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: <c8b590a0-3535-51f1-3c7d-a67da4bcfc5e@redhat.com>
Date:   Wed, 12 Oct 2022 09:19:53 -0400
MIME-Version: 1.0
User-Agent: Mozilla/5.0 (X11; Linux x86_64; rv:91.0) Gecko/20100101
 Thunderbird/91.12.0
Subject: Re: [PATCH] locking/rwsem: Prevent non-first waiter from spinning in
 down_write() slowpath
Content-Language: en-US
To:     Hillf Danton <hdanton@sina.com>,
        Mukesh Ojha <quic_mojha@quicinc.com>
Cc:     linux-kernel@vger.kernel.org, john.p.donnelly@oracle.com,
        linux-mm@kvack.org, Peter Zijlstra <peterz@infradead.org>,
        Will Deacon <will@kernel.org>,
        Boqun Feng <boqun.feng@gmail.com>,
        Ingo Molnar <mingo@redhat.com>
References: <20221012040410.403-1-hdanton@sina.com>
From:   Waiman Long <longman@redhat.com>
In-Reply-To: <20221012040410.403-1-hdanton@sina.com>
Content-Type: text/plain; charset=UTF-8; format=flowed
Content-Transfer-Encoding: 7bit
Precedence: bulk

On 10/12/22 00:04, Hillf Danton wrote:
>> you mean, you want to check and change waiter->handoff_set on every run
>> rwsem_try_write_lock().
>>
> Yes, with RWSEM_FLAG_HANDOFF set, it is too late for non first waiters to
> spin, and with both RWSEM_LOCK_MASK and RWSEM_FLAG_HANDOFF set, the rivals
> in the RWSEM_LOCK_MASK have an uphand over the first waiter wrt acquiring
> the lock, and it is not a bad option for the first waiter to take a step
> back off.
>
> 		if (count & RWSEM_LOCK_MASK) {
> 			if (has_handoff || (!rt_task(waiter->task) &&
> 					    !time_after(jiffies, waiter->timeout)))
> 				return false;
>
> 			new |= RWSEM_FLAG_HANDOFF;
> 		} else {
>
>> But does it break optimistic spinning ? @waiman ?
> Waiters spin for acquiring lock instead of lockup and your report shows
> spinning too much makes trouble. The key is stop spinning neither too
> late nor too early. My proposal is a simple one with as few heuristics
> added as possible.

Yes, too much spinning is bad if we have RT tasks in the mix, otherwise 
it should be fine.

Cheers,
Longman