[PATCH 4/7] Implementation of write-tracking migration thread.

[Andrey Gruzdev]

Signed-off-by: Andrey Gruzdev <andrey.gruzdev@virtuozzo.com>
---
 migration/migration.c | 174 +++++++++++++++++++++++++++++++++++++++++-
 migration/migration.h |   3 +
 migration/savevm.c    |   1 -
 migration/savevm.h    |   2 +
 4 files changed, 177 insertions(+), 3 deletions(-)

diff --git a/migration/migration.c b/migration/migration.c
index ff0364dde0..1ffbb4ce4a 100644
--- a/migration/migration.c
+++ b/migration/migration.c
@@ -2013,6 +2013,7 @@ void migrate_init(MigrationState *s)
      * locks.
      */
     s->cleanup_bh = 0;
+    s->wt_vm_start_bh = 0;
     s->to_dst_file = NULL;
     s->state = MIGRATION_STATUS_NONE;
     s->rp_state.from_dst_file = NULL;
@@ -3551,6 +3552,21 @@ static void migration_iteration_finish(MigrationState *s)
     qemu_mutex_unlock_iothread();
 }
 
+static void wt_migration_iteration_finish(MigrationState *s)
+{
+    /* TODO: implement */
+}
+
+/*
+ * Return true if continue to the next iteration directly, false
+ * otherwise.
+ */
+static MigIterateState wt_migration_iteration_run(MigrationState *s)
+{
+    /* TODO: implement */
+    return MIG_ITERATE_RESUME;
+}
+
 void migration_make_urgent_request(void)
 {
     qemu_sem_post(&migrate_get_current()->rate_limit_sem);
@@ -3698,6 +3714,154 @@ static void *migration_thread(void *opaque)
     return NULL;
 }
 
+static void wt_migration_vm_start_bh(void *opaque)
+{
+    /* TODO: implement */
+}
+
+/*
+ * Master migration thread on the source VM.
+ * This is an alternative implementation of live migration
+ * which uses userfault_fd write protection mechanism introduced in
+ * 5.7 kernel. Compared to existing dirty page logging migration
+ * it produces much lesser traffic and smaller snapshot images since
+ * no page duplicates can get into the stream. Another the key point
+ * is that generated vmstate stream reflects machine state 'frozen'
+ * at the beginning of migration compared to dirty page logging
+ * mechanism, which effectively results in that saved snapshot is the
+ * state at the end of migration process.
+ */
+static void *wt_migration_thread(void *opaque)
+{
+    MigrationState *s = opaque;
+    int64_t setup_start;
+    MigThrError thr_error;
+    QEMUFile *fb;
+
+    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);
+    }
+    s->setup_time = qemu_clock_get_ms(QEMU_CLOCK_HOST) - setup_start;
+
+    migrate_set_state(&s->state, MIGRATION_STATUS_SETUP,
+                      MIGRATION_STATUS_ACTIVE);
+    trace_migration_thread_setup_complete();
+    s->downtime_start = qemu_clock_get_ms(QEMU_CLOCK_REALTIME);
+
+    qemu_mutex_lock_iothread();
+
+    bool fail_early = false;
+    do {
+        if (global_state_store()) {
+            fail_early = true;
+            break;
+        }
+        /* Forcibly stop VM before saving state of vCPUs and devices */
+        if (vm_stop_force_state(RUN_STATE_PAUSED)) {
+            fail_early = true;
+            break;
+        }
+        /*
+         * 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)) 
{
+            fail_early = true;
+            break;
+        }
+        /* Now initialize UFFD context and start tracking RAM writes */
+        if (ram_write_tracking_start()) {
+            fail_early = true;
+        }
+    } while (false);
+
+    if (fail_early) {
+        migrate_set_state(&s->state, MIGRATION_STATUS_ACTIVE,
+                          MIGRATION_STATUS_FAILED);
+
+        qemu_mutex_unlock_iothread();
+        goto fail;
+    }
+
+    /*
+     * 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->wt_vm_start_bh = qemu_bh_new(wt_migration_vm_start_bh, s);
+    qemu_bh_schedule(s->wt_vm_start_bh);
+
+    qemu_mutex_unlock_iothread();
+
+    while (migration_is_active(s)) {
+        MigIterateState iter_state = wt_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:
+    wt_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;
@@ -3761,8 +3925,14 @@ 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_track_writes_ram()) {
+        qemu_thread_create(&s->thread, "wt_live_migration",
+                wt_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;
 }
 
diff --git a/migration/migration.h b/migration/migration.h
index 339ae720e0..c3b4c7f2fd 100644
--- a/migration/migration.h
+++ b/migration/migration.h
@@ -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 *wt_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
diff --git a/migration/savevm.c b/migration/savevm.c
index 5f937a2762..62d5f8a869 100644
--- a/migration/savevm.c
+++ b/migration/savevm.c
@@ -1352,7 +1352,6 @@ 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)
diff --git a/migration/savevm.h b/migration/savevm.h
index ba64a7e271..aaee2528ed 100644
--- a/migration/savevm.h
+++ b/migration/savevm.h
@@ -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
-- 
2.25.1