From mboxrd@z Thu Jan 1 00:00:00 1970 From: Jason Wang Subject: Re: [PATCH net] tuntap: raise EPOLLOUT on device up Date: Fri, 18 May 2018 22:11:54 +0800 Message-ID: References: <1526648443-24128-1-git-send-email-jasowang@redhat.com> <20180518161253-mutt-send-email-mst@kernel.org> <6159b23e-eeda-1d4b-6a30-63b1a30666eb@redhat.com> <20180518170155-mutt-send-email-mst@kernel.org> Mime-Version: 1.0 Content-Type: text/plain; charset=utf-8; format=flowed Content-Transfer-Encoding: 8bit Cc: netdev@vger.kernel.org, linux-kernel@vger.kernel.org, Hannes Frederic Sowa , Eric Dumazet To: "Michael S. Tsirkin" Return-path: Received: from mx3-rdu2.redhat.com ([66.187.233.73]:59920 "EHLO mx1.redhat.com" rhost-flags-OK-OK-OK-FAIL) by vger.kernel.org with ESMTP id S1750957AbeEROMD (ORCPT ); Fri, 18 May 2018 10:12:03 -0400 In-Reply-To: <20180518170155-mutt-send-email-mst@kernel.org> Content-Language: en-US Sender: netdev-owner@vger.kernel.org List-ID: On 2018年05月18日 22:06, Michael S. Tsirkin wrote: > On Fri, May 18, 2018 at 10:00:31PM +0800, Jason Wang wrote: >> >> On 2018年05月18日 21:26, Jason Wang wrote: >>> >>> On 2018年05月18日 21:13, Michael S. Tsirkin wrote: >>>> On Fri, May 18, 2018 at 09:00:43PM +0800, Jason Wang wrote: >>>>> We return -EIO on device down but can not raise EPOLLOUT after it was >>>>> up. This may confuse user like vhost which expects tuntap to raise >>>>> EPOLLOUT to re-enable its TX routine after tuntap is down. This could >>>>> be easily reproduced by transmitting packets from VM while down and up >>>>> the tap device. Fixing this by set SOCKWQ_ASYNC_NOSPACE on -EIO. >>>>> >>>>> Cc: Hannes Frederic Sowa >>>>> Cc: Eric Dumazet >>>>> Fixes: 1bd4978a88ac2 ("tun: honor IFF_UP in tun_get_user()") >>>>> Signed-off-by: Jason Wang >>>>> --- >>>>>   drivers/net/tun.c | 4 +++- >>>>>   1 file changed, 3 insertions(+), 1 deletion(-) >>>>> >>>>> diff --git a/drivers/net/tun.c b/drivers/net/tun.c >>>>> index d45ac37..1b29761 100644 >>>>> --- a/drivers/net/tun.c >>>>> +++ b/drivers/net/tun.c >>>>> @@ -1734,8 +1734,10 @@ static ssize_t tun_get_user(struct >>>>> tun_struct *tun, struct tun_file *tfile, >>>>>       int skb_xdp = 1; >>>>>       bool frags = tun_napi_frags_enabled(tun); >>>>>   -    if (!(tun->dev->flags & IFF_UP)) >>>>> +    if (!(tun->dev->flags & IFF_UP)) { >>>> Isn't this racy?  What if flag is cleared at this point? >>> I think you mean "set at this point"? Then yes, so we probably need to >>> set the bit during tun_net_close(). >>> >>> Thanks >> Looks no need, vhost will poll socket after it see EIO. So we are ok here? >> >> Thanks > In fact I don't even understand why does this help any longer. > We disable tx polling and only enable it on demand for a better rx performance. You may want to have a look at : commit feb8892cb441c742d4220cf7ced001e7fa070731 Author: Jason Wang Date:   Mon Nov 13 11:45:34 2017 +0800     vhost_net: conditionally enable tx polling Thanks