Merge tag 'mlx5-fixes-2022-12-28' of git://git.kernel.org/pub/scm/linux/kernel/git/saeed/linux

mlx5-fixes-2022-12-28

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

@@ -468,7 +468,7 @@ static int mlx5_devlink_enable_roce_validate(struct devlink *devlink, u32 id,
 	bool new_state = val.vbool;
 
 	if (new_state && !MLX5_CAP_GEN(dev, roce) &&
-	    !MLX5_CAP_GEN(dev, roce_rw_supported)) {
+	    !(MLX5_CAP_GEN(dev, roce_rw_supported) && MLX5_CAP_GEN_MAX(dev, roce))) {
 		NL_SET_ERR_MSG_MOD(extack, "Device doesn't support RoCE");
 		return -EOPNOTSUPP;
 	}
@@ -563,7 +563,7 @@ static int mlx5_devlink_eq_depth_validate(struct devlink *devlink, u32 id,
 					  union devlink_param_value val,
 					  struct netlink_ext_ack *extack)
 {
-	return (val.vu16 >= 64 && val.vu16 <= 4096) ? 0 : -EINVAL;
+	return (val.vu32 >= 64 && val.vu32 <= 4096) ? 0 : -EINVAL;
 }
 
 static const struct devlink_param mlx5_devlink_params[] = {

drivers/net/ethernet/mellanox/mlx5/core/en/reporter_rx.c

@@ -459,7 +459,11 @@ static int mlx5e_rx_reporter_diagnose(struct devlink_health_reporter *reporter,
 		goto unlock;
 
 	for (i = 0; i < priv->channels.num; i++) {
-		struct mlx5e_rq *rq = &priv->channels.c[i]->rq;
+		struct mlx5e_channel *c = priv->channels.c[i];
+		struct mlx5e_rq *rq;
+
+		rq = test_bit(MLX5E_CHANNEL_STATE_XSK, c->state) ?
+			&c->xskrq : &c->rq;
 
 		err = mlx5e_rx_reporter_build_diagnose_output(rq, fmsg);
 		if (err)

drivers/net/ethernet/mellanox/mlx5/core/en/tc_ct.c

@@ -2103,14 +2103,9 @@ mlx5_tc_ct_init_check_support(struct mlx5e_priv *priv,
 static void
 mlx5_ct_tc_create_dbgfs(struct mlx5_tc_ct_priv *ct_priv)
 {
-	bool is_fdb = ct_priv->ns_type == MLX5_FLOW_NAMESPACE_FDB;
 	struct mlx5_tc_ct_debugfs *ct_dbgfs = &ct_priv->debugfs;
-	char dirname[16] = {};
 
-	if (sscanf(dirname, "ct_%s", is_fdb ? "fdb" : "nic") < 0)
-		return;
-
-	ct_dbgfs->root = debugfs_create_dir(dirname, mlx5_debugfs_get_dev_root(ct_priv->dev));
+	ct_dbgfs->root = debugfs_create_dir("ct", mlx5_debugfs_get_dev_root(ct_priv->dev));
 	debugfs_create_atomic_t("offloaded", 0400, ct_dbgfs->root,
 				&ct_dbgfs->stats.offloaded);
 	debugfs_create_atomic_t("rx_dropped", 0400, ct_dbgfs->root,

drivers/net/ethernet/mellanox/mlx5/core/en/tc_tun_encap.c

@@ -222,7 +222,7 @@ void mlx5e_tc_encap_flows_del(struct mlx5e_priv *priv,
 	int err;
 
 	list_for_each_entry(flow, flow_list, tmp_list) {
-		if (!mlx5e_is_offloaded_flow(flow) || flow_flag_test(flow, SLOW))
+		if (!mlx5e_is_offloaded_flow(flow))
 			continue;
 
 		attr = mlx5e_tc_get_encap_attr(flow);
@@ -231,6 +231,13 @@ void mlx5e_tc_encap_flows_del(struct mlx5e_priv *priv,
 		esw_attr->dests[flow->tmp_entry_index].flags &= ~MLX5_ESW_DEST_ENCAP_VALID;
 		esw_attr->dests[flow->tmp_entry_index].pkt_reformat = NULL;
 
+		/* Clear pkt_reformat before checking slow path flag. Because
+		 * in next iteration, the same flow is already set slow path
+		 * flag, but still need to clear the pkt_reformat.
+		 */
+		if (flow_flag_test(flow, SLOW))
+			continue;
+
 		/* update from encap rule to slow path rule */
 		spec = &flow->attr->parse_attr->spec;
 		rule = mlx5e_tc_offload_to_slow_path(esw, flow, spec);

drivers/net/ethernet/mellanox/mlx5/core/en/tc_tun_geneve.c

@@ -273,6 +273,11 @@ static int mlx5e_tc_tun_parse_geneve_options(struct mlx5e_priv *priv,
 		 geneve_tlv_option_0_data, be32_to_cpu(opt_data_key));
 	MLX5_SET(fte_match_set_misc3, misc_3_c,
 		 geneve_tlv_option_0_data, be32_to_cpu(opt_data_mask));
+	if (MLX5_CAP_ESW_FLOWTABLE_FDB(priv->mdev,
+				       ft_field_support.geneve_tlv_option_0_exist)) {
+		MLX5_SET_TO_ONES(fte_match_set_misc, misc_c, geneve_tlv_option_0_exist);
+		MLX5_SET_TO_ONES(fte_match_set_misc, misc_v, geneve_tlv_option_0_exist);
+	}
 
 	spec->match_criteria_enable |= MLX5_MATCH_MISC_PARAMETERS_3;
 

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

@@ -1305,7 +1305,7 @@ static int mlx5e_alloc_xdpsq(struct mlx5e_channel *c,
 	sq->channel   = c;
 	sq->uar_map   = mdev->mlx5e_res.hw_objs.bfreg.map;
 	sq->min_inline_mode = params->tx_min_inline_mode;
-	sq->hw_mtu    = MLX5E_SW2HW_MTU(params, params->sw_mtu);
+	sq->hw_mtu    = MLX5E_SW2HW_MTU(params, params->sw_mtu) - ETH_FCS_LEN;
 	sq->xsk_pool  = xsk_pool;
 
 	sq->stats = sq->xsk_pool ?

drivers/net/ethernet/mellanox/mlx5/core/esw/acl/egress_lgcy.c

@@ -67,6 +67,7 @@ static void esw_acl_egress_lgcy_groups_destroy(struct mlx5_vport *vport)
 int esw_acl_egress_lgcy_setup(struct mlx5_eswitch *esw,
 			      struct mlx5_vport *vport)
 {
+	bool vst_mode_steering = esw_vst_mode_is_steering(esw);
 	struct mlx5_flow_destination drop_ctr_dst = {};
 	struct mlx5_flow_destination *dst = NULL;
 	struct mlx5_fc *drop_counter = NULL;
@@ -77,6 +78,7 @@ int esw_acl_egress_lgcy_setup(struct mlx5_eswitch *esw,
 	 */
 	int table_size = 2;
 	int dest_num = 0;
+	int actions_flag;
 	int err = 0;
 
 	if (vport->egress.legacy.drop_counter) {
@@ -119,8 +121,11 @@ int esw_acl_egress_lgcy_setup(struct mlx5_eswitch *esw,
 		  vport->vport, vport->info.vlan, vport->info.qos);
 
 	/* Allowed vlan rule */
+	actions_flag = MLX5_FLOW_CONTEXT_ACTION_ALLOW;
+	if (vst_mode_steering)
+		actions_flag |= MLX5_FLOW_CONTEXT_ACTION_VLAN_POP;
 	err = esw_egress_acl_vlan_create(esw, vport, NULL, vport->info.vlan,
-					 MLX5_FLOW_CONTEXT_ACTION_ALLOW);
+					 actions_flag);
 	if (err)
 		goto out;
 

drivers/net/ethernet/mellanox/mlx5/core/esw/acl/ingress_lgcy.c

@@ -139,11 +139,14 @@ static void esw_acl_ingress_lgcy_groups_destroy(struct mlx5_vport *vport)
 int esw_acl_ingress_lgcy_setup(struct mlx5_eswitch *esw,
 			       struct mlx5_vport *vport)
 {
+	bool vst_mode_steering = esw_vst_mode_is_steering(esw);
 	struct mlx5_flow_destination drop_ctr_dst = {};
 	struct mlx5_flow_destination *dst = NULL;
 	struct mlx5_flow_act flow_act = {};
 	struct mlx5_flow_spec *spec = NULL;
 	struct mlx5_fc *counter = NULL;
+	bool vst_check_cvlan = false;
+	bool vst_push_cvlan = false;
 	/* The ingress acl table contains 4 groups
 	 * (2 active rules at the same time -
 	 *      1 allow rule from one of the first 3 groups.
@@ -203,7 +206,26 @@ int esw_acl_ingress_lgcy_setup(struct mlx5_eswitch *esw,
 		goto out;
 	}
 
-	if (vport->info.vlan || vport->info.qos)
+	if ((vport->info.vlan || vport->info.qos)) {
+		if (vst_mode_steering)
+			vst_push_cvlan = true;
+		else if (!MLX5_CAP_ESW(esw->dev, vport_cvlan_insert_always))
+			vst_check_cvlan = true;
+	}
+
+	if (vst_check_cvlan || vport->info.spoofchk)
+		spec->match_criteria_enable = MLX5_MATCH_OUTER_HEADERS;
+
+	/* Create ingress allow rule */
+	flow_act.action = MLX5_FLOW_CONTEXT_ACTION_ALLOW;
+	if (vst_push_cvlan) {
+		flow_act.action |= MLX5_FLOW_CONTEXT_ACTION_VLAN_PUSH;
+		flow_act.vlan[0].prio = vport->info.qos;
+		flow_act.vlan[0].vid = vport->info.vlan;
+		flow_act.vlan[0].ethtype = ETH_P_8021Q;
+	}
+
+	if (vst_check_cvlan)
 		MLX5_SET_TO_ONES(fte_match_param, spec->match_criteria,
 				 outer_headers.cvlan_tag);
 
@@ -218,9 +240,6 @@ int esw_acl_ingress_lgcy_setup(struct mlx5_eswitch *esw,
 		ether_addr_copy(smac_v, vport->info.mac);
 	}
 
-	/* Create ingress allow rule */
-	spec->match_criteria_enable = MLX5_MATCH_OUTER_HEADERS;
-	flow_act.action = MLX5_FLOW_CONTEXT_ACTION_ALLOW;
 	vport->ingress.allow_rule = mlx5_add_flow_rules(vport->ingress.acl, spec,
 							&flow_act, NULL, 0);
 	if (IS_ERR(vport->ingress.allow_rule)) {
@@ -232,6 +251,9 @@ int esw_acl_ingress_lgcy_setup(struct mlx5_eswitch *esw,
 		goto out;
 	}
 
+	if (!vst_check_cvlan && !vport->info.spoofchk)
+		goto out;
+
 	memset(&flow_act, 0, sizeof(flow_act));
 	flow_act.action = MLX5_FLOW_CONTEXT_ACTION_DROP;
 	/* Attach drop flow counter */
@@ -257,7 +279,8 @@ int esw_acl_ingress_lgcy_setup(struct mlx5_eswitch *esw,
 	return 0;
 
 out:
-	esw_acl_ingress_lgcy_cleanup(esw, vport);
+	if (err)
+		esw_acl_ingress_lgcy_cleanup(esw, vport);
 	kvfree(spec);
 	return err;
 }

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

@@ -161,10 +161,17 @@ static int modify_esw_vport_cvlan(struct mlx5_core_dev *dev, u16 vport,
 			 esw_vport_context.vport_cvlan_strip, 1);
 
 	if (set_flags & SET_VLAN_INSERT) {
-		/* insert only if no vlan in packet */
-		MLX5_SET(modify_esw_vport_context_in, in,
-			 esw_vport_context.vport_cvlan_insert, 1);
-
+		if (MLX5_CAP_ESW(dev, vport_cvlan_insert_always)) {
+			/* insert either if vlan exist in packet or not */
+			MLX5_SET(modify_esw_vport_context_in, in,
+				 esw_vport_context.vport_cvlan_insert,
+				 MLX5_VPORT_CVLAN_INSERT_ALWAYS);
+		} else {
+			/* insert only if no vlan in packet */
+			MLX5_SET(modify_esw_vport_context_in, in,
+				 esw_vport_context.vport_cvlan_insert,
+				 MLX5_VPORT_CVLAN_INSERT_WHEN_NO_CVLAN);
+		}
 		MLX5_SET(modify_esw_vport_context_in, in,
 			 esw_vport_context.cvlan_pcp, qos);
 		MLX5_SET(modify_esw_vport_context_in, in,
@@ -809,6 +816,7 @@ static int mlx5_esw_vport_caps_get(struct mlx5_eswitch *esw, struct mlx5_vport *
 
 static int esw_vport_setup(struct mlx5_eswitch *esw, struct mlx5_vport *vport)
 {
+	bool vst_mode_steering = esw_vst_mode_is_steering(esw);
 	u16 vport_num = vport->vport;
 	int flags;
 	int err;
@@ -839,8 +847,9 @@ static int esw_vport_setup(struct mlx5_eswitch *esw, struct mlx5_vport *vport)
 
 	flags = (vport->info.vlan || vport->info.qos) ?
 		SET_VLAN_STRIP | SET_VLAN_INSERT : 0;
-	modify_esw_vport_cvlan(esw->dev, vport_num, vport->info.vlan,
-			       vport->info.qos, flags);
+	if (esw->mode == MLX5_ESWITCH_OFFLOADS || !vst_mode_steering)
+		modify_esw_vport_cvlan(esw->dev, vport_num, vport->info.vlan,
+				       vport->info.qos, flags);
 
 	return 0;
 
@@ -1848,6 +1857,7 @@ int __mlx5_eswitch_set_vport_vlan(struct mlx5_eswitch *esw,
 				  u16 vport, u16 vlan, u8 qos, u8 set_flags)
 {
 	struct mlx5_vport *evport = mlx5_eswitch_get_vport(esw, vport);
+	bool vst_mode_steering = esw_vst_mode_is_steering(esw);
 	int err = 0;
 
 	if (IS_ERR(evport))
@@ -1855,9 +1865,11 @@ int __mlx5_eswitch_set_vport_vlan(struct mlx5_eswitch *esw,
 	if (vlan > 4095 || qos > 7)
 		return -EINVAL;
 
-	err = modify_esw_vport_cvlan(esw->dev, vport, vlan, qos, set_flags);
-	if (err)
-		return err;
+	if (esw->mode == MLX5_ESWITCH_OFFLOADS || !vst_mode_steering) {
+		err = modify_esw_vport_cvlan(esw->dev, vport, vlan, qos, set_flags);
+		if (err)
+			return err;
+	}
 
 	evport->info.vlan = vlan;
 	evport->info.qos = qos;

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

@@ -527,6 +527,12 @@ int mlx5_eswitch_del_vlan_action(struct mlx5_eswitch *esw,
 int __mlx5_eswitch_set_vport_vlan(struct mlx5_eswitch *esw,
 				  u16 vport, u16 vlan, u8 qos, u8 set_flags);
 
+static inline bool esw_vst_mode_is_steering(struct mlx5_eswitch *esw)
+{
+	return (MLX5_CAP_ESW_EGRESS_ACL(esw->dev, pop_vlan) &&
+		MLX5_CAP_ESW_INGRESS_ACL(esw->dev, push_vlan));
+}
+
 static inline bool mlx5_eswitch_vlan_actions_supported(struct mlx5_core_dev *dev,
 						       u8 vlan_depth)
 {

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

@@ -674,6 +674,12 @@ static void mlx5_fw_fatal_reporter_err_work(struct work_struct *work)
 	dev = container_of(priv, struct mlx5_core_dev, priv);
 	devlink = priv_to_devlink(dev);
 
+	mutex_lock(&dev->intf_state_mutex);
+	if (test_bit(MLX5_DROP_NEW_HEALTH_WORK, &health->flags)) {
+		mlx5_core_err(dev, "health works are not permitted at this stage\n");
+		return;
+	}
+	mutex_unlock(&dev->intf_state_mutex);
 	enter_error_state(dev, false);
 	if (IS_ERR_OR_NULL(health->fw_fatal_reporter)) {
 		devl_lock(devlink);

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

@@ -71,6 +71,10 @@ static void mlx5i_build_nic_params(struct mlx5_core_dev *mdev,
 	params->packet_merge.type = MLX5E_PACKET_MERGE_NONE;
 	params->hard_mtu = MLX5_IB_GRH_BYTES + MLX5_IPOIB_HARD_LEN;
 	params->tunneled_offload_en = false;
+
+	/* CQE compression is not supported for IPoIB */
+	params->rx_cqe_compress_def = false;
+	MLX5E_SET_PFLAG(params, MLX5E_PFLAG_RX_CQE_COMPRESS, params->rx_cqe_compress_def);
 }
 
 /* Called directly after IPoIB netdevice was created to initialize SW structs */

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

@@ -228,6 +228,7 @@ static void mlx5_ldev_free(struct kref *ref)
 	if (ldev->nb.notifier_call)
 		unregister_netdevice_notifier_net(&init_net, &ldev->nb);
 	mlx5_lag_mp_cleanup(ldev);
+	cancel_delayed_work_sync(&ldev->bond_work);
 	destroy_workqueue(ldev->wq);
 	mlx5_lag_mpesw_cleanup(ldev);
 	mutex_destroy(&ldev->lock);

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

@@ -613,7 +613,7 @@ static int handle_hca_cap(struct mlx5_core_dev *dev, void *set_ctx)
 		MLX5_SET(cmd_hca_cap, set_hca_cap, num_total_dynamic_vf_msix,
 			 MLX5_CAP_GEN_MAX(dev, num_total_dynamic_vf_msix));
 
-	if (MLX5_CAP_GEN(dev, roce_rw_supported))
+	if (MLX5_CAP_GEN(dev, roce_rw_supported) && MLX5_CAP_GEN_MAX(dev, roce))
 		MLX5_SET(cmd_hca_cap, set_hca_cap, roce,
 			 mlx5_is_roce_on(dev));
 
@@ -1050,6 +1050,8 @@ static int mlx5_init_once(struct mlx5_core_dev *dev)
 err_tables_cleanup:
 	mlx5_geneve_destroy(dev->geneve);
 	mlx5_vxlan_destroy(dev->vxlan);
+	mlx5_cleanup_clock(dev);
+	mlx5_cleanup_reserved_gids(dev);
 	mlx5_cq_debugfs_cleanup(dev);
 	mlx5_fw_reset_cleanup(dev);
 err_events_cleanup:

include/linux/mlx5/device.h

@@ -1090,6 +1090,11 @@ enum {
 	MLX5_VPORT_ADMIN_STATE_AUTO  = 0x2,
 };
 
+enum {
+	MLX5_VPORT_CVLAN_INSERT_WHEN_NO_CVLAN  = 0x1,
+	MLX5_VPORT_CVLAN_INSERT_ALWAYS         = 0x3,
+};
+
 enum {
 	MLX5_L3_PROT_TYPE_IPV4		= 0,
 	MLX5_L3_PROT_TYPE_IPV6		= 1,

include/linux/mlx5/mlx5_ifc.h

@@ -913,7 +913,8 @@ struct mlx5_ifc_e_switch_cap_bits {
 	u8         vport_svlan_insert[0x1];
 	u8         vport_cvlan_insert_if_not_exist[0x1];
 	u8         vport_cvlan_insert_overwrite[0x1];
-	u8         reserved_at_5[0x2];
+	u8         reserved_at_5[0x1];
+	u8         vport_cvlan_insert_always[0x1];
 	u8         esw_shared_ingress_acl[0x1];
 	u8         esw_uplink_ingress_acl[0x1];
 	u8         root_ft_on_other_esw[0x1];