From mboxrd@z Thu Jan 1 00:00:00 1970 From: Zoltan Kiss Subject: Re: NAPI rescheduling and the delay caused by it Date: Wed, 11 Dec 2013 18:52:21 +0000 Message-ID: <52A8B465.60304@citrix.com> References: <529F7A87.5080303@citrix.com> <1386189718.30495.131.camel@edumazet-glaptop2.roam.corp.google.com> <529F9D4B.1020208@citrix.com> <1386199931.30495.139.camel@edumazet-glaptop2.roam.corp.google.com> <6F39C955CEA9D14BAA91CC78568B93012D5039@AMSPEX01CL02.citrite.net> <1386638065.30495.338.camel@edumazet-glaptop2.roam.corp.google.com> Mime-Version: 1.0 Content-Type: text/plain; charset="UTF-8"; format=flowed Content-Transfer-Encoding: 7bit Cc: "netdev@vger.kernel.org" , "xen-devel@lists.xenproject.org" , Malcolm Crossley , Jonathan Davies , Paul Durrant , Wei Liu , Ian Campbell To: Eric Dumazet Return-path: Received: from smtp.citrix.com ([66.165.176.89]:24638 "EHLO SMTP.CITRIX.COM" rhost-flags-OK-OK-OK-OK) by vger.kernel.org with ESMTP id S1750800Ab3LKSwY (ORCPT ); Wed, 11 Dec 2013 13:52:24 -0500 In-Reply-To: <1386638065.30495.338.camel@edumazet-glaptop2.roam.corp.google.com> Sender: netdev-owner@vger.kernel.org List-ID: On 10/12/13 01:14, Eric Dumazet wrote: > On Mon, 2013-12-09 at 23:39 +0000, Zoltan Kiss wrote: >> I found another suspect however: my grant mapping patches do the >> unmapping from the NAPI instance where otherwise we receive the >> packets from the guest. But this means we call napi_schedule from the >> zerocopy callback, which can be run by anyone who free up that skb, >> including an another VIF's RX thread (which actually does the transmit >> TO the guest). I guess that might be bad. > > Same problem : napi_schedule() is meant to be used from interrupt > context. Indeed, avoiding napi_schedule seems to solve the issue. Thanks for the advices! Zoli