#include <linux/topology.h>
#include <linux/cpu.h>
#include <linux/notifier.h>
+#include <linux/rwsem.h>
-#include <asm/pgalloc.h>
#include <asm/tlbflush.h>
#include <asm/div64.h>
#include <linux/swapops.h>
+/* possible outcome of pageout() */
+typedef enum {
+ /* failed to write page out, page is locked */
+ PAGE_KEEP,
+ /* move page to the active list, page is locked */
+ PAGE_ACTIVATE,
+ /* page has been sent to the disk successfully, page is unlocked */
+ PAGE_SUCCESS,
+ /* page is clean and locked */
+ PAGE_CLEAN,
+} pageout_t;
+
+struct scan_control {
+ /* Ask refill_inactive_zone, or shrink_cache to scan this many pages */
+ unsigned long nr_to_scan;
+
+ /* Incremented by the number of inactive pages that were scanned */
+ unsigned long nr_scanned;
+
+ /* Incremented by the number of pages reclaimed */
+ unsigned long nr_reclaimed;
+
+ unsigned long nr_mapped; /* From page_state */
+
+ /* How many pages shrink_cache() should reclaim */
+ int nr_to_reclaim;
+
+ /* Ask shrink_caches, or shrink_zone to scan at this priority */
+ unsigned int priority;
+
+ /* This context's GFP mask */
+ unsigned int gfp_mask;
+
+ int may_writepage;
+};
+
/*
- * From 0 .. 100. Higher means more swappy.
+ * The list of shrinker callbacks used by to apply pressure to
+ * ageable caches.
*/
-int vm_swappiness = 60;
-static long total_memory;
+struct shrinker {
+ shrinker_t shrinker;
+ struct list_head list;
+ int seeks; /* seeks to recreate an obj */
+ long nr; /* objs pending delete */
+};
#define lru_to_page(_head) (list_entry((_head)->prev, struct page, lru))
if ((_page)->lru.prev != _base) { \
struct page *prev; \
\
- prev = lru_to_page(&(_page->lru)); \
+ prev = lru_to_page(&(_page->lru)); \
prefetchw(&prev->_field); \
} \
} while (0)
#endif
/*
- * The list of shrinker callbacks used by to apply pressure to
- * ageable caches.
+ * From 0 .. 100. Higher means more swappy.
*/
-struct shrinker {
- shrinker_t shrinker;
- struct list_head list;
- int seeks; /* seeks to recreate an obj */
- long nr; /* objs pending delete */
-};
+int vm_swappiness = 60;
+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;
}
-
EXPORT_SYMBOL(set_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
* slab to avoid swapping.
*
* We do weird things to avoid (scanned*seeks*entries) overflowing 32 bits.
+ *
+ * `lru_pages' represents the number of on-LRU pages in all the zones which
+ * are eligible for the caller's allocation attempt. It is used for balancing
+ * slab reclaim versus page reclaim.
*/
-static int shrink_slab(unsigned long scanned, unsigned int gfp_mask)
+static int shrink_slab(unsigned long scanned, unsigned int gfp_mask,
+ unsigned long lru_pages)
{
struct shrinker *shrinker;
- long pages;
- if (down_trylock(&shrinker_sem))
+ if (scanned == 0)
+ scanned = SWAP_CLUSTER_MAX;
+
+ if (!down_read_trylock(&shrinker_rwsem))
return 0;
- pages = nr_used_zone_pages();
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);
- do_div(delta, pages + 1);
+ do_div(delta, lru_pages + 1);
shrinker->nr += delta;
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;
unlock_page(page);
}
-/* possible outcome of pageout() */
-typedef enum {
- /* failed to write page out, page is locked */
- PAGE_KEEP,
- /* move page to the active list, page is locked */
- PAGE_ACTIVATE,
- /* page has been sent to the disk successfully, page is unlocked */
- PAGE_SUCCESS,
- /* page is clean and locked */
- PAGE_CLEAN,
-} pageout_t;
-
/*
* pageout is called by shrink_list() for each dirty page. Calls ->writepage().
*/
return PAGE_CLEAN;
}
-struct scan_control {
- /* Ask refill_inactive_zone, or shrink_cache to scan this many pages */
- unsigned long nr_to_scan;
-
- /* Incremented by the number of inactive pages that were scanned */
- unsigned long nr_scanned;
-
- /* Incremented by the number of pages reclaimed */
- unsigned long nr_reclaimed;
-
- unsigned long nr_mapped; /* From page_state */
-
- /* Ask shrink_caches, or shrink_zone to scan at this priority */
- unsigned int priority;
-
- /* This context's GFP mask */
- unsigned int gfp_mask;
-
- int may_writepage;
-};
-
/*
* shrink_list adds the number of reclaimed pages to sc->nr_reclaimed
*/
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);
+ referenced = page_referenced(page, 1);
+ /* 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)
if (current_is_kswapd())
mod_page_state(kswapd_steal, nr_freed);
mod_page_state_zone(zone, pgsteal, nr_freed);
+ sc->nr_to_reclaim -= nr_freed;
spin_lock_irq(&zone->lru_lock);
/*
page = lru_to_page(&l_hold);
list_del(&page->lru);
if (page_mapped(page)) {
- if (!reclaim_mapped) {
- list_add(&page->lru, &l_active);
- continue;
- }
- page_map_lock(page);
- if (page_referenced(page)) {
- page_map_unlock(page);
+ if (!reclaim_mapped ||
+ (total_swap_pages == 0 && PageAnon(page)) ||
+ page_referenced(page, 0)) {
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);
}
}
/*
- * Scan `nr_pages' from this zone. Returns the number of reclaimed pages.
* This is a basic per-zone page freer. Used by both kswapd and direct reclaim.
*/
static void
shrink_zone(struct zone *zone, struct scan_control *sc)
{
- unsigned long scan_active, scan_inactive;
- int count;
-
- scan_inactive = (zone->nr_active + zone->nr_inactive) >> sc->priority;
+ unsigned long nr_active;
+ unsigned long nr_inactive;
/*
- * Try to keep the active list 2/3 of the size of the cache. And
- * make sure that refill_inactive is given a decent number of pages.
- *
- * The "scan_active + 1" here is important. With pagecache-intensive
- * workloads the inactive list is huge, and `ratio' evaluates to zero
- * all the time. Which pins the active list memory. So we add one to
- * `scan_active' just to make sure that the kernel will slowly sift
- * through the active list.
+ * Add one to `nr_to_scan' just to make sure that the kernel will
+ * slowly sift through the active list.
*/
- if (zone->nr_active >= 4*(zone->nr_inactive*2 + 1)) {
- /* Don't scan more than 4 times the inactive list scan size */
- scan_active = 4*scan_inactive;
- } else {
- unsigned long long tmp;
-
- /* Cast to long long so the multiply doesn't overflow */
-
- tmp = (unsigned long long)scan_inactive * zone->nr_active;
- do_div(tmp, zone->nr_inactive*2 + 1);
- scan_active = (unsigned long)tmp;
- }
-
- atomic_add(scan_active + 1, &zone->nr_scan_active);
- count = atomic_read(&zone->nr_scan_active);
- if (count >= SWAP_CLUSTER_MAX) {
- atomic_set(&zone->nr_scan_active, 0);
- sc->nr_to_scan = count;
- refill_inactive_zone(zone, sc);
- }
+ zone->nr_scan_active += (zone->nr_active >> sc->priority) + 1;
+ nr_active = zone->nr_scan_active;
+ if (nr_active >= 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)
+ zone->nr_scan_inactive = 0;
+ else
+ nr_inactive = 0;
+
+ sc->nr_to_reclaim = SWAP_CLUSTER_MAX;
+
+ while (nr_active || nr_inactive) {
+ if (nr_active) {
+ sc->nr_to_scan = min(nr_active,
+ (unsigned long)SWAP_CLUSTER_MAX);
+ nr_active -= sc->nr_to_scan;
+ refill_inactive_zone(zone, sc);
+ }
- atomic_add(scan_inactive, &zone->nr_scan_inactive);
- count = atomic_read(&zone->nr_scan_inactive);
- if (count >= SWAP_CLUSTER_MAX) {
- atomic_set(&zone->nr_scan_inactive, 0);
- sc->nr_to_scan = count;
- shrink_cache(zone, sc);
+ if (nr_inactive) {
+ sc->nr_to_scan = min(nr_inactive,
+ (unsigned long)SWAP_CLUSTER_MAX);
+ nr_inactive -= sc->nr_to_scan;
+ shrink_cache(zone, sc);
+ if (sc->nr_to_reclaim <= 0)
+ break;
+ }
}
}
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;
int total_scanned = 0, total_reclaimed = 0;
struct reclaim_state *reclaim_state = current->reclaim_state;
struct scan_control sc;
+ unsigned long lru_pages = 0;
int i;
sc.gfp_mask = gfp_mask;
inc_page_state(allocstall);
- for (i = 0; zones[i] != 0; i++)
- zones[i]->temp_priority = DEF_PRIORITY;
+ for (i = 0; zones[i] != NULL; i++) {
+ struct zone *zone = zones[i];
+
+ zone->temp_priority = DEF_PRIORITY;
+ lru_pages += zone->nr_active + zone->nr_inactive;
+ }
for (priority = DEF_PRIORITY; priority >= 0; priority--) {
sc.nr_mapped = read_page_state(nr_mapped);
sc.nr_reclaimed = 0;
sc.priority = priority;
shrink_caches(zones, &sc);
- shrink_slab(sc.nr_scanned, gfp_mask);
+ shrink_slab(sc.nr_scanned, gfp_mask, lru_pages);
if (reclaim_state) {
sc.nr_reclaimed += reclaim_state->reclaimed_slab;
reclaim_state->reclaimed_slab = 0;
blk_congestion_wait(WRITE, HZ/10);
}
if ((gfp_mask & __GFP_FS) && !(gfp_mask & __GFP_NORETRY))
- out_of_memory();
+ out_of_memory(gfp_mask);
out:
for (i = 0; zones[i] != 0; i++)
zones[i]->prev_priority = zones[i]->temp_priority;
static int balance_pgdat(pg_data_t *pgdat, int nr_pages)
{
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) {
/*
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;
end_zone = pgdat->nr_zones - 1;
}
scan:
+ for (i = 0; i <= end_zone; i++) {
+ struct zone *zone = pgdat->node_zones + i;
+
+ lru_pages += zone->nr_active + zone->nr_inactive;
+ }
+
/*
* Now scan the zone in the dma->highmem direction, stopping
* at the last zone which needs scanning.
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;
sc.priority = priority;
shrink_zone(zone, &sc);
reclaim_state->reclaimed_slab = 0;
- shrink_slab(sc.nr_scanned, GFP_KERNEL);
+ shrink_slab(sc.nr_scanned, GFP_KERNEL, lru_pages);
sc.nr_reclaimed += reclaim_state->reclaimed_slab;
total_reclaimed += sc.nr_reclaimed;
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;
}
* If there are applications that are active memory-allocators
* (most normal use), this basically shouldn't matter.
*/
-int kswapd(void *p)
+static int kswapd(void *p)
{
pg_data_t *pgdat = (pg_data_t*)p;
struct task_struct *tsk = current;
balance_pgdat(pgdat, 0);
}
+ return 0;
}
/*
*/
void wakeup_kswapd(struct zone *zone)
{
+ if (zone->present_pages == 0)
+ return;
if (zone->free_pages > zone->pages_low)
return;
if (!waitqueue_active(&zone->zone_pgdat->kswapd_wait))
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;
git://git.onelab.eu / linux-2.6.git / blobdiff