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>

1 files changed, 5 insertions, 2 deletions

diff --git a/drivers/infiniband/ulp/ipoib/ipoib.h b/drivers/infiniband/ulp/ipoib/ipoib.h
index f1f142dc64b1..9044f8803532 100644
--- a/drivers/infiniband/ulp/ipoib/ipoib.h
+++ b/drivers/infiniband/ulp/ipoib/ipoib.h
@@ -95,6 +95,8 @@ enum {
         IPOIB_MCAST_FLAG_SENDONLY = 1,
         IPOIB_MCAST_FLAG_BUSY     = 2,  /* joining or already joined */
         IPOIB_MCAST_FLAG_ATTACHED = 3,
+
+        MAX_SEND_CQE              = 16,
 };
 
 #define IPOIB_OP_RECV   (1ul << 31)
@@ -285,7 +287,8 @@ struct ipoib_dev_priv {
         u16               pkey_index;
         struct ib_pd     *pd;
         struct ib_mr     *mr;
-        struct ib_cq     *cq;
+        struct ib_cq     *recv_cq;
+        struct ib_cq     *send_cq;
         struct ib_qp     *qp;
         u32               qkey;
 
@@ -305,6 +308,7 @@ struct ipoib_dev_priv {
         struct ib_sge        tx_sge[MAX_SKB_FRAGS + 1];
         struct ib_send_wr    tx_wr;
         unsigned             tx_outstanding;
+        struct ib_wc         send_wc[MAX_SEND_CQE];
 
         struct ib_recv_wr    rx_wr;
         struct ib_sge        rx_sge[IPOIB_UD_RX_SG];
@@ -662,7 +666,6 @@ static inline int ipoib_register_debugfs(void) { return 0; }
 static inline void ipoib_unregister_debugfs(void) { }
 #endif
 
-
 #define ipoib_printk(level, priv, format, arg...)       \
         printk(level "%s: " format, ((struct ipoib_dev_priv *) priv)->dev->name , ## arg)
 #define ipoib_warn(priv, format, arg...)                \