Series comparison

-[Qemu-devel] [PULL 00/14] Net patches
+[PULL 00/13] Net patches
-The following changes since commit 6632f6ff96f0537fc34cdc00c760656fc62e23c5:
+The following changes since commit df722e33d5da26ea8604500ca8f509245a0ea524:
-  Merge remote-tracking branch 'remotes/famz/tags/block-and-testing-pull-request' into staging (2017-07-17 11:46:36 +0100)
+  Merge tag 'bsd-user-arm-pull-request' of gitlab.com:bsdimp/qemu into staging (2022-01-08 09:37:59 -0800)
 are available in the git repository at:
   https://github.com/jasowang/qemu.git tags/net-pull-request
-for you to fetch changes up to 189ae6bb5ce1f5a322f8691d00fe942ba43dd601:
+for you to fetch changes up to 5136cc6d3b8b74f4fa572f0874656947a401330e:
-  virtio-net: fix offload ctrl endian (2017-07-17 20:13:56 +0800)
+  net/vmnet: update MAINTAINERS list (2022-01-10 11:30:55 +0800)
 ----------------------------------------------------------------
-- fix virtio-net ctrl offload endian
+----------------------------------------------------------------
-- vnet header support for variou COLO netfilters and compare thread
+Peter Foley (2):
       net/tap: Set return code on failure
       net: Fix uninitialized data usage
-----------------------------------------------------------------
+Philippe Mathieu-Daudé (1):
-Jason Wang (1):
+      hw/net/vmxnet3: Log guest-triggerable errors using LOG_GUEST_ERROR
       virtio-net: fix offload ctrl endian
-Michal Privoznik (1):
+Rao Lei (1):
-      virtion-net: Prefer is_power_of_2()
+      net/filter: Optimize filter_send to coroutine
-Zhang Chen (12):
+Vladislav Yaroshchuk (7):
-      net: Add vnet_hdr_len arguments in NetClientState
+      net/vmnet: add vmnet dependency and customizable option
-      net/net.c: Add vnet_hdr support in SocketReadState
+      net/vmnet: add vmnet backends to qapi/net
-      net/filter-mirror.c: Introduce parameter for filter_send()
+      net/vmnet: implement shared mode (vmnet-shared)
-      net/filter-mirror.c: Make filter mirror support vnet support.
+      net/vmnet: implement host mode (vmnet-host)
-      net/filter-mirror.c: Add new option to enable vnet support for filter-redirector
+      net/vmnet: implement bridged mode (vmnet-bridged)
-      net/colo.c: Make vnet_hdr_len as packet property
+      net/vmnet: update qemu-options.hx
-      net/colo-compare.c: Introduce parameter for compare_chr_send()
+      net/vmnet: update MAINTAINERS list
       net/colo-compare.c: Make colo-compare support vnet_hdr_len
       net/colo.c: Add vnet packet parse feature in colo-proxy
       net/colo-compare.c: Add vnet packet's tcp/udp/icmp compare
       net/filter-rewriter.c: Make filter-rewriter support vnet_hdr_len
       docs/colo-proxy.txt: Update colo-proxy usage of net driver with vnet_header
- docs/colo-proxy.txt   | 26 ++++++++++++++++
+Zhang Chen (2):
- hw/net/virtio-net.c   |  4 ++-
+      net/colo-compare.c: Optimize compare order for performance
- include/net/net.h     | 10 ++++--
+      net/colo-compare.c: Update the default value comments
- net/colo-compare.c    | 84 ++++++++++++++++++++++++++++++++++++++++++---------
- net/colo.c            |  9 +++---
+ MAINTAINERS                   |   5 +
- net/colo.h            |  4 ++-
+ hw/net/vmxnet3.c              |   4 +-
- net/filter-mirror.c   | 75 +++++++++++++++++++++++++++++++++++++++++----
+ meson.build                   |   4 +
- net/filter-rewriter.c | 37 ++++++++++++++++++++++-
+ meson_options.txt             |   2 +
- net/net.c             | 37 ++++++++++++++++++++---
+ net/clients.h                 |  11 ++
- net/socket.c          |  8 ++---
+ net/colo-compare.c            |  28 ++--
- qemu-options.hx       | 19 ++++++------
+ net/filter-mirror.c           |  66 +++++++--
-files changed, 265 insertions(+), 48 deletions(-)
+ net/meson.build               |   7 +
  net/net.c                     |  10 ++
  net/tap-linux.c               |   1 +
  net/tap.c                     |   1 +
  net/vmnet-bridged.m           | 111 ++++++++++++++
  net/vmnet-common.m            | 330 ++++++++++++++++++++++++++++++++++++++++++
  net/vmnet-host.c              | 105 ++++++++++++++
  net/vmnet-shared.c            |  91 ++++++++++++
  net/vmnet_int.h               |  48 ++++++
  qapi/net.json                 | 132 ++++++++++++++++-
  qemu-options.hx               |  25 ++++
  scripts/meson-buildoptions.sh |   3 +
 files changed, 954 insertions(+), 30 deletions(-)
  create mode 100644 net/vmnet-bridged.m
  create mode 100644 net/vmnet-common.m
  create mode 100644 net/vmnet-host.c
  create mode 100644 net/vmnet-shared.c
  create mode 100644 net/vmnet_int.h

-[Qemu-devel] [PULL 01/14] net: Add vnet_hdr_len arguments in NetClientState
+Deleted patch
-From: Zhang Chen <zhangchen.fnst@cn.fujitsu.com>
-Add vnet_hdr_len arguments in NetClientState
-that make other module get real vnet_hdr_len easily.
-Signed-off-by: Zhang Chen <zhangchen.fnst@cn.fujitsu.com>
-Signed-off-by: Jason Wang <jasowang@redhat.com>
----
- include/net/net.h | 1 +
- net/net.c         | 1 +
-files changed, 2 insertions(+)
-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 @@ struct NetClientState {
-     unsigned int queue_index;
-     unsigned rxfilter_notify_enabled:1;
-     int vring_enable;
-+    int vnet_hdr_len;
-     QTAILQ_HEAD(NetFilterHead, NetFilterState) filters;
- };
-diff --git a/net/net.c b/net/net.c
-index XXXXXXX..XXXXXXX 100644
---- a/net/net.c
-+++ b/net/net.c
-@@ -XXX,XX +XXX,XX @@ void qemu_set_vnet_hdr_len(NetClientState *nc, int len)
-         return;
-     }
-+    nc->vnet_hdr_len = len;
-     nc->info->set_vnet_hdr_len(nc, len);
- }
---
-.7.4

-[Qemu-devel] [PULL 14/14] virtio-net: fix offload ctrl endian
+[PULL 01/13] hw/net/vmxnet3: Log guest-triggerable errors using LOG_GUEST_ERROR
-Spec said offloads should be le64, so use virtio_ldq_p() to guarantee
+From: Philippe Mathieu-Daudé <philmd@redhat.com>
 valid endian.
-Fixes: 644c98587d4c ("virtio-net: dynamic network offloads configuration")
+The "Interrupt Cause" register (VMXNET3_REG_ICR) is read-only.
-Cc: qemu-stable@nongnu.org
+Write accesses are ignored. Log them with as LOG_GUEST_ERROR
-Cc: Dmitry Fleytman <dfleytma@redhat.com>
+instead of aborting:
   [R +0.239743] writeq 0xe0002031 0x46291a5a55460800
   ERROR:hw/net/vmxnet3.c:1819:vmxnet3_io_bar1_write: code should not be reached
   Thread 1 "qemu-system-i38" received signal SIGABRT, Aborted.
   (gdb) bt
   #3  0x74c397d3 in __GI_abort () at abort.c:79
   #4  0x76d3cd4c in g_assertion_message (domain=<optimized out>, file=<optimized out>, line=<optimized out>, func=<optimized out>, message=<optimized out>) at ../glib/gtestutils.c:3223
   #5  0x76d9d45f in g_assertion_message_expr
       (domain=0x0, file=0x59fc2e53 "hw/net/vmxnet3.c", line=1819, func=0x59fc11e0 <__func__.vmxnet3_io_bar1_write> "vmxnet3_io_bar1_write", expr=<optimized out>)
       at ../glib/gtestutils.c:3249
   #6  0x57e80a3a in vmxnet3_io_bar1_write (opaque=0x62814100, addr=56, val=70, size=4) at hw/net/vmxnet3.c:1819
   #7  0x58c2d894 in memory_region_write_accessor (mr=0x62816b90, addr=56, value=0x7fff9450, size=4, shift=0, mask=4294967295, attrs=...) at softmmu/memory.c:492
   #8  0x58c2d1d2 in access_with_adjusted_size (addr=56, value=0x7fff9450, size=1, access_size_min=4, access_size_max=4, access_fn=
 x58c2d290 <memory_region_write_accessor>, mr=0x62816b90, attrs=...) at softmmu/memory.c:554
   #9  0x58c2bae7 in memory_region_dispatch_write (mr=0x62816b90, addr=56, data=70, op=MO_8, attrs=...) at softmmu/memory.c:1504
   #10 0x58bfd034 in flatview_write_continue (fv=0x606000181700, addr=0xe0002038, attrs=..., ptr=0x7fffb9e0, len=1, addr1=56, l=1, mr=0x62816b90)
       at softmmu/physmem.c:2782
   #11 0x58beba00 in flatview_write (fv=0x606000181700, addr=0xe0002031, attrs=..., buf=0x7fffb9e0, len=8) at softmmu/physmem.c:2822
   #12 0x58beb589 in address_space_write (as=0x608000015f20, addr=0xe0002031, attrs=..., buf=0x7fffb9e0, len=8) at softmmu/physmem.c:2914
 Reported-by: Dike <dike199774@qq.com>
 Reported-by: Duhao <504224090@qq.com>
 BugLink: https://bugzilla.redhat.com/show_bug.cgi?id=2032932
 Signed-off-by: Philippe Mathieu-Daudé <philmd@redhat.com>
 Signed-off-by: Jason Wang <jasowang@redhat.com>
 ---
- hw/net/virtio-net.c | 2 ++
+ hw/net/vmxnet3.c | 4 +++-
-file changed, 2 insertions(+)
+file changed, 3 insertions(+), 1 deletion(-)
-diff --git a/hw/net/virtio-net.c b/hw/net/virtio-net.c
+diff --git a/hw/net/vmxnet3.c b/hw/net/vmxnet3.c
 index XXXXXXX..XXXXXXX 100644
---- a/hw/net/virtio-net.c
+--- a/hw/net/vmxnet3.c
-+++ b/hw/net/virtio-net.c
++++ b/hw/net/vmxnet3.c
-@@ -XXX,XX +XXX,XX @@ static int virtio_net_handle_offloads(VirtIONet *n, uint8_t cmd,
+@@ -XXX,XX +XXX,XX @@ vmxnet3_io_bar1_write(void *opaque,
-     if (cmd == VIRTIO_NET_CTRL_GUEST_OFFLOADS_SET) {
+     case VMXNET3_REG_ICR:
-         uint64_t supported_offloads;
+         VMW_CBPRN("Write BAR1 [VMXNET3_REG_ICR] = %" PRIx64 ", size %d",
+                   val, size);
-+        offloads = virtio_ldq_p(vdev, &offloads);
+-        g_assert_not_reached();
-+
++        qemu_log_mask(LOG_GUEST_ERROR,
-         if (!n->has_vnet_hdr) {
++                      "%s: write to read-only register VMXNET3_REG_ICR\n",
-             return VIRTIO_NET_ERR;
++                      TYPE_VMXNET3);
-         }
+         break;
      /* Event Cause Register */
 --
 .7.4

-[Qemu-devel] [PULL 13/14] virtion-net: Prefer is_power_of_2()
+[PULL 02/13] net/tap: Set return code on failure
-From: Michal Privoznik <mprivozn@redhat.com>
+From: Peter Foley <pefoley@google.com>
-We have a function that checks if given number is power of two.
+Match the other error handling in this function.
 We should prefer it instead of expanding the check on our own.
-Signed-off-by: Michal Privoznik <mprivozn@redhat.com>
+Fixes: e7b347d0bf6 ("net: detect errors from probing vnet hdr flag for TAP devices")
 Reviewed-by: Patrick Venture <venture@google.com>
 Reviewed-by: Philippe Mathieu-Daudé <f4bug@amsat.org>
 Signed-off-by: Peter Foley <pefoley@google.com>
 Signed-off-by: Jason Wang <jasowang@redhat.com>
 ---
- hw/net/virtio-net.c | 2 +-
+ net/tap.c | 1 +
-file changed, 1 insertion(+), 1 deletion(-)
+file changed, 1 insertion(+)
-diff --git a/hw/net/virtio-net.c b/hw/net/virtio-net.c
+diff --git a/net/tap.c b/net/tap.c
 index XXXXXXX..XXXXXXX 100644
---- a/hw/net/virtio-net.c
+--- a/net/tap.c
-+++ b/hw/net/virtio-net.c
++++ b/net/tap.c
-@@ -XXX,XX +XXX,XX @@ static void virtio_net_device_realize(DeviceState *dev, Error **errp)
+@@ -XXX,XX +XXX,XX @@ int net_init_tap(const Netdev *netdev, const char *name,
-      */
+             if (i == 0) {
-     if (n->net_conf.rx_queue_size < VIRTIO_NET_RX_QUEUE_MIN_SIZE ||
+                 vnet_hdr = tap_probe_vnet_hdr(fd, errp);
-         n->net_conf.rx_queue_size > VIRTQUEUE_MAX_SIZE ||
+                 if (vnet_hdr < 0) {
--        (n->net_conf.rx_queue_size & (n->net_conf.rx_queue_size - 1))) {
++                    ret = -1;
-+        !is_power_of_2(n->net_conf.rx_queue_size)) {
+                     goto free_fail;
-         error_setg(errp, "Invalid rx_queue_size (= %" PRIu16 "), "
+                 }
-                    "must be a power of 2 between %d and %d.",
+             } else if (vnet_hdr != tap_probe_vnet_hdr(fd, NULL)) {
                     n->net_conf.rx_queue_size, VIRTIO_NET_RX_QUEUE_MIN_SIZE,
 --
 .7.4

-[Qemu-devel] [PULL 12/14] docs/colo-proxy.txt: Update colo-proxy usage of net driver with vnet_header
+[PULL 03/13] net: Fix uninitialized data usage
-From: Zhang Chen <zhangchen.fnst@cn.fujitsu.com>
+From: Peter Foley <pefoley@google.com>
-Signed-off-by: Zhang Chen <zhangchen.fnst@cn.fujitsu.com>
+e.g.
 15:16:20.151506 Uninitialized bytes in ioctl_common_pre at offset 0 inside [0x7ffc516af9b8, 4)
 15:16:20.151659 ==588974==WARNING: MemorySanitizer: use-of-uninitialized-value
 15:16:20.312923     #0 0x5639b88acb21 in tap_probe_vnet_hdr_len third_party/qemu/net/tap-linux.c:183:9
 15:16:20.312952     #1 0x5639b88afd66 in net_tap_fd_init third_party/qemu/net/tap.c:409:9
 15:16:20.312954     #2 0x5639b88b2d1b in net_init_tap_one third_party/qemu/net/tap.c:681:19
 15:16:20.312956     #3 0x5639b88b16a8 in net_init_tap third_party/qemu/net/tap.c:912:13
 15:16:20.312957     #4 0x5639b8890175 in net_client_init1 third_party/qemu/net/net.c:1110:9
 15:16:20.312958     #5 0x5639b888f912 in net_client_init third_party/qemu/net/net.c:1208:15
 15:16:20.312960     #6 0x5639b8894aa5 in net_param_nic third_party/qemu/net/net.c:1588:11
 15:16:20.312961     #7 0x5639b900cd18 in qemu_opts_foreach third_party/qemu/util/qemu-option.c:1135:14
 15:16:20.312962     #8 0x5639b889393c in net_init_clients third_party/qemu/net/net.c:1612:9
 15:16:20.312964     #9 0x5639b717aaf3 in qemu_create_late_backends third_party/qemu/softmmu/vl.c:1962:5
 15:16:20.312965     #10 0x5639b717aaf3 in qemu_init third_party/qemu/softmmu/vl.c:3694:5
 15:16:20.312967     #11 0x5639b71083b8 in main third_party/qemu/softmmu/main.c:49:5
 15:16:20.312968     #12 0x7f464de1d8d2 in __libc_start_main (/usr/grte/v5/lib64/libc.so.6+0x628d2)
 15:16:20.312969     #13 0x5639b6bbd389 in _start /usr/grte/v5/debug-src/src/csu/../sysdeps/x86_64/start.S:120
 15:16:20.312970
 15:16:20.312975   Uninitialized value was stored to memory at
 15:16:20.313393     #0 0x5639b88acbee in tap_probe_vnet_hdr_len third_party/qemu/net/tap-linux.c
 15:16:20.313396     #1 0x5639b88afd66 in net_tap_fd_init third_party/qemu/net/tap.c:409:9
 15:16:20.313398     #2 0x5639b88b2d1b in net_init_tap_one third_party/qemu/net/tap.c:681:19
 15:16:20.313399     #3 0x5639b88b16a8 in net_init_tap third_party/qemu/net/tap.c:912:13
 15:16:20.313400     #4 0x5639b8890175 in net_client_init1 third_party/qemu/net/net.c:1110:9
 15:16:20.313401     #5 0x5639b888f912 in net_client_init third_party/qemu/net/net.c:1208:15
 15:16:20.313403     #6 0x5639b8894aa5 in net_param_nic third_party/qemu/net/net.c:1588:11
 15:16:20.313404     #7 0x5639b900cd18 in qemu_opts_foreach third_party/qemu/util/qemu-option.c:1135:14
 15:16:20.313405     #8 0x5639b889393c in net_init_clients third_party/qemu/net/net.c:1612:9
 15:16:20.313407     #9 0x5639b717aaf3 in qemu_create_late_backends third_party/qemu/softmmu/vl.c:1962:5
 15:16:20.313408     #10 0x5639b717aaf3 in qemu_init third_party/qemu/softmmu/vl.c:3694:5
 15:16:20.313409     #11 0x5639b71083b8 in main third_party/qemu/softmmu/main.c:49:5
 15:16:20.313410     #12 0x7f464de1d8d2 in __libc_start_main (/usr/grte/v5/lib64/libc.so.6+0x628d2)
 15:16:20.313412     #13 0x5639b6bbd389 in _start /usr/grte/v5/debug-src/src/csu/../sysdeps/x86_64/start.S:120
 15:16:20.313413
 15:16:20.313417   Uninitialized value was stored to memory at
 15:16:20.313791     #0 0x5639b88affbd in net_tap_fd_init third_party/qemu/net/tap.c:400:26
 15:16:20.313826     #1 0x5639b88b2d1b in net_init_tap_one third_party/qemu/net/tap.c:681:19
 15:16:20.313829     #2 0x5639b88b16a8 in net_init_tap third_party/qemu/net/tap.c:912:13
 15:16:20.313831     #3 0x5639b8890175 in net_client_init1 third_party/qemu/net/net.c:1110:9
 15:16:20.313836     #4 0x5639b888f912 in net_client_init third_party/qemu/net/net.c:1208:15
 15:16:20.313838     #5 0x5639b8894aa5 in net_param_nic third_party/qemu/net/net.c:1588:11
 15:16:20.313839     #6 0x5639b900cd18 in qemu_opts_foreach third_party/qemu/util/qemu-option.c:1135:14
 15:16:20.313841     #7 0x5639b889393c in net_init_clients third_party/qemu/net/net.c:1612:9
 15:16:20.313843     #8 0x5639b717aaf3 in qemu_create_late_backends third_party/qemu/softmmu/vl.c:1962:5
 15:16:20.313844     #9 0x5639b717aaf3 in qemu_init third_party/qemu/softmmu/vl.c:3694:5
 15:16:20.313845     #10 0x5639b71083b8 in main third_party/qemu/softmmu/main.c:49:5
 15:16:20.313846     #11 0x7f464de1d8d2 in __libc_start_main (/usr/grte/v5/lib64/libc.so.6+0x628d2)
 15:16:20.313847     #12 0x5639b6bbd389 in _start /usr/grte/v5/debug-src/src/csu/../sysdeps/x86_64/start.S:120
 15:16:20.313849
 15:16:20.313851   Uninitialized value was created by an allocation of 'ifr' in the stack frame of function 'tap_probe_vnet_hdr'
 15:16:20.313855     #0 0x5639b88ac680 in tap_probe_vnet_hdr third_party/qemu/net/tap-linux.c:151
 15:16:20.313856
 15:16:20.313878 SUMMARY: MemorySanitizer: use-of-uninitialized-value third_party/qemu/net/tap-linux.c:183:9 in tap_probe_vnet_hdr_len
 Fixes: dc69004c7d8 ("net: move tap_probe_vnet_hdr() to tap-linux.c")
 Reviewed-by: Hao Wu <wuhaotsh@google.com>
 Reviewed-by: Patrick Venture <venture@google.com>
 Reviewed-by: Philippe Mathieu-Daudé <f4bug@amsat.org>
 Signed-off-by: Peter Foley <pefoley@google.com>
 Signed-off-by: Jason Wang <jasowang@redhat.com>
 ---
- docs/colo-proxy.txt | 26 ++++++++++++++++++++++++++
+ net/tap-linux.c | 1 +
-file changed, 26 insertions(+)
+file changed, 1 insertion(+)
-diff --git a/docs/colo-proxy.txt b/docs/colo-proxy.txt
+diff --git a/net/tap-linux.c b/net/tap-linux.c
 index XXXXXXX..XXXXXXX 100644
---- a/docs/colo-proxy.txt
+--- a/net/tap-linux.c
-+++ b/docs/colo-proxy.txt
++++ b/net/tap-linux.c
-@@ -XXX,XX +XXX,XX @@ Secondary(ip:3.3.3.8):
+@@ -XXX,XX +XXX,XX @@ void tap_set_sndbuf(int fd, const NetdevTapOptions *tap, Error **errp)
- -chardev socket,id=red1,host=3.3.3.3,port=9004
+ int tap_probe_vnet_hdr(int fd, Error **errp)
- -object filter-redirector,id=f1,netdev=hn0,queue=tx,indev=red0
+ {
- -object filter-redirector,id=f2,netdev=hn0,queue=rx,outdev=red1
+     struct ifreq ifr;
-+-object filter-rewriter,id=f3,netdev=hn0,queue=all
++    memset(&ifr, 0, sizeof(ifr));
-+
-+If you want to use virtio-net-pci or other driver with vnet_header:
+     if (ioctl(fd, TUNGETIFF, &ifr) != 0) {
-+
+         /* TUNGETIFF is available since kernel v2.6.27 */
 +Primary(ip:3.3.3.3):
 +-netdev tap,id=hn0,vhost=off,script=/etc/qemu-ifup,downscript=/etc/qemu-ifdown
 +-device e1000,id=e0,netdev=hn0,mac=52:a4:00:12:78:66
 +-chardev socket,id=mirror0,host=3.3.3.3,port=9003,server,nowait
 +-chardev socket,id=compare1,host=3.3.3.3,port=9004,server,nowait
 +-chardev socket,id=compare0,host=3.3.3.3,port=9001,server,nowait
 +-chardev socket,id=compare0-0,host=3.3.3.3,port=9001
 +-chardev socket,id=compare_out,host=3.3.3.3,port=9005,server,nowait
 +-chardev socket,id=compare_out0,host=3.3.3.3,port=9005
 +-object filter-mirror,id=m0,netdev=hn0,queue=tx,outdev=mirror0,vnet_hdr_support
 +-object filter-redirector,netdev=hn0,id=redire0,queue=rx,indev=compare_out,vnet_hdr_support
 +-object filter-redirector,netdev=hn0,id=redire1,queue=rx,outdev=compare0,vnet_hdr_support
 +-object colo-compare,id=comp0,primary_in=compare0-0,secondary_in=compare1,outdev=compare_out0,vnet_hdr_support
 +
 +Secondary(ip:3.3.3.8):
 +-netdev tap,id=hn0,vhost=off,script=/etc/qemu-ifup,down script=/etc/qemu-ifdown
 +-device e1000,netdev=hn0,mac=52:a4:00:12:78:66
 +-chardev socket,id=red0,host=3.3.3.3,port=9003
 +-chardev socket,id=red1,host=3.3.3.3,port=9004
 +-object filter-redirector,id=f1,netdev=hn0,queue=tx,indev=red0,vnet_hdr_support
 +-object filter-redirector,id=f2,netdev=hn0,queue=rx,outdev=red1,vnet_hdr_support
 +-object filter-rewriter,id=f3,netdev=hn0,queue=all,vnet_hdr_support
  Note:
    a.COLO-proxy must work with COLO-frame and Block-replication.
 --
 .7.4

-[Qemu-devel] [PULL 08/14] net/colo-compare.c: Make colo-compare support vnet_hdr_len
+[PULL 04/13] net/colo-compare.c: Optimize compare order for performance
-From: Zhang Chen <zhangchen.fnst@cn.fujitsu.com>
+From: Zhang Chen <chen.zhang@intel.com>
-We add the vnet_hdr_support option for colo-compare, default is disabled.
+COLO-compare use the glib function g_queue_find_custom to dump
-If you use virtio-net-pci or other driver needs vnet_hdr, please enable it.
+another VM's networking packet to compare. But this function always
-You can use it for example:
+start find from the queue->head(here is the newest packet), It will
--object colo-compare,id=comp0,primary_in=compare0-0,secondary_in=compare1,outdev=compare_out0,vnet_hdr_support
+reduce the success rate of comparison. So this patch reversed
 the order of the queues for performance.
-COLO-compare can get vnet header length from filter,
+Signed-off-by: Zhang Chen <chen.zhang@intel.com>
-Add vnet_hdr_len to struct packet and output packet with
+Reported-by: leirao <lei.rao@intel.com>
 the vnet_hdr_len.
 Signed-off-by: Zhang Chen <zhangchen.fnst@cn.fujitsu.com>
 Signed-off-by: Jason Wang <jasowang@redhat.com>
 ---
- net/colo-compare.c | 60 +++++++++++++++++++++++++++++++++++++++++++++++-------
+ net/colo-compare.c | 26 +++++++++++++-------------
- qemu-options.hx    |  4 ++--
+file changed, 13 insertions(+), 13 deletions(-)
 files changed, 55 insertions(+), 9 deletions(-)
 diff --git a/net/colo-compare.c b/net/colo-compare.c
 index XXXXXXX..XXXXXXX 100644
 --- a/net/colo-compare.c
 +++ b/net/colo-compare.c
-@@ -XXX,XX +XXX,XX @@ typedef struct CompareState {
+@@ -XXX,XX +XXX,XX @@ static void colo_compare_inconsistency_notify(CompareState *s)
-     CharBackend chr_out;
+ /* Use restricted to colo_insert_packet() */
      SocketReadState pri_rs;
      SocketReadState sec_rs;
 +    bool vnet_hdr;
      /* connection list: the connections belonged to this NIC could be found
       * in this list.
@@ -XXX,XX +XXX,XX @@ enum {
  static int compare_chr_send(CompareState *s,
                              const uint8_t *buf,
 -                            uint32_t size);
 +                            uint32_t size,
 +                            uint32_t vnet_hdr_len);
  static gint seq_sorter(Packet *a, Packet *b, gpointer data)
  {
-@@ -XXX,XX +XXX,XX @@ static void colo_compare_connection(void *opaque, void *user_data)
+-    return a->tcp_seq - b->tcp_seq;
-         }
++    return b->tcp_seq - a->tcp_seq;
          if (result) {
 -            ret = compare_chr_send(s, pkt->data, pkt->size);
 +            ret = compare_chr_send(s,
 +                                   pkt->data,
 +                                   pkt->size,
 +                                   pkt->vnet_hdr_len);
              if (ret < 0) {
                  error_report("colo_send_primary_packet failed");
              }
@@ -XXX,XX +XXX,XX @@ static void colo_compare_connection(void *opaque, void *user_data)
  static int compare_chr_send(CompareState *s,
                              const uint8_t *buf,
 -                            uint32_t size)
 +                            uint32_t size,
 +                            uint32_t vnet_hdr_len)
  {
      int ret = 0;
      uint32_t len = htonl(size);
@@ -XXX,XX +XXX,XX @@ static int compare_chr_send(CompareState *s,
          goto err;
      }
 +    if (s->vnet_hdr) {
 +        /*
 +         * We send vnet header len make other module(like filter-redirector)
 +         * know how to parse net packet correctly.
 +         */
 +        len = htonl(vnet_hdr_len);
 +        ret = qemu_chr_fe_write_all(&s->chr_out, (uint8_t *)&len, sizeof(len));
 +        if (ret != sizeof(len)) {
 +            goto err;
 +        }
 +    }
 +
      ret = qemu_chr_fe_write_all(&s->chr_out, (uint8_t *)buf, size);
      if (ret != size) {
          goto err;
@@ -XXX,XX +XXX,XX @@ static void compare_set_outdev(Object *obj, const char *value, Error **errp)
      s->outdev = g_strdup(value);
  }
-+static bool compare_get_vnet_hdr(Object *obj, Error **errp)
+ static void fill_pkt_tcp_info(void *data, uint32_t *max_ack)
-+{
+@@ -XXX,XX +XXX,XX @@ pri:
-+    CompareState *s = COLO_COMPARE(obj);
+     if (g_queue_is_empty(&conn->primary_list)) {
 +
 +    return s->vnet_hdr;
 +}
 +
 +static void compare_set_vnet_hdr(Object *obj,
 +                                 bool value,
 +                                 Error **errp)
 +{
 +    CompareState *s = COLO_COMPARE(obj);
 +
 +    s->vnet_hdr = value;
 +}
 +
  static void compare_pri_rs_finalize(SocketReadState *pri_rs)
  {
      CompareState *s = container_of(pri_rs, CompareState, pri_rs);
      if (packet_enqueue(s, PRIMARY_IN)) {
          trace_colo_compare_main("primary: unsupported packet in");
 -        compare_chr_send(s, pri_rs->buf, pri_rs->packet_len);
 +        compare_chr_send(s,
 +                         pri_rs->buf,
 +                         pri_rs->packet_len,
 +                         pri_rs->vnet_hdr_len);
      } else {
          /* compare connection */
          g_queue_foreach(&s->conn_list, colo_compare_connection, s);
@@ -XXX,XX +XXX,XX @@ static void colo_compare_complete(UserCreatable *uc, Error **errp)
          return;
      }
+-    ppkt = g_queue_pop_head(&conn->primary_list);
--    net_socket_rs_init(&s->pri_rs, compare_pri_rs_finalize, false);
++    ppkt = g_queue_pop_tail(&conn->primary_list);
--    net_socket_rs_init(&s->sec_rs, compare_sec_rs_finalize, false);
+ sec:
-+    net_socket_rs_init(&s->pri_rs, compare_pri_rs_finalize, s->vnet_hdr);
+     if (g_queue_is_empty(&conn->secondary_list)) {
-+    net_socket_rs_init(&s->sec_rs, compare_sec_rs_finalize, s->vnet_hdr);
+-        g_queue_push_head(&conn->primary_list, ppkt);
++        g_queue_push_tail(&conn->primary_list, ppkt);
-     g_queue_init(&s->conn_list);
+         return;
+     }
 -    spkt = g_queue_pop_head(&conn->secondary_list);
 +    spkt = g_queue_pop_tail(&conn->secondary_list);
      if (ppkt->tcp_seq == ppkt->seq_end) {
          colo_release_primary_pkt(s, ppkt);
@@ -XXX,XX +XXX,XX @@ sec:
              }
          }
          if (!ppkt) {
 -            g_queue_push_head(&conn->secondary_list, spkt);
 +            g_queue_push_tail(&conn->secondary_list, spkt);
              goto pri;
          }
      }
@@ -XXX,XX +XXX,XX @@ sec:
          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);
 +            g_queue_push_tail(&conn->secondary_list, spkt);
              goto pri;
          } else if (mark == COLO_COMPARE_FREE_SECONDARY) {
              conn->compare_seq = spkt->seq_end;
@@ -XXX,XX +XXX,XX @@ sec:
              goto pri;
          }
      } else {
 -        g_queue_push_head(&conn->primary_list, ppkt);
 -        g_queue_push_head(&conn->secondary_list, spkt);
 +        g_queue_push_tail(&conn->primary_list, ppkt);
 +        g_queue_push_tail(&conn->secondary_list, spkt);
  #ifdef DEBUG_COLO_PACKETS
          qemu_hexdump(stderr, "colo-compare ppkt", ppkt->data, ppkt->size);
@@ -XXX,XX +XXX,XX @@ static void colo_compare_packet(CompareState *s, Connection *conn,
      while (!g_queue_is_empty(&conn->primary_list) &&
             !g_queue_is_empty(&conn->secondary_list)) {
 -        pkt = g_queue_pop_head(&conn->primary_list);
 +        pkt = g_queue_pop_tail(&conn->primary_list);
          result = g_queue_find_custom(&conn->secondary_list,
                   pkt, (GCompareFunc)HandlePacket);
@@ -XXX,XX +XXX,XX @@ static void colo_compare_packet(CompareState *s, Connection *conn,
               * timeout, it will trigger a checkpoint request.
               */
              trace_colo_compare_main("packet different");
 -            g_queue_push_head(&conn->primary_list, pkt);
 +            g_queue_push_tail(&conn->primary_list, pkt);
              colo_compare_inconsistency_notify(s);
              break;
@@ -XXX,XX +XXX,XX @@ static int compare_chr_send(CompareState *s,
          entry->buf = g_malloc(size);
          memcpy(entry->buf, buf, size);
      }
 -    g_queue_push_head(&sendco->send_list, entry);
 +    g_queue_push_tail(&sendco->send_list, entry);
      if (sendco->done) {
          sendco->co = qemu_coroutine_create(_compare_chr_send, sendco);
 @@ -XXX,XX +XXX,XX @@ static void colo_flush_packets(void *opaque, void *user_data)
+     Packet *pkt = NULL;
      while (!g_queue_is_empty(&conn->primary_list)) {
-         pkt = g_queue_pop_head(&conn->primary_list);
+-        pkt = g_queue_pop_head(&conn->primary_list);
--        compare_chr_send(s, pkt->data, pkt->size);
++        pkt = g_queue_pop_tail(&conn->primary_list);
-+        compare_chr_send(s,
+         compare_chr_send(s,
-+                         pkt->data,
+                          pkt->data,
-+                         pkt->size,
+                          pkt->size,
-+                         pkt->vnet_hdr_len);
+@@ -XXX,XX +XXX,XX @@ static void colo_flush_packets(void *opaque, void *user_data)
          packet_destroy_partial(pkt, NULL);
      }
      while (!g_queue_is_empty(&conn->secondary_list)) {
 -        pkt = g_queue_pop_head(&conn->secondary_list);
 +        pkt = g_queue_pop_tail(&conn->secondary_list);
          packet_destroy(pkt, NULL);
      }
-     while (!g_queue_is_empty(&conn->secondary_list)) {
-@@ -XXX,XX +XXX,XX @@ static void colo_compare_class_init(ObjectClass *oc, void *data)
- static void colo_compare_init(Object *obj)
- {
-+    CompareState *s = COLO_COMPARE(obj);
-+
-     object_property_add_str(obj, "primary_in",
-                             compare_get_pri_indev, compare_set_pri_indev,
-                             NULL);
-@@ -XXX,XX +XXX,XX @@ static void colo_compare_init(Object *obj)
-     object_property_add_str(obj, "outdev",
-                             compare_get_outdev, compare_set_outdev,
-                             NULL);
-+
-+    s->vnet_hdr = false;
-+    object_property_add_bool(obj, "vnet_hdr_support", compare_get_vnet_hdr,
-+                             compare_set_vnet_hdr, NULL);
  }
- static void colo_compare_finalize(Object *obj)
-diff --git a/qemu-options.hx b/qemu-options.hx
-index XXXXXXX..XXXXXXX 100644
---- a/qemu-options.hx
-+++ b/qemu-options.hx
-@@ -XXX,XX +XXX,XX @@ Dump the network traffic on netdev @var{dev} to the file specified by
- The file format is libpcap, so it can be analyzed with tools such as tcpdump
- or Wireshark.
--@item -object colo-compare,id=@var{id},primary_in=@var{chardevid},secondary_in=@var{chardevid},
--outdev=@var{chardevid}
-+@item -object colo-compare,id=@var{id},primary_in=@var{chardevid},secondary_in=@var{chardevid},outdev=@var{chardevid}[,vnet_hdr_support]
- Colo-compare gets packet from primary_in@var{chardevid} and secondary_in@var{chardevid}, than compare primary packet with
- secondary packet. If the packets are same, we will output primary
- packet to outdev@var{chardevid}, else we will notify colo-frame
- do checkpoint and send primary packet to outdev@var{chardevid}.
-+if it has the vnet_hdr_support flag, colo compare will send/recv packet with vnet_hdr_len.
- we must use it with the help of filter-mirror and filter-redirector.
 --
 .7.4

-[Qemu-devel] [PULL 10/14] net/colo-compare.c: Add vnet packet's tcp/udp/icmp compare
+[PULL 05/13] net/colo-compare.c: Update the default value comments
-From: Zhang Chen <zhangchen.fnst@cn.fujitsu.com>
+From: Zhang Chen <chen.zhang@intel.com>
-COLO-Proxy just focus on packet payload, so we skip vnet header.
+Make the comments consistent with the REGULAR_PACKET_CHECK_MS.
-Signed-off-by: Zhang Chen <zhangchen.fnst@cn.fujitsu.com>
+Signed-off-by: Zhang Chen <chen.zhang@intel.com>
 Signed-off-by: Jason Wang <jasowang@redhat.com>
 ---
- net/colo-compare.c | 8 ++++++--
+ net/colo-compare.c | 2 +-
-file changed, 6 insertions(+), 2 deletions(-)
+file changed, 1 insertion(+), 1 deletion(-)
 diff --git a/net/colo-compare.c b/net/colo-compare.c
 index XXXXXXX..XXXXXXX 100644
 --- a/net/colo-compare.c
 +++ b/net/colo-compare.c
-@@ -XXX,XX +XXX,XX @@ static int colo_packet_compare_common(Packet *ppkt, Packet *spkt, int offset)
+@@ -XXX,XX +XXX,XX @@ static void colo_compare_complete(UserCreatable *uc, Error **errp)
                                     sec_ip_src, sec_ip_dst);
      }
-+    offset = ppkt->vnet_hdr_len + offset;
+     if (!s->expired_scan_cycle) {
-+
+-        /* Set default value to 3000 MS */
-     if (ppkt->size == spkt->size) {
++        /* Set default value to 1000 MS */
--        return memcmp(ppkt->data + offset, spkt->data + offset,
+         s->expired_scan_cycle = REGULAR_PACKET_CHECK_MS;
-+        return memcmp(ppkt->data + offset,
+     }
-+                      spkt->data + offset,
                        spkt->size - offset);
      } else {
          trace_colo_compare_main("Net packet size are not the same");
@@ -XXX,XX +XXX,XX @@ static int colo_packet_compare_tcp(Packet *spkt, Packet *ppkt)
       */
      if (ptcp->th_off > 5) {
          ptrdiff_t tcp_offset;
 +
          tcp_offset = ppkt->transport_header - (uint8_t *)ppkt->data
 -                     + (ptcp->th_off * 4);
 +                     + (ptcp->th_off * 4) - ppkt->vnet_hdr_len;
          res = colo_packet_compare_common(ppkt, spkt, tcp_offset);
      } else if (ptcp->th_sum == stcp->th_sum) {
          res = colo_packet_compare_common(ppkt, spkt, ETH_HLEN);
 --
 .7.4

-[Qemu-devel] [PULL 03/14] net/filter-mirror.c: Introduce parameter for filter_send()
+[PULL 06/13] net/filter: Optimize filter_send to coroutine
-From: Zhang Chen <zhangchen.fnst@cn.fujitsu.com>
+From: Rao Lei <lei.rao@intel.com>
-This patch change the filter_send() parameter from CharBackend to MirrorState,
+This patch is to improve the logic of QEMU main thread sleep code in
-we can get more information like vnet_hdr(We use it to support packet with vnet_header).
+qemu_chr_write_buffer() where it can be blocked and can't run other
 coroutines during COLO IO stress test.
-Signed-off-by: Zhang Chen <zhangchen.fnst@cn.fujitsu.com>
+Our approach is to put filter_send() in a coroutine. In this way,
 filter_send() will call qemu_coroutine_yield() in qemu_co_sleep_ns(),
 so that it can be scheduled out and QEMU main thread has opportunity to
 run other tasks.
 Signed-off-by: Lei Rao <lei.rao@intel.com>
 Signed-off-by: Zhang Chen <chen.zhang@intel.com>
 Reviewed-by: Li Zhijian <lizhijian@fujitsu.com>
 Reviewed-by: Zhang Chen <chen.zhang@intel.com>
 Signed-off-by: Jason Wang <jasowang@redhat.com>
 ---
- net/filter-mirror.c | 10 +++++-----
+ net/filter-mirror.c | 66 ++++++++++++++++++++++++++++++++++++++++++-----------
-file changed, 5 insertions(+), 5 deletions(-)
+file changed, 53 insertions(+), 13 deletions(-)
 diff --git a/net/filter-mirror.c b/net/filter-mirror.c
 index XXXXXXX..XXXXXXX 100644
 --- a/net/filter-mirror.c
 +++ b/net/filter-mirror.c
-@@ -XXX,XX +XXX,XX @@ typedef struct MirrorState {
+@@ -XXX,XX +XXX,XX @@
-     SocketReadState rs;
+ #include "chardev/char-fe.h"
- } MirrorState;
+ #include "qemu/iov.h"
+ #include "qemu/sockets.h"
--static int filter_send(CharBackend *chr_out,
++#include "block/aio-wait.h"
-+static int filter_send(MirrorState *s,
-                        const struct iovec *iov,
+ #define TYPE_FILTER_MIRROR "filter-mirror"
-                        int iovcnt)
+ typedef struct MirrorState MirrorState;
@@ -XXX,XX +XXX,XX @@ struct MirrorState {
      bool vnet_hdr;
  };
 -static int filter_send(MirrorState *s,
 -                       const struct iovec *iov,
 -                       int iovcnt)
 +typedef struct FilterSendCo {
 +    MirrorState *s;
 +    char *buf;
 +    ssize_t size;
 +    bool done;
 +    int ret;
 +} FilterSendCo;
 +
 +static int _filter_send(MirrorState *s,
 +                       char *buf,
 +                       ssize_t size)
  {
-@@ -XXX,XX +XXX,XX @@ static int filter_send(CharBackend *chr_out,
+     NetFilterState *nf = NETFILTER(s);
      int ret = 0;
 -    ssize_t size = 0;
      uint32_t len = 0;
 -    char *buf;
 -
 -    size = iov_size(iov, iovcnt);
 -    if (!size) {
 -        return 0;
 -    }
      len = htonl(size);
      ret = qemu_chr_fe_write_all(&s->chr_out, (uint8_t *)&len, sizeof(len));
@@ -XXX,XX +XXX,XX @@ static int filter_send(MirrorState *s,
          }
      }
-     len = htonl(size);
+-    buf = g_malloc(size);
--    ret = qemu_chr_fe_write_all(chr_out, (uint8_t *)&len, sizeof(len));
+-    iov_to_buf(iov, iovcnt, 0, buf, size);
-+    ret = qemu_chr_fe_write_all(&s->chr_out, (uint8_t *)&len, sizeof(len));
+     ret = qemu_chr_fe_write_all(&s->chr_out, (uint8_t *)buf, size);
-     if (ret != sizeof(len)) {
+-    g_free(buf);
      if (ret != size) {
          goto err;
      }
+@@ -XXX,XX +XXX,XX @@ err:
-     buf = g_malloc(size);
+     return ret < 0 ? ret : -EIO;
-     iov_to_buf(iov, iovcnt, 0, buf, size);
+ }
--    ret = qemu_chr_fe_write_all(chr_out, (uint8_t *)buf, size);
-+    ret = qemu_chr_fe_write_all(&s->chr_out, (uint8_t *)buf, size);
++static void coroutine_fn filter_send_co(void *opaque)
-     g_free(buf);
++{
-     if (ret != size) {
++    FilterSendCo *data = opaque;
-         goto err;
++
-@@ -XXX,XX +XXX,XX @@ static ssize_t filter_mirror_receive_iov(NetFilterState *nf,
++    data->ret = _filter_send(data->s, data->buf, data->size);
-     MirrorState *s = FILTER_MIRROR(nf);
++    data->done = true;
-     int ret;
++    g_free(data->buf);
++    aio_wait_kick();
--    ret = filter_send(&s->chr_out, iov, iovcnt);
++}
-+    ret = filter_send(s, iov, iovcnt);
++
-     if (ret) {
++static int filter_send(MirrorState *s,
-         error_report("filter mirror send failed(%s)", strerror(-ret));
++                       const struct iovec *iov,
-     }
++                       int iovcnt)
-@@ -XXX,XX +XXX,XX @@ static ssize_t filter_redirector_receive_iov(NetFilterState *nf,
++{
-     int ret;
++    ssize_t size = iov_size(iov, iovcnt);
++    char *buf = NULL;
-     if (qemu_chr_fe_backend_connected(&s->chr_out)) {
++
--        ret = filter_send(&s->chr_out, iov, iovcnt);
++    if (!size) {
-+        ret = filter_send(s, iov, iovcnt);
++        return 0;
-         if (ret) {
++    }
-             error_report("filter redirector send failed(%s)", strerror(-ret));
++
-         }
++    buf = g_malloc(size);
 +    iov_to_buf(iov, iovcnt, 0, buf, size);
 +
 +    FilterSendCo data = {
 +        .s = s,
 +        .size = size,
 +        .buf = buf,
 +        .ret = 0,
 +    };
 +
 +    Coroutine *co = qemu_coroutine_create(filter_send_co, &data);
 +    qemu_coroutine_enter(co);
 +
 +    while (!data.done) {
 +        aio_poll(qemu_get_aio_context(), true);
 +    }
 +
 +    return data.ret;
 +}
 +
  static void redirector_to_filter(NetFilterState *nf,
                                   const uint8_t *buf,
                                   int len)
 --
 .7.4

-[Qemu-devel] [PULL 09/14] net/colo.c: Add vnet packet parse feature in colo-proxy
+[PULL 07/13] net/vmnet: add vmnet dependency and customizable option
-From: Zhang Chen <zhangchen.fnst@cn.fujitsu.com>
+From: Vladislav Yaroshchuk <yaroshchuk2000@gmail.com>
-Make colo-compare and filter-rewriter can parse vnet packet.
+Signed-off-by: Vladislav Yaroshchuk <yaroshchuk2000@gmail.com>
 Signed-off-by: Zhang Chen <zhangchen.fnst@cn.fujitsu.com>
 Signed-off-by: Jason Wang <jasowang@redhat.com>
 ---
- net/colo.c | 6 +++---
+ meson.build                   | 4 ++++
-file changed, 3 insertions(+), 3 deletions(-)
+ meson_options.txt             | 2 ++
  scripts/meson-buildoptions.sh | 3 +++
 files changed, 9 insertions(+)
-diff --git a/net/colo.c b/net/colo.c
+diff --git a/meson.build b/meson.build
 index XXXXXXX..XXXXXXX 100644
---- a/net/colo.c
+--- a/meson.build
-+++ b/net/colo.c
++++ b/meson.build
-@@ -XXX,XX +XXX,XX @@ int parse_packet_early(Packet *pkt)
+@@ -XXX,XX +XXX,XX @@ if cocoa.found() and get_option('gtk').enabled()
- {
+   error('Cocoa and GTK+ cannot be enabled at the same time')
-     int network_length;
+ endif
-     static const uint8_t vlan[] = {0x81, 0x00};
--    uint8_t *data = pkt->data;
++vmnet = dependency('appleframeworks', modules: 'vmnet', required: get_option('vmnet'))
-+    uint8_t *data = pkt->data + pkt->vnet_hdr_len;
++
-     uint16_t l3_proto;
+ seccomp = not_found
-     ssize_t l2hdr_len = eth_get_l2_hdr_length(data);
+ if not get_option('seccomp').auto() or have_system or have_tools
+   seccomp = dependency('libseccomp', version: '>=2.3.0',
--    if (pkt->size < ETH_HLEN) {
+@@ -XXX,XX +XXX,XX @@ config_host_data.set('CONFIG_SECCOMP', seccomp.found())
-+    if (pkt->size < ETH_HLEN + pkt->vnet_hdr_len) {
+ config_host_data.set('CONFIG_SNAPPY', snappy.found())
-         trace_colo_proxy_main("pkt->size < ETH_HLEN");
+ config_host_data.set('CONFIG_USB_LIBUSB', libusb.found())
-         return 1;
+ config_host_data.set('CONFIG_VDE', vde.found())
-     }
++config_host_data.set('CONFIG_VMNET', vmnet.found())
-@@ -XXX,XX +XXX,XX @@ int parse_packet_early(Packet *pkt)
+ config_host_data.set('CONFIG_VHOST_USER_BLK_SERVER', have_vhost_user_blk_server)
-     }
+ config_host_data.set('CONFIG_VNC', vnc.found())
+ config_host_data.set('CONFIG_VNC_JPEG', jpeg.found())
-     network_length = pkt->ip->ip_hl * 4;
+@@ -XXX,XX +XXX,XX @@ endif
--    if (pkt->size < l2hdr_len + network_length) {
+ summary_info += {'JACK support':      jack}
-+    if (pkt->size < l2hdr_len + network_length + pkt->vnet_hdr_len) {
+ summary_info += {'brlapi support':    brlapi}
-         trace_colo_proxy_main("pkt->size < network_header + network_length");
+ summary_info += {'vde support':       vde}
-         return 1;
++summary_info += {'vmnet.framework support': vmnet}
-     }
+ summary_info += {'netmap support':    have_netmap}
  summary_info += {'l2tpv3 support':    have_l2tpv3}
  summary_info += {'Linux AIO support': libaio}
 diff --git a/meson_options.txt b/meson_options.txt
 index XXXXXXX..XXXXXXX 100644
 --- a/meson_options.txt
 +++ b/meson_options.txt
@@ -XXX,XX +XXX,XX @@ option('netmap', type : 'feature', value : 'auto',
         description: 'netmap network backend support')
  option('vde', type : 'feature', value : 'auto',
         description: 'vde network backend support')
 +option('vmnet', type : 'feature', value : 'auto',
 +       description: 'vmnet.framework network backend support')
  option('virglrenderer', type : 'feature', value : 'auto',
         description: 'virgl rendering support')
  option('vnc', type : 'feature', value : 'auto',
 diff --git a/scripts/meson-buildoptions.sh b/scripts/meson-buildoptions.sh
 index XXXXXXX..XXXXXXX 100644
 --- a/scripts/meson-buildoptions.sh
 +++ b/scripts/meson-buildoptions.sh
@@ -XXX,XX +XXX,XX @@ meson_options_help() {
    printf "%s\n" '  u2f             U2F emulation support'
    printf "%s\n" '  usb-redir       libusbredir support'
    printf "%s\n" '  vde             vde network backend support'
 +  printf "%s\n" '  vmnet           vmnet.framework network backend support'
    printf "%s\n" '  vhost-user-blk-server'
    printf "%s\n" '                  build vhost-user-blk server'
    printf "%s\n" '  virglrenderer   virgl rendering support'
@@ -XXX,XX +XXX,XX @@ _meson_option_parse() {
      --disable-usb-redir) printf "%s" -Dusb_redir=disabled ;;
      --enable-vde) printf "%s" -Dvde=enabled ;;
      --disable-vde) printf "%s" -Dvde=disabled ;;
 +    --enable-vmnet) printf "%s" -Dvmnet=enabled ;;
 +    --disable-vmnet) printf "%s" -Dvmnet=disabled ;;
      --enable-vhost-user-blk-server) printf "%s" -Dvhost_user_blk_server=enabled ;;
      --disable-vhost-user-blk-server) printf "%s" -Dvhost_user_blk_server=disabled ;;
      --enable-virglrenderer) printf "%s" -Dvirglrenderer=enabled ;;
 --
 .7.4

-[Qemu-devel] [PULL 02/14] net/net.c: Add vnet_hdr support in SocketReadState
+[PULL 08/13] net/vmnet: add vmnet backends to qapi/net
-From: Zhang Chen <zhangchen.fnst@cn.fujitsu.com>
+From: Vladislav Yaroshchuk <yaroshchuk2000@gmail.com>
-We add a flag to decide whether net_fill_rstate() need read
+The vmnet framework is an API for virtual machines to read and write
-the vnet_hdr_len or not.
+packets.
-Signed-off-by: Zhang Chen <zhangchen.fnst@cn.fujitsu.com>
+The API allows a Guest OS interface to be in host mode or shared
-Suggested-by: Jason Wang <jasowang@redhat.com>
+mode. Interfaces in host mode can communicate with the native host
 system and other interfaces running in host mode. In shared mode, the
 network interface can send and receive packets to the Internet, the
 native host, and other interfaces running in sharing mode.
 Create separate netdevs for each vmnet operating mode:
 - vmnet-host
 - vmnet-shared
 - vmnet-bridged
 Signed-off-by: Vladislav Yaroshchuk <yaroshchuk2000@gmail.com>
 Signed-off-by: Jason Wang <jasowang@redhat.com>
 ---
- include/net/net.h   |  9 +++++++--
+ net/clients.h       |  11 +++++
- net/colo-compare.c  |  4 ++--
+ net/meson.build     |   7 +++
- net/filter-mirror.c |  2 +-
+ net/net.c           |  10 ++++
- net/net.c           | 36 ++++++++++++++++++++++++++++++++----
+ net/vmnet-bridged.m |  25 ++++++++++
- net/socket.c        |  8 ++++----
+ net/vmnet-common.m  |  19 ++++++++
-files changed, 46 insertions(+), 13 deletions(-)
+ net/vmnet-host.c    |  24 ++++++++++
+ net/vmnet-shared.c  |  25 ++++++++++
-diff --git a/include/net/net.h b/include/net/net.h
+ net/vmnet_int.h     |  25 ++++++++++
  qapi/net.json       | 132 +++++++++++++++++++++++++++++++++++++++++++++++++++-
 files changed, 276 insertions(+), 2 deletions(-)
  create mode 100644 net/vmnet-bridged.m
  create mode 100644 net/vmnet-common.m
  create mode 100644 net/vmnet-host.c
  create mode 100644 net/vmnet-shared.c
  create mode 100644 net/vmnet_int.h
 diff --git a/net/clients.h b/net/clients.h
 index XXXXXXX..XXXXXXX 100644
---- a/include/net/net.h
+--- a/net/clients.h
-+++ b/include/net/net.h
++++ b/net/clients.h
-@@ -XXX,XX +XXX,XX @@ typedef struct NICState {
+@@ -XXX,XX +XXX,XX @@ int net_init_vhost_user(const Netdev *netdev, const char *name,
- } NICState;
+ int net_init_vhost_vdpa(const Netdev *netdev, const char *name,
- struct SocketReadState {
+                         NetClientState *peer, Error **errp);
--    int state; /* 0 = getting length, 1 = getting data */
++#ifdef CONFIG_VMNET
-+    /* 0 = getting length, 1 = getting vnet header length, 2 = getting data */
++int net_init_vmnet_host(const Netdev *netdev, const char *name,
-+    int state;
++                          NetClientState *peer, Error **errp);
-+    /* This flag decide whether to read the vnet_hdr_len field */
++
-+    bool vnet_hdr;
++int net_init_vmnet_shared(const Netdev *netdev, const char *name,
-     uint32_t index;
++                          NetClientState *peer, Error **errp);
-     uint32_t packet_len;
++
-+    uint32_t vnet_hdr_len;
++int net_init_vmnet_bridged(const Netdev *netdev, const char *name,
-     uint8_t buf[NET_BUFSIZE];
++                          NetClientState *peer, Error **errp);
-     SocketReadStateFinalize *finalize;
++#endif /* CONFIG_VMNET */
- };
++
-@@ -XXX,XX +XXX,XX @@ ssize_t qemu_deliver_packet_iov(NetClientState *sender,
+ #endif /* QEMU_NET_CLIENTS_H */
- void print_net_client(Monitor *mon, NetClientState *nc);
+diff --git a/net/meson.build b/net/meson.build
  void hmp_info_network(Monitor *mon, const QDict *qdict);
  void net_socket_rs_init(SocketReadState *rs,
 -                        SocketReadStateFinalize *finalize);
 +                        SocketReadStateFinalize *finalize,
 +                        bool vnet_hdr);
  /* NIC info */
 diff --git a/net/colo-compare.c b/net/colo-compare.c
 index XXXXXXX..XXXXXXX 100644
---- a/net/colo-compare.c
+--- a/net/meson.build
-+++ b/net/colo-compare.c
++++ b/net/meson.build
-@@ -XXX,XX +XXX,XX @@ static void colo_compare_complete(UserCreatable *uc, Error **errp)
+@@ -XXX,XX +XXX,XX @@ softmmu_ss.add(when: 'CONFIG_POSIX', if_true: files(tap_posix))
-         return;
+ softmmu_ss.add(when: 'CONFIG_WIN32', if_true: files('tap-win32.c'))
-     }
+ softmmu_ss.add(when: 'CONFIG_VHOST_NET_VDPA', if_true: files('vhost-vdpa.c'))
--    net_socket_rs_init(&s->pri_rs, compare_pri_rs_finalize);
++vmnet_files = files(
--    net_socket_rs_init(&s->sec_rs, compare_sec_rs_finalize);
++  'vmnet-common.m',
-+    net_socket_rs_init(&s->pri_rs, compare_pri_rs_finalize, false);
++  'vmnet-bridged.m',
-+    net_socket_rs_init(&s->sec_rs, compare_sec_rs_finalize, false);
++  'vmnet-host.c',
++  'vmnet-shared.c'
-     g_queue_init(&s->conn_list);
++)
++softmmu_ss.add(when: vmnet, if_true: vmnet_files)
-diff --git a/net/filter-mirror.c b/net/filter-mirror.c
+ subdir('can')
 index XXXXXXX..XXXXXXX 100644
 --- a/net/filter-mirror.c
 +++ b/net/filter-mirror.c
@@ -XXX,XX +XXX,XX @@ static void filter_redirector_setup(NetFilterState *nf, Error **errp)
          }
      }
 -    net_socket_rs_init(&s->rs, redirector_rs_finalize);
 +    net_socket_rs_init(&s->rs, redirector_rs_finalize, false);
      if (s->indev) {
          chr = qemu_chr_find(s->indev);
 diff --git a/net/net.c b/net/net.c
 index XXXXXXX..XXXXXXX 100644
 --- a/net/net.c
 +++ b/net/net.c
-@@ -XXX,XX +XXX,XX @@ QemuOptsList qemu_net_opts = {
+@@ -XXX,XX +XXX,XX @@ static int (* const net_client_init_fun[NET_CLIENT_DRIVER__MAX])(
  #ifdef CONFIG_L2TPV3
          [NET_CLIENT_DRIVER_L2TPV3]    = net_init_l2tpv3,
  #endif
 +#ifdef CONFIG_VMNET
 +        [NET_CLIENT_DRIVER_VMNET_HOST] = net_init_vmnet_host,
 +        [NET_CLIENT_DRIVER_VMNET_SHARED] = net_init_vmnet_shared,
 +        [NET_CLIENT_DRIVER_VMNET_BRIDGED] = net_init_vmnet_bridged,
 +#endif /* CONFIG_VMNET */
  };
- void net_socket_rs_init(SocketReadState *rs,
--                        SocketReadStateFinalize *finalize)
+@@ -XXX,XX +XXX,XX @@ void show_netdevs(void)
-+                        SocketReadStateFinalize *finalize,
+ #ifdef CONFIG_VHOST_VDPA
-+                        bool vnet_hdr)
+         "vhost-vdpa",
- {
+ #endif
-     rs->state = 0;
++#ifdef CONFIG_VMNET
-+    rs->vnet_hdr = vnet_hdr;
++        "vmnet-host",
-     rs->index = 0;
++        "vmnet-shared",
-     rs->packet_len = 0;
++        "vmnet-bridged",
-+    rs->vnet_hdr_len = 0;
++#endif
-     memset(rs->buf, 0, sizeof(rs->buf));
+     };
-     rs->finalize = finalize;
- }
+     qemu_printf("Available netdev backend types:\n");
-@@ -XXX,XX +XXX,XX @@ int net_fill_rstate(SocketReadState *rs, const uint8_t *buf, int size)
+diff --git a/net/vmnet-bridged.m b/net/vmnet-bridged.m
-     unsigned int l;
+new file mode 100644
+index XXXXXXX..XXXXXXX
-     while (size > 0) {
+--- /dev/null
--        /* reassemble a packet from the network */
++++ b/net/vmnet-bridged.m
--        switch (rs->state) { /* 0 = getting length, 1 = getting data */
+@@ -XXX,XX +XXX,XX @@
-+        /* Reassemble a packet from the network.
++/*
-+         * 0 = getting length.
++ * vmnet-bridged.m
-+         * 1 = getting vnet header length.
++ *
-+         * 2 = getting data.
++ * Copyright(c) 2021 Vladislav Yaroshchuk <yaroshchuk2000@gmail.com>
-+         */
++ *
-+        switch (rs->state) {
++ * This work is licensed under the terms of the GNU GPL, version 2 or later.
-         case 0:
++ * See the COPYING file in the top-level directory.
-             l = 4 - rs->index;
++ *
-             if (l > size) {
++ */
-@@ -XXX,XX +XXX,XX @@ int net_fill_rstate(SocketReadState *rs, const uint8_t *buf, int size)
++
-                 /* got length */
++#include "qemu/osdep.h"
-                 rs->packet_len = ntohl(*(uint32_t *)rs->buf);
++#include "qapi/qapi-types-net.h"
-                 rs->index = 0;
++#include "vmnet_int.h"
--                rs->state = 1;
++#include "clients.h"
-+                if (rs->vnet_hdr) {
++#include "qemu/error-report.h"
-+                    rs->state = 1;
++#include "qapi/error.h"
-+                } else {
++
-+                    rs->state = 2;
++#include <vmnet/vmnet.h>
-+                    rs->vnet_hdr_len = 0;
++
-+                }
++int net_init_vmnet_bridged(const Netdev *netdev, const char *name,
-             }
++                           NetClientState *peer, Error **errp)
-             break;
++{
-         case 1:
++  error_setg(errp, "vmnet-bridged is not implemented yet");
-+            l = 4 - rs->index;
++  return -1;
-+            if (l > size) {
++}
-+                l = size;
+diff --git a/net/vmnet-common.m b/net/vmnet-common.m
-+            }
+new file mode 100644
-+            memcpy(rs->buf + rs->index, buf, l);
+index XXXXXXX..XXXXXXX
-+            buf += l;
+--- /dev/null
-+            size -= l;
++++ b/net/vmnet-common.m
-+            rs->index += l;
+@@ -XXX,XX +XXX,XX @@
-+            if (rs->index == 4) {
++/*
-+                /* got vnet header length */
++ * vmnet-common.m - network client wrapper for Apple vmnet.framework
-+                rs->vnet_hdr_len = ntohl(*(uint32_t *)rs->buf);
++ *
-+                rs->index = 0;
++ * Copyright(c) 2021 Vladislav Yaroshchuk <yaroshchuk2000@gmail.com>
-+                rs->state = 2;
++ * Copyright(c) 2021 Phillip Tennen <phillip@axleos.com>
-+            }
++ *
-+            break;
++ * This work is licensed under the terms of the GNU GPL, version 2 or later.
-+        case 2:
++ * See the COPYING file in the top-level directory.
-             l = rs->packet_len - rs->index;
++ *
-             if (l > size) {
++ */
-                 l = size;
++
-diff --git a/net/socket.c b/net/socket.c
++#include "qemu/osdep.h"
 +#include "qapi/qapi-types-net.h"
 +#include "vmnet_int.h"
 +#include "clients.h"
 +#include "qemu/error-report.h"
 +#include "qapi/error.h"
 +
 +#include <vmnet/vmnet.h>
 diff --git a/net/vmnet-host.c b/net/vmnet-host.c
 new file mode 100644
 index XXXXXXX..XXXXXXX
 --- /dev/null
 +++ b/net/vmnet-host.c
@@ -XXX,XX +XXX,XX @@
 +/*
 + * vmnet-host.c
 + *
 + * Copyright(c) 2021 Vladislav Yaroshchuk <yaroshchuk2000@gmail.com>
 + *
 + * This work is licensed under the terms of the GNU GPL, version 2 or later.
 + * See the COPYING file in the top-level directory.
 + *
 + */
 +
 +#include "qemu/osdep.h"
 +#include "qapi/qapi-types-net.h"
 +#include "vmnet_int.h"
 +#include "clients.h"
 +#include "qemu/error-report.h"
 +#include "qapi/error.h"
 +
 +#include <vmnet/vmnet.h>
 +
 +int net_init_vmnet_host(const Netdev *netdev, const char *name,
 +                        NetClientState *peer, Error **errp) {
 +  error_setg(errp, "vmnet-host is not implemented yet");
 +  return -1;
 +}
 diff --git a/net/vmnet-shared.c b/net/vmnet-shared.c
 new file mode 100644
 index XXXXXXX..XXXXXXX
 --- /dev/null
 +++ b/net/vmnet-shared.c
@@ -XXX,XX +XXX,XX @@
 +/*
 + * vmnet-shared.c
 + *
 + * Copyright(c) 2021 Vladislav Yaroshchuk <yaroshchuk2000@gmail.com>
 + *
 + * This work is licensed under the terms of the GNU GPL, version 2 or later.
 + * See the COPYING file in the top-level directory.
 + *
 + */
 +
 +#include "qemu/osdep.h"
 +#include "qapi/qapi-types-net.h"
 +#include "vmnet_int.h"
 +#include "clients.h"
 +#include "qemu/error-report.h"
 +#include "qapi/error.h"
 +
 +#include <vmnet/vmnet.h>
 +
 +int net_init_vmnet_shared(const Netdev *netdev, const char *name,
 +                          NetClientState *peer, Error **errp)
 +{
 +  error_setg(errp, "vmnet-shared is not implemented yet");
 +  return -1;
 +}
 diff --git a/net/vmnet_int.h b/net/vmnet_int.h
 new file mode 100644
 index XXXXXXX..XXXXXXX
 --- /dev/null
 +++ b/net/vmnet_int.h
@@ -XXX,XX +XXX,XX @@
 +/*
 + * vmnet_int.h
 + *
 + * Copyright(c) 2021 Vladislav Yaroshchuk <yaroshchuk2000@gmail.com>
 + *
 + * This work is licensed under the terms of the GNU GPL, version 2 or later.
 + * See the COPYING file in the top-level directory.
 + *
 + */
 +#ifndef VMNET_INT_H
 +#define VMNET_INT_H
 +
 +#include "qemu/osdep.h"
 +#include "vmnet_int.h"
 +#include "clients.h"
 +
 +#include <vmnet/vmnet.h>
 +
 +typedef struct VmnetCommonState {
 +  NetClientState nc;
 +
 +} VmnetCommonState;
 +
 +
 +#endif /* VMNET_INT_H */
 diff --git a/qapi/net.json b/qapi/net.json
 index XXXXXXX..XXXXXXX 100644
---- a/net/socket.c
+--- a/qapi/net.json
-+++ b/net/socket.c
++++ b/qapi/net.json
-@@ -XXX,XX +XXX,XX @@ static void net_socket_send(void *opaque)
+@@ -XXX,XX +XXX,XX @@
-         closesocket(s->fd);
+     '*queues':       'int' } }
-         s->fd = -1;
+ ##
--        net_socket_rs_init(&s->rs, net_socket_rs_finalize);
++# @NetdevVmnetHostOptions:
-+        net_socket_rs_init(&s->rs, net_socket_rs_finalize, false);
++#
-         s->nc.link_down = true;
++# vmnet (host mode) network backend.
-         memset(s->nc.info_str, 0, sizeof(s->nc.info_str));
++#
++# Allows the vmnet interface to communicate with other vmnet
-@@ -XXX,XX +XXX,XX @@ static NetSocketState *net_socket_fd_init_dgram(NetClientState *peer,
++# interfaces that are in host mode and also with the host.
-     s->fd = fd;
++#
-     s->listen_fd = -1;
++# @start-address: The starting IPv4 address to use for the interface.
-     s->send_fn = net_socket_send_dgram;
++#                 Must be in the private IP range (RFC 1918). Must be
--    net_socket_rs_init(&s->rs, net_socket_rs_finalize);
++#                 specified along with @end-address and @subnet-mask.
-+    net_socket_rs_init(&s->rs, net_socket_rs_finalize, false);
++#                 This address is used as the gateway address. The
-     net_socket_read_poll(s, true);
++#                 subsequent address up to and including end-address are
++#                 placed in the DHCP pool.
-     /* mcast: save bound address as dst */
++#
-@@ -XXX,XX +XXX,XX @@ static NetSocketState *net_socket_fd_init_stream(NetClientState *peer,
++# @end-address: The DHCP IPv4 range end address to use for the
++#               interface. Must be in the private IP range (RFC 1918).
-     s->fd = fd;
++#               Must be specified along with @start-address and
-     s->listen_fd = -1;
++#               @subnet-mask.
--    net_socket_rs_init(&s->rs, net_socket_rs_finalize);
++#
-+    net_socket_rs_init(&s->rs, net_socket_rs_finalize, false);
++# @subnet-mask: The IPv4 subnet mask to use on the interface. Must
++#               be specified along with @start-address and @subnet-mask.
-     /* Disable Nagle algorithm on TCP sockets to reduce latency */
++#
-     socket_set_nodelay(fd);
++# @isolated: Enable isolation for this interface. Interface isolation
-@@ -XXX,XX +XXX,XX @@ static int net_socket_listen_init(NetClientState *peer,
++#            ensures that vmnet interface is not able to communicate
-     s->fd = -1;
++#            with any other vmnet interfaces. Only communication with
-     s->listen_fd = fd;
++#            host is allowed.
-     s->nc.link_down = true;
++#
--    net_socket_rs_init(&s->rs, net_socket_rs_finalize);
++# @net-uuid: The identifier (UUID) to uniquely identify the isolated
-+    net_socket_rs_init(&s->rs, net_socket_rs_finalize, false);
++#            network vmnet interface should be added to. If
++#            set, no DHCP service is provided for this interface and
-     qemu_set_fd_handler(s->listen_fd, net_socket_accept, NULL, s);
++#            network communication is allowed only with other interfaces
-     return 0;
++#            added to this network identified by the UUID.
 +#
 +# Since: 7.0
 +##
 +{ 'struct': 'NetdevVmnetHostOptions',
 +  'data': {
 +    '*start-address': 'str',
 +    '*end-address':   'str',
 +    '*subnet-mask':   'str',
 +    '*isolated':      'bool',
 +    '*net-uuid':      'str' },
 +  'if': 'CONFIG_VMNET' }
 +
 +##
 +# @NetdevVmnetSharedOptions:
 +#
 +# vmnet (shared mode) network backend.
 +#
 +# Allows traffic originating from the vmnet interface to reach the
 +# Internet through a network address translator (NAT).
 +# The vmnet interface can communicate with the host and with
 +# other shared mode interfaces on the same subnet. If no DHCP
 +# settings, subnet mask and IPv6 prefix specified, the interface can
 +# communicate with any of other interfaces in shared mode.
 +#
 +# @start-address: The starting IPv4 address to use for the interface.
 +#                 Must be in the private IP range (RFC 1918). Must be
 +#                 specified along with @end-address and @subnet-mask.
 +#                 This address is used as the gateway address. The
 +#                 subsequent address up to and including end-address are
 +#                 placed in the DHCP pool.
 +#
 +# @end-address: The DHCP IPv4 range end address to use for the
 +#               interface. Must be in the private IP range (RFC 1918).
 +#               Must be specified along with @start-address and @subnet-mask.
 +#
 +# @subnet-mask: The IPv4 subnet mask to use on the interface. Must
 +#                be specified along with @start-address and @subnet-mask.
 +#
 +# @isolated: Enable isolation for this interface. Interface isolation
 +#            ensures that vmnet interface is not able to communicate
 +#            with any other vmnet interfaces. Only communication with
 +#            host is allowed.
 +#
 +# @nat66-prefix: The IPv6 prefix to use into guest network. Must be a
 +#                unique local address i.e. start with fd00::/8 and have
 +#                length of 64.
 +#
 +# Since: 7.0
 +##
 +{ 'struct': 'NetdevVmnetSharedOptions',
 +  'data': {
 +    '*start-address': 'str',
 +    '*end-address':   'str',
 +    '*subnet-mask':   'str',
 +    '*isolated':      'bool',
 +    '*nat66-prefix':  'str' },
 +  'if': 'CONFIG_VMNET' }
 +
 +##
 +# @NetdevVmnetBridgedOptions:
 +#
 +# vmnet (bridged mode) network backend.
 +#
 +# Bridges the vmnet interface with a physical network interface.
 +#
 +# @ifname: The name of the physical interface to be bridged.
 +#
 +# @isolated: Enable isolation for this interface. Interface isolation
 +#            ensures that vmnet interface is not able to communicate
 +#            with any other vmnet interfaces. Only communication with
 +#            host is allowed.
 +#
 +# Since: 7.0
 +##
 +{ 'struct': 'NetdevVmnetBridgedOptions',
 +  'data': {
 +    'ifname':     'str',
 +    '*isolated':  'str' },
 +  'if': 'CONFIG_VMNET' }
 +
 +##
  # @NetClientDriver:
  #
  # Available netdev drivers.
@@ -XXX,XX +XXX,XX @@
  # Since: 2.7
  #
  #        @vhost-vdpa since 5.1
 +#        @vmnet-host since 7.0
 +#        @vmnet-shared since 7.0
 +#        @vmnet-bridged since 7.0
  ##
  { 'enum': 'NetClientDriver',
    'data': [ 'none', 'nic', 'user', 'tap', 'l2tpv3', 'socket', 'vde',
 -            'bridge', 'hubport', 'netmap', 'vhost-user', 'vhost-vdpa' ] }
 +            'bridge', 'hubport', 'netmap', 'vhost-user', 'vhost-vdpa',
 +            { 'name': 'vmnet-host', 'if': 'CONFIG_VMNET' },
 +            { 'name': 'vmnet-shared', 'if': 'CONFIG_VMNET' },
 +            { 'name': 'vmnet-bridged', 'if': 'CONFIG_VMNET' }] }
  ##
  # @Netdev:
@@ -XXX,XX +XXX,XX @@
  # Since: 1.2
  #
  #        'l2tpv3' - since 2.1
 +#        'vmnet-host' - since 7.0
 +#        'vmnet-shared' - since 7.0
 +#        'vmnet-bridged' - since 7.0
  ##
  { 'union': 'Netdev',
    'base': { 'id': 'str', 'type': 'NetClientDriver' },
@@ -XXX,XX +XXX,XX @@
      'hubport':  'NetdevHubPortOptions',
      'netmap':   'NetdevNetmapOptions',
      'vhost-user': 'NetdevVhostUserOptions',
 -    'vhost-vdpa': 'NetdevVhostVDPAOptions' } }
 +    'vhost-vdpa': 'NetdevVhostVDPAOptions',
 +    'vmnet-host': { 'type': 'NetdevVmnetHostOptions',
 +                    'if': 'CONFIG_VMNET' },
 +    'vmnet-shared': { 'type': 'NetdevVmnetSharedOptions',
 +                      'if': 'CONFIG_VMNET' },
 +    'vmnet-bridged': { 'type': 'NetdevVmnetBridgedOptions',
 +                       'if': 'CONFIG_VMNET' } } }
  ##
  # @RxState:
 --
 .7.4

-[Qemu-devel] [PULL 07/14] net/colo-compare.c: Introduce parameter for compare_chr_send()
+[PULL 09/13] net/vmnet: implement shared mode (vmnet-shared)
-From: Zhang Chen <zhangchen.fnst@cn.fujitsu.com>
+From: Vladislav Yaroshchuk <yaroshchuk2000@gmail.com>
-This patch change the compare_chr_send() parameter from CharBackend to CompareState,
+Interaction with vmnet.framework in different modes
-we can get more information like vnet_hdr(We use it to support packet with vnet_header).
+differs only on configuration stage, so we can create
+common `send`, `receive`, etc. procedures and reuse them.
-Signed-off-by: Zhang Chen <zhangchen.fnst@cn.fujitsu.com>
 vmnet.framework supports iov, but writing more than
 one iov into vmnet interface fails with
 'VMNET_INVALID_ARGUMENT'. Collecting provided iovs into
 one and passing it to vmnet works fine. That's the
 reason why receive_iov() left unimplemented. But it still
 works with good enough performance having .receive()
 implemented only.
 Also, there is no way to unsubscribe from vmnet packages
 receiving except registering and unregistering event
 callback or simply drop packages just ignoring and
 not processing them when related flag is set. Here we do
 using the second way.
 Signed-off-by: Phillip Tennen <phillip@axleos.com>
 Signed-off-by: Vladislav Yaroshchuk <yaroshchuk2000@gmail.com>
 Signed-off-by: Jason Wang <jasowang@redhat.com>
 ---
- net/colo-compare.c | 14 +++++++-------
+ net/vmnet-common.m | 311 +++++++++++++++++++++++++++++++++++++++++++++++++++++
-file changed, 7 insertions(+), 7 deletions(-)
+ net/vmnet-shared.c |  74 ++++++++++++-
+ net/vmnet_int.h    |  23 ++++
-diff --git a/net/colo-compare.c b/net/colo-compare.c
+files changed, 404 insertions(+), 4 deletions(-)
 diff --git a/net/vmnet-common.m b/net/vmnet-common.m
 index XXXXXXX..XXXXXXX 100644
---- a/net/colo-compare.c
+--- a/net/vmnet-common.m
-+++ b/net/colo-compare.c
++++ b/net/vmnet-common.m
-@@ -XXX,XX +XXX,XX @@ enum {
+@@ -XXX,XX +XXX,XX @@
-     SECONDARY_IN,
+  */
- };
+ #include "qemu/osdep.h"
--static int compare_chr_send(CharBackend *out,
++#include "qemu/main-loop.h"
-+static int compare_chr_send(CompareState *s,
++#include "qemu/log.h"
-                             const uint8_t *buf,
+ #include "qapi/qapi-types-net.h"
-                             uint32_t size);
+ #include "vmnet_int.h"
+ #include "clients.h"
-@@ -XXX,XX +XXX,XX @@ static void colo_compare_connection(void *opaque, void *user_data)
+@@ -XXX,XX +XXX,XX @@
-         }
+ #include "qapi/error.h"
-         if (result) {
+ #include <vmnet/vmnet.h>
--            ret = compare_chr_send(&s->chr_out, pkt->data, pkt->size);
++#include <dispatch/dispatch.h>
-+            ret = compare_chr_send(s, pkt->data, pkt->size);
++
-             if (ret < 0) {
++#ifdef DEBUG
-                 error_report("colo_send_primary_packet failed");
++#define D(x) x
-             }
++#define D_LOG(...) qemu_log(__VA_ARGS__)
-@@ -XXX,XX +XXX,XX @@ static void colo_compare_connection(void *opaque, void *user_data)
++#else
-     }
++#define D(x) do { } while (0)
 +#define D_LOG(...) do { } while (0)
 +#endif
 +
 +typedef struct vmpktdesc vmpktdesc_t;
 +typedef struct iovec iovec_t;
 +
 +static void vmnet_set_send_enabled(VmnetCommonState *s, bool enable)
 +{
 +    s->send_enabled = enable;
 +}
 +
 +
 +static void vmnet_send_completed(NetClientState *nc, ssize_t len)
 +{
 +    VmnetCommonState *s = DO_UPCAST(VmnetCommonState, nc, nc);
 +    vmnet_set_send_enabled(s, true);
 +}
 +
 +
 +static void vmnet_send(NetClientState *nc,
 +                       interface_event_t event_id,
 +                       xpc_object_t event)
 +{
 +    assert(event_id == VMNET_INTERFACE_PACKETS_AVAILABLE);
 +
 +    VmnetCommonState *s;
 +    uint64_t packets_available;
 +
 +    struct iovec *iov;
 +    struct vmpktdesc *packets;
 +    int pkt_cnt;
 +    int i;
 +
 +    vmnet_return_t if_status;
 +    ssize_t size;
 +
 +    s = DO_UPCAST(VmnetCommonState, nc, nc);
 +
 +    packets_available = xpc_dictionary_get_uint64(
 +        event,
 +        vmnet_estimated_packets_available_key
 +    );
 +
 +    pkt_cnt = (packets_available < VMNET_PACKETS_LIMIT) ?
 +              packets_available :
 +              VMNET_PACKETS_LIMIT;
 +
 +
 +    iov = s->iov_buf;
 +    packets = s->packets_buf;
 +
 +    for (i = 0; i < pkt_cnt; ++i) {
 +        packets[i].vm_pkt_size = s->max_packet_size;
 +        packets[i].vm_pkt_iovcnt = 1;
 +        packets[i].vm_flags = 0;
 +    }
 +
 +    if_status = vmnet_read(s->vmnet_if, packets, &pkt_cnt);
 +    if (if_status != VMNET_SUCCESS) {
 +        error_printf("vmnet: read failed: %s\n",
 +                     vmnet_status_map_str(if_status));
 +    }
 +    qemu_mutex_lock_iothread();
 +    for (i = 0; i < pkt_cnt; ++i) {
 +        size = qemu_send_packet_async(nc,
 +                                      iov[i].iov_base,
 +                                      packets[i].vm_pkt_size,
 +                                      vmnet_send_completed);
 +        if (size == 0) {
 +            vmnet_set_send_enabled(s, false);
 +        } else if (size < 0) {
 +            break;
 +        }
 +    }
 +    qemu_mutex_unlock_iothread();
 +
 +}
 +
 +
 +static void vmnet_register_event_callback(VmnetCommonState *s)
 +{
 +    dispatch_queue_t avail_pkt_q = dispatch_queue_create(
 +        "org.qemu.vmnet.if_queue",
 +        DISPATCH_QUEUE_SERIAL
 +    );
 +
 +    vmnet_interface_set_event_callback(
 +        s->vmnet_if,
 +        VMNET_INTERFACE_PACKETS_AVAILABLE,
 +        avail_pkt_q,
 +        ^(interface_event_t event_id, xpc_object_t event) {
 +          if (s->send_enabled) {
 +              vmnet_send(&s->nc, event_id, event);
 +          }
 +        });
 +}
 +
 +
 +static void vmnet_bufs_init(VmnetCommonState *s)
 +{
 +    int i;
 +    struct vmpktdesc *packets;
 +    struct iovec *iov;
 +
 +    packets = s->packets_buf;
 +    iov = s->iov_buf;
 +
 +    for (i = 0; i < VMNET_PACKETS_LIMIT; ++i) {
 +        iov[i].iov_len = s->max_packet_size;
 +        iov[i].iov_base = g_malloc0(iov[i].iov_len);
 +        packets[i].vm_pkt_iov = iov + i;
 +    }
 +}
 +
 +
 +const char *vmnet_status_map_str(vmnet_return_t status)
 +{
 +    switch (status) {
 +    case VMNET_SUCCESS:
 +        return "success";
 +    case VMNET_FAILURE:
 +        return "general failure";
 +    case VMNET_MEM_FAILURE:
 +        return "memory allocation failure";
 +    case VMNET_INVALID_ARGUMENT:
 +        return "invalid argument specified";
 +    case VMNET_SETUP_INCOMPLETE:
 +        return "interface setup is not complete";
 +    case VMNET_INVALID_ACCESS:
 +        return "invalid access, permission denied";
 +    case VMNET_PACKET_TOO_BIG:
 +        return "packet size is larger than MTU";
 +    case VMNET_BUFFER_EXHAUSTED:
 +        return "buffers exhausted in kernel";
 +    case VMNET_TOO_MANY_PACKETS:
 +        return "packet count exceeds limit";
 +    case VMNET_SHARING_SERVICE_BUSY:
 +        return "conflict, sharing service is in use";
 +    default:
 +        return "unknown vmnet error";
 +    }
 +}
 +
 +
 +int vmnet_if_create(NetClientState *nc,
 +                    xpc_object_t if_desc,
 +                    Error **errp,
 +                    void (*completion_callback)(xpc_object_t interface_param))
 +{
 +    VmnetCommonState *s;
 +
 +    dispatch_queue_t if_create_q;
 +    dispatch_semaphore_t if_created_sem;
 +
 +    __block vmnet_return_t if_status;
 +
 +    if_create_q = dispatch_queue_create("org.qemu.vmnet.create",
 +                                        DISPATCH_QUEUE_SERIAL);
 +    if_created_sem = dispatch_semaphore_create(0);
 +
 +    xpc_dictionary_set_bool(
 +        if_desc,
 +        vmnet_allocate_mac_address_key,
 +        false
 +    );
 +
 +    D(D_LOG("vmnet.start.interface_desc:\n");
 +    xpc_dictionary_apply(if_desc,
 +                         ^bool(const char *k, xpc_object_t v) {
 +                           char *desc = xpc_copy_description(v);
 +                           D_LOG("  %s=%s\n", k, desc);
 +                           free(desc);
 +                           return true;
 +                         }));
 +
 +    s = DO_UPCAST(VmnetCommonState, nc, nc);
 +    s->vmnet_if = vmnet_start_interface(
 +        if_desc,
 +        if_create_q,
 +        ^(vmnet_return_t status, xpc_object_t interface_param) {
 +          if_status = status;
 +          if (status != VMNET_SUCCESS || !interface_param) {
 +              dispatch_semaphore_signal(if_created_sem);
 +              return;
 +          }
 +
 +          D(D_LOG("vmnet.start.interface_param:\n");
 +                xpc_dictionary_apply(interface_param,
 +                                     ^bool(const char *k, xpc_object_t v) {
 +                                       char *desc = xpc_copy_description(v);
 +                                       D_LOG("  %s=%s\n", k, desc);
 +                                       free(desc);
 +                                       return true;
 +                                     }));
 +
 +          s->mtu = xpc_dictionary_get_uint64(
 +              interface_param,
 +              vmnet_mtu_key);
 +          s->max_packet_size = xpc_dictionary_get_uint64(
 +              interface_param,
 +              vmnet_max_packet_size_key);
 +
 +          if (completion_callback) {
 +              completion_callback(interface_param);
 +          }
 +          dispatch_semaphore_signal(if_created_sem);
 +        });
 +
 +    if (s->vmnet_if == NULL) {
 +        error_setg(errp, "unable to create interface with requested params");
 +        return -1;
 +    }
 +
 +    dispatch_semaphore_wait(if_created_sem, DISPATCH_TIME_FOREVER);
 +    dispatch_release(if_create_q);
 +
 +    if (if_status != VMNET_SUCCESS) {
 +        error_setg(errp,
 +                   "cannot create vmnet interface: %s",
 +                   vmnet_status_map_str(if_status));
 +        return -1;
 +    }
 +
 +    vmnet_register_event_callback(s);
 +    vmnet_bufs_init(s);
 +    vmnet_set_send_enabled(s, true);
 +
 +    return 0;
 +}
 +
 +
 +ssize_t vmnet_receive_common(NetClientState *nc,
 +                             const uint8_t *buf,
 +                             size_t size)
 +{
 +    VmnetCommonState *s;
 +    vmpktdesc_t packet;
 +    iovec_t iov;
 +    int pkt_cnt;
 +    vmnet_return_t if_status;
 +
 +    s = DO_UPCAST(VmnetCommonState, nc, nc);
 +
 +    if (size > s->max_packet_size) {
 +        warn_report("vmnet: packet is too big, %zu > %llu\n",
 +                    packet.vm_pkt_size,
 +                    s->max_packet_size);
 +        return -1;
 +    }
 +
 +    iov.iov_base = (char *) buf;
 +    iov.iov_len = size;
 +
 +    packet.vm_pkt_iovcnt = 1;
 +    packet.vm_flags = 0;
 +    packet.vm_pkt_size = size;
 +    packet.vm_pkt_iov = &iov;
 +
 +    pkt_cnt = 1;
 +    if_status = vmnet_write(s->vmnet_if, &packet, &pkt_cnt);
 +
 +    if (if_status != VMNET_SUCCESS) {
 +        error_report("vmnet: write error: %s\n",
 +                     vmnet_status_map_str(if_status));
 +    }
 +
 +    if (if_status == VMNET_SUCCESS && pkt_cnt) {
 +        return size;
 +    }
 +    return 0;
 +}
 +
 +
 +void vmnet_cleanup_common(NetClientState *nc)
 +{
 +    VmnetCommonState *s;
 +    dispatch_queue_t if_destroy_q;
 +
 +    s = DO_UPCAST(VmnetCommonState, nc, nc);
 +
 +    qemu_purge_queued_packets(nc);
 +    vmnet_set_send_enabled(s, false);
 +
 +    if (s->vmnet_if == NULL) {
 +        return;
 +    }
 +
 +    if_destroy_q = dispatch_queue_create(
 +        "org.qemu.vmnet.destroy",
 +        DISPATCH_QUEUE_SERIAL
 +    );
 +
 +    vmnet_stop_interface(
 +        s->vmnet_if,
 +        if_destroy_q,
 +        ^(vmnet_return_t status) {
 +        });
 +
 +    for (int i = 0; i < VMNET_PACKETS_LIMIT; ++i) {
 +        g_free(s->iov_buf[i].iov_base);
 +    }
 +}
 diff --git a/net/vmnet-shared.c b/net/vmnet-shared.c
 index XXXXXXX..XXXXXXX 100644
 --- a/net/vmnet-shared.c
 +++ b/net/vmnet-shared.c
@@ -XXX,XX +XXX,XX @@
  #include "qemu/osdep.h"
  #include "qapi/qapi-types-net.h"
 +#include "qapi/error.h"
  #include "vmnet_int.h"
  #include "clients.h"
 -#include "qemu/error-report.h"
 -#include "qapi/error.h"
  #include <vmnet/vmnet.h>
 +typedef struct VmnetSharedState {
 +  VmnetCommonState cs;
 +} VmnetSharedState;
 +
 +
 +static xpc_object_t create_if_desc(const Netdev *netdev, Error **errp)
 +{
 +    const NetdevVmnetSharedOptions *options = &(netdev->u.vmnet_shared);
 +    xpc_object_t if_desc = xpc_dictionary_create(NULL, NULL, 0);
 +
 +    xpc_dictionary_set_uint64(
 +        if_desc,
 +        vmnet_operation_mode_key,
 +        VMNET_SHARED_MODE
 +    );
 +
 +    xpc_dictionary_set_bool(
 +        if_desc,
 +        vmnet_enable_isolation_key,
 +        options->isolated
 +    );
 +
 +    if (options->has_nat66_prefix) {
 +        xpc_dictionary_set_string(if_desc,
 +                                  vmnet_nat66_prefix_key,
 +                                  options->nat66_prefix);
 +    }
 +
 +    if (options->has_start_address ||
 +        options->has_end_address ||
 +        options->has_subnet_mask) {
 +
 +        if (options->has_start_address &&
 +            options->has_end_address &&
 +            options->has_subnet_mask) {
 +
 +            xpc_dictionary_set_string(if_desc,
 +                                      vmnet_start_address_key,
 +                                      options->start_address);
 +            xpc_dictionary_set_string(if_desc,
 +                                      vmnet_end_address_key,
 +                                      options->end_address);
 +            xpc_dictionary_set_string(if_desc,
 +                                      vmnet_subnet_mask_key,
 +                                      options->subnet_mask);
 +        } else {
 +            error_setg(
 +                errp,
 +                "'start-address', 'end-address', 'subnet_mask' "
 +                "should be provided together"
 +            );
 +        }
 +    }
 +
 +    return if_desc;
 +}
 +
 +static NetClientInfo net_vmnet_shared_info = {
 +    .type = NET_CLIENT_DRIVER_VMNET_SHARED,
 +    .size = sizeof(VmnetSharedState),
 +    .receive = vmnet_receive_common,
 +    .cleanup = vmnet_cleanup_common,
 +};
 +
  int net_init_vmnet_shared(const Netdev *netdev, const char *name,
                            NetClientState *peer, Error **errp)
  {
 -  error_setg(errp, "vmnet-shared is not implemented yet");
 -  return -1;
 +    NetClientState *nc = qemu_new_net_client(&net_vmnet_shared_info,
 +                                             peer, "vmnet-shared", name);
 +    xpc_object_t if_desc = create_if_desc(netdev, errp);
 +
 +    return vmnet_if_create(nc, if_desc, errp, NULL);
  }
+diff --git a/net/vmnet_int.h b/net/vmnet_int.h
--static int compare_chr_send(CharBackend *out,
+index XXXXXXX..XXXXXXX 100644
-+static int compare_chr_send(CompareState *s,
+--- a/net/vmnet_int.h
-                             const uint8_t *buf,
++++ b/net/vmnet_int.h
-                             uint32_t size)
+@@ -XXX,XX +XXX,XX @@
- {
-@@ -XXX,XX +XXX,XX @@ static int compare_chr_send(CharBackend *out,
+ #include <vmnet/vmnet.h>
-         return 0;
-     }
++#define VMNET_PACKETS_LIMIT 50
++
--    ret = qemu_chr_fe_write_all(out, (uint8_t *)&len, sizeof(len));
+ typedef struct VmnetCommonState {
-+    ret = qemu_chr_fe_write_all(&s->chr_out, (uint8_t *)&len, sizeof(len));
+   NetClientState nc;
-     if (ret != sizeof(len)) {
++  interface_ref vmnet_if;
-         goto err;
++
-     }
++  bool send_enabled;
++
--    ret = qemu_chr_fe_write_all(out, (uint8_t *)buf, size);
++  uint64_t mtu;
-+    ret = qemu_chr_fe_write_all(&s->chr_out, (uint8_t *)buf, size);
++  uint64_t max_packet_size;
-     if (ret != size) {
++
-         goto err;
++  struct vmpktdesc packets_buf[VMNET_PACKETS_LIMIT];
-     }
++  struct iovec iov_buf[VMNET_PACKETS_LIMIT];
-@@ -XXX,XX +XXX,XX @@ static void compare_pri_rs_finalize(SocketReadState *pri_rs)
+ } VmnetCommonState;
-     if (packet_enqueue(s, PRIMARY_IN)) {
-         trace_colo_compare_main("primary: unsupported packet in");
++const char *vmnet_status_map_str(vmnet_return_t status);
--        compare_chr_send(&s->chr_out, pri_rs->buf, pri_rs->packet_len);
++
-+        compare_chr_send(s, pri_rs->buf, pri_rs->packet_len);
++int vmnet_if_create(NetClientState *nc,
-     } else {
++                    xpc_object_t if_desc,
-         /* compare connection */
++                    Error **errp,
-         g_queue_foreach(&s->conn_list, colo_compare_connection, s);
++                    void (*completion_callback)(xpc_object_t interface_param));
-@@ -XXX,XX +XXX,XX @@ static void colo_flush_packets(void *opaque, void *user_data)
++
++ssize_t vmnet_receive_common(NetClientState *nc,
-     while (!g_queue_is_empty(&conn->primary_list)) {
++                             const uint8_t *buf,
-         pkt = g_queue_pop_head(&conn->primary_list);
++                             size_t size);
--        compare_chr_send(&s->chr_out, pkt->data, pkt->size);
++
-+        compare_chr_send(s, pkt->data, pkt->size);
++void vmnet_cleanup_common(NetClientState *nc);
-         packet_destroy(pkt, NULL);
-     }
+ #endif /* VMNET_INT_H */
      while (!g_queue_is_empty(&conn->secondary_list)) {
 --
 .7.4

-[Qemu-devel] [PULL 04/14] net/filter-mirror.c: Make filter mirror support vnet support.
+[PULL 10/13] net/vmnet: implement host mode (vmnet-host)
-From: Zhang Chen <zhangchen.fnst@cn.fujitsu.com>
+From: Vladislav Yaroshchuk <yaroshchuk2000@gmail.com>
-We add the vnet_hdr_support option for filter-mirror, default is disabled.
+Signed-off-by: Vladislav Yaroshchuk <yaroshchuk2000@gmail.com>
 If you use virtio-net-pci or other driver needs vnet_hdr, please enable it.
 You can use it for example:
 -object filter-mirror,id=m0,netdev=hn0,queue=tx,outdev=mirror0,vnet_hdr_support
 If it has vnet_hdr_support flag, we will change the sending packet format from
 struct {int size; const uint8_t buf[];} to {int size; int vnet_hdr_len; const uint8_t buf[];}.
 make other module(like colo-compare) know how to parse net packet correctly.
 Signed-off-by: Zhang Chen <zhangchen.fnst@cn.fujitsu.com>
 Signed-off-by: Jason Wang <jasowang@redhat.com>
 ---
- net/filter-mirror.c | 42 +++++++++++++++++++++++++++++++++++++++++-
+ net/vmnet-host.c | 93 ++++++++++++++++++++++++++++++++++++++++++++++++++++----
- qemu-options.hx     |  5 ++---
+file changed, 87 insertions(+), 6 deletions(-)
 files changed, 43 insertions(+), 4 deletions(-)
-diff --git a/net/filter-mirror.c b/net/filter-mirror.c
+diff --git a/net/vmnet-host.c b/net/vmnet-host.c
 index XXXXXXX..XXXXXXX 100644
---- a/net/filter-mirror.c
+--- a/net/vmnet-host.c
-+++ b/net/filter-mirror.c
++++ b/net/vmnet-host.c
-@@ -XXX,XX +XXX,XX @@ typedef struct MirrorState {
+@@ -XXX,XX +XXX,XX @@
-     CharBackend chr_in;
+  */
-     CharBackend chr_out;
-     SocketReadState rs;
+ #include "qemu/osdep.h"
-+    bool vnet_hdr;
++#include "qemu/uuid.h"
- } MirrorState;
+ #include "qapi/qapi-types-net.h"
+-#include "vmnet_int.h"
- static int filter_send(MirrorState *s,
+-#include "clients.h"
-                        const struct iovec *iov,
+-#include "qemu/error-report.h"
-                        int iovcnt)
+ #include "qapi/error.h"
- {
++#include "clients.h"
-+    NetFilterState *nf = NETFILTER(s);
++#include "vmnet_int.h"
-     int ret = 0;
-     ssize_t size = 0;
+ #include <vmnet/vmnet.h>
-     uint32_t len = 0;
-@@ -XXX,XX +XXX,XX @@ static int filter_send(MirrorState *s,
++typedef struct VmnetHostState {
-         goto err;
++  VmnetCommonState cs;
-     }
++  QemuUUID network_uuid;
++} VmnetHostState;
 +    if (s->vnet_hdr) {
 +        /*
 +         * If vnet_hdr = on, we send vnet header len to make other
 +         * module(like colo-compare) know how to parse net
 +         * packet correctly.
 +         */
 +        ssize_t vnet_hdr_len;
 +
-+        vnet_hdr_len = nf->netdev->vnet_hdr_len;
++static xpc_object_t create_if_desc(const Netdev *netdev,
 +                                   NetClientState *nc,
 +                                   Error **errp)
 +{
 +    const NetdevVmnetHostOptions *options = &(netdev->u.vmnet_host);
 +    VmnetCommonState *cs = DO_UPCAST(VmnetCommonState, nc, nc);
 +    VmnetHostState *hs = DO_UPCAST(VmnetHostState, cs, cs);
 +
-+        len = htonl(vnet_hdr_len);
++    xpc_object_t if_desc = xpc_dictionary_create(NULL, NULL, 0);
-+        ret = qemu_chr_fe_write_all(&s->chr_out, (uint8_t *)&len, sizeof(len));
++
-+        if (ret != sizeof(len)) {
++    xpc_dictionary_set_uint64(
-+            goto err;
++        if_desc,
 +        vmnet_operation_mode_key,
 +        VMNET_HOST_MODE
 +    );
 +
 +    xpc_dictionary_set_bool(
 +        if_desc,
 +        vmnet_enable_isolation_key,
 +        options->isolated
 +    );
 +
 +    if (options->has_net_uuid) {
 +        if (qemu_uuid_parse(options->net_uuid, &hs->network_uuid) < 0) {
 +            error_setg(errp, "Invalid UUID provided in 'net-uuid'");
 +        }
 +
 +        xpc_dictionary_set_uuid(
 +            if_desc,
 +            vmnet_network_identifier_key,
 +            hs->network_uuid.data
 +        );
 +    }
 +
 +    if (options->has_start_address ||
 +        options->has_end_address ||
 +        options->has_subnet_mask) {
 +
 +        if (options->has_start_address &&
 +            options->has_end_address &&
 +            options->has_subnet_mask) {
 +
 +            xpc_dictionary_set_string(if_desc,
 +                                      vmnet_start_address_key,
 +                                      options->start_address);
 +            xpc_dictionary_set_string(if_desc,
 +                                      vmnet_end_address_key,
 +                                      options->end_address);
 +            xpc_dictionary_set_string(if_desc,
 +                                      vmnet_subnet_mask_key,
 +                                      options->subnet_mask);
 +        } else {
 +            error_setg(
 +                errp,
 +                "'start-address', 'end-address', 'subnet_mask' "
 +                "should be provided together"
 +            );
 +        }
 +    }
 +
-     buf = g_malloc(size);
++    return if_desc;
      iov_to_buf(iov, iovcnt, 0, buf, size);
      ret = qemu_chr_fe_write_all(&s->chr_out, (uint8_t *)buf, size);
@@ -XXX,XX +XXX,XX @@ static void filter_redirector_setup(NetFilterState *nf, Error **errp)
          }
      }
 -    net_socket_rs_init(&s->rs, redirector_rs_finalize, false);
 +    net_socket_rs_init(&s->rs, redirector_rs_finalize, s->vnet_hdr);
      if (s->indev) {
          chr = qemu_chr_find(s->indev);
@@ -XXX,XX +XXX,XX @@ static void filter_mirror_set_outdev(Object *obj,
      }
  }
 +static bool filter_mirror_get_vnet_hdr(Object *obj, Error **errp)
 +{
 +    MirrorState *s = FILTER_MIRROR(obj);
 +
 +    return s->vnet_hdr;
 +}
 +
-+static void filter_mirror_set_vnet_hdr(Object *obj, bool value, Error **errp)
++static NetClientInfo net_vmnet_host_info = {
 +    .type = NET_CLIENT_DRIVER_VMNET_HOST,
 +    .size = sizeof(VmnetHostState),
 +    .receive = vmnet_receive_common,
 +    .cleanup = vmnet_cleanup_common,
 +};
 +
  int net_init_vmnet_host(const Netdev *netdev, const char *name,
 -                        NetClientState *peer, Error **errp) {
 -  error_setg(errp, "vmnet-host is not implemented yet");
 -  return -1;
 +                        NetClientState *peer, Error **errp)
 +{
-+    MirrorState *s = FILTER_MIRROR(obj);
++    NetClientState *nc;
 +    xpc_object_t if_desc;
 +
-+    s->vnet_hdr = value;
++    nc = qemu_new_net_client(&net_vmnet_host_info,
-+}
++                             peer, "vmnet-host", name);
-+
++    if_desc = create_if_desc(netdev, nc, errp);
- static char *filter_redirector_get_outdev(Object *obj, Error **errp)
++    return vmnet_if_create(nc, if_desc, errp, NULL);
  {
      MirrorState *s = FILTER_REDIRECTOR(obj);
@@ -XXX,XX +XXX,XX @@ static void filter_redirector_set_outdev(Object *obj,
  static void filter_mirror_init(Object *obj)
  {
 +    MirrorState *s = FILTER_MIRROR(obj);
 +
      object_property_add_str(obj, "outdev", filter_mirror_get_outdev,
                              filter_mirror_set_outdev, NULL);
 +
 +    s->vnet_hdr = false;
 +    object_property_add_bool(obj, "vnet_hdr_support",
 +                             filter_mirror_get_vnet_hdr,
 +                             filter_mirror_set_vnet_hdr, NULL);
  }
- static void filter_redirector_init(Object *obj)
-diff --git a/qemu-options.hx b/qemu-options.hx
-index XXXXXXX..XXXXXXX 100644
---- a/qemu-options.hx
-+++ b/qemu-options.hx
-@@ -XXX,XX +XXX,XX @@ queue @var{all|rx|tx} is an option that can be applied to any netfilter.
- @option{tx}: the filter is attached to the transmit queue of the netdev,
-              where it will receive packets sent by the netdev.
--@item -object filter-mirror,id=@var{id},netdev=@var{netdevid},outdev=@var{chardevid}[,queue=@var{all|rx|tx}]
-+@item -object filter-mirror,id=@var{id},netdev=@var{netdevid},outdev=@var{chardevid},queue=@var{all|rx|tx}[,vnet_hdr_support]
--filter-mirror on netdev @var{netdevid},mirror net packet to chardev
--@var{chardevid}
-+filter-mirror on netdev @var{netdevid},mirror net packet to chardev@var{chardevid}, if it has the vnet_hdr_support flag, filter-mirror will mirror packet with vnet_hdr_len.
- @item -object filter-redirector,id=@var{id},netdev=@var{netdevid},indev=@var{chardevid},
- outdev=@var{chardevid}[,queue=@var{all|rx|tx}]
 --
 .7.4

-[Qemu-devel] [PULL 05/14] net/filter-mirror.c: Add new option to enable vnet support for filter-redirector
+[PULL 11/13] net/vmnet: implement bridged mode (vmnet-bridged)
-From: Zhang Chen <zhangchen.fnst@cn.fujitsu.com>
+From: Vladislav Yaroshchuk <yaroshchuk2000@gmail.com>
-We add the vnet_hdr_support option for filter-redirector, default is disabled.
+Signed-off-by: Vladislav Yaroshchuk <yaroshchuk2000@gmail.com>
 If you use virtio-net-pci net driver or other driver needs vnet_hdr, please enable it.
 Because colo-compare or other modules needs the vnet_hdr_len to parse
 packet, we add this new option send the len to others.
 You can use it for example:
 -object filter-redirector,id=r0,netdev=hn0,queue=tx,outdev=red0,vnet_hdr_support
 Signed-off-by: Zhang Chen <zhangchen.fnst@cn.fujitsu.com>
 Signed-off-by: Jason Wang <jasowang@redhat.com>
 ---
- net/filter-mirror.c | 23 +++++++++++++++++++++++
+ net/vmnet-bridged.m | 98 +++++++++++++++++++++++++++++++++++++++++++++++++----
- qemu-options.hx     |  6 +++---
+file changed, 92 insertions(+), 6 deletions(-)
 files changed, 26 insertions(+), 3 deletions(-)
-diff --git a/net/filter-mirror.c b/net/filter-mirror.c
+diff --git a/net/vmnet-bridged.m b/net/vmnet-bridged.m
 index XXXXXXX..XXXXXXX 100644
---- a/net/filter-mirror.c
+--- a/net/vmnet-bridged.m
-+++ b/net/filter-mirror.c
++++ b/net/vmnet-bridged.m
-@@ -XXX,XX +XXX,XX @@ static void filter_redirector_set_outdev(Object *obj,
+@@ -XXX,XX +XXX,XX @@
-     s->outdev = g_strdup(value);
- }
+ #include "qemu/osdep.h"
+ #include "qapi/qapi-types-net.h"
-+static bool filter_redirector_get_vnet_hdr(Object *obj, Error **errp)
+-#include "vmnet_int.h"
 -#include "clients.h"
 -#include "qemu/error-report.h"
  #include "qapi/error.h"
 +#include "clients.h"
 +#include "vmnet_int.h"
  #include <vmnet/vmnet.h>
 +typedef struct VmnetBridgedState {
 +  VmnetCommonState cs;
 +} VmnetBridgedState;
 +
 +static bool validate_ifname(const char *ifname)
 +{
-+    MirrorState *s = FILTER_REDIRECTOR(obj);
++    xpc_object_t shared_if_list = vmnet_copy_shared_interface_list();
 +    __block bool match = false;
 +
-+    return s->vnet_hdr;
++    xpc_array_apply(
 +        shared_if_list,
 +        ^bool(size_t index, xpc_object_t value) {
 +          if (strcmp(xpc_string_get_string_ptr(value), ifname) == 0) {
 +              match = true;
 +              return false;
 +          }
 +          return true;
 +        });
 +
 +    return match;
 +}
 +
-+static void filter_redirector_set_vnet_hdr(Object *obj,
++static const char *get_valid_ifnames(void)
 +                                           bool value,
 +                                           Error **errp)
 +{
-+    MirrorState *s = FILTER_REDIRECTOR(obj);
++    xpc_object_t shared_if_list = vmnet_copy_shared_interface_list();
 +    __block char *if_list = NULL;
 +
-+    s->vnet_hdr = value;
++    xpc_array_apply(
 +        shared_if_list,
 +        ^bool(size_t index, xpc_object_t value) {
 +          if_list = g_strconcat(xpc_string_get_string_ptr(value),
 +                                " ",
 +                                if_list,
 +                                NULL);
 +          return true;
 +        });
 +
 +    if (if_list) {
 +        return if_list;
 +    }
 +    return "[no interfaces]";
 +}
 +
- static void filter_mirror_init(Object *obj)
++static xpc_object_t create_if_desc(const Netdev *netdev, Error **errp)
 +{
 +    const NetdevVmnetBridgedOptions *options = &(netdev->u.vmnet_bridged);
 +    xpc_object_t if_desc = xpc_dictionary_create(NULL, NULL, 0);
 +
 +    xpc_dictionary_set_uint64(
 +        if_desc,
 +        vmnet_operation_mode_key,
 +        VMNET_BRIDGED_MODE
 +    );
 +
 +    xpc_dictionary_set_bool(
 +        if_desc,
 +        vmnet_enable_isolation_key,
 +        options->isolated
 +    );
 +
 +    if (validate_ifname(options->ifname)) {
 +        xpc_dictionary_set_string(if_desc,
 +                                  vmnet_shared_interface_name_key,
 +                                  options->ifname);
 +    } else {
 +        return NULL;
 +    }
 +    return if_desc;
 +}
 +
 +static NetClientInfo net_vmnet_bridged_info = {
 +    .type = NET_CLIENT_DRIVER_VMNET_BRIDGED,
 +    .size = sizeof(VmnetBridgedState),
 +    .receive = vmnet_receive_common,
 +    .cleanup = vmnet_cleanup_common,
 +};
 +
  int net_init_vmnet_bridged(const Netdev *netdev, const char *name,
                             NetClientState *peer, Error **errp)
  {
-     MirrorState *s = FILTER_MIRROR(obj);
+-  error_setg(errp, "vmnet-bridged is not implemented yet");
-@@ -XXX,XX +XXX,XX @@ static void filter_mirror_init(Object *obj)
+-  return -1;
+-}
- static void filter_redirector_init(Object *obj)
++    NetClientState *nc = qemu_new_net_client(&net_vmnet_bridged_info,
- {
++                                             peer, "vmnet-bridged", name);
-+    MirrorState *s = FILTER_REDIRECTOR(obj);
++    xpc_object_t if_desc = create_if_desc(netdev, errp);;
 +
-     object_property_add_str(obj, "indev", filter_redirector_get_indev,
++    if (!if_desc) {
-                             filter_redirector_set_indev, NULL);
++        error_setg(errp,
-     object_property_add_str(obj, "outdev", filter_redirector_get_outdev,
++                   "unsupported ifname, should be one of: %s",
-                             filter_redirector_set_outdev, NULL);
++                   get_valid_ifnames());
 +        return -1;
 +    }
 +
-+    s->vnet_hdr = false;
++    return vmnet_if_create(nc, if_desc, errp, NULL);
-+    object_property_add_bool(obj, "vnet_hdr_support",
++}
-+                             filter_redirector_get_vnet_hdr,
+\ No newline at end of file
 +                             filter_redirector_set_vnet_hdr, NULL);
  }
  static void filter_mirror_fini(Object *obj)
 diff --git a/qemu-options.hx b/qemu-options.hx
 index XXXXXXX..XXXXXXX 100644
 --- a/qemu-options.hx
 +++ b/qemu-options.hx
@@ -XXX,XX +XXX,XX @@ queue @var{all|rx|tx} is an option that can be applied to any netfilter.
  filter-mirror on netdev @var{netdevid},mirror net packet to chardev@var{chardevid}, if it has the vnet_hdr_support flag, filter-mirror will mirror packet with vnet_hdr_len.
 -@item -object filter-redirector,id=@var{id},netdev=@var{netdevid},indev=@var{chardevid},
 -outdev=@var{chardevid}[,queue=@var{all|rx|tx}]
 +@item -object filter-redirector,id=@var{id},netdev=@var{netdevid},indev=@var{chardevid},outdev=@var{chardevid},queue=@var{all|rx|tx}[,vnet_hdr_support]
  filter-redirector on netdev @var{netdevid},redirect filter's net packet to chardev
 -@var{chardevid},and redirect indev's packet to filter.
 +@var{chardevid},and redirect indev's packet to filter.if it has the vnet_hdr_support flag,
 +filter-redirector will redirect packet with vnet_hdr_len.
  Create a filter-redirector we need to differ outdev id from indev id, id can not
  be the same. we can just use indev or outdev, but at least one of indev or outdev
  need to be specified.
 --
 .7.4

-[Qemu-devel] [PULL 11/14] net/filter-rewriter.c: Make filter-rewriter support vnet_hdr_len
+[PULL 12/13] net/vmnet: update qemu-options.hx
-From: Zhang Chen <zhangchen.fnst@cn.fujitsu.com>
+From: Vladislav Yaroshchuk <yaroshchuk2000@gmail.com>
-We add the vnet_hdr_support option for filter-rewriter, default is disabled.
+Signed-off-by: Vladislav Yaroshchuk <yaroshchuk2000@gmail.com>
 If you use virtio-net-pci or other driver needs vnet_hdr, please enable it.
 You can use it for example:
 -object filter-rewriter,id=rew0,netdev=hn0,queue=all,vnet_hdr_support
 We get the vnet_hdr_len from NetClientState that make us
 parse net packet correctly.
 Signed-off-by: Zhang Chen <zhangchen.fnst@cn.fujitsu.com>
 Signed-off-by: Jason Wang <jasowang@redhat.com>
 ---
- net/filter-rewriter.c | 37 ++++++++++++++++++++++++++++++++++++-
+ qemu-options.hx | 25 +++++++++++++++++++++++++
- qemu-options.hx       |  4 ++--
+file changed, 25 insertions(+)
 files changed, 38 insertions(+), 3 deletions(-)
-diff --git a/net/filter-rewriter.c b/net/filter-rewriter.c
-index XXXXXXX..XXXXXXX 100644
---- a/net/filter-rewriter.c
-+++ b/net/filter-rewriter.c
-@@ -XXX,XX +XXX,XX @@
- #include "qemu-common.h"
- #include "qapi/error.h"
- #include "qapi/qmp/qerror.h"
-+#include "qemu/error-report.h"
- #include "qapi-visit.h"
- #include "qom/object.h"
- #include "qemu/main-loop.h"
-@@ -XXX,XX +XXX,XX @@ typedef struct RewriterState {
-     NetQueue *incoming_queue;
-     /* hashtable to save connection */
-     GHashTable *connection_track_table;
-+    bool vnet_hdr;
- } RewriterState;
- static void filter_rewriter_flush(NetFilterState *nf)
-@@ -XXX,XX +XXX,XX @@ static ssize_t colo_rewriter_receive_iov(NetFilterState *nf,
-     ConnectionKey key;
-     Packet *pkt;
-     ssize_t size = iov_size(iov, iovcnt);
-+    ssize_t vnet_hdr_len = 0;
-     char *buf = g_malloc0(size);
-     iov_to_buf(iov, iovcnt, 0, buf, size);
--    pkt = packet_new(buf, size, 0);
-+
-+    if (s->vnet_hdr) {
-+        vnet_hdr_len = nf->netdev->vnet_hdr_len;
-+    }
-+
-+    pkt = packet_new(buf, size, vnet_hdr_len);
-     g_free(buf);
-     /*
-@@ -XXX,XX +XXX,XX @@ static void colo_rewriter_setup(NetFilterState *nf, Error **errp)
-     s->incoming_queue = qemu_new_net_queue(qemu_netfilter_pass_to_next, nf);
- }
-+static bool filter_rewriter_get_vnet_hdr(Object *obj, Error **errp)
-+{
-+    RewriterState *s = FILTER_COLO_REWRITER(obj);
-+
-+    return s->vnet_hdr;
-+}
-+
-+static void filter_rewriter_set_vnet_hdr(Object *obj,
-+                                         bool value,
-+                                         Error **errp)
-+{
-+    RewriterState *s = FILTER_COLO_REWRITER(obj);
-+
-+    s->vnet_hdr = value;
-+}
-+
-+static void filter_rewriter_init(Object *obj)
-+{
-+    RewriterState *s = FILTER_COLO_REWRITER(obj);
-+
-+    s->vnet_hdr = false;
-+    object_property_add_bool(obj, "vnet_hdr_support",
-+                             filter_rewriter_get_vnet_hdr,
-+                             filter_rewriter_set_vnet_hdr, NULL);
-+}
-+
- static void colo_rewriter_class_init(ObjectClass *oc, void *data)
- {
-     NetFilterClass *nfc = NETFILTER_CLASS(oc);
-@@ -XXX,XX +XXX,XX @@ static const TypeInfo colo_rewriter_info = {
-     .name = TYPE_FILTER_REWRITER,
-     .parent = TYPE_NETFILTER,
-     .class_init = colo_rewriter_class_init,
-+    .instance_init = filter_rewriter_init,
-     .instance_size = sizeof(RewriterState),
- };
 diff --git a/qemu-options.hx b/qemu-options.hx
 index XXXXXXX..XXXXXXX 100644
 --- a/qemu-options.hx
 +++ b/qemu-options.hx
-@@ -XXX,XX +XXX,XX @@ Create a filter-redirector we need to differ outdev id from indev id, id can not
+@@ -XXX,XX +XXX,XX @@ DEF("netdev", HAS_ARG, QEMU_OPTION_netdev,
- be the same. we can just use indev or outdev, but at least one of indev or outdev
+     "-netdev vhost-vdpa,id=str,vhostdev=/path/to/dev\n"
- need to be specified.
+     "                configure a vhost-vdpa network,Establish a vhost-vdpa netdev\n"
+ #endif
--@item -object filter-rewriter,id=@var{id},netdev=@var{netdevid}[,queue=@var{all|rx|tx}]
++#ifdef CONFIG_VMNET
-+@item -object filter-rewriter,id=@var{id},netdev=@var{netdevid},queue=@var{all|rx|tx},[vnet_hdr_support]
++    "-netdev vmnet-host,id=str[,isolated=on|off][,net-uuid=uuid]\n"
++    "         [,start-address=addr,end-address=addr,subnet-mask=mask]\n"
- Filter-rewriter is a part of COLO project.It will rewrite tcp packet to
++    "                configure a vmnet network backend in host mode with ID 'str',\n"
- secondary from primary to keep secondary tcp connection,and rewrite
++    "                isolate this interface from others with 'isolated',\n"
- tcp packet to primary from secondary make tcp packet can be handled by
++    "                configure the address range and choose a subnet mask,\n"
--client.
++    "                specify network UUID 'uuid' to disable DHCP and interact with\n"
-+client.if it has the vnet_hdr_support flag, we can parse packet with vnet header.
++    "                vmnet-host interfaces within this isolated network\n"
++    "-netdev vmnet-shared,id=str[,isolated=on|off][,nat66-prefix=addr]\n"
- usage:
++    "         [,start-address=addr,end-address=addr,subnet-mask=mask]\n"
- colo secondary:
++    "                configure a vmnet network backend in shared mode with ID 'str',\n"
 +    "                configure the address range and choose a subnet mask,\n"
 +    "                set IPv6 ULA prefix (of length 64) to use for internal network,\n"
 +    "                isolate this interface from others with 'isolated'\n"
 +    "-netdev vmnet-bridged,id=str,ifname=name[,isolated=on|off]\n"
 +    "                configure a vmnet network backend in bridged mode with ID 'str',\n"
 +    "                use 'ifname=name' to select a physical network interface to be bridged,\n"
 +    "                isolate this interface from others with 'isolated'\n"
 +#endif
      "-netdev hubport,id=str,hubid=n[,netdev=nd]\n"
      "                configure a hub port on the hub with ID 'n'\n", QEMU_ARCH_ALL)
  DEF("nic", HAS_ARG, QEMU_OPTION_nic,
@@ -XXX,XX +XXX,XX @@ DEF("nic", HAS_ARG, QEMU_OPTION_nic,
  #ifdef CONFIG_POSIX
      "vhost-user|"
  #endif
 +#ifdef CONFIG_VMNET
 +    "vmnet-host|vmnet-shared|vmnet-bridged|"
 +#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"
@@ -XXX,XX +XXX,XX @@ DEF("net", HAS_ARG, QEMU_OPTION_net,
  #ifdef CONFIG_NETMAP
      "netmap|"
  #endif
 +#ifdef CONFIG_VMNET
 +    "vmnet-host|vmnet-shared|vmnet-bridged|"
 +#endif
      "socket][,option][,option][,...]\n"
      "                old way to initialize a host network interface\n"
      "                (use the -netdev option if possible instead)\n", QEMU_ARCH_ALL)
 --
 .7.4

-[Qemu-devel] [PULL 06/14] net/colo.c: Make vnet_hdr_len as packet property
+[PULL 13/13] net/vmnet: update MAINTAINERS list
-From: Zhang Chen <zhangchen.fnst@cn.fujitsu.com>
+From: Vladislav Yaroshchuk <yaroshchuk2000@gmail.com>
-We can use this property flush and send packet with vnet_hdr_len.
+Signed-off-by: Vladislav Yaroshchuk <yaroshchuk2000@gmail.com>
 Signed-off-by: Zhang Chen <zhangchen.fnst@cn.fujitsu.com>
 Signed-off-by: Jason Wang <jasowang@redhat.com>
 ---
- net/colo-compare.c    | 8 ++++++--
+ MAINTAINERS | 5 +++++
- net/colo.c            | 3 ++-
+file changed, 5 insertions(+)
  net/colo.h            | 4 +++-
  net/filter-rewriter.c | 2 +-
 files changed, 12 insertions(+), 5 deletions(-)
-diff --git a/net/colo-compare.c b/net/colo-compare.c
+diff --git a/MAINTAINERS b/MAINTAINERS
 index XXXXXXX..XXXXXXX 100644
---- a/net/colo-compare.c
+--- a/MAINTAINERS
-+++ b/net/colo-compare.c
++++ b/MAINTAINERS
-@@ -XXX,XX +XXX,XX @@ static int packet_enqueue(CompareState *s, int mode)
+@@ -XXX,XX +XXX,XX @@ W: http://info.iet.unipi.it/~luigi/netmap/
-     Connection *conn;
+ S: Maintained
+ F: net/netmap.c
-     if (mode == PRIMARY_IN) {
--        pkt = packet_new(s->pri_rs.buf, s->pri_rs.packet_len);
++Apple vmnet network backends
-+        pkt = packet_new(s->pri_rs.buf,
++M: Vladislav Yaroshchuk <yaroshchuk2000@gmail.com>
-+                         s->pri_rs.packet_len,
++S: Maintained
-+                         s->pri_rs.vnet_hdr_len);
++F: net/vmnet*
-     } else {
++
--        pkt = packet_new(s->sec_rs.buf, s->sec_rs.packet_len);
+ Host Memory Backends
-+        pkt = packet_new(s->sec_rs.buf,
+ M: David Hildenbrand <david@redhat.com>
-+                         s->sec_rs.packet_len,
+ M: Igor Mammedov <imammedo@redhat.com>
 +                         s->sec_rs.vnet_hdr_len);
      }
      if (parse_packet_early(pkt)) {
 diff --git a/net/colo.c b/net/colo.c
 index XXXXXXX..XXXXXXX 100644
 --- a/net/colo.c
 +++ b/net/colo.c
@@ -XXX,XX +XXX,XX @@ void connection_destroy(void *opaque)
      g_slice_free(Connection, conn);
  }
 -Packet *packet_new(const void *data, int size)
 +Packet *packet_new(const void *data, int size, int vnet_hdr_len)
  {
      Packet *pkt = g_slice_new(Packet);
      pkt->data = g_memdup(data, size);
      pkt->size = size;
      pkt->creation_ms = qemu_clock_get_ms(QEMU_CLOCK_HOST);
 +    pkt->vnet_hdr_len = vnet_hdr_len;
      return pkt;
  }
 diff --git a/net/colo.h b/net/colo.h
 index XXXXXXX..XXXXXXX 100644
 --- a/net/colo.h
 +++ b/net/colo.h
@@ -XXX,XX +XXX,XX @@ typedef struct Packet {
      int size;
      /* Time of packet creation, in wall clock ms */
      int64_t creation_ms;
 +    /* Get vnet_hdr_len from filter */
 +    uint32_t vnet_hdr_len;
  } Packet;
  typedef struct ConnectionKey {
@@ -XXX,XX +XXX,XX @@ Connection *connection_get(GHashTable *connection_track_table,
                             ConnectionKey *key,
                             GQueue *conn_list);
  void connection_hashtable_reset(GHashTable *connection_track_table);
 -Packet *packet_new(const void *data, int size);
 +Packet *packet_new(const void *data, int size, int vnet_hdr_len);
  void packet_destroy(void *opaque, void *user_data);
  #endif /* QEMU_COLO_PROXY_H */
 diff --git a/net/filter-rewriter.c b/net/filter-rewriter.c
 index XXXXXXX..XXXXXXX 100644
 --- a/net/filter-rewriter.c
 +++ b/net/filter-rewriter.c
@@ -XXX,XX +XXX,XX @@ static ssize_t colo_rewriter_receive_iov(NetFilterState *nf,
      char *buf = g_malloc0(size);
      iov_to_buf(iov, iovcnt, 0, buf, size);
 -    pkt = packet_new(buf, size);
 +    pkt = packet_new(buf, size, 0);
      g_free(buf);
      /*
 --
 .7.4

The following changes since commit 6632f6ff96f0537fc34cdc00c760656fc62e23c5:

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

are available in the git repository at:

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

for you to fetch changes up to 189ae6bb5ce1f5a322f8691d00fe942ba43dd601:

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

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

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

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

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

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

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

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

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

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

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

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

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

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

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

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

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

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

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

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

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

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

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

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

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

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

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

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

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

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

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

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

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

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

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

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

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

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

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

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

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

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

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

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

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

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

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

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

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

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

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

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

From: Michal Privoznik <mprivozn@redhat.com>

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

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

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

The following changes since commit df722e33d5da26ea8604500ca8f509245a0ea524:

Merge tag 'bsd-user-arm-pull-request' of gitlab.com:bsdimp/qemu into staging (2022-01-08 09:37:59 -0800)

are available in the git repository at:

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

for you to fetch changes up to 5136cc6d3b8b74f4fa572f0874656947a401330e:

net/vmnet: update MAINTAINERS list (2022-01-10 11:30:55 +0800)

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

----------------------------------------------------------------
Peter Foley (2):
      net/tap: Set return code on failure
      net: Fix uninitialized data usage

Philippe Mathieu-Daudé (1):
      hw/net/vmxnet3: Log guest-triggerable errors using LOG_GUEST_ERROR

Rao Lei (1):
      net/filter: Optimize filter_send to coroutine

Vladislav Yaroshchuk (7):
      net/vmnet: add vmnet dependency and customizable option
      net/vmnet: add vmnet backends to qapi/net
      net/vmnet: implement shared mode (vmnet-shared)
      net/vmnet: implement host mode (vmnet-host)
      net/vmnet: implement bridged mode (vmnet-bridged)
      net/vmnet: update qemu-options.hx
      net/vmnet: update MAINTAINERS list

Zhang Chen (2):
      net/colo-compare.c: Optimize compare order for performance
      net/colo-compare.c: Update the default value comments

From: Philippe Mathieu-Daudé <philmd@redhat.com>

The "Interrupt Cause" register (VMXNET3_REG_ICR) is read-only.
Write accesses are ignored. Log them with as LOG_GUEST_ERROR
instead of aborting:

[R +0.239743] writeq 0xe0002031 0x46291a5a55460800
  ERROR:hw/net/vmxnet3.c:1819:vmxnet3_io_bar1_write: code should not be reached
  Thread 1 "qemu-system-i38" received signal SIGABRT, Aborted.
  (gdb) bt
  #3  0x74c397d3 in __GI_abort () at abort.c:79
  #4  0x76d3cd4c in g_assertion_message (domain=<optimized out>, file=<optimized out>, line=<optimized out>, func=<optimized out>, message=<optimized out>) at ../glib/gtestutils.c:3223
  #5  0x76d9d45f in g_assertion_message_expr
      (domain=0x0, file=0x59fc2e53 "hw/net/vmxnet3.c", line=1819, func=0x59fc11e0 <__func__.vmxnet3_io_bar1_write> "vmxnet3_io_bar1_write", expr=<optimized out>)
      at ../glib/gtestutils.c:3249
  #6  0x57e80a3a in vmxnet3_io_bar1_write (opaque=0x62814100, addr=56, val=70, size=4) at hw/net/vmxnet3.c:1819
  #7  0x58c2d894 in memory_region_write_accessor (mr=0x62816b90, addr=56, value=0x7fff9450, size=4, shift=0, mask=4294967295, attrs=...) at softmmu/memory.c:492
  #8  0x58c2d1d2 in access_with_adjusted_size (addr=56, value=0x7fff9450, size=1, access_size_min=4, access_size_max=4, access_fn=
      0x58c2d290 <memory_region_write_accessor>, mr=0x62816b90, attrs=...) at softmmu/memory.c:554
  #9  0x58c2bae7 in memory_region_dispatch_write (mr=0x62816b90, addr=56, data=70, op=MO_8, attrs=...) at softmmu/memory.c:1504
  #10 0x58bfd034 in flatview_write_continue (fv=0x606000181700, addr=0xe0002038, attrs=..., ptr=0x7fffb9e0, len=1, addr1=56, l=1, mr=0x62816b90)
      at softmmu/physmem.c:2782
  #11 0x58beba00 in flatview_write (fv=0x606000181700, addr=0xe0002031, attrs=..., buf=0x7fffb9e0, len=8) at softmmu/physmem.c:2822
  #12 0x58beb589 in address_space_write (as=0x608000015f20, addr=0xe0002031, attrs=..., buf=0x7fffb9e0, len=8) at softmmu/physmem.c:2914

Reported-by: Dike <dike199774@qq.com>
Reported-by: Duhao <504224090@qq.com>
BugLink: https://bugzilla.redhat.com/show_bug.cgi?id=2032932
Signed-off-by: Philippe Mathieu-Daudé <philmd@redhat.com>
Signed-off-by: Jason Wang <jasowang@redhat.com>
---
 hw/net/vmxnet3.c | 4 +++-
 1 file changed, 3 insertions(+), 1 deletion(-)

diff --git a/hw/net/vmxnet3.c b/hw/net/vmxnet3.c
index XXXXXXX..XXXXXXX 100644
--- a/hw/net/vmxnet3.c
+++ b/hw/net/vmxnet3.c
@@ -XXX,XX +XXX,XX @@ vmxnet3_io_bar1_write(void *opaque,
     case VMXNET3_REG_ICR:
         VMW_CBPRN("Write BAR1 [VMXNET3_REG_ICR] = %" PRIx64 ", size %d",
                   val, size);
-        g_assert_not_reached();
+        qemu_log_mask(LOG_GUEST_ERROR,
+                      "%s: write to read-only register VMXNET3_REG_ICR\n",
+                      TYPE_VMXNET3);
         break;
 
     /* Event Cause Register */
-- 
2.7.4

From: Peter Foley <pefoley@google.com>

e.g.
1109 15:16:20.151506 Uninitialized bytes in ioctl_common_pre at offset 0 inside [0x7ffc516af9b8, 4)
 1109 15:16:20.151659 ==588974==WARNING: MemorySanitizer: use-of-uninitialized-value
 1109 15:16:20.312923     #0 0x5639b88acb21 in tap_probe_vnet_hdr_len third_party/qemu/net/tap-linux.c:183:9
 1109 15:16:20.312952     #1 0x5639b88afd66 in net_tap_fd_init third_party/qemu/net/tap.c:409:9
 1109 15:16:20.312954     #2 0x5639b88b2d1b in net_init_tap_one third_party/qemu/net/tap.c:681:19
 1109 15:16:20.312956     #3 0x5639b88b16a8 in net_init_tap third_party/qemu/net/tap.c:912:13
 1109 15:16:20.312957     #4 0x5639b8890175 in net_client_init1 third_party/qemu/net/net.c:1110:9
 1109 15:16:20.312958     #5 0x5639b888f912 in net_client_init third_party/qemu/net/net.c:1208:15
 1109 15:16:20.312960     #6 0x5639b8894aa5 in net_param_nic third_party/qemu/net/net.c:1588:11
 1109 15:16:20.312961     #7 0x5639b900cd18 in qemu_opts_foreach third_party/qemu/util/qemu-option.c:1135:14
 1109 15:16:20.312962     #8 0x5639b889393c in net_init_clients third_party/qemu/net/net.c:1612:9
 1109 15:16:20.312964     #9 0x5639b717aaf3 in qemu_create_late_backends third_party/qemu/softmmu/vl.c:1962:5
 1109 15:16:20.312965     #10 0x5639b717aaf3 in qemu_init third_party/qemu/softmmu/vl.c:3694:5
 1109 15:16:20.312967     #11 0x5639b71083b8 in main third_party/qemu/softmmu/main.c:49:5
 1109 15:16:20.312968     #12 0x7f464de1d8d2 in __libc_start_main (/usr/grte/v5/lib64/libc.so.6+0x628d2)
 1109 15:16:20.312969     #13 0x5639b6bbd389 in _start /usr/grte/v5/debug-src/src/csu/../sysdeps/x86_64/start.S:120
 1109 15:16:20.312970
 1109 15:16:20.312975   Uninitialized value was stored to memory at
 1109 15:16:20.313393     #0 0x5639b88acbee in tap_probe_vnet_hdr_len third_party/qemu/net/tap-linux.c
 1109 15:16:20.313396     #1 0x5639b88afd66 in net_tap_fd_init third_party/qemu/net/tap.c:409:9
 1109 15:16:20.313398     #2 0x5639b88b2d1b in net_init_tap_one third_party/qemu/net/tap.c:681:19
 1109 15:16:20.313399     #3 0x5639b88b16a8 in net_init_tap third_party/qemu/net/tap.c:912:13
 1109 15:16:20.313400     #4 0x5639b8890175 in net_client_init1 third_party/qemu/net/net.c:1110:9
 1109 15:16:20.313401     #5 0x5639b888f912 in net_client_init third_party/qemu/net/net.c:1208:15
 1109 15:16:20.313403     #6 0x5639b8894aa5 in net_param_nic third_party/qemu/net/net.c:1588:11
 1109 15:16:20.313404     #7 0x5639b900cd18 in qemu_opts_foreach third_party/qemu/util/qemu-option.c:1135:14
 1109 15:16:20.313405     #8 0x5639b889393c in net_init_clients third_party/qemu/net/net.c:1612:9
 1109 15:16:20.313407     #9 0x5639b717aaf3 in qemu_create_late_backends third_party/qemu/softmmu/vl.c:1962:5
 1109 15:16:20.313408     #10 0x5639b717aaf3 in qemu_init third_party/qemu/softmmu/vl.c:3694:5
 1109 15:16:20.313409     #11 0x5639b71083b8 in main third_party/qemu/softmmu/main.c:49:5
 1109 15:16:20.313410     #12 0x7f464de1d8d2 in __libc_start_main (/usr/grte/v5/lib64/libc.so.6+0x628d2)
 1109 15:16:20.313412     #13 0x5639b6bbd389 in _start /usr/grte/v5/debug-src/src/csu/../sysdeps/x86_64/start.S:120
 1109 15:16:20.313413
 1109 15:16:20.313417   Uninitialized value was stored to memory at
 1109 15:16:20.313791     #0 0x5639b88affbd in net_tap_fd_init third_party/qemu/net/tap.c:400:26
 1109 15:16:20.313826     #1 0x5639b88b2d1b in net_init_tap_one third_party/qemu/net/tap.c:681:19
 1109 15:16:20.313829     #2 0x5639b88b16a8 in net_init_tap third_party/qemu/net/tap.c:912:13
 1109 15:16:20.313831     #3 0x5639b8890175 in net_client_init1 third_party/qemu/net/net.c:1110:9
 1109 15:16:20.313836     #4 0x5639b888f912 in net_client_init third_party/qemu/net/net.c:1208:15
 1109 15:16:20.313838     #5 0x5639b8894aa5 in net_param_nic third_party/qemu/net/net.c:1588:11
 1109 15:16:20.313839     #6 0x5639b900cd18 in qemu_opts_foreach third_party/qemu/util/qemu-option.c:1135:14
 1109 15:16:20.313841     #7 0x5639b889393c in net_init_clients third_party/qemu/net/net.c:1612:9
 1109 15:16:20.313843     #8 0x5639b717aaf3 in qemu_create_late_backends third_party/qemu/softmmu/vl.c:1962:5
 1109 15:16:20.313844     #9 0x5639b717aaf3 in qemu_init third_party/qemu/softmmu/vl.c:3694:5
 1109 15:16:20.313845     #10 0x5639b71083b8 in main third_party/qemu/softmmu/main.c:49:5
 1109 15:16:20.313846     #11 0x7f464de1d8d2 in __libc_start_main (/usr/grte/v5/lib64/libc.so.6+0x628d2)
 1109 15:16:20.313847     #12 0x5639b6bbd389 in _start /usr/grte/v5/debug-src/src/csu/../sysdeps/x86_64/start.S:120
 1109 15:16:20.313849
 1109 15:16:20.313851   Uninitialized value was created by an allocation of 'ifr' in the stack frame of function 'tap_probe_vnet_hdr'
 1109 15:16:20.313855     #0 0x5639b88ac680 in tap_probe_vnet_hdr third_party/qemu/net/tap-linux.c:151
 1109 15:16:20.313856
 1109 15:16:20.313878 SUMMARY: MemorySanitizer: use-of-uninitialized-value third_party/qemu/net/tap-linux.c:183:9 in tap_probe_vnet_hdr_len

Fixes: dc69004c7d8 ("net: move tap_probe_vnet_hdr() to tap-linux.c")
Reviewed-by: Hao Wu <wuhaotsh@google.com>
Reviewed-by: Patrick Venture <venture@google.com>
Reviewed-by: Philippe Mathieu-Daudé <f4bug@amsat.org>
Signed-off-by: Peter Foley <pefoley@google.com>
Signed-off-by: Jason Wang <jasowang@redhat.com>
---
 net/tap-linux.c | 1 +
 1 file changed, 1 insertion(+)

diff --git a/net/tap-linux.c b/net/tap-linux.c
index XXXXXXX..XXXXXXX 100644
--- a/net/tap-linux.c
+++ b/net/tap-linux.c
@@ -XXX,XX +XXX,XX @@ void tap_set_sndbuf(int fd, const NetdevTapOptions *tap, Error **errp)
 int tap_probe_vnet_hdr(int fd, Error **errp)
 {
     struct ifreq ifr;
+    memset(&ifr, 0, sizeof(ifr));
 
     if (ioctl(fd, TUNGETIFF, &ifr) != 0) {
         /* TUNGETIFF is available since kernel v2.6.27 */
-- 
2.7.4

From: Zhang Chen <chen.zhang@intel.com>

COLO-compare use the glib function g_queue_find_custom to dump
another VM's networking packet to compare. But this function always
start find from the queue->head(here is the newest packet), It will
reduce the success rate of comparison. So this patch reversed
the order of the queues for performance.

Signed-off-by: Zhang Chen <chen.zhang@intel.com>
Reported-by: leirao <lei.rao@intel.com>
Signed-off-by: Jason Wang <jasowang@redhat.com>
---
 net/colo-compare.c | 26 +++++++++++++-------------
 1 file changed, 13 insertions(+), 13 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 void colo_compare_inconsistency_notify(CompareState *s)
 /* Use restricted to colo_insert_packet() */
 static gint seq_sorter(Packet *a, Packet *b, gpointer data)
 {
-    return a->tcp_seq - b->tcp_seq;
+    return b->tcp_seq - a->tcp_seq;
 }
 
 static void fill_pkt_tcp_info(void *data, uint32_t *max_ack)
@@ -XXX,XX +XXX,XX @@ pri:
     if (g_queue_is_empty(&conn->primary_list)) {
         return;
     }
-    ppkt = g_queue_pop_head(&conn->primary_list);
+    ppkt = g_queue_pop_tail(&conn->primary_list);
 sec:
     if (g_queue_is_empty(&conn->secondary_list)) {
-        g_queue_push_head(&conn->primary_list, ppkt);
+        g_queue_push_tail(&conn->primary_list, ppkt);
         return;
     }
-    spkt = g_queue_pop_head(&conn->secondary_list);
+    spkt = g_queue_pop_tail(&conn->secondary_list);
 
     if (ppkt->tcp_seq == ppkt->seq_end) {
         colo_release_primary_pkt(s, ppkt);
@@ -XXX,XX +XXX,XX @@ sec:
             }
         }
         if (!ppkt) {
-            g_queue_push_head(&conn->secondary_list, spkt);
+            g_queue_push_tail(&conn->secondary_list, spkt);
             goto pri;
         }
     }
@@ -XXX,XX +XXX,XX @@ sec:
         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);
+            g_queue_push_tail(&conn->secondary_list, spkt);
             goto pri;
         } else if (mark == COLO_COMPARE_FREE_SECONDARY) {
             conn->compare_seq = spkt->seq_end;
@@ -XXX,XX +XXX,XX @@ sec:
             goto pri;
         }
     } else {
-        g_queue_push_head(&conn->primary_list, ppkt);
-        g_queue_push_head(&conn->secondary_list, spkt);
+        g_queue_push_tail(&conn->primary_list, ppkt);
+        g_queue_push_tail(&conn->secondary_list, spkt);
 
 #ifdef DEBUG_COLO_PACKETS
         qemu_hexdump(stderr, "colo-compare ppkt", ppkt->data, ppkt->size);
@@ -XXX,XX +XXX,XX @@ static void colo_compare_packet(CompareState *s, Connection *conn,
 
     while (!g_queue_is_empty(&conn->primary_list) &&
            !g_queue_is_empty(&conn->secondary_list)) {
-        pkt = g_queue_pop_head(&conn->primary_list);
+        pkt = g_queue_pop_tail(&conn->primary_list);
         result = g_queue_find_custom(&conn->secondary_list,
                  pkt, (GCompareFunc)HandlePacket);
 
@@ -XXX,XX +XXX,XX @@ static void colo_compare_packet(CompareState *s, Connection *conn,
              * timeout, it will trigger a checkpoint request.
              */
             trace_colo_compare_main("packet different");
-            g_queue_push_head(&conn->primary_list, pkt);
+            g_queue_push_tail(&conn->primary_list, pkt);
 
             colo_compare_inconsistency_notify(s);
             break;
@@ -XXX,XX +XXX,XX @@ static int compare_chr_send(CompareState *s,
         entry->buf = g_malloc(size);
         memcpy(entry->buf, buf, size);
     }
-    g_queue_push_head(&sendco->send_list, entry);
+    g_queue_push_tail(&sendco->send_list, entry);
 
     if (sendco->done) {
         sendco->co = qemu_coroutine_create(_compare_chr_send, sendco);
@@ -XXX,XX +XXX,XX @@ static void colo_flush_packets(void *opaque, void *user_data)
     Packet *pkt = NULL;
 
     while (!g_queue_is_empty(&conn->primary_list)) {
-        pkt = g_queue_pop_head(&conn->primary_list);
+        pkt = g_queue_pop_tail(&conn->primary_list);
         compare_chr_send(s,
                          pkt->data,
                          pkt->size,
@@ -XXX,XX +XXX,XX @@ static void colo_flush_packets(void *opaque, void *user_data)
         packet_destroy_partial(pkt, NULL);
     }
     while (!g_queue_is_empty(&conn->secondary_list)) {
-        pkt = g_queue_pop_head(&conn->secondary_list);
+        pkt = g_queue_pop_tail(&conn->secondary_list);
         packet_destroy(pkt, NULL);
     }
 }
-- 
2.7.4

From: Rao Lei <lei.rao@intel.com>

This patch is to improve the logic of QEMU main thread sleep code in
qemu_chr_write_buffer() where it can be blocked and can't run other
coroutines during COLO IO stress test.

Our approach is to put filter_send() in a coroutine. In this way,
filter_send() will call qemu_coroutine_yield() in qemu_co_sleep_ns(),
so that it can be scheduled out and QEMU main thread has opportunity to
run other tasks.

Signed-off-by: Lei Rao <lei.rao@intel.com>
Signed-off-by: Zhang Chen <chen.zhang@intel.com>
Reviewed-by: Li Zhijian <lizhijian@fujitsu.com>
Reviewed-by: Zhang Chen <chen.zhang@intel.com>
Signed-off-by: Jason Wang <jasowang@redhat.com>
---
 net/filter-mirror.c | 66 ++++++++++++++++++++++++++++++++++++++++++-----------
 1 file changed, 53 insertions(+), 13 deletions(-)

diff --git a/net/filter-mirror.c b/net/filter-mirror.c
index XXXXXXX..XXXXXXX 100644
--- a/net/filter-mirror.c
+++ b/net/filter-mirror.c
@@ -XXX,XX +XXX,XX @@
 #include "chardev/char-fe.h"
 #include "qemu/iov.h"
 #include "qemu/sockets.h"
+#include "block/aio-wait.h"
 
 #define TYPE_FILTER_MIRROR "filter-mirror"
 typedef struct MirrorState MirrorState;
@@ -XXX,XX +XXX,XX @@ struct MirrorState {
     bool vnet_hdr;
 };
 
-static int filter_send(MirrorState *s,
-                       const struct iovec *iov,
-                       int iovcnt)
+typedef struct FilterSendCo {
+    MirrorState *s;
+    char *buf;
+    ssize_t size;
+    bool done;
+    int ret;
+} FilterSendCo;
+
+static int _filter_send(MirrorState *s,
+                       char *buf,
+                       ssize_t size)
 {
     NetFilterState *nf = NETFILTER(s);
     int ret = 0;
-    ssize_t size = 0;
     uint32_t len = 0;
-    char *buf;
-
-    size = iov_size(iov, iovcnt);
-    if (!size) {
-        return 0;
-    }
 
     len = htonl(size);
     ret = qemu_chr_fe_write_all(&s->chr_out, (uint8_t *)&len, sizeof(len));
@@ -XXX,XX +XXX,XX @@ static int filter_send(MirrorState *s,
         }
     }
 
-    buf = g_malloc(size);
-    iov_to_buf(iov, iovcnt, 0, buf, size);
     ret = qemu_chr_fe_write_all(&s->chr_out, (uint8_t *)buf, size);
-    g_free(buf);
     if (ret != size) {
         goto err;
     }
@@ -XXX,XX +XXX,XX @@ err:
     return ret < 0 ? ret : -EIO;
 }
 
+static void coroutine_fn filter_send_co(void *opaque)
+{
+    FilterSendCo *data = opaque;
+
+    data->ret = _filter_send(data->s, data->buf, data->size);
+    data->done = true;
+    g_free(data->buf);
+    aio_wait_kick();
+}
+
+static int filter_send(MirrorState *s,
+                       const struct iovec *iov,
+                       int iovcnt)
+{
+    ssize_t size = iov_size(iov, iovcnt);
+    char *buf = NULL;
+
+    if (!size) {
+        return 0;
+    }
+
+    buf = g_malloc(size);
+    iov_to_buf(iov, iovcnt, 0, buf, size);
+
+    FilterSendCo data = {
+        .s = s,
+        .size = size,
+        .buf = buf,
+        .ret = 0,
+    };
+
+    Coroutine *co = qemu_coroutine_create(filter_send_co, &data);
+    qemu_coroutine_enter(co);
+
+    while (!data.done) {
+        aio_poll(qemu_get_aio_context(), true);
+    }
+
+    return data.ret;
+}
+
 static void redirector_to_filter(NetFilterState *nf,
                                  const uint8_t *buf,
                                  int len)
-- 
2.7.4

From: Vladislav Yaroshchuk <yaroshchuk2000@gmail.com>

Signed-off-by: Vladislav Yaroshchuk <yaroshchuk2000@gmail.com>
Signed-off-by: Jason Wang <jasowang@redhat.com>
---
 meson.build                   | 4 ++++
 meson_options.txt             | 2 ++
 scripts/meson-buildoptions.sh | 3 +++
 3 files changed, 9 insertions(+)

diff --git a/meson.build b/meson.build
index XXXXXXX..XXXXXXX 100644
--- a/meson.build
+++ b/meson.build
@@ -XXX,XX +XXX,XX @@ if cocoa.found() and get_option('gtk').enabled()
   error('Cocoa and GTK+ cannot be enabled at the same time')
 endif
 
+vmnet = dependency('appleframeworks', modules: 'vmnet', required: get_option('vmnet'))
+
 seccomp = not_found
 if not get_option('seccomp').auto() or have_system or have_tools
   seccomp = dependency('libseccomp', version: '>=2.3.0',
@@ -XXX,XX +XXX,XX @@ config_host_data.set('CONFIG_SECCOMP', seccomp.found())
 config_host_data.set('CONFIG_SNAPPY', snappy.found())
 config_host_data.set('CONFIG_USB_LIBUSB', libusb.found())
 config_host_data.set('CONFIG_VDE', vde.found())
+config_host_data.set('CONFIG_VMNET', vmnet.found())
 config_host_data.set('CONFIG_VHOST_USER_BLK_SERVER', have_vhost_user_blk_server)
 config_host_data.set('CONFIG_VNC', vnc.found())
 config_host_data.set('CONFIG_VNC_JPEG', jpeg.found())
@@ -XXX,XX +XXX,XX @@ endif
 summary_info += {'JACK support':      jack}
 summary_info += {'brlapi support':    brlapi}
 summary_info += {'vde support':       vde}
+summary_info += {'vmnet.framework support': vmnet}
 summary_info += {'netmap support':    have_netmap}
 summary_info += {'l2tpv3 support':    have_l2tpv3}
 summary_info += {'Linux AIO support': libaio}
diff --git a/meson_options.txt b/meson_options.txt
index XXXXXXX..XXXXXXX 100644
--- a/meson_options.txt
+++ b/meson_options.txt
@@ -XXX,XX +XXX,XX @@ option('netmap', type : 'feature', value : 'auto',
        description: 'netmap network backend support')
 option('vde', type : 'feature', value : 'auto',
        description: 'vde network backend support')
+option('vmnet', type : 'feature', value : 'auto',
+       description: 'vmnet.framework network backend support')
 option('virglrenderer', type : 'feature', value : 'auto',
        description: 'virgl rendering support')
 option('vnc', type : 'feature', value : 'auto',
diff --git a/scripts/meson-buildoptions.sh b/scripts/meson-buildoptions.sh
index XXXXXXX..XXXXXXX 100644
--- a/scripts/meson-buildoptions.sh
+++ b/scripts/meson-buildoptions.sh
@@ -XXX,XX +XXX,XX @@ meson_options_help() {
   printf "%s\n" '  u2f             U2F emulation support'
   printf "%s\n" '  usb-redir       libusbredir support'
   printf "%s\n" '  vde             vde network backend support'
+  printf "%s\n" '  vmnet           vmnet.framework network backend support'
   printf "%s\n" '  vhost-user-blk-server'
   printf "%s\n" '                  build vhost-user-blk server'
   printf "%s\n" '  virglrenderer   virgl rendering support'
@@ -XXX,XX +XXX,XX @@ _meson_option_parse() {
     --disable-usb-redir) printf "%s" -Dusb_redir=disabled ;;
     --enable-vde) printf "%s" -Dvde=enabled ;;
     --disable-vde) printf "%s" -Dvde=disabled ;;
+    --enable-vmnet) printf "%s" -Dvmnet=enabled ;;
+    --disable-vmnet) printf "%s" -Dvmnet=disabled ;;
     --enable-vhost-user-blk-server) printf "%s" -Dvhost_user_blk_server=enabled ;;
     --disable-vhost-user-blk-server) printf "%s" -Dvhost_user_blk_server=disabled ;;
     --enable-virglrenderer) printf "%s" -Dvirglrenderer=enabled ;;
-- 
2.7.4

From: Vladislav Yaroshchuk <yaroshchuk2000@gmail.com>

The vmnet framework is an API for virtual machines to read and write
packets.

The API allows a Guest OS interface to be in host mode or shared
mode. Interfaces in host mode can communicate with the native host
system and other interfaces running in host mode. In shared mode, the
network interface can send and receive packets to the Internet, the
native host, and other interfaces running in sharing mode.

Create separate netdevs for each vmnet operating mode:

- vmnet-host
- vmnet-shared
- vmnet-bridged

Signed-off-by: Vladislav Yaroshchuk <yaroshchuk2000@gmail.com>
Signed-off-by: Jason Wang <jasowang@redhat.com>
---
 net/clients.h       |  11 +++++
 net/meson.build     |   7 +++
 net/net.c           |  10 ++++
 net/vmnet-bridged.m |  25 ++++++++++
 net/vmnet-common.m  |  19 ++++++++
 net/vmnet-host.c    |  24 ++++++++++
 net/vmnet-shared.c  |  25 ++++++++++
 net/vmnet_int.h     |  25 ++++++++++
 qapi/net.json       | 132 +++++++++++++++++++++++++++++++++++++++++++++++++++-
 9 files changed, 276 insertions(+), 2 deletions(-)
 create mode 100644 net/vmnet-bridged.m
 create mode 100644 net/vmnet-common.m
 create mode 100644 net/vmnet-host.c
 create mode 100644 net/vmnet-shared.c
 create mode 100644 net/vmnet_int.h

diff --git a/net/clients.h b/net/clients.h
index XXXXXXX..XXXXXXX 100644
--- a/net/clients.h
+++ b/net/clients.h
@@ -XXX,XX +XXX,XX @@ int net_init_vhost_user(const Netdev *netdev, const char *name,
 
 int net_init_vhost_vdpa(const Netdev *netdev, const char *name,
                         NetClientState *peer, Error **errp);
+#ifdef CONFIG_VMNET
+int net_init_vmnet_host(const Netdev *netdev, const char *name,
+                          NetClientState *peer, Error **errp);
+
+int net_init_vmnet_shared(const Netdev *netdev, const char *name,
+                          NetClientState *peer, Error **errp);
+
+int net_init_vmnet_bridged(const Netdev *netdev, const char *name,
+                          NetClientState *peer, Error **errp);
+#endif /* CONFIG_VMNET */
+
 #endif /* QEMU_NET_CLIENTS_H */
diff --git a/net/meson.build b/net/meson.build
index XXXXXXX..XXXXXXX 100644
--- a/net/meson.build
+++ b/net/meson.build
@@ -XXX,XX +XXX,XX @@ softmmu_ss.add(when: 'CONFIG_POSIX', if_true: files(tap_posix))
 softmmu_ss.add(when: 'CONFIG_WIN32', if_true: files('tap-win32.c'))
 softmmu_ss.add(when: 'CONFIG_VHOST_NET_VDPA', if_true: files('vhost-vdpa.c'))
 
+vmnet_files = files(
+  'vmnet-common.m',
+  'vmnet-bridged.m',
+  'vmnet-host.c',
+  'vmnet-shared.c'
+)
+softmmu_ss.add(when: vmnet, if_true: vmnet_files)
 subdir('can')
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 (* const net_client_init_fun[NET_CLIENT_DRIVER__MAX])(
 #ifdef CONFIG_L2TPV3
         [NET_CLIENT_DRIVER_L2TPV3]    = net_init_l2tpv3,
 #endif
+#ifdef CONFIG_VMNET
+        [NET_CLIENT_DRIVER_VMNET_HOST] = net_init_vmnet_host,
+        [NET_CLIENT_DRIVER_VMNET_SHARED] = net_init_vmnet_shared,
+        [NET_CLIENT_DRIVER_VMNET_BRIDGED] = net_init_vmnet_bridged,
+#endif /* CONFIG_VMNET */
 };
 
 
@@ -XXX,XX +XXX,XX @@ void show_netdevs(void)
 #ifdef CONFIG_VHOST_VDPA
         "vhost-vdpa",
 #endif
+#ifdef CONFIG_VMNET
+        "vmnet-host",
+        "vmnet-shared",
+        "vmnet-bridged",
+#endif
     };
 
     qemu_printf("Available netdev backend types:\n");
diff --git a/net/vmnet-bridged.m b/net/vmnet-bridged.m
new file mode 100644
index XXXXXXX..XXXXXXX
--- /dev/null
+++ b/net/vmnet-bridged.m
@@ -XXX,XX +XXX,XX @@
+/*
+ * vmnet-bridged.m
+ *
+ * Copyright(c) 2021 Vladislav Yaroshchuk <yaroshchuk2000@gmail.com>
+ *
+ * This work is licensed under the terms of the GNU GPL, version 2 or later.
+ * See the COPYING file in the top-level directory.
+ *
+ */
+
+#include "qemu/osdep.h"
+#include "qapi/qapi-types-net.h"
+#include "vmnet_int.h"
+#include "clients.h"
+#include "qemu/error-report.h"
+#include "qapi/error.h"
+
+#include <vmnet/vmnet.h>
+
+int net_init_vmnet_bridged(const Netdev *netdev, const char *name,
+                           NetClientState *peer, Error **errp)
+{
+  error_setg(errp, "vmnet-bridged is not implemented yet");
+  return -1;
+}
diff --git a/net/vmnet-common.m b/net/vmnet-common.m
new file mode 100644
index XXXXXXX..XXXXXXX
--- /dev/null
+++ b/net/vmnet-common.m
@@ -XXX,XX +XXX,XX @@
+/*
+ * vmnet-common.m - network client wrapper for Apple vmnet.framework
+ *
+ * Copyright(c) 2021 Vladislav Yaroshchuk <yaroshchuk2000@gmail.com>
+ * Copyright(c) 2021 Phillip Tennen <phillip@axleos.com>
+ *
+ * This work is licensed under the terms of the GNU GPL, version 2 or later.
+ * See the COPYING file in the top-level directory.
+ *
+ */
+
+#include "qemu/osdep.h"
+#include "qapi/qapi-types-net.h"
+#include "vmnet_int.h"
+#include "clients.h"
+#include "qemu/error-report.h"
+#include "qapi/error.h"
+
+#include <vmnet/vmnet.h>
diff --git a/net/vmnet-host.c b/net/vmnet-host.c
new file mode 100644
index XXXXXXX..XXXXXXX
--- /dev/null
+++ b/net/vmnet-host.c
@@ -XXX,XX +XXX,XX @@
+/*
+ * vmnet-host.c
+ *
+ * Copyright(c) 2021 Vladislav Yaroshchuk <yaroshchuk2000@gmail.com>
+ *
+ * This work is licensed under the terms of the GNU GPL, version 2 or later.
+ * See the COPYING file in the top-level directory.
+ *
+ */
+
+#include "qemu/osdep.h"
+#include "qapi/qapi-types-net.h"
+#include "vmnet_int.h"
+#include "clients.h"
+#include "qemu/error-report.h"
+#include "qapi/error.h"
+
+#include <vmnet/vmnet.h>
+
+int net_init_vmnet_host(const Netdev *netdev, const char *name,
+                        NetClientState *peer, Error **errp) {
+  error_setg(errp, "vmnet-host is not implemented yet");
+  return -1;
+}
diff --git a/net/vmnet-shared.c b/net/vmnet-shared.c
new file mode 100644
index XXXXXXX..XXXXXXX
--- /dev/null
+++ b/net/vmnet-shared.c
@@ -XXX,XX +XXX,XX @@
+/*
+ * vmnet-shared.c
+ *
+ * Copyright(c) 2021 Vladislav Yaroshchuk <yaroshchuk2000@gmail.com>
+ *
+ * This work is licensed under the terms of the GNU GPL, version 2 or later.
+ * See the COPYING file in the top-level directory.
+ *
+ */
+
+#include "qemu/osdep.h"
+#include "qapi/qapi-types-net.h"
+#include "vmnet_int.h"
+#include "clients.h"
+#include "qemu/error-report.h"
+#include "qapi/error.h"
+
+#include <vmnet/vmnet.h>
+
+int net_init_vmnet_shared(const Netdev *netdev, const char *name,
+                          NetClientState *peer, Error **errp)
+{
+  error_setg(errp, "vmnet-shared is not implemented yet");
+  return -1;
+}
diff --git a/net/vmnet_int.h b/net/vmnet_int.h
new file mode 100644
index XXXXXXX..XXXXXXX
--- /dev/null
+++ b/net/vmnet_int.h
@@ -XXX,XX +XXX,XX @@
+/*
+ * vmnet_int.h
+ *
+ * Copyright(c) 2021 Vladislav Yaroshchuk <yaroshchuk2000@gmail.com>
+ *
+ * This work is licensed under the terms of the GNU GPL, version 2 or later.
+ * See the COPYING file in the top-level directory.
+ *
+ */
+#ifndef VMNET_INT_H
+#define VMNET_INT_H
+
+#include "qemu/osdep.h"
+#include "vmnet_int.h"
+#include "clients.h"
+
+#include <vmnet/vmnet.h>
+
+typedef struct VmnetCommonState {
+  NetClientState nc;
+
+} VmnetCommonState;
+
+
+#endif /* VMNET_INT_H */
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 @@
     '*queues':       'int' } }
 
 ##
+# @NetdevVmnetHostOptions:
+#
+# vmnet (host mode) network backend.
+#
+# Allows the vmnet interface to communicate with other vmnet
+# interfaces that are in host mode and also with the host.
+#
+# @start-address: The starting IPv4 address to use for the interface.
+#                 Must be in the private IP range (RFC 1918). Must be
+#                 specified along with @end-address and @subnet-mask.
+#                 This address is used as the gateway address. The
+#                 subsequent address up to and including end-address are
+#                 placed in the DHCP pool.
+#
+# @end-address: The DHCP IPv4 range end address to use for the
+#               interface. Must be in the private IP range (RFC 1918).
+#               Must be specified along with @start-address and
+#               @subnet-mask.
+#
+# @subnet-mask: The IPv4 subnet mask to use on the interface. Must
+#               be specified along with @start-address and @subnet-mask.
+#
+# @isolated: Enable isolation for this interface. Interface isolation
+#            ensures that vmnet interface is not able to communicate
+#            with any other vmnet interfaces. Only communication with
+#            host is allowed.
+#
+# @net-uuid: The identifier (UUID) to uniquely identify the isolated
+#            network vmnet interface should be added to. If
+#            set, no DHCP service is provided for this interface and
+#            network communication is allowed only with other interfaces
+#            added to this network identified by the UUID.
+#
+# Since: 7.0
+##
+{ 'struct': 'NetdevVmnetHostOptions',
+  'data': {
+    '*start-address': 'str',
+    '*end-address':   'str',
+    '*subnet-mask':   'str',
+    '*isolated':      'bool',
+    '*net-uuid':      'str' },
+  'if': 'CONFIG_VMNET' }
+
+##
+# @NetdevVmnetSharedOptions:
+#
+# vmnet (shared mode) network backend.
+#
+# Allows traffic originating from the vmnet interface to reach the
+# Internet through a network address translator (NAT).
+# The vmnet interface can communicate with the host and with
+# other shared mode interfaces on the same subnet. If no DHCP
+# settings, subnet mask and IPv6 prefix specified, the interface can
+# communicate with any of other interfaces in shared mode.
+#
+# @start-address: The starting IPv4 address to use for the interface.
+#                 Must be in the private IP range (RFC 1918). Must be
+#                 specified along with @end-address and @subnet-mask.
+#                 This address is used as the gateway address. The
+#                 subsequent address up to and including end-address are
+#                 placed in the DHCP pool.
+#
+# @end-address: The DHCP IPv4 range end address to use for the
+#               interface. Must be in the private IP range (RFC 1918).
+#               Must be specified along with @start-address and @subnet-mask.
+#
+# @subnet-mask: The IPv4 subnet mask to use on the interface. Must
+#                be specified along with @start-address and @subnet-mask.
+#
+# @isolated: Enable isolation for this interface. Interface isolation
+#            ensures that vmnet interface is not able to communicate
+#            with any other vmnet interfaces. Only communication with
+#            host is allowed.
+#
+# @nat66-prefix: The IPv6 prefix to use into guest network. Must be a
+#                unique local address i.e. start with fd00::/8 and have
+#                length of 64.
+#
+# Since: 7.0
+##
+{ 'struct': 'NetdevVmnetSharedOptions',
+  'data': {
+    '*start-address': 'str',
+    '*end-address':   'str',
+    '*subnet-mask':   'str',
+    '*isolated':      'bool',
+    '*nat66-prefix':  'str' },
+  'if': 'CONFIG_VMNET' }
+
+##
+# @NetdevVmnetBridgedOptions:
+#
+# vmnet (bridged mode) network backend.
+#
+# Bridges the vmnet interface with a physical network interface.
+#
+# @ifname: The name of the physical interface to be bridged.
+#
+# @isolated: Enable isolation for this interface. Interface isolation
+#            ensures that vmnet interface is not able to communicate
+#            with any other vmnet interfaces. Only communication with
+#            host is allowed.
+#
+# Since: 7.0
+##
+{ 'struct': 'NetdevVmnetBridgedOptions',
+  'data': {
+    'ifname':     'str',
+    '*isolated':  'str' },
+  'if': 'CONFIG_VMNET' }
+
+##
 # @NetClientDriver:
 #
 # Available netdev drivers.
@@ -XXX,XX +XXX,XX @@
 # Since: 2.7
 #
 #        @vhost-vdpa since 5.1
+#        @vmnet-host since 7.0
+#        @vmnet-shared since 7.0
+#        @vmnet-bridged since 7.0
 ##
 { 'enum': 'NetClientDriver',
   'data': [ 'none', 'nic', 'user', 'tap', 'l2tpv3', 'socket', 'vde',
-            'bridge', 'hubport', 'netmap', 'vhost-user', 'vhost-vdpa' ] }
+            'bridge', 'hubport', 'netmap', 'vhost-user', 'vhost-vdpa',
+            { 'name': 'vmnet-host', 'if': 'CONFIG_VMNET' },
+            { 'name': 'vmnet-shared', 'if': 'CONFIG_VMNET' },
+            { 'name': 'vmnet-bridged', 'if': 'CONFIG_VMNET' }] }
 
 ##
 # @Netdev:
@@ -XXX,XX +XXX,XX @@
 # Since: 1.2
 #
 #        'l2tpv3' - since 2.1
+#        'vmnet-host' - since 7.0
+#        'vmnet-shared' - since 7.0
+#        'vmnet-bridged' - since 7.0
 ##
 { 'union': 'Netdev',
   'base': { 'id': 'str', 'type': 'NetClientDriver' },
@@ -XXX,XX +XXX,XX @@
     'hubport':  'NetdevHubPortOptions',
     'netmap':   'NetdevNetmapOptions',
     'vhost-user': 'NetdevVhostUserOptions',
-    'vhost-vdpa': 'NetdevVhostVDPAOptions' } }
+    'vhost-vdpa': 'NetdevVhostVDPAOptions',
+    'vmnet-host': { 'type': 'NetdevVmnetHostOptions',
+                    'if': 'CONFIG_VMNET' },
+    'vmnet-shared': { 'type': 'NetdevVmnetSharedOptions',
+                      'if': 'CONFIG_VMNET' },
+    'vmnet-bridged': { 'type': 'NetdevVmnetBridgedOptions',
+                       'if': 'CONFIG_VMNET' } } }
 
 ##
 # @RxState:
-- 
2.7.4

From: Vladislav Yaroshchuk <yaroshchuk2000@gmail.com>

Interaction with vmnet.framework in different modes
differs only on configuration stage, so we can create
common `send`, `receive`, etc. procedures and reuse them.

vmnet.framework supports iov, but writing more than
one iov into vmnet interface fails with
'VMNET_INVALID_ARGUMENT'. Collecting provided iovs into
one and passing it to vmnet works fine. That's the
reason why receive_iov() left unimplemented. But it still
works with good enough performance having .receive()
implemented only.

Also, there is no way to unsubscribe from vmnet packages
receiving except registering and unregistering event
callback or simply drop packages just ignoring and
not processing them when related flag is set. Here we do
using the second way.

Signed-off-by: Phillip Tennen <phillip@axleos.com>
Signed-off-by: Vladislav Yaroshchuk <yaroshchuk2000@gmail.com>
Signed-off-by: Jason Wang <jasowang@redhat.com>
---
 net/vmnet-common.m | 311 +++++++++++++++++++++++++++++++++++++++++++++++++++++
 net/vmnet-shared.c |  74 ++++++++++++-
 net/vmnet_int.h    |  23 ++++
 3 files changed, 404 insertions(+), 4 deletions(-)

diff --git a/net/vmnet-common.m b/net/vmnet-common.m
index XXXXXXX..XXXXXXX 100644
--- a/net/vmnet-common.m
+++ b/net/vmnet-common.m
@@ -XXX,XX +XXX,XX @@
  */
 
 #include "qemu/osdep.h"
+#include "qemu/main-loop.h"
+#include "qemu/log.h"
 #include "qapi/qapi-types-net.h"
 #include "vmnet_int.h"
 #include "clients.h"
@@ -XXX,XX +XXX,XX @@
 #include "qapi/error.h"
 
 #include <vmnet/vmnet.h>
+#include <dispatch/dispatch.h>
+
+#ifdef DEBUG
+#define D(x) x
+#define D_LOG(...) qemu_log(__VA_ARGS__)
+#else
+#define D(x) do { } while (0)
+#define D_LOG(...) do { } while (0)
+#endif
+
+typedef struct vmpktdesc vmpktdesc_t;
+typedef struct iovec iovec_t;
+
+static void vmnet_set_send_enabled(VmnetCommonState *s, bool enable)
+{
+    s->send_enabled = enable;
+}
+
+
+static void vmnet_send_completed(NetClientState *nc, ssize_t len)
+{
+    VmnetCommonState *s = DO_UPCAST(VmnetCommonState, nc, nc);
+    vmnet_set_send_enabled(s, true);
+}
+
+
+static void vmnet_send(NetClientState *nc,
+                       interface_event_t event_id,
+                       xpc_object_t event)
+{
+    assert(event_id == VMNET_INTERFACE_PACKETS_AVAILABLE);
+
+    VmnetCommonState *s;
+    uint64_t packets_available;
+
+    struct iovec *iov;
+    struct vmpktdesc *packets;
+    int pkt_cnt;
+    int i;
+
+    vmnet_return_t if_status;
+    ssize_t size;
+
+    s = DO_UPCAST(VmnetCommonState, nc, nc);
+
+    packets_available = xpc_dictionary_get_uint64(
+        event,
+        vmnet_estimated_packets_available_key
+    );
+
+    pkt_cnt = (packets_available < VMNET_PACKETS_LIMIT) ?
+              packets_available :
+              VMNET_PACKETS_LIMIT;
+
+
+    iov = s->iov_buf;
+    packets = s->packets_buf;
+
+    for (i = 0; i < pkt_cnt; ++i) {
+        packets[i].vm_pkt_size = s->max_packet_size;
+        packets[i].vm_pkt_iovcnt = 1;
+        packets[i].vm_flags = 0;
+    }
+
+    if_status = vmnet_read(s->vmnet_if, packets, &pkt_cnt);
+    if (if_status != VMNET_SUCCESS) {
+        error_printf("vmnet: read failed: %s\n",
+                     vmnet_status_map_str(if_status));
+    }
+    qemu_mutex_lock_iothread();
+    for (i = 0; i < pkt_cnt; ++i) {
+        size = qemu_send_packet_async(nc,
+                                      iov[i].iov_base,
+                                      packets[i].vm_pkt_size,
+                                      vmnet_send_completed);
+        if (size == 0) {
+            vmnet_set_send_enabled(s, false);
+        } else if (size < 0) {
+            break;
+        }
+    }
+    qemu_mutex_unlock_iothread();
+
+}
+
+
+static void vmnet_register_event_callback(VmnetCommonState *s)
+{
+    dispatch_queue_t avail_pkt_q = dispatch_queue_create(
+        "org.qemu.vmnet.if_queue",
+        DISPATCH_QUEUE_SERIAL
+    );
+
+    vmnet_interface_set_event_callback(
+        s->vmnet_if,
+        VMNET_INTERFACE_PACKETS_AVAILABLE,
+        avail_pkt_q,
+        ^(interface_event_t event_id, xpc_object_t event) {
+          if (s->send_enabled) {
+              vmnet_send(&s->nc, event_id, event);
+          }
+        });
+}
+
+
+static void vmnet_bufs_init(VmnetCommonState *s)
+{
+    int i;
+    struct vmpktdesc *packets;
+    struct iovec *iov;
+
+    packets = s->packets_buf;
+    iov = s->iov_buf;
+
+    for (i = 0; i < VMNET_PACKETS_LIMIT; ++i) {
+        iov[i].iov_len = s->max_packet_size;
+        iov[i].iov_base = g_malloc0(iov[i].iov_len);
+        packets[i].vm_pkt_iov = iov + i;
+    }
+}
+
+
+const char *vmnet_status_map_str(vmnet_return_t status)
+{
+    switch (status) {
+    case VMNET_SUCCESS:
+        return "success";
+    case VMNET_FAILURE:
+        return "general failure";
+    case VMNET_MEM_FAILURE:
+        return "memory allocation failure";
+    case VMNET_INVALID_ARGUMENT:
+        return "invalid argument specified";
+    case VMNET_SETUP_INCOMPLETE:
+        return "interface setup is not complete";
+    case VMNET_INVALID_ACCESS:
+        return "invalid access, permission denied";
+    case VMNET_PACKET_TOO_BIG:
+        return "packet size is larger than MTU";
+    case VMNET_BUFFER_EXHAUSTED:
+        return "buffers exhausted in kernel";
+    case VMNET_TOO_MANY_PACKETS:
+        return "packet count exceeds limit";
+    case VMNET_SHARING_SERVICE_BUSY:
+        return "conflict, sharing service is in use";
+    default:
+        return "unknown vmnet error";
+    }
+}
+
+
+int vmnet_if_create(NetClientState *nc,
+                    xpc_object_t if_desc,
+                    Error **errp,
+                    void (*completion_callback)(xpc_object_t interface_param))
+{
+    VmnetCommonState *s;
+
+    dispatch_queue_t if_create_q;
+    dispatch_semaphore_t if_created_sem;
+
+    __block vmnet_return_t if_status;
+
+    if_create_q = dispatch_queue_create("org.qemu.vmnet.create",
+                                        DISPATCH_QUEUE_SERIAL);
+    if_created_sem = dispatch_semaphore_create(0);
+
+    xpc_dictionary_set_bool(
+        if_desc,
+        vmnet_allocate_mac_address_key,
+        false
+    );
+
+    D(D_LOG("vmnet.start.interface_desc:\n");
+    xpc_dictionary_apply(if_desc,
+                         ^bool(const char *k, xpc_object_t v) {
+                           char *desc = xpc_copy_description(v);
+                           D_LOG("  %s=%s\n", k, desc);
+                           free(desc);
+                           return true;
+                         }));
+
+    s = DO_UPCAST(VmnetCommonState, nc, nc);
+    s->vmnet_if = vmnet_start_interface(
+        if_desc,
+        if_create_q,
+        ^(vmnet_return_t status, xpc_object_t interface_param) {
+          if_status = status;
+          if (status != VMNET_SUCCESS || !interface_param) {
+              dispatch_semaphore_signal(if_created_sem);
+              return;
+          }
+
+          D(D_LOG("vmnet.start.interface_param:\n");
+                xpc_dictionary_apply(interface_param,
+                                     ^bool(const char *k, xpc_object_t v) {
+                                       char *desc = xpc_copy_description(v);
+                                       D_LOG("  %s=%s\n", k, desc);
+                                       free(desc);
+                                       return true;
+                                     }));
+
+          s->mtu = xpc_dictionary_get_uint64(
+              interface_param,
+              vmnet_mtu_key);
+          s->max_packet_size = xpc_dictionary_get_uint64(
+              interface_param,
+              vmnet_max_packet_size_key);
+
+          if (completion_callback) {
+              completion_callback(interface_param);
+          }
+          dispatch_semaphore_signal(if_created_sem);
+        });
+
+    if (s->vmnet_if == NULL) {
+        error_setg(errp, "unable to create interface with requested params");
+        return -1;
+    }
+
+    dispatch_semaphore_wait(if_created_sem, DISPATCH_TIME_FOREVER);
+    dispatch_release(if_create_q);
+
+    if (if_status != VMNET_SUCCESS) {
+        error_setg(errp,
+                   "cannot create vmnet interface: %s",
+                   vmnet_status_map_str(if_status));
+        return -1;
+    }
+
+    vmnet_register_event_callback(s);
+    vmnet_bufs_init(s);
+    vmnet_set_send_enabled(s, true);
+
+    return 0;
+}
+
+
+ssize_t vmnet_receive_common(NetClientState *nc,
+                             const uint8_t *buf,
+                             size_t size)
+{
+    VmnetCommonState *s;
+    vmpktdesc_t packet;
+    iovec_t iov;
+    int pkt_cnt;
+    vmnet_return_t if_status;
+
+    s = DO_UPCAST(VmnetCommonState, nc, nc);
+
+    if (size > s->max_packet_size) {
+        warn_report("vmnet: packet is too big, %zu > %llu\n",
+                    packet.vm_pkt_size,
+                    s->max_packet_size);
+        return -1;
+    }
+
+    iov.iov_base = (char *) buf;
+    iov.iov_len = size;
+
+    packet.vm_pkt_iovcnt = 1;
+    packet.vm_flags = 0;
+    packet.vm_pkt_size = size;
+    packet.vm_pkt_iov = &iov;
+
+    pkt_cnt = 1;
+    if_status = vmnet_write(s->vmnet_if, &packet, &pkt_cnt);
+
+    if (if_status != VMNET_SUCCESS) {
+        error_report("vmnet: write error: %s\n",
+                     vmnet_status_map_str(if_status));
+    }
+
+    if (if_status == VMNET_SUCCESS && pkt_cnt) {
+        return size;
+    }
+    return 0;
+}
+
+
+void vmnet_cleanup_common(NetClientState *nc)
+{
+    VmnetCommonState *s;
+    dispatch_queue_t if_destroy_q;
+
+    s = DO_UPCAST(VmnetCommonState, nc, nc);
+
+    qemu_purge_queued_packets(nc);
+    vmnet_set_send_enabled(s, false);
+
+    if (s->vmnet_if == NULL) {
+        return;
+    }
+
+    if_destroy_q = dispatch_queue_create(
+        "org.qemu.vmnet.destroy",
+        DISPATCH_QUEUE_SERIAL
+    );
+
+    vmnet_stop_interface(
+        s->vmnet_if,
+        if_destroy_q,
+        ^(vmnet_return_t status) {
+        });
+
+    for (int i = 0; i < VMNET_PACKETS_LIMIT; ++i) {
+        g_free(s->iov_buf[i].iov_base);
+    }
+}
diff --git a/net/vmnet-shared.c b/net/vmnet-shared.c
index XXXXXXX..XXXXXXX 100644
--- a/net/vmnet-shared.c
+++ b/net/vmnet-shared.c
@@ -XXX,XX +XXX,XX @@
 
 #include "qemu/osdep.h"
 #include "qapi/qapi-types-net.h"
+#include "qapi/error.h"
 #include "vmnet_int.h"
 #include "clients.h"
-#include "qemu/error-report.h"
-#include "qapi/error.h"
 
 #include <vmnet/vmnet.h>
 
+typedef struct VmnetSharedState {
+  VmnetCommonState cs;
+} VmnetSharedState;
+
+
+static xpc_object_t create_if_desc(const Netdev *netdev, Error **errp)
+{
+    const NetdevVmnetSharedOptions *options = &(netdev->u.vmnet_shared);
+    xpc_object_t if_desc = xpc_dictionary_create(NULL, NULL, 0);
+
+    xpc_dictionary_set_uint64(
+        if_desc,
+        vmnet_operation_mode_key,
+        VMNET_SHARED_MODE
+    );
+
+    xpc_dictionary_set_bool(
+        if_desc,
+        vmnet_enable_isolation_key,
+        options->isolated
+    );
+
+    if (options->has_nat66_prefix) {
+        xpc_dictionary_set_string(if_desc,
+                                  vmnet_nat66_prefix_key,
+                                  options->nat66_prefix);
+    }
+
+    if (options->has_start_address ||
+        options->has_end_address ||
+        options->has_subnet_mask) {
+
+        if (options->has_start_address &&
+            options->has_end_address &&
+            options->has_subnet_mask) {
+
+            xpc_dictionary_set_string(if_desc,
+                                      vmnet_start_address_key,
+                                      options->start_address);
+            xpc_dictionary_set_string(if_desc,
+                                      vmnet_end_address_key,
+                                      options->end_address);
+            xpc_dictionary_set_string(if_desc,
+                                      vmnet_subnet_mask_key,
+                                      options->subnet_mask);
+        } else {
+            error_setg(
+                errp,
+                "'start-address', 'end-address', 'subnet_mask' "
+                "should be provided together"
+            );
+        }
+    }
+
+    return if_desc;
+}
+
+static NetClientInfo net_vmnet_shared_info = {
+    .type = NET_CLIENT_DRIVER_VMNET_SHARED,
+    .size = sizeof(VmnetSharedState),
+    .receive = vmnet_receive_common,
+    .cleanup = vmnet_cleanup_common,
+};
+
 int net_init_vmnet_shared(const Netdev *netdev, const char *name,
                           NetClientState *peer, Error **errp)
 {
-  error_setg(errp, "vmnet-shared is not implemented yet");
-  return -1;
+    NetClientState *nc = qemu_new_net_client(&net_vmnet_shared_info,
+                                             peer, "vmnet-shared", name);
+    xpc_object_t if_desc = create_if_desc(netdev, errp);
+
+    return vmnet_if_create(nc, if_desc, errp, NULL);
 }
diff --git a/net/vmnet_int.h b/net/vmnet_int.h
index XXXXXXX..XXXXXXX 100644
--- a/net/vmnet_int.h
+++ b/net/vmnet_int.h
@@ -XXX,XX +XXX,XX @@
 
 #include <vmnet/vmnet.h>
 
+#define VMNET_PACKETS_LIMIT 50
+
 typedef struct VmnetCommonState {
   NetClientState nc;
+  interface_ref vmnet_if;
+
+  bool send_enabled;
+
+  uint64_t mtu;
+  uint64_t max_packet_size;
+
+  struct vmpktdesc packets_buf[VMNET_PACKETS_LIMIT];
+  struct iovec iov_buf[VMNET_PACKETS_LIMIT];
 
 } VmnetCommonState;
 
+const char *vmnet_status_map_str(vmnet_return_t status);
+
+int vmnet_if_create(NetClientState *nc,
+                    xpc_object_t if_desc,
+                    Error **errp,
+                    void (*completion_callback)(xpc_object_t interface_param));
+
+ssize_t vmnet_receive_common(NetClientState *nc,
+                             const uint8_t *buf,
+                             size_t size);
+
+void vmnet_cleanup_common(NetClientState *nc);
 
 #endif /* VMNET_INT_H */
-- 
2.7.4

From: Vladislav Yaroshchuk <yaroshchuk2000@gmail.com>

Signed-off-by: Vladislav Yaroshchuk <yaroshchuk2000@gmail.com>
Signed-off-by: Jason Wang <jasowang@redhat.com>
---
 net/vmnet-host.c | 93 ++++++++++++++++++++++++++++++++++++++++++++++++++++----
 1 file changed, 87 insertions(+), 6 deletions(-)

diff --git a/net/vmnet-host.c b/net/vmnet-host.c
index XXXXXXX..XXXXXXX 100644
--- a/net/vmnet-host.c
+++ b/net/vmnet-host.c
@@ -XXX,XX +XXX,XX @@
  */
 
 #include "qemu/osdep.h"
+#include "qemu/uuid.h"
 #include "qapi/qapi-types-net.h"
-#include "vmnet_int.h"
-#include "clients.h"
-#include "qemu/error-report.h"
 #include "qapi/error.h"
+#include "clients.h"
+#include "vmnet_int.h"
 
 #include <vmnet/vmnet.h>
 
+typedef struct VmnetHostState {
+  VmnetCommonState cs;
+  QemuUUID network_uuid;
+} VmnetHostState;
+
+static xpc_object_t create_if_desc(const Netdev *netdev,
+                                   NetClientState *nc,
+                                   Error **errp)
+{
+    const NetdevVmnetHostOptions *options = &(netdev->u.vmnet_host);
+    VmnetCommonState *cs = DO_UPCAST(VmnetCommonState, nc, nc);
+    VmnetHostState *hs = DO_UPCAST(VmnetHostState, cs, cs);
+
+    xpc_object_t if_desc = xpc_dictionary_create(NULL, NULL, 0);
+
+    xpc_dictionary_set_uint64(
+        if_desc,
+        vmnet_operation_mode_key,
+        VMNET_HOST_MODE
+    );
+
+    xpc_dictionary_set_bool(
+        if_desc,
+        vmnet_enable_isolation_key,
+        options->isolated
+    );
+
+    if (options->has_net_uuid) {
+        if (qemu_uuid_parse(options->net_uuid, &hs->network_uuid) < 0) {
+            error_setg(errp, "Invalid UUID provided in 'net-uuid'");
+        }
+
+        xpc_dictionary_set_uuid(
+            if_desc,
+            vmnet_network_identifier_key,
+            hs->network_uuid.data
+        );
+    }
+
+    if (options->has_start_address ||
+        options->has_end_address ||
+        options->has_subnet_mask) {
+
+        if (options->has_start_address &&
+            options->has_end_address &&
+            options->has_subnet_mask) {
+
+            xpc_dictionary_set_string(if_desc,
+                                      vmnet_start_address_key,
+                                      options->start_address);
+            xpc_dictionary_set_string(if_desc,
+                                      vmnet_end_address_key,
+                                      options->end_address);
+            xpc_dictionary_set_string(if_desc,
+                                      vmnet_subnet_mask_key,
+                                      options->subnet_mask);
+        } else {
+            error_setg(
+                errp,
+                "'start-address', 'end-address', 'subnet_mask' "
+                "should be provided together"
+            );
+        }
+    }
+
+    return if_desc;
+}
+
+static NetClientInfo net_vmnet_host_info = {
+    .type = NET_CLIENT_DRIVER_VMNET_HOST,
+    .size = sizeof(VmnetHostState),
+    .receive = vmnet_receive_common,
+    .cleanup = vmnet_cleanup_common,
+};
+
 int net_init_vmnet_host(const Netdev *netdev, const char *name,
-                        NetClientState *peer, Error **errp) {
-  error_setg(errp, "vmnet-host is not implemented yet");
-  return -1;
+                        NetClientState *peer, Error **errp)
+{
+    NetClientState *nc;
+    xpc_object_t if_desc;
+
+    nc = qemu_new_net_client(&net_vmnet_host_info,
+                             peer, "vmnet-host", name);
+    if_desc = create_if_desc(netdev, nc, errp);
+    return vmnet_if_create(nc, if_desc, errp, NULL);
 }
-- 
2.7.4

From: Vladislav Yaroshchuk <yaroshchuk2000@gmail.com>

Signed-off-by: Vladislav Yaroshchuk <yaroshchuk2000@gmail.com>
Signed-off-by: Jason Wang <jasowang@redhat.com>
---
 net/vmnet-bridged.m | 98 +++++++++++++++++++++++++++++++++++++++++++++++++----
 1 file changed, 92 insertions(+), 6 deletions(-)

diff --git a/net/vmnet-bridged.m b/net/vmnet-bridged.m
index XXXXXXX..XXXXXXX 100644
--- a/net/vmnet-bridged.m
+++ b/net/vmnet-bridged.m
@@ -XXX,XX +XXX,XX @@
 
 #include "qemu/osdep.h"
 #include "qapi/qapi-types-net.h"
-#include "vmnet_int.h"
-#include "clients.h"
-#include "qemu/error-report.h"
 #include "qapi/error.h"
+#include "clients.h"
+#include "vmnet_int.h"
 
 #include <vmnet/vmnet.h>
 
+typedef struct VmnetBridgedState {
+  VmnetCommonState cs;
+} VmnetBridgedState;
+
+static bool validate_ifname(const char *ifname)
+{
+    xpc_object_t shared_if_list = vmnet_copy_shared_interface_list();
+    __block bool match = false;
+
+    xpc_array_apply(
+        shared_if_list,
+        ^bool(size_t index, xpc_object_t value) {
+          if (strcmp(xpc_string_get_string_ptr(value), ifname) == 0) {
+              match = true;
+              return false;
+          }
+          return true;
+        });
+
+    return match;
+}
+
+static const char *get_valid_ifnames(void)
+{
+    xpc_object_t shared_if_list = vmnet_copy_shared_interface_list();
+    __block char *if_list = NULL;
+
+    xpc_array_apply(
+        shared_if_list,
+        ^bool(size_t index, xpc_object_t value) {
+          if_list = g_strconcat(xpc_string_get_string_ptr(value),
+                                " ",
+                                if_list,
+                                NULL);
+          return true;
+        });
+
+    if (if_list) {
+        return if_list;
+    }
+    return "[no interfaces]";
+}
+
+static xpc_object_t create_if_desc(const Netdev *netdev, Error **errp)
+{
+    const NetdevVmnetBridgedOptions *options = &(netdev->u.vmnet_bridged);
+    xpc_object_t if_desc = xpc_dictionary_create(NULL, NULL, 0);
+
+    xpc_dictionary_set_uint64(
+        if_desc,
+        vmnet_operation_mode_key,
+        VMNET_BRIDGED_MODE
+    );
+
+    xpc_dictionary_set_bool(
+        if_desc,
+        vmnet_enable_isolation_key,
+        options->isolated
+    );
+
+    if (validate_ifname(options->ifname)) {
+        xpc_dictionary_set_string(if_desc,
+                                  vmnet_shared_interface_name_key,
+                                  options->ifname);
+    } else {
+        return NULL;
+    }
+    return if_desc;
+}
+
+static NetClientInfo net_vmnet_bridged_info = {
+    .type = NET_CLIENT_DRIVER_VMNET_BRIDGED,
+    .size = sizeof(VmnetBridgedState),
+    .receive = vmnet_receive_common,
+    .cleanup = vmnet_cleanup_common,
+};
+
 int net_init_vmnet_bridged(const Netdev *netdev, const char *name,
                            NetClientState *peer, Error **errp)
 {
-  error_setg(errp, "vmnet-bridged is not implemented yet");
-  return -1;
-}
+    NetClientState *nc = qemu_new_net_client(&net_vmnet_bridged_info,
+                                             peer, "vmnet-bridged", name);
+    xpc_object_t if_desc = create_if_desc(netdev, errp);;
+
+    if (!if_desc) {
+        error_setg(errp,
+                   "unsupported ifname, should be one of: %s",
+                   get_valid_ifnames());
+        return -1;
+    }
+
+    return vmnet_if_create(nc, if_desc, errp, NULL);
+}
\ No newline at end of file
-- 
2.7.4

From: Vladislav Yaroshchuk <yaroshchuk2000@gmail.com>

Signed-off-by: Vladislav Yaroshchuk <yaroshchuk2000@gmail.com>
Signed-off-by: Jason Wang <jasowang@redhat.com>
---
 qemu-options.hx | 25 +++++++++++++++++++++++++
 1 file changed, 25 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,
     "-netdev vhost-vdpa,id=str,vhostdev=/path/to/dev\n"
     "                configure a vhost-vdpa network,Establish a vhost-vdpa netdev\n"
 #endif
+#ifdef CONFIG_VMNET
+    "-netdev vmnet-host,id=str[,isolated=on|off][,net-uuid=uuid]\n"
+    "         [,start-address=addr,end-address=addr,subnet-mask=mask]\n"
+    "                configure a vmnet network backend in host mode with ID 'str',\n"
+    "                isolate this interface from others with 'isolated',\n"
+    "                configure the address range and choose a subnet mask,\n"
+    "                specify network UUID 'uuid' to disable DHCP and interact with\n"
+    "                vmnet-host interfaces within this isolated network\n"
+    "-netdev vmnet-shared,id=str[,isolated=on|off][,nat66-prefix=addr]\n"
+    "         [,start-address=addr,end-address=addr,subnet-mask=mask]\n"
+    "                configure a vmnet network backend in shared mode with ID 'str',\n"
+    "                configure the address range and choose a subnet mask,\n"
+    "                set IPv6 ULA prefix (of length 64) to use for internal network,\n"
+    "                isolate this interface from others with 'isolated'\n"
+    "-netdev vmnet-bridged,id=str,ifname=name[,isolated=on|off]\n"
+    "                configure a vmnet network backend in bridged mode with ID 'str',\n"
+    "                use 'ifname=name' to select a physical network interface to be bridged,\n"
+    "                isolate this interface from others with 'isolated'\n"
+#endif
     "-netdev hubport,id=str,hubid=n[,netdev=nd]\n"
     "                configure a hub port on the hub with ID 'n'\n", QEMU_ARCH_ALL)
 DEF("nic", HAS_ARG, QEMU_OPTION_nic,
@@ -XXX,XX +XXX,XX @@ DEF("nic", HAS_ARG, QEMU_OPTION_nic,
 #ifdef CONFIG_POSIX
     "vhost-user|"
 #endif
+#ifdef CONFIG_VMNET
+    "vmnet-host|vmnet-shared|vmnet-bridged|"
+#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"
@@ -XXX,XX +XXX,XX @@ DEF("net", HAS_ARG, QEMU_OPTION_net,
 #ifdef CONFIG_NETMAP
     "netmap|"
 #endif
+#ifdef CONFIG_VMNET
+    "vmnet-host|vmnet-shared|vmnet-bridged|"
+#endif
     "socket][,option][,option][,...]\n"
     "                old way to initialize a host network interface\n"
     "                (use the -netdev option if possible instead)\n", QEMU_ARCH_ALL)
-- 
2.7.4