Re: [Qemu-devel] [ RFC Patch v6 2/3] virtio-net rsc: support coalescing ipv6 tcp traffic
On 2016年05月30日 12:25, Jason Wang wrote: On 2016年05月29日 00:37, w...@redhat.com wrote: From: Wei Xu Most stuffs are like ipv4 2 differences between ipv4 and ipv6. 1. Fragment length in ipv4 header includes itself, while it's not included for ipv6, thus means ipv6 can carry a real '65535' payload. 2. IPv6 header does not need calculate header checksum. Signed-off-by: Wei Xu --- hw/net/virtio-net.c | 152 +--- 1 file changed, 144 insertions(+), 8 deletions(-) diff --git a/hw/net/virtio-net.c b/hw/net/virtio-net.c index b3bb63b..cc8cbe4 100644 --- a/hw/net/virtio-net.c +++ b/hw/net/virtio-net.c @@ -53,6 +53,10 @@ /* header length 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, This value affects the performance a lot, and should be tuned carefully, '30'(300us) is the recommended value to pass the WHQL test, '5' can gain 2x netperf throughput with @@ -1724,6 +1728,25 @@ 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 virtio_net_hdr *vhdr, struct ip_header *ip) { @@ -1742,7 +1765,9 @@ static size_t virtio_net_rsc_drain_seg(NetRscChain *chain, NetRscSeg *seg) struct virtio_net_hdr *h; h = (struct virtio_net_hdr *)seg->buf; -virtio_net_rsc_ipv4_checksum(h, seg->unit.ip); +if ((chain->proto == ETH_P_IP) && seg->is_coalesced) { +virtio_net_rsc_ipv4_checksum(h, seg->unit.ip); +} ret = virtio_net_do_receive(seg->nc, seg->buf, seg->size); QTAILQ_REMOVE(&chain->buffers, seg, next); g_free(seg->buf); @@ -1798,7 +1823,7 @@ static void virtio_net_rsc_cache_buf(NetRscChain *chain, NetClientState *nc, hdr_len = chain->n->guest_hdr_len; seg = g_malloc(sizeof(NetRscSeg)); seg->buf = g_malloc(hdr_len + sizeof(struct eth_header)\ - + VIRTIO_NET_MAX_TCP_PAYLOAD); + + sizeof(struct ip6_header) + VIRTIO_NET_MAX_TCP_PAYLOAD); memcpy(seg->buf, buf, size); seg->size = size; seg->packets = 1; @@ -1809,7 +1834,18 @@ 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, @@ -1929,6 +1965,24 @@ 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, @@ -1981,7 +2035,11 @@ static size_t virtio_net_rsc_do_coalesce(NetRscChain *chain, NetCl
Re: [Qemu-devel] [ RFC Patch v6 2/3] virtio-net rsc: support coalescing ipv6 tcp traffic
On 2016年05月29日 00:37, w...@redhat.com wrote: From: Wei Xu Most stuffs are like ipv4 2 differences between ipv4 and ipv6. 1. Fragment length in ipv4 header includes itself, while it's not included for ipv6, thus means ipv6 can carry a real '65535' payload. 2. IPv6 header does not need calculate header checksum. Signed-off-by: Wei Xu --- hw/net/virtio-net.c | 152 +--- 1 file changed, 144 insertions(+), 8 deletions(-) diff --git a/hw/net/virtio-net.c b/hw/net/virtio-net.c index b3bb63b..cc8cbe4 100644 --- a/hw/net/virtio-net.c +++ b/hw/net/virtio-net.c @@ -53,6 +53,10 @@ /* header length 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, This value affects the performance a lot, and should be tuned carefully, '30'(300us) is the recommended value to pass the WHQL test, '5' can gain 2x netperf throughput with @@ -1724,6 +1728,25 @@ 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 virtio_net_hdr *vhdr, struct ip_header *ip) { @@ -1742,7 +1765,9 @@ static size_t virtio_net_rsc_drain_seg(NetRscChain *chain, NetRscSeg *seg) struct virtio_net_hdr *h; h = (struct virtio_net_hdr *)seg->buf; -virtio_net_rsc_ipv4_checksum(h, seg->unit.ip); +if ((chain->proto == ETH_P_IP) && seg->is_coalesced) { +virtio_net_rsc_ipv4_checksum(h, seg->unit.ip); +} ret = virtio_net_do_receive(seg->nc, seg->buf, seg->size); QTAILQ_REMOVE(&chain->buffers, seg, next); g_free(seg->buf); @@ -1798,7 +1823,7 @@ static void virtio_net_rsc_cache_buf(NetRscChain *chain, NetClientState *nc, hdr_len = chain->n->guest_hdr_len; seg = g_malloc(sizeof(NetRscSeg)); seg->buf = g_malloc(hdr_len + sizeof(struct eth_header)\ - + VIRTIO_NET_MAX_TCP_PAYLOAD); + + sizeof(struct ip6_header) + VIRTIO_NET_MAX_TCP_PAYLOAD); memcpy(seg->buf, buf, size); seg->size = size; seg->packets = 1; @@ -1809,7 +1834,18 @@ 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, @@ -1929,6 +1965,24 @@ 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, @@ -1981,7 +2035,11 @@ static size_t virtio_net_rsc_do_coalesce(NetRscChain *chain, NetClientState *nc