[<prev] [next>] [<thread-prev] [thread-next>] [day] [month] [year] [list]
Message-ID: <20220113154301.qd3ayuhrcjnsaim7@steredhat>
Date: Thu, 13 Jan 2022 16:44:47 +0100
From: Stefano Garzarella <sgarzare@...hat.com>
To: "Michael S. Tsirkin" <mst@...hat.com>
Cc: virtualization@...ts.linux-foundation.org, netdev@...r.kernel.org,
stefanha@...hat.com, Jason Wang <jasowang@...hat.com>,
linux-kernel@...r.kernel.org, kvm@...r.kernel.org
Subject: Re: [RFC PATCH] vhost: cache avail index in vhost_enable_notify()
On Thu, Jan 13, 2022 at 10:19:46AM -0500, Michael S. Tsirkin wrote:
>On Thu, Jan 13, 2022 at 03:56:42PM +0100, Stefano Garzarella wrote:
>> In vhost_enable_notify() we enable the notifications and we read
>> the avail index to check if new buffers have become available in
>> the meantime. In this case, the device would go to re-read avail
>> index to access the descriptor.
>>
>> As we already do in other place, we can cache the value in `avail_idx`
>> and compare it with `last_avail_idx` to check if there are new
>> buffers available.
>>
>> Signed-off-by: Stefano Garzarella <sgarzare@...hat.com>
>
>I guess we can ... but what's the point?
>
That without this patch if avail index is new, then device when will
call vhost_get_vq_desc() will find old value in cache and will read it
again.
With this patch we also do the same path and update the cache every time
we read avail index.
I marked it RFC because I don't know if it's worth it :-)
Stefano
Powered by blists - more mailing lists