#include <linux/delay.h>
#include <linux/kthread.h>
#include <linux/freezer.h>
+#include <linux/memcontrol.h>
+#include <linux/delayacct.h>
#include <asm/tlbflush.h>
#include <asm/div64.h>
int all_unreclaimable;
int order;
+
+ /* Which cgroup do we reclaim from */
+ struct mem_cgroup *mem_cgroup;
+
+ /* Pluggable isolate pages callback */
+ unsigned long (*isolate_pages)(unsigned long nr, struct list_head *dst,
+ unsigned long *scanned, int order, int mode,
+ struct zone *z, struct mem_cgroup *mem_cont,
+ int active);
};
#define lru_to_page(_head) (list_entry((_head)->prev, struct page, lru))
static LIST_HEAD(shrinker_list);
static DECLARE_RWSEM(shrinker_rwsem);
+#ifdef CONFIG_CGROUP_MEM_RES_CTLR
+#define scan_global_lru(sc) (!(sc)->mem_cgroup)
+#else
+#define scan_global_lru(sc) (1)
+#endif
+
/*
* Add a shrinker callback to be called from the vm
*/
* percentages of the lru and ageable caches. This should balance the seeks
* generated by these structures.
*
- * If the vm encounted mapped pages on the LRU it increase the pressure on
+ * If the vm encountered mapped pages on the LRU it increase the pressure on
* slab to avoid swapping.
*
* We do weird things to avoid (scanned*seeks*entries) overflowing 32 bits.
shrinker->nr += delta;
if (shrinker->nr < 0) {
printk(KERN_ERR "%s: nr=%ld\n",
- __FUNCTION__, shrinker->nr);
+ __func__, shrinker->nr);
shrinker->nr = max_pass;
}
unlock_page(page);
}
+/* Request for sync pageout. */
+enum pageout_io {
+ PAGEOUT_IO_ASYNC,
+ PAGEOUT_IO_SYNC,
+};
+
/* possible outcome of pageout() */
typedef enum {
/* failed to write page out, page is locked */
* pageout is called by shrink_page_list() for each dirty page.
* Calls ->writepage().
*/
-static pageout_t pageout(struct page *page, struct address_space *mapping)
+static pageout_t pageout(struct page *page, struct address_space *mapping,
+ enum pageout_io sync_writeback)
{
/*
* If the page is dirty, only perform writeback if that write
if (PagePrivate(page)) {
if (try_to_free_buffers(page)) {
ClearPageDirty(page);
- printk("%s: orphaned page\n", __FUNCTION__);
+ printk("%s: orphaned page\n", __func__);
return PAGE_CLEAN;
}
}
ClearPageReclaim(page);
return PAGE_ACTIVATE;
}
+
+ /*
+ * Wait on writeback if requested to. This happens when
+ * direct reclaiming a large contiguous area and the
+ * first attempt to free a range of pages fails.
+ */
+ if (PageWriteback(page) && sync_writeback == PAGEOUT_IO_SYNC)
+ wait_on_page_writeback(page);
+
if (!PageWriteback(page)) {
/* synchronous write or broken a_ops? */
ClearPageReclaim(page);
}
/*
- * Attempt to detach a locked page from its ->mapping. If it is dirty or if
- * someone else has a ref on the page, abort and return 0. If it was
- * successfully detached, return 1. Assumes the caller has a single ref on
- * this page.
+ * Same as remove_mapping, but if the page is removed from the mapping, it
+ * gets returned with a refcount of 0.
*/
-int remove_mapping(struct address_space *mapping, struct page *page)
+static int __remove_mapping(struct address_space *mapping, struct page *page)
{
BUG_ON(!PageLocked(page));
BUG_ON(mapping != page_mapping(page));
- write_lock_irq(&mapping->tree_lock);
+ spin_lock_irq(&mapping->tree_lock);
/*
* The non racy check for a busy page.
*
* Note that if SetPageDirty is always performed via set_page_dirty,
* and thus under tree_lock, then this ordering is not required.
*/
- if (unlikely(page_count(page) != 2))
+ if (!page_freeze_refs(page, 2))
goto cannot_free;
- smp_rmb();
- if (unlikely(PageDirty(page)))
+ /* note: atomic_cmpxchg in page_freeze_refs provides the smp_rmb */
+ if (unlikely(PageDirty(page))) {
+ page_unfreeze_refs(page, 2);
goto cannot_free;
+ }
if (PageSwapCache(page)) {
swp_entry_t swap = { .val = page_private(page) };
__delete_from_swap_cache(page);
- write_unlock_irq(&mapping->tree_lock);
+ spin_unlock_irq(&mapping->tree_lock);
swap_free(swap);
- __put_page(page); /* The pagecache ref */
- return 1;
+ } else {
+ __remove_from_page_cache(page);
+ spin_unlock_irq(&mapping->tree_lock);
}
- __remove_from_page_cache(page);
- write_unlock_irq(&mapping->tree_lock);
- __put_page(page);
return 1;
cannot_free:
- write_unlock_irq(&mapping->tree_lock);
+ spin_unlock_irq(&mapping->tree_lock);
+ return 0;
+}
+
+/*
+ * Attempt to detach a locked page from its ->mapping. If it is dirty or if
+ * someone else has a ref on the page, abort and return 0. If it was
+ * successfully detached, return 1. Assumes the caller has a single ref on
+ * this page.
+ */
+int remove_mapping(struct address_space *mapping, struct page *page)
+{
+ if (__remove_mapping(mapping, page)) {
+ /*
+ * Unfreezing the refcount with 1 rather than 2 effectively
+ * drops the pagecache ref for us without requiring another
+ * atomic operation.
+ */
+ page_unfreeze_refs(page, 1);
+ return 1;
+ }
return 0;
}
* shrink_page_list() returns the number of reclaimed pages
*/
static unsigned long shrink_page_list(struct list_head *page_list,
- struct scan_control *sc)
+ struct scan_control *sc,
+ enum pageout_io sync_writeback)
{
LIST_HEAD(ret_pages);
struct pagevec freed_pvec;
page = lru_to_page(page_list);
list_del(&page->lru);
- if (TestSetPageLocked(page))
+ if (!trylock_page(page))
goto keep;
VM_BUG_ON(PageActive(page));
if (page_mapped(page) || PageSwapCache(page))
sc->nr_scanned++;
- if (PageWriteback(page))
- goto keep_locked;
+ may_enter_fs = (sc->gfp_mask & __GFP_FS) ||
+ (PageSwapCache(page) && (sc->gfp_mask & __GFP_IO));
+
+ if (PageWriteback(page)) {
+ /*
+ * Synchronous reclaim is performed in two passes,
+ * first an asynchronous pass over the list to
+ * start parallel writeback, and a second synchronous
+ * pass to wait for the IO to complete. Wait here
+ * for any page for which writeback has already
+ * started.
+ */
+ if (sync_writeback == PAGEOUT_IO_SYNC && may_enter_fs)
+ wait_on_page_writeback(page);
+ else
+ goto keep_locked;
+ }
- referenced = page_referenced(page, 1);
+ referenced = page_referenced(page, 1, sc->mem_cgroup);
/* In active use or really unfreeable? Activate it. */
if (sc->order <= PAGE_ALLOC_COSTLY_ORDER &&
referenced && page_mapping_inuse(page))
#endif /* CONFIG_SWAP */
mapping = page_mapping(page);
- may_enter_fs = (sc->gfp_mask & __GFP_FS) ||
- (PageSwapCache(page) && (sc->gfp_mask & __GFP_IO));
/*
* The page is mapped into the page tables of one or more
goto keep_locked;
/* Page is dirty, try to write it out here */
- switch(pageout(page, mapping)) {
+ switch (pageout(page, mapping, sync_writeback)) {
case PAGE_KEEP:
goto keep_locked;
case PAGE_ACTIVATE:
* A synchronous write - probably a ramdisk. Go
* ahead and try to reclaim the page.
*/
- if (TestSetPageLocked(page))
+ if (!trylock_page(page))
goto keep;
if (PageDirty(page) || PageWriteback(page))
goto keep_locked;
if (PagePrivate(page)) {
if (!try_to_release_page(page, sc->gfp_mask))
goto activate_locked;
- if (!mapping && page_count(page) == 1)
- goto free_it;
+ if (!mapping && page_count(page) == 1) {
+ unlock_page(page);
+ if (put_page_testzero(page))
+ goto free_it;
+ else {
+ /*
+ * rare race with speculative reference.
+ * the speculative reference will free
+ * this page shortly, so we may
+ * increment nr_reclaimed here (and
+ * leave it off the LRU).
+ */
+ nr_reclaimed++;
+ continue;
+ }
+ }
}
- if (!mapping || !remove_mapping(mapping, page))
+ if (!mapping || !__remove_mapping(mapping, page))
goto keep_locked;
-free_it:
unlock_page(page);
+free_it:
nr_reclaimed++;
- if (!pagevec_add(&freed_pvec, page))
- __pagevec_release_nonlru(&freed_pvec);
+ if (!pagevec_add(&freed_pvec, page)) {
+ __pagevec_free(&freed_pvec);
+ pagevec_reinit(&freed_pvec);
+ }
continue;
activate_locked:
}
list_splice(&ret_pages, page_list);
if (pagevec_count(&freed_pvec))
- __pagevec_release_nonlru(&freed_pvec);
+ __pagevec_free(&freed_pvec);
count_vm_events(PGACTIVATE, pgactivate);
return nr_reclaimed;
}
*
* returns 0 on success, -ve errno on failure.
*/
-static int __isolate_lru_page(struct page *page, int mode)
+int __isolate_lru_page(struct page *page, int mode)
{
int ret = -EINVAL;
return nr_taken;
}
+static unsigned long isolate_pages_global(unsigned long nr,
+ struct list_head *dst,
+ unsigned long *scanned, int order,
+ int mode, struct zone *z,
+ struct mem_cgroup *mem_cont,
+ int active)
+{
+ if (active)
+ return isolate_lru_pages(nr, &z->active_list, dst,
+ scanned, order, mode);
+ else
+ return isolate_lru_pages(nr, &z->inactive_list, dst,
+ scanned, order, mode);
+}
+
/*
* clear_active_flags() is a helper for shrink_active_list(), clearing
* any active bits from the pages in the list.
unsigned long nr_freed;
unsigned long nr_active;
- nr_taken = isolate_lru_pages(sc->swap_cluster_max,
- &zone->inactive_list,
+ nr_taken = sc->isolate_pages(sc->swap_cluster_max,
&page_list, &nr_scan, sc->order,
(sc->order > PAGE_ALLOC_COSTLY_ORDER)?
- ISOLATE_BOTH : ISOLATE_INACTIVE);
+ ISOLATE_BOTH : ISOLATE_INACTIVE,
+ zone, sc->mem_cgroup, 0);
nr_active = clear_active_flags(&page_list);
+ __count_vm_events(PGDEACTIVATE, nr_active);
__mod_zone_page_state(zone, NR_ACTIVE, -nr_active);
__mod_zone_page_state(zone, NR_INACTIVE,
-(nr_taken - nr_active));
- zone->pages_scanned += nr_scan;
+ if (scan_global_lru(sc))
+ zone->pages_scanned += nr_scan;
spin_unlock_irq(&zone->lru_lock);
nr_scanned += nr_scan;
- nr_freed = shrink_page_list(&page_list, sc);
+ nr_freed = shrink_page_list(&page_list, sc, PAGEOUT_IO_ASYNC);
+
+ /*
+ * If we are direct reclaiming for contiguous pages and we do
+ * not reclaim everything in the list, try again and wait
+ * for IO to complete. This will stall high-order allocations
+ * but that should be acceptable to the caller
+ */
+ if (nr_freed < nr_taken && !current_is_kswapd() &&
+ sc->order > PAGE_ALLOC_COSTLY_ORDER) {
+ congestion_wait(WRITE, HZ/10);
+
+ /*
+ * The attempt at page out may have made some
+ * of the pages active, mark them inactive again.
+ */
+ nr_active = clear_active_flags(&page_list);
+ count_vm_events(PGDEACTIVATE, nr_active);
+
+ nr_freed += shrink_page_list(&page_list, sc,
+ PAGEOUT_IO_SYNC);
+ }
+
nr_reclaimed += nr_freed;
local_irq_disable();
if (current_is_kswapd()) {
__count_zone_vm_events(PGSCAN_KSWAPD, zone, nr_scan);
__count_vm_events(KSWAPD_STEAL, nr_freed);
- } else
+ } else if (scan_global_lru(sc))
__count_zone_vm_events(PGSCAN_DIRECT, zone, nr_scan);
+
__count_zone_vm_events(PGSTEAL, zone, nr_freed);
if (nr_taken == 0)
}
/*
+ * Determine we should try to reclaim mapped pages.
+ * This is called only when sc->mem_cgroup is NULL.
+ */
+static int calc_reclaim_mapped(struct scan_control *sc, struct zone *zone,
+ int priority)
+{
+ long mapped_ratio;
+ long distress;
+ long swap_tendency;
+ long imbalance;
+ int reclaim_mapped = 0;
+ int prev_priority;
+
+ if (scan_global_lru(sc) && zone_is_near_oom(zone))
+ return 1;
+ /*
+ * `distress' is a measure of how much trouble we're having
+ * reclaiming pages. 0 -> no problems. 100 -> great trouble.
+ */
+ if (scan_global_lru(sc))
+ prev_priority = zone->prev_priority;
+ else
+ prev_priority = mem_cgroup_get_reclaim_priority(sc->mem_cgroup);
+
+ distress = 100 >> min(prev_priority, priority);
+
+ /*
+ * The point of this algorithm is to decide when to start
+ * reclaiming mapped memory instead of just pagecache. Work out
+ * how much memory
+ * is mapped.
+ */
+ if (scan_global_lru(sc))
+ mapped_ratio = ((global_page_state(NR_FILE_MAPPED) +
+ global_page_state(NR_ANON_PAGES)) * 100) /
+ vm_total_pages;
+ else
+ mapped_ratio = mem_cgroup_calc_mapped_ratio(sc->mem_cgroup);
+
+ /*
+ * Now decide how much we really want to unmap some pages. The
+ * mapped ratio is downgraded - just because there's a lot of
+ * mapped memory doesn't necessarily mean that page reclaim
+ * isn't succeeding.
+ *
+ * The distress ratio is important - we don't want to start
+ * going oom.
+ *
+ * A 100% value of vm_swappiness overrides this algorithm
+ * altogether.
+ */
+ swap_tendency = mapped_ratio / 2 + distress + sc->swappiness;
+
+ /*
+ * If there's huge imbalance between active and inactive
+ * (think active 100 times larger than inactive) we should
+ * become more permissive, or the system will take too much
+ * cpu before it start swapping during memory pressure.
+ * Distress is about avoiding early-oom, this is about
+ * making swappiness graceful despite setting it to low
+ * values.
+ *
+ * Avoid div by zero with nr_inactive+1, and max resulting
+ * value is vm_total_pages.
+ */
+ if (scan_global_lru(sc)) {
+ imbalance = zone_page_state(zone, NR_ACTIVE);
+ imbalance /= zone_page_state(zone, NR_INACTIVE) + 1;
+ } else
+ imbalance = mem_cgroup_reclaim_imbalance(sc->mem_cgroup);
+
+ /*
+ * Reduce the effect of imbalance if swappiness is low,
+ * this means for a swappiness very low, the imbalance
+ * must be much higher than 100 for this logic to make
+ * the difference.
+ *
+ * Max temporary value is vm_total_pages*100.
+ */
+ imbalance *= (vm_swappiness + 1);
+ imbalance /= 100;
+
+ /*
+ * If not much of the ram is mapped, makes the imbalance
+ * less relevant, it's high priority we refill the inactive
+ * list with mapped pages only in presence of high ratio of
+ * mapped pages.
+ *
+ * Max temporary value is vm_total_pages*100.
+ */
+ imbalance *= mapped_ratio;
+ imbalance /= 100;
+
+ /* apply imbalance feedback to swap_tendency */
+ swap_tendency += imbalance;
+
+ /*
+ * Now use this metric to decide whether to start moving mapped
+ * memory onto the inactive list.
+ */
+ if (swap_tendency >= 100)
+ reclaim_mapped = 1;
+
+ return reclaim_mapped;
+}
+
+/*
* This moves pages from the active list to the inactive list.
*
* We move them the other way if the page is referenced by one or more
* The downside is that we have to touch page->_count against each page.
* But we had to alter page->flags anyway.
*/
+
+
static void shrink_active_list(unsigned long nr_pages, struct zone *zone,
struct scan_control *sc, int priority)
{
struct pagevec pvec;
int reclaim_mapped = 0;
- if (sc->may_swap) {
- long mapped_ratio;
- long distress;
- long swap_tendency;
-
- if (zone_is_near_oom(zone))
- goto force_reclaim_mapped;
-
- /*
- * `distress' is a measure of how much trouble we're having
- * reclaiming pages. 0 -> no problems. 100 -> great trouble.
- */
- distress = 100 >> min(zone->prev_priority, priority);
-
- /*
- * The point of this algorithm is to decide when to start
- * reclaiming mapped memory instead of just pagecache. Work out
- * how much memory
- * is mapped.
- */
- mapped_ratio = ((global_page_state(NR_FILE_MAPPED) +
- global_page_state(NR_ANON_PAGES)) * 100) /
- vm_total_pages;
-
- /*
- * Now decide how much we really want to unmap some pages. The
- * mapped ratio is downgraded - just because there's a lot of
- * mapped memory doesn't necessarily mean that page reclaim
- * isn't succeeding.
- *
- * The distress ratio is important - we don't want to start
- * going oom.
- *
- * A 100% value of vm_swappiness overrides this algorithm
- * altogether.
- */
- swap_tendency = mapped_ratio / 2 + distress + sc->swappiness;
-
- /*
- * Now use this metric to decide whether to start moving mapped
- * memory onto the inactive list.
- */
- if (swap_tendency >= 100)
-force_reclaim_mapped:
- reclaim_mapped = 1;
- }
+ if (sc->may_swap)
+ reclaim_mapped = calc_reclaim_mapped(sc, zone, priority);
lru_add_drain();
spin_lock_irq(&zone->lru_lock);
- pgmoved = isolate_lru_pages(nr_pages, &zone->active_list,
- &l_hold, &pgscanned, sc->order, ISOLATE_ACTIVE);
- zone->pages_scanned += pgscanned;
+ pgmoved = sc->isolate_pages(nr_pages, &l_hold, &pgscanned, sc->order,
+ ISOLATE_ACTIVE, zone,
+ sc->mem_cgroup, 1);
+ /*
+ * zone->pages_scanned is used for detect zone's oom
+ * mem_cgroup remembers nr_scan by itself.
+ */
+ if (scan_global_lru(sc))
+ zone->pages_scanned += pgscanned;
+
__mod_zone_page_state(zone, NR_ACTIVE, -pgmoved);
spin_unlock_irq(&zone->lru_lock);
if (page_mapped(page)) {
if (!reclaim_mapped ||
(total_swap_pages == 0 && PageAnon(page)) ||
- page_referenced(page, 0)) {
+ page_referenced(page, 0, sc->mem_cgroup)) {
list_add(&page->lru, &l_active);
continue;
}
ClearPageActive(page);
list_move(&page->lru, &zone->inactive_list);
+ mem_cgroup_move_lists(page, false);
pgmoved++;
if (!pagevec_add(&pvec, page)) {
__mod_zone_page_state(zone, NR_INACTIVE, pgmoved);
VM_BUG_ON(PageLRU(page));
SetPageLRU(page);
VM_BUG_ON(!PageActive(page));
+
list_move(&page->lru, &zone->active_list);
+ mem_cgroup_move_lists(page, true);
pgmoved++;
if (!pagevec_add(&pvec, page)) {
__mod_zone_page_state(zone, NR_ACTIVE, pgmoved);
unsigned long nr_to_scan;
unsigned long nr_reclaimed = 0;
- atomic_inc(&zone->reclaim_in_progress);
+ if (scan_global_lru(sc)) {
+ /*
+ * Add one to nr_to_scan just to make sure that the kernel
+ * will slowly sift through the active list.
+ */
+ zone->nr_scan_active +=
+ (zone_page_state(zone, NR_ACTIVE) >> priority) + 1;
+ nr_active = zone->nr_scan_active;
+ zone->nr_scan_inactive +=
+ (zone_page_state(zone, NR_INACTIVE) >> priority) + 1;
+ nr_inactive = zone->nr_scan_inactive;
+ if (nr_inactive >= sc->swap_cluster_max)
+ zone->nr_scan_inactive = 0;
+ else
+ nr_inactive = 0;
+
+ if (nr_active >= sc->swap_cluster_max)
+ zone->nr_scan_active = 0;
+ else
+ nr_active = 0;
+ } else {
+ /*
+ * This reclaim occurs not because zone memory shortage but
+ * because memory controller hits its limit.
+ * Then, don't modify zone reclaim related data.
+ */
+ nr_active = mem_cgroup_calc_reclaim_active(sc->mem_cgroup,
+ zone, priority);
- /*
- * Add one to `nr_to_scan' just to make sure that the kernel will
- * slowly sift through the active list.
- */
- zone->nr_scan_active +=
- (zone_page_state(zone, NR_ACTIVE) >> priority) + 1;
- nr_active = zone->nr_scan_active;
- if (nr_active >= sc->swap_cluster_max)
- zone->nr_scan_active = 0;
- else
- nr_active = 0;
+ nr_inactive = mem_cgroup_calc_reclaim_inactive(sc->mem_cgroup,
+ zone, priority);
+ }
- zone->nr_scan_inactive +=
- (zone_page_state(zone, NR_INACTIVE) >> priority) + 1;
- nr_inactive = zone->nr_scan_inactive;
- if (nr_inactive >= sc->swap_cluster_max)
- zone->nr_scan_inactive = 0;
- else
- nr_inactive = 0;
while (nr_active || nr_inactive) {
if (nr_active) {
}
throttle_vm_writeout(sc->gfp_mask);
-
- atomic_dec(&zone->reclaim_in_progress);
return nr_reclaimed;
}
* If a zone is deemed to be full of pinned pages then just give it a light
* scan then give up on it.
*/
-static unsigned long shrink_zones(int priority, struct zone **zones,
+static unsigned long shrink_zones(int priority, struct zonelist *zonelist,
struct scan_control *sc)
{
+ enum zone_type high_zoneidx = gfp_zone(sc->gfp_mask);
unsigned long nr_reclaimed = 0;
- int i;
+ struct zoneref *z;
+ struct zone *zone;
sc->all_unreclaimable = 1;
- for (i = 0; zones[i] != NULL; i++) {
- struct zone *zone = zones[i];
-
+ for_each_zone_zonelist(zone, z, zonelist, high_zoneidx) {
if (!populated_zone(zone))
continue;
+ /*
+ * Take care memory controller reclaiming has small influence
+ * to global LRU.
+ */
+ if (scan_global_lru(sc)) {
+ if (!cpuset_zone_allowed_hardwall(zone, GFP_KERNEL))
+ continue;
+ note_zone_scanning_priority(zone, priority);
- if (!cpuset_zone_allowed_hardwall(zone, GFP_KERNEL))
- continue;
-
- note_zone_scanning_priority(zone, priority);
-
- if (zone->all_unreclaimable && priority != DEF_PRIORITY)
- continue; /* Let kswapd poll it */
-
- sc->all_unreclaimable = 0;
+ if (zone_is_all_unreclaimable(zone) &&
+ priority != DEF_PRIORITY)
+ continue; /* Let kswapd poll it */
+ sc->all_unreclaimable = 0;
+ } else {
+ /*
+ * Ignore cpuset limitation here. We just want to reduce
+ * # of used pages by us regardless of memory shortage.
+ */
+ sc->all_unreclaimable = 0;
+ mem_cgroup_note_reclaim_priority(sc->mem_cgroup,
+ priority);
+ }
nr_reclaimed += shrink_zone(priority, zone, sc);
}
+
return nr_reclaimed;
}
* hope that some of these pages can be written. But if the allocating task
* holds filesystem locks which prevent writeout this might not work, and the
* allocation attempt will fail.
+ *
+ * returns: 0, if no pages reclaimed
+ * else, the number of pages reclaimed
*/
-unsigned long try_to_free_pages(struct zone **zones, int order, gfp_t gfp_mask)
+static unsigned long do_try_to_free_pages(struct zonelist *zonelist,
+ struct scan_control *sc)
{
int priority;
- int ret = 0;
+ unsigned long ret = 0;
unsigned long total_scanned = 0;
unsigned long nr_reclaimed = 0;
struct reclaim_state *reclaim_state = current->reclaim_state;
unsigned long lru_pages = 0;
- int i;
- struct scan_control sc = {
- .gfp_mask = gfp_mask,
- .may_writepage = !laptop_mode,
- .swap_cluster_max = SWAP_CLUSTER_MAX,
- .may_swap = 1,
- .swappiness = vm_swappiness,
- .order = order,
- };
+ struct zoneref *z;
+ struct zone *zone;
+ enum zone_type high_zoneidx = gfp_zone(sc->gfp_mask);
- count_vm_event(ALLOCSTALL);
+ delayacct_freepages_start();
- for (i = 0; zones[i] != NULL; i++) {
- struct zone *zone = zones[i];
+ if (scan_global_lru(sc))
+ count_vm_event(ALLOCSTALL);
+ /*
+ * mem_cgroup will not do shrink_slab.
+ */
+ if (scan_global_lru(sc)) {
+ for_each_zone_zonelist(zone, z, zonelist, high_zoneidx) {
- if (!cpuset_zone_allowed_hardwall(zone, GFP_KERNEL))
- continue;
+ if (!cpuset_zone_allowed_hardwall(zone, GFP_KERNEL))
+ continue;
- lru_pages += zone_page_state(zone, NR_ACTIVE)
- + zone_page_state(zone, NR_INACTIVE);
+ lru_pages += zone_page_state(zone, NR_ACTIVE)
+ + zone_page_state(zone, NR_INACTIVE);
+ }
}
for (priority = DEF_PRIORITY; priority >= 0; priority--) {
- sc.nr_scanned = 0;
+ sc->nr_scanned = 0;
if (!priority)
disable_swap_token();
- nr_reclaimed += shrink_zones(priority, zones, &sc);
- shrink_slab(sc.nr_scanned, gfp_mask, lru_pages);
- if (reclaim_state) {
- nr_reclaimed += reclaim_state->reclaimed_slab;
- reclaim_state->reclaimed_slab = 0;
+ nr_reclaimed += shrink_zones(priority, zonelist, sc);
+ /*
+ * Don't shrink slabs when reclaiming memory from
+ * over limit cgroups
+ */
+ if (scan_global_lru(sc)) {
+ shrink_slab(sc->nr_scanned, sc->gfp_mask, lru_pages);
+ if (reclaim_state) {
+ nr_reclaimed += reclaim_state->reclaimed_slab;
+ reclaim_state->reclaimed_slab = 0;
+ }
}
- total_scanned += sc.nr_scanned;
- if (nr_reclaimed >= sc.swap_cluster_max) {
- ret = 1;
+ total_scanned += sc->nr_scanned;
+ if (nr_reclaimed >= sc->swap_cluster_max) {
+ ret = nr_reclaimed;
goto out;
}
* that's undesirable in laptop mode, where we *want* lumpy
* writeout. So in laptop mode, write out the whole world.
*/
- if (total_scanned > sc.swap_cluster_max +
- sc.swap_cluster_max / 2) {
+ if (total_scanned > sc->swap_cluster_max +
+ sc->swap_cluster_max / 2) {
wakeup_pdflush(laptop_mode ? 0 : total_scanned);
- sc.may_writepage = 1;
+ sc->may_writepage = 1;
}
/* Take a nap, wait for some writeback to complete */
- if (sc.nr_scanned && priority < DEF_PRIORITY - 2)
+ if (sc->nr_scanned && priority < DEF_PRIORITY - 2)
congestion_wait(WRITE, HZ/10);
}
- /* top priority shrink_caches still had more to do? don't OOM, then */
- if (!sc.all_unreclaimable)
- ret = 1;
+ /* top priority shrink_zones still had more to do? don't OOM, then */
+ if (!sc->all_unreclaimable && scan_global_lru(sc))
+ ret = nr_reclaimed;
out:
/*
* Now that we've scanned all the zones at this priority level, note
*/
if (priority < 0)
priority = 0;
- for (i = 0; zones[i] != 0; i++) {
- struct zone *zone = zones[i];
- if (!cpuset_zone_allowed_hardwall(zone, GFP_KERNEL))
- continue;
+ if (scan_global_lru(sc)) {
+ for_each_zone_zonelist(zone, z, zonelist, high_zoneidx) {
+
+ if (!cpuset_zone_allowed_hardwall(zone, GFP_KERNEL))
+ continue;
+
+ zone->prev_priority = priority;
+ }
+ } else
+ mem_cgroup_record_reclaim_priority(sc->mem_cgroup, priority);
+
+ delayacct_freepages_end();
- zone->prev_priority = priority;
- }
return ret;
}
+unsigned long try_to_free_pages(struct zonelist *zonelist, int order,
+ gfp_t gfp_mask)
+{
+ struct scan_control sc = {
+ .gfp_mask = gfp_mask,
+ .may_writepage = !laptop_mode,
+ .swap_cluster_max = SWAP_CLUSTER_MAX,
+ .may_swap = 1,
+ .swappiness = vm_swappiness,
+ .order = order,
+ .mem_cgroup = NULL,
+ .isolate_pages = isolate_pages_global,
+ };
+
+ return do_try_to_free_pages(zonelist, &sc);
+}
+
+#ifdef CONFIG_CGROUP_MEM_RES_CTLR
+
+unsigned long try_to_free_mem_cgroup_pages(struct mem_cgroup *mem_cont,
+ gfp_t gfp_mask)
+{
+ struct scan_control sc = {
+ .may_writepage = !laptop_mode,
+ .may_swap = 1,
+ .swap_cluster_max = SWAP_CLUSTER_MAX,
+ .swappiness = vm_swappiness,
+ .order = 0,
+ .mem_cgroup = mem_cont,
+ .isolate_pages = mem_cgroup_isolate_pages,
+ };
+ struct zonelist *zonelist;
+
+ sc.gfp_mask = (gfp_mask & GFP_RECLAIM_MASK) |
+ (GFP_HIGHUSER_MOVABLE & ~GFP_RECLAIM_MASK);
+ zonelist = NODE_DATA(numa_node_id())->node_zonelists;
+ return do_try_to_free_pages(zonelist, &sc);
+}
+#endif
+
/*
* For kswapd, balance_pgdat() will work across all this node's zones until
* they are all at pages_high.
.swap_cluster_max = SWAP_CLUSTER_MAX,
.swappiness = vm_swappiness,
.order = order,
+ .mem_cgroup = NULL,
+ .isolate_pages = isolate_pages_global,
};
/*
* temp_priority is used to remember the scanning priority at which
if (!populated_zone(zone))
continue;
- if (zone->all_unreclaimable && priority != DEF_PRIORITY)
+ if (zone_is_all_unreclaimable(zone) &&
+ priority != DEF_PRIORITY)
continue;
if (!zone_watermark_ok(zone, order, zone->pages_high,
if (!populated_zone(zone))
continue;
- if (zone->all_unreclaimable && priority != DEF_PRIORITY)
+ if (zone_is_all_unreclaimable(zone) &&
+ priority != DEF_PRIORITY)
continue;
if (!zone_watermark_ok(zone, order, zone->pages_high,
temp_priority[i] = priority;
sc.nr_scanned = 0;
note_zone_scanning_priority(zone, priority);
- nr_reclaimed += shrink_zone(priority, zone, &sc);
+ /*
+ * We put equal pressure on every zone, unless one
+ * zone has way too many pages free already.
+ */
+ if (!zone_watermark_ok(zone, order, 8*zone->pages_high,
+ end_zone, 0))
+ nr_reclaimed += shrink_zone(priority, zone, &sc);
reclaim_state->reclaimed_slab = 0;
nr_slab = shrink_slab(sc.nr_scanned, GFP_KERNEL,
lru_pages);
nr_reclaimed += reclaim_state->reclaimed_slab;
total_scanned += sc.nr_scanned;
- if (zone->all_unreclaimable)
+ if (zone_is_all_unreclaimable(zone))
continue;
if (nr_slab == 0 && zone->pages_scanned >=
(zone_page_state(zone, NR_ACTIVE)
+ zone_page_state(zone, NR_INACTIVE)) * 6)
- zone->all_unreclaimable = 1;
+ zone_set_flag(zone,
+ ZONE_ALL_UNRECLAIMABLE);
/*
* If we've done a decent amount of scanning and
* the reclaim ratio is low, start doing writepage
struct reclaim_state reclaim_state = {
.reclaimed_slab = 0,
};
- cpumask_t cpumask;
+ node_to_cpumask_ptr(cpumask, pgdat->node_id);
- cpumask = node_to_cpumask(pgdat->node_id);
- if (!cpus_empty(cpumask))
- set_cpus_allowed(tsk, cpumask);
+ if (!cpus_empty(*cpumask))
+ set_cpus_allowed_ptr(tsk, cpumask);
current->reclaim_state = &reclaim_state;
/*
* trying to free the first piece of memory in the first place).
*/
tsk->flags |= PF_MEMALLOC | PF_SWAPWRITE | PF_KSWAPD;
+ set_freezable();
order = 0;
for ( ; ; ) {
if (!populated_zone(zone))
continue;
- if (zone->all_unreclaimable && prio != DEF_PRIORITY)
+ if (zone_is_all_unreclaimable(zone) && prio != DEF_PRIORITY)
continue;
/* For pass = 0 we don't shrink the active list */
.swap_cluster_max = nr_pages,
.may_writepage = 1,
.swappiness = vm_swappiness,
+ .isolate_pages = isolate_pages_global,
};
current->reclaim_state = &reclaim_state;
static int __devinit cpu_callback(struct notifier_block *nfb,
unsigned long action, void *hcpu)
{
- pg_data_t *pgdat;
- cpumask_t mask;
+ int nid;
if (action == CPU_ONLINE || action == CPU_ONLINE_FROZEN) {
- for_each_online_pgdat(pgdat) {
- mask = node_to_cpumask(pgdat->node_id);
- if (any_online_cpu(mask) != NR_CPUS)
+ for_each_node_state(nid, N_HIGH_MEMORY) {
+ pg_data_t *pgdat = NODE_DATA(nid);
+ node_to_cpumask_ptr(mask, pgdat->node_id);
+
+ if (any_online_cpu(*mask) < nr_cpu_ids)
/* One of our CPUs online: restore mask */
- set_cpus_allowed(pgdat->kswapd, mask);
+ set_cpus_allowed_ptr(pgdat->kswapd, mask);
}
}
return NOTIFY_OK;
int nid;
swap_setup();
- for_each_online_node(nid)
+ for_each_node_state(nid, N_HIGH_MEMORY)
kswapd_run(nid);
hotcpu_notifier(cpu_callback, 0);
return 0;
int zone_reclaim_mode __read_mostly;
#define RECLAIM_OFF 0
-#define RECLAIM_ZONE (1<<0) /* Run shrink_cache on the zone */
+#define RECLAIM_ZONE (1<<0) /* Run shrink_inactive_list on the zone */
#define RECLAIM_WRITE (1<<1) /* Writeout pages during reclaim */
#define RECLAIM_SWAP (1<<2) /* Swap pages out during reclaim */
SWAP_CLUSTER_MAX),
.gfp_mask = gfp_mask,
.swappiness = vm_swappiness,
+ .isolate_pages = isolate_pages_global,
};
unsigned long slab_reclaimable;
int zone_reclaim(struct zone *zone, gfp_t gfp_mask, unsigned int order)
{
- cpumask_t mask;
int node_id;
+ int ret;
/*
* Zone reclaim reclaims unmapped file backed pages and
<= zone->min_slab_pages)
return 0;
+ if (zone_is_all_unreclaimable(zone))
+ return 0;
+
/*
- * Avoid concurrent zone reclaims, do not reclaim in a zone that does
- * not have reclaimable pages and if we should not delay the allocation
- * then do not scan.
+ * Do not scan if the allocation should not be delayed.
*/
- if (!(gfp_mask & __GFP_WAIT) ||
- zone->all_unreclaimable ||
- atomic_read(&zone->reclaim_in_progress) > 0 ||
- (current->flags & PF_MEMALLOC))
+ if (!(gfp_mask & __GFP_WAIT) || (current->flags & PF_MEMALLOC))
return 0;
/*
* as wide as possible.
*/
node_id = zone_to_nid(zone);
- mask = node_to_cpumask(node_id);
- if (!cpus_empty(mask) && node_id != numa_node_id())
+ if (node_state(node_id, N_CPU) && node_id != numa_node_id())
return 0;
- return __zone_reclaim(zone, gfp_mask, order);
+
+ if (zone_test_and_set_flag(zone, ZONE_RECLAIM_LOCKED))
+ return 0;
+ ret = __zone_reclaim(zone, gfp_mask, order);
+ zone_clear_flag(zone, ZONE_RECLAIM_LOCKED);
+
+ return ret;
}
#endif
git://ftp.safe.ca / safe / jmp / linux-2.6 / blobdiff