migration: stop vm for cpr

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.sistare@oracle.com>
Reviewed-by: Peter Xu <peterx@redhat.com>
Link: https://lore.kernel.org/r/1708622920-68779-11-git-send-email-steven.sistare@oracle.com
Signed-off-by: Peter Xu <peterx@redhat.com>
This commit is contained in:
Steve Sistare 2024-02-22 09:28:36 -08:00 committed by Peter Xu
parent 4af667f87c
commit 9867d4ddd0
3 changed files with 32 additions and 22 deletions

View file

@ -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,

View file

@ -167,11 +167,19 @@ static gint page_request_addr_cmp(gconstpointer ap, gconstpointer bp)
return (a > b) - (a < b);
}
int migration_stop_vm(RunState state)
static int migration_stop_vm(MigrationState *s, RunState state)
{
int ret = vm_stop_force_state(state);
int ret;
migration_downtime_start(s);
s->vm_old_state = runstate_get();
global_state_store();
ret = vm_stop_force_state(state);
trace_vmstate_downtime_checkpoint("src-vm-stopped");
trace_migration_completion_vm_stop(ret);
return ret;
}
@ -1602,6 +1610,11 @@ 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;
@ -2454,10 +2467,7 @@ static int postcopy_start(MigrationState *ms, Error **errp)
bql_lock();
trace_postcopy_start_set_run();
migration_downtime_start(ms);
global_state_store();
ret = migration_stop_vm(RUN_STATE_FINISH_MIGRATE);
ret = migration_stop_vm(ms, RUN_STATE_FINISH_MIGRATE);
if (ret < 0) {
goto fail;
}
@ -2652,15 +2662,12 @@ static int migration_completion_precopy(MigrationState *s,
int ret;
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)) {
ret = migration_stop_vm(s, RUN_STATE_FINISH_MIGRATE);
if (ret < 0) {
goto out_unlock;
}
}
ret = migration_maybe_pause(s, current_active_state,
@ -3500,15 +3507,10 @@ static void *bg_migration_thread(void *opaque)
s->setup_time = qemu_clock_get_ms(QEMU_CLOCK_HOST) - setup_start;
trace_migration_thread_setup_complete();
migration_downtime_start(s);
bql_lock();
s->vm_old_state = runstate_get();
global_state_store();
/* Forcibly stop VM before saving state of vCPUs and devices */
if (migration_stop_vm(RUN_STATE_PAUSED)) {
if (migration_stop_vm(s, RUN_STATE_PAUSED)) {
goto fail;
}
/*
@ -3584,6 +3586,7 @@ 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.
@ -3655,6 +3658,14 @@ void migrate_fd_connect(MigrationState *s, Error *error_in)
return;
}
if (migrate_mode_is_cpr(s)) {
ret = migration_stop_vm(s, RUN_STATE_FINISH_MIGRATE);
if (ret < 0) {
error_setg(&local_err, "migration_stop_vm failed, error %d", -ret);
goto fail;
}
}
if (migrate_background_snapshot()) {
qemu_thread_create(&s->thread, "bg_snapshot",
bg_migration_thread, s, QEMU_THREAD_JOINABLE);

View file

@ -541,6 +541,4 @@ int migration_rp_wait(MigrationState *s);
*/
void migration_rp_kick(MigrationState *s);
int migration_stop_vm(RunState state);
#endif