void migrate_start_colo_process(MigrationState *s)
{
qemu_mutex_unlock_iothread();
qemu_sem_init(&s->colo_checkpoint_sem, 0);
s->colo_delay_timer = timer_new_ms(QEMU_CLOCK_HOST,
colo_checkpoint_notify, s);
qemu_sem_init(&s->colo_exit_sem, 0);
migrate_set_state(&s->state, MIGRATION_STATUS_ACTIVE,
MIGRATION_STATUS_COLO);
colo_process_checkpoint(s);
qemu_mutex_lock_iothread();
}
int postcopy_ram_enable_notify(MigrationIncomingState *mis)
{
/* Open the fd for the kernel to give us userfaults */
mis->userfault_fd = syscall(__NR_userfaultfd, O_CLOEXEC | O_NONBLOCK);
if (mis->userfault_fd == -1) {
error_report("%s: Failed to open userfault fd: %s", __func__,
strerror(errno));
return -1;
}
/*
* Although the host check already tested the API, we need to
* do the check again as an ABI handshake on the new fd.
*/
if (!ufd_check_and_apply(mis->userfault_fd, mis)) {
return -1;
}
/* Now an eventfd we use to tell the fault-thread to quit */
mis->userfault_event_fd = eventfd(0, EFD_CLOEXEC);
if (mis->userfault_event_fd == -1) {
error_report("%s: Opening userfault_event_fd: %s", __func__,
strerror(errno));
close(mis->userfault_fd);
return -1;
}
qemu_sem_init(&mis->fault_thread_sem, 0);
qemu_thread_create(&mis->fault_thread, "postcopy/fault",
postcopy_ram_fault_thread, mis, QEMU_THREAD_JOINABLE);
qemu_sem_wait(&mis->fault_thread_sem);
qemu_sem_destroy(&mis->fault_thread_sem);
mis->have_fault_thread = true;
/* Mark so that we get notified of accesses to unwritten areas */
if (qemu_ram_foreach_block(ram_block_enable_notify, mis)) {
return -1;
}
/*
* Ballooning can mark pages as absent while we're postcopying
* that would cause false userfaults.
*/
qemu_balloon_inhibit(true);
trace_postcopy_ram_enable_notify();
return 0;
}
void *colo_process_incoming_thread(void *opaque)
{
MigrationIncomingState *mis = opaque;
QEMUFile *fb = NULL;
QIOChannelBuffer *bioc = NULL; /* Cache incoming device state */
uint64_t total_size;
uint64_t value;
Error *local_err = NULL;
qemu_sem_init(&mis->colo_incoming_sem, 0);
migrate_set_state(&mis->state, MIGRATION_STATUS_ACTIVE,
MIGRATION_STATUS_COLO);
failover_init_state();
mis->to_src_file = qemu_file_get_return_path(mis->from_src_file);
if (!mis->to_src_file) {
error_report("COLO incoming thread: Open QEMUFile to_src_file failed");
goto out;
}
/*
* Note: the communication between Primary side and Secondary side
* should be sequential, we set the fd to unblocked in migration incoming
* coroutine, and here we are in the COLO incoming thread, so it is ok to
* set the fd back to blocked.
*/
qemu_file_set_blocking(mis->from_src_file, true);
bioc = qio_channel_buffer_new(COLO_BUFFER_BASE_SIZE);
fb = qemu_fopen_channel_input(QIO_CHANNEL(bioc));
object_unref(OBJECT(bioc));
colo_send_message(mis->to_src_file, COLO_MESSAGE_CHECKPOINT_READY,
&local_err);
if (local_err) {
goto out;
}
while (mis->state == MIGRATION_STATUS_COLO) {
int request = 0;
colo_wait_handle_message(mis->from_src_file, &request, &local_err);
if (local_err) {
goto out;
}
assert(request);
if (failover_get_state() != FAILOVER_STATUS_NONE) {
error_report("failover request");
goto out;
}
/* FIXME: This is unnecessary for periodic checkpoint mode */
colo_send_message(mis->to_src_file, COLO_MESSAGE_CHECKPOINT_REPLY,
&local_err);
if (local_err) {
goto out;
}
colo_receive_check_message(mis->from_src_file,
COLO_MESSAGE_VMSTATE_SEND, &local_err);
if (local_err) {
goto out;
}
value = colo_receive_message_value(mis->from_src_file,
COLO_MESSAGE_VMSTATE_SIZE, &local_err);
if (local_err) {
goto out;
}
/*
* Read VM device state data into channel buffer,
* It's better to re-use the memory allocated.
* Here we need to handle the channel buffer directly.
*/
if (value > bioc->capacity) {
bioc->capacity = value;
bioc->data = g_realloc(bioc->data, bioc->capacity);
}
total_size = qemu_get_buffer(mis->from_src_file, bioc->data, value);
if (total_size != value) {
error_report("Got %" PRIu64 " VMState data, less than expected"
" %" PRIu64, total_size, value);
goto out;
}
bioc->usage = total_size;
qio_channel_io_seek(QIO_CHANNEL(bioc), 0, 0, NULL);
colo_send_message(mis->to_src_file, COLO_MESSAGE_VMSTATE_RECEIVED,
&local_err);
if (local_err) {
goto out;
}
qemu_mutex_lock_iothread();
qemu_system_reset(VMRESET_SILENT);
vmstate_loading = true;
if (qemu_loadvm_state(fb) < 0) {
error_report("COLO: loadvm failed");
qemu_mutex_unlock_iothread();
goto out;
}
vmstate_loading = false;
qemu_mutex_unlock_iothread();
if (failover_get_state() == FAILOVER_STATUS_RELAUNCH) {
failover_set_state(FAILOVER_STATUS_RELAUNCH,
FAILOVER_STATUS_NONE);
failover_request_active(NULL);
goto out;
}
colo_send_message(mis->to_src_file, COLO_MESSAGE_VMSTATE_LOADED,
&local_err);
if (local_err) {
goto out;
}
}
out:
vmstate_loading = false;
/* Throw the unreported error message after exited from loop */
if (local_err) {
error_report_err(local_err);
}
if (fb) {
qemu_fclose(fb);
}
/* Hope this not to be too long to loop here */
qemu_sem_wait(&mis->colo_incoming_sem);
qemu_sem_destroy(&mis->colo_incoming_sem);
/* Must be called after failover BH is completed */
if (mis->to_src_file) {
qemu_fclose(mis->to_src_file);
}
migration_incoming_exit_colo();
return NULL;
}
void *colo_process_incoming_thread(void *opaque)
{
MigrationIncomingState *mis = opaque;
QEMUFile *fb = NULL;
QIOChannelBuffer *bioc = NULL; /* Cache incoming device state */
uint64_t total_size;
uint64_t value;
Error *local_err = NULL;
int ret;
rcu_register_thread();
qemu_sem_init(&mis->colo_incoming_sem, 0);
migrate_set_state(&mis->state, MIGRATION_STATUS_ACTIVE,
MIGRATION_STATUS_COLO);
failover_init_state();
mis->to_src_file = qemu_file_get_return_path(mis->from_src_file);
if (!mis->to_src_file) {
error_report("COLO incoming thread: Open QEMUFile to_src_file failed");
goto out;
}
/*
* Note: the communication between Primary side and Secondary side
* should be sequential, we set the fd to unblocked in migration incoming
* coroutine, and here we are in the COLO incoming thread, so it is ok to
* set the fd back to blocked.
*/
qemu_file_set_blocking(mis->from_src_file, true);
bioc = qio_channel_buffer_new(COLO_BUFFER_BASE_SIZE);
fb = qemu_fopen_channel_input(QIO_CHANNEL(bioc));
object_unref(OBJECT(bioc));
qemu_mutex_lock_iothread();
#ifdef CONFIG_REPLICATION
replication_start_all(REPLICATION_MODE_SECONDARY, &local_err);
if (local_err) {
qemu_mutex_unlock_iothread();
goto out;
}
#else
abort();
#endif
vm_start();
trace_colo_vm_state_change("stop", "run");
qemu_mutex_unlock_iothread();
colo_send_message(mis->to_src_file, COLO_MESSAGE_CHECKPOINT_READY,
&local_err);
if (local_err) {
goto out;
}
while (mis->state == MIGRATION_STATUS_COLO) {
int request = 0;
colo_wait_handle_message(mis->from_src_file, &request, &local_err);
if (local_err) {
goto out;
}
assert(request);
if (failover_get_state() != FAILOVER_STATUS_NONE) {
error_report("failover request");
goto out;
}
qemu_mutex_lock_iothread();
vm_stop_force_state(RUN_STATE_COLO);
trace_colo_vm_state_change("run", "stop");
qemu_mutex_unlock_iothread();
/* FIXME: This is unnecessary for periodic checkpoint mode */
colo_send_message(mis->to_src_file, COLO_MESSAGE_CHECKPOINT_REPLY,
&local_err);
if (local_err) {
goto out;
}
colo_receive_check_message(mis->from_src_file,
COLO_MESSAGE_VMSTATE_SEND, &local_err);
if (local_err) {
goto out;
}
qemu_mutex_lock_iothread();
cpu_synchronize_all_pre_loadvm();
ret = qemu_loadvm_state_main(mis->from_src_file, mis);
qemu_mutex_unlock_iothread();
if (ret < 0) {
error_report("Load VM's live state (ram) error");
goto out;
}
value = colo_receive_message_value(mis->from_src_file,
COLO_MESSAGE_VMSTATE_SIZE, &local_err);
if (local_err) {
goto out;
}
/*
* Read VM device state data into channel buffer,
* It's better to re-use the memory allocated.
* Here we need to handle the channel buffer directly.
*/
if (value > bioc->capacity) {
bioc->capacity = value;
bioc->data = g_realloc(bioc->data, bioc->capacity);
}
total_size = qemu_get_buffer(mis->from_src_file, bioc->data, value);
if (total_size != value) {
error_report("Got %" PRIu64 " VMState data, less than expected"
" %" PRIu64, total_size, value);
goto out;
}
bioc->usage = total_size;
qio_channel_io_seek(QIO_CHANNEL(bioc), 0, 0, NULL);
colo_send_message(mis->to_src_file, COLO_MESSAGE_VMSTATE_RECEIVED,
&local_err);
if (local_err) {
goto out;
}
qemu_mutex_lock_iothread();
vmstate_loading = true;
ret = qemu_load_device_state(fb);
if (ret < 0) {
error_report("COLO: load device state failed");
qemu_mutex_unlock_iothread();
goto out;
}
#ifdef CONFIG_REPLICATION
replication_get_error_all(&local_err);
if (local_err) {
qemu_mutex_unlock_iothread();
goto out;
}
/* discard colo disk buffer */
replication_do_checkpoint_all(&local_err);
if (local_err) {
qemu_mutex_unlock_iothread();
goto out;
}
#else
abort();
#endif
/* Notify all filters of all NIC to do checkpoint */
colo_notify_filters_event(COLO_EVENT_CHECKPOINT, &local_err);
if (local_err) {
qemu_mutex_unlock_iothread();
goto out;
}
vmstate_loading = false;
vm_start();
trace_colo_vm_state_change("stop", "run");
qemu_mutex_unlock_iothread();
if (failover_get_state() == FAILOVER_STATUS_RELAUNCH) {
failover_set_state(FAILOVER_STATUS_RELAUNCH,
FAILOVER_STATUS_NONE);
failover_request_active(NULL);
goto out;
}
colo_send_message(mis->to_src_file, COLO_MESSAGE_VMSTATE_LOADED,
&local_err);
if (local_err) {
goto out;
}
}
out:
vmstate_loading = false;
/* Throw the unreported error message after exited from loop */
if (local_err) {
error_report_err(local_err);
}
switch (failover_get_state()) {
case FAILOVER_STATUS_NONE:
qapi_event_send_colo_exit(COLO_MODE_SECONDARY,
COLO_EXIT_REASON_ERROR);
break;
case FAILOVER_STATUS_REQUIRE:
qapi_event_send_colo_exit(COLO_MODE_SECONDARY,
COLO_EXIT_REASON_REQUEST);
break;
default:
abort();
}
if (fb) {
qemu_fclose(fb);
}
/* Hope this not to be too long to loop here */
qemu_sem_wait(&mis->colo_incoming_sem);
qemu_sem_destroy(&mis->colo_incoming_sem);
/* Must be called after failover BH is completed */
if (mis->to_src_file) {
qemu_fclose(mis->to_src_file);
}
migration_incoming_disable_colo();
rcu_unregister_thread();
return NULL;
}