migration/multifd: Terminate the TLS connection

The multifd recv side has been getting a TLS error of
GNUTLS_E_PREMATURE_TERMINATION at the end of migration when the send
side closes the sockets without ending the TLS session. This has been
masked by the code not checking the migration error after loadvm.

Start ending the TLS session at multifd_send_shutdown() so the recv
side always sees a clean termination (EOF) and we can start to
differentiate that from an actual premature termination that might
possibly happen in the middle of the migration.

There's nothing to be done if a previous migration error has already
broken the connection, so add a comment explaining it and ignore any
errors coming from gnutls_bye().

This doesn't break compat with older recv-side QEMUs because EOF has
always caused the recv thread to exit cleanly.

Reviewed-by: Peter Xu <peterx@redhat.com>
Signed-off-by: Fabiano Rosas <farosas@suse.de>

diff --git a/migration/multifd.c b/migration/multifd.c
index ab73d6d984cf56fdcac3959ca719067d4bc289d0..0296758c08208afc4503257b7e73ba4e8ccef811 100644 (file)
--- a/migration/multifd.c
+++ b/migration/multifd.c
@@ -490,6 +490,36 @@ void multifd_send_shutdown(void)
         return;
     }
 
+    for (i = 0; i < migrate_multifd_channels(); i++) {
+        MultiFDSendParams *p = &multifd_send_state->params[i];
+
+        /* thread_created implies the TLS handshake has succeeded */
+        if (p->tls_thread_created && p->thread_created) {
+            Error *local_err = NULL;
+            /*
+             * The destination expects the TLS session to always be
+             * properly terminated. This helps to detect a premature
+             * termination in the middle of the stream.  Note that
+             * older QEMUs always break the connection on the source
+             * and the destination always sees
+             * GNUTLS_E_PREMATURE_TERMINATION.
+             */
+            migration_tls_channel_end(p->c, &local_err);
+
+            /*
+             * The above can return an error in case the migration has
+             * already failed. If the migration succeeded, errors are
+             * not expected but there's no need to kill the source.
+             */
+            if (local_err && !migration_has_failed(migrate_get_current())) {
+                warn_report(
+                    "multifd_send_%d: Failed to terminate TLS connection: %s",
+                    p->id, error_get_pretty(local_err));
+                break;
+            }
+        }
+    }
+
     multifd_send_terminate_threads();
 
     for (i = 0; i < migrate_multifd_channels(); i++) {
@@ -1141,7 +1171,13 @@ static void *multifd_recv_thread(void *opaque)
 
             ret = qio_channel_read_all_eof(p->c, (void *)p->packet,
                                            p->packet_len, &local_err);
-            if (ret == 0 || ret == -1) {   /* 0: EOF  -1: Error */
+            if (!ret) {
+                /* EOF */
+                assert(!local_err);
+                break;
+            }
+
+            if (ret == -1) {
                 break;
             }
 

diff --git a/migration/tls.c b/migration/tls.c
index fa03d9136ca3201ee362e54333037e6740f9f2dc..5cbf952383691d9311936b810f4d738725df44f9 100644 (file)
--- a/migration/tls.c
+++ b/migration/tls.c
@@ -156,6 +156,11 @@ void migration_tls_channel_connect(MigrationState *s,
                               NULL);
 }
 
+void migration_tls_channel_end(QIOChannel *ioc, Error **errp)
+{
+    qio_channel_tls_bye(QIO_CHANNEL_TLS(ioc), errp);
+}
+
 bool migrate_channel_requires_tls_upgrade(QIOChannel *ioc)
 {
     if (!migrate_tls()) {

diff --git a/migration/tls.h b/migration/tls.h
index 5797d153cb01d620b1e83190c0f4d9dee3124fe0..58b25e12281cef1ff97493f713ae5821191cc951 100644 (file)
--- a/migration/tls.h
+++ b/migration/tls.h
@@ -36,7 +36,7 @@ void migration_tls_channel_connect(MigrationState *s,
                                    QIOChannel *ioc,
                                    const char *hostname,
                                    Error **errp);
-
+void migration_tls_channel_end(QIOChannel *ioc, Error **errp);
 /* Whether the QIO channel requires further TLS handshake? */
 bool migrate_channel_requires_tls_upgrade(QIOChannel *ioc);