1 files changed, 55 insertions, 17 deletions

diff --git a/migration/migration.c b/migration/migration.c
index a2e362541d..a5c22e327d 100644
--- a/migration/migration.c
+++ b/migration/migration.c
@@ -235,6 +235,8 @@ void migration_object_init(void)
     qemu_sem_init(&current_incoming->postcopy_pause_sem_dst, 0);
     qemu_sem_init(&current_incoming->postcopy_pause_sem_fault, 0);
     qemu_sem_init(&current_incoming->postcopy_pause_sem_fast_load, 0);
+    qemu_sem_init(&current_incoming->postcopy_qemufile_dst_done, 0);
+
     qemu_mutex_init(&current_incoming->page_request_mutex);
     current_incoming->page_requested = g_tree_new(page_request_addr_cmp);
 
@@ -737,6 +739,31 @@ void migration_fd_process_incoming(QEMUFile *f, Error **errp)
     migration_incoming_process();
 }
 
+/*
+ * Returns true when we want to start a new incoming migration process,
+ * false otherwise.
+ */
+static bool migration_should_start_incoming(bool main_channel)
+{
+    /* Multifd doesn't start unless all channels are established */
+    if (migrate_use_multifd()) {
+        return migration_has_all_channels();
+    }
+
+    /* Preempt channel only starts when the main channel is created */
+    if (migrate_postcopy_preempt()) {
+        return main_channel;
+    }
+
+    /*
+     * For all the rest types of migration, we should only reach here when
+     * it's the main channel that's being created, and we should always
+     * proceed with this channel.
+     */
+    assert(main_channel);
+    return true;
+}
+
 void migration_ioc_process_incoming(QIOChannel *ioc, Error **errp)
 {
     MigrationIncomingState *mis = migration_incoming_get_current();
@@ -798,7 +825,7 @@ void migration_ioc_process_incoming(QIOChannel *ioc, Error **errp)
         }
     }
 
-    if (migration_has_all_channels()) {
+    if (migration_should_start_incoming(default_channel)) {
         /* If it's a recovery, we're done */
         if (postcopy_try_recover()) {
             return;
@@ -3159,6 +3186,13 @@ static int await_return_path_close_on_source(MigrationState *ms)
     return ms->rp_state.error;
 }
 
+static inline void
+migration_wait_main_channel(MigrationState *ms)
+{
+    /* Wait until one PONG message received */
+    qemu_sem_wait(&ms->rp_state.rp_pong_acks);
+}
+
 /*
  * Switch from normal iteration to postcopy
  * Returns non-0 on error
@@ -3173,9 +3207,12 @@ static int postcopy_start(MigrationState *ms)
     bool restart_block = false;
     int cur_state = MIGRATION_STATUS_ACTIVE;
 
-    if (postcopy_preempt_wait_channel(ms)) {
-        migrate_set_state(&ms->state, ms->state, MIGRATION_STATUS_FAILED);
-        return -1;
+    if (migrate_postcopy_preempt()) {
+        migration_wait_main_channel(ms);
+        if (postcopy_preempt_establish_channel(ms)) {
+            migrate_set_state(&ms->state, ms->state, MIGRATION_STATUS_FAILED);
+            return -1;
+        }
     }
 
     if (!migrate_pause_before_switchover()) {
@@ -3587,6 +3624,20 @@ static int postcopy_do_resume(MigrationState *s)
     }
 
     /*
+     * If preempt is enabled, re-establish the preempt channel.  Note that
+     * we do it after resume prepare to make sure the main channel will be
+     * created before the preempt channel.  E.g. with weak network, the
+     * dest QEMU may get messed up with the preempt and main channels on
+     * the order of connection setup.  This guarantees the correct order.
+     */
+    ret = postcopy_preempt_establish_channel(s);
+    if (ret) {
+        error_report("%s: postcopy_preempt_establish_channel(): %d",
+                     __func__, ret);
+        return ret;
+    }
+
+    /*
      * Last handshake with destination on the resume (destination will
      * switch to postcopy-active afterwards)
      */
@@ -3647,14 +3698,6 @@ static MigThrError postcopy_pause(MigrationState *s)
         if (s->state == MIGRATION_STATUS_POSTCOPY_RECOVER) {
             /* Woken up by a recover procedure. Give it a shot */
 
-            if (postcopy_preempt_wait_channel(s)) {
-                /*
-                 * Preempt enabled, and new channel create failed; loop
-                 * back to wait for another recovery.
-                 */
-                continue;
-            }
-
             /*
              * Firstly, let's wake up the return path now, with a new
              * return path channel.
@@ -4347,11 +4390,6 @@ void migrate_fd_connect(MigrationState *s, Error *error_in)
         }
     }
 
-    /* This needs to be done before resuming a postcopy */
-    if (migrate_postcopy_preempt()) {
-        postcopy_preempt_setup(s);
-    }
-
     if (resume) {
         /* Wakeup the main migration thread to do the recovery */
         migrate_set_state(&s->state, MIGRATION_STATUS_POSTCOPY_PAUSED,