From mboxrd@z Thu Jan  1 00:00:00 1970
Received: from mailman by lists.gnu.org with tmda-scanned (Exim 4.43)
	id 1M6NwR-0007tP-M1
	for qemu-devel@nongnu.org; Tue, 19 May 2009 07:57:08 -0400
Received: from exim by lists.gnu.org with spam-scanned (Exim 4.43)
	id 1M6NwN-0007q7-SA
	for qemu-devel@nongnu.org; Tue, 19 May 2009 07:57:07 -0400
Received: from [199.232.76.173] (port=43622 helo=monty-python.gnu.org)
	by lists.gnu.org with esmtp (Exim 4.43) id 1M6NwN-0007pz-OD
	for qemu-devel@nongnu.org; Tue, 19 May 2009 07:57:03 -0400
Received: from mx2.redhat.com ([66.187.237.31]:46315)
	by monty-python.gnu.org with esmtp (Exim 4.60)
	(envelope-from <avi@redhat.com>) id 1M6NwN-0001VH-1b
	for qemu-devel@nongnu.org; Tue, 19 May 2009 07:57:03 -0400
Message-ID: <4A129E89.7030603@redhat.com>
Date: Tue, 19 May 2009 14:56:57 +0300
From: Avi Kivity <avi@redhat.com>
MIME-Version: 1.0
Subject: Re: [Qemu-devel] [PATCH 0/13] Add generic packet buffering API
References: <1242726931-5726-1-git-send-email-markmc@redhat.com>	
	<4A128785.9040903@redhat.com> <1242729209.16653.19.camel@blaa>
In-Reply-To: <1242729209.16653.19.camel@blaa>
Content-Type: text/plain; charset=ISO-8859-1; format=flowed
Content-Transfer-Encoding: 7bit
List-Id: qemu-devel.nongnu.org
List-Unsubscribe: <http://lists.nongnu.org/mailman/listinfo/qemu-devel>,
	<mailto:qemu-devel-request@nongnu.org?subject=unsubscribe>
List-Archive: <http://lists.gnu.org/pipermail/qemu-devel>
List-Post: <mailto:qemu-devel@nongnu.org>
List-Help: <mailto:qemu-devel-request@nongnu.org?subject=help>
List-Subscribe: <http://lists.nongnu.org/mailman/listinfo/qemu-devel>,
	<mailto:qemu-devel-request@nongnu.org?subject=subscribe>
To: Mark McLoughlin <markmc@redhat.com>
Cc: Anthony Liguori <aliguori@us.ibm.com>, qemu-devel@nongnu.org

Mark McLoughlin wrote:
>> It will need adjustments to the device models; for example we'll need 
>> virtqueue_pop_commit() after we're certain the tap had enough room for 
>> our packet and virtqueue_pop_cancel() (to unmap the buffers) if we don't.
>>     
>
> Yep, it's possible with virtio. However, you can't unpop the buffer from
> a tap file descriptor or socket.
>
> The alternative in those cases is to implement buffering for each, or to
> always check the receiving side has buffers available before popping. I
> choose this option because checking in advance for each packet seems
> expensive - i.e. a syscall for tap/socket or a trawl through the ring
> for virtio.
>   

For virtio (or the other emulated devices) the check is pretty cheap; 
furthermore you only need to do it when something changes (notification 
or a pop).

So, with the disadvantage of an asymmetrical API, we have:

transmit():
   conditional pop
   tap->receive()
   commit pop / cancel pop

receive():
   tap->send()
   if (no more room)
       tap->stop()

receive_notify():
    if (more room)
       tap->start()

-- 
error compiling committee.c: too many arguments to function