#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/topology.h>
#include <linux/cpu.h>
#include <linux/notifier.h>
+#include <linux/rwsem.h>
#include <asm/tlbflush.h>
#include <asm/div64.h>
static long total_memory;
static LIST_HEAD(shrinker_list);
-static DECLARE_MUTEX(shrinker_sem);
+static DECLARE_RWSEM(shrinker_rwsem);
/*
* Add a shrinker callback to be called from the vm
shrinker->shrinker = theshrinker;
shrinker->seeks = seeks;
shrinker->nr = 0;
- down(&shrinker_sem);
+ down_write(&shrinker_rwsem);
list_add(&shrinker->list, &shrinker_list);
- up(&shrinker_sem);
+ up_write(&shrinker_rwsem);
}
return shrinker;
}
*/
void remove_shrinker(struct shrinker *shrinker)
{
- down(&shrinker_sem);
+ down_write(&shrinker_rwsem);
list_del(&shrinker->list);
- up(&shrinker_sem);
+ up_write(&shrinker_rwsem);
kfree(shrinker);
}
EXPORT_SYMBOL(remove_shrinker);
-
+
#define SHRINK_BATCH 128
/*
* Call the shrink functions to age shrinkable caches
{
struct shrinker *shrinker;
- if (down_trylock(&shrinker_sem))
+ if (scanned == 0)
+ scanned = SWAP_CLUSTER_MAX;
+
+ if (!down_read_trylock(&shrinker_rwsem))
return 0;
list_for_each_entry(shrinker, &shrinker_list, list) {
unsigned long long delta;
+ unsigned long total_scan;
delta = (4 * scanned) / shrinker->seeks;
delta *= (*shrinker->shrinker)(0, gfp_mask);
if (shrinker->nr < 0)
shrinker->nr = LONG_MAX; /* It wrapped! */
- if (shrinker->nr <= SHRINK_BATCH)
- continue;
- while (shrinker->nr) {
- long this_scan = shrinker->nr;
+ total_scan = shrinker->nr;
+ shrinker->nr = 0;
+
+ while (total_scan >= SHRINK_BATCH) {
+ long this_scan = SHRINK_BATCH;
int shrink_ret;
- if (this_scan > 128)
- this_scan = 128;
shrink_ret = (*shrinker->shrinker)(this_scan, gfp_mask);
- mod_page_state(slabs_scanned, this_scan);
- shrinker->nr -= this_scan;
if (shrink_ret == -1)
break;
+ mod_page_state(slabs_scanned, this_scan);
+ total_scan -= this_scan;
+
cond_resched();
}
+
+ shrinker->nr += total_scan;
}
- up(&shrinker_sem);
+ up_read(&shrinker_rwsem);
return 0;
}
-/* Must be called with page's rmap lock held. */
+/* Called without lock on whether page is mapped, so answer is unstable */
static inline int page_mapping_inuse(struct page *page)
{
struct address_space *mapping;
int may_enter_fs;
int referenced;
+ cond_resched();
+
page = lru_to_page(page_list);
list_del(&page->lru);
BUG_ON(PageActive(page));
- if (PageWriteback(page))
- goto keep_locked;
-
sc->nr_scanned++;
/* Double the slab pressure for mapped and swapcache pages */
if (page_mapped(page) || PageSwapCache(page))
sc->nr_scanned++;
- page_map_lock(page);
- referenced = page_referenced(page);
- if (referenced && page_mapping_inuse(page)) {
- /* In active use or really unfreeable. Activate it. */
- page_map_unlock(page);
+ if (PageWriteback(page))
+ goto keep_locked;
+
+ referenced = page_referenced(page, 1, sc->priority <= 0);
+ /* In active use or really unfreeable? Activate it. */
+ if (referenced && page_mapping_inuse(page))
goto activate_locked;
- }
#ifdef CONFIG_SWAP
/*
* Anonymous process memory has backing store?
* Try to allocate it some swap space here.
- *
- * XXX: implement swap clustering ?
*/
if (PageAnon(page) && !PageSwapCache(page)) {
- page_map_unlock(page);
if (!add_to_swap(page))
goto activate_locked;
- page_map_lock(page);
}
#endif /* CONFIG_SWAP */
if (page_mapped(page) && mapping) {
switch (try_to_unmap(page)) {
case SWAP_FAIL:
- page_map_unlock(page);
goto activate_locked;
case SWAP_AGAIN:
- page_map_unlock(page);
goto keep_locked;
case SWAP_SUCCESS:
; /* try to free the page below */
}
}
- page_map_unlock(page);
if (PageDirty(page)) {
if (referenced)
nr_taken++;
}
zone->nr_inactive -= nr_taken;
- zone->pages_scanned += nr_taken;
+ zone->pages_scanned += nr_scan;
spin_unlock_irq(&zone->lru_lock);
if (nr_taken == 0)
}
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)) {
- if (!reclaim_mapped) {
+ if (!reclaim_mapped ||
+ (total_swap_pages == 0 && PageAnon(page)) ||
+ page_referenced(page, 0, sc->priority <= 0)) {
list_add(&page->lru, &l_active);
continue;
}
- page_map_lock(page);
- if (page_referenced(page)) {
- page_map_unlock(page);
- list_add(&page->lru, &l_active);
- continue;
- }
- page_map_unlock(page);
- }
- /*
- * FIXME: need to consider page_count(page) here if/when we
- * reap orphaned pages via the LRU (Daniel's locking stuff)
- */
- if (total_swap_pages == 0 && PageAnon(page)) {
- list_add(&page->lru, &l_active);
- continue;
}
list_add(&page->lru, &l_inactive);
}
for (i = 0; zones[i] != NULL; i++) {
struct zone *zone = zones[i];
+ if (zone->present_pages == 0)
+ continue;
+
zone->temp_priority = sc->priority;
if (zone->prev_priority > sc->priority)
zone->prev_priority = sc->priority;
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;
* 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;
int priority;
int i;
- int total_scanned = 0, total_reclaimed = 0;
+ int total_scanned, total_reclaimed;
struct reclaim_state *reclaim_state = current->reclaim_state;
struct scan_control sc;
+loop_again:
+ total_scanned = 0;
+ total_reclaimed = 0;
sc.gfp_mask = GFP_KERNEL;
sc.may_writepage = 0;
sc.nr_mapped = read_page_state(nr_mapped);
}
for (priority = DEF_PRIORITY; priority >= 0; priority--) {
- int all_zones_ok = 1;
int end_zone = 0; /* Inclusive. 0 = ZONE_DMA */
unsigned long lru_pages = 0;
+ all_zones_ok = 1;
+
if (nr_pages == 0) {
/*
* Scan in the highmem->dma direction for the highest
for (i = pgdat->nr_zones - 1; i >= 0; i--) {
struct zone *zone = pgdat->node_zones + i;
+ if (zone->present_pages == 0)
+ continue;
+
if (zone->all_unreclaimable &&
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;
}
for (i = 0; i <= end_zone; i++) {
struct zone *zone = pgdat->node_zones + i;
+ if (zone->present_pages == 0)
+ continue;
+
if (zone->all_unreclaimable && priority != DEF_PRIORITY)
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;
shrink_slab(sc.nr_scanned, GFP_KERNEL, lru_pages);
sc.nr_reclaimed += reclaim_state->reclaimed_slab;
total_reclaimed += sc.nr_reclaimed;
+ total_scanned += sc.nr_scanned;
if (zone->all_unreclaimable)
continue;
- if (zone->pages_scanned > zone->present_pages * 2)
+ if (zone->pages_scanned >= (zone->nr_active +
+ zone->nr_inactive) * 4)
zone->all_unreclaimable = 1;
/*
* If we've done a decent amount of scanning and
*/
if (total_scanned && priority < DEF_PRIORITY - 2)
blk_congestion_wait(WRITE, HZ/10);
+
+ /*
+ * We do this so kswapd doesn't build up large priorities for
+ * example when it is freeing in parallel with allocators. It
+ * matches the direct reclaim path behaviour in terms of impact
+ * on zone->*_priority.
+ */
+ if (total_reclaimed >= SWAP_CLUSTER_MAX)
+ break;
}
out:
for (i = 0; i < pgdat->nr_zones; i++) {
zone->prev_priority = zone->temp_priority;
}
+ if (!all_zones_ok) {
+ cond_resched();
+ goto loop_again;
+ }
+
return total_reclaimed;
}
*/
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)
{
- if (zone->free_pages > zone->pages_low)
+ pg_data_t *pgdat;
+
+ if (zone->present_pages == 0)
+ return;
+
+ 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 (!waitqueue_active(&zone->zone_pgdat->kswapd_wait))
return;
wake_up_interruptible(&zone->zone_pgdat->kswapd_wait);
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)
swap_setup();
for_each_pgdat(pgdat)
pgdat->kswapd
- = find_task_by_pid(kernel_thread(kswapd, pgdat, CLONE_KERNEL));
+ = find_task_by_real_pid(kernel_thread(kswapd, pgdat, CLONE_KERNEL));
total_memory = nr_free_pagecache_pages();
hotcpu_notifier(cpu_callback, 0);
return 0;