aboutsummaryrefslogtreecommitdiffstats
path: root/mm/workingset.c
diff options
context:
space:
mode:
Diffstat (limited to 'mm/workingset.c')
-rw-r--r--mm/workingset.c69
1 files changed, 53 insertions, 16 deletions
diff --git a/mm/workingset.c b/mm/workingset.c
index c963831d354f..474186b76ced 100644
--- a/mm/workingset.c
+++ b/mm/workingset.c
@@ -213,28 +213,53 @@ static void unpack_shadow(void *shadow, int *memcgidp, pg_data_t **pgdat,
*workingsetp = workingset;
}
+static void advance_inactive_age(struct mem_cgroup *memcg, pg_data_t *pgdat)
+{
+ /*
+ * Reclaiming a cgroup means reclaiming all its children in a
+ * round-robin fashion. That means that each cgroup has an LRU
+ * order that is composed of the LRU orders of its child
+ * cgroups; and every page has an LRU position not just in the
+ * cgroup that owns it, but in all of that group's ancestors.
+ *
+ * So when the physical inactive list of a leaf cgroup ages,
+ * the virtual inactive lists of all its parents, including
+ * the root cgroup's, age as well.
+ */
+ do {
+ struct lruvec *lruvec;
+
+ lruvec = mem_cgroup_lruvec(memcg, pgdat);
+ atomic_long_inc(&lruvec->inactive_age);
+ } while (memcg && (memcg = parent_mem_cgroup(memcg)));
+}
+
/**
* workingset_eviction - note the eviction of a page from memory
+ * @target_memcg: the cgroup that is causing the reclaim
* @page: the page being evicted
*
* Returns a shadow entry to be stored in @page->mapping->i_pages in place
* of the evicted @page so that a later refault can be detected.
*/
-void *workingset_eviction(struct page *page)
+void *workingset_eviction(struct page *page, struct mem_cgroup *target_memcg)
{
struct pglist_data *pgdat = page_pgdat(page);
- struct mem_cgroup *memcg = page_memcg(page);
- int memcgid = mem_cgroup_id(memcg);
unsigned long eviction;
struct lruvec *lruvec;
+ int memcgid;
/* Page is fully exclusive and pins page->mem_cgroup */
VM_BUG_ON_PAGE(PageLRU(page), page);
VM_BUG_ON_PAGE(page_count(page), page);
VM_BUG_ON_PAGE(!PageLocked(page), page);
- lruvec = mem_cgroup_lruvec(pgdat, memcg);
- eviction = atomic_long_inc_return(&lruvec->inactive_age);
+ advance_inactive_age(page_memcg(page), pgdat);
+
+ lruvec = mem_cgroup_lruvec(target_memcg, pgdat);
+ /* XXX: target_memcg can be NULL, go through lruvec */
+ memcgid = mem_cgroup_id(lruvec_memcg(lruvec));
+ eviction = atomic_long_read(&lruvec->inactive_age);
return pack_shadow(memcgid, pgdat, eviction, PageWorkingset(page));
}
@@ -244,10 +269,13 @@ void *workingset_eviction(struct page *page)
* @shadow: shadow entry of the evicted page
*
* Calculates and evaluates the refault distance of the previously
- * evicted page in the context of the node it was allocated in.
+ * evicted page in the context of the node and the memcg whose memory
+ * pressure caused the eviction.
*/
void workingset_refault(struct page *page, void *shadow)
{
+ struct mem_cgroup *eviction_memcg;
+ struct lruvec *eviction_lruvec;
unsigned long refault_distance;
struct pglist_data *pgdat;
unsigned long active_file;
@@ -277,12 +305,12 @@ void workingset_refault(struct page *page, void *shadow)
* would be better if the root_mem_cgroup existed in all
* configurations instead.
*/
- memcg = mem_cgroup_from_id(memcgid);
- if (!mem_cgroup_disabled() && !memcg)
+ eviction_memcg = mem_cgroup_from_id(memcgid);
+ if (!mem_cgroup_disabled() && !eviction_memcg)
goto out;
- lruvec = mem_cgroup_lruvec(pgdat, memcg);
- refault = atomic_long_read(&lruvec->inactive_age);
- active_file = lruvec_lru_size(lruvec, LRU_ACTIVE_FILE, MAX_NR_ZONES);
+ eviction_lruvec = mem_cgroup_lruvec(eviction_memcg, pgdat);
+ refault = atomic_long_read(&eviction_lruvec->inactive_age);
+ active_file = lruvec_page_state(eviction_lruvec, NR_ACTIVE_FILE);
/*
* Calculate the refault distance
@@ -302,6 +330,17 @@ void workingset_refault(struct page *page, void *shadow)
*/
refault_distance = (refault - eviction) & EVICTION_MASK;
+ /*
+ * The activation decision for this page is made at the level
+ * where the eviction occurred, as that is where the LRU order
+ * during page reclaim is being determined.
+ *
+ * However, the cgroup that will own the page is the one that
+ * is actually experiencing the refault event.
+ */
+ memcg = page_memcg(page);
+ lruvec = mem_cgroup_lruvec(memcg, pgdat);
+
inc_lruvec_state(lruvec, WORKINGSET_REFAULT);
/*
@@ -313,7 +352,7 @@ void workingset_refault(struct page *page, void *shadow)
goto out;
SetPageActive(page);
- atomic_long_inc(&lruvec->inactive_age);
+ advance_inactive_age(memcg, pgdat);
inc_lruvec_state(lruvec, WORKINGSET_ACTIVATE);
/* Page was active prior to eviction */
@@ -332,7 +371,6 @@ out:
void workingset_activation(struct page *page)
{
struct mem_cgroup *memcg;
- struct lruvec *lruvec;
rcu_read_lock();
/*
@@ -345,8 +383,7 @@ void workingset_activation(struct page *page)
memcg = page_memcg_rcu(page);
if (!mem_cgroup_disabled() && !memcg)
goto out;
- lruvec = mem_cgroup_lruvec(page_pgdat(page), memcg);
- atomic_long_inc(&lruvec->inactive_age);
+ advance_inactive_age(memcg, page_pgdat(page));
out:
rcu_read_unlock();
}
@@ -426,7 +463,7 @@ static unsigned long count_shadow_nodes(struct shrinker *shrinker,
struct lruvec *lruvec;
int i;
- lruvec = mem_cgroup_lruvec(NODE_DATA(sc->nid), sc->memcg);
+ lruvec = mem_cgroup_lruvec(sc->memcg, NODE_DATA(sc->nid));
for (pages = 0, i = 0; i < NR_LRU_LISTS; i++)
pages += lruvec_page_state_local(lruvec,
NR_LRU_BASE + i);