From mboxrd@z Thu Jan 1 00:00:00 1970 Return-Path: Received: (majordomo@vger.kernel.org) by vger.kernel.org via listexpand id S1752556AbbKKTUE (ORCPT ); Wed, 11 Nov 2015 14:20:04 -0500 Received: from shards.monkeyblade.net ([149.20.54.216]:50401 "EHLO shards.monkeyblade.net" rhost-flags-OK-OK-OK-OK) by vger.kernel.org with ESMTP id S1751708AbbKKTT6 convert rfc822-to-8bit (ORCPT ); Wed, 11 Nov 2015 14:19:58 -0500 Date: Wed, 11 Nov 2015 14:19:56 -0500 (EST) Message-Id: <20151111.141956.1056130800039910138.davem@davemloft.net> To: mans@mansr.com Cc: romieu@fr.zoreil.com, linux-kernel@vger.kernel.org, netdev@vger.kernel.org, slash.tmp@free.fr Subject: Re: [PATCH v5] net: ethernet: add driver for Aurora VLSI NB8800 Ethernet controller From: David Miller In-Reply-To: References: <20151111.141311.1893172622045238748.davem@davemloft.net> X-Mailer: Mew version 6.6 on Emacs 24.5 / Mule 6.0 (HANACHIRUSATO) Mime-Version: 1.0 Content-Type: Text/Plain; charset=iso-8859-1 Content-Transfer-Encoding: 8BIT X-Greylist: Sender succeeded SMTP AUTH, not delayed by milter-greylist-4.5.12 (shards.monkeyblade.net [149.20.54.216]); Wed, 11 Nov 2015 11:19:58 -0800 (PST) Sender: linux-kernel-owner@vger.kernel.org List-ID: X-Mailing-List: linux-kernel@vger.kernel.org From: Måns Rullgård Date: Wed, 11 Nov 2015 19:17:07 +0000 > David Miller writes: > >> From: Måns Rullgård >> Date: Wed, 11 Nov 2015 19:09:19 +0000 >> >>> David Miller writes: >>> >>>> From: Måns Rullgård >>>> Date: Wed, 11 Nov 2015 18:25:05 +0000 >>>> >>>>> If the TX DMA channel is idle when start_xmit is called, it can be >>>>> started immediately. Checking the DMA status and starting it if >>>>> idle has to be done atomically somehow. >>>> >>>> ->ndo_start_xmit() is guaranteed to be invoked atomically, protected >>>> by the TX queue spinlock. >>> >>> Yes, but the DMA needs to be restarted from some other context if it was >>> busy when start_xmit checked. >> >> Then you can probably use the TXQ lock in the interrupt handler just for >> that. > > That seems a bit heavy-handed when the critical section for this is only > a tiny part of the start_xmit function. Then what synchornization primitive other than spin locks are you going to use for this? My point is that there is a spinlock the core code is _already_ taking, unconditionally, when ->ndo_start_xmit() executes. And you can therefore take advantage of that rather than using another lock of your own.