fridtjof/qemu-cr16
1
0
Fork 0
Code Issues Pull requests Projects Releases Packages Wiki Activity Actions

vfio/migration: Add x-migration-load-config-after-iter VFIO property

Browse source 
This property allows configuring whether to start the config load only
after all iterables were loaded, during non-iterables loading phase.
Such interlocking is required for ARM64 due to this platform VFIO
dependency on interrupt controller being loaded first.

The property defaults to AUTO, which means ON for ARM, OFF for other
platforms.

Reviewed-by: Fabiano Rosas <farosas@suse.de>
Reviewed-by: Avihai Horon <avihaih@nvidia.com>
Signed-off-by: Maciej S. Szmigiero <maciej.szmigiero@oracle.com>
Link: https://lore.kernel.org/qemu-devel/0e03c60dbc91f9a9ba2516929574df605b7dfcb4.1752589295.git.maciej.szmigiero@oracle.com
Signed-off-by: Cédric Le Goater <clg@redhat.com>
This commit is contained in:
Maciej S. Szmigiero 2025-07-15 16:37:36 +02:00 • committed by Cédric Le Goater
parent a59d06305f
commit 6380b0a02f
10 changed files with 129 additions and 1 deletions
Download patch file Download diff file Expand all files Collapse all files

6
docs/devel/migration/vfio.rst
View file

@ -247,3 +247,9 @@ The multifd VFIO device state transfer is controlled by
"x-migration-multifd-transfer" VFIO device property. This property defaults to
AUTO, which means that VFIO device state transfer via multifd channels is
attempted in configurations that otherwise support it.
Some host platforms (like ARM64) require that VFIO device config is loaded only
after all iterables were loaded, during non-iterables loading phase.
Such interlocking is controlled by "x-migration-load-config-after-iter" VFIO
device property, which in its default setting (AUTO) does so only on platforms
that actually require it.

1
hw/core/machine.c
View file

@ -39,6 +39,7 @@
GlobalProperty hw_compat_10_0[] = {
{ "scsi-hd", "dpofua", "off" },
{ "vfio-pci", "x-migration-load-config-after-iter", "off" },
};
const size_t hw_compat_10_0_len = G_N_ELEMENTS(hw_compat_10_0);

17
hw/vfio/helpers.c
View file

@ -209,3 +209,20 @@ retry:
return info;
}
bool vfio_arch_wants_loading_config_after_iter(void)
{
/*
* Starting the config load only after all iterables were loaded (during
* non-iterables loading phase) is required for ARM64 due to this platform
* VFIO dependency on interrupt controller being loaded first.
*
* See commit d329f5032e17 ("vfio: Move the saving of the config space to
* the right place in VFIO migration").
*/
#if defined(TARGET_ARM)
return true;
#else
return false;
#endif
}

79
hw/vfio/migration-multifd.c
View file

@ -23,6 +23,7 @@
#include "migration-multifd.h"
#include "vfio-migration-internal.h"
#include "trace.h"
#include "vfio-helpers.h"
#define VFIO_DEVICE_STATE_CONFIG_STATE (1)
@ -35,6 +36,18 @@ typedef struct VFIODeviceStatePacket {
uint8_t data[0];
} QEMU_PACKED VFIODeviceStatePacket;
bool vfio_load_config_after_iter(VFIODevice *vbasedev)
{
if (vbasedev->migration_load_config_after_iter == ON_OFF_AUTO_ON) {
return true;
} else if (vbasedev->migration_load_config_after_iter == ON_OFF_AUTO_OFF) {
return false;
}
assert(vbasedev->migration_load_config_after_iter == ON_OFF_AUTO_AUTO);
return vfio_arch_wants_loading_config_after_iter();
}
/* type safety */
typedef struct VFIOStateBuffers {
GArray *array;
@ -50,6 +63,9 @@ typedef struct VFIOMultifd {
bool load_bufs_thread_running;
bool load_bufs_thread_want_exit;
bool load_bufs_iter_done;
QemuCond load_bufs_iter_done_cond;
VFIOStateBuffers load_bufs;
QemuCond load_bufs_buffer_ready_cond;
QemuCond load_bufs_thread_finished_cond;
@ -394,6 +410,22 @@ static bool vfio_load_bufs_thread(void *opaque, bool *should_quit, Error **errp)
multifd->load_buf_idx++;
}
if (vfio_load_config_after_iter(vbasedev)) {
while (!multifd->load_bufs_iter_done) {
qemu_cond_wait(&multifd->load_bufs_iter_done_cond,
&multifd->load_bufs_mutex);
/*
* Need to re-check cancellation immediately after wait in case
* cond was signalled by vfio_load_cleanup_load_bufs_thread().
*/
if (vfio_load_bufs_thread_want_exit(multifd, should_quit)) {
error_setg(errp, "operation cancelled");
goto thread_exit;
}
}
}
if (!vfio_load_bufs_thread_load_config(vbasedev, errp)) {
goto thread_exit;
}
@ -413,6 +445,48 @@ thread_exit:
return ret;
}
int vfio_load_state_config_load_ready(VFIODevice *vbasedev)
{
VFIOMigration *migration = vbasedev->migration;
VFIOMultifd *multifd = migration->multifd;
int ret = 0;
if (!vfio_multifd_transfer_enabled(vbasedev)) {
error_report("%s: got DEV_CONFIG_LOAD_READY outside multifd transfer",
vbasedev->name);
return -EINVAL;
}
if (!vfio_load_config_after_iter(vbasedev)) {
error_report("%s: got DEV_CONFIG_LOAD_READY but was disabled",
vbasedev->name);
return -EINVAL;
}
assert(multifd);
/* The lock order is load_bufs_mutex -> BQL so unlock BQL here first */
bql_unlock();
WITH_QEMU_LOCK_GUARD(&multifd->load_bufs_mutex) {
if (multifd->load_bufs_iter_done) {
/* Can't print error here as we're outside BQL */
ret = -EINVAL;
break;
}
multifd->load_bufs_iter_done = true;
qemu_cond_signal(&multifd->load_bufs_iter_done_cond);
}
bql_lock();
if (ret) {
error_report("%s: duplicate DEV_CONFIG_LOAD_READY",
vbasedev->name);
}
return ret;
}
static VFIOMultifd *vfio_multifd_new(void)
{
VFIOMultifd *multifd = g_new(VFIOMultifd, 1);
@ -425,6 +499,9 @@ static VFIOMultifd *vfio_multifd_new(void)
multifd->load_buf_idx_last = UINT32_MAX;
qemu_cond_init(&multifd->load_bufs_buffer_ready_cond);
multifd->load_bufs_iter_done = false;
qemu_cond_init(&multifd->load_bufs_iter_done_cond);
multifd->load_bufs_thread_running = false;
multifd->load_bufs_thread_want_exit = false;
qemu_cond_init(&multifd->load_bufs_thread_finished_cond);
@ -448,6 +525,7 @@ static void vfio_load_cleanup_load_bufs_thread(VFIOMultifd *multifd)
multifd->load_bufs_thread_want_exit = true;
qemu_cond_signal(&multifd->load_bufs_buffer_ready_cond);
qemu_cond_signal(&multifd->load_bufs_iter_done_cond);
qemu_cond_wait(&multifd->load_bufs_thread_finished_cond,
&multifd->load_bufs_mutex);
}
@ -460,6 +538,7 @@ static void vfio_multifd_free(VFIOMultifd *multifd)
vfio_load_cleanup_load_bufs_thread(multifd);
qemu_cond_destroy(&multifd->load_bufs_thread_finished_cond);
qemu_cond_destroy(&multifd->load_bufs_iter_done_cond);
vfio_state_buffers_destroy(&multifd->load_bufs);
qemu_cond_destroy(&multifd->load_bufs_buffer_ready_cond);
qemu_mutex_destroy(&multifd->load_bufs_mutex);

3
hw/vfio/migration-multifd.h
View file

@ -20,9 +20,12 @@ void vfio_multifd_cleanup(VFIODevice *vbasedev);
bool vfio_multifd_transfer_supported(void);
bool vfio_multifd_transfer_enabled(VFIODevice *vbasedev);
bool vfio_load_config_after_iter(VFIODevice *vbasedev);
bool vfio_multifd_load_state_buffer(void *opaque, char *data, size_t data_size,
Error **errp);
int vfio_load_state_config_load_ready(VFIODevice *vbasedev);
void vfio_multifd_emit_dummy_eos(VFIODevice *vbasedev, QEMUFile *f);
bool

10
hw/vfio/migration.c
View file

@ -675,7 +675,11 @@ static void vfio_save_state(QEMUFile *f, void *opaque)
int ret;
if (vfio_multifd_transfer_enabled(vbasedev)) {
vfio_multifd_emit_dummy_eos(vbasedev, f);
if (vfio_load_config_after_iter(vbasedev)) {
qemu_put_be64(f, VFIO_MIG_FLAG_DEV_CONFIG_LOAD_READY);
} else {
vfio_multifd_emit_dummy_eos(vbasedev, f);
}
return;
}
@ -784,6 +788,10 @@ static int vfio_load_state(QEMUFile *f, void *opaque, int version_id)
return ret;
}
case VFIO_MIG_FLAG_DEV_CONFIG_LOAD_READY:
{
return vfio_load_state_config_load_ready(vbasedev);
}
default:
error_report("%s: Unknown tag 0x%"PRIx64, vbasedev->name, data);
return -EINVAL;

10
hw/vfio/pci.c
View file

@ -3642,6 +3642,9 @@ static const Property vfio_pci_dev_properties[] = {
vbasedev.migration_multifd_transfer,
vfio_pci_migration_multifd_transfer_prop, OnOffAuto,
.set_default = true, .defval.i = ON_OFF_AUTO_AUTO),
DEFINE_PROP_ON_OFF_AUTO("x-migration-load-config-after-iter", VFIOPCIDevice,
vbasedev.migration_load_config_after_iter,
ON_OFF_AUTO_AUTO),
DEFINE_PROP_BOOL("migration-events", VFIOPCIDevice,
vbasedev.migration_events, false),
DEFINE_PROP_BOOL("x-no-mmap", VFIOPCIDevice, vbasedev.no_mmap, false),
@ -3818,6 +3821,13 @@ static void vfio_pci_dev_class_init(ObjectClass *klass, const void *data)
"x-migration-multifd-transfer",
"Transfer this device state via "
"multifd channels when live migrating it");
object_class_property_set_description(klass, /* 10.1 */
"x-migration-load-config-after-iter",
"Start the config load only after "
"all iterables were loaded (during "
"non-iterables loading phase) when "
"doing live migration of device state "
"via multifd channels");
}
static const TypeInfo vfio_pci_dev_info = {

2
hw/vfio/vfio-helpers.h
View file

@ -32,4 +32,6 @@ struct vfio_device_info *vfio_get_device_info(int fd);
int vfio_kvm_device_add_fd(int fd, Error **errp);
int vfio_kvm_device_del_fd(int fd, Error **errp);
bool vfio_arch_wants_loading_config_after_iter(void);
#endif /* HW_VFIO_VFIO_HELPERS_H */

1
hw/vfio/vfio-migration-internal.h
View file

@ -32,6 +32,7 @@
#define VFIO_MIG_FLAG_DEV_SETUP_STATE (0xffffffffef100003ULL)
#define VFIO_MIG_FLAG_DEV_DATA_STATE (0xffffffffef100004ULL)
#define VFIO_MIG_FLAG_DEV_INIT_DATA_SENT (0xffffffffef100005ULL)
#define VFIO_MIG_FLAG_DEV_CONFIG_LOAD_READY (0xffffffffef100006ULL)
typedef struct VFIODevice VFIODevice;
typedef struct VFIOMultifd VFIOMultifd;

1
include/hw/vfio/vfio-device.h
View file

@ -67,6 +67,7 @@ typedef struct VFIODevice {
bool ram_block_discard_allowed;
OnOffAuto enable_migration;
OnOffAuto migration_multifd_transfer;
OnOffAuto migration_load_config_after_iter;
bool migration_events;
bool use_region_fds;
VFIODeviceOps *ops;