@@ -1130,7 +1130,6 @@ static void fill_source_migration_info(MigrationInfo *info)
info->status = s->state;
}
-#ifdef CONFIG_LINUX
typedef enum WriteTrackingSupport {
WT_SUPPORT_UNKNOWN = 0,
WT_SUPPORT_ABSENT,
@@ -1155,7 +1154,6 @@ WriteTrackingSupport migrate_query_write_tracking(void)
return WT_SUPPORT_COMPATIBLE;
}
-#endif /* CONFIG_LINUX */
/**
* @migration_caps_check - check capability validity
@@ -1219,7 +1217,6 @@ static bool migrate_caps_check(bool *cap_list,
}
if (cap_list[MIGRATION_CAPABILITY_BACKGROUND_SNAPSHOT]) {
-#ifdef CONFIG_LINUX
WriteTrackingSupport wt_support;
int idx;
/*
@@ -1250,11 +1247,6 @@ static bool migrate_caps_check(bool *cap_list,
return false;
}
}
-#else
- error_setg(errp,
- "Background-snapshot is not supported on non-Linux hosts");
- return false;
-#endif
}
return true;
@@ -2016,6 +2008,7 @@ void migrate_init(MigrationState *s)
* locks.
*/
s->cleanup_bh = 0;
+ s->vm_start_bh = 0;
s->to_dst_file = NULL;
s->state = MIGRATION_STATUS_NONE;
s->rp_state.from_dst_file = NULL;
@@ -3233,6 +3226,50 @@ fail:
MIGRATION_STATUS_FAILED);
}
+/**
+ * bg_migration_completion: Used by bg_migration_thread when after all the
+ * RAM has been saved. The caller 'breaks' the loop when this returns.
+ *
+ * @s: Current migration state
+ */
+static void bg_migration_completion(MigrationState *s)
+{
+ int current_active_state = s->state;
+
+ /*
+ * Stop tracking RAM writes - un-protect memory, un-register UFFD
+ * memory ranges, flush kernel wait queues and wake up threads
+ * waiting for write fault to be resolved.
+ */
+ ram_write_tracking_stop();
+
+ if (s->state == MIGRATION_STATUS_ACTIVE) {
+ /*
+ * By this moment we have RAM content saved into the migration stream.
+ * The next step is to flush the non-RAM content (device state)
+ * right after the ram content. The device state has been stored into
+ * the temporary buffer before RAM saving started.
+ */
+ qemu_put_buffer(s->to_dst_file, s->bioc->data, s->bioc->usage);
+ qemu_fflush(s->to_dst_file);
+ } else if (s->state == MIGRATION_STATUS_CANCELLING) {
+ goto fail;
+ }
+
+ if (qemu_file_get_error(s->to_dst_file)) {
+ trace_migration_completion_file_err();
+ goto fail;
+ }
+
+ migrate_set_state(&s->state, current_active_state,
+ MIGRATION_STATUS_COMPLETED);
+ return;
+
+fail:
+ migrate_set_state(&s->state, current_active_state,
+ MIGRATION_STATUS_FAILED);
+}
+
bool migrate_colo_enabled(void)
{
MigrationState *s = migrate_get_current();
@@ -3573,6 +3610,47 @@ static void migration_iteration_finish(MigrationState *s)
qemu_mutex_unlock_iothread();
}
+static void bg_migration_iteration_finish(MigrationState *s)
+{
+ qemu_mutex_lock_iothread();
+ switch (s->state) {
+ case MIGRATION_STATUS_COMPLETED:
+ migration_calculate_complete(s);
+ break;
+
+ case MIGRATION_STATUS_ACTIVE:
+ case MIGRATION_STATUS_FAILED:
+ case MIGRATION_STATUS_CANCELLED:
+ case MIGRATION_STATUS_CANCELLING:
+ break;
+
+ default:
+ /* Should not reach here, but if so, forgive the VM. */
+ error_report("%s: Unknown ending state %d", __func__, s->state);
+ break;
+ }
+
+ migrate_fd_cleanup_schedule(s);
+ qemu_mutex_unlock_iothread();
+}
+
+/*
+ * Return true if continue to the next iteration directly, false
+ * otherwise.
+ */
+static MigIterateState bg_migration_iteration_run(MigrationState *s)
+{
+ int res;
+
+ res = qemu_savevm_state_iterate(s->to_dst_file, false);
+ if (res > 0) {
+ bg_migration_completion(s);
+ return MIG_ITERATE_BREAK;
+ }
+
+ return MIG_ITERATE_RESUME;
+}
+
void migration_make_urgent_request(void)
{
qemu_sem_post(&migrate_get_current()->rate_limit_sem);
@@ -3720,6 +3798,165 @@ static void *migration_thread(void *opaque)
return NULL;
}
+static void bg_migration_vm_start_bh(void *opaque)
+{
+ MigrationState *s = opaque;
+
+ qemu_bh_delete(s->vm_start_bh);
+ s->vm_start_bh = NULL;
+
+ vm_start();
+ s->downtime = qemu_clock_get_ms(QEMU_CLOCK_REALTIME) - s->downtime_start;
+}
+
+/**
+ * Background snapshot thread, based on live migration code.
+ * This is an alternative implementation of live migration mechanism
+ * introduced specifically to support background snapshots.
+ *
+ * It takes advantage of userfault_fd write protection mechanism introduced
+ * in v5.7 kernel. Compared to existing dirty page logging migration much
+ * lesser stream traffic is produced resulting in smaller snapshot images,
+ * simply cause of no page duplicates can get into the stream.
+ *
+ * Another key point is that generated vmstate stream reflects machine state
+ * 'frozen' at the beginning of snapshot creation compared to dirty page logging
+ * mechanism, which effectively results in that saved snapshot is the state of VM
+ * at the end of the process.
+ */
+static void *bg_migration_thread(void *opaque)
+{
+ MigrationState *s = opaque;
+ int64_t setup_start;
+ MigThrError thr_error;
+ QEMUFile *fb;
+ bool early_fail = true;
+
+ rcu_register_thread();
+ object_ref(OBJECT(s));
+
+ qemu_file_set_rate_limit(s->to_dst_file, INT64_MAX);
+
+ setup_start = qemu_clock_get_ms(QEMU_CLOCK_HOST);
+ /*
+ * We want to save vmstate for the moment when migration has been
+ * initiated but also we want to save RAM content while VM is running.
+ * The RAM content should appear first in the vmstate. So, we first
+ * stash the non-RAM part of the vmstate to the temporary buffer,
+ * then write RAM part of the vmstate to the migration stream
+ * with vCPUs running and, finally, write stashed non-RAM part of
+ * the vmstate from the buffer to the migration stream.
+ */
+ s->bioc = qio_channel_buffer_new(128 * 1024);
+ qio_channel_set_name(QIO_CHANNEL(s->bioc), "vmstate-buffer");
+ fb = qemu_fopen_channel_output(QIO_CHANNEL(s->bioc));
+ object_unref(OBJECT(s->bioc));
+
+ update_iteration_initial_status(s);
+
+ qemu_savevm_state_header(s->to_dst_file);
+ qemu_savevm_state_setup(s->to_dst_file);
+
+ if (qemu_savevm_state_guest_unplug_pending()) {
+ migrate_set_state(&s->state, MIGRATION_STATUS_SETUP,
+ MIGRATION_STATUS_WAIT_UNPLUG);
+
+ while (s->state == MIGRATION_STATUS_WAIT_UNPLUG &&
+ qemu_savevm_state_guest_unplug_pending()) {
+ qemu_sem_timedwait(&s->wait_unplug_sem, 250);
+ }
+
+ migrate_set_state(&s->state, MIGRATION_STATUS_WAIT_UNPLUG,
+ MIGRATION_STATUS_ACTIVE);
+ } else {
+ migrate_set_state(&s->state, MIGRATION_STATUS_SETUP,
+ MIGRATION_STATUS_ACTIVE);
+ }
+ s->setup_time = qemu_clock_get_ms(QEMU_CLOCK_HOST) - setup_start;
+
+ trace_migration_thread_setup_complete();
+ s->downtime_start = qemu_clock_get_ms(QEMU_CLOCK_REALTIME);
+
+ qemu_mutex_lock_iothread();
+
+ /*
+ * If VM is currently in suspended state, then, to make a valid runstate
+ * transition in vm_stop_force_state() we need to wakeup it up.
+ */
+ qemu_system_wakeup_request(QEMU_WAKEUP_REASON_OTHER, NULL);
+ s->vm_was_running = runstate_is_running();
+
+ if (global_state_store()) {
+ goto fail;
+ }
+ /* Forcibly stop VM before saving state of vCPUs and devices */
+ if (vm_stop_force_state(RUN_STATE_PAUSED)) {
+ goto fail;
+ }
+ /*
+ * Put vCPUs in sync with shadow context structures, then
+ * save their state to channel-buffer along with devices.
+ */
+ cpu_synchronize_all_states();
+ if (qemu_savevm_state_complete_precopy_non_iterable(fb, false, false)) {
+ goto fail;
+ }
+ /* Now initialize UFFD context and start tracking RAM writes */
+ if (ram_write_tracking_start()) {
+ goto fail;
+ }
+ early_fail = false;
+
+ /*
+ * Start VM from BH handler to avoid write-fault lock here.
+ * UFFD-WP protection for the whole RAM is already enabled so
+ * calling VM state change notifiers from vm_start() would initiate
+ * writes to virtio VQs memory which is in write-protected region.
+ */
+ s->vm_start_bh = qemu_bh_new(bg_migration_vm_start_bh, s);
+ qemu_bh_schedule(s->vm_start_bh);
+
+ qemu_mutex_unlock_iothread();
+
+ while (migration_is_active(s)) {
+ MigIterateState iter_state = bg_migration_iteration_run(s);
+ if (iter_state == MIG_ITERATE_SKIP) {
+ continue;
+ } else if (iter_state == MIG_ITERATE_BREAK) {
+ break;
+ }
+
+ /*
+ * Try to detect any kind of failures, and see whether we
+ * should stop the migration now.
+ */
+ thr_error = migration_detect_error(s);
+ if (thr_error == MIG_THR_ERR_FATAL) {
+ /* Stop migration */
+ break;
+ }
+
+ migration_update_counters(s, qemu_clock_get_ms(QEMU_CLOCK_REALTIME));
+ }
+
+ trace_migration_thread_after_loop();
+
+fail:
+ if (early_fail) {
+ migrate_set_state(&s->state, MIGRATION_STATUS_ACTIVE,
+ MIGRATION_STATUS_FAILED);
+ qemu_mutex_unlock_iothread();
+ }
+
+ bg_migration_iteration_finish(s);
+
+ qemu_fclose(fb);
+ object_unref(OBJECT(s));
+ rcu_unregister_thread();
+
+ return NULL;
+}
+
void migrate_fd_connect(MigrationState *s, Error *error_in)
{
Error *local_err = NULL;
@@ -3783,8 +4020,14 @@ void migrate_fd_connect(MigrationState *s, Error *error_in)
migrate_fd_cleanup(s);
return;
}
- qemu_thread_create(&s->thread, "live_migration", migration_thread, s,
- QEMU_THREAD_JOINABLE);
+
+ if (migrate_background_snapshot()) {
+ qemu_thread_create(&s->thread, "bg_snapshot",
+ bg_migration_thread, s, QEMU_THREAD_JOINABLE);
+ } else {
+ qemu_thread_create(&s->thread, "live_migration",
+ migration_thread, s, QEMU_THREAD_JOINABLE);
+ }
s->migration_thread_running = true;
}
@@ -20,6 +20,7 @@
#include "qemu/thread.h"
#include "qemu/coroutine_int.h"
#include "io/channel.h"
+#include "io/channel-buffer.h"
#include "net/announce.h"
#include "qom/object.h"
@@ -147,8 +148,10 @@ struct MigrationState {
/*< public >*/
QemuThread thread;
+ QEMUBH *vm_start_bh;
QEMUBH *cleanup_bh;
QEMUFile *to_dst_file;
+ QIOChannelBuffer *bioc;
/*
* Protects to_dst_file pointer. We need to make sure we won't
* yield or hang during the critical section, since this lock will
@@ -1355,7 +1355,6 @@ int qemu_savevm_state_complete_precopy_iterable(QEMUFile *f, bool in_postcopy)
return 0;
}
-static
int qemu_savevm_state_complete_precopy_non_iterable(QEMUFile *f,
bool in_postcopy,
bool inactivate_disks)
@@ -64,5 +64,7 @@ int qemu_loadvm_state(QEMUFile *f);
void qemu_loadvm_state_cleanup(void);
int qemu_loadvm_state_main(QEMUFile *f, MigrationIncomingState *mis);
int qemu_load_device_state(QEMUFile *f);
+int qemu_savevm_state_complete_precopy_non_iterable(QEMUFile *f,
+ bool in_postcopy, bool inactivate_disks);
#endif