RDMA/cxgb4: Use DSGLs for fastreg and adapter memory writes for T5.

It enables direct DMA by HW to memory region PBL arrays and fast register PBL
arrays from host memory, vs the T4 way of passing these arrays in the WR itself.
The result is lower latency for memory registration, and larger PBL array
support for fast register operations.

This patch also updates ULP_TX_MEM_WRITE command fields for T5. Ordering bit of
ULP_TX_MEM_WRITE is at bit position 22 in T5 and at 23 in T4.

Signed-off-by: Vipul Pandya <vipul@chelsio.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
diff --git a/drivers/net/ethernet/chelsio/cxgb4/t4_msg.h b/drivers/net/ethernet/chelsio/cxgb4/t4_msg.h
index 0c9f14f..47656ac 100644
--- a/drivers/net/ethernet/chelsio/cxgb4/t4_msg.h
+++ b/drivers/net/ethernet/chelsio/cxgb4/t4_msg.h
@@ -787,4 +787,12 @@
 #define ULP_MEMIO_LOCK(x) ((x) << 31)
 };
 
+#define S_T5_ULP_MEMIO_IMM    23
+#define V_T5_ULP_MEMIO_IMM(x) ((x) << S_T5_ULP_MEMIO_IMM)
+#define F_T5_ULP_MEMIO_IMM    V_T5_ULP_MEMIO_IMM(1U)
+
+#define S_T5_ULP_MEMIO_ORDER    22
+#define V_T5_ULP_MEMIO_ORDER(x) ((x) << S_T5_ULP_MEMIO_ORDER)
+#define F_T5_ULP_MEMIO_ORDER    V_T5_ULP_MEMIO_ORDER(1U)
+
 #endif  /* __T4_MSG_H */