[PATCH net-next 0/8] net: hns3: add some cleanups & optimizations

[PATCH net-next 0/8] net: hns3: add some cleanups & optimizations

[Huazhong Tan]

This patchset includes some cleanups and optimizations for the HNS3
ethernet driver.

[patch 1/8] removes unused and unnecessary structures.

[patch 2/8] uses a ETH_ALEN u8 array to replace two mac_addr_*
field in struct hclge_mac_mgr_tbl_entry_cmd.

[patch 3/8] optimizes the barrier used in the IO path.

[patch 4/8] introduces macro ring_to_netdev() to get netdevive
from struct hns3_enet_ring variable.

[patch 5/8] makes struct hns3_enet_ring to be cacheline aligned

[patch 6/8] adds a minor cleanup for hns3_handle_rx_bd().

[patch 7/8] removes linear data allocating for fraglist SKB.

[patch 8/8] clears hardware error when resetting.

---
note:
In previous patchset, there are some bugfixes which needs below
new feature, which is only in 'net-next' but not in 'net' now:
net: hns3: support tx-scatter-gather-fraglist feature
net: hns3: add support for spoof check setting

So, these bugfixes will be upstreamed when the patch needed is
on 'net' tree.
---

Guojia Liao (1):
  net: hns3: optimized MAC address in management table.

Jian Shen (1):
  net: hns3: log and clear hardware error after reset complete

Yunsheng Lin (6):
  net: hns3: remove struct hns3_nic_ring_data in hns3_enet module
  net: hns3: minor optimization for barrier in IO path
  net: hns3: introduce ring_to_netdev() in enet module
  net: hns3: make struct hns3_enet_ring cacheline aligned
  net: hns3: minor cleanup for hns3_handle_rx_bd()
  net: hns3: do not allocate linear data for fraglist skb

 drivers/net/ethernet/hisilicon/hns3/hns3_debugfs.c |  24 +--
 drivers/net/ethernet/hisilicon/hns3/hns3_enet.c    | 204 ++++++++-------------
 drivers/net/ethernet/hisilicon/hns3/hns3_enet.h    |  20 +-
 drivers/net/ethernet/hisilicon/hns3/hns3_ethtool.c |  33 ++--
 .../net/ethernet/hisilicon/hns3/hns3pf/hclge_cmd.h |   4 +-
 .../ethernet/hisilicon/hns3/hns3pf/hclge_main.c    |   6 +-
 6 files changed, 111 insertions(+), 180 deletions(-)

-- 
2.7.4

[PATCH net-next 1/8] net: hns3: remove struct hns3_nic_ring_data in hns3_enet module

[Huazhong Tan]

From: Yunsheng Lin <linyunsheng@huawei.com>

Only the queue_index field in struct hns3_nic_ring_data is
used, other field is unused and unnecessary for hns3 driver,
so this patch removes it and move the queue_index field to
hns3_enet_ring.

This patch also removes an unused struct hns_queue declaration.

Signed-off-by: Yunsheng Lin <linyunsheng@huawei.com>
Signed-off-by: Huazhong Tan <tanhuazhong@huawei.com>
---
 drivers/net/ethernet/hisilicon/hns3/hns3_debugfs.c |  24 ++--
 drivers/net/ethernet/hisilicon/hns3/hns3_enet.c    | 139 +++++++--------------
 drivers/net/ethernet/hisilicon/hns3/hns3_enet.h    |  16 +--
 drivers/net/ethernet/hisilicon/hns3/hns3_ethtool.c |  33 +++--
 4 files changed, 74 insertions(+), 138 deletions(-)

diff --git a/drivers/net/ethernet/hisilicon/hns3/hns3_debugfs.c b/drivers/net/ethernet/hisilicon/hns3/hns3_debugfs.c
index 28961a6..fe5bc6f 100644
--- a/drivers/net/ethernet/hisilicon/hns3/hns3_debugfs.c
+++ b/drivers/net/ethernet/hisilicon/hns3/hns3_debugfs.c
@@ -16,15 +16,14 @@ static int hns3_dbg_queue_info(struct hnae3_handle *h,
 			       const char *cmd_buf)
 {
 	struct hns3_nic_priv *priv = h->priv;
-	struct hns3_nic_ring_data *ring_data;
 	struct hns3_enet_ring *ring;
 	u32 base_add_l, base_add_h;
 	u32 queue_num, queue_max;
 	u32 value, i = 0;
 	int cnt;
 
-	if (!priv->ring_data) {
-		dev_err(&h->pdev->dev, "ring_data is NULL\n");
+	if (!priv->ring) {
+		dev_err(&h->pdev->dev, "priv->ring is NULL\n");
 		return -EFAULT;
 	}
 
@@ -44,7 +43,6 @@ static int hns3_dbg_queue_info(struct hnae3_handle *h,
 		return -EINVAL;
 	}
 
-	ring_data = priv->ring_data;
 	for (i = queue_num; i < queue_max; i++) {
 		/* Each cycle needs to determine whether the instance is reset,
 		 * to prevent reference to invalid memory. And need to ensure
@@ -54,7 +52,7 @@ static int hns3_dbg_queue_info(struct hnae3_handle *h,
 		    test_bit(HNS3_NIC_STATE_RESETTING, &priv->state))
 			return -EPERM;
 
-		ring = ring_data[(u32)(i + h->kinfo.num_tqps)].ring;
+		ring = &priv->ring[(u32)(i + h->kinfo.num_tqps)];
 		base_add_h = readl_relaxed(ring->tqp->io_base +
 					   HNS3_RING_RX_RING_BASEADDR_H_REG);
 		base_add_l = readl_relaxed(ring->tqp->io_base +
@@ -86,7 +84,7 @@ static int hns3_dbg_queue_info(struct hnae3_handle *h,
 				      HNS3_RING_RX_RING_PKTNUM_RECORD_REG);
 		dev_info(&h->pdev->dev, "RX(%d) RING PKTNUM: %u\n", i, value);
 
-		ring = ring_data[i].ring;
+		ring = &priv->ring[i];
 		base_add_h = readl_relaxed(ring->tqp->io_base +
 					   HNS3_RING_TX_RING_BASEADDR_H_REG);
 		base_add_l = readl_relaxed(ring->tqp->io_base +
@@ -130,7 +128,6 @@ static int hns3_dbg_queue_info(struct hnae3_handle *h,
 static int hns3_dbg_queue_map(struct hnae3_handle *h)
 {
 	struct hns3_nic_priv *priv = h->priv;
-	struct hns3_nic_ring_data *ring_data;
 	int i;
 
 	if (!h->ae_algo->ops->get_global_queue_id)
@@ -143,15 +140,12 @@ static int hns3_dbg_queue_map(struct hnae3_handle *h)
 		u16 global_qid;
 
 		global_qid = h->ae_algo->ops->get_global_queue_id(h, i);
-		ring_data = &priv->ring_data[i];
-		if (!ring_data || !ring_data->ring ||
-		    !ring_data->ring->tqp_vector)
+		if (!priv->ring || !priv->ring[i].tqp_vector)
 			continue;
 
 		dev_info(&h->pdev->dev,
 			 "      %4d            %4d            %4d\n",
-			 i, global_qid,
-			 ring_data->ring->tqp_vector->vector_irq);
+			 i, global_qid, priv->ring[i].tqp_vector->vector_irq);
 	}
 
 	return 0;
@@ -160,7 +154,6 @@ static int hns3_dbg_queue_map(struct hnae3_handle *h)
 static int hns3_dbg_bd_info(struct hnae3_handle *h, const char *cmd_buf)
 {
 	struct hns3_nic_priv *priv = h->priv;
-	struct hns3_nic_ring_data *ring_data;
 	struct hns3_desc *rx_desc, *tx_desc;
 	struct device *dev = &h->pdev->dev;
 	struct hns3_enet_ring *ring;
@@ -183,8 +176,7 @@ static int hns3_dbg_bd_info(struct hnae3_handle *h, const char *cmd_buf)
 		return -EINVAL;
 	}
 
-	ring_data = priv->ring_data;
-	ring  = ring_data[q_num].ring;
+	ring  = &priv->ring[q_num];
 	value = readl_relaxed(ring->tqp->io_base + HNS3_RING_TX_RING_TAIL_REG);
 	tx_index = (cnt == 1) ? value : tx_index;
 
@@ -214,7 +206,7 @@ static int hns3_dbg_bd_info(struct hnae3_handle *h, const char *cmd_buf)
 	dev_info(dev, "(TX)vld_ra_ri: %u\n", tx_desc->tx.bdtp_fe_sc_vld_ra_ri);
 	dev_info(dev, "(TX)mss: %u\n", tx_desc->tx.mss);
 
-	ring  = ring_data[q_num + h->kinfo.num_tqps].ring;
+	ring  = &priv->ring[q_num + h->kinfo.num_tqps];
 	value = readl_relaxed(ring->tqp->io_base + HNS3_RING_RX_RING_TAIL_REG);
 	rx_index = (cnt == 1) ? value : tx_index;
 	rx_desc	 = &ring->desc[rx_index];
diff --git a/drivers/net/ethernet/hisilicon/hns3/hns3_enet.c b/drivers/net/ethernet/hisilicon/hns3/hns3_enet.c
index 6e0b261..635bdda 100644
--- a/drivers/net/ethernet/hisilicon/hns3/hns3_enet.c
+++ b/drivers/net/ethernet/hisilicon/hns3/hns3_enet.c
@@ -483,7 +483,7 @@ static void hns3_reset_tx_queue(struct hnae3_handle *h)
 
 	for (i = 0; i < h->kinfo.num_tqps; i++) {
 		dev_queue = netdev_get_tx_queue(ndev,
-						priv->ring_data[i].queue_index);
+						priv->ring[i].queue_index);
 		netdev_tx_reset_queue(dev_queue);
 	}
 }
@@ -1390,9 +1390,7 @@ static int hns3_fill_skb_to_desc(struct hns3_enet_ring *ring,
 netdev_tx_t hns3_nic_net_xmit(struct sk_buff *skb, struct net_device *netdev)
 {
 	struct hns3_nic_priv *priv = netdev_priv(netdev);
-	struct hns3_nic_ring_data *ring_data =
-		&tx_ring_data(priv, skb->queue_mapping);
-	struct hns3_enet_ring *ring = ring_data->ring;
+	struct hns3_enet_ring *ring = &priv->ring[skb->queue_mapping];
 	struct netdev_queue *dev_queue;
 	int pre_ntu, next_to_use_head;
 	struct sk_buff *frag_skb;
@@ -1444,7 +1442,7 @@ netdev_tx_t hns3_nic_net_xmit(struct sk_buff *skb, struct net_device *netdev)
 				cpu_to_le16(BIT(HNS3_TXD_FE_B));
 
 	/* Complete translate all packets */
-	dev_queue = netdev_get_tx_queue(netdev, ring_data->queue_index);
+	dev_queue = netdev_get_tx_queue(netdev, ring->queue_index);
 	netdev_tx_sent_queue(dev_queue, skb->len);
 
 	wmb(); /* Commit all data before submit */
@@ -1461,7 +1459,7 @@ netdev_tx_t hns3_nic_net_xmit(struct sk_buff *skb, struct net_device *netdev)
 	return NETDEV_TX_OK;
 
 out_net_tx_busy:
-	netif_stop_subqueue(netdev, ring_data->queue_index);
+	netif_stop_subqueue(netdev, ring->queue_index);
 	smp_mb(); /* Commit all data before submit */
 
 	return NETDEV_TX_BUSY;
@@ -1584,7 +1582,7 @@ static void hns3_nic_get_stats64(struct net_device *netdev,
 
 	for (idx = 0; idx < queue_num; idx++) {
 		/* fetch the tx stats */
-		ring = priv->ring_data[idx].ring;
+		ring = &priv->ring[idx];
 		do {
 			start = u64_stats_fetch_begin_irq(&ring->syncp);
 			tx_bytes += ring->stats.tx_bytes;
@@ -1602,7 +1600,7 @@ static void hns3_nic_get_stats64(struct net_device *netdev,
 		} while (u64_stats_fetch_retry_irq(&ring->syncp, start));
 
 		/* fetch the rx stats */
-		ring = priv->ring_data[idx + queue_num].ring;
+		ring = &priv->ring[idx + queue_num];
 		do {
 			start = u64_stats_fetch_begin_irq(&ring->syncp);
 			rx_bytes += ring->stats.rx_bytes;
@@ -1807,7 +1805,7 @@ static bool hns3_get_tx_timeo_queue_info(struct net_device *ndev)
 
 	priv->tx_timeout_count++;
 
-	tx_ring = priv->ring_data[timeout_queue].ring;
+	tx_ring = &priv->ring[timeout_queue];
 	napi = &tx_ring->tqp_vector->napi;
 
 	netdev_info(ndev,
@@ -3484,13 +3482,13 @@ static int hns3_nic_init_vector_data(struct hns3_nic_priv *priv)
 		tqp_vector = &priv->tqp_vector[vector_i];
 
 		hns3_add_ring_to_group(&tqp_vector->tx_group,
-				       priv->ring_data[i].ring);
+				       &priv->ring[i]);
 
 		hns3_add_ring_to_group(&tqp_vector->rx_group,
-				       priv->ring_data[i + tqp_num].ring);
+				       &priv->ring[i + tqp_num]);
 
-		priv->ring_data[i].ring->tqp_vector = tqp_vector;
-		priv->ring_data[i + tqp_num].ring->tqp_vector = tqp_vector;
+		priv->ring[i].tqp_vector = tqp_vector;
+		priv->ring[i + tqp_num].tqp_vector = tqp_vector;
 		tqp_vector->num_tqps++;
 	}
 
@@ -3634,28 +3632,22 @@ static int hns3_nic_dealloc_vector_data(struct hns3_nic_priv *priv)
 	return 0;
 }
 
-static int hns3_ring_get_cfg(struct hnae3_queue *q, struct hns3_nic_priv *priv,
-			     unsigned int ring_type)
+static void hns3_ring_get_cfg(struct hnae3_queue *q, struct hns3_nic_priv *priv,
+			      unsigned int ring_type)
 {
-	struct hns3_nic_ring_data *ring_data = priv->ring_data;
 	int queue_num = priv->ae_handle->kinfo.num_tqps;
-	struct pci_dev *pdev = priv->ae_handle->pdev;
 	struct hns3_enet_ring *ring;
 	int desc_num;
 
-	ring = devm_kzalloc(&pdev->dev, sizeof(*ring), GFP_KERNEL);
-	if (!ring)
-		return -ENOMEM;
-
 	if (ring_type == HNAE3_RING_TYPE_TX) {
+		ring = &priv->ring[q->tqp_index];
 		desc_num = priv->ae_handle->kinfo.num_tx_desc;
-		ring_data[q->tqp_index].ring = ring;
-		ring_data[q->tqp_index].queue_index = q->tqp_index;
+		ring->queue_index = q->tqp_index;
 		ring->io_base = (u8 __iomem *)q->io_base + HNS3_TX_REG_OFFSET;
 	} else {
+		ring = &priv->ring[q->tqp_index + queue_num];
 		desc_num = priv->ae_handle->kinfo.num_rx_desc;
-		ring_data[q->tqp_index + queue_num].ring = ring;
-		ring_data[q->tqp_index + queue_num].queue_index = q->tqp_index;
+		ring->queue_index = q->tqp_index;
 		ring->io_base = q->io_base;
 	}
 
@@ -3670,76 +3662,41 @@ static int hns3_ring_get_cfg(struct hnae3_queue *q, struct hns3_nic_priv *priv,
 	ring->desc_num = desc_num;
 	ring->next_to_use = 0;
 	ring->next_to_clean = 0;
-
-	return 0;
 }
 
-static int hns3_queue_to_ring(struct hnae3_queue *tqp,
-			      struct hns3_nic_priv *priv)
+static void hns3_queue_to_ring(struct hnae3_queue *tqp,
+			       struct hns3_nic_priv *priv)
 {
-	int ret;
-
-	ret = hns3_ring_get_cfg(tqp, priv, HNAE3_RING_TYPE_TX);
-	if (ret)
-		return ret;
-
-	ret = hns3_ring_get_cfg(tqp, priv, HNAE3_RING_TYPE_RX);
-	if (ret) {
-		devm_kfree(priv->dev, priv->ring_data[tqp->tqp_index].ring);
-		return ret;
-	}
-
-	return 0;
+	hns3_ring_get_cfg(tqp, priv, HNAE3_RING_TYPE_TX);
+	hns3_ring_get_cfg(tqp, priv, HNAE3_RING_TYPE_RX);
 }
 
 static int hns3_get_ring_config(struct hns3_nic_priv *priv)
 {
 	struct hnae3_handle *h = priv->ae_handle;
 	struct pci_dev *pdev = h->pdev;
-	int i, ret;
+	int i;
 
-	priv->ring_data =  devm_kzalloc(&pdev->dev,
-					array3_size(h->kinfo.num_tqps,
-						    sizeof(*priv->ring_data),
-						    2),
-					GFP_KERNEL);
-	if (!priv->ring_data)
+	priv->ring = devm_kzalloc(&pdev->dev,
+				  array3_size(h->kinfo.num_tqps,
+					      sizeof(*priv->ring), 2),
+				  GFP_KERNEL);
+	if (!priv->ring)
 		return -ENOMEM;
 
-	for (i = 0; i < h->kinfo.num_tqps; i++) {
-		ret = hns3_queue_to_ring(h->kinfo.tqp[i], priv);
-		if (ret)
-			goto err;
-	}
+	for (i = 0; i < h->kinfo.num_tqps; i++)
+		hns3_queue_to_ring(h->kinfo.tqp[i], priv);
 
 	return 0;
-err:
-	while (i--) {
-		devm_kfree(priv->dev, priv->ring_data[i].ring);
-		devm_kfree(priv->dev,
-			   priv->ring_data[i + h->kinfo.num_tqps].ring);
-	}
-
-	devm_kfree(&pdev->dev, priv->ring_data);
-	priv->ring_data = NULL;
-	return ret;
 }
 
 static void hns3_put_ring_config(struct hns3_nic_priv *priv)
 {
-	struct hnae3_handle *h = priv->ae_handle;
-	int i;
-
-	if (!priv->ring_data)
+	if (!priv->ring)
 		return;
 
-	for (i = 0; i < h->kinfo.num_tqps; i++) {
-		devm_kfree(priv->dev, priv->ring_data[i].ring);
-		devm_kfree(priv->dev,
-			   priv->ring_data[i + h->kinfo.num_tqps].ring);
-	}
-	devm_kfree(priv->dev, priv->ring_data);
-	priv->ring_data = NULL;
+	devm_kfree(priv->dev, priv->ring);
+	priv->ring = NULL;
 }
 
 static int hns3_alloc_ring_memory(struct hns3_enet_ring *ring)
@@ -3856,7 +3813,7 @@ static void hns3_init_tx_ring_tc(struct hns3_nic_priv *priv)
 		for (j = 0; j < tc_info->tqp_count; j++) {
 			struct hnae3_queue *q;
 
-			q = priv->ring_data[tc_info->tqp_offset + j].ring->tqp;
+			q = priv->ring[tc_info->tqp_offset + j].tqp;
 			hns3_write_dev(q, HNS3_RING_TX_RING_TC_REG,
 				       tc_info->tc);
 		}
@@ -3871,21 +3828,21 @@ int hns3_init_all_ring(struct hns3_nic_priv *priv)
 	int ret;
 
 	for (i = 0; i < ring_num; i++) {
-		ret = hns3_alloc_ring_memory(priv->ring_data[i].ring);
+		ret = hns3_alloc_ring_memory(&priv->ring[i]);
 		if (ret) {
 			dev_err(priv->dev,
 				"Alloc ring memory fail! ret=%d\n", ret);
 			goto out_when_alloc_ring_memory;
 		}
 
-		u64_stats_init(&priv->ring_data[i].ring->syncp);
+		u64_stats_init(&priv->ring[i].syncp);
 	}
 
 	return 0;
 
 out_when_alloc_ring_memory:
 	for (j = i - 1; j >= 0; j--)
-		hns3_fini_ring(priv->ring_data[j].ring);
+		hns3_fini_ring(&priv->ring[j]);
 
 	return -ENOMEM;
 }
@@ -3896,8 +3853,8 @@ int hns3_uninit_all_ring(struct hns3_nic_priv *priv)
 	int i;
 
 	for (i = 0; i < h->kinfo.num_tqps; i++) {
-		hns3_fini_ring(priv->ring_data[i].ring);
-		hns3_fini_ring(priv->ring_data[i + h->kinfo.num_tqps].ring);
+		hns3_fini_ring(&priv->ring[i]);
+		hns3_fini_ring(&priv->ring[i + h->kinfo.num_tqps]);
 	}
 	return 0;
 }
@@ -4058,7 +4015,7 @@ static int hns3_client_init(struct hnae3_handle *handle)
 	ret = hns3_init_all_ring(priv);
 	if (ret) {
 		ret = -ENOMEM;
-		goto out_init_ring_data;
+		goto out_init_ring;
 	}
 
 	ret = hns3_init_phy(netdev);
@@ -4097,12 +4054,12 @@ static int hns3_client_init(struct hnae3_handle *handle)
 	hns3_uninit_phy(netdev);
 out_init_phy:
 	hns3_uninit_all_ring(priv);
-out_init_ring_data:
+out_init_ring:
 	hns3_nic_uninit_vector_data(priv);
 out_init_vector_data:
 	hns3_nic_dealloc_vector_data(priv);
 out_alloc_vector_data:
-	priv->ring_data = NULL;
+	priv->ring = NULL;
 out_get_ring_cfg:
 	priv->ae_handle = NULL;
 	free_netdev(netdev);
@@ -4309,10 +4266,10 @@ static void hns3_clear_all_ring(struct hnae3_handle *h, bool force)
 	for (i = 0; i < h->kinfo.num_tqps; i++) {
 		struct hns3_enet_ring *ring;
 
-		ring = priv->ring_data[i].ring;
+		ring = &priv->ring[i];
 		hns3_clear_tx_ring(ring);
 
-		ring = priv->ring_data[i + h->kinfo.num_tqps].ring;
+		ring = &priv->ring[i + h->kinfo.num_tqps];
 		/* Continue to clear other rings even if clearing some
 		 * rings failed.
 		 */
@@ -4336,16 +4293,16 @@ int hns3_nic_reset_all_ring(struct hnae3_handle *h)
 		if (ret)
 			return ret;
 
-		hns3_init_ring_hw(priv->ring_data[i].ring);
+		hns3_init_ring_hw(&priv->ring[i]);
 
 		/* We need to clear tx ring here because self test will
 		 * use the ring and will not run down before up
 		 */
-		hns3_clear_tx_ring(priv->ring_data[i].ring);
-		priv->ring_data[i].ring->next_to_clean = 0;
-		priv->ring_data[i].ring->next_to_use = 0;
+		hns3_clear_tx_ring(&priv->ring[i]);
+		priv->ring[i].next_to_clean = 0;
+		priv->ring[i].next_to_use = 0;
 
-		rx_ring = priv->ring_data[i + h->kinfo.num_tqps].ring;
+		rx_ring = &priv->ring[i + h->kinfo.num_tqps];
 		hns3_init_ring_hw(rx_ring);
 		ret = hns3_clear_rx_ring(rx_ring);
 		if (ret)
diff --git a/drivers/net/ethernet/hisilicon/hns3/hns3_enet.h b/drivers/net/ethernet/hisilicon/hns3/hns3_enet.h
index c5b7c22..3322284 100644
--- a/drivers/net/ethernet/hisilicon/hns3/hns3_enet.h
+++ b/drivers/net/ethernet/hisilicon/hns3/hns3_enet.h
@@ -409,6 +409,7 @@ struct hns3_enet_ring {
 	struct hns3_enet_ring *next;
 	struct hns3_enet_tqp_vector *tqp_vector;
 	struct hnae3_queue *tqp;
+	int queue_index;
 	struct device *dev; /* will be used for DMA mapping of descriptors */
 
 	/* statistic */
@@ -436,17 +437,6 @@ struct hns3_enet_ring {
 	struct sk_buff *tail_skb;
 };
 
-struct hns_queue;
-
-struct hns3_nic_ring_data {
-	struct hns3_enet_ring *ring;
-	struct napi_struct napi;
-	int queue_index;
-	int (*poll_one)(struct hns3_nic_ring_data *, int, void *);
-	void (*ex_process)(struct hns3_nic_ring_data *, struct sk_buff *);
-	void (*fini_process)(struct hns3_nic_ring_data *);
-};
-
 enum hns3_flow_level_range {
 	HNS3_FLOW_LOW = 0,
 	HNS3_FLOW_MID = 1,
@@ -522,7 +512,7 @@ struct hns3_nic_priv {
 	 * the cb for nic to manage the ring buffer, the first half of the
 	 * array is for tx_ring and vice versa for the second half
 	 */
-	struct hns3_nic_ring_data *ring_data;
+	struct hns3_enet_ring *ring;
 	struct hns3_enet_tqp_vector *tqp_vector;
 	u16 vector_num;
 
@@ -620,8 +610,6 @@ static inline bool hns3_nic_resetting(struct net_device *netdev)
 #define ring_to_dma_dir(ring) (HNAE3_IS_TX_RING(ring) ? \
 	DMA_TO_DEVICE : DMA_FROM_DEVICE)
 
-#define tx_ring_data(priv, idx) ((priv)->ring_data[idx])
-
 #define hns3_buf_size(_ring) ((_ring)->buf_size)
 
 static inline unsigned int hns3_page_order(struct hns3_enet_ring *ring)
diff --git a/drivers/net/ethernet/hisilicon/hns3/hns3_ethtool.c b/drivers/net/ethernet/hisilicon/hns3/hns3_ethtool.c
index 680c350..50b07b9 100644
--- a/drivers/net/ethernet/hisilicon/hns3/hns3_ethtool.c
+++ b/drivers/net/ethernet/hisilicon/hns3/hns3_ethtool.c
@@ -203,7 +203,7 @@ static u32 hns3_lb_check_rx_ring(struct hns3_nic_priv *priv, u32 budget)
 
 	kinfo = &h->kinfo;
 	for (i = kinfo->num_tqps; i < kinfo->num_tqps * 2; i++) {
-		struct hns3_enet_ring *ring = priv->ring_data[i].ring;
+		struct hns3_enet_ring *ring = &priv->ring[i];
 		struct hns3_enet_ring_group *rx_group;
 		u64 pre_rx_pkt;
 
@@ -226,7 +226,7 @@ static void hns3_lb_clear_tx_ring(struct hns3_nic_priv *priv, u32 start_ringid,
 	u32 i;
 
 	for (i = start_ringid; i <= end_ringid; i++) {
-		struct hns3_enet_ring *ring = priv->ring_data[i].ring;
+		struct hns3_enet_ring *ring = &priv->ring[i];
 
 		hns3_clean_tx_ring(ring);
 	}
@@ -491,7 +491,7 @@ static u64 *hns3_get_stats_tqps(struct hnae3_handle *handle, u64 *data)
 
 	/* get stats for Tx */
 	for (i = 0; i < kinfo->num_tqps; i++) {
-		ring = nic_priv->ring_data[i].ring;
+		ring = &nic_priv->ring[i];
 		for (j = 0; j < HNS3_TXQ_STATS_COUNT; j++) {
 			stat = (u8 *)ring + hns3_txq_stats[j].stats_offset;
 			*data++ = *(u64 *)stat;
@@ -500,7 +500,7 @@ static u64 *hns3_get_stats_tqps(struct hnae3_handle *handle, u64 *data)
 
 	/* get stats for Rx */
 	for (i = 0; i < kinfo->num_tqps; i++) {
-		ring = nic_priv->ring_data[i + kinfo->num_tqps].ring;
+		ring = &nic_priv->ring[i + kinfo->num_tqps];
 		for (j = 0; j < HNS3_RXQ_STATS_COUNT; j++) {
 			stat = (u8 *)ring + hns3_rxq_stats[j].stats_offset;
 			*data++ = *(u64 *)stat;
@@ -603,8 +603,8 @@ static void hns3_get_ringparam(struct net_device *netdev,
 	param->tx_max_pending = HNS3_RING_MAX_PENDING;
 	param->rx_max_pending = HNS3_RING_MAX_PENDING;
 
-	param->tx_pending = priv->ring_data[0].ring->desc_num;
-	param->rx_pending = priv->ring_data[queue_num].ring->desc_num;
+	param->tx_pending = priv->ring[0].desc_num;
+	param->rx_pending = priv->ring[queue_num].desc_num;
 }
 
 static void hns3_get_pauseparam(struct net_device *netdev,
@@ -906,9 +906,8 @@ static void hns3_change_all_ring_bd_num(struct hns3_nic_priv *priv,
 	h->kinfo.num_rx_desc = rx_desc_num;
 
 	for (i = 0; i < h->kinfo.num_tqps; i++) {
-		priv->ring_data[i].ring->desc_num = tx_desc_num;
-		priv->ring_data[i + h->kinfo.num_tqps].ring->desc_num =
-			rx_desc_num;
+		priv->ring[i].desc_num = tx_desc_num;
+		priv->ring[i + h->kinfo.num_tqps].desc_num = rx_desc_num;
 	}
 }
 
@@ -924,7 +923,7 @@ static struct hns3_enet_ring *hns3_backup_ringparam(struct hns3_nic_priv *priv)
 		return NULL;
 
 	for (i = 0; i < handle->kinfo.num_tqps * 2; i++) {
-		memcpy(&tmp_rings[i], priv->ring_data[i].ring,
+		memcpy(&tmp_rings[i], &priv->ring[i],
 		       sizeof(struct hns3_enet_ring));
 		tmp_rings[i].skb = NULL;
 	}
@@ -972,8 +971,8 @@ static int hns3_set_ringparam(struct net_device *ndev,
 	/* Hardware requires that its descriptors must be multiple of eight */
 	new_tx_desc_num = ALIGN(param->tx_pending, HNS3_RING_BD_MULTIPLE);
 	new_rx_desc_num = ALIGN(param->rx_pending, HNS3_RING_BD_MULTIPLE);
-	old_tx_desc_num = priv->ring_data[0].ring->desc_num;
-	old_rx_desc_num = priv->ring_data[queue_num].ring->desc_num;
+	old_tx_desc_num = priv->ring[0].desc_num;
+	old_rx_desc_num = priv->ring[queue_num].desc_num;
 	if (old_tx_desc_num == new_tx_desc_num &&
 	    old_rx_desc_num == new_rx_desc_num)
 		return 0;
@@ -1002,7 +1001,7 @@ static int hns3_set_ringparam(struct net_device *ndev,
 		hns3_change_all_ring_bd_num(priv, old_tx_desc_num,
 					    old_rx_desc_num);
 		for (i = 0; i < h->kinfo.num_tqps * 2; i++)
-			memcpy(priv->ring_data[i].ring, &tmp_rings[i],
+			memcpy(&priv->ring[i], &tmp_rings[i],
 			       sizeof(struct hns3_enet_ring));
 	} else {
 		for (i = 0; i < h->kinfo.num_tqps * 2; i++)
@@ -1103,8 +1102,8 @@ static int hns3_get_coalesce_per_queue(struct net_device *netdev, u32 queue,
 		return -EINVAL;
 	}
 
-	tx_vector = priv->ring_data[queue].ring->tqp_vector;
-	rx_vector = priv->ring_data[queue_num + queue].ring->tqp_vector;
+	tx_vector = priv->ring[queue].tqp_vector;
+	rx_vector = priv->ring[queue_num + queue].tqp_vector;
 
 	cmd->use_adaptive_tx_coalesce =
 			tx_vector->tx_group.coal.gl_adapt_enable;
@@ -1229,8 +1228,8 @@ static void hns3_set_coalesce_per_queue(struct net_device *netdev,
 	struct hnae3_handle *h = priv->ae_handle;
 	int queue_num = h->kinfo.num_tqps;
 
-	tx_vector = priv->ring_data[queue].ring->tqp_vector;
-	rx_vector = priv->ring_data[queue_num + queue].ring->tqp_vector;
+	tx_vector = priv->ring[queue].tqp_vector;
+	rx_vector = priv->ring[queue_num + queue].tqp_vector;
 
 	tx_vector->tx_group.coal.gl_adapt_enable =
 				cmd->use_adaptive_tx_coalesce;
-- 
2.7.4

[PATCH net-next 2/8] net: hns3: optimized MAC address in management table.

[Huazhong Tan]

From: Guojia Liao <liaoguojia@huawei.com>

mac_addr_hi32 and mac_addr_lo16 are used to store the MAC address
for management table. But using array of mac_addr[ETH_ALEN] would
be more general and not need to care about the big-endian mode of
the CPU.

Signed-off-by: Guojia Liao <liaoguojia@huawei.com>
Signed-off-by: Huazhong Tan <tanhuazhong@huawei.com>
---
 drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_cmd.h  | 4 ++--
 drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_main.c | 3 +--
 2 files changed, 3 insertions(+), 4 deletions(-)

diff --git a/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_cmd.h b/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_cmd.h
index 3578832..919911f 100644
--- a/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_cmd.h
+++ b/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_cmd.h
@@ -5,6 +5,7 @@
 #define __HCLGE_CMD_H
 #include <linux/types.h>
 #include <linux/io.h>
+#include <linux/etherdevice.h>
 
 #define HCLGE_CMDQ_TX_TIMEOUT		30000
 
@@ -712,8 +713,7 @@ struct hclge_mac_mgr_tbl_entry_cmd {
 	u8      flags;
 	u8      resp_code;
 	__le16  vlan_tag;
-	__le32  mac_addr_hi32;
-	__le16  mac_addr_lo16;
+	u8      mac_addr[ETH_ALEN];
 	__le16  rsv1;
 	__le16  ethter_type;
 	__le16  egress_port;
diff --git a/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_main.c b/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_main.c
index 8a3a4fd..ffdb8ce 100644
--- a/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_main.c
+++ b/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_main.c
@@ -325,8 +325,7 @@ static const struct hclge_mac_mgr_tbl_entry_cmd hclge_mgr_table[] = {
 	{
 		.flags = HCLGE_MAC_MGR_MASK_VLAN_B,
 		.ethter_type = cpu_to_le16(ETH_P_LLDP),
-		.mac_addr_hi32 = cpu_to_le32(htonl(0x0180C200)),
-		.mac_addr_lo16 = cpu_to_le16(htons(0x000E)),
+		.mac_addr = {0x01, 0x80, 0xc2, 0x00, 0x00, 0x0e},
 		.i_port_bitmap = 0x1,
 	},
 };
-- 
2.7.4

[PATCH net-next 3/8] net: hns3: minor optimization for barrier in IO path

[Huazhong Tan]

From: Yunsheng Lin <linyunsheng@huawei.com>

Currently, the TX and RX ring in a queue is bounded to the
same IRQ, there may be unnecessary barrier op when only one of
the ring need to be processed.

This patch adjusts the location of rmb() in hns3_clean_tx_ring()
and adds a checking in hns3_clean_rx_ring() to avoid unnecessary
barrier op when there is nothing to do for the ring.

Signed-off-by: Yunsheng Lin <linyunsheng@huawei.com>
Signed-off-by: Huazhong Tan <tanhuazhong@huawei.com>
---
 drivers/net/ethernet/hisilicon/hns3/hns3_enet.c | 10 +++++++---
 1 file changed, 7 insertions(+), 3 deletions(-)

diff --git a/drivers/net/ethernet/hisilicon/hns3/hns3_enet.c b/drivers/net/ethernet/hisilicon/hns3/hns3_enet.c
index 635bdda..089cd58 100644
--- a/drivers/net/ethernet/hisilicon/hns3/hns3_enet.c
+++ b/drivers/net/ethernet/hisilicon/hns3/hns3_enet.c
@@ -2485,11 +2485,12 @@ void hns3_clean_tx_ring(struct hns3_enet_ring *ring)
 	int head;
 
 	head = readl_relaxed(ring->tqp->io_base + HNS3_RING_TX_RING_HEAD_REG);
-	rmb(); /* Make sure head is ready before touch any data */
 
 	if (is_ring_empty(ring) || head == ring->next_to_clean)
 		return; /* no data to poll */
 
+	rmb(); /* Make sure head is ready before touch any data */
+
 	if (unlikely(!is_valid_clean_head(ring, head))) {
 		netdev_err(netdev, "wrong head (%d, %d-%d)\n", head,
 			   ring->next_to_use, ring->next_to_clean);
@@ -3105,11 +3106,14 @@ int hns3_clean_rx_ring(struct hns3_enet_ring *ring, int budget,
 	int err, num;
 
 	num = readl_relaxed(ring->tqp->io_base + HNS3_RING_RX_RING_FBDNUM_REG);
-	rmb(); /* Make sure num taken effect before the other data is touched */
-
 	num -= unused_count;
 	unused_count -= ring->pending_buf;
 
+	if (num <= 0)
+		goto out;
+
+	rmb(); /* Make sure num taken effect before the other data is touched */
+
 	while (recv_pkts < budget && recv_bds < num) {
 		/* Reuse or realloc buffers */
 		if (unused_count >= RCB_NOF_ALLOC_RX_BUFF_ONCE) {
-- 
2.7.4

[PATCH net-next 4/8] net: hns3: introduce ring_to_netdev() in enet module

[Huazhong Tan]

From: Yunsheng Lin <linyunsheng@huawei.com>

There are a few places that need to access the netdev of a ring
through ring->tqp->handle->kinfo.netdev, and ring->tqp is a struct
which both in enet and hclge modules, it is better to use the
struct that is only used in enet module.

This patch adds the ring_to_netdev() to access the netdev of ring
through ring->tqp_vector->napi.dev.

Signed-off-by: Yunsheng Lin <linyunsheng@huawei.com>
Signed-off-by: Huazhong Tan <tanhuazhong@huawei.com>
---
 drivers/net/ethernet/hisilicon/hns3/hns3_enet.c | 14 +++++++-------
 drivers/net/ethernet/hisilicon/hns3/hns3_enet.h |  2 ++
 2 files changed, 9 insertions(+), 7 deletions(-)

diff --git a/drivers/net/ethernet/hisilicon/hns3/hns3_enet.c b/drivers/net/ethernet/hisilicon/hns3/hns3_enet.c
index 089cd58..422fa4d 100644
--- a/drivers/net/ethernet/hisilicon/hns3/hns3_enet.c
+++ b/drivers/net/ethernet/hisilicon/hns3/hns3_enet.c
@@ -2478,7 +2478,7 @@ static int is_valid_clean_head(struct hns3_enet_ring *ring, int h)
 
 void hns3_clean_tx_ring(struct hns3_enet_ring *ring)
 {
-	struct net_device *netdev = ring->tqp->handle->kinfo.netdev;
+	struct net_device *netdev = ring_to_netdev(ring);
 	struct hns3_nic_priv *priv = netdev_priv(netdev);
 	struct netdev_queue *dev_queue;
 	int bytes, pkts;
@@ -2560,7 +2560,7 @@ static void hns3_nic_alloc_rx_buffers(struct hns3_enet_ring *ring,
 				ring->stats.sw_err_cnt++;
 				u64_stats_update_end(&ring->syncp);
 
-				hns3_rl_err(ring->tqp_vector->napi.dev,
+				hns3_rl_err(ring_to_netdev(ring),
 					    "alloc rx buffer failed: %d\n",
 					    ret);
 				break;
@@ -2669,7 +2669,7 @@ static int hns3_gro_complete(struct sk_buff *skb, u32 l234info)
 static void hns3_rx_checksum(struct hns3_enet_ring *ring, struct sk_buff *skb,
 			     u32 l234info, u32 bd_base_info, u32 ol_info)
 {
-	struct net_device *netdev = ring->tqp->handle->kinfo.netdev;
+	struct net_device *netdev = ring_to_netdev(ring);
 	int l3_type, l4_type;
 	int ol4_type;
 
@@ -2785,7 +2785,7 @@ static int hns3_alloc_skb(struct hns3_enet_ring *ring, unsigned int length,
 {
 #define HNS3_NEED_ADD_FRAG	1
 	struct hns3_desc_cb *desc_cb = &ring->desc_cb[ring->next_to_clean];
-	struct net_device *netdev = ring->tqp->handle->kinfo.netdev;
+	struct net_device *netdev = ring_to_netdev(ring);
 	struct sk_buff *skb;
 
 	ring->skb = napi_alloc_skb(&ring->tqp_vector->napi, HNS3_RX_HEAD_SIZE);
@@ -2866,7 +2866,7 @@ static int hns3_add_frag(struct hns3_enet_ring *ring, struct hns3_desc *desc,
 			new_skb = napi_alloc_skb(&ring->tqp_vector->napi,
 						 HNS3_RX_HEAD_SIZE);
 			if (unlikely(!new_skb)) {
-				hns3_rl_err(ring->tqp_vector->napi.dev,
+				hns3_rl_err(ring_to_netdev(ring),
 					    "alloc rx fraglist skb fail\n");
 				return -ENXIO;
 			}
@@ -2942,7 +2942,7 @@ static void hns3_set_rx_skb_rss_type(struct hns3_enet_ring *ring,
 
 static int hns3_handle_bdinfo(struct hns3_enet_ring *ring, struct sk_buff *skb)
 {
-	struct net_device *netdev = ring->tqp->handle->kinfo.netdev;
+	struct net_device *netdev = ring_to_netdev(ring);
 	enum hns3_pkt_l2t_type l2_frame_type;
 	u32 bd_base_info, l234info, ol_info;
 	struct hns3_desc *desc;
@@ -4224,7 +4224,7 @@ static int hns3_clear_rx_ring(struct hns3_enet_ring *ring)
 				/* if alloc new buffer fail, exit directly
 				 * and reclear in up flow.
 				 */
-				netdev_warn(ring->tqp->handle->kinfo.netdev,
+				netdev_warn(ring_to_netdev(ring),
 					    "reserve buffer map failed, ret = %d\n",
 					    ret);
 				return ret;
diff --git a/drivers/net/ethernet/hisilicon/hns3/hns3_enet.h b/drivers/net/ethernet/hisilicon/hns3/hns3_enet.h
index 3322284..8a88002 100644
--- a/drivers/net/ethernet/hisilicon/hns3/hns3_enet.h
+++ b/drivers/net/ethernet/hisilicon/hns3/hns3_enet.h
@@ -607,6 +607,8 @@ static inline bool hns3_nic_resetting(struct net_device *netdev)
 
 #define ring_to_dev(ring) ((ring)->dev)
 
+#define ring_to_netdev(ring)	((ring)->tqp_vector->napi.dev)
+
 #define ring_to_dma_dir(ring) (HNAE3_IS_TX_RING(ring) ? \
 	DMA_TO_DEVICE : DMA_FROM_DEVICE)
 
-- 
2.7.4

[PATCH net-next 5/8] net: hns3: make struct hns3_enet_ring cacheline aligned

[Huazhong Tan]

From: Yunsheng Lin <linyunsheng@huawei.com>

Since struct hns3_enet_ring is a frequently used in critical data
path, so make it cacheline aligned as struct hns3_enet_tqp_vector.

Signed-off-by: Yunsheng Lin <linyunsheng@huawei.com>
Signed-off-by: Huazhong Tan <tanhuazhong@huawei.com>
---
 drivers/net/ethernet/hisilicon/hns3/hns3_enet.h | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/drivers/net/ethernet/hisilicon/hns3/hns3_enet.h b/drivers/net/ethernet/hisilicon/hns3/hns3_enet.h
index 8a88002..0725dc5 100644
--- a/drivers/net/ethernet/hisilicon/hns3/hns3_enet.h
+++ b/drivers/net/ethernet/hisilicon/hns3/hns3_enet.h
@@ -435,7 +435,7 @@ struct hns3_enet_ring {
 	int pending_buf;
 	struct sk_buff *skb;
 	struct sk_buff *tail_skb;
-};
+} ____cacheline_internodealigned_in_smp;
 
 enum hns3_flow_level_range {
 	HNS3_FLOW_LOW = 0,
-- 
2.7.4

[PATCH net-next 6/8] net: hns3: minor cleanup for hns3_handle_rx_bd()

[Huazhong Tan]

From: Yunsheng Lin <linyunsheng@huawei.com>

Since commit e55970950556 ("net: hns3: Add handling of GRO Pkts
not fully RX'ed in NAPI poll"), ring->skb is used to record the
current SKB when processing the RX BD in hns3_handle_rx_bd(),
so the parameter out_skb is unnecessary.

This patch also adjusts the err checking to reduce duplication
in hns3_handle_rx_bd(), and "err == -ENXIO" is rare case, so put
it in the unlikely annotation.

Signed-off-by: Yunsheng Lin <linyunsheng@huawei.com>
Signed-off-by: Huazhong Tan <tanhuazhong@huawei.com>
---
 drivers/net/ethernet/hisilicon/hns3/hns3_enet.c | 38 +++++++++----------------
 1 file changed, 13 insertions(+), 25 deletions(-)

diff --git a/drivers/net/ethernet/hisilicon/hns3/hns3_enet.c b/drivers/net/ethernet/hisilicon/hns3/hns3_enet.c
index 422fa4d..1c5e0d2 100644
--- a/drivers/net/ethernet/hisilicon/hns3/hns3_enet.c
+++ b/drivers/net/ethernet/hisilicon/hns3/hns3_enet.c
@@ -2831,10 +2831,10 @@ static int hns3_alloc_skb(struct hns3_enet_ring *ring, unsigned int length,
 }
 
 static int hns3_add_frag(struct hns3_enet_ring *ring, struct hns3_desc *desc,
-			 struct sk_buff **out_skb, bool pending)
+			 bool pending)
 {
-	struct sk_buff *skb = *out_skb;
-	struct sk_buff *head_skb = *out_skb;
+	struct sk_buff *skb = ring->skb;
+	struct sk_buff *head_skb = skb;
 	struct sk_buff *new_skb;
 	struct hns3_desc_cb *desc_cb;
 	struct hns3_desc *pre_desc;
@@ -3017,8 +3017,7 @@ static int hns3_handle_bdinfo(struct hns3_enet_ring *ring, struct sk_buff *skb)
 	return 0;
 }
 
-static int hns3_handle_rx_bd(struct hns3_enet_ring *ring,
-			     struct sk_buff **out_skb)
+static int hns3_handle_rx_bd(struct hns3_enet_ring *ring)
 {
 	struct sk_buff *skb = ring->skb;
 	struct hns3_desc_cb *desc_cb;
@@ -3056,12 +3055,12 @@ static int hns3_handle_rx_bd(struct hns3_enet_ring *ring,
 
 	if (!skb) {
 		ret = hns3_alloc_skb(ring, length, ring->va);
-		*out_skb = skb = ring->skb;
+		skb = ring->skb;
 
 		if (ret < 0) /* alloc buffer fail */
 			return ret;
 		if (ret > 0) { /* need add frag */
-			ret = hns3_add_frag(ring, desc, &skb, false);
+			ret = hns3_add_frag(ring, desc, false);
 			if (ret)
 				return ret;
 
@@ -3072,7 +3071,7 @@ static int hns3_handle_rx_bd(struct hns3_enet_ring *ring,
 			       ALIGN(ring->pull_len, sizeof(long)));
 		}
 	} else {
-		ret = hns3_add_frag(ring, desc, &skb, true);
+		ret = hns3_add_frag(ring, desc, true);
 		if (ret)
 			return ret;
 
@@ -3090,8 +3089,6 @@ static int hns3_handle_rx_bd(struct hns3_enet_ring *ring,
 	}
 
 	skb_record_rx_queue(skb, ring->tqp->tqp_index);
-	*out_skb = skb;
-
 	return 0;
 }
 
@@ -3100,7 +3097,6 @@ int hns3_clean_rx_ring(struct hns3_enet_ring *ring, int budget,
 {
 #define RCB_NOF_ALLOC_RX_BUFF_ONCE 16
 	int unused_count = hns3_desc_unused(ring);
-	struct sk_buff *skb = ring->skb;
 	int recv_pkts = 0;
 	int recv_bds = 0;
 	int err, num;
@@ -3123,27 +3119,19 @@ int hns3_clean_rx_ring(struct hns3_enet_ring *ring, int budget,
 		}
 
 		/* Poll one pkt */
-		err = hns3_handle_rx_bd(ring, &skb);
-		if (unlikely(!skb)) /* This fault cannot be repaired */
+		err = hns3_handle_rx_bd(ring);
+		/* Do not get FE for the packet or failed to alloc skb */
+		if (unlikely(!ring->skb || err == -ENXIO)) {
 			goto out;
-
-		if (err == -ENXIO) { /* Do not get FE for the packet */
-			goto out;
-		} else if (unlikely(err)) {  /* Do jump the err */
-			recv_bds += ring->pending_buf;
-			unused_count += ring->pending_buf;
-			ring->skb = NULL;
-			ring->pending_buf = 0;
-			continue;
+		} else if (likely(!err)) {
+			rx_fn(ring, ring->skb);
+			recv_pkts++;
 		}
 
-		rx_fn(ring, skb);
 		recv_bds += ring->pending_buf;
 		unused_count += ring->pending_buf;
 		ring->skb = NULL;
 		ring->pending_buf = 0;
-
-		recv_pkts++;
 	}
 
 out:
-- 
2.7.4

[PATCH net-next 7/8] net: hns3: do not allocate linear data for fraglist skb

[Huazhong Tan]

From: Yunsheng Lin <linyunsheng@huawei.com>

Currently, napi_alloc_skb() is used to allocate skb for fraglist
when the head skb is not enough to hold the remaining data, and
the remaining data is added to the frags part of the fraglist skb,
leaving the linear part unused.

So this patch passes length of 0 to allocate fraglist skb with
zero size of linear data.

Signed-off-by: Yunsheng Lin <linyunsheng@huawei.com>
Signed-off-by: Huazhong Tan <tanhuazhong@huawei.com>
---
 drivers/net/ethernet/hisilicon/hns3/hns3_enet.c | 3 +--
 1 file changed, 1 insertion(+), 2 deletions(-)

diff --git a/drivers/net/ethernet/hisilicon/hns3/hns3_enet.c b/drivers/net/ethernet/hisilicon/hns3/hns3_enet.c
index 1c5e0d2..0fdd684 100644
--- a/drivers/net/ethernet/hisilicon/hns3/hns3_enet.c
+++ b/drivers/net/ethernet/hisilicon/hns3/hns3_enet.c
@@ -2863,8 +2863,7 @@ static int hns3_add_frag(struct hns3_enet_ring *ring, struct hns3_desc *desc,
 			return -ENXIO;
 
 		if (unlikely(ring->frag_num >= MAX_SKB_FRAGS)) {
-			new_skb = napi_alloc_skb(&ring->tqp_vector->napi,
-						 HNS3_RX_HEAD_SIZE);
+			new_skb = napi_alloc_skb(&ring->tqp_vector->napi, 0);
 			if (unlikely(!new_skb)) {
 				hns3_rl_err(ring_to_netdev(ring),
 					    "alloc rx fraglist skb fail\n");
-- 
2.7.4

[PATCH net-next 8/8] net: hns3: log and clear hardware error after reset complete

[Huazhong Tan]

From: Jian Shen <shenjian15@huawei.com>

When device is resetting, the CMDQ service may be stopped until
reset completed. If a new RAS error occurs at this moment, it
will no be able to clear the RAS source. This patch fixes it
by clear the RAS source after reset complete.

Signed-off-by: Jian Shen <shenjian15@huawei.com>
Signed-off-by: Huazhong Tan <tanhuazhong@huawei.com>
---
 drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_main.c | 3 +++
 1 file changed, 3 insertions(+)

diff --git a/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_main.c b/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_main.c
index ffdb8ce..95c3897 100644
--- a/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_main.c
+++ b/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_main.c
@@ -9781,6 +9781,9 @@ static int hclge_reset_ae_dev(struct hnae3_ae_dev *ae_dev)
 		return ret;
 	}
 
+	/* Log and clear the hw errors those already occurred */
+	hclge_handle_all_hns_hw_errors(ae_dev);
+
 	/* Re-enable the hw error interrupts because
 	 * the interrupts get disabled on global reset.
 	 */
-- 
2.7.4

Re: [PATCH net-next 0/8] net: hns3: add some cleanups & optimizations

[Jakub Kicinski]

On Sat, 19 Oct 2019 16:03:48 +0800, Huazhong Tan wrote:
> This patchset includes some cleanups and optimizations for the HNS3
> ethernet driver.
> 
> [patch 1/8] removes unused and unnecessary structures.
> 
> [patch 2/8] uses a ETH_ALEN u8 array to replace two mac_addr_*
> field in struct hclge_mac_mgr_tbl_entry_cmd.
> 
> [patch 3/8] optimizes the barrier used in the IO path.
> 
> [patch 4/8] introduces macro ring_to_netdev() to get netdevive
> from struct hns3_enet_ring variable.
> 
> [patch 5/8] makes struct hns3_enet_ring to be cacheline aligned
> 
> [patch 6/8] adds a minor cleanup for hns3_handle_rx_bd().
> 
> [patch 7/8] removes linear data allocating for fraglist SKB.
> 
> [patch 8/8] clears hardware error when resetting.
> 
> ---
> note:
> In previous patchset, there are some bugfixes which needs below
> new feature, which is only in 'net-next' but not in 'net' now:
> net: hns3: support tx-scatter-gather-fraglist feature
> net: hns3: add support for spoof check setting
> 
> So, these bugfixes will be upstreamed when the patch needed is
> on 'net' tree.

Thanks! Looks good to me now.

Re: [PATCH net-next 0/8] net: hns3: add some cleanups & optimizations

[David Miller]

From: Huazhong Tan <tanhuazhong@huawei.com>
Date: Sat, 19 Oct 2019 16:03:48 +0800

> This patchset includes some cleanups and optimizations for the HNS3
> ethernet driver.
 ...

Series applied.