RDMA/cma: Fix lockdep false positive recursive locking

The following lockdep problem was reported by Or Gerlitz <ogerlitz@mellanox.com>:

    [ INFO: possible recursive locking detected ]
    3.3.0-32035-g1b2649e-dirty #4 Not tainted
    ---------------------------------------------
    kworker/5:1/418 is trying to acquire lock:
     (&id_priv->handler_mutex){+.+.+.}, at: [<ffffffffa0138a41>] rdma_destroy_i    d+0x33/0x1f0 [rdma_cm]

    but task is already holding lock:
     (&id_priv->handler_mutex){+.+.+.}, at: [<ffffffffa0135130>] cma_disable_ca    llback+0x24/0x45 [rdma_cm]

    other info that might help us debug this:
     Possible unsafe locking scenario:

           CPU0
           ----
      lock(&id_priv->handler_mutex);
      lock(&id_priv->handler_mutex);

     *** DEADLOCK ***

     May be due to missing lock nesting notation

    3 locks held by kworker/5:1/418:
     #0:  (ib_cm){.+.+.+}, at: [<ffffffff81042ac1>] process_one_work+0x210/0x4a    6
     #1:  ((&(&work->work)->work)){+.+.+.}, at: [<ffffffff81042ac1>] process_on    e_work+0x210/0x4a6
     #2:  (&id_priv->handler_mutex){+.+.+.}, at: [<ffffffffa0135130>] cma_disab    le_callback+0x24/0x45 [rdma_cm]

    stack backtrace:
    Pid: 418, comm: kworker/5:1 Not tainted 3.3.0-32035-g1b2649e-dirty #4
    Call Trace:
     [<ffffffff8102b0fb>] ? console_unlock+0x1f4/0x204
     [<ffffffff81068771>] __lock_acquire+0x16b5/0x174e
     [<ffffffff8106461f>] ? save_trace+0x3f/0xb3
     [<ffffffff810688fa>] lock_acquire+0xf0/0x116
     [<ffffffffa0138a41>] ? rdma_destroy_id+0x33/0x1f0 [rdma_cm]
     [<ffffffff81364351>] mutex_lock_nested+0x64/0x2ce
     [<ffffffffa0138a41>] ? rdma_destroy_id+0x33/0x1f0 [rdma_cm]
     [<ffffffff81065a78>] ? trace_hardirqs_on_caller+0x11e/0x155
     [<ffffffff81065abc>] ? trace_hardirqs_on+0xd/0xf
     [<ffffffffa0138a41>] rdma_destroy_id+0x33/0x1f0 [rdma_cm]
     [<ffffffffa0139c02>] cma_req_handler+0x418/0x644 [rdma_cm]
     [<ffffffffa012ee88>] cm_process_work+0x32/0x119 [ib_cm]
     [<ffffffffa0130299>] cm_req_handler+0x928/0x982 [ib_cm]
     [<ffffffffa01302f3>] ? cm_req_handler+0x982/0x982 [ib_cm]
     [<ffffffffa0130326>] cm_work_handler+0x33/0xfe5 [ib_cm]
     [<ffffffff81065a78>] ? trace_hardirqs_on_caller+0x11e/0x155
     [<ffffffffa01302f3>] ? cm_req_handler+0x982/0x982 [ib_cm]
     [<ffffffff81042b6e>] process_one_work+0x2bd/0x4a6
     [<ffffffff81042ac1>] ? process_one_work+0x210/0x4a6
     [<ffffffff813669f3>] ? _raw_spin_unlock_irq+0x2b/0x40
     [<ffffffff8104316e>] worker_thread+0x1d6/0x350
     [<ffffffff81042f98>] ? rescuer_thread+0x241/0x241
     [<ffffffff81046a32>] kthread+0x84/0x8c
     [<ffffffff8136e854>] kernel_thread_helper+0x4/0x10
     [<ffffffff81366d59>] ? retint_restore_args+0xe/0xe
     [<ffffffff810469ae>] ? __init_kthread_worker+0x56/0x56
     [<ffffffff8136e850>] ? gs_change+0xb/0xb

The actual locking is fine, since we're dealing with different locks,
but from the same lock class.  cma_disable_callback() acquires the
listening id mutex, whereas rdma_destroy_id() acquires the mutex for
the new connection id.  To fix this, delay the call to
rdma_destroy_id() until we've released the listening id mutex.

Signed-off-by: Sean Hefty <sean.hefty@intel.com>
Signed-off-by: Roland Dreier <roland@purestorage.com>

diff --git a/drivers/infiniband/core/cma.c b/drivers/infiniband/core/cma.c
index e3e470fecaa99499835b80d53b83dda3b5f50350..79c7eebb970fde92262a775e0ec22503854c1de7 100644 (file)
--- a/drivers/infiniband/core/cma.c
+++ b/drivers/infiniband/core/cma.c
@@ -1218,13 +1218,13 @@ static int cma_req_handler(struct ib_cm_id *cm_id, struct ib_cm_event *ib_event)
        }
        if (!conn_id) {
                ret = -ENOMEM;
-               goto out;
+               goto err1;
        }
 
        mutex_lock_nested(&conn_id->handler_mutex, SINGLE_DEPTH_NESTING);
        ret = cma_acquire_dev(conn_id);
        if (ret)
-               goto release_conn_id;
+               goto err2;
 
        conn_id->cm_id.ib = cm_id;
        cm_id->context = conn_id;
@@ -1236,31 +1236,33 @@ static int cma_req_handler(struct ib_cm_id *cm_id, struct ib_cm_event *ib_event)
         */
        atomic_inc(&conn_id->refcount);
        ret = conn_id->id.event_handler(&conn_id->id, &event);
-       if (!ret) {
-               /*
-                * Acquire mutex to prevent user executing rdma_destroy_id()
-                * while we're accessing the cm_id.
-                */
-               mutex_lock(&lock);
-               if (cma_comp(conn_id, RDMA_CM_CONNECT) && (conn_id->id.qp_type != IB_QPT_UD))
-                       ib_send_cm_mra(cm_id, CMA_CM_MRA_SETTING, NULL, 0);
-               mutex_unlock(&lock);
-               mutex_unlock(&conn_id->handler_mutex);
-               cma_deref_id(conn_id);
-               goto out;
-       }
+       if (ret)
+               goto err3;
+
+       /*
+        * Acquire mutex to prevent user executing rdma_destroy_id()
+        * while we're accessing the cm_id.
+        */
+       mutex_lock(&lock);
+       if (cma_comp(conn_id, RDMA_CM_CONNECT) && (conn_id->id.qp_type != IB_QPT_UD))
+               ib_send_cm_mra(cm_id, CMA_CM_MRA_SETTING, NULL, 0);
+       mutex_unlock(&lock);
+       mutex_unlock(&conn_id->handler_mutex);
+       mutex_unlock(&listen_id->handler_mutex);
        cma_deref_id(conn_id);
+       return 0;
 
+err3:
+       cma_deref_id(conn_id);
        /* Destroy the CM ID by returning a non-zero value. */
        conn_id->cm_id.ib = NULL;
-
-release_conn_id:
+err2:
        cma_exch(conn_id, RDMA_CM_DESTROYING);
        mutex_unlock(&conn_id->handler_mutex);
-       rdma_destroy_id(&conn_id->id);
-
-out:
+err1:
        mutex_unlock(&listen_id->handler_mutex);
+       if (conn_id)
+               rdma_destroy_id(&conn_id->id);
        return ret;
 }