#include <linux/pagemap.h>
#include <linux/init.h>
#include <linux/highmem.h>
+#include <linux/vmstat.h>
#include <linux/file.h>
#include <linux/writeback.h>
#include <linux/blkdev.h>
#include <linux/rwsem.h>
#include <linux/delay.h>
#include <linux/kthread.h>
+#include <linux/freezer.h>
#include <asm/tlbflush.h>
#include <asm/div64.h>
int swappiness;
int all_unreclaimable;
-};
-/*
- * The list of shrinker callbacks used by to apply pressure to
- * ageable caches.
- */
-struct shrinker {
- shrinker_t shrinker;
- struct list_head list;
- int seeks; /* seeks to recreate an obj */
- long nr; /* objs pending delete */
+ int order;
};
#define lru_to_page(_head) (list_entry((_head)->prev, struct page, lru))
/*
* Add a shrinker callback to be called from the vm
*/
-struct shrinker *set_shrinker(int seeks, shrinker_t theshrinker)
+void register_shrinker(struct shrinker *shrinker)
{
- struct shrinker *shrinker;
-
- shrinker = kmalloc(sizeof(*shrinker), GFP_KERNEL);
- if (shrinker) {
- shrinker->shrinker = theshrinker;
- shrinker->seeks = seeks;
- shrinker->nr = 0;
- down_write(&shrinker_rwsem);
- list_add_tail(&shrinker->list, &shrinker_list);
- up_write(&shrinker_rwsem);
- }
- return shrinker;
+ shrinker->nr = 0;
+ down_write(&shrinker_rwsem);
+ list_add_tail(&shrinker->list, &shrinker_list);
+ up_write(&shrinker_rwsem);
}
-EXPORT_SYMBOL(set_shrinker);
+EXPORT_SYMBOL(register_shrinker);
/*
* Remove one
*/
-void remove_shrinker(struct shrinker *shrinker)
+void unregister_shrinker(struct shrinker *shrinker)
{
down_write(&shrinker_rwsem);
list_del(&shrinker->list);
up_write(&shrinker_rwsem);
- kfree(shrinker);
}
-EXPORT_SYMBOL(remove_shrinker);
+EXPORT_SYMBOL(unregister_shrinker);
#define SHRINK_BATCH 128
/*
* 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.
list_for_each_entry(shrinker, &shrinker_list, list) {
unsigned long long delta;
unsigned long total_scan;
- unsigned long max_pass = (*shrinker->shrinker)(0, gfp_mask);
+ unsigned long max_pass = (*shrinker->shrink)(0, gfp_mask);
delta = (4 * scanned) / shrinker->seeks;
delta *= max_pass;
int shrink_ret;
int nr_before;
- nr_before = (*shrinker->shrinker)(0, gfp_mask);
- shrink_ret = (*shrinker->shrinker)(this_scan, gfp_mask);
+ nr_before = (*shrinker->shrink)(0, gfp_mask);
+ shrink_ret = (*shrinker->shrink)(this_scan, gfp_mask);
if (shrink_ret == -1)
break;
if (shrink_ret < nr_before)
struct page *page, int error)
{
lock_page(page);
- if (page_mapping(page) == mapping) {
- if (error == -ENOSPC)
- set_bit(AS_ENOSPC, &mapping->flags);
- else
- set_bit(AS_EIO, &mapping->flags);
- }
+ if (page_mapping(page) == mapping)
+ mapping_set_error(mapping, error);
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
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);
}
-
+ inc_zone_page_state(page, NR_VMSCAN_WRITE);
return PAGE_SUCCESS;
}
return PAGE_CLEAN;
}
+/*
+ * 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)
{
BUG_ON(!PageLocked(page));
BUG_ON(mapping != page_mapping(page));
write_lock_irq(&mapping->tree_lock);
-
/*
- * The non-racy check for busy page. It is critical to check
- * PageDirty _after_ making sure that the page is freeable and
- * not in use by anybody. (pagecache + us == 2)
+ * The non racy check for a busy page.
+ *
+ * Must be careful with the order of the tests. When someone has
+ * a ref to the page, it may be possible that they dirty it then
+ * drop the reference. So if PageDirty is tested before page_count
+ * here, then the following race may occur:
+ *
+ * get_user_pages(&page);
+ * [user mapping goes away]
+ * write_to(page);
+ * !PageDirty(page) [good]
+ * SetPageDirty(page);
+ * put_page(page);
+ * !page_count(page) [good, discard it]
+ *
+ * [oops, our write_to data is lost]
+ *
+ * Reversing the order of the tests ensures such a situation cannot
+ * escape unnoticed. The smp_rmb is needed to ensure the page->flags
+ * load is not satisfied before that of page->_count.
+ *
+ * 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))
goto cannot_free;
* 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;
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);
/* In active use or really unfreeable? Activate it. */
- if (referenced && page_mapping_inuse(page))
+ if (sc->order <= PAGE_ALLOC_COSTLY_ORDER &&
+ referenced && page_mapping_inuse(page))
goto activate_locked;
#ifdef CONFIG_SWAP
#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
}
if (PageDirty(page)) {
- if (referenced)
+ if (sc->order <= PAGE_ALLOC_COSTLY_ORDER && referenced)
goto keep_locked;
if (!may_enter_fs)
goto keep_locked;
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:
return nr_reclaimed;
}
+/* LRU Isolation modes. */
+#define ISOLATE_INACTIVE 0 /* Isolate inactive pages. */
+#define ISOLATE_ACTIVE 1 /* Isolate active pages. */
+#define ISOLATE_BOTH 2 /* Isolate both active and inactive pages. */
+
+/*
+ * Attempt to remove the specified page from its LRU. Only take this page
+ * if it is of the appropriate PageActive status. Pages which are being
+ * freed elsewhere are also ignored.
+ *
+ * page: page to consider
+ * mode: one of the LRU isolation modes defined above
+ *
+ * returns 0 on success, -ve errno on failure.
+ */
+static int __isolate_lru_page(struct page *page, int mode)
+{
+ int ret = -EINVAL;
+
+ /* Only take pages on the LRU. */
+ if (!PageLRU(page))
+ return ret;
+
+ /*
+ * When checking the active state, we need to be sure we are
+ * dealing with comparible boolean values. Take the logical not
+ * of each.
+ */
+ if (mode != ISOLATE_BOTH && (!PageActive(page) != !mode))
+ return ret;
+
+ ret = -EBUSY;
+ if (likely(get_page_unless_zero(page))) {
+ /*
+ * Be careful not to clear PageLRU until after we're
+ * sure the page is not being freed elsewhere -- the
+ * page release code relies on it.
+ */
+ ClearPageLRU(page);
+ ret = 0;
+ }
+
+ return ret;
+}
+
/*
* zone->lru_lock is heavily contended. Some of the functions that
* shrink the lists perform better by taking out a batch of pages
* @src: The LRU list to pull pages off.
* @dst: The temp list to put pages on to.
* @scanned: The number of pages that were scanned.
+ * @order: The caller's attempted allocation order
+ * @mode: One of the LRU isolation modes
*
* returns how many pages were moved onto *@dst.
*/
static unsigned long isolate_lru_pages(unsigned long nr_to_scan,
struct list_head *src, struct list_head *dst,
- unsigned long *scanned)
+ unsigned long *scanned, int order, int mode)
{
unsigned long nr_taken = 0;
- struct page *page;
unsigned long scan;
for (scan = 0; scan < nr_to_scan && !list_empty(src); scan++) {
- struct list_head *target;
+ struct page *page;
+ unsigned long pfn;
+ unsigned long end_pfn;
+ unsigned long page_pfn;
+ int zone_id;
+
page = lru_to_page(src);
prefetchw_prev_lru_page(page, src, flags);
VM_BUG_ON(!PageLRU(page));
- list_del(&page->lru);
- target = src;
- if (likely(get_page_unless_zero(page))) {
- /*
- * Be careful not to clear PageLRU until after we're
- * sure the page is not being freed elsewhere -- the
- * page release code relies on it.
- */
- ClearPageLRU(page);
- target = dst;
+ switch (__isolate_lru_page(page, mode)) {
+ case 0:
+ list_move(&page->lru, dst);
nr_taken++;
- } /* else it is being freed elsewhere */
+ break;
+
+ case -EBUSY:
+ /* else it is being freed elsewhere */
+ list_move(&page->lru, src);
+ continue;
- list_add(&page->lru, target);
+ default:
+ BUG();
+ }
+
+ if (!order)
+ continue;
+
+ /*
+ * Attempt to take all pages in the order aligned region
+ * surrounding the tag page. Only take those pages of
+ * the same active state as that tag page. We may safely
+ * round the target page pfn down to the requested order
+ * as the mem_map is guarenteed valid out to MAX_ORDER,
+ * where that page is in a different zone we will detect
+ * it from its zone id and abort this block scan.
+ */
+ zone_id = page_zone_id(page);
+ page_pfn = page_to_pfn(page);
+ pfn = page_pfn & ~((1 << order) - 1);
+ end_pfn = pfn + (1 << order);
+ for (; pfn < end_pfn; pfn++) {
+ struct page *cursor_page;
+
+ /* The target page is in the block, ignore it. */
+ if (unlikely(pfn == page_pfn))
+ continue;
+
+ /* Avoid holes within the zone. */
+ if (unlikely(!pfn_valid_within(pfn)))
+ break;
+
+ cursor_page = pfn_to_page(pfn);
+ /* Check that we have not crossed a zone boundary. */
+ if (unlikely(page_zone_id(cursor_page) != zone_id))
+ continue;
+ switch (__isolate_lru_page(cursor_page, mode)) {
+ case 0:
+ list_move(&cursor_page->lru, dst);
+ nr_taken++;
+ scan++;
+ break;
+
+ case -EBUSY:
+ /* else it is being freed elsewhere */
+ list_move(&cursor_page->lru, src);
+ default:
+ break;
+ }
+ }
}
*scanned = scan;
}
/*
+ * clear_active_flags() is a helper for shrink_active_list(), clearing
+ * any active bits from the pages in the list.
+ */
+static unsigned long clear_active_flags(struct list_head *page_list)
+{
+ int nr_active = 0;
+ struct page *page;
+
+ list_for_each_entry(page, page_list, lru)
+ if (PageActive(page)) {
+ ClearPageActive(page);
+ nr_active++;
+ }
+
+ return nr_active;
+}
+
+/*
* shrink_inactive_list() is a helper for shrink_zone(). It returns the number
* of reclaimed pages
*/
unsigned long nr_taken;
unsigned long nr_scan;
unsigned long nr_freed;
+ unsigned long nr_active;
nr_taken = isolate_lru_pages(sc->swap_cluster_max,
- &zone->inactive_list,
- &page_list, &nr_scan);
- zone->nr_inactive -= nr_taken;
+ &zone->inactive_list,
+ &page_list, &nr_scan, sc->order,
+ (sc->order > PAGE_ALLOC_COSTLY_ORDER)?
+ ISOLATE_BOTH : ISOLATE_INACTIVE);
+ 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;
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_vm_events(KSWAPD_STEAL, nr_freed);
} else
__count_zone_vm_events(PGSCAN_DIRECT, zone, nr_scan);
- __count_vm_events(PGACTIVATE, nr_freed);
+ __count_zone_vm_events(PGSTEAL, zone, nr_freed);
if (nr_taken == 0)
goto done;
return nr_reclaimed;
}
+/*
+ * We are about to scan this zone at a certain priority level. If that priority
+ * level is smaller (ie: more urgent) than the previous priority, then note
+ * that priority level within the zone. This is done so that when the next
+ * process comes in to scan this zone, it will immediately start out at this
+ * priority level rather than having to build up its own scanning priority.
+ * Here, this priority affects only the reclaim-mapped threshold.
+ */
+static inline void note_zone_scanning_priority(struct zone *zone, int priority)
+{
+ if (priority < zone->prev_priority)
+ zone->prev_priority = priority;
+}
+
static inline int zone_is_near_oom(struct zone *zone)
{
- return zone->pages_scanned >= (zone->nr_active + zone->nr_inactive)*3;
+ return zone->pages_scanned >= (zone_page_state(zone, NR_ACTIVE)
+ + zone_page_state(zone, NR_INACTIVE))*3;
}
/*
* But we had to alter page->flags anyway.
*/
static void shrink_active_list(unsigned long nr_pages, struct zone *zone,
- struct scan_control *sc)
+ struct scan_control *sc, int priority)
{
unsigned long pgmoved;
int pgdeactivate = 0;
long mapped_ratio;
long distress;
long swap_tendency;
+ long imbalance;
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 >> zone->prev_priority;
+ distress = 100 >> min(zone->prev_priority, priority);
/*
* The point of this algorithm is to decide when to start
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.
+ */
+ imbalance = zone_page_state(zone, NR_ACTIVE);
+ imbalance /= zone_page_state(zone, NR_INACTIVE) + 1;
+
+ /*
+ * 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.
*/
lru_add_drain();
spin_lock_irq(&zone->lru_lock);
pgmoved = isolate_lru_pages(nr_pages, &zone->active_list,
- &l_hold, &pgscanned);
+ &l_hold, &pgscanned, sc->order, ISOLATE_ACTIVE);
zone->pages_scanned += pgscanned;
- zone->nr_active -= pgmoved;
+ __mod_zone_page_state(zone, NR_ACTIVE, -pgmoved);
spin_unlock_irq(&zone->lru_lock);
while (!list_empty(&l_hold)) {
list_move(&page->lru, &zone->inactive_list);
pgmoved++;
if (!pagevec_add(&pvec, page)) {
- zone->nr_inactive += pgmoved;
+ __mod_zone_page_state(zone, NR_INACTIVE, pgmoved);
spin_unlock_irq(&zone->lru_lock);
pgdeactivate += pgmoved;
pgmoved = 0;
spin_lock_irq(&zone->lru_lock);
}
}
- zone->nr_inactive += pgmoved;
+ __mod_zone_page_state(zone, NR_INACTIVE, pgmoved);
pgdeactivate += pgmoved;
if (buffer_heads_over_limit) {
spin_unlock_irq(&zone->lru_lock);
list_move(&page->lru, &zone->active_list);
pgmoved++;
if (!pagevec_add(&pvec, page)) {
- zone->nr_active += pgmoved;
+ __mod_zone_page_state(zone, NR_ACTIVE, pgmoved);
pgmoved = 0;
spin_unlock_irq(&zone->lru_lock);
__pagevec_release(&pvec);
spin_lock_irq(&zone->lru_lock);
}
}
- zone->nr_active += pgmoved;
+ __mod_zone_page_state(zone, NR_ACTIVE, pgmoved);
__count_zone_vm_events(PGREFILL, zone, pgscanned);
__count_vm_events(PGDEACTIVATE, pgdeactivate);
unsigned long nr_to_scan;
unsigned long nr_reclaimed = 0;
- atomic_inc(&zone->reclaim_in_progress);
-
/*
* 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->nr_active >> priority) + 1;
+ 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;
- zone->nr_scan_inactive += (zone->nr_inactive >> priority) + 1;
+ 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;
nr_to_scan = min(nr_active,
(unsigned long)sc->swap_cluster_max);
nr_active -= nr_to_scan;
- shrink_active_list(nr_to_scan, zone, sc);
+ shrink_active_list(nr_to_scan, zone, sc, priority);
}
if (nr_inactive) {
}
}
- throttle_vm_writeout();
-
- atomic_dec(&zone->reclaim_in_progress);
+ throttle_vm_writeout(sc->gfp_mask);
return nr_reclaimed;
}
if (!populated_zone(zone))
continue;
- if (!cpuset_zone_allowed(zone, __GFP_HARDWALL))
+ if (!cpuset_zone_allowed_hardwall(zone, GFP_KERNEL))
continue;
- zone->temp_priority = priority;
- if (zone->prev_priority > priority)
- zone->prev_priority = priority;
+ note_zone_scanning_priority(zone, priority);
- if (zone->all_unreclaimable && priority != DEF_PRIORITY)
+ if (zone_is_all_unreclaimable(zone) && priority != DEF_PRIORITY)
continue; /* Let kswapd poll it */
sc->all_unreclaimable = 0;
* holds filesystem locks which prevent writeout this might not work, and the
* allocation attempt will fail.
*/
-unsigned long try_to_free_pages(struct zone **zones, gfp_t gfp_mask)
+unsigned long try_to_free_pages(struct zone **zones, int order, gfp_t gfp_mask)
{
int priority;
int ret = 0;
.swap_cluster_max = SWAP_CLUSTER_MAX,
.may_swap = 1,
.swappiness = vm_swappiness,
+ .order = order,
};
count_vm_event(ALLOCSTALL);
for (i = 0; zones[i] != NULL; i++) {
struct zone *zone = zones[i];
- if (!cpuset_zone_allowed(zone, __GFP_HARDWALL))
+ if (!cpuset_zone_allowed_hardwall(zone, GFP_KERNEL))
continue;
- zone->temp_priority = DEF_PRIORITY;
- lru_pages += zone->nr_active + zone->nr_inactive;
+ lru_pages += zone_page_state(zone, NR_ACTIVE)
+ + zone_page_state(zone, NR_INACTIVE);
}
for (priority = DEF_PRIORITY; priority >= 0; priority--) {
/* Take a nap, wait for some writeback to complete */
if (sc.nr_scanned && priority < DEF_PRIORITY - 2)
- blk_congestion_wait(WRITE, HZ/10);
+ congestion_wait(WRITE, HZ/10);
}
/* top priority shrink_caches still had more to do? don't OOM, then */
if (!sc.all_unreclaimable)
ret = 1;
out:
- for (i = 0; zones[i] != 0; i++) {
+ /*
+ * Now that we've scanned all the zones at this priority level, note
+ * that level within the zone so that the next thread which performs
+ * scanning of this zone will immediately start out at this priority
+ * level. This affects only the decision whether or not to bring
+ * mapped pages onto the inactive list.
+ */
+ if (priority < 0)
+ priority = 0;
+ for (i = 0; zones[i] != NULL; i++) {
struct zone *zone = zones[i];
- if (!cpuset_zone_allowed(zone, __GFP_HARDWALL))
+ if (!cpuset_zone_allowed_hardwall(zone, GFP_KERNEL))
continue;
- zone->prev_priority = zone->temp_priority;
+ zone->prev_priority = priority;
}
return ret;
}
.may_swap = 1,
.swap_cluster_max = SWAP_CLUSTER_MAX,
.swappiness = vm_swappiness,
+ .order = order,
};
+ /*
+ * temp_priority is used to remember the scanning priority at which
+ * this zone was successfully refilled to free_pages == pages_high.
+ */
+ int temp_priority[MAX_NR_ZONES];
loop_again:
total_scanned = 0;
sc.may_writepage = !laptop_mode;
count_vm_event(PAGEOUTRUN);
- for (i = 0; i < pgdat->nr_zones; i++) {
- struct zone *zone = pgdat->node_zones + i;
-
- zone->temp_priority = DEF_PRIORITY;
- }
+ for (i = 0; i < pgdat->nr_zones; i++)
+ temp_priority[i] = DEF_PRIORITY;
for (priority = DEF_PRIORITY; priority >= 0; priority--) {
int end_zone = 0; /* Inclusive. 0 = ZONE_DMA */
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,
0, 0)) {
end_zone = i;
- goto scan;
+ break;
}
}
- goto out;
-scan:
+ if (i < 0)
+ goto out;
+
for (i = 0; i <= end_zone; i++) {
struct zone *zone = pgdat->node_zones + i;
- lru_pages += zone->nr_active + zone->nr_inactive;
+ lru_pages += zone_page_state(zone, NR_ACTIVE)
+ + zone_page_state(zone, NR_INACTIVE);
}
/*
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,
end_zone, 0))
all_zones_ok = 0;
- zone->temp_priority = priority;
- if (zone->prev_priority > priority)
- zone->prev_priority = priority;
+ temp_priority[i] = priority;
sc.nr_scanned = 0;
- nr_reclaimed += shrink_zone(priority, zone, &sc);
+ note_zone_scanning_priority(zone, priority);
+ /*
+ * 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->nr_active + zone->nr_inactive) * 6)
- zone->all_unreclaimable = 1;
+ (zone_page_state(zone, NR_ACTIVE)
+ + zone_page_state(zone, NR_INACTIVE)) * 6)
+ 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
* another pass across the zones.
*/
if (total_scanned && priority < DEF_PRIORITY - 2)
- blk_congestion_wait(WRITE, HZ/10);
+ congestion_wait(WRITE, HZ/10);
/*
* We do this so kswapd doesn't build up large priorities for
break;
}
out:
+ /*
+ * Note within each zone the priority level at which this zone was
+ * brought into a happy state. So that the next thread which scans this
+ * zone will start out at that priority level.
+ */
for (i = 0; i < pgdat->nr_zones; i++) {
struct zone *zone = pgdat->node_zones + i;
- zone->prev_priority = zone->temp_priority;
+ zone->prev_priority = temp_priority[i];
}
if (!all_zones_ok) {
cond_resched();
+
+ try_to_freeze();
+
goto loop_again;
}
* 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 ( ; ; ) {
unsigned long new_order;
- try_to_freeze();
-
prepare_to_wait(&pgdat->kswapd_wait, &wait, TASK_INTERRUPTIBLE);
new_order = pgdat->kswapd_max_order;
pgdat->kswapd_max_order = 0;
*/
order = new_order;
} else {
- schedule();
+ if (!freezing(current))
+ schedule();
+
order = pgdat->kswapd_max_order;
}
finish_wait(&pgdat->kswapd_wait, &wait);
- balance_pgdat(pgdat, order);
+ if (!try_to_freeze()) {
+ /* We can speed up thawing tasks if we don't call
+ * balance_pgdat after returning from the refrigerator
+ */
+ balance_pgdat(pgdat, order);
+ }
}
return 0;
}
return;
if (pgdat->kswapd_max_order < order)
pgdat->kswapd_max_order = order;
- if (!cpuset_zone_allowed(zone, __GFP_HARDWALL))
+ if (!cpuset_zone_allowed_hardwall(zone, GFP_KERNEL))
return;
if (!waitqueue_active(&pgdat->kswapd_wait))
return;
*
* For pass > 3 we also try to shrink the LRU lists that contain a few pages
*/
-static unsigned long shrink_all_zones(unsigned long nr_pages, int pass,
- int prio, struct scan_control *sc)
+static unsigned long shrink_all_zones(unsigned long nr_pages, int prio,
+ int pass, struct scan_control *sc)
{
struct zone *zone;
unsigned long nr_to_scan, ret = 0;
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 */
if (pass > 0) {
- zone->nr_scan_active += (zone->nr_active >> prio) + 1;
+ zone->nr_scan_active +=
+ (zone_page_state(zone, NR_ACTIVE) >> prio) + 1;
if (zone->nr_scan_active >= nr_pages || pass > 3) {
zone->nr_scan_active = 0;
- nr_to_scan = min(nr_pages, zone->nr_active);
- shrink_active_list(nr_to_scan, zone, sc);
+ nr_to_scan = min(nr_pages,
+ zone_page_state(zone, NR_ACTIVE));
+ shrink_active_list(nr_to_scan, zone, sc, prio);
}
}
- zone->nr_scan_inactive += (zone->nr_inactive >> prio) + 1;
+ zone->nr_scan_inactive +=
+ (zone_page_state(zone, NR_INACTIVE) >> prio) + 1;
if (zone->nr_scan_inactive >= nr_pages || pass > 3) {
zone->nr_scan_inactive = 0;
- nr_to_scan = min(nr_pages, zone->nr_inactive);
+ nr_to_scan = min(nr_pages,
+ zone_page_state(zone, NR_INACTIVE));
ret += shrink_inactive_list(nr_to_scan, zone, sc);
if (ret >= nr_pages)
return ret;
return ret;
}
+static unsigned long count_lru_pages(void)
+{
+ return global_page_state(NR_ACTIVE) + global_page_state(NR_INACTIVE);
+}
+
/*
* Try to free `nr_pages' of memory, system-wide, and return the number of
* freed pages.
unsigned long ret = 0;
int pass;
struct reclaim_state reclaim_state;
- struct zone *zone;
struct scan_control sc = {
.gfp_mask = GFP_KERNEL,
.may_swap = 0,
current->reclaim_state = &reclaim_state;
- lru_pages = 0;
- for_each_zone(zone)
- lru_pages += zone->nr_active + zone->nr_inactive;
-
- nr_slab = global_page_state(NR_SLAB);
+ lru_pages = count_lru_pages();
+ nr_slab = global_page_state(NR_SLAB_RECLAIMABLE);
/* If slab caches are huge, it's better to hit them first */
while (nr_slab >= lru_pages) {
reclaim_state.reclaimed_slab = 0;
for (pass = 0; pass < 5; pass++) {
int prio;
- /* Needed for shrinking slab caches later on */
- if (!lru_pages)
- for_each_zone(zone) {
- lru_pages += zone->nr_active;
- lru_pages += zone->nr_inactive;
- }
-
/* Force reclaiming mapped pages in the passes #3 and #4 */
if (pass > 2) {
sc.may_swap = 1;
goto out;
reclaim_state.reclaimed_slab = 0;
- shrink_slab(sc.nr_scanned, sc.gfp_mask, lru_pages);
+ shrink_slab(sc.nr_scanned, sc.gfp_mask,
+ count_lru_pages());
ret += reclaim_state.reclaimed_slab;
if (ret >= nr_pages)
goto out;
if (sc.nr_scanned && prio < DEF_PRIORITY - 2)
- blk_congestion_wait(WRITE, HZ / 10);
+ congestion_wait(WRITE, HZ / 10);
}
-
- lru_pages = 0;
}
/*
* If ret = 0, we could not shrink LRUs, but there may be something
* in slab caches
*/
- if (!ret)
+ if (!ret) {
do {
reclaim_state.reclaimed_slab = 0;
- shrink_slab(nr_pages, sc.gfp_mask, lru_pages);
+ shrink_slab(nr_pages, sc.gfp_mask, count_lru_pages());
ret += reclaim_state.reclaimed_slab;
} while (ret < nr_pages && reclaim_state.reclaimed_slab > 0);
+ }
out:
current->reclaim_state = NULL;
}
#endif
-#ifdef CONFIG_HOTPLUG_CPU
/* It's optimal to keep kswapds on the same CPUs as their memory, but
not required for correctness. So if the last cpu in a node goes
away, we get changed to run anywhere: as the first one comes back,
{
pg_data_t *pgdat;
cpumask_t mask;
+ int nid;
- if (action == CPU_ONLINE) {
- for_each_online_pgdat(pgdat) {
+ if (action == CPU_ONLINE || action == CPU_ONLINE_FROZEN) {
+ for_each_node_state(nid, N_HIGH_MEMORY) {
+ pgdat = NODE_DATA(nid);
mask = node_to_cpumask(pgdat->node_id);
if (any_online_cpu(mask) != NR_CPUS)
/* One of our CPUs online: restore mask */
}
return NOTIFY_OK;
}
-#endif /* CONFIG_HOTPLUG_CPU */
/*
* This kswapd start function will be called by init and node-hot-add.
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;
#define RECLAIM_ZONE (1<<0) /* Run shrink_cache on the zone */
#define RECLAIM_WRITE (1<<1) /* Writeout pages during reclaim */
#define RECLAIM_SWAP (1<<2) /* Swap pages out during reclaim */
-#define RECLAIM_SLAB (1<<3) /* Do a global slab shrink if the zone is out of memory */
/*
* Priority for ZONE_RECLAIM. This determines the fraction of pages
int sysctl_min_unmapped_ratio = 1;
/*
+ * If the number of slab pages in a zone grows beyond this percentage then
+ * slab reclaim needs to occur.
+ */
+int sysctl_min_slab_ratio = 5;
+
+/*
* Try to free up some pages from this zone through reclaim.
*/
static int __zone_reclaim(struct zone *zone, gfp_t gfp_mask, unsigned int order)
.gfp_mask = gfp_mask,
.swappiness = vm_swappiness,
};
+ unsigned long slab_reclaimable;
disable_swap_token();
cond_resched();
reclaim_state.reclaimed_slab = 0;
p->reclaim_state = &reclaim_state;
- /*
- * Free memory by calling shrink zone with increasing priorities
- * until we have enough memory freed.
- */
- priority = ZONE_RECLAIM_PRIORITY;
- do {
- nr_reclaimed += shrink_zone(priority, zone, &sc);
- priority--;
- } while (priority >= 0 && nr_reclaimed < nr_pages);
+ if (zone_page_state(zone, NR_FILE_PAGES) -
+ zone_page_state(zone, NR_FILE_MAPPED) >
+ zone->min_unmapped_pages) {
+ /*
+ * Free memory by calling shrink zone with increasing
+ * priorities until we have enough memory freed.
+ */
+ priority = ZONE_RECLAIM_PRIORITY;
+ do {
+ note_zone_scanning_priority(zone, priority);
+ nr_reclaimed += shrink_zone(priority, zone, &sc);
+ priority--;
+ } while (priority >= 0 && nr_reclaimed < nr_pages);
+ }
- if (nr_reclaimed < nr_pages && (zone_reclaim_mode & RECLAIM_SLAB)) {
+ slab_reclaimable = zone_page_state(zone, NR_SLAB_RECLAIMABLE);
+ if (slab_reclaimable > zone->min_slab_pages) {
/*
* shrink_slab() does not currently allow us to determine how
- * many pages were freed in this zone. So we just shake the slab
- * a bit and then go off node for this particular allocation
- * despite possibly having freed enough memory to allocate in
- * this zone. If we freed local memory then the next
- * allocations will be local again.
+ * many pages were freed in this zone. So we take the current
+ * number of slab pages and shake the slab until it is reduced
+ * by the same nr_pages that we used for reclaiming unmapped
+ * pages.
*
- * shrink_slab will free memory on all zones and may take
- * a long time.
+ * Note that shrink_slab will free memory on all zones and may
+ * take a long time.
*/
- shrink_slab(sc.nr_scanned, gfp_mask, order);
+ while (shrink_slab(sc.nr_scanned, gfp_mask, order) &&
+ zone_page_state(zone, NR_SLAB_RECLAIMABLE) >
+ slab_reclaimable - nr_pages)
+ ;
+
+ /*
+ * Update nr_reclaimed by the number of slab pages we
+ * reclaimed from this zone.
+ */
+ nr_reclaimed += slab_reclaimable -
+ zone_page_state(zone, NR_SLAB_RECLAIMABLE);
}
p->reclaim_state = NULL;
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.
+ * Zone reclaim reclaims unmapped file backed pages and
+ * slab pages if we are over the defined limits.
*
* A small portion of unmapped file backed pages is needed for
* file I/O otherwise pages read by file I/O will be immediately
* unmapped file backed pages.
*/
if (zone_page_state(zone, NR_FILE_PAGES) -
- zone_page_state(zone, NR_FILE_MAPPED) <= zone->min_unmapped_ratio)
+ zone_page_state(zone, NR_FILE_MAPPED) <= zone->min_unmapped_pages
+ && zone_page_state(zone, NR_SLAB_RECLAIMABLE)
+ <= 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;
/*
* over remote processors and spread off node memory allocations
* as wide as possible.
*/
- node_id = zone->zone_pgdat->node_id;
- mask = node_to_cpumask(node_id);
- if (!cpus_empty(mask) && node_id != numa_node_id())
+ node_id = zone_to_nid(zone);
+ if (node_state(node_id, N_CPU) && node_id != numa_node_id())
+ return 0;
+
+ if (zone_test_and_set_flag(zone, ZONE_RECLAIM_LOCKED))
return 0;
- return __zone_reclaim(zone, gfp_mask, order);
+ ret = __zone_reclaim(zone, gfp_mask, order);
+ zone_clear_flag(zone, ZONE_RECLAIM_LOCKED);
+
+ return ret;
}
#endif