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

Migration pull for 9.1

Browse Source 
- Het's new test cases for "channels"
 - Het's fix for a typo for vsock parsing
 - Cedric's VFIO error report series
 - Cedric's one more patch for dirty-bitmap error reports
 - Zhijian's rdma deprecation patch
 - Yuan's zeropage optimization to fix double faults on anon mem
 - Zhijian's COLO fix on a crash
 -----BEGIN PGP SIGNATURE-----
 
 iIgEABYKADAWIQS5GE3CDMRX2s990ak7X8zN86vXBgUCZig4HxIccGV0ZXJ4QHJl
 ZGhhdC5jb20ACgkQO1/MzfOr1wbQiwD/V5nSJzSuAG4Ra1Fjo+LRG2TT6qk8eNCi
 fIytehSw6cYA/0wqarxOF0tr7ikeyhtG3w4xFf44kk6KcPkoVSl1tqoL
 =pJmQ
 -----END PGP SIGNATURE-----

Merge tag 'migration-20240423-pull-request' of https://gitlab.com/peterx/qemu into staging

Migration pull for 9.1

- Het's new test cases for "channels"
- Het's fix for a typo for vsock parsing
- Cedric's VFIO error report series
- Cedric's one more patch for dirty-bitmap error reports
- Zhijian's rdma deprecation patch
- Yuan's zeropage optimization to fix double faults on anon mem
- Zhijian's COLO fix on a crash

# -----BEGIN PGP SIGNATURE-----
#
# iIgEABYKADAWIQS5GE3CDMRX2s990ak7X8zN86vXBgUCZig4HxIccGV0ZXJ4QHJl
# ZGhhdC5jb20ACgkQO1/MzfOr1wbQiwD/V5nSJzSuAG4Ra1Fjo+LRG2TT6qk8eNCi
# fIytehSw6cYA/0wqarxOF0tr7ikeyhtG3w4xFf44kk6KcPkoVSl1tqoL
# =pJmQ
# -----END PGP SIGNATURE-----
# gpg: Signature made Tue 23 Apr 2024 03:37:19 PM PDT
# gpg:                using EDDSA key B9184DC20CC457DACF7DD1A93B5FCCCDF3ABD706
# gpg:                issuer "peterx@redhat.com"
# gpg: Good signature from "Peter Xu <xzpeter@gmail.com>" [unknown]
# gpg:                 aka "Peter Xu <peterx@redhat.com>" [unknown]
# gpg: WARNING: This key is not certified with a trusted signature!
# gpg:          There is no indication that the signature belongs to the owner.
# Primary key fingerprint: B918 4DC2 0CC4 57DA CF7D  D1A9 3B5F CCCD F3AB D706

* tag 'migration-20240423-pull-request' of https://gitlab.com/peterx/qemu: (26 commits)
  migration/colo: Fix bdrv_graph_rdlock_main_loop: Assertion `!qemu_in_coroutine()' failed.
  migration/multifd: solve zero page causing multiple page faults
  migration: Add Error** argument to add_bitmaps_to_list()
  migration: Modify ram_init_bitmaps() to report dirty tracking errors
  migration: Add Error** argument to xbzrle_init()
  migration: Add Error** argument to ram_state_init()
  memory: Add Error** argument to the global_dirty_log routines
  migration: Introduce ram_bitmaps_destroy()
  memory: Add Error** argument to .log_global_start() handler
  migration: Add Error** argument to .load_setup() handler
  migration: Add Error** argument to .save_setup() handler
  migration: Add Error** argument to qemu_savevm_state_setup()
  migration: Add Error** argument to vmstate_save()
  migration: Always report an error in ram_save_setup()
  migration: Always report an error in block_save_setup()
  vfio: Always report an error in vfio_save_setup()
  s390/stattrib: Add Error** argument to set_migrationmode() handler
  tests/qtest/migration: Fix typo for vsock in SocketAddress_to_str
  tests/qtest/migration: Add negative tests to validate migration QAPIs
  tests/qtest/migration: Add multifd_tcp_plain test using list of channels instead of uri
  ...

Signed-off-by: Richard Henderson <richard.henderson@linaro.org>
This commit is contained in:
Richard Henderson 2024-04-23 21:32:22 -07:00
commit 88daa112d4
28 changed files with 558 additions and 216 deletions

5
hw/i386/xen/xen-hvm.c

@ -457,11 +457,12 @@ static void xen_log_sync(MemoryListener *listener, MemoryRegionSection *section)
int128_get64(section->size));
}
static void xen_log_global_start(MemoryListener *listener)
static bool xen_log_global_start(MemoryListener *listener, Error **errp)
{
if (xen_enabled()) {
xen_in_migration = true;
}
return true;
}
static void xen_log_global_stop(MemoryListener *listener)
@ -668,7 +669,7 @@ void xen_hvm_modified_memory(ram_addr_t start, ram_addr_t length)
void qmp_xen_set_global_dirty_log(bool enable, Error **errp)
{
if (enable) {
memory_global_dirty_log_start(GLOBAL_DIRTY_MIGRATION);
memory_global_dirty_log_start(GLOBAL_DIRTY_MIGRATION, errp);
} else {
memory_global_dirty_log_stop(GLOBAL_DIRTY_MIGRATION);
}

2
hw/ppc/spapr.c

@ -2174,7 +2174,7 @@ static const VMStateDescription vmstate_spapr = {
}
};
static int htab_save_setup(QEMUFile *f, void *opaque)
static int htab_save_setup(QEMUFile *f, void *opaque, Error **errp)
{
SpaprMachineState *spapr = opaque;

12
hw/s390x/s390-stattrib-kvm.c

@ -17,6 +17,7 @@
#include "sysemu/kvm.h"
#include "exec/ram_addr.h"
#include "kvm/kvm_s390x.h"
#include "qapi/error.h"
Object *kvm_s390_stattrib_create(void)
{
@ -137,14 +138,21 @@ static void kvm_s390_stattrib_synchronize(S390StAttribState *sa)
}
}
static int kvm_s390_stattrib_set_migrationmode(S390StAttribState *sa, bool val)
static int kvm_s390_stattrib_set_migrationmode(S390StAttribState *sa, bool val,
Error **errp)
{
struct kvm_device_attr attr = {
.group = KVM_S390_VM_MIGRATION,
.attr = val,
.addr = 0,
};
return kvm_vm_ioctl(kvm_state, KVM_SET_DEVICE_ATTR, &attr);
int r;
r = kvm_vm_ioctl(kvm_state, KVM_SET_DEVICE_ATTR, &attr);
if (r) {
error_setg_errno(errp, -r, "setting KVM_S390_VM_MIGRATION failed");
}
return r;
}
static long long kvm_s390_stattrib_get_dirtycount(S390StAttribState *sa)

15
hw/s390x/s390-stattrib.c

@ -60,11 +60,13 @@ void hmp_migrationmode(Monitor *mon, const QDict *qdict)
S390StAttribState *sas = s390_get_stattrib_device();
S390StAttribClass *sac = S390_STATTRIB_GET_CLASS(sas);
uint64_t what = qdict_get_int(qdict, "mode");
Error *local_err = NULL;
int r;
r = sac->set_migrationmode(sas, what);
r = sac->set_migrationmode(sas, what, &local_err);
if (r < 0) {
monitor_printf(mon, "Error: %s", strerror(-r));
monitor_printf(mon, "Error: %s", error_get_pretty(local_err));
error_free(local_err);
}
}
@ -166,7 +168,7 @@ static int cmma_load(QEMUFile *f, void *opaque, int version_id)
return ret;
}
static int cmma_save_setup(QEMUFile *f, void *opaque)
static int cmma_save_setup(QEMUFile *f, void *opaque, Error **errp)
{
S390StAttribState *sas = S390_STATTRIB(opaque);
S390StAttribClass *sac = S390_STATTRIB_GET_CLASS(sas);
@ -175,7 +177,7 @@ static int cmma_save_setup(QEMUFile *f, void *opaque)
* Signal that we want to start a migration, thus needing PGSTE dirty
* tracking.
*/
res = sac->set_migrationmode(sas, 1);
res = sac->set_migrationmode(sas, true, errp);
if (res) {
return res;
}
@ -260,7 +262,7 @@ static void cmma_save_cleanup(void *opaque)
{
S390StAttribState *sas = S390_STATTRIB(opaque);
S390StAttribClass *sac = S390_STATTRIB_GET_CLASS(sas);
sac->set_migrationmode(sas, 0);
sac->set_migrationmode(sas, false, NULL);
}
static bool cmma_active(void *opaque)
@ -293,7 +295,8 @@ static long long qemu_s390_get_dirtycount_stub(S390StAttribState *sa)
{
return 0;
}
static int qemu_s390_set_migrationmode_stub(S390StAttribState *sa, bool value)
static int qemu_s390_set_migrationmode_stub(S390StAttribState *sa, bool value,
Error **errp)
{
return 0;
}

4
hw/vfio/common.c

@ -1066,7 +1066,8 @@ out:
return ret;
}
static void vfio_listener_log_global_start(MemoryListener *listener)
static bool vfio_listener_log_global_start(MemoryListener *listener,
Error **errp)
{
VFIOContainerBase *bcontainer = container_of(listener, VFIOContainerBase,
listener);
@ -1083,6 +1084,7 @@ static void vfio_listener_log_global_start(MemoryListener *listener)
ret, strerror(-ret));
vfio_set_migration_error(ret);
}
return !ret;
}
static void vfio_listener_log_global_stop(MemoryListener *listener)

29
hw/vfio/migration.c

@ -376,11 +376,12 @@ static int vfio_save_prepare(void *opaque, Error **errp)
return 0;
}
static int vfio_save_setup(QEMUFile *f, void *opaque)
static int vfio_save_setup(QEMUFile *f, void *opaque, Error **errp)
{
VFIODevice *vbasedev = opaque;
VFIOMigration *migration = vbasedev->migration;
uint64_t stop_copy_size = VFIO_MIG_DEFAULT_DATA_BUFFER_SIZE;
int ret;
qemu_put_be64(f, VFIO_MIG_FLAG_DEV_SETUP_STATE);
@ -389,19 +390,19 @@ static int vfio_save_setup(QEMUFile *f, void *opaque)
stop_copy_size);
migration->data_buffer = g_try_malloc0(migration->data_buffer_size);
if (!migration->data_buffer) {
error_report("%s: Failed to allocate migration data buffer",
vbasedev->name);
error_setg(errp, "%s: Failed to allocate migration data buffer",
vbasedev->name);
return -ENOMEM;
}
if (vfio_precopy_supported(vbasedev)) {
int ret;
switch (migration->device_state) {
case VFIO_DEVICE_STATE_RUNNING:
ret = vfio_migration_set_state(vbasedev, VFIO_DEVICE_STATE_PRE_COPY,
VFIO_DEVICE_STATE_RUNNING);
if (ret) {
error_setg(errp, "%s: Failed to set new PRE_COPY state",
vbasedev->name);
return ret;
}
@ -412,6 +413,8 @@ static int vfio_save_setup(QEMUFile *f, void *opaque)
/* vfio_save_complete_precopy() will go to STOP_COPY */
break;
default:
error_setg(errp, "%s: Invalid device state %d", vbasedev->name,
migration->device_state);
return -EINVAL;
}
}
@ -420,7 +423,12 @@ static int vfio_save_setup(QEMUFile *f, void *opaque)
qemu_put_be64(f, VFIO_MIG_FLAG_END_OF_STATE);
return qemu_file_get_error(f);
ret = qemu_file_get_error(f);
if (ret < 0) {
error_setg_errno(errp, -ret, "%s: save setup failed", vbasedev->name);
}
return ret;
}
static void vfio_save_cleanup(void *opaque)
@ -580,12 +588,17 @@ static void vfio_save_state(QEMUFile *f, void *opaque)
}
}
static int vfio_load_setup(QEMUFile *f, void *opaque)
static int vfio_load_setup(QEMUFile *f, void *opaque, Error **errp)
{
VFIODevice *vbasedev = opaque;
int ret;
return vfio_migration_set_state(vbasedev, VFIO_DEVICE_STATE_RESUMING,
ret = vfio_migration_set_state(vbasedev, VFIO_DEVICE_STATE_RESUMING,
vbasedev->migration->device_state);
if (ret) {
error_setg(errp, "%s: Failed to set RESUMING state", vbasedev->name);
}
return ret;
}
static int vfio_load_cleanup(void *opaque)

3
hw/virtio/vhost.c

@ -1044,7 +1044,7 @@ check_dev_state:
return r;
}
static void vhost_log_global_start(MemoryListener *listener)
static bool vhost_log_global_start(MemoryListener *listener, Error **errp)
{
int r;
@ -1052,6 +1052,7 @@ static void vhost_log_global_start(MemoryListener *listener)
if (r < 0) {
abort();
}
return true;
}
static void vhost_log_global_stop(MemoryListener *listener)

10
include/exec/memory.h

@ -1001,8 +1001,11 @@ struct MemoryListener {
* active at that time.
*
* @listener: The #MemoryListener.
* @errp: pointer to Error*, to store an error if it happens.
*
* Return: true on success, else false setting @errp with error.
*/
void (*log_global_start)(MemoryListener *listener);
bool (*log_global_start)(MemoryListener *listener, Error **errp);
/**
* @log_global_stop:
@ -2581,8 +2584,11 @@ void memory_listener_unregister(MemoryListener *listener);
* memory_global_dirty_log_start: begin dirty logging for all regions
*
* @flags: purpose of starting dirty log, migration or dirty rate
* @errp: pointer to Error*, to store an error if it happens.
*
* Return: true on success, else false setting @errp with error.
*/
void memory_global_dirty_log_start(unsigned int flags);
bool memory_global_dirty_log_start(unsigned int flags, Error **errp);
/**
* memory_global_dirty_log_stop: end dirty logging for all regions

2
include/exec/ramblock.h

@ -58,7 +58,7 @@ struct RAMBlock {
off_t bitmap_offset;
uint64_t pages_offset;
/* bitmap of already received pages in postcopy */
/* Bitmap of already received pages. Only used on destination side. */
unsigned long *receivedmap;
/*

2
include/hw/s390x/storage-attributes.h

@ -39,7 +39,7 @@ struct S390StAttribClass {
int (*set_stattr)(S390StAttribState *sa, uint64_t start_gfn,
uint32_t count, uint8_t *values);
void (*synchronize)(S390StAttribState *sa);
int (*set_migrationmode)(S390StAttribState *sa, bool value);
int (*set_migrationmode)(S390StAttribState *sa, bool value, Error **errp);
int (*get_active)(S390StAttribState *sa);
long long (*get_dirtycount)(S390StAttribState *sa);
};

6
include/migration/register.h

@ -60,10 +60,11 @@ typedef struct SaveVMHandlers {
*
* @f: QEMUFile where to send the data
* @opaque: data pointer passed to register_savevm_live()
* @errp: pointer to Error*, to store an error if it happens.
*
* Returns zero to indicate success and negative for error
*/
int (*save_setup)(QEMUFile *f, void *opaque);
int (*save_setup)(QEMUFile *f, void *opaque, Error **errp);
/**
* @save_cleanup
@ -233,10 +234,11 @@ typedef struct SaveVMHandlers {
*
* @f: QEMUFile where to receive the data
* @opaque: data pointer passed to register_savevm_live()
* @errp: pointer to Error*, to store an error if it happens.
*
* Returns zero to indicate success and negative for error
*/
int (*load_setup)(QEMUFile *f, void *opaque);
int (*load_setup)(QEMUFile *f, void *opaque, Error **errp);
/**
* @load_cleanup

34
migration/block-dirty-bitmap.c

@ -481,13 +481,13 @@ static void dirty_bitmap_do_save_cleanup(DBMSaveState *s)
/* Called with the BQL taken. */
static int add_bitmaps_to_list(DBMSaveState *s, BlockDriverState *bs,
const char *bs_name, GHashTable *alias_map)
const char *bs_name, GHashTable *alias_map,
Error **errp)
{
BdrvDirtyBitmap *bitmap;
SaveBitmapState *dbms;
GHashTable *bitmap_aliases;
const char *node_alias, *bitmap_name, *bitmap_alias;
Error *local_err = NULL;
/* When an alias map is given, @bs_name must be @bs's node name */
assert(!alias_map || !strcmp(bs_name, bdrv_get_node_name(bs)));
@ -504,8 +504,8 @@ static int add_bitmaps_to_list(DBMSaveState *s, BlockDriverState *bs,
bitmap_name = bdrv_dirty_bitmap_name(bitmap);
if (!bs_name || strcmp(bs_name, "") == 0) {
error_report("Bitmap '%s' in unnamed node can't be migrated",
bitmap_name);
error_setg(errp, "Bitmap '%s' in unnamed node can't be migrated",
bitmap_name);
return -1;
}
@ -525,9 +525,9 @@ static int add_bitmaps_to_list(DBMSaveState *s, BlockDriverState *bs,
}
if (node_alias[0] == '#') {
error_report("Bitmap '%s' in a node with auto-generated "
"name '%s' can't be migrated",
bitmap_name, node_alias);
error_setg(errp, "Bitmap '%s' in a node with auto-generated "
"name '%s' can't be migrated",
bitmap_name, node_alias);
return -1;
}
@ -538,8 +538,7 @@ static int add_bitmaps_to_list(DBMSaveState *s, BlockDriverState *bs,
continue;
}
if (bdrv_dirty_bitmap_check(bitmap, BDRV_BITMAP_DEFAULT, &local_err)) {
error_report_err(local_err);
if (bdrv_dirty_bitmap_check(bitmap, BDRV_BITMAP_DEFAULT, errp)) {
return -1;
}
@ -558,9 +557,9 @@ static int add_bitmaps_to_list(DBMSaveState *s, BlockDriverState *bs,
}
} else {
if (strlen(bitmap_name) > UINT8_MAX) {
error_report("Cannot migrate bitmap '%s' on node '%s': "
"Name is longer than %u bytes",
bitmap_name, bs_name, UINT8_MAX);
error_setg(errp, "Cannot migrate bitmap '%s' on node '%s': "
"Name is longer than %u bytes",
bitmap_name, bs_name, UINT8_MAX);
return -1;
}
bitmap_alias = bitmap_name;
@ -599,7 +598,7 @@ static int add_bitmaps_to_list(DBMSaveState *s, BlockDriverState *bs,
}
/* Called with the BQL taken. */
static int init_dirty_bitmap_migration(DBMSaveState *s)
static int init_dirty_bitmap_migration(DBMSaveState *s, Error **errp)
{
BlockDriverState *bs;
SaveBitmapState *dbms;
@ -643,7 +642,7 @@ static int init_dirty_bitmap_migration(DBMSaveState *s)
}
if (bs && bs->drv && !bs->drv->is_filter) {
if (add_bitmaps_to_list(s, bs, name, NULL)) {
if (add_bitmaps_to_list(s, bs, name, NULL, errp)) {
goto fail;
}
g_hash_table_add(handled_by_blk, bs);
@ -656,7 +655,8 @@ static int init_dirty_bitmap_migration(DBMSaveState *s)
continue;
}
if (add_bitmaps_to_list(s, bs, bdrv_get_node_name(bs), alias_map)) {
if (add_bitmaps_to_list(s, bs, bdrv_get_node_name(bs), alias_map,
errp)) {
goto fail;
}
}
@ -1213,12 +1213,12 @@ fail:
return ret;
}
static int dirty_bitmap_save_setup(QEMUFile *f, void *opaque)
static int dirty_bitmap_save_setup(QEMUFile *f, void *opaque, Error **errp)
{
DBMSaveState *s = &((DBMState *)opaque)->save;
SaveBitmapState *dbms = NULL;
if (init_dirty_bitmap_migration(s) < 0) {
if (init_dirty_bitmap_migration(s, errp) < 0) {
return -1;
}

17
migration/block.c

@ -367,7 +367,7 @@ static void unset_dirty_tracking(void)
}
}
static int init_blk_migration(QEMUFile *f)
static int init_blk_migration(QEMUFile *f, Error **errp)
{
BlockDriverState *bs;
BlkMigDevState *bmds;
@ -378,7 +378,6 @@ static int init_blk_migration(QEMUFile *f)
BlkMigDevState *bmds;
BlockDriverState *bs;
} *bmds_bs;
Error *local_err = NULL;
int ret;
GRAPH_RDLOCK_GUARD_MAINLOOP();
@ -406,6 +405,8 @@ static int init_blk_migration(QEMUFile *f)
continue;
}
if (sectors < 0) {
error_setg(errp, "Error getting length of block device %s",
bdrv_get_device_name(bs));
ret = sectors;
bdrv_next_cleanup(&it);
goto out;
@ -442,9 +443,8 @@ static int init_blk_migration(QEMUFile *f)
bs = bmds_bs[i].bs;
if (bmds) {
ret = blk_insert_bs(bmds->blk, bs, &local_err);
ret = blk_insert_bs(bmds->blk, bs, errp);
if (ret < 0) {
error_report_err(local_err);
goto out;
}
@ -711,7 +711,7 @@ static void block_migration_cleanup(void *opaque)
blk_mig_unlock();
}
static int block_save_setup(QEMUFile *f, void *opaque)
static int block_save_setup(QEMUFile *f, void *opaque, Error **errp)
{
int ret;
@ -721,7 +721,7 @@ static int block_save_setup(QEMUFile *f, void *opaque)
warn_report("block migration is deprecated;"
" use blockdev-mirror with NBD instead");
ret = init_blk_migration(f);
ret = init_blk_migration(f, errp);
if (ret < 0) {
return ret;
}
@ -729,10 +729,15 @@ static int block_save_setup(QEMUFile *f, void *opaque)
/* start track dirty blocks */
ret = set_dirty_tracking();
if (ret) {
error_setg_errno(errp, -ret, "Failed to start block dirty tracking");
return ret;
}
ret = flush_blks(f);
if (ret) {
error_setg_errno(errp, -ret, "Flushing block failed");
return ret;
}
blk_mig_reset_dirty_cursor();
qemu_put_be64(f, BLK_MIG_FLAG_EOS);

18
migration/colo.c

@ -835,6 +835,16 @@ static void *colo_process_incoming_thread(void *opaque)
return NULL;
}
/* Make sure all file formats throw away their mutable metadata */
bql_lock();
bdrv_activate_all(&local_err);
if (local_err) {
bql_unlock();
error_report_err(local_err);
return NULL;
}
bql_unlock();
failover_init_state();
mis->to_src_file = qemu_file_get_return_path(mis->from_src_file);
@ -922,7 +932,6 @@ out:
int coroutine_fn colo_incoming_co(void)
{
MigrationIncomingState *mis = migration_incoming_get_current();
Error *local_err = NULL;
QemuThread th;
assert(bql_locked());
@ -931,13 +940,6 @@ int coroutine_fn colo_incoming_co(void)
return 0;
}
/* Make sure all file formats throw away their mutable metadata */
bdrv_activate_all(&local_err);
if (local_err) {
error_report_err(local_err);
return -EINVAL;
}
qemu_thread_create(&th, "COLO incoming", colo_process_incoming_thread,
mis, QEMU_THREAD_JOINABLE);

13
migration/dirtyrate.c

@ -90,9 +90,15 @@ static int64_t do_calculate_dirtyrate(DirtyPageRecord dirty_pages,
void global_dirty_log_change(unsigned int flag, bool start)
{
Error *local_err = NULL;
bool ret;
bql_lock();
if (start) {
memory_global_dirty_log_start(flag);
ret = memory_global_dirty_log_start(flag, &local_err);
if (!ret) {
error_report_err(local_err);
}
} else {
memory_global_dirty_log_stop(flag);
}
@ -608,9 +614,12 @@ static void calculate_dirtyrate_dirty_bitmap(struct DirtyRateConfig config)
{
int64_t start_time;
DirtyPageRecord dirty_pages;
Error *local_err = NULL;
bql_lock();
memory_global_dirty_log_start(GLOBAL_DIRTY_DIRTY_RATE);
if (!memory_global_dirty_log_start(GLOBAL_DIRTY_DIRTY_RATE, &local_err)) {
error_report_err(local_err);
}
/*
* 1'round of log sync may return all 1 bits with

33
migration/migration.c

@ -3431,6 +3431,8 @@ static void *migration_thread(void *opaque)
int64_t setup_start = qemu_clock_get_ms(QEMU_CLOCK_HOST);
MigThrError thr_error;
bool urgent = false;
Error *local_err = NULL;
int ret;
thread = migration_threads_add("live_migration", qemu_get_thread_id());
@ -3474,12 +3476,24 @@ static void *migration_thread(void *opaque)
}
bql_lock();
qemu_savevm_state_setup(s->to_dst_file);
ret = qemu_savevm_state_setup(s->to_dst_file, &local_err);
bql_unlock();
qemu_savevm_wait_unplug(s, MIGRATION_STATUS_SETUP,
MIGRATION_STATUS_ACTIVE);
/*
* Handle SETUP failures after waiting for virtio-net-failover
* devices to unplug. This to preserve migration state transitions.
*/
if (ret) {
migrate_set_error(s, local_err);
error_free(local_err);
migrate_set_state(&s->state, MIGRATION_STATUS_ACTIVE,
MIGRATION_STATUS_FAILED);
goto out;
}
s->setup_time = qemu_clock_get_ms(QEMU_CLOCK_HOST) - setup_start;
trace_migration_thread_setup_complete();
@ -3553,6 +3567,8 @@ static void *bg_migration_thread(void *opaque)
MigThrError thr_error;
QEMUFile *fb;
bool early_fail = true;
Error *local_err = NULL;
int ret;
rcu_register_thread();
object_ref(OBJECT(s));
@ -3586,12 +3602,24 @@ static void *bg_migration_thread(void *opaque)
bql_lock();
qemu_savevm_state_header(s->to_dst_file);
qemu_savevm_state_setup(s->to_dst_file);
ret = qemu_savevm_state_setup(s->to_dst_file, &local_err);
bql_unlock();
qemu_savevm_wait_unplug(s, MIGRATION_STATUS_SETUP,
MIGRATION_STATUS_ACTIVE);
/*
* Handle SETUP failures after waiting for virtio-net-failover
* devices to unplug. This to preserve migration state transitions.
*/
if (ret) {
migrate_set_error(s, local_err);
error_free(local_err);
migrate_set_state(&s->state, MIGRATION_STATUS_ACTIVE,
MIGRATION_STATUS_FAILED);
goto fail_setup;
}
s->setup_time = qemu_clock_get_ms(QEMU_CLOCK_HOST) - setup_start;
trace_migration_thread_setup_complete();
@ -3660,6 +3688,7 @@ fail:
bql_unlock();
}
fail_setup:
bg_migration_iteration_finish(s);
qemu_fclose(fb);

4
migration/multifd-zero-page.c

@ -80,8 +80,10 @@ void multifd_recv_zero_page_process(MultiFDRecvParams *p)
{
for (int i = 0; i < p->zero_num; i++) {
void *page = p->host + p->zero[i];
if (!buffer_is_zero(page, p->page_size)) {
if (ramblock_recv_bitmap_test_byte_offset(p->block, p->zero[i])) {
memset(page, 0, p->page_size);
} else {
ramblock_recv_bitmap_set_offset(p->block, p->zero[i]);
}
}
}

1
migration/multifd-zlib.c

@ -284,6 +284,7 @@ static int zlib_recv(MultiFDRecvParams *p, Error **errp)
int flush = Z_NO_FLUSH;
unsigned long start = zs->total_out;
ramblock_recv_bitmap_set_offset(p->block, p->normal[i]);
if (i == p->normal_num - 1) {
flush = Z_SYNC_FLUSH;
}

1
migration/multifd-zstd.c

@ -278,6 +278,7 @@ static int zstd_recv(MultiFDRecvParams *p, Error **errp)
z->in.pos = 0;
for (i = 0; i < p->normal_num; i++) {
ramblock_recv_bitmap_set_offset(p->block, p->normal[i]);
z->out.dst = p->host + p->normal[i];
z->out.size = p->page_size;
z->out.pos = 0;

1
migration/multifd.c

@ -277,6 +277,7 @@ static int nocomp_recv(MultiFDRecvParams *p, Error **errp)
for (int i = 0; i < p->normal_num; i++) {
p->iov[i].iov_base = p->host + p->normal[i];
p->iov[i].iov_len = p->page_size;
ramblock_recv_bitmap_set_offset(p->block, p->normal[i]);
}
return qio_channel_readv_all(p->c, p->iov, p->normal_num, errp);
}

110
migration/ram.c

@ -275,6 +275,10 @@ void ramblock_recv_bitmap_set_range(RAMBlock *rb, void *host_addr,
nr);
}
void ramblock_recv_bitmap_set_offset(RAMBlock *rb, uint64_t byte_offset)
{
set_bit_atomic(byte_offset >> TARGET_PAGE_BITS, rb->receivedmap);
}
#define RAMBLOCK_RECV_BITMAP_ENDING (0x0123456789abcdefULL)
/*
@ -2438,10 +2442,23 @@ static void xbzrle_cleanup(void)
XBZRLE_cache_unlock();
}
static void ram_bitmaps_destroy(void)
{
RAMBlock *block;
RAMBLOCK_FOREACH_NOT_IGNORED(block) {
g_free(block->clear_bmap);
block->clear_bmap = NULL;
g_free(block->bmap);
block->bmap = NULL;
g_free(block->file_bmap);
block->file_bmap = NULL;
}
}
static void ram_save_cleanup(void *opaque)
{
RAMState **rsp = opaque;
RAMBlock *block;
/* We don't use dirty log with background snapshots */
if (!migrate_background_snapshot()) {
@ -2458,12 +2475,7 @@ static void ram_save_cleanup(void *opaque)
}
}
RAMBLOCK_FOREACH_NOT_IGNORED(block) {
g_free(block->clear_bmap);
block->clear_bmap = NULL;
g_free(block->bmap);
block->bmap = NULL;
}
ram_bitmaps_destroy();
xbzrle_cleanup();
compress_threads_save_cleanup();
@ -2719,44 +2731,41 @@ int ram_discard_range(const char *rbname, uint64_t start, size_t length)
* For every allocation, we will try not to crash the VM if the
* allocation failed.
*/
static int xbzrle_init(void)
static bool xbzrle_init(Error **errp)
{
Error *local_err = NULL;
if (!migrate_xbzrle()) {
return 0;
return true;
}
XBZRLE_cache_lock();
XBZRLE.zero_target_page = g_try_malloc0(TARGET_PAGE_SIZE);
if (!XBZRLE.zero_target_page) {
error_report("%s: Error allocating zero page", __func__);
error_setg(errp, "%s: Error allocating zero page", __func__);
goto err_out;
}
XBZRLE.cache = cache_init(migrate_xbzrle_cache_size(),
TARGET_PAGE_SIZE, &local_err);
TARGET_PAGE_SIZE, errp);
if (!XBZRLE.cache) {
error_report_err(local_err);
goto free_zero_page;
}
XBZRLE.encoded_buf = g_try_malloc0(TARGET_PAGE_SIZE);
if (!XBZRLE.encoded_buf) {
error_report("%s: Error allocating encoded_buf", __func__);
error_setg(errp, "%s: Error allocating encoded_buf", __func__);
goto free_cache;
}
XBZRLE.current_buf = g_try_malloc(TARGET_PAGE_SIZE);
if (!XBZRLE.current_buf) {
error_report("%s: Error allocating current_buf", __func__);
error_setg(errp, "%s: Error allocating current_buf", __func__);
goto free_encoded_buf;
}
/* We are all good */
XBZRLE_cache_unlock();
return 0;
return true;
free_encoded_buf:
g_free(XBZRLE.encoded_buf);
@ -2769,16 +2778,16 @@ free_zero_page:
XBZRLE.zero_target_page = NULL;
err_out:
XBZRLE_cache_unlock();
return -ENOMEM;
return false;
}
static int ram_state_init(RAMState **rsp)
static bool ram_state_init(RAMState **rsp, Error **errp)
{
*rsp = g_try_new0(RAMState, 1);
if (!*rsp) {
error_report("%s: Init ramstate fail", __func__);
return -1;
error_setg(errp, "%s: Init ramstate fail", __func__);
return false;
}
qemu_mutex_init(&(*rsp)->bitmap_mutex);
@ -2794,7 +2803,7 @@ static int ram_state_init(RAMState **rsp)
(*rsp)->migration_dirty_pages = (*rsp)->ram_bytes_total >> TARGET_PAGE_BITS;
ram_state_reset(*rsp);
return 0;
return true;
}
static void ram_list_init_bitmaps(void)
@ -2852,39 +2861,53 @@ static void migration_bitmap_clear_discarded_pages(RAMState *rs)
}
}
static void ram_init_bitmaps(RAMState *rs)
static bool ram_init_bitmaps(RAMState *rs, Error **errp)
{
bool ret = true;
qemu_mutex_lock_ramlist();
WITH_RCU_READ_LOCK_GUARD() {
ram_list_init_bitmaps();
/* We don't use dirty log with background snapshots */
if (!migrate_background_snapshot()) {
memory_global_dirty_log_start(GLOBAL_DIRTY_MIGRATION);
ret = memory_global_dirty_log_start(GLOBAL_DIRTY_MIGRATION, errp);
if (!ret) {
goto out_unlock;
}
migration_bitmap_sync_precopy(rs, false);
}
}
out_unlock:
qemu_mutex_unlock_ramlist();
if (!ret) {
ram_bitmaps_destroy();
return false;
}
/*
* After an eventual first bitmap sync, fixup the initial bitmap
* containing all 1s to exclude any discarded pages from migration.
*/
migration_bitmap_clear_discarded_pages(rs);
return true;
}
static int ram_init_all(RAMState **rsp)
static int ram_init_all(RAMState **rsp, Error **errp)
{
if (ram_state_init(rsp)) {
if (!ram_state_init(rsp, errp)) {
return -1;
}
if (xbzrle_init()) {
if (!xbzrle_init(errp)) {
ram_state_cleanup(rsp);
return -1;
}
ram_init_bitmaps(*rsp);
if (!ram_init_bitmaps(*rsp, errp)) {
return -1;
}
return 0;
}
@ -3066,20 +3089,22 @@ static bool mapped_ram_read_header(QEMUFile *file, MappedRamHeader *header,
*
* @f: QEMUFile where to send the data
* @opaque: RAMState pointer
* @errp: pointer to Error*, to store an error if it happens.
*/
static int ram_save_setup(QEMUFile *f, void *opaque)
static int ram_save_setup(QEMUFile *f, void *opaque, Error **errp)
{
RAMState **rsp = opaque;
RAMBlock *block;
int ret, max_hg_page_size;
if (compress_threads_save_setup()) {
error_setg(errp, "%s: failed to start compress threads", __func__);
return -1;
}
/* migration has already setup the bitmap, reuse it. */
if (!migration_in_colo_state()) {
if (ram_init_all(rsp) != 0) {
if (ram_init_all(rsp, errp) != 0) {
compress_threads_save_cleanup();
return -1;
}
@ -3116,12 +3141,14 @@ static int ram_save_setup(QEMUFile *f, void *opaque)
ret = rdma_registration_start(f, RAM_CONTROL_SETUP);
if (ret < 0) {
error_setg(errp, "%s: failed to start RDMA registration", __func__);
qemu_file_set_error(f, ret);
return ret;
}
ret = rdma_registration_stop(f, RAM_CONTROL_SETUP);
if (ret < 0) {
error_setg(errp, "%s: failed to stop RDMA registration", __func__);
qemu_file_set_error(f, ret);
return ret;
}
@ -3138,6 +3165,7 @@ static int ram_save_setup(QEMUFile *f, void *opaque)
ret = multifd_send_sync_main();
bql_lock();
if (ret < 0) {
error_setg(errp, "%s: multifd synchronization failed", __func__);
return ret;
}
@ -3147,7 +3175,11 @@ static int ram_save_setup(QEMUFile *f, void *opaque)
}
qemu_put_be64(f, RAM_SAVE_FLAG_EOS);
return qemu_fflush(f);
ret = qemu_fflush(f);
if (ret < 0) {
error_setg_errno(errp, -ret, "%s failed", __func__);
}
return ret;
}
static void ram_save_file_bmap(QEMUFile *f)
@ -3592,7 +3624,11 @@ void ram_handle_zero(void *host, uint64_t size)
static void colo_init_ram_state(void)
{
ram_state_init(&ram_state);
Error *local_err = NULL;
if (!ram_state_init(&ram_state, &local_err)) {
error_report_err(local_err);
}
}
/*
@ -3647,6 +3683,8 @@ int colo_init_ram_cache(void)
void colo_incoming_start_dirty_log(void)
{
RAMBlock *block = NULL;
Error *local_err = NULL;
/* For memory_global_dirty_log_start below. */
bql_lock();
qemu_mutex_lock_ramlist();
@ -3658,7 +3696,10 @@ void colo_incoming_start_dirty_log(void)
/* Discard this dirty bitmap record */
bitmap_zero(block->bmap, block->max_length >> TARGET_PAGE_BITS);
}
memory_global_dirty_log_start(GLOBAL_DIRTY_MIGRATION);
if (!memory_global_dirty_log_start(GLOBAL_DIRTY_MIGRATION,
&local_err)) {
error_report_err(local_err);
}
}
ram_state->migration_dirty_pages = 0;
qemu_mutex_unlock_ramlist();
@ -3694,8 +3735,9 @@ void colo_release_ram_cache(void)
*
* @f: QEMUFile where to receive the data
* @opaque: RAMState pointer
* @errp: pointer to Error*, to store an error if it happens.
*/
static int ram_load_setup(QEMUFile *f, void *opaque)
static int ram_load_setup(QEMUFile *f, void *opaque, Error **errp)
{
xbzrle_load_setup();
ramblock_recv_map_init();

1
migration/ram.h

@ -69,6 +69,7 @@ int ramblock_recv_bitmap_test(RAMBlock *rb, void *host_addr);
bool ramblock_recv_bitmap_test_byte_offset(RAMBlock *rb, uint64_t byte_offset);
void ramblock_recv_bitmap_set(RAMBlock *rb, void *host_addr);
void ramblock_recv_bitmap_set_range(RAMBlock *rb, void *host_addr, size_t nr);
void ramblock_recv_bitmap_set_offset(RAMBlock *rb, uint64_t byte_offset);
int64_t ramblock_recv_bitmap_send(QEMUFile *file,
const char *block_name);
bool ram_dirty_bitmap_reload(MigrationState *s, RAMBlock *rb, Error **errp);

57
migration/savevm.c

@ -1009,11 +1009,10 @@ static void save_section_footer(QEMUFile *f, SaveStateEntry *se)
}
}
static int vmstate_save(QEMUFile *f, SaveStateEntry *se, JSONWriter *vmdesc)
static int vmstate_save(QEMUFile *f, SaveStateEntry *se, JSONWriter *vmdesc,
Error **errp)
{
int ret;
Error *local_err = NULL;
MigrationState *s = migrate_get_current();
if ((!se->ops || !se->ops->save_state) && !se->vmsd) {
return 0;
@ -1035,10 +1034,9 @@ static int vmstate_save(QEMUFile *f, SaveStateEntry *se, JSONWriter *vmdesc)
if (!se->vmsd) {
vmstate_save_old_style(f, se, vmdesc);
} else {
ret = vmstate_save_state_with_err(f, se->vmsd, se->opaque, vmdesc, &local_err);
ret = vmstate_save_state_with_err(f, se->vmsd, se->opaque, vmdesc,
errp);
if (ret) {
migrate_set_error(s, local_err);
error_report_err(local_err);
return ret;
}
}
@ -1312,11 +1310,11 @@ int qemu_savevm_state_prepare(Error **errp)
return 0;
}
void qemu_savevm_state_setup(QEMUFile *f)
int qemu_savevm_state_setup(QEMUFile *f, Error **errp)
{
ERRP_GUARD();
MigrationState *ms = migrate_get_current();
SaveStateEntry *se;
Error *local_err = NULL;
int ret = 0;
json_writer_int64(ms->vmdesc, "page_size", qemu_target_page_size());
@ -1325,8 +1323,9 @@ void qemu_savevm_state_setup(QEMUFile *f)
trace_savevm_state_setup();
QTAILQ_FOREACH(se, &savevm_state.handlers, entry) {
if (se->vmsd && se->vmsd->early_setup) {
ret = vmstate_save(f, se, ms->vmdesc);
ret = vmstate_save(f, se, ms->vmdesc, errp);
if (ret) {
migrate_set_error(ms, *errp);
qemu_file_set_error(f, ret);
break;
}
@ -1343,7 +1342,7 @@ void qemu_savevm_state_setup(QEMUFile *f)
}
save_section_header(f, se, QEMU_VM_SECTION_START);
ret = se->ops->save_setup(f, se->opaque);
ret = se->ops->save_setup(f, se->opaque, errp);
save_section_footer(f, se);
if (ret < 0) {
qemu_file_set_error(f, ret);
@ -1352,12 +1351,11 @@ void qemu_savevm_state_setup(QEMUFile *f)
}
if (ret) {
return;
return ret;
}
if (precopy_notify(PRECOPY_NOTIFY_SETUP, &local_err)) {
error_report_err(local_err);
}
/* TODO: Should we check that errp is set in case of failure ? */
return precopy_notify(PRECOPY_NOTIFY_SETUP, errp);
}
int qemu_savevm_state_resume_prepare(MigrationState *s)
@ -1542,6 +1540,7 @@ int qemu_savevm_state_complete_precopy_non_iterable(QEMUFile *f,
JSONWriter *vmdesc = ms->vmdesc;
int vmdesc_len;
SaveStateEntry *se;
Error *local_err = NULL;
int ret;
QTAILQ_FOREACH(se, &savevm_state.handlers, entry) {
@ -1552,8 +1551,10 @@ int qemu_savevm_state_complete_precopy_non_iterable(QEMUFile *f,
start_ts_each = qemu_clock_get_us(QEMU_CLOCK_REALTIME);
ret = vmstate_save(f, se, vmdesc);
ret = vmstate_save(f, se, vmdesc, &local_err);
if (ret) {
migrate_set_error(ms, local_err);
error_report_err(local_err);
qemu_file_set_error(f, ret);
return ret;
}
@ -1568,7 +1569,6 @@ int qemu_savevm_state_complete_precopy_non_iterable(QEMUFile *f,
* bdrv_activate_all() on the other end won't fail. */
ret = bdrv_inactivate_all();
if (ret) {
Error *local_err = NULL;
error_setg(&local_err, "%s: bdrv_inactivate_all() failed (%d)",
__func__, ret);
migrate_set_error(ms, local_err);
@ -1723,7 +1723,10 @@ static int qemu_savevm_state(QEMUFile *f, Error **errp)
ms->to_dst_file = f;
qemu_savevm_state_header(f);
qemu_savevm_state_setup(f);
ret = qemu_savevm_state_setup(f, errp);
if (ret) {
goto cleanup;
}
while (qemu_file_get_error(f) == 0) {
if (qemu_savevm_state_iterate(f, false) > 0) {
@ -1736,10 +1739,11 @@ static int qemu_savevm_state(QEMUFile *f, Error **errp)
qemu_savevm_state_complete_precopy(f, false, false);
ret = qemu_file_get_error(f);
}
qemu_savevm_state_cleanup();
if (ret != 0) {
error_setg_errno(errp, -ret, "Error while writing VM state");
}
cleanup:
qemu_savevm_state_cleanup();
if (ret != 0) {
status = MIGRATION_STATUS_FAILED;
@ -1764,6 +1768,8 @@ void qemu_savevm_live_state(QEMUFile *f)
int qemu_save_device_state(QEMUFile *f)
{
MigrationState *ms = migrate_get_current();
Error *local_err = NULL;
SaveStateEntry *se;
if (!migration_in_colo_state()) {
@ -1778,8 +1784,10 @@ int qemu_save_device_state(QEMUFile *f)
if (se->is_ram) {
continue;
}
ret = vmstate_save(f, se, NULL);
ret = vmstate_save(f, se, NULL, &local_err);
if (ret) {
migrate_set_error(ms, local_err);
error_report_err(local_err);
return ret;
}
}
@ -2760,8 +2768,9 @@ static void qemu_loadvm_state_switchover_ack_needed(MigrationIncomingState *mis)
trace_loadvm_state_switchover_ack_needed(mis->switchover_ack_pending_num);
}
static int qemu_loadvm_state_setup(QEMUFile *f)
static int qemu_loadvm_state_setup(QEMUFile *f, Error **errp)
{
ERRP_GUARD();
SaveStateEntry *se;
int ret;
@ -2776,10 +2785,11 @@ static int qemu_loadvm_state_setup(QEMUFile *f)
}
}
ret = se->ops->load_setup(f, se->opaque);
ret = se->ops->load_setup(f, se->opaque, errp);
if (ret < 0) {
error_prepend(errp, "Load state of device %s failed: ",
se->idstr);
qemu_file_set_error(f, ret);
error_report("Load state of device %s failed", se->idstr);
return ret;
}
}
@ -2960,7 +2970,8 @@ int qemu_loadvm_state(QEMUFile *f)
return ret;
}
if (qemu_loadvm_state_setup(f) != 0) {
if (qemu_loadvm_state_setup(f, &local_err) != 0) {
error_report_err(local_err);
return -EINVAL;
}

2
migration/savevm.h

@ -32,7 +32,7 @@
bool qemu_savevm_state_blocked(Error **errp);
void qemu_savevm_non_migratable_list(strList **reasons);
int qemu_savevm_state_prepare(Error **errp);
void qemu_savevm_state_setup(QEMUFile *f);
int qemu_savevm_state_setup(QEMUFile *f, Error **errp);
bool qemu_savevm_state_guest_unplug_pending(void);
int qemu_savevm_state_resume_prepare(MigrationState *s);
void qemu_savevm_state_header(QEMUFile *f);

44
system/memory.c

@ -2919,7 +2919,30 @@ static unsigned int postponed_stop_flags;
static VMChangeStateEntry *vmstate_change;
static void memory_global_dirty_log_stop_postponed_run(void);
void memory_global_dirty_log_start(unsigned int flags)
static bool memory_global_dirty_log_do_start(Error **errp)
{
MemoryListener *listener;
QTAILQ_FOREACH(listener, &memory_listeners, link) {
if (listener->log_global_start) {
if (!listener->log_global_start(listener, errp)) {
goto err;
}
}
}
return true;
err:
while ((listener = QTAILQ_PREV(listener, link)) != NULL) {
if (listener->log_global_stop) {
listener->log_global_stop(listener);
}
}
return false;
}
bool memory_global_dirty_log_start(unsigned int flags, Error **errp)
{
unsigned int old_flags;
@ -2933,7 +2956,7 @@ void memory_global_dirty_log_start(unsigned int flags)
flags &= ~global_dirty_tracking;
if (!flags) {
return;
return true;
}
old_flags = global_dirty_tracking;
@ -2941,11 +2964,17 @@ void memory_global_dirty_log_start(unsigned int flags)
trace_global_dirty_changed(global_dirty_tracking);
if (!old_flags) {
MEMORY_LISTENER_CALL_GLOBAL(log_global_start, Forward);
if (!memory_global_dirty_log_do_start(errp)) {
global_dirty_tracking &= ~flags;
trace_global_dirty_changed(global_dirty_tracking);
return false;
}
memory_region_transaction_begin();
memory_region_update_pending = true;
memory_region_transaction_commit();
}
return true;
}
static void memory_global_dirty_log_do_stop(unsigned int flags)
@ -3019,8 +3048,15 @@ static void listener_add_address_space(MemoryListener *listener,
listener->begin(listener);
}
if (global_dirty_tracking) {
/*
* Currently only VFIO can fail log_global_start(), and it's not
* yet allowed to hotplug any PCI device during migration. So this
* should never fail when invoked, guard it with error_abort. If
* it can start to fail in the future, we need to be able to fail
* the whole listener_add_address_space() and its callers.
*/
if (listener->log_global_start) {
listener->log_global_start(listener);
listener->log_global_start(listener, &error_abort);
}
}

158
tests/qtest/migration-helpers.c

@ -13,6 +13,11 @@
#include "qemu/osdep.h"
#include "qemu/ctype.h"
#include "qapi/qmp/qjson.h"
#include "qapi/qapi-visit-sockets.h"
#include "qapi/qobject-input-visitor.h"
#include "qapi/error.h"
#include "qapi/qmp/qlist.h"
#include "qemu/cutils.h"
#include "migration-helpers.h"
@ -24,6 +29,127 @@
*/
#define MIGRATION_STATUS_WAIT_TIMEOUT 120
static char *SocketAddress_to_str(SocketAddress *addr)
{
switch (addr->type) {
case SOCKET_ADDRESS_TYPE_INET:
return g_strdup_printf("tcp:%s:%s",
addr->u.inet.host,
addr->u.inet.port);
case SOCKET_ADDRESS_TYPE_UNIX:
return g_strdup_printf("unix:%s",
addr->u.q_unix.path);
case SOCKET_ADDRESS_TYPE_FD:
return g_strdup_printf("fd:%s", addr->u.fd.str);
case SOCKET_ADDRESS_TYPE_VSOCK:
return g_strdup_printf("vsock:%s:%s",
addr->u.vsock.cid,
addr->u.vsock.port);
default:
return g_strdup("unknown address type");
}
}
static QDict *SocketAddress_to_qdict(SocketAddress *addr)
{
QDict *dict = qdict_new();
switch (addr->type) {
case SOCKET_ADDRESS_TYPE_INET:
qdict_put_str(dict, "type", "inet");
qdict_put_str(dict, "host", addr->u.inet.host);
qdict_put_str(dict, "port", addr->u.inet.port);
break;
case SOCKET_ADDRESS_TYPE_UNIX:
qdict_put_str(dict, "type", "unix");
qdict_put_str(dict, "path", addr->u.q_unix.path);
break;
case SOCKET_ADDRESS_TYPE_FD:
qdict_put_str(dict, "type", "fd");
qdict_put_str(dict, "str", addr->u.fd.str);
break;
case SOCKET_ADDRESS_TYPE_VSOCK:
qdict_put_str(dict, "type", "vsock");
qdict_put_str(dict, "cid", addr->u.vsock.cid);
qdict_put_str(dict, "port", addr->u.vsock.port);
break;
default:
g_assert_not_reached();
break;
}
return dict;
}
static SocketAddress *migrate_get_socket_address(QTestState *who)
{
QDict *rsp;
SocketAddressList *addrs;
SocketAddress *addr;
Visitor *iv = NULL;
QObject *object;
rsp = migrate_query(who);
object = qdict_get(rsp, "socket-address");
iv = qobject_input_visitor_new(object);
visit_type_SocketAddressList(iv, NULL, &addrs, &error_abort);
addr = addrs->value;
visit_free(iv);
qobject_unref(rsp);
return addr;
}
static char *
migrate_get_connect_uri(QTestState *who)
{
SocketAddress *addrs;
char *connect_uri;
addrs = migrate_get_socket_address(who);
connect_uri = SocketAddress_to_str(addrs);
qapi_free_SocketAddress(addrs);
return connect_uri;
}
static QDict *
migrate_get_connect_qdict(QTestState *who)
{
SocketAddress *addrs;
QDict *connect_qdict;
addrs = migrate_get_socket_address(who);
connect_qdict = SocketAddress_to_qdict(addrs);
qapi_free_SocketAddress(addrs);
return connect_qdict;
}
static void migrate_set_ports(QTestState *to, QList *channel_list)
{
QDict *addr;
QListEntry *entry;
const char *addr_port = NULL;
addr = migrate_get_connect_qdict(to);
QLIST_FOREACH_ENTRY(channel_list, entry) {
QDict *channel = qobject_to(QDict, qlist_entry_obj(entry));
QDict *addrdict = qdict_get_qdict(channel, "addr");
if (qdict_haskey(addrdict, "port") &&
qdict_haskey(addr, "port") &&
(strcmp(qdict_get_str(addrdict, "port"), "0") == 0)) {
addr_port = qdict_get_str(addr, "port");
qdict_put_str(addrdict, "port", g_strdup(addr_port));
}
}
qobject_unref(addr);
}
bool migrate_watch_for_events(QTestState *who, const char *name,
QDict *event, void *opaque)
{
@ -43,7 +169,8 @@ bool migrate_watch_for_events(QTestState *who, const char *name,
return false;
}
void migrate_qmp_fail(QTestState *who, const char *uri, const char *fmt, ...)
void migrate_qmp_fail(QTestState *who, const char *uri,
const char *channels, const char *fmt, ...)
{
va_list ap;
QDict *args, *err;
@ -53,7 +180,15 @@ void migrate_qmp_fail(QTestState *who, const char *uri, const char *fmt, ...)
va_end(ap);
g_assert(!qdict_haskey(args, "uri"));
qdict_put_str(args, "uri", uri);
if (uri) {
qdict_put_str(args, "uri", uri);
}
g_assert(!qdict_haskey(args, "channels"));
if (channels) {
QObject *channels_obj = qobject_from_json(channels, &error_abort);
qdict_put_obj(args, "channels", channels_obj);
}
err = qtest_qmp_assert_failure_ref(
who, "{ 'execute': 'migrate', 'arguments': %p}", args);
@ -68,17 +203,32 @@ void migrate_qmp_fail(QTestState *who, const char *uri, const char *fmt, ...)
* Arguments are built from @fmt... (formatted like
* qobject_from_jsonf_nofail()) with "uri": @uri spliced in.
*/
void migrate_qmp(QTestState *who, const char *uri, const char *fmt, ...)
void migrate_qmp(QTestState *who, QTestState *to, const char *uri,
const char *channels, const char *fmt, ...)
{
va_list ap;
QDict *args;
g_autofree char *connect_uri = NULL;
va_start(ap, fmt);
args = qdict_from_vjsonf_nofail(fmt, ap);
va_end(ap);
g_assert(!qdict_haskey(args, "uri"));
qdict_put_str(args, "uri", uri);
if (uri) {
qdict_put_str(args, "uri", uri);
} else if (!channels) {
connect_uri = migrate_get_connect_uri(to);
qdict_put_str(args, "uri", connect_uri);
}
g_assert(!qdict_haskey(args, "channels"));
if (channels) {
QObject *channels_obj = qobject_from_json(channels, &error_abort);
QList *channel_list = qobject_to(QList, channels_obj);
migrate_set_ports(to, channel_list);
qdict_put_obj(args, "channels", channels_obj);
}
qtest_qmp_assert_success(who,
"{ 'execute': 'migrate', 'arguments': %p}", args);

10
tests/qtest/migration-helpers.h

@ -25,15 +25,17 @@ typedef struct QTestMigrationState {
bool migrate_watch_for_events(QTestState *who, const char *name,
QDict *event, void *opaque);
G_GNUC_PRINTF(3, 4)
void migrate_qmp(QTestState *who, const char *uri, const char *fmt, ...);
G_GNUC_PRINTF(5, 6)
void migrate_qmp(QTestState *who, QTestState *to, const char *uri,
const char *channels, const char *fmt, ...);
G_GNUC_PRINTF(3, 4)
void migrate_incoming_qmp(QTestState *who, const char *uri,
const char *fmt, ...);
G_GNUC_PRINTF(3, 4)
void migrate_qmp_fail(QTestState *who, const char *uri, const char *fmt, ...);
G_GNUC_PRINTF(4, 5)
void migrate_qmp_fail(QTestState *who, const char *uri,
const char *channels, const char *fmt, ...);
void migrate_set_capability(QTestState *who, const char *capability,
bool value);

180
tests/qtest/migration-test.c

@ -13,16 +13,12 @@
#include "qemu/osdep.h"
#include "libqtest.h"
#include "qapi/error.h"
#include "qapi/qmp/qdict.h"
#include "qemu/module.h"
#include "qemu/option.h"
#include "qemu/range.h"
#include "qemu/sockets.h"
#include "chardev/char.h"
#include "qapi/qapi-visit-sockets.h"
#include "qapi/qobject-input-visitor.h"
#include "qapi/qobject-output-visitor.h"
#include "crypto/tlscredspsk.h"
#include "qapi/qmp/qlist.h"
@ -369,50 +365,6 @@ static void cleanup(const char *filename)
unlink(path);
}
static char *SocketAddress_to_str(SocketAddress *addr)
{
switch (addr->type) {
case SOCKET_ADDRESS_TYPE_INET:
return g_strdup_printf("tcp:%s:%s",
addr->u.inet.host,
addr->u.inet.port);
case SOCKET_ADDRESS_TYPE_UNIX:
return g_strdup_printf("unix:%s",
addr->u.q_unix.path);
case SOCKET_ADDRESS_TYPE_FD:
return g_strdup_printf("fd:%s", addr->u.fd.str);
case SOCKET_ADDRESS_TYPE_VSOCK:
return g_strdup_printf("tcp:%s:%s",
addr->u.vsock.cid,
addr->u.vsock.port);
default:
return g_strdup("unknown address type");
}
}
static char *migrate_get_socket_address(QTestState *who, const char *parameter)
{
QDict *rsp;
char *result;
SocketAddressList *addrs;
Visitor *iv = NULL;
QObject *object;
rsp = migrate_query(who);
object = qdict_get(rsp, parameter);
iv = qobject_input_visitor_new(object);
visit_type_SocketAddressList(iv, NULL, &addrs, &error_abort);
visit_free(iv);
/* we are only using a single address */
result = SocketAddress_to_str(addrs->value);
qapi_free_SocketAddressList(addrs);
qobject_unref(rsp);
return result;
}
static long long migrate_get_parameter_int(QTestState *who,
const char *parameter)
{
@ -703,6 +655,13 @@ typedef struct {
*/
const char *connect_uri;
/*
* Optional: JSON-formatted list of src QEMU URIs. If a port is
* defined as '0' in any QDict key a value of '0' will be
* automatically converted to the correct destination port.
*/
const char *connect_channels;
/* Optional: callback to run at start to set migration parameters */
TestMigrateStartHook start_hook;
/* Optional: callback to run at finish to cleanup */
@ -1349,8 +1308,7 @@ static int migrate_postcopy_prepare(QTestState **from_ptr,
wait_for_serial("src_serial");
wait_for_suspend(from, &src_state);
g_autofree char *uri = migrate_get_socket_address(to, "socket-address");
migrate_qmp(from, uri, "{}");
migrate_qmp(from, to, NULL, NULL, "{}");
migrate_wait_for_dirty_mem(from, to);
@ -1500,7 +1458,7 @@ static void postcopy_recover_fail(QTestState *from, QTestState *to)
g_assert_cmpint(ret, ==, 1);
migrate_recover(to, "fd:fd-mig");
migrate_qmp(from, "fd:fd-mig", "{'resume': true}");
migrate_qmp(from, to, "fd:fd-mig", NULL, "{'resume': true}");
/*
* Make sure both QEMU instances will go into RECOVER stage, then test
@ -1588,7 +1546,7 @@ static void test_postcopy_recovery_common(MigrateCommon *args)
* Try to rebuild the migration channel using the resume flag and
* the newly created channel
*/
migrate_qmp(from, uri, "{'resume': true}");
migrate_qmp(from, to, uri, NULL, "{'resume': true}");
/* Restore the postcopy bandwidth to unlimited */
migrate_set_parameter_int(from, "max-postcopy-bandwidth", 0);
@ -1669,7 +1627,7 @@ static void test_baddest(void)
if (test_migrate_start(&from, &to, "tcp:127.0.0.1:0", &args)) {
return;
}
migrate_qmp(from, "tcp:127.0.0.1:0", "{}");
migrate_qmp(from, to, "tcp:127.0.0.1:0", NULL, "{}");
wait_for_migration_fail(from, false);
test_migrate_end(from, to, false);
}
@ -1708,7 +1666,7 @@ static void test_analyze_script(void)
uri = g_strdup_printf("exec:cat > %s", file);
migrate_ensure_converge(from);
migrate_qmp(from, uri, "{}");
migrate_qmp(from, to, uri, NULL, "{}");
wait_for_migration_complete(from);
pid = fork();
@ -1733,7 +1691,6 @@ static void test_precopy_common(MigrateCommon *args)
{
QTestState *from, *to;
void *data_hook = NULL;
g_autofree char *connect_uri = NULL;
if (test_migrate_start(&from, &to, args->listen_uri, &args->start)) {
return;
@ -1766,18 +1723,12 @@ static void test_precopy_common(MigrateCommon *args)
}
}
if (!args->connect_uri) {
connect_uri = migrate_get_socket_address(to, "socket-address");
} else {
connect_uri = g_strdup(args->connect_uri);
}
if (args->result == MIG_TEST_QMP_ERROR) {
migrate_qmp_fail(from, connect_uri, "{}");
migrate_qmp_fail(from, args->connect_uri, args->connect_channels, "{}");
goto finish;
}
migrate_qmp(from, connect_uri, "{}");
migrate_qmp(from, to, args->connect_uri, args->connect_channels, "{}");
if (args->result != MIG_TEST_SUCCEED) {
bool allow_active = args->result == MIG_TEST_FAIL;
@ -1843,7 +1794,6 @@ static void test_file_common(MigrateCommon *args, bool stop_src)
{
QTestState *from, *to;
void *data_hook = NULL;
g_autofree char *connect_uri = g_strdup(args->connect_uri);
if (test_migrate_start(&from, &to, args->listen_uri, &args->start)) {
return;
@ -1869,18 +1819,18 @@ static void test_file_common(MigrateCommon *args, bool stop_src)
}
if (args->result == MIG_TEST_QMP_ERROR) {
migrate_qmp_fail(from, connect_uri, "{}");
migrate_qmp_fail(from, args->connect_uri, NULL, "{}");
goto finish;
}
migrate_qmp(from, connect_uri, "{}");
migrate_qmp(from, to, args->connect_uri, NULL, "{}");
wait_for_migration_complete(from);
/*
* We need to wait for the source to finish before starting the
* destination.
*/
migrate_incoming_qmp(to, connect_uri, "{}");
migrate_incoming_qmp(to, args->connect_uri, "{}");
wait_for_migration_complete(to);
if (stop_src) {
@ -2029,7 +1979,7 @@ static void test_ignore_shared(void)
/* Wait for the first serial output from the source */
wait_for_serial("src_serial");
migrate_qmp(from, uri, "{}");
migrate_qmp(from, to, uri, NULL, "{}");
migrate_wait_for_dirty_mem(from, to);
@ -2568,7 +2518,7 @@ static void do_test_validate_uuid(MigrateStart *args, bool should_fail)
/* Wait for the first serial output from the source */
wait_for_serial("src_serial");
migrate_qmp(from, uri, "{}");
migrate_qmp(from, to, uri, NULL, "{}");
if (should_fail) {
qtest_set_expected_status(to, EXIT_FAILURE);
@ -2621,6 +2571,55 @@ static void test_validate_uuid_dst_not_set(void)
do_test_validate_uuid(&args, false);
}
static void do_test_validate_uri_channel(MigrateCommon *args)
{
QTestState *from, *to;
if (test_migrate_start(&from, &to, args->listen_uri, &args->start)) {
return;
}
/* Wait for the first serial output from the source */
wait_for_serial("src_serial");
/*
* 'uri' and 'channels' validation is checked even before the migration
* starts.
*/
migrate_qmp_fail(from, args->connect_uri, args->connect_channels, "{}");
test_migrate_end(from, to, false);
}
static void test_validate_uri_channels_both_set(void)
{
MigrateCommon args = {
.start = {
.hide_stderr = true,
},
.listen_uri = "defer",
.connect_uri = "tcp:127.0.0.1:0",
.connect_channels = "[ { 'channel-type': 'main',"
" 'addr': { 'transport': 'socket',"
" 'type': 'inet',"
" 'host': '127.0.0.1',"
" 'port': '0' } } ]",
};
do_test_validate_uri_channel(&args);
}
static void test_validate_uri_channels_none_set(void)
{
MigrateCommon args = {
.start = {
.hide_stderr = true,
},
.listen_uri = "defer",
};
do_test_validate_uri_channel(&args);
}
/*
* The way auto_converge works, we need to do too many passes to
* run this test. Auto_converge logic is only run once every
@ -2671,7 +2670,7 @@ static void test_migrate_auto_converge(void)
/* Wait for the first serial output from the source */
wait_for_serial("src_serial");
migrate_qmp(from, uri, "{}");
migrate_qmp(from, to, uri, NULL, "{}");
/* Wait for throttling begins */
percentage = 0;
@ -2778,7 +2777,7 @@ test_migrate_precopy_tcp_multifd_zstd_start(QTestState *from,
}
#endif /* CONFIG_ZSTD */
static void test_multifd_tcp_none(void)
static void test_multifd_tcp_uri_none(void)
{
MigrateCommon args = {
.listen_uri = "defer",
@ -2823,6 +2822,21 @@ static void test_multifd_tcp_no_zero_page(void)
test_precopy_common(&args);
}
static void test_multifd_tcp_channels_none(void)
{
MigrateCommon args = {
.listen_uri = "defer",
.start_hook = test_migrate_precopy_tcp_multifd_start,
.live = true,
.connect_channels = "[ { 'channel-type': 'main',"
" 'addr': { 'transport': 'socket',"
" 'type': 'inet',"
" 'host': '127.0.0.1',"
" 'port': '0' } } ]",
};
test_precopy_common(&args);
}
static void test_multifd_tcp_zlib(void)
{
MigrateCommon args = {
@ -3017,7 +3031,6 @@ static void test_multifd_tcp_cancel(void)
.hide_stderr = true,
};
QTestState *from, *to, *to2;
g_autofree char *uri = NULL;
if (test_migrate_start(&from, &to, "defer", &args)) {
return;
@ -3038,9 +3051,7 @@ static void test_multifd_tcp_cancel(void)
/* Wait for the first serial output from the source */
wait_for_serial("src_serial");
uri = migrate_get_socket_address(to, "socket-address");
migrate_qmp(from, uri, "{}");
migrate_qmp(from, to, NULL, NULL, "{}");
migrate_wait_for_dirty_mem(from, to);
@ -3065,14 +3076,11 @@ static void test_multifd_tcp_cancel(void)
/* Start incoming migration from the 1st socket */
migrate_incoming_qmp(to2, "tcp:127.0.0.1:0", "{}");
g_free(uri);
uri = migrate_get_socket_address(to2, "socket-address");
wait_for_migration_status(from, "cancelled", NULL);
migrate_ensure_non_converge(from);
migrate_qmp(from, uri, "{}");
migrate_qmp(from, to2, NULL, NULL, "{}");
migrate_wait_for_dirty_mem(from, to2);
@ -3405,7 +3413,7 @@ static void test_migrate_dirty_limit(void)
migrate_dirty_limit_wait_showup(from, dirtylimit_period, dirtylimit_value);
/* Start migrate */
migrate_qmp(from, uri, "{}");
migrate_qmp(from, to, args.connect_uri, NULL, "{}");
/* Wait for dirty limit throttle begin */
throttle_us_per_full = 0;
@ -3446,7 +3454,7 @@ static void test_migrate_dirty_limit(void)
}
/* Start migrate */
migrate_qmp(from, uri, "{}");
migrate_qmp(from, to, args.connect_uri, NULL, "{}");
/* Wait for dirty limit throttle begin */
throttle_us_per_full = 0;
@ -3720,6 +3728,10 @@ int main(int argc, char **argv)
test_validate_uuid_src_not_set);
migration_test_add("/migration/validate_uuid_dst_not_set",
test_validate_uuid_dst_not_set);
migration_test_add("/migration/validate_uri/channels/both_set",
test_validate_uri_channels_both_set);
migration_test_add("/migration/validate_uri/channels/none_set",
test_validate_uri_channels_none_set);
/*
* See explanation why this test is slow on function definition
*/
@ -3732,8 +3744,10 @@ int main(int argc, char **argv)
test_migrate_dirty_limit);
}
}
migration_test_add("/migration/multifd/tcp/plain/none",
test_multifd_tcp_none);
migration_test_add("/migration/multifd/tcp/uri/plain/none",
test_multifd_tcp_uri_none);
migration_test_add("/migration/multifd/tcp/channels/plain/none",
test_multifd_tcp_channels_none);
migration_test_add("/migration/multifd/tcp/plain/zero-page/legacy",
test_multifd_tcp_zero_page_legacy);
migration_test_add("/migration/multifd/tcp/plain/zero-page/none",