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

[Jason Wang <jasowang@redhat.com>]

On 03/15/2016 05:17 PM, wexu@redhat.com wrote:
> From: Wei Xu <wexu@redhat.com>
>
> 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' unit.
>
> Signed-off-by: Wei Xu <wexu@redhat.com>
> ---
>  hw/net/virtio-net.c        | 146 ++++++++++++++++++++++++++++++++++++++++-----
>  include/hw/virtio/virtio.h |   5 +-
>  2 files changed, 135 insertions(+), 16 deletions(-)
>
> diff --git a/hw/net/virtio-net.c b/hw/net/virtio-net.c
> index c23b45f..ef61b74 100644
> --- a/hw/net/virtio-net.c
> +++ b/hw/net/virtio-net.c
> @@ -52,9 +52,14 @@
>  #define MAX_IP4_PAYLOAD (65535 - IP4_HDR_SZ)
>  #define MAX_TCP_PAYLOAD 65535
>  
> -/* max payload with virtio header */
> +#define IP6_HDR_SZ (sizeof(struct ip6_header))
> +#define ETH_IP6_HDR_SZ (ETH_HDR_SZ + IP6_HDR_SZ)
> +#define IP6_ADDR_SIZE   32      /* ipv6 saddr + daddr */
> +#define MAX_IP6_PAYLOAD MAX_TCP_PAYLOAD
> +
> +/* ip6 max payload, payload in ipv6 don't include the  header */
>  #define MAX_VIRTIO_PAYLOAD  (sizeof(struct virtio_net_hdr_mrg_rxbuf) \
> -                                + ETH_HDR_SZ + MAX_TCP_PAYLOAD)
> +                                + ETH_IP6_HDR_SZ + MAX_IP6_PAYLOAD)
>  
>  #define IP4_HEADER_LEN 5 /* header lenght value in ip header without option */
>  
> @@ -1722,14 +1727,27 @@ static void virtio_net_rsc_extract_unit4(NetRscChain *chain,
>  {
>      uint16_t ip_hdrlen;
>  
> -    unit->ip = (struct ip_header *)(buf + chain->hdr_size + ETH_HDR_SZ);
> -    ip_hdrlen = ((0xF & unit->ip->ip_ver_len) << 2);
> -    unit->ip_plen = &unit->ip->ip_len;
> -    unit->tcp = (struct tcp_header *)(((uint8_t *)unit->ip) + ip_hdrlen);
> +    unit->u_ip.ip = (struct ip_header *)(buf + chain->hdr_size + ETH_HDR_SZ);
> +    ip_hdrlen = ((0xF & unit->u_ip.ip->ip_ver_len) << 2);
> +    unit->ip_plen = &unit->u_ip.ip->ip_len;
> +    unit->tcp = (struct tcp_header *)(((uint8_t *)unit->u_ip.ip) + ip_hdrlen);
>      unit->tcp_hdrlen = (htons(unit->tcp->th_offset_flags) & 0xF000) >> 10;
>      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)
> +{
> +    unit->u_ip.ip6 = (struct ip6_header *)(buf + chain->hdr_size + ETH_HDR_SZ);

The u_ip seems a little bit redundant. How about use a simple void * and
cast it to ipv4/ipv6 in proto specific callbacks?

The introducing of u_ip leads unnecessary ipv4 codes changes for ipv6
coalescing implementation.

> +    unit->ip_plen = &(unit->u_ip.ip6->ip6_ctlun.ip6_un1.ip6_un1_plen);
> +    unit->tcp = (struct tcp_header *)(((uint8_t *)unit->u_ip.ip6)\
> +                                    + IP6_HDR_SZ);
> +    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;
> @@ -1743,7 +1761,10 @@ 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.u_ip.ip);
> +    }
> +
>      ret = virtio_net_do_receive(seg->nc, seg->buf, seg->size);
>      QTAILQ_REMOVE(&chain->buffers, seg, next);
>      g_free(seg->buf);
> @@ -1807,7 +1828,11 @@ 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);
> +    if (chain->proto == ETH_P_IP) {
> +        virtio_net_rsc_extract_unit4(chain, seg->buf, &seg->unit);
> +    } else {

A switch and a g_assert_not_reached() is better than this.

> +        virtio_net_rsc_extract_unit6(chain, seg->buf, &seg->unit);
> +    }
>  }
>  
>  static int32_t virtio_net_rsc_handle_ack(NetRscChain *chain, NetRscSeg *seg,
> @@ -1930,8 +1955,8 @@ coalesce:
>  static int32_t virtio_net_rsc_coalesce4(NetRscChain *chain, NetRscSeg *seg,
>                          const uint8_t *buf, size_t size, NetRscUnit *unit)
>  {
> -    if ((unit->ip->ip_src ^ seg->unit.ip->ip_src)
> -        || (unit->ip->ip_dst ^ seg->unit.ip->ip_dst)
> +    if ((unit->u_ip.ip->ip_src ^ seg->unit.u_ip.ip->ip_src)
> +        || (unit->u_ip.ip->ip_dst ^ seg->unit.u_ip.ip->ip_dst)
>          || (unit->tcp->th_sport ^ seg->unit.tcp->th_sport)
>          || (unit->tcp->th_dport ^ seg->unit.tcp->th_dport)) {
>          chain->stat.no_match++;
> @@ -1941,6 +1966,22 @@ 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)
> +{
> +    if (memcmp(&unit->u_ip.ip6->ip6_src, &seg->unit.u_ip.ip6->ip6_src,
> +               sizeof(struct in6_address))
> +        || memcmp(&unit->u_ip.ip6->ip6_dst, &seg->unit.u_ip.ip6->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,
> @@ -1983,7 +2024,11 @@ 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) {
> @@ -2082,7 +2127,8 @@ static size_t virtio_net_rsc_receive4(void *opq, NetClientState* nc,
>  
>      chain = (NetRscChain *)opq;
>      virtio_net_rsc_extract_unit4(chain, buf, &unit);
> -    if (RSC_WANT != virtio_net_rsc_sanity_check4(chain, unit.ip, buf, size)) {
> +    if (RSC_WANT != virtio_net_rsc_sanity_check4(chain,
> +                                                 unit.u_ip.ip, buf, size)) {
>          return virtio_net_do_receive(nc, buf, size);
>      }
>  
> @@ -2102,13 +2148,74 @@ 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 *ip, const uint8_t *buf, size_t size)

Indentation is wrong here.

> +{
> +    uint16_t ip_len;
> +
> +    if (size < (chain->hdr_size + ETH_IP6_HDR_SZ + TCP_HDR_SZ)) {
> +        return RSC_BYPASS;
> +    }
> +
> +    if (((0xF0 & ip->ip6_ctlun.ip6_un1.ip6_un1_flow) >> 4)
> +        != IP_HEADER_VERSION_6) {
> +        return RSC_BYPASS;
> +    }
> +
> +    /* Both option and protocol is checked in this */
> +    if (ip->ip6_ctlun.ip6_un1.ip6_un1_nxt != IPPROTO_TCP) {
> +        chain->stat.bypass_not_tcp++;
> +        return RSC_BYPASS;
> +    }
> +
> +    /* Sanity check */

The comment is useless.

> +    ip_len = htons(ip->ip6_ctlun.ip6_un1.ip6_un1_plen);
> +    if (ip_len < TCP_HDR_SZ
> +        || ip_len > (size - chain->hdr_size - ETH_IP6_HDR_SZ)) {
> +        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)
> +{

Rather similar to ipv4 version, need to unify the code.

> +    int32_t ret;
> +    NetRscChain *chain;
> +    NetRscUnit unit;
> +
> +    chain = (NetRscChain *)opq;
> +    virtio_net_rsc_extract_unit6(chain, buf, &unit);
> +    if (RSC_WANT != virtio_net_rsc_sanity_check6(chain,
> +                                                 unit.u_ip.ip6, 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,
> +                        ((chain->hdr_size + ETH_HDR_SZ) + 8), IP6_ADDR_SIZE,
> +                        (chain->hdr_size + ETH_IP6_HDR_SZ), 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;
>  
>      /* Only handle IPv4/6 */
> -    if (proto != (uint16_t)ETH_P_IP) {
> +    if ((proto != (uint16_t)ETH_P_IP) && (proto != (uint16_t)ETH_P_IPV6)) {
>          return NULL;
>      }
>  
> @@ -2121,7 +2228,11 @@ static NetRscChain *virtio_net_rsc_lookup_chain(VirtIONet * n,
>      chain = g_malloc(sizeof(*chain));
>      chain->hdr_size = n->guest_hdr_len;
>      chain->proto = proto;
> -    chain->max_payload = MAX_IP4_PAYLOAD;
> +    if (proto == (uint16_t)ETH_P_IP) {
> +        chain->max_payload = MAX_IP4_PAYLOAD;
> +    } else {
> +        chain->max_payload = MAX_IP6_PAYLOAD;
> +    }
>      chain->drain_timer = timer_new_ns(QEMU_CLOCK_VIRTUAL,
>                                        virtio_net_rsc_purge, chain);
>      memset(&chain->stat, 0, sizeof(chain->stat));
> @@ -2153,7 +2264,12 @@ 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);
> +        }
>      }
>  }
>  
> diff --git a/include/hw/virtio/virtio.h b/include/hw/virtio/virtio.h
> index 3b1dfa8..13d20a4 100644
> --- a/include/hw/virtio/virtio.h
> +++ b/include/hw/virtio/virtio.h
> @@ -170,7 +170,10 @@ typedef struct NetRscStat {
>  
>  /* Rsc unit general info used to checking if can coalescing */
>  typedef struct NetRscUnit {
> -   struct ip_header *ip;   /* ip header */
> +    union {
> +        struct ip_header *ip;   /* ip header */
> +        struct ip6_header *ip6; /* ip6 header */
> +    } u_ip;
>     uint16_t *ip_plen;      /* data len pointer in ip header field */
>     struct tcp_header *tcp; /* tcp header */
>     uint16_t tcp_hdrlen;    /* tcp header len */