net: hns3: add support for TX push mode

For the device that supports the TX push capability, the BD can
be directly copied to the device memory. However, due to hardware
restrictions, the push mode can be used only when there are no
more than two BDs, otherwise, the doorbell mode based on device
memory is used.

Signed-off-by: Yufeng Mo <moyufeng@huawei.com>
Signed-off-by: Guangbin Huang <huangguangbin2@huawei.com>
Signed-off-by: David S. Miller <davem@davemloft.net>

1 files changed, 75 insertions, 4 deletions

diff --git a/drivers/net/ethernet/hisilicon/hns3/hns3_enet.c b/drivers/net/ethernet/hisilicon/hns3/hns3_enet.c
index babc5d7a3b52..0b8a73c40b12 100644
--- a/drivers/net/ethernet/hisilicon/hns3/hns3_enet.c
+++ b/drivers/net/ethernet/hisilicon/hns3/hns3_enet.c
@@ -2028,9 +2028,73 @@ static int hns3_fill_skb_to_desc(struct hns3_enet_ring *ring,
 	return bd_num;
 }
 
+static void hns3_tx_push_bd(struct hns3_enet_ring *ring, int num)
+{
+#define HNS3_BYTES_PER_64BIT		8
+
+	struct hns3_desc desc[HNS3_MAX_PUSH_BD_NUM] = {};
+	int offset = 0;
+
+	/* make sure everything is visible to device before
+	 * excuting tx push or updating doorbell
+	 */
+	dma_wmb();
+
+	do {
+		int idx = (ring->next_to_use - num + ring->desc_num) %
+			  ring->desc_num;
+
+		u64_stats_update_begin(&ring->syncp);
+		ring->stats.tx_push++;
+		u64_stats_update_end(&ring->syncp);
+		memcpy(&desc[offset], &ring->desc[idx],
+		       sizeof(struct hns3_desc));
+		offset++;
+	} while (--num);
+
+	__iowrite64_copy(ring->tqp->mem_base, desc,
+			 (sizeof(struct hns3_desc) * HNS3_MAX_PUSH_BD_NUM) /
+			 HNS3_BYTES_PER_64BIT);
+
+	io_stop_wc();
+}
+
+static void hns3_tx_mem_doorbell(struct hns3_enet_ring *ring)
+{
+#define HNS3_MEM_DOORBELL_OFFSET	64
+
+	__le64 bd_num = cpu_to_le64((u64)ring->pending_buf);
+
+	/* make sure everything is visible to device before
+	 * excuting tx push or updating doorbell
+	 */
+	dma_wmb();
+
+	__iowrite64_copy(ring->tqp->mem_base + HNS3_MEM_DOORBELL_OFFSET,
+			 &bd_num, 1);
+	u64_stats_update_begin(&ring->syncp);
+	ring->stats.tx_mem_doorbell += ring->pending_buf;
+	u64_stats_update_end(&ring->syncp);
+
+	io_stop_wc();
+}
+
 static void hns3_tx_doorbell(struct hns3_enet_ring *ring, int num,
 			     bool doorbell)
 {
+	struct net_device *netdev = ring_to_netdev(ring);
+	struct hns3_nic_priv *priv = netdev_priv(netdev);
+
+	/* when tx push is enabled, the packet whose number of BD below
+	 * HNS3_MAX_PUSH_BD_NUM can be pushed directly.
+	 */
+	if (test_bit(HNS3_NIC_STATE_TX_PUSH_ENABLE, &priv->state) && num &&
+	    !ring->pending_buf && num <= HNS3_MAX_PUSH_BD_NUM && doorbell) {
+		hns3_tx_push_bd(ring, num);
+		WRITE_ONCE(ring->last_to_use, ring->next_to_use);
+		return;
+	}
+
 	ring->pending_buf += num;
 
 	if (!doorbell) {
@@ -2038,11 +2102,12 @@ static void hns3_tx_doorbell(struct hns3_enet_ring *ring, int num,
 		return;
 	}
 
-	if (!ring->pending_buf)
-		return;
+	if (ring->tqp->mem_base)
+		hns3_tx_mem_doorbell(ring);
+	else
+		writel(ring->pending_buf,
+		       ring->tqp->io_base + HNS3_RING_TX_RING_TAIL_REG);
 
-	writel(ring->pending_buf,
-	       ring->tqp->io_base + HNS3_RING_TX_RING_TAIL_REG);
 	ring->pending_buf = 0;
 	WRITE_ONCE(ring->last_to_use, ring->next_to_use);
 }
@@ -2732,6 +2797,9 @@ static void hns3_dump_queue_stats(struct net_device *ndev,
 		    "seg_pkt_cnt: %llu, tx_more: %llu, restart_queue: %llu, tx_busy: %llu\n",
 		    tx_ring->stats.seg_pkt_cnt, tx_ring->stats.tx_more,
 		    tx_ring->stats.restart_queue, tx_ring->stats.tx_busy);
+
+	netdev_info(ndev, "tx_push: %llu, tx_mem_doorbell: %llu\n",
+		    tx_ring->stats.tx_push, tx_ring->stats.tx_mem_doorbell);
 }
 
 static void hns3_dump_queue_reg(struct net_device *ndev,
@@ -5094,6 +5162,9 @@ static void hns3_state_init(struct hnae3_handle *handle)
 
 	set_bit(HNS3_NIC_STATE_INITED, &priv->state);
 
+	if (test_bit(HNAE3_DEV_SUPPORT_TX_PUSH_B, ae_dev->caps))
+		set_bit(HNS3_NIC_STATE_TX_PUSH_ENABLE, &priv->state);
+
 	if (ae_dev->dev_version >= HNAE3_DEVICE_VERSION_V3)
 		set_bit(HNAE3_PFLAG_LIMIT_PROMISC, &handle->supported_pflags);