Merge branch 'mlx5-misc-fixes-2025-06-10'

Mark Bloch says:

====================
mlx5 misc fixes 2025-06-10

This patchset includes misc fixes from the team for the mlx5 core
and Ethernet drivers.
====================

Link: https://patch.msgid.link/20250610151514.1094735-1-mbloch@nvidia.com
Signed-off-by: Jakub Kicinski <kuba@kernel.org>

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

@@ -43,7 +43,6 @@
 #include "en/fs_ethtool.h"
 
 #define LANES_UNKNOWN		 0
-#define MAX_LANES		 8
 
 void mlx5e_ethtool_get_drvinfo(struct mlx5e_priv *priv,
 			       struct ethtool_drvinfo *drvinfo)
@@ -1098,10 +1097,8 @@ static void get_link_properties(struct net_device *netdev,
 		speed = info->speed;
 		lanes = info->lanes;
 		duplex = DUPLEX_FULL;
-	} else if (data_rate_oper) {
+	} else if (data_rate_oper)
 		speed = 100 * data_rate_oper;
-		lanes = MAX_LANES;
-	}
 
 out:
 	link_ksettings->base.duplex = duplex;

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

@@ -2028,9 +2028,8 @@ mlx5e_tc_add_fdb_flow(struct mlx5e_priv *priv,
 	return err;
 }
 
-static bool mlx5_flow_has_geneve_opt(struct mlx5e_tc_flow *flow)
+static bool mlx5_flow_has_geneve_opt(struct mlx5_flow_spec *spec)
 {
-	struct mlx5_flow_spec *spec = &flow->attr->parse_attr->spec;
 	void *headers_v = MLX5_ADDR_OF(fte_match_param,
 				       spec->match_value,
 				       misc_parameters_3);
@@ -2069,7 +2068,7 @@ static void mlx5e_tc_del_fdb_flow(struct mlx5e_priv *priv,
 	}
 	complete_all(&flow->del_hw_done);
 
-	if (mlx5_flow_has_geneve_opt(flow))
+	if (mlx5_flow_has_geneve_opt(&attr->parse_attr->spec))
 		mlx5_geneve_tlv_option_del(priv->mdev->geneve);
 
 	if (flow->decap_route)
@@ -2574,12 +2573,13 @@ static int parse_tunnel_attr(struct mlx5e_priv *priv,
 
 		err = mlx5e_tc_tun_parse(filter_dev, priv, tmp_spec, f, match_level);
 		if (err) {
-			kvfree(tmp_spec);
 			NL_SET_ERR_MSG_MOD(extack, "Failed to parse tunnel attributes");
 			netdev_warn(priv->netdev, "Failed to parse tunnel attributes");
-			return err;
+		} else {
+			err = mlx5e_tc_set_attr_rx_tun(flow, tmp_spec);
 		}
-		err = mlx5e_tc_set_attr_rx_tun(flow, tmp_spec);
+		if (mlx5_flow_has_geneve_opt(tmp_spec))
+			mlx5_geneve_tlv_option_del(priv->mdev->geneve);
 		kvfree(tmp_spec);
 		if (err)
 			return err;

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

@@ -1295,12 +1295,15 @@ mlx5_eswitch_enable_pf_vf_vports(struct mlx5_eswitch *esw,
 		ret = mlx5_eswitch_load_pf_vf_vport(esw, MLX5_VPORT_ECPF, enabled_events);
 		if (ret)
 			goto ecpf_err;
-		if (mlx5_core_ec_sriov_enabled(esw->dev)) {
-			ret = mlx5_eswitch_load_ec_vf_vports(esw, esw->esw_funcs.num_ec_vfs,
-							     enabled_events);
-			if (ret)
-				goto ec_vf_err;
-		}
+	}
+
+	/* Enable ECVF vports */
+	if (mlx5_core_ec_sriov_enabled(esw->dev)) {
+		ret = mlx5_eswitch_load_ec_vf_vports(esw,
+						     esw->esw_funcs.num_ec_vfs,
+						     enabled_events);
+		if (ret)
+			goto ec_vf_err;
 	}
 
 	/* Enable VF vports */
@@ -1331,9 +1334,11 @@ void mlx5_eswitch_disable_pf_vf_vports(struct mlx5_eswitch *esw)
 {
 	mlx5_eswitch_unload_vf_vports(esw, esw->esw_funcs.num_vfs);
 
+	if (mlx5_core_ec_sriov_enabled(esw->dev))
+		mlx5_eswitch_unload_ec_vf_vports(esw,
+						 esw->esw_funcs.num_ec_vfs);
+
 	if (mlx5_ecpf_vport_exists(esw->dev)) {
-		if (mlx5_core_ec_sriov_enabled(esw->dev))
-			mlx5_eswitch_unload_ec_vf_vports(esw, esw->esw_funcs.num_vfs);
 		mlx5_eswitch_unload_pf_vf_vport(esw, MLX5_VPORT_ECPF);
 	}
 

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

@@ -2228,6 +2228,7 @@ try_add_to_existing_fg(struct mlx5_flow_table *ft,
 	struct mlx5_flow_handle *rule;
 	struct match_list *iter;
 	bool take_write = false;
+	bool try_again = false;
 	struct fs_fte *fte;
 	u64  version = 0;
 	int err;
@@ -2292,6 +2293,7 @@ try_add_to_existing_fg(struct mlx5_flow_table *ft,
 		nested_down_write_ref_node(&g->node, FS_LOCK_PARENT);
 
 		if (!g->node.active) {
+			try_again = true;
 			up_write_ref_node(&g->node, false);
 			continue;
 		}
@@ -2313,7 +2315,8 @@ try_add_to_existing_fg(struct mlx5_flow_table *ft,
 			tree_put_node(&fte->node, false);
 		return rule;
 	}
-	rule = ERR_PTR(-ENOENT);
+	err = try_again ? -EAGAIN : -ENOENT;
+	rule = ERR_PTR(err);
 out:
 	kmem_cache_free(steering->ftes_cache, fte);
 	return rule;

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

@@ -291,7 +291,7 @@ static void free_4k(struct mlx5_core_dev *dev, u64 addr, u32 function)
 static int alloc_system_page(struct mlx5_core_dev *dev, u32 function)
 {
 	struct device *device = mlx5_core_dma_dev(dev);
-	int nid = dev_to_node(device);
+	int nid = dev->priv.numa_node;
 	struct page *page;
 	u64 zero_addr = 1;
 	u64 addr;

drivers/net/ethernet/mellanox/mlx5/core/steering/hws/action.c

@@ -1370,8 +1370,8 @@ mlx5hws_action_create_dest_array(struct mlx5hws_context *ctx,
 	struct mlx5hws_cmd_set_fte_attr fte_attr = {0};
 	struct mlx5hws_cmd_forward_tbl *fw_island;
 	struct mlx5hws_action *action;
-	u32 i /*, packet_reformat_id*/;
-	int ret;
+	int ret, last_dest_idx = -1;
+	u32 i;
 
 	if (num_dest <= 1) {
 		mlx5hws_err(ctx, "Action must have multiple dests\n");
@@ -1401,11 +1401,8 @@ mlx5hws_action_create_dest_array(struct mlx5hws_context *ctx,
 			dest_list[i].destination_id = dests[i].dest->dest_obj.obj_id;
 			fte_attr.action_flags |= MLX5_FLOW_CONTEXT_ACTION_FWD_DEST;
 			fte_attr.ignore_flow_level = ignore_flow_level;
-			/* ToDo: In SW steering we have a handling of 'go to WIRE'
-			 * destination here by upper layer setting 'is_wire_ft' flag
-			 * if the destination is wire.
-			 * This is because uplink should be last dest in the list.
-			 */
+			if (dests[i].is_wire_ft)
+				last_dest_idx = i;
 			break;
 		case MLX5HWS_ACTION_TYP_VPORT:
 			dest_list[i].destination_type = MLX5_FLOW_DESTINATION_TYPE_VPORT;
@@ -1429,6 +1426,9 @@ mlx5hws_action_create_dest_array(struct mlx5hws_context *ctx,
 		}
 	}
 
+	if (last_dest_idx != -1)
+		swap(dest_list[last_dest_idx], dest_list[num_dest - 1]);
+
 	fte_attr.dests_num = num_dest;
 	fte_attr.dests = dest_list;
 

drivers/net/ethernet/mellanox/mlx5/core/steering/hws/definer.c

@@ -785,6 +785,9 @@ hws_definer_conv_outer(struct mlx5hws_definer_conv_data *cd,
 	HWS_SET_HDR(fc, match_param, IP_PROTOCOL_O,
 		    outer_headers.ip_protocol,
 		    eth_l3_outer.protocol_next_header);
+	HWS_SET_HDR(fc, match_param, IP_VERSION_O,
+		    outer_headers.ip_version,
+		    eth_l3_outer.ip_version);
 	HWS_SET_HDR(fc, match_param, IP_TTL_O,
 		    outer_headers.ttl_hoplimit,
 		    eth_l3_outer.time_to_live_hop_limit);

drivers/net/ethernet/mellanox/mlx5/core/steering/hws/fs_hws.c

@@ -966,6 +966,9 @@ static int mlx5_fs_fte_get_hws_actions(struct mlx5_flow_root_namespace *ns,
 			switch (attr->type) {
 			case MLX5_FLOW_DESTINATION_TYPE_FLOW_TABLE:
 				dest_action = mlx5_fs_get_dest_action_ft(fs_ctx, dst);
+				if (dst->dest_attr.ft->flags &
+				    MLX5_FLOW_TABLE_UPLINK_VPORT)
+					dest_actions[num_dest_actions].is_wire_ft = true;
 				break;
 			case MLX5_FLOW_DESTINATION_TYPE_FLOW_TABLE_NUM:
 				dest_action = mlx5_fs_get_dest_action_table_num(fs_ctx,
@@ -1357,6 +1360,7 @@ mlx5_cmd_hws_packet_reformat_alloc(struct mlx5_flow_root_namespace *ns,
 		pkt_reformat->fs_hws_action.pr_data = pr_data;
 	}
 
+	mutex_init(&pkt_reformat->fs_hws_action.lock);
 	pkt_reformat->owner = MLX5_FLOW_RESOURCE_OWNER_HWS;
 	pkt_reformat->fs_hws_action.hws_action = hws_action;
 	return 0;
@@ -1503,7 +1507,6 @@ static int mlx5_cmd_hws_modify_header_alloc(struct mlx5_flow_root_namespace *ns,
 		err = -ENOMEM;
 		goto release_mh;
 	}
-	mutex_init(&modify_hdr->fs_hws_action.lock);
 	modify_hdr->fs_hws_action.mh_data = mh_data;
 	modify_hdr->fs_hws_action.fs_pool = pool;
 	modify_hdr->owner = MLX5_FLOW_RESOURCE_OWNER_SW;

drivers/net/ethernet/mellanox/mlx5/core/steering/hws/mlx5hws.h

@@ -213,6 +213,7 @@ struct mlx5hws_action_dest_attr {
 	struct mlx5hws_action *dest;
 	/* Optional reformat action */
 	struct mlx5hws_action *reformat;
+	bool is_wire_ft;
 };
 
 /**