#include <linux/freezer.h>
#include <linux/memcontrol.h>
#include <linux/delayacct.h>
+#include <linux/sysctl.h>
#include <asm/tlbflush.h>
#include <asm/div64.h>
/* Incremented by the number of inactive pages that were scanned */
unsigned long nr_scanned;
+ /* Number of pages freed so far during a call to shrink_zones() */
+ unsigned long nr_reclaimed;
+
/* This context's GFP mask */
gfp_t gfp_mask;
int may_writepage;
+ /* Can mapped pages be reclaimed? */
+ int may_unmap;
+
/* Can pages be swapped as part of reclaim? */
int may_swap;
/* Which cgroup do we reclaim from */
struct mem_cgroup *mem_cgroup;
+ /*
+ * Nodemask of nodes allowed by the caller. If NULL, all nodes
+ * are scanned.
+ */
+ nodemask_t *nodemask;
+
/* Pluggable isolate pages callback */
unsigned long (*isolate_pages)(unsigned long nr, struct list_head *dst,
unsigned long *scanned, int order, int mode,
static DECLARE_RWSEM(shrinker_rwsem);
#ifdef CONFIG_CGROUP_MEM_RES_CTLR
-#define scan_global_lru(sc) (!(sc)->mem_cgroup)
+#define scanning_global_lru(sc) (!(sc)->mem_cgroup)
#else
-#define scan_global_lru(sc) (1)
+#define scanning_global_lru(sc) (1)
#endif
+static struct zone_reclaim_stat *get_reclaim_stat(struct zone *zone,
+ struct scan_control *sc)
+{
+ if (!scanning_global_lru(sc))
+ return mem_cgroup_get_reclaim_stat(sc->mem_cgroup, zone);
+
+ return &zone->reclaim_stat;
+}
+
+static unsigned long zone_nr_pages(struct zone *zone, struct scan_control *sc,
+ enum lru_list lru)
+{
+ if (!scanning_global_lru(sc))
+ return mem_cgroup_zone_nr_pages(sc->mem_cgroup, zone, lru);
+
+ return zone_page_state(zone, NR_LRU_BASE + lru);
+}
+
+
/*
* Add a shrinker callback to be called from the vm
*/
do_div(delta, lru_pages + 1);
shrinker->nr += delta;
if (shrinker->nr < 0) {
- printk(KERN_ERR "%s: nr=%ld\n",
- __func__, shrinker->nr);
+ printk(KERN_ERR "shrink_slab: %pF negative objects to "
+ "delete nr=%ld\n",
+ shrinker->shrink, shrinker->nr);
shrinker->nr = max_pass;
}
static inline int is_page_cache_freeable(struct page *page)
{
- return page_count(page) - !!PagePrivate(page) == 2;
+ return page_count(page) - !!page_has_private(page) == 2;
}
static int may_write_to_queue(struct backing_dev_info *bdi)
* Some data journaling orphaned pages can have
* page->mapping == NULL while being dirty with clean buffers.
*/
- if (PagePrivate(page)) {
+ if (page_has_private(page)) {
if (try_to_free_buffers(page)) {
ClearPageDirty(page);
printk("%s: orphaned page\n", __func__);
swp_entry_t swap = { .val = page_private(page) };
__delete_from_swap_cache(page);
spin_unlock_irq(&mapping->tree_lock);
- swap_free(swap);
+ swapcache_free(swap, page);
} else {
__remove_from_page_cache(page);
spin_unlock_irq(&mapping->tree_lock);
+ mem_cgroup_uncharge_cache_page(page);
}
return 1;
return 0;
}
+/**
+ * putback_lru_page - put previously isolated page onto appropriate LRU list
+ * @page: page to be put back to appropriate lru list
+ *
+ * Add previously isolated @page to appropriate LRU list.
+ * Page may still be unevictable for other reasons.
+ *
+ * lru_lock must not be held, interrupts must be enabled.
+ */
+void putback_lru_page(struct page *page)
+{
+ int lru;
+ int active = !!TestClearPageActive(page);
+ int was_unevictable = PageUnevictable(page);
+
+ VM_BUG_ON(PageLRU(page));
+
+redo:
+ ClearPageUnevictable(page);
+
+ if (page_evictable(page, NULL)) {
+ /*
+ * For evictable pages, we can use the cache.
+ * In event of a race, worst case is we end up with an
+ * unevictable page on [in]active list.
+ * We know how to handle that.
+ */
+ lru = active + page_is_file_cache(page);
+ lru_cache_add_lru(page, lru);
+ } else {
+ /*
+ * Put unevictable pages directly on zone's unevictable
+ * list.
+ */
+ lru = LRU_UNEVICTABLE;
+ add_page_to_unevictable_list(page);
+ }
+
+ /*
+ * page's status can change while we move it among lru. If an evictable
+ * page is on unevictable list, it never be freed. To avoid that,
+ * check after we added it to the list, again.
+ */
+ if (lru == LRU_UNEVICTABLE && page_evictable(page, NULL)) {
+ if (!isolate_lru_page(page)) {
+ put_page(page);
+ goto redo;
+ }
+ /* This means someone else dropped this page from LRU
+ * So, it will be freed or putback to LRU again. There is
+ * nothing to do here.
+ */
+ }
+
+ if (was_unevictable && lru != LRU_UNEVICTABLE)
+ count_vm_event(UNEVICTABLE_PGRESCUED);
+ else if (!was_unevictable && lru == LRU_UNEVICTABLE)
+ count_vm_event(UNEVICTABLE_PGCULLED);
+
+ put_page(page); /* drop ref from isolate */
+}
+
/*
* shrink_page_list() returns the number of reclaimed pages
*/
struct pagevec freed_pvec;
int pgactivate = 0;
unsigned long nr_reclaimed = 0;
+ unsigned long vm_flags;
cond_resched();
sc->nr_scanned++;
- if (!sc->may_swap && page_mapped(page))
+ if (unlikely(!page_evictable(page, NULL)))
+ goto cull_mlocked;
+
+ if (!sc->may_unmap && page_mapped(page))
goto keep_locked;
/* Double the slab pressure for mapped and swapcache pages */
goto keep_locked;
}
- referenced = page_referenced(page, 1, sc->mem_cgroup);
- /* In active use or really unfreeable? Activate it. */
+ referenced = page_referenced(page, 1,
+ sc->mem_cgroup, &vm_flags);
+ /*
+ * In active use or really unfreeable? Activate it.
+ * If page which have PG_mlocked lost isoltation race,
+ * try_to_unmap moves it to unevictable list
+ */
if (sc->order <= PAGE_ALLOC_COSTLY_ORDER &&
- referenced && page_mapping_inuse(page))
+ referenced && page_mapping_inuse(page)
+ && !(vm_flags & VM_LOCKED))
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 (!add_to_swap(page, GFP_ATOMIC))
+ if (PageAnon(page) && !PageSwapCache(page)) {
+ if (!(sc->gfp_mask & __GFP_IO))
+ goto keep_locked;
+ if (!add_to_swap(page))
goto activate_locked;
-#endif /* CONFIG_SWAP */
+ may_enter_fs = 1;
+ }
mapping = page_mapping(page);
goto activate_locked;
case SWAP_AGAIN:
goto keep_locked;
+ case SWAP_MLOCK:
+ goto cull_mlocked;
case SWAP_SUCCESS:
; /* try to free the page below */
}
* possible for a page to have PageDirty set, but it is actually
* clean (all its buffers are clean). This happens if the
* buffers were written out directly, with submit_bh(). ext3
- * will do this, as well as the blockdev mapping.
+ * will do this, as well as the blockdev mapping.
* try_to_release_page() will discover that cleanness and will
* drop the buffers and mark the page clean - it can be freed.
*
* process address space (page_count == 1) it can be freed.
* Otherwise, leave the page on the LRU so it is swappable.
*/
- if (PagePrivate(page)) {
+ if (page_has_private(page)) {
if (!try_to_release_page(page, sc->gfp_mask))
goto activate_locked;
if (!mapping && page_count(page) == 1) {
if (!mapping || !__remove_mapping(mapping, page))
goto keep_locked;
- unlock_page(page);
+ /*
+ * At this point, we have no other references and there is
+ * no way to pick any more up (removed from LRU, removed
+ * from pagecache). Can use non-atomic bitops now (and
+ * we obviously don't have to worry about waking up a process
+ * waiting on the page lock, because there are no references.
+ */
+ __clear_page_locked(page);
free_it:
nr_reclaimed++;
if (!pagevec_add(&freed_pvec, page)) {
}
continue;
+cull_mlocked:
+ if (PageSwapCache(page))
+ try_to_free_swap(page);
+ unlock_page(page);
+ putback_lru_page(page);
+ continue;
+
activate_locked:
/* Not a candidate for swapping, so reclaim swap space. */
if (PageSwapCache(page) && vm_swap_full())
- remove_exclusive_swap_page_ref(page);
+ try_to_free_swap(page);
+ VM_BUG_ON(PageActive(page));
SetPageActive(page);
pgactivate++;
keep_locked:
unlock_page(page);
keep:
list_add(&page->lru, &ret_pages);
- VM_BUG_ON(PageLRU(page));
+ VM_BUG_ON(PageLRU(page) || PageUnevictable(page));
}
list_splice(&ret_pages, page_list);
if (pagevec_count(&freed_pvec))
if (mode != ISOLATE_BOTH && (!page_is_file_cache(page) != !file))
return ret;
+ /*
+ * When this function is being called for lumpy reclaim, we
+ * initially look into all LRU pages, active, inactive and
+ * unevictable; only give shrink_page_list evictable pages.
+ */
+ if (PageUnevictable(page))
+ return ret;
+
ret = -EBUSY;
+
if (likely(get_page_unless_zero(page))) {
/*
* Be careful not to clear PageLRU until after we're
switch (__isolate_lru_page(page, mode, file)) {
case 0:
list_move(&page->lru, dst);
+ mem_cgroup_del_lru(page);
nr_taken++;
break;
case -EBUSY:
/* else it is being freed elsewhere */
list_move(&page->lru, src);
+ mem_cgroup_rotate_lru_list(page, page_lru(page));
continue;
default:
/* 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, file)) {
- case 0:
+ if (__isolate_lru_page(cursor_page, mode, file) == 0) {
list_move(&cursor_page->lru, dst);
+ mem_cgroup_del_lru(cursor_page);
nr_taken++;
scan++;
- break;
-
- case -EBUSY:
- /* else it is being freed elsewhere */
- list_move(&cursor_page->lru, src);
- default:
- break;
}
}
}
* Returns -EBUSY if the page was not on an LRU list.
*
* The returned page will have PageLRU() cleared. If it was found on
- * the active list, it will have PageActive set. That flag may need
- * to be cleared by the caller before letting the page go.
+ * the active list, it will have PageActive set. If it was found on
+ * the unevictable list, it will have the PageUnevictable bit set. That flag
+ * may need to be cleared by the caller before letting the page go.
*
* The vmstat statistic corresponding to the list on which the page was
* found will be decremented.
spin_lock_irq(&zone->lru_lock);
if (PageLRU(page) && get_page_unless_zero(page)) {
- int lru = LRU_BASE;
+ int lru = page_lru(page);
ret = 0;
ClearPageLRU(page);
- lru += page_is_file_cache(page) + !!PageActive(page);
del_page_from_lru_list(zone, page, lru);
}
spin_unlock_irq(&zone->lru_lock);
* of reclaimed pages
*/
static unsigned long shrink_inactive_list(unsigned long max_scan,
- struct zone *zone, struct scan_control *sc, int file)
+ struct zone *zone, struct scan_control *sc,
+ int priority, int file)
{
LIST_HEAD(page_list);
struct pagevec pvec;
unsigned long nr_scanned = 0;
unsigned long nr_reclaimed = 0;
+ struct zone_reclaim_stat *reclaim_stat = get_reclaim_stat(zone, sc);
+ int lumpy_reclaim = 0;
+
+ /*
+ * If we need a large contiguous chunk of memory, or have
+ * trouble getting a small set of contiguous pages, we
+ * will reclaim both active and inactive pages.
+ *
+ * We use the same threshold as pageout congestion_wait below.
+ */
+ if (sc->order > PAGE_ALLOC_COSTLY_ORDER)
+ lumpy_reclaim = 1;
+ else if (sc->order && priority < DEF_PRIORITY - 2)
+ lumpy_reclaim = 1;
pagevec_init(&pvec, 1);
unsigned long nr_freed;
unsigned long nr_active;
unsigned int count[NR_LRU_LISTS] = { 0, };
- int mode = (sc->order > PAGE_ALLOC_COSTLY_ORDER) ?
- ISOLATE_BOTH : ISOLATE_INACTIVE;
+ int mode = lumpy_reclaim ? ISOLATE_BOTH : ISOLATE_INACTIVE;
nr_taken = sc->isolate_pages(sc->swap_cluster_max,
&page_list, &nr_scan, sc->order, mode,
__mod_zone_page_state(zone, NR_INACTIVE_ANON,
-count[LRU_INACTIVE_ANON]);
- if (scan_global_lru(sc)) {
+ if (scanning_global_lru(sc))
zone->pages_scanned += nr_scan;
- zone->recent_scanned[0] += count[LRU_INACTIVE_ANON];
- zone->recent_scanned[0] += count[LRU_ACTIVE_ANON];
- zone->recent_scanned[1] += count[LRU_INACTIVE_FILE];
- zone->recent_scanned[1] += count[LRU_ACTIVE_FILE];
- }
+
+ reclaim_stat->recent_scanned[0] += count[LRU_INACTIVE_ANON];
+ reclaim_stat->recent_scanned[0] += count[LRU_ACTIVE_ANON];
+ reclaim_stat->recent_scanned[1] += count[LRU_INACTIVE_FILE];
+ reclaim_stat->recent_scanned[1] += count[LRU_ACTIVE_FILE];
+
spin_unlock_irq(&zone->lru_lock);
nr_scanned += nr_scan;
* 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);
+ lumpy_reclaim) {
+ congestion_wait(BLK_RW_ASYNC, HZ/10);
/*
* The attempt at page out may have made some
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))
+ } else if (scanning_global_lru(sc))
__count_zone_vm_events(PGSCAN_DIRECT, zone, nr_scan);
__count_zone_vm_events(PGSTEAL, zone, nr_freed);
* Put back any unfreeable pages.
*/
while (!list_empty(&page_list)) {
+ int lru;
page = lru_to_page(&page_list);
VM_BUG_ON(PageLRU(page));
- SetPageLRU(page);
list_del(&page->lru);
- add_page_to_lru_list(zone, page, page_lru(page));
- if (PageActive(page) && scan_global_lru(sc)) {
+ if (unlikely(!page_evictable(page, NULL))) {
+ spin_unlock_irq(&zone->lru_lock);
+ putback_lru_page(page);
+ spin_lock_irq(&zone->lru_lock);
+ continue;
+ }
+ SetPageLRU(page);
+ lru = page_lru(page);
+ add_page_to_lru_list(zone, page, lru);
+ if (PageActive(page)) {
int file = !!page_is_file_cache(page);
- zone->recent_rotated[file]++;
+ reclaim_stat->recent_rotated[file]++;
}
if (!pagevec_add(&pvec, page)) {
spin_unlock_irq(&zone->lru_lock);
zone->prev_priority = priority;
}
-static inline int zone_is_near_oom(struct zone *zone)
-{
- return zone->pages_scanned >= (zone_lru_pages(zone) * 3);
-}
-
/*
* This moves pages from the active list to the inactive list.
*
* But we had to alter page->flags anyway.
*/
+static void move_active_pages_to_lru(struct zone *zone,
+ struct list_head *list,
+ enum lru_list lru)
+{
+ unsigned long pgmoved = 0;
+ struct pagevec pvec;
+ struct page *page;
+
+ pagevec_init(&pvec, 1);
+
+ while (!list_empty(list)) {
+ page = lru_to_page(list);
+ prefetchw_prev_lru_page(page, list, flags);
+
+ VM_BUG_ON(PageLRU(page));
+ SetPageLRU(page);
+
+ VM_BUG_ON(!PageActive(page));
+ if (!is_active_lru(lru))
+ ClearPageActive(page); /* we are de-activating */
+
+ list_move(&page->lru, &zone->lru[lru].list);
+ mem_cgroup_add_lru_list(page, lru);
+ pgmoved++;
+
+ if (!pagevec_add(&pvec, page) || list_empty(list)) {
+ spin_unlock_irq(&zone->lru_lock);
+ if (buffer_heads_over_limit)
+ pagevec_strip(&pvec);
+ __pagevec_release(&pvec);
+ spin_lock_irq(&zone->lru_lock);
+ }
+ }
+ __mod_zone_page_state(zone, NR_LRU_BASE + lru, pgmoved);
+ if (!is_active_lru(lru))
+ __count_vm_events(PGDEACTIVATE, pgmoved);
+}
static void shrink_active_list(unsigned long nr_pages, struct zone *zone,
struct scan_control *sc, int priority, int file)
{
unsigned long pgmoved;
- int pgdeactivate = 0;
unsigned long pgscanned;
+ unsigned long vm_flags;
LIST_HEAD(l_hold); /* The pages which were snipped off */
+ LIST_HEAD(l_active);
LIST_HEAD(l_inactive);
struct page *page;
- struct pagevec pvec;
- enum lru_list lru;
+ struct zone_reclaim_stat *reclaim_stat = get_reclaim_stat(zone, sc);
lru_add_drain();
spin_lock_irq(&zone->lru_lock);
* zone->pages_scanned is used for detect zone's oom
* mem_cgroup remembers nr_scan by itself.
*/
- if (scan_global_lru(sc)) {
+ if (scanning_global_lru(sc)) {
zone->pages_scanned += pgscanned;
- zone->recent_scanned[!!file] += pgmoved;
}
+ reclaim_stat->recent_scanned[!!file] += pgmoved;
+ __count_zone_vm_events(PGREFILL, zone, pgscanned);
if (file)
__mod_zone_page_state(zone, NR_ACTIVE_FILE, -pgmoved);
else
__mod_zone_page_state(zone, NR_ACTIVE_ANON, -pgmoved);
spin_unlock_irq(&zone->lru_lock);
- pgmoved = 0;
+ pgmoved = 0; /* count referenced (mapping) mapped pages */
while (!list_empty(&l_hold)) {
cond_resched();
page = lru_to_page(&l_hold);
list_del(&page->lru);
+ if (unlikely(!page_evictable(page, NULL))) {
+ putback_lru_page(page);
+ continue;
+ }
+
/* page_referenced clears PageReferenced */
if (page_mapping_inuse(page) &&
- page_referenced(page, 0, sc->mem_cgroup))
+ page_referenced(page, 0, sc->mem_cgroup, &vm_flags)) {
pgmoved++;
+ /*
+ * Identify referenced, file-backed active pages and
+ * give them one more trip around the active list. So
+ * that executable code get better chances to stay in
+ * memory under moderate memory pressure. Anon pages
+ * are not likely to be evicted by use-once streaming
+ * IO, plus JVM can create lots of anon VM_EXEC pages,
+ * so we ignore them here.
+ */
+ if ((vm_flags & VM_EXEC) && !PageAnon(page)) {
+ list_add(&page->lru, &l_active);
+ continue;
+ }
+ }
list_add(&page->lru, &l_inactive);
}
/*
- * Count referenced pages from currently used mappings as
- * rotated, even though they are moved to the inactive list.
- * This helps balance scan pressure between file and anonymous
- * pages in get_scan_ratio.
+ * Move pages back to the lru list.
*/
- zone->recent_rotated[!!file] += pgmoved;
-
+ spin_lock_irq(&zone->lru_lock);
/*
- * Move the pages to the [file or anon] inactive list.
+ * Count referenced pages from currently used mappings as rotated,
+ * even though only some of them are actually re-activated. This
+ * helps balance scan pressure between file and anonymous pages in
+ * get_scan_ratio.
*/
- pagevec_init(&pvec, 1);
+ reclaim_stat->recent_rotated[!!file] += pgmoved;
- pgmoved = 0;
- lru = LRU_BASE + file * LRU_FILE;
- spin_lock_irq(&zone->lru_lock);
- while (!list_empty(&l_inactive)) {
- page = lru_to_page(&l_inactive);
- prefetchw_prev_lru_page(page, &l_inactive, flags);
- VM_BUG_ON(PageLRU(page));
- SetPageLRU(page);
- VM_BUG_ON(!PageActive(page));
- ClearPageActive(page);
+ move_active_pages_to_lru(zone, &l_active,
+ LRU_ACTIVE + file * LRU_FILE);
+ move_active_pages_to_lru(zone, &l_inactive,
+ LRU_BASE + file * LRU_FILE);
- list_move(&page->lru, &zone->lru[lru].list);
- mem_cgroup_move_lists(page, false);
- pgmoved++;
- if (!pagevec_add(&pvec, page)) {
- __mod_zone_page_state(zone, NR_LRU_BASE + lru, pgmoved);
- spin_unlock_irq(&zone->lru_lock);
- pgdeactivate += pgmoved;
- pgmoved = 0;
- if (buffer_heads_over_limit)
- pagevec_strip(&pvec);
- __pagevec_release(&pvec);
- spin_lock_irq(&zone->lru_lock);
- }
- }
- __mod_zone_page_state(zone, NR_LRU_BASE + lru, pgmoved);
- pgdeactivate += pgmoved;
- if (buffer_heads_over_limit) {
- spin_unlock_irq(&zone->lru_lock);
- pagevec_strip(&pvec);
- spin_lock_irq(&zone->lru_lock);
- }
- __count_zone_vm_events(PGREFILL, zone, pgscanned);
- __count_vm_events(PGDEACTIVATE, pgdeactivate);
spin_unlock_irq(&zone->lru_lock);
- if (vm_swap_full())
- pagevec_swap_free(&pvec);
+}
- pagevec_release(&pvec);
+static int inactive_anon_is_low_global(struct zone *zone)
+{
+ unsigned long active, inactive;
+
+ active = zone_page_state(zone, NR_ACTIVE_ANON);
+ inactive = zone_page_state(zone, NR_INACTIVE_ANON);
+
+ if (inactive * zone->inactive_ratio < active)
+ return 1;
+
+ return 0;
+}
+
+/**
+ * inactive_anon_is_low - check if anonymous pages need to be deactivated
+ * @zone: zone to check
+ * @sc: scan control of this context
+ *
+ * Returns true if the zone does not have enough inactive anon pages,
+ * meaning some active anon pages need to be deactivated.
+ */
+static int inactive_anon_is_low(struct zone *zone, struct scan_control *sc)
+{
+ int low;
+
+ if (scanning_global_lru(sc))
+ low = inactive_anon_is_low_global(zone);
+ else
+ low = mem_cgroup_inactive_anon_is_low(sc->mem_cgroup);
+ return low;
+}
+
+static int inactive_file_is_low_global(struct zone *zone)
+{
+ unsigned long active, inactive;
+
+ active = zone_page_state(zone, NR_ACTIVE_FILE);
+ inactive = zone_page_state(zone, NR_INACTIVE_FILE);
+
+ return (active > inactive);
+}
+
+/**
+ * inactive_file_is_low - check if file pages need to be deactivated
+ * @zone: zone to check
+ * @sc: scan control of this context
+ *
+ * When the system is doing streaming IO, memory pressure here
+ * ensures that active file pages get deactivated, until more
+ * than half of the file pages are on the inactive list.
+ *
+ * Once we get to that situation, protect the system's working
+ * set from being evicted by disabling active file page aging.
+ *
+ * This uses a different ratio than the anonymous pages, because
+ * the page cache uses a use-once replacement algorithm.
+ */
+static int inactive_file_is_low(struct zone *zone, struct scan_control *sc)
+{
+ int low;
+
+ if (scanning_global_lru(sc))
+ low = inactive_file_is_low_global(zone);
+ else
+ low = mem_cgroup_inactive_file_is_low(sc->mem_cgroup);
+ return low;
}
static unsigned long shrink_list(enum lru_list lru, unsigned long nr_to_scan,
{
int file = is_file_lru(lru);
- if (lru == LRU_ACTIVE_FILE) {
+ if (lru == LRU_ACTIVE_FILE && inactive_file_is_low(zone, sc)) {
shrink_active_list(nr_to_scan, zone, sc, priority, file);
return 0;
}
- if (lru == LRU_ACTIVE_ANON &&
- (!scan_global_lru(sc) || inactive_anon_is_low(zone))) {
+ if (lru == LRU_ACTIVE_ANON && inactive_anon_is_low(zone, sc)) {
shrink_active_list(nr_to_scan, zone, sc, priority, file);
return 0;
}
- return shrink_inactive_list(nr_to_scan, zone, sc, file);
+ return shrink_inactive_list(nr_to_scan, zone, sc, priority, file);
}
/*
unsigned long anon, file, free;
unsigned long anon_prio, file_prio;
unsigned long ap, fp;
-
- anon = zone_page_state(zone, NR_ACTIVE_ANON) +
- zone_page_state(zone, NR_INACTIVE_ANON);
- file = zone_page_state(zone, NR_ACTIVE_FILE) +
- zone_page_state(zone, NR_INACTIVE_FILE);
- free = zone_page_state(zone, NR_FREE_PAGES);
-
- /* If we have no swap space, do not bother scanning anon pages. */
- if (nr_swap_pages <= 0) {
- percent[0] = 0;
- percent[1] = 100;
- return;
- }
-
- /* If we have very few page cache pages, force-scan anon pages. */
- if (unlikely(file + free <= zone->pages_high)) {
- percent[0] = 100;
- percent[1] = 0;
- return;
+ struct zone_reclaim_stat *reclaim_stat = get_reclaim_stat(zone, sc);
+
+ anon = zone_nr_pages(zone, sc, LRU_ACTIVE_ANON) +
+ zone_nr_pages(zone, sc, LRU_INACTIVE_ANON);
+ file = zone_nr_pages(zone, sc, LRU_ACTIVE_FILE) +
+ zone_nr_pages(zone, sc, LRU_INACTIVE_FILE);
+
+ if (scanning_global_lru(sc)) {
+ free = zone_page_state(zone, NR_FREE_PAGES);
+ /* If we have very few page cache pages,
+ force-scan anon pages. */
+ if (unlikely(file + free <= high_wmark_pages(zone))) {
+ percent[0] = 100;
+ percent[1] = 0;
+ return;
+ }
}
/*
*
* anon in [0], file in [1]
*/
- if (unlikely(zone->recent_scanned[0] > anon / 4)) {
+ if (unlikely(reclaim_stat->recent_scanned[0] > anon / 4)) {
spin_lock_irq(&zone->lru_lock);
- zone->recent_scanned[0] /= 2;
- zone->recent_rotated[0] /= 2;
+ reclaim_stat->recent_scanned[0] /= 2;
+ reclaim_stat->recent_rotated[0] /= 2;
spin_unlock_irq(&zone->lru_lock);
}
- if (unlikely(zone->recent_scanned[1] > file / 4)) {
+ if (unlikely(reclaim_stat->recent_scanned[1] > file / 4)) {
spin_lock_irq(&zone->lru_lock);
- zone->recent_scanned[1] /= 2;
- zone->recent_rotated[1] /= 2;
+ reclaim_stat->recent_scanned[1] /= 2;
+ reclaim_stat->recent_rotated[1] /= 2;
spin_unlock_irq(&zone->lru_lock);
}
file_prio = 200 - sc->swappiness;
/*
- * anon recent_rotated[0]
- * %anon = 100 * ----------- / ----------------- * IO cost
- * anon + file rotate_sum
+ * The amount of pressure on anon vs file pages is inversely
+ * proportional to the fraction of recently scanned pages on
+ * each list that were recently referenced and in active use.
*/
- ap = (anon_prio + 1) * (zone->recent_scanned[0] + 1);
- ap /= zone->recent_rotated[0] + 1;
+ ap = (anon_prio + 1) * (reclaim_stat->recent_scanned[0] + 1);
+ ap /= reclaim_stat->recent_rotated[0] + 1;
- fp = (file_prio + 1) * (zone->recent_scanned[1] + 1);
- fp /= zone->recent_rotated[1] + 1;
+ fp = (file_prio + 1) * (reclaim_stat->recent_scanned[1] + 1);
+ fp /= reclaim_stat->recent_rotated[1] + 1;
/* Normalize to percentages */
percent[0] = 100 * ap / (ap + fp + 1);
percent[1] = 100 - percent[0];
}
+/*
+ * Smallish @nr_to_scan's are deposited in @nr_saved_scan,
+ * until we collected @swap_cluster_max pages to scan.
+ */
+static unsigned long nr_scan_try_batch(unsigned long nr_to_scan,
+ unsigned long *nr_saved_scan,
+ unsigned long swap_cluster_max)
+{
+ unsigned long nr;
+
+ *nr_saved_scan += nr_to_scan;
+ nr = *nr_saved_scan;
+
+ if (nr >= swap_cluster_max)
+ *nr_saved_scan = 0;
+ else
+ nr = 0;
+
+ return nr;
+}
/*
* This is a basic per-zone page freer. Used by both kswapd and direct reclaim.
*/
-static unsigned long shrink_zone(int priority, struct zone *zone,
+static void shrink_zone(int priority, struct zone *zone,
struct scan_control *sc)
{
unsigned long nr[NR_LRU_LISTS];
unsigned long nr_to_scan;
- unsigned long nr_reclaimed = 0;
unsigned long percent[2]; /* anon @ 0; file @ 1 */
enum lru_list l;
+ unsigned long nr_reclaimed = sc->nr_reclaimed;
+ unsigned long swap_cluster_max = sc->swap_cluster_max;
+ int noswap = 0;
- get_scan_ratio(zone, sc, percent);
+ /* If we have no swap space, do not bother scanning anon pages. */
+ if (!sc->may_swap || (nr_swap_pages <= 0)) {
+ noswap = 1;
+ percent[0] = 0;
+ percent[1] = 100;
+ } else
+ get_scan_ratio(zone, sc, percent);
- for_each_lru(l) {
- if (scan_global_lru(sc)) {
- int file = is_file_lru(l);
- int scan;
- /*
- * Add one to nr_to_scan just to make sure that the
- * kernel will slowly sift through each list.
- */
- scan = zone_page_state(zone, NR_LRU_BASE + l);
- if (priority) {
- scan >>= priority;
- scan = (scan * percent[file]) / 100;
- }
- zone->lru[l].nr_scan += scan + 1;
- nr[l] = zone->lru[l].nr_scan;
- if (nr[l] >= sc->swap_cluster_max)
- zone->lru[l].nr_scan = 0;
- else
- nr[l] = 0;
- } else {
- /*
- * This reclaim occurs not because zone memory shortage
- * but because memory controller hits its limit.
- * Don't modify zone reclaim related data.
- */
- nr[l] = mem_cgroup_calc_reclaim(sc->mem_cgroup, zone,
- priority, l);
+ for_each_evictable_lru(l) {
+ int file = is_file_lru(l);
+ unsigned long scan;
+
+ scan = zone_nr_pages(zone, sc, l);
+ if (priority || noswap) {
+ scan >>= priority;
+ scan = (scan * percent[file]) / 100;
}
+ if (scanning_global_lru(sc))
+ nr[l] = nr_scan_try_batch(scan,
+ &zone->lru[l].nr_saved_scan,
+ swap_cluster_max);
+ else
+ nr[l] = scan;
}
while (nr[LRU_INACTIVE_ANON] || nr[LRU_ACTIVE_FILE] ||
nr[LRU_INACTIVE_FILE]) {
- for_each_lru(l) {
+ for_each_evictable_lru(l) {
if (nr[l]) {
- nr_to_scan = min(nr[l],
- (unsigned long)sc->swap_cluster_max);
+ nr_to_scan = min(nr[l], swap_cluster_max);
nr[l] -= nr_to_scan;
nr_reclaimed += shrink_list(l, nr_to_scan,
- zone, sc, priority);
+ zone, sc, priority);
}
}
+ /*
+ * On large memory systems, scan >> priority can become
+ * really large. This is fine for the starting priority;
+ * we want to put equal scanning pressure on each zone.
+ * However, if the VM has a harder time of freeing pages,
+ * with multiple processes reclaiming pages, the total
+ * freeing target can get unreasonably large.
+ */
+ if (nr_reclaimed > swap_cluster_max &&
+ priority < DEF_PRIORITY && !current_is_kswapd())
+ break;
}
+ sc->nr_reclaimed = nr_reclaimed;
+
/*
* Even if we did not try to evict anon pages at all, we want to
* rebalance the anon lru active/inactive ratio.
*/
- if (!scan_global_lru(sc) || inactive_anon_is_low(zone))
- shrink_active_list(SWAP_CLUSTER_MAX, zone, sc, priority, 0);
- else if (!scan_global_lru(sc))
+ if (inactive_anon_is_low(zone, sc) && nr_swap_pages > 0)
shrink_active_list(SWAP_CLUSTER_MAX, zone, sc, priority, 0);
throttle_vm_writeout(sc->gfp_mask);
- return nr_reclaimed;
}
/*
* try to reclaim pages from zones which will satisfy the caller's allocation
* request.
*
- * We reclaim from a zone even if that zone is over pages_high. Because:
+ * We reclaim from a zone even if that zone is over high_wmark_pages(zone).
+ * Because:
* a) The caller may be trying to free *extra* pages to satisfy a higher-order
* allocation or
- * b) The zones may be over pages_high but they must go *over* pages_high to
- * satisfy the `incremental min' zone defense algorithm.
- *
- * Returns the number of reclaimed pages.
+ * b) The target zone may be at high_wmark_pages(zone) but the lower zones
+ * must go *over* high_wmark_pages(zone) to satisfy the `incremental min'
+ * zone defense algorithm.
*
* If a zone is deemed to be full of pinned pages then just give it a light
* scan then give up on it.
*/
-static unsigned long shrink_zones(int priority, struct zonelist *zonelist,
+static void shrink_zones(int priority, struct zonelist *zonelist,
struct scan_control *sc)
{
enum zone_type high_zoneidx = gfp_zone(sc->gfp_mask);
- unsigned long nr_reclaimed = 0;
struct zoneref *z;
struct zone *zone;
sc->all_unreclaimable = 1;
- for_each_zone_zonelist(zone, z, zonelist, high_zoneidx) {
+ for_each_zone_zonelist_nodemask(zone, z, zonelist, high_zoneidx,
+ sc->nodemask) {
if (!populated_zone(zone))
continue;
/*
* Take care memory controller reclaiming has small influence
* to global LRU.
*/
- if (scan_global_lru(sc)) {
+ if (scanning_global_lru(sc)) {
if (!cpuset_zone_allowed_hardwall(zone, GFP_KERNEL))
continue;
note_zone_scanning_priority(zone, priority);
priority);
}
- nr_reclaimed += shrink_zone(priority, zone, sc);
+ shrink_zone(priority, zone, sc);
}
-
- return nr_reclaimed;
}
/*
int priority;
unsigned long ret = 0;
unsigned long total_scanned = 0;
- unsigned long nr_reclaimed = 0;
struct reclaim_state *reclaim_state = current->reclaim_state;
unsigned long lru_pages = 0;
struct zoneref *z;
delayacct_freepages_start();
- if (scan_global_lru(sc))
+ if (scanning_global_lru(sc))
count_vm_event(ALLOCSTALL);
/*
* mem_cgroup will not do shrink_slab.
*/
- if (scan_global_lru(sc)) {
+ if (scanning_global_lru(sc)) {
for_each_zone_zonelist(zone, z, zonelist, high_zoneidx) {
if (!cpuset_zone_allowed_hardwall(zone, GFP_KERNEL))
sc->nr_scanned = 0;
if (!priority)
disable_swap_token();
- nr_reclaimed += shrink_zones(priority, zonelist, sc);
+ shrink_zones(priority, zonelist, sc);
/*
* Don't shrink slabs when reclaiming memory from
* over limit cgroups
*/
- if (scan_global_lru(sc)) {
+ if (scanning_global_lru(sc)) {
shrink_slab(sc->nr_scanned, sc->gfp_mask, lru_pages);
if (reclaim_state) {
- nr_reclaimed += reclaim_state->reclaimed_slab;
+ sc->nr_reclaimed += reclaim_state->reclaimed_slab;
reclaim_state->reclaimed_slab = 0;
}
}
total_scanned += sc->nr_scanned;
- if (nr_reclaimed >= sc->swap_cluster_max) {
- ret = nr_reclaimed;
+ if (sc->nr_reclaimed >= sc->swap_cluster_max) {
+ ret = sc->nr_reclaimed;
goto out;
}
*/
if (total_scanned > sc->swap_cluster_max +
sc->swap_cluster_max / 2) {
- wakeup_pdflush(laptop_mode ? 0 : total_scanned);
+ wakeup_flusher_threads(laptop_mode ? 0 : total_scanned);
sc->may_writepage = 1;
}
/* Take a nap, wait for some writeback to complete */
if (sc->nr_scanned && priority < DEF_PRIORITY - 2)
- congestion_wait(WRITE, HZ/10);
+ congestion_wait(BLK_RW_ASYNC, HZ/10);
}
/* top priority shrink_zones still had more to do? don't OOM, then */
- if (!sc->all_unreclaimable && scan_global_lru(sc))
- ret = nr_reclaimed;
+ if (!sc->all_unreclaimable && scanning_global_lru(sc))
+ ret = sc->nr_reclaimed;
out:
/*
* Now that we've scanned all the zones at this priority level, note
if (priority < 0)
priority = 0;
- if (scan_global_lru(sc)) {
+ if (scanning_global_lru(sc)) {
for_each_zone_zonelist(zone, z, zonelist, high_zoneidx) {
if (!cpuset_zone_allowed_hardwall(zone, GFP_KERNEL))
}
unsigned long try_to_free_pages(struct zonelist *zonelist, int order,
- gfp_t gfp_mask)
+ gfp_t gfp_mask, nodemask_t *nodemask)
{
struct scan_control sc = {
.gfp_mask = gfp_mask,
.may_writepage = !laptop_mode,
.swap_cluster_max = SWAP_CLUSTER_MAX,
+ .may_unmap = 1,
.may_swap = 1,
.swappiness = vm_swappiness,
.order = order,
.mem_cgroup = NULL,
.isolate_pages = isolate_pages_global,
+ .nodemask = nodemask,
};
return do_try_to_free_pages(zonelist, &sc);
#ifdef CONFIG_CGROUP_MEM_RES_CTLR
unsigned long try_to_free_mem_cgroup_pages(struct mem_cgroup *mem_cont,
- gfp_t gfp_mask)
+ gfp_t gfp_mask,
+ bool noswap,
+ unsigned int swappiness)
{
struct scan_control sc = {
.may_writepage = !laptop_mode,
- .may_swap = 1,
+ .may_unmap = 1,
+ .may_swap = !noswap,
.swap_cluster_max = SWAP_CLUSTER_MAX,
- .swappiness = vm_swappiness,
+ .swappiness = swappiness,
.order = 0,
.mem_cgroup = mem_cont,
.isolate_pages = mem_cgroup_isolate_pages,
+ .nodemask = NULL, /* we don't care the placement */
};
struct zonelist *zonelist;
/*
* For kswapd, balance_pgdat() will work across all this node's zones until
- * they are all at pages_high.
+ * they are all at high_wmark_pages(zone).
*
* Returns the number of pages which were actually freed.
*
* the zone for when the problem goes away.
*
* kswapd scans the zones in the highmem->normal->dma direction. It skips
- * zones which have free_pages > pages_high, but once a zone is found to have
- * free_pages <= pages_high, we scan that zone and the lower zones regardless
- * of the number of free pages in the lower zones. This interoperates with
- * the page allocator fallback scheme to ensure that aging of pages is balanced
- * across the zones.
+ * zones which have free_pages > high_wmark_pages(zone), but once a zone is
+ * found to have free_pages <= high_wmark_pages(zone), we scan that zone and the
+ * lower zones regardless of the number of free pages in the lower zones. This
+ * interoperates with the page allocator fallback scheme to ensure that aging
+ * of pages is balanced across the zones.
*/
static unsigned long balance_pgdat(pg_data_t *pgdat, int order)
{
int priority;
int i;
unsigned long total_scanned;
- unsigned long nr_reclaimed;
struct reclaim_state *reclaim_state = current->reclaim_state;
struct scan_control sc = {
.gfp_mask = GFP_KERNEL,
+ .may_unmap = 1,
.may_swap = 1,
.swap_cluster_max = SWAP_CLUSTER_MAX,
.swappiness = vm_swappiness,
};
/*
* temp_priority is used to remember the scanning priority at which
- * this zone was successfully refilled to free_pages == pages_high.
+ * this zone was successfully refilled to
+ * free_pages == high_wmark_pages(zone).
*/
int temp_priority[MAX_NR_ZONES];
loop_again:
total_scanned = 0;
- nr_reclaimed = 0;
+ sc.nr_reclaimed = 0;
sc.may_writepage = !laptop_mode;
count_vm_event(PAGEOUTRUN);
* Do some background aging of the anon list, to give
* pages a chance to be referenced before reclaiming.
*/
- if (inactive_anon_is_low(zone))
+ if (inactive_anon_is_low(zone, &sc))
shrink_active_list(SWAP_CLUSTER_MAX, zone,
&sc, priority, 0);
- if (!zone_watermark_ok(zone, order, zone->pages_high,
- 0, 0)) {
+ if (!zone_watermark_ok(zone, order,
+ high_wmark_pages(zone), 0, 0)) {
end_zone = i;
break;
}
priority != DEF_PRIORITY)
continue;
- if (!zone_watermark_ok(zone, order, zone->pages_high,
- end_zone, 0))
+ if (!zone_watermark_ok(zone, order,
+ high_wmark_pages(zone), end_zone, 0))
all_zones_ok = 0;
temp_priority[i] = priority;
sc.nr_scanned = 0;
* 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);
+ if (!zone_watermark_ok(zone, order,
+ 8*high_wmark_pages(zone), end_zone, 0))
+ 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;
+ sc.nr_reclaimed += reclaim_state->reclaimed_slab;
total_scanned += sc.nr_scanned;
if (zone_is_all_unreclaimable(zone))
continue;
* even in laptop mode
*/
if (total_scanned > SWAP_CLUSTER_MAX * 2 &&
- total_scanned > nr_reclaimed + nr_reclaimed / 2)
+ total_scanned > sc.nr_reclaimed + sc.nr_reclaimed / 2)
sc.may_writepage = 1;
}
if (all_zones_ok)
* another pass across the zones.
*/
if (total_scanned && priority < DEF_PRIORITY - 2)
- congestion_wait(WRITE, HZ/10);
+ congestion_wait(BLK_RW_ASYNC, 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 (nr_reclaimed >= SWAP_CLUSTER_MAX)
+ if (sc.nr_reclaimed >= SWAP_CLUSTER_MAX)
break;
}
out:
try_to_freeze();
+ /*
+ * Fragmentation may mean that the system cannot be
+ * rebalanced for high-order allocations in all zones.
+ * At this point, if nr_reclaimed < SWAP_CLUSTER_MAX,
+ * it means the zones have been fully scanned and are still
+ * not balanced. For high-order allocations, there is
+ * little point trying all over again as kswapd may
+ * infinite loop.
+ *
+ * Instead, recheck all watermarks at order-0 as they
+ * are the most important. If watermarks are ok, kswapd will go
+ * back to sleep. High-order users can still perform direct
+ * reclaim if they wish.
+ */
+ if (sc.nr_reclaimed < SWAP_CLUSTER_MAX)
+ order = sc.order = 0;
+
goto loop_again;
}
- return nr_reclaimed;
+ return sc.nr_reclaimed;
}
/*
struct reclaim_state reclaim_state = {
.reclaimed_slab = 0,
};
- node_to_cpumask_ptr(cpumask, pgdat->node_id);
+ const struct cpumask *cpumask = cpumask_of_node(pgdat->node_id);
+
+ lockdep_set_current_reclaim_state(GFP_KERNEL);
- if (!cpus_empty(*cpumask))
+ if (!cpumask_empty(cpumask))
set_cpus_allowed_ptr(tsk, cpumask);
current->reclaim_state = &reclaim_state;
return;
pgdat = zone->zone_pgdat;
- if (zone_watermark_ok(zone, order, zone->pages_low, 0, 0))
+ if (zone_watermark_ok(zone, order, low_wmark_pages(zone), 0, 0))
return;
if (pgdat->kswapd_max_order < order)
pgdat->kswapd_max_order = order;
+ global_page_state(NR_INACTIVE_FILE);
}
-#ifdef CONFIG_PM
+#ifdef CONFIG_HIBERNATION
/*
* 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
+ * from LRU lists system-wide, for given pass and priority.
*
* 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 prio,
+static void 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;
- enum lru_list l;
-
- for_each_zone(zone) {
+ unsigned long nr_reclaimed = 0;
- if (!populated_zone(zone))
- continue;
+ for_each_populated_zone(zone) {
+ enum lru_list l;
if (zone_is_all_unreclaimable(zone) && prio != DEF_PRIORITY)
continue;
- for_each_lru(l) {
- /* For pass = 0 we don't shrink the active list */
- if (pass == 0 &&
- (l == LRU_ACTIVE || l == LRU_ACTIVE_FILE))
+ for_each_evictable_lru(l) {
+ enum zone_stat_item ls = NR_LRU_BASE + l;
+ unsigned long lru_pages = zone_page_state(zone, ls);
+
+ /* For pass = 0, we don't shrink the active list */
+ if (pass == 0 && (l == LRU_ACTIVE_ANON ||
+ l == LRU_ACTIVE_FILE))
continue;
- zone->lru[l].nr_scan +=
- (zone_page_state(zone, NR_LRU_BASE + l)
- >> prio) + 1;
- if (zone->lru[l].nr_scan >= nr_pages || pass > 3) {
- zone->lru[l].nr_scan = 0;
- nr_to_scan = min(nr_pages,
- zone_page_state(zone,
- NR_LRU_BASE + l));
- ret += shrink_list(l, nr_to_scan, zone,
+ zone->lru[l].nr_saved_scan += (lru_pages >> prio) + 1;
+ if (zone->lru[l].nr_saved_scan >= nr_pages || pass > 3) {
+ unsigned long nr_to_scan;
+
+ zone->lru[l].nr_saved_scan = 0;
+ nr_to_scan = min(nr_pages, lru_pages);
+ nr_reclaimed += shrink_list(l, nr_to_scan, zone,
sc, prio);
- if (ret >= nr_pages)
- return ret;
+ if (nr_reclaimed >= nr_pages) {
+ sc->nr_reclaimed += nr_reclaimed;
+ return;
+ }
}
}
}
-
- return ret;
+ sc->nr_reclaimed += nr_reclaimed;
}
/*
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_unmap = 0,
.may_writepage = 1,
- .swappiness = vm_swappiness,
.isolate_pages = isolate_pages_global,
+ .nr_reclaimed = 0,
};
current->reclaim_state = &reclaim_state;
if (!reclaim_state.reclaimed_slab)
break;
- ret += reclaim_state.reclaimed_slab;
- if (ret >= nr_pages)
+ sc.nr_reclaimed += reclaim_state.reclaimed_slab;
+ if (sc.nr_reclaimed >= nr_pages)
goto out;
nr_slab -= reclaim_state.reclaimed_slab;
int prio;
/* Force reclaiming mapped pages in the passes #3 and #4 */
- if (pass > 2) {
- sc.may_swap = 1;
- sc.swappiness = 100;
- }
+ if (pass > 2)
+ sc.may_unmap = 1;
for (prio = DEF_PRIORITY; prio >= 0; prio--) {
- unsigned long nr_to_scan = nr_pages - ret;
+ unsigned long nr_to_scan = nr_pages - sc.nr_reclaimed;
sc.nr_scanned = 0;
- ret += shrink_all_zones(nr_to_scan, prio, pass, &sc);
- if (ret >= nr_pages)
+ sc.swap_cluster_max = nr_to_scan;
+ shrink_all_zones(nr_to_scan, prio, pass, &sc);
+ if (sc.nr_reclaimed >= nr_pages)
goto out;
reclaim_state.reclaimed_slab = 0;
shrink_slab(sc.nr_scanned, sc.gfp_mask,
global_lru_pages());
- ret += reclaim_state.reclaimed_slab;
- if (ret >= nr_pages)
+ sc.nr_reclaimed += reclaim_state.reclaimed_slab;
+ if (sc.nr_reclaimed >= nr_pages)
goto out;
if (sc.nr_scanned && prio < DEF_PRIORITY - 2)
- congestion_wait(WRITE, HZ / 10);
+ congestion_wait(BLK_RW_ASYNC, HZ / 10);
}
}
/*
- * If ret = 0, we could not shrink LRUs, but there may be something
- * in slab caches
+ * If sc.nr_reclaimed = 0, we could not shrink LRUs, but there may be
+ * something in slab caches
*/
- if (!ret) {
+ if (!sc.nr_reclaimed) {
do {
reclaim_state.reclaimed_slab = 0;
shrink_slab(nr_pages, sc.gfp_mask, global_lru_pages());
- ret += reclaim_state.reclaimed_slab;
- } while (ret < nr_pages && reclaim_state.reclaimed_slab > 0);
+ sc.nr_reclaimed += reclaim_state.reclaimed_slab;
+ } while (sc.nr_reclaimed < nr_pages &&
+ reclaim_state.reclaimed_slab > 0);
}
+
out:
current->reclaim_state = NULL;
- return ret;
+ return sc.nr_reclaimed;
}
-#endif
+#endif /* CONFIG_HIBERNATION */
/* 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
if (action == CPU_ONLINE || action == CPU_ONLINE_FROZEN) {
for_each_node_state(nid, N_HIGH_MEMORY) {
pg_data_t *pgdat = NODE_DATA(nid);
- node_to_cpumask_ptr(mask, pgdat->node_id);
+ const struct cpumask *mask;
- if (any_online_cpu(*mask) < nr_cpu_ids)
+ mask = cpumask_of_node(pgdat->node_id);
+
+ if (cpumask_any_and(cpu_online_mask, mask) < nr_cpu_ids)
/* One of our CPUs online: restore mask */
set_cpus_allowed_ptr(pgdat->kswapd, mask);
}
*/
int sysctl_min_slab_ratio = 5;
+static inline unsigned long zone_unmapped_file_pages(struct zone *zone)
+{
+ unsigned long file_mapped = zone_page_state(zone, NR_FILE_MAPPED);
+ unsigned long file_lru = zone_page_state(zone, NR_INACTIVE_FILE) +
+ zone_page_state(zone, NR_ACTIVE_FILE);
+
+ /*
+ * It's possible for there to be more file mapped pages than
+ * accounted for by the pages on the file LRU lists because
+ * tmpfs pages accounted for as ANON can also be FILE_MAPPED
+ */
+ return (file_lru > file_mapped) ? (file_lru - file_mapped) : 0;
+}
+
+/* Work out how many page cache pages we can reclaim in this reclaim_mode */
+static long zone_pagecache_reclaimable(struct zone *zone)
+{
+ long nr_pagecache_reclaimable;
+ long delta = 0;
+
+ /*
+ * If RECLAIM_SWAP is set, then all file pages are considered
+ * potentially reclaimable. Otherwise, we have to worry about
+ * pages like swapcache and zone_unmapped_file_pages() provides
+ * a better estimate
+ */
+ if (zone_reclaim_mode & RECLAIM_SWAP)
+ nr_pagecache_reclaimable = zone_page_state(zone, NR_FILE_PAGES);
+ else
+ nr_pagecache_reclaimable = zone_unmapped_file_pages(zone);
+
+ /* If we can't clean pages, remove dirty pages from consideration */
+ if (!(zone_reclaim_mode & RECLAIM_WRITE))
+ delta += zone_page_state(zone, NR_FILE_DIRTY);
+
+ /* Watch for any possible underflows due to delta */
+ if (unlikely(delta > nr_pagecache_reclaimable))
+ delta = nr_pagecache_reclaimable;
+
+ return nr_pagecache_reclaimable - delta;
+}
+
/*
* Try to free up some pages from this zone through reclaim.
*/
struct task_struct *p = current;
struct reclaim_state reclaim_state;
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),
+ .may_unmap = !!(zone_reclaim_mode & RECLAIM_SWAP),
+ .may_swap = 1,
.swap_cluster_max = max_t(unsigned long, nr_pages,
SWAP_CLUSTER_MAX),
.gfp_mask = gfp_mask,
.swappiness = vm_swappiness,
+ .order = order,
.isolate_pages = isolate_pages_global,
};
unsigned long slab_reclaimable;
reclaim_state.reclaimed_slab = 0;
p->reclaim_state = &reclaim_state;
- if (zone_page_state(zone, NR_FILE_PAGES) -
- zone_page_state(zone, NR_FILE_MAPPED) >
- zone->min_unmapped_pages) {
+ if (zone_pagecache_reclaimable(zone) > 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);
+ shrink_zone(priority, zone, &sc);
priority--;
- } while (priority >= 0 && nr_reclaimed < nr_pages);
+ } while (priority >= 0 && sc.nr_reclaimed < nr_pages);
}
slab_reclaimable = zone_page_state(zone, NR_SLAB_RECLAIMABLE);
* Update nr_reclaimed by the number of slab pages we
* reclaimed from this zone.
*/
- nr_reclaimed += slab_reclaimable -
+ sc.nr_reclaimed += slab_reclaimable -
zone_page_state(zone, NR_SLAB_RECLAIMABLE);
}
p->reclaim_state = NULL;
current->flags &= ~(PF_MEMALLOC | PF_SWAPWRITE);
- return nr_reclaimed >= nr_pages;
+ return sc.nr_reclaimed >= nr_pages;
}
int zone_reclaim(struct zone *zone, gfp_t gfp_mask, unsigned int order)
* 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;
+ if (zone_pagecache_reclaimable(zone) <= zone->min_unmapped_pages &&
+ zone_page_state(zone, NR_SLAB_RECLAIMABLE) <= zone->min_slab_pages)
+ return ZONE_RECLAIM_FULL;
if (zone_is_all_unreclaimable(zone))
- return 0;
+ return ZONE_RECLAIM_FULL;
/*
* Do not scan if the allocation should not be delayed.
*/
if (!(gfp_mask & __GFP_WAIT) || (current->flags & PF_MEMALLOC))
- return 0;
+ return ZONE_RECLAIM_NOSCAN;
/*
* Only run zone reclaim on the local zone or on zones that do not
*/
node_id = zone_to_nid(zone);
if (node_state(node_id, N_CPU) && node_id != numa_node_id())
- return 0;
+ return ZONE_RECLAIM_NOSCAN;
if (zone_test_and_set_flag(zone, ZONE_RECLAIM_LOCKED))
- return 0;
+ return ZONE_RECLAIM_NOSCAN;
+
ret = __zone_reclaim(zone, gfp_mask, order);
zone_clear_flag(zone, ZONE_RECLAIM_LOCKED);
+ if (!ret)
+ count_vm_event(PGSCAN_ZONE_RECLAIM_FAILED);
+
return ret;
}
#endif
+
+/*
+ * page_evictable - test whether a page is evictable
+ * @page: the page to test
+ * @vma: the VMA in which the page is or will be mapped, may be NULL
+ *
+ * Test whether page is evictable--i.e., should be placed on active/inactive
+ * lists vs unevictable list. The vma argument is !NULL when called from the
+ * fault path to determine how to instantate a new page.
+ *
+ * Reasons page might not be evictable:
+ * (1) page's mapping marked unevictable
+ * (2) page is part of an mlocked VMA
+ *
+ */
+int page_evictable(struct page *page, struct vm_area_struct *vma)
+{
+
+ if (mapping_unevictable(page_mapping(page)))
+ return 0;
+
+ if (PageMlocked(page) || (vma && is_mlocked_vma(vma, page)))
+ return 0;
+
+ return 1;
+}
+
+/**
+ * check_move_unevictable_page - check page for evictability and move to appropriate zone lru list
+ * @page: page to check evictability and move to appropriate lru list
+ * @zone: zone page is in
+ *
+ * Checks a page for evictability and moves the page to the appropriate
+ * zone lru list.
+ *
+ * Restrictions: zone->lru_lock must be held, page must be on LRU and must
+ * have PageUnevictable set.
+ */
+static void check_move_unevictable_page(struct page *page, struct zone *zone)
+{
+ VM_BUG_ON(PageActive(page));
+
+retry:
+ ClearPageUnevictable(page);
+ if (page_evictable(page, NULL)) {
+ enum lru_list l = LRU_INACTIVE_ANON + page_is_file_cache(page);
+
+ __dec_zone_state(zone, NR_UNEVICTABLE);
+ list_move(&page->lru, &zone->lru[l].list);
+ mem_cgroup_move_lists(page, LRU_UNEVICTABLE, l);
+ __inc_zone_state(zone, NR_INACTIVE_ANON + l);
+ __count_vm_event(UNEVICTABLE_PGRESCUED);
+ } else {
+ /*
+ * rotate unevictable list
+ */
+ SetPageUnevictable(page);
+ list_move(&page->lru, &zone->lru[LRU_UNEVICTABLE].list);
+ mem_cgroup_rotate_lru_list(page, LRU_UNEVICTABLE);
+ if (page_evictable(page, NULL))
+ goto retry;
+ }
+}
+
+/**
+ * scan_mapping_unevictable_pages - scan an address space for evictable pages
+ * @mapping: struct address_space to scan for evictable pages
+ *
+ * Scan all pages in mapping. Check unevictable pages for
+ * evictability and move them to the appropriate zone lru list.
+ */
+void scan_mapping_unevictable_pages(struct address_space *mapping)
+{
+ pgoff_t next = 0;
+ pgoff_t end = (i_size_read(mapping->host) + PAGE_CACHE_SIZE - 1) >>
+ PAGE_CACHE_SHIFT;
+ struct zone *zone;
+ struct pagevec pvec;
+
+ if (mapping->nrpages == 0)
+ return;
+
+ pagevec_init(&pvec, 0);
+ while (next < end &&
+ pagevec_lookup(&pvec, mapping, next, PAGEVEC_SIZE)) {
+ int i;
+ int pg_scanned = 0;
+
+ zone = NULL;
+
+ for (i = 0; i < pagevec_count(&pvec); i++) {
+ struct page *page = pvec.pages[i];
+ pgoff_t page_index = page->index;
+ struct zone *pagezone = page_zone(page);
+
+ pg_scanned++;
+ if (page_index > next)
+ next = page_index;
+ next++;
+
+ if (pagezone != zone) {
+ if (zone)
+ spin_unlock_irq(&zone->lru_lock);
+ zone = pagezone;
+ spin_lock_irq(&zone->lru_lock);
+ }
+
+ if (PageLRU(page) && PageUnevictable(page))
+ check_move_unevictable_page(page, zone);
+ }
+ if (zone)
+ spin_unlock_irq(&zone->lru_lock);
+ pagevec_release(&pvec);
+
+ count_vm_events(UNEVICTABLE_PGSCANNED, pg_scanned);
+ }
+
+}
+
+/**
+ * scan_zone_unevictable_pages - check unevictable list for evictable pages
+ * @zone - zone of which to scan the unevictable list
+ *
+ * Scan @zone's unevictable LRU lists to check for pages that have become
+ * evictable. Move those that have to @zone's inactive list where they
+ * become candidates for reclaim, unless shrink_inactive_zone() decides
+ * to reactivate them. Pages that are still unevictable are rotated
+ * back onto @zone's unevictable list.
+ */
+#define SCAN_UNEVICTABLE_BATCH_SIZE 16UL /* arbitrary lock hold batch size */
+static void scan_zone_unevictable_pages(struct zone *zone)
+{
+ struct list_head *l_unevictable = &zone->lru[LRU_UNEVICTABLE].list;
+ unsigned long scan;
+ unsigned long nr_to_scan = zone_page_state(zone, NR_UNEVICTABLE);
+
+ while (nr_to_scan > 0) {
+ unsigned long batch_size = min(nr_to_scan,
+ SCAN_UNEVICTABLE_BATCH_SIZE);
+
+ spin_lock_irq(&zone->lru_lock);
+ for (scan = 0; scan < batch_size; scan++) {
+ struct page *page = lru_to_page(l_unevictable);
+
+ if (!trylock_page(page))
+ continue;
+
+ prefetchw_prev_lru_page(page, l_unevictable, flags);
+
+ if (likely(PageLRU(page) && PageUnevictable(page)))
+ check_move_unevictable_page(page, zone);
+
+ unlock_page(page);
+ }
+ spin_unlock_irq(&zone->lru_lock);
+
+ nr_to_scan -= batch_size;
+ }
+}
+
+
+/**
+ * scan_all_zones_unevictable_pages - scan all unevictable lists for evictable pages
+ *
+ * A really big hammer: scan all zones' unevictable LRU lists to check for
+ * pages that have become evictable. Move those back to the zones'
+ * inactive list where they become candidates for reclaim.
+ * This occurs when, e.g., we have unswappable pages on the unevictable lists,
+ * and we add swap to the system. As such, it runs in the context of a task
+ * that has possibly/probably made some previously unevictable pages
+ * evictable.
+ */
+static void scan_all_zones_unevictable_pages(void)
+{
+ struct zone *zone;
+
+ for_each_zone(zone) {
+ scan_zone_unevictable_pages(zone);
+ }
+}
+
+/*
+ * scan_unevictable_pages [vm] sysctl handler. On demand re-scan of
+ * all nodes' unevictable lists for evictable pages
+ */
+unsigned long scan_unevictable_pages;
+
+int scan_unevictable_handler(struct ctl_table *table, int write,
+ struct file *file, void __user *buffer,
+ size_t *length, loff_t *ppos)
+{
+ proc_doulongvec_minmax(table, write, file, buffer, length, ppos);
+
+ if (write && *(unsigned long *)table->data)
+ scan_all_zones_unevictable_pages();
+
+ scan_unevictable_pages = 0;
+ return 0;
+}
+
+/*
+ * per node 'scan_unevictable_pages' attribute. On demand re-scan of
+ * a specified node's per zone unevictable lists for evictable pages.
+ */
+
+static ssize_t read_scan_unevictable_node(struct sys_device *dev,
+ struct sysdev_attribute *attr,
+ char *buf)
+{
+ return sprintf(buf, "0\n"); /* always zero; should fit... */
+}
+
+static ssize_t write_scan_unevictable_node(struct sys_device *dev,
+ struct sysdev_attribute *attr,
+ const char *buf, size_t count)
+{
+ struct zone *node_zones = NODE_DATA(dev->id)->node_zones;
+ struct zone *zone;
+ unsigned long res;
+ unsigned long req = strict_strtoul(buf, 10, &res);
+
+ if (!req)
+ return 1; /* zero is no-op */
+
+ for (zone = node_zones; zone - node_zones < MAX_NR_ZONES; ++zone) {
+ if (!populated_zone(zone))
+ continue;
+ scan_zone_unevictable_pages(zone);
+ }
+ return 1;
+}
+
+
+static SYSDEV_ATTR(scan_unevictable_pages, S_IRUGO | S_IWUSR,
+ read_scan_unevictable_node,
+ write_scan_unevictable_node);
+
+int scan_unevictable_register_node(struct node *node)
+{
+ return sysdev_create_file(&node->sysdev, &attr_scan_unevictable_pages);
+}
+
+void scan_unevictable_unregister_node(struct node *node)
+{
+ sysdev_remove_file(&node->sysdev, &attr_scan_unevictable_pages);
+}
+