From mboxrd@z Thu Jan 1 00:00:00 1970 From: David Miller Subject: Re: softirq warnings when calling dev_kfree_skb_irq - bug in conntrack? Date: Tue, 03 Aug 2010 00:23:18 -0700 (PDT) Message-ID: <20100803.002318.209965574.davem@davemloft.net> References: <4C571476.7070301@goop.org> <1280819074.3874.8.camel@jlt3.sipsolutions.net> Mime-Version: 1.0 Content-Type: Text/Plain; charset=us-ascii Content-Transfer-Encoding: 7bit Cc: jeremy@goop.org, Xen-devel@lists.xensource.com, Ian.Campbell@citrix.com, eric.dumazet@gmail.com, netdev@vger.kernel.org, dongxiao.xu@intel.com, kaber@trash.net To: johannes@sipsolutions.net Return-path: In-Reply-To: <1280819074.3874.8.camel@jlt3.sipsolutions.net> List-Unsubscribe: , List-Post: List-Help: List-Subscribe: , Sender: xen-devel-bounces@lists.xensource.com Errors-To: xen-devel-bounces@lists.xensource.com List-Id: netdev.vger.kernel.org From: Johannes Berg Date: Tue, 03 Aug 2010 09:04:34 +0200 > I had this too: > http://article.gmane.org/gmane.linux.network/167590 > > But I'm not convinced it's conntrack, I'd think it's > > commit 15e83ed78864d0625e87a85f09b297c0919a4797 > Author: Eric Dumazet > Date: Wed May 19 23:16:03 2010 +0000 > > net: remove zap_completion_queue > > which, from the looks of it, ought to be reverted because it failed to > take into account that dev_kfree_skb() can do more things that require > non-irq-context than just calling skb->destructor, like for instance the > conntrack thing we see here. Agreed. I'll revert this and queue that up for 2.6.35-stable