Merge branch 'hns3-next'

Huazhong Tan says:

====================
code optimizations & bugfixes for HNS3 driver

This patch-set includes code optimizations and bugfixes for the HNS3
ethernet controller driver.

[patch 1/11 - 3/11] fixes some bugs about the IO path

[patch 4/11 - 6/11] includes some optimization and bugfixes
about mailbox handling

[patch 7/11 - 11/11] adds misc code optimizations and bugfixes.

Change log:
V2->V3: fixes comments from Neil Horman, removes [patch 8/12]
V1->V2: adds modification on [patch 8/12]
====================
Signed-off-by: David S. Miller <davem@davemloft.net>

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

@@ -84,12 +84,15 @@ struct hclgevf_mbx_resp_status {
 struct hclge_mbx_vf_to_pf_cmd {
 	u8 rsv;
 	u8 mbx_src_vfid; /* Auto filled by IMP */
-	u8 rsv1[2];
+	u8 mbx_need_resp;
+	u8 rsv1[1];
 	u8 msg_len;
 	u8 rsv2[3];
 	u8 msg[HCLGE_MBX_MAX_MSG_SIZE];
 };
 
+#define HCLGE_MBX_NEED_RESP_BIT		BIT(0)
+
 struct hclge_mbx_pf_to_vf_cmd {
 	u8 dest_vfid;
 	u8 rsv[3];
@@ -111,7 +114,7 @@ struct hclgevf_mbx_arq_ring {
 	struct hclgevf_dev *hdev;
 	u32 head;
 	u32 tail;
-	u32 count;
+	atomic_t count;
 	u16 msg_q[HCLGE_MBX_MAX_ARQ_MSG_NUM][HCLGE_MBX_MAX_ARQ_MSG_SIZE];
 };
 

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

@@ -2214,14 +2214,22 @@ static void hns3_reuse_buffer(struct hns3_enet_ring *ring, int i)
 static void hns3_nic_reclaim_one_desc(struct hns3_enet_ring *ring, int *bytes,
 				      int *pkts)
 {
-	struct hns3_desc_cb *desc_cb = &ring->desc_cb[ring->next_to_clean];
+	int ntc = ring->next_to_clean;
+	struct hns3_desc_cb *desc_cb;
 
+	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, ring->next_to_clean);
+	hns3_free_buffer_detach(ring, ntc);
 
-	ring_ptr_move_fw(ring, next_to_clean);
+	if (++ntc == ring->desc_num)
+		ntc = 0;
+
+	/* 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);
 }
 
 static int is_valid_clean_head(struct hns3_enet_ring *ring, int h)
@@ -2689,36 +2697,37 @@ static int hns3_set_gro_and_checksum(struct hns3_enet_ring *ring,
 }
 
 static void hns3_set_rx_skb_rss_type(struct hns3_enet_ring *ring,
-				     struct sk_buff *skb)
+				     struct sk_buff *skb, u32 rss_hash)
 {
 	struct hnae3_handle *handle = ring->tqp->handle;
 	enum pkt_hash_types rss_type;
-	struct hns3_desc *desc;
-	int last_bd;
 
-	/* When driver handle the rss type, ring->next_to_clean indicates the
-	 * first descriptor of next packet, need -1 here.
-	 */
-	last_bd = (ring->next_to_clean - 1 + ring->desc_num) % ring->desc_num;
-	desc = &ring->desc[last_bd];
-
-	if (le32_to_cpu(desc->rx.rss_hash))
+	if (rss_hash)
 		rss_type = handle->kinfo.rss_type;
 	else
 		rss_type = PKT_HASH_TYPE_NONE;
 
-	skb_set_hash(skb, le32_to_cpu(desc->rx.rss_hash), rss_type);
+	skb_set_hash(skb, rss_hash, rss_type);
 }
 
-static int hns3_handle_bdinfo(struct hns3_enet_ring *ring, struct sk_buff *skb,
-			      struct hns3_desc *desc)
+static int hns3_handle_bdinfo(struct hns3_enet_ring *ring, struct sk_buff *skb)
 {
 	struct net_device *netdev = ring->tqp->handle->kinfo.netdev;
-	u32 bd_base_info = le32_to_cpu(desc->rx.bd_base_info);
-	u32 l234info = le32_to_cpu(desc->rx.l234_info);
 	enum hns3_pkt_l2t_type l2_frame_type;
+	u32 bd_base_info, l234info;
+	struct hns3_desc *desc;
 	unsigned int len;
-	int ret;
+	int pre_ntc, ret;
+
+	/* bdinfo handled below is only valid on the last BD of the
+	 * current packet, and ring->next_to_clean indicates the first
+	 * descriptor of next packet, so need - 1 below.
+	 */
+	pre_ntc = ring->next_to_clean ? (ring->next_to_clean - 1) :
+					(ring->desc_num - 1);
+	desc = &ring->desc[pre_ntc];
+	bd_base_info = le32_to_cpu(desc->rx.bd_base_info);
+	l234info = le32_to_cpu(desc->rx.l234_info);
 
 	/* Based on hw strategy, the tag offloaded will be stored at
 	 * ot_vlan_tag in two layer tag case, and stored at vlan_tag
@@ -2779,6 +2788,8 @@ static int hns3_handle_bdinfo(struct hns3_enet_ring *ring, struct sk_buff *skb,
 	u64_stats_update_end(&ring->syncp);
 
 	ring->tqp_vector->rx_group.total_bytes += len;
+
+	hns3_set_rx_skb_rss_type(ring, skb, le32_to_cpu(desc->rx.rss_hash));
 	return 0;
 }
 
@@ -2848,14 +2859,13 @@ static int hns3_handle_rx_bd(struct hns3_enet_ring *ring,
 		       ALIGN(ring->pull_len, sizeof(long)));
 	}
 
-	ret = hns3_handle_bdinfo(ring, skb, desc);
+	ret = hns3_handle_bdinfo(ring, skb);
 	if (unlikely(ret)) {
 		dev_kfree_skb_any(skb);
 		return ret;
 	}
 
 	*out_skb = skb;
-	hns3_set_rx_skb_rss_type(ring, skb);
 
 	return 0;
 }
@@ -2866,7 +2876,7 @@ int hns3_clean_rx_ring(
 {
 #define RCB_NOF_ALLOC_RX_BUFF_ONCE 16
 	int recv_pkts, recv_bds, clean_count, err;
-	int unused_count = hns3_desc_unused(ring) - ring->pending_buf;
+	int unused_count = hns3_desc_unused(ring);
 	struct sk_buff *skb = ring->skb;
 	int num;
 
@@ -2875,6 +2885,7 @@ int hns3_clean_rx_ring(
 
 	recv_pkts = 0, recv_bds = 0, clean_count = 0;
 	num -= unused_count;
+	unused_count -= ring->pending_buf;
 
 	while (recv_pkts < budget && recv_bds < num) {
 		/* Reuse or realloc buffers */
@@ -3476,6 +3487,7 @@ static int hns3_get_ring_config(struct hns3_nic_priv *priv)
 	}
 
 	devm_kfree(&pdev->dev, priv->ring_data);
+	priv->ring_data = NULL;
 	return ret;
 }
 
@@ -3484,12 +3496,16 @@ static void hns3_put_ring_config(struct hns3_nic_priv *priv)
 	struct hnae3_handle *h = priv->ae_handle;
 	int i;
 
+	if (!priv->ring_data)
+		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;
 }
 
 static int hns3_alloc_ring_memory(struct hns3_enet_ring *ring)
@@ -3909,8 +3925,6 @@ static void hns3_client_uninit(struct hnae3_handle *handle, bool reset)
 
 	hns3_dbg_uninit(handle);
 
-	priv->ring_data = NULL;
-
 out_netdev_free:
 	free_netdev(netdev);
 }
@@ -4257,12 +4271,10 @@ static int hns3_reset_notify_init_enet(struct hnae3_handle *handle)
 	hns3_uninit_all_ring(priv);
 err_uninit_vector:
 	hns3_nic_uninit_vector_data(priv);
-	priv->ring_data = NULL;
 err_dealloc_vector:
 	hns3_nic_dealloc_vector_data(priv);
 err_put_ring:
 	hns3_put_ring_config(priv);
-	priv->ring_data = NULL;
 
 	return ret;
 }
@@ -4324,7 +4336,6 @@ static int hns3_reset_notify_uninit_enet(struct hnae3_handle *handle)
 		netdev_err(netdev, "uninit ring error\n");
 
 	hns3_put_ring_config(priv);
-	priv->ring_data = NULL;
 
 	return ret;
 }

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

@@ -581,8 +581,11 @@ union l4_hdr_info {
 
 static inline int ring_space(struct hns3_enet_ring *ring)
 {
-	int begin = ring->next_to_clean;
-	int end = ring->next_to_use;
+	/* This smp_load_acquire() pairs with smp_store_release() in
+	 * hns3_nic_reclaim_one_desc called by hns3_clean_tx_ring.
+	 */
+	int begin = smp_load_acquire(&ring->next_to_clean);
+	int end = READ_ONCE(ring->next_to_use);
 
 	return ((end >= begin) ? (ring->desc_num - end + begin) :
 			(begin - end)) - 1;

drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_err.c

@@ -1653,8 +1653,6 @@ int hclge_handle_hw_msix_error(struct hclge_dev *hdev,
 	if (ret) {
 		dev_err(dev, "fail(%d) to query msix int status bd num\n",
 			ret);
-		/* reset everything for now */
-		set_bit(HNAE3_GLOBAL_RESET, reset_requests);
 		return ret;
 	}
 
@@ -1675,8 +1673,6 @@ int hclge_handle_hw_msix_error(struct hclge_dev *hdev,
 	if (ret) {
 		dev_err(dev, "query all mpf msix int cmd failed (%d)\n",
 			ret);
-		/* reset everything for now */
-		set_bit(HNAE3_GLOBAL_RESET, reset_requests);
 		goto msi_error;
 	}
 
@@ -1710,8 +1706,6 @@ int hclge_handle_hw_msix_error(struct hclge_dev *hdev,
 	if (ret) {
 		dev_err(dev, "clear all mpf msix int cmd failed (%d)\n",
 			ret);
-		/* reset everything for now */
-		set_bit(HNAE3_GLOBAL_RESET, reset_requests);
 		goto msi_error;
 	}
 
@@ -1725,8 +1719,6 @@ int hclge_handle_hw_msix_error(struct hclge_dev *hdev,
 	if (ret) {
 		dev_err(dev, "query all pf msix int cmd failed (%d)\n",
 			ret);
-		/* reset everything for now */
-		set_bit(HNAE3_GLOBAL_RESET, reset_requests);
 		goto msi_error;
 	}
 
@@ -1767,8 +1759,6 @@ int hclge_handle_hw_msix_error(struct hclge_dev *hdev,
 	if (ret) {
 		dev_err(dev, "clear all pf msix int cmd failed (%d)\n",
 			ret);
-		/* reset everything for now */
-		set_bit(HNAE3_GLOBAL_RESET, reset_requests);
 	}
 
 	/* query and clear mac tnl interruptions */

drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_main.c

@@ -5337,8 +5337,8 @@ static int hclge_set_serdes_loopback(struct hclge_dev *hdev, bool en,
 #define HCLGE_SERDES_RETRY_MS	10
 #define HCLGE_SERDES_RETRY_NUM	100
 
-#define HCLGE_MAC_LINK_STATUS_MS   20
-#define HCLGE_MAC_LINK_STATUS_NUM  10
+#define HCLGE_MAC_LINK_STATUS_MS   10
+#define HCLGE_MAC_LINK_STATUS_NUM  100
 #define HCLGE_MAC_LINK_STATUS_DOWN 0
 #define HCLGE_MAC_LINK_STATUS_UP   1
 

drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_mbx.c

@@ -212,8 +212,7 @@ static int hclge_set_vf_promisc_mode(struct hclge_vport *vport,
 }
 
 static int hclge_set_vf_uc_mac_addr(struct hclge_vport *vport,
-				    struct hclge_mbx_vf_to_pf_cmd *mbx_req,
-				    bool gen_resp)
+				    struct hclge_mbx_vf_to_pf_cmd *mbx_req)
 {
 	const u8 *mac_addr = (const u8 *)(&mbx_req->msg[2]);
 	struct hclge_dev *hdev = vport->back;
@@ -249,7 +248,7 @@ static int hclge_set_vf_uc_mac_addr(struct hclge_vport *vport,
 		return -EIO;
 	}
 
-	if (gen_resp)
+	if (mbx_req->mbx_need_resp & HCLGE_MBX_NEED_RESP_BIT)
 		hclge_gen_resp_to_vf(vport, mbx_req, status, NULL, 0);
 
 	return 0;
@@ -597,7 +596,7 @@ void hclge_mbx_handler(struct hclge_dev *hdev)
 					ret);
 			break;
 		case HCLGE_MBX_SET_UNICAST:
-			ret = hclge_set_vf_uc_mac_addr(vport, req, true);
+			ret = hclge_set_vf_uc_mac_addr(vport, req);
 			if (ret)
 				dev_err(&hdev->pdev->dev,
 					"PF fail(%d) to set VF UC MAC Addr\n",

drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_tm.c

@@ -1331,8 +1331,11 @@ int hclge_pause_setup_hw(struct hclge_dev *hdev, bool init)
 	ret = hclge_pfc_setup_hw(hdev);
 	if (init && ret == -EOPNOTSUPP)
 		dev_warn(&hdev->pdev->dev, "GE MAC does not support pfc\n");
-	else
+	else if (ret) {
+		dev_err(&hdev->pdev->dev, "config pfc failed! ret = %d\n",
+			ret);
 		return ret;
+	}
 
 	return hclge_tm_bp_setup(hdev);
 }

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

@@ -340,7 +340,7 @@ int hclgevf_cmd_init(struct hclgevf_dev *hdev)
 	hdev->arq.hdev = hdev;
 	hdev->arq.head = 0;
 	hdev->arq.tail = 0;
-	hdev->arq.count = 0;
+	atomic_set(&hdev->arq.count, 0);
 	hdev->hw.cmq.csq.next_to_clean = 0;
 	hdev->hw.cmq.csq.next_to_use = 0;
 	hdev->hw.cmq.crq.next_to_clean = 0;

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

@@ -1758,7 +1758,7 @@ static void hclgevf_keep_alive_task(struct work_struct *work)
 
 	hdev = container_of(work, struct hclgevf_dev, keep_alive_task);
 
-	if (test_bit(HCLGEVF_STATE_RST_HANDLING, &hdev->state))
+	if (test_bit(HCLGEVF_STATE_CMD_DISABLE, &hdev->state))
 		return;
 
 	ret = hclgevf_send_mbx_msg(hdev, HCLGE_MBX_KEEP_ALIVE, 0, NULL,
@@ -2050,8 +2050,10 @@ static void hclgevf_ae_stop(struct hnae3_handle *handle)
 
 	set_bit(HCLGEVF_STATE_DOWN, &hdev->state);
 
-	for (i = 0; i < handle->kinfo.num_tqps; i++)
-		hclgevf_reset_tqp(handle, i);
+	if (hdev->reset_type != HNAE3_VF_RESET)
+		for (i = 0; i < handle->kinfo.num_tqps; i++)
+			if (hclgevf_reset_tqp(handle, i))
+				break;
 
 	/* reset tqp stats */
 	hclgevf_reset_tqp_stats(handle);

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

@@ -98,6 +98,8 @@ int hclgevf_send_mbx_msg(struct hclgevf_dev *hdev, u16 code, u16 subcode,
 	}
 
 	hclgevf_cmd_setup_basic_desc(&desc, HCLGEVF_OPC_MBX_VF_TO_PF, false);
+	req->mbx_need_resp |= need_resp ? HCLGE_MBX_NEED_RESP_BIT :
+					  ~HCLGE_MBX_NEED_RESP_BIT;
 	req->msg[0] = code;
 	req->msg[1] = subcode;
 	memcpy(&req->msg[2], msg_data, msg_len);
@@ -212,7 +214,8 @@ void hclgevf_mbx_handler(struct hclgevf_dev *hdev)
 			/* we will drop the async msg if we find ARQ as full
 			 * and continue with next message
 			 */
-			if (hdev->arq.count >= HCLGE_MBX_MAX_ARQ_MSG_NUM) {
+			if (atomic_read(&hdev->arq.count) >=
+			    HCLGE_MBX_MAX_ARQ_MSG_NUM) {
 				dev_warn(&hdev->pdev->dev,
 					 "Async Q full, dropping msg(%d)\n",
 					 req->msg[1]);
@@ -224,7 +227,7 @@ void hclgevf_mbx_handler(struct hclgevf_dev *hdev)
 			memcpy(&msg_q[0], req->msg,
 			       HCLGE_MBX_MAX_ARQ_MSG_SIZE * sizeof(u16));
 			hclge_mbx_tail_ptr_move_arq(hdev->arq);
-			hdev->arq.count++;
+			atomic_inc(&hdev->arq.count);
 
 			hclgevf_mbx_task_schedule(hdev);
 
@@ -317,7 +320,7 @@ void hclgevf_mbx_async_handler(struct hclgevf_dev *hdev)
 		}
 
 		hclge_mbx_head_ptr_move_arq(hdev->arq);
-		hdev->arq.count--;
+		atomic_dec(&hdev->arq.count);
 		msg_q = hdev->arq.msg_q[hdev->arq.head];
 	}
 }