net/mlx5: Implement devlink port function cmds to control ipsec_packet

Implement devlink port function commands to enable / disable IPsec
packet offloads. This is used to control the IPsec capability of the
device.

When ipsec_offload is enabled for a VF, it prevents adding IPsec packet
offloads on the PF, because the two cannot be active simultaneously due
to HW constraints. Conversely, if there are any active IPsec packet
offloads on the PF, it's not allowed to enable ipsec_packet on a VF,
until PF IPsec offloads are cleared.

Signed-off-by: Dima Chumak <dchumak@nvidia.com>
Signed-off-by: Leon Romanovsky <leonro@nvidia.com>
Signed-off-by: Saeed Mahameed <saeedm@nvidia.com>
Link: https://lore.kernel.org/r/20230825062836.103744-9-saeed@kernel.org
Signed-off-by: Jakub Kicinski <kuba@kernel.org>

Documentation/networking/device_drivers/ethernet/mellanox/mlx5/switchdev.rst

@@ -200,6 +200,16 @@ IPsec capability enabled, any IPsec offloading is blocked on the PF.
 mlx5 driver support devlink port function attr mechanism to setup ipsec_crypto
 capability. (refer to Documentation/networking/devlink/devlink-port.rst)
 
+IPsec packet capability setup
+~~~~~~~~~~~~~~~~~~~~~~~~~~~~~
+User who wants mlx5 PCI VFs to be able to perform IPsec packet offloading need
+to explicitly enable the VF ipsec_packet capability. Enabling IPsec capability
+for VFs is supported starting with ConnectX6dx devices and above. When a VF has
+IPsec capability enabled, any IPsec offloading is blocked on the PF.
+
+mlx5 driver support devlink port function attr mechanism to setup ipsec_packet
+capability. (refer to Documentation/networking/devlink/devlink-port.rst)
+
 SF state setup
 --------------
 

drivers/net/ethernet/mellanox/mlx5/core/esw/devlink_port.c

@@ -95,6 +95,8 @@ static const struct devlink_port_ops mlx5_esw_pf_vf_dl_port_ops = {
 #ifdef CONFIG_XFRM_OFFLOAD
 	.port_fn_ipsec_crypto_get = mlx5_devlink_port_fn_ipsec_crypto_get,
 	.port_fn_ipsec_crypto_set = mlx5_devlink_port_fn_ipsec_crypto_set,
+	.port_fn_ipsec_packet_get = mlx5_devlink_port_fn_ipsec_packet_get,
+	.port_fn_ipsec_packet_set = mlx5_devlink_port_fn_ipsec_packet_set,
 #endif /* CONFIG_XFRM_OFFLOAD */
 };
 

drivers/net/ethernet/mellanox/mlx5/core/esw/ipsec.c

@@ -37,6 +37,7 @@ free:
 
 enum esw_vport_ipsec_offload {
 	MLX5_ESW_VPORT_IPSEC_CRYPTO_OFFLOAD,
+	MLX5_ESW_VPORT_IPSEC_PACKET_OFFLOAD,
 };
 
 int mlx5_esw_ipsec_vf_offload_get(struct mlx5_core_dev *dev, struct mlx5_vport *vport)
@@ -55,6 +56,7 @@ int mlx5_esw_ipsec_vf_offload_get(struct mlx5_core_dev *dev, struct mlx5_vport *
 
 	if (!ipsec_enabled) {
 		vport->info.ipsec_crypto_enabled = false;
+		vport->info.ipsec_packet_enabled = false;
 		return 0;
 	}
 
@@ -69,6 +71,8 @@ int mlx5_esw_ipsec_vf_offload_get(struct mlx5_core_dev *dev, struct mlx5_vport *
 	hca_cap = MLX5_ADDR_OF(query_hca_cap_out, query_cap, capability);
 	vport->info.ipsec_crypto_enabled =
 		MLX5_GET(ipsec_cap, hca_cap, ipsec_crypto_offload);
+	vport->info.ipsec_packet_enabled =
+		MLX5_GET(ipsec_cap, hca_cap, ipsec_full_offload);
 free:
 	kvfree(query_cap);
 	return err;
@@ -143,6 +147,9 @@ static int esw_ipsec_vf_set_bytype(struct mlx5_core_dev *dev, struct mlx5_vport
 	case MLX5_ESW_VPORT_IPSEC_CRYPTO_OFFLOAD:
 		MLX5_SET(ipsec_cap, cap, ipsec_crypto_offload, enable);
 		break;
+	case MLX5_ESW_VPORT_IPSEC_PACKET_OFFLOAD:
+		MLX5_SET(ipsec_cap, cap, ipsec_full_offload, enable);
+		break;
 	default:
 		ret = -EOPNOTSUPP;
 		goto free;
@@ -222,15 +229,28 @@ static int esw_ipsec_vf_offload_set_bytype(struct mlx5_eswitch *esw, struct mlx5
 		err = esw_ipsec_vf_set_bytype(dev, vport, enable, type);
 		if (err)
 			return err;
-		err = esw_ipsec_vf_set_generic(dev, vport->vport, enable);
+		err = mlx5_esw_ipsec_vf_offload_get(dev, vport);
 		if (err)
 			return err;
+
+		/* The generic ipsec_offload cap can be disabled only if both
+		 * ipsec_crypto_offload and ipsec_full_offload aren't enabled.
+		 */
+		if (!vport->info.ipsec_crypto_enabled &&
+		    !vport->info.ipsec_packet_enabled) {
+			err = esw_ipsec_vf_set_generic(dev, vport->vport, enable);
+			if (err)
+				return err;
+		}
 	}
 
 	switch (type) {
 	case MLX5_ESW_VPORT_IPSEC_CRYPTO_OFFLOAD:
 		vport->info.ipsec_crypto_enabled = enable;
 		break;
+	case MLX5_ESW_VPORT_IPSEC_PACKET_OFFLOAD:
+		vport->info.ipsec_packet_enabled = enable;
+		break;
 	default:
 		return -EINVAL;
 	}
@@ -301,9 +321,49 @@ free:
 	return err;
 }
 
+int mlx5_esw_ipsec_vf_packet_offload_supported(struct mlx5_core_dev *dev,
+					       u16 vport_num)
+{
+	int query_sz = MLX5_ST_SZ_BYTES(query_hca_cap_out);
+	void *hca_cap, *query_cap;
+	int ret;
+
+	if (!mlx5_esw_ipsec_vf_offload_supported(dev))
+		return -EOPNOTSUPP;
+
+	ret = esw_ipsec_offload_supported(dev, vport_num);
+	if (ret)
+		return ret;
+
+	query_cap = kvzalloc(query_sz, GFP_KERNEL);
+	if (!query_cap)
+		return -ENOMEM;
+
+	ret = mlx5_vport_get_other_func_cap(dev, vport_num, query_cap, MLX5_CAP_FLOW_TABLE);
+	if (ret)
+		goto out;
+
+	hca_cap = MLX5_ADDR_OF(query_hca_cap_out, query_cap, capability);
+	if (!MLX5_GET(flow_table_nic_cap, hca_cap, flow_table_properties_nic_receive.decap)) {
+		ret = -EOPNOTSUPP;
+		goto out;
+	}
+
+out:
+	kvfree(query_cap);
+	return ret;
+}
+
 int mlx5_esw_ipsec_vf_crypto_offload_set(struct mlx5_eswitch *esw, struct mlx5_vport *vport,
 					 bool enable)
 {
 	return esw_ipsec_vf_offload_set_bytype(esw, vport, enable,
 					       MLX5_ESW_VPORT_IPSEC_CRYPTO_OFFLOAD);
 }
+
+int mlx5_esw_ipsec_vf_packet_offload_set(struct mlx5_eswitch *esw, struct mlx5_vport *vport,
+					 bool enable)
+{
+	return esw_ipsec_vf_offload_set_bytype(esw, vport, enable,
+					       MLX5_ESW_VPORT_IPSEC_PACKET_OFFLOAD);
+}

drivers/net/ethernet/mellanox/mlx5/core/eswitch.c

@@ -834,7 +834,6 @@ static int mlx5_esw_vport_caps_get(struct mlx5_eswitch *esw, struct mlx5_vport *
 	vport->info.mig_enabled = MLX5_GET(cmd_hca_cap_2, hca_caps, migratable);
 
 	err = mlx5_esw_ipsec_vf_offload_get(esw->dev, vport);
-
 out_free:
 	kfree(query_ctx);
 	return err;
@@ -917,7 +916,8 @@ int mlx5_esw_vport_enable(struct mlx5_eswitch *esw, struct mlx5_vport *vport,
 	/* Sync with current vport context */
 	vport->enabled_events = enabled_events;
 	vport->enabled = true;
-	if (vport->vport != MLX5_VPORT_PF && vport->info.ipsec_crypto_enabled)
+	if (vport->vport != MLX5_VPORT_PF &&
+	    (vport->info.ipsec_crypto_enabled || vport->info.ipsec_packet_enabled))
 		esw->enabled_ipsec_vf_count++;
 
 	/* Esw manager is trusted by default. Host PF (vport 0) is trusted as well
@@ -975,7 +975,8 @@ void mlx5_esw_vport_disable(struct mlx5_eswitch *esw, struct mlx5_vport *vport)
 	    MLX5_CAP_GEN(esw->dev, vhca_resource_manager))
 		mlx5_esw_vport_vhca_id_clear(esw, vport_num);
 
-	if (vport->vport != MLX5_VPORT_PF && vport->info.ipsec_crypto_enabled)
+	if (vport->vport != MLX5_VPORT_PF &&
+	    (vport->info.ipsec_crypto_enabled || vport->info.ipsec_packet_enabled))
 		esw->enabled_ipsec_vf_count--;
 
 	/* We don't assume VFs will cleanup after themselves.

drivers/net/ethernet/mellanox/mlx5/core/eswitch.h

@@ -164,6 +164,7 @@ struct mlx5_vport_info {
 	u8                      roce_enabled: 1;
 	u8                      mig_enabled: 1;
 	u8                      ipsec_crypto_enabled: 1;
+	u8                      ipsec_packet_enabled: 1;
 };
 
 /* Vport context events */
@@ -565,6 +566,10 @@ int mlx5_devlink_port_fn_ipsec_crypto_get(struct devlink_port *port, bool *is_en
 					  struct netlink_ext_ack *extack);
 int mlx5_devlink_port_fn_ipsec_crypto_set(struct devlink_port *port, bool enable,
 					  struct netlink_ext_ack *extack);
+int mlx5_devlink_port_fn_ipsec_packet_get(struct devlink_port *port, bool *is_enabled,
+					  struct netlink_ext_ack *extack);
+int mlx5_devlink_port_fn_ipsec_packet_set(struct devlink_port *port, bool enable,
+					  struct netlink_ext_ack *extack);
 #endif /* CONFIG_XFRM_OFFLOAD */
 void *mlx5_eswitch_get_uplink_priv(struct mlx5_eswitch *esw, u8 rep_type);
 
@@ -872,6 +877,13 @@ int mlx5_esw_ipsec_vf_crypto_offload_supported(struct mlx5_core_dev *dev,
 					       u16 vport_num);
 int mlx5_esw_ipsec_vf_crypto_offload_set(struct mlx5_eswitch *esw, struct mlx5_vport *vport,
 					 bool enable);
+int mlx5_esw_ipsec_vf_packet_offload_set(struct mlx5_eswitch *esw, struct mlx5_vport *vport,
+					 bool enable);
+int mlx5_esw_ipsec_vf_packet_offload_supported(struct mlx5_core_dev *dev,
+					       u16 vport_num);
+void mlx5_esw_vport_ipsec_offload_enable(struct mlx5_eswitch *esw);
+void mlx5_esw_vport_ipsec_offload_disable(struct mlx5_eswitch *esw);
+
 #else  /* CONFIG_MLX5_ESWITCH */
 /* eswitch API stubs */
 static inline int  mlx5_eswitch_init(struct mlx5_core_dev *dev) { return 0; }

drivers/net/ethernet/mellanox/mlx5/core/eswitch_offloads.c

@@ -4451,4 +4451,88 @@ unlock:
 	mutex_unlock(&esw->state_lock);
 	return err;
 }
+
+int mlx5_devlink_port_fn_ipsec_packet_get(struct devlink_port *port, bool *is_enabled,
+					  struct netlink_ext_ack *extack)
+{
+	struct mlx5_eswitch *esw;
+	struct mlx5_vport *vport;
+	int err = 0;
+
+	esw = mlx5_devlink_eswitch_get(port->devlink);
+	if (IS_ERR(esw))
+		return PTR_ERR(esw);
+
+	if (!mlx5_esw_ipsec_vf_offload_supported(esw->dev)) {
+		NL_SET_ERR_MSG_MOD(extack, "Device doesn't support IPsec packet");
+		return -EOPNOTSUPP;
+	}
+
+	vport = mlx5_devlink_port_vport_get(port);
+
+	mutex_lock(&esw->state_lock);
+	if (!vport->enabled) {
+		err = -EOPNOTSUPP;
+		goto unlock;
+	}
+
+	*is_enabled = vport->info.ipsec_packet_enabled;
+unlock:
+	mutex_unlock(&esw->state_lock);
+	return err;
+}
+
+int mlx5_devlink_port_fn_ipsec_packet_set(struct devlink_port *port,
+					  bool enable,
+					  struct netlink_ext_ack *extack)
+{
+	struct mlx5_eswitch *esw;
+	struct mlx5_vport *vport;
+	u16 vport_num;
+	int err;
+
+	esw = mlx5_devlink_eswitch_get(port->devlink);
+	if (IS_ERR(esw))
+		return PTR_ERR(esw);
+
+	vport_num = mlx5_esw_devlink_port_index_to_vport_num(port->index);
+	err = mlx5_esw_ipsec_vf_packet_offload_supported(esw->dev, vport_num);
+	if (err) {
+		NL_SET_ERR_MSG_MOD(extack,
+				   "Device doesn't support IPsec packet mode");
+		return err;
+	}
+
+	vport = mlx5_devlink_port_vport_get(port);
+	mutex_lock(&esw->state_lock);
+	if (!vport->enabled) {
+		err = -EOPNOTSUPP;
+		NL_SET_ERR_MSG_MOD(extack, "Eswitch vport is disabled");
+		goto unlock;
+	}
+
+	if (vport->info.ipsec_packet_enabled == enable)
+		goto unlock;
+
+	if (!esw->enabled_ipsec_vf_count && esw->dev->num_ipsec_offloads) {
+		err = -EBUSY;
+		goto unlock;
+	}
+
+	err = mlx5_esw_ipsec_vf_packet_offload_set(esw, vport, enable);
+	if (err) {
+		NL_SET_ERR_MSG_MOD(extack,
+				   "Failed to set IPsec packet mode");
+		goto unlock;
+	}
+
+	vport->info.ipsec_packet_enabled = enable;
+	if (enable)
+		esw->enabled_ipsec_vf_count++;
+	else
+		esw->enabled_ipsec_vf_count--;
+unlock:
+	mutex_unlock(&esw->state_lock);
+	return err;
+}
 #endif /* CONFIG_XFRM_OFFLOAD */