linux-kernel - [tip:sched/core] sched: Fix load corruption from update_cfs

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

Date:	Thu, 18 Nov 2010 14:11:16 GMT
From:	tip-bot for Paul Turner <pjt@...gle.com>
To:	linux-tip-commits@...r.kernel.org
Cc:	linux-kernel@...r.kernel.org, hpa@...or.com, mingo@...hat.com,
	a.p.zijlstra@...llo.nl, pjt@...gle.com, tglx@...utronix.de,
	mingo@...e.hu
Subject: [tip:sched/core] sched: Fix load corruption from update_cfs_shares()

Commit-ID:  f0d7442a5924a802b66eef79b3708f77297bfb35
Gitweb:     http://git.kernel.org/tip/f0d7442a5924a802b66eef79b3708f77297bfb35
Author:     Paul Turner <pjt@...gle.com>
AuthorDate: Mon, 15 Nov 2010 15:47:03 -0800
Committer:  Ingo Molnar <mingo@...e.hu>
CommitDate: Thu, 18 Nov 2010 13:27:47 +0100

sched: Fix load corruption from update_cfs_shares()

As part of enqueue_entity both a new entity weight and its contribution to the
queuing cfs_rq / rq are updated.  Since update_cfs_shares will only update the
queueing weights when the entity is on_rq (which in this case it is not yet),
there's a dependency loop here:

update_cfs_shares needs account_entity_enqueue to update cfs_rq->load.weight
account_entity_enqueue needs the updated weight for the queuing cfs_rq load[*]

Fix this and avoid spurious dequeue/enqueues by issuing update_cfs_shares as
if we had accounted the enqueue already.

This was also resulting in rq->load corruption previously.

[*]: this dependency also exists when using the group cfs_rq w/
     update_cfs_shares as the weight of the enqueued entity changes
     without the load being updated.

Signed-off-by: Paul Turner <pjt@...gle.com>
Signed-off-by: Peter Zijlstra <a.p.zijlstra@...llo.nl>
LKML-Reference: <20101115234937.844900206@...gle.com>
Signed-off-by: Ingo Molnar <mingo@...e.hu>
---
 kernel/sched_fair.c |   16 ++++++++--------
 1 files changed, 8 insertions(+), 8 deletions(-)

diff --git a/kernel/sched_fair.c b/kernel/sched_fair.c
index 46ff658..d52b97a 100644
--- a/kernel/sched_fair.c
+++ b/kernel/sched_fair.c
@@ -718,7 +718,7 @@ static void reweight_entity(struct cfs_rq *cfs_rq, struct sched_entity *se,
 		account_entity_enqueue(cfs_rq, se);
 }
 
-static void update_cfs_shares(struct cfs_rq *cfs_rq)
+static void update_cfs_shares(struct cfs_rq *cfs_rq, long weight_delta)
 {
 	struct task_group *tg;
 	struct sched_entity *se;
@@ -732,7 +732,7 @@ static void update_cfs_shares(struct cfs_rq *cfs_rq)
 	if (!se)
 		return;
 
-	load = cfs_rq->load.weight;
+	load = cfs_rq->load.weight + weight_delta;
 
 	load_weight = atomic_read(&tg->load_weight);
 	load_weight -= cfs_rq->load_contribution;
@@ -754,7 +754,7 @@ static inline void update_cfs_load(struct cfs_rq *cfs_rq, int lb)
 {
 }
 
-static inline void update_cfs_shares(struct cfs_rq *cfs_rq)
+static inline void update_cfs_shares(struct cfs_rq *cfs_rq, long weight_delta)
 {
 }
 #endif /* CONFIG_FAIR_GROUP_SCHED */
@@ -881,8 +881,8 @@ enqueue_entity(struct cfs_rq *cfs_rq, struct sched_entity *se, int flags)
 	 */
 	update_curr(cfs_rq);
 	update_cfs_load(cfs_rq, 0);
+	update_cfs_shares(cfs_rq, se->load.weight);
 	account_entity_enqueue(cfs_rq, se);
-	update_cfs_shares(cfs_rq);
 
 	if (flags & ENQUEUE_WAKEUP) {
 		place_entity(cfs_rq, se, 0);
@@ -944,7 +944,7 @@ dequeue_entity(struct cfs_rq *cfs_rq, struct sched_entity *se, int flags)
 	update_cfs_load(cfs_rq, 0);
 	account_entity_dequeue(cfs_rq, se);
 	update_min_vruntime(cfs_rq);
-	update_cfs_shares(cfs_rq);
+	update_cfs_shares(cfs_rq, 0);
 
 	/*
 	 * Normalize the entity after updating the min_vruntime because the
@@ -1177,7 +1177,7 @@ enqueue_task_fair(struct rq *rq, struct task_struct *p, int flags)
 		struct cfs_rq *cfs_rq = cfs_rq_of(se);
 
 		update_cfs_load(cfs_rq, 0);
-		update_cfs_shares(cfs_rq);
+		update_cfs_shares(cfs_rq, 0);
 	}
 
 	hrtick_update(rq);
@@ -1207,7 +1207,7 @@ static void dequeue_task_fair(struct rq *rq, struct task_struct *p, int flags)
 		struct cfs_rq *cfs_rq = cfs_rq_of(se);
 
 		update_cfs_load(cfs_rq, 0);
-		update_cfs_shares(cfs_rq);
+		update_cfs_shares(cfs_rq, 0);
 	}
 
 	hrtick_update(rq);
@@ -2034,7 +2034,7 @@ static int tg_shares_up(struct task_group *tg, int cpu)
 	 * We need to update shares after updating tg->load_weight in
 	 * order to adjust the weight of groups with long running tasks.
 	 */
-	update_cfs_shares(cfs_rq);
+	update_cfs_shares(cfs_rq, 0);
 
 	raw_spin_unlock_irqrestore(&rq->lock, flags);
 
--
To unsubscribe from this list: send the line "unsubscribe linux-kernel" in
the body of a message to majordomo@...r.kernel.org
More majordomo info at  http://vger.kernel.org/majordomo-info.html
Please read the FAQ at  http://www.tux.org/lkml/