mirrors/qemu
1
0
Fork 0
Code Issues Pull Requests Packages Projects Releases Wiki Activity

Migration pull request

Browse Source 
- Fabiano's fixed-ram patches (1-5 only)
 - Peter's cleanups on multifd tls IOC referencing
 - Steve's cpr patches for vfio (migration patches only)
 - Fabiano's fix on mbps stats racing with COMPLETE state
 - Fabiano's fix on return path thread hang
 -----BEGIN PGP SIGNATURE-----
 
 iIcEABYKADAWIQS5GE3CDMRX2s990ak7X8zN86vXBgUCZd7AbhIccGV0ZXJ4QHJl
 ZGhhdC5jb20ACgkQO1/MzfOr1wbg0gDyA3Vg3pIqCJ+u+hLZ+QKxY/pnu8Y5kF+E
 HK2IdslQUQD+OX4ATUnl+CGMiVX9fjs1fKx0Z0Qetq8gC1YJF13yuA0=
 =P2QF
 -----END PGP SIGNATURE-----

Merge tag 'migration-next-pull-request' of https://gitlab.com/peterx/qemu into staging

Migration pull request

- Fabiano's fixed-ram patches (1-5 only)
- Peter's cleanups on multifd tls IOC referencing
- Steve's cpr patches for vfio (migration patches only)
- Fabiano's fix on mbps stats racing with COMPLETE state
- Fabiano's fix on return path thread hang

# -----BEGIN PGP SIGNATURE-----
#
# iIcEABYKADAWIQS5GE3CDMRX2s990ak7X8zN86vXBgUCZd7AbhIccGV0ZXJ4QHJl
# ZGhhdC5jb20ACgkQO1/MzfOr1wbg0gDyA3Vg3pIqCJ+u+hLZ+QKxY/pnu8Y5kF+E
# HK2IdslQUQD+OX4ATUnl+CGMiVX9fjs1fKx0Z0Qetq8gC1YJF13yuA0=
# =P2QF
# -----END PGP SIGNATURE-----
# gpg: Signature made Wed 28 Feb 2024 05:11:10 GMT
# gpg:                using EDDSA key B9184DC20CC457DACF7DD1A93B5FCCCDF3ABD706
# gpg:                issuer "peterx@redhat.com"
# gpg: Good signature from "Peter Xu <xzpeter@gmail.com>" [marginal]
# gpg:                 aka "Peter Xu <peterx@redhat.com>" [marginal]
# gpg: WARNING: This key is not certified with sufficiently trusted signatures!
# gpg:          It is not certain that the signature belongs to the owner.
# Primary key fingerprint: B918 4DC2 0CC4 57DA CF7D  D1A9 3B5F CCCD F3AB D706

* tag 'migration-next-pull-request' of https://gitlab.com/peterx/qemu: (25 commits)
  migration: Use migrate_has_error() in close_return_path_on_source()
  migration: Join the return path thread before releasing to_dst_file
  migration: Fix qmp_query_migrate mbps value
  migration: options incompatible with cpr
  migration: update cpr-reboot description
  migration: stop vm for cpr
  migration: notifier error checking
  migration: refactor migrate_fd_connect failures
  migration: per-mode notifiers
  migration: MigrationNotifyFunc
  migration: remove postcopy_after_devices
  migration: MigrationEvent for notifiers
  migration: convert to NotifierWithReturn
  migration: remove error from notifier data
  notify: pass error to notifier with return
  migration/multifd: Drop unnecessary helper to destroy IOC
  migration/multifd: Cleanup outgoing_args in state destroy
  migration/multifd: Make multifd_channel_connect() return void
  migration/multifd: Drop registered_yank
  migration/multifd: Cleanup TLS iochannel referencing
  ...

Signed-off-by: Peter Maydell <peter.maydell@linaro.org>
This commit is contained in:
Peter Maydell 2024-02-28 17:27:10 +00:00
commit c0c6a0e352
24 changed files with 354 additions and 211 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

4
docs/devel/migration/main.rst
View File

@ -41,6 +41,10 @@ over any transport.
- exec migration: do the migration using the stdin/stdout through a process.
- fd migration: do the migration using a file descriptor that is
passed to QEMU. QEMU doesn't care how this file descriptor is opened.
- file migration: do the migration using a file that is passed to QEMU
by path. A file offset option is supported to allow a management
application to add its own metadata to the start of the file without
QEMU interference.
In addition, support is included for migration using RDMA, which
transports the page data using ``RDMA``, where the hardware takes care of

13
hw/net/virtio-net.c
View File

@ -3504,7 +3504,7 @@ out:
return !err;
}
static void virtio_net_handle_migration_primary(VirtIONet *n, MigrationState *s)
static void virtio_net_handle_migration_primary(VirtIONet *n, MigrationEvent *e)
{
bool should_be_hidden;
Error *err = NULL;
@ -3516,7 +3516,7 @@ static void virtio_net_handle_migration_primary(VirtIONet *n, MigrationState *s)
should_be_hidden = qatomic_read(&n->failover_primary_hidden);
if (migration_in_setup(s) && !should_be_hidden) {
if (e->type == MIG_EVENT_PRECOPY_SETUP && !should_be_hidden) {
if (failover_unplug_primary(n, dev)) {
vmstate_unregister(VMSTATE_IF(dev), qdev_get_vmsd(dev), dev);
qapi_event_send_unplug_primary(dev->id);
@ -3524,7 +3524,7 @@ static void virtio_net_handle_migration_primary(VirtIONet *n, MigrationState *s)
} else {
warn_report("couldn't unplug primary device");
}
} else if (migration_has_failed(s)) {
} else if (e->type == MIG_EVENT_PRECOPY_FAILED) {
/* We already unplugged the device let's plug it back */
if (!failover_replug_primary(n, dev, &err)) {
if (err) {
@ -3534,11 +3534,12 @@ static void virtio_net_handle_migration_primary(VirtIONet *n, MigrationState *s)
}
}
static void virtio_net_migration_state_notifier(Notifier *notifier, void *data)
static int virtio_net_migration_state_notifier(NotifierWithReturn *notifier,
MigrationEvent *e, Error **errp)
{
MigrationState *s = data;
VirtIONet *n = container_of(notifier, VirtIONet, migration_state);
virtio_net_handle_migration_primary(n, s);
virtio_net_handle_migration_primary(n, e);
return 0;
}
static bool failover_hide_primary_device(DeviceListener *listener,

13
hw/vfio/migration.c
View File

@ -754,22 +754,19 @@ static void vfio_vmstate_change(void *opaque, bool running, RunState state)
mig_state_to_str(new_state));
}
static void vfio_migration_state_notifier(Notifier *notifier, void *data)
static int vfio_migration_state_notifier(NotifierWithReturn *notifier,
MigrationEvent *e, Error **errp)
{
MigrationState *s = data;
VFIOMigration *migration = container_of(notifier, VFIOMigration,
migration_state);
VFIODevice *vbasedev = migration->vbasedev;
trace_vfio_migration_state_notifier(vbasedev->name,
MigrationStatus_str(s->state));
trace_vfio_migration_state_notifier(vbasedev->name, e->type);
switch (s->state) {
case MIGRATION_STATUS_CANCELLING:
case MIGRATION_STATUS_CANCELLED:
case MIGRATION_STATUS_FAILED:
if (e->type == MIG_EVENT_PRECOPY_FAILED) {
vfio_migration_set_state_or_reset(vbasedev, VFIO_DEVICE_STATE_RUNNING);
}
return 0;
}
static void vfio_migration_free(VFIODevice *vbasedev)

2
hw/vfio/trace-events
View File

@ -153,7 +153,7 @@ vfio_load_state(const char *name, uint64_t data) " (%s) data 0x%"PRIx64
vfio_load_state_device_data(const char *name, uint64_t data_size, int ret) " (%s) size 0x%"PRIx64" ret %d"
vfio_migration_realize(const char *name) " (%s)"
vfio_migration_set_state(const char *name, const char *state) " (%s) state %s"
vfio_migration_state_notifier(const char *name, const char *state) " (%s) state %s"
vfio_migration_state_notifier(const char *name, int state) " (%s) state %d"
vfio_save_block(const char *name, int data_size) " (%s) data_size %d"
vfio_save_cleanup(const char *name) " (%s)"
vfio_save_complete_precopy(const char *name, int ret) " (%s) ret %d"

10
hw/virtio/vhost-user.c
View File

@ -2084,7 +2084,7 @@ static int vhost_user_postcopy_end(struct vhost_dev *dev, Error **errp)
}
static int vhost_user_postcopy_notifier(NotifierWithReturn *notifier,
void *opaque)
void *opaque, Error **errp)
{
struct PostcopyNotifyData *pnd = opaque;
struct vhost_user *u = container_of(notifier, struct vhost_user,
@ -2096,20 +2096,20 @@ static int vhost_user_postcopy_notifier(NotifierWithReturn *notifier,
if (!virtio_has_feature(dev->protocol_features,
VHOST_USER_PROTOCOL_F_PAGEFAULT)) {
/* TODO: Get the device name into this error somehow */
error_setg(pnd->errp,
error_setg(errp,
"vhost-user backend not capable of postcopy");
return -ENOENT;
}
break;
case POSTCOPY_NOTIFY_INBOUND_ADVISE:
return vhost_user_postcopy_advise(dev, pnd->errp);
return vhost_user_postcopy_advise(dev, errp);
case POSTCOPY_NOTIFY_INBOUND_LISTEN:
return vhost_user_postcopy_listen(dev, pnd->errp);
return vhost_user_postcopy_listen(dev, errp);
case POSTCOPY_NOTIFY_INBOUND_END:
return vhost_user_postcopy_end(dev, pnd->errp);
return vhost_user_postcopy_end(dev, errp);
default:
/* We ignore notifications we don't know */

3
hw/virtio/virtio-balloon.c
View File

@ -633,7 +633,8 @@ static void virtio_balloon_free_page_done(VirtIOBalloon *s)
}
static int
virtio_balloon_free_page_hint_notify(NotifierWithReturn *n, void *data)
virtio_balloon_free_page_hint_notify(NotifierWithReturn *n, void *data,
Error **errp)
{
VirtIOBalloon *dev = container_of(n, VirtIOBalloon, free_page_hint_notify);
VirtIODevice *vdev = VIRTIO_DEVICE(dev);

2
include/hw/vfio/vfio-common.h
View File

@ -62,7 +62,7 @@ typedef struct VFIORegion {
typedef struct VFIOMigration {
struct VFIODevice *vbasedev;
VMChangeStateEntry *vm_state;
Notifier migration_state;
NotifierWithReturn migration_state;
uint32_t device_state;
int data_fd;
void *data_buffer;

2
include/hw/virtio/virtio-net.h
View File

@ -221,7 +221,7 @@ struct VirtIONet {
DeviceListener primary_listener;
QDict *primary_opts;
bool primary_opts_from_json;
Notifier migration_state;
NotifierWithReturn migration_state;
VirtioNetRssData rss_data;
struct NetRxPkt *rx_pkt;
struct EBPFRSSContext ebpf_rss;

47
include/migration/misc.h
View File

@ -31,7 +31,6 @@ typedef enum PrecopyNotifyReason {
typedef struct PrecopyNotifyData {
enum PrecopyNotifyReason reason;
Error **errp;
} PrecopyNotifyData;
void precopy_infrastructure_init(void);
@ -61,15 +60,51 @@ void migration_object_init(void);
void migration_shutdown(void);
bool migration_is_idle(void);
bool migration_is_active(MigrationState *);
void migration_add_notifier(Notifier *notify,
void (*func)(Notifier *notifier, void *data));
void migration_remove_notifier(Notifier *notify);
void migration_call_notifiers(MigrationState *s);
bool migrate_mode_is_cpr(MigrationState *);
typedef enum MigrationEventType {
MIG_EVENT_PRECOPY_SETUP,
MIG_EVENT_PRECOPY_DONE,
MIG_EVENT_PRECOPY_FAILED,
MIG_EVENT_MAX
} MigrationEventType;
typedef struct MigrationEvent {
MigrationEventType type;
} MigrationEvent;
/*
* A MigrationNotifyFunc may return an error code and an Error object,
* but only when @e->type is MIG_EVENT_PRECOPY_SETUP. The code is an int
* to allow for different failure modes and recovery actions.
*/
typedef int (*MigrationNotifyFunc)(NotifierWithReturn *notify,
MigrationEvent *e, Error **errp);
/*
* Register the notifier @notify to be called when a migration event occurs
* for MIG_MODE_NORMAL, as specified by the MigrationEvent passed to @func.
* Notifiers may receive events in any of the following orders:
* - MIG_EVENT_PRECOPY_SETUP -> MIG_EVENT_PRECOPY_DONE
* - MIG_EVENT_PRECOPY_SETUP -> MIG_EVENT_PRECOPY_FAILED
* - MIG_EVENT_PRECOPY_FAILED
*/
void migration_add_notifier(NotifierWithReturn *notify,
MigrationNotifyFunc func);
/*
* Same as migration_add_notifier, but applies to be specified @mode.
*/
void migration_add_notifier_mode(NotifierWithReturn *notify,
MigrationNotifyFunc func, MigMode mode);
void migration_remove_notifier(NotifierWithReturn *notify);
int migration_call_notifiers(MigrationState *s, MigrationEventType type,
Error **errp);
bool migration_in_setup(MigrationState *);
bool migration_has_finished(MigrationState *);
bool migration_has_failed(MigrationState *);
/* ...and after the device transmission */
bool migration_in_postcopy_after_devices(MigrationState *);
/* True if incoming migration entered POSTCOPY_INCOMING_DISCARD */
bool migration_in_incoming_postcopy(void);
/* True if incoming migration entered POSTCOPY_INCOMING_ADVISE */

8
include/qemu/notify.h
View File

@ -45,12 +45,16 @@ bool notifier_list_empty(NotifierList *list);
/* Same as Notifier but allows .notify() to return errors */
typedef struct NotifierWithReturn NotifierWithReturn;
/* Return int to allow for different failure modes and recovery actions */
typedef int (*NotifierWithReturnFunc)(NotifierWithReturn *notifier, void *data,
Error **errp);
struct NotifierWithReturn {
/**
* Return 0 on success (next notifier will be invoked), otherwise
* notifier_with_return_list_notify() will stop and return the value.
*/
int (*notify)(NotifierWithReturn *notifier, void *data);
NotifierWithReturnFunc notify;
QLIST_ENTRY(NotifierWithReturn) node;
};
@ -69,6 +73,6 @@ void notifier_with_return_list_add(NotifierWithReturnList *list,
void notifier_with_return_remove(NotifierWithReturn *notifier);
int notifier_with_return_list_notify(NotifierWithReturnList *list,
void *data);
void *data, Error **errp);
#endif

192
migration/migration.c
View File

@ -69,8 +69,13 @@
#include "qemu/sockets.h"
#include "sysemu/kvm.h"
static NotifierList migration_state_notifiers =
NOTIFIER_LIST_INITIALIZER(migration_state_notifiers);
#define NOTIFIER_ELEM_INIT(array, elem) \
[elem] = NOTIFIER_WITH_RETURN_LIST_INITIALIZER((array)[elem])
static NotifierWithReturnList migration_state_notifiers[] = {
NOTIFIER_ELEM_INIT(migration_state_notifiers, MIG_MODE_NORMAL),
NOTIFIER_ELEM_INIT(migration_state_notifiers, MIG_MODE_CPR_REBOOT),
};
/* Messages sent on the return path from destination to source */
enum mig_rp_message_type {
@ -102,6 +107,7 @@ static int migration_maybe_pause(MigrationState *s,
int new_state);
static void migrate_fd_cancel(MigrationState *s);
static bool close_return_path_on_source(MigrationState *s);
static void migration_completion_end(MigrationState *s);
static void migration_downtime_start(MigrationState *s)
{
@ -162,11 +168,19 @@ 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;
}
@ -1319,6 +1333,8 @@ void migrate_set_state(int *state, int old_state, int new_state)
static void migrate_fd_cleanup(MigrationState *s)
{
MigrationEventType type;
g_free(s->hostname);
s->hostname = NULL;
json_writer_free(s->vmdesc);
@ -1326,6 +1342,8 @@ static void migrate_fd_cleanup(MigrationState *s)
qemu_savevm_state_cleanup();
close_return_path_on_source(s);
if (s->to_dst_file) {
QEMUFile *tmp;
@ -1350,12 +1368,6 @@ static void migrate_fd_cleanup(MigrationState *s)
qemu_fclose(tmp);
}
/*
* We already cleaned up to_dst_file, so errors from the return
* path might be due to that, ignore them.
*/
close_return_path_on_source(s);
assert(!migration_is_active(s));
if (s->state == MIGRATION_STATUS_CANCELLING) {
@ -1367,7 +1379,9 @@ static void migrate_fd_cleanup(MigrationState *s)
/* It is used on info migrate. We can't free it */
error_report_err(error_copy(s->error));
}
migration_call_notifiers(s);
type = migration_has_failed(s) ? MIG_EVENT_PRECOPY_FAILED :
MIG_EVENT_PRECOPY_DONE;
migration_call_notifiers(s, type, NULL);
block_cleanup_parameters();
yank_unregister_instance(MIGRATION_YANK_INSTANCE);
}
@ -1459,24 +1473,39 @@ static void migrate_fd_cancel(MigrationState *s)
}
}
void migration_add_notifier(Notifier *notify,
void (*func)(Notifier *notifier, void *data))
void migration_add_notifier_mode(NotifierWithReturn *notify,
MigrationNotifyFunc func, MigMode mode)
{
notify->notify = func;
notifier_list_add(&migration_state_notifiers, notify);
notify->notify = (NotifierWithReturnFunc)func;
notifier_with_return_list_add(&migration_state_notifiers[mode], notify);
}
void migration_remove_notifier(Notifier *notify)
void migration_add_notifier(NotifierWithReturn *notify,
MigrationNotifyFunc func)
{
migration_add_notifier_mode(notify, func, MIG_MODE_NORMAL);
}
void migration_remove_notifier(NotifierWithReturn *notify)
{
if (notify->notify) {
notifier_remove(notify);
notifier_with_return_remove(notify);
notify->notify = NULL;
}
}
void migration_call_notifiers(MigrationState *s)
int migration_call_notifiers(MigrationState *s, MigrationEventType type,
Error **errp)
{
notifier_list_notify(&migration_state_notifiers, s);
MigMode mode = s->parameters.mode;
MigrationEvent e;
int ret;
e.type = type;
ret = notifier_with_return_list_notify(&migration_state_notifiers[mode],
&e, errp);
assert(!ret || type == MIG_EVENT_PRECOPY_SETUP);
return ret;
}
bool migration_in_setup(MigrationState *s)
@ -1520,11 +1549,6 @@ bool migration_postcopy_is_alive(int state)
}
}
bool migration_in_postcopy_after_devices(MigrationState *s)
{
return migration_in_postcopy() && s->postcopy_after_devices;
}
bool migration_in_incoming_postcopy(void)
{
PostcopyState ps = postcopy_state_get();
@ -1583,6 +1607,11 @@ 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;
@ -1606,7 +1635,6 @@ int migrate_init(MigrationState *s, Error **errp)
s->expected_downtime = 0;
s->setup_time = 0;
s->start_postcopy = false;
s->postcopy_after_devices = false;
s->migration_thread_running = false;
error_free(s->error);
s->error = NULL;
@ -1922,6 +1950,23 @@ static bool migrate_prepare(MigrationState *s, bool blk, bool blk_inc,
return false;
}
if (migrate_mode_is_cpr(s)) {
const char *conflict = NULL;
if (migrate_postcopy()) {
conflict = "postcopy";
} else if (migrate_background_snapshot()) {
conflict = "background snapshot";
} else if (migrate_colo()) {
conflict = "COLO";
}
if (conflict) {
error_setg(errp, "Cannot use %s with CPR", conflict);
return false;
}
}
if (blk || blk_inc) {
if (migrate_colo()) {
error_setg(errp, "No disk migration is required in COLO mode");
@ -2384,8 +2429,7 @@ static bool close_return_path_on_source(MigrationState *ms)
* cause it to unblock if it's stuck waiting for the destination.
*/
WITH_QEMU_LOCK_GUARD(&ms->qemu_file_lock) {
if (ms->to_dst_file && ms->rp_state.from_dst_file &&
qemu_file_get_error(ms->to_dst_file)) {
if (migrate_has_error(ms) && ms->rp_state.from_dst_file) {
qemu_file_shutdown(ms->rp_state.from_dst_file);
}
}
@ -2436,10 +2480,7 @@ 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;
}
@ -2536,8 +2577,7 @@ static int postcopy_start(MigrationState *ms, Error **errp)
* at the transition to postcopy and after the device state; in particular
* spice needs to trigger a transition now
*/
ms->postcopy_after_devices = true;
migration_call_notifiers(ms);
migration_call_notifiers(ms, MIG_EVENT_PRECOPY_DONE, NULL);
migration_downtime_end(ms);
@ -2557,11 +2597,10 @@ static int postcopy_start(MigrationState *ms, Error **errp)
ret = qemu_file_get_error(ms->to_dst_file);
if (ret) {
error_setg(errp, "postcopy_start: Migration stream errored");
migrate_set_state(&ms->state, MIGRATION_STATUS_POSTCOPY_ACTIVE,
MIGRATION_STATUS_FAILED);
error_setg_errno(errp, -ret, "postcopy_start: Migration stream error");
bql_lock();
goto fail;
}
trace_postcopy_preempt_enabled(migrate_postcopy_preempt());
return ret;
@ -2582,6 +2621,7 @@ fail:
error_report_err(local_err);
}
}
migration_call_notifiers(ms, MIG_EVENT_PRECOPY_FAILED, NULL);
bql_unlock();
return -1;
}
@ -2635,16 +2675,13 @@ 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 (!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,
MIGRATION_STATUS_DEVICE);
@ -2746,8 +2783,7 @@ static void migration_completion(MigrationState *s)
migrate_set_state(&s->state, MIGRATION_STATUS_ACTIVE,
MIGRATION_STATUS_COLO);
} else {
migrate_set_state(&s->state, current_active_state,
MIGRATION_STATUS_COMPLETED);
migration_completion_end(s);
}
return;
@ -2784,8 +2820,7 @@ static void bg_migration_completion(MigrationState *s)
goto fail;
}
migrate_set_state(&s->state, current_active_state,
MIGRATION_STATUS_COMPLETED);
migration_completion_end(s);
return;
fail:
@ -2874,6 +2909,13 @@ static MigThrError postcopy_pause(MigrationState *s)
while (true) {
QEMUFile *file;
/*
* We're already pausing, so ignore any errors on the return
* path and just wait for the thread to finish. It will be
* re-created when we resume.
*/
close_return_path_on_source(s);
/*
* Current channel is possibly broken. Release it. Note that this is
* guaranteed even without lock because to_dst_file should only be
@ -2893,13 +2935,6 @@ static MigThrError postcopy_pause(MigrationState *s)
qemu_file_shutdown(file);
qemu_fclose(file);
/*
* We're already pausing, so ignore any errors on the return
* path and just wait for the thread to finish. It will be
* re-created when we resume.
*/
close_return_path_on_source(s);
migrate_set_state(&s->state, s->state,
MIGRATION_STATUS_POSTCOPY_PAUSED);
@ -2987,18 +3022,28 @@ static MigThrError migration_detect_error(MigrationState *s)
}
}
static void migration_calculate_complete(MigrationState *s)
static void migration_completion_end(MigrationState *s)
{
uint64_t bytes = migration_transferred_bytes();
int64_t end_time = qemu_clock_get_ms(QEMU_CLOCK_REALTIME);
int64_t transfer_time;
/*
* Take the BQL here so that query-migrate on the QMP thread sees:
* - atomic update of s->total_time and s->mbps;
* - correct ordering of s->mbps update vs. s->state;
*/
bql_lock();
migration_downtime_end(s);
s->total_time = end_time - s->start_time;
transfer_time = s->total_time - s->setup_time;
if (transfer_time) {
s->mbps = ((double) bytes * 8.0) / transfer_time / 1000;
}
migrate_set_state(&s->state, s->state,
MIGRATION_STATUS_COMPLETED);
bql_unlock();
}
static void update_iteration_initial_status(MigrationState *s)
@ -3145,7 +3190,6 @@ static void migration_iteration_finish(MigrationState *s)
bql_lock();
switch (s->state) {
case MIGRATION_STATUS_COMPLETED:
migration_calculate_complete(s);
runstate_set(RUN_STATE_POSTMIGRATE);
break;
case MIGRATION_STATUS_COLO:
@ -3189,9 +3233,6 @@ static void bg_migration_iteration_finish(MigrationState *s)
bql_lock();
switch (s->state) {
case MIGRATION_STATUS_COMPLETED:
migration_calculate_complete(s);
break;
case MIGRATION_STATUS_ACTIVE:
case MIGRATION_STATUS_FAILED:
case MIGRATION_STATUS_CANCELLED:
@ -3483,15 +3524,10 @@ 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;
}
/*
@ -3567,6 +3603,7 @@ 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.
@ -3601,7 +3638,9 @@ void migrate_fd_connect(MigrationState *s, Error *error_in)
rate_limit = migrate_max_bandwidth();
/* Notify before starting migration thread */
migration_call_notifiers(s);
if (migration_call_notifiers(s, MIG_EVENT_PRECOPY_SETUP, &local_err)) {
goto fail;
}
}
migration_rate_set(rate_limit);
@ -3615,11 +3654,7 @@ void migrate_fd_connect(MigrationState *s, Error *error_in)
if (migrate_postcopy_ram() || migrate_return_path()) {
if (open_return_path_on_source(s)) {
error_setg(&local_err, "Unable to open return-path for postcopy");
migrate_set_state(&s->state, s->state, MIGRATION_STATUS_FAILED);
migrate_set_error(s, local_err);
error_report_err(local_err);
migrate_fd_cleanup(s);
return;
goto fail;
}
}
@ -3640,6 +3675,14 @@ 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);
@ -3648,6 +3691,13 @@ void migrate_fd_connect(MigrationState *s, Error *error_in)
migration_thread, s, QEMU_THREAD_JOINABLE);
}
s->migration_thread_running = true;
return;
fail:
migrate_set_error(s, local_err);
migrate_set_state(&s->state, s->state, MIGRATION_STATUS_FAILED);
error_report_err(local_err);
migrate_fd_cleanup(s);
}
static void migration_class_init(ObjectClass *klass, void *data)

4
migration/migration.h
View File

@ -348,8 +348,6 @@ struct MigrationState {
/* Flag set once the migration has been asked to enter postcopy */
bool start_postcopy;
/* Flag set after postcopy has sent the device state */
bool postcopy_after_devices;
/* Flag set once the migration thread is running (and needs joining) */
bool migration_thread_running;
@ -543,6 +541,4 @@ int migration_rp_wait(MigrationState *s);
*/
void migration_rp_kick(MigrationState *s);
int migration_stop_vm(RunState state);
#endif

105
migration/multifd.c
View File

@ -79,6 +79,19 @@ struct {
MultiFDMethods *ops;
} *multifd_send_state;
struct {
MultiFDRecvParams *params;
/* number of created threads */
int count;
/* syncs main thread and channels */
QemuSemaphore sem_sync;
/* global number of generated multifd packets */
uint64_t packet_num;
int exiting;
/* multifd ops */
MultiFDMethods *ops;
} *multifd_recv_state;
/* Multifd without compression */
/**
@ -440,6 +453,11 @@ static bool multifd_send_should_exit(void)
return qatomic_read(&multifd_send_state->exiting);
}
static bool multifd_recv_should_exit(void)
{
return qatomic_read(&multifd_recv_state->exiting);
}
/*
* The migration thread can wait on either of the two semaphores. This
* function can be used to kick the main thread out of waiting on either of
@ -641,18 +659,13 @@ static void multifd_send_terminate_threads(void)
}
}
static int multifd_send_channel_destroy(QIOChannel *send)
{
return socket_send_channel_destroy(send);
}
static bool multifd_send_cleanup_channel(MultiFDSendParams *p, Error **errp)
{
if (p->registered_yank) {
if (p->c) {
migration_ioc_unregister_yank(p->c);
}
multifd_send_channel_destroy(p->c);
object_unref(OBJECT(p->c));
p->c = NULL;
}
qemu_sem_destroy(&p->sem);
qemu_sem_destroy(&p->sem_sync);
g_free(p->name);
@ -671,6 +684,7 @@ static bool multifd_send_cleanup_channel(MultiFDSendParams *p, Error **errp)
static void multifd_send_cleanup_state(void)
{
socket_cleanup_outgoing_migration();
qemu_sem_destroy(&multifd_send_state->channels_created);
qemu_sem_destroy(&multifd_send_state->channels_ready);
g_free(multifd_send_state->params);
@ -873,16 +887,22 @@ out:
static void multifd_new_send_channel_async(QIOTask *task, gpointer opaque);
typedef struct {
MultiFDSendParams *p;
QIOChannelTLS *tioc;
} MultiFDTLSThreadArgs;
static void *multifd_tls_handshake_thread(void *opaque)
{
MultiFDSendParams *p = opaque;
QIOChannelTLS *tioc = QIO_CHANNEL_TLS(p->c);
MultiFDTLSThreadArgs *args = opaque;
qio_channel_tls_handshake(tioc,
qio_channel_tls_handshake(args->tioc,
multifd_new_send_channel_async,
p,
args->p,
NULL,
NULL);
g_free(args);
return NULL;
}
@ -892,6 +912,7 @@ static bool multifd_tls_channel_connect(MultiFDSendParams *p,
{
MigrationState *s = migrate_get_current();
const char *hostname = s->hostname;
MultiFDTLSThreadArgs *args;
QIOChannelTLS *tioc;
tioc = migration_tls_client_create(ioc, hostname, errp);
@ -906,29 +927,29 @@ static bool multifd_tls_channel_connect(MultiFDSendParams *p,
object_unref(OBJECT(ioc));
trace_multifd_tls_outgoing_handshake_start(ioc, tioc, hostname);
qio_channel_set_name(QIO_CHANNEL(tioc), "multifd-tls-outgoing");
p->c = QIO_CHANNEL(tioc);
args = g_new0(MultiFDTLSThreadArgs, 1);
args->tioc = tioc;
args->p = p;
p->tls_thread_created = true;
qemu_thread_create(&p->tls_thread, "multifd-tls-handshake-worker",
multifd_tls_handshake_thread, p,
multifd_tls_handshake_thread, args,
QEMU_THREAD_JOINABLE);
return true;
}
static bool multifd_channel_connect(MultiFDSendParams *p,
QIOChannel *ioc,
Error **errp)
static void multifd_channel_connect(MultiFDSendParams *p, QIOChannel *ioc)
{
qio_channel_set_delay(ioc, false);
migration_ioc_register_yank(ioc);
p->registered_yank = true;
/* Setup p->c only if the channel is completely setup */
p->c = ioc;
p->thread_created = true;
qemu_thread_create(&p->thread, p->name, multifd_send_thread, p,
QEMU_THREAD_JOINABLE);
return true;
}
/*
@ -960,7 +981,8 @@ static void multifd_new_send_channel_async(QIOTask *task, gpointer opaque)
return;
}
} else {
ret = multifd_channel_connect(p, ioc, &local_err);
multifd_channel_connect(p, ioc);
ret = true;
}
out:
@ -976,14 +998,12 @@ out:
trace_multifd_new_send_channel_async_error(p->id, local_err);
multifd_send_set_error(local_err);
if (!p->c) {
/*
* If no channel has been created, drop the initial
* reference. Otherwise cleanup happens at
* multifd_send_channel_destroy()
* For error cases (TLS or non-TLS), IO channel is always freed here
* rather than when cleanup multifd: since p->c is not set, multifd
* cleanup code doesn't even know its existence.
*/
object_unref(OBJECT(ioc));
}
error_free(local_err);
}
@ -1063,24 +1083,16 @@ bool multifd_send_setup(void)
return true;
}
struct {
MultiFDRecvParams *params;
/* number of created threads */
int count;
/* syncs main thread and channels */
QemuSemaphore sem_sync;
/* global number of generated multifd packets */
uint64_t packet_num;
/* multifd ops */
MultiFDMethods *ops;
} *multifd_recv_state;
static void multifd_recv_terminate_threads(Error *err)
{
int i;
trace_multifd_recv_terminate_threads(err != NULL);
if (qatomic_xchg(&multifd_recv_state->exiting, 1)) {
return;
}
if (err) {
MigrationState *s = migrate_get_current();
migrate_set_error(s, err);
@ -1094,8 +1106,12 @@ static void multifd_recv_terminate_threads(Error *err)
for (i = 0; i < migrate_multifd_channels(); i++) {
MultiFDRecvParams *p = &multifd_recv_state->params[i];
qemu_mutex_lock(&p->mutex);
p->quit = true;
/*
* multifd_recv_thread may hung at MULTIFD_FLAG_SYNC handle code,
* however try to wakeup it without harm in cleanup phase.
*/
qemu_sem_post(&p->sem_sync);
/*
* We could arrive here for two reasons:
* - normal quit, i.e. everything went fine, just finished
@ -1105,7 +1121,6 @@ static void multifd_recv_terminate_threads(Error *err)
if (p->c) {
qio_channel_shutdown(p->c, QIO_CHANNEL_SHUTDOWN_BOTH, NULL);
}
qemu_mutex_unlock(&p->mutex);
}
}
@ -1155,12 +1170,6 @@ void multifd_recv_cleanup(void)
for (i = 0; i < migrate_multifd_channels(); i++) {
MultiFDRecvParams *p = &multifd_recv_state->params[i];
/*
* multifd_recv_thread may hung at MULTIFD_FLAG_SYNC handle code,
* however try to wakeup it without harm in cleanup phase.
*/
qemu_sem_post(&p->sem_sync);
if (p->thread_created) {
qemu_thread_join(&p->thread);
}
@ -1210,7 +1219,7 @@ static void *multifd_recv_thread(void *opaque)
while (true) {
uint32_t flags;
if (p->quit) {
if (multifd_recv_should_exit()) {
break;
}
@ -1274,6 +1283,7 @@ int multifd_recv_setup(Error **errp)
multifd_recv_state = g_malloc0(sizeof(*multifd_recv_state));
multifd_recv_state->params = g_new0(MultiFDRecvParams, thread_count);
qatomic_set(&multifd_recv_state->count, 0);
qatomic_set(&multifd_recv_state->exiting, 0);
qemu_sem_init(&multifd_recv_state->sem_sync, 0);
multifd_recv_state->ops = multifd_ops[migrate_multifd_compression()];
@ -1282,7 +1292,6 @@ int multifd_recv_setup(Error **errp)
qemu_mutex_init(&p->mutex);
qemu_sem_init(&p->sem_sync, 0);
p->quit = false;
p->id = i;
p->packet_len = sizeof(MultiFDPacket_t)
+ sizeof(uint64_t) * page_count;

2
migration/multifd.h
View File

@ -78,8 +78,6 @@ typedef struct {
bool tls_thread_created;
/* communication channel */
QIOChannel *c;
/* is the yank function registered */
bool registered_yank;
/* packet allocated len */
uint32_t packet_len;
/* guest page size */

3
migration/postcopy-ram.c
View File

@ -77,10 +77,9 @@ int postcopy_notify(enum PostcopyNotifyReason reason, Error **errp)
{
struct PostcopyNotifyData pnd;
pnd.reason = reason;
pnd.errp = errp;
return notifier_with_return_list_notify(&postcopy_notifier_list,
&pnd);
&pnd, errp);
}
/*

1
migration/postcopy-ram.h
View File

@ -128,7 +128,6 @@ enum PostcopyNotifyReason {
struct PostcopyNotifyData {
enum PostcopyNotifyReason reason;
Error **errp;
};
void postcopy_add_notifier(NotifierWithReturn *nn);

3
migration/ram.c
View File

@ -426,9 +426,8 @@ int precopy_notify(PrecopyNotifyReason reason, Error **errp)
{
PrecopyNotifyData pnd;
pnd.reason = reason;
pnd.errp = errp;
return notifier_with_return_list_notify(&precopy_notifier_list, &pnd);
return notifier_with_return_list_notify(&precopy_notifier_list, &pnd, errp);
}
uint64_t ram_bytes_remaining(void)

19
migration/socket.c
View File

@ -60,17 +60,6 @@ QIOChannel *socket_send_channel_create_sync(Error **errp)
return QIO_CHANNEL(sioc);
}
int socket_send_channel_destroy(QIOChannel *send)
{
/* Remove channel */
object_unref(OBJECT(send));
if (outgoing_args.saddr) {
qapi_free_SocketAddress(outgoing_args.saddr);
outgoing_args.saddr = NULL;
}
return 0;
}
struct SocketConnectData {
MigrationState *s;
char *hostname;
@ -137,6 +126,14 @@ void socket_start_outgoing_migration(MigrationState *s,
NULL);
}
void socket_cleanup_outgoing_migration(void)
{
if (outgoing_args.saddr) {
qapi_free_SocketAddress(outgoing_args.saddr);
outgoing_args.saddr = NULL;
}
}
static void socket_accept_incoming_migration(QIONetListener *listener,
QIOChannelSocket *cioc,
gpointer opaque)

3
migration/socket.h
View File

@ -23,10 +23,11 @@
void socket_send_channel_create(QIOTaskFunc f, void *data);
QIOChannel *socket_send_channel_create_sync(Error **errp);
int socket_send_channel_destroy(QIOChannel *send);
void socket_start_incoming_migration(SocketAddress *saddr, Error **errp);
void socket_start_outgoing_migration(MigrationState *s,
SocketAddress *saddr, Error **errp);
void socket_cleanup_outgoing_migration(void);
#endif

14
net/vhost-vdpa.c
View File

@ -34,7 +34,7 @@
typedef struct VhostVDPAState {
NetClientState nc;
struct vhost_vdpa vhost_vdpa;
Notifier migration_state;
NotifierWithReturn migration_state;
VHostNetState *vhost_net;
/* Control commands shadow buffers */
@ -322,17 +322,17 @@ static void vhost_vdpa_net_log_global_enable(VhostVDPAState *s, bool enable)
}
}
static void vdpa_net_migration_state_notifier(Notifier *notifier, void *data)
static int vdpa_net_migration_state_notifier(NotifierWithReturn *notifier,
MigrationEvent *e, Error **errp)
{
MigrationState *migration = data;
VhostVDPAState *s = container_of(notifier, VhostVDPAState,
migration_state);
VhostVDPAState *s = container_of(notifier, VhostVDPAState, migration_state);
if (migration_in_setup(migration)) {
if (e->type == MIG_EVENT_PRECOPY_SETUP) {
vhost_vdpa_net_log_global_enable(s, true);
} else if (migration_has_failed(migration)) {
} else if (e->type == MIG_EVENT_PRECOPY_FAILED) {
vhost_vdpa_net_log_global_enable(s, false);
}
return 0;
}
static void vhost_vdpa_net_data_start_first(VhostVDPAState *s)

35
qapi/migration.json
View File

@ -636,18 +636,29 @@
#
# @normal: the original form of migration. (since 8.2)
#
# @cpr-reboot: The migrate command saves state to a file, allowing one to
# quit qemu, reboot to an updated kernel, and restart an updated
# version of qemu. The caller must specify a migration URI
# that writes to and reads from a file. Unlike normal mode,
# the use of certain local storage options does not block the
# migration, but the caller must not modify guest block devices
# between the quit and restart. To avoid saving guest RAM to the
# file, the memory backend must be shared, and the @x-ignore-shared
# migration capability must be set. Guest RAM must be non-volatile
# across reboot, such as by backing it with a dax device, but this
# is not enforced. The restarted qemu arguments must match those
# used to initially start qemu, plus the -incoming option.
# @cpr-reboot: The migrate command stops the VM and saves state to the URI.
# After quitting qemu, the user resumes by running qemu -incoming.
#
# This mode allows the user to quit qemu, and restart an updated version
# of qemu. The user may even update and reboot the OS before restarting,
# as long as the URI persists across a reboot.
#
# Unlike normal mode, the use of certain local storage options does not
# block the migration, but the user must not modify guest block devices
# between the quit and restart.
#
# This mode supports vfio devices provided the user first puts the guest
# in the suspended runstate, such as by issuing guest-suspend-ram to the
# qemu guest agent.
#
# Best performance is achieved when the memory backend is shared and the
# @x-ignore-shared migration capability is set, but this is not required.
# Further, if the user reboots before restarting such a configuration, the
# shared backend must be be non-volatile across reboot, such as by backing
# it with a dax device.
#
# cpr-reboot may not be used with postcopy, colo, or background-snapshot.
#
# (since 8.2)
##
{ 'enum': 'MigMode',

46
tests/qtest/migration-test.c
View File

@ -2423,7 +2423,7 @@ static void test_migrate_fd_finish_hook(QTestState *from,
qobject_unref(rsp);
}
static void test_migrate_fd_proto(void)
static void test_migrate_precopy_fd_socket(void)
{
MigrateCommon args = {
.listen_uri = "defer",
@ -2433,6 +2433,45 @@ static void test_migrate_fd_proto(void)
};
test_precopy_common(&args);
}
static void *migrate_precopy_fd_file_start(QTestState *from, QTestState *to)
{
g_autofree char *file = g_strdup_printf("%s/%s", tmpfs, FILE_TEST_FILENAME);
int src_flags = O_CREAT | O_RDWR;
int dst_flags = O_CREAT | O_RDWR;
int fds[2];
fds[0] = open(file, src_flags, 0660);
assert(fds[0] != -1);
fds[1] = open(file, dst_flags, 0660);
assert(fds[1] != -1);
qtest_qmp_fds_assert_success(to, &fds[0], 1,
"{ 'execute': 'getfd',"
" 'arguments': { 'fdname': 'fd-mig' }}");
qtest_qmp_fds_assert_success(from, &fds[1], 1,
"{ 'execute': 'getfd',"
" 'arguments': { 'fdname': 'fd-mig' }}");
close(fds[0]);
close(fds[1]);
return NULL;
}
static void test_migrate_precopy_fd_file(void)
{
MigrateCommon args = {
.listen_uri = "defer",
.connect_uri = "fd:fd-mig",
.start_hook = migrate_precopy_fd_file_start,
.finish_hook = test_migrate_fd_finish_hook
};
test_file_common(&args, true);
}
#endif /* _WIN32 */
static void do_test_validate_uuid(MigrateStart *args, bool should_fail)
@ -3527,7 +3566,10 @@ int main(int argc, char **argv)
/* migration_test_add("/migration/ignore_shared", test_ignore_shared); */
#ifndef _WIN32
migration_test_add("/migration/fd_proto", test_migrate_fd_proto);
migration_test_add("/migration/precopy/fd/tcp",
test_migrate_precopy_fd_socket);
migration_test_add("/migration/precopy/fd/file",
test_migrate_precopy_fd_file);
#endif
migration_test_add("/migration/validate_uuid", test_validate_uuid);
migration_test_add("/migration/validate_uuid_error",

17
ui/spice-core.c
View File

@ -42,7 +42,7 @@
/* core bits */
static SpiceServer *spice_server;
static Notifier migration_state;
static NotifierWithReturn migration_state;
static const char *auth = "spice";
static char *auth_passwd;
static time_t auth_expires = TIME_MAX;
@ -568,24 +568,23 @@ static SpiceInfo *qmp_query_spice_real(Error **errp)
return info;
}
static void migration_state_notifier(Notifier *notifier, void *data)
static int migration_state_notifier(NotifierWithReturn *notifier,
MigrationEvent *e, Error **errp)
{
MigrationState *s = data;
if (!spice_have_target_host) {
return;
return 0;
}
if (migration_in_setup(s)) {
if (e->type == MIG_EVENT_PRECOPY_SETUP) {
spice_server_migrate_start(spice_server);
} else if (migration_has_finished(s) ||
migration_in_postcopy_after_devices(s)) {
} else if (e->type == MIG_EVENT_PRECOPY_DONE) {
spice_server_migrate_end(spice_server, true);
spice_have_target_host = false;
} else if (migration_has_failed(s)) {
} else if (e->type == MIG_EVENT_PRECOPY_FAILED) {
spice_server_migrate_end(spice_server, false);
spice_have_target_host = false;
}
return 0;
}
int qemu_spice_migrate_info(const char *hostname, int port, int tls_port,

5
util/notify.c
View File

@ -61,13 +61,14 @@ void notifier_with_return_remove(NotifierWithReturn *notifier)
QLIST_REMOVE(notifier, node);
}
int notifier_with_return_list_notify(NotifierWithReturnList *list, void *data)
int notifier_with_return_list_notify(NotifierWithReturnList *list, void *data,
Error **errp)
{
NotifierWithReturn *notifier, *next;
int ret = 0;
QLIST_FOREACH_SAFE(notifier, &list->notifiers, node, next) {
ret = notifier->notify(notifier, data);
ret = notifier->notify(notifier, data, errp);
if (ret != 0) {
break;
}