migration: Unify block node activation error handling

Migration code activates all block driver nodes on the destination when
the migration completes. It does so by calling
bdrv_invalidate_cache_all() and blk_resume_after_migration(). There is
one code path for precopy and one for postcopy migration, resulting in
four function calls, which used to have three different failure modes.

This patch unifies the behaviour so that failure to activate all block
nodes is non-fatal, but the error message is logged and the VM isn't
automatically started. 'cont' will retry activating the block nodes.

Signed-off-by: Kevin Wolf <kwolf@redhat.com>
Reviewed-by: Eric Blake <eblake@redhat.com>

3 files changed, 19 insertions, 27 deletions

diff --git a/migration/migration.c b/migration/migration.c
index 799952ce99..04af71988d 100644
--- a/migration/migration.c
+++ b/migration/migration.c
@@ -338,20 +338,14 @@ static void process_incoming_migration_bh(void *opaque)
     Error *local_err = NULL;
     MigrationIncomingState *mis = opaque;
 
-    /* Make sure all file formats flush their mutable metadata */
+    /* Make sure all file formats flush their mutable metadata.
+     * If we get an error here, just don't restart the VM yet. */
     bdrv_invalidate_cache_all(&local_err);
-    if (local_err) {
-        migrate_set_state(&mis->state, MIGRATION_STATUS_ACTIVE,
-                          MIGRATION_STATUS_FAILED);
-        error_report_err(local_err);
-        migrate_decompress_threads_join();
-        exit(EXIT_FAILURE);
+    if (!local_err) {
+        blk_resume_after_migration(&local_err);
     }
-
-    /* If we get an error here, just don't restart the VM yet. */
-    blk_resume_after_migration(&local_err);
     if (local_err) {
-        error_free(local_err);
+        error_report_err(local_err);
         local_err = NULL;
         autostart = false;
     }
diff --git a/migration/savevm.c b/migration/savevm.c
index 352a8f23b5..3ca8d11704 100644
--- a/migration/savevm.c
+++ b/migration/savevm.c
@@ -1612,16 +1612,14 @@ static void loadvm_postcopy_handle_run_bh(void *opaque)
 
     qemu_announce_self();
 
-    /* Make sure all file formats flush their mutable metadata */
+    /* Make sure all file formats flush their mutable metadata.
+     * If we get an error here, just don't restart the VM yet. */
     bdrv_invalidate_cache_all(&local_err);
-    if (local_err) {
-        error_report_err(local_err);
+    if (!local_err) {
+        blk_resume_after_migration(&local_err);
     }
-
-    /* If we get an error here, just don't restart the VM yet. */
-    blk_resume_after_migration(&local_err);
     if (local_err) {
-        error_free(local_err);
+        error_report_err(local_err);
         local_err = NULL;
         autostart = false;
     }
diff --git a/qmp.c b/qmp.c
index ab74cd729d..25b5050f9f 100644
--- a/qmp.c
+++ b/qmp.c
@@ -196,15 +196,15 @@ void qmp_cont(Error **errp)
     }
 
     /* Continuing after completed migration. Images have been inactivated to
-     * allow the destination to take control. Need to get control back now. */
-    if (runstate_check(RUN_STATE_FINISH_MIGRATE) ||
-        runstate_check(RUN_STATE_POSTMIGRATE))
-    {
-        bdrv_invalidate_cache_all(&local_err);
-        if (local_err) {
-            error_propagate(errp, local_err);
-            return;
-        }
+     * allow the destination to take control. Need to get control back now.
+     *
+     * If there are no inactive block nodes (e.g. because the VM was just
+     * paused rather than completing a migration), bdrv_inactivate_all() simply
+     * doesn't do anything. */
+    bdrv_invalidate_cache_all(&local_err);
+    if (local_err) {
+        error_propagate(errp, local_err);
+        return;
     }
 
     blk_resume_after_migration(&local_err);