net/mlx4_en: Port aggregation configuration

Capture NETDEV events generated by the bonding driver and based on that
make decisions of how to configure port aggregation in the mlx4 core driver.

This includes setting the V2P port table and re-creating the interested
interfaces in bonded/non-bonded mode.

Signed-off-by: Moni Shoua <monis@mellanox.com>
Signed-off-by: Or Gerlitz <ogerlitz@mellanox.com>
Signed-off-by: David S. Miller <davem@davemloft.net>

3 files changed, 189 insertions, 0 deletions

diff --git a/drivers/net/ethernet/mellanox/mlx4/en_main.c b/drivers/net/ethernet/mellanox/mlx4/en_main.c
index c643d2bbb7b9..58d5a07d0ff4 100644
--- a/drivers/net/ethernet/mellanox/mlx4/en_main.c
+++ b/drivers/net/ethernet/mellanox/mlx4/en_main.c
@@ -214,6 +214,8 @@ static void mlx4_en_remove(struct mlx4_dev *dev, void *endev_ptr)
         iounmap(mdev->uar_map);
         mlx4_uar_free(dev, &mdev->priv_uar);
         mlx4_pd_free(dev, mdev->priv_pdn);
+        if (mdev->nb.notifier_call)
+                unregister_netdevice_notifier(&mdev->nb);
         kfree(mdev);
 }
 
@@ -298,6 +300,12 @@ static void *mlx4_en_add(struct mlx4_dev *dev)
                 if (mlx4_en_init_netdev(mdev, i, &mdev->profile.prof[i]))
                         mdev->pndev[i] = NULL;
         }
+        /* register notifier */
+        mdev->nb.notifier_call = mlx4_en_netdev_event;
+        if (register_netdevice_notifier(&mdev->nb)) {
+                mdev->nb.notifier_call = NULL;
+                mlx4_err(mdev, "Failed to create notifier\n");
+        }
 
         return mdev;
 
diff --git a/drivers/net/ethernet/mellanox/mlx4/en_netdev.c b/drivers/net/ethernet/mellanox/mlx4/en_netdev.c
index e075ff1f4e80..028937b2a199 100644
--- a/drivers/net/ethernet/mellanox/mlx4/en_netdev.c
+++ b/drivers/net/ethernet/mellanox/mlx4/en_netdev.c
@@ -2062,6 +2062,7 @@ void mlx4_en_destroy_netdev(struct net_device *dev)
         /* Detach the netdev so tasks would not attempt to access it */
         mutex_lock(&mdev->state_lock);
         mdev->pndev[priv->port] = NULL;
+        mdev->upper[priv->port] = NULL;
         mutex_unlock(&mdev->state_lock);
 
         mlx4_en_free_resources(priv);
@@ -2441,6 +2442,180 @@ static const struct net_device_ops mlx4_netdev_ops_master = {
 #endif
 };
 
+struct mlx4_en_bond {
+        struct work_struct work;
+        struct mlx4_en_priv *priv;
+        int is_bonded;
+        struct mlx4_port_map port_map;
+};
+
+static void mlx4_en_bond_work(struct work_struct *work)
+{
+        struct mlx4_en_bond *bond = container_of(work,
+                                                     struct mlx4_en_bond,
+                                                     work);
+        int err = 0;
+        struct mlx4_dev *dev = bond->priv->mdev->dev;
+
+        if (bond->is_bonded) {
+                if (!mlx4_is_bonded(dev)) {
+                        err = mlx4_bond(dev);
+                        if (err)
+                                en_err(bond->priv, "Fail to bond device\n");
+                }
+                if (!err) {
+                        err = mlx4_port_map_set(dev, &bond->port_map);
+                        if (err)
+                                en_err(bond->priv, "Fail to set port map [%d][%d]: %d\n",
+                                       bond->port_map.port1,
+                                       bond->port_map.port2,
+                                       err);
+                }
+        } else if (mlx4_is_bonded(dev)) {
+                err = mlx4_unbond(dev);
+                if (err)
+                        en_err(bond->priv, "Fail to unbond device\n");
+        }
+        dev_put(bond->priv->dev);
+        kfree(bond);
+}
+
+static int mlx4_en_queue_bond_work(struct mlx4_en_priv *priv, int is_bonded,
+                                   u8 v2p_p1, u8 v2p_p2)
+{
+        struct mlx4_en_bond *bond = NULL;
+
+        bond = kzalloc(sizeof(*bond), GFP_ATOMIC);
+        if (!bond)
+                return -ENOMEM;
+
+        INIT_WORK(&bond->work, mlx4_en_bond_work);
+        bond->priv = priv;
+        bond->is_bonded = is_bonded;
+        bond->port_map.port1 = v2p_p1;
+        bond->port_map.port2 = v2p_p2;
+        dev_hold(priv->dev);
+        queue_work(priv->mdev->workqueue, &bond->work);
+        return 0;
+}
+
+int mlx4_en_netdev_event(struct notifier_block *this,
+                         unsigned long event, void *ptr)
+{
+        struct net_device *ndev = netdev_notifier_info_to_dev(ptr);
+        u8 port = 0;
+        struct mlx4_en_dev *mdev;
+        struct mlx4_dev *dev;
+        int i, num_eth_ports = 0;
+        bool do_bond = true;
+        struct mlx4_en_priv *priv;
+        u8 v2p_port1 = 0;
+        u8 v2p_port2 = 0;
+
+        if (!net_eq(dev_net(ndev), &init_net))
+                return NOTIFY_DONE;
+
+        mdev = container_of(this, struct mlx4_en_dev, nb);
+        dev = mdev->dev;
+
+        /* Go into this mode only when two network devices set on two ports
+         * of the same mlx4 device are slaves of the same bonding master
+         */
+        mlx4_foreach_port(i, dev, MLX4_PORT_TYPE_ETH) {
+                ++num_eth_ports;
+                if (!port && (mdev->pndev[i] == ndev))
+                        port = i;
+                mdev->upper[i] = mdev->pndev[i] ?
+                        netdev_master_upper_dev_get(mdev->pndev[i]) : NULL;
+                /* condition not met: network device is a slave */
+                if (!mdev->upper[i])
+                        do_bond = false;
+                if (num_eth_ports < 2)
+                        continue;
+                /* condition not met: same master */
+                if (mdev->upper[i] != mdev->upper[i-1])
+                        do_bond = false;
+        }
+        /* condition not met: 2 salves */
+        do_bond = (num_eth_ports ==  2) ? do_bond : false;
+
+        /* handle only events that come with enough info */
+        if ((do_bond && (event != NETDEV_BONDING_INFO)) || !port)
+                return NOTIFY_DONE;
+
+        priv = netdev_priv(ndev);
+        if (do_bond) {
+                struct netdev_notifier_bonding_info *notifier_info = ptr;
+                struct netdev_bonding_info *bonding_info =
+                        &notifier_info->bonding_info;
+
+                /* required mode 1, 2 or 4 */
+                if ((bonding_info->master.bond_mode != BOND_MODE_ACTIVEBACKUP) &&
+                    (bonding_info->master.bond_mode != BOND_MODE_XOR) &&
+                    (bonding_info->master.bond_mode != BOND_MODE_8023AD))
+                        do_bond = false;
+
+                /* require exactly 2 slaves */
+                if (bonding_info->master.num_slaves != 2)
+                        do_bond = false;
+
+                /* calc v2p */
+                if (do_bond) {
+                        if (bonding_info->master.bond_mode ==
+                            BOND_MODE_ACTIVEBACKUP) {
+                                /* in active-backup mode virtual ports are
+                                 * mapped to the physical port of the active
+                                 * slave */
+                                if (bonding_info->slave.state ==
+                                    BOND_STATE_BACKUP) {
+                                        if (port == 1) {
+                                                v2p_port1 = 2;
+                                                v2p_port2 = 2;
+                                        } else {
+                                                v2p_port1 = 1;
+                                                v2p_port2 = 1;
+                                        }
+                                } else { /* BOND_STATE_ACTIVE */
+                                        if (port == 1) {
+                                                v2p_port1 = 1;
+                                                v2p_port2 = 1;
+                                        } else {
+                                                v2p_port1 = 2;
+                                                v2p_port2 = 2;
+                                        }
+                                }
+                        } else { /* Active-Active */
+                                /* in active-active mode a virtual port is
+                                 * mapped to the native physical port if and only
+                                 * if the physical port is up */
+                                __s8 link = bonding_info->slave.link;
+
+                                if (port == 1)
+                                        v2p_port2 = 2;
+                                else
+                                        v2p_port1 = 1;
+                                if ((link == BOND_LINK_UP) ||
+                                    (link == BOND_LINK_FAIL)) {
+                                        if (port == 1)
+                                                v2p_port1 = 1;
+                                        else
+                                                v2p_port2 = 2;
+                                } else { /* BOND_LINK_DOWN || BOND_LINK_BACK */
+                                        if (port == 1)
+                                                v2p_port1 = 2;
+                                        else
+                                                v2p_port2 = 1;
+                                }
+                        }
+                }
+        }
+
+        mlx4_en_queue_bond_work(priv, do_bond,
+                                v2p_port1, v2p_port2);
+
+        return NOTIFY_DONE;
+}
+
 int mlx4_en_init_netdev(struct mlx4_en_dev *mdev, int port,
                         struct mlx4_en_port_profile *prof)
 {
@@ -2623,6 +2798,7 @@ int mlx4_en_init_netdev(struct mlx4_en_dev *mdev, int port,
         }
 
         mdev->pndev[port] = dev;
+        mdev->upper[port] = NULL;
 
         netif_carrier_off(dev);
         mlx4_en_set_default_moderation(priv);
diff --git a/drivers/net/ethernet/mellanox/mlx4/mlx4_en.h b/drivers/net/ethernet/mellanox/mlx4/mlx4_en.h
index 944a112dff37..2a8268e6be15 100644
--- a/drivers/net/ethernet/mellanox/mlx4/mlx4_en.h
+++ b/drivers/net/ethernet/mellanox/mlx4/mlx4_en.h
@@ -390,6 +390,7 @@ struct mlx4_en_dev {
         struct pci_dev          *pdev;
         struct mutex            state_lock;
         struct net_device       *pndev[MLX4_MAX_PORTS + 1];
+        struct net_device       *upper[MLX4_MAX_PORTS + 1];
         u32                     port_cnt;
         bool                    device_up;
         struct mlx4_en_profile  profile;
@@ -410,6 +411,7 @@ struct mlx4_en_dev {
         unsigned long           overflow_period;
         struct ptp_clock        *ptp_clock;
         struct ptp_clock_info   ptp_clock_info;
+        struct notifier_block   nb;
 };
 
 
@@ -845,6 +847,9 @@ int mlx4_en_reset_config(struct net_device *dev,
                          struct hwtstamp_config ts_config,
                          netdev_features_t new_features);
 
+int mlx4_en_netdev_event(struct notifier_block *this,
+                         unsigned long event, void *ptr);
+
 /*
  * Functions for time stamping
  */