#include <linux/cpuset.h>
#include <linux/notifier.h>
#include <linux/rwsem.h>
+#include <linux/delay.h>
#include <asm/tlbflush.h>
#include <asm/div64.h>
#include <linux/swapops.h>
-/* possible outcome of pageout() */
-typedef enum {
- /* failed to write page out, page is locked */
- PAGE_KEEP,
- /* move page to the active list, page is locked */
- PAGE_ACTIVATE,
- /* page has been sent to the disk successfully, page is unlocked */
- PAGE_SUCCESS,
- /* page is clean and locked */
- PAGE_CLEAN,
-} pageout_t;
+#include "internal.h"
struct scan_control {
- /* Ask refill_inactive_zone, or shrink_cache to scan this many pages */
- unsigned long nr_to_scan;
-
/* Incremented by the number of inactive pages that were scanned */
unsigned long nr_scanned;
- /* Incremented by the number of pages reclaimed */
- unsigned long nr_reclaimed;
-
unsigned long nr_mapped; /* From page_state */
- /* Ask shrink_caches, or shrink_zone to scan at this priority */
- unsigned int priority;
-
/* This context's GFP mask */
gfp_t gfp_mask;
*
* Returns the number of slab objects which we shrunk.
*/
-int shrink_slab(unsigned long scanned, gfp_t gfp_mask, unsigned long lru_pages)
+unsigned long shrink_slab(unsigned long scanned, gfp_t gfp_mask,
+ unsigned long lru_pages)
{
struct shrinker *shrinker;
- int ret = 0;
+ unsigned long ret = 0;
if (scanned == 0)
scanned = SWAP_CLUSTER_MAX;
}
/*
- * pageout is called by shrink_list() for each dirty page. Calls ->writepage().
+ * pageout is called by shrink_page_list() for each dirty page.
+ * Calls ->writepage().
*/
-static pageout_t pageout(struct page *page, struct address_space *mapping)
+pageout_t pageout(struct page *page, struct address_space *mapping)
{
/*
* If the page is dirty, only perform writeback if that write
return PAGE_CLEAN;
}
-static int remove_mapping(struct address_space *mapping, struct page *page)
+int remove_mapping(struct address_space *mapping, struct page *page)
{
if (!mapping)
return 0; /* truncate got there first */
}
/*
- * shrink_list adds the number of reclaimed pages to sc->nr_reclaimed
+ * shrink_page_list() returns the number of reclaimed pages
*/
-static int shrink_list(struct list_head *page_list, struct scan_control *sc)
+static unsigned long shrink_page_list(struct list_head *page_list,
+ struct scan_control *sc)
{
LIST_HEAD(ret_pages);
struct pagevec freed_pvec;
int pgactivate = 0;
- int reclaimed = 0;
+ unsigned long nr_reclaimed = 0;
cond_resched();
BUG_ON(PageActive(page));
sc->nr_scanned++;
+
+ if (!sc->may_swap && page_mapped(page))
+ goto keep_locked;
+
/* Double the slab pressure for mapped and swapcache pages */
if (page_mapped(page) || PageSwapCache(page))
sc->nr_scanned++;
* Anonymous process memory has backing store?
* Try to allocate it some swap space here.
*/
- if (PageAnon(page) && !PageSwapCache(page)) {
- if (!sc->may_swap)
- goto keep_locked;
+ if (PageAnon(page) && !PageSwapCache(page))
if (!add_to_swap(page, GFP_ATOMIC))
goto activate_locked;
- }
#endif /* CONFIG_SWAP */
mapping = page_mapping(page);
* processes. Try to unmap it here.
*/
if (page_mapped(page) && mapping) {
- /*
- * No unmapping if we do not swap
- */
- if (!sc->may_swap)
- goto keep_locked;
-
- switch (try_to_unmap(page)) {
+ switch (try_to_unmap(page, 0)) {
case SWAP_FAIL:
goto activate_locked;
case SWAP_AGAIN:
free_it:
unlock_page(page);
- reclaimed++;
+ nr_reclaimed++;
if (!pagevec_add(&freed_pvec, page))
__pagevec_release_nonlru(&freed_pvec);
continue;
if (pagevec_count(&freed_pvec))
__pagevec_release_nonlru(&freed_pvec);
mod_page_state(pgactivate, pgactivate);
- sc->nr_reclaimed += reclaimed;
- return reclaimed;
-}
-
-#ifdef CONFIG_MIGRATION
-static inline void move_to_lru(struct page *page)
-{
- list_del(&page->lru);
- if (PageActive(page)) {
- /*
- * lru_cache_add_active checks that
- * the PG_active bit is off.
- */
- ClearPageActive(page);
- lru_cache_add_active(page);
- } else {
- lru_cache_add(page);
- }
- put_page(page);
-}
-
-/*
- * Add isolated pages on the list back to the LRU.
- *
- * returns the number of pages put back.
- */
-int putback_lru_pages(struct list_head *l)
-{
- struct page *page;
- struct page *page2;
- int count = 0;
-
- list_for_each_entry_safe(page, page2, l, lru) {
- move_to_lru(page);
- count++;
- }
- return count;
+ return nr_reclaimed;
}
/*
- * swapout a single page
- * page is locked upon entry, unlocked on exit
- */
-static int swap_page(struct page *page)
-{
- struct address_space *mapping = page_mapping(page);
-
- if (page_mapped(page) && mapping)
- if (try_to_unmap(page) != SWAP_SUCCESS)
- goto unlock_retry;
-
- if (PageDirty(page)) {
- /* Page is dirty, try to write it out here */
- switch(pageout(page, mapping)) {
- case PAGE_KEEP:
- case PAGE_ACTIVATE:
- goto unlock_retry;
-
- case PAGE_SUCCESS:
- goto retry;
-
- case PAGE_CLEAN:
- ; /* try to free the page below */
- }
- }
-
- if (PagePrivate(page)) {
- if (!try_to_release_page(page, GFP_KERNEL) ||
- (!mapping && page_count(page) == 1))
- goto unlock_retry;
- }
-
- if (remove_mapping(mapping, page)) {
- /* Success */
- unlock_page(page);
- return 0;
- }
-
-unlock_retry:
- unlock_page(page);
-
-retry:
- return -EAGAIN;
-}
-/*
- * migrate_pages
- *
- * Two lists are passed to this function. The first list
- * contains the pages isolated from the LRU to be migrated.
- * The second list contains new pages that the pages isolated
- * can be moved to. If the second list is NULL then all
- * pages are swapped out.
- *
- * The function returns after 10 attempts or if no pages
- * are movable anymore because t has become empty
- * or no retryable pages exist anymore.
- *
- * SIMPLIFIED VERSION: This implementation of migrate_pages
- * is only swapping out pages and never touches the second
- * list. The direct migration patchset
- * extends this function to avoid the use of swap.
- *
- * Return: Number of pages not migrated when "to" ran empty.
- */
-int migrate_pages(struct list_head *from, struct list_head *to,
- struct list_head *moved, struct list_head *failed)
-{
- int retry;
- int nr_failed = 0;
- int pass = 0;
- struct page *page;
- struct page *page2;
- int swapwrite = current->flags & PF_SWAPWRITE;
- int rc;
-
- if (!swapwrite)
- current->flags |= PF_SWAPWRITE;
-
-redo:
- retry = 0;
-
- list_for_each_entry_safe(page, page2, from, lru) {
- cond_resched();
-
- rc = 0;
- if (page_count(page) == 1)
- /* page was freed from under us. So we are done. */
- goto next;
-
- /*
- * Skip locked pages during the first two passes to give the
- * functions holding the lock time to release the page. Later we
- * use lock_page() to have a higher chance of acquiring the
- * lock.
- */
- rc = -EAGAIN;
- if (pass > 2)
- lock_page(page);
- else
- if (TestSetPageLocked(page))
- goto next;
-
- /*
- * Only wait on writeback if we have already done a pass where
- * we we may have triggered writeouts for lots of pages.
- */
- if (pass > 0) {
- wait_on_page_writeback(page);
- } else {
- if (PageWriteback(page))
- goto unlock_page;
- }
-
- /*
- * Anonymous pages must have swap cache references otherwise
- * the information contained in the page maps cannot be
- * preserved.
- */
- if (PageAnon(page) && !PageSwapCache(page)) {
- if (!add_to_swap(page, GFP_KERNEL)) {
- rc = -ENOMEM;
- goto unlock_page;
- }
- }
-
- /*
- * Page is properly locked and writeback is complete.
- * Try to migrate the page.
- */
- rc = swap_page(page);
- goto next;
-
-unlock_page:
- unlock_page(page);
-
-next:
- if (rc == -EAGAIN) {
- retry++;
- } else if (rc) {
- /* Permanent failure */
- list_move(&page->lru, failed);
- nr_failed++;
- } else {
- /* Success */
- list_move(&page->lru, moved);
- }
- }
- if (retry && pass++ < 10)
- goto redo;
-
- if (!swapwrite)
- current->flags &= ~PF_SWAPWRITE;
-
- return nr_failed + retry;
-}
-
-/*
- * Isolate one page from the LRU lists and put it on the
- * indicated list with elevated refcount.
- *
- * Result:
- * 0 = page not on LRU list
- * 1 = page removed from LRU list and added to the specified list.
- */
-int isolate_lru_page(struct page *page)
-{
- int ret = 0;
-
- if (PageLRU(page)) {
- struct zone *zone = page_zone(page);
- spin_lock_irq(&zone->lru_lock);
- if (TestClearPageLRU(page)) {
- ret = 1;
- get_page(page);
- if (PageActive(page))
- del_page_from_active_list(zone, page);
- else
- del_page_from_inactive_list(zone, page);
- }
- spin_unlock_irq(&zone->lru_lock);
- }
-
- return ret;
-}
-#endif
-
-/*
* zone->lru_lock is heavily contended. Some of the functions that
* shrink the lists perform better by taking out a batch of pages
* and working on them outside the LRU lock.
*
* returns how many pages were moved onto *@dst.
*/
-static int isolate_lru_pages(int nr_to_scan, struct list_head *src,
- struct list_head *dst, int *scanned)
+static unsigned long isolate_lru_pages(unsigned long nr_to_scan,
+ struct list_head *src, struct list_head *dst,
+ unsigned long *scanned)
{
- int nr_taken = 0;
+ unsigned long nr_taken = 0;
struct page *page;
- int scan = 0;
+ unsigned long scan;
- while (scan++ < nr_to_scan && !list_empty(src)) {
+ for (scan = 0; scan < nr_to_scan && !list_empty(src); scan++) {
+ struct list_head *target;
page = lru_to_page(src);
prefetchw_prev_lru_page(page, src, flags);
- if (!TestClearPageLRU(page))
- BUG();
+ BUG_ON(!PageLRU(page));
+
list_del(&page->lru);
- if (get_page_testone(page)) {
+ target = src;
+ if (likely(get_page_unless_zero(page))) {
/*
- * It is being freed elsewhere
+ * Be careful not to clear PageLRU until after we're
+ * sure the page is not being freed elsewhere -- the
+ * page release code relies on it.
*/
- __put_page(page);
- SetPageLRU(page);
- list_add(&page->lru, src);
- continue;
- } else {
- list_add(&page->lru, dst);
+ ClearPageLRU(page);
+ target = dst;
nr_taken++;
- }
+ } /* else it is being freed elsewhere */
+
+ list_add(&page->lru, target);
}
*scanned = scan;
}
/*
- * shrink_cache() adds the number of pages reclaimed to sc->nr_reclaimed
+ * shrink_inactive_list() is a helper for shrink_zone(). It returns the number
+ * of reclaimed pages
*/
-static void shrink_cache(struct zone *zone, struct scan_control *sc)
+static unsigned long shrink_inactive_list(unsigned long max_scan,
+ struct zone *zone, struct scan_control *sc)
{
LIST_HEAD(page_list);
struct pagevec pvec;
- int max_scan = sc->nr_to_scan;
+ unsigned long nr_scanned = 0;
+ unsigned long nr_reclaimed = 0;
pagevec_init(&pvec, 1);
lru_add_drain();
spin_lock_irq(&zone->lru_lock);
- while (max_scan > 0) {
+ do {
struct page *page;
- int nr_taken;
- int nr_scan;
- int nr_freed;
+ unsigned long nr_taken;
+ unsigned long nr_scan;
+ unsigned long nr_freed;
nr_taken = isolate_lru_pages(sc->swap_cluster_max,
&zone->inactive_list,
zone->pages_scanned += nr_scan;
spin_unlock_irq(&zone->lru_lock);
- if (nr_taken == 0)
- goto done;
-
- max_scan -= nr_scan;
- nr_freed = shrink_list(&page_list, sc);
-
+ nr_scanned += nr_scan;
+ nr_freed = shrink_page_list(&page_list, sc);
+ nr_reclaimed += nr_freed;
local_irq_disable();
if (current_is_kswapd()) {
__mod_page_state_zone(zone, pgscan_kswapd, nr_scan);
__mod_page_state_zone(zone, pgscan_direct, nr_scan);
__mod_page_state_zone(zone, pgsteal, nr_freed);
+ if (nr_taken == 0)
+ goto done;
+
spin_lock(&zone->lru_lock);
/*
* Put back any unfreeable pages.
*/
while (!list_empty(&page_list)) {
page = lru_to_page(&page_list);
- if (TestSetPageLRU(page))
- BUG();
+ BUG_ON(PageLRU(page));
+ SetPageLRU(page);
list_del(&page->lru);
if (PageActive(page))
add_page_to_active_list(zone, page);
spin_lock_irq(&zone->lru_lock);
}
}
- }
- spin_unlock_irq(&zone->lru_lock);
+ } while (nr_scanned < max_scan);
+ spin_unlock(&zone->lru_lock);
done:
+ local_irq_enable();
pagevec_release(&pvec);
+ return nr_reclaimed;
}
/*
* The downside is that we have to touch page->_count against each page.
* But we had to alter page->flags anyway.
*/
-static void
-refill_inactive_zone(struct zone *zone, struct scan_control *sc)
+static void shrink_active_list(unsigned long nr_pages, struct zone *zone,
+ struct scan_control *sc)
{
- int pgmoved;
+ unsigned long pgmoved;
int pgdeactivate = 0;
- int pgscanned;
- int nr_pages = sc->nr_to_scan;
+ unsigned long pgscanned;
LIST_HEAD(l_hold); /* The pages which were snipped off */
LIST_HEAD(l_inactive); /* Pages to go onto the inactive_list */
LIST_HEAD(l_active); /* Pages to go onto the active_list */
struct page *page;
struct pagevec pvec;
int reclaim_mapped = 0;
- long mapped_ratio;
- long distress;
- long swap_tendency;
+
+ if (sc->may_swap) {
+ long mapped_ratio;
+ long distress;
+ long swap_tendency;
+
+ /*
+ * `distress' is a measure of how much trouble we're having
+ * reclaiming pages. 0 -> no problems. 100 -> great trouble.
+ */
+ distress = 100 >> zone->prev_priority;
+
+ /*
+ * The point of this algorithm is to decide when to start
+ * reclaiming mapped memory instead of just pagecache. Work out
+ * how much memory
+ * is mapped.
+ */
+ mapped_ratio = (sc->nr_mapped * 100) / total_memory;
+
+ /*
+ * Now decide how much we really want to unmap some pages. The
+ * mapped ratio is downgraded - just because there's a lot of
+ * mapped memory doesn't necessarily mean that page reclaim
+ * isn't succeeding.
+ *
+ * The distress ratio is important - we don't want to start
+ * going oom.
+ *
+ * A 100% value of vm_swappiness overrides this algorithm
+ * altogether.
+ */
+ swap_tendency = mapped_ratio / 2 + distress + vm_swappiness;
+
+ /*
+ * Now use this metric to decide whether to start moving mapped
+ * memory onto the inactive list.
+ */
+ if (swap_tendency >= 100)
+ reclaim_mapped = 1;
+ }
lru_add_drain();
spin_lock_irq(&zone->lru_lock);
zone->nr_active -= pgmoved;
spin_unlock_irq(&zone->lru_lock);
- /*
- * `distress' is a measure of how much trouble we're having reclaiming
- * pages. 0 -> no problems. 100 -> great trouble.
- */
- distress = 100 >> zone->prev_priority;
-
- /*
- * The point of this algorithm is to decide when to start reclaiming
- * mapped memory instead of just pagecache. Work out how much memory
- * is mapped.
- */
- mapped_ratio = (sc->nr_mapped * 100) / total_memory;
-
- /*
- * Now decide how much we really want to unmap some pages. The mapped
- * ratio is downgraded - just because there's a lot of mapped memory
- * doesn't necessarily mean that page reclaim isn't succeeding.
- *
- * The distress ratio is important - we don't want to start going oom.
- *
- * A 100% value of vm_swappiness overrides this algorithm altogether.
- */
- swap_tendency = mapped_ratio / 2 + distress + vm_swappiness;
-
- /*
- * Now use this metric to decide whether to start moving mapped memory
- * onto the inactive list.
- */
- if (swap_tendency >= 100)
- reclaim_mapped = 1;
-
while (!list_empty(&l_hold)) {
cond_resched();
page = lru_to_page(&l_hold);
while (!list_empty(&l_inactive)) {
page = lru_to_page(&l_inactive);
prefetchw_prev_lru_page(page, &l_inactive, flags);
- if (TestSetPageLRU(page))
- BUG();
- if (!TestClearPageActive(page))
- BUG();
+ BUG_ON(PageLRU(page));
+ SetPageLRU(page);
+ BUG_ON(!PageActive(page));
+ ClearPageActive(page);
+
list_move(&page->lru, &zone->inactive_list);
pgmoved++;
if (!pagevec_add(&pvec, page)) {
while (!list_empty(&l_active)) {
page = lru_to_page(&l_active);
prefetchw_prev_lru_page(page, &l_active, flags);
- if (TestSetPageLRU(page))
- BUG();
+ BUG_ON(PageLRU(page));
+ SetPageLRU(page);
BUG_ON(!PageActive(page));
list_move(&page->lru, &zone->active_list);
pgmoved++;
/*
* This is a basic per-zone page freer. Used by both kswapd and direct reclaim.
*/
-static void
-shrink_zone(struct zone *zone, struct scan_control *sc)
+static unsigned long shrink_zone(int priority, struct zone *zone,
+ struct scan_control *sc)
{
unsigned long nr_active;
unsigned long nr_inactive;
+ unsigned long nr_to_scan;
+ unsigned long nr_reclaimed = 0;
atomic_inc(&zone->reclaim_in_progress);
* Add one to `nr_to_scan' just to make sure that the kernel will
* slowly sift through the active list.
*/
- zone->nr_scan_active += (zone->nr_active >> sc->priority) + 1;
+ zone->nr_scan_active += (zone->nr_active >> priority) + 1;
nr_active = zone->nr_scan_active;
if (nr_active >= sc->swap_cluster_max)
zone->nr_scan_active = 0;
else
nr_active = 0;
- zone->nr_scan_inactive += (zone->nr_inactive >> sc->priority) + 1;
+ zone->nr_scan_inactive += (zone->nr_inactive >> priority) + 1;
nr_inactive = zone->nr_scan_inactive;
if (nr_inactive >= sc->swap_cluster_max)
zone->nr_scan_inactive = 0;
while (nr_active || nr_inactive) {
if (nr_active) {
- sc->nr_to_scan = min(nr_active,
+ nr_to_scan = min(nr_active,
(unsigned long)sc->swap_cluster_max);
- nr_active -= sc->nr_to_scan;
- refill_inactive_zone(zone, sc);
+ nr_active -= nr_to_scan;
+ shrink_active_list(nr_to_scan, zone, sc);
}
if (nr_inactive) {
- sc->nr_to_scan = min(nr_inactive,
+ nr_to_scan = min(nr_inactive,
(unsigned long)sc->swap_cluster_max);
- nr_inactive -= sc->nr_to_scan;
- shrink_cache(zone, sc);
+ nr_inactive -= nr_to_scan;
+ nr_reclaimed += shrink_inactive_list(nr_to_scan, zone,
+ sc);
}
}
throttle_vm_writeout();
atomic_dec(&zone->reclaim_in_progress);
+ return nr_reclaimed;
}
/*
* If a zone is deemed to be full of pinned pages then just give it a light
* scan then give up on it.
*/
-static void
-shrink_caches(struct zone **zones, struct scan_control *sc)
+static unsigned long shrink_zones(int priority, struct zone **zones,
+ struct scan_control *sc)
{
+ unsigned long nr_reclaimed = 0;
int i;
for (i = 0; zones[i] != NULL; i++) {
if (!cpuset_zone_allowed(zone, __GFP_HARDWALL))
continue;
- zone->temp_priority = sc->priority;
- if (zone->prev_priority > sc->priority)
- zone->prev_priority = sc->priority;
+ zone->temp_priority = priority;
+ if (zone->prev_priority > priority)
+ zone->prev_priority = priority;
- if (zone->all_unreclaimable && sc->priority != DEF_PRIORITY)
+ if (zone->all_unreclaimable && priority != DEF_PRIORITY)
continue; /* Let kswapd poll it */
- shrink_zone(zone, sc);
+ nr_reclaimed += shrink_zone(priority, zone, sc);
}
+ return nr_reclaimed;
}
/*
* holds filesystem locks which prevent writeout this might not work, and the
* allocation attempt will fail.
*/
-int try_to_free_pages(struct zone **zones, gfp_t gfp_mask)
+unsigned long try_to_free_pages(struct zone **zones, gfp_t gfp_mask)
{
int priority;
int ret = 0;
- int total_scanned = 0, total_reclaimed = 0;
+ unsigned long total_scanned = 0;
+ unsigned long nr_reclaimed = 0;
struct reclaim_state *reclaim_state = current->reclaim_state;
- struct scan_control sc;
unsigned long lru_pages = 0;
int i;
-
- sc.gfp_mask = gfp_mask;
- sc.may_writepage = !laptop_mode;
- sc.may_swap = 1;
+ struct scan_control sc = {
+ .gfp_mask = gfp_mask,
+ .may_writepage = !laptop_mode,
+ .swap_cluster_max = SWAP_CLUSTER_MAX,
+ .may_swap = 1,
+ };
inc_page_state(allocstall);
for (priority = DEF_PRIORITY; priority >= 0; priority--) {
sc.nr_mapped = read_page_state(nr_mapped);
sc.nr_scanned = 0;
- sc.nr_reclaimed = 0;
- sc.priority = priority;
- sc.swap_cluster_max = SWAP_CLUSTER_MAX;
if (!priority)
disable_swap_token();
- shrink_caches(zones, &sc);
+ nr_reclaimed += shrink_zones(priority, zones, &sc);
shrink_slab(sc.nr_scanned, gfp_mask, lru_pages);
if (reclaim_state) {
- sc.nr_reclaimed += reclaim_state->reclaimed_slab;
+ nr_reclaimed += reclaim_state->reclaimed_slab;
reclaim_state->reclaimed_slab = 0;
}
total_scanned += sc.nr_scanned;
- total_reclaimed += sc.nr_reclaimed;
- if (total_reclaimed >= sc.swap_cluster_max) {
+ if (nr_reclaimed >= sc.swap_cluster_max) {
ret = 1;
goto out;
}
* that's undesirable in laptop mode, where we *want* lumpy
* writeout. So in laptop mode, write out the whole world.
*/
- if (total_scanned > sc.swap_cluster_max + sc.swap_cluster_max/2) {
+ if (total_scanned > sc.swap_cluster_max +
+ sc.swap_cluster_max / 2) {
wakeup_pdflush(laptop_mode ? 0 : total_scanned);
sc.may_writepage = 1;
}
* the page allocator fallback scheme to ensure that aging of pages is balanced
* across the zones.
*/
-static int balance_pgdat(pg_data_t *pgdat, int nr_pages, int order)
+static unsigned long balance_pgdat(pg_data_t *pgdat, unsigned long nr_pages,
+ int order)
{
- int to_free = nr_pages;
+ unsigned long to_free = nr_pages;
int all_zones_ok;
int priority;
int i;
- int total_scanned, total_reclaimed;
+ unsigned long total_scanned;
+ unsigned long nr_reclaimed;
struct reclaim_state *reclaim_state = current->reclaim_state;
- struct scan_control sc;
+ struct scan_control sc = {
+ .gfp_mask = GFP_KERNEL,
+ .may_swap = 1,
+ .swap_cluster_max = nr_pages ? nr_pages : SWAP_CLUSTER_MAX,
+ };
loop_again:
total_scanned = 0;
- total_reclaimed = 0;
- sc.gfp_mask = GFP_KERNEL;
- sc.may_writepage = !laptop_mode;
- sc.may_swap = 1;
+ nr_reclaimed = 0;
+ sc.may_writepage = !laptop_mode,
sc.nr_mapped = read_page_state(nr_mapped);
inc_page_state(pageoutrun);
if (zone->prev_priority > priority)
zone->prev_priority = priority;
sc.nr_scanned = 0;
- sc.nr_reclaimed = 0;
- sc.priority = priority;
- sc.swap_cluster_max = nr_pages? nr_pages : SWAP_CLUSTER_MAX;
- atomic_inc(&zone->reclaim_in_progress);
- shrink_zone(zone, &sc);
- atomic_dec(&zone->reclaim_in_progress);
+ nr_reclaimed += shrink_zone(priority, zone, &sc);
reclaim_state->reclaimed_slab = 0;
nr_slab = shrink_slab(sc.nr_scanned, GFP_KERNEL,
lru_pages);
- sc.nr_reclaimed += reclaim_state->reclaimed_slab;
- total_reclaimed += sc.nr_reclaimed;
+ nr_reclaimed += reclaim_state->reclaimed_slab;
total_scanned += sc.nr_scanned;
if (zone->all_unreclaimable)
continue;
* even in laptop mode
*/
if (total_scanned > SWAP_CLUSTER_MAX * 2 &&
- total_scanned > total_reclaimed+total_reclaimed/2)
+ total_scanned > nr_reclaimed + nr_reclaimed / 2)
sc.may_writepage = 1;
}
- if (nr_pages && to_free > total_reclaimed)
+ if (nr_pages && to_free > nr_reclaimed)
continue; /* swsusp: need to do more work */
if (all_zones_ok)
break; /* kswapd: all done */
* matches the direct reclaim path behaviour in terms of impact
* on zone->*_priority.
*/
- if ((total_reclaimed >= SWAP_CLUSTER_MAX) && (!nr_pages))
+ if ((nr_reclaimed >= SWAP_CLUSTER_MAX) && !nr_pages)
break;
}
out:
goto loop_again;
}
- return total_reclaimed;
+ return nr_reclaimed;
}
/*
* Try to free `nr_pages' of memory, system-wide. Returns the number of freed
* pages.
*/
-int shrink_all_memory(int nr_pages)
+unsigned long shrink_all_memory(unsigned long nr_pages)
{
pg_data_t *pgdat;
- int nr_to_free = nr_pages;
- int ret = 0;
+ unsigned long nr_to_free = nr_pages;
+ unsigned long ret = 0;
+ unsigned retry = 2;
struct reclaim_state reclaim_state = {
.reclaimed_slab = 0,
};
current->reclaim_state = &reclaim_state;
- for_each_pgdat(pgdat) {
- int freed;
+repeat:
+ for_each_online_pgdat(pgdat) {
+ unsigned long freed;
+
freed = balance_pgdat(pgdat, nr_to_free, 0);
ret += freed;
nr_to_free -= freed;
- if (nr_to_free <= 0)
+ if ((long)nr_to_free <= 0)
break;
}
+ if (retry-- && ret < nr_pages) {
+ blk_congestion_wait(WRITE, HZ/5);
+ goto repeat;
+ }
current->reclaim_state = NULL;
return ret;
}
not required for correctness. So if the last cpu in a node goes
away, we get changed to run anywhere: as the first one comes back,
restore their cpu bindings. */
-static int __devinit cpu_callback(struct notifier_block *nfb,
- unsigned long action,
- void *hcpu)
+static int cpu_callback(struct notifier_block *nfb,
+ unsigned long action, void *hcpu)
{
pg_data_t *pgdat;
cpumask_t mask;
if (action == CPU_ONLINE) {
- for_each_pgdat(pgdat) {
+ for_each_online_pgdat(pgdat) {
mask = node_to_cpumask(pgdat->node_id);
if (any_online_cpu(mask) != NR_CPUS)
/* One of our CPUs online: restore mask */
static int __init kswapd_init(void)
{
pg_data_t *pgdat;
+
swap_setup();
- for_each_pgdat(pgdat)
- pgdat->kswapd
- = find_task_by_pid(kernel_thread(kswapd, pgdat, CLONE_KERNEL));
+ for_each_online_pgdat(pgdat) {
+ pid_t pid;
+
+ pid = kernel_thread(kswapd, pgdat, CLONE_KERNEL);
+ BUG_ON(pid < 0);
+ read_lock(&tasklist_lock);
+ pgdat->kswapd = find_task_by_pid(pid);
+ read_unlock(&tasklist_lock);
+ }
total_memory = nr_free_pagecache_pages();
hotcpu_notifier(cpu_callback, 0);
return 0;
*/
int zone_reclaim_mode __read_mostly;
+#define RECLAIM_OFF 0
+#define RECLAIM_ZONE (1<<0) /* Run shrink_cache on the zone */
+#define RECLAIM_WRITE (1<<1) /* Writeout pages during reclaim */
+#define RECLAIM_SWAP (1<<2) /* Swap pages out during reclaim */
+#define RECLAIM_SLAB (1<<3) /* Do a global slab shrink if the zone is out of memory */
+
/*
* Mininum time between zone reclaim scans
*/
/*
* Try to free up some pages from this zone through reclaim.
*/
-int zone_reclaim(struct zone *zone, gfp_t gfp_mask, unsigned int order)
+static int __zone_reclaim(struct zone *zone, gfp_t gfp_mask, unsigned int order)
{
- int nr_pages;
+ /* Minimum pages needed in order to stay on node */
+ const unsigned long nr_pages = 1 << order;
struct task_struct *p = current;
struct reclaim_state reclaim_state;
- struct scan_control sc;
- cpumask_t mask;
- int node_id;
-
- if (time_before(jiffies,
- zone->last_unsuccessful_zone_reclaim + zone_reclaim_interval))
- return 0;
-
- if (!(gfp_mask & __GFP_WAIT) ||
- zone->all_unreclaimable ||
- atomic_read(&zone->reclaim_in_progress) > 0)
- return 0;
-
- node_id = zone->zone_pgdat->node_id;
- mask = node_to_cpumask(node_id);
- if (!cpus_empty(mask) && node_id != numa_node_id())
- return 0;
-
- sc.may_writepage = 0;
- sc.may_swap = 0;
- sc.nr_scanned = 0;
- sc.nr_reclaimed = 0;
- sc.priority = ZONE_RECLAIM_PRIORITY + 1;
- sc.nr_mapped = read_page_state(nr_mapped);
- sc.gfp_mask = gfp_mask;
+ int priority;
+ unsigned long nr_reclaimed = 0;
+ struct scan_control sc = {
+ .may_writepage = !!(zone_reclaim_mode & RECLAIM_WRITE),
+ .may_swap = !!(zone_reclaim_mode & RECLAIM_SWAP),
+ .nr_mapped = read_page_state(nr_mapped),
+ .swap_cluster_max = max_t(unsigned long, nr_pages,
+ SWAP_CLUSTER_MAX),
+ .gfp_mask = gfp_mask,
+ };
disable_swap_token();
-
- nr_pages = 1 << order;
- if (nr_pages > SWAP_CLUSTER_MAX)
- sc.swap_cluster_max = nr_pages;
- else
- sc.swap_cluster_max = SWAP_CLUSTER_MAX;
-
cond_resched();
- p->flags |= PF_MEMALLOC;
+ /*
+ * We need to be able to allocate from the reserves for RECLAIM_SWAP
+ * and we also need to be able to write out pages for RECLAIM_WRITE
+ * and RECLAIM_SWAP.
+ */
+ p->flags |= PF_MEMALLOC | PF_SWAPWRITE;
reclaim_state.reclaimed_slab = 0;
p->reclaim_state = &reclaim_state;
* Free memory by calling shrink zone with increasing priorities
* until we have enough memory freed.
*/
+ priority = ZONE_RECLAIM_PRIORITY;
do {
- sc.priority--;
- shrink_zone(zone, &sc);
+ nr_reclaimed += shrink_zone(priority, zone, &sc);
+ priority--;
+ } while (priority >= 0 && nr_reclaimed < nr_pages);
- } while (sc.nr_reclaimed < nr_pages && sc.priority > 0);
+ if (nr_reclaimed < nr_pages && (zone_reclaim_mode & RECLAIM_SLAB)) {
+ /*
+ * shrink_slab() does not currently allow us to determine how
+ * many pages were freed in this zone. So we just shake the slab
+ * a bit and then go off node for this particular allocation
+ * despite possibly having freed enough memory to allocate in
+ * this zone. If we freed local memory then the next
+ * allocations will be local again.
+ *
+ * shrink_slab will free memory on all zones and may take
+ * a long time.
+ */
+ shrink_slab(sc.nr_scanned, gfp_mask, order);
+ }
p->reclaim_state = NULL;
- current->flags &= ~PF_MEMALLOC;
+ current->flags &= ~(PF_MEMALLOC | PF_SWAPWRITE);
- if (sc.nr_reclaimed == 0)
+ if (nr_reclaimed == 0) {
+ /*
+ * We were unable to reclaim enough pages to stay on node. We
+ * now allow off node accesses for a certain time period before
+ * trying again to reclaim pages from the local zone.
+ */
zone->last_unsuccessful_zone_reclaim = jiffies;
+ }
- return sc.nr_reclaimed >= nr_pages;
+ return nr_reclaimed >= nr_pages;
}
-#endif
+int zone_reclaim(struct zone *zone, gfp_t gfp_mask, unsigned int order)
+{
+ cpumask_t mask;
+ int node_id;
+
+ /*
+ * Do not reclaim if there was a recent unsuccessful attempt at zone
+ * reclaim. In that case we let allocations go off node for the
+ * zone_reclaim_interval. Otherwise we would scan for each off-node
+ * page allocation.
+ */
+ if (time_before(jiffies,
+ zone->last_unsuccessful_zone_reclaim + zone_reclaim_interval))
+ return 0;
+
+ /*
+ * Avoid concurrent zone reclaims, do not reclaim in a zone that does
+ * not have reclaimable pages and if we should not delay the allocation
+ * then do not scan.
+ */
+ if (!(gfp_mask & __GFP_WAIT) ||
+ zone->all_unreclaimable ||
+ atomic_read(&zone->reclaim_in_progress) > 0 ||
+ (current->flags & PF_MEMALLOC))
+ return 0;
+
+ /*
+ * Only run zone reclaim on the local zone or on zones that do not
+ * have associated processors. This will favor the local processor
+ * over remote processors and spread off node memory allocations
+ * as wide as possible.
+ */
+ node_id = zone->zone_pgdat->node_id;
+ mask = node_to_cpumask(node_id);
+ if (!cpus_empty(mask) && node_id != numa_node_id())
+ return 0;
+ return __zone_reclaim(zone, gfp_mask, order);
+}
+#endif