[Qemu-devel] [PATCH v6 32/47] Postcopy: Postcopy startup in migration thread

["Dr. David Alan Gilbert (git)" <dgilbert@redhat.com>]

From: "Dr. David Alan Gilbert" <dgilbert@redhat.com>

Rework the migration thread to setup and start postcopy.

Signed-off-by: Dr. David Alan Gilbert <dgilbert@redhat.com>
---
 include/migration/migration.h |   3 +
 migration/migration.c         | 163 ++++++++++++++++++++++++++++++++++++++++--
 trace-events                  |   4 ++
 3 files changed, 165 insertions(+), 5 deletions(-)

diff --git a/include/migration/migration.h b/include/migration/migration.h
index 36451de..c02266e 100644
--- a/include/migration/migration.h
+++ b/include/migration/migration.h
@@ -119,6 +119,9 @@ struct MigrationState
     /* Flag set once the migration has been asked to enter postcopy */
     bool start_postcopy;
 
+    /* Flag set once the migration thread is running (and needs joining) */
+    bool started_migration_thread;
+
     /* bitmap of pages that have been sent at least once
      * only maintained and used in postcopy at the moment
      * where it's used to send the dirtymap at the start
diff --git a/migration/migration.c b/migration/migration.c
index 63205c3..611aca8 100644
--- a/migration/migration.c
+++ b/migration/migration.c
@@ -469,7 +469,10 @@ static void migrate_fd_cleanup(void *opaque)
     if (s->file) {
         trace_migrate_fd_cleanup();
         qemu_mutex_unlock_iothread();
-        qemu_thread_join(&s->thread);
+        if (s->started_migration_thread) {
+            qemu_thread_join(&s->thread);
+            s->started_migration_thread = false;
+        }
         qemu_mutex_lock_iothread();
 
         qemu_fclose(s->file);
@@ -886,7 +889,6 @@ out:
     return NULL;
 }
 
-__attribute__ (( unused )) /* Until later in patch series */
 static int open_return_path_on_source(MigrationState *ms)
 {
 
@@ -925,23 +927,141 @@ static int await_return_path_close_on_source(MigrationState *ms)
 }
 
 /*
+ * Switch from normal iteration to postcopy
+ * Returns non-0 on error
+ */
+static int postcopy_start(MigrationState *ms, bool *old_vm_running)
+{
+    int ret;
+    const QEMUSizedBuffer *qsb;
+    int64_t time_at_stop = qemu_clock_get_ms(QEMU_CLOCK_REALTIME);
+    migrate_set_state(ms, MIGRATION_STATUS_ACTIVE,
+                      MIGRATION_STATUS_POSTCOPY_ACTIVE);
+
+    trace_postcopy_start();
+    qemu_mutex_lock_iothread();
+    trace_postcopy_start_set_run();
+
+    qemu_system_wakeup_request(QEMU_WAKEUP_REASON_OTHER);
+    *old_vm_running = runstate_is_running();
+
+    ret = vm_stop_force_state(RUN_STATE_FINISH_MIGRATE);
+
+    if (ret < 0) {
+        goto fail;
+    }
+
+    /*
+     * in Finish migrate and with the io-lock held everything should
+     * be quiet, but we've potentially still got dirty pages and we
+     * need to tell the destination to throw any pages it's already received
+     * that are dirty
+     */
+    if (ram_postcopy_send_discard_bitmap(ms)) {
+        error_report("postcopy send discard bitmap failed");
+        goto fail;
+    }
+
+    /*
+     * send rest of state - note things that are doing postcopy
+     * will notice we're in POSTCOPY_ACTIVE and not actually
+     * wrap their state up here
+     */
+    qemu_file_set_rate_limit(ms->file, INT64_MAX);
+    /* Ping just for debugging, helps line traces up */
+    qemu_savevm_send_ping(ms->file, 2);
+
+    /*
+     * We need to leave the fd free for page transfers during the
+     * loading of the device state, so wrap all the remaining
+     * commands and state into a package that gets sent in one go
+     */
+    QEMUFile *fb = qemu_bufopen("w", NULL);
+    if (!fb) {
+        error_report("Failed to create buffered file");
+        goto fail;
+    }
+
+    qemu_savevm_state_complete_precopy(fb);
+    qemu_savevm_send_ping(fb, 3);
+
+    qemu_savevm_send_postcopy_run(fb);
+
+    /* <><> end of stuff going into the package */
+    qsb = qemu_buf_get(fb);
+
+    /* Now send that blob */
+    if (qemu_savevm_send_packaged(ms->file, qsb)) {
+        goto fail_closefb;
+    }
+    qemu_fclose(fb);
+    ms->downtime =  qemu_clock_get_ms(QEMU_CLOCK_REALTIME) - time_at_stop;
+
+    qemu_mutex_unlock_iothread();
+
+    /*
+     * Although this ping is just for debug, it could potentially be
+     * used for getting a better measurement of downtime at the source.
+     */
+    qemu_savevm_send_ping(ms->file, 4);
+
+    ret = qemu_file_get_error(ms->file);
+    if (ret) {
+        error_report("postcopy_start: Migration stream errored");
+        migrate_set_state(ms, MIGRATION_STATUS_POSTCOPY_ACTIVE,
+                              MIGRATION_STATUS_FAILED);
+    }
+
+    return ret;
+
+fail_closefb:
+    qemu_fclose(fb);
+fail:
+    migrate_set_state(ms, MIGRATION_STATUS_POSTCOPY_ACTIVE,
+                          MIGRATION_STATUS_FAILED);
+    qemu_mutex_unlock_iothread();
+    return -1;
+}
+
+/*
  * Master migration thread on the source VM.
  * It drives the migration and pumps the data down the outgoing channel.
  */
 static void *migration_thread(void *opaque)
 {
     MigrationState *s = opaque;
+    /* Used by the bandwidth calcs, updated later */
     int64_t initial_time = qemu_clock_get_ms(QEMU_CLOCK_REALTIME);
     int64_t setup_start = qemu_clock_get_ms(QEMU_CLOCK_HOST);
     int64_t initial_bytes = 0;
     int64_t max_size = 0;
     int64_t start_time = initial_time;
     bool old_vm_running = false;
+    bool entered_postcopy = false;
+    /* The active state we expect to be in; ACTIVE or POSTCOPY_ACTIVE */
+    enum MigrationStatus current_active_type = MIGRATION_STATUS_ACTIVE;
 
     qemu_savevm_state_header(s->file);
+
+    if (migrate_postcopy_ram()) {
+        /* Now tell the dest that it should open its end so it can reply */
+        qemu_savevm_send_open_return_path(s->file);
+
+        /* And do a ping that will make stuff easier to debug */
+        qemu_savevm_send_ping(s->file, 1);
+
+        /*
+         * Tell the destination that we *might* want to do postcopy later;
+         * if the other end can't do postcopy it should fail now, nice and
+         * early.
+         */
+        qemu_savevm_send_postcopy_advise(s->file);
+    }
+
     qemu_savevm_state_begin(s->file, &s->params);
 
     s->setup_time = qemu_clock_get_ms(QEMU_CLOCK_HOST) - setup_start;
+    current_active_type = MIGRATION_STATUS_ACTIVE;
     migrate_set_state(s, MIGRATION_STATUS_SETUP, MIGRATION_STATUS_ACTIVE);
 
     trace_migration_thread_setup_complete();
@@ -960,6 +1080,22 @@ static void *migration_thread(void *opaque)
             trace_migrate_pending(pending_size, max_size,
                                   pend_post, pend_nonpost);
             if (pending_size && pending_size >= max_size) {
+                /* Still a significant amount to transfer */
+
+                current_time = qemu_clock_get_ms(QEMU_CLOCK_REALTIME);
+                if (migrate_postcopy_ram() &&
+                    s->state != MIGRATION_STATUS_POSTCOPY_ACTIVE &&
+                    pend_nonpost <= max_size &&
+                    atomic_read(&s->start_postcopy)) {
+
+                    if (!postcopy_start(s, &old_vm_running)) {
+                        current_active_type = MIGRATION_STATUS_POSTCOPY_ACTIVE;
+                        entered_postcopy = true;
+                    }
+
+                    continue;
+                }
+                /* Just another iteration step */
                 qemu_savevm_state_iterate(s->file);
             } else {
                 int ret;
@@ -991,8 +1127,8 @@ static void *migration_thread(void *opaque)
         }
 
         if (qemu_file_get_error(s->file)) {
-            migrate_set_state(s, MIGRATION_STATUS_ACTIVE,
-                              MIGRATION_STATUS_FAILED);
+            migrate_set_state(s, current_active_type, MIGRATION_STATUS_FAILED);
+            trace_migration_thread_file_err();
             break;
         }
         current_time = qemu_clock_get_ms(QEMU_CLOCK_REALTIME);
@@ -1023,12 +1159,15 @@ static void *migration_thread(void *opaque)
         }
     }
 
+    trace_migration_thread_after_loop();
     qemu_mutex_lock_iothread();
     if (s->state == MIGRATION_STATUS_COMPLETED) {
         int64_t end_time = qemu_clock_get_ms(QEMU_CLOCK_REALTIME);
         uint64_t transferred_bytes = qemu_ftell(s->file);
         s->total_time = end_time - s->total_time;
-        s->downtime = end_time - start_time;
+        if (!entered_postcopy) {
+            s->downtime = end_time - start_time;
+        }
         if (s->total_time) {
             s->mbps = (((double) transferred_bytes * 8.0) /
                        ((double) s->total_time)) / 1000;
@@ -1060,8 +1199,22 @@ void migrate_fd_connect(MigrationState *s)
     /* Notify before starting migration thread */
     notifier_list_notify(&migration_state_notifiers, s);
 
+    /* Open the return path; currently for postcopy but other things might
+     * also want it.
+     */
+    if (migrate_postcopy_ram()) {
+        if (open_return_path_on_source(s)) {
+            error_report("Unable to open return-path for postcopy");
+            migrate_set_state(s, MIGRATION_STATUS_SETUP,
+                              MIGRATION_STATUS_FAILED);
+            migrate_fd_cleanup(s);
+            return;
+        }
+    }
+
     qemu_thread_create(&s->thread, "migration", migration_thread, s,
                        QEMU_THREAD_JOINABLE);
+    s->started_migration_thread = true;
 }
 
 PostcopyState  postcopy_state_get(MigrationIncomingState *mis)
diff --git a/trace-events b/trace-events
index b2099ee..efee724 100644
--- a/trace-events
+++ b/trace-events
@@ -1406,9 +1406,13 @@ migrate_fd_error(void) ""
 migrate_fd_cancel(void) ""
 migrate_pending(uint64_t size, uint64_t max, uint64_t post, uint64_t nonpost) "pending size %" PRIu64 " max %" PRIu64 " (post=%" PRIu64 " nonpost=%" PRIu64 ")"
 migrate_send_rp_message(int msg_type, uint16_t len) "%d: len %d"
+migration_thread_after_loop(void) ""
+migration_thread_file_err(void) ""
 migration_thread_setup_complete(void) ""
 open_return_path_on_source(void) ""
 open_return_path_on_source_continue(void) ""
+postcopy_start(void) ""
+postcopy_start_set_run(void) ""
 source_return_path_thread_bad_end(void) ""
 source_return_path_thread_end(void) ""
 source_return_path_thread_entry(void) ""
-- 
2.1.0