IB/qib: Fix QP locate/remove race

remove_qp() can execute concurrently with a qib_lookup_qpn() on
another CPU, which in of itself, is ok, given the RCU locking.

The issue is that remove_qp() NULLs out the qp->next field so that a
qib_lookup_qpn() might fail to find a qp if it occurs after the one
that is being deleted.  This is a momentary issue and subsequent
qib_lookup_qpn() calls would find the qp's since the search restarts
from the bucket head.  At scale, the issue might causes dropped
packets and unnecessary retransmissions.

The fix just deletes the qp->next NULL assignment to prevent the
remove_qp() from hiding qp's from qib_lookup_qpn().

Reviewed-by: Dean Luick <dean.luick@intel.com>
Signed-off-by: Mike Marciniszyn <mike.marciniszyn@intel.com>
Signed-off-by: Roland Dreier <roland@purestorage.com>

diff --git a/drivers/infiniband/hw/qib/qib_qp.c b/drivers/infiniband/hw/qib/qib_qp.c
index 35275099cafd660cd2fc20ab865d08c417f51735..a6a2cc2ba260ddd80ca6e23982864ec8e969e9b4 100644 (file)
--- a/drivers/infiniband/hw/qib/qib_qp.c
+++ b/drivers/infiniband/hw/qib/qib_qp.c
@@ -268,8 +268,9 @@ static void remove_qp(struct qib_ibdev *dev, struct qib_qp *qp)
                                qpp = &q->next)
                        if (q == qp) {
                                atomic_dec(&qp->refcount);
-                               *qpp = qp->next;
-                               rcu_assign_pointer(qp->next, NULL);
+                               rcu_assign_pointer(*qpp,
+                                       rcu_dereference_protected(qp->next,
+                                        lockdep_is_held(&dev->qpt_lock)));
                                break;
                        }
        }