The kernel currently allows dying tasks to exceed the memcg limits.
The allocation is expected to be the last one and the occupied memory
will be freed soon.
This is not always true because it can be part of the huge vmalloc
allocation. Allowed once, they will repeat over and over again.
Moreover lifetime of the allocated object can differ from
In addition the lifetime of the dying task.
Multiple such allocations running concurrently can not only overuse
the memcg limit, but can lead to a global out of memory and,
in the worst case, cause the host to panic.
Signed-off-by: Vasily Averin <vvs@xxxxxxxxxxxxx>
---
mm/memcontrol.c | 23 +++++------------------
1 file changed, 5 insertions(+), 18 deletions(-)
diff --git a/mm/memcontrol.c b/mm/memcontrol.c
index 389b5766e74f..67195fcfbddf 100644
--- a/mm/memcontrol.c
+++ b/mm/memcontrol.c
@@ -1834,6 +1834,9 @@ static enum oom_status mem_cgroup_oom(struct mem_cgroup *memcg, gfp_t mask, int
return OOM_ASYNC;
}
+ if (should_force_charge())
+ return OOM_SKIPPED;
+
mem_cgroup_mark_under_oom(memcg);
locked = mem_cgroup_oom_trylock(memcg);
@@ -2622,15 +2625,6 @@ static int try_charge_memcg(struct mem_cgroup *memcg, gfp_t gfp_mask,
if (gfp_mask & __GFP_ATOMIC)
goto force;
- /*
- * Unlike in global OOM situations, memcg is not in a physical
- * memory shortage. Allow dying and OOM-killed tasks to
- * bypass the last charges so that they can exit quickly and
- * free their memory.
- */
- if (unlikely(should_force_charge()))
- goto force;
-
/*
* Prevent unbounded recursion when reclaim operations need to
* allocate memory. This might exceed the limits temporarily,
@@ -2688,9 +2682,6 @@ static int try_charge_memcg(struct mem_cgroup *memcg, gfp_t gfp_mask,
if (gfp_mask & __GFP_RETRY_MAYFAIL)
goto nomem;
- if (fatal_signal_pending(current))
- goto force;
-
/*
* keep retrying as long as the memcg oom killer is able to make
* a forward progress or bypass the charge if the oom killer
@@ -2698,15 +2689,11 @@ static int try_charge_memcg(struct mem_cgroup *memcg, gfp_t gfp_mask,
*/
oom_status = mem_cgroup_oom(mem_over_limit, gfp_mask,
get_order(nr_pages * PAGE_SIZE));
- switch (oom_status) {
- case OOM_SUCCESS:
+ if (oom_status == OOM_SUCCESS) {
nr_retries = MAX_RECLAIM_RETRIES;
goto retry;
- case OOM_FAILED:
+ } else if (oom_status == OOM_FAILED)
goto force;
- default:
- goto nomem;
- }
nomem:
if (!(gfp_mask & __GFP_NOFAIL))
return -ENOMEM;
--
2.31.1
