diff mbox

fs, mm: account filp and names caches to kmemcg

Message ID 20171013070001.mglwdzdrqjt47clz@dhcp22.suse.cz (mailing list archive)
State New, archived
Headers show

Commit Message

Michal Hocko Oct. 13, 2017, 7 a.m. UTC
Just to be explicit what I've had in mind. This hasn't been even compile
tested but it should provide at least an idea where I am trying to go..
---
diff mbox

Patch

diff --git a/mm/memcontrol.c b/mm/memcontrol.c
index d5f3a62887cf..91fa05372114 100644
--- a/mm/memcontrol.c
+++ b/mm/memcontrol.c
@@ -1528,26 +1528,36 @@  static void memcg_oom_recover(struct mem_cgroup *memcg)
 
 static void mem_cgroup_oom(struct mem_cgroup *memcg, gfp_t mask, int order)
 {
-	if (!current->memcg_may_oom)
-		return;
 	/*
 	 * 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.
+	 * cgroup v1 allowes sync users space handling so we cannot afford
+	 * to get stuck here for that configuration. 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.
 	 *
-	 * 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.
+	 * 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 so we can stay
+	 * in the the try_charge context and keep retrying as long as there
+	 * are oom victims to select.
 	 */
-	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->memcg_may_oom)
+			return false;
+		css_get(&memcg->css);
+		current->memcg_in_oom = memcg;
+		current->memcg_oom_gfp_mask = mask;
+		current->memcg_oom_order = order;
+
+		return false;
+	}
+
+	return mem_cgroup_out_of_memory(memcg, mask, order);
 }
 
 /**
@@ -2007,8 +2017,11 @@  static int try_charge(struct mem_cgroup *memcg, gfp_t gfp_mask,
 
 	mem_cgroup_event(mem_over_limit, MEMCG_OOM);
 
-	mem_cgroup_oom(mem_over_limit, gfp_mask,
-		       get_order(nr_pages * PAGE_SIZE));
+	if (mem_cgroup_oom(mem_over_limit, gfp_mask,
+		       get_order(nr_pages * PAGE_SIZE))) {
+		nr_retries = MEM_CGROUP_RECLAIM_RETRIES;
+		goto retry;
+	}
 nomem:
 	if (!(gfp_mask & __GFP_NOFAIL))
 		return -ENOMEM;