migration: Add Error** argument to qemu_savevm_state_setup()

This prepares ground for the changes coming next which add an Error**
argument to the .save_setup() handler. Callers of qemu_savevm_state_setup()
now handle the error and fail earlier setting the migration state from
MIGRATION_STATUS_SETUP to MIGRATION_STATUS_FAILED.

In qemu_savevm_state(), move the cleanup to preserve the error
reported by .save_setup() handlers.

Since the previous behavior was to ignore errors at this step of
migration, this change should be examined closely to check that
cleanups are still correctly done.

Signed-off-by: Cédric Le Goater <clg@redhat.com>
Reviewed-by: Peter Xu <peterx@redhat.com>
Link: https://lore.kernel.org/r/20240320064911.545001-7-clg@redhat.com
Signed-off-by: Peter Xu <peterx@redhat.com>

3 files changed, 47 insertions, 14 deletions

diff --git a/migration/migration.c b/migration/migration.c
index 86bf76e925..696762bc64 100644
--- a/migration/migration.c
+++ b/migration/migration.c
@@ -3431,6 +3431,8 @@ static void *migration_thread(void *opaque)
     int64_t setup_start = qemu_clock_get_ms(QEMU_CLOCK_HOST);
     MigThrError thr_error;
     bool urgent = false;
+    Error *local_err = NULL;
+    int ret;
 
     thread = migration_threads_add("live_migration", qemu_get_thread_id());
 
@@ -3474,12 +3476,24 @@ static void *migration_thread(void *opaque)
     }
 
     bql_lock();
-    qemu_savevm_state_setup(s->to_dst_file);
+    ret = qemu_savevm_state_setup(s->to_dst_file, &local_err);
     bql_unlock();
 
     qemu_savevm_wait_unplug(s, MIGRATION_STATUS_SETUP,
                                MIGRATION_STATUS_ACTIVE);
 
+    /*
+     * Handle SETUP failures after waiting for virtio-net-failover
+     * devices to unplug. This to preserve migration state transitions.
+     */
+    if (ret) {
+        migrate_set_error(s, local_err);
+        error_free(local_err);
+        migrate_set_state(&s->state, MIGRATION_STATUS_ACTIVE,
+                          MIGRATION_STATUS_FAILED);
+        goto out;
+    }
+
     s->setup_time = qemu_clock_get_ms(QEMU_CLOCK_HOST) - setup_start;
 
     trace_migration_thread_setup_complete();
@@ -3553,6 +3567,8 @@ static void *bg_migration_thread(void *opaque)
     MigThrError thr_error;
     QEMUFile *fb;
     bool early_fail = true;
+    Error *local_err = NULL;
+    int ret;
 
     rcu_register_thread();
     object_ref(OBJECT(s));
@@ -3586,12 +3602,24 @@ static void *bg_migration_thread(void *opaque)
 
     bql_lock();
     qemu_savevm_state_header(s->to_dst_file);
-    qemu_savevm_state_setup(s->to_dst_file);
+    ret = qemu_savevm_state_setup(s->to_dst_file, &local_err);
     bql_unlock();
 
     qemu_savevm_wait_unplug(s, MIGRATION_STATUS_SETUP,
                                MIGRATION_STATUS_ACTIVE);
 
+    /*
+     * Handle SETUP failures after waiting for virtio-net-failover
+     * devices to unplug. This to preserve migration state transitions.
+     */
+    if (ret) {
+        migrate_set_error(s, local_err);
+        error_free(local_err);
+        migrate_set_state(&s->state, MIGRATION_STATUS_ACTIVE,
+                          MIGRATION_STATUS_FAILED);
+        goto fail_setup;
+    }
+
     s->setup_time = qemu_clock_get_ms(QEMU_CLOCK_HOST) - setup_start;
 
     trace_migration_thread_setup_complete();
@@ -3660,6 +3688,7 @@ fail:
         bql_unlock();
     }
 
+fail_setup:
     bg_migration_iteration_finish(s);
 
     qemu_fclose(fb);
diff --git a/migration/savevm.c b/migration/savevm.c
index 6252fc37b7..327e9b346e 100644
--- a/migration/savevm.c
+++ b/migration/savevm.c
@@ -1310,11 +1310,11 @@ int qemu_savevm_state_prepare(Error **errp)
     return 0;
 }
 
-void qemu_savevm_state_setup(QEMUFile *f)
+int qemu_savevm_state_setup(QEMUFile *f, Error **errp)
 {
+    ERRP_GUARD();
     MigrationState *ms = migrate_get_current();
     SaveStateEntry *se;
-    Error *local_err = NULL;
     int ret = 0;
 
     json_writer_int64(ms->vmdesc, "page_size", qemu_target_page_size());
@@ -1323,10 +1323,9 @@ void qemu_savevm_state_setup(QEMUFile *f)
     trace_savevm_state_setup();
     QTAILQ_FOREACH(se, &savevm_state.handlers, entry) {
         if (se->vmsd && se->vmsd->early_setup) {
-            ret = vmstate_save(f, se, ms->vmdesc, &local_err);
+            ret = vmstate_save(f, se, ms->vmdesc, errp);
             if (ret) {
-                migrate_set_error(ms, local_err);
-                error_report_err(local_err);
+                migrate_set_error(ms, *errp);
                 qemu_file_set_error(f, ret);
                 break;
             }
@@ -1346,18 +1345,19 @@ void qemu_savevm_state_setup(QEMUFile *f)
         ret = se->ops->save_setup(f, se->opaque);
         save_section_footer(f, se);
         if (ret < 0) {
+            error_setg(errp, "failed to setup SaveStateEntry with id(name): "
+                       "%d(%s): %d", se->section_id, se->idstr, ret);
             qemu_file_set_error(f, ret);
             break;
         }
     }
 
     if (ret) {
-        return;
+        return ret;
     }
 
-    if (precopy_notify(PRECOPY_NOTIFY_SETUP, &local_err)) {
-        error_report_err(local_err);
-    }
+    /* TODO: Should we check that errp is set in case of failure ? */
+    return precopy_notify(PRECOPY_NOTIFY_SETUP, errp);
 }
 
 int qemu_savevm_state_resume_prepare(MigrationState *s)
@@ -1725,7 +1725,10 @@ static int qemu_savevm_state(QEMUFile *f, Error **errp)
     ms->to_dst_file = f;
 
     qemu_savevm_state_header(f);
-    qemu_savevm_state_setup(f);
+    ret = qemu_savevm_state_setup(f, errp);
+    if (ret) {
+        goto cleanup;
+    }
 
     while (qemu_file_get_error(f) == 0) {
         if (qemu_savevm_state_iterate(f, false) > 0) {
@@ -1738,10 +1741,11 @@ static int qemu_savevm_state(QEMUFile *f, Error **errp)
         qemu_savevm_state_complete_precopy(f, false, false);
         ret = qemu_file_get_error(f);
     }
-    qemu_savevm_state_cleanup();
     if (ret != 0) {
         error_setg_errno(errp, -ret, "Error while writing VM state");
     }
+cleanup:
+    qemu_savevm_state_cleanup();
 
     if (ret != 0) {
         status = MIGRATION_STATUS_FAILED;
diff --git a/migration/savevm.h b/migration/savevm.h
index 74669733dd..9ec96a995c 100644
--- a/migration/savevm.h
+++ b/migration/savevm.h
@@ -32,7 +32,7 @@
 bool qemu_savevm_state_blocked(Error **errp);
 void qemu_savevm_non_migratable_list(strList **reasons);
 int qemu_savevm_state_prepare(Error **errp);
-void qemu_savevm_state_setup(QEMUFile *f);
+int qemu_savevm_state_setup(QEMUFile *f, Error **errp);
 bool qemu_savevm_state_guest_unplug_pending(void);
 int qemu_savevm_state_resume_prepare(MigrationState *s);
 void qemu_savevm_state_header(QEMUFile *f);