Series comparison

-[Qemu-devel] [PULL 00/14] Net patches
+[PULL 0/8] Net patches
-The following changes since commit 6632f6ff96f0537fc34cdc00c760656fc62e23c5:
+The following changes since commit 99d6b11b5b44d7dd64f4cb1973184e40a4a174f8:
-  Merge remote-tracking branch 'remotes/famz/tags/block-and-testing-pull-request' into staging (2017-07-17 11:46:36 +0100)
+  Merge tag 'pull-target-arm-20220922' of https://git.linaro.org/people/pmaydell/qemu-arm into staging (2022-09-26 13:38:26 -0400)
 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 bf769f742c3624952f125b303878a77ea870c156:
-  virtio-net: fix offload ctrl endian (2017-07-17 20:13:56 +0800)
+  virtio: del net client if net_init_tap_one failed (2022-09-27 15:14:37 +0800)
 ----------------------------------------------------------------
-- fix virtio-net ctrl offload endian
+----------------------------------------------------------------
-- vnet header support for variou COLO netfilters and compare thread
+Ding Hui (1):
       e1000e: set RX desc status with DD flag in a separate operation
-----------------------------------------------------------------
+Eugenio Pérez (6):
-Jason Wang (1):
+      vdpa: Make VhostVDPAState cvq_cmd_in_buffer control ack type
-      virtio-net: fix offload ctrl endian
+      vdpa: extract vhost_vdpa_net_load_mac from vhost_vdpa_net_load
       vdpa: Add vhost_vdpa_net_load_mq
       vdpa: validate MQ CVQ commands
       virtio-net: Update virtio-net curr_queue_pairs in vdpa backends
       vdpa: Allow MQ feature in SVQ
-Michal Privoznik (1):
+lu zhipeng (1):
-      virtion-net: Prefer is_power_of_2()
+      virtio: del net client if net_init_tap_one failed
-Zhang Chen (12):
+ hw/net/e1000e_core.c |  53 ++++++++++++++++++++++-
-      net: Add vnet_hdr_len arguments in NetClientState
+ hw/net/virtio-net.c  |  17 +++-----
-      net/net.c: Add vnet_hdr support in SocketReadState
+ net/tap.c            |  18 +++++---
-      net/filter-mirror.c: Introduce parameter for filter_send()
+ net/vhost-vdpa.c     | 119 +++++++++++++++++++++++++++++++++++++--------------
-      net/filter-mirror.c: Make filter mirror support vnet support.
+files changed, 157 insertions(+), 50 deletions(-)
       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 ++++++++++++++++
+Ding Hui (1):
- hw/net/virtio-net.c   |  4 ++-
+  e1000e: set RX desc status with DD flag in a separate operation
- include/net/net.h     | 10 ++++--
- net/colo-compare.c    | 84 ++++++++++++++++++++++++++++++++++++++++++---------
+Eugenio Pérez (6):
- net/colo.c            |  9 +++---
+  vdpa: Make VhostVDPAState cvq_cmd_in_buffer control ack type
- net/colo.h            |  4 ++-
+  vdpa: extract vhost_vdpa_net_load_mac from vhost_vdpa_net_load
- net/filter-mirror.c   | 75 +++++++++++++++++++++++++++++++++++++++++----
+  vdpa: Add vhost_vdpa_net_load_mq
- net/filter-rewriter.c | 37 ++++++++++++++++++++++-
+  vdpa: validate MQ CVQ commands
- net/net.c             | 37 ++++++++++++++++++++---
+  virtio-net: Update virtio-net curr_queue_pairs in vdpa backends
- net/socket.c          |  8 ++---
+  vdpa: Allow MQ feature in SVQ
- qemu-options.hx       | 19 ++++++------
-files changed, 265 insertions(+), 48 deletions(-)
+lu zhipeng (1):
   virtio: del net client if net_init_tap_one failed
  hw/net/e1000e_core.c |  53 ++++++++++++++++++++++-
  hw/net/virtio-net.c  |  17 +++-----
  net/tap.c            |  18 +++++---
  net/vhost-vdpa.c     | 119 +++++++++++++++++++++++++++++++++++++--------------
 files changed, 157 insertions(+), 50 deletions(-)
 --
 .7.4

-[Qemu-devel] [PULL 08/14] net/colo-compare.c: Make colo-compare support vnet_hdr_len
+[PULL 1/8] e1000e: set RX desc status with DD flag in a separate operation
-From: Zhang Chen <zhangchen.fnst@cn.fujitsu.com>
+From: Ding Hui <dinghui@sangfor.com.cn>
-We add the vnet_hdr_support option for colo-compare, default is disabled.
+Like commit 034d00d48581 ("e1000: set RX descriptor status in
-If you use virtio-net-pci or other driver needs vnet_hdr, please enable it.
+a separate operation"), there is also same issue in e1000e, which
-You can use it for example:
+would cause lost packets or stop sending packets to VM with DPDK.
 -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,
+Do similar fix in e1000e.
 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>
+Resolves: https://gitlab.com/qemu-project/qemu/-/issues/402
 Signed-off-by: Ding Hui <dinghui@sangfor.com.cn>
 Signed-off-by: Jason Wang <jasowang@redhat.com>
 ---
- net/colo-compare.c | 60 +++++++++++++++++++++++++++++++++++++++++++++++-------
+ hw/net/e1000e_core.c | 53 +++++++++++++++++++++++++++++++++++++++++++++++++++-
- qemu-options.hx    |  4 ++--
+file changed, 52 insertions(+), 1 deletion(-)
 files changed, 55 insertions(+), 9 deletions(-)
-diff --git a/net/colo-compare.c b/net/colo-compare.c
+diff --git a/hw/net/e1000e_core.c b/hw/net/e1000e_core.c
 index XXXXXXX..XXXXXXX 100644
---- a/net/colo-compare.c
+--- a/hw/net/e1000e_core.c
-+++ b/net/colo-compare.c
++++ b/hw/net/e1000e_core.c
-@@ -XXX,XX +XXX,XX @@ typedef struct CompareState {
+@@ -XXX,XX +XXX,XX @@ struct NetRxPkt *pkt, const E1000E_RSSInfo *rss_info,
      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) {
-+        /*
++static inline void
-+         * We send vnet header len make other module(like filter-redirector)
++e1000e_pci_dma_write_rx_desc(E1000ECore *core, dma_addr_t addr,
-+         * know how to parse net packet correctly.
++                             uint8_t *desc, dma_addr_t len)
-+         */
++{
-+        len = htonl(vnet_hdr_len);
++    PCIDevice *dev = core->owner;
-+        ret = qemu_chr_fe_write_all(&s->chr_out, (uint8_t *)&len, sizeof(len));
++
-+        if (ret != sizeof(len)) {
++    if (e1000e_rx_use_legacy_descriptor(core)) {
-+            goto err;
++        struct e1000_rx_desc *d = (struct e1000_rx_desc *) desc;
 +        size_t offset = offsetof(struct e1000_rx_desc, status);
 +        uint8_t status = d->status;
 +
 +        d->status &= ~E1000_RXD_STAT_DD;
 +        pci_dma_write(dev, addr, desc, len);
 +
 +        if (status & E1000_RXD_STAT_DD) {
 +            d->status = status;
 +            pci_dma_write(dev, addr + offset, &status, sizeof(status));
 +        }
 +    } else {
 +        if (core->mac[RCTL] & E1000_RCTL_DTYP_PS) {
 +            union e1000_rx_desc_packet_split *d =
 +                (union e1000_rx_desc_packet_split *) desc;
 +            size_t offset = offsetof(union e1000_rx_desc_packet_split,
 +                wb.middle.status_error);
 +            uint32_t status = d->wb.middle.status_error;
 +
 +            d->wb.middle.status_error &= ~E1000_RXD_STAT_DD;
 +            pci_dma_write(dev, addr, desc, len);
 +
 +            if (status & E1000_RXD_STAT_DD) {
 +                d->wb.middle.status_error = status;
 +                pci_dma_write(dev, addr + offset, &status, sizeof(status));
 +            }
 +        } else {
 +            union e1000_rx_desc_extended *d =
 +                (union e1000_rx_desc_extended *) desc;
 +            size_t offset = offsetof(union e1000_rx_desc_extended,
 +                wb.upper.status_error);
 +            uint32_t status = d->wb.upper.status_error;
 +
 +            d->wb.upper.status_error &= ~E1000_RXD_STAT_DD;
 +            pci_dma_write(dev, addr, desc, len);
 +
 +            if (status & E1000_RXD_STAT_DD) {
 +                d->wb.upper.status_error = status;
 +                pci_dma_write(dev, addr + offset, &status, sizeof(status));
 +            }
 +        }
 +    }
-+
-     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,
+ typedef struct e1000e_ba_state_st {
-+                                 bool value,
+     uint16_t written[MAX_PS_BUFFERS];
-+                                 Error **errp)
+     uint8_t cur_idx;
-+{
+@@ -XXX,XX +XXX,XX @@ e1000e_write_packet_to_guest(E1000ECore *core, struct NetRxPkt *pkt,
-+    CompareState *s = COLO_COMPARE(obj);
-+
+         e1000e_write_rx_descr(core, desc, is_last ? core->rx_pkt : NULL,
-+    s->vnet_hdr = value;
+                            rss_info, do_ps ? ps_hdr_len : 0, &bastate.written);
-+}
+-        pci_dma_write(d, base, &desc, core->rx_desc_len);
-+
++        e1000e_pci_dma_write_rx_desc(core, base, desc, core->rx_desc_len);
- static void compare_pri_rs_finalize(SocketReadState *pri_rs)
- {
+         e1000e_ring_advance(core, rxi,
-     CompareState *s = container_of(pri_rs, CompareState, pri_rs);
+                             core->rx_desc_len / E1000_MIN_RX_DESC_LEN);
      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 07/14] net/colo-compare.c: Introduce parameter for compare_chr_send()
+[PULL 2/8] vdpa: Make VhostVDPAState cvq_cmd_in_buffer control ack type
-From: Zhang Chen <zhangchen.fnst@cn.fujitsu.com>
+From: Eugenio Pérez <eperezma@redhat.com>
-This patch change the compare_chr_send() parameter from CharBackend to CompareState,
+This allows to simplify the code. Rename to status while we're at it.
 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: Eugenio Pérez <eperezma@redhat.com>
 Signed-off-by: Jason Wang <jasowang@redhat.com>
 ---
- net/colo-compare.c | 14 +++++++-------
+ net/vhost-vdpa.c | 23 ++++++++++++-----------
-file changed, 7 insertions(+), 7 deletions(-)
+file changed, 12 insertions(+), 11 deletions(-)
-diff --git a/net/colo-compare.c b/net/colo-compare.c
+diff --git a/net/vhost-vdpa.c b/net/vhost-vdpa.c
 index XXXXXXX..XXXXXXX 100644
---- a/net/colo-compare.c
+--- a/net/vhost-vdpa.c
-+++ b/net/colo-compare.c
++++ b/net/vhost-vdpa.c
-@@ -XXX,XX +XXX,XX @@ enum {
+@@ -XXX,XX +XXX,XX @@ typedef struct VhostVDPAState {
-     SECONDARY_IN,
+     VHostNetState *vhost_net;
- };
+     /* Control commands shadow buffers */
--static int compare_chr_send(CharBackend *out,
+-    void *cvq_cmd_out_buffer, *cvq_cmd_in_buffer;
-+static int compare_chr_send(CompareState *s,
++    void *cvq_cmd_out_buffer;
-                             const uint8_t *buf,
++    virtio_net_ctrl_ack *status;
-                             uint32_t size);
++
+     bool started;
-@@ -XXX,XX +XXX,XX @@ static void colo_compare_connection(void *opaque, void *user_data)
+ } VhostVDPAState;
-         }
+@@ -XXX,XX +XXX,XX @@ static void vhost_vdpa_cleanup(NetClientState *nc)
-         if (result) {
+     struct vhost_dev *dev = &s->vhost_net->dev;
--            ret = compare_chr_send(&s->chr_out, pkt->data, pkt->size);
-+            ret = compare_chr_send(s, pkt->data, pkt->size);
+     qemu_vfree(s->cvq_cmd_out_buffer);
-             if (ret < 0) {
+-    qemu_vfree(s->cvq_cmd_in_buffer);
-                 error_report("colo_send_primary_packet failed");
++    qemu_vfree(s->status);
-             }
+     if (dev->vq_index + dev->nvqs == dev->vq_index_end) {
-@@ -XXX,XX +XXX,XX @@ static void colo_compare_connection(void *opaque, void *user_data)
+         g_clear_pointer(&s->vhost_vdpa.iova_tree, vhost_iova_tree_delete);
      }
@@ -XXX,XX +XXX,XX @@ static int vhost_vdpa_net_cvq_start(NetClientState *nc)
          return r;
      }
 -    r = vhost_vdpa_cvq_map_buf(&s->vhost_vdpa, s->cvq_cmd_in_buffer,
 +    r = vhost_vdpa_cvq_map_buf(&s->vhost_vdpa, s->status,
                                 vhost_vdpa_net_cvq_cmd_page_len(), true);
      if (unlikely(r < 0)) {
          vhost_vdpa_cvq_unmap_buf(&s->vhost_vdpa, s->cvq_cmd_out_buffer);
@@ -XXX,XX +XXX,XX @@ static void vhost_vdpa_net_cvq_stop(NetClientState *nc)
      if (s->vhost_vdpa.shadow_vqs_enabled) {
          vhost_vdpa_cvq_unmap_buf(&s->vhost_vdpa, s->cvq_cmd_out_buffer);
 -        vhost_vdpa_cvq_unmap_buf(&s->vhost_vdpa, s->cvq_cmd_in_buffer);
 +        vhost_vdpa_cvq_unmap_buf(&s->vhost_vdpa, s->status);
      }
  }
--static int compare_chr_send(CharBackend *out,
+@@ -XXX,XX +XXX,XX @@ static ssize_t vhost_vdpa_net_cvq_add(VhostVDPAState *s, size_t out_len,
-+static int compare_chr_send(CompareState *s,
+         .iov_len = out_len,
-                             const uint8_t *buf,
+     };
-                             uint32_t size)
+     const struct iovec in = {
- {
+-        .iov_base = s->cvq_cmd_in_buffer,
-@@ -XXX,XX +XXX,XX @@ static int compare_chr_send(CharBackend *out,
++        .iov_base = s->status,
-         return 0;
+         .iov_len = sizeof(virtio_net_ctrl_ack),
      };
      VhostShadowVirtqueue *svq = g_ptr_array_index(s->vhost_vdpa.shadow_vqs, 0);
@@ -XXX,XX +XXX,XX @@ static int vhost_vdpa_net_load(NetClientState *nc)
              return dev_written;
          }
 -        return *((virtio_net_ctrl_ack *)s->cvq_cmd_in_buffer) != VIRTIO_NET_OK;
 +        return *s->status != VIRTIO_NET_OK;
      }
--    ret = qemu_chr_fe_write_all(out, (uint8_t *)&len, sizeof(len));
+     return 0;
-+    ret = qemu_chr_fe_write_all(&s->chr_out, (uint8_t *)&len, sizeof(len));
+@@ -XXX,XX +XXX,XX @@ static int vhost_vdpa_net_handle_ctrl_avail(VhostShadowVirtqueue *svq,
-     if (ret != sizeof(len)) {
+         goto out;
          goto err;
      }
--    ret = qemu_chr_fe_write_all(out, (uint8_t *)buf, size);
+-    memcpy(&status, s->cvq_cmd_in_buffer, sizeof(status));
-+    ret = qemu_chr_fe_write_all(&s->chr_out, (uint8_t *)buf, size);
+-    if (status != VIRTIO_NET_OK) {
-     if (ret != size) {
++    if (*s->status != VIRTIO_NET_OK) {
-         goto err;
+         return VIRTIO_NET_ERR;
      }
-@@ -XXX,XX +XXX,XX @@ static void compare_pri_rs_finalize(SocketReadState *pri_rs)
+@@ -XXX,XX +XXX,XX @@ static NetClientState *net_vhost_vdpa_init(NetClientState *peer,
-     if (packet_enqueue(s, PRIMARY_IN)) {
+         s->cvq_cmd_out_buffer = qemu_memalign(qemu_real_host_page_size(),
-         trace_colo_compare_main("primary: unsupported packet in");
+                                             vhost_vdpa_net_cvq_cmd_page_len());
--        compare_chr_send(&s->chr_out, pri_rs->buf, pri_rs->packet_len);
+         memset(s->cvq_cmd_out_buffer, 0, vhost_vdpa_net_cvq_cmd_page_len());
-+        compare_chr_send(s, pri_rs->buf, pri_rs->packet_len);
+-        s->cvq_cmd_in_buffer = qemu_memalign(qemu_real_host_page_size(),
-     } else {
+-                                            vhost_vdpa_net_cvq_cmd_page_len());
-         /* compare connection */
+-        memset(s->cvq_cmd_in_buffer, 0, vhost_vdpa_net_cvq_cmd_page_len());
-         g_queue_foreach(&s->conn_list, colo_compare_connection, s);
++        s->status = qemu_memalign(qemu_real_host_page_size(),
-@@ -XXX,XX +XXX,XX @@ static void colo_flush_packets(void *opaque, void *user_data)
++                                  vhost_vdpa_net_cvq_cmd_page_len());
++        memset(s->status, 0, vhost_vdpa_net_cvq_cmd_page_len());
-     while (!g_queue_is_empty(&conn->primary_list)) {
-         pkt = g_queue_pop_head(&conn->primary_list);
+         s->vhost_vdpa.shadow_vq_ops = &vhost_vdpa_net_svq_ops;
--        compare_chr_send(&s->chr_out, pkt->data, pkt->size);
+         s->vhost_vdpa.shadow_vq_ops_opaque = s;
 +        compare_chr_send(s, pkt->data, pkt->size);
          packet_destroy(pkt, NULL);
      }
      while (!g_queue_is_empty(&conn->secondary_list)) {
 --
 .7.4

-[Qemu-devel] [PULL 02/14] net/net.c: Add vnet_hdr support in SocketReadState
+[PULL 3/8] vdpa: extract vhost_vdpa_net_load_mac from vhost_vdpa_net_load
-From: Zhang Chen <zhangchen.fnst@cn.fujitsu.com>
+From: Eugenio Pérez <eperezma@redhat.com>
-We add a flag to decide whether net_fill_rstate() need read
+Since there may be many commands we need to issue to load the NIC
-the vnet_hdr_len or not.
+state, let's split them in individual functions
-Signed-off-by: Zhang Chen <zhangchen.fnst@cn.fujitsu.com>
+Signed-off-by: Eugenio Pérez <eperezma@redhat.com>
 Suggested-by: Jason Wang <jasowang@redhat.com>
 Signed-off-by: Jason Wang <jasowang@redhat.com>
 ---
- include/net/net.h   |  9 +++++++--
+ net/vhost-vdpa.c | 62 ++++++++++++++++++++++++++++++++++++--------------------
- net/colo-compare.c  |  4 ++--
+file changed, 40 insertions(+), 22 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/net/vhost-vdpa.c b/net/vhost-vdpa.c
 index XXXXXXX..XXXXXXX 100644
---- a/include/net/net.h
+--- a/net/vhost-vdpa.c
-+++ b/include/net/net.h
++++ b/net/vhost-vdpa.c
-@@ -XXX,XX +XXX,XX @@ typedef struct NICState {
+@@ -XXX,XX +XXX,XX @@ static ssize_t vhost_vdpa_net_cvq_add(VhostVDPAState *s, size_t out_len,
- } NICState;
+     return vhost_svq_poll(svq);
+ }
- struct SocketReadState {
--    int state; /* 0 = getting length, 1 = getting data */
++static ssize_t vhost_vdpa_net_load_cmd(VhostVDPAState *s, uint8_t class,
-+    /* 0 = getting length, 1 = getting vnet header length, 2 = getting data */
++                                       uint8_t cmd, const void *data,
-+    int state;
++                                       size_t data_size)
-+    /* This flag decide whether to read the vnet_hdr_len field */
++{
-+    bool vnet_hdr;
++    const struct virtio_net_ctrl_hdr ctrl = {
-     uint32_t index;
++        .class = class,
-     uint32_t packet_len;
++        .cmd = cmd,
-+    uint32_t vnet_hdr_len;
++    };
-     uint8_t buf[NET_BUFSIZE];
++
-     SocketReadStateFinalize *finalize;
++    assert(data_size < vhost_vdpa_net_cvq_cmd_page_len() - sizeof(ctrl));
- };
++
-@@ -XXX,XX +XXX,XX @@ ssize_t qemu_deliver_packet_iov(NetClientState *sender,
++    memcpy(s->cvq_cmd_out_buffer, &ctrl, sizeof(ctrl));
- void print_net_client(Monitor *mon, NetClientState *nc);
++    memcpy(s->cvq_cmd_out_buffer + sizeof(ctrl), data, data_size);
- void hmp_info_network(Monitor *mon, const QDict *qdict);
++
- void net_socket_rs_init(SocketReadState *rs,
++    return vhost_vdpa_net_cvq_add(s, sizeof(ctrl) + data_size,
--                        SocketReadStateFinalize *finalize);
++                                  sizeof(virtio_net_ctrl_ack));
-+                        SocketReadStateFinalize *finalize,
++}
-+                        bool vnet_hdr);
++
++static int vhost_vdpa_net_load_mac(VhostVDPAState *s, const VirtIONet *n)
- /* NIC info */
++{
++    uint64_t features = n->parent_obj.guest_features;
-diff --git a/net/colo-compare.c b/net/colo-compare.c
++    if (features & BIT_ULL(VIRTIO_NET_F_CTRL_MAC_ADDR)) {
-index XXXXXXX..XXXXXXX 100644
++        ssize_t dev_written = vhost_vdpa_net_load_cmd(s, VIRTIO_NET_CTRL_MAC,
---- a/net/colo-compare.c
++                                                  VIRTIO_NET_CTRL_MAC_ADDR_SET,
-+++ b/net/colo-compare.c
++                                                  n->mac, sizeof(n->mac));
-@@ -XXX,XX +XXX,XX @@ static void colo_compare_complete(UserCreatable *uc, Error **errp)
++        if (unlikely(dev_written < 0)) {
-         return;
++            return dev_written;
 +        }
 +
 +        return *s->status != VIRTIO_NET_OK;
 +    }
 +
 +    return 0;
 +}
 +
  static int vhost_vdpa_net_load(NetClientState *nc)
  {
      VhostVDPAState *s = DO_UPCAST(VhostVDPAState, nc, nc);
 -    const struct vhost_vdpa *v = &s->vhost_vdpa;
 +    struct vhost_vdpa *v = &s->vhost_vdpa;
      const VirtIONet *n;
 -    uint64_t features;
 +    int r;
      assert(nc->info->type == NET_CLIENT_DRIVER_VHOST_VDPA);
@@ -XXX,XX +XXX,XX @@ static int vhost_vdpa_net_load(NetClientState *nc)
      }
--    net_socket_rs_init(&s->pri_rs, compare_pri_rs_finalize);
+     n = VIRTIO_NET(v->dev->vdev);
--    net_socket_rs_init(&s->sec_rs, compare_sec_rs_finalize);
+-    features = n->parent_obj.guest_features;
-+    net_socket_rs_init(&s->pri_rs, compare_pri_rs_finalize, false);
+-    if (features & BIT_ULL(VIRTIO_NET_F_CTRL_MAC_ADDR)) {
-+    net_socket_rs_init(&s->sec_rs, compare_sec_rs_finalize, false);
+-        const struct virtio_net_ctrl_hdr ctrl = {
+-            .class = VIRTIO_NET_CTRL_MAC,
-     g_queue_init(&s->conn_list);
+-            .cmd = VIRTIO_NET_CTRL_MAC_ADDR_SET,
+-        };
-diff --git a/net/filter-mirror.c b/net/filter-mirror.c
+-        char *cursor = s->cvq_cmd_out_buffer;
-index XXXXXXX..XXXXXXX 100644
+-        ssize_t dev_written;
---- a/net/filter-mirror.c
+-
-+++ b/net/filter-mirror.c
+-        memcpy(cursor, &ctrl, sizeof(ctrl));
-@@ -XXX,XX +XXX,XX @@ static void filter_redirector_setup(NetFilterState *nf, Error **errp)
+-        cursor += sizeof(ctrl);
-         }
+-        memcpy(cursor, n->mac, sizeof(n->mac));
 -
 -        dev_written = vhost_vdpa_net_cvq_add(s, sizeof(ctrl) + sizeof(n->mac),
 -                                             sizeof(virtio_net_ctrl_ack));
 -        if (unlikely(dev_written < 0)) {
 -            return dev_written;
 -        }
 -
 -        return *s->status != VIRTIO_NET_OK;
 +    r = vhost_vdpa_net_load_mac(s, n);
 +    if (unlikely(r < 0)) {
 +        return r;
      }
--    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;
 --
 .7.4

-[Qemu-devel] [PULL 11/14] net/filter-rewriter.c: Make filter-rewriter support vnet_hdr_len
+[PULL 4/8] vdpa: Add vhost_vdpa_net_load_mq
-From: Zhang Chen <zhangchen.fnst@cn.fujitsu.com>
+From: Eugenio Pérez <eperezma@redhat.com>
-We add the vnet_hdr_support option for filter-rewriter, default is disabled.
+Same way as with the MAC, restore the expected number of queues at
-If you use virtio-net-pci or other driver needs vnet_hdr, please enable it.
+device's start.
 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
+Signed-off-by: Eugenio Pérez <eperezma@redhat.com>
 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 ++++++++++++++++++++++++++++++++++++-
+ net/vhost-vdpa.c | 26 ++++++++++++++++++++++++++
- qemu-options.hx       |  4 ++--
+file changed, 26 insertions(+)
 files changed, 38 insertions(+), 3 deletions(-)
-diff --git a/net/filter-rewriter.c b/net/filter-rewriter.c
+diff --git a/net/vhost-vdpa.c b/net/vhost-vdpa.c
 index XXXXXXX..XXXXXXX 100644
---- a/net/filter-rewriter.c
+--- a/net/vhost-vdpa.c
-+++ b/net/filter-rewriter.c
++++ b/net/vhost-vdpa.c
-@@ -XXX,XX +XXX,XX @@
+@@ -XXX,XX +XXX,XX @@ static int vhost_vdpa_net_load_mac(VhostVDPAState *s, const VirtIONet *n)
- #include "qemu-common.h"
+     return 0;
- #include "qapi/error.h"
+ }
- #include "qapi/qmp/qerror.h"
-+#include "qemu/error-report.h"
++static int vhost_vdpa_net_load_mq(VhostVDPAState *s,
- #include "qapi-visit.h"
++                                  const VirtIONet *n)
- #include "qom/object.h"
++{
- #include "qemu/main-loop.h"
++    struct virtio_net_ctrl_mq mq;
-@@ -XXX,XX +XXX,XX @@ typedef struct RewriterState {
++    uint64_t features = n->parent_obj.guest_features;
-     NetQueue *incoming_queue;
++    ssize_t dev_written;
      /* 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) {
++    if (!(features & BIT_ULL(VIRTIO_NET_F_MQ))) {
-+        vnet_hdr_len = nf->netdev->vnet_hdr_len;
++        return 0;
 +    }
 +
-+    pkt = packet_new(buf, size, vnet_hdr_len);
++    mq.virtqueue_pairs = cpu_to_le16(n->curr_queue_pairs);
-     g_free(buf);
++    dev_written = vhost_vdpa_net_load_cmd(s, VIRTIO_NET_CTRL_MQ,
++                                          VIRTIO_NET_CTRL_MQ_VQ_PAIRS_SET, &mq,
-     /*
++                                          sizeof(mq));
-@@ -XXX,XX +XXX,XX @@ static void colo_rewriter_setup(NetFilterState *nf, Error **errp)
++    if (unlikely(dev_written < 0)) {
-     s->incoming_queue = qemu_new_net_queue(qemu_netfilter_pass_to_next, nf);
++        return dev_written;
- }
++    }
 +static bool filter_rewriter_get_vnet_hdr(Object *obj, Error **errp)
 +{
 +    RewriterState *s = FILTER_COLO_REWRITER(obj);
 +
-+    return s->vnet_hdr;
++    return *s->status != VIRTIO_NET_OK;
 +}
 +
-+static void filter_rewriter_set_vnet_hdr(Object *obj,
+ static int vhost_vdpa_net_load(NetClientState *nc)
 +                                         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);
+     VhostVDPAState *s = DO_UPCAST(VhostVDPAState, nc, nc);
-@@ -XXX,XX +XXX,XX @@ static const TypeInfo colo_rewriter_info = {
+@@ -XXX,XX +XXX,XX @@ static int vhost_vdpa_net_load(NetClientState *nc)
-     .name = TYPE_FILTER_REWRITER,
+     if (unlikely(r < 0)) {
-     .parent = TYPE_NETFILTER,
+         return r;
-     .class_init = colo_rewriter_class_init,
+     }
-+    .instance_init = filter_rewriter_init,
++    r = vhost_vdpa_net_load_mq(s, n);
-     .instance_size = sizeof(RewriterState),
++    if (unlikely(r)) {
- };
++        return r;
++    }
-diff --git a/qemu-options.hx b/qemu-options.hx
-index XXXXXXX..XXXXXXX 100644
+     return 0;
---- 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 14/14] virtio-net: fix offload ctrl endian
+[PULL 5/8] vdpa: validate MQ CVQ commands
-Spec said offloads should be le64, so use virtio_ldq_p() to guarantee
+From: Eugenio Pérez <eperezma@redhat.com>
 valid endian.
-Fixes: 644c98587d4c ("virtio-net: dynamic network offloads configuration")
+So we are sure we can update the device model properly before sending to
-Cc: qemu-stable@nongnu.org
+the device.
-Cc: Dmitry Fleytman <dfleytma@redhat.com>
 Signed-off-by: Eugenio Pérez <eperezma@redhat.com>
 Signed-off-by: Jason Wang <jasowang@redhat.com>
 ---
- hw/net/virtio-net.c | 2 ++
+ net/vhost-vdpa.c | 9 +++++++++
-file changed, 2 insertions(+)
+file changed, 9 insertions(+)
-diff --git a/hw/net/virtio-net.c b/hw/net/virtio-net.c
+diff --git a/net/vhost-vdpa.c b/net/vhost-vdpa.c
 index XXXXXXX..XXXXXXX 100644
---- a/hw/net/virtio-net.c
+--- a/net/vhost-vdpa.c
-+++ b/hw/net/virtio-net.c
++++ b/net/vhost-vdpa.c
-@@ -XXX,XX +XXX,XX @@ static int virtio_net_handle_offloads(VirtIONet *n, uint8_t cmd,
+@@ -XXX,XX +XXX,XX @@ static bool vhost_vdpa_net_cvq_validate_cmd(const void *out_buf, size_t len)
-     if (cmd == VIRTIO_NET_CTRL_GUEST_OFFLOADS_SET) {
+                           __func__, ctrl.cmd);
-         uint64_t supported_offloads;
+         };
+         break;
-+        offloads = virtio_ldq_p(vdev, &offloads);
++    case VIRTIO_NET_CTRL_MQ:
-+
++        switch (ctrl.cmd) {
-         if (!n->has_vnet_hdr) {
++        case VIRTIO_NET_CTRL_MQ_VQ_PAIRS_SET:
-             return VIRTIO_NET_ERR;
++            return true;
-         }
++        default:
 +            qemu_log_mask(LOG_GUEST_ERROR, "%s: invalid mq cmd %u\n",
 +                          __func__, ctrl.cmd);
 +        };
 +        break;
      default:
          qemu_log_mask(LOG_GUEST_ERROR, "%s: invalid control class %u\n",
                        __func__, ctrl.class);
 --
 .7.4

-[Qemu-devel] [PULL 13/14] virtion-net: Prefer is_power_of_2()
+[PULL 6/8] virtio-net: Update virtio-net curr_queue_pairs in vdpa backends
-From: Michal Privoznik <mprivozn@redhat.com>
+From: Eugenio Pérez <eperezma@redhat.com>
-We have a function that checks if given number is power of two.
+It was returned as error before. Instead of it, simply update the
-We should prefer it instead of expanding the check on our own.
+corresponding field so qemu can send it in the migration data.
-Signed-off-by: Michal Privoznik <mprivozn@redhat.com>
+Signed-off-by: Eugenio Pérez <eperezma@redhat.com>
 Acked-by: Si-Wei Liu <si-wei.liu@oracle.com>
 Signed-off-by: Jason Wang <jasowang@redhat.com>
 ---
- hw/net/virtio-net.c | 2 +-
+ hw/net/virtio-net.c | 17 ++++++-----------
-file changed, 1 insertion(+), 1 deletion(-)
+file changed, 6 insertions(+), 11 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_device_realize(DeviceState *dev, Error **errp)
+@@ -XXX,XX +XXX,XX @@ static int virtio_net_handle_mq(VirtIONet *n, uint8_t cmd,
-      */
+         return VIRTIO_NET_ERR;
-     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))) {
+-    /* Avoid changing the number of queue_pairs for vdpa device in
-+        !is_power_of_2(n->net_conf.rx_queue_size)) {
+-     * userspace handler. A future fix is needed to handle the mq
-         error_setg(errp, "Invalid rx_queue_size (= %" PRIu16 "), "
+-     * change in userspace handler with vhost-vdpa. Let's disable
-                    "must be a power of 2 between %d and %d.",
+-     * the mq handling from userspace for now and only allow get
-                    n->net_conf.rx_queue_size, VIRTIO_NET_RX_QUEUE_MIN_SIZE,
+-     * done through the kernel. Ripples may be seen when falling
 -     * back to userspace, but without doing it qemu process would
 -     * crash on a recursive entry to virtio_net_set_status().
 -     */
 +    n->curr_queue_pairs = queue_pairs;
      if (nc->peer && nc->peer->info->type == NET_CLIENT_DRIVER_VHOST_VDPA) {
 -        return VIRTIO_NET_ERR;
 +        /*
 +         * Avoid updating the backend for a vdpa device: We're only interested
 +         * in updating the device model queues.
 +         */
 +        return VIRTIO_NET_OK;
      }
 -
 -    n->curr_queue_pairs = queue_pairs;
      /* stop the backend before changing the number of queue_pairs to avoid handling a
       * disabled queue */
      virtio_net_set_status(vdev, vdev->status);
 --
 .7.4

-[Qemu-devel] [PULL 12/14] docs/colo-proxy.txt: Update colo-proxy usage of net driver with vnet_header
+[PULL 7/8] vdpa: Allow MQ feature in SVQ
-From: Zhang Chen <zhangchen.fnst@cn.fujitsu.com>
+From: Eugenio Pérez <eperezma@redhat.com>
-Signed-off-by: Zhang Chen <zhangchen.fnst@cn.fujitsu.com>
+Finally enable SVQ with MQ feature.
 Signed-off-by: Eugenio Pérez <eperezma@redhat.com>
 Signed-off-by: Jason Wang <jasowang@redhat.com>
 ---
- docs/colo-proxy.txt | 26 ++++++++++++++++++++++++++
+ net/vhost-vdpa.c | 1 +
-file changed, 26 insertions(+)
+file changed, 1 insertion(+)
-diff --git a/docs/colo-proxy.txt b/docs/colo-proxy.txt
+diff --git a/net/vhost-vdpa.c b/net/vhost-vdpa.c
 index XXXXXXX..XXXXXXX 100644
---- a/docs/colo-proxy.txt
+--- a/net/vhost-vdpa.c
-+++ b/docs/colo-proxy.txt
++++ b/net/vhost-vdpa.c
-@@ -XXX,XX +XXX,XX @@ Secondary(ip:3.3.3.8):
+@@ -XXX,XX +XXX,XX @@ static const uint64_t vdpa_svq_device_features =
- -chardev socket,id=red1,host=3.3.3.3,port=9004
+     BIT_ULL(VIRTIO_NET_F_MRG_RXBUF) |
- -object filter-redirector,id=f1,netdev=hn0,queue=tx,indev=red0
+     BIT_ULL(VIRTIO_NET_F_STATUS) |
- -object filter-redirector,id=f2,netdev=hn0,queue=rx,outdev=red1
+     BIT_ULL(VIRTIO_NET_F_CTRL_VQ) |
-+-object filter-rewriter,id=f3,netdev=hn0,queue=all
++    BIT_ULL(VIRTIO_NET_F_MQ) |
-+
+     BIT_ULL(VIRTIO_F_ANY_LAYOUT) |
-+If you want to use virtio-net-pci or other driver with vnet_header:
+     BIT_ULL(VIRTIO_NET_F_CTRL_MAC_ADDR) |
-+
+     BIT_ULL(VIRTIO_NET_F_RSC_EXT) |
 +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

-[Qemu-devel] [PULL 01/14] net: Add vnet_hdr_len arguments in NetClientState
+[PULL 8/8] virtio: del net client if net_init_tap_one failed
-From: Zhang Chen <zhangchen.fnst@cn.fujitsu.com>
+From: lu zhipeng <luzhipeng@cestc.cn>
-Add vnet_hdr_len arguments in NetClientState
+If the net tap initializes successful, but failed during
-that make other module get real vnet_hdr_len easily.
+network card hot-plugging, the net-tap will remains,
 so cleanup.
-Signed-off-by: Zhang Chen <zhangchen.fnst@cn.fujitsu.com>
+Signed-off-by: lu zhipeng <luzhipeng@cestc.cn>
 Signed-off-by: Jason Wang <jasowang@redhat.com>
 ---
- include/net/net.h | 1 +
+ net/tap.c | 18 ++++++++++++------
- net/net.c         | 1 +
+file changed, 12 insertions(+), 6 deletions(-)
 files changed, 2 insertions(+)
-diff --git a/include/net/net.h b/include/net/net.h
+diff --git a/net/tap.c b/net/tap.c
 index XXXXXXX..XXXXXXX 100644
---- a/include/net/net.h
+--- a/net/tap.c
-+++ b/include/net/net.h
++++ b/net/tap.c
-@@ -XXX,XX +XXX,XX @@ struct NetClientState {
+@@ -XXX,XX +XXX,XX @@ static void net_init_tap_one(const NetdevTapOptions *tap, NetClientState *peer,
-     unsigned int queue_index;
+     tap_set_sndbuf(s->fd, tap, &err);
-     unsigned rxfilter_notify_enabled:1;
+     if (err) {
-     int vring_enable;
+         error_propagate(errp, err);
-+    int vnet_hdr_len;
+-        return;
-     QTAILQ_HEAD(NetFilterHead, NetFilterState) filters;
++        goto failed;
  };
 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 @@ void qemu_set_vnet_hdr_len(NetClientState *nc, int len)
          return;
      }
-+    nc->vnet_hdr_len = len;
+     if (tap->has_fd || tap->has_fds) {
-     nc->info->set_vnet_hdr_len(nc, len);
+@@ -XXX,XX +XXX,XX @@ static void net_init_tap_one(const NetdevTapOptions *tap, NetClientState *peer,
                  } else {
                      warn_report_err(err);
                  }
 -                return;
 +                goto failed;
              }
              if (!g_unix_set_fd_nonblocking(vhostfd, true, NULL)) {
                  error_setg_errno(errp, errno, "%s: Can't use file descriptor %d",
                                   name, fd);
 -                return;
 +                goto failed;
              }
          } else {
              vhostfd = open("/dev/vhost-net", O_RDWR);
@@ -XXX,XX +XXX,XX @@ static void net_init_tap_one(const NetdevTapOptions *tap, NetClientState *peer,
                      warn_report("tap: open vhost char device failed: %s",
                                  strerror(errno));
                  }
 -                return;
 +                goto failed;
              }
              if (!g_unix_set_fd_nonblocking(vhostfd, true, NULL)) {
                  error_setg_errno(errp, errno, "Failed to set FD nonblocking");
 -                return;
 +                goto failed;
              }
          }
          options.opaque = (void *)(uintptr_t)vhostfd;
@@ -XXX,XX +XXX,XX @@ static void net_init_tap_one(const NetdevTapOptions *tap, NetClientState *peer,
              } else {
                  warn_report(VHOST_NET_INIT_FAILED);
              }
 -            return;
 +            goto failed;
          }
      } else if (vhostfdname) {
          error_setg(errp, "vhostfd(s)= is not valid without vhost");
 +        goto failed;
      }
 +
 +    return;
 +
 +failed:
 +    qemu_del_net_client(&s->nc);
  }
+ static int get_fds(char *str, char *fds[], int max)
 --
 .7.4

-[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.
+Deleted patch
-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 ++---
-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}]
---
-.7.4

-[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 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

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 99d6b11b5b44d7dd64f4cb1973184e40a4a174f8:

Merge tag 'pull-target-arm-20220922' of https://git.linaro.org/people/pmaydell/qemu-arm into staging (2022-09-26 13:38:26 -0400)

are available in the git repository at:

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

for you to fetch changes up to bf769f742c3624952f125b303878a77ea870c156:

virtio: del net client if net_init_tap_one failed (2022-09-27 15:14:37 +0800)

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

----------------------------------------------------------------
Ding Hui (1):
      e1000e: set RX desc status with DD flag in a separate operation

Eugenio Pérez (6):
      vdpa: Make VhostVDPAState cvq_cmd_in_buffer control ack type
      vdpa: extract vhost_vdpa_net_load_mac from vhost_vdpa_net_load
      vdpa: Add vhost_vdpa_net_load_mq
      vdpa: validate MQ CVQ commands
      virtio-net: Update virtio-net curr_queue_pairs in vdpa backends
      vdpa: Allow MQ feature in SVQ

lu zhipeng (1):
      virtio: del net client if net_init_tap_one failed

hw/net/e1000e_core.c |  53 ++++++++++++++++++++++-
 hw/net/virtio-net.c  |  17 +++-----
 net/tap.c            |  18 +++++---
 net/vhost-vdpa.c     | 119 +++++++++++++++++++++++++++++++++++++--------------
 4 files changed, 157 insertions(+), 50 deletions(-)

Ding Hui (1):
  e1000e: set RX desc status with DD flag in a separate operation

Eugenio Pérez (6):
  vdpa: Make VhostVDPAState cvq_cmd_in_buffer control ack type
  vdpa: extract vhost_vdpa_net_load_mac from vhost_vdpa_net_load
  vdpa: Add vhost_vdpa_net_load_mq
  vdpa: validate MQ CVQ commands
  virtio-net: Update virtio-net curr_queue_pairs in vdpa backends
  vdpa: Allow MQ feature in SVQ

lu zhipeng (1):
  virtio: del net client if net_init_tap_one failed

-- 
2.7.4

From: Ding Hui <dinghui@sangfor.com.cn>

Like commit 034d00d48581 ("e1000: set RX descriptor status in
a separate operation"), there is also same issue in e1000e, which
would cause lost packets or stop sending packets to VM with DPDK.

Do similar fix in e1000e.

Resolves: https://gitlab.com/qemu-project/qemu/-/issues/402
Signed-off-by: Ding Hui <dinghui@sangfor.com.cn>
Signed-off-by: Jason Wang <jasowang@redhat.com>
---
 hw/net/e1000e_core.c | 53 +++++++++++++++++++++++++++++++++++++++++++++++++++-
 1 file changed, 52 insertions(+), 1 deletion(-)

diff --git a/hw/net/e1000e_core.c b/hw/net/e1000e_core.c
index XXXXXXX..XXXXXXX 100644
--- a/hw/net/e1000e_core.c
+++ b/hw/net/e1000e_core.c
@@ -XXX,XX +XXX,XX @@ struct NetRxPkt *pkt, const E1000E_RSSInfo *rss_info,
     }
 }
 
+static inline void
+e1000e_pci_dma_write_rx_desc(E1000ECore *core, dma_addr_t addr,
+                             uint8_t *desc, dma_addr_t len)
+{
+    PCIDevice *dev = core->owner;
+
+    if (e1000e_rx_use_legacy_descriptor(core)) {
+        struct e1000_rx_desc *d = (struct e1000_rx_desc *) desc;
+        size_t offset = offsetof(struct e1000_rx_desc, status);
+        uint8_t status = d->status;
+
+        d->status &= ~E1000_RXD_STAT_DD;
+        pci_dma_write(dev, addr, desc, len);
+
+        if (status & E1000_RXD_STAT_DD) {
+            d->status = status;
+            pci_dma_write(dev, addr + offset, &status, sizeof(status));
+        }
+    } else {
+        if (core->mac[RCTL] & E1000_RCTL_DTYP_PS) {
+            union e1000_rx_desc_packet_split *d =
+                (union e1000_rx_desc_packet_split *) desc;
+            size_t offset = offsetof(union e1000_rx_desc_packet_split,
+                wb.middle.status_error);
+            uint32_t status = d->wb.middle.status_error;
+
+            d->wb.middle.status_error &= ~E1000_RXD_STAT_DD;
+            pci_dma_write(dev, addr, desc, len);
+
+            if (status & E1000_RXD_STAT_DD) {
+                d->wb.middle.status_error = status;
+                pci_dma_write(dev, addr + offset, &status, sizeof(status));
+            }
+        } else {
+            union e1000_rx_desc_extended *d =
+                (union e1000_rx_desc_extended *) desc;
+            size_t offset = offsetof(union e1000_rx_desc_extended,
+                wb.upper.status_error);
+            uint32_t status = d->wb.upper.status_error;
+
+            d->wb.upper.status_error &= ~E1000_RXD_STAT_DD;
+            pci_dma_write(dev, addr, desc, len);
+
+            if (status & E1000_RXD_STAT_DD) {
+                d->wb.upper.status_error = status;
+                pci_dma_write(dev, addr + offset, &status, sizeof(status));
+            }
+        }
+    }
+}
+
 typedef struct e1000e_ba_state_st {
     uint16_t written[MAX_PS_BUFFERS];
     uint8_t cur_idx;
@@ -XXX,XX +XXX,XX @@ e1000e_write_packet_to_guest(E1000ECore *core, struct NetRxPkt *pkt,
 
         e1000e_write_rx_descr(core, desc, is_last ? core->rx_pkt : NULL,
                            rss_info, do_ps ? ps_hdr_len : 0, &bastate.written);
-        pci_dma_write(d, base, &desc, core->rx_desc_len);
+        e1000e_pci_dma_write_rx_desc(core, base, desc, core->rx_desc_len);
 
         e1000e_ring_advance(core, rxi,
                             core->rx_desc_len / E1000_MIN_RX_DESC_LEN);
-- 
2.7.4

From: Eugenio Pérez <eperezma@redhat.com>

This allows to simplify the code. Rename to status while we're at it.

Signed-off-by: Eugenio Pérez <eperezma@redhat.com>
Signed-off-by: Jason Wang <jasowang@redhat.com>
---
 net/vhost-vdpa.c | 23 ++++++++++++-----------
 1 file changed, 12 insertions(+), 11 deletions(-)

diff --git a/net/vhost-vdpa.c b/net/vhost-vdpa.c
index XXXXXXX..XXXXXXX 100644
--- a/net/vhost-vdpa.c
+++ b/net/vhost-vdpa.c
@@ -XXX,XX +XXX,XX @@ typedef struct VhostVDPAState {
     VHostNetState *vhost_net;
 
     /* Control commands shadow buffers */
-    void *cvq_cmd_out_buffer, *cvq_cmd_in_buffer;
+    void *cvq_cmd_out_buffer;
+    virtio_net_ctrl_ack *status;
+
     bool started;
 } VhostVDPAState;
 
@@ -XXX,XX +XXX,XX @@ static void vhost_vdpa_cleanup(NetClientState *nc)
     struct vhost_dev *dev = &s->vhost_net->dev;
 
     qemu_vfree(s->cvq_cmd_out_buffer);
-    qemu_vfree(s->cvq_cmd_in_buffer);
+    qemu_vfree(s->status);
     if (dev->vq_index + dev->nvqs == dev->vq_index_end) {
         g_clear_pointer(&s->vhost_vdpa.iova_tree, vhost_iova_tree_delete);
     }
@@ -XXX,XX +XXX,XX @@ static int vhost_vdpa_net_cvq_start(NetClientState *nc)
         return r;
     }
 
-    r = vhost_vdpa_cvq_map_buf(&s->vhost_vdpa, s->cvq_cmd_in_buffer,
+    r = vhost_vdpa_cvq_map_buf(&s->vhost_vdpa, s->status,
                                vhost_vdpa_net_cvq_cmd_page_len(), true);
     if (unlikely(r < 0)) {
         vhost_vdpa_cvq_unmap_buf(&s->vhost_vdpa, s->cvq_cmd_out_buffer);
@@ -XXX,XX +XXX,XX @@ static void vhost_vdpa_net_cvq_stop(NetClientState *nc)
 
     if (s->vhost_vdpa.shadow_vqs_enabled) {
         vhost_vdpa_cvq_unmap_buf(&s->vhost_vdpa, s->cvq_cmd_out_buffer);
-        vhost_vdpa_cvq_unmap_buf(&s->vhost_vdpa, s->cvq_cmd_in_buffer);
+        vhost_vdpa_cvq_unmap_buf(&s->vhost_vdpa, s->status);
     }
 }
 
@@ -XXX,XX +XXX,XX @@ static ssize_t vhost_vdpa_net_cvq_add(VhostVDPAState *s, size_t out_len,
         .iov_len = out_len,
     };
     const struct iovec in = {
-        .iov_base = s->cvq_cmd_in_buffer,
+        .iov_base = s->status,
         .iov_len = sizeof(virtio_net_ctrl_ack),
     };
     VhostShadowVirtqueue *svq = g_ptr_array_index(s->vhost_vdpa.shadow_vqs, 0);
@@ -XXX,XX +XXX,XX @@ static int vhost_vdpa_net_load(NetClientState *nc)
             return dev_written;
         }
 
-        return *((virtio_net_ctrl_ack *)s->cvq_cmd_in_buffer) != VIRTIO_NET_OK;
+        return *s->status != VIRTIO_NET_OK;
     }
 
     return 0;
@@ -XXX,XX +XXX,XX @@ static int vhost_vdpa_net_handle_ctrl_avail(VhostShadowVirtqueue *svq,
         goto out;
     }
 
-    memcpy(&status, s->cvq_cmd_in_buffer, sizeof(status));
-    if (status != VIRTIO_NET_OK) {
+    if (*s->status != VIRTIO_NET_OK) {
         return VIRTIO_NET_ERR;
     }
 
@@ -XXX,XX +XXX,XX @@ static NetClientState *net_vhost_vdpa_init(NetClientState *peer,
         s->cvq_cmd_out_buffer = qemu_memalign(qemu_real_host_page_size(),
                                             vhost_vdpa_net_cvq_cmd_page_len());
         memset(s->cvq_cmd_out_buffer, 0, vhost_vdpa_net_cvq_cmd_page_len());
-        s->cvq_cmd_in_buffer = qemu_memalign(qemu_real_host_page_size(),
-                                            vhost_vdpa_net_cvq_cmd_page_len());
-        memset(s->cvq_cmd_in_buffer, 0, vhost_vdpa_net_cvq_cmd_page_len());
+        s->status = qemu_memalign(qemu_real_host_page_size(),
+                                  vhost_vdpa_net_cvq_cmd_page_len());
+        memset(s->status, 0, vhost_vdpa_net_cvq_cmd_page_len());
 
         s->vhost_vdpa.shadow_vq_ops = &vhost_vdpa_net_svq_ops;
         s->vhost_vdpa.shadow_vq_ops_opaque = s;
-- 
2.7.4

From: Eugenio Pérez <eperezma@redhat.com>

Since there may be many commands we need to issue to load the NIC
state, let's split them in individual functions

Signed-off-by: Eugenio Pérez <eperezma@redhat.com>
Signed-off-by: Jason Wang <jasowang@redhat.com>
---
 net/vhost-vdpa.c | 62 ++++++++++++++++++++++++++++++++++++--------------------
 1 file changed, 40 insertions(+), 22 deletions(-)

diff --git a/net/vhost-vdpa.c b/net/vhost-vdpa.c
index XXXXXXX..XXXXXXX 100644
--- a/net/vhost-vdpa.c
+++ b/net/vhost-vdpa.c
@@ -XXX,XX +XXX,XX @@ static ssize_t vhost_vdpa_net_cvq_add(VhostVDPAState *s, size_t out_len,
     return vhost_svq_poll(svq);
 }
 
+static ssize_t vhost_vdpa_net_load_cmd(VhostVDPAState *s, uint8_t class,
+                                       uint8_t cmd, const void *data,
+                                       size_t data_size)
+{
+    const struct virtio_net_ctrl_hdr ctrl = {
+        .class = class,
+        .cmd = cmd,
+    };
+
+    assert(data_size < vhost_vdpa_net_cvq_cmd_page_len() - sizeof(ctrl));
+
+    memcpy(s->cvq_cmd_out_buffer, &ctrl, sizeof(ctrl));
+    memcpy(s->cvq_cmd_out_buffer + sizeof(ctrl), data, data_size);
+
+    return vhost_vdpa_net_cvq_add(s, sizeof(ctrl) + data_size,
+                                  sizeof(virtio_net_ctrl_ack));
+}
+
+static int vhost_vdpa_net_load_mac(VhostVDPAState *s, const VirtIONet *n)
+{
+    uint64_t features = n->parent_obj.guest_features;
+    if (features & BIT_ULL(VIRTIO_NET_F_CTRL_MAC_ADDR)) {
+        ssize_t dev_written = vhost_vdpa_net_load_cmd(s, VIRTIO_NET_CTRL_MAC,
+                                                  VIRTIO_NET_CTRL_MAC_ADDR_SET,
+                                                  n->mac, sizeof(n->mac));
+        if (unlikely(dev_written < 0)) {
+            return dev_written;
+        }
+
+        return *s->status != VIRTIO_NET_OK;
+    }
+
+    return 0;
+}
+
 static int vhost_vdpa_net_load(NetClientState *nc)
 {
     VhostVDPAState *s = DO_UPCAST(VhostVDPAState, nc, nc);
-    const struct vhost_vdpa *v = &s->vhost_vdpa;
+    struct vhost_vdpa *v = &s->vhost_vdpa;
     const VirtIONet *n;
-    uint64_t features;
+    int r;
 
     assert(nc->info->type == NET_CLIENT_DRIVER_VHOST_VDPA);
 
@@ -XXX,XX +XXX,XX @@ static int vhost_vdpa_net_load(NetClientState *nc)
     }
 
     n = VIRTIO_NET(v->dev->vdev);
-    features = n->parent_obj.guest_features;
-    if (features & BIT_ULL(VIRTIO_NET_F_CTRL_MAC_ADDR)) {
-        const struct virtio_net_ctrl_hdr ctrl = {
-            .class = VIRTIO_NET_CTRL_MAC,
-            .cmd = VIRTIO_NET_CTRL_MAC_ADDR_SET,
-        };
-        char *cursor = s->cvq_cmd_out_buffer;
-        ssize_t dev_written;
-
-        memcpy(cursor, &ctrl, sizeof(ctrl));
-        cursor += sizeof(ctrl);
-        memcpy(cursor, n->mac, sizeof(n->mac));
-
-        dev_written = vhost_vdpa_net_cvq_add(s, sizeof(ctrl) + sizeof(n->mac),
-                                             sizeof(virtio_net_ctrl_ack));
-        if (unlikely(dev_written < 0)) {
-            return dev_written;
-        }
-
-        return *s->status != VIRTIO_NET_OK;
+    r = vhost_vdpa_net_load_mac(s, n);
+    if (unlikely(r < 0)) {
+        return r;
     }
 
     return 0;
-- 
2.7.4

From: Eugenio Pérez <eperezma@redhat.com>

Same way as with the MAC, restore the expected number of queues at
device's start.

Signed-off-by: Eugenio Pérez <eperezma@redhat.com>
Signed-off-by: Jason Wang <jasowang@redhat.com>
---
 net/vhost-vdpa.c | 26 ++++++++++++++++++++++++++
 1 file changed, 26 insertions(+)

diff --git a/net/vhost-vdpa.c b/net/vhost-vdpa.c
index XXXXXXX..XXXXXXX 100644
--- a/net/vhost-vdpa.c
+++ b/net/vhost-vdpa.c
@@ -XXX,XX +XXX,XX @@ static int vhost_vdpa_net_load_mac(VhostVDPAState *s, const VirtIONet *n)
     return 0;
 }
 
+static int vhost_vdpa_net_load_mq(VhostVDPAState *s,
+                                  const VirtIONet *n)
+{
+    struct virtio_net_ctrl_mq mq;
+    uint64_t features = n->parent_obj.guest_features;
+    ssize_t dev_written;
+
+    if (!(features & BIT_ULL(VIRTIO_NET_F_MQ))) {
+        return 0;
+    }
+
+    mq.virtqueue_pairs = cpu_to_le16(n->curr_queue_pairs);
+    dev_written = vhost_vdpa_net_load_cmd(s, VIRTIO_NET_CTRL_MQ,
+                                          VIRTIO_NET_CTRL_MQ_VQ_PAIRS_SET, &mq,
+                                          sizeof(mq));
+    if (unlikely(dev_written < 0)) {
+        return dev_written;
+    }
+
+    return *s->status != VIRTIO_NET_OK;
+}
+
 static int vhost_vdpa_net_load(NetClientState *nc)
 {
     VhostVDPAState *s = DO_UPCAST(VhostVDPAState, nc, nc);
@@ -XXX,XX +XXX,XX @@ static int vhost_vdpa_net_load(NetClientState *nc)
     if (unlikely(r < 0)) {
         return r;
     }
+    r = vhost_vdpa_net_load_mq(s, n);
+    if (unlikely(r)) {
+        return r;
+    }
 
     return 0;
 }
-- 
2.7.4

From: Eugenio Pérez <eperezma@redhat.com>

So we are sure we can update the device model properly before sending to
the device.

Signed-off-by: Eugenio Pérez <eperezma@redhat.com>
Signed-off-by: Jason Wang <jasowang@redhat.com>
---
 net/vhost-vdpa.c | 9 +++++++++
 1 file changed, 9 insertions(+)

diff --git a/net/vhost-vdpa.c b/net/vhost-vdpa.c
index XXXXXXX..XXXXXXX 100644
--- a/net/vhost-vdpa.c
+++ b/net/vhost-vdpa.c
@@ -XXX,XX +XXX,XX @@ static bool vhost_vdpa_net_cvq_validate_cmd(const void *out_buf, size_t len)
                           __func__, ctrl.cmd);
         };
         break;
+    case VIRTIO_NET_CTRL_MQ:
+        switch (ctrl.cmd) {
+        case VIRTIO_NET_CTRL_MQ_VQ_PAIRS_SET:
+            return true;
+        default:
+            qemu_log_mask(LOG_GUEST_ERROR, "%s: invalid mq cmd %u\n",
+                          __func__, ctrl.cmd);
+        };
+        break;
     default:
         qemu_log_mask(LOG_GUEST_ERROR, "%s: invalid control class %u\n",
                       __func__, ctrl.class);
-- 
2.7.4

From: Eugenio Pérez <eperezma@redhat.com>

It was returned as error before. Instead of it, simply update the
corresponding field so qemu can send it in the migration data.

Signed-off-by: Eugenio Pérez <eperezma@redhat.com>
Acked-by: Si-Wei Liu <si-wei.liu@oracle.com>
Signed-off-by: Jason Wang <jasowang@redhat.com>
---
 hw/net/virtio-net.c | 17 ++++++-----------
 1 file changed, 6 insertions(+), 11 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_handle_mq(VirtIONet *n, uint8_t cmd,
         return VIRTIO_NET_ERR;
     }
 
-    /* Avoid changing the number of queue_pairs for vdpa device in
-     * userspace handler. A future fix is needed to handle the mq
-     * change in userspace handler with vhost-vdpa. Let's disable
-     * the mq handling from userspace for now and only allow get
-     * done through the kernel. Ripples may be seen when falling
-     * back to userspace, but without doing it qemu process would
-     * crash on a recursive entry to virtio_net_set_status().
-     */
+    n->curr_queue_pairs = queue_pairs;
     if (nc->peer && nc->peer->info->type == NET_CLIENT_DRIVER_VHOST_VDPA) {
-        return VIRTIO_NET_ERR;
+        /*
+         * Avoid updating the backend for a vdpa device: We're only interested
+         * in updating the device model queues.
+         */
+        return VIRTIO_NET_OK;
     }
-
-    n->curr_queue_pairs = queue_pairs;
     /* stop the backend before changing the number of queue_pairs to avoid handling a
      * disabled queue */
     virtio_net_set_status(vdev, vdev->status);
-- 
2.7.4

From: lu zhipeng <luzhipeng@cestc.cn>

If the net tap initializes successful, but failed during
network card hot-plugging, the net-tap will remains,
so cleanup.

Signed-off-by: lu zhipeng <luzhipeng@cestc.cn>
Signed-off-by: Jason Wang <jasowang@redhat.com>
---
 net/tap.c | 18 ++++++++++++------
 1 file changed, 12 insertions(+), 6 deletions(-)

diff --git a/net/tap.c b/net/tap.c
index XXXXXXX..XXXXXXX 100644
--- a/net/tap.c
+++ b/net/tap.c
@@ -XXX,XX +XXX,XX @@ static void net_init_tap_one(const NetdevTapOptions *tap, NetClientState *peer,
     tap_set_sndbuf(s->fd, tap, &err);
     if (err) {
         error_propagate(errp, err);
-        return;
+        goto failed;
     }
 
     if (tap->has_fd || tap->has_fds) {
@@ -XXX,XX +XXX,XX @@ static void net_init_tap_one(const NetdevTapOptions *tap, NetClientState *peer,
                 } else {
                     warn_report_err(err);
                 }
-                return;
+                goto failed;
             }
             if (!g_unix_set_fd_nonblocking(vhostfd, true, NULL)) {
                 error_setg_errno(errp, errno, "%s: Can't use file descriptor %d",
                                  name, fd);
-                return;
+                goto failed;
             }
         } else {
             vhostfd = open("/dev/vhost-net", O_RDWR);
@@ -XXX,XX +XXX,XX @@ static void net_init_tap_one(const NetdevTapOptions *tap, NetClientState *peer,
                     warn_report("tap: open vhost char device failed: %s",
                                 strerror(errno));
                 }
-                return;
+                goto failed;
             }
             if (!g_unix_set_fd_nonblocking(vhostfd, true, NULL)) {
                 error_setg_errno(errp, errno, "Failed to set FD nonblocking");
-                return;
+                goto failed;
             }
         }
         options.opaque = (void *)(uintptr_t)vhostfd;
@@ -XXX,XX +XXX,XX @@ static void net_init_tap_one(const NetdevTapOptions *tap, NetClientState *peer,
             } else {
                 warn_report(VHOST_NET_INIT_FAILED);
             }
-            return;
+            goto failed;
         }
     } else if (vhostfdname) {
         error_setg(errp, "vhostfd(s)= is not valid without vhost");
+        goto failed;
     }
+
+    return;
+
+failed:
+    qemu_del_net_client(&s->nc);
 }
 
 static int get_fds(char *str, char *fds[], int max)
-- 
2.7.4