From mboxrd@z Thu Jan 1 00:00:00 1970 Return-Path: Received: (majordomo@vger.kernel.org) by vger.kernel.org via listexpand id S1753938Ab3KAXe4 (ORCPT ); Fri, 1 Nov 2013 19:34:56 -0400 Received: from webmail.solarflare.com ([12.187.104.25]:30689 "EHLO webmail.solarflare.com" rhost-flags-OK-OK-OK-OK) by vger.kernel.org with ESMTP id S1752003Ab3KAXez (ORCPT ); Fri, 1 Nov 2013 19:34:55 -0400 Message-ID: <1383348890.1737.40.camel@bwh-desktop.uk.level5networks.com> Subject: Re: [PATCH] bnx2: Use dev_kfree_skb_any() in bnx2_tx_int() From: Ben Hutchings To: David Miller CC: , , , , Date: Fri, 1 Nov 2013 23:34:50 +0000 In-Reply-To: <20131101.180147.629210014672277622.davem@davemloft.net> References: <20131031.002602.2030884257299947291.davem@davemloft.net> <20131101.180147.629210014672277622.davem@davemloft.net> Organization: Solarflare Content-Type: text/plain; charset="UTF-8" X-Mailer: Evolution 3.6.4 (3.6.4-3.fc18) MIME-Version: 1.0 Content-Transfer-Encoding: 8bit X-Originating-IP: [10.17.20.137] X-TM-AS-Product-Ver: SMEX-10.0.0.1412-7.000.1014-20260.002 X-TM-AS-Result: No--28.390000-0.000000-31 X-TM-AS-User-Approved-Sender: Yes X-TM-AS-User-Blocked-Sender: No Sender: linux-kernel-owner@vger.kernel.org List-ID: X-Mailing-List: linux-kernel@vger.kernel.org On Fri, 2013-11-01 at 18:01 -0400, David Miller wrote: > From: Cong Wang > Date: Thu, 31 Oct 2013 21:19:16 -0700 > > > 2013年10月30日 下午9:26于 "David Miller" 写道： > >> > >> We have to provide a softint compatible environment for this callback > >> to run in else everything is completely broken. > >> > >> All these drivers can safely assume softirq safe locking is > >> sufficient, you're suggesting we need to take this hardirq safety and > >> I'm really not willing to allow things to go that far. A lot of > >> effort has been expended precisely to avoid that kind of overhead and > >> cost. > > > > Alright, I am thinking to move netpoll_poll_dev() to a delayed work. > > What if the printk is outputting a message that will help us discover > that work queues are deadlocked? > > You can't delay the message, because every layer of indirection you > add increases the possibility that the message it never seen. You > have to do it synchronously. As you've said, the ndo_start_xmit and NAPI poll operations are intended to be called in softirq context, so everything that interlocks with them will use spin_lock_bh(). Calling them from hardirq context obviously opens the possibility of a deadlock. How do you expect anyone to solve that? I think that most of the time netpoll doesn't actually call the NAPI poll function, and the driver ndo_start_xmit function doesn't take any locks, so we don't actually hit the deadlock in practice (on mainline kernels - RT is a different story). Obviously, the less machinery netpoll relies on continuing to work, the better, so it should preferably defer to sofirq context rather than workqueue context. I think this means hooking queue_process() into net_tx_action(), and then cutting out much of the rest of netpoll. Ben. -- Ben Hutchings, Staff Engineer, Solarflare Not speaking for my employer; that's the marketing department's job. They asked us to note that Solarflare product names are trademarked.