[Qemu-devel] [PATCH v7 38/42] Start up a postcopy/listener thread ready for incoming page data

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

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

The loading of a device state (during postcopy) may access guest
memory that's still on the source machine and thus might need
a page fill; split off a separate thread that handles the incoming
page data so that the original incoming migration code can finish
off the device data.

Signed-off-by: Dr. David Alan Gilbert <dgilbert@redhat.com>
---
 include/migration/migration.h |  4 +++
 migration/migration.c         |  6 ++++
 migration/savevm.c            | 79 ++++++++++++++++++++++++++++++++++++++++++-
 trace-events                  |  2 ++
 4 files changed, 90 insertions(+), 1 deletion(-)

diff --git a/include/migration/migration.h b/include/migration/migration.h
index 4f954ca..da6529d 100644
--- a/include/migration/migration.h
+++ b/include/migration/migration.h
@@ -75,6 +75,10 @@ struct MigrationIncomingState {
     QemuThread     fault_thread;
     QemuSemaphore  fault_thread_sem;
 
+    bool           have_listen_thread;
+    QemuThread     listen_thread;
+    QemuSemaphore  listen_thread_sem;
+
     /* For the kernel to send us notifications */
     int            userfault_fd;
     /* To tell the fault_thread to quit */
diff --git a/migration/migration.c b/migration/migration.c
index 7fa982e..e908b50 100644
--- a/migration/migration.c
+++ b/migration/migration.c
@@ -1222,6 +1222,12 @@ static int postcopy_start(MigrationState *ms, bool *old_vm_running)
         goto fail;
     }
 
+    /*
+     * Make sure the receiver can get incoming pages before we send the rest
+     * of the state
+     */
+    qemu_savevm_send_postcopy_listen(fb);
+
     qemu_savevm_state_complete_precopy(fb);
     qemu_savevm_send_ping(fb, 3);
 
diff --git a/migration/savevm.c b/migration/savevm.c
index b87238a..258c551 100644
--- a/migration/savevm.c
+++ b/migration/savevm.c
@@ -1314,6 +1314,65 @@ static int loadvm_postcopy_ram_handle_discard(MigrationIncomingState *mis,
     return 0;
 }
 
+/*
+ * Triggered by a postcopy_listen command; this thread takes over reading
+ * the input stream, leaving the main thread free to carry on loading the rest
+ * of the device state (from RAM).
+ * (TODO:This could do with being in a postcopy file - but there again it's
+ * just another input loop, not that postcopy specific)
+ */
+static void *postcopy_ram_listen_thread(void *opaque)
+{
+    QEMUFile *f = opaque;
+    MigrationIncomingState *mis = migration_incoming_get_current();
+    int load_res;
+
+    qemu_sem_post(&mis->listen_thread_sem);
+    trace_postcopy_ram_listen_thread_start();
+
+    /*
+     * Because we're a thread and not a coroutine we can't yield
+     * in qemu_file, and thus we must be blocking now.
+     */
+    qemu_file_change_blocking(f, true);
+    load_res = qemu_loadvm_state_main(f, mis);
+    /* And non-blocking again so we don't block in any cleanup */
+    qemu_file_change_blocking(f, false);
+
+    trace_postcopy_ram_listen_thread_exit();
+    if (load_res < 0) {
+        error_report("%s: loadvm failed: %d", __func__, load_res);
+        qemu_file_set_error(f, load_res);
+    } else {
+        /*
+         * This looks good, but it's possible that the device loading in the
+         * main thread hasn't finished yet, and so we might not be in 'RUN'
+         * state yet; wait for the end of the main thread.
+         */
+        qemu_event_wait(&mis->main_thread_load_event);
+    }
+    postcopy_ram_incoming_cleanup(mis);
+    /*
+     * If everything has worked fine, then the main thread has waited
+     * for us to start, and we're the last use of the mis.
+     * (If something broke then qemu will have to exit anyway since it's
+     * got a bad migration state).
+     */
+    migration_incoming_state_destroy();
+
+    if (load_res < 0) {
+        /*
+         * If something went wrong then we have a bad state so exit;
+         * depending how far we got it might be possible at this point
+         * to leave the guest running and fire MCEs for pages that never
+         * arrived as a desperate recovery step.
+         */
+        exit(EXIT_FAILURE);
+    }
+
+    return NULL;
+}
+
 /* After this message we must be able to immediately receive postcopy data */
 static int loadvm_postcopy_handle_listen(MigrationIncomingState *mis)
 {
@@ -1333,7 +1392,20 @@ static int loadvm_postcopy_handle_listen(MigrationIncomingState *mis)
         return -1;
     }
 
-    /* TODO start up the postcopy listening thread */
+    if (mis->have_listen_thread) {
+        error_report("CMD_POSTCOPY_RAM_LISTEN already has a listen thread");
+        return -1;
+    }
+
+    mis->have_listen_thread = true;
+    /* Start up the listening thread and wait for it to signal ready */
+    qemu_sem_init(&mis->listen_thread_sem, 0);
+    qemu_thread_create(&mis->listen_thread, "postcopy/listen",
+                       postcopy_ram_listen_thread, mis->file,
+                       QEMU_THREAD_JOINABLE);
+    qemu_sem_wait(&mis->listen_thread_sem);
+    qemu_sem_destroy(&mis->listen_thread_sem);
+
     return 0;
 }
 
@@ -1657,6 +1729,11 @@ int qemu_loadvm_state(QEMUFile *f)
     qemu_event_set(&mis->main_thread_load_event);
 
     trace_qemu_loadvm_state_post_main(ret);
+    if (mis->have_listen_thread) {
+        /* Listen thread still going, can't clean up yet */
+        return ret;
+    }
+
     if (ret == 0) {
         int file_error_after_eof = qemu_file_get_error(f);
 
diff --git a/trace-events b/trace-events
index ab201f9..a6c7839 100644
--- a/trace-events
+++ b/trace-events
@@ -1199,6 +1199,8 @@ loadvm_postcopy_ram_handle_discard_end(void) ""
 loadvm_postcopy_ram_handle_discard_header(const char *ramid, uint16_t len) "%s: %ud"
 loadvm_process_command(uint16_t com, uint16_t len) "com=0x%x len=%d"
 loadvm_process_command_ping(uint32_t val) "%x"
+postcopy_ram_listen_thread_exit(void) ""
+postcopy_ram_listen_thread_start(void) ""
 qemu_savevm_send_postcopy_advise(void) ""
 qemu_savevm_send_postcopy_ram_discard(const char *id, uint16_t len) "%s: %ud"
 savevm_section_start(const char *id, unsigned int section_id) "%s, section_id %u"
-- 
2.4.3