Received-SPF: pass (google.com: domain of linux-kernel+bounces-128444-linux.lists.archive=gmail.com@vger.kernel.org designates 2604:1380:40f1:3f00::1 as permitted sender) client-ip=2604:1380:40f1:3f00::1;
Date: Tue, 2 Apr 2024 19:42:03 +0200
From: Greg KH <gregkh@linuxfoundation.org>
To: Aaro Koskinen <aaro.koskinen@iki.fi>
Cc: stable@vger.kernel.org, Waiman Long <longman@redhat.com>,
	Mukesh Ojha <quic_mojha@quicinc.com>,
	Peter Zijlstra <peterz@infradead.org>, mingo@redhat.com,
	will@kernel.org, boqun.feng@gmail.com, linux-kernel@vger.kernel.org,
	Gokul krishna Krishnakumar <quic_gokukris@quicinc.com>
Subject: Re: [PATCH v2] locking/rwsem: Disable preemption while trying for
 rwsem lock
Message-ID: <2024040242-babbling-dreamy-6336@gregkh>
References: <1662661467-24203-1-git-send-email-quic_mojha@quicinc.com>
 <20240305110402.GA72649@darkstar.musicnaut.iki.fi>
 <b92644e5-529b-4403-aba7-d316262cc8ac@redhat.com>
 <20240402173032.GC91663@darkstar.musicnaut.iki.fi>
Precedence: bulk
MIME-Version: 1.0
Content-Type: text/plain; charset=us-ascii
Content-Disposition: inline
In-Reply-To: <20240402173032.GC91663@darkstar.musicnaut.iki.fi>

On Tue, Apr 02, 2024 at 08:30:32PM +0300, Aaro Koskinen wrote:
> Stable team,
> 
> Please cherry-pick this patch into v5.15 stable:
> 
> 	locking/rwsem: Disable preemption while trying for rwsem lock
> 
> 	commit 48dfb5d2560d36fb16c7d430c229d1604ea7d185
> 
> It fixes the following bug present in v5.15:
> 
> > > > From: Gokul krishna Krishnakumar <quic_gokukris@quicinc.com>
> > > > We observe RT task is hogging CPU when trying to acquire rwsem lock
> > > > which was acquired by a kworker task but before the rwsem owner was set.
> > > > 
> > > > Here is the scenario:
> > > > 1. CFS task (affined to a particular CPU) takes rwsem lock.
> > > > 
> > > > 2. CFS task gets preempted by a RT task before setting owner.
> > > > 
> > > > 3. RT task (FIFO) is trying to acquire the lock, but spinning until
> > > > RT throttling happens for the lock as the lock was taken by CFS task.
> 
> If the RT throttling is disabled, the RT task will remain looping forever
> in the kernel. If the system is UP, it will lock up completely.
> 
> The issue can be easily reproduced by running RT task and normal task which
> are affined to the same CPU core.

Does this only affect the -rt patchset, or is this an issue with a
"clean" kernel release?

thanks,

greg k-h