From patchwork Fri Jun 10 10:56:17 2011 Content-Type: text/plain; charset="utf-8" MIME-Version: 1.0 Content-Transfer-Encoding: 7bit X-Patchwork-Submitter: Jason Wang X-Patchwork-Id: 99880 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 948E7B6FF4 for ; Fri, 10 Jun 2011 20:55:55 +1000 (EST) Received: (majordomo@vger.kernel.org) by vger.kernel.org via listexpand id S1755621Ab1FJKzf (ORCPT ); Fri, 10 Jun 2011 06:55:35 -0400 Received: from mx1.redhat.com ([209.132.183.28]:24344 "EHLO mx1.redhat.com" rhost-flags-OK-OK-OK-OK) by vger.kernel.org with ESMTP id S1755444Ab1FJKzd (ORCPT ); Fri, 10 Jun 2011 06:55:33 -0400 Received: from int-mx12.intmail.prod.int.phx2.redhat.com (int-mx12.intmail.prod.int.phx2.redhat.com [10.5.11.25]) by mx1.redhat.com (8.14.4/8.14.4) with ESMTP id p5AAtMfe030127 (version=TLSv1/SSLv3 cipher=DHE-RSA-AES256-SHA bits=256 verify=OK); Fri, 10 Jun 2011 06:55:23 -0400 Received: from dhcp-91-7.nay.redhat.com (dhcp-8-146.nay.redhat.com [10.66.8.146]) by int-mx12.intmail.prod.int.phx2.redhat.com (8.14.4/8.14.4) with ESMTP id p5AAtHnV030320; Fri, 10 Jun 2011 06:55:18 -0400 From: Jason Wang To: rusty@rustcorp.com.au, mst@redhat.com, davem@davemloft.net, netdev@vger.kernel.org, linux-kernel@vger.kernel.org, virtualization@lists.linux-foundation.org Cc: yvugenfi@redhat.com, kvm@vger.kernel.org, herbert@gondor.hengli.com.au, Jason Wang Subject: [PATCH] virtio_net: introduce VIRTIO_NET_HDR_F_DATA_VALID Date: Fri, 10 Jun 2011 18:56:17 +0800 Message-Id: <1307703377-3798-1-git-send-email-jasowang@redhat.com> X-Scanned-By: MIMEDefang 2.68 on 10.5.11.25 Sender: netdev-owner@vger.kernel.org Precedence: bulk List-ID: X-Mailing-List: netdev@vger.kernel.org There's no need for the guest to validate the checksum if it have been validated by host nics. So this patch introduces a new flag - VIRTIO_NET_HDR_F_DATA_VALID which is used to bypass the checksum examing in guest. The backend (tap/macvtap) may set this flag when met skbs with CHECKSUM_UNNECESSARY to save cpu utilization. No feature negotiation is needed as old driver just ignore this flag. Iperf shows 12%-30% performance improvement for UDP traffic. For TCP, when gro is on no difference as it produces skb with partial checksum. But when gro is disabled, 20% or even higher improvement could be measured by netperf. Signed-off-by: Jason Wang Acked-by: Michael S. Tsirkin --- drivers/net/macvtap.c | 2 ++ drivers/net/tun.c | 2 ++ drivers/net/virtio_net.c | 2 ++ include/linux/virtio_net.h | 1 + net/packet/af_packet.c | 2 ++ 5 files changed, 9 insertions(+), 0 deletions(-) diff --git a/drivers/net/macvtap.c b/drivers/net/macvtap.c index 6696e56..ecee0fe 100644 --- a/drivers/net/macvtap.c +++ b/drivers/net/macvtap.c @@ -508,6 +508,8 @@ static int macvtap_skb_to_vnet_hdr(const struct sk_buff *skb, vnet_hdr->flags = VIRTIO_NET_HDR_F_NEEDS_CSUM; vnet_hdr->csum_start = skb_checksum_start_offset(skb); vnet_hdr->csum_offset = skb->csum_offset; + } else if (skb->ip_summed == CHECKSUM_UNNECESSARY) { + vnet_hdr->flags = VIRTIO_NET_HDR_F_DATA_VALID; } /* else everything is zero */ return 0; diff --git a/drivers/net/tun.c b/drivers/net/tun.c index 74e9405..f43fa45 100644 --- a/drivers/net/tun.c +++ b/drivers/net/tun.c @@ -788,6 +788,8 @@ static __inline__ ssize_t tun_put_user(struct tun_struct *tun, gso.flags = VIRTIO_NET_HDR_F_NEEDS_CSUM; gso.csum_start = skb_checksum_start_offset(skb); gso.csum_offset = skb->csum_offset; + } else if (skb->ip_summed == CHECKSUM_UNNECESSARY) { + gso.flags = VIRTIO_NET_HDR_F_DATA_VALID; } /* else everything is zero */ if (unlikely(memcpy_toiovecend(iv, (void *)&gso, total, diff --git a/drivers/net/virtio_net.c b/drivers/net/virtio_net.c index f685324..be3686a 100644 --- a/drivers/net/virtio_net.c +++ b/drivers/net/virtio_net.c @@ -274,6 +274,8 @@ static void receive_buf(struct net_device *dev, void *buf, unsigned int len) hdr->hdr.csum_start, hdr->hdr.csum_offset)) goto frame_err; + } else if (hdr->hdr.flags & VIRTIO_NET_HDR_F_DATA_VALID) { + skb->ip_summed = CHECKSUM_UNNECESSARY; } skb->protocol = eth_type_trans(skb, dev); diff --git a/include/linux/virtio_net.h b/include/linux/virtio_net.h index 136040b..970d5a2 100644 --- a/include/linux/virtio_net.h +++ b/include/linux/virtio_net.h @@ -63,6 +63,7 @@ struct virtio_net_config { * specify GSO or CSUM features, you can simply ignore the header. */ struct virtio_net_hdr { #define VIRTIO_NET_HDR_F_NEEDS_CSUM 1 // Use csum_start, csum_offset +#define VIRTIO_NET_HDR_F_DATA_VALID 2 // Csum is valid __u8 flags; #define VIRTIO_NET_HDR_GSO_NONE 0 // Not a GSO frame #define VIRTIO_NET_HDR_GSO_TCPV4 1 // GSO frame, IPv4 TCP (TSO) diff --git a/net/packet/af_packet.c b/net/packet/af_packet.c index c0c3cda..99ca471 100644 --- a/net/packet/af_packet.c +++ b/net/packet/af_packet.c @@ -1681,6 +1681,8 @@ static int packet_recvmsg(struct kiocb *iocb, struct socket *sock, vnet_hdr.flags = VIRTIO_NET_HDR_F_NEEDS_CSUM; vnet_hdr.csum_start = skb_checksum_start_offset(skb); vnet_hdr.csum_offset = skb->csum_offset; + } else if (skb->ip_summed == CHECKSUM_UNNECESSARY) { + vnet_hdr.flags = VIRTIO_NET_HDR_F_DATA_VALID; } /* else everything is zero */ err = memcpy_toiovec(msg->msg_iov, (void *)&vnet_hdr,