IPoIB: Use separate CQ for UD send completions

Use a dedicated CQ for UD send completions. Also, do not arm the UD
send CQ, which reduces the number of interrupts generated.  This patch
farther reduces overhead by not calling poll CQ for every posted send
WR -- it does polls only when there 16 or more outstanding work requests.

Signed-off-by: Eli Cohen <eli@mellanox.co.il>
Signed-off-by: Roland Dreier <rolandd@cisco.com>
diff --git a/drivers/infiniband/ulp/ipoib/ipoib_cm.c b/drivers/infiniband/ulp/ipoib/ipoib_cm.c
index 9db7b0b..97e67d3 100644
--- a/drivers/infiniband/ulp/ipoib/ipoib_cm.c
+++ b/drivers/infiniband/ulp/ipoib/ipoib_cm.c
@@ -249,8 +249,8 @@
 	struct ipoib_dev_priv *priv = netdev_priv(dev);
 	struct ib_qp_init_attr attr = {
 		.event_handler = ipoib_cm_rx_event_handler,
-		.send_cq = priv->cq, /* For drain WR */
-		.recv_cq = priv->cq,
+		.send_cq = priv->recv_cq, /* For drain WR */
+		.recv_cq = priv->recv_cq,
 		.srq = priv->cm.srq,
 		.cap.max_send_wr = 1, /* For drain WR */
 		.cap.max_send_sge = 1, /* FIXME: 0 Seems not to work */
@@ -951,8 +951,8 @@
 {
 	struct ipoib_dev_priv *priv = netdev_priv(dev);
 	struct ib_qp_init_attr attr = {
-		.send_cq		= priv->cq,
-		.recv_cq		= priv->cq,
+		.send_cq		= priv->recv_cq,
+		.recv_cq		= priv->recv_cq,
 		.srq			= priv->cm.srq,
 		.cap.max_send_wr	= ipoib_sendq_size,
 		.cap.max_send_sge	= 1,