migration/savevm.c | 16 ++++++++-------- monitor/hmp-cmds.c | 7 +------ 2 files changed, 9 insertions(+), 14 deletions(-)
The HMP loadvm code is calling load_snapshot rather than
qmp_snapshot_load, in order to bypass the job infrastructure. The code
around it is almost the same, with one difference: hmp_loadvm is
restarting the VM if load_snapshot fails, qmp_snapshot_load is doing so
if load_snapshot succeeds.
Fix the bug in QMP by moving the common code to load_snapshot.
Cc: qemu-stable@nongnu.org
Signed-off-by: Paolo Bonzini <pbonzini@redhat.com>
---
migration/savevm.c | 16 ++++++++--------
monitor/hmp-cmds.c | 7 +------
2 files changed, 9 insertions(+), 14 deletions(-)
diff --git a/migration/savevm.c b/migration/savevm.c
index 52e2d72e4b..a899191cbf 100644
--- a/migration/savevm.c
+++ b/migration/savevm.c
@@ -2992,6 +2992,7 @@ bool load_snapshot(const char *name, const char *vmstate,
int ret;
AioContext *aio_context;
MigrationIncomingState *mis = migration_incoming_get_current();
+ int saved_vm_running = runstate_is_running();
if (!bdrv_all_can_snapshot(has_devices, devices, errp)) {
return false;
@@ -3024,6 +3025,8 @@ bool load_snapshot(const char *name, const char *vmstate,
return false;
}
+ vm_stop(RUN_STATE_RESTORE_VM);
+
/*
* Flush the record/replay queue. Now the VM state is going
* to change. Therefore we don't need to preserve its consistency
@@ -3061,13 +3064,17 @@ bool load_snapshot(const char *name, const char *vmstate,
if (ret < 0) {
error_setg(errp, "Error %d while loading VM state", ret);
- return false;
+ goto err_restart;
}
return true;
err_drain:
bdrv_drain_all_end();
+err_restart:
+ if (saved_vm_running) {
+ vm_start();
+ }
return false;
}
@@ -3135,17 +3142,10 @@ static void snapshot_load_job_bh(void *opaque)
{
Job *job = opaque;
SnapshotJob *s = container_of(job, SnapshotJob, common);
- int orig_vm_running;
job_progress_set_remaining(&s->common, 1);
- orig_vm_running = runstate_is_running();
- vm_stop(RUN_STATE_RESTORE_VM);
-
s->ret = load_snapshot(s->tag, s->vmstate, true, s->devices, s->errp);
- if (s->ret && orig_vm_running) {
- vm_start();
- }
job_progress_update(&s->common, 1);
diff --git a/monitor/hmp-cmds.c b/monitor/hmp-cmds.c
index 0ad5b77477..a39436c8cb 100644
--- a/monitor/hmp-cmds.c
+++ b/monitor/hmp-cmds.c
@@ -1127,15 +1127,10 @@ void hmp_balloon(Monitor *mon, const QDict *qdict)
void hmp_loadvm(Monitor *mon, const QDict *qdict)
{
- int saved_vm_running = runstate_is_running();
const char *name = qdict_get_str(qdict, "name");
Error *err = NULL;
- vm_stop(RUN_STATE_RESTORE_VM);
-
- if (!load_snapshot(name, NULL, false, NULL, &err) && saved_vm_running) {
- vm_start();
- }
+ load_snapshot(name, NULL, false, NULL, &err);
hmp_handle_error(mon, err);
}
--
2.26.2
* Paolo Bonzini (pbonzini@redhat.com) wrote: > The HMP loadvm code is calling load_snapshot rather than > qmp_snapshot_load, in order to bypass the job infrastructure. The code > around it is almost the same, with one difference: hmp_loadvm is > restarting the VM if load_snapshot fails, qmp_snapshot_load is doing so > if load_snapshot succeeds. > > Fix the bug in QMP by moving the common code to load_snapshot. So I agree it's nice to have them consistent, but hmm. > Cc: qemu-stable@nongnu.org > Signed-off-by: Paolo Bonzini <pbonzini@redhat.com> > --- > migration/savevm.c | 16 ++++++++-------- > monitor/hmp-cmds.c | 7 +------ > 2 files changed, 9 insertions(+), 14 deletions(-) > > diff --git a/migration/savevm.c b/migration/savevm.c > index 52e2d72e4b..a899191cbf 100644 > --- a/migration/savevm.c > +++ b/migration/savevm.c > @@ -2992,6 +2992,7 @@ bool load_snapshot(const char *name, const char *vmstate, > int ret; > AioContext *aio_context; > MigrationIncomingState *mis = migration_incoming_get_current(); > + int saved_vm_running = runstate_is_running(); > > if (!bdrv_all_can_snapshot(has_devices, devices, errp)) { > return false; > @@ -3024,6 +3025,8 @@ bool load_snapshot(const char *name, const char *vmstate, > return false; > } > > + vm_stop(RUN_STATE_RESTORE_VM); > + > /* > * Flush the record/replay queue. Now the VM state is going > * to change. Therefore we don't need to preserve its consistency > @@ -3061,13 +3064,17 @@ bool load_snapshot(const char *name, const char *vmstate, > > if (ret < 0) { > error_setg(errp, "Error %d while loading VM state", ret); > - return false; > + goto err_restart; > } I don't think this is safe. If qemu_loadvm_state(f) fails, depending on the point that it fails, the state of the VM is in a part loaded, indeterminate state - it doesn't seem right to auto-restart it. Note, that's a destinct failure from the earlier failures, e.g. trying to find the snapshot and noticing it doesn't exist - that's OK to restart the VM. Then there's the question of what to do if the load_snapshot succeeds; qmp's behaviour of running the loaded-VM doesn't seem wrong to me; although you'd think that would be based on the loaded state not the original; but that's probably a different question. Dave > return true; > > err_drain: > bdrv_drain_all_end(); > +err_restart: > + if (saved_vm_running) { > + vm_start(); > + } > return false; > } > > @@ -3135,17 +3142,10 @@ static void snapshot_load_job_bh(void *opaque) > { > Job *job = opaque; > SnapshotJob *s = container_of(job, SnapshotJob, common); > - int orig_vm_running; > > job_progress_set_remaining(&s->common, 1); > > - orig_vm_running = runstate_is_running(); > - vm_stop(RUN_STATE_RESTORE_VM); > - > s->ret = load_snapshot(s->tag, s->vmstate, true, s->devices, s->errp); > - if (s->ret && orig_vm_running) { > - vm_start(); > - } > > job_progress_update(&s->common, 1); > > diff --git a/monitor/hmp-cmds.c b/monitor/hmp-cmds.c > index 0ad5b77477..a39436c8cb 100644 > --- a/monitor/hmp-cmds.c > +++ b/monitor/hmp-cmds.c > @@ -1127,15 +1127,10 @@ void hmp_balloon(Monitor *mon, const QDict *qdict) > > void hmp_loadvm(Monitor *mon, const QDict *qdict) > { > - int saved_vm_running = runstate_is_running(); > const char *name = qdict_get_str(qdict, "name"); > Error *err = NULL; > > - vm_stop(RUN_STATE_RESTORE_VM); > - > - if (!load_snapshot(name, NULL, false, NULL, &err) && saved_vm_running) { > - vm_start(); > - } > + load_snapshot(name, NULL, false, NULL, &err); > hmp_handle_error(mon, err); > } > > -- > 2.26.2 > -- Dr. David Alan Gilbert / dgilbert@redhat.com / Manchester, UK
On Tue, May 04, 2021 at 12:58:26PM -0400, Paolo Bonzini wrote: > The HMP loadvm code is calling load_snapshot rather than > qmp_snapshot_load, in order to bypass the job infrastructure. The code > around it is almost the same, with one difference: hmp_loadvm is > restarting the VM if load_snapshot fails, qmp_snapshot_load is doing so > if load_snapshot succeeds. > > Fix the bug in QMP by moving the common code to load_snapshot. I'm wondering how did you discover this bug ? > Cc: qemu-stable@nongnu.org > Signed-off-by: Paolo Bonzini <pbonzini@redhat.com> > --- > migration/savevm.c | 16 ++++++++-------- > monitor/hmp-cmds.c | 7 +------ > 2 files changed, 9 insertions(+), 14 deletions(-) We ought to assert this behaviour in some test cases We have qemu-iotests/068 for HMP and qemu-iotests/tests/internal-snapshots-qapi for QMP... ....doh, i just realize we never got the latter merged. > > diff --git a/migration/savevm.c b/migration/savevm.c > index 52e2d72e4b..a899191cbf 100644 > --- a/migration/savevm.c > +++ b/migration/savevm.c > @@ -2992,6 +2992,7 @@ bool load_snapshot(const char *name, const char *vmstate, > int ret; > AioContext *aio_context; > MigrationIncomingState *mis = migration_incoming_get_current(); > + int saved_vm_running = runstate_is_running(); > > if (!bdrv_all_can_snapshot(has_devices, devices, errp)) { > return false; > @@ -3024,6 +3025,8 @@ bool load_snapshot(const char *name, const char *vmstate, > return false; > } > > + vm_stop(RUN_STATE_RESTORE_VM); > + > /* > * Flush the record/replay queue. Now the VM state is going > * to change. Therefore we don't need to preserve its consistency > @@ -3061,13 +3064,17 @@ bool load_snapshot(const char *name, const char *vmstate, > > if (ret < 0) { > error_setg(errp, "Error %d while loading VM state", ret); > - return false; > + goto err_restart; > } > > return true; > > err_drain: > bdrv_drain_all_end(); > +err_restart: > + if (saved_vm_running) { > + vm_start(); > + } > return false; > } > > @@ -3135,17 +3142,10 @@ static void snapshot_load_job_bh(void *opaque) > { > Job *job = opaque; > SnapshotJob *s = container_of(job, SnapshotJob, common); > - int orig_vm_running; > > job_progress_set_remaining(&s->common, 1); > > - orig_vm_running = runstate_is_running(); > - vm_stop(RUN_STATE_RESTORE_VM); > - > s->ret = load_snapshot(s->tag, s->vmstate, true, s->devices, s->errp); > - if (s->ret && orig_vm_running) { > - vm_start(); > - } > > job_progress_update(&s->common, 1); > > diff --git a/monitor/hmp-cmds.c b/monitor/hmp-cmds.c > index 0ad5b77477..a39436c8cb 100644 > --- a/monitor/hmp-cmds.c > +++ b/monitor/hmp-cmds.c > @@ -1127,15 +1127,10 @@ void hmp_balloon(Monitor *mon, const QDict *qdict) > > void hmp_loadvm(Monitor *mon, const QDict *qdict) > { > - int saved_vm_running = runstate_is_running(); > const char *name = qdict_get_str(qdict, "name"); > Error *err = NULL; > > - vm_stop(RUN_STATE_RESTORE_VM); > - > - if (!load_snapshot(name, NULL, false, NULL, &err) && saved_vm_running) { > - vm_start(); > - } > + load_snapshot(name, NULL, false, NULL, &err); > hmp_handle_error(mon, err); > } > > -- > 2.26.2 > > Regards, Daniel -- |: https://berrange.com -o- https://www.flickr.com/photos/dberrange :| |: https://libvirt.org -o- https://fstop138.berrange.com :| |: https://entangle-photo.org -o- https://www.instagram.com/dberrange :|
On 5/4/21 11:58 AM, Paolo Bonzini wrote: > The HMP loadvm code is calling load_snapshot rather than > qmp_snapshot_load, in order to bypass the job infrastructure. The code > around it is almost the same, with one difference: hmp_loadvm is > restarting the VM if load_snapshot fails, qmp_snapshot_load is doing so > if load_snapshot succeeds. > > Fix the bug in QMP by moving the common code to load_snapshot. > > Cc: qemu-stable@nongnu.org > Signed-off-by: Paolo Bonzini <pbonzini@redhat.com> > --- > migration/savevm.c | 16 ++++++++-------- > monitor/hmp-cmds.c | 7 +------ > 2 files changed, 9 insertions(+), 14 deletions(-) Reviewed-by: Eric Blake <eblake@redhat.com> -- Eric Blake, Principal Software Engineer Red Hat, Inc. +1-919-301-3226 Virtualization: qemu.org | libvirt.org
© 2016 - 2024 Red Hat, Inc.