memcg: refactor mem_cgroup_oom

Patch series "memcg: robust enforcement of memory.high", v2.

Due to the semantics of memory.high enforcement i.e.  throttle the
workload without oom-kill, we are trying to use it for right sizing the
workloads in our production environment.  However we observed the
mechanism fails for some specific applications which does big chunck of
allocations in a single syscall.  The reason behind this failure is due
to the limitation of the memory.high enforcement's current
implementation.

This patch series solves this issue by enforcing the memory.high
synchronously if the current process has accumulated a large amount of
high overcharge.

This patch (of 4):

The function mem_cgroup_oom returns enum which has four possible values
but the caller does not care about such values and only cares if the
return value is OOM_SUCCESS or not.  So, remove the enum altogether and
make mem_cgroup_oom returns a simple bool.

Link: https://lkml.kernel.org/r/20220211064917.2028469-1-shakeelb@google.com
Link: https://lkml.kernel.org/r/20220211064917.2028469-2-shakeelb@google.com
Signed-off-by: Shakeel Butt <shakeelb@google.com>
Reviewed-by: Roman Gushchin <guro@fb.com>
Cc: Roman Gushchin <roman.gushchin@linux.dev>
Cc: Johannes Weiner <hannes@cmpxchg.org>
Cc: Michal Hocko <mhocko@suse.com>
Cc: Chris Down <chris@chrisdown.name>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>

1 files changed, 17 insertions, 27 deletions

diff --git a/mm/memcontrol.c b/mm/memcontrol.c
index 5318c3fb92f4..0451cc06b157 100644
--- a/mm/memcontrol.c
+++ b/mm/memcontrol.c
@@ -1796,20 +1796,16 @@ static void memcg_oom_recover(struct mem_cgroup *memcg)
 		__wake_up(&memcg_oom_waitq, TASK_NORMAL, 0, memcg);
 }
 
-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)
+/*
+ * Returns true if successfully killed one or more processes. Though in some
+ * corner cases it can return true even without killing any process.
+ */
+static bool mem_cgroup_oom(struct mem_cgroup *memcg, gfp_t mask, int order)
 {
-	enum oom_status ret;
-	bool locked;
+	bool locked, ret;
 
 	if (order > PAGE_ALLOC_COSTLY_ORDER)
-		return OOM_SKIPPED;
+		return false;
 
 	memcg_memory_event(memcg, MEMCG_OOM);
 
@@ -1832,14 +1828,13 @@ static enum oom_status mem_cgroup_oom(struct mem_cgroup *memcg, gfp_t mask, int
 	 * victim and then we have to bail out from the charge path.
 	 */
 	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 (current->in_user_fault) {
+			css_get(&memcg->css);
+			current->memcg_in_oom = memcg;
+			current->memcg_oom_gfp_mask = mask;
+			current->memcg_oom_order = order;
+		}
+		return false;
 	}
 
 	mem_cgroup_mark_under_oom(memcg);
@@ -1850,10 +1845,7 @@ static enum oom_status mem_cgroup_oom(struct mem_cgroup *memcg, gfp_t mask, int
 		mem_cgroup_oom_notify(memcg);
 
 	mem_cgroup_unmark_under_oom(memcg);
-	if (mem_cgroup_out_of_memory(memcg, mask, order))
-		ret = OOM_SUCCESS;
-	else
-		ret = OOM_FAILED;
+	ret = mem_cgroup_out_of_memory(memcg, mask, order);
 
 	if (locked)
 		mem_cgroup_oom_unlock(memcg);
@@ -2546,7 +2538,6 @@ static int try_charge_memcg(struct mem_cgroup *memcg, gfp_t gfp_mask,
 	int nr_retries = MAX_RECLAIM_RETRIES;
 	struct mem_cgroup *mem_over_limit;
 	struct page_counter *counter;
-	enum oom_status oom_status;
 	unsigned long nr_reclaimed;
 	bool passed_oom = false;
 	bool may_swap = true;
@@ -2649,9 +2640,8 @@ retry:
 	 * 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));
-	if (oom_status == OOM_SUCCESS) {
+	if (mem_cgroup_oom(mem_over_limit, gfp_mask,
+			   get_order(nr_pages * PAGE_SIZE))) {
 		passed_oom = true;
 		nr_retries = MAX_RECLAIM_RETRIES;
 		goto retry;