diff --git a/drivers/net/bonding/bond_alb.c b/drivers/net/bonding/bond_alb.c
index 1cc2cd894f877c..28dc04c848ce2e 100644
--- a/drivers/net/bonding/bond_alb.c
+++ b/drivers/net/bonding/bond_alb.c
@@ -1299,8 +1299,8 @@ void bond_alb_deinitialize(struct bonding *bond)
 		rlb_deinitialize(bond);
 }
 
-static netdev_tx_t bond_do_alb_xmit(struct sk_buff *skb, struct bonding *bond,
-				    struct slave *tx_slave)
+static bool bond_do_alb_xmit(struct sk_buff *skb, struct bonding *bond,
+			     struct slave *tx_slave)
 {
 	struct alb_bond_info *bond_info = &(BOND_ALB_INFO(bond));
 	struct ethhdr *eth_data = eth_hdr(skb);
@@ -1319,7 +1319,7 @@ static netdev_tx_t bond_do_alb_xmit(struct sk_buff *skb, struct bonding *bond,
 		}
 
 		bond_dev_queue_xmit(bond, skb, tx_slave->dev);
-		goto out;
+		return true;
 	}
 
 	if (tx_slave && bond->params.tlb_dynamic_lb) {
@@ -1330,11 +1330,11 @@ static netdev_tx_t bond_do_alb_xmit(struct sk_buff *skb, struct bonding *bond,
 
 	/* no suitable interface, frame not sent */
 	bond_tx_drop(bond->dev, skb);
-out:
-	return NETDEV_TX_OK;
+
+	return false;
 }
 
-netdev_tx_t bond_tlb_xmit(struct sk_buff *skb, struct net_device *bond_dev)
+bool bond_tlb_xmit(struct sk_buff *skb, struct net_device *bond_dev)
 {
 	struct bonding *bond = netdev_priv(bond_dev);
 	struct ethhdr *eth_data;
@@ -1372,7 +1372,7 @@ netdev_tx_t bond_tlb_xmit(struct sk_buff *skb, struct net_device *bond_dev)
 	return bond_do_alb_xmit(skb, bond, tx_slave);
 }
 
-netdev_tx_t bond_alb_xmit(struct sk_buff *skb, struct net_device *bond_dev)
+bool bond_alb_xmit(struct sk_buff *skb, struct net_device *bond_dev)
 {
 	struct bonding *bond = netdev_priv(bond_dev);
 	struct ethhdr *eth_data;
diff --git a/drivers/net/bonding/bond_main.c b/drivers/net/bonding/bond_main.c
index 1e9d5d35fc7866..3e52fd25f78374 100644
--- a/drivers/net/bonding/bond_main.c
+++ b/drivers/net/bonding/bond_main.c
@@ -251,8 +251,6 @@ static struct flow_dissector flow_keys_bonding __read_mostly;
 
 static int bond_init(struct net_device *bond_dev);
 static void bond_uninit(struct net_device *bond_dev);
-static void bond_get_stats(struct net_device *bond_dev,
-			   struct rtnl_link_stats64 *stats);
 static void bond_slave_arr_handler(struct work_struct *work);
 static bool bond_time_in_interval(struct bonding *bond, unsigned long last_act,
 				  int mod);
@@ -1258,8 +1256,10 @@ static rx_handler_result_t bond_handle_frame(struct sk_buff **pskb)
 	 */
 	if (bond_should_deliver_exact_match(skb, slave, bond)) {
 		if (is_link_local_ether_addr(eth_hdr(skb)->h_dest))
-			return RX_HANDLER_PASS;
-		return RX_HANDLER_EXACT;
+			ret = RX_HANDLER_PASS;
+		else
+			ret = RX_HANDLER_EXACT;
+		goto out;
 	}
 
 	skb->dev = bond->dev;
@@ -1277,6 +1277,23 @@ static rx_handler_result_t bond_handle_frame(struct sk_buff **pskb)
 				  bond->dev->addr_len);
 	}
 
+out:
+	if (ret == RX_HANDLER_ANOTHER) {
+		struct bond_pcpu_stats *pcpu_stats;
+
+		pcpu_stats = this_cpu_ptr(bond->pcpu_stats);
+		u64_stats_update_begin(&pcpu_stats->syncp);
+		pcpu_stats->rx_packets++;
+		pcpu_stats->rx_bytes += skb->len;
+		if (skb->pkt_type == PACKET_MULTICAST)
+			pcpu_stats->rx_multicast++;
+		u64_stats_update_end(&pcpu_stats->syncp);
+	} else if (ret == RX_HANDLER_EXACT) {
+		this_cpu_inc(bond->pcpu_stats->rx_nohandler);
+	} else if (ret == RX_HANDLER_PASS) {
+		this_cpu_inc(bond->pcpu_stats->rx_dropped);
+	}
+
 	return ret;
 }
 
@@ -1608,8 +1625,6 @@ int bond_enslave(struct net_device *bond_dev, struct net_device *slave_dev,
 	}
 
 	slave_dev->priv_flags |= IFF_BONDING;
-	/* initialize slave stats */
-	dev_get_stats(new_slave->dev, &new_slave->slave_stats);
 
 	if (bond_is_lb(bond)) {
 		/* bond_alb_init_slave() must be called before all other stages since
@@ -1944,9 +1959,6 @@ static int __bond_release_one(struct net_device *bond_dev,
 
 	bond_sysfs_slave_del(slave);
 
-	/* recompute stats just before removing the slave */
-	bond_get_stats(bond->dev, &bond->bond_stats);
-
 	bond_upper_dev_unlink(bond, slave);
 	/* unregister rx_handler early so bond_handle_frame wouldn't be called
 	 * for this slave anymore.
@@ -3497,60 +3509,39 @@ static int bond_close(struct net_device *bond_dev)
 	return 0;
 }
 
-/* fold stats, assuming all rtnl_link_stats64 fields are u64, but
- * that some drivers can provide 32bit values only.
- */
-static void bond_fold_stats(struct rtnl_link_stats64 *_res,
-			    const struct rtnl_link_stats64 *_new,
-			    const struct rtnl_link_stats64 *_old)
-{
-	const u64 *new = (const u64 *)_new;
-	const u64 *old = (const u64 *)_old;
-	u64 *res = (u64 *)_res;
-	int i;
-
-	for (i = 0; i < sizeof(*_res) / sizeof(u64); i++) {
-		u64 nv = new[i];
-		u64 ov = old[i];
-		s64 delta = nv - ov;
-
-		/* detects if this particular field is 32bit only */
-		if (((nv | ov) >> 32) == 0)
-			delta = (s64)(s32)((u32)nv - (u32)ov);
-
-		/* filter anomalies, some drivers reset their stats
-		 * at down/up events.
-		 */
-		if (delta > 0)
-			res[i] += delta;
-	}
-}
-
 static void bond_get_stats(struct net_device *bond_dev,
 			   struct rtnl_link_stats64 *stats)
 {
+	u64 rx_packets, rx_bytes, rx_multicast, tx_packets, tx_bytes;
+	u32 rx_dropped = 0, tx_dropped = 0, rx_nohandler = 0;
 	struct bonding *bond = netdev_priv(bond_dev);
-	struct rtnl_link_stats64 temp;
-	struct list_head *iter;
-	struct slave *slave;
-
-	spin_lock(&bond->stats_lock);
-	memcpy(stats, &bond->bond_stats, sizeof(*stats));
-
-	rcu_read_lock();
-	bond_for_each_slave_rcu(bond, slave, iter) {
-		const struct rtnl_link_stats64 *new =
-			dev_get_stats(slave->dev, &temp);
-
-		bond_fold_stats(stats, new, &slave->slave_stats);
-
-		/* save off the slave stats for the next run */
-		memcpy(&slave->slave_stats, new, sizeof(*new));
-	}
-	rcu_read_unlock();
+	struct bond_pcpu_stats *p;
+	unsigned int start;
+	int i;
 
-	memcpy(&bond->bond_stats, stats, sizeof(*stats));
-	spin_unlock(&bond->stats_lock);
+	for_each_possible_cpu(i) {
+		p = per_cpu_ptr(bond->pcpu_stats, i);
+		do {
+			start = u64_stats_fetch_begin_irq(&p->syncp);
+			rx_packets      = p->rx_packets;
+			rx_bytes        = p->rx_bytes;
+			rx_multicast    = p->rx_multicast;
+			tx_packets      = p->tx_packets;
+			tx_bytes        = p->tx_bytes;
+		} while (u64_stats_fetch_retry_irq(&p->syncp, start));
+
+		stats->rx_packets       += rx_packets;
+		stats->rx_bytes         += rx_bytes;
+		stats->multicast        += rx_multicast;
+		stats->tx_packets       += tx_packets;
+		stats->tx_bytes         += tx_bytes;
+		rx_dropped		+= p->rx_dropped;
+		tx_dropped		+= p->tx_dropped;
+		rx_nohandler		+= p->rx_nohandler;
+	}
+	stats->rx_dropped       = rx_dropped;
+	stats->tx_dropped       = tx_dropped;
+	stats->rx_nohandler     = rx_nohandler;
 }
 
 static int bond_do_ioctl(struct net_device *bond_dev, struct ifreq *ifr, int cmd)
@@ -3885,7 +3876,8 @@ static int bond_set_mac_address(struct net_device *bond_dev, void *addr)
  * it fails, it tries to find the first available slave for transmission.
  * The skb is consumed in all cases, thus the function is void.
  */
-static void bond_xmit_slave_id(struct bonding *bond, struct sk_buff *skb, int slave_id)
+static bool bond_xmit_slave_id(struct bonding *bond, struct sk_buff *skb,
+			       int slave_id)
 {
 	struct list_head *iter;
 	struct slave *slave;
@@ -3896,7 +3888,7 @@ static void bond_xmit_slave_id(struct bonding *bond, struct sk_buff *skb, int sl
 		if (--i < 0) {
 			if (bond_slave_can_tx(slave)) {
 				bond_dev_queue_xmit(bond, skb, slave->dev);
-				return;
+				return true;
 			}
 		}
 	}
@@ -3908,11 +3900,12 @@ static void bond_xmit_slave_id(struct bonding *bond, struct sk_buff *skb, int sl
 			break;
 		if (bond_slave_can_tx(slave)) {
 			bond_dev_queue_xmit(bond, skb, slave->dev);
-			return;
+			return true;
 		}
 	}
 	/* no slave that can tx has been found */
 	bond_tx_drop(bond->dev, skb);
+	return false;
 }
 
 /**
@@ -3948,8 +3941,8 @@ static u32 bond_rr_gen_slave_id(struct bonding *bond)
 	return slave_id;
 }
 
-static netdev_tx_t bond_xmit_roundrobin(struct sk_buff *skb,
-					struct net_device *bond_dev)
+static bool bond_xmit_roundrobin(struct sk_buff *skb,
+				 struct net_device *bond_dev)
 {
 	struct bonding *bond = netdev_priv(bond_dev);
 	struct slave *slave;
@@ -3972,11 +3965,12 @@ static netdev_tx_t bond_xmit_roundrobin(struct sk_buff *skb,
 		iph = ip_hdr(skb);
 		if (iph->protocol == IPPROTO_IGMP) {
 			slave = rcu_dereference(bond->curr_active_slave);
-			if (slave)
+			if (slave) {
 				bond_dev_queue_xmit(bond, skb, slave->dev);
-			else
-				bond_xmit_slave_id(bond, skb, 0);
-			return NETDEV_TX_OK;
+				return true;
+			} else {
+				return bond_xmit_slave_id(bond, skb, 0);
+			}
 		}
 	}
 
@@ -3984,29 +3978,28 @@ static netdev_tx_t bond_xmit_roundrobin(struct sk_buff *skb,
 	slave_cnt = READ_ONCE(bond->slave_cnt);
 	if (likely(slave_cnt)) {
 		slave_id = bond_rr_gen_slave_id(bond);
-		bond_xmit_slave_id(bond, skb, slave_id % slave_cnt);
-	} else {
-		bond_tx_drop(bond_dev, skb);
+		return bond_xmit_slave_id(bond, skb, slave_id % slave_cnt);
 	}
-	return NETDEV_TX_OK;
+	bond_tx_drop(bond_dev, skb);
+	return false;
 }
 
 /* In active-backup mode, we know that bond->curr_active_slave is always valid if
  * the bond has a usable interface.
  */
-static netdev_tx_t bond_xmit_activebackup(struct sk_buff *skb,
-					  struct net_device *bond_dev)
+static bool bond_xmit_activebackup(struct sk_buff *skb,
+				   struct net_device *bond_dev)
 {
 	struct bonding *bond = netdev_priv(bond_dev);
 	struct slave *slave;
 
 	slave = rcu_dereference(bond->curr_active_slave);
-	if (slave)
+	if (slave) {
 		bond_dev_queue_xmit(bond, skb, slave->dev);
-	else
-		bond_tx_drop(bond_dev, skb);
-
-	return NETDEV_TX_OK;
+		return true;
+	}
+	bond_tx_drop(bond_dev, skb);
+	return false;
 }
 
 /* Use this to update slave_array when (a) it's not appropriate to update
@@ -4137,8 +4130,8 @@ int bond_update_slave_arr(struct bonding *bond, struct slave *skipslave)
  * usable slave array is formed in the control path. The xmit function
  * just calculates hash and sends the packet out.
  */
-static netdev_tx_t bond_3ad_xor_xmit(struct sk_buff *skb,
-				     struct net_device *dev)
+static bool bond_3ad_xor_xmit(struct sk_buff *skb,
+			      struct net_device *dev)
 {
 	struct bonding *bond = netdev_priv(dev);
 	struct slave *slave;
@@ -4150,20 +4143,20 @@ static netdev_tx_t bond_3ad_xor_xmit(struct sk_buff *skb,
 	if (likely(count)) {
 		slave = slaves->arr[bond_xmit_hash(bond, skb) % count];
 		bond_dev_queue_xmit(bond, skb, slave->dev);
-	} else {
-		bond_tx_drop(dev, skb);
+		return true;
 	}
-
-	return NETDEV_TX_OK;
+	bond_tx_drop(dev, skb);
+	return false;
 }
 
 /* in broadcast mode, we send everything to all usable interfaces. */
-static netdev_tx_t bond_xmit_broadcast(struct sk_buff *skb,
-				       struct net_device *bond_dev)
+static bool bond_xmit_broadcast(struct sk_buff *skb,
+				struct net_device *bond_dev)
 {
 	struct bonding *bond = netdev_priv(bond_dev);
 	struct slave *slave = NULL;
 	struct list_head *iter;
+	int ret = 0;
 
 	bond_for_each_slave_rcu(bond, slave, iter) {
 		if (bond_is_last_slave(bond, slave))
@@ -4177,14 +4170,18 @@ static netdev_tx_t bond_xmit_broadcast(struct sk_buff *skb,
 				continue;
 			}
 			bond_dev_queue_xmit(bond, skb2, slave->dev);
+			ret++;
 		}
 	}
-	if (slave && bond_slave_is_up(slave) && slave->link == BOND_LINK_UP)
+
+	if (slave && bond_slave_is_up(slave) && slave->link == BOND_LINK_UP) {
 		bond_dev_queue_xmit(bond, skb, slave->dev);
-	else
-		bond_tx_drop(bond_dev, skb);
+		ret++;
+	}
 
-	return NETDEV_TX_OK;
+	if (!ret)
+		bond_tx_drop(bond_dev, skb);
+	return !!ret;
 }
 
 /*------------------------- Device initialization ---------------------------*/
@@ -4237,13 +4234,13 @@ static u16 bond_select_queue(struct net_device *dev, struct sk_buff *skb,
 	return txq;
 }
 
-static netdev_tx_t __bond_start_xmit(struct sk_buff *skb, struct net_device *dev)
+static bool __bond_start_xmit(struct sk_buff *skb, struct net_device *dev)
 {
 	struct bonding *bond = netdev_priv(dev);
 
 	if (bond_should_override_tx_queue(bond) &&
 	    !bond_slave_override(bond, skb))
-		return NETDEV_TX_OK;
+		return true;
 
 	switch (BOND_MODE(bond)) {
 	case BOND_MODE_ROUNDROBIN:
@@ -4264,14 +4261,14 @@ static netdev_tx_t __bond_start_xmit(struct sk_buff *skb, struct net_device *dev
 		netdev_err(dev, "Unknown bonding mode %d\n", BOND_MODE(bond));
 		WARN_ON_ONCE(1);
 		bond_tx_drop(dev, skb);
-		return NETDEV_TX_OK;
+		return false;
 	}
 }
 
 static netdev_tx_t bond_start_xmit(struct sk_buff *skb, struct net_device *dev)
 {
 	struct bonding *bond = netdev_priv(dev);
-	netdev_tx_t ret = NETDEV_TX_OK;
+	int len = skb->len;
 
 	/* If we risk deadlock from transmitting this in the
 	 * netpoll path, tell netpoll to queue the frame for later tx
@@ -4280,13 +4277,24 @@ static netdev_tx_t bond_start_xmit(struct sk_buff *skb, struct net_device *dev)
 		return NETDEV_TX_BUSY;
 
 	rcu_read_lock();
-	if (bond_has_slaves(bond))
-		ret = __bond_start_xmit(skb, dev);
-	else
+	if (bond_has_slaves(bond)) {
+		if (__bond_start_xmit(skb, dev)) {
+			struct bond_pcpu_stats *pcpu_stats;
+
+			pcpu_stats = this_cpu_ptr(bond->pcpu_stats);
+			u64_stats_update_begin(&pcpu_stats->syncp);
+			pcpu_stats->tx_packets++;
+			pcpu_stats->tx_bytes += len;
+			u64_stats_update_end(&pcpu_stats->syncp);
+		} else {
+			this_cpu_inc(bond->pcpu_stats->tx_dropped);
+		}
+	} else {
 		bond_tx_drop(dev, skb);
+	}
 	rcu_read_unlock();
 
-	return ret;
+	return NETDEV_TX_OK;
 }
 
 static int bond_ethtool_get_link_ksettings(struct net_device *bond_dev,
@@ -4368,8 +4376,10 @@ static const struct device_type bond_type = {
 static void bond_destructor(struct net_device *bond_dev)
 {
 	struct bonding *bond = netdev_priv(bond_dev);
+
 	if (bond->wq)
 		destroy_workqueue(bond->wq);
+	free_percpu(bond->pcpu_stats);
 }
 
 void bond_setup(struct net_device *bond_dev)
@@ -4445,7 +4455,6 @@ static void bond_uninit(struct net_device *bond_dev)
 
 	list_del(&bond->bond_list);
 
-	lockdep_unregister_key(&bond->stats_lock_key);
 	bond_debug_unregister(bond);
 }
 
@@ -4845,13 +4854,13 @@ static int bond_init(struct net_device *bond_dev)
 
 	netdev_dbg(bond_dev, "Begin bond_init\n");
 
-	bond->wq = alloc_ordered_workqueue(bond_dev->name, WQ_MEM_RECLAIM);
-	if (!bond->wq)
+	bond->pcpu_stats = netdev_alloc_pcpu_stats(struct bond_pcpu_stats);
+	if (!bond->pcpu_stats)
 		return -ENOMEM;
 
-	spin_lock_init(&bond->stats_lock);
-	lockdep_register_key(&bond->stats_lock_key);
-	lockdep_set_class(&bond->stats_lock, &bond->stats_lock_key);
+	bond->wq = alloc_ordered_workqueue(bond_dev->name, WQ_MEM_RECLAIM);
+	if (!bond->wq)
+		goto err_alloc_workqueue;
 
 	list_add_tail(&bond->bond_list, &bn->dev_list);
 
@@ -4865,6 +4874,9 @@ static int bond_init(struct net_device *bond_dev)
 		eth_hw_addr_random(bond_dev);
 
 	return 0;
+err_alloc_workqueue:
+	free_percpu(bond->pcpu_stats);
+	return -ENOMEM;
 }
 
 unsigned int bond_get_num_tx_queues(void)
diff --git a/include/net/bond_alb.h b/include/net/bond_alb.h
index b3504fcd773dcf..89c0545458cd1a 100644
--- a/include/net/bond_alb.h
+++ b/include/net/bond_alb.h
@@ -156,8 +156,8 @@ int bond_alb_init_slave(struct bonding *bond, struct slave *slave);
 void bond_alb_deinit_slave(struct bonding *bond, struct slave *slave);
 void bond_alb_handle_link_change(struct bonding *bond, struct slave *slave, char link);
 void bond_alb_handle_active_change(struct bonding *bond, struct slave *new_slave);
-int bond_alb_xmit(struct sk_buff *skb, struct net_device *bond_dev);
-int bond_tlb_xmit(struct sk_buff *skb, struct net_device *bond_dev);
+bool bond_alb_xmit(struct sk_buff *skb, struct net_device *bond_dev);
+bool bond_tlb_xmit(struct sk_buff *skb, struct net_device *bond_dev);
 void bond_alb_monitor(struct work_struct *);
 int bond_alb_set_mac_address(struct net_device *bond_dev, void *addr);
 void bond_alb_clear_vlan(struct bonding *bond, unsigned short vlan_id);
diff --git a/include/net/bonding.h b/include/net/bonding.h
index 3d56b026bb9e77..53106e59ff9cb6 100644
--- a/include/net/bonding.h
+++ b/include/net/bonding.h
@@ -111,6 +111,18 @@ static inline int is_netpoll_tx_blocked(struct net_device *dev)
 #define is_netpoll_tx_blocked(dev) (0)
 #endif
 
+struct bond_pcpu_stats {
+	u64                     rx_packets;
+	u64                     rx_bytes;
+	u64                     rx_multicast;
+	u64                     tx_packets;
+	u64                     tx_bytes;
+	struct u64_stats_sync   syncp;
+	u32                     rx_dropped;
+	u32                     tx_dropped;
+	u32                     rx_nohandler;
+};
+
 struct bond_params {
 	int mode;
 	int xmit_policy;
@@ -177,7 +189,6 @@ struct slave {
 #endif
 	struct delayed_work notify_work;
 	struct kobject kobj;
-	struct rtnl_link_stats64 slave_stats;
 };
 
 struct bond_up_slave {
@@ -213,7 +224,6 @@ struct bonding {
 	 * ALB mode (6) - to sync the use and modifications of its hash table
 	 */
 	spinlock_t mode_lock;
-	spinlock_t stats_lock;
 	u8	 send_peer_notif;
 	u8       igmp_retrans;
 #ifdef CONFIG_PROC_FS
@@ -236,8 +246,7 @@ struct bonding {
 	/* debugging support via debugfs */
 	struct	 dentry *debug_dir;
 #endif /* CONFIG_DEBUG_FS */
-	struct rtnl_link_stats64 bond_stats;
-	struct lock_class_key stats_lock_key;
+	struct   bond_pcpu_stats __percpu *pcpu_stats;
 };
 
 #define bond_slave_get_rcu(dev) \