migration: preserve suspended for snapshot

Restoring a snapshot can break a suspended guest.  Snapshots suffer from
the same suspended-state issues that affect live migration, plus they must
handle an additional problematic scenario, which is that a running vm must
remain running if it loads a suspended snapshot.

To save, the existing vm_stop call now completely stops the suspended
state.  Finish with vm_resume to leave the vm in the state it had prior
to the save, correctly restoring the suspended state.

To load, if the snapshot is not suspended, then vm_stop + vm_resume
correctly handles all states, and leaves the vm in the state it had prior
to the load.  However, if the snapshot is suspended, restoration is
trickier.  First, call vm_resume to restore the state to suspended so the
current state matches the saved state.  Then, if the pre-load state is
running, call wakeup to resume running.

Prior to these changes, the vm_stop to RUN_STATE_SAVE_VM and
RUN_STATE_RESTORE_VM did not change runstate if the current state was
suspended, but now it does, so allow these transitions.

Signed-off-by: Steve Sistare <steven.sistare@oracle.com>
Reviewed-by: Peter Xu <peterx@redhat.com>
Link: https://lore.kernel.org/r/1704312341-66640-8-git-send-email-steven.sistare@oracle.com
Signed-off-by: Peter Xu <peterx@redhat.com>

2 files changed, 18 insertions, 13 deletions

diff --git a/migration/migration-hmp-cmds.c b/migration/migration-hmp-cmds.c
index 99710c8..740a219 100644
--- a/migration/migration-hmp-cmds.c
+++ b/migration/migration-hmp-cmds.c
@@ -399,15 +399,17 @@ void hmp_info_migrate_parameters(Monitor *mon, const QDict *qdict)
 
 void hmp_loadvm(Monitor *mon, const QDict *qdict)
 {
-    int saved_vm_running  = runstate_is_running();
+    RunState saved_state = runstate_get();
+
     const char *name = qdict_get_str(qdict, "name");
     Error *err = NULL;
 
     vm_stop(RUN_STATE_RESTORE_VM);
 
-    if (load_snapshot(name, NULL, false, NULL, &err) && saved_vm_running) {
-        vm_start();
+    if (load_snapshot(name, NULL, false, NULL, &err)) {
+        load_snapshot_resume(saved_state);
     }
+
     hmp_handle_error(mon, err);
 }
 
diff --git a/migration/savevm.c b/migration/savevm.c
index 1b9ab7b..74f915f 100644
--- a/migration/savevm.c
+++ b/migration/savevm.c
@@ -3046,7 +3046,7 @@ bool save_snapshot(const char *name, bool overwrite, const char *vmstate,
     QEMUSnapshotInfo sn1, *sn = &sn1;
     int ret = -1, ret2;
     QEMUFile *f;
-    int saved_vm_running;
+    RunState saved_state = runstate_get();
     uint64_t vm_state_size;
     g_autoptr(GDateTime) now = g_date_time_new_now_local();
 
@@ -3092,8 +3092,6 @@ bool save_snapshot(const char *name, bool overwrite, const char *vmstate,
         return false;
     }
 
-    saved_vm_running = runstate_is_running();
-
     global_state_store();
     vm_stop(RUN_STATE_SAVE_VM);
 
@@ -3147,9 +3145,7 @@ bool save_snapshot(const char *name, bool overwrite, const char *vmstate,
  the_end:
     bdrv_drain_all_end();
 
-    if (saved_vm_running) {
-        vm_start();
-    }
+    vm_resume(saved_state);
     return ret == 0;
 }
 
@@ -3317,6 +3313,14 @@ err_drain:
     return false;
 }
 
+void load_snapshot_resume(RunState state)
+{
+    vm_resume(state);
+    if (state == RUN_STATE_RUNNING && runstate_get() == RUN_STATE_SUSPENDED) {
+        qemu_system_wakeup_request(QEMU_WAKEUP_REASON_OTHER, &error_abort);
+    }
+}
+
 bool delete_snapshot(const char *name, bool has_devices,
                      strList *devices, Error **errp)
 {
@@ -3381,16 +3385,15 @@ static void snapshot_load_job_bh(void *opaque)
 {
     Job *job = opaque;
     SnapshotJob *s = container_of(job, SnapshotJob, common);
-    int orig_vm_running;
+    RunState orig_state = runstate_get();
 
     job_progress_set_remaining(&s->common, 1);
 
-    orig_vm_running = runstate_is_running();
     vm_stop(RUN_STATE_RESTORE_VM);
 
     s->ret = load_snapshot(s->tag, s->vmstate, true, s->devices, s->errp);
-    if (s->ret && orig_vm_running) {
-        vm_start();
+    if (s->ret) {
+        load_snapshot_resume(orig_state);
     }
 
     job_progress_update(&s->common, 1);