#include <linux/delay.h>
#include <linux/kthread.h>
#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 pages be swapped as part of reclaim? */
- int may_swap;
+ /* Can mapped pages be reclaimed? */
+ int may_unmap;
/* This context's SWAP_CLUSTER_MAX. If freeing memory for
* suspend, we effectively ignore SWAP_CLUSTER_MAX.
int all_unreclaimable;
int order;
+
+ /* 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,
+ struct zone *z, struct mem_cgroup *mem_cont,
+ int active, int file);
};
#define lru_to_page(_head) (list_entry((_head)->prev, struct page, lru))
static LIST_HEAD(shrinker_list);
static DECLARE_RWSEM(shrinker_rwsem);
+#ifdef CONFIG_CGROUP_MEM_RES_CTLR
+#define scanning_global_lru(sc) (!(sc)->mem_cgroup)
+#else
+#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",
- __FUNCTION__, shrinker->nr);
+ printk(KERN_ERR "shrink_slab: %pF negative objects to "
+ "delete nr=%ld\n",
+ shrinker->shrink, shrinker->nr);
shrinker->nr = max_pass;
}
if (PagePrivate(page)) {
if (try_to_free_buffers(page)) {
ClearPageDirty(page);
- printk("%s: orphaned page\n", __FUNCTION__);
+ printk("%s: orphaned page\n", __func__);
return PAGE_CLEAN;
}
}
}
/*
- * Attempt to detach a locked page from its ->mapping. If it is dirty or if
- * someone else has a ref on the page, abort and return 0. If it was
- * successfully detached, return 1. Assumes the caller has a single ref on
- * this page.
+ * Same as remove_mapping, but if the page is removed from the mapping, it
+ * gets returned with a refcount of 0.
*/
-int remove_mapping(struct address_space *mapping, struct page *page)
+static int __remove_mapping(struct address_space *mapping, struct page *page)
{
BUG_ON(!PageLocked(page));
BUG_ON(mapping != page_mapping(page));
- write_lock_irq(&mapping->tree_lock);
+ spin_lock_irq(&mapping->tree_lock);
/*
* The non racy check for a busy page.
*
* Note that if SetPageDirty is always performed via set_page_dirty,
* and thus under tree_lock, then this ordering is not required.
*/
- if (unlikely(page_count(page) != 2))
+ if (!page_freeze_refs(page, 2))
goto cannot_free;
- smp_rmb();
- if (unlikely(PageDirty(page)))
+ /* note: atomic_cmpxchg in page_freeze_refs provides the smp_rmb */
+ if (unlikely(PageDirty(page))) {
+ page_unfreeze_refs(page, 2);
goto cannot_free;
+ }
if (PageSwapCache(page)) {
swp_entry_t swap = { .val = page_private(page) };
__delete_from_swap_cache(page);
- write_unlock_irq(&mapping->tree_lock);
+ spin_unlock_irq(&mapping->tree_lock);
swap_free(swap);
- __put_page(page); /* The pagecache ref */
- return 1;
+ } else {
+ __remove_from_page_cache(page);
+ spin_unlock_irq(&mapping->tree_lock);
}
- __remove_from_page_cache(page);
- write_unlock_irq(&mapping->tree_lock);
- __put_page(page);
return 1;
cannot_free:
- write_unlock_irq(&mapping->tree_lock);
+ spin_unlock_irq(&mapping->tree_lock);
return 0;
}
+/*
+ * Attempt to detach a locked page from its ->mapping. If it is dirty or if
+ * someone else has a ref on the page, abort and return 0. If it was
+ * successfully detached, return 1. Assumes the caller has a single ref on
+ * this page.
+ */
+int remove_mapping(struct address_space *mapping, struct page *page)
+{
+ if (__remove_mapping(mapping, page)) {
+ /*
+ * Unfreezing the refcount with 1 rather than 2 effectively
+ * drops the pagecache ref for us without requiring another
+ * atomic operation.
+ */
+ page_unfreeze_refs(page, 1);
+ return 1;
+ }
+ return 0;
+}
+
+/**
+ * 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.
+ */
+#ifdef CONFIG_UNEVICTABLE_LRU
+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 */
+}
+
+#else /* CONFIG_UNEVICTABLE_LRU */
+
+void putback_lru_page(struct page *page)
+{
+ int lru;
+ VM_BUG_ON(PageLRU(page));
+
+ lru = !!TestClearPageActive(page) + page_is_file_cache(page);
+ lru_cache_add_lru(page, lru);
+ put_page(page);
+}
+#endif /* CONFIG_UNEVICTABLE_LRU */
+
+
/*
* shrink_page_list() returns the number of reclaimed pages
*/
page = lru_to_page(page_list);
list_del(&page->lru);
- if (TestSetPageLocked(page))
+ if (!trylock_page(page))
goto keep;
VM_BUG_ON(PageActive(page));
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);
+ referenced = page_referenced(page, 1, sc->mem_cgroup);
/* In active use or really unfreeable? Activate it. */
if (sc->order <= PAGE_ALLOC_COSTLY_ORDER &&
referenced && page_mapping_inuse(page))
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 */
}
* A synchronous write - probably a ramdisk. Go
* ahead and try to reclaim the page.
*/
- if (TestSetPageLocked(page))
+ if (!trylock_page(page))
goto keep;
if (PageDirty(page) || PageWriteback(page))
goto keep_locked;
* 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.
*
if (PagePrivate(page)) {
if (!try_to_release_page(page, sc->gfp_mask))
goto activate_locked;
- if (!mapping && page_count(page) == 1)
- goto free_it;
+ if (!mapping && page_count(page) == 1) {
+ unlock_page(page);
+ if (put_page_testzero(page))
+ goto free_it;
+ else {
+ /*
+ * rare race with speculative reference.
+ * the speculative reference will free
+ * this page shortly, so we may
+ * increment nr_reclaimed here (and
+ * leave it off the LRU).
+ */
+ nr_reclaimed++;
+ continue;
+ }
+ }
}
- if (!mapping || !remove_mapping(mapping, page))
+ if (!mapping || !__remove_mapping(mapping, page))
goto keep_locked;
+ /*
+ * 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:
- unlock_page(page);
nr_reclaimed++;
- if (!pagevec_add(&freed_pvec, page))
- __pagevec_release_nonlru(&freed_pvec);
+ if (!pagevec_add(&freed_pvec, page)) {
+ __pagevec_free(&freed_pvec);
+ pagevec_reinit(&freed_pvec);
+ }
+ continue;
+
+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())
+ 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))
- __pagevec_release_nonlru(&freed_pvec);
+ __pagevec_free(&freed_pvec);
count_vm_events(PGACTIVATE, pgactivate);
return nr_reclaimed;
}
*
* returns 0 on success, -ve errno on failure.
*/
-static int __isolate_lru_page(struct page *page, int mode)
+int __isolate_lru_page(struct page *page, int mode, int file)
{
int ret = -EINVAL;
if (mode != ISOLATE_BOTH && (!PageActive(page) != !mode))
return ret;
+ 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
*/
ClearPageLRU(page);
ret = 0;
+ mem_cgroup_del_lru(page);
}
return ret;
* @scanned: The number of pages that were scanned.
* @order: The caller's attempted allocation order
* @mode: One of the LRU isolation modes
+ * @file: True [1] if isolating file [!anon] pages
*
* returns how many pages were moved onto *@dst.
*/
static unsigned long isolate_lru_pages(unsigned long nr_to_scan,
struct list_head *src, struct list_head *dst,
- unsigned long *scanned, int order, int mode)
+ unsigned long *scanned, int order, int mode, int file)
{
unsigned long nr_taken = 0;
unsigned long scan;
VM_BUG_ON(!PageLRU(page));
- switch (__isolate_lru_page(page, mode)) {
+ switch (__isolate_lru_page(page, mode, file)) {
case 0:
list_move(&page->lru, dst);
nr_taken++;
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)) {
+ switch (__isolate_lru_page(cursor_page, mode, file)) {
case 0:
list_move(&cursor_page->lru, dst);
nr_taken++;
/* else it is being freed elsewhere */
list_move(&cursor_page->lru, src);
default:
- break;
+ break; /* ! on LRU or wrong list */
}
}
}
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, int file)
+{
+ int lru = LRU_BASE;
+ if (active)
+ lru += LRU_ACTIVE;
+ if (file)
+ lru += LRU_FILE;
+ return isolate_lru_pages(nr, &z->lru[lru].list, dst, scanned, order,
+ mode, !!file);
+}
+
/*
* clear_active_flags() is a helper for shrink_active_list(), clearing
* any active bits from the pages in the list.
*/
-static unsigned long clear_active_flags(struct list_head *page_list)
+static unsigned long clear_active_flags(struct list_head *page_list,
+ unsigned int *count)
{
int nr_active = 0;
+ int lru;
struct page *page;
- list_for_each_entry(page, page_list, lru)
+ list_for_each_entry(page, page_list, lru) {
+ lru = page_is_file_cache(page);
if (PageActive(page)) {
+ lru += LRU_ACTIVE;
ClearPageActive(page);
nr_active++;
}
+ count[lru]++;
+ }
return nr_active;
}
+/**
+ * isolate_lru_page - tries to isolate a page from its LRU list
+ * @page: page to isolate from its LRU list
+ *
+ * Isolates a @page from an LRU list, clears PageLRU and adjusts the
+ * vmstat statistic corresponding to whatever LRU list the page was on.
+ *
+ * Returns 0 if the page was removed from an LRU list.
+ * 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. 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.
+ *
+ * Restrictions:
+ * (1) Must be called with an elevated refcount on the page. This is a
+ * fundamentnal difference from isolate_lru_pages (which is called
+ * without a stable reference).
+ * (2) the lru_lock must not be held.
+ * (3) interrupts must be enabled.
+ */
+int isolate_lru_page(struct page *page)
+{
+ int ret = -EBUSY;
+
+ if (PageLRU(page)) {
+ struct zone *zone = page_zone(page);
+
+ spin_lock_irq(&zone->lru_lock);
+ if (PageLRU(page) && get_page_unless_zero(page)) {
+ int lru = page_lru(page);
+ ret = 0;
+ ClearPageLRU(page);
+
+ del_page_from_lru_list(zone, page, lru);
+ }
+ spin_unlock_irq(&zone->lru_lock);
+ }
+ return ret;
+}
+
/*
* shrink_inactive_list() is a helper for shrink_zone(). It returns the number
* of reclaimed pages
*/
static unsigned long shrink_inactive_list(unsigned long max_scan,
- struct zone *zone, struct scan_control *sc)
+ 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);
pagevec_init(&pvec, 1);
unsigned long nr_scan;
unsigned long nr_freed;
unsigned long nr_active;
+ unsigned int count[NR_LRU_LISTS] = { 0, };
+ int mode = ISOLATE_INACTIVE;
- nr_taken = isolate_lru_pages(sc->swap_cluster_max,
- &zone->inactive_list,
- &page_list, &nr_scan, sc->order,
- (sc->order > PAGE_ALLOC_COSTLY_ORDER)?
- ISOLATE_BOTH : ISOLATE_INACTIVE);
- nr_active = clear_active_flags(&page_list);
+ /*
+ * 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)
+ mode = ISOLATE_BOTH;
+ else if (sc->order && priority < DEF_PRIORITY - 2)
+ mode = ISOLATE_BOTH;
+
+ nr_taken = sc->isolate_pages(sc->swap_cluster_max,
+ &page_list, &nr_scan, sc->order, mode,
+ zone, sc->mem_cgroup, 0, file);
+ nr_active = clear_active_flags(&page_list, count);
__count_vm_events(PGDEACTIVATE, nr_active);
- __mod_zone_page_state(zone, NR_ACTIVE, -nr_active);
- __mod_zone_page_state(zone, NR_INACTIVE,
- -(nr_taken - nr_active));
- zone->pages_scanned += nr_scan;
+ __mod_zone_page_state(zone, NR_ACTIVE_FILE,
+ -count[LRU_ACTIVE_FILE]);
+ __mod_zone_page_state(zone, NR_INACTIVE_FILE,
+ -count[LRU_INACTIVE_FILE]);
+ __mod_zone_page_state(zone, NR_ACTIVE_ANON,
+ -count[LRU_ACTIVE_ANON]);
+ __mod_zone_page_state(zone, NR_INACTIVE_ANON,
+ -count[LRU_INACTIVE_ANON]);
+
+ if (scanning_global_lru(sc))
+ zone->pages_scanned += nr_scan;
+
+ 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;
* The attempt at page out may have made some
* of the pages active, mark them inactive again.
*/
- nr_active = clear_active_flags(&page_list);
+ nr_active = clear_active_flags(&page_list, count);
count_vm_events(PGDEACTIVATE, nr_active);
nr_freed += shrink_page_list(&page_list, sc,
if (current_is_kswapd()) {
__count_zone_vm_events(PGSCAN_KSWAPD, zone, nr_scan);
__count_vm_events(KSWAPD_STEAL, nr_freed);
- } else
+ } else if (scanning_global_lru(sc))
__count_zone_vm_events(PGSCAN_DIRECT, zone, nr_scan);
+
__count_zone_vm_events(PGSTEAL, zone, nr_freed);
if (nr_taken == 0)
* 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);
- if (PageActive(page))
- add_page_to_active_list(zone, page);
- else
- add_page_to_inactive_list(zone, page);
+ 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);
+ reclaim_stat->recent_rotated[file]++;
+ }
if (!pagevec_add(&pvec, page)) {
spin_unlock_irq(&zone->lru_lock);
__pagevec_release(&pvec);
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;
-}
-
/*
* This moves pages from the active list to the inactive list.
*
* The downside is that we have to touch page->_count against each page.
* But we had to alter page->flags anyway.
*/
+
+
static void shrink_active_list(unsigned long nr_pages, struct zone *zone,
- struct scan_control *sc, int priority)
+ struct scan_control *sc, int priority, int file)
{
unsigned long pgmoved;
int pgdeactivate = 0;
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 */
+ LIST_HEAD(l_inactive);
struct page *page;
struct pagevec pvec;
- int reclaim_mapped = 0;
-
- if (sc->may_swap) {
- long mapped_ratio;
- long distress;
- long swap_tendency;
- long imbalance;
-
- if (zone_is_near_oom(zone))
- goto force_reclaim_mapped;
-
- /*
- * `distress' is a measure of how much trouble we're having
- * reclaiming pages. 0 -> no problems. 100 -> great trouble.
- */
- distress = 100 >> min(zone->prev_priority, priority);
-
- /*
- * The point of this algorithm is to decide when to start
- * reclaiming mapped memory instead of just pagecache. Work out
- * how much memory
- * is mapped.
- */
- mapped_ratio = ((global_page_state(NR_FILE_MAPPED) +
- global_page_state(NR_ANON_PAGES)) * 100) /
- vm_total_pages;
-
- /*
- * Now decide how much we really want to unmap some pages. The
- * mapped ratio is downgraded - just because there's a lot of
- * mapped memory doesn't necessarily mean that page reclaim
- * isn't succeeding.
- *
- * The distress ratio is important - we don't want to start
- * going oom.
- *
- * A 100% value of vm_swappiness overrides this algorithm
- * altogether.
- */
- swap_tendency = mapped_ratio / 2 + distress + sc->swappiness;
-
- /*
- * If there's huge imbalance between active and inactive
- * (think active 100 times larger than inactive) we should
- * become more permissive, or the system will take too much
- * cpu before it start swapping during memory pressure.
- * Distress is about avoiding early-oom, this is about
- * making swappiness graceful despite setting it to low
- * values.
- *
- * Avoid div by zero with nr_inactive+1, and max resulting
- * value is vm_total_pages.
- */
- imbalance = zone_page_state(zone, NR_ACTIVE);
- imbalance /= zone_page_state(zone, NR_INACTIVE) + 1;
-
- /*
- * Reduce the effect of imbalance if swappiness is low,
- * this means for a swappiness very low, the imbalance
- * must be much higher than 100 for this logic to make
- * the difference.
- *
- * Max temporary value is vm_total_pages*100.
- */
- imbalance *= (vm_swappiness + 1);
- imbalance /= 100;
-
- /*
- * If not much of the ram is mapped, makes the imbalance
- * less relevant, it's high priority we refill the inactive
- * list with mapped pages only in presence of high ratio of
- * mapped pages.
- *
- * Max temporary value is vm_total_pages*100.
- */
- imbalance *= mapped_ratio;
- imbalance /= 100;
-
- /* apply imbalance feedback to swap_tendency */
- swap_tendency += imbalance;
-
- /*
- * Now use this metric to decide whether to start moving mapped
- * memory onto the inactive list.
- */
- if (swap_tendency >= 100)
-force_reclaim_mapped:
- reclaim_mapped = 1;
- }
+ enum lru_list lru;
+ struct zone_reclaim_stat *reclaim_stat = get_reclaim_stat(zone, sc);
lru_add_drain();
spin_lock_irq(&zone->lru_lock);
- pgmoved = isolate_lru_pages(nr_pages, &zone->active_list,
- &l_hold, &pgscanned, sc->order, ISOLATE_ACTIVE);
- zone->pages_scanned += pgscanned;
- __mod_zone_page_state(zone, NR_ACTIVE, -pgmoved);
+ pgmoved = sc->isolate_pages(nr_pages, &l_hold, &pgscanned, sc->order,
+ ISOLATE_ACTIVE, zone,
+ sc->mem_cgroup, 1, file);
+ /*
+ * zone->pages_scanned is used for detect zone's oom
+ * mem_cgroup remembers nr_scan by itself.
+ */
+ if (scanning_global_lru(sc)) {
+ zone->pages_scanned += pgscanned;
+ }
+ reclaim_stat->recent_scanned[!!file] += pgmoved;
+
+ 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;
while (!list_empty(&l_hold)) {
cond_resched();
page = lru_to_page(&l_hold);
list_del(&page->lru);
- if (page_mapped(page)) {
- if (!reclaim_mapped ||
- (total_swap_pages == 0 && PageAnon(page)) ||
- page_referenced(page, 0)) {
- list_add(&page->lru, &l_active);
- continue;
- }
+
+ 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))
+ pgmoved++;
+
list_add(&page->lru, &l_inactive);
}
+ /*
+ * Move the pages to the [file or anon] inactive list.
+ */
pagevec_init(&pvec, 1);
- pgmoved = 0;
+ lru = LRU_BASE + file * LRU_FILE;
+
spin_lock_irq(&zone->lru_lock);
+ /*
+ * 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.
+ */
+ reclaim_stat->recent_rotated[!!file] += pgmoved;
+
+ pgmoved = 0;
while (!list_empty(&l_inactive)) {
page = lru_to_page(&l_inactive);
prefetchw_prev_lru_page(page, &l_inactive, flags);
VM_BUG_ON(!PageActive(page));
ClearPageActive(page);
- list_move(&page->lru, &zone->inactive_list);
+ list_move(&page->lru, &zone->lru[lru].list);
+ mem_cgroup_add_lru_list(page, lru);
pgmoved++;
if (!pagevec_add(&pvec, page)) {
- __mod_zone_page_state(zone, NR_INACTIVE, pgmoved);
+ __mod_zone_page_state(zone, NR_LRU_BASE + lru, pgmoved);
spin_unlock_irq(&zone->lru_lock);
pgdeactivate += pgmoved;
pgmoved = 0;
spin_lock_irq(&zone->lru_lock);
}
}
- __mod_zone_page_state(zone, NR_INACTIVE, pgmoved);
+ __mod_zone_page_state(zone, NR_LRU_BASE + lru, pgmoved);
pgdeactivate += pgmoved;
- if (buffer_heads_over_limit) {
- spin_unlock_irq(&zone->lru_lock);
+ __count_zone_vm_events(PGREFILL, zone, pgscanned);
+ __count_vm_events(PGDEACTIVATE, pgdeactivate);
+ spin_unlock_irq(&zone->lru_lock);
+ if (buffer_heads_over_limit)
pagevec_strip(&pvec);
- spin_lock_irq(&zone->lru_lock);
+ 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 unsigned long shrink_list(enum lru_list lru, unsigned long nr_to_scan,
+ struct zone *zone, struct scan_control *sc, int priority)
+{
+ int file = is_file_lru(lru);
+
+ if (lru == LRU_ACTIVE_FILE) {
+ shrink_active_list(nr_to_scan, zone, sc, priority, file);
+ return 0;
}
- pgmoved = 0;
- while (!list_empty(&l_active)) {
- page = lru_to_page(&l_active);
- prefetchw_prev_lru_page(page, &l_active, flags);
- VM_BUG_ON(PageLRU(page));
- SetPageLRU(page);
- VM_BUG_ON(!PageActive(page));
- list_move(&page->lru, &zone->active_list);
- pgmoved++;
- if (!pagevec_add(&pvec, page)) {
- __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);
+ 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, priority, file);
+}
+
+/*
+ * Determine how aggressively the anon and file LRU lists should be
+ * scanned. The relative value of each set of LRU lists is determined
+ * by looking at the fraction of the pages scanned we did rotate back
+ * onto the active list instead of evict.
+ *
+ * percent[0] specifies how much pressure to put on ram/swap backed
+ * memory, while percent[1] determines pressure on the file LRUs.
+ */
+static void get_scan_ratio(struct zone *zone, struct scan_control *sc,
+ unsigned long *percent)
+{
+ unsigned long anon, file, free;
+ unsigned long anon_prio, file_prio;
+ unsigned long ap, fp;
+ struct zone_reclaim_stat *reclaim_stat = get_reclaim_stat(zone, sc);
+
+ /* If we have no swap space, do not bother scanning anon pages. */
+ if (nr_swap_pages <= 0) {
+ percent[0] = 0;
+ percent[1] = 100;
+ return;
+ }
+
+ 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 <= zone->pages_high)) {
+ percent[0] = 100;
+ percent[1] = 0;
+ return;
}
}
- __mod_zone_page_state(zone, NR_ACTIVE, pgmoved);
- __count_zone_vm_events(PGREFILL, zone, pgscanned);
- __count_vm_events(PGDEACTIVATE, pgdeactivate);
- spin_unlock_irq(&zone->lru_lock);
+ /*
+ * OK, so we have swap space and a fair amount of page cache
+ * pages. We use the recently rotated / recently scanned
+ * ratios to determine how valuable each cache is.
+ *
+ * Because workloads change over time (and to avoid overflow)
+ * we keep these statistics as a floating average, which ends
+ * up weighing recent references more than old ones.
+ *
+ * anon in [0], file in [1]
+ */
+ if (unlikely(reclaim_stat->recent_scanned[0] > anon / 4)) {
+ spin_lock_irq(&zone->lru_lock);
+ reclaim_stat->recent_scanned[0] /= 2;
+ reclaim_stat->recent_rotated[0] /= 2;
+ spin_unlock_irq(&zone->lru_lock);
+ }
- pagevec_release(&pvec);
+ if (unlikely(reclaim_stat->recent_scanned[1] > file / 4)) {
+ spin_lock_irq(&zone->lru_lock);
+ reclaim_stat->recent_scanned[1] /= 2;
+ reclaim_stat->recent_rotated[1] /= 2;
+ spin_unlock_irq(&zone->lru_lock);
+ }
+
+ /*
+ * With swappiness at 100, anonymous and file have the same priority.
+ * This scanning priority is essentially the inverse of IO cost.
+ */
+ anon_prio = sc->swappiness;
+ file_prio = 200 - sc->swappiness;
+
+ /*
+ * 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) * (reclaim_stat->recent_scanned[0] + 1);
+ ap /= reclaim_stat->recent_rotated[0] + 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];
}
+
/*
* 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_active;
- unsigned long nr_inactive;
+ 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;
- /*
- * Add one to `nr_to_scan' just to make sure that the kernel will
- * slowly sift through the active list.
- */
- zone->nr_scan_active +=
- (zone_page_state(zone, NR_ACTIVE) >> priority) + 1;
- nr_active = zone->nr_scan_active;
- if (nr_active >= sc->swap_cluster_max)
- zone->nr_scan_active = 0;
- else
- nr_active = 0;
+ get_scan_ratio(zone, sc, percent);
- zone->nr_scan_inactive +=
- (zone_page_state(zone, NR_INACTIVE) >> priority) + 1;
- nr_inactive = zone->nr_scan_inactive;
- if (nr_inactive >= sc->swap_cluster_max)
- zone->nr_scan_inactive = 0;
- else
- nr_inactive = 0;
-
- while (nr_active || nr_inactive) {
- if (nr_active) {
- nr_to_scan = min(nr_active,
- (unsigned long)sc->swap_cluster_max);
- nr_active -= nr_to_scan;
- shrink_active_list(nr_to_scan, zone, sc, priority);
+ for_each_evictable_lru(l) {
+ int file = is_file_lru(l);
+ int scan;
+
+ scan = zone_nr_pages(zone, sc, l);
+ if (priority) {
+ scan >>= priority;
+ scan = (scan * percent[file]) / 100;
}
+ if (scanning_global_lru(sc)) {
+ zone->lru[l].nr_scan += scan;
+ nr[l] = zone->lru[l].nr_scan;
+ if (nr[l] >= swap_cluster_max)
+ zone->lru[l].nr_scan = 0;
+ else
+ nr[l] = 0;
+ } else
+ nr[l] = scan;
+ }
+
+ while (nr[LRU_INACTIVE_ANON] || nr[LRU_ACTIVE_FILE] ||
+ nr[LRU_INACTIVE_FILE]) {
+ for_each_evictable_lru(l) {
+ if (nr[l]) {
+ nr_to_scan = min(nr[l], swap_cluster_max);
+ nr[l] -= nr_to_scan;
- if (nr_inactive) {
- nr_to_scan = min(nr_inactive,
- (unsigned long)sc->swap_cluster_max);
- nr_inactive -= nr_to_scan;
- nr_reclaimed += shrink_inactive_list(nr_to_scan, zone,
- sc);
+ nr_reclaimed += shrink_list(l, nr_to_scan,
+ 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 (inactive_anon_is_low(zone, sc))
+ shrink_active_list(SWAP_CLUSTER_MAX, zone, sc, priority, 0);
+
throttle_vm_writeout(sc->gfp_mask);
- return nr_reclaimed;
}
/*
* 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.
- *
* If a zone is deemed to be full of pinned pages then just give it a light
* scan then give up on it.
*/
-static unsigned long shrink_zones(int priority, struct zone **zones,
+static void shrink_zones(int priority, struct zonelist *zonelist,
struct scan_control *sc)
{
- unsigned long nr_reclaimed = 0;
- int i;
+ enum zone_type high_zoneidx = gfp_zone(sc->gfp_mask);
+ struct zoneref *z;
+ struct zone *zone;
sc->all_unreclaimable = 1;
- for (i = 0; zones[i] != NULL; i++) {
- struct zone *zone = zones[i];
-
+ for_each_zone_zonelist_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 (scanning_global_lru(sc)) {
+ if (!cpuset_zone_allowed_hardwall(zone, GFP_KERNEL))
+ continue;
+ note_zone_scanning_priority(zone, priority);
- if (!cpuset_zone_allowed_hardwall(zone, GFP_KERNEL))
- continue;
-
- note_zone_scanning_priority(zone, priority);
-
- if (zone_is_all_unreclaimable(zone) && priority != DEF_PRIORITY)
- continue; /* Let kswapd poll it */
-
- sc->all_unreclaimable = 0;
+ if (zone_is_all_unreclaimable(zone) &&
+ priority != DEF_PRIORITY)
+ continue; /* Let kswapd poll it */
+ sc->all_unreclaimable = 0;
+ } else {
+ /*
+ * Ignore cpuset limitation here. We just want to reduce
+ * # of used pages by us regardless of memory shortage.
+ */
+ sc->all_unreclaimable = 0;
+ mem_cgroup_note_reclaim_priority(sc->mem_cgroup,
+ priority);
+ }
- nr_reclaimed += shrink_zone(priority, zone, sc);
+ shrink_zone(priority, zone, sc);
}
- return nr_reclaimed;
}
-
+
/*
* This is the main entry point to direct page reclaim.
*
* hope that some of these pages can be written. But if the allocating task
* holds filesystem locks which prevent writeout this might not work, and the
* allocation attempt will fail.
+ *
+ * returns: 0, if no pages reclaimed
+ * else, the number of pages reclaimed
*/
-unsigned long try_to_free_pages(struct zone **zones, int order, gfp_t gfp_mask)
+static unsigned long do_try_to_free_pages(struct zonelist *zonelist,
+ struct scan_control *sc)
{
int priority;
- int ret = 0;
+ unsigned long ret = 0;
unsigned long total_scanned = 0;
- unsigned long nr_reclaimed = 0;
struct reclaim_state *reclaim_state = current->reclaim_state;
unsigned long lru_pages = 0;
- int i;
- struct scan_control sc = {
- .gfp_mask = gfp_mask,
- .may_writepage = !laptop_mode,
- .swap_cluster_max = SWAP_CLUSTER_MAX,
- .may_swap = 1,
- .swappiness = vm_swappiness,
- .order = order,
- };
+ struct zoneref *z;
+ struct zone *zone;
+ enum zone_type high_zoneidx = gfp_zone(sc->gfp_mask);
- count_vm_event(ALLOCSTALL);
+ delayacct_freepages_start();
- for (i = 0; zones[i] != NULL; i++) {
- struct zone *zone = zones[i];
+ if (scanning_global_lru(sc))
+ count_vm_event(ALLOCSTALL);
+ /*
+ * mem_cgroup will not do shrink_slab.
+ */
+ if (scanning_global_lru(sc)) {
+ for_each_zone_zonelist(zone, z, zonelist, high_zoneidx) {
- if (!cpuset_zone_allowed_hardwall(zone, GFP_KERNEL))
- continue;
+ if (!cpuset_zone_allowed_hardwall(zone, GFP_KERNEL))
+ continue;
- lru_pages += zone_page_state(zone, NR_ACTIVE)
- + zone_page_state(zone, NR_INACTIVE);
+ lru_pages += zone_lru_pages(zone);
+ }
}
for (priority = DEF_PRIORITY; priority >= 0; priority--) {
- sc.nr_scanned = 0;
+ sc->nr_scanned = 0;
if (!priority)
disable_swap_token();
- nr_reclaimed += shrink_zones(priority, zones, &sc);
- shrink_slab(sc.nr_scanned, gfp_mask, lru_pages);
- if (reclaim_state) {
- nr_reclaimed += reclaim_state->reclaimed_slab;
- reclaim_state->reclaimed_slab = 0;
+ shrink_zones(priority, zonelist, sc);
+ /*
+ * Don't shrink slabs when reclaiming memory from
+ * over limit cgroups
+ */
+ if (scanning_global_lru(sc)) {
+ shrink_slab(sc->nr_scanned, sc->gfp_mask, lru_pages);
+ if (reclaim_state) {
+ 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 = 1;
+ total_scanned += sc->nr_scanned;
+ if (sc->nr_reclaimed >= sc->swap_cluster_max) {
+ ret = sc->nr_reclaimed;
goto out;
}
* that's undesirable in laptop mode, where we *want* lumpy
* writeout. So in laptop mode, write out the whole world.
*/
- if (total_scanned > sc.swap_cluster_max +
- sc.swap_cluster_max / 2) {
+ if (total_scanned > sc->swap_cluster_max +
+ sc->swap_cluster_max / 2) {
wakeup_pdflush(laptop_mode ? 0 : total_scanned);
- sc.may_writepage = 1;
+ sc->may_writepage = 1;
}
/* Take a nap, wait for some writeback to complete */
- if (sc.nr_scanned && priority < DEF_PRIORITY - 2)
+ if (sc->nr_scanned && priority < DEF_PRIORITY - 2)
congestion_wait(WRITE, HZ/10);
}
- /* top priority shrink_caches still had more to do? don't OOM, then */
- if (!sc.all_unreclaimable)
- ret = 1;
+ /* top priority shrink_zones still had more to do? don't OOM, then */
+ if (!sc->all_unreclaimable && 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;
- for (i = 0; zones[i] != NULL; i++) {
- struct zone *zone = zones[i];
- if (!cpuset_zone_allowed_hardwall(zone, GFP_KERNEL))
- continue;
+ if (scanning_global_lru(sc)) {
+ for_each_zone_zonelist(zone, z, zonelist, high_zoneidx) {
+
+ if (!cpuset_zone_allowed_hardwall(zone, GFP_KERNEL))
+ continue;
+
+ zone->prev_priority = priority;
+ }
+ } else
+ mem_cgroup_record_reclaim_priority(sc->mem_cgroup, priority);
+
+ delayacct_freepages_end();
- zone->prev_priority = priority;
- }
return ret;
}
+unsigned long try_to_free_pages(struct zonelist *zonelist, int order,
+ gfp_t gfp_mask, nodemask_t *nodemask)
+{
+ struct scan_control sc = {
+ .gfp_mask = gfp_mask,
+ .may_writepage = !laptop_mode,
+ .swap_cluster_max = SWAP_CLUSTER_MAX,
+ .may_unmap = 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,
+ bool noswap,
+ unsigned int swappiness)
+{
+ struct scan_control sc = {
+ .may_writepage = !laptop_mode,
+ .may_unmap = 1,
+ .swap_cluster_max = SWAP_CLUSTER_MAX,
+ .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;
+
+ if (noswap)
+ sc.may_unmap = 0;
+
+ sc.gfp_mask = (gfp_mask & GFP_RECLAIM_MASK) |
+ (GFP_HIGHUSER_MOVABLE & ~GFP_RECLAIM_MASK);
+ zonelist = NODE_DATA(numa_node_id())->node_zonelists;
+ return do_try_to_free_pages(zonelist, &sc);
+}
+#endif
+
/*
* For kswapd, balance_pgdat() will work across all this node's zones until
* they are all at pages_high.
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_swap = 1,
+ .may_unmap = 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
loop_again:
total_scanned = 0;
- nr_reclaimed = 0;
+ sc.nr_reclaimed = 0;
sc.may_writepage = !laptop_mode;
count_vm_event(PAGEOUTRUN);
priority != DEF_PRIORITY)
continue;
+ /*
+ * Do some background aging of the anon list, to give
+ * pages a chance to be referenced before reclaiming.
+ */
+ 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)) {
end_zone = i;
for (i = 0; i <= end_zone; i++) {
struct zone *zone = pgdat->node_zones + i;
- lru_pages += zone_page_state(zone, NR_ACTIVE)
- + zone_page_state(zone, NR_INACTIVE);
+ lru_pages += zone_lru_pages(zone);
}
/*
*/
if (!zone_watermark_ok(zone, order, 8*zone->pages_high,
end_zone, 0))
- nr_reclaimed += shrink_zone(priority, zone, &sc);
+ 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;
if (nr_slab == 0 && zone->pages_scanned >=
- (zone_page_state(zone, NR_ACTIVE)
- + zone_page_state(zone, NR_INACTIVE)) * 6)
+ (zone_lru_pages(zone) * 6))
zone_set_flag(zone,
ZONE_ALL_UNRECLAIMABLE);
/*
* 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)
* 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;
}
/*
* The background pageout daemon, started as a kernel thread
- * from the init process.
+ * from the init process.
*
* This basically trickles out pages so that we have _some_
* free memory available even if there is no other activity
struct reclaim_state reclaim_state = {
.reclaimed_slab = 0,
};
- cpumask_t cpumask;
+ node_to_cpumask_ptr(cpumask, pgdat->node_id);
+
+ lockdep_set_current_reclaim_state(GFP_KERNEL);
- cpumask = node_to_cpumask(pgdat->node_id);
- if (!cpus_empty(cpumask))
- set_cpus_allowed(tsk, cpumask);
+ if (!cpumask_empty(cpumask))
+ set_cpus_allowed_ptr(tsk, cpumask);
current->reclaim_state = &reclaim_state;
/*
wake_up_interruptible(&pgdat->kswapd_wait);
}
+unsigned long global_lru_pages(void)
+{
+ return global_page_state(NR_ACTIVE_ANON)
+ + global_page_state(NR_ACTIVE_FILE)
+ + global_page_state(NR_INACTIVE_ANON)
+ + global_page_state(NR_INACTIVE_FILE);
+}
+
#ifdef CONFIG_PM
/*
* 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;
+ unsigned long nr_reclaimed = 0;
- for_each_zone(zone) {
-
- 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 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);
- }
- }
+ for_each_evictable_lru(l) {
+ enum zone_stat_item ls = NR_LRU_BASE + l;
+ unsigned long lru_pages = zone_page_state(zone, ls);
- 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;
+ /* 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 += (lru_pages >> prio) + 1;
+ if (zone->lru[l].nr_scan >= nr_pages || pass > 3) {
+ unsigned long nr_to_scan;
+
+ zone->lru[l].nr_scan = 0;
+ nr_to_scan = min(nr_pages, lru_pages);
+ nr_reclaimed += shrink_list(l, nr_to_scan, zone,
+ sc, prio);
+ if (nr_reclaimed >= nr_pages) {
+ sc->nr_reclaimed = nr_reclaimed;
+ return;
+ }
+ }
}
}
-
- return ret;
-}
-
-static unsigned long count_lru_pages(void)
-{
- return global_page_state(NR_ACTIVE) + global_page_state(NR_INACTIVE);
+ 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,
};
current->reclaim_state = &reclaim_state;
- lru_pages = count_lru_pages();
+ lru_pages = global_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) {
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,
- count_lru_pages());
- ret += reclaim_state.reclaimed_slab;
- if (ret >= nr_pages)
+ global_lru_pages());
+ sc.nr_reclaimed += reclaim_state.reclaimed_slab;
+ if (sc.nr_reclaimed >= nr_pages)
goto out;
if (sc.nr_scanned && prio < DEF_PRIORITY - 2)
}
/*
- * 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, count_lru_pages());
- ret += reclaim_state.reclaimed_slab;
- } while (ret < nr_pages && reclaim_state.reclaimed_slab > 0);
+ shrink_slab(nr_pages, sc.gfp_mask, global_lru_pages());
+ 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
static int __devinit cpu_callback(struct notifier_block *nfb,
unsigned long action, void *hcpu)
{
- pg_data_t *pgdat;
- cpumask_t mask;
int nid;
if (action == CPU_ONLINE || action == CPU_ONLINE_FROZEN) {
for_each_node_state(nid, N_HIGH_MEMORY) {
- pgdat = NODE_DATA(nid);
- mask = node_to_cpumask(pgdat->node_id);
- if (any_online_cpu(mask) != NR_CPUS)
+ pg_data_t *pgdat = NODE_DATA(nid);
+ node_to_cpumask_ptr(mask, pgdat->node_id);
+
+ if (cpumask_any_and(cpu_online_mask, mask) < nr_cpu_ids)
/* One of our CPUs online: restore mask */
- set_cpus_allowed(pgdat->kswapd, mask);
+ set_cpus_allowed_ptr(pgdat->kswapd, mask);
}
}
return NOTIFY_OK;
int zone_reclaim_mode __read_mostly;
#define RECLAIM_OFF 0
-#define RECLAIM_ZONE (1<<0) /* Run shrink_cache on the zone */
+#define RECLAIM_ZONE (1<<0) /* Run shrink_inactive_list on the zone */
#define RECLAIM_WRITE (1<<1) /* Writeout pages during reclaim */
#define RECLAIM_SWAP (1<<2) /* Swap pages out during reclaim */
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),
.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;
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)
return ret;
}
#endif
+
+#ifdef CONFIG_UNEVICTABLE_LRU
+/*
+ * 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);
+}
+
+#endif
Code Review / linux-2.6.git / blobdiff