[v8 3/4] mm, oom: add cgroup v2 mount option for cgroup-aware OOM killer

[Roman Gushchin]

Add a "groupoom" cgroup v2 mount option to enable the cgroup-aware
OOM killer. If not set, the OOM selection is performed in
a "traditional" per-process way.

The behavior can be changed dynamically by remounting the cgroupfs.

Signed-off-by: Roman Gushchin <g...@fb.com>
Cc: Michal Hocko <mho...@kernel.org>
Cc: Vladimir Davydov <vdavydov....@gmail.com>
Cc: Johannes Weiner <han...@cmpxchg.org>
Cc: Tetsuo Handa <penguin-ker...@i-love.sakura.ne.jp>
Cc: David Rientjes <rient...@google.com>
Cc: Andrew Morton <a...@linux-foundation.org>
Cc: Tejun Heo <t...@kernel.org>
Cc: kernel-t...@fb.com
Cc: cgro...@vger.kernel.org
Cc: linux-doc@vger.kernel.org
Cc: linux-ker...@vger.kernel.org
Cc: linux...@kvack.org
---
 include/linux/cgroup-defs.h |  5 +++++
 kernel/cgroup/cgroup.c      | 10 ++++++++++
 mm/memcontrol.c             |  3 +++
 3 files changed, 18 insertions(+)

diff --git a/include/linux/cgroup-defs.h b/include/linux/cgroup-defs.h
index ade4a78a54c2..db4ff3e233a9 100644
--- a/include/linux/cgroup-defs.h
+++ b/include/linux/cgroup-defs.h
@@ -79,6 +79,11 @@ enum {
         * Enable cpuset controller in v1 cgroup to use v2 behavior.
         */
        CGRP_ROOT_CPUSET_V2_MODE = (1 << 4),
+
+       /*
+        * Enable cgroup-aware OOM killer.
+        */
+       CGRP_GROUP_OOM = (1 << 5),
 };
 
 /* cftype->flags */
diff --git a/kernel/cgroup/cgroup.c b/kernel/cgroup/cgroup.c
index d6551cd45238..5f8a97a233bb 100644
--- a/kernel/cgroup/cgroup.c
+++ b/kernel/cgroup/cgroup.c
@@ -1699,6 +1699,9 @@ static int parse_cgroup_root_flags(char *data, unsigned 
int *root_flags)
                if (!strcmp(token, "nsdelegate")) {
                        *root_flags |= CGRP_ROOT_NS_DELEGATE;
                        continue;
+               } else if (!strcmp(token, "groupoom")) {
+                       *root_flags |= CGRP_GROUP_OOM;
+                       continue;
                }
 
                pr_err("cgroup2: unknown option \"%s\"\n", token);
@@ -1715,6 +1718,11 @@ static void apply_cgroup_root_flags(unsigned int 
root_flags)
                        cgrp_dfl_root.flags |= CGRP_ROOT_NS_DELEGATE;
                else
                        cgrp_dfl_root.flags &= ~CGRP_ROOT_NS_DELEGATE;
+
+               if (root_flags & CGRP_GROUP_OOM)
+                       cgrp_dfl_root.flags |= CGRP_GROUP_OOM;
+               else
+                       cgrp_dfl_root.flags &= ~CGRP_GROUP_OOM;
        }
 }
 
@@ -1722,6 +1730,8 @@ static int cgroup_show_options(struct seq_file *seq, 
struct kernfs_root *kf_root
 {
        if (cgrp_dfl_root.flags & CGRP_ROOT_NS_DELEGATE)
                seq_puts(seq, ",nsdelegate");
+       if (cgrp_dfl_root.flags & CGRP_GROUP_OOM)
+               seq_puts(seq, ",groupoom");
        return 0;
 }
 
diff --git a/mm/memcontrol.c b/mm/memcontrol.c
index da2b12ea4667..d645f70cb3a7 100644
--- a/mm/memcontrol.c
+++ b/mm/memcontrol.c
@@ -2871,6 +2871,9 @@ bool mem_cgroup_select_oom_victim(struct oom_control *oc)
        if (!cgroup_subsys_on_dfl(memory_cgrp_subsys))
                return false;
 
+       if (!(cgrp_dfl_root.flags & CGRP_GROUP_OOM))
+               return false;
+
        if (oc->memcg)
                root = oc->memcg;
        else
-- 
2.13.5

--
To unsubscribe from this list: send the line "unsubscribe linux-doc" in
the body of a message to majord...@vger.kernel.org
More majordomo info at  http://vger.kernel.org/majordomo-info.html