#include <linux/swap.h>
#include <linux/interrupt.h>
#include <linux/pagemap.h>
+#include <linux/jiffies.h>
#include <linux/bootmem.h>
#include <linux/compiler.h>
#include <linux/kernel.h>
#include <linux/pagevec.h>
#include <linux/blkdev.h>
#include <linux/slab.h>
+#include <linux/oom.h>
#include <linux/notifier.h>
#include <linux/topology.h>
#include <linux/sysctl.h>
#include <linux/pfn.h>
#include <linux/backing-dev.h>
#include <linux/fault-inject.h>
+#include <linux/page-isolation.h>
+#include <linux/memcontrol.h>
#include <asm/tlbflush.h>
#include <asm/div64.h>
long nr_swap_pages;
int percpu_pagelist_fraction;
+#ifdef CONFIG_HUGETLB_PAGE_SIZE_VARIABLE
+int pageblock_order __read_mostly;
+#endif
+
static void __free_pages_ok(struct page *page, unsigned int order);
/*
#ifdef CONFIG_ARCH_POPULATES_NODE_MAP
/*
- * MAX_ACTIVE_REGIONS determines the maxmimum number of distinct
+ * 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
static unsigned long __meminitdata node_boundary_end_pfn[MAX_NUMNODES];
#endif /* CONFIG_MEMORY_HOTPLUG_RESERVE */
unsigned long __initdata required_kernelcore;
- unsigned long __initdata required_movablecore;
+ static unsigned long __initdata required_movablecore;
unsigned long __meminitdata zone_movable_pfn[MAX_NUMNODES];
/* movable_zone is the "real" zone pages in ZONE_MOVABLE are taken from */
EXPORT_SYMBOL(nr_node_ids);
#endif
-#ifdef CONFIG_PAGE_GROUP_BY_MOBILITY
int page_group_by_mobility_disabled __read_mostly;
-static inline int get_pageblock_migratetype(struct page *page)
-{
- if (unlikely(page_group_by_mobility_disabled))
- return MIGRATE_UNMOVABLE;
-
- return get_pageblock_flags_group(page, PB_migrate, PB_migrate_end);
-}
-
static void set_pageblock_migratetype(struct page *page, int migratetype)
{
set_pageblock_flags_group(page, (unsigned long)migratetype,
PB_migrate, PB_migrate_end);
}
-static inline int allocflags_to_migratetype(gfp_t gfp_flags, int order)
-{
- WARN_ON((gfp_flags & GFP_MOVABLE_MASK) == GFP_MOVABLE_MASK);
-
- if (unlikely(page_group_by_mobility_disabled))
- return MIGRATE_UNMOVABLE;
-
- /* Cluster high-order atomic allocations together */
- if (unlikely(order > 0) &&
- (!(gfp_flags & __GFP_WAIT) || in_interrupt()))
- return MIGRATE_HIGHATOMIC;
-
- /* Cluster based on mobility */
- return (((gfp_flags & __GFP_MOVABLE) != 0) << 1) |
- ((gfp_flags & __GFP_RECLAIMABLE) != 0);
-}
-
-#else
-static inline int get_pageblock_migratetype(struct page *page)
-{
- return MIGRATE_UNMOVABLE;
-}
-
-static void set_pageblock_migratetype(struct page *page, int migratetype)
-{
-}
-
-static inline int allocflags_to_migratetype(gfp_t gfp_flags, int order)
-{
- return MIGRATE_UNMOVABLE;
-}
-#endif /* CONFIG_PAGE_GROUP_BY_MOBILITY */
-
#ifdef CONFIG_DEBUG_VM
static int page_outside_zone_boundaries(struct zone *zone, struct page *page)
{
static void bad_page(struct page *page)
{
- 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"
- KERN_EMERG "Trying to fix it up, but a reboot is needed\n"
- KERN_EMERG "Backtrace:\n",
+ void *pc = page_get_page_cgroup(page);
+
+ 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);
+ }
+ printk(KERN_EMERG "Trying to fix it up, but a reboot is needed\n"
+ KERN_EMERG "Backtrace:\n");
dump_stack();
page->flags &= ~(1 << PG_lru |
1 << PG_private |
{
int i;
- VM_BUG_ON((gfp_flags & (__GFP_WAIT | __GFP_HIGHMEM)) == __GFP_HIGHMEM);
/*
* clear_highpage() will use KM_USER0, so it's a bug to use __GFP_ZERO
* and __GFP_HIGHMEM from hard or soft interrupt context.
clear_highpage(page + i);
}
-/*
- * function for dealing with page's order in buddy system.
- * zone->lock is already acquired when we use these.
- * So, we don't need atomic page->flags operations here.
- */
-static inline unsigned long page_order(struct page *page)
-{
- return page_private(page);
-}
-
static inline void set_page_order(struct page *page, int order)
{
set_page_private(page, order);
{
if (unlikely(page_mapcount(page) |
(page->mapping != NULL) |
+ (page_get_page_cgroup(page) != NULL) |
(page_count(page) != 0) |
(page->flags & (
1 << PG_lru |
struct list_head *list, int order)
{
spin_lock(&zone->lock);
- zone->all_unreclaimable = 0;
+ zone_clear_flag(zone, ZONE_ALL_UNRECLAIMABLE);
zone->pages_scanned = 0;
while (count--) {
struct page *page;
static void free_one_page(struct zone *zone, struct page *page, int order)
{
spin_lock(&zone->lock);
- zone->all_unreclaimable = 0;
+ zone_clear_flag(zone, ZONE_ALL_UNRECLAIMABLE);
zone->pages_scanned = 0;
__free_one_page(page, zone, order);
spin_unlock(&zone->lock);
/*
* permit the bootmem allocator to evade page validation on high-order frees
*/
-void fastcall __init __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);
{
if (unlikely(page_mapcount(page) |
(page->mapping != NULL) |
+ (page_get_page_cgroup(page) != NULL) |
(page_count(page) != 0) |
(page->flags & (
1 << PG_lru |
return 0;
}
-#ifdef CONFIG_PAGE_GROUP_BY_MOBILITY
+/*
+ * 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,
+ int migratetype)
+{
+ unsigned int current_order;
+ struct free_area * area;
+ struct page *page;
+
+ /* Find a page of the appropriate size in the preferred list */
+ for (current_order = order; current_order < MAX_ORDER; ++current_order) {
+ area = &(zone->free_area[current_order]);
+ if (list_empty(&area->free_list[migratetype]))
+ continue;
+
+ page = list_entry(area->free_list[migratetype].next,
+ struct page, lru);
+ 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 NULL;
+}
+
+
/*
* 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_HIGHATOMIC },
- [MIGRATE_RECLAIMABLE] = { MIGRATE_UNMOVABLE, MIGRATE_MOVABLE, MIGRATE_HIGHATOMIC },
- [MIGRATE_MOVABLE] = { MIGRATE_RECLAIMABLE, MIGRATE_UNMOVABLE,MIGRATE_HIGHATOMIC },
- [MIGRATE_HIGHATOMIC] = { MIGRATE_RECLAIMABLE, MIGRATE_UNMOVABLE,MIGRATE_MOVABLE},
+ [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 */
};
/*
* Move the free pages in a range to the free lists of the requested type.
- * Note that start_page and end_pages are not aligned in a MAX_ORDER_NR_PAGES
+ * Note that start_page and end_pages are not aligned on a pageblock
* boundary. If alignment is required, use move_freepages_block()
*/
int move_freepages(struct zone *zone,
{
struct page *page;
unsigned long order;
- int blocks_moved = 0;
+ int pages_moved = 0;
#ifndef CONFIG_HOLES_IN_ZONE
/*
* CONFIG_HOLES_IN_ZONE is set. This bug check is probably redundant
* anyway as we check zone boundaries in move_freepages_block().
* Remove at a later date when no bug reports exist related to
- * CONFIG_PAGE_GROUP_BY_MOBILITY
+ * grouping pages by mobility
*/
BUG_ON(page_zone(start_page) != page_zone(end_page));
#endif
list_add(&page->lru,
&zone->free_area[order].free_list[migratetype]);
page += 1 << order;
- blocks_moved++;
+ pages_moved += 1 << order;
}
- return blocks_moved;
+ return pages_moved;
}
int move_freepages_block(struct zone *zone, struct page *page, int migratetype)
struct page *start_page, *end_page;
start_pfn = page_to_pfn(page);
- start_pfn = start_pfn & ~(MAX_ORDER_NR_PAGES-1);
+ start_pfn = start_pfn & ~(pageblock_nr_pages-1);
start_page = pfn_to_page(start_pfn);
- end_page = start_page + MAX_ORDER_NR_PAGES - 1;
- end_pfn = start_pfn + MAX_ORDER_NR_PAGES - 1;
+ end_page = start_page + pageblock_nr_pages - 1;
+ end_pfn = start_pfn + pageblock_nr_pages - 1;
/* Do not cross zone boundaries */
if (start_pfn < zone->zone_start_pfn)
return move_freepages(zone, start_page, end_page, migratetype);
}
-/* Return the page with the lowest PFN in the list */
-static struct page *min_page(struct list_head *list)
-{
- unsigned long min_pfn = -1UL;
- struct page *min_page = NULL, *page;;
-
- list_for_each_entry(page, list, lru) {
- unsigned long pfn = page_to_pfn(page);
- if (pfn < min_pfn) {
- min_pfn = pfn;
- min_page = page;
- }
- }
-
- return min_page;
-}
-
/* Remove an element from the buddy allocator from the fallback list */
static struct page *__rmqueue_fallback(struct zone *zone, int order,
int start_migratetype)
int current_order;
struct page *page;
int migratetype, i;
- int nonatomic_fallback_atomic = 0;
-retry:
/* 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++) {
migratetype = fallbacks[start_migratetype][i];
- /*
- * Make it hard to fallback to blocks used for
- * high-order atomic allocations
- */
- if (migratetype == MIGRATE_HIGHATOMIC &&
- start_migratetype != MIGRATE_UNMOVABLE &&
- !nonatomic_fallback_atomic)
+ /* MIGRATE_RESERVE handled later if necessary */
+ if (migratetype == MIGRATE_RESERVE)
continue;
area = &(zone->free_area[current_order]);
if (list_empty(&area->free_list[migratetype]))
continue;
- /* Bias kernel allocations towards low pfns */
page = list_entry(area->free_list[migratetype].next,
struct page, lru);
- if (unlikely(start_migratetype != MIGRATE_MOVABLE))
- page = min_page(&area->free_list[migratetype]);
area->nr_free--;
/*
* If breaking a large block of pages, move all free
- * pages to the preferred allocation list
+ * 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 >= MAX_ORDER / 2)) {
+ if (unlikely(current_order >= (pageblock_order >> 1)) ||
+ start_migratetype == MIGRATE_RECLAIMABLE) {
+ 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)))
+ set_pageblock_migratetype(page,
+ start_migratetype);
+
migratetype = start_migratetype;
- move_freepages_block(zone, page, migratetype);
}
/* Remove the page from the freelists */
__mod_zone_page_state(zone, NR_FREE_PAGES,
-(1UL << order));
- if (current_order == MAX_ORDER - 1)
+ if (current_order == pageblock_order)
set_pageblock_migratetype(page,
start_migratetype);
}
}
- /* Allow fallback to high-order atomic blocks if memory is that low */
- if (!nonatomic_fallback_atomic) {
- nonatomic_fallback_atomic = 1;
- goto retry;
- }
-
- return NULL;
+ /* Use MIGRATE_RESERVE rather than fail an allocation */
+ return __rmqueue_smallest(zone, order, MIGRATE_RESERVE);
}
-#else
-static struct page *__rmqueue_fallback(struct zone *zone, int order,
- int start_migratetype)
-{
- return NULL;
-}
-#endif /* CONFIG_PAGE_GROUP_BY_MOBILITY */
-/*
+/*
* Do the hard work of removing an element from the buddy allocator.
* Call me with the zone->lock already held.
*/
static struct page *__rmqueue(struct zone *zone, unsigned int order,
int migratetype)
{
- struct free_area * area;
- unsigned int current_order;
struct page *page;
- /* Find a page of the appropriate size in the preferred list */
- for (current_order = order; current_order < MAX_ORDER; ++current_order) {
- area = &(zone->free_area[current_order]);
- if (list_empty(&area->free_list[migratetype]))
- continue;
-
- page = list_entry(area->free_list[migratetype].next,
- struct page, lru);
- 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);
- goto got_page;
- }
+ page = __rmqueue_smallest(zone, order, migratetype);
- page = __rmqueue_fallback(zone, order, migratetype);
-
-got_page:
+ if (unlikely(!page))
+ page = __rmqueue_fallback(zone, order, migratetype);
return page;
}
struct page *page = __rmqueue(zone, order, migratetype);
if (unlikely(page == NULL))
break;
+
+ /*
+ * Split buddy pages returned by expand() are received here
+ * in physical page order. The page is added to the callers and
+ * list and the list head then moves forward. From the callers
+ * perspective, the linked list is ordered by page number in
+ * some conditions. This is useful for IO devices that can
+ * merge IO requests if the physical pages are ordered
+ * properly.
+ */
list_add(&page->lru, list);
set_page_private(page, migratetype);
+ list = &page->lru;
}
spin_unlock(&zone->lock);
return i;
}
#endif
-static void __drain_pages(unsigned int cpu)
+/*
+ * Drain pages of the indicated processor.
+ *
+ * The processor must either be the current processor and the
+ * thread pinned to the current processor or a processor that
+ * is not online.
+ */
+static void drain_pages(unsigned int cpu)
{
unsigned long flags;
struct zone *zone;
- int i;
for_each_zone(zone) {
struct per_cpu_pageset *pset;
+ struct per_cpu_pages *pcp;
if (!populated_zone(zone))
continue;
pset = zone_pcp(zone, cpu);
- for (i = 0; i < ARRAY_SIZE(pset->pcp); i++) {
- struct per_cpu_pages *pcp;
-
- pcp = &pset->pcp[i];
- local_irq_save(flags);
- free_pages_bulk(zone, pcp->count, &pcp->list, 0);
- pcp->count = 0;
- local_irq_restore(flags);
- }
+
+ pcp = &pset->pcp;
+ local_irq_save(flags);
+ free_pages_bulk(zone, pcp->count, &pcp->list, 0);
+ pcp->count = 0;
+ local_irq_restore(flags);
}
}
+/*
+ * Spill all of this CPU's per-cpu pages back into the buddy allocator.
+ */
+void drain_local_pages(void *arg)
+{
+ drain_pages(smp_processor_id());
+}
+
+/*
+ * Spill all the per-cpu pages from all CPUs back into the buddy allocator
+ */
+void drain_all_pages(void)
+{
+ on_each_cpu(drain_local_pages, NULL, 0, 1);
+}
+
#ifdef CONFIG_HIBERNATION
void mark_free_pages(struct zone *zone)
}
#endif /* CONFIG_PM */
-#if defined(CONFIG_HIBERNATION) || defined(CONFIG_PAGE_GROUP_BY_MOBILITY)
-/*
- * Spill all of this CPU's per-cpu pages back into the buddy allocator.
- */
-void drain_local_pages(void)
-{
- unsigned long flags;
-
- local_irq_save(flags);
- __drain_pages(smp_processor_id());
- local_irq_restore(flags);
-}
-
-void smp_drain_local_pages(void *arg)
-{
- drain_local_pages();
-}
-
-/*
- * Spill all the per-cpu pages from all CPUs back into the buddy allocator
- */
-void drain_all_local_pages(void)
-{
- unsigned long flags;
-
- local_irq_save(flags);
- __drain_pages(smp_processor_id());
- local_irq_restore(flags);
-
- smp_call_function(smp_drain_local_pages, NULL, 0, 1);
-}
-#else
-void drain_all_local_pages(void) {}
-#endif /* CONFIG_HIBERNATION || CONFIG_PAGE_GROUP_BY_MOBILITY */
-
/*
* Free a 0-order page
*/
-static void fastcall free_hot_cold_page(struct page *page, int cold)
+static void free_hot_cold_page(struct page *page, int cold)
{
struct zone *zone = page_zone(page);
struct per_cpu_pages *pcp;
arch_free_page(page, 0);
kernel_map_pages(page, 1, 0);
- pcp = &zone_pcp(zone, get_cpu())->pcp[cold];
+ pcp = &zone_pcp(zone, get_cpu())->pcp;
local_irq_save(flags);
__count_vm_event(PGFREE);
- list_add(&page->lru, &pcp->list);
+ if (cold)
+ list_add_tail(&page->lru, &pcp->list);
+ else
+ list_add(&page->lru, &pcp->list);
set_page_private(page, get_pageblock_migratetype(page));
pcp->count++;
if (pcp->count >= pcp->high) {
put_cpu();
}
-void fastcall free_hot_page(struct page *page)
+void free_hot_page(struct page *page)
{
free_hot_cold_page(page, 0);
}
-void fastcall free_cold_page(struct page *page)
+void free_cold_page(struct page *page)
{
free_hot_cold_page(page, 1);
}
struct page *page;
int cold = !!(gfp_flags & __GFP_COLD);
int cpu;
- int migratetype = allocflags_to_migratetype(gfp_flags, order);
+ int migratetype = allocflags_to_migratetype(gfp_flags);
again:
cpu = get_cpu();
if (likely(order == 0)) {
struct per_cpu_pages *pcp;
- pcp = &zone_pcp(zone, cpu)->pcp[cold];
+ pcp = &zone_pcp(zone, cpu)->pcp;
local_irq_save(flags);
if (!pcp->count) {
pcp->count = rmqueue_bulk(zone, 0,
goto failed;
}
-#ifdef CONFIG_PAGE_GROUP_BY_MOBILITY
/* Find a page of the appropriate migrate type */
- list_for_each_entry(page, &pcp->list, lru)
- if (page_private(page) == migratetype)
- break;
+ 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->batch, &pcp->list, migratetype);
page = list_entry(pcp->list.next, struct page, lru);
}
-#else
- page = list_entry(pcp->list.next, struct page, lru);
-#endif /* CONFIG_PAGE_GROUP_BY_MOBILITY */
list_del(&page->lru);
pcp->count--;
* skip over zones that are not allowed by the cpuset, or that have
* been recently (in last second) found to be nearly full. See further
* comments in mmzone.h. Reduces cache footprint of zonelist scans
- * that have to skip over alot of full or unallowed zones.
+ * that have to skip over a lot of full or unallowed zones.
*
* If the zonelist cache is present in the passed in zonelist, then
* returns a pointer to the allowed node mask (either the current
if (!zlc)
return NULL;
- if (jiffies - zlc->last_full_zap > 1 * HZ) {
+ if (time_after(jiffies, zlc->last_full_zap + HZ)) {
bitmap_zero(zlc->fullzones, MAX_ZONES_PER_ZONELIST);
zlc->last_full_zap = jiffies;
}
/*
* This is the 'heart' of the zoned buddy allocator.
*/
-struct page * fastcall
+struct page *
__alloc_pages(gfp_t gfp_mask, unsigned int order,
struct zonelist *zonelist)
{
cond_resched();
if (order != 0)
- drain_all_local_pages();
+ drain_all_pages();
if (likely(did_some_progress)) {
page = get_page_from_freelist(gfp_mask, order,
if (page)
goto got_pg;
} else if ((gfp_mask & __GFP_FS) && !(gfp_mask & __GFP_NORETRY)) {
+ if (!try_set_zone_oom(zonelist)) {
+ schedule_timeout_uninterruptible(1);
+ goto restart;
+ }
+
/*
* Go through the zonelist yet one more time, keep
* very high watermark here, this is only to catch
*/
page = get_page_from_freelist(gfp_mask|__GFP_HARDWALL, order,
zonelist, ALLOC_WMARK_HIGH|ALLOC_CPUSET);
- if (page)
+ if (page) {
+ clear_zonelist_oom(zonelist);
goto got_pg;
+ }
/* The OOM killer will not help higher order allocs so fail */
- if (order > PAGE_ALLOC_COSTLY_ORDER)
+ if (order > PAGE_ALLOC_COSTLY_ORDER) {
+ clear_zonelist_oom(zonelist);
goto nopage;
+ }
out_of_memory(zonelist, gfp_mask, order);
+ clear_zonelist_oom(zonelist);
goto restart;
}
/*
* Common helper functions.
*/
-fastcall unsigned long __get_free_pages(gfp_t gfp_mask, unsigned int order)
+unsigned long __get_free_pages(gfp_t gfp_mask, unsigned int order)
{
struct page * page;
page = alloc_pages(gfp_mask, order);
EXPORT_SYMBOL(__get_free_pages);
-fastcall unsigned long get_zeroed_page(gfp_t gfp_mask)
+unsigned long get_zeroed_page(gfp_t gfp_mask)
{
struct page * page;
free_hot_cold_page(pvec->pages[i], pvec->cold);
}
-fastcall void __free_pages(struct page *page, unsigned int order)
+void __free_pages(struct page *page, unsigned int order)
{
if (put_page_testzero(page)) {
if (order == 0)
EXPORT_SYMBOL(__free_pages);
-fastcall void free_pages(unsigned long addr, unsigned int order)
+void free_pages(unsigned long addr, unsigned int order)
{
if (addr != 0) {
VM_BUG_ON(!virt_addr_valid((void *)addr));
pageset = zone_pcp(zone, cpu);
- printk("CPU %4d: Hot: hi:%5d, btch:%4d usd:%4d "
- "Cold: hi:%5d, btch:%4d usd:%4d\n",
- cpu, pageset->pcp[0].high,
- pageset->pcp[0].batch, pageset->pcp[0].count,
- pageset->pcp[1].high, pageset->pcp[1].batch,
- pageset->pcp[1].count);
+ printk("CPU %4d: hi:%5d, btch:%4d usd:%4d\n",
+ cpu, pageset->pcp.high,
+ pageset->pcp.batch, pageset->pcp.count);
}
}
K(zone_page_state(zone, NR_INACTIVE)),
K(zone->present_pages),
zone->pages_scanned,
- (zone->all_unreclaimable ? "yes" : "no")
+ (zone_is_all_unreclaimable(zone) ? "yes" : "no")
);
printk("lowmem_reserve[]:");
for (i = 0; i < MAX_NR_ZONES; i++)
printk("= %lukB\n", K(total));
}
+ printk("%ld total pagecache pages\n", global_page_state(NR_FILE_PAGES));
+
show_swap_cache_info();
}
__build_all_zonelists(NULL);
cpuset_init_current_mems_allowed();
} else {
- /* we have to stop all cpus to guaranntee there is no user
+ /* we have to stop all cpus to guarantee there is no user
of zonelist */
stop_machine_run(__build_all_zonelists, NULL, NR_CPUS);
/* cpuset refresh routine should be here */
* made on memory-hotadd so a system can start with mobility
* disabled and enable it later
*/
- if (vm_total_pages < (MAX_ORDER_NR_PAGES * MIGRATE_TYPES))
+ if (vm_total_pages < (pageblock_nr_pages * MIGRATE_TYPES))
page_group_by_mobility_disabled = 1;
else
page_group_by_mobility_disabled = 0;
#define LONG_ALIGN(x) (((x)+(sizeof(long))-1)&~((sizeof(long))-1))
/*
+ * 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
+ * higher will lead to a bigger reserve which will get freed as contiguous
+ * blocks as reclaim kicks in
+ */
+static void setup_zone_migrate_reserve(struct zone *zone)
+{
+ unsigned long start_pfn, pfn, end_pfn;
+ struct page *page;
+ unsigned long reserve, block_migratetype;
+
+ /* 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) >>
+ pageblock_order;
+
+ for (pfn = start_pfn; pfn < end_pfn; pfn += pageblock_nr_pages) {
+ if (!pfn_valid(pfn))
+ continue;
+ page = pfn_to_page(pfn);
+
+ /* 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;
+ }
+
+ /* 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 the reserve is met and this is a previous reserved block,
+ * take it back
+ */
+ if (block_migratetype == MIGRATE_RESERVE) {
+ set_pageblock_migratetype(page, MIGRATE_MOVABLE);
+ move_freepages_block(zone, page, MIGRATE_MOVABLE);
+ }
+ }
+}
+
+/*
* Initially all pages are reserved - free ones are freed
* up by free_all_bootmem() once the early boot process is
* done. Non-atomic initialization, single-pass.
* movable at startup. This will force kernel allocations
* to reserve their blocks rather than leaking throughout
* the address space during boot when many long-lived
- * kernel allocations are made
+ * kernel allocations are made. Later some blocks near
+ * the start are marked MIGRATE_RESERVE by
+ * setup_zone_migrate_reserve()
*/
- set_pageblock_migratetype(page, MIGRATE_MOVABLE);
+ if ((pfn & (pageblock_nr_pages-1)))
+ set_pageblock_migratetype(page, MIGRATE_MOVABLE);
INIT_LIST_HEAD(&page->lru);
#ifdef WANT_PAGE_VIRTUAL
}
}
-static void __meminit zone_init_free_lists(struct pglist_data *pgdat,
- struct zone *zone, unsigned long size)
+static void __meminit zone_init_free_lists(struct zone *zone)
{
int order, t;
for_each_migratetype_order(order, t) {
memmap_init_zone((size), (nid), (zone), (start_pfn), MEMMAP_EARLY)
#endif
-static int __devinit zone_batchsize(struct zone *zone)
+static int zone_batchsize(struct zone *zone)
{
int batch;
memset(p, 0, sizeof(*p));
- pcp = &p->pcp[0]; /* hot */
+ pcp = &p->pcp;
pcp->count = 0;
pcp->high = 6 * batch;
pcp->batch = max(1UL, 1 * batch);
INIT_LIST_HEAD(&pcp->list);
-
- pcp = &p->pcp[1]; /* cold*/
- pcp->count = 0;
- pcp->high = 2 * batch;
- pcp->batch = max(1UL, batch/2);
- INIT_LIST_HEAD(&pcp->list);
}
/*
{
struct per_cpu_pages *pcp;
- pcp = &p->pcp[0]; /* hot list */
+ pcp = &p->pcp;
pcp->high = high;
pcp->batch = max(1UL, high/4);
if ((high/4) > (PAGE_SHIFT * 8))
memmap_init(size, pgdat->node_id, zone_idx(zone), zone_start_pfn);
- zone_init_free_lists(pgdat, zone, zone->spanned_pages);
+ zone_init_free_lists(zone);
return 0;
}
/*
* Basic iterator support. Return the next active range of PFNs for a node
- * Note: nid == MAX_NUMNODES returns next region regardles of node
+ * Note: nid == MAX_NUMNODES returns next region regardless of node
*/
static int __meminit next_active_region_index_in_nid(int index, int nid)
{
#ifndef CONFIG_SPARSEMEM
/*
* Calculate the size of the zone->blockflags rounded to an unsigned long
- * Start by making sure zonesize is a multiple of MAX_ORDER-1 by rounding up
- * Then figure 1 NR_PAGEBLOCK_BITS worth of bits per MAX_ORDER-1, finally
+ * Start by making sure zonesize is a multiple of pageblock_order by rounding
+ * up. Then use 1 NR_PAGEBLOCK_BITS worth of bits per pageblock, finally
* round what is now in bits to nearest long in bits, then return it in
* bytes.
*/
{
unsigned long usemapsize;
- usemapsize = roundup(zonesize, MAX_ORDER_NR_PAGES);
- usemapsize = usemapsize >> (MAX_ORDER-1);
+ usemapsize = roundup(zonesize, pageblock_nr_pages);
+ usemapsize = usemapsize >> pageblock_order;
usemapsize *= NR_PAGEBLOCK_BITS;
usemapsize = roundup(usemapsize, 8 * sizeof(unsigned long));
struct zone *zone, 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)
+{
+ /* Check that pageblock_nr_pages has not already been setup */
+ if (pageblock_order)
+ return;
+
+ /*
+ * Assume the largest contiguous order of interest is a huge page.
+ * This value may be variable depending on boot parameters on IA64
+ */
+ pageblock_order = order;
+}
+#else /* CONFIG_HUGETLB_PAGE_SIZE_VARIABLE */
+
+/*
+ * 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
+ */
+static inline int pageblock_default_order(unsigned int order)
+{
+ return MAX_ORDER-1;
+}
+#define set_pageblock_order(x) do {} while (0)
+
+#endif /* CONFIG_HUGETLB_PAGE_SIZE_VARIABLE */
+
/*
* Set up the zone data structures:
* - mark all pages reserved
* - mark all memory queues empty
* - clear the memory bitmaps
*/
-static void __meminit free_area_init_core(struct pglist_data *pgdat,
+static void __paginginit free_area_init_core(struct pglist_data *pgdat,
unsigned long *zones_size, unsigned long *zholes_size)
{
enum zone_type j;
zone->nr_scan_active = 0;
zone->nr_scan_inactive = 0;
zap_zone_vm_stats(zone);
- atomic_set(&zone->reclaim_in_progress, 0);
+ zone->flags = 0;
if (!size)
continue;
+ set_pageblock_order(pageblock_default_order());
setup_usemap(pgdat, zone, size);
ret = init_currently_empty_zone(zone, zone_start_pfn,
size, MEMMAP_EARLY);
mem_map = NODE_DATA(0)->node_mem_map;
#ifdef CONFIG_ARCH_POPULATES_NODE_MAP
if (page_to_pfn(mem_map) != pgdat->node_start_pfn)
- mem_map -= pgdat->node_start_pfn;
+ mem_map -= (pgdat->node_start_pfn - ARCH_PFN_OFFSET);
#endif /* CONFIG_ARCH_POPULATES_NODE_MAP */
}
#endif
#endif /* CONFIG_FLAT_NODE_MEM_MAP */
}
-void __meminit free_area_init_node(int nid, struct pglist_data *pgdat,
+void __paginginit free_area_init_node(int nid, struct pglist_data *pgdat,
unsigned long *zones_size, unsigned long node_start_pfn,
unsigned long *zholes_size)
{
* Sum pages in active regions for movable zone.
* Populate N_HIGH_MEMORY for calculating usable_nodes.
*/
-unsigned long __init early_calculate_totalpages(void)
+static unsigned long __init early_calculate_totalpages(void)
{
int i;
unsigned long totalpages = 0;
int cpu = (unsigned long)hcpu;
if (action == CPU_DEAD || action == CPU_DEAD_FROZEN) {
- local_irq_disable();
- __drain_pages(cpu);
+ drain_pages(cpu);
+
+ /*
+ * Spill the event counters of the dead processor
+ * into the current processors event counters.
+ * This artificially elevates the count of the current
+ * processor.
+ */
vm_events_fold_cpu(cpu);
- local_irq_enable();
+
+ /*
+ * Zero the differential counters of the dead processor
+ * so that the vm statistics are consistent.
+ *
+ * This is only okay since the processor is dead and cannot
+ * race with what we are doing.
+ */
refresh_cpu_vm_stats(cpu);
}
return NOTIFY_OK;
zone->pages_low = zone->pages_min + (tmp >> 2);
zone->pages_high = zone->pages_min + (tmp >> 1);
+ setup_zone_migrate_reserve(zone);
spin_unlock_irqrestore(&zone->lru_lock, flags);
}
{
#ifdef CONFIG_SPARSEMEM
pfn &= (PAGES_PER_SECTION-1);
- return (pfn >> (MAX_ORDER-1)) * NR_PAGEBLOCK_BITS;
+ return (pfn >> pageblock_order) * NR_PAGEBLOCK_BITS;
#else
pfn = pfn - zone->zone_start_pfn;
- return (pfn >> (MAX_ORDER-1)) * NR_PAGEBLOCK_BITS;
+ return (pfn >> pageblock_order) * NR_PAGEBLOCK_BITS;
#endif /* CONFIG_SPARSEMEM */
}
/**
- * get_pageblock_flags_group - Return the requested group of flags for the MAX_ORDER_NR_PAGES block of pages
+ * get_pageblock_flags_group - 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
}
/**
- * set_pageblock_flags_group - Set the requested group of flags for a MAX_ORDER_NR_PAGES block of pages
+ * set_pageblock_flags_group - 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
else
__clear_bit(bitidx + start_bitidx, bitmap);
}
+
+/*
+ * 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.
+ */
+
+int set_migratetype_isolate(struct page *page)
+{
+ struct zone *zone;
+ unsigned long flags;
+ int ret = -EBUSY;
+
+ zone = page_zone(page);
+ spin_lock_irqsave(&zone->lock, flags);
+ /*
+ * In future, more migrate types will be able to be isolation target.
+ */
+ if (get_pageblock_migratetype(page) != MIGRATE_MOVABLE)
+ goto out;
+ set_pageblock_migratetype(page, MIGRATE_ISOLATE);
+ move_freepages_block(zone, page, MIGRATE_ISOLATE);
+ ret = 0;
+out:
+ spin_unlock_irqrestore(&zone->lock, flags);
+ if (!ret)
+ drain_all_pages();
+ return ret;
+}
+
+void unset_migratetype_isolate(struct page *page)
+{
+ 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);
+}
+
+#ifdef CONFIG_MEMORY_HOTREMOVE
+/*
+ * All pages in the range must be isolated before calling this.
+ */
+void
+__offline_isolated_pages(unsigned long start_pfn, unsigned long end_pfn)
+{
+ struct page *page;
+ struct zone *zone;
+ int order, i;
+ unsigned long pfn;
+ unsigned long flags;
+ /* find the first valid pfn */
+ for (pfn = start_pfn; pfn < end_pfn; pfn++)
+ if (pfn_valid(pfn))
+ break;
+ if (pfn == end_pfn)
+ return;
+ zone = page_zone(pfn_to_page(pfn));
+ spin_lock_irqsave(&zone->lock, flags);
+ pfn = start_pfn;
+ while (pfn < end_pfn) {
+ if (!pfn_valid(pfn)) {
+ pfn++;
+ continue;
+ }
+ page = pfn_to_page(pfn);
+ BUG_ON(page_count(page));
+ BUG_ON(!PageBuddy(page));
+ order = page_order(page);
+#ifdef CONFIG_DEBUG_VM
+ printk(KERN_INFO "remove from free list %lx %d %lx\n",
+ pfn, 1 << order, end_pfn);
+#endif
+ list_del(&page->lru);
+ rmv_page_order(page);
+ zone->free_area[order].nr_free--;
+ __mod_zone_page_state(zone, NR_FREE_PAGES,
+ - (1UL << order));
+ for (i = 0; i < (1 << order); i++)
+ SetPageReserved((page+i));
+ pfn += (1 << order);
+ }
+ spin_unlock_irqrestore(&zone->lock, flags);
+}
+#endif
git://ftp.safe.ca / safe / jmp / linux-2.6 / blobdiff