Merge branch 'hns3-next'

Huazhong Tan says:

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

There are some misc updates for the HNS3 ethernet driver.
====================

Signed-off-by: David S. Miller <[e-mail]>

drivers/net/ethernet/hisilicon/hns3/hnae3.h

···
 #define hnae3_dev_stash_supported(hdev) \
 	test_bit(HNAE3_DEV_SUPPORT_STASH_B, (hdev)->ae_dev->caps)
 
+#define hnae3_ae_dev_tqp_txrx_indep_supported(ae_dev) \
+	test_bit(HNAE3_DEV_SUPPORT_TQP_TXRX_INDEP_B, (ae_dev)->caps)
+
 #define ring_ptr_move_fw(ring, p) \
 	((ring)->p = ((ring)->p + 1) % (ring)->desc_num)
 #define ring_ptr_move_bw(ring, p) \

drivers/net/ethernet/hisilicon/hns3/hns3_debugfs.c

···
 static int hns3_dbg_queue_info(struct hnae3_handle *h,
 			       const char *cmd_buf)
 {
+	struct hnae3_ae_dev *ae_dev = pci_get_drvdata(h->pdev);
 	struct hns3_nic_priv *priv = h->priv;
 	struct hns3_enet_ring *ring;
 	u32 base_add_l, base_add_h;
···
 
 		value = readl_relaxed(ring->tqp->io_base +
 				      HNS3_RING_TX_RING_PKTNUM_RECORD_REG);
-		dev_info(&h->pdev->dev, "TX(%u) RING PKTNUM: %u\n\n", i,
-			 value);
+		dev_info(&h->pdev->dev, "TX(%u) RING PKTNUM: %u\n", i, value);
+
+		value = readl_relaxed(ring->tqp->io_base + HNS3_RING_EN_REG);
+		dev_info(&h->pdev->dev, "TX/RX(%u) RING EN: %s\n", i,
+			 value ? "enable" : "disable");
+
+		if (hnae3_ae_dev_tqp_txrx_indep_supported(ae_dev)) {
+			value = readl_relaxed(ring->tqp->io_base +
+					      HNS3_RING_TX_EN_REG);
+			dev_info(&h->pdev->dev, "TX(%u) RING EN: %s\n", i,
+				 value ? "enable" : "disable");
+
+			value = readl_relaxed(ring->tqp->io_base +
+					      HNS3_RING_RX_EN_REG);
+			dev_info(&h->pdev->dev, "RX(%u) RING EN: %s\n", i,
+				 value ? "enable" : "disable");
+		}
+
+		dev_info(&h->pdev->dev, "\n");
 	}
 
 	return 0;
···
 	dev_info(&h->pdev->dev, "queue map\n");
 	dev_info(&h->pdev->dev, "bd info <q_num> <bd index>\n");
 	dev_info(&h->pdev->dev, "dev capability\n");
+	dev_info(&h->pdev->dev, "dev spec\n");
 
 	if (!hns3_is_phys_func(h->pdev))
 		return;
···
 		 test_bit(HNAE3_DEV_SUPPORT_PTP_B, caps) ? "yes" : "no");
 	dev_info(&h->pdev->dev, "support INT QL: %s\n",
 		 test_bit(HNAE3_DEV_SUPPORT_INT_QL_B, caps) ? "yes" : "no");
+}
+
+static void hns3_dbg_dev_specs(struct hnae3_handle *h)
+{
+	struct hnae3_ae_dev *ae_dev = pci_get_drvdata(h->pdev);
+	struct hnae3_dev_specs *dev_specs = &ae_dev->dev_specs;
+	struct hnae3_knic_private_info *kinfo = &h->kinfo;
+	struct hns3_nic_priv *priv  = h->priv;
+
+	dev_info(priv->dev, "MAC entry num: %u\n", dev_specs->mac_entry_num);
+	dev_info(priv->dev, "MNG entry num: %u\n", dev_specs->mng_entry_num);
+	dev_info(priv->dev, "MAX non tso bd num: %u\n",
+		 dev_specs->max_non_tso_bd_num);
+	dev_info(priv->dev, "RSS ind tbl size: %u\n",
+		 dev_specs->rss_ind_tbl_size);
+	dev_info(priv->dev, "RSS key size: %u\n", dev_specs->rss_key_size);
+	dev_info(priv->dev, "RSS size: %u\n", kinfo->rss_size);
+	dev_info(priv->dev, "Allocated RSS size: %u\n", kinfo->req_rss_size);
+	dev_info(priv->dev, "Task queue pairs numbers: %u\n", kinfo->num_tqps);
+
+	dev_info(priv->dev, "RX buffer length: %u\n", kinfo->rx_buf_len);
+	dev_info(priv->dev, "Desc num per TX queue: %u\n", kinfo->num_tx_desc);
+	dev_info(priv->dev, "Desc num per RX queue: %u\n", kinfo->num_rx_desc);
+	dev_info(priv->dev, "Total number of enabled TCs: %u\n", kinfo->num_tc);
+	dev_info(priv->dev, "MAX INT QL: %u\n", dev_specs->int_ql_max);
 }
 
 static ssize_t hns3_dbg_cmd_read(struct file *filp, char __user *buffer,
···
 		ret = hns3_dbg_bd_info(handle, cmd_buf);
 	else if (strncmp(cmd_buf, "dev capability", 14) == 0)
 		hns3_dbg_dev_caps(handle);
+	else if (strncmp(cmd_buf, "dev spec", 8) == 0)
+		hns3_dbg_dev_specs(handle);
 	else if (handle->ae_algo->ops->dbg_run_cmd)
 		ret = handle->ae_algo->ops->dbg_run_cmd(handle, cmd_buf);
 	else

drivers/net/ethernet/hisilicon/hns3/hns3_enet.c

···
 
 	/* normal or tunnel packet */
 	l4_offset = l4.hdr - skb->data;
-	hdr_len = (l4.tcp->doff << 2) + l4_offset;
 
 	/* remove payload length from inner pseudo checksum when tso */
 	l4_paylen = skb->len - l4_offset;
-	csum_replace_by_diff(&l4.tcp->check,
-			     (__force __wsum)htonl(l4_paylen));
+
+	if (skb_shinfo(skb)->gso_type & SKB_GSO_UDP_L4) {
+		hdr_len = sizeof(*l4.udp) + l4_offset;
+		csum_replace_by_diff(&l4.udp->check,
+				     (__force __wsum)htonl(l4_paylen));
+	} else {
+		hdr_len = (l4.tcp->doff << 2) + l4_offset;
+		csum_replace_by_diff(&l4.tcp->check,
+				     (__force __wsum)htonl(l4_paylen));
+	}
 
 	/* find the txbd field values */
 	*paylen = skb->len - hdr_len;
···
 	return bd_num;
 }
 
-static unsigned int hns3_tx_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)
 {
 	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) &&
-		   skb_shinfo(skb)->nr_frags < HNS3_MAX_NON_TSO_BD_NUM))
+		   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)))
+		     (!skb_is_gso(skb) && skb->len >
+		      HNS3_MAX_NON_TSO_SIZE(max_non_tso_bd_num))))
 		return HNS3_MAX_TSO_BD_NUM + 1U;
 
 	bd_num = hns3_skb_bd_num(skb, bd_size, bd_num);
···
 	return skb_inner_transport_offset(skb) + inner_tcp_hdrlen(skb);
 }
 
-/* HW need every continuous 8 buffer data to be larger than MSS,
- * we simplify it by ensuring skb_headlen + the first continuous
- * 7 frags to to be larger than gso header len + mss, and the remaining
- * continuous 7 frags to be larger than MSS except the last 7 frags.
+/* HW need every continuous max_non_tso_bd_num buffer data to be larger
+ * than MSS, we simplify it by ensuring skb_headlen + the first continuous
+ * max_non_tso_bd_num - 1 frags to be larger than gso header len + mss,
+ * and the remaining continuous max_non_tso_bd_num - 1 frags to be larger
+ * than MSS except the last max_non_tso_bd_num - 1 frags.
  */
 static bool hns3_skb_need_linearized(struct sk_buff *skb, unsigned int *bd_size,
-				     unsigned int bd_num)
+				     unsigned int bd_num, u8 max_non_tso_bd_num)
 {
 	unsigned int tot_len = 0;
 	int i;
 
-	for (i = 0; i < HNS3_MAX_NON_TSO_BD_NUM - 1U; i++)
+	for (i = 0; i < max_non_tso_bd_num - 1U; i++)
 		tot_len += bd_size[i];
 
-	/* ensure the first 8 frags is greater than mss + header */
-	if (tot_len + bd_size[HNS3_MAX_NON_TSO_BD_NUM - 1U] <
+	/* ensure the first max_non_tso_bd_num frags is greater than
+	 * mss + header
+	 */
+	if (tot_len + bd_size[max_non_tso_bd_num - 1U] <
 	    skb_shinfo(skb)->gso_size + hns3_gso_hdr_len(skb))
 		return true;
 
-	/* ensure every continuous 7 buffer is greater than mss
-	 * except the last one.
+	/* ensure every continuous max_non_tso_bd_num - 1 buffer is greater
+	 * than mss except the last one.
 	 */
-	for (i = 0; i < bd_num - HNS3_MAX_NON_TSO_BD_NUM; i++) {
+	for (i = 0; i < bd_num - max_non_tso_bd_num; i++) {
 		tot_len -= bd_size[i];
-		tot_len += bd_size[i + HNS3_MAX_NON_TSO_BD_NUM - 1U];
+		tot_len += bd_size[i + max_non_tso_bd_num - 1U];
 
 		if (tot_len < skb_shinfo(skb)->gso_size)
 			return true;
···
 				  struct sk_buff *skb)
 {
 	struct hns3_nic_priv *priv = netdev_priv(netdev);
+	u8 max_non_tso_bd_num = priv->max_non_tso_bd_num;
 	unsigned int bd_size[HNS3_MAX_TSO_BD_NUM + 1U];
 	unsigned int bd_num;
 
-	bd_num = hns3_tx_bd_num(skb, bd_size);
-	if (unlikely(bd_num > HNS3_MAX_NON_TSO_BD_NUM)) {
+	bd_num = hns3_tx_bd_num(skb, bd_size, max_non_tso_bd_num);
+	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)) {
-			trace_hns3_over_8bd(skb);
+		    !hns3_skb_need_linearized(skb, bd_size, bd_num,
+					      max_non_tso_bd_num)) {
+			trace_hns3_over_max_bd(skb);
 			goto out;
 		}
 
···
 		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 > HNS3_MAX_NON_TSO_BD_NUM)) {
-			trace_hns3_over_8bd(skb);
+		     bd_num > max_non_tso_bd_num)) {
+			trace_hns3_over_max_bd(skb);
 			return -ENOMEM;
 		}
 
···
 			netdev->hw_features |= NETIF_F_NTUPLE;
 			netdev->features |= NETIF_F_NTUPLE;
 		}
+	}
+
+	if (test_bit(HNAE3_DEV_SUPPORT_UDP_GSO_B, ae_dev->caps)) {
+		netdev->hw_features |= NETIF_F_GSO_UDP_L4;
+		netdev->features |= NETIF_F_GSO_UDP_L4;
+		netdev->vlan_features |= NETIF_F_GSO_UDP_L4;
+		netdev->hw_enc_features |= NETIF_F_GSO_UDP_L4;
 	}
 }
 
···
 static int hns3_client_init(struct hnae3_handle *handle)
 {
 	struct pci_dev *pdev = handle->pdev;
+	struct hnae3_ae_dev *ae_dev = pci_get_drvdata(pdev);
 	u16 alloc_tqps, max_rss_size;
 	struct hns3_nic_priv *priv;
 	struct net_device *netdev;
···
 	priv->netdev = netdev;
 	priv->ae_handle = handle;
 	priv->tx_timeout_count = 0;
+	priv->max_non_tso_bd_num = ae_dev->dev_specs.max_non_tso_bd_num;
 	set_bit(HNS3_NIC_STATE_DOWN, &priv->state);
 
 	handle->msg_enable = netif_msg_init(debug, DEFAULT_MSG_LEVEL);

drivers/net/ethernet/hisilicon/hns3/hns3_enet.h

···
 #define HNS3_RING_TX_RING_EBD_OFFSET_REG	0x00070
 #define HNS3_RING_TX_RING_BD_ERR_REG		0x00074
 #define HNS3_RING_EN_REG			0x00090
+#define HNS3_RING_RX_EN_REG			0x00098
+#define HNS3_RING_TX_EN_REG			0x000D4
 
 #define HNS3_RX_HEAD_SIZE			256
 
···
 #define HNS3_VECTOR_INITED			1
 
 #define HNS3_MAX_BD_SIZE			65535
-#define HNS3_MAX_NON_TSO_BD_NUM			8U
 #define HNS3_MAX_TSO_BD_NUM			63U
 #define HNS3_MAX_TSO_SIZE \
 	(HNS3_MAX_BD_SIZE * HNS3_MAX_TSO_BD_NUM)
 
-#define HNS3_MAX_NON_TSO_SIZE \
-	(HNS3_MAX_BD_SIZE * HNS3_MAX_NON_TSO_BD_NUM)
+#define HNS3_MAX_NON_TSO_SIZE(max_non_tso_bd_num) \
+	(HNS3_MAX_BD_SIZE * (max_non_tso_bd_num))
 
 #define HNS3_VECTOR_GL0_OFFSET			0x100
 #define HNS3_VECTOR_GL1_OFFSET			0x200
···
 	struct hns3_enet_ring *ring;
 	struct hns3_enet_tqp_vector *tqp_vector;
 	u16 vector_num;
+	u8 max_non_tso_bd_num;
 
 	u64 tx_timeout_count;
 

drivers/net/ethernet/hisilicon/hns3/hns3_ethtool.c

···
 	struct hnae3_handle *h = priv->ae_handle;
 	int st_param[HNS3_SELF_TEST_TYPE_NUM][2];
 	bool if_running = netif_running(ndev);
-#if IS_ENABLED(CONFIG_VLAN_8021Q)
-	bool dis_vlan_filter;
-#endif
 	int test_index = 0;
 	u32 i;
 
···
 
 #if IS_ENABLED(CONFIG_VLAN_8021Q)
 	/* Disable the vlan filter for selftest does not support it */
-	dis_vlan_filter = (ndev->features & NETIF_F_HW_VLAN_CTAG_FILTER) &&
-				h->ae_algo->ops->enable_vlan_filter;
-	if (dis_vlan_filter)
+	if (h->ae_algo->ops->enable_vlan_filter)
 		h->ae_algo->ops->enable_vlan_filter(h, false);
 #endif
 
···
 		h->ae_algo->ops->halt_autoneg(h, false);
 
 #if IS_ENABLED(CONFIG_VLAN_8021Q)
-	if (dis_vlan_filter)
+	if (h->ae_algo->ops->enable_vlan_filter)
 		h->ae_algo->ops->enable_vlan_filter(h, true);
 #endif
 

drivers/net/ethernet/hisilicon/hns3/hns3_trace.h

···
 	)
 );
 
-DEFINE_EVENT(hns3_skb_template, hns3_over_8bd,
+DEFINE_EVENT(hns3_skb_template, hns3_over_max_bd,
 	TP_PROTO(struct sk_buff *skb),
 	TP_ARGS(skb));
 

drivers/net/ethernet/hisilicon/hns3/hns3vf/hclgevf_main.c

···
 	return ret;
 }
 
+static int hclgevf_notify_roce_client(struct hclgevf_dev *hdev,
+				      enum hnae3_reset_notify_type type)
+{
+	struct hnae3_client *client = hdev->roce_client;
+	struct hnae3_handle *handle = &hdev->roce;
+	int ret;
+
+	if (!test_bit(HCLGEVF_STATE_ROCE_REGISTERED, &hdev->state) || !client)
+		return 0;
+
+	if (!client->ops->reset_notify)
+		return -EOPNOTSUPP;
+
+	ret = client->ops->reset_notify(handle, type);
+	if (ret)
+		dev_err(&hdev->pdev->dev, "notify roce client failed %d(%d)",
+			type, ret);
+	return ret;
+}
+
 static int hclgevf_reset_wait(struct hclgevf_dev *hdev)
 {
 #define HCLGEVF_RESET_WAIT_US	20000
···
 
 	hdev->rst_stats.rst_cnt++;
 
+	/* perform reset of the stack & ae device for a client */
+	ret = hclgevf_notify_roce_client(hdev, HNAE3_DOWN_CLIENT);
+	if (ret)
+		return ret;
+
 	rtnl_lock();
 	/* bring down the nic to stop any ongoing TX/RX */
 	ret = hclgevf_notify_client(hdev, HNAE3_DOWN_CLIENT);
···
 	int ret;
 
 	hdev->rst_stats.hw_rst_done_cnt++;
+	ret = hclgevf_notify_roce_client(hdev, HNAE3_UNINIT_CLIENT);
+	if (ret)
+		return ret;
 
 	rtnl_lock();
 	/* now, re-initialize the nic client and ae device */
···
 		dev_err(&hdev->pdev->dev, "failed to reset VF stack\n");
 		return ret;
 	}
+
+	ret = hclgevf_notify_roce_client(hdev, HNAE3_INIT_CLIENT);
+	/* ignore RoCE notify error if it fails HCLGEVF_RESET_MAX_FAIL_CNT - 1
+	 * times
+	 */
+	if (ret &&
+	    hdev->rst_stats.rst_fail_cnt < HCLGEVF_RESET_MAX_FAIL_CNT - 1)
+		return ret;
+
+	ret = hclgevf_notify_roce_client(hdev, HNAE3_UP_CLIENT);
+	if (ret)
+		return ret;
 
 	hdev->last_reset_time = jiffies;
 	hdev->rst_stats.rst_done_cnt++;
···
 	if (ret)
 		return ret;
 
+	set_bit(HCLGEVF_STATE_ROCE_REGISTERED, &hdev->state);
 	hnae3_set_client_init_flag(client, ae_dev, 1);
 
 	return 0;
···
 
 	/* un-init roce, if it exists */
 	if (hdev->roce_client) {
+		clear_bit(HCLGEVF_STATE_ROCE_REGISTERED, &hdev->state);
 		hdev->roce_client->ops->uninit_instance(&hdev->roce, 0);
 		hdev->roce_client = NULL;
 		hdev->roce.client = NULL;
···
 	return !!hclgevf_read_dev(&hdev->hw, HCLGEVF_RST_ING);
 }
 
+static bool hclgevf_get_cmdq_stat(struct hnae3_handle *handle)
+{
+	struct hclgevf_dev *hdev = hclgevf_ae_get_hdev(handle);
+
+	return test_bit(HCLGEVF_STATE_CMD_DISABLE, &hdev->state);
+}
+
 static bool hclgevf_ae_dev_resetting(struct hnae3_handle *handle)
 {
 	struct hclgevf_dev *hdev = hclgevf_ae_get_hdev(handle);
···
 	.get_link_mode = hclgevf_get_link_mode,
 	.set_promisc_mode = hclgevf_set_promisc_mode,
 	.request_update_promisc_mode = hclgevf_request_update_promisc_mode,
+	.get_cmdq_stat = hclgevf_get_cmdq_stat,
 };
 
 static struct hnae3_ae_algo ae_algovf = {

drivers/net/ethernet/hisilicon/hns3/hns3vf/hclgevf_main.h

···
 	HCLGEVF_STATE_IRQ_INITED,
 	HCLGEVF_STATE_REMOVING,
 	HCLGEVF_STATE_NIC_REGISTERED,
+	HCLGEVF_STATE_ROCE_REGISTERED,
 	/* task states */
 	HCLGEVF_STATE_RST_SERVICE_SCHED,
 	HCLGEVF_STATE_RST_HANDLING,