Series comparison

-[Qemu-devel] [PULL 00/14] Net patches
+[PULL 0/6] Net patches
-The following changes since commit 6632f6ff96f0537fc34cdc00c760656fc62e23c5:
+The following changes since commit 6b99bb046dd36a6dd5525b8f88c2dcddae49222a:
-  Merge remote-tracking branch 'remotes/famz/tags/block-and-testing-pull-request' into staging (2017-07-17 11:46:36 +0100)
+  Merge tag 'pull-lu-20241122' of https://gitlab.com/rth7680/qemu into staging (2024-11-24 13:39:06 +0000)
-are available in the git repository at:
+are available in the Git repository at:
   https://github.com/jasowang/qemu.git tags/net-pull-request
-for you to fetch changes up to 189ae6bb5ce1f5a322f8691d00fe942ba43dd601:
+for you to fetch changes up to 7987d2be5a8bc3a502f89ba8cf3ac3e09f64d1ce:
-  virtio-net: fix offload ctrl endian (2017-07-17 20:13:56 +0800)
+  virtio-net: Copy received header to buffer (2024-11-25 14:00:51 +0800)
 ----------------------------------------------------------------
+-----BEGIN PGP SIGNATURE-----
-- fix virtio-net ctrl offload endian
+iQEzBAABCAAdFiEEIV1G9IJGaJ7HfzVi7wSWWzmNYhEFAmdEEtgACgkQ7wSWWzmN
-- vnet header support for variou COLO netfilters and compare thread
+YhH5qAgAlKdcx/gFt4EBXtjVq/qbPluEGOQxvcRYLlN90rPLHPgCjAoT5ly3fIv1
 kCgcVZyG8SdGu1n0TzTTS9kg5tL7weQ9xEWwF0oyyuZABgAB7w/wpC8MHSkJFOn
 Tv+2Iab0dJ+e1pw71OMpE/YR5X2xq5vopsSHRtnyGWfRPGswJFwka+f8FS5DSiq
 CeNxADgTkPxJgDmOrNSsAPz8Rns77FAZdvDMqFjx1Lrqm8kPv9jzwOMO+a/2LpC
 t6OkpFzGjiiskPjSnSn/tzo4TfWYoABjJaI7b3vEqmNEJSTAaxltZNtSXZucctEt
 ihnFdjr/wPwGK/5Wu+qGnfDbFNxBw==
 =W4y1
 -----END PGP SIGNATURE-----
 ----------------------------------------------------------------
-Jason Wang (1):
+Akihiko Odaki (6):
-      virtio-net: fix offload ctrl endian
+      net: checksum: Convert data to void *
       virtio-net: Fix size check in dhclient workaround
       virtio-net: Do not check for the queue before RSS
       virtio-net: Fix hash reporting when the queue changes
       virtio-net: Initialize hash reporting values
       virtio-net: Copy received header to buffer
-Michal Privoznik (1):
+ hw/net/virtio-net.c    | 108 +++++++++++++++++++++++++++----------------------
-      virtion-net: Prefer is_power_of_2()
+ include/net/checksum.h |   2 +-
+ net/checksum.c         |   4 +-
-Zhang Chen (12):
+files changed, 63 insertions(+), 51 deletions(-)
       net: Add vnet_hdr_len arguments in NetClientState
       net/net.c: Add vnet_hdr support in SocketReadState
       net/filter-mirror.c: Introduce parameter for filter_send()
       net/filter-mirror.c: Make filter mirror support vnet support.
       net/filter-mirror.c: Add new option to enable vnet support for filter-redirector
       net/colo.c: Make vnet_hdr_len as packet property
       net/colo-compare.c: Introduce parameter for compare_chr_send()
       net/colo-compare.c: Make colo-compare support vnet_hdr_len
       net/colo.c: Add vnet packet parse feature in colo-proxy
       net/colo-compare.c: Add vnet packet's tcp/udp/icmp compare
       net/filter-rewriter.c: Make filter-rewriter support vnet_hdr_len
       docs/colo-proxy.txt: Update colo-proxy usage of net driver with vnet_header
  docs/colo-proxy.txt   | 26 ++++++++++++++++
  hw/net/virtio-net.c   |  4 ++-
  include/net/net.h     | 10 ++++--
  net/colo-compare.c    | 84 ++++++++++++++++++++++++++++++++++++++++++---------
  net/colo.c            |  9 +++---
  net/colo.h            |  4 ++-
  net/filter-mirror.c   | 75 +++++++++++++++++++++++++++++++++++++++++----
  net/filter-rewriter.c | 37 ++++++++++++++++++++++-
  net/net.c             | 37 ++++++++++++++++++++---
  net/socket.c          |  8 ++---
  qemu-options.hx       | 19 ++++++------
 files changed, 265 insertions(+), 48 deletions(-)

-[Qemu-devel] [PULL 01/14] net: Add vnet_hdr_len arguments in NetClientState
+[PULL 1/6] net: checksum: Convert data to void *
-From: Zhang Chen <zhangchen.fnst@cn.fujitsu.com>
+From: Akihiko Odaki <akihiko.odaki@daynix.com>
-Add vnet_hdr_len arguments in NetClientState
+Convert the data parameter of net_checksum_calculate() to void * to
-that make other module get real vnet_hdr_len easily.
+save unnecessary casts for callers.
-Signed-off-by: Zhang Chen <zhangchen.fnst@cn.fujitsu.com>
+Signed-off-by: Akihiko Odaki <akihiko.odaki@daynix.com>
 Reviewed-by: Philippe Mathieu-Daudé <philmd@linaro.org>
 Signed-off-by: Jason Wang <jasowang@redhat.com>
 ---
- include/net/net.h | 1 +
+ include/net/checksum.h | 2 +-
- net/net.c         | 1 +
+ net/checksum.c         | 4 ++--
-files changed, 2 insertions(+)
+files changed, 3 insertions(+), 3 deletions(-)
-diff --git a/include/net/net.h b/include/net/net.h
+diff --git a/include/net/checksum.h b/include/net/checksum.h
 index XXXXXXX..XXXXXXX 100644
---- a/include/net/net.h
+--- a/include/net/checksum.h
-+++ b/include/net/net.h
++++ b/include/net/checksum.h
-@@ -XXX,XX +XXX,XX @@ struct NetClientState {
+@@ -XXX,XX +XXX,XX @@ uint32_t net_checksum_add_cont(int len, uint8_t *buf, int seq);
-     unsigned int queue_index;
+ uint16_t net_checksum_finish(uint32_t sum);
-     unsigned rxfilter_notify_enabled:1;
+ uint16_t net_checksum_tcpudp(uint16_t length, uint16_t proto,
-     int vring_enable;
+                              uint8_t *addrs, uint8_t *buf);
-+    int vnet_hdr_len;
+-void net_checksum_calculate(uint8_t *data, int length, int csum_flag);
-     QTAILQ_HEAD(NetFilterHead, NetFilterState) filters;
++void net_checksum_calculate(void *data, int length, int csum_flag);
- };
+ static inline uint32_t
-diff --git a/net/net.c b/net/net.c
+ net_checksum_add(int len, uint8_t *buf)
 diff --git a/net/checksum.c b/net/checksum.c
 index XXXXXXX..XXXXXXX 100644
---- a/net/net.c
+--- a/net/checksum.c
-+++ b/net/net.c
++++ b/net/checksum.c
-@@ -XXX,XX +XXX,XX @@ void qemu_set_vnet_hdr_len(NetClientState *nc, int len)
+@@ -XXX,XX +XXX,XX @@ uint16_t net_checksum_tcpudp(uint16_t length, uint16_t proto,
      return net_checksum_finish(sum);
  }
 -void net_checksum_calculate(uint8_t *data, int length, int csum_flag)
 +void net_checksum_calculate(void *data, int length, int csum_flag)
  {
      int mac_hdr_len, ip_len;
      struct ip_header *ip;
@@ -XXX,XX +XXX,XX @@ void net_checksum_calculate(uint8_t *data, int length, int csum_flag)
          return;
      }
-+    nc->vnet_hdr_len = len;
+-    ip = (struct ip_header *)(data + mac_hdr_len);
-     nc->info->set_vnet_hdr_len(nc, len);
++    ip = (struct ip_header *)((uint8_t *)data + mac_hdr_len);
- }
+     if (IP_HEADER_VERSION(ip) != IP_HEADER_VERSION_4) {
          return; /* not IPv4 */
 --
-.7.4
+.42.0

-[Qemu-devel] [PULL 13/14] virtion-net: Prefer is_power_of_2()
+[PULL 2/6] virtio-net: Fix size check in dhclient workaround
-From: Michal Privoznik <mprivozn@redhat.com>
+From: Akihiko Odaki <akihiko.odaki@daynix.com>
-We have a function that checks if given number is power of two.
+work_around_broken_dhclient() accesses IP and UDP headers to detect
-We should prefer it instead of expanding the check on our own.
+relevant packets and to calculate checksums, but it didn't check if
 the packet has size sufficient to accommodate them, causing out-of-bound
 access hazards. Fix this by correcting the size requirement.
-Signed-off-by: Michal Privoznik <mprivozn@redhat.com>
+Fixes: 1d41b0c1ec66 ("Work around dhclient brokenness")
 Cc: qemu-stable@nongnu.org
 Signed-off-by: Akihiko Odaki <akihiko.odaki@daynix.com>
 Signed-off-by: Jason Wang <jasowang@redhat.com>
 ---
- hw/net/virtio-net.c | 2 +-
+ hw/net/virtio-net.c | 5 ++++-
-file changed, 1 insertion(+), 1 deletion(-)
+file changed, 4 insertions(+), 1 deletion(-)
 diff --git a/hw/net/virtio-net.c b/hw/net/virtio-net.c
 index XXXXXXX..XXXXXXX 100644
 --- a/hw/net/virtio-net.c
 +++ b/hw/net/virtio-net.c
-@@ -XXX,XX +XXX,XX @@ static void virtio_net_device_realize(DeviceState *dev, Error **errp)
+@@ -XXX,XX +XXX,XX @@ static void virtio_net_hdr_swap(VirtIODevice *vdev, struct virtio_net_hdr *hdr)
-      */
+ static void work_around_broken_dhclient(struct virtio_net_hdr *hdr,
-     if (n->net_conf.rx_queue_size < VIRTIO_NET_RX_QUEUE_MIN_SIZE ||
+                                         uint8_t *buf, size_t size)
-         n->net_conf.rx_queue_size > VIRTQUEUE_MAX_SIZE ||
+ {
--        (n->net_conf.rx_queue_size & (n->net_conf.rx_queue_size - 1))) {
++    size_t csum_size = ETH_HLEN + sizeof(struct ip_header) +
-+        !is_power_of_2(n->net_conf.rx_queue_size)) {
++                       sizeof(struct udp_header);
-         error_setg(errp, "Invalid rx_queue_size (= %" PRIu16 "), "
++
-                    "must be a power of 2 between %d and %d.",
+     if ((hdr->flags & VIRTIO_NET_HDR_F_NEEDS_CSUM) && /* missing csum */
-                    n->net_conf.rx_queue_size, VIRTIO_NET_RX_QUEUE_MIN_SIZE,
+-        (size > 27 && size < 1500) && /* normal sized MTU */
 +        (size >= csum_size && size < 1500) && /* normal sized MTU */
          (buf[12] == 0x08 && buf[13] == 0x00) && /* ethertype == IPv4 */
          (buf[23] == 17) && /* ip.protocol == UDP */
          (buf[34] == 0 && buf[35] == 67)) { /* udp.srcport == bootps */
 --
-.7.4
+.42.0

-[Qemu-devel] [PULL 02/14] net/net.c: Add vnet_hdr support in SocketReadState
+[PULL 3/6] virtio-net: Do not check for the queue before RSS
-From: Zhang Chen <zhangchen.fnst@cn.fujitsu.com>
+From: Akihiko Odaki <akihiko.odaki@daynix.com>
-We add a flag to decide whether net_fill_rstate() need read
+virtio_net_can_receive() checks if the queue is ready, but RSS will
-the vnet_hdr_len or not.
+change the queue to use so, strictly speaking, we may still be able to
 receive the packet even if the queue initially provided is not ready.
 Perform RSS before virtio_net_can_receive() to cover such a case.
-Signed-off-by: Zhang Chen <zhangchen.fnst@cn.fujitsu.com>
+Fixes: 4474e37a5b3a ("virtio-net: implement RX RSS processing")
-Suggested-by: Jason Wang <jasowang@redhat.com>
+Signed-off-by: Akihiko Odaki <akihiko.odaki@daynix.com>
 Signed-off-by: Jason Wang <jasowang@redhat.com>
 ---
- include/net/net.h   |  9 +++++++--
+ hw/net/virtio-net.c | 8 ++++----
- net/colo-compare.c  |  4 ++--
+file changed, 4 insertions(+), 4 deletions(-)
  net/filter-mirror.c |  2 +-
  net/net.c           | 36 ++++++++++++++++++++++++++++++++----
  net/socket.c        |  8 ++++----
 files changed, 46 insertions(+), 13 deletions(-)
-diff --git a/include/net/net.h b/include/net/net.h
+diff --git a/hw/net/virtio-net.c b/hw/net/virtio-net.c
 index XXXXXXX..XXXXXXX 100644
---- a/include/net/net.h
+--- a/hw/net/virtio-net.c
-+++ b/include/net/net.h
++++ b/hw/net/virtio-net.c
-@@ -XXX,XX +XXX,XX @@ typedef struct NICState {
+@@ -XXX,XX +XXX,XX @@ static ssize_t virtio_net_receive_rcu(NetClientState *nc, const uint8_t *buf,
- } NICState;
+     size_t offset, i, guest_offset, j;
+     ssize_t err;
- struct SocketReadState {
--    int state; /* 0 = getting length, 1 = getting data */
+-    if (!virtio_net_can_receive(nc)) {
-+    /* 0 = getting length, 1 = getting vnet header length, 2 = getting data */
+-        return -1;
-+    int state;
+-    }
-+    /* This flag decide whether to read the vnet_hdr_len field */
+-
-+    bool vnet_hdr;
+     if (!no_rss && n->rss_data.enabled && n->rss_data.enabled_software_rss) {
-     uint32_t index;
+         int index = virtio_net_process_rss(nc, buf, size, &extra_hdr);
-     uint32_t packet_len;
+         if (index >= 0) {
-+    uint32_t vnet_hdr_len;
+@@ -XXX,XX +XXX,XX @@ static ssize_t virtio_net_receive_rcu(NetClientState *nc, const uint8_t *buf,
      uint8_t buf[NET_BUFSIZE];
      SocketReadStateFinalize *finalize;
  };
@@ -XXX,XX +XXX,XX @@ ssize_t qemu_deliver_packet_iov(NetClientState *sender,
  void print_net_client(Monitor *mon, NetClientState *nc);
  void hmp_info_network(Monitor *mon, const QDict *qdict);
  void net_socket_rs_init(SocketReadState *rs,
 -                        SocketReadStateFinalize *finalize);
 +                        SocketReadStateFinalize *finalize,
 +                        bool vnet_hdr);
  /* NIC info */
 diff --git a/net/colo-compare.c b/net/colo-compare.c
 index XXXXXXX..XXXXXXX 100644
 --- a/net/colo-compare.c
 +++ b/net/colo-compare.c
@@ -XXX,XX +XXX,XX @@ static void colo_compare_complete(UserCreatable *uc, Error **errp)
          return;
      }
 -    net_socket_rs_init(&s->pri_rs, compare_pri_rs_finalize);
 -    net_socket_rs_init(&s->sec_rs, compare_sec_rs_finalize);
 +    net_socket_rs_init(&s->pri_rs, compare_pri_rs_finalize, false);
 +    net_socket_rs_init(&s->sec_rs, compare_sec_rs_finalize, false);
      g_queue_init(&s->conn_list);
 diff --git a/net/filter-mirror.c b/net/filter-mirror.c
 index XXXXXXX..XXXXXXX 100644
 --- a/net/filter-mirror.c
 +++ b/net/filter-mirror.c
@@ -XXX,XX +XXX,XX @@ static void filter_redirector_setup(NetFilterState *nf, Error **errp)
          }
      }
--    net_socket_rs_init(&s->rs, redirector_rs_finalize);
++    if (!virtio_net_can_receive(nc)) {
-+    net_socket_rs_init(&s->rs, redirector_rs_finalize, false);
++        return -1;
++    }
-     if (s->indev) {
++
-         chr = qemu_chr_find(s->indev);
+     /* hdr_len refers to the header we supply to the guest */
-diff --git a/net/net.c b/net/net.c
+     if (!virtio_net_has_buffers(q, size + n->guest_hdr_len - n->host_hdr_len)) {
-index XXXXXXX..XXXXXXX 100644
+         return 0;
 --- a/net/net.c
 +++ b/net/net.c
@@ -XXX,XX +XXX,XX @@ QemuOptsList qemu_net_opts = {
  };
  void net_socket_rs_init(SocketReadState *rs,
 -                        SocketReadStateFinalize *finalize)
 +                        SocketReadStateFinalize *finalize,
 +                        bool vnet_hdr)
  {
      rs->state = 0;
 +    rs->vnet_hdr = vnet_hdr;
      rs->index = 0;
      rs->packet_len = 0;
 +    rs->vnet_hdr_len = 0;
      memset(rs->buf, 0, sizeof(rs->buf));
      rs->finalize = finalize;
  }
@@ -XXX,XX +XXX,XX @@ int net_fill_rstate(SocketReadState *rs, const uint8_t *buf, int size)
      unsigned int l;
      while (size > 0) {
 -        /* reassemble a packet from the network */
 -        switch (rs->state) { /* 0 = getting length, 1 = getting data */
 +        /* Reassemble a packet from the network.
 +         * 0 = getting length.
 +         * 1 = getting vnet header length.
 +         * 2 = getting data.
 +         */
 +        switch (rs->state) {
          case 0:
              l = 4 - rs->index;
              if (l > size) {
@@ -XXX,XX +XXX,XX @@ int net_fill_rstate(SocketReadState *rs, const uint8_t *buf, int size)
                  /* got length */
                  rs->packet_len = ntohl(*(uint32_t *)rs->buf);
                  rs->index = 0;
 -                rs->state = 1;
 +                if (rs->vnet_hdr) {
 +                    rs->state = 1;
 +                } else {
 +                    rs->state = 2;
 +                    rs->vnet_hdr_len = 0;
 +                }
              }
              break;
          case 1:
 +            l = 4 - rs->index;
 +            if (l > size) {
 +                l = size;
 +            }
 +            memcpy(rs->buf + rs->index, buf, l);
 +            buf += l;
 +            size -= l;
 +            rs->index += l;
 +            if (rs->index == 4) {
 +                /* got vnet header length */
 +                rs->vnet_hdr_len = ntohl(*(uint32_t *)rs->buf);
 +                rs->index = 0;
 +                rs->state = 2;
 +            }
 +            break;
 +        case 2:
              l = rs->packet_len - rs->index;
              if (l > size) {
                  l = size;
 diff --git a/net/socket.c b/net/socket.c
 index XXXXXXX..XXXXXXX 100644
 --- a/net/socket.c
 +++ b/net/socket.c
@@ -XXX,XX +XXX,XX @@ static void net_socket_send(void *opaque)
          closesocket(s->fd);
          s->fd = -1;
 -        net_socket_rs_init(&s->rs, net_socket_rs_finalize);
 +        net_socket_rs_init(&s->rs, net_socket_rs_finalize, false);
          s->nc.link_down = true;
          memset(s->nc.info_str, 0, sizeof(s->nc.info_str));
@@ -XXX,XX +XXX,XX @@ static NetSocketState *net_socket_fd_init_dgram(NetClientState *peer,
      s->fd = fd;
      s->listen_fd = -1;
      s->send_fn = net_socket_send_dgram;
 -    net_socket_rs_init(&s->rs, net_socket_rs_finalize);
 +    net_socket_rs_init(&s->rs, net_socket_rs_finalize, false);
      net_socket_read_poll(s, true);
      /* mcast: save bound address as dst */
@@ -XXX,XX +XXX,XX @@ static NetSocketState *net_socket_fd_init_stream(NetClientState *peer,
      s->fd = fd;
      s->listen_fd = -1;
 -    net_socket_rs_init(&s->rs, net_socket_rs_finalize);
 +    net_socket_rs_init(&s->rs, net_socket_rs_finalize, false);
      /* Disable Nagle algorithm on TCP sockets to reduce latency */
      socket_set_nodelay(fd);
@@ -XXX,XX +XXX,XX @@ static int net_socket_listen_init(NetClientState *peer,
      s->fd = -1;
      s->listen_fd = fd;
      s->nc.link_down = true;
 -    net_socket_rs_init(&s->rs, net_socket_rs_finalize);
 +    net_socket_rs_init(&s->rs, net_socket_rs_finalize, false);
      qemu_set_fd_handler(s->listen_fd, net_socket_accept, NULL, s);
      return 0;
 --
-.7.4
+.42.0

-[Qemu-devel] [PULL 03/14] net/filter-mirror.c: Introduce parameter for filter_send()
+Deleted patch
-From: Zhang Chen <zhangchen.fnst@cn.fujitsu.com>
-This patch change the filter_send() parameter from CharBackend to MirrorState,
-we can get more information like vnet_hdr(We use it to support packet with vnet_header).
-Signed-off-by: Zhang Chen <zhangchen.fnst@cn.fujitsu.com>
-Signed-off-by: Jason Wang <jasowang@redhat.com>
----
- net/filter-mirror.c | 10 +++++-----
-file changed, 5 insertions(+), 5 deletions(-)
-diff --git a/net/filter-mirror.c b/net/filter-mirror.c
-index XXXXXXX..XXXXXXX 100644
---- a/net/filter-mirror.c
-+++ b/net/filter-mirror.c
-@@ -XXX,XX +XXX,XX @@ typedef struct MirrorState {
-     SocketReadState rs;
- } MirrorState;
--static int filter_send(CharBackend *chr_out,
-+static int filter_send(MirrorState *s,
-                        const struct iovec *iov,
-                        int iovcnt)
- {
-@@ -XXX,XX +XXX,XX @@ static int filter_send(CharBackend *chr_out,
-     }
-     len = htonl(size);
--    ret = qemu_chr_fe_write_all(chr_out, (uint8_t *)&len, sizeof(len));
-+    ret = qemu_chr_fe_write_all(&s->chr_out, (uint8_t *)&len, sizeof(len));
-     if (ret != sizeof(len)) {
-         goto err;
-     }
-     buf = g_malloc(size);
-     iov_to_buf(iov, iovcnt, 0, buf, size);
--    ret = qemu_chr_fe_write_all(chr_out, (uint8_t *)buf, size);
-+    ret = qemu_chr_fe_write_all(&s->chr_out, (uint8_t *)buf, size);
-     g_free(buf);
-     if (ret != size) {
-         goto err;
-@@ -XXX,XX +XXX,XX @@ static ssize_t filter_mirror_receive_iov(NetFilterState *nf,
-     MirrorState *s = FILTER_MIRROR(nf);
-     int ret;
--    ret = filter_send(&s->chr_out, iov, iovcnt);
-+    ret = filter_send(s, iov, iovcnt);
-     if (ret) {
-         error_report("filter mirror send failed(%s)", strerror(-ret));
-     }
-@@ -XXX,XX +XXX,XX @@ static ssize_t filter_redirector_receive_iov(NetFilterState *nf,
-     int ret;
-     if (qemu_chr_fe_backend_connected(&s->chr_out)) {
--        ret = filter_send(&s->chr_out, iov, iovcnt);
-+        ret = filter_send(s, iov, iovcnt);
-         if (ret) {
-             error_report("filter redirector send failed(%s)", strerror(-ret));
-         }
---
-.7.4

-[Qemu-devel] [PULL 04/14] net/filter-mirror.c: Make filter mirror support vnet support.
+[PULL 4/6] virtio-net: Fix hash reporting when the queue changes
-From: Zhang Chen <zhangchen.fnst@cn.fujitsu.com>
+From: Akihiko Odaki <akihiko.odaki@daynix.com>
-We add the vnet_hdr_support option for filter-mirror, default is disabled.
+virtio_net_process_rss() fills the values used for hash reporting, but
-If you use virtio-net-pci or other driver needs vnet_hdr, please enable it.
+the values used to be thrown away with a recursive function call if
-You can use it for example:
+the queue changes after RSS. Avoid the function call to keep the values.
 -object filter-mirror,id=m0,netdev=hn0,queue=tx,outdev=mirror0,vnet_hdr_support
-If it has vnet_hdr_support flag, we will change the sending packet format from
+Fixes: a4c960eedcd2 ("virtio-net: Do not write hashes to peer buffer")
-struct {int size; const uint8_t buf[];} to {int size; int vnet_hdr_len; const uint8_t buf[];}.
+Buglink: https://issues.redhat.com/browse/RHEL-59572
-make other module(like colo-compare) know how to parse net packet correctly.
+Signed-off-by: Akihiko Odaki <akihiko.odaki@daynix.com>
 Signed-off-by: Zhang Chen <zhangchen.fnst@cn.fujitsu.com>
 Signed-off-by: Jason Wang <jasowang@redhat.com>
 ---
- net/filter-mirror.c | 42 +++++++++++++++++++++++++++++++++++++++++-
+ hw/net/virtio-net.c | 14 +++++++-------
- qemu-options.hx     |  5 ++---
+file changed, 7 insertions(+), 7 deletions(-)
 files changed, 43 insertions(+), 4 deletions(-)
-diff --git a/net/filter-mirror.c b/net/filter-mirror.c
+diff --git a/hw/net/virtio-net.c b/hw/net/virtio-net.c
 index XXXXXXX..XXXXXXX 100644
---- a/net/filter-mirror.c
+--- a/hw/net/virtio-net.c
-+++ b/net/filter-mirror.c
++++ b/hw/net/virtio-net.c
-@@ -XXX,XX +XXX,XX @@ typedef struct MirrorState {
+@@ -XXX,XX +XXX,XX @@ static int virtio_net_process_rss(NetClientState *nc, const uint8_t *buf,
-     CharBackend chr_in;
+ }
-     CharBackend chr_out;
-     SocketReadState rs;
+ static ssize_t virtio_net_receive_rcu(NetClientState *nc, const uint8_t *buf,
-+    bool vnet_hdr;
+-                                      size_t size, bool no_rss)
- } MirrorState;
++                                      size_t size)
  static int filter_send(MirrorState *s,
                         const struct iovec *iov,
                         int iovcnt)
  {
-+    NetFilterState *nf = NETFILTER(s);
+     VirtIONet *n = qemu_get_nic_opaque(nc);
-     int ret = 0;
+-    VirtIONetQueue *q = virtio_net_get_subqueue(nc);
-     ssize_t size = 0;
++    VirtIONetQueue *q;
-     uint32_t len = 0;
+     VirtIODevice *vdev = VIRTIO_DEVICE(n);
-@@ -XXX,XX +XXX,XX @@ static int filter_send(MirrorState *s,
+     VirtQueueElement *elems[VIRTQUEUE_MAX_SIZE];
-         goto err;
+     size_t lens[VIRTQUEUE_MAX_SIZE];
-     }
+@@ -XXX,XX +XXX,XX @@ static ssize_t virtio_net_receive_rcu(NetClientState *nc, const uint8_t *buf,
+     size_t offset, i, guest_offset, j;
-+    if (s->vnet_hdr) {
+     ssize_t err;
-+        /*
-+         * If vnet_hdr = on, we send vnet header len to make other
+-    if (!no_rss && n->rss_data.enabled && n->rss_data.enabled_software_rss) {
-+         * module(like colo-compare) know how to parse net
++    if (n->rss_data.enabled && n->rss_data.enabled_software_rss) {
-+         * packet correctly.
+         int index = virtio_net_process_rss(nc, buf, size, &extra_hdr);
-+         */
+         if (index >= 0) {
-+        ssize_t vnet_hdr_len;
+-            NetClientState *nc2 =
-+
+-                qemu_get_subqueue(n->nic, index % n->curr_queue_pairs);
-+        vnet_hdr_len = nf->netdev->vnet_hdr_len;
+-            return virtio_net_receive_rcu(nc2, buf, size, true);
-+
++            nc = qemu_get_subqueue(n->nic, index % n->curr_queue_pairs);
 +        len = htonl(vnet_hdr_len);
 +        ret = qemu_chr_fe_write_all(&s->chr_out, (uint8_t *)&len, sizeof(len));
 +        if (ret != sizeof(len)) {
 +            goto err;
 +        }
 +    }
 +
      buf = g_malloc(size);
      iov_to_buf(iov, iovcnt, 0, buf, size);
      ret = qemu_chr_fe_write_all(&s->chr_out, (uint8_t *)buf, size);
@@ -XXX,XX +XXX,XX @@ static void filter_redirector_setup(NetFilterState *nf, Error **errp)
          }
      }
--    net_socket_rs_init(&s->rs, redirector_rs_finalize, false);
+@@ -XXX,XX +XXX,XX @@ static ssize_t virtio_net_receive_rcu(NetClientState *nc, const uint8_t *buf,
-+    net_socket_rs_init(&s->rs, redirector_rs_finalize, s->vnet_hdr);
+         return -1;
      if (s->indev) {
          chr = qemu_chr_find(s->indev);
@@ -XXX,XX +XXX,XX @@ static void filter_mirror_set_outdev(Object *obj,
      }
++    q = virtio_net_get_subqueue(nc);
++
+     /* hdr_len refers to the header we supply to the guest */
+     if (!virtio_net_has_buffers(q, size + n->guest_hdr_len - n->host_hdr_len)) {
+         return 0;
+@@ -XXX,XX +XXX,XX @@ static ssize_t virtio_net_do_receive(NetClientState *nc, const uint8_t *buf,
+ {
+     RCU_READ_LOCK_GUARD();
+-    return virtio_net_receive_rcu(nc, buf, size, false);
++    return virtio_net_receive_rcu(nc, buf, size);
  }
-+static bool filter_mirror_get_vnet_hdr(Object *obj, Error **errp)
+ /*
 +{
 +    MirrorState *s = FILTER_MIRROR(obj);
 +
 +    return s->vnet_hdr;
 +}
 +
 +static void filter_mirror_set_vnet_hdr(Object *obj, bool value, Error **errp)
 +{
 +    MirrorState *s = FILTER_MIRROR(obj);
 +
 +    s->vnet_hdr = value;
 +}
 +
  static char *filter_redirector_get_outdev(Object *obj, Error **errp)
  {
      MirrorState *s = FILTER_REDIRECTOR(obj);
@@ -XXX,XX +XXX,XX @@ static void filter_redirector_set_outdev(Object *obj,
  static void filter_mirror_init(Object *obj)
  {
 +    MirrorState *s = FILTER_MIRROR(obj);
 +
      object_property_add_str(obj, "outdev", filter_mirror_get_outdev,
                              filter_mirror_set_outdev, NULL);
 +
 +    s->vnet_hdr = false;
 +    object_property_add_bool(obj, "vnet_hdr_support",
 +                             filter_mirror_get_vnet_hdr,
 +                             filter_mirror_set_vnet_hdr, NULL);
  }
  static void filter_redirector_init(Object *obj)
 diff --git a/qemu-options.hx b/qemu-options.hx
 index XXXXXXX..XXXXXXX 100644
 --- a/qemu-options.hx
 +++ b/qemu-options.hx
@@ -XXX,XX +XXX,XX @@ queue @var{all|rx|tx} is an option that can be applied to any netfilter.
  @option{tx}: the filter is attached to the transmit queue of the netdev,
               where it will receive packets sent by the netdev.
 -@item -object filter-mirror,id=@var{id},netdev=@var{netdevid},outdev=@var{chardevid}[,queue=@var{all|rx|tx}]
 +@item -object filter-mirror,id=@var{id},netdev=@var{netdevid},outdev=@var{chardevid},queue=@var{all|rx|tx}[,vnet_hdr_support]
 -filter-mirror on netdev @var{netdevid},mirror net packet to chardev
 -@var{chardevid}
 +filter-mirror on netdev @var{netdevid},mirror net packet to chardev@var{chardevid}, if it has the vnet_hdr_support flag, filter-mirror will mirror packet with vnet_hdr_len.
  @item -object filter-redirector,id=@var{id},netdev=@var{netdevid},indev=@var{chardevid},
  outdev=@var{chardevid}[,queue=@var{all|rx|tx}]
 --
-.7.4
+.42.0

-[Qemu-devel] [PULL 05/14] net/filter-mirror.c: Add new option to enable vnet support for filter-redirector
+Deleted patch
-From: Zhang Chen <zhangchen.fnst@cn.fujitsu.com>
-We add the vnet_hdr_support option for filter-redirector, default is disabled.
-If you use virtio-net-pci net driver or other driver needs vnet_hdr, please enable it.
-Because colo-compare or other modules needs the vnet_hdr_len to parse
-packet, we add this new option send the len to others.
-You can use it for example:
--object filter-redirector,id=r0,netdev=hn0,queue=tx,outdev=red0,vnet_hdr_support
-Signed-off-by: Zhang Chen <zhangchen.fnst@cn.fujitsu.com>
-Signed-off-by: Jason Wang <jasowang@redhat.com>
----
- net/filter-mirror.c | 23 +++++++++++++++++++++++
- qemu-options.hx     |  6 +++---
-files changed, 26 insertions(+), 3 deletions(-)
-diff --git a/net/filter-mirror.c b/net/filter-mirror.c
-index XXXXXXX..XXXXXXX 100644
---- a/net/filter-mirror.c
-+++ b/net/filter-mirror.c
-@@ -XXX,XX +XXX,XX @@ static void filter_redirector_set_outdev(Object *obj,
-     s->outdev = g_strdup(value);
- }
-+static bool filter_redirector_get_vnet_hdr(Object *obj, Error **errp)
-+{
-+    MirrorState *s = FILTER_REDIRECTOR(obj);
-+
-+    return s->vnet_hdr;
-+}
-+
-+static void filter_redirector_set_vnet_hdr(Object *obj,
-+                                           bool value,
-+                                           Error **errp)
-+{
-+    MirrorState *s = FILTER_REDIRECTOR(obj);
-+
-+    s->vnet_hdr = value;
-+}
-+
- static void filter_mirror_init(Object *obj)
- {
-     MirrorState *s = FILTER_MIRROR(obj);
-@@ -XXX,XX +XXX,XX @@ static void filter_mirror_init(Object *obj)
- static void filter_redirector_init(Object *obj)
- {
-+    MirrorState *s = FILTER_REDIRECTOR(obj);
-+
-     object_property_add_str(obj, "indev", filter_redirector_get_indev,
-                             filter_redirector_set_indev, NULL);
-     object_property_add_str(obj, "outdev", filter_redirector_get_outdev,
-                             filter_redirector_set_outdev, NULL);
-+
-+    s->vnet_hdr = false;
-+    object_property_add_bool(obj, "vnet_hdr_support",
-+                             filter_redirector_get_vnet_hdr,
-+                             filter_redirector_set_vnet_hdr, NULL);
- }
- static void filter_mirror_fini(Object *obj)
-diff --git a/qemu-options.hx b/qemu-options.hx
-index XXXXXXX..XXXXXXX 100644
---- a/qemu-options.hx
-+++ b/qemu-options.hx
-@@ -XXX,XX +XXX,XX @@ queue @var{all|rx|tx} is an option that can be applied to any netfilter.
- filter-mirror on netdev @var{netdevid},mirror net packet to chardev@var{chardevid}, if it has the vnet_hdr_support flag, filter-mirror will mirror packet with vnet_hdr_len.
--@item -object filter-redirector,id=@var{id},netdev=@var{netdevid},indev=@var{chardevid},
--outdev=@var{chardevid}[,queue=@var{all|rx|tx}]
-+@item -object filter-redirector,id=@var{id},netdev=@var{netdevid},indev=@var{chardevid},outdev=@var{chardevid},queue=@var{all|rx|tx}[,vnet_hdr_support]
- filter-redirector on netdev @var{netdevid},redirect filter's net packet to chardev
--@var{chardevid},and redirect indev's packet to filter.
-+@var{chardevid},and redirect indev's packet to filter.if it has the vnet_hdr_support flag,
-+filter-redirector will redirect packet with vnet_hdr_len.
- Create a filter-redirector we need to differ outdev id from indev id, id can not
- be the same. we can just use indev or outdev, but at least one of indev or outdev
- need to be specified.
---
-.7.4

-[Qemu-devel] [PULL 06/14] net/colo.c: Make vnet_hdr_len as packet property
+Deleted patch
-From: Zhang Chen <zhangchen.fnst@cn.fujitsu.com>
-We can use this property flush and send packet with vnet_hdr_len.
-Signed-off-by: Zhang Chen <zhangchen.fnst@cn.fujitsu.com>
-Signed-off-by: Jason Wang <jasowang@redhat.com>
----
- net/colo-compare.c    | 8 ++++++--
- net/colo.c            | 3 ++-
- net/colo.h            | 4 +++-
- net/filter-rewriter.c | 2 +-
-files changed, 12 insertions(+), 5 deletions(-)
-diff --git a/net/colo-compare.c b/net/colo-compare.c
-index XXXXXXX..XXXXXXX 100644
---- a/net/colo-compare.c
-+++ b/net/colo-compare.c
-@@ -XXX,XX +XXX,XX @@ static int packet_enqueue(CompareState *s, int mode)
-     Connection *conn;
-     if (mode == PRIMARY_IN) {
--        pkt = packet_new(s->pri_rs.buf, s->pri_rs.packet_len);
-+        pkt = packet_new(s->pri_rs.buf,
-+                         s->pri_rs.packet_len,
-+                         s->pri_rs.vnet_hdr_len);
-     } else {
--        pkt = packet_new(s->sec_rs.buf, s->sec_rs.packet_len);
-+        pkt = packet_new(s->sec_rs.buf,
-+                         s->sec_rs.packet_len,
-+                         s->sec_rs.vnet_hdr_len);
-     }
-     if (parse_packet_early(pkt)) {
-diff --git a/net/colo.c b/net/colo.c
-index XXXXXXX..XXXXXXX 100644
---- a/net/colo.c
-+++ b/net/colo.c
-@@ -XXX,XX +XXX,XX @@ void connection_destroy(void *opaque)
-     g_slice_free(Connection, conn);
- }
--Packet *packet_new(const void *data, int size)
-+Packet *packet_new(const void *data, int size, int vnet_hdr_len)
- {
-     Packet *pkt = g_slice_new(Packet);
-     pkt->data = g_memdup(data, size);
-     pkt->size = size;
-     pkt->creation_ms = qemu_clock_get_ms(QEMU_CLOCK_HOST);
-+    pkt->vnet_hdr_len = vnet_hdr_len;
-     return pkt;
- }
-diff --git a/net/colo.h b/net/colo.h
-index XXXXXXX..XXXXXXX 100644
---- a/net/colo.h
-+++ b/net/colo.h
-@@ -XXX,XX +XXX,XX @@ typedef struct Packet {
-     int size;
-     /* Time of packet creation, in wall clock ms */
-     int64_t creation_ms;
-+    /* Get vnet_hdr_len from filter */
-+    uint32_t vnet_hdr_len;
- } Packet;
- typedef struct ConnectionKey {
-@@ -XXX,XX +XXX,XX @@ Connection *connection_get(GHashTable *connection_track_table,
-                            ConnectionKey *key,
-                            GQueue *conn_list);
- void connection_hashtable_reset(GHashTable *connection_track_table);
--Packet *packet_new(const void *data, int size);
-+Packet *packet_new(const void *data, int size, int vnet_hdr_len);
- void packet_destroy(void *opaque, void *user_data);
- #endif /* QEMU_COLO_PROXY_H */
-diff --git a/net/filter-rewriter.c b/net/filter-rewriter.c
-index XXXXXXX..XXXXXXX 100644
---- a/net/filter-rewriter.c
-+++ b/net/filter-rewriter.c
-@@ -XXX,XX +XXX,XX @@ static ssize_t colo_rewriter_receive_iov(NetFilterState *nf,
-     char *buf = g_malloc0(size);
-     iov_to_buf(iov, iovcnt, 0, buf, size);
--    pkt = packet_new(buf, size);
-+    pkt = packet_new(buf, size, 0);
-     g_free(buf);
-     /*
---
-.7.4

-[Qemu-devel] [PULL 14/14] virtio-net: fix offload ctrl endian
+[PULL 5/6] virtio-net: Initialize hash reporting values
-Spec said offloads should be le64, so use virtio_ldq_p() to guarantee
+From: Akihiko Odaki <akihiko.odaki@daynix.com>
 valid endian.
-Fixes: 644c98587d4c ("virtio-net: dynamic network offloads configuration")
+The specification says hash_report should be set to
-Cc: qemu-stable@nongnu.org
+VIRTIO_NET_HASH_REPORT_NONE if VIRTIO_NET_F_HASH_REPORT is negotiated
-Cc: Dmitry Fleytman <dfleytma@redhat.com>
+but not configured with VIRTIO_NET_CTRL_MQ_RSS_CONFIG. However,
 virtio_net_receive_rcu() instead wrote out the content of the extra_hdr
 variable, which is not uninitialized in such a case.
 Fix this by zeroing the extra_hdr.
 Fixes: e22f0603fb2f ("virtio-net: reference implementation of hash report")
 Signed-off-by: Akihiko Odaki <akihiko.odaki@daynix.com>
 Reviewed-by: Philippe Mathieu-Daudé <philmd@linaro.org>
 Signed-off-by: Jason Wang <jasowang@redhat.com>
 ---
  hw/net/virtio-net.c | 2 ++
 file changed, 2 insertions(+)
 diff --git a/hw/net/virtio-net.c b/hw/net/virtio-net.c
 index XXXXXXX..XXXXXXX 100644
 --- a/hw/net/virtio-net.c
 +++ b/hw/net/virtio-net.c
-@@ -XXX,XX +XXX,XX @@ static int virtio_net_handle_offloads(VirtIONet *n, uint8_t cmd,
+@@ -XXX,XX +XXX,XX @@ static ssize_t virtio_net_receive_rcu(NetClientState *nc, const uint8_t *buf,
-     if (cmd == VIRTIO_NET_CTRL_GUEST_OFFLOADS_SET) {
+     size_t offset, i, guest_offset, j;
-         uint64_t supported_offloads;
+     ssize_t err;
-+        offloads = virtio_ldq_p(vdev, &offloads);
++    memset(&extra_hdr, 0, sizeof(extra_hdr));
 +
-         if (!n->has_vnet_hdr) {
+     if (n->rss_data.enabled && n->rss_data.enabled_software_rss) {
-             return VIRTIO_NET_ERR;
+         int index = virtio_net_process_rss(nc, buf, size, &extra_hdr);
-         }
+         if (index >= 0) {
 --
-.7.4
+.42.0

-[Qemu-devel] [PULL 07/14] net/colo-compare.c: Introduce parameter for compare_chr_send()
+[PULL 6/6] virtio-net: Copy received header to buffer
-From: Zhang Chen <zhangchen.fnst@cn.fujitsu.com>
+From: Akihiko Odaki <akihiko.odaki@daynix.com>
-This patch change the compare_chr_send() parameter from CharBackend to CompareState,
+receive_header() used to cast the const qualifier of the pointer to the
-we can get more information like vnet_hdr(We use it to support packet with vnet_header).
+received packet away to modify the header. Avoid this by copying the
 received header to buffer.
-Signed-off-by: Zhang Chen <zhangchen.fnst@cn.fujitsu.com>
+Signed-off-by: Akihiko Odaki <akihiko.odaki@daynix.com>
 Signed-off-by: Jason Wang <jasowang@redhat.com>
 ---
- net/colo-compare.c | 14 +++++++-------
+ hw/net/virtio-net.c | 85 ++++++++++++++++++++++++---------------------
-file changed, 7 insertions(+), 7 deletions(-)
+file changed, 46 insertions(+), 39 deletions(-)
-diff --git a/net/colo-compare.c b/net/colo-compare.c
+diff --git a/hw/net/virtio-net.c b/hw/net/virtio-net.c
 index XXXXXXX..XXXXXXX 100644
---- a/net/colo-compare.c
+--- a/hw/net/virtio-net.c
-+++ b/net/colo-compare.c
++++ b/hw/net/virtio-net.c
-@@ -XXX,XX +XXX,XX @@ enum {
+@@ -XXX,XX +XXX,XX @@ static void virtio_net_hdr_swap(VirtIODevice *vdev, struct virtio_net_hdr *hdr)
-     SECONDARY_IN,
+  * cache.
- };
+  */
+ static void work_around_broken_dhclient(struct virtio_net_hdr *hdr,
--static int compare_chr_send(CharBackend *out,
+-                                        uint8_t *buf, size_t size)
-+static int compare_chr_send(CompareState *s,
++                                        size_t *hdr_len, const uint8_t *buf,
-                             const uint8_t *buf,
++                                        size_t buf_size, size_t *buf_offset)
-                             uint32_t size);
+ {
+     size_t csum_size = ETH_HLEN + sizeof(struct ip_header) +
-@@ -XXX,XX +XXX,XX @@ static void colo_compare_connection(void *opaque, void *user_data)
+                        sizeof(struct udp_header);
-         }
++    buf += *buf_offset;
-         if (result) {
++    buf_size -= *buf_offset;
--            ret = compare_chr_send(&s->chr_out, pkt->data, pkt->size);
++
-+            ret = compare_chr_send(s, pkt->data, pkt->size);
+     if ((hdr->flags & VIRTIO_NET_HDR_F_NEEDS_CSUM) && /* missing csum */
-             if (ret < 0) {
+-        (size >= csum_size && size < 1500) && /* normal sized MTU */
-                 error_report("colo_send_primary_packet failed");
++        (buf_size >= csum_size && buf_size < 1500) && /* normal sized MTU */
-             }
+         (buf[12] == 0x08 && buf[13] == 0x00) && /* ethertype == IPv4 */
-@@ -XXX,XX +XXX,XX @@ static void colo_compare_connection(void *opaque, void *user_data)
+         (buf[23] == 17) && /* ip.protocol == UDP */
          (buf[34] == 0 && buf[35] == 67)) { /* udp.srcport == bootps */
 -        net_checksum_calculate(buf, size, CSUM_UDP);
 +        memcpy((uint8_t *)hdr + *hdr_len, buf, csum_size);
 +        net_checksum_calculate((uint8_t *)hdr + *hdr_len, csum_size, CSUM_UDP);
          hdr->flags &= ~VIRTIO_NET_HDR_F_NEEDS_CSUM;
 +        *hdr_len += csum_size;
 +        *buf_offset += csum_size;
      }
  }
--static int compare_chr_send(CharBackend *out,
+-static void receive_header(VirtIONet *n, const struct iovec *iov, int iov_cnt,
-+static int compare_chr_send(CompareState *s,
+-                           const void *buf, size_t size)
-                             const uint8_t *buf,
++static size_t receive_header(VirtIONet *n, struct virtio_net_hdr *hdr,
-                             uint32_t size)
++                             const void *buf, size_t buf_size,
 +                             size_t *buf_offset)
  {
-@@ -XXX,XX +XXX,XX @@ static int compare_chr_send(CharBackend *out,
+-    if (n->has_vnet_hdr) {
-         return 0;
+-        /* FIXME this cast is evil */
 -        void *wbuf = (void *)buf;
 -        work_around_broken_dhclient(wbuf, wbuf + n->host_hdr_len,
 -                                    size - n->host_hdr_len);
 +    size_t hdr_len = n->guest_hdr_len;
 -        if (n->needs_vnet_hdr_swap) {
 -            virtio_net_hdr_swap(VIRTIO_DEVICE(n), wbuf);
 -        }
 -        iov_from_buf(iov, iov_cnt, 0, buf, sizeof(struct virtio_net_hdr));
 -    } else {
 -        struct virtio_net_hdr hdr = {
 -            .flags = 0,
 -            .gso_type = VIRTIO_NET_HDR_GSO_NONE
 -        };
 -        iov_from_buf(iov, iov_cnt, 0, &hdr, sizeof hdr);
 +    memcpy(hdr, buf, sizeof(struct virtio_net_hdr));
 +
 +    *buf_offset = n->host_hdr_len;
 +    work_around_broken_dhclient(hdr, &hdr_len, buf, buf_size, buf_offset);
 +
 +    if (n->needs_vnet_hdr_swap) {
 +        virtio_net_hdr_swap(VIRTIO_DEVICE(n), hdr);
      }
++
--    ret = qemu_chr_fe_write_all(out, (uint8_t *)&len, sizeof(len));
++    return hdr_len;
-+    ret = qemu_chr_fe_write_all(&s->chr_out, (uint8_t *)&len, sizeof(len));
+ }
-     if (ret != sizeof(len)) {
-         goto err;
+ static int receive_filter(VirtIONet *n, const uint8_t *buf, int size)
@@ -XXX,XX +XXX,XX @@ static int virtio_net_process_rss(NetClientState *nc, const uint8_t *buf,
      return (index == new_index) ? -1 : new_index;
  }
 +typedef struct Header {
 +    struct virtio_net_hdr_v1_hash virtio_net;
 +    struct eth_header eth;
 +    struct ip_header ip;
 +    struct udp_header udp;
 +} Header;
 +
  static ssize_t virtio_net_receive_rcu(NetClientState *nc, const uint8_t *buf,
                                        size_t size)
  {
@@ -XXX,XX +XXX,XX @@ static ssize_t virtio_net_receive_rcu(NetClientState *nc, const uint8_t *buf,
      VirtQueueElement *elems[VIRTQUEUE_MAX_SIZE];
      size_t lens[VIRTQUEUE_MAX_SIZE];
      struct iovec mhdr_sg[VIRTQUEUE_MAX_SIZE];
 -    struct virtio_net_hdr_v1_hash extra_hdr;
 +    Header hdr;
      unsigned mhdr_cnt = 0;
      size_t offset, i, guest_offset, j;
      ssize_t err;
 -    memset(&extra_hdr, 0, sizeof(extra_hdr));
 +    memset(&hdr.virtio_net, 0, sizeof(hdr.virtio_net));
      if (n->rss_data.enabled && n->rss_data.enabled_software_rss) {
 -        int index = virtio_net_process_rss(nc, buf, size, &extra_hdr);
 +        int index = virtio_net_process_rss(nc, buf, size, &hdr.virtio_net);
          if (index >= 0) {
              nc = qemu_get_subqueue(n->nic, index % n->curr_queue_pairs);
          }
@@ -XXX,XX +XXX,XX @@ static ssize_t virtio_net_receive_rcu(NetClientState *nc, const uint8_t *buf,
              if (n->mergeable_rx_bufs) {
                  mhdr_cnt = iov_copy(mhdr_sg, ARRAY_SIZE(mhdr_sg),
                                      sg, elem->in_num,
 -                                    offsetof(typeof(extra_hdr), hdr.num_buffers),
 -                                    sizeof(extra_hdr.hdr.num_buffers));
 +                                    offsetof(typeof(hdr),
 +                                             virtio_net.hdr.num_buffers),
 +                                    sizeof(hdr.virtio_net.hdr.num_buffers));
              }
 -            receive_header(n, sg, elem->in_num, buf, size);
 -            if (n->rss_data.populate_hash) {
 -                offset = offsetof(typeof(extra_hdr), hash_value);
 -                iov_from_buf(sg, elem->in_num, offset,
 -                             (char *)&extra_hdr + offset,
 -                             sizeof(extra_hdr.hash_value) +
 -                             sizeof(extra_hdr.hash_report));
 -            }
 -            offset = n->host_hdr_len;
 -            total += n->guest_hdr_len;
 -            guest_offset = n->guest_hdr_len;
 +            guest_offset = n->has_vnet_hdr ?
 +                           receive_header(n, (struct virtio_net_hdr *)&hdr,
 +                                          buf, size, &offset) :
 +                           n->guest_hdr_len;
 +
 +            iov_from_buf(sg, elem->in_num, 0, &hdr, guest_offset);
 +            total += guest_offset;
          } else {
              guest_offset = 0;
          }
@@ -XXX,XX +XXX,XX @@ static ssize_t virtio_net_receive_rcu(NetClientState *nc, const uint8_t *buf,
      }
--    ret = qemu_chr_fe_write_all(out, (uint8_t *)buf, size);
+     if (mhdr_cnt) {
-+    ret = qemu_chr_fe_write_all(&s->chr_out, (uint8_t *)buf, size);
+-        virtio_stw_p(vdev, &extra_hdr.hdr.num_buffers, i);
-     if (ret != size) {
++        virtio_stw_p(vdev, &hdr.virtio_net.hdr.num_buffers, i);
-         goto err;
+         iov_from_buf(mhdr_sg, mhdr_cnt,
 ,
 -                     &extra_hdr.hdr.num_buffers,
 -                     sizeof extra_hdr.hdr.num_buffers);
 +                     &hdr.virtio_net.hdr.num_buffers,
 +                     sizeof hdr.virtio_net.hdr.num_buffers);
      }
-@@ -XXX,XX +XXX,XX @@ static void compare_pri_rs_finalize(SocketReadState *pri_rs)
+     for (j = 0; j < i; j++) {
      if (packet_enqueue(s, PRIMARY_IN)) {
          trace_colo_compare_main("primary: unsupported packet in");
 -        compare_chr_send(&s->chr_out, pri_rs->buf, pri_rs->packet_len);
 +        compare_chr_send(s, pri_rs->buf, pri_rs->packet_len);
      } else {
          /* compare connection */
          g_queue_foreach(&s->conn_list, colo_compare_connection, s);
@@ -XXX,XX +XXX,XX @@ static void colo_flush_packets(void *opaque, void *user_data)
      while (!g_queue_is_empty(&conn->primary_list)) {
          pkt = g_queue_pop_head(&conn->primary_list);
 -        compare_chr_send(&s->chr_out, pkt->data, pkt->size);
 +        compare_chr_send(s, pkt->data, pkt->size);
          packet_destroy(pkt, NULL);
      }
      while (!g_queue_is_empty(&conn->secondary_list)) {
 --
-.7.4
+.42.0

-[Qemu-devel] [PULL 08/14] net/colo-compare.c: Make colo-compare support vnet_hdr_len
+Deleted patch
-From: Zhang Chen <zhangchen.fnst@cn.fujitsu.com>
-We add the vnet_hdr_support option for colo-compare, default is disabled.
-If you use virtio-net-pci or other driver needs vnet_hdr, please enable it.
-You can use it for example:
--object colo-compare,id=comp0,primary_in=compare0-0,secondary_in=compare1,outdev=compare_out0,vnet_hdr_support
-COLO-compare can get vnet header length from filter,
-Add vnet_hdr_len to struct packet and output packet with
-the vnet_hdr_len.
-Signed-off-by: Zhang Chen <zhangchen.fnst@cn.fujitsu.com>
-Signed-off-by: Jason Wang <jasowang@redhat.com>
----
- net/colo-compare.c | 60 +++++++++++++++++++++++++++++++++++++++++++++++-------
- qemu-options.hx    |  4 ++--
-files changed, 55 insertions(+), 9 deletions(-)
-diff --git a/net/colo-compare.c b/net/colo-compare.c
-index XXXXXXX..XXXXXXX 100644
---- a/net/colo-compare.c
-+++ b/net/colo-compare.c
-@@ -XXX,XX +XXX,XX @@ typedef struct CompareState {
-     CharBackend chr_out;
-     SocketReadState pri_rs;
-     SocketReadState sec_rs;
-+    bool vnet_hdr;
-     /* connection list: the connections belonged to this NIC could be found
-      * in this list.
-@@ -XXX,XX +XXX,XX @@ enum {
- static int compare_chr_send(CompareState *s,
-                             const uint8_t *buf,
--                            uint32_t size);
-+                            uint32_t size,
-+                            uint32_t vnet_hdr_len);
- static gint seq_sorter(Packet *a, Packet *b, gpointer data)
- {
-@@ -XXX,XX +XXX,XX @@ static void colo_compare_connection(void *opaque, void *user_data)
-         }
-         if (result) {
--            ret = compare_chr_send(s, pkt->data, pkt->size);
-+            ret = compare_chr_send(s,
-+                                   pkt->data,
-+                                   pkt->size,
-+                                   pkt->vnet_hdr_len);
-             if (ret < 0) {
-                 error_report("colo_send_primary_packet failed");
-             }
-@@ -XXX,XX +XXX,XX @@ static void colo_compare_connection(void *opaque, void *user_data)
- static int compare_chr_send(CompareState *s,
-                             const uint8_t *buf,
--                            uint32_t size)
-+                            uint32_t size,
-+                            uint32_t vnet_hdr_len)
- {
-     int ret = 0;
-     uint32_t len = htonl(size);
-@@ -XXX,XX +XXX,XX @@ static int compare_chr_send(CompareState *s,
-         goto err;
-     }
-+    if (s->vnet_hdr) {
-+        /*
-+         * We send vnet header len make other module(like filter-redirector)
-+         * know how to parse net packet correctly.
-+         */
-+        len = htonl(vnet_hdr_len);
-+        ret = qemu_chr_fe_write_all(&s->chr_out, (uint8_t *)&len, sizeof(len));
-+        if (ret != sizeof(len)) {
-+            goto err;
-+        }
-+    }
-+
-     ret = qemu_chr_fe_write_all(&s->chr_out, (uint8_t *)buf, size);
-     if (ret != size) {
-         goto err;
-@@ -XXX,XX +XXX,XX @@ static void compare_set_outdev(Object *obj, const char *value, Error **errp)
-     s->outdev = g_strdup(value);
- }
-+static bool compare_get_vnet_hdr(Object *obj, Error **errp)
-+{
-+    CompareState *s = COLO_COMPARE(obj);
-+
-+    return s->vnet_hdr;
-+}
-+
-+static void compare_set_vnet_hdr(Object *obj,
-+                                 bool value,
-+                                 Error **errp)
-+{
-+    CompareState *s = COLO_COMPARE(obj);
-+
-+    s->vnet_hdr = value;
-+}
-+
- static void compare_pri_rs_finalize(SocketReadState *pri_rs)
- {
-     CompareState *s = container_of(pri_rs, CompareState, pri_rs);
-     if (packet_enqueue(s, PRIMARY_IN)) {
-         trace_colo_compare_main("primary: unsupported packet in");
--        compare_chr_send(s, pri_rs->buf, pri_rs->packet_len);
-+        compare_chr_send(s,
-+                         pri_rs->buf,
-+                         pri_rs->packet_len,
-+                         pri_rs->vnet_hdr_len);
-     } else {
-         /* compare connection */
-         g_queue_foreach(&s->conn_list, colo_compare_connection, s);
-@@ -XXX,XX +XXX,XX @@ static void colo_compare_complete(UserCreatable *uc, Error **errp)
-         return;
-     }
--    net_socket_rs_init(&s->pri_rs, compare_pri_rs_finalize, false);
--    net_socket_rs_init(&s->sec_rs, compare_sec_rs_finalize, false);
-+    net_socket_rs_init(&s->pri_rs, compare_pri_rs_finalize, s->vnet_hdr);
-+    net_socket_rs_init(&s->sec_rs, compare_sec_rs_finalize, s->vnet_hdr);
-     g_queue_init(&s->conn_list);
-@@ -XXX,XX +XXX,XX @@ static void colo_flush_packets(void *opaque, void *user_data)
-     while (!g_queue_is_empty(&conn->primary_list)) {
-         pkt = g_queue_pop_head(&conn->primary_list);
--        compare_chr_send(s, pkt->data, pkt->size);
-+        compare_chr_send(s,
-+                         pkt->data,
-+                         pkt->size,
-+                         pkt->vnet_hdr_len);
-         packet_destroy(pkt, NULL);
-     }
-     while (!g_queue_is_empty(&conn->secondary_list)) {
-@@ -XXX,XX +XXX,XX @@ static void colo_compare_class_init(ObjectClass *oc, void *data)
- static void colo_compare_init(Object *obj)
- {
-+    CompareState *s = COLO_COMPARE(obj);
-+
-     object_property_add_str(obj, "primary_in",
-                             compare_get_pri_indev, compare_set_pri_indev,
-                             NULL);
-@@ -XXX,XX +XXX,XX @@ static void colo_compare_init(Object *obj)
-     object_property_add_str(obj, "outdev",
-                             compare_get_outdev, compare_set_outdev,
-                             NULL);
-+
-+    s->vnet_hdr = false;
-+    object_property_add_bool(obj, "vnet_hdr_support", compare_get_vnet_hdr,
-+                             compare_set_vnet_hdr, NULL);
- }
- static void colo_compare_finalize(Object *obj)
-diff --git a/qemu-options.hx b/qemu-options.hx
-index XXXXXXX..XXXXXXX 100644
---- a/qemu-options.hx
-+++ b/qemu-options.hx
-@@ -XXX,XX +XXX,XX @@ Dump the network traffic on netdev @var{dev} to the file specified by
- The file format is libpcap, so it can be analyzed with tools such as tcpdump
- or Wireshark.
--@item -object colo-compare,id=@var{id},primary_in=@var{chardevid},secondary_in=@var{chardevid},
--outdev=@var{chardevid}
-+@item -object colo-compare,id=@var{id},primary_in=@var{chardevid},secondary_in=@var{chardevid},outdev=@var{chardevid}[,vnet_hdr_support]
- Colo-compare gets packet from primary_in@var{chardevid} and secondary_in@var{chardevid}, than compare primary packet with
- secondary packet. If the packets are same, we will output primary
- packet to outdev@var{chardevid}, else we will notify colo-frame
- do checkpoint and send primary packet to outdev@var{chardevid}.
-+if it has the vnet_hdr_support flag, colo compare will send/recv packet with vnet_hdr_len.
- we must use it with the help of filter-mirror and filter-redirector.
---
-.7.4

-[Qemu-devel] [PULL 09/14] net/colo.c: Add vnet packet parse feature in colo-proxy
+Deleted patch
-From: Zhang Chen <zhangchen.fnst@cn.fujitsu.com>
-Make colo-compare and filter-rewriter can parse vnet packet.
-Signed-off-by: Zhang Chen <zhangchen.fnst@cn.fujitsu.com>
-Signed-off-by: Jason Wang <jasowang@redhat.com>
----
- net/colo.c | 6 +++---
-file changed, 3 insertions(+), 3 deletions(-)
-diff --git a/net/colo.c b/net/colo.c
-index XXXXXXX..XXXXXXX 100644
---- a/net/colo.c
-+++ b/net/colo.c
-@@ -XXX,XX +XXX,XX @@ int parse_packet_early(Packet *pkt)
- {
-     int network_length;
-     static const uint8_t vlan[] = {0x81, 0x00};
--    uint8_t *data = pkt->data;
-+    uint8_t *data = pkt->data + pkt->vnet_hdr_len;
-     uint16_t l3_proto;
-     ssize_t l2hdr_len = eth_get_l2_hdr_length(data);
--    if (pkt->size < ETH_HLEN) {
-+    if (pkt->size < ETH_HLEN + pkt->vnet_hdr_len) {
-         trace_colo_proxy_main("pkt->size < ETH_HLEN");
-         return 1;
-     }
-@@ -XXX,XX +XXX,XX @@ int parse_packet_early(Packet *pkt)
-     }
-     network_length = pkt->ip->ip_hl * 4;
--    if (pkt->size < l2hdr_len + network_length) {
-+    if (pkt->size < l2hdr_len + network_length + pkt->vnet_hdr_len) {
-         trace_colo_proxy_main("pkt->size < network_header + network_length");
-         return 1;
-     }
---
-.7.4

-[Qemu-devel] [PULL 10/14] net/colo-compare.c: Add vnet packet's tcp/udp/icmp compare
+Deleted patch
-From: Zhang Chen <zhangchen.fnst@cn.fujitsu.com>
-COLO-Proxy just focus on packet payload, so we skip vnet header.
-Signed-off-by: Zhang Chen <zhangchen.fnst@cn.fujitsu.com>
-Signed-off-by: Jason Wang <jasowang@redhat.com>
----
- net/colo-compare.c | 8 ++++++--
-file changed, 6 insertions(+), 2 deletions(-)
-diff --git a/net/colo-compare.c b/net/colo-compare.c
-index XXXXXXX..XXXXXXX 100644
---- a/net/colo-compare.c
-+++ b/net/colo-compare.c
-@@ -XXX,XX +XXX,XX @@ static int colo_packet_compare_common(Packet *ppkt, Packet *spkt, int offset)
-                                    sec_ip_src, sec_ip_dst);
-     }
-+    offset = ppkt->vnet_hdr_len + offset;
-+
-     if (ppkt->size == spkt->size) {
--        return memcmp(ppkt->data + offset, spkt->data + offset,
-+        return memcmp(ppkt->data + offset,
-+                      spkt->data + offset,
-                       spkt->size - offset);
-     } else {
-         trace_colo_compare_main("Net packet size are not the same");
-@@ -XXX,XX +XXX,XX @@ static int colo_packet_compare_tcp(Packet *spkt, Packet *ppkt)
-      */
-     if (ptcp->th_off > 5) {
-         ptrdiff_t tcp_offset;
-+
-         tcp_offset = ppkt->transport_header - (uint8_t *)ppkt->data
--                     + (ptcp->th_off * 4);
-+                     + (ptcp->th_off * 4) - ppkt->vnet_hdr_len;
-         res = colo_packet_compare_common(ppkt, spkt, tcp_offset);
-     } else if (ptcp->th_sum == stcp->th_sum) {
-         res = colo_packet_compare_common(ppkt, spkt, ETH_HLEN);
---
-.7.4

-[Qemu-devel] [PULL 11/14] net/filter-rewriter.c: Make filter-rewriter support vnet_hdr_len
+Deleted patch
-From: Zhang Chen <zhangchen.fnst@cn.fujitsu.com>
-We add the vnet_hdr_support option for filter-rewriter, default is disabled.
-If you use virtio-net-pci or other driver needs vnet_hdr, please enable it.
-You can use it for example:
--object filter-rewriter,id=rew0,netdev=hn0,queue=all,vnet_hdr_support
-We get the vnet_hdr_len from NetClientState that make us
-parse net packet correctly.
-Signed-off-by: Zhang Chen <zhangchen.fnst@cn.fujitsu.com>
-Signed-off-by: Jason Wang <jasowang@redhat.com>
----
- net/filter-rewriter.c | 37 ++++++++++++++++++++++++++++++++++++-
- qemu-options.hx       |  4 ++--
-files changed, 38 insertions(+), 3 deletions(-)
-diff --git a/net/filter-rewriter.c b/net/filter-rewriter.c
-index XXXXXXX..XXXXXXX 100644
---- a/net/filter-rewriter.c
-+++ b/net/filter-rewriter.c
-@@ -XXX,XX +XXX,XX @@
- #include "qemu-common.h"
- #include "qapi/error.h"
- #include "qapi/qmp/qerror.h"
-+#include "qemu/error-report.h"
- #include "qapi-visit.h"
- #include "qom/object.h"
- #include "qemu/main-loop.h"
-@@ -XXX,XX +XXX,XX @@ typedef struct RewriterState {
-     NetQueue *incoming_queue;
-     /* hashtable to save connection */
-     GHashTable *connection_track_table;
-+    bool vnet_hdr;
- } RewriterState;
- static void filter_rewriter_flush(NetFilterState *nf)
-@@ -XXX,XX +XXX,XX @@ static ssize_t colo_rewriter_receive_iov(NetFilterState *nf,
-     ConnectionKey key;
-     Packet *pkt;
-     ssize_t size = iov_size(iov, iovcnt);
-+    ssize_t vnet_hdr_len = 0;
-     char *buf = g_malloc0(size);
-     iov_to_buf(iov, iovcnt, 0, buf, size);
--    pkt = packet_new(buf, size, 0);
-+
-+    if (s->vnet_hdr) {
-+        vnet_hdr_len = nf->netdev->vnet_hdr_len;
-+    }
-+
-+    pkt = packet_new(buf, size, vnet_hdr_len);
-     g_free(buf);
-     /*
-@@ -XXX,XX +XXX,XX @@ static void colo_rewriter_setup(NetFilterState *nf, Error **errp)
-     s->incoming_queue = qemu_new_net_queue(qemu_netfilter_pass_to_next, nf);
- }
-+static bool filter_rewriter_get_vnet_hdr(Object *obj, Error **errp)
-+{
-+    RewriterState *s = FILTER_COLO_REWRITER(obj);
-+
-+    return s->vnet_hdr;
-+}
-+
-+static void filter_rewriter_set_vnet_hdr(Object *obj,
-+                                         bool value,
-+                                         Error **errp)
-+{
-+    RewriterState *s = FILTER_COLO_REWRITER(obj);
-+
-+    s->vnet_hdr = value;
-+}
-+
-+static void filter_rewriter_init(Object *obj)
-+{
-+    RewriterState *s = FILTER_COLO_REWRITER(obj);
-+
-+    s->vnet_hdr = false;
-+    object_property_add_bool(obj, "vnet_hdr_support",
-+                             filter_rewriter_get_vnet_hdr,
-+                             filter_rewriter_set_vnet_hdr, NULL);
-+}
-+
- static void colo_rewriter_class_init(ObjectClass *oc, void *data)
- {
-     NetFilterClass *nfc = NETFILTER_CLASS(oc);
-@@ -XXX,XX +XXX,XX @@ static const TypeInfo colo_rewriter_info = {
-     .name = TYPE_FILTER_REWRITER,
-     .parent = TYPE_NETFILTER,
-     .class_init = colo_rewriter_class_init,
-+    .instance_init = filter_rewriter_init,
-     .instance_size = sizeof(RewriterState),
- };
-diff --git a/qemu-options.hx b/qemu-options.hx
-index XXXXXXX..XXXXXXX 100644
---- a/qemu-options.hx
-+++ b/qemu-options.hx
-@@ -XXX,XX +XXX,XX @@ Create a filter-redirector we need to differ outdev id from indev id, id can not
- be the same. we can just use indev or outdev, but at least one of indev or outdev
- need to be specified.
--@item -object filter-rewriter,id=@var{id},netdev=@var{netdevid}[,queue=@var{all|rx|tx}]
-+@item -object filter-rewriter,id=@var{id},netdev=@var{netdevid},queue=@var{all|rx|tx},[vnet_hdr_support]
- Filter-rewriter is a part of COLO project.It will rewrite tcp packet to
- secondary from primary to keep secondary tcp connection,and rewrite
- tcp packet to primary from secondary make tcp packet can be handled by
--client.
-+client.if it has the vnet_hdr_support flag, we can parse packet with vnet header.
- usage:
- colo secondary:
---
-.7.4

-[Qemu-devel] [PULL 12/14] docs/colo-proxy.txt: Update colo-proxy usage of net driver with vnet_header
+Deleted patch
-From: Zhang Chen <zhangchen.fnst@cn.fujitsu.com>
-Signed-off-by: Zhang Chen <zhangchen.fnst@cn.fujitsu.com>
-Signed-off-by: Jason Wang <jasowang@redhat.com>
----
- docs/colo-proxy.txt | 26 ++++++++++++++++++++++++++
-file changed, 26 insertions(+)
-diff --git a/docs/colo-proxy.txt b/docs/colo-proxy.txt
-index XXXXXXX..XXXXXXX 100644
---- a/docs/colo-proxy.txt
-+++ b/docs/colo-proxy.txt
-@@ -XXX,XX +XXX,XX @@ Secondary(ip:3.3.3.8):
- -chardev socket,id=red1,host=3.3.3.3,port=9004
- -object filter-redirector,id=f1,netdev=hn0,queue=tx,indev=red0
- -object filter-redirector,id=f2,netdev=hn0,queue=rx,outdev=red1
-+-object filter-rewriter,id=f3,netdev=hn0,queue=all
-+
-+If you want to use virtio-net-pci or other driver with vnet_header:
-+
-+Primary(ip:3.3.3.3):
-+-netdev tap,id=hn0,vhost=off,script=/etc/qemu-ifup,downscript=/etc/qemu-ifdown
-+-device e1000,id=e0,netdev=hn0,mac=52:a4:00:12:78:66
-+-chardev socket,id=mirror0,host=3.3.3.3,port=9003,server,nowait
-+-chardev socket,id=compare1,host=3.3.3.3,port=9004,server,nowait
-+-chardev socket,id=compare0,host=3.3.3.3,port=9001,server,nowait
-+-chardev socket,id=compare0-0,host=3.3.3.3,port=9001
-+-chardev socket,id=compare_out,host=3.3.3.3,port=9005,server,nowait
-+-chardev socket,id=compare_out0,host=3.3.3.3,port=9005
-+-object filter-mirror,id=m0,netdev=hn0,queue=tx,outdev=mirror0,vnet_hdr_support
-+-object filter-redirector,netdev=hn0,id=redire0,queue=rx,indev=compare_out,vnet_hdr_support
-+-object filter-redirector,netdev=hn0,id=redire1,queue=rx,outdev=compare0,vnet_hdr_support
-+-object colo-compare,id=comp0,primary_in=compare0-0,secondary_in=compare1,outdev=compare_out0,vnet_hdr_support
-+
-+Secondary(ip:3.3.3.8):
-+-netdev tap,id=hn0,vhost=off,script=/etc/qemu-ifup,down script=/etc/qemu-ifdown
-+-device e1000,netdev=hn0,mac=52:a4:00:12:78:66
-+-chardev socket,id=red0,host=3.3.3.3,port=9003
-+-chardev socket,id=red1,host=3.3.3.3,port=9004
-+-object filter-redirector,id=f1,netdev=hn0,queue=tx,indev=red0,vnet_hdr_support
-+-object filter-redirector,id=f2,netdev=hn0,queue=rx,outdev=red1,vnet_hdr_support
-+-object filter-rewriter,id=f3,netdev=hn0,queue=all,vnet_hdr_support
- Note:
-   a.COLO-proxy must work with COLO-frame and Block-replication.
---
-.7.4

The following changes since commit 6632f6ff96f0537fc34cdc00c760656fc62e23c5:

Merge remote-tracking branch 'remotes/famz/tags/block-and-testing-pull-request' into staging (2017-07-17 11:46:36 +0100)

are available in the git repository at:

https://github.com/jasowang/qemu.git tags/net-pull-request

for you to fetch changes up to 189ae6bb5ce1f5a322f8691d00fe942ba43dd601:

virtio-net: fix offload ctrl endian (2017-07-17 20:13:56 +0800)

----------------------------------------------------------------

- fix virtio-net ctrl offload endian
- vnet header support for variou COLO netfilters and compare thread

----------------------------------------------------------------
Jason Wang (1):
      virtio-net: fix offload ctrl endian

Michal Privoznik (1):
      virtion-net: Prefer is_power_of_2()

Zhang Chen (12):
      net: Add vnet_hdr_len arguments in NetClientState
      net/net.c: Add vnet_hdr support in SocketReadState
      net/filter-mirror.c: Introduce parameter for filter_send()
      net/filter-mirror.c: Make filter mirror support vnet support.
      net/filter-mirror.c: Add new option to enable vnet support for filter-redirector
      net/colo.c: Make vnet_hdr_len as packet property
      net/colo-compare.c: Introduce parameter for compare_chr_send()
      net/colo-compare.c: Make colo-compare support vnet_hdr_len
      net/colo.c: Add vnet packet parse feature in colo-proxy
      net/colo-compare.c: Add vnet packet's tcp/udp/icmp compare
      net/filter-rewriter.c: Make filter-rewriter support vnet_hdr_len
      docs/colo-proxy.txt: Update colo-proxy usage of net driver with vnet_header

From: Zhang Chen <zhangchen.fnst@cn.fujitsu.com>

We add a flag to decide whether net_fill_rstate() need read
the vnet_hdr_len or not.

Signed-off-by: Zhang Chen <zhangchen.fnst@cn.fujitsu.com>
Suggested-by: Jason Wang <jasowang@redhat.com>
Signed-off-by: Jason Wang <jasowang@redhat.com>
---
 include/net/net.h   |  9 +++++++--
 net/colo-compare.c  |  4 ++--
 net/filter-mirror.c |  2 +-
 net/net.c           | 36 ++++++++++++++++++++++++++++++++----
 net/socket.c        |  8 ++++----
 5 files changed, 46 insertions(+), 13 deletions(-)

diff --git a/include/net/net.h b/include/net/net.h
index XXXXXXX..XXXXXXX 100644
--- a/include/net/net.h
+++ b/include/net/net.h
@@ -XXX,XX +XXX,XX @@ typedef struct NICState {
 } NICState;
 
 struct SocketReadState {
-    int state; /* 0 = getting length, 1 = getting data */
+    /* 0 = getting length, 1 = getting vnet header length, 2 = getting data */
+    int state;
+    /* This flag decide whether to read the vnet_hdr_len field */
+    bool vnet_hdr;
     uint32_t index;
     uint32_t packet_len;
+    uint32_t vnet_hdr_len;
     uint8_t buf[NET_BUFSIZE];
     SocketReadStateFinalize *finalize;
 };
@@ -XXX,XX +XXX,XX @@ ssize_t qemu_deliver_packet_iov(NetClientState *sender,
 void print_net_client(Monitor *mon, NetClientState *nc);
 void hmp_info_network(Monitor *mon, const QDict *qdict);
 void net_socket_rs_init(SocketReadState *rs,
-                        SocketReadStateFinalize *finalize);
+                        SocketReadStateFinalize *finalize,
+                        bool vnet_hdr);
 
 /* NIC info */
 
diff --git a/net/colo-compare.c b/net/colo-compare.c
index XXXXXXX..XXXXXXX 100644
--- a/net/colo-compare.c
+++ b/net/colo-compare.c
@@ -XXX,XX +XXX,XX @@ static void colo_compare_complete(UserCreatable *uc, Error **errp)
         return;
     }
 
-    net_socket_rs_init(&s->pri_rs, compare_pri_rs_finalize);
-    net_socket_rs_init(&s->sec_rs, compare_sec_rs_finalize);
+    net_socket_rs_init(&s->pri_rs, compare_pri_rs_finalize, false);
+    net_socket_rs_init(&s->sec_rs, compare_sec_rs_finalize, false);
 
     g_queue_init(&s->conn_list);
 
diff --git a/net/filter-mirror.c b/net/filter-mirror.c
index XXXXXXX..XXXXXXX 100644
--- a/net/filter-mirror.c
+++ b/net/filter-mirror.c
@@ -XXX,XX +XXX,XX @@ static void filter_redirector_setup(NetFilterState *nf, Error **errp)
         }
     }
 
-    net_socket_rs_init(&s->rs, redirector_rs_finalize);
+    net_socket_rs_init(&s->rs, redirector_rs_finalize, false);
 
     if (s->indev) {
         chr = qemu_chr_find(s->indev);
diff --git a/net/net.c b/net/net.c
index XXXXXXX..XXXXXXX 100644
--- a/net/net.c
+++ b/net/net.c
@@ -XXX,XX +XXX,XX @@ QemuOptsList qemu_net_opts = {
 };
 
 void net_socket_rs_init(SocketReadState *rs,
-                        SocketReadStateFinalize *finalize)
+                        SocketReadStateFinalize *finalize,
+                        bool vnet_hdr)
 {
     rs->state = 0;
+    rs->vnet_hdr = vnet_hdr;
     rs->index = 0;
     rs->packet_len = 0;
+    rs->vnet_hdr_len = 0;
     memset(rs->buf, 0, sizeof(rs->buf));
     rs->finalize = finalize;
 }
@@ -XXX,XX +XXX,XX @@ int net_fill_rstate(SocketReadState *rs, const uint8_t *buf, int size)
     unsigned int l;
 
     while (size > 0) {
-        /* reassemble a packet from the network */
-        switch (rs->state) { /* 0 = getting length, 1 = getting data */
+        /* Reassemble a packet from the network.
+         * 0 = getting length.
+         * 1 = getting vnet header length.
+         * 2 = getting data.
+         */
+        switch (rs->state) {
         case 0:
             l = 4 - rs->index;
             if (l > size) {
@@ -XXX,XX +XXX,XX @@ int net_fill_rstate(SocketReadState *rs, const uint8_t *buf, int size)
                 /* got length */
                 rs->packet_len = ntohl(*(uint32_t *)rs->buf);
                 rs->index = 0;
-                rs->state = 1;
+                if (rs->vnet_hdr) {
+                    rs->state = 1;
+                } else {
+                    rs->state = 2;
+                    rs->vnet_hdr_len = 0;
+                }
             }
             break;
         case 1:
+            l = 4 - rs->index;
+            if (l > size) {
+                l = size;
+            }
+            memcpy(rs->buf + rs->index, buf, l);
+            buf += l;
+            size -= l;
+            rs->index += l;
+            if (rs->index == 4) {
+                /* got vnet header length */
+                rs->vnet_hdr_len = ntohl(*(uint32_t *)rs->buf);
+                rs->index = 0;
+                rs->state = 2;
+            }
+            break;
+        case 2:
             l = rs->packet_len - rs->index;
             if (l > size) {
                 l = size;
diff --git a/net/socket.c b/net/socket.c
index XXXXXXX..XXXXXXX 100644
--- a/net/socket.c
+++ b/net/socket.c
@@ -XXX,XX +XXX,XX @@ static void net_socket_send(void *opaque)
         closesocket(s->fd);
 
         s->fd = -1;
-        net_socket_rs_init(&s->rs, net_socket_rs_finalize);
+        net_socket_rs_init(&s->rs, net_socket_rs_finalize, false);
         s->nc.link_down = true;
         memset(s->nc.info_str, 0, sizeof(s->nc.info_str));
 
@@ -XXX,XX +XXX,XX @@ static NetSocketState *net_socket_fd_init_dgram(NetClientState *peer,
     s->fd = fd;
     s->listen_fd = -1;
     s->send_fn = net_socket_send_dgram;
-    net_socket_rs_init(&s->rs, net_socket_rs_finalize);
+    net_socket_rs_init(&s->rs, net_socket_rs_finalize, false);
     net_socket_read_poll(s, true);
 
     /* mcast: save bound address as dst */
@@ -XXX,XX +XXX,XX @@ static NetSocketState *net_socket_fd_init_stream(NetClientState *peer,
 
     s->fd = fd;
     s->listen_fd = -1;
-    net_socket_rs_init(&s->rs, net_socket_rs_finalize);
+    net_socket_rs_init(&s->rs, net_socket_rs_finalize, false);
 
     /* Disable Nagle algorithm on TCP sockets to reduce latency */
     socket_set_nodelay(fd);
@@ -XXX,XX +XXX,XX @@ static int net_socket_listen_init(NetClientState *peer,
     s->fd = -1;
     s->listen_fd = fd;
     s->nc.link_down = true;
-    net_socket_rs_init(&s->rs, net_socket_rs_finalize);
+    net_socket_rs_init(&s->rs, net_socket_rs_finalize, false);
 
     qemu_set_fd_handler(s->listen_fd, net_socket_accept, NULL, s);
     return 0;
-- 
2.7.4

From: Zhang Chen <zhangchen.fnst@cn.fujitsu.com>

This patch change the filter_send() parameter from CharBackend to MirrorState,
we can get more information like vnet_hdr(We use it to support packet with vnet_header).

Signed-off-by: Zhang Chen <zhangchen.fnst@cn.fujitsu.com>
Signed-off-by: Jason Wang <jasowang@redhat.com>
---
 net/filter-mirror.c | 10 +++++-----
 1 file changed, 5 insertions(+), 5 deletions(-)

diff --git a/net/filter-mirror.c b/net/filter-mirror.c
index XXXXXXX..XXXXXXX 100644
--- a/net/filter-mirror.c
+++ b/net/filter-mirror.c
@@ -XXX,XX +XXX,XX @@ typedef struct MirrorState {
     SocketReadState rs;
 } MirrorState;
 
-static int filter_send(CharBackend *chr_out,
+static int filter_send(MirrorState *s,
                        const struct iovec *iov,
                        int iovcnt)
 {
@@ -XXX,XX +XXX,XX @@ static int filter_send(CharBackend *chr_out,
     }
 
     len = htonl(size);
-    ret = qemu_chr_fe_write_all(chr_out, (uint8_t *)&len, sizeof(len));
+    ret = qemu_chr_fe_write_all(&s->chr_out, (uint8_t *)&len, sizeof(len));
     if (ret != sizeof(len)) {
         goto err;
     }
 
     buf = g_malloc(size);
     iov_to_buf(iov, iovcnt, 0, buf, size);
-    ret = qemu_chr_fe_write_all(chr_out, (uint8_t *)buf, size);
+    ret = qemu_chr_fe_write_all(&s->chr_out, (uint8_t *)buf, size);
     g_free(buf);
     if (ret != size) {
         goto err;
@@ -XXX,XX +XXX,XX @@ static ssize_t filter_mirror_receive_iov(NetFilterState *nf,
     MirrorState *s = FILTER_MIRROR(nf);
     int ret;
 
-    ret = filter_send(&s->chr_out, iov, iovcnt);
+    ret = filter_send(s, iov, iovcnt);
     if (ret) {
         error_report("filter mirror send failed(%s)", strerror(-ret));
     }
@@ -XXX,XX +XXX,XX @@ static ssize_t filter_redirector_receive_iov(NetFilterState *nf,
     int ret;
 
     if (qemu_chr_fe_backend_connected(&s->chr_out)) {
-        ret = filter_send(&s->chr_out, iov, iovcnt);
+        ret = filter_send(s, iov, iovcnt);
         if (ret) {
             error_report("filter redirector send failed(%s)", strerror(-ret));
         }
-- 
2.7.4

From: Zhang Chen <zhangchen.fnst@cn.fujitsu.com>

We add the vnet_hdr_support option for filter-mirror, default is disabled.
If you use virtio-net-pci or other driver needs vnet_hdr, please enable it.
You can use it for example:
-object filter-mirror,id=m0,netdev=hn0,queue=tx,outdev=mirror0,vnet_hdr_support

If it has vnet_hdr_support flag, we will change the sending packet format from
struct {int size; const uint8_t buf[];} to {int size; int vnet_hdr_len; const uint8_t buf[];}.
make other module(like colo-compare) know how to parse net packet correctly.

Signed-off-by: Zhang Chen <zhangchen.fnst@cn.fujitsu.com>
Signed-off-by: Jason Wang <jasowang@redhat.com>
---
 net/filter-mirror.c | 42 +++++++++++++++++++++++++++++++++++++++++-
 qemu-options.hx     |  5 ++---
 2 files changed, 43 insertions(+), 4 deletions(-)

diff --git a/net/filter-mirror.c b/net/filter-mirror.c
index XXXXXXX..XXXXXXX 100644
--- a/net/filter-mirror.c
+++ b/net/filter-mirror.c
@@ -XXX,XX +XXX,XX @@ typedef struct MirrorState {
     CharBackend chr_in;
     CharBackend chr_out;
     SocketReadState rs;
+    bool vnet_hdr;
 } MirrorState;
 
 static int filter_send(MirrorState *s,
                        const struct iovec *iov,
                        int iovcnt)
 {
+    NetFilterState *nf = NETFILTER(s);
     int ret = 0;
     ssize_t size = 0;
     uint32_t len = 0;
@@ -XXX,XX +XXX,XX @@ static int filter_send(MirrorState *s,
         goto err;
     }
 
+    if (s->vnet_hdr) {
+        /*
+         * If vnet_hdr = on, we send vnet header len to make other
+         * module(like colo-compare) know how to parse net
+         * packet correctly.
+         */
+        ssize_t vnet_hdr_len;
+
+        vnet_hdr_len = nf->netdev->vnet_hdr_len;
+
+        len = htonl(vnet_hdr_len);
+        ret = qemu_chr_fe_write_all(&s->chr_out, (uint8_t *)&len, sizeof(len));
+        if (ret != sizeof(len)) {
+            goto err;
+        }
+    }
+
     buf = g_malloc(size);
     iov_to_buf(iov, iovcnt, 0, buf, size);
     ret = qemu_chr_fe_write_all(&s->chr_out, (uint8_t *)buf, size);
@@ -XXX,XX +XXX,XX @@ static void filter_redirector_setup(NetFilterState *nf, Error **errp)
         }
     }
 
-    net_socket_rs_init(&s->rs, redirector_rs_finalize, false);
+    net_socket_rs_init(&s->rs, redirector_rs_finalize, s->vnet_hdr);
 
     if (s->indev) {
         chr = qemu_chr_find(s->indev);
@@ -XXX,XX +XXX,XX @@ static void filter_mirror_set_outdev(Object *obj,
     }
 }
 
+static bool filter_mirror_get_vnet_hdr(Object *obj, Error **errp)
+{
+    MirrorState *s = FILTER_MIRROR(obj);
+
+    return s->vnet_hdr;
+}
+
+static void filter_mirror_set_vnet_hdr(Object *obj, bool value, Error **errp)
+{
+    MirrorState *s = FILTER_MIRROR(obj);
+
+    s->vnet_hdr = value;
+}
+
 static char *filter_redirector_get_outdev(Object *obj, Error **errp)
 {
     MirrorState *s = FILTER_REDIRECTOR(obj);
@@ -XXX,XX +XXX,XX @@ static void filter_redirector_set_outdev(Object *obj,
 
 static void filter_mirror_init(Object *obj)
 {
+    MirrorState *s = FILTER_MIRROR(obj);
+
     object_property_add_str(obj, "outdev", filter_mirror_get_outdev,
                             filter_mirror_set_outdev, NULL);
+
+    s->vnet_hdr = false;
+    object_property_add_bool(obj, "vnet_hdr_support",
+                             filter_mirror_get_vnet_hdr,
+                             filter_mirror_set_vnet_hdr, NULL);
 }
 
 static void filter_redirector_init(Object *obj)
diff --git a/qemu-options.hx b/qemu-options.hx
index XXXXXXX..XXXXXXX 100644
--- a/qemu-options.hx
+++ b/qemu-options.hx
@@ -XXX,XX +XXX,XX @@ queue @var{all|rx|tx} is an option that can be applied to any netfilter.
 @option{tx}: the filter is attached to the transmit queue of the netdev,
              where it will receive packets sent by the netdev.
 
-@item -object filter-mirror,id=@var{id},netdev=@var{netdevid},outdev=@var{chardevid}[,queue=@var{all|rx|tx}]
+@item -object filter-mirror,id=@var{id},netdev=@var{netdevid},outdev=@var{chardevid},queue=@var{all|rx|tx}[,vnet_hdr_support]
 
-filter-mirror on netdev @var{netdevid},mirror net packet to chardev
-@var{chardevid}
+filter-mirror on netdev @var{netdevid},mirror net packet to chardev@var{chardevid}, if it has the vnet_hdr_support flag, filter-mirror will mirror packet with vnet_hdr_len.
 
 @item -object filter-redirector,id=@var{id},netdev=@var{netdevid},indev=@var{chardevid},
 outdev=@var{chardevid}[,queue=@var{all|rx|tx}]
-- 
2.7.4

From: Zhang Chen <zhangchen.fnst@cn.fujitsu.com>

We add the vnet_hdr_support option for filter-redirector, default is disabled.
If you use virtio-net-pci net driver or other driver needs vnet_hdr, please enable it.
Because colo-compare or other modules needs the vnet_hdr_len to parse
packet, we add this new option send the len to others.
You can use it for example:
-object filter-redirector,id=r0,netdev=hn0,queue=tx,outdev=red0,vnet_hdr_support

Signed-off-by: Zhang Chen <zhangchen.fnst@cn.fujitsu.com>
Signed-off-by: Jason Wang <jasowang@redhat.com>
---
 net/filter-mirror.c | 23 +++++++++++++++++++++++
 qemu-options.hx     |  6 +++---
 2 files changed, 26 insertions(+), 3 deletions(-)

diff --git a/net/filter-mirror.c b/net/filter-mirror.c
index XXXXXXX..XXXXXXX 100644
--- a/net/filter-mirror.c
+++ b/net/filter-mirror.c
@@ -XXX,XX +XXX,XX @@ static void filter_redirector_set_outdev(Object *obj,
     s->outdev = g_strdup(value);
 }
 
+static bool filter_redirector_get_vnet_hdr(Object *obj, Error **errp)
+{
+    MirrorState *s = FILTER_REDIRECTOR(obj);
+
+    return s->vnet_hdr;
+}
+
+static void filter_redirector_set_vnet_hdr(Object *obj,
+                                           bool value,
+                                           Error **errp)
+{
+    MirrorState *s = FILTER_REDIRECTOR(obj);
+
+    s->vnet_hdr = value;
+}
+
 static void filter_mirror_init(Object *obj)
 {
     MirrorState *s = FILTER_MIRROR(obj);
@@ -XXX,XX +XXX,XX @@ static void filter_mirror_init(Object *obj)
 
 static void filter_redirector_init(Object *obj)
 {
+    MirrorState *s = FILTER_REDIRECTOR(obj);
+
     object_property_add_str(obj, "indev", filter_redirector_get_indev,
                             filter_redirector_set_indev, NULL);
     object_property_add_str(obj, "outdev", filter_redirector_get_outdev,
                             filter_redirector_set_outdev, NULL);
+
+    s->vnet_hdr = false;
+    object_property_add_bool(obj, "vnet_hdr_support",
+                             filter_redirector_get_vnet_hdr,
+                             filter_redirector_set_vnet_hdr, NULL);
 }
 
 static void filter_mirror_fini(Object *obj)
diff --git a/qemu-options.hx b/qemu-options.hx
index XXXXXXX..XXXXXXX 100644
--- a/qemu-options.hx
+++ b/qemu-options.hx
@@ -XXX,XX +XXX,XX @@ queue @var{all|rx|tx} is an option that can be applied to any netfilter.
 
 filter-mirror on netdev @var{netdevid},mirror net packet to chardev@var{chardevid}, if it has the vnet_hdr_support flag, filter-mirror will mirror packet with vnet_hdr_len.
 
-@item -object filter-redirector,id=@var{id},netdev=@var{netdevid},indev=@var{chardevid},
-outdev=@var{chardevid}[,queue=@var{all|rx|tx}]
+@item -object filter-redirector,id=@var{id},netdev=@var{netdevid},indev=@var{chardevid},outdev=@var{chardevid},queue=@var{all|rx|tx}[,vnet_hdr_support]
 
 filter-redirector on netdev @var{netdevid},redirect filter's net packet to chardev
-@var{chardevid},and redirect indev's packet to filter.
+@var{chardevid},and redirect indev's packet to filter.if it has the vnet_hdr_support flag,
+filter-redirector will redirect packet with vnet_hdr_len.
 Create a filter-redirector we need to differ outdev id from indev id, id can not
 be the same. we can just use indev or outdev, but at least one of indev or outdev
 need to be specified.
-- 
2.7.4

From: Zhang Chen <zhangchen.fnst@cn.fujitsu.com>

We can use this property flush and send packet with vnet_hdr_len.

Signed-off-by: Zhang Chen <zhangchen.fnst@cn.fujitsu.com>
Signed-off-by: Jason Wang <jasowang@redhat.com>
---
 net/colo-compare.c    | 8 ++++++--
 net/colo.c            | 3 ++-
 net/colo.h            | 4 +++-
 net/filter-rewriter.c | 2 +-
 4 files changed, 12 insertions(+), 5 deletions(-)

diff --git a/net/colo-compare.c b/net/colo-compare.c
index XXXXXXX..XXXXXXX 100644
--- a/net/colo-compare.c
+++ b/net/colo-compare.c
@@ -XXX,XX +XXX,XX @@ static int packet_enqueue(CompareState *s, int mode)
     Connection *conn;
 
     if (mode == PRIMARY_IN) {
-        pkt = packet_new(s->pri_rs.buf, s->pri_rs.packet_len);
+        pkt = packet_new(s->pri_rs.buf,
+                         s->pri_rs.packet_len,
+                         s->pri_rs.vnet_hdr_len);
     } else {
-        pkt = packet_new(s->sec_rs.buf, s->sec_rs.packet_len);
+        pkt = packet_new(s->sec_rs.buf,
+                         s->sec_rs.packet_len,
+                         s->sec_rs.vnet_hdr_len);
     }
 
     if (parse_packet_early(pkt)) {
diff --git a/net/colo.c b/net/colo.c
index XXXXXXX..XXXXXXX 100644
--- a/net/colo.c
+++ b/net/colo.c
@@ -XXX,XX +XXX,XX @@ void connection_destroy(void *opaque)
     g_slice_free(Connection, conn);
 }
 
-Packet *packet_new(const void *data, int size)
+Packet *packet_new(const void *data, int size, int vnet_hdr_len)
 {
     Packet *pkt = g_slice_new(Packet);
 
     pkt->data = g_memdup(data, size);
     pkt->size = size;
     pkt->creation_ms = qemu_clock_get_ms(QEMU_CLOCK_HOST);
+    pkt->vnet_hdr_len = vnet_hdr_len;
 
     return pkt;
 }
diff --git a/net/colo.h b/net/colo.h
index XXXXXXX..XXXXXXX 100644
--- a/net/colo.h
+++ b/net/colo.h
@@ -XXX,XX +XXX,XX @@ typedef struct Packet {
     int size;
     /* Time of packet creation, in wall clock ms */
     int64_t creation_ms;
+    /* Get vnet_hdr_len from filter */
+    uint32_t vnet_hdr_len;
 } Packet;
 
 typedef struct ConnectionKey {
@@ -XXX,XX +XXX,XX @@ Connection *connection_get(GHashTable *connection_track_table,
                            ConnectionKey *key,
                            GQueue *conn_list);
 void connection_hashtable_reset(GHashTable *connection_track_table);
-Packet *packet_new(const void *data, int size);
+Packet *packet_new(const void *data, int size, int vnet_hdr_len);
 void packet_destroy(void *opaque, void *user_data);
 
 #endif /* QEMU_COLO_PROXY_H */
diff --git a/net/filter-rewriter.c b/net/filter-rewriter.c
index XXXXXXX..XXXXXXX 100644
--- a/net/filter-rewriter.c
+++ b/net/filter-rewriter.c
@@ -XXX,XX +XXX,XX @@ static ssize_t colo_rewriter_receive_iov(NetFilterState *nf,
     char *buf = g_malloc0(size);
 
     iov_to_buf(iov, iovcnt, 0, buf, size);
-    pkt = packet_new(buf, size);
+    pkt = packet_new(buf, size, 0);
     g_free(buf);
 
     /*
-- 
2.7.4

From: Zhang Chen <zhangchen.fnst@cn.fujitsu.com>

This patch change the compare_chr_send() parameter from CharBackend to CompareState,
we can get more information like vnet_hdr(We use it to support packet with vnet_header).

Signed-off-by: Zhang Chen <zhangchen.fnst@cn.fujitsu.com>
Signed-off-by: Jason Wang <jasowang@redhat.com>
---
 net/colo-compare.c | 14 +++++++-------
 1 file changed, 7 insertions(+), 7 deletions(-)

diff --git a/net/colo-compare.c b/net/colo-compare.c
index XXXXXXX..XXXXXXX 100644
--- a/net/colo-compare.c
+++ b/net/colo-compare.c
@@ -XXX,XX +XXX,XX @@ enum {
     SECONDARY_IN,
 };
 
-static int compare_chr_send(CharBackend *out,
+static int compare_chr_send(CompareState *s,
                             const uint8_t *buf,
                             uint32_t size);
 
@@ -XXX,XX +XXX,XX @@ static void colo_compare_connection(void *opaque, void *user_data)
         }
 
         if (result) {
-            ret = compare_chr_send(&s->chr_out, pkt->data, pkt->size);
+            ret = compare_chr_send(s, pkt->data, pkt->size);
             if (ret < 0) {
                 error_report("colo_send_primary_packet failed");
             }
@@ -XXX,XX +XXX,XX @@ static void colo_compare_connection(void *opaque, void *user_data)
     }
 }
 
-static int compare_chr_send(CharBackend *out,
+static int compare_chr_send(CompareState *s,
                             const uint8_t *buf,
                             uint32_t size)
 {
@@ -XXX,XX +XXX,XX @@ static int compare_chr_send(CharBackend *out,
         return 0;
     }
 
-    ret = qemu_chr_fe_write_all(out, (uint8_t *)&len, sizeof(len));
+    ret = qemu_chr_fe_write_all(&s->chr_out, (uint8_t *)&len, sizeof(len));
     if (ret != sizeof(len)) {
         goto err;
     }
 
-    ret = qemu_chr_fe_write_all(out, (uint8_t *)buf, size);
+    ret = qemu_chr_fe_write_all(&s->chr_out, (uint8_t *)buf, size);
     if (ret != size) {
         goto err;
     }
@@ -XXX,XX +XXX,XX @@ static void compare_pri_rs_finalize(SocketReadState *pri_rs)
 
     if (packet_enqueue(s, PRIMARY_IN)) {
         trace_colo_compare_main("primary: unsupported packet in");
-        compare_chr_send(&s->chr_out, pri_rs->buf, pri_rs->packet_len);
+        compare_chr_send(s, pri_rs->buf, pri_rs->packet_len);
     } else {
         /* compare connection */
         g_queue_foreach(&s->conn_list, colo_compare_connection, s);
@@ -XXX,XX +XXX,XX @@ static void colo_flush_packets(void *opaque, void *user_data)
 
     while (!g_queue_is_empty(&conn->primary_list)) {
         pkt = g_queue_pop_head(&conn->primary_list);
-        compare_chr_send(&s->chr_out, pkt->data, pkt->size);
+        compare_chr_send(s, pkt->data, pkt->size);
         packet_destroy(pkt, NULL);
     }
     while (!g_queue_is_empty(&conn->secondary_list)) {
-- 
2.7.4

From: Zhang Chen <zhangchen.fnst@cn.fujitsu.com>

We add the vnet_hdr_support option for colo-compare, default is disabled.
If you use virtio-net-pci or other driver needs vnet_hdr, please enable it.
You can use it for example:
-object colo-compare,id=comp0,primary_in=compare0-0,secondary_in=compare1,outdev=compare_out0,vnet_hdr_support

COLO-compare can get vnet header length from filter,
Add vnet_hdr_len to struct packet and output packet with
the vnet_hdr_len.

Signed-off-by: Zhang Chen <zhangchen.fnst@cn.fujitsu.com>
Signed-off-by: Jason Wang <jasowang@redhat.com>
---
 net/colo-compare.c | 60 +++++++++++++++++++++++++++++++++++++++++++++++-------
 qemu-options.hx    |  4 ++--
 2 files changed, 55 insertions(+), 9 deletions(-)

diff --git a/net/colo-compare.c b/net/colo-compare.c
index XXXXXXX..XXXXXXX 100644
--- a/net/colo-compare.c
+++ b/net/colo-compare.c
@@ -XXX,XX +XXX,XX @@ typedef struct CompareState {
     CharBackend chr_out;
     SocketReadState pri_rs;
     SocketReadState sec_rs;
+    bool vnet_hdr;
 
     /* connection list: the connections belonged to this NIC could be found
      * in this list.
@@ -XXX,XX +XXX,XX @@ enum {
 
 static int compare_chr_send(CompareState *s,
                             const uint8_t *buf,
-                            uint32_t size);
+                            uint32_t size,
+                            uint32_t vnet_hdr_len);
 
 static gint seq_sorter(Packet *a, Packet *b, gpointer data)
 {
@@ -XXX,XX +XXX,XX @@ static void colo_compare_connection(void *opaque, void *user_data)
         }
 
         if (result) {
-            ret = compare_chr_send(s, pkt->data, pkt->size);
+            ret = compare_chr_send(s,
+                                   pkt->data,
+                                   pkt->size,
+                                   pkt->vnet_hdr_len);
             if (ret < 0) {
                 error_report("colo_send_primary_packet failed");
             }
@@ -XXX,XX +XXX,XX @@ static void colo_compare_connection(void *opaque, void *user_data)
 
 static int compare_chr_send(CompareState *s,
                             const uint8_t *buf,
-                            uint32_t size)
+                            uint32_t size,
+                            uint32_t vnet_hdr_len)
 {
     int ret = 0;
     uint32_t len = htonl(size);
@@ -XXX,XX +XXX,XX @@ static int compare_chr_send(CompareState *s,
         goto err;
     }
 
+    if (s->vnet_hdr) {
+        /*
+         * We send vnet header len make other module(like filter-redirector)
+         * know how to parse net packet correctly.
+         */
+        len = htonl(vnet_hdr_len);
+        ret = qemu_chr_fe_write_all(&s->chr_out, (uint8_t *)&len, sizeof(len));
+        if (ret != sizeof(len)) {
+            goto err;
+        }
+    }
+
     ret = qemu_chr_fe_write_all(&s->chr_out, (uint8_t *)buf, size);
     if (ret != size) {
         goto err;
@@ -XXX,XX +XXX,XX @@ static void compare_set_outdev(Object *obj, const char *value, Error **errp)
     s->outdev = g_strdup(value);
 }
 
+static bool compare_get_vnet_hdr(Object *obj, Error **errp)
+{
+    CompareState *s = COLO_COMPARE(obj);
+
+    return s->vnet_hdr;
+}
+
+static void compare_set_vnet_hdr(Object *obj,
+                                 bool value,
+                                 Error **errp)
+{
+    CompareState *s = COLO_COMPARE(obj);
+
+    s->vnet_hdr = value;
+}
+
 static void compare_pri_rs_finalize(SocketReadState *pri_rs)
 {
     CompareState *s = container_of(pri_rs, CompareState, pri_rs);
 
     if (packet_enqueue(s, PRIMARY_IN)) {
         trace_colo_compare_main("primary: unsupported packet in");
-        compare_chr_send(s, pri_rs->buf, pri_rs->packet_len);
+        compare_chr_send(s,
+                         pri_rs->buf,
+                         pri_rs->packet_len,
+                         pri_rs->vnet_hdr_len);
     } else {
         /* compare connection */
         g_queue_foreach(&s->conn_list, colo_compare_connection, s);
@@ -XXX,XX +XXX,XX @@ static void colo_compare_complete(UserCreatable *uc, Error **errp)
         return;
     }
 
-    net_socket_rs_init(&s->pri_rs, compare_pri_rs_finalize, false);
-    net_socket_rs_init(&s->sec_rs, compare_sec_rs_finalize, false);
+    net_socket_rs_init(&s->pri_rs, compare_pri_rs_finalize, s->vnet_hdr);
+    net_socket_rs_init(&s->sec_rs, compare_sec_rs_finalize, s->vnet_hdr);
 
     g_queue_init(&s->conn_list);
 
@@ -XXX,XX +XXX,XX @@ static void colo_flush_packets(void *opaque, void *user_data)
 
     while (!g_queue_is_empty(&conn->primary_list)) {
         pkt = g_queue_pop_head(&conn->primary_list);
-        compare_chr_send(s, pkt->data, pkt->size);
+        compare_chr_send(s,
+                         pkt->data,
+                         pkt->size,
+                         pkt->vnet_hdr_len);
         packet_destroy(pkt, NULL);
     }
     while (!g_queue_is_empty(&conn->secondary_list)) {
@@ -XXX,XX +XXX,XX @@ static void colo_compare_class_init(ObjectClass *oc, void *data)
 
 static void colo_compare_init(Object *obj)
 {
+    CompareState *s = COLO_COMPARE(obj);
+
     object_property_add_str(obj, "primary_in",
                             compare_get_pri_indev, compare_set_pri_indev,
                             NULL);
@@ -XXX,XX +XXX,XX @@ static void colo_compare_init(Object *obj)
     object_property_add_str(obj, "outdev",
                             compare_get_outdev, compare_set_outdev,
                             NULL);
+
+    s->vnet_hdr = false;
+    object_property_add_bool(obj, "vnet_hdr_support", compare_get_vnet_hdr,
+                             compare_set_vnet_hdr, NULL);
 }
 
 static void colo_compare_finalize(Object *obj)
diff --git a/qemu-options.hx b/qemu-options.hx
index XXXXXXX..XXXXXXX 100644
--- a/qemu-options.hx
+++ b/qemu-options.hx
@@ -XXX,XX +XXX,XX @@ Dump the network traffic on netdev @var{dev} to the file specified by
 The file format is libpcap, so it can be analyzed with tools such as tcpdump
 or Wireshark.
 
-@item -object colo-compare,id=@var{id},primary_in=@var{chardevid},secondary_in=@var{chardevid},
-outdev=@var{chardevid}
+@item -object colo-compare,id=@var{id},primary_in=@var{chardevid},secondary_in=@var{chardevid},outdev=@var{chardevid}[,vnet_hdr_support]
 
 Colo-compare gets packet from primary_in@var{chardevid} and secondary_in@var{chardevid}, than compare primary packet with
 secondary packet. If the packets are same, we will output primary
 packet to outdev@var{chardevid}, else we will notify colo-frame
 do checkpoint and send primary packet to outdev@var{chardevid}.
+if it has the vnet_hdr_support flag, colo compare will send/recv packet with vnet_hdr_len.
 
 we must use it with the help of filter-mirror and filter-redirector.
 
-- 
2.7.4

From: Zhang Chen <zhangchen.fnst@cn.fujitsu.com>

Make colo-compare and filter-rewriter can parse vnet packet.

Signed-off-by: Zhang Chen <zhangchen.fnst@cn.fujitsu.com>
Signed-off-by: Jason Wang <jasowang@redhat.com>
---
 net/colo.c | 6 +++---
 1 file changed, 3 insertions(+), 3 deletions(-)

diff --git a/net/colo.c b/net/colo.c
index XXXXXXX..XXXXXXX 100644
--- a/net/colo.c
+++ b/net/colo.c
@@ -XXX,XX +XXX,XX @@ int parse_packet_early(Packet *pkt)
 {
     int network_length;
     static const uint8_t vlan[] = {0x81, 0x00};
-    uint8_t *data = pkt->data;
+    uint8_t *data = pkt->data + pkt->vnet_hdr_len;
     uint16_t l3_proto;
     ssize_t l2hdr_len = eth_get_l2_hdr_length(data);
 
-    if (pkt->size < ETH_HLEN) {
+    if (pkt->size < ETH_HLEN + pkt->vnet_hdr_len) {
         trace_colo_proxy_main("pkt->size < ETH_HLEN");
         return 1;
     }
@@ -XXX,XX +XXX,XX @@ int parse_packet_early(Packet *pkt)
     }
 
     network_length = pkt->ip->ip_hl * 4;
-    if (pkt->size < l2hdr_len + network_length) {
+    if (pkt->size < l2hdr_len + network_length + pkt->vnet_hdr_len) {
         trace_colo_proxy_main("pkt->size < network_header + network_length");
         return 1;
     }
-- 
2.7.4

From: Zhang Chen <zhangchen.fnst@cn.fujitsu.com>

COLO-Proxy just focus on packet payload, so we skip vnet header.

Signed-off-by: Zhang Chen <zhangchen.fnst@cn.fujitsu.com>
Signed-off-by: Jason Wang <jasowang@redhat.com>
---
 net/colo-compare.c | 8 ++++++--
 1 file changed, 6 insertions(+), 2 deletions(-)

diff --git a/net/colo-compare.c b/net/colo-compare.c
index XXXXXXX..XXXXXXX 100644
--- a/net/colo-compare.c
+++ b/net/colo-compare.c
@@ -XXX,XX +XXX,XX @@ static int colo_packet_compare_common(Packet *ppkt, Packet *spkt, int offset)
                                    sec_ip_src, sec_ip_dst);
     }
 
+    offset = ppkt->vnet_hdr_len + offset;
+
     if (ppkt->size == spkt->size) {
-        return memcmp(ppkt->data + offset, spkt->data + offset,
+        return memcmp(ppkt->data + offset,
+                      spkt->data + offset,
                       spkt->size - offset);
     } else {
         trace_colo_compare_main("Net packet size are not the same");
@@ -XXX,XX +XXX,XX @@ static int colo_packet_compare_tcp(Packet *spkt, Packet *ppkt)
      */
     if (ptcp->th_off > 5) {
         ptrdiff_t tcp_offset;
+
         tcp_offset = ppkt->transport_header - (uint8_t *)ppkt->data
-                     + (ptcp->th_off * 4);
+                     + (ptcp->th_off * 4) - ppkt->vnet_hdr_len;
         res = colo_packet_compare_common(ppkt, spkt, tcp_offset);
     } else if (ptcp->th_sum == stcp->th_sum) {
         res = colo_packet_compare_common(ppkt, spkt, ETH_HLEN);
-- 
2.7.4

From: Zhang Chen <zhangchen.fnst@cn.fujitsu.com>

We add the vnet_hdr_support option for filter-rewriter, default is disabled.
If you use virtio-net-pci or other driver needs vnet_hdr, please enable it.
You can use it for example:
-object filter-rewriter,id=rew0,netdev=hn0,queue=all,vnet_hdr_support

We get the vnet_hdr_len from NetClientState that make us
parse net packet correctly.

Signed-off-by: Zhang Chen <zhangchen.fnst@cn.fujitsu.com>
Signed-off-by: Jason Wang <jasowang@redhat.com>
---
 net/filter-rewriter.c | 37 ++++++++++++++++++++++++++++++++++++-
 qemu-options.hx       |  4 ++--
 2 files changed, 38 insertions(+), 3 deletions(-)

diff --git a/net/filter-rewriter.c b/net/filter-rewriter.c
index XXXXXXX..XXXXXXX 100644
--- a/net/filter-rewriter.c
+++ b/net/filter-rewriter.c
@@ -XXX,XX +XXX,XX @@
 #include "qemu-common.h"
 #include "qapi/error.h"
 #include "qapi/qmp/qerror.h"
+#include "qemu/error-report.h"
 #include "qapi-visit.h"
 #include "qom/object.h"
 #include "qemu/main-loop.h"
@@ -XXX,XX +XXX,XX @@ typedef struct RewriterState {
     NetQueue *incoming_queue;
     /* hashtable to save connection */
     GHashTable *connection_track_table;
+    bool vnet_hdr;
 } RewriterState;
 
 static void filter_rewriter_flush(NetFilterState *nf)
@@ -XXX,XX +XXX,XX @@ static ssize_t colo_rewriter_receive_iov(NetFilterState *nf,
     ConnectionKey key;
     Packet *pkt;
     ssize_t size = iov_size(iov, iovcnt);
+    ssize_t vnet_hdr_len = 0;
     char *buf = g_malloc0(size);
 
     iov_to_buf(iov, iovcnt, 0, buf, size);
-    pkt = packet_new(buf, size, 0);
+
+    if (s->vnet_hdr) {
+        vnet_hdr_len = nf->netdev->vnet_hdr_len;
+    }
+
+    pkt = packet_new(buf, size, vnet_hdr_len);
     g_free(buf);
 
     /*
@@ -XXX,XX +XXX,XX @@ static void colo_rewriter_setup(NetFilterState *nf, Error **errp)
     s->incoming_queue = qemu_new_net_queue(qemu_netfilter_pass_to_next, nf);
 }
 
+static bool filter_rewriter_get_vnet_hdr(Object *obj, Error **errp)
+{
+    RewriterState *s = FILTER_COLO_REWRITER(obj);
+
+    return s->vnet_hdr;
+}
+
+static void filter_rewriter_set_vnet_hdr(Object *obj,
+                                         bool value,
+                                         Error **errp)
+{
+    RewriterState *s = FILTER_COLO_REWRITER(obj);
+
+    s->vnet_hdr = value;
+}
+
+static void filter_rewriter_init(Object *obj)
+{
+    RewriterState *s = FILTER_COLO_REWRITER(obj);
+
+    s->vnet_hdr = false;
+    object_property_add_bool(obj, "vnet_hdr_support",
+                             filter_rewriter_get_vnet_hdr,
+                             filter_rewriter_set_vnet_hdr, NULL);
+}
+
 static void colo_rewriter_class_init(ObjectClass *oc, void *data)
 {
     NetFilterClass *nfc = NETFILTER_CLASS(oc);
@@ -XXX,XX +XXX,XX @@ static const TypeInfo colo_rewriter_info = {
     .name = TYPE_FILTER_REWRITER,
     .parent = TYPE_NETFILTER,
     .class_init = colo_rewriter_class_init,
+    .instance_init = filter_rewriter_init,
     .instance_size = sizeof(RewriterState),
 };
 
diff --git a/qemu-options.hx b/qemu-options.hx
index XXXXXXX..XXXXXXX 100644
--- a/qemu-options.hx
+++ b/qemu-options.hx
@@ -XXX,XX +XXX,XX @@ Create a filter-redirector we need to differ outdev id from indev id, id can not
 be the same. we can just use indev or outdev, but at least one of indev or outdev
 need to be specified.
 
-@item -object filter-rewriter,id=@var{id},netdev=@var{netdevid}[,queue=@var{all|rx|tx}]
+@item -object filter-rewriter,id=@var{id},netdev=@var{netdevid},queue=@var{all|rx|tx},[vnet_hdr_support]
 
 Filter-rewriter is a part of COLO project.It will rewrite tcp packet to
 secondary from primary to keep secondary tcp connection,and rewrite
 tcp packet to primary from secondary make tcp packet can be handled by
-client.
+client.if it has the vnet_hdr_support flag, we can parse packet with vnet header.
 
 usage:
 colo secondary:
-- 
2.7.4

From: Zhang Chen <zhangchen.fnst@cn.fujitsu.com>

Signed-off-by: Zhang Chen <zhangchen.fnst@cn.fujitsu.com>
Signed-off-by: Jason Wang <jasowang@redhat.com>
---
 docs/colo-proxy.txt | 26 ++++++++++++++++++++++++++
 1 file changed, 26 insertions(+)

diff --git a/docs/colo-proxy.txt b/docs/colo-proxy.txt
index XXXXXXX..XXXXXXX 100644
--- a/docs/colo-proxy.txt
+++ b/docs/colo-proxy.txt
@@ -XXX,XX +XXX,XX @@ Secondary(ip:3.3.3.8):
 -chardev socket,id=red1,host=3.3.3.3,port=9004
 -object filter-redirector,id=f1,netdev=hn0,queue=tx,indev=red0
 -object filter-redirector,id=f2,netdev=hn0,queue=rx,outdev=red1
+-object filter-rewriter,id=f3,netdev=hn0,queue=all
+
+If you want to use virtio-net-pci or other driver with vnet_header:
+
+Primary(ip:3.3.3.3):
+-netdev tap,id=hn0,vhost=off,script=/etc/qemu-ifup,downscript=/etc/qemu-ifdown
+-device e1000,id=e0,netdev=hn0,mac=52:a4:00:12:78:66
+-chardev socket,id=mirror0,host=3.3.3.3,port=9003,server,nowait
+-chardev socket,id=compare1,host=3.3.3.3,port=9004,server,nowait
+-chardev socket,id=compare0,host=3.3.3.3,port=9001,server,nowait
+-chardev socket,id=compare0-0,host=3.3.3.3,port=9001
+-chardev socket,id=compare_out,host=3.3.3.3,port=9005,server,nowait
+-chardev socket,id=compare_out0,host=3.3.3.3,port=9005
+-object filter-mirror,id=m0,netdev=hn0,queue=tx,outdev=mirror0,vnet_hdr_support
+-object filter-redirector,netdev=hn0,id=redire0,queue=rx,indev=compare_out,vnet_hdr_support
+-object filter-redirector,netdev=hn0,id=redire1,queue=rx,outdev=compare0,vnet_hdr_support
+-object colo-compare,id=comp0,primary_in=compare0-0,secondary_in=compare1,outdev=compare_out0,vnet_hdr_support
+
+Secondary(ip:3.3.3.8):
+-netdev tap,id=hn0,vhost=off,script=/etc/qemu-ifup,down script=/etc/qemu-ifdown
+-device e1000,netdev=hn0,mac=52:a4:00:12:78:66
+-chardev socket,id=red0,host=3.3.3.3,port=9003
+-chardev socket,id=red1,host=3.3.3.3,port=9004
+-object filter-redirector,id=f1,netdev=hn0,queue=tx,indev=red0,vnet_hdr_support
+-object filter-redirector,id=f2,netdev=hn0,queue=rx,outdev=red1,vnet_hdr_support
+-object filter-rewriter,id=f3,netdev=hn0,queue=all,vnet_hdr_support
 
 Note:
   a.COLO-proxy must work with COLO-frame and Block-replication.
-- 
2.7.4

From: Michal Privoznik <mprivozn@redhat.com>

We have a function that checks if given number is power of two.
We should prefer it instead of expanding the check on our own.

Signed-off-by: Michal Privoznik <mprivozn@redhat.com>
Signed-off-by: Jason Wang <jasowang@redhat.com>
---
 hw/net/virtio-net.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/hw/net/virtio-net.c b/hw/net/virtio-net.c
index XXXXXXX..XXXXXXX 100644
--- a/hw/net/virtio-net.c
+++ b/hw/net/virtio-net.c
@@ -XXX,XX +XXX,XX @@ static void virtio_net_device_realize(DeviceState *dev, Error **errp)
      */
     if (n->net_conf.rx_queue_size < VIRTIO_NET_RX_QUEUE_MIN_SIZE ||
         n->net_conf.rx_queue_size > VIRTQUEUE_MAX_SIZE ||
-        (n->net_conf.rx_queue_size & (n->net_conf.rx_queue_size - 1))) {
+        !is_power_of_2(n->net_conf.rx_queue_size)) {
         error_setg(errp, "Invalid rx_queue_size (= %" PRIu16 "), "
                    "must be a power of 2 between %d and %d.",
                    n->net_conf.rx_queue_size, VIRTIO_NET_RX_QUEUE_MIN_SIZE,
-- 
2.7.4

The following changes since commit 6b99bb046dd36a6dd5525b8f88c2dcddae49222a:

Merge tag 'pull-lu-20241122' of https://gitlab.com/rth7680/qemu into staging (2024-11-24 13:39:06 +0000)

are available in the Git repository at:

https://github.com/jasowang/qemu.git tags/net-pull-request

for you to fetch changes up to 7987d2be5a8bc3a502f89ba8cf3ac3e09f64d1ce:

virtio-net: Copy received header to buffer (2024-11-25 14:00:51 +0800)

----------------------------------------------------------------
-----BEGIN PGP SIGNATURE-----

iQEzBAABCAAdFiEEIV1G9IJGaJ7HfzVi7wSWWzmNYhEFAmdEEtgACgkQ7wSWWzmN
YhH5qAgAlKdcx/gFt4EBXtjVq/qbPluEGOQxvcRYLlN90rPLHPgCjAoT5ly3fIv1
4kCgcVZyG8SdGu1n0TzTTS9kg5tL7weQ9xEWwF0oyyuZABgAB7w/wpC8MHSkJFOn
2Tv+2Iab0dJ+e1pw71OMpE/YR5X2xq5vopsSHRtnyGWfRPGswJFwka+f8FS5DSiq
2CeNxADgTkPxJgDmOrNSsAPz8Rns77FAZdvDMqFjx1Lrqm8kPv9jzwOMO+a/2LpC
t6OkpFzGjiiskPjSnSn/tzo4TfWYoABjJaI7b3vEqmNEJSTAaxltZNtSXZucctEt
1ihnFdjr/wPwGK/5Wu+qGnfDbFNxBw==
=W4y1
-----END PGP SIGNATURE-----

----------------------------------------------------------------
Akihiko Odaki (6):
      net: checksum: Convert data to void *
      virtio-net: Fix size check in dhclient workaround
      virtio-net: Do not check for the queue before RSS
      virtio-net: Fix hash reporting when the queue changes
      virtio-net: Initialize hash reporting values
      virtio-net: Copy received header to buffer

hw/net/virtio-net.c    | 108 +++++++++++++++++++++++++++----------------------
 include/net/checksum.h |   2 +-
 net/checksum.c         |   4 +-
 3 files changed, 63 insertions(+), 51 deletions(-)

From: Akihiko Odaki <akihiko.odaki@daynix.com>

Convert the data parameter of net_checksum_calculate() to void * to
save unnecessary casts for callers.

Signed-off-by: Akihiko Odaki <akihiko.odaki@daynix.com>
Reviewed-by: Philippe Mathieu-Daudé <philmd@linaro.org>
Signed-off-by: Jason Wang <jasowang@redhat.com>
---
 include/net/checksum.h | 2 +-
 net/checksum.c         | 4 ++--
 2 files changed, 3 insertions(+), 3 deletions(-)

diff --git a/include/net/checksum.h b/include/net/checksum.h
index XXXXXXX..XXXXXXX 100644
--- a/include/net/checksum.h
+++ b/include/net/checksum.h
@@ -XXX,XX +XXX,XX @@ uint32_t net_checksum_add_cont(int len, uint8_t *buf, int seq);
 uint16_t net_checksum_finish(uint32_t sum);
 uint16_t net_checksum_tcpudp(uint16_t length, uint16_t proto,
                              uint8_t *addrs, uint8_t *buf);
-void net_checksum_calculate(uint8_t *data, int length, int csum_flag);
+void net_checksum_calculate(void *data, int length, int csum_flag);
 
 static inline uint32_t
 net_checksum_add(int len, uint8_t *buf)
diff --git a/net/checksum.c b/net/checksum.c
index XXXXXXX..XXXXXXX 100644
--- a/net/checksum.c
+++ b/net/checksum.c
@@ -XXX,XX +XXX,XX @@ uint16_t net_checksum_tcpudp(uint16_t length, uint16_t proto,
     return net_checksum_finish(sum);
 }
 
-void net_checksum_calculate(uint8_t *data, int length, int csum_flag)
+void net_checksum_calculate(void *data, int length, int csum_flag)
 {
     int mac_hdr_len, ip_len;
     struct ip_header *ip;
@@ -XXX,XX +XXX,XX @@ void net_checksum_calculate(uint8_t *data, int length, int csum_flag)
         return;
     }
 
-    ip = (struct ip_header *)(data + mac_hdr_len);
+    ip = (struct ip_header *)((uint8_t *)data + mac_hdr_len);
 
     if (IP_HEADER_VERSION(ip) != IP_HEADER_VERSION_4) {
         return; /* not IPv4 */
-- 
2.42.0

From: Akihiko Odaki <akihiko.odaki@daynix.com>

work_around_broken_dhclient() accesses IP and UDP headers to detect
relevant packets and to calculate checksums, but it didn't check if
the packet has size sufficient to accommodate them, causing out-of-bound
access hazards. Fix this by correcting the size requirement.

Fixes: 1d41b0c1ec66 ("Work around dhclient brokenness")
Cc: qemu-stable@nongnu.org
Signed-off-by: Akihiko Odaki <akihiko.odaki@daynix.com>
Signed-off-by: Jason Wang <jasowang@redhat.com>
---
 hw/net/virtio-net.c | 5 ++++-
 1 file changed, 4 insertions(+), 1 deletion(-)

From: Akihiko Odaki <akihiko.odaki@daynix.com>

virtio_net_can_receive() checks if the queue is ready, but RSS will
change the queue to use so, strictly speaking, we may still be able to
receive the packet even if the queue initially provided is not ready.
Perform RSS before virtio_net_can_receive() to cover such a case.

Fixes: 4474e37a5b3a ("virtio-net: implement RX RSS processing")
Signed-off-by: Akihiko Odaki <akihiko.odaki@daynix.com>
Signed-off-by: Jason Wang <jasowang@redhat.com>
---
 hw/net/virtio-net.c | 8 ++++----
 1 file changed, 4 insertions(+), 4 deletions(-)

diff --git a/hw/net/virtio-net.c b/hw/net/virtio-net.c
index XXXXXXX..XXXXXXX 100644
--- a/hw/net/virtio-net.c
+++ b/hw/net/virtio-net.c
@@ -XXX,XX +XXX,XX @@ static ssize_t virtio_net_receive_rcu(NetClientState *nc, const uint8_t *buf,
     size_t offset, i, guest_offset, j;
     ssize_t err;
 
-    if (!virtio_net_can_receive(nc)) {
-        return -1;
-    }
-
     if (!no_rss && n->rss_data.enabled && n->rss_data.enabled_software_rss) {
         int index = virtio_net_process_rss(nc, buf, size, &extra_hdr);
         if (index >= 0) {
@@ -XXX,XX +XXX,XX @@ static ssize_t virtio_net_receive_rcu(NetClientState *nc, const uint8_t *buf,
         }
     }
 
+    if (!virtio_net_can_receive(nc)) {
+        return -1;
+    }
+
     /* hdr_len refers to the header we supply to the guest */
     if (!virtio_net_has_buffers(q, size + n->guest_hdr_len - n->host_hdr_len)) {
         return 0;
-- 
2.42.0

From: Akihiko Odaki <akihiko.odaki@daynix.com>

virtio_net_process_rss() fills the values used for hash reporting, but
the values used to be thrown away with a recursive function call if
the queue changes after RSS. Avoid the function call to keep the values.

Fixes: a4c960eedcd2 ("virtio-net: Do not write hashes to peer buffer")
Buglink: https://issues.redhat.com/browse/RHEL-59572
Signed-off-by: Akihiko Odaki <akihiko.odaki@daynix.com>
Signed-off-by: Jason Wang <jasowang@redhat.com>
---
 hw/net/virtio-net.c | 14 +++++++-------
 1 file changed, 7 insertions(+), 7 deletions(-)

diff --git a/hw/net/virtio-net.c b/hw/net/virtio-net.c
index XXXXXXX..XXXXXXX 100644
--- a/hw/net/virtio-net.c
+++ b/hw/net/virtio-net.c
@@ -XXX,XX +XXX,XX @@ static int virtio_net_process_rss(NetClientState *nc, const uint8_t *buf,
 }
 
 static ssize_t virtio_net_receive_rcu(NetClientState *nc, const uint8_t *buf,
-                                      size_t size, bool no_rss)
+                                      size_t size)
 {
     VirtIONet *n = qemu_get_nic_opaque(nc);
-    VirtIONetQueue *q = virtio_net_get_subqueue(nc);
+    VirtIONetQueue *q;
     VirtIODevice *vdev = VIRTIO_DEVICE(n);
     VirtQueueElement *elems[VIRTQUEUE_MAX_SIZE];
     size_t lens[VIRTQUEUE_MAX_SIZE];
@@ -XXX,XX +XXX,XX @@ static ssize_t virtio_net_receive_rcu(NetClientState *nc, const uint8_t *buf,
     size_t offset, i, guest_offset, j;
     ssize_t err;
 
-    if (!no_rss && n->rss_data.enabled && n->rss_data.enabled_software_rss) {
+    if (n->rss_data.enabled && n->rss_data.enabled_software_rss) {
         int index = virtio_net_process_rss(nc, buf, size, &extra_hdr);
         if (index >= 0) {
-            NetClientState *nc2 =
-                qemu_get_subqueue(n->nic, index % n->curr_queue_pairs);
-            return virtio_net_receive_rcu(nc2, buf, size, true);
+            nc = qemu_get_subqueue(n->nic, index % n->curr_queue_pairs);
         }
     }
 
@@ -XXX,XX +XXX,XX @@ static ssize_t virtio_net_receive_rcu(NetClientState *nc, const uint8_t *buf,
         return -1;
     }
 
+    q = virtio_net_get_subqueue(nc);
+
     /* hdr_len refers to the header we supply to the guest */
     if (!virtio_net_has_buffers(q, size + n->guest_hdr_len - n->host_hdr_len)) {
         return 0;
@@ -XXX,XX +XXX,XX @@ static ssize_t virtio_net_do_receive(NetClientState *nc, const uint8_t *buf,
 {
     RCU_READ_LOCK_GUARD();
 
-    return virtio_net_receive_rcu(nc, buf, size, false);
+    return virtio_net_receive_rcu(nc, buf, size);
 }
 
 /*
-- 
2.42.0

From: Akihiko Odaki <akihiko.odaki@daynix.com>

The specification says hash_report should be set to
VIRTIO_NET_HASH_REPORT_NONE if VIRTIO_NET_F_HASH_REPORT is negotiated
but not configured with VIRTIO_NET_CTRL_MQ_RSS_CONFIG. However,
virtio_net_receive_rcu() instead wrote out the content of the extra_hdr
variable, which is not uninitialized in such a case.

Fix this by zeroing the extra_hdr.

Fixes: e22f0603fb2f ("virtio-net: reference implementation of hash report")
Signed-off-by: Akihiko Odaki <akihiko.odaki@daynix.com>
Reviewed-by: Philippe Mathieu-Daudé <philmd@linaro.org>
Signed-off-by: Jason Wang <jasowang@redhat.com>
---
 hw/net/virtio-net.c | 2 ++
 1 file changed, 2 insertions(+)

diff --git a/hw/net/virtio-net.c b/hw/net/virtio-net.c
index XXXXXXX..XXXXXXX 100644
--- a/hw/net/virtio-net.c
+++ b/hw/net/virtio-net.c
@@ -XXX,XX +XXX,XX @@ static ssize_t virtio_net_receive_rcu(NetClientState *nc, const uint8_t *buf,
     size_t offset, i, guest_offset, j;
     ssize_t err;
 
+    memset(&extra_hdr, 0, sizeof(extra_hdr));
+
     if (n->rss_data.enabled && n->rss_data.enabled_software_rss) {
         int index = virtio_net_process_rss(nc, buf, size, &extra_hdr);
         if (index >= 0) {
-- 
2.42.0

From: Akihiko Odaki <akihiko.odaki@daynix.com>

receive_header() used to cast the const qualifier of the pointer to the
received packet away to modify the header. Avoid this by copying the
received header to buffer.

Signed-off-by: Akihiko Odaki <akihiko.odaki@daynix.com>
Signed-off-by: Jason Wang <jasowang@redhat.com>
---
 hw/net/virtio-net.c | 85 ++++++++++++++++++++++++---------------------
 1 file changed, 46 insertions(+), 39 deletions(-)

diff --git a/hw/net/virtio-net.c b/hw/net/virtio-net.c
index XXXXXXX..XXXXXXX 100644
--- a/hw/net/virtio-net.c
+++ b/hw/net/virtio-net.c
@@ -XXX,XX +XXX,XX @@ static void virtio_net_hdr_swap(VirtIODevice *vdev, struct virtio_net_hdr *hdr)
  * cache.
  */
 static void work_around_broken_dhclient(struct virtio_net_hdr *hdr,
-                                        uint8_t *buf, size_t size)
+                                        size_t *hdr_len, const uint8_t *buf,
+                                        size_t buf_size, size_t *buf_offset)
 {
     size_t csum_size = ETH_HLEN + sizeof(struct ip_header) +
                        sizeof(struct udp_header);
 
+    buf += *buf_offset;
+    buf_size -= *buf_offset;
+
     if ((hdr->flags & VIRTIO_NET_HDR_F_NEEDS_CSUM) && /* missing csum */
-        (size >= csum_size && size < 1500) && /* normal sized MTU */
+        (buf_size >= csum_size && buf_size < 1500) && /* normal sized MTU */
         (buf[12] == 0x08 && buf[13] == 0x00) && /* ethertype == IPv4 */
         (buf[23] == 17) && /* ip.protocol == UDP */
         (buf[34] == 0 && buf[35] == 67)) { /* udp.srcport == bootps */
-        net_checksum_calculate(buf, size, CSUM_UDP);
+        memcpy((uint8_t *)hdr + *hdr_len, buf, csum_size);
+        net_checksum_calculate((uint8_t *)hdr + *hdr_len, csum_size, CSUM_UDP);
         hdr->flags &= ~VIRTIO_NET_HDR_F_NEEDS_CSUM;
+        *hdr_len += csum_size;
+        *buf_offset += csum_size;
     }
 }
 
-static void receive_header(VirtIONet *n, const struct iovec *iov, int iov_cnt,
-                           const void *buf, size_t size)
+static size_t receive_header(VirtIONet *n, struct virtio_net_hdr *hdr,
+                             const void *buf, size_t buf_size,
+                             size_t *buf_offset)
 {
-    if (n->has_vnet_hdr) {
-        /* FIXME this cast is evil */
-        void *wbuf = (void *)buf;
-        work_around_broken_dhclient(wbuf, wbuf + n->host_hdr_len,
-                                    size - n->host_hdr_len);
+    size_t hdr_len = n->guest_hdr_len;
 
-        if (n->needs_vnet_hdr_swap) {
-            virtio_net_hdr_swap(VIRTIO_DEVICE(n), wbuf);
-        }
-        iov_from_buf(iov, iov_cnt, 0, buf, sizeof(struct virtio_net_hdr));
-    } else {
-        struct virtio_net_hdr hdr = {
-            .flags = 0,
-            .gso_type = VIRTIO_NET_HDR_GSO_NONE
-        };
-        iov_from_buf(iov, iov_cnt, 0, &hdr, sizeof hdr);
+    memcpy(hdr, buf, sizeof(struct virtio_net_hdr));
+
+    *buf_offset = n->host_hdr_len;
+    work_around_broken_dhclient(hdr, &hdr_len, buf, buf_size, buf_offset);
+
+    if (n->needs_vnet_hdr_swap) {
+        virtio_net_hdr_swap(VIRTIO_DEVICE(n), hdr);
     }
+
+    return hdr_len;
 }
 
 static int receive_filter(VirtIONet *n, const uint8_t *buf, int size)
@@ -XXX,XX +XXX,XX @@ static int virtio_net_process_rss(NetClientState *nc, const uint8_t *buf,
     return (index == new_index) ? -1 : new_index;
 }
 
+typedef struct Header {
+    struct virtio_net_hdr_v1_hash virtio_net;
+    struct eth_header eth;
+    struct ip_header ip;
+    struct udp_header udp;
+} Header;
+
 static ssize_t virtio_net_receive_rcu(NetClientState *nc, const uint8_t *buf,
                                       size_t size)
 {
@@ -XXX,XX +XXX,XX @@ static ssize_t virtio_net_receive_rcu(NetClientState *nc, const uint8_t *buf,
     VirtQueueElement *elems[VIRTQUEUE_MAX_SIZE];
     size_t lens[VIRTQUEUE_MAX_SIZE];
     struct iovec mhdr_sg[VIRTQUEUE_MAX_SIZE];
-    struct virtio_net_hdr_v1_hash extra_hdr;
+    Header hdr;
     unsigned mhdr_cnt = 0;
     size_t offset, i, guest_offset, j;
     ssize_t err;
 
-    memset(&extra_hdr, 0, sizeof(extra_hdr));
+    memset(&hdr.virtio_net, 0, sizeof(hdr.virtio_net));
 
     if (n->rss_data.enabled && n->rss_data.enabled_software_rss) {
-        int index = virtio_net_process_rss(nc, buf, size, &extra_hdr);
+        int index = virtio_net_process_rss(nc, buf, size, &hdr.virtio_net);
         if (index >= 0) {
             nc = qemu_get_subqueue(n->nic, index % n->curr_queue_pairs);
         }
@@ -XXX,XX +XXX,XX @@ static ssize_t virtio_net_receive_rcu(NetClientState *nc, const uint8_t *buf,
             if (n->mergeable_rx_bufs) {
                 mhdr_cnt = iov_copy(mhdr_sg, ARRAY_SIZE(mhdr_sg),
                                     sg, elem->in_num,
-                                    offsetof(typeof(extra_hdr), hdr.num_buffers),
-                                    sizeof(extra_hdr.hdr.num_buffers));
+                                    offsetof(typeof(hdr),
+                                             virtio_net.hdr.num_buffers),
+                                    sizeof(hdr.virtio_net.hdr.num_buffers));
             }
 
-            receive_header(n, sg, elem->in_num, buf, size);
-            if (n->rss_data.populate_hash) {
-                offset = offsetof(typeof(extra_hdr), hash_value);
-                iov_from_buf(sg, elem->in_num, offset,
-                             (char *)&extra_hdr + offset,
-                             sizeof(extra_hdr.hash_value) +
-                             sizeof(extra_hdr.hash_report));
-            }
-            offset = n->host_hdr_len;
-            total += n->guest_hdr_len;
-            guest_offset = n->guest_hdr_len;
+            guest_offset = n->has_vnet_hdr ?
+                           receive_header(n, (struct virtio_net_hdr *)&hdr,
+                                          buf, size, &offset) :
+                           n->guest_hdr_len;
+
+            iov_from_buf(sg, elem->in_num, 0, &hdr, guest_offset);
+            total += guest_offset;
         } else {
             guest_offset = 0;
         }
@@ -XXX,XX +XXX,XX @@ static ssize_t virtio_net_receive_rcu(NetClientState *nc, const uint8_t *buf,
     }
 
     if (mhdr_cnt) {
-        virtio_stw_p(vdev, &extra_hdr.hdr.num_buffers, i);
+        virtio_stw_p(vdev, &hdr.virtio_net.hdr.num_buffers, i);
         iov_from_buf(mhdr_sg, mhdr_cnt,
                      0,
-                     &extra_hdr.hdr.num_buffers,
-                     sizeof extra_hdr.hdr.num_buffers);
+                     &hdr.virtio_net.hdr.num_buffers,
+                     sizeof hdr.virtio_net.hdr.num_buffers);
     }
 
     for (j = 0; j < i; j++) {
-- 
2.42.0