ibmveth: Use lighter weight read memory barrier in ibmveth_poll

antonblanchard · davem330 · commit f89e49e79f83 · 2010-09-06T18:21:41.000-07:00
We want to order the read in ibmveth_rxq_pending_buffer and the read of
ibmveth_rxq_buffer_valid which are both cacheable memory. smp_rmb() is good
enough for this.

Signed-off-by: Anton Blanchard &lt;anton@samba.org&gt;
Signed-off-by: Santiago Leon &lt;santil@linux.vnet.ibm.com&gt;
Signed-off-by: David S. Miller &lt;davem@davemloft.net&gt;
diff --git a/drivers/net/ibmveth.c b/drivers/net/ibmveth.c
@@ -1010,7 +1010,7 @@ static int ibmveth_poll(struct napi_struct *napi, int budget)
 		if (!ibmveth_rxq_pending_buffer(adapter))
 			break;
 
-		rmb();
+		smp_rmb();
 		if (!ibmveth_rxq_buffer_valid(adapter)) {
 			wmb(); /* suggested by larson1 */
 			adapter->rx_invalid_buffer++;
