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

Version: GnuPG v1
 
 iQEcBAABAgAGBQJdGr/CAAoJEO8Ells5jWIRJY4H/10pMuRX11WDSQqc/ejQMywj
 3v+CBFTaNnCvbPqEFKH6p/1Y1KV/G1+ODzuat71QVjHqzlX/tCcLtNVrzIsozal+
 R42PADVpBuOGYC9CBBKZxKpORm4YEOApwERKAmjoTDKJUbho1TOOt60Vz7ctlybb
 nlEDdNogSKZ7ZxSj/Nn5NvaZnQPpS3ZpFcqMwr1ofQtCuUsYi9DNREd+NLwaknZS
 O3ib6nAFxBH4dpA0bSKWJHZi8QU1GcIdvs0iDeSnzvlCgwjbv3pM6eYkse90jXq+
 Sq0ZxSMb+97CCu54b5wu8EqOhzBaasVcKApR3NRQc5vHBI/1WMNB5eFWmfSpzWM=
 =3+Zi
 -----END PGP SIGNATURE-----

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

# gpg: Signature made Tue 02 Jul 2019 03:21:54 BST
# gpg:                using RSA key EF04965B398D6211
# gpg: Good signature from "Jason Wang (Jason Wang on RedHat) <jasowang@redhat.com>" [marginal]
# gpg: WARNING: This key is not certified with sufficiently trusted signatures!
# gpg:          It is not certain 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:
  migration/colo.c: Add missed filter notify for Xen COLO.
  COLO-compare: Add colo-compare remote notify support
  COLO-compare: Make the compare_chr_send() can send notification message.
  COLO-compare: Add remote notification chardev handler frame
  COLO-compare: Add new parameter to communicate with remote colo-frame
  net/announce: Expand test for stopping self announce
  net/announce: Add HMP optional ID
  net/announce: Add optional ID
  net/announce: Add HMP optional interface list
  net/announce: Allow optional list of interfaces
  net: remove unused get_str_sep() function
  net: use g_strsplit() for parsing host address and port
  net: avoid using variable length array in net_client_init()
  net: fix assertion failure when ipv6-prefixlen is not a number
  ftgmac100: do not link to netdev
  qemu-bridge-helper: Document known shortcomings
  MAINTAINERS: Add qemu-bridge-helper.c to "Network device backends"

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

MAINTAINERS

@@ -1944,6 +1944,7 @@ M: Jason Wang <jasowang@redhat.com>
 S: Maintained
 F: net/
 F: include/net/
+F: qemu-bridge-helper.c
 T: git https://github.com/jasowang/qemu.git net
 F: qapi/net.json
 

hmp-commands.hx

@@ -955,8 +955,8 @@ ETEXI
 
     {
         .name       = "announce_self",
-        .args_type  = "",
+        .args_type  = "interfaces:s?,id:s?",
-        .params     = "",
+        .params     = "[interfaces] [id]",
         .help       = "Trigger GARP/RARP announcements",
         .cmd        = hmp_announce_self,
     },
@@ -967,6 +967,9 @@ STEXI
 Trigger a round of GARP/RARP broadcasts; this is useful for explicitly updating the
 network infrastructure after a reconfiguration or some forms of migration.
 The timings of the round are set by the migration announce parameters.
+An optional comma separated @var{interfaces} list restricts the announce to the
+named set of interfaces. An optional @var{id} can be used to start a separate announce
+timer and to change the parameters of it later.
 ETEXI
 
     {

hw/net/ftgmac100.c

@@ -1017,8 +1017,6 @@ static void ftgmac100_realize(DeviceState *dev, Error **errp)
     sysbus_init_irq(sbd, &s->irq);
     qemu_macaddr_default_if_unset(&s->conf.macaddr);
 
-    s->conf.peers.ncs[0] = nd_table[0].netdev;
-
     s->nic = qemu_new_nic(&net_ftgmac100_info, &s->conf,
                           object_get_typename(OBJECT(dev)), DEVICE(dev)->id,
                           s);

hw/net/virtio-net.c

@@ -2360,7 +2360,7 @@ static int virtio_net_post_load_device(void *opaque, int version_id)
             timer_mod(n->announce_timer.tm,
                       qemu_clock_get_ms(n->announce_timer.type));
         } else {
-            qemu_announce_timer_del(&n->announce_timer);
+            qemu_announce_timer_del(&n->announce_timer, false);
         }
     }
 
@@ -2784,7 +2784,7 @@ static void virtio_net_device_unrealize(DeviceState *dev, Error **errp)
         virtio_net_del_queue(n, i);
     }
 
-    qemu_announce_timer_del(&n->announce_timer);
+    qemu_announce_timer_del(&n->announce_timer, false);
     g_free(n->vqs);
     qemu_del_nic(n->nic);
     virtio_net_rsc_cleanup(n);

include/net/announce.h

@@ -22,8 +22,12 @@ struct AnnounceTimer {
 /* Returns: update the timer to the next time point */
 int64_t qemu_announce_timer_step(AnnounceTimer *timer);
 
-/* Delete the underlying timer */
+/*
-void qemu_announce_timer_del(AnnounceTimer *timer);
+ * Delete the underlying timer and other data
+ * If 'free_named' true and the timer is a named timer, then remove
+ * it from the list of named timers and free the AnnounceTimer itself.
+ */
+void qemu_announce_timer_del(AnnounceTimer *timer, bool free_named);
 
 /*
  * Under BQL/main thread

migration/colo.c

@@ -259,6 +259,8 @@ ReplicationStatus *qmp_query_xen_replication_status(Error **errp)
 void qmp_xen_colo_do_checkpoint(Error **errp)
 {
     replication_do_checkpoint_all(errp);
+    /* Notify all filters of all NIC to do checkpoint */
+    colo_notify_filters_event(COLO_EVENT_CHECKPOINT, errp);
 }
 #endif
 

monitor/hmp-cmds.c

@@ -27,6 +27,7 @@
 #include "monitor/monitor-internal.h"
 #include "monitor/qdev.h"
 #include "qapi/error.h"
+#include "qapi/clone-visitor.h"
 #include "qapi/opts-visitor.h"
 #include "qapi/qapi-builtin-visit.h"
 #include "qapi/qapi-commands-block.h"
@@ -38,6 +39,7 @@
 #include "qapi/qapi-commands-run-state.h"
 #include "qapi/qapi-commands-tpm.h"
 #include "qapi/qapi-commands-ui.h"
+#include "qapi/qapi-visit-net.h"
 #include "qapi/qmp/qdict.h"
 #include "qapi/qmp/qerror.h"
 #include "qapi/string-input-visitor.h"
@@ -67,6 +69,32 @@ static void hmp_handle_error(Monitor *mon, Error **errp)
     }
 }
 
+/*
+ * Produce a strList from a comma separated list.
+ * A NULL or empty input string return NULL.
+ */
+static strList *strList_from_comma_list(const char *in)
+{
+    strList *res = NULL;
+    strList **hook = &res;
+
+    while (in && in[0]) {
+        char *comma = strchr(in, ',');
+        *hook = g_new0(strList, 1);
+
+        if (comma) {
+            (*hook)->value = g_strndup(in, comma - in);
+            in = comma + 1; /* skip the , */
+        } else {
+            (*hook)->value = g_strdup(in);
+            in = NULL;
+        }
+        hook = &(*hook)->next;
+    }
+
+    return res;
+}
+
 void hmp_info_name(Monitor *mon, const QDict *qdict)
 {
     NameInfo *info;
@@ -1631,7 +1659,18 @@ void hmp_info_snapshots(Monitor *mon, const QDict *qdict)
 
 void hmp_announce_self(Monitor *mon, const QDict *qdict)
 {
-    qmp_announce_self(migrate_announce_params(), NULL);
+    const char *interfaces_str = qdict_get_try_str(qdict, "interfaces");
+    const char *id = qdict_get_try_str(qdict, "id");
+    AnnounceParameters *params = QAPI_CLONE(AnnounceParameters,
+                                            migrate_announce_params());
+
+    qapi_free_strList(params->interfaces);
+    params->interfaces = strList_from_comma_list(interfaces_str);
+    params->has_interfaces = params->interfaces != NULL;
+    params->id = g_strdup(id);
+    params->has_id = !!params->id;
+    qmp_announce_self(params, NULL);
+    qapi_free_AnnounceParameters(params);
 }
 
 void hmp_migrate_cancel(Monitor *mon, const QDict *qdict)

net/announce.c

@@ -15,6 +15,8 @@
 #include "qapi/qapi-commands-net.h"
 #include "trace.h"
 
+static GData *named_timers;
+
 int64_t qemu_announce_timer_step(AnnounceTimer *timer)
 {
     int64_t step;
@@ -31,13 +33,38 @@ int64_t qemu_announce_timer_step(AnnounceTimer *timer)
     return step;
 }
 
-void qemu_announce_timer_del(AnnounceTimer *timer)
+/*
+ * If 'free_named' is true, then remove the timer from the list
+ * and free the timer itself.
+ */
+void qemu_announce_timer_del(AnnounceTimer *timer, bool free_named)
 {
+    bool free_timer = false;
     if (timer->tm) {
         timer_del(timer->tm);
         timer_free(timer->tm);
         timer->tm = NULL;
     }
+    qapi_free_strList(timer->params.interfaces);
+    timer->params.interfaces = NULL;
+    if (free_named && timer->params.has_id) {
+        AnnounceTimer *list_timer;
+        /*
+         * Sanity check: There should only be one timer on the list with
+         * the id.
+         */
+        list_timer = g_datalist_get_data(&named_timers, timer->params.id);
+        assert(timer == list_timer);
+        free_timer = true;
+        g_datalist_remove_data(&named_timers, timer->params.id);
+    }
+    trace_qemu_announce_timer_del(free_named, free_timer, timer->params.id);
+    g_free(timer->params.id);
+    timer->params.id = NULL;
+
+    if (free_timer) {
+        g_free(timer);
+    }
 }
 
 /*
@@ -54,7 +81,7 @@ void qemu_announce_timer_reset(AnnounceTimer *timer,
      * We're under the BQL, so the current timer can't
      * be firing, so we should be able to delete it.
      */
-    qemu_announce_timer_del(timer);
+    qemu_announce_timer_del(timer, false);
 
     QAPI_CLONE_MEMBERS(AnnounceParameters, &timer->params, params);
     timer->round = params->rounds;
@@ -96,29 +123,53 @@ static int announce_self_create(uint8_t *buf,
 
 static void qemu_announce_self_iter(NICState *nic, void *opaque)
 {
+    AnnounceTimer *timer = opaque;
     uint8_t buf[60];
     int len;
+    bool skip;
 
-    trace_qemu_announce_self_iter(qemu_ether_ntoa(&nic->conf->macaddr));
+    if (timer->params.has_interfaces) {
-    len = announce_self_create(buf, nic->conf->macaddr.a);
+        strList *entry = timer->params.interfaces;
+        /* Skip unless we find our name in the requested list */
+        skip = true;
 
-    qemu_send_packet_raw(qemu_get_queue(nic), buf, len);
+        while (entry) {
+            if (!strcmp(entry->value, nic->ncs->name)) {
+                /* Found us */
+                skip = false;
+                break;
+            }
+            entry = entry->next;
+        }
+    } else {
+        skip = false;
+    }
 
-    /* if the NIC provides it's own announcement support, use it as well */
+    trace_qemu_announce_self_iter(timer->params.has_id ? timer->params.id : "_",
-    if (nic->ncs->info->announce) {
+                                  nic->ncs->name,
-        nic->ncs->info->announce(nic->ncs);
+                                  qemu_ether_ntoa(&nic->conf->macaddr), skip);
+
+    if (!skip) {
+        len = announce_self_create(buf, nic->conf->macaddr.a);
+
+        qemu_send_packet_raw(qemu_get_queue(nic), buf, len);
+
+        /* if the NIC provides it's own announcement support, use it as well */
+        if (nic->ncs->info->announce) {
+            nic->ncs->info->announce(nic->ncs);
+        }
     }
 }
 static void qemu_announce_self_once(void *opaque)
 {
     AnnounceTimer *timer = (AnnounceTimer *)opaque;
 
-    qemu_foreach_nic(qemu_announce_self_iter, NULL);
+    qemu_foreach_nic(qemu_announce_self_iter, timer);
 
     if (--timer->round) {
         qemu_announce_timer_step(timer);
     } else {
-        qemu_announce_timer_del(timer);
+        qemu_announce_timer_del(timer, true);
     }
 }
 
@@ -129,12 +180,24 @@ void qemu_announce_self(AnnounceTimer *timer, AnnounceParameters *params)
     if (params->rounds) {
         qemu_announce_self_once(timer);
     } else {
-        qemu_announce_timer_del(timer);
+        qemu_announce_timer_del(timer, true);
     }
 }
 
 void qmp_announce_self(AnnounceParameters *params, Error **errp)
 {
-    static AnnounceTimer announce_timer;
+    AnnounceTimer *named_timer;
-    qemu_announce_self(&announce_timer, params);
+    if (!params->has_id) {
+        params->id = g_strdup("");
+        params->has_id = true;
+    }
+
+    named_timer = g_datalist_get_data(&named_timers, params->id);
+
+    if (!named_timer) {
+        named_timer = g_new0(AnnounceTimer, 1);
+        g_datalist_set_data(&named_timers, params->id, named_timer);
+    }
+
+    qemu_announce_self(named_timer, params);
 }

net/colo-compare.c

@@ -83,11 +83,14 @@ typedef struct CompareState {
     char *pri_indev;
     char *sec_indev;
     char *outdev;
+    char *notify_dev;
     CharBackend chr_pri_in;
     CharBackend chr_sec_in;
     CharBackend chr_out;
+    CharBackend chr_notify_dev;
     SocketReadState pri_rs;
     SocketReadState sec_rs;
+    SocketReadState notify_rs;
     bool vnet_hdr;
 
     /*
@@ -117,16 +120,33 @@ enum {
     SECONDARY_IN,
 };
 
-static void colo_compare_inconsistency_notify(void)
-{
-    notifier_list_notify(&colo_compare_notifiers,
-                migrate_get_current());
-}
 
 static int compare_chr_send(CompareState *s,
                             const uint8_t *buf,
                             uint32_t size,
-                            uint32_t vnet_hdr_len);
+                            uint32_t vnet_hdr_len,
+                            bool notify_remote_frame);
+
+static void notify_remote_frame(CompareState *s)
+{
+    char msg[] = "DO_CHECKPOINT";
+    int ret = 0;
+
+    ret = compare_chr_send(s, (uint8_t *)msg, strlen(msg), 0, true);
+    if (ret < 0) {
+        error_report("Notify Xen COLO-frame failed");
+    }
+}
+
+static void colo_compare_inconsistency_notify(CompareState *s)
+{
+    if (s->notify_dev) {
+        notify_remote_frame(s);
+    } else {
+        notifier_list_notify(&colo_compare_notifiers,
+                             migrate_get_current());
+    }
+}
 
 static gint seq_sorter(Packet *a, Packet *b, gpointer data)
 {
@@ -238,7 +258,8 @@ static void colo_release_primary_pkt(CompareState *s, Packet *pkt)
     ret = compare_chr_send(s,
                            pkt->data,
                            pkt->size,
-                           pkt->vnet_hdr_len);
+                           pkt->vnet_hdr_len,
+                           false);
     if (ret < 0) {
         error_report("colo send primary packet failed");
     }
@@ -430,7 +451,7 @@ sec:
         qemu_hexdump((char *)spkt->data, stderr,
                      "colo-compare spkt", spkt->size);
 
-        colo_compare_inconsistency_notify();
+        colo_compare_inconsistency_notify(s);
     }
 }
 
@@ -572,7 +593,7 @@ void colo_compare_unregister_notifier(Notifier *notify)
 }
 
 static int colo_old_packet_check_one_conn(Connection *conn,
-                                           void *user_data)
+                                          CompareState *s)
 {
     GList *result = NULL;
     int64_t check_time = REGULAR_PACKET_CHECK_MS;
@@ -583,7 +604,7 @@ static int colo_old_packet_check_one_conn(Connection *conn,
 
     if (result) {
         /* Do checkpoint will flush old packet */
-        colo_compare_inconsistency_notify();
+        colo_compare_inconsistency_notify(s);
         return 0;
     }
 
@@ -603,7 +624,7 @@ static void colo_old_packet_check(void *opaque)
      * If we find one old packet, stop finding job and notify
      * COLO frame do checkpoint.
      */
-    g_queue_find_custom(&s->conn_list, NULL,
+    g_queue_find_custom(&s->conn_list, s,
                         (GCompareFunc)colo_old_packet_check_one_conn);
 }
 
@@ -632,7 +653,8 @@ static void colo_compare_packet(CompareState *s, Connection *conn,
              */
             trace_colo_compare_main("packet different");
             g_queue_push_head(&conn->primary_list, pkt);
-            colo_compare_inconsistency_notify();
+
+            colo_compare_inconsistency_notify(s);
             break;
         }
     }
@@ -668,7 +690,8 @@ 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 vnet_hdr_len)
+                            uint32_t vnet_hdr_len,
+                            bool notify_remote_frame)
 {
     int ret = 0;
     uint32_t len = htonl(size);
@@ -677,7 +700,14 @@ static int compare_chr_send(CompareState *s,
         return 0;
     }
 
-    ret = qemu_chr_fe_write_all(&s->chr_out, (uint8_t *)&len, sizeof(len));
+    if (notify_remote_frame) {
+        ret = qemu_chr_fe_write_all(&s->chr_notify_dev,
+                                    (uint8_t *)&len,
+                                    sizeof(len));
+    } else {
+        ret = qemu_chr_fe_write_all(&s->chr_out, (uint8_t *)&len, sizeof(len));
+    }
+
     if (ret != sizeof(len)) {
         goto err;
     }
@@ -688,13 +718,26 @@ static int compare_chr_send(CompareState *s,
          * 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 (!notify_remote_frame) {
+            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 (notify_remote_frame) {
+        ret = qemu_chr_fe_write_all(&s->chr_notify_dev,
+                                    (uint8_t *)buf,
+                                    size);
+    } else {
+        ret = qemu_chr_fe_write_all(&s->chr_out, (uint8_t *)buf, size);
+    }
+
     if (ret != size) {
         goto err;
     }
@@ -744,6 +787,19 @@ static void compare_sec_chr_in(void *opaque, const uint8_t *buf, int size)
     }
 }
 
+static void compare_notify_chr(void *opaque, const uint8_t *buf, int size)
+{
+    CompareState *s = COLO_COMPARE(opaque);
+    int ret;
+
+    ret = net_fill_rstate(&s->notify_rs, buf, size);
+    if (ret == -1) {
+        qemu_chr_fe_set_handlers(&s->chr_notify_dev, NULL, NULL, NULL, NULL,
+                                 NULL, NULL, true);
+        error_report("colo-compare notify_dev error");
+    }
+}
+
 /*
  * Check old packet regularly so it can watch for any packets
  * that the secondary hasn't produced equivalents of.
@@ -831,6 +887,11 @@ static void colo_compare_iothread(CompareState *s)
     qemu_chr_fe_set_handlers(&s->chr_sec_in, compare_chr_can_read,
                              compare_sec_chr_in, NULL, NULL,
                              s, s->worker_context, true);
+    if (s->notify_dev) {
+        qemu_chr_fe_set_handlers(&s->chr_notify_dev, compare_chr_can_read,
+                                 compare_notify_chr, NULL, NULL,
+                                 s, s->worker_context, true);
+    }
 
     colo_compare_timer_init(s);
     s->event_bh = qemu_bh_new(colo_compare_handle_event, s);
@@ -897,6 +958,21 @@ static void compare_set_vnet_hdr(Object *obj,
     s->vnet_hdr = value;
 }
 
+static char *compare_get_notify_dev(Object *obj, Error **errp)
+{
+    CompareState *s = COLO_COMPARE(obj);
+
+    return g_strdup(s->notify_dev);
+}
+
+static void compare_set_notify_dev(Object *obj, const char *value, Error **errp)
+{
+    CompareState *s = COLO_COMPARE(obj);
+
+    g_free(s->notify_dev);
+    s->notify_dev = g_strdup(value);
+}
+
 static void compare_pri_rs_finalize(SocketReadState *pri_rs)
 {
     CompareState *s = container_of(pri_rs, CompareState, pri_rs);
@@ -907,7 +983,8 @@ static void compare_pri_rs_finalize(SocketReadState *pri_rs)
         compare_chr_send(s,
                          pri_rs->buf,
                          pri_rs->packet_len,
-                         pri_rs->vnet_hdr_len);
+                         pri_rs->vnet_hdr_len,
+                         false);
     } else {
         /* compare packet in the specified connection */
         colo_compare_connection(conn, s);
@@ -927,6 +1004,27 @@ static void compare_sec_rs_finalize(SocketReadState *sec_rs)
     }
 }
 
+static void compare_notify_rs_finalize(SocketReadState *notify_rs)
+{
+    CompareState *s = container_of(notify_rs, CompareState, notify_rs);
+
+    /* Get Xen colo-frame's notify and handle the message */
+    char *data = g_memdup(notify_rs->buf, notify_rs->packet_len);
+    char msg[] = "COLO_COMPARE_GET_XEN_INIT";
+    int ret;
+
+    if (!strcmp(data, "COLO_USERSPACE_PROXY_INIT")) {
+        ret = compare_chr_send(s, (uint8_t *)msg, strlen(msg), 0, true);
+        if (ret < 0) {
+            error_report("Notify Xen COLO-frame INIT failed");
+        }
+    }
+
+    if (!strcmp(data, "COLO_CHECKPOINT")) {
+        /* colo-compare do checkpoint, flush pri packet and remove sec packet */
+        g_queue_foreach(&s->conn_list, colo_flush_packets, s);
+    }
+}
 
 /*
  * Return 0 is success.
@@ -997,6 +1095,17 @@ static void colo_compare_complete(UserCreatable *uc, Error **errp)
     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);
 
+    /* Try to enable remote notify chardev, currently just for Xen COLO */
+    if (s->notify_dev) {
+        if (find_and_check_chardev(&chr, s->notify_dev, errp) ||
+            !qemu_chr_fe_init(&s->chr_notify_dev, chr, errp)) {
+            return;
+        }
+
+        net_socket_rs_init(&s->notify_rs, compare_notify_rs_finalize,
+                           s->vnet_hdr);
+    }
+
     QTAILQ_INSERT_TAIL(&net_compares, s, next);
 
     g_queue_init(&s->conn_list);
@@ -1024,7 +1133,8 @@ static void colo_flush_packets(void *opaque, void *user_data)
         compare_chr_send(s,
                          pkt->data,
                          pkt->size,
-                         pkt->vnet_hdr_len);
+                         pkt->vnet_hdr_len,
+                         false);
         packet_destroy(pkt, NULL);
     }
     while (!g_queue_is_empty(&conn->secondary_list)) {
@@ -1057,6 +1167,10 @@ static void colo_compare_init(Object *obj)
                             (Object **)&s->iothread,
                             object_property_allow_set_link,
                             OBJ_PROP_LINK_STRONG, NULL);
+    /* This parameter just for Xen COLO */
+    object_property_add_str(obj, "notify_dev",
+                            compare_get_notify_dev, compare_set_notify_dev,
+                            NULL);
 
     s->vnet_hdr = false;
     object_property_add_bool(obj, "vnet_hdr_support", compare_get_vnet_hdr,
@@ -1071,6 +1185,10 @@ static void colo_compare_finalize(Object *obj)
     qemu_chr_fe_deinit(&s->chr_pri_in, false);
     qemu_chr_fe_deinit(&s->chr_sec_in, false);
     qemu_chr_fe_deinit(&s->chr_out, false);
+    if (s->notify_dev) {
+        qemu_chr_fe_deinit(&s->chr_notify_dev, false);
+    }
+
     if (s->iothread) {
         colo_compare_timer_del(s);
     }
@@ -1103,6 +1221,7 @@ static void colo_compare_finalize(Object *obj)
     g_free(s->pri_indev);
     g_free(s->sec_indev);
     g_free(s->outdev);
+    g_free(s->notify_dev);
 }
 
 static const TypeInfo colo_compare_info = {

net/net.c

@@ -64,55 +64,42 @@ static QTAILQ_HEAD(, NetClientState) net_clients;
 /***********************************************************/
 /* network device redirectors */
 
-static int get_str_sep(char *buf, int buf_size, const char **pp, int sep)
-{
-    const char *p, *p1;
-    int len;
-    p = *pp;
-    p1 = strchr(p, sep);
-    if (!p1)
-        return -1;
-    len = p1 - p;
-    p1++;
-    if (buf_size > 0) {
-        if (len > buf_size - 1)
-            len = buf_size - 1;
-        memcpy(buf, p, len);
-        buf[len] = '\0';
-    }
-    *pp = p1;
-    return 0;
-}
-
 int parse_host_port(struct sockaddr_in *saddr, const char *str,
                     Error **errp)
 {
-    char buf[512];
+    gchar **substrings;
     struct hostent *he;
-    const char *p, *r;
+    const char *addr, *p, *r;
-    int port;
+    int port, ret = 0;
 
-    p = str;
+    substrings = g_strsplit(str, ":", 2);
-    if (get_str_sep(buf, sizeof(buf), &p, ':') < 0) {
+    if (!substrings || !substrings[0] || !substrings[1]) {
         error_setg(errp, "host address '%s' doesn't contain ':' "
                    "separating host from port", str);
-        return -1;
+        ret = -1;
+        goto out;
     }
+
+    addr = substrings[0];
+    p = substrings[1];
+
     saddr->sin_family = AF_INET;
-    if (buf[0] == '\0') {
+    if (addr[0] == '\0') {
         saddr->sin_addr.s_addr = 0;
     } else {
-        if (qemu_isdigit(buf[0])) {
+        if (qemu_isdigit(addr[0])) {
-            if (!inet_aton(buf, &saddr->sin_addr)) {
+            if (!inet_aton(addr, &saddr->sin_addr)) {
                 error_setg(errp, "host address '%s' is not a valid "
-                           "IPv4 address", buf);
+                           "IPv4 address", addr);
-                return -1;
+                ret = -1;
+                goto out;
             }
         } else {
-            he = gethostbyname(buf);
+            he = gethostbyname(addr);
             if (he == NULL) {
-                error_setg(errp, "can't resolve host address '%s'", buf);
+                error_setg(errp, "can't resolve host address '%s'", addr);
-                return - 1;
+                ret = -1;
+                goto out;
             }
             saddr->sin_addr = *(struct in_addr *)he->h_addr;
         }
@@ -120,10 +107,14 @@ int parse_host_port(struct sockaddr_in *saddr, const char *str,
     port = strtol(p, (char **)&r, 0);
     if (r == p) {
         error_setg(errp, "port number '%s' is invalid", p);
-        return -1;
+        ret = -1;
+        goto out;
     }
     saddr->sin_port = htons(port);
-    return 0;
+
+out:
+    g_strfreev(substrings);
+    return ret;
 }
 
 char *qemu_mac_strdup_printf(const uint8_t *macaddr)
@@ -1105,6 +1096,7 @@ static void show_netdevs(void)
 
 static int net_client_init(QemuOpts *opts, bool is_netdev, Error **errp)
 {
+    gchar **substrings = NULL;
     void *object = NULL;
     Error *err = NULL;
     int ret = -1;
@@ -1120,28 +1112,33 @@ static int net_client_init(QemuOpts *opts, bool is_netdev, Error **errp)
         const char *ip6_net = qemu_opt_get(opts, "ipv6-net");
 
         if (ip6_net) {
-            char buf[strlen(ip6_net) + 1];
+            char *prefix_addr;
+            unsigned long prefix_len = 64; /* Default 64bit prefix length. */
 
-            if (get_str_sep(buf, sizeof(buf), &ip6_net, '/') < 0) {
+            substrings = g_strsplit(ip6_net, "/", 2);
-                /* Default 64bit prefix length.  */
+            if (!substrings || !substrings[0]) {
-                qemu_opt_set(opts, "ipv6-prefix", ip6_net, &error_abort);
+                error_setg(errp, QERR_INVALID_PARAMETER_VALUE, "ipv6-net",
-                qemu_opt_set_number(opts, "ipv6-prefixlen", 64, &error_abort);
+                           "a valid IPv6 prefix");
-            } else {
+                goto out;
+            }
+
+            prefix_addr = substrings[0];
+
+            if (substrings[1]) {
                 /* User-specified prefix length.  */
-                unsigned long len;
                 int err;
 
-                qemu_opt_set(opts, "ipv6-prefix", buf, &error_abort);
+                err = qemu_strtoul(substrings[1], NULL, 10, &prefix_len);
-                err = qemu_strtoul(ip6_net, NULL, 10, &len);
-
                 if (err) {
                     error_setg(errp, QERR_INVALID_PARAMETER_VALUE,
-                              "ipv6-prefix", "a number");
+                               "ipv6-prefixlen", "a number");
-                } else {
+                    goto out;
-                    qemu_opt_set_number(opts, "ipv6-prefixlen", len,
-                                        &error_abort);
                 }
             }
+
+            qemu_opt_set(opts, "ipv6-prefix", prefix_addr, &error_abort);
+            qemu_opt_set_number(opts, "ipv6-prefixlen", prefix_len,
+                                &error_abort);
             qemu_opt_unset(opts, "ipv6-net");
         }
     }
@@ -1162,7 +1159,9 @@ static int net_client_init(QemuOpts *opts, bool is_netdev, Error **errp)
         qapi_free_NetLegacy(object);
     }
 
+out:
     error_propagate(errp, err);
+    g_strfreev(substrings);
     visit_free(v);
     return ret;
 }

net/trace-events

@@ -1,7 +1,8 @@
 # See docs/devel/tracing.txt for syntax documentation.
 
 # announce.c
-qemu_announce_self_iter(const char *mac) "%s"
+qemu_announce_self_iter(const char *id, const char *name, const char *mac, int skip) "%s:%s:%s skip: %d"
+qemu_announce_timer_del(bool free_named, bool free_timer, char *id) "free named: %d free timer: %d id: %s"
 
 # vhost-user.c
 vhost_user_event(const char *chr, int event) "chr: %s got event: %d"

qapi/net.json

@@ -699,6 +699,13 @@
 #
 # @step: Delay increase (in ms) after each self-announcement attempt
 #
+# @interfaces: An optional list of interface names, which restricts the
+#        announcement to the listed interfaces. (Since 4.1)
+#
+# @id: A name to be used to identify an instance of announce-timers
+#        and to allow it to modified later.  Not for use as
+#        part of the migration parameters. (Since 4.1)
+#
 # Since: 4.0
 ##
 
@@ -706,7 +713,9 @@
   'data': { 'initial': 'int',
             'max': 'int',
             'rounds': 'int',
-            'step': 'int' } }
+            'step': 'int',
+            '*interfaces': ['str'],
+            '*id' : 'str' } }
 
 ##
 # @announce-self:
@@ -718,9 +727,10 @@
 #
 # Example:
 #
-# -> { "execute": "announce-self"
+# -> { "execute": "announce-self",
 #      "arguments": {
-#          "initial": 50, "max": 550, "rounds": 10, "step": 50 } }
+#          "initial": 50, "max": 550, "rounds": 10, "step": 50,
+#          "interfaces": ["vn2", "vn3"], "id": "bob" } }
 # <- { "return": {} }
 #
 # Since: 4.0

qemu-bridge-helper.c

@@ -10,7 +10,17 @@
  *
  * This work is licensed under the terms of the GNU GPL, version 2.  See
  * the COPYING file in the top-level directory.
- *
+ */
+
+/*
+ * Known shortcomings:
+ * - There is no manual page
+ * - The syntax of the ACL file is not documented anywhere
+ * - parse_acl_file() doesn't report fopen() failure properly, fails
+ *   to check ferror() after fgets() failure, arbitrarily truncates
+ *   long lines, handles whitespace inconsistently, error messages
+ *   don't point to the offending file and line, errors in included
+ *   files are reported, but otherwise ignored, ...
  */
 
 #include "qemu/osdep.h"

qemu-options.hx

@@ -4477,7 +4477,7 @@ 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},iothread=@var{id}[,vnet_hdr_support]
+@item -object colo-compare,id=@var{id},primary_in=@var{chardevid},secondary_in=@var{chardevid},outdev=@var{chardevid},iothread=@var{id}[,vnet_hdr_support][,notify_dev=@var{id}]
 
 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
@@ -4486,11 +4486,15 @@ do checkpoint and send primary packet to outdev@var{chardevid}.
 In order to improve efficiency, we need to put the task of comparison
 in another thread. If it has the vnet_hdr_support flag, colo compare
 will send/recv packet with vnet_hdr_len.
+If you want to use Xen COLO, will need the notify_dev to notify Xen
+colo-frame to do checkpoint.
 
 we must use it with the help of filter-mirror and filter-redirector.
 
 @example
 
+KVM COLO
+
 primary:
 -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
@@ -4514,6 +4518,33 @@ secondary:
 -object filter-redirector,id=f1,netdev=hn0,queue=tx,indev=red0
 -object filter-redirector,id=f2,netdev=hn0,queue=rx,outdev=red1
 
+
+Xen COLO
+
+primary:
+-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
+-chardev socket,id=notify_way,host=3.3.3.3,port=9009,server,nowait
+-object filter-mirror,id=m0,netdev=hn0,queue=tx,outdev=mirror0
+-object filter-redirector,netdev=hn0,id=redire0,queue=rx,indev=compare_out
+-object filter-redirector,netdev=hn0,id=redire1,queue=rx,outdev=compare0
+-object iothread,id=iothread1
+-object colo-compare,id=comp0,primary_in=compare0-0,secondary_in=compare1,outdev=compare_out0,notify_dev=nofity_way,iothread=iothread1
+
+secondary:
+-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
+-object filter-redirector,id=f2,netdev=hn0,queue=rx,outdev=red1
+
 @end example
 
 If you want to know the detail of above command line, you can read

tests/virtio-net-test.c

@@ -184,21 +184,72 @@ static void announce_self(void *obj, void *data, QGuestAllocator *t_alloc)
     QDict *rsp;
     int ret;
     uint16_t *proto = (uint16_t *)&buffer[12];
+    size_t total_received = 0;
+    uint64_t start, now, last_rxt, deadline;
 
+    /* Send a set of packets over a few second period */
     rsp = qmp("{ 'execute' : 'announce-self', "
                   " 'arguments': {"
-                      " 'initial': 50, 'max': 550,"
+                      " 'initial': 20, 'max': 100,"
-                      " 'rounds': 10, 'step': 50 } }");
+                      " 'rounds': 300, 'step': 10, 'id': 'bob' } }");
     assert(!qdict_haskey(rsp, "error"));
     qobject_unref(rsp);
 
-    /* Catch the packet and make sure it's a RARP */
+    /* Catch the first packet and make sure it's a RARP */
     ret = qemu_recv(sv[0], &len, sizeof(len), 0);
     g_assert_cmpint(ret, ==,  sizeof(len));
     len = ntohl(len);
 
     ret = qemu_recv(sv[0], buffer, len, 0);
     g_assert_cmpint(*proto, ==, htons(ETH_P_RARP));
+
+    /*
+     * Stop the announcment by settings rounds to 0 on the
+     * existing timer.
+     */
+    rsp = qmp("{ 'execute' : 'announce-self', "
+                  " 'arguments': {"
+                      " 'initial': 20, 'max': 100,"
+                      " 'rounds': 0, 'step': 10, 'id': 'bob' } }");
+    assert(!qdict_haskey(rsp, "error"));
+    qobject_unref(rsp);
+
+    /* Now make sure the packets stop */
+
+    /* Times are in us */
+    start = g_get_monotonic_time();
+    /* 30 packets, max gap 100ms, * 4 for wiggle */
+    deadline = start + 1000 * (100 * 30 * 4);
+    last_rxt = start;
+
+    while (true) {
+        int saved_err;
+        ret = qemu_recv(sv[0], buffer, 60, MSG_DONTWAIT);
+        saved_err = errno;
+        now = g_get_monotonic_time();
+        g_assert_cmpint(now, <, deadline);
+
+        if (ret >= 0) {
+            if (ret) {
+                last_rxt = now;
+            }
+            total_received += ret;
+
+            /* Check it's not spewing loads */
+            g_assert_cmpint(total_received, <, 60 * 30 * 2);
+        } else {
+            g_assert_cmpint(saved_err, ==, EAGAIN);
+
+            /* 400ms, i.e. 4 worst case gaps */
+            if ((now - last_rxt) > (1000 * 100 * 4)) {
+                /* Nothings arrived for a while - must have stopped */
+                break;
+            };
+
+            /* 100ms */
+            g_usleep(1000 * 100);
+        }
+    };
 }
 
 static void virtio_net_test_cleanup(void *sockets)