[<prev] [next>] [<thread-prev] [day] [month] [year] [list]
Message-ID: <20170718113617.d4mpsmyzbhz3nr2l@hirez.programming.kicks-ass.net>
Date: Tue, 18 Jul 2017 13:36:17 +0200
From: Peter Zijlstra <peterz@...radead.org>
To: Prateek Sood <prsood@...eaurora.org>
Cc: mingo@...hat.com, sramana@...eaurora.org,
linux-kernel@...r.kernel.org
Subject: Re: [PATCH] osq_lock: avoid live-lock issue for RT task
On Fri, Jul 14, 2017 at 07:19:09PM +0530, Prateek Sood wrote:
> Live Lock due to task spinning while unqueue of CPU osq_node
> from optimistic_spin_queue. Task T1 had decremented mutex count to
> acquire the lock on CPU0. Before setting owner it got preempted.
You've been working on ancient kernels... That can no longer happen.
Please see if this is still an issue after:
3ca0ff571b09 ("locking/mutex: Rework mutex::owner")
If so, please write an up-to-date Changelog and patch (it doesn't
apply because of commit
5aff60a191e5 ("locking/osq: Break out of spin-wait busy waiting loop for a preempted vCPU in osq_lock()")
)
Powered by blists - more mailing lists