linux-kernel - [GIT PULL] scheduler fix

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]

Message-ID: <20181231145827.GA83750@gmail.com>
Date:   Mon, 31 Dec 2018 15:58:27 +0100
From:   Ingo Molnar <mingo@...nel.org>
To:     Linus Torvalds <torvalds@...ux-foundation.org>
Cc:     linux-kernel@...r.kernel.org,
        Peter Zijlstra <a.p.zijlstra@...llo.nl>,
        Vincent Guittot <vincent.guittot@...aro.org>,
        Thomas Gleixner <tglx@...utronix.de>,
        Andrew Morton <akpm@...ux-foundation.org>,
        Tejun Heo <tj@...nel.org>
Subject: [GIT PULL] scheduler fix

Linus,

Please pull the latest sched-urgent-for-linus git tree from:

   git://git.kernel.org/pub/scm/linux/kernel/git/tip/tip.git sched-urgent-for-linus

   # HEAD: c40f7d74c741a907cfaeb73a7697081881c497d0 sched/fair: Fix infinite loop in update_blocked_averages() by reverting a9e7f6544b9c

This is a revert for a lockup in cgroups-intense workloads - the real 
fixes will come later.

Happy new year,

	Ingo

------------------>
Linus Torvalds (1):
      sched/fair: Fix infinite loop in update_blocked_averages() by reverting a9e7f6544b9c


 kernel/sched/fair.c | 43 +++++++++----------------------------------
 1 file changed, 9 insertions(+), 34 deletions(-)

diff --git a/kernel/sched/fair.c b/kernel/sched/fair.c
index d1907506318a..6483834f1278 100644
--- a/kernel/sched/fair.c
+++ b/kernel/sched/fair.c
@@ -352,10 +352,9 @@ static inline void list_del_leaf_cfs_rq(struct cfs_rq *cfs_rq)
 	}
 }
 
-/* Iterate thr' all leaf cfs_rq's on a runqueue */
-#define for_each_leaf_cfs_rq_safe(rq, cfs_rq, pos)			\
-	list_for_each_entry_safe(cfs_rq, pos, &rq->leaf_cfs_rq_list,	\
-				 leaf_cfs_rq_list)
+/* Iterate through all leaf cfs_rq's on a runqueue: */
+#define for_each_leaf_cfs_rq(rq, cfs_rq) \
+	list_for_each_entry_rcu(cfs_rq, &rq->leaf_cfs_rq_list, leaf_cfs_rq_list)
 
 /* Do the two (enqueued) entities belong to the same group ? */
 static inline struct cfs_rq *
@@ -447,8 +446,8 @@ static inline void list_del_leaf_cfs_rq(struct cfs_rq *cfs_rq)
 {
 }
 
-#define for_each_leaf_cfs_rq_safe(rq, cfs_rq, pos)	\
-		for (cfs_rq = &rq->cfs, pos = NULL; cfs_rq; cfs_rq = pos)
+#define for_each_leaf_cfs_rq(rq, cfs_rq)	\
+		for (cfs_rq = &rq->cfs; cfs_rq; cfs_rq = NULL)
 
 static inline struct sched_entity *parent_entity(struct sched_entity *se)
 {
@@ -7647,27 +7646,10 @@ static inline bool others_have_blocked(struct rq *rq)
 
 #ifdef CONFIG_FAIR_GROUP_SCHED
 
-static inline bool cfs_rq_is_decayed(struct cfs_rq *cfs_rq)
-{
-	if (cfs_rq->load.weight)
-		return false;
-
-	if (cfs_rq->avg.load_sum)
-		return false;
-
-	if (cfs_rq->avg.util_sum)
-		return false;
-
-	if (cfs_rq->avg.runnable_load_sum)
-		return false;
-
-	return true;
-}
-
 static void update_blocked_averages(int cpu)
 {
 	struct rq *rq = cpu_rq(cpu);
-	struct cfs_rq *cfs_rq, *pos;
+	struct cfs_rq *cfs_rq;
 	const struct sched_class *curr_class;
 	struct rq_flags rf;
 	bool done = true;
@@ -7679,7 +7661,7 @@ static void update_blocked_averages(int cpu)
 	 * Iterates the task_group tree in a bottom up fashion, see
 	 * list_add_leaf_cfs_rq() for details.
 	 */
-	for_each_leaf_cfs_rq_safe(rq, cfs_rq, pos) {
+	for_each_leaf_cfs_rq(rq, cfs_rq) {
 		struct sched_entity *se;
 
 		/* throttled entities do not contribute to load */
@@ -7694,13 +7676,6 @@ static void update_blocked_averages(int cpu)
 		if (se && !skip_blocked_update(se))
 			update_load_avg(cfs_rq_of(se), se, 0);
 
-		/*
-		 * There can be a lot of idle CPU cgroups.  Don't let fully
-		 * decayed cfs_rqs linger on the list.
-		 */
-		if (cfs_rq_is_decayed(cfs_rq))
-			list_del_leaf_cfs_rq(cfs_rq);
-
 		/* Don't need periodic decay once load/util_avg are null */
 		if (cfs_rq_has_blocked(cfs_rq))
 			done = false;
@@ -10570,10 +10545,10 @@ const struct sched_class fair_sched_class = {
 #ifdef CONFIG_SCHED_DEBUG
 void print_cfs_stats(struct seq_file *m, int cpu)
 {
-	struct cfs_rq *cfs_rq, *pos;
+	struct cfs_rq *cfs_rq;
 
 	rcu_read_lock();
-	for_each_leaf_cfs_rq_safe(cpu_rq(cpu), cfs_rq, pos)
+	for_each_leaf_cfs_rq(cpu_rq(cpu), cfs_rq)
 		print_cfs_rq(m, cpu, cfs_rq);
 	rcu_read_unlock();
 }