From: Steve Wise <swise@opengridcomputing.com>
Date: Thu, 11 Feb 2010 23:40:29 +0000 (-0800)
Subject: RDMA/cxgb3: Remove BUG_ON() on CQ rearm failure
X-Git-Tag: v2.6.34-rc1~225^2~7^2~4
X-Git-Url: https://git.openpandora.org/cgi-bin/gitweb.cgi?a=commitdiff_plain;h=2542322485be45853cc72d542d8ed84fae82c981;p=pandora-kernel.git

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 0677fc7dfd51..8837d56f9c92 100644
--- 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;