linux-kernel - [PATCH v2] sched/fair: Sanity check 'best' in pick

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>] [day] [month] [year] [list]

Date: Wed, 31 Jan 2024 20:03:40 +0800
From: "Tiwei Bie" <tiwei.btw@...group.com>
To: peterz@...radead.org,
	mingo@...hat.com,
	wuyun.abel@...edance.com
Cc: "Tiwei Bie" <tiwei.btw@...group.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>
Subject: [PATCH v2] sched/fair: Sanity check 'best' in pick_eevdf()

Before commit 2227a957e1d5 ("sched/eevdf: Sort the rbtree by virtual
deadline"), there was a sanity check to catch unexpected failures in the
EEVDF scheduling, which was helpful in identifying problems. It would
be better to restore its previous capability.

Signed-off-by: Tiwei Bie <tiwei.btw@...group.com>
---
Refer:
https://lore.kernel.org/lkml/23cbb613-c8a2-4f07-b83b-fa3104bef642@bytedance.com/

v1 -> v2:
- improve commit log and error message;

 kernel/sched/fair.c | 19 +++++++++++++++----
 1 file changed, 15 insertions(+), 4 deletions(-)

diff --git a/kernel/sched/fair.c b/kernel/sched/fair.c
index 533547e3c90a..aeb3b8fee641 100644
--- a/kernel/sched/fair.c
+++ b/kernel/sched/fair.c
@@ -878,7 +878,7 @@ struct sched_entity *__pick_first_entity(struct cfs_rq *cfs_rq)
 static struct sched_entity *pick_eevdf(struct cfs_rq *cfs_rq)
 {
 	struct rb_node *node = cfs_rq->tasks_timeline.rb_root.rb_node;
-	struct sched_entity *se = __pick_first_entity(cfs_rq);
+	struct sched_entity *first = __pick_first_entity(cfs_rq);
 	struct sched_entity *curr = cfs_rq->curr;
 	struct sched_entity *best = NULL;
 
@@ -887,7 +887,7 @@ static struct sched_entity *pick_eevdf(struct cfs_rq *cfs_rq)
 	 * in this cfs_rq, saving some cycles.
 	 */
 	if (cfs_rq->nr_running == 1)
-		return curr && curr->on_rq ? curr : se;
+		return curr && curr->on_rq ? curr : first;
 
 	if (curr && (!curr->on_rq || !entity_eligible(cfs_rq, curr)))
 		curr = NULL;
@@ -900,14 +900,15 @@ static struct sched_entity *pick_eevdf(struct cfs_rq *cfs_rq)
 		return curr;
 
 	/* Pick the leftmost entity if it's eligible */
-	if (se && entity_eligible(cfs_rq, se)) {
-		best = se;
+	if (first && entity_eligible(cfs_rq, first)) {
+		best = first;
 		goto found;
 	}
 
 	/* Heap search for the EEVD entity */
 	while (node) {
 		struct rb_node *left = node->rb_left;
+		struct sched_entity *se;
 
 		/*
 		 * Eligible entities in left subtree are always better
@@ -937,6 +938,16 @@ static struct sched_entity *pick_eevdf(struct cfs_rq *cfs_rq)
 	if (!best || (curr && entity_before(curr, best)))
 		best = curr;
 
+	/* This is not expected to happen. */
+	if (unlikely(!best)) {
+		if (printk_ratelimit()) {
+			printk_deferred(KERN_ERR
+				"EEVDF scheduling failed on CPU%d, picking leftmost\n",
+				cpu_of(rq_of(cfs_rq)));
+		}
+		best = first;
+	}
+
 	return best;
 }
 
-- 
2.34.1