diff options
Diffstat (limited to 'mm/page_alloc.c')
| -rw-r--r-- | mm/page_alloc.c | 838 |
1 files changed, 538 insertions, 300 deletions
diff --git a/mm/page_alloc.c b/mm/page_alloc.c index 46285d28e43b..dbd0d5cbbcbb 100644 --- a/mm/page_alloc.c +++ b/mm/page_alloc.c @@ -1,3 +1,4 @@ +// SPDX-License-Identifier: GPL-2.0-only /* * linux/mm/page_alloc.c * @@ -43,12 +44,12 @@ #include <linux/mempolicy.h> #include <linux/memremap.h> #include <linux/stop_machine.h> +#include <linux/random.h> #include <linux/sort.h> #include <linux/pfn.h> #include <linux/backing-dev.h> #include <linux/fault-inject.h> #include <linux/page-isolation.h> -#include <linux/page_ext.h> #include <linux/debugobjects.h> #include <linux/kmemleak.h> #include <linux/compaction.h> @@ -72,6 +73,7 @@ #include <asm/tlbflush.h> #include <asm/div64.h> #include "internal.h" +#include "shuffle.h" /* prevent >1 _updater_ of zone percpu pageset ->high and ->batch fields */ static DEFINE_MUTEX(pcp_batch_high_lock); @@ -133,6 +135,55 @@ unsigned long totalcma_pages __read_mostly; int percpu_pagelist_fraction; gfp_t gfp_allowed_mask __read_mostly = GFP_BOOT_MASK; +#ifdef CONFIG_INIT_ON_ALLOC_DEFAULT_ON +DEFINE_STATIC_KEY_TRUE(init_on_alloc); +#else +DEFINE_STATIC_KEY_FALSE(init_on_alloc); +#endif +EXPORT_SYMBOL(init_on_alloc); + +#ifdef CONFIG_INIT_ON_FREE_DEFAULT_ON +DEFINE_STATIC_KEY_TRUE(init_on_free); +#else +DEFINE_STATIC_KEY_FALSE(init_on_free); +#endif +EXPORT_SYMBOL(init_on_free); + +static int __init early_init_on_alloc(char *buf) +{ + int ret; + bool bool_result; + + if (!buf) + return -EINVAL; + ret = kstrtobool(buf, &bool_result); + if (bool_result && page_poisoning_enabled()) + pr_info("mem auto-init: CONFIG_PAGE_POISONING is on, will take precedence over init_on_alloc\n"); + if (bool_result) + static_branch_enable(&init_on_alloc); + else + static_branch_disable(&init_on_alloc); + return ret; +} +early_param("init_on_alloc", early_init_on_alloc); + +static int __init early_init_on_free(char *buf) +{ + int ret; + bool bool_result; + + if (!buf) + return -EINVAL; + ret = kstrtobool(buf, &bool_result); + if (bool_result && page_poisoning_enabled()) + pr_info("mem auto-init: CONFIG_PAGE_POISONING is on, will take precedence over init_on_free\n"); + if (bool_result) + static_branch_enable(&init_on_free); + else + static_branch_disable(&init_on_free); + return ret; +} +early_param("init_on_free", early_init_on_free); /* * A cached value of the page's pageblock's migratetype, used when the page is @@ -221,8 +272,6 @@ int sysctl_lowmem_reserve_ratio[MAX_NR_ZONES] = { [ZONE_MOVABLE] = 0, }; -EXPORT_SYMBOL(totalram_pages); - static char * const zone_names[MAX_NR_ZONES] = { #ifdef CONFIG_ZONE_DMA "DMA", @@ -266,7 +315,20 @@ compound_page_dtor * const compound_page_dtors[] = { int min_free_kbytes = 1024; int user_min_free_kbytes = -1; +#ifdef CONFIG_DISCONTIGMEM +/* + * DiscontigMem defines memory ranges as separate pg_data_t even if the ranges + * are not on separate NUMA nodes. Functionally this works but with + * watermark_boost_factor, it can reclaim prematurely as the ranges can be + * quite small. By default, do not boost watermarks on discontigmem as in + * many cases very high-order allocations like THP are likely to be + * unsupported and the premature reclaim offsets the advantage of long-term + * fragmentation avoidance. + */ +int watermark_boost_factor __read_mostly; +#else int watermark_boost_factor __read_mostly = 15000; +#endif int watermark_scale_factor = 10; static unsigned long nr_kernel_pages __initdata; @@ -289,8 +351,8 @@ EXPORT_SYMBOL(movable_zone); #endif /* CONFIG_HAVE_MEMBLOCK_NODE_MAP */ #if MAX_NUMNODES > 1 -int nr_node_ids __read_mostly = MAX_NUMNODES; -int nr_online_nodes __read_mostly = 1; +unsigned int nr_node_ids __read_mostly = MAX_NUMNODES; +unsigned int nr_online_nodes __read_mostly = 1; EXPORT_SYMBOL(nr_node_ids); EXPORT_SYMBOL(nr_online_nodes); #endif @@ -630,30 +692,29 @@ void prep_compound_page(struct page *page, unsigned int order) #ifdef CONFIG_DEBUG_PAGEALLOC unsigned int _debug_guardpage_minorder; -bool _debug_pagealloc_enabled __read_mostly - = IS_ENABLED(CONFIG_DEBUG_PAGEALLOC_ENABLE_DEFAULT); + +#ifdef CONFIG_DEBUG_PAGEALLOC_ENABLE_DEFAULT +DEFINE_STATIC_KEY_TRUE(_debug_pagealloc_enabled); +#else +DEFINE_STATIC_KEY_FALSE(_debug_pagealloc_enabled); +#endif EXPORT_SYMBOL(_debug_pagealloc_enabled); -bool _debug_guardpage_enabled __read_mostly; + +DEFINE_STATIC_KEY_FALSE(_debug_guardpage_enabled); static int __init early_debug_pagealloc(char *buf) { - if (!buf) - return -EINVAL; - return kstrtobool(buf, &_debug_pagealloc_enabled); -} -early_param("debug_pagealloc", early_debug_pagealloc); + bool enable = false; -static bool need_debug_guardpage(void) -{ - /* If we don't use debug_pagealloc, we don't need guard page */ - if (!debug_pagealloc_enabled()) - return false; + if (kstrtobool(buf, &enable)) + return -EINVAL; - if (!debug_guardpage_minorder()) - return false; + if (enable) + static_branch_enable(&_debug_pagealloc_enabled); - return true; + return 0; } +early_param("debug_pagealloc", early_debug_pagealloc); static void init_debug_guardpage(void) { @@ -663,14 +724,9 @@ static void init_debug_guardpage(void) if (!debug_guardpage_minorder()) return; - _debug_guardpage_enabled = true; + static_branch_enable(&_debug_guardpage_enabled); } -struct page_ext_operations debug_guardpage_ops = { - .need = need_debug_guardpage, - .init = init_debug_guardpage, -}; - static int __init debug_guardpage_minorder_setup(char *buf) { unsigned long res; @@ -688,20 +744,13 @@ early_param("debug_guardpage_minorder", debug_guardpage_minorder_setup); static inline bool set_page_guard(struct zone *zone, struct page *page, unsigned int order, int migratetype) { - struct page_ext *page_ext; - if (!debug_guardpage_enabled()) return false; if (order >= debug_guardpage_minorder()) return false; - page_ext = lookup_page_ext(page); - if (unlikely(!page_ext)) - return false; - - __set_bit(PAGE_EXT_DEBUG_GUARD, &page_ext->flags); - + __SetPageGuard(page); INIT_LIST_HEAD(&page->lru); set_page_private(page, order); /* Guard pages are not available for any usage */ @@ -713,23 +762,16 @@ static inline bool set_page_guard(struct zone *zone, struct page *page, static inline void clear_page_guard(struct zone *zone, struct page *page, unsigned int order, int migratetype) { - struct page_ext *page_ext; - if (!debug_guardpage_enabled()) return; - page_ext = lookup_page_ext(page); - if (unlikely(!page_ext)) - return; - - __clear_bit(PAGE_EXT_DEBUG_GUARD, &page_ext->flags); + __ClearPageGuard(page); set_page_private(page, 0); if (!is_migrate_isolate(migratetype)) __mod_zone_freepage_state(zone, (1 << order), migratetype); } #else -struct page_ext_operations debug_guardpage_ops; static inline bool set_page_guard(struct zone *zone, struct page *page, unsigned int order, int migratetype) { return false; } static inline void clear_page_guard(struct zone *zone, struct page *page, @@ -742,12 +784,6 @@ static inline void set_page_order(struct page *page, unsigned int order) __SetPageBuddy(page); } -static inline void rmv_page_order(struct page *page) -{ - __ClearPageBuddy(page); - set_page_private(page, 0); -} - /* * This function checks whether a page is free && is the buddy * we can coalesce a page and its buddy if @@ -789,6 +825,57 @@ static inline int page_is_buddy(struct page *page, struct page *buddy, return 0; } +#ifdef CONFIG_COMPACTION +static inline struct capture_control *task_capc(struct zone *zone) +{ + struct capture_control *capc = current->capture_control; + + return capc && + !(current->flags & PF_KTHREAD) && + !capc->page && + capc->cc->zone == zone && + capc->cc->direct_compaction ? capc : NULL; +} + +static inline bool +compaction_capture(struct capture_control *capc, struct page *page, + int order, int migratetype) +{ + if (!capc || order != capc->cc->order) + return false; + + /* Do not accidentally pollute CMA or isolated regions*/ + if (is_migrate_cma(migratetype) || + is_migrate_isolate(migratetype)) + return false; + + /* + * Do not let lower order allocations polluate a movable pageblock. + * This might let an unmovable request use a reclaimable pageblock + * and vice-versa but no more than normal fallback logic which can + * have trouble finding a high-order free page. + */ + if (order < pageblock_order && migratetype == MIGRATE_MOVABLE) + return false; + + capc->page = page; + return true; +} + +#else +static inline struct capture_control *task_capc(struct zone *zone) +{ + return NULL; +} + +static inline bool +compaction_capture(struct capture_control *capc, struct page *page, + int order, int migratetype) +{ + return false; +} +#endif /* CONFIG_COMPACTION */ + /* * Freeing function for a buddy system allocator. * @@ -822,6 +909,7 @@ static inline void __free_one_page(struct page *page, unsigned long uninitialized_var(buddy_pfn); struct page *buddy; unsigned int max_order; + struct capture_control *capc = task_capc(zone); max_order = min_t(unsigned int, MAX_ORDER, pageblock_order + 1); @@ -837,6 +925,11 @@ static inline void __free_one_page(struct page *page, continue_merging: while (order < max_order - 1) { + if (compaction_capture(capc, page, order, migratetype)) { + __mod_zone_freepage_state(zone, -(1 << order), + migratetype); + return; + } buddy_pfn = __find_buddy_pfn(pfn, order); buddy = page + (buddy_pfn - pfn); @@ -848,13 +941,10 @@ continue_merging: * Our buddy is free or it is CONFIG_DEBUG_PAGEALLOC guard page, * merge with it and move up one order. */ - if (page_is_guard(buddy)) { + if (page_is_guard(buddy)) clear_page_guard(zone, buddy, order, migratetype); - } else { - list_del(&buddy->lru); - zone->free_area[order].nr_free--; - rmv_page_order(buddy); - } + else + del_page_from_free_area(buddy, &zone->free_area[order]); combined_pfn = buddy_pfn & pfn; page = page + (combined_pfn - pfn); pfn = combined_pfn; @@ -896,7 +986,8 @@ done_merging: * so it's less likely to be used soon and more likely to be merged * as a higher order page */ - if ((order < MAX_ORDER-2) && pfn_valid_within(buddy_pfn)) { + if ((order < MAX_ORDER-2) && pfn_valid_within(buddy_pfn) + && !is_shuffle_order(order)) { struct page *higher_page, *higher_buddy; combined_pfn = buddy_pfn & pfn; higher_page = page + (combined_pfn - pfn); @@ -904,15 +995,18 @@ done_merging: higher_buddy = higher_page + (buddy_pfn - combined_pfn); if (pfn_valid_within(buddy_pfn) && page_is_buddy(higher_page, higher_buddy, order + 1)) { - list_add_tail(&page->lru, - &zone->free_area[order].free_list[migratetype]); - goto out; + add_to_free_area_tail(page, &zone->free_area[order], + migratetype); + return; } } - list_add(&page->lru, &zone->free_area[order].free_list[migratetype]); -out: - zone->free_area[order].nr_free++; + if (is_shuffle_order(order)) + add_to_free_area_random(page, &zone->free_area[order], + migratetype); + else + add_to_free_area(page, &zone->free_area[order], migratetype); + } /* @@ -1022,6 +1116,14 @@ out: return ret; } +static void kernel_init_free_pages(struct page *page, int numpages) +{ + int i; + + for (i = 0; i < numpages; i++) + clear_highpage(page + i); +} + static __always_inline bool free_pages_prepare(struct page *page, unsigned int order, bool check_free) { @@ -1056,7 +1158,7 @@ static __always_inline bool free_pages_prepare(struct page *page, if (PageMappingFlags(page)) page->mapping = NULL; if (memcg_kmem_enabled() && PageKmemcg(page)) - memcg_kmem_uncharge(page, order); + __memcg_kmem_uncharge(page, order); if (check_free) bad += free_pages_check(page); if (bad) @@ -1073,27 +1175,49 @@ static __always_inline bool free_pages_prepare(struct page *page, PAGE_SIZE << order); } arch_free_page(page, order); + if (want_init_on_free()) + kernel_init_free_pages(page, 1 << order); + kernel_poison_pages(page, 1 << order, 0); - kernel_map_pages(page, 1 << order, 0); + if (debug_pagealloc_enabled()) + kernel_map_pages(page, 1 << order, 0); + kasan_free_nondeferred_pages(page, order); return true; } #ifdef CONFIG_DEBUG_VM -static inline bool free_pcp_prepare(struct page *page) +/* + * With DEBUG_VM enabled, order-0 pages are checked immediately when being freed + * to pcp lists. With debug_pagealloc also enabled, they are also rechecked when + * moved from pcp lists to free lists. + */ +static bool free_pcp_prepare(struct page *page) { return free_pages_prepare(page, 0, true); } -static inline bool bulkfree_pcp_prepare(struct page *page) +static bool bulkfree_pcp_prepare(struct page *page) { - return false; + if (debug_pagealloc_enabled()) + return free_pages_check(page); + else + return false; } #else +/* + * With DEBUG_VM disabled, order-0 pages being freed are checked only when + * moving from pcp lists to free list in order to reduce overhead. With + * debug_pagealloc enabled, they are checked also immediately when being freed + * to the pcp lists. + */ static bool free_pcp_prepare(struct page *page) { - return free_pages_prepare(page, 0, false); + if (debug_pagealloc_enabled()) + return free_pages_prepare(page, 0, true); + else + return free_pages_prepare(page, 0, false); } static bool bulkfree_pcp_prepare(struct page *page) @@ -1303,7 +1427,7 @@ static void __free_pages_ok(struct page *page, unsigned int order) local_irq_restore(flags); } -static void __init __free_pages_boot_core(struct page *page, unsigned int order) +void __free_pages_core(struct page *page, unsigned int order) { unsigned int nr_pages = 1 << order; struct page *p = page; @@ -1344,36 +1468,22 @@ int __meminit early_pfn_to_nid(unsigned long pfn) #endif #ifdef CONFIG_NODES_SPAN_OTHER_NODES -static inline bool __meminit __maybe_unused -meminit_pfn_in_nid(unsigned long pfn, int node, - struct mminit_pfnnid_cache *state) +/* 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) { int nid; - nid = __early_pfn_to_nid(pfn, state); + nid = __early_pfn_to_nid(pfn, &early_pfnnid_cache); 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 __maybe_unused -meminit_pfn_in_nid(unsigned long pfn, int node, - struct mminit_pfnnid_cache *state) -{ - return true; -} #endif @@ -1382,7 +1492,7 @@ void __init memblock_free_pages(struct page *page, unsigned long pfn, { if (early_page_uninitialised(pfn)) return; - return __free_pages_boot_core(page, order); + __free_pages_core(page, order); } /* @@ -1472,14 +1582,14 @@ static void __init deferred_free_range(unsigned long pfn, if (nr_pages == pageblock_nr_pages && (pfn & (pageblock_nr_pages - 1)) == 0) { set_pageblock_migratetype(page, MIGRATE_MOVABLE); - __free_pages_boot_core(page, pageblock_order); + __free_pages_core(page, pageblock_order); return; } for (i = 0; i < nr_pages; i++, page++, pfn++) { if ((pfn & (pageblock_nr_pages - 1)) == 0) set_pageblock_migratetype(page, MIGRATE_MOVABLE); - __free_pages_boot_core(page, 0); + __free_pages_core(page, 0); } } @@ -1502,21 +1612,13 @@ static inline void __init pgdat_init_report_one_done(void) * * Then, we check if a current large page is valid by only checking the validity * of the head pfn. - * - * Finally, meminit_pfn_in_nid is checked on systems where pfns can interleave - * within a node: a pfn is between start and end of a node, but does not belong - * to this memory node. */ -static inline bool __init -deferred_pfn_valid(int nid, unsigned long pfn, - struct mminit_pfnnid_cache *nid_init_state) +static inline bool __init deferred_pfn_valid(unsigned long pfn) { if (!pfn_valid_within(pfn)) return false; if (!(pfn & (pageblock_nr_pages - 1)) && !pfn_valid(pfn)) return false; - if (!meminit_pfn_in_nid(pfn, nid, nid_init_state)) - return false; return true; } @@ -1524,15 +1626,14 @@ deferred_pfn_valid(int nid, unsigned long pfn, * Free pages to buddy allocator. Try to free aligned pages in * pageblock_nr_pages sizes. */ -static void __init deferred_free_pages(int nid, int zid, unsigned long pfn, +static void __init deferred_free_pages(unsigned long pfn, unsigned long end_pfn) { - struct mminit_pfnnid_cache nid_init_state = { }; unsigned long nr_pgmask = pageblock_nr_pages - 1; unsigned long nr_free = 0; for (; pfn < end_pfn; pfn++) { - if (!deferred_pfn_valid(nid, pfn, &nid_init_state)) { + if (!deferred_pfn_valid(pfn)) { deferred_free_range(pfn - nr_free, nr_free); nr_free = 0; } else if (!(pfn & nr_pgmask)) { @@ -1552,17 +1653,18 @@ static void __init deferred_free_pages(int nid, int zid, unsigned long pfn, * by performing it only once every pageblock_nr_pages. * Return number of pages initialized. */ -static unsigned long __init deferred_init_pages(int nid, int zid, +static unsigned long __init deferred_init_pages(struct zone *zone, unsigned long pfn, unsigned long end_pfn) { - struct mminit_pfnnid_cache nid_init_state = { }; unsigned long nr_pgmask = pageblock_nr_pages - 1; + int nid = zone_to_nid(zone); unsigned long nr_pages = 0; + int zid = zone_idx(zone); struct page *page = NULL; for (; pfn < end_pfn; pfn++) { - if (!deferred_pfn_valid(nid, pfn, &nid_init_state)) { + if (!deferred_pfn_valid(pfn)) { page = NULL; continue; } else if (!page || !(pfn & nr_pgmask)) { @@ -1577,18 +1679,100 @@ static unsigned long __init deferred_init_pages(int nid, int zid, return (nr_pages); } +/* + * This function is meant to pre-load the iterator for the zone init. + * Specifically it walks through the ranges until we are caught up to the + * first_init_pfn value and exits there. If we never encounter the value we + * return false indicating there are no valid ranges left. + */ +static bool __init +deferred_init_mem_pfn_range_in_zone(u64 *i, struct zone *zone, + unsigned long *spfn, unsigned long *epfn, + unsigned long first_init_pfn) +{ + u64 j; + + /* + * Start out by walking through the ranges in this zone that have + * already been initialized. We don't need to do anything with them + * so we just need to flush them out of the system. + */ + for_each_free_mem_pfn_range_in_zone(j, zone, spfn, epfn) { + if (*epfn <= first_init_pfn) + continue; + if (*spfn < first_init_pfn) + *spfn = first_init_pfn; + *i = j; + return true; + } + + return false; +} + +/* + * Initialize and free pages. We do it in two loops: first we initialize + * struct page, then free to buddy allocator, because while we are + * freeing pages we can access pages that are ahead (computing buddy + * page in __free_one_page()). + * + * In order to try and keep some memory in the cache we have the loop + * broken along max page order boundaries. This way we will not cause + * any issues with the buddy page computation. + */ +static unsigned long __init +deferred_init_maxorder(u64 *i, struct zone *zone, unsigned long *start_pfn, + unsigned long *end_pfn) +{ + unsigned long mo_pfn = ALIGN(*start_pfn + 1, MAX_ORDER_NR_PAGES); + unsigned long spfn = *start_pfn, epfn = *end_pfn; + unsigned long nr_pages = 0; + u64 j = *i; + + /* First we loop through and initialize the page values */ + for_each_free_mem_pfn_range_in_zone_from(j, zone, start_pfn, end_pfn) { + unsigned long t; + + if (mo_pfn <= *start_pfn) + break; + + t = min(mo_pfn, *end_pfn); + nr_pages += deferred_init_pages(zone, *start_pfn, t); + + if (mo_pfn < *end_pfn) { + *start_pfn = mo_pfn; + break; + } + } + + /* Reset values and now loop through freeing pages as needed */ + swap(j, *i); + + for_each_free_mem_pfn_range_in_zone_from(j, zone, &spfn, &epfn) { + unsigned long t; + + if (mo_pfn <= spfn) + break; + + t = min(mo_pfn, epfn); + deferred_free_pages(spfn, t); + + if (mo_pfn <= epfn) + break; + } + + return nr_pages; +} + /* Initialise remaining memory on a node */ static int __init deferred_init_memmap(void *data) { pg_data_t *pgdat = data; - int nid = pgdat->node_id; + const struct cpumask *cpumask = cpumask_of_node(pgdat->node_id); + unsigned long spfn = 0, epfn = 0, nr_pages = 0; + unsigned long first_init_pfn, flags; unsigned long start = jiffies; - unsigned long nr_pages = 0; - unsigned long spfn, epfn, first_init_pfn, flags; - phys_addr_t spa, epa; - int zid; struct zone *zone; - const struct cpumask *cpumask = cpumask_of_node(pgdat->node_id); + int zid; u64 i; /* Bind memory initialisation thread to a local node if possible */ @@ -1614,31 +1798,27 @@ static int __init deferred_init_memmap(void *data) if (first_init_pfn < zone_end_pfn(zone)) break; } - first_init_pfn = max(zone->zone_start_pfn, first_init_pfn); + + /* If the zone is empty somebody else may have cleared out the zone */ + if (!deferred_init_mem_pfn_range_in_zone(&i, zone, &spfn, &epfn, + first_init_pfn)) + goto zone_empty; /* - * Initialize and free pages. We do it in two loops: first we initialize - * struct page, than free to buddy allocator, because while we are - * freeing pages we can access pages that are ahead (computing buddy - * page in __free_one_page()). + * Initialize and free pages in MAX_ORDER sized increments so + * that we can avoid introducing any issues with the buddy + * allocator. */ - for_each_free_mem_range(i, nid, MEMBLOCK_NONE, &spa, &epa, NULL) { - spfn = max_t(unsigned long, first_init_pfn, PFN_UP(spa)); - epfn = min_t(unsigned long, zone_end_pfn(zone), PFN_DOWN(epa)); - nr_pages += deferred_init_pages(nid, zid, spfn, epfn); - } - for_each_free_mem_range(i, nid, MEMBLOCK_NONE, &spa, &epa, NULL) { - spfn = max_t(unsigned long, first_init_pfn, PFN_UP(spa)); - epfn = min_t(unsigned long, zone_end_pfn(zone), PFN_DOWN(epa)); - deferred_free_pages(nid, zid, spfn, epfn); - } + while (spfn < epfn) + nr_pages += deferred_init_maxorder(&i, zone, &spfn, &epfn); +zone_empty: pgdat_resize_unlock(pgdat, &flags); /* 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)); + pr_info("node %d initialised, %lu pages in %ums\n", + pgdat->node_id, nr_pages, jiffies_to_msecs(jiffies - start)); pgdat_init_report_one_done(); return 0; @@ -1662,14 +1842,11 @@ static int __init deferred_init_memmap(void *data) static noinline bool __init deferred_grow_zone(struct zone *zone, unsigned int order) { - int zid = zone_idx(zone); - int nid = zone_to_nid(zone); - pg_data_t *pgdat = NODE_DATA(nid); unsigned long nr_pages_needed = ALIGN(1 << order, PAGES_PER_SECTION); - unsigned long nr_pages = 0; - unsigned long first_init_pfn, spfn, epfn, t, flags; + pg_data_t *pgdat = zone->zone_pgdat; unsigned long first_deferred_pfn = pgdat->first_deferred_pfn; - phys_addr_t spa, epa; + unsigned long spfn, epfn, flags; + unsigned long nr_pages = 0; u64 i; /* Only the last zone may have deferred pages */ @@ -1698,38 +1875,36 @@ deferred_grow_zone(struct zone *zone, unsigned int order) return true; } - first_init_pfn = max(zone->zone_start_pfn, first_deferred_pfn); - - if (first_init_pfn >= pgdat_end_pfn(pgdat)) { + /* If the zone is empty somebody else may have cleared out the zone */ + if (!deferred_init_mem_pfn_range_in_zone(&i, zone, &spfn, &epfn, + first_deferred_pfn)) { + pgdat->first_deferred_pfn = ULONG_MAX; pgdat_resize_unlock(pgdat, &flags); - return false; + /* Retry only once. */ + return first_deferred_pfn != ULONG_MAX; } - for_each_free_mem_range(i, nid, MEMBLOCK_NONE, &spa, &epa, NULL) { - spfn = max_t(unsigned long, first_init_pfn, PFN_UP(spa)); - epfn = min_t(unsigned long, zone_end_pfn(zone), PFN_DOWN(epa)); + /* + * Initialize and free pages in MAX_ORDER sized increments so + * that we can avoid introducing any issues with the buddy + * allocator. + */ + while (spfn < epfn) { + /* update our first deferred PFN for this section */ + first_deferred_pfn = spfn; - while (spfn < epfn && nr_pages < nr_pages_needed) { - t = ALIGN(spfn + PAGES_PER_SECTION, PAGES_PER_SECTION); - first_deferred_pfn = min(t, epfn); - nr_pages += deferred_init_pages(nid, zid, spfn, - first_deferred_pfn); - spfn = first_deferred_pfn; - } + nr_pages += deferred_init_maxorder(&i, zone, &spfn, &epfn); + /* We should only stop along section boundaries */ + if ((first_deferred_pfn ^ spfn) < PAGES_PER_SECTION) + continue; + + /* If our quota has been met we can stop here */ if (nr_pages >= nr_pages_needed) break; } - for_each_free_mem_range(i, nid, MEMBLOCK_NONE, &spa, &epa, NULL) { - spfn = max_t(unsigned long, first_init_pfn, PFN_UP(spa)); - epfn = min_t(unsigned long, first_deferred_pfn, PFN_DOWN(epa)); - deferred_free_pages(nid, zid, spfn, epfn); - - if (first_deferred_pfn == epfn) - break; - } - pgdat->first_deferred_pfn = first_deferred_pfn; + pgdat->first_deferred_pfn = spfn; pgdat_resize_unlock(pgdat, &flags); return nr_pages > 0; @@ -1752,9 +1927,9 @@ _deferred_grow_zone(struct zone *zone, unsigned int order) void __init page_alloc_init_late(void) { struct zone *zone; + int nid; #ifdef CONFIG_DEFERRED_STRUCT_PAGE_INIT - int nid; /* There will be num_node_state(N_MEMORY) threads */ atomic_set(&pgdat_init_n_undone, num_node_state(N_MEMORY)); @@ -1774,13 +1949,19 @@ void __init page_alloc_init_late(void) /* Reinit limits that are based on free pages after the kernel is up */ files_maxfiles_init(); #endif -#ifdef CONFIG_ARCH_DISCARD_MEMBLOCK + /* Discard memblock private memory */ memblock_discard(); -#endif + + for_each_node_state(nid, N_MEMORY) + shuffle_free_memory(NODE_DATA(nid)); for_each_populated_zone(zone) set_zone_contiguous(zone); + +#ifdef CONFIG_DEBUG_PAGEALLOC + init_debug_guardpage(); +#endif } #ifdef CONFIG_CMA @@ -1849,8 +2030,7 @@ static inline void expand(struct zone *zone, struct page *page, if (set_page_guard(zone, &page[size], high, migratetype)) continue; - list_add(&page[size].lru, &area->free_list[migratetype]); - area->nr_free++; + add_to_free_area(&page[size], area, migratetype); set_page_order(&page[size], high); } } @@ -1865,7 +2045,7 @@ static void check_new_page_bad(struct page *page) if (unlikely(page->mapping != NULL)) bad_reason = "non-NULL mapping"; if (unlikely(page_ref_count(page) != 0)) - bad_reason = "nonzero _count"; + bad_reason = "nonzero _refcount"; if (unlikely(page->flags & __PG_HWPOISON)) { bad_reason = "HWPoisoned (hardware-corrupted)"; bad_flags = __PG_HWPOISON; @@ -1899,28 +2079,44 @@ static inline int check_new_page(struct page *page) static inline bool free_pages_prezeroed(void) { - return IS_ENABLED(CONFIG_PAGE_POISONING_ZERO) && - page_poisoning_enabled(); + return (IS_ENABLED(CONFIG_PAGE_POISONING_ZERO) && + page_poisoning_enabled()) || want_init_on_free(); } #ifdef CONFIG_DEBUG_VM -static bool check_pcp_refill(struct page *page) +/* + * With DEBUG_VM enabled, order-0 pages are checked for expected state when + * being allocated from pcp lists. With debug_pagealloc also enabled, they are + * also checked when pcp lists are refilled from the free lists. + */ +static inline bool check_pcp_refill(struct page *page) { - return false; + if (debug_pagealloc_enabled()) + return check_new_page(page); + else + return false; } -static bool check_new_pcp(struct page *page) +static inline bool check_new_pcp(struct page *page) { return check_new_page(page); } #else -static bool check_pcp_refill(struct page *page) +/* + * With DEBUG_VM disabled, free order-0 pages are checked for expected state + * when pcp lists are being refilled from the free lists. With debug_pagealloc + * enabled, they are also checked when being allocated from the pcp lists. + */ +static inline bool check_pcp_refill(struct page *page) { return check_new_page(page); } -static bool check_new_pcp(struct page *page) +static inline bool check_new_pcp(struct page *page) { - return false; + if (debug_pagealloc_enabled()) + return check_new_page(page); + else + return false; } #endif /* CONFIG_DEBUG_VM */ @@ -1944,22 +2140,20 @@ inline void post_alloc_hook(struct page *page, unsigned int order, set_page_refcounted(page); arch_alloc_page(page, order); - kernel_map_pages(page, 1 << order, 1); - kernel_poison_pages(page, 1 << order, 1); + if (debug_pagealloc_enabled()) + kernel_map_pages(page, 1 << order, 1); kasan_alloc_pages(page, order); + kernel_poison_pages(page, 1 << order, 1); set_page_owner(page, order, gfp_flags); } static void prep_new_page(struct page *page, unsigned int order, gfp_t gfp_flags, unsigned int alloc_flags) { - int i; - post_alloc_hook(page, order, gfp_flags); - if (!free_pages_prezeroed() && (gfp_flags & __GFP_ZERO)) - for (i = 0; i < (1 << order); i++) - clear_highpage(page + i); + if (!free_pages_prezeroed() && want_init_on_alloc(gfp_flags)) + kernel_init_free_pages(page, 1 << order); if (order && (gfp_flags & __GFP_COMP)) prep_compound_page(page, order); @@ -1991,13 +2185,10 @@ struct page *__rmqueue_smallest(struct zone *zone, unsigned int order, /* Find a page of the appropriate size in the preferred list */ for (current_order = order; current_order < MAX_ORDER; ++current_order) { area = &(zone->free_area[current_order]); - page = list_first_entry_or_null(&area->free_list[migratetype], - struct page, lru); + page = get_page_from_free_area(area, migratetype); if (!page) continue; - list_del(&page->lru); - rmv_page_order(page); - area->nr_free--; + del_page_from_free_area(page, area); expand(zone, page, order, current_order, area, migratetype); set_pcppage_migratetype(page, migratetype); return page; @@ -2083,8 +2274,7 @@ static int move_freepages(struct zone *zone, } order = page_order(page); - list_move(&page->lru, - &zone->free_area[order].free_list[migratetype]); + move_to_free_area(page, &zone->free_area[order], migratetype); page += 1 << order; pages_moved += 1 << order; } @@ -2170,6 +2360,18 @@ static inline void boost_watermark(struct zone *zone) max_boost = mult_frac(zone->_watermark[WMARK_HIGH], watermark_boost_factor, 10000); + + /* + * high watermark may be uninitialised if fragmentation occurs + * very early in boot so do not boost. We do not fall + * through and boost by pageblock_nr_pages as failing + * allocations that early means that reclaim is not going + * to help and it may even be impossible to reclaim the + * boosted watermark resulting in a hang. + */ + if (!max_boost) + return; + max_boost = max(pageblock_nr_pages, max_boost); zone->watermark_boost = min(zone->watermark_boost + pageblock_nr_pages, @@ -2260,7 +2462,7 @@ static void steal_suitable_fallback(struct zone *zone, struct page *page, single_page: area = &zone->free_area[current_order]; - list_move(&page->lru, &area->free_list[start_type]); + move_to_free_area(page, area, start_type); } /* @@ -2284,7 +2486,7 @@ int find_suitable_fallback(struct free_area *area, unsigned int order, if (fallback_mt == MIGRATE_TYPES) break; - if (list_empty(&area->free_list[fallback_mt])) + if (free_area_empty(area, fallback_mt)) continue; if (can_steal_fallback(order, migratetype)) @@ -2371,9 +2573,7 @@ static bool unreserve_highatomic_pageblock(const struct alloc_context *ac, for (order = 0; order < MAX_ORDER; order++) { struct free_area *area = &(zone->free_area[order]); - page = list_first_entry_or_null( - &area->free_list[MIGRATE_HIGHATOMIC], - struct page, lru); + page = get_page_from_free_area(area, MIGRATE_HIGHATOMIC); if (!page) continue; @@ -2496,8 +2696,7 @@ find_smallest: VM_BUG_ON(current_order == MAX_ORDER); do_steal: - page = list_first_entry(&area->free_list[fallback_mt], - struct page, lru); + page = get_page_from_free_area(area, fallback_mt); steal_suitable_fallback(zone, page, alloc_flags, start_migratetype, can_steal); @@ -2934,6 +3133,7 @@ EXPORT_SYMBOL_GPL(split_page); int __isolate_free_page(struct page *page, unsigned int order) { + struct free_area *area = &page_zone(page)->free_area[order]; unsigned long watermark; struct zone *zone; int mt; @@ -2950,7 +3150,7 @@ int __isolate_free_page(struct page *page, unsigned int order) * watermark, because we already know our high-order page * exists. */ - watermark = min_wmark_pages(zone) + (1UL << order); + watermark = zone->_watermark[WMARK_MIN] + (1UL << order); if (!zone_watermark_ok(zone, 0, watermark, 0, ALLOC_CMA)) return 0; @@ -2958,9 +3158,8 @@ int __isolate_free_page(struct page *page, unsigned int order) } /* Remove page from free list */ - list_del(&page->lru); - zone->free_area[order].nr_free--; - rmv_page_order(page); + + del_page_from_free_area(page, area); /* * Set the pageblock if the isolated page is at least half of a @@ -3035,9 +3234,8 @@ static struct page *__rmqueue_pcplist(struct zone *zone, int migratetype, /* Lock and remove page from the per-cpu list */ static struct page *rmqueue_pcplist(struct zone *preferred_zone, - struct zone *zone, unsigned int order, - gfp_t gfp_flags, int migratetype, - unsigned int alloc_flags) + struct zone *zone, gfp_t gfp_flags, + int migratetype, unsigned int alloc_flags) { struct per_cpu_pages *pcp; struct list_head *list; @@ -3049,7 +3247,7 @@ static struct page *rmqueue_pcplist(struct zone *preferred_zone, list = &pcp->lists[migratetype]; page = __rmqueue_pcplist(zone, migratetype, alloc_flags, pcp, list); if (page) { - __count_zid_vm_events(PGALLOC, page_zonenum(page), 1 << order); + __count_zid_vm_events(PGALLOC, page_zonenum(page), 1); zone_statistics(preferred_zone, zone); } local_irq_restore(flags); @@ -3069,8 +3267,8 @@ struct page *rmqueue(struct zone *preferred_zone, struct page *page; if (likely(order == 0)) { - page = rmqueue_pcplist(preferred_zone, zone, order, - gfp_flags, migratetype, alloc_flags); + page = rmqueue_pcplist(preferred_zone, zone, gfp_flags, + migratetype, alloc_flags); goto out; } @@ -3161,24 +3359,14 @@ static int __init fail_page_alloc_debugfs(void) dir = fault_create_debugfs_attr("fail_page_alloc", NULL, &fail_page_alloc.attr); - if (IS_ERR(dir)) - return PTR_ERR(dir); - - if (!debugfs_create_bool("ignore-gfp-wait", mode, dir, - &fail_page_alloc.ignore_gfp_reclaim)) - goto fail; - if (!debugfs_create_bool("ignore-gfp-highmem", mode, dir, - &fail_page_alloc.ignore_gfp_highmem)) - goto fail; - if (!debugfs_create_u32("min-order", mode, dir, - &fail_page_alloc.min_order)) - goto fail; - return 0; -fail: - debugfs_remove_recursive(dir); + debugfs_create_bool("ignore-gfp-wait", mode, dir, + &fail_page_alloc.ignore_gfp_reclaim); + debugfs_create_bool("ignore-gfp-highmem", mode, dir, + &fail_page_alloc.ignore_gfp_highmem); + debugfs_create_u32("min-order", mode, dir, &fail_page_alloc.min_order); - return -ENOMEM; + return 0; } late_initcall(fail_page_alloc_debugfs); @@ -3268,13 +3456,13 @@ bool __zone_watermark_ok(struct zone *z, unsigned int order, unsigned long mark, continue; for (mt = 0; mt < MIGRATE_PCPTYPES; mt++) { - if (!list_empty(&area->free_list[mt])) + if (!free_area_empty(area, mt)) return true; } #ifdef CONFIG_CMA if ((alloc_flags & ALLOC_CMA) && - !list_empty(&area->free_list[MIGRATE_CMA])) { + !free_area_empty(area, MIGRATE_CMA)) { return true; } #endif @@ -3360,8 +3548,11 @@ alloc_flags_nofragment(struct zone *zone, gfp_t gfp_mask) alloc_flags |= ALLOC_KSWAPD; #ifdef CONFIG_ZONE_DMA32 + if (!zone) + return alloc_flags; + if (zone_idx(zone) != ZONE_NORMAL) - goto out; + return alloc_flags; /* * If ZONE_DMA32 exists, assume it is the one after ZONE_NORMAL and @@ -3370,9 +3561,9 @@ alloc_flags_nofragment(struct zone *zone, gfp_t gfp_mask) */ BUILD_BUG_ON(ZONE_NORMAL - ZONE_DMA32 != 1); if (nr_online_nodes > 1 && !populated_zone(--zone)) - goto out; + return alloc_flags; -out: + alloc_flags |= ALLOC_NOFRAGMENT; #endif /* CONFIG_ZONE_DMA32 */ return alloc_flags; } @@ -3698,7 +3889,7 @@ __alloc_pages_direct_compact(gfp_t gfp_mask, unsigned int order, unsigned int alloc_flags, const struct alloc_context *ac, enum compact_priority prio, enum compact_result *compact_result) { - struct page *page; + struct page *page = NULL; unsigned long pflags; unsigned int noreclaim_flag; @@ -3709,21 +3900,24 @@ __alloc_pages_direct_compact(gfp_t gfp_mask, unsigned int order, noreclaim_flag = memalloc_noreclaim_save(); *compact_result = try_to_compact_pages(gfp_mask, order, alloc_flags, ac, - prio); + prio, &page); memalloc_noreclaim_restore(noreclaim_flag); psi_memstall_leave(&pflags); - if (*compact_result <= COMPACT_INACTIVE) - return NULL; - /* * At least in one zone compaction wasn't deferred or skipped, so let's * count a compaction stall */ count_vm_event(COMPACTSTALL); - page = get_page_from_freelist(gfp_mask, order, alloc_flags, ac); + /* Prep a captured page if available */ + if (page) + prep_new_page(page, order, gfp_mask, alloc_flags); + + /* Try get a page from the freelist if available */ + if (!page) + page = get_page_from_freelist(gfp_mask, order, alloc_flags, ac); if (page) { struct zone *zone = page_zone(page); @@ -4556,7 +4750,7 @@ __alloc_pages_nodemask(gfp_t gfp_mask, unsigned int order, int preferred_nid, out: if (memcg_kmem_enabled() && (gfp_mask & __GFP_ACCOUNT) && page && - unlikely(memcg_kmem_charge(page, gfp_mask, order) != 0)) { + unlikely(__memcg_kmem_charge(page, gfp_mask, order) != 0)) { __free_pages(page, order); page = NULL; } @@ -4675,11 +4869,11 @@ refill: /* Even if we own the page, we do not use atomic_set(). * This would break get_page_unless_zero() users. */ - page_ref_add(page, size); + page_ref_add(page, PAGE_FRAG_CACHE_MAX_SIZE); /* reset page count bias and offset to start of new frag */ nc->pfmemalloc = page_is_pfmemalloc(page); - nc->pagecnt_bias = size + 1; + nc->pagecnt_bias = PAGE_FRAG_CACHE_MAX_SIZE + 1; nc->offset = size; } @@ -4695,10 +4889,10 @@ refill: size = nc->size; #endif /* OK, page count is 0, we can safely set it */ - set_page_count(page, size + 1); + set_page_count(page, PAGE_FRAG_CACHE_MAX_SIZE + 1); /* reset page count bias and offset to start of new frag */ - nc->pagecnt_bias = size + 1; + nc->pagecnt_bias = PAGE_FRAG_CACHE_MAX_SIZE + 1; offset = size - fragsz; } @@ -4740,7 +4934,7 @@ static void *make_alloc_exact(unsigned long addr, unsigned int order, /** * alloc_pages_exact - allocate an exact number physically-contiguous pages. * @size: the number of bytes to allocate - * @gfp_mask: GFP flags for the allocation + * @gfp_mask: GFP flags for the allocation, must not contain __GFP_COMP * * This function is similar to alloc_pages(), except that it allocates the * minimum number of pages to satisfy the request. alloc_pages() can only @@ -4749,12 +4943,17 @@ static void *make_alloc_exact(unsigned long addr, unsigned int order, * This function is also limited by MAX_ORDER. * * Memory allocated by this function must be released by free_pages_exact(). + * + * Return: pointer to the allocated area or %NULL in case of error. */ void *alloc_pages_exact(size_t size, gfp_t gfp_mask) { unsigned int order = get_order(size); unsigned long addr; + if (WARN_ON_ONCE(gfp_mask & __GFP_COMP)) + gfp_mask &= ~__GFP_COMP; + addr = __get_free_pages(gfp_mask, order); return make_alloc_exact(addr, order, size); } @@ -4765,15 +4964,22 @@ EXPORT_SYMBOL(alloc_pages_exact); * pages on a node. * @nid: the preferred node ID where memory should be allocated * @size: the number of bytes to allocate - * @gfp_mask: GFP flags for the allocation + * @gfp_mask: GFP flags for the allocation, must not contain __GFP_COMP * * Like alloc_pages_exact(), but try to allocate on node nid first before falling * back. + * + * Return: pointer to the allocated area or %NULL in case of error. */ void * __meminit alloc_pages_exact_nid(int nid, size_t size, gfp_t gfp_mask) { unsigned int order = get_order(size); - struct page *p = alloc_pages_node(nid, gfp_mask, order); + struct page *p; + + if (WARN_ON_ONCE(gfp_mask & __GFP_COMP)) + gfp_mask &= ~__GFP_COMP; + + p = alloc_pages_node(nid, gfp_mask, order); if (!p) return NULL; return make_alloc_exact((unsigned long)page_address(p), order, size); @@ -4802,11 +5008,13 @@ EXPORT_SYMBOL(free_pages_exact); * nr_free_zone_pages - count number of pages beyond high watermark * @offset: The zone index of the highest zone * - * nr_free_zone_pages() counts the number of counts pages which are beyond the + * nr_free_zone_pages() counts the number of pages which are beyond the * high watermark within all zones at or below a given zone index. For each * zone, the number of pages is calculated as: * * nr_free_zone_pages = managed_pages - high_pages + * + * Return: number of pages beyond high watermark. */ static unsigned long nr_free_zone_pages(int offset) { @@ -4833,6 +5041,9 @@ static unsigned long nr_free_zone_pages(int offset) * * nr_free_buffer_pages() counts the number of pages which are beyond the high * watermark within ZONE_DMA and ZONE_NORMAL. + * + * Return: number of pages beyond high watermark within ZONE_DMA and + * ZONE_NORMAL. */ unsigned long nr_free_buffer_pages(void) { @@ -4845,6 +5056,8 @@ EXPORT_SYMBOL_GPL(nr_free_buffer_pages); * * nr_free_pagecache_pages() counts the number of pages which are beyond the * high watermark within all zones. + * + * Return: number of pages beyond high watermark within all zones. */ unsigned long nr_free_pagecache_pages(void) { @@ -5176,7 +5389,7 @@ void show_free_areas(unsigned int filter, nodemask_t *nodemask) types[order] = 0; for (type = 0; type < MIGRATE_TYPES; type++) { - if (!list_empty(&area->free_list[type])) + if (!free_area_empty(area, type)) types[order] |= 1 << type; } } @@ -5291,7 +5504,8 @@ static int node_load[MAX_NUMNODES]; * from each node to each node in the system), and should also prefer nodes * with no CPUs, since presumably they'll have very little allocation pressure * on them otherwise. - * It returns -1 if no node is found. + * + * Return: node id of the found node or %NUMA_NO_NODE if no node is found. */ static int find_next_best_node(int node, nodemask_t *used_node_mask) { @@ -5597,7 +5811,7 @@ void __ref build_all_zonelists(pg_data_t *pgdat) else page_group_by_mobility_disabled = 0; - pr_info("Built %i zonelists, mobility grouping %s. Total pages: %ld\n", + pr_info("Built %u zonelists, mobility grouping %s. Total pages: %ld\n", nr_online_nodes, page_group_by_mobility_disabled ? "off" : "on", vm_total_pages); @@ -6004,7 +6218,7 @@ int __meminit __early_pfn_to_nid(unsigned long pfn, return state->last_nid; nid = memblock_search_pfn_nid(pfn, &start_pfn, &end_pfn); - if (nid != -1) { + if (nid != NUMA_NO_NODE) { state->last_start = start_pfn; state->last_end = end_pfn; state->last_nid = nid; @@ -6154,13 +6368,15 @@ static unsigned long __init zone_spanned_pages_in_node(int nid, unsigned long *zone_end_pfn, unsigned long *ignored) { + unsigned long zone_low = arch_zone_lowest_possible_pfn[zone_type]; + unsigned long zone_high = arch_zone_highest_possible_pfn[zone_type]; /* 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]; + *zone_start_pfn = clamp(node_start_pfn, zone_low, zone_high); + *zone_end_pfn = clamp(node_end_pfn, zone_low, zone_high); adjust_zone_range_for_zone_movable(nid, zone_type, node_start_pfn, node_end_pfn, zone_start_pfn, zone_end_pfn); @@ -6202,7 +6418,7 @@ unsigned long __init __absent_pages_in_range(int nid, * @start_pfn: The start PFN to start searching for holes * @end_pfn: The end PFN to stop searching for holes * - * It returns the number of pages frames in memory holes within a range. + * Return: the number of pages frames in memory holes within a range. */ unsigned long __init absent_pages_in_range(unsigned long start_pfn, unsigned long end_pfn) @@ -6364,10 +6580,14 @@ static void __ref setup_usemap(struct pglist_data *pgdat, { unsigned long usemapsize = usemap_size(zone_start_pfn, zonesize); zone->pageblock_flags = NULL; - if (usemapsize) + if (usemapsize) { zone->pageblock_flags = - memblock_alloc_node_nopanic(usemapsize, - pgdat->node_id); + memblock_alloc_node(usemapsize, SMP_CACHE_BYTES, + pgdat->node_id); + if (!zone->pageblock_flags) + panic("Failed to allocate %ld bytes for zone %s pageblock flags on node %d\n", + usemapsize, zone->name, pgdat->node_id); + } } #else static inline void setup_usemap(struct pglist_data *pgdat, struct zone *zone, @@ -6596,7 +6816,11 @@ static void __ref alloc_node_mem_map(struct pglist_data *pgdat) end = pgdat_end_pfn(pgdat); end = ALIGN(end, MAX_ORDER_NR_PAGES); size = (end - start) * sizeof(struct page); - map = memblock_alloc_node_nopanic(size, pgdat->node_id); + map = memblock_alloc_node(size, SMP_CACHE_BYTES, + pgdat->node_id); + if (!map) + panic("Failed to allocate %ld bytes for node %d memory map\n", + size, pgdat->node_id); pgdat->node_mem_map = map + offset; } pr_debug("%s: node %d, pgdat %08lx, node_mem_map %08lx\n", @@ -6752,14 +6976,14 @@ void __init setup_nr_node_ids(void) * model has fine enough granularity to avoid incorrect mapping for the * populated node map. * - * Returns the determined alignment in pfn's. 0 if there is no alignment + * Return: the determined alignment in pfn's. 0 if there is no alignment * requirement (single node). */ unsigned long __init node_map_pfn_alignment(void) { unsigned long accl_mask = 0, last_end = 0; unsigned long start, end, mask; - int last_nid = -1; + int last_nid = NUMA_NO_NODE; int i, nid; for_each_mem_pfn_range(i, MAX_NUMNODES, &start, &end, &nid) { @@ -6807,7 +7031,7 @@ static unsigned long __init find_min_pfn_for_node(int nid) /** * find_min_pfn_with_active_regions - Find the minimum PFN registered * - * It returns the minimum PFN based on information provided via + * Return: the minimum PFN based on information provided via * memblock_set_node(). */ unsigned long __init find_min_pfn_with_active_regions(void) @@ -7255,7 +7479,6 @@ unsigned long free_reserved_area(void *start, void *end, int poison, const char return pages; } -EXPORT_SYMBOL(free_reserved_area); #ifdef CONFIG_HIGHMEM void free_highmem_page(struct page *page) @@ -7368,10 +7591,28 @@ static int page_alloc_cpu_dead(unsigned int cpu) return 0; } +#ifdef CONFIG_NUMA +int hashdist = HASHDIST_DEFAULT; + +static int __init set_hashdist(char *str) +{ + if (!str) + return 0; + hashdist = simple_strtoul(str, &str, 0); + return 1; +} +__setup("hashdist=", set_hashdist); +#endif + void __init page_alloc_init(void) { int ret; +#ifdef CONFIG_NUMA + if (num_node_state(N_MEMORY) == 1) + hashdist = 0; +#endif + ret = cpuhp_setup_state_nocalls(CPUHP_PAGE_ALLOC_DEAD, "mm/page_alloc:dead", NULL, page_alloc_cpu_dead); @@ -7484,7 +7725,7 @@ static void __setup_per_zone_wmarks(void) * value here. * * The WMARK_HIGH-WMARK_LOW and (WMARK_LOW-WMARK_MIN) - * deltas control asynch page reclaim, and so should + * deltas control async page reclaim, and so should * not be capped for highmem. */ unsigned long min_pages; @@ -7756,19 +7997,6 @@ out: return ret; } -#ifdef CONFIG_NUMA -int hashdist = HASHDIST_DEFAULT; - -static int __init set_hashdist(char *str) -{ - if (!str) - return 0; - hashdist = simple_strtoul(str, &str, 0); - return 1; -} -__setup("hashdist=", set_hashdist); -#endif - #ifndef __HAVE_ARCH_RESERVED_KERNEL_PAGES /* * Returns the number of pages that arch has reserved but @@ -7815,6 +8043,7 @@ void *__init alloc_large_system_hash(const char *tablename, unsigned long log2qty, size; void *table = NULL; gfp_t gfp_flags; + bool virt; /* allow the kernel cmdline to have a say */ if (!numentries) { @@ -7871,34 +8100,34 @@ void *__init alloc_large_system_hash(const char *tablename, gfp_flags = (flags & HASH_ZERO) ? GFP_ATOMIC | __GFP_ZERO : GFP_ATOMIC; do { + virt = false; size = bucketsize << log2qty; if (flags & HASH_EARLY) { if (flags & HASH_ZERO) - table = memblock_alloc_nopanic(size, - SMP_CACHE_BYTES); + table = memblock_alloc(size, SMP_CACHE_BYTES); else table = memblock_alloc_raw(size, SMP_CACHE_BYTES); - } else if (hashdist) { + } else if (get_order(size) >= MAX_ORDER || hashdist) { table = __vmalloc(size, gfp_flags, PAGE_KERNEL); + virt = true; } else { /* * If bucketsize is not a power-of-two, we may free * some pages at the end of hash table which * alloc_pages_exact() automatically does */ - if (get_order(size) < MAX_ORDER) { - table = alloc_pages_exact(size, gfp_flags); - kmemleak_alloc(table, size, 1, gfp_flags); - } + table = alloc_pages_exact(size, gfp_flags); + kmemleak_alloc(table, size, 1, gfp_flags); } } while (!table && size > PAGE_SIZE && --log2qty); if (!table) panic("Failed to allocate %s hash table\n", tablename); - pr_info("%s hash table entries: %ld (order: %d, %lu bytes)\n", - tablename, 1UL << log2qty, ilog2(size) - PAGE_SHIFT, size); + pr_info("%s hash table entries: %ld (order: %d, %lu bytes, %s)\n", + tablename, 1UL << log2qty, ilog2(size) - PAGE_SHIFT, size, + virt ? "vmalloc" : "linear"); if (_hash_shift) *_hash_shift = log2qty; @@ -7920,7 +8149,10 @@ void *__init alloc_large_system_hash(const char *tablename, bool has_unmovable_pages(struct zone *zone, struct page *page, int count, int migratetype, int flags) { - unsigned long pfn, iter, found; + unsigned long found; + unsigned long iter = 0; + unsigned long pfn = page_to_pfn(page); + const char *reason = "unmovable page"; /* * TODO we could make this much more efficient by not checking every @@ -7930,17 +8162,20 @@ bool has_unmovable_pages(struct zone *zone, struct page *page, int count, * can still lead to having bootmem allocations in zone_movable. */ - /* - * CMA allocations (alloc_contig_range) really need to mark isolate - * CMA pageblocks even when they are not movable in fact so consider - * them movable here. - */ - if (is_migrate_cma(migratetype) && - is_migrate_cma(get_pageblock_migratetype(page))) - return false; + if (is_migrate_cma_page(page)) { + /* + * CMA allocations (alloc_contig_range) really need to mark + * isolate CMA pageblocks even when they are not movable in fact + * so consider them movable here. + */ + if (is_migrate_cma(migratetype)) + return false; + + reason = "CMA page"; + goto unmovable; + } - pfn = page_to_pfn(page); - for (found = 0, iter = 0; iter < pageblock_nr_pages; iter++) { + for (found = 0; iter < pageblock_nr_pages; iter++) { unsigned long check = pfn + iter; if (!pfn_valid_within(check)) @@ -7961,7 +8196,7 @@ bool has_unmovable_pages(struct zone *zone, struct page *page, int count, /* * Hugepages are not in LRU lists, but they're movable. - * We need not scan over tail pages bacause we don't + * We need not scan over tail pages because we don't * handle each tail page individually in migration. */ if (PageHuge(page)) { @@ -8020,12 +8255,11 @@ bool has_unmovable_pages(struct zone *zone, struct page *page, int count, unmovable: WARN_ON_ONCE(zone_idx(zone) == ZONE_MOVABLE); if (flags & REPORT_FAILURE) - dump_page(pfn_to_page(pfn+iter), "unmovable page"); + dump_page(pfn_to_page(pfn + iter), reason); return true; } -#if (defined(CONFIG_MEMORY_ISOLATION) && defined(CONFIG_COMPACTION)) || defined(CONFIG_CMA) - +#ifdef CONFIG_CONTIG_ALLOC static unsigned long pfn_max_align_down(unsigned long pfn) { return pfn & ~(max_t(unsigned long, MAX_ORDER_NR_PAGES, @@ -8100,7 +8334,7 @@ static int __alloc_contig_migrate_range(struct compact_control *cc, * pageblocks in the range. Once isolated, the pageblocks should not * be modified by others. * - * Returns zero on success or negative error code. On success all + * Return: zero on success or negative error code. On success all * pages which PFN is in [start, end) are allocated for the caller and * need to be freed with free_contig_range(). */ @@ -8148,7 +8382,7 @@ int alloc_contig_range(unsigned long start, unsigned long end, ret = start_isolate_page_range(pfn_max_align_down(start), pfn_max_align_up(end), migratetype, 0); - if (ret) + if (ret < 0) return ret; /* @@ -8184,7 +8418,6 @@ int alloc_contig_range(unsigned long start, unsigned long end, */ lru_add_drain_all(); - drain_all_pages(cc.zone); order = 0; outer_start = start; @@ -8235,8 +8468,9 @@ done: pfn_max_align_up(end), migratetype); return ret; } +#endif /* CONFIG_CONTIG_ALLOC */ -void free_contig_range(unsigned long pfn, unsigned nr_pages) +void free_contig_range(unsigned long pfn, unsigned int nr_pages) { unsigned int count = 0; @@ -8248,7 +8482,6 @@ void free_contig_range(unsigned long pfn, unsigned nr_pages) } WARN(count != 0, "%d pages are still in use!\n", count); } -#endif #ifdef CONFIG_MEMORY_HOTPLUG /* @@ -8290,7 +8523,7 @@ void zone_pcp_reset(struct zone *zone) * All pages in the range must be in a single zone and isolated * before calling this. */ -void +unsigned long __offline_isolated_pages(unsigned long start_pfn, unsigned long end_pfn) { struct page *page; @@ -8298,12 +8531,15 @@ __offline_isolated_pages(unsigned long start_pfn, unsigned long end_pfn) unsigned int order, i; unsigned long pfn; unsigned long flags; + unsigned long offlined_pages = 0; + /* find the first valid pfn */ for (pfn = start_pfn; pfn < end_pfn; pfn++) if (pfn_valid(pfn)) break; if (pfn == end_pfn) - return; + return offlined_pages; + offline_mem_sections(pfn, end_pfn); zone = page_zone(pfn_to_page(pfn)); spin_lock_irqsave(&zone->lock, flags); @@ -8321,24 +8557,26 @@ __offline_isolated_pages(unsigned long start_pfn, unsigned long end_pfn) if (unlikely(!PageBuddy(page) && PageHWPoison(page))) { pfn++; SetPageReserved(page); + offlined_pages++; continue; } BUG_ON(page_count(page)); BUG_ON(!PageBuddy(page)); order = page_order(page); + offlined_pages += 1 << order; #ifdef CONFIG_DEBUG_VM pr_info("remove from free list %lx %d %lx\n", pfn, 1 << order, end_pfn); #endif - list_del(&page->lru); - rmv_page_order(page); - zone->free_area[order].nr_free--; + del_page_from_free_area(page, &zone->free_area[order]); for (i = 0; i < (1 << order); i++) SetPageReserved((page+i)); pfn += (1 << order); } spin_unlock_irqrestore(&zone->lock, flags); + + return offlined_pages; } #endif |