#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/cpuset.h>
#include <linux/notifier.h>
#include <linux/rwsem.h>
+#include <linux/delay.h>
+#include <linux/kthread.h>
+#include <linux/freezer.h>
+#include <linux/memcontrol.h>
#include <asm/tlbflush.h>
#include <asm/div64.h>
#include <linux/swapops.h>
-/* possible outcome of pageout() */
-typedef enum {
- /* failed to write page out, page is locked */
- PAGE_KEEP,
- /* move page to the active list, page is locked */
- PAGE_ACTIVATE,
- /* page has been sent to the disk successfully, page is unlocked */
- PAGE_SUCCESS,
- /* page is clean and locked */
- PAGE_CLEAN,
-} pageout_t;
+#include "internal.h"
struct scan_control {
- /* Ask refill_inactive_zone, or shrink_cache to scan this many pages */
- unsigned long nr_to_scan;
-
/* Incremented by the number of inactive pages that were scanned */
unsigned long nr_scanned;
- /* Incremented by the number of pages reclaimed */
- unsigned long nr_reclaimed;
-
- unsigned long nr_mapped; /* From page_state */
-
- /* Ask shrink_caches, or shrink_zone to scan at this priority */
- unsigned int priority;
-
/* This context's GFP mask */
gfp_t gfp_mask;
* In this context, it doesn't matter that we scan the
* whole list at once. */
int swap_cluster_max;
-};
-/*
- * 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 swappiness;
+
+ 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))
* From 0 .. 100. Higher means more swappy.
*/
int vm_swappiness = 60;
-static long total_memory;
+long vm_total_pages; /* The total number of pages which the VM controls */
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
*/
-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.
*
* Returns the number of slab objects which we shrunk.
*/
-int shrink_slab(unsigned long scanned, gfp_t gfp_mask, unsigned long lru_pages)
+unsigned long shrink_slab(unsigned long scanned, gfp_t gfp_mask,
+ unsigned long lru_pages)
{
struct shrinker *shrinker;
- int ret = 0;
+ unsigned long ret = 0;
if (scanned == 0)
scanned = SWAP_CLUSTER_MAX;
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)
ret += nr_before - shrink_ret;
- mod_page_state(slabs_scanned, this_scan);
+ count_vm_events(SLABS_SCANNED, this_scan);
total_scan -= this_scan;
cond_resched();
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 */
+ PAGE_KEEP,
+ /* move page to the active list, page is locked */
+ PAGE_ACTIVATE,
+ /* page has been sent to the disk successfully, page is unlocked */
+ PAGE_SUCCESS,
+ /* page is clean and locked */
+ PAGE_CLEAN,
+} pageout_t;
+
/*
- * pageout is called by shrink_list() for each dirty page. Calls ->writepage().
+ * 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
struct writeback_control wbc = {
.sync_mode = WB_SYNC_NONE,
.nr_to_write = SWAP_CLUSTER_MAX,
+ .range_start = 0,
+ .range_end = LLONG_MAX,
.nonblocking = 1,
.for_reclaim = 1,
};
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;
}
-static int remove_mapping(struct address_space *mapping, struct page *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.
+ */
+int remove_mapping(struct address_space *mapping, struct page *page)
{
- if (!mapping)
- return 0; /* truncate got there first */
+ 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_list adds the number of reclaimed pages to sc->nr_reclaimed
+ * shrink_page_list() returns the number of reclaimed pages
*/
-static int shrink_list(struct list_head *page_list, struct scan_control *sc)
+static unsigned long shrink_page_list(struct list_head *page_list,
+ struct scan_control *sc,
+ enum pageout_io sync_writeback)
{
LIST_HEAD(ret_pages);
struct pagevec freed_pvec;
int pgactivate = 0;
- int reclaimed = 0;
+ unsigned long nr_reclaimed = 0;
cond_resched();
if (TestSetPageLocked(page))
goto keep;
- BUG_ON(PageActive(page));
+ VM_BUG_ON(PageActive(page));
sc->nr_scanned++;
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 (referenced && page_mapping_inuse(page))
+ if (sc->order <= PAGE_ALLOC_COSTLY_ORDER &&
+ referenced && page_mapping_inuse(page))
goto activate_locked;
#ifdef CONFIG_SWAP
* Anonymous process memory has backing store?
* Try to allocate it some swap space here.
*/
- if (PageAnon(page) && !PageSwapCache(page)) {
- if (!sc->may_swap)
- goto keep_locked;
+ if (PageAnon(page) && !PageSwapCache(page))
if (!add_to_swap(page, GFP_ATOMIC))
goto activate_locked;
- }
#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
* processes. Try to unmap it here.
*/
if (page_mapped(page) && mapping) {
- /*
- * No unmapping if we do not swap
- */
- if (!sc->may_swap)
- goto keep_locked;
-
switch (try_to_unmap(page, 0)) {
case SWAP_FAIL:
goto activate_locked;
}
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:
goto free_it;
}
- if (!remove_mapping(mapping, page))
+ if (!mapping || !remove_mapping(mapping, page))
goto keep_locked;
free_it:
unlock_page(page);
- reclaimed++;
+ nr_reclaimed++;
if (!pagevec_add(&freed_pvec, page))
__pagevec_release_nonlru(&freed_pvec);
continue;
unlock_page(page);
keep:
list_add(&page->lru, &ret_pages);
- BUG_ON(PageLRU(page));
+ VM_BUG_ON(PageLRU(page));
}
list_splice(&ret_pages, page_list);
if (pagevec_count(&freed_pvec))
__pagevec_release_nonlru(&freed_pvec);
- mod_page_state(pgactivate, pgactivate);
- sc->nr_reclaimed += reclaimed;
- return reclaimed;
+ count_vm_events(PGACTIVATE, pgactivate);
+ return nr_reclaimed;
}
-#ifdef CONFIG_MIGRATION
-static inline void move_to_lru(struct page *page)
+/* 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.
+ */
+int __isolate_lru_page(struct page *page, int mode)
{
- list_del(&page->lru);
- if (PageActive(page)) {
+ 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))) {
/*
- * lru_cache_add_active checks that
- * the PG_active bit is off.
+ * 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.
*/
- ClearPageActive(page);
- lru_cache_add_active(page);
- } else {
- lru_cache_add(page);
+ ClearPageLRU(page);
+ ret = 0;
}
- put_page(page);
+
+ return ret;
}
/*
- * Add isolated pages on the list back to the LRU.
+ * zone->lru_lock is heavily contended. Some of the functions that
+ * shrink the lists perform better by taking out a batch of pages
+ * and working on them outside the LRU lock.
*
- * returns the number of pages put back.
+ * For pagecache intensive workloads, this function is the hottest
+ * spot in the kernel (apart from copy_*_user functions).
+ *
+ * Appropriate locks must be held before calling this function.
+ *
+ * @nr_to_scan: The number of pages to look through on the list.
+ * @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.
*/
-int putback_lru_pages(struct list_head *l)
+static unsigned long isolate_lru_pages(unsigned long nr_to_scan,
+ struct list_head *src, struct list_head *dst,
+ unsigned long *scanned, int order, int mode)
{
- struct page *page;
- struct page *page2;
- int count = 0;
+ unsigned long nr_taken = 0;
+ unsigned long scan;
+
+ for (scan = 0; scan < nr_to_scan && !list_empty(src); scan++) {
+ 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));
+
+ switch (__isolate_lru_page(page, mode)) {
+ case 0:
+ list_move(&page->lru, dst);
+ nr_taken++;
+ break;
+
+ case -EBUSY:
+ /* else it is being freed elsewhere */
+ list_move(&page->lru, src);
+ continue;
+
+ 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;
- list_for_each_entry_safe(page, page2, l, lru) {
- move_to_lru(page);
- count++;
+ /* 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;
+ }
+ }
}
- return count;
+
+ *scanned = scan;
+ 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);
}
/*
- * Non migratable page
+ * clear_active_flags() is a helper for shrink_active_list(), clearing
+ * any active bits from the pages in the list.
*/
-int fail_migrate_page(struct page *newpage, struct page *page)
+static unsigned long clear_active_flags(struct list_head *page_list)
{
- return -EIO;
+ 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;
}
-EXPORT_SYMBOL(fail_migrate_page);
/*
- * swapout a single page
- * page is locked upon entry, unlocked on exit
+ * shrink_inactive_list() is a helper for shrink_zone(). It returns the number
+ * of reclaimed pages
*/
-static int swap_page(struct page *page)
+static unsigned long shrink_inactive_list(unsigned long max_scan,
+ struct zone *zone, struct scan_control *sc)
{
- struct address_space *mapping = page_mapping(page);
+ LIST_HEAD(page_list);
+ struct pagevec pvec;
+ unsigned long nr_scanned = 0;
+ unsigned long nr_reclaimed = 0;
+
+ pagevec_init(&pvec, 1);
+
+ lru_add_drain();
+ spin_lock_irq(&zone->lru_lock);
+ do {
+ struct page *page;
+ unsigned long nr_taken;
+ unsigned long nr_scan;
+ unsigned long nr_freed;
+ unsigned long nr_active;
+
+ 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,
+ 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));
+ if (scan_global_lru(sc))
+ zone->pages_scanned += nr_scan;
+ spin_unlock_irq(&zone->lru_lock);
- if (page_mapped(page) && mapping)
- if (try_to_unmap(page, 1) != SWAP_SUCCESS)
- goto unlock_retry;
+ nr_scanned += nr_scan;
+ nr_freed = shrink_page_list(&page_list, sc, PAGEOUT_IO_ASYNC);
- if (PageDirty(page)) {
- /* Page is dirty, try to write it out here */
- switch(pageout(page, mapping)) {
- case PAGE_KEEP:
- case PAGE_ACTIVATE:
- goto unlock_retry;
+ /*
+ * 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);
- case PAGE_SUCCESS:
- goto retry;
+ /*
+ * 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);
- case PAGE_CLEAN:
- ; /* try to free the page below */
+ nr_freed += shrink_page_list(&page_list, sc,
+ PAGEOUT_IO_SYNC);
}
- }
- if (PagePrivate(page)) {
- if (!try_to_release_page(page, GFP_KERNEL) ||
- (!mapping && page_count(page) == 1))
- goto unlock_retry;
- }
+ 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 if (scan_global_lru(sc))
+ __count_zone_vm_events(PGSCAN_DIRECT, zone, nr_scan);
- if (remove_mapping(mapping, page)) {
- /* Success */
- unlock_page(page);
- return 0;
- }
+ __count_zone_vm_events(PGSTEAL, zone, nr_freed);
-unlock_retry:
- unlock_page(page);
+ if (nr_taken == 0)
+ goto done;
-retry:
- return -EAGAIN;
+ spin_lock(&zone->lru_lock);
+ /*
+ * Put back any unfreeable pages.
+ */
+ while (!list_empty(&page_list)) {
+ page = lru_to_page(&page_list);
+ VM_BUG_ON(PageLRU(page));
+ SetPageLRU(page);
+ list_del(&page->lru);
+ if (PageActive(page))
+ add_page_to_active_list(zone, page);
+ else
+ add_page_to_inactive_list(zone, page);
+ if (!pagevec_add(&pvec, page)) {
+ spin_unlock_irq(&zone->lru_lock);
+ __pagevec_release(&pvec);
+ spin_lock_irq(&zone->lru_lock);
+ }
+ }
+ } while (nr_scanned < max_scan);
+ spin_unlock(&zone->lru_lock);
+done:
+ local_irq_enable();
+ pagevec_release(&pvec);
+ return nr_reclaimed;
}
-EXPORT_SYMBOL(swap_page);
/*
- * Page migration was first developed in the context of the memory hotplug
- * project. The main authors of the migration code are:
- *
- * IWAMOTO Toshihiro <iwamoto@valinux.co.jp>
- * Hirokazu Takahashi <taka@valinux.co.jp>
- * Dave Hansen <haveblue@us.ibm.com>
- * Christoph Lameter <clameter@sgi.com>
+ * 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_page_state(zone, NR_ACTIVE)
+ + zone_page_state(zone, NR_INACTIVE))*3;
+}
/*
- * Remove references for a page and establish the new page with the correct
- * basic settings to be able to stop accesses to the page.
+ * Determine we should try to reclaim mapped pages.
+ * This is called only when sc->mem_cgroup is NULL.
*/
-int migrate_page_remove_references(struct page *newpage,
- struct page *page, int nr_refs)
+static int calc_reclaim_mapped(struct scan_control *sc, struct zone *zone,
+ int priority)
{
- struct address_space *mapping = page_mapping(page);
- struct page **radix_pointer;
+ 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;
/*
- * Avoid doing any of the following work if the page count
- * indicates that the page is in use or truncate has removed
- * the page.
+ * `distress' is a measure of how much trouble we're having
+ * reclaiming pages. 0 -> no problems. 100 -> great trouble.
*/
- if (!mapping || page_mapcount(page) + nr_refs != page_count(page))
- return 1;
+ 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);
/*
- * Establish swap ptes for anonymous pages or destroy pte
- * maps for files.
- *
- * In order to reestablish file backed mappings the fault handlers
- * will take the radix tree_lock which may then be used to stop
- * processses from accessing this page until the new page is ready.
+ * 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.
*
- * A process accessing via a swap pte (an anonymous page) will take a
- * page_lock on the old page which will block the process until the
- * migration attempt is complete. At that time the PageSwapCache bit
- * will be examined. If the page was migrated then the PageSwapCache
- * bit will be clear and the operation to retrieve the page will be
- * retried which will find the new page in the radix tree. Then a new
- * direct mapping may be generated based on the radix tree contents.
+ * The distress ratio is important - we don't want to start
+ * going oom.
*
- * If the page was not migrated then the PageSwapCache bit
- * is still set and the operation may continue.
+ * A 100% value of vm_swappiness overrides this algorithm
+ * altogether.
*/
- try_to_unmap(page, 1);
+ swap_tendency = mapped_ratio / 2 + distress + sc->swappiness;
/*
- * Give up if we were unable to remove all mappings.
+ * 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 (page_mapcount(page))
- return 1;
-
- write_lock_irq(&mapping->tree_lock);
-
- radix_pointer = (struct page **)radix_tree_lookup_slot(
- &mapping->page_tree,
- page_index(page));
-
- if (!page_mapping(page) || page_count(page) != nr_refs ||
- *radix_pointer != page) {
- write_unlock_irq(&mapping->tree_lock);
- return 1;
- }
+ 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);
/*
- * Now we know that no one else is looking at the page.
+ * 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.
*
- * Certain minimal information about a page must be available
- * in order for other subsystems to properly handle the page if they
- * find it through the radix tree update before we are finished
- * copying the page.
+ * Max temporary value is vm_total_pages*100.
*/
- get_page(newpage);
- newpage->index = page->index;
- newpage->mapping = page->mapping;
- if (PageSwapCache(page)) {
- SetPageSwapCache(newpage);
- set_page_private(newpage, page_private(page));
- }
-
- *radix_pointer = newpage;
- __put_page(page);
- write_unlock_irq(&mapping->tree_lock);
-
- return 0;
-}
-EXPORT_SYMBOL(migrate_page_remove_references);
-
-/*
- * Copy the page to its new location
- */
-void migrate_page_copy(struct page *newpage, struct page *page)
-{
- copy_highpage(newpage, page);
-
- if (PageError(page))
- SetPageError(newpage);
- if (PageReferenced(page))
- SetPageReferenced(newpage);
- if (PageUptodate(page))
- SetPageUptodate(newpage);
- if (PageActive(page))
- SetPageActive(newpage);
- if (PageChecked(page))
- SetPageChecked(newpage);
- if (PageMappedToDisk(page))
- SetPageMappedToDisk(newpage);
-
- if (PageDirty(page)) {
- clear_page_dirty_for_io(page);
- set_page_dirty(newpage);
- }
-
- ClearPageSwapCache(page);
- ClearPageActive(page);
- ClearPagePrivate(page);
- set_page_private(page, 0);
- page->mapping = NULL;
+ imbalance *= (vm_swappiness + 1);
+ imbalance /= 100;
/*
- * If any waiters have accumulated on the new page then
- * wake them up.
+ * 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.
*/
- if (PageWriteback(newpage))
- end_page_writeback(newpage);
-}
-EXPORT_SYMBOL(migrate_page_copy);
+ imbalance *= mapped_ratio;
+ imbalance /= 100;
-/*
- * Common logic to directly migrate a single page suitable for
- * pages that do not use PagePrivate.
- *
- * Pages are locked upon entry and exit.
- */
-int migrate_page(struct page *newpage, struct page *page)
-{
- BUG_ON(PageWriteback(page)); /* Writeback must be complete */
-
- if (migrate_page_remove_references(newpage, page, 2))
- return -EAGAIN;
-
- migrate_page_copy(newpage, page);
+ /* apply imbalance feedback to swap_tendency */
+ swap_tendency += imbalance;
/*
- * Remove auxiliary swap entries and replace
- * them with real ptes.
- *
- * Note that a real pte entry will allow processes that are not
- * waiting on the page lock to use the new page via the page tables
- * before the new page is unlocked.
+ * Now use this metric to decide whether to start moving mapped
+ * memory onto the inactive list.
*/
- remove_from_swap(newpage);
- return 0;
+ if (swap_tendency >= 100)
+ reclaim_mapped = 1;
+
+ return reclaim_mapped;
}
-EXPORT_SYMBOL(migrate_page);
/*
- * migrate_pages
+ * This moves pages from the active list to the inactive list.
*
- * Two lists are passed to this function. The first list
- * contains the pages isolated from the LRU to be migrated.
- * The second list contains new pages that the pages isolated
- * can be moved to. If the second list is NULL then all
- * pages are swapped out.
+ * We move them the other way if the page is referenced by one or more
+ * processes, from rmap.
*
- * The function returns after 10 attempts or if no pages
- * are movable anymore because to has become empty
- * or no retryable pages exist anymore.
+ * If the pages are mostly unmapped, the processing is fast and it is
+ * appropriate to hold zone->lru_lock across the whole operation. But if
+ * the pages are mapped, the processing is slow (page_referenced()) so we
+ * should drop zone->lru_lock around each page. It's impossible to balance
+ * this, so instead we remove the pages from the LRU while processing them.
+ * It is safe to rely on PG_active against the non-LRU pages in here because
+ * nobody will play with that bit on a non-LRU page.
*
- * Return: Number of pages not migrated when "to" ran empty.
+ * The downside is that we have to touch page->_count against each page.
+ * But we had to alter page->flags anyway.
*/
-int migrate_pages(struct list_head *from, struct list_head *to,
- struct list_head *moved, struct list_head *failed)
-{
- int retry;
- int nr_failed = 0;
- int pass = 0;
- struct page *page;
- struct page *page2;
- int swapwrite = current->flags & PF_SWAPWRITE;
- int rc;
-
- if (!swapwrite)
- current->flags |= PF_SWAPWRITE;
-redo:
- retry = 0;
- list_for_each_entry_safe(page, page2, from, lru) {
- struct page *newpage = NULL;
- struct address_space *mapping;
-
- cond_resched();
-
- rc = 0;
- if (page_count(page) == 1)
- /* page was freed from under us. So we are done. */
- goto next;
-
- if (to && list_empty(to))
- break;
-
- /*
- * Skip locked pages during the first two passes to give the
- * functions holding the lock time to release the page. Later we
- * use lock_page() to have a higher chance of acquiring the
- * lock.
- */
- rc = -EAGAIN;
- if (pass > 2)
- lock_page(page);
- else
- if (TestSetPageLocked(page))
- goto next;
-
- /*
- * Only wait on writeback if we have already done a pass where
- * we we may have triggered writeouts for lots of pages.
- */
- if (pass > 0) {
- wait_on_page_writeback(page);
- } else {
- if (PageWriteback(page))
- goto unlock_page;
- }
-
- /*
- * Anonymous pages must have swap cache references otherwise
- * the information contained in the page maps cannot be
- * preserved.
- */
- if (PageAnon(page) && !PageSwapCache(page)) {
- if (!add_to_swap(page, GFP_KERNEL)) {
- rc = -ENOMEM;
- goto unlock_page;
- }
- }
-
- if (!to) {
- rc = swap_page(page);
- goto next;
- }
-
- newpage = lru_to_page(to);
- lock_page(newpage);
-
- /*
- * Pages are properly locked and writeback is complete.
- * Try to migrate the page.
- */
- mapping = page_mapping(page);
- if (!mapping)
- goto unlock_both;
-
- if (mapping->a_ops->migratepage) {
- /*
- * Most pages have a mapping and most filesystems
- * should provide a migration function. Anonymous
- * pages are part of swap space which also has its
- * own migration function. This is the most common
- * path for page migration.
- */
- rc = mapping->a_ops->migratepage(newpage, page);
- goto unlock_both;
- }
-
- /*
- * Default handling if a filesystem does not provide
- * a migration function. We can only migrate clean
- * pages so try to write out any dirty pages first.
- */
- if (PageDirty(page)) {
- switch (pageout(page, mapping)) {
- case PAGE_KEEP:
- case PAGE_ACTIVATE:
- goto unlock_both;
-
- case PAGE_SUCCESS:
- unlock_page(newpage);
- goto next;
-
- case PAGE_CLEAN:
- ; /* try to migrate the page below */
- }
- }
-
- /*
- * Buffers are managed in a filesystem specific way.
- * We must have no buffers or drop them.
- */
- if (!page_has_buffers(page) ||
- try_to_release_page(page, GFP_KERNEL)) {
- rc = migrate_page(newpage, page);
- goto unlock_both;
- }
-
- /*
- * On early passes with mapped pages simply
- * retry. There may be a lock held for some
- * buffers that may go away. Later
- * swap them out.
- */
- if (pass > 4) {
- /*
- * Persistently unable to drop buffers..... As a
- * measure of last resort we fall back to
- * swap_page().
- */
- unlock_page(newpage);
- newpage = NULL;
- rc = swap_page(page);
- goto next;
- }
-
-unlock_both:
- unlock_page(newpage);
-
-unlock_page:
- unlock_page(page);
-
-next:
- if (rc == -EAGAIN) {
- retry++;
- } else if (rc) {
- /* Permanent failure */
- list_move(&page->lru, failed);
- nr_failed++;
- } else {
- if (newpage) {
- /* Successful migration. Return page to LRU */
- move_to_lru(newpage);
- }
- list_move(&page->lru, moved);
- }
- }
- if (retry && pass++ < 10)
- goto redo;
-
- if (!swapwrite)
- current->flags &= ~PF_SWAPWRITE;
-
- return nr_failed + retry;
-}
-
-/*
- * Isolate one page from the LRU lists and put it on the
- * indicated list with elevated refcount.
- *
- * Result:
- * 0 = page not on LRU list
- * 1 = page removed from LRU list and added to the specified list.
- */
-int isolate_lru_page(struct page *page)
-{
- int ret = 0;
-
- if (PageLRU(page)) {
- struct zone *zone = page_zone(page);
- spin_lock_irq(&zone->lru_lock);
- if (TestClearPageLRU(page)) {
- ret = 1;
- get_page(page);
- if (PageActive(page))
- del_page_from_active_list(zone, page);
- else
- del_page_from_inactive_list(zone, page);
- }
- spin_unlock_irq(&zone->lru_lock);
- }
-
- return ret;
-}
-#endif
-
-/*
- * zone->lru_lock is heavily contended. Some of the functions that
- * shrink the lists perform better by taking out a batch of pages
- * and working on them outside the LRU lock.
- *
- * For pagecache intensive workloads, this function is the hottest
- * spot in the kernel (apart from copy_*_user functions).
- *
- * Appropriate locks must be held before calling this function.
- *
- * @nr_to_scan: The number of pages to look through on the list.
- * @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.
- *
- * returns how many pages were moved onto *@dst.
- */
-static int isolate_lru_pages(int nr_to_scan, struct list_head *src,
- struct list_head *dst, int *scanned)
+static void shrink_active_list(unsigned long nr_pages, struct zone *zone,
+ struct scan_control *sc, int priority)
{
- int nr_taken = 0;
- struct page *page;
- int scan = 0;
-
- while (scan++ < nr_to_scan && !list_empty(src)) {
- page = lru_to_page(src);
- prefetchw_prev_lru_page(page, src, flags);
-
- if (!TestClearPageLRU(page))
- BUG();
- list_del(&page->lru);
- if (get_page_testone(page)) {
- /*
- * It is being freed elsewhere
- */
- __put_page(page);
- SetPageLRU(page);
- list_add(&page->lru, src);
- continue;
- } else {
- list_add(&page->lru, dst);
- nr_taken++;
- }
- }
-
- *scanned = scan;
- return nr_taken;
-}
-
-/*
- * shrink_cache() adds the number of pages reclaimed to sc->nr_reclaimed
- */
-static void shrink_cache(struct zone *zone, struct scan_control *sc)
-{
- LIST_HEAD(page_list);
- struct pagevec pvec;
- int max_scan = sc->nr_to_scan;
-
- pagevec_init(&pvec, 1);
-
- lru_add_drain();
- spin_lock_irq(&zone->lru_lock);
- while (max_scan > 0) {
- struct page *page;
- int nr_taken;
- int nr_scan;
- int nr_freed;
-
- nr_taken = isolate_lru_pages(sc->swap_cluster_max,
- &zone->inactive_list,
- &page_list, &nr_scan);
- zone->nr_inactive -= nr_taken;
- zone->pages_scanned += nr_scan;
- spin_unlock_irq(&zone->lru_lock);
-
- if (nr_taken == 0)
- goto done;
-
- max_scan -= nr_scan;
- nr_freed = shrink_list(&page_list, sc);
-
- local_irq_disable();
- if (current_is_kswapd()) {
- __mod_page_state_zone(zone, pgscan_kswapd, nr_scan);
- __mod_page_state(kswapd_steal, nr_freed);
- } else
- __mod_page_state_zone(zone, pgscan_direct, nr_scan);
- __mod_page_state_zone(zone, pgsteal, nr_freed);
-
- spin_lock(&zone->lru_lock);
- /*
- * Put back any unfreeable pages.
- */
- while (!list_empty(&page_list)) {
- page = lru_to_page(&page_list);
- if (TestSetPageLRU(page))
- BUG();
- list_del(&page->lru);
- if (PageActive(page))
- add_page_to_active_list(zone, page);
- else
- add_page_to_inactive_list(zone, page);
- if (!pagevec_add(&pvec, page)) {
- spin_unlock_irq(&zone->lru_lock);
- __pagevec_release(&pvec);
- spin_lock_irq(&zone->lru_lock);
- }
- }
- }
- spin_unlock_irq(&zone->lru_lock);
-done:
- pagevec_release(&pvec);
-}
-
-/*
- * 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
- * processes, from rmap.
- *
- * If the pages are mostly unmapped, the processing is fast and it is
- * appropriate to hold zone->lru_lock across the whole operation. But if
- * the pages are mapped, the processing is slow (page_referenced()) so we
- * should drop zone->lru_lock around each page. It's impossible to balance
- * this, so instead we remove the pages from the LRU while processing them.
- * It is safe to rely on PG_active against the non-LRU pages in here because
- * nobody will play with that bit on a non-LRU page.
- *
- * The downside is that we have to touch page->_count against each page.
- * But we had to alter page->flags anyway.
- */
-static void
-refill_inactive_zone(struct zone *zone, struct scan_control *sc)
-{
- int pgmoved;
+ unsigned long pgmoved;
int pgdeactivate = 0;
- int pgscanned;
- int nr_pages = sc->nr_to_scan;
+ unsigned long pgscanned;
LIST_HEAD(l_hold); /* The pages which were snipped off */
LIST_HEAD(l_inactive); /* Pages to go onto the inactive_list */
LIST_HEAD(l_active); /* Pages to go onto the active_list */
struct pagevec pvec;
int reclaim_mapped = 0;
- if (unlikely(sc->may_swap)) {
- long mapped_ratio;
- long distress;
- long swap_tendency;
-
- /*
- * `distress' is a measure of how much trouble we're having
- * reclaiming pages. 0 -> no problems. 100 -> great trouble.
- */
- distress = 100 >> zone->prev_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 = (sc->nr_mapped * 100) / total_memory;
-
- /*
- * 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 + vm_swappiness;
-
- /*
- * Now use this metric to decide whether to start moving mapped
- * memory onto the inactive list.
- */
- if (swap_tendency >= 100)
- 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);
- zone->pages_scanned += pgscanned;
- zone->nr_active -= pgmoved;
+ 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);
while (!list_empty(&l_hold)) {
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;
}
while (!list_empty(&l_inactive)) {
page = lru_to_page(&l_inactive);
prefetchw_prev_lru_page(page, &l_inactive, flags);
- if (TestSetPageLRU(page))
- BUG();
- if (!TestClearPageActive(page))
- BUG();
+ VM_BUG_ON(PageLRU(page));
+ SetPageLRU(page);
+ VM_BUG_ON(!PageActive(page));
+ ClearPageActive(page);
+
list_move(&page->lru, &zone->inactive_list);
+ mem_cgroup_move_lists(page, false);
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);
while (!list_empty(&l_active)) {
page = lru_to_page(&l_active);
prefetchw_prev_lru_page(page, &l_active, flags);
- if (TestSetPageLRU(page))
- BUG();
- BUG_ON(!PageActive(page));
+ 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)) {
- 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;
- spin_unlock(&zone->lru_lock);
+ __mod_zone_page_state(zone, NR_ACTIVE, pgmoved);
- __mod_page_state_zone(zone, pgrefill, pgscanned);
- __mod_page_state(pgdeactivate, pgdeactivate);
- local_irq_enable();
+ __count_zone_vm_events(PGREFILL, zone, pgscanned);
+ __count_vm_events(PGDEACTIVATE, pgdeactivate);
+ spin_unlock_irq(&zone->lru_lock);
pagevec_release(&pvec);
}
/*
* This is a basic per-zone page freer. Used by both kswapd and direct reclaim.
*/
-static void
-shrink_zone(struct zone *zone, struct scan_control *sc)
+static unsigned long shrink_zone(int priority, struct zone *zone,
+ struct scan_control *sc)
{
unsigned long nr_active;
unsigned long nr_inactive;
+ 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;
- /*
- * 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 >> sc->priority) + 1;
- nr_active = zone->nr_scan_active;
- if (nr_active >= sc->swap_cluster_max)
- zone->nr_scan_active = 0;
- else
- nr_active = 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);
+
+ nr_inactive = mem_cgroup_calc_reclaim_inactive(sc->mem_cgroup,
+ zone, priority);
+ }
- zone->nr_scan_inactive += (zone->nr_inactive >> sc->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) {
- sc->nr_to_scan = min(nr_active,
+ nr_to_scan = min(nr_active,
(unsigned long)sc->swap_cluster_max);
- nr_active -= sc->nr_to_scan;
- refill_inactive_zone(zone, sc);
+ nr_active -= nr_to_scan;
+ shrink_active_list(nr_to_scan, zone, sc, priority);
}
if (nr_inactive) {
- sc->nr_to_scan = min(nr_inactive,
+ nr_to_scan = min(nr_inactive,
(unsigned long)sc->swap_cluster_max);
- nr_inactive -= sc->nr_to_scan;
- shrink_cache(zone, sc);
+ nr_inactive -= nr_to_scan;
+ nr_reclaimed += shrink_inactive_list(nr_to_scan, zone,
+ sc);
}
}
- throttle_vm_writeout();
-
- atomic_dec(&zone->reclaim_in_progress);
+ throttle_vm_writeout(sc->gfp_mask);
+ 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 void
-shrink_caches(struct zone **zones, struct scan_control *sc)
+static unsigned long shrink_zones(int priority, struct zone **zones,
+ struct scan_control *sc)
{
+ unsigned long nr_reclaimed = 0;
int i;
+
+ sc->all_unreclaimable = 1;
for (i = 0; zones[i] != NULL; i++) {
struct zone *zone = zones[i];
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(zone, __GFP_HARDWALL))
- continue;
-
- zone->temp_priority = sc->priority;
- if (zone->prev_priority > sc->priority)
- zone->prev_priority = sc->priority;
-
- if (zone->all_unreclaimable && sc->priority != DEF_PRIORITY)
- continue; /* Let kswapd poll it */
+ 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);
+ }
- shrink_zone(zone, sc);
+ nr_reclaimed += shrink_zone(priority, zone, sc);
}
+
+ return nr_reclaimed;
}
/*
* holds filesystem locks which prevent writeout this might not work, and the
* allocation attempt will fail.
*/
-int try_to_free_pages(struct zone **zones, gfp_t gfp_mask)
+static unsigned long do_try_to_free_pages(struct zone **zones, gfp_t gfp_mask,
+ struct scan_control *sc)
{
int priority;
int ret = 0;
- int total_scanned = 0, total_reclaimed = 0;
+ unsigned long total_scanned = 0;
+ unsigned long nr_reclaimed = 0;
struct reclaim_state *reclaim_state = current->reclaim_state;
- struct scan_control sc;
unsigned long lru_pages = 0;
int i;
- sc.gfp_mask = gfp_mask;
- sc.may_writepage = !laptop_mode;
- sc.may_swap = 1;
-
- inc_page_state(allocstall);
-
- 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 (i = 0; zones[i] != NULL; i++) {
+ struct zone *zone = zones[i];
- if (!cpuset_zone_allowed(zone, __GFP_HARDWALL))
- continue;
+ 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--) {
- sc.nr_mapped = read_page_state(nr_mapped);
- sc.nr_scanned = 0;
- sc.nr_reclaimed = 0;
- sc.priority = priority;
- sc.swap_cluster_max = SWAP_CLUSTER_MAX;
+ sc->nr_scanned = 0;
if (!priority)
disable_swap_token();
- shrink_caches(zones, &sc);
- shrink_slab(sc.nr_scanned, gfp_mask, lru_pages);
- if (reclaim_state) {
- sc.nr_reclaimed += reclaim_state->reclaimed_slab;
- reclaim_state->reclaimed_slab = 0;
+ nr_reclaimed += shrink_zones(priority, zones, sc);
+ /*
+ * Don't shrink slabs when reclaiming memory from
+ * over limit cgroups
+ */
+ if (scan_global_lru(sc)) {
+ shrink_slab(sc->nr_scanned, gfp_mask, lru_pages);
+ if (reclaim_state) {
+ nr_reclaimed += reclaim_state->reclaimed_slab;
+ reclaim_state->reclaimed_slab = 0;
+ }
}
- total_scanned += sc.nr_scanned;
- total_reclaimed += sc.nr_reclaimed;
- if (total_reclaimed >= sc.swap_cluster_max) {
+ total_scanned += sc->nr_scanned;
+ if (nr_reclaimed >= sc->swap_cluster_max) {
ret = 1;
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)
- blk_congestion_wait(WRITE, HZ/10);
+ 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 && scan_global_lru(sc))
+ ret = 1;
out:
- for (i = 0; zones[i] != 0; i++) {
- struct zone *zone = zones[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;
- if (!cpuset_zone_allowed(zone, __GFP_HARDWALL))
- continue;
+ if (scan_global_lru(sc)) {
+ for (i = 0; zones[i] != NULL; i++) {
+ struct zone *zone = zones[i];
+
+ if (!cpuset_zone_allowed_hardwall(zone, GFP_KERNEL))
+ continue;
+
+ zone->prev_priority = priority;
+ }
+ } else
+ mem_cgroup_record_reclaim_priority(sc->mem_cgroup, priority);
- zone->prev_priority = zone->temp_priority;
- }
return ret;
}
+unsigned long try_to_free_pages(struct zone **zones, 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(zones, gfp_mask, &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 = {
+ .gfp_mask = gfp_mask,
+ .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 zone **zones;
+ int target_zone = gfp_zone(GFP_HIGHUSER_MOVABLE);
+
+ zones = NODE_DATA(numa_node_id())->node_zonelists[target_zone].zones;
+ if (do_try_to_free_pages(zones, sc.gfp_mask, &sc))
+ return 1;
+ return 0;
+}
+#endif
+
/*
* For kswapd, balance_pgdat() will work across all this node's zones until
* they are all at pages_high.
*
- * If `nr_pages' is non-zero then it is the number of pages which are to be
- * reclaimed, regardless of the zone occupancies. This is a software suspend
- * special.
- *
* Returns the number of pages which were actually freed.
*
* There is special handling here for zones which are full of pinned pages.
* the page allocator fallback scheme to ensure that aging of pages is balanced
* across the zones.
*/
-static int balance_pgdat(pg_data_t *pgdat, int nr_pages, int order)
+static unsigned long balance_pgdat(pg_data_t *pgdat, int order)
{
- int to_free = nr_pages;
int all_zones_ok;
int priority;
int i;
- int total_scanned, total_reclaimed;
+ unsigned long total_scanned;
+ unsigned long nr_reclaimed;
struct reclaim_state *reclaim_state = current->reclaim_state;
- struct scan_control sc;
+ struct scan_control sc = {
+ .gfp_mask = GFP_KERNEL,
+ .may_swap = 1,
+ .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
+ * this zone was successfully refilled to free_pages == pages_high.
+ */
+ int temp_priority[MAX_NR_ZONES];
loop_again:
total_scanned = 0;
- total_reclaimed = 0;
- sc.gfp_mask = GFP_KERNEL;
+ nr_reclaimed = 0;
sc.may_writepage = !laptop_mode;
- sc.may_swap = 1;
- sc.nr_mapped = read_page_state(nr_mapped);
-
- inc_page_state(pageoutrun);
+ 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 */
all_zones_ok = 1;
- if (nr_pages == 0) {
- /*
- * Scan in the highmem->dma direction for the highest
- * zone which needs scanning
- */
- for (i = pgdat->nr_zones - 1; i >= 0; i--) {
- struct zone *zone = pgdat->node_zones + i;
+ /*
+ * Scan in the highmem->dma direction for the highest
+ * zone which needs scanning
+ */
+ for (i = pgdat->nr_zones - 1; i >= 0; i--) {
+ struct zone *zone = pgdat->node_zones + i;
- if (!populated_zone(zone))
- continue;
+ if (!populated_zone(zone))
+ continue;
- if (zone->all_unreclaimable &&
- priority != DEF_PRIORITY)
- continue;
+ 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;
- }
+ if (!zone_watermark_ok(zone, order, zone->pages_high,
+ 0, 0)) {
+ end_zone = i;
+ break;
}
- goto out;
- } else {
- end_zone = pgdat->nr_zones - 1;
}
-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 (nr_pages == 0) { /* Not software suspend */
- 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;
+ if (!zone_watermark_ok(zone, order, zone->pages_high,
+ end_zone, 0))
+ all_zones_ok = 0;
+ temp_priority[i] = priority;
sc.nr_scanned = 0;
- sc.nr_reclaimed = 0;
- sc.priority = priority;
- sc.swap_cluster_max = nr_pages? nr_pages : SWAP_CLUSTER_MAX;
- shrink_zone(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);
- sc.nr_reclaimed += reclaim_state->reclaimed_slab;
- total_reclaimed += sc.nr_reclaimed;
+ 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) * 4)
- 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
* even in laptop mode
*/
if (total_scanned > SWAP_CLUSTER_MAX * 2 &&
- total_scanned > total_reclaimed+total_reclaimed/2)
+ total_scanned > nr_reclaimed + nr_reclaimed / 2)
sc.may_writepage = 1;
}
- if (nr_pages && to_free > total_reclaimed)
- continue; /* swsusp: need to do more work */
if (all_zones_ok)
break; /* kswapd: all done */
/*
* 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
* matches the direct reclaim path behaviour in terms of impact
* on zone->*_priority.
*/
- if ((total_reclaimed >= SWAP_CLUSTER_MAX) && (!nr_pages))
+ if (nr_reclaimed >= SWAP_CLUSTER_MAX)
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;
}
- return total_reclaimed;
+ return nr_reclaimed;
}
/*
};
cpumask_t cpumask;
- daemonize("kswapd%d", pgdat->node_id);
cpumask = node_to_cpumask(pgdat->node_id);
if (!cpus_empty(cpumask))
set_cpus_allowed(tsk, cpumask);
* 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, 0, 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;
#ifdef CONFIG_PM
/*
- * Try to free `nr_pages' of memory, system-wide. Returns the number of freed
- * pages.
+ * Helper function for shrink_all_memory(). Tries to reclaim 'nr_pages' pages
+ * from LRU lists system-wide, for given pass and priority, and returns the
+ * number of reclaimed pages
+ *
+ * For pass > 3 we also try to shrink the LRU lists that contain a few pages
*/
-int shrink_all_memory(int nr_pages)
+static unsigned long shrink_all_zones(unsigned long nr_pages, int prio,
+ int pass, struct scan_control *sc)
{
- pg_data_t *pgdat;
- int nr_to_free = nr_pages;
- int ret = 0;
- struct reclaim_state reclaim_state = {
- .reclaimed_slab = 0,
+ struct zone *zone;
+ unsigned long nr_to_scan, ret = 0;
+
+ for_each_zone(zone) {
+
+ if (!populated_zone(zone))
+ continue;
+
+ 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_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_page_state(zone, NR_ACTIVE));
+ shrink_active_list(nr_to_scan, zone, sc, prio);
+ }
+ }
+
+ 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_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.
+ *
+ * Rather than trying to age LRUs the aim is to preserve the overall
+ * LRU order by reclaiming preferentially
+ * inactive > active > active referenced > active mapped
+ */
+unsigned long shrink_all_memory(unsigned long nr_pages)
+{
+ unsigned long lru_pages, nr_slab;
+ unsigned long ret = 0;
+ int pass;
+ struct reclaim_state reclaim_state;
+ struct scan_control sc = {
+ .gfp_mask = GFP_KERNEL,
+ .may_swap = 0,
+ .swap_cluster_max = nr_pages,
+ .may_writepage = 1,
+ .swappiness = vm_swappiness,
+ .isolate_pages = isolate_pages_global,
};
current->reclaim_state = &reclaim_state;
- for_each_pgdat(pgdat) {
- int freed;
- freed = balance_pgdat(pgdat, nr_to_free, 0);
- ret += freed;
- nr_to_free -= freed;
- if (nr_to_free <= 0)
+
+ 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;
+ shrink_slab(nr_pages, sc.gfp_mask, lru_pages);
+ if (!reclaim_state.reclaimed_slab)
break;
+
+ ret += reclaim_state.reclaimed_slab;
+ if (ret >= nr_pages)
+ goto out;
+
+ nr_slab -= reclaim_state.reclaimed_slab;
+ }
+
+ /*
+ * We try to shrink LRUs in 5 passes:
+ * 0 = Reclaim from inactive_list only
+ * 1 = Reclaim from active list but don't reclaim mapped
+ * 2 = 2nd pass of type 1
+ * 3 = Reclaim mapped (normal reclaim)
+ * 4 = 2nd pass of type 3
+ */
+ for (pass = 0; pass < 5; pass++) {
+ int prio;
+
+ /* Force reclaiming mapped pages in the passes #3 and #4 */
+ if (pass > 2) {
+ sc.may_swap = 1;
+ sc.swappiness = 100;
+ }
+
+ for (prio = DEF_PRIORITY; prio >= 0; prio--) {
+ unsigned long nr_to_scan = nr_pages - ret;
+
+ sc.nr_scanned = 0;
+ ret += shrink_all_zones(nr_to_scan, prio, pass, &sc);
+ if (ret >= nr_pages)
+ goto out;
+
+ reclaim_state.reclaimed_slab = 0;
+ 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)
+ congestion_wait(WRITE, HZ / 10);
+ }
}
+
+ /*
+ * If ret = 0, we could not shrink LRUs, but there may be something
+ * in slab caches
+ */
+ if (!ret) {
+ do {
+ reclaim_state.reclaimed_slab = 0;
+ 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;
+
return ret;
}
#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,
restore their cpu bindings. */
static int __devinit cpu_callback(struct notifier_block *nfb,
- unsigned long action,
- void *hcpu)
+ unsigned long action, void *hcpu)
{
pg_data_t *pgdat;
cpumask_t mask;
+ int nid;
- if (action == CPU_ONLINE) {
- for_each_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.
+ * On node-hot-add, kswapd will moved to proper cpus if cpus are hot-added.
+ */
+int kswapd_run(int nid)
+{
+ pg_data_t *pgdat = NODE_DATA(nid);
+ int ret = 0;
+
+ if (pgdat->kswapd)
+ return 0;
+
+ pgdat->kswapd = kthread_run(kswapd, pgdat, "kswapd%d", nid);
+ if (IS_ERR(pgdat->kswapd)) {
+ /* failure at boot is fatal */
+ BUG_ON(system_state == SYSTEM_BOOTING);
+ printk("Failed to start kswapd on node %d\n",nid);
+ ret = -1;
+ }
+ return ret;
+}
static int __init kswapd_init(void)
{
- pg_data_t *pgdat;
+ int nid;
+
swap_setup();
- for_each_pgdat(pgdat)
- pgdat->kswapd
- = find_task_by_pid(kernel_thread(kswapd, pgdat, CLONE_KERNEL));
- total_memory = nr_free_pagecache_pages();
+ for_each_node_state(nid, N_HIGH_MEMORY)
+ kswapd_run(nid);
hotcpu_notifier(cpu_callback, 0);
return 0;
}
*
* If non-zero call zone_reclaim when the number of free pages falls below
* the watermarks.
- *
- * In the future we may add flags to the mode. However, the page allocator
- * should only have to check that zone_reclaim_mode != 0 before calling
- * zone_reclaim().
*/
int zone_reclaim_mode __read_mostly;
#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 */
-
-/*
- * Mininum time between zone reclaim scans
- */
-int zone_reclaim_interval __read_mostly = 30*HZ;
/*
* Priority for ZONE_RECLAIM. This determines the fraction of pages
#define ZONE_RECLAIM_PRIORITY 4
/*
+ * Percentage of pages in a zone that must be unmapped for zone_reclaim to
+ * occur.
+ */
+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.
*/
-int zone_reclaim(struct zone *zone, gfp_t gfp_mask, unsigned int order)
+static int __zone_reclaim(struct zone *zone, gfp_t gfp_mask, unsigned int order)
{
- int nr_pages;
+ /* Minimum pages needed in order to stay on node */
+ const unsigned long nr_pages = 1 << order;
struct task_struct *p = current;
struct reclaim_state reclaim_state;
- struct scan_control sc;
- cpumask_t mask;
- int node_id;
-
- if (time_before(jiffies,
- zone->last_unsuccessful_zone_reclaim + zone_reclaim_interval))
- return 0;
-
- if (!(gfp_mask & __GFP_WAIT) ||
- zone->all_unreclaimable ||
- atomic_read(&zone->reclaim_in_progress) > 0)
- return 0;
-
- node_id = zone->zone_pgdat->node_id;
- mask = node_to_cpumask(node_id);
- if (!cpus_empty(mask) && node_id != numa_node_id())
- return 0;
-
- sc.may_writepage = !!(zone_reclaim_mode & RECLAIM_WRITE);
- sc.may_swap = !!(zone_reclaim_mode & RECLAIM_SWAP);
- sc.nr_scanned = 0;
- sc.nr_reclaimed = 0;
- sc.priority = ZONE_RECLAIM_PRIORITY + 1;
- sc.nr_mapped = read_page_state(nr_mapped);
- sc.gfp_mask = gfp_mask;
+ int priority;
+ unsigned long nr_reclaimed = 0;
+ struct scan_control sc = {
+ .may_writepage = !!(zone_reclaim_mode & RECLAIM_WRITE),
+ .may_swap = !!(zone_reclaim_mode & RECLAIM_SWAP),
+ .swap_cluster_max = max_t(unsigned long, nr_pages,
+ SWAP_CLUSTER_MAX),
+ .gfp_mask = gfp_mask,
+ .swappiness = vm_swappiness,
+ .isolate_pages = isolate_pages_global,
+ };
+ unsigned long slab_reclaimable;
disable_swap_token();
-
- nr_pages = 1 << order;
- if (nr_pages > SWAP_CLUSTER_MAX)
- sc.swap_cluster_max = nr_pages;
- else
- sc.swap_cluster_max = SWAP_CLUSTER_MAX;
-
cond_resched();
- p->flags |= PF_MEMALLOC;
- 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.
+ * We need to be able to allocate from the reserves for RECLAIM_SWAP
+ * and we also need to be able to write out pages for RECLAIM_WRITE
+ * and RECLAIM_SWAP.
*/
- do {
- sc.priority--;
- shrink_zone(zone, &sc);
+ p->flags |= PF_MEMALLOC | PF_SWAPWRITE;
+ reclaim_state.reclaimed_slab = 0;
+ p->reclaim_state = &reclaim_state;
- } while (sc.nr_reclaimed < nr_pages && sc.priority > 0);
+ 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 (sc.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 the zone. So we just
- * shake the slab and then go offnode for a single allocation.
+ * shrink_slab() does not currently allow us to determine how
+ * 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.
+ */
+ 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.
*/
- shrink_slab(sc.nr_scanned, gfp_mask, order);
- sc.nr_reclaimed = 1; /* Avoid getting the off node timeout */
+ nr_reclaimed += slab_reclaimable -
+ zone_page_state(zone, NR_SLAB_RECLAIMABLE);
}
p->reclaim_state = NULL;
- current->flags &= ~PF_MEMALLOC;
+ current->flags &= ~(PF_MEMALLOC | PF_SWAPWRITE);
+ return nr_reclaimed >= nr_pages;
+}
+
+int zone_reclaim(struct zone *zone, gfp_t gfp_mask, unsigned int order)
+{
+ int node_id;
+ int ret;
- if (sc.nr_reclaimed == 0)
- zone->last_unsuccessful_zone_reclaim = jiffies;
+ /*
+ * 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
+ * thrown out if the zone is overallocated. So we do not reclaim
+ * if less than a specified percentage of the zone is used by
+ * unmapped file backed pages.
+ */
+ if (zone_page_state(zone, NR_FILE_PAGES) -
+ zone_page_state(zone, NR_FILE_MAPPED) <= zone->min_unmapped_pages
+ && zone_page_state(zone, NR_SLAB_RECLAIMABLE)
+ <= zone->min_slab_pages)
+ return 0;
- return sc.nr_reclaimed >= nr_pages;
+ if (zone_is_all_unreclaimable(zone))
+ return 0;
+
+ /*
+ * Do not scan if the allocation should not be delayed.
+ */
+ if (!(gfp_mask & __GFP_WAIT) || (current->flags & PF_MEMALLOC))
+ return 0;
+
+ /*
+ * Only run zone reclaim on the local zone or on zones that do not
+ * have associated processors. This will favor the local processor
+ * over remote processors and spread off node memory allocations
+ * as wide as possible.
+ */
+ 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;
+ ret = __zone_reclaim(zone, gfp_mask, order);
+ zone_clear_flag(zone, ZONE_RECLAIM_LOCKED);
+
+ return ret;
}
#endif
-