From mboxrd@z Thu Jan 1 00:00:00 1970 Return-Path: Received: (majordomo@vger.kernel.org) by vger.kernel.org via listexpand id S938317AbcISC0S (ORCPT ); Sun, 18 Sep 2016 22:26:18 -0400 Received: from shards.monkeyblade.net ([184.105.139.130]:51902 "EHLO shards.monkeyblade.net" rhost-flags-OK-OK-OK-OK) by vger.kernel.org with ESMTP id S1751488AbcISC0K (ORCPT ); Sun, 18 Sep 2016 22:26:10 -0400 Date: Sun, 18 Sep 2016 22:26:07 -0400 (EDT) Message-Id: <20160918.222607.1930094684278444086.davem@davemloft.net> To: vkuznets@redhat.com Cc: netdev@vger.kernel.org, linux-kernel@vger.kernel.org, ptalbert@redhat.com, boris.ostrovsky@oracle.com, david.vrabel@citrix.com, jgross@suse.com, xen-devel@lists.xenproject.org Subject: Re: [PATCH net-next RESEND] xen-netfront: avoid packet loss when ethernet header crosses page boundary From: David Miller In-Reply-To: <1474023554-24520-1-git-send-email-vkuznets@redhat.com> References: <1474023554-24520-1-git-send-email-vkuznets@redhat.com> X-Mailer: Mew version 6.7 on Emacs 24.5 / Mule 6.0 (HANACHIRUSATO) Mime-Version: 1.0 Content-Type: Text/Plain; charset=us-ascii Content-Transfer-Encoding: 7bit X-Greylist: Sender succeeded SMTP AUTH, not delayed by milter-greylist-4.5.12 (shards.monkeyblade.net [149.20.54.216]); Sun, 18 Sep 2016 19:26:10 -0700 (PDT) Sender: linux-kernel-owner@vger.kernel.org List-ID: X-Mailing-List: linux-kernel@vger.kernel.org From: Vitaly Kuznetsov Date: Fri, 16 Sep 2016 12:59:14 +0200 > @@ -595,6 +596,19 @@ static int xennet_start_xmit(struct sk_buff *skb, struct net_device *dev) > offset = offset_in_page(skb->data); > len = skb_headlen(skb); > > + /* The first req should be at least ETH_HLEN size or the packet will be > + * dropped by netback. > + */ > + if (unlikely(PAGE_SIZE - offset < ETH_HLEN)) { > + nskb = skb_copy(skb, GFP_ATOMIC); > + if (!nskb) > + goto drop; > + dev_kfree_skb_any(skb); > + skb = nskb; > + page = virt_to_page(skb->data); > + offset = offset_in_page(skb->data); > + } > + > spin_lock_irqsave(&queue->tx_lock, flags); I think you also have to recalculate 'len' in this case too, as skb_headlen() will definitely be different for nskb. In fact, I can't see how this code can work properly without that fix.