Series comparison

-[Qemu-devel] [PULL 0/6] Net patches
+[Qemu-devel] [PULL 0/9] Net patches
-The following changes since commit e607bbee553cfe73072870cef458cfa4e78133e2:
+The following changes since commit 136c67e07869227b21b3f627316e03679ce7b738:
-  Merge remote-tracking branch 'remotes/edgar/tags/edgar/xilinx-next-2018-01-26.for-upstream' into staging (2018-01-26 14:24:25 +0000)
+  Merge remote-tracking branch 'remotes/bkoppelmann/tags/pull-tricore-2018-03-02' into staging (2018-03-02 16:56:20 +0000)
 are available in the git repository at:
   https://github.com/jasowang/qemu.git tags/net-pull-request
-for you to fetch changes up to bf4835a4d5338bb7424827715df22570a8adc67c:
+for you to fetch changes up to 46d4d36d0bf2b24b205f2f604f0905db80264eef:
-  MAINTAINERS: update Dmitry Fleytman email (2018-01-29 16:05:38 +0800)
+  tap: setting error appropriately when calling net_init_tap_one() (2018-03-05 10:30:16 +0800)
 ----------------------------------------------------------------
 ----------------------------------------------------------------
-Mao Zhongyi (2):
+Jay Zhou (1):
-      colo: modified the payload compare function
+      tap: setting error appropriately when calling net_init_tap_one()
       colo: compare the packet based on the tcp sequence number
-Philippe Mathieu-Daudé (1):
+Thomas Huth (8):
-      MAINTAINERS: update Dmitry Fleytman email
+      net: Move error reporting from net_init_client/netdev to the calling site
       net: List available netdevs with "-netdev help"
       net: Only show vhost-user in the help text if CONFIG_POSIX is defined
       net: Make net_client_init() static
       net: Remove the deprecated way of dumping network packets
       net: Remove the deprecated 'host_net_add' and 'host_net_remove' HMP commands
       net: Add a new convenience option "--nic" to configure default/on-board NICs
       hw/net: Remove unnecessary header includes
-Thomas Huth (3):
+ hmp-commands.hx         |  30 ------
-      net: Allow hubports to connect to other netdevs
+ hmp.h                   |   3 -
-      net: Allow netdevs to be used with 'hostfwd_add' and 'hostfwd_remove'
+ hw/net/e1000.c          |   1 -
-      qemu-doc: Get rid of "vlan=X" example in the documentation
+ hw/net/lance.c          |   3 -
+ hw/net/ne2000.c         |   2 -
- MAINTAINERS        |   8 +-
+ hw/net/pcnet-pci.c      |   1 -
- hmp-commands.hx    |   4 +-
+ hw/net/pcnet.c          |   1 -
- net/colo-compare.c | 411 +++++++++++++++++++++++++++++++++--------------------
+ hw/net/rtl8139.c        |   2 -
- net/colo.c         |   9 ++
+ hw/net/xgmac.c          |   1 -
- net/colo.h         |  15 ++
+ include/net/net.h       |   4 +-
- net/hub.c          |  27 +++-
+ include/net/vhost_net.h |   3 +
- net/hub.h          |   3 +-
+ include/sysemu/sysemu.h |   1 +
- net/net.c          |   2 +-
+ monitor.c               |  61 ------------
- net/slirp.c        |  33 +++--
+ net/dump.c              | 102 +--------------------
- net/trace-events   |   2 +-
+ net/net.c               | 239 +++++++++++++++++++++++-------------------------
- qapi/net.json      |   4 +-
+ net/tap.c               |  22 ++++-
- qemu-options.hx    |  12 +-
+ qapi/net.json           |  29 ++----
-files changed, 347 insertions(+), 183 deletions(-)
+ qemu-doc.texi           |  16 ----
  qemu-options.hx         |  48 +++++++---
  tests/test-hmp.c        |   2 -
  vl.c                    |  10 +-
 files changed, 190 insertions(+), 391 deletions(-)

-[Qemu-devel] [PULL 1/6] colo: modified the payload compare function
+[Qemu-devel] [PULL 1/9] net: Move error reporting from net_init_client/netdev to the calling site
-From: Mao Zhongyi <maozy.fnst@cn.fujitsu.com>
+From: Thomas Huth <thuth@redhat.com>
-Modified the function colo_packet_compare_common to prepare for the
+It looks strange that net_init_client() and net_init_netdev() both
-tcp packet comparison in the next patch.
+take an "Error **errp" parameter, but then do the error reporting
 with "error_report_err(local_err)" on their own. Let's move the
 error reporting to the calling site instead to simplify this code
 a little bit.
-Cc: Zhang Chen <zhangckid@gmail.com>
+Reviewed-by: Eric Blake <eblake@redhat.com>
-Cc: Li Zhijian <lizhijian@cn.fujitsu.com>
+Reviewed-by: Paolo Bonzini <pbonzini@redhat.com>
-Cc: Jason Wang <jasowang@redhat.com>
+Signed-off-by: Thomas Huth <thuth@redhat.com>
 Signed-off-by: Mao Zhongyi <maozy.fnst@cn.fujitsu.com>
 Signed-off-by: Li Zhijian <lizhijian@cn.fujitsu.com>
 Signed-off-by: Zhang Chen <zhangckid@gmail.com>
 Reviewed-by: Zhang Chen <zhangckid@gmail.com>
 Signed-off-by: Jason Wang <jasowang@redhat.com>
 ---
- net/colo-compare.c | 88 +++++++++++++++++++++++++++---------------------------
+ include/net/net.h |  2 +-
-file changed, 44 insertions(+), 44 deletions(-)
+ net/net.c         | 29 +++++------------------------
  vl.c              |  3 ++-
 files changed, 8 insertions(+), 26 deletions(-)
-diff --git a/net/colo-compare.c b/net/colo-compare.c
+diff --git a/include/net/net.h b/include/net/net.h
 index XXXXXXX..XXXXXXX 100644
---- a/net/colo-compare.c
+--- a/include/net/net.h
-+++ b/net/colo-compare.c
++++ b/include/net/net.h
-@@ -XXX,XX +XXX,XX @@ static int packet_enqueue(CompareState *s, int mode, Connection **con)
+@@ -XXX,XX +XXX,XX @@ extern const char *legacy_bootp_filename;
-  * return:    0  means packet same
-  *            > 0 || < 0 means packet different
+ int net_client_init(QemuOpts *opts, bool is_netdev, Error **errp);
-  */
+ int net_client_parse(QemuOptsList *opts_list, const char *str);
--static int colo_packet_compare_common(Packet *ppkt,
+-int net_init_clients(void);
--                                      Packet *spkt,
++int net_init_clients(Error **errp);
--                                      int poffset,
+ void net_check_clients(void);
--                                      int soffset)
+ void net_cleanup(void);
-+static int colo_compare_packet_payload(Packet *ppkt,
+ void hmp_host_net_add(Monitor *mon, const QDict *qdict);
-+                                       Packet *spkt,
+diff --git a/net/net.c b/net/net.c
-+                                       uint16_t poffset,
+index XXXXXXX..XXXXXXX 100644
-+                                       uint16_t soffset,
+--- a/net/net.c
-+                                       uint16_t len)
++++ b/net/net.c
-+
+@@ -XXX,XX +XXX,XX @@ void net_check_clients(void)
  static int net_init_client(void *dummy, QemuOpts *opts, Error **errp)
  {
-     if (trace_event_get_state_backends(TRACE_COLO_COMPARE_MISCOMPARE)) {
+-    Error *local_err = NULL;
          char pri_ip_src[20], pri_ip_dst[20], sec_ip_src[20], sec_ip_dst[20];
@@ -XXX,XX +XXX,XX @@ static int colo_packet_compare_common(Packet *ppkt,
                                     sec_ip_src, sec_ip_dst);
      }
 -    poffset = ppkt->vnet_hdr_len + poffset;
 -    soffset = ppkt->vnet_hdr_len + soffset;
 -
--    if (ppkt->size - poffset == spkt->size - soffset) {
+-    net_client_init(opts, false, &local_err);
--        return memcmp(ppkt->data + poffset,
+-    if (local_err) {
--                      spkt->data + soffset,
+-        error_report_err(local_err);
 -                      spkt->size - soffset);
 -    } else {
 -        trace_colo_compare_main("Net packet size are not the same");
 -        return -1;
 -    }
-+    return memcmp(ppkt->data + poffset, spkt->data + soffset, len);
+-
 -    return 0;
 +    return net_client_init(opts, false, errp);
  }
- /*
+ static int net_init_netdev(void *dummy, QemuOpts *opts, Error **errp)
@@ -XXX,XX +XXX,XX @@ static int colo_packet_compare_tcp(Packet *spkt, Packet *ppkt)
       * the secondary guest's timestamp. COLO just focus on payload,
       * so we just need skip this field.
       */
 -    if (ptcp->th_off > 5) {
 -        ptrdiff_t ptcp_offset, stcp_offset;
 -        ptcp_offset = ppkt->transport_header - (uint8_t *)ppkt->data
 -                      + (ptcp->th_off * 4) - ppkt->vnet_hdr_len;
 -        stcp_offset = spkt->transport_header - (uint8_t *)spkt->data
 -                      + (stcp->th_off * 4) - spkt->vnet_hdr_len;
 +    ptrdiff_t ptcp_offset, stcp_offset;
 -        /*
 -         * When network is busy, some tcp options(like sack) will unpredictable
 -         * occur in primary side or secondary side. it will make packet size
 -         * not same, but the two packet's payload is identical. colo just
 -         * care about packet payload, so we skip the option field.
 -         */
 -        res = colo_packet_compare_common(ppkt, spkt, ptcp_offset, stcp_offset);
 -    } else if (ptcp->th_sum == stcp->th_sum) {
 -        res = colo_packet_compare_common(ppkt, spkt, ETH_HLEN, ETH_HLEN);
 +    ptcp_offset = ppkt->transport_header - (uint8_t *)ppkt->data
 +                  + (ptcp->th_off << 2) - ppkt->vnet_hdr_len;
 +    stcp_offset = spkt->transport_header - (uint8_t *)spkt->data
 +                  + (stcp->th_off << 2) - spkt->vnet_hdr_len;
 +    if (ppkt->size - ptcp_offset == spkt->size - stcp_offset) {
 +        res = colo_compare_packet_payload(ppkt, spkt,
 +                                          ptcp_offset, stcp_offset,
 +                                          ppkt->size - ptcp_offset);
      } else {
 +        trace_colo_compare_main("TCP: payload size of packets are different");
          res = -1;
      }
@@ -XXX,XX +XXX,XX @@ static int colo_packet_compare_tcp(Packet *spkt, Packet *ppkt)
   */
  static int colo_packet_compare_udp(Packet *spkt, Packet *ppkt)
  {
+-    Error *local_err = NULL;
 -    int ret;
--    int network_header_length = ppkt->ip->ip_hl * 4;
-+    uint16_t network_header_length = ppkt->ip->ip_hl << 2;
-+    uint16_t offset = network_header_length + ETH_HLEN + ppkt->vnet_hdr_len;
-     trace_colo_compare_main("compare udp");
-@@ -XXX,XX +XXX,XX @@ static int colo_packet_compare_udp(Packet *spkt, Packet *ppkt)
-      * other field like TOS,TTL,IP Checksum. we only need to compare
-      * the ip payload here.
-      */
--    ret = colo_packet_compare_common(ppkt, spkt,
--                                     network_header_length + ETH_HLEN,
--                                     network_header_length + ETH_HLEN);
 -
--    if (ret) {
+-    ret = net_client_init(opts, true, &local_err);
-+    if (ppkt->size != spkt->size) {
+-    if (local_err) {
-+        trace_colo_compare_main("UDP: payload size of packets are different");
+-        error_report_err(local_err);
-+        return -1;
+-        return -1;
-+    }
+-    }
 +    if (colo_compare_packet_payload(ppkt, spkt, offset, offset,
 +                                    ppkt->size - offset)) {
          trace_colo_compare_udp_miscompare("primary pkt size", ppkt->size);
          trace_colo_compare_udp_miscompare("Secondary pkt size", spkt->size);
          if (trace_event_get_state_backends(TRACE_COLO_COMPARE_MISCOMPARE)) {
@@ -XXX,XX +XXX,XX @@ static int colo_packet_compare_udp(Packet *spkt, Packet *ppkt)
              qemu_hexdump((char *)spkt->data, stderr, "colo-compare sec pkt",
                           spkt->size);
          }
 +        return -1;
 +    } else {
 +        return 0;
      }
 -
 -    return ret;
++    return net_client_init(opts, true, errp);
  }
- /*
+-int net_init_clients(void)
-@@ -XXX,XX +XXX,XX @@ static int colo_packet_compare_udp(Packet *spkt, Packet *ppkt)
++int net_init_clients(Error **errp)
   */
  static int colo_packet_compare_icmp(Packet *spkt, Packet *ppkt)
  {
--    int network_header_length = ppkt->ip->ip_hl * 4;
+-    QemuOptsList *net = qemu_find_opts("net");
-+    uint16_t network_header_length = ppkt->ip->ip_hl << 2;
+-
-+    uint16_t offset = network_header_length + ETH_HLEN + ppkt->vnet_hdr_len;
+     net_change_state_entry =
+         qemu_add_vm_change_state_handler(net_vm_change_state_handler, NULL);
-     trace_colo_compare_main("compare icmp");
+     QTAILQ_INIT(&net_clients);
-@@ -XXX,XX +XXX,XX @@ static int colo_packet_compare_icmp(Packet *spkt, Packet *ppkt)
-      * other field like TOS,TTL,IP Checksum. we only need to compare
+     if (qemu_opts_foreach(qemu_find_opts("netdev"),
-      * the ip payload here.
+-                          net_init_netdev, NULL, NULL)) {
-      */
++                          net_init_netdev, NULL, errp)) {
--    if (colo_packet_compare_common(ppkt, spkt,
+         return -1;
 -                                   network_header_length + ETH_HLEN,
 -                                   network_header_length + ETH_HLEN)) {
 +    if (ppkt->size != spkt->size) {
 +        trace_colo_compare_main("ICMP: payload size of packets are different");
 +        return -1;
 +    }
 +    if (colo_compare_packet_payload(ppkt, spkt, offset, offset,
 +                                    ppkt->size - offset)) {
          trace_colo_compare_icmp_miscompare("primary pkt size",
                                             ppkt->size);
          trace_colo_compare_icmp_miscompare("Secondary pkt size",
@@ -XXX,XX +XXX,XX @@ static int colo_packet_compare_icmp(Packet *spkt, Packet *ppkt)
   */
  static int colo_packet_compare_other(Packet *spkt, Packet *ppkt)
  {
 +    uint16_t offset = ppkt->vnet_hdr_len;
 +
      trace_colo_compare_main("compare other");
      if (trace_event_get_state_backends(TRACE_COLO_COMPARE_MISCOMPARE)) {
          char pri_ip_src[20], pri_ip_dst[20], sec_ip_src[20], sec_ip_dst[20];
@@ -XXX,XX +XXX,XX @@ static int colo_packet_compare_other(Packet *spkt, Packet *ppkt)
                                     sec_ip_src, sec_ip_dst);
      }
--    return colo_packet_compare_common(ppkt, spkt, 0, 0);
+-    if (qemu_opts_foreach(net, net_init_client, NULL, NULL)) {
-+    if (ppkt->size != spkt->size) {
++    if (qemu_opts_foreach(qemu_find_opts("net"), net_init_client, NULL, errp)) {
-+        trace_colo_compare_main("Other: payload size of packets are different");
+         return -1;
-+        return -1;
+     }
-+    }
-+    return colo_compare_packet_payload(ppkt, spkt, offset, offset,
+diff --git a/vl.c b/vl.c
-+                                       ppkt->size - offset);
+index XXXXXXX..XXXXXXX 100644
- }
+--- a/vl.c
++++ b/vl.c
- static int colo_old_packet_check_one(Packet *pkt, int64_t *check_time)
+@@ -XXX,XX +XXX,XX @@ int main(int argc, char **argv, char **envp)
      colo_info_init();
 -    if (net_init_clients() < 0) {
 +    if (net_init_clients(&err) < 0) {
 +        error_report_err(err);
          exit(1);
      }
 --
 .7.4

-[Qemu-devel] [PULL 6/6] MAINTAINERS: update Dmitry Fleytman email
+[Qemu-devel] [PULL 2/9] net: List available netdevs with "-netdev help"
-From: Philippe Mathieu-Daudé <f4bug@amsat.org>
+From: Thomas Huth <thuth@redhat.com>
-gently asked by his automatic reply :)
+Other options like "-chardev" or "-device" feature a nice help text
 with the available devices when being called with "help" or "?".
 Since it is quite useful, especially if you want to see which network
 backends have been compiled into the QEMU binary, let's provide such
 a help text for "-netdev", too.
-Signed-off-by: Philippe Mathieu-Daudé <f4bug@amsat.org>
+Reviewed-by: Paolo Bonzini <pbonzini@redhat.com>
 Reviewed-by: Eric Blake <eblake@redhat.com>
 Signed-off-by: Thomas Huth <thuth@redhat.com>
 Signed-off-by: Jason Wang <jasowang@redhat.com>
 ---
- MAINTAINERS | 8 ++++----
+ net/net.c | 37 ++++++++++++++++++++++++++++++++++++-
-file changed, 4 insertions(+), 4 deletions(-)
+file changed, 36 insertions(+), 1 deletion(-)
-diff --git a/MAINTAINERS b/MAINTAINERS
+diff --git a/net/net.c b/net/net.c
 index XXXXXXX..XXXXXXX 100644
---- a/MAINTAINERS
+--- a/net/net.c
-+++ b/MAINTAINERS
++++ b/net/net.c
-@@ -XXX,XX +XXX,XX @@ F: hw/scsi/mfi.h
+@@ -XXX,XX +XXX,XX @@ static int net_client_init1(const void *object, bool is_netdev, Error **errp)
- F: tests/megasas-test.c
+     return 0;
+ }
- Network packet abstractions
--M: Dmitry Fleytman <dmitry@daynix.com>
++static void show_netdevs(void)
-+M: Dmitry Fleytman <dmitry.fleytman@gmail.com>
++{
- S: Maintained
++    int idx;
- F: include/net/eth.h
++    const char *available_netdevs[] = {
- F: net/eth.c
++        "socket",
-@@ -XXX,XX +XXX,XX @@ F: hw/net/net_rx_pkt*
++        "hubport",
- F: hw/net/net_tx_pkt*
++        "tap",
++#ifdef CONFIG_SLIRP
- Vmware
++        "user",
--M: Dmitry Fleytman <dmitry@daynix.com>
++#endif
-+M: Dmitry Fleytman <dmitry.fleytman@gmail.com>
++#ifdef CONFIG_L2TPV3
- S: Maintained
++        "l2tpv3",
- F: hw/net/vmxnet*
++#endif
- F: hw/scsi/vmw_pvscsi*
++#ifdef CONFIG_VDE
-@@ -XXX,XX +XXX,XX @@ F: hw/mem/nvdimm.c
++        "vde",
- F: include/hw/mem/nvdimm.h
++#endif
++#ifdef CONFIG_NET_BRIDGE
- e1000x
++        "bridge",
--M: Dmitry Fleytman <dmitry@daynix.com>
++#endif
-+M: Dmitry Fleytman <dmitry.fleytman@gmail.com>
++#ifdef CONFIG_NETMAP
- S: Maintained
++        "netmap",
- F: hw/net/e1000x*
++#endif
++#ifdef CONFIG_POSIX
- e1000e
++        "vhost-user",
--M: Dmitry Fleytman <dmitry@daynix.com>
++#endif
-+M: Dmitry Fleytman <dmitry.fleytman@gmail.com>
++    };
- S: Maintained
++
- F: hw/net/e1000e*
++    printf("Available netdev backend types:\n");
 +    for (idx = 0; idx < ARRAY_SIZE(available_netdevs); idx++) {
 +        puts(available_netdevs[idx]);
 +    }
 +}
  int net_client_init(QemuOpts *opts, bool is_netdev, Error **errp)
  {
@@ -XXX,XX +XXX,XX @@ int net_client_init(QemuOpts *opts, bool is_netdev, Error **errp)
      int ret = -1;
      Visitor *v = opts_visitor_new(opts);
 -    {
 +    if (is_netdev && is_help_option(qemu_opt_get(opts, "type"))) {
 +        show_netdevs();
 +        exit(0);
 +    } else {
          /* Parse convenience option format ip6-net=fec0::0[/64] */
          const char *ip6_net = qemu_opt_get(opts, "ipv6-net");
 --
 .7.4

-[Qemu-devel] [PULL 5/6] qemu-doc: Get rid of "vlan=X" example in the documentation
+[Qemu-devel] [PULL 3/9] net: Only show vhost-user in the help text if CONFIG_POSIX is defined
 From: Thomas Huth <thuth@redhat.com>
-The vlan concept is marked as deprecated, so we should not use
+According to net/Makefile.objs we only link in the vhost-user code
-this for examples in the documentation anymore.
+if CONFIG_POSIX has been set. So the help screen should also only
 show this information if CONFIG_POSIX has been defined.
+Reviewed-by: Paolo Bonzini <pbonzini@redhat.com>
 Signed-off-by: Thomas Huth <thuth@redhat.com>
 Signed-off-by: Jason Wang <jasowang@redhat.com>
 ---
- qemu-options.hx | 4 ++--
+ qemu-options.hx | 2 ++
-file changed, 2 insertions(+), 2 deletions(-)
+file changed, 2 insertions(+)
 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 @@ qemu-system-i386 linux.img -net nic -net tap
+@@ -XXX,XX +XXX,XX @@ DEF("netdev", HAS_ARG, QEMU_OPTION_netdev,
- #launch a QEMU instance with two NICs, each one connected
+     "                VALE port (created on the fly) called 'name' ('nmname' is name of the \n"
- #to a TAP device
+     "                netmap device, defaults to '/dev/netmap')\n"
- qemu-system-i386 linux.img \
+ #endif
--                 -net nic,vlan=0 -net tap,vlan=0,ifname=tap0 \
++#ifdef CONFIG_POSIX
--                 -net nic,vlan=1 -net tap,vlan=1,ifname=tap1
+     "-netdev vhost-user,id=str,chardev=dev[,vhostforce=on|off]\n"
-+        -netdev tap,id=nd0,ifname=tap0 -device e1000,netdev=nd0 \
+     "                configure a vhost-user network, backed by a chardev 'dev'\n"
-+        -netdev tap,id=nd1,ifname=tap1 -device rtl8139,netdev=nd1
++#endif
- @end example
+     "-netdev hubport,id=str,hubid=n[,netdev=nd]\n"
+     "                configure a hub port on QEMU VLAN 'n'\n", QEMU_ARCH_ALL)
- @example
+ DEF("net", HAS_ARG, QEMU_OPTION_net,
 --
 .7.4

-New patch
+[Qemu-devel] [PULL 4/9] net: Make net_client_init() static
+From: Thomas Huth <thuth@redhat.com>
+The function is only used within net.c, so there's no need that
+this is a global function.
+While we're at it, also remove the unused prototype compute_mcast_idx()
+(the function has been removed in commit d9caeb09b107e91122d10ba4a08a).
+Reviewed-by: Paolo Bonzini <pbonzini@redhat.com>
+Signed-off-by: Thomas Huth <thuth@redhat.com>
+Signed-off-by: Jason Wang <jasowang@redhat.com>
+---
+ include/net/net.h | 2 --
+ net/net.c         | 2 +-
+files changed, 1 insertion(+), 3 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 @@ extern const char *host_net_devices[];
+ extern const char *legacy_tftp_prefix;
+ extern const char *legacy_bootp_filename;
+-int net_client_init(QemuOpts *opts, bool is_netdev, Error **errp);
+ int net_client_parse(QemuOptsList *opts_list, const char *str);
+ int net_init_clients(Error **errp);
+ void net_check_clients(void);
+@@ -XXX,XX +XXX,XX @@ void qdev_set_nic_properties(DeviceState *dev, NICInfo *nd);
+ #define POLYNOMIAL_LE 0xedb88320
+ uint32_t net_crc32(const uint8_t *p, int len);
+ uint32_t net_crc32_le(const uint8_t *p, int len);
+-unsigned compute_mcast_idx(const uint8_t *ep);
+ #define vmstate_offset_macaddr(_state, _field)                       \
+     vmstate_offset_array(_state, _field.a, uint8_t,                \
+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 @@ static void show_netdevs(void)
+     }
+ }
+-int net_client_init(QemuOpts *opts, bool is_netdev, Error **errp)
++static int net_client_init(QemuOpts *opts, bool is_netdev, Error **errp)
+ {
+     void *object = NULL;
+     Error *err = NULL;
+--
+.7.4

-[Qemu-devel] [PULL 3/6] net: Allow hubports to connect to other netdevs
+[Qemu-devel] [PULL 5/9] net: Remove the deprecated way of dumping network packets
 From: Thomas Huth <thuth@redhat.com>
-QEMU can emulate hubs to connect NICs and netdevs. This is currently
+"-net dump" has been marked as deprecated since QEMU v2.10, since it
-primarily used for the mis-named 'vlan' feature of the networking
+only works with the deprecated 'vlan' parameter (or hubs). Network
-subsystem. Now the 'vlan' feature has been marked as deprecated, since
+dumping should be done with "-object filter-dump" nowadays instead.
-its name is rather confusing and the users often rather mis-configure
+Since nobody complained so far about the deprecation message, let's
-their network when trying to use it. But while the 'vlan' parameter
+finally get rid of "-net dump" now.
-should be removed at one point in time, the basic idea of emulating
 a hub in QEMU is still good: It's useful for bundling up the output of
 multiple NICs into one single l2tp netdev for example.
 Now to be able to use the hubport feature without 'vlan's, there is one
 missing piece: The possibility to connect a hubport to a netdev, too.
 This patch adds this possibility by introducing a new "netdev=..."
 parameter to the hubports.
 To bundle up the output of multiple NICs into one socket netdev, you can
 now run QEMU with these parameters for example:
 qemu-system-ppc64 ... -netdev socket,id=s1,connect=:11122 \
     -netdev hubport,hubid=1,id=h1,netdev=s1 \
     -netdev hubport,hubid=1,id=h2 -device e1000,netdev=h2 \
     -netdev hubport,hubid=1,id=h3 -device virtio-net-pci,netdev=h3
 For using the socket netdev, you have got to start another QEMU as the
 receiving side first, for example with network dumping enabled:
 qemu-system-x86_64 -M isapc -netdev socket,id=s0,listen=:11122 \
     -device ne2k_isa,netdev=s0 \
     -object filter-dump,id=f1,netdev=s0,file=/tmp/dump.dat
 After the ppc64 guest tried to boot from both NICs, you can see in the
 dump file (using Wireshark, for example), that the output of both NICs
 (the e1000 and the virtio-net-pci) has been successfully transfered
 via the socket netdev in this case.
 Suggested-by: Paolo Bonzini <pbonzini@redhat.com>
 Signed-off-by: Thomas Huth <thuth@redhat.com>
 Signed-off-by: Jason Wang <jasowang@redhat.com>
 ---
- net/hub.c       | 27 +++++++++++++++++++++------
+ net/dump.c      | 102 ++------------------------------------------------------
- net/hub.h       |  3 ++-
+ net/net.c       |   9 +----
- net/net.c       |  2 +-
+ qapi/net.json   |  29 ++++------------
- qapi/net.json   |  4 +++-
+ qemu-doc.texi   |   6 ----
- qemu-options.hx |  8 +++++---
+ qemu-options.hx |   8 -----
-files changed, 32 insertions(+), 12 deletions(-)
+files changed, 9 insertions(+), 145 deletions(-)
-diff --git a/net/hub.c b/net/hub.c
+diff --git a/net/dump.c b/net/dump.c
 index XXXXXXX..XXXXXXX 100644
---- a/net/hub.c
+--- a/net/dump.c
-+++ b/net/hub.c
++++ b/net/dump.c
-@@ -XXX,XX +XXX,XX @@
+@@ -XXX,XX +XXX,XX @@ static int net_dump_state_init(DumpState *s, const char *filename,
-  */
+     fd = open(filename, O_CREAT | O_TRUNC | O_WRONLY | O_BINARY, 0644);
- #include "qemu/osdep.h"
+     if (fd < 0) {
-+#include "qapi/error.h"
+-        error_setg_errno(errp, errno, "-net dump: can't open %s", filename);
- #include "monitor/monitor.h"
++        error_setg_errno(errp, errno, "net dump: can't open %s", filename);
- #include "net/net.h"
+         return -1;
  #include "clients.h"
@@ -XXX,XX +XXX,XX @@ static NetClientInfo net_hub_port_info = {
      .cleanup = net_hub_port_cleanup,
  };
 -static NetHubPort *net_hub_port_new(NetHub *hub, const char *name)
 +static NetHubPort *net_hub_port_new(NetHub *hub, const char *name,
 +                                    NetClientState *hubpeer)
  {
      NetClientState *nc;
      NetHubPort *port;
@@ -XXX,XX +XXX,XX @@ static NetHubPort *net_hub_port_new(NetHub *hub, const char *name)
          name = default_name;
      }
--    nc = qemu_new_net_client(&net_hub_port_info, NULL, "hub", name);
+@@ -XXX,XX +XXX,XX @@ static int net_dump_state_init(DumpState *s, const char *filename,
-+    nc = qemu_new_net_client(&net_hub_port_info, hubpeer, "hub", name);
+     hdr.linktype = 1;
-     port = DO_UPCAST(NetHubPort, nc, nc);
-     port->id = id;
+     if (write(fd, &hdr, sizeof(hdr)) < sizeof(hdr)) {
-     port->hub = hub;
+-        error_setg_errno(errp, errno, "-net dump write error");
-@@ -XXX,XX +XXX,XX @@ static NetHubPort *net_hub_port_new(NetHub *hub, const char *name)
++        error_setg_errno(errp, errno, "net dump write error");
+         close(fd);
- /**
+         return -1;
   * Create a port on a given hub
 + * @hub_id: Number of the hub
   * @name: Net client name or NULL for default name.
 + * @hubpeer: Peer to use (if "netdev=id" has been specified)
   *
   * If there is no existing hub with the given id then a new hub is created.
   */
 -NetClientState *net_hub_add_port(int hub_id, const char *name)
 +NetClientState *net_hub_add_port(int hub_id, const char *name,
 +                                 NetClientState *hubpeer)
  {
      NetHub *hub;
      NetHubPort *port;
@@ -XXX,XX +XXX,XX @@ NetClientState *net_hub_add_port(int hub_id, const char *name)
          hub = net_hub_new(hub_id);
      }
+@@ -XXX,XX +XXX,XX @@ static int net_dump_state_init(DumpState *s, const char *filename,
 -    port = net_hub_port_new(hub, name);
 +    port = net_hub_port_new(hub, name, hubpeer);
      return &port->nc;
  }
@@ -XXX,XX +XXX,XX @@ NetClientState *net_hub_port_find(int hub_id)
          }
      }
 -    nc = net_hub_add_port(hub_id, NULL);
 +    nc = net_hub_add_port(hub_id, NULL, NULL);
      return nc;
  }
@@ -XXX,XX +XXX,XX @@ int net_init_hubport(const Netdev *netdev, const char *name,
                       NetClientState *peer, Error **errp)
  {
      const NetdevHubPortOptions *hubport;
 +    NetClientState *hubpeer = NULL;
      assert(netdev->type == NET_CLIENT_DRIVER_HUBPORT);
      assert(!peer);
      hubport = &netdev->u.hubport;
 -    net_hub_add_port(hubport->hubid, name);
 +    if (hubport->has_netdev) {
 +        hubpeer = qemu_find_netdev(hubport->netdev);
 +        if (!hubpeer) {
 +            error_setg(errp, "netdev '%s' not found", hubport->netdev);
 +            return -1;
 +        }
 +    }
 +
 +    net_hub_add_port(hubport->hubid, name, hubpeer);
 +
      return 0;
  }
-diff --git a/net/hub.h b/net/hub.h
+-/* Dumping via VLAN netclient */
-index XXXXXXX..XXXXXXX 100644
+-
---- a/net/hub.h
+-struct DumpNetClient {
-+++ b/net/hub.h
+-    NetClientState nc;
-@@ -XXX,XX +XXX,XX @@
+-    DumpState ds;
+-};
- #include "qemu-common.h"
+-typedef struct DumpNetClient DumpNetClient;
+-
--NetClientState *net_hub_add_port(int hub_id, const char *name);
+-static ssize_t dumpclient_receive(NetClientState *nc, const uint8_t *buf,
-+NetClientState *net_hub_add_port(int hub_id, const char *name,
+-                                  size_t size)
-+                                 NetClientState *hubpeer);
+-{
- NetClientState *net_hub_find_client_by_name(int hub_id, const char *name);
+-    DumpNetClient *dc = DO_UPCAST(DumpNetClient, nc, nc);
- void net_hub_info(Monitor *mon);
+-    struct iovec iov = {
- void net_hub_check_clients(void);
+-        .iov_base = (void *)buf,
 -        .iov_len = size
 -    };
 -
 -    return dump_receive_iov(&dc->ds, &iov, 1);
 -}
 -
 -static ssize_t dumpclient_receive_iov(NetClientState *nc,
 -                                      const struct iovec *iov, int cnt)
 -{
 -    DumpNetClient *dc = DO_UPCAST(DumpNetClient, nc, nc);
 -
 -    return dump_receive_iov(&dc->ds, iov, cnt);
 -}
 -
 -static void dumpclient_cleanup(NetClientState *nc)
 -{
 -    DumpNetClient *dc = DO_UPCAST(DumpNetClient, nc, nc);
 -
 -    dump_cleanup(&dc->ds);
 -}
 -
 -static NetClientInfo net_dump_info = {
 -    .type = NET_CLIENT_DRIVER_DUMP,
 -    .size = sizeof(DumpNetClient),
 -    .receive = dumpclient_receive,
 -    .receive_iov = dumpclient_receive_iov,
 -    .cleanup = dumpclient_cleanup,
 -};
 -
 -int net_init_dump(const Netdev *netdev, const char *name,
 -                  NetClientState *peer, Error **errp)
 -{
 -    int len, rc;
 -    const char *file;
 -    char def_file[128];
 -    const NetdevDumpOptions *dump;
 -    NetClientState *nc;
 -    DumpNetClient *dnc;
 -
 -    assert(netdev->type == NET_CLIENT_DRIVER_DUMP);
 -    dump = &netdev->u.dump;
 -
 -    assert(peer);
 -
 -    error_report("'-net dump' is deprecated. "
 -                 "Please use '-object filter-dump' instead.");
 -
 -    if (dump->has_file) {
 -        file = dump->file;
 -    } else {
 -        int id;
 -        int ret;
 -
 -        ret = net_hub_id_for_client(peer, &id);
 -        assert(ret == 0); /* peer must be on a hub */
 -
 -        snprintf(def_file, sizeof(def_file), "qemu-vlan%d.pcap", id);
 -        file = def_file;
 -    }
 -
 -    if (dump->has_len) {
 -        if (dump->len > INT_MAX) {
 -            error_setg(errp, "invalid length: %"PRIu64, dump->len);
 -            return -1;
 -        }
 -        len = dump->len;
 -    } else {
 -        len = 65536;
 -    }
 -
 -    nc = qemu_new_net_client(&net_dump_info, peer, "dump", name);
 -    snprintf(nc->info_str, sizeof(nc->info_str),
 -             "dump to %s (len=%d)", file, len);
 -
 -    dnc = DO_UPCAST(DumpNetClient, nc, nc);
 -    rc = net_dump_state_init(&dnc->ds, file, len, errp);
 -    if (rc) {
 -        qemu_del_net_client(nc);
 -    }
 -    return rc;
 -}
 -
 -/* Dumping via filter */
 -
  #define TYPE_FILTER_DUMP "filter-dump"
  #define FILTER_DUMP(obj) \
 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 @@ static QTAILQ_HEAD(, NetClientState) net_clients;
+ const char *host_net_devices[] = {
+     "tap",
+     "socket",
+-    "dump",
+ #ifdef CONFIG_NET_BRIDGE
+     "bridge",
+ #endif
+@@ -XXX,XX +XXX,XX @@ static int (* const net_client_init_fun[NET_CLIENT_DRIVER__MAX])(
+ #ifdef CONFIG_NETMAP
+         [NET_CLIENT_DRIVER_NETMAP]    = net_init_netmap,
+ #endif
+-        [NET_CLIENT_DRIVER_DUMP]      = net_init_dump,
+ #ifdef CONFIG_NET_BRIDGE
+         [NET_CLIENT_DRIVER_BRIDGE]    = net_init_bridge,
+ #endif
 @@ -XXX,XX +XXX,XX @@ static int net_client_init1(const void *object, bool is_netdev, Error **errp)
-         /* Do not add to a vlan if it's a nic with a netdev= parameter. */
+         netdev = object;
-         if (netdev->type != NET_CLIENT_DRIVER_NIC ||
+         name = netdev->id;
-             !opts->u.nic.has_netdev) {
--            peer = net_hub_add_port(net->has_vlan ? net->vlan : 0, NULL);
+-        if (netdev->type == NET_CLIENT_DRIVER_DUMP ||
-+            peer = net_hub_add_port(net->has_vlan ? net->vlan : 0, NULL, NULL);
+-            netdev->type == NET_CLIENT_DRIVER_NIC ||
-         }
++        if (netdev->type == NET_CLIENT_DRIVER_NIC ||
+             !net_client_init_fun[netdev->type]) {
-         if (net->has_vlan && !vlan_warned) {
+             error_setg(errp, QERR_INVALID_PARAMETER_VALUE, "type",
                         "a netdev backend type");
@@ -XXX,XX +XXX,XX @@ static int net_client_init1(const void *object, bool is_netdev, Error **errp)
              legacy.type = NET_CLIENT_DRIVER_VDE;
              legacy.u.vde = opts->u.vde;
              break;
 -        case NET_LEGACY_OPTIONS_TYPE_DUMP:
 -            legacy.type = NET_CLIENT_DRIVER_DUMP;
 -            legacy.u.dump = opts->u.dump;
 -            break;
          case NET_LEGACY_OPTIONS_TYPE_BRIDGE:
              legacy.type = NET_CLIENT_DRIVER_BRIDGE;
              legacy.u.bridge = opts->u.bridge;
 diff --git a/qapi/net.json b/qapi/net.json
 index XXXXXXX..XXXXXXX 100644
 --- a/qapi/net.json
 +++ b/qapi/net.json
 @@ -XXX,XX +XXX,XX @@
- # Connect two or more net clients through a software hub.
+ #
- #
+ # Add a network backend.
- # @hubid: hub identifier number
+ #
-+# @netdev: used to connect hub to a netdev instead of a device (since 2.12)
+-# @type: the type of network backend.  Current valid values are 'user', 'tap',
- #
+-#        'vde', 'socket', 'dump' and 'bridge'
- # Since: 1.2
++# @type: the type of network backend. Possible values are listed in
- ##
++#        NetClientDriver (excluding 'none' and 'nic')
- { 'struct': 'NetdevHubPortOptions',
+ #
-   'data': {
+ # @id: the name of the new network backend
--    'hubid':     'int32' } }
+ #
-+    'hubid':     'int32',
+@@ -XXX,XX +XXX,XX @@
-+    '*netdev':    'str' } }
+     '*mode':  'uint16' } }
  ##
- # @NetdevNetmapOptions:
+-# @NetdevDumpOptions:
 -#
 -# Dump VLAN network traffic to a file.
 -#
 -# @len: per-packet size limit (64k default). Understands [TGMKkb]
 -# suffixes.
 -#
 -# @file: dump file path (default is qemu-vlan0.pcap)
 -#
 -# Since: 1.2
 -##
 -{ 'struct': 'NetdevDumpOptions',
 -  'data': {
 -    '*len':  'size',
 -    '*file': 'str' } }
 -
 -##
  # @NetdevBridgeOptions:
  #
  # Connect a host TAP network interface to a host bridge device.
@@ -XXX,XX +XXX,XX @@
  # Available netdev drivers.
  #
  # Since: 2.7
 +#
 +# 'dump' - removed with 2.12
  ##
  { 'enum': 'NetClientDriver',
 -  'data': [ 'none', 'nic', 'user', 'tap', 'l2tpv3', 'socket', 'vde', 'dump',
 +  'data': [ 'none', 'nic', 'user', 'tap', 'l2tpv3', 'socket', 'vde',
              'bridge', 'hubport', 'netmap', 'vhost-user' ] }
  ##
@@ -XXX,XX +XXX,XX @@
      'l2tpv3':   'NetdevL2TPv3Options',
      'socket':   'NetdevSocketOptions',
      'vde':      'NetdevVdeOptions',
 -    'dump':     'NetdevDumpOptions',
      'bridge':   'NetdevBridgeOptions',
      'hubport':  'NetdevHubPortOptions',
      'netmap':   'NetdevNetmapOptions',
@@ -XXX,XX +XXX,XX @@
  ##
  { 'enum': 'NetLegacyOptionsType',
    'data': ['none', 'nic', 'user', 'tap', 'l2tpv3', 'socket', 'vde',
 -           'dump', 'bridge', 'netmap', 'vhost-user'] }
 +           'bridge', 'netmap', 'vhost-user'] }
  ##
  # @NetLegacyOptions:
@@ -XXX,XX +XXX,XX @@
      'l2tpv3':   'NetdevL2TPv3Options',
      'socket':   'NetdevSocketOptions',
      'vde':      'NetdevVdeOptions',
 -    'dump':     'NetdevDumpOptions',
      'bridge':   'NetdevBridgeOptions',
      'netmap':   'NetdevNetmapOptions',
      'vhost-user': 'NetdevVhostUserOptions' } }
 diff --git a/qemu-doc.texi b/qemu-doc.texi
 index XXXXXXX..XXXXXXX 100644
 --- a/qemu-doc.texi
 +++ b/qemu-doc.texi
@@ -XXX,XX +XXX,XX @@ that can be specified with the ``-device'' parameter.
  The drive addr argument is replaced by the the addr argument
  that can be specified with the ``-device'' parameter.
 -@subsection -net dump (since 2.10.0)
 -
 -The ``--net dump'' argument is now replaced with the
 -``-object filter-dump'' argument which works in combination
 -with the modern ``-netdev`` backends instead.
 -
  @subsection -usbdevice (since 2.10.0)
  The ``-usbdevice DEV'' argument is now a synonym for setting
 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 @@ DEF("netdev", HAS_ARG, QEMU_OPTION_netdev,
+@@ -XXX,XX +XXX,XX @@ DEF("net", HAS_ARG, QEMU_OPTION_net,
- #endif
+     "                configure or create an on-board (or machine default) NIC and\n"
-     "-netdev vhost-user,id=str,chardev=dev[,vhostforce=on|off]\n"
+     "                connect it either to VLAN 'n' or the netdev 'nd' (for pluggable\n"
-     "                configure a vhost-user network, backed by a chardev 'dev'\n"
+     "                NICs please use '-device devtype,netdev=nd' instead)\n"
--    "-netdev hubport,id=str,hubid=n\n"
+-    "-net dump[,vlan=n][,file=f][,len=n]\n"
-+    "-netdev hubport,id=str,hubid=n[,netdev=nd]\n"
+-    "                dump traffic on vlan 'n' to file 'f' (max n bytes per packet)\n"
-     "                configure a hub port on QEMU VLAN 'n'\n", QEMU_ARCH_ALL)
+     "-net none       use it alone to have zero network devices. If no -net option\n"
- DEF("net", HAS_ARG, QEMU_OPTION_net,
+     "                is provided, the default is '-net nic -net user'\n"
-     "-net nic[,vlan=n][,netdev=nd][,macaddr=mac][,model=type][,name=str][,addr=str][,vectors=v]\n"
+     "-net ["
-@@ -XXX,XX +XXX,XX @@ vde_switch -F -sock /tmp/myswitch
+@@ -XXX,XX +XXX,XX @@ qemu -m 512 -object memory-backend-file,id=mem,size=512M,mem-path=/hugetlbfs,sha
- qemu-system-i386 linux.img -net nic -net vde,sock=/tmp/myswitch
+      -device virtio-net-pci,netdev=net0
  @end example
--@item -netdev hubport,id=@var{id},hubid=@var{hubid}
+-@item -net dump[,vlan=@var{n}][,file=@var{file}][,len=@var{len}]
-+@item -netdev hubport,id=@var{id},hubid=@var{hubid}[,netdev=@var{nd}]
+-Dump network traffic on VLAN @var{n} to file @var{file} (@file{qemu-vlan0.pcap} by default).
+-At most @var{len} bytes (64k by default) per packet are stored. The file format is
- Create a hub port on QEMU "vlan" @var{hubid}.
+-libpcap, so it can be analyzed with tools such as tcpdump or Wireshark.
+-Note: For devices created with '-netdev', use '-object filter-dump,...' instead.
- The hubport netdev lets you connect a NIC to a QEMU "vlan" instead of a single
+-
- netdev.  @code{-net} and @code{-device} with parameter @option{vlan} create the
+ @item -net none
--required hub automatically.
+ Indicate that no network devices should be configured. It is used to
-+required hub automatically. Alternatively, you can also connect the hubport
+ override the default configuration (@option{-net nic -net user}) which
 +to another netdev with ID @var{nd} by using the @option{netdev=@var{nd}}
 +option.
  @item -netdev vhost-user,chardev=@var{id}[,vhostforce=on|off][,queues=n]
 --
 .7.4

-[Qemu-devel] [PULL 4/6] net: Allow netdevs to be used with 'hostfwd_add' and 'hostfwd_remove'
+[Qemu-devel] [PULL 6/9] net: Remove the deprecated 'host_net_add' and 'host_net_remove' HMP commands
 From: Thomas Huth <thuth@redhat.com>
-It does not make much sense to limit these commands to the legacy 'vlan'
+They are deprecated since QEMU v2.10, and so far nobody complained that
-concept only, they should work with the modern netdevs, too. So now
+these commands are still necessary for any reason - and since you can use
-it is possible to use this command with one, two or three parameters.
+'netdev_add' and 'netdev_remove' instead, there also should not be any
+real reason. Since they are also standing in the way for the upcoming
-With one parameter, the command installs a hostfwd rule on the default
+'vlan' clean-up, it's now time to remove them.
-"user" network:
-    hostfwd_add tcp:...
+Reviewed-by: Paolo Bonzini <pbonzini@redhat.com>
 With two parameters, the command installs a hostfwd rule on a netdev
 (that's the new way of using this command):
     hostfwd_add netdev_id tcp:...
 With three parameters, the command installs a rule on a 'vlan' (aka hub):
     hostfwd_add hub_id name tcp:...
 Same applies to the hostfwd_remove command now.
 Signed-off-by: Thomas Huth <thuth@redhat.com>
 Signed-off-by: Jason Wang <jasowang@redhat.com>
 ---
- hmp-commands.hx |  4 ++--
+ hmp-commands.hx  | 30 ------------------
- net/slirp.c     | 33 +++++++++++++++++++++++----------
+ hmp.h            |  3 --
-files changed, 25 insertions(+), 12 deletions(-)
+ monitor.c        | 61 ------------------------------------
  net/net.c        | 94 --------------------------------------------------------
  qemu-doc.texi    | 10 ------
  tests/test-hmp.c |  2 --
 files changed, 200 deletions(-)
 diff --git a/hmp-commands.hx b/hmp-commands.hx
 index XXXXXXX..XXXXXXX 100644
 --- a/hmp-commands.hx
 +++ b/hmp-commands.hx
-@@ -XXX,XX +XXX,XX @@ ETEXI
+@@ -XXX,XX +XXX,XX @@ Inject PCIe AER error
  ETEXI
      {
-         .name       = "hostfwd_add",
+-        .name       = "host_net_add",
-         .args_type  = "arg1:s,arg2:s?,arg3:s?",
+-        .args_type  = "device:s,opts:s?",
--        .params     = "[vlan_id name] [tcp|udp]:[hostaddr]:hostport-[guestaddr]:guestport",
+-        .params     = "tap|user|socket|vde|netmap|bridge|vhost-user|dump [options]",
-+        .params     = "[hub_id name]|[netdev_id] [tcp|udp]:[hostaddr]:hostport-[guestaddr]:guestport",
+-        .help       = "add host VLAN client (deprecated, use netdev_add instead)",
-         .help       = "redirect TCP or UDP connections from host to guest (requires -net user)",
+-        .cmd        = hmp_host_net_add,
-         .cmd        = hmp_hostfwd_add,
+-        .command_completion = host_net_add_completion,
-     },
+-    },
-@@ -XXX,XX +XXX,XX @@ ETEXI
+-
-     {
+-STEXI
-         .name       = "hostfwd_remove",
+-@item host_net_add
-         .args_type  = "arg1:s,arg2:s?,arg3:s?",
+-@findex host_net_add
--        .params     = "[vlan_id name] [tcp|udp]:[hostaddr]:hostport",
+-Add host VLAN client. Deprecated, please use @code{netdev_add} instead.
-+        .params     = "[hub_id name]|[netdev_id] [tcp|udp]:[hostaddr]:hostport",
+-ETEXI
-         .help       = "remove host-to-guest TCP or UDP redirection",
+-
-         .cmd        = hmp_hostfwd_remove,
+-    {
-     },
+-        .name       = "host_net_remove",
-diff --git a/net/slirp.c b/net/slirp.c
+-        .args_type  = "vlan_id:i,device:s",
-index XXXXXXX..XXXXXXX 100644
+-        .params     = "vlan_id name",
---- a/net/slirp.c
+-        .help       = "remove host VLAN client (deprecated, use netdev_del instead)",
-+++ b/net/slirp.c
+-        .cmd        = hmp_host_net_remove,
-@@ -XXX,XX +XXX,XX @@ error:
+-        .command_completion = host_net_remove_completion,
-     return -1;
+-    },
 -
 -STEXI
 -@item host_net_remove
 -@findex host_net_remove
 -Remove host VLAN client. Deprecated, please use @code{netdev_del} instead.
 -ETEXI
 -
 -    {
          .name       = "netdev_add",
          .args_type  = "netdev:O",
          .params     = "[user|tap|socket|vde|bridge|hubport|netmap|vhost-user],id=str[,prop=value][,...]",
 diff --git a/hmp.h b/hmp.h
 index XXXXXXX..XXXXXXX 100644
 --- a/hmp.h
 +++ b/hmp.h
@@ -XXX,XX +XXX,XX @@ void migrate_set_capability_completion(ReadLineState *rs, int nb_args,
                                         const char *str);
  void migrate_set_parameter_completion(ReadLineState *rs, int nb_args,
                                        const char *str);
 -void host_net_add_completion(ReadLineState *rs, int nb_args, const char *str);
 -void host_net_remove_completion(ReadLineState *rs, int nb_args,
 -                                const char *str);
  void delvm_completion(ReadLineState *rs, int nb_args, const char *str);
  void loadvm_completion(ReadLineState *rs, int nb_args, const char *str);
  void hmp_rocker(Monitor *mon, const QDict *qdict);
 diff --git a/monitor.c b/monitor.c
 index XXXXXXX..XXXXXXX 100644
 --- a/monitor.c
 +++ b/monitor.c
@@ -XXX,XX +XXX,XX @@ void migrate_set_parameter_completion(ReadLineState *rs, int nb_args,
      }
  }
--static SlirpState *slirp_lookup(Monitor *mon, const char *vlan,
+-void host_net_add_completion(ReadLineState *rs, int nb_args, const char *str)
--                                const char *stack)
+-{
-+static SlirpState *slirp_lookup(Monitor *mon, const char *hub_id,
+-    int i;
-+                                const char *name)
+-    size_t len;
 -    if (nb_args != 2) {
 -        return;
 -    }
 -    len = strlen(str);
 -    readline_set_completion_index(rs, len);
 -    for (i = 0; host_net_devices[i]; i++) {
 -        if (!strncmp(host_net_devices[i], str, len)) {
 -            readline_add_completion(rs, host_net_devices[i]);
 -        }
 -    }
 -}
 -
 -void host_net_remove_completion(ReadLineState *rs, int nb_args, const char *str)
 -{
 -    NetClientState *ncs[MAX_QUEUE_NUM];
 -    int count, i, len;
 -
 -    len = strlen(str);
 -    readline_set_completion_index(rs, len);
 -    if (nb_args == 2) {
 -        count = qemu_find_net_clients_except(NULL, ncs,
 -                                             NET_CLIENT_DRIVER_NONE,
 -                                             MAX_QUEUE_NUM);
 -        for (i = 0; i < MIN(count, MAX_QUEUE_NUM); i++) {
 -            int id;
 -            char name[16];
 -
 -            if (net_hub_id_for_client(ncs[i], &id)) {
 -                continue;
 -            }
 -            snprintf(name, sizeof(name), "%d", id);
 -            if (!strncmp(str, name, len)) {
 -                readline_add_completion(rs, name);
 -            }
 -        }
 -        return;
 -    } else if (nb_args == 3) {
 -        count = qemu_find_net_clients_except(NULL, ncs,
 -                                             NET_CLIENT_DRIVER_NIC,
 -                                             MAX_QUEUE_NUM);
 -        for (i = 0; i < MIN(count, MAX_QUEUE_NUM); i++) {
 -            int id;
 -            const char *name;
 -
 -            if (ncs[i]->info->type == NET_CLIENT_DRIVER_HUBPORT ||
 -                net_hub_id_for_client(ncs[i], &id)) {
 -                continue;
 -            }
 -            name = ncs[i]->name;
 -            if (!strncmp(str, name, len)) {
 -                readline_add_completion(rs, name);
 -            }
 -        }
 -        return;
 -    }
 -}
 -
  static void vm_completion(ReadLineState *rs, const char *str)
  {
--
+     size_t len;
--    if (vlan) {
+diff --git a/net/net.c b/net/net.c
-+    if (name) {
+index XXXXXXX..XXXXXXX 100644
-         NetClientState *nc;
+--- a/net/net.c
--        nc = net_hub_find_client_by_name(strtol(vlan, NULL, 0), stack);
++++ b/net/net.c
--        if (!nc) {
+@@ -XXX,XX +XXX,XX @@
--            monitor_printf(mon, "unrecognized (vlan-id, stackname) pair\n");
+ static VMChangeStateEntry *net_change_state_entry;
--            return NULL;
+ static QTAILQ_HEAD(, NetClientState) net_clients;
-+        if (hub_id) {
-+            nc = net_hub_find_client_by_name(strtol(hub_id, NULL, 0), name);
+-const char *host_net_devices[] = {
-+            if (!nc) {
+-    "tap",
-+                monitor_printf(mon, "unrecognized (vlan-id, stackname) pair\n");
+-    "socket",
-+                return NULL;
+-#ifdef CONFIG_NET_BRIDGE
-+            }
+-    "bridge",
-+        } else {
+-#endif
-+            nc = qemu_find_netdev(name);
+-#ifdef CONFIG_NETMAP
-+            if (!nc) {
+-    "netmap",
-+                monitor_printf(mon, "unrecognized netdev id '%s'\n", name);
+-#endif
-+                return NULL;
+-#ifdef CONFIG_SLIRP
-+            }
+-    "user",
-         }
+-#endif
-         if (strcmp(nc->model, "user")) {
+-#ifdef CONFIG_VDE
-             monitor_printf(mon, "invalid device specified\n");
+-    "vde",
-@@ -XXX,XX +XXX,XX @@ void hmp_hostfwd_remove(Monitor *mon, const QDict *qdict)
+-#endif
-     const char *arg2 = qdict_get_try_str(qdict, "arg2");
+-    "vhost-user",
-     const char *arg3 = qdict_get_try_str(qdict, "arg3");
+-    NULL,
+-};
--    if (arg2) {
+-
-+    if (arg3) {
+ /***********************************************************/
-         s = slirp_lookup(mon, arg1, arg2);
+ /* network device redirectors */
-         src_str = arg3;
-+    } else if (arg2) {
+@@ -XXX,XX +XXX,XX @@ static int net_client_init(QemuOpts *opts, bool is_netdev, Error **errp)
-+        s = slirp_lookup(mon, NULL, arg1);
+     return ret;
-+        src_str = arg2;
+ }
-     } else {
-         s = slirp_lookup(mon, NULL, NULL);
+-
-         src_str = arg1;
+-static int net_host_check_device(const char *device)
-@@ -XXX,XX +XXX,XX @@ void hmp_hostfwd_add(Monitor *mon, const QDict *qdict)
+-{
-     const char *arg2 = qdict_get_try_str(qdict, "arg2");
+-    int i;
-     const char *arg3 = qdict_get_try_str(qdict, "arg3");
+-    for (i = 0; host_net_devices[i]; i++) {
+-        if (!strncmp(host_net_devices[i], device,
--    if (arg2) {
+-                     strlen(host_net_devices[i]))) {
-+    if (arg3) {
+-            return 1;
-         s = slirp_lookup(mon, arg1, arg2);
+-        }
-         redir_str = arg3;
+-    }
-+    } else if (arg2) {
+-
-+        s = slirp_lookup(mon, NULL, arg1);
+-    return 0;
-+        redir_str = arg2;
+-}
-     } else {
+-
-         s = slirp_lookup(mon, NULL, NULL);
+-void hmp_host_net_add(Monitor *mon, const QDict *qdict)
-         redir_str = arg1;
+-{
 -    const char *device = qdict_get_str(qdict, "device");
 -    const char *opts_str = qdict_get_try_str(qdict, "opts");
 -    Error *local_err = NULL;
 -    QemuOpts *opts;
 -    static bool warned;
 -
 -    if (!warned && !qtest_enabled()) {
 -        error_report("host_net_add is deprecated, use netdev_add instead");
 -        warned = true;
 -    }
 -
 -    if (!net_host_check_device(device)) {
 -        monitor_printf(mon, "invalid host network device %s\n", device);
 -        return;
 -    }
 -
 -    opts = qemu_opts_parse_noisily(qemu_find_opts("net"),
 -                                   opts_str ? opts_str : "", false);
 -    if (!opts) {
 -        return;
 -    }
 -
 -    qemu_opt_set(opts, "type", device, &error_abort);
 -
 -    net_client_init(opts, false, &local_err);
 -    if (local_err) {
 -        error_report_err(local_err);
 -        monitor_printf(mon, "adding host network device %s failed\n", device);
 -    }
 -}
 -
 -void hmp_host_net_remove(Monitor *mon, const QDict *qdict)
 -{
 -    NetClientState *nc;
 -    int vlan_id = qdict_get_int(qdict, "vlan_id");
 -    const char *device = qdict_get_str(qdict, "device");
 -    static bool warned;
 -
 -    if (!warned && !qtest_enabled()) {
 -        error_report("host_net_remove is deprecated, use netdev_del instead");
 -        warned = true;
 -    }
 -
 -    nc = net_hub_find_client_by_name(vlan_id, device);
 -    if (!nc) {
 -        error_report("Host network device '%s' on hub '%d' not found",
 -                     device, vlan_id);
 -        return;
 -    }
 -    if (nc->info->type == NET_CLIENT_DRIVER_NIC) {
 -        error_report("invalid host network device '%s'", device);
 -        return;
 -    }
 -
 -    qemu_del_net_client(nc->peer);
 -    qemu_del_net_client(nc);
 -    qemu_opts_del(qemu_opts_find(qemu_find_opts("net"), device));
 -}
 -
  void netdev_add(QemuOpts *opts, Error **errp)
  {
      net_client_init(opts, true, errp);
 diff --git a/qemu-doc.texi b/qemu-doc.texi
 index XXXXXXX..XXXXXXX 100644
 --- a/qemu-doc.texi
 +++ b/qemu-doc.texi
@@ -XXX,XX +XXX,XX @@ from qcow2 images.
  The ``query-cpus'' command is replaced by the ``query-cpus-fast'' command.
 -@section System emulator human monitor commands
 -
 -@subsection host_net_add (since 2.10.0)
 -
 -The ``host_net_add'' command is replaced by the ``netdev_add'' command.
 -
 -@subsection host_net_remove (since 2.10.0)
 -
 -The ``host_net_remove'' command is replaced by the ``netdev_del'' command.
 -
  @section System emulator devices
  @subsection ivshmem (since 2.6.0)
 diff --git a/tests/test-hmp.c b/tests/test-hmp.c
 index XXXXXXX..XXXXXXX 100644
 --- a/tests/test-hmp.c
 +++ b/tests/test-hmp.c
@@ -XXX,XX +XXX,XX @@ static const char *hmp_cmds[] = {
      "dump-guest-memory /dev/null 0 4096",
      "dump-guest-memory /dev/null",
      "gdbserver",
 -    "host_net_add user id=net0",
      "hostfwd_add tcp::43210-:43210",
      "hostfwd_remove tcp::43210-:43210",
 -    "host_net_remove 0 net0",
      "i /w 0",
      "log all",
      "log none",
 --
 .7.4

-[Qemu-devel] [PULL 2/6] colo: compare the packet based on the tcp sequence number
+[Qemu-devel] [PULL 7/9] net: Add a new convenience option "--nic" to configure default/on-board NICs
-From: Mao Zhongyi <maozy.fnst@cn.fujitsu.com>
+From: Thomas Huth <thuth@redhat.com>
-Packet size some time different or when network is busy.
+The legacy "-net" option can be quite confusing for the users since most
-Based on same payload size, but TCP protocol can not
+people do not expect to get a "vlan" hub between their emulated guest
-guarantee send the same one packet in the same way,
+hardware and the host backend. But so far, we are also not able to get
+rid of "-net" completely, since it is the only way to configure on-board
-like that:
+NICs that can not be instantiated via "-device" yet. It's also a little
-We send this payload:
+bit shorter to type "-net nic -net tap" instead of "-device xyz,netdev=n1
-------------------------------
+-netdev tap,id=n1".
-| header |1|2|3|4|5|6|7|8|9|0|
-------------------------------
+So what we need is a new convenience option that is shorter to type than
+the full -device + -netdev stuff, and which can be used to configure the
-primary:
+on-board NICs that can not be handled via -device yet. Thus this patch now
-ppkt1:
+provides such a new option "--nic": It adds an entry in the nd_table to
-----------------
+configure a on-board / default NIC, creates a host backend and connects
-| header |1|2|3|
+the two directly, without a confusing "vlan" hub inbetween.
-----------------
-ppkt2:
+Reviewed-by: Paolo Bonzini <pbonzini@redhat.com>
-------------------------
+Signed-off-by: Thomas Huth <thuth@redhat.com>
 | header |4|5|6|7|8|9|0|
 ------------------------
 secondary:
 spkt1:
 ------------------------------
 | header |1|2|3|4|5|6|7|8|9|0|
 ------------------------------
 In the original method, ppkt1 and ppkt2 are different in size and
 spkt1, so they can't compare and trigger the checkpoint.
 I have tested FTP get 200M and 1G file many times, I found that
 the performance was less than 1% of the native.
 Now I reconstructed the comparison of TCP packets based on the
 TCP sequence number. first of all, ppkt1 and spkt1 have the same
 starting sequence number, so they can compare, even though their
 length is different. And then ppkt1 with a smaller payload length
 is used as the comparison length, if the payload is same, send
 out the ppkt1 and record the offset(the length of ppkt1 payload)
 in spkt1. The next comparison, ppkt2 and spkt1 can be compared
 from the recorded position of spkt1.
 like that:
 ----------------
 | header |1|2|3| ppkt1
 ---------|-----|
          |     |
 ---------v-----v--------------
 | header |1|2|3|4|5|6|7|8|9|0| spkt1
 ---------------|\------------|
                | \offset     |
       ---------v-------------v
       | header |4|5|6|7|8|9|0| ppkt2
       ------------------------
 In this way, the performance can reach native 20% in my multiple
 tests.
 Cc: Zhang Chen <zhangckid@gmail.com>
 Cc: Li Zhijian <lizhijian@cn.fujitsu.com>
 Cc: Jason Wang <jasowang@redhat.com>
 Signed-off-by: Mao Zhongyi <maozy.fnst@cn.fujitsu.com>
 Signed-off-by: Li Zhijian <lizhijian@cn.fujitsu.com>
 Signed-off-by: Zhang Chen <zhangckid@gmail.com>
 Reviewed-by: Zhang Chen <zhangckid@gmail.com>
 Tested-by: Zhang Chen <zhangckid@gmail.com>
 Signed-off-by: Jason Wang <jasowang@redhat.com>
 ---
- net/colo-compare.c | 343 +++++++++++++++++++++++++++++++++++------------------
+ include/sysemu/sysemu.h |  1 +
- net/colo.c         |   9 ++
+ net/net.c               | 78 +++++++++++++++++++++++++++++++++++++++++++++++++
- net/colo.h         |  15 +++
+ qemu-options.hx         | 40 +++++++++++++++++++++----
- net/trace-events   |   2 +-
+ vl.c                    |  7 +++++
-files changed, 250 insertions(+), 119 deletions(-)
+files changed, 120 insertions(+), 6 deletions(-)
-diff --git a/net/colo-compare.c b/net/colo-compare.c
+diff --git a/include/sysemu/sysemu.h b/include/sysemu/sysemu.h
 index XXXXXXX..XXXXXXX 100644
---- a/net/colo-compare.c
+--- a/include/sysemu/sysemu.h
-+++ b/net/colo-compare.c
++++ b/include/sysemu/sysemu.h
-@@ -XXX,XX +XXX,XX @@
+@@ -XXX,XX +XXX,XX @@ extern QemuOptsList bdrv_runtime_opts;
- #define COMPARE_READ_LEN_MAX NET_BUFSIZE
+ extern QemuOptsList qemu_chardev_opts;
- #define MAX_QUEUE_SIZE 1024
+ extern QemuOptsList qemu_device_opts;
+ extern QemuOptsList qemu_netdev_opts;
-+#define COLO_COMPARE_FREE_PRIMARY     0x01
++extern QemuOptsList qemu_nic_opts;
-+#define COLO_COMPARE_FREE_SECONDARY   0x02
+ extern QemuOptsList qemu_net_opts;
-+
+ extern QemuOptsList qemu_global_opts;
- /* TODO: Should be configurable */
+ extern QemuOptsList qemu_mon_opts;
- #define REGULAR_PACKET_CHECK_MS 3000
+diff --git a/net/net.c b/net/net.c
+index XXXXXXX..XXXXXXX 100644
-@@ -XXX,XX +XXX,XX @@ static gint seq_sorter(Packet *a, Packet *b, gpointer data)
+--- a/net/net.c
-     return ntohl(atcp->th_seq) - ntohl(btcp->th_seq);
++++ b/net/net.c
@@ -XXX,XX +XXX,XX @@ static int net_init_netdev(void *dummy, QemuOpts *opts, Error **errp)
      return net_client_init(opts, true, errp);
  }
-+static void fill_pkt_tcp_info(void *data, uint32_t *max_ack)
++/* For the convenience "--nic" parameter */
 +static int net_param_nic(void *dummy, QemuOpts *opts, Error **errp)
 +{
-+    Packet *pkt = data;
++    char *mac, *nd_id;
-+    struct tcphdr *tcphd;
++    int idx, ret;
-+
++    NICInfo *ni;
-+    tcphd = (struct tcphdr *)pkt->transport_header;
++    const char *type;
 +
-+    pkt->tcp_seq = ntohl(tcphd->th_seq);
++    type = qemu_opt_get(opts, "type");
-+    pkt->tcp_ack = ntohl(tcphd->th_ack);
++    if (type && g_str_equal(type, "none")) {
-+    *max_ack = *max_ack > pkt->tcp_ack ? *max_ack : pkt->tcp_ack;
++        return 0;    /* Nothing to do, default_net is cleared in vl.c */
-+    pkt->header_size = pkt->transport_header - (uint8_t *)pkt->data
++    }
-+                       + (tcphd->th_off << 2) - pkt->vnet_hdr_len;
++
-+    pkt->payload_size = pkt->size - pkt->header_size;
++    idx = nic_get_free_idx();
-+    pkt->seq_end = pkt->tcp_seq + pkt->payload_size;
++    if (idx == -1 || nb_nics >= MAX_NICS) {
-+    pkt->flags = tcphd->th_flags;
++        error_setg(errp, "no more on-board/default NIC slots available");
 +        return -1;
 +    }
 +
 +    if (!type) {
 +        qemu_opt_set(opts, "type", "user", &error_abort);
 +    }
 +
 +    ni = &nd_table[idx];
 +    memset(ni, 0, sizeof(*ni));
 +    ni->model = qemu_opt_get_del(opts, "model");
 +
 +    /* Create an ID if the user did not specify one */
 +    nd_id = g_strdup(qemu_opts_id(opts));
 +    if (!nd_id) {
 +        nd_id = g_strdup_printf("__org.qemu.nic%i\n", idx);
 +        qemu_opts_set_id(opts, nd_id);
 +    }
 +
 +    /* Handle MAC address */
 +    mac = qemu_opt_get_del(opts, "mac");
 +    if (mac) {
 +        ret = net_parse_macaddr(ni->macaddr.a, mac);
 +        g_free(mac);
 +        if (ret) {
 +            error_setg(errp, "invalid syntax for ethernet address");
 +            return -1;
 +        }
 +        if (is_multicast_ether_addr(ni->macaddr.a)) {
 +            error_setg(errp, "NIC cannot have multicast MAC address");
 +            return -1;
 +        }
 +    }
 +    qemu_macaddr_default_if_unset(&ni->macaddr);
 +
 +    ret = net_client_init(opts, true, errp);
 +    if (ret == 0) {
 +        ni->netdev = qemu_find_netdev(nd_id);
 +        ni->used = true;
 +        nb_nics++;
 +    }
 +
 +    g_free(nd_id);
 +    return ret;
 +}
 +
- /*
+ int net_init_clients(Error **errp)
   * Return 1 on success, if return 0 means the
   * packet will be dropped
   */
 -static int colo_insert_packet(GQueue *queue, Packet *pkt)
 +static int colo_insert_packet(GQueue *queue, Packet *pkt, uint32_t *max_ack)
  {
-     if (g_queue_get_length(queue) <= MAX_QUEUE_SIZE) {
+     net_change_state_entry =
-         if (pkt->ip->ip_p == IPPROTO_TCP) {
+@@ -XXX,XX +XXX,XX @@ int net_init_clients(Error **errp)
-+            fill_pkt_tcp_info(pkt, max_ack);
+         return -1;
              g_queue_insert_sorted(queue,
                                    pkt,
                                    (GCompareDataFunc)seq_sorter,
@@ -XXX,XX +XXX,XX @@ static int packet_enqueue(CompareState *s, int mode, Connection **con)
      }
-     if (mode == PRIMARY_IN) {
++    if (qemu_opts_foreach(qemu_find_opts("nic"), net_param_nic, NULL, errp)) {
--        if (!colo_insert_packet(&conn->primary_list, pkt)) {
++        return -1;
-+        if (!colo_insert_packet(&conn->primary_list, pkt, &conn->pack)) {
++    }
-             error_report("colo compare primary queue size too big,"
++
-                          "drop packet");
+     if (qemu_opts_foreach(qemu_find_opts("net"), net_init_client, NULL, errp)) {
-         }
+         return -1;
-     } else {
+     }
--        if (!colo_insert_packet(&conn->secondary_list, pkt)) {
+@@ -XXX,XX +XXX,XX @@ QemuOptsList qemu_netdev_opts = {
-+        if (!colo_insert_packet(&conn->secondary_list, pkt, &conn->sack)) {
+     },
-             error_report("colo compare secondary queue size too big,"
+ };
-                          "drop packet");
-         }
++QemuOptsList qemu_nic_opts = {
-@@ -XXX,XX +XXX,XX @@ static int packet_enqueue(CompareState *s, int mode, Connection **con)
++    .name = "nic",
-     return 0;
++    .implied_opt_name = "type",
- }
++    .head = QTAILQ_HEAD_INITIALIZER(qemu_nic_opts.head),
++    .desc = {
-+static inline bool after(uint32_t seq1, uint32_t seq2)
++        /*
-+{
++         * no elements => accept any params
-+        return (int32_t)(seq1 - seq2) > 0;
++         * validation will happen later
 +}
 +
 +static void colo_release_primary_pkt(CompareState *s, Packet *pkt)
 +{
 +    int ret;
 +    ret = compare_chr_send(s,
 +                           pkt->data,
 +                           pkt->size,
 +                           pkt->vnet_hdr_len);
 +    if (ret < 0) {
 +        error_report("colo send primary packet failed");
 +    }
 +    trace_colo_compare_main("packet same and release packet");
 +    packet_destroy(pkt, NULL);
 +}
 +
  /*
   * The IP packets sent by primary and secondary
   * will be compared in here
@@ -XXX,XX +XXX,XX @@ static int colo_compare_packet_payload(Packet *ppkt,
  }
  /*
 - * Called from the compare thread on the primary
 - * for compare tcp packet
 - * compare_tcp copied from Dr. David Alan Gilbert's branch
 - */
 -static int colo_packet_compare_tcp(Packet *spkt, Packet *ppkt)
 + * return true means that the payload is consist and
 + * need to make the next comparison, false means do
 + * the checkpoint
 +*/
 +static bool colo_mark_tcp_pkt(Packet *ppkt, Packet *spkt,
 +                              int8_t *mark, uint32_t max_ack)
  {
 -    struct tcphdr *ptcp, *stcp;
 -    int res;
 +    *mark = 0;
 +
 +    if (ppkt->tcp_seq == spkt->tcp_seq && ppkt->seq_end == spkt->seq_end) {
 +        if (colo_compare_packet_payload(ppkt, spkt,
 +                                        ppkt->header_size, spkt->header_size,
 +                                        ppkt->payload_size)) {
 +            *mark = COLO_COMPARE_FREE_SECONDARY | COLO_COMPARE_FREE_PRIMARY;
 +            return true;
 +        }
 +    }
 +    if (ppkt->tcp_seq == spkt->tcp_seq && ppkt->seq_end == spkt->seq_end) {
 +        if (colo_compare_packet_payload(ppkt, spkt,
 +                                        ppkt->header_size, spkt->header_size,
 +                                        ppkt->payload_size)) {
 +            *mark = COLO_COMPARE_FREE_SECONDARY | COLO_COMPARE_FREE_PRIMARY;
 +            return true;
 +        }
 +    }
 +
 +    /* one part of secondary packet payload still need to be compared */
 +    if (!after(ppkt->seq_end, spkt->seq_end)) {
 +        if (colo_compare_packet_payload(ppkt, spkt,
 +                                        ppkt->header_size + ppkt->offset,
 +                                        spkt->header_size + spkt->offset,
 +                                        ppkt->payload_size - ppkt->offset)) {
 +            if (!after(ppkt->tcp_ack, max_ack)) {
 +                *mark = COLO_COMPARE_FREE_PRIMARY;
 +                spkt->offset += ppkt->payload_size - ppkt->offset;
 +                return true;
 +            } else {
 +                /* secondary guest hasn't ack the data, don't send
 +                 * out this packet
 +                 */
 +                return false;
 +            }
 +        }
 +    } else {
 +        /* primary packet is longer than secondary packet, compare
 +         * the same part and mark the primary packet offset
 +         */
-+        if (colo_compare_packet_payload(ppkt, spkt,
++        { /* end of list */ }
-+                                        ppkt->header_size + ppkt->offset,
++    },
-+                                        spkt->header_size + spkt->offset,
++};
-+                                        spkt->payload_size - spkt->offset)) {
++
-+            *mark = COLO_COMPARE_FREE_SECONDARY;
+ QemuOptsList qemu_net_opts = {
-+            ppkt->offset += spkt->payload_size - spkt->offset;
+     .name = "net",
-+            return true;
+     .implied_opt_name = "type",
-+        }
+diff --git a/qemu-options.hx b/qemu-options.hx
-+    }
+index XXXXXXX..XXXXXXX 100644
+--- a/qemu-options.hx
--    trace_colo_compare_main("compare tcp");
++++ b/qemu-options.hx
-+    return false;
+@@ -XXX,XX +XXX,XX @@ DEF("netdev", HAS_ARG, QEMU_OPTION_netdev,
-+}
+ #endif
+     "-netdev hubport,id=str,hubid=n[,netdev=nd]\n"
--    ptcp = (struct tcphdr *)ppkt->transport_header;
+     "                configure a hub port on QEMU VLAN 'n'\n", QEMU_ARCH_ALL)
--    stcp = (struct tcphdr *)spkt->transport_header;
++DEF("nic", HAS_ARG, QEMU_OPTION_nic,
-+static void colo_compare_tcp(CompareState *s, Connection *conn)
++    "--nic [tap|bridge|"
-+{
++#ifdef CONFIG_SLIRP
-+    Packet *ppkt = NULL, *spkt = NULL;
++    "user|"
-+    int8_t mark;
++#endif
++#ifdef __linux__
-     /*
++    "l2tpv3|"
--     * The 'identification' field in the IP header is *very* random
++#endif
--     * it almost never matches.  Fudge this by ignoring differences in
++#ifdef CONFIG_VDE
--     * unfragmented packets; they'll normally sort themselves out if different
++    "vde|"
--     * anyway, and it should recover at the TCP level.
++#endif
--     * An alternative would be to get both the primary and secondary to rewrite
++#ifdef CONFIG_NETMAP
--     * somehow; but that would need some sync traffic to sync the state
++    "netmap|"
--     */
++#endif
--    if (ntohs(ppkt->ip->ip_off) & IP_DF) {
++#ifdef CONFIG_POSIX
--        spkt->ip->ip_id = ppkt->ip->ip_id;
++    "vhost-user|"
--        /* and the sum will be different if the IDs were different */
++#endif
--        spkt->ip->ip_sum = ppkt->ip->ip_sum;
++    "socket][,option][,...][mac=macaddr]\n"
-+     * If ppkt and spkt have the same payload, but ppkt's ACK
++    "                initialize an on-board / default host NIC (using MAC address\n"
-+     * is greater than spkt's ACK, in this case we can not
++    "                macaddr) and connect it to the given host network backend\n"
-+     * send the ppkt because it will cause the secondary guest
++    "--nic none      use it alone to have zero network devices (the default is to\n"
-+     * to miss sending some data in the next. Therefore, we
++    "                provided a 'user' network connection)\n",
-+     * record the maximum ACK in the current queue at both
++    QEMU_ARCH_ALL)
-+     * primary side and secondary side. Only when the ack is
+ DEF("net", HAS_ARG, QEMU_OPTION_net,
-+     * less than the smaller of the two maximum ack, then we
+     "-net nic[,vlan=n][,netdev=nd][,macaddr=mac][,model=type][,name=str][,addr=str][,vectors=v]\n"
-+     * can ensure that the packet's payload is acknowledged by
+     "                configure or create an on-board (or machine default) NIC and\n"
-+     * primary and secondary.
+     "                connect it either to VLAN 'n' or the netdev 'nd' (for pluggable\n"
-+    */
+     "                NICs please use '-device devtype,netdev=nd' instead)\n"
-+    uint32_t min_ack = conn->pack > conn->sack ? conn->sack : conn->pack;
+-    "-net none       use it alone to have zero network devices. If no -net option\n"
-+
+-    "                is provided, the default is '-net nic -net user'\n"
-+pri:
+     "-net ["
-+    if (g_queue_is_empty(&conn->primary_list)) {
+ #ifdef CONFIG_SLIRP
-+        return;
+     "user|"
-     }
+@@ -XXX,XX +XXX,XX @@ qemu -m 512 -object memory-backend-file,id=mem,size=512M,mem-path=/hugetlbfs,sha
-+    ppkt = g_queue_pop_head(&conn->primary_list);
+      -device virtio-net-pci,netdev=net0
-+sec:
+ @end example
-+    if (g_queue_is_empty(&conn->secondary_list)) {
-+        g_queue_push_head(&conn->primary_list, ppkt);
+-@item -net none
-+        return;
+-Indicate that no network devices should be configured. It is used to
-+    }
+-override the default configuration (@option{-net nic -net user}) which
-+    spkt = g_queue_pop_head(&conn->secondary_list);
+-is activated if no @option{-net} options are provided.
++@item --nic [tap|bridge|user|l2tpv3|vde|netmap|vhost-user|socket][,...][,mac=macaddr]
--    /*
++
--     * Check tcp header length for tcp option field.
++This option is a shortcut for setting both, the on-board (default) guest NIC
--     * th_off > 5 means this tcp packet have options field.
++hardware and the host network backend in one go. The host backend options are
--     * The tcp options maybe always different.
++the same as with the corresponding @option{--netdev} option. The guest NIC
--     * for example:
++hardware MAC address can be set with @option{mac=@var{macaddr}}.
--     * From RFC 7323.
++
--     * TCP Timestamps option (TSopt):
++@item --nic none
--     * Kind: 8
++Indicate that no network devices should be configured. It is used to override
--     *
++the default configuration (default NIC with @option{--net user} backend) which
--     * Length: 10 bytes
++is activated if no other networking options are provided.
--     *
+ ETEXI
--     *    +-------+-------+---------------------+---------------------+
--     *    |Kind=8 |  10   |   TS Value (TSval)  |TS Echo Reply (TSecr)|
+ STEXI
--     *    +-------+-------+---------------------+---------------------+
+diff --git a/vl.c b/vl.c
--     *       1       1              4                     4
+index XXXXXXX..XXXXXXX 100644
--     *
+--- a/vl.c
--     * In this case the primary guest's timestamp always different with
++++ b/vl.c
--     * the secondary guest's timestamp. COLO just focus on payload,
+@@ -XXX,XX +XXX,XX @@ int main(int argc, char **argv, char **envp)
--     * so we just need skip this field.
+     qemu_add_opts(&qemu_chardev_opts);
--     */
+     qemu_add_opts(&qemu_device_opts);
-+    if (ppkt->tcp_seq == ppkt->seq_end) {
+     qemu_add_opts(&qemu_netdev_opts);
-+        colo_release_primary_pkt(s, ppkt);
++    qemu_add_opts(&qemu_nic_opts);
-+        ppkt = NULL;
+     qemu_add_opts(&qemu_net_opts);
-+    }
+     qemu_add_opts(&qemu_rtc_opts);
+     qemu_add_opts(&qemu_global_opts);
--    ptrdiff_t ptcp_offset, stcp_offset;
+@@ -XXX,XX +XXX,XX @@ int main(int argc, char **argv, char **envp)
-+    if (ppkt && conn->compare_seq && !after(ppkt->seq_end, conn->compare_seq)) {
+                     exit(1);
-+        trace_colo_compare_main("pri: this packet has compared");
+                 }
-+        colo_release_primary_pkt(s, ppkt);
+                 break;
-+        ppkt = NULL;
++            case QEMU_OPTION_nic:
-+    }
++                default_net = 0;
++                if (net_client_parse(qemu_find_opts("nic"), optarg) == -1) {
--    ptcp_offset = ppkt->transport_header - (uint8_t *)ppkt->data
++                    exit(1);
--                  + (ptcp->th_off << 2) - ppkt->vnet_hdr_len;
++                }
--    stcp_offset = spkt->transport_header - (uint8_t *)spkt->data
++                break;
--                  + (stcp->th_off << 2) - spkt->vnet_hdr_len;
+             case QEMU_OPTION_net:
--    if (ppkt->size - ptcp_offset == spkt->size - stcp_offset) {
+                 default_net = 0;
--        res = colo_compare_packet_payload(ppkt, spkt,
+                 if (net_client_parse(qemu_find_opts("net"), optarg) == -1) {
 -                                          ptcp_offset, stcp_offset,
 -                                          ppkt->size - ptcp_offset);
 +    if (spkt->tcp_seq == spkt->seq_end) {
 +        packet_destroy(spkt, NULL);
 +        if (!ppkt) {
 +            goto pri;
 +        } else {
 +            goto sec;
 +        }
      } else {
 -        trace_colo_compare_main("TCP: payload size of packets are different");
 -        res = -1;
 +        if (conn->compare_seq && !after(spkt->seq_end, conn->compare_seq)) {
 +            trace_colo_compare_main("sec: this packet has compared");
 +            packet_destroy(spkt, NULL);
 +            if (!ppkt) {
 +                goto pri;
 +            } else {
 +                goto sec;
 +            }
 +        }
 +        if (!ppkt) {
 +            g_queue_push_head(&conn->secondary_list, spkt);
 +            goto pri;
 +        }
      }
 -    if (res != 0 &&
 -        trace_event_get_state_backends(TRACE_COLO_COMPARE_MISCOMPARE)) {
 -        char pri_ip_src[20], pri_ip_dst[20], sec_ip_src[20], sec_ip_dst[20];
 -
 -        strcpy(pri_ip_src, inet_ntoa(ppkt->ip->ip_src));
 -        strcpy(pri_ip_dst, inet_ntoa(ppkt->ip->ip_dst));
 -        strcpy(sec_ip_src, inet_ntoa(spkt->ip->ip_src));
 -        strcpy(sec_ip_dst, inet_ntoa(spkt->ip->ip_dst));
 -
 -        trace_colo_compare_ip_info(ppkt->size, pri_ip_src,
 -                                   pri_ip_dst, spkt->size,
 -                                   sec_ip_src, sec_ip_dst);
 -
 -        trace_colo_compare_tcp_info("pri tcp packet",
 -                                    ntohl(ptcp->th_seq),
 -                                    ntohl(ptcp->th_ack),
 -                                    res, ptcp->th_flags,
 -                                    ppkt->size);
 -
 -        trace_colo_compare_tcp_info("sec tcp packet",
 -                                    ntohl(stcp->th_seq),
 -                                    ntohl(stcp->th_ack),
 -                                    res, stcp->th_flags,
 -                                    spkt->size);
 +    if (colo_mark_tcp_pkt(ppkt, spkt, &mark, min_ack)) {
 +        trace_colo_compare_tcp_info("pri",
 +                                    ppkt->tcp_seq, ppkt->tcp_ack,
 +                                    ppkt->header_size, ppkt->payload_size,
 +                                    ppkt->offset, ppkt->flags);
 +
 +        trace_colo_compare_tcp_info("sec",
 +                                    spkt->tcp_seq, spkt->tcp_ack,
 +                                    spkt->header_size, spkt->payload_size,
 +                                    spkt->offset, spkt->flags);
 +
 +        if (mark == COLO_COMPARE_FREE_PRIMARY) {
 +            conn->compare_seq = ppkt->seq_end;
 +            colo_release_primary_pkt(s, ppkt);
 +            g_queue_push_head(&conn->secondary_list, spkt);
 +            goto pri;
 +        }
 +        if (mark == COLO_COMPARE_FREE_SECONDARY) {
 +            conn->compare_seq = spkt->seq_end;
 +            packet_destroy(spkt, NULL);
 +            goto sec;
 +        }
 +        if (mark == (COLO_COMPARE_FREE_PRIMARY | COLO_COMPARE_FREE_SECONDARY)) {
 +            conn->compare_seq = ppkt->seq_end;
 +            colo_release_primary_pkt(s, ppkt);
 +            packet_destroy(spkt, NULL);
 +            goto pri;
 +        }
 +    } else {
 +        g_queue_push_head(&conn->primary_list, ppkt);
 +        g_queue_push_head(&conn->secondary_list, spkt);
          qemu_hexdump((char *)ppkt->data, stderr,
                       "colo-compare ppkt", ppkt->size);
          qemu_hexdump((char *)spkt->data, stderr,
                       "colo-compare spkt", spkt->size);
 -    }
 -    return res;
 +        /*
 +         * colo_compare_inconsistent_notify();
 +         * TODO: notice to checkpoint();
 +         */
 +    }
  }
 +
  /*
   * Called from the compare thread on the primary
   * for compare udp packet
@@ -XXX,XX +XXX,XX @@ static void colo_old_packet_check(void *opaque)
                          (GCompareFunc)colo_old_packet_check_one_conn);
  }
 -/*
 - * Called from the compare thread on the primary
 - * for compare packet with secondary list of the
 - * specified connection when a new packet was
 - * queued to it.
 - */
 -static void colo_compare_connection(void *opaque, void *user_data)
 +static void colo_compare_packet(CompareState *s, Connection *conn,
 +                                int (*HandlePacket)(Packet *spkt,
 +                                Packet *ppkt))
  {
 -    CompareState *s = user_data;
 -    Connection *conn = opaque;
      Packet *pkt = NULL;
      GList *result = NULL;
 -    int ret;
      while (!g_queue_is_empty(&conn->primary_list) &&
             !g_queue_is_empty(&conn->secondary_list)) {
          pkt = g_queue_pop_head(&conn->primary_list);
 -        switch (conn->ip_proto) {
 -        case IPPROTO_TCP:
 -            result = g_queue_find_custom(&conn->secondary_list,
 -                     pkt, (GCompareFunc)colo_packet_compare_tcp);
 -            break;
 -        case IPPROTO_UDP:
 -            result = g_queue_find_custom(&conn->secondary_list,
 -                     pkt, (GCompareFunc)colo_packet_compare_udp);
 -            break;
 -        case IPPROTO_ICMP:
 -            result = g_queue_find_custom(&conn->secondary_list,
 -                     pkt, (GCompareFunc)colo_packet_compare_icmp);
 -            break;
 -        default:
 -            result = g_queue_find_custom(&conn->secondary_list,
 -                     pkt, (GCompareFunc)colo_packet_compare_other);
 -            break;
 -        }
 +        result = g_queue_find_custom(&conn->secondary_list,
 +                 pkt, (GCompareFunc)HandlePacket);
          if (result) {
 -            ret = compare_chr_send(s,
 -                                   pkt->data,
 -                                   pkt->size,
 -                                   pkt->vnet_hdr_len);
 -            if (ret < 0) {
 -                error_report("colo_send_primary_packet failed");
 -            }
 -            trace_colo_compare_main("packet same and release packet");
 +            colo_release_primary_pkt(s, pkt);
              g_queue_remove(&conn->secondary_list, result->data);
 -            packet_destroy(pkt, NULL);
          } else {
              /*
               * If one packet arrive late, the secondary_list or
@@ -XXX,XX +XXX,XX @@ static void colo_compare_connection(void *opaque, void *user_data)
      }
  }
 +/*
 + * Called from the compare thread on the primary
 + * for compare packet with secondary list of the
 + * specified connection when a new packet was
 + * queued to it.
 + */
 +static void colo_compare_connection(void *opaque, void *user_data)
 +{
 +    CompareState *s = user_data;
 +    Connection *conn = opaque;
 +
 +    switch (conn->ip_proto) {
 +    case IPPROTO_TCP:
 +        colo_compare_tcp(s, conn);
 +        break;
 +    case IPPROTO_UDP:
 +        colo_compare_packet(s, conn, colo_packet_compare_udp);
 +        break;
 +    case IPPROTO_ICMP:
 +        colo_compare_packet(s, conn, colo_packet_compare_icmp);
 +        break;
 +    default:
 +        colo_compare_packet(s, conn, colo_packet_compare_other);
 +        break;
 +    }
 +}
 +
  static int compare_chr_send(CompareState *s,
                              const uint8_t *buf,
                              uint32_t size,
 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 @@ Connection *connection_new(ConnectionKey *key)
      conn->processing = false;
      conn->offset = 0;
      conn->syn_flag = 0;
 +    conn->pack = 0;
 +    conn->sack = 0;
      g_queue_init(&conn->primary_list);
      g_queue_init(&conn->secondary_list);
@@ -XXX,XX +XXX,XX @@ Packet *packet_new(const void *data, int size, int vnet_hdr_len)
      pkt->size = size;
      pkt->creation_ms = qemu_clock_get_ms(QEMU_CLOCK_HOST);
      pkt->vnet_hdr_len = vnet_hdr_len;
 +    pkt->tcp_seq = 0;
 +    pkt->tcp_ack = 0;
 +    pkt->seq_end = 0;
 +    pkt->header_size = 0;
 +    pkt->payload_size = 0;
 +    pkt->offset = 0;
 +    pkt->flags = 0;
      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 {
      int64_t creation_ms;
      /* Get vnet_hdr_len from filter */
      uint32_t vnet_hdr_len;
 +    uint32_t tcp_seq; /* sequence number */
 +    uint32_t tcp_ack; /* acknowledgement number */
 +    /* the sequence number of the last byte of the packet */
 +    uint32_t seq_end;
 +    uint8_t header_size;  /* the header length */
 +    uint16_t payload_size; /* the payload length */
 +    /* record the payload offset(the length that has been compared) */
 +    uint16_t offset;
 +    uint8_t flags; /* Flags(aka Control bits) */
  } Packet;
  typedef struct ConnectionKey {
@@ -XXX,XX +XXX,XX @@ typedef struct Connection {
      /* flag to enqueue unprocessed_connections */
      bool processing;
      uint8_t ip_proto;
 +    /* record the sequence number that has been compared */
 +    uint32_t compare_seq;
 +    /* the maximum of acknowledgement number in primary_list queue */
 +    uint32_t pack;
 +    /* the maximum of acknowledgement number in secondary_list queue */
 +    uint32_t sack;
      /* offset = secondary_seq - primary_seq */
      tcp_seq  offset;
      /*
 diff --git a/net/trace-events b/net/trace-events
 index XXXXXXX..XXXXXXX 100644
 --- a/net/trace-events
 +++ b/net/trace-events
@@ -XXX,XX +XXX,XX @@ colo_compare_icmp_miscompare(const char *sta, int size) ": %s = %d"
  colo_compare_ip_info(int psize, const char *sta, const char *stb, int ssize, const char *stc, const char *std) "ppkt size = %d, ip_src = %s, ip_dst = %s, spkt size = %d, ip_src = %s, ip_dst = %s"
  colo_old_packet_check_found(int64_t old_time) "%" PRId64
  colo_compare_miscompare(void) ""
 -colo_compare_tcp_info(const char *pkt, uint32_t seq, uint32_t ack, int res, uint32_t flag, int size) "side: %s seq/ack= %u/%u res= %d flags= 0x%x pkt_size: %d\n"
 +colo_compare_tcp_info(const char *pkt, uint32_t seq, uint32_t ack, int hdlen, int pdlen, int offset, int flags) "%s: seq/ack= %u/%u hdlen= %d pdlen= %d offset= %d flags=%d\n"
  # net/filter-rewriter.c
  colo_filter_rewriter_debug(void) ""
 --
 .7.4

-New patch
+[Qemu-devel] [PULL 8/9] hw/net: Remove unnecessary header includes
+From: Thomas Huth <thuth@redhat.com>
+Headers like "hw/loader.h" and "qemu/sockets.h" are not needed in
+the hw/net/*.c files. And Some other headers are included via other
+headers already, so we can drop them, too.
+Signed-off-by: Thomas Huth <thuth@redhat.com>
+Signed-off-by: Jason Wang <jasowang@redhat.com>
+---
+ hw/net/e1000.c     | 1 -
+ hw/net/lance.c     | 3 ---
+ hw/net/ne2000.c    | 2 --
+ hw/net/pcnet-pci.c | 1 -
+ hw/net/pcnet.c     | 1 -
+ hw/net/rtl8139.c   | 2 --
+ hw/net/xgmac.c     | 1 -
+files changed, 11 deletions(-)
+diff --git a/hw/net/e1000.c b/hw/net/e1000.c
+index XXXXXXX..XXXXXXX 100644
+--- a/hw/net/e1000.c
++++ b/hw/net/e1000.c
+@@ -XXX,XX +XXX,XX @@
+ #include "hw/pci/pci.h"
+ #include "net/net.h"
+ #include "net/checksum.h"
+-#include "hw/loader.h"
+ #include "sysemu/sysemu.h"
+ #include "sysemu/dma.h"
+ #include "qemu/iov.h"
+diff --git a/hw/net/lance.c b/hw/net/lance.c
+index XXXXXXX..XXXXXXX 100644
+--- a/hw/net/lance.c
++++ b/hw/net/lance.c
+@@ -XXX,XX +XXX,XX @@
+  */
+ #include "qemu/osdep.h"
+-#include "hw/sysbus.h"
+-#include "net/net.h"
+ #include "qemu/timer.h"
+-#include "qemu/sockets.h"
+ #include "hw/sparc/sparc32_dma.h"
+ #include "hw/net/lance.h"
+ #include "trace.h"
+diff --git a/hw/net/ne2000.c b/hw/net/ne2000.c
+index XXXXXXX..XXXXXXX 100644
+--- a/hw/net/ne2000.c
++++ b/hw/net/ne2000.c
+@@ -XXX,XX +XXX,XX @@
+  */
+ #include "qemu/osdep.h"
+ #include "hw/pci/pci.h"
+-#include "net/net.h"
+ #include "net/eth.h"
+ #include "ne2000.h"
+-#include "hw/loader.h"
+ #include "sysemu/sysemu.h"
+ /* debug NE2000 card */
+diff --git a/hw/net/pcnet-pci.c b/hw/net/pcnet-pci.c
+index XXXXXXX..XXXXXXX 100644
+--- a/hw/net/pcnet-pci.c
++++ b/hw/net/pcnet-pci.c
+@@ -XXX,XX +XXX,XX @@
+ #include "qemu/osdep.h"
+ #include "hw/pci/pci.h"
+ #include "net/net.h"
+-#include "hw/loader.h"
+ #include "qemu/timer.h"
+ #include "sysemu/dma.h"
+ #include "sysemu/sysemu.h"
+diff --git a/hw/net/pcnet.c b/hw/net/pcnet.c
+index XXXXXXX..XXXXXXX 100644
+--- a/hw/net/pcnet.c
++++ b/hw/net/pcnet.c
+@@ -XXX,XX +XXX,XX @@
+ #include "net/net.h"
+ #include "net/eth.h"
+ #include "qemu/timer.h"
+-#include "qemu/sockets.h"
+ #include "sysemu/sysemu.h"
+ #include "trace.h"
+diff --git a/hw/net/rtl8139.c b/hw/net/rtl8139.c
+index XXXXXXX..XXXXXXX 100644
+--- a/hw/net/rtl8139.c
++++ b/hw/net/rtl8139.c
+@@ -XXX,XX +XXX,XX @@
+ #include "qemu/timer.h"
+ #include "net/net.h"
+ #include "net/eth.h"
+-#include "hw/loader.h"
+ #include "sysemu/sysemu.h"
+-#include "qemu/iov.h"
+ /* debug RTL8139 card */
+ //#define DEBUG_RTL8139 1
+diff --git a/hw/net/xgmac.c b/hw/net/xgmac.c
+index XXXXXXX..XXXXXXX 100644
+--- a/hw/net/xgmac.c
++++ b/hw/net/xgmac.c
+@@ -XXX,XX +XXX,XX @@
+ #include "hw/sysbus.h"
+ #include "qemu/log.h"
+ #include "net/net.h"
+-#include "net/checksum.h"
+ #ifdef DEBUG_XGMAC
+ #define DEBUGF_BRK(message, args...) do { \
+--
+.7.4

-New patch
+[Qemu-devel] [PULL 9/9] tap: setting error appropriately when calling net_init_tap_one()
+From: Jay Zhou <jianjay.zhou@huawei.com>
+If netdev_add tap,id=net0,...,vhost=on failed in net_init_tap_one(),
+the followed up device_add virtio-net-pci,netdev=net0 will fail
+too, prints:
+   TUNSETOFFLOAD ioctl() failed: Bad file descriptor TUNSETOFFLOAD
+   ioctl() failed: Bad file descriptor
+The reason is that the fd of tap is closed when error occured after
+calling net_init_tap_one().
+The fd should be closed when calling net_init_tap_one failed:
+   - if tap_set_sndbuf() failed
+   - if tap_set_sndbuf() succeeded but vhost failed to open or
+     initialize with vhostforce flag on
+   - with wrong vhost command line parameter
+The fd should not be closed just because vhost failed to open or
+initialize but without vhostforce flag. So the followed up
+device_add can fall back to userspace virtio successfully.
+Suggested-by: Michael S. Tsirkin <mst@redhat.com>
+Suggested-by: Igor Mammedov <imammedo@redhat.com>
+Suggested-by: Jason Wang <jasowang@redhat.com>
+Signed-off-by: Jay Zhou <jianjay.zhou@huawei.com>
+Signed-off-by: Jason Wang <jasowang@redhat.com>
+---
+ include/net/vhost_net.h |  3 +++
+ net/tap.c               | 22 +++++++++++++++++-----
+files changed, 20 insertions(+), 5 deletions(-)
+diff --git a/include/net/vhost_net.h b/include/net/vhost_net.h
+index XXXXXXX..XXXXXXX 100644
+--- a/include/net/vhost_net.h
++++ b/include/net/vhost_net.h
+@@ -XXX,XX +XXX,XX @@
+ #include "net/net.h"
+ #include "hw/virtio/vhost-backend.h"
++#define VHOST_NET_INIT_FAILED \
++    "vhost-net requested but could not be initialized"
++
+ struct vhost_net;
+ typedef struct vhost_net VHostNetState;
+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,
+         if (vhostfdname) {
+             vhostfd = monitor_fd_param(cur_mon, vhostfdname, &err);
+             if (vhostfd == -1) {
+-                error_propagate(errp, err);
++                if (tap->has_vhostforce && tap->vhostforce) {
++                    error_propagate(errp, err);
++                } else {
++                    warn_report_err(err);
++                }
+                 return;
+             }
+         } else {
+             vhostfd = open("/dev/vhost-net", O_RDWR);
+             if (vhostfd < 0) {
+-                error_setg_errno(errp, errno,
+-                                 "tap: open vhost char device failed");
++                if (tap->has_vhostforce && tap->vhostforce) {
++                    error_setg_errno(errp, errno,
++                                     "tap: open vhost char device failed");
++                } else {
++                    warn_report("tap: open vhost char device failed: %s",
++                                strerror(errno));
++                }
+                 return;
+             }
+             fcntl(vhostfd, F_SETFL, O_NONBLOCK);
+@@ -XXX,XX +XXX,XX @@ static void net_init_tap_one(const NetdevTapOptions *tap, NetClientState *peer,
+         s->vhost_net = vhost_net_init(&options);
+         if (!s->vhost_net) {
+-            error_setg(errp,
+-                       "vhost-net requested but could not be initialized");
++            if (tap->has_vhostforce && tap->vhostforce) {
++                error_setg(errp, VHOST_NET_INIT_FAILED);
++            } else {
++                warn_report(VHOST_NET_INIT_FAILED);
++            }
+             return;
+         }
+     } else if (vhostfdname) {
+--
+.7.4

The following changes since commit e607bbee553cfe73072870cef458cfa4e78133e2:

Merge remote-tracking branch 'remotes/edgar/tags/edgar/xilinx-next-2018-01-26.for-upstream' into staging (2018-01-26 14:24:25 +0000)

are available in the git repository at:

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

for you to fetch changes up to bf4835a4d5338bb7424827715df22570a8adc67c:

MAINTAINERS: update Dmitry Fleytman email (2018-01-29 16:05:38 +0800)

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

----------------------------------------------------------------
Mao Zhongyi (2):
      colo: modified the payload compare function
      colo: compare the packet based on the tcp sequence number

Philippe Mathieu-Daudé (1):
      MAINTAINERS: update Dmitry Fleytman email

Thomas Huth (3):
      net: Allow hubports to connect to other netdevs
      net: Allow netdevs to be used with 'hostfwd_add' and 'hostfwd_remove'
      qemu-doc: Get rid of "vlan=X" example in the documentation

From: Mao Zhongyi <maozy.fnst@cn.fujitsu.com>

Modified the function colo_packet_compare_common to prepare for the
tcp packet comparison in the next patch.

Cc: Zhang Chen <zhangckid@gmail.com>
Cc: Li Zhijian <lizhijian@cn.fujitsu.com>
Cc: Jason Wang <jasowang@redhat.com>

Signed-off-by: Mao Zhongyi <maozy.fnst@cn.fujitsu.com>
Signed-off-by: Li Zhijian <lizhijian@cn.fujitsu.com>
Signed-off-by: Zhang Chen <zhangckid@gmail.com>
Reviewed-by: Zhang Chen <zhangckid@gmail.com>
Signed-off-by: Jason Wang <jasowang@redhat.com>
---
 net/colo-compare.c | 88 +++++++++++++++++++++++++++---------------------------
 1 file changed, 44 insertions(+), 44 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 **con)
  * return:    0  means packet same
  *            > 0 || < 0 means packet different
  */
-static int colo_packet_compare_common(Packet *ppkt,
-                                      Packet *spkt,
-                                      int poffset,
-                                      int soffset)
+static int colo_compare_packet_payload(Packet *ppkt,
+                                       Packet *spkt,
+                                       uint16_t poffset,
+                                       uint16_t soffset,
+                                       uint16_t len)
+
 {
     if (trace_event_get_state_backends(TRACE_COLO_COMPARE_MISCOMPARE)) {
         char pri_ip_src[20], pri_ip_dst[20], sec_ip_src[20], sec_ip_dst[20];
@@ -XXX,XX +XXX,XX @@ static int colo_packet_compare_common(Packet *ppkt,
                                    sec_ip_src, sec_ip_dst);
     }
 
-    poffset = ppkt->vnet_hdr_len + poffset;
-    soffset = ppkt->vnet_hdr_len + soffset;
-
-    if (ppkt->size - poffset == spkt->size - soffset) {
-        return memcmp(ppkt->data + poffset,
-                      spkt->data + soffset,
-                      spkt->size - soffset);
-    } else {
-        trace_colo_compare_main("Net packet size are not the same");
-        return -1;
-    }
+    return memcmp(ppkt->data + poffset, spkt->data + soffset, len);
 }
 
 /*
@@ -XXX,XX +XXX,XX @@ static int colo_packet_compare_tcp(Packet *spkt, Packet *ppkt)
      * the secondary guest's timestamp. COLO just focus on payload,
      * so we just need skip this field.
      */
-    if (ptcp->th_off > 5) {
-        ptrdiff_t ptcp_offset, stcp_offset;
 
-        ptcp_offset = ppkt->transport_header - (uint8_t *)ppkt->data
-                      + (ptcp->th_off * 4) - ppkt->vnet_hdr_len;
-        stcp_offset = spkt->transport_header - (uint8_t *)spkt->data
-                      + (stcp->th_off * 4) - spkt->vnet_hdr_len;
+    ptrdiff_t ptcp_offset, stcp_offset;
 
-        /*
-         * When network is busy, some tcp options(like sack) will unpredictable
-         * occur in primary side or secondary side. it will make packet size
-         * not same, but the two packet's payload is identical. colo just
-         * care about packet payload, so we skip the option field.
-         */
-        res = colo_packet_compare_common(ppkt, spkt, ptcp_offset, stcp_offset);
-    } else if (ptcp->th_sum == stcp->th_sum) {
-        res = colo_packet_compare_common(ppkt, spkt, ETH_HLEN, ETH_HLEN);
+    ptcp_offset = ppkt->transport_header - (uint8_t *)ppkt->data
+                  + (ptcp->th_off << 2) - ppkt->vnet_hdr_len;
+    stcp_offset = spkt->transport_header - (uint8_t *)spkt->data
+                  + (stcp->th_off << 2) - spkt->vnet_hdr_len;
+    if (ppkt->size - ptcp_offset == spkt->size - stcp_offset) {
+        res = colo_compare_packet_payload(ppkt, spkt,
+                                          ptcp_offset, stcp_offset,
+                                          ppkt->size - ptcp_offset);
     } else {
+        trace_colo_compare_main("TCP: payload size of packets are different");
         res = -1;
     }
 
@@ -XXX,XX +XXX,XX @@ static int colo_packet_compare_tcp(Packet *spkt, Packet *ppkt)
  */
 static int colo_packet_compare_udp(Packet *spkt, Packet *ppkt)
 {
-    int ret;
-    int network_header_length = ppkt->ip->ip_hl * 4;
+    uint16_t network_header_length = ppkt->ip->ip_hl << 2;
+    uint16_t offset = network_header_length + ETH_HLEN + ppkt->vnet_hdr_len;
 
     trace_colo_compare_main("compare udp");
 
@@ -XXX,XX +XXX,XX @@ static int colo_packet_compare_udp(Packet *spkt, Packet *ppkt)
      * other field like TOS,TTL,IP Checksum. we only need to compare
      * the ip payload here.
      */
-    ret = colo_packet_compare_common(ppkt, spkt,
-                                     network_header_length + ETH_HLEN,
-                                     network_header_length + ETH_HLEN);
-
-    if (ret) {
+    if (ppkt->size != spkt->size) {
+        trace_colo_compare_main("UDP: payload size of packets are different");
+        return -1;
+    }
+    if (colo_compare_packet_payload(ppkt, spkt, offset, offset,
+                                    ppkt->size - offset)) {
         trace_colo_compare_udp_miscompare("primary pkt size", ppkt->size);
         trace_colo_compare_udp_miscompare("Secondary pkt size", spkt->size);
         if (trace_event_get_state_backends(TRACE_COLO_COMPARE_MISCOMPARE)) {
@@ -XXX,XX +XXX,XX @@ static int colo_packet_compare_udp(Packet *spkt, Packet *ppkt)
             qemu_hexdump((char *)spkt->data, stderr, "colo-compare sec pkt",
                          spkt->size);
         }
+        return -1;
+    } else {
+        return 0;
     }
-
-    return ret;
 }
 
 /*
@@ -XXX,XX +XXX,XX @@ static int colo_packet_compare_udp(Packet *spkt, Packet *ppkt)
  */
 static int colo_packet_compare_icmp(Packet *spkt, Packet *ppkt)
 {
-    int network_header_length = ppkt->ip->ip_hl * 4;
+    uint16_t network_header_length = ppkt->ip->ip_hl << 2;
+    uint16_t offset = network_header_length + ETH_HLEN + ppkt->vnet_hdr_len;
 
     trace_colo_compare_main("compare icmp");
 
@@ -XXX,XX +XXX,XX @@ static int colo_packet_compare_icmp(Packet *spkt, Packet *ppkt)
      * other field like TOS,TTL,IP Checksum. we only need to compare
      * the ip payload here.
      */
-    if (colo_packet_compare_common(ppkt, spkt,
-                                   network_header_length + ETH_HLEN,
-                                   network_header_length + ETH_HLEN)) {
+    if (ppkt->size != spkt->size) {
+        trace_colo_compare_main("ICMP: payload size of packets are different");
+        return -1;
+    }
+    if (colo_compare_packet_payload(ppkt, spkt, offset, offset,
+                                    ppkt->size - offset)) {
         trace_colo_compare_icmp_miscompare("primary pkt size",
                                            ppkt->size);
         trace_colo_compare_icmp_miscompare("Secondary pkt size",
@@ -XXX,XX +XXX,XX @@ static int colo_packet_compare_icmp(Packet *spkt, Packet *ppkt)
  */
 static int colo_packet_compare_other(Packet *spkt, Packet *ppkt)
 {
+    uint16_t offset = ppkt->vnet_hdr_len;
+
     trace_colo_compare_main("compare other");
     if (trace_event_get_state_backends(TRACE_COLO_COMPARE_MISCOMPARE)) {
         char pri_ip_src[20], pri_ip_dst[20], sec_ip_src[20], sec_ip_dst[20];
@@ -XXX,XX +XXX,XX @@ static int colo_packet_compare_other(Packet *spkt, Packet *ppkt)
                                    sec_ip_src, sec_ip_dst);
     }
 
-    return colo_packet_compare_common(ppkt, spkt, 0, 0);
+    if (ppkt->size != spkt->size) {
+        trace_colo_compare_main("Other: payload size of packets are different");
+        return -1;
+    }
+    return colo_compare_packet_payload(ppkt, spkt, offset, offset,
+                                       ppkt->size - offset);
 }
 
 static int colo_old_packet_check_one(Packet *pkt, int64_t *check_time)
-- 
2.7.4

From: Mao Zhongyi <maozy.fnst@cn.fujitsu.com>

Packet size some time different or when network is busy.
Based on same payload size, but TCP protocol can not
guarantee send the same one packet in the same way,

like that:
We send this payload:
------------------------------
| header |1|2|3|4|5|6|7|8|9|0|
------------------------------

primary:
ppkt1:
----------------
| header |1|2|3|
----------------
ppkt2:
------------------------
| header |4|5|6|7|8|9|0|
------------------------

secondary:
spkt1:
------------------------------
| header |1|2|3|4|5|6|7|8|9|0|
------------------------------

In the original method, ppkt1 and ppkt2 are different in size and
spkt1, so they can't compare and trigger the checkpoint.

I have tested FTP get 200M and 1G file many times, I found that
the performance was less than 1% of the native.

Now I reconstructed the comparison of TCP packets based on the
TCP sequence number. first of all, ppkt1 and spkt1 have the same
starting sequence number, so they can compare, even though their
length is different. And then ppkt1 with a smaller payload length
is used as the comparison length, if the payload is same, send
out the ppkt1 and record the offset(the length of ppkt1 payload)
in spkt1. The next comparison, ppkt2 and spkt1 can be compared
from the recorded position of spkt1.

like that:
----------------
| header |1|2|3| ppkt1
---------|-----|
         |     |
---------v-----v--------------
| header |1|2|3|4|5|6|7|8|9|0| spkt1
---------------|\------------|
               | \offset     |
      ---------v-------------v
      | header |4|5|6|7|8|9|0| ppkt2
      ------------------------

In this way, the performance can reach native 20% in my multiple
tests.

Cc: Zhang Chen <zhangckid@gmail.com>
Cc: Li Zhijian <lizhijian@cn.fujitsu.com>
Cc: Jason Wang <jasowang@redhat.com>

Signed-off-by: Mao Zhongyi <maozy.fnst@cn.fujitsu.com>
Signed-off-by: Li Zhijian <lizhijian@cn.fujitsu.com>
Signed-off-by: Zhang Chen <zhangckid@gmail.com>
Reviewed-by: Zhang Chen <zhangckid@gmail.com>
Tested-by: Zhang Chen <zhangckid@gmail.com>
Signed-off-by: Jason Wang <jasowang@redhat.com>
---
 net/colo-compare.c | 343 +++++++++++++++++++++++++++++++++++------------------
 net/colo.c         |   9 ++
 net/colo.h         |  15 +++
 net/trace-events   |   2 +-
 4 files changed, 250 insertions(+), 119 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 @@
 #define COMPARE_READ_LEN_MAX NET_BUFSIZE
 #define MAX_QUEUE_SIZE 1024
 
+#define COLO_COMPARE_FREE_PRIMARY     0x01
+#define COLO_COMPARE_FREE_SECONDARY   0x02
+
 /* TODO: Should be configurable */
 #define REGULAR_PACKET_CHECK_MS 3000
 
@@ -XXX,XX +XXX,XX @@ static gint seq_sorter(Packet *a, Packet *b, gpointer data)
     return ntohl(atcp->th_seq) - ntohl(btcp->th_seq);
 }
 
+static void fill_pkt_tcp_info(void *data, uint32_t *max_ack)
+{
+    Packet *pkt = data;
+    struct tcphdr *tcphd;
+
+    tcphd = (struct tcphdr *)pkt->transport_header;
+
+    pkt->tcp_seq = ntohl(tcphd->th_seq);
+    pkt->tcp_ack = ntohl(tcphd->th_ack);
+    *max_ack = *max_ack > pkt->tcp_ack ? *max_ack : pkt->tcp_ack;
+    pkt->header_size = pkt->transport_header - (uint8_t *)pkt->data
+                       + (tcphd->th_off << 2) - pkt->vnet_hdr_len;
+    pkt->payload_size = pkt->size - pkt->header_size;
+    pkt->seq_end = pkt->tcp_seq + pkt->payload_size;
+    pkt->flags = tcphd->th_flags;
+}
+
 /*
  * Return 1 on success, if return 0 means the
  * packet will be dropped
  */
-static int colo_insert_packet(GQueue *queue, Packet *pkt)
+static int colo_insert_packet(GQueue *queue, Packet *pkt, uint32_t *max_ack)
 {
     if (g_queue_get_length(queue) <= MAX_QUEUE_SIZE) {
         if (pkt->ip->ip_p == IPPROTO_TCP) {
+            fill_pkt_tcp_info(pkt, max_ack);
             g_queue_insert_sorted(queue,
                                   pkt,
                                   (GCompareDataFunc)seq_sorter,
@@ -XXX,XX +XXX,XX @@ static int packet_enqueue(CompareState *s, int mode, Connection **con)
     }
 
     if (mode == PRIMARY_IN) {
-        if (!colo_insert_packet(&conn->primary_list, pkt)) {
+        if (!colo_insert_packet(&conn->primary_list, pkt, &conn->pack)) {
             error_report("colo compare primary queue size too big,"
                          "drop packet");
         }
     } else {
-        if (!colo_insert_packet(&conn->secondary_list, pkt)) {
+        if (!colo_insert_packet(&conn->secondary_list, pkt, &conn->sack)) {
             error_report("colo compare secondary queue size too big,"
                          "drop packet");
         }
@@ -XXX,XX +XXX,XX @@ static int packet_enqueue(CompareState *s, int mode, Connection **con)
     return 0;
 }
 
+static inline bool after(uint32_t seq1, uint32_t seq2)
+{
+        return (int32_t)(seq1 - seq2) > 0;
+}
+
+static void colo_release_primary_pkt(CompareState *s, Packet *pkt)
+{
+    int ret;
+    ret = compare_chr_send(s,
+                           pkt->data,
+                           pkt->size,
+                           pkt->vnet_hdr_len);
+    if (ret < 0) {
+        error_report("colo send primary packet failed");
+    }
+    trace_colo_compare_main("packet same and release packet");
+    packet_destroy(pkt, NULL);
+}
+
 /*
  * The IP packets sent by primary and secondary
  * will be compared in here
@@ -XXX,XX +XXX,XX @@ static int colo_compare_packet_payload(Packet *ppkt,
 }
 
 /*
- * Called from the compare thread on the primary
- * for compare tcp packet
- * compare_tcp copied from Dr. David Alan Gilbert's branch
- */
-static int colo_packet_compare_tcp(Packet *spkt, Packet *ppkt)
+ * return true means that the payload is consist and
+ * need to make the next comparison, false means do
+ * the checkpoint
+*/
+static bool colo_mark_tcp_pkt(Packet *ppkt, Packet *spkt,
+                              int8_t *mark, uint32_t max_ack)
 {
-    struct tcphdr *ptcp, *stcp;
-    int res;
+    *mark = 0;
+
+    if (ppkt->tcp_seq == spkt->tcp_seq && ppkt->seq_end == spkt->seq_end) {
+        if (colo_compare_packet_payload(ppkt, spkt,
+                                        ppkt->header_size, spkt->header_size,
+                                        ppkt->payload_size)) {
+            *mark = COLO_COMPARE_FREE_SECONDARY | COLO_COMPARE_FREE_PRIMARY;
+            return true;
+        }
+    }
+    if (ppkt->tcp_seq == spkt->tcp_seq && ppkt->seq_end == spkt->seq_end) {
+        if (colo_compare_packet_payload(ppkt, spkt,
+                                        ppkt->header_size, spkt->header_size,
+                                        ppkt->payload_size)) {
+            *mark = COLO_COMPARE_FREE_SECONDARY | COLO_COMPARE_FREE_PRIMARY;
+            return true;
+        }
+    }
+
+    /* one part of secondary packet payload still need to be compared */
+    if (!after(ppkt->seq_end, spkt->seq_end)) {
+        if (colo_compare_packet_payload(ppkt, spkt,
+                                        ppkt->header_size + ppkt->offset,
+                                        spkt->header_size + spkt->offset,
+                                        ppkt->payload_size - ppkt->offset)) {
+            if (!after(ppkt->tcp_ack, max_ack)) {
+                *mark = COLO_COMPARE_FREE_PRIMARY;
+                spkt->offset += ppkt->payload_size - ppkt->offset;
+                return true;
+            } else {
+                /* secondary guest hasn't ack the data, don't send
+                 * out this packet
+                 */
+                return false;
+            }
+        }
+    } else {
+        /* primary packet is longer than secondary packet, compare
+         * the same part and mark the primary packet offset
+         */
+        if (colo_compare_packet_payload(ppkt, spkt,
+                                        ppkt->header_size + ppkt->offset,
+                                        spkt->header_size + spkt->offset,
+                                        spkt->payload_size - spkt->offset)) {
+            *mark = COLO_COMPARE_FREE_SECONDARY;
+            ppkt->offset += spkt->payload_size - spkt->offset;
+            return true;
+        }
+    }
 
-    trace_colo_compare_main("compare tcp");
+    return false;
+}
 
-    ptcp = (struct tcphdr *)ppkt->transport_header;
-    stcp = (struct tcphdr *)spkt->transport_header;
+static void colo_compare_tcp(CompareState *s, Connection *conn)
+{
+    Packet *ppkt = NULL, *spkt = NULL;
+    int8_t mark;
 
     /*
-     * The 'identification' field in the IP header is *very* random
-     * it almost never matches.  Fudge this by ignoring differences in
-     * unfragmented packets; they'll normally sort themselves out if different
-     * anyway, and it should recover at the TCP level.
-     * An alternative would be to get both the primary and secondary to rewrite
-     * somehow; but that would need some sync traffic to sync the state
-     */
-    if (ntohs(ppkt->ip->ip_off) & IP_DF) {
-        spkt->ip->ip_id = ppkt->ip->ip_id;
-        /* and the sum will be different if the IDs were different */
-        spkt->ip->ip_sum = ppkt->ip->ip_sum;
+     * If ppkt and spkt have the same payload, but ppkt's ACK
+     * is greater than spkt's ACK, in this case we can not
+     * send the ppkt because it will cause the secondary guest
+     * to miss sending some data in the next. Therefore, we
+     * record the maximum ACK in the current queue at both
+     * primary side and secondary side. Only when the ack is
+     * less than the smaller of the two maximum ack, then we
+     * can ensure that the packet's payload is acknowledged by
+     * primary and secondary.
+    */
+    uint32_t min_ack = conn->pack > conn->sack ? conn->sack : conn->pack;
+
+pri:
+    if (g_queue_is_empty(&conn->primary_list)) {
+        return;
     }
+    ppkt = g_queue_pop_head(&conn->primary_list);
+sec:
+    if (g_queue_is_empty(&conn->secondary_list)) {
+        g_queue_push_head(&conn->primary_list, ppkt);
+        return;
+    }
+    spkt = g_queue_pop_head(&conn->secondary_list);
 
-    /*
-     * Check tcp header length for tcp option field.
-     * th_off > 5 means this tcp packet have options field.
-     * The tcp options maybe always different.
-     * for example:
-     * From RFC 7323.
-     * TCP Timestamps option (TSopt):
-     * Kind: 8
-     *
-     * Length: 10 bytes
-     *
-     *    +-------+-------+---------------------+---------------------+
-     *    |Kind=8 |  10   |   TS Value (TSval)  |TS Echo Reply (TSecr)|
-     *    +-------+-------+---------------------+---------------------+
-     *       1       1              4                     4
-     *
-     * In this case the primary guest's timestamp always different with
-     * the secondary guest's timestamp. COLO just focus on payload,
-     * so we just need skip this field.
-     */
+    if (ppkt->tcp_seq == ppkt->seq_end) {
+        colo_release_primary_pkt(s, ppkt);
+        ppkt = NULL;
+    }
 
-    ptrdiff_t ptcp_offset, stcp_offset;
+    if (ppkt && conn->compare_seq && !after(ppkt->seq_end, conn->compare_seq)) {
+        trace_colo_compare_main("pri: this packet has compared");
+        colo_release_primary_pkt(s, ppkt);
+        ppkt = NULL;
+    }
 
-    ptcp_offset = ppkt->transport_header - (uint8_t *)ppkt->data
-                  + (ptcp->th_off << 2) - ppkt->vnet_hdr_len;
-    stcp_offset = spkt->transport_header - (uint8_t *)spkt->data
-                  + (stcp->th_off << 2) - spkt->vnet_hdr_len;
-    if (ppkt->size - ptcp_offset == spkt->size - stcp_offset) {
-        res = colo_compare_packet_payload(ppkt, spkt,
-                                          ptcp_offset, stcp_offset,
-                                          ppkt->size - ptcp_offset);
+    if (spkt->tcp_seq == spkt->seq_end) {
+        packet_destroy(spkt, NULL);
+        if (!ppkt) {
+            goto pri;
+        } else {
+            goto sec;
+        }
     } else {
-        trace_colo_compare_main("TCP: payload size of packets are different");
-        res = -1;
+        if (conn->compare_seq && !after(spkt->seq_end, conn->compare_seq)) {
+            trace_colo_compare_main("sec: this packet has compared");
+            packet_destroy(spkt, NULL);
+            if (!ppkt) {
+                goto pri;
+            } else {
+                goto sec;
+            }
+        }
+        if (!ppkt) {
+            g_queue_push_head(&conn->secondary_list, spkt);
+            goto pri;
+        }
     }
 
-    if (res != 0 &&
-        trace_event_get_state_backends(TRACE_COLO_COMPARE_MISCOMPARE)) {
-        char pri_ip_src[20], pri_ip_dst[20], sec_ip_src[20], sec_ip_dst[20];
-
-        strcpy(pri_ip_src, inet_ntoa(ppkt->ip->ip_src));
-        strcpy(pri_ip_dst, inet_ntoa(ppkt->ip->ip_dst));
-        strcpy(sec_ip_src, inet_ntoa(spkt->ip->ip_src));
-        strcpy(sec_ip_dst, inet_ntoa(spkt->ip->ip_dst));
-
-        trace_colo_compare_ip_info(ppkt->size, pri_ip_src,
-                                   pri_ip_dst, spkt->size,
-                                   sec_ip_src, sec_ip_dst);
-
-        trace_colo_compare_tcp_info("pri tcp packet",
-                                    ntohl(ptcp->th_seq),
-                                    ntohl(ptcp->th_ack),
-                                    res, ptcp->th_flags,
-                                    ppkt->size);
-
-        trace_colo_compare_tcp_info("sec tcp packet",
-                                    ntohl(stcp->th_seq),
-                                    ntohl(stcp->th_ack),
-                                    res, stcp->th_flags,
-                                    spkt->size);
+    if (colo_mark_tcp_pkt(ppkt, spkt, &mark, min_ack)) {
+        trace_colo_compare_tcp_info("pri",
+                                    ppkt->tcp_seq, ppkt->tcp_ack,
+                                    ppkt->header_size, ppkt->payload_size,
+                                    ppkt->offset, ppkt->flags);
+
+        trace_colo_compare_tcp_info("sec",
+                                    spkt->tcp_seq, spkt->tcp_ack,
+                                    spkt->header_size, spkt->payload_size,
+                                    spkt->offset, spkt->flags);
+
+        if (mark == COLO_COMPARE_FREE_PRIMARY) {
+            conn->compare_seq = ppkt->seq_end;
+            colo_release_primary_pkt(s, ppkt);
+            g_queue_push_head(&conn->secondary_list, spkt);
+            goto pri;
+        }
+        if (mark == COLO_COMPARE_FREE_SECONDARY) {
+            conn->compare_seq = spkt->seq_end;
+            packet_destroy(spkt, NULL);
+            goto sec;
+        }
+        if (mark == (COLO_COMPARE_FREE_PRIMARY | COLO_COMPARE_FREE_SECONDARY)) {
+            conn->compare_seq = ppkt->seq_end;
+            colo_release_primary_pkt(s, ppkt);
+            packet_destroy(spkt, NULL);
+            goto pri;
+        }
+    } else {
+        g_queue_push_head(&conn->primary_list, ppkt);
+        g_queue_push_head(&conn->secondary_list, spkt);
 
         qemu_hexdump((char *)ppkt->data, stderr,
                      "colo-compare ppkt", ppkt->size);
         qemu_hexdump((char *)spkt->data, stderr,
                      "colo-compare spkt", spkt->size);
-    }
 
-    return res;
+        /*
+         * colo_compare_inconsistent_notify();
+         * TODO: notice to checkpoint();
+         */
+    }
 }
 
+
 /*
  * Called from the compare thread on the primary
  * for compare udp packet
@@ -XXX,XX +XXX,XX @@ static void colo_old_packet_check(void *opaque)
                         (GCompareFunc)colo_old_packet_check_one_conn);
 }
 
-/*
- * Called from the compare thread on the primary
- * for compare packet with secondary list of the
- * specified connection when a new packet was
- * queued to it.
- */
-static void colo_compare_connection(void *opaque, void *user_data)
+static void colo_compare_packet(CompareState *s, Connection *conn,
+                                int (*HandlePacket)(Packet *spkt,
+                                Packet *ppkt))
 {
-    CompareState *s = user_data;
-    Connection *conn = opaque;
     Packet *pkt = NULL;
     GList *result = NULL;
-    int ret;
 
     while (!g_queue_is_empty(&conn->primary_list) &&
            !g_queue_is_empty(&conn->secondary_list)) {
         pkt = g_queue_pop_head(&conn->primary_list);
-        switch (conn->ip_proto) {
-        case IPPROTO_TCP:
-            result = g_queue_find_custom(&conn->secondary_list,
-                     pkt, (GCompareFunc)colo_packet_compare_tcp);
-            break;
-        case IPPROTO_UDP:
-            result = g_queue_find_custom(&conn->secondary_list,
-                     pkt, (GCompareFunc)colo_packet_compare_udp);
-            break;
-        case IPPROTO_ICMP:
-            result = g_queue_find_custom(&conn->secondary_list,
-                     pkt, (GCompareFunc)colo_packet_compare_icmp);
-            break;
-        default:
-            result = g_queue_find_custom(&conn->secondary_list,
-                     pkt, (GCompareFunc)colo_packet_compare_other);
-            break;
-        }
+        result = g_queue_find_custom(&conn->secondary_list,
+                 pkt, (GCompareFunc)HandlePacket);
 
         if (result) {
-            ret = compare_chr_send(s,
-                                   pkt->data,
-                                   pkt->size,
-                                   pkt->vnet_hdr_len);
-            if (ret < 0) {
-                error_report("colo_send_primary_packet failed");
-            }
-            trace_colo_compare_main("packet same and release packet");
+            colo_release_primary_pkt(s, pkt);
             g_queue_remove(&conn->secondary_list, result->data);
-            packet_destroy(pkt, NULL);
         } else {
             /*
              * If one packet arrive late, the secondary_list or
@@ -XXX,XX +XXX,XX @@ static void colo_compare_connection(void *opaque, void *user_data)
     }
 }
 
+/*
+ * Called from the compare thread on the primary
+ * for compare packet with secondary list of the
+ * specified connection when a new packet was
+ * queued to it.
+ */
+static void colo_compare_connection(void *opaque, void *user_data)
+{
+    CompareState *s = user_data;
+    Connection *conn = opaque;
+
+    switch (conn->ip_proto) {
+    case IPPROTO_TCP:
+        colo_compare_tcp(s, conn);
+        break;
+    case IPPROTO_UDP:
+        colo_compare_packet(s, conn, colo_packet_compare_udp);
+        break;
+    case IPPROTO_ICMP:
+        colo_compare_packet(s, conn, colo_packet_compare_icmp);
+        break;
+    default:
+        colo_compare_packet(s, conn, colo_packet_compare_other);
+        break;
+    }
+}
+
 static int compare_chr_send(CompareState *s,
                             const uint8_t *buf,
                             uint32_t size,
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 @@ Connection *connection_new(ConnectionKey *key)
     conn->processing = false;
     conn->offset = 0;
     conn->syn_flag = 0;
+    conn->pack = 0;
+    conn->sack = 0;
     g_queue_init(&conn->primary_list);
     g_queue_init(&conn->secondary_list);
 
@@ -XXX,XX +XXX,XX @@ Packet *packet_new(const void *data, int size, int vnet_hdr_len)
     pkt->size = size;
     pkt->creation_ms = qemu_clock_get_ms(QEMU_CLOCK_HOST);
     pkt->vnet_hdr_len = vnet_hdr_len;
+    pkt->tcp_seq = 0;
+    pkt->tcp_ack = 0;
+    pkt->seq_end = 0;
+    pkt->header_size = 0;
+    pkt->payload_size = 0;
+    pkt->offset = 0;
+    pkt->flags = 0;
 
     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 {
     int64_t creation_ms;
     /* Get vnet_hdr_len from filter */
     uint32_t vnet_hdr_len;
+    uint32_t tcp_seq; /* sequence number */
+    uint32_t tcp_ack; /* acknowledgement number */
+    /* the sequence number of the last byte of the packet */
+    uint32_t seq_end;
+    uint8_t header_size;  /* the header length */
+    uint16_t payload_size; /* the payload length */
+    /* record the payload offset(the length that has been compared) */
+    uint16_t offset;
+    uint8_t flags; /* Flags(aka Control bits) */
 } Packet;
 
 typedef struct ConnectionKey {
@@ -XXX,XX +XXX,XX @@ typedef struct Connection {
     /* flag to enqueue unprocessed_connections */
     bool processing;
     uint8_t ip_proto;
+    /* record the sequence number that has been compared */
+    uint32_t compare_seq;
+    /* the maximum of acknowledgement number in primary_list queue */
+    uint32_t pack;
+    /* the maximum of acknowledgement number in secondary_list queue */
+    uint32_t sack;
     /* offset = secondary_seq - primary_seq */
     tcp_seq  offset;
     /*
diff --git a/net/trace-events b/net/trace-events
index XXXXXXX..XXXXXXX 100644
--- a/net/trace-events
+++ b/net/trace-events
@@ -XXX,XX +XXX,XX @@ colo_compare_icmp_miscompare(const char *sta, int size) ": %s = %d"
 colo_compare_ip_info(int psize, const char *sta, const char *stb, int ssize, const char *stc, const char *std) "ppkt size = %d, ip_src = %s, ip_dst = %s, spkt size = %d, ip_src = %s, ip_dst = %s"
 colo_old_packet_check_found(int64_t old_time) "%" PRId64
 colo_compare_miscompare(void) ""
-colo_compare_tcp_info(const char *pkt, uint32_t seq, uint32_t ack, int res, uint32_t flag, int size) "side: %s seq/ack= %u/%u res= %d flags= 0x%x pkt_size: %d\n"
+colo_compare_tcp_info(const char *pkt, uint32_t seq, uint32_t ack, int hdlen, int pdlen, int offset, int flags) "%s: seq/ack= %u/%u hdlen= %d pdlen= %d offset= %d flags=%d\n"
 
 # net/filter-rewriter.c
 colo_filter_rewriter_debug(void) ""
-- 
2.7.4

From: Thomas Huth <thuth@redhat.com>

QEMU can emulate hubs to connect NICs and netdevs. This is currently
primarily used for the mis-named 'vlan' feature of the networking
subsystem. Now the 'vlan' feature has been marked as deprecated, since
its name is rather confusing and the users often rather mis-configure
their network when trying to use it. But while the 'vlan' parameter
should be removed at one point in time, the basic idea of emulating
a hub in QEMU is still good: It's useful for bundling up the output of
multiple NICs into one single l2tp netdev for example.

Now to be able to use the hubport feature without 'vlan's, there is one
missing piece: The possibility to connect a hubport to a netdev, too.
This patch adds this possibility by introducing a new "netdev=..."
parameter to the hubports.

To bundle up the output of multiple NICs into one socket netdev, you can
now run QEMU with these parameters for example:

qemu-system-ppc64 ... -netdev socket,id=s1,connect=:11122 \
    -netdev hubport,hubid=1,id=h1,netdev=s1 \
    -netdev hubport,hubid=1,id=h2 -device e1000,netdev=h2 \
    -netdev hubport,hubid=1,id=h3 -device virtio-net-pci,netdev=h3

For using the socket netdev, you have got to start another QEMU as the
receiving side first, for example with network dumping enabled:

qemu-system-x86_64 -M isapc -netdev socket,id=s0,listen=:11122 \
    -device ne2k_isa,netdev=s0 \
    -object filter-dump,id=f1,netdev=s0,file=/tmp/dump.dat

After the ppc64 guest tried to boot from both NICs, you can see in the
dump file (using Wireshark, for example), that the output of both NICs
(the e1000 and the virtio-net-pci) has been successfully transfered
via the socket netdev in this case.

Suggested-by: Paolo Bonzini <pbonzini@redhat.com>
Signed-off-by: Thomas Huth <thuth@redhat.com>
Signed-off-by: Jason Wang <jasowang@redhat.com>
---
 net/hub.c       | 27 +++++++++++++++++++++------
 net/hub.h       |  3 ++-
 net/net.c       |  2 +-
 qapi/net.json   |  4 +++-
 qemu-options.hx |  8 +++++---
 5 files changed, 32 insertions(+), 12 deletions(-)

diff --git a/net/hub.c b/net/hub.c
index XXXXXXX..XXXXXXX 100644
--- a/net/hub.c
+++ b/net/hub.c
@@ -XXX,XX +XXX,XX @@
  */
 
 #include "qemu/osdep.h"
+#include "qapi/error.h"
 #include "monitor/monitor.h"
 #include "net/net.h"
 #include "clients.h"
@@ -XXX,XX +XXX,XX @@ static NetClientInfo net_hub_port_info = {
     .cleanup = net_hub_port_cleanup,
 };
 
-static NetHubPort *net_hub_port_new(NetHub *hub, const char *name)
+static NetHubPort *net_hub_port_new(NetHub *hub, const char *name,
+                                    NetClientState *hubpeer)
 {
     NetClientState *nc;
     NetHubPort *port;
@@ -XXX,XX +XXX,XX @@ static NetHubPort *net_hub_port_new(NetHub *hub, const char *name)
         name = default_name;
     }
 
-    nc = qemu_new_net_client(&net_hub_port_info, NULL, "hub", name);
+    nc = qemu_new_net_client(&net_hub_port_info, hubpeer, "hub", name);
     port = DO_UPCAST(NetHubPort, nc, nc);
     port->id = id;
     port->hub = hub;
@@ -XXX,XX +XXX,XX @@ static NetHubPort *net_hub_port_new(NetHub *hub, const char *name)
 
 /**
  * Create a port on a given hub
+ * @hub_id: Number of the hub
  * @name: Net client name or NULL for default name.
+ * @hubpeer: Peer to use (if "netdev=id" has been specified)
  *
  * If there is no existing hub with the given id then a new hub is created.
  */
-NetClientState *net_hub_add_port(int hub_id, const char *name)
+NetClientState *net_hub_add_port(int hub_id, const char *name,
+                                 NetClientState *hubpeer)
 {
     NetHub *hub;
     NetHubPort *port;
@@ -XXX,XX +XXX,XX @@ NetClientState *net_hub_add_port(int hub_id, const char *name)
         hub = net_hub_new(hub_id);
     }
 
-    port = net_hub_port_new(hub, name);
+    port = net_hub_port_new(hub, name, hubpeer);
     return &port->nc;
 }
 
@@ -XXX,XX +XXX,XX @@ NetClientState *net_hub_port_find(int hub_id)
         }
     }
 
-    nc = net_hub_add_port(hub_id, NULL);
+    nc = net_hub_add_port(hub_id, NULL, NULL);
     return nc;
 }
 
@@ -XXX,XX +XXX,XX @@ int net_init_hubport(const Netdev *netdev, const char *name,
                      NetClientState *peer, Error **errp)
 {
     const NetdevHubPortOptions *hubport;
+    NetClientState *hubpeer = NULL;
 
     assert(netdev->type == NET_CLIENT_DRIVER_HUBPORT);
     assert(!peer);
     hubport = &netdev->u.hubport;
 
-    net_hub_add_port(hubport->hubid, name);
+    if (hubport->has_netdev) {
+        hubpeer = qemu_find_netdev(hubport->netdev);
+        if (!hubpeer) {
+            error_setg(errp, "netdev '%s' not found", hubport->netdev);
+            return -1;
+        }
+    }
+
+    net_hub_add_port(hubport->hubid, name, hubpeer);
+
     return 0;
 }
 
diff --git a/net/hub.h b/net/hub.h
index XXXXXXX..XXXXXXX 100644
--- a/net/hub.h
+++ b/net/hub.h
@@ -XXX,XX +XXX,XX @@
 
 #include "qemu-common.h"
 
-NetClientState *net_hub_add_port(int hub_id, const char *name);
+NetClientState *net_hub_add_port(int hub_id, const char *name,
+                                 NetClientState *hubpeer);
 NetClientState *net_hub_find_client_by_name(int hub_id, const char *name);
 void net_hub_info(Monitor *mon);
 void net_hub_check_clients(void);
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 @@ static int net_client_init1(const void *object, bool is_netdev, Error **errp)
         /* Do not add to a vlan if it's a nic with a netdev= parameter. */
         if (netdev->type != NET_CLIENT_DRIVER_NIC ||
             !opts->u.nic.has_netdev) {
-            peer = net_hub_add_port(net->has_vlan ? net->vlan : 0, NULL);
+            peer = net_hub_add_port(net->has_vlan ? net->vlan : 0, NULL, NULL);
         }
 
         if (net->has_vlan && !vlan_warned) {
diff --git a/qapi/net.json b/qapi/net.json
index XXXXXXX..XXXXXXX 100644
--- a/qapi/net.json
+++ b/qapi/net.json
@@ -XXX,XX +XXX,XX @@
 # Connect two or more net clients through a software hub.
 #
 # @hubid: hub identifier number
+# @netdev: used to connect hub to a netdev instead of a device (since 2.12)
 #
 # Since: 1.2
 ##
 { 'struct': 'NetdevHubPortOptions',
   'data': {
-    'hubid':     'int32' } }
+    'hubid':     'int32',
+    '*netdev':    'str' } }
 
 ##
 # @NetdevNetmapOptions:
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 @@ DEF("netdev", HAS_ARG, QEMU_OPTION_netdev,
 #endif
     "-netdev vhost-user,id=str,chardev=dev[,vhostforce=on|off]\n"
     "                configure a vhost-user network, backed by a chardev 'dev'\n"
-    "-netdev hubport,id=str,hubid=n\n"
+    "-netdev hubport,id=str,hubid=n[,netdev=nd]\n"
     "                configure a hub port on QEMU VLAN 'n'\n", QEMU_ARCH_ALL)
 DEF("net", HAS_ARG, QEMU_OPTION_net,
     "-net nic[,vlan=n][,netdev=nd][,macaddr=mac][,model=type][,name=str][,addr=str][,vectors=v]\n"
@@ -XXX,XX +XXX,XX @@ vde_switch -F -sock /tmp/myswitch
 qemu-system-i386 linux.img -net nic -net vde,sock=/tmp/myswitch
 @end example
 
-@item -netdev hubport,id=@var{id},hubid=@var{hubid}
+@item -netdev hubport,id=@var{id},hubid=@var{hubid}[,netdev=@var{nd}]
 
 Create a hub port on QEMU "vlan" @var{hubid}.
 
 The hubport netdev lets you connect a NIC to a QEMU "vlan" instead of a single
 netdev.  @code{-net} and @code{-device} with parameter @option{vlan} create the
-required hub automatically.
+required hub automatically. Alternatively, you can also connect the hubport
+to another netdev with ID @var{nd} by using the @option{netdev=@var{nd}}
+option.
 
 @item -netdev vhost-user,chardev=@var{id}[,vhostforce=on|off][,queues=n]
 
-- 
2.7.4

From: Thomas Huth <thuth@redhat.com>

It does not make much sense to limit these commands to the legacy 'vlan'
concept only, they should work with the modern netdevs, too. So now
it is possible to use this command with one, two or three parameters.

With one parameter, the command installs a hostfwd rule on the default
"user" network:
    hostfwd_add tcp:...

With two parameters, the command installs a hostfwd rule on a netdev
(that's the new way of using this command):
    hostfwd_add netdev_id tcp:...

With three parameters, the command installs a rule on a 'vlan' (aka hub):
    hostfwd_add hub_id name tcp:...

Same applies to the hostfwd_remove command now.

Signed-off-by: Thomas Huth <thuth@redhat.com>
Signed-off-by: Jason Wang <jasowang@redhat.com>
---
 hmp-commands.hx |  4 ++--
 net/slirp.c     | 33 +++++++++++++++++++++++----------
 2 files changed, 25 insertions(+), 12 deletions(-)

diff --git a/hmp-commands.hx b/hmp-commands.hx
index XXXXXXX..XXXXXXX 100644
--- a/hmp-commands.hx
+++ b/hmp-commands.hx
@@ -XXX,XX +XXX,XX @@ ETEXI
     {
         .name       = "hostfwd_add",
         .args_type  = "arg1:s,arg2:s?,arg3:s?",
-        .params     = "[vlan_id name] [tcp|udp]:[hostaddr]:hostport-[guestaddr]:guestport",
+        .params     = "[hub_id name]|[netdev_id] [tcp|udp]:[hostaddr]:hostport-[guestaddr]:guestport",
         .help       = "redirect TCP or UDP connections from host to guest (requires -net user)",
         .cmd        = hmp_hostfwd_add,
     },
@@ -XXX,XX +XXX,XX @@ ETEXI
     {
         .name       = "hostfwd_remove",
         .args_type  = "arg1:s,arg2:s?,arg3:s?",
-        .params     = "[vlan_id name] [tcp|udp]:[hostaddr]:hostport",
+        .params     = "[hub_id name]|[netdev_id] [tcp|udp]:[hostaddr]:hostport",
         .help       = "remove host-to-guest TCP or UDP redirection",
         .cmd        = hmp_hostfwd_remove,
     },
diff --git a/net/slirp.c b/net/slirp.c
index XXXXXXX..XXXXXXX 100644
--- a/net/slirp.c
+++ b/net/slirp.c
@@ -XXX,XX +XXX,XX @@ error:
     return -1;
 }
 
-static SlirpState *slirp_lookup(Monitor *mon, const char *vlan,
-                                const char *stack)
+static SlirpState *slirp_lookup(Monitor *mon, const char *hub_id,
+                                const char *name)
 {
-
-    if (vlan) {
+    if (name) {
         NetClientState *nc;
-        nc = net_hub_find_client_by_name(strtol(vlan, NULL, 0), stack);
-        if (!nc) {
-            monitor_printf(mon, "unrecognized (vlan-id, stackname) pair\n");
-            return NULL;
+        if (hub_id) {
+            nc = net_hub_find_client_by_name(strtol(hub_id, NULL, 0), name);
+            if (!nc) {
+                monitor_printf(mon, "unrecognized (vlan-id, stackname) pair\n");
+                return NULL;
+            }
+        } else {
+            nc = qemu_find_netdev(name);
+            if (!nc) {
+                monitor_printf(mon, "unrecognized netdev id '%s'\n", name);
+                return NULL;
+            }
         }
         if (strcmp(nc->model, "user")) {
             monitor_printf(mon, "invalid device specified\n");
@@ -XXX,XX +XXX,XX @@ void hmp_hostfwd_remove(Monitor *mon, const QDict *qdict)
     const char *arg2 = qdict_get_try_str(qdict, "arg2");
     const char *arg3 = qdict_get_try_str(qdict, "arg3");
 
-    if (arg2) {
+    if (arg3) {
         s = slirp_lookup(mon, arg1, arg2);
         src_str = arg3;
+    } else if (arg2) {
+        s = slirp_lookup(mon, NULL, arg1);
+        src_str = arg2;
     } else {
         s = slirp_lookup(mon, NULL, NULL);
         src_str = arg1;
@@ -XXX,XX +XXX,XX @@ void hmp_hostfwd_add(Monitor *mon, const QDict *qdict)
     const char *arg2 = qdict_get_try_str(qdict, "arg2");
     const char *arg3 = qdict_get_try_str(qdict, "arg3");
 
-    if (arg2) {
+    if (arg3) {
         s = slirp_lookup(mon, arg1, arg2);
         redir_str = arg3;
+    } else if (arg2) {
+        s = slirp_lookup(mon, NULL, arg1);
+        redir_str = arg2;
     } else {
         s = slirp_lookup(mon, NULL, NULL);
         redir_str = arg1;
-- 
2.7.4

From: Philippe Mathieu-Daudé <f4bug@amsat.org>

gently asked by his automatic reply :)

Signed-off-by: Philippe Mathieu-Daudé <f4bug@amsat.org>
Signed-off-by: Jason Wang <jasowang@redhat.com>
---
 MAINTAINERS | 8 ++++----
 1 file changed, 4 insertions(+), 4 deletions(-)

diff --git a/MAINTAINERS b/MAINTAINERS
index XXXXXXX..XXXXXXX 100644
--- a/MAINTAINERS
+++ b/MAINTAINERS
@@ -XXX,XX +XXX,XX @@ F: hw/scsi/mfi.h
 F: tests/megasas-test.c
 
 Network packet abstractions
-M: Dmitry Fleytman <dmitry@daynix.com>
+M: Dmitry Fleytman <dmitry.fleytman@gmail.com>
 S: Maintained
 F: include/net/eth.h
 F: net/eth.c
@@ -XXX,XX +XXX,XX @@ F: hw/net/net_rx_pkt*
 F: hw/net/net_tx_pkt*
 
 Vmware
-M: Dmitry Fleytman <dmitry@daynix.com>
+M: Dmitry Fleytman <dmitry.fleytman@gmail.com>
 S: Maintained
 F: hw/net/vmxnet*
 F: hw/scsi/vmw_pvscsi*
@@ -XXX,XX +XXX,XX @@ F: hw/mem/nvdimm.c
 F: include/hw/mem/nvdimm.h
 
 e1000x
-M: Dmitry Fleytman <dmitry@daynix.com>
+M: Dmitry Fleytman <dmitry.fleytman@gmail.com>
 S: Maintained
 F: hw/net/e1000x*
 
 e1000e
-M: Dmitry Fleytman <dmitry@daynix.com>
+M: Dmitry Fleytman <dmitry.fleytman@gmail.com>
 S: Maintained
 F: hw/net/e1000e*
 
-- 
2.7.4

The following changes since commit 136c67e07869227b21b3f627316e03679ce7b738:

Merge remote-tracking branch 'remotes/bkoppelmann/tags/pull-tricore-2018-03-02' into staging (2018-03-02 16:56:20 +0000)

are available in the git repository at:

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

for you to fetch changes up to 46d4d36d0bf2b24b205f2f604f0905db80264eef:

tap: setting error appropriately when calling net_init_tap_one() (2018-03-05 10:30:16 +0800)

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

----------------------------------------------------------------
Jay Zhou (1):
      tap: setting error appropriately when calling net_init_tap_one()

Thomas Huth (8):
      net: Move error reporting from net_init_client/netdev to the calling site
      net: List available netdevs with "-netdev help"
      net: Only show vhost-user in the help text if CONFIG_POSIX is defined
      net: Make net_client_init() static
      net: Remove the deprecated way of dumping network packets
      net: Remove the deprecated 'host_net_add' and 'host_net_remove' HMP commands
      net: Add a new convenience option "--nic" to configure default/on-board NICs
      hw/net: Remove unnecessary header includes

From: Thomas Huth <thuth@redhat.com>

It looks strange that net_init_client() and net_init_netdev() both
take an "Error **errp" parameter, but then do the error reporting
with "error_report_err(local_err)" on their own. Let's move the
error reporting to the calling site instead to simplify this code
a little bit.

Reviewed-by: Eric Blake <eblake@redhat.com>
Reviewed-by: Paolo Bonzini <pbonzini@redhat.com>
Signed-off-by: Thomas Huth <thuth@redhat.com>
Signed-off-by: Jason Wang <jasowang@redhat.com>
---
 include/net/net.h |  2 +-
 net/net.c         | 29 +++++------------------------
 vl.c              |  3 ++-
 3 files changed, 8 insertions(+), 26 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 @@ extern const char *legacy_bootp_filename;
 
 int net_client_init(QemuOpts *opts, bool is_netdev, Error **errp);
 int net_client_parse(QemuOptsList *opts_list, const char *str);
-int net_init_clients(void);
+int net_init_clients(Error **errp);
 void net_check_clients(void);
 void net_cleanup(void);
 void hmp_host_net_add(Monitor *mon, const QDict *qdict);
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 net_check_clients(void)
 
 static int net_init_client(void *dummy, QemuOpts *opts, Error **errp)
 {
-    Error *local_err = NULL;
-
-    net_client_init(opts, false, &local_err);
-    if (local_err) {
-        error_report_err(local_err);
-        return -1;
-    }
-
-    return 0;
+    return net_client_init(opts, false, errp);
 }
 
 static int net_init_netdev(void *dummy, QemuOpts *opts, Error **errp)
 {
-    Error *local_err = NULL;
-    int ret;
-
-    ret = net_client_init(opts, true, &local_err);
-    if (local_err) {
-        error_report_err(local_err);
-        return -1;
-    }
-
-    return ret;
+    return net_client_init(opts, true, errp);
 }
 
-int net_init_clients(void)
+int net_init_clients(Error **errp)
 {
-    QemuOptsList *net = qemu_find_opts("net");
-
     net_change_state_entry =
         qemu_add_vm_change_state_handler(net_vm_change_state_handler, NULL);
 
     QTAILQ_INIT(&net_clients);
 
     if (qemu_opts_foreach(qemu_find_opts("netdev"),
-                          net_init_netdev, NULL, NULL)) {
+                          net_init_netdev, NULL, errp)) {
         return -1;
     }
 
-    if (qemu_opts_foreach(net, net_init_client, NULL, NULL)) {
+    if (qemu_opts_foreach(qemu_find_opts("net"), net_init_client, NULL, errp)) {
         return -1;
     }
 
diff --git a/vl.c b/vl.c
index XXXXXXX..XXXXXXX 100644
--- a/vl.c
+++ b/vl.c
@@ -XXX,XX +XXX,XX @@ int main(int argc, char **argv, char **envp)
 
     colo_info_init();
 
-    if (net_init_clients() < 0) {
+    if (net_init_clients(&err) < 0) {
+        error_report_err(err);
         exit(1);
     }
 
-- 
2.7.4

From: Thomas Huth <thuth@redhat.com>

Other options like "-chardev" or "-device" feature a nice help text
with the available devices when being called with "help" or "?".
Since it is quite useful, especially if you want to see which network
backends have been compiled into the QEMU binary, let's provide such
a help text for "-netdev", too.

Reviewed-by: Paolo Bonzini <pbonzini@redhat.com>
Reviewed-by: Eric Blake <eblake@redhat.com>
Signed-off-by: Thomas Huth <thuth@redhat.com>
Signed-off-by: Jason Wang <jasowang@redhat.com>
---
 net/net.c | 37 ++++++++++++++++++++++++++++++++++++-
 1 file changed, 36 insertions(+), 1 deletion(-)

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 @@ static int net_client_init1(const void *object, bool is_netdev, Error **errp)
     return 0;
 }
 
+static void show_netdevs(void)
+{
+    int idx;
+    const char *available_netdevs[] = {
+        "socket",
+        "hubport",
+        "tap",
+#ifdef CONFIG_SLIRP
+        "user",
+#endif
+#ifdef CONFIG_L2TPV3
+        "l2tpv3",
+#endif
+#ifdef CONFIG_VDE
+        "vde",
+#endif
+#ifdef CONFIG_NET_BRIDGE
+        "bridge",
+#endif
+#ifdef CONFIG_NETMAP
+        "netmap",
+#endif
+#ifdef CONFIG_POSIX
+        "vhost-user",
+#endif
+    };
+
+    printf("Available netdev backend types:\n");
+    for (idx = 0; idx < ARRAY_SIZE(available_netdevs); idx++) {
+        puts(available_netdevs[idx]);
+    }
+}
 
 int net_client_init(QemuOpts *opts, bool is_netdev, Error **errp)
 {
@@ -XXX,XX +XXX,XX @@ int net_client_init(QemuOpts *opts, bool is_netdev, Error **errp)
     int ret = -1;
     Visitor *v = opts_visitor_new(opts);
 
-    {
+    if (is_netdev && is_help_option(qemu_opt_get(opts, "type"))) {
+        show_netdevs();
+        exit(0);
+    } else {
         /* Parse convenience option format ip6-net=fec0::0[/64] */
         const char *ip6_net = qemu_opt_get(opts, "ipv6-net");
 
-- 
2.7.4

From: Thomas Huth <thuth@redhat.com>

According to net/Makefile.objs we only link in the vhost-user code
if CONFIG_POSIX has been set. So the help screen should also only
show this information if CONFIG_POSIX has been defined.

Reviewed-by: Paolo Bonzini <pbonzini@redhat.com>
Signed-off-by: Thomas Huth <thuth@redhat.com>
Signed-off-by: Jason Wang <jasowang@redhat.com>
---
 qemu-options.hx | 2 ++
 1 file changed, 2 insertions(+)

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 @@ DEF("netdev", HAS_ARG, QEMU_OPTION_netdev,
     "                VALE port (created on the fly) called 'name' ('nmname' is name of the \n"
     "                netmap device, defaults to '/dev/netmap')\n"
 #endif
+#ifdef CONFIG_POSIX
     "-netdev vhost-user,id=str,chardev=dev[,vhostforce=on|off]\n"
     "                configure a vhost-user network, backed by a chardev 'dev'\n"
+#endif
     "-netdev hubport,id=str,hubid=n[,netdev=nd]\n"
     "                configure a hub port on QEMU VLAN 'n'\n", QEMU_ARCH_ALL)
 DEF("net", HAS_ARG, QEMU_OPTION_net,
-- 
2.7.4

From: Thomas Huth <thuth@redhat.com>

The function is only used within net.c, so there's no need that
this is a global function.

While we're at it, also remove the unused prototype compute_mcast_idx()
(the function has been removed in commit d9caeb09b107e91122d10ba4a08a).

Reviewed-by: Paolo Bonzini <pbonzini@redhat.com>
Signed-off-by: Thomas Huth <thuth@redhat.com>
Signed-off-by: Jason Wang <jasowang@redhat.com>
---
 include/net/net.h | 2 --
 net/net.c         | 2 +-
 2 files changed, 1 insertion(+), 3 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 @@ extern const char *host_net_devices[];
 extern const char *legacy_tftp_prefix;
 extern const char *legacy_bootp_filename;
 
-int net_client_init(QemuOpts *opts, bool is_netdev, Error **errp);
 int net_client_parse(QemuOptsList *opts_list, const char *str);
 int net_init_clients(Error **errp);
 void net_check_clients(void);
@@ -XXX,XX +XXX,XX @@ void qdev_set_nic_properties(DeviceState *dev, NICInfo *nd);
 #define POLYNOMIAL_LE 0xedb88320
 uint32_t net_crc32(const uint8_t *p, int len);
 uint32_t net_crc32_le(const uint8_t *p, int len);
-unsigned compute_mcast_idx(const uint8_t *ep);
 
 #define vmstate_offset_macaddr(_state, _field)                       \
     vmstate_offset_array(_state, _field.a, uint8_t,                \
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 @@ static void show_netdevs(void)
     }
 }
 
-int net_client_init(QemuOpts *opts, bool is_netdev, Error **errp)
+static int net_client_init(QemuOpts *opts, bool is_netdev, Error **errp)
 {
     void *object = NULL;
     Error *err = NULL;
-- 
2.7.4

From: Thomas Huth <thuth@redhat.com>

"-net dump" has been marked as deprecated since QEMU v2.10, since it
only works with the deprecated 'vlan' parameter (or hubs). Network
dumping should be done with "-object filter-dump" nowadays instead.
Since nobody complained so far about the deprecation message, let's
finally get rid of "-net dump" now.

Signed-off-by: Thomas Huth <thuth@redhat.com>
Signed-off-by: Jason Wang <jasowang@redhat.com>
---
 net/dump.c      | 102 ++------------------------------------------------------
 net/net.c       |   9 +----
 qapi/net.json   |  29 ++++------------
 qemu-doc.texi   |   6 ----
 qemu-options.hx |   8 -----
 5 files changed, 9 insertions(+), 145 deletions(-)

diff --git a/net/dump.c b/net/dump.c
index XXXXXXX..XXXXXXX 100644
--- a/net/dump.c
+++ b/net/dump.c
@@ -XXX,XX +XXX,XX @@ static int net_dump_state_init(DumpState *s, const char *filename,
 
     fd = open(filename, O_CREAT | O_TRUNC | O_WRONLY | O_BINARY, 0644);
     if (fd < 0) {
-        error_setg_errno(errp, errno, "-net dump: can't open %s", filename);
+        error_setg_errno(errp, errno, "net dump: can't open %s", filename);
         return -1;
     }
 
@@ -XXX,XX +XXX,XX @@ static int net_dump_state_init(DumpState *s, const char *filename,
     hdr.linktype = 1;
 
     if (write(fd, &hdr, sizeof(hdr)) < sizeof(hdr)) {
-        error_setg_errno(errp, errno, "-net dump write error");
+        error_setg_errno(errp, errno, "net dump write error");
         close(fd);
         return -1;
     }
@@ -XXX,XX +XXX,XX @@ static int net_dump_state_init(DumpState *s, const char *filename,
     return 0;
 }
 
-/* Dumping via VLAN netclient */
-
-struct DumpNetClient {
-    NetClientState nc;
-    DumpState ds;
-};
-typedef struct DumpNetClient DumpNetClient;
-
-static ssize_t dumpclient_receive(NetClientState *nc, const uint8_t *buf,
-                                  size_t size)
-{
-    DumpNetClient *dc = DO_UPCAST(DumpNetClient, nc, nc);
-    struct iovec iov = {
-        .iov_base = (void *)buf,
-        .iov_len = size
-    };
-
-    return dump_receive_iov(&dc->ds, &iov, 1);
-}
-
-static ssize_t dumpclient_receive_iov(NetClientState *nc,
-                                      const struct iovec *iov, int cnt)
-{
-    DumpNetClient *dc = DO_UPCAST(DumpNetClient, nc, nc);
-
-    return dump_receive_iov(&dc->ds, iov, cnt);
-}
-
-static void dumpclient_cleanup(NetClientState *nc)
-{
-    DumpNetClient *dc = DO_UPCAST(DumpNetClient, nc, nc);
-
-    dump_cleanup(&dc->ds);
-}
-
-static NetClientInfo net_dump_info = {
-    .type = NET_CLIENT_DRIVER_DUMP,
-    .size = sizeof(DumpNetClient),
-    .receive = dumpclient_receive,
-    .receive_iov = dumpclient_receive_iov,
-    .cleanup = dumpclient_cleanup,
-};
-
-int net_init_dump(const Netdev *netdev, const char *name,
-                  NetClientState *peer, Error **errp)
-{
-    int len, rc;
-    const char *file;
-    char def_file[128];
-    const NetdevDumpOptions *dump;
-    NetClientState *nc;
-    DumpNetClient *dnc;
-
-    assert(netdev->type == NET_CLIENT_DRIVER_DUMP);
-    dump = &netdev->u.dump;
-
-    assert(peer);
-
-    error_report("'-net dump' is deprecated. "
-                 "Please use '-object filter-dump' instead.");
-
-    if (dump->has_file) {
-        file = dump->file;
-    } else {
-        int id;
-        int ret;
-
-        ret = net_hub_id_for_client(peer, &id);
-        assert(ret == 0); /* peer must be on a hub */
-
-        snprintf(def_file, sizeof(def_file), "qemu-vlan%d.pcap", id);
-        file = def_file;
-    }
-
-    if (dump->has_len) {
-        if (dump->len > INT_MAX) {
-            error_setg(errp, "invalid length: %"PRIu64, dump->len);
-            return -1;
-        }
-        len = dump->len;
-    } else {
-        len = 65536;
-    }
-
-    nc = qemu_new_net_client(&net_dump_info, peer, "dump", name);
-    snprintf(nc->info_str, sizeof(nc->info_str),
-             "dump to %s (len=%d)", file, len);
-
-    dnc = DO_UPCAST(DumpNetClient, nc, nc);
-    rc = net_dump_state_init(&dnc->ds, file, len, errp);
-    if (rc) {
-        qemu_del_net_client(nc);
-    }
-    return rc;
-}
-
-/* Dumping via filter */
-
 #define TYPE_FILTER_DUMP "filter-dump"
 
 #define FILTER_DUMP(obj) \
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 @@ static QTAILQ_HEAD(, NetClientState) net_clients;
 const char *host_net_devices[] = {
     "tap",
     "socket",
-    "dump",
 #ifdef CONFIG_NET_BRIDGE
     "bridge",
 #endif
@@ -XXX,XX +XXX,XX @@ static int (* const net_client_init_fun[NET_CLIENT_DRIVER__MAX])(
 #ifdef CONFIG_NETMAP
         [NET_CLIENT_DRIVER_NETMAP]    = net_init_netmap,
 #endif
-        [NET_CLIENT_DRIVER_DUMP]      = net_init_dump,
 #ifdef CONFIG_NET_BRIDGE
         [NET_CLIENT_DRIVER_BRIDGE]    = net_init_bridge,
 #endif
@@ -XXX,XX +XXX,XX @@ static int net_client_init1(const void *object, bool is_netdev, Error **errp)
         netdev = object;
         name = netdev->id;
 
-        if (netdev->type == NET_CLIENT_DRIVER_DUMP ||
-            netdev->type == NET_CLIENT_DRIVER_NIC ||
+        if (netdev->type == NET_CLIENT_DRIVER_NIC ||
             !net_client_init_fun[netdev->type]) {
             error_setg(errp, QERR_INVALID_PARAMETER_VALUE, "type",
                        "a netdev backend type");
@@ -XXX,XX +XXX,XX @@ static int net_client_init1(const void *object, bool is_netdev, Error **errp)
             legacy.type = NET_CLIENT_DRIVER_VDE;
             legacy.u.vde = opts->u.vde;
             break;
-        case NET_LEGACY_OPTIONS_TYPE_DUMP:
-            legacy.type = NET_CLIENT_DRIVER_DUMP;
-            legacy.u.dump = opts->u.dump;
-            break;
         case NET_LEGACY_OPTIONS_TYPE_BRIDGE:
             legacy.type = NET_CLIENT_DRIVER_BRIDGE;
             legacy.u.bridge = opts->u.bridge;
diff --git a/qapi/net.json b/qapi/net.json
index XXXXXXX..XXXXXXX 100644
--- a/qapi/net.json
+++ b/qapi/net.json
@@ -XXX,XX +XXX,XX @@
 #
 # Add a network backend.
 #
-# @type: the type of network backend.  Current valid values are 'user', 'tap',
-#        'vde', 'socket', 'dump' and 'bridge'
+# @type: the type of network backend. Possible values are listed in
+#        NetClientDriver (excluding 'none' and 'nic')
 #
 # @id: the name of the new network backend
 #
@@ -XXX,XX +XXX,XX @@
     '*mode':  'uint16' } }
 
 ##
-# @NetdevDumpOptions:
-#
-# Dump VLAN network traffic to a file.
-#
-# @len: per-packet size limit (64k default). Understands [TGMKkb]
-# suffixes.
-#
-# @file: dump file path (default is qemu-vlan0.pcap)
-#
-# Since: 1.2
-##
-{ 'struct': 'NetdevDumpOptions',
-  'data': {
-    '*len':  'size',
-    '*file': 'str' } }
-
-##
 # @NetdevBridgeOptions:
 #
 # Connect a host TAP network interface to a host bridge device.
@@ -XXX,XX +XXX,XX @@
 # Available netdev drivers.
 #
 # Since: 2.7
+#
+# 'dump' - removed with 2.12
 ##
 { 'enum': 'NetClientDriver',
-  'data': [ 'none', 'nic', 'user', 'tap', 'l2tpv3', 'socket', 'vde', 'dump',
+  'data': [ 'none', 'nic', 'user', 'tap', 'l2tpv3', 'socket', 'vde',
             'bridge', 'hubport', 'netmap', 'vhost-user' ] }
 
 ##
@@ -XXX,XX +XXX,XX @@
     'l2tpv3':   'NetdevL2TPv3Options',
     'socket':   'NetdevSocketOptions',
     'vde':      'NetdevVdeOptions',
-    'dump':     'NetdevDumpOptions',
     'bridge':   'NetdevBridgeOptions',
     'hubport':  'NetdevHubPortOptions',
     'netmap':   'NetdevNetmapOptions',
@@ -XXX,XX +XXX,XX @@
 ##
 { 'enum': 'NetLegacyOptionsType',
   'data': ['none', 'nic', 'user', 'tap', 'l2tpv3', 'socket', 'vde',
-           'dump', 'bridge', 'netmap', 'vhost-user'] }
+           'bridge', 'netmap', 'vhost-user'] }
 
 ##
 # @NetLegacyOptions:
@@ -XXX,XX +XXX,XX @@
     'l2tpv3':   'NetdevL2TPv3Options',
     'socket':   'NetdevSocketOptions',
     'vde':      'NetdevVdeOptions',
-    'dump':     'NetdevDumpOptions',
     'bridge':   'NetdevBridgeOptions',
     'netmap':   'NetdevNetmapOptions',
     'vhost-user': 'NetdevVhostUserOptions' } }
diff --git a/qemu-doc.texi b/qemu-doc.texi
index XXXXXXX..XXXXXXX 100644
--- a/qemu-doc.texi
+++ b/qemu-doc.texi
@@ -XXX,XX +XXX,XX @@ that can be specified with the ``-device'' parameter.
 The drive addr argument is replaced by the the addr argument
 that can be specified with the ``-device'' parameter.
 
-@subsection -net dump (since 2.10.0)
-
-The ``--net dump'' argument is now replaced with the
-``-object filter-dump'' argument which works in combination
-with the modern ``-netdev`` backends instead.
-
 @subsection -usbdevice (since 2.10.0)
 
 The ``-usbdevice DEV'' argument is now a synonym for setting
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 @@ DEF("net", HAS_ARG, QEMU_OPTION_net,
     "                configure or create an on-board (or machine default) NIC and\n"
     "                connect it either to VLAN 'n' or the netdev 'nd' (for pluggable\n"
     "                NICs please use '-device devtype,netdev=nd' instead)\n"
-    "-net dump[,vlan=n][,file=f][,len=n]\n"
-    "                dump traffic on vlan 'n' to file 'f' (max n bytes per packet)\n"
     "-net none       use it alone to have zero network devices. If no -net option\n"
     "                is provided, the default is '-net nic -net user'\n"
     "-net ["
@@ -XXX,XX +XXX,XX @@ qemu -m 512 -object memory-backend-file,id=mem,size=512M,mem-path=/hugetlbfs,sha
      -device virtio-net-pci,netdev=net0
 @end example
 
-@item -net dump[,vlan=@var{n}][,file=@var{file}][,len=@var{len}]
-Dump network traffic on VLAN @var{n} to file @var{file} (@file{qemu-vlan0.pcap} by default).
-At most @var{len} bytes (64k by default) per packet are stored. The file format is
-libpcap, so it can be analyzed with tools such as tcpdump or Wireshark.
-Note: For devices created with '-netdev', use '-object filter-dump,...' instead.
-
 @item -net none
 Indicate that no network devices should be configured. It is used to
 override the default configuration (@option{-net nic -net user}) which
-- 
2.7.4

From: Thomas Huth <thuth@redhat.com>

They are deprecated since QEMU v2.10, and so far nobody complained that
these commands are still necessary for any reason - and since you can use
'netdev_add' and 'netdev_remove' instead, there also should not be any
real reason. Since they are also standing in the way for the upcoming
'vlan' clean-up, it's now time to remove them.

Reviewed-by: Paolo Bonzini <pbonzini@redhat.com>
Signed-off-by: Thomas Huth <thuth@redhat.com>
Signed-off-by: Jason Wang <jasowang@redhat.com>
---
 hmp-commands.hx  | 30 ------------------
 hmp.h            |  3 --
 monitor.c        | 61 ------------------------------------
 net/net.c        | 94 --------------------------------------------------------
 qemu-doc.texi    | 10 ------
 tests/test-hmp.c |  2 --
 6 files changed, 200 deletions(-)

diff --git a/hmp-commands.hx b/hmp-commands.hx
index XXXXXXX..XXXXXXX 100644
--- a/hmp-commands.hx
+++ b/hmp-commands.hx
@@ -XXX,XX +XXX,XX @@ Inject PCIe AER error
 ETEXI
 
     {
-        .name       = "host_net_add",
-        .args_type  = "device:s,opts:s?",
-        .params     = "tap|user|socket|vde|netmap|bridge|vhost-user|dump [options]",
-        .help       = "add host VLAN client (deprecated, use netdev_add instead)",
-        .cmd        = hmp_host_net_add,
-        .command_completion = host_net_add_completion,
-    },
-
-STEXI
-@item host_net_add
-@findex host_net_add
-Add host VLAN client. Deprecated, please use @code{netdev_add} instead.
-ETEXI
-
-    {
-        .name       = "host_net_remove",
-        .args_type  = "vlan_id:i,device:s",
-        .params     = "vlan_id name",
-        .help       = "remove host VLAN client (deprecated, use netdev_del instead)",
-        .cmd        = hmp_host_net_remove,
-        .command_completion = host_net_remove_completion,
-    },
-
-STEXI
-@item host_net_remove
-@findex host_net_remove
-Remove host VLAN client. Deprecated, please use @code{netdev_del} instead.
-ETEXI
-
-    {
         .name       = "netdev_add",
         .args_type  = "netdev:O",
         .params     = "[user|tap|socket|vde|bridge|hubport|netmap|vhost-user],id=str[,prop=value][,...]",
diff --git a/hmp.h b/hmp.h
index XXXXXXX..XXXXXXX 100644
--- a/hmp.h
+++ b/hmp.h
@@ -XXX,XX +XXX,XX @@ void migrate_set_capability_completion(ReadLineState *rs, int nb_args,
                                        const char *str);
 void migrate_set_parameter_completion(ReadLineState *rs, int nb_args,
                                       const char *str);
-void host_net_add_completion(ReadLineState *rs, int nb_args, const char *str);
-void host_net_remove_completion(ReadLineState *rs, int nb_args,
-                                const char *str);
 void delvm_completion(ReadLineState *rs, int nb_args, const char *str);
 void loadvm_completion(ReadLineState *rs, int nb_args, const char *str);
 void hmp_rocker(Monitor *mon, const QDict *qdict);
diff --git a/monitor.c b/monitor.c
index XXXXXXX..XXXXXXX 100644
--- a/monitor.c
+++ b/monitor.c
@@ -XXX,XX +XXX,XX @@ void migrate_set_parameter_completion(ReadLineState *rs, int nb_args,
     }
 }
 
-void host_net_add_completion(ReadLineState *rs, int nb_args, const char *str)
-{
-    int i;
-    size_t len;
-    if (nb_args != 2) {
-        return;
-    }
-    len = strlen(str);
-    readline_set_completion_index(rs, len);
-    for (i = 0; host_net_devices[i]; i++) {
-        if (!strncmp(host_net_devices[i], str, len)) {
-            readline_add_completion(rs, host_net_devices[i]);
-        }
-    }
-}
-
-void host_net_remove_completion(ReadLineState *rs, int nb_args, const char *str)
-{
-    NetClientState *ncs[MAX_QUEUE_NUM];
-    int count, i, len;
-
-    len = strlen(str);
-    readline_set_completion_index(rs, len);
-    if (nb_args == 2) {
-        count = qemu_find_net_clients_except(NULL, ncs,
-                                             NET_CLIENT_DRIVER_NONE,
-                                             MAX_QUEUE_NUM);
-        for (i = 0; i < MIN(count, MAX_QUEUE_NUM); i++) {
-            int id;
-            char name[16];
-
-            if (net_hub_id_for_client(ncs[i], &id)) {
-                continue;
-            }
-            snprintf(name, sizeof(name), "%d", id);
-            if (!strncmp(str, name, len)) {
-                readline_add_completion(rs, name);
-            }
-        }
-        return;
-    } else if (nb_args == 3) {
-        count = qemu_find_net_clients_except(NULL, ncs,
-                                             NET_CLIENT_DRIVER_NIC,
-                                             MAX_QUEUE_NUM);
-        for (i = 0; i < MIN(count, MAX_QUEUE_NUM); i++) {
-            int id;
-            const char *name;
-
-            if (ncs[i]->info->type == NET_CLIENT_DRIVER_HUBPORT ||
-                net_hub_id_for_client(ncs[i], &id)) {
-                continue;
-            }
-            name = ncs[i]->name;
-            if (!strncmp(str, name, len)) {
-                readline_add_completion(rs, name);
-            }
-        }
-        return;
-    }
-}
-
 static void vm_completion(ReadLineState *rs, const char *str)
 {
     size_t len;
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 @@
 static VMChangeStateEntry *net_change_state_entry;
 static QTAILQ_HEAD(, NetClientState) net_clients;
 
-const char *host_net_devices[] = {
-    "tap",
-    "socket",
-#ifdef CONFIG_NET_BRIDGE
-    "bridge",
-#endif
-#ifdef CONFIG_NETMAP
-    "netmap",
-#endif
-#ifdef CONFIG_SLIRP
-    "user",
-#endif
-#ifdef CONFIG_VDE
-    "vde",
-#endif
-    "vhost-user",
-    NULL,
-};
-
 /***********************************************************/
 /* network device redirectors */
 
@@ -XXX,XX +XXX,XX @@ static int net_client_init(QemuOpts *opts, bool is_netdev, Error **errp)
     return ret;
 }
 
-
-static int net_host_check_device(const char *device)
-{
-    int i;
-    for (i = 0; host_net_devices[i]; i++) {
-        if (!strncmp(host_net_devices[i], device,
-                     strlen(host_net_devices[i]))) {
-            return 1;
-        }
-    }
-
-    return 0;
-}
-
-void hmp_host_net_add(Monitor *mon, const QDict *qdict)
-{
-    const char *device = qdict_get_str(qdict, "device");
-    const char *opts_str = qdict_get_try_str(qdict, "opts");
-    Error *local_err = NULL;
-    QemuOpts *opts;
-    static bool warned;
-
-    if (!warned && !qtest_enabled()) {
-        error_report("host_net_add is deprecated, use netdev_add instead");
-        warned = true;
-    }
-
-    if (!net_host_check_device(device)) {
-        monitor_printf(mon, "invalid host network device %s\n", device);
-        return;
-    }
-
-    opts = qemu_opts_parse_noisily(qemu_find_opts("net"),
-                                   opts_str ? opts_str : "", false);
-    if (!opts) {
-        return;
-    }
-
-    qemu_opt_set(opts, "type", device, &error_abort);
-
-    net_client_init(opts, false, &local_err);
-    if (local_err) {
-        error_report_err(local_err);
-        monitor_printf(mon, "adding host network device %s failed\n", device);
-    }
-}
-
-void hmp_host_net_remove(Monitor *mon, const QDict *qdict)
-{
-    NetClientState *nc;
-    int vlan_id = qdict_get_int(qdict, "vlan_id");
-    const char *device = qdict_get_str(qdict, "device");
-    static bool warned;
-
-    if (!warned && !qtest_enabled()) {
-        error_report("host_net_remove is deprecated, use netdev_del instead");
-        warned = true;
-    }
-
-    nc = net_hub_find_client_by_name(vlan_id, device);
-    if (!nc) {
-        error_report("Host network device '%s' on hub '%d' not found",
-                     device, vlan_id);
-        return;
-    }
-    if (nc->info->type == NET_CLIENT_DRIVER_NIC) {
-        error_report("invalid host network device '%s'", device);
-        return;
-    }
-
-    qemu_del_net_client(nc->peer);
-    qemu_del_net_client(nc);
-    qemu_opts_del(qemu_opts_find(qemu_find_opts("net"), device));
-}
-
 void netdev_add(QemuOpts *opts, Error **errp)
 {
     net_client_init(opts, true, errp);
diff --git a/qemu-doc.texi b/qemu-doc.texi
index XXXXXXX..XXXXXXX 100644
--- a/qemu-doc.texi
+++ b/qemu-doc.texi
@@ -XXX,XX +XXX,XX @@ from qcow2 images.
 
 The ``query-cpus'' command is replaced by the ``query-cpus-fast'' command.
 
-@section System emulator human monitor commands
-
-@subsection host_net_add (since 2.10.0)
-
-The ``host_net_add'' command is replaced by the ``netdev_add'' command.
-
-@subsection host_net_remove (since 2.10.0)
-
-The ``host_net_remove'' command is replaced by the ``netdev_del'' command.
-
 @section System emulator devices
 
 @subsection ivshmem (since 2.6.0)
diff --git a/tests/test-hmp.c b/tests/test-hmp.c
index XXXXXXX..XXXXXXX 100644
--- a/tests/test-hmp.c
+++ b/tests/test-hmp.c
@@ -XXX,XX +XXX,XX @@ static const char *hmp_cmds[] = {
     "dump-guest-memory /dev/null 0 4096",
     "dump-guest-memory /dev/null",
     "gdbserver",
-    "host_net_add user id=net0",
     "hostfwd_add tcp::43210-:43210",
     "hostfwd_remove tcp::43210-:43210",
-    "host_net_remove 0 net0",
     "i /w 0",
     "log all",
     "log none",
-- 
2.7.4

From: Thomas Huth <thuth@redhat.com>

The legacy "-net" option can be quite confusing for the users since most
people do not expect to get a "vlan" hub between their emulated guest
hardware and the host backend. But so far, we are also not able to get
rid of "-net" completely, since it is the only way to configure on-board
NICs that can not be instantiated via "-device" yet. It's also a little
bit shorter to type "-net nic -net tap" instead of "-device xyz,netdev=n1
-netdev tap,id=n1".

So what we need is a new convenience option that is shorter to type than
the full -device + -netdev stuff, and which can be used to configure the
on-board NICs that can not be handled via -device yet. Thus this patch now
provides such a new option "--nic": It adds an entry in the nd_table to
configure a on-board / default NIC, creates a host backend and connects
the two directly, without a confusing "vlan" hub inbetween.

Reviewed-by: Paolo Bonzini <pbonzini@redhat.com>
Signed-off-by: Thomas Huth <thuth@redhat.com>
Signed-off-by: Jason Wang <jasowang@redhat.com>
---
 include/sysemu/sysemu.h |  1 +
 net/net.c               | 78 +++++++++++++++++++++++++++++++++++++++++++++++++
 qemu-options.hx         | 40 +++++++++++++++++++++----
 vl.c                    |  7 +++++
 4 files changed, 120 insertions(+), 6 deletions(-)

diff --git a/include/sysemu/sysemu.h b/include/sysemu/sysemu.h
index XXXXXXX..XXXXXXX 100644
--- a/include/sysemu/sysemu.h
+++ b/include/sysemu/sysemu.h
@@ -XXX,XX +XXX,XX @@ extern QemuOptsList bdrv_runtime_opts;
 extern QemuOptsList qemu_chardev_opts;
 extern QemuOptsList qemu_device_opts;
 extern QemuOptsList qemu_netdev_opts;
+extern QemuOptsList qemu_nic_opts;
 extern QemuOptsList qemu_net_opts;
 extern QemuOptsList qemu_global_opts;
 extern QemuOptsList qemu_mon_opts;
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 @@ static int net_init_netdev(void *dummy, QemuOpts *opts, Error **errp)
     return net_client_init(opts, true, errp);
 }
 
+/* For the convenience "--nic" parameter */
+static int net_param_nic(void *dummy, QemuOpts *opts, Error **errp)
+{
+    char *mac, *nd_id;
+    int idx, ret;
+    NICInfo *ni;
+    const char *type;
+
+    type = qemu_opt_get(opts, "type");
+    if (type && g_str_equal(type, "none")) {
+        return 0;    /* Nothing to do, default_net is cleared in vl.c */
+    }
+
+    idx = nic_get_free_idx();
+    if (idx == -1 || nb_nics >= MAX_NICS) {
+        error_setg(errp, "no more on-board/default NIC slots available");
+        return -1;
+    }
+
+    if (!type) {
+        qemu_opt_set(opts, "type", "user", &error_abort);
+    }
+
+    ni = &nd_table[idx];
+    memset(ni, 0, sizeof(*ni));
+    ni->model = qemu_opt_get_del(opts, "model");
+
+    /* Create an ID if the user did not specify one */
+    nd_id = g_strdup(qemu_opts_id(opts));
+    if (!nd_id) {
+        nd_id = g_strdup_printf("__org.qemu.nic%i\n", idx);
+        qemu_opts_set_id(opts, nd_id);
+    }
+
+    /* Handle MAC address */
+    mac = qemu_opt_get_del(opts, "mac");
+    if (mac) {
+        ret = net_parse_macaddr(ni->macaddr.a, mac);
+        g_free(mac);
+        if (ret) {
+            error_setg(errp, "invalid syntax for ethernet address");
+            return -1;
+        }
+        if (is_multicast_ether_addr(ni->macaddr.a)) {
+            error_setg(errp, "NIC cannot have multicast MAC address");
+            return -1;
+        }
+    }
+    qemu_macaddr_default_if_unset(&ni->macaddr);
+
+    ret = net_client_init(opts, true, errp);
+    if (ret == 0) {
+        ni->netdev = qemu_find_netdev(nd_id);
+        ni->used = true;
+        nb_nics++;
+    }
+
+    g_free(nd_id);
+    return ret;
+}
+
 int net_init_clients(Error **errp)
 {
     net_change_state_entry =
@@ -XXX,XX +XXX,XX @@ int net_init_clients(Error **errp)
         return -1;
     }
 
+    if (qemu_opts_foreach(qemu_find_opts("nic"), net_param_nic, NULL, errp)) {
+        return -1;
+    }
+
     if (qemu_opts_foreach(qemu_find_opts("net"), net_init_client, NULL, errp)) {
         return -1;
     }
@@ -XXX,XX +XXX,XX @@ QemuOptsList qemu_netdev_opts = {
     },
 };
 
+QemuOptsList qemu_nic_opts = {
+    .name = "nic",
+    .implied_opt_name = "type",
+    .head = QTAILQ_HEAD_INITIALIZER(qemu_nic_opts.head),
+    .desc = {
+        /*
+         * no elements => accept any params
+         * validation will happen later
+         */
+        { /* end of list */ }
+    },
+};
+
 QemuOptsList qemu_net_opts = {
     .name = "net",
     .implied_opt_name = "type",
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 @@ DEF("netdev", HAS_ARG, QEMU_OPTION_netdev,
 #endif
     "-netdev hubport,id=str,hubid=n[,netdev=nd]\n"
     "                configure a hub port on QEMU VLAN 'n'\n", QEMU_ARCH_ALL)
+DEF("nic", HAS_ARG, QEMU_OPTION_nic,
+    "--nic [tap|bridge|"
+#ifdef CONFIG_SLIRP
+    "user|"
+#endif
+#ifdef __linux__
+    "l2tpv3|"
+#endif
+#ifdef CONFIG_VDE
+    "vde|"
+#endif
+#ifdef CONFIG_NETMAP
+    "netmap|"
+#endif
+#ifdef CONFIG_POSIX
+    "vhost-user|"
+#endif
+    "socket][,option][,...][mac=macaddr]\n"
+    "                initialize an on-board / default host NIC (using MAC address\n"
+    "                macaddr) and connect it to the given host network backend\n"
+    "--nic none      use it alone to have zero network devices (the default is to\n"
+    "                provided a 'user' network connection)\n",
+    QEMU_ARCH_ALL)
 DEF("net", HAS_ARG, QEMU_OPTION_net,
     "-net nic[,vlan=n][,netdev=nd][,macaddr=mac][,model=type][,name=str][,addr=str][,vectors=v]\n"
     "                configure or create an on-board (or machine default) NIC and\n"
     "                connect it either to VLAN 'n' or the netdev 'nd' (for pluggable\n"
     "                NICs please use '-device devtype,netdev=nd' instead)\n"
-    "-net none       use it alone to have zero network devices. If no -net option\n"
-    "                is provided, the default is '-net nic -net user'\n"
     "-net ["
 #ifdef CONFIG_SLIRP
     "user|"
@@ -XXX,XX +XXX,XX @@ qemu -m 512 -object memory-backend-file,id=mem,size=512M,mem-path=/hugetlbfs,sha
      -device virtio-net-pci,netdev=net0
 @end example
 
-@item -net none
-Indicate that no network devices should be configured. It is used to
-override the default configuration (@option{-net nic -net user}) which
-is activated if no @option{-net} options are provided.
+@item --nic [tap|bridge|user|l2tpv3|vde|netmap|vhost-user|socket][,...][,mac=macaddr]
+
+This option is a shortcut for setting both, the on-board (default) guest NIC
+hardware and the host network backend in one go. The host backend options are
+the same as with the corresponding @option{--netdev} option. The guest NIC
+hardware MAC address can be set with @option{mac=@var{macaddr}}.
+
+@item --nic none
+Indicate that no network devices should be configured. It is used to override
+the default configuration (default NIC with @option{--net user} backend) which
+is activated if no other networking options are provided.
 ETEXI
 
 STEXI
diff --git a/vl.c b/vl.c
index XXXXXXX..XXXXXXX 100644
--- a/vl.c
+++ b/vl.c
@@ -XXX,XX +XXX,XX @@ int main(int argc, char **argv, char **envp)
     qemu_add_opts(&qemu_chardev_opts);
     qemu_add_opts(&qemu_device_opts);
     qemu_add_opts(&qemu_netdev_opts);
+    qemu_add_opts(&qemu_nic_opts);
     qemu_add_opts(&qemu_net_opts);
     qemu_add_opts(&qemu_rtc_opts);
     qemu_add_opts(&qemu_global_opts);
@@ -XXX,XX +XXX,XX @@ int main(int argc, char **argv, char **envp)
                     exit(1);
                 }
                 break;
+            case QEMU_OPTION_nic:
+                default_net = 0;
+                if (net_client_parse(qemu_find_opts("nic"), optarg) == -1) {
+                    exit(1);
+                }
+                break;
             case QEMU_OPTION_net:
                 default_net = 0;
                 if (net_client_parse(qemu_find_opts("net"), optarg) == -1) {
-- 
2.7.4

From: Thomas Huth <thuth@redhat.com>

Headers like "hw/loader.h" and "qemu/sockets.h" are not needed in
the hw/net/*.c files. And Some other headers are included via other
headers already, so we can drop them, too.

diff --git a/hw/net/e1000.c b/hw/net/e1000.c
index XXXXXXX..XXXXXXX 100644
--- a/hw/net/e1000.c
+++ b/hw/net/e1000.c
@@ -XXX,XX +XXX,XX @@
 #include "hw/pci/pci.h"
 #include "net/net.h"
 #include "net/checksum.h"
-#include "hw/loader.h"
 #include "sysemu/sysemu.h"
 #include "sysemu/dma.h"
 #include "qemu/iov.h"
diff --git a/hw/net/lance.c b/hw/net/lance.c
index XXXXXXX..XXXXXXX 100644
--- a/hw/net/lance.c
+++ b/hw/net/lance.c
@@ -XXX,XX +XXX,XX @@
  */
 
 #include "qemu/osdep.h"
-#include "hw/sysbus.h"
-#include "net/net.h"
 #include "qemu/timer.h"
-#include "qemu/sockets.h"
 #include "hw/sparc/sparc32_dma.h"
 #include "hw/net/lance.h"
 #include "trace.h"
diff --git a/hw/net/ne2000.c b/hw/net/ne2000.c
index XXXXXXX..XXXXXXX 100644
--- a/hw/net/ne2000.c
+++ b/hw/net/ne2000.c
@@ -XXX,XX +XXX,XX @@
  */
 #include "qemu/osdep.h"
 #include "hw/pci/pci.h"
-#include "net/net.h"
 #include "net/eth.h"
 #include "ne2000.h"
-#include "hw/loader.h"
 #include "sysemu/sysemu.h"
 
 /* debug NE2000 card */
diff --git a/hw/net/pcnet-pci.c b/hw/net/pcnet-pci.c
index XXXXXXX..XXXXXXX 100644
--- a/hw/net/pcnet-pci.c
+++ b/hw/net/pcnet-pci.c
@@ -XXX,XX +XXX,XX @@
 #include "qemu/osdep.h"
 #include "hw/pci/pci.h"
 #include "net/net.h"
-#include "hw/loader.h"
 #include "qemu/timer.h"
 #include "sysemu/dma.h"
 #include "sysemu/sysemu.h"
diff --git a/hw/net/pcnet.c b/hw/net/pcnet.c
index XXXXXXX..XXXXXXX 100644
--- a/hw/net/pcnet.c
+++ b/hw/net/pcnet.c
@@ -XXX,XX +XXX,XX @@
 #include "net/net.h"
 #include "net/eth.h"
 #include "qemu/timer.h"
-#include "qemu/sockets.h"
 #include "sysemu/sysemu.h"
 #include "trace.h"
 
diff --git a/hw/net/rtl8139.c b/hw/net/rtl8139.c
index XXXXXXX..XXXXXXX 100644
--- a/hw/net/rtl8139.c
+++ b/hw/net/rtl8139.c
@@ -XXX,XX +XXX,XX @@
 #include "qemu/timer.h"
 #include "net/net.h"
 #include "net/eth.h"
-#include "hw/loader.h"
 #include "sysemu/sysemu.h"
-#include "qemu/iov.h"
 
 /* debug RTL8139 card */
 //#define DEBUG_RTL8139 1
diff --git a/hw/net/xgmac.c b/hw/net/xgmac.c
index XXXXXXX..XXXXXXX 100644
--- a/hw/net/xgmac.c
+++ b/hw/net/xgmac.c
@@ -XXX,XX +XXX,XX @@
 #include "hw/sysbus.h"
 #include "qemu/log.h"
 #include "net/net.h"
-#include "net/checksum.h"
 
 #ifdef DEBUG_XGMAC
 #define DEBUGF_BRK(message, args...) do { \
-- 
2.7.4

From: Jay Zhou <jianjay.zhou@huawei.com>

If netdev_add tap,id=net0,...,vhost=on failed in net_init_tap_one(),
the followed up device_add virtio-net-pci,netdev=net0 will fail
too, prints:

TUNSETOFFLOAD ioctl() failed: Bad file descriptor TUNSETOFFLOAD
   ioctl() failed: Bad file descriptor

The reason is that the fd of tap is closed when error occured after
calling net_init_tap_one().

The fd should be closed when calling net_init_tap_one failed:
   - if tap_set_sndbuf() failed
   - if tap_set_sndbuf() succeeded but vhost failed to open or
     initialize with vhostforce flag on
   - with wrong vhost command line parameter
The fd should not be closed just because vhost failed to open or
initialize but without vhostforce flag. So the followed up
device_add can fall back to userspace virtio successfully.

Suggested-by: Michael S. Tsirkin <mst@redhat.com>
Suggested-by: Igor Mammedov <imammedo@redhat.com>
Suggested-by: Jason Wang <jasowang@redhat.com>
Signed-off-by: Jay Zhou <jianjay.zhou@huawei.com>
Signed-off-by: Jason Wang <jasowang@redhat.com>
---
 include/net/vhost_net.h |  3 +++
 net/tap.c               | 22 +++++++++++++++++-----
 2 files changed, 20 insertions(+), 5 deletions(-)

diff --git a/include/net/vhost_net.h b/include/net/vhost_net.h
index XXXXXXX..XXXXXXX 100644
--- a/include/net/vhost_net.h
+++ b/include/net/vhost_net.h
@@ -XXX,XX +XXX,XX @@
 #include "net/net.h"
 #include "hw/virtio/vhost-backend.h"
 
+#define VHOST_NET_INIT_FAILED \
+    "vhost-net requested but could not be initialized"
+
 struct vhost_net;
 typedef struct vhost_net VHostNetState;
 
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,
         if (vhostfdname) {
             vhostfd = monitor_fd_param(cur_mon, vhostfdname, &err);
             if (vhostfd == -1) {
-                error_propagate(errp, err);
+                if (tap->has_vhostforce && tap->vhostforce) {
+                    error_propagate(errp, err);
+                } else {
+                    warn_report_err(err);
+                }
                 return;
             }
         } else {
             vhostfd = open("/dev/vhost-net", O_RDWR);
             if (vhostfd < 0) {
-                error_setg_errno(errp, errno,
-                                 "tap: open vhost char device failed");
+                if (tap->has_vhostforce && tap->vhostforce) {
+                    error_setg_errno(errp, errno,
+                                     "tap: open vhost char device failed");
+                } else {
+                    warn_report("tap: open vhost char device failed: %s",
+                                strerror(errno));
+                }
                 return;
             }
             fcntl(vhostfd, F_SETFL, O_NONBLOCK);
@@ -XXX,XX +XXX,XX @@ static void net_init_tap_one(const NetdevTapOptions *tap, NetClientState *peer,
 
         s->vhost_net = vhost_net_init(&options);
         if (!s->vhost_net) {
-            error_setg(errp,
-                       "vhost-net requested but could not be initialized");
+            if (tap->has_vhostforce && tap->vhostforce) {
+                error_setg(errp, VHOST_NET_INIT_FAILED);
+            } else {
+                warn_report(VHOST_NET_INIT_FAILED);
+            }
             return;
         }
     } else if (vhostfdname) {
-- 
2.7.4