#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>
int swap_cluster_max;
int swappiness;
+
+ int all_unreclaimable;
};
/*
/* 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;
*/
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))
return 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;
+}
+
+static inline int zone_is_near_oom(struct zone *zone)
+{
+ return zone->pages_scanned >= (zone->nr_active + zone->nr_inactive)*3;
+}
+
/*
* This moves pages from the active list to the inactive list.
*
* But we had to alter page->flags anyway.
*/
static void shrink_active_list(unsigned long nr_pages, struct zone *zone,
- struct scan_control *sc)
+ struct scan_control *sc, int priority)
{
unsigned long pgmoved;
int pgdeactivate = 0;
long distress;
long swap_tendency;
+ 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 >> zone->prev_priority;
+ distress = 100 >> min(zone->prev_priority, priority);
/*
* The point of this algorithm is to decide when to start
* memory onto the inactive list.
*/
if (swap_tendency >= 100)
+force_reclaim_mapped:
reclaim_mapped = 1;
}
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)) {
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);
+ shrink_active_list(nr_to_scan, zone, sc, priority);
}
if (nr_inactive) {
unsigned long nr_reclaimed = 0;
int i;
+ sc->all_unreclaimable = 1;
for (i = 0; zones[i] != NULL; i++) {
struct zone *zone = zones[i];
if (!cpuset_zone_allowed(zone, __GFP_HARDWALL))
continue;
- zone->temp_priority = priority;
- if (zone->prev_priority > priority)
- zone->prev_priority = priority;
+ note_zone_scanning_priority(zone, priority);
if (zone->all_unreclaimable && priority != DEF_PRIORITY)
continue; /* Let kswapd poll it */
+ sc->all_unreclaimable = 0;
+
nr_reclaimed += shrink_zone(priority, zone, sc);
}
return nr_reclaimed;
if (!cpuset_zone_allowed(zone, __GFP_HARDWALL))
continue;
- zone->temp_priority = DEF_PRIORITY;
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)
+ ret = 1;
out:
+ /*
+ * Now that we've scanned all the zones at this priority level, note
+ * that level within the zone so that the next thread which performs
+ * scanning of this zone will immediately start out at this priority
+ * level. This affects only the decision whether or not to bring
+ * mapped pages onto the inactive list.
+ */
+ if (priority < 0)
+ priority = 0;
for (i = 0; zones[i] != 0; i++) {
struct zone *zone = zones[i];
if (!cpuset_zone_allowed(zone, __GFP_HARDWALL))
continue;
- zone->prev_priority = zone->temp_priority;
+ zone->prev_priority = priority;
}
return ret;
}
.swap_cluster_max = SWAP_CLUSTER_MAX,
.swappiness = vm_swappiness,
};
+ /*
+ * temp_priority is used to remember the scanning priority at which
+ * this zone was successfully refilled to free_pages == pages_high.
+ */
+ int temp_priority[MAX_NR_ZONES];
loop_again:
total_scanned = 0;
sc.may_writepage = !laptop_mode;
count_vm_event(PAGEOUTRUN);
- for (i = 0; i < pgdat->nr_zones; i++) {
- struct zone *zone = pgdat->node_zones + i;
-
- zone->temp_priority = DEF_PRIORITY;
- }
+ 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 */
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;
if (!zone_watermark_ok(zone, order, zone->pages_high,
end_zone, 0))
all_zones_ok = 0;
- zone->temp_priority = priority;
- if (zone->prev_priority > priority)
- zone->prev_priority = priority;
+ temp_priority[i] = priority;
sc.nr_scanned = 0;
+ note_zone_scanning_priority(zone, priority);
nr_reclaimed += shrink_zone(priority, zone, &sc);
reclaim_state->reclaimed_slab = 0;
nr_slab = shrink_slab(sc.nr_scanned, GFP_KERNEL,
if (zone->all_unreclaimable)
continue;
if (nr_slab == 0 && zone->pages_scanned >=
- (zone->nr_active + zone->nr_inactive) * 4)
+ (zone->nr_active + zone->nr_inactive) * 6)
zone->all_unreclaimable = 1;
/*
* If we've done a decent amount of scanning and
* 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
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 = zone->temp_priority;
+ zone->prev_priority = temp_priority[i];
}
if (!all_zones_ok) {
cond_resched();
if (zone->nr_scan_active >= nr_pages || pass > 3) {
zone->nr_scan_active = 0;
nr_to_scan = min(nr_pages, zone->nr_active);
- shrink_active_list(nr_to_scan, zone, sc);
+ shrink_active_list(nr_to_scan, zone, sc, prio);
}
}
for_each_zone(zone)
lru_pages += zone->nr_active + zone->nr_inactive;
- nr_slab = global_page_state(NR_SLAB);
+ 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;
goto out;
if (sc.nr_scanned && prio < DEF_PRIORITY - 2)
- blk_congestion_wait(WRITE, HZ / 10);
+ congestion_wait(WRITE, HZ / 10);
}
lru_pages = 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 */
/*
* Priority for ZONE_RECLAIM. This determines the fraction of pages
*/
int sysctl_min_unmapped_ratio = 1;
+/*
+ * If the number of slab pages in a zone grows beyond this percentage then
+ * slab reclaim needs to occur.
+ */
+int sysctl_min_slab_ratio = 5;
+
/*
* Try to free up some pages from this zone through reclaim.
*/
.gfp_mask = gfp_mask,
.swappiness = vm_swappiness,
};
+ unsigned long slab_reclaimable;
disable_swap_token();
cond_resched();
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 {
- nr_reclaimed += shrink_zone(priority, zone, &sc);
- priority--;
- } while (priority >= 0 && nr_reclaimed < nr_pages);
+ if (zone_page_state(zone, NR_FILE_PAGES) -
+ zone_page_state(zone, NR_FILE_MAPPED) >
+ zone->min_unmapped_pages) {
+ /*
+ * Free memory by calling shrink zone with increasing
+ * priorities until we have enough memory freed.
+ */
+ priority = ZONE_RECLAIM_PRIORITY;
+ do {
+ note_zone_scanning_priority(zone, priority);
+ nr_reclaimed += shrink_zone(priority, zone, &sc);
+ priority--;
+ } while (priority >= 0 && nr_reclaimed < nr_pages);
+ }
- if (nr_reclaimed < nr_pages && (zone_reclaim_mode & RECLAIM_SLAB)) {
+ 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 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.
+ * many pages were freed in this zone. So we take the current
+ * number of slab pages and shake the slab until it is reduced
+ * by the same nr_pages that we used for reclaiming unmapped
+ * pages.
*
- * shrink_slab will free memory on all zones and may take
- * a long time.
+ * 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)
+ ;
+
+ /*
+ * Update nr_reclaimed by the number of slab pages we
+ * reclaimed from this zone.
*/
- shrink_slab(sc.nr_scanned, gfp_mask, order);
+ nr_reclaimed += slab_reclaimable -
+ zone_page_state(zone, NR_SLAB_RECLAIMABLE);
}
p->reclaim_state = NULL;
int node_id;
/*
- * Zone reclaim reclaims unmapped file backed pages.
+ * Zone reclaim reclaims unmapped file backed pages and
+ * slab pages if we are over the defined limits.
*
* A small portion of unmapped file backed pages is needed for
* file I/O otherwise pages read by file I/O will be immediately
* 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_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;