Merge branch 'net-hns3-add-aRFS-feature-and-fix-FEC-bugs-for-HNS3-driver'

Huazhong Tan says:

====================
net: hns3: add aRFS feature and fix FEC bugs for HNS3 driver

This patchset adds some new features support and fixes some bugs:
[Patch 1/4 - 3/4] adds support for aRFS
[Patch 4/4] fix FEC configuration issue
====================
Signed-off-by: David S. Miller <davem@davemloft.net>

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

@@ -343,6 +343,8 @@ struct hnae3_ae_dev {
  *   Enable/disable hardware strip vlan tag of packets received
  * set_gro_en
  *   Enable/disable HW GRO
+ * add_arfs_entry
+ *   Check the 5-tuples of flow, and create flow director rule
  */
 struct hnae3_ae_ops {
 	int (*init_ae_dev)(struct hnae3_ae_dev *ae_dev);
@@ -492,6 +494,8 @@ struct hnae3_ae_ops {
 				struct ethtool_rxnfc *cmd, u32 *rule_locs);
 	int (*restore_fd_rules)(struct hnae3_handle *handle);
 	void (*enable_fd)(struct hnae3_handle *handle, bool enable);
+	int (*add_arfs_entry)(struct hnae3_handle *handle, u16 queue_id,
+			      u16 flow_id, struct flow_keys *fkeys);
 	int (*dbg_run_cmd)(struct hnae3_handle *handle, char *cmd_buf);
 	pci_ers_result_t (*handle_hw_ras_error)(struct hnae3_ae_dev *ae_dev);
 	bool (*get_hw_reset_stat)(struct hnae3_handle *handle);

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

@@ -4,6 +4,9 @@
 #include <linux/dma-mapping.h>
 #include <linux/etherdevice.h>
 #include <linux/interrupt.h>
+#ifdef CONFIG_RFS_ACCEL
+#include <linux/cpu_rmap.h>
+#endif
 #include <linux/if_vlan.h>
 #include <linux/ip.h>
 #include <linux/ipv6.h>
@@ -79,23 +82,6 @@ static irqreturn_t hns3_irq_handle(int irq, void *vector)
 	return IRQ_HANDLED;
 }
 
-/* This callback function is used to set affinity changes to the irq affinity
- * masks when the irq_set_affinity_notifier function is used.
- */
-static void hns3_nic_irq_affinity_notify(struct irq_affinity_notify *notify,
-					 const cpumask_t *mask)
-{
-	struct hns3_enet_tqp_vector *tqp_vectors =
-		container_of(notify, struct hns3_enet_tqp_vector,
-			     affinity_notify);
-
-	tqp_vectors->affinity_mask = *mask;
-}
-
-static void hns3_nic_irq_affinity_release(struct kref *ref)
-{
-}
-
 static void hns3_nic_uninit_irq(struct hns3_nic_priv *priv)
 {
 	struct hns3_enet_tqp_vector *tqp_vectors;
@@ -107,8 +93,7 @@ static void hns3_nic_uninit_irq(struct hns3_nic_priv *priv)
 		if (tqp_vectors->irq_init_flag != HNS3_VECTOR_INITED)
 			continue;
 
-		/* clear the affinity notifier and affinity mask */
-		irq_set_affinity_notifier(tqp_vectors->vector_irq, NULL);
+		/* clear the affinity mask */
 		irq_set_affinity_hint(tqp_vectors->vector_irq, NULL);
 
 		/* release the irq resource */
@@ -161,12 +146,6 @@ static int hns3_nic_init_irq(struct hns3_nic_priv *priv)
 			return ret;
 		}
 
-		tqp_vectors->affinity_notify.notify =
-					hns3_nic_irq_affinity_notify;
-		tqp_vectors->affinity_notify.release =
-					hns3_nic_irq_affinity_release;
-		irq_set_affinity_notifier(tqp_vectors->vector_irq,
-					  &tqp_vectors->affinity_notify);
 		irq_set_affinity_hint(tqp_vectors->vector_irq,
 				      &tqp_vectors->affinity_mask);
 
@@ -340,6 +319,40 @@ static void hns3_tqp_disable(struct hnae3_queue *tqp)
 	hns3_write_dev(tqp, HNS3_RING_EN_REG, rcb_reg);
 }
 
+static void hns3_free_rx_cpu_rmap(struct net_device *netdev)
+{
+#ifdef CONFIG_RFS_ACCEL
+	free_irq_cpu_rmap(netdev->rx_cpu_rmap);
+	netdev->rx_cpu_rmap = NULL;
+#endif
+}
+
+static int hns3_set_rx_cpu_rmap(struct net_device *netdev)
+{
+#ifdef CONFIG_RFS_ACCEL
+	struct hns3_nic_priv *priv = netdev_priv(netdev);
+	struct hns3_enet_tqp_vector *tqp_vector;
+	int i, ret;
+
+	if (!netdev->rx_cpu_rmap) {
+		netdev->rx_cpu_rmap = alloc_irq_cpu_rmap(priv->vector_num);
+		if (!netdev->rx_cpu_rmap)
+			return -ENOMEM;
+	}
+
+	for (i = 0; i < priv->vector_num; i++) {
+		tqp_vector = &priv->tqp_vector[i];
+		ret = irq_cpu_rmap_add(netdev->rx_cpu_rmap,
+				       tqp_vector->vector_irq);
+		if (ret) {
+			hns3_free_rx_cpu_rmap(netdev);
+			return ret;
+		}
+	}
+#endif
+	return 0;
+}
+
 static int hns3_nic_net_up(struct net_device *netdev)
 {
 	struct hns3_nic_priv *priv = netdev_priv(netdev);
@@ -351,11 +364,16 @@ static int hns3_nic_net_up(struct net_device *netdev)
 	if (ret)
 		return ret;
 
+	/* the device can work without cpu rmap, only aRFS needs it */
+	ret = hns3_set_rx_cpu_rmap(netdev);
+	if (ret)
+		netdev_warn(netdev, "set rx cpu rmap fail, ret=%d!\n", ret);
+
 	/* get irq resource for all vectors */
 	ret = hns3_nic_init_irq(priv);
 	if (ret) {
 		netdev_err(netdev, "hns init irq failed! ret=%d\n", ret);
-		return ret;
+		goto free_rmap;
 	}
 
 	clear_bit(HNS3_NIC_STATE_DOWN, &priv->state);
@@ -384,7 +402,8 @@ static int hns3_nic_net_up(struct net_device *netdev)
 		hns3_vector_disable(&priv->tqp_vector[j]);
 
 	hns3_nic_uninit_irq(priv);
-
+free_rmap:
+	hns3_free_rx_cpu_rmap(netdev);
 	return ret;
 }
 
@@ -467,6 +486,8 @@ static void hns3_nic_net_down(struct net_device *netdev)
 	if (ops->stop)
 		ops->stop(priv->ae_handle);
 
+	hns3_free_rx_cpu_rmap(netdev);
+
 	/* free irq resources */
 	hns3_nic_uninit_irq(priv);
 
@@ -1722,6 +1743,32 @@ static void hns3_nic_net_timeout(struct net_device *ndev)
 		h->ae_algo->ops->reset_event(h->pdev, h);
 }
 
+#ifdef CONFIG_RFS_ACCEL
+static int hns3_rx_flow_steer(struct net_device *dev, const struct sk_buff *skb,
+			      u16 rxq_index, u32 flow_id)
+{
+	struct hnae3_handle *h = hns3_get_handle(dev);
+	struct flow_keys fkeys;
+
+	if (!h->ae_algo->ops->add_arfs_entry)
+		return -EOPNOTSUPP;
+
+	if (skb->encapsulation)
+		return -EPROTONOSUPPORT;
+
+	if (!skb_flow_dissect_flow_keys(skb, &fkeys, 0))
+		return -EPROTONOSUPPORT;
+
+	if ((fkeys.basic.n_proto != htons(ETH_P_IP) &&
+	     fkeys.basic.n_proto != htons(ETH_P_IPV6)) ||
+	    (fkeys.basic.ip_proto != IPPROTO_TCP &&
+	     fkeys.basic.ip_proto != IPPROTO_UDP))
+		return -EPROTONOSUPPORT;
+
+	return h->ae_algo->ops->add_arfs_entry(h, rxq_index, flow_id, &fkeys);
+}
+#endif
+
 static const struct net_device_ops hns3_nic_netdev_ops = {
 	.ndo_open		= hns3_nic_net_open,
 	.ndo_stop		= hns3_nic_net_stop,
@@ -1737,6 +1784,10 @@ static const struct net_device_ops hns3_nic_netdev_ops = {
 	.ndo_vlan_rx_add_vid	= hns3_vlan_rx_add_vid,
 	.ndo_vlan_rx_kill_vid	= hns3_vlan_rx_kill_vid,
 	.ndo_set_vf_vlan	= hns3_ndo_set_vf_vlan,
+#ifdef CONFIG_RFS_ACCEL
+	.ndo_rx_flow_steer	= hns3_rx_flow_steer,
+#endif
+
 };
 
 bool hns3_is_phys_func(struct pci_dev *pdev)
@@ -2828,6 +2879,7 @@ static int hns3_handle_rx_bd(struct hns3_enet_ring *ring,
 		return ret;
 	}
 
+	skb_record_rx_queue(skb, ring->tqp->tqp_index);
 	*out_skb = skb;
 
 	return 0;
@@ -3331,8 +3383,6 @@ static void hns3_nic_uninit_vector_data(struct hns3_nic_priv *priv)
 		hns3_free_vector_ring_chain(tqp_vector, &vector_ring_chain);
 
 		if (tqp_vector->irq_init_flag == HNS3_VECTOR_INITED) {
-			irq_set_affinity_notifier(tqp_vector->vector_irq,
-						  NULL);
 			irq_set_affinity_hint(tqp_vector->vector_irq, NULL);
 			free_irq(tqp_vector->vector_irq, tqp_vector);
 			tqp_vector->irq_init_flag = HNS3_VECTOR_NOT_INITED;

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

@@ -578,6 +578,16 @@ static const struct key_info tuple_key_info[] = {
 #define MAX_KEY_BYTES	(MAX_KEY_DWORDS * 4)
 #define MAX_META_DATA_LENGTH	32
 
+/* assigned by firmware, the real filter number for each pf may be less */
+#define MAX_FD_FILTER_NUM	4096
+#define HCLGE_FD_ARFS_EXPIRE_TIMER_INTERVAL	5
+
+enum HCLGE_FD_ACTIVE_RULE_TYPE {
+	HCLGE_FD_RULE_NONE,
+	HCLGE_FD_ARFS_ACTIVE,
+	HCLGE_FD_EP_ACTIVE,
+};
+
 enum HCLGE_FD_PACKET_TYPE {
 	NIC_PACKET,
 	ROCE_PACKET,
@@ -630,6 +640,8 @@ struct hclge_fd_rule {
 	u16 vf_id;
 	u16 queue_id;
 	u16 location;
+	u16 flow_id;	/* only used for arfs */
+	enum HCLGE_FD_ACTIVE_RULE_TYPE rule_type;
 };
 
 struct hclge_fd_ad_data {
@@ -809,7 +821,11 @@ struct hclge_dev {
 
 	struct hclge_fd_cfg fd_cfg;
 	struct hlist_head fd_rule_list;
+	spinlock_t fd_rule_lock; /* protect fd_rule_list and fd_bmap */
 	u16 hclge_fd_rule_num;
+	u16 fd_arfs_expire_timer;
+	unsigned long fd_bmap[BITS_TO_LONGS(MAX_FD_FILTER_NUM)];
+	enum HCLGE_FD_ACTIVE_RULE_TYPE fd_active_type;
 	u8 fd_en;
 
 	u16 wanted_umv_size;