Re: [Qemu-devel] [ RFC Patch v6 2/3] virtio-net rsc: support coalescing ipv6 tcp traffic

[Jason Wang <jasowang@redhat.com>]

On 2016年05月29日 00:37, wexu@redhat.com wrote:
> From: Wei Xu <wexu@redhat.com>
>
> 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 <wexu@redhat.com>
> ---
>   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, '300000'(300us) is the recommended
>      value to pass the WHQL test, '50000' 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,
>       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) {
> @@ -2106,13 +2164,82 @@ static size_t virtio_net_rsc_receive4(NetRscChain *chain, 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);

Same issue as ipv4, looks not safe if you analyze header before doing 
sanity check.

> +    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;
>       }
>   
> @@ -2125,8 +2252,13 @@ 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;
> -    chain->gso_type = VIRTIO_NET_HDR_GSO_TCPV4;
> +    if (proto == (uint16_t)ETH_P_IP) {
> +        chain->max_payload = VIRTIO_NET_MAX_IP4_PAYLOAD;
> +        chain->gso_type = VIRTIO_NET_HDR_GSO_TCPV4;
> +    } else {
> +        chain->max_payload = VIRTIO_NET_MAX_IP6_PAYLOAD;
> +        chain->gso_type = VIRTIO_NET_HDR_GSO_TCPV6;
> +    }
>       chain->drain_timer = timer_new_ns(QEMU_CLOCK_VIRTUAL,
>                                         virtio_net_rsc_purge, chain);
>       memset(&chain->stat, 0, sizeof(chain->stat));
> @@ -2158,7 +2290,11 @@ 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);
> +        }
>       }
>   }
>