From mboxrd@z Thu Jan 1 00:00:00 1970 From: David Miller Subject: Re: [PATCH net-next] net: increase LL_MAX_HEADER if HYPERV_NET is enabled Date: Tue, 03 Nov 2015 14:50:27 -0500 (EST) Message-ID: <20151103.145027.1401610638879230478.davem@davemloft.net> References: <20151103.132015.944876907781932861.davem@davemloft.net> Mime-Version: 1.0 Content-Type: Text/Plain; charset=us-ascii Content-Transfer-Encoding: 7bit Cc: eric.dumazet@gmail.com, kys@microsoft.com, edumazet@google.com, netdev@vger.kernel.org To: haiyangz@microsoft.com Return-path: Received: from shards.monkeyblade.net ([149.20.54.216]:46952 "EHLO shards.monkeyblade.net" rhost-flags-OK-OK-OK-OK) by vger.kernel.org with ESMTP id S932478AbbKCTuc (ORCPT ); Tue, 3 Nov 2015 14:50:32 -0500 In-Reply-To: Sender: netdev-owner@vger.kernel.org List-ID: From: Haiyang Zhang Date: Tue, 3 Nov 2015 18:49:05 +0000 >> -----Original Message----- >> From: David Miller [mailto:davem@davemloft.net] >> Sent: Tuesday, November 3, 2015 1:20 PM >> To: Haiyang Zhang >> Cc: eric.dumazet@gmail.com; KY Srinivasan ; >> edumazet@google.com; netdev@vger.kernel.org >> Subject: Re: [PATCH net-next] net: increase LL_MAX_HEADER if HYPERV_NET >> is enabled >> >> From: Haiyang Zhang >> Date: Tue, 3 Nov 2015 17:34:47 +0000 >> >> > But we still keep this busy return in our code, just for "weird corner cases". >> >> The queue_stopped condition must be precise. > > The only case we return NETDEV_TX_BUSY is when the outgoing ring buffer is full, > which almost never happens because we stop the xmit queue if ring is <10% available. I don't think you understand. You must perform the queue stop operation such that it is impossible for your ->ndo_start_xmit() method to be invoked in a way such that you cannot transmit the SKB given to you immediately. It's quite tiring to keep trying to explain this over and over repeatedly.