migration (postcopy): move bdrv_invalidate_cache_all of of coroutine context

There is a possibility to hit an assert in qcow2_get_specific_info that
s->qcow_version is undefined. This happens when VM in starting from
suspended state, i.e. it processes incoming migration, and in the same
time 'info block' is called.

The problem is that qcow2_invalidate_cache() closes the image and
memset()s BDRVQcowState in the middle.

The patch moves processing of bdrv_invalidate_cache_all out of
coroutine context for postcopy migration to avoid that. This function
is called with the following stack:
  process_incoming_migration_co
  qemu_loadvm_state
  qemu_loadvm_state_main
  loadvm_process_command
  loadvm_postcopy_handle_run

Signed-off-by: Denis V. Lunev <den@openvz.org>
Tested-by: Dr. David Alan Gilbert <dgilbert@redhat.com>
Reviewed-by: Fam Zheng <famz@redhat.com>
CC: Paolo Bonzini <pbonzini@redhat.com>
CC: Juan Quintela <quintela@redhat.com>
CC: Amit Shah <amit.shah@redhat.com>
Message-Id: <1456304019-10507-3-git-send-email-den@openvz.org>
Signed-off-by: Amit Shah <amit.shah@redhat.com>
This commit is contained in:
Denis V. Lunev 2016-02-24 11:53:39 +03:00 committed by Amit Shah
parent 0aa6aefc9c
commit ea6a55bcc0

View File

@ -1495,17 +1495,10 @@ static int loadvm_postcopy_handle_listen(MigrationIncomingState *mis)
return 0;
}
/* After all discards we can start running and asking for pages */
static int loadvm_postcopy_handle_run(MigrationIncomingState *mis)
static void loadvm_postcopy_handle_run_bh(void *opaque)
{
PostcopyState ps = postcopy_state_set(POSTCOPY_INCOMING_RUNNING);
Error *local_err = NULL;
trace_loadvm_postcopy_handle_run();
if (ps != POSTCOPY_INCOMING_LISTENING) {
error_report("CMD_POSTCOPY_RUN in wrong postcopy state (%d)", ps);
return -1;
}
MigrationIncomingState *mis = opaque;
/* TODO we should move all of this lot into postcopy_ram.c or a shared code
* in migration.c
@ -1518,7 +1511,6 @@ static int loadvm_postcopy_handle_run(MigrationIncomingState *mis)
bdrv_invalidate_cache_all(&local_err);
if (local_err) {
error_report_err(local_err);
return -1;
}
trace_loadvm_postcopy_handle_run_cpu_sync();
@ -1534,6 +1526,23 @@ static int loadvm_postcopy_handle_run(MigrationIncomingState *mis)
runstate_set(RUN_STATE_PAUSED);
}
qemu_bh_delete(mis->bh);
}
/* After all discards we can start running and asking for pages */
static int loadvm_postcopy_handle_run(MigrationIncomingState *mis)
{
PostcopyState ps = postcopy_state_set(POSTCOPY_INCOMING_RUNNING);
trace_loadvm_postcopy_handle_run();
if (ps != POSTCOPY_INCOMING_LISTENING) {
error_report("CMD_POSTCOPY_RUN in wrong postcopy state (%d)", ps);
return -1;
}
mis->bh = qemu_bh_new(loadvm_postcopy_handle_run_bh, NULL);
qemu_bh_schedule(mis->bh);
/* We need to finish reading the stream from the package
* and also stop reading anything more from the stream that loaded the
* package (since it's now being read by the listener thread).