RDMA/cxgb3: Remove BUG_ON() on CQ rearm failure

Failure to rearm a CQ means the cxgb3 device is wedged, but we shouldn't
kill the whole system with a BUG_ON() if this happens.

Signed-off-by: Steve Wise <swise@opengridcomputing.com>
Signed-off-by: Roland Dreier <rolandd@cisco.com>

diff --git a/drivers/infiniband/hw/cxgb3/cxio_hal.c b/drivers/infiniband/hw/cxgb3/cxio_hal.c
index 0677fc7dfd51d3dc6c0c920ca0c3d8bff843be82..8837d56f9c92302f9bb6890213637eda9ea5a1dc 100644 (file)
--- a/drivers/infiniband/hw/cxgb3/cxio_hal.c
+++ b/drivers/infiniband/hw/cxgb3/cxio_hal.c
@@ -109,7 +109,6 @@ int cxio_hal_cq_op(struct cxio_rdev *rdev_p, struct t3_cq *cq,
                while (!CQ_VLD_ENTRY(rptr, cq->size_log2, cqe)) {
                        udelay(1);
                        if (i++ > 1000000) {
-                               BUG_ON(1);
                                printk(KERN_ERR "%s: stalled rnic\n",
                                       rdev_p->dev_name);
                                return -EIO;