Merge branch 'mellanox/mlx5-next' into rdma.git for-next

From the mlx5-next branch at
  git://git.kernel.org/pub/scm/linux/kernel/git/mellanox/linux

Required for dependencies in following patches

* mellanox/mlx5-next:
  net/mlx5: Add support to get lag physical port
  net/mlx5: Change lag mutex lock to spin lock
  bonding: Implement ndo_get_xmit_slave
  bonding: Add array of all slaves
  bonding: Add function to get the xmit slave in active-backup mode
  bonding: Add helper function to get the xmit slave in rr mode
  bonding: Add helper function to get the xmit slave based on hash
  bonding/alb: Add helper functions to get the xmit slave
  bonding: Rename slave_arr to usable_slaves
  bonding: Export skip slave logic to function
  net/core: Introduce netdev_get_xmit_slave

drivers/net/bonding/bond_alb.c

@@ -1334,11 +1334,11 @@ static netdev_tx_t bond_do_alb_xmit(struct sk_buff *skb, struct bonding *bond,
 	return NETDEV_TX_OK;
 }
 
-netdev_tx_t bond_tlb_xmit(struct sk_buff *skb, struct net_device *bond_dev)
+struct slave *bond_xmit_tlb_slave_get(struct bonding *bond,
+				      struct sk_buff *skb)
 {
-	struct bonding *bond = netdev_priv(bond_dev);
-	struct ethhdr *eth_data;
 	struct slave *tx_slave = NULL;
+	struct ethhdr *eth_data;
 	u32 hash_index;
 
 	skb_reset_mac_header(skb);
@@ -1360,7 +1360,7 @@ netdev_tx_t bond_tlb_xmit(struct sk_buff *skb, struct net_device *bond_dev)
 				struct bond_up_slave *slaves;
 				unsigned int count;
 
-				slaves = rcu_dereference(bond->slave_arr);
+				slaves = rcu_dereference(bond->usable_slaves);
 				count = slaves ? READ_ONCE(slaves->count) : 0;
 				if (likely(count))
 					tx_slave = slaves->arr[hash_index %
@@ -1369,20 +1369,29 @@ netdev_tx_t bond_tlb_xmit(struct sk_buff *skb, struct net_device *bond_dev)
 			break;
 		}
 	}
-	return bond_do_alb_xmit(skb, bond, tx_slave);
+	return tx_slave;
 }
 
-netdev_tx_t bond_alb_xmit(struct sk_buff *skb, struct net_device *bond_dev)
+netdev_tx_t bond_tlb_xmit(struct sk_buff *skb, struct net_device *bond_dev)
 {
 	struct bonding *bond = netdev_priv(bond_dev);
-	struct ethhdr *eth_data;
+	struct slave *tx_slave;
+
+	tx_slave = bond_xmit_tlb_slave_get(bond, skb);
+	return bond_do_alb_xmit(skb, bond, tx_slave);
+}
+
+struct slave *bond_xmit_alb_slave_get(struct bonding *bond,
+				      struct sk_buff *skb)
+{
 	struct alb_bond_info *bond_info = &(BOND_ALB_INFO(bond));
-	struct slave *tx_slave = NULL;
 	static const __be32 ip_bcast = htonl(0xffffffff);
-	int hash_size = 0;
+	struct slave *tx_slave = NULL;
+	const u8 *hash_start = NULL;
 	bool do_tx_balance = true;
+	struct ethhdr *eth_data;
 	u32 hash_index = 0;
-	const u8 *hash_start = NULL;
+	int hash_size = 0;
 
 	skb_reset_mac_header(skb);
 	eth_data = eth_hdr(skb);
@@ -1494,14 +1503,22 @@ netdev_tx_t bond_alb_xmit(struct sk_buff *skb, struct net_device *bond_dev)
 			struct bond_up_slave *slaves;
 			unsigned int count;
 
-			slaves = rcu_dereference(bond->slave_arr);
+			slaves = rcu_dereference(bond->usable_slaves);
 			count = slaves ? READ_ONCE(slaves->count) : 0;
 			if (likely(count))
 				tx_slave = slaves->arr[bond_xmit_hash(bond, skb) %
 						       count];
 		}
 	}
+	return tx_slave;
+}
+
+netdev_tx_t bond_alb_xmit(struct sk_buff *skb, struct net_device *bond_dev)
+{
+	struct bonding *bond = netdev_priv(bond_dev);
+	struct slave *tx_slave = NULL;
 
+	tx_slave = bond_xmit_alb_slave_get(bond, skb);
 	return bond_do_alb_xmit(skb, bond, tx_slave);
 }
 

drivers/net/bonding/bond_main.c

@@ -3923,16 +3923,15 @@ static int bond_set_mac_address(struct net_device *bond_dev, void *addr)
 }
 
 /**
- * bond_xmit_slave_id - transmit skb through slave with slave_id
+ * bond_get_slave_by_id - get xmit slave with slave_id
  * @bond: bonding device that is transmitting
- * @skb: buffer to transmit
  * @slave_id: slave id up to slave_cnt-1 through which to transmit
  *
- * This function tries to transmit through slave with slave_id but in case
+ * This function tries to get slave with slave_id but in case
  * 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 struct slave *bond_get_slave_by_id(struct bonding *bond,
+					  int slave_id)
 {
 	struct list_head *iter;
 	struct slave *slave;
@@ -3941,10 +3940,8 @@ static void bond_xmit_slave_id(struct bonding *bond, struct sk_buff *skb, int sl
 	/* Here we start from the slave with slave_id */
 	bond_for_each_slave_rcu(bond, slave, iter) {
 		if (--i < 0) {
-			if (bond_slave_can_tx(slave)) {
-				bond_dev_queue_xmit(bond, skb, slave->dev);
-				return;
-			}
+			if (bond_slave_can_tx(slave))
+				return slave;
 		}
 	}
 
@@ -3953,13 +3950,11 @@ static void bond_xmit_slave_id(struct bonding *bond, struct sk_buff *skb, int sl
 	bond_for_each_slave_rcu(bond, slave, iter) {
 		if (--i < 0)
 			break;
-		if (bond_slave_can_tx(slave)) {
-			bond_dev_queue_xmit(bond, skb, slave->dev);
-			return;
-		}
+		if (bond_slave_can_tx(slave))
+			return slave;
 	}
-	/* no slave that can tx has been found */
-	bond_tx_drop(bond->dev, skb);
+
+	return NULL;
 }
 
 /**
@@ -3995,10 +3990,9 @@ 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 struct slave *bond_xmit_roundrobin_slave_get(struct bonding *bond,
+						    struct sk_buff *skb)
 {
-	struct bonding *bond = netdev_priv(bond_dev);
 	struct slave *slave;
 	int slave_cnt;
 	u32 slave_id;
@@ -4020,24 +4014,40 @@ static netdev_tx_t bond_xmit_roundrobin(struct sk_buff *skb,
 		if (iph->protocol == IPPROTO_IGMP) {
 			slave = rcu_dereference(bond->curr_active_slave);
 			if (slave)
-				bond_dev_queue_xmit(bond, skb, slave->dev);
-			else
-				bond_xmit_slave_id(bond, skb, 0);
-			return NETDEV_TX_OK;
+				return slave;
+			return bond_get_slave_by_id(bond, 0);
 		}
 	}
 
 non_igmp:
 	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);
+		slave_id = bond_rr_gen_slave_id(bond) % slave_cnt;
+		return bond_get_slave_by_id(bond, slave_id);
 	}
+	return NULL;
+}
+
+static netdev_tx_t bond_xmit_roundrobin(struct sk_buff *skb,
+					struct net_device *bond_dev)
+{
+	struct bonding *bond = netdev_priv(bond_dev);
+	struct slave *slave;
+
+	slave = bond_xmit_roundrobin_slave_get(bond, skb);
+	if (slave)
+		bond_dev_queue_xmit(bond, skb, slave->dev);
+	else
+		bond_tx_drop(bond_dev, skb);
 	return NETDEV_TX_OK;
 }
 
+static struct slave *bond_xmit_activebackup_slave_get(struct bonding *bond,
+						      struct sk_buff *skb)
+{
+	return rcu_dereference(bond->curr_active_slave);
+}
+
 /* In active-backup mode, we know that bond->curr_active_slave is always valid if
  * the bond has a usable interface.
  */
@@ -4047,7 +4057,7 @@ static netdev_tx_t bond_xmit_activebackup(struct sk_buff *skb,
 	struct bonding *bond = netdev_priv(bond_dev);
 	struct slave *slave;
 
-	slave = rcu_dereference(bond->curr_active_slave);
+	slave = bond_xmit_activebackup_slave_get(bond, skb);
 	if (slave)
 		bond_dev_queue_xmit(bond, skb, slave->dev);
 	else
@@ -4087,6 +4097,61 @@ static void bond_slave_arr_handler(struct work_struct *work)
 	bond_slave_arr_work_rearm(bond, 1);
 }
 
+static void bond_skip_slave(struct bond_up_slave *slaves,
+			    struct slave *skipslave)
+{
+	int idx;
+
+	/* Rare situation where caller has asked to skip a specific
+	 * slave but allocation failed (most likely!). BTW this is
+	 * only possible when the call is initiated from
+	 * __bond_release_one(). In this situation; overwrite the
+	 * skipslave entry in the array with the last entry from the
+	 * array to avoid a situation where the xmit path may choose
+	 * this to-be-skipped slave to send a packet out.
+	 */
+	for (idx = 0; slaves && idx < slaves->count; idx++) {
+		if (skipslave == slaves->arr[idx]) {
+			slaves->arr[idx] =
+				slaves->arr[slaves->count - 1];
+			slaves->count--;
+			break;
+		}
+	}
+}
+
+static void bond_set_slave_arr(struct bonding *bond,
+			       struct bond_up_slave *usable_slaves,
+			       struct bond_up_slave *all_slaves)
+{
+	struct bond_up_slave *usable, *all;
+
+	usable = rtnl_dereference(bond->usable_slaves);
+	rcu_assign_pointer(bond->usable_slaves, usable_slaves);
+	kfree_rcu(usable, rcu);
+
+	all = rtnl_dereference(bond->all_slaves);
+	rcu_assign_pointer(bond->all_slaves, all_slaves);
+	kfree_rcu(all, rcu);
+}
+
+static void bond_reset_slave_arr(struct bonding *bond)
+{
+	struct bond_up_slave *usable, *all;
+
+	usable = rtnl_dereference(bond->usable_slaves);
+	if (usable) {
+		RCU_INIT_POINTER(bond->usable_slaves, NULL);
+		kfree_rcu(usable, rcu);
+	}
+
+	all = rtnl_dereference(bond->all_slaves);
+	if (all) {
+		RCU_INIT_POINTER(bond->all_slaves, NULL);
+		kfree_rcu(all, rcu);
+	}
+}
+
 /* Build the usable slaves array in control path for modes that use xmit-hash
  * to determine the slave interface -
  * (a) BOND_MODE_8023AD
@@ -4097,9 +4162,9 @@ static void bond_slave_arr_handler(struct work_struct *work)
  */
 int bond_update_slave_arr(struct bonding *bond, struct slave *skipslave)
 {
+	struct bond_up_slave *usable_slaves = NULL, *all_slaves = NULL;
 	struct slave *slave;
 	struct list_head *iter;
-	struct bond_up_slave *new_arr, *old_arr;
 	int agg_id = 0;
 	int ret = 0;
 
@@ -4107,11 +4172,12 @@ int bond_update_slave_arr(struct bonding *bond, struct slave *skipslave)
 	WARN_ON(lockdep_is_held(&bond->mode_lock));
 #endif
 
-	new_arr = kzalloc(offsetof(struct bond_up_slave, arr[bond->slave_cnt]),
-			  GFP_KERNEL);
-	if (!new_arr) {
+	usable_slaves = kzalloc(struct_size(usable_slaves, arr,
+					    bond->slave_cnt), GFP_KERNEL);
+	all_slaves = kzalloc(struct_size(all_slaves, arr,
+					 bond->slave_cnt), GFP_KERNEL);
+	if (!usable_slaves || !all_slaves) {
 		ret = -ENOMEM;
-		pr_err("Failed to build slave-array.\n");
 		goto out;
 	}
 	if (BOND_MODE(bond) == BOND_MODE_8023AD) {
@@ -4119,20 +4185,19 @@ int bond_update_slave_arr(struct bonding *bond, struct slave *skipslave)
 
 		if (bond_3ad_get_active_agg_info(bond, &ad_info)) {
 			pr_debug("bond_3ad_get_active_agg_info failed\n");
-			kfree_rcu(new_arr, rcu);
 			/* No active aggragator means it's not safe to use
 			 * the previous array.
 			 */
-			old_arr = rtnl_dereference(bond->slave_arr);
-			if (old_arr) {
-				RCU_INIT_POINTER(bond->slave_arr, NULL);
-				kfree_rcu(old_arr, rcu);
-			}
+			bond_reset_slave_arr(bond);
 			goto out;
 		}
 		agg_id = ad_info.aggregator_id;
 	}
 	bond_for_each_slave(bond, slave, iter) {
+		if (skipslave == slave)
+			continue;
+
+		all_slaves->arr[all_slaves->count++] = slave;
 		if (BOND_MODE(bond) == BOND_MODE_8023AD) {
 			struct aggregator *agg;
 
@@ -4142,44 +4207,45 @@ int bond_update_slave_arr(struct bonding *bond, struct slave *skipslave)
 		}
 		if (!bond_slave_can_tx(slave))
 			continue;
-		if (skipslave == slave)
-			continue;
 
 		slave_dbg(bond->dev, slave->dev, "Adding slave to tx hash array[%d]\n",
-			  new_arr->count);
+			  usable_slaves->count);
 
-		new_arr->arr[new_arr->count++] = slave;
+		usable_slaves->arr[usable_slaves->count++] = slave;
 	}
 
-	old_arr = rtnl_dereference(bond->slave_arr);
-	rcu_assign_pointer(bond->slave_arr, new_arr);
-	if (old_arr)
-		kfree_rcu(old_arr, rcu);
+	bond_set_slave_arr(bond, usable_slaves, all_slaves);
+	return ret;
 out:
 	if (ret != 0 && skipslave) {
-		int idx;
-
-		/* Rare situation where caller has asked to skip a specific
-		 * slave but allocation failed (most likely!). BTW this is
-		 * only possible when the call is initiated from
-		 * __bond_release_one(). In this situation; overwrite the
-		 * skipslave entry in the array with the last entry from the
-		 * array to avoid a situation where the xmit path may choose
-		 * this to-be-skipped slave to send a packet out.
-		 */
-		old_arr = rtnl_dereference(bond->slave_arr);
-		for (idx = 0; old_arr != NULL && idx < old_arr->count; idx++) {
-			if (skipslave == old_arr->arr[idx]) {
-				old_arr->arr[idx] =
-				    old_arr->arr[old_arr->count-1];
-				old_arr->count--;
-				break;
-			}
-		}
+		bond_skip_slave(rtnl_dereference(bond->all_slaves),
+				skipslave);
+		bond_skip_slave(rtnl_dereference(bond->usable_slaves),
+				skipslave);
 	}
+	kfree_rcu(all_slaves, rcu);
+	kfree_rcu(usable_slaves, rcu);
+
 	return ret;
 }
 
+static struct slave *bond_xmit_3ad_xor_slave_get(struct bonding *bond,
+						 struct sk_buff *skb,
+						 struct bond_up_slave *slaves)
+{
+	struct slave *slave;
+	unsigned int count;
+	u32 hash;
+
+	hash = bond_xmit_hash(bond, skb);
+	count = slaves ? READ_ONCE(slaves->count) : 0;
+	if (unlikely(!count))
+		return NULL;
+
+	slave = slaves->arr[hash % count];
+	return slave;
+}
+
 /* Use this Xmit function for 3AD as well as XOR modes. The current
  * usable slave array is formed in the control path. The xmit function
  * just calculates hash and sends the packet out.
@@ -4188,18 +4254,15 @@ static netdev_tx_t bond_3ad_xor_xmit(struct sk_buff *skb,
 				     struct net_device *dev)
 {
 	struct bonding *bond = netdev_priv(dev);
-	struct slave *slave;
 	struct bond_up_slave *slaves;
-	unsigned int count;
+	struct slave *slave;
 
-	slaves = rcu_dereference(bond->slave_arr);
-	count = slaves ? READ_ONCE(slaves->count) : 0;
-	if (likely(count)) {
-		slave = slaves->arr[bond_xmit_hash(bond, skb) % count];
+	slaves = rcu_dereference(bond->usable_slaves);
+	slave = bond_xmit_3ad_xor_slave_get(bond, skb, slaves);
+	if (likely(slave))
 		bond_dev_queue_xmit(bond, skb, slave->dev);
-	} else {
+	else
 		bond_tx_drop(dev, skb);
-	}
 
 	return NETDEV_TX_OK;
 }
@@ -4284,6 +4347,48 @@ static u16 bond_select_queue(struct net_device *dev, struct sk_buff *skb,
 	return txq;
 }
 
+static struct net_device *bond_xmit_get_slave(struct net_device *master_dev,
+					      struct sk_buff *skb,
+					      bool all_slaves)
+{
+	struct bonding *bond = netdev_priv(master_dev);
+	struct bond_up_slave *slaves;
+	struct slave *slave = NULL;
+
+	switch (BOND_MODE(bond)) {
+	case BOND_MODE_ROUNDROBIN:
+		slave = bond_xmit_roundrobin_slave_get(bond, skb);
+		break;
+	case BOND_MODE_ACTIVEBACKUP:
+		slave = bond_xmit_activebackup_slave_get(bond, skb);
+		break;
+	case BOND_MODE_8023AD:
+	case BOND_MODE_XOR:
+		if (all_slaves)
+			slaves = rcu_dereference(bond->all_slaves);
+		else
+			slaves = rcu_dereference(bond->usable_slaves);
+		slave = bond_xmit_3ad_xor_slave_get(bond, skb, slaves);
+		break;
+	case BOND_MODE_BROADCAST:
+		break;
+	case BOND_MODE_ALB:
+		slave = bond_xmit_alb_slave_get(bond, skb);
+		break;
+	case BOND_MODE_TLB:
+		slave = bond_xmit_tlb_slave_get(bond, skb);
+		break;
+	default:
+		/* Should never happen, mode already checked */
+		WARN_ONCE(true, "Unknown bonding mode");
+		break;
+	}
+
+	if (slave)
+		return slave->dev;
+	return NULL;
+}
+
 static netdev_tx_t __bond_start_xmit(struct sk_buff *skb, struct net_device *dev)
 {
 	struct bonding *bond = netdev_priv(dev);
@@ -4405,6 +4510,7 @@ static const struct net_device_ops bond_netdev_ops = {
 	.ndo_del_slave		= bond_release,
 	.ndo_fix_features	= bond_fix_features,
 	.ndo_features_check	= passthru_features_check,
+	.ndo_get_xmit_slave	= bond_xmit_get_slave,
 };
 
 static const struct device_type bond_type = {
@@ -4472,9 +4578,9 @@ void bond_setup(struct net_device *bond_dev)
 static void bond_uninit(struct net_device *bond_dev)
 {
 	struct bonding *bond = netdev_priv(bond_dev);
+	struct bond_up_slave *usable, *all;
 	struct list_head *iter;
 	struct slave *slave;
-	struct bond_up_slave *arr;
 
 	bond_netpoll_cleanup(bond_dev);
 
@@ -4483,10 +4589,16 @@ static void bond_uninit(struct net_device *bond_dev)
 		__bond_release_one(bond_dev, slave->dev, true, true);
 	netdev_info(bond_dev, "Released all slaves\n");
 
-	arr = rtnl_dereference(bond->slave_arr);
-	if (arr) {
-		RCU_INIT_POINTER(bond->slave_arr, NULL);
-		kfree_rcu(arr, rcu);
+	usable = rtnl_dereference(bond->usable_slaves);
+	if (usable) {
+		RCU_INIT_POINTER(bond->usable_slaves, NULL);
+		kfree_rcu(usable, rcu);
+	}
+
+	all = rtnl_dereference(bond->all_slaves);
+	if (all) {
+		RCU_INIT_POINTER(bond->all_slaves, NULL);
+		kfree_rcu(all, rcu);
 	}
 
 	list_del(&bond->bond_list);

drivers/net/ethernet/mellanox/mlx5/core/lag.c

@@ -42,7 +42,7 @@
  * Beware of lock dependencies (preferably, no locks should be acquired
  * under it).
  */
-static DEFINE_MUTEX(lag_mutex);
+static DEFINE_SPINLOCK(lag_lock);
 
 static int mlx5_cmd_create_lag(struct mlx5_core_dev *dev, u8 remap_port1,
 			       u8 remap_port2)
@@ -274,9 +274,9 @@ static void mlx5_do_bond(struct mlx5_lag *ldev)
 	if (!dev0 || !dev1)
 		return;
 
-	mutex_lock(&lag_mutex);
+	spin_lock(&lag_lock);
 	tracker = ldev->tracker;
-	mutex_unlock(&lag_mutex);
+	spin_unlock(&lag_lock);
 
 	do_bond = tracker.is_bonded && mlx5_lag_check_prereq(ldev);
 
@@ -458,9 +458,9 @@ static int mlx5_lag_netdev_event(struct notifier_block *this,
 		break;
 	}
 
-	mutex_lock(&lag_mutex);
+	spin_lock(&lag_lock);
 	ldev->tracker = tracker;
-	mutex_unlock(&lag_mutex);
+	spin_unlock(&lag_lock);
 
 	if (changed)
 		mlx5_queue_bond_work(ldev, 0);
@@ -502,7 +502,7 @@ static void mlx5_lag_dev_add_pf(struct mlx5_lag *ldev,
 	if (fn >= MLX5_MAX_PORTS)
 		return;
 
-	mutex_lock(&lag_mutex);
+	spin_lock(&lag_lock);
 	ldev->pf[fn].dev    = dev;
 	ldev->pf[fn].netdev = netdev;
 	ldev->tracker.netdev_state[fn].link_up = 0;
@@ -510,7 +510,7 @@ static void mlx5_lag_dev_add_pf(struct mlx5_lag *ldev,
 
 	dev->priv.lag = ldev;
 
-	mutex_unlock(&lag_mutex);
+	spin_unlock(&lag_lock);
 }
 
 static void mlx5_lag_dev_remove_pf(struct mlx5_lag *ldev,
@@ -525,11 +525,11 @@ static void mlx5_lag_dev_remove_pf(struct mlx5_lag *ldev,
 	if (i == MLX5_MAX_PORTS)
 		return;
 
-	mutex_lock(&lag_mutex);
+	spin_lock(&lag_lock);
 	memset(&ldev->pf[i], 0, sizeof(*ldev->pf));
 
 	dev->priv.lag = NULL;
-	mutex_unlock(&lag_mutex);
+	spin_unlock(&lag_lock);
 }
 
 /* Must be called with intf_mutex held */
@@ -607,10 +607,10 @@ bool mlx5_lag_is_roce(struct mlx5_core_dev *dev)
 	struct mlx5_lag *ldev;
 	bool res;
 
-	mutex_lock(&lag_mutex);
+	spin_lock(&lag_lock);
 	ldev = mlx5_lag_dev_get(dev);
 	res  = ldev && __mlx5_lag_is_roce(ldev);
-	mutex_unlock(&lag_mutex);
+	spin_unlock(&lag_lock);
 
 	return res;
 }
@@ -621,10 +621,10 @@ bool mlx5_lag_is_active(struct mlx5_core_dev *dev)
 	struct mlx5_lag *ldev;
 	bool res;
 
-	mutex_lock(&lag_mutex);
+	spin_lock(&lag_lock);
 	ldev = mlx5_lag_dev_get(dev);
 	res  = ldev && __mlx5_lag_is_active(ldev);
-	mutex_unlock(&lag_mutex);
+	spin_unlock(&lag_lock);
 
 	return res;
 }
@@ -635,10 +635,10 @@ bool mlx5_lag_is_sriov(struct mlx5_core_dev *dev)
 	struct mlx5_lag *ldev;
 	bool res;
 
-	mutex_lock(&lag_mutex);
+	spin_lock(&lag_lock);
 	ldev = mlx5_lag_dev_get(dev);
 	res  = ldev && __mlx5_lag_is_sriov(ldev);
-	mutex_unlock(&lag_mutex);
+	spin_unlock(&lag_lock);
 
 	return res;
 }
@@ -664,7 +664,7 @@ struct net_device *mlx5_lag_get_roce_netdev(struct mlx5_core_dev *dev)
 	struct net_device *ndev = NULL;
 	struct mlx5_lag *ldev;
 
-	mutex_lock(&lag_mutex);
+	spin_lock(&lag_lock);
 	ldev = mlx5_lag_dev_get(dev);
 
 	if (!(ldev && __mlx5_lag_is_roce(ldev)))
@@ -681,12 +681,36 @@ struct net_device *mlx5_lag_get_roce_netdev(struct mlx5_core_dev *dev)
 		dev_hold(ndev);
 
 unlock:
-	mutex_unlock(&lag_mutex);
+	spin_unlock(&lag_lock);
 
 	return ndev;
 }
 EXPORT_SYMBOL(mlx5_lag_get_roce_netdev);
 
+u8 mlx5_lag_get_slave_port(struct mlx5_core_dev *dev,
+			   struct net_device *slave)
+{
+	struct mlx5_lag *ldev;
+	u8 port = 0;
+
+	spin_lock(&lag_lock);
+	ldev = mlx5_lag_dev_get(dev);
+	if (!(ldev && __mlx5_lag_is_roce(ldev)))
+		goto unlock;
+
+	if (ldev->pf[MLX5_LAG_P1].netdev == slave)
+		port = MLX5_LAG_P1;
+	else
+		port = MLX5_LAG_P2;
+
+	port = ldev->v2p_map[port];
+
+unlock:
+	spin_unlock(&lag_lock);
+	return port;
+}
+EXPORT_SYMBOL(mlx5_lag_get_slave_port);
+
 bool mlx5_lag_intf_add(struct mlx5_interface *intf, struct mlx5_priv *priv)
 {
 	struct mlx5_core_dev *dev = container_of(priv, struct mlx5_core_dev,
@@ -723,7 +747,7 @@ int mlx5_lag_query_cong_counters(struct mlx5_core_dev *dev,
 
 	memset(values, 0, sizeof(*values) * num_counters);
 
-	mutex_lock(&lag_mutex);
+	spin_lock(&lag_lock);
 	ldev = mlx5_lag_dev_get(dev);
 	if (ldev && __mlx5_lag_is_roce(ldev)) {
 		num_ports = MLX5_MAX_PORTS;
@@ -733,6 +757,7 @@ int mlx5_lag_query_cong_counters(struct mlx5_core_dev *dev,
 		num_ports = 1;
 		mdev[MLX5_LAG_P1] = dev;
 	}
+	spin_unlock(&lag_lock);
 
 	for (i = 0; i < num_ports; ++i) {
 		u32 in[MLX5_ST_SZ_DW(query_cong_statistics_in)] = {};
@@ -742,14 +767,13 @@ int mlx5_lag_query_cong_counters(struct mlx5_core_dev *dev,
 		ret = mlx5_cmd_exec_inout(mdev[i], query_cong_statistics, in,
 					  out);
 		if (ret)
-			goto unlock;
+			goto free;
 
 		for (j = 0; j < num_counters; ++j)
 			values[j] += be64_to_cpup((__be64 *)(out + offsets[j]));
 	}
 
-unlock:
-	mutex_unlock(&lag_mutex);
+free:
 	kvfree(out);
 	return ret;
 }

include/linux/mlx5/driver.h

@@ -1074,6 +1074,8 @@ bool mlx5_lag_is_sriov(struct mlx5_core_dev *dev);
 bool mlx5_lag_is_multipath(struct mlx5_core_dev *dev);
 bool mlx5_lag_is_active(struct mlx5_core_dev *dev);
 struct net_device *mlx5_lag_get_roce_netdev(struct mlx5_core_dev *dev);
+u8 mlx5_lag_get_slave_port(struct mlx5_core_dev *dev,
+			   struct net_device *slave);
 int mlx5_lag_query_cong_counters(struct mlx5_core_dev *dev,
 				 u64 *values,
 				 int num_counters,

include/linux/netdevice.h

@@ -1146,6 +1146,12 @@ struct netdev_net_notifier {
  * int (*ndo_del_slave)(struct net_device *dev, struct net_device *slave_dev);
  *	Called to release previously enslaved netdev.
  *
+ * struct net_device *(*ndo_get_xmit_slave)(struct net_device *dev,
+ *					    struct sk_buff *skb,
+ *					    bool all_slaves);
+ *	Get the xmit slave of master device. If all_slaves is true, function
+ *	assume all the slaves can transmit.
+ *
  *      Feature/offload setting functions.
  * netdev_features_t (*ndo_fix_features)(struct net_device *dev,
  *		netdev_features_t features);
@@ -1389,6 +1395,9 @@ struct net_device_ops {
 						 struct netlink_ext_ack *extack);
 	int			(*ndo_del_slave)(struct net_device *dev,
 						 struct net_device *slave_dev);
+	struct net_device*	(*ndo_get_xmit_slave)(struct net_device *dev,
+						      struct sk_buff *skb,
+						      bool all_slaves);
 	netdev_features_t	(*ndo_fix_features)(struct net_device *dev,
 						    netdev_features_t features);
 	int			(*ndo_set_features)(struct net_device *dev,
@@ -2731,6 +2740,9 @@ void netdev_freemem(struct net_device *dev);
 void synchronize_net(void);
 int init_dummy_netdev(struct net_device *dev);
 
+struct net_device *netdev_get_xmit_slave(struct net_device *dev,
+					 struct sk_buff *skb,
+					 bool all_slaves);
 struct net_device *dev_get_by_index(struct net *net, int ifindex);
 struct net_device *__dev_get_by_index(struct net *net, int ifindex);
 struct net_device *dev_get_by_index_rcu(struct net *net, int ifindex);

include/net/bond_alb.h

@@ -158,6 +158,10 @@ void bond_alb_handle_link_change(struct bonding *bond, struct slave *slave, char
 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);
+struct slave *bond_xmit_alb_slave_get(struct bonding *bond,
+				      struct sk_buff *skb);
+struct slave *bond_xmit_tlb_slave_get(struct bonding *bond,
+				      struct sk_buff *skb);
 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);

include/net/bonding.h

@@ -200,7 +200,8 @@ struct bonding {
 	struct   slave __rcu *curr_active_slave;
 	struct   slave __rcu *current_arp_slave;
 	struct   slave __rcu *primary_slave;
-	struct   bond_up_slave __rcu *slave_arr; /* Array of usable slaves */
+	struct   bond_up_slave __rcu *usable_slaves;
+	struct   bond_up_slave __rcu *all_slaves;
 	bool     force_primary;
 	s32      slave_cnt; /* never change this value outside the attach/detach wrappers */
 	int     (*recv_probe)(const struct sk_buff *, struct bonding *,

net/core/dev.c

@@ -7785,6 +7785,28 @@ void netdev_bonding_info_change(struct net_device *dev,
 }
 EXPORT_SYMBOL(netdev_bonding_info_change);
 
+/**
+ * netdev_get_xmit_slave - Get the xmit slave of master device
+ * @skb: The packet
+ * @all_slaves: assume all the slaves are active
+ *
+ * The reference counters are not incremented so the caller must be
+ * careful with locks. The caller must hold RCU lock.
+ * %NULL is returned if no slave is found.
+ */
+
+struct net_device *netdev_get_xmit_slave(struct net_device *dev,
+					 struct sk_buff *skb,
+					 bool all_slaves)
+{
+	const struct net_device_ops *ops = dev->netdev_ops;
+
+	if (!ops->ndo_get_xmit_slave)
+		return NULL;
+	return ops->ndo_get_xmit_slave(dev, skb, all_slaves);
+}
+EXPORT_SYMBOL(netdev_get_xmit_slave);
+
 static void netdev_adjacent_add_links(struct net_device *dev)
 {
 	struct netdev_adjacent *iter;