Merge branch 'hns3-misc'

Huazhong Tan says:

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

This series include some updates for the HNS3 ethernet driver.

   flow director configuration").
====================

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

11 files changed, 321 insertions, 179 deletions

diff --git a/drivers/net/ethernet/hisilicon/hns3/hnae3.h b/drivers/net/ethernet/hisilicon/hns3/hnae3.h
index 01d6bfc0917c..a234116ba0e5 100644
--- a/drivers/net/ethernet/hisilicon/hns3/hnae3.h
+++ b/drivers/net/ethernet/hisilicon/hns3/hnae3.h
@@ -579,7 +579,7 @@ struct hnae3_ae_ops {
 				      int vector_num,
 				      struct hnae3_ring_chain_node *vr_chain);
 
-	int (*reset_queue)(struct hnae3_handle *handle, u16 queue_id);
+	int (*reset_queue)(struct hnae3_handle *handle);
 	u32 (*get_fw_version)(struct hnae3_handle *handle);
 	void (*get_mdix_mode)(struct hnae3_handle *handle,
 			      u8 *tp_mdix_ctrl, u8 *tp_mdix);
diff --git a/drivers/net/ethernet/hisilicon/hns3/hns3_enet.c b/drivers/net/ethernet/hisilicon/hns3/hns3_enet.c
index c73de36b3843..f59cd719b5b4 100644
--- a/drivers/net/ethernet/hisilicon/hns3/hns3_enet.c
+++ b/drivers/net/ethernet/hisilicon/hns3/hns3_enet.c
@@ -694,7 +694,7 @@ void hns3_enable_vlan_filter(struct net_device *netdev, bool enable)
 }
 
 static int hns3_set_tso(struct sk_buff *skb, u32 *paylen_fdop_ol4cs,
-			u16 *mss, u32 *type_cs_vlan_tso)
+			u16 *mss, u32 *type_cs_vlan_tso, u32 *send_bytes)
 {
 	u32 l4_offset, hdr_len;
 	union l3_hdr_info l3;
@@ -750,6 +750,8 @@ static int hns3_set_tso(struct sk_buff *skb, u32 *paylen_fdop_ol4cs,
 				     (__force __wsum)htonl(l4_paylen));
 	}
 
+	*send_bytes = (skb_shinfo(skb)->gso_segs - 1) * hdr_len + skb->len;
+
 	/* find the txbd field values */
 	*paylen_fdop_ol4cs = skb->len - hdr_len;
 	hns3_set_field(*type_cs_vlan_tso, HNS3_TXD_TSO_B, 1);
@@ -1076,7 +1078,8 @@ static bool hns3_check_hw_tx_csum(struct sk_buff *skb)
 }
 
 static int hns3_fill_skb_desc(struct hns3_enet_ring *ring,
-			      struct sk_buff *skb, struct hns3_desc *desc)
+			      struct sk_buff *skb, struct hns3_desc *desc,
+			      struct hns3_desc_cb *desc_cb)
 {
 	u32 ol_type_vlan_len_msec = 0;
 	u32 paylen_ol4cs = skb->len;
@@ -1105,6 +1108,8 @@ static int hns3_fill_skb_desc(struct hns3_enet_ring *ring,
 			       1);
 	}
 
+	desc_cb->send_bytes = skb->len;
+
 	if (skb->ip_summed == CHECKSUM_PARTIAL) {
 		u8 ol4_proto, il4_proto;
 
@@ -1140,7 +1145,7 @@ static int hns3_fill_skb_desc(struct hns3_enet_ring *ring,
 		}
 
 		ret = hns3_set_tso(skb, &paylen_ol4cs, &mss_hw_csum,
-				   &type_cs_vlan_tso);
+				   &type_cs_vlan_tso, &desc_cb->send_bytes);
 		if (unlikely(ret < 0)) {
 			u64_stats_update_begin(&ring->syncp);
 			ring->stats.tx_tso_err++;
@@ -1275,30 +1280,29 @@ static unsigned int hns3_skb_bd_num(struct sk_buff *skb, unsigned int *bd_size,
 }
 
 static unsigned int hns3_tx_bd_num(struct sk_buff *skb, unsigned int *bd_size,
-				   u8 max_non_tso_bd_num)
+				   u8 max_non_tso_bd_num, unsigned int bd_num,
+				   unsigned int recursion_level)
 {
+#define HNS3_MAX_RECURSION_LEVEL	24
+
 	struct sk_buff *frag_skb;
-	unsigned int bd_num = 0;
 
 	/* If the total len is within the max bd limit */
-	if (likely(skb->len <= HNS3_MAX_BD_SIZE && !skb_has_frag_list(skb) &&
+	if (likely(skb->len <= HNS3_MAX_BD_SIZE && !recursion_level &&
+		   !skb_has_frag_list(skb) &&
 		   skb_shinfo(skb)->nr_frags < max_non_tso_bd_num))
 		return skb_shinfo(skb)->nr_frags + 1U;
 
-	/* The below case will always be linearized, return
-	 * HNS3_MAX_BD_NUM_TSO + 1U to make sure it is linearized.
-	 */
-	if (unlikely(skb->len > HNS3_MAX_TSO_SIZE ||
-		     (!skb_is_gso(skb) && skb->len >
-		      HNS3_MAX_NON_TSO_SIZE(max_non_tso_bd_num))))
-		return HNS3_MAX_TSO_BD_NUM + 1U;
+	if (unlikely(recursion_level >= HNS3_MAX_RECURSION_LEVEL))
+		return UINT_MAX;
 
 	bd_num = hns3_skb_bd_num(skb, bd_size, bd_num);
 	if (!skb_has_frag_list(skb) || bd_num > HNS3_MAX_TSO_BD_NUM)
 		return bd_num;
 
 	skb_walk_frags(skb, frag_skb) {
-		bd_num = hns3_skb_bd_num(frag_skb, bd_size, bd_num);
+		bd_num = hns3_tx_bd_num(frag_skb, bd_size, max_non_tso_bd_num,
+					bd_num, recursion_level + 1);
 		if (bd_num > HNS3_MAX_TSO_BD_NUM)
 			return bd_num;
 	}
@@ -1358,6 +1362,43 @@ void hns3_shinfo_pack(struct skb_shared_info *shinfo, __u32 *size)
 		size[i] = skb_frag_size(&shinfo->frags[i]);
 }
 
+static int hns3_skb_linearize(struct hns3_enet_ring *ring,
+			      struct sk_buff *skb,
+			      u8 max_non_tso_bd_num,
+			      unsigned int bd_num)
+{
+	/* 'bd_num == UINT_MAX' means the skb' fraglist has a
+	 * recursion level of over HNS3_MAX_RECURSION_LEVEL.
+	 */
+	if (bd_num == UINT_MAX) {
+		u64_stats_update_begin(&ring->syncp);
+		ring->stats.over_max_recursion++;
+		u64_stats_update_end(&ring->syncp);
+		return -ENOMEM;
+	}
+
+	/* The skb->len has exceeded the hw limitation, linearization
+	 * will not help.
+	 */
+	if (skb->len > HNS3_MAX_TSO_SIZE ||
+	    (!skb_is_gso(skb) && skb->len >
+	     HNS3_MAX_NON_TSO_SIZE(max_non_tso_bd_num))) {
+		u64_stats_update_begin(&ring->syncp);
+		ring->stats.hw_limitation++;
+		u64_stats_update_end(&ring->syncp);
+		return -ENOMEM;
+	}
+
+	if (__skb_linearize(skb)) {
+		u64_stats_update_begin(&ring->syncp);
+		ring->stats.sw_err_cnt++;
+		u64_stats_update_end(&ring->syncp);
+		return -ENOMEM;
+	}
+
+	return 0;
+}
+
 static int hns3_nic_maybe_stop_tx(struct hns3_enet_ring *ring,
 				  struct net_device *netdev,
 				  struct sk_buff *skb)
@@ -1367,7 +1408,7 @@ static int hns3_nic_maybe_stop_tx(struct hns3_enet_ring *ring,
 	unsigned int bd_size[HNS3_MAX_TSO_BD_NUM + 1U];
 	unsigned int bd_num;
 
-	bd_num = hns3_tx_bd_num(skb, bd_size, max_non_tso_bd_num);
+	bd_num = hns3_tx_bd_num(skb, bd_size, max_non_tso_bd_num, 0, 0);
 	if (unlikely(bd_num > max_non_tso_bd_num)) {
 		if (bd_num <= HNS3_MAX_TSO_BD_NUM && skb_is_gso(skb) &&
 		    !hns3_skb_need_linearized(skb, bd_size, bd_num,
@@ -1376,16 +1417,11 @@ static int hns3_nic_maybe_stop_tx(struct hns3_enet_ring *ring,
 			goto out;
 		}
 
-		if (__skb_linearize(skb))
+		if (hns3_skb_linearize(ring, skb, max_non_tso_bd_num,
+				       bd_num))
 			return -ENOMEM;
 
 		bd_num = hns3_tx_bd_count(skb->len);
-		if ((skb_is_gso(skb) && bd_num > HNS3_MAX_TSO_BD_NUM) ||
-		    (!skb_is_gso(skb) &&
-		     bd_num > max_non_tso_bd_num)) {
-			trace_hns3_over_max_bd(skb);
-			return -ENOMEM;
-		}
 
 		u64_stats_update_begin(&ring->syncp);
 		ring->stats.tx_copy++;
@@ -1409,6 +1445,10 @@ out:
 		return bd_num;
 	}
 
+	u64_stats_update_begin(&ring->syncp);
+	ring->stats.tx_busy++;
+	u64_stats_update_end(&ring->syncp);
+
 	return -EBUSY;
 }
 
@@ -1456,6 +1496,7 @@ static int hns3_fill_skb_to_desc(struct hns3_enet_ring *ring,
 				 struct sk_buff *skb, enum hns_desc_type type)
 {
 	unsigned int size = skb_headlen(skb);
+	struct sk_buff *frag_skb;
 	int i, ret, bd_num = 0;
 
 	if (size) {
@@ -1480,6 +1521,15 @@ static int hns3_fill_skb_to_desc(struct hns3_enet_ring *ring,
 		bd_num += ret;
 	}
 
+	skb_walk_frags(skb, frag_skb) {
+		ret = hns3_fill_skb_to_desc(ring, frag_skb,
+					    DESC_TYPE_FRAGLIST_SKB);
+		if (unlikely(ret < 0))
+			return ret;
+
+		bd_num += ret;
+	}
+
 	return bd_num;
 }
 
@@ -1508,16 +1558,20 @@ 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_enet_ring *ring = &priv->ring[skb->queue_mapping];
+	struct hns3_desc_cb *desc_cb = &ring->desc_cb[ring->next_to_use];
 	struct netdev_queue *dev_queue;
 	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)) {
 		hns3_tx_doorbell(ring, 0, !netdev_xmit_more());
+
+		u64_stats_update_begin(&ring->syncp);
+		ring->stats.sw_err_cnt++;
+		u64_stats_update_end(&ring->syncp);
+
 		return NETDEV_TX_OK;
 	}
 
@@ -1527,15 +1581,8 @@ netdev_tx_t hns3_nic_net_xmit(struct sk_buff *skb, struct net_device *netdev)
 	ret = hns3_nic_maybe_stop_tx(ring, netdev, skb);
 	if (unlikely(ret <= 0)) {
 		if (ret == -EBUSY) {
-			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);
-			ring->stats.sw_err_cnt++;
-			u64_stats_update_end(&ring->syncp);
 		}
 
 		hns3_rl_err(netdev, "xmit error: %d!\n", ret);
@@ -1544,25 +1591,19 @@ netdev_tx_t hns3_nic_net_xmit(struct sk_buff *skb, struct net_device *netdev)
 
 	next_to_use_head = ring->next_to_use;
 
-	ret = hns3_fill_skb_desc(ring, skb, &ring->desc[ring->next_to_use]);
+	ret = hns3_fill_skb_desc(ring, skb, &ring->desc[ring->next_to_use],
+				 desc_cb);
 	if (unlikely(ret < 0))
 		goto fill_err;
 
+	/* 'ret < 0' means filling error, 'ret == 0' means skb->len is
+	 * zero, which is unlikely, and 'ret > 0' means how many tx desc
+	 * need to be notified to the hw.
+	 */
 	ret = hns3_fill_skb_to_desc(ring, skb, DESC_TYPE_SKB);
-	if (unlikely(ret < 0))
+	if (unlikely(ret <= 0))
 		goto fill_err;
 
-	bd_num += ret;
-
-	skb_walk_frags(skb, frag_skb) {
-		ret = hns3_fill_skb_to_desc(ring, frag_skb,
-					    DESC_TYPE_FRAGLIST_SKB);
-		if (unlikely(ret < 0))
-			goto fill_err;
-
-		bd_num += ret;
-	}
-
 	pre_ntu = ring->next_to_use ? (ring->next_to_use - 1) :
 					(ring->desc_num - 1);
 	ring->desc[pre_ntu].tx.bdtp_fe_sc_vld_ra_ri |=
@@ -1571,9 +1612,9 @@ 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);
-	doorbell = __netdev_tx_sent_queue(dev_queue, skb->len,
+	doorbell = __netdev_tx_sent_queue(dev_queue, desc_cb->send_bytes,
 					  netdev_xmit_more());
-	hns3_tx_doorbell(ring, bd_num, doorbell);
+	hns3_tx_doorbell(ring, ret, doorbell);
 
 	return NETDEV_TX_OK;
 
@@ -1745,11 +1786,15 @@ static void hns3_nic_get_stats64(struct net_device *netdev,
 			tx_drop += ring->stats.tx_l4_proto_err;
 			tx_drop += ring->stats.tx_l2l3l4_err;
 			tx_drop += ring->stats.tx_tso_err;
+			tx_drop += ring->stats.over_max_recursion;
+			tx_drop += ring->stats.hw_limitation;
 			tx_errors += ring->stats.sw_err_cnt;
 			tx_errors += ring->stats.tx_vlan_err;
 			tx_errors += ring->stats.tx_l4_proto_err;
 			tx_errors += ring->stats.tx_l2l3l4_err;
 			tx_errors += ring->stats.tx_tso_err;
+			tx_errors += ring->stats.over_max_recursion;
+			tx_errors += ring->stats.hw_limitation;
 		} while (u64_stats_fetch_retry_irq(&ring->syncp, start));
 
 		/* fetch the rx stats */
@@ -2688,8 +2733,12 @@ static bool hns3_nic_reclaim_desc(struct hns3_enet_ring *ring,
 			break;
 
 		desc_cb = &ring->desc_cb[ntc];
-		(*pkts) += (desc_cb->type == DESC_TYPE_SKB);
-		(*bytes) += desc_cb->length;
+
+		if (desc_cb->type == DESC_TYPE_SKB) {
+			(*pkts)++;
+			(*bytes) += desc_cb->send_bytes;
+		}
+
 		/* desc_cb will be cleaned, after hnae3_free_buffer_detach */
 		hns3_free_buffer_detach(ring, ntc, budget);
 
@@ -4455,11 +4504,11 @@ int hns3_nic_reset_all_ring(struct hnae3_handle *h)
 	int i, j;
 	int ret;
 
-	for (i = 0; i < h->kinfo.num_tqps; i++) {
-		ret = h->ae_algo->ops->reset_queue(h, i);
-		if (ret)
-			return ret;
+	ret = h->ae_algo->ops->reset_queue(h);
+	if (ret)
+		return ret;
 
+	for (i = 0; i < h->kinfo.num_tqps; i++) {
 		hns3_init_ring_hw(&priv->ring[i]);
 
 		/* We need to clear tx ring here because self test will
diff --git a/drivers/net/ethernet/hisilicon/hns3/hns3_enet.h b/drivers/net/ethernet/hisilicon/hns3/hns3_enet.h
index d069b04ee587..daa04aeb0942 100644
--- a/drivers/net/ethernet/hisilicon/hns3/hns3_enet.h
+++ b/drivers/net/ethernet/hisilicon/hns3/hns3_enet.h
@@ -298,7 +298,12 @@ struct hns3_desc_cb {
 
 	/* priv data for the desc, e.g. skb when use with ip stack */
 	void *priv;
-	u32 page_offset;
+
+	union {
+		u32 page_offset;	/* for rx */
+		u32 send_bytes;		/* for tx */
+	};
+
 	u32 length;     /* length of the buffer */
 
 	u16 reuse_flag;
@@ -376,6 +381,8 @@ struct ring_stats {
 			u64 tx_l4_proto_err;
 			u64 tx_l2l3l4_err;
 			u64 tx_tso_err;
+			u64 over_max_recursion;
+			u64 hw_limitation;
 		};
 		struct {
 			u64 rx_pkts;
diff --git a/drivers/net/ethernet/hisilicon/hns3/hns3_ethtool.c b/drivers/net/ethernet/hisilicon/hns3/hns3_ethtool.c
index 0ae6140882b7..b48faf769b1c 100644
--- a/drivers/net/ethernet/hisilicon/hns3/hns3_ethtool.c
+++ b/drivers/net/ethernet/hisilicon/hns3/hns3_ethtool.c
@@ -44,6 +44,8 @@ static const struct hns3_stats hns3_txq_stats[] = {
 	HNS3_TQP_STAT("l4_proto_err", tx_l4_proto_err),
 	HNS3_TQP_STAT("l2l3l4_err", tx_l2l3l4_err),
 	HNS3_TQP_STAT("tso_err", tx_tso_err),
+	HNS3_TQP_STAT("over_max_recursion", over_max_recursion),
+	HNS3_TQP_STAT("hw_limitation", hw_limitation),
 };
 
 #define HNS3_TXQ_STATS_COUNT ARRAY_SIZE(hns3_txq_stats)
diff --git a/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_cmd.h b/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_cmd.h
index 7feab8405d7c..c6fc22e29581 100644
--- a/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_cmd.h
+++ b/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_cmd.h
@@ -948,10 +948,16 @@ struct hclge_reset_tqp_queue_cmd {
 
 #define HCLGE_CFG_RESET_MAC_B		3
 #define HCLGE_CFG_RESET_FUNC_B		7
+#define HCLGE_CFG_RESET_RCB_B		1
 struct hclge_reset_cmd {
 	u8 mac_func_reset;
 	u8 fun_reset_vfid;
-	u8 rsv[22];
+	u8 fun_reset_rcb;
+	u8 rsv;
+	__le16 fun_reset_rcb_vqid_start;
+	__le16 fun_reset_rcb_vqid_num;
+	u8 fun_reset_rcb_return_status;
+	u8 rsv1[15];
 };
 
 #define HCLGE_PF_RESET_DONE_BIT		BIT(0)
diff --git a/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_main.c b/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_main.c
index d964e2c527f0..bc805d5fb16e 100644
--- a/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_main.c
+++ b/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_main.c
@@ -6439,8 +6439,9 @@ static int hclge_add_fd_entry_common(struct hclge_dev *hdev,
 	if (ret)
 		goto out;
 
-	hclge_update_fd_list(hdev, HCLGE_FD_ACTIVE, rule->location, rule);
+	rule->state = HCLGE_FD_ACTIVE;
 	hdev->fd_active_type = rule->rule_type;
+	hclge_update_fd_list(hdev, rule->state, rule->location, rule);
 
 out:
 	spin_unlock_bh(&hdev->fd_rule_lock);
@@ -7002,6 +7003,7 @@ static void hclge_fd_build_arfs_rule(const struct hclge_fd_rule_tuples *tuples,
 	rule->action = 0;
 	rule->vf_id = 0;
 	rule->rule_type = HCLGE_FD_ARFS_ACTIVE;
+	rule->state = HCLGE_FD_TO_ADD;
 	if (tuples->ether_proto == ETH_P_IP) {
 		if (tuples->ip_proto == IPPROTO_TCP)
 			rule->flow_type = TCP_V4_FLOW;
@@ -7064,8 +7066,7 @@ static int hclge_add_fd_entry_by_arfs(struct hnae3_handle *handle, u16 queue_id,
 		rule->arfs.flow_id = flow_id;
 		rule->queue_id = queue_id;
 		hclge_fd_build_arfs_rule(&new_tuples, rule);
-		hclge_update_fd_list(hdev, HCLGE_FD_TO_ADD, rule->location,
-				     rule);
+		hclge_update_fd_list(hdev, rule->state, rule->location, rule);
 		hdev->fd_active_type = HCLGE_FD_ARFS_ACTIVE;
 	} else if (rule->queue_id != queue_id) {
 		rule->queue_id = queue_id;
@@ -7796,13 +7797,12 @@ static int hclge_set_phy_loopback(struct hclge_dev *hdev, bool en)
 	return ret;
 }
 
-static int hclge_tqp_enable(struct hclge_dev *hdev, unsigned int tqp_id,
-			    int stream_id, bool enable)
+static int hclge_tqp_enable_cmd_send(struct hclge_dev *hdev, u16 tqp_id,
+				     u16 stream_id, bool enable)
 {
 	struct hclge_desc desc;
 	struct hclge_cfg_com_tqp_queue_cmd *req =
 		(struct hclge_cfg_com_tqp_queue_cmd *)desc.data;
-	int ret;
 
 	hclge_cmd_setup_basic_desc(&desc, HCLGE_OPC_CFG_COM_TQP_QUEUE, false);
 	req->tqp_id = cpu_to_le16(tqp_id);
@@ -7810,20 +7810,30 @@ static int hclge_tqp_enable(struct hclge_dev *hdev, unsigned int tqp_id,
 	if (enable)
 		req->enable |= 1U << HCLGE_TQP_ENABLE_B;
 
-	ret = hclge_cmd_send(&hdev->hw, &desc, 1);
-	if (ret)
-		dev_err(&hdev->pdev->dev,
-			"Tqp enable fail, status =%d.\n", ret);
-	return ret;
+	return hclge_cmd_send(&hdev->hw, &desc, 1);
+}
+
+static int hclge_tqp_enable(struct hnae3_handle *handle, bool enable)
+{
+	struct hclge_vport *vport = hclge_get_vport(handle);
+	struct hclge_dev *hdev = vport->back;
+	int ret;
+	u16 i;
+
+	for (i = 0; i < handle->kinfo.num_tqps; i++) {
+		ret = hclge_tqp_enable_cmd_send(hdev, i, 0, enable);
+		if (ret)
+			return ret;
+	}
+	return 0;
 }
 
 static int hclge_set_loopback(struct hnae3_handle *handle,
 			      enum hnae3_loop loop_mode, bool en)
 {
 	struct hclge_vport *vport = hclge_get_vport(handle);
-	struct hnae3_knic_private_info *kinfo;
 	struct hclge_dev *hdev = vport->back;
-	int i, ret;
+	int ret;
 
 	/* Loopback can be enabled in three places: SSU, MAC, and serdes. By
 	 * default, SSU loopback is enabled, so if the SMAC and the DMAC are
@@ -7860,14 +7870,12 @@ static int hclge_set_loopback(struct hnae3_handle *handle,
 	if (ret)
 		return ret;
 
-	kinfo = &vport->nic.kinfo;
-	for (i = 0; i < kinfo->num_tqps; i++) {
-		ret = hclge_tqp_enable(hdev, i, 0, en);
-		if (ret)
-			return ret;
-	}
+	ret = hclge_tqp_enable(handle, en);
+	if (ret)
+		dev_err(&hdev->pdev->dev, "failed to %s tqp in loopback, ret = %d\n",
+			en ? "enable" : "disable", ret);
 
-	return 0;
+	return ret;
 }
 
 static int hclge_set_default_loopback(struct hclge_dev *hdev)
@@ -7954,7 +7962,6 @@ static void hclge_ae_stop(struct hnae3_handle *handle)
 {
 	struct hclge_vport *vport = hclge_get_vport(handle);
 	struct hclge_dev *hdev = vport->back;
-	int i;
 
 	set_bit(HCLGE_STATE_DOWN, &hdev->state);
 	spin_lock_bh(&hdev->fd_rule_lock);
@@ -7971,8 +7978,7 @@ static void hclge_ae_stop(struct hnae3_handle *handle)
 		return;
 	}
 
-	for (i = 0; i < handle->kinfo.num_tqps; i++)
-		hclge_reset_tqp(handle, i);
+	hclge_reset_tqp(handle);
 
 	hclge_config_mac_tnl_int(hdev, false);
 
@@ -10346,7 +10352,7 @@ out:
 	return ret;
 }
 
-static int hclge_send_reset_tqp_cmd(struct hclge_dev *hdev, u16 queue_id,
+static int hclge_reset_tqp_cmd_send(struct hclge_dev *hdev, u16 queue_id,
 				    bool enable)
 {
 	struct hclge_reset_tqp_queue_cmd *req;
@@ -10402,94 +10408,114 @@ u16 hclge_covert_handle_qid_global(struct hnae3_handle *handle, u16 queue_id)
 	return tqp->index;
 }
 
-int hclge_reset_tqp(struct hnae3_handle *handle, u16 queue_id)
+static int hclge_reset_tqp_cmd(struct hnae3_handle *handle)
 {
 	struct hclge_vport *vport = hclge_get_vport(handle);
 	struct hclge_dev *hdev = vport->back;
-	int reset_try_times = 0;
+	u16 reset_try_times = 0;
 	int reset_status;
 	u16 queue_gid;
 	int ret;
+	u16 i;
 
-	queue_gid = hclge_covert_handle_qid_global(handle, queue_id);
-
-	ret = hclge_tqp_enable(hdev, queue_id, 0, false);
-	if (ret) {
-		dev_err(&hdev->pdev->dev, "Disable tqp fail, ret = %d\n", ret);
-		return ret;
-	}
+	for (i = 0; i < handle->kinfo.num_tqps; i++) {
+		queue_gid = hclge_covert_handle_qid_global(handle, i);
+		ret = hclge_reset_tqp_cmd_send(hdev, queue_gid, true);
+		if (ret) {
+			dev_err(&hdev->pdev->dev,
+				"failed to send reset tqp cmd, ret = %d\n",
+				ret);
+			return ret;
+		}
 
-	ret = hclge_send_reset_tqp_cmd(hdev, queue_gid, true);
-	if (ret) {
-		dev_err(&hdev->pdev->dev,
-			"Send reset tqp cmd fail, ret = %d\n", ret);
-		return ret;
-	}
+		while (reset_try_times++ < HCLGE_TQP_RESET_TRY_TIMES) {
+			reset_status = hclge_get_reset_status(hdev, queue_gid);
+			if (reset_status)
+				break;
 
-	while (reset_try_times++ < HCLGE_TQP_RESET_TRY_TIMES) {
-		reset_status = hclge_get_reset_status(hdev, queue_gid);
-		if (reset_status)
-			break;
+			/* Wait for tqp hw reset */
+			usleep_range(1000, 1200);
+		}
 
-		/* Wait for tqp hw reset */
-		usleep_range(1000, 1200);
-	}
+		if (reset_try_times >= HCLGE_TQP_RESET_TRY_TIMES) {
+			dev_err(&hdev->pdev->dev,
+				"wait for tqp hw reset timeout\n");
+			return -ETIME;
+		}
 
-	if (reset_try_times >= HCLGE_TQP_RESET_TRY_TIMES) {
-		dev_err(&hdev->pdev->dev, "Reset TQP fail\n");
-		return ret;
+		ret = hclge_reset_tqp_cmd_send(hdev, queue_gid, false);
+		if (ret) {
+			dev_err(&hdev->pdev->dev,
+				"failed to deassert soft reset, ret = %d\n",
+				ret);
+			return ret;
+		}
+		reset_try_times = 0;
 	}
-
-	ret = hclge_send_reset_tqp_cmd(hdev, queue_gid, false);
-	if (ret)
-		dev_err(&hdev->pdev->dev,
-			"Deassert the soft reset fail, ret = %d\n", ret);
-
-	return ret;
+	return 0;
 }
 
-void hclge_reset_vf_queue(struct hclge_vport *vport, u16 queue_id)
+static int hclge_reset_rcb(struct hnae3_handle *handle)
 {
-	struct hnae3_handle *handle = &vport->nic;
+#define HCLGE_RESET_RCB_NOT_SUPPORT	0U
+#define HCLGE_RESET_RCB_SUCCESS		1U
+
+	struct hclge_vport *vport = hclge_get_vport(handle);
 	struct hclge_dev *hdev = vport->back;
-	int reset_try_times = 0;
-	int reset_status;
+	struct hclge_reset_cmd *req;
+	struct hclge_desc desc;
+	u8 return_status;
 	u16 queue_gid;
 	int ret;
 
-	if (queue_id >= handle->kinfo.num_tqps) {
-		dev_warn(&hdev->pdev->dev, "Invalid vf queue id(%u)\n",
-			 queue_id);
-		return;
-	}
+	queue_gid = hclge_covert_handle_qid_global(handle, 0);
 
-	queue_gid = hclge_covert_handle_qid_global(&vport->nic, queue_id);
+	req = (struct hclge_reset_cmd *)desc.data;
+	hclge_cmd_setup_basic_desc(&desc, HCLGE_OPC_CFG_RST_TRIGGER, false);
+	hnae3_set_bit(req->fun_reset_rcb, HCLGE_CFG_RESET_RCB_B, 1);
+	req->fun_reset_rcb_vqid_start = cpu_to_le16(queue_gid);
+	req->fun_reset_rcb_vqid_num = cpu_to_le16(handle->kinfo.num_tqps);
 
-	ret = hclge_send_reset_tqp_cmd(hdev, queue_gid, true);
+	ret = hclge_cmd_send(&hdev->hw, &desc, 1);
 	if (ret) {
-		dev_warn(&hdev->pdev->dev,
-			 "Send reset tqp cmd fail, ret = %d\n", ret);
-		return;
+		dev_err(&hdev->pdev->dev,
+			"failed to send rcb reset cmd, ret = %d\n", ret);
+		return ret;
 	}
 
-	while (reset_try_times++ < HCLGE_TQP_RESET_TRY_TIMES) {
-		reset_status = hclge_get_reset_status(hdev, queue_gid);
-		if (reset_status)
-			break;
+	return_status = req->fun_reset_rcb_return_status;
+	if (return_status == HCLGE_RESET_RCB_SUCCESS)
+		return 0;
 
-		/* Wait for tqp hw reset */
-		usleep_range(1000, 1200);
+	if (return_status != HCLGE_RESET_RCB_NOT_SUPPORT) {
+		dev_err(&hdev->pdev->dev, "failed to reset rcb, ret = %u\n",
+			return_status);
+		return -EIO;
 	}
 
-	if (reset_try_times >= HCLGE_TQP_RESET_TRY_TIMES) {
-		dev_warn(&hdev->pdev->dev, "Reset TQP fail\n");
-		return;
+	/* if reset rcb cmd is unsupported, we need to send reset tqp cmd
+	 * again to reset all tqps
+	 */
+	return hclge_reset_tqp_cmd(handle);
+}
+
+int hclge_reset_tqp(struct hnae3_handle *handle)
+{
+	struct hclge_vport *vport = hclge_get_vport(handle);
+	struct hclge_dev *hdev = vport->back;
+	int ret;
+
+	/* only need to disable PF's tqp */
+	if (!vport->vport_id) {
+		ret = hclge_tqp_enable(handle, false);
+		if (ret) {
+			dev_err(&hdev->pdev->dev,
+				"failed to disable tqp, ret = %d\n", ret);
+			return ret;
+		}
 	}
 
-	ret = hclge_send_reset_tqp_cmd(hdev, queue_gid, false);
-	if (ret)
-		dev_warn(&hdev->pdev->dev,
-			 "Deassert the soft reset fail, ret = %d\n", ret);
+	return hclge_reset_rcb(handle);
 }
 
 static u32 hclge_get_fw_version(struct hnae3_handle *handle)
@@ -11929,7 +11955,6 @@ static int hclge_get_64_bit_regs(struct hclge_dev *hdev, u32 regs_num,
 #define REG_LEN_PER_LINE	(REG_NUM_PER_LINE * sizeof(u32))
 #define REG_SEPARATOR_LINE	1
 #define REG_NUM_REMAIN_MASK	3
-#define BD_LIST_MAX_NUM		30
 
 int hclge_query_bd_num_cmd_send(struct hclge_dev *hdev, struct hclge_desc *desc)
 {
@@ -12023,15 +12048,19 @@ static int hclge_get_dfx_reg_len(struct hclge_dev *hdev, int *len)
 {
 	u32 dfx_reg_type_num = ARRAY_SIZE(hclge_dfx_bd_offset_list);
 	int data_len_per_desc, bd_num, i;
-	int bd_num_list[BD_LIST_MAX_NUM];
+	int *bd_num_list;
 	u32 data_len;
 	int ret;
 
+	bd_num_list = kcalloc(dfx_reg_type_num, sizeof(int), GFP_KERNEL);
+	if (!bd_num_list)
+		return -ENOMEM;
+
 	ret = hclge_get_dfx_reg_bd_num(hdev, bd_num_list, dfx_reg_type_num);
 	if (ret) {
 		dev_err(&hdev->pdev->dev,
 			"Get dfx reg bd num fail, status is %d.\n", ret);
-		return ret;
+		goto out;
 	}
 
 	data_len_per_desc = sizeof_field(struct hclge_desc, data);
@@ -12042,6 +12071,8 @@ static int hclge_get_dfx_reg_len(struct hclge_dev *hdev, int *len)
 		*len += (data_len / REG_LEN_PER_LINE + 1) * REG_LEN_PER_LINE;
 	}
 
+out:
+	kfree(bd_num_list);
 	return ret;
 }
 
@@ -12049,16 +12080,20 @@ static int hclge_get_dfx_reg(struct hclge_dev *hdev, void *data)
 {
 	u32 dfx_reg_type_num = ARRAY_SIZE(hclge_dfx_bd_offset_list);
 	int bd_num, bd_num_max, buf_len, i;
-	int bd_num_list[BD_LIST_MAX_NUM];
 	struct hclge_desc *desc_src;
+	int *bd_num_list;
 	u32 *reg = data;
 	int ret;
 
+	bd_num_list = kcalloc(dfx_reg_type_num, sizeof(int), GFP_KERNEL);
+	if (!bd_num_list)
+		return -ENOMEM;
+
 	ret = hclge_get_dfx_reg_bd_num(hdev, bd_num_list, dfx_reg_type_num);
 	if (ret) {
 		dev_err(&hdev->pdev->dev,
 			"Get dfx reg bd num fail, status is %d.\n", ret);
-		return ret;
+		goto out;
 	}
 
 	bd_num_max = bd_num_list[0];
@@ -12067,8 +12102,10 @@ static int hclge_get_dfx_reg(struct hclge_dev *hdev, void *data)
 
 	buf_len = sizeof(*desc_src) * bd_num_max;
 	desc_src = kzalloc(buf_len, GFP_KERNEL);
-	if (!desc_src)
-		return -ENOMEM;
+	if (!desc_src) {
+		ret = -ENOMEM;
+		goto out;
+	}
 
 	for (i = 0; i < dfx_reg_type_num; i++) {
 		bd_num = bd_num_list[i];
@@ -12084,6 +12121,8 @@ static int hclge_get_dfx_reg(struct hclge_dev *hdev, void *data)
 	}
 
 	kfree(desc_src);
+out:
+	kfree(bd_num_list);
 	return ret;
 }
 
diff --git a/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_main.h b/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_main.h
index dc3d29d41848..c1aaf7c534c9 100644
--- a/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_main.h
+++ b/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_main.h
@@ -1053,8 +1053,7 @@ int hclge_rss_init_hw(struct hclge_dev *hdev);
 void hclge_rss_indir_init_cfg(struct hclge_dev *hdev);
 
 void hclge_mbx_handler(struct hclge_dev *hdev);
-int hclge_reset_tqp(struct hnae3_handle *handle, u16 queue_id);
-void hclge_reset_vf_queue(struct hclge_vport *vport, u16 queue_id);
+int hclge_reset_tqp(struct hnae3_handle *handle);
 int hclge_cfg_flowctrl(struct hclge_dev *hdev);
 int hclge_func_reset_cmd(struct hclge_dev *hdev, int func_id);
 int hclge_vport_start(struct hclge_vport *vport);
diff --git a/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_mbx.c b/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_mbx.c
index 51a36e74f088..c88607bdda59 100644
--- a/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_mbx.c
+++ b/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_mbx.c
@@ -550,14 +550,32 @@ static void hclge_get_link_mode(struct hclge_vport *vport,
 			   HCLGE_MBX_LINK_STAT_MODE, dest_vfid);
 }
 
-static void hclge_mbx_reset_vf_queue(struct hclge_vport *vport,
-				     struct hclge_mbx_vf_to_pf_cmd *mbx_req)
+static int hclge_mbx_reset_vf_queue(struct hclge_vport *vport,
+				    struct hclge_mbx_vf_to_pf_cmd *mbx_req,
+				    struct hclge_respond_to_vf_msg *resp_msg)
 {
+#define HCLGE_RESET_ALL_QUEUE_DONE	1U
+	struct hnae3_handle *handle = &vport->nic;
+	struct hclge_dev *hdev = vport->back;
 	u16 queue_id;
+	int ret;
 
 	memcpy(&queue_id, mbx_req->msg.data, sizeof(queue_id));
+	resp_msg->data[0] = HCLGE_RESET_ALL_QUEUE_DONE;
+	resp_msg->len = sizeof(u8);
 
-	hclge_reset_vf_queue(vport, queue_id);
+	/* pf will reset vf's all queues at a time. So it is unnecessary
+	 * to reset queues if queue_id > 0, just return success.
+	 */
+	if (queue_id > 0)
+		return 0;
+
+	ret = hclge_reset_tqp(handle);
+	if (ret)
+		dev_err(&hdev->pdev->dev, "failed to reset vf %u queue, ret = %d\n",
+			vport->vport_id - HCLGE_VF_VPORT_START_NUM, ret);
+
+	return ret;
 }
 
 static int hclge_reset_vf(struct hclge_vport *vport)
@@ -783,7 +801,7 @@ void hclge_mbx_handler(struct hclge_dev *hdev)
 					ret);
 			break;
 		case HCLGE_MBX_QUEUE_RESET:
-			hclge_mbx_reset_vf_queue(vport, req);
+			ret = hclge_mbx_reset_vf_queue(vport, req, &resp_msg);
 			break;
 		case HCLGE_MBX_RESET:
 			ret = hclge_reset_vf(vport);
diff --git a/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_tm.c b/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_tm.c
index aa81b8c56fce..ebb962bad451 100644
--- a/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_tm.c
+++ b/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_tm.c
@@ -664,15 +664,6 @@ static void hclge_tm_update_kinfo_rss_size(struct hclge_vport *vport)
 		kinfo->rss_size = kinfo->req_rss_size;
 	} else if (kinfo->rss_size > max_rss_size ||
 		   (!kinfo->req_rss_size && kinfo->rss_size < max_rss_size)) {
-		/* if user not set rss, the rss_size should compare with the
-		 * valid msi numbers to ensure one to one map between tqp and
-		 * irq as default.
-		 */
-		if (!kinfo->req_rss_size)
-			max_rss_size = min_t(u16, max_rss_size,
-					     (hdev->num_nic_msi - 1) /
-					     kinfo->tc_info.num_tc);
-
 		/* Set to the maximum specification value (max_rss_size). */
 		kinfo->rss_size = max_rss_size;
 	}
diff --git a/drivers/net/ethernet/hisilicon/hns3/hns3vf/hclgevf_cmd.h b/drivers/net/ethernet/hisilicon/hns3/hns3vf/hclgevf_cmd.h
index 8a37a22a176b..c6dc11b32aa7 100644
--- a/drivers/net/ethernet/hisilicon/hns3/hns3vf/hclgevf_cmd.h
+++ b/drivers/net/ethernet/hisilicon/hns3/hns3vf/hclgevf_cmd.h
@@ -223,11 +223,14 @@ struct hclgevf_rss_indirection_table_cmd {
 };
 
 #define HCLGEVF_RSS_TC_OFFSET_S		0
-#define HCLGEVF_RSS_TC_OFFSET_M		(0x3ff << HCLGEVF_RSS_TC_OFFSET_S)
+#define HCLGEVF_RSS_TC_OFFSET_M		GENMASK(10, 0)
+#define HCLGEVF_RSS_TC_SIZE_MSB_B	11
 #define HCLGEVF_RSS_TC_SIZE_S		12
-#define HCLGEVF_RSS_TC_SIZE_M		(0x7 << HCLGEVF_RSS_TC_SIZE_S)
+#define HCLGEVF_RSS_TC_SIZE_M		GENMASK(14, 12)
 #define HCLGEVF_RSS_TC_VALID_B		15
 #define HCLGEVF_MAX_TC_NUM		8
+#define HCLGEVF_RSS_TC_SIZE_MSB_OFFSET	3
+
 struct hclgevf_rss_tc_mode_cmd {
 	__le16 rss_tc_mode[HCLGEVF_MAX_TC_NUM];
 	u8 rsv[8];
diff --git a/drivers/net/ethernet/hisilicon/hns3/hns3vf/hclgevf_main.c b/drivers/net/ethernet/hisilicon/hns3/hns3vf/hclgevf_main.c
index 5e512cd01a96..1682769112d0 100644
--- a/drivers/net/ethernet/hisilicon/hns3/hns3vf/hclgevf_main.c
+++ b/drivers/net/ethernet/hisilicon/hns3/hns3vf/hclgevf_main.c
@@ -706,6 +706,9 @@ static int hclgevf_set_rss_tc_mode(struct hclgevf_dev *hdev,  u16 rss_size)
 			      (tc_valid[i] & 0x1));
 		hnae3_set_field(mode, HCLGEVF_RSS_TC_SIZE_M,
 				HCLGEVF_RSS_TC_SIZE_S, tc_size[i]);
+		hnae3_set_bit(mode, HCLGEVF_RSS_TC_SIZE_MSB_B,
+			      tc_size[i] >> HCLGEVF_RSS_TC_SIZE_MSB_OFFSET &
+			      0x1);
 		hnae3_set_field(mode, HCLGEVF_RSS_TC_OFFSET_M,
 				HCLGEVF_RSS_TC_OFFSET_S, tc_offset[i]);
 
@@ -1240,12 +1243,11 @@ static void hclgevf_sync_promisc_mode(struct hclgevf_dev *hdev)
 	}
 }
 
-static int hclgevf_tqp_enable(struct hclgevf_dev *hdev, unsigned int tqp_id,
-			      int stream_id, bool enable)
+static int hclgevf_tqp_enable_cmd_send(struct hclgevf_dev *hdev, u16 tqp_id,
+				       u16 stream_id, bool enable)
 {
 	struct hclgevf_cfg_com_tqp_queue_cmd *req;
 	struct hclgevf_desc desc;
-	int status;
 
 	req = (struct hclgevf_cfg_com_tqp_queue_cmd *)desc.data;
 
@@ -1256,12 +1258,22 @@ static int hclgevf_tqp_enable(struct hclgevf_dev *hdev, unsigned int tqp_id,
 	if (enable)
 		req->enable |= 1U << HCLGEVF_TQP_ENABLE_B;
 
-	status = hclgevf_cmd_send(&hdev->hw, &desc, 1);
-	if (status)
-		dev_err(&hdev->pdev->dev,
-			"TQP enable fail, status =%d.\n", status);
+	return hclgevf_cmd_send(&hdev->hw, &desc, 1);
+}
 
-	return status;
+static int hclgevf_tqp_enable(struct hnae3_handle *handle, bool enable)
+{
+	struct hclgevf_dev *hdev = hclgevf_ae_get_hdev(handle);
+	int ret;
+	u16 i;
+
+	for (i = 0; i < handle->kinfo.num_tqps; i++) {
+		ret = hclgevf_tqp_enable_cmd_send(hdev, i, 0, enable);
+		if (ret)
+			return ret;
+	}
+
+	return 0;
 }
 
 static void hclgevf_reset_tqp_stats(struct hnae3_handle *handle)
@@ -1710,20 +1722,39 @@ static int hclgevf_en_hw_strip_rxvtag(struct hnae3_handle *handle, bool enable)
 	return hclgevf_send_mbx_msg(hdev, &send_msg, false, NULL, 0);
 }
 
-static int hclgevf_reset_tqp(struct hnae3_handle *handle, u16 queue_id)
+static int hclgevf_reset_tqp(struct hnae3_handle *handle)
 {
+#define HCLGEVF_RESET_ALL_QUEUE_DONE	1U
 	struct hclgevf_dev *hdev = hclgevf_ae_get_hdev(handle);
 	struct hclge_vf_to_pf_msg send_msg;
+	u8 return_status = 0;
 	int ret;
+	u16 i;
 
 	/* disable vf queue before send queue reset msg to PF */
-	ret = hclgevf_tqp_enable(hdev, queue_id, 0, false);
-	if (ret)
+	ret = hclgevf_tqp_enable(handle, false);
+	if (ret) {
+		dev_err(&hdev->pdev->dev, "failed to disable tqp, ret = %d\n",
+			ret);
 		return ret;
+	}
 
 	hclgevf_build_send_msg(&send_msg, HCLGE_MBX_QUEUE_RESET, 0);
-	memcpy(send_msg.data, &queue_id, sizeof(queue_id));
-	return hclgevf_send_mbx_msg(hdev, &send_msg, true, NULL, 0);
+
+	ret = hclgevf_send_mbx_msg(hdev, &send_msg, true, &return_status,
+				   sizeof(return_status));
+	if (ret || return_status == HCLGEVF_RESET_ALL_QUEUE_DONE)
+		return ret;
+
+	for (i = 1; i < handle->kinfo.num_tqps; i++) {
+		hclgevf_build_send_msg(&send_msg, HCLGE_MBX_QUEUE_RESET, 0);
+		memcpy(send_msg.data, &i, sizeof(i));
+		ret = hclgevf_send_mbx_msg(hdev, &send_msg, true, NULL, 0);
+		if (ret)
+			return ret;
+	}
+
+	return 0;
 }
 
 static int hclgevf_set_mtu(struct hnae3_handle *handle, int new_mtu)
@@ -2636,14 +2667,11 @@ static int hclgevf_ae_start(struct hnae3_handle *handle)
 static void hclgevf_ae_stop(struct hnae3_handle *handle)
 {
 	struct hclgevf_dev *hdev = hclgevf_ae_get_hdev(handle);
-	int i;
 
 	set_bit(HCLGEVF_STATE_DOWN, &hdev->state);
 
 	if (hdev->reset_type != HNAE3_VF_RESET)
-		for (i = 0; i < handle->kinfo.num_tqps; i++)
-			if (hclgevf_reset_tqp(handle, i))
-				break;
+		hclgevf_reset_tqp(handle);
 
 	hclgevf_reset_tqp_stats(handle);
 	hclgevf_update_link_status(hdev, 0);