#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 <linux/debugobjects.h>
#include <asm/tlbflush.h>
#include <asm/div64.h>
#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 */
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)
-{
- WARN_ON((gfp_flags & GFP_MOVABLE_MASK) == GFP_MOVABLE_MASK);
-
- if (unlikely(page_group_by_mobility_disabled))
- return MIGRATE_UNMOVABLE;
-
- /* Cluster based on mobility */
- return (((gfp_flags & __GFP_MOVABLE) != 0) << 1) |
- ((gfp_flags & __GFP_RECLAIMABLE) != 0);
-}
-
#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 |
- 1 << PG_locked |
- 1 << PG_active |
- 1 << PG_dirty |
- 1 << PG_reclaim |
- 1 << PG_slab |
- 1 << PG_swapcache |
- 1 << PG_writeback |
- 1 << PG_buddy );
+ page->flags &= ~PAGE_FLAGS_CLEAR_WHEN_BAD;
set_page_count(page, 0);
reset_page_mapcount(page);
page->mapping = NULL;
{
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 |
- 1 << PG_private |
- 1 << PG_locked |
- 1 << PG_active |
- 1 << PG_slab |
- 1 << PG_swapcache |
- 1 << PG_writeback |
- 1 << PG_reserved |
- 1 << PG_buddy ))))
+ (page->flags & PAGE_FLAGS_CHECK_AT_FREE)))
bad_page(page);
if (PageDirty(page))
__ClearPageDirty(page);
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);
if (reserved)
return;
- if (!PageHighMem(page))
+ if (!PageHighMem(page)) {
debug_check_no_locks_freed(page_address(page),PAGE_SIZE<<order);
+ debug_check_no_obj_freed(page_address(page),
+ PAGE_SIZE << order);
+ }
arch_free_page(page, order);
kernel_map_pages(page, 1 << order, 0);
/*
* 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 __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 |
- 1 << PG_private |
- 1 << PG_locked |
- 1 << PG_active |
- 1 << PG_dirty |
- 1 << PG_slab |
- 1 << PG_swapcache |
- 1 << PG_writeback |
- 1 << PG_reserved |
- 1 << PG_buddy ))))
+ (page->flags & PAGE_FLAGS_CHECK_AT_PREP)))
bad_page(page);
/*
if (PageReserved(page))
return 1;
- page->flags &= ~(1 << PG_uptodate | 1 << PG_error | 1 << PG_readahead |
+ 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);
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)
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--;
/*
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, 1);
+}
+
#ifdef CONFIG_HIBERNATION
void mark_free_pages(struct zone *zone)
#endif /* CONFIG_PM */
/*
- * 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);
-}
-
-/*
* 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;
if (free_pages_check(page))
return;
- if (!PageHighMem(page))
+ 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[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);
}
* we cheat by calling it from here, in the order > 0 path. Saves a branch
* or two.
*/
-static struct page *buffered_rmqueue(struct zonelist *zonelist,
+static struct page *buffered_rmqueue(struct zone *preferred_zone,
struct zone *zone, int order, gfp_t gfp_flags)
{
unsigned long flags;
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,
}
/* 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)) {
}
__count_zone_vm_events(PGALLOC, zone, 1 << order);
- zone_statistics(zonelist, zone);
+ zone_statistics(preferred_zone, zone);
local_irq_restore(flags);
put_cpu();
* 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;
}
* We are low on memory in the second scan, and should leave no stone
* unturned looking for a free page.
*/
-static int zlc_zone_worth_trying(struct zonelist *zonelist, struct zone **z,
+static int zlc_zone_worth_trying(struct zonelist *zonelist, struct zoneref *z,
nodemask_t *allowednodes)
{
struct zonelist_cache *zlc; /* cached zonelist speedup info */
if (!zlc)
return 1;
- i = z - zonelist->zones;
+ i = z - zonelist->_zonerefs;
n = zlc->z_to_n[i];
/* This zone is worth trying if it is allowed but not full */
* zlc->fullzones, so that subsequent attempts to allocate a page
* from that zone don't waste time re-examining it.
*/
-static void zlc_mark_zone_full(struct zonelist *zonelist, struct zone **z)
+static void zlc_mark_zone_full(struct zonelist *zonelist, struct zoneref *z)
{
struct zonelist_cache *zlc; /* cached zonelist speedup info */
int i; /* index of *z in zonelist zones */
if (!zlc)
return;
- i = z - zonelist->zones;
+ i = z - zonelist->_zonerefs;
set_bit(i, zlc->fullzones);
}
return NULL;
}
-static int zlc_zone_worth_trying(struct zonelist *zonelist, struct zone **z,
+static int zlc_zone_worth_trying(struct zonelist *zonelist, struct zoneref *z,
nodemask_t *allowednodes)
{
return 1;
}
-static void zlc_mark_zone_full(struct zonelist *zonelist, struct zone **z)
+static void zlc_mark_zone_full(struct zonelist *zonelist, struct zoneref *z)
{
}
#endif /* CONFIG_NUMA */
* a page.
*/
static struct page *
-get_page_from_freelist(gfp_t gfp_mask, unsigned int order,
- struct zonelist *zonelist, int alloc_flags)
+get_page_from_freelist(gfp_t gfp_mask, nodemask_t *nodemask, unsigned int order,
+ struct zonelist *zonelist, int high_zoneidx, int alloc_flags)
{
- struct zone **z;
+ struct zoneref *z;
struct page *page = NULL;
- int classzone_idx = zone_idx(zonelist->zones[0]);
- struct zone *zone;
+ int classzone_idx;
+ struct zone *zone, *preferred_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 */
- enum zone_type highest_zoneidx = -1; /* Gets set for policy zonelists */
+
+ (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.
* See also cpuset_zone_allowed() comment in kernel/cpuset.c.
*/
- z = zonelist->zones;
-
- do {
- /*
- * In NUMA, this could be a policy zonelist which contains
- * zones that may not be allowed by the current gfp_mask.
- * Check the zone is allowed by the current flags
- */
- if (unlikely(alloc_should_filter_zonelist(zonelist))) {
- if (highest_zoneidx == -1)
- highest_zoneidx = gfp_zone(gfp_mask);
- if (zone_idx(*z) > highest_zoneidx)
- continue;
- }
-
+ for_each_zone_zonelist_nodemask(zone, z, zonelist,
+ high_zoneidx, nodemask) {
if (NUMA_BUILD && zlc_active &&
!zlc_zone_worth_trying(zonelist, z, allowednodes))
continue;
- zone = *z;
if ((alloc_flags & ALLOC_CPUSET) &&
!cpuset_zone_allowed_softwall(zone, gfp_mask))
goto try_next_zone;
}
}
- page = buffered_rmqueue(zonelist, zone, order, gfp_mask);
+ page = buffered_rmqueue(preferred_zone, zone, order, gfp_mask);
if (page)
break;
this_zone_full:
zlc_active = 1;
did_zlc_setup = 1;
}
- } while (*(++z) != NULL);
+ }
if (unlikely(NUMA_BUILD && page == NULL && zlc_active)) {
/* Disable zlc cache for second zonelist scan */
/*
* This is the 'heart' of the zoned buddy allocator.
*/
-struct page * fastcall
-__alloc_pages(gfp_t gfp_mask, unsigned int order,
- struct zonelist *zonelist)
+static struct page *
+__alloc_pages_internal(gfp_t gfp_mask, unsigned int order,
+ struct zonelist *zonelist, nodemask_t *nodemask)
{
const gfp_t wait = gfp_mask & __GFP_WAIT;
- struct zone **z;
+ 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;
- int did_some_progress;
+ unsigned long did_some_progress;
+ unsigned long pages_reclaimed = 0;
might_sleep_if(wait);
return NULL;
restart:
- z = zonelist->zones; /* the list of zones suitable for gfp_mask */
+ z = zonelist->_zonerefs; /* the list of zones suitable for gfp_mask */
- if (unlikely(*z == NULL)) {
+ if (unlikely(!z->zone)) {
/*
* Happens if we have an empty zonelist as a result of
* GFP_THISNODE being used on a memoryless node
return NULL;
}
- page = get_page_from_freelist(gfp_mask|__GFP_HARDWALL, order,
- zonelist, ALLOC_WMARK_LOW|ALLOC_CPUSET);
+ page = get_page_from_freelist(gfp_mask|__GFP_HARDWALL, nodemask, order,
+ zonelist, high_zoneidx, ALLOC_WMARK_LOW|ALLOC_CPUSET);
if (page)
goto got_pg;
if (NUMA_BUILD && (gfp_mask & GFP_THISNODE) == GFP_THISNODE)
goto nopage;
- for (z = zonelist->zones; *z; z++)
- wakeup_kswapd(*z, order);
+ for_each_zone_zonelist(zone, z, zonelist, high_zoneidx)
+ wakeup_kswapd(zone, order);
/*
* OK, we're below the kswapd watermark and have kicked background
* Ignore cpuset if GFP_ATOMIC (!wait) rather than fail alloc.
* See also cpuset_zone_allowed() comment in kernel/cpuset.c.
*/
- page = get_page_from_freelist(gfp_mask, order, zonelist, alloc_flags);
+ page = get_page_from_freelist(gfp_mask, nodemask, order, zonelist,
+ high_zoneidx, alloc_flags);
if (page)
goto got_pg;
if (!(gfp_mask & __GFP_NOMEMALLOC)) {
nofail_alloc:
/* go through the zonelist yet again, ignoring mins */
- page = get_page_from_freelist(gfp_mask, order,
- zonelist, ALLOC_NO_WATERMARKS);
+ 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) {
reclaim_state.reclaimed_slab = 0;
p->reclaim_state = &reclaim_state;
- did_some_progress = try_to_free_pages(zonelist->zones, order, gfp_mask);
+ did_some_progress = try_to_free_pages(zonelist, order, gfp_mask);
p->reclaim_state = NULL;
p->flags &= ~PF_MEMALLOC;
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,
- zonelist, alloc_flags);
+ 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, order,
- zonelist, ALLOC_WMARK_HIGH|ALLOC_CPUSET);
- if (page)
+ 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)
+ 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, __GFP_REPEAT means __GFP_NOFAIL for order
- * <= 3, but that may not be true in other implementations.
+ * 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.
*/
+ pages_reclaimed += did_some_progress;
do_retry = 0;
if (!(gfp_mask & __GFP_NORETRY)) {
- if ((order <= PAGE_ALLOC_COSTLY_ORDER) ||
- (gfp_mask & __GFP_REPEAT))
+ 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;
}
return page;
}
+struct page *
+__alloc_pages(gfp_t gfp_mask, unsigned int order,
+ struct zonelist *zonelist)
+{
+ return __alloc_pages_internal(gfp_mask, order, zonelist, NULL);
+}
+
+struct page *
+__alloc_pages_nodemask(gfp_t gfp_mask, unsigned int order,
+ struct zonelist *zonelist, nodemask_t *nodemask)
+{
+ return __alloc_pages_internal(gfp_mask, order, zonelist, nodemask);
+}
+
EXPORT_SYMBOL(__alloc_pages);
/*
* 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));
static unsigned int nr_free_zone_pages(int offset)
{
+ struct zoneref *z;
+ struct zone *zone;
+
/* Just pick one node, since fallback list is circular */
- pg_data_t *pgdat = NODE_DATA(numa_node_id());
unsigned int sum = 0;
- struct zonelist *zonelist = pgdat->node_zonelists + offset;
- struct zone **zonep = zonelist->zones;
- struct zone *zone;
+ struct zonelist *zonelist = node_zonelist(numa_node_id(), GFP_KERNEL);
- for (zone = *zonep++; zone; zone = *zonep++) {
+ for_each_zone_zonelist(zone, z, zonelist, offset) {
unsigned long size = zone->present_pages;
unsigned long high = zone->pages_high;
if (size > high)
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();
}
+static void zoneref_set_zone(struct zone *zone, struct zoneref *zoneref)
+{
+ zoneref->zone = zone;
+ zoneref->zone_idx = zone_idx(zone);
+}
+
/*
* Builds allocation fallback zone lists.
*
zone_type--;
zone = pgdat->node_zones + zone_type;
if (populated_zone(zone)) {
- zonelist->zones[nr_zones++] = zone;
+ zoneref_set_zone(zone,
+ &zonelist->_zonerefs[nr_zones++]);
check_highest_zone(zone_type);
}
int n, val;
int min_val = INT_MAX;
int best_node = -1;
+ node_to_cpumask_ptr(tmp, 0);
/* Use the local node if we haven't already */
if (!node_isset(node, *used_node_mask)) {
}
for_each_node_state(n, N_HIGH_MEMORY) {
- cpumask_t tmp;
/* Don't want a node to appear more than once */
if (node_isset(n, *used_node_mask))
val += (n < node);
/* Give preference to headless and unused nodes */
- tmp = node_to_cpumask(n);
- if (!cpus_empty(tmp))
+ node_to_cpumask_ptr_next(tmp, n);
+ if (!cpus_empty(*tmp))
val += PENALTY_FOR_NODE_WITH_CPUS;
/* Slight preference for less loaded node */
*/
static void build_zonelists_in_node_order(pg_data_t *pgdat, int node)
{
- enum zone_type i;
int j;
struct zonelist *zonelist;
- for (i = 0; i < MAX_NR_ZONES; i++) {
- zonelist = pgdat->node_zonelists + i;
- for (j = 0; zonelist->zones[j] != NULL; j++)
- ;
- j = build_zonelists_node(NODE_DATA(node), zonelist, j, i);
- zonelist->zones[j] = NULL;
- }
+ zonelist = &pgdat->node_zonelists[0];
+ for (j = 0; zonelist->_zonerefs[j].zone != NULL; j++)
+ ;
+ j = build_zonelists_node(NODE_DATA(node), zonelist, j,
+ MAX_NR_ZONES - 1);
+ zonelist->_zonerefs[j].zone = NULL;
+ zonelist->_zonerefs[j].zone_idx = 0;
}
/*
*/
static void build_thisnode_zonelists(pg_data_t *pgdat)
{
- enum zone_type i;
int j;
struct zonelist *zonelist;
- for (i = 0; i < MAX_NR_ZONES; i++) {
- zonelist = pgdat->node_zonelists + MAX_NR_ZONES + i;
- j = build_zonelists_node(pgdat, zonelist, 0, i);
- zonelist->zones[j] = NULL;
- }
+ zonelist = &pgdat->node_zonelists[1];
+ j = build_zonelists_node(pgdat, zonelist, 0, MAX_NR_ZONES - 1);
+ zonelist->_zonerefs[j].zone = NULL;
+ zonelist->_zonerefs[j].zone_idx = 0;
}
/*
static void build_zonelists_in_zone_order(pg_data_t *pgdat, int nr_nodes)
{
- enum zone_type i;
int pos, j, node;
int zone_type; /* needs to be signed */
struct zone *z;
struct zonelist *zonelist;
- for (i = 0; i < MAX_NR_ZONES; i++) {
- zonelist = pgdat->node_zonelists + i;
- pos = 0;
- for (zone_type = i; zone_type >= 0; zone_type--) {
- for (j = 0; j < nr_nodes; j++) {
- node = node_order[j];
- z = &NODE_DATA(node)->node_zones[zone_type];
- if (populated_zone(z)) {
- zonelist->zones[pos++] = z;
- check_highest_zone(zone_type);
- }
+ zonelist = &pgdat->node_zonelists[0];
+ pos = 0;
+ for (zone_type = MAX_NR_ZONES - 1; zone_type >= 0; zone_type--) {
+ for (j = 0; j < nr_nodes; j++) {
+ node = node_order[j];
+ z = &NODE_DATA(node)->node_zones[zone_type];
+ if (populated_zone(z)) {
+ zoneref_set_zone(z,
+ &zonelist->_zonerefs[pos++]);
+ check_highest_zone(zone_type);
}
}
- zonelist->zones[pos] = NULL;
}
+ zonelist->_zonerefs[pos].zone = NULL;
+ zonelist->_zonerefs[pos].zone_idx = 0;
}
static int default_zonelist_order(void)
/* initialize zonelists */
for (i = 0; i < MAX_ZONELISTS; i++) {
zonelist = pgdat->node_zonelists + i;
- zonelist->zones[0] = NULL;
+ zonelist->_zonerefs[0].zone = NULL;
+ zonelist->_zonerefs[0].zone_idx = 0;
}
/* NUMA-aware ordering of nodes */
/* Construct the zonelist performance cache - see further mmzone.h */
static void build_zonelist_cache(pg_data_t *pgdat)
{
- int i;
-
- for (i = 0; i < MAX_NR_ZONES; i++) {
- struct zonelist *zonelist;
- struct zonelist_cache *zlc;
- struct zone **z;
+ struct zonelist *zonelist;
+ struct zonelist_cache *zlc;
+ struct zoneref *z;
- zonelist = pgdat->node_zonelists + i;
- zonelist->zlcache_ptr = zlc = &zonelist->zlcache;
- bitmap_zero(zlc->fullzones, MAX_ZONES_PER_ZONELIST);
- for (z = zonelist->zones; *z; z++)
- zlc->z_to_n[z - zonelist->zones] = zone_to_nid(*z);
- }
+ zonelist = &pgdat->node_zonelists[0];
+ zonelist->zlcache_ptr = zlc = &zonelist->zlcache;
+ bitmap_zero(zlc->fullzones, MAX_ZONES_PER_ZONELIST);
+ for (z = zonelist->_zonerefs; z->zone; z++)
+ zlc->z_to_n[z - zonelist->_zonerefs] = zonelist_node_idx(z);
}
static void build_zonelists(pg_data_t *pgdat)
{
int node, local_node;
- enum zone_type i,j;
+ enum zone_type j;
+ struct zonelist *zonelist;
local_node = pgdat->node_id;
- for (i = 0; i < MAX_NR_ZONES; i++) {
- struct zonelist *zonelist;
- zonelist = pgdat->node_zonelists + i;
+ zonelist = &pgdat->node_zonelists[0];
+ j = build_zonelists_node(pgdat, zonelist, 0, MAX_NR_ZONES - 1);
- j = build_zonelists_node(pgdat, zonelist, 0, i);
- /*
- * Now we build the zonelist so that it contains the zones
- * of all the other nodes.
- * We don't want to pressure a particular node, so when
- * building the zones for node N, we make sure that the
- * zones coming right after the local ones are those from
- * node N+1 (modulo N)
- */
- for (node = local_node + 1; node < MAX_NUMNODES; node++) {
- if (!node_online(node))
- continue;
- j = build_zonelists_node(NODE_DATA(node), zonelist, j, i);
- }
- for (node = 0; node < local_node; node++) {
- if (!node_online(node))
- continue;
- j = build_zonelists_node(NODE_DATA(node), zonelist, j, i);
- }
-
- zonelist->zones[j] = NULL;
+ /*
+ * Now we build the zonelist so that it contains the zones
+ * of all the other nodes.
+ * We don't want to pressure a particular node, so when
+ * building the zones for node N, we make sure that the
+ * zones coming right after the local ones are those from
+ * node N+1 (modulo N)
+ */
+ for (node = local_node + 1; node < MAX_NUMNODES; node++) {
+ if (!node_online(node))
+ continue;
+ j = build_zonelists_node(NODE_DATA(node), zonelist, j,
+ MAX_NR_ZONES - 1);
}
+ for (node = 0; node < local_node; node++) {
+ if (!node_online(node))
+ continue;
+ j = build_zonelists_node(NODE_DATA(node), zonelist, j,
+ MAX_NR_ZONES - 1);
+ }
+
+ zonelist->_zonerefs[j].zone = NULL;
+ zonelist->_zonerefs[j].zone_idx = 0;
}
/* non-NUMA variant of zonelist performance cache - just NULL zlcache_ptr */
static void build_zonelist_cache(pg_data_t *pgdat)
{
- int i;
-
- for (i = 0; i < MAX_NR_ZONES; i++)
- pgdat->node_zonelists[i].zlcache_ptr = NULL;
+ pgdat->node_zonelists[0].zlcache_ptr = NULL;
+ pgdat->node_zonelists[1].zlcache_ptr = NULL;
}
#endif /* CONFIG_NUMA */
__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 */
struct page *page;
unsigned long end_pfn = start_pfn + size;
unsigned long pfn;
+ struct zone *z;
+ z = &NODE_DATA(nid)->node_zones[zone];
for (pfn = start_pfn; pfn < end_pfn; pfn++) {
/*
* There can be holes in boot-time mem_map[]s
init_page_count(page);
reset_page_mapcount(page);
SetPageReserved(page);
-
/*
* Mark the block movable so that blocks are reserved for
* movable at startup. This will force kernel allocations
* kernel allocations are made. Later some blocks near
* the start are marked MIGRATE_RESERVE by
* setup_zone_migrate_reserve()
+ *
+ * bitmap is created for zone's valid pfn range. but memmap
+ * can be created for invalid pages (for alignment)
+ * check here not to call set_pageblock_migratetype() against
+ * pfn out of zone.
*/
- if ((pfn & (pageblock_nr_pages-1)))
+ if ((z->zone_start_pfn <= pfn)
+ && (pfn < z->zone_start_pfn + z->spanned_pages)
+ && !(pfn & (pageblock_nr_pages - 1)))
set_pageblock_migratetype(page, MIGRATE_MOVABLE);
INIT_LIST_HEAD(&page->lru);
}
}
-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))
alloc_size = zone->wait_table_hash_nr_entries
* sizeof(wait_queue_head_t);
- if (system_state == SYSTEM_BOOTING) {
+ if (!slab_is_available()) {
zone->wait_table = (wait_queue_head_t *)
alloc_bootmem_node(pgdat, alloc_size);
} else {
zone->zone_start_pfn = zone_start_pfn;
- 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)
{
#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)
{
}
#else /* CONFIG_HUGETLB_PAGE_SIZE_VARIABLE */
-/* Defined this way to avoid accidently referencing HUGETLB_PAGE_ORDER */
+/*
+ * When CONFIG_HUGETLB_PAGE_SIZE_VARIABLE is not set, set_pageblock_order()
+ * and pageblock_default_order() are unused as pageblock_order is set
+ * at compile-time. See include/linux/pageblock-flags.h for the values of
+ * pageblock_order based on the kernel config
+ */
+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 */
* - 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;
* is used by this zone for memmap. This affects the watermark
* and per-cpu initialisations
*/
- memmap_pages = (size * sizeof(struct page)) >> PAGE_SHIFT;
+ memmap_pages =
+ PAGE_ALIGN(size * sizeof(struct page)) >> PAGE_SHIFT;
if (realsize >= memmap_pages) {
realsize -= memmap_pages;
printk(KERN_DEBUG
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(HUGETLB_PAGE_ORDER);
+ set_pageblock_order(pageblock_default_order());
setup_usemap(pgdat, zone, size);
ret = init_currently_empty_zone(zone, zone_start_pfn,
size, MEMMAP_EARLY);
BUG_ON(ret);
+ memmap_init(size, nid, j, zone_start_pfn);
zone_start_pfn += size;
}
}
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;
else if (hashdist)
table = __vmalloc(size, GFP_ATOMIC, PAGE_KERNEL);
else {
- unsigned long order;
- for (order = 0; ((1UL << order) << PAGE_SHIFT) < size; order++)
- ;
+ 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
pfn = page_to_pfn(page);
bitmap = get_pageblock_bitmap(zone, pfn);
bitidx = pfn_to_bitidx(zone, pfn);
+ VM_BUG_ON(pfn < zone->zone_start_pfn);
+ VM_BUG_ON(pfn >= zone->zone_start_pfn + zone->spanned_pages);
for (; start_bitidx <= end_bitidx; start_bitidx++, value <<= 1)
if (flags & value)
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