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

Version: GnuPG v1
 
 iQEcBAABAgAGBQJZbKrNAAoJEO8Ells5jWIRzWkH/0GgEkT5XqSPR8gTixxR5+aT
 1+LvlqI861/oR3aZ/1+6nzbFF4RBHO0TJb9v8HovfaOMU/tjaVMOGOD98+rqToa7
 2P2BTQo5jfsQhzGj2GBWnjpTqYunUjXdT0jjZAdERGqrNjoFOGhAjFXPvTKL23d5
 haDgRQgTh2z4w+rvuHNQ79S8tCDtUGvH1i9fIpWNnVLlv4Lea8XJlm7p2+jNQslF
 W2ysoQ6PR/3HihtqMwsh4ZBJAQfhEpJcrcLeq5wWEdg40U2JVA1MjpX0q58X6fRJ
 YQ36K0vxmdnxdCK6NnoMLkGqI12aRqJnFEq0Avc3dC2U0OWIfNk4mp8X0Vr8o+s=
 =z3QF
 -----END PGP SIGNATURE-----

Merge remote-tracking branch 'remotes/jasowang/tags/net-pull-request' into staging

# gpg: Signature made Mon 17 Jul 2017 13:17:17 BST
# gpg:                using RSA key 0xEF04965B398D6211
# gpg: Good signature from "Jason Wang (Jason Wang on RedHat) <jasowang@redhat.com>"
# gpg: WARNING: This key is not certified with a trusted signature!
# gpg:          There is no indication that the signature belongs to the owner.
# Primary key fingerprint: 215D 46F4 8246 689E C77F  3562 EF04 965B 398D 6211

* remotes/jasowang/tags/net-pull-request:
  virtio-net: fix offload ctrl endian
  virtion-net: Prefer is_power_of_2()
  docs/colo-proxy.txt: Update colo-proxy usage of net driver with vnet_header
  net/filter-rewriter.c: Make filter-rewriter support vnet_hdr_len
  net/colo-compare.c: Add vnet packet's tcp/udp/icmp compare
  net/colo.c: Add vnet packet parse feature in colo-proxy
  net/colo-compare.c: Make colo-compare support vnet_hdr_len
  net/colo-compare.c: Introduce parameter for compare_chr_send()
  net/colo.c: Make vnet_hdr_len as packet property
  net/filter-mirror.c: Add new option to enable vnet support for filter-redirector
  net/filter-mirror.c: Make filter mirror support vnet support.
  net/filter-mirror.c: Introduce parameter for filter_send()
  net/net.c: Add vnet_hdr support in SocketReadState
  net: Add vnet_hdr_len arguments in NetClientState

Signed-off-by: Peter Maydell <peter.maydell@linaro.org>

docs/colo-proxy.txt

@@ -182,6 +182,32 @@ 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.

hw/net/virtio-net.c

@@ -758,6 +758,8 @@ static int virtio_net_handle_offloads(VirtIONet *n, uint8_t cmd,
     if (cmd == VIRTIO_NET_CTRL_GUEST_OFFLOADS_SET) {
         uint64_t supported_offloads;
 
+        offloads = virtio_ldq_p(vdev, &offloads);
+
         if (!n->has_vnet_hdr) {
             return VIRTIO_NET_ERR;
         }
@@ -1942,7 +1944,7 @@ 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,

include/net/net.h

@@ -100,6 +100,7 @@ struct NetClientState {
     unsigned int queue_index;
     unsigned rxfilter_notify_enabled:1;
     int vring_enable;
+    int vnet_hdr_len;
     QTAILQ_HEAD(NetFilterHead, NetFilterState) filters;
 };
 
@@ -111,9 +112,13 @@ 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;
 };
@@ -176,7 +181,8 @@ 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 */
 

net/colo-compare.c

@@ -73,6 +73,7 @@ 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.
@@ -97,9 +98,10 @@ enum {
     SECONDARY_IN,
 };
 
-static int compare_chr_send(CharBackend *out,
+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)
 {
@@ -121,9 +123,13 @@ 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)) {
@@ -195,8 +201,11 @@ 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");
@@ -255,8 +264,9 @@ 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);
@@ -479,7 +489,10 @@ 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,
+                                   pkt->vnet_hdr_len);
             if (ret < 0) {
                 error_report("colo_send_primary_packet failed");
             }
@@ -500,9 +513,10 @@ 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)
+                            uint32_t size,
+                            uint32_t vnet_hdr_len)
 {
     int ret = 0;
     uint32_t len = htonl(size);
@@ -511,12 +525,24 @@ 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);
+    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;
     }
@@ -655,13 +681,32 @@ 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->chr_out, 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);
@@ -743,8 +788,8 @@ 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->pri_rs, compare_pri_rs_finalize, s->vnet_hdr);
-    net_socket_rs_init(&s->sec_rs, compare_sec_rs_finalize);
+    net_socket_rs_init(&s->sec_rs, compare_sec_rs_finalize, s->vnet_hdr);
 
     g_queue_init(&s->conn_list);
 
@@ -770,7 +815,10 @@ 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,
+                         pkt->vnet_hdr_len);
         packet_destroy(pkt, NULL);
     }
     while (!g_queue_is_empty(&conn->secondary_list)) {
@@ -788,6 +836,8 @@ 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);
@@ -797,6 +847,10 @@ 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)

net/colo.c

@@ -43,11 +43,11 @@ 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;
     }
@@ -73,7 +73,7 @@ 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;
     }
@@ -153,13 +153,14 @@ 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;
 }

net/colo.h

@@ -43,6 +43,8 @@ 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 {
@@ -82,7 +84,7 @@ 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 */

net/filter-mirror.c

@@ -41,12 +41,14 @@ typedef struct MirrorState {
     CharBackend chr_in;
     CharBackend chr_out;
     SocketReadState rs;
+    bool vnet_hdr;
 } MirrorState;
 
-static int filter_send(CharBackend *chr_out,
+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;
@@ -58,14 +60,31 @@ 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;
     }
 
+    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(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;
@@ -141,7 +160,7 @@ 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));
     }
@@ -164,7 +183,7 @@ 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));
         }
@@ -229,7 +248,7 @@ 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, s->vnet_hdr);
 
     if (s->indev) {
         chr = qemu_chr_find(s->indev);
@@ -318,6 +337,20 @@ 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);
@@ -335,18 +368,48 @@ 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);
+
     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)
 {
+    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)

net/filter-rewriter.c

@@ -17,6 +17,7 @@
 #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"
@@ -33,6 +34,7 @@ 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)
@@ -155,10 +157,16 @@ 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);
+
+    if (s->vnet_hdr) {
+        vnet_hdr_len = nf->netdev->vnet_hdr_len;
+    }
+
+    pkt = packet_new(buf, size, vnet_hdr_len);
     g_free(buf);
 
     /*
@@ -237,6 +245,32 @@ 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);
@@ -250,6 +284,7 @@ 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),
 };
 

net/net.c

@@ -492,6 +492,7 @@ void qemu_set_vnet_hdr_len(NetClientState *nc, int len)
         return;
     }
 
+    nc->vnet_hdr_len = len;
     nc->info->set_vnet_hdr_len(nc, len);
 }
 
@@ -1615,11 +1616,14 @@ 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;
 }
@@ -1634,8 +1638,12 @@ int net_fill_rstate(SocketReadState *rs, const uint8_t *buf, int size)
     unsigned int l;
 
     while (size > 0) {
-        /* reassemble a packet from the network */
+        /* Reassemble a packet from the network.
-        switch (rs->state) { /* 0 = getting length, 1 = getting data */
+         * 0 = getting length.
+         * 1 = getting vnet header length.
+         * 2 = getting data.
+         */
+        switch (rs->state) {
         case 0:
             l = 4 - rs->index;
             if (l > size) {
@@ -1649,10 +1657,31 @@ 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;

net/socket.c

@@ -174,7 +174,7 @@ 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));
 
@@ -366,7 +366,7 @@ 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 */
@@ -417,7 +417,7 @@ 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);
@@ -522,7 +522,7 @@ 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;

qemu-options.hx

@@ -4249,26 +4249,25 @@ 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
+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.
-@var{chardevid}
 
-@item -object filter-redirector,id=@var{id},netdev=@var{netdevid},indev=@var{chardevid},
+@item -object filter-redirector,id=@var{id},netdev=@var{netdevid},indev=@var{chardevid},outdev=@var{chardevid},queue=@var{all|rx|tx}[,vnet_hdr_support]
-outdev=@var{chardevid}[,queue=@var{all|rx|tx}]
 
 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.
 
-@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:
@@ -4283,13 +4282,13 @@ 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},
+@item -object colo-compare,id=@var{id},primary_in=@var{chardevid},secondary_in=@var{chardevid},outdev=@var{chardevid}[,vnet_hdr_support]
-outdev=@var{chardevid}
 
 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.