Merge tag 'mlx5-fixes-2021-05-18' of git://git.kernel.org/pub/scm/linux/kernel/git/saeed/linux

Saeed Mahameed says:

====================
mlx5 fixes 2021-05-18

This series introduces some fixes to mlx5 driver.

Please pull and let me know if there is any problem.
====================
Signed-off-by: David S. Miller <davem@davemloft.net>

drivers/infiniband/hw/mlx5/mr.c

@@ -743,10 +743,10 @@ int mlx5_mr_cache_init(struct mlx5_ib_dev *dev)
 		ent->xlt = (1 << ent->order) * sizeof(struct mlx5_mtt) /
 			   MLX5_IB_UMR_OCTOWORD;
 		ent->access_mode = MLX5_MKC_ACCESS_MODE_MTT;
-		if ((dev->mdev->profile->mask & MLX5_PROF_MASK_MR_CACHE) &&
+		if ((dev->mdev->profile.mask & MLX5_PROF_MASK_MR_CACHE) &&
 		    !dev->is_rep && mlx5_core_is_pf(dev->mdev) &&
 		    mlx5_ib_can_load_pas_with_umr(dev, 0))
-			ent->limit = dev->mdev->profile->mr_cache[i].limit;
+			ent->limit = dev->mdev->profile.mr_cache[i].limit;
 		else
 			ent->limit = 0;
 		spin_lock_irq(&ent->lock);

drivers/net/ethernet/mellanox/mlx5/core/en/rep/bond.c

@@ -223,6 +223,8 @@ static void mlx5e_rep_changelowerstate_event(struct net_device *netdev, void *pt
 	rpriv = priv->ppriv;
 	fwd_vport_num = rpriv->rep->vport;
 	lag_dev = netdev_master_upper_dev_get(netdev);
+	if (!lag_dev)
+		return;
 
 	netdev_dbg(netdev, "lag_dev(%s)'s slave vport(%d) is txable(%d)\n",
 		   lag_dev->name, fwd_vport_num, net_lag_port_dev_txable(netdev));

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

@@ -1505,7 +1505,7 @@ mlx5e_init_fib_work_ipv4(struct mlx5e_priv *priv,
 
 	fen_info = container_of(info, struct fib_entry_notifier_info, info);
 	fib_dev = fib_info_nh(fen_info->fi, 0)->fib_nh_dev;
-	if (fib_dev->netdev_ops != &mlx5e_netdev_ops ||
+	if (!fib_dev || fib_dev->netdev_ops != &mlx5e_netdev_ops ||
 	    fen_info->dst_len != 32)
 		return NULL;
 

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

@@ -35,6 +35,7 @@
 #include <linux/ipv6.h>
 #include <linux/tcp.h>
 #include <linux/mlx5/fs.h>
+#include <linux/mlx5/mpfs.h>
 #include "en.h"
 #include "en_rep.h"
 #include "lib/mpfs.h"

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

@@ -889,10 +889,13 @@ int mlx5e_open_rq(struct mlx5e_params *params, struct mlx5e_rq_param *param,
 void mlx5e_activate_rq(struct mlx5e_rq *rq)
 {
 	set_bit(MLX5E_RQ_STATE_ENABLED, &rq->state);
-	if (rq->icosq)
+	if (rq->icosq) {
 		mlx5e_trigger_irq(rq->icosq);
-	else
+	} else {
+		local_bh_disable();
 		napi_schedule(rq->cq.napi);
+		local_bh_enable();
+	}
 }
 
 void mlx5e_deactivate_rq(struct mlx5e_rq *rq)
@@ -2697,7 +2700,7 @@ static int mlx5e_update_netdev_queues(struct mlx5e_priv *priv)
 	int err;
 
 	old_num_txqs = netdev->real_num_tx_queues;
-	old_ntc = netdev->num_tc;
+	old_ntc = netdev->num_tc ? : 1;
 
 	nch = priv->channels.params.num_channels;
 	ntc = priv->channels.params.num_tc;
@@ -5229,6 +5232,11 @@ static void mlx5e_update_features(struct net_device *netdev)
 	rtnl_unlock();
 }
 
+static void mlx5e_reset_channels(struct net_device *netdev)
+{
+	netdev_reset_tc(netdev);
+}
+
 int mlx5e_attach_netdev(struct mlx5e_priv *priv)
 {
 	const bool take_rtnl = priv->netdev->reg_state == NETREG_REGISTERED;
@@ -5283,6 +5291,7 @@ int mlx5e_attach_netdev(struct mlx5e_priv *priv)
 	profile->cleanup_tx(priv);
 
 out:
+	mlx5e_reset_channels(priv->netdev);
 	set_bit(MLX5E_STATE_DESTROYING, &priv->state);
 	cancel_work_sync(&priv->update_stats_work);
 	return err;
@@ -5300,6 +5309,7 @@ void mlx5e_detach_netdev(struct mlx5e_priv *priv)
 
 	profile->cleanup_rx(priv);
 	profile->cleanup_tx(priv);
+	mlx5e_reset_channels(priv->netdev);
 	cancel_work_sync(&priv->update_stats_work);
 }
 

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

@@ -1322,10 +1322,10 @@ mlx5e_tc_add_fdb_flow(struct mlx5e_priv *priv,
 		      struct netlink_ext_ack *extack)
 {
 	struct mlx5_eswitch *esw = priv->mdev->priv.eswitch;
-	struct net_device *out_dev, *encap_dev = NULL;
 	struct mlx5e_tc_flow_parse_attr *parse_attr;
 	struct mlx5_flow_attr *attr = flow->attr;
 	bool vf_tun = false, encap_valid = true;
+	struct net_device *encap_dev = NULL;
 	struct mlx5_esw_flow_attr *esw_attr;
 	struct mlx5_fc *counter = NULL;
 	struct mlx5e_rep_priv *rpriv;
@@ -1371,16 +1371,22 @@ mlx5e_tc_add_fdb_flow(struct mlx5e_priv *priv,
 	esw_attr = attr->esw_attr;
 
 	for (out_index = 0; out_index < MLX5_MAX_FLOW_FWD_VPORTS; out_index++) {
+		struct net_device *out_dev;
 		int mirred_ifindex;
 
 		if (!(esw_attr->dests[out_index].flags & MLX5_ESW_DEST_ENCAP))
 			continue;
 
 		mirred_ifindex = parse_attr->mirred_ifindex[out_index];
-		out_dev = __dev_get_by_index(dev_net(priv->netdev),
-					     mirred_ifindex);
+		out_dev = dev_get_by_index(dev_net(priv->netdev), mirred_ifindex);
+		if (!out_dev) {
+			NL_SET_ERR_MSG_MOD(extack, "Requested mirred device not found");
+			err = -ENODEV;
+			goto err_out;
+		}
 		err = mlx5e_attach_encap(priv, flow, out_dev, out_index,
 					 extack, &encap_dev, &encap_valid);
+		dev_put(out_dev);
 		if (err)
 			goto err_out;
 
@@ -1393,6 +1399,12 @@ mlx5e_tc_add_fdb_flow(struct mlx5e_priv *priv,
 		esw_attr->dests[out_index].mdev = out_priv->mdev;
 	}
 
+	if (vf_tun && esw_attr->out_count > 1) {
+		NL_SET_ERR_MSG_MOD(extack, "VF tunnel encap with mirroring is not supported");
+		err = -EOPNOTSUPP;
+		goto err_out;
+	}
+
 	err = mlx5_eswitch_add_vlan_action(esw, attr);
 	if (err)
 		goto err_out;
@@ -3526,8 +3538,12 @@ static int add_vlan_push_action(struct mlx5e_priv *priv,
 	if (err)
 		return err;
 
-	*out_dev = dev_get_by_index_rcu(dev_net(vlan_dev),
-					dev_get_iflink(vlan_dev));
+	rcu_read_lock();
+	*out_dev = dev_get_by_index_rcu(dev_net(vlan_dev), dev_get_iflink(vlan_dev));
+	rcu_read_unlock();
+	if (!*out_dev)
+		return -ENODEV;
+
 	if (is_vlan_dev(*out_dev))
 		err = add_vlan_push_action(priv, attr, out_dev, action);
 

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

@@ -35,6 +35,7 @@
 #include <linux/mlx5/mlx5_ifc.h>
 #include <linux/mlx5/vport.h>
 #include <linux/mlx5/fs.h>
+#include <linux/mlx5/mpfs.h>
 #include "esw/acl/lgcy.h"
 #include "esw/legacy.h"
 #include "mlx5_core.h"

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

@@ -65,7 +65,7 @@ mlx5_eswitch_termtbl_create(struct mlx5_core_dev *dev,
 {
 	struct mlx5_flow_table_attr ft_attr = {};
 	struct mlx5_flow_namespace *root_ns;
-	int err;
+	int err, err2;
 
 	root_ns = mlx5_get_flow_namespace(dev, MLX5_FLOW_NAMESPACE_FDB);
 	if (!root_ns) {
@@ -76,33 +76,34 @@ mlx5_eswitch_termtbl_create(struct mlx5_core_dev *dev,
 	/* As this is the terminating action then the termination table is the
 	 * same prio as the slow path
 	 */
-	ft_attr.flags = MLX5_FLOW_TABLE_TERMINATION |
+	ft_attr.flags = MLX5_FLOW_TABLE_TERMINATION | MLX5_FLOW_TABLE_UNMANAGED |
 			MLX5_FLOW_TABLE_TUNNEL_EN_REFORMAT;
-	ft_attr.prio = FDB_SLOW_PATH;
+	ft_attr.prio = FDB_TC_OFFLOAD;
 	ft_attr.max_fte = 1;
+	ft_attr.level = 1;
 	ft_attr.autogroup.max_num_groups = 1;
 	tt->termtbl = mlx5_create_auto_grouped_flow_table(root_ns, &ft_attr);
 	if (IS_ERR(tt->termtbl)) {
-		esw_warn(dev, "Failed to create termination table (error %d)\n",
-			 IS_ERR(tt->termtbl));
-		return -EOPNOTSUPP;
+		err = PTR_ERR(tt->termtbl);
+		esw_warn(dev, "Failed to create termination table, err %pe\n", tt->termtbl);
+		return err;
 	}
 
 	tt->rule = mlx5_add_flow_rules(tt->termtbl, NULL, flow_act,
 				       &tt->dest, 1);
 	if (IS_ERR(tt->rule)) {
-		esw_warn(dev, "Failed to create termination table rule (error %d)\n",
-			 IS_ERR(tt->rule));
+		err = PTR_ERR(tt->rule);
+		esw_warn(dev, "Failed to create termination table rule, err %pe\n", tt->rule);
 		goto add_flow_err;
 	}
 	return 0;
 
 add_flow_err:
-	err = mlx5_destroy_flow_table(tt->termtbl);
-	if (err)
-		esw_warn(dev, "Failed to destroy termination table\n");
+	err2 = mlx5_destroy_flow_table(tt->termtbl);
+	if (err2)
+		esw_warn(dev, "Failed to destroy termination table, err %d\n", err2);
 
-	return -EOPNOTSUPP;
+	return err;
 }
 
 static struct mlx5_termtbl_handle *
@@ -172,19 +173,6 @@ mlx5_eswitch_termtbl_put(struct mlx5_eswitch *esw,
 	}
 }
 
-static bool mlx5_eswitch_termtbl_is_encap_reformat(struct mlx5_pkt_reformat *rt)
-{
-	switch (rt->reformat_type) {
-	case MLX5_REFORMAT_TYPE_L2_TO_VXLAN:
-	case MLX5_REFORMAT_TYPE_L2_TO_NVGRE:
-	case MLX5_REFORMAT_TYPE_L2_TO_L2_TUNNEL:
-	case MLX5_REFORMAT_TYPE_L2_TO_L3_TUNNEL:
-		return true;
-	default:
-		return false;
-	}
-}
-
 static void
 mlx5_eswitch_termtbl_actions_move(struct mlx5_flow_act *src,
 				  struct mlx5_flow_act *dst)
@@ -202,14 +190,6 @@ mlx5_eswitch_termtbl_actions_move(struct mlx5_flow_act *src,
 			memset(&src->vlan[1], 0, sizeof(src->vlan[1]));
 		}
 	}
-
-	if (src->action & MLX5_FLOW_CONTEXT_ACTION_PACKET_REFORMAT &&
-	    mlx5_eswitch_termtbl_is_encap_reformat(src->pkt_reformat)) {
-		src->action &= ~MLX5_FLOW_CONTEXT_ACTION_PACKET_REFORMAT;
-		dst->action |= MLX5_FLOW_CONTEXT_ACTION_PACKET_REFORMAT;
-		dst->pkt_reformat = src->pkt_reformat;
-		src->pkt_reformat = NULL;
-	}
 }
 
 static bool mlx5_eswitch_offload_is_uplink_port(const struct mlx5_eswitch *esw,
@@ -238,6 +218,7 @@ mlx5_eswitch_termtbl_required(struct mlx5_eswitch *esw,
 	int i;
 
 	if (!MLX5_CAP_ESW_FLOWTABLE_FDB(esw->dev, termination_table) ||
+	    !MLX5_CAP_ESW_FLOWTABLE_FDB(esw->dev, ignore_flow_level) ||
 	    attr->flags & MLX5_ESW_ATTR_FLAG_SLOW_PATH ||
 	    !mlx5_eswitch_offload_is_uplink_port(esw, spec))
 		return false;
@@ -279,12 +260,19 @@ mlx5_eswitch_add_termtbl_rule(struct mlx5_eswitch *esw,
 		if (dest[i].type != MLX5_FLOW_DESTINATION_TYPE_VPORT)
 			continue;
 
+		if (attr->dests[num_vport_dests].flags & MLX5_ESW_DEST_ENCAP) {
+			term_tbl_act.action |= MLX5_FLOW_CONTEXT_ACTION_PACKET_REFORMAT;
+			term_tbl_act.pkt_reformat = attr->dests[num_vport_dests].pkt_reformat;
+		} else {
+			term_tbl_act.action &= ~MLX5_FLOW_CONTEXT_ACTION_PACKET_REFORMAT;
+			term_tbl_act.pkt_reformat = NULL;
+		}
+
 		/* get the terminating table for the action list */
 		tt = mlx5_eswitch_termtbl_get_create(esw, &term_tbl_act,
 						     &dest[i], attr);
 		if (IS_ERR(tt)) {
-			esw_warn(esw->dev, "Failed to get termination table (error %d)\n",
-				 IS_ERR(tt));
+			esw_warn(esw->dev, "Failed to get termination table, err %pe\n", tt);
 			goto revert_changes;
 		}
 		attr->dests[num_vport_dests].termtbl = tt;
@@ -301,6 +289,9 @@ mlx5_eswitch_add_termtbl_rule(struct mlx5_eswitch *esw,
 		goto revert_changes;
 
 	/* create the FTE */
+	flow_act->action &= ~MLX5_FLOW_CONTEXT_ACTION_PACKET_REFORMAT;
+	flow_act->pkt_reformat = NULL;
+	flow_act->flags |= FLOW_ACT_IGNORE_FLOW_LEVEL;
 	rule = mlx5_add_flow_rules(fdb, spec, flow_act, dest, num_dest);
 	if (IS_ERR(rule))
 		goto revert_changes;

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

@@ -307,6 +307,11 @@ int mlx5_lag_mp_init(struct mlx5_lag *ldev)
 	struct lag_mp *mp = &ldev->lag_mp;
 	int err;
 
+	/* always clear mfi, as it might become stale when a route delete event
+	 * has been missed
+	 */
+	mp->mfi = NULL;
+
 	if (mp->fib_nb.notifier_call)
 		return 0;
 
@@ -335,4 +340,5 @@ void mlx5_lag_mp_cleanup(struct mlx5_lag *ldev)
 	unregister_fib_notifier(&init_net, &mp->fib_nb);
 	destroy_workqueue(mp->wq);
 	mp->fib_nb.notifier_call = NULL;
+	mp->mfi = NULL;
 }

drivers/net/ethernet/mellanox/mlx5/core/lib/mpfs.c

@@ -33,6 +33,7 @@
 #include <linux/etherdevice.h>
 #include <linux/mlx5/driver.h>
 #include <linux/mlx5/mlx5_ifc.h>
+#include <linux/mlx5/mpfs.h>
 #include <linux/mlx5/eswitch.h>
 #include "mlx5_core.h"
 #include "lib/mpfs.h"
@@ -175,6 +176,7 @@ int mlx5_mpfs_add_mac(struct mlx5_core_dev *dev, u8 *mac)
 	mutex_unlock(&mpfs->lock);
 	return err;
 }
+EXPORT_SYMBOL(mlx5_mpfs_add_mac);
 
 int mlx5_mpfs_del_mac(struct mlx5_core_dev *dev, u8 *mac)
 {
@@ -206,3 +208,4 @@ int mlx5_mpfs_del_mac(struct mlx5_core_dev *dev, u8 *mac)
 	mutex_unlock(&mpfs->lock);
 	return err;
 }
+EXPORT_SYMBOL(mlx5_mpfs_del_mac);

drivers/net/ethernet/mellanox/mlx5/core/lib/mpfs.h

@@ -84,12 +84,9 @@ struct l2addr_node {
 #ifdef CONFIG_MLX5_MPFS
 int  mlx5_mpfs_init(struct mlx5_core_dev *dev);
 void mlx5_mpfs_cleanup(struct mlx5_core_dev *dev);
-int  mlx5_mpfs_add_mac(struct mlx5_core_dev *dev, u8 *mac);
-int  mlx5_mpfs_del_mac(struct mlx5_core_dev *dev, u8 *mac);
 #else /* #ifndef CONFIG_MLX5_MPFS */
 static inline int  mlx5_mpfs_init(struct mlx5_core_dev *dev) { return 0; }
 static inline void mlx5_mpfs_cleanup(struct mlx5_core_dev *dev) {}
-static inline int  mlx5_mpfs_add_mac(struct mlx5_core_dev *dev, u8 *mac) { return 0; }
-static inline int  mlx5_mpfs_del_mac(struct mlx5_core_dev *dev, u8 *mac) { return 0; }
 #endif
+
 #endif

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

@@ -503,7 +503,7 @@ static int handle_hca_cap_odp(struct mlx5_core_dev *dev, void *set_ctx)
 
 static int handle_hca_cap(struct mlx5_core_dev *dev, void *set_ctx)
 {
-	struct mlx5_profile *prof = dev->profile;
+	struct mlx5_profile *prof = &dev->profile;
 	void *set_hca_cap;
 	int err;
 
@@ -524,11 +524,11 @@ static int handle_hca_cap(struct mlx5_core_dev *dev, void *set_ctx)
 		 to_fw_pkey_sz(dev, 128));
 
 	/* Check log_max_qp from HCA caps to set in current profile */
-	if (MLX5_CAP_GEN_MAX(dev, log_max_qp) < profile[prof_sel].log_max_qp) {
+	if (MLX5_CAP_GEN_MAX(dev, log_max_qp) < prof->log_max_qp) {
 		mlx5_core_warn(dev, "log_max_qp value in current profile is %d, changing it to HCA capability limit (%d)\n",
-			       profile[prof_sel].log_max_qp,
+			       prof->log_max_qp,
 			       MLX5_CAP_GEN_MAX(dev, log_max_qp));
-		profile[prof_sel].log_max_qp = MLX5_CAP_GEN_MAX(dev, log_max_qp);
+		prof->log_max_qp = MLX5_CAP_GEN_MAX(dev, log_max_qp);
 	}
 	if (prof->mask & MLX5_PROF_MASK_QP_SIZE)
 		MLX5_SET(cmd_hca_cap, set_hca_cap, log_max_qp,
@@ -1381,8 +1381,7 @@ int mlx5_mdev_init(struct mlx5_core_dev *dev, int profile_idx)
 	struct mlx5_priv *priv = &dev->priv;
 	int err;
 
-	dev->profile = &profile[profile_idx];
-
+	memcpy(&dev->profile, &profile[profile_idx], sizeof(dev->profile));
 	INIT_LIST_HEAD(&priv->ctx_list);
 	spin_lock_init(&priv->ctx_lock);
 	mutex_init(&dev->intf_state_mutex);

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

@@ -95,9 +95,10 @@ int mlx5_get_default_msix_vec_count(struct mlx5_core_dev *dev, int num_vfs)
 int mlx5_set_msix_vec_count(struct mlx5_core_dev *dev, int function_id,
 			    int msix_vec_count)
 {
-	int sz = MLX5_ST_SZ_BYTES(set_hca_cap_in);
+	int query_sz = MLX5_ST_SZ_BYTES(query_hca_cap_out);
+	int set_sz = MLX5_ST_SZ_BYTES(set_hca_cap_in);
+	void *hca_cap = NULL, *query_cap = NULL, *cap;
 	int num_vf_msix, min_msix, max_msix;
-	void *hca_cap, *cap;
 	int ret;
 
 	num_vf_msix = MLX5_CAP_GEN_MAX(dev, num_total_dynamic_vf_msix);
@@ -116,11 +117,20 @@ int mlx5_set_msix_vec_count(struct mlx5_core_dev *dev, int function_id,
 	if (msix_vec_count > max_msix)
 		return -EOVERFLOW;
 
-	hca_cap = kzalloc(sz, GFP_KERNEL);
-	if (!hca_cap)
-		return -ENOMEM;
+	query_cap = kzalloc(query_sz, GFP_KERNEL);
+	hca_cap = kzalloc(set_sz, GFP_KERNEL);
+	if (!hca_cap || !query_cap) {
+		ret = -ENOMEM;
+		goto out;
+	}
+
+	ret = mlx5_vport_get_other_func_cap(dev, function_id, query_cap);
+	if (ret)
+		goto out;
 
 	cap = MLX5_ADDR_OF(set_hca_cap_in, hca_cap, capability);
+	memcpy(cap, MLX5_ADDR_OF(query_hca_cap_out, query_cap, capability),
+	       MLX5_UN_SZ_BYTES(hca_cap_union));
 	MLX5_SET(cmd_hca_cap, cap, dynamic_msix_table_size, msix_vec_count);
 
 	MLX5_SET(set_hca_cap_in, hca_cap, opcode, MLX5_CMD_OP_SET_HCA_CAP);
@@ -130,7 +140,9 @@ int mlx5_set_msix_vec_count(struct mlx5_core_dev *dev, int function_id,
 	MLX5_SET(set_hca_cap_in, hca_cap, op_mod,
 		 MLX5_SET_HCA_CAP_OP_MOD_GENERAL_DEVICE << 1);
 	ret = mlx5_cmd_exec_in(dev, set_hca_cap, hca_cap);
+out:
 	kfree(hca_cap);
+	kfree(query_cap);
 	return ret;
 }
 

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

@@ -136,10 +136,10 @@ static enum devlink_port_fn_state mlx5_sf_to_devlink_state(u8 hw_state)
 	switch (hw_state) {
 	case MLX5_VHCA_STATE_ACTIVE:
 	case MLX5_VHCA_STATE_IN_USE:
-	case MLX5_VHCA_STATE_TEARDOWN_REQUEST:
 		return DEVLINK_PORT_FN_STATE_ACTIVE;
 	case MLX5_VHCA_STATE_INVALID:
 	case MLX5_VHCA_STATE_ALLOCATED:
+	case MLX5_VHCA_STATE_TEARDOWN_REQUEST:
 	default:
 		return DEVLINK_PORT_FN_STATE_INACTIVE;
 	}
@@ -192,14 +192,17 @@ int mlx5_devlink_sf_port_fn_state_get(struct devlink *devlink, struct devlink_po
 	return err;
 }
 
-static int mlx5_sf_activate(struct mlx5_core_dev *dev, struct mlx5_sf *sf)
+static int mlx5_sf_activate(struct mlx5_core_dev *dev, struct mlx5_sf *sf,
+			    struct netlink_ext_ack *extack)
 {
 	int err;
 
 	if (mlx5_sf_is_active(sf))
 		return 0;
-	if (sf->hw_state != MLX5_VHCA_STATE_ALLOCATED)
-		return -EINVAL;
+	if (sf->hw_state != MLX5_VHCA_STATE_ALLOCATED) {
+		NL_SET_ERR_MSG_MOD(extack, "SF is inactivated but it is still attached");
+		return -EBUSY;
+	}
 
 	err = mlx5_cmd_sf_enable_hca(dev, sf->hw_fn_id);
 	if (err)
@@ -226,7 +229,8 @@ static int mlx5_sf_deactivate(struct mlx5_core_dev *dev, struct mlx5_sf *sf)
 
 static int mlx5_sf_state_set(struct mlx5_core_dev *dev, struct mlx5_sf_table *table,
 			     struct mlx5_sf *sf,
-			     enum devlink_port_fn_state state)
+			     enum devlink_port_fn_state state,
+			     struct netlink_ext_ack *extack)
 {
 	int err = 0;
 
@@ -234,7 +238,7 @@ static int mlx5_sf_state_set(struct mlx5_core_dev *dev, struct mlx5_sf_table *ta
 	if (state == mlx5_sf_to_devlink_state(sf->hw_state))
 		goto out;
 	if (state == DEVLINK_PORT_FN_STATE_ACTIVE)
-		err = mlx5_sf_activate(dev, sf);
+		err = mlx5_sf_activate(dev, sf, extack);
 	else if (state == DEVLINK_PORT_FN_STATE_INACTIVE)
 		err = mlx5_sf_deactivate(dev, sf);
 	else
@@ -265,7 +269,7 @@ int mlx5_devlink_sf_port_fn_state_set(struct devlink *devlink, struct devlink_po
 		goto out;
 	}
 
-	err = mlx5_sf_state_set(dev, table, sf, state);
+	err = mlx5_sf_state_set(dev, table, sf, state, extack);
 out:
 	mlx5_sf_table_put(table);
 	return err;

drivers/vdpa/mlx5/net/mlx5_vnet.c

@@ -15,6 +15,7 @@
 #include <linux/mlx5/vport.h>
 #include <linux/mlx5/fs.h>
 #include <linux/mlx5/mlx5_ifc_vdpa.h>
+#include <linux/mlx5/mpfs.h>
 #include "mlx5_vdpa.h"
 
 MODULE_AUTHOR("Eli Cohen <eli@mellanox.com>");
@@ -1859,11 +1860,16 @@ static int mlx5_vdpa_set_map(struct vdpa_device *vdev, struct vhost_iotlb *iotlb
 static void mlx5_vdpa_free(struct vdpa_device *vdev)
 {
 	struct mlx5_vdpa_dev *mvdev = to_mvdev(vdev);
+	struct mlx5_core_dev *pfmdev;
 	struct mlx5_vdpa_net *ndev;
 
 	ndev = to_mlx5_vdpa_ndev(mvdev);
 
 	free_resources(ndev);
+	if (!is_zero_ether_addr(ndev->config.mac)) {
+		pfmdev = pci_get_drvdata(pci_physfn(mvdev->mdev->pdev));
+		mlx5_mpfs_del_mac(pfmdev, ndev->config.mac);
+	}
 	mlx5_vdpa_free_resources(&ndev->mvdev);
 	mutex_destroy(&ndev->reslock);
 }
@@ -1990,6 +1996,7 @@ static int mlx5_vdpa_dev_add(struct vdpa_mgmt_dev *v_mdev, const char *name)
 {
 	struct mlx5_vdpa_mgmtdev *mgtdev = container_of(v_mdev, struct mlx5_vdpa_mgmtdev, mgtdev);
 	struct virtio_net_config *config;
+	struct mlx5_core_dev *pfmdev;
 	struct mlx5_vdpa_dev *mvdev;
 	struct mlx5_vdpa_net *ndev;
 	struct mlx5_core_dev *mdev;
@@ -2023,10 +2030,17 @@ static int mlx5_vdpa_dev_add(struct vdpa_mgmt_dev *v_mdev, const char *name)
 	if (err)
 		goto err_mtu;
 
+	if (!is_zero_ether_addr(config->mac)) {
+		pfmdev = pci_get_drvdata(pci_physfn(mdev->pdev));
+		err = mlx5_mpfs_add_mac(pfmdev, config->mac);
+		if (err)
+			goto err_mtu;
+	}
+
 	mvdev->vdev.dma_dev = mdev->device;
 	err = mlx5_vdpa_alloc_resources(&ndev->mvdev);
 	if (err)
-		goto err_mtu;
+		goto err_mpfs;
 
 	err = alloc_resources(ndev);
 	if (err)
@@ -2044,6 +2058,9 @@ static int mlx5_vdpa_dev_add(struct vdpa_mgmt_dev *v_mdev, const char *name)
 	free_resources(ndev);
 err_res:
 	mlx5_vdpa_free_resources(&ndev->mvdev);
+err_mpfs:
+	if (!is_zero_ether_addr(config->mac))
+		mlx5_mpfs_del_mac(pfmdev, config->mac);
 err_mtu:
 	mutex_destroy(&ndev->reslock);
 	put_device(&mvdev->vdev.dev);

include/linux/mlx5/driver.h

@@ -703,6 +703,27 @@ struct mlx5_hv_vhca;
 #define MLX5_LOG_SW_ICM_BLOCK_SIZE(dev) (MLX5_CAP_DEV_MEM(dev, log_sw_icm_alloc_granularity))
 #define MLX5_SW_ICM_BLOCK_SIZE(dev) (1 << MLX5_LOG_SW_ICM_BLOCK_SIZE(dev))
 
+enum {
+	MLX5_PROF_MASK_QP_SIZE		= (u64)1 << 0,
+	MLX5_PROF_MASK_MR_CACHE		= (u64)1 << 1,
+};
+
+enum {
+	MR_CACHE_LAST_STD_ENTRY = 20,
+	MLX5_IMR_MTT_CACHE_ENTRY,
+	MLX5_IMR_KSM_CACHE_ENTRY,
+	MAX_MR_CACHE_ENTRIES
+};
+
+struct mlx5_profile {
+	u64	mask;
+	u8	log_max_qp;
+	struct {
+		int	size;
+		int	limit;
+	} mr_cache[MAX_MR_CACHE_ENTRIES];
+};
+
 struct mlx5_core_dev {
 	struct device *device;
 	enum mlx5_coredev_type coredev_type;
@@ -731,7 +752,7 @@ struct mlx5_core_dev {
 	struct mutex		intf_state_mutex;
 	unsigned long		intf_state;
 	struct mlx5_priv	priv;
-	struct mlx5_profile	*profile;
+	struct mlx5_profile	profile;
 	u32			issi;
 	struct mlx5e_resources  mlx5e_res;
 	struct mlx5_dm          *dm;
@@ -1083,18 +1104,6 @@ static inline u8 mlx5_mkey_variant(u32 mkey)
 	return mkey & 0xff;
 }
 
-enum {
-	MLX5_PROF_MASK_QP_SIZE		= (u64)1 << 0,
-	MLX5_PROF_MASK_MR_CACHE		= (u64)1 << 1,
-};
-
-enum {
-	MR_CACHE_LAST_STD_ENTRY = 20,
-	MLX5_IMR_MTT_CACHE_ENTRY,
-	MLX5_IMR_KSM_CACHE_ENTRY,
-	MAX_MR_CACHE_ENTRIES
-};
-
 /* Async-atomic event notifier used by mlx5 core to forward FW
  * evetns recived from event queue to mlx5 consumers.
  * Optimise event queue dipatching.
@@ -1148,15 +1157,6 @@ int mlx5_rdma_rn_get_params(struct mlx5_core_dev *mdev,
 			    struct ib_device *device,
 			    struct rdma_netdev_alloc_params *params);
 
-struct mlx5_profile {
-	u64	mask;
-	u8	log_max_qp;
-	struct {
-		int	size;
-		int	limit;
-	} mr_cache[MAX_MR_CACHE_ENTRIES];
-};
-
 enum {
 	MLX5_PCI_DEV_IS_VF		= 1 << 0,
 };

include/linux/mlx5/mpfs.h

+/* SPDX-License-Identifier: GPL-2.0 OR Linux-OpenIB
+ * Copyright (c) 2021 Mellanox Technologies Ltd.
+ */
+
+#ifndef _MLX5_MPFS_
+#define _MLX5_MPFS_
+
+struct mlx5_core_dev;
+
+#ifdef CONFIG_MLX5_MPFS
+int  mlx5_mpfs_add_mac(struct mlx5_core_dev *dev, u8 *mac);
+int  mlx5_mpfs_del_mac(struct mlx5_core_dev *dev, u8 *mac);
+#else /* #ifndef CONFIG_MLX5_MPFS */
+static inline int  mlx5_mpfs_add_mac(struct mlx5_core_dev *dev, u8 *mac) { return 0; }
+static inline int  mlx5_mpfs_del_mac(struct mlx5_core_dev *dev, u8 *mac) { return 0; }
+#endif
+
+#endif