#include <linux/bootmem.h>
#include <linux/compiler.h>
#include <linux/kernel.h>
+#include <linux/kmemcheck.h>
#include <linux/module.h>
#include <linux/suspend.h>
#include <linux/pagevec.h>
#include <linux/backing-dev.h>
#include <linux/fault-inject.h>
#include <linux/page-isolation.h>
-#include <linux/memcontrol.h>
+#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 <asm/tlbflush.h>
#include <asm/div64.h>
unsigned long totalram_pages __read_mostly;
unsigned long totalreserve_pages __read_mostly;
-long nr_swap_pages;
int percpu_pagelist_fraction;
+gfp_t gfp_allowed_mask __read_mostly = GFP_BOOT_MASK;
+
+#ifdef CONFIG_PM_SLEEP
+/*
+ * The following functions are used by the suspend/hibernate code to temporarily
+ * change gfp_allowed_mask in order to avoid using I/O during memory allocations
+ * while devices are suspended. To avoid races with the suspend/hibernate code,
+ * they should always be called with pm_mutex held (gfp_allowed_mask also should
+ * 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)
+{
+ WARN_ON(!mutex_is_locked(&pm_mutex));
+ gfp_allowed_mask = mask;
+}
+
+gfp_t clear_gfp_allowed_mask(gfp_t mask)
+{
+ gfp_t ret = gfp_allowed_mask;
+
+ WARN_ON(!mutex_is_locked(&pm_mutex));
+ gfp_allowed_mask &= ~mask;
+ return ret;
+}
+#endif /* CONFIG_PM_SLEEP */
#ifdef CONFIG_HUGETLB_PAGE_SIZE_VARIABLE
int pageblock_order __read_mostly;
int min_free_kbytes = 1024;
-unsigned long __meminitdata nr_kernel_pages;
-unsigned long __meminitdata nr_all_pages;
+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
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];
-#ifdef CONFIG_MEMORY_HOTPLUG_RESERVE
- static unsigned long __meminitdata node_boundary_start_pfn[MAX_NUMNODES];
- static unsigned long __meminitdata node_boundary_end_pfn[MAX_NUMNODES];
-#endif /* CONFIG_MEMORY_HOTPLUG_RESERVE */
static unsigned long __initdata required_kernelcore;
static unsigned long __initdata required_movablecore;
static unsigned long __meminitdata zone_movable_pfn[MAX_NUMNODES];
#if MAX_NUMNODES > 1
int nr_node_ids __read_mostly = MAX_NUMNODES;
+int nr_online_nodes __read_mostly = 1;
EXPORT_SYMBOL(nr_node_ids);
+EXPORT_SYMBOL(nr_online_nodes);
#endif
int page_group_by_mobility_disabled __read_mostly;
static void set_pageblock_migratetype(struct page *page, int migratetype)
{
+
+ if (unlikely(page_group_by_mobility_disabled))
+ migratetype = MIGRATE_UNMOVABLE;
+
set_pageblock_flags_group(page, (unsigned long)migratetype,
PB_migrate, PB_migrate_end);
}
+bool oom_killer_disabled __read_mostly;
+
#ifdef CONFIG_DEBUG_VM
static int page_outside_zone_boundaries(struct zone *zone, struct page *page)
{
static void bad_page(struct page *page)
{
- void *pc = page_get_page_cgroup(page);
+ static unsigned long resume;
+ static unsigned long nr_shown;
+ static unsigned long nr_unshown;
- printk(KERN_EMERG "Bad page state in process '%s'\n" KERN_EMERG
- "page:%p flags:0x%0*lx mapping:%p mapcount:%d count:%d\n",
- current->comm, page, (int)(2*sizeof(unsigned long)),
- (unsigned long)page->flags, page->mapping,
- page_mapcount(page), page_count(page));
- if (pc) {
- printk(KERN_EMERG "cgroup:%p\n", pc);
- page_reset_bad_cgroup(page);
+ /* Don't complain about poisoned pages */
+ if (PageHWPoison(page)) {
+ __ClearPageBuddy(page);
+ return;
}
- printk(KERN_EMERG "Trying to fix it up, but a reboot is needed\n"
- KERN_EMERG "Backtrace:\n");
+
+ /*
+ * Allow a burst of 60 reports, then keep quiet for that minute;
+ * or allow a steady drip of one report per second.
+ */
+ if (nr_shown == 60) {
+ if (time_before(jiffies, resume)) {
+ nr_unshown++;
+ goto out;
+ }
+ if (nr_unshown) {
+ printk(KERN_ALERT
+ "BUG: Bad page state: %lu messages suppressed\n",
+ nr_unshown);
+ nr_unshown = 0;
+ }
+ nr_shown = 0;
+ }
+ if (nr_shown++ == 0)
+ resume = jiffies + 60 * HZ;
+
+ printk(KERN_ALERT "BUG: Bad page state in process %s pfn:%05lx\n",
+ current->comm, page_to_pfn(page));
+ dump_page(page);
+
dump_stack();
- page->flags &= ~PAGE_FLAGS_CLEAR_WHEN_BAD;
- set_page_count(page, 0);
- reset_page_mapcount(page);
- page->mapping = NULL;
+out:
+ /* Leave bad fields for debug, except PageBuddy could make trouble */
+ __ClearPageBuddy(page);
add_taint(TAINT_BAD_PAGE);
}
{
int i;
int nr_pages = 1 << order;
- struct page *p = page + 1;
set_compound_page_dtor(page, free_compound_page);
set_compound_order(page, order);
__SetPageHead(page);
- for (i = 1; i < nr_pages; i++, p++) {
- if (unlikely((i & (MAX_ORDER_NR_PAGES - 1)) == 0))
- p = pfn_to_page(page_to_pfn(page) + i);
+ for (i = 1; i < nr_pages; i++) {
+ struct page *p = page + i;
+
__SetPageTail(p);
p->first_page = page;
}
}
-static void destroy_compound_page(struct page *page, unsigned long order)
+static int destroy_compound_page(struct page *page, unsigned long order)
{
int i;
int nr_pages = 1 << order;
- struct page *p = page + 1;
+ int bad = 0;
- if (unlikely(compound_order(page) != order))
+ if (unlikely(compound_order(page) != order) ||
+ unlikely(!PageHead(page))) {
bad_page(page);
+ bad++;
+ }
- if (unlikely(!PageHead(page)))
- bad_page(page);
__ClearPageHead(page);
- for (i = 1; i < nr_pages; i++, p++) {
- if (unlikely((i & (MAX_ORDER_NR_PAGES - 1)) == 0))
- p = pfn_to_page(page_to_pfn(page) + i);
- if (unlikely(!PageTail(p) |
- (p->first_page != page)))
+ for (i = 1; i < nr_pages; i++) {
+ struct page *p = page + i;
+
+ if (unlikely(!PageTail(p) || (p->first_page != page))) {
bad_page(page);
+ bad++;
+ }
__ClearPageTail(p);
}
+
+ return bad;
}
static inline void prep_zero_page(struct page *page, int order, gfp_t gfp_flags)
return 0;
if (PageBuddy(buddy) && page_order(buddy) == order) {
- BUG_ON(page_count(buddy) != 0);
+ VM_BUG_ON(page_count(buddy) != 0);
return 1;
}
return 0;
*/
static inline void __free_one_page(struct page *page,
- struct zone *zone, unsigned int order)
+ struct zone *zone, unsigned int order,
+ int migratetype)
{
unsigned long page_idx;
- int order_size = 1 << order;
- int migratetype = get_pageblock_migratetype(page);
+ unsigned long combined_idx;
+ struct page *buddy;
if (unlikely(PageCompound(page)))
- destroy_compound_page(page, order);
+ if (unlikely(destroy_compound_page(page, order)))
+ return;
+
+ VM_BUG_ON(migratetype == -1);
page_idx = page_to_pfn(page) & ((1 << MAX_ORDER) - 1);
- VM_BUG_ON(page_idx & (order_size - 1));
+ VM_BUG_ON(page_idx & ((1 << order) - 1));
VM_BUG_ON(bad_range(zone, page));
- __mod_zone_page_state(zone, NR_FREE_PAGES, order_size);
while (order < MAX_ORDER-1) {
- unsigned long combined_idx;
- struct page *buddy;
-
buddy = __page_find_buddy(page, page_idx, order);
if (!page_is_buddy(page, buddy, order))
break;
order++;
}
set_page_order(page, order);
- list_add(&page->lru,
- &zone->free_area[order].free_list[migratetype]);
+
+ /*
+ * If this is not the largest possible page, check if the buddy
+ * of the next-highest order is free. If it is, it's possible
+ * that pages are being freed that will coalesce soon. In case,
+ * that is happening, add the free page to the tail of the list
+ * so it's less likely to be used soon and more likely to be merged
+ * as a higher order page
+ */
+ if ((order < MAX_ORDER-1) && 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);
+ if (page_is_buddy(higher_page, higher_buddy, order + 1)) {
+ list_add_tail(&page->lru,
+ &zone->free_area[order].free_list[migratetype]);
+ goto out;
+ }
+ }
+
+ list_add(&page->lru, &zone->free_area[order].free_list[migratetype]);
+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) |
- (page_get_page_cgroup(page) != NULL) |
- (page_count(page) != 0) |
- (page->flags & PAGE_FLAGS_CHECK_AT_FREE)))
+ (atomic_read(&page->_count) != 0) |
+ (page->flags & PAGE_FLAGS_CHECK_AT_FREE))) {
bad_page(page);
- if (PageDirty(page))
- __ClearPageDirty(page);
- if (PageSwapBacked(page))
- __ClearPageSwapBacked(page);
- /*
- * For now, we report if PG_reserved was found set, but do not
- * clear it, and do not free the page. But we shall soon need
- * to do more, for when the ZERO_PAGE count wraps negative.
- */
- return PageReserved(page);
+ return 1;
+ }
+ if (page->flags & PAGE_FLAGS_CHECK_AT_PREP)
+ page->flags &= ~PAGE_FLAGS_CHECK_AT_PREP;
+ return 0;
}
/*
- * Frees a list of pages.
+ * Frees a number of pages from the PCP lists
* Assumes all pages on list are in same zone, and of same order.
* count is the number of pages to free.
*
* And clear the zone's pages_scanned counter, to hold off the "all pages are
* pinned" detection logic.
*/
-static void free_pages_bulk(struct zone *zone, int count,
- struct list_head *list, int order)
+static void free_pcppages_bulk(struct zone *zone, int count,
+ struct per_cpu_pages *pcp)
{
+ int migratetype = 0;
+ int batch_free = 0;
+
spin_lock(&zone->lock);
- zone_clear_flag(zone, ZONE_ALL_UNRECLAIMABLE);
+ zone->all_unreclaimable = 0;
zone->pages_scanned = 0;
- while (count--) {
+
+ __mod_zone_page_state(zone, NR_FREE_PAGES, count);
+ while (count) {
struct page *page;
+ struct list_head *list;
- VM_BUG_ON(list_empty(list));
- page = list_entry(list->prev, struct page, lru);
- /* have to delete it as __free_one_page list manipulates */
- list_del(&page->lru);
- __free_one_page(page, zone, order);
+ /*
+ * Remove pages from lists in a round-robin fashion. A
+ * batch_free count is maintained that is incremented when an
+ * empty list is encountered. This is so more pages are freed
+ * off fuller lists instead of spinning excessively around empty
+ * lists
+ */
+ do {
+ batch_free++;
+ if (++migratetype == MIGRATE_PCPTYPES)
+ migratetype = 0;
+ list = &pcp->lists[migratetype];
+ } while (list_empty(list));
+
+ do {
+ page = list_entry(list->prev, struct page, lru);
+ /* must delete as __free_one_page list manipulates */
+ list_del(&page->lru);
+ /* 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));
+ } while (--count && --batch_free && !list_empty(list));
}
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, int order,
+ int migratetype)
{
spin_lock(&zone->lock);
- zone_clear_flag(zone, ZONE_ALL_UNRECLAIMABLE);
+ zone->all_unreclaimable = 0;
zone->pages_scanned = 0;
- __free_one_page(page, zone, order);
+
+ __mod_zone_page_state(zone, NR_FREE_PAGES, 1 << order);
+ __free_one_page(page, zone, order, migratetype);
spin_unlock(&zone->lock);
}
-static void __free_pages_ok(struct page *page, unsigned int order)
+static bool free_pages_prepare(struct page *page, unsigned int order)
{
- unsigned long flags;
int i;
- int reserved = 0;
+ int bad = 0;
- for (i = 0 ; i < (1 << order) ; ++i)
- reserved += free_pages_check(page + i);
- if (reserved)
- return;
+ trace_mm_page_free_direct(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 (bad)
+ return false;
if (!PageHighMem(page)) {
debug_check_no_locks_freed(page_address(page),PAGE_SIZE<<order);
arch_free_page(page, order);
kernel_map_pages(page, 1 << order, 0);
+ return true;
+}
+
+static void __free_pages_ok(struct page *page, unsigned int order)
+{
+ unsigned long flags;
+ int wasMlocked = __TestClearPageMlocked(page);
+
+ if (!free_pages_prepare(page, order))
+ return;
+
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);
+ free_one_page(page_zone(page), page, order,
+ get_pageblock_migratetype(page));
local_irq_restore(flags);
}
/*
* This page is about to be returned from the page allocator
*/
-static int prep_new_page(struct page *page, int order, gfp_t gfp_flags)
+static inline int check_new_page(struct page *page)
{
if (unlikely(page_mapcount(page) |
(page->mapping != NULL) |
- (page_get_page_cgroup(page) != NULL) |
- (page_count(page) != 0) |
- (page->flags & PAGE_FLAGS_CHECK_AT_PREP)))
+ (atomic_read(&page->_count) != 0) |
+ (page->flags & PAGE_FLAGS_CHECK_AT_PREP))) {
bad_page(page);
-
- /*
- * For now, we report if PG_reserved was found set, but do not
- * clear it, and do not allocate the page: as a safety net.
- */
- if (PageReserved(page))
return 1;
+ }
+ return 0;
+}
+
+static int prep_new_page(struct page *page, int order, gfp_t gfp_flags)
+{
+ int i;
+
+ for (i = 0; i < (1 << order); i++) {
+ struct page *p = page + i;
+ if (unlikely(check_new_page(p)))
+ return 1;
+ }
- page->flags &= ~(1 << PG_uptodate | 1 << PG_error | 1 << PG_reclaim |
- 1 << PG_referenced | 1 << PG_arch_1 |
- 1 << PG_owner_priv_1 | 1 << PG_mappedtodisk);
set_page_private(page, 0);
set_page_refcounted(page);
* Go through the free lists for the given migratetype and remove
* the smallest available page from the freelists
*/
-static struct page *__rmqueue_smallest(struct zone *zone, unsigned int order,
+static inline
+struct page *__rmqueue_smallest(struct zone *zone, unsigned int order,
int migratetype)
{
unsigned int current_order;
list_del(&page->lru);
rmv_page_order(page);
area->nr_free--;
- __mod_zone_page_state(zone, NR_FREE_PAGES, - (1UL << order));
expand(zone, page, order, current_order, area, migratetype);
return page;
}
return move_freepages(zone, start_page, end_page, migratetype);
}
+static void change_pageblock_range(struct page *pageblock_page,
+ int start_order, int migratetype)
+{
+ int nr_pageblocks = 1 << (start_order - pageblock_order);
+
+ while (nr_pageblocks--) {
+ set_pageblock_migratetype(pageblock_page, migratetype);
+ pageblock_page += pageblock_nr_pages;
+ }
+}
+
/* Remove an element from the buddy allocator from the fallback list */
-static struct page *__rmqueue_fallback(struct zone *zone, int order,
- int start_migratetype)
+static inline struct page *
+__rmqueue_fallback(struct zone *zone, int order, int start_migratetype)
{
struct free_area * area;
int current_order;
* agressive about taking ownership of free pages
*/
if (unlikely(current_order >= (pageblock_order >> 1)) ||
- start_migratetype == MIGRATE_RECLAIMABLE) {
+ 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)))
+ if (pages >= (1 << (pageblock_order-1)) ||
+ page_group_by_mobility_disabled)
set_pageblock_migratetype(page,
start_migratetype);
/* Remove the page from the freelists */
list_del(&page->lru);
rmv_page_order(page);
- __mod_zone_page_state(zone, NR_FREE_PAGES,
- -(1UL << order));
- if (current_order == pageblock_order)
- set_pageblock_migratetype(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);
+
+ trace_mm_page_alloc_extfrag(page, order, current_order,
+ start_migratetype, migratetype);
+
return page;
}
}
- /* Use MIGRATE_RESERVE rather than fail an allocation */
- return __rmqueue_smallest(zone, order, MIGRATE_RESERVE);
+ return NULL;
}
/*
{
struct page *page;
+retry_reserve:
page = __rmqueue_smallest(zone, order, migratetype);
- if (unlikely(!page))
+ if (unlikely(!page) && migratetype != MIGRATE_RESERVE) {
page = __rmqueue_fallback(zone, order, migratetype);
+ /*
+ * Use MIGRATE_RESERVE rather than fail an allocation. goto
+ * is used because __rmqueue_smallest is an inline function
+ * and we want just one call site
+ */
+ if (!page) {
+ migratetype = MIGRATE_RESERVE;
+ goto retry_reserve;
+ }
+ }
+
+ trace_mm_page_alloc_zone_locked(page, order, migratetype);
return page;
}
*/
static int rmqueue_bulk(struct zone *zone, unsigned int order,
unsigned long count, struct list_head *list,
- int migratetype)
+ int migratetype, int cold)
{
int i;
* merge IO requests if the physical pages are ordered
* properly.
*/
- list_add(&page->lru, list);
+ if (likely(cold == 0))
+ list_add(&page->lru, list);
+ else
+ list_add_tail(&page->lru, list);
set_page_private(page, migratetype);
list = &page->lru;
}
+ __mod_zone_page_state(zone, NR_FREE_PAGES, -(i << order));
spin_unlock(&zone->lock);
return i;
}
to_drain = pcp->batch;
else
to_drain = pcp->count;
- free_pages_bulk(zone, to_drain, &pcp->list, 0);
+ free_pcppages_bulk(zone, to_drain, pcp);
pcp->count -= to_drain;
local_irq_restore(flags);
}
unsigned long flags;
struct zone *zone;
- for_each_zone(zone) {
+ for_each_populated_zone(zone) {
struct per_cpu_pageset *pset;
struct per_cpu_pages *pcp;
- if (!populated_zone(zone))
- continue;
-
- pset = zone_pcp(zone, cpu);
+ local_irq_save(flags);
+ pset = per_cpu_ptr(zone->pageset, cpu);
pcp = &pset->pcp;
- local_irq_save(flags);
- free_pages_bulk(zone, pcp->count, &pcp->list, 0);
+ free_pcppages_bulk(zone, pcp->count, pcp);
pcp->count = 0;
local_irq_restore(flags);
}
/*
* Free a 0-order page
+ * cold == 1 ? free a cold page : free a hot page
*/
-static void free_hot_cold_page(struct page *page, int cold)
+void free_hot_cold_page(struct page *page, int cold)
{
struct zone *zone = page_zone(page);
struct per_cpu_pages *pcp;
unsigned long flags;
+ int migratetype;
+ int wasMlocked = __TestClearPageMlocked(page);
- if (PageAnon(page))
- page->mapping = NULL;
- if (free_pages_check(page))
+ if (!free_pages_prepare(page, 0))
return;
- if (!PageHighMem(page)) {
- debug_check_no_locks_freed(page_address(page), PAGE_SIZE);
- debug_check_no_obj_freed(page_address(page), PAGE_SIZE);
- }
- arch_free_page(page, 0);
- kernel_map_pages(page, 1, 0);
-
- pcp = &zone_pcp(zone, get_cpu())->pcp;
+ migratetype = get_pageblock_migratetype(page);
+ set_page_private(page, migratetype);
local_irq_save(flags);
+ if (unlikely(wasMlocked))
+ free_page_mlock(page);
__count_vm_event(PGFREE);
+
+ /*
+ * We only track unmovable, reclaimable and movable on pcp lists.
+ * Free ISOLATE pages back to the allocator because they are being
+ * offlined but treat RESERVE as movable pages so we can get those
+ * areas back if necessary. Otherwise, we may have to free
+ * excessively into the page allocator
+ */
+ if (migratetype >= MIGRATE_PCPTYPES) {
+ if (unlikely(migratetype == MIGRATE_ISOLATE)) {
+ free_one_page(zone, page, 0, migratetype);
+ goto out;
+ }
+ migratetype = MIGRATE_MOVABLE;
+ }
+
+ pcp = &this_cpu_ptr(zone->pageset)->pcp;
if (cold)
- list_add_tail(&page->lru, &pcp->list);
+ list_add_tail(&page->lru, &pcp->lists[migratetype]);
else
- list_add(&page->lru, &pcp->list);
- set_page_private(page, get_pageblock_migratetype(page));
+ list_add(&page->lru, &pcp->lists[migratetype]);
pcp->count++;
if (pcp->count >= pcp->high) {
- free_pages_bulk(zone, pcp->batch, &pcp->list, 0);
+ free_pcppages_bulk(zone, pcp->batch, pcp);
pcp->count -= pcp->batch;
}
- local_irq_restore(flags);
- put_cpu();
-}
-void free_hot_page(struct page *page)
-{
- free_hot_cold_page(page, 0);
-}
-
-void free_cold_page(struct page *page)
-{
- free_hot_cold_page(page, 1);
+out:
+ local_irq_restore(flags);
}
/*
VM_BUG_ON(PageCompound(page));
VM_BUG_ON(!page_count(page));
+
+#ifdef CONFIG_KMEMCHECK
+ /*
+ * Split shadow pages too, because free(page[0]) would
+ * otherwise free the whole shadow.
+ */
+ if (kmemcheck_page_is_tracked(page))
+ split_page(virt_to_page(page[0].shadow), order);
+#endif
+
for (i = 1; i < (1 << order); i++)
set_page_refcounted(page + i);
}
/*
+ * Similar to split_page except the page is already free. As this is only
+ * being used for migration, the migratetype of the block also changes.
+ * As this is called with interrupts disabled, the caller is responsible
+ * for calling arch_alloc_page() and kernel_map_page() after interrupts
+ * are enabled.
+ *
+ * Note: this is probably too low level an operation for use in drivers.
+ * Please consult with lkml before using this in your driver.
+ */
+int split_free_page(struct page *page)
+{
+ unsigned int order;
+ unsigned long watermark;
+ struct zone *zone;
+
+ 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))
+ 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;
+}
+
+/*
* Really, prep_compound_page() should be called from __rmqueue_bulk(). But
* we cheat by calling it from here, in the order > 0 path. Saves a branch
* or two.
*/
-static struct page *buffered_rmqueue(struct zone *preferred_zone,
- struct zone *zone, int order, gfp_t gfp_flags)
+static inline
+struct page *buffered_rmqueue(struct zone *preferred_zone,
+ struct zone *zone, int order, gfp_t gfp_flags,
+ int migratetype)
{
unsigned long flags;
struct page *page;
int cold = !!(gfp_flags & __GFP_COLD);
- int cpu;
- int migratetype = allocflags_to_migratetype(gfp_flags);
again:
- cpu = get_cpu();
if (likely(order == 0)) {
struct per_cpu_pages *pcp;
+ struct list_head *list;
- pcp = &zone_pcp(zone, cpu)->pcp;
local_irq_save(flags);
- if (!pcp->count) {
- pcp->count = rmqueue_bulk(zone, 0,
- pcp->batch, &pcp->list, migratetype);
- if (unlikely(!pcp->count))
+ pcp = &this_cpu_ptr(zone->pageset)->pcp;
+ list = &pcp->lists[migratetype];
+ if (list_empty(list)) {
+ pcp->count += rmqueue_bulk(zone, 0,
+ pcp->batch, list,
+ migratetype, cold);
+ if (unlikely(list_empty(list)))
goto failed;
}
- /* Find a page of the appropriate migrate type */
- if (cold) {
- list_for_each_entry_reverse(page, &pcp->list, lru)
- if (page_private(page) == migratetype)
- break;
- } else {
- list_for_each_entry(page, &pcp->list, lru)
- if (page_private(page) == migratetype)
- break;
- }
-
- /* Allocate more to the pcp list if necessary */
- if (unlikely(&page->lru == &pcp->list)) {
- pcp->count += rmqueue_bulk(zone, 0,
- pcp->batch, &pcp->list, migratetype);
- page = list_entry(pcp->list.next, struct page, lru);
- }
+ if (cold)
+ page = list_entry(list->prev, struct page, lru);
+ else
+ page = list_entry(list->next, struct page, lru);
list_del(&page->lru);
pcp->count--;
} else {
+ if (unlikely(gfp_flags & __GFP_NOFAIL)) {
+ /*
+ * __GFP_NOFAIL is not to be used in new code.
+ *
+ * All __GFP_NOFAIL callers should be fixed so that they
+ * properly detect and handle allocation failures.
+ *
+ * We most definitely don't want callers attempting to
+ * allocate greater than order-1 page units with
+ * __GFP_NOFAIL.
+ */
+ WARN_ON_ONCE(order > 1);
+ }
spin_lock_irqsave(&zone->lock, flags);
page = __rmqueue(zone, order, migratetype);
spin_unlock(&zone->lock);
if (!page)
goto failed;
+ __mod_zone_page_state(zone, NR_FREE_PAGES, -(1 << order));
}
__count_zone_vm_events(PGALLOC, zone, 1 << order);
zone_statistics(preferred_zone, zone);
local_irq_restore(flags);
- put_cpu();
VM_BUG_ON(bad_range(zone, page));
if (prep_new_page(page, order, gfp_flags))
failed:
local_irq_restore(flags);
- put_cpu();
return NULL;
}
-#define ALLOC_NO_WATERMARKS 0x01 /* don't check watermarks at all */
-#define ALLOC_WMARK_MIN 0x02 /* use pages_min watermark */
-#define ALLOC_WMARK_LOW 0x04 /* use pages_low watermark */
-#define ALLOC_WMARK_HIGH 0x08 /* use pages_high watermark */
+/* 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 */
*/
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 zonelist *zonelist, int high_zoneidx, int alloc_flags,
+ struct zone *preferred_zone, int migratetype)
{
struct zoneref *z;
struct page *page = NULL;
int classzone_idx;
- struct zone *zone, *preferred_zone;
+ 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 */
- (void)first_zones_zonelist(zonelist, high_zoneidx, nodemask,
- &preferred_zone);
- if (!preferred_zone)
- return NULL;
-
classzone_idx = zone_idx(preferred_zone);
-
zonelist_scan:
/*
* Scan zonelist, looking for a zone with enough free.
!cpuset_zone_allowed_softwall(zone, gfp_mask))
goto try_next_zone;
+ BUILD_BUG_ON(ALLOC_NO_WATERMARKS < NR_WMARK);
if (!(alloc_flags & ALLOC_NO_WATERMARKS)) {
unsigned long mark;
- if (alloc_flags & ALLOC_WMARK_MIN)
- mark = zone->pages_min;
- else if (alloc_flags & ALLOC_WMARK_LOW)
- mark = zone->pages_low;
- else
- mark = zone->pages_high;
- if (!zone_watermark_ok(zone, order, mark,
- classzone_idx, alloc_flags)) {
- if (!zone_reclaim_mode ||
- !zone_reclaim(zone, gfp_mask, order))
+ int ret;
+
+ mark = zone->watermark[alloc_flags & ALLOC_WMARK_MASK];
+ if (zone_watermark_ok(zone, order, mark,
+ classzone_idx, alloc_flags))
+ goto try_this_zone;
+
+ if (zone_reclaim_mode == 0)
+ goto this_zone_full;
+
+ ret = zone_reclaim(zone, gfp_mask, order);
+ switch (ret) {
+ case ZONE_RECLAIM_NOSCAN:
+ /* did not scan */
+ goto try_next_zone;
+ case ZONE_RECLAIM_FULL:
+ /* scanned but unreclaimable */
+ goto this_zone_full;
+ default:
+ /* did we reclaim enough */
+ if (!zone_watermark_ok(zone, order, mark,
+ classzone_idx, alloc_flags))
goto this_zone_full;
}
}
- page = buffered_rmqueue(preferred_zone, zone, order, gfp_mask);
+try_this_zone:
+ page = buffered_rmqueue(preferred_zone, zone, order,
+ gfp_mask, migratetype);
if (page)
break;
this_zone_full:
if (NUMA_BUILD)
zlc_mark_zone_full(zonelist, z);
try_next_zone:
- if (NUMA_BUILD && !did_zlc_setup) {
- /* we do zlc_setup after the first zone is tried */
+ 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;
return page;
}
+static inline int
+should_alloc_retry(gfp_t gfp_mask, unsigned int order,
+ unsigned long pages_reclaimed)
+{
+ /* Do not loop if specifically requested */
+ if (gfp_mask & __GFP_NORETRY)
+ return 0;
+
+ /*
+ * In this implementation, order <= PAGE_ALLOC_COSTLY_ORDER
+ * means __GFP_NOFAIL, but that may not be true in other
+ * implementations.
+ */
+ if (order <= PAGE_ALLOC_COSTLY_ORDER)
+ return 1;
+
+ /*
+ * For order > PAGE_ALLOC_COSTLY_ORDER, if __GFP_REPEAT is
+ * specified, then we retry until we no longer reclaim any pages
+ * (above), or we've reclaimed an order of pages at least as
+ * large as the allocation's order. In both cases, if the
+ * allocation still fails, we stop retrying.
+ */
+ if (gfp_mask & __GFP_REPEAT && pages_reclaimed < (1 << order))
+ return 1;
+
+ /*
+ * Don't let big-order allocations loop unless the caller
+ * explicitly requests that.
+ */
+ if (gfp_mask & __GFP_NOFAIL)
+ return 1;
+
+ return 0;
+}
+
+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)
+{
+ struct page *page;
+
+ /* Acquire the OOM killer lock for the zones in zonelist */
+ if (!try_set_zone_oom(zonelist, gfp_mask)) {
+ schedule_timeout_uninterruptible(1);
+ return NULL;
+ }
+
+ /*
+ * Go through the zonelist yet one more time, keep very high watermark
+ * here, this is only to catch a parallel oom killing, we must fail if
+ * we're still under heavy pressure.
+ */
+ page = get_page_from_freelist(gfp_mask|__GFP_HARDWALL, nodemask,
+ order, zonelist, high_zoneidx,
+ ALLOC_WMARK_HIGH|ALLOC_CPUSET,
+ preferred_zone, migratetype);
+ if (page)
+ goto out;
+
+ if (!(gfp_mask & __GFP_NOFAIL)) {
+ /* The OOM killer will not help higher order allocs */
+ if (order > PAGE_ALLOC_COSTLY_ORDER)
+ goto out;
+ /*
+ * GFP_THISNODE contains __GFP_NORETRY and we never hit this.
+ * Sanity check for bare calls of __GFP_THISNODE, not real OOM.
+ * The caller should handle page allocation failure by itself if
+ * it specifies __GFP_THISNODE.
+ * Note: Hugepage uses it but will hit PAGE_ALLOC_COSTLY_ORDER.
+ */
+ if (gfp_mask & __GFP_THISNODE)
+ goto out;
+ }
+ /* Exhausted what can be done so it's blamo time */
+ out_of_memory(zonelist, gfp_mask, order, nodemask);
+
+out:
+ clear_zonelist_oom(zonelist, gfp_mask);
+ return page;
+}
+
+#ifdef CONFIG_COMPACTION
+/* Try memory compaction for high-order allocations before reclaim */
+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)
+{
+ struct page *page;
+
+ if (!order || compaction_deferred(preferred_zone))
+ return NULL;
+
+ *did_some_progress = try_to_compact_pages(zonelist, order, gfp_mask,
+ nodemask);
+ if (*did_some_progress != COMPACT_SKIPPED) {
+
+ /* Page migration frees to the PCP lists but we want merging */
+ drain_pages(get_cpu());
+ put_cpu();
+
+ page = get_page_from_freelist(gfp_mask, nodemask,
+ order, zonelist, high_zoneidx,
+ alloc_flags, preferred_zone,
+ migratetype);
+ if (page) {
+ preferred_zone->compact_considered = 0;
+ preferred_zone->compact_defer_shift = 0;
+ count_vm_event(COMPACTSUCCESS);
+ return page;
+ }
+
+ /*
+ * It's bad if compaction run occurs and fails.
+ * The most likely reason is that pages exist,
+ * but not enough to satisfy watermarks.
+ */
+ count_vm_event(COMPACTFAIL);
+ defer_compaction(preferred_zone);
+
+ cond_resched();
+ }
+
+ return NULL;
+}
+#else
+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)
+{
+ 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)
+{
+ struct page *page = NULL;
+ struct reclaim_state reclaim_state;
+ struct task_struct *p = current;
+
+ cond_resched();
+
+ /* We now go into synchronous reclaim */
+ cpuset_memory_pressure_bump();
+ p->flags |= PF_MEMALLOC;
+ lockdep_set_current_reclaim_state(gfp_mask);
+ reclaim_state.reclaimed_slab = 0;
+ p->reclaim_state = &reclaim_state;
+
+ *did_some_progress = try_to_free_pages(zonelist, order, gfp_mask, nodemask);
+
+ p->reclaim_state = NULL;
+ lockdep_clear_current_reclaim_state();
+ p->flags &= ~PF_MEMALLOC;
+
+ cond_resched();
+
+ if (order != 0)
+ drain_all_pages();
+
+ if (likely(*did_some_progress))
+ page = get_page_from_freelist(gfp_mask, nodemask, order,
+ zonelist, high_zoneidx,
+ alloc_flags, preferred_zone,
+ migratetype);
+ return page;
+}
+
/*
- * This is the 'heart' of the zoned buddy allocator.
+ * This is called in the allocator slow-path if the allocation request is of
+ * sufficient urgency to ignore watermarks and take other desperate measures
*/
-struct page *
-__alloc_pages_internal(gfp_t gfp_mask, unsigned int order,
- struct zonelist *zonelist, nodemask_t *nodemask)
+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)
+{
+ struct page *page;
+
+ do {
+ page = get_page_from_freelist(gfp_mask, nodemask, order,
+ zonelist, high_zoneidx, ALLOC_NO_WATERMARKS,
+ preferred_zone, migratetype);
+
+ if (!page && gfp_mask & __GFP_NOFAIL)
+ congestion_wait(BLK_RW_ASYNC, HZ/50);
+ } while (!page && (gfp_mask & __GFP_NOFAIL));
+
+ return page;
+}
+
+static inline
+void wake_all_kswapd(unsigned int order, struct zonelist *zonelist,
+ enum zone_type high_zoneidx)
{
- const gfp_t wait = gfp_mask & __GFP_WAIT;
- enum zone_type high_zoneidx = gfp_zone(gfp_mask);
struct zoneref *z;
struct zone *zone;
- struct page *page;
- struct reclaim_state reclaim_state;
- struct task_struct *p = current;
- int do_retry;
- int alloc_flags;
- unsigned long did_some_progress;
- unsigned long pages_reclaimed = 0;
- might_sleep_if(wait);
+ for_each_zone_zonelist(zone, z, zonelist, high_zoneidx)
+ wakeup_kswapd(zone, order);
+}
- if (should_fail_alloc_page(gfp_mask, order))
- return NULL;
+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;
-restart:
- z = zonelist->_zonerefs; /* the list of zones suitable for gfp_mask */
+ /* __GFP_HIGH is assumed to be the same as ALLOC_HIGH to save a branch. */
+ BUILD_BUG_ON(__GFP_HIGH != ALLOC_HIGH);
- if (unlikely(!z->zone)) {
+ /*
+ * 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).
+ */
+ alloc_flags |= (gfp_mask & __GFP_HIGH);
+
+ if (!wait) {
+ alloc_flags |= ALLOC_HARDER;
/*
- * Happens if we have an empty zonelist as a result of
- * GFP_THISNODE being used on a memoryless node
+ * Ignore cpuset if GFP_ATOMIC (!wait) rather than fail alloc.
+ * See also cpuset_zone_allowed() comment in kernel/cpuset.c.
*/
- return NULL;
+ alloc_flags &= ~ALLOC_CPUSET;
+ } else if (unlikely(rt_task(p)) && !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))))
+ alloc_flags |= ALLOC_NO_WATERMARKS;
}
- page = get_page_from_freelist(gfp_mask|__GFP_HARDWALL, nodemask, order,
- zonelist, high_zoneidx, ALLOC_WMARK_LOW|ALLOC_CPUSET);
- if (page)
- goto got_pg;
+ return alloc_flags;
+}
+
+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)
+{
+ 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;
+
+ /*
+ * In the slowpath, we sanity check order to avoid ever trying to
+ * reclaim >= MAX_ORDER areas which will never succeed. Callers may
+ * be using allocators in order of preference for an area that is
+ * too large.
+ */
+ if (order >= MAX_ORDER) {
+ WARN_ON_ONCE(!(gfp_mask & __GFP_NOWARN));
+ return NULL;
+ }
/*
* GFP_THISNODE (meaning __GFP_THISNODE, __GFP_NORETRY and
if (NUMA_BUILD && (gfp_mask & GFP_THISNODE) == GFP_THISNODE)
goto nopage;
- for_each_zone_zonelist(zone, z, zonelist, high_zoneidx)
- wakeup_kswapd(zone, order);
+restart:
+ wake_all_kswapd(order, zonelist, high_zoneidx);
/*
* OK, we're below the kswapd watermark and have kicked background
* reclaim. Now things get more complex, so set up alloc_flags according
* to how we want to proceed.
- *
- * 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).
*/
- alloc_flags = ALLOC_WMARK_MIN;
- if ((unlikely(rt_task(p)) && !in_interrupt()) || !wait)
- alloc_flags |= ALLOC_HARDER;
- if (gfp_mask & __GFP_HIGH)
- alloc_flags |= ALLOC_HIGH;
- if (wait)
- alloc_flags |= ALLOC_CPUSET;
+ alloc_flags = gfp_to_alloc_flags(gfp_mask);
- /*
- * Go through the zonelist again. Let __GFP_HIGH and allocations
- * coming from realtime tasks go deeper into reserves.
- *
- * This is the last chance, in general, before the goto nopage.
- * Ignore cpuset if GFP_ATOMIC (!wait) rather than fail alloc.
- * See also cpuset_zone_allowed() comment in kernel/cpuset.c.
- */
+ /* 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);
+ high_zoneidx, alloc_flags & ~ALLOC_NO_WATERMARKS,
+ preferred_zone, migratetype);
if (page)
goto got_pg;
- /* This allocation should allow future memory freeing. */
-
rebalance:
- if (((p->flags & PF_MEMALLOC) || unlikely(test_thread_flag(TIF_MEMDIE)))
- && !in_interrupt()) {
- if (!(gfp_mask & __GFP_NOMEMALLOC)) {
-nofail_alloc:
- /* go through the zonelist yet again, ignoring mins */
- page = get_page_from_freelist(gfp_mask, nodemask, order,
- zonelist, high_zoneidx, ALLOC_NO_WATERMARKS);
- if (page)
- goto got_pg;
- if (gfp_mask & __GFP_NOFAIL) {
- congestion_wait(WRITE, HZ/50);
- goto nofail_alloc;
- }
- }
- goto nopage;
+ /* Allocate without watermarks if the context allows */
+ if (alloc_flags & ALLOC_NO_WATERMARKS) {
+ page = __alloc_pages_high_priority(gfp_mask, order,
+ zonelist, high_zoneidx, nodemask,
+ preferred_zone, migratetype);
+ if (page)
+ goto got_pg;
}
/* Atomic allocations - we can't balance anything */
if (!wait)
goto nopage;
- cond_resched();
+ /* Avoid recursion of direct reclaim */
+ if (p->flags & PF_MEMALLOC)
+ goto nopage;
- /* We now go into synchronous reclaim */
- cpuset_memory_pressure_bump();
- p->flags |= PF_MEMALLOC;
- reclaim_state.reclaimed_slab = 0;
- p->reclaim_state = &reclaim_state;
+ /* Avoid allocations with no watermarks from looping endlessly */
+ if (test_thread_flag(TIF_MEMDIE) && !(gfp_mask & __GFP_NOFAIL))
+ goto nopage;
- did_some_progress = try_to_free_pages(zonelist, order, gfp_mask);
+ /* Try direct compaction */
+ page = __alloc_pages_direct_compact(gfp_mask, order,
+ zonelist, high_zoneidx,
+ nodemask,
+ alloc_flags, preferred_zone,
+ migratetype, &did_some_progress);
+ if (page)
+ goto got_pg;
- p->reclaim_state = NULL;
- p->flags &= ~PF_MEMALLOC;
+ /* 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);
+ if (page)
+ goto got_pg;
- cond_resched();
+ /*
+ * If we failed to make any progress reclaiming, then we are
+ * 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_killer_disabled)
+ goto nopage;
+ page = __alloc_pages_may_oom(gfp_mask, order,
+ zonelist, high_zoneidx,
+ nodemask, preferred_zone,
+ migratetype);
+ if (page)
+ goto got_pg;
- if (order != 0)
- drain_all_pages();
+ /*
+ * The OOM killer does not trigger for high-order
+ * ~__GFP_NOFAIL allocations so if no progress is being
+ * made, there are no other options and retrying is
+ * unlikely to help.
+ */
+ if (order > PAGE_ALLOC_COSTLY_ORDER &&
+ !(gfp_mask & __GFP_NOFAIL))
+ goto nopage;
- if (likely(did_some_progress)) {
- page = get_page_from_freelist(gfp_mask, nodemask, order,
- zonelist, high_zoneidx, alloc_flags);
- if (page)
- goto got_pg;
- } else if ((gfp_mask & __GFP_FS) && !(gfp_mask & __GFP_NORETRY)) {
- if (!try_set_zone_oom(zonelist, gfp_mask)) {
- schedule_timeout_uninterruptible(1);
goto restart;
}
-
- /*
- * Go through the zonelist yet one more time, keep
- * very high watermark here, this is only to catch
- * a parallel oom killing, we must fail if we're still
- * under heavy pressure.
- */
- page = get_page_from_freelist(gfp_mask|__GFP_HARDWALL, nodemask,
- order, zonelist, high_zoneidx,
- ALLOC_WMARK_HIGH|ALLOC_CPUSET);
- if (page) {
- clear_zonelist_oom(zonelist, gfp_mask);
- goto got_pg;
- }
-
- /* The OOM killer will not help higher order allocs so fail */
- if (order > PAGE_ALLOC_COSTLY_ORDER) {
- clear_zonelist_oom(zonelist, gfp_mask);
- goto nopage;
- }
-
- out_of_memory(zonelist, gfp_mask, order);
- clear_zonelist_oom(zonelist, gfp_mask);
- goto restart;
}
- /*
- * Don't let big-order allocations loop unless the caller explicitly
- * requests that. Wait for some write requests to complete then retry.
- *
- * In this implementation, order <= PAGE_ALLOC_COSTLY_ORDER
- * means __GFP_NOFAIL, but that may not be true in other
- * implementations.
- *
- * For order > PAGE_ALLOC_COSTLY_ORDER, if __GFP_REPEAT is
- * specified, then we retry until we no longer reclaim any pages
- * (above), or we've reclaimed an order of pages at least as
- * large as the allocation's order. In both cases, if the
- * allocation still fails, we stop retrying.
- */
+ /* Check if we should retry the allocation */
pages_reclaimed += did_some_progress;
- do_retry = 0;
- if (!(gfp_mask & __GFP_NORETRY)) {
- if (order <= PAGE_ALLOC_COSTLY_ORDER) {
- do_retry = 1;
- } else {
- if (gfp_mask & __GFP_REPEAT &&
- pages_reclaimed < (1 << order))
- do_retry = 1;
- }
- if (gfp_mask & __GFP_NOFAIL)
- do_retry = 1;
- }
- if (do_retry) {
- congestion_wait(WRITE, HZ/50);
+ if (should_alloc_retry(gfp_mask, order, pages_reclaimed)) {
+ /* Wait for some write requests to complete then retry */
+ congestion_wait(BLK_RW_ASYNC, HZ/50);
goto rebalance;
}
dump_stack();
show_mem();
}
+ return page;
got_pg:
+ if (kmemcheck_enabled)
+ kmemcheck_pagealloc_alloc(page, order, gfp_mask);
return page;
+
}
-EXPORT_SYMBOL(__alloc_pages_internal);
+
+/*
+ * This is the 'heart' of the zoned buddy allocator.
+ */
+struct page *
+__alloc_pages_nodemask(gfp_t gfp_mask, unsigned int order,
+ struct zonelist *zonelist, nodemask_t *nodemask)
+{
+ enum zone_type high_zoneidx = gfp_zone(gfp_mask);
+ struct zone *preferred_zone;
+ struct page *page;
+ int migratetype = allocflags_to_migratetype(gfp_mask);
+
+ gfp_mask &= gfp_allowed_mask;
+
+ lockdep_trace_alloc(gfp_mask);
+
+ might_sleep_if(gfp_mask & __GFP_WAIT);
+
+ if (should_fail_alloc_page(gfp_mask, order))
+ return NULL;
+
+ /*
+ * Check the zones suitable for the gfp_mask contain at least one
+ * valid zone. It's possible to have an empty zonelist as a result
+ * of GFP_THISNODE and a memoryless node
+ */
+ if (unlikely(!zonelist->_zonerefs->zone))
+ return NULL;
+
+ get_mems_allowed();
+ /* 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;
+ }
+
+ /* 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))
+ page = __alloc_pages_slowpath(gfp_mask, order,
+ zonelist, high_zoneidx, nodemask,
+ preferred_zone, migratetype);
+ put_mems_allowed();
+
+ trace_mm_page_alloc(page, order, gfp_mask, migratetype);
+ return page;
+}
+EXPORT_SYMBOL(__alloc_pages_nodemask);
/*
* Common helper functions.
*/
unsigned long __get_free_pages(gfp_t gfp_mask, unsigned int order)
{
- struct page * page;
+ struct page *page;
+
+ /*
+ * __get_free_pages() returns a 32-bit address, which cannot represent
+ * a highmem page
+ */
+ VM_BUG_ON((gfp_mask & __GFP_HIGHMEM) != 0);
+
page = alloc_pages(gfp_mask, order);
if (!page)
return 0;
return (unsigned long) page_address(page);
}
-
EXPORT_SYMBOL(__get_free_pages);
unsigned long get_zeroed_page(gfp_t gfp_mask)
{
- struct page * page;
-
- /*
- * get_zeroed_page() returns a 32-bit address, which cannot represent
- * a highmem page
- */
- VM_BUG_ON((gfp_mask & __GFP_HIGHMEM) != 0);
-
- page = alloc_pages(gfp_mask | __GFP_ZERO, 0);
- if (page)
- return (unsigned long) page_address(page);
- return 0;
+ return __get_free_pages(gfp_mask | __GFP_ZERO, 0);
}
-
EXPORT_SYMBOL(get_zeroed_page);
void __pagevec_free(struct pagevec *pvec)
{
int i = pagevec_count(pvec);
- while (--i >= 0)
+ 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_page(page);
+ free_hot_cold_page(page, 0);
else
__free_pages_ok(page, order);
}
unsigned long alloc_end = addr + (PAGE_SIZE << order);
unsigned long used = addr + PAGE_ALIGN(size);
- split_page(virt_to_page(addr), order);
+ split_page(virt_to_page((void *)addr), order);
while (used < alloc_end) {
free_page(used);
used += PAGE_SIZE;
for_each_zone_zonelist(zone, z, zonelist, offset) {
unsigned long size = zone->present_pages;
- unsigned long high = zone->pages_high;
+ unsigned long high = high_wmark_pages(zone);
if (size > high)
sum += size - high;
}
int cpu;
struct zone *zone;
- for_each_zone(zone) {
- if (!populated_zone(zone))
- continue;
-
+ for_each_populated_zone(zone) {
show_node(zone);
printk("%s per-cpu:\n", zone->name);
for_each_online_cpu(cpu) {
struct per_cpu_pageset *pageset;
- pageset = zone_pcp(zone, cpu);
+ pageset = per_cpu_ptr(zone->pageset, cpu);
printk("CPU %4d: hi:%5d, btch:%4d usd:%4d\n",
cpu, pageset->pcp.high,
}
}
- printk("Active:%lu inactive:%lu dirty:%lu writeback:%lu unstable:%lu\n"
- " free:%lu slab:%lu mapped:%lu pagetables:%lu bounce:%lu\n",
- global_page_state(NR_ACTIVE),
- global_page_state(NR_INACTIVE),
+ printk("active_anon:%lu inactive_anon:%lu isolated_anon:%lu\n"
+ " active_file:%lu inactive_file:%lu isolated_file:%lu\n"
+ " 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",
+ global_page_state(NR_ACTIVE_ANON),
+ global_page_state(NR_INACTIVE_ANON),
+ global_page_state(NR_ISOLATED_ANON),
+ global_page_state(NR_ACTIVE_FILE),
+ global_page_state(NR_INACTIVE_FILE),
+ global_page_state(NR_ISOLATED_FILE),
+ global_page_state(NR_UNEVICTABLE),
global_page_state(NR_FILE_DIRTY),
global_page_state(NR_WRITEBACK),
global_page_state(NR_UNSTABLE_NFS),
global_page_state(NR_FREE_PAGES),
- global_page_state(NR_SLAB_RECLAIMABLE) +
- global_page_state(NR_SLAB_UNRECLAIMABLE),
+ global_page_state(NR_SLAB_RECLAIMABLE),
+ global_page_state(NR_SLAB_UNRECLAIMABLE),
global_page_state(NR_FILE_MAPPED),
+ global_page_state(NR_SHMEM),
global_page_state(NR_PAGETABLE),
global_page_state(NR_BOUNCE));
- for_each_zone(zone) {
+ for_each_populated_zone(zone) {
int i;
- if (!populated_zone(zone))
- continue;
-
show_node(zone);
printk("%s"
" free:%lukB"
" min:%lukB"
" low:%lukB"
" high:%lukB"
- " active:%lukB"
- " inactive:%lukB"
+ " active_anon:%lukB"
+ " inactive_anon:%lukB"
+ " active_file:%lukB"
+ " inactive_file:%lukB"
+ " unevictable:%lukB"
+ " isolated(anon):%lukB"
+ " isolated(file):%lukB"
" present:%lukB"
+ " mlocked:%lukB"
+ " dirty:%lukB"
+ " writeback:%lukB"
+ " mapped:%lukB"
+ " shmem:%lukB"
+ " slab_reclaimable:%lukB"
+ " slab_unreclaimable:%lukB"
+ " kernel_stack:%lukB"
+ " pagetables:%lukB"
+ " unstable:%lukB"
+ " bounce:%lukB"
+ " writeback_tmp:%lukB"
" pages_scanned:%lu"
" all_unreclaimable? %s"
"\n",
zone->name,
K(zone_page_state(zone, NR_FREE_PAGES)),
- K(zone->pages_min),
- K(zone->pages_low),
- K(zone->pages_high),
- K(zone_page_state(zone, NR_ACTIVE)),
- K(zone_page_state(zone, NR_INACTIVE)),
+ K(min_wmark_pages(zone)),
+ K(low_wmark_pages(zone)),
+ K(high_wmark_pages(zone)),
+ K(zone_page_state(zone, NR_ACTIVE_ANON)),
+ K(zone_page_state(zone, NR_INACTIVE_ANON)),
+ K(zone_page_state(zone, NR_ACTIVE_FILE)),
+ K(zone_page_state(zone, NR_INACTIVE_FILE)),
+ K(zone_page_state(zone, NR_UNEVICTABLE)),
+ K(zone_page_state(zone, NR_ISOLATED_ANON)),
+ K(zone_page_state(zone, NR_ISOLATED_FILE)),
K(zone->present_pages),
+ K(zone_page_state(zone, NR_MLOCK)),
+ K(zone_page_state(zone, NR_FILE_DIRTY)),
+ K(zone_page_state(zone, NR_WRITEBACK)),
+ K(zone_page_state(zone, NR_FILE_MAPPED)),
+ K(zone_page_state(zone, NR_SHMEM)),
+ K(zone_page_state(zone, NR_SLAB_RECLAIMABLE)),
+ K(zone_page_state(zone, NR_SLAB_UNRECLAIMABLE)),
+ zone_page_state(zone, NR_KERNEL_STACK) *
+ THREAD_SIZE / 1024,
+ 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_WRITEBACK_TEMP)),
zone->pages_scanned,
- (zone_is_all_unreclaimable(zone) ? "yes" : "no")
+ (zone->all_unreclaimable ? "yes" : "no")
);
printk("lowmem_reserve[]:");
for (i = 0; i < MAX_NR_ZONES; i++)
printk("\n");
}
- for_each_zone(zone) {
+ for_each_populated_zone(zone) {
unsigned long nr[MAX_ORDER], flags, order, total = 0;
- if (!populated_zone(zone))
- continue;
-
show_node(zone);
printk("%s: ", zone->name);
* sysctl handler for numa_zonelist_order
*/
int numa_zonelist_order_handler(ctl_table *table, int write,
- struct file *file, void __user *buffer, size_t *length,
+ void __user *buffer, size_t *length,
loff_t *ppos)
{
char saved_string[NUMA_ZONELIST_ORDER_LEN];
int ret;
+ static DEFINE_MUTEX(zl_order_mutex);
+ mutex_lock(&zl_order_mutex);
if (write)
- strncpy(saved_string, (char*)table->data,
- NUMA_ZONELIST_ORDER_LEN);
- ret = proc_dostring(table, write, file, buffer, length, ppos);
+ strcpy(saved_string, (char*)table->data);
+ ret = proc_dostring(table, write, buffer, length, ppos);
if (ret)
- return ret;
+ goto out;
if (write) {
int oldval = user_zonelist_order;
if (__parse_numa_zonelist_order((char*)table->data)) {
strncpy((char*)table->data, saved_string,
NUMA_ZONELIST_ORDER_LEN);
user_zonelist_order = oldval;
- } else if (oldval != user_zonelist_order)
- build_all_zonelists();
+ } else if (oldval != user_zonelist_order) {
+ mutex_lock(&zonelists_mutex);
+ build_all_zonelists(NULL);
+ mutex_unlock(&zonelists_mutex);
+ }
}
- return 0;
+out:
+ mutex_unlock(&zl_order_mutex);
+ return ret;
}
-#define MAX_NODE_LOAD (num_online_nodes())
+#define MAX_NODE_LOAD (nr_online_nodes)
static int node_load[MAX_NUMNODES];
/**
int n, val;
int min_val = INT_MAX;
int best_node = -1;
- node_to_cpumask_ptr(tmp, 0);
+ const struct cpumask *tmp = cpumask_of_node(0);
/* Use the local node if we haven't already */
if (!node_isset(node, *used_node_mask)) {
val += (n < node);
/* Give preference to headless and unused nodes */
- node_to_cpumask_ptr_next(tmp, n);
- if (!cpus_empty(*tmp))
+ tmp = cpumask_of_node(n);
+ if (!cpumask_empty(tmp))
val += PENALTY_FOR_NODE_WITH_CPUS;
/* Slight preference for less loaded node */
struct zone *z;
int average_size;
/*
- * ZONE_DMA and ZONE_DMA32 can be very small area in the sytem.
+ * 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 confgigures zone order.
+ * This function detect ZONE_DMA/DMA32 size and configures zone order.
*/
/* Is there ZONE_NORMAL ? (ex. ppc has only DMA zone..) */
low_kmem_size = 0;
if (zone_type < ZONE_NORMAL)
low_kmem_size += z->present_pages;
total_size += z->present_pages;
+ } else if (zone_type == ZONE_NORMAL) {
+ /*
+ * If any node has only lowmem, then node order
+ * is preferred to allow kernel allocations
+ * locally; otherwise, they can easily infringe
+ * on other nodes when there is an abundance of
+ * lowmem available to allocate from.
+ */
+ return ZONELIST_ORDER_NODE;
}
}
}
/* NUMA-aware ordering of nodes */
local_node = pgdat->node_id;
- load = num_online_nodes();
+ load = nr_online_nodes;
prev_node = local_node;
nodes_clear(used_mask);
- memset(node_load, 0, sizeof(node_load));
memset(node_order, 0, sizeof(node_order));
j = 0;
pgdat->node_zonelists[0].zlcache_ptr = NULL;
}
-#endif /* CONFIG_NUMA */
+#endif /* CONFIG_NUMA */
+
+/*
+ * Boot pageset table. One per cpu which is going to be used for all
+ * zones and all nodes. The parameters will be set in such a way
+ * that an item put on a list will immediately be handed over to
+ * the buddy list. This is safe since pageset manipulation is done
+ * with interrupts disabled.
+ *
+ * The boot_pagesets must be kept even after bootup is complete for
+ * unused processors and/or zones. They do play a role for bootstrapping
+ * hotplugged processors.
+ *
+ * zoneinfo_show() and maybe other functions do
+ * not check if the processor is online before following the pageset pointer.
+ * Other parts of the kernel may not check if the zone is available.
+ */
+static void setup_pageset(struct per_cpu_pageset *p, unsigned long batch);
+static DEFINE_PER_CPU(struct per_cpu_pageset, boot_pageset);
+static void setup_zone_pageset(struct zone *zone);
+
+/*
+ * Global mutex to protect against size modification of zonelists
+ * as well as to serialize pageset setup for the new populated zone.
+ */
+DEFINE_MUTEX(zonelists_mutex);
/* return values int ....just for stop_machine() */
-static int __build_all_zonelists(void *dummy)
+static __init_refok int __build_all_zonelists(void *data)
{
int nid;
+ int cpu;
+#ifdef CONFIG_NUMA
+ memset(node_load, 0, sizeof(node_load));
+#endif
for_each_online_node(nid) {
pg_data_t *pgdat = NODE_DATA(nid);
build_zonelists(pgdat);
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
+ * each zone will be allocated later when the per cpu
+ * allocator is available.
+ *
+ * boot_pagesets are used also for bootstrapping offline
+ * cpus if the system is already booted because the pagesets
+ * are needed to initialize allocators on a specific cpu too.
+ * F.e. the percpu allocator needs the page allocator which
+ * needs the percpu allocator in order to allocate its pagesets
+ * (a chicken-egg dilemma).
+ */
+ for_each_possible_cpu(cpu)
+ setup_pageset(&per_cpu(boot_pageset, cpu), 0);
+
return 0;
}
-void build_all_zonelists(void)
+/*
+ * Called with zonelists_mutex held always
+ * unless system_state == SYSTEM_BOOTING.
+ */
+void build_all_zonelists(void *data)
{
set_zonelist_order();
} else {
/* we have to stop all cpus to guarantee there is no user
of zonelist */
- stop_machine(__build_all_zonelists, NULL, NULL);
+ stop_machine(__build_all_zonelists, data, NULL);
/* cpuset refresh routine should be here */
}
vm_total_pages = nr_free_pagecache_pages();
printk("Built %i zonelists in %s order, mobility grouping %s. "
"Total pages: %ld\n",
- num_online_nodes(),
+ nr_online_nodes,
zonelist_order_name[current_zonelist_order],
page_group_by_mobility_disabled ? "off" : "on",
vm_total_pages);
/*
* Mark a number of pageblocks as MIGRATE_RESERVE. The number
- * of blocks reserved is based on zone->pages_min. The memory within the
- * reserve will tend to store contiguous free pages. Setting min_free_kbytes
+ * of blocks reserved is based on min_wmark_pages(zone). The memory within
+ * the reserve will tend to store contiguous free pages. Setting min_free_kbytes
* higher will lead to a bigger reserve which will get freed as contiguous
* blocks as reclaim kicks in
*/
{
unsigned long start_pfn, pfn, end_pfn;
struct page *page;
- unsigned long reserve, block_migratetype;
+ unsigned long block_migratetype;
+ int reserve;
/* Get the start pfn, end pfn and the number of blocks to reserve */
start_pfn = zone->zone_start_pfn;
end_pfn = start_pfn + zone->spanned_pages;
- reserve = roundup(zone->pages_min, pageblock_nr_pages) >>
+ reserve = roundup(min_wmark_pages(zone), pageblock_nr_pages) >>
pageblock_order;
+ /*
+ * Reserve blocks are generally in place to help high-order atomic
+ * allocations that are short-lived. A min_free_kbytes value that
+ * would result in more than 2 reserve blocks for atomic allocations
+ * is assumed to be in place to help anti-fragmentation for the
+ * future allocation of hugepages at runtime.
+ */
+ reserve = min(2, reserve);
+
for (pfn = start_pfn; pfn < end_pfn; pfn += pageblock_nr_pages) {
if (!pfn_valid(pfn))
continue;
unsigned long pfn;
struct zone *z;
+ if (highest_memmap_pfn < end_pfn - 1)
+ highest_memmap_pfn = end_pfn - 1;
+
z = &NODE_DATA(nid)->node_zones[zone];
for (pfn = start_pfn; pfn < end_pfn; pfn++) {
/*
static int zone_batchsize(struct zone *zone)
{
+#ifdef CONFIG_MMU
int batch;
/*
* of pages of one half of the possible page colors
* and the other with pages of the other colors.
*/
- batch = (1 << (fls(batch + batch/2)-1)) - 1;
+ batch = rounddown_pow_of_two(batch + batch/2) - 1;
return batch;
+
+#else
+ /* The deferral and batching of frees should be suppressed under NOMMU
+ * conditions.
+ *
+ * The problem is that NOMMU needs to be able to allocate large chunks
+ * of contiguous memory as there's no hardware page translation to
+ * assemble apparent contiguous memory from discontiguous pages.
+ *
+ * Queueing large contiguous runs of pages for batching, however,
+ * causes the pages to actually be freed in smaller chunks. As there
+ * can be a significant delay between the individual batches being
+ * recycled, this leads to the once large chunks of space being
+ * fragmented and becoming unavailable for high-order allocations.
+ */
+ return 0;
+#endif
}
static void setup_pageset(struct per_cpu_pageset *p, unsigned long batch)
{
struct per_cpu_pages *pcp;
+ int migratetype;
memset(p, 0, sizeof(*p));
pcp->count = 0;
pcp->high = 6 * batch;
pcp->batch = max(1UL, 1 * batch);
- INIT_LIST_HEAD(&pcp->list);
+ for (migratetype = 0; migratetype < MIGRATE_PCPTYPES; migratetype++)
+ INIT_LIST_HEAD(&pcp->lists[migratetype]);
}
/*
pcp->batch = PAGE_SHIFT * 8;
}
-
-#ifdef CONFIG_NUMA
-/*
- * Boot pageset table. One per cpu which is going to be used for all
- * zones and all nodes. The parameters will be set in such a way
- * that an item put on a list will immediately be handed over to
- * the buddy list. This is safe since pageset manipulation is done
- * with interrupts disabled.
- *
- * Some NUMA counter updates may also be caught by the boot pagesets.
- *
- * The boot_pagesets must be kept even after bootup is complete for
- * unused processors and/or zones. They do play a role for bootstrapping
- * hotplugged processors.
- *
- * zoneinfo_show() and maybe other functions do
- * not check if the processor is online before following the pageset pointer.
- * Other parts of the kernel may not check if the zone is available.
- */
-static struct per_cpu_pageset boot_pageset[NR_CPUS];
-
-/*
- * Dynamically allocate memory for the
- * per cpu pageset array in struct zone.
- */
-static int __cpuinit process_zones(int cpu)
+static __meminit void setup_zone_pageset(struct zone *zone)
{
- struct zone *zone, *dzone;
- int node = cpu_to_node(cpu);
-
- node_set_state(node, N_CPU); /* this node has a cpu */
-
- for_each_zone(zone) {
+ int cpu;
- if (!populated_zone(zone))
- continue;
+ zone->pageset = alloc_percpu(struct per_cpu_pageset);
- zone_pcp(zone, cpu) = kmalloc_node(sizeof(struct per_cpu_pageset),
- GFP_KERNEL, node);
- if (!zone_pcp(zone, cpu))
- goto bad;
+ for_each_possible_cpu(cpu) {
+ struct per_cpu_pageset *pcp = per_cpu_ptr(zone->pageset, cpu);
- setup_pageset(zone_pcp(zone, cpu), zone_batchsize(zone));
+ setup_pageset(pcp, zone_batchsize(zone));
if (percpu_pagelist_fraction)
- setup_pagelist_highmark(zone_pcp(zone, cpu),
- (zone->present_pages / percpu_pagelist_fraction));
- }
-
- return 0;
-bad:
- for_each_zone(dzone) {
- if (!populated_zone(dzone))
- continue;
- if (dzone == zone)
- break;
- kfree(zone_pcp(dzone, cpu));
- zone_pcp(dzone, cpu) = NULL;
- }
- return -ENOMEM;
-}
-
-static inline void free_zone_pagesets(int cpu)
-{
- struct zone *zone;
-
- for_each_zone(zone) {
- struct per_cpu_pageset *pset = zone_pcp(zone, cpu);
-
- /* Free per_cpu_pageset if it is slab allocated */
- if (pset != &boot_pageset[cpu])
- kfree(pset);
- zone_pcp(zone, cpu) = NULL;
+ setup_pagelist_highmark(pcp,
+ (zone->present_pages /
+ percpu_pagelist_fraction));
}
}
-static int __cpuinit pageset_cpuup_callback(struct notifier_block *nfb,
- unsigned long action,
- void *hcpu)
-{
- int cpu = (long)hcpu;
- int ret = NOTIFY_OK;
-
- switch (action) {
- case CPU_UP_PREPARE:
- case CPU_UP_PREPARE_FROZEN:
- if (process_zones(cpu))
- ret = NOTIFY_BAD;
- break;
- case CPU_UP_CANCELED:
- case CPU_UP_CANCELED_FROZEN:
- case CPU_DEAD:
- case CPU_DEAD_FROZEN:
- free_zone_pagesets(cpu);
- break;
- default:
- break;
- }
- return ret;
-}
-
-static struct notifier_block __cpuinitdata pageset_notifier =
- { &pageset_cpuup_callback, NULL, 0 };
-
+/*
+ * Allocate per cpu pagesets and initialize them.
+ * Before this call only boot pagesets were available.
+ */
void __init setup_per_cpu_pageset(void)
{
- int err;
+ struct zone *zone;
- /* Initialize per_cpu_pageset for cpu 0.
- * A cpuup callback will do this for every cpu
- * as it comes online
- */
- err = process_zones(smp_processor_id());
- BUG_ON(err);
- register_cpu_notifier(&pageset_notifier);
+ for_each_populated_zone(zone)
+ setup_zone_pageset(zone);
}
-#endif
-
static noinline __init_refok
int zone_wait_table_init(struct zone *zone, unsigned long zone_size_pages)
{
return 0;
}
-static __meminit void zone_pcp_init(struct zone *zone)
+static int __zone_pcp_update(void *data)
{
+ struct zone *zone = data;
int cpu;
- unsigned long batch = zone_batchsize(zone);
+ unsigned long batch = zone_batchsize(zone), flags;
- for (cpu = 0; cpu < NR_CPUS; cpu++) {
-#ifdef CONFIG_NUMA
- /* Early boot. Slab allocator not functional yet */
- zone_pcp(zone, cpu) = &boot_pageset[cpu];
- setup_pageset(&boot_pageset[cpu],0);
-#else
- setup_pageset(zone_pcp(zone,cpu), batch);
-#endif
+ 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)
+{
+ /*
+ * per cpu subsystem is not up at this point. The following code
+ * relies on the ability of the linker to provide the
+ * offset of a (static) per cpu variable into the per cpu area.
+ */
+ zone->pageset = &boot_pageset;
+
if (zone->present_pages)
- printk(KERN_DEBUG " %s zone: %lu pages, LIFO batch:%lu\n",
- zone->name, zone->present_pages, batch);
+ 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,
* was used and there are no special requirements, this is a convenient
* alternative
*/
-int __meminit early_pfn_to_nid(unsigned long pfn)
+int __meminit __early_pfn_to_nid(unsigned long pfn)
{
int i;
if (start_pfn <= pfn && pfn < end_pfn)
return early_node_map[i].nid;
}
+ /* This is a memory hole */
+ return -1;
+}
+#endif /* CONFIG_HAVE_ARCH_EARLY_PFN_TO_NID */
+
+int __meminit early_pfn_to_nid(unsigned long pfn)
+{
+ int nid;
+ nid = __early_pfn_to_nid(pfn);
+ if (nid >= 0)
+ return nid;
+ /* just returns 0 */
return 0;
}
-#endif /* CONFIG_HAVE_ARCH_EARLY_PFN_TO_NID */
+
+#ifdef CONFIG_NODES_SPAN_OTHER_NODES
+bool __meminit early_pfn_in_nid(unsigned long pfn, int node)
+{
+ int nid;
+
+ nid = __early_pfn_to_nid(pfn);
+ if (nid >= 0 && nid != node)
+ return false;
+ return true;
+}
+#endif
/* Basic iterator support to walk early_node_map[] */
#define for_each_active_range_index_in_nid(i, nid) \
}
}
+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);
+ }
+ return nr_range;
+}
+
+#ifdef CONFIG_NO_BOOTMEM
+void * __init __alloc_memory_core_early(int nid, u64 size, u64 align,
+ u64 goal, u64 limit)
+{
+ int i;
+ void *ptr;
+
+ /* 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;
+
+ ei_last = early_node_map[i].end_pfn;
+ ei_last <<= PAGE_SHIFT;
+ ei_start = early_node_map[i].start_pfn;
+ ei_start <<= PAGE_SHIFT;
+ addr = find_early_area(ei_start, ei_last,
+ goal, limit, size, align);
+
+ if (addr == -1ULL)
+ continue;
+
+#if 0
+ printk(KERN_DEBUG "alloc (nid=%d %llx - %llx) (%llx - %llx) %llx %llx => %llx\n",
+ nid,
+ ei_start, ei_last, goal, limit, size,
+ align, addr);
+#endif
+
+ ptr = phys_to_virt(addr);
+ memset(ptr, 0, size);
+ reserve_early_without_check(addr, addr + size, "BOOTMEM");
+ return ptr;
+ }
+
+ return NULL;
+}
+#endif
+
+
void __init work_with_active_regions(int nid, work_fn_t work_fn, void *data)
{
int i;
}
/**
- * push_node_boundaries - Push node boundaries to at least the requested boundary
- * @nid: The nid of the node to push the boundary for
- * @start_pfn: The start pfn of the node
- * @end_pfn: The end pfn of the node
- *
- * In reserve-based hot-add, mem_map is allocated that is unused until hotadd
- * time. Specifically, on x86_64, SRAT will report ranges that can potentially
- * be hotplugged even though no physical memory exists. This function allows
- * an arch to push out the node boundaries so mem_map is allocated that can
- * be used later.
- */
-#ifdef CONFIG_MEMORY_HOTPLUG_RESERVE
-void __init push_node_boundaries(unsigned int nid,
- unsigned long start_pfn, unsigned long end_pfn)
-{
- mminit_dprintk(MMINIT_TRACE, "zoneboundary",
- "Entering push_node_boundaries(%u, %lu, %lu)\n",
- nid, start_pfn, end_pfn);
-
- /* Initialise the boundary for this node if necessary */
- if (node_boundary_end_pfn[nid] == 0)
- node_boundary_start_pfn[nid] = -1UL;
-
- /* Update the boundaries */
- if (node_boundary_start_pfn[nid] > start_pfn)
- node_boundary_start_pfn[nid] = start_pfn;
- if (node_boundary_end_pfn[nid] < end_pfn)
- node_boundary_end_pfn[nid] = end_pfn;
-}
-
-/* If necessary, push the node boundary out for reserve hotadd */
-static void __meminit account_node_boundary(unsigned int nid,
- unsigned long *start_pfn, unsigned long *end_pfn)
-{
- mminit_dprintk(MMINIT_TRACE, "zoneboundary",
- "Entering account_node_boundary(%u, %lu, %lu)\n",
- nid, *start_pfn, *end_pfn);
-
- /* Return if boundary information has not been provided */
- if (node_boundary_end_pfn[nid] == 0)
- return;
-
- /* Check the boundaries and update if necessary */
- if (node_boundary_start_pfn[nid] < *start_pfn)
- *start_pfn = node_boundary_start_pfn[nid];
- if (node_boundary_end_pfn[nid] > *end_pfn)
- *end_pfn = node_boundary_end_pfn[nid];
-}
-#else
-void __init push_node_boundaries(unsigned int nid,
- unsigned long start_pfn, unsigned long end_pfn) {}
-
-static void __meminit account_node_boundary(unsigned int nid,
- unsigned long *start_pfn, unsigned long *end_pfn) {}
-#endif
-
-
-/**
* get_pfn_range_for_nid - Return the start and end page frames for a node
* @nid: The nid to return the range for. If MAX_NUMNODES, the min and max PFN are returned.
* @start_pfn: Passed by reference. On return, it will have the node start_pfn.
if (*start_pfn == -1UL)
*start_pfn = 0;
-
- /* Push the node boundaries out if requested */
- account_node_boundary(nid, start_pfn, end_pfn);
}
/*
* Return the number of holes in a range on a node. If nid is MAX_NUMNODES,
* then all holes in the requested range will be accounted for.
*/
-static unsigned long __meminit __absent_pages_in_range(int nid,
+unsigned long __meminit __absent_pages_in_range(int nid,
unsigned long range_start_pfn,
unsigned long range_end_pfn)
{
{
unsigned long usemapsize = usemap_size(zonesize);
zone->pageblock_flags = NULL;
- if (usemapsize) {
+ if (usemapsize)
zone->pageblock_flags = alloc_bootmem_node(pgdat, usemapsize);
- memset(zone->pageblock_flags, 0, usemapsize);
- }
}
#else
static void inline setup_usemap(struct pglist_data *pgdat,
pgdat->nr_zones = 0;
init_waitqueue_head(&pgdat->kswapd_wait);
pgdat->kswapd_max_order = 0;
+ pgdat_page_cgroup_init(pgdat);
for (j = 0; j < MAX_NR_ZONES; j++) {
struct zone *zone = pgdat->node_zones + j;
PAGE_ALIGN(size * sizeof(struct page)) >> PAGE_SHIFT;
if (realsize >= memmap_pages) {
realsize -= memmap_pages;
- mminit_dprintk(MMINIT_TRACE, "memmap_init",
- "%s zone: %lu pages used for memmap\n",
- zone_names[j], 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",
/* Account for reserved pages */
if (j == 0 && realsize > dma_reserve) {
realsize -= dma_reserve;
- mminit_dprintk(MMINIT_TRACE, "memmap_init",
- "%s zone: %lu pages reserved\n",
+ printk(KERN_DEBUG " %s zone: %lu pages reserved\n",
zone_names[0], dma_reserve);
}
zone_pcp_init(zone);
for_each_lru(l) {
INIT_LIST_HEAD(&zone->lru[l].list);
- zone->lru[l].nr_scan = 0;
+ 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;
if (!size)
}
/* Merge backward if suitable */
- if (start_pfn < early_node_map[i].end_pfn &&
+ 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;
{
memset(early_node_map, 0, sizeof(early_node_map));
nr_nodemap_entries = 0;
-#ifdef CONFIG_MEMORY_HOTPLUG_RESERVE
- memset(node_boundary_start_pfn, 0, sizeof(node_boundary_start_pfn));
- memset(node_boundary_end_pfn, 0, sizeof(node_boundary_end_pfn));
-#endif /* CONFIG_MEMORY_HOTPLUG_RESERVE */
}
/* Compare two active node_active_regions */
}
/* sort the node_map by start_pfn */
-static void __init sort_node_map(void)
+void __init sort_node_map(void)
{
sort(early_node_map, (size_t)nr_nodemap_entries,
sizeof(struct node_active_region),
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];
unsigned long totalpages = early_calculate_totalpages();
int usable_nodes = nodes_weight(node_states[N_HIGH_MEMORY]);
/* If kernelcore was not specified, there is no ZONE_MOVABLE */
if (!required_kernelcore)
- return;
+ goto out;
/* usable_startpfn is the lowest possible pfn ZONE_MOVABLE can be at */
find_usable_zone_for_movable();
for (nid = 0; nid < MAX_NUMNODES; nid++)
zone_movable_pfn[nid] =
roundup(zone_movable_pfn[nid], MAX_ORDER_NR_PAGES);
+
+out:
+ /* restore the node_state */
+ node_states[N_HIGH_MEMORY] = saved_node_state;
}
/* Any regular memory on that node ? */
for (i = 0; i < MAX_NR_ZONES; i++) {
if (i == ZONE_MOVABLE)
continue;
- printk(" %-8s %0#10lx -> %0#10lx\n",
- zone_names[i],
+ printk(" %-8s ", zone_names[i]);
+ if (arch_zone_lowest_possible_pfn[i] ==
+ arch_zone_highest_possible_pfn[i])
+ printk("empty\n");
+ else
+ printk("%0#10lx -> %0#10lx\n",
arch_zone_lowest_possible_pfn[i],
arch_zone_highest_possible_pfn[i]);
}
}
#ifndef CONFIG_NEED_MULTIPLE_NODES
-struct pglist_data __refdata contig_page_data = { .bdata = &bootmem_node_data[0] };
+struct pglist_data __refdata contig_page_data = {
+#ifndef CONFIG_NO_BOOTMEM
+ .bdata = &bootmem_node_data[0]
+#endif
+ };
EXPORT_SYMBOL(contig_page_data);
#endif
max = zone->lowmem_reserve[j];
}
- /* we treat pages_high as reserved pages. */
- max += zone->pages_high;
+ /* we treat the high watermark as reserved pages. */
+ max += high_wmark_pages(zone);
if (max > zone->present_pages)
max = zone->present_pages;
}
/**
- * setup_per_zone_pages_min - called when min_free_kbytes changes.
+ * setup_per_zone_wmarks - called when min_free_kbytes changes
+ * or when memory is hot-{added|removed}
*
- * Ensures that the pages_{min,low,high} values for each zone are set correctly
- * with respect to min_free_kbytes.
+ * Ensures that the watermark[min,low,high] values for each zone are set
+ * correctly with respect to min_free_kbytes.
*/
-void setup_per_zone_pages_min(void)
+void setup_per_zone_wmarks(void)
{
unsigned long pages_min = min_free_kbytes >> (PAGE_SHIFT - 10);
unsigned long lowmem_pages = 0;
for_each_zone(zone) {
u64 tmp;
- spin_lock_irqsave(&zone->lru_lock, flags);
+ spin_lock_irqsave(&zone->lock, flags);
tmp = (u64)pages_min * zone->present_pages;
do_div(tmp, lowmem_pages);
if (is_highmem(zone)) {
* need highmem pages, so cap pages_min to a small
* value here.
*
- * The (pages_high-pages_low) and (pages_low-pages_min)
+ * The WMARK_HIGH-WMARK_LOW and (WMARK_LOW-WMARK_MIN)
* deltas controls asynch page reclaim, and so should
* not be capped for highmem.
*/
min_pages = SWAP_CLUSTER_MAX;
if (min_pages > 128)
min_pages = 128;
- zone->pages_min = min_pages;
+ zone->watermark[WMARK_MIN] = min_pages;
} else {
/*
* If it's a lowmem zone, reserve a number of pages
* proportionate to the zone's size.
*/
- zone->pages_min = tmp;
+ zone->watermark[WMARK_MIN] = tmp;
}
- zone->pages_low = zone->pages_min + (tmp >> 2);
- zone->pages_high = zone->pages_min + (tmp >> 1);
+ zone->watermark[WMARK_LOW] = min_wmark_pages(zone) + (tmp >> 2);
+ zone->watermark[WMARK_HIGH] = min_wmark_pages(zone) + (tmp >> 1);
setup_zone_migrate_reserve(zone);
- spin_unlock_irqrestore(&zone->lru_lock, flags);
+ spin_unlock_irqrestore(&zone->lock, flags);
}
/* update totalreserve_pages */
}
/*
+ * 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
+ * to be referenced again before it is swapped out.
+ *
+ * The inactive_anon ratio is the target ratio of ACTIVE_ANON to
+ * INACTIVE_ANON pages on this zone's LRU, maintained by the
+ * pageout code. A zone->inactive_ratio of 3 means 3:1 or 25% of
+ * the anonymous pages are kept on the inactive list.
+ *
+ * total target max
+ * memory ratio inactive anon
+ * -------------------------------------
+ * 10MB 1 5MB
+ * 100MB 1 50MB
+ * 1GB 3 250MB
+ * 10GB 10 0.9GB
+ * 100GB 31 3GB
+ * 1TB 101 10GB
+ * 10TB 320 32GB
+ */
+void calculate_zone_inactive_ratio(struct zone *zone)
+{
+ unsigned int gb, ratio;
+
+ /* Zone size in gigabytes */
+ gb = zone->present_pages >> (30 - PAGE_SHIFT);
+ if (gb)
+ ratio = int_sqrt(10 * gb);
+ else
+ ratio = 1;
+
+ zone->inactive_ratio = ratio;
+}
+
+static void __init setup_per_zone_inactive_ratio(void)
+{
+ struct zone *zone;
+
+ for_each_zone(zone)
+ calculate_zone_inactive_ratio(zone);
+}
+
+/*
* Initialise min_free_kbytes.
*
* For small machines we want it small (128k min). For large machines
* 8192MB: 11584k
* 16384MB: 16384k
*/
-static int __init init_per_zone_pages_min(void)
+static int __init init_per_zone_wmark_min(void)
{
unsigned long lowmem_kbytes;
min_free_kbytes = 128;
if (min_free_kbytes > 65536)
min_free_kbytes = 65536;
- setup_per_zone_pages_min();
+ setup_per_zone_wmarks();
setup_per_zone_lowmem_reserve();
+ setup_per_zone_inactive_ratio();
return 0;
}
-module_init(init_per_zone_pages_min)
+module_init(init_per_zone_wmark_min)
/*
* min_free_kbytes_sysctl_handler - just a wrapper around proc_dointvec() so
* changes.
*/
int min_free_kbytes_sysctl_handler(ctl_table *table, int write,
- struct file *file, void __user *buffer, size_t *length, loff_t *ppos)
+ void __user *buffer, size_t *length, loff_t *ppos)
{
- proc_dointvec(table, write, file, buffer, length, ppos);
+ proc_dointvec(table, write, buffer, length, ppos);
if (write)
- setup_per_zone_pages_min();
+ setup_per_zone_wmarks();
return 0;
}
#ifdef CONFIG_NUMA
int sysctl_min_unmapped_ratio_sysctl_handler(ctl_table *table, int write,
- struct file *file, void __user *buffer, size_t *length, loff_t *ppos)
+ void __user *buffer, size_t *length, loff_t *ppos)
{
struct zone *zone;
int rc;
- rc = proc_dointvec_minmax(table, write, file, buffer, length, ppos);
+ rc = proc_dointvec_minmax(table, write, buffer, length, ppos);
if (rc)
return rc;
}
int sysctl_min_slab_ratio_sysctl_handler(ctl_table *table, int write,
- struct file *file, void __user *buffer, size_t *length, loff_t *ppos)
+ void __user *buffer, size_t *length, loff_t *ppos)
{
struct zone *zone;
int rc;
- rc = proc_dointvec_minmax(table, write, file, buffer, length, ppos);
+ rc = proc_dointvec_minmax(table, write, buffer, length, ppos);
if (rc)
return rc;
* whenever sysctl_lowmem_reserve_ratio changes.
*
* The reserve ratio obviously has absolutely no relation with the
- * pages_min watermarks. The lowmem reserve ratio can only make sense
+ * 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,
- struct file *file, void __user *buffer, size_t *length, loff_t *ppos)
+ void __user *buffer, size_t *length, loff_t *ppos)
{
- proc_dointvec_minmax(table, write, file, buffer, length, ppos);
+ proc_dointvec_minmax(table, write, buffer, length, ppos);
setup_per_zone_lowmem_reserve();
return 0;
}
*/
int percpu_pagelist_fraction_sysctl_handler(ctl_table *table, int write,
- struct file *file, void __user *buffer, size_t *length, loff_t *ppos)
+ void __user *buffer, size_t *length, loff_t *ppos)
{
struct zone *zone;
unsigned int cpu;
int ret;
- ret = proc_dointvec_minmax(table, write, file, buffer, length, ppos);
+ ret = proc_dointvec_minmax(table, write, buffer, length, ppos);
if (!write || (ret == -EINVAL))
return ret;
- for_each_zone(zone) {
- for_each_online_cpu(cpu) {
+ for_each_populated_zone(zone) {
+ for_each_possible_cpu(cpu) {
unsigned long high;
high = zone->present_pages / percpu_pagelist_fraction;
- setup_pagelist_highmark(zone_pcp(zone, cpu), high);
+ setup_pagelist_highmark(
+ per_cpu_ptr(zone->pageset, cpu), high);
}
}
return 0;
numentries <<= (PAGE_SHIFT - scale);
/* Make sure we've got at least a 0-order allocation.. */
- if (unlikely((numentries * bucketsize) < PAGE_SIZE))
+ if (unlikely(flags & HASH_SMALL)) {
+ /* Makes no sense without HASH_EARLY */
+ WARN_ON(!(flags & HASH_EARLY));
+ if (!(numentries >> *_hash_shift)) {
+ numentries = 1UL << *_hash_shift;
+ BUG_ON(!numentries);
+ }
+ } else if (unlikely((numentries * bucketsize) < PAGE_SIZE))
numentries = PAGE_SIZE / bucketsize;
}
numentries = roundup_pow_of_two(numentries);
else if (hashdist)
table = __vmalloc(size, GFP_ATOMIC, PAGE_KERNEL);
else {
- unsigned long order = get_order(size);
- table = (void*) __get_free_pages(GFP_ATOMIC, order);
/*
* If bucketsize is not a power-of-two, we may free
- * some pages at the end of hash table.
+ * some pages at the end of hash table which
+ * alloc_pages_exact() automatically does
*/
- if (table) {
- unsigned long alloc_end = (unsigned long)table +
- (PAGE_SIZE << order);
- unsigned long used = (unsigned long)table +
- PAGE_ALIGN(size);
- split_page(virt_to_page(table), order);
- while (used < alloc_end) {
- free_page(used);
- used += PAGE_SIZE;
- }
+ if (get_order(size) < MAX_ORDER) {
+ table = alloc_pages_exact(size, GFP_ATOMIC);
+ kmemleak_alloc(table, size, 1, GFP_ATOMIC);
}
}
} while (!table && size > PAGE_SIZE && --log2qty);
return table;
}
-#ifdef CONFIG_OUT_OF_LINE_PFN_TO_PAGE
-struct page *pfn_to_page(unsigned long pfn)
-{
- return __pfn_to_page(pfn);
-}
-unsigned long page_to_pfn(struct page *page)
-{
- return __page_to_pfn(page);
-}
-EXPORT_SYMBOL(pfn_to_page);
-EXPORT_SYMBOL(page_to_pfn);
-#endif /* CONFIG_OUT_OF_LINE_PFN_TO_PAGE */
-
/* Return a pointer to the bitmap storing bits affecting a block of pages */
static inline unsigned long *get_pageblock_bitmap(struct zone *zone,
unsigned long pfn)
int set_migratetype_isolate(struct page *page)
{
struct zone *zone;
- unsigned long flags;
+ struct page *curr_page;
+ unsigned long flags, pfn, iter;
+ unsigned long immobile = 0;
+ struct memory_isolate_notify arg;
+ int notifier_ret;
int ret = -EBUSY;
+ int zone_idx;
zone = page_zone(page);
+ zone_idx = zone_idx(zone);
+
spin_lock_irqsave(&zone->lock, flags);
+ if (get_pageblock_migratetype(page) == MIGRATE_MOVABLE ||
+ zone_idx == ZONE_MOVABLE) {
+ ret = 0;
+ goto out;
+ }
+
+ pfn = page_to_pfn(page);
+ arg.start_pfn = pfn;
+ arg.nr_pages = pageblock_nr_pages;
+ arg.pages_found = 0;
+
/*
- * In future, more migrate types will be able to be isolation target.
+ * 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.
*/
- if (get_pageblock_migratetype(page) != MIGRATE_MOVABLE)
+ notifier_ret = memory_isolate_notify(MEM_ISOLATE_COUNT, &arg);
+ notifier_ret = notifier_to_errno(notifier_ret);
+ if (notifier_ret || !arg.pages_found)
goto out;
- set_pageblock_migratetype(page, MIGRATE_ISOLATE);
- move_freepages_block(zone, page, MIGRATE_ISOLATE);
- ret = 0;
+
+ for (iter = pfn; iter < (pfn + pageblock_nr_pages); iter++) {
+ if (!pfn_valid_within(pfn))
+ continue;
+
+ curr_page = pfn_to_page(iter);
+ if (!page_count(curr_page) || PageLRU(curr_page))
+ continue;
+
+ immobile++;
+ }
+
+ if (arg.pages_found == immobile)
+ ret = 0;
+
out:
+ if (!ret) {
+ set_pageblock_migratetype(page, MIGRATE_ISOLATE);
+ move_freepages_block(zone, page, MIGRATE_ISOLATE);
+ }
+
spin_unlock_irqrestore(&zone->lock, flags);
if (!ret)
drain_all_pages();
spin_unlock_irqrestore(&zone->lock, flags);
}
#endif
+
+#ifdef CONFIG_MEMORY_FAILURE
+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;
+
+ spin_lock_irqsave(&zone->lock, flags);
+ for (order = 0; order < MAX_ORDER; order++) {
+ struct page *page_head = page - (pfn & ((1 << order) - 1));
+
+ if (PageBuddy(page_head) && page_order(page_head) >= order)
+ break;
+ }
+ spin_unlock_irqrestore(&zone->lock, flags);
+
+ return order < MAX_ORDER;
+}
+#endif
+
+static struct trace_print_flags pageflag_names[] = {
+ {1UL << PG_locked, "locked" },
+ {1UL << PG_error, "error" },
+ {1UL << PG_referenced, "referenced" },
+ {1UL << PG_uptodate, "uptodate" },
+ {1UL << PG_dirty, "dirty" },
+ {1UL << PG_lru, "lru" },
+ {1UL << PG_active, "active" },
+ {1UL << PG_slab, "slab" },
+ {1UL << PG_owner_priv_1, "owner_priv_1" },
+ {1UL << PG_arch_1, "arch_1" },
+ {1UL << PG_reserved, "reserved" },
+ {1UL << PG_private, "private" },
+ {1UL << PG_private_2, "private_2" },
+ {1UL << PG_writeback, "writeback" },
+#ifdef CONFIG_PAGEFLAGS_EXTENDED
+ {1UL << PG_head, "head" },
+ {1UL << PG_tail, "tail" },
+#else
+ {1UL << PG_compound, "compound" },
+#endif
+ {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
+ {1UL << PG_mlocked, "mlocked" },
+#endif
+#ifdef CONFIG_ARCH_USES_PG_UNCACHED
+ {1UL << PG_uncached, "uncached" },
+#endif
+#ifdef CONFIG_MEMORY_FAILURE
+ {1UL << PG_hwpoison, "hwpoison" },
+#endif
+ {-1UL, NULL },
+};
+
+static void dump_page_flags(unsigned long flags)
+{
+ const char *delim = "";
+ unsigned long mask;
+ int i;
+
+ printk(KERN_ALERT "page flags: %#lx(", flags);
+
+ /* remove zone id */
+ flags &= (1UL << NR_PAGEFLAGS) - 1;
+
+ for (i = 0; pageflag_names[i].name && flags; i++) {
+
+ mask = pageflag_names[i].mask;
+ if ((flags & mask) != mask)
+ continue;
+
+ flags &= ~mask;
+ printk("%s%s", delim, pageflag_names[i].name);
+ delim = "|";
+ }
+
+ /* check for left over flags */
+ if (flags)
+ printk("%s%#lx", delim, flags);
+
+ printk(")\n");
+}
+
+void dump_page(struct page *page)
+{
+ printk(KERN_ALERT
+ "page:%p count:%d mapcount:%d mapping:%p index:%#lx\n",
+ page, page_count(page), page_mapcount(page),
+ page->mapping, page->index);
+ dump_page_flags(page->flags);
+}
git://ftp.safe.ca / safe / jmp / linux-2.6 / blobdiff