From patchwork Sun Apr 3 19:25:56 2016 Content-Type: text/plain; charset="utf-8" MIME-Version: 1.0 Content-Transfer-Encoding: 7bit X-Patchwork-Submitter: Wei Xu X-Patchwork-Id: 605651 Return-Path: X-Original-To: incoming@patchwork.ozlabs.org Delivered-To: patchwork-incoming@bilbo.ozlabs.org Received: from lists.gnu.org (lists.gnu.org [208.118.235.17]) (using TLSv1 with cipher AES256-SHA (256/256 bits)) (No client certificate requested) by ozlabs.org (Postfix) with ESMTPS id 3qdQCD09v9z9s9k for ; Mon, 4 Apr 2016 05:28:40 +1000 (AEST) Received: from localhost ([::1]:54943 helo=lists.gnu.org) by lists.gnu.org with esmtp (Exim 4.71) (envelope-from ) id 1amnhO-0008Dw-86 for incoming@patchwork.ozlabs.org; Sun, 03 Apr 2016 15:28:38 -0400 Received: from eggs.gnu.org ([2001:4830:134:3::10]:54202) by lists.gnu.org with esmtp (Exim 4.71) (envelope-from ) id 1amnfC-00050P-3D for qemu-devel@nongnu.org; Sun, 03 Apr 2016 15:26:25 -0400 Received: from Debian-exim by eggs.gnu.org with spam-scanned (Exim 4.71) (envelope-from ) id 1amnfA-0005Wv-IV for qemu-devel@nongnu.org; Sun, 03 Apr 2016 15:26:22 -0400 Received: from mx1.redhat.com ([209.132.183.28]:36675) by eggs.gnu.org with esmtp (Exim 4.71) (envelope-from ) id 1amnfA-0005Wm-9B for qemu-devel@nongnu.org; Sun, 03 Apr 2016 15:26:20 -0400 Received: from int-mx14.intmail.prod.int.phx2.redhat.com (int-mx14.intmail.prod.int.phx2.redhat.com [10.5.11.27]) (using TLSv1.2 with cipher ECDHE-RSA-AES256-GCM-SHA384 (256/256 bits)) (No client certificate requested) by mx1.redhat.com (Postfix) with ESMTPS id F0F337F09B for ; Sun, 3 Apr 2016 19:26:19 +0000 (UTC) Received: from wei-thinkpad.nay.redhat.com (vpn1-7-151.pek2.redhat.com [10.72.7.151]) by int-mx14.intmail.prod.int.phx2.redhat.com (8.14.4/8.14.4) with ESMTP id u33JQ7nc013812; Sun, 3 Apr 2016 15:26:17 -0400 From: wexu@redhat.com To: qemu-devel@nongnu.org Date: Mon, 4 Apr 2016 03:25:56 +0800 Message-Id: <1459711556-10273-4-git-send-email-wexu@redhat.com> In-Reply-To: <1459711556-10273-1-git-send-email-wexu@redhat.com> References: <1459711556-10273-1-git-send-email-wexu@redhat.com> X-Scanned-By: MIMEDefang 2.68 on 10.5.11.27 X-detected-operating-system: by eggs.gnu.org: GNU/Linux 3.x X-Received-From: 209.132.183.28 Cc: victork@redhat.com, mst@redhat.com, jasowang@redhat.com, yvugenfi@redhat.com, Wei Xu , marcel@redhat.com, dfleytma@redhat.com Subject: [Qemu-devel] [ RFC Patch v4 3/3] virtio-net rsc: support coalescing ipv6 tcp traffic X-BeenThere: qemu-devel@nongnu.org X-Mailman-Version: 2.1.14 Precedence: list List-Id: List-Unsubscribe: , List-Archive: List-Post: List-Help: List-Subscribe: , Errors-To: qemu-devel-bounces+incoming=patchwork.ozlabs.org@nongnu.org Sender: qemu-devel-bounces+incoming=patchwork.ozlabs.org@nongnu.org From: Wei Xu Most things like ipv4 except there is a significant difference between ipv4 and ipv6, the fragment lenght in ipv4 header includes itself, while it's not included for ipv6, thus means ipv6 can carry a real '65535' payload. Signed-off-by: Wei Xu --- hw/net/virtio-net.c | 147 +++++++++++++++++++++++++++++++++++++++++++++++++--- 1 file changed, 141 insertions(+), 6 deletions(-) diff --git a/hw/net/virtio-net.c b/hw/net/virtio-net.c index 81e8e71..2d09352 100644 --- a/hw/net/virtio-net.c +++ b/hw/net/virtio-net.c @@ -50,6 +50,10 @@ /* header lenght value in ip header without option */ #define VIRTIO_NET_IP4_HEADER_LENGTH 5 +#define ETH_IP6_HDR_SZ (ETH_HDR_SZ + IP6_HDR_SZ) +#define VIRTIO_NET_IP6_ADDR_SIZE 32 /* ipv6 saddr + daddr */ +#define VIRTIO_NET_MAX_IP6_PAYLOAD VIRTIO_NET_MAX_TCP_PAYLOAD + /* Purge coalesced packets timer interval */ #define VIRTIO_NET_RSC_INTERVAL 300000 @@ -1725,6 +1729,25 @@ static void virtio_net_rsc_extract_unit4(NetRscChain *chain, unit->payload = htons(*unit->ip_plen) - ip_hdrlen - unit->tcp_hdrlen; } +static void virtio_net_rsc_extract_unit6(NetRscChain *chain, + const uint8_t *buf, NetRscUnit* unit) +{ + uint16_t hdr_len; + struct ip6_header *ip6; + + hdr_len = ((VirtIONet *)(chain->n))->guest_hdr_len; + ip6 = (struct ip6_header *)(buf + hdr_len + sizeof(struct eth_header)); + unit->ip = ip6; + unit->ip_plen = &(ip6->ip6_ctlun.ip6_un1.ip6_un1_plen); + unit->tcp = (struct tcp_header *)(((uint8_t *)unit->ip)\ + + sizeof(struct ip6_header)); + unit->tcp_hdrlen = (htons(unit->tcp->th_offset_flags) & 0xF000) >> 10; + + /* There is a difference between payload lenght in ipv4 and v6, + ip header is excluded in ipv6 */ + unit->payload = htons(*unit->ip_plen) - unit->tcp_hdrlen; +} + static void virtio_net_rsc_ipv4_checksum(struct ip_header *ip) { uint32_t sum; @@ -1738,7 +1761,9 @@ static size_t virtio_net_rsc_drain_seg(NetRscChain *chain, NetRscSeg *seg) { int ret; - virtio_net_rsc_ipv4_checksum(seg->unit.ip); + if ((chain->proto == ETH_P_IP) && seg->is_coalesced) { + virtio_net_rsc_ipv4_checksum(seg->unit.ip); + } ret = virtio_net_do_receive(seg->nc, seg->buf, seg->size); QTAILQ_REMOVE(&chain->buffers, seg, next); g_free(seg->buf); @@ -1804,7 +1829,18 @@ static void virtio_net_rsc_cache_buf(NetRscChain *chain, NetClientState *nc, QTAILQ_INSERT_TAIL(&chain->buffers, seg, next); chain->stat.cache++; - virtio_net_rsc_extract_unit4(chain, seg->buf, &seg->unit); + switch (chain->proto) { + case ETH_P_IP: + virtio_net_rsc_extract_unit4(chain, seg->buf, &seg->unit); + break; + + case ETH_P_IPV6: + virtio_net_rsc_extract_unit6(chain, seg->buf, &seg->unit); + break; + + default: + g_assert_not_reached(); + } } static int32_t virtio_net_rsc_handle_ack(NetRscChain *chain, NetRscSeg *seg, @@ -1948,6 +1984,24 @@ static int32_t virtio_net_rsc_coalesce4(NetRscChain *chain, NetRscSeg *seg, return virtio_net_rsc_coalesce_data(chain, seg, buf, unit); } +static int32_t virtio_net_rsc_coalesce6(NetRscChain *chain, NetRscSeg *seg, + const uint8_t *buf, size_t size, NetRscUnit *unit) +{ + struct ip6_header *ip1, *ip2; + + ip1 = (struct ip6_header *)(unit->ip); + ip2 = (struct ip6_header *)(seg->unit.ip); + if (memcmp(&ip1->ip6_src, &ip2->ip6_src, sizeof(struct in6_address)) + || memcmp(&ip1->ip6_dst, &ip2->ip6_dst, sizeof(struct in6_address)) + || (unit->tcp->th_sport ^ seg->unit.tcp->th_sport) + || (unit->tcp->th_dport ^ seg->unit.tcp->th_dport)) { + chain->stat.no_match++; + return RSC_NO_MATCH; + } + + return virtio_net_rsc_coalesce_data(chain, seg, buf, unit); +} + /* Pakcets with 'SYN' should bypass, other flag should be sent after drain * to prevent out of order */ static int virtio_net_rsc_tcp_ctrl_check(NetRscChain *chain, @@ -1991,7 +2045,11 @@ static size_t virtio_net_rsc_do_coalesce(NetRscChain *chain, NetClientState *nc, NetRscSeg *seg, *nseg; QTAILQ_FOREACH_SAFE(seg, &chain->buffers, next, nseg) { - ret = virtio_net_rsc_coalesce4(chain, seg, buf, size, unit); + if (chain->proto == ETH_P_IP) { + ret = virtio_net_rsc_coalesce4(chain, seg, buf, size, unit); + } else { + ret = virtio_net_rsc_coalesce6(chain, seg, buf, size, unit); + } if (ret == RSC_FINAL) { if (virtio_net_rsc_drain_seg(chain, seg) == 0) { @@ -2116,13 +2174,82 @@ static size_t virtio_net_rsc_receive4(void *opq, NetClientState* nc, return virtio_net_rsc_do_coalesce(chain, nc, buf, size, &unit); } +static int32_t virtio_net_rsc_sanity_check6(NetRscChain *chain, + struct ip6_header *ip6, + const uint8_t *buf, size_t size) +{ + uint16_t ip_len; + uint16_t hdr_len; + + hdr_len = ((VirtIONet *)(chain->n))->guest_hdr_len; + if (size < (hdr_len + sizeof(struct eth_header) + sizeof(struct ip6_header) + + sizeof(tcp_header))) { + return RSC_BYPASS; + } + + if (((ip6->ip6_ctlun.ip6_un1.ip6_un1_flow & 0xF0) >> 4) + != IP_HEADER_VERSION_6) { + return RSC_BYPASS; + } + + /* Both option and protocol is checked in this */ + if (ip6->ip6_ctlun.ip6_un1.ip6_un1_nxt != IPPROTO_TCP) { + chain->stat.bypass_not_tcp++; + return RSC_BYPASS; + } + + ip_len = htons(ip6->ip6_ctlun.ip6_un1.ip6_un1_plen); + if (ip_len < sizeof(struct tcp_header) + || ip_len > (size - hdr_len - sizeof(struct eth_header) + - sizeof(struct ip6_header))) { + chain->stat.ip_hacked++; + return RSC_BYPASS; + } + + return RSC_WANT; +} + +static size_t virtio_net_rsc_receive6(void *opq, NetClientState* nc, + const uint8_t *buf, size_t size) +{ + int32_t ret; + uint16_t hdr_len; + NetRscChain *chain; + NetRscUnit unit; + + chain = (NetRscChain *)opq; + hdr_len = ((VirtIONet *)(chain->n))->guest_hdr_len; + virtio_net_rsc_extract_unit6(chain, buf, &unit); + if (RSC_WANT != virtio_net_rsc_sanity_check6(chain, + unit.ip, buf, size)) { + return virtio_net_do_receive(nc, buf, size); + } + + ret = virtio_net_rsc_tcp_ctrl_check(chain, unit.tcp); + if (ret == RSC_BYPASS) { + return virtio_net_do_receive(nc, buf, size); + } else if (ret == RSC_FINAL) { + return virtio_net_rsc_drain_flow(chain, nc, buf, size, + ((hdr_len + sizeof(struct eth_header)) + 8), + VIRTIO_NET_IP6_ADDR_SIZE, + hdr_len + sizeof(struct eth_header) + sizeof(struct ip6_header), + VIRTIO_NET_TCP_PORT_SIZE); + } + + if (virtio_net_rsc_empty_cache(chain, nc, buf, size)) { + return size; + } + + return virtio_net_rsc_do_coalesce(chain, nc, buf, size, &unit); +} + static NetRscChain *virtio_net_rsc_lookup_chain(VirtIONet * n, NetClientState *nc, uint16_t proto) { NetRscChain *chain; - if (proto != (uint16_t)ETH_P_IP) { + if ((proto != (uint16_t)ETH_P_IP) && (proto != (uint16_t)ETH_P_IPV6)) { return NULL; } @@ -2135,7 +2262,11 @@ static NetRscChain *virtio_net_rsc_lookup_chain(VirtIONet * n, chain = g_malloc(sizeof(*chain)); chain->n = n; chain->proto = proto; - chain->max_payload = VIRTIO_NET_MAX_IP4_PAYLOAD; + if (proto == (uint16_t)ETH_P_IP) { + chain->max_payload = VIRTIO_NET_MAX_IP4_PAYLOAD; + } else { + chain->max_payload = VIRTIO_NET_MAX_IP6_PAYLOAD; + } chain->drain_timer = timer_new_ns(QEMU_CLOCK_VIRTUAL, virtio_net_rsc_purge, chain); memset(&chain->stat, 0, sizeof(chain->stat)); @@ -2167,7 +2298,11 @@ static ssize_t virtio_net_rsc_receive(NetClientState *nc, return virtio_net_do_receive(nc, buf, size); } else { chain->stat.received++; - return virtio_net_rsc_receive4(chain, nc, buf, size); + if (proto == (uint16_t)ETH_P_IP) { + return virtio_net_rsc_receive4(chain, nc, buf, size); + } else { + return virtio_net_rsc_receive6(chain, nc, buf, size); + } } }