From:   Huangzhaoyang <huangzhaoyang@gmail.com>
To:     Johannes Weiner <hannes@cmpxchg.org>,
        Suren Baghdasaryan <surenb@google.com>,
        Zhaoyang Huang <zhaoyang.huang@unisoc.com>, linux-mm@kvack.org,
        linux-kernel@vger.kernel.org
Subject: [PATCH v2] psi: fix possible trigger missing in the window
Date:   Tue, 21 Dec 2021 16:33:57 +0800
Message-Id: <1640075637-14520-1-git-send-email-huangzhaoyang@gmail.com>
Precedence: bulk

From: Zhaoyang Huang <zhaoyang.huang@unisoc.com>

There could be missing wake up if the rest of the window remain the
same stall states as the polling_total updates for every polling_min_period.
Introducing threshold_breach flag to record the trigger's status and update
the logic.

Suggested-by: Suren Baghdasaryan <surenb@google.com>
Signed-off-by: Zhaoyang Huang <zhaoyang.huang@unisoc.com>
---
v2: modify the logic according to Suren's suggestion
---
---
 include/linux/psi_types.h |  2 ++
 kernel/sched/psi.c        | 38 +++++++++++++++++++++++---------------
 2 files changed, 25 insertions(+), 15 deletions(-)

diff --git a/include/linux/psi_types.h b/include/linux/psi_types.h
index 0a23300..87b694a 100644
--- a/include/linux/psi_types.h
+++ b/include/linux/psi_types.h
@@ -132,6 +132,8 @@ struct psi_trigger {
 
 	/* Refcounting to prevent premature destruction */
 	struct kref refcount;
+
+	bool threshold_breach;
 };
 
 struct psi_group {
diff --git a/kernel/sched/psi.c b/kernel/sched/psi.c
index 1652f2b..5c67ab9 100644
--- a/kernel/sched/psi.c
+++ b/kernel/sched/psi.c
@@ -524,24 +524,29 @@ static u64 update_triggers(struct psi_group *group, u64 now)
 	 */
 	list_for_each_entry(t, &group->triggers, node) {
 		u64 growth;
+		bool trigger_stalled =
+			group->polling_total[t->state] != total[t->state];
 
-		/* Check for stall activity */
-		if (group->polling_total[t->state] == total[t->state])
-			continue;
-
-		/*
-		 * Multiple triggers might be looking at the same state,
-		 * remember to update group->polling_total[] once we've
-		 * been through all of them. Also remember to extend the
-		 * polling time if we see new stall activity.
-		 */
-		new_stall = true;
-
-		/* Calculate growth since last update */
-		growth = window_update(&t->win, now, total[t->state]);
-		if (growth < t->threshold)
+		/* Check for stall activity or a previous threshold breach */
+		if (!trigger_stalled && !t->threshold_breach)
 			continue;
 
+		if (trigger_stalled) {
+			/*
+			 * Multiple triggers might be looking at the same state,
+			 * remember to update group->polling_total[] once we've
+			 * been through all of them. Also remember to extend the
+			 * polling time if we see new stall activity.
+			 */
+			new_stall = true;
+
+			/* Calculate growth since last update */
+			growth = window_update(&t->win, now, total[t->state]);
+			if (growth < t->threshold)
+				continue;
+
+			t->threshold_breach = true;
+		}
 		/* Limit event signaling to once per window */
 		if (now < t->last_event_time + t->win.size)
 			continue;
@@ -550,6 +555,8 @@ static u64 update_triggers(struct psi_group *group, u64 now)
 		if (cmpxchg(&t->event, 0, 1) == 0)
 			wake_up_interruptible(&t->event_wait);
 		t->last_event_time = now;
+		/* Reset threshold breach flag once event got generated */
+		t->threshold_breach = false;
 	}
 
 	if (new_stall)
@@ -1152,6 +1159,7 @@ struct psi_trigger *psi_trigger_create(struct psi_group *group,
 	t->last_event_time = 0;
 	init_waitqueue_head(&t->event_wait);
 	kref_init(&t->refcount);
+	t->threshold_breach = false;
 
 	mutex_lock(&group->trigger_lock);
 
-- 
1.9.1