#include <linux/highmem.h>
#include <linux/file.h>
#include <linux/writeback.h>
-#include <linux/suspend.h>
#include <linux/blkdev.h>
#include <linux/buffer_head.h> /* for try_to_release_page(),
buffer_heads_over_limit */
#include <linux/rmap.h>
#include <linux/topology.h>
#include <linux/cpu.h>
+#include <linux/cpuset.h>
#include <linux/notifier.h>
#include <linux/rwsem.h>
#include <asm/div64.h>
#include <linux/swapops.h>
-#include <linux/vs_cvirt.h>
/* possible outcome of pageout() */
unsigned int gfp_mask;
int may_writepage;
+
+ /* 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;
};
/*
shrinker->seeks = seeks;
shrinker->nr = 0;
down_write(&shrinker_rwsem);
- list_add(&shrinker->list, &shrinker_list);
+ list_add_tail(&shrinker->list, &shrinker_list);
up_write(&shrinker_rwsem);
}
return shrinker;
*/
if (!is_page_cache_freeable(page))
return PAGE_KEEP;
- if (!mapping)
+ if (!mapping) {
+ /*
+ * Some data journaling orphaned pages can have
+ * page->mapping == NULL while being dirty with clean buffers.
+ */
+ if (PagePrivate(page)) {
+ if (try_to_free_buffers(page)) {
+ ClearPageDirty(page);
+ printk("%s: orphaned page\n", __FUNCTION__);
+ return PAGE_CLEAN;
+ }
+ }
return PAGE_KEEP;
+ }
if (mapping->a_ops->writepage == NULL)
return PAGE_ACTIVATE;
if (!may_write_to_queue(mapping->backing_dev_info))
int may_enter_fs;
int referenced;
+ cond_resched();
+
page = lru_to_page(page_list);
list_del(&page->lru);
if (!mapping)
goto keep_locked; /* truncate got there first */
- spin_lock_irq(&mapping->tree_lock);
+ write_lock_irq(&mapping->tree_lock);
/*
* The non-racy check for busy page. It is critical to check
* not in use by anybody. (pagecache + us == 2)
*/
if (page_count(page) != 2 || PageDirty(page)) {
- spin_unlock_irq(&mapping->tree_lock);
+ write_unlock_irq(&mapping->tree_lock);
goto keep_locked;
}
if (PageSwapCache(page)) {
swp_entry_t swap = { .val = page->private };
__delete_from_swap_cache(page);
- spin_unlock_irq(&mapping->tree_lock);
+ write_unlock_irq(&mapping->tree_lock);
swap_free(swap);
__put_page(page); /* The pagecache ref */
goto free_it;
#endif /* CONFIG_SWAP */
__remove_from_page_cache(page);
- spin_unlock_irq(&mapping->tree_lock);
+ write_unlock_irq(&mapping->tree_lock);
__put_page(page);
free_it:
}
/*
- * zone->lru_lock is heavily contented. We relieve it by quickly privatising
- * a batch of pages and working on them outside the lock. Any pages which were
- * not freed will be added back to the LRU.
+ * 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.
*
- * shrink_cache() adds the number of pages reclaimed to sc->nr_reclaimed
+ * For pagecache intensive workloads, this function is the hottest
+ * spot in the kernel (apart from copy_*_user functions).
*
- * For pagecache intensive workloads, the first loop here is the hottest spot
- * in the kernel (apart from the copy_*_user functions).
+ * Appropriate locks must be held before calling this function.
+ *
+ * @nr_to_scan: The number of pages to look through on the list.
+ * @src: The LRU list to pull pages off.
+ * @dst: The temp list to put pages on to.
+ * @scanned: The number of pages that were scanned.
+ *
+ * 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)
+{
+ int nr_taken = 0;
+ struct page *page;
+ int scan = 0;
+
+ while (scan++ < nr_to_scan && !list_empty(src)) {
+ page = lru_to_page(src);
+ prefetchw_prev_lru_page(page, src, flags);
+
+ if (!TestClearPageLRU(page))
+ BUG();
+ list_del(&page->lru);
+ if (get_page_testone(page)) {
+ /*
+ * It is being freed elsewhere
+ */
+ __put_page(page);
+ SetPageLRU(page);
+ list_add(&page->lru, src);
+ continue;
+ } else {
+ list_add(&page->lru, dst);
+ nr_taken++;
+ }
+ }
+
+ *scanned = scan;
+ return nr_taken;
+}
+
+/*
+ * shrink_cache() adds the number of pages reclaimed to sc->nr_reclaimed
*/
static void shrink_cache(struct zone *zone, struct scan_control *sc)
{
spin_lock_irq(&zone->lru_lock);
while (max_scan > 0) {
struct page *page;
- int nr_taken = 0;
- int nr_scan = 0;
+ int nr_taken;
+ int nr_scan;
int nr_freed;
- while (nr_scan++ < SWAP_CLUSTER_MAX &&
- !list_empty(inactive_list)) {
- page = lru_to_page(inactive_list);
-
- prefetchw_prev_lru_page(page,
- inactive_list, flags);
-
- if (!TestClearPageLRU(page))
- BUG();
- list_del(&page->lru);
- if (get_page_testone(page)) {
- /*
- * It is being freed elsewhere
- */
- __put_page(page);
- SetPageLRU(page);
- list_add(&page->lru, inactive_list);
- continue;
- }
- list_add(&page->lru, &page_list);
- nr_taken++;
- }
+ nr_taken = isolate_lru_pages(sc->swap_cluster_max,
+ &zone->inactive_list,
+ &page_list, &nr_scan);
zone->nr_inactive -= nr_taken;
+ zone->pages_scanned += nr_scan;
spin_unlock_irq(&zone->lru_lock);
if (nr_taken == 0)
{
int pgmoved;
int pgdeactivate = 0;
- int pgscanned = 0;
+ int pgscanned;
int nr_pages = sc->nr_to_scan;
LIST_HEAD(l_hold); /* The pages which were snipped off */
LIST_HEAD(l_inactive); /* Pages to go onto the inactive_list */
struct list_head *inactive_list = &zone->inactive_list;
lru_add_drain();
- pgmoved = 0;
spin_lock_irq(&zone->lru_lock);
- while (pgscanned < nr_pages && !list_empty(active_list)) {
- page = lru_to_page(active_list);
- prefetchw_prev_lru_page(page, active_list, flags);
- if (!TestClearPageLRU(page))
- BUG();
- list_del(&page->lru);
- if (get_page_testone(page)) {
- /*
- * It was already free! release_pages() or put_page()
- * are about to remove it from the LRU and free it. So
- * put the refcount back and put the page back on the
- * LRU
- */
- __put_page(page);
- SetPageLRU(page);
- list_add(&page->lru, active_list);
- } else {
- list_add(&page->lru, &l_hold);
- pgmoved++;
- }
- pgscanned++;
- }
+ pgmoved = isolate_lru_pages(nr_pages, &zone->active_list,
+ &l_hold, &pgscanned);
zone->pages_scanned += pgscanned;
zone->nr_active -= pgmoved;
spin_unlock_irq(&zone->lru_lock);
reclaim_mapped = 1;
while (!list_empty(&l_hold)) {
+ cond_resched();
page = lru_to_page(&l_hold);
list_del(&page->lru);
if (page_mapped(page)) {
*/
zone->nr_scan_active += (zone->nr_active >> sc->priority) + 1;
nr_active = zone->nr_scan_active;
- if (nr_active >= SWAP_CLUSTER_MAX)
+ 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;
nr_inactive = zone->nr_scan_inactive;
- if (nr_inactive >= SWAP_CLUSTER_MAX)
+ if (nr_inactive >= sc->swap_cluster_max)
zone->nr_scan_inactive = 0;
else
nr_inactive = 0;
- sc->nr_to_reclaim = SWAP_CLUSTER_MAX;
+ sc->nr_to_reclaim = sc->swap_cluster_max;
while (nr_active || nr_inactive) {
if (nr_active) {
sc->nr_to_scan = min(nr_active,
- (unsigned long)SWAP_CLUSTER_MAX);
+ (unsigned long)sc->swap_cluster_max);
nr_active -= sc->nr_to_scan;
refill_inactive_zone(zone, sc);
}
if (nr_inactive) {
sc->nr_to_scan = min(nr_inactive,
- (unsigned long)SWAP_CLUSTER_MAX);
+ (unsigned long)sc->swap_cluster_max);
nr_inactive -= sc->nr_to_scan;
shrink_cache(zone, sc);
if (sc->nr_to_reclaim <= 0)
break;
}
}
+
+ throttle_vm_writeout();
}
/*
if (zone->present_pages == 0)
continue;
+ if (!cpuset_zone_allowed(zone))
+ continue;
+
zone->temp_priority = sc->priority;
if (zone->prev_priority > sc->priority)
zone->prev_priority = sc->priority;
for (i = 0; zones[i] != NULL; i++) {
struct zone *zone = zones[i];
+ if (!cpuset_zone_allowed(zone))
+ continue;
+
zone->temp_priority = DEF_PRIORITY;
lru_pages += zone->nr_active + zone->nr_inactive;
}
sc.nr_scanned = 0;
sc.nr_reclaimed = 0;
sc.priority = priority;
+ sc.swap_cluster_max = SWAP_CLUSTER_MAX;
shrink_caches(zones, &sc);
shrink_slab(sc.nr_scanned, gfp_mask, lru_pages);
if (reclaim_state) {
sc.nr_reclaimed += reclaim_state->reclaimed_slab;
reclaim_state->reclaimed_slab = 0;
}
- if (sc.nr_reclaimed >= SWAP_CLUSTER_MAX) {
+ total_scanned += sc.nr_scanned;
+ total_reclaimed += sc.nr_reclaimed;
+ if (total_reclaimed >= sc.swap_cluster_max) {
ret = 1;
goto out;
}
- total_scanned += sc.nr_scanned;
- total_reclaimed += sc.nr_reclaimed;
/*
* 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 > SWAP_CLUSTER_MAX + SWAP_CLUSTER_MAX/2) {
+ if (total_scanned > sc.swap_cluster_max + sc.swap_cluster_max/2) {
wakeup_bdflush(laptop_mode ? 0 : total_scanned);
sc.may_writepage = 1;
}
if (sc.nr_scanned && priority < DEF_PRIORITY - 2)
blk_congestion_wait(WRITE, HZ/10);
}
- if ((gfp_mask & __GFP_FS) && !(gfp_mask & __GFP_NORETRY))
- out_of_memory(gfp_mask);
out:
- for (i = 0; zones[i] != 0; i++)
- zones[i]->prev_priority = zones[i]->temp_priority;
+ for (i = 0; zones[i] != 0; i++) {
+ struct zone *zone = zones[i];
+
+ if (!cpuset_zone_allowed(zone))
+ continue;
+
+ zone->prev_priority = zone->temp_priority;
+ }
return ret;
}
* 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)
+static int balance_pgdat(pg_data_t *pgdat, int nr_pages, int order)
{
int to_free = nr_pages;
int all_zones_ok;
priority != DEF_PRIORITY)
continue;
- if (zone->free_pages <= zone->pages_high) {
+ if (!zone_watermark_ok(zone, order,
+ zone->pages_high, 0, 0, 0)) {
end_zone = i;
goto scan;
}
continue;
if (nr_pages == 0) { /* Not software suspend */
- if (zone->free_pages <= zone->pages_high)
+ if (!zone_watermark_ok(zone, order,
+ zone->pages_high, end_zone, 0, 0))
all_zones_ok = 0;
}
zone->temp_priority = priority;
sc.nr_scanned = 0;
sc.nr_reclaimed = 0;
sc.priority = priority;
+ sc.swap_cluster_max = nr_pages? nr_pages : SWAP_CLUSTER_MAX;
shrink_zone(zone, &sc);
reclaim_state->reclaimed_slab = 0;
shrink_slab(sc.nr_scanned, GFP_KERNEL, lru_pages);
* matches the direct reclaim path behaviour in terms of impact
* on zone->*_priority.
*/
- if (total_reclaimed >= SWAP_CLUSTER_MAX)
+ if ((total_reclaimed >= SWAP_CLUSTER_MAX) && (!nr_pages))
break;
}
out:
*/
static int kswapd(void *p)
{
+ unsigned long order;
pg_data_t *pgdat = (pg_data_t*)p;
struct task_struct *tsk = current;
DEFINE_WAIT(wait);
*/
tsk->flags |= PF_MEMALLOC|PF_KSWAPD;
+ order = 0;
for ( ; ; ) {
+ unsigned long new_order;
if (current->flags & PF_FREEZE)
refrigerator(PF_FREEZE);
+
prepare_to_wait(&pgdat->kswapd_wait, &wait, TASK_INTERRUPTIBLE);
- schedule();
+ new_order = pgdat->kswapd_max_order;
+ pgdat->kswapd_max_order = 0;
+ if (order < new_order) {
+ /*
+ * Don't sleep if someone wants a larger 'order'
+ * allocation
+ */
+ order = new_order;
+ } else {
+ schedule();
+ order = pgdat->kswapd_max_order;
+ }
finish_wait(&pgdat->kswapd_wait, &wait);
- balance_pgdat(pgdat, 0);
+
+ balance_pgdat(pgdat, 0, order);
}
return 0;
}
/*
* A zone is low on free memory, so wake its kswapd task to service it.
*/
-void wakeup_kswapd(struct zone *zone)
+void wakeup_kswapd(struct zone *zone, int order)
{
+ pg_data_t *pgdat;
+
if (zone->present_pages == 0)
return;
- if (zone->free_pages > zone->pages_low)
+
+ pgdat = zone->zone_pgdat;
+ if (zone_watermark_ok(zone, order, zone->pages_low, 0, 0, 0))
+ return;
+ if (pgdat->kswapd_max_order < order)
+ pgdat->kswapd_max_order = order;
+ if (!cpuset_zone_allowed(zone))
return;
if (!waitqueue_active(&zone->zone_pgdat->kswapd_wait))
return;
current->reclaim_state = &reclaim_state;
for_each_pgdat(pgdat) {
int freed;
- freed = balance_pgdat(pgdat, nr_to_free);
+ freed = balance_pgdat(pgdat, nr_to_free, 0);
ret += freed;
nr_to_free -= freed;
if (nr_to_free <= 0)
git://git.onelab.eu / linux-2.6.git / blobdiff