mm, vmpressure: pass-through notification support

By default, vmpressure events are not pass-through, i.e.  they propagate
up through the memcg hierarchy until an event notifier is found for any
threshold level.

This presents a difficulty when a thread waiting on a read(2) for a
vmpressure event cannot distinguish between local memory pressure and
memory pressure in a descendant memcg, especially when that thread may
not control the memcg hierarchy.

Consider a user-controlled child memcg with a smaller limit than a
top-level memcg controlled by the "Activity Manager" specified in
Documentation/cgroup-v1/memory.txt.  It may register for memory pressure
notification for descendant memcgs to make a policy decision: oom kill a
low priority job, increase the limit, decrease other limits, etc.  If it
registers for memory pressure notification on the top-level memcg, it
currently cannot distinguish between memory pressure in its own memcg or
a descendant memcg, which is user-controlled.

Conversely, if a user registers for memory pressure notification on
their own descendant memcg, the Activity Manager does not receive any
pressure notification for that child memcg hierarchy.  Vmpressure events
are not received for ancestor memcgs if the memcg experiencing pressure
have notifiers registered, perhaps outside the knowledge of the thread
waiting on read(2) at the top level.

Both of these are consequences of vmpressure notification not being
pass-through.

This implements a pass-through behavior for vmpressure events.  When
writing to control.event_control, vmpressure event handlers may
optionally specify a mode.  There are two new modes:

 - "hierarchy": always propagate memory pressure events up the hierarchy
   regardless if descendant memcgs have their own notifiers registered,
   and

 - "local": only receive notifications when the memcg for which the
   event is registered experiences memory pressure.

Of course, processes may register for one notification of "low,local",
for example, and another for "low".

If no mode is specified, the current behavior is maintained for
backwards compatibility.

See the change to Documentation/cgroup-v1/memory.txt for full
specification.

[dan.carpenter@oracle.com: free the same pointer we allocated]
  Link: http://lkml.kernel.org/r/20170613191820.GA20003@elgon.mountain
Link: http://lkml.kernel.org/r/alpine.DEB.2.10.1705311421320.8946@chino.kir.corp.google.com
Signed-off-by: David Rientjes <rientjes@google.com>
Signed-off-by: Dan Carpenter <dan.carpenter@oracle.com>
Cc: Johannes Weiner <hannes@cmpxchg.org>
Cc: Vlastimil Babka <vbabka@suse.cz>
Cc: Minchan Kim <minchan@kernel.org>
Cc: Jonathan Corbet <corbet@lwn.net>
Cc: Anton Vorontsov <anton@enomsg.org>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>

1 files changed, 93 insertions, 29 deletions

diff --git a/mm/vmpressure.c b/mm/vmpressure.c
index ce0618b..85350ce 100644
--- a/mm/vmpressure.c
+++ b/mm/vmpressure.c
@@ -93,12 +93,25 @@ enum vmpressure_levels {
 	VMPRESSURE_NUM_LEVELS,
 };
 
+enum vmpressure_modes {
+	VMPRESSURE_NO_PASSTHROUGH = 0,
+	VMPRESSURE_HIERARCHY,
+	VMPRESSURE_LOCAL,
+	VMPRESSURE_NUM_MODES,
+};
+
 static const char * const vmpressure_str_levels[] = {
 	[VMPRESSURE_LOW] = "low",
 	[VMPRESSURE_MEDIUM] = "medium",
 	[VMPRESSURE_CRITICAL] = "critical",
 };
 
+static const char * const vmpressure_str_modes[] = {
+	[VMPRESSURE_NO_PASSTHROUGH] = "default",
+	[VMPRESSURE_HIERARCHY] = "hierarchy",
+	[VMPRESSURE_LOCAL] = "local",
+};
+
 static enum vmpressure_levels vmpressure_level(unsigned long pressure)
 {
 	if (pressure >= vmpressure_level_critical)
@@ -141,27 +154,31 @@ out:
 struct vmpressure_event {
 	struct eventfd_ctx *efd;
 	enum vmpressure_levels level;
+	enum vmpressure_modes mode;
 	struct list_head node;
 };
 
 static bool vmpressure_event(struct vmpressure *vmpr,
-			     enum vmpressure_levels level)
+			     const enum vmpressure_levels level,
+			     bool ancestor, bool signalled)
 {
 	struct vmpressure_event *ev;
-	bool signalled = false;
+	bool ret = false;
 
 	mutex_lock(&vmpr->events_lock);
-
 	list_for_each_entry(ev, &vmpr->events, node) {
-		if (level >= ev->level) {
-			eventfd_signal(ev->efd, 1);
-			signalled = true;
-		}
+		if (ancestor && ev->mode == VMPRESSURE_LOCAL)
+			continue;
+		if (signalled && ev->mode == VMPRESSURE_NO_PASSTHROUGH)
+			continue;
+		if (level < ev->level)
+			continue;
+		eventfd_signal(ev->efd, 1);
+		ret = true;
 	}
-
 	mutex_unlock(&vmpr->events_lock);
 
-	return signalled;
+	return ret;
 }
 
 static void vmpressure_work_fn(struct work_struct *work)
@@ -170,6 +187,8 @@ static void vmpressure_work_fn(struct work_struct *work)
 	unsigned long scanned;
 	unsigned long reclaimed;
 	enum vmpressure_levels level;
+	bool ancestor = false;
+	bool signalled = false;
 
 	spin_lock(&vmpr->sr_lock);
 	/*
@@ -194,12 +213,9 @@ static void vmpressure_work_fn(struct work_struct *work)
 	level = vmpressure_calc_level(scanned, reclaimed);
 
 	do {
-		if (vmpressure_event(vmpr, level))
-			break;
-		/*
-		 * If not handled, propagate the event upward into the
-		 * hierarchy.
-		 */
+		if (vmpressure_event(vmpr, level, ancestor, signalled))
+			signalled = true;
+		ancestor = true;
 	} while ((vmpr = vmpressure_parent(vmpr)));
 }
 
@@ -326,17 +342,40 @@ void vmpressure_prio(gfp_t gfp, struct mem_cgroup *memcg, int prio)
 	vmpressure(gfp, memcg, true, vmpressure_win, 0);
 }
 
+static enum vmpressure_levels str_to_level(const char *arg)
+{
+	enum vmpressure_levels level;
+
+	for (level = 0; level < VMPRESSURE_NUM_LEVELS; level++)
+		if (!strcmp(vmpressure_str_levels[level], arg))
+			return level;
+	return -1;
+}
+
+static enum vmpressure_modes str_to_mode(const char *arg)
+{
+	enum vmpressure_modes mode;
+
+	for (mode = 0; mode < VMPRESSURE_NUM_MODES; mode++)
+		if (!strcmp(vmpressure_str_modes[mode], arg))
+			return mode;
+	return -1;
+}
+
+#define MAX_VMPRESSURE_ARGS_LEN	(strlen("critical") + strlen("hierarchy") + 2)
+
 /**
  * vmpressure_register_event() - Bind vmpressure notifications to an eventfd
  * @memcg:	memcg that is interested in vmpressure notifications
  * @eventfd:	eventfd context to link notifications with
- * @args:	event arguments (used to set up a pressure level threshold)
+ * @args:	event arguments (pressure level threshold, optional mode)
  *
  * This function associates eventfd context with the vmpressure
  * infrastructure, so that the notifications will be delivered to the
- * @eventfd. The @args parameter is a string that denotes pressure level
- * threshold (one of vmpressure_str_levels, i.e. "low", "medium", or
- * "critical").
+ * @eventfd. The @args parameter is a comma-delimited string that denotes a
+ * pressure level threshold (one of vmpressure_str_levels, i.e. "low", "medium",
+ * or "critical") and an optional mode (one of vmpressure_str_modes, i.e.
+ * "hierarchy" or "local").
  *
  * To be used as memcg event method.
  */
@@ -345,28 +384,53 @@ int vmpressure_register_event(struct mem_cgroup *memcg,
 {
 	struct vmpressure *vmpr = memcg_to_vmpressure(memcg);
 	struct vmpressure_event *ev;
-	int level;
+	enum vmpressure_modes mode = VMPRESSURE_NO_PASSTHROUGH;
+	enum vmpressure_levels level = -1;
+	char *spec, *spec_orig;
+	char *token;
+	int ret = 0;
+
+	spec_orig = spec = kzalloc(MAX_VMPRESSURE_ARGS_LEN + 1, GFP_KERNEL);
+	if (!spec) {
+		ret = -ENOMEM;
+		goto out;
+	}
+	strncpy(spec, args, MAX_VMPRESSURE_ARGS_LEN);
 
-	for (level = 0; level < VMPRESSURE_NUM_LEVELS; level++) {
-		if (!strcmp(vmpressure_str_levels[level], args))
-			break;
+	/* Find required level */
+	token = strsep(&spec, ",");
+	level = str_to_level(token);
+	if (level == -1) {
+		ret = -EINVAL;
+		goto out;
 	}
 
-	if (level >= VMPRESSURE_NUM_LEVELS)
-		return -EINVAL;
+	/* Find optional mode */
+	token = strsep(&spec, ",");
+	if (token) {
+		mode = str_to_mode(token);
+		if (mode == -1) {
+			ret = -EINVAL;
+			goto out;
+		}
+	}
 
 	ev = kzalloc(sizeof(*ev), GFP_KERNEL);
-	if (!ev)
-		return -ENOMEM;
+	if (!ev) {
+		ret = -ENOMEM;
+		goto out;
+	}
 
 	ev->efd = eventfd;
 	ev->level = level;
+	ev->mode = mode;
 
 	mutex_lock(&vmpr->events_lock);
 	list_add(&ev->node, &vmpr->events);
 	mutex_unlock(&vmpr->events_lock);
-
-	return 0;
+out:
+	kfree(spec_orig);
+	return ret;
 }
 
 /**