From mboxrd@z Thu Jan 1 00:00:00 1970 From: "Jan Beulich" Subject: Re: [PATCH v2] xen-netfront: pull on receive skb may need to happen earlier Date: Tue, 16 Jul 2013 12:26:50 +0100 Message-ID: <51E54A1A02000078000E557C@nat28.tlf.novell.com> References: <51E5327902000078000E5426@nat28.tlf.novell.com> <20130716102524.GC5674@zion.uk.xensource.com> Mime-Version: 1.0 Content-Type: text/plain; charset=US-ASCII Content-Transfer-Encoding: 8BIT Cc: "Ian Campbell" , , "Dion Kant" , "xen-devel" , , To: "Wei Liu" Return-path: Received: from nat28.tlf.novell.com ([130.57.49.28]:42958 "EHLO nat28.tlf.novell.com" rhost-flags-OK-OK-OK-OK) by vger.kernel.org with ESMTP id S932075Ab3GPL0z convert rfc822-to-8bit (ORCPT ); Tue, 16 Jul 2013 07:26:55 -0400 In-Reply-To: <20130716102524.GC5674@zion.uk.xensource.com> Content-Disposition: inline Sender: netdev-owner@vger.kernel.org List-ID: >>> On 16.07.13 at 12:25, Wei Liu wrote: > On Tue, Jul 16, 2013 at 10:46:01AM +0100, Jan Beulich wrote: >> Due to commit 3683243b ("xen-netfront: use __pskb_pull_tail to ensure >> linear area is big enough on RX") xennet_fill_frags() may end up >> filling MAX_SKB_FRAGS + 1 fragments in a receive skb, and only reduce >> the fragment count subsequently via __pskb_pull_tail(). That's a >> result of xennet_get_responses() allowing a maximum of one more slot to >> be consumed (and intermediately transformed into a fragment) if the >> head slot has a size less than or equal to RX_COPY_THRESHOLD. >> >> Hence we need to adjust xennet_fill_frags() to pull earlier if we >> reached the maximum fragment count - due to the described behavior of >> xennet_get_responses() this guarantees that at least the first fragment >> will get completely consumed, and hence the fragment count reduced. >> >> In order to not needlessly call __pskb_pull_tail() twice, make the >> original call conditional upon the pull target not having been reached >> yet, and defer the newly added one as much as possible (an alternative >> would have been to always call the function right before the call to >> xennet_fill_frags(), but that would imply more frequent cases of >> needing to call it twice). >> >> Signed-off-by: Jan Beulich >> Cc: Wei Liu >> Cc: Ian Campbell >> Cc: stable@vger.kernel.org (3.6 onwards) >> --- >> v2: Use skb_add_rx_frag() to keep all accounting fields up to date as >> we go (skb->len needing intermediate updating was pointed out by >> Wei Liu and David Miller, shinfo->nr_frags needing updating before >> calling __pskb_pull_tail() was spotted out by Dion Kant). > > Jan and Dion, is this a confirmed fix for SuSE kernel? > > I complied and tested it, at least it didn't break things for me. The > tests I ran were 1) scp large_file to domU; 2) iperf from Dom0 to DomU; > 3) netperf from Dom0 to DomU. Yes, the equivalent of this applied to our driver fixes the issue for Dion. Jan