Received-SPF: pass (google.com: best guess record for domain of linux-kernel-owner@vger.kernel.org designates 209.132.180.67 as permitted sender) client-ip=209.132.180.67;
Subject: Re: [RFC] eventfd: add EFD_AUTORESET flag
To:     Stefan Hajnoczi <stefanha@gmail.com>
Cc:     Paolo Bonzini <pbonzini@redhat.com>,
        Stefan Hajnoczi <stefanha@redhat.com>,
        linux-fsdevel@vger.kernel.org, kvm@vger.kernel.org,
        linux-kernel@vger.kernel.org,
        Davide Libenzi <davidel@xmailserver.org>,
        Alexander Viro <viro@zeniv.linux.org.uk>
References: <20200129172010.162215-1-stefanha@redhat.com>
 <66566792-58a4-bf65-6723-7d2887c84160@redhat.com>
 <20200212102912.GA464050@stefanha-x1.localdomain>
 <156cb709-282a-ddb6-6f34-82b4bb211f73@redhat.com>
 <cadb4320-4717-1a41-dfb5-bb782fd0a5da@scylladb.com>
 <20200219103704.GA1076032@stefanha-x1.localdomain>
From:   Avi Kivity <avi@scylladb.com>
Organization: ScyllaDB
Message-ID: <c5ea733d-b766-041b-30b9-a9a9b5167462@scylladb.com>
Date:   Wed, 19 Feb 2020 12:43:51 +0200
User-Agent: Mozilla/5.0 (X11; Linux x86_64; rv:68.0) Gecko/20100101
 Thunderbird/68.4.1
MIME-Version: 1.0
In-Reply-To: <20200219103704.GA1076032@stefanha-x1.localdomain>
Content-Type: text/plain; charset=windows-1252; format=flowed
Content-Transfer-Encoding: 7bit
Content-Language: en-US
Sender: linux-kernel-owner@vger.kernel.org
Precedence: bulk


On 19/02/2020 12.37, Stefan Hajnoczi wrote:
> On Wed, Feb 12, 2020 at 12:54:30PM +0200, Avi Kivity wrote:
>> On 12/02/2020 12.47, Paolo Bonzini wrote:
>>> On 12/02/20 11:29, Stefan Hajnoczi wrote:
>>>> On Wed, Feb 12, 2020 at 09:31:32AM +0100, Paolo Bonzini wrote:
>>>>> On 29/01/20 18:20, Stefan Hajnoczi wrote:
>>>>>> +	/* Semaphore semantics don't make sense when autoreset is enabled */
>>>>>> +	if ((flags & EFD_SEMAPHORE) && (flags & EFD_AUTORESET))
>>>>>> +		return -EINVAL;
>>>>>> +
>>>>> I think they do, you just want to subtract 1 instead of setting the
>>>>> count to 0.  This way, writing 1 would be the post operation on the
>>>>> semaphore, while poll() would be the wait operation.
>>>> True!  Then EFD_AUTORESET is not a fitting name.  EFD_AUTOREAD or
>>>> EFD_POLL_READS?
>>> Avi's suggestion also makes sense.  Switching the event loop from poll()
>>> to IORING_OP_POLL_ADD would be good on its own, and then you could make
>>> it use IORING_OP_READV for eventfds.
>>>
>>> In QEMU parlance, perhaps you need a different abstraction than
>>> EventNotifier (let's call it WakeupNotifier) which would also use
>>> eventfd but it would provide a smaller API.  Thanks to the smaller API,
>>> it would not need EFD_NONBLOCK, unlike the regular EventNotifier, and it
>>> could either set up a poll() handler calling read(), or use
>>> IORING_OP_READV when io_uring is in use.
>>>
>> Just to be clear, for best performance don't use IORING_OP_POLL_ADD, just
>> IORING_OP_READ. That's what you say in the second paragraph but the first
>> can be misleading.


Actually it turns out that current uring OP_READ throws the work into a 
workqueue. Jens is fixing that now.


> Thanks, that's a nice idea!  I already have experimental io_uring fd
> monitoring code written for QEMU and will extend it to use IORING_OP_READ.


Note linux-aio can do IOCB_CMD_POLL, starting with 4.19.