summaryrefslogtreecommitdiffstats
path: root/mm/memcontrol.c
diff options
context:
space:
mode:
authorMichal Hocko <mhocko@suse.com>2018-08-17 15:47:11 -0700
committerLinus Torvalds <torvalds@linux-foundation.org>2018-08-17 16:20:30 -0700
commit29ef680ae7c21110af8e6416d84d8a72fc147b14 (patch)
treee051bc36f19520a0f2a3951f064ac5224b388168 /mm/memcontrol.c
parentd39f8fb4b7776dcb09ec3bf7a321547083078ee3 (diff)
downloadlinux-29ef680ae7c21110af8e6416d84d8a72fc147b14.tar.bz2
memcg, oom: move out_of_memory back to the charge path
Commit 3812c8c8f395 ("mm: memcg: do not trap chargers with full callstack on OOM") has changed the ENOMEM semantic of memcg charges. Rather than invoking the oom killer from the charging context it delays the oom killer to the page fault path (pagefault_out_of_memory). This in turn means that many users (e.g. slab or g-u-p) will get ENOMEM when the corresponding memcg hits the hard limit and the memcg is is OOM. This is behavior is inconsistent with !memcg case where the oom killer is invoked from the allocation context and the allocator keeps retrying until it succeeds. The difference in the behavior is user visible. mmap(MAP_POPULATE) might result in not fully populated ranges while the mmap return code doesn't tell that to the userspace. Random syscalls might fail with ENOMEM etc. The primary motivation of the different memcg oom semantic was the deadlock avoidance. Things have changed since then, though. We have an async oom teardown by the oom reaper now and so we do not have to rely on the victim to tear down its memory anymore. Therefore we can return to the original semantic as long as the memcg oom killer is not handed over to the users space. There is still one thing to be careful about here though. If the oom killer is not able to make any forward progress - e.g. because there is no eligible task to kill - then we have to bail out of the charge path to prevent from same class of deadlocks. We have basically two options here. Either we fail the charge with ENOMEM or force the charge and allow overcharge. The first option has been considered more harmful than useful because rare inconsistencies in the ENOMEM behavior is hard to test for and error prone. Basically the same reason why the page allocator doesn't fail allocations under such conditions. The later might allow runaways but those should be really unlikely unless somebody misconfigures the system. E.g. allowing to migrate tasks away from the memcg to a different unlimited memcg with move_charge_at_immigrate disabled. Link: http://lkml.kernel.org/r/20180628151101.25307-1-mhocko@kernel.org Signed-off-by: Michal Hocko <mhocko@suse.com> Acked-by: Greg Thelen <gthelen@google.com> Cc: Johannes Weiner <hannes@cmpxchg.org> Cc: Shakeel Butt <shakeelb@google.com> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
Diffstat (limited to 'mm/memcontrol.c')
-rw-r--r--mm/memcontrol.c75
1 files changed, 60 insertions, 15 deletions
diff --git a/mm/memcontrol.c b/mm/memcontrol.c
index c071af193986..d6724bed57d8 100644
--- a/mm/memcontrol.c
+++ b/mm/memcontrol.c
@@ -1534,28 +1534,53 @@ static void memcg_oom_recover(struct mem_cgroup *memcg)
__wake_up(&memcg_oom_waitq, TASK_NORMAL, 0, memcg);
}
-static void mem_cgroup_oom(struct mem_cgroup *memcg, gfp_t mask, int order)
+enum oom_status {
+ OOM_SUCCESS,
+ OOM_FAILED,
+ OOM_ASYNC,
+ OOM_SKIPPED
+};
+
+static enum oom_status mem_cgroup_oom(struct mem_cgroup *memcg, gfp_t mask, int order)
{
- if (!current->memcg_may_oom || order > PAGE_ALLOC_COSTLY_ORDER)
- return;
+ if (order > PAGE_ALLOC_COSTLY_ORDER)
+ return OOM_SKIPPED;
+
/*
* We are in the middle of the charge context here, so we
* don't want to block when potentially sitting on a callstack
* that holds all kinds of filesystem and mm locks.
*
- * Also, the caller may handle a failed allocation gracefully
- * (like optional page cache readahead) and so an OOM killer
- * invocation might not even be necessary.
+ * cgroup1 allows disabling the OOM killer and waiting for outside
+ * handling until the charge can succeed; remember the context and put
+ * the task to sleep at the end of the page fault when all locks are
+ * released.
+ *
+ * On the other hand, in-kernel OOM killer allows for an async victim
+ * memory reclaim (oom_reaper) and that means that we are not solely
+ * relying on the oom victim to make a forward progress and we can
+ * invoke the oom killer here.
*
- * That's why we don't do anything here except remember the
- * OOM context and then deal with it at the end of the page
- * fault when the stack is unwound, the locks are released,
- * and when we know whether the fault was overall successful.
+ * Please note that mem_cgroup_out_of_memory might fail to find a
+ * victim and then we have to bail out from the charge path.
*/
- css_get(&memcg->css);
- current->memcg_in_oom = memcg;
- current->memcg_oom_gfp_mask = mask;
- current->memcg_oom_order = order;
+ if (memcg->oom_kill_disable) {
+ if (!current->in_user_fault)
+ return OOM_SKIPPED;
+ css_get(&memcg->css);
+ current->memcg_in_oom = memcg;
+ current->memcg_oom_gfp_mask = mask;
+ current->memcg_oom_order = order;
+
+ return OOM_ASYNC;
+ }
+
+ if (mem_cgroup_out_of_memory(memcg, mask, order))
+ return OOM_SUCCESS;
+
+ WARN(1,"Memory cgroup charge failed because of no reclaimable memory! "
+ "This looks like a misconfiguration or a kernel bug.");
+ return OOM_FAILED;
}
/**
@@ -1950,6 +1975,8 @@ static int try_charge(struct mem_cgroup *memcg, gfp_t gfp_mask,
unsigned long nr_reclaimed;
bool may_swap = true;
bool drained = false;
+ bool oomed = false;
+ enum oom_status oom_status;
if (mem_cgroup_is_root(memcg))
return 0;
@@ -2037,6 +2064,9 @@ retry:
if (nr_retries--)
goto retry;
+ if (gfp_mask & __GFP_RETRY_MAYFAIL && oomed)
+ goto nomem;
+
if (gfp_mask & __GFP_NOFAIL)
goto force;
@@ -2045,8 +2075,23 @@ retry:
memcg_memory_event(mem_over_limit, MEMCG_OOM);
- mem_cgroup_oom(mem_over_limit, gfp_mask,
+ /*
+ * keep retrying as long as the memcg oom killer is able to make
+ * a forward progress or bypass the charge if the oom killer
+ * couldn't make any progress.
+ */
+ oom_status = mem_cgroup_oom(mem_over_limit, gfp_mask,
get_order(nr_pages * PAGE_SIZE));
+ switch (oom_status) {
+ case OOM_SUCCESS:
+ nr_retries = MEM_CGROUP_RECLAIM_RETRIES;
+ oomed = true;
+ goto retry;
+ case OOM_FAILED:
+ goto force;
+ default:
+ goto nomem;
+ }
nomem:
if (!(gfp_mask & __GFP_NOFAIL))
return -ENOMEM;