migration: Cleanup during exit

Currently we cleanup the migration object as we exit main after the
main_loop finishes; however if there's a migration running things
get messy and we can end up with the migration thread still trying
to access freed structures.

We now take a ref to the object around the migration thread itself,
so the act of dropping the ref during exit doesn't cause us to lose
the state until the thread quits.

Cancelling the migration during migration also tries to get the thread
to quit.

We do this a bit earlier; so hopefully migration gets out of the way
before all the devices etc are freed.

Signed-off-by: Dr. David Alan Gilbert <dgilbert@redhat.com>
Tested-by: Alex Bennée <alex.bennee@linaro.org>
Message-Id: <20190227164900.16378-1-dgilbert@redhat.com>
Reviewed-by: Juan Quintela <quintela@redhat.com>
Reviewed-by: Alex Bennée <alex.bennee@linaro.org>
Signed-off-by: Dr. David Alan Gilbert <dgilbert@redhat.com>

3 files changed, 16 insertions, 3 deletions

diff --git a/include/migration/misc.h b/include/migration/misc.h
index 0471e04d1f..6f9df74436 100644
--- a/include/migration/misc.h
+++ b/include/migration/misc.h
@@ -36,7 +36,7 @@ void dump_vmstate_json_to_file(FILE *out_fp);
 
 /* migration/migration.c */
 void migration_object_init(void);
-void migration_object_finalize(void);
+void migration_shutdown(void);
 void qemu_start_incoming_migration(const char *uri, Error **errp);
 bool migration_is_idle(void);
 void add_migration_state_change_notifier(Notifier *notify);
diff --git a/migration/migration.c b/migration/migration.c
index e44f77af02..d45561f9b8 100644
--- a/migration/migration.c
+++ b/migration/migration.c
@@ -126,6 +126,7 @@ 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);
 
 void migration_object_init(void)
 {
@@ -167,8 +168,13 @@ void migration_object_init(void)
     }
 }
 
-void migration_object_finalize(void)
+void migration_shutdown(void)
 {
+    /*
+     * Cancel the current migration - that will (eventually)
+     * stop the migration using this structure
+     */
+    migrate_fd_cancel(current_migration);
     object_unref(OBJECT(current_migration));
 }
 
@@ -3134,6 +3140,7 @@ static void *migration_thread(void *opaque)
 
     rcu_register_thread();
 
+    object_ref(OBJECT(s));
     s->iteration_start_time = qemu_clock_get_ms(QEMU_CLOCK_REALTIME);
 
     qemu_savevm_state_header(s->to_dst_file);
@@ -3230,6 +3237,7 @@ static void *migration_thread(void *opaque)
 
     trace_migration_thread_after_loop();
     migration_iteration_finish(s);
+    object_unref(OBJECT(s));
     rcu_unregister_thread();
     return NULL;
 }
diff --git a/vl.c b/vl.c
index fd0d51320d..5be8cf4f11 100644
--- a/vl.c
+++ b/vl.c
@@ -4579,6 +4579,12 @@ int main(int argc, char **argv, char **envp)
 
     gdbserver_cleanup();
 
+    /*
+     * cleaning up the migration object cancels any existing migration
+     * try to do this early so that it also stops using devices.
+     */
+    migration_shutdown();
+
     /* No more vcpu or device emulation activity beyond this point */
     vm_shutdown();
 
@@ -4594,7 +4600,6 @@ int main(int argc, char **argv, char **envp)
     monitor_cleanup();
     qemu_chr_cleanup();
     user_creatable_cleanup();
-    migration_object_finalize();
     /* TODO: unref root container, check all devices are ok */
 
     return 0;