linux-kernel - Re: [External] Re: [PATCH] sched/core: Avoid obvious double update_rq

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]

Message-ID: <df0c4d87-68be-7aef-597f-043b3c7fea59@arm.com>
Date:   Wed, 20 Apr 2022 21:11:58 +0200
From:   Dietmar Eggemann <dietmar.eggemann@....com>
To:     Hao Jia <jiahao.os@...edance.com>,
        Peter Zijlstra <peterz@...radead.org>
Cc:     mingo@...hat.com, juri.lelli@...hat.com,
        vincent.guittot@...aro.org, rostedt@...dmis.org,
        bsegall@...gle.com, mgorman@...e.de, bristot@...hat.com,
        linux-kernel@...r.kernel.org
Subject: Re: [External] Re: [PATCH] sched/core: Avoid obvious double
 update_rq_clock warning

On 20/04/2022 10:29, Hao Jia wrote:
> On 4/19/22 6:48 PM, Peter Zijlstra wrote:
>> On Mon, Apr 18, 2022 at 05:09:29PM +0800, Hao Jia wrote:

[...]

>> I'm really not sure about this part though. This is a bit of a mess. The
>> balancer doesn't really need the pinning stuff. I realize you did that
>> because we got the clock annotation mixed up with that, but urgh.
>>
>> Basically we want double_rq_lock() / double_lock_balance() to clear
>> RQCF_UPDATED, right? Perhaps do that directly?
>>
>> (maybe with an inline helper and a wee comment?)
>>
>> The only immediate problem with this would appear to be that
>> _double_rq_lock() behaves differently when it returns 0. Not sure that
>> matters.
>>
>> Hmm?
> 
> Thanks for your review comments.
> As you have prompted, the WARN_DOUBLE_CLOCK warning is still triggered
> when _double_rq_lock() returns 0.
> Please review the solution below, and based on your review, I will
> submit the v2 patch as soon as possible.
> Thanks.


[...]

Maybe something like this:

-->8--

From: Dietmar Eggemann <dietmar.eggemann@....com>
Date: Wed, 20 Apr 2022 11:12:10 +0200
Subject: [PATCH] sched/core: Clear RQCF_UPDATED in _double_lock_balance() &
 double_rq_lock()

Signed-off-by: Dietmar Eggemann <dietmar.eggemann@....com>
---
 kernel/sched/core.c  |  6 +++---
 kernel/sched/sched.h | 20 ++++++++++++++++----
 2 files changed, 19 insertions(+), 7 deletions(-)

diff --git a/kernel/sched/core.c b/kernel/sched/core.c
index 068c088e9584..f4cfe7eea861 100644
--- a/kernel/sched/core.c
+++ b/kernel/sched/core.c
@@ -610,10 +610,10 @@ void double_rq_lock(struct rq *rq1, struct rq *rq2)
 		swap(rq1, rq2);
 
 	raw_spin_rq_lock(rq1);
-	if (__rq_lockp(rq1) == __rq_lockp(rq2))
-		return;
+	if (__rq_lockp(rq1) != __rq_lockp(rq2))
+		raw_spin_rq_lock_nested(rq2, SINGLE_DEPTH_NESTING);
 
-	raw_spin_rq_lock_nested(rq2, SINGLE_DEPTH_NESTING);
+	rq_clock_clear_update(rq1, rq2);
 }
 #endif
 
diff --git a/kernel/sched/sched.h b/kernel/sched/sched.h
index 58263f90c559..3a77b10d7cc4 100644
--- a/kernel/sched/sched.h
+++ b/kernel/sched/sched.h
@@ -2515,6 +2515,16 @@ static inline bool rq_order_less(struct rq *rq1, struct rq *rq2)
 
 extern void double_rq_lock(struct rq *rq1, struct rq *rq2);
 
+#ifdef CONFIG_SCHED_DEBUG
+static inline void rq_clock_clear_update(struct rq *rq1, struct rq *rq2)
+{
+	rq1->clock_update_flags &= (RQCF_REQ_SKIP|RQCF_ACT_SKIP);
+	rq2->clock_update_flags &= (RQCF_REQ_SKIP|RQCF_ACT_SKIP);
+}
+#else
+static inline void rq_clock_clear_update(struct rq *rq1, struct rq *rq2) {}
+#endif
+
 #ifdef CONFIG_PREEMPTION
 
 /*
@@ -2549,14 +2559,15 @@ static inline int _double_lock_balance(struct rq *this_rq, struct rq *busiest)
 	__acquires(busiest->lock)
 	__acquires(this_rq->lock)
 {
-	if (__rq_lockp(this_rq) == __rq_lockp(busiest))
-		return 0;
-
-	if (likely(raw_spin_rq_trylock(busiest)))
+	if (__rq_lockp(this_rq) == __rq_lockp(busiest) ||
+	    likely(raw_spin_rq_trylock(busiest))) {
+		rq_clock_clear_update(this_rq, busiest);
 		return 0;
+	}
 
 	if (rq_order_less(this_rq, busiest)) {
 		raw_spin_rq_lock_nested(busiest, SINGLE_DEPTH_NESTING);
+		rq_clock_clear_update(this_rq, busiest);
 		return 0;
 	}
 
@@ -2650,6 +2661,7 @@ static inline void double_rq_lock(struct rq *rq1, struct rq *rq2)
 	BUG_ON(rq1 != rq2);
 	raw_spin_rq_lock(rq1);
 	__acquire(rq2->lock);	/* Fake it out ;) */
+	rq_clock_clear_update(rq1, rq2);
 }
 
 /*
-- 
2.25.1