From: Mike Marciniszyn <mike.marciniszyn@intel.com>
Date: Thu, 12 May 2016 17:23:03 +0000 (-0700)
Subject: IB/hfi1: Fix potential panic with sdma drained mechanism
X-Git-Url: https://git.karo-electronics.de/?a=commitdiff_plain;h=b96b040445f5d84fb8aa2ff986be71f5069c976e;p=linux-beck.git

IB/hfi1: Fix potential panic with sdma drained mechanism

The guard is backwards, potentially causing the SDMA client
to panic if a wait structure was not specified.

psm and verbs are not exposed to the issue, but fix the
code just to be correct.

Fixes: a545f5308b6c ("staging/rdma/hfi: fix CQ completion order issue")
Reviewed-by: Dennis Dalessandro <dennis.dalessandro@intel.com>
Signed-off-by: Mike Marciniszyn <mike.marciniszyn@intel.com>
Signed-off-by: Doug Ledford <dledford@redhat.com>
---

diff --git a/drivers/staging/rdma/hfi1/sdma.c b/drivers/staging/rdma/hfi1/sdma.c
index abb8ebc1fcac..e938017f78e3 100644
--- a/drivers/staging/rdma/hfi1/sdma.c
+++ b/drivers/staging/rdma/hfi1/sdma.c
@@ -376,7 +376,7 @@ static inline void complete_tx(struct sdma_engine *sde,
 	sdma_txclean(sde->dd, tx);
 	if (complete)
 		(*complete)(tx, res);
-	if (iowait_sdma_dec(wait) && wait)
+	if (wait && iowait_sdma_dec(wait))
 		iowait_drain_wakeup(wait);
 }