migration: re-active images while migration been canceled after inactive them

commit fe904ea824 fixed a case
which migration aborted QEMU because it didn't regain the control
of images while some errors happened.

Actually, there are another two cases can trigger the same error reports:
" bdrv_co_do_pwritev: Assertion `!(bs->open_flags & 0x0800)' failed",

Case 1, codes path:
migration_thread()
    migration_completion()
        bdrv_inactivate_all() ----------------> inactivate images
        qemu_savevm_state_complete_precopy()
            socket_writev_buffer() --------> error because destination fails
                qemu_fflush() ----------------> set error on migration stream
-> qmp_migrate_cancel() ----------------> user cancelled migration concurrently
    -> migrate_set_state() ------------------> set migrate CANCELLIN
    migration_completion() -----------------> go on to fail_invalidate
	if (s->state == MIGRATION_STATUS_ACTIVE) -> Jump this branch

Case 2, codes path:
migration_thread()
    migration_completion()
        bdrv_inactivate_all() ----------------> inactivate images
    migreation_completion() finished
-> qmp_migrate_cancel() ---------------> user cancelled migration concurrently
    qemu_mutex_lock_iothread();
    qemu_bh_schedule (s->cleanup_bh);

As we can see from above, qmp_migrate_cancel can slip in whenever
migration_thread does not hold the global lock. If this happens after
bdrv_inactive_all() been called, the above error reports will appear.

To prevent this, we can call bdrv_invalidate_cache_all() in qmp_migrate_cancel()
directly if we find images become inactive.

Besides, bdrv_invalidate_cache_all() in migration_completion() doesn't have the
protection of big lock, fix it by add the missing qemu_mutex_lock_iothread();

Signed-off-by: zhanghailiang <zhang.zhanghailiang@huawei.com>
Message-Id: <1485244792-11248-1-git-send-email-zhang.zhanghailiang@huawei.com>
Reviewed-by: Dr. David Alan Gilbert <dgilbert@redhat.com>
Reviewed-by: Stefan Hajnoczi <stefanha@redhat.com>
Signed-off-by: Dr. David Alan Gilbert <dgilbert@redhat.com>
This commit is contained in:
zhanghailiang 2017-01-24 15:59:52 +08:00 committed by Dr. David Alan Gilbert
parent b67b8c3a9d
commit 1d2acc3162
2 changed files with 18 additions and 0 deletions

View File

@ -180,6 +180,9 @@ struct MigrationState
/* Flag set once the migration thread is running (and needs joining) */
bool migration_thread_running;
/* Flag set once the migration thread called bdrv_inactivate_all */
bool block_inactive;
/* Queue of outstanding page requests from the destination */
QemuMutex src_page_req_mutex;
QSIMPLEQ_HEAD(src_page_requests, MigrationSrcPageRequest) src_page_requests;

View File

@ -1006,6 +1006,16 @@ static void migrate_fd_cancel(MigrationState *s)
if (s->state == MIGRATION_STATUS_CANCELLING && f) {
qemu_file_shutdown(f);
}
if (s->state == MIGRATION_STATUS_CANCELLING && s->block_inactive) {
Error *local_err = NULL;
bdrv_invalidate_cache_all(&local_err);
if (local_err) {
error_report_err(local_err);
} else {
s->block_inactive = false;
}
}
}
void add_migration_state_change_notifier(Notifier *notify)
@ -1745,6 +1755,7 @@ static void migration_completion(MigrationState *s, int current_active_state,
if (ret >= 0) {
qemu_file_set_rate_limit(s->to_dst_file, INT64_MAX);
qemu_savevm_state_complete_precopy(s->to_dst_file, false);
s->block_inactive = true;
}
}
qemu_mutex_unlock_iothread();
@ -1795,10 +1806,14 @@ fail_invalidate:
if (s->state == MIGRATION_STATUS_ACTIVE) {
Error *local_err = NULL;
qemu_mutex_lock_iothread();
bdrv_invalidate_cache_all(&local_err);
if (local_err) {
error_report_err(local_err);
} else {
s->block_inactive = false;
}
qemu_mutex_unlock_iothread();
}
fail: