[dpdk-stable] [PATCH v3 19.11.6 5/6] net/hns3: reduce address calculation in Rx

[Lijun Ou <oulijun@huawei.com>]

From: "Wei Hu (Xavier)" <xavier.huwei@huawei.com>

[ upstream commit 323df8941b57027752ee9d191f1ac6f359bd524e ]

This patch adds the internal function named hns3_write_reg_opt to avoid
performance loss from address calculation during register access in the
'.rx_pkt_burst' ops implementation function named hns3_recv_pkts.

In addition, because hardware always access register in little-endian
mode based on hns3 network engine, so driver should also call
rte_cpu_to_le_32 to convert data in little-endian mode before writing
register and call rte_le_to_cpu_32 to convert data after reading from
register. Here the driver encapsulates the data conversion operation in
the register read/write operation function as below:
  hns3_write_reg
  hns3_write_reg_opt
  hns3_read_reg
Therefore, when calling these functions, conversion is not required
again.

Signed-off-by: Chengwen Feng <fengchengwen@huawei.com>
Signed-off-by: Wei Hu (Xavier) <xavier.huwei@huawei.com>
---
 drivers/net/hns3/hns3_ethdev.h | 29 +++++++++++++++++++++++++++--
 drivers/net/hns3/hns3_rxtx.c   | 14 +++-----------
 drivers/net/hns3/hns3_rxtx.h   |  1 +
 3 files changed, 31 insertions(+), 13 deletions(-)

diff --git a/drivers/net/hns3/hns3_ethdev.h b/drivers/net/hns3/hns3_ethdev.h
index e0a04f8..ba01622 100644
--- a/drivers/net/hns3/hns3_ethdev.h
+++ b/drivers/net/hns3/hns3_ethdev.h
@@ -579,14 +579,39 @@ struct hns3_adapter {
 	type __max2 = (y);                      \
 	__max1 > __max2 ? __max1 : __max2; })
 
+/*
+ * Because hardware always access register in little-endian mode based on hns3
+ * network engine, so driver should also call rte_cpu_to_le_32 to convert data
+ * in little-endian mode before writing register and call rte_le_to_cpu_32 to
+ * convert data after reading from register.
+ *
+ * Here the driver encapsulates the data conversion operation in the register
+ * read/write operation function as below:
+ *   hns3_write_reg
+ *   hns3_write_reg_opt
+ *   hns3_read_reg
+ * Therefore, when calling these functions, conversion is not required again.
+ */
 static inline void hns3_write_reg(void *base, uint32_t reg, uint32_t value)
 {
-	rte_write32(value, (volatile void *)((char *)base + reg));
+	rte_write32(rte_cpu_to_le_32(value),
+		    (volatile void *)((char *)base + reg));
+}
+
+/*
+ * The optimized function for writing registers used in the '.rx_pkt_burst' and
+ * '.tx_pkt_burst' ops implementation function.
+ */
+static inline void hns3_write_reg_opt(volatile void *addr, uint32_t value)
+{
+	rte_io_wmb();
+	rte_write32_relaxed(rte_cpu_to_le_32(value), addr);
 }
 
 static inline uint32_t hns3_read_reg(void *base, uint32_t reg)
 {
-	return rte_read32((volatile void *)((char *)base + reg));
+	uint32_t read_val = rte_read32((volatile void *)((char *)base + reg));
+	return rte_le_to_cpu_32(read_val);
 }
 
 #define hns3_write_dev(a, reg, value) \
diff --git a/drivers/net/hns3/hns3_rxtx.c b/drivers/net/hns3/hns3_rxtx.c
index 41d957a..78c73ea 100644
--- a/drivers/net/hns3/hns3_rxtx.c
+++ b/drivers/net/hns3/hns3_rxtx.c
@@ -1305,6 +1305,8 @@ hns3_rx_queue_setup(struct rte_eth_dev *dev, uint16_t idx, uint16_t nb_desc,
 	rxq->configured = true;
 	rxq->io_base = (void *)((char *)hw->io_base + HNS3_TQP_REG_OFFSET +
 				idx * HNS3_TQP_REG_SIZE);
+	rxq->io_head_reg = (volatile void *)((char *)rxq->io_base +
+			   HNS3_RING_RX_HEAD_REG);
 	rxq->rx_buf_len = rx_buf_size;
 	rxq->l2_errors = 0;
 	rxq->pkt_len_errors = 0;
@@ -1448,16 +1450,6 @@ hns3_dev_supported_ptypes_get(struct rte_eth_dev *dev)
 	return NULL;
 }
 
-static void
-hns3_clean_rx_buffers(struct hns3_rx_queue *rxq, int count)
-{
-	rxq->next_to_use += count;
-	if (rxq->next_to_use >= rxq->nb_rx_desc)
-		rxq->next_to_use -= rxq->nb_rx_desc;
-
-	hns3_write_dev(rxq, HNS3_RING_RX_HEAD_REG, count);
-}
-
 static int
 hns3_handle_bdinfo(struct hns3_rx_queue *rxq, struct rte_mbuf *rxm,
 		   uint32_t bd_base_info, uint32_t l234_info,
@@ -1770,7 +1762,7 @@ hns3_recv_pkts(void *rx_queue, struct rte_mbuf **rx_pkts, uint16_t nb_pkts)
 
 	rxq->rx_free_hold += nb_rx_bd;
 	if (rxq->rx_free_hold > rxq->rx_free_thresh) {
-		hns3_clean_rx_buffers(rxq, rxq->rx_free_hold);
+		hns3_write_reg_opt(rxq->io_head_reg, rxq->rx_free_hold);
 		rxq->rx_free_hold = 0;
 	}
 
diff --git a/drivers/net/hns3/hns3_rxtx.h b/drivers/net/hns3/hns3_rxtx.h
index 6211665..fd4f419 100644
--- a/drivers/net/hns3/hns3_rxtx.h
+++ b/drivers/net/hns3/hns3_rxtx.h
@@ -231,6 +231,7 @@ struct hns3_entry {
 
 struct hns3_rx_queue {
 	void *io_base;
+	volatile void *io_head_reg;
 	struct hns3_adapter *hns;
 	struct rte_mempool *mb_pool;
 	struct hns3_desc *rx_ring;
-- 
2.7.4