Merge branch 'mlx5-next' of git://git.kernel.org/pub/scm/linux/kernel/git/mellanox/linux

This merge includes updates to bonding driver needed for the rdma stack,
to avoid conflicts with the RDMA branch.

Maor Gottlieb Says:

====================
Bonding: Add support to get xmit slave

The following series adds support to get the LAG master xmit slave by
introducing new .ndo - ndo_get_xmit_slave. Every LAG module can
implement it and it first implemented in the bond driver.
This is follow-up to the RFC discussion [1].

The main motivation for doing this is for drivers that offload part
of the LAG functionality. For example, Mellanox Connect-X hardware
implements RoCE LAG which selects the TX affinity when the resources
are created and port is remapped when it goes down.

The first part of this patchset introduces the new .ndo and add the
support to the bonding module.

The second part adds support to get the RoCE LAG xmit slave by building
skb of the RoCE packet based on the AH attributes and call to the new
.ndo.

The third part change the mlx5 driver driver to set the QP's affinity
port according to the slave which found by the .ndo.
====================

Signed-off-by: Saeed Mahameed <saeedm@mellanox.com>

2 files changed, 214 insertions, 77 deletions

diff --git a/drivers/net/bonding/bond_alb.c b/drivers/net/bonding/bond_alb.c
index 3a598d04b156..095ea51d1853 100644
--- a/drivers/net/bonding/bond_alb.c
+++ b/drivers/net/bonding/bond_alb.c
@@ -1331,11 +1331,11 @@ static netdev_tx_t bond_do_alb_xmit(struct sk_buff *skb, struct bonding *bond,
 	return bond_tx_drop(bond->dev, skb);
 }
 
-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);
@@ -1357,7 +1357,7 @@ 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 %
@@ -1366,20 +1366,29 @@ 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);
@@ -1491,14 +1500,22 @@ 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);
 }
 
diff --git a/drivers/net/bonding/bond_main.c b/drivers/net/bonding/bond_main.c
index 4f9e7c421f57..a25c65d4af71 100644
--- a/drivers/net/bonding/bond_main.c
+++ b/drivers/net/bonding/bond_main.c
@@ -3923,16 +3923,15 @@ unwind:
 }
 
 /**
- * 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 netdev_tx_t 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;
@@ -3942,7 +3941,7 @@ static netdev_tx_t bond_xmit_slave_id(struct bonding *bond, struct sk_buff *skb,
 	bond_for_each_slave_rcu(bond, slave, iter) {
 		if (--i < 0) {
 			if (bond_slave_can_tx(slave))
-				return bond_dev_queue_xmit(bond, skb, slave->dev);
+				return slave;
 		}
 	}
 
@@ -3952,10 +3951,10 @@ static netdev_tx_t bond_xmit_slave_id(struct bonding *bond, struct sk_buff *skb,
 		if (--i < 0)
 			break;
 		if (bond_slave_can_tx(slave))
-			return bond_dev_queue_xmit(bond, skb, slave->dev);
+			return slave;
 	}
 	/* no slave that can tx has been found */
-	return bond_tx_drop(bond->dev, skb);
+	return NULL;
 }
 
 /**
@@ -3991,10 +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;
@@ -4016,20 +4014,39 @@ 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)
-				return bond_dev_queue_xmit(bond, skb, slave->dev);
-			return bond_xmit_slave_id(bond, skb, 0);
+				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);
-		return bond_xmit_slave_id(bond, skb, slave_id % slave_cnt);
+		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 (likely(slave))
+		return bond_dev_queue_xmit(bond, skb, slave->dev);
+
 	return bond_tx_drop(bond_dev, skb);
 }
 
+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.
  */
@@ -4039,7 +4056,7 @@ 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)
 		return bond_dev_queue_xmit(bond, skb, slave->dev);
 
@@ -4077,6 +4094,61 @@ err:
 	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
@@ -4087,9 +4159,9 @@ err:
  */
 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;
 
@@ -4097,11 +4169,12 @@ 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) {
@@ -4109,20 +4182,19 @@ 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;
 
@@ -4132,44 +4204,45 @@ 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.
@@ -4178,16 +4251,14 @@ 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))
 		return bond_dev_queue_xmit(bond, skb, slave->dev);
-	}
+
 	return bond_tx_drop(dev, skb);
 }
 
@@ -4269,6 +4340,48 @@ 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);
@@ -4389,6 +4502,7 @@ 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 = {
@@ -4456,9 +4570,9 @@ 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);
 
@@ -4467,10 +4581,16 @@ 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);