#include <linux/mm.h>
#include <linux/module.h>
-#include <linux/slab.h>
+#include <linux/gfp.h>
#include <linux/kernel_stat.h>
#include <linux/swap.h>
#include <linux/pagemap.h>
#include "internal.h"
+#define CREATE_TRACE_POINTS
+#include <trace/events/vmscan.h>
+
struct scan_control {
/* 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;
+ /* How many pages shrink_list() should reclaim */
+ unsigned long nr_to_reclaim;
+
+ unsigned long hibernation_mode;
+
/* This context's GFP mask */
gfp_t gfp_mask;
/* Can pages be swapped as part of reclaim? */
int may_swap;
- /* This context's SWAP_CLUSTER_MAX. If freeing memory for
- * suspend, we effectively ignore SWAP_CLUSTER_MAX.
- * In this context, it doesn't matter that we scan the
- * whole list at once. */
- int swap_cluster_max;
-
int swappiness;
- int all_unreclaimable;
-
int order;
+ /*
+ * Intend to reclaim enough contenious memory rather than to reclaim
+ * enough amount memory. I.e, it's the mode for high order allocation.
+ */
+ bool lumpy_reclaim_mode;
+
/* Which cgroup do we reclaim from */
struct mem_cgroup *mem_cgroup;
* 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))
return &zone->reclaim_stat;
}
-static unsigned long zone_nr_pages(struct zone *zone, struct scan_control *sc,
- enum lru_list lru)
+static unsigned long zone_nr_lru_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);
list_for_each_entry(shrinker, &shrinker_list, list) {
unsigned long long delta;
unsigned long total_scan;
- unsigned long max_pass = (*shrinker->shrink)(0, gfp_mask);
+ unsigned long max_pass;
+ max_pass = (*shrinker->shrink)(shrinker, 0, gfp_mask);
delta = (4 * scanned) / shrinker->seeks;
delta *= max_pass;
do_div(delta, lru_pages + 1);
int shrink_ret;
int nr_before;
- nr_before = (*shrinker->shrink)(0, gfp_mask);
- shrink_ret = (*shrinker->shrink)(this_scan, gfp_mask);
+ nr_before = (*shrinker->shrink)(shrinker, 0, gfp_mask);
+ shrink_ret = (*shrinker->shrink)(shrinker, this_scan,
+ gfp_mask);
if (shrink_ret == -1)
break;
if (shrink_ret < nr_before)
return ret;
}
-/* Called without lock on whether page is mapped, so answer is unstable */
-static inline int page_mapping_inuse(struct page *page)
-{
- struct address_space *mapping;
-
- /* Page is in somebody's page tables. */
- if (page_mapped(page))
- return 1;
-
- /* Be more reluctant to reclaim swapcache than pagecache */
- if (PageSwapCache(page))
- return 1;
-
- mapping = page_mapping(page);
- if (!mapping)
- return 0;
-
- /* File is mmap'd by somebody? */
- return mapping_mapped(mapping);
-}
-
static inline int is_page_cache_freeable(struct page *page)
{
+ /*
+ * A freeable page cache page is referenced only by the caller
+ * that isolated the page, the page cache radix tree and
+ * optional buffer heads at page->private.
+ */
return page_count(page) - page_has_private(page) == 2;
}
static void handle_write_error(struct address_space *mapping,
struct page *page, int error)
{
- lock_page(page);
+ lock_page_nosync(page);
if (page_mapping(page) == mapping)
mapping_set_error(mapping, error);
unlock_page(page);
* stalls if we need to run get_block(). We could test
* PagePrivate for that.
*
- * If this process is currently in generic_file_write() against
+ * If this process is currently in __generic_file_aio_write() against
* this page's queue, we can perform writeback even if that
* will block.
*
* block, for some throttling. This happens by accident, because
* swap_backing_dev_info is bust: it doesn't reflect the
* congestion state of the swapdevs. Easy to fix, if needed.
- * See swapfile.c:page_queue_congested().
*/
if (!is_page_cache_freeable(page))
return PAGE_KEEP;
/* synchronous write or broken a_ops? */
ClearPageReclaim(page);
}
+ trace_mm_vmscan_writepage(page,
+ trace_reclaim_flags(page, sync_writeback));
inc_zone_page_state(page, NR_VMSCAN_WRITE);
return PAGE_SUCCESS;
}
*/
lru = LRU_UNEVICTABLE;
add_page_to_unevictable_list(page);
+ /*
+ * When racing with an mlock clearing (page is
+ * unlocked), make sure that if the other thread does
+ * not observe our setting of PG_lru and fails
+ * isolation, we see PG_mlocked cleared below and move
+ * the page back to the evictable list.
+ *
+ * The other side is TestClearPageMlocked().
+ */
+ smp_mb();
}
/*
put_page(page); /* drop ref from isolate */
}
+enum page_references {
+ PAGEREF_RECLAIM,
+ PAGEREF_RECLAIM_CLEAN,
+ PAGEREF_KEEP,
+ PAGEREF_ACTIVATE,
+};
+
+static enum page_references page_check_references(struct page *page,
+ struct scan_control *sc)
+{
+ int referenced_ptes, referenced_page;
+ unsigned long vm_flags;
+
+ referenced_ptes = page_referenced(page, 1, sc->mem_cgroup, &vm_flags);
+ referenced_page = TestClearPageReferenced(page);
+
+ /* Lumpy reclaim - ignore references */
+ if (sc->lumpy_reclaim_mode)
+ return PAGEREF_RECLAIM;
+
+ /*
+ * Mlock lost the isolation race with us. Let try_to_unmap()
+ * move the page to the unevictable list.
+ */
+ if (vm_flags & VM_LOCKED)
+ return PAGEREF_RECLAIM;
+
+ if (referenced_ptes) {
+ if (PageAnon(page))
+ return PAGEREF_ACTIVATE;
+ /*
+ * All mapped pages start out with page table
+ * references from the instantiating fault, so we need
+ * to look twice if a mapped file page is used more
+ * than once.
+ *
+ * Mark it and spare it for another trip around the
+ * inactive list. Another page table reference will
+ * lead to its activation.
+ *
+ * Note: the mark is set for activated pages as well
+ * so that recently deactivated but used pages are
+ * quickly recovered.
+ */
+ SetPageReferenced(page);
+
+ if (referenced_page)
+ return PAGEREF_ACTIVATE;
+
+ return PAGEREF_KEEP;
+ }
+
+ /* Reclaim if clean, defer dirty pages to writeback */
+ if (referenced_page)
+ return PAGEREF_RECLAIM_CLEAN;
+
+ return PAGEREF_RECLAIM;
+}
+
+static noinline_for_stack void free_page_list(struct list_head *free_pages)
+{
+ struct pagevec freed_pvec;
+ struct page *page, *tmp;
+
+ pagevec_init(&freed_pvec, 1);
+
+ list_for_each_entry_safe(page, tmp, free_pages, lru) {
+ list_del(&page->lru);
+ if (!pagevec_add(&freed_pvec, page)) {
+ __pagevec_free(&freed_pvec);
+ pagevec_reinit(&freed_pvec);
+ }
+ }
+
+ pagevec_free(&freed_pvec);
+}
+
/*
* shrink_page_list() returns the number of reclaimed pages
*/
enum pageout_io sync_writeback)
{
LIST_HEAD(ret_pages);
- struct pagevec freed_pvec;
+ LIST_HEAD(free_pages);
int pgactivate = 0;
unsigned long nr_reclaimed = 0;
- unsigned long vm_flags;
cond_resched();
- pagevec_init(&freed_pvec, 1);
while (!list_empty(page_list)) {
+ enum page_references references;
struct address_space *mapping;
struct page *page;
int may_enter_fs;
- int referenced;
cond_resched();
goto keep_locked;
}
- 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)
- && !(vm_flags & VM_LOCKED))
+ references = page_check_references(page, sc);
+ switch (references) {
+ case PAGEREF_ACTIVATE:
goto activate_locked;
+ case PAGEREF_KEEP:
+ goto keep_locked;
+ case PAGEREF_RECLAIM:
+ case PAGEREF_RECLAIM_CLEAN:
+ ; /* try to reclaim the page below */
+ }
/*
* Anonymous process memory has backing store?
* processes. Try to unmap it here.
*/
if (page_mapped(page) && mapping) {
- switch (try_to_unmap(page, 0)) {
+ switch (try_to_unmap(page, TTU_UNMAP)) {
case SWAP_FAIL:
goto activate_locked;
case SWAP_AGAIN:
}
if (PageDirty(page)) {
- if (sc->order <= PAGE_ALLOC_COSTLY_ORDER && referenced)
+ if (references == PAGEREF_RECLAIM_CLEAN)
goto keep_locked;
if (!may_enter_fs)
goto keep_locked;
__clear_page_locked(page);
free_it:
nr_reclaimed++;
- if (!pagevec_add(&freed_pvec, page)) {
- __pagevec_free(&freed_pvec);
- pagevec_reinit(&freed_pvec);
- }
+
+ /*
+ * Is there need to periodically free_page_list? It would
+ * appear not as the counts should be low
+ */
+ list_add(&page->lru, &free_pages);
continue;
cull_mlocked:
list_add(&page->lru, &ret_pages);
VM_BUG_ON(PageLRU(page) || PageUnevictable(page));
}
+
+ free_page_list(&free_pages);
+
list_splice(&ret_pages, page_list);
- if (pagevec_count(&freed_pvec))
- __pagevec_free(&freed_pvec);
count_vm_events(PGACTIVATE, pgactivate);
return nr_reclaimed;
}
-/* LRU Isolation modes. */
-#define ISOLATE_INACTIVE 0 /* Isolate inactive pages. */
-#define ISOLATE_ACTIVE 1 /* Isolate active pages. */
-#define ISOLATE_BOTH 2 /* Isolate both active and inactive pages. */
-
/*
* Attempt to remove the specified page from its LRU. Only take this page
* if it is of the appropriate PageActive status. Pages which are being
unsigned long *scanned, int order, int mode, int file)
{
unsigned long nr_taken = 0;
+ unsigned long nr_lumpy_taken = 0;
+ unsigned long nr_lumpy_dirty = 0;
+ unsigned long nr_lumpy_failed = 0;
unsigned long scan;
for (scan = 0; scan < nr_to_scan && !list_empty(src); scan++) {
list_move(&cursor_page->lru, dst);
mem_cgroup_del_lru(cursor_page);
nr_taken++;
+ nr_lumpy_taken++;
+ if (PageDirty(cursor_page))
+ nr_lumpy_dirty++;
scan++;
+ } else {
+ if (mode == ISOLATE_BOTH &&
+ page_count(cursor_page))
+ nr_lumpy_failed++;
}
}
}
*scanned = scan;
+
+ trace_mm_vmscan_lru_isolate(order,
+ nr_to_scan, scan,
+ nr_taken,
+ nr_lumpy_taken, nr_lumpy_dirty, nr_lumpy_failed,
+ mode);
return nr_taken;
}
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;
ClearPageActive(page);
nr_active++;
}
- count[lru]++;
+ if (count)
+ count[lru]++;
}
return nr_active;
}
/*
- * shrink_inactive_list() is a helper for shrink_zone(). It returns the number
- * of reclaimed pages
+ * TODO: Try merging with migrations version of putback_lru_pages
*/
-static unsigned long shrink_inactive_list(unsigned long max_scan,
- struct zone *zone, struct scan_control *sc,
- int priority, int file)
+static noinline_for_stack void
+putback_lru_pages(struct zone *zone, struct scan_control *sc,
+ unsigned long nr_anon, unsigned long nr_file,
+ struct list_head *page_list)
{
- LIST_HEAD(page_list);
+ struct page *page;
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;
- while (unlikely(too_many_isolated(zone, file, sc))) {
- congestion_wait(WRITE, HZ/10);
-
- /* We are about to die and free our memory. Return now. */
- if (fatal_signal_pending(current))
- return SWAP_CLUSTER_MAX;
- }
+ pagevec_init(&pvec, 1);
/*
- * 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.
+ * Put back any unfreeable pages.
*/
- if (sc->order > PAGE_ALLOC_COSTLY_ORDER)
- lumpy_reclaim = 1;
- else if (sc->order && priority < DEF_PRIORITY - 2)
- lumpy_reclaim = 1;
+ spin_lock(&zone->lru_lock);
+ while (!list_empty(page_list)) {
+ int lru;
+ page = lru_to_page(page_list);
+ VM_BUG_ON(PageLRU(page));
+ list_del(&page->lru);
+ 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 (is_active_lru(lru)) {
+ int file = is_file_lru(lru);
+ reclaim_stat->recent_rotated[file]++;
+ }
+ if (!pagevec_add(&pvec, page)) {
+ spin_unlock_irq(&zone->lru_lock);
+ __pagevec_release(&pvec);
+ spin_lock_irq(&zone->lru_lock);
+ }
+ }
+ __mod_zone_page_state(zone, NR_ISOLATED_ANON, -nr_anon);
+ __mod_zone_page_state(zone, NR_ISOLATED_FILE, -nr_file);
- pagevec_init(&pvec, 1);
+ spin_unlock_irq(&zone->lru_lock);
+ pagevec_release(&pvec);
+}
- lru_add_drain();
- spin_lock_irq(&zone->lru_lock);
- do {
- struct page *page;
- unsigned long nr_taken;
- unsigned long nr_scan;
- unsigned long nr_freed;
- unsigned long nr_active;
- unsigned int count[NR_LRU_LISTS] = { 0, };
- int mode = lumpy_reclaim ? ISOLATE_BOTH : ISOLATE_INACTIVE;
- unsigned long nr_anon;
- unsigned long nr_file;
-
- nr_taken = sc->isolate_pages(sc->swap_cluster_max,
- &page_list, &nr_scan, sc->order, mode,
- zone, sc->mem_cgroup, 0, file);
+static noinline_for_stack void update_isolated_counts(struct zone *zone,
+ struct scan_control *sc,
+ unsigned long *nr_anon,
+ unsigned long *nr_file,
+ struct list_head *isolated_list)
+{
+ unsigned long nr_active;
+ unsigned int count[NR_LRU_LISTS] = { 0, };
+ struct zone_reclaim_stat *reclaim_stat = get_reclaim_stat(zone, sc);
- if (scanning_global_lru(sc)) {
- zone->pages_scanned += nr_scan;
- if (current_is_kswapd())
- __count_zone_vm_events(PGSCAN_KSWAPD, zone,
- nr_scan);
- else
- __count_zone_vm_events(PGSCAN_DIRECT, zone,
- nr_scan);
- }
+ nr_active = clear_active_flags(isolated_list, count);
+ __count_vm_events(PGDEACTIVATE, nr_active);
+
+ __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]);
+
+ *nr_anon = count[LRU_ACTIVE_ANON] + count[LRU_INACTIVE_ANON];
+ *nr_file = count[LRU_ACTIVE_FILE] + count[LRU_INACTIVE_FILE];
+ __mod_zone_page_state(zone, NR_ISOLATED_ANON, *nr_anon);
+ __mod_zone_page_state(zone, NR_ISOLATED_FILE, *nr_file);
+
+ reclaim_stat->recent_scanned[0] += *nr_anon;
+ reclaim_stat->recent_scanned[1] += *nr_file;
+}
- if (nr_taken == 0)
- goto done;
+/*
+ * Returns true if the caller should wait to clean dirty/writeback pages.
+ *
+ * If we are direct reclaiming for contiguous pages and we do not reclaim
+ * everything in the list, try again and wait for writeback IO to complete.
+ * This will stall high-order allocations noticeably. Only do that when really
+ * need to free the pages under high memory pressure.
+ */
+static inline bool should_reclaim_stall(unsigned long nr_taken,
+ unsigned long nr_freed,
+ int priority,
+ struct scan_control *sc)
+{
+ int lumpy_stall_priority;
- nr_active = clear_active_flags(&page_list, count);
- __count_vm_events(PGDEACTIVATE, nr_active);
+ /* kswapd should not stall on sync IO */
+ if (current_is_kswapd())
+ return false;
- __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]);
+ /* Only stall on lumpy reclaim */
+ if (!sc->lumpy_reclaim_mode)
+ return false;
- nr_anon = count[LRU_ACTIVE_ANON] + count[LRU_INACTIVE_ANON];
- nr_file = count[LRU_ACTIVE_FILE] + count[LRU_INACTIVE_FILE];
- __mod_zone_page_state(zone, NR_ISOLATED_ANON, nr_anon);
- __mod_zone_page_state(zone, NR_ISOLATED_FILE, nr_file);
+ /* If we have relaimed everything on the isolated list, no stall */
+ if (nr_freed == nr_taken)
+ return false;
- 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];
+ /*
+ * For high-order allocations, there are two stall thresholds.
+ * High-cost allocations stall immediately where as lower
+ * order allocations such as stacks require the scanning
+ * priority to be much higher before stalling.
+ */
+ if (sc->order > PAGE_ALLOC_COSTLY_ORDER)
+ lumpy_stall_priority = DEF_PRIORITY;
+ else
+ lumpy_stall_priority = DEF_PRIORITY / 3;
- spin_unlock_irq(&zone->lru_lock);
+ return priority <= lumpy_stall_priority;
+}
- nr_scanned += nr_scan;
- nr_freed = shrink_page_list(&page_list, sc, PAGEOUT_IO_ASYNC);
+/*
+ * shrink_inactive_list() is a helper for shrink_zone(). It returns the number
+ * of reclaimed pages
+ */
+static noinline_for_stack unsigned long
+shrink_inactive_list(unsigned long nr_to_scan, struct zone *zone,
+ struct scan_control *sc, int priority, int file)
+{
+ LIST_HEAD(page_list);
+ unsigned long nr_scanned;
+ unsigned long nr_reclaimed = 0;
+ unsigned long nr_taken;
+ unsigned long nr_active;
+ unsigned long nr_anon;
+ unsigned long nr_file;
+ while (unlikely(too_many_isolated(zone, file, sc))) {
+ congestion_wait(BLK_RW_ASYNC, HZ/10);
+
+ /* We are about to die and free our memory. Return now. */
+ if (fatal_signal_pending(current))
+ return SWAP_CLUSTER_MAX;
+ }
+
+
+ lru_add_drain();
+ spin_lock_irq(&zone->lru_lock);
+
+ if (scanning_global_lru(sc)) {
+ nr_taken = isolate_pages_global(nr_to_scan,
+ &page_list, &nr_scanned, sc->order,
+ sc->lumpy_reclaim_mode ?
+ ISOLATE_BOTH : ISOLATE_INACTIVE,
+ zone, 0, file);
+ zone->pages_scanned += nr_scanned;
+ if (current_is_kswapd())
+ __count_zone_vm_events(PGSCAN_KSWAPD, zone,
+ nr_scanned);
+ else
+ __count_zone_vm_events(PGSCAN_DIRECT, zone,
+ nr_scanned);
+ } else {
+ nr_taken = mem_cgroup_isolate_pages(nr_to_scan,
+ &page_list, &nr_scanned, sc->order,
+ sc->lumpy_reclaim_mode ?
+ ISOLATE_BOTH : ISOLATE_INACTIVE,
+ zone, sc->mem_cgroup,
+ 0, file);
/*
- * If we are direct reclaiming for contiguous pages and we do
- * not reclaim everything in the list, try again and wait
- * for IO to complete. This will stall high-order allocations
- * but that should be acceptable to the caller
+ * mem_cgroup_isolate_pages() keeps track of
+ * scanned pages on its own.
*/
- if (nr_freed < nr_taken && !current_is_kswapd() &&
- lumpy_reclaim) {
- congestion_wait(BLK_RW_ASYNC, HZ/10);
+ }
- /*
- * The attempt at page out may have made some
- * of the pages active, mark them inactive again.
- */
- nr_active = clear_active_flags(&page_list, count);
- count_vm_events(PGDEACTIVATE, nr_active);
+ if (nr_taken == 0) {
+ spin_unlock_irq(&zone->lru_lock);
+ return 0;
+ }
- nr_freed += shrink_page_list(&page_list, sc,
- PAGEOUT_IO_SYNC);
- }
+ update_isolated_counts(zone, sc, &nr_anon, &nr_file, &page_list);
+
+ spin_unlock_irq(&zone->lru_lock);
- nr_reclaimed += nr_freed;
+ nr_reclaimed = shrink_page_list(&page_list, sc, PAGEOUT_IO_ASYNC);
- local_irq_disable();
- if (current_is_kswapd())
- __count_vm_events(KSWAPD_STEAL, nr_freed);
- __count_zone_vm_events(PGSTEAL, zone, nr_freed);
+ /* Check if we should syncronously wait for writeback */
+ if (should_reclaim_stall(nr_taken, nr_reclaimed, priority, sc)) {
+ congestion_wait(BLK_RW_ASYNC, HZ/10);
- spin_lock(&zone->lru_lock);
/*
- * Put back any unfreeable pages.
+ * The attempt at page out may have made some
+ * of the pages active, mark them inactive again.
*/
- while (!list_empty(&page_list)) {
- int lru;
- page = lru_to_page(&page_list);
- VM_BUG_ON(PageLRU(page));
- list_del(&page->lru);
- 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 (is_active_lru(lru)) {
- int file = is_file_lru(lru);
- reclaim_stat->recent_rotated[file]++;
- }
- if (!pagevec_add(&pvec, page)) {
- spin_unlock_irq(&zone->lru_lock);
- __pagevec_release(&pvec);
- spin_lock_irq(&zone->lru_lock);
- }
- }
- __mod_zone_page_state(zone, NR_ISOLATED_ANON, -nr_anon);
- __mod_zone_page_state(zone, NR_ISOLATED_FILE, -nr_file);
+ nr_active = clear_active_flags(&page_list, NULL);
+ count_vm_events(PGDEACTIVATE, nr_active);
- } while (nr_scanned < max_scan);
+ nr_reclaimed += shrink_page_list(&page_list, sc, PAGEOUT_IO_SYNC);
+ }
-done:
- spin_unlock_irq(&zone->lru_lock);
- pagevec_release(&pvec);
- return nr_reclaimed;
-}
+ local_irq_disable();
+ if (current_is_kswapd())
+ __count_vm_events(KSWAPD_STEAL, nr_reclaimed);
+ __count_zone_vm_events(PGSTEAL, zone, nr_reclaimed);
-/*
- * We are about to scan this zone at a certain priority level. If that priority
- * level is smaller (ie: more urgent) than the previous priority, then note
- * that priority level within the zone. This is done so that when the next
- * process comes in to scan this zone, it will immediately start out at this
- * priority level rather than having to build up its own scanning priority.
- * Here, this priority affects only the reclaim-mapped threshold.
- */
-static inline void note_zone_scanning_priority(struct zone *zone, int priority)
-{
- if (priority < zone->prev_priority)
- zone->prev_priority = priority;
+ putback_lru_pages(zone, sc, nr_anon, nr_file, &page_list);
+ return nr_reclaimed;
}
/*
lru_add_drain();
spin_lock_irq(&zone->lru_lock);
- nr_taken = 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)) {
+ nr_taken = isolate_pages_global(nr_pages, &l_hold,
+ &pgscanned, sc->order,
+ ISOLATE_ACTIVE, zone,
+ 1, file);
zone->pages_scanned += pgscanned;
+ } else {
+ nr_taken = mem_cgroup_isolate_pages(nr_pages, &l_hold,
+ &pgscanned, sc->order,
+ ISOLATE_ACTIVE, zone,
+ sc->mem_cgroup, 1, file);
+ /*
+ * mem_cgroup_isolate_pages() keeps track of
+ * scanned pages on its own.
+ */
}
+
reclaim_stat->recent_scanned[file] += nr_taken;
__count_zone_vm_events(PGREFILL, zone, pgscanned);
continue;
}
- /* page_referenced clears PageReferenced */
- if (page_mapping_inuse(page) &&
- page_referenced(page, 0, sc->mem_cgroup, &vm_flags)) {
+ if (page_referenced(page, 0, sc->mem_cgroup, &vm_flags)) {
nr_rotated++;
/*
* Identify referenced, file-backed active pages and
* IO, plus JVM can create lots of anon VM_EXEC pages,
* so we ignore them here.
*/
- if ((vm_flags & VM_EXEC) && !PageAnon(page)) {
+ if ((vm_flags & VM_EXEC) && page_is_file_cache(page)) {
list_add(&page->lru, &l_active);
continue;
}
return low;
}
+static int inactive_list_is_low(struct zone *zone, struct scan_control *sc,
+ int file)
+{
+ if (file)
+ return inactive_file_is_low(zone, sc);
+ else
+ return inactive_anon_is_low(zone, sc);
+}
+
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 && inactive_file_is_low(zone, sc)) {
- shrink_active_list(nr_to_scan, zone, sc, priority, file);
+ if (is_active_lru(lru)) {
+ if (inactive_list_is_low(zone, sc, file))
+ shrink_active_list(nr_to_scan, zone, sc, priority, file);
return 0;
}
- 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);
}
+/*
+ * 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 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;
+}
+
/*
* 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.
+ * nr[0] = anon pages to scan; nr[1] = file pages to scan
*/
-static void get_scan_ratio(struct zone *zone, struct scan_control *sc,
- unsigned long *percent)
+static void get_scan_count(struct zone *zone, struct scan_control *sc,
+ unsigned long *nr, int priority)
{
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);
+ u64 fraction[2], denominator;
+ enum lru_list l;
+ int noswap = 0;
+
+ /* If we have no swap space, do not bother scanning anon pages. */
+ if (!sc->may_swap || (nr_swap_pages <= 0)) {
+ noswap = 1;
+ fraction[0] = 0;
+ fraction[1] = 1;
+ denominator = 1;
+ goto out;
+ }
- 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);
+ anon = zone_nr_lru_pages(zone, sc, LRU_ACTIVE_ANON) +
+ zone_nr_lru_pages(zone, sc, LRU_INACTIVE_ANON);
+ file = zone_nr_lru_pages(zone, sc, LRU_ACTIVE_FILE) +
+ zone_nr_lru_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;
+ fraction[0] = 1;
+ fraction[1] = 0;
+ denominator = 1;
+ goto out;
}
}
+ /*
+ * 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;
+
/*
* OK, so we have swap space and a fair amount of page cache
* pages. We use the recently rotated / recently scanned
*
* anon in [0], file in [1]
*/
+ spin_lock_irq(&zone->lru_lock);
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);
}
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
fp = (file_prio + 1) * (reclaim_stat->recent_scanned[1] + 1);
fp /= reclaim_stat->recent_rotated[1] + 1;
+ spin_unlock_irq(&zone->lru_lock);
+
+ fraction[0] = ap;
+ fraction[1] = fp;
+ denominator = ap + fp + 1;
+out:
+ for_each_evictable_lru(l) {
+ int file = is_file_lru(l);
+ unsigned long scan;
- /* Normalize to percentages */
- percent[0] = 100 * ap / (ap + fp + 1);
- percent[1] = 100 - percent[0];
+ scan = zone_nr_lru_pages(zone, sc, l);
+ if (priority || noswap) {
+ scan >>= priority;
+ scan = div64_u64(scan * fraction[file], denominator);
+ }
+ nr[l] = nr_scan_try_batch(scan,
+ &reclaim_stat->nr_saved_scan[l]);
+ }
}
-/*
- * 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)
+static void set_lumpy_reclaim_mode(int priority, struct scan_control *sc)
{
- unsigned long nr;
-
- *nr_saved_scan += nr_to_scan;
- nr = *nr_saved_scan;
-
- if (nr >= swap_cluster_max)
- *nr_saved_scan = 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.
+ */
+ if (sc->order > PAGE_ALLOC_COSTLY_ORDER)
+ sc->lumpy_reclaim_mode = 1;
+ else if (sc->order && priority < DEF_PRIORITY - 2)
+ sc->lumpy_reclaim_mode = 1;
else
- nr = 0;
-
- return nr;
+ sc->lumpy_reclaim_mode = 0;
}
/*
{
unsigned long nr[NR_LRU_LISTS];
unsigned long nr_to_scan;
- 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;
+ unsigned long nr_to_reclaim = sc->nr_to_reclaim;
- /* 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_evictable_lru(l) {
- int file = is_file_lru(l);
- unsigned long scan;
+ get_scan_count(zone, sc, nr, priority);
- 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;
- }
+ set_lumpy_reclaim_mode(priority, sc);
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_to_scan = min_t(unsigned long,
+ nr[l], SWAP_CLUSTER_MAX);
nr[l] -= nr_to_scan;
nr_reclaimed += shrink_list(l, nr_to_scan,
* 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())
+ if (nr_reclaimed >= nr_to_reclaim && priority < DEF_PRIORITY)
break;
}
* If a zone is deemed to be full of pinned pages then just give it a light
* scan then give up on it.
*/
-static void shrink_zones(int priority, struct zonelist *zonelist,
+static bool shrink_zones(int priority, struct zonelist *zonelist,
struct scan_control *sc)
{
- enum zone_type high_zoneidx = gfp_zone(sc->gfp_mask);
struct zoneref *z;
struct zone *zone;
+ bool all_unreclaimable = true;
- sc->all_unreclaimable = 1;
- for_each_zone_zonelist_nodemask(zone, z, zonelist, high_zoneidx,
- sc->nodemask) {
+ for_each_zone_zonelist_nodemask(zone, z, zonelist,
+ gfp_zone(sc->gfp_mask), sc->nodemask) {
if (!populated_zone(zone))
continue;
/*
if (scanning_global_lru(sc)) {
if (!cpuset_zone_allowed_hardwall(zone, GFP_KERNEL))
continue;
- note_zone_scanning_priority(zone, priority);
-
- if (zone_is_all_unreclaimable(zone) &&
- priority != DEF_PRIORITY)
+ if (zone->all_unreclaimable && priority != DEF_PRIORITY)
continue; /* Let kswapd poll it */
- sc->all_unreclaimable = 0;
- } else {
- /*
- * Ignore cpuset limitation here. We just want to reduce
- * # of used pages by us regardless of memory shortage.
- */
- sc->all_unreclaimable = 0;
- mem_cgroup_note_reclaim_priority(sc->mem_cgroup,
- priority);
}
shrink_zone(priority, zone, sc);
+ all_unreclaimable = false;
}
+ return all_unreclaimable;
}
/*
*
* If the caller is !__GFP_FS then the probability of a failure is reasonably
* high - the zone may be full of dirty or under-writeback pages, which this
- * caller can't do much about. We kick pdflush and take explicit naps in the
- * 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.
+ * caller can't do much about. We kick the writeback threads and take explicit
+ * naps in the 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
struct scan_control *sc)
{
int priority;
- unsigned long ret = 0;
+ bool all_unreclaimable;
unsigned long total_scanned = 0;
struct reclaim_state *reclaim_state = current->reclaim_state;
- unsigned long lru_pages = 0;
struct zoneref *z;
struct zone *zone;
- enum zone_type high_zoneidx = gfp_zone(sc->gfp_mask);
+ unsigned long writeback_threshold;
+ get_mems_allowed();
delayacct_freepages_start();
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;
-
- lru_pages += zone_reclaimable_pages(zone);
- }
- }
for (priority = DEF_PRIORITY; priority >= 0; priority--) {
sc->nr_scanned = 0;
if (!priority)
disable_swap_token();
- shrink_zones(priority, zonelist, sc);
+ all_unreclaimable = shrink_zones(priority, zonelist, sc);
/*
* Don't shrink slabs when reclaiming memory from
* over limit cgroups
*/
if (scanning_global_lru(sc)) {
+ unsigned long lru_pages = 0;
+ for_each_zone_zonelist(zone, z, zonelist,
+ gfp_zone(sc->gfp_mask)) {
+ if (!cpuset_zone_allowed_hardwall(zone, GFP_KERNEL))
+ continue;
+
+ lru_pages += zone_reclaimable_pages(zone);
+ }
+
shrink_slab(sc->nr_scanned, sc->gfp_mask, lru_pages);
if (reclaim_state) {
sc->nr_reclaimed += reclaim_state->reclaimed_slab;
}
}
total_scanned += sc->nr_scanned;
- if (sc->nr_reclaimed >= sc->swap_cluster_max) {
- ret = sc->nr_reclaimed;
+ if (sc->nr_reclaimed >= sc->nr_to_reclaim)
goto out;
- }
/*
* Try to write back as many pages as we just scanned. This
* 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) {
+ writeback_threshold = sc->nr_to_reclaim + sc->nr_to_reclaim / 2;
+ if (total_scanned > writeback_threshold) {
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)
+ if (!sc->hibernation_mode && sc->nr_scanned &&
+ priority < DEF_PRIORITY - 2)
congestion_wait(BLK_RW_ASYNC, HZ/10);
}
- /* 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;
- if (scanning_global_lru(sc)) {
- for_each_zone_zonelist(zone, z, zonelist, high_zoneidx) {
-
- if (!cpuset_zone_allowed_hardwall(zone, GFP_KERNEL))
- continue;
+ delayacct_freepages_end();
+ put_mems_allowed();
- zone->prev_priority = priority;
- }
- } else
- mem_cgroup_record_reclaim_priority(sc->mem_cgroup, priority);
+ if (sc->nr_reclaimed)
+ return sc->nr_reclaimed;
- delayacct_freepages_end();
+ /* top priority shrink_zones still had more to do? don't OOM, then */
+ if (scanning_global_lru(sc) && !all_unreclaimable)
+ return 1;
- return ret;
+ return 0;
}
unsigned long try_to_free_pages(struct zonelist *zonelist, int order,
gfp_t gfp_mask, nodemask_t *nodemask)
{
+ unsigned long nr_reclaimed;
struct scan_control sc = {
.gfp_mask = gfp_mask,
.may_writepage = !laptop_mode,
- .swap_cluster_max = SWAP_CLUSTER_MAX,
+ .nr_to_reclaim = 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);
+ trace_mm_vmscan_direct_reclaim_begin(order,
+ sc.may_writepage,
+ gfp_mask);
+
+ nr_reclaimed = do_try_to_free_pages(zonelist, &sc);
+
+ trace_mm_vmscan_direct_reclaim_end(nr_reclaimed);
+
+ return nr_reclaimed;
}
#ifdef CONFIG_CGROUP_MEM_RES_CTLR
+unsigned long mem_cgroup_shrink_node_zone(struct mem_cgroup *mem,
+ gfp_t gfp_mask, bool noswap,
+ unsigned int swappiness,
+ struct zone *zone, int nid)
+{
+ struct scan_control sc = {
+ .may_writepage = !laptop_mode,
+ .may_unmap = 1,
+ .may_swap = !noswap,
+ .swappiness = swappiness,
+ .order = 0,
+ .mem_cgroup = mem,
+ };
+ nodemask_t nm = nodemask_of_node(nid);
+
+ sc.gfp_mask = (gfp_mask & GFP_RECLAIM_MASK) |
+ (GFP_HIGHUSER_MOVABLE & ~GFP_RECLAIM_MASK);
+ sc.nodemask = &nm;
+ sc.nr_reclaimed = 0;
+ sc.nr_scanned = 0;
+
+ trace_mm_vmscan_memcg_softlimit_reclaim_begin(0,
+ sc.may_writepage,
+ sc.gfp_mask);
+
+ /*
+ * NOTE: Although we can get the priority field, using it
+ * here is not a good idea, since it limits the pages we can scan.
+ * if we don't reclaim here, the shrink_zone from balance_pgdat
+ * will pick up pages from other mem cgroup's as well. We hack
+ * the priority and make it zero.
+ */
+ shrink_zone(0, zone, &sc);
+
+ trace_mm_vmscan_memcg_softlimit_reclaim_end(sc.nr_reclaimed);
+
+ return sc.nr_reclaimed;
+}
+
unsigned long try_to_free_mem_cgroup_pages(struct mem_cgroup *mem_cont,
gfp_t gfp_mask,
bool noswap,
unsigned int swappiness)
{
+ struct zonelist *zonelist;
+ unsigned long nr_reclaimed;
struct scan_control sc = {
.may_writepage = !laptop_mode,
.may_unmap = 1,
.may_swap = !noswap,
- .swap_cluster_max = SWAP_CLUSTER_MAX,
+ .nr_to_reclaim = 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;
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);
+
+ trace_mm_vmscan_memcg_reclaim_begin(0,
+ sc.may_writepage,
+ sc.gfp_mask);
+
+ nr_reclaimed = do_try_to_free_pages(zonelist, &sc);
+
+ trace_mm_vmscan_memcg_reclaim_end(nr_reclaimed);
+
+ return nr_reclaimed;
}
#endif
+/* is kswapd sleeping prematurely? */
+static int sleeping_prematurely(pg_data_t *pgdat, int order, long remaining)
+{
+ int i;
+
+ /* If a direct reclaimer woke kswapd within HZ/10, it's premature */
+ if (remaining)
+ return 1;
+
+ /* If after HZ/10, a zone is below the high mark, it's premature */
+ for (i = 0; i < pgdat->nr_zones; i++) {
+ struct zone *zone = pgdat->node_zones + i;
+
+ if (!populated_zone(zone))
+ continue;
+
+ if (zone->all_unreclaimable)
+ continue;
+
+ if (!zone_watermark_ok(zone, order, high_wmark_pages(zone),
+ 0, 0))
+ return 1;
+ }
+
+ return 0;
+}
+
/*
* For kswapd, balance_pgdat() will work across all this node's zones until
* they are all at high_wmark_pages(zone).
.gfp_mask = GFP_KERNEL,
.may_unmap = 1,
.may_swap = 1,
- .swap_cluster_max = SWAP_CLUSTER_MAX,
+ /*
+ * kswapd doesn't want to be bailed out while reclaim. because
+ * we want to put equal scanning pressure on each zone.
+ */
+ .nr_to_reclaim = ULONG_MAX,
.swappiness = vm_swappiness,
.order = order,
.mem_cgroup = NULL,
- .isolate_pages = isolate_pages_global,
};
- /*
- * temp_priority is used to remember the scanning priority at which
- * this zone was successfully refilled to
- * free_pages == high_wmark_pages(zone).
- */
- int temp_priority[MAX_NR_ZONES];
-
loop_again:
total_scanned = 0;
sc.nr_reclaimed = 0;
sc.may_writepage = !laptop_mode;
count_vm_event(PAGEOUTRUN);
- for (i = 0; i < pgdat->nr_zones; i++)
- temp_priority[i] = DEF_PRIORITY;
-
for (priority = DEF_PRIORITY; priority >= 0; priority--) {
int end_zone = 0; /* Inclusive. 0 = ZONE_DMA */
unsigned long lru_pages = 0;
+ int has_under_min_watermark_zone = 0;
/* The swap token gets in the way of swapout... */
if (!priority)
if (!populated_zone(zone))
continue;
- if (zone_is_all_unreclaimable(zone) &&
- priority != DEF_PRIORITY)
+ if (zone->all_unreclaimable && priority != DEF_PRIORITY)
continue;
/*
for (i = 0; i <= end_zone; i++) {
struct zone *zone = pgdat->node_zones + i;
int nr_slab;
+ int nid, zid;
if (!populated_zone(zone))
continue;
- if (zone_is_all_unreclaimable(zone) &&
- priority != DEF_PRIORITY)
+ if (zone->all_unreclaimable && priority != DEF_PRIORITY)
continue;
- 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;
- note_zone_scanning_priority(zone, priority);
+
+ nid = pgdat->node_id;
+ zid = zone_idx(zone);
+ /*
+ * Call soft limit reclaim before calling shrink_zone.
+ * For now we ignore the return value
+ */
+ mem_cgroup_soft_limit_reclaim(zone, order, sc.gfp_mask,
+ nid, zid);
/*
* We put equal pressure on every zone, unless one
* zone has way too many pages free already.
lru_pages);
sc.nr_reclaimed += reclaim_state->reclaimed_slab;
total_scanned += sc.nr_scanned;
- if (zone_is_all_unreclaimable(zone))
+ if (zone->all_unreclaimable)
continue;
- if (nr_slab == 0 && zone->pages_scanned >=
- (zone_reclaimable_pages(zone) * 6))
- zone_set_flag(zone,
- ZONE_ALL_UNRECLAIMABLE);
+ if (nr_slab == 0 &&
+ zone->pages_scanned >= (zone_reclaimable_pages(zone) * 6))
+ zone->all_unreclaimable = 1;
/*
* If we've done a decent amount of scanning and
* the reclaim ratio is low, start doing writepage
if (total_scanned > SWAP_CLUSTER_MAX * 2 &&
total_scanned > sc.nr_reclaimed + sc.nr_reclaimed / 2)
sc.may_writepage = 1;
+
+ if (!zone_watermark_ok(zone, order,
+ high_wmark_pages(zone), end_zone, 0)) {
+ all_zones_ok = 0;
+ /*
+ * We are still under min water mark. This
+ * means that we have a GFP_ATOMIC allocation
+ * failure risk. Hurry up!
+ */
+ if (!zone_watermark_ok(zone, order,
+ min_wmark_pages(zone), end_zone, 0))
+ has_under_min_watermark_zone = 1;
+ }
+
}
if (all_zones_ok)
break; /* kswapd: all done */
* OK, kswapd is getting into trouble. Take a nap, then take
* another pass across the zones.
*/
- if (total_scanned && priority < DEF_PRIORITY - 2)
- congestion_wait(BLK_RW_ASYNC, HZ/10);
+ if (total_scanned && (priority < DEF_PRIORITY - 2)) {
+ if (has_under_min_watermark_zone)
+ count_vm_event(KSWAPD_SKIP_CONGESTION_WAIT);
+ else
+ congestion_wait(BLK_RW_ASYNC, HZ/10);
+ }
/*
* We do this so kswapd doesn't build up large priorities for
break;
}
out:
- /*
- * Note within each zone the priority level at which this zone was
- * brought into a happy state. So that the next thread which scans this
- * zone will start out at that priority level.
- */
- for (i = 0; i < pgdat->nr_zones; i++) {
- struct zone *zone = pgdat->node_zones + i;
-
- zone->prev_priority = temp_priority[i];
- }
if (!all_zones_ok) {
cond_resched();
order = 0;
for ( ; ; ) {
unsigned long new_order;
+ int ret;
prepare_to_wait(&pgdat->kswapd_wait, &wait, TASK_INTERRUPTIBLE);
new_order = pgdat->kswapd_max_order;
*/
order = new_order;
} else {
- if (!freezing(current))
- schedule();
+ if (!freezing(current) && !kthread_should_stop()) {
+ long remaining = 0;
+
+ /* Try to sleep for a short interval */
+ if (!sleeping_prematurely(pgdat, order, remaining)) {
+ remaining = schedule_timeout(HZ/10);
+ finish_wait(&pgdat->kswapd_wait, &wait);
+ prepare_to_wait(&pgdat->kswapd_wait, &wait, TASK_INTERRUPTIBLE);
+ }
+
+ /*
+ * After a short sleep, check if it was a
+ * premature sleep. If not, then go fully
+ * to sleep until explicitly woken up
+ */
+ if (!sleeping_prematurely(pgdat, order, remaining)) {
+ trace_mm_vmscan_kswapd_sleep(pgdat->node_id);
+ schedule();
+ } else {
+ if (remaining)
+ count_vm_event(KSWAPD_LOW_WMARK_HIT_QUICKLY);
+ else
+ count_vm_event(KSWAPD_HIGH_WMARK_HIT_QUICKLY);
+ }
+ }
order = pgdat->kswapd_max_order;
}
finish_wait(&pgdat->kswapd_wait, &wait);
- if (!try_to_freeze()) {
- /* We can speed up thawing tasks if we don't call
- * balance_pgdat after returning from the refrigerator
- */
+ ret = try_to_freeze();
+ if (kthread_should_stop())
+ break;
+
+ /*
+ * We can speed up thawing tasks if we don't call balance_pgdat
+ * after returning from the refrigerator
+ */
+ if (!ret) {
+ trace_mm_vmscan_kswapd_wake(pgdat->node_id, order);
balance_pgdat(pgdat, order);
}
}
return;
if (pgdat->kswapd_max_order < order)
pgdat->kswapd_max_order = order;
+ trace_mm_vmscan_wakeup_kswapd(pgdat->node_id, zone_idx(zone), order);
if (!cpuset_zone_allowed_hardwall(zone, GFP_KERNEL))
return;
if (!waitqueue_active(&pgdat->kswapd_wait))
#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.
- *
- * For pass > 3 we also try to shrink the LRU lists that contain a few pages
- */
-static void shrink_all_zones(unsigned long nr_pages, int prio,
- int pass, struct scan_control *sc)
-{
- struct zone *zone;
- unsigned long nr_reclaimed = 0;
-
- for_each_populated_zone(zone) {
- enum lru_list l;
-
- if (zone_is_all_unreclaimable(zone) && prio != DEF_PRIORITY)
- continue;
-
- 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_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 (nr_reclaimed >= nr_pages) {
- sc->nr_reclaimed += nr_reclaimed;
- return;
- }
- }
- }
- }
- sc->nr_reclaimed += nr_reclaimed;
-}
-
-/*
- * Try to free `nr_pages' of memory, system-wide, and return the number of
+ * Try to free `nr_to_reclaim' of memory, system-wide, and return the number of
* freed pages.
*
* Rather than trying to age LRUs the aim is to preserve the overall
* LRU order by reclaiming preferentially
* inactive > active > active referenced > active mapped
*/
-unsigned long shrink_all_memory(unsigned long nr_pages)
+unsigned long shrink_all_memory(unsigned long nr_to_reclaim)
{
- unsigned long lru_pages, nr_slab;
- int pass;
struct reclaim_state reclaim_state;
struct scan_control sc = {
- .gfp_mask = GFP_KERNEL,
- .may_unmap = 0,
+ .gfp_mask = GFP_HIGHUSER_MOVABLE,
+ .may_swap = 1,
+ .may_unmap = 1,
.may_writepage = 1,
- .isolate_pages = isolate_pages_global,
- .nr_reclaimed = 0,
+ .nr_to_reclaim = nr_to_reclaim,
+ .hibernation_mode = 1,
+ .swappiness = vm_swappiness,
+ .order = 0,
};
+ struct zonelist * zonelist = node_zonelist(numa_node_id(), sc.gfp_mask);
+ struct task_struct *p = current;
+ unsigned long nr_reclaimed;
- current->reclaim_state = &reclaim_state;
-
- lru_pages = global_reclaimable_pages();
- nr_slab = global_page_state(NR_SLAB_RECLAIMABLE);
- /* If slab caches are huge, it's better to hit them first */
- while (nr_slab >= lru_pages) {
- reclaim_state.reclaimed_slab = 0;
- shrink_slab(nr_pages, sc.gfp_mask, lru_pages);
- if (!reclaim_state.reclaimed_slab)
- break;
-
- sc.nr_reclaimed += reclaim_state.reclaimed_slab;
- if (sc.nr_reclaimed >= nr_pages)
- goto out;
-
- nr_slab -= reclaim_state.reclaimed_slab;
- }
-
- /*
- * We try to shrink LRUs in 5 passes:
- * 0 = Reclaim from inactive_list only
- * 1 = Reclaim from active list but don't reclaim mapped
- * 2 = 2nd pass of type 1
- * 3 = Reclaim mapped (normal reclaim)
- * 4 = 2nd pass of type 3
- */
- for (pass = 0; pass < 5; pass++) {
- int prio;
-
- /* Force reclaiming mapped pages in the passes #3 and #4 */
- if (pass > 2)
- sc.may_unmap = 1;
-
- for (prio = DEF_PRIORITY; prio >= 0; prio--) {
- unsigned long nr_to_scan = nr_pages - sc.nr_reclaimed;
-
- sc.nr_scanned = 0;
- 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_reclaimable_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(BLK_RW_ASYNC, HZ / 10);
- }
- }
-
- /*
- * If sc.nr_reclaimed = 0, we could not shrink LRUs, but there may be
- * something in slab caches
- */
- if (!sc.nr_reclaimed) {
- do {
- reclaim_state.reclaimed_slab = 0;
- shrink_slab(nr_pages, sc.gfp_mask,
- global_reclaimable_pages());
- sc.nr_reclaimed += reclaim_state.reclaimed_slab;
- } while (sc.nr_reclaimed < nr_pages &&
- reclaim_state.reclaimed_slab > 0);
- }
+ p->flags |= PF_MEMALLOC;
+ lockdep_set_current_reclaim_state(sc.gfp_mask);
+ reclaim_state.reclaimed_slab = 0;
+ p->reclaim_state = &reclaim_state;
+ nr_reclaimed = do_try_to_free_pages(zonelist, &sc);
-out:
- current->reclaim_state = NULL;
+ p->reclaim_state = NULL;
+ lockdep_clear_current_reclaim_state();
+ p->flags &= ~PF_MEMALLOC;
- return sc.nr_reclaimed;
+ return nr_reclaimed;
}
#endif /* CONFIG_HIBERNATION */
return ret;
}
+/*
+ * Called by memory hotplug when all memory in a node is offlined.
+ */
+void kswapd_stop(int nid)
+{
+ struct task_struct *kswapd = NODE_DATA(nid)->kswapd;
+
+ if (kswapd)
+ kthread_stop(kswapd);
+}
+
static int __init kswapd_init(void)
{
int nid;
.may_writepage = !!(zone_reclaim_mode & RECLAIM_WRITE),
.may_unmap = !!(zone_reclaim_mode & RECLAIM_SWAP),
.may_swap = 1,
- .swap_cluster_max = max_t(unsigned long, nr_pages,
- SWAP_CLUSTER_MAX),
+ .nr_to_reclaim = 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;
+ unsigned long nr_slab_pages0, nr_slab_pages1;
- disable_swap_token();
cond_resched();
/*
* We need to be able to allocate from the reserves for RECLAIM_SWAP
* and RECLAIM_SWAP.
*/
p->flags |= PF_MEMALLOC | PF_SWAPWRITE;
+ lockdep_set_current_reclaim_state(gfp_mask);
reclaim_state.reclaimed_slab = 0;
p->reclaim_state = &reclaim_state;
*/
priority = ZONE_RECLAIM_PRIORITY;
do {
- note_zone_scanning_priority(zone, priority);
shrink_zone(priority, zone, &sc);
priority--;
} while (priority >= 0 && sc.nr_reclaimed < nr_pages);
}
- slab_reclaimable = zone_page_state(zone, NR_SLAB_RECLAIMABLE);
- if (slab_reclaimable > zone->min_slab_pages) {
+ nr_slab_pages0 = zone_page_state(zone, NR_SLAB_RECLAIMABLE);
+ if (nr_slab_pages0 > zone->min_slab_pages) {
/*
* shrink_slab() does not currently allow us to determine how
* many pages were freed in this zone. So we take the current
* Note that shrink_slab will free memory on all zones and may
* take a long time.
*/
- while (shrink_slab(sc.nr_scanned, gfp_mask, order) &&
- zone_page_state(zone, NR_SLAB_RECLAIMABLE) >
- slab_reclaimable - nr_pages)
- ;
+ for (;;) {
+ unsigned long lru_pages = zone_reclaimable_pages(zone);
+
+ /* No reclaimable slab or very low memory pressure */
+ if (!shrink_slab(sc.nr_scanned, gfp_mask, lru_pages))
+ break;
+
+ /* Freed enough memory */
+ nr_slab_pages1 = zone_page_state(zone,
+ NR_SLAB_RECLAIMABLE);
+ if (nr_slab_pages1 + nr_pages <= nr_slab_pages0)
+ break;
+ }
/*
* Update nr_reclaimed by the number of slab pages we
* reclaimed from this zone.
*/
- sc.nr_reclaimed += slab_reclaimable -
- zone_page_state(zone, NR_SLAB_RECLAIMABLE);
+ nr_slab_pages1 = zone_page_state(zone, NR_SLAB_RECLAIMABLE);
+ if (nr_slab_pages1 < nr_slab_pages0)
+ sc.nr_reclaimed += nr_slab_pages0 - nr_slab_pages1;
}
p->reclaim_state = NULL;
current->flags &= ~(PF_MEMALLOC | PF_SWAPWRITE);
+ lockdep_clear_current_reclaim_state();
return sc.nr_reclaimed >= nr_pages;
}
zone_page_state(zone, NR_SLAB_RECLAIMABLE) <= zone->min_slab_pages)
return ZONE_RECLAIM_FULL;
- if (zone_is_all_unreclaimable(zone))
+ if (zone->all_unreclaimable)
return ZONE_RECLAIM_FULL;
/*
unsigned long scan_unevictable_pages;
int scan_unevictable_handler(struct ctl_table *table, int write,
- struct file *file, void __user *buffer,
+ void __user *buffer,
size_t *length, loff_t *ppos)
{
- proc_doulongvec_minmax(table, write, file, buffer, length, ppos);
+ proc_doulongvec_minmax(table, write, buffer, length, ppos);
if (write && *(unsigned long *)table->data)
scan_all_zones_unevictable_pages();