From a2326705e5a6bb21338b3d84f1b0e0b4f46cbc82 Mon Sep 17 00:00:00 2001
From: Peter Xu <peterx@redhat.com>
Date: Tue, 24 Oct 2023 12:39:33 -0400
Subject: [PATCH] migration: Stop migration immediately in RDMA error paths

In multiple places, RDMA errors are handled in a strange way, where it only
sets qemu_file_set_error() but not stop the migration immediately.

It's not obvious what will happen later if there is already an error.  Make
all such failures stop migration immediately.

Cc: Zhijian Li (Fujitsu) <lizhijian@fujitsu.com>
Cc: Markus Armbruster <armbru@redhat.com>
Cc: Juan Quintela <quintela@redhat.com>
Cc: Fabiano Rosas <farosas@suse.de>
Reported-by: Thomas Huth <thuth@redhat.com>
Signed-off-by: Peter Xu <peterx@redhat.com>
Reviewed-by: Juan Quintela <quintela@redhat.com>
Reviewed-by: Fabiano Rosas <farosas@suse.de>
Signed-off-by: Juan Quintela <quintela@redhat.com>
Message-ID: <20231024163933.516546-1-peterx@redhat.com>
---
 migration/ram.c | 21 ++++++++++-----------
 1 file changed, 10 insertions(+), 11 deletions(-)

diff --git a/migration/ram.c b/migration/ram.c
index 024dedb6b1..20e6153114 100644
--- a/migration/ram.c
+++ b/migration/ram.c
@@ -2973,11 +2973,13 @@ static int ram_save_setup(QEMUFile *f, void *opaque)
     ret = rdma_registration_start(f, RAM_CONTROL_SETUP);
     if (ret < 0) {
         qemu_file_set_error(f, ret);
+        return ret;
     }
 
     ret = rdma_registration_stop(f, RAM_CONTROL_SETUP);
     if (ret < 0) {
         qemu_file_set_error(f, ret);
+        return ret;
     }
 
     migration_ops = g_malloc0(sizeof(MigrationOps));
@@ -3043,6 +3045,7 @@ static int ram_save_iterate(QEMUFile *f, void *opaque)
         ret = rdma_registration_start(f, RAM_CONTROL_ROUND);
         if (ret < 0) {
             qemu_file_set_error(f, ret);
+            goto out;
         }
 
         t0 = qemu_clock_get_ns(QEMU_CLOCK_REALTIME);
@@ -3147,8 +3150,6 @@ static int ram_save_complete(QEMUFile *f, void *opaque)
     rs->last_stage = !migration_in_colo_state();
 
     WITH_RCU_READ_LOCK_GUARD() {
-        int rdma_reg_ret;
-
         if (!migration_in_postcopy()) {
             migration_bitmap_sync_precopy(rs, true);
         }
@@ -3156,6 +3157,7 @@ static int ram_save_complete(QEMUFile *f, void *opaque)
         ret = rdma_registration_start(f, RAM_CONTROL_FINISH);
         if (ret < 0) {
             qemu_file_set_error(f, ret);
+            return ret;
         }
 
         /* try transferring iterative blocks of memory */
@@ -3171,24 +3173,21 @@ static int ram_save_complete(QEMUFile *f, void *opaque)
                 break;
             }
             if (pages < 0) {
-                ret = pages;
-                break;
+                qemu_mutex_unlock(&rs->bitmap_mutex);
+                return pages;
             }
         }
         qemu_mutex_unlock(&rs->bitmap_mutex);
 
         compress_flush_data();
 
-        rdma_reg_ret = rdma_registration_stop(f, RAM_CONTROL_FINISH);
-        if (rdma_reg_ret < 0) {
-            qemu_file_set_error(f, rdma_reg_ret);
+        ret = rdma_registration_stop(f, RAM_CONTROL_FINISH);
+        if (ret < 0) {
+            qemu_file_set_error(f, ret);
+            return ret;
         }
     }
 
-    if (ret < 0) {
-        return ret;
-    }
-
     ret = multifd_send_sync_main(rs->pss[RAM_CHANNEL_PRECOPY].pss_channel);
     if (ret < 0) {
         return ret;