}
#endif
-unsigned long zone_reclaimable_pages(struct zone *zone)
+static unsigned long zone_reclaimable_pages(struct zone *zone)
{
int nr;
nr_pages_scanned, lru_pages,
max_pass, delta, total_scan);
- while (total_scan >= batch_size) {
+ /*
+ * Normally, we should not scan less than batch_size objects in one
+ * pass to avoid too frequent shrinker calls, but if the slab has less
+ * than batch_size objects in total and we are really tight on memory,
+ * we will try to reclaim all available objects, otherwise we can end
+ * up failing allocations although there are plenty of reclaimable
+ * objects spread over several slabs with usage less than the
+ * batch_size.
+ *
+ * We detect the "tight on memory" situations by looking at the total
+ * number of objects we want to scan (total_scan). If it is greater
+ * than the total number of objects on slab (max_pass), we must be
+ * scanning at high prio and therefore should try to reclaim as much as
+ * possible.
+ */
+ while (total_scan >= batch_size ||
+ total_scan >= max_pass) {
unsigned long ret;
+ unsigned long nr_to_scan = min(batch_size, total_scan);
- shrinkctl->nr_to_scan = batch_size;
+ shrinkctl->nr_to_scan = nr_to_scan;
ret = shrinker->scan_objects(shrinker, shrinkctl);
if (ret == SHRINK_STOP)
break;
freed += ret;
- count_vm_events(SLABS_SCANNED, batch_size);
- total_scan -= batch_size;
+ count_vm_events(SLABS_SCANNED, nr_to_scan);
+ total_scan -= nr_to_scan;
cond_resched();
}
}
list_for_each_entry(shrinker, &shrinker_list, list) {
- for_each_node_mask(shrinkctl->nid, shrinkctl->nodes_to_scan) {
- if (!node_online(shrinkctl->nid))
- continue;
-
- if (!(shrinker->flags & SHRINKER_NUMA_AWARE) &&
- (shrinkctl->nid != 0))
- break;
-
+ if (!(shrinker->flags & SHRINKER_NUMA_AWARE)) {
+ shrinkctl->nid = 0;
freed += shrink_slab_node(shrinkctl, shrinker,
- nr_pages_scanned, lru_pages);
+ nr_pages_scanned, lru_pages);
+ continue;
+ }
+
+ for_each_node_mask(shrinkctl->nid, shrinkctl->nodes_to_scan) {
+ if (node_online(shrinkctl->nid))
+ freed += shrink_slab_node(shrinkctl, shrinker,
+ nr_pages_scanned, lru_pages);
}
}
bool is_unevictable;
int was_unevictable = PageUnevictable(page);
- VM_BUG_ON(PageLRU(page));
+ VM_BUG_ON_PAGE(PageLRU(page), page);
redo:
ClearPageUnevictable(page);
if (!trylock_page(page))
goto keep;
- VM_BUG_ON(PageActive(page));
- VM_BUG_ON(page_zone(page) != zone);
+ VM_BUG_ON_PAGE(PageActive(page), page);
+ VM_BUG_ON_PAGE(page_zone(page) != zone, page);
sc->nr_scanned++;
/* Not a candidate for swapping, so reclaim swap space. */
if (PageSwapCache(page) && vm_swap_full())
try_to_free_swap(page);
- VM_BUG_ON(PageActive(page));
+ VM_BUG_ON_PAGE(PageActive(page), page);
SetPageActive(page);
pgactivate++;
keep_locked:
unlock_page(page);
keep:
list_add(&page->lru, &ret_pages);
- VM_BUG_ON(PageLRU(page) || PageUnevictable(page));
+ VM_BUG_ON_PAGE(PageLRU(page) || PageUnevictable(page), page);
}
free_hot_cold_page_list(&free_pages, 1);
page = lru_to_page(src);
prefetchw_prev_lru_page(page, src, flags);
- VM_BUG_ON(!PageLRU(page));
+ VM_BUG_ON_PAGE(!PageLRU(page), page);
switch (__isolate_lru_page(page, mode)) {
case 0:
{
int ret = -EBUSY;
- VM_BUG_ON(!page_count(page));
+ VM_BUG_ON_PAGE(!page_count(page), page);
if (PageLRU(page)) {
struct zone *zone = page_zone(page);
struct page *page = lru_to_page(page_list);
int lru;
- VM_BUG_ON(PageLRU(page));
+ VM_BUG_ON_PAGE(PageLRU(page), page);
list_del(&page->lru);
if (unlikely(!page_evictable(page))) {
spin_unlock_irq(&zone->lru_lock);
* If dirty pages are scanned that are not queued for IO, it
* implies that flushers are not keeping up. In this case, flag
* the zone ZONE_TAIL_LRU_DIRTY and kswapd will start writing
- * pages from reclaim context. It will forcibly stall in the
- * next check.
+ * pages from reclaim context.
*/
if (nr_unqueued_dirty == nr_taken)
zone_set_flag(zone, ZONE_TAIL_LRU_DIRTY);
/*
- * In addition, if kswapd scans pages marked marked for
- * immediate reclaim and under writeback (nr_immediate), it
- * implies that pages are cycling through the LRU faster than
+ * If kswapd scans pages marked marked for immediate
+ * reclaim and under writeback (nr_immediate), it implies
+ * that pages are cycling through the LRU faster than
* they are written so also forcibly stall.
*/
- if (nr_unqueued_dirty == nr_taken || nr_immediate)
+ if (nr_immediate)
congestion_wait(BLK_RW_ASYNC, HZ/10);
}
page = lru_to_page(list);
lruvec = mem_cgroup_page_lruvec(page, zone);
- VM_BUG_ON(PageLRU(page));
+ VM_BUG_ON_PAGE(PageLRU(page), page);
SetPageLRU(page);
nr_pages = hpage_nr_pages(page);
for (i = 0; i <= ZONE_NORMAL; i++) {
zone = &pgdat->node_zones[i];
+ if (!populated_zone(zone))
+ continue;
+
pfmemalloc_reserve += min_wmark_pages(zone);
free_pages += zone_page_state(zone, NR_FREE_PAGES);
}
+ /* If there are no reserves (unexpected config) then do not throttle */
+ if (!pfmemalloc_reserve)
+ return true;
+
wmark_ok = free_pages > pfmemalloc_reserve / 2;
/* kswapd must be awake if processes are being throttled */
static bool throttle_direct_reclaim(gfp_t gfp_mask, struct zonelist *zonelist,
nodemask_t *nodemask)
{
+ struct zoneref *z;
struct zone *zone;
- int high_zoneidx = gfp_zone(gfp_mask);
- pg_data_t *pgdat;
+ pg_data_t *pgdat = NULL;
/*
* Kernel threads should not be throttled as they may be indirectly
if (fatal_signal_pending(current))
goto out;
- /* Check if the pfmemalloc reserves are ok */
- first_zones_zonelist(zonelist, high_zoneidx, NULL, &zone);
- pgdat = zone->zone_pgdat;
- if (pfmemalloc_watermark_ok(pgdat))
+ /*
+ * Check if the pfmemalloc reserves are ok by finding the first node
+ * with a usable ZONE_NORMAL or lower zone. The expectation is that
+ * GFP_KERNEL will be required for allocating network buffers when
+ * swapping over the network so ZONE_HIGHMEM is unusable.
+ *
+ * Throttling is based on the first usable node and throttled processes
+ * wait on a queue until kswapd makes progress and wakes them. There
+ * is an affinity then between processes waking up and where reclaim
+ * progress has been made assuming the process wakes on the same node.
+ * More importantly, processes running on remote nodes will not compete
+ * for remote pfmemalloc reserves and processes on different nodes
+ * should make reasonable progress.
+ */
+ for_each_zone_zonelist_nodemask(zone, z, zonelist,
+ gfp_mask, nodemask) {
+ if (zone_idx(zone) > ZONE_NORMAL)
+ continue;
+
+ /* Throttle based on the first usable node */
+ pgdat = zone->zone_pgdat;
+ if (pfmemalloc_watermark_ok(pgdat))
+ goto out;
+ break;
+ }
+
+ /* If no zone was usable by the allocation flags then do not throttle */
+ if (!pgdat)
goto out;
/* Account for the throttling */
}
}
+ tsk->flags &= ~(PF_MEMALLOC | PF_SWAPWRITE | PF_KSWAPD);
current->reclaim_state = NULL;
+ lockdep_clear_current_reclaim_state();
+
return 0;
}
wake_up_interruptible(&pgdat->kswapd_wait);
}
-/*
- * The reclaimable count would be mostly accurate.
- * The less reclaimable pages may be
- * - mlocked pages, which will be moved to unevictable list when encountered
- * - mapped pages, which may require several travels to be reclaimed
- * - dirty pages, which is not "instantly" reclaimable
- */
-unsigned long global_reclaimable_pages(void)
-{
- int nr;
-
- nr = global_page_state(NR_ACTIVE_FILE) +
- global_page_state(NR_INACTIVE_FILE);
-
- if (get_nr_swap_pages() > 0)
- nr += global_page_state(NR_ACTIVE_ANON) +
- global_page_state(NR_INACTIVE_ANON);
-
- return nr;
-}
-
#ifdef CONFIG_HIBERNATION
/*
* Try to free `nr_to_reclaim' of memory, system-wide, and return the number of
if (page_evictable(page)) {
enum lru_list lru = page_lru_base_type(page);
- VM_BUG_ON(PageActive(page));
+ VM_BUG_ON_PAGE(PageActive(page), page);
ClearPageUnevictable(page);
del_page_from_lru_list(page, lruvec, LRU_UNEVICTABLE);
add_page_to_lru_list(page, lruvec, lru);