IPoIB/cm: Use common CQ for CM send completions

Use the same CQ for CM send completions as for all other IPoIB
completions.  This means all completions are processed via the same
NAPI polling routine.  This should help reduce the number of
interrupts for bi-directional traffic (such as TCP) and fixes "driver
is hogging interrupts" errors reported for IPoIB send side, e.g.
<https://bugs.openfabrics.org/show_bug.cgi?id=508>

To do this, keep a per-interface counter of outstanding send WRs, and
stop the interface when this counter reaches the send queue size to
avoid CQ overruns.

Signed-off-by: Michael S. Tsirkin <mst@mellanox.co.il>
Signed-off-by: Roland Dreier <rolandd@cisco.com>

1 files changed, 1 insertions, 3 deletions

diff --git a/drivers/infiniband/ulp/ipoib/ipoib_main.c b/drivers/infiniband/ulp/ipoib/ipoib_main.c
index e072f3c32ce6..ace2345960ee 100644
--- a/drivers/infiniband/ulp/ipoib/ipoib_main.c
+++ b/drivers/infiniband/ulp/ipoib/ipoib_main.c
@@ -148,8 +148,6 @@ static int ipoib_stop(struct net_device *dev)
 
         netif_stop_queue(dev);
 
-        clear_bit(IPOIB_FLAG_NETIF_STOPPED, &priv->flags);
-
         /*
          * Now flush workqueue to make sure a scheduled task doesn't
          * bring our internal state back up.
@@ -895,7 +893,7 @@ int ipoib_dev_init(struct net_device *dev, struct ib_device *ca, int port)
                 goto out_rx_ring_cleanup;
         }
 
-        /* priv->tx_head & tx_tail are already 0 */
+        /* priv->tx_head, tx_tail & tx_outstanding are already 0 */
 
         if (ipoib_ib_dev_init(dev, ca, port))
                 goto out_tx_ring_cleanup;