Merge branch 'bonding-team-offload'

Jiri Pirko says:

====================
bonding/team offload + mlxsw implementation

This patchset introduces needed infrastructure for link aggregation
offload - for both team and bonding. It also implements the offload
in mlxsw driver.

Particulary, this patchset introduces possibility for upper driver
(bond/team/bridge/..) to pass type-specific info down to notifier listeners.
Info is passed along with NETDEV_CHANGEUPPER/NETDEV_PRECHANGEUPPER
notifiers. Listeners (drivers of netdevs being enslaved) can react
accordingly.

Other extension is for run-time use. This patchset introduces
new netdev notifier type - NETDEV_CHANGELOWERSTATE. Along with this
notification, the upper driver (bond/team/bridge/..) can pass some
information about lower device change, particulary link-up and
TX-enabled states. Listeners (drivers of netdevs being enslaved)
can react accordingly.

The last part of the patchset is implementation of LAG offload in mlxsw,
using both previously introduced infrastructre extensions.

Note that bond-speficic (and ugly) NETDEV_BONDING_INFO used by mlx4
can be removed and mlx4 can use the extensions this patchset adds.
I plan to convert it and get rid of NETDEV_BONDING_INFO in
a follow-up patchset.

v2->v3:
- one small fix in patch 1
v1->v2:
- added patch 1 and 2 per Andy's request
- couple of more or less cosmetic changes described in couple other patches
====================

Signed-off-by: David S. Miller <davem@davemloft.net>

3 files changed, 89 insertions, 7 deletions

diff --git a/include/linux/if_team.h b/include/linux/if_team.h
index a6aa970758a2..b84e49c3a738 100644
--- a/include/linux/if_team.h
+++ b/include/linux/if_team.h
@@ -164,6 +164,7 @@ struct team_mode {
 	size_t priv_size;
 	size_t port_priv_size;
 	const struct team_mode_ops *ops;
+	enum netdev_lag_tx_type lag_tx_type;
 };
 
 #define TEAM_PORT_HASHBITS 4
diff --git a/include/linux/netdevice.h b/include/linux/netdevice.h
index fcbc5259c630..fa84b59eb197 100644
--- a/include/linux/netdevice.h
+++ b/include/linux/netdevice.h
@@ -1273,6 +1273,7 @@ struct net_device_ops {
  * @IFF_NO_QUEUE: device can run without qdisc attached
  * @IFF_OPENVSWITCH: device is a Open vSwitch master
  * @IFF_L3MDEV_SLAVE: device is enslaved to an L3 master device
+ * @IFF_TEAM: device is a team device
  */
 enum netdev_priv_flags {
 	IFF_802_1Q_VLAN			= 1<<0,
@@ -1299,6 +1300,7 @@ enum netdev_priv_flags {
 	IFF_NO_QUEUE			= 1<<21,
 	IFF_OPENVSWITCH			= 1<<22,
 	IFF_L3MDEV_SLAVE		= 1<<23,
+	IFF_TEAM			= 1<<24,
 };
 
 #define IFF_802_1Q_VLAN			IFF_802_1Q_VLAN
@@ -1325,6 +1327,7 @@ enum netdev_priv_flags {
 #define IFF_NO_QUEUE			IFF_NO_QUEUE
 #define IFF_OPENVSWITCH			IFF_OPENVSWITCH
 #define IFF_L3MDEV_SLAVE		IFF_L3MDEV_SLAVE
+#define IFF_TEAM			IFF_TEAM
 
 /**
  *	struct net_device - The DEVICE structure.
@@ -2107,6 +2110,24 @@ struct pcpu_sw_netstats {
 #define netdev_alloc_pcpu_stats(type)					\
 	__netdev_alloc_pcpu_stats(type, GFP_KERNEL);
 
+enum netdev_lag_tx_type {
+	NETDEV_LAG_TX_TYPE_UNKNOWN,
+	NETDEV_LAG_TX_TYPE_RANDOM,
+	NETDEV_LAG_TX_TYPE_BROADCAST,
+	NETDEV_LAG_TX_TYPE_ROUNDROBIN,
+	NETDEV_LAG_TX_TYPE_ACTIVEBACKUP,
+	NETDEV_LAG_TX_TYPE_HASH,
+};
+
+struct netdev_lag_upper_info {
+	enum netdev_lag_tx_type tx_type;
+};
+
+struct netdev_lag_lower_state_info {
+	u8 link_up : 1,
+	   tx_enabled : 1;
+};
+
 #include <linux/notifier.h>
 
 /* netdevice notifier chain. Please remember to update the rtnetlink
@@ -2142,6 +2163,7 @@ struct pcpu_sw_netstats {
 #define NETDEV_CHANGEINFODATA	0x0018
 #define NETDEV_BONDING_INFO	0x0019
 #define NETDEV_PRECHANGEUPPER	0x001A
+#define NETDEV_CHANGELOWERSTATE	0x001B
 
 int register_netdevice_notifier(struct notifier_block *nb);
 int unregister_netdevice_notifier(struct notifier_block *nb);
@@ -2160,6 +2182,12 @@ struct netdev_notifier_changeupper_info {
 	struct net_device *upper_dev; /* new upper dev */
 	bool master; /* is upper dev master */
 	bool linking; /* is the nofication for link or unlink */
+	void *upper_info; /* upper dev info */
+};
+
+struct netdev_notifier_changelowerstate_info {
+	struct netdev_notifier_info info; /* must be first */
+	void *lower_state_info; /* is lower dev state */
 };
 
 static inline void netdev_notifier_info_init(struct netdev_notifier_info *info,
@@ -3616,15 +3644,15 @@ struct net_device *netdev_master_upper_dev_get(struct net_device *dev);
 struct net_device *netdev_master_upper_dev_get_rcu(struct net_device *dev);
 int netdev_upper_dev_link(struct net_device *dev, struct net_device *upper_dev);
 int netdev_master_upper_dev_link(struct net_device *dev,
-				 struct net_device *upper_dev);
-int netdev_master_upper_dev_link_private(struct net_device *dev,
-					 struct net_device *upper_dev,
-					 void *private);
+				 struct net_device *upper_dev,
+				 void *upper_priv, void *upper_info);
 void netdev_upper_dev_unlink(struct net_device *dev,
 			     struct net_device *upper_dev);
 void netdev_adjacent_rename_links(struct net_device *dev, char *oldname);
 void *netdev_lower_dev_get_private(struct net_device *dev,
 				   struct net_device *lower_dev);
+void netdev_lower_state_changed(struct net_device *lower_dev,
+				void *lower_state_info);
 
 /* RSS keys are 40 or 52 bytes long */
 #define NETDEV_RSS_KEY_LEN 52
@@ -3889,6 +3917,26 @@ static inline bool netif_is_ovs_master(const struct net_device *dev)
 	return dev->priv_flags & IFF_OPENVSWITCH;
 }
 
+static inline bool netif_is_team_master(struct net_device *dev)
+{
+	return dev->priv_flags & IFF_TEAM;
+}
+
+static inline bool netif_is_team_port(struct net_device *dev)
+{
+	return dev->priv_flags & IFF_TEAM_PORT;
+}
+
+static inline bool netif_is_lag_master(struct net_device *dev)
+{
+	return netif_is_bond_master(dev) || netif_is_team_master(dev);
+}
+
+static inline bool netif_is_lag_port(struct net_device *dev)
+{
+	return netif_is_bond_slave(dev) || netif_is_team_port(dev);
+}
+
 /* This device needs to keep skb dst for qdisc enqueue or ndo_start_xmit() */
 static inline void netif_keep_dst(struct net_device *dev)
 {
diff --git a/include/net/bonding.h b/include/net/bonding.h
index c1740a2794a3..ee6c52053aa3 100644
--- a/include/net/bonding.h
+++ b/include/net/bonding.h
@@ -165,7 +165,8 @@ struct slave {
 	u8     backup:1,   /* indicates backup slave. Value corresponds with
 			      BOND_STATE_ACTIVE and BOND_STATE_BACKUP */
 	       inactive:1, /* indicates inactive slave */
-	       should_notify:1; /* indicateds whether the state changed */
+	       should_notify:1, /* indicates whether the state changed */
+	       should_notify_link:1; /* indicates whether the link changed */
 	u8     duplex;
 	u32    original_mtu;
 	u32    link_failure_count;
@@ -246,6 +247,7 @@ struct bonding {
 	((struct slave *) rtnl_dereference(dev->rx_handler_data))
 
 void bond_queue_slave_event(struct slave *slave);
+void bond_lower_state_changed(struct slave *slave);
 
 struct bond_vlan_tag {
 	__be16		vlan_proto;
@@ -327,6 +329,7 @@ static inline void bond_set_active_slave(struct slave *slave)
 	if (slave->backup) {
 		slave->backup = 0;
 		bond_queue_slave_event(slave);
+		bond_lower_state_changed(slave);
 		rtmsg_ifinfo(RTM_NEWLINK, slave->dev, 0, GFP_ATOMIC);
 	}
 }
@@ -336,6 +339,7 @@ static inline void bond_set_backup_slave(struct slave *slave)
 	if (!slave->backup) {
 		slave->backup = 1;
 		bond_queue_slave_event(slave);
+		bond_lower_state_changed(slave);
 		rtmsg_ifinfo(RTM_NEWLINK, slave->dev, 0, GFP_ATOMIC);
 	}
 }
@@ -348,6 +352,7 @@ static inline void bond_set_slave_state(struct slave *slave,
 
 	slave->backup = slave_state;
 	if (notify) {
+		bond_lower_state_changed(slave);
 		rtmsg_ifinfo(RTM_NEWLINK, slave->dev, 0, GFP_ATOMIC);
 		bond_queue_slave_event(slave);
 		slave->should_notify = 0;
@@ -379,6 +384,7 @@ static inline void bond_slave_state_notify(struct bonding *bond)
 
 	bond_for_each_slave(bond, tmp, iter) {
 		if (tmp->should_notify) {
+			bond_lower_state_changed(tmp);
 			rtmsg_ifinfo(RTM_NEWLINK, tmp->dev, 0, GFP_ATOMIC);
 			tmp->should_notify = 0;
 		}
@@ -504,10 +510,37 @@ static inline bool bond_is_slave_inactive(struct slave *slave)
 	return slave->inactive;
 }
 
-static inline void bond_set_slave_link_state(struct slave *slave, int state)
+static inline void bond_set_slave_link_state(struct slave *slave, int state,
+					     bool notify)
 {
+	if (slave->link == state)
+		return;
+
 	slave->link = state;
-	bond_queue_slave_event(slave);
+	if (notify) {
+		bond_queue_slave_event(slave);
+		bond_lower_state_changed(slave);
+		slave->should_notify_link = 0;
+	} else {
+		if (slave->should_notify_link)
+			slave->should_notify_link = 0;
+		else
+			slave->should_notify_link = 1;
+	}
+}
+
+static inline void bond_slave_link_notify(struct bonding *bond)
+{
+	struct list_head *iter;
+	struct slave *tmp;
+
+	bond_for_each_slave(bond, tmp, iter) {
+		if (tmp->should_notify_link) {
+			bond_queue_slave_event(tmp);
+			bond_lower_state_changed(tmp);
+			tmp->should_notify_link = 0;
+		}
+	}
 }
 
 static inline __be32 bond_confirm_addr(struct net_device *dev, __be32 dst, __be32 local)