static void primary_vm_do_failover(void)
{
MigrationState *s = migrate_get_current();
int old_state;
migrate_set_state(&s->state, MIGRATION_STATUS_COLO,
MIGRATION_STATUS_COMPLETED);
/*
* Wake up COLO thread which may blocked in recv() or send(),
* The s->rp_state.from_dst_file and s->to_dst_file may use the
* same fd, but we still shutdown the fd for twice, it is harmless.
*/
if (s->to_dst_file) {
qemu_file_shutdown(s->to_dst_file);
}
if (s->rp_state.from_dst_file) {
qemu_file_shutdown(s->rp_state.from_dst_file);
}
old_state = failover_set_state(FAILOVER_STATUS_ACTIVE,
FAILOVER_STATUS_COMPLETED);
if (old_state != FAILOVER_STATUS_ACTIVE) {
error_report("Incorrect state (%s) while doing failover for Primary VM",
FailoverStatus_lookup[old_state]);
return;
}
/* Notify COLO thread that failover work is finished */
qemu_sem_post(&s->colo_exit_sem);
}
void colo_checkpoint_notify(void *opaque)
{
MigrationState *s = opaque;
int64_t next_notify_time;
qemu_sem_post(&s->colo_checkpoint_sem);
s->colo_checkpoint_time = qemu_clock_get_ms(QEMU_CLOCK_HOST);
next_notify_time = s->colo_checkpoint_time +
s->parameters.x_checkpoint_delay;
timer_mod(s->colo_delay_timer, next_notify_time);
}
static void secondary_vm_do_failover(void)
{
int old_state;
MigrationIncomingState *mis = migration_incoming_get_current();
/* Can not do failover during the process of VM's loading VMstate, Or
* it will break the secondary VM.
*/
if (vmstate_loading) {
old_state = failover_set_state(FAILOVER_STATUS_ACTIVE,
FAILOVER_STATUS_RELAUNCH);
if (old_state != FAILOVER_STATUS_ACTIVE) {
error_report("Unknown error while do failover for secondary VM,"
"old_state: %s", FailoverStatus_lookup[old_state]);
}
return;
}
migrate_set_state(&mis->state, MIGRATION_STATUS_COLO,
MIGRATION_STATUS_COMPLETED);
if (!autostart) {
error_report("\"-S\" qemu option will be ignored in secondary side");
/* recover runstate to normal migration finish state */
autostart = true;
}
/*
* Make sure COLO incoming thread not block in recv or send,
* If mis->from_src_file and mis->to_src_file use the same fd,
* The second shutdown() will return -1, we ignore this value,
* It is harmless.
*/
if (mis->from_src_file) {
qemu_file_shutdown(mis->from_src_file);
}
if (mis->to_src_file) {
qemu_file_shutdown(mis->to_src_file);
}
old_state = failover_set_state(FAILOVER_STATUS_ACTIVE,
FAILOVER_STATUS_COMPLETED);
if (old_state != FAILOVER_STATUS_ACTIVE) {
error_report("Incorrect state (%s) while doing failover for "
"secondary VM", FailoverStatus_lookup[old_state]);
return;
}
/* Notify COLO incoming thread that failover work is finished */
qemu_sem_post(&mis->colo_incoming_sem);
/* For Secondary VM, jump to incoming co */
if (mis->migration_incoming_co) {
qemu_coroutine_enter(mis->migration_incoming_co);
}
}
static void primary_vm_do_failover(void)
{
#ifdef CONFIG_REPLICATION
MigrationState *s = migrate_get_current();
int old_state;
Error *local_err = NULL;
migrate_set_state(&s->state, MIGRATION_STATUS_COLO,
MIGRATION_STATUS_COMPLETED);
/*
* kick COLO thread which might wait at
* qemu_sem_wait(&s->colo_checkpoint_sem).
*/
colo_checkpoint_notify(migrate_get_current());
/*
* Wake up COLO thread which may blocked in recv() or send(),
* The s->rp_state.from_dst_file and s->to_dst_file may use the
* same fd, but we still shutdown the fd for twice, it is harmless.
*/
if (s->to_dst_file) {
qemu_file_shutdown(s->to_dst_file);
}
if (s->rp_state.from_dst_file) {
qemu_file_shutdown(s->rp_state.from_dst_file);
}
old_state = failover_set_state(FAILOVER_STATUS_ACTIVE,
FAILOVER_STATUS_COMPLETED);
if (old_state != FAILOVER_STATUS_ACTIVE) {
error_report("Incorrect state (%s) while doing failover for Primary VM",
FailoverStatus_str(old_state));
return;
}
replication_stop_all(true, &local_err);
if (local_err) {
error_report_err(local_err);
local_err = NULL;
}
/* Notify COLO thread that failover work is finished */
qemu_sem_post(&s->colo_exit_sem);
#else
abort();
#endif
}
/*
* Handle faults detected by the USERFAULT markings
*/
static void *postcopy_ram_fault_thread(void *opaque)
{
MigrationIncomingState *mis = opaque;
struct uffd_msg msg;
int ret;
size_t index;
RAMBlock *rb = NULL;
trace_postcopy_ram_fault_thread_entry();
mis->last_rb = NULL; /* last RAMBlock we sent part of */
qemu_sem_post(&mis->fault_thread_sem);
struct pollfd *pfd;
size_t pfd_len = 2 + mis->postcopy_remote_fds->len;
pfd = g_new0(struct pollfd, pfd_len);
pfd[0].fd = mis->userfault_fd;
pfd[0].events = POLLIN;
pfd[1].fd = mis->userfault_event_fd;
pfd[1].events = POLLIN; /* Waiting for eventfd to go positive */
trace_postcopy_ram_fault_thread_fds_core(pfd[0].fd, pfd[1].fd);
for (index = 0; index < mis->postcopy_remote_fds->len; index++) {
struct PostCopyFD *pcfd = &g_array_index(mis->postcopy_remote_fds,
struct PostCopyFD, index);
pfd[2 + index].fd = pcfd->fd;
pfd[2 + index].events = POLLIN;
trace_postcopy_ram_fault_thread_fds_extra(2 + index, pcfd->idstr,
pcfd->fd);
}
while (true) {
ram_addr_t rb_offset;
int poll_result;
/*
* We're mainly waiting for the kernel to give us a faulting HVA,
* however we can be told to quit via userfault_quit_fd which is
* an eventfd
*/
poll_result = poll(pfd, pfd_len, -1 /* Wait forever */);
if (poll_result == -1) {
error_report("%s: userfault poll: %s", __func__, strerror(errno));
break;
}
if (pfd[1].revents) {
uint64_t tmp64 = 0;
/* Consume the signal */
if (read(mis->userfault_event_fd, &tmp64, 8) != 8) {
/* Nothing obviously nicer than posting this error. */
error_report("%s: read() failed", __func__);
}
if (atomic_read(&mis->fault_thread_quit)) {
trace_postcopy_ram_fault_thread_quit();
break;
}
}
if (pfd[0].revents) {
poll_result--;
ret = read(mis->userfault_fd, &msg, sizeof(msg));
if (ret != sizeof(msg)) {
if (errno == EAGAIN) {
/*
* if a wake up happens on the other thread just after
* the poll, there is nothing to read.
*/
continue;
}
if (ret < 0) {
error_report("%s: Failed to read full userfault "
"message: %s",
__func__, strerror(errno));
break;
} else {
error_report("%s: Read %d bytes from userfaultfd "
"expected %zd",
__func__, ret, sizeof(msg));
break; /* Lost alignment, don't know what we'd read next */
}
}
if (msg.event != UFFD_EVENT_PAGEFAULT) {
error_report("%s: Read unexpected event %ud from userfaultfd",
__func__, msg.event);
continue; /* It's not a page fault, shouldn't happen */
}
rb = qemu_ram_block_from_host(
(void *)(uintptr_t)msg.arg.pagefault.address,
true, &rb_offset);
if (!rb) {
error_report("postcopy_ram_fault_thread: Fault outside guest: %"
PRIx64, (uint64_t)msg.arg.pagefault.address);
break;
}
rb_offset &= ~(qemu_ram_pagesize(rb) - 1);
trace_postcopy_ram_fault_thread_request(msg.arg.pagefault.address,
qemu_ram_get_idstr(rb),
rb_offset,
msg.arg.pagefault.feat.ptid);
mark_postcopy_blocktime_begin(
(uintptr_t)(msg.arg.pagefault.address),
msg.arg.pagefault.feat.ptid, rb);
/*
* Send the request to the source - we want to request one
* of our host page sizes (which is >= TPS)
*/
if (rb != mis->last_rb) {
mis->last_rb = rb;
migrate_send_rp_req_pages(mis, qemu_ram_get_idstr(rb),
rb_offset, qemu_ram_pagesize(rb));
} else {
/* Save some space */
migrate_send_rp_req_pages(mis, NULL,
rb_offset, qemu_ram_pagesize(rb));
}
}
/* Now handle any requests from external processes on shared memory */
/* TODO: May need to handle devices deregistering during postcopy */
for (index = 2; index < pfd_len && poll_result; index++) {
if (pfd[index].revents) {
struct PostCopyFD *pcfd =
&g_array_index(mis->postcopy_remote_fds,
struct PostCopyFD, index - 2);
poll_result--;
if (pfd[index].revents & POLLERR) {
error_report("%s: POLLERR on poll %zd fd=%d",
__func__, index, pcfd->fd);
pfd[index].events = 0;
continue;
}
ret = read(pcfd->fd, &msg, sizeof(msg));
if (ret != sizeof(msg)) {
if (errno == EAGAIN) {
/*
* if a wake up happens on the other thread just after
* the poll, there is nothing to read.
*/
continue;
}
if (ret < 0) {
error_report("%s: Failed to read full userfault "
"message: %s (shared) revents=%d",
__func__, strerror(errno),
pfd[index].revents);
/*TODO: Could just disable this sharer */
break;
} else {
error_report("%s: Read %d bytes from userfaultfd "
"expected %zd (shared)",
__func__, ret, sizeof(msg));
/*TODO: Could just disable this sharer */
break; /*Lost alignment,don't know what we'd read next*/
}
}
if (msg.event != UFFD_EVENT_PAGEFAULT) {
error_report("%s: Read unexpected event %ud "
"from userfaultfd (shared)",
__func__, msg.event);
continue; /* It's not a page fault, shouldn't happen */
}
/* Call the device handler registered with us */
ret = pcfd->handler(pcfd, &msg);
if (ret) {
error_report("%s: Failed to resolve shared fault on %zd/%s",
__func__, index, pcfd->idstr);
/* TODO: Fail? Disable this sharer? */
}
}
}
}
trace_postcopy_ram_fault_thread_exit();
g_free(pfd);
return NULL;
}
static void secondary_vm_do_failover(void)
{
/* COLO needs enable block-replication */
#ifdef CONFIG_REPLICATION
int old_state;
MigrationIncomingState *mis = migration_incoming_get_current();
Error *local_err = NULL;
/* Can not do failover during the process of VM's loading VMstate, Or
* it will break the secondary VM.
*/
if (vmstate_loading) {
old_state = failover_set_state(FAILOVER_STATUS_ACTIVE,
FAILOVER_STATUS_RELAUNCH);
if (old_state != FAILOVER_STATUS_ACTIVE) {
error_report("Unknown error while do failover for secondary VM,"
"old_state: %s", FailoverStatus_str(old_state));
}
return;
}
migrate_set_state(&mis->state, MIGRATION_STATUS_COLO,
MIGRATION_STATUS_COMPLETED);
replication_stop_all(true, &local_err);
if (local_err) {
error_report_err(local_err);
}
/* Notify all filters of all NIC to do checkpoint */
colo_notify_filters_event(COLO_EVENT_FAILOVER, &local_err);
if (local_err) {
error_report_err(local_err);
}
if (!autostart) {
error_report("\"-S\" qemu option will be ignored in secondary side");
/* recover runstate to normal migration finish state */
autostart = true;
}
/*
* Make sure COLO incoming thread not block in recv or send,
* If mis->from_src_file and mis->to_src_file use the same fd,
* The second shutdown() will return -1, we ignore this value,
* It is harmless.
*/
if (mis->from_src_file) {
qemu_file_shutdown(mis->from_src_file);
}
if (mis->to_src_file) {
qemu_file_shutdown(mis->to_src_file);
}
old_state = failover_set_state(FAILOVER_STATUS_ACTIVE,
FAILOVER_STATUS_COMPLETED);
if (old_state != FAILOVER_STATUS_ACTIVE) {
error_report("Incorrect state (%s) while doing failover for "
"secondary VM", FailoverStatus_str(old_state));
return;
}
/* Notify COLO incoming thread that failover work is finished */
qemu_sem_post(&mis->colo_incoming_sem);
/* For Secondary VM, jump to incoming co */
if (mis->migration_incoming_co) {
qemu_coroutine_enter(mis->migration_incoming_co);
}
#else
abort();
#endif
}
