[PATCH QEMU HCI-8.1 v3 14/28] migration: yank: Move register instance earlier

[Andrey Drobyshev <andrey.drobyshev@virtuozzo.com>]

From: Fabiano Rosas <farosas@suse.de>

Move the register_instance call to migrate_prepare() so it can be
paired with the unregister_instance at migration_cleanup(). Otherwise,
the cleanup cannot be run when cpr_state_save() fails because the
instance is registered only after it.

When resuming from a paused postcopy migration, migrate_prepare()
returns early, but migration_cleanup() doesn't run, so the yank will
remain paired.

andrey.drobyshev:
    This commit was cherry-picked from the upstream commit 7e714392437c,
    adapted for the hci-dev base, which predates the upstream
    migration_connect_set_error() -> migration_connect_error_propagate()
    rename (77c82edadbe0): the error propagation calls in qmp_migrate()
    and qmp_migrate_finish() keep the older spelling.

    Also fixed here: upstream left the yank instance registered when
    qmp_migrate_finish() fails before connecting (nothing calls
    migration_cleanup() then), so the next migrate command aborted on
    yank_register_instance(&error_abort); and the unregister at the out:
    label ran on a resume, which never registered the instance.  Upstream
    fixed both in 6b587af5ec9d ("migration: Fold migration_cleanup() into
    migration_connect_error_propagate()"), which needs the above rework;
    this is the equivalent for our base.

    Also refuse migrate while an incoming postcopy migration is still in
    progress: the guest already runs then, but the incoming side still
    holds the yank instance, so registering it with &error_abort would
    abort QEMU.

Reviewed-by: Peter Xu <peterx@redhat.com>
Reviewed-by: Prasad Pandit <pjp@fedoraproject.org>
Link: https://lore.kernel.org/qemu-devel/20260123141656.6765-11-farosas@suse.de
Signed-off-by: Fabiano Rosas <farosas@suse.de>
---
 migration/migration.c | 40 ++++++++++++++++++++++++----------------
 1 file changed, 24 insertions(+), 16 deletions(-)

diff --git a/migration/migration.c b/migration/migration.c
index 2f8ef20c036..0b830956532 100644
--- a/migration/migration.c
+++ b/migration/migration.c
@@ -2174,6 +2174,15 @@ static bool migrate_prepare(MigrationState *s, bool resume, Error **errp)
         return false;
     }
 
+    /*
+     * The guest already runs during incoming postcopy, but the incoming
+     * migration still holds the yank instance registered below.
+     */
+    if (migration_incoming_postcopy_advised()) {
+        error_setg(errp, "Incoming postcopy migration is still in progress");
+        return false;
+    }
+
     if (runstate_check(RUN_STATE_POSTMIGRATE)) {
         error_setg(errp, "Can't migrate the vm that was paused due to "
                    "previous migration");
@@ -2235,11 +2244,12 @@ static bool migrate_prepare(MigrationState *s, bool resume, Error **errp)
         return false;
     }
 
+    yank_register_instance(MIGRATION_YANK_INSTANCE, &error_abort);
+
     return true;
 }
 
-static void qmp_migrate_finish(MigrationAddress *addr, bool resume_requested,
-                               Error **errp);
+static void qmp_migrate_finish(MigrationAddress *addr, Error **errp);
 
 static void migrate_hup_add(MigrationState *s, QIOChannel *ioc, GSourceFunc cb,
                             void *opaque)
@@ -2264,7 +2274,7 @@ static gboolean qmp_migrate_finish_cb(QIOChannel *channel,
 {
     MigrationAddress *addr = opaque;
 
-    qmp_migrate_finish(addr, false, NULL);
+    qmp_migrate_finish(addr, NULL);
 
     cpr_state_close();
     migrate_hup_delete(migrate_get_current());
@@ -2276,7 +2286,6 @@ void qmp_migrate(const char *uri, bool has_channels,
                  MigrationChannelList *channels, bool has_detach, bool detach,
                  bool has_resume, bool resume, Error **errp)
 {
-    bool resume_requested;
     Error *local_err = NULL;
     MigrationState *s = migrate_get_current();
     g_autoptr(MigrationChannel) channel = NULL;
@@ -2329,8 +2338,7 @@ void qmp_migrate(const char *uri, bool has_channels,
         return;
     }
 
-    resume_requested = has_resume && resume;
-    if (!migrate_prepare(s, resume_requested, errp)) {
+    if (!migrate_prepare(s, has_resume && resume, errp)) {
         /* Error detected, put into errp */
         return;
     }
@@ -2354,27 +2362,26 @@ void qmp_migrate(const char *uri, bool has_channels,
                         QAPI_CLONE(MigrationAddress, addr));
 
     } else {
-        qmp_migrate_finish(addr, resume_requested, errp);
+        qmp_migrate_finish(addr, errp);
     }
 
 out:
     if (local_err) {
+        /* A resume didn't register it, see migrate_prepare() */
+        if (s->state != MIGRATION_STATUS_POSTCOPY_RECOVER_SETUP) {
+            yank_unregister_instance(MIGRATION_YANK_INSTANCE);
+        }
         migration_connect_set_error(s, local_err);
         error_propagate(errp, local_err);
     }
 }
 
-static void qmp_migrate_finish(MigrationAddress *addr, bool resume_requested,
-                               Error **errp)
+static void qmp_migrate_finish(MigrationAddress *addr, Error **errp)
 {
     MigrationState *s = migrate_get_current();
     Error *local_err = NULL;
-
-    if (!resume_requested) {
-        if (!yank_register_instance(MIGRATION_YANK_INSTANCE, errp)) {
-            return;
-        }
-    }
+    /* Before the start functions below change the state */
+    bool resume = s->state == MIGRATION_STATUS_POSTCOPY_RECOVER_SETUP;
 
     if (addr->transport == MIGRATION_ADDRESS_TYPE_SOCKET) {
         SocketAddress *saddr = &addr->u.socket;
@@ -2401,7 +2408,8 @@ static void qmp_migrate_finish(MigrationAddress *addr, bool resume_requested,
     }
 
     if (local_err) {
-        if (!resume_requested) {
+        /* Nothing connected: migration_cleanup() won't unregister it */
+        if (!resume) {
             yank_unregister_instance(MIGRATION_YANK_INSTANCE);
         }
         migration_connect_set_error(s, local_err);

-- 
2.47.1