Merge branch 'net-hns3-updates-for-next'

Huazhong Tan says:

====================
net: hns3: updates for -next

There are some optimizations related to IO path.

Change since V1:
- fixes a unsuitable handling in hns3_lb_clear_tx_ring() of #6 which
  pointed out by Saeed Mahameed.

previous version:
V1: https://patchwork.ozlabs.org/project/netdev/cover/1600085217-26245-1-git-send-email-tanhuazhong@huawei.com/
====================

Signed-off-by: David S. Miller <davem@davemloft.net>

3 files changed, 140 insertions, 111 deletions

diff --git a/drivers/net/ethernet/hisilicon/hns3/hns3_enet.c b/drivers/net/ethernet/hisilicon/hns3/hns3_enet.c
index 93825a433915..feeaf758b669 100644
--- a/drivers/net/ethernet/hisilicon/hns3/hns3_enet.c
+++ b/drivers/net/ethernet/hisilicon/hns3/hns3_enet.c
@@ -1383,6 +1383,27 @@ static int hns3_fill_skb_to_desc(struct hns3_enet_ring *ring,
 	return bd_num;
 }
 
+static void hns3_tx_doorbell(struct hns3_enet_ring *ring, int num,
+			     bool doorbell)
+{
+	ring->pending_buf += num;
+
+	if (!doorbell) {
+		u64_stats_update_begin(&ring->syncp);
+		ring->stats.tx_more++;
+		u64_stats_update_end(&ring->syncp);
+		return;
+	}
+
+	if (!ring->pending_buf)
+		return;
+
+	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);
+}
+
 netdev_tx_t hns3_nic_net_xmit(struct sk_buff *skb, struct net_device *netdev)
 {
 	struct hns3_nic_priv *priv = netdev_priv(netdev);
@@ -1391,11 +1412,14 @@ netdev_tx_t hns3_nic_net_xmit(struct sk_buff *skb, struct net_device *netdev)
 	int pre_ntu, next_to_use_head;
 	struct sk_buff *frag_skb;
 	int bd_num = 0;
+	bool doorbell;
 	int ret;
 
 	/* Hardware can only handle short frames above 32 bytes */
-	if (skb_put_padto(skb, HNS3_MIN_TX_LEN))
+	if (skb_put_padto(skb, HNS3_MIN_TX_LEN)) {
+		hns3_tx_doorbell(ring, 0, !netdev_xmit_more());
 		return NETDEV_TX_OK;
+	}
 
 	/* Prefetch the data used later */
 	prefetch(skb->data);
@@ -1406,6 +1430,7 @@ netdev_tx_t hns3_nic_net_xmit(struct sk_buff *skb, struct net_device *netdev)
 			u64_stats_update_begin(&ring->syncp);
 			ring->stats.tx_busy++;
 			u64_stats_update_end(&ring->syncp);
+			hns3_tx_doorbell(ring, 0, true);
 			return NETDEV_TX_BUSY;
 		} else if (ret == -ENOMEM) {
 			u64_stats_update_begin(&ring->syncp);
@@ -1446,11 +1471,9 @@ netdev_tx_t hns3_nic_net_xmit(struct sk_buff *skb, struct net_device *netdev)
 
 	/* Complete translate all packets */
 	dev_queue = netdev_get_tx_queue(netdev, ring->queue_index);
-	netdev_tx_sent_queue(dev_queue, skb->len);
-
-	wmb(); /* Commit all data before submit */
-
-	hnae3_queue_xmit(ring->tqp, bd_num);
+	doorbell = __netdev_tx_sent_queue(dev_queue, skb->len,
+					  netdev_xmit_more());
+	hns3_tx_doorbell(ring, bd_num, doorbell);
 
 	return NETDEV_TX_OK;
 
@@ -1459,6 +1482,7 @@ fill_err:
 
 out_err_tx_ok:
 	dev_kfree_skb_any(skb);
+	hns3_tx_doorbell(ring, 0, !netdev_xmit_more());
 	return NETDEV_TX_OK;
 }
 
@@ -1839,13 +1863,13 @@ static bool hns3_get_tx_timeo_queue_info(struct net_device *ndev)
 		    tx_ring->next_to_clean, napi->state);
 
 	netdev_info(ndev,
-		    "tx_pkts: %llu, tx_bytes: %llu, io_err_cnt: %llu, sw_err_cnt: %llu\n",
+		    "tx_pkts: %llu, tx_bytes: %llu, sw_err_cnt: %llu, tx_pending: %d\n",
 		    tx_ring->stats.tx_pkts, tx_ring->stats.tx_bytes,
-		    tx_ring->stats.io_err_cnt, tx_ring->stats.sw_err_cnt);
+		    tx_ring->stats.sw_err_cnt, tx_ring->pending_buf);
 
 	netdev_info(ndev,
-		    "seg_pkt_cnt: %llu, tx_err_cnt: %llu, restart_queue: %llu, tx_busy: %llu\n",
-		    tx_ring->stats.seg_pkt_cnt, tx_ring->stats.tx_err_cnt,
+		    "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);
 
 	/* When mac received many pause frames continuous, it's unable to send
@@ -2302,17 +2326,19 @@ static int hns3_alloc_buffer(struct hns3_enet_ring *ring,
 	cb->buf  = page_address(p);
 	cb->length = hns3_page_size(ring);
 	cb->type = DESC_TYPE_PAGE;
+	page_ref_add(p, USHRT_MAX - 1);
+	cb->pagecnt_bias = USHRT_MAX;
 
 	return 0;
 }
 
 static void hns3_free_buffer(struct hns3_enet_ring *ring,
-			     struct hns3_desc_cb *cb)
+			     struct hns3_desc_cb *cb, int budget)
 {
 	if (cb->type == DESC_TYPE_SKB)
-		dev_kfree_skb_any((struct sk_buff *)cb->priv);
-	else if (!HNAE3_IS_TX_RING(ring))
-		put_page((struct page *)cb->priv);
+		napi_consume_skb(cb->priv, budget);
+	else if (!HNAE3_IS_TX_RING(ring) && cb->pagecnt_bias)
+		__page_frag_cache_drain(cb->priv, cb->pagecnt_bias);
 	memset(cb, 0, sizeof(*cb));
 }
 
@@ -2344,7 +2370,8 @@ static void hns3_buffer_detach(struct hns3_enet_ring *ring, int i)
 	ring->desc[i].addr = 0;
 }
 
-static void hns3_free_buffer_detach(struct hns3_enet_ring *ring, int i)
+static void hns3_free_buffer_detach(struct hns3_enet_ring *ring, int i,
+				    int budget)
 {
 	struct hns3_desc_cb *cb = &ring->desc_cb[i];
 
@@ -2352,7 +2379,7 @@ static void hns3_free_buffer_detach(struct hns3_enet_ring *ring, int i)
 		return;
 
 	hns3_buffer_detach(ring, i);
-	hns3_free_buffer(ring, cb);
+	hns3_free_buffer(ring, cb, budget);
 }
 
 static void hns3_free_buffers(struct hns3_enet_ring *ring)
@@ -2360,7 +2387,7 @@ static void hns3_free_buffers(struct hns3_enet_ring *ring)
 	int i;
 
 	for (i = 0; i < ring->desc_num; i++)
-		hns3_free_buffer_detach(ring, i);
+		hns3_free_buffer_detach(ring, i, 0);
 }
 
 /* free desc along with its attached buffer */
@@ -2405,7 +2432,7 @@ static int hns3_alloc_and_map_buffer(struct hns3_enet_ring *ring,
 	return 0;
 
 out_with_buf:
-	hns3_free_buffer(ring, cb);
+	hns3_free_buffer(ring, cb, 0);
 out:
 	return ret;
 }
@@ -2437,7 +2464,7 @@ static int hns3_alloc_ring_buffers(struct hns3_enet_ring *ring)
 
 out_buffer_fail:
 	for (j = i - 1; j >= 0; j--)
-		hns3_free_buffer_detach(ring, j);
+		hns3_free_buffer_detach(ring, j, 0);
 	return ret;
 }
 
@@ -2464,71 +2491,62 @@ static void hns3_reuse_buffer(struct hns3_enet_ring *ring, int i)
 			DMA_FROM_DEVICE);
 }
 
-static void hns3_nic_reclaim_desc(struct hns3_enet_ring *ring, int head,
-				  int *bytes, int *pkts)
+static bool hns3_nic_reclaim_desc(struct hns3_enet_ring *ring,
+				  int *bytes, int *pkts, int budget)
 {
+	/* pair with ring->last_to_use update in hns3_tx_doorbell(),
+	 * smp_store_release() is not used in hns3_tx_doorbell() because
+	 * the doorbell operation already have the needed barrier operation.
+	 */
+	int ltu = smp_load_acquire(&ring->last_to_use);
 	int ntc = ring->next_to_clean;
 	struct hns3_desc_cb *desc_cb;
+	bool reclaimed = false;
+	struct hns3_desc *desc;
+
+	while (ltu != ntc) {
+		desc = &ring->desc[ntc];
+
+		if (le16_to_cpu(desc->tx.bdtp_fe_sc_vld_ra_ri) &
+				BIT(HNS3_TXD_VLD_B))
+			break;
 
-	while (head != ntc) {
 		desc_cb = &ring->desc_cb[ntc];
 		(*pkts) += (desc_cb->type == DESC_TYPE_SKB);
 		(*bytes) += desc_cb->length;
 		/* desc_cb will be cleaned, after hnae3_free_buffer_detach */
-		hns3_free_buffer_detach(ring, ntc);
+		hns3_free_buffer_detach(ring, ntc, budget);
 
 		if (++ntc == ring->desc_num)
 			ntc = 0;
 
 		/* Issue prefetch for next Tx descriptor */
 		prefetch(&ring->desc_cb[ntc]);
+		reclaimed = true;
 	}
 
+	if (unlikely(!reclaimed))
+		return false;
+
 	/* This smp_store_release() pairs with smp_load_acquire() in
 	 * ring_space called by hns3_nic_net_xmit.
 	 */
 	smp_store_release(&ring->next_to_clean, ntc);
+	return true;
 }
 
-static int is_valid_clean_head(struct hns3_enet_ring *ring, int h)
-{
-	int u = ring->next_to_use;
-	int c = ring->next_to_clean;
-
-	if (unlikely(h > ring->desc_num))
-		return 0;
-
-	return u > c ? (h > c && h <= u) : (h > c || h <= u);
-}
-
-void hns3_clean_tx_ring(struct hns3_enet_ring *ring)
+void hns3_clean_tx_ring(struct hns3_enet_ring *ring, int budget)
 {
 	struct net_device *netdev = ring_to_netdev(ring);
 	struct hns3_nic_priv *priv = netdev_priv(netdev);
 	struct netdev_queue *dev_queue;
 	int bytes, pkts;
-	int head;
-
-	head = readl_relaxed(ring->tqp->io_base + HNS3_RING_TX_RING_HEAD_REG);
-
-	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))) {
-		hns3_rl_err(netdev, "wrong head (%d, %d-%d)\n", head,
-			    ring->next_to_use, ring->next_to_clean);
-
-		u64_stats_update_begin(&ring->syncp);
-		ring->stats.io_err_cnt++;
-		u64_stats_update_end(&ring->syncp);
-		return;
-	}
 
 	bytes = 0;
 	pkts = 0;
-	hns3_nic_reclaim_desc(ring, head, &bytes, &pkts);
+
+	if (unlikely(!hns3_nic_reclaim_desc(ring, &bytes, &pkts, budget)))
+		return;
 
 	ring->tqp_vector->tx_group.total_bytes += bytes;
 	ring->tqp_vector->tx_group.total_packets += pkts;
@@ -2600,8 +2618,7 @@ static void hns3_nic_alloc_rx_buffers(struct hns3_enet_ring *ring,
 		ring_ptr_move_fw(ring, next_to_use);
 	}
 
-	wmb(); /* Make all data has been write before submit */
-	writel_relaxed(i, ring->tqp->io_base + HNS3_RING_RX_RING_HEAD_REG);
+	writel(i, ring->tqp->io_base + HNS3_RING_RX_RING_HEAD_REG);
 }
 
 static bool hns3_page_is_reusable(struct page *page)
@@ -2610,6 +2627,11 @@ static bool hns3_page_is_reusable(struct page *page)
 		!page_is_pfmemalloc(page);
 }
 
+static bool hns3_can_reuse_page(struct hns3_desc_cb *cb)
+{
+	return (page_count(cb->priv) - cb->pagecnt_bias) == 1;
+}
+
 static void hns3_nic_reuse_page(struct sk_buff *skb, int i,
 				struct hns3_enet_ring *ring, int pull_len,
 				struct hns3_desc_cb *desc_cb)
@@ -2618,6 +2640,7 @@ static void hns3_nic_reuse_page(struct sk_buff *skb, int i,
 	int size = le16_to_cpu(desc->rx.size);
 	u32 truesize = hns3_buf_size(ring);
 
+	desc_cb->pagecnt_bias--;
 	skb_add_rx_frag(skb, i, desc_cb->priv, desc_cb->page_offset + pull_len,
 			size - pull_len, truesize);
 
@@ -2625,20 +2648,27 @@ static void hns3_nic_reuse_page(struct sk_buff *skb, int i,
 	 * when page_offset rollback to zero, flag default unreuse
 	 */
 	if (unlikely(!hns3_page_is_reusable(desc_cb->priv)) ||
-	    (!desc_cb->page_offset && page_count(desc_cb->priv) > 1))
+	    (!desc_cb->page_offset && !hns3_can_reuse_page(desc_cb))) {
+		__page_frag_cache_drain(desc_cb->priv, desc_cb->pagecnt_bias);
 		return;
+	}
 
 	/* Move offset up to the next cache line */
 	desc_cb->page_offset += truesize;
 
 	if (desc_cb->page_offset + truesize <= hns3_page_size(ring)) {
 		desc_cb->reuse_flag = 1;
-		/* Bump ref count on page before it is given */
-		get_page(desc_cb->priv);
-	} else if (page_count(desc_cb->priv) == 1) {
+	} else if (hns3_can_reuse_page(desc_cb)) {
 		desc_cb->reuse_flag = 1;
 		desc_cb->page_offset = 0;
-		get_page(desc_cb->priv);
+	} else if (desc_cb->pagecnt_bias) {
+		__page_frag_cache_drain(desc_cb->priv, desc_cb->pagecnt_bias);
+		return;
+	}
+
+	if (unlikely(!desc_cb->pagecnt_bias)) {
+		page_ref_add(desc_cb->priv, USHRT_MAX);
+		desc_cb->pagecnt_bias = USHRT_MAX;
 	}
 }
 
@@ -2814,6 +2844,16 @@ static bool hns3_parse_vlan_tag(struct hns3_enet_ring *ring,
 	}
 }
 
+static void hns3_rx_ring_move_fw(struct hns3_enet_ring *ring)
+{
+	ring->desc[ring->next_to_clean].rx.bd_base_info &=
+		cpu_to_le32(~BIT(HNS3_RXD_VLD_B));
+	ring->next_to_clean += 1;
+
+	if (unlikely(ring->next_to_clean == ring->desc_num))
+		ring->next_to_clean = 0;
+}
+
 static int hns3_alloc_skb(struct hns3_enet_ring *ring, unsigned int length,
 			  unsigned char *va)
 {
@@ -2846,9 +2886,10 @@ static int hns3_alloc_skb(struct hns3_enet_ring *ring, unsigned int length,
 		if (likely(hns3_page_is_reusable(desc_cb->priv)))
 			desc_cb->reuse_flag = 1;
 		else /* This page cannot be reused so discard it */
-			put_page(desc_cb->priv);
+			__page_frag_cache_drain(desc_cb->priv,
+						desc_cb->pagecnt_bias);
 
-		ring_ptr_move_fw(ring, next_to_clean);
+		hns3_rx_ring_move_fw(ring);
 		return 0;
 	}
 	u64_stats_update_begin(&ring->syncp);
@@ -2859,7 +2900,7 @@ static int hns3_alloc_skb(struct hns3_enet_ring *ring, unsigned int length,
 	__skb_put(skb, ring->pull_len);
 	hns3_nic_reuse_page(skb, ring->frag_num++, ring, ring->pull_len,
 			    desc_cb);
-	ring_ptr_move_fw(ring, next_to_clean);
+	hns3_rx_ring_move_fw(ring);
 
 	return 0;
 }
@@ -2914,7 +2955,7 @@ static int hns3_add_frag(struct hns3_enet_ring *ring)
 
 		hns3_nic_reuse_page(skb, ring->frag_num++, ring, 0, desc_cb);
 		trace_hns3_rx_desc(ring);
-		ring_ptr_move_fw(ring, next_to_clean);
+		hns3_rx_ring_move_fw(ring);
 		ring->pending_buf++;
 	} while (!(bd_base_info & BIT(HNS3_RXD_FE_B)));
 
@@ -3056,32 +3097,32 @@ static int hns3_handle_rx_bd(struct hns3_enet_ring *ring)
 
 	prefetch(desc);
 
-	length = le16_to_cpu(desc->rx.size);
-	bd_base_info = le32_to_cpu(desc->rx.bd_base_info);
+	if (!skb) {
+		bd_base_info = le32_to_cpu(desc->rx.bd_base_info);
 
-	/* Check valid BD */
-	if (unlikely(!(bd_base_info & BIT(HNS3_RXD_VLD_B))))
-		return -ENXIO;
+		/* Check valid BD */
+		if (unlikely(!(bd_base_info & BIT(HNS3_RXD_VLD_B))))
+			return -ENXIO;
+
+		dma_rmb();
+		length = le16_to_cpu(desc->rx.size);
 
-	if (!skb) {
 		ring->va = desc_cb->buf + desc_cb->page_offset;
 
 		dma_sync_single_for_cpu(ring_to_dev(ring),
 				desc_cb->dma + desc_cb->page_offset,
 				hns3_buf_size(ring),
 				DMA_FROM_DEVICE);
-	}
 
-	/* Prefetch first cache line of first page
-	 * Idea is to cache few bytes of the header of the packet. Our L1 Cache
-	 * line size is 64B so need to prefetch twice to make it 128B. But in
-	 * actual we can have greater size of caches with 128B Level 1 cache
-	 * lines. In such a case, single fetch would suffice to cache in the
-	 * relevant part of the header.
-	 */
-	net_prefetch(ring->va);
+		/* Prefetch first cache line of first page.
+		 * Idea is to cache few bytes of the header of the packet.
+		 * Our L1 Cache line size is 64B so need to prefetch twice to make
+		 * it 128B. But in actual we can have greater size of caches with
+		 * 128B Level 1 cache lines. In such a case, single fetch would
+		 * suffice to cache in the relevant part of the header.
+		 */
+		net_prefetch(ring->va);
 
-	if (!skb) {
 		ret = hns3_alloc_skb(ring, length, ring->va);
 		skb = ring->skb;
 
@@ -3121,19 +3162,11 @@ 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);
 	int recv_pkts = 0;
-	int recv_bds = 0;
-	int err, num;
+	int err;
 
-	num = readl_relaxed(ring->tqp->io_base + HNS3_RING_RX_RING_FBDNUM_REG);
-	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) {
+	while (recv_pkts < budget) {
 		/* Reuse or realloc buffers */
 		if (unused_count >= RCB_NOF_ALLOC_RX_BUFF_ONCE) {
 			hns3_nic_alloc_rx_buffers(ring, unused_count);
@@ -3151,7 +3184,6 @@ int hns3_clean_rx_ring(struct hns3_enet_ring *ring, int budget,
 			recv_pkts++;
 		}
 
-		recv_bds += ring->pending_buf;
 		unused_count += ring->pending_buf;
 		ring->skb = NULL;
 		ring->pending_buf = 0;
@@ -3320,7 +3352,7 @@ static int hns3_nic_common_poll(struct napi_struct *napi, int budget)
 	 * budget and be more aggressive about cleaning up the Tx descriptors.
 	 */
 	hns3_for_each_ring(ring, tqp_vector->tx_group)
-		hns3_clean_tx_ring(ring);
+		hns3_clean_tx_ring(ring, budget);
 
 	/* make sure rx ring budget not smaller than 1 */
 	if (tqp_vector->num_tqps > 1)
@@ -3673,6 +3705,7 @@ static void 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;
+	ring->last_to_use = 0;
 }
 
 static void hns3_queue_to_ring(struct hnae3_queue *tqp,
@@ -3752,6 +3785,7 @@ void hns3_fini_ring(struct hns3_enet_ring *ring)
 	ring->desc_cb = NULL;
 	ring->next_to_clean = 0;
 	ring->next_to_use = 0;
+	ring->last_to_use = 0;
 	ring->pending_buf = 0;
 	if (ring->skb) {
 		dev_kfree_skb_any(ring->skb);
@@ -4162,9 +4196,11 @@ static void hns3_clear_tx_ring(struct hns3_enet_ring *ring)
 {
 	while (ring->next_to_clean != ring->next_to_use) {
 		ring->desc[ring->next_to_clean].tx.bdtp_fe_sc_vld_ra_ri = 0;
-		hns3_free_buffer_detach(ring, ring->next_to_clean);
+		hns3_free_buffer_detach(ring, ring->next_to_clean, 0);
 		ring_ptr_move_fw(ring, next_to_clean);
 	}
+
+	ring->pending_buf = 0;
 }
 
 static int hns3_clear_rx_ring(struct hns3_enet_ring *ring)
@@ -4267,6 +4303,7 @@ int hns3_nic_reset_all_ring(struct hnae3_handle *h)
 		hns3_clear_tx_ring(&priv->ring[i]);
 		priv->ring[i].next_to_clean = 0;
 		priv->ring[i].next_to_use = 0;
+		priv->ring[i].last_to_use = 0;
 
 		rx_ring = &priv->ring[i + h->kinfo.num_tqps];
 		hns3_init_ring_hw(rx_ring);
diff --git a/drivers/net/ethernet/hisilicon/hns3/hns3_enet.h b/drivers/net/ethernet/hisilicon/hns3/hns3_enet.h
index 98ca6ead0b7d..8a6c8bae8fa6 100644
--- a/drivers/net/ethernet/hisilicon/hns3/hns3_enet.h
+++ b/drivers/net/ethernet/hisilicon/hns3/hns3_enet.h
@@ -287,6 +287,7 @@ struct hns3_desc_cb {
 
 	/* desc type, used by the ring user to mark the type of the priv data */
 	u16 type;
+	u16 pagecnt_bias;
 };
 
 enum hns3_pkt_l3type {
@@ -343,14 +344,13 @@ enum hns3_pkt_ol4type {
 };
 
 struct ring_stats {
-	u64 io_err_cnt;
 	u64 sw_err_cnt;
 	u64 seg_pkt_cnt;
 	union {
 		struct {
 			u64 tx_pkts;
 			u64 tx_bytes;
-			u64 tx_err_cnt;
+			u64 tx_more;
 			u64 restart_queue;
 			u64 tx_busy;
 			u64 tx_copy;
@@ -396,8 +396,10 @@ struct hns3_enet_ring {
 	 * next_to_use
 	 */
 	int next_to_clean;
-
-	u32 pull_len; /* head length for current packet */
+	union {
+		int last_to_use;	/* last idx used by xmit */
+		u32 pull_len;		/* memcpy len for current rx packet */
+	};
 	u32 frag_num;
 	void *va; /* first buffer address for current packet */
 
@@ -512,11 +514,6 @@ static inline int ring_space(struct hns3_enet_ring *ring)
 			(begin - end)) - 1;
 }
 
-static inline int is_ring_empty(struct hns3_enet_ring *ring)
-{
-	return ring->next_to_use == ring->next_to_clean;
-}
-
 static inline u32 hns3_read_reg(void __iomem *base, u32 reg)
 {
 	return readl(base + reg);
@@ -542,9 +539,6 @@ static inline bool hns3_nic_resetting(struct net_device *netdev)
 #define hns3_write_dev(a, reg, value) \
 	hns3_write_reg((a)->io_base, (reg), (value))
 
-#define hnae3_queue_xmit(tqp, buf_num) writel_relaxed(buf_num, \
-		(tqp)->io_base + HNS3_RING_TX_RING_TAIL_REG)
-
 #define ring_to_dev(ring) ((ring)->dev)
 
 #define ring_to_netdev(ring)	((ring)->tqp_vector->napi.dev)
@@ -582,7 +576,7 @@ void hns3_ethtool_set_ops(struct net_device *netdev);
 int hns3_set_channels(struct net_device *netdev,
 		      struct ethtool_channels *ch);
 
-void hns3_clean_tx_ring(struct hns3_enet_ring *ring);
+void hns3_clean_tx_ring(struct hns3_enet_ring *ring, int budget);
 int hns3_init_all_ring(struct hns3_nic_priv *priv);
 int hns3_uninit_all_ring(struct hns3_nic_priv *priv);
 int hns3_nic_reset_all_ring(struct hnae3_handle *h);
diff --git a/drivers/net/ethernet/hisilicon/hns3/hns3_ethtool.c b/drivers/net/ethernet/hisilicon/hns3/hns3_ethtool.c
index 2622e04e8eed..52c780475d3a 100644
--- a/drivers/net/ethernet/hisilicon/hns3/hns3_ethtool.c
+++ b/drivers/net/ethernet/hisilicon/hns3/hns3_ethtool.c
@@ -27,12 +27,11 @@ struct hns3_sfp_type {
 
 static const struct hns3_stats hns3_txq_stats[] = {
 	/* Tx per-queue statistics */
-	HNS3_TQP_STAT("io_err_cnt", io_err_cnt),
 	HNS3_TQP_STAT("dropped", sw_err_cnt),
 	HNS3_TQP_STAT("seg_pkt_cnt", seg_pkt_cnt),
 	HNS3_TQP_STAT("packets", tx_pkts),
 	HNS3_TQP_STAT("bytes", tx_bytes),
-	HNS3_TQP_STAT("errors", tx_err_cnt),
+	HNS3_TQP_STAT("more", tx_more),
 	HNS3_TQP_STAT("wake", restart_queue),
 	HNS3_TQP_STAT("busy", tx_busy),
 	HNS3_TQP_STAT("copy", tx_copy),
@@ -46,7 +45,6 @@ static const struct hns3_stats hns3_txq_stats[] = {
 
 static const struct hns3_stats hns3_rxq_stats[] = {
 	/* Rx per-queue statistics */
-	HNS3_TQP_STAT("io_err_cnt", io_err_cnt),
 	HNS3_TQP_STAT("dropped", sw_err_cnt),
 	HNS3_TQP_STAT("seg_pkt_cnt", seg_pkt_cnt),
 	HNS3_TQP_STAT("packets", rx_pkts),
@@ -232,7 +230,7 @@ static void hns3_lb_clear_tx_ring(struct hns3_nic_priv *priv, u32 start_ringid,
 	for (i = start_ringid; i <= end_ringid; i++) {
 		struct hns3_enet_ring *ring = &priv->ring[i];
 
-		hns3_clean_tx_ring(ring);
+		hns3_clean_tx_ring(ring, 0);
 	}
 }