsz, gfp_t gfp_mask) +{ + unsigned int size = PAGE_SIZE; + struct page *page; + int offset; + + if (unlikely(!nc->va)) { +refill: + page = __page_frag_refill(nc, gfp_mask); + if (!page) + return NULL; + +#if (PAGE_SIZE < PAGE_FRAG_CACHE_MAX_SIZE) + /* if size can vary use size else just use PAGE_SIZE */ + size = nc->size; +#endif + /* Even if we own the page, we do not use atomic_set(). + * This would break get_page_unless_zero() users. + */ + atomic_add(size - 1, &page->_count); + + /* reset page count bias and offset to start of new frag */ + nc->pfmemalloc = page_is_pfmemalloc(page); + nc->pagecnt_bias = size; + nc->offset = size; + } + + offset = nc->offset - fragsz; + if (unlikely(offset < 0)) { + page = virt_to_page(nc->va); + + if (!atomic_sub_and_test(nc->pagecnt_bias, &page->_count)) + goto refill; + +#if (PAGE_SIZE < PAGE_FRAG_CACHE_MAX_SIZE) + /* if size can vary use size else just use PAGE_SIZE */ + size = nc->size; +#endif + /* OK, page count is 0, we can safely set it */ + atomic_set(&page->_count, size); + + /* reset page count bias and offset to start of new frag */ + nc->pagecnt_bias = size; + offset = size - fragsz; + } + + nc->pagecnt_bias--; + nc->offset = offset; + + return nc->va + offset; +} +EXPORT_SYMBOL(__alloc_page_frag); + +/* + * Frees a page fragment allocated out of either a compound or order 0 page. + */ +void __free_page_frag(void *addr) +{ + struct page *page = virt_to_head_page(addr); + + if (unlikely(put_page_testzero(page))) + __free_pages_ok(page, compound_order(page)); +} +EXPORT_SYMBOL(__free_page_frag); + +/* * alloc_kmem_pages charges newly allocated pages to the kmem resource counter * of the current memory cgroup. * @@ -3040,24 +3471,24 @@ EXPORT_SYMBOL(free_pages); struct page *alloc_kmem_pages(gfp_t gfp_mask, unsigned int order) { struct page *page; - struct mem_cgroup *memcg = NULL; - if (!memcg_kmem_newpage_charge(gfp_mask, &memcg, order)) - return NULL; page = alloc_pages(gfp_mask, order); - memcg_kmem_commit_charge(page, memcg, order); + if (page && memcg_kmem_charge(page, gfp_mask, order) != 0) { + __free_pages(page, order); + page = NULL; + } return page; } struct page *alloc_kmem_pages_node(int nid, gfp_t gfp_mask, unsigned int order) { struct page *page; - struct mem_cgroup *memcg = NULL; - if (!memcg_kmem_newpage_charge(gfp_mask, &memcg, order)) - return NULL; page = alloc_pages_node(nid, gfp_mask, order); - memcg_kmem_commit_charge(page, memcg, order); + if (page && memcg_kmem_charge(page, gfp_mask, order) != 0) { + __free_pages(page, order); + page = NULL; + } return page; } @@ -3067,7 +3498,7 @@ struct page *alloc_kmem_pages_node(int nid, gfp_t gfp_mask, unsigned int order) */ void __free_kmem_pages(struct page *page, unsigned int order) { - memcg_kmem_uncharge_pages(page, order); + memcg_kmem_uncharge(page, order); __free_pages(page, order); } @@ -3079,7 +3510,8 @@ void free_kmem_pages(unsigned long addr, unsigned int order) } } -static void *make_alloc_exact(unsigned long addr, unsigned order, size_t size) +static void *make_alloc_exact(unsigned long addr, unsigned int order, + size_t size) { if (addr) { unsigned long alloc_end = addr + (PAGE_SIZE << order); @@ -3126,12 +3558,10 @@ EXPORT_SYMBOL(alloc_pages_exact); * * Like alloc_pages_exact(), but try to allocate on node nid first before falling * back. - * Note this is not alloc_pages_exact_node() which allocates on a specific node, - * but is not exact. */ void * __meminit alloc_pages_exact_nid(int nid, size_t size, gfp_t gfp_mask) { - unsigned order = get_order(size); + unsigned int order = get_order(size); struct page *p = alloc_pages_node(nid, gfp_mask, order); if (!p) return NULL; @@ -3278,9 +3708,9 @@ static void show_migration_types(unsigned char type) { static const char types[MIGRATE_TYPES] = { [MIGRATE_UNMOVABLE] = 'U', - [MIGRATE_RECLAIMABLE] = 'E', [MIGRATE_MOVABLE] = 'M', - [MIGRATE_RESERVE] = 'R', + [MIGRATE_RECLAIMABLE] = 'E', + [MIGRATE_HIGHATOMIC] = 'H', #ifdef CONFIG_CMA [MIGRATE_CMA] = 'C', #endif @@ -3433,7 +3863,8 @@ void show_free_areas(unsigned int filter) } for_each_populated_zone(zone) { - unsigned long nr[MAX_ORDER], flags, order, total = 0; + unsigned int order; + unsigned long nr[MAX_ORDER], flags, total = 0; unsigned char types[MAX_ORDER]; if (skip_free_areas_node(filter, zone_to_nid(zone))) @@ -3782,7 +4213,7 @@ static void build_zonelists(pg_data_t *pgdat) nodemask_t used_mask; int local_node, prev_node; struct zonelist *zonelist; - int order = current_zonelist_order; + unsigned int order = current_zonelist_order; /* initialize zonelists */ for (i = 0; i < MAX_ZONELISTS; i++) { @@ -3826,20 +4257,6 @@ static void build_zonelists(pg_data_t *pgdat) build_thisnode_zonelists(pgdat); } -/* Construct the zonelist performance cache - see further mmzone.h */ -static void build_zonelist_cache(pg_data_t *pgdat) -{ - struct zonelist *zonelist; - struct zonelist_cache *zlc; - struct zoneref *z; - - zonelist = &pgdat->node_zonelists[0]; - zonelist->zlcache_ptr = zlc = &zonelist->zlcache; - bitmap_zero(zlc->fullzones, MAX_ZONES_PER_ZONELIST); - for (z = zonelist->_zonerefs; z->zone; z++) - zlc->z_to_n[z - zonelist->_zonerefs] = zonelist_node_idx(z); -} - #ifdef CONFIG_HAVE_MEMORYLESS_NODES /* * Return node id of node used for "local" allocations. @@ -3900,12 +4317,6 @@ static void build_zonelists(pg_data_t *pgdat) zonelist->_zonerefs[j].zone_idx = 0; } -/* non-NUMA variant of zonelist performance cache - just NULL zlcache_ptr */ -static void build_zonelist_cache(pg_data_t *pgdat) -{ - pgdat->node_zonelists[0].zlcache_ptr = NULL; -} - #endif /* CONFIG_NUMA */ /* @@ -3946,14 +4357,12 @@ static int __build_all_zonelists(void *data) if (self && !node_online(self->node_id)) { build_zonelists(self); - build_zonelist_cache(self); } for_each_online_node(nid) { pg_data_t *pgdat = NODE_DATA(nid); build_zonelists(pgdat); - build_zonelist_cache(pgdat); } /* @@ -4113,117 +4522,6 @@ static inline unsigned long wait_table_bits(unsigned long size) } /* - * Check if a pageblock contains reserved pages - */ -static int pageblock_is_reserved(unsigned long start_pfn, unsigned long end_pfn) -{ - unsigned long pfn; - - for (pfn = start_pfn; pfn < end_pfn; pfn++) { - if (!pfn_valid_within(pfn) || PageReserved(pfn_to_page(pfn))) - return 1; - } - return 0; -} - -/* - * Mark a number of pageblocks as MIGRATE_RESERVE. The number - * of blocks reserved is based on min_wmark_pages(zone). The memory within - * the reserve will tend to store contiguous free pages. Setting min_free_kbytes - * higher will lead to a bigger reserve which will get freed as contiguous - * blocks as reclaim kicks in - */ -static void setup_zone_migrate_reserve(struct zone *zone) -{ - unsigned long start_pfn, pfn, end_pfn, block_end_pfn; - struct page *page; - unsigned long block_migratetype; - int reserve; - int old_reserve; - - /* - * Get the start pfn, end pfn and the number of blocks to reserve - * We have to be careful to be aligned to pageblock_nr_pages to - * make sure that we always check pfn_valid for the first page in - * the block. - */ - start_pfn = zone->zone_start_pfn; - end_pfn = zone_end_pfn(zone); - start_pfn = roundup(start_pfn, pageblock_nr_pages); - reserve = roundup(min_wmark_pages(zone), pageblock_nr_pages) >> - pageblock_order; - - /* - * Reserve blocks are generally in place to help high-order atomic - * allocations that are short-lived. A min_free_kbytes value that - * would result in more than 2 reserve blocks for atomic allocations - * is assumed to be in place to help anti-fragmentation for the - * future allocation of hugepages at runtime. - */ - reserve = min(2, reserve); - old_reserve = zone->nr_migrate_reserve_block; - - /* When memory hot-add, we almost always need to do nothing */ - if (reserve == old_reserve) - return; - zone->nr_migrate_reserve_block = reserve; - - for (pfn = start_pfn; pfn < end_pfn; pfn += pageblock_nr_pages) { - if (!pfn_valid(pfn)) - continue; - page = pfn_to_page(pfn); - - /* Watch out for overlapping nodes */ - if (page_to_nid(page) != zone_to_nid(zone)) - continue; - - block_migratetype = get_pageblock_migratetype(page); - - /* Only test what is necessary when the reserves are not met */ - if (reserve > 0) { - /* - * Blocks with reserved pages will never free, skip - * them. - */ - block_end_pfn = min(pfn + pageblock_nr_pages, end_pfn); - if (pageblock_is_reserved(pfn, block_end_pfn)) - continue; - - /* If this block is reserved, account for it */ - if (block_migratetype == MIGRATE_RESERVE) { - reserve--; - continue; - } - - /* Suitable for reserving if this block is movable */ - if (block_migratetype == MIGRATE_MOVABLE) { - set_pageblock_migratetype(page, - MIGRATE_RESERVE); - move_freepages_block(zone, page, - MIGRATE_RESERVE); - reserve--; - continue; - } - } else if (!old_reserve) { - /* - * At boot time we don't need to scan the whole zone - * for turning off MIGRATE_RESERVE. - */ - break; - } - - /* - * If the reserve is met and this is a previous reserved block, - * take it back - */ - if (block_migratetype == MIGRATE_RESERVE) { - set_pageblock_migratetype(page, MIGRATE_MOVABLE); - move_freepages_block(zone, page, MIGRATE_MOVABLE); - } - } -} - -/* * Initially all pages are reserved - free ones are freed * up by free_all_bootmem() once the early boot process is * done. Non-atomic initialization, single-pass. @@ -4231,15 +4529,16 @@ static void setup_zone_migrate_reserve(struct zone *zone) void __meminit memmap_init_zone(unsigned long size, int nid, unsigned long zone, unsigned long start_pfn, enum memmap_context context) { - struct page *page; + pg_data_t *pgdat = NODE_DATA(nid); unsigned long end_pfn = start_pfn + size; unsigned long pfn; struct zone *z; + unsigned long nr_initialised = 0; if (highest_memmap_pfn < end_pfn - 1) highest_memmap_pfn = end_pfn - 1; - z = &NODE_DATA(nid)->node_zones[zone]; + z = &pgdat->node_zones[zone]; for (pfn = start_pfn; pfn < end_pfn; pfn++) { /* * There can be holes in boot-time mem_map[]s @@ -4251,39 +4550,31 @@ void __meminit memmap_init_zone(unsigned long size, int nid, unsigned long zone, continue; if (!early_pfn_in_nid(pfn, nid)) continue; + if (!update_defer_init(pgdat, pfn, end_pfn, + &nr_initialised)) + break; } - page = pfn_to_page(pfn); - set_page_links(page, zone, nid, pfn); - mminit_verify_page_links(page, zone, nid, pfn); - init_page_count(page); - page_mapcount_reset(page); - page_cpupid_reset_last(page); - SetPageReserved(page); + /* * Mark the block movable so that blocks are reserved for * movable at startup. This will force kernel allocations * to reserve their blocks rather than leaking throughout * the address space during boot when many long-lived - * kernel allocations are made. Later some blocks near - * the start are marked MIGRATE_RESERVE by - * setup_zone_migrate_reserve() + * kernel allocations are made. * * bitmap is created for zone's valid pfn range. but memmap * can be created for invalid pages (for alignment) * check here not to call set_pageblock_migratetype() against * pfn out of zone. */ - if ((z->zone_start_pfn <= pfn) - && (pfn < zone_end_pfn(z)) - && !(pfn & (pageblock_nr_pages - 1))) - set_pageblock_migratetype(page, MIGRATE_MOVABLE); + if (!(pfn & (pageblock_nr_pages - 1))) { + struct page *page = pfn_to_page(pfn); - INIT_LIST_HEAD(&page->lru); -#ifdef WANT_PAGE_VIRTUAL - /* The shift won't overflow because ZONE_NORMAL is below 4G. */ - if (!is_highmem_idx(zone)) - set_page_address(page, __va(pfn << PAGE_SHIFT)); -#endif + __init_single_page(page, pfn, zone, nid); + set_pageblock_migratetype(page, MIGRATE_MOVABLE); + } else { + __init_single_pfn(pfn, zone, nid); + } } } @@ -4516,8 +4807,7 @@ static __meminit void zone_pcp_init(struct zone *zone) int __meminit init_currently_empty_zone(struct zone *zone, unsigned long zone_start_pfn, - unsigned long size, - enum memmap_context context) + unsigned long size) { struct pglist_data *pgdat = zone->zone_pgdat; int ret; @@ -4541,57 +4831,30 @@ int __meminit init_currently_empty_zone(struct zone *zone, #ifdef CONFIG_HAVE_MEMBLOCK_NODE_MAP #ifndef CONFIG_HAVE_ARCH_EARLY_PFN_TO_NID + /* * Required by SPARSEMEM. Given a PFN, return what node the PFN is on. */ -int __meminit __early_pfn_to_nid(unsigned long pfn) +int __meminit __early_pfn_to_nid(unsigned long pfn, + struct mminit_pfnnid_cache *state) { unsigned long start_pfn, end_pfn; int nid; - /* - * NOTE: The following SMP-unsafe globals are only used early in boot - * when the kernel is running single-threaded. - */ - static unsigned long __meminitdata last_start_pfn, last_end_pfn; - static int __meminitdata last_nid; - if (last_start_pfn <= pfn && pfn < last_end_pfn) - return last_nid; + if (state->last_start <= pfn && pfn < state->last_end) + return state->last_nid; nid = memblock_search_pfn_nid(pfn, &start_pfn, &end_pfn); if (nid != -1) { - last_start_pfn = start_pfn; - last_end_pfn = end_pfn; - last_nid = nid; + state->last_start = start_pfn; + state->last_end = end_pfn; + state->last_nid = nid; } return nid; } #endif /* CONFIG_HAVE_ARCH_EARLY_PFN_TO_NID */ -int __meminit early_pfn_to_nid(unsigned long pfn) -{ - int nid; - - nid = __early_pfn_to_nid(pfn); - if (nid >= 0) - return nid; - /* just returns 0 */ - return 0; -} - -#ifdef CONFIG_NODES_SPAN_OTHER_NODES -bool __meminit early_pfn_in_nid(unsigned long pfn, int node) -{ - int nid; - - nid = __early_pfn_to_nid(pfn); - if (nid >= 0 && nid != node) - return false; - return true; -} -#endif - /** * free_bootmem_with_active_regions - Call memblock_free_early_nid for each active range * @nid: The node to free memory on. If MAX_NUMNODES, all nodes are freed. @@ -4731,6 +4994,10 @@ static unsigned long __meminit zone_spanned_pages_in_node(int nid, { unsigned long zone_start_pfn, zone_end_pfn; + /* When hotadd a new node from cpu_up(), the node should be empty */ + if (!node_start_pfn && !node_end_pfn) + return 0; + /* Get the start and end of the zone */ zone_start_pfn = arch_zone_lowest_possible_pfn[zone_type]; zone_end_pfn = arch_zone_highest_possible_pfn[zone_type]; @@ -4794,6 +5061,10 @@ static unsigned long __meminit zone_absent_pages_in_node(int nid, unsigned long zone_high = arch_zone_highest_possible_pfn[zone_type]; unsigned long zone_start_pfn, zone_end_pfn; + /* When hotadd a new node from cpu_up(), the node should be empty */ + if (!node_start_pfn && !node_end_pfn) + return 0; + zone_start_pfn = clamp(node_start_pfn, zone_low, zone_high); zone_end_pfn = clamp(node_end_pfn, zone_low, zone_high); @@ -4833,22 +5104,28 @@ static void __meminit calculate_node_totalpages(struct pglist_data *pgdat, unsigned long *zones_size, unsigned long *zholes_size) { - unsigned long realtotalpages, totalpages = 0; + unsigned long realtotalpages = 0, totalpages = 0; enum zone_type i; - for (i = 0; i < MAX_NR_ZONES; i++) - totalpages += zone_spanned_pages_in_node(pgdat->node_id, i, - node_start_pfn, - node_end_pfn, - zones_size); - pgdat->node_spanned_pages = totalpages; - - realtotalpages = totalpages; - for (i = 0; i < MAX_NR_ZONES; i++) - realtotalpages -= - zone_absent_pages_in_node(pgdat->node_id, i, + for (i = 0; i < MAX_NR_ZONES; i++) { + struct zone *zone = pgdat->node_zones + i; + unsigned long size, real_size; + + size = zone_spanned_pages_in_node(pgdat->node_id, i, + node_start_pfn, + node_end_pfn, + zones_size); + real_size = size - zone_absent_pages_in_node(pgdat->node_id, i, node_start_pfn, node_end_pfn, zholes_size); + zone->spanned_pages = size; + zone->present_pages = real_size; + + totalpages += size; + realtotalpages += real_size; + } + + pgdat->node_spanned_pages = totalpages; pgdat->node_present_pages = realtotalpages; printk(KERN_DEBUG "On node %d totalpages: %lu\n", pgdat->node_id, realtotalpages); @@ -4957,9 +5234,7 @@ static unsigned long __paginginit calc_memmap_size(unsigned long spanned_pages, * * NOTE: pgdat should get zeroed by caller. */ -static void __paginginit free_area_init_core(struct pglist_data *pgdat, - unsigned long node_start_pfn, unsigned long node_end_pfn, - unsigned long *zones_size, unsigned long *zholes_size) +static void __paginginit free_area_init_core(struct pglist_data *pgdat) { enum zone_type j; int nid = pgdat->node_id; @@ -4980,12 +5255,8 @@ static void __paginginit free_area_init_core(struct pglist_data *pgdat, struct zone *zone = pgdat->node_zones + j; unsigned long size, realsize, freesize, memmap_pages; - size = zone_spanned_pages_in_node(nid, j, node_start_pfn, - node_end_pfn, zones_size); - realsize = freesize = size - zone_absent_pages_in_node(nid, j, - node_start_pfn, - node_end_pfn, - zholes_size); + size = zone->spanned_pages; + realsize = freesize = zone->present_pages; /* * Adjust freesize so that it accounts for how much memory @@ -5020,8 +5291,6 @@ static void __paginginit free_area_init_core(struct pglist_data *pgdat, nr_kernel_pages -= memmap_pages; nr_all_pages += freesize; - zone->spanned_pages = size; - zone->present_pages = realsize; /* * Set an approximate value for lowmem here, it will be adjusted * when the bootmem allocator frees pages into the buddy system. @@ -5050,8 +5319,7 @@ static void __paginginit free_area_init_core(struct pglist_data *pgdat, set_pageblock_order(); setup_usemap(pgdat, zone, zone_start_pfn, size); - ret = init_currently_empty_zone(zone, zone_start_pfn, - size, MEMMAP_EARLY); + ret = init_currently_empty_zone(zone, zone_start_pfn, size); BUG_ON(ret); memmap_init(size, nid, j, zone_start_pfn); zone_start_pfn += size; @@ -5060,14 +5328,19 @@ static void __paginginit free_area_init_core(struct pglist_data *pgdat, static void __init_refok alloc_node_mem_map(struct pglist_data *pgdat) { + unsigned long __maybe_unused start = 0; + unsigned long __maybe_unused offset = 0; + /* Skip empty nodes */ if (!pgdat->node_spanned_pages) return; #ifdef CONFIG_FLAT_NODE_MEM_MAP + start = pgdat->node_start_pfn & ~(MAX_ORDER_NR_PAGES - 1); + offset = pgdat->node_start_pfn - start; /* ia64 gets its own node_mem_map, before this, without bootmem */ if (!pgdat->node_mem_map) { - unsigned long size, start, end; + unsigned long size, end; struct page *map; /* @@ -5075,7 +5348,6 @@ static void __init_refok alloc_node_mem_map(struct pglist_data *pgdat) * aligned but the node_mem_map endpoints must be in order * for the buddy allocator to function correctly. */ - start = pgdat->node_start_pfn & ~(MAX_ORDER_NR_PAGES - 1); end = pgdat_end_pfn(pgdat); end = ALIGN(end, MAX_ORDER_NR_PAGES); size = (end - start) * sizeof(struct page); @@ -5083,7 +5355,7 @@ static void __init_refok alloc_node_mem_map(struct pglist_data *pgdat) if (!map) map = memblock_virt_alloc_node_nopanic(size, pgdat->node_id); - pgdat->node_mem_map = map + (pgdat->node_start_pfn - start); + pgdat->node_mem_map = map + offset; } #ifndef CONFIG_NEED_MULTIPLE_NODES /* @@ -5091,9 +5363,9 @@ static void __init_refok alloc_node_mem_map(struct pglist_data *pgdat) */ if (pgdat == NODE_DATA(0)) { mem_map = NODE_DATA(0)->node_mem_map; -#ifdef CONFIG_HAVE_MEMBLOCK_NODE_MAP +#if defined(CONFIG_HAVE_MEMBLOCK_NODE_MAP) || defined(CONFIG_FLATMEM) if (page_to_pfn(mem_map) != pgdat->node_start_pfn) - mem_map -= (pgdat->node_start_pfn - ARCH_PFN_OFFSET); + mem_map -= offset; #endif /* CONFIG_HAVE_MEMBLOCK_NODE_MAP */ } #endif @@ -5110,12 +5382,14 @@ void __paginginit free_area_init_node(int nid, unsigned long *zones_size, /* pg_data_t should be reset to zero when it's allocated */ WARN_ON(pgdat->nr_zones || pgdat->classzone_idx); + reset_deferred_meminit(pgdat); pgdat->node_id = nid; pgdat->node_start_pfn = node_start_pfn; #ifdef CONFIG_HAVE_MEMBLOCK_NODE_MAP get_pfn_range_for_nid(nid, &start_pfn, &end_pfn); pr_info("Initmem setup node %d [mem %#018Lx-%#018Lx]\n", nid, - (u64)start_pfn << PAGE_SHIFT, ((u64)end_pfn << PAGE_SHIFT) - 1); + (u64)start_pfn << PAGE_SHIFT, + end_pfn ? ((u64)end_pfn << PAGE_SHIFT) - 1 : 0); #endif calculate_node_totalpages(pgdat, start_pfn, end_pfn, zones_size, zholes_size); @@ -5127,8 +5401,7 @@ void __paginginit free_area_init_node(int nid, unsigned long *zones_size, (unsigned long)pgdat->node_mem_map); #endif - free_area_init_core(pgdat, start_pfn, end_pfn, - zones_size, zholes_size); + free_area_init_core(pgdat); } #ifdef CONFIG_HAVE_MEMBLOCK_NODE_MAP @@ -5139,11 +5412,9 @@ void __paginginit free_area_init_node(int nid, unsigned long *zones_size, */ void __init setup_nr_node_ids(void) { - unsigned int node; - unsigned int highest = 0; + unsigned int highest; - for_each_node_mask(node, node_possible_map) - highest = node; + highest = find_last_bit(node_possible_map.bits, MAX_NUMNODES); nr_node_ids = highest + 1; } #endif @@ -5306,13 +5577,17 @@ static void __init find_zone_movable_pfns_for_nodes(void) */ required_movablecore = roundup(required_movablecore, MAX_ORDER_NR_PAGES); + required_movablecore = min(totalpages, required_movablecore); corepages = totalpages - required_movablecore; required_kernelcore = max(required_kernelcore, corepages); } - /* If kernelcore was not specified, there is no ZONE_MOVABLE */ - if (!required_kernelcore) + /* + * If kernelcore was not specified or kernelcore size is larger + * than totalpages, there is no ZONE_MOVABLE. + */ + if (!required_kernelcore || required_kernelcore >= totalpages) goto out; /* usable_startpfn is the lowest possible pfn ZONE_MOVABLE can be at */ @@ -5664,7 +5939,7 @@ void __init mem_init_print_info(const char *str) * set_dma_reserve - set the specified number of pages reserved in the first zone * @new_dma_reserve: The number of pages to mark reserved * - * The per-cpu batchsize and zone watermarks are determined by present_pages. + * The per-cpu batchsize and zone watermarks are determined by managed_pages. * In the DMA zone, a significant percentage may be consumed by kernel image * and other unfreeable allocations which can skew the watermarks badly. This * function may optionally be used to account for unfreeable pages in the @@ -5718,7 +5993,7 @@ void __init page_alloc_init(void) } /* - * calculate_totalreserve_pages - called when sysctl_lower_zone_reserve_ratio + * calculate_totalreserve_pages - called when sysctl_lowmem_reserve_ratio * or min_free_kbytes changes. */ static void calculate_totalreserve_pages(void) @@ -5762,7 +6037,7 @@ static void calculate_totalreserve_pages(void) /* * setup_per_zone_lowmem_reserve - called whenever - * sysctl_lower_zone_reserve_ratio changes. Ensures that each zone + * sysctl_lowmem_reserve_ratio changes. Ensures that each zone * has a correct pages reserved value, so an adequate number of * pages are left in the zone after a successful __alloc_pages(). */ @@ -5848,7 +6123,6 @@ static void __setup_per_zone_wmarks(void) high_wmark_pages(zone) - low_wmark_pages(zone) - atomic_long_read(&zone->vm_stat[NR_ALLOC_BATCH])); - setup_zone_migrate_reserve(zone); spin_unlock_irqrestore(&zone->lock, flags); } @@ -6078,9 +6352,9 @@ out: return ret; } +#ifdef CONFIG_NUMA int hashdist = HASHDIST_DEFAULT; -#ifdef CONFIG_NUMA static int __init set_hashdist(char *str) { if (!str) @@ -6470,7 +6744,8 @@ int alloc_contig_range(unsigned long start, unsigned long end, unsigned migratetype) { unsigned long outer_start, outer_end; - int ret = 0, order; + unsigned int order; + int ret = 0; struct compact_control cc = { .nr_migratepages = 0, |