#include <linux/pagemap.h>
#include <linux/init.h>
#include <linux/highmem.h>
+#include <linux/vmstat.h>
#include <linux/file.h>
#include <linux/writeback.h>
#include <linux/blkdev.h>
#include <linux/rwsem.h>
#include <linux/delay.h>
#include <linux/kthread.h>
+#include <linux/freezer.h>
#include <asm/tlbflush.h>
#include <asm/div64.h>
/* synchronous write or broken a_ops? */
ClearPageReclaim(page);
}
-
+ inc_zone_page_state(page, NR_VMSCAN_WRITE);
return PAGE_SUCCESS;
}
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.
+ */
int remove_mapping(struct address_space *mapping, struct page *page)
{
- if (!mapping)
- return 0; /* truncate got there first */
+ BUG_ON(!PageLocked(page));
+ BUG_ON(mapping != page_mapping(page));
write_lock_irq(&mapping->tree_lock);
-
/*
- * The non-racy check for busy page. It is critical to check
- * PageDirty _after_ making sure that the page is freeable and
- * not in use by anybody. (pagecache + us == 2)
+ * The non racy check for a busy page.
+ *
+ * Must be careful with the order of the tests. When someone has
+ * a ref to the page, it may be possible that they dirty it then
+ * drop the reference. So if PageDirty is tested before page_count
+ * here, then the following race may occur:
+ *
+ * get_user_pages(&page);
+ * [user mapping goes away]
+ * write_to(page);
+ * !PageDirty(page) [good]
+ * SetPageDirty(page);
+ * put_page(page);
+ * !page_count(page) [good, discard it]
+ *
+ * [oops, our write_to data is lost]
+ *
+ * Reversing the order of the tests ensures such a situation cannot
+ * escape unnoticed. The smp_rmb is needed to ensure the page->flags
+ * load is not satisfied before that of page->_count.
+ *
+ * Note that if SetPageDirty is always performed via set_page_dirty,
+ * and thus under tree_lock, then this ordering is not required.
*/
if (unlikely(page_count(page) != 2))
goto cannot_free;
if (TestSetPageLocked(page))
goto keep;
- BUG_ON(PageActive(page));
+ VM_BUG_ON(PageActive(page));
sc->nr_scanned++;
goto free_it;
}
- if (!remove_mapping(mapping, page))
+ if (!mapping || !remove_mapping(mapping, page))
goto keep_locked;
free_it:
unlock_page(page);
keep:
list_add(&page->lru, &ret_pages);
- BUG_ON(PageLRU(page));
+ VM_BUG_ON(PageLRU(page));
}
list_splice(&ret_pages, page_list);
if (pagevec_count(&freed_pvec))
page = lru_to_page(src);
prefetchw_prev_lru_page(page, src, flags);
- BUG_ON(!PageLRU(page));
+ VM_BUG_ON(!PageLRU(page));
list_del(&page->lru);
target = src;
__count_vm_events(KSWAPD_STEAL, nr_freed);
} else
__count_zone_vm_events(PGSCAN_DIRECT, zone, nr_scan);
- __count_vm_events(PGACTIVATE, nr_freed);
+ __count_zone_vm_events(PGSTEAL, zone, nr_freed);
if (nr_taken == 0)
goto done;
*/
while (!list_empty(&page_list)) {
page = lru_to_page(&page_list);
- BUG_ON(PageLRU(page));
+ VM_BUG_ON(PageLRU(page));
SetPageLRU(page);
list_del(&page->lru);
if (PageActive(page))
while (!list_empty(&l_inactive)) {
page = lru_to_page(&l_inactive);
prefetchw_prev_lru_page(page, &l_inactive, flags);
- BUG_ON(PageLRU(page));
+ VM_BUG_ON(PageLRU(page));
SetPageLRU(page);
- BUG_ON(!PageActive(page));
+ VM_BUG_ON(!PageActive(page));
ClearPageActive(page);
list_move(&page->lru, &zone->inactive_list);
while (!list_empty(&l_active)) {
page = lru_to_page(&l_active);
prefetchw_prev_lru_page(page, &l_active, flags);
- BUG_ON(PageLRU(page));
+ VM_BUG_ON(PageLRU(page));
SetPageLRU(page);
- BUG_ON(!PageActive(page));
+ VM_BUG_ON(!PageActive(page));
list_move(&page->lru, &zone->active_list);
pgmoved++;
if (!pagevec_add(&pvec, page)) {
}
}
- throttle_vm_writeout();
+ throttle_vm_writeout(sc->gfp_mask);
atomic_dec(&zone->reclaim_in_progress);
return nr_reclaimed;
if (!populated_zone(zone))
continue;
- if (!cpuset_zone_allowed(zone, __GFP_HARDWALL))
+ if (!cpuset_zone_allowed_hardwall(zone, GFP_KERNEL))
continue;
note_zone_scanning_priority(zone, priority);
for (i = 0; zones[i] != NULL; i++) {
struct zone *zone = zones[i];
- if (!cpuset_zone_allowed(zone, __GFP_HARDWALL))
+ if (!cpuset_zone_allowed_hardwall(zone, GFP_KERNEL))
continue;
lru_pages += zone->nr_active + zone->nr_inactive;
/* Take a nap, wait for some writeback to complete */
if (sc.nr_scanned && priority < DEF_PRIORITY - 2)
- blk_congestion_wait(WRITE, HZ/10);
+ congestion_wait(WRITE, HZ/10);
}
/* top priority shrink_caches still had more to do? don't OOM, then */
- if (!sc.all_unreclaimable || nr_reclaimed)
+ if (!sc.all_unreclaimable)
ret = 1;
-
out:
/*
* Now that we've scanned all the zones at this priority level, note
for (i = 0; zones[i] != 0; i++) {
struct zone *zone = zones[i];
- if (!cpuset_zone_allowed(zone, __GFP_HARDWALL))
+ if (!cpuset_zone_allowed_hardwall(zone, GFP_KERNEL))
continue;
zone->prev_priority = priority;
if (!zone_watermark_ok(zone, order, zone->pages_high,
0, 0)) {
end_zone = i;
- goto scan;
+ break;
}
}
- goto out;
-scan:
+ if (i < 0)
+ goto out;
+
for (i = 0; i <= end_zone; i++) {
struct zone *zone = pgdat->node_zones + i;
* another pass across the zones.
*/
if (total_scanned && priority < DEF_PRIORITY - 2)
- blk_congestion_wait(WRITE, HZ/10);
+ congestion_wait(WRITE, HZ/10);
/*
* We do this so kswapd doesn't build up large priorities for
}
if (!all_zones_ok) {
cond_resched();
+
+ try_to_freeze();
+
goto loop_again;
}
return;
if (pgdat->kswapd_max_order < order)
pgdat->kswapd_max_order = order;
- if (!cpuset_zone_allowed(zone, __GFP_HARDWALL))
+ if (!cpuset_zone_allowed_hardwall(zone, GFP_KERNEL))
return;
if (!waitqueue_active(&pgdat->kswapd_wait))
return;
*
* 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 pass,
- int prio, struct scan_control *sc)
+static unsigned long 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;
return ret;
}
+static unsigned long count_lru_pages(void)
+{
+ struct zone *zone;
+ unsigned long ret = 0;
+
+ for_each_zone(zone)
+ ret += zone->nr_active + zone->nr_inactive;
+ return ret;
+}
+
/*
* Try to free `nr_pages' of memory, system-wide, and return the number of
* freed pages.
unsigned long ret = 0;
int pass;
struct reclaim_state reclaim_state;
- struct zone *zone;
struct scan_control sc = {
.gfp_mask = GFP_KERNEL,
.may_swap = 0,
current->reclaim_state = &reclaim_state;
- lru_pages = 0;
- for_each_zone(zone)
- lru_pages += zone->nr_active + zone->nr_inactive;
-
- nr_slab = global_page_state(NR_SLAB);
+ lru_pages = count_lru_pages();
+ nr_slab = global_page_state(NR_SLAB_RECLAIMABLE);
/* If slab caches are huge, it's better to hit them first */
while (nr_slab >= lru_pages) {
reclaim_state.reclaimed_slab = 0;
for (pass = 0; pass < 5; pass++) {
int prio;
- /* Needed for shrinking slab caches later on */
- if (!lru_pages)
- for_each_zone(zone) {
- lru_pages += zone->nr_active;
- lru_pages += zone->nr_inactive;
- }
-
/* Force reclaiming mapped pages in the passes #3 and #4 */
if (pass > 2) {
sc.may_swap = 1;
goto out;
reclaim_state.reclaimed_slab = 0;
- shrink_slab(sc.nr_scanned, sc.gfp_mask, lru_pages);
+ shrink_slab(sc.nr_scanned, sc.gfp_mask,
+ count_lru_pages());
ret += reclaim_state.reclaimed_slab;
if (ret >= nr_pages)
goto out;
if (sc.nr_scanned && prio < DEF_PRIORITY - 2)
- blk_congestion_wait(WRITE, HZ / 10);
+ congestion_wait(WRITE, HZ / 10);
}
-
- lru_pages = 0;
}
/*
* If ret = 0, we could not shrink LRUs, but there may be something
* in slab caches
*/
- if (!ret)
+ if (!ret) {
do {
reclaim_state.reclaimed_slab = 0;
- shrink_slab(nr_pages, sc.gfp_mask, lru_pages);
+ shrink_slab(nr_pages, sc.gfp_mask, count_lru_pages());
ret += reclaim_state.reclaimed_slab;
} while (ret < nr_pages && reclaim_state.reclaimed_slab > 0);
+ }
out:
current->reclaim_state = NULL;
}
#endif
-#ifdef CONFIG_HOTPLUG_CPU
/* It's optimal to keep kswapds on the same CPUs as their memory, but
not required for correctness. So if the last cpu in a node goes
away, we get changed to run anywhere: as the first one comes back,
}
return NOTIFY_OK;
}
-#endif /* CONFIG_HOTPLUG_CPU */
/*
* This kswapd start function will be called by init and node-hot-add.
.gfp_mask = gfp_mask,
.swappiness = vm_swappiness,
};
+ unsigned long slab_reclaimable;
disable_swap_token();
cond_resched();
if (zone_page_state(zone, NR_FILE_PAGES) -
zone_page_state(zone, NR_FILE_MAPPED) >
- zone->min_unmapped_ratio) {
+ zone->min_unmapped_pages) {
/*
* Free memory by calling shrink zone with increasing
* priorities until we have enough memory freed.
} while (priority >= 0 && nr_reclaimed < nr_pages);
}
- if (zone_page_state(zone, NR_SLAB) > zone->min_slab_pages) {
+ slab_reclaimable = zone_page_state(zone, NR_SLAB_RECLAIMABLE);
+ if (slab_reclaimable > zone->min_slab_pages) {
/*
* shrink_slab() does not currently allow us to determine how
* many pages were freed in this zone. So we take the current
* Note that shrink_slab will free memory on all zones and may
* take a long time.
*/
- unsigned long limit = zone_page_state(zone,
- NR_SLAB) - nr_pages;
-
while (shrink_slab(sc.nr_scanned, gfp_mask, order) &&
- zone_page_state(zone, NR_SLAB) > limit)
+ zone_page_state(zone, NR_SLAB_RECLAIMABLE) >
+ slab_reclaimable - nr_pages)
;
+
+ /*
+ * Update nr_reclaimed by the number of slab pages we
+ * reclaimed from this zone.
+ */
+ nr_reclaimed += slab_reclaimable -
+ zone_page_state(zone, NR_SLAB_RECLAIMABLE);
}
p->reclaim_state = NULL;
* unmapped file backed pages.
*/
if (zone_page_state(zone, NR_FILE_PAGES) -
- zone_page_state(zone, NR_FILE_MAPPED) <= zone->min_unmapped_ratio
- && zone_page_state(zone, NR_SLAB)
+ zone_page_state(zone, NR_FILE_MAPPED) <= zone->min_unmapped_pages
+ && zone_page_state(zone, NR_SLAB_RECLAIMABLE)
<= zone->min_slab_pages)
return 0;
* over remote processors and spread off node memory allocations
* as wide as possible.
*/
- node_id = zone->zone_pgdat->node_id;
+ node_id = zone_to_nid(zone);
mask = node_to_cpumask(node_id);
if (!cpus_empty(mask) && node_id != numa_node_id())
return 0;