mm: memcg: count pte references from every member of the reclaimed hierarchy

The rmap walker checking page table references has historically
ignored references from VMAs that were not part of the memcg that was
being reclaimed during memcg hard limit reclaim.

When transitioning global reclaim to memcg hierarchy reclaim, I missed
that bit and now references from outside a memcg are ignored even
during global reclaim.

Reverting back to traditional behaviour - count all references during
global reclaim and only mind references of the memcg being reclaimed
during limit reclaim would be one option.

However, the more generic idea is to ignore references exactly then
when they are outside the hierarchy that is currently under reclaim;
because only then will their reclamation be of any use to help the
pressure situation.  It makes no sense to ignore references from a
sibling memcg and then evict a page that will be immediately refaulted
by that sibling which contributes to the same usage of the common
ancestor under reclaim.

The solution: make the rmap walker ignore references from VMAs that
are not part of the hierarchy that is being reclaimed.

Flat limit reclaim will stay the same, hierarchical limit reclaim will
mind the references only to pages that the hierarchy owns.  Global
reclaim, since it reclaims from all memcgs, will be fixed to regard
all references.

Signed-off-by: Johannes Weiner <hannes@cmpxchg.org>
Reported-by: Konstantin Khlebnikov <khlebnikov@openvz.org>
Acked-by: Konstantin Khlebnikov<khlebnikov@openvz.org>
Cc: KAMEZAWA Hiroyuki <kamezawa.hiroyu@jp.fujitsu.com>
Cc: Michal Hocko <mhocko@suse.cz>
Cc: Li Zefan <lizf@cn.fujitsu.com>
Cc: Li Zefan <lizf@cn.fujitsu.com>
Cc: Tejun Heo <tj@kernel.org>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>

diff --git a/include/linux/memcontrol.h b/include/linux/memcontrol.h
index 00ecc00f2cb0137ba7dba5203705883b0bbb2a6a..8eb55e30bc2bd85a86c62fd871f49872300739d0 100644 (file)
--- a/include/linux/memcontrol.h
+++ b/include/linux/memcontrol.h
@@ -79,6 +79,7 @@ extern void mem_cgroup_uncharge_cache_page(struct page *page);
 
 extern void mem_cgroup_out_of_memory(struct mem_cgroup *memcg, gfp_t gfp_mask,
                                     int order);
+bool __mem_cgroup_same_or_subtree(const struct mem_cgroup *, struct mem_cgroup *);
 int task_in_mem_cgroup(struct task_struct *task, const struct mem_cgroup *memcg);
 
 extern struct mem_cgroup *try_get_mem_cgroup_from_page(struct page *page);
@@ -92,10 +93,13 @@ static inline
 int mm_match_cgroup(const struct mm_struct *mm, const struct mem_cgroup *cgroup)
 {
        struct mem_cgroup *memcg;
+       int match;
+
        rcu_read_lock();
        memcg = mem_cgroup_from_task(rcu_dereference((mm)->owner));
+       match = __mem_cgroup_same_or_subtree(cgroup, memcg);
        rcu_read_unlock();
-       return cgroup == memcg;
+       return match;
 }
 
 extern struct cgroup_subsys_state *mem_cgroup_css(struct mem_cgroup *memcg);

diff --git a/mm/memcontrol.c b/mm/memcontrol.c
index 954c152beb9261dfaa3114108eb0639f05d177f3..8342a083890795236f6c360fd856ce3a99477e07 100644 (file)
--- a/mm/memcontrol.c
+++ b/mm/memcontrol.c
@@ -1168,17 +1168,23 @@ struct lruvec *mem_cgroup_lru_move_lists(struct zone *zone,
  * Checks whether given mem is same or in the root_mem_cgroup's
  * hierarchy subtree
  */
-static bool mem_cgroup_same_or_subtree(const struct mem_cgroup *root_memcg,
-               struct mem_cgroup *memcg)
+bool __mem_cgroup_same_or_subtree(const struct mem_cgroup *root_memcg,
+                                 struct mem_cgroup *memcg)
 {
-       bool ret;
-
        if (root_memcg == memcg)
                return true;
        if (!root_memcg->use_hierarchy)
                return false;
+       return css_is_ancestor(&memcg->css, &root_memcg->css);
+}
+
+static bool mem_cgroup_same_or_subtree(const struct mem_cgroup *root_memcg,
+                                      struct mem_cgroup *memcg)
+{
+       bool ret;
+
        rcu_read_lock();
-       ret = css_is_ancestor(&memcg->css, &root_memcg->css);
+       ret = __mem_cgroup_same_or_subtree(root_memcg, memcg);
        rcu_read_unlock();
        return ret;
 }

diff --git a/mm/vmscan.c b/mm/vmscan.c
index 68e5819d0f1bc5345ba5488acecd7387b1dda27d..8fffc65a84de545e01ac71366585cea399e9ec39 100644 (file)
--- a/mm/vmscan.c
+++ b/mm/vmscan.c
@@ -645,7 +645,8 @@ static enum page_references page_check_references(struct page *page,
        int referenced_ptes, referenced_page;
        unsigned long vm_flags;
 
-       referenced_ptes = page_referenced(page, 1, mz->mem_cgroup, &vm_flags);
+       referenced_ptes = page_referenced(page, 1, sc->target_mem_cgroup,
+                                         &vm_flags);
        referenced_page = TestClearPageReferenced(page);
 
        /*
@@ -1513,7 +1514,8 @@ static void shrink_active_list(unsigned long nr_to_scan,
                        }
                }
 
-               if (page_referenced(page, 0, mz->mem_cgroup, &vm_flags)) {
+               if (page_referenced(page, 0, sc->target_mem_cgroup,
+                                   &vm_flags)) {
                        nr_rotated += hpage_nr_pages(page);
                        /*
                         * Identify referenced, file-backed active pages and