diff options
Diffstat (limited to 'mm/page_alloc.c')
| -rw-r--r-- | mm/page_alloc.c | 3718 |
1 files changed, 2396 insertions, 1322 deletions
diff --git a/mm/page_alloc.c b/mm/page_alloc.c index 07a654486f7..ef44ad736ca 100644 --- a/mm/page_alloc.c +++ b/mm/page_alloc.c @@ -30,6 +30,7 @@ #include <linux/pagevec.h> #include <linux/blkdev.h> #include <linux/slab.h> +#include <linux/ratelimit.h> #include <linux/oom.h> #include <linux/notifier.h> #include <linux/topology.h> @@ -39,6 +40,7 @@ #include <linux/memory_hotplug.h> #include <linux/nodemask.h> #include <linux/vmalloc.h> +#include <linux/vmstat.h> #include <linux/mempolicy.h> #include <linux/stop_machine.h> #include <linux/sort.h> @@ -49,15 +51,26 @@ #include <linux/page_cgroup.h> #include <linux/debugobjects.h> #include <linux/kmemleak.h> -#include <linux/memory.h> #include <linux/compaction.h> #include <trace/events/kmem.h> #include <linux/ftrace_event.h> - +#include <linux/memcontrol.h> +#include <linux/prefetch.h> +#include <linux/mm_inline.h> +#include <linux/migrate.h> +#include <linux/page-debug-flags.h> +#include <linux/hugetlb.h> +#include <linux/sched/rt.h> + +#include <asm/sections.h> #include <asm/tlbflush.h> #include <asm/div64.h> #include "internal.h" +/* prevent >1 _updater_ of zone percpu pageset ->high and ->batch fields */ +static DEFINE_MUTEX(pcp_batch_high_lock); +#define MIN_PERCPU_PAGELIST_FRACTION (8) + #ifdef CONFIG_USE_PERCPU_NUMA_NODE_ID DEFINE_PER_CPU(int, numa_node); EXPORT_PER_CPU_SYMBOL(numa_node); @@ -85,13 +98,27 @@ nodemask_t node_states[NR_NODE_STATES] __read_mostly = { #ifdef CONFIG_HIGHMEM [N_HIGH_MEMORY] = { { [0] = 1UL } }, #endif +#ifdef CONFIG_MOVABLE_NODE + [N_MEMORY] = { { [0] = 1UL } }, +#endif [N_CPU] = { { [0] = 1UL } }, #endif /* NUMA */ }; EXPORT_SYMBOL(node_states); +/* Protect totalram_pages and zone->managed_pages */ +static DEFINE_SPINLOCK(managed_page_count_lock); + unsigned long totalram_pages __read_mostly; unsigned long totalreserve_pages __read_mostly; +/* + * When calculating the number of globally allowed dirty pages, there + * is a certain number of per-zone reserves that should not be + * considered dirtyable memory. This is the sum of those reserves + * over all existing zones that contribute dirtyable memory. + */ +unsigned long dirty_balance_reserve __read_mostly; + int percpu_pagelist_fraction; gfp_t gfp_allowed_mask __read_mostly = GFP_BOOT_MASK; @@ -104,19 +131,31 @@ gfp_t gfp_allowed_mask __read_mostly = GFP_BOOT_MASK; * only be modified with pm_mutex held, unless the suspend/hibernate code is * guaranteed not to run in parallel with that modification). */ -void set_gfp_allowed_mask(gfp_t mask) + +static gfp_t saved_gfp_mask; + +void pm_restore_gfp_mask(void) { WARN_ON(!mutex_is_locked(&pm_mutex)); - gfp_allowed_mask = mask; + if (saved_gfp_mask) { + gfp_allowed_mask = saved_gfp_mask; + saved_gfp_mask = 0; + } } -gfp_t clear_gfp_allowed_mask(gfp_t mask) +void pm_restrict_gfp_mask(void) { - gfp_t ret = gfp_allowed_mask; - WARN_ON(!mutex_is_locked(&pm_mutex)); - gfp_allowed_mask &= ~mask; - return ret; + WARN_ON(saved_gfp_mask); + saved_gfp_mask = gfp_allowed_mask; + gfp_allowed_mask &= ~GFP_IOFS; +} + +bool pm_suspended_storage(void) +{ + if ((gfp_allowed_mask & GFP_IOFS) == GFP_IOFS) + return false; + return true; } #endif /* CONFIG_PM_SLEEP */ @@ -167,44 +206,23 @@ static char * const zone_names[MAX_NR_ZONES] = { }; int min_free_kbytes = 1024; +int user_min_free_kbytes = -1; static unsigned long __meminitdata nr_kernel_pages; static unsigned long __meminitdata nr_all_pages; static unsigned long __meminitdata dma_reserve; -#ifdef CONFIG_ARCH_POPULATES_NODE_MAP - /* - * MAX_ACTIVE_REGIONS determines the maximum number of distinct - * ranges of memory (RAM) that may be registered with add_active_range(). - * Ranges passed to add_active_range() will be merged if possible - * so the number of times add_active_range() can be called is - * related to the number of nodes and the number of holes - */ - #ifdef CONFIG_MAX_ACTIVE_REGIONS - /* Allow an architecture to set MAX_ACTIVE_REGIONS to save memory */ - #define MAX_ACTIVE_REGIONS CONFIG_MAX_ACTIVE_REGIONS - #else - #if MAX_NUMNODES >= 32 - /* If there can be many nodes, allow up to 50 holes per node */ - #define MAX_ACTIVE_REGIONS (MAX_NUMNODES*50) - #else - /* By default, allow up to 256 distinct regions */ - #define MAX_ACTIVE_REGIONS 256 - #endif - #endif - - static struct node_active_region __meminitdata early_node_map[MAX_ACTIVE_REGIONS]; - static int __meminitdata nr_nodemap_entries; - static unsigned long __meminitdata arch_zone_lowest_possible_pfn[MAX_NR_ZONES]; - static unsigned long __meminitdata arch_zone_highest_possible_pfn[MAX_NR_ZONES]; - static unsigned long __initdata required_kernelcore; - static unsigned long __initdata required_movablecore; - static unsigned long __meminitdata zone_movable_pfn[MAX_NUMNODES]; - - /* movable_zone is the "real" zone pages in ZONE_MOVABLE are taken from */ - int movable_zone; - EXPORT_SYMBOL(movable_zone); -#endif /* CONFIG_ARCH_POPULATES_NODE_MAP */ +#ifdef CONFIG_HAVE_MEMBLOCK_NODE_MAP +static unsigned long __meminitdata arch_zone_lowest_possible_pfn[MAX_NR_ZONES]; +static unsigned long __meminitdata arch_zone_highest_possible_pfn[MAX_NR_ZONES]; +static unsigned long __initdata required_kernelcore; +static unsigned long __initdata required_movablecore; +static unsigned long __meminitdata zone_movable_pfn[MAX_NUMNODES]; + +/* movable_zone is the "real" zone pages in ZONE_MOVABLE are taken from */ +int movable_zone; +EXPORT_SYMBOL(movable_zone); +#endif /* CONFIG_HAVE_MEMBLOCK_NODE_MAP */ #if MAX_NUMNODES > 1 int nr_node_ids __read_mostly = MAX_NUMNODES; @@ -215,10 +233,10 @@ EXPORT_SYMBOL(nr_online_nodes); int page_group_by_mobility_disabled __read_mostly; -static void set_pageblock_migratetype(struct page *page, int migratetype) +void set_pageblock_migratetype(struct page *page, int migratetype) { - - if (unlikely(page_group_by_mobility_disabled)) + if (unlikely(page_group_by_mobility_disabled && + migratetype < MIGRATE_PCPTYPES)) migratetype = MIGRATE_UNMOVABLE; set_pageblock_flags_group(page, (unsigned long)migratetype, @@ -233,15 +251,21 @@ static int page_outside_zone_boundaries(struct zone *zone, struct page *page) int ret = 0; unsigned seq; unsigned long pfn = page_to_pfn(page); + unsigned long sp, start_pfn; do { seq = zone_span_seqbegin(zone); - if (pfn >= zone->zone_start_pfn + zone->spanned_pages) - ret = 1; - else if (pfn < zone->zone_start_pfn) + start_pfn = zone->zone_start_pfn; + sp = zone->spanned_pages; + if (!zone_spans_pfn(zone, pfn)) ret = 1; } while (zone_span_seqretry(zone, seq)); + if (ret) + pr_err("page 0x%lx outside node %d zone %s [ 0x%lx - 0x%lx ]\n", + pfn, zone_to_nid(zone), zone->name, + start_pfn, start_pfn + sp); + return ret; } @@ -273,7 +297,8 @@ static inline int bad_range(struct zone *zone, struct page *page) } #endif -static void bad_page(struct page *page) +static void bad_page(struct page *page, const char *reason, + unsigned long bad_flags) { static unsigned long resume; static unsigned long nr_shown; @@ -281,7 +306,7 @@ static void bad_page(struct page *page) /* Don't complain about poisoned pages */ if (PageHWPoison(page)) { - __ClearPageBuddy(page); + page_mapcount_reset(page); /* remove PageBuddy */ return; } @@ -307,13 +332,14 @@ static void bad_page(struct page *page) printk(KERN_ALERT "BUG: Bad page state in process %s pfn:%05lx\n", current->comm, page_to_pfn(page)); - dump_page(page); + dump_page_badflags(page, reason, bad_flags); + print_modules(); dump_stack(); out: /* Leave bad fields for debug, except PageBuddy could make trouble */ - __ClearPageBuddy(page); - add_taint(TAINT_BAD_PAGE); + page_mapcount_reset(page); /* remove PageBuddy */ + add_taint(TAINT_BAD_PAGE, LOCKDEP_NOW_UNRELIABLE); } /* @@ -323,8 +349,8 @@ out: * * The remaining PAGE_SIZE pages are called "tail pages". * - * All pages have PG_compound set. All pages have their ->private pointing at - * the head page (even the head page has this). + * All pages have PG_compound set. All tail pages have their ->first_page + * pointing at the head page. * * 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. @@ -346,21 +372,23 @@ void prep_compound_page(struct page *page, unsigned long order) __SetPageHead(page); for (i = 1; i < nr_pages; i++) { struct page *p = page + i; - - __SetPageTail(p); + set_page_count(p, 0); p->first_page = page; + /* Make sure p->first_page is always valid for PageTail() */ + smp_wmb(); + __SetPageTail(p); } } +/* update __split_huge_page_refcount if you change this function */ static int destroy_compound_page(struct page *page, unsigned long order) { int i; int nr_pages = 1 << order; int bad = 0; - if (unlikely(compound_order(page) != order) || - unlikely(!PageHead(page))) { - bad_page(page); + if (unlikely(compound_order(page) != order)) { + bad_page(page, "wrong compound order", 0); bad++; } @@ -369,8 +397,11 @@ static int destroy_compound_page(struct page *page, unsigned long order) for (i = 1; i < nr_pages; i++) { struct page *p = page + i; - if (unlikely(!PageTail(p) || (p->first_page != page))) { - bad_page(page); + if (unlikely(!PageTail(p))) { + bad_page(page, "PageTail not set", 0); + bad++; + } else if (unlikely(p->first_page != page)) { + bad_page(page, "first_page not consistent", 0); bad++; } __ClearPageTail(p); @@ -379,7 +410,8 @@ static int destroy_compound_page(struct page *page, unsigned long order) return bad; } -static inline void prep_zero_page(struct page *page, int order, gfp_t gfp_flags) +static inline void prep_zero_page(struct page *page, unsigned int order, + gfp_t gfp_flags) { int i; @@ -392,7 +424,38 @@ static inline void prep_zero_page(struct page *page, int order, gfp_t gfp_flags) clear_highpage(page + i); } -static inline void set_page_order(struct page *page, int order) +#ifdef CONFIG_DEBUG_PAGEALLOC +unsigned int _debug_guardpage_minorder; + +static int __init debug_guardpage_minorder_setup(char *buf) +{ + unsigned long res; + + if (kstrtoul(buf, 10, &res) < 0 || res > MAX_ORDER / 2) { + printk(KERN_ERR "Bad debug_guardpage_minorder value\n"); + return 0; + } + _debug_guardpage_minorder = res; + printk(KERN_INFO "Setting debug_guardpage_minorder to %lu\n", res); + return 0; +} +__setup("debug_guardpage_minorder=", debug_guardpage_minorder_setup); + +static inline void set_page_guard_flag(struct page *page) +{ + __set_bit(PAGE_DEBUG_FLAG_GUARD, &page->debug_flags); +} + +static inline void clear_page_guard_flag(struct page *page) +{ + __clear_bit(PAGE_DEBUG_FLAG_GUARD, &page->debug_flags); +} +#else +static inline void set_page_guard_flag(struct page *page) { } +static inline void clear_page_guard_flag(struct page *page) { } +#endif + +static inline void set_page_order(struct page *page, unsigned int order) { set_page_private(page, order); __SetPageBuddy(page); @@ -421,18 +484,10 @@ static inline void rmv_page_order(struct page *page) * * Assumption: *_mem_map is contiguous at least up to MAX_ORDER */ -static inline struct page * -__page_find_buddy(struct page *page, unsigned long page_idx, unsigned int order) -{ - unsigned long buddy_idx = page_idx ^ (1 << order); - - return page + (buddy_idx - page_idx); -} - static inline unsigned long -__find_combined_index(unsigned long page_idx, unsigned int order) +__find_buddy_index(unsigned long page_idx, unsigned int order) { - return (page_idx & ~(1 << order)); + return page_idx ^ (1 << order); } /* @@ -443,22 +498,39 @@ __find_combined_index(unsigned long page_idx, unsigned int order) * (c) a page and its buddy have the same order && * (d) a page and its buddy are in the same zone. * - * For recording whether a page is in the buddy system, we use PG_buddy. - * Setting, clearing, and testing PG_buddy is serialized by zone->lock. + * For recording whether a page is in the buddy system, we set ->_mapcount + * PAGE_BUDDY_MAPCOUNT_VALUE. + * Setting, clearing, and testing _mapcount PAGE_BUDDY_MAPCOUNT_VALUE is + * serialized by zone->lock. * * For recording page's order, we use page_private(page). */ static inline int page_is_buddy(struct page *page, struct page *buddy, - int order) + unsigned int order) { if (!pfn_valid_within(page_to_pfn(buddy))) return 0; - if (page_zone_id(page) != page_zone_id(buddy)) - return 0; + if (page_is_guard(buddy) && page_order(buddy) == order) { + VM_BUG_ON_PAGE(page_count(buddy) != 0, buddy); + + if (page_zone_id(page) != page_zone_id(buddy)) + return 0; + + return 1; + } if (PageBuddy(buddy) && page_order(buddy) == order) { - VM_BUG_ON(page_count(buddy) != 0); + VM_BUG_ON_PAGE(page_count(buddy) != 0, buddy); + + /* + * zone check is done late to avoid uselessly + * calculating zone/node ids for pages that could + * never merge. + */ + if (page_zone_id(page) != page_zone_id(buddy)) + return 0; + return 1; } return 0; @@ -477,46 +549,61 @@ static inline int page_is_buddy(struct page *page, struct page *buddy, * as necessary, plus some accounting needed to play nicely with other * parts of the VM system. * At each level, we keep a list of pages, which are heads of continuous - * free pages of length of (1 << order) and marked with PG_buddy. Page's - * order is recorded in page_private(page) field. + * free pages of length of (1 << order) and marked with _mapcount + * PAGE_BUDDY_MAPCOUNT_VALUE. Page's order is recorded in page_private(page) + * field. * So when we are allocating or freeing one, we can derive the state of the - * other. That is, if we allocate a small block, and both were - * free, the remainder of the region must be split into blocks. + * other. That is, if we allocate a small block, and both were + * free, the remainder of the region must be split into blocks. * If a block is freed, and its buddy is also free, then this - * triggers coalescing into a block of larger size. + * triggers coalescing into a block of larger size. * - * -- wli + * -- nyc */ static inline void __free_one_page(struct page *page, + unsigned long pfn, struct zone *zone, unsigned int order, int migratetype) { unsigned long page_idx; unsigned long combined_idx; + unsigned long uninitialized_var(buddy_idx); struct page *buddy; + VM_BUG_ON(!zone_is_initialized(zone)); + if (unlikely(PageCompound(page))) if (unlikely(destroy_compound_page(page, order))) return; VM_BUG_ON(migratetype == -1); - page_idx = page_to_pfn(page) & ((1 << MAX_ORDER) - 1); + page_idx = pfn & ((1 << MAX_ORDER) - 1); - VM_BUG_ON(page_idx & ((1 << order) - 1)); - VM_BUG_ON(bad_range(zone, page)); + VM_BUG_ON_PAGE(page_idx & ((1 << order) - 1), page); + VM_BUG_ON_PAGE(bad_range(zone, page), page); while (order < MAX_ORDER-1) { - buddy = __page_find_buddy(page, page_idx, order); + buddy_idx = __find_buddy_index(page_idx, order); + buddy = page + (buddy_idx - page_idx); if (!page_is_buddy(page, buddy, order)) break; - - /* Our buddy is free, merge with it and move up one order. */ - list_del(&buddy->lru); - zone->free_area[order].nr_free--; - rmv_page_order(buddy); - combined_idx = __find_combined_index(page_idx, order); + /* + * 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)) { + clear_page_guard_flag(buddy); + set_page_private(page, 0); + __mod_zone_freepage_state(zone, 1 << order, + migratetype); + } else { + list_del(&buddy->lru); + zone->free_area[order].nr_free--; + rmv_page_order(buddy); + } + combined_idx = buddy_idx & page_idx; page = page + (combined_idx - page_idx); page_idx = combined_idx; order++; @@ -533,9 +620,10 @@ static inline void __free_one_page(struct page *page, */ if ((order < MAX_ORDER-2) && pfn_valid_within(page_to_pfn(buddy))) { struct page *higher_page, *higher_buddy; - combined_idx = __find_combined_index(page_idx, order); - higher_page = page + combined_idx - page_idx; - higher_buddy = __page_find_buddy(higher_page, combined_idx, order + 1); + combined_idx = buddy_idx & page_idx; + higher_page = page + (combined_idx - page_idx); + buddy_idx = __find_buddy_index(combined_idx, order + 1); + higher_buddy = higher_page + (buddy_idx - combined_idx); if (page_is_buddy(higher_page, higher_buddy, order + 1)) { list_add_tail(&page->lru, &zone->free_area[order].free_list[migratetype]); @@ -548,26 +636,28 @@ out: zone->free_area[order].nr_free++; } -/* - * free_page_mlock() -- clean up attempts to free and mlocked() page. - * Page should not be on lru, so no need to fix that up. - * free_pages_check() will verify... - */ -static inline void free_page_mlock(struct page *page) -{ - __dec_zone_page_state(page, NR_MLOCK); - __count_vm_event(UNEVICTABLE_MLOCKFREED); -} - static inline int free_pages_check(struct page *page) { - if (unlikely(page_mapcount(page) | - (page->mapping != NULL) | - (atomic_read(&page->_count) != 0) | - (page->flags & PAGE_FLAGS_CHECK_AT_FREE))) { - bad_page(page); + const char *bad_reason = NULL; + unsigned long bad_flags = 0; + + if (unlikely(page_mapcount(page))) + bad_reason = "nonzero mapcount"; + if (unlikely(page->mapping != NULL)) + bad_reason = "non-NULL mapping"; + if (unlikely(atomic_read(&page->_count) != 0)) + bad_reason = "nonzero _count"; + if (unlikely(page->flags & PAGE_FLAGS_CHECK_AT_FREE)) { + bad_reason = "PAGE_FLAGS_CHECK_AT_FREE flag(s) set"; + bad_flags = PAGE_FLAGS_CHECK_AT_FREE; + } + if (unlikely(mem_cgroup_bad_page_check(page))) + bad_reason = "cgroup check failed"; + if (unlikely(bad_reason)) { + bad_page(page, bad_reason, bad_flags); return 1; } + page_cpupid_reset_last(page); if (page->flags & PAGE_FLAGS_CHECK_AT_PREP) page->flags &= ~PAGE_FLAGS_CHECK_AT_PREP; return 0; @@ -592,7 +682,6 @@ static void free_pcppages_bulk(struct zone *zone, int count, int to_free = count; spin_lock(&zone->lock); - zone->all_unreclaimable = 0; zone->pages_scanned = 0; while (to_free) { @@ -613,28 +702,41 @@ static void free_pcppages_bulk(struct zone *zone, int count, list = &pcp->lists[migratetype]; } while (list_empty(list)); + /* This is the only non-empty list. Free them all. */ + if (batch_free == MIGRATE_PCPTYPES) + batch_free = to_free; + do { + int mt; /* migratetype of the to-be-freed page */ + page = list_entry(list->prev, struct page, lru); /* must delete as __free_one_page list manipulates */ list_del(&page->lru); + mt = get_freepage_migratetype(page); /* MIGRATE_MOVABLE list may include MIGRATE_RESERVEs */ - __free_one_page(page, zone, 0, page_private(page)); - trace_mm_page_pcpu_drain(page, 0, page_private(page)); + __free_one_page(page, page_to_pfn(page), zone, 0, mt); + trace_mm_page_pcpu_drain(page, 0, mt); + if (likely(!is_migrate_isolate_page(page))) { + __mod_zone_page_state(zone, NR_FREE_PAGES, 1); + if (is_migrate_cma(mt)) + __mod_zone_page_state(zone, NR_FREE_CMA_PAGES, 1); + } } while (--to_free && --batch_free && !list_empty(list)); } - __mod_zone_page_state(zone, NR_FREE_PAGES, count); spin_unlock(&zone->lock); } -static void free_one_page(struct zone *zone, struct page *page, int order, +static void free_one_page(struct zone *zone, + struct page *page, unsigned long pfn, + unsigned int order, int migratetype) { spin_lock(&zone->lock); - zone->all_unreclaimable = 0; zone->pages_scanned = 0; - __free_one_page(page, zone, order, migratetype); - __mod_zone_page_state(zone, NR_FREE_PAGES, 1 << order); + __free_one_page(page, pfn, zone, order, migratetype); + if (unlikely(!is_migrate_isolate(migratetype))) + __mod_zone_freepage_state(zone, 1 << order, migratetype); spin_unlock(&zone->lock); } @@ -643,21 +745,19 @@ static bool free_pages_prepare(struct page *page, unsigned int order) int i; int bad = 0; - trace_mm_page_free_direct(page, order); + trace_mm_page_free(page, order); kmemcheck_free_shadow(page, order); - for (i = 0; i < (1 << order); i++) { - struct page *pg = page + i; - - if (PageAnon(pg)) - pg->mapping = NULL; - bad += free_pages_check(pg); - } + if (PageAnon(page)) + page->mapping = NULL; + for (i = 0; i < (1 << order); i++) + bad += free_pages_check(page + i); if (bad) return false; if (!PageHighMem(page)) { - debug_check_no_locks_freed(page_address(page),PAGE_SIZE<<order); + debug_check_no_locks_freed(page_address(page), + PAGE_SIZE << order); debug_check_no_obj_freed(page_address(page), PAGE_SIZE << order); } @@ -670,48 +770,70 @@ static bool free_pages_prepare(struct page *page, unsigned int order) static void __free_pages_ok(struct page *page, unsigned int order) { unsigned long flags; - int wasMlocked = __TestClearPageMlocked(page); + int migratetype; + unsigned long pfn = page_to_pfn(page); if (!free_pages_prepare(page, order)) return; + migratetype = get_pfnblock_migratetype(page, pfn); local_irq_save(flags); - if (unlikely(wasMlocked)) - free_page_mlock(page); __count_vm_events(PGFREE, 1 << order); - free_one_page(page_zone(page), page, order, - get_pageblock_migratetype(page)); + set_freepage_migratetype(page, migratetype); + free_one_page(page_zone(page), page, pfn, order, migratetype); local_irq_restore(flags); } -/* - * permit the bootmem allocator to evade page validation on high-order frees - */ -void __meminit __free_pages_bootmem(struct page *page, unsigned int order) +void __init __free_pages_bootmem(struct page *page, unsigned int order) { - if (order == 0) { - __ClearPageReserved(page); - set_page_count(page, 0); - set_page_refcounted(page); - __free_page(page); - } else { - int loop; + unsigned int nr_pages = 1 << order; + struct page *p = page; + unsigned int loop; - prefetchw(page); - for (loop = 0; loop < BITS_PER_LONG; loop++) { - struct page *p = &page[loop]; + prefetchw(p); + for (loop = 0; loop < (nr_pages - 1); loop++, p++) { + prefetchw(p + 1); + __ClearPageReserved(p); + set_page_count(p, 0); + } + __ClearPageReserved(p); + set_page_count(p, 0); - if (loop + 1 < BITS_PER_LONG) - prefetchw(p + 1); - __ClearPageReserved(p); - set_page_count(p, 0); - } + page_zone(page)->managed_pages += nr_pages; + set_page_refcounted(page); + __free_pages(page, order); +} +#ifdef CONFIG_CMA +/* Free whole pageblock and set its migration type to MIGRATE_CMA. */ +void __init init_cma_reserved_pageblock(struct page *page) +{ + unsigned i = pageblock_nr_pages; + struct page *p = page; + + do { + __ClearPageReserved(p); + set_page_count(p, 0); + } while (++p, --i); + + set_pageblock_migratetype(page, MIGRATE_CMA); + + if (pageblock_order >= MAX_ORDER) { + i = pageblock_nr_pages; + p = page; + do { + set_page_refcounted(p); + __free_pages(p, MAX_ORDER - 1); + p += MAX_ORDER_NR_PAGES; + } while (i -= MAX_ORDER_NR_PAGES); + } else { set_page_refcounted(page); - __free_pages(page, order); + __free_pages(page, pageblock_order); } -} + adjust_managed_page_count(page, pageblock_nr_pages); +} +#endif /* * The order of subdivision here is critical for the IO subsystem. @@ -725,7 +847,7 @@ void __meminit __free_pages_bootmem(struct page *page, unsigned int order) * large block of memory acted on by a series of small allocations. * This behavior is a critical factor in sglist merging's success. * - * -- wli + * -- nyc */ static inline void expand(struct zone *zone, struct page *page, int low, int high, struct free_area *area, @@ -737,7 +859,25 @@ static inline void expand(struct zone *zone, struct page *page, area--; high--; size >>= 1; - VM_BUG_ON(bad_range(zone, &page[size])); + VM_BUG_ON_PAGE(bad_range(zone, &page[size]), &page[size]); + +#ifdef CONFIG_DEBUG_PAGEALLOC + if (high < debug_guardpage_minorder()) { + /* + * Mark as guard pages (or page), that will allow to + * merge back to allocator when buddy will be freed. + * Corresponding page table entries will not be touched, + * pages will stay not present in virtual address space + */ + INIT_LIST_HEAD(&page[size].lru); + set_page_guard_flag(&page[size]); + set_page_private(&page[size], high); + /* Guard pages are not available for any usage */ + __mod_zone_freepage_state(zone, -(1 << high), + migratetype); + continue; + } +#endif list_add(&page[size].lru, &area->free_list[migratetype]); area->nr_free++; set_page_order(&page[size], high); @@ -749,17 +889,29 @@ static inline void expand(struct zone *zone, struct page *page, */ static inline int check_new_page(struct page *page) { - if (unlikely(page_mapcount(page) | - (page->mapping != NULL) | - (atomic_read(&page->_count) != 0) | - (page->flags & PAGE_FLAGS_CHECK_AT_PREP))) { - bad_page(page); + const char *bad_reason = NULL; + unsigned long bad_flags = 0; + + if (unlikely(page_mapcount(page))) + bad_reason = "nonzero mapcount"; + if (unlikely(page->mapping != NULL)) + bad_reason = "non-NULL mapping"; + if (unlikely(atomic_read(&page->_count) != 0)) + bad_reason = "nonzero _count"; + 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; + } + if (unlikely(mem_cgroup_bad_page_check(page))) + bad_reason = "cgroup check failed"; + if (unlikely(bad_reason)) { + bad_page(page, bad_reason, bad_flags); return 1; } return 0; } -static int prep_new_page(struct page *page, int order, gfp_t gfp_flags) +static int prep_new_page(struct page *page, unsigned int order, gfp_t gfp_flags) { int i; @@ -793,7 +945,7 @@ struct page *__rmqueue_smallest(struct zone *zone, unsigned int order, int migratetype) { unsigned int current_order; - struct free_area * area; + struct free_area *area; struct page *page; /* Find a page of the appropriate size in the preferred list */ @@ -808,6 +960,7 @@ 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); return page; } @@ -819,11 +972,19 @@ struct page *__rmqueue_smallest(struct zone *zone, unsigned int order, * This array describes the order lists are fallen back to when * the free lists for the desirable migrate type are depleted */ -static int fallbacks[MIGRATE_TYPES][MIGRATE_TYPES-1] = { - [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_RESERVE] = { MIGRATE_RESERVE, MIGRATE_RESERVE, MIGRATE_RESERVE }, /* Never used */ +static int fallbacks[MIGRATE_TYPES][4] = { + [MIGRATE_UNMOVABLE] = { MIGRATE_RECLAIMABLE, MIGRATE_MOVABLE, MIGRATE_RESERVE }, + [MIGRATE_RECLAIMABLE] = { MIGRATE_UNMOVABLE, MIGRATE_MOVABLE, MIGRATE_RESERVE }, +#ifdef CONFIG_CMA + [MIGRATE_MOVABLE] = { MIGRATE_CMA, MIGRATE_RECLAIMABLE, MIGRATE_UNMOVABLE, MIGRATE_RESERVE }, + [MIGRATE_CMA] = { MIGRATE_RESERVE }, /* Never used */ +#else + [MIGRATE_MOVABLE] = { MIGRATE_RECLAIMABLE, MIGRATE_UNMOVABLE, MIGRATE_RESERVE }, +#endif + [MIGRATE_RESERVE] = { MIGRATE_RESERVE }, /* Never used */ +#ifdef CONFIG_MEMORY_ISOLATION + [MIGRATE_ISOLATE] = { MIGRATE_RESERVE }, /* Never used */ +#endif }; /* @@ -831,7 +992,7 @@ static int fallbacks[MIGRATE_TYPES][MIGRATE_TYPES-1] = { * Note that start_page and end_pages are not aligned on a pageblock * boundary. If alignment is required, use move_freepages_block() */ -static int move_freepages(struct zone *zone, +int move_freepages(struct zone *zone, struct page *start_page, struct page *end_page, int migratetype) { @@ -852,7 +1013,7 @@ static int move_freepages(struct zone *zone, for (page = start_page; page <= end_page;) { /* Make sure we are not inadvertently changing nodes */ - VM_BUG_ON(page_to_nid(page) != zone_to_nid(zone)); + VM_BUG_ON_PAGE(page_to_nid(page) != zone_to_nid(zone), page); if (!pfn_valid_within(page_to_pfn(page))) { page++; @@ -865,9 +1026,9 @@ static int move_freepages(struct zone *zone, } order = page_order(page); - list_del(&page->lru); - list_add(&page->lru, - &zone->free_area[order].free_list[migratetype]); + list_move(&page->lru, + &zone->free_area[order].free_list[migratetype]); + set_freepage_migratetype(page, migratetype); page += 1 << order; pages_moved += 1 << order; } @@ -875,7 +1036,7 @@ static int move_freepages(struct zone *zone, return pages_moved; } -static int move_freepages_block(struct zone *zone, struct page *page, +int move_freepages_block(struct zone *zone, struct page *page, int migratetype) { unsigned long start_pfn, end_pfn; @@ -888,9 +1049,9 @@ static int move_freepages_block(struct zone *zone, struct page *page, end_pfn = start_pfn + pageblock_nr_pages - 1; /* Do not cross zone boundaries */ - if (start_pfn < zone->zone_start_pfn) + if (!zone_spans_pfn(zone, start_pfn)) start_page = page; - if (end_pfn >= zone->zone_start_pfn + zone->spanned_pages) + if (!zone_spans_pfn(zone, end_pfn)) return 0; return move_freepages(zone, start_page, end_page, migratetype); @@ -907,24 +1068,77 @@ static void change_pageblock_range(struct page *pageblock_page, } } +/* + * If breaking a large block of pages, move all free pages to the preferred + * allocation list. If falling back for a reclaimable kernel allocation, be + * more aggressive about taking ownership of free pages. + * + * On the other hand, never change migration type of MIGRATE_CMA pageblocks + * nor move CMA pages to different free lists. We don't want unmovable pages + * to be allocated from MIGRATE_CMA areas. + * + * Returns the new migratetype of the pageblock (or the same old migratetype + * if it was unchanged). + */ +static int try_to_steal_freepages(struct zone *zone, struct page *page, + int start_type, int fallback_type) +{ + int current_order = page_order(page); + + /* + * When borrowing from MIGRATE_CMA, we need to release the excess + * buddy pages to CMA itself. We also ensure the freepage_migratetype + * is set to CMA so it is returned to the correct freelist in case + * the page ends up being not actually allocated from the pcp lists. + */ + if (is_migrate_cma(fallback_type)) + return fallback_type; + + /* Take ownership for orders >= pageblock_order */ + if (current_order >= pageblock_order) { + change_pageblock_range(page, current_order, start_type); + return start_type; + } + + if (current_order >= pageblock_order / 2 || + start_type == MIGRATE_RECLAIMABLE || + page_group_by_mobility_disabled) { + int pages; + + pages = move_freepages_block(zone, page, start_type); + + /* Claim the whole block if over half of it is free */ + if (pages >= (1 << (pageblock_order-1)) || + page_group_by_mobility_disabled) { + + set_pageblock_migratetype(page, start_type); + return start_type; + } + + } + + return fallback_type; +} + /* Remove an element from the buddy allocator from the fallback list */ static inline struct page * -__rmqueue_fallback(struct zone *zone, int order, int start_migratetype) +__rmqueue_fallback(struct zone *zone, unsigned int order, int start_migratetype) { - struct free_area * area; - int current_order; + struct free_area *area; + unsigned int current_order; struct page *page; - int migratetype, i; + int migratetype, new_type, i; /* Find the largest possible block of pages in the other list */ - for (current_order = MAX_ORDER-1; current_order >= order; - --current_order) { - for (i = 0; i < MIGRATE_TYPES - 1; i++) { + for (current_order = MAX_ORDER-1; + current_order >= order && current_order <= MAX_ORDER-1; + --current_order) { + for (i = 0;; i++) { migratetype = fallbacks[start_migratetype][i]; /* MIGRATE_RESERVE handled later if necessary */ if (migratetype == MIGRATE_RESERVE) - continue; + break; area = &(zone->free_area[current_order]); if (list_empty(&area->free_list[migratetype])) @@ -934,41 +1148,25 @@ __rmqueue_fallback(struct zone *zone, int order, int start_migratetype) struct page, lru); area->nr_free--; - /* - * If breaking a large block of pages, move all free - * pages to the preferred allocation list. If falling - * back for a reclaimable kernel allocation, be more - * agressive about taking ownership of free pages - */ - if (unlikely(current_order >= (pageblock_order >> 1)) || - start_migratetype == MIGRATE_RECLAIMABLE || - page_group_by_mobility_disabled) { - unsigned long pages; - pages = move_freepages_block(zone, page, - start_migratetype); - - /* Claim the whole block if over half of it is free */ - if (pages >= (1 << (pageblock_order-1)) || - page_group_by_mobility_disabled) - set_pageblock_migratetype(page, - start_migratetype); - - migratetype = start_migratetype; - } + new_type = try_to_steal_freepages(zone, page, + start_migratetype, + migratetype); /* Remove the page from the freelists */ list_del(&page->lru); rmv_page_order(page); - /* Take ownership for orders >= pageblock_order */ - if (current_order >= pageblock_order) - change_pageblock_range(page, current_order, - start_migratetype); - - expand(zone, page, order, current_order, area, migratetype); + expand(zone, page, order, current_order, area, + new_type); + /* The freepage_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 type. + */ + set_freepage_migratetype(page, new_type); trace_mm_page_alloc_extfrag(page, order, current_order, - start_migratetype, migratetype); + start_migratetype, migratetype, new_type); return page; } @@ -1007,17 +1205,17 @@ retry_reserve: return page; } -/* +/* * Obtain a specified number of elements from the buddy allocator, all under * a single hold of the lock, for efficiency. Add them to the supplied list. * Returns the number of new pages which were placed at *list. */ -static int rmqueue_bulk(struct zone *zone, unsigned int order, +static int rmqueue_bulk(struct zone *zone, unsigned int order, unsigned long count, struct list_head *list, - int migratetype, int cold) + int migratetype, bool cold) { int i; - + spin_lock(&zone->lock); for (i = 0; i < count; ++i) { struct page *page = __rmqueue(zone, order, migratetype); @@ -1033,12 +1231,14 @@ static int rmqueue_bulk(struct zone *zone, unsigned int order, * merge IO requests if the physical pages are ordered * properly. */ - if (likely(cold == 0)) + if (likely(!cold)) list_add(&page->lru, list); else list_add_tail(&page->lru, list); - set_page_private(page, migratetype); list = &page->lru; + if (is_migrate_cma(get_freepage_migratetype(page))) + __mod_zone_page_state(zone, NR_FREE_CMA_PAGES, + -(1 << order)); } __mod_zone_page_state(zone, NR_FREE_PAGES, -(i << order)); spin_unlock(&zone->lock); @@ -1058,14 +1258,18 @@ void drain_zone_pages(struct zone *zone, struct per_cpu_pages *pcp) { unsigned long flags; int to_drain; + unsigned long batch; local_irq_save(flags); - if (pcp->count >= pcp->batch) - to_drain = pcp->batch; + batch = ACCESS_ONCE(pcp->batch); + if (pcp->count >= batch) + to_drain = batch; else to_drain = pcp->count; - free_pcppages_bulk(zone, to_drain, pcp); - pcp->count -= to_drain; + if (to_drain > 0) { + free_pcppages_bulk(zone, to_drain, pcp); + pcp->count -= to_drain; + } local_irq_restore(flags); } #endif @@ -1090,8 +1294,10 @@ static void drain_pages(unsigned int cpu) pset = per_cpu_ptr(zone->pageset, cpu); pcp = &pset->pcp; - free_pcppages_bulk(zone, pcp->count, pcp); - pcp->count = 0; + if (pcp->count) { + free_pcppages_bulk(zone, pcp->count, pcp); + pcp->count = 0; + } local_irq_restore(flags); } } @@ -1105,11 +1311,47 @@ void drain_local_pages(void *arg) } /* - * Spill all the per-cpu pages from all CPUs back into the buddy allocator + * Spill all the per-cpu pages from all CPUs back into the buddy allocator. + * + * Note that this code is protected against sending an IPI to an offline + * CPU but does not guarantee sending an IPI to newly hotplugged CPUs: + * on_each_cpu_mask() blocks hotplug and won't talk to offlined CPUs but + * nothing keeps CPUs from showing up after we populated the cpumask and + * before the call to on_each_cpu_mask(). */ void drain_all_pages(void) { - on_each_cpu(drain_local_pages, NULL, 1); + int cpu; + struct per_cpu_pageset *pcp; + struct zone *zone; + + /* + * Allocate in the BSS so we wont require allocation in + * direct reclaim path for CONFIG_CPUMASK_OFFSTACK=y + */ + static cpumask_t cpus_with_pcps; + + /* + * We don't care about racing with CPU hotplug event + * as offline notification will cause the notified + * cpu to drain that CPU pcps and on_each_cpu_mask + * disables preemption as part of its processing + */ + for_each_online_cpu(cpu) { + bool has_pcps = false; + for_each_populated_zone(zone) { + pcp = per_cpu_ptr(zone->pageset, cpu); + if (pcp->pcp.count) { + has_pcps = true; + break; + } + } + if (has_pcps) + cpumask_set_cpu(cpu, &cpus_with_pcps); + else + cpumask_clear_cpu(cpu, &cpus_with_pcps); + } + on_each_cpu_mask(&cpus_with_pcps, drain_local_pages, NULL, 1); } #ifdef CONFIG_HIBERNATION @@ -1118,15 +1360,15 @@ void mark_free_pages(struct zone *zone) { unsigned long pfn, max_zone_pfn; unsigned long flags; - int order, t; + unsigned int order, t; struct list_head *curr; - if (!zone->spanned_pages) + if (zone_is_empty(zone)) return; spin_lock_irqsave(&zone->lock, flags); - max_zone_pfn = zone->zone_start_pfn + zone->spanned_pages; + max_zone_pfn = zone_end_pfn(zone); for (pfn = zone->zone_start_pfn; pfn < max_zone_pfn; pfn++) if (pfn_valid(pfn)) { struct page *page = pfn_to_page(pfn); @@ -1150,24 +1392,22 @@ void mark_free_pages(struct zone *zone) /* * Free a 0-order page - * cold == 1 ? free a cold page : free a hot page + * cold == true ? free a cold page : free a hot page */ -void free_hot_cold_page(struct page *page, int cold) +void free_hot_cold_page(struct page *page, bool cold) { struct zone *zone = page_zone(page); struct per_cpu_pages *pcp; unsigned long flags; + unsigned long pfn = page_to_pfn(page); int migratetype; - int wasMlocked = __TestClearPageMlocked(page); if (!free_pages_prepare(page, 0)) return; - migratetype = get_pageblock_migratetype(page); - set_page_private(page, migratetype); + migratetype = get_pfnblock_migratetype(page, pfn); + set_freepage_migratetype(page, migratetype); local_irq_save(flags); - if (unlikely(wasMlocked)) - free_page_mlock(page); __count_vm_event(PGFREE); /* @@ -1178,22 +1418,23 @@ void free_hot_cold_page(struct page *page, int cold) * excessively into the page allocator */ if (migratetype >= MIGRATE_PCPTYPES) { - if (unlikely(migratetype == MIGRATE_ISOLATE)) { - free_one_page(zone, page, 0, migratetype); + if (unlikely(is_migrate_isolate(migratetype))) { + free_one_page(zone, page, pfn, 0, migratetype); goto out; } migratetype = MIGRATE_MOVABLE; } pcp = &this_cpu_ptr(zone->pageset)->pcp; - if (cold) - list_add_tail(&page->lru, &pcp->lists[migratetype]); - else + if (!cold) list_add(&page->lru, &pcp->lists[migratetype]); + else + list_add_tail(&page->lru, &pcp->lists[migratetype]); pcp->count++; if (pcp->count >= pcp->high) { - free_pcppages_bulk(zone, pcp->batch, pcp); - pcp->count -= pcp->batch; + unsigned long batch = ACCESS_ONCE(pcp->batch); + free_pcppages_bulk(zone, batch, pcp); + pcp->count -= batch; } out: @@ -1201,6 +1442,19 @@ out: } /* + * Free a list of 0-order pages + */ +void free_hot_cold_page_list(struct list_head *list, bool cold) +{ + struct page *page, *next; + + list_for_each_entry_safe(page, next, list, lru) { + trace_mm_page_free_batched(page, cold); + free_hot_cold_page(page, cold); + } +} + +/* * split_page takes a non-compound higher-order page, and splits it into * n (1<<order) sub-pages: page[0..n] * Each sub-page must be freed individually. @@ -1212,8 +1466,8 @@ void split_page(struct page *page, unsigned int order) { int i; - VM_BUG_ON(PageCompound(page)); - VM_BUG_ON(!page_count(page)); + VM_BUG_ON_PAGE(PageCompound(page), page); + VM_BUG_ON_PAGE(!page_count(page), page); #ifdef CONFIG_KMEMCHECK /* @@ -1227,6 +1481,46 @@ void split_page(struct page *page, unsigned int order) for (i = 1; i < (1 << order); i++) set_page_refcounted(page + i); } +EXPORT_SYMBOL_GPL(split_page); + +static int __isolate_free_page(struct page *page, unsigned int order) +{ + unsigned long watermark; + struct zone *zone; + int mt; + + BUG_ON(!PageBuddy(page)); + + zone = page_zone(page); + mt = get_pageblock_migratetype(page); + + if (!is_migrate_isolate(mt)) { + /* Obey watermarks as if the page was being allocated */ + watermark = low_wmark_pages(zone) + (1 << order); + if (!zone_watermark_ok(zone, 0, watermark, 0, 0)) + return 0; + + __mod_zone_freepage_state(zone, -(1UL << order), mt); + } + + /* Remove page from free list */ + list_del(&page->lru); + zone->free_area[order].nr_free--; + rmv_page_order(page); + + /* Set the pageblock if the isolated page is at least a pageblock */ + if (order >= pageblock_order - 1) { + struct page *endpage = page + (1 << order) - 1; + for (; page < endpage; page += pageblock_nr_pages) { + int mt = get_pageblock_migratetype(page); + if (!is_migrate_isolate(mt) && !is_migrate_cma(mt)) + set_pageblock_migratetype(page, + MIGRATE_MOVABLE); + } + } + + return 1UL << order; +} /* * Similar to split_page except the page is already free. As this is only @@ -1241,36 +1535,18 @@ void split_page(struct page *page, unsigned int order) int split_free_page(struct page *page) { unsigned int order; - unsigned long watermark; - struct zone *zone; + int nr_pages; - BUG_ON(!PageBuddy(page)); - - zone = page_zone(page); order = page_order(page); - /* Obey watermarks as if the page was being allocated */ - watermark = low_wmark_pages(zone) + (1 << order); - if (!zone_watermark_ok(zone, 0, watermark, 0, 0)) + nr_pages = __isolate_free_page(page, order); + if (!nr_pages) return 0; - /* Remove page from free list */ - list_del(&page->lru); - zone->free_area[order].nr_free--; - rmv_page_order(page); - __mod_zone_page_state(zone, NR_FREE_PAGES, -(1UL << order)); - /* Split into individual pages */ set_page_refcounted(page); split_page(page, order); - - if (order >= pageblock_order - 1) { - struct page *endpage = page + (1 << order) - 1; - for (; page < endpage; page += pageblock_nr_pages) - set_pageblock_migratetype(page, MIGRATE_MOVABLE); - } - - return 1 << order; + return nr_pages; } /* @@ -1280,12 +1556,12 @@ int split_free_page(struct page *page) */ static inline struct page *buffered_rmqueue(struct zone *preferred_zone, - struct zone *zone, int order, gfp_t gfp_flags, - int migratetype) + struct zone *zone, unsigned int order, + gfp_t gfp_flags, int migratetype) { unsigned long flags; struct page *page; - int cold = !!(gfp_flags & __GFP_COLD); + bool cold = ((gfp_flags & __GFP_COLD) != 0); again: if (likely(order == 0)) { @@ -1329,14 +1605,17 @@ again: spin_unlock(&zone->lock); if (!page) goto failed; - __mod_zone_page_state(zone, NR_FREE_PAGES, -(1 << order)); + __mod_zone_freepage_state(zone, -(1 << order), + get_freepage_migratetype(page)); } + __mod_zone_page_state(zone, NR_ALLOC_BATCH, -(1 << order)); + __count_zone_vm_events(PGALLOC, zone, 1 << order); - zone_statistics(preferred_zone, zone); + zone_statistics(preferred_zone, zone, gfp_flags); local_irq_restore(flags); - VM_BUG_ON(bad_range(zone, page)); + VM_BUG_ON_PAGE(bad_range(zone, page), page); if (prep_new_page(page, order, gfp_flags)) goto again; return page; @@ -1346,36 +1625,14 @@ failed: return NULL; } -/* The ALLOC_WMARK bits are used as an index to zone->watermark */ -#define ALLOC_WMARK_MIN WMARK_MIN -#define ALLOC_WMARK_LOW WMARK_LOW -#define ALLOC_WMARK_HIGH WMARK_HIGH -#define ALLOC_NO_WATERMARKS 0x04 /* don't check watermarks at all */ - -/* Mask to get the watermark bits */ -#define ALLOC_WMARK_MASK (ALLOC_NO_WATERMARKS-1) - -#define ALLOC_HARDER 0x10 /* try to alloc harder */ -#define ALLOC_HIGH 0x20 /* __GFP_HIGH set */ -#define ALLOC_CPUSET 0x40 /* check for correct cpuset */ - #ifdef CONFIG_FAIL_PAGE_ALLOC -static struct fail_page_alloc_attr { +static struct { struct fault_attr attr; u32 ignore_gfp_highmem; u32 ignore_gfp_wait; u32 min_order; - -#ifdef CONFIG_FAULT_INJECTION_DEBUG_FS - - struct dentry *ignore_gfp_highmem_file; - struct dentry *ignore_gfp_wait_file; - struct dentry *min_order_file; - -#endif /* CONFIG_FAULT_INJECTION_DEBUG_FS */ - } fail_page_alloc = { .attr = FAULT_ATTR_INITIALIZER, .ignore_gfp_wait = 1, @@ -1389,16 +1646,16 @@ static int __init setup_fail_page_alloc(char *str) } __setup("fail_page_alloc=", setup_fail_page_alloc); -static int should_fail_alloc_page(gfp_t gfp_mask, unsigned int order) +static bool should_fail_alloc_page(gfp_t gfp_mask, unsigned int order) { if (order < fail_page_alloc.min_order) - return 0; + return false; if (gfp_mask & __GFP_NOFAIL) - return 0; + return false; if (fail_page_alloc.ignore_gfp_highmem && (gfp_mask & __GFP_HIGHMEM)) - return 0; + return false; if (fail_page_alloc.ignore_gfp_wait && (gfp_mask & __GFP_WAIT)) - return 0; + return false; return should_fail(&fail_page_alloc.attr, 1 << order); } @@ -1407,38 +1664,29 @@ static int should_fail_alloc_page(gfp_t gfp_mask, unsigned int order) static int __init fail_page_alloc_debugfs(void) { - mode_t mode = S_IFREG | S_IRUSR | S_IWUSR; + umode_t mode = S_IFREG | S_IRUSR | S_IWUSR; struct dentry *dir; - int err; - - err = init_fault_attr_dentries(&fail_page_alloc.attr, - "fail_page_alloc"); - if (err) - return err; - dir = fail_page_alloc.attr.dentries.dir; - fail_page_alloc.ignore_gfp_wait_file = - debugfs_create_bool("ignore-gfp-wait", mode, dir, - &fail_page_alloc.ignore_gfp_wait); + 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_wait)) + 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; - fail_page_alloc.ignore_gfp_highmem_file = - debugfs_create_bool("ignore-gfp-highmem", mode, dir, - &fail_page_alloc.ignore_gfp_highmem); - fail_page_alloc.min_order_file = - debugfs_create_u32("min-order", mode, dir, - &fail_page_alloc.min_order); - - if (!fail_page_alloc.ignore_gfp_wait_file || - !fail_page_alloc.ignore_gfp_highmem_file || - !fail_page_alloc.min_order_file) { - err = -ENOMEM; - debugfs_remove(fail_page_alloc.ignore_gfp_wait_file); - debugfs_remove(fail_page_alloc.ignore_gfp_highmem_file); - debugfs_remove(fail_page_alloc.min_order_file); - cleanup_fault_attr_dentries(&fail_page_alloc.attr); - } + return 0; +fail: + debugfs_remove_recursive(dir); - return err; + return -ENOMEM; } late_initcall(fail_page_alloc_debugfs); @@ -1447,32 +1695,40 @@ late_initcall(fail_page_alloc_debugfs); #else /* CONFIG_FAIL_PAGE_ALLOC */ -static inline int should_fail_alloc_page(gfp_t gfp_mask, unsigned int order) +static inline bool should_fail_alloc_page(gfp_t gfp_mask, unsigned int order) { - return 0; + return false; } #endif /* CONFIG_FAIL_PAGE_ALLOC */ /* - * Return 1 if free pages are above 'mark'. This takes into account the order + * Return true if free pages are above 'mark'. This takes into account the order * of the allocation. */ -int zone_watermark_ok(struct zone *z, int order, unsigned long mark, - int classzone_idx, int alloc_flags) +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 my go negative - that's OK */ long min = mark; - long free_pages = zone_nr_free_pages(z) - (1 << order) + 1; + long lowmem_reserve = z->lowmem_reserve[classzone_idx]; int o; + long free_cma = 0; + free_pages -= (1 << order) - 1; if (alloc_flags & ALLOC_HIGH) min -= min / 2; if (alloc_flags & ALLOC_HARDER) 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); +#endif - if (free_pages <= min + z->lowmem_reserve[classzone_idx]) - return 0; + if (free_pages - free_cma <= min + lowmem_reserve) + 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; @@ -1481,9 +1737,28 @@ int zone_watermark_ok(struct zone *z, int order, unsigned long mark, min >>= 1; if (free_pages <= min) - return 0; + return false; } - return 1; + return true; +} + +bool zone_watermark_ok(struct zone *z, unsigned int order, unsigned long mark, + int classzone_idx, int alloc_flags) +{ + return __zone_watermark_ok(z, order, mark, classzone_idx, alloc_flags, + zone_page_state(z, NR_FREE_PAGES)); +} + +bool zone_watermark_ok_safe(struct zone *z, unsigned int order, + unsigned long mark, int classzone_idx, int alloc_flags) +{ + 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, + free_pages); } #ifdef CONFIG_NUMA @@ -1494,9 +1769,9 @@ int zone_watermark_ok(struct zone *z, int order, unsigned long mark, * 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 in zonelist, then + * 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_HIGH_MEMORY].) + * tasks mems_allowed, or node_states[N_MEMORY].) * * If the zonelist cache is not available for this zonelist, does * nothing and returns NULL. @@ -1525,7 +1800,7 @@ static nodemask_t *zlc_setup(struct zonelist *zonelist, int alloc_flags) allowednodes = !in_interrupt() && (alloc_flags & ALLOC_CPUSET) ? &cpuset_current_mems_allowed : - &node_states[N_HIGH_MEMORY]; + &node_states[N_MEMORY]; return allowednodes; } @@ -1588,6 +1863,32 @@ static void zlc_mark_zone_full(struct zonelist *zonelist, struct zoneref *z) 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; +} + +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) @@ -1604,6 +1905,21 @@ static int zlc_zone_worth_trying(struct zonelist *zonelist, struct zoneref *z, 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; +} + +static bool zone_allows_reclaim(struct zone *local_zone, struct zone *zone) +{ + return true; +} + #endif /* CONFIG_NUMA */ /* @@ -1613,57 +1929,136 @@ static void zlc_mark_zone_full(struct zonelist *zonelist, struct zoneref *z) static struct page * get_page_from_freelist(gfp_t gfp_mask, nodemask_t *nodemask, unsigned int order, struct zonelist *zonelist, int high_zoneidx, int alloc_flags, - struct zone *preferred_zone, int migratetype) + struct zone *preferred_zone, int classzone_idx, int migratetype) { struct zoneref *z; struct page *page = NULL; - int classzone_idx; 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); - classzone_idx = zone_idx(preferred_zone); zonelist_scan: /* * Scan zonelist, looking for a zone with enough free. - * See also cpuset_zone_allowed() comment in kernel/cpuset.c. + * See also __cpuset_node_allowed_softwall() comment in kernel/cpuset.c. */ for_each_zone_zonelist_nodemask(zone, z, zonelist, high_zoneidx, nodemask) { - if (NUMA_BUILD && zlc_active && + unsigned long mark; + + if (IS_ENABLED(CONFIG_NUMA) && zlc_active && !zlc_zone_worth_trying(zonelist, z, allowednodes)) continue; - if ((alloc_flags & ALLOC_CPUSET) && + if (cpusets_enabled() && + (alloc_flags & ALLOC_CPUSET) && !cpuset_zone_allowed_softwall(zone, gfp_mask)) - goto try_next_zone; + continue; + /* + * Distribute pages in proportion to the individual + * zone size to ensure fair page aging. The zone a + * page was allocated in should have no effect on the + * time the page has in memory before being reclaimed. + */ + if (alloc_flags & ALLOC_FAIR) { + if (!zone_local(preferred_zone, zone)) + continue; + if (zone_page_state(zone, NR_ALLOC_BATCH) <= 0) + continue; + } + /* + * When allocating a page cache page for writing, we + * want to get it from a zone that is within its dirty + * limit, such that no single zone holds more than its + * proportional share of globally allowed dirty pages. + * The dirty limits take into account the zone's + * lowmem reserves and high watermark so that kswapd + * should be able to balance it without having to + * write pages from its LRU list. + * + * This may look like it could increase pressure on + * lower zones by failing allocations in higher zones + * before they are full. But the pages that do spill + * over are limited as the lower zones are protected + * by this very same mechanism. It should not become + * a practical burden to them. + * + * XXX: For now, allow allocations to potentially + * exceed the per-zone dirty limit in the slowpath + * (ALLOC_WMARK_LOW 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)) + continue; - BUILD_BUG_ON(ALLOC_NO_WATERMARKS < NR_WMARK); - if (!(alloc_flags & ALLOC_NO_WATERMARKS)) { - unsigned long mark; + mark = zone->watermark[alloc_flags & ALLOC_WMARK_MASK]; + if (!zone_watermark_ok(zone, order, mark, + classzone_idx, alloc_flags)) { int ret; - mark = zone->watermark[alloc_flags & ALLOC_WMARK_MASK]; - if (zone_watermark_ok(zone, order, mark, - classzone_idx, alloc_flags)) + /* Checked here to keep the fast path fast */ + BUILD_BUG_ON(ALLOC_NO_WATERMARKS < NR_WMARK); + if (alloc_flags & ALLOC_NO_WATERMARKS) goto try_this_zone; - if (zone_reclaim_mode == 0) + 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(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); switch (ret) { case ZONE_RECLAIM_NOSCAN: /* did not scan */ - goto try_next_zone; + continue; case ZONE_RECLAIM_FULL: /* scanned but unreclaimable */ - goto this_zone_full; + continue; default: /* did we reclaim enough */ - if (!zone_watermark_ok(zone, order, mark, + if (zone_watermark_ok(zone, order, mark, 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; } } @@ -1673,36 +2068,110 @@ try_this_zone: if (page) break; this_zone_full: - if (NUMA_BUILD) + if (IS_ENABLED(CONFIG_NUMA) && zlc_active) zlc_mark_zone_full(zonelist, z); -try_next_zone: - if (NUMA_BUILD && !did_zlc_setup && nr_online_nodes > 1) { - /* - * we do zlc_setup after the first zone is tried but only - * if there are multiple nodes make it worthwhile - */ - allowednodes = zlc_setup(zonelist, alloc_flags); - zlc_active = 1; - did_zlc_setup = 1; - } } - if (unlikely(NUMA_BUILD && page == NULL && zlc_active)) { + if (unlikely(IS_ENABLED(CONFIG_NUMA) && page == NULL && zlc_active)) { /* Disable zlc cache for second zonelist scan */ zlc_active = 0; goto zonelist_scan; } + + if (page) + /* + * page->pfmemalloc is set when ALLOC_NO_WATERMARKS was + * necessary to allocate the page. The expectation is + * that the caller is taking steps that will free more + * memory. The caller should avoid the page being used + * for !PFMEMALLOC purposes. + */ + page->pfmemalloc = !!(alloc_flags & ALLOC_NO_WATERMARKS); + return page; } +/* + * Large machines with many possible nodes should not always dump per-node + * meminfo in irq context. + */ +static inline bool should_suppress_show_mem(void) +{ + bool ret = false; + +#if NODES_SHIFT > 8 + ret = in_interrupt(); +#endif + return ret; +} + +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, ...) +{ + unsigned int filter = SHOW_MEM_FILTER_NODES; + + if ((gfp_mask & __GFP_NOWARN) || !__ratelimit(&nopage_rs) || + debug_guardpage_minorder() > 0) + return; + + /* + * This documents exceptions given to allocations in certain + * contexts that are allowed to allocate outside current's set + * of allowed nodes. + */ + if (!(gfp_mask & __GFP_NOMEMALLOC)) + if (test_thread_flag(TIF_MEMDIE) || + (current->flags & (PF_MEMALLOC | PF_EXITING))) + filter &= ~SHOW_MEM_FILTER_NODES; + if (in_interrupt() || !(gfp_mask & __GFP_WAIT)) + filter &= ~SHOW_MEM_FILTER_NODES; + + if (fmt) { + struct va_format vaf; + va_list args; + + va_start(args, fmt); + + vaf.fmt = fmt; + vaf.va = &args; + + pr_warn("%pV", &vaf); + + va_end(args); + } + + pr_warn("%s: page allocation failure: order:%d, mode:0x%x\n", + current->comm, order, gfp_mask); + + dump_stack(); + if (!should_suppress_show_mem()) + 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 @@ -1721,13 +2190,6 @@ should_alloc_retry(gfp_t gfp_mask, unsigned int order, if (gfp_mask & __GFP_REPEAT && pages_reclaimed < (1 << order)) return 1; - /* - * Don't let big-order allocations loop unless the caller - * explicitly requests that. - */ - if (gfp_mask & __GFP_NOFAIL) - return 1; - return 0; } @@ -1735,7 +2197,7 @@ static inline struct page * __alloc_pages_may_oom(gfp_t gfp_mask, unsigned int order, struct zonelist *zonelist, enum zone_type high_zoneidx, nodemask_t *nodemask, struct zone *preferred_zone, - int migratetype) + int classzone_idx, int migratetype) { struct page *page; @@ -1753,7 +2215,7 @@ __alloc_pages_may_oom(gfp_t gfp_mask, unsigned int order, page = get_page_from_freelist(gfp_mask|__GFP_HARDWALL, nodemask, order, zonelist, high_zoneidx, ALLOC_WMARK_HIGH|ALLOC_CPUSET, - preferred_zone, migratetype); + preferred_zone, classzone_idx, migratetype); if (page) goto out; @@ -1775,7 +2237,7 @@ __alloc_pages_may_oom(gfp_t gfp_mask, unsigned int order, goto out; } /* Exhausted what can be done so it's blamo time */ - out_of_memory(zonelist, gfp_mask, order, nodemask); + out_of_memory(zonelist, gfp_mask, order, nodemask, false); out: clear_zonelist_oom(zonelist, gfp_mask); @@ -1788,16 +2250,26 @@ static struct page * __alloc_pages_direct_compact(gfp_t gfp_mask, unsigned int order, struct zonelist *zonelist, enum zone_type high_zoneidx, nodemask_t *nodemask, int alloc_flags, struct zone *preferred_zone, - int migratetype, unsigned long *did_some_progress) + int classzone_idx, int migratetype, enum migrate_mode mode, + bool *contended_compaction, bool *deferred_compaction, + unsigned long *did_some_progress) { - struct page *page; + if (!order) + return NULL; - if (!order || compaction_deferred(preferred_zone)) + if (compaction_deferred(preferred_zone, order)) { + *deferred_compaction = true; return NULL; + } + current->flags |= PF_MEMALLOC; *did_some_progress = try_to_compact_pages(zonelist, order, gfp_mask, - nodemask); + nodemask, mode, + contended_compaction); + current->flags &= ~PF_MEMALLOC; + if (*did_some_progress != COMPACT_SKIPPED) { + struct page *page; /* Page migration frees to the PCP lists but we want merging */ drain_pages(get_cpu()); @@ -1805,11 +2277,11 @@ __alloc_pages_direct_compact(gfp_t gfp_mask, unsigned int order, page = get_page_from_freelist(gfp_mask, nodemask, order, zonelist, high_zoneidx, - alloc_flags, preferred_zone, - migratetype); + alloc_flags & ~ALLOC_NO_WATERMARKS, + preferred_zone, classzone_idx, migratetype); if (page) { - preferred_zone->compact_considered = 0; - preferred_zone->compact_defer_shift = 0; + preferred_zone->compact_blockskip_flush = false; + compaction_defer_reset(preferred_zone, order, true); count_vm_event(COMPACTSUCCESS); return page; } @@ -1820,7 +2292,13 @@ __alloc_pages_direct_compact(gfp_t gfp_mask, unsigned int order, * but not enough to satisfy watermarks. */ count_vm_event(COMPACTFAIL); - defer_compaction(preferred_zone); + + /* + * As async compaction considers a subset of pageblocks, only + * defer if the failure was a sync compaction failure. + */ + if (mode != MIGRATE_ASYNC) + defer_compaction(preferred_zone, order); cond_resched(); } @@ -1832,48 +2310,66 @@ static inline struct page * __alloc_pages_direct_compact(gfp_t gfp_mask, unsigned int order, struct zonelist *zonelist, enum zone_type high_zoneidx, nodemask_t *nodemask, int alloc_flags, struct zone *preferred_zone, - int migratetype, unsigned long *did_some_progress) + int classzone_idx, int migratetype, + enum migrate_mode mode, bool *contended_compaction, + bool *deferred_compaction, unsigned long *did_some_progress) { return NULL; } #endif /* CONFIG_COMPACTION */ -/* The really slow allocator path where we enter direct reclaim */ -static inline struct page * -__alloc_pages_direct_reclaim(gfp_t gfp_mask, unsigned int order, - struct zonelist *zonelist, enum zone_type high_zoneidx, - nodemask_t *nodemask, int alloc_flags, struct zone *preferred_zone, - int migratetype, unsigned long *did_some_progress) +/* Perform direct synchronous page reclaim */ +static int +__perform_reclaim(gfp_t gfp_mask, unsigned int order, struct zonelist *zonelist, + nodemask_t *nodemask) { - struct page *page = NULL; struct reclaim_state reclaim_state; - struct task_struct *p = current; - bool drained = false; + int progress; cond_resched(); /* We now go into synchronous reclaim */ cpuset_memory_pressure_bump(); - p->flags |= PF_MEMALLOC; + current->flags |= PF_MEMALLOC; lockdep_set_current_reclaim_state(gfp_mask); reclaim_state.reclaimed_slab = 0; - p->reclaim_state = &reclaim_state; + current->reclaim_state = &reclaim_state; - *did_some_progress = try_to_free_pages(zonelist, order, gfp_mask, nodemask); + progress = try_to_free_pages(zonelist, order, gfp_mask, nodemask); - p->reclaim_state = NULL; + current->reclaim_state = NULL; lockdep_clear_current_reclaim_state(); - p->flags &= ~PF_MEMALLOC; + current->flags &= ~PF_MEMALLOC; cond_resched(); + return progress; +} + +/* The really slow allocator path where we enter direct reclaim */ +static inline struct page * +__alloc_pages_direct_reclaim(gfp_t gfp_mask, unsigned int order, + struct zonelist *zonelist, enum zone_type high_zoneidx, + nodemask_t *nodemask, int alloc_flags, struct zone *preferred_zone, + int classzone_idx, int migratetype, unsigned long *did_some_progress) +{ + struct page *page = NULL; + bool drained = false; + + *did_some_progress = __perform_reclaim(gfp_mask, order, zonelist, + nodemask); if (unlikely(!(*did_some_progress))) return NULL; + /* After successful reclaim, reconsider all zones for allocation */ + if (IS_ENABLED(CONFIG_NUMA)) + zlc_clear_zones_full(zonelist); + retry: page = get_page_from_freelist(gfp_mask, nodemask, order, zonelist, high_zoneidx, - alloc_flags, preferred_zone, + alloc_flags & ~ALLOC_NO_WATERMARKS, + preferred_zone, classzone_idx, migratetype); /* @@ -1897,14 +2393,14 @@ static inline struct page * __alloc_pages_high_priority(gfp_t gfp_mask, unsigned int order, struct zonelist *zonelist, enum zone_type high_zoneidx, nodemask_t *nodemask, struct zone *preferred_zone, - int migratetype) + int classzone_idx, int migratetype) { struct page *page; do { page = get_page_from_freelist(gfp_mask, nodemask, order, zonelist, high_zoneidx, ALLOC_NO_WATERMARKS, - preferred_zone, migratetype); + preferred_zone, classzone_idx, migratetype); if (!page && gfp_mask & __GFP_NOFAIL) wait_iff_congested(preferred_zone, BLK_RW_ASYNC, HZ/50); @@ -1913,23 +2409,45 @@ __alloc_pages_high_priority(gfp_t gfp_mask, unsigned int order, return page; } -static inline -void wake_all_kswapd(unsigned int order, struct zonelist *zonelist, - enum zone_type high_zoneidx) +static void reset_alloc_batches(struct zonelist *zonelist, + enum zone_type high_zoneidx, + struct zone *preferred_zone) +{ + struct zoneref *z; + struct zone *zone; + + for_each_zone_zonelist(zone, z, zonelist, high_zoneidx) { + /* + * Only reset the batches of zones that were actually + * considered in the fairness pass, we don't want to + * trash fairness information for zones that are not + * actually part of this zonelist's round-robin cycle. + */ + if (!zone_local(preferred_zone, zone)) + continue; + mod_zone_page_state(zone, NR_ALLOC_BATCH, + high_wmark_pages(zone) - low_wmark_pages(zone) - + atomic_long_read(&zone->vm_stat[NR_ALLOC_BATCH])); + } +} + +static void wake_all_kswapds(unsigned int order, + struct zonelist *zonelist, + enum zone_type high_zoneidx, + struct zone *preferred_zone) { struct zoneref *z; struct zone *zone; for_each_zone_zonelist(zone, z, zonelist, high_zoneidx) - wakeup_kswapd(zone, order); + wakeup_kswapd(zone, order, zone_idx(preferred_zone)); } static inline int gfp_to_alloc_flags(gfp_t gfp_mask) { - struct task_struct *p = current; int alloc_flags = ALLOC_WMARK_MIN | ALLOC_CPUSET; - const gfp_t wait = gfp_mask & __GFP_WAIT; + 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); @@ -1938,42 +2456,61 @@ 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 (!wait) and ALLOC_HIGH (__GFP_HIGH). + * set both ALLOC_HARDER (atomic == true) and ALLOC_HIGH (__GFP_HIGH). */ alloc_flags |= (__force int) (gfp_mask & __GFP_HIGH); - if (!wait) { - alloc_flags |= ALLOC_HARDER; + if (atomic) { /* - * Ignore cpuset if GFP_ATOMIC (!wait) rather than fail alloc. - * See also cpuset_zone_allowed() comment in kernel/cpuset.c. + * Not worth trying to allocate harder for __GFP_NOMEMALLOC even + * if it can't schedule. + */ + if (!(gfp_mask & __GFP_NOMEMALLOC)) + alloc_flags |= ALLOC_HARDER; + /* + * Ignore cpuset mems for GFP_ATOMIC rather than fail, see the + * comment for __cpuset_node_allowed_softwall(). */ alloc_flags &= ~ALLOC_CPUSET; - } else if (unlikely(rt_task(p)) && !in_interrupt()) + } else if (unlikely(rt_task(current)) && !in_interrupt()) alloc_flags |= ALLOC_HARDER; if (likely(!(gfp_mask & __GFP_NOMEMALLOC))) { - if (!in_interrupt() && - ((p->flags & PF_MEMALLOC) || - unlikely(test_thread_flag(TIF_MEMDIE)))) + if (gfp_mask & __GFP_MEMALLOC) + alloc_flags |= ALLOC_NO_WATERMARKS; + else if (in_serving_softirq() && (current->flags & PF_MEMALLOC)) + alloc_flags |= ALLOC_NO_WATERMARKS; + else if (!in_interrupt() && + ((current->flags & PF_MEMALLOC) || + unlikely(test_thread_flag(TIF_MEMDIE)))) alloc_flags |= ALLOC_NO_WATERMARKS; } - +#ifdef CONFIG_CMA + if (allocflags_to_migratetype(gfp_mask) == MIGRATE_MOVABLE) + alloc_flags |= ALLOC_CMA; +#endif return alloc_flags; } +bool gfp_pfmemalloc_allowed(gfp_t gfp_mask) +{ + return !!(gfp_to_alloc_flags(gfp_mask) & ALLOC_NO_WATERMARKS); +} + static inline struct page * __alloc_pages_slowpath(gfp_t gfp_mask, unsigned int order, struct zonelist *zonelist, enum zone_type high_zoneidx, nodemask_t *nodemask, struct zone *preferred_zone, - int migratetype) + int classzone_idx, int migratetype) { const gfp_t wait = gfp_mask & __GFP_WAIT; struct page *page = NULL; int alloc_flags; unsigned long pages_reclaimed = 0; unsigned long did_some_progress; - struct task_struct *p = current; + enum migrate_mode migration_mode = MIGRATE_ASYNC; + bool deferred_compaction = false; + bool contended_compaction = false; /* * In the slowpath, we sanity check order to avoid ever trying to @@ -1994,11 +2531,13 @@ __alloc_pages_slowpath(gfp_t gfp_mask, unsigned int order, * allowed per node queues are empty and that nodes are * over allocated. */ - if (NUMA_BUILD && (gfp_mask & GFP_THISNODE) == GFP_THISNODE) + if (IS_ENABLED(CONFIG_NUMA) && + (gfp_mask & GFP_THISNODE) == GFP_THISNODE) goto nopage; restart: - wake_all_kswapd(order, zonelist, high_zoneidx); + if (!(gfp_mask & __GFP_NO_KSWAPD)) + wake_all_kswapds(order, zonelist, high_zoneidx, preferred_zone); /* * OK, we're below the kswapd watermark and have kicked background @@ -2007,50 +2546,100 @@ restart: */ alloc_flags = gfp_to_alloc_flags(gfp_mask); + /* + * Find the true preferred zone if the allocation is unconstrained by + * cpusets. + */ + if (!(alloc_flags & ALLOC_CPUSET) && !nodemask) { + struct zoneref *preferred_zoneref; + preferred_zoneref = first_zones_zonelist(zonelist, high_zoneidx, + NULL, &preferred_zone); + classzone_idx = zonelist_zone_idx(preferred_zoneref); + } + +rebalance: /* This is the last chance, in general, before the goto nopage. */ page = get_page_from_freelist(gfp_mask, nodemask, order, zonelist, high_zoneidx, alloc_flags & ~ALLOC_NO_WATERMARKS, - preferred_zone, migratetype); + preferred_zone, classzone_idx, migratetype); if (page) goto got_pg; -rebalance: /* Allocate without watermarks if the context allows */ if (alloc_flags & ALLOC_NO_WATERMARKS) { + /* + * Ignore mempolicies if ALLOC_NO_WATERMARKS on the grounds + * the allocation is high priority and these type of + * allocations are system rather than user orientated + */ + zonelist = node_zonelist(numa_node_id(), gfp_mask); + page = __alloc_pages_high_priority(gfp_mask, order, zonelist, high_zoneidx, nodemask, - preferred_zone, migratetype); - if (page) + preferred_zone, classzone_idx, migratetype); + if (page) { goto got_pg; + } } /* Atomic allocations - we can't balance anything */ - if (!wait) + if (!wait) { + /* + * All existing users of the deprecated __GFP_NOFAIL are + * blockable, so warn of any new users that actually allow this + * type of allocation to fail. + */ + WARN_ON_ONCE(gfp_mask & __GFP_NOFAIL); goto nopage; + } /* Avoid recursion of direct reclaim */ - if (p->flags & PF_MEMALLOC) + if (current->flags & PF_MEMALLOC) goto nopage; /* Avoid allocations with no watermarks from looping endlessly */ if (test_thread_flag(TIF_MEMDIE) && !(gfp_mask & __GFP_NOFAIL)) goto nopage; - /* Try direct compaction */ - page = __alloc_pages_direct_compact(gfp_mask, order, - zonelist, high_zoneidx, - nodemask, - alloc_flags, preferred_zone, - migratetype, &did_some_progress); + /* + * Try direct compaction. The first pass is asynchronous. Subsequent + * attempts after direct reclaim are synchronous + */ + page = __alloc_pages_direct_compact(gfp_mask, order, zonelist, + high_zoneidx, nodemask, alloc_flags, + preferred_zone, + classzone_idx, migratetype, + migration_mode, &contended_compaction, + &deferred_compaction, + &did_some_progress); if (page) goto got_pg; + /* + * It can become very expensive to allocate transparent hugepages at + * fault, so use asynchronous memory compaction for THP unless it is + * khugepaged trying to collapse. + */ + if (!(gfp_mask & __GFP_NO_KSWAPD) || (current->flags & PF_KTHREAD)) + migration_mode = MIGRATE_SYNC_LIGHT; + + /* + * If compaction is deferred for high-order allocations, it is because + * sync compaction recently failed. In this is the case and the caller + * requested a movable allocation that does not heavily disrupt the + * system then fail the allocation instead of entering direct reclaim. + */ + if ((deferred_compaction || contended_compaction) && + (gfp_mask & __GFP_NO_KSWAPD)) + goto nopage; + /* Try direct reclaim and then allocating */ page = __alloc_pages_direct_reclaim(gfp_mask, order, zonelist, high_zoneidx, nodemask, alloc_flags, preferred_zone, - migratetype, &did_some_progress); + classzone_idx, migratetype, + &did_some_progress); if (page) goto got_pg; @@ -2059,13 +2648,17 @@ rebalance: * running out of options and have to consider going OOM */ if (!did_some_progress) { - if ((gfp_mask & __GFP_FS) && !(gfp_mask & __GFP_NORETRY)) { + if (oom_gfp_allowed(gfp_mask)) { if (oom_killer_disabled) goto nopage; + /* Coredumps can quickly deplete all memory reserves */ + if ((current->flags & PF_DUMPCORE) && + !(gfp_mask & __GFP_NOFAIL)) + goto nopage; page = __alloc_pages_may_oom(gfp_mask, order, zonelist, high_zoneidx, nodemask, preferred_zone, - migratetype); + classzone_idx, migratetype); if (page) goto got_pg; @@ -2093,26 +2686,36 @@ rebalance: /* Check if we should retry the allocation */ pages_reclaimed += did_some_progress; - if (should_alloc_retry(gfp_mask, order, pages_reclaimed)) { + if (should_alloc_retry(gfp_mask, order, did_some_progress, + pages_reclaimed)) { /* Wait for some write requests to complete then retry */ wait_iff_congested(preferred_zone, BLK_RW_ASYNC, HZ/50); goto rebalance; + } 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, zonelist, + high_zoneidx, nodemask, alloc_flags, + preferred_zone, + classzone_idx, migratetype, + migration_mode, &contended_compaction, + &deferred_compaction, + &did_some_progress); + if (page) + goto got_pg; } nopage: - if (!(gfp_mask & __GFP_NOWARN) && printk_ratelimit()) { - printk(KERN_WARNING "%s: page allocation failure." - " order:%d, mode:0x%x\n", - p->comm, order, gfp_mask); - dump_stack(); - show_mem(); - } + warn_alloc_failed(gfp_mask, order, NULL); return page; got_pg: if (kmemcheck_enabled) kmemcheck_pagealloc_alloc(page, order, gfp_mask); - return page; + return page; } /* @@ -2124,8 +2727,12 @@ __alloc_pages_nodemask(gfp_t gfp_mask, unsigned int order, { enum zone_type high_zoneidx = gfp_zone(gfp_mask); struct zone *preferred_zone; - struct page *page; + struct zoneref *preferred_zoneref; + struct page *page = NULL; int migratetype = allocflags_to_migratetype(gfp_mask); + unsigned int cpuset_mems_cookie; + int alloc_flags = ALLOC_WMARK_LOW|ALLOC_CPUSET|ALLOC_FAIR; + int classzone_idx; gfp_mask &= gfp_allowed_mask; @@ -2144,25 +2751,66 @@ __alloc_pages_nodemask(gfp_t gfp_mask, unsigned int order, if (unlikely(!zonelist->_zonerefs->zone)) return NULL; - get_mems_allowed(); +retry_cpuset: + cpuset_mems_cookie = read_mems_allowed_begin(); + /* The preferred zone is used for statistics later */ - first_zones_zonelist(zonelist, high_zoneidx, nodemask, &preferred_zone); - if (!preferred_zone) { - put_mems_allowed(); - return NULL; - } + preferred_zoneref = first_zones_zonelist(zonelist, high_zoneidx, + nodemask ? : &cpuset_current_mems_allowed, + &preferred_zone); + if (!preferred_zone) + goto out; + classzone_idx = zonelist_zone_idx(preferred_zoneref); +#ifdef CONFIG_CMA + if (allocflags_to_migratetype(gfp_mask) == MIGRATE_MOVABLE) + alloc_flags |= ALLOC_CMA; +#endif +retry: /* First allocation attempt */ page = get_page_from_freelist(gfp_mask|__GFP_HARDWALL, nodemask, order, - zonelist, high_zoneidx, ALLOC_WMARK_LOW|ALLOC_CPUSET, - preferred_zone, migratetype); - if (unlikely(!page)) + zonelist, high_zoneidx, alloc_flags, + preferred_zone, classzone_idx, migratetype); + if (unlikely(!page)) { + /* + * The first pass makes sure allocations are spread + * fairly within the local node. However, the local + * node might have free pages left after the fairness + * batches are exhausted, and remote zones haven't + * even been considered yet. Try once more without + * fairness, and include remote zones now, before + * entering the slowpath and waking kswapd: prefer + * spilling to a remote zone over swapping locally. + */ + if (alloc_flags & ALLOC_FAIR) { + reset_alloc_batches(zonelist, high_zoneidx, + preferred_zone); + alloc_flags &= ~ALLOC_FAIR; + goto retry; + } + /* + * Runtime PM, block IO and its error handling path + * can deadlock because I/O on the device might not + * complete. + */ + gfp_mask = memalloc_noio_flags(gfp_mask); page = __alloc_pages_slowpath(gfp_mask, order, zonelist, high_zoneidx, nodemask, - preferred_zone, migratetype); - put_mems_allowed(); + preferred_zone, classzone_idx, migratetype); + } trace_mm_page_alloc(page, order, gfp_mask, migratetype); + +out: + /* + * When updating a task's mems_allowed, it is possible to race with + * parallel threads in such a way that an allocation can fail while + * the mask is being updated. If a page allocation is about to fail, + * check if the cpuset changed during allocation and if so, retry. + */ + if (unlikely(!page && read_mems_allowed_retry(cpuset_mems_cookie))) + goto retry_cpuset; + return page; } EXPORT_SYMBOL(__alloc_pages_nodemask); @@ -2193,21 +2841,11 @@ unsigned long get_zeroed_page(gfp_t gfp_mask) } EXPORT_SYMBOL(get_zeroed_page); -void __pagevec_free(struct pagevec *pvec) -{ - int i = pagevec_count(pvec); - - while (--i >= 0) { - trace_mm_pagevec_free(pvec->pages[i], pvec->cold); - free_hot_cold_page(pvec->pages[i], pvec->cold); - } -} - void __free_pages(struct page *page, unsigned int order) { if (put_page_testzero(page)) { if (order == 0) - free_hot_cold_page(page, 0); + free_hot_cold_page(page, false); else __free_pages_ok(page, order); } @@ -2225,6 +2863,70 @@ void free_pages(unsigned long addr, unsigned int order) EXPORT_SYMBOL(free_pages); +/* + * alloc_kmem_pages charges newly allocated pages to the kmem resource counter + * of the current memory cgroup. + * + * It should be used when the caller would like to use kmalloc, but since the + * allocation is large, it has to fall back to the page allocator. + */ +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); + 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); + return page; +} + +/* + * __free_kmem_pages and free_kmem_pages will free pages allocated with + * alloc_kmem_pages. + */ +void __free_kmem_pages(struct page *page, unsigned int order) +{ + memcg_kmem_uncharge_pages(page, order); + __free_pages(page, order); +} + +void free_kmem_pages(unsigned long addr, unsigned int order) +{ + if (addr != 0) { + VM_BUG_ON(!virt_addr_valid((void *)addr)); + __free_kmem_pages(virt_to_page((void *)addr), order); + } +} + +static void *make_alloc_exact(unsigned long addr, unsigned order, size_t size) +{ + if (addr) { + unsigned long alloc_end = addr + (PAGE_SIZE << order); + unsigned long used = addr + PAGE_ALIGN(size); + + split_page(virt_to_page((void *)addr), order); + while (used < alloc_end) { + free_page(used); + used += PAGE_SIZE; + } + } + return (void *)addr; +} + /** * alloc_pages_exact - allocate an exact number physically-contiguous pages. * @size: the number of bytes to allocate @@ -2244,22 +2946,33 @@ void *alloc_pages_exact(size_t size, gfp_t gfp_mask) unsigned long addr; addr = __get_free_pages(gfp_mask, order); - if (addr) { - unsigned long alloc_end = addr + (PAGE_SIZE << order); - unsigned long used = addr + PAGE_ALIGN(size); - - split_page(virt_to_page((void *)addr), order); - while (used < alloc_end) { - free_page(used); - used += PAGE_SIZE; - } - } - - return (void *)addr; + return make_alloc_exact(addr, order, size); } EXPORT_SYMBOL(alloc_pages_exact); /** + * alloc_pages_exact_nid - allocate an exact number of physically-contiguous + * 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 + * + * 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 *alloc_pages_exact_nid(int nid, size_t size, gfp_t gfp_mask) +{ + unsigned order = get_order(size); + struct page *p = alloc_pages_node(nid, gfp_mask, order); + if (!p) + return NULL; + return make_alloc_exact((unsigned long)page_address(p), order, size); +} +EXPORT_SYMBOL(alloc_pages_exact_nid); + +/** * free_pages_exact - release memory allocated via alloc_pages_exact() * @virt: the value returned by alloc_pages_exact. * @size: size of allocation, same value as passed to alloc_pages_exact(). @@ -2278,18 +2991,27 @@ void free_pages_exact(void *virt, size_t size) } EXPORT_SYMBOL(free_pages_exact); -static unsigned int nr_free_zone_pages(int offset) +/** + * 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 + * high watermark within all zones at or below a given zone index. For each + * zone, the number of pages is calculated as: + * managed_pages - high_pages + */ +static unsigned long nr_free_zone_pages(int offset) { struct zoneref *z; struct zone *zone; /* Just pick one node, since fallback list is circular */ - unsigned int sum = 0; + unsigned long sum = 0; struct zonelist *zonelist = node_zonelist(numa_node_id(), GFP_KERNEL); for_each_zone_zonelist(zone, z, zonelist, offset) { - unsigned long size = zone->present_pages; + unsigned long size = zone->managed_pages; unsigned long high = high_wmark_pages(zone); if (size > high) sum += size - high; @@ -2298,26 +3020,32 @@ static unsigned int nr_free_zone_pages(int offset) return sum; } -/* - * Amount of free RAM allocatable within ZONE_DMA and ZONE_NORMAL +/** + * nr_free_buffer_pages - count number of pages beyond high watermark + * + * nr_free_buffer_pages() counts the number of pages which are beyond the high + * watermark within ZONE_DMA and ZONE_NORMAL. */ -unsigned int nr_free_buffer_pages(void) +unsigned long nr_free_buffer_pages(void) { return nr_free_zone_pages(gfp_zone(GFP_USER)); } EXPORT_SYMBOL_GPL(nr_free_buffer_pages); -/* - * Amount of free RAM allocatable within all zones +/** + * nr_free_pagecache_pages - count number of pages beyond high watermark + * + * nr_free_pagecache_pages() counts the number of pages which are beyond the + * high watermark within all zones. */ -unsigned int nr_free_pagecache_pages(void) +unsigned long nr_free_pagecache_pages(void) { return nr_free_zone_pages(gfp_zone(GFP_HIGHUSER_MOVABLE)); } static inline void show_node(struct zone *zone) { - if (NUMA_BUILD) + if (IS_ENABLED(CONFIG_NUMA)) printk("Node %d ", zone_to_nid(zone)); } @@ -2337,12 +3065,16 @@ EXPORT_SYMBOL(si_meminfo); #ifdef CONFIG_NUMA void si_meminfo_node(struct sysinfo *val, int nid) { + int zone_type; /* needs to be signed */ + unsigned long managed_pages = 0; pg_data_t *pgdat = NODE_DATA(nid); - val->totalram = pgdat->node_present_pages; + for (zone_type = 0; zone_type < MAX_NR_ZONES; zone_type++) + managed_pages += pgdat->node_zones[zone_type].managed_pages; + val->totalram = managed_pages; val->freeram = node_page_state(nid, NR_FREE_PAGES); #ifdef CONFIG_HIGHMEM - val->totalhigh = pgdat->node_zones[ZONE_HIGHMEM].present_pages; + val->totalhigh = pgdat->node_zones[ZONE_HIGHMEM].managed_pages; val->freehigh = zone_page_state(&pgdat->node_zones[ZONE_HIGHMEM], NR_FREE_PAGES); #else @@ -2353,19 +3085,70 @@ void si_meminfo_node(struct sysinfo *val, int nid) } #endif +/* + * Determine whether the node should be displayed or not, depending on whether + * SHOW_MEM_FILTER_NODES was passed to show_free_areas(). + */ +bool skip_free_areas_node(unsigned int flags, int nid) +{ + bool ret = false; + unsigned int cpuset_mems_cookie; + + if (!(flags & SHOW_MEM_FILTER_NODES)) + goto out; + + do { + cpuset_mems_cookie = read_mems_allowed_begin(); + ret = !node_isset(nid, cpuset_current_mems_allowed); + } while (read_mems_allowed_retry(cpuset_mems_cookie)); +out: + return ret; +} + #define K(x) ((x) << (PAGE_SHIFT-10)) +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', +#ifdef CONFIG_CMA + [MIGRATE_CMA] = 'C', +#endif +#ifdef CONFIG_MEMORY_ISOLATION + [MIGRATE_ISOLATE] = 'I', +#endif + }; + char tmp[MIGRATE_TYPES + 1]; + char *p = tmp; + int i; + + for (i = 0; i < MIGRATE_TYPES; i++) { + if (type & (1 << i)) + *p++ = types[i]; + } + + *p = '\0'; + printk("(%s) ", tmp); +} + /* * Show free area list (used inside shift_scroll-lock stuff) * We also calculate the percentage fragmentation. We do this by counting the * memory on each free list with the exception of the first item on the list. + * Suppresses nodes that are not allowed by current's cpuset if + * SHOW_MEM_FILTER_NODES is passed. */ -void show_free_areas(void) +void show_free_areas(unsigned int filter) { int cpu; struct zone *zone; for_each_populated_zone(zone) { + if (skip_free_areas_node(filter, zone_to_nid(zone))) + continue; show_node(zone); printk("%s per-cpu:\n", zone->name); @@ -2385,7 +3168,8 @@ void show_free_areas(void) " unevictable:%lu" " dirty:%lu writeback:%lu unstable:%lu\n" " free:%lu slab_reclaimable:%lu slab_unreclaimable:%lu\n" - " mapped:%lu shmem:%lu pagetables:%lu bounce:%lu\n", + " mapped:%lu shmem:%lu pagetables:%lu bounce:%lu\n" + " free_cma:%lu\n", global_page_state(NR_ACTIVE_ANON), global_page_state(NR_INACTIVE_ANON), global_page_state(NR_ISOLATED_ANON), @@ -2402,11 +3186,14 @@ void show_free_areas(void) global_page_state(NR_FILE_MAPPED), global_page_state(NR_SHMEM), global_page_state(NR_PAGETABLE), - global_page_state(NR_BOUNCE)); + global_page_state(NR_BOUNCE), + global_page_state(NR_FREE_CMA_PAGES)); for_each_populated_zone(zone) { int i; + if (skip_free_areas_node(filter, zone_to_nid(zone))) + continue; show_node(zone); printk("%s" " free:%lukB" @@ -2421,6 +3208,7 @@ void show_free_areas(void) " isolated(anon):%lukB" " isolated(file):%lukB" " present:%lukB" + " managed:%lukB" " mlocked:%lukB" " dirty:%lukB" " writeback:%lukB" @@ -2432,12 +3220,13 @@ void show_free_areas(void) " pagetables:%lukB" " unstable:%lukB" " bounce:%lukB" + " free_cma:%lukB" " writeback_tmp:%lukB" " pages_scanned:%lu" " all_unreclaimable? %s" "\n", zone->name, - K(zone_nr_free_pages(zone)), + K(zone_page_state(zone, NR_FREE_PAGES)), K(min_wmark_pages(zone)), K(low_wmark_pages(zone)), K(high_wmark_pages(zone)), @@ -2449,6 +3238,7 @@ void show_free_areas(void) K(zone_page_state(zone, NR_ISOLATED_ANON)), K(zone_page_state(zone, NR_ISOLATED_FILE)), K(zone->present_pages), + K(zone->managed_pages), K(zone_page_state(zone, NR_MLOCK)), K(zone_page_state(zone, NR_FILE_DIRTY)), K(zone_page_state(zone, NR_WRITEBACK)), @@ -2461,9 +3251,10 @@ void show_free_areas(void) K(zone_page_state(zone, NR_PAGETABLE)), K(zone_page_state(zone, NR_UNSTABLE_NFS)), K(zone_page_state(zone, NR_BOUNCE)), + K(zone_page_state(zone, NR_FREE_CMA_PAGES)), K(zone_page_state(zone, NR_WRITEBACK_TEMP)), zone->pages_scanned, - (zone->all_unreclaimable ? "yes" : "no") + (!zone_reclaimable(zone) ? "yes" : "no") ); printk("lowmem_reserve[]:"); for (i = 0; i < MAX_NR_ZONES; i++) @@ -2472,22 +3263,39 @@ void show_free_areas(void) } for_each_populated_zone(zone) { - unsigned long nr[MAX_ORDER], flags, order, total = 0; + unsigned long nr[MAX_ORDER], flags, order, total = 0; + unsigned char types[MAX_ORDER]; + if (skip_free_areas_node(filter, zone_to_nid(zone))) + continue; show_node(zone); printk("%s: ", zone->name); spin_lock_irqsave(&zone->lock, flags); for (order = 0; order < MAX_ORDER; order++) { - nr[order] = zone->free_area[order].nr_free; + struct free_area *area = &zone->free_area[order]; + int type; + + nr[order] = area->nr_free; total += nr[order] << order; + + types[order] = 0; + for (type = 0; type < MIGRATE_TYPES; type++) { + if (!list_empty(&area->free_list[type])) + types[order] |= 1 << type; + } } spin_unlock_irqrestore(&zone->lock, flags); - for (order = 0; order < MAX_ORDER; order++) + for (order = 0; order < MAX_ORDER; order++) { printk("%lu*%lukB ", nr[order], K(1UL) << order); + if (nr[order]) + show_migration_types(types[order]); + } printk("= %lukB\n", K(total)); } + hugetlb_show_meminfo(); + printk("%ld total pagecache pages\n", global_page_state(NR_FILE_PAGES)); show_swap_cache_info(); @@ -2505,12 +3313,10 @@ static void zoneref_set_zone(struct zone *zone, struct zoneref *zoneref) * Add all populated zones of a node to the zonelist. */ static int build_zonelists_node(pg_data_t *pgdat, struct zonelist *zonelist, - int nr_zones, enum zone_type zone_type) + int nr_zones) { struct zone *zone; - - BUG_ON(zone_type >= MAX_NR_ZONES); - zone_type++; + enum zone_type zone_type = MAX_NR_ZONES; do { zone_type--; @@ -2520,8 +3326,8 @@ static int build_zonelists_node(pg_data_t *pgdat, struct zonelist *zonelist, &zonelist->_zonerefs[nr_zones++]); check_highest_zone(zone_type); } - } while (zone_type); + return nr_zones; } @@ -2580,16 +3386,23 @@ static int __parse_numa_zonelist_order(char *s) static __init int setup_numa_zonelist_order(char *s) { - if (s) - return __parse_numa_zonelist_order(s); - return 0; + int ret; + + if (!s) + return 0; + + ret = __parse_numa_zonelist_order(s); + if (ret == 0) + strlcpy(numa_zonelist_order, s, NUMA_ZONELIST_ORDER_LEN); + + return ret; } early_param("numa_zonelist_order", setup_numa_zonelist_order); /* * sysctl handler for numa_zonelist_order */ -int numa_zonelist_order_handler(ctl_table *table, int write, +int numa_zonelist_order_handler(struct ctl_table *table, int write, void __user *buffer, size_t *length, loff_t *ppos) { @@ -2598,23 +3411,30 @@ int numa_zonelist_order_handler(ctl_table *table, int write, static DEFINE_MUTEX(zl_order_mutex); mutex_lock(&zl_order_mutex); - if (write) - strcpy(saved_string, (char*)table->data); + if (write) { + if (strlen((char *)table->data) >= NUMA_ZONELIST_ORDER_LEN) { + ret = -EINVAL; + goto out; + } + strcpy(saved_string, (char *)table->data); + } ret = proc_dostring(table, write, buffer, length, ppos); if (ret) goto out; if (write) { int oldval = user_zonelist_order; - if (__parse_numa_zonelist_order((char*)table->data)) { + + ret = __parse_numa_zonelist_order((char *)table->data); + if (ret) { /* * bogus value. restore saved string */ - strncpy((char*)table->data, saved_string, + strncpy((char *)table->data, saved_string, NUMA_ZONELIST_ORDER_LEN); user_zonelist_order = oldval; } else if (oldval != user_zonelist_order) { mutex_lock(&zonelists_mutex); - build_all_zonelists(NULL); + build_all_zonelists(NULL, NULL); mutex_unlock(&zonelists_mutex); } } @@ -2645,7 +3465,7 @@ static int find_next_best_node(int node, nodemask_t *used_node_mask) { int n, val; int min_val = INT_MAX; - int best_node = -1; + int best_node = NUMA_NO_NODE; const struct cpumask *tmp = cpumask_of_node(0); /* Use the local node if we haven't already */ @@ -2654,7 +3474,7 @@ static int find_next_best_node(int node, nodemask_t *used_node_mask) return node; } - for_each_node_state(n, N_HIGH_MEMORY) { + for_each_node_state(n, N_MEMORY) { /* Don't want a node to appear more than once */ if (node_isset(n, *used_node_mask)) @@ -2701,8 +3521,7 @@ static void build_zonelists_in_node_order(pg_data_t *pgdat, int node) zonelist = &pgdat->node_zonelists[0]; for (j = 0; zonelist->_zonerefs[j].zone != NULL; j++) ; - j = build_zonelists_node(NODE_DATA(node), zonelist, j, - MAX_NR_ZONES - 1); + j = build_zonelists_node(NODE_DATA(node), zonelist, j); zonelist->_zonerefs[j].zone = NULL; zonelist->_zonerefs[j].zone_idx = 0; } @@ -2716,7 +3535,7 @@ static void build_thisnode_zonelists(pg_data_t *pgdat) struct zonelist *zonelist; zonelist = &pgdat->node_zonelists[1]; - j = build_zonelists_node(pgdat, zonelist, 0, MAX_NR_ZONES - 1); + j = build_zonelists_node(pgdat, zonelist, 0); zonelist->_zonerefs[j].zone = NULL; zonelist->_zonerefs[j].zone_idx = 0; } @@ -2756,11 +3575,11 @@ static void build_zonelists_in_zone_order(pg_data_t *pgdat, int nr_nodes) static int default_zonelist_order(void) { int nid, zone_type; - unsigned long low_kmem_size,total_size; + unsigned long low_kmem_size, total_size; struct zone *z; int average_size; /* - * ZONE_DMA and ZONE_DMA32 can be very small area in the system. + * ZONE_DMA and ZONE_DMA32 can be very small area in the system. * If they are really small and used heavily, the system can fall * into OOM very easily. * This function detect ZONE_DMA/DMA32 size and configures zone order. @@ -2773,8 +3592,8 @@ static int default_zonelist_order(void) z = &NODE_DATA(nid)->node_zones[zone_type]; if (populated_zone(z)) { if (zone_type < ZONE_NORMAL) - low_kmem_size += z->present_pages; - total_size += z->present_pages; + low_kmem_size += z->managed_pages; + total_size += z->managed_pages; } else if (zone_type == ZONE_NORMAL) { /* * If any node has only lowmem, then node order @@ -2792,11 +3611,11 @@ static int default_zonelist_order(void) return ZONELIST_ORDER_NODE; /* * look into each node's config. - * If there is a node whose DMA/DMA32 memory is very big area on - * local memory, NODE_ORDER may be suitable. - */ + * If there is a node whose DMA/DMA32 memory is very big area on + * local memory, NODE_ORDER may be suitable. + */ average_size = total_size / - (nodes_weight(node_states[N_HIGH_MEMORY]) + 1); + (nodes_weight(node_states[N_MEMORY]) + 1); for_each_online_node(nid) { low_kmem_size = 0; total_size = 0; @@ -2850,21 +3669,13 @@ static void build_zonelists(pg_data_t *pgdat) j = 0; while ((node = find_next_best_node(local_node, &used_mask)) >= 0) { - int distance = node_distance(local_node, node); - - /* - * If another node is sufficiently far away then it is better - * to reclaim pages in a zone before going off node. - */ - if (distance > RECLAIM_DISTANCE) - zone_reclaim_mode = 1; - /* * We don't want to pressure a particular node. * So adding penalty to the first node in same * distance group to make it round-robin. */ - if (distance != node_distance(local_node, prev_node)) + if (node_distance(local_node, node) != + node_distance(local_node, prev_node)) node_load[node] = load; prev_node = node; @@ -2932,7 +3743,7 @@ static void build_zonelists(pg_data_t *pgdat) local_node = pgdat->node_id; zonelist = &pgdat->node_zonelists[0]; - j = build_zonelists_node(pgdat, zonelist, 0, MAX_NR_ZONES - 1); + j = build_zonelists_node(pgdat, zonelist, 0); /* * Now we build the zonelist so that it contains the zones @@ -2945,14 +3756,12 @@ static void build_zonelists(pg_data_t *pgdat) for (node = local_node + 1; node < MAX_NUMNODES; node++) { if (!node_online(node)) continue; - j = build_zonelists_node(NODE_DATA(node), zonelist, j, - MAX_NR_ZONES - 1); + j = build_zonelists_node(NODE_DATA(node), zonelist, j); } for (node = 0; node < local_node; node++) { if (!node_online(node)) continue; - j = build_zonelists_node(NODE_DATA(node), zonelist, j, - MAX_NR_ZONES - 1); + j = build_zonelists_node(NODE_DATA(node), zonelist, j); } zonelist->_zonerefs[j].zone = NULL; @@ -2993,14 +3802,21 @@ static void setup_zone_pageset(struct zone *zone); DEFINE_MUTEX(zonelists_mutex); /* return values int ....just for stop_machine() */ -static __init_refok int __build_all_zonelists(void *data) +static int __build_all_zonelists(void *data) { int nid; int cpu; + pg_data_t *self = data; #ifdef CONFIG_NUMA memset(node_load, 0, sizeof(node_load)); #endif + + 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); @@ -3008,14 +3824,6 @@ static __init_refok int __build_all_zonelists(void *data) build_zonelist_cache(pgdat); } -#ifdef CONFIG_MEMORY_HOTPLUG - /* Setup real pagesets for the new zone */ - if (data) { - struct zone *zone = data; - setup_zone_pageset(zone); - } -#endif - /* * Initialize the boot_pagesets that are going to be used * for bootstrapping processors. The real pagesets for @@ -3053,7 +3861,7 @@ static __init_refok int __build_all_zonelists(void *data) * Called with zonelists_mutex held always * unless system_state == SYSTEM_BOOTING. */ -void build_all_zonelists(void *data) +void __ref build_all_zonelists(pg_data_t *pgdat, struct zone *zone) { set_zonelist_order(); @@ -3062,9 +3870,13 @@ void build_all_zonelists(void *data) mminit_verify_zonelist(); cpuset_init_current_mems_allowed(); } else { +#ifdef CONFIG_MEMORY_HOTPLUG + if (zone) + setup_zone_pageset(zone); +#endif /* we have to stop all cpus to guarantee there is no user of zonelist */ - stop_machine(__build_all_zonelists, data, NULL); + stop_machine(__build_all_zonelists, pgdat, NULL); /* cpuset refresh routine should be here */ } vm_total_pages = nr_free_pagecache_pages(); @@ -3157,7 +3969,19 @@ static inline unsigned long wait_table_bits(unsigned long size) return ffz(~size); } -#define LONG_ALIGN(x) (((x)+(sizeof(long))-1)&~((sizeof(long))-1)) +/* + * 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 @@ -3168,14 +3992,21 @@ static inline unsigned long wait_table_bits(unsigned long size) */ static void setup_zone_migrate_reserve(struct zone *zone) { - unsigned long start_pfn, pfn, end_pfn; + 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 */ + /* + * 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 = start_pfn + zone->spanned_pages; + 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; @@ -3187,6 +4018,12 @@ static void setup_zone_migrate_reserve(struct zone *zone) * 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)) @@ -3197,24 +4034,39 @@ static void setup_zone_migrate_reserve(struct zone *zone) if (page_to_nid(page) != zone_to_nid(zone)) continue; - /* Blocks with reserved pages will never free, skip them. */ - if (PageReserved(page)) - continue; - block_migratetype = get_pageblock_migratetype(page); - /* If this block is reserved, account for it */ - if (reserve > 0 && block_migratetype == MIGRATE_RESERVE) { - reserve--; - continue; - } + /* 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; - /* Suitable for reserving if this block is movable */ - if (reserve > 0 && block_migratetype == MIGRATE_MOVABLE) { - set_pageblock_migratetype(page, MIGRATE_RESERVE); - move_freepages_block(zone, page, MIGRATE_RESERVE); - reserve--; - 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; } /* @@ -3261,7 +4113,8 @@ void __meminit memmap_init_zone(unsigned long size, int nid, unsigned long zone, set_page_links(page, zone, nid, pfn); mminit_verify_page_links(page, zone, nid, pfn); init_page_count(page); - reset_page_mapcount(page); + page_mapcount_reset(page); + page_cpupid_reset_last(page); SetPageReserved(page); /* * Mark the block movable so that blocks are reserved for @@ -3278,7 +4131,7 @@ void __meminit memmap_init_zone(unsigned long size, int nid, unsigned long zone, * pfn out of zone. */ if ((z->zone_start_pfn <= pfn) - && (pfn < z->zone_start_pfn + z->spanned_pages) + && (pfn < zone_end_pfn(z)) && !(pfn & (pageblock_nr_pages - 1))) set_pageblock_migratetype(page, MIGRATE_MOVABLE); @@ -3293,7 +4146,7 @@ void __meminit memmap_init_zone(unsigned long size, int nid, unsigned long zone, static void __meminit zone_init_free_lists(struct zone *zone) { - int order, t; + unsigned int order, t; for_each_migratetype_order(order, t) { INIT_LIST_HEAD(&zone->free_area[order].free_list[t]); zone->free_area[order].nr_free = 0; @@ -3316,7 +4169,7 @@ static int zone_batchsize(struct zone *zone) * * OK, so we don't know how big the cache is. So guess. */ - batch = zone->present_pages / 1024; + batch = zone->managed_pages / 1024; if (batch * PAGE_SIZE > 512 * 1024) batch = (512 * 1024) / PAGE_SIZE; batch /= 4; /* We effectively *= 4 below */ @@ -3355,7 +4208,40 @@ static int zone_batchsize(struct zone *zone) #endif } -static void setup_pageset(struct per_cpu_pageset *p, unsigned long batch) +/* + * pcp->high and pcp->batch values are related and dependent on one another: + * ->batch must never be higher then ->high. + * The following function updates them in a safe manner without read side + * locking. + * + * Any new users of pcp->batch and pcp->high should ensure they can cope with + * those fields changing asynchronously (acording the the above rule). + * + * mutex_is_locked(&pcp_batch_high_lock) required when calling this function + * outside of boot time (or some other assurance that no concurrent updaters + * exist). + */ +static void pageset_update(struct per_cpu_pages *pcp, unsigned long high, + unsigned long batch) +{ + /* start with a fail safe value for batch */ + pcp->batch = 1; + smp_wmb(); + + /* Update high, then batch, in order */ + pcp->high = high; + smp_wmb(); + + pcp->batch = batch; +} + +/* a companion to pageset_set_high() */ +static void pageset_set_batch(struct per_cpu_pageset *p, unsigned long batch) +{ + pageset_update(&p->pcp, 6 * batch, max(1UL, 1 * batch)); +} + +static void pageset_init(struct per_cpu_pageset *p) { struct per_cpu_pages *pcp; int migratetype; @@ -3364,45 +4250,55 @@ static void setup_pageset(struct per_cpu_pageset *p, unsigned long batch) pcp = &p->pcp; pcp->count = 0; - pcp->high = 6 * batch; - pcp->batch = max(1UL, 1 * batch); for (migratetype = 0; migratetype < MIGRATE_PCPTYPES; migratetype++) INIT_LIST_HEAD(&pcp->lists[migratetype]); } +static void setup_pageset(struct per_cpu_pageset *p, unsigned long batch) +{ + pageset_init(p); + pageset_set_batch(p, batch); +} + /* - * setup_pagelist_highmark() sets the high water mark for hot per_cpu_pagelist + * pageset_set_high() sets the high water mark for hot per_cpu_pagelist * to the value high for the pageset p. */ - -static void setup_pagelist_highmark(struct per_cpu_pageset *p, +static void pageset_set_high(struct per_cpu_pageset *p, unsigned long high) { - struct per_cpu_pages *pcp; + unsigned long batch = max(1UL, high / 4); + if ((high / 4) > (PAGE_SHIFT * 8)) + batch = PAGE_SHIFT * 8; - pcp = &p->pcp; - pcp->high = high; - pcp->batch = max(1UL, high/4); - if ((high/4) > (PAGE_SHIFT * 8)) - pcp->batch = PAGE_SHIFT * 8; + pageset_update(&p->pcp, high, batch); } -static __meminit void setup_zone_pageset(struct zone *zone) +static void pageset_set_high_and_batch(struct zone *zone, + struct per_cpu_pageset *pcp) { - int cpu; - - zone->pageset = alloc_percpu(struct per_cpu_pageset); + if (percpu_pagelist_fraction) + pageset_set_high(pcp, + (zone->managed_pages / + percpu_pagelist_fraction)); + else + pageset_set_batch(pcp, zone_batchsize(zone)); +} - for_each_possible_cpu(cpu) { - struct per_cpu_pageset *pcp = per_cpu_ptr(zone->pageset, cpu); +static void __meminit zone_pageset_init(struct zone *zone, int cpu) +{ + struct per_cpu_pageset *pcp = per_cpu_ptr(zone->pageset, cpu); - setup_pageset(pcp, zone_batchsize(zone)); + pageset_init(pcp); + pageset_set_high_and_batch(zone, pcp); +} - if (percpu_pagelist_fraction) - setup_pagelist_highmark(pcp, - (zone->present_pages / - percpu_pagelist_fraction)); - } +static void __meminit setup_zone_pageset(struct zone *zone) +{ + int cpu; + zone->pageset = alloc_percpu(struct per_cpu_pageset); + for_each_possible_cpu(cpu) + zone_pageset_init(zone, cpu); } /* @@ -3421,7 +4317,6 @@ static noinline __init_refok int zone_wait_table_init(struct zone *zone, unsigned long zone_size_pages) { int i; - struct pglist_data *pgdat = zone->zone_pgdat; size_t alloc_size; /* @@ -3437,7 +4332,8 @@ int zone_wait_table_init(struct zone *zone, unsigned long zone_size_pages) if (!slab_is_available()) { zone->wait_table = (wait_queue_head_t *) - alloc_bootmem_node(pgdat, alloc_size); + memblock_virt_alloc_node_nopanic( + alloc_size, zone->zone_pgdat->node_id); } else { /* * This case means that a zone whose size was 0 gets new memory @@ -3454,38 +4350,12 @@ int zone_wait_table_init(struct zone *zone, unsigned long zone_size_pages) if (!zone->wait_table) return -ENOMEM; - for(i = 0; i < zone->wait_table_hash_nr_entries; ++i) + for (i = 0; i < zone->wait_table_hash_nr_entries; ++i) init_waitqueue_head(zone->wait_table + i); return 0; } -static int __zone_pcp_update(void *data) -{ - struct zone *zone = data; - int cpu; - unsigned long batch = zone_batchsize(zone), flags; - - for_each_possible_cpu(cpu) { - struct per_cpu_pageset *pset; - struct per_cpu_pages *pcp; - - pset = per_cpu_ptr(zone->pageset, cpu); - pcp = &pset->pcp; - - local_irq_save(flags); - free_pcppages_bulk(zone, pcp->count, pcp); - setup_pageset(pset, batch); - local_irq_restore(flags); - } - return 0; -} - -void zone_pcp_update(struct zone *zone) -{ - stop_machine(__zone_pcp_update, zone, NULL); -} - static __meminit void zone_pcp_init(struct zone *zone) { /* @@ -3495,13 +4365,13 @@ static __meminit void zone_pcp_init(struct zone *zone) */ zone->pageset = &boot_pageset; - if (zone->present_pages) + if (populated_zone(zone)) printk(KERN_DEBUG " %s zone: %lu pages, LIFO batch:%u\n", zone->name, zone->present_pages, zone_batchsize(zone)); } -__meminit int init_currently_empty_zone(struct zone *zone, +int __meminit init_currently_empty_zone(struct zone *zone, unsigned long zone_start_pfn, unsigned long size, enum memmap_context context) @@ -3526,55 +4396,33 @@ __meminit int init_currently_empty_zone(struct zone *zone, return 0; } -#ifdef CONFIG_ARCH_POPULATES_NODE_MAP -/* - * Basic iterator support. Return the first range of PFNs for a node - * Note: nid == MAX_NUMNODES returns first region regardless of node - */ -static int __meminit first_active_region_index_in_nid(int nid) -{ - int i; - - for (i = 0; i < nr_nodemap_entries; i++) - if (nid == MAX_NUMNODES || early_node_map[i].nid == nid) - return i; - - return -1; -} - -/* - * Basic iterator support. Return the next active range of PFNs for a node - * Note: nid == MAX_NUMNODES returns next region regardless of node - */ -static int __meminit next_active_region_index_in_nid(int index, int nid) -{ - for (index = index + 1; index < nr_nodemap_entries; index++) - if (nid == MAX_NUMNODES || early_node_map[index].nid == nid) - return index; - - return -1; -} - +#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. - * Architectures may implement their own version but if add_active_range() - * was used and there are no special requirements, this is a convenient - * alternative */ int __meminit __early_pfn_to_nid(unsigned long pfn) { - int i; + 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; - for (i = 0; i < nr_nodemap_entries; i++) { - unsigned long start_pfn = early_node_map[i].start_pfn; - unsigned long end_pfn = early_node_map[i].end_pfn; + if (last_start_pfn <= pfn && pfn < last_end_pfn) + return last_nid; - if (start_pfn <= pfn && pfn < end_pfn) - return early_node_map[i].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; } - /* This is a memory hole */ - return -1; + + return nid; } #endif /* CONFIG_HAVE_ARCH_EARLY_PFN_TO_NID */ @@ -3601,148 +4449,45 @@ bool __meminit early_pfn_in_nid(unsigned long pfn, int node) } #endif -/* Basic iterator support to walk early_node_map[] */ -#define for_each_active_range_index_in_nid(i, nid) \ - for (i = first_active_region_index_in_nid(nid); i != -1; \ - i = next_active_region_index_in_nid(i, nid)) - /** - * free_bootmem_with_active_regions - Call free_bootmem_node for each active range + * 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. - * @max_low_pfn: The highest PFN that will be passed to free_bootmem_node + * @max_low_pfn: The highest PFN that will be passed to memblock_free_early_nid * - * If an architecture guarantees that all ranges registered with - * add_active_ranges() contain no holes and may be freed, this - * this function may be used instead of calling free_bootmem() manually. + * If an architecture guarantees that all ranges registered contain no holes + * and may be freed, this this function may be used instead of calling + * memblock_free_early_nid() manually. */ -void __init free_bootmem_with_active_regions(int nid, - unsigned long max_low_pfn) -{ - int i; - - for_each_active_range_index_in_nid(i, nid) { - unsigned long size_pages = 0; - unsigned long end_pfn = early_node_map[i].end_pfn; - - if (early_node_map[i].start_pfn >= max_low_pfn) - continue; - - if (end_pfn > max_low_pfn) - end_pfn = max_low_pfn; - - size_pages = end_pfn - early_node_map[i].start_pfn; - free_bootmem_node(NODE_DATA(early_node_map[i].nid), - PFN_PHYS(early_node_map[i].start_pfn), - size_pages << PAGE_SHIFT); - } -} - -#ifdef CONFIG_HAVE_MEMBLOCK -u64 __init find_memory_core_early(int nid, u64 size, u64 align, - u64 goal, u64 limit) +void __init free_bootmem_with_active_regions(int nid, unsigned long max_low_pfn) { - int i; - - /* Need to go over early_node_map to find out good range for node */ - for_each_active_range_index_in_nid(i, nid) { - u64 addr; - u64 ei_start, ei_last; - u64 final_start, final_end; - - ei_last = early_node_map[i].end_pfn; - ei_last <<= PAGE_SHIFT; - ei_start = early_node_map[i].start_pfn; - ei_start <<= PAGE_SHIFT; - - final_start = max(ei_start, goal); - final_end = min(ei_last, limit); - - if (final_start >= final_end) - continue; - - addr = memblock_find_in_range(final_start, final_end, size, align); - - if (addr == MEMBLOCK_ERROR) - continue; - - return addr; - } + unsigned long start_pfn, end_pfn; + int i, this_nid; - return MEMBLOCK_ERROR; -} -#endif + for_each_mem_pfn_range(i, nid, &start_pfn, &end_pfn, &this_nid) { + start_pfn = min(start_pfn, max_low_pfn); + end_pfn = min(end_pfn, max_low_pfn); -int __init add_from_early_node_map(struct range *range, int az, - int nr_range, int nid) -{ - int i; - u64 start, end; - - /* need to go over early_node_map to find out good range for node */ - for_each_active_range_index_in_nid(i, nid) { - start = early_node_map[i].start_pfn; - end = early_node_map[i].end_pfn; - nr_range = add_range(range, az, nr_range, start, end); + if (start_pfn < end_pfn) + memblock_free_early_nid(PFN_PHYS(start_pfn), + (end_pfn - start_pfn) << PAGE_SHIFT, + this_nid); } - return nr_range; } -#ifdef CONFIG_NO_BOOTMEM -void * __init __alloc_memory_core_early(int nid, u64 size, u64 align, - u64 goal, u64 limit) -{ - void *ptr; - u64 addr; - - if (limit > memblock.current_limit) - limit = memblock.current_limit; - - addr = find_memory_core_early(nid, size, align, goal, limit); - - if (addr == MEMBLOCK_ERROR) - return NULL; - - ptr = phys_to_virt(addr); - memset(ptr, 0, size); - memblock_x86_reserve_range(addr, addr + size, "BOOTMEM"); - /* - * The min_count is set to 0 so that bootmem allocated blocks - * are never reported as leaks. - */ - kmemleak_alloc(ptr, size, 0, 0); - return ptr; -} -#endif - - -void __init work_with_active_regions(int nid, work_fn_t work_fn, void *data) -{ - int i; - int ret; - - for_each_active_range_index_in_nid(i, nid) { - ret = work_fn(early_node_map[i].start_pfn, - early_node_map[i].end_pfn, data); - if (ret) - break; - } -} /** * sparse_memory_present_with_active_regions - Call memory_present for each active range * @nid: The node to call memory_present for. If MAX_NUMNODES, all nodes will be used. * - * If an architecture guarantees that all ranges registered with - * add_active_ranges() contain no holes and may be freed, this - * function may be used instead of calling memory_present() manually. + * If an architecture guarantees that all ranges registered contain no holes and may + * be freed, this function may be used instead of calling memory_present() manually. */ void __init sparse_memory_present_with_active_regions(int nid) { - int i; + unsigned long start_pfn, end_pfn; + int i, this_nid; - for_each_active_range_index_in_nid(i, nid) - memory_present(early_node_map[i].nid, - early_node_map[i].start_pfn, - early_node_map[i].end_pfn); + for_each_mem_pfn_range(i, nid, &start_pfn, &end_pfn, &this_nid) + memory_present(this_nid, start_pfn, end_pfn); } /** @@ -3752,20 +4497,22 @@ void __init sparse_memory_present_with_active_regions(int nid) * @end_pfn: Passed by reference. On return, it will have the node end_pfn. * * It returns the start and end page frame of a node based on information - * provided by an arch calling add_active_range(). If called for a node + * provided by memblock_set_node(). If called for a node * with no available memory, a warning is printed and the start and end * PFNs will be 0. */ void __meminit get_pfn_range_for_nid(unsigned int nid, unsigned long *start_pfn, unsigned long *end_pfn) { + unsigned long this_start_pfn, this_end_pfn; int i; + *start_pfn = -1UL; *end_pfn = 0; - for_each_active_range_index_in_nid(i, nid) { - *start_pfn = min(*start_pfn, early_node_map[i].start_pfn); - *end_pfn = max(*end_pfn, early_node_map[i].end_pfn); + for_each_mem_pfn_range(i, nid, &this_start_pfn, &this_end_pfn, NULL) { + *start_pfn = min(*start_pfn, this_start_pfn); + *end_pfn = max(*end_pfn, this_end_pfn); } if (*start_pfn == -1UL) @@ -3795,7 +4542,7 @@ static void __init find_usable_zone_for_movable(void) /* * The zone ranges provided by the architecture do not include ZONE_MOVABLE - * because it is sized independant of architecture. Unlike the other zones, + * because it is sized independent of architecture. Unlike the other zones, * the starting point for ZONE_MOVABLE is not fixed. It may be different * in each node depending on the size of each node and how evenly kernelcore * is distributed. This helper function adjusts the zone ranges @@ -3835,13 +4582,13 @@ static void __meminit adjust_zone_range_for_zone_movable(int nid, */ static unsigned long __meminit zone_spanned_pages_in_node(int nid, unsigned long zone_type, + unsigned long node_start_pfn, + unsigned long node_end_pfn, unsigned long *ignored) { - unsigned long node_start_pfn, node_end_pfn; unsigned long zone_start_pfn, zone_end_pfn; - /* Get the start and end of the node and zone */ - get_pfn_range_for_nid(nid, &node_start_pfn, &node_end_pfn); + /* 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]; adjust_zone_range_for_zone_movable(nid, zone_type, @@ -3868,46 +4615,16 @@ unsigned long __meminit __absent_pages_in_range(int nid, unsigned long range_start_pfn, unsigned long range_end_pfn) { - int i = 0; - unsigned long prev_end_pfn = 0, hole_pages = 0; - unsigned long start_pfn; - - /* Find the end_pfn of the first active range of pfns in the node */ - i = first_active_region_index_in_nid(nid); - if (i == -1) - return 0; - - prev_end_pfn = min(early_node_map[i].start_pfn, range_end_pfn); - - /* Account for ranges before physical memory on this node */ - if (early_node_map[i].start_pfn > range_start_pfn) - hole_pages = prev_end_pfn - range_start_pfn; - - /* Find all holes for the zone within the node */ - for (; i != -1; i = next_active_region_index_in_nid(i, nid)) { - - /* No need to continue if prev_end_pfn is outside the zone */ - if (prev_end_pfn >= range_end_pfn) - break; - - /* Make sure the end of the zone is not within the hole */ - start_pfn = min(early_node_map[i].start_pfn, range_end_pfn); - prev_end_pfn = max(prev_end_pfn, range_start_pfn); + unsigned long nr_absent = range_end_pfn - range_start_pfn; + unsigned long start_pfn, end_pfn; + int i; - /* Update the hole size cound and move on */ - if (start_pfn > range_start_pfn) { - BUG_ON(prev_end_pfn > start_pfn); - hole_pages += start_pfn - prev_end_pfn; - } - prev_end_pfn = early_node_map[i].end_pfn; + for_each_mem_pfn_range(i, nid, &start_pfn, &end_pfn, NULL) { + start_pfn = clamp(start_pfn, range_start_pfn, range_end_pfn); + end_pfn = clamp(end_pfn, range_start_pfn, range_end_pfn); + nr_absent -= end_pfn - start_pfn; } - - /* Account for ranges past physical memory on this node */ - if (range_end_pfn > prev_end_pfn) - hole_pages += range_end_pfn - - max(range_start_pfn, prev_end_pfn); - - return hole_pages; + return nr_absent; } /** @@ -3926,16 +4643,16 @@ unsigned long __init absent_pages_in_range(unsigned long start_pfn, /* Return the number of page frames in holes in a zone on a node */ static unsigned long __meminit zone_absent_pages_in_node(int nid, unsigned long zone_type, + unsigned long node_start_pfn, + unsigned long node_end_pfn, unsigned long *ignored) { - unsigned long node_start_pfn, node_end_pfn; + unsigned long zone_low = arch_zone_lowest_possible_pfn[zone_type]; + unsigned long zone_high = arch_zone_highest_possible_pfn[zone_type]; unsigned long zone_start_pfn, zone_end_pfn; - get_pfn_range_for_nid(nid, &node_start_pfn, &node_end_pfn); - zone_start_pfn = max(arch_zone_lowest_possible_pfn[zone_type], - node_start_pfn); - zone_end_pfn = min(arch_zone_highest_possible_pfn[zone_type], - node_end_pfn); + 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, @@ -3943,9 +4660,11 @@ static unsigned long __meminit zone_absent_pages_in_node(int nid, return __absent_pages_in_range(nid, zone_start_pfn, zone_end_pfn); } -#else +#else /* CONFIG_HAVE_MEMBLOCK_NODE_MAP */ static inline unsigned long __meminit zone_spanned_pages_in_node(int nid, unsigned long zone_type, + unsigned long node_start_pfn, + unsigned long node_end_pfn, unsigned long *zones_size) { return zones_size[zone_type]; @@ -3953,6 +4672,8 @@ static inline unsigned long __meminit zone_spanned_pages_in_node(int nid, static inline unsigned long __meminit zone_absent_pages_in_node(int nid, unsigned long zone_type, + unsigned long node_start_pfn, + unsigned long node_end_pfn, unsigned long *zholes_size) { if (!zholes_size) @@ -3961,24 +4682,30 @@ static inline unsigned long __meminit zone_absent_pages_in_node(int nid, return zholes_size[zone_type]; } -#endif +#endif /* CONFIG_HAVE_MEMBLOCK_NODE_MAP */ static void __meminit calculate_node_totalpages(struct pglist_data *pgdat, - unsigned long *zones_size, unsigned long *zholes_size) + unsigned long node_start_pfn, + unsigned long node_end_pfn, + unsigned long *zones_size, + unsigned long *zholes_size) { unsigned long realtotalpages, totalpages = 0; enum zone_type i; for (i = 0; i < MAX_NR_ZONES; i++) totalpages += zone_spanned_pages_in_node(pgdat->node_id, i, - zones_size); + 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, - zholes_size); + node_start_pfn, node_end_pfn, + zholes_size); pgdat->node_present_pages = realtotalpages; printk(KERN_DEBUG "On node %d totalpages: %lu\n", pgdat->node_id, realtotalpages); @@ -3992,10 +4719,11 @@ static void __meminit calculate_node_totalpages(struct pglist_data *pgdat, * round what is now in bits to nearest long in bits, then return it in * bytes. */ -static unsigned long __init usemap_size(unsigned long zonesize) +static unsigned long __init usemap_size(unsigned long zone_start_pfn, unsigned long zonesize) { unsigned long usemapsize; + zonesize += zone_start_pfn & (pageblock_nr_pages-1); usemapsize = roundup(zonesize, pageblock_nr_pages); usemapsize = usemapsize >> pageblock_order; usemapsize *= NR_PAGEBLOCK_BITS; @@ -4005,39 +4733,42 @@ static unsigned long __init usemap_size(unsigned long zonesize) } static void __init setup_usemap(struct pglist_data *pgdat, - struct zone *zone, unsigned long zonesize) + struct zone *zone, + unsigned long zone_start_pfn, + unsigned long zonesize) { - unsigned long usemapsize = usemap_size(zonesize); + unsigned long usemapsize = usemap_size(zone_start_pfn, zonesize); zone->pageblock_flags = NULL; if (usemapsize) - zone->pageblock_flags = alloc_bootmem_node(pgdat, usemapsize); + zone->pageblock_flags = + memblock_virt_alloc_node_nopanic(usemapsize, + pgdat->node_id); } #else -static void inline setup_usemap(struct pglist_data *pgdat, - struct zone *zone, unsigned long zonesize) {} +static inline void setup_usemap(struct pglist_data *pgdat, struct zone *zone, + unsigned long zone_start_pfn, unsigned long zonesize) {} #endif /* CONFIG_SPARSEMEM */ #ifdef CONFIG_HUGETLB_PAGE_SIZE_VARIABLE -/* Return a sensible default order for the pageblock size. */ -static inline int pageblock_default_order(void) -{ - if (HPAGE_SHIFT > PAGE_SHIFT) - return HUGETLB_PAGE_ORDER; - - return MAX_ORDER-1; -} - /* Initialise the number of pages represented by NR_PAGEBLOCK_BITS */ -static inline void __init set_pageblock_order(unsigned int order) +void __paginginit set_pageblock_order(void) { + unsigned int order; + /* Check that pageblock_nr_pages has not already been setup */ if (pageblock_order) return; + if (HPAGE_SHIFT > PAGE_SHIFT) + order = HUGETLB_PAGE_ORDER; + else + order = MAX_ORDER - 1; + /* * Assume the largest contiguous order of interest is a huge page. - * This value may be variable depending on boot parameters on IA64 + * This value may be variable depending on boot parameters on IA64 and + * powerpc. */ pageblock_order = order; } @@ -4045,25 +4776,46 @@ static inline void __init set_pageblock_order(unsigned int order) /* * When CONFIG_HUGETLB_PAGE_SIZE_VARIABLE is not set, set_pageblock_order() - * and pageblock_default_order() are unused as pageblock_order is set - * at compile-time. See include/linux/pageblock-flags.h for the values of - * pageblock_order based on the kernel config + * is unused as pageblock_order is set at compile-time. See + * include/linux/pageblock-flags.h for the values of pageblock_order based on + * the kernel config */ -static inline int pageblock_default_order(unsigned int order) +void __paginginit set_pageblock_order(void) { - return MAX_ORDER-1; } -#define set_pageblock_order(x) do {} while (0) #endif /* CONFIG_HUGETLB_PAGE_SIZE_VARIABLE */ +static unsigned long __paginginit calc_memmap_size(unsigned long spanned_pages, + unsigned long present_pages) +{ + unsigned long pages = spanned_pages; + + /* + * Provide a more accurate estimation if there are holes within + * the zone and SPARSEMEM is in use. If there are holes within the + * zone, each populated memory region may cost us one or two extra + * memmap pages due to alignment because memmap pages for each + * populated regions may not naturally algined on page boundary. + * So the (present_pages >> 4) heuristic is a tradeoff for that. + */ + if (spanned_pages > present_pages + (present_pages >> 4) && + IS_ENABLED(CONFIG_SPARSEMEM)) + pages = present_pages; + + return PAGE_ALIGN(pages * sizeof(struct page)) >> PAGE_SHIFT; +} + /* * Set up the zone data structures: * - mark all pages reserved * - mark all memory queues empty * - clear the memory bitmaps + * + * 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) { enum zone_type j; @@ -4072,79 +4824,87 @@ static void __paginginit free_area_init_core(struct pglist_data *pgdat, int ret; pgdat_resize_init(pgdat); - pgdat->nr_zones = 0; +#ifdef CONFIG_NUMA_BALANCING + spin_lock_init(&pgdat->numabalancing_migrate_lock); + pgdat->numabalancing_migrate_nr_pages = 0; + pgdat->numabalancing_migrate_next_window = jiffies; +#endif init_waitqueue_head(&pgdat->kswapd_wait); - pgdat->kswapd_max_order = 0; + init_waitqueue_head(&pgdat->pfmemalloc_wait); pgdat_page_cgroup_init(pgdat); - + for (j = 0; j < MAX_NR_ZONES; j++) { struct zone *zone = pgdat->node_zones + j; - unsigned long size, realsize, memmap_pages; - enum lru_list l; + unsigned long size, realsize, freesize, memmap_pages; - size = zone_spanned_pages_in_node(nid, j, zones_size); - realsize = size - zone_absent_pages_in_node(nid, j, + 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); /* - * Adjust realsize so that it accounts for how much memory + * Adjust freesize so that it accounts for how much memory * is used by this zone for memmap. This affects the watermark * and per-cpu initialisations */ - memmap_pages = - PAGE_ALIGN(size * sizeof(struct page)) >> PAGE_SHIFT; - if (realsize >= memmap_pages) { - realsize -= memmap_pages; + memmap_pages = calc_memmap_size(size, realsize); + if (freesize >= memmap_pages) { + freesize -= memmap_pages; if (memmap_pages) printk(KERN_DEBUG " %s zone: %lu pages used for memmap\n", zone_names[j], memmap_pages); } else printk(KERN_WARNING - " %s zone: %lu pages exceeds realsize %lu\n", - zone_names[j], memmap_pages, realsize); + " %s zone: %lu pages exceeds freesize %lu\n", + zone_names[j], memmap_pages, freesize); /* Account for reserved pages */ - if (j == 0 && realsize > dma_reserve) { - realsize -= dma_reserve; + if (j == 0 && freesize > dma_reserve) { + freesize -= dma_reserve; printk(KERN_DEBUG " %s zone: %lu pages reserved\n", zone_names[0], dma_reserve); } if (!is_highmem_idx(j)) - nr_kernel_pages += realsize; - nr_all_pages += realsize; + nr_kernel_pages += freesize; + /* Charge for highmem memmap if there are enough kernel pages */ + else if (nr_kernel_pages > memmap_pages * 2) + 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. + * And all highmem pages will be managed by the buddy system. + */ + zone->managed_pages = is_highmem_idx(j) ? realsize : freesize; #ifdef CONFIG_NUMA zone->node = nid; - zone->min_unmapped_pages = (realsize*sysctl_min_unmapped_ratio) + zone->min_unmapped_pages = (freesize*sysctl_min_unmapped_ratio) / 100; - zone->min_slab_pages = (realsize * sysctl_min_slab_ratio) / 100; + zone->min_slab_pages = (freesize * sysctl_min_slab_ratio) / 100; #endif zone->name = zone_names[j]; spin_lock_init(&zone->lock); spin_lock_init(&zone->lru_lock); zone_seqlock_init(zone); zone->zone_pgdat = pgdat; - zone_pcp_init(zone); - for_each_lru(l) { - INIT_LIST_HEAD(&zone->lru[l].list); - zone->reclaim_stat.nr_saved_scan[l] = 0; - } - zone->reclaim_stat.recent_rotated[0] = 0; - zone->reclaim_stat.recent_rotated[1] = 0; - zone->reclaim_stat.recent_scanned[0] = 0; - zone->reclaim_stat.recent_scanned[1] = 0; - zap_zone_vm_stats(zone); - zone->flags = 0; + + /* For bootup, initialized properly in watermark setup */ + mod_zone_page_state(zone, NR_ALLOC_BATCH, zone->managed_pages); + + lruvec_init(&zone->lruvec); if (!size) continue; - set_pageblock_order(pageblock_default_order()); - setup_usemap(pgdat, zone, size); + set_pageblock_order(); + setup_usemap(pgdat, zone, zone_start_pfn, size); ret = init_currently_empty_zone(zone, zone_start_pfn, size, MEMMAP_EARLY); BUG_ON(ret); @@ -4171,12 +4931,13 @@ static void __init_refok alloc_node_mem_map(struct pglist_data *pgdat) * for the buddy allocator to function correctly. */ start = pgdat->node_start_pfn & ~(MAX_ORDER_NR_PAGES - 1); - end = pgdat->node_start_pfn + pgdat->node_spanned_pages; + end = pgdat_end_pfn(pgdat); end = ALIGN(end, MAX_ORDER_NR_PAGES); size = (end - start) * sizeof(struct page); map = alloc_remap(pgdat->node_id, size); if (!map) - map = alloc_bootmem_node(pgdat, size); + map = memblock_virt_alloc_node_nopanic(size, + pgdat->node_id); pgdat->node_mem_map = map + (pgdat->node_start_pfn - start); } #ifndef CONFIG_NEED_MULTIPLE_NODES @@ -4185,10 +4946,10 @@ 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_ARCH_POPULATES_NODE_MAP +#ifdef CONFIG_HAVE_MEMBLOCK_NODE_MAP if (page_to_pfn(mem_map) != pgdat->node_start_pfn) mem_map -= (pgdat->node_start_pfn - ARCH_PFN_OFFSET); -#endif /* CONFIG_ARCH_POPULATES_NODE_MAP */ +#endif /* CONFIG_HAVE_MEMBLOCK_NODE_MAP */ } #endif #endif /* CONFIG_FLAT_NODE_MEM_MAP */ @@ -4198,10 +4959,19 @@ void __paginginit free_area_init_node(int nid, unsigned long *zones_size, unsigned long node_start_pfn, unsigned long *zholes_size) { pg_data_t *pgdat = NODE_DATA(nid); + unsigned long start_pfn = 0; + unsigned long end_pfn = 0; + + /* pg_data_t should be reset to zero when it's allocated */ + WARN_ON(pgdat->nr_zones || pgdat->classzone_idx); pgdat->node_id = nid; pgdat->node_start_pfn = node_start_pfn; - calculate_node_totalpages(pgdat, zones_size, zholes_size); +#ifdef CONFIG_HAVE_MEMBLOCK_NODE_MAP + get_pfn_range_for_nid(nid, &start_pfn, &end_pfn); +#endif + calculate_node_totalpages(pgdat, start_pfn, end_pfn, + zones_size, zholes_size); alloc_node_mem_map(pgdat); #ifdef CONFIG_FLAT_NODE_MEM_MAP @@ -4210,16 +4980,17 @@ void __paginginit free_area_init_node(int nid, unsigned long *zones_size, (unsigned long)pgdat->node_mem_map); #endif - free_area_init_core(pgdat, zones_size, zholes_size); + free_area_init_core(pgdat, start_pfn, end_pfn, + zones_size, zholes_size); } -#ifdef CONFIG_ARCH_POPULATES_NODE_MAP +#ifdef CONFIG_HAVE_MEMBLOCK_NODE_MAP #if MAX_NUMNODES > 1 /* * Figure out the number of possible node ids. */ -static void __init setup_nr_node_ids(void) +void __init setup_nr_node_ids(void) { unsigned int node; unsigned int highest = 0; @@ -4228,185 +4999,67 @@ static void __init setup_nr_node_ids(void) highest = node; nr_node_ids = highest + 1; } -#else -static inline void setup_nr_node_ids(void) -{ -} #endif /** - * add_active_range - Register a range of PFNs backed by physical memory - * @nid: The node ID the range resides on - * @start_pfn: The start PFN of the available physical memory - * @end_pfn: The end PFN of the available physical memory + * node_map_pfn_alignment - determine the maximum internode alignment + * + * This function should be called after node map is populated and sorted. + * It calculates the maximum power of two alignment which can distinguish + * all the nodes. + * + * For example, if all nodes are 1GiB and aligned to 1GiB, the return value + * would indicate 1GiB alignment with (1 << (30 - PAGE_SHIFT)). If the + * nodes are shifted by 256MiB, 256MiB. Note that if only the last node is + * shifted, 1GiB is enough and this function will indicate so. + * + * This is used to test whether pfn -> nid mapping of the chosen memory + * model has fine enough granularity to avoid incorrect mapping for the + * populated node map. * - * These ranges are stored in an early_node_map[] and later used by - * free_area_init_nodes() to calculate zone sizes and holes. If the - * range spans a memory hole, it is up to the architecture to ensure - * the memory is not freed by the bootmem allocator. If possible - * the range being registered will be merged with existing ranges. + * Returns the determined alignment in pfn's. 0 if there is no alignment + * requirement (single node). */ -void __init add_active_range(unsigned int nid, unsigned long start_pfn, - unsigned long end_pfn) +unsigned long __init node_map_pfn_alignment(void) { - int i; - - mminit_dprintk(MMINIT_TRACE, "memory_register", - "Entering add_active_range(%d, %#lx, %#lx) " - "%d entries of %d used\n", - nid, start_pfn, end_pfn, - nr_nodemap_entries, MAX_ACTIVE_REGIONS); - - mminit_validate_memmodel_limits(&start_pfn, &end_pfn); + unsigned long accl_mask = 0, last_end = 0; + unsigned long start, end, mask; + int last_nid = -1; + int i, nid; - /* Merge with existing active regions if possible */ - for (i = 0; i < nr_nodemap_entries; i++) { - if (early_node_map[i].nid != nid) + for_each_mem_pfn_range(i, MAX_NUMNODES, &start, &end, &nid) { + if (!start || last_nid < 0 || last_nid == nid) { + last_nid = nid; + last_end = end; continue; - - /* Skip if an existing region covers this new one */ - if (start_pfn >= early_node_map[i].start_pfn && - end_pfn <= early_node_map[i].end_pfn) - return; - - /* Merge forward if suitable */ - if (start_pfn <= early_node_map[i].end_pfn && - end_pfn > early_node_map[i].end_pfn) { - early_node_map[i].end_pfn = end_pfn; - return; } - /* Merge backward if suitable */ - if (start_pfn < early_node_map[i].start_pfn && - end_pfn >= early_node_map[i].start_pfn) { - early_node_map[i].start_pfn = start_pfn; - return; - } - } - - /* Check that early_node_map is large enough */ - if (i >= MAX_ACTIVE_REGIONS) { - printk(KERN_CRIT "More than %d memory regions, truncating\n", - MAX_ACTIVE_REGIONS); - return; - } - - early_node_map[i].nid = nid; - early_node_map[i].start_pfn = start_pfn; - early_node_map[i].end_pfn = end_pfn; - nr_nodemap_entries = i + 1; -} - -/** - * remove_active_range - Shrink an existing registered range of PFNs - * @nid: The node id the range is on that should be shrunk - * @start_pfn: The new PFN of the range - * @end_pfn: The new PFN of the range - * - * i386 with NUMA use alloc_remap() to store a node_mem_map on a local node. - * The map is kept near the end physical page range that has already been - * registered. This function allows an arch to shrink an existing registered - * range. - */ -void __init remove_active_range(unsigned int nid, unsigned long start_pfn, - unsigned long end_pfn) -{ - int i, j; - int removed = 0; - - printk(KERN_DEBUG "remove_active_range (%d, %lu, %lu)\n", - nid, start_pfn, end_pfn); - - /* Find the old active region end and shrink */ - for_each_active_range_index_in_nid(i, nid) { - if (early_node_map[i].start_pfn >= start_pfn && - early_node_map[i].end_pfn <= end_pfn) { - /* clear it */ - early_node_map[i].start_pfn = 0; - early_node_map[i].end_pfn = 0; - removed = 1; - continue; - } - if (early_node_map[i].start_pfn < start_pfn && - early_node_map[i].end_pfn > start_pfn) { - unsigned long temp_end_pfn = early_node_map[i].end_pfn; - early_node_map[i].end_pfn = start_pfn; - if (temp_end_pfn > end_pfn) - add_active_range(nid, end_pfn, temp_end_pfn); - continue; - } - if (early_node_map[i].start_pfn >= start_pfn && - early_node_map[i].end_pfn > end_pfn && - early_node_map[i].start_pfn < end_pfn) { - early_node_map[i].start_pfn = end_pfn; - continue; - } - } - - if (!removed) - return; + /* + * Start with a mask granular enough to pin-point to the + * start pfn and tick off bits one-by-one until it becomes + * too coarse to separate the current node from the last. + */ + mask = ~((1 << __ffs(start)) - 1); + while (mask && last_end <= (start & (mask << 1))) + mask <<= 1; - /* remove the blank ones */ - for (i = nr_nodemap_entries - 1; i > 0; i--) { - if (early_node_map[i].nid != nid) - continue; - if (early_node_map[i].end_pfn) - continue; - /* we found it, get rid of it */ - for (j = i; j < nr_nodemap_entries - 1; j++) - memcpy(&early_node_map[j], &early_node_map[j+1], - sizeof(early_node_map[j])); - j = nr_nodemap_entries - 1; - memset(&early_node_map[j], 0, sizeof(early_node_map[j])); - nr_nodemap_entries--; + /* accumulate all internode masks */ + accl_mask |= mask; } -} - -/** - * remove_all_active_ranges - Remove all currently registered regions - * - * During discovery, it may be found that a table like SRAT is invalid - * and an alternative discovery method must be used. This function removes - * all currently registered regions. - */ -void __init remove_all_active_ranges(void) -{ - memset(early_node_map, 0, sizeof(early_node_map)); - nr_nodemap_entries = 0; -} - -/* Compare two active node_active_regions */ -static int __init cmp_node_active_region(const void *a, const void *b) -{ - struct node_active_region *arange = (struct node_active_region *)a; - struct node_active_region *brange = (struct node_active_region *)b; - - /* Done this way to avoid overflows */ - if (arange->start_pfn > brange->start_pfn) - return 1; - if (arange->start_pfn < brange->start_pfn) - return -1; - return 0; -} - -/* sort the node_map by start_pfn */ -void __init sort_node_map(void) -{ - sort(early_node_map, (size_t)nr_nodemap_entries, - sizeof(struct node_active_region), - cmp_node_active_region, NULL); + /* convert mask to number of pages */ + return ~accl_mask + 1; } /* Find the lowest pfn for a node */ static unsigned long __init find_min_pfn_for_node(int nid) { - int i; unsigned long min_pfn = ULONG_MAX; + unsigned long start_pfn; + int i; - /* Assuming a sorted map, the first range found has the starting pfn */ - for_each_active_range_index_in_nid(i, nid) - min_pfn = min(min_pfn, early_node_map[i].start_pfn); + for_each_mem_pfn_range(i, nid, &start_pfn, NULL, NULL) + min_pfn = min(min_pfn, start_pfn); if (min_pfn == ULONG_MAX) { printk(KERN_WARNING @@ -4421,7 +5074,7 @@ 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 - * add_active_range(). + * memblock_set_node(). */ unsigned long __init find_min_pfn_with_active_regions(void) { @@ -4431,21 +5084,22 @@ unsigned long __init find_min_pfn_with_active_regions(void) /* * early_calculate_totalpages() * Sum pages in active regions for movable zone. - * Populate N_HIGH_MEMORY for calculating usable_nodes. + * Populate N_MEMORY for calculating usable_nodes. */ static unsigned long __init early_calculate_totalpages(void) { - int i; unsigned long totalpages = 0; + unsigned long start_pfn, end_pfn; + int i, nid; + + for_each_mem_pfn_range(i, MAX_NUMNODES, &start_pfn, &end_pfn, &nid) { + unsigned long pages = end_pfn - start_pfn; - for (i = 0; i < nr_nodemap_entries; i++) { - unsigned long pages = early_node_map[i].end_pfn - - early_node_map[i].start_pfn; totalpages += pages; if (pages) - node_set_state(early_node_map[i].nid, N_HIGH_MEMORY); + node_set_state(nid, N_MEMORY); } - return totalpages; + return totalpages; } /* @@ -4454,18 +5108,42 @@ static unsigned long __init early_calculate_totalpages(void) * memory. When they don't, some nodes will have more kernelcore than * others */ -static void __init find_zone_movable_pfns_for_nodes(unsigned long *movable_pfn) +static void __init find_zone_movable_pfns_for_nodes(void) { int i, nid; unsigned long usable_startpfn; unsigned long kernelcore_node, kernelcore_remaining; /* save the state before borrow the nodemask */ - nodemask_t saved_node_state = node_states[N_HIGH_MEMORY]; + nodemask_t saved_node_state = node_states[N_MEMORY]; unsigned long totalpages = early_calculate_totalpages(); - int usable_nodes = nodes_weight(node_states[N_HIGH_MEMORY]); + int usable_nodes = nodes_weight(node_states[N_MEMORY]); + struct memblock_region *r; + + /* Need to find movable_zone earlier when movable_node is specified. */ + find_usable_zone_for_movable(); /* - * If movablecore was specified, calculate what size of + * If movable_node is specified, ignore kernelcore and movablecore + * options. + */ + if (movable_node_is_enabled()) { + for_each_memblock(memory, r) { + if (!memblock_is_hotpluggable(r)) + continue; + + nid = r->nid; + + usable_startpfn = PFN_DOWN(r->base); + zone_movable_pfn[nid] = zone_movable_pfn[nid] ? + min(usable_startpfn, zone_movable_pfn[nid]) : + usable_startpfn; + } + + goto out2; + } + + /* + * If movablecore=nn[KMG] was specified, calculate what size of * kernelcore that corresponds so that memory usable for * any allocation type is evenly spread. If both kernelcore * and movablecore are specified, then the value of kernelcore @@ -4491,13 +5169,14 @@ static void __init find_zone_movable_pfns_for_nodes(unsigned long *movable_pfn) goto out; /* usable_startpfn is the lowest possible pfn ZONE_MOVABLE can be at */ - find_usable_zone_for_movable(); usable_startpfn = arch_zone_lowest_possible_pfn[movable_zone]; restart: /* Spread kernelcore memory as evenly as possible throughout nodes */ kernelcore_node = required_kernelcore / usable_nodes; - for_each_node_state(nid, N_HIGH_MEMORY) { + for_each_node_state(nid, N_MEMORY) { + unsigned long start_pfn, end_pfn; + /* * Recalculate kernelcore_node if the division per node * now exceeds what is necessary to satisfy the requested @@ -4514,13 +5193,10 @@ restart: kernelcore_remaining = kernelcore_node; /* Go through each range of PFNs within this node */ - for_each_active_range_index_in_nid(i, nid) { - unsigned long start_pfn, end_pfn; + for_each_mem_pfn_range(i, nid, &start_pfn, &end_pfn, NULL) { unsigned long size_pages; - start_pfn = max(early_node_map[i].start_pfn, - zone_movable_pfn[nid]); - end_pfn = early_node_map[i].end_pfn; + start_pfn = max(start_pfn, zone_movable_pfn[nid]); if (start_pfn >= end_pfn) continue; @@ -4563,7 +5239,7 @@ restart: /* * Some kernelcore has been met, update counts and * break if the kernelcore for this node has been - * satisified + * satisfied */ required_kernelcore -= min(required_kernelcore, size_pages); @@ -4577,12 +5253,13 @@ restart: * If there is still required_kernelcore, we do another pass with one * less node in the count. This will push zone_movable_pfn[nid] further * along on the nodes that still have memory until kernelcore is - * satisified + * satisfied */ usable_nodes--; if (usable_nodes && required_kernelcore > usable_nodes) goto restart; +out2: /* Align start of ZONE_MOVABLE on all nids to MAX_ORDER_NR_PAGES */ for (nid = 0; nid < MAX_NUMNODES; nid++) zone_movable_pfn[nid] = @@ -4590,21 +5267,27 @@ restart: out: /* restore the node_state */ - node_states[N_HIGH_MEMORY] = saved_node_state; + node_states[N_MEMORY] = saved_node_state; } -/* Any regular memory on that node ? */ -static void check_for_regular_memory(pg_data_t *pgdat) +/* Any regular or high memory on that node ? */ +static void check_for_memory(pg_data_t *pgdat, int nid) { -#ifdef CONFIG_HIGHMEM enum zone_type zone_type; - for (zone_type = 0; zone_type <= ZONE_NORMAL; zone_type++) { + if (N_MEMORY == N_NORMAL_MEMORY) + return; + + for (zone_type = 0; zone_type <= ZONE_MOVABLE - 1; zone_type++) { struct zone *zone = &pgdat->node_zones[zone_type]; - if (zone->present_pages) - node_set_state(zone_to_nid(zone), N_NORMAL_MEMORY); + if (populated_zone(zone)) { + node_set_state(nid, N_HIGH_MEMORY); + if (N_NORMAL_MEMORY != N_HIGH_MEMORY && + zone_type <= ZONE_NORMAL) + node_set_state(nid, N_NORMAL_MEMORY); + break; + } } -#endif } /** @@ -4612,7 +5295,7 @@ static void check_for_regular_memory(pg_data_t *pgdat) * @max_zone_pfn: an array of max PFNs for each zone * * This will call free_area_init_node() for each active node in the system. - * Using the page ranges provided by add_active_range(), the size of each + * Using the page ranges provided by memblock_set_node(), the size of each * zone in each node and their holes is calculated. If the maximum PFN * between two adjacent zones match, it is assumed that the zone is empty. * For example, if arch_max_dma_pfn == arch_max_dma32_pfn, it is assumed @@ -4622,11 +5305,8 @@ static void check_for_regular_memory(pg_data_t *pgdat) */ void __init free_area_init_nodes(unsigned long *max_zone_pfn) { - unsigned long nid; - int i; - - /* Sort early_node_map as initialisation assumes it is sorted */ - sort_node_map(); + unsigned long start_pfn, end_pfn; + int i, nid; /* Record where the zone boundaries are */ memset(arch_zone_lowest_possible_pfn, 0, @@ -4648,36 +5328,37 @@ void __init free_area_init_nodes(unsigned long *max_zone_pfn) /* Find the PFNs that ZONE_MOVABLE begins at in each node */ memset(zone_movable_pfn, 0, sizeof(zone_movable_pfn)); - find_zone_movable_pfns_for_nodes(zone_movable_pfn); + find_zone_movable_pfns_for_nodes(); /* Print out the zone ranges */ - printk("Zone PFN ranges:\n"); + printk("Zone ranges:\n"); for (i = 0; i < MAX_NR_ZONES; i++) { if (i == ZONE_MOVABLE) continue; - printk(" %-8s ", zone_names[i]); + printk(KERN_CONT " %-8s ", zone_names[i]); if (arch_zone_lowest_possible_pfn[i] == arch_zone_highest_possible_pfn[i]) - printk("empty\n"); + printk(KERN_CONT "empty\n"); else - printk("%0#10lx -> %0#10lx\n", - arch_zone_lowest_possible_pfn[i], - arch_zone_highest_possible_pfn[i]); + printk(KERN_CONT "[mem %0#10lx-%0#10lx]\n", + arch_zone_lowest_possible_pfn[i] << PAGE_SHIFT, + (arch_zone_highest_possible_pfn[i] + << PAGE_SHIFT) - 1); } /* Print out the PFNs ZONE_MOVABLE begins at in each node */ - printk("Movable zone start PFN for each node\n"); + printk("Movable zone start for each node\n"); for (i = 0; i < MAX_NUMNODES; i++) { if (zone_movable_pfn[i]) - printk(" Node %d: %lu\n", i, zone_movable_pfn[i]); + printk(" Node %d: %#010lx\n", i, + zone_movable_pfn[i] << PAGE_SHIFT); } - /* Print out the early_node_map[] */ - printk("early_node_map[%d] active PFN ranges\n", nr_nodemap_entries); - for (i = 0; i < nr_nodemap_entries; i++) - printk(" %3d: %0#10lx -> %0#10lx\n", early_node_map[i].nid, - early_node_map[i].start_pfn, - early_node_map[i].end_pfn); + /* Print out the early node map */ + printk("Early memory node ranges\n"); + for_each_mem_pfn_range(i, MAX_NUMNODES, &start_pfn, &end_pfn, &nid) + printk(" node %3d: [mem %#010lx-%#010lx]\n", nid, + start_pfn << PAGE_SHIFT, (end_pfn << PAGE_SHIFT) - 1); /* Initialise every node */ mminit_verify_pageflags_layout(); @@ -4689,8 +5370,8 @@ void __init free_area_init_nodes(unsigned long *max_zone_pfn) /* Any memory on that node */ if (pgdat->node_present_pages) - node_set_state(nid, N_HIGH_MEMORY); - check_for_regular_memory(pgdat); + node_set_state(nid, N_MEMORY); + check_for_memory(pgdat, nid); } } @@ -4730,7 +5411,104 @@ static int __init cmdline_parse_movablecore(char *p) early_param("kernelcore", cmdline_parse_kernelcore); early_param("movablecore", cmdline_parse_movablecore); -#endif /* CONFIG_ARCH_POPULATES_NODE_MAP */ +#endif /* CONFIG_HAVE_MEMBLOCK_NODE_MAP */ + +void adjust_managed_page_count(struct page *page, long count) +{ + spin_lock(&managed_page_count_lock); + page_zone(page)->managed_pages += count; + totalram_pages += count; +#ifdef CONFIG_HIGHMEM + if (PageHighMem(page)) + totalhigh_pages += count; +#endif + spin_unlock(&managed_page_count_lock); +} +EXPORT_SYMBOL(adjust_managed_page_count); + +unsigned long free_reserved_area(void *start, void *end, int poison, char *s) +{ + void *pos; + unsigned long pages = 0; + + start = (void *)PAGE_ALIGN((unsigned long)start); + end = (void *)((unsigned long)end & PAGE_MASK); + for (pos = start; pos < end; pos += PAGE_SIZE, pages++) { + if ((unsigned int)poison <= 0xFF) + memset(pos, poison, PAGE_SIZE); + free_reserved_page(virt_to_page(pos)); + } + + if (pages && s) + pr_info("Freeing %s memory: %ldK (%p - %p)\n", + s, pages << (PAGE_SHIFT - 10), start, end); + + return pages; +} +EXPORT_SYMBOL(free_reserved_area); + +#ifdef CONFIG_HIGHMEM +void free_highmem_page(struct page *page) +{ + __free_reserved_page(page); + totalram_pages++; + page_zone(page)->managed_pages++; + totalhigh_pages++; +} +#endif + + +void __init mem_init_print_info(const char *str) +{ + unsigned long physpages, codesize, datasize, rosize, bss_size; + unsigned long init_code_size, init_data_size; + + physpages = get_num_physpages(); + codesize = _etext - _stext; + datasize = _edata - _sdata; + rosize = __end_rodata - __start_rodata; + bss_size = __bss_stop - __bss_start; + init_data_size = __init_end - __init_begin; + init_code_size = _einittext - _sinittext; + + /* + * Detect special cases and adjust section sizes accordingly: + * 1) .init.* may be embedded into .data sections + * 2) .init.text.* may be out of [__init_begin, __init_end], + * please refer to arch/tile/kernel/vmlinux.lds.S. + * 3) .rodata.* may be embedded into .text or .data sections. + */ +#define adj_init_size(start, end, size, pos, adj) \ + do { \ + if (start <= pos && pos < end && size > adj) \ + size -= adj; \ + } while (0) + + adj_init_size(__init_begin, __init_end, init_data_size, + _sinittext, init_code_size); + adj_init_size(_stext, _etext, codesize, _sinittext, init_code_size); + adj_init_size(_sdata, _edata, datasize, __init_begin, init_data_size); + adj_init_size(_stext, _etext, codesize, __start_rodata, rosize); + adj_init_size(_sdata, _edata, datasize, __start_rodata, rosize); + +#undef adj_init_size + + printk("Memory: %luK/%luK available " + "(%luK kernel code, %luK rwdata, %luK rodata, " + "%luK init, %luK bss, %luK reserved" +#ifdef CONFIG_HIGHMEM + ", %luK highmem" +#endif + "%s%s)\n", + nr_free_pages() << (PAGE_SHIFT-10), physpages << (PAGE_SHIFT-10), + codesize >> 10, datasize >> 10, rosize >> 10, + (init_data_size + init_code_size) >> 10, bss_size >> 10, + (physpages - totalram_pages) << (PAGE_SHIFT-10), +#ifdef CONFIG_HIGHMEM + totalhigh_pages << (PAGE_SHIFT-10), +#endif + str ? ", " : "", str ? str : ""); +} /** * set_dma_reserve - set the specified number of pages reserved in the first zone @@ -4748,15 +5526,6 @@ void __init set_dma_reserve(unsigned long new_dma_reserve) dma_reserve = new_dma_reserve; } -#ifndef CONFIG_NEED_MULTIPLE_NODES -struct pglist_data __refdata contig_page_data = { -#ifndef CONFIG_NO_BOOTMEM - .bdata = &bootmem_node_data[0] -#endif - }; -EXPORT_SYMBOL(contig_page_data); -#endif - void __init free_area_init(unsigned long *zones_size) { free_area_init_node(0, zones_size, @@ -4769,6 +5538,7 @@ static int page_alloc_cpu_notify(struct notifier_block *self, int cpu = (unsigned long)hcpu; if (action == CPU_DEAD || action == CPU_DEAD_FROZEN) { + lru_add_drain_cpu(cpu); drain_pages(cpu); /* @@ -4786,7 +5556,7 @@ static int page_alloc_cpu_notify(struct notifier_block *self, * This is only okay since the processor is dead and cannot * race with what we are doing. */ - refresh_cpu_vm_stats(cpu); + cpu_vm_stats_fold(cpu); } return NOTIFY_OK; } @@ -4820,11 +5590,22 @@ static void calculate_totalreserve_pages(void) /* we treat the high watermark as reserved pages. */ max += high_wmark_pages(zone); - if (max > zone->present_pages) - max = zone->present_pages; + if (max > zone->managed_pages) + max = zone->managed_pages; reserve_pages += max; + /* + * Lowmem reserves are not available to + * GFP_HIGHUSER page cache allocations and + * kswapd tries to balance zones to their high + * watermark. As a result, neither should be + * regarded as dirtyable memory, to prevent a + * situation where reclaim has to clean pages + * in order to balance the zones. + */ + zone->dirty_balance_reserve = max; } } + dirty_balance_reserve = reserve_pages; totalreserve_pages = reserve_pages; } @@ -4842,7 +5623,7 @@ static void setup_per_zone_lowmem_reserve(void) for_each_online_pgdat(pgdat) { for (j = 0; j < MAX_NR_ZONES; j++) { struct zone *zone = pgdat->node_zones + j; - unsigned long present_pages = zone->present_pages; + unsigned long managed_pages = zone->managed_pages; zone->lowmem_reserve[j] = 0; @@ -4856,9 +5637,9 @@ static void setup_per_zone_lowmem_reserve(void) sysctl_lowmem_reserve_ratio[idx] = 1; lower_zone = pgdat->node_zones + idx; - lower_zone->lowmem_reserve[j] = present_pages / + lower_zone->lowmem_reserve[j] = managed_pages / sysctl_lowmem_reserve_ratio[idx]; - present_pages += lower_zone->present_pages; + managed_pages += lower_zone->managed_pages; } } } @@ -4867,14 +5648,7 @@ static void setup_per_zone_lowmem_reserve(void) calculate_totalreserve_pages(); } -/** - * setup_per_zone_wmarks - called when min_free_kbytes changes - * or when memory is hot-{added|removed} - * - * Ensures that the watermark[min,low,high] values for each zone are set - * correctly with respect to min_free_kbytes. - */ -void setup_per_zone_wmarks(void) +static void __setup_per_zone_wmarks(void) { unsigned long pages_min = min_free_kbytes >> (PAGE_SHIFT - 10); unsigned long lowmem_pages = 0; @@ -4884,14 +5658,14 @@ void setup_per_zone_wmarks(void) /* Calculate total number of !ZONE_HIGHMEM pages */ for_each_zone(zone) { if (!is_highmem(zone)) - lowmem_pages += zone->present_pages; + lowmem_pages += zone->managed_pages; } for_each_zone(zone) { u64 tmp; spin_lock_irqsave(&zone->lock, flags); - tmp = (u64)pages_min * zone->present_pages; + tmp = (u64)pages_min * zone->managed_pages; do_div(tmp, lowmem_pages); if (is_highmem(zone)) { /* @@ -4903,13 +5677,10 @@ void setup_per_zone_wmarks(void) * deltas controls asynch page reclaim, and so should * not be capped for highmem. */ - int min_pages; + unsigned long min_pages; - min_pages = zone->present_pages / 1024; - if (min_pages < SWAP_CLUSTER_MAX) - min_pages = SWAP_CLUSTER_MAX; - if (min_pages > 128) - min_pages = 128; + min_pages = zone->managed_pages / 1024; + min_pages = clamp(min_pages, SWAP_CLUSTER_MAX, 128UL); zone->watermark[WMARK_MIN] = min_pages; } else { /* @@ -4921,6 +5692,12 @@ void setup_per_zone_wmarks(void) zone->watermark[WMARK_LOW] = min_wmark_pages(zone) + (tmp >> 2); zone->watermark[WMARK_HIGH] = min_wmark_pages(zone) + (tmp >> 1); + + __mod_zone_page_state(zone, NR_ALLOC_BATCH, + high_wmark_pages(zone) - + low_wmark_pages(zone) - + zone_page_state(zone, NR_ALLOC_BATCH)); + setup_zone_migrate_reserve(zone); spin_unlock_irqrestore(&zone->lock, flags); } @@ -4929,6 +5706,20 @@ void setup_per_zone_wmarks(void) calculate_totalreserve_pages(); } +/** + * setup_per_zone_wmarks - called when min_free_kbytes changes + * or when memory is hot-{added|removed} + * + * Ensures that the watermark[min,low,high] values for each zone are set + * correctly with respect to min_free_kbytes. + */ +void setup_per_zone_wmarks(void) +{ + mutex_lock(&zonelists_mutex); + __setup_per_zone_wmarks(); + mutex_unlock(&zonelists_mutex); +} + /* * The inactive anon list should be small enough that the VM never has to * do too much work, but large enough that each inactive page has a chance @@ -4950,12 +5741,12 @@ void setup_per_zone_wmarks(void) * 1TB 101 10GB * 10TB 320 32GB */ -void calculate_zone_inactive_ratio(struct zone *zone) +static void __meminit calculate_zone_inactive_ratio(struct zone *zone) { unsigned int gb, ratio; /* Zone size in gigabytes */ - gb = zone->present_pages >> (30 - PAGE_SHIFT); + gb = zone->managed_pages >> (30 - PAGE_SHIFT); if (gb) ratio = int_sqrt(10 * gb); else @@ -4964,7 +5755,7 @@ void calculate_zone_inactive_ratio(struct zone *zone) zone->inactive_ratio = ratio; } -static void __init setup_per_zone_inactive_ratio(void) +static void __meminit setup_per_zone_inactive_ratio(void) { struct zone *zone; @@ -4979,7 +5770,7 @@ static void __init setup_per_zone_inactive_ratio(void) * we want it large (64MB max). But it is not linear, because network * bandwidth does not increase linearly with machine size. We use * - * min_free_kbytes = 4 * sqrt(lowmem_kbytes), for better accuracy: + * min_free_kbytes = 4 * sqrt(lowmem_kbytes), for better accuracy: * min_free_kbytes = sqrt(lowmem_kbytes * 16) * * which yields @@ -4996,18 +5787,26 @@ static void __init setup_per_zone_inactive_ratio(void) * 8192MB: 11584k * 16384MB: 16384k */ -static int __init init_per_zone_wmark_min(void) +int __meminit init_per_zone_wmark_min(void) { unsigned long lowmem_kbytes; + int new_min_free_kbytes; lowmem_kbytes = nr_free_buffer_pages() * (PAGE_SIZE >> 10); - - min_free_kbytes = int_sqrt(lowmem_kbytes * 16); - if (min_free_kbytes < 128) - min_free_kbytes = 128; - if (min_free_kbytes > 65536) - min_free_kbytes = 65536; + new_min_free_kbytes = int_sqrt(lowmem_kbytes * 16); + + if (new_min_free_kbytes > user_min_free_kbytes) { + min_free_kbytes = new_min_free_kbytes; + if (min_free_kbytes < 128) + min_free_kbytes = 128; + if (min_free_kbytes > 65536) + min_free_kbytes = 65536; + } else { + pr_warn("min_free_kbytes is not updated to %d because user defined value %d is preferred\n", + new_min_free_kbytes, user_min_free_kbytes); + } setup_per_zone_wmarks(); + refresh_zone_stat_thresholds(); setup_per_zone_lowmem_reserve(); setup_per_zone_inactive_ratio(); return 0; @@ -5015,21 +5814,28 @@ static int __init init_per_zone_wmark_min(void) module_init(init_per_zone_wmark_min) /* - * min_free_kbytes_sysctl_handler - just a wrapper around proc_dointvec() so + * min_free_kbytes_sysctl_handler - just a wrapper around proc_dointvec() so * that we can call two helper functions whenever min_free_kbytes * changes. */ -int min_free_kbytes_sysctl_handler(ctl_table *table, int write, +int min_free_kbytes_sysctl_handler(struct ctl_table *table, int write, void __user *buffer, size_t *length, loff_t *ppos) { - proc_dointvec(table, write, buffer, length, ppos); - if (write) + int rc; + + rc = proc_dointvec_minmax(table, write, buffer, length, ppos); + if (rc) + return rc; + + if (write) { + user_min_free_kbytes = min_free_kbytes; setup_per_zone_wmarks(); + } return 0; } #ifdef CONFIG_NUMA -int sysctl_min_unmapped_ratio_sysctl_handler(ctl_table *table, int write, +int sysctl_min_unmapped_ratio_sysctl_handler(struct ctl_table *table, int write, void __user *buffer, size_t *length, loff_t *ppos) { struct zone *zone; @@ -5040,12 +5846,12 @@ int sysctl_min_unmapped_ratio_sysctl_handler(ctl_table *table, int write, return rc; for_each_zone(zone) - zone->min_unmapped_pages = (zone->present_pages * + zone->min_unmapped_pages = (zone->managed_pages * sysctl_min_unmapped_ratio) / 100; return 0; } -int sysctl_min_slab_ratio_sysctl_handler(ctl_table *table, int write, +int sysctl_min_slab_ratio_sysctl_handler(struct ctl_table *table, int write, void __user *buffer, size_t *length, loff_t *ppos) { struct zone *zone; @@ -5056,7 +5862,7 @@ int sysctl_min_slab_ratio_sysctl_handler(ctl_table *table, int write, return rc; for_each_zone(zone) - zone->min_slab_pages = (zone->present_pages * + zone->min_slab_pages = (zone->managed_pages * sysctl_min_slab_ratio) / 100; return 0; } @@ -5071,7 +5877,7 @@ int sysctl_min_slab_ratio_sysctl_handler(ctl_table *table, int write, * minimum watermarks. The lowmem reserve ratio can only make sense * if in function of the boot time zone sizes. */ -int lowmem_reserve_ratio_sysctl_handler(ctl_table *table, int write, +int lowmem_reserve_ratio_sysctl_handler(struct ctl_table *table, int write, void __user *buffer, size_t *length, loff_t *ppos) { proc_dointvec_minmax(table, write, buffer, length, ppos); @@ -5081,29 +5887,45 @@ int lowmem_reserve_ratio_sysctl_handler(ctl_table *table, int write, /* * percpu_pagelist_fraction - changes the pcp->high for each zone on each - * cpu. It is the fraction of total pages in each zone that a hot per cpu pagelist - * can have before it gets flushed back to buddy allocator. + * cpu. It is the fraction of total pages in each zone that a hot per cpu + * pagelist can have before it gets flushed back to buddy allocator. */ - -int percpu_pagelist_fraction_sysctl_handler(ctl_table *table, int write, +int percpu_pagelist_fraction_sysctl_handler(struct ctl_table *table, int write, void __user *buffer, size_t *length, loff_t *ppos) { struct zone *zone; - unsigned int cpu; + int old_percpu_pagelist_fraction; int ret; + mutex_lock(&pcp_batch_high_lock); + old_percpu_pagelist_fraction = percpu_pagelist_fraction; + ret = proc_dointvec_minmax(table, write, buffer, length, ppos); - if (!write || (ret == -EINVAL)) - return ret; + if (!write || ret < 0) + goto out; + + /* Sanity checking to avoid pcp imbalance */ + if (percpu_pagelist_fraction && + percpu_pagelist_fraction < MIN_PERCPU_PAGELIST_FRACTION) { + percpu_pagelist_fraction = old_percpu_pagelist_fraction; + ret = -EINVAL; + goto out; + } + + /* No change? */ + if (percpu_pagelist_fraction == old_percpu_pagelist_fraction) + goto out; + for_each_populated_zone(zone) { - for_each_possible_cpu(cpu) { - unsigned long high; - high = zone->present_pages / percpu_pagelist_fraction; - setup_pagelist_highmark( - per_cpu_ptr(zone->pageset, cpu), high); - } + unsigned int cpu; + + for_each_possible_cpu(cpu) + pageset_set_high_and_batch(zone, + per_cpu_ptr(zone->pageset, cpu)); } - return 0; +out: + mutex_unlock(&pcp_batch_high_lock); + return ret; } int hashdist = HASHDIST_DEFAULT; @@ -5132,9 +5954,10 @@ void *__init alloc_large_system_hash(const char *tablename, int flags, unsigned int *_hash_shift, unsigned int *_hash_mask, - unsigned long limit) + unsigned long low_limit, + unsigned long high_limit) { - unsigned long long max = limit; + unsigned long long max = high_limit; unsigned long log2qty, size; void *table = NULL; @@ -5142,9 +5965,10 @@ void *__init alloc_large_system_hash(const char *tablename, if (!numentries) { /* round applicable memory size up to nearest megabyte */ numentries = nr_kernel_pages; - numentries += (1UL << (20 - PAGE_SHIFT)) - 1; - numentries >>= 20 - PAGE_SHIFT; - numentries <<= 20 - PAGE_SHIFT; + + /* It isn't necessary when PAGE_SIZE >= 1MB */ + if (PAGE_SHIFT < 20) + numentries = round_up(numentries, (1<<20)/PAGE_SIZE); /* limit to 1 bucket per 2^scale bytes of low memory */ if (scale > PAGE_SHIFT) @@ -5170,7 +5994,10 @@ void *__init alloc_large_system_hash(const char *tablename, max = ((unsigned long long)nr_all_pages << PAGE_SHIFT) >> 4; do_div(max, bucketsize); } + max = min(max, 0x80000000ULL); + if (numentries < low_limit) + numentries = low_limit; if (numentries > max) numentries = max; @@ -5179,7 +6006,7 @@ void *__init alloc_large_system_hash(const char *tablename, do { size = bucketsize << log2qty; if (flags & HASH_EARLY) - table = alloc_bootmem_nopanic(size); + table = memblock_virt_alloc_nopanic(size, 0); else if (hashdist) table = __vmalloc(size, GFP_ATOMIC, PAGE_KERNEL); else { @@ -5229,102 +6056,143 @@ static inline int pfn_to_bitidx(struct zone *zone, unsigned long pfn) pfn &= (PAGES_PER_SECTION-1); return (pfn >> pageblock_order) * NR_PAGEBLOCK_BITS; #else - pfn = pfn - zone->zone_start_pfn; + pfn = pfn - round_down(zone->zone_start_pfn, pageblock_nr_pages); return (pfn >> pageblock_order) * NR_PAGEBLOCK_BITS; #endif /* CONFIG_SPARSEMEM */ } /** - * get_pageblock_flags_group - Return the requested group of flags for the pageblock_nr_pages block of pages + * get_pfnblock_flags_mask - Return the requested group of flags for the pageblock_nr_pages block of pages * @page: The page within the block of interest - * @start_bitidx: The first bit of interest to retrieve - * @end_bitidx: The last bit of interest - * returns pageblock_bits flags + * @pfn: The target page frame number + * @end_bitidx: The last bit of interest to retrieve + * @mask: mask of bits that the caller is interested in + * + * Return: pageblock_bits flags */ -unsigned long get_pageblock_flags_group(struct page *page, - int start_bitidx, int end_bitidx) +unsigned long get_pfnblock_flags_mask(struct page *page, unsigned long pfn, + unsigned long end_bitidx, + unsigned long mask) { struct zone *zone; unsigned long *bitmap; - unsigned long pfn, bitidx; - unsigned long flags = 0; - unsigned long value = 1; + unsigned long bitidx, word_bitidx; + unsigned long word; zone = page_zone(page); - pfn = page_to_pfn(page); bitmap = get_pageblock_bitmap(zone, pfn); bitidx = pfn_to_bitidx(zone, pfn); + word_bitidx = bitidx / BITS_PER_LONG; + bitidx &= (BITS_PER_LONG-1); - for (; start_bitidx <= end_bitidx; start_bitidx++, value <<= 1) - if (test_bit(bitidx + start_bitidx, bitmap)) - flags |= value; - - return flags; + word = bitmap[word_bitidx]; + bitidx += end_bitidx; + return (word >> (BITS_PER_LONG - bitidx - 1)) & mask; } /** - * set_pageblock_flags_group - Set the requested group of flags for a pageblock_nr_pages block of pages + * set_pfnblock_flags_mask - Set the requested group of flags for a pageblock_nr_pages block of pages * @page: The page within the block of interest - * @start_bitidx: The first bit of interest - * @end_bitidx: The last bit of interest * @flags: The flags to set + * @pfn: The target page frame number + * @end_bitidx: The last bit of interest + * @mask: mask of bits that the caller is interested in */ -void set_pageblock_flags_group(struct page *page, unsigned long flags, - int start_bitidx, int end_bitidx) +void set_pfnblock_flags_mask(struct page *page, unsigned long flags, + unsigned long pfn, + unsigned long end_bitidx, + unsigned long mask) { struct zone *zone; unsigned long *bitmap; - unsigned long pfn, bitidx; - unsigned long value = 1; + unsigned long bitidx, word_bitidx; + unsigned long old_word, word; + + BUILD_BUG_ON(NR_PAGEBLOCK_BITS != 4); zone = page_zone(page); - pfn = page_to_pfn(page); bitmap = get_pageblock_bitmap(zone, pfn); bitidx = pfn_to_bitidx(zone, pfn); - VM_BUG_ON(pfn < zone->zone_start_pfn); - VM_BUG_ON(pfn >= zone->zone_start_pfn + zone->spanned_pages); + word_bitidx = bitidx / BITS_PER_LONG; + bitidx &= (BITS_PER_LONG-1); - for (; start_bitidx <= end_bitidx; start_bitidx++, value <<= 1) - if (flags & value) - __set_bit(bitidx + start_bitidx, bitmap); - else - __clear_bit(bitidx + start_bitidx, bitmap); + VM_BUG_ON_PAGE(!zone_spans_pfn(zone, pfn), page); + + bitidx += end_bitidx; + mask <<= (BITS_PER_LONG - bitidx - 1); + flags <<= (BITS_PER_LONG - bitidx - 1); + + word = ACCESS_ONCE(bitmap[word_bitidx]); + for (;;) { + old_word = cmpxchg(&bitmap[word_bitidx], word, (word & ~mask) | flags); + if (word == old_word) + break; + word = old_word; + } } /* - * This is designed as sub function...plz see page_isolation.c also. - * set/clear page block's type to be ISOLATE. - * page allocater never alloc memory from ISOLATE block. + * This function checks whether pageblock includes unmovable pages or not. + * If @count is not zero, it is okay to include less @count unmovable pages + * + * PageLRU check without isolation or lru_lock could race so that + * MIGRATE_MOVABLE block might include unmovable pages. It means you can't + * expect this function should be exact. */ - -static int -__count_immobile_pages(struct zone *zone, struct page *page, int count) +bool has_unmovable_pages(struct zone *zone, struct page *page, int count, + bool skip_hwpoisoned_pages) { unsigned long pfn, iter, found; + int mt; + /* * For avoiding noise data, lru_add_drain_all() should be called - * If ZONE_MOVABLE, the zone never contains immobile pages + * If ZONE_MOVABLE, the zone never contains unmovable pages */ if (zone_idx(zone) == ZONE_MOVABLE) - return true; - - if (get_pageblock_migratetype(page) == MIGRATE_MOVABLE) - return true; + return false; + mt = get_pageblock_migratetype(page); + if (mt == MIGRATE_MOVABLE || is_migrate_cma(mt)) + return false; pfn = page_to_pfn(page); for (found = 0, iter = 0; iter < pageblock_nr_pages; iter++) { unsigned long check = pfn + iter; - if (!pfn_valid_within(check)) { - iter++; + if (!pfn_valid_within(check)) continue; - } + page = pfn_to_page(check); - if (!page_count(page)) { + + /* + * Hugepages are not in LRU lists, but they're movable. + * We need not scan over tail pages bacause we don't + * handle each tail page individually in migration. + */ + if (PageHuge(page)) { + iter = round_up(iter + 1, 1<<compound_order(page)) - 1; + continue; + } + + /* + * We can't use page_count without pin a page + * because another CPU can free compound page. + * This check already skips compound tails of THP + * because their page->_count is zero at all time. + */ + if (!atomic_read(&page->_count)) { if (PageBuddy(page)) iter += (1 << page_order(page)) - 1; continue; } + + /* + * The HWPoisoned page may be not in buddy system, and + * page_count() is not 0. + */ + if (skip_hwpoisoned_pages && PageHWPoison(page)) + continue; + if (!PageLRU(page)) found++; /* @@ -5341,87 +6209,268 @@ __count_immobile_pages(struct zone *zone, struct page *page, int count) * page at boot. */ if (found > count) - return false; + return true; } - return true; + return false; } bool is_pageblock_removable_nolock(struct page *page) { - struct zone *zone = page_zone(page); - return __count_immobile_pages(zone, page, 0); + struct zone *zone; + unsigned long pfn; + + /* + * We have to be careful here because we are iterating over memory + * sections which are not zone aware so we might end up outside of + * the zone but still within the section. + * We have to take care about the node as well. If the node is offline + * its NODE_DATA will be NULL - see page_zone. + */ + if (!node_online(page_to_nid(page))) + return false; + + zone = page_zone(page); + pfn = page_to_pfn(page); + if (!zone_spans_pfn(zone, pfn)) + return false; + + return !has_unmovable_pages(zone, page, 0, true); } -int set_migratetype_isolate(struct page *page) +#ifdef CONFIG_CMA + +static unsigned long pfn_max_align_down(unsigned long pfn) { - struct zone *zone; - unsigned long flags, pfn; - struct memory_isolate_notify arg; - int notifier_ret; - int ret = -EBUSY; - int zone_idx; + return pfn & ~(max_t(unsigned long, MAX_ORDER_NR_PAGES, + pageblock_nr_pages) - 1); +} - zone = page_zone(page); - zone_idx = zone_idx(zone); +static unsigned long pfn_max_align_up(unsigned long pfn) +{ + return ALIGN(pfn, max_t(unsigned long, MAX_ORDER_NR_PAGES, + pageblock_nr_pages)); +} - spin_lock_irqsave(&zone->lock, flags); +/* [start, end) must belong to a single zone. */ +static int __alloc_contig_migrate_range(struct compact_control *cc, + unsigned long start, unsigned long end) +{ + /* This function is based on compact_zone() from compaction.c. */ + unsigned long nr_reclaimed; + unsigned long pfn = start; + unsigned int tries = 0; + int ret = 0; - pfn = page_to_pfn(page); - arg.start_pfn = pfn; - arg.nr_pages = pageblock_nr_pages; - arg.pages_found = 0; + migrate_prep(); + + while (pfn < end || !list_empty(&cc->migratepages)) { + if (fatal_signal_pending(current)) { + ret = -EINTR; + break; + } + + if (list_empty(&cc->migratepages)) { + cc->nr_migratepages = 0; + pfn = isolate_migratepages_range(cc->zone, cc, + pfn, end, true); + if (!pfn) { + ret = -EINTR; + break; + } + tries = 0; + } else if (++tries == 5) { + ret = ret < 0 ? ret : -EBUSY; + break; + } + + nr_reclaimed = reclaim_clean_pages_from_list(cc->zone, + &cc->migratepages); + cc->nr_migratepages -= nr_reclaimed; + + ret = migrate_pages(&cc->migratepages, alloc_migrate_target, + NULL, 0, cc->mode, MR_CMA); + } + if (ret < 0) { + putback_movable_pages(&cc->migratepages); + return ret; + } + return 0; +} + +/** + * alloc_contig_range() -- tries to allocate given range of pages + * @start: start PFN to allocate + * @end: one-past-the-last PFN to allocate + * @migratetype: migratetype of the underlaying pageblocks (either + * #MIGRATE_MOVABLE or #MIGRATE_CMA). All pageblocks + * in range must have the same migratetype and it must + * be either of the two. + * + * The PFN range does not have to be pageblock or MAX_ORDER_NR_PAGES + * aligned, however it's the caller's responsibility to guarantee that + * we are the only thread that changes migrate type of pageblocks the + * pages fall in. + * + * The PFN range must belong to a single zone. + * + * Returns 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(). + */ +int alloc_contig_range(unsigned long start, unsigned long end, + unsigned migratetype) +{ + unsigned long outer_start, outer_end; + int ret = 0, order; + + struct compact_control cc = { + .nr_migratepages = 0, + .order = -1, + .zone = page_zone(pfn_to_page(start)), + .mode = MIGRATE_SYNC, + .ignore_skip_hint = true, + }; + INIT_LIST_HEAD(&cc.migratepages); /* - * It may be possible to isolate a pageblock even if the - * migratetype is not MIGRATE_MOVABLE. The memory isolation - * notifier chain is used by balloon drivers to return the - * number of pages in a range that are held by the balloon - * driver to shrink memory. If all the pages are accounted for - * by balloons, are free, or on the LRU, isolation can continue. - * Later, for example, when memory hotplug notifier runs, these - * pages reported as "can be isolated" should be isolated(freed) - * by the balloon driver through the memory notifier chain. - */ - notifier_ret = memory_isolate_notify(MEM_ISOLATE_COUNT, &arg); - notifier_ret = notifier_to_errno(notifier_ret); - if (notifier_ret) - goto out; - /* - * FIXME: Now, memory hotplug doesn't call shrink_slab() by itself. - * We just check MOVABLE pages. + * What we do here is we mark all pageblocks in range as + * MIGRATE_ISOLATE. Because pageblock and max order pages may + * have different sizes, and due to the way page allocator + * work, we align the range to biggest of the two pages so + * that page allocator won't try to merge buddies from + * different pageblocks and change MIGRATE_ISOLATE to some + * other migration type. + * + * Once the pageblocks are marked as MIGRATE_ISOLATE, we + * migrate the pages from an unaligned range (ie. pages that + * we are interested in). This will put all the pages in + * range back to page allocator as MIGRATE_ISOLATE. + * + * When this is done, we take the pages in range from page + * allocator removing them from the buddy system. This way + * page allocator will never consider using them. + * + * This lets us mark the pageblocks back as + * MIGRATE_CMA/MIGRATE_MOVABLE so that free pages in the + * aligned range but not in the unaligned, original range are + * put back to page allocator so that buddy can use them. */ - if (__count_immobile_pages(zone, page, arg.pages_found)) - ret = 0; + + ret = start_isolate_page_range(pfn_max_align_down(start), + pfn_max_align_up(end), migratetype, + false); + if (ret) + return ret; + + ret = __alloc_contig_migrate_range(&cc, start, end); + if (ret) + goto done; /* - * immobile means "not-on-lru" paes. If immobile is larger than - * removable-by-driver pages reported by notifier, we'll fail. + * Pages from [start, end) are within a MAX_ORDER_NR_PAGES + * aligned blocks that are marked as MIGRATE_ISOLATE. What's + * more, all pages in [start, end) are free in page allocator. + * What we are going to do is to allocate all pages from + * [start, end) (that is remove them from page allocator). + * + * The only problem is that pages at the beginning and at the + * end of interesting range may be not aligned with pages that + * page allocator holds, ie. they can be part of higher order + * pages. Because of this, we reserve the bigger range and + * once this is done free the pages we are not interested in. + * + * We don't have to hold zone->lock here because the pages are + * isolated thus they won't get removed from buddy. */ -out: - if (!ret) { - set_pageblock_migratetype(page, MIGRATE_ISOLATE); - move_freepages_block(zone, page, MIGRATE_ISOLATE); + lru_add_drain_all(); + drain_all_pages(); + + order = 0; + outer_start = start; + while (!PageBuddy(pfn_to_page(outer_start))) { + if (++order >= MAX_ORDER) { + ret = -EBUSY; + goto done; + } + outer_start &= ~0UL << order; } - spin_unlock_irqrestore(&zone->lock, flags); - if (!ret) - drain_all_pages(); + /* Make sure the range is really isolated. */ + if (test_pages_isolated(outer_start, end, false)) { + pr_warn("alloc_contig_range test_pages_isolated(%lx, %lx) failed\n", + outer_start, end); + ret = -EBUSY; + goto done; + } + + + /* Grab isolated pages from freelists. */ + outer_end = isolate_freepages_range(&cc, outer_start, end); + if (!outer_end) { + ret = -EBUSY; + goto done; + } + + /* Free head and tail (if any) */ + if (start != outer_start) + free_contig_range(outer_start, start - outer_start); + if (end != outer_end) + free_contig_range(end, outer_end - end); + +done: + undo_isolate_page_range(pfn_max_align_down(start), + pfn_max_align_up(end), migratetype); return ret; } -void unset_migratetype_isolate(struct page *page) +void free_contig_range(unsigned long pfn, unsigned nr_pages) +{ + unsigned int count = 0; + + for (; nr_pages--; pfn++) { + struct page *page = pfn_to_page(pfn); + + count += page_count(page) != 1; + __free_page(page); + } + WARN(count != 0, "%d pages are still in use!\n", count); +} +#endif + +#ifdef CONFIG_MEMORY_HOTPLUG +/* + * The zone indicated has a new number of managed_pages; batch sizes and percpu + * page high values need to be recalulated. + */ +void __meminit zone_pcp_update(struct zone *zone) +{ + unsigned cpu; + mutex_lock(&pcp_batch_high_lock); + for_each_possible_cpu(cpu) + pageset_set_high_and_batch(zone, + per_cpu_ptr(zone->pageset, cpu)); + mutex_unlock(&pcp_batch_high_lock); +} +#endif + +void zone_pcp_reset(struct zone *zone) { - struct zone *zone; unsigned long flags; - zone = page_zone(page); - spin_lock_irqsave(&zone->lock, flags); - if (get_pageblock_migratetype(page) != MIGRATE_ISOLATE) - goto out; - set_pageblock_migratetype(page, MIGRATE_MOVABLE); - move_freepages_block(zone, page, MIGRATE_MOVABLE); -out: - spin_unlock_irqrestore(&zone->lock, flags); + int cpu; + struct per_cpu_pageset *pset; + + /* avoid races with drain_pages() */ + local_irq_save(flags); + if (zone->pageset != &boot_pageset) { + for_each_online_cpu(cpu) { + pset = per_cpu_ptr(zone->pageset, cpu); + drain_zonestat(zone, pset); + } + free_percpu(zone->pageset); + zone->pageset = &boot_pageset; + } + local_irq_restore(flags); } #ifdef CONFIG_MEMORY_HOTREMOVE @@ -5433,7 +6482,7 @@ __offline_isolated_pages(unsigned long start_pfn, unsigned long end_pfn) { struct page *page; struct zone *zone; - int order, i; + unsigned int order, i; unsigned long pfn; unsigned long flags; /* find the first valid pfn */ @@ -5451,6 +6500,16 @@ __offline_isolated_pages(unsigned long start_pfn, unsigned long end_pfn) continue; } page = pfn_to_page(pfn); + /* + * The HWPoisoned page may be not in buddy system, and + * page_count() is not 0. + */ + if (unlikely(!PageBuddy(page) && PageHWPoison(page))) { + pfn++; + SetPageReserved(page); + continue; + } + BUG_ON(page_count(page)); BUG_ON(!PageBuddy(page)); order = page_order(page); @@ -5461,8 +6520,6 @@ __offline_isolated_pages(unsigned long start_pfn, unsigned long end_pfn) list_del(&page->lru); rmv_page_order(page); zone->free_area[order].nr_free--; - __mod_zone_page_state(zone, NR_FREE_PAGES, - - (1UL << order)); for (i = 0; i < (1 << order); i++) SetPageReserved((page+i)); pfn += (1 << order); @@ -5477,7 +6534,7 @@ bool is_free_buddy_page(struct page *page) struct zone *zone = page_zone(page); unsigned long pfn = page_to_pfn(page); unsigned long flags; - int order; + unsigned int order; spin_lock_irqsave(&zone->lock, flags); for (order = 0; order < MAX_ORDER; order++) { @@ -5492,7 +6549,7 @@ bool is_free_buddy_page(struct page *page) } #endif -static struct trace_print_flags pageflag_names[] = { +static const struct trace_print_flags pageflag_names[] = { {1UL << PG_locked, "locked" }, {1UL << PG_error, "error" }, {1UL << PG_referenced, "referenced" }, @@ -5516,7 +6573,6 @@ static struct trace_print_flags pageflag_names[] = { {1UL << PG_swapcache, "swapcache" }, {1UL << PG_mappedtodisk, "mappedtodisk" }, {1UL << PG_reclaim, "reclaim" }, - {1UL << PG_buddy, "buddy" }, {1UL << PG_swapbacked, "swapbacked" }, {1UL << PG_unevictable, "unevictable" }, #ifdef CONFIG_MMU @@ -5528,7 +6584,9 @@ static struct trace_print_flags pageflag_names[] = { #ifdef CONFIG_MEMORY_FAILURE {1UL << PG_hwpoison, "hwpoison" }, #endif - {-1UL, NULL }, +#ifdef CONFIG_TRANSPARENT_HUGEPAGE + {1UL << PG_compound_lock, "compound_lock" }, +#endif }; static void dump_page_flags(unsigned long flags) @@ -5537,12 +6595,14 @@ static void dump_page_flags(unsigned long flags) unsigned long mask; int i; + BUILD_BUG_ON(ARRAY_SIZE(pageflag_names) != __NR_PAGEFLAGS); + printk(KERN_ALERT "page flags: %#lx(", flags); /* remove zone id */ flags &= (1UL << NR_PAGEFLAGS) - 1; - for (i = 0; pageflag_names[i].name && flags; i++) { + for (i = 0; i < ARRAY_SIZE(pageflag_names) && flags; i++) { mask = pageflag_names[i].mask; if ((flags & mask) != mask) @@ -5560,11 +6620,25 @@ static void dump_page_flags(unsigned long flags) printk(")\n"); } -void dump_page(struct page *page) +void dump_page_badflags(struct page *page, const char *reason, + unsigned long badflags) { printk(KERN_ALERT "page:%p count:%d mapcount:%d mapping:%p index:%#lx\n", - page, page_count(page), page_mapcount(page), + page, atomic_read(&page->_count), page_mapcount(page), page->mapping, page->index); dump_page_flags(page->flags); + if (reason) + pr_alert("page dumped because: %s\n", reason); + if (page->flags & badflags) { + pr_alert("bad because of flags:\n"); + dump_page_flags(page->flags & badflags); + } + mem_cgroup_print_bad_page(page); +} + +void dump_page(struct page *page, const char *reason) +{ + dump_page_badflags(page, reason, 0); } +EXPORT_SYMBOL(dump_page); |