mm, memcg: allow system oom killer to be disabledmm/oom

Now that system oom conditions can properly be handled from userspace,
allow the oom killer to be disabled.  Otherwise, the kernel will
immediately kill a process and memory will be freed.  The userspace oom
handler may have a different policy.

Signed-off-by: David Rientjes <rientjes@google.com>

4 files changed, 19 insertions, 5 deletions

diff --git a/Documentation/cgroups/memory.txt b/Documentation/cgroups/memory.txt
index 4ed05d6bdc1dd..4240b0cfb96fe 100644
--- a/Documentation/cgroups/memory.txt
+++ b/Documentation/cgroups/memory.txt
@@ -755,8 +755,8 @@ You can disable the OOM-killer by writing "1" to memory.oom_control file, as:
 
 	# echo 1 > memory.oom_control
 
-This operation is only allowed to the top cgroup of a sub-hierarchy and does
-not include the root memcg.
+This operation is only allowed to the top cgroup of a sub-hierarchy.  If
+disabled for the root memcg, the system oom killer is disabled.
 If OOM-killer is disabled, tasks under cgroup will hang/sleep
 in memory cgroup's OOM-waitqueue when they request accountable memory.
 
diff --git a/include/linux/memcontrol.h b/include/linux/memcontrol.h
index efa928e36d1d2..68b48ad7b92d8 100644
--- a/include/linux/memcontrol.h
+++ b/include/linux/memcontrol.h
@@ -159,6 +159,7 @@ bool mem_cgroup_oom_synchronize(bool wait);
 extern bool mem_cgroup_alloc_use_oom_reserve(void);
 extern u64 mem_cgroup_root_oom_reserve(void);
 extern void mem_cgroup_root_oom_notify(void);
+extern bool mem_cgroup_root_oom_disable(void);
 
 #ifdef CONFIG_MEMCG_SWAP
 extern int do_swap_account;
@@ -415,6 +416,11 @@ static inline void mem_cgroup_root_oom_notify(void)
 {
 }
 
+static inline bool mem_cgroup_root_oom_disable(void)
+{
+	return false;
+}
+
 static inline void mem_cgroup_inc_page_stat(struct page *page,
 					    enum mem_cgroup_stat_index idx)
 {
diff --git a/mm/memcontrol.c b/mm/memcontrol.c
index da4464c02b466..52d04ba38cf14 100644
--- a/mm/memcontrol.c
+++ b/mm/memcontrol.c
@@ -5976,13 +5976,13 @@ static int mem_cgroup_oom_control_write(struct cgroup_subsys_state *css,
 	struct mem_cgroup *memcg = mem_cgroup_from_css(css);
 	struct mem_cgroup *parent = mem_cgroup_from_css(css_parent(&memcg->css));
 
-	/* cannot set to root cgroup and only 0 and 1 are allowed */
-	if (!parent || !((val == 0) || (val == 1)))
+	/* only 0 and 1 are allowed */
+	if (val != !!val)
 		return -EINVAL;
 
 	mutex_lock(&memcg_create_mutex);
 	/* oom-kill-disable is a flag for subhierarchy. */
-	if ((parent->use_hierarchy) || memcg_has_children(memcg)) {
+	if (parent && (parent->use_hierarchy || memcg_has_children(memcg))) {
 		mutex_unlock(&memcg_create_mutex);
 		return -EINVAL;
 	}
@@ -6062,6 +6062,11 @@ u64 mem_cgroup_root_oom_reserve(void)
 	return root_mem_cgroup->oom_reserve >> PAGE_SHIFT;
 }
 
+bool mem_cgroup_root_oom_disable(void)
+{
+	return root_mem_cgroup->oom_kill_disable;
+}
+
 #ifdef CONFIG_MEMCG_KMEM
 static int memcg_init_kmem(struct mem_cgroup *memcg, struct cgroup_subsys *ss)
 {
diff --git a/mm/oom_kill.c b/mm/oom_kill.c
index 329053d3c456f..26aee00e107b0 100644
--- a/mm/oom_kill.c
+++ b/mm/oom_kill.c
@@ -656,6 +656,9 @@ void out_of_memory(struct zonelist *zonelist, gfp_t gfp_mask,
 	mpol_mask = (constraint == CONSTRAINT_MEMORY_POLICY) ? nodemask : NULL;
 	check_panic_on_oom(constraint, gfp_mask, order, mpol_mask);
 
+	if (mem_cgroup_root_oom_disable())
+		return;
+
 	if (sysctl_oom_kill_allocating_task && current->mm &&
 	    !oom_unkillable_task(current, NULL, nodemask) &&
 	    current->signal->oom_score_adj != OOM_SCORE_ADJ_MIN) {