#include <linux/mm.h>
#include <linux/module.h>
-#include <linux/slab.h>
+#include <linux/gfp.h>
#include <linux/kernel_stat.h>
#include <linux/swap.h>
#include <linux/pagemap.h>
int swappiness;
- int all_unreclaimable;
-
int order;
+ /*
+ * Intend to reclaim enough contenious memory rather than to reclaim
+ * enough amount memory. I.e, it's the mode for high order allocation.
+ */
+ bool lumpy_reclaim_mode;
+
/* Which cgroup do we reclaim from */
struct mem_cgroup *mem_cgroup;
return ret;
}
-/* 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;
-
- /* Page is in somebody's page tables. */
- if (page_mapped(page))
- return 1;
-
- /* Be more reluctant to reclaim swapcache than pagecache */
- if (PageSwapCache(page))
- return 1;
-
- mapping = page_mapping(page);
- if (!mapping)
- return 0;
-
- /* File is mmap'd by somebody? */
- return mapping_mapped(mapping);
-}
-
static inline int is_page_cache_freeable(struct page *page)
{
/*
put_page(page); /* drop ref from isolate */
}
+enum page_references {
+ PAGEREF_RECLAIM,
+ PAGEREF_RECLAIM_CLEAN,
+ PAGEREF_KEEP,
+ PAGEREF_ACTIVATE,
+};
+
+static enum page_references page_check_references(struct page *page,
+ struct scan_control *sc)
+{
+ int referenced_ptes, referenced_page;
+ unsigned long vm_flags;
+
+ referenced_ptes = page_referenced(page, 1, sc->mem_cgroup, &vm_flags);
+ referenced_page = TestClearPageReferenced(page);
+
+ /* Lumpy reclaim - ignore references */
+ if (sc->lumpy_reclaim_mode)
+ return PAGEREF_RECLAIM;
+
+ /*
+ * Mlock lost the isolation race with us. Let try_to_unmap()
+ * move the page to the unevictable list.
+ */
+ if (vm_flags & VM_LOCKED)
+ return PAGEREF_RECLAIM;
+
+ if (referenced_ptes) {
+ if (PageAnon(page))
+ return PAGEREF_ACTIVATE;
+ /*
+ * All mapped pages start out with page table
+ * references from the instantiating fault, so we need
+ * to look twice if a mapped file page is used more
+ * than once.
+ *
+ * Mark it and spare it for another trip around the
+ * inactive list. Another page table reference will
+ * lead to its activation.
+ *
+ * Note: the mark is set for activated pages as well
+ * so that recently deactivated but used pages are
+ * quickly recovered.
+ */
+ SetPageReferenced(page);
+
+ if (referenced_page)
+ return PAGEREF_ACTIVATE;
+
+ return PAGEREF_KEEP;
+ }
+
+ /* Reclaim if clean, defer dirty pages to writeback */
+ if (referenced_page)
+ return PAGEREF_RECLAIM_CLEAN;
+
+ return PAGEREF_RECLAIM;
+}
+
/*
* shrink_page_list() returns the number of reclaimed pages
*/
struct pagevec freed_pvec;
int pgactivate = 0;
unsigned long nr_reclaimed = 0;
- unsigned long vm_flags;
cond_resched();
pagevec_init(&freed_pvec, 1);
while (!list_empty(page_list)) {
+ enum page_references references;
struct address_space *mapping;
struct page *page;
int may_enter_fs;
- int referenced;
cond_resched();
goto keep_locked;
}
- referenced = page_referenced(page, 1,
- sc->mem_cgroup, &vm_flags);
- /*
- * In active use or really unfreeable? Activate it.
- * If page which have PG_mlocked lost isoltation race,
- * try_to_unmap moves it to unevictable list
- */
- if (sc->order <= PAGE_ALLOC_COSTLY_ORDER &&
- referenced && page_mapping_inuse(page)
- && !(vm_flags & VM_LOCKED))
+ references = page_check_references(page, sc);
+ switch (references) {
+ case PAGEREF_ACTIVATE:
goto activate_locked;
+ case PAGEREF_KEEP:
+ goto keep_locked;
+ case PAGEREF_RECLAIM:
+ case PAGEREF_RECLAIM_CLEAN:
+ ; /* try to reclaim the page below */
+ }
/*
* Anonymous process memory has backing store?
}
if (PageDirty(page)) {
- if (sc->order <= PAGE_ALLOC_COSTLY_ORDER && referenced)
+ if (references == PAGEREF_RECLAIM_CLEAN)
goto keep_locked;
if (!may_enter_fs)
goto keep_locked;
return nr_reclaimed;
}
-/* LRU Isolation modes. */
-#define ISOLATE_INACTIVE 0 /* Isolate inactive pages. */
-#define ISOLATE_ACTIVE 1 /* Isolate active pages. */
-#define ISOLATE_BOTH 2 /* Isolate both active and inactive pages. */
-
/*
* Attempt to remove the specified page from its LRU. Only take this page
* if it is of the appropriate PageActive status. Pages which are being
unsigned long nr_scanned = 0;
unsigned long nr_reclaimed = 0;
struct zone_reclaim_stat *reclaim_stat = get_reclaim_stat(zone, sc);
- int lumpy_reclaim = 0;
while (unlikely(too_many_isolated(zone, file, sc))) {
congestion_wait(BLK_RW_ASYNC, HZ/10);
return SWAP_CLUSTER_MAX;
}
- /*
- * If we need a large contiguous chunk of memory, or have
- * trouble getting a small set of contiguous pages, we
- * will reclaim both active and inactive pages.
- *
- * We use the same threshold as pageout congestion_wait below.
- */
- if (sc->order > PAGE_ALLOC_COSTLY_ORDER)
- lumpy_reclaim = 1;
- else if (sc->order && priority < DEF_PRIORITY - 2)
- lumpy_reclaim = 1;
pagevec_init(&pvec, 1);
unsigned long nr_freed;
unsigned long nr_active;
unsigned int count[NR_LRU_LISTS] = { 0, };
- int mode = lumpy_reclaim ? ISOLATE_BOTH : ISOLATE_INACTIVE;
+ int mode = sc->lumpy_reclaim_mode ? ISOLATE_BOTH : ISOLATE_INACTIVE;
unsigned long nr_anon;
unsigned long nr_file;
* but that should be acceptable to the caller
*/
if (nr_freed < nr_taken && !current_is_kswapd() &&
- lumpy_reclaim) {
+ sc->lumpy_reclaim_mode) {
congestion_wait(BLK_RW_ASYNC, HZ/10);
/*
continue;
}
- /* page_referenced clears PageReferenced */
- if (page_mapping_inuse(page) &&
- page_referenced(page, 0, sc->mem_cgroup, &vm_flags)) {
+ if (page_referenced(page, 0, sc->mem_cgroup, &vm_flags)) {
nr_rotated++;
/*
* Identify referenced, file-backed active pages and
return shrink_inactive_list(nr_to_scan, zone, sc, priority, file);
}
+/*
+ * Smallish @nr_to_scan's are deposited in @nr_saved_scan,
+ * until we collected @swap_cluster_max pages to scan.
+ */
+static unsigned long nr_scan_try_batch(unsigned long nr_to_scan,
+ unsigned long *nr_saved_scan)
+{
+ unsigned long nr;
+
+ *nr_saved_scan += nr_to_scan;
+ nr = *nr_saved_scan;
+
+ if (nr >= SWAP_CLUSTER_MAX)
+ *nr_saved_scan = 0;
+ else
+ nr = 0;
+
+ return nr;
+}
+
/*
* Determine how aggressively the anon and file LRU lists should be
* scanned. The relative value of each set of LRU lists is determined
* by looking at the fraction of the pages scanned we did rotate back
* onto the active list instead of evict.
*
- * percent[0] specifies how much pressure to put on ram/swap backed
- * memory, while percent[1] determines pressure on the file LRUs.
+ * nr[0] = anon pages to scan; nr[1] = file pages to scan
*/
-static void get_scan_ratio(struct zone *zone, struct scan_control *sc,
- unsigned long *percent)
+static void get_scan_count(struct zone *zone, struct scan_control *sc,
+ unsigned long *nr, int priority)
{
unsigned long anon, file, free;
unsigned long anon_prio, file_prio;
unsigned long ap, fp;
struct zone_reclaim_stat *reclaim_stat = get_reclaim_stat(zone, sc);
+ u64 fraction[2], denominator;
+ enum lru_list l;
+ int noswap = 0;
+
+ /* If we have no swap space, do not bother scanning anon pages. */
+ if (!sc->may_swap || (nr_swap_pages <= 0)) {
+ noswap = 1;
+ fraction[0] = 0;
+ fraction[1] = 1;
+ denominator = 1;
+ goto out;
+ }
anon = zone_nr_lru_pages(zone, sc, LRU_ACTIVE_ANON) +
zone_nr_lru_pages(zone, sc, LRU_INACTIVE_ANON);
/* If we have very few page cache pages,
force-scan anon pages. */
if (unlikely(file + free <= high_wmark_pages(zone))) {
- percent[0] = 100;
- percent[1] = 0;
- return;
+ fraction[0] = 1;
+ fraction[1] = 0;
+ denominator = 1;
+ goto out;
}
}
fp = (file_prio + 1) * (reclaim_stat->recent_scanned[1] + 1);
fp /= reclaim_stat->recent_rotated[1] + 1;
- /* Normalize to percentages */
- percent[0] = 100 * ap / (ap + fp + 1);
- percent[1] = 100 - percent[0];
+ fraction[0] = ap;
+ fraction[1] = fp;
+ denominator = ap + fp + 1;
+out:
+ for_each_evictable_lru(l) {
+ int file = is_file_lru(l);
+ unsigned long scan;
+
+ scan = zone_nr_lru_pages(zone, sc, l);
+ if (priority || noswap) {
+ scan >>= priority;
+ scan = div64_u64(scan * fraction[file], denominator);
+ }
+ nr[l] = nr_scan_try_batch(scan,
+ &reclaim_stat->nr_saved_scan[l]);
+ }
}
-/*
- * Smallish @nr_to_scan's are deposited in @nr_saved_scan,
- * until we collected @swap_cluster_max pages to scan.
- */
-static unsigned long nr_scan_try_batch(unsigned long nr_to_scan,
- unsigned long *nr_saved_scan)
+static void set_lumpy_reclaim_mode(int priority, struct scan_control *sc)
{
- unsigned long nr;
-
- *nr_saved_scan += nr_to_scan;
- nr = *nr_saved_scan;
-
- if (nr >= SWAP_CLUSTER_MAX)
- *nr_saved_scan = 0;
+ /*
+ * If we need a large contiguous chunk of memory, or have
+ * trouble getting a small set of contiguous pages, we
+ * will reclaim both active and inactive pages.
+ */
+ if (sc->order > PAGE_ALLOC_COSTLY_ORDER)
+ sc->lumpy_reclaim_mode = 1;
+ else if (sc->order && priority < DEF_PRIORITY - 2)
+ sc->lumpy_reclaim_mode = 1;
else
- nr = 0;
-
- return nr;
+ sc->lumpy_reclaim_mode = 0;
}
/*
{
unsigned long nr[NR_LRU_LISTS];
unsigned long nr_to_scan;
- unsigned long percent[2]; /* anon @ 0; file @ 1 */
enum lru_list l;
unsigned long nr_reclaimed = sc->nr_reclaimed;
unsigned long nr_to_reclaim = sc->nr_to_reclaim;
- struct zone_reclaim_stat *reclaim_stat = get_reclaim_stat(zone, sc);
- int noswap = 0;
- /* If we have no swap space, do not bother scanning anon pages. */
- if (!sc->may_swap || (nr_swap_pages <= 0)) {
- noswap = 1;
- percent[0] = 0;
- percent[1] = 100;
- } else
- get_scan_ratio(zone, sc, percent);
+ get_scan_count(zone, sc, nr, priority);
- for_each_evictable_lru(l) {
- int file = is_file_lru(l);
- unsigned long scan;
-
- scan = zone_nr_lru_pages(zone, sc, l);
- if (priority || noswap) {
- scan >>= priority;
- scan = (scan * percent[file]) / 100;
- }
- nr[l] = nr_scan_try_batch(scan,
- &reclaim_stat->nr_saved_scan[l]);
- }
+ set_lumpy_reclaim_mode(priority, sc);
while (nr[LRU_INACTIVE_ANON] || nr[LRU_ACTIVE_FILE] ||
nr[LRU_INACTIVE_FILE]) {
* If a zone is deemed to be full of pinned pages then just give it a light
* scan then give up on it.
*/
-static void shrink_zones(int priority, struct zonelist *zonelist,
+static int shrink_zones(int priority, struct zonelist *zonelist,
struct scan_control *sc)
{
enum zone_type high_zoneidx = gfp_zone(sc->gfp_mask);
struct zoneref *z;
struct zone *zone;
+ int progress = 0;
- sc->all_unreclaimable = 1;
for_each_zone_zonelist_nodemask(zone, z, zonelist, high_zoneidx,
sc->nodemask) {
if (!populated_zone(zone))
continue;
note_zone_scanning_priority(zone, priority);
- if (zone_is_all_unreclaimable(zone) &&
- priority != DEF_PRIORITY)
+ if (zone->all_unreclaimable && priority != DEF_PRIORITY)
continue; /* Let kswapd poll it */
- sc->all_unreclaimable = 0;
} else {
/*
* Ignore cpuset limitation here. We just want to reduce
* # of used pages by us regardless of memory shortage.
*/
- sc->all_unreclaimable = 0;
mem_cgroup_note_reclaim_priority(sc->mem_cgroup,
priority);
}
shrink_zone(priority, zone, sc);
+ progress = 1;
}
+ return progress;
}
/*
enum zone_type high_zoneidx = gfp_zone(sc->gfp_mask);
unsigned long writeback_threshold;
+ get_mems_allowed();
delayacct_freepages_start();
if (scanning_global_lru(sc))
sc->nr_scanned = 0;
if (!priority)
disable_swap_token();
- shrink_zones(priority, zonelist, sc);
+ ret = shrink_zones(priority, zonelist, sc);
/*
* Don't shrink slabs when reclaiming memory from
* over limit cgroups
congestion_wait(BLK_RW_ASYNC, HZ/10);
}
/* top priority shrink_zones still had more to do? don't OOM, then */
- if (!sc->all_unreclaimable && scanning_global_lru(sc))
+ if (ret && scanning_global_lru(sc))
ret = sc->nr_reclaimed;
out:
/*
mem_cgroup_record_reclaim_priority(sc->mem_cgroup, priority);
delayacct_freepages_end();
+ put_mems_allowed();
return ret;
}
if (!populated_zone(zone))
continue;
- if (zone_is_all_unreclaimable(zone))
+ if (zone->all_unreclaimable)
continue;
if (!zone_watermark_ok(zone, order, high_wmark_pages(zone),
if (!populated_zone(zone))
continue;
- if (zone_is_all_unreclaimable(zone) &&
- priority != DEF_PRIORITY)
+ if (zone->all_unreclaimable && priority != DEF_PRIORITY)
continue;
/*
if (!populated_zone(zone))
continue;
- if (zone_is_all_unreclaimable(zone) &&
- priority != DEF_PRIORITY)
+ if (zone->all_unreclaimable && priority != DEF_PRIORITY)
continue;
- if (!zone_watermark_ok(zone, order,
- high_wmark_pages(zone), end_zone, 0))
- all_zones_ok = 0;
temp_priority[i] = priority;
sc.nr_scanned = 0;
note_zone_scanning_priority(zone, priority);
lru_pages);
sc.nr_reclaimed += reclaim_state->reclaimed_slab;
total_scanned += sc.nr_scanned;
- if (zone_is_all_unreclaimable(zone))
+ if (zone->all_unreclaimable)
continue;
- if (nr_slab == 0 && zone->pages_scanned >=
- (zone_reclaimable_pages(zone) * 6))
- zone_set_flag(zone,
- ZONE_ALL_UNRECLAIMABLE);
+ if (nr_slab == 0 &&
+ zone->pages_scanned >= (zone_reclaimable_pages(zone) * 6))
+ zone->all_unreclaimable = 1;
/*
* If we've done a decent amount of scanning and
* the reclaim ratio is low, start doing writepage
total_scanned > sc.nr_reclaimed + sc.nr_reclaimed / 2)
sc.may_writepage = 1;
- /*
- * We are still under min water mark. it mean we have
- * GFP_ATOMIC allocation failure risk. Hurry up!
- */
- if (!zone_watermark_ok(zone, order, min_wmark_pages(zone),
- end_zone, 0))
- has_under_min_watermark_zone = 1;
+ if (!zone_watermark_ok(zone, order,
+ high_wmark_pages(zone), end_zone, 0)) {
+ all_zones_ok = 0;
+ /*
+ * We are still under min water mark. This
+ * means that we have a GFP_ATOMIC allocation
+ * failure risk. Hurry up!
+ */
+ if (!zone_watermark_ok(zone, order,
+ min_wmark_pages(zone), end_zone, 0))
+ has_under_min_watermark_zone = 1;
+ }
}
if (all_zones_ok)
* and RECLAIM_SWAP.
*/
p->flags |= PF_MEMALLOC | PF_SWAPWRITE;
+ lockdep_set_current_reclaim_state(gfp_mask);
reclaim_state.reclaimed_slab = 0;
p->reclaim_state = &reclaim_state;
p->reclaim_state = NULL;
current->flags &= ~(PF_MEMALLOC | PF_SWAPWRITE);
+ lockdep_clear_current_reclaim_state();
return sc.nr_reclaimed >= nr_pages;
}
zone_page_state(zone, NR_SLAB_RECLAIMABLE) <= zone->min_slab_pages)
return ZONE_RECLAIM_FULL;
- if (zone_is_all_unreclaimable(zone))
+ if (zone->all_unreclaimable)
return ZONE_RECLAIM_FULL;
/*