pgdat_reclaimable_pages(pgdat) * 6;
}
-unsigned long lruvec_lru_size(struct lruvec *lruvec, enum lru_list lru)
+/**
+ * lruvec_lru_size - Returns the number of pages on the given LRU list.
+ * @lruvec: lru vector
+ * @lru: lru to use
+ * @zone_idx: zones to consider (use MAX_NR_ZONES for the whole LRU list)
+ */
+unsigned long lruvec_lru_size(struct lruvec *lruvec, enum lru_list lru, int zone_idx)
{
+ unsigned long lru_size;
+ int zid;
+
if (!mem_cgroup_disabled())
- return mem_cgroup_get_lru_size(lruvec, lru);
+ lru_size = mem_cgroup_get_lru_size(lruvec, lru);
+ else
+ lru_size = node_page_state(lruvec_pgdat(lruvec), NR_LRU_BASE + lru);
+
+ for (zid = zone_idx + 1; zid < MAX_NR_ZONES; zid++) {
+ struct zone *zone = &lruvec_pgdat(lruvec)->node_zones[zid];
+ unsigned long size;
+
+ if (!managed_zone(zone))
+ continue;
+
+ if (!mem_cgroup_disabled())
+ size = mem_cgroup_get_zone_lru_size(lruvec, lru, zid);
+ else
+ size = zone_page_state(&lruvec_pgdat(lruvec)->node_zones[zid],
+ NR_ZONE_LRU_BASE + lru);
+ lru_size -= min(size, lru_size);
+ }
+
+ return lru_size;
- return node_page_state(lruvec_pgdat(lruvec), NR_LRU_BASE + lru);
}
/*
*/
void unregister_shrinker(struct shrinker *shrinker)
{
+ if (!shrinker->nr_deferred)
+ return;
down_write(&shrinker_rwsem);
list_del(&shrinker->list);
up_write(&shrinker_rwsem);
kfree(shrinker->nr_deferred);
+ shrinker->nr_deferred = NULL;
}
EXPORT_SYMBOL(unregister_shrinker);
int nid = shrinkctl->nid;
long batch_size = shrinker->batch ? shrinker->batch
: SHRINK_BATCH;
+ long scanned = 0, next_deferred;
freeable = shrinker->count_objects(shrinker, shrinkctl);
if (freeable == 0)
pr_err("shrink_slab: %pF negative objects to delete nr=%ld\n",
shrinker->scan_objects, total_scan);
total_scan = freeable;
- }
+ next_deferred = nr;
+ } else
+ next_deferred = total_scan;
/*
* We need to avoid excessive windup on filesystem shrinkers
count_vm_events(SLABS_SCANNED, nr_to_scan);
total_scan -= nr_to_scan;
+ scanned += nr_to_scan;
cond_resched();
}
+ if (next_deferred >= scanned)
+ next_deferred -= scanned;
+ else
+ next_deferred = 0;
/*
* move the unused scan count back into the shrinker in a
* manner that handles concurrent updates. If we exhausted the
* scan, there is no need to do an update.
*/
- if (total_scan > 0)
- new_nr = atomic_long_add_return(total_scan,
+ if (next_deferred > 0)
+ new_nr = atomic_long_add_return(next_deferred,
&shrinker->nr_deferred[nid]);
else
new_nr = atomic_long_read(&shrinker->nr_deferred[nid]);
if (PageDirty(page)) {
struct address_space *mapping;
+ bool migrate_dirty;
/* ISOLATE_CLEAN means only clean pages */
if (mode & ISOLATE_CLEAN)
/*
* Only pages without mappings or that have a
* ->migratepage callback are possible to migrate
- * without blocking
+ * without blocking. However, we can be racing with
+ * truncation so it's necessary to lock the page
+ * to stabilise the mapping as truncation holds
+ * the page lock until after the page is removed
+ * from the page cache.
*/
+ if (!trylock_page(page))
+ return ret;
+
mapping = page_mapping(page);
- if (mapping && !mapping->a_ops->migratepage)
+ migrate_dirty = !mapping || mapping->a_ops->migratepage;
+ unlock_page(page);
+ if (!migrate_dirty)
return ret;
}
}
* be complete before mem_cgroup_update_lru_size due to a santity check.
*/
static __always_inline void update_lru_sizes(struct lruvec *lruvec,
- enum lru_list lru, unsigned long *nr_zone_taken,
- unsigned long nr_taken)
+ enum lru_list lru, unsigned long *nr_zone_taken)
{
int zid;
continue;
__update_lru_size(lruvec, lru, zid, -nr_zone_taken[zid]);
- }
-
#ifdef CONFIG_MEMCG
- mem_cgroup_update_lru_size(lruvec, lru, -nr_taken);
+ mem_cgroup_update_lru_size(lruvec, lru, zid, -nr_zone_taken[zid]);
#endif
+ }
+
}
/*
*nr_scanned = scan;
trace_mm_vmscan_lru_isolate(sc->reclaim_idx, sc->order, nr_to_scan, scan,
nr_taken, mode, is_file_lru(lru));
- update_lru_sizes(lruvec, lru, nr_zone_taken, nr_taken);
+ update_lru_sizes(lruvec, lru, nr_zone_taken);
return nr_taken;
}
struct scan_control *sc)
{
unsigned long inactive_ratio;
- unsigned long inactive;
- unsigned long active;
+ unsigned long inactive, active;
+ enum lru_list inactive_lru = file * LRU_FILE;
+ enum lru_list active_lru = file * LRU_FILE + LRU_ACTIVE;
unsigned long gb;
- struct pglist_data *pgdat = lruvec_pgdat(lruvec);
- int zid;
/*
* If we don't have swap space, anonymous page deactivation
if (!file && !total_swap_pages)
return false;
- inactive = lruvec_lru_size(lruvec, file * LRU_FILE);
- active = lruvec_lru_size(lruvec, file * LRU_FILE + LRU_ACTIVE);
-
- /*
- * For zone-constrained allocations, it is necessary to check if
- * deactivations are required for lowmem to be reclaimed. This
- * calculates the inactive/active pages available in eligible zones.
- */
- for (zid = sc->reclaim_idx + 1; zid < MAX_NR_ZONES; zid++) {
- struct zone *zone = &pgdat->node_zones[zid];
- unsigned long inactive_zone, active_zone;
-
- if (!managed_zone(zone))
- continue;
-
- inactive_zone = zone_page_state(zone,
- NR_ZONE_LRU_BASE + (file * LRU_FILE));
- active_zone = zone_page_state(zone,
- NR_ZONE_LRU_BASE + (file * LRU_FILE) + LRU_ACTIVE);
-
- inactive -= min(inactive, inactive_zone);
- active -= min(active, active_zone);
- }
+ inactive = lruvec_lru_size(lruvec, inactive_lru, sc->reclaim_idx);
+ active = lruvec_lru_size(lruvec, active_lru, sc->reclaim_idx);
gb = (inactive + active) >> (30 - PAGE_SHIFT);
if (gb)
* system is under heavy pressure.
*/
if (!inactive_list_is_low(lruvec, true, sc) &&
- lruvec_lru_size(lruvec, LRU_INACTIVE_FILE) >> sc->priority) {
+ lruvec_lru_size(lruvec, LRU_INACTIVE_FILE, sc->reclaim_idx) >> sc->priority) {
scan_balance = SCAN_FILE;
goto out;
}
* anon in [0], file in [1]
*/
- anon = lruvec_lru_size(lruvec, LRU_ACTIVE_ANON) +
- lruvec_lru_size(lruvec, LRU_INACTIVE_ANON);
- file = lruvec_lru_size(lruvec, LRU_ACTIVE_FILE) +
- lruvec_lru_size(lruvec, LRU_INACTIVE_FILE);
+ anon = lruvec_lru_size(lruvec, LRU_ACTIVE_ANON, MAX_NR_ZONES) +
+ lruvec_lru_size(lruvec, LRU_INACTIVE_ANON, MAX_NR_ZONES);
+ file = lruvec_lru_size(lruvec, LRU_ACTIVE_FILE, MAX_NR_ZONES) +
+ lruvec_lru_size(lruvec, LRU_INACTIVE_FILE, MAX_NR_ZONES);
spin_lock_irq(&pgdat->lru_lock);
if (unlikely(reclaim_stat->recent_scanned[0] > anon / 4)) {
unsigned long size;
unsigned long scan;
- size = lruvec_lru_size(lruvec, lru);
+ size = lruvec_lru_size(lruvec, lru, sc->reclaim_idx);
scan = size >> sc->priority;
if (!scan && pass && force_scan)
}
}
+ cond_resched();
+
if (nr_reclaimed < nr_to_reclaim || scan_adjusted)
continue;
} while (should_continue_reclaim(pgdat, sc->nr_reclaimed - nr_reclaimed,
sc->nr_scanned - nr_scanned, sc));
+ /*
+ * Kswapd gives up on balancing particular nodes after too
+ * many failures to reclaim anything from them and goes to
+ * sleep. On reclaim progress, reset the failure counter. A
+ * successful direct reclaim run will revive a dormant kswapd.
+ */
+ if (reclaimable)
+ pgdat->kswapd_failures = 0;
+
return reclaimable;
}
GFP_KERNEL | __GFP_HARDWALL))
continue;
- if (sc->priority != DEF_PRIORITY &&
- !pgdat_reclaimable(zone->zone_pgdat))
- continue; /* Let kswapd poll it */
-
/*
* If we already have plenty of memory free for
* compaction in this zone, don't free any more.
return 0;
}
-static bool pfmemalloc_watermark_ok(pg_data_t *pgdat)
+static bool allow_direct_reclaim(pg_data_t *pgdat)
{
struct zone *zone;
unsigned long pfmemalloc_reserve = 0;
int i;
bool wmark_ok;
+ if (pgdat->kswapd_failures >= MAX_RECLAIM_RETRIES)
+ return true;
+
for (i = 0; i <= ZONE_NORMAL; i++) {
zone = &pgdat->node_zones[i];
- if (!managed_zone(zone) ||
- pgdat_reclaimable_pages(pgdat) == 0)
+ if (!managed_zone(zone))
+ continue;
+
+ if (!zone_reclaimable_pages(zone))
continue;
pfmemalloc_reserve += min_wmark_pages(zone);
/* Throttle based on the first usable node */
pgdat = zone->zone_pgdat;
- if (pfmemalloc_watermark_ok(pgdat))
+ if (allow_direct_reclaim(pgdat))
goto out;
break;
}
*/
if (!(gfp_mask & __GFP_FS)) {
wait_event_interruptible_timeout(pgdat->pfmemalloc_wait,
- pfmemalloc_watermark_ok(pgdat), HZ);
+ allow_direct_reclaim(pgdat), HZ);
goto check_pending;
}
/* Throttle until kswapd wakes the process */
wait_event_killable(zone->zone_pgdat->pfmemalloc_wait,
- pfmemalloc_watermark_ok(pgdat));
+ allow_direct_reclaim(pgdat));
check_pending:
if (fatal_signal_pending(current))
unsigned long nr_reclaimed;
struct scan_control sc = {
.nr_to_reclaim = SWAP_CLUSTER_MAX,
- .gfp_mask = (gfp_mask = memalloc_noio_flags(gfp_mask)),
+ .gfp_mask = memalloc_noio_flags(gfp_mask),
.reclaim_idx = gfp_zone(gfp_mask),
.order = order,
.nodemask = nodemask,
* 1 is returned so that the page allocator does not OOM kill at this
* point.
*/
- if (throttle_direct_reclaim(gfp_mask, zonelist, nodemask))
+ if (throttle_direct_reclaim(sc.gfp_mask, zonelist, nodemask))
return 1;
trace_mm_vmscan_direct_reclaim_begin(order,
sc.may_writepage,
- gfp_mask,
+ sc.gfp_mask,
sc.reclaim_idx);
nr_reclaimed = do_try_to_free_pages(zonelist, &sc);
*/
clear_bit(PGDAT_CONGESTED, &zone->zone_pgdat->flags);
clear_bit(PGDAT_DIRTY, &zone->zone_pgdat->flags);
+ clear_bit(PGDAT_WRITEBACK, &zone->zone_pgdat->flags);
return true;
}
/*
* The throttled processes are normally woken up in balance_pgdat() as
- * soon as pfmemalloc_watermark_ok() is true. But there is a potential
+ * soon as allow_direct_reclaim() is true. But there is a potential
* race between when kswapd checks the watermarks and a process gets
* throttled. There is also a potential race if processes get
* throttled, kswapd wakes, a large process exits thereby balancing the
if (waitqueue_active(&pgdat->pfmemalloc_wait))
wake_up_all(&pgdat->pfmemalloc_wait);
+ /* Hopeless node, leave it to direct reclaim */
+ if (pgdat->kswapd_failures >= MAX_RECLAIM_RETRIES)
+ return true;
+
for (i = 0; i <= classzone_idx; i++) {
struct zone *zone = pgdat->node_zones + i;
count_vm_event(PAGEOUTRUN);
do {
+ unsigned long nr_reclaimed = sc.nr_reclaimed;
bool raise_priority = true;
- sc.nr_reclaimed = 0;
sc.reclaim_idx = classzone_idx;
/*
* If we're getting trouble reclaiming, start doing writepage
* even in laptop mode.
*/
- if (sc.priority < DEF_PRIORITY - 2 || !pgdat_reclaimable(pgdat))
+ if (sc.priority < DEF_PRIORITY - 2)
sc.may_writepage = 1;
/* Call soft limit reclaim before calling shrink_node. */
* able to safely make forward progress. Wake them
*/
if (waitqueue_active(&pgdat->pfmemalloc_wait) &&
- pfmemalloc_watermark_ok(pgdat))
+ allow_direct_reclaim(pgdat))
wake_up_all(&pgdat->pfmemalloc_wait);
/* Check if kswapd should be suspending */
* Raise priority if scanning rate is too low or there was no
* progress in reclaiming pages
*/
- if (raise_priority || !sc.nr_reclaimed)
+ nr_reclaimed = sc.nr_reclaimed - nr_reclaimed;
+ if (raise_priority || !nr_reclaimed)
sc.priority--;
} while (sc.priority >= 1);
+ if (!sc.nr_reclaimed)
+ pgdat->kswapd_failures++;
+
out:
/*
* Return the order kswapd stopped reclaiming at as
if (!waitqueue_active(&pgdat->kswapd_wait))
return;
+ /* Hopeless node, leave it to direct reclaim */
+ if (pgdat->kswapd_failures >= MAX_RECLAIM_RETRIES)
+ return;
+
/* Only wake kswapd if all zones are unbalanced */
for (z = 0; z <= classzone_idx; z++) {
zone = pgdat->node_zones + z;
const unsigned long nr_pages = 1 << order;
struct task_struct *p = current;
struct reclaim_state reclaim_state;
- int classzone_idx = gfp_zone(gfp_mask);
struct scan_control sc = {
.nr_to_reclaim = max(nr_pages, SWAP_CLUSTER_MAX),
- .gfp_mask = (gfp_mask = memalloc_noio_flags(gfp_mask)),
+ .gfp_mask = memalloc_noio_flags(gfp_mask),
.order = order,
.priority = NODE_RECLAIM_PRIORITY,
.may_writepage = !!(node_reclaim_mode & RECLAIM_WRITE),
.may_unmap = !!(node_reclaim_mode & RECLAIM_UNMAP),
.may_swap = 1,
- .reclaim_idx = classzone_idx,
+ .reclaim_idx = gfp_zone(gfp_mask),
};
cond_resched();
* and RECLAIM_UNMAP.
*/
p->flags |= PF_MEMALLOC | PF_SWAPWRITE;
- lockdep_set_current_reclaim_state(gfp_mask);
+ lockdep_set_current_reclaim_state(sc.gfp_mask);
reclaim_state.reclaimed_slab = 0;
p->reclaim_state = &reclaim_state;
sum_zone_node_page_state(pgdat->node_id, NR_SLAB_RECLAIMABLE) <= pgdat->min_slab_pages)
return NODE_RECLAIM_FULL;
- if (!pgdat_reclaimable(pgdat))
- return NODE_RECLAIM_FULL;
-
/*
* Do not scan if the allocation should not be delayed.
*/
*/
int page_evictable(struct page *page)
{
- return !mapping_unevictable(page_mapping(page)) && !PageMlocked(page);
+ int ret;
+
+ /* Prevent address_space of inode and swap cache from being freed */
+ rcu_read_lock();
+ ret = !mapping_unevictable(page_mapping(page)) && !PageMlocked(page);
+ rcu_read_unlock();
+ return ret;
}
#ifdef CONFIG_SHMEM