From mboxrd@z Thu Jan 1 00:00:00 1970 From: Eric Dumazet Subject: [PATCH net-next] net: allow large number of tx queues Date: Thu, 20 Jun 2013 01:15:51 -0700 Message-ID: <1371716151.3252.390.camel@edumazet-glaptop> References: <1371620452-49349-1-git-send-email-jasowang@redhat.com> <1371620452-49349-2-git-send-email-jasowang@redhat.com> <1371623518.3252.267.camel@edumazet-glaptop> <20130619091132.GA2816@redhat.com> <1371635763.3252.289.camel@edumazet-glaptop> <20130619154059.GA13735@redhat.com> <1371657511.3252.324.camel@edumazet-glaptop> <20130619180709.GA15017@redhat.com> Mime-Version: 1.0 Content-Type: text/plain; charset="UTF-8" Content-Transfer-Encoding: 7bit Cc: Jason Wang , davem@davemloft.net, hkchu@google.com, netdev To: "Michael S. Tsirkin" Return-path: Received: from mail-bk0-f52.google.com ([209.85.214.52]:57284 "EHLO mail-bk0-f52.google.com" rhost-flags-OK-OK-OK-OK) by vger.kernel.org with ESMTP id S1754498Ab3FTIP4 (ORCPT ); Thu, 20 Jun 2013 04:15:56 -0400 Received: by mail-bk0-f52.google.com with SMTP id d7so2692795bkh.39 for ; Thu, 20 Jun 2013 01:15:55 -0700 (PDT) In-Reply-To: <20130619180709.GA15017@redhat.com> Sender: netdev-owner@vger.kernel.org List-ID: From: Eric Dumazet On Wed, 2013-06-19 at 21:07 +0300, Michael S. Tsirkin wrote: > As we have explicit code to recover, maybe set __GFP_NOWARN? > If we are out of memory, vzalloc will warn too, we don't > need two warnings. Yes, that's absolutely the right thing to do. Its yet not clear this patch is really needed, but here it is. Thanks [PATCH net-next] net: allow large number of tx queues netif_alloc_netdev_queues() uses kcalloc() to allocate memory for the "struct netdev_queue *_tx" array. For large number of tx queues, kcalloc() might fail, so this patch does a fallback to vzalloc(). As vmalloc() adds overhead on a critical network path, add __GFP_REPEAT to kzalloc() flags to do this fallback only when really needed. Signed-off-by: Eric Dumazet --- net/core/dev.c | 26 +++++++++++++++++++------- 1 file changed, 19 insertions(+), 7 deletions(-) diff --git a/net/core/dev.c b/net/core/dev.c index fa007db..722f633 100644 --- a/net/core/dev.c +++ b/net/core/dev.c @@ -130,6 +130,7 @@ #include #include #include +#include #include "net-sysfs.h" @@ -5253,17 +5254,28 @@ static void netdev_init_one_queue(struct net_device *dev, #endif } +static void netif_free_tx_queues(struct net_device *dev) +{ + if (is_vmalloc_addr(dev->_tx)) + vfree(dev->_tx); + else + kfree(dev->_tx); +} + static int netif_alloc_netdev_queues(struct net_device *dev) { unsigned int count = dev->num_tx_queues; struct netdev_queue *tx; + size_t sz = count * sizeof(*tx); - BUG_ON(count < 1); - - tx = kcalloc(count, sizeof(struct netdev_queue), GFP_KERNEL); - if (!tx) - return -ENOMEM; + BUG_ON(count < 1 || count > 0xffff); + tx = kzalloc(sz, GFP_KERNEL | __GFP_NOWARN | __GFP_REPEAT); + if (!tx) { + tx = vzalloc(sz); + if (!tx) + return -ENOMEM; + } dev->_tx = tx; netdev_for_each_tx_queue(dev, netdev_init_one_queue, NULL); @@ -5811,7 +5823,7 @@ free_all: free_pcpu: free_percpu(dev->pcpu_refcnt); - kfree(dev->_tx); + netif_free_tx_queues(dev); #ifdef CONFIG_RPS kfree(dev->_rx); #endif @@ -5836,7 +5848,7 @@ void free_netdev(struct net_device *dev) release_net(dev_net(dev)); - kfree(dev->_tx); + netif_free_tx_queues(dev); #ifdef CONFIG_RPS kfree(dev->_rx); #endif