mm, memcontrol: implement memory.swap.events

Add swap max and fail events so that userland can monitor and respond to
running out of swap.

I'm not too sure about the fail event.  Right now, it's a bit confusing
which stats / events are recursive and which aren't and also which ones
reflect events which originate from a given cgroup and which targets the
cgroup.  No idea what the right long term solution is and it could just
be that growing them organically is actually the only right thing to do.

Link: http://lkml.kernel.org/r/20180416231151.GI1911913@devbig577.frc2.facebook.com
Signed-off-by: Tejun Heo <tj@kernel.org>
Reviewed-by: Andrew Morton <akpm@linux-foundation.org>
Cc: Johannes Weiner <hannes@cmpxchg.org>
Cc: Michal Hocko <mhocko@kernel.org>
Cc: Vladimir Davydov <vdavydov.dev@gmail.com>
Cc: Roman Gushchin <guro@fb.com>
Cc: Rik van Riel <riel@surriel.com>
Cc: <linux-api@vger.kernel.org>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>

3 files changed, 44 insertions, 1 deletions

diff --git a/Documentation/admin-guide/cgroup-v2.rst b/Documentation/admin-guide/cgroup-v2.rst
index 74cdeaed9f7a..b0dda10b9382 100644
--- a/Documentation/admin-guide/cgroup-v2.rst
+++ b/Documentation/admin-guide/cgroup-v2.rst
@@ -1199,6 +1199,22 @@ PAGE_SIZE multiple when read back.
 	Swap usage hard limit.  If a cgroup's swap usage reaches this
 	limit, anonymous memory of the cgroup will not be swapped out.
 
+  memory.swap.events
+	A read-only flat-keyed file which exists on non-root cgroups.
+	The following entries are defined.  Unless specified
+	otherwise, a value change in this file generates a file
+	modified event.
+
+	  max
+		The number of times the cgroup's swap usage was about
+		to go over the max boundary and swap allocation
+		failed.
+
+	  fail
+		The number of times swap allocation failed either
+		because of running out of swap system-wide or max
+		limit.
+
 
 Usage Guidelines
 ~~~~~~~~~~~~~~~~
diff --git a/include/linux/memcontrol.h b/include/linux/memcontrol.h
index d99b71bc2c66..517096c3cc99 100644
--- a/include/linux/memcontrol.h
+++ b/include/linux/memcontrol.h
@@ -53,6 +53,8 @@ enum memcg_memory_event {
 	MEMCG_HIGH,
 	MEMCG_MAX,
 	MEMCG_OOM,
+	MEMCG_SWAP_MAX,
+	MEMCG_SWAP_FAIL,
 	MEMCG_NR_MEMORY_EVENTS,
 };
 
@@ -208,6 +210,9 @@ struct mem_cgroup {
 	atomic_long_t memory_events[MEMCG_NR_MEMORY_EVENTS];
 	struct cgroup_file events_file;
 
+	/* handle for "memory.swap.events" */
+	struct cgroup_file swap_events_file;
+
 	/* protect arrays of thresholds */
 	struct mutex thresholds_lock;
 
diff --git a/mm/memcontrol.c b/mm/memcontrol.c
index e8166521a474..d86665cf4a49 100644
--- a/mm/memcontrol.c
+++ b/mm/memcontrol.c
@@ -6012,13 +6012,17 @@ int mem_cgroup_try_charge_swap(struct page *page, swp_entry_t entry)
 	if (!memcg)
 		return 0;
 
-	if (!entry.val)
+	if (!entry.val) {
+		memcg_memory_event(memcg, MEMCG_SWAP_FAIL);
 		return 0;
+	}
 
 	memcg = mem_cgroup_id_get_online(memcg);
 
 	if (!mem_cgroup_is_root(memcg) &&
 	    !page_counter_try_charge(&memcg->swap, nr_pages, &counter)) {
+		memcg_memory_event(memcg, MEMCG_SWAP_MAX);
+		memcg_memory_event(memcg, MEMCG_SWAP_FAIL);
 		mem_cgroup_id_put(memcg);
 		return -ENOMEM;
 	}
@@ -6156,6 +6160,18 @@ static ssize_t swap_max_write(struct kernfs_open_file *of,
 	return nbytes;
 }
 
+static int swap_events_show(struct seq_file *m, void *v)
+{
+	struct mem_cgroup *memcg = mem_cgroup_from_css(seq_css(m));
+
+	seq_printf(m, "max %lu\n",
+		   atomic_long_read(&memcg->memory_events[MEMCG_SWAP_MAX]));
+	seq_printf(m, "fail %lu\n",
+		   atomic_long_read(&memcg->memory_events[MEMCG_SWAP_FAIL]));
+
+	return 0;
+}
+
 static struct cftype swap_files[] = {
 	{
 		.name = "swap.current",
@@ -6168,6 +6184,12 @@ static struct cftype swap_files[] = {
 		.seq_show = swap_max_show,
 		.write = swap_max_write,
 	},
+	{
+		.name = "swap.events",
+		.flags = CFTYPE_NOT_ON_ROOT,
+		.file_offset = offsetof(struct mem_cgroup, swap_events_file),
+		.seq_show = swap_events_show,
+	},
 	{ }	/* terminate */
 };