/* Register a handler for external shared memory postcopy
* called on the destination.
*/
void postcopy_register_shared_ufd(struct PostCopyFD *pcfd)
{
MigrationIncomingState *mis = migration_incoming_get_current();
mis->postcopy_remote_fds = g_array_append_val(mis->postcopy_remote_fds,
*pcfd);
}
static uint32_t get_postcopy_total_blocktime(void)
{
MigrationIncomingState *mis = migration_incoming_get_current();
PostcopyBlocktimeContext *bc = mis->blocktime_ctx;
if (!bc) {
return 0;
}
return bc->total_blocktime;
}
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);
}
}
/*
* This function just populates MigrationInfo from postcopy's
* blocktime context. It will not populate MigrationInfo,
* unless postcopy-blocktime capability was set.
*
* @info: pointer to MigrationInfo to populate
*/
void fill_destination_postcopy_migration_info(MigrationInfo *info)
{
MigrationIncomingState *mis = migration_incoming_get_current();
PostcopyBlocktimeContext *bc = mis->blocktime_ctx;
if (!bc) {
return;
}
info->has_postcopy_blocktime = true;
info->postcopy_blocktime = bc->total_blocktime;
info->has_postcopy_vcpu_blocktime = true;
info->postcopy_vcpu_blocktime = get_vcpu_blocktime_list(bc);
}
/* Unregister a handler for external shared memory postcopy
*/
void postcopy_unregister_shared_ufd(struct PostCopyFD *pcfd)
{
guint i;
MigrationIncomingState *mis = migration_incoming_get_current();
GArray *pcrfds = mis->postcopy_remote_fds;
for (i = 0; i < pcrfds->len; i++) {
struct PostCopyFD *cur = &g_array_index(pcrfds, struct PostCopyFD, i);
if (cur->fd == pcfd->fd) {
mis->postcopy_remote_fds = g_array_remove_index(pcrfds, i);
return;
}
}
}
int postcopy_notify_shared_wake(RAMBlock *rb, uint64_t offset)
{
int i;
MigrationIncomingState *mis = migration_incoming_get_current();
GArray *pcrfds = mis->postcopy_remote_fds;
for (i = 0; i < pcrfds->len; i++) {
struct PostCopyFD *cur = &g_array_index(pcrfds, struct PostCopyFD, i);
int ret = cur->waker(cur, rb, offset);
if (ret) {
return ret;
}
}
return 0;
}
/*
* This function just provide calculated blocktime per cpu and trace it.
* Total blocktime is calculated in mark_postcopy_blocktime_end.
*
*
* Assume we have 3 CPU
*
* S1 E1 S1 E1
* -----***********------------xxx***************------------------------> CPU1
*
* S2 E2
* ------------****************xxx---------------------------------------> CPU2
*
* S3 E3
* ------------------------****xxx********-------------------------------> CPU3
*
* We have sequence S1,S2,E1,S3,S1,E2,E3,E1
* S2,E1 - doesn't match condition due to sequence S1,S2,E1 doesn't include CPU3
* S3,S1,E2 - sequence includes all CPUs, in this case overlap will be S1,E2 -
* it's a part of total blocktime.
* S1 - here is last_begin
* Legend of the picture is following:
* * - means blocktime per vCPU
* x - means overlapped blocktime (total blocktime)
*
* @addr: host virtual address
*/
static void mark_postcopy_blocktime_end(uintptr_t addr)
{
MigrationIncomingState *mis = migration_incoming_get_current();
PostcopyBlocktimeContext *dc = mis->blocktime_ctx;
int i, affected_cpu = 0;
bool vcpu_total_blocktime = false;
uint32_t read_vcpu_time, low_time_offset;
if (!dc) {
return;
}
low_time_offset = get_low_time_offset(dc);
/* lookup cpu, to clear it,
* that algorithm looks straighforward, but it's not
* optimal, more optimal algorithm is keeping tree or hash
* where key is address value is a list of */
for (i = 0; i < smp_cpus; i++) {
uint32_t vcpu_blocktime = 0;
read_vcpu_time = atomic_fetch_add(&dc->page_fault_vcpu_time[i], 0);
if (atomic_fetch_add(&dc->vcpu_addr[i], 0) != addr ||
read_vcpu_time == 0) {
continue;
}
atomic_xchg(&dc->vcpu_addr[i], 0);
vcpu_blocktime = low_time_offset - read_vcpu_time;
affected_cpu += 1;
/* we need to know is that mark_postcopy_end was due to
* faulted page, another possible case it's prefetched
* page and in that case we shouldn't be here */
if (!vcpu_total_blocktime &&
atomic_fetch_add(&dc->smp_cpus_down, 0) == smp_cpus) {
vcpu_total_blocktime = true;
}
/* continue cycle, due to one page could affect several vCPUs */
dc->vcpu_blocktime[i] += vcpu_blocktime;
}
atomic_sub(&dc->smp_cpus_down, affected_cpu);
if (vcpu_total_blocktime) {
dc->total_blocktime += low_time_offset - atomic_fetch_add(
&dc->last_begin, 0);
}
trace_mark_postcopy_blocktime_end(addr, dc, dc->total_blocktime,
affected_cpu);
}
/*
* This function is being called when pagefault occurs. It
* tracks down vCPU blocking time.
*
* @addr: faulted host virtual address
* @ptid: faulted process thread id
* @rb: ramblock appropriate to addr
*/
static void mark_postcopy_blocktime_begin(uintptr_t addr, uint32_t ptid,
RAMBlock *rb)
{
int cpu, already_received;
MigrationIncomingState *mis = migration_incoming_get_current();
PostcopyBlocktimeContext *dc = mis->blocktime_ctx;
uint32_t low_time_offset;
if (!dc || ptid == 0) {
return;
}
cpu = get_mem_fault_cpu_index(ptid);
if (cpu < 0) {
return;
}
low_time_offset = get_low_time_offset(dc);
if (dc->vcpu_addr[cpu] == 0) {
atomic_inc(&dc->smp_cpus_down);
}
atomic_xchg(&dc->last_begin, low_time_offset);
atomic_xchg(&dc->page_fault_vcpu_time[cpu], low_time_offset);
atomic_xchg(&dc->vcpu_addr[cpu], addr);
/* check it here, not at the begining of the function,
* due to, check could accur early than bitmap_set in
* qemu_ufd_copy_ioctl */
already_received = ramblock_recv_bitmap_test(rb, (void *)addr);
if (already_received) {
atomic_xchg(&dc->vcpu_addr[cpu], 0);
atomic_xchg(&dc->page_fault_vcpu_time[cpu], 0);
atomic_dec(&dc->smp_cpus_down);
}
trace_mark_postcopy_blocktime_begin(addr, dc, dc->page_fault_vcpu_time[cpu],
cpu, already_received);
}
/*
* Callback from shared fault handlers to ask for a page,
* the page must be specified by a RAMBlock and an offset in that rb
* Note: Only for use by shared fault handlers (in fault thread)
*/
int postcopy_request_shared_page(struct PostCopyFD *pcfd, RAMBlock *rb,
uint64_t client_addr, uint64_t rb_offset)
{
size_t pagesize = qemu_ram_pagesize(rb);
uint64_t aligned_rbo = rb_offset & ~(pagesize - 1);
MigrationIncomingState *mis = migration_incoming_get_current();
trace_postcopy_request_shared_page(pcfd->idstr, qemu_ram_get_idstr(rb),
rb_offset);
if (ramblock_recv_bitmap_test_byte_offset(rb, aligned_rbo)) {
trace_postcopy_request_shared_page_present(pcfd->idstr,
qemu_ram_get_idstr(rb), rb_offset);
return postcopy_wake_shared(pcfd, client_addr, rb);
}
if (rb != mis->last_rb) {
mis->last_rb = rb;
migrate_send_rp_req_pages(mis, qemu_ram_get_idstr(rb),
aligned_rbo, pagesize);
} else {
/* Save some space */
migrate_send_rp_req_pages(mis, NULL, aligned_rbo, pagesize);
}
return 0;
}
bool migration_incoming_in_colo_state(void)
{
MigrationIncomingState *mis = migration_incoming_get_current();
return mis && (mis->state == MIGRATION_STATUS_COLO);
}
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
}
