Return-Path: Received: (majordomo@vger.kernel.org) by vger.kernel.org via listexpand id S1754526AbbEECPb (ORCPT ); Mon, 4 May 2015 22:15:31 -0400 Received: from shadbolt.e.decadent.org.uk ([88.96.1.126]:50892 "EHLO shadbolt.e.decadent.org.uk" rhost-flags-OK-OK-OK-OK) by vger.kernel.org with ESMTP id S1752067AbbEEBV5 (ORCPT ); Mon, 4 May 2015 21:21:57 -0400 Content-Type: text/plain; charset="UTF-8" Content-Disposition: inline Content-Transfer-Encoding: 8bit MIME-Version: 1.0 From: Ben Hutchings To: linux-kernel@vger.kernel.org, stable@vger.kernel.org CC: akpm@linux-foundation.org, "Eric Dumazet" , "Prasad Sodagudi" , "Subash Abhinov Kasiviswanathan" , "Tom Herbert" , "David S. Miller" Date: Tue, 05 May 2015 02:16:39 +0100 Message-ID: X-Mailer: LinuxStableQueue (scripts by bwh) Subject: [PATCH 3.2 186/221] net: rps: fix cpu unplug In-Reply-To: X-SA-Exim-Connect-IP: 192.168.4.249 X-SA-Exim-Mail-From: ben@decadent.org.uk X-SA-Exim-Scanned: No (on shadbolt.decadent.org.uk); SAEximRunCond expanded to false Sender: linux-kernel-owner@vger.kernel.org List-ID: X-Mailing-List: linux-kernel@vger.kernel.org Content-Length: 2769 Lines: 77 3.2.69-rc1 review patch. If anyone has any objections, please let me know. ------------------ From: Eric Dumazet [ Upstream commit ac64da0b83d82abe62f78b3d0e21cca31aea24fa ] softnet_data.input_pkt_queue is protected by a spinlock that we must hold when transferring packets from victim queue to an active one. This is because other cpus could still be trying to enqueue packets into victim queue. A second problem is that when we transfert the NAPI poll_list from victim to current cpu, we absolutely need to special case the percpu backlog, because we do not want to add complex locking to protect process_queue : Only owner cpu is allowed to manipulate it, unless cpu is offline. Based on initial patch from Prasad Sodagudi & Subash Abhinov Kasiviswanathan. This version is better because we do not slow down packet processing, only make migration safer. Reported-by: Prasad Sodagudi Reported-by: Subash Abhinov Kasiviswanathan Signed-off-by: Eric Dumazet Cc: Tom Herbert Signed-off-by: David S. Miller Signed-off-by: Ben Hutchings --- net/core/dev.c | 20 +++++++++++++++----- 1 file changed, 15 insertions(+), 5 deletions(-) --- a/net/core/dev.c +++ b/net/core/dev.c @@ -6338,10 +6338,20 @@ static int dev_cpu_callback(struct notif oldsd->output_queue = NULL; oldsd->output_queue_tailp = &oldsd->output_queue; } - /* Append NAPI poll list from offline CPU. */ - if (!list_empty(&oldsd->poll_list)) { - list_splice_init(&oldsd->poll_list, &sd->poll_list); - raise_softirq_irqoff(NET_RX_SOFTIRQ); + /* Append NAPI poll list from offline CPU, with one exception : + * process_backlog() must be called by cpu owning percpu backlog. + * We properly handle process_queue & input_pkt_queue later. + */ + while (!list_empty(&oldsd->poll_list)) { + struct napi_struct *napi = list_first_entry(&oldsd->poll_list, + struct napi_struct, + poll_list); + + list_del_init(&napi->poll_list); + if (napi->poll == process_backlog) + napi->state = 0; + else + ____napi_schedule(sd, napi); } raise_softirq_irqoff(NET_TX_SOFTIRQ); @@ -6352,7 +6362,7 @@ static int dev_cpu_callback(struct notif netif_rx(skb); input_queue_head_incr(oldsd); } - while ((skb = __skb_dequeue(&oldsd->input_pkt_queue))) { + while ((skb = skb_dequeue(&oldsd->input_pkt_queue))) { netif_rx(skb); input_queue_head_incr(oldsd); } -- To unsubscribe from this list: send the line "unsubscribe linux-kernel" in the body of a message to majordomo@vger.kernel.org More majordomo info at http://vger.kernel.org/majordomo-info.html Please read the FAQ at http://www.tux.org/lkml/