Message-ID: <0e036ff5-c0f1-96a7-cb07-222c7552201f@redhat.com>
Date:   Thu, 23 Feb 2023 09:16:33 -0500
MIME-Version: 1.0
User-Agent: Mozilla/5.0 (X11; Linux x86_64; rv:102.0) Gecko/20100101
 Thunderbird/102.6.0
Subject: Re: [PATCH v2 2/3] locking/rwsem: Enable early rwsem writer lock
 handoff
Content-Language: en-US
To:     Peter Zijlstra <peterz@infradead.org>
Cc:     Ingo Molnar <mingo@redhat.com>, Will Deacon <will@kernel.org>,
        Boqun Feng <boqun.feng@gmail.com>,
        linux-kernel@vger.kernel.org, Hillf Danton <hdanton@sina.com>
References: <20230216210933.1169097-1-longman@redhat.com>
 <20230216210933.1169097-3-longman@redhat.com>
 <Y/dc01A9+k6KuHTc@hirez.programming.kicks-ass.net>
From:   Waiman Long <longman@redhat.com>
In-Reply-To: <Y/dc01A9+k6KuHTc@hirez.programming.kicks-ass.net>
Content-Type: text/plain; charset=UTF-8; format=flowed
Content-Transfer-Encoding: 7bit
Precedence: bulk


On 2/23/23 07:32, Peter Zijlstra wrote:
> On Thu, Feb 16, 2023 at 04:09:32PM -0500, Waiman Long wrote:
>> @@ -432,19 +433,39 @@ static void rwsem_mark_wake(struct rw_semaphore *sem,
>>   		 * Mark writer at the front of the queue for wakeup.
>>   		 * Until the task is actually later awoken later by
>>   		 * the caller, other writers are able to steal it.
>> +		 *
>> +		 * *Unless* HANDOFF is set, in which case only the
>> +		 * first waiter is allowed to take it.
>> +		 *
>>   		 * Readers, on the other hand, will block as they
>>   		 * will notice the queued writer.
>>   		 */
>>   		wake_q_add(wake_q, waiter->task);
>>   		lockevent_inc(rwsem_wake_writer);
>> +
>> +		if ((count & RWSEM_LOCK_MASK) || !(count & RWSEM_FLAG_HANDOFF))
>> +			return;
>> +
>> +		/*
>> +		 * If the rwsem is free and handoff flag is set with wait_lock
>> +		 * held, no other CPUs can take an active lock. We can do an
>> +		 * early handoff.
>> +		 */
>> +		adjustment = RWSEM_WRITER_LOCKED - RWSEM_FLAG_HANDOFF;
>> +		atomic_long_set(&sem->owner, (long)waiter->task);
>> +		waiter->task = NULL;
>> +		atomic_long_add(adjustment, &sem->count);
>> +		rwsem_del_waiter(sem, waiter);
>> +		lockevent_inc(rwsem_wlock_ehandoff);
>>   	}
> *sigh*... you can't even properly copy/paste from the reader side :/
> This is broken, the moment you do waiter->task = NULL, waiter can
> dissapear from under you and that rwsem_del_waiter() is a UaF.
>
> Nor did you unify the reader and writer side and still have a giant
> trainwreck on your hands..
>
> Surely all that isn't too hard... let me post it.
>
Right, I should keep the clearing after deleting the waiter. Thanks for 
spotting that. I will review your patches soon.

Cheers,
Longman