From patchwork Mon Aug 18 13:37:17 2014 Content-Type: text/plain; charset="utf-8" MIME-Version: 1.0 Content-Transfer-Encoding: 7bit X-Patchwork-Submitter: Pankaj Gupta X-Patchwork-Id: 381008 X-Patchwork-Delegate: davem@davemloft.net Return-Path: X-Original-To: patchwork-incoming@ozlabs.org Delivered-To: patchwork-incoming@ozlabs.org Received: from vger.kernel.org (vger.kernel.org [209.132.180.67]) by ozlabs.org (Postfix) with ESMTP id C834C140110 for ; Mon, 18 Aug 2014 23:38:36 +1000 (EST) Received: (majordomo@vger.kernel.org) by vger.kernel.org via listexpand id S1751774AbaHRNiT (ORCPT ); Mon, 18 Aug 2014 09:38:19 -0400 Received: from mx1.redhat.com ([209.132.183.28]:46063 "EHLO mx1.redhat.com" rhost-flags-OK-OK-OK-OK) by vger.kernel.org with ESMTP id S1751743AbaHRNiR (ORCPT ); Mon, 18 Aug 2014 09:38:17 -0400 Received: from int-mx13.intmail.prod.int.phx2.redhat.com (int-mx13.intmail.prod.int.phx2.redhat.com [10.5.11.26]) by mx1.redhat.com (8.14.4/8.14.4) with ESMTP id s7IDbx00031722 (version=TLSv1/SSLv3 cipher=DHE-RSA-AES256-GCM-SHA384 bits=256 verify=OK); Mon, 18 Aug 2014 09:38:00 -0400 Received: from dhcp223-82.pnq.redhat.com ([10.65.223.17]) by int-mx13.intmail.prod.int.phx2.redhat.com (8.14.4/8.14.4) with ESMTP id s7IDbNm7011293 (version=TLSv1/SSLv3 cipher=DHE-RSA-AES256-GCM-SHA384 bits=256 verify=NO); Mon, 18 Aug 2014 09:37:54 -0400 From: Pankaj Gupta To: linux-kernel@vger.kernel.org, netdev@vger.kernel.org Cc: davem@davemloft.net, jasowang@redhat.com, mst@redhat.com, dgibson@redhat.com, vfalico@gmail.com, edumazet@google.com, vyasevic@redhat.com, hkchu@google.com, wuzhy@linux.vnet.ibm.com, xemul@parallels.com, therbert@google.com, bhutchings@solarflare.com, xii@google.com, stephen@networkplumber.org, Pankaj Gupta Subject: [RFC 1/4] net: allow large number of rx queues Date: Mon, 18 Aug 2014 19:07:17 +0530 Message-Id: <1408369040-1216-2-git-send-email-pagupta@redhat.com> In-Reply-To: <1408369040-1216-1-git-send-email-pagupta@redhat.com> References: <1408369040-1216-1-git-send-email-pagupta@redhat.com> X-Scanned-By: MIMEDefang 2.68 on 10.5.11.26 Sender: netdev-owner@vger.kernel.org Precedence: bulk List-ID: X-Mailing-List: netdev@vger.kernel.org netif_alloc_rx_queues() uses kcalloc() to allocate memory for "struct netdev_queue *_rx" array. If we are doing large rx queue allocation kcalloc() might fail, so this patch does a fallback to vzalloc(). Similar implementation is done for tx queue allocation in netif_alloc_netdev_queues(). We avoid failure of high order memory allocation with the help of vzalloc(), this allows us to do large rx and tx queue allocation which in turn helps us to increase the number of queues in tun. As vmalloc() adds overhead on a critical network path, __GFP_REPEAT flag is used with kzalloc() to do this fallback only when really needed. Signed-off-by: Pankaj Gupta Reviewed-by: Michael S. Tsirkin Reviewed-by: David Gibson --- net/core/dev.c | 20 +++++++++++++------- 1 file changed, 13 insertions(+), 7 deletions(-) diff --git a/net/core/dev.c b/net/core/dev.c index 1c15b18..a455a02 100644 --- a/net/core/dev.c +++ b/net/core/dev.c @@ -5942,17 +5942,24 @@ void netif_stacked_transfer_operstate(const struct net_device *rootdev, EXPORT_SYMBOL(netif_stacked_transfer_operstate); #ifdef CONFIG_SYSFS +static void netif_free_rx_queues(struct net_device *dev) +{ + kvfree(dev->_rx); +} + static int netif_alloc_rx_queues(struct net_device *dev) { unsigned int i, count = dev->num_rx_queues; struct netdev_rx_queue *rx; - + size_t sz = count * sizeof(*rx); BUG_ON(count < 1); - rx = kcalloc(count, sizeof(struct netdev_rx_queue), GFP_KERNEL); - if (!rx) - return -ENOMEM; - + rx = kzalloc(sz, GFP_KERNEL | __GFP_NOWARN | __GFP_REPEAT); + if (!rx) { + rx = vzalloc(sz); + if (!rx) + return -ENOMEM; + } dev->_rx = rx; for (i = 0; i < count; i++) @@ -6581,9 +6588,8 @@ void free_netdev(struct net_device *dev) netif_free_tx_queues(dev); #ifdef CONFIG_SYSFS - kfree(dev->_rx); + netif_free_rx_queues(dev); #endif - kfree(rcu_dereference_protected(dev->ingress_queue, 1)); /* Flush device addresses */