mm: memcg: enable memcg OOM killer only for user faults

System calls and kernel faults (uaccess, gup) can handle an out of memory
situation gracefully and just return -ENOMEM.

Enable the memcg OOM killer only for user faults, where it's really the
only option available.

Signed-off-by: Johannes Weiner <hannes@cmpxchg.org>
Acked-by: Michal Hocko <mhocko@suse.cz>
Cc: David Rientjes <rientjes@google.com>
Cc: KAMEZAWA Hiroyuki <kamezawa.hiroyu@jp.fujitsu.com>
Cc: azurIt <azurit@pobox.sk>
Cc: KOSAKI Motohiro <kosaki.motohiro@jp.fujitsu.com>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>

2 files changed, 47 insertions, 0 deletions

diff --git a/include/linux/memcontrol.h b/include/linux/memcontrol.h
index d4d1f9b0dbba..34ac6497d01a 100644
--- a/include/linux/memcontrol.h
+++ b/include/linux/memcontrol.h
@@ -151,6 +151,37 @@ extern void mem_cgroup_print_oom_info(struct mem_cgroup *memcg,
 extern void mem_cgroup_replace_page_cache(struct page *oldpage,
                                         struct page *newpage);
 
+/**
+ * mem_cgroup_toggle_oom - toggle the memcg OOM killer for the current task
+ * @new: true to enable, false to disable
+ *
+ * Toggle whether a failed memcg charge should invoke the OOM killer
+ * or just return -ENOMEM.  Returns the previous toggle state.
+ */
+static inline bool mem_cgroup_toggle_oom(bool new)
+{
+        bool old;
+
+        old = current->memcg_oom.may_oom;
+        current->memcg_oom.may_oom = new;
+
+        return old;
+}
+
+static inline void mem_cgroup_enable_oom(void)
+{
+        bool old = mem_cgroup_toggle_oom(true);
+
+        WARN_ON(old == true);
+}
+
+static inline void mem_cgroup_disable_oom(void)
+{
+        bool old = mem_cgroup_toggle_oom(false);
+
+        WARN_ON(old == false);
+}
+
 #ifdef CONFIG_MEMCG_SWAP
 extern int do_swap_account;
 #endif
@@ -383,6 +414,19 @@ static inline void mem_cgroup_end_update_page_stat(struct page *page,
 {
 }
 
+static inline bool mem_cgroup_toggle_oom(bool new)
+{
+        return false;
+}
+
+static inline void mem_cgroup_enable_oom(void)
+{
+}
+
+static inline void mem_cgroup_disable_oom(void)
+{
+}
+
 static inline void mem_cgroup_inc_page_stat(struct page *page,
                                             enum mem_cgroup_page_stat_item idx)
 {
diff --git a/include/linux/sched.h b/include/linux/sched.h
index 45f254dddafc..9ce1fa53031f 100644
--- a/include/linux/sched.h
+++ b/include/linux/sched.h
@@ -1393,6 +1393,9 @@ struct task_struct {
                 unsigned long memsw_nr_pages; /* uncharged mem+swap usage */
         } memcg_batch;
         unsigned int memcg_kmem_skip_account;
+        struct memcg_oom_info {
+                unsigned int may_oom:1;
+        } memcg_oom;
 #endif
 #ifdef CONFIG_UPROBES
         struct uprobe_task *utask;