1 files changed, 43 insertions, 315 deletions

diff --git a/drivers/net/ethernet/mellanox/mlx5/core/eswitch.c b/drivers/net/ethernet/mellanox/mlx5/core/eswitch.c
index 97e6cb6f13c1..ec136b499204 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/eswitch.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/eswitch.c
@@ -38,6 +38,7 @@
 #include <linux/mlx5/mpfs.h>
 #include "esw/acl/lgcy.h"
 #include "esw/legacy.h"
+#include "esw/qos.h"
 #include "mlx5_core.h"
 #include "lib/eq.h"
 #include "eswitch.h"
@@ -740,201 +741,6 @@ static void esw_vport_change_handler(struct work_struct *work)
 	mutex_unlock(&esw->state_lock);
 }
 
-static bool element_type_supported(struct mlx5_eswitch *esw, int type)
-{
-	const struct mlx5_core_dev *dev = esw->dev;
-
-	switch (type) {
-	case SCHEDULING_CONTEXT_ELEMENT_TYPE_TSAR:
-		return MLX5_CAP_QOS(dev, esw_element_type) &
-		       ELEMENT_TYPE_CAP_MASK_TASR;
-	case SCHEDULING_CONTEXT_ELEMENT_TYPE_VPORT:
-		return MLX5_CAP_QOS(dev, esw_element_type) &
-		       ELEMENT_TYPE_CAP_MASK_VPORT;
-	case SCHEDULING_CONTEXT_ELEMENT_TYPE_VPORT_TC:
-		return MLX5_CAP_QOS(dev, esw_element_type) &
-		       ELEMENT_TYPE_CAP_MASK_VPORT_TC;
-	case SCHEDULING_CONTEXT_ELEMENT_TYPE_PARA_VPORT_TC:
-		return MLX5_CAP_QOS(dev, esw_element_type) &
-		       ELEMENT_TYPE_CAP_MASK_PARA_VPORT_TC;
-	}
-	return false;
-}
-
-/* Vport QoS management */
-static void esw_create_tsar(struct mlx5_eswitch *esw)
-{
-	u32 tsar_ctx[MLX5_ST_SZ_DW(scheduling_context)] = {0};
-	struct mlx5_core_dev *dev = esw->dev;
-	__be32 *attr;
-	int err;
-
-	if (!MLX5_CAP_GEN(dev, qos) || !MLX5_CAP_QOS(dev, esw_scheduling))
-		return;
-
-	if (!element_type_supported(esw, SCHEDULING_CONTEXT_ELEMENT_TYPE_TSAR))
-		return;
-
-	if (esw->qos.enabled)
-		return;
-
-	MLX5_SET(scheduling_context, tsar_ctx, element_type,
-		 SCHEDULING_CONTEXT_ELEMENT_TYPE_TSAR);
-
-	attr = MLX5_ADDR_OF(scheduling_context, tsar_ctx, element_attributes);
-	*attr = cpu_to_be32(TSAR_ELEMENT_TSAR_TYPE_DWRR << 16);
-
-	err = mlx5_create_scheduling_element_cmd(dev,
-						 SCHEDULING_HIERARCHY_E_SWITCH,
-						 tsar_ctx,
-						 &esw->qos.root_tsar_id);
-	if (err) {
-		esw_warn(esw->dev, "E-Switch create TSAR failed (%d)\n", err);
-		return;
-	}
-
-	esw->qos.enabled = true;
-}
-
-static void esw_destroy_tsar(struct mlx5_eswitch *esw)
-{
-	int err;
-
-	if (!esw->qos.enabled)
-		return;
-
-	err = mlx5_destroy_scheduling_element_cmd(esw->dev,
-						  SCHEDULING_HIERARCHY_E_SWITCH,
-						  esw->qos.root_tsar_id);
-	if (err)
-		esw_warn(esw->dev, "E-Switch destroy TSAR failed (%d)\n", err);
-
-	esw->qos.enabled = false;
-}
-
-static int esw_vport_enable_qos(struct mlx5_eswitch *esw,
-				struct mlx5_vport *vport,
-				u32 initial_max_rate, u32 initial_bw_share)
-{
-	u32 sched_ctx[MLX5_ST_SZ_DW(scheduling_context)] = {0};
-	struct mlx5_core_dev *dev = esw->dev;
-	void *vport_elem;
-	int err = 0;
-
-	if (!esw->qos.enabled)
-		return 0;
-
-	if (vport->qos.enabled)
-		return -EEXIST;
-
-	MLX5_SET(scheduling_context, sched_ctx, element_type,
-		 SCHEDULING_CONTEXT_ELEMENT_TYPE_VPORT);
-	vport_elem = MLX5_ADDR_OF(scheduling_context, sched_ctx,
-				  element_attributes);
-	MLX5_SET(vport_element, vport_elem, vport_number, vport->vport);
-	MLX5_SET(scheduling_context, sched_ctx, parent_element_id,
-		 esw->qos.root_tsar_id);
-	MLX5_SET(scheduling_context, sched_ctx, max_average_bw,
-		 initial_max_rate);
-	MLX5_SET(scheduling_context, sched_ctx, bw_share, initial_bw_share);
-
-	err = mlx5_create_scheduling_element_cmd(dev,
-						 SCHEDULING_HIERARCHY_E_SWITCH,
-						 sched_ctx,
-						 &vport->qos.esw_tsar_ix);
-	if (err) {
-		esw_warn(esw->dev, "E-Switch create TSAR vport element failed (vport=%d,err=%d)\n",
-			 vport->vport, err);
-		return err;
-	}
-
-	vport->qos.enabled = true;
-	return 0;
-}
-
-static void esw_vport_disable_qos(struct mlx5_eswitch *esw,
-				  struct mlx5_vport *vport)
-{
-	int err;
-
-	if (!vport->qos.enabled)
-		return;
-
-	err = mlx5_destroy_scheduling_element_cmd(esw->dev,
-						  SCHEDULING_HIERARCHY_E_SWITCH,
-						  vport->qos.esw_tsar_ix);
-	if (err)
-		esw_warn(esw->dev, "E-Switch destroy TSAR vport element failed (vport=%d,err=%d)\n",
-			 vport->vport, err);
-
-	vport->qos.enabled = false;
-}
-
-static int esw_vport_qos_config(struct mlx5_eswitch *esw,
-				struct mlx5_vport *vport,
-				u32 max_rate, u32 bw_share)
-{
-	u32 sched_ctx[MLX5_ST_SZ_DW(scheduling_context)] = {0};
-	struct mlx5_core_dev *dev = esw->dev;
-	void *vport_elem;
-	u32 bitmask = 0;
-	int err = 0;
-
-	if (!MLX5_CAP_GEN(dev, qos) || !MLX5_CAP_QOS(dev, esw_scheduling))
-		return -EOPNOTSUPP;
-
-	if (!vport->qos.enabled)
-		return -EIO;
-
-	MLX5_SET(scheduling_context, sched_ctx, element_type,
-		 SCHEDULING_CONTEXT_ELEMENT_TYPE_VPORT);
-	vport_elem = MLX5_ADDR_OF(scheduling_context, sched_ctx,
-				  element_attributes);
-	MLX5_SET(vport_element, vport_elem, vport_number, vport->vport);
-	MLX5_SET(scheduling_context, sched_ctx, parent_element_id,
-		 esw->qos.root_tsar_id);
-	MLX5_SET(scheduling_context, sched_ctx, max_average_bw,
-		 max_rate);
-	MLX5_SET(scheduling_context, sched_ctx, bw_share, bw_share);
-	bitmask |= MODIFY_SCHEDULING_ELEMENT_IN_MODIFY_BITMASK_MAX_AVERAGE_BW;
-	bitmask |= MODIFY_SCHEDULING_ELEMENT_IN_MODIFY_BITMASK_BW_SHARE;
-
-	err = mlx5_modify_scheduling_element_cmd(dev,
-						 SCHEDULING_HIERARCHY_E_SWITCH,
-						 sched_ctx,
-						 vport->qos.esw_tsar_ix,
-						 bitmask);
-	if (err) {
-		esw_warn(esw->dev, "E-Switch modify TSAR vport element failed (vport=%d,err=%d)\n",
-			 vport->vport, err);
-		return err;
-	}
-
-	return 0;
-}
-
-int mlx5_esw_modify_vport_rate(struct mlx5_eswitch *esw, u16 vport_num,
-			       u32 rate_mbps)
-{
-	u32 ctx[MLX5_ST_SZ_DW(scheduling_context)] = {};
-	struct mlx5_vport *vport;
-
-	vport = mlx5_eswitch_get_vport(esw, vport_num);
-	if (IS_ERR(vport))
-		return PTR_ERR(vport);
-
-	if (!vport->qos.enabled)
-		return -EOPNOTSUPP;
-
-	MLX5_SET(scheduling_context, ctx, max_average_bw, rate_mbps);
-
-	return mlx5_modify_scheduling_element_cmd(esw->dev,
-						  SCHEDULING_HIERARCHY_E_SWITCH,
-						  ctx,
-						  vport->qos.esw_tsar_ix,
-						  MODIFY_SCHEDULING_ELEMENT_IN_MODIFY_BITMASK_MAX_AVERAGE_BW);
-}
-
 static void node_guid_gen_from_mac(u64 *node_guid, const u8 *mac)
 {
 	((u8 *)node_guid)[7] = mac[0];
@@ -976,7 +782,7 @@ static int esw_vport_setup(struct mlx5_eswitch *esw, struct mlx5_vport *vport)
 		return err;
 
 	/* Attach vport to the eswitch rate limiter */
-	esw_vport_enable_qos(esw, vport, vport->qos.max_rate, vport->qos.bw_share);
+	mlx5_esw_qos_vport_enable(esw, vport, vport->qos.max_rate, vport->qos.bw_share);
 
 	if (mlx5_esw_is_manager_vport(esw, vport_num))
 		return 0;
@@ -1013,7 +819,7 @@ static void esw_vport_cleanup(struct mlx5_eswitch *esw, struct mlx5_vport *vport
 					      vport_num, 1,
 					      MLX5_VPORT_ADMIN_STATE_DOWN);
 
-	esw_vport_disable_qos(esw, vport);
+	mlx5_esw_qos_vport_disable(esw, vport);
 	esw_vport_cleanup_acl(esw, vport);
 }
 
@@ -1454,12 +1260,10 @@ int mlx5_eswitch_enable_locked(struct mlx5_eswitch *esw, int mode, int num_vfs)
 
 	mlx5_eswitch_update_num_of_vfs(esw, num_vfs);
 
-	esw_create_tsar(esw);
+	mlx5_esw_qos_create(esw);
 
 	esw->mode = mode;
 
-	mlx5_lag_update(esw->dev);
-
 	if (mode == MLX5_ESWITCH_LEGACY) {
 		err = esw_legacy_enable(esw);
 	} else {
@@ -1486,7 +1290,7 @@ abort:
 	if (mode == MLX5_ESWITCH_OFFLOADS)
 		mlx5_rescan_drivers(esw->dev);
 
-	esw_destroy_tsar(esw);
+	mlx5_esw_qos_destroy(esw);
 	mlx5_esw_acls_ns_cleanup(esw);
 	return err;
 }
@@ -1494,7 +1298,7 @@ abort:
 /**
  * mlx5_eswitch_enable - Enable eswitch
  * @esw:	Pointer to eswitch
- * @num_vfs:	Enable eswitch swich for given number of VFs.
+ * @num_vfs:	Enable eswitch switch for given number of VFs.
  *		Caller must pass num_vfs > 0 when enabling eswitch for
  *		vf vports.
  * mlx5_eswitch_enable() returns 0 on success or error code on failure.
@@ -1506,6 +1310,7 @@ int mlx5_eswitch_enable(struct mlx5_eswitch *esw, int num_vfs)
 	if (!mlx5_esw_allowed(esw))
 		return 0;
 
+	mlx5_lag_disable_change(esw->dev);
 	down_write(&esw->mode_lock);
 	if (esw->mode == MLX5_ESWITCH_NONE) {
 		ret = mlx5_eswitch_enable_locked(esw, MLX5_ESWITCH_LEGACY, num_vfs);
@@ -1519,6 +1324,7 @@ int mlx5_eswitch_enable(struct mlx5_eswitch *esw, int num_vfs)
 			esw->esw_funcs.num_vfs = num_vfs;
 	}
 	up_write(&esw->mode_lock);
+	mlx5_lag_enable_change(esw->dev);
 	return ret;
 }
 
@@ -1550,12 +1356,10 @@ void mlx5_eswitch_disable_locked(struct mlx5_eswitch *esw, bool clear_vf)
 	old_mode = esw->mode;
 	esw->mode = MLX5_ESWITCH_NONE;
 
-	mlx5_lag_update(esw->dev);
-
 	if (old_mode == MLX5_ESWITCH_OFFLOADS)
 		mlx5_rescan_drivers(esw->dev);
 
-	esw_destroy_tsar(esw);
+	mlx5_esw_qos_destroy(esw);
 	mlx5_esw_acls_ns_cleanup(esw);
 
 	if (clear_vf)
@@ -1567,10 +1371,12 @@ void mlx5_eswitch_disable(struct mlx5_eswitch *esw, bool clear_vf)
 	if (!mlx5_esw_allowed(esw))
 		return;
 
+	mlx5_lag_disable_change(esw->dev);
 	down_write(&esw->mode_lock);
 	mlx5_eswitch_disable_locked(esw, clear_vf);
 	esw->esw_funcs.num_vfs = 0;
 	up_write(&esw->mode_lock);
+	mlx5_lag_enable_change(esw->dev);
 }
 
 static int mlx5_query_hca_cap_host_pf(struct mlx5_core_dev *dev, void *out)
@@ -1759,7 +1565,9 @@ int mlx5_eswitch_init(struct mlx5_core_dev *dev)
 	ida_init(&esw->offloads.vport_metadata_ida);
 	xa_init_flags(&esw->offloads.vhca_map, XA_FLAGS_ALLOC);
 	mutex_init(&esw->state_lock);
+	lockdep_register_key(&esw->mode_lock_key);
 	init_rwsem(&esw->mode_lock);
+	lockdep_set_class(&esw->mode_lock, &esw->mode_lock_key);
 
 	esw->enabled_vports = 0;
 	esw->mode = MLX5_ESWITCH_NONE;
@@ -1793,6 +1601,7 @@ void mlx5_eswitch_cleanup(struct mlx5_eswitch *esw)
 
 	esw->dev->priv.eswitch = NULL;
 	destroy_workqueue(esw->work_queue);
+	lockdep_unregister_key(&esw->mode_lock_key);
 	mutex_destroy(&esw->state_lock);
 	WARN_ON(!xa_empty(&esw->offloads.vhca_map));
 	xa_destroy(&esw->offloads.vhca_map);
@@ -1889,8 +1698,7 @@ is_port_function_supported(struct mlx5_eswitch *esw, u16 vport_num)
 	       mlx5_esw_is_sf_vport(esw, vport_num);
 }
 
-int mlx5_devlink_port_function_hw_addr_get(struct devlink *devlink,
-					   struct devlink_port *port,
+int mlx5_devlink_port_function_hw_addr_get(struct devlink_port *port,
 					   u8 *hw_addr, int *hw_addr_len,
 					   struct netlink_ext_ack *extack)
 {
@@ -1899,7 +1707,7 @@ int mlx5_devlink_port_function_hw_addr_get(struct devlink *devlink,
 	int err = -EOPNOTSUPP;
 	u16 vport_num;
 
-	esw = mlx5_devlink_eswitch_get(devlink);
+	esw = mlx5_devlink_eswitch_get(port->devlink);
 	if (IS_ERR(esw))
 		return PTR_ERR(esw);
 
@@ -1923,8 +1731,7 @@ int mlx5_devlink_port_function_hw_addr_get(struct devlink *devlink,
 	return err;
 }
 
-int mlx5_devlink_port_function_hw_addr_set(struct devlink *devlink,
-					   struct devlink_port *port,
+int mlx5_devlink_port_function_hw_addr_set(struct devlink_port *port,
 					   const u8 *hw_addr, int hw_addr_len,
 					   struct netlink_ext_ack *extack)
 {
@@ -1933,7 +1740,7 @@ int mlx5_devlink_port_function_hw_addr_set(struct devlink *devlink,
 	int err = -EOPNOTSUPP;
 	u16 vport_num;
 
-	esw = mlx5_devlink_eswitch_get(devlink);
+	esw = mlx5_devlink_eswitch_get(port->devlink);
 	if (IS_ERR(esw)) {
 		NL_SET_ERR_MSG_MOD(extack, "Eswitch doesn't support set hw_addr");
 		return PTR_ERR(esw);
@@ -2049,110 +1856,6 @@ int __mlx5_eswitch_set_vport_vlan(struct mlx5_eswitch *esw,
 	return err;
 }
 
-static u32 calculate_vports_min_rate_divider(struct mlx5_eswitch *esw)
-{
-	u32 fw_max_bw_share = MLX5_CAP_QOS(esw->dev, max_tsar_bw_share);
-	struct mlx5_vport *evport;
-	u32 max_guarantee = 0;
-	unsigned long i;
-
-	mlx5_esw_for_each_vport(esw, i, evport) {
-		if (!evport->enabled || evport->qos.min_rate < max_guarantee)
-			continue;
-		max_guarantee = evport->qos.min_rate;
-	}
-
-	if (max_guarantee)
-		return max_t(u32, max_guarantee / fw_max_bw_share, 1);
-	return 0;
-}
-
-static int normalize_vports_min_rate(struct mlx5_eswitch *esw)
-{
-	u32 fw_max_bw_share = MLX5_CAP_QOS(esw->dev, max_tsar_bw_share);
-	u32 divider = calculate_vports_min_rate_divider(esw);
-	struct mlx5_vport *evport;
-	u32 vport_max_rate;
-	u32 vport_min_rate;
-	unsigned long i;
-	u32 bw_share;
-	int err;
-
-	mlx5_esw_for_each_vport(esw, i, evport) {
-		if (!evport->enabled)
-			continue;
-		vport_min_rate = evport->qos.min_rate;
-		vport_max_rate = evport->qos.max_rate;
-		bw_share = 0;
-
-		if (divider)
-			bw_share = MLX5_RATE_TO_BW_SHARE(vport_min_rate,
-							 divider,
-							 fw_max_bw_share);
-
-		if (bw_share == evport->qos.bw_share)
-			continue;
-
-		err = esw_vport_qos_config(esw, evport, vport_max_rate,
-					   bw_share);
-		if (!err)
-			evport->qos.bw_share = bw_share;
-		else
-			return err;
-	}
-
-	return 0;
-}
-
-int mlx5_eswitch_set_vport_rate(struct mlx5_eswitch *esw, u16 vport,
-				u32 max_rate, u32 min_rate)
-{
-	struct mlx5_vport *evport = mlx5_eswitch_get_vport(esw, vport);
-	u32 fw_max_bw_share;
-	u32 previous_min_rate;
-	bool min_rate_supported;
-	bool max_rate_supported;
-	int err = 0;
-
-	if (!mlx5_esw_allowed(esw))
-		return -EPERM;
-	if (IS_ERR(evport))
-		return PTR_ERR(evport);
-
-	fw_max_bw_share = MLX5_CAP_QOS(esw->dev, max_tsar_bw_share);
-	min_rate_supported = MLX5_CAP_QOS(esw->dev, esw_bw_share) &&
-				fw_max_bw_share >= MLX5_MIN_BW_SHARE;
-	max_rate_supported = MLX5_CAP_QOS(esw->dev, esw_rate_limit);
-
-	if ((min_rate && !min_rate_supported) || (max_rate && !max_rate_supported))
-		return -EOPNOTSUPP;
-
-	mutex_lock(&esw->state_lock);
-
-	if (min_rate == evport->qos.min_rate)
-		goto set_max_rate;
-
-	previous_min_rate = evport->qos.min_rate;
-	evport->qos.min_rate = min_rate;
-	err = normalize_vports_min_rate(esw);
-	if (err) {
-		evport->qos.min_rate = previous_min_rate;
-		goto unlock;
-	}
-
-set_max_rate:
-	if (max_rate == evport->qos.max_rate)
-		goto unlock;
-
-	err = esw_vport_qos_config(esw, evport, max_rate, evport->qos.bw_share);
-	if (!err)
-		evport->qos.max_rate = max_rate;
-
-unlock:
-	mutex_unlock(&esw->state_lock);
-	return err;
-}
-
 int mlx5_eswitch_get_vport_stats(struct mlx5_eswitch *esw,
 				 u16 vport_num,
 				 struct ifla_vf_stats *vf_stats)
@@ -2366,10 +2069,23 @@ int mlx5_esw_try_lock(struct mlx5_eswitch *esw)
  */
 void mlx5_esw_unlock(struct mlx5_eswitch *esw)
 {
+	if (!mlx5_esw_allowed(esw))
+		return;
 	up_write(&esw->mode_lock);
 }
 
 /**
+ * mlx5_esw_lock() - Take write lock on esw mode lock
+ * @esw: eswitch device.
+ */
+void mlx5_esw_lock(struct mlx5_eswitch *esw)
+{
+	if (!mlx5_esw_allowed(esw))
+		return;
+	down_write(&esw->mode_lock);
+}
+
+/**
  * mlx5_eswitch_get_total_vports - Get total vports of the eswitch
  *
  * @dev: Pointer to core device
@@ -2384,3 +2100,15 @@ u16 mlx5_eswitch_get_total_vports(const struct mlx5_core_dev *dev)
 	return mlx5_esw_allowed(esw) ? esw->total_vports : 0;
 }
 EXPORT_SYMBOL_GPL(mlx5_eswitch_get_total_vports);
+
+/**
+ * mlx5_eswitch_get_core_dev - Get the mdev device
+ * @esw : eswitch device.
+ *
+ * Return the mellanox core device which manages the eswitch.
+ */
+struct mlx5_core_dev *mlx5_eswitch_get_core_dev(struct mlx5_eswitch *esw)
+{
+	return mlx5_esw_allowed(esw) ? esw->dev : NULL;
+}
+EXPORT_SYMBOL(mlx5_eswitch_get_core_dev);