From mboxrd@z Thu Jan 1 00:00:00 1970 From: David Miller Subject: Re: [PATCH net] tg3: Fix RSS ring refill race condition Date: Wed, 21 Mar 2012 21:58:24 -0400 (EDT) Message-ID: <20120321.215824.1259388773873717864.davem@davemloft.net> References: <1332380314-14198-1-git-send-email-mchan@broadcom.com> Mime-Version: 1.0 Content-Type: Text/Plain; charset=us-ascii Content-Transfer-Encoding: 7bit Cc: netdev@vger.kernel.org To: mchan@broadcom.com Return-path: Received: from shards.monkeyblade.net ([198.137.202.13]:48672 "EHLO shards.monkeyblade.net" rhost-flags-OK-OK-OK-OK) by vger.kernel.org with ESMTP id S1752707Ab2CVB6c (ORCPT ); Wed, 21 Mar 2012 21:58:32 -0400 In-Reply-To: <1332380314-14198-1-git-send-email-mchan@broadcom.com> Sender: netdev-owner@vger.kernel.org List-ID: From: "Michael Chan" Date: Wed, 21 Mar 2012 17:38:33 -0800 > The RSS feature in tg3 hardware has only one rx producer ring for all > RSS rings. NAPI vector 1 is special and handles the refilling of the > rx producer ring on behalf of all RSS rings. There is a race condition > between these RSS NAPIs and the NAPI[1]. If NAPI[1] finishes checking > for refill and then another RSS ring empties the rx producer ring > before NAPI[1] exits NAPI, the chip will be completely out of SKBs in > the rx producer ring. > > We fix this by adding a flag tp->rx_refill and rely on napi_schedule()/ > napi_complete() to help synchronize it to close the race condition. > > Update driver version to 3.123. > > Signed-off-by: Michael Chan Applied.