[PATCH net-next v5 09/10] bnge: add aRFS flow steering ndo support

[Vikas Gupta]

Introduce the ndo_rx_flow_steer callback (bnge_rx_flow_steer) to
support aRFS.

This callback creates an NTUPLE filter that steers matching packets
to the appropriate RX queue. The implementation dissects flow keys
from the SKB, creates an NTUPLE filter with the associated L2 filter,
inserts it into the NTUPLE hash table, and schedules the sp_task
workqueue via BNGE_RX_NTP_FLTR_SP_EVENT to program the filter
in the firmware.

Add bnge_cfg_ntp_filters() called from the periodic timer via sp_task
to handle deferred filter programming and expiration via
rps_may_expire_flow().

bnge_timer() queues aRFS aging only while NTUPLE is enabled. NTUPLE
can only be turned off with the interface closed, and
bnge_close_core() then deletes the timer and purges dynamic
aRFS filters.

Note that, if the L2 filter is freed before sp_task programs the rule,
the captured firmware id is stale. The NTUPLE alloc either fails (id
gone) or binds to a recycled id for a different filter. The rule is
then dropped, or it stays until it ages out.

Signed-off-by: Vikas Gupta <vikas.gupta@xxxxxxxxxxxx>
Reviewed-by: Dharmender Garg <dharmender.garg@xxxxxxxxxxxx>
---
 .../net/ethernet/broadcom/bnge/bnge_ethtool.c |   5 +-
 .../net/ethernet/broadcom/bnge/bnge_filter.c  |  85 ++++++++++-
 .../net/ethernet/broadcom/bnge/bnge_filter.h  |   5 +-
 .../ethernet/broadcom/bnge/bnge_hwrm_lib.c    |   2 +-
 .../net/ethernet/broadcom/bnge/bnge_netdev.c  | 138 ++++++++++++++++++
 .../net/ethernet/broadcom/bnge/bnge_netdev.h  |   1 +
 6 files changed, 228 insertions(+), 8 deletions(-)

diff --git a/drivers/net/ethernet/broadcom/bnge/bnge_ethtool.c b/drivers/net/ethernet/broadcom/bnge/bnge_ethtool.c
index dfffb3efc333..b4c0db43adf4 100644
--- a/drivers/net/ethernet/broadcom/bnge/bnge_ethtool.c
+++ b/drivers/net/ethernet/broadcom/bnge/bnge_ethtool.c
@@ -1261,7 +1261,7 @@ static int bnge_get_all_fltr_ids_rcu(struct bnge_net *bn,
 
 		head = &tbl[i];
 		hlist_for_each_entry_rcu(fltr, head, hlist) {
-			if (!fltr->flags ||
+			if (!bnge_is_usr_fltr(fltr) ||
 			    test_bit(BNGE_FLTR_FW_DELETED, &fltr->state))
 				continue;
 			if (j == id_cnt)
@@ -1285,7 +1285,8 @@ static struct bnge_filter_base *bnge_get_one_fltr_rcu(struct bnge_net *bn,
 
 		head = &tbl[i];
 		hlist_for_each_entry_rcu(fltr, head, hlist) {
-			if (fltr->flags && fltr->sw_id + offset == id)
+			if (bnge_is_usr_fltr(fltr) &&
+			    fltr->sw_id + offset == id)
 				return fltr;
 		}
 	}
diff --git a/drivers/net/ethernet/broadcom/bnge/bnge_filter.c b/drivers/net/ethernet/broadcom/bnge/bnge_filter.c
index 9b3ed0733623..8309f6d57bc6 100644
--- a/drivers/net/ethernet/broadcom/bnge/bnge_filter.c
+++ b/drivers/net/ethernet/broadcom/bnge/bnge_filter.c
@@ -56,7 +56,7 @@ const struct bnge_flow_masks BNGE_FLOW_IPV4_MASK_ALL = {
 	},
 };
 
-static bool bnge_is_usr_fltr(struct bnge_filter_base *fltr)
+bool bnge_is_usr_fltr(struct bnge_filter_base *fltr)
 {
 	return (fltr->type == BNGE_FLTR_TYPE_L2 &&
 		fltr->flags & BNGE_ACT_RING_DST) ||
@@ -116,7 +116,7 @@ void bnge_del_ntp_filter(struct bnge_net *bn, struct bnge_ntuple_filter *nfltr)
 	hlist_del(&fltr->hlist);
 	bnge_del_usr_fltr_node(bn, fltr);
 	clear_bit(fltr->sw_id, bn->ntp_fltr_bmap);
-	bn->ntp_fltr_count--;
+	WRITE_ONCE(bn->ntp_fltr_count, bn->ntp_fltr_count - 1);
 	kfree(fltr);
 }
 
@@ -127,7 +127,7 @@ void bnge_del_ntp_filter_rcu(struct bnge_net *bn,
 	hlist_del_rcu(&fltr->base.hlist);
 	bnge_del_usr_fltr_node(bn, &fltr->base);
 	clear_bit(fltr->base.sw_id, bn->ntp_fltr_bmap);
-	bn->ntp_fltr_count--;
+	WRITE_ONCE(bn->ntp_fltr_count, bn->ntp_fltr_count - 1);
 	spin_unlock_bh(&bn->ntp_fltr_lock);
 
 	kfree_rcu(fltr, base.rcu);
@@ -538,7 +538,7 @@ int bnge_insert_ntp_filter(struct bnge_net *bn, struct bnge_ntuple_filter *fltr,
 	hlist_add_head_rcu(&fltr->base.hlist, head);
 
 	bnge_insert_usr_fltr(bn, &fltr->base);
-	bn->ntp_fltr_count++;
+	WRITE_ONCE(bn->ntp_fltr_count, bn->ntp_fltr_count + 1);
 
 	spin_unlock_bh(&bn->ntp_fltr_lock);
 
@@ -696,3 +696,80 @@ void bnge_clear_usr_fltrs(struct bnge_net *bn)
 		}
 	}
 }
+
+void bnge_cfg_ntp_filters(struct bnge_net *bn)
+{
+#ifdef CONFIG_RFS_ACCEL
+	struct bnge_ntuple_filter *fltr, *tmp;
+	LIST_HEAD(install_list);
+	LIST_HEAD(update_list);
+	LIST_HEAD(expire_list);
+	u32 flow_id;
+	int i, rc;
+	u16 rxq;
+
+	rcu_read_lock();
+	for (i = 0; i < BNGE_NTP_FLTR_HASH_SIZE; i++) {
+		hlist_for_each_entry_rcu(fltr, &bn->ntp_fltr_hash_tbl[i],
+					 base.hlist) {
+			if (test_bit(BNGE_FLTR_VALID, &fltr->base.state)) {
+				if (fltr->base.flags & BNGE_ACT_NO_AGING)
+					continue;
+				if (test_and_clear_bit(BNGE_FLTR_RXQ_UPDATE,
+						       &fltr->base.state)) {
+					list_add(&fltr->base.list_node,
+						 &update_list);
+					continue;
+				}
+				rxq = READ_ONCE(fltr->base.rxq);
+				flow_id = READ_ONCE(fltr->flow_id);
+				if (rps_may_expire_flow(bn->netdev, rxq,
+							flow_id,
+							fltr->base.sw_id))
+					list_add(&fltr->base.list_node,
+						 &expire_list);
+			} else {
+				/* The install below reads the current rxq; order the
+				 * clear before that read.
+				 */
+				clear_bit(BNGE_FLTR_RXQ_UPDATE,
+					  &fltr->base.state);
+				smp_mb__after_atomic();
+				list_add(&fltr->base.list_node, &install_list);
+			}
+		}
+	}
+	rcu_read_unlock();
+
+	/* Free the old HW rule; reinstall it below on the new queue. */
+	list_for_each_entry_safe(fltr, tmp, &update_list, base.list_node) {
+		list_del_init(&fltr->base.list_node);
+		/* If the free fails the rule stays on the old queue. It is not
+		 * retried, so a firmware that keeps failing is not hit on every
+		 * tick.
+		 */
+		if (bnge_hwrm_cfa_ntuple_filter_free(bn->bd, fltr))
+			continue;
+		clear_bit(BNGE_FLTR_FW_DELETED, &fltr->base.state);
+		list_add(&fltr->base.list_node, &install_list);
+	}
+
+	list_for_each_entry_safe(fltr, tmp, &install_list, base.list_node) {
+		list_del_init(&fltr->base.list_node);
+		rc = bnge_hwrm_cfa_ntuple_filter_alloc(bn->bd, fltr);
+		if (rc)
+			bnge_del_ntp_filter_rcu(bn, fltr);
+		else
+			set_bit(BNGE_FLTR_VALID, &fltr->base.state);
+	}
+
+	list_for_each_entry_safe(fltr, tmp, &expire_list, base.list_node) {
+		list_del_init(&fltr->base.list_node);
+		/* Retargeted by bnge_rx_flow_steer() after the scan */
+		if (test_bit(BNGE_FLTR_RXQ_UPDATE, &fltr->base.state))
+			continue;
+		bnge_hwrm_cfa_ntuple_filter_free(bn->bd, fltr);
+		bnge_del_ntp_filter_rcu(bn, fltr);
+	}
+#endif
+}
diff --git a/drivers/net/ethernet/broadcom/bnge/bnge_filter.h b/drivers/net/ethernet/broadcom/bnge/bnge_filter.h
index 9c5453d5b50a..a7d2983bc25e 100644
--- a/drivers/net/ethernet/broadcom/bnge/bnge_filter.h
+++ b/drivers/net/ethernet/broadcom/bnge/bnge_filter.h
@@ -19,7 +19,8 @@ enum {
 
 enum {
 	BNGE_FLTR_VALID,
-	BNGE_FLTR_FW_DELETED
+	BNGE_FLTR_FW_DELETED,
+	BNGE_FLTR_RXQ_UPDATE
 };
 
 enum {
@@ -97,6 +98,7 @@ struct bnge_ntuple_filter {
 #define BNGE_FLTR_ID_INVALID	cpu_to_le64(0xffffffffffffffffULL)
 
 void bnge_free_ntp_fltrs(struct bnge_net *bn, bool skip_user_filters);
+bool bnge_is_usr_fltr(struct bnge_filter_base *fltr);
 u32 bnge_get_ntp_filter_idx(struct bnge_net *bn, struct flow_keys *fkeys,
 			    const struct sk_buff *skb);
 int bnge_insert_ntp_filter(struct bnge_net *bn, struct bnge_ntuple_filter *fltr,
@@ -123,4 +125,5 @@ void bnge_del_ntp_filter_rcu(struct bnge_net *bn,
 			     struct bnge_ntuple_filter *fltr);
 void bnge_cfg_usr_fltrs(struct bnge_net *bn);
 void bnge_clear_usr_fltrs(struct bnge_net *bn);
+void bnge_cfg_ntp_filters(struct bnge_net *bn);
 #endif /* _BNGE_FILTER_H_ */
diff --git a/drivers/net/ethernet/broadcom/bnge/bnge_hwrm_lib.c b/drivers/net/ethernet/broadcom/bnge/bnge_hwrm_lib.c
index bb6233351484..ce41d94838e6 100644
--- a/drivers/net/ethernet/broadcom/bnge/bnge_hwrm_lib.c
+++ b/drivers/net/ethernet/broadcom/bnge/bnge_hwrm_lib.c
@@ -1007,8 +1007,8 @@ bnge_cfg_rfs_ring_tbl_idx(struct bnge_dev *bd,
 			  struct bnge_ntuple_filter *fltr)
 {
 	struct bnge_net *bn = netdev_priv(bd->netdev);
+	u32 rxq = READ_ONCE(fltr->base.rxq);
 	struct bnge_vnic_info *def_vnic;
-	u32 rxq = fltr->base.rxq;
 	u32 enables;
 
 	if (fltr->base.flags & BNGE_ACT_RSS_CTX) {
diff --git a/drivers/net/ethernet/broadcom/bnge/bnge_netdev.c b/drivers/net/ethernet/broadcom/bnge/bnge_netdev.c
index f72b912d52f6..835619604dc2 100644
--- a/drivers/net/ethernet/broadcom/bnge/bnge_netdev.c
+++ b/drivers/net/ethernet/broadcom/bnge/bnge_netdev.c
@@ -303,6 +303,12 @@ static void bnge_timer(struct timer_list *t)
 	if (BNGE_LINK_IS_UP(bd) && bn->stats_coal_ticks)
 		bnge_queue_sp_work(bn, BNGE_PERIODIC_STATS_SP_EVENT);
 
+#ifdef CONFIG_RFS_ACCEL
+	if ((bn->priv_flags & BNGE_NET_EN_NTUPLE) &&
+	    READ_ONCE(bn->ntp_fltr_count))
+		bnge_queue_sp_work(bn, BNGE_RX_NTP_FLTR_SP_EVENT);
+#endif
+
 	mod_timer(&bn->timer, jiffies + bn->current_interval);
 }
 
@@ -444,6 +450,9 @@ static void bnge_sp_task(struct work_struct *work)
 			bnge_init_ethtool_link_settings(bn);
 	}
 
+	if (test_and_clear_bit(BNGE_RX_NTP_FLTR_SP_EVENT, &bn->sp_event))
+		bnge_cfg_ntp_filters(bn);
+
 	netdev_unlock(bn->netdev);
 }
 
@@ -3201,6 +3210,132 @@ static int bnge_set_features(struct net_device *dev, netdev_features_t features)
 	return 0;
 }
 
+#ifdef CONFIG_RFS_ACCEL
+static __le64 bnge_lookup_l2_filter_from_key(struct bnge_net *bn,
+					     struct bnge_l2_key *key)
+{
+	u32 idx;
+
+	idx = jhash2(&key->filter_key, BNGE_L2_KEY_SIZE, bn->hash_seed) &
+	      BNGE_L2_FLTR_HASH_MASK;
+	return bnge_lookup_l2_filter_rcu(bn, key, idx);
+}
+
+static int bnge_rx_flow_steer(struct net_device *dev, const struct sk_buff *skb,
+			      u16 rxq_index, u32 flow_id)
+{
+	struct ethhdr *eth = (struct ethhdr *)skb_mac_header(skb);
+	struct bnge_ntuple_filter *fltr, *new_fltr;
+	struct bnge_net *bn = netdev_priv(dev);
+	struct flow_keys *fkeys;
+	__le64 filter_id;
+	u32 flags, idx;
+	int rc = 0;
+
+	/* Hold rcu_read_lock() across the L2 filter lookup and check
+	 * BNGE_STATE_OPEN inside it. bnge_close_core() clears the
+	 * flag before bnge_shutdown_nic() frees the L2 filters via
+	 * kfree_rcu(), so if we observe the device open here the
+	 * filter cannot be freed under us for the duration of
+	 * this critical section.
+	 */
+	rcu_read_lock();
+	if (!test_bit(BNGE_STATE_OPEN, &bn->bd->state)) {
+		rcu_read_unlock();
+		return -EINVAL;
+	}
+
+	if (ether_addr_equal(dev->dev_addr, eth->h_dest)) {
+		struct bnge_vnic_info *vnic = &bn->vnic_info[BNGE_VNIC_DEFAULT];
+		struct bnge_l2_filter *l2_filter;
+
+		if (!vnic->uc_filter_count) {
+			rcu_read_unlock();
+			return -EINVAL;
+		}
+		l2_filter = vnic->l2_filters[0];
+		filter_id = l2_filter->base.filter_id;
+	} else {
+		struct bnge_l2_key key;
+
+		ether_addr_copy(key.dst_mac_addr, eth->h_dest);
+		key.vlan = 0;
+
+		filter_id = bnge_lookup_l2_filter_from_key(bn, &key);
+		if (filter_id == BNGE_FLTR_ID_INVALID) {
+			rcu_read_unlock();
+			return -EINVAL;
+		}
+	}
+	rcu_read_unlock();
+
+	new_fltr = kzalloc_obj(*new_fltr, GFP_ATOMIC);
+	if (!new_fltr)
+		return -ENOMEM;
+
+	fkeys = &new_fltr->fkeys;
+	if (!skb_flow_dissect_flow_keys(skb, fkeys, 0)) {
+		rc = -EPROTONOSUPPORT;
+		goto err_free;
+	}
+
+	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)) {
+		rc = -EPROTONOSUPPORT;
+		goto err_free;
+	}
+	new_fltr->fmasks = BNGE_FLOW_IPV4_MASK_ALL;
+	if (fkeys->basic.n_proto == htons(ETH_P_IPV6))
+		new_fltr->fmasks = BNGE_FLOW_IPV6_MASK_ALL;
+
+	flags = fkeys->control.flags;
+	if (flags & FLOW_DIS_IS_FRAGMENT) {
+		rc = -EPROTONOSUPPORT;
+		goto err_free;
+	}
+
+	new_fltr->l2_filter_id = filter_id;
+
+	idx = bnge_get_ntp_filter_idx(bn, fkeys, skb);
+	rcu_read_lock();
+	fltr = bnge_lookup_ntp_filter_from_idx(bn, new_fltr, idx);
+	/* Filter already exists. If the flow moved to another queue,
+	 * retarget it, sp_task reprograms it in hardware.
+	 */
+	if (fltr) {
+		if (!(fltr->base.flags & BNGE_ACT_NO_AGING) &&
+		    READ_ONCE(fltr->base.rxq) != rxq_index) {
+			spin_lock_bh(&bn->ntp_fltr_lock);
+			WRITE_ONCE(fltr->base.rxq, rxq_index);
+			WRITE_ONCE(fltr->flow_id, flow_id);
+			/* Pairs with test_and_clear_bit() in sp_task */
+			smp_mb__before_atomic();
+			set_bit(BNGE_FLTR_RXQ_UPDATE, &fltr->base.state);
+			spin_unlock_bh(&bn->ntp_fltr_lock);
+			bnge_queue_sp_work(bn, BNGE_RX_NTP_FLTR_SP_EVENT);
+		}
+		rc = fltr->base.sw_id;
+		rcu_read_unlock();
+		goto err_free;
+	}
+	rcu_read_unlock();
+
+	new_fltr->flow_id = flow_id;
+	new_fltr->base.rxq = rxq_index;
+	rc = bnge_insert_ntp_filter(bn, new_fltr, idx);
+	if (!rc) {
+		bnge_queue_sp_work(bn, BNGE_RX_NTP_FLTR_SP_EVENT);
+		return new_fltr->base.sw_id;
+	}
+
+err_free:
+	kfree(new_fltr);
+	return rc;
+}
+#endif
+
 static const struct net_device_ops bnge_netdev_ops = {
 	.ndo_open		= bnge_open,
 	.ndo_stop		= bnge_close,
@@ -3210,6 +3345,9 @@ static const struct net_device_ops bnge_netdev_ops = {
 	.ndo_features_check	= bnge_features_check,
 	.ndo_fix_features	= bnge_fix_features,
 	.ndo_set_features	= bnge_set_features,
+#ifdef CONFIG_RFS_ACCEL
+	.ndo_rx_flow_steer	= bnge_rx_flow_steer,
+#endif
 };
 
 static void bnge_init_mac_addr(struct bnge_dev *bd)
diff --git a/drivers/net/ethernet/broadcom/bnge/bnge_netdev.h b/drivers/net/ethernet/broadcom/bnge/bnge_netdev.h
index 2a1ec811de01..74dbca600cbe 100644
--- a/drivers/net/ethernet/broadcom/bnge/bnge_netdev.h
+++ b/drivers/net/ethernet/broadcom/bnge/bnge_netdev.h
@@ -282,6 +282,7 @@ enum bnge_sp_event {
 	BNGE_LINK_CFG_CHANGE_SP_EVENT,
 	BNGE_UPDATE_PHY_SP_EVENT,
 	BNGE_PERIODIC_STATS_SP_EVENT,
+	BNGE_RX_NTP_FLTR_SP_EVENT,
 };
 
 #define BNGE_NTP_FLTR_HASH_SIZE	512
-- 
2.52.0