void migrate_fd_put_ready(void *opaque)
{
FdMigrationState *s = opaque;
if (s->state != MIG_STATE_ACTIVE) {
DPRINTF("put_ready returning because of non-active state\n");
return;
}
DPRINTF("iterate\n");
if (qemu_savevm_state_iterate(s->mon, s->file) == 1) {
int state;
int old_vm_running = vm_running;
DPRINTF("done iterating\n");
vm_stop(VMSTOP_MIGRATE);
if ((qemu_savevm_state_complete(s->mon, s->file)) < 0) {
if (old_vm_running) {
vm_start();
}
state = MIG_STATE_ERROR;
} else {
state = MIG_STATE_COMPLETED;
}
if (migrate_fd_cleanup(s) < 0) {
if (old_vm_running) {
vm_start();
}
state = MIG_STATE_ERROR;
}
s->state = state;
notifier_list_notify(&migration_state_notifiers);
}
}
static void migrate_ft_trans_connect(FdMigrationState *s, int old_vm_running)
{
/* close buffered_file and open ft_trans_file
* NB: fd won't get closed, and reused by ft_trans_file
*/
qemu_fclose(s->file);
s->file = qemu_fopen_ops_ft_trans(s,
migrate_fd_put_buffer,
migrate_fd_get_buffer,
migrate_ft_trans_put_ready,
migrate_ft_trans_get_ready,
migrate_fd_wait_for_unfreeze,
migrate_fd_close,
1);
socket_set_nodelay(s->fd);
/* events are tapped from now */
if (event_tap_register(migrate_ft_trans_put_ready) < 0) {
migrate_ft_trans_error(s);
}
event_tap_schedule_suspend();
if (old_vm_running) {
vm_start();
}
}
MigrationState *migrate_get_current(void)
{
static MigrationState current_migration = {
.state = MIG_STATE_NONE,
.bandwidth_limit = MAX_THROTTLE,
.xbzrle_cache_size = DEFAULT_MIGRATE_CACHE_SIZE,
.mbps = -1,
};
return ¤t_migration;
}
void qemu_start_incoming_migration(const char *uri, Error **errp)
{
const char *p;
if (strstart(uri, "tcp:", &p))
tcp_start_incoming_migration(p, errp);
#ifdef CONFIG_RDMA
else if (strstart(uri, "rdma:", &p))
rdma_start_incoming_migration(p, errp);
#endif
#if !defined(WIN32)
else if (strstart(uri, "exec:", &p))
exec_start_incoming_migration(p, errp);
else if (strstart(uri, "unix:", &p))
unix_start_incoming_migration(p, errp);
else if (strstart(uri, "fd:", &p))
fd_start_incoming_migration(p, errp);
#endif
else {
error_setg(errp, "unknown migration protocol: %s", uri);
}
}
static void process_incoming_migration_co(void *opaque)
{
QEMUFile *f = opaque;
int ret;
ret = qemu_loadvm_state(f);
qemu_fclose(f);
free_xbzrle_decoded_buf();
if (ret < 0) {
fprintf(stderr, "load of migration failed\n");
exit(EXIT_FAILURE);
}
qemu_announce_self();
DPRINTF("successfully loaded vm state\n");
bdrv_clear_incoming_migration_all();
/* Make sure all file formats flush their mutable metadata */
bdrv_invalidate_cache_all();
if (autostart) {
vm_start();
} else {
runstate_set(RUN_STATE_PAUSED);
}
}
static void process_incoming_migration_co(void *opaque)
{
QEMUFile *f = opaque;
int ret;
ret = qemu_loadvm_state(f);
qemu_set_fd_handler(qemu_get_fd(f), NULL, NULL, NULL);
qemu_fclose(f);
if (ret < 0) {
fprintf(stderr, "load of migration failed\n");
exit(0);
}
qemu_announce_self();
DPRINTF("successfully loaded vm state\n");
bdrv_clear_incoming_migration_all();
/* Make sure all file formats flush their mutable metadata */
bdrv_invalidate_cache_all();
if (autostart) {
vm_start();
} else {
runstate_set(RUN_STATE_PAUSED);
}
}
static void migrate_fd_put_ready(void *opaque)
{
MigrationState *s = opaque;
int ret;
if (s->state != MIG_STATE_ACTIVE) {
DPRINTF("put_ready returning because of non-active state\n");
return;
}
DPRINTF("iterate\n");
ret = qemu_savevm_state_iterate(s->mon, s->file);
if (ret < 0) {
migrate_fd_error(s);
} else if (ret == 1) {
int old_vm_running = runstate_is_running();
DPRINTF("done iterating\n");
vm_stop_force_state(RUN_STATE_FINISH_MIGRATE);
if (qemu_savevm_state_complete(s->mon, s->file) < 0) {
migrate_fd_error(s);
} else {
migrate_fd_completed(s);
}
if (s->state != MIG_STATE_COMPLETED) {
if (old_vm_running) {
vm_start();
}
}
}
}
void migrate_fd_put_ready(void *opaque)
{
FdMigrationState *s = opaque;
if (s->state != MIG_STATE_ACTIVE) {
dprintf("put_ready returning because of non-active state\n");
return;
}
dprintf("iterate\n");
if (qemu_savevm_state_iterate(s->file) == 1) {
int state;
dprintf("done iterating\n");
vm_stop(0);
bdrv_flush_all();
if ((qemu_savevm_state_complete(s->file)) < 0) {
vm_start();
state = MIG_STATE_ERROR;
} else {
state = MIG_STATE_COMPLETED;
}
migrate_fd_cleanup(s);
s->state = state;
}
}
void qmp_cont(Error **errp)
{
Error *local_err = NULL;
BlockBackend *blk;
BlockDriverState *bs;
if (runstate_needs_reset()) {
error_setg(errp, "Resetting the Virtual Machine is required");
return;
} else if (runstate_check(RUN_STATE_SUSPENDED)) {
return;
}
for (blk = blk_next(NULL); blk; blk = blk_next(blk)) {
blk_iostatus_reset(blk);
}
for (bs = bdrv_next(NULL); bs; bs = bdrv_next(bs)) {
bdrv_add_key(bs, NULL, &local_err);
if (local_err) {
error_propagate(errp, local_err);
return;
}
}
if (runstate_check(RUN_STATE_INMIGRATE)) {
autostart = 1;
} else {
vm_start();
}
}
int exec_start_incoming_migration(const char *command)
{
int ret;
QEMUFile *f;
dprintf("Attempting to start an incoming migration\n");
f = qemu_popen_cmd(command, "r");
if(f == NULL) {
dprintf("Unable to apply qemu wrapper to popen file\n");
return -errno;
}
vm_stop(0); /* just in case */
ret = qemu_loadvm_state(f);
if (ret < 0) {
fprintf(stderr, "load of migration failed\n");
goto err;
}
qemu_announce_self();
dprintf("successfully loaded vm state\n");
vm_start();
qemu_fclose(f);
return 0;
err:
qemu_fclose(f);
return -errno;
}
void do_savevm(const char *name)
{
QEMUFile *f;
int saved_vm_running, ret;
f = qemu_fopen(name, "wb");
/* ??? Should this occur after vm_stop? */
qemu_aio_flush();
saved_vm_running = vm_running;
vm_stop(0);
if (!f) {
fprintf(logfile, "Failed to open savevm file '%s'\n", name);
goto the_end;
}
ret = qemu_savevm_state(f);
qemu_fclose(f);
if (ret < 0)
fprintf(logfile, "Error %d while writing VM to savevm file '%s'\n",
ret, name);
the_end:
if (saved_vm_running)
vm_start();
return;
}
int main(int argc, char** argv)
{
int fp = open(argv[1], O_RDONLY);
if(fp < 0) {
perror("Error opening file");
return 1;
}
VmFile vmfile = vmfile_open(fp);
if(vmfile == NULL) {
printf("Error: %d\n", vmerrno);
return vmerrno;
}
printf("Header: %s\n", vmfile_header_get(vmfile));
printf("Version : %d.%d\n", vmfile_version_major_get(vmfile),\
vmfile_version_minor_get(vmfile));
printf("Start Of Code Segment: %d\n", vmfile_entry_get(vmfile));
printf("Instructions: %d\n", vmfile_size_get(vmfile));
printf("Instruction Dump:\n");
vmfile_inst_print(vmfile);
printf("Output of Program\n");
VmState state = vmstate_new(vmfile);
Vm vm = vm_new(vmfile, state);
vm_start(vm);
vmfile_close(vmfile);
vmstate_del(state);
vm_del(vm);
return 0;
}
static void migrate_ft_trans_error(FdMigrationState *s)
{
ft_mode = FT_ERROR;
qemu_savevm_state_cancel(s->mon, s->file);
migrate_fd_error(s);
/* we need to set vm running to avoid assert in virtio-net */
vm_start();
event_tap_unregister();
vm_stop(0);
}
static int migrate_ft_trans_get_ready(void *opaque)
{
FdMigrationState *s = opaque;
int ret = -1;
if (ft_mode != FT_TRANSACTION_RECV) {
fprintf(stderr,
"migrate_ft_trans_get_ready: invalid ft_mode %d\n", ft_mode);
goto error_out;
}
/* flush and check if events are remaining */
vm_start();
ret = event_tap_flush_one();
if (ret < 0) {
fprintf(stderr, "event_tap_flush_one failed\n");
goto error_out;
}
if (ret) {
ft_mode = FT_TRANSACTION_BEGIN;
} else {
ft_mode = FT_TRANSACTION_ATOMIC;
ret = migrate_ft_trans_commit(s);
if (ret < 0) {
goto error_out;
}
if (ret) {
goto out;
}
}
vm_start();
ret = 0;
goto out;
error_out:
migrate_ft_trans_error(s);
out:
return ret;
}
/* Resume execution. */
static inline void gdb_continue(GDBState *s)
{
#ifdef CONFIG_USER_ONLY
s->running_state = 1;
#else
if (!runstate_needs_reset()) {
vm_start();
}
#endif
}
void process_incoming_migration(QEMUFile *f)
{
if (qemu_loadvm_state(f) < 0) {
fprintf(stderr, "load of migration failed\n");
exit(0);
}
qemu_announce_self();
DPRINTF("successfully loaded vm state\n");
if (autostart)
vm_start();
}
void qmp_cont(Error **errp)
{
Error *local_err = NULL;
BlockBackend *blk;
BlockDriverState *bs;
BdrvNextIterator *it;
/* if there is a dump in background, we should wait until the dump
* finished */
if (dump_in_progress()) {
error_setg(errp, "There is a dump in process, please wait.");
return;
}
if (runstate_needs_reset()) {
error_setg(errp, "Resetting the Virtual Machine is required");
return;
} else if (runstate_check(RUN_STATE_SUSPENDED)) {
return;
}
for (blk = blk_next(NULL); blk; blk = blk_next(blk)) {
blk_iostatus_reset(blk);
}
it = NULL;
while ((it = bdrv_next(it, &bs))) {
bdrv_add_key(bs, NULL, &local_err);
if (local_err) {
error_propagate(errp, local_err);
return;
}
}
/* Continuing after completed migration. Images have been inactivated to
* allow the destination to take control. Need to get control back now. */
if (runstate_check(RUN_STATE_FINISH_MIGRATE) ||
runstate_check(RUN_STATE_POSTMIGRATE))
{
bdrv_invalidate_cache_all(&local_err);
if (local_err) {
error_propagate(errp, local_err);
return;
}
}
if (runstate_check(RUN_STATE_INMIGRATE)) {
autostart = 1;
} else {
vm_start();
}
}
/* Resume execution. */
static inline void gdb_continue(GDBState *s)
{
#ifdef CONFIG_USER_ONLY
s->running_state = 1;
#else
if (runstate_check(RUN_STATE_GUEST_PANICKED)) {
runstate_set(RUN_STATE_DEBUG);
}
if (!runstate_needs_reset()) {
vm_start();
}
#endif
}
void start_hypervisor()
{
int i;
uint8_t nr_vcpus = 1; // TODO: It will be read from configuration file.
uint32_t pcpu = smp_processor_id();
if (pcpu == 0) {
timemanager_init();
sched_init();
vm_setup();
for (i = 0; i < NUM_GUESTS_STATIC; i++) {
vmid_t vmid;
if ((vmid = vm_create(nr_vcpus)) == VM_CREATE_FAILED) {
printf("vm_create(vm[%d]) is failed\n", i);
goto error;
}
if (vm_init(vmid) != HALTED) {
printf("vm_init(vm[%d]) is failed\n", i);
goto error;
}
if (vm_start(vmid) != RUNNING) {
printf("vm_start(vm[%d]) is failed\n", i);
goto error;
}
}
smp_pen = 1;
} else {
while (!smp_pen) ;
printf("cpu[%d] is enabled\n", pcpu);
}
/*
* TODO: Add a function - return vmid or vcpu_id to execute for the first time.
* TODO: Rename guest_sched_start to do_schedule or something others.
* do_schedule(vmid) or do_schedule(vcpu_id)
*/
printf("sched_start!!!\n");
sched_start();
/* The code flow must not reach here */
error:
printf("-------- [%s] ERROR: K-Hypervisor must not reach here\n", __func__);
abort();
}
static void tcp_accept_incoming_migration(void *opaque)
{
struct sockaddr_in addr;
socklen_t addrlen = sizeof(addr);
int s = (unsigned long)opaque;
QEMUFile *f;
int c, ret;
do {
c = accept(s, (struct sockaddr *)&addr, &addrlen);
} while (c == -1 && socket_error() == EINTR);
dprintf("accepted migration\n");
if (c == -1) {
fprintf(stderr, "could not accept migration connection\n");
return;
}
f = qemu_fopen_socket(c);
if (f == NULL) {
fprintf(stderr, "could not qemu_fopen socket\n");
goto out;
}
vm_stop(0); /* just in case */
ret = qemu_loadvm_state(f);
if (ret < 0) {
fprintf(stderr, "load of migration failed\n");
goto out_fopen;
}
qemu_announce_self();
dprintf("successfully loaded vm state\n");
/* we've successfully migrated, close the server socket */
qemu_set_fd_handler2(s, NULL, NULL, NULL, NULL);
close(s);
vm_start();
out_fopen:
qemu_fclose(f);
out:
close(c);
}
void process_incoming_migration(QEMUFile *f)
{
if (qemu_loadvm_state(f) < 0) {
fprintf(stderr, "load of migration failed\n");
exit(0);
}
qemu_announce_self();
DPRINTF("successfully loaded vm state\n");
/* Make sure all file formats flush their mutable metadata */
bdrv_invalidate_cache_all();
if (autostart) {
vm_start();
} else {
runstate_set(RUN_STATE_PRELAUNCH);
}
}
void qmp_cont(Error **errp)
{
Error *local_err = NULL;
BlockBackend *blk;
BlockDriverState *bs;
if (runstate_needs_reset()) {
error_setg(errp, "Resetting the Virtual Machine is required");
return;
} else if (runstate_check(RUN_STATE_SUSPENDED)) {
return;
}
for (blk = blk_next(NULL); blk; blk = blk_next(blk)) {
blk_iostatus_reset(blk);
}
for (bs = bdrv_next(NULL); bs; bs = bdrv_next(bs)) {
bdrv_add_key(bs, NULL, &local_err);
if (local_err) {
error_propagate(errp, local_err);
return;
}
}
/* Continuing after completed migration. Images have been inactivated to
* allow the destination to take control. Need to get control back now. */
if (runstate_check(RUN_STATE_FINISH_MIGRATE) ||
runstate_check(RUN_STATE_POSTMIGRATE))
{
bdrv_invalidate_cache_all(&local_err);
if (local_err) {
error_propagate(errp, local_err);
return;
}
}
if (runstate_check(RUN_STATE_INMIGRATE)) {
autostart = 1;
} else {
vm_start();
}
}
static void exec_accept_incoming_migration(void *opaque)
{
QEMUFile *f = opaque;
int ret;
ret = qemu_loadvm_state(f);
if (ret < 0) {
fprintf(stderr, "load of migration failed\n");
goto err;
}
qemu_announce_self();
dprintf("successfully loaded vm state\n");
/* we've successfully migrated, close the fd */
qemu_set_fd_handler2(qemu_stdio_fd(f), NULL, NULL, NULL, NULL);
if (autostart)
vm_start();
err:
qemu_fclose(f);
}
void qmp_cont(Error **errp)
{
BlockBackend *blk;
Error *local_err = NULL;
/* if there is a dump in background, we should wait until the dump
* finished */
if (dump_in_progress()) {
error_setg(errp, "There is a dump in process, please wait.");
return;
}
if (runstate_needs_reset()) {
error_setg(errp, "Resetting the Virtual Machine is required");
return;
} else if (runstate_check(RUN_STATE_SUSPENDED)) {
return;
}
for (blk = blk_next(NULL); blk; blk = blk_next(blk)) {
blk_iostatus_reset(blk);
}
/* Continuing after completed migration. Images have been inactivated to
* allow the destination to take control. Need to get control back now.
*
* If there are no inactive block nodes (e.g. because the VM was just
* paused rather than completing a migration), bdrv_inactivate_all() simply
* doesn't do anything. */
bdrv_invalidate_cache_all(&local_err);
if (local_err) {
error_propagate(errp, local_err);
return;
}
if (runstate_check(RUN_STATE_INMIGRATE)) {
autostart = 1;
} else {
vm_start();
}
}
static void tcp_accept_incoming_migration(void *opaque)
{
SockAddress addr;
int s = (unsigned long)opaque;
QEMUFile *f;
int c, ret;
c = socket_accept(s, &addr);
dprintf("accepted migration\n");
if (c == -1) {
fprintf(stderr, "could not accept migration connection\n");
return;
}
f = qemu_fopen_socket(c);
if (f == NULL) {
fprintf(stderr, "could not qemu_fopen socket\n");
goto out;
}
vm_stop(0); /* just in case */
ret = qemu_loadvm_state(f);
if (ret < 0) {
fprintf(stderr, "load of migration failed\n");
goto out_fopen;
}
qemu_announce_self();
dprintf("successfully loaded vm state\n");
/* we've successfully migrated, close the server socket */
qemu_set_fd_handler2(s, NULL, NULL, NULL, NULL);
socket_close(s);
vm_start();
out_fopen:
qemu_fclose(f);
out:
socket_close(c);
}
void do_loadvm(const char *name)
{
QEMUFile *f;
int saved_vm_running, ret;
/* Flush all IO requests so they don't interfere with the new state. */
qemu_aio_flush();
saved_vm_running = vm_running;
vm_stop(0);
/* restore the VM state */
f = qemu_fopen(name, "rb");
if (!f) {
fprintf(logfile, "Could not open VM state file\n");
goto the_end;
}
ret = qemu_loadvm_state(f);
qemu_fclose(f);
if (ret < 0) {
fprintf(logfile, "Error %d while loading savevm file '%s'\n",
ret, name);
goto the_end;
}
#if 0
/* del tmp file */
if (unlink(name) == -1)
fprintf(stderr, "delete tmp qemu state file failed.\n");
#endif
the_end:
if (saved_vm_running)
vm_start();
}
static int
vm_reboot_cb(vm_t* vm, void* token)
{
struct pwr_token* pwr_token = (struct pwr_token*)token;
uint32_t dtb_addr;
void* entry;
int err;
printf("Received reboot from linux\n");
//pwm_vmsig(0);
vm_sem_wait();
return 0;
// pwm_linux_action(1);
return -1;
#if 0
entry = install_linux_kernel(vm, pwr_token->linux_bin);
dtb_addr = install_linux_dtb(vm, pwr_token->device_tree);
if (entry == NULL || dtb_addr == 0) {
printf("Failed to reload linux\n");
return -1;
}
err = vm_set_bootargs(vm, entry, MACH_TYPE, dtb_addr);
if (err) {
printf("Failed to set boot args\n");
return -1;
}
err = vm_start(vm);
if (err) {
printf("Failed to restart linux\n");
return -1;
}
printf("VM restarted\n");
return 0;
#endif
}
void migrate_fd_put_ready(MigrationState *s)
{
int ret;
if (s->state != MIG_STATE_ACTIVE) {
DPRINTF("put_ready returning because of non-active state\n");
return;
}
DPRINTF("iterate\n");
ret = qemu_savevm_state_iterate(s->file);
if (ret < 0) {
migrate_fd_error(s);
} else if (ret == 1) {
int old_vm_running = runstate_is_running();
int64_t start_time, end_time;
DPRINTF("done iterating\n");
start_time = qemu_get_clock_ms(rt_clock);
qemu_system_wakeup_request(QEMU_WAKEUP_REASON_OTHER);
vm_stop_force_state(RUN_STATE_FINISH_MIGRATE);
if (qemu_savevm_state_complete(s->file) < 0) {
migrate_fd_error(s);
} else {
migrate_fd_completed(s);
}
end_time = qemu_get_clock_ms(rt_clock);
s->total_time = end_time - s->total_time;
s->downtime = end_time - start_time;
if (s->state != MIG_STATE_COMPLETED) {
if (old_vm_running) {
vm_start();
}
}
}
}
static void colo_process_checkpoint(MigrationState *s)
{
QIOChannelBuffer *bioc;
QEMUFile *fb = NULL;
int64_t current_time = qemu_clock_get_ms(QEMU_CLOCK_HOST);
Error *local_err = NULL;
int ret;
failover_init_state();
s->rp_state.from_dst_file = qemu_file_get_return_path(s->to_dst_file);
if (!s->rp_state.from_dst_file) {
error_report("Open QEMUFile from_dst_file failed");
goto out;
}
/*
* Wait for Secondary finish loading VM states and enter COLO
* restore.
*/
colo_receive_check_message(s->rp_state.from_dst_file,
COLO_MESSAGE_CHECKPOINT_READY, &local_err);
if (local_err) {
goto out;
}
bioc = qio_channel_buffer_new(COLO_BUFFER_BASE_SIZE);
fb = qemu_fopen_channel_output(QIO_CHANNEL(bioc));
object_unref(OBJECT(bioc));
qemu_mutex_lock_iothread();
vm_start();
qemu_mutex_unlock_iothread();
trace_colo_vm_state_change("stop", "run");
timer_mod(s->colo_delay_timer,
current_time + s->parameters.x_checkpoint_delay);
while (s->state == MIGRATION_STATUS_COLO) {
if (failover_get_state() != FAILOVER_STATUS_NONE) {
error_report("failover request");
goto out;
}
qemu_sem_wait(&s->colo_checkpoint_sem);
ret = colo_do_checkpoint_transaction(s, bioc, fb);
if (ret < 0) {
goto out;
}
}
out:
/* Throw the unreported error message after exited from loop */
if (local_err) {
error_report_err(local_err);
}
if (fb) {
qemu_fclose(fb);
}
timer_del(s->colo_delay_timer);
/* Hope this not to be too long to wait here */
qemu_sem_wait(&s->colo_exit_sem);
qemu_sem_destroy(&s->colo_exit_sem);
/*
* Must be called after failover BH is completed,
* Or the failover BH may shutdown the wrong fd that
* re-used by other threads after we release here.
*/
if (s->rp_state.from_dst_file) {
qemu_fclose(s->rp_state.from_dst_file);
}
}
static int colo_do_checkpoint_transaction(MigrationState *s,
QIOChannelBuffer *bioc,
QEMUFile *fb)
{
Error *local_err = NULL;
int ret = -1;
colo_send_message(s->to_dst_file, COLO_MESSAGE_CHECKPOINT_REQUEST,
&local_err);
if (local_err) {
goto out;
}
colo_receive_check_message(s->rp_state.from_dst_file,
COLO_MESSAGE_CHECKPOINT_REPLY, &local_err);
if (local_err) {
goto out;
}
/* Reset channel-buffer directly */
qio_channel_io_seek(QIO_CHANNEL(bioc), 0, 0, NULL);
bioc->usage = 0;
qemu_mutex_lock_iothread();
if (failover_get_state() != FAILOVER_STATUS_NONE) {
qemu_mutex_unlock_iothread();
goto out;
}
vm_stop_force_state(RUN_STATE_COLO);
qemu_mutex_unlock_iothread();
trace_colo_vm_state_change("run", "stop");
/*
* Failover request bh could be called after vm_stop_force_state(),
* So we need check failover_request_is_active() again.
*/
if (failover_get_state() != FAILOVER_STATUS_NONE) {
goto out;
}
/* Disable block migration */
s->params.blk = 0;
s->params.shared = 0;
qemu_savevm_state_header(fb);
qemu_savevm_state_begin(fb, &s->params);
qemu_mutex_lock_iothread();
qemu_savevm_state_complete_precopy(fb, false);
qemu_mutex_unlock_iothread();
qemu_fflush(fb);
colo_send_message(s->to_dst_file, COLO_MESSAGE_VMSTATE_SEND, &local_err);
if (local_err) {
goto out;
}
/*
* We need the size of the VMstate data in Secondary side,
* With which we can decide how much data should be read.
*/
colo_send_message_value(s->to_dst_file, COLO_MESSAGE_VMSTATE_SIZE,
bioc->usage, &local_err);
if (local_err) {
goto out;
}
qemu_put_buffer(s->to_dst_file, bioc->data, bioc->usage);
qemu_fflush(s->to_dst_file);
ret = qemu_file_get_error(s->to_dst_file);
if (ret < 0) {
goto out;
}
colo_receive_check_message(s->rp_state.from_dst_file,
COLO_MESSAGE_VMSTATE_RECEIVED, &local_err);
if (local_err) {
goto out;
}
colo_receive_check_message(s->rp_state.from_dst_file,
COLO_MESSAGE_VMSTATE_LOADED, &local_err);
if (local_err) {
goto out;
}
ret = 0;
qemu_mutex_lock_iothread();
vm_start();
qemu_mutex_unlock_iothread();
trace_colo_vm_state_change("stop", "run");
out:
if (local_err) {
error_report_err(local_err);
}
return ret;
}
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;
}
static void colo_process_checkpoint(MigrationState *s)
{
QIOChannelBuffer *bioc;
QEMUFile *fb = NULL;
int64_t current_time = qemu_clock_get_ms(QEMU_CLOCK_HOST);
Error *local_err = NULL;
int ret;
failover_init_state();
s->rp_state.from_dst_file = qemu_file_get_return_path(s->to_dst_file);
if (!s->rp_state.from_dst_file) {
error_report("Open QEMUFile from_dst_file failed");
goto out;
}
packets_compare_notifier.notify = colo_compare_notify_checkpoint;
colo_compare_register_notifier(&packets_compare_notifier);
/*
* Wait for Secondary finish loading VM states and enter COLO
* restore.
*/
colo_receive_check_message(s->rp_state.from_dst_file,
COLO_MESSAGE_CHECKPOINT_READY, &local_err);
if (local_err) {
goto out;
}
bioc = qio_channel_buffer_new(COLO_BUFFER_BASE_SIZE);
fb = qemu_fopen_channel_output(QIO_CHANNEL(bioc));
object_unref(OBJECT(bioc));
qemu_mutex_lock_iothread();
#ifdef CONFIG_REPLICATION
replication_start_all(REPLICATION_MODE_PRIMARY, &local_err);
if (local_err) {
qemu_mutex_unlock_iothread();
goto out;
}
#else
abort();
#endif
vm_start();
qemu_mutex_unlock_iothread();
trace_colo_vm_state_change("stop", "run");
timer_mod(s->colo_delay_timer,
current_time + s->parameters.x_checkpoint_delay);
while (s->state == MIGRATION_STATUS_COLO) {
if (failover_get_state() != FAILOVER_STATUS_NONE) {
error_report("failover request");
goto out;
}
qemu_sem_wait(&s->colo_checkpoint_sem);
if (s->state != MIGRATION_STATUS_COLO) {
goto out;
}
ret = colo_do_checkpoint_transaction(s, bioc, fb);
if (ret < 0) {
goto out;
}
}
out:
/* Throw the unreported error message after exited from loop */
if (local_err) {
error_report_err(local_err);
}
if (fb) {
qemu_fclose(fb);
}
/*
* There are only two reasons we can get here, some error happened
* or the user triggered failover.
*/
switch (failover_get_state()) {
case FAILOVER_STATUS_NONE:
qapi_event_send_colo_exit(COLO_MODE_PRIMARY,
COLO_EXIT_REASON_ERROR);
break;
case FAILOVER_STATUS_REQUIRE:
qapi_event_send_colo_exit(COLO_MODE_PRIMARY,
COLO_EXIT_REASON_REQUEST);
break;
default:
abort();
}
/* Hope this not to be too long to wait here */
qemu_sem_wait(&s->colo_exit_sem);
qemu_sem_destroy(&s->colo_exit_sem);
/*
* It is safe to unregister notifier after failover finished.
* Besides, colo_delay_timer and colo_checkpoint_sem can't be
* released befor unregister notifier, or there will be use-after-free
* error.
*/
colo_compare_unregister_notifier(&packets_compare_notifier);
timer_del(s->colo_delay_timer);
timer_free(s->colo_delay_timer);
qemu_sem_destroy(&s->colo_checkpoint_sem);
/*
* Must be called after failover BH is completed,
* Or the failover BH may shutdown the wrong fd that
* re-used by other threads after we release here.
*/
if (s->rp_state.from_dst_file) {
qemu_fclose(s->rp_state.from_dst_file);
}
}