summary refs log tree commit diff stats
path: root/migration/migration.c
diff options
context:
space:
mode:
Diffstat (limited to 'migration/migration.c')
-rw-r--r--migration/migration.c550
1 files changed, 406 insertions, 144 deletions
diff --git a/migration/migration.c b/migration/migration.c
index 6abcbefd9c..28a34c9068 100644
--- a/migration/migration.c
+++ b/migration/migration.c
@@ -66,6 +66,7 @@
 #include "sysemu/qtest.h"
 #include "options.h"
 #include "sysemu/dirtylimit.h"
+#include "qemu/sockets.h"
 
 static NotifierList migration_state_notifiers =
     NOTIFIER_LIST_INITIALIZER(migration_state_notifiers);
@@ -92,31 +93,55 @@ enum mig_rp_message_type {
 static MigrationState *current_migration;
 static MigrationIncomingState *current_incoming;
 
-static GSList *migration_blockers;
+static GSList *migration_blockers[MIG_MODE__MAX];
 
 static bool migration_object_check(MigrationState *ms, Error **errp);
 static int migration_maybe_pause(MigrationState *s,
                                  int *current_active_state,
                                  int new_state);
 static void migrate_fd_cancel(MigrationState *s);
-static int close_return_path_on_source(MigrationState *s);
+static bool close_return_path_on_source(MigrationState *s);
+
+static void migration_downtime_start(MigrationState *s)
+{
+    trace_vmstate_downtime_checkpoint("src-downtime-start");
+    s->downtime_start = qemu_clock_get_ms(QEMU_CLOCK_REALTIME);
+}
+
+static void migration_downtime_end(MigrationState *s)
+{
+    int64_t now = qemu_clock_get_ms(QEMU_CLOCK_REALTIME);
+
+    /*
+     * If downtime already set, should mean that postcopy already set it,
+     * then that should be the real downtime already.
+     */
+    if (!s->downtime) {
+        s->downtime = now - s->downtime_start;
+    }
+
+    trace_vmstate_downtime_checkpoint("src-downtime-end");
+}
 
 static bool migration_needs_multiple_sockets(void)
 {
     return migrate_multifd() || migrate_postcopy_preempt();
 }
 
-static bool uri_supports_multi_channels(const char *uri)
+static bool transport_supports_multi_channels(SocketAddress *saddr)
 {
-    return strstart(uri, "tcp:", NULL) || strstart(uri, "unix:", NULL) ||
-           strstart(uri, "vsock:", NULL);
+    return saddr->type == SOCKET_ADDRESS_TYPE_INET ||
+           saddr->type == SOCKET_ADDRESS_TYPE_UNIX ||
+           saddr->type == SOCKET_ADDRESS_TYPE_VSOCK;
 }
 
 static bool
-migration_channels_and_uri_compatible(const char *uri, Error **errp)
+migration_channels_and_transport_compatible(MigrationAddress *addr,
+                                            Error **errp)
 {
     if (migration_needs_multiple_sockets() &&
-        !uri_supports_multi_channels(uri)) {
+        (addr->transport == MIGRATION_ADDRESS_TYPE_SOCKET) &&
+        !transport_supports_multi_channels(&addr->u.socket)) {
         error_setg(errp, "Migration requires multi-channel URIs (e.g. tcp)");
         return false;
     }
@@ -131,6 +156,15 @@ static gint page_request_addr_cmp(gconstpointer ap, gconstpointer bp)
     return (a > b) - (a < b);
 }
 
+int migration_stop_vm(RunState state)
+{
+    int ret = vm_stop_force_state(state);
+
+    trace_vmstate_downtime_checkpoint("src-vm-stopped");
+
+    return ret;
+}
+
 void migration_object_init(void)
 {
     /* This can only be called once. */
@@ -423,25 +457,114 @@ void migrate_add_address(SocketAddress *address)
                       QAPI_CLONE(SocketAddress, address));
 }
 
-static void qemu_start_incoming_migration(const char *uri, Error **errp)
+bool migrate_uri_parse(const char *uri, MigrationChannel **channel,
+                       Error **errp)
 {
-    const char *p = NULL;
+    g_autoptr(MigrationChannel) val = g_new0(MigrationChannel, 1);
+    g_autoptr(MigrationAddress) addr = g_new0(MigrationAddress, 1);
+    SocketAddress *saddr = NULL;
+    InetSocketAddress *isock = &addr->u.rdma;
+    strList **tail = &addr->u.exec.args;
+
+    if (strstart(uri, "exec:", NULL)) {
+        addr->transport = MIGRATION_ADDRESS_TYPE_EXEC;
+#ifdef WIN32
+        QAPI_LIST_APPEND(tail, g_strdup(exec_get_cmd_path()));
+        QAPI_LIST_APPEND(tail, g_strdup("/c"));
+#else
+        QAPI_LIST_APPEND(tail, g_strdup("/bin/sh"));
+        QAPI_LIST_APPEND(tail, g_strdup("-c"));
+#endif
+        QAPI_LIST_APPEND(tail, g_strdup(uri + strlen("exec:")));
+    } else if (strstart(uri, "rdma:", NULL)) {
+        if (inet_parse(isock, uri + strlen("rdma:"), errp)) {
+            qapi_free_InetSocketAddress(isock);
+            return false;
+        }
+        addr->transport = MIGRATION_ADDRESS_TYPE_RDMA;
+    } else if (strstart(uri, "tcp:", NULL) ||
+                strstart(uri, "unix:", NULL) ||
+                strstart(uri, "vsock:", NULL) ||
+                strstart(uri, "fd:", NULL)) {
+        addr->transport = MIGRATION_ADDRESS_TYPE_SOCKET;
+        saddr = socket_parse(uri, errp);
+        if (!saddr) {
+            return false;
+        }
+        addr->u.socket.type = saddr->type;
+        addr->u.socket.u = saddr->u;
+    } else if (strstart(uri, "file:", NULL)) {
+        addr->transport = MIGRATION_ADDRESS_TYPE_FILE;
+        addr->u.file.filename = g_strdup(uri + strlen("file:"));
+        if (file_parse_offset(addr->u.file.filename, &addr->u.file.offset,
+                              errp)) {
+            return false;
+        }
+    } else {
+        error_setg(errp, "unknown migration protocol: %s", uri);
+        return false;
+    }
+
+    val->channel_type = MIGRATION_CHANNEL_TYPE_MAIN;
+    val->addr = g_steal_pointer(&addr);
+    *channel = g_steal_pointer(&val);
+    return true;
+}
+
+static void qemu_start_incoming_migration(const char *uri, bool has_channels,
+                                          MigrationChannelList *channels,
+                                          Error **errp)
+{
+    MigrationChannel *channel = NULL;
+    MigrationAddress *addr = NULL;
     MigrationIncomingState *mis = migration_incoming_get_current();
 
-    /* URI is not suitable for migration? */
-    if (!migration_channels_and_uri_compatible(uri, errp)) {
+    /*
+     * Having preliminary checks for uri and channel
+     */
+    if (uri && has_channels) {
+        error_setg(errp, "'uri' and 'channels' arguments are mutually "
+                   "exclusive; exactly one of the two should be present in "
+                   "'migrate-incoming' qmp command ");
+        return;
+    } else if (channels) {
+        /* To verify that Migrate channel list has only item */
+        if (channels->next) {
+            error_setg(errp, "Channel list has more than one entries");
+            return;
+        }
+        channel = channels->value;
+    } else if (uri) {
+        /* caller uses the old URI syntax */
+        if (!migrate_uri_parse(uri, &channel, errp)) {
+            return;
+        }
+    } else {
+        error_setg(errp, "neither 'uri' or 'channels' argument are "
+                   "specified in 'migrate-incoming' qmp command ");
+        return;
+    }
+    addr = channel->addr;
+
+    /* transport mechanism not suitable for migration? */
+    if (!migration_channels_and_transport_compatible(addr, errp)) {
         return;
     }
 
     migrate_set_state(&mis->state, MIGRATION_STATUS_NONE,
                       MIGRATION_STATUS_SETUP);
 
-    if (strstart(uri, "tcp:", &p) ||
-        strstart(uri, "unix:", NULL) ||
-        strstart(uri, "vsock:", NULL)) {
-        socket_start_incoming_migration(p ? p : uri, errp);
+    if (addr->transport == MIGRATION_ADDRESS_TYPE_SOCKET) {
+        SocketAddress *saddr = &addr->u.socket;
+        if (saddr->type == SOCKET_ADDRESS_TYPE_INET ||
+            saddr->type == SOCKET_ADDRESS_TYPE_UNIX ||
+            saddr->type == SOCKET_ADDRESS_TYPE_VSOCK) {
+            socket_start_incoming_migration(saddr, errp);
+        } else if (saddr->type == SOCKET_ADDRESS_TYPE_FD) {
+            fd_start_incoming_migration(saddr->u.fd.str, errp);
+        }
 #ifdef CONFIG_RDMA
-    } else if (strstart(uri, "rdma:", &p)) {
+    } else if (addr->transport == MIGRATION_ADDRESS_TYPE_RDMA) {
         if (migrate_compress()) {
             error_setg(errp, "RDMA and compression can't be used together");
             return;
@@ -454,14 +577,12 @@ static void qemu_start_incoming_migration(const char *uri, Error **errp)
             error_setg(errp, "RDMA and multifd can't be used together");
             return;
         }
-        rdma_start_incoming_migration(p, errp);
+        rdma_start_incoming_migration(&addr->u.rdma, errp);
 #endif
-    } else if (strstart(uri, "exec:", &p)) {
-        exec_start_incoming_migration(p, errp);
-    } else if (strstart(uri, "fd:", &p)) {
-        fd_start_incoming_migration(p, errp);
-    } else if (strstart(uri, "file:", &p)) {
-        file_start_incoming_migration(p, errp);
+    } else if (addr->transport == MIGRATION_ADDRESS_TYPE_EXEC) {
+        exec_start_incoming_migration(addr->u.exec.args, errp);
+    } else if (addr->transport == MIGRATION_ADDRESS_TYPE_FILE) {
+        file_start_incoming_migration(&addr->u.file, errp);
     } else {
         error_setg(errp, "unknown migration protocol: %s", uri);
     }
@@ -472,6 +593,8 @@ static void process_incoming_migration_bh(void *opaque)
     Error *local_err = NULL;
     MigrationIncomingState *mis = opaque;
 
+    trace_vmstate_downtime_checkpoint("dst-precopy-bh-enter");
+
     /* If capability late_block_activate is set:
      * Only fire up the block code now if we're going to restart the
      * VM, else 'cont' will do it.
@@ -497,6 +620,8 @@ static void process_incoming_migration_bh(void *opaque)
      */
     qemu_announce_self(&mis->announce_timer, migrate_announce_params());
 
+    trace_vmstate_downtime_checkpoint("dst-precopy-bh-announced");
+
     multifd_load_shutdown();
 
     dirty_bitmap_mig_before_vm_start();
@@ -514,6 +639,7 @@ static void process_incoming_migration_bh(void *opaque)
     } else {
         runstate_set(global_state_get_runstate());
     }
+    trace_vmstate_downtime_checkpoint("dst-precopy-bh-vm-started");
     /*
      * This must happen after any state changes since as soon as an external
      * observer sees this event they might start to prod at the VM assuming
@@ -548,6 +674,8 @@ process_incoming_migration_co(void *opaque)
     ret = qemu_loadvm_state(mis->from_src_file);
     mis->loadvm_co = NULL;
 
+    trace_vmstate_downtime_checkpoint("dst-precopy-loadvm-completed");
+
     ps = postcopy_state_get();
     trace_process_incoming_migration_co_end(ret, ps);
     if (ps != POSTCOPY_INCOMING_NONE) {
@@ -1006,7 +1134,7 @@ static void fill_source_migration_info(MigrationInfo *info)
 {
     MigrationState *s = migrate_get_current();
     int state = qatomic_read(&s->state);
-    GSList *cur_blocker = migration_blockers;
+    GSList *cur_blocker = migration_blockers[migrate_mode()];
 
     info->blocked_reasons = NULL;
 
@@ -1356,6 +1484,17 @@ bool migration_in_postcopy(void)
     }
 }
 
+bool migration_postcopy_is_alive(int state)
+{
+    switch (state) {
+    case MIGRATION_STATUS_POSTCOPY_ACTIVE:
+    case MIGRATION_STATUS_POSTCOPY_RECOVER:
+        return true;
+    default:
+        return false;
+    }
+}
+
 bool migration_in_postcopy_after_devices(MigrationState *s)
 {
     return migration_in_postcopy() && s->postcopy_after_devices;
@@ -1438,7 +1577,6 @@ int migrate_init(MigrationState *s, Error **errp)
     s->to_dst_file = NULL;
     s->state = MIGRATION_STATUS_NONE;
     s->rp_state.from_dst_file = NULL;
-    s->rp_state.error = false;
     s->mbps = 0.0;
     s->pages_per_second = 0.0;
     s->downtime = 0;
@@ -1470,44 +1608,112 @@ int migrate_init(MigrationState *s, Error **errp)
     return 0;
 }
 
-int migrate_add_blocker_internal(Error **reasonp, Error **errp)
+static bool is_busy(Error **reasonp, Error **errp)
 {
+    ERRP_GUARD();
+
     /* Snapshots are similar to migrations, so check RUN_STATE_SAVE_VM too. */
     if (runstate_check(RUN_STATE_SAVE_VM) || !migration_is_idle()) {
         error_propagate_prepend(errp, *reasonp,
                                 "disallowing migration blocker "
                                 "(migration/snapshot in progress) for: ");
         *reasonp = NULL;
-        return -EBUSY;
+        return true;
     }
-
-    migration_blockers = g_slist_prepend(migration_blockers, *reasonp);
-    return 0;
+    return false;
 }
 
-int migrate_add_blocker(Error **reasonp, Error **errp)
+static bool is_only_migratable(Error **reasonp, Error **errp, int modes)
 {
-    if (only_migratable) {
+    ERRP_GUARD();
+
+    if (only_migratable && (modes & BIT(MIG_MODE_NORMAL))) {
         error_propagate_prepend(errp, *reasonp,
                                 "disallowing migration blocker "
                                 "(--only-migratable) for: ");
         *reasonp = NULL;
+        return true;
+    }
+    return false;
+}
+
+static int get_modes(MigMode mode, va_list ap)
+{
+    int modes = 0;
+
+    while (mode != -1 && mode != MIG_MODE_ALL) {
+        assert(mode >= MIG_MODE_NORMAL && mode < MIG_MODE__MAX);
+        modes |= BIT(mode);
+        mode = va_arg(ap, MigMode);
+    }
+    if (mode == MIG_MODE_ALL) {
+        modes = BIT(MIG_MODE__MAX) - 1;
+    }
+    return modes;
+}
+
+static int add_blockers(Error **reasonp, Error **errp, int modes)
+{
+    for (MigMode mode = 0; mode < MIG_MODE__MAX; mode++) {
+        if (modes & BIT(mode)) {
+            migration_blockers[mode] = g_slist_prepend(migration_blockers[mode],
+                                                       *reasonp);
+        }
+    }
+    return 0;
+}
+
+int migrate_add_blocker(Error **reasonp, Error **errp)
+{
+    return migrate_add_blocker_modes(reasonp, errp, MIG_MODE_ALL);
+}
+
+int migrate_add_blocker_normal(Error **reasonp, Error **errp)
+{
+    return migrate_add_blocker_modes(reasonp, errp, MIG_MODE_NORMAL, -1);
+}
+
+int migrate_add_blocker_modes(Error **reasonp, Error **errp, MigMode mode, ...)
+{
+    int modes;
+    va_list ap;
+
+    va_start(ap, mode);
+    modes = get_modes(mode, ap);
+    va_end(ap);
+
+    if (is_only_migratable(reasonp, errp, modes)) {
         return -EACCES;
+    } else if (is_busy(reasonp, errp)) {
+        return -EBUSY;
     }
+    return add_blockers(reasonp, errp, modes);
+}
 
-    return migrate_add_blocker_internal(reasonp, errp);
+int migrate_add_blocker_internal(Error **reasonp, Error **errp)
+{
+    int modes = BIT(MIG_MODE__MAX) - 1;
+
+    if (is_busy(reasonp, errp)) {
+        return -EBUSY;
+    }
+    return add_blockers(reasonp, errp, modes);
 }
 
 void migrate_del_blocker(Error **reasonp)
 {
     if (*reasonp) {
-        migration_blockers = g_slist_remove(migration_blockers, *reasonp);
+        for (MigMode mode = 0; mode < MIG_MODE__MAX; mode++) {
+            migration_blockers[mode] = g_slist_remove(migration_blockers[mode],
+                                                      *reasonp);
+        }
         error_free(*reasonp);
         *reasonp = NULL;
     }
 }
 
-void qmp_migrate_incoming(const char *uri, Error **errp)
+void qmp_migrate_incoming(const char *uri, bool has_channels,
+                          MigrationChannelList *channels, Error **errp)
 {
     Error *local_err = NULL;
     static bool once = true;
@@ -1525,7 +1731,7 @@ void qmp_migrate_incoming(const char *uri, Error **errp)
         return;
     }
 
-    qemu_start_incoming_migration(uri, &local_err);
+    qemu_start_incoming_migration(uri, has_channels, channels, &local_err);
 
     if (local_err) {
         yank_unregister_instance(MIGRATION_YANK_INSTANCE);
@@ -1561,7 +1767,7 @@ void qmp_migrate_recover(const char *uri, Error **errp)
      * only re-setup the migration stream and poke existing migration
      * to continue using that newly established channel.
      */
-    qemu_start_incoming_migration(uri, errp);
+    qemu_start_incoming_migration(uri, false, NULL, errp);
 }
 
 void qmp_migrate_pause(Error **errp)
@@ -1570,8 +1776,15 @@ void qmp_migrate_pause(Error **errp)
     MigrationIncomingState *mis = migration_incoming_get_current();
     int ret = 0;
 
-    if (ms->state == MIGRATION_STATUS_POSTCOPY_ACTIVE) {
+    if (migration_postcopy_is_alive(ms->state)) {
         /* Source side, during postcopy */
+        Error *error = NULL;
+
+        /* Tell the core migration that we're pausing */
+        error_setg(&error, "Postcopy migration is paused by the user");
+        migrate_set_error(ms, error);
+        error_free(error);
+
         qemu_mutex_lock(&ms->qemu_file_lock);
         if (ms->to_dst_file) {
             ret = qemu_file_shutdown(ms->to_dst_file);
@@ -1580,10 +1793,17 @@ void qmp_migrate_pause(Error **errp)
         if (ret) {
             error_setg(errp, "Failed to pause source migration");
         }
+
+        /*
+         * Kick the migration thread out of any waiting windows (on behalf
+         * of the rp thread).
+         */
+        migration_rp_kick(ms);
+
         return;
     }
 
-    if (mis->state == MIGRATION_STATUS_POSTCOPY_ACTIVE) {
+    if (migration_postcopy_is_alive(mis->state)) {
         ret = qemu_file_shutdown(mis->from_src_file);
         if (ret) {
             error_setg(errp, "Failed to pause destination migration");
@@ -1592,17 +1812,19 @@ void qmp_migrate_pause(Error **errp)
     }
 
     error_setg(errp, "migrate-pause is currently only supported "
-               "during postcopy-active state");
+               "during postcopy-active or postcopy-recover state");
 }
 
 bool migration_is_blocked(Error **errp)
 {
+    GSList *blockers = migration_blockers[migrate_mode()];
+
     if (qemu_savevm_state_blocked(errp)) {
         return true;
     }
 
-    if (migration_blockers) {
-        error_propagate(errp, error_copy(migration_blockers->data));
+    if (blockers) {
+        error_propagate(errp, error_copy(blockers->data));
         return true;
     }
 
@@ -1702,17 +1924,46 @@ static bool migrate_prepare(MigrationState *s, bool blk, bool blk_inc,
     return true;
 }
 
-void qmp_migrate(const char *uri, bool has_blk, bool blk,
+void qmp_migrate(const char *uri, bool has_channels,
+                 MigrationChannelList *channels, bool has_blk, bool blk,
                  bool has_inc, bool inc, bool has_detach, bool detach,
                  bool has_resume, bool resume, Error **errp)
 {
     bool resume_requested;
     Error *local_err = NULL;
     MigrationState *s = migrate_get_current();
-    const char *p = NULL;
+    MigrationChannel *channel = NULL;
+    MigrationAddress *addr = NULL;
 
-    /* URI is not suitable for migration? */
-    if (!migration_channels_and_uri_compatible(uri, errp)) {
+    /*
+     * Having preliminary checks for uri and channel
+     */
+    if (uri && has_channels) {
+        error_setg(errp, "'uri' and 'channels' arguments are mutually "
+                   "exclusive; exactly one of the two should be present in "
+                   "'migrate' qmp command ");
+        return;
+    } else if (channels) {
+        /* To verify that Migrate channel list has only item */
+        if (channels->next) {
+            error_setg(errp, "Channel list has more than one entries");
+            return;
+        }
+        channel = channels->value;
+    } else if (uri) {
+        /* caller uses the old URI syntax */
+        if (!migrate_uri_parse(uri, &channel, errp)) {
+            return;
+        }
+    } else {
+        error_setg(errp, "neither 'uri' or 'channels' argument are "
+                   "specified in 'migrate' qmp command ");
+        return;
+    }
+    addr = channel->addr;
+
+    /* transport mechanism not suitable for migration? */
+    if (!migration_channels_and_transport_compatible(addr, errp)) {
         return;
     }
 
@@ -1729,20 +1980,23 @@ void qmp_migrate(const char *uri, bool has_blk, bool blk,
         }
     }
 
-    if (strstart(uri, "tcp:", &p) ||
-        strstart(uri, "unix:", NULL) ||
-        strstart(uri, "vsock:", NULL)) {
-        socket_start_outgoing_migration(s, p ? p : uri, &local_err);
+    if (addr->transport == MIGRATION_ADDRESS_TYPE_SOCKET) {
+        SocketAddress *saddr = &addr->u.socket;
+        if (saddr->type == SOCKET_ADDRESS_TYPE_INET ||
+            saddr->type == SOCKET_ADDRESS_TYPE_UNIX ||
+            saddr->type == SOCKET_ADDRESS_TYPE_VSOCK) {
+            socket_start_outgoing_migration(s, saddr, &local_err);
+        } else if (saddr->type == SOCKET_ADDRESS_TYPE_FD) {
+            fd_start_outgoing_migration(s, saddr->u.fd.str, &local_err);
+        }
 #ifdef CONFIG_RDMA
-    } else if (strstart(uri, "rdma:", &p)) {
-        rdma_start_outgoing_migration(s, p, &local_err);
+    } else if (addr->transport == MIGRATION_ADDRESS_TYPE_RDMA) {
+        rdma_start_outgoing_migration(s, &addr->u.rdma, &local_err);
 #endif
-    } else if (strstart(uri, "exec:", &p)) {
-        exec_start_outgoing_migration(s, p, &local_err);
-    } else if (strstart(uri, "fd:", &p)) {
-        fd_start_outgoing_migration(s, p, &local_err);
-    } else if (strstart(uri, "file:", &p)) {
-        file_start_outgoing_migration(s, p, &local_err);
+    } else if (addr->transport == MIGRATION_ADDRESS_TYPE_EXEC) {
+        exec_start_outgoing_migration(s, addr->u.exec.args, &local_err);
+    } else if (addr->transport == MIGRATION_ADDRESS_TYPE_FILE) {
+        file_start_outgoing_migration(s, &addr->u.file, &local_err);
     } else {
         error_setg(&local_err, QERR_INVALID_PARAMETER_VALUE, "uri",
                    "a valid migration protocol");
@@ -1777,19 +2031,21 @@ void qmp_migrate_continue(MigrationStatus state, Error **errp)
     qemu_sem_post(&s->pause_sem);
 }
 
-/* migration thread support */
-/*
- * Something bad happened to the RP stream, mark an error
- * The caller shall print or trace something to indicate why
- */
-static void mark_source_rp_bad(MigrationState *s)
+int migration_rp_wait(MigrationState *s)
 {
-    s->rp_state.error = true;
-}
+    /* If migration has failure already, ignore the wait */
+    if (migrate_has_error(s)) {
+        return -1;
+    }
 
-void migration_rp_wait(MigrationState *s)
-{
     qemu_sem_wait(&s->rp_state.rp_sem);
+
+    /* After wait, double check that there's no failure */
+    if (migrate_has_error(s)) {
+        return -1;
+    }
+
+    return 0;
 }
 
 void migration_rp_kick(MigrationState *s)
@@ -1817,8 +2073,9 @@ static struct rp_cmd_args {
  * We're allowed to send more than requested (e.g. to round to our page size)
  * and we don't need to send pages that have already been sent.
  */
-static void migrate_handle_rp_req_pages(MigrationState *ms, const char* rbname,
-                                       ram_addr_t start, size_t len)
+static void
+migrate_handle_rp_req_pages(MigrationState *ms, const char* rbname,
+                            ram_addr_t start, size_t len, Error **errp)
 {
     long our_host_ps = qemu_real_host_page_size();
 
@@ -1830,38 +2087,37 @@ static void migrate_handle_rp_req_pages(MigrationState *ms, const char* rbname,
      */
     if (!QEMU_IS_ALIGNED(start, our_host_ps) ||
         !QEMU_IS_ALIGNED(len, our_host_ps)) {
-        error_report("%s: Misaligned page request, start: " RAM_ADDR_FMT
-                     " len: %zd", __func__, start, len);
-        mark_source_rp_bad(ms);
+        error_setg(errp, "MIG_RP_MSG_REQ_PAGES: Misaligned page request, start:"
+                   RAM_ADDR_FMT " len: %zd", start, len);
         return;
     }
 
-    if (ram_save_queue_pages(rbname, start, len)) {
-        mark_source_rp_bad(ms);
-    }
+    ram_save_queue_pages(rbname, start, len, errp);
 }
 
-static int migrate_handle_rp_recv_bitmap(MigrationState *s, char *block_name)
+static bool migrate_handle_rp_recv_bitmap(MigrationState *s, char *block_name,
+                                          Error **errp)
 {
     RAMBlock *block = qemu_ram_block_by_name(block_name);
 
     if (!block) {
-        error_report("%s: invalid block name '%s'", __func__, block_name);
-        return -EINVAL;
+        error_setg(errp, "MIG_RP_MSG_RECV_BITMAP has invalid block name '%s'",
+                   block_name);
+        return false;
     }
 
     /* Fetch the received bitmap and refresh the dirty bitmap */
-    return ram_dirty_bitmap_reload(s, block);
+    return ram_dirty_bitmap_reload(s, block, errp);
 }
 
-static int migrate_handle_rp_resume_ack(MigrationState *s, uint32_t value)
+static bool migrate_handle_rp_resume_ack(MigrationState *s,
+                                         uint32_t value, Error **errp)
 {
     trace_source_return_path_thread_resume_ack(value);
 
     if (value != MIGRATION_RESUME_ACK_VALUE) {
-        error_report("%s: illegal resume_ack value %"PRIu32,
-                     __func__, value);
-        return -1;
+        error_setg(errp, "illegal resume_ack value %"PRIu32, value);
+        return false;
     }
 
     /* Now both sides are active. */
@@ -1871,7 +2127,7 @@ static int migrate_handle_rp_resume_ack(MigrationState *s, uint32_t value)
     /* Notify send thread that time to continue send pages */
     migration_rp_kick(s);
 
-    return 0;
+    return true;
 }
 
 /*
@@ -1919,48 +2175,46 @@ static void *source_return_path_thread(void *opaque)
     uint32_t tmp32, sibling_error;
     ram_addr_t start = 0; /* =0 to silence warning */
     size_t  len = 0, expected_len;
+    Error *err = NULL;
     int res;
 
     trace_source_return_path_thread_entry();
     rcu_register_thread();
 
-    while (!ms->rp_state.error && !qemu_file_get_error(rp) &&
-           migration_is_setup_or_active(ms->state)) {
+    while (migration_is_setup_or_active(ms->state)) {
         trace_source_return_path_thread_loop_top();
+
         header_type = qemu_get_be16(rp);
         header_len = qemu_get_be16(rp);
 
         if (qemu_file_get_error(rp)) {
-            mark_source_rp_bad(ms);
+            qemu_file_get_error_obj(rp, &err);
             goto out;
         }
 
         if (header_type >= MIG_RP_MSG_MAX ||
             header_type == MIG_RP_MSG_INVALID) {
-            error_report("RP: Received invalid message 0x%04x length 0x%04x",
-                         header_type, header_len);
-            mark_source_rp_bad(ms);
+            error_setg(&err, "Received invalid message 0x%04x length 0x%04x",
+                       header_type, header_len);
             goto out;
         }
 
         if ((rp_cmd_args[header_type].len != -1 &&
             header_len != rp_cmd_args[header_type].len) ||
             header_len > sizeof(buf)) {
-            error_report("RP: Received '%s' message (0x%04x) with"
-                         "incorrect length %d expecting %zu",
-                         rp_cmd_args[header_type].name, header_type, header_len,
-                         (size_t)rp_cmd_args[header_type].len);
-            mark_source_rp_bad(ms);
+            error_setg(&err, "Received '%s' message (0x%04x) with"
+                       "incorrect length %d expecting %zu",
+                       rp_cmd_args[header_type].name, header_type, header_len,
+                       (size_t)rp_cmd_args[header_type].len);
             goto out;
         }
 
         /* We know we've got a valid header by this point */
         res = qemu_get_buffer(rp, buf, header_len);
         if (res != header_len) {
-            error_report("RP: Failed reading data for message 0x%04x"
-                         " read %d expected %d",
-                         header_type, res, header_len);
-            mark_source_rp_bad(ms);
+            error_setg(&err, "Failed reading data for message 0x%04x"
+                       " read %d expected %d",
+                       header_type, res, header_len);
             goto out;
         }
 
@@ -1970,8 +2224,7 @@ static void *source_return_path_thread(void *opaque)
             sibling_error = ldl_be_p(buf);
             trace_source_return_path_thread_shut(sibling_error);
             if (sibling_error) {
-                error_report("RP: Sibling indicated error %d", sibling_error);
-                mark_source_rp_bad(ms);
+                error_setg(&err, "Sibling indicated error %d", sibling_error);
             }
             /*
              * We'll let the main thread deal with closing the RP
@@ -1989,7 +2242,10 @@ static void *source_return_path_thread(void *opaque)
         case MIG_RP_MSG_REQ_PAGES:
             start = ldq_be_p(buf);
             len = ldl_be_p(buf + 8);
-            migrate_handle_rp_req_pages(ms, NULL, start, len);
+            migrate_handle_rp_req_pages(ms, NULL, start, len, &err);
+            if (err) {
+                goto out;
+            }
             break;
 
         case MIG_RP_MSG_REQ_PAGES_ID:
@@ -2004,32 +2260,32 @@ static void *source_return_path_thread(void *opaque)
                 expected_len += tmp32;
             }
             if (header_len != expected_len) {
-                error_report("RP: Req_Page_id with length %d expecting %zd",
-                             header_len, expected_len);
-                mark_source_rp_bad(ms);
+                error_setg(&err, "Req_Page_id with length %d expecting %zd",
+                           header_len, expected_len);
+                goto out;
+            }
+            migrate_handle_rp_req_pages(ms, (char *)&buf[13], start, len,
+                                        &err);
+            if (err) {
                 goto out;
             }
-            migrate_handle_rp_req_pages(ms, (char *)&buf[13], start, len);
             break;
 
         case MIG_RP_MSG_RECV_BITMAP:
             if (header_len < 1) {
-                error_report("%s: missing block name", __func__);
-                mark_source_rp_bad(ms);
+                error_setg(&err, "MIG_RP_MSG_RECV_BITMAP missing block name");
                 goto out;
             }
             /* Format: len (1B) + idstr (<255B). This ends the idstr. */
             buf[buf[0] + 1] = '\0';
-            if (migrate_handle_rp_recv_bitmap(ms, (char *)(buf + 1))) {
-                mark_source_rp_bad(ms);
+            if (!migrate_handle_rp_recv_bitmap(ms, (char *)(buf + 1), &err)) {
                 goto out;
             }
             break;
 
         case MIG_RP_MSG_RESUME_ACK:
             tmp32 = ldl_be_p(buf);
-            if (migrate_handle_rp_resume_ack(ms, tmp32)) {
-                mark_source_rp_bad(ms);
+            if (!migrate_handle_rp_resume_ack(ms, tmp32, &err)) {
                 goto out;
             }
             break;
@@ -2045,13 +2301,29 @@ static void *source_return_path_thread(void *opaque)
     }
 
 out:
-    if (qemu_file_get_error(rp)) {
+    if (err) {
+        migrate_set_error(ms, err);
+        error_free(err);
         trace_source_return_path_thread_bad_end();
-        mark_source_rp_bad(ms);
+    }
+
+    if (ms->state == MIGRATION_STATUS_POSTCOPY_RECOVER) {
+        /*
+         * this will be extremely unlikely: that we got yet another network
+         * issue during recovering of the 1st network failure.. during this
+         * period the main migration thread can be waiting on rp_sem for
+         * this thread to sync with the other side.
+         *
+         * When this happens, explicitly kick the migration thread out of
+         * RECOVER stage and back to PAUSED, so the admin can try
+         * everything again.
+         */
+        migration_rp_kick(ms);
     }
 
     trace_source_return_path_thread_end();
     rcu_unregister_thread();
+
     return NULL;
 }
 
@@ -2073,12 +2345,11 @@ static int open_return_path_on_source(MigrationState *ms)
     return 0;
 }
 
-static int close_return_path_on_source(MigrationState *ms)
+/* Return true if error detected, or false otherwise */
+static bool close_return_path_on_source(MigrationState *ms)
 {
-    int ret;
-
     if (!ms->rp_state.rp_thread_created) {
-        return 0;
+        return false;
     }
 
     trace_migration_return_path_end_before();
@@ -2096,18 +2367,13 @@ static int close_return_path_on_source(MigrationState *ms)
         }
     }
 
-    trace_await_return_path_close_on_source_joining();
     qemu_thread_join(&ms->rp_state.rp_thread);
     ms->rp_state.rp_thread_created = false;
-    trace_await_return_path_close_on_source_close();
-
-    ret = ms->rp_state.error;
-    ms->rp_state.error = false;
-
     migration_release_dst_files(ms);
+    trace_migration_return_path_end_after();
 
-    trace_migration_return_path_end_after(ret);
-    return ret;
+    /* Return path will persist the error in MigrationState when quit */
+    return migrate_has_error(ms);
 }
 
 static inline void
@@ -2126,7 +2392,6 @@ static int postcopy_start(MigrationState *ms, Error **errp)
     int ret;
     QIOChannelBuffer *bioc;
     QEMUFile *fb;
-    int64_t time_at_stop = qemu_clock_get_ms(QEMU_CLOCK_REALTIME);
     uint64_t bandwidth = migrate_max_postcopy_bandwidth();
     bool restart_block = false;
     int cur_state = MIGRATION_STATUS_ACTIVE;
@@ -2148,9 +2413,11 @@ static int postcopy_start(MigrationState *ms, Error **errp)
     qemu_mutex_lock_iothread();
     trace_postcopy_start_set_run();
 
+    migration_downtime_start(ms);
+
     qemu_system_wakeup_request(QEMU_WAKEUP_REASON_OTHER, NULL);
     global_state_store();
-    ret = vm_stop_force_state(RUN_STATE_FINISH_MIGRATE);
+    ret = migration_stop_vm(RUN_STATE_FINISH_MIGRATE);
     if (ret < 0) {
         goto fail;
     }
@@ -2250,7 +2517,7 @@ static int postcopy_start(MigrationState *ms, Error **errp)
     ms->postcopy_after_devices = true;
     migration_call_notifiers(ms);
 
-    ms->downtime =  qemu_clock_get_ms(QEMU_CLOCK_REALTIME) - time_at_stop;
+    migration_downtime_end(ms);
 
     qemu_mutex_unlock_iothread();
 
@@ -2346,13 +2613,13 @@ static int migration_completion_precopy(MigrationState *s,
     int ret;
 
     qemu_mutex_lock_iothread();
-    s->downtime_start = qemu_clock_get_ms(QEMU_CLOCK_REALTIME);
+    migration_downtime_start(s);
     qemu_system_wakeup_request(QEMU_WAKEUP_REASON_OTHER, NULL);
 
     s->vm_old_state = runstate_get();
     global_state_store();
 
-    ret = vm_stop_force_state(RUN_STATE_FINISH_MIGRATE);
+    ret = migration_stop_vm(RUN_STATE_FINISH_MIGRATE);
     trace_migration_completion_vm_stop(ret);
     if (ret < 0) {
         goto out_unlock;
@@ -2519,7 +2786,9 @@ static int postcopy_resume_handshake(MigrationState *s)
     qemu_savevm_send_postcopy_resume(s->to_dst_file);
 
     while (s->state == MIGRATION_STATUS_POSTCOPY_RECOVER) {
-        migration_rp_wait(s);
+        if (migration_rp_wait(s)) {
+            return -1;
+        }
     }
 
     if (s->state == MIGRATION_STATUS_POSTCOPY_ACTIVE) {
@@ -2703,15 +2972,8 @@ static void migration_calculate_complete(MigrationState *s)
     int64_t end_time = qemu_clock_get_ms(QEMU_CLOCK_REALTIME);
     int64_t transfer_time;
 
+    migration_downtime_end(s);
     s->total_time = end_time - s->start_time;
-    if (!s->downtime) {
-        /*
-         * It's still not set, so we are precopy migration.  For
-         * postcopy, downtime is calculated during postcopy_start().
-         */
-        s->downtime = end_time - s->downtime_start;
-    }
-
     transfer_time = s->total_time - s->setup_time;
     if (transfer_time) {
         s->mbps = ((double) bytes * 8.0) / transfer_time / 1000;
@@ -3130,7 +3392,7 @@ static void bg_migration_vm_start_bh(void *opaque)
     s->vm_start_bh = NULL;
 
     vm_start();
-    s->downtime = qemu_clock_get_ms(QEMU_CLOCK_REALTIME) - s->downtime_start;
+    migration_downtime_end(s);
 }
 
 /**
@@ -3197,7 +3459,7 @@ static void *bg_migration_thread(void *opaque)
     s->setup_time = qemu_clock_get_ms(QEMU_CLOCK_HOST) - setup_start;
 
     trace_migration_thread_setup_complete();
-    s->downtime_start = qemu_clock_get_ms(QEMU_CLOCK_REALTIME);
+    migration_downtime_start(s);
 
     qemu_mutex_lock_iothread();
 
@@ -3210,7 +3472,7 @@ static void *bg_migration_thread(void *opaque)
 
     global_state_store();
     /* Forcibly stop VM before saving state of vCPUs and devices */
-    if (vm_stop_force_state(RUN_STATE_PAUSED)) {
+    if (migration_stop_vm(RUN_STATE_PAUSED)) {
         goto fail;
     }
     /*