On Thu, Feb 08, 2024 at 10:54:03AM -0800, Steve Sistare wrote:
> When migration for cpr is initiated, stop the vm and set state
> RUN_STATE_FINISH_MIGRATE before ram is saved. This eliminates the
> possibility of ram and device state being out of sync, and guarantees
> that a guest in the suspended state remains suspended, because qmp_cont
> rejects a cont command in the RUN_STATE_FINISH_MIGRATE state.
>
> Signed-off-by: Steve Sistare <steven.sist...@oracle.com>
> ---
> include/migration/misc.h | 1 +
> migration/migration.c | 32 +++++++++++++++++++++++++-------
> 2 files changed, 26 insertions(+), 7 deletions(-)
>
> diff --git a/include/migration/misc.h b/include/migration/misc.h
> index 6dc234b..54c99a3 100644
> --- a/include/migration/misc.h
> +++ b/include/migration/misc.h
> @@ -60,6 +60,7 @@ void migration_object_init(void);
> void migration_shutdown(void);
> bool migration_is_idle(void);
> bool migration_is_active(MigrationState *);
> +bool migrate_mode_is_cpr(MigrationState *);
>
> typedef enum MigrationEventType {
> MIG_EVENT_PRECOPY_SETUP,
> diff --git a/migration/migration.c b/migration/migration.c
> index d1fce9e..fc5c587 100644
> --- a/migration/migration.c
> +++ b/migration/migration.c
> @@ -1603,6 +1603,11 @@ bool migration_is_active(MigrationState *s)
> s->state == MIGRATION_STATUS_POSTCOPY_ACTIVE);
> }
>
> +bool migrate_mode_is_cpr(MigrationState *s)
> +{
> + return s->parameters.mode == MIG_MODE_CPR_REBOOT;
> +}
> +
> int migrate_init(MigrationState *s, Error **errp)
> {
> int ret;
> @@ -2651,13 +2656,14 @@ static int
> migration_completion_precopy(MigrationState *s,
> bql_lock();
> migration_downtime_start(s);
>
> - s->vm_old_state = runstate_get();
> - global_state_store();
> -
> - ret = migration_stop_vm(RUN_STATE_FINISH_MIGRATE);
> - trace_migration_completion_vm_stop(ret);
> - if (ret < 0) {
> - goto out_unlock;
> + if (!migrate_mode_is_cpr(s)) {
> + s->vm_old_state = runstate_get();
> + global_state_store();
> + ret = migration_stop_vm(RUN_STATE_FINISH_MIGRATE);
> + trace_migration_completion_vm_stop(ret);
> + if (ret < 0) {
> + goto out_unlock;
> + }
> }
>
> ret = migration_maybe_pause(s, current_active_state,
> @@ -3576,6 +3582,7 @@ void migrate_fd_connect(MigrationState *s, Error
> *error_in)
> Error *local_err = NULL;
> uint64_t rate_limit;
> bool resume = s->state == MIGRATION_STATUS_POSTCOPY_PAUSED;
> + int ret;
>
> /*
> * If there's a previous error, free it and prepare for another one.
> @@ -3651,6 +3658,17 @@ void migrate_fd_connect(MigrationState *s, Error
> *error_in)
> goto fail;
> }
>
> + if (migrate_mode_is_cpr(s)) {
> + s->vm_old_state = runstate_get();
> + global_state_store();
> + ret = migration_stop_vm(RUN_STATE_FINISH_MIGRATE);
> + trace_migration_completion_vm_stop(ret);
> + if (ret < 0) {
> + error_setg(&local_err, "migration_stop_vm failed, error %d",
> -ret);
> + goto fail;
> + }
> + }
Could we have a helper function for the shared codes?
How about postcopy? I know it's nonsense to enable postcopy for cpr.. but
iiuc we don't yet forbid an user doing so. Maybe we should?
> +
> if (migrate_background_snapshot()) {
> qemu_thread_create(&s->thread, "bg_snapshot",
> bg_migration_thread, s, QEMU_THREAD_JOINABLE);
> --
> 1.8.3.1
>
--
Peter Xu
