linux-kernel - [PATCH] sched: fix throttle accounting with nested bandwidth limits

lists.openwall.net		lists / announce owl-users owl-dev john-users john-dev passwdqc-users yescrypt popa3d-users / oss-security kernel-hardening musl sabotage tlsify passwords / crypt-dev xvendor / Bugtraq Full-Disclosure linux-kernel linux-netdev linux-ext4 linux-hardening linux-cve-announce PHC
Open Source and information security mailing list archives

Hash Suite: Windows password security audit tool. GUI, reports in PDF.

[<prev] [next>] [thread-next>] [day] [month] [year] [list]

Date:   Thu, 15 Jun 2023 13:12:52 -0700
From:   Josh Don <joshdon@...gle.com>
To:     Peter Zijlstra <peterz@...radead.org>
Cc:     Ingo Molnar <mingo@...hat.com>, Juri Lelli <juri.lelli@...hat.com>,
        Vincent Guittot <vincent.guittot@...aro.org>,
        Dietmar Eggemann <dietmar.eggemann@....com>,
        Steven Rostedt <rostedt@...dmis.org>,
        Ben Segall <bsegall@...gle.com>, Mel Gorman <mgorman@...e.de>,
        Daniel Bristot de Oliveira <bristot@...hat.com>,
        Valentin Schneider <vschneid@...hat.com>,
        linux-kernel@...r.kernel.org, Josh Don <joshdon@...gle.com>
Subject: [PATCH] sched: fix throttle accounting with nested bandwidth limits

This fixes two issues:
- throttled_clock should only be set on the group that is actually
  getting throttled
- self-throttled time should only be accounted on entry/exit to
  throttled state when we have nested limits

Fixes: 88cb2868250c ("sched: add throttled time stat for throttled children")
Fixes: 3ab150d011da ("sched: don't account throttle time for empty groups")
Signed-off-by: Josh Don <joshdon@...gle.com>
---
 kernel/sched/fair.c | 25 +++++++++++++------------
 1 file changed, 13 insertions(+), 12 deletions(-)

diff --git a/kernel/sched/fair.c b/kernel/sched/fair.c
index 0219cf870cef..a5fc825a8d70 100644
--- a/kernel/sched/fair.c
+++ b/kernel/sched/fair.c
@@ -4787,6 +4787,7 @@ place_entity(struct cfs_rq *cfs_rq, struct sched_entity *se, int initial)
 }
 
 static void check_enqueue_throttle(struct cfs_rq *cfs_rq);
+static inline int cfs_rq_throttled(struct cfs_rq *cfs_rq);
 
 static inline bool cfs_bandwidth_used(void);
 
@@ -4879,7 +4880,7 @@ enqueue_entity(struct cfs_rq *cfs_rq, struct sched_entity *se, int flags)
 #ifdef CONFIG_CFS_BANDWIDTH
 			struct rq *rq = rq_of(cfs_rq);
 
-			if (!cfs_rq->throttled_clock)
+			if (cfs_rq_throttled(cfs_rq) && !cfs_rq->throttled_clock)
 				cfs_rq->throttled_clock = rq_clock(rq);
 			if (!cfs_rq->throttled_clock_self)
 				cfs_rq->throttled_clock_self = rq_clock(rq);
@@ -5387,17 +5388,17 @@ static int tg_unthrottle_up(struct task_group *tg, void *data)
 		/* Add cfs_rq with load or one or more already running entities to the list */
 		if (!cfs_rq_is_decayed(cfs_rq))
 			list_add_leaf_cfs_rq(cfs_rq);
-	}
 
-	if (cfs_rq->throttled_clock_self) {
-		u64 delta = rq_clock(rq) - cfs_rq->throttled_clock_self;
+		if (cfs_rq->throttled_clock_self) {
+			u64 delta = rq_clock(rq) - cfs_rq->throttled_clock_self;
 
-		cfs_rq->throttled_clock_self = 0;
+			cfs_rq->throttled_clock_self = 0;
 
-		if (SCHED_WARN_ON((s64)delta < 0))
-			delta = 0;
+			if (SCHED_WARN_ON((s64)delta < 0))
+				delta = 0;
 
-		cfs_rq->throttled_clock_self_time += delta;
+			cfs_rq->throttled_clock_self_time += delta;
+		}
 	}
 
 	return 0;
@@ -5412,13 +5413,13 @@ static int tg_throttle_down(struct task_group *tg, void *data)
 	if (!cfs_rq->throttle_count) {
 		cfs_rq->throttled_clock_pelt = rq_clock_pelt(rq);
 		list_del_leaf_cfs_rq(cfs_rq);
+
+		SCHED_WARN_ON(cfs_rq->throttled_clock_self);
+		if (cfs_rq->nr_running)
+			cfs_rq->throttled_clock_self = rq_clock(rq);
 	}
 	cfs_rq->throttle_count++;
 
-	SCHED_WARN_ON(cfs_rq->throttled_clock_self);
-	if (cfs_rq->nr_running)
-		cfs_rq->throttled_clock_self = rq_clock(rq);
-
 	return 0;
 }
 
-- 
2.41.0.162.gfafddb0af9-goog