Merge tag 'migration-20250310-pull-request' of https://gitlab.com/farosas/qemu into staging

Migration pull request

- Fix use-after-free in incoming migration
- Improve cpr migration blocker for volatile ram
- Fix RDMA migration

# -----BEGIN PGP SIGNATURE-----
#
# iQJEBAABCAAuFiEEqhtIsKIjJqWkw2TPx5jcdBvsMZ0FAmfPaCAQHGZhcm9zYXNA
# c3VzZS5kZQAKCRDHmNx0G+wxnQy9EADRp/6GaSzoqWgafU8DGM5Q69HyKiZ888DZ
# 7qXqJeH3c95nvOnIw2BMhUYX4t8kkAbUcWlr7L8KCjZT/6N/d1/Z5fimqymRkw4x
# +8kDyADv5FY0339aMLf3qBbIAQj/gvPvg8H+e+hXfokZqoYgLXZ0eqNAz8MjIcyN
# +A+waEBMLNvTgZyTQl2TbCvb+mbRial8u8C9BIoILhn/gNuoMX7lbt0tq41HZwe0
# l3v16jnXlsDvQUXp99bGySomRgkcYqdAt+HWHLje3frT/Ap8dGaUJKlpgJ8DXJiA
# fV1reKihJdj37q9GSG8cR02W+ATBesiecufV4TUPNQYQzTdxn3fOMwdc3Pck074D
# YAQxFT20OPou+NRxjYoHT/GqFUY36/2qBJpt7TY3ramdklHJhXpRyedK4rppTZNn
# pC3lnbpA/LHRmfD1Nh0CRmqZpbV+qW1BWEgMwk4qui46BxYWHxKHFpxAuwlJQmcw
# RxY8qPhIXQM03tiTgIddBNDZLoVqRoUP7YpzR7MMa1rz0T5inNFMcNGm72WpKODE
# rzpw4ezXO7+D4/QmMq3PoPfhFv3QFnH6jaGj8JkJM378KLvh4fQ0woXtDKFl4Tbq
# 1oBZ17WUv6aHr75b+KMyKJNLinvMu5WF5WoRYIt1lNXaqk7I494yvIjtRrimWZIS
# Z5Q0tpUmpw==
# =yEH0
# -----END PGP SIGNATURE-----
# gpg: Signature made Tue 11 Mar 2025 06:30:56 HKT
# gpg:                using RSA key AA1B48B0A22326A5A4C364CFC798DC741BEC319D
# gpg:                issuer "farosas@suse.de"
# gpg: Good signature from "Fabiano Rosas <farosas@suse.de>" [unknown]
# gpg:                 aka "Fabiano Almeida Rosas <fabiano.rosas@suse.com>" [unknown]
# gpg: WARNING: The key's User ID is not certified with a trusted signature!
# gpg:          There is no indication that the signature belongs to the owner.
# Primary key fingerprint: AA1B 48B0 A223 26A5 A4C3  64CF C798 DC74 1BEC 319D

* tag 'migration-20250310-pull-request' of https://gitlab.com/farosas/qemu:
  migration: Prioritize RDMA in ram_save_target_page()
  migration: ram block cpr blockers
  migration: Fix UAF for incoming migration on MigrationState

Signed-off-by: Stefan Hajnoczi <stefanha@redhat.com>

1 files changed, 38 insertions, 2 deletions

diff --git a/migration/migration.c b/migration/migration.c
index 1833cfe358..d46e776e24 100644
--- a/migration/migration.c
+++ b/migration/migration.c
@@ -116,6 +116,27 @@ static void migration_downtime_start(MigrationState *s)
     s->downtime_start = qemu_clock_get_ms(QEMU_CLOCK_REALTIME);
 }
 
+/*
+ * This is unfortunate: incoming migration actually needs the outgoing
+ * migration state (MigrationState) to be there too, e.g. to query
+ * capabilities, parameters, using locks, setup errors, etc.
+ *
+ * NOTE: when calling this, making sure current_migration exists and not
+ * been freed yet!  Otherwise trying to access the refcount is already
+ * an use-after-free itself..
+ *
+ * TODO: Move shared part of incoming / outgoing out into separate object.
+ * Then this is not needed.
+ */
+static void migrate_incoming_ref_outgoing_state(void)
+{
+    object_ref(migrate_get_current());
+}
+static void migrate_incoming_unref_outgoing_state(void)
+{
+    object_unref(migrate_get_current());
+}
+
 static void migration_downtime_end(MigrationState *s)
 {
     int64_t now = qemu_clock_get_ms(QEMU_CLOCK_REALTIME);
@@ -863,7 +884,7 @@ process_incoming_migration_co(void *opaque)
              * postcopy thread.
              */
             trace_process_incoming_migration_co_postcopy_end_main();
-            return;
+            goto out;
         }
         /* Else if something went wrong then just fall out of the normal exit */
     }
@@ -879,7 +900,8 @@ process_incoming_migration_co(void *opaque)
     }
 
     migration_bh_schedule(process_incoming_migration_bh, mis);
-    return;
+    goto out;
+
 fail:
     migrate_set_state(&mis->state, MIGRATION_STATUS_ACTIVE,
                       MIGRATION_STATUS_FAILED);
@@ -896,6 +918,9 @@ fail:
 
         exit(EXIT_FAILURE);
     }
+out:
+    /* Pairs with the refcount taken in qmp_migrate_incoming() */
+    migrate_incoming_unref_outgoing_state();
 }
 
 /**
@@ -1901,6 +1926,17 @@ void qmp_migrate_incoming(const char *uri, bool has_channels,
         return;
     }
 
+    /*
+     * Making sure MigrationState is available until incoming migration
+     * completes.
+     *
+     * NOTE: QEMU _might_ leak this refcount in some failure paths, but
+     * that's OK.  This is the minimum change we need to at least making
+     * sure success case is clean on the refcount.  We can try harder to
+     * make it accurate for any kind of failures, but it might be an
+     * overkill and doesn't bring us much benefit.
+     */
+    migrate_incoming_ref_outgoing_state();
     once = false;
 }