[for-next 00/15][PULL request] Mellanox mlx5 core driver updates 2016-08-24

@@ -96,6 +96,10 @@
 #define OFFLOADS_NUM_PRIOS 1
 #define OFFLOADS_MIN_LEVEL (ANCHOR_MIN_LEVEL + 1)
 
+#define LAG_PRIO_NUM_LEVELS 1
+#define LAG_NUM_PRIOS 1
+#define LAG_MIN_LEVEL (OFFLOADS_MIN_LEVEL + 1)
+
 struct node_caps {
 	size_t	arr_sz;
 	long	*caps;

@@ -111,12 +115,16 @@ static struct init_tree_node {
 	int num_levels;
 } root_fs = {
 	.type = FS_TYPE_NAMESPACE,
-	.ar_size = 6,
+	.ar_size = 7,
 	.children = (struct init_tree_node[]) {
 		ADD_PRIO(0, BY_PASS_MIN_LEVEL, 0,
 			 FS_CHAINING_CAPS,
 			 ADD_NS(ADD_MULTIPLE_PRIO(MLX5_BY_PASS_NUM_PRIOS,
 						  BY_PASS_PRIO_NUM_LEVELS))),
+		ADD_PRIO(0, LAG_MIN_LEVEL, 0,
+			 FS_CHAINING_CAPS,
+			 ADD_NS(ADD_MULTIPLE_PRIO(LAG_NUM_PRIOS,
+						  LAG_PRIO_NUM_LEVELS))),
 		ADD_PRIO(0, OFFLOADS_MIN_LEVEL, 0, {},
 			 ADD_NS(ADD_MULTIPLE_PRIO(OFFLOADS_NUM_PRIOS, OFFLOADS_MAX_FT))),
 		ADD_PRIO(0, ETHTOOL_MIN_LEVEL, 0,

@@ -1396,6 +1404,7 @@ struct mlx5_flow_namespace *mlx5_get_flow_namespace(struct mlx5_core_dev *dev,
 
 	switch (type) {
 	case MLX5_FLOW_NAMESPACE_BYPASS:
+	case MLX5_FLOW_NAMESPACE_LAG:
 	case MLX5_FLOW_NAMESPACE_OFFLOADS:
 	case MLX5_FLOW_NAMESPACE_ETHTOOL:
 	case MLX5_FLOW_NAMESPACE_KERNEL:

@@ -54,6 +54,7 @@ static inline void build_leftovers_ft_param(int *priority,
 
 enum mlx5_flow_namespace_type {
 	MLX5_FLOW_NAMESPACE_BYPASS,
+	MLX5_FLOW_NAMESPACE_LAG,
 	MLX5_FLOW_NAMESPACE_OFFLOADS,
 	MLX5_FLOW_NAMESPACE_ETHTOOL,
 	MLX5_FLOW_NAMESPACE_KERNEL,

@@ -2025,6 +2025,10 @@ static int mlx5e_create_tis(struct mlx5e_priv *priv, int tc)
 
 	MLX5_SET(tisc, tisc, prio, tc << 1);
 	MLX5_SET(tisc, tisc, transport_domain, mdev->mlx5e_res.td.tdn);
+
+	if (mlx5_lag_is_lacp_owner(mdev))
+		MLX5_SET(tisc, tisc, strict_lag_tx_port_affinity, 1);
+
 	return mlx5_core_create_tis(mdev, in, sizeof(in), &priv->tisn[tc]);
 }
 

@@ -107,4 +107,16 @@ void mlx5_remove_dev_by_protocol(struct mlx5_core_dev *dev, int protocol);
 void mlx5e_init(void);
 void mlx5e_cleanup(void);
 
+static inline int mlx5_lag_is_lacp_owner(struct mlx5_core_dev *dev)
+{
+	/* LACP owner conditions:
+	 * 1) Function is physical.
+	 * 2) LAG is supported by FW.
+	 * 3) LAG is managed by driver (currently the only option).
+	 */
+	return  MLX5_CAP_GEN(dev, vport_group_manager) &&
+		   (MLX5_CAP_GEN(dev, num_lag_ports) > 1) &&
+		    MLX5_CAP_GEN(dev, lag_master);
+}
+
 #endif /* __MLX5_CORE_H__ */

@@ -3,7 +3,7 @@ obj-$(CONFIG_MLX5_CORE)		+= mlx5_core.o
 mlx5_core-y :=	main.o cmd.o debugfs.o fw.o eq.o uar.o pagealloc.o \
 		health.o mcg.o cq.o srq.o alloc.o qp.o port.o mr.o pd.o \
 		mad.o transobj.o vport.o sriov.o fs_cmd.o fs_core.o \
-		fs_counters.o rl.o
+		fs_counters.o rl.o lag.o
 
 mlx5_core-$(CONFIG_MLX5_CORE_EN) += wq.o eswitch.o eswitch_offloads.o \
 		en_main.o en_common.o en_fs.o en_ethtool.o en_tx.o \

@@ -3369,6 +3369,8 @@ static void mlx5e_nic_enable(struct mlx5e_priv *priv)
 	struct mlx5_eswitch *esw = mdev->priv.eswitch;
 	struct mlx5_eswitch_rep rep;
 
+	mlx5_lag_add(mdev, netdev);
+
 	if (mlx5e_vxlan_allowed(mdev)) {
 		rtnl_lock();
 		udp_tunnel_get_rx_info(netdev);

@@ -3391,6 +3393,7 @@ static void mlx5e_nic_disable(struct mlx5e_priv *priv)
 {
 	queue_work(priv->wq, &priv->set_rx_mode_work);
 	mlx5e_disable_async_events(priv);
+	mlx5_lag_remove(priv->mdev);
 }
 
 static const struct mlx5e_profile mlx5e_nic_profile = {

@@ -0,0 +1,530 @@
+/*
+ * Copyright (c) 2016, Mellanox Technologies. All rights reserved.
+ *
+ * This software is available to you under a choice of one of two
+ * licenses.  You may choose to be licensed under the terms of the GNU
+ * General Public License (GPL) Version 2, available from the file
+ * COPYING in the main directory of this source tree, or the
+ * OpenIB.org BSD license below:
+ *
+ *     Redistribution and use in source and binary forms, with or
+ *     without modification, are permitted provided that the following
+ *     conditions are met:
+ *
+ *      - Redistributions of source code must retain the above
+ *        copyright notice, this list of conditions and the following
+ *        disclaimer.
+ *
+ *      - Redistributions in binary form must reproduce the above
+ *        copyright notice, this list of conditions and the following
+ *        disclaimer in the documentation and/or other materials
+ *        provided with the distribution.
+ *
+ * THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND,
+ * EXPRESS OR IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF
+ * MERCHANTABILITY, FITNESS FOR A PARTICULAR PURPOSE AND
+ * NONINFRINGEMENT. IN NO EVENT SHALL THE AUTHORS OR COPYRIGHT HOLDERS
+ * BE LIABLE FOR ANY CLAIM, DAMAGES OR OTHER LIABILITY, WHETHER IN AN
+ * ACTION OF CONTRACT, TORT OR OTHERWISE, ARISING FROM, OUT OF OR IN
+ * CONNECTION WITH THE SOFTWARE OR THE USE OR OTHER DEALINGS IN THE
+ * SOFTWARE.
+ */
+
+#include <linux/netdevice.h>
+#include <linux/mlx5/driver.h>
+#include <linux/mlx5/vport.h>
+#include "mlx5_core.h"
+
+enum {
+	MLX5_LAG_FLAG_BONDED = 1 << 0,
+};
+
+struct lag_func {
+	struct mlx5_core_dev *dev;
+	struct net_device    *netdev;
+};
+
+/* Used for collection of netdev event info. */
+struct lag_tracker {
+	enum   netdev_lag_tx_type           tx_type;
+	struct netdev_lag_lower_state_info  netdev_state[MLX5_MAX_PORTS];
+	bool is_bonded;
+};
+
+/* LAG data of a ConnectX card.
+ * It serves both its phys functions.
+ */
+struct mlx5_lag {
+	u8                        flags;
+	u8                        v2p_map[MLX5_MAX_PORTS];
+	struct lag_func           pf[MLX5_MAX_PORTS];
+	struct lag_tracker        tracker;
+	struct delayed_work       bond_work;
+	struct notifier_block     nb;
+};
+
+/* General purpose, use for short periods of time.
+ * Beware of lock dependencies (preferably, no locks should be acquired
+ * under it).
+ */
+static DEFINE_MUTEX(lag_mutex);
+
+static int mlx5_cmd_create_lag(struct mlx5_core_dev *dev, u8 remap_port1,
+			       u8 remap_port2)
+{
+	u32   in[MLX5_ST_SZ_DW(create_lag_in)]   = {0};
+	u32   out[MLX5_ST_SZ_DW(create_lag_out)] = {0};
+	void *lag_ctx = MLX5_ADDR_OF(create_lag_in, in, ctx);
+
+	MLX5_SET(create_lag_in, in, opcode, MLX5_CMD_OP_CREATE_LAG);
+
+	MLX5_SET(lagc, lag_ctx, tx_remap_affinity_1, remap_port1);
+	MLX5_SET(lagc, lag_ctx, tx_remap_affinity_2, remap_port2);
+
+	return mlx5_cmd_exec(dev, in, sizeof(in), out, sizeof(out));
+}
+
+static int mlx5_cmd_modify_lag(struct mlx5_core_dev *dev, u8 remap_port1,
+			       u8 remap_port2)
+{
+	u32   in[MLX5_ST_SZ_DW(modify_lag_in)]   = {0};
+	u32   out[MLX5_ST_SZ_DW(modify_lag_out)] = {0};
+	void *lag_ctx = MLX5_ADDR_OF(modify_lag_in, in, ctx);
+
+	MLX5_SET(modify_lag_in, in, opcode, MLX5_CMD_OP_MODIFY_LAG);
+	MLX5_SET(modify_lag_in, in, field_select, 0x1);
+
+	MLX5_SET(lagc, lag_ctx, tx_remap_affinity_1, remap_port1);
+	MLX5_SET(lagc, lag_ctx, tx_remap_affinity_2, remap_port2);
+
+	return mlx5_cmd_exec(dev, in, sizeof(in), out, sizeof(out));
+}
+
+static int mlx5_cmd_destroy_lag(struct mlx5_core_dev *dev)
+{
+	u32  in[MLX5_ST_SZ_DW(destroy_lag_in)]  = {0};
+	u32 out[MLX5_ST_SZ_DW(destroy_lag_out)] = {0};
+
+	MLX5_SET(destroy_lag_in, in, opcode, MLX5_CMD_OP_DESTROY_LAG);
+
+	return mlx5_cmd_exec(dev, in, sizeof(in), out, sizeof(out));
+}
+
+static struct mlx5_lag *mlx5_lag_dev_get(struct mlx5_core_dev *dev)
+{
+	return dev->priv.lag;
+}
+
+static int mlx5_lag_dev_get_netdev_idx(struct mlx5_lag *ldev,
+				       struct net_device *ndev)
+{
+	int i;
+
+	for (i = 0; i < MLX5_MAX_PORTS; i++)
+		if (ldev->pf[i].netdev == ndev)
+			return i;
+
+	return -1;
+}
+
+static bool mlx5_lag_is_bonded(struct mlx5_lag *ldev)
+{
+	return !!(ldev->flags & MLX5_LAG_FLAG_BONDED);
+}
+
+static void mlx5_infer_tx_affinity_mapping(struct lag_tracker *tracker,
+					   u8 *port1, u8 *port2)
+{
+	if (tracker->tx_type == NETDEV_LAG_TX_TYPE_ACTIVEBACKUP) {
+		if (tracker->netdev_state[0].tx_enabled) {
+			*port1 = 1;
+			*port2 = 1;
+		} else {
+			*port1 = 2;
+			*port2 = 2;
+		}
+	} else {
+		*port1 = 1;
+		*port2 = 2;
+		if (!tracker->netdev_state[0].link_up)
+			*port1 = 2;
+		else if (!tracker->netdev_state[1].link_up)
+			*port2 = 1;
+	}
+}
+
+static void mlx5_activate_lag(struct mlx5_lag *ldev,
+			      struct lag_tracker *tracker)
+{
+	struct mlx5_core_dev *dev0 = ldev->pf[0].dev;
+	int err;
+
+	ldev->flags |= MLX5_LAG_FLAG_BONDED;
+
+	mlx5_infer_tx_affinity_mapping(tracker, &ldev->v2p_map[0],
+				       &ldev->v2p_map[1]);
+
+	err = mlx5_cmd_create_lag(dev0, ldev->v2p_map[0], ldev->v2p_map[1]);
+	if (err)
+		mlx5_core_err(dev0,
+			      "Failed to create LAG (%d)\n",
+			      err);
+}
+
+static void mlx5_deactivate_lag(struct mlx5_lag *ldev)
+{
+	struct mlx5_core_dev *dev0 = ldev->pf[0].dev;
+	int err;
+
+	ldev->flags &= ~MLX5_LAG_FLAG_BONDED;
+
+	err = mlx5_cmd_destroy_lag(dev0);
+	if (err)
+		mlx5_core_err(dev0,
+			      "Failed to destroy LAG (%d)\n",
+			      err);
+}
+
+static void mlx5_do_bond(struct mlx5_lag *ldev)
+{
+	struct mlx5_core_dev *dev0 = ldev->pf[0].dev;
+	struct mlx5_core_dev *dev1 = ldev->pf[1].dev;
+	struct lag_tracker tracker;
+	u8 v2p_port1, v2p_port2;
+	int i, err;
+
+	if (!dev0 || !dev1)
+		return;
+
+	mutex_lock(&lag_mutex);
+	tracker = ldev->tracker;
+	mutex_unlock(&lag_mutex);
+
+	if (tracker.is_bonded && !mlx5_lag_is_bonded(ldev)) {
+		for (i = 0; i < MLX5_MAX_PORTS; i++)
+			mlx5_remove_dev_by_protocol(ldev->pf[i].dev,
+						    MLX5_INTERFACE_PROTOCOL_IB);
+
+		mlx5_activate_lag(ldev, &tracker);
+
+		mlx5_add_dev_by_protocol(dev0, MLX5_INTERFACE_PROTOCOL_IB);
+		mlx5_nic_vport_enable_roce(dev1);
+	} else if (tracker.is_bonded && mlx5_lag_is_bonded(ldev)) {
+		mlx5_infer_tx_affinity_mapping(&tracker, &v2p_port1,
+					       &v2p_port2);
+
+		if ((v2p_port1 != ldev->v2p_map[0]) ||
+		    (v2p_port2 != ldev->v2p_map[1])) {
+			ldev->v2p_map[0] = v2p_port1;
+			ldev->v2p_map[1] = v2p_port2;
+
+			err = mlx5_cmd_modify_lag(dev0, v2p_port1, v2p_port2);
+			if (err)
+				mlx5_core_err(dev0,
+					      "Failed to modify LAG (%d)\n",
+					      err);
+		}
+	} else if (!tracker.is_bonded && mlx5_lag_is_bonded(ldev)) {
+		mlx5_remove_dev_by_protocol(dev0, MLX5_INTERFACE_PROTOCOL_IB);
+		mlx5_nic_vport_disable_roce(dev1);
+
+		mlx5_deactivate_lag(ldev);
+
+		for (i = 0; i < MLX5_MAX_PORTS; i++)
+			if (ldev->pf[i].dev)
+				mlx5_add_dev_by_protocol(ldev->pf[i].dev,
+							 MLX5_INTERFACE_PROTOCOL_IB);
+	}
+}
+
+static void mlx5_queue_bond_work(struct mlx5_lag *ldev, unsigned long delay)
+{
+	schedule_delayed_work(&ldev->bond_work, delay);
+}
+
+static void mlx5_do_bond_work(struct work_struct *work)
+{
+	struct delayed_work *delayed_work = to_delayed_work(work);
+	struct mlx5_lag *ldev = container_of(delayed_work, struct mlx5_lag,
+					     bond_work);
+	int status;
+
+	status = mutex_trylock(&mlx5_intf_mutex);
+	if (!status) {
+		/* 1 sec delay. */
+		mlx5_queue_bond_work(ldev, HZ);
+		return;
+	}
+
+	mlx5_do_bond(ldev);
+	mutex_unlock(&mlx5_intf_mutex);
+}
+
+static int mlx5_handle_changeupper_event(struct mlx5_lag *ldev,
+					 struct lag_tracker *tracker,
+					 struct net_device *ndev,
+					 struct netdev_notifier_changeupper_info *info)
+{
+	struct net_device *upper = info->upper_dev, *ndev_tmp;
+	struct netdev_lag_upper_info *lag_upper_info;
+	bool is_bonded;
+	int bond_status = 0;
+	int num_slaves = 0;
+	int idx;
+
+	if (!netif_is_lag_master(upper))
+		return 0;
+
+	lag_upper_info = info->upper_info;
+
+	/* The event may still be of interest if the slave does not belong to
+	 * us, but is enslaved to a master which has one or more of our netdevs
+	 * as slaves (e.g., if a new slave is added to a master that bonds two
+	 * of our netdevs, we should unbond).
+	 */
+	rcu_read_lock();
+	for_each_netdev_in_bond_rcu(upper, ndev_tmp) {
+		idx = mlx5_lag_dev_get_netdev_idx(ldev, ndev_tmp);
+		if (idx > -1)
+			bond_status |= (1 << idx);
+
+		num_slaves++;
+	}
+	rcu_read_unlock();
+
+	/* None of this lagdev's netdevs are slaves of this master. */
+	if (!(bond_status & 0x3))
+		return 0;
+
+	if (lag_upper_info)
+		tracker->tx_type = lag_upper_info->tx_type;
+
+	/* Determine bonding status:
+	 * A device is considered bonded if both its physical ports are slaves
+	 * of the same lag master, and only them.
+	 * Lag mode must be activebackup or hash.
+	 */
+	is_bonded = (num_slaves == MLX5_MAX_PORTS) &&
+		    (bond_status == 0x3) &&
+		    ((tracker->tx_type == NETDEV_LAG_TX_TYPE_ACTIVEBACKUP) ||
+		     (tracker->tx_type == NETDEV_LAG_TX_TYPE_HASH));
+
+	if (tracker->is_bonded != is_bonded) {
+		tracker->is_bonded = is_bonded;
+		return 1;
+	}
+
+	return 0;
+}
+
+static int mlx5_handle_changelowerstate_event(struct mlx5_lag *ldev,
+					      struct lag_tracker *tracker,
+					      struct net_device *ndev,
+					      struct netdev_notifier_changelowerstate_info *info)
+{
+	struct netdev_lag_lower_state_info *lag_lower_info;
+	int idx;
+
+	if (!netif_is_lag_port(ndev))
+		return 0;
+
+	idx = mlx5_lag_dev_get_netdev_idx(ldev, ndev);
+	if (idx == -1)
+		return 0;
+
+	/* This information is used to determine virtual to physical
+	 * port mapping.
+	 */
+	lag_lower_info = info->lower_state_info;
+	if (!lag_lower_info)
+		return 0;
+
+	tracker->netdev_state[idx] = *lag_lower_info;
+
+	return 1;
+}
+
+static int mlx5_lag_netdev_event(struct notifier_block *this,
+				 unsigned long event, void *ptr)
+{
+	struct net_device *ndev = netdev_notifier_info_to_dev(ptr);
+	struct lag_tracker tracker;
+	struct mlx5_lag *ldev;
+	int changed = 0;
+
+	if (!net_eq(dev_net(ndev), &init_net))
+		return NOTIFY_DONE;
+
+	if ((event != NETDEV_CHANGEUPPER) && (event != NETDEV_CHANGELOWERSTATE))
+		return NOTIFY_DONE;
+
+	ldev    = container_of(this, struct mlx5_lag, nb);
+	tracker = ldev->tracker;
+
+	switch (event) {
+	case NETDEV_CHANGEUPPER:
+		changed = mlx5_handle_changeupper_event(ldev, &tracker, ndev,
+							ptr);
+		break;
+	case NETDEV_CHANGELOWERSTATE:
+		changed = mlx5_handle_changelowerstate_event(ldev, &tracker,
+							     ndev, ptr);
+		break;
+	}
+
+	mutex_lock(&lag_mutex);
+	ldev->tracker = tracker;
+	mutex_unlock(&lag_mutex);
+
+	if (changed)
+		mlx5_queue_bond_work(ldev, 0);
+
+	return NOTIFY_DONE;
+}
+
+static struct mlx5_lag *mlx5_lag_dev_alloc(void)
+{
+	struct mlx5_lag *ldev;
+
+	ldev = kzalloc(sizeof(*ldev), GFP_KERNEL);
+	if (!ldev)
+		return NULL;
+
+	INIT_DELAYED_WORK(&ldev->bond_work, mlx5_do_bond_work);
+
+	return ldev;
+}
+
+static void mlx5_lag_dev_free(struct mlx5_lag *ldev)
+{
+	kfree(ldev);
+}
+
+static void mlx5_lag_dev_add_pf(struct mlx5_lag *ldev,
+				struct mlx5_core_dev *dev,
+				struct net_device *netdev)
+{
+	unsigned int fn = PCI_FUNC(dev->pdev->devfn);
+
+	if (fn >= MLX5_MAX_PORTS)
+		return;
+
+	mutex_lock(&lag_mutex);
+	ldev->pf[fn].dev    = dev;
+	ldev->pf[fn].netdev = netdev;
+	ldev->tracker.netdev_state[fn].link_up = 0;
+	ldev->tracker.netdev_state[fn].tx_enabled = 0;
+
+	dev->priv.lag = ldev;
+	mutex_unlock(&lag_mutex);
+}
+
+static void mlx5_lag_dev_remove_pf(struct mlx5_lag *ldev,
+				   struct mlx5_core_dev *dev)
+{
+	int i;
+
+	for (i = 0; i < MLX5_MAX_PORTS; i++)
+		if (ldev->pf[i].dev == dev)
+			break;
+
+	if (i == MLX5_MAX_PORTS)
+		return;
+
+	mutex_lock(&lag_mutex);
+	memset(&ldev->pf[i], 0, sizeof(*ldev->pf));
+
+	dev->priv.lag = NULL;
+	mutex_unlock(&lag_mutex);
+}
+
+static u16 mlx5_gen_pci_id(struct mlx5_core_dev *dev)
+{
+	return (u16)((dev->pdev->bus->number << 8) |
+		     PCI_SLOT(dev->pdev->devfn));
+}
+
+/* Must be called with intf_mutex held */
+void mlx5_lag_add(struct mlx5_core_dev *dev, struct net_device *netdev)
+{
+	struct mlx5_lag *ldev = NULL;
+	struct mlx5_core_dev *tmp_dev;
+	struct mlx5_priv *priv;
+	u16 pci_id;
+
+	if (!MLX5_CAP_GEN(dev, vport_group_manager) ||
+	    !MLX5_CAP_GEN(dev, lag_master) ||
+	    (MLX5_CAP_GEN(dev, num_lag_ports) != MLX5_MAX_PORTS))
+		return;
+
+	pci_id = mlx5_gen_pci_id(dev);
+
+	mlx5_core_for_each_priv(priv) {
+		tmp_dev = container_of(priv, struct mlx5_core_dev, priv);
+		if ((dev != tmp_dev) &&
+		    (mlx5_gen_pci_id(tmp_dev) == pci_id)) {
+			ldev = tmp_dev->priv.lag;
+			break;
+		}
+	}
+
+	if (!ldev) {
+		ldev = mlx5_lag_dev_alloc();
+		if (!ldev) {
+			mlx5_core_err(dev, "Failed to alloc lag dev\n");
+			return;
+		}
+	}
+
+	mlx5_lag_dev_add_pf(ldev, dev, netdev);
+
+	if (!ldev->nb.notifier_call) {
+		ldev->nb.notifier_call = mlx5_lag_netdev_event;
+		if (register_netdevice_notifier(&ldev->nb)) {
+			ldev->nb.notifier_call = NULL;
+			mlx5_core_err(dev, "Failed to register LAG netdev notifier\n");
+		}
+	}
+}
+
+/* Must be called with intf_mutex held */
+void mlx5_lag_remove(struct mlx5_core_dev *dev)
+{
+	struct mlx5_lag *ldev;
+	int i;
+
+	ldev = mlx5_lag_dev_get(dev);
+	if (!ldev)
+		return;
+
+	if (mlx5_lag_is_bonded(ldev))
+		mlx5_deactivate_lag(ldev);
+
+	mlx5_lag_dev_remove_pf(ldev, dev);
+
+	for (i = 0; i < MLX5_MAX_PORTS; i++)
+		if (ldev->pf[i].dev)
+			break;
+
+	if (i == MLX5_MAX_PORTS) {
+		if (ldev->nb.notifier_call)
+			unregister_netdevice_notifier(&ldev->nb);
+		cancel_delayed_work_sync(&ldev->bond_work);
+		mlx5_lag_dev_free(ldev);
+	}
+}
+
+bool mlx5_lag_is_active(struct mlx5_core_dev *dev)
+{
+	struct mlx5_lag *ldev;
+	bool res;
+
+	mutex_lock(&lag_mutex);
+	ldev = mlx5_lag_dev_get(dev);
+	res  = ldev && mlx5_lag_is_bonded(ldev);
+	mutex_unlock(&lag_mutex);
+
+	return res;
+}
+EXPORT_SYMBOL(mlx5_lag_is_active);
+

@@ -73,8 +73,9 @@ module_param_named(prof_sel, prof_sel, int, 0444);
 MODULE_PARM_DESC(prof_sel, "profile selector. Valid range 0 - 2");
 
 static LIST_HEAD(intf_list);
-static LIST_HEAD(dev_list);
-static DEFINE_MUTEX(intf_mutex);
+
+LIST_HEAD(mlx5_dev_list);
+DEFINE_MUTEX(mlx5_intf_mutex);
 
 struct mlx5_device_context {
 	struct list_head	list;

@@ -820,11 +821,11 @@ static int mlx5_register_device(struct mlx5_core_dev *dev)
 	struct mlx5_priv *priv = &dev->priv;
 	struct mlx5_interface *intf;
 
-	mutex_lock(&intf_mutex);
-	list_add_tail(&priv->dev_list, &dev_list);
+	mutex_lock(&mlx5_intf_mutex);
+	list_add_tail(&priv->dev_list, &mlx5_dev_list);
 	list_for_each_entry(intf, &intf_list, list)
 		mlx5_add_device(intf, priv);
-	mutex_unlock(&intf_mutex);
+	mutex_unlock(&mlx5_intf_mutex);
 
 	return 0;
 }

@@ -834,11 +835,11 @@ static void mlx5_unregister_device(struct mlx5_core_dev *dev)
 	struct mlx5_priv *priv = &dev->priv;
 	struct mlx5_interface *intf;
 
-	mutex_lock(&intf_mutex);
+	mutex_lock(&mlx5_intf_mutex);
 	list_for_each_entry(intf, &intf_list, list)
 		mlx5_remove_device(intf, priv);
 	list_del(&priv->dev_list);
-	mutex_unlock(&intf_mutex);
+	mutex_unlock(&mlx5_intf_mutex);
 }
 
 int mlx5_register_interface(struct mlx5_interface *intf)

@@ -848,11 +849,11 @@ int mlx5_register_interface(struct mlx5_interface *intf)
 	if (!intf->add || !intf->remove)
 		return -EINVAL;
 
-	mutex_lock(&intf_mutex);
+	mutex_lock(&mlx5_intf_mutex);
 	list_add_tail(&intf->list, &intf_list);
-	list_for_each_entry(priv, &dev_list, dev_list)
+	list_for_each_entry(priv, &mlx5_dev_list, dev_list)
 		mlx5_add_device(intf, priv);
-	mutex_unlock(&intf_mutex);
+	mutex_unlock(&mlx5_intf_mutex);
 
 	return 0;
 }

@@ -862,11 +863,11 @@ void mlx5_unregister_interface(struct mlx5_interface *intf)
 {
 	struct mlx5_priv *priv;
 
-	mutex_lock(&intf_mutex);
-	list_for_each_entry(priv, &dev_list, dev_list)
+	mutex_lock(&mlx5_intf_mutex);
+	list_for_each_entry(priv, &mlx5_dev_list, dev_list)
 		mlx5_remove_device(intf, priv);
 	list_del(&intf->list);
-	mutex_unlock(&intf_mutex);
+	mutex_unlock(&mlx5_intf_mutex);
 }
 EXPORT_SYMBOL(mlx5_unregister_interface);
 

@@ -892,6 +893,30 @@ void *mlx5_get_protocol_dev(struct mlx5_core_dev *mdev, int protocol)
 }
 EXPORT_SYMBOL(mlx5_get_protocol_dev);
 
+/* Must be called with intf_mutex held */
+void mlx5_add_dev_by_protocol(struct mlx5_core_dev *dev, int protocol)
+{
+	struct mlx5_interface *intf;
+
+	list_for_each_entry(intf, &intf_list, list)
+		if (intf->protocol == protocol) {
+			mlx5_add_device(intf, &dev->priv);
+			break;
+		}
+}
+
+/* Must be called with intf_mutex held */
+void mlx5_remove_dev_by_protocol(struct mlx5_core_dev *dev, int protocol)
+{
+	struct mlx5_interface *intf;
+
+	list_for_each_entry(intf, &intf_list, list)
+		if (intf->protocol == protocol) {
+			mlx5_remove_device(intf, &dev->priv);
+			break;
+		}
+}
+
 static int mlx5_pci_init(struct mlx5_core_dev *dev, struct mlx5_priv *priv)
 {
 	struct pci_dev *pdev = dev->pdev;

@@ -46,6 +46,9 @@
 
 extern int mlx5_core_debug_mask;
 
+extern struct list_head mlx5_dev_list;
+extern struct mutex mlx5_intf_mutex;
+
 #define mlx5_core_dbg(__dev, format, ...)				\
 	dev_dbg(&(__dev)->pdev->dev, "%s:%s:%d:(pid %d): " format,	\
 		 (__dev)->priv.name, __func__, __LINE__, current->pid,	\

@@ -70,6 +73,9 @@ do {									\
 #define mlx5_core_info(__dev, format, ...)				\
 	dev_info(&(__dev)->pdev->dev, format, ##__VA_ARGS__)
 
+#define mlx5_core_for_each_priv(__priv)					\
+	list_for_each_entry(__priv, &mlx5_dev_list, dev_list)
+
 enum {
 	MLX5_CMD_DATA, /* print command payload only */
 	MLX5_CMD_TIME, /* print command execution time */

@@ -92,6 +98,12 @@ u32 mlx5_get_msix_vec(struct mlx5_core_dev *dev, int vecidx);
 struct mlx5_eq *mlx5_eqn2eq(struct mlx5_core_dev *dev, int eqn);
 void mlx5_cq_tasklet_cb(unsigned long data);
 
+void mlx5_lag_add(struct mlx5_core_dev *dev, struct net_device *netdev);
+void mlx5_lag_remove(struct mlx5_core_dev *dev);
+
+void mlx5_add_dev_by_protocol(struct mlx5_core_dev *dev, int protocol);
+void mlx5_remove_dev_by_protocol(struct mlx5_core_dev *dev, int protocol);
+
 void mlx5e_init(void);
 void mlx5e_cleanup(void);
 

@@ -477,6 +477,7 @@ struct mlx5_fc_stats {
 };
 
 struct mlx5_eswitch;
+struct mlx5_lag;
 
 struct mlx5_rl_entry {
 	u32                     rate;

@@ -550,6 +551,7 @@ struct mlx5_priv {
 	struct mlx5_flow_steering *steering;
 	struct mlx5_eswitch     *eswitch;
 	struct mlx5_core_sriov	sriov;
+	struct mlx5_lag		*lag;
 	unsigned long		pci_dev_data;
 	struct mlx5_fc_stats		fc_stats;
 	struct mlx5_rl_table            rl_table;

@@ -942,6 +944,8 @@ int mlx5_register_interface(struct mlx5_interface *intf);
 void mlx5_unregister_interface(struct mlx5_interface *intf);
 int mlx5_core_query_vendor_id(struct mlx5_core_dev *mdev, u32 *vendor_id);
 
+bool mlx5_lag_is_active(struct mlx5_core_dev *dev);
+
 struct mlx5_profile {
 	u64	mask;
 	u8	log_max_qp;

@@ -1427,6 +1427,16 @@ struct mlx5_flow_namespace *mlx5_get_flow_namespace(struct mlx5_core_dev *dev,
 			return &steering->esw_ingress_root_ns->ns;
 		else
 			return NULL;
+	case MLX5_FLOW_NAMESPACE_SNIFFER_RX:
+		if (steering->sniffer_rx_root_ns)
+			return &steering->sniffer_rx_root_ns->ns;
+		else
+			return NULL;
+	case MLX5_FLOW_NAMESPACE_SNIFFER_TX:
+		if (steering->sniffer_tx_root_ns)
+			return &steering->sniffer_tx_root_ns->ns;
+		else
+			return NULL;
 	default:
 		return NULL;
 	}

@@ -1726,10 +1736,46 @@ void mlx5_cleanup_fs(struct mlx5_core_dev *dev)
 	cleanup_root_ns(steering->esw_egress_root_ns);
 	cleanup_root_ns(steering->esw_ingress_root_ns);
 	cleanup_root_ns(steering->fdb_root_ns);
+	cleanup_root_ns(steering->sniffer_rx_root_ns);
+	cleanup_root_ns(steering->sniffer_tx_root_ns);
 	mlx5_cleanup_fc_stats(dev);
 	kfree(steering);
 }
 
+static int init_sniffer_tx_root_ns(struct mlx5_flow_steering *steering)
+{
+	struct fs_prio *prio;
+
+	steering->sniffer_tx_root_ns = create_root_ns(steering, FS_FT_SNIFFER_TX);
+	if (!steering->sniffer_tx_root_ns)
+		return -ENOMEM;
+
+	/* Create single prio */
+	prio = fs_create_prio(&steering->sniffer_tx_root_ns->ns, 0, 1);
+	if (IS_ERR(prio)) {
+		cleanup_root_ns(steering->sniffer_tx_root_ns);
+		return PTR_ERR(prio);
+	}
+	return 0;
+}
+
+static int init_sniffer_rx_root_ns(struct mlx5_flow_steering *steering)
+{
+	struct fs_prio *prio;
+
+	steering->sniffer_rx_root_ns = create_root_ns(steering, FS_FT_SNIFFER_RX);
+	if (!steering->sniffer_rx_root_ns)
+		return -ENOMEM;
+
+	/* Create single prio */
+	prio = fs_create_prio(&steering->sniffer_rx_root_ns->ns, 0, 1);
+	if (IS_ERR(prio)) {
+		cleanup_root_ns(steering->sniffer_rx_root_ns);
+		return PTR_ERR(prio);
+	}
+	return 0;
+}
+
 static int init_fdb_root_ns(struct mlx5_flow_steering *steering)
 {
 	struct fs_prio *prio;

@@ -1826,6 +1872,18 @@ int mlx5_init_fs(struct mlx5_core_dev *dev)
 		}
 	}
 
+	if (MLX5_CAP_FLOWTABLE_SNIFFER_RX(dev, ft_support)) {
+		err = init_sniffer_rx_root_ns(steering);
+		if (err)
+			goto err;
+	}
+
+	if (MLX5_CAP_FLOWTABLE_SNIFFER_TX(dev, ft_support)) {
+		err = init_sniffer_tx_root_ns(steering);
+		if (err)
+			goto err;
+	}
+
 	return 0;
 err:
 	mlx5_cleanup_fs(dev);

@@ -49,6 +49,8 @@ enum fs_flow_table_type {
 	FS_FT_ESW_EGRESS_ACL  = 0x2,
 	FS_FT_ESW_INGRESS_ACL = 0x3,
 	FS_FT_FDB             = 0X4,
+	FS_FT_SNIFFER_RX	= 0X5,
+	FS_FT_SNIFFER_TX	= 0X6,
 };
 
 enum fs_flow_table_op_mod {

@@ -66,6 +68,8 @@ struct mlx5_flow_steering {
 	struct mlx5_flow_root_namespace *fdb_root_ns;
 	struct mlx5_flow_root_namespace *esw_egress_root_ns;
 	struct mlx5_flow_root_namespace *esw_ingress_root_ns;
+	struct mlx5_flow_root_namespace	*sniffer_tx_root_ns;
+	struct mlx5_flow_root_namespace	*sniffer_rx_root_ns;
 };
 
 struct fs_node {

@@ -63,6 +63,8 @@ enum mlx5_flow_namespace_type {
 	MLX5_FLOW_NAMESPACE_FDB,
 	MLX5_FLOW_NAMESPACE_ESW_EGRESS,
 	MLX5_FLOW_NAMESPACE_ESW_INGRESS,
+	MLX5_FLOW_NAMESPACE_SNIFFER_RX,
+	MLX5_FLOW_NAMESPACE_SNIFFER_TX,
 };
 
 struct mlx5_flow_table;