Received-SPF: pass (google.com: domain of linux-kernel-owner@vger.kernel.org designates 2620:137:e000::1:20 as permitted sender) client-ip=2620:137:e000::1:20;
Message-ID: <c7cae935-c378-24bf-7e9c-bbf5feb4185a@redhat.com>
Date:   Tue, 17 Jan 2023 14:40:22 -0500
MIME-Version: 1.0
User-Agent: Mozilla/5.0 (X11; Linux x86_64; rv:102.0) Gecko/20100101
 Thunderbird/102.4.0
Subject: Re: [PATCH] rtmutex: ensure we wake up the top waiter
Content-Language: en-US
From:   Waiman Long <longman@redhat.com>
To:     Wander Lairson Costa <wander@redhat.com>,
        Peter Zijlstra <peterz@infradead.org>,
        Ingo Molnar <mingo@redhat.com>, Will Deacon <will@kernel.org>,
        Boqun Feng <boqun.feng@gmail.com>,
        "open list:LOCKING PRIMITIVES" <linux-kernel@vger.kernel.org>
Cc:     Thomas Gleixner <tglx@linutronix.de>,
        Sebastian Andrzej Siewior <bigeasy@linutronix.de>
References: <20230117172649.52465-1-wander@redhat.com>
 <23a15414-927c-ba0d-eb6a-58f6191ce17b@redhat.com>
In-Reply-To: <23a15414-927c-ba0d-eb6a-58f6191ce17b@redhat.com>
Content-Type: text/plain; charset=UTF-8; format=flowed
Content-Transfer-Encoding: 8bit
Precedence: bulk

On 1/17/23 14:32, Waiman Long wrote:
> On 1/17/23 12:26, Wander Lairson Costa wrote:
>> In task_blocked_on_lock() we save the owner, release the wait_lock and
>> call rt_mutex_adjust_prio_chain(). Before we acquire the wait_lock
>> again, the owner may release the lock and deboost.
> Are you referring to task_blocks_on_rt_mutex(), not 
> task_blocked_on_lock()?
>>
>> rt_mutex_adjust_prio_chain() acquires the wait_lock. In the requeue
>> phase, waiter may be initially in the top of the queue, but after
>> dequeued and requeued it may no longer be true.
>>
>> This scenario ends up waking the wrong task, which will verify it is no
>> the top waiter and comes back to sleep. Now we have a situation in which
>> no task is holding the lock but no one acquires it.
>>
>> We can reproduce the bug in PREEMPT_RT with stress-ng:
>>
>> while true; do
>>      stress-ng --sched deadline --sched-period 1000000000 \
>>              --sched-runtime 800000000 --sched-deadline \
>>              1000000000 --mmapfork 23 -t 20
>> done
>>
>> Signed-off-by: Wander Lairson Costa <wander@redhat.com>
>> ---
>>   kernel/locking/rtmutex.c | 5 +++--
>>   1 file changed, 3 insertions(+), 2 deletions(-)
>>
>> diff --git a/kernel/locking/rtmutex.c b/kernel/locking/rtmutex.c
>> index 010cf4e6d0b8..728f434de2bb 100644
>> --- a/kernel/locking/rtmutex.c
>> +++ b/kernel/locking/rtmutex.c
>> @@ -901,8 +901,9 @@ static int __sched 
>> rt_mutex_adjust_prio_chain(struct task_struct *task,
>>            * then we need to wake the new top waiter up to try
>>            * to get the lock.
>>            */
>> -        if (prerequeue_top_waiter != rt_mutex_top_waiter(lock))
>> -            wake_up_state(waiter->task, waiter->wake_state);
>> +        top_waiter = rt_mutex_top_waiter(lock);
>> +        if (prerequeue_top_waiter != top_waiter)
>> +            wake_up_state(top_waiter->task, top_waiter->wake_state);
>>           raw_spin_unlock_irq(&lock->wait_lock);
>>           return 0;
>>       }
>
> I would say that if a rt_mutex has no owner but have waiters, we 
> should always wake up the top waiter whether or not it is the current 
> waiter. So what is the result of the stress-ng run above? Is it a 
> hang? It is not clear from your patch description.

BTW, if it is a hang. What arch has this problem? x86 or arm64? There is 
a recent report of some rt_mutex locking issue in arm64, I believe. I 
don't know if it will be related. So it is important to know in what 
arch you see this problem.

Cheers,
Longman