linux-kernel - [RFC 35/60] cosched: Adjust rq_lock() functions to work with hierarchical runqueues

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:   Fri,  7 Sep 2018 23:40:22 +0200
From:   Jan H. Schönherr <jschoenh@...zon.de>
To:     Ingo Molnar <mingo@...hat.com>,
        Peter Zijlstra <peterz@...radead.org>
Cc:     Jan H. Schönherr <jschoenh@...zon.de>,
        linux-kernel@...r.kernel.org
Subject: [RFC 35/60] cosched: Adjust rq_lock() functions to work with hierarchical runqueues

Locks within the runqueue hierarchy are always taken from bottom to top
to avoid deadlocks. Let the lock validator know about this by declaring
different runqueue levels as distinct lock classes.

Signed-off-by: Jan H. Schönherr <jschoenh@...zon.de>
---
 kernel/sched/sched.h | 29 ++++++++++++++++++++++++++---
 1 file changed, 26 insertions(+), 3 deletions(-)

diff --git a/kernel/sched/sched.h b/kernel/sched/sched.h
index 594eb9489f3d..bc3631b8b955 100644
--- a/kernel/sched/sched.h
+++ b/kernel/sched/sched.h
@@ -2083,11 +2083,26 @@ task_rq_unlock(struct rq *rq, struct task_struct *p, struct rq_flags *rf)
 	raw_spin_unlock_irqrestore(&p->pi_lock, rf->flags);
 }
 
+#ifdef CONFIG_COSCHEDULING
+/*
+ * The hierarchical runqueues have locks which are taken from bottom to
+ * top. For lock validation, we use the level to calculate the subclass.
+ * As it is sometimes necessary to take two locks on the same level, we
+ * leave some space in the subclass values for that purpose.
+ */
+#define RQ_LOCK_SUBCLASS(rq)		(2 * (rq)->sdrq_data.level)
+#define RQ_LOCK_SUBCLASS_NESTED(rq)	(2 * (rq)->sdrq_data.level + 1)
+#else
+#define RQ_LOCK_SUBCLASS(rq)		0
+#define RQ_LOCK_SUBCLASS_NESTED(rq)	SINGLE_DEPTH_NESTING
+#endif
+
 static inline void
 rq_lock_irqsave(struct rq *rq, struct rq_flags *rf)
 	__acquires(rq->lock)
 {
-	raw_spin_lock_irqsave(&rq->lock, rf->flags);
+	raw_spin_lock_irqsave_nested(&rq->lock, rf->flags,
+				     RQ_LOCK_SUBCLASS(rq));
 	rq_pin_lock(rq, rf);
 }
 
@@ -2095,6 +2110,14 @@ static inline void
 rq_lock_irq(struct rq *rq, struct rq_flags *rf)
 	__acquires(rq->lock)
 {
+	/*
+	 * There's no raw_spin_lock_irq_nested(). This is probably fine, as at
+	 * most the first lock should be acquired this way. There might be some
+	 * false negatives, though, if we start with a non-bottom lock and
+	 * classify it incorrectly.
+	 */
+	SCHED_WARN_ON(RQ_LOCK_SUBCLASS(rq));
+
 	raw_spin_lock_irq(&rq->lock);
 	rq_pin_lock(rq, rf);
 }
@@ -2103,7 +2126,7 @@ static inline void
 rq_lock(struct rq *rq, struct rq_flags *rf)
 	__acquires(rq->lock)
 {
-	raw_spin_lock(&rq->lock);
+	raw_spin_lock_nested(&rq->lock, RQ_LOCK_SUBCLASS(rq));
 	rq_pin_lock(rq, rf);
 }
 
@@ -2111,7 +2134,7 @@ static inline void
 rq_relock(struct rq *rq, struct rq_flags *rf)
 	__acquires(rq->lock)
 {
-	raw_spin_lock(&rq->lock);
+	raw_spin_lock_nested(&rq->lock, RQ_LOCK_SUBCLASS(rq));
 	rq_repin_lock(rq, rf);
 }
 
-- 
2.9.3.1.gcba166c.dirty