commit 4ce56229087860805877075ddb29dd44578365a9
author Fabiano Rosas <farosas@suse.de> Tue Sep 17 15:58:02 2024 -0300
committer Peter Xu <peterx@redhat.com> Wed Sep 18 14:27:39 2024 -0400
tree 71a450828f48ea21f0cc805a3ce8ffdccd2bab7f
parent 90a384d461af79c8948f1150523f868ef4862573

migration/multifd: Fix rb->receivedmap cleanup race

Fix a segmentation fault in multifd when rb->receivedmap is cleared
too early.

After commit 5ef7e26bdb ("migration/multifd: solve zero page causing
multiple page faults"), multifd started using the rb->receivedmap
bitmap, which belongs to ram.c and is initialized and *freed* from the
ram SaveVMHandlers.

Multifd threads are live until migration_incoming_state_destroy(),
which is called after qemu_loadvm_state_cleanup(), leading to a crash
when accessing rb->receivedmap.

process_incoming_migration_co()        ...
  qemu_loadvm_state()                  multifd_nocomp_recv()
    qemu_loadvm_state_cleanup()          ramblock_recv_bitmap_set_offset()
      rb->receivedmap = NULL               set_bit_atomic(..., rb->receivedmap)
  ...
  migration_incoming_state_destroy()
    multifd_recv_cleanup()
      multifd_recv_terminate_threads(NULL)

Move the loadvm cleanup into migration_incoming_state_destroy(), after
multifd_recv_cleanup() to ensure multifd threads have already exited
when rb->receivedmap is cleared.

Adjust the postcopy listen thread comment to indicate that we still
want to skip the cpu synchronization.

CC: qemu-stable@nongnu.org
Fixes: 5ef7e26bdb ("migration/multifd: solve zero page causing multiple page faults")
Signed-off-by: Fabiano Rosas <farosas@suse.de>
Link: https://lore.kernel.org/r/20240917185802.15619-3-farosas@suse.de
[peterx: added comment in migration_incoming_state_destroy()]
Signed-off-by: Peter Xu <peterx@redhat.com>

migration/migration.c

diff --git a/migration/migration.c b/migration/migration.c
index 3dea06d..ae2be31 100644
--- a/migration/migration.c
+++ b/migration/migration.c
@@ -378,6 +378,11 @@
     struct MigrationIncomingState *mis = migration_incoming_get_current();
 
     multifd_recv_cleanup();
+    /*
+     * RAM state cleanup needs to happen after multifd cleanup, because
+     * multifd threads can use some of its states (receivedmap).
+     */
+    qemu_loadvm_state_cleanup();
 
     if (mis->to_src_file) {
         /* Tell source that we are done */

migration/savevm.c

diff --git a/migration/savevm.c b/migration/savevm.c
index d075969..7e1e271 100644
--- a/migration/savevm.c
+++ b/migration/savevm.c
@@ -2979,7 +2979,10 @@
     trace_qemu_loadvm_state_post_main(ret);
 
     if (mis->have_listen_thread) {
-        /* Listen thread still going, can't clean up yet */
+        /*
+         * Postcopy listen thread still going, don't synchronize the
+         * cpus yet.
+         */
         return ret;
     }
 
@@ -3022,7 +3025,6 @@
         }
     }
 
-    qemu_loadvm_state_cleanup();
     cpu_synchronize_all_post_init();
 
     return ret;