IB/core: Add IPoIB UD LSO support

LSO (large send offload) allows the networking stack to pass SKBs with
data size larger than the MTU to the IPoIB driver and have the HCA HW
fragment the data to multiple MSS-sized packets.  Add a device
capability flag IB_DEVICE_UD_TSO for devices that can perform TCP
segmentation offload, a new send work request opcode IB_WR_LSO,
header, hlen and mss fields for the work request structure, and a new
IB_WC_LSO completion type.

Signed-off-by: Eli Cohen <eli@mellanox.co.il>
Signed-off-by: Roland Dreier <rolandd@cisco.com>
diff --git a/include/rdma/ib_verbs.h b/include/rdma/ib_verbs.h
index c3299be..66928e9 100644
--- a/include/rdma/ib_verbs.h
+++ b/include/rdma/ib_verbs.h
@@ -104,6 +104,7 @@
 	 * IPoIB driver may set NETIF_F_IP_CSUM for datagram mode.
 	 */
 	IB_DEVICE_UD_IP_CSUM		= (1<<18),
+	IB_DEVICE_UD_TSO		= (1<<19),
 };
 
 enum ib_atomic_cap {
@@ -411,6 +412,7 @@
 	IB_WC_COMP_SWAP,
 	IB_WC_FETCH_ADD,
 	IB_WC_BIND_MW,
+	IB_WC_LSO,
 /*
  * Set value of IB_WC_RECV so consumers can test if a completion is a
  * receive by testing (opcode & IB_WC_RECV).
@@ -622,7 +624,8 @@
 	IB_WR_SEND_WITH_IMM,
 	IB_WR_RDMA_READ,
 	IB_WR_ATOMIC_CMP_AND_SWP,
-	IB_WR_ATOMIC_FETCH_AND_ADD
+	IB_WR_ATOMIC_FETCH_AND_ADD,
+	IB_WR_LSO
 };
 
 enum ib_send_flags {
@@ -660,6 +663,9 @@
 		} atomic;
 		struct {
 			struct ib_ah *ah;
+			void   *header;
+			int     hlen;
+			int     mss;
 			u32	remote_qpn;
 			u32	remote_qkey;
 			u16	pkey_index; /* valid for GSI only */