From mboxrd@z Thu Jan 1 00:00:00 1970 From: Eric Dumazet Subject: [NET] net: reorder struct net_device_ops Date: Fri, 20 Mar 2009 10:44:16 +0100 Message-ID: <49C36570.4010903@cosmosbay.com> References: <49C354B5.3060404@cosmosbay.com> <20090320.013611.67498837.davem@davemloft.net> Mime-Version: 1.0 Content-Type: text/plain; charset=ISO-8859-1 Content-Transfer-Encoding: QUOTED-PRINTABLE Cc: netdev@vger.kernel.org To: David Miller Return-path: Received: from gw1.cosmosbay.com ([212.99.114.194]:39256 "EHLO gw1.cosmosbay.com" rhost-flags-OK-OK-OK-OK) by vger.kernel.org with ESMTP id S1756514AbZCTJoZ convert rfc822-to-8bit (ORCPT ); Fri, 20 Mar 2009 05:44:25 -0400 In-Reply-To: <20090320.013611.67498837.davem@davemloft.net> Sender: netdev-owner@vger.kernel.org List-ID: David Miller a =E9crit : > From: Eric Dumazet > Date: Fri, 20 Mar 2009 09:32:53 +0100 >=20 >> There is no point to use prefetch() call here. >> start_xmit() is a function like others... >> >> Signed-off-by: Eric Dumazet >=20 > Yes but the operation pointer might not be in the CPU > cache at this time? >=20 > And if it's not we can get it into the cpu whilst we do > other processing, such as the dev_queue_xmit_nit() stuff. This slow down fast path, but we can find a compromise. I saw a strange effect on oprofile because of this prefetch() on a situation we call xxx.xxx times per second dev_hard_start_xmit() (So this ought to be in CPU cache already) prefetch() is *free* only if the address computation is fast too :) Thank you [NET] net: reorder struct net_device_ops Moving ndo_start_xmit() field at first position in struct net_device_ops reduce the assembly needed to compute the prefetch() address. There seems to be an issue here on some cpus as spotted by oprofile in dev_hard_start_xmit() (prefetch() has a dependancy on previous add instruction) mov %eax,-0x14(%ebp) /* store ops */ add $0x10,%eax /* compute &ops->ndo_start_xmit */ prefetcht0 (%eax) /* stall here */ After patch, no add instruction is needed anymore. Signed-off-by: Eric Dumazet diff --git a/include/linux/netdevice.h b/include/linux/netdevice.h index be3ebd7..e507c6e 100644 --- a/include/linux/netdevice.h +++ b/include/linux/netdevice.h @@ -547,14 +547,14 @@ struct netdev_queue { */ #define HAVE_NET_DEVICE_OPS struct net_device_ops { - int (*ndo_init)(struct net_device *dev); - void (*ndo_uninit)(struct net_device *dev); - int (*ndo_open)(struct net_device *dev); - int (*ndo_stop)(struct net_device *dev); int (*ndo_start_xmit) (struct sk_buff *skb, struct net_device *dev); u16 (*ndo_select_queue)(struct net_device *dev, struct sk_buff *skb); + int (*ndo_init)(struct net_device *dev); + void (*ndo_uninit)(struct net_device *dev); + int (*ndo_open)(struct net_device *dev); + int (*ndo_stop)(struct net_device *dev); #define HAVE_CHANGE_RX_FLAGS void (*ndo_change_rx_flags)(struct net_device *dev, int flags); diff --git a/net/core/dev.c b/net/core/dev.c index c013031..2e5ebd0 100644 --- a/net/core/dev.c +++ b/net/core/dev.c @@ -1670,7 +1670,7 @@ int dev_hard_start_xmit(struct sk_buff *skb, stru= ct net_device *dev, const struct net_device_ops *ops =3D dev->netdev_ops; int rc; =20 - prefetch(&dev->netdev_ops->ndo_start_xmit); + prefetch(&ops->ndo_start_xmit); if (likely(!skb->next)) { if (!list_empty(&ptype_all)) dev_queue_xmit_nit(skb, dev);