net-next/hinic: add checksum offload and TSO support

This patch adds checksum offload and TSO support for the HiNIC
driver. Perfomance test (Iperf) shows more than 100% improvement
in TCP streams.

Signed-off-by: Zhao Chen <zhaochen6@huawei.com>
Signed-off-by: Xue Chaojing <xuechaojing@huawei.com>
Signed-off-by: David S. Miller <davem@davemloft.net>

Author: Zhao Chen

drivers/net/ethernet/huawei/hinic/hinic_hw_dev.h

@@ -58,6 +58,8 @@ enum hinic_port_cmd {
 
 	HINIC_PORT_CMD_GET_GLOBAL_QPN   = 102,
 
+	HINIC_PORT_CMD_SET_TSO          = 112,
+
 	HINIC_PORT_CMD_GET_CAP          = 170,
 };
 

drivers/net/ethernet/huawei/hinic/hinic_hw_qp.c

@@ -70,8 +70,6 @@
 #define SQ_MASKED_IDX(sq, idx)  ((idx) & (sq)->wq->mask)
 #define RQ_MASKED_IDX(rq, idx)  ((idx) & (rq)->wq->mask)
 
-#define TX_MAX_MSS_DEFAULT      0x3E00
-
 enum sq_wqe_type {
 	SQ_NORMAL_WQE = 0,
 };
@@ -494,33 +492,16 @@ static void sq_prepare_ctrl(struct hinic_sq_ctrl *ctrl, u16 prod_idx,
 			  HINIC_SQ_CTRL_SET(SQ_NORMAL_WQE, DATA_FORMAT)     |
 			  HINIC_SQ_CTRL_SET(ctrl_size, LEN);
 
-	ctrl->queue_info = HINIC_SQ_CTRL_SET(TX_MAX_MSS_DEFAULT,
-					     QUEUE_INFO_MSS);
+	ctrl->queue_info = HINIC_SQ_CTRL_SET(HINIC_MSS_DEFAULT,
+					     QUEUE_INFO_MSS) |
+			   HINIC_SQ_CTRL_SET(1, QUEUE_INFO_UC);
 }
 
 static void sq_prepare_task(struct hinic_sq_task *task)
 {
-	task->pkt_info0 =
-		HINIC_SQ_TASK_INFO0_SET(0, L2HDR_LEN) |
-		HINIC_SQ_TASK_INFO0_SET(HINIC_L4_OFF_DISABLE, L4_OFFLOAD) |
-		HINIC_SQ_TASK_INFO0_SET(HINIC_OUTER_L3TYPE_UNKNOWN,
-					INNER_L3TYPE) |
-		HINIC_SQ_TASK_INFO0_SET(HINIC_VLAN_OFF_DISABLE,
-					VLAN_OFFLOAD) |
-		HINIC_SQ_TASK_INFO0_SET(HINIC_PKT_NOT_PARSED, PARSE_FLAG);
-
-	task->pkt_info1 =
-		HINIC_SQ_TASK_INFO1_SET(HINIC_MEDIA_UNKNOWN, MEDIA_TYPE) |
-		HINIC_SQ_TASK_INFO1_SET(0, INNER_L4_LEN) |
-		HINIC_SQ_TASK_INFO1_SET(0, INNER_L3_LEN);
-
-	task->pkt_info2 =
-		HINIC_SQ_TASK_INFO2_SET(0, TUNNEL_L4_LEN) |
-		HINIC_SQ_TASK_INFO2_SET(0, OUTER_L3_LEN)  |
-		HINIC_SQ_TASK_INFO2_SET(HINIC_TUNNEL_L4TYPE_UNKNOWN,
-					TUNNEL_L4TYPE)    |
-		HINIC_SQ_TASK_INFO2_SET(HINIC_OUTER_L3TYPE_UNKNOWN,
-					OUTER_L3TYPE);
+	task->pkt_info0 = 0;
+	task->pkt_info1 = 0;
+	task->pkt_info2 = 0;
 
 	task->ufo_v6_identify = 0;
 
@@ -529,6 +510,86 @@ static void sq_prepare_task(struct hinic_sq_task *task)
 	task->zero_pad = 0;
 }
 
+void hinic_task_set_l2hdr(struct hinic_sq_task *task, u32 len)
+{
+	task->pkt_info0 |= HINIC_SQ_TASK_INFO0_SET(len, L2HDR_LEN);
+}
+
+void hinic_task_set_outter_l3(struct hinic_sq_task *task,
+			      enum hinic_l3_offload_type l3_type,
+			      u32 network_len)
+{
+	task->pkt_info2 |= HINIC_SQ_TASK_INFO2_SET(l3_type, OUTER_L3TYPE) |
+			   HINIC_SQ_TASK_INFO2_SET(network_len, OUTER_L3LEN);
+}
+
+void hinic_task_set_inner_l3(struct hinic_sq_task *task,
+			     enum hinic_l3_offload_type l3_type,
+			     u32 network_len)
+{
+	task->pkt_info0 |= HINIC_SQ_TASK_INFO0_SET(l3_type, INNER_L3TYPE);
+	task->pkt_info1 |= HINIC_SQ_TASK_INFO1_SET(network_len, INNER_L3LEN);
+}
+
+void hinic_task_set_tunnel_l4(struct hinic_sq_task *task,
+			      enum hinic_l4_offload_type l4_type,
+			      u32 tunnel_len)
+{
+	task->pkt_info2 |= HINIC_SQ_TASK_INFO2_SET(l4_type, TUNNEL_L4TYPE) |
+			   HINIC_SQ_TASK_INFO2_SET(tunnel_len, TUNNEL_L4LEN);
+}
+
+void hinic_set_cs_inner_l4(struct hinic_sq_task *task, u32 *queue_info,
+			   enum hinic_l4_offload_type l4_offload,
+			   u32 l4_len, u32 offset)
+{
+	u32 tcp_udp_cs = 0, sctp = 0;
+	u32 mss = HINIC_MSS_DEFAULT;
+
+	if (l4_offload == TCP_OFFLOAD_ENABLE ||
+	    l4_offload == UDP_OFFLOAD_ENABLE)
+		tcp_udp_cs = 1;
+	else if (l4_offload == SCTP_OFFLOAD_ENABLE)
+		sctp = 1;
+
+	task->pkt_info0 |= HINIC_SQ_TASK_INFO0_SET(l4_offload, L4_OFFLOAD);
+	task->pkt_info1 |= HINIC_SQ_TASK_INFO1_SET(l4_len, INNER_L4LEN);
+
+	*queue_info |= HINIC_SQ_CTRL_SET(offset, QUEUE_INFO_PLDOFF) |
+		       HINIC_SQ_CTRL_SET(tcp_udp_cs, QUEUE_INFO_TCPUDP_CS) |
+		       HINIC_SQ_CTRL_SET(sctp, QUEUE_INFO_SCTP);
+
+	*queue_info = HINIC_SQ_CTRL_CLEAR(*queue_info, QUEUE_INFO_MSS);
+	*queue_info |= HINIC_SQ_CTRL_SET(mss, QUEUE_INFO_MSS);
+}
+
+void hinic_set_tso_inner_l4(struct hinic_sq_task *task, u32 *queue_info,
+			    enum hinic_l4_offload_type l4_offload,
+			    u32 l4_len, u32 offset, u32 ip_ident, u32 mss)
+{
+	u32 tso = 0, ufo = 0;
+
+	if (l4_offload == TCP_OFFLOAD_ENABLE)
+		tso = 1;
+	else if (l4_offload == UDP_OFFLOAD_ENABLE)
+		ufo = 1;
+
+	task->ufo_v6_identify = ip_ident;
+
+	task->pkt_info0 |= HINIC_SQ_TASK_INFO0_SET(l4_offload, L4_OFFLOAD);
+	task->pkt_info0 |= HINIC_SQ_TASK_INFO0_SET(tso || ufo, TSO_FLAG);
+	task->pkt_info1 |= HINIC_SQ_TASK_INFO1_SET(l4_len, INNER_L4LEN);
+
+	*queue_info |= HINIC_SQ_CTRL_SET(offset, QUEUE_INFO_PLDOFF) |
+		       HINIC_SQ_CTRL_SET(tso, QUEUE_INFO_TSO) |
+		       HINIC_SQ_CTRL_SET(ufo, QUEUE_INFO_UFO) |
+		       HINIC_SQ_CTRL_SET(!!l4_offload, QUEUE_INFO_TCPUDP_CS);
+
+	/* set MSS value */
+	*queue_info = HINIC_SQ_CTRL_CLEAR(*queue_info, QUEUE_INFO_MSS);
+	*queue_info |= HINIC_SQ_CTRL_SET(mss, QUEUE_INFO_MSS);
+}
+
 /**
  * hinic_sq_prepare_wqe - prepare wqe before insert to the queue
  * @sq: send queue
@@ -612,6 +673,16 @@ struct hinic_sq_wqe *hinic_sq_get_wqe(struct hinic_sq *sq,
 	return &hw_wqe->sq_wqe;
 }
 
+/**
+ * hinic_sq_return_wqe - return the wqe to the sq
+ * @sq: send queue
+ * @wqe_size: the size of the wqe
+ **/
+void hinic_sq_return_wqe(struct hinic_sq *sq, unsigned int wqe_size)
+{
+	hinic_return_wqe(sq->wq, wqe_size);
+}
+
 /**
  * hinic_sq_write_wqe - write the wqe to the sq
  * @sq: send queue

drivers/net/ethernet/huawei/hinic/hinic_hw_qp.h

@@ -149,6 +149,31 @@ int hinic_get_sq_free_wqebbs(struct hinic_sq *sq);
 
 int hinic_get_rq_free_wqebbs(struct hinic_rq *rq);
 
+void hinic_task_set_l2hdr(struct hinic_sq_task *task, u32 len);
+
+void hinic_task_set_outter_l3(struct hinic_sq_task *task,
+			      enum hinic_l3_offload_type l3_type,
+			      u32 network_len);
+
+void hinic_task_set_inner_l3(struct hinic_sq_task *task,
+			     enum hinic_l3_offload_type l3_type,
+			     u32 network_len);
+
+void hinic_task_set_tunnel_l4(struct hinic_sq_task *task,
+			      enum hinic_l4_offload_type l4_type,
+			      u32 tunnel_len);
+
+void hinic_set_cs_inner_l4(struct hinic_sq_task *task,
+			   u32 *queue_info,
+			   enum hinic_l4_offload_type l4_offload,
+			   u32 l4_len, u32 offset);
+
+void hinic_set_tso_inner_l4(struct hinic_sq_task *task,
+			    u32 *queue_info,
+			    enum hinic_l4_offload_type l4_offload,
+			    u32 l4_len,
+			    u32 offset, u32 ip_ident, u32 mss);
+
 void hinic_sq_prepare_wqe(struct hinic_sq *sq, u16 prod_idx,
 			  struct hinic_sq_wqe *wqe, struct hinic_sge *sges,
 			  int nr_sges);
@@ -159,6 +184,8 @@ void hinic_sq_write_db(struct hinic_sq *sq, u16 prod_idx, unsigned int wqe_size,
 struct hinic_sq_wqe *hinic_sq_get_wqe(struct hinic_sq *sq,
 				      unsigned int wqe_size, u16 *prod_idx);
 
+void hinic_sq_return_wqe(struct hinic_sq *sq, unsigned int wqe_size);
+
 void hinic_sq_write_wqe(struct hinic_sq *sq, u16 prod_idx,
 			struct hinic_sq_wqe *wqe, struct sk_buff *skb,
 			unsigned int wqe_size);

drivers/net/ethernet/huawei/hinic/hinic_hw_wq.c

@@ -774,6 +774,20 @@ struct hinic_hw_wqe *hinic_get_wqe(struct hinic_wq *wq, unsigned int wqe_size,
 	return WQ_PAGE_ADDR(wq, *prod_idx) + WQE_PAGE_OFF(wq, *prod_idx);
 }
 
+/**
+ * hinic_return_wqe - return the wqe when transmit failed
+ * @wq: wq to return wqe
+ * @wqe_size: wqe size
+ **/
+void hinic_return_wqe(struct hinic_wq *wq, unsigned int wqe_size)
+{
+	int num_wqebbs = ALIGN(wqe_size, wq->wqebb_size) / wq->wqebb_size;
+
+	atomic_sub(num_wqebbs, &wq->prod_idx);
+
+	atomic_add(num_wqebbs, &wq->delta);
+}
+
 /**
  * hinic_put_wqe - return the wqe place to use for a new wqe
  * @wq: wq to return wqe

drivers/net/ethernet/huawei/hinic/hinic_hw_wq.h

@@ -104,6 +104,8 @@ void hinic_wq_free(struct hinic_wqs *wqs, struct hinic_wq *wq);
 struct hinic_hw_wqe *hinic_get_wqe(struct hinic_wq *wq, unsigned int wqe_size,
 				   u16 *prod_idx);
 
+void hinic_return_wqe(struct hinic_wq *wq, unsigned int wqe_size);
+
 void hinic_put_wqe(struct hinic_wq *wq, unsigned int wqe_size);
 
 struct hinic_hw_wqe *hinic_read_wqe(struct hinic_wq *wq, unsigned int wqe_size,

drivers/net/ethernet/huawei/hinic/hinic_hw_wqe.h

@@ -62,19 +62,33 @@
 			(((val) >> HINIC_CMDQ_WQE_HEADER_##member##_SHIFT) \
 			 & HINIC_CMDQ_WQE_HEADER_##member##_MASK)
 
-#define HINIC_SQ_CTRL_BUFDESC_SECT_LEN_SHIFT    0
-#define HINIC_SQ_CTRL_TASKSECT_LEN_SHIFT        16
-#define HINIC_SQ_CTRL_DATA_FORMAT_SHIFT         22
-#define HINIC_SQ_CTRL_LEN_SHIFT                 29
-
-#define HINIC_SQ_CTRL_BUFDESC_SECT_LEN_MASK     0xFF
-#define HINIC_SQ_CTRL_TASKSECT_LEN_MASK         0x1F
-#define HINIC_SQ_CTRL_DATA_FORMAT_MASK          0x1
-#define HINIC_SQ_CTRL_LEN_MASK                  0x3
-
-#define HINIC_SQ_CTRL_QUEUE_INFO_MSS_SHIFT      13
-
-#define HINIC_SQ_CTRL_QUEUE_INFO_MSS_MASK       0x3FFF
+#define HINIC_SQ_CTRL_BUFDESC_SECT_LEN_SHIFT           0
+#define HINIC_SQ_CTRL_TASKSECT_LEN_SHIFT               16
+#define HINIC_SQ_CTRL_DATA_FORMAT_SHIFT                22
+#define HINIC_SQ_CTRL_LEN_SHIFT                        29
+
+#define HINIC_SQ_CTRL_BUFDESC_SECT_LEN_MASK            0xFF
+#define HINIC_SQ_CTRL_TASKSECT_LEN_MASK                0x1F
+#define HINIC_SQ_CTRL_DATA_FORMAT_MASK                 0x1
+#define HINIC_SQ_CTRL_LEN_MASK                         0x3
+
+#define HINIC_SQ_CTRL_QUEUE_INFO_PLDOFF_SHIFT          2
+#define HINIC_SQ_CTRL_QUEUE_INFO_UFO_SHIFT             10
+#define HINIC_SQ_CTRL_QUEUE_INFO_TSO_SHIFT             11
+#define HINIC_SQ_CTRL_QUEUE_INFO_TCPUDP_CS_SHIFT       12
+#define HINIC_SQ_CTRL_QUEUE_INFO_MSS_SHIFT             13
+#define HINIC_SQ_CTRL_QUEUE_INFO_SCTP_SHIFT            27
+#define HINIC_SQ_CTRL_QUEUE_INFO_UC_SHIFT              28
+#define HINIC_SQ_CTRL_QUEUE_INFO_PRI_SHIFT             29
+
+#define HINIC_SQ_CTRL_QUEUE_INFO_PLDOFF_MASK           0xFF
+#define HINIC_SQ_CTRL_QUEUE_INFO_UFO_MASK              0x1
+#define HINIC_SQ_CTRL_QUEUE_INFO_TSO_MASK              0x1
+#define HINIC_SQ_CTRL_QUEUE_INFO_TCPUDP_CS_MASK	       0x1
+#define HINIC_SQ_CTRL_QUEUE_INFO_MSS_MASK              0x3FFF
+#define HINIC_SQ_CTRL_QUEUE_INFO_SCTP_MASK             0x1
+#define HINIC_SQ_CTRL_QUEUE_INFO_UC_MASK               0x1
+#define HINIC_SQ_CTRL_QUEUE_INFO_PRI_MASK              0x7
 
 #define HINIC_SQ_CTRL_SET(val, member)          \
 		(((u32)(val) & HINIC_SQ_CTRL_##member##_MASK) \
@@ -84,6 +98,10 @@
 		(((val) >> HINIC_SQ_CTRL_##member##_SHIFT) \
 		 & HINIC_SQ_CTRL_##member##_MASK)
 
+#define HINIC_SQ_CTRL_CLEAR(val, member)	\
+		((u32)(val) & (~(HINIC_SQ_CTRL_##member##_MASK \
+		 << HINIC_SQ_CTRL_##member##_SHIFT)))
+
 #define HINIC_SQ_TASK_INFO0_L2HDR_LEN_SHIFT     0
 #define HINIC_SQ_TASK_INFO0_L4_OFFLOAD_SHIFT    8
 #define HINIC_SQ_TASK_INFO0_INNER_L3TYPE_SHIFT  10
@@ -108,28 +126,28 @@
 
 /* 8 bits reserved */
 #define HINIC_SQ_TASK_INFO1_MEDIA_TYPE_SHIFT    8
-#define HINIC_SQ_TASK_INFO1_INNER_L4_LEN_SHIFT  16
-#define HINIC_SQ_TASK_INFO1_INNER_L3_LEN_SHIFT  24
+#define HINIC_SQ_TASK_INFO1_INNER_L4LEN_SHIFT   16
+#define HINIC_SQ_TASK_INFO1_INNER_L3LEN_SHIFT   24
 
 /* 8 bits reserved */
 #define HINIC_SQ_TASK_INFO1_MEDIA_TYPE_MASK     0xFF
-#define HINIC_SQ_TASK_INFO1_INNER_L4_LEN_MASK   0xFF
-#define HINIC_SQ_TASK_INFO1_INNER_L3_LEN_MASK   0xFF
+#define HINIC_SQ_TASK_INFO1_INNER_L4LEN_MASK    0xFF
+#define HINIC_SQ_TASK_INFO1_INNER_L3LEN_MASK    0xFF
 
 #define HINIC_SQ_TASK_INFO1_SET(val, member)    \
 		(((u32)(val) & HINIC_SQ_TASK_INFO1_##member##_MASK) <<  \
 		 HINIC_SQ_TASK_INFO1_##member##_SHIFT)
 
-#define HINIC_SQ_TASK_INFO2_TUNNEL_L4_LEN_SHIFT 0
-#define HINIC_SQ_TASK_INFO2_OUTER_L3_LEN_SHIFT  12
-#define HINIC_SQ_TASK_INFO2_TUNNEL_L4TYPE_SHIFT 19
+#define HINIC_SQ_TASK_INFO2_TUNNEL_L4LEN_SHIFT  0
+#define HINIC_SQ_TASK_INFO2_OUTER_L3LEN_SHIFT   8
+#define HINIC_SQ_TASK_INFO2_TUNNEL_L4TYPE_SHIFT 16
 /* 1 bit reserved */
-#define HINIC_SQ_TASK_INFO2_OUTER_L3TYPE_SHIFT  22
+#define HINIC_SQ_TASK_INFO2_OUTER_L3TYPE_SHIFT  24
 /* 8 bits reserved */
 
-#define HINIC_SQ_TASK_INFO2_TUNNEL_L4_LEN_MASK  0xFFF
-#define HINIC_SQ_TASK_INFO2_OUTER_L3_LEN_MASK   0x7F
-#define HINIC_SQ_TASK_INFO2_TUNNEL_L4TYPE_MASK  0x3
+#define HINIC_SQ_TASK_INFO2_TUNNEL_L4LEN_MASK   0xFF
+#define HINIC_SQ_TASK_INFO2_OUTER_L3LEN_MASK    0xFF
+#define HINIC_SQ_TASK_INFO2_TUNNEL_L4TYPE_MASK  0x7
 /* 1 bit reserved */
 #define HINIC_SQ_TASK_INFO2_OUTER_L3TYPE_MASK   0x3
 /* 8 bits reserved */
@@ -187,12 +205,15 @@
 		 sizeof(struct hinic_sq_task) + \
 		 (nr_sges) * sizeof(struct hinic_sq_bufdesc))
 
-#define HINIC_SCMD_DATA_LEN             16
+#define HINIC_SCMD_DATA_LEN                     16
+
+#define HINIC_MAX_SQ_BUFDESCS                   17
 
-#define HINIC_MAX_SQ_BUFDESCS           17
+#define HINIC_SQ_WQE_MAX_SIZE                   320
+#define HINIC_RQ_WQE_SIZE                       32
 
-#define HINIC_SQ_WQE_MAX_SIZE           320
-#define HINIC_RQ_WQE_SIZE               32
+#define HINIC_MSS_DEFAULT		        0x3E00
+#define HINIC_MSS_MIN		                0x50
 
 enum hinic_l4offload_type {
 	HINIC_L4_OFF_DISABLE            = 0,
@@ -211,6 +232,26 @@ enum hinic_pkt_parsed {
 	HINIC_PKT_PARSED     = 1,
 };
 
+enum hinic_l3_offload_type {
+	L3TYPE_UNKNOWN = 0,
+	IPV6_PKT = 1,
+	IPV4_PKT_NO_CHKSUM_OFFLOAD = 2,
+	IPV4_PKT_WITH_CHKSUM_OFFLOAD = 3,
+};
+
+enum hinic_l4_offload_type {
+	OFFLOAD_DISABLE     = 0,
+	TCP_OFFLOAD_ENABLE  = 1,
+	SCTP_OFFLOAD_ENABLE = 2,
+	UDP_OFFLOAD_ENABLE  = 3,
+};
+
+enum hinic_l4_tunnel_type {
+	NOT_TUNNEL,
+	TUNNEL_UDP_NO_CSUM,
+	TUNNEL_UDP_CSUM,
+};
+
 enum hinic_outer_l3type {
 	HINIC_OUTER_L3TYPE_UNKNOWN              = 0,
 	HINIC_OUTER_L3TYPE_IPV6                 = 1,