path: root/include/linux
diff options
authorYang Shi <yang.shi@linux.alibaba.com>2019-09-23 15:38:15 -0700
committerLinus Torvalds <torvalds@linux-foundation.org>2019-09-24 15:54:11 -0700
commit87eaceb3faa59b9b4d940ec9554ce251325d83fe (patch)
treee01af1eb069f448c047ad4151fd35ad211e3aeb9 /include/linux
parent0a432dcbeb32edcd211a5d8f7847d0da7642a8b4 (diff)
mm: thp: make deferred split shrinker memcg aware
Currently THP deferred split shrinker is not memcg aware, this may cause premature OOM with some configuration. For example the below test would run into premature OOM easily: $ cgcreate -g memory:thp $ echo 4G > /sys/fs/cgroup/memory/thp/memory/limit_in_bytes $ cgexec -g memory:thp transhuge-stress 4000 transhuge-stress comes from kernel selftest. It is easy to hit OOM, but there are still a lot THP on the deferred split queue, memcg direct reclaim can't touch them since the deferred split shrinker is not memcg aware. Convert deferred split shrinker memcg aware by introducing per memcg deferred split queue. The THP should be on either per node or per memcg deferred split queue if it belongs to a memcg. When the page is immigrated to the other memcg, it will be immigrated to the target memcg's deferred split queue too. Reuse the second tail page's deferred_list for per memcg list since the same THP can't be on multiple deferred split queues. [yang.shi@linux.alibaba.com: simplify deferred split queue dereference per Kirill Tkhai] Link: http://lkml.kernel.org/r/1566496227-84952-5-git-send-email-yang.shi@linux.alibaba.com Link: http://lkml.kernel.org/r/1565144277-36240-5-git-send-email-yang.shi@linux.alibaba.com Signed-off-by: Yang Shi <yang.shi@linux.alibaba.com> Acked-by: Kirill A. Shutemov <kirill.shutemov@linux.intel.com> Reviewed-by: Kirill Tkhai <ktkhai@virtuozzo.com> Cc: Johannes Weiner <hannes@cmpxchg.org> Cc: Michal Hocko <mhocko@suse.com> Cc: "Kirill A . Shutemov" <kirill.shutemov@linux.intel.com> Cc: Hugh Dickins <hughd@google.com> Cc: Shakeel Butt <shakeelb@google.com> Cc: David Rientjes <rientjes@google.com> Cc: Qian Cai <cai@lca.pw> Cc: Vladimir Davydov <vdavydov.dev@gmail.com> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
Diffstat (limited to 'include/linux')
3 files changed, 14 insertions, 0 deletions
diff --git a/include/linux/huge_mm.h b/include/linux/huge_mm.h
index 45ede62aa85b..61c9ffd89b05 100644
--- a/include/linux/huge_mm.h
+++ b/include/linux/huge_mm.h
@@ -267,6 +267,15 @@ static inline bool thp_migration_supported(void)
+static inline struct list_head *page_deferred_list(struct page *page)
+ /*
+ * Global or memcg deferred list in the second tail pages is
+ * occupied by compound_head.
+ */
+ return &page[2].deferred_list;
#define HPAGE_PMD_SHIFT ({ BUILD_BUG(); 0; })
#define HPAGE_PMD_MASK ({ BUILD_BUG(); 0; })
diff --git a/include/linux/memcontrol.h b/include/linux/memcontrol.h
index a3c0a639c824..9b60863429cc 100644
--- a/include/linux/memcontrol.h
+++ b/include/linux/memcontrol.h
@@ -330,6 +330,10 @@ struct mem_cgroup {
struct list_head event_list;
spinlock_t event_list_lock;
+ struct deferred_split deferred_split_queue;
struct mem_cgroup_per_node *nodeinfo[0];
/* WARNING: nodeinfo must be the last member here */
diff --git a/include/linux/mm_types.h b/include/linux/mm_types.h
index 0b739f360cec..5183e0d77dfa 100644
--- a/include/linux/mm_types.h
+++ b/include/linux/mm_types.h
@@ -138,6 +138,7 @@ struct page {
struct { /* Second tail page of compound page */
unsigned long _compound_pad_1; /* compound_head */
unsigned long _compound_pad_2;
+ /* For both global and memcg */
struct list_head deferred_list;
struct { /* Page table pages */

Privacy Policy