block/nbd: Fix hang in .bdrv_close()

When nbd_close() is called from a coroutine, the connection_co never
gets to run, and thus nbd_teardown_connection() hangs.

This is because aio_co_enter() only puts the connection_co into the main
coroutine's wake-up queue, so this main coroutine needs to yield and
wait for connection_co to terminate.

Suggested-by: Kevin Wolf <kwolf@redhat.com>
Signed-off-by: Max Reitz <mreitz@redhat.com>
Message-Id: <20200122164532.178040-2-mreitz@redhat.com>
Reviewed-by: Eric Blake <eblake@redhat.com>
Reviewed-by: Maxim Levitsky <mlevitsk@redhat.com>
Signed-off-by: Max Reitz <mreitz@redhat.com>

diff --git a/block/nbd.c b/block/nbd.c
index d085554f21ea3604b6e3b922983274b5cbbb5484..6d3b22f844eab36971e61024c143d928065fd6fd 100644 (file)
--- a/block/nbd.c
+++ b/block/nbd.c
@@ -70,6 +70,7 @@ typedef struct BDRVNBDState {
     CoMutex send_mutex;
     CoQueue free_sema;
     Coroutine *connection_co;
+    Coroutine *teardown_co;
     QemuCoSleepState *connection_co_sleep_ns_state;
     bool drained;
     bool wait_drained_end;
@@ -203,7 +204,15 @@ static void nbd_teardown_connection(BlockDriverState *bs)
             qemu_co_sleep_wake(s->connection_co_sleep_ns_state);
         }
     }
-    BDRV_POLL_WHILE(bs, s->connection_co);
+    if (qemu_in_coroutine()) {
+        s->teardown_co = qemu_coroutine_self();
+        /* connection_co resumes us when it terminates */
+        qemu_coroutine_yield();
+        s->teardown_co = NULL;
+    } else {
+        BDRV_POLL_WHILE(bs, s->connection_co);
+    }
+    assert(!s->connection_co);
 }
 
 static bool nbd_client_connecting(BDRVNBDState *s)
@@ -395,6 +404,9 @@ static coroutine_fn void nbd_connection_entry(void *opaque)
         s->ioc = NULL;
     }
 
+    if (s->teardown_co) {
+        aio_co_wake(s->teardown_co);
+    }
     aio_wait_kick();
 }