unsigned int priority;
/* This context's GFP mask */
- unsigned int gfp_mask;
+ gfp_t gfp_mask;
int may_writepage;
+ /* 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
*
* Returns the number of slab objects which we shrunk.
*/
-static int shrink_slab(unsigned long scanned, unsigned int gfp_mask,
+static int shrink_slab(unsigned long scanned, gfp_t gfp_mask,
unsigned long lru_pages)
{
struct shrinker *shrinker;
* Try to allocate it some swap space here.
*/
if (PageAnon(page) && !PageSwapCache(page)) {
+ if (!sc->may_swap)
+ goto keep_locked;
if (!add_to_swap(page))
goto activate_locked;
}
* PageDirty _after_ making sure that the page is freeable and
* not in use by anybody. (pagecache + us == 2)
*/
- if (page_count(page) != 2 || PageDirty(page)) {
- write_unlock_irq(&mapping->tree_lock);
- goto keep_locked;
- }
+ if (unlikely(page_count(page) != 2))
+ goto cannot_free;
+ smp_rmb();
+ if (unlikely(PageDirty(page)))
+ goto cannot_free;
#ifdef CONFIG_SWAP
if (PageSwapCache(page)) {
- swp_entry_t swap = { .val = page->private };
+ swp_entry_t swap = { .val = page_private(page) };
__delete_from_swap_cache(page);
write_unlock_irq(&mapping->tree_lock);
swap_free(swap);
__pagevec_release_nonlru(&freed_pvec);
continue;
+cannot_free:
+ write_unlock_irq(&mapping->tree_lock);
+ goto keep_locked;
+
activate_locked:
SetPageActive(page);
pgactivate++;
unsigned long nr_active;
unsigned long nr_inactive;
+ 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.
}
throttle_vm_writeout();
+
+ atomic_dec(&zone->reclaim_in_progress);
}
/*
if (zone->present_pages == 0)
continue;
- if (!cpuset_zone_allowed(zone))
+ if (!cpuset_zone_allowed(zone, __GFP_HARDWALL))
continue;
zone->temp_priority = sc->priority;
* holds filesystem locks which prevent writeout this might not work, and the
* allocation attempt will fail.
*/
-int try_to_free_pages(struct zone **zones,
- unsigned int gfp_mask, unsigned int order)
+int try_to_free_pages(struct zone **zones, gfp_t gfp_mask)
{
int priority;
int ret = 0;
sc.gfp_mask = gfp_mask;
sc.may_writepage = 0;
+ sc.may_swap = 1;
inc_page_state(allocstall);
for (i = 0; zones[i] != NULL; i++) {
struct zone *zone = zones[i];
- if (!cpuset_zone_allowed(zone))
+ if (!cpuset_zone_allowed(zone, __GFP_HARDWALL))
continue;
zone->temp_priority = DEF_PRIORITY;
* writeout. So in laptop mode, write out the whole world.
*/
if (total_scanned > sc.swap_cluster_max + sc.swap_cluster_max/2) {
- wakeup_bdflush(laptop_mode ? 0 : total_scanned);
+ wakeup_pdflush(laptop_mode ? 0 : total_scanned);
sc.may_writepage = 1;
}
for (i = 0; zones[i] != 0; i++) {
struct zone *zone = zones[i];
- if (!cpuset_zone_allowed(zone))
+ if (!cpuset_zone_allowed(zone, __GFP_HARDWALL))
continue;
zone->prev_priority = zone->temp_priority;
total_reclaimed = 0;
sc.gfp_mask = GFP_KERNEL;
sc.may_writepage = 0;
+ sc.may_swap = 1;
sc.nr_mapped = read_page_state(nr_mapped);
inc_page_state(pageoutrun);
continue;
if (!zone_watermark_ok(zone, order,
- zone->pages_high, 0, 0, 0)) {
+ zone->pages_high, 0, 0)) {
end_zone = i;
goto scan;
}
if (nr_pages == 0) { /* Not software suspend */
if (!zone_watermark_ok(zone, order,
- zone->pages_high, end_zone, 0, 0))
+ zone->pages_high, end_zone, 0))
all_zones_ok = 0;
}
zone->temp_priority = priority;
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);
reclaim_state->reclaimed_slab = 0;
nr_slab = shrink_slab(sc.nr_scanned, GFP_KERNEL,
lru_pages);
order = 0;
for ( ; ; ) {
unsigned long new_order;
- if (current->flags & PF_FREEZE)
- refrigerator(PF_FREEZE);
+
+ try_to_freeze();
prepare_to_wait(&pgdat->kswapd_wait, &wait, TASK_INTERRUPTIBLE);
new_order = pgdat->kswapd_max_order;
return;
pgdat = zone->zone_pgdat;
- if (zone_watermark_ok(zone, order, zone->pages_low, 0, 0, 0))
+ if (zone_watermark_ok(zone, order, zone->pages_low, 0, 0))
return;
if (pgdat->kswapd_max_order < order)
pgdat->kswapd_max_order = order;
- if (!cpuset_zone_allowed(zone))
+ if (!cpuset_zone_allowed(zone, __GFP_HARDWALL))
return;
- if (!waitqueue_active(&zone->zone_pgdat->kswapd_wait))
+ if (!waitqueue_active(&pgdat->kswapd_wait))
return;
- wake_up_interruptible(&zone->zone_pgdat->kswapd_wait);
+ wake_up_interruptible(&pgdat->kswapd_wait);
}
#ifdef CONFIG_PM
}
module_init(kswapd_init)
+
+
+/*
+ * Try to free up some pages from this zone through reclaim.
+ */
+int zone_reclaim(struct zone *zone, gfp_t gfp_mask, unsigned int order)
+{
+ struct scan_control sc;
+ int nr_pages = 1 << order;
+ int total_reclaimed = 0;
+
+ /* The reclaim may sleep, so don't do it if sleep isn't allowed */
+ if (!(gfp_mask & __GFP_WAIT))
+ return 0;
+ if (zone->all_unreclaimable)
+ return 0;
+
+ sc.gfp_mask = gfp_mask;
+ sc.may_writepage = 0;
+ sc.may_swap = 0;
+ sc.nr_mapped = read_page_state(nr_mapped);
+ sc.nr_scanned = 0;
+ sc.nr_reclaimed = 0;
+ /* scan at the highest priority */
+ sc.priority = 0;
+
+ if (nr_pages > SWAP_CLUSTER_MAX)
+ sc.swap_cluster_max = nr_pages;
+ else
+ sc.swap_cluster_max = SWAP_CLUSTER_MAX;
+
+ /* Don't reclaim the zone if there are other reclaimers active */
+ if (atomic_read(&zone->reclaim_in_progress) > 0)
+ goto out;
+
+ shrink_zone(zone, &sc);
+ total_reclaimed = sc.nr_reclaimed;
+
+ out:
+ return total_reclaimed;
+}
+
+asmlinkage long sys_set_zone_reclaim(unsigned int node, unsigned int zone,
+ unsigned int state)
+{
+ struct zone *z;
+ int i;
+
+ if (!capable(CAP_SYS_ADMIN))
+ return -EACCES;
+
+ if (node >= MAX_NUMNODES || !node_online(node))
+ return -EINVAL;
+
+ /* This will break if we ever add more zones */
+ if (!(zone & (1<<ZONE_DMA|1<<ZONE_NORMAL|1<<ZONE_HIGHMEM)))
+ return -EINVAL;
+
+ for (i = 0; i < MAX_NR_ZONES; i++) {
+ if (!(zone & 1<<i))
+ continue;
+
+ z = &NODE_DATA(node)->node_zones[i];
+
+ if (state)
+ z->reclaim_pages = 1;
+ else
+ z->reclaim_pages = 0;
+ }
+
+ return 0;
+}