Merge tag 'mlx5-updates-2021-10-04' of git://git.kernel.org/pub/scm/linux/kernel/git/saeed/linux

Saeed Mahameed says:

====================
mlx5-updates-2021-10-04

Misc updates for mlx5 driver

1) Add TX max rate support for MQPRIO channel mode
2) Trivial TC action and modify header refactoring
3) TC support for accept action in fdb offloads
4) Allow single IRQ for PCI functions

5) Bridge offload: Pop PVID VLAN header on egress miss

Vlad Buslov says:
=================

With current architecture of mlx5 bridge offload it is possible for a
packet to match in ingress table by source MAC (resulting VLAN header push
in case of port with configured PVID) and then miss in egress table when
destination MAC is not in FDB. Due to the lack of hardware learning in
NICs, this, in turn, results packet going to software data path with PVID
VLAN already added by hardware. This doesn't break software bridge since it
accepts either untagged packets or packets with any provisioned VLAN on
ports with PVID, but can break ingress TC, if affected part of Ethernet
header is matched by classifier.

Improve compatibility with software TC by restoring the packet header on
egress miss. Effectively, this change implements atomicity of mlx5 bridge
offload implementation - packet is either modified and redirected to
destination port or appears unmodified in software.

=================

=================

Signed-off-by: David S. Miller <[e-mail]>

drivers/infiniband/hw/mlx5/odp.c

···
 
 	eq->irq_nb.notifier_call = mlx5_ib_eq_pf_int;
 	param = (struct mlx5_eq_param) {
+		.irq_index = MLX5_IRQ_EQ_CTRL,
 		.nent = MLX5_IB_NUM_PF_EQE,
 	};
 	param.mask[0] = 1ull << MLX5_EVENT_TYPE_PAGE_FAULT;

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

···
 		u16 mode;
 		u8 num_tc;
 		struct netdev_tc_txq tc_to_txq[TC_MAX_QUEUE];
+		struct {
+			struct mlx5e_mqprio_rl *rl;
+		} channel;
 	} mqprio;
 	bool rx_cqe_compress_def;
 	bool tunneled_offload_en;
···
 #endif
 	struct mlx5e_scratchpad    scratchpad;
 	struct mlx5e_htb           htb;
+	struct mlx5e_mqprio_rl    *mqprio_rl;
 };
 
 struct mlx5e_rx_handlers {
···
 		    struct mlx5e_modify_sq_param *p);
 int mlx5e_open_txqsq(struct mlx5e_channel *c, u32 tisn, int txq_ix,
 		     struct mlx5e_params *params, struct mlx5e_sq_param *param,
-		     struct mlx5e_txqsq *sq, int tc, u16 qos_queue_group_id, u16 qos_qid);
+		     struct mlx5e_txqsq *sq, int tc, u16 qos_queue_group_id,
+		     struct mlx5e_sq_stats *sq_stats);
 void mlx5e_activate_txqsq(struct mlx5e_txqsq *sq);
 void mlx5e_deactivate_txqsq(struct mlx5e_txqsq *sq);
 void mlx5e_free_txqsq(struct mlx5e_txqsq *sq);

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

···
 
 #define BYTES_IN_MBIT 125000
 
+int mlx5e_qos_bytes_rate_check(struct mlx5_core_dev *mdev, u64 nbytes)
+{
+	if (nbytes < BYTES_IN_MBIT) {
+		qos_warn(mdev, "Input rate (%llu Bytes/sec) below minimum supported (%u Bytes/sec)\n",
+			 nbytes, BYTES_IN_MBIT);
+		return -EINVAL;
+	}
+	return 0;
+}
+
+static u32 mlx5e_qos_bytes2mbits(struct mlx5_core_dev *mdev, u64 nbytes)
+{
+	return div_u64(nbytes, BYTES_IN_MBIT);
+}
+
 int mlx5e_qos_max_leaf_nodes(struct mlx5_core_dev *mdev)
 {
 	return min(MLX5E_QOS_MAX_LEAF_NODES, mlx5_qos_max_leaf_nodes(mdev));
···
 	if (err)
 		goto err_free_sq;
 	err = mlx5e_open_txqsq(c, priv->tisn[c->lag_port][0], txq_ix, params,
-			       &param_sq, sq, 0, node->hw_id, node->qid);
+			       &param_sq, sq, 0, node->hw_id,
+			       priv->htb.qos_sq_stats[node->qid]);
 	if (err)
 		goto err_close_cq;
 
···
 		err = mlx5e_qos_update_children(priv, node, extack);
 
 	return err;
+}
+
+struct mlx5e_mqprio_rl {
+	struct mlx5_core_dev *mdev;
+	u32 root_id;
+	u32 *leaves_id;
+	u8 num_tc;
+};
+
+struct mlx5e_mqprio_rl *mlx5e_mqprio_rl_alloc(void)
+{
+	return kvzalloc(sizeof(struct mlx5e_mqprio_rl), GFP_KERNEL);
+}
+
+void mlx5e_mqprio_rl_free(struct mlx5e_mqprio_rl *rl)
+{
+	kvfree(rl);
+}
+
+int mlx5e_mqprio_rl_init(struct mlx5e_mqprio_rl *rl, struct mlx5_core_dev *mdev, u8 num_tc,
+			 u64 max_rate[])
+{
+	int err;
+	int tc;
+
+	if (!mlx5_qos_is_supported(mdev)) {
+		qos_warn(mdev, "Missing QoS capabilities. Try disabling SRIOV or use a supported device.");
+		return -EOPNOTSUPP;
+	}
+	if (num_tc > mlx5e_qos_max_leaf_nodes(mdev))
+		return -EINVAL;
+
+	rl->mdev = mdev;
+	rl->num_tc = num_tc;
+	rl->leaves_id = kvcalloc(num_tc, sizeof(*rl->leaves_id), GFP_KERNEL);
+	if (!rl->leaves_id)
+		return -ENOMEM;
+
+	err = mlx5_qos_create_root_node(mdev, &rl->root_id);
+	if (err)
+		goto err_free_leaves;
+
+	qos_dbg(mdev, "Root created, id %#x\n", rl->root_id);
+
+	for (tc = 0; tc < num_tc; tc++) {
+		u32 max_average_bw;
+
+		max_average_bw = mlx5e_qos_bytes2mbits(mdev, max_rate[tc]);
+		err = mlx5_qos_create_leaf_node(mdev, rl->root_id, 0, max_average_bw,
+						&rl->leaves_id[tc]);
+		if (err)
+			goto err_destroy_leaves;
+
+		qos_dbg(mdev, "Leaf[%d] created, id %#x, max average bw %u Mbits/sec\n",
+			tc, rl->leaves_id[tc], max_average_bw);
+	}
+	return 0;
+
+err_destroy_leaves:
+	while (--tc >= 0)
+		mlx5_qos_destroy_node(mdev, rl->leaves_id[tc]);
+	mlx5_qos_destroy_node(mdev, rl->root_id);
+err_free_leaves:
+	kvfree(rl->leaves_id);
+	return err;
+}
+
+void mlx5e_mqprio_rl_cleanup(struct mlx5e_mqprio_rl *rl)
+{
+	int tc;
+
+	for (tc = 0; tc < rl->num_tc; tc++)
+		mlx5_qos_destroy_node(rl->mdev, rl->leaves_id[tc]);
+	mlx5_qos_destroy_node(rl->mdev, rl->root_id);
+	kvfree(rl->leaves_id);
+}
+
+int mlx5e_mqprio_rl_get_node_hw_id(struct mlx5e_mqprio_rl *rl, int tc, u32 *hw_id)
+{
+	if (tc >= rl->num_tc)
+		return -EINVAL;
+
+	*hw_id = rl->leaves_id[tc];
+	return 0;
 }

drivers/net/ethernet/mellanox/mlx5/core/en/qos.h

···
 struct mlx5e_channels;
 struct mlx5e_channel;
 
+int mlx5e_qos_bytes_rate_check(struct mlx5_core_dev *mdev, u64 nbytes);
 int mlx5e_qos_max_leaf_nodes(struct mlx5_core_dev *mdev);
 int mlx5e_qos_cur_leaf_nodes(struct mlx5e_priv *priv);
 
···
 int mlx5e_htb_node_modify(struct mlx5e_priv *priv, u16 classid, u64 rate, u64 ceil,
 			  struct netlink_ext_ack *extack);
 
+/* MQPRIO TX rate limit */
+struct mlx5e_mqprio_rl;
+struct mlx5e_mqprio_rl *mlx5e_mqprio_rl_alloc(void);
+void mlx5e_mqprio_rl_free(struct mlx5e_mqprio_rl *rl);
+int mlx5e_mqprio_rl_init(struct mlx5e_mqprio_rl *rl, struct mlx5_core_dev *mdev, u8 num_tc,
+			 u64 max_rate[]);
+void mlx5e_mqprio_rl_cleanup(struct mlx5e_mqprio_rl *rl);
+int mlx5e_mqprio_rl_get_node_hw_id(struct mlx5e_mqprio_rl *rl, int tc, u32 *hw_id);
 #endif

drivers/net/ethernet/mellanox/mlx5/core/en/tc/sample.c

···
 	}
 	sample_flow->pre_attr = pre_attr;
 
-	return sample_flow->post_rule;
+	return sample_flow->pre_rule;
 
 err_pre_offload_rule:
 	kfree(pre_attr);
···
 err_obj_id:
 	sampler_put(tc_psample, sample_flow->sampler);
 err_sampler:
-	if (!post_act_handle)
+	if (sample_flow->post_rule)
 		del_post_rule(esw, sample_flow, attr);
 err_post_rule:
 	if (post_act_handle)
···
 			  struct mlx5_flow_handle *rule,
 			  struct mlx5_flow_attr *attr)
 {
-	struct mlx5_esw_flow_attr *esw_attr = attr->esw_attr;
 	struct mlx5e_sample_flow *sample_flow;
-	struct mlx5_vport_tbl_attr tbl_attr;
 	struct mlx5_eswitch *esw;
 
 	if (IS_ERR_OR_NULL(tc_psample))
···
 	 */
 	sample_flow = attr->sample_attr->sample_flow;
 	mlx5_eswitch_del_offloaded_rule(esw, sample_flow->pre_rule, sample_flow->pre_attr);
-	if (!sample_flow->post_act_handle)
-		mlx5_eswitch_del_offloaded_rule(esw, sample_flow->post_rule,
-						sample_flow->post_attr);
 
 	sample_restore_put(tc_psample, sample_flow->restore);
 	mapping_remove(esw->offloads.reg_c0_obj_pool, attr->sample_attr->restore_obj_id);
 	sampler_put(tc_psample, sample_flow->sampler);
-	if (sample_flow->post_act_handle) {
+	if (sample_flow->post_act_handle)
 		mlx5e_tc_post_act_del(tc_psample->post_act, sample_flow->post_act_handle);
-	} else {
-		tbl_attr.chain = attr->chain;
-		tbl_attr.prio = attr->prio;
-		tbl_attr.vport = esw_attr->in_rep->vport;
-		tbl_attr.vport_ns = &mlx5_esw_vport_tbl_sample_ns;
-		mlx5_esw_vporttbl_put(esw, &tbl_attr);
-		kfree(sample_flow->post_attr);
-	}
+	else
+		del_post_rule(esw, sample_flow, attr);
 
 	kfree(sample_flow->pre_attr);
 	kfree(sample_flow);

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

···
 
 		uplink_dev = mlx5_eswitch_uplink_get_proto_dev(esw, REP_ETH);
 		attr->fl.fl4.flowi4_oif = uplink_dev->ifindex;
+	} else {
+		struct mlx5e_tc_tunnel *tunnel = mlx5e_get_tc_tun(mirred_dev);
+
+		if (tunnel && tunnel->get_remote_ifindex)
+			attr->fl.fl4.flowi4_oif = tunnel->get_remote_ifindex(mirred_dev);
 	}
 
 	rt = ip_route_output_key(dev_net(mirred_dev), &attr->fl.fl4);
···
 				       struct net_device *mirred_dev,
 				       struct mlx5e_tc_tun_route_attr *attr)
 {
+	struct mlx5e_tc_tunnel *tunnel = mlx5e_get_tc_tun(mirred_dev);
 	struct net_device *route_dev;
 	struct net_device *out_dev;
 	struct dst_entry *dst;
 	struct neighbour *n;
 	int ret;
 
+	if (tunnel && tunnel->get_remote_ifindex)
+		attr->fl.fl6.flowi6_oif = tunnel->get_remote_ifindex(mirred_dev);
 	dst = ipv6_stub->ipv6_dst_lookup_flow(dev_net(mirred_dev), NULL, &attr->fl.fl6,
 					      NULL);
 	if (IS_ERR(dst))

drivers/net/ethernet/mellanox/mlx5/core/en/tc_tun.h

···
 			    void *headers_v);
 	bool (*encap_info_equal)(struct mlx5e_encap_key *a,
 				 struct mlx5e_encap_key *b);
+	int (*get_remote_ifindex)(struct net_device *mirred_dev);
 };
 
 extern struct mlx5e_tc_tunnel vxlan_tunnel;

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

···
 	return 0;
 }
 
+static int mlx5e_tc_tun_get_remote_ifindex(struct net_device *mirred_dev)
+{
+	const struct vxlan_dev *vxlan = netdev_priv(mirred_dev);
+	const struct vxlan_rdst *dst = &vxlan->default_dst;
+
+	return dst->remote_ifindex;
+}
+
 struct mlx5e_tc_tunnel vxlan_tunnel = {
 	.tunnel_type          = MLX5E_TC_TUNNEL_TYPE_VXLAN,
 	.match_level          = MLX5_MATCH_L4,
···
 	.parse_udp_ports      = mlx5e_tc_tun_parse_udp_ports_vxlan,
 	.parse_tunnel         = mlx5e_tc_tun_parse_vxlan,
 	.encap_info_equal     = mlx5e_tc_tun_encap_info_equal_generic,
+	.get_remote_ifindex   = mlx5e_tc_tun_get_remote_ifindex,
 };

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

···
 
 int mlx5e_open_txqsq(struct mlx5e_channel *c, u32 tisn, int txq_ix,
 		     struct mlx5e_params *params, struct mlx5e_sq_param *param,
-		     struct mlx5e_txqsq *sq, int tc, u16 qos_queue_group_id, u16 qos_qid)
+		     struct mlx5e_txqsq *sq, int tc, u16 qos_queue_group_id,
+		     struct mlx5e_sq_stats *sq_stats)
 {
 	struct mlx5e_create_sq_param csp = {};
 	u32 tx_rate;
···
 	if (err)
 		return err;
 
-	if (qos_queue_group_id)
-		sq->stats = c->priv->htb.qos_sq_stats[qos_qid];
-	else
-		sq->stats = &c->priv->channel_stats[c->ix].sq[tc];
+	sq->stats = sq_stats;
 
 	csp.tisn            = tisn;
 	csp.tis_lst_sz      = 1;
···
 		mlx5e_close_cq(&c->sq[tc].cq);
 }
 
+static int mlx5e_mqprio_txq_to_tc(struct netdev_tc_txq *tc_to_txq, unsigned int txq)
+{
+	int tc;
+
+	for (tc = 0; tc < TC_MAX_QUEUE; tc++)
+		if (txq - tc_to_txq[tc].offset < tc_to_txq[tc].count)
+			return tc;
+
+	WARN(1, "Unexpected TCs configuration. No match found for txq %u", txq);
+	return -ENOENT;
+}
+
+static int mlx5e_txq_get_qos_node_hw_id(struct mlx5e_params *params, int txq_ix,
+					u32 *hw_id)
+{
+	int tc;
+
+	if (params->mqprio.mode != TC_MQPRIO_MODE_CHANNEL ||
+	    !params->mqprio.channel.rl) {
+		*hw_id = 0;
+		return 0;
+	}
+
+	tc = mlx5e_mqprio_txq_to_tc(params->mqprio.tc_to_txq, txq_ix);
+	if (tc < 0)
+		return tc;
+
+	return mlx5e_mqprio_rl_get_node_hw_id(params->mqprio.channel.rl, tc, hw_id);
+}
+
 static int mlx5e_open_sqs(struct mlx5e_channel *c,
 			  struct mlx5e_params *params,
 			  struct mlx5e_channel_param *cparam)
···
 
 	for (tc = 0; tc < mlx5e_get_dcb_num_tc(params); tc++) {
 		int txq_ix = c->ix + tc * params->num_channels;
+		u32 qos_queue_group_id;
+
+		err = mlx5e_txq_get_qos_node_hw_id(params, txq_ix, &qos_queue_group_id);
+		if (err)
+			goto err_close_sqs;
 
 		err = mlx5e_open_txqsq(c, c->priv->tisn[c->lag_port][tc], txq_ix,
-				       params, &cparam->txq_sq, &c->sq[tc], tc, 0, 0);
+				       params, &cparam->txq_sq, &c->sq[tc], tc,
+				       qos_queue_group_id,
+				       &c->priv->channel_stats[c->ix].sq[tc]);
 		if (err)
 			goto err_close_sqs;
 	}
···
 		netdev_warn(netdev, "netif_set_real_num_rx_queues failed, %d\n", err);
 		goto err_txqs;
 	}
+	if (priv->mqprio_rl != priv->channels.params.mqprio.channel.rl) {
+		if (priv->mqprio_rl) {
+			mlx5e_mqprio_rl_cleanup(priv->mqprio_rl);
+			mlx5e_mqprio_rl_free(priv->mqprio_rl);
+		}
+		priv->mqprio_rl = priv->channels.params.mqprio.channel.rl;
+	}
 
 	return 0;
 
···
 {
 	params->mqprio.mode = TC_MQPRIO_MODE_DCB;
 	params->mqprio.num_tc = num_tc;
+	params->mqprio.channel.rl = NULL;
 	mlx5e_mqprio_build_default_tc_to_txq(params->mqprio.tc_to_txq, num_tc,
 					     params->num_channels);
 }
 
 static void mlx5e_params_mqprio_channel_set(struct mlx5e_params *params,
-					    struct tc_mqprio_qopt *qopt)
+					    struct tc_mqprio_qopt *qopt,
+					    struct mlx5e_mqprio_rl *rl)
 {
 	params->mqprio.mode = TC_MQPRIO_MODE_CHANNEL;
 	params->mqprio.num_tc = qopt->num_tc;
+	params->mqprio.channel.rl = rl;
 	mlx5e_mqprio_build_tc_to_txq(params->mqprio.tc_to_txq, qopt);
 }
 
···
 			netdev_err(netdev, "Min tx rate is not supported\n");
 			return -EINVAL;
 		}
+
 		if (mqprio->max_rate[i]) {
-			netdev_err(netdev, "Max tx rate is not supported\n");
-			return -EINVAL;
+			int err;
+
+			err = mlx5e_qos_bytes_rate_check(priv->mdev, mqprio->max_rate[i]);
+			if (err)
+				return err;
 		}
 
 		if (mqprio->qopt.offset[i] != agg_count) {
···
 	return 0;
 }
 
+static bool mlx5e_mqprio_rate_limit(struct tc_mqprio_qopt_offload *mqprio)
+{
+	int tc;
+
+	for (tc = 0; tc < mqprio->qopt.num_tc; tc++)
+		if (mqprio->max_rate[tc])
+			return true;
+	return false;
+}
+
 static int mlx5e_setup_tc_mqprio_channel(struct mlx5e_priv *priv,
 					 struct tc_mqprio_qopt_offload *mqprio)
 {
 	mlx5e_fp_preactivate preactivate;
 	struct mlx5e_params new_params;
+	struct mlx5e_mqprio_rl *rl;
 	bool nch_changed;
 	int err;
 
···
 	if (err)
 		return err;
 
+	rl = NULL;
+	if (mlx5e_mqprio_rate_limit(mqprio)) {
+		rl = mlx5e_mqprio_rl_alloc();
+		if (!rl)
+			return -ENOMEM;
+		err = mlx5e_mqprio_rl_init(rl, priv->mdev, mqprio->qopt.num_tc,
+					   mqprio->max_rate);
+		if (err) {
+			mlx5e_mqprio_rl_free(rl);
+			return err;
+		}
+	}
+
 	new_params = priv->channels.params;
-	mlx5e_params_mqprio_channel_set(&new_params, &mqprio->qopt);
+	mlx5e_params_mqprio_channel_set(&new_params, &mqprio->qopt, rl);
 
 	nch_changed = mlx5e_get_dcb_num_tc(&priv->channels.params) > 1;
 	preactivate = nch_changed ? mlx5e_num_channels_changed_ctx :
 		mlx5e_update_netdev_queues_ctx;
-	return mlx5e_safe_switch_params(priv, &new_params, preactivate, NULL, true);
+	err = mlx5e_safe_switch_params(priv, &new_params, preactivate, NULL, true);
+	if (err && rl) {
+		mlx5e_mqprio_rl_cleanup(rl);
+		mlx5e_mqprio_rl_free(rl);
+	}
+
+	return err;
 }
 
 static int mlx5e_setup_tc_mqprio(struct mlx5e_priv *priv,
···
 	for (i = 0; i < priv->htb.max_qos_sqs; i++)
 		kfree(priv->htb.qos_sq_stats[i]);
 	kvfree(priv->htb.qos_sq_stats);
+
+	if (priv->mqprio_rl) {
+		mlx5e_mqprio_rl_cleanup(priv->mqprio_rl);
+		mlx5e_mqprio_rl_free(priv->mqprio_rl);
+	}
 
 	memset(priv, 0, sizeof(*priv));
 }

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

···
 	return true;
 }
 
-static bool actions_match_supported(struct mlx5e_priv *priv,
-				    struct flow_action *flow_action,
-				    struct mlx5e_tc_flow_parse_attr *parse_attr,
-				    struct mlx5e_tc_flow *flow,
-				    struct netlink_ext_ack *extack)
+static bool
+actions_match_supported_fdb(struct mlx5e_priv *priv,
+			    struct mlx5e_tc_flow_parse_attr *parse_attr,
+			    struct mlx5e_tc_flow *flow,
+			    struct netlink_ext_ack *extack)
 {
-	bool ct_flow = false, ct_clear = false;
-	u32 actions;
+	struct mlx5_esw_flow_attr *esw_attr = flow->attr->esw_attr;
+	bool ct_flow, ct_clear;
 
-	ct_clear = flow->attr->ct_attr.ct_action &
-		TCA_CT_ACT_CLEAR;
+	ct_clear = flow->attr->ct_attr.ct_action & TCA_CT_ACT_CLEAR;
 	ct_flow = flow_flag_test(flow, CT) && !ct_clear;
-	actions = flow->attr->action;
+
+	if (esw_attr->split_count && ct_flow &&
+	    !MLX5_CAP_GEN(esw_attr->in_mdev, reg_c_preserve)) {
+		/* All registers used by ct are cleared when using
+		 * split rules.
+		 */
+		NL_SET_ERR_MSG_MOD(extack, "Can't offload mirroring with action ct");
+		return false;
+	}
+
+	if (esw_attr->split_count > 0 && !mlx5_esw_has_fwd_fdb(priv->mdev)) {
+		NL_SET_ERR_MSG_MOD(extack,
+				   "current firmware doesn't support split rule for port mirroring");
+		netdev_warn_once(priv->netdev,
+				 "current firmware doesn't support split rule for port mirroring\n");
+		return false;
+	}
+
+	return true;
+}
+
+static bool
+actions_match_supported(struct mlx5e_priv *priv,
+			struct flow_action *flow_action,
+			struct mlx5e_tc_flow_parse_attr *parse_attr,
+			struct mlx5e_tc_flow *flow,
+			struct netlink_ext_ack *extack)
+{
+	u32 actions = flow->attr->action;
+	bool ct_flow, ct_clear;
+
+	ct_clear = flow->attr->ct_attr.ct_action & TCA_CT_ACT_CLEAR;
+	ct_flow = flow_flag_test(flow, CT) && !ct_clear;
 
 	if (!(actions &
 	      (MLX5_FLOW_CONTEXT_ACTION_FWD_DEST | MLX5_FLOW_CONTEXT_ACTION_DROP))) {
···
 		return false;
 	}
 
-	if (mlx5e_is_eswitch_flow(flow)) {
-		if (flow->attr->esw_attr->split_count && ct_flow &&
-		    !MLX5_CAP_GEN(flow->attr->esw_attr->in_mdev, reg_c_preserve)) {
-			/* All registers used by ct are cleared when using
-			 * split rules.
-			 */
-			NL_SET_ERR_MSG_MOD(extack,
-					   "Can't offload mirroring with action ct");
-			return false;
-		}
-	}
+	if (actions & MLX5_FLOW_CONTEXT_ACTION_MOD_HDR &&
+	    !modify_header_match_supported(priv, &parse_attr->spec, flow_action,
+					   actions, ct_flow, ct_clear, extack))
+		return false;
 
-	if (actions & MLX5_FLOW_CONTEXT_ACTION_MOD_HDR)
-		return modify_header_match_supported(priv, &parse_attr->spec,
-						     flow_action, actions,
-						     ct_flow, ct_clear,
-						     extack);
+	if (mlx5e_is_eswitch_flow(flow) &&
+	    !actions_match_supported_fdb(priv, parse_attr, flow, extack))
+		return false;
 
 	return true;
 }
···
 	return 0;
 }
 
-static int parse_tc_nic_actions(struct mlx5e_priv *priv,
-				struct flow_action *flow_action,
+static int
+actions_prepare_mod_hdr_actions(struct mlx5e_priv *priv,
 				struct mlx5e_tc_flow *flow,
+				struct mlx5_flow_attr *attr,
+				struct pedit_headers_action *hdrs,
 				struct netlink_ext_ack *extack)
+{
+	struct mlx5e_tc_flow_parse_attr *parse_attr = attr->parse_attr;
+	enum mlx5_flow_namespace_type ns_type;
+	int err;
+
+	if (!hdrs[TCA_PEDIT_KEY_EX_CMD_SET].pedits &&
+	    !hdrs[TCA_PEDIT_KEY_EX_CMD_ADD].pedits)
+		return 0;
+
+	ns_type = get_flow_name_space(flow);
+
+	err = alloc_tc_pedit_action(priv, ns_type, parse_attr, hdrs,
+				    &attr->action, extack);
+	if (err)
+		return err;
+
+	/* In case all pedit actions are skipped, remove the MOD_HDR flag. */
+	if (parse_attr->mod_hdr_acts.num_actions > 0)
+		return 0;
+
+	attr->action &= ~MLX5_FLOW_CONTEXT_ACTION_MOD_HDR;
+	dealloc_mod_hdr_actions(&parse_attr->mod_hdr_acts);
+
+	if (ns_type != MLX5_FLOW_NAMESPACE_FDB)
+		return 0;
+
+	if (!((attr->action & MLX5_FLOW_CONTEXT_ACTION_VLAN_POP) ||
+	      (attr->action & MLX5_FLOW_CONTEXT_ACTION_VLAN_PUSH)))
+		attr->esw_attr->split_count = 0;
+
+	return 0;
+}
+
+static int
+parse_tc_nic_actions(struct mlx5e_priv *priv,
+		     struct flow_action *flow_action,
+		     struct mlx5e_tc_flow *flow,
+		     struct netlink_ext_ack *extack)
 {
 	struct mlx5e_tc_flow_parse_attr *parse_attr;
 	struct mlx5_flow_attr *attr = flow->attr;
···
 		}
 	}
 
-	if (hdrs[TCA_PEDIT_KEY_EX_CMD_SET].pedits ||
-	    hdrs[TCA_PEDIT_KEY_EX_CMD_ADD].pedits) {
-		err = alloc_tc_pedit_action(priv, MLX5_FLOW_NAMESPACE_KERNEL,
-					    parse_attr, hdrs, &action, extack);
-		if (err)
-			return err;
-		/* in case all pedit actions are skipped, remove the MOD_HDR
-		 * flag.
-		 */
-		if (parse_attr->mod_hdr_acts.num_actions == 0) {
-			action &= ~MLX5_FLOW_CONTEXT_ACTION_MOD_HDR;
-			dealloc_mod_hdr_actions(&parse_attr->mod_hdr_acts);
-		}
-	}
-
 	attr->action = action;
 
 	if (attr->dest_chain && parse_attr->mirred_ifindex[0]) {
 		NL_SET_ERR_MSG(extack, "Mirroring goto chain rules isn't supported");
 		return -EOPNOTSUPP;
 	}
+
+	err = actions_prepare_mod_hdr_actions(priv, flow, attr, hdrs, extack);
+	if (err)
+		return err;
 
 	if (!actions_match_supported(priv, flow_action, parse_attr, flow, extack))
 		return -EOPNOTSUPP;
···
 
 	flow_action_for_each(i, act, flow_action) {
 		switch (act->id) {
+		case FLOW_ACTION_ACCEPT:
+			action |= MLX5_FLOW_CONTEXT_ACTION_FWD_DEST |
+				MLX5_FLOW_CONTEXT_ACTION_COUNT;
+			attr->flags |= MLX5_ESW_ATTR_FLAG_ACCEPT;
+			break;
 		case FLOW_ACTION_DROP:
 			action |= MLX5_FLOW_CONTEXT_ACTION_DROP |
 				  MLX5_FLOW_CONTEXT_ACTION_COUNT;
···
 			return err;
 	}
 
-	if (hdrs[TCA_PEDIT_KEY_EX_CMD_SET].pedits ||
-	    hdrs[TCA_PEDIT_KEY_EX_CMD_ADD].pedits) {
-		err = alloc_tc_pedit_action(priv, MLX5_FLOW_NAMESPACE_FDB,
-					    parse_attr, hdrs, &action, extack);
-		if (err)
-			return err;
-		/* in case all pedit actions are skipped, remove the MOD_HDR
-		 * flag. we might have set split_count either by pedit or
-		 * pop/push. if there is no pop/push either, reset it too.
-		 */
-		if (parse_attr->mod_hdr_acts.num_actions == 0) {
-			action &= ~MLX5_FLOW_CONTEXT_ACTION_MOD_HDR;
-			dealloc_mod_hdr_actions(&parse_attr->mod_hdr_acts);
-			if (!((action & MLX5_FLOW_CONTEXT_ACTION_VLAN_POP) ||
-			      (action & MLX5_FLOW_CONTEXT_ACTION_VLAN_PUSH)))
-				esw_attr->split_count = 0;
-		}
-	}
-
 	attr->action = action;
+
+	err = actions_prepare_mod_hdr_actions(priv, flow, attr, hdrs, extack);
+	if (err)
+		return err;
+
 	if (!actions_match_supported(priv, flow_action, parse_attr, flow, extack))
 		return -EOPNOTSUPP;
 
···
 
 		NL_SET_ERR_MSG(extack, "Decap with goto isn't supported");
 		netdev_warn(priv->netdev, "Decap with goto isn't supported");
-		return -EOPNOTSUPP;
-	}
-
-	if (esw_attr->split_count > 0 && !mlx5_esw_has_fwd_fdb(priv->mdev)) {
-		NL_SET_ERR_MSG_MOD(extack,
-				   "current firmware doesn't support split rule for port mirroring");
-		netdev_warn_once(priv->netdev, "current firmware doesn't support split rule for port mirroring\n");
 		return -EOPNOTSUPP;
 	}
 
···
 	}
 	uplink_priv->tunnel_mapping = mapping;
 
-	/* 0xFFF is reserved for stack devices slow path table mark */
+	/* Two last values are reserved for stack devices slow path table mark
+	 * and bridge ingress push mark.
+	 */
 	mapping = mapping_create_for_id(mapping_id, MAPPING_TYPE_TUNNEL_ENC_OPTS,
-					sz_enc_opts, ENC_OPTS_BITS_MASK - 1, true);
+					sz_enc_opts, ENC_OPTS_BITS_MASK - 2, true);
 	if (IS_ERR(mapping)) {
 		err = PTR_ERR(mapping);
 		goto err_enc_opts_mapping;

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

···
 	mlx5_eq_notifier_register(dev, &table->cq_err_nb);
 
 	param = (struct mlx5_eq_param) {
+		.irq_index = MLX5_IRQ_EQ_CTRL,
 		.nent = MLX5_NUM_CMD_EQE,
 		.mask[0] = 1ull << MLX5_EVENT_TYPE_CMD,
 	};
···
 	mlx5_cmd_allowed_opcode(dev, CMD_ALLOWED_OPCODE_ALL);
 
 	param = (struct mlx5_eq_param) {
+		.irq_index = MLX5_IRQ_EQ_CTRL,
 		.nent = MLX5_NUM_ASYNC_EQE,
 	};
 
···
 		goto err2;
 
 	param = (struct mlx5_eq_param) {
+		.irq_index = MLX5_IRQ_EQ_CTRL,
 		.nent = /* TODO: sriov max_vf + */ 1,
 		.mask[0] = 1ull << MLX5_EVENT_TYPE_PAGE_REQUEST,
 	};
···
 	ncomp_eqs = table->num_comp_eqs;
 	nent = MLX5_COMP_EQ_SIZE;
 	for (i = 0; i < ncomp_eqs; i++) {
-		int vecidx = i + MLX5_IRQ_VEC_COMP_BASE;
 		struct mlx5_eq_param param = {};
+		int vecidx = i;
 
 		eq = kzalloc(sizeof(*eq), GFP_KERNEL);
 		if (!eq) {
···
 		goto err_out;
 	}
 
-	vecidx = MLX5_IRQ_VEC_COMP_BASE;
-	for (; vecidx < eq_table->num_comp_eqs + MLX5_IRQ_VEC_COMP_BASE;
-	     vecidx++) {
+	for (vecidx = 0; vecidx < eq_table->num_comp_eqs; vecidx++) {
 		err = irq_cpu_rmap_add(eq_table->rmap,
 				       pci_irq_vector(mdev->pdev, vecidx));
 		if (err) {

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

···
 #define MLX5_ESW_BRIDGE_EGRESS_TABLE_VLAN_GRP_IDX_TO (MLX5_ESW_BRIDGE_EGRESS_TABLE_SIZE / 2 - 1)
 #define MLX5_ESW_BRIDGE_EGRESS_TABLE_MAC_GRP_IDX_FROM \
 	(MLX5_ESW_BRIDGE_EGRESS_TABLE_VLAN_GRP_IDX_TO + 1)
-#define MLX5_ESW_BRIDGE_EGRESS_TABLE_MAC_GRP_IDX_TO (MLX5_ESW_BRIDGE_EGRESS_TABLE_SIZE - 1)
+#define MLX5_ESW_BRIDGE_EGRESS_TABLE_MAC_GRP_IDX_TO (MLX5_ESW_BRIDGE_EGRESS_TABLE_SIZE - 2)
+#define MLX5_ESW_BRIDGE_EGRESS_TABLE_MISS_GRP_IDX_FROM \
+	(MLX5_ESW_BRIDGE_EGRESS_TABLE_MAC_GRP_IDX_TO + 1)
+#define MLX5_ESW_BRIDGE_EGRESS_TABLE_MISS_GRP_IDX_TO (MLX5_ESW_BRIDGE_EGRESS_TABLE_SIZE - 1)
 
 #define MLX5_ESW_BRIDGE_SKIP_TABLE_SIZE 0
 
···
 	struct mlx5_flow_table *egress_ft;
 	struct mlx5_flow_group *egress_vlan_fg;
 	struct mlx5_flow_group *egress_mac_fg;
+	struct mlx5_flow_group *egress_miss_fg;
+	struct mlx5_pkt_reformat *egress_miss_pkt_reformat;
+	struct mlx5_flow_handle *egress_miss_handle;
 	unsigned long ageing_time;
 	u32 flags;
 };
···
 		mlx5_esw_bridge_fdb_offload_notify(entry->dev, entry->key.addr,
 						   entry->key.vid,
 						   SWITCHDEV_FDB_DEL_TO_BRIDGE);
+}
+
+static bool mlx5_esw_bridge_pkt_reformat_vlan_pop_supported(struct mlx5_eswitch *esw)
+{
+	return BIT(MLX5_CAP_ESW_FLOWTABLE_FDB(esw->dev, reformat_remove)) &&
+		MLX5_CAP_GEN_2(esw->dev, max_reformat_remove_size) >= sizeof(struct vlan_hdr) &&
+		MLX5_CAP_GEN_2(esw->dev, max_reformat_remove_offset) >=
+		offsetof(struct vlan_ethhdr, h_vlan_proto);
+}
+
+static struct mlx5_pkt_reformat *
+mlx5_esw_bridge_pkt_reformat_vlan_pop_create(struct mlx5_eswitch *esw)
+{
+	struct mlx5_pkt_reformat_params reformat_params = {};
+
+	reformat_params.type = MLX5_REFORMAT_TYPE_REMOVE_HDR;
+	reformat_params.param_0 = MLX5_REFORMAT_CONTEXT_ANCHOR_MAC_START;
+	reformat_params.param_1 = offsetof(struct vlan_ethhdr, h_vlan_proto);
+	reformat_params.size = sizeof(struct vlan_hdr);
+	return mlx5_packet_reformat_alloc(esw->dev, &reformat_params, MLX5_FLOW_NAMESPACE_FDB);
 }
 
 static struct mlx5_flow_table *
···
 	return fg;
 }
 
+static struct mlx5_flow_group *
+mlx5_esw_bridge_egress_miss_fg_create(struct mlx5_eswitch *esw, struct mlx5_flow_table *egress_ft)
+{
+	int inlen = MLX5_ST_SZ_BYTES(create_flow_group_in);
+	struct mlx5_flow_group *fg;
+	u32 *in, *match;
+
+	in = kvzalloc(inlen, GFP_KERNEL);
+	if (!in)
+		return ERR_PTR(-ENOMEM);
+
+	MLX5_SET(create_flow_group_in, in, match_criteria_enable, MLX5_MATCH_MISC_PARAMETERS_2);
+	match = MLX5_ADDR_OF(create_flow_group_in, in, match_criteria);
+
+	MLX5_SET(fte_match_param, match, misc_parameters_2.metadata_reg_c_1, ESW_TUN_MASK);
+
+	MLX5_SET(create_flow_group_in, in, start_flow_index,
+		 MLX5_ESW_BRIDGE_EGRESS_TABLE_MISS_GRP_IDX_FROM);
+	MLX5_SET(create_flow_group_in, in, end_flow_index,
+		 MLX5_ESW_BRIDGE_EGRESS_TABLE_MISS_GRP_IDX_TO);
+
+	fg = mlx5_create_flow_group(egress_ft, in);
+	if (IS_ERR(fg))
+		esw_warn(esw->dev,
+			 "Failed to create bridge egress table miss flow group (err=%ld)\n",
+			 PTR_ERR(fg));
+	kvfree(in);
+	return fg;
+}
+
 static int
 mlx5_esw_bridge_ingress_table_init(struct mlx5_esw_bridge_offloads *br_offloads)
 {
 	struct mlx5_flow_group *mac_fg, *filter_fg, *vlan_fg;
 	struct mlx5_flow_table *ingress_ft, *skip_ft;
+	struct mlx5_eswitch *esw = br_offloads->esw;
 	int err;
 
-	if (!mlx5_eswitch_vport_match_metadata_enabled(br_offloads->esw))
+	if (!mlx5_eswitch_vport_match_metadata_enabled(esw))
 		return -EOPNOTSUPP;
 
 	ingress_ft = mlx5_esw_bridge_table_create(MLX5_ESW_BRIDGE_INGRESS_TABLE_SIZE,
 						  MLX5_ESW_BRIDGE_LEVEL_INGRESS_TABLE,
-						  br_offloads->esw);
+						  esw);
 	if (IS_ERR(ingress_ft))
 		return PTR_ERR(ingress_ft);
 
 	skip_ft = mlx5_esw_bridge_table_create(MLX5_ESW_BRIDGE_SKIP_TABLE_SIZE,
 					       MLX5_ESW_BRIDGE_LEVEL_SKIP_TABLE,
-					       br_offloads->esw);
+					       esw);
 	if (IS_ERR(skip_ft)) {
 		err = PTR_ERR(skip_ft);
 		goto err_skip_tbl;
 	}
 
-	vlan_fg = mlx5_esw_bridge_ingress_vlan_fg_create(br_offloads->esw, ingress_ft);
+	vlan_fg = mlx5_esw_bridge_ingress_vlan_fg_create(esw, ingress_ft);
 	if (IS_ERR(vlan_fg)) {
 		err = PTR_ERR(vlan_fg);
 		goto err_vlan_fg;
 	}
 
-	filter_fg = mlx5_esw_bridge_ingress_filter_fg_create(br_offloads->esw, ingress_ft);
+	filter_fg = mlx5_esw_bridge_ingress_filter_fg_create(esw, ingress_ft);
 	if (IS_ERR(filter_fg)) {
 		err = PTR_ERR(filter_fg);
 		goto err_filter_fg;
 	}
 
-	mac_fg = mlx5_esw_bridge_ingress_mac_fg_create(br_offloads->esw, ingress_ft);
+	mac_fg = mlx5_esw_bridge_ingress_mac_fg_create(esw, ingress_ft);
 	if (IS_ERR(mac_fg)) {
 		err = PTR_ERR(mac_fg);
 		goto err_mac_fg;
···
 	br_offloads->ingress_ft = NULL;
 }
 
+static struct mlx5_flow_handle *
+mlx5_esw_bridge_egress_miss_flow_create(struct mlx5_flow_table *egress_ft,
+					struct mlx5_flow_table *skip_ft,
+					struct mlx5_pkt_reformat *pkt_reformat);
+
 static int
 mlx5_esw_bridge_egress_table_init(struct mlx5_esw_bridge_offloads *br_offloads,
 				  struct mlx5_esw_bridge *bridge)
 {
-	struct mlx5_flow_group *mac_fg, *vlan_fg;
+	struct mlx5_flow_group *miss_fg = NULL, *mac_fg, *vlan_fg;
+	struct mlx5_pkt_reformat *miss_pkt_reformat = NULL;
+	struct mlx5_flow_handle *miss_handle = NULL;
+	struct mlx5_eswitch *esw = br_offloads->esw;
 	struct mlx5_flow_table *egress_ft;
 	int err;
 
 	egress_ft = mlx5_esw_bridge_table_create(MLX5_ESW_BRIDGE_EGRESS_TABLE_SIZE,
 						 MLX5_ESW_BRIDGE_LEVEL_EGRESS_TABLE,
-						 br_offloads->esw);
+						 esw);
 	if (IS_ERR(egress_ft))
 		return PTR_ERR(egress_ft);
 
-	vlan_fg = mlx5_esw_bridge_egress_vlan_fg_create(br_offloads->esw, egress_ft);
+	vlan_fg = mlx5_esw_bridge_egress_vlan_fg_create(esw, egress_ft);
 	if (IS_ERR(vlan_fg)) {
 		err = PTR_ERR(vlan_fg);
 		goto err_vlan_fg;
 	}
 
-	mac_fg = mlx5_esw_bridge_egress_mac_fg_create(br_offloads->esw, egress_ft);
+	mac_fg = mlx5_esw_bridge_egress_mac_fg_create(esw, egress_ft);
 	if (IS_ERR(mac_fg)) {
 		err = PTR_ERR(mac_fg);
 		goto err_mac_fg;
 	}
 
+	if (mlx5_esw_bridge_pkt_reformat_vlan_pop_supported(esw)) {
+		miss_fg = mlx5_esw_bridge_egress_miss_fg_create(esw, egress_ft);
+		if (IS_ERR(miss_fg)) {
+			esw_warn(esw->dev, "Failed to create miss flow group (err=%ld)\n",
+				 PTR_ERR(miss_fg));
+			miss_fg = NULL;
+			goto skip_miss_flow;
+		}
+
+		miss_pkt_reformat = mlx5_esw_bridge_pkt_reformat_vlan_pop_create(esw);
+		if (IS_ERR(miss_pkt_reformat)) {
+			esw_warn(esw->dev,
+				 "Failed to alloc packet reformat REMOVE_HEADER (err=%ld)\n",
+				 PTR_ERR(miss_pkt_reformat));
+			miss_pkt_reformat = NULL;
+			mlx5_destroy_flow_group(miss_fg);
+			miss_fg = NULL;
+			goto skip_miss_flow;
+		}
+
+		miss_handle = mlx5_esw_bridge_egress_miss_flow_create(egress_ft,
+								      br_offloads->skip_ft,
+								      miss_pkt_reformat);
+		if (IS_ERR(miss_handle)) {
+			esw_warn(esw->dev, "Failed to create miss flow (err=%ld)\n",
+				 PTR_ERR(miss_handle));
+			miss_handle = NULL;
+			mlx5_packet_reformat_dealloc(esw->dev, miss_pkt_reformat);
+			miss_pkt_reformat = NULL;
+			mlx5_destroy_flow_group(miss_fg);
+			miss_fg = NULL;
+			goto skip_miss_flow;
+		}
+	}
+skip_miss_flow:
+
 	bridge->egress_ft = egress_ft;
 	bridge->egress_vlan_fg = vlan_fg;
 	bridge->egress_mac_fg = mac_fg;
+	bridge->egress_miss_fg = miss_fg;
+	bridge->egress_miss_pkt_reformat = miss_pkt_reformat;
+	bridge->egress_miss_handle = miss_handle;
 	return 0;
 
 err_mac_fg:
···
 static void
 mlx5_esw_bridge_egress_table_cleanup(struct mlx5_esw_bridge *bridge)
 {
+	if (bridge->egress_miss_handle)
+		mlx5_del_flow_rules(bridge->egress_miss_handle);
+	if (bridge->egress_miss_pkt_reformat)
+		mlx5_packet_reformat_dealloc(bridge->br_offloads->esw->dev,
+					     bridge->egress_miss_pkt_reformat);
+	if (bridge->egress_miss_fg)
+		mlx5_destroy_flow_group(bridge->egress_miss_fg);
 	mlx5_destroy_flow_group(bridge->egress_mac_fg);
 	mlx5_destroy_flow_group(bridge->egress_vlan_fg);
 	mlx5_destroy_flow_table(bridge->egress_ft);
···
 		 mlx5_eswitch_get_vport_metadata_for_match(esw, vport_num));
 
 	if (vlan && vlan->pkt_reformat_push) {
-		flow_act.action |= MLX5_FLOW_CONTEXT_ACTION_PACKET_REFORMAT;
+		flow_act.action |= MLX5_FLOW_CONTEXT_ACTION_PACKET_REFORMAT |
+			MLX5_FLOW_CONTEXT_ACTION_MOD_HDR;
 		flow_act.pkt_reformat = vlan->pkt_reformat_push;
+		flow_act.modify_hdr = vlan->pkt_mod_hdr_push_mark;
 	} else if (vlan) {
 		MLX5_SET_TO_ONES(fte_match_param, rule_spec->match_criteria,
 				 outer_headers.cvlan_tag);
···
 		dest.vport.vhca_id = esw_owner_vhca_id;
 	}
 	handle = mlx5_add_flow_rules(bridge->egress_ft, rule_spec, &flow_act, &dest, 1);
+
+	kvfree(rule_spec);
+	return handle;
+}
+
+static struct mlx5_flow_handle *
+mlx5_esw_bridge_egress_miss_flow_create(struct mlx5_flow_table *egress_ft,
+					struct mlx5_flow_table *skip_ft,
+					struct mlx5_pkt_reformat *pkt_reformat)
+{
+	struct mlx5_flow_destination dest = {
+		.type = MLX5_FLOW_DESTINATION_TYPE_FLOW_TABLE,
+		.ft = skip_ft,
+	};
+	struct mlx5_flow_act flow_act = {
+		.action = MLX5_FLOW_CONTEXT_ACTION_FWD_DEST |
+		MLX5_FLOW_CONTEXT_ACTION_PACKET_REFORMAT,
+		.flags = FLOW_ACT_NO_APPEND,
+		.pkt_reformat = pkt_reformat,
+	};
+	struct mlx5_flow_spec *rule_spec;
+	struct mlx5_flow_handle *handle;
+
+	rule_spec = kvzalloc(sizeof(*rule_spec), GFP_KERNEL);
+	if (!rule_spec)
+		return ERR_PTR(-ENOMEM);
+
+	rule_spec->match_criteria_enable = MLX5_MATCH_MISC_PARAMETERS_2;
+
+	MLX5_SET(fte_match_param, rule_spec->match_criteria,
+		 misc_parameters_2.metadata_reg_c_1, ESW_TUN_MASK);
+	MLX5_SET(fte_match_param, rule_spec->match_value, misc_parameters_2.metadata_reg_c_1,
+		 ESW_TUN_BRIDGE_INGRESS_PUSH_VLAN_MARK);
+
+	handle = mlx5_add_flow_rules(egress_ft, rule_spec, &flow_act, &dest, 1);
 
 	kvfree(rule_spec);
 	return handle;
···
 static int
 mlx5_esw_bridge_vlan_pop_create(struct mlx5_esw_bridge_vlan *vlan, struct mlx5_eswitch *esw)
 {
-	struct mlx5_pkt_reformat_params reformat_params = {};
 	struct mlx5_pkt_reformat *pkt_reformat;
 
-	if (!BIT(MLX5_CAP_ESW_FLOWTABLE_FDB(esw->dev, reformat_remove)) ||
-	    MLX5_CAP_GEN_2(esw->dev, max_reformat_remove_size) < sizeof(struct vlan_hdr) ||
-	    MLX5_CAP_GEN_2(esw->dev, max_reformat_remove_offset) <
-	    offsetof(struct vlan_ethhdr, h_vlan_proto)) {
+	if (!mlx5_esw_bridge_pkt_reformat_vlan_pop_supported(esw)) {
 		esw_warn(esw->dev, "Packet reformat REMOVE_HEADER is not supported\n");
 		return -EOPNOTSUPP;
 	}
 
-	reformat_params.type = MLX5_REFORMAT_TYPE_REMOVE_HDR;
-	reformat_params.param_0 = MLX5_REFORMAT_CONTEXT_ANCHOR_MAC_START;
-	reformat_params.param_1 = offsetof(struct vlan_ethhdr, h_vlan_proto);
-	reformat_params.size = sizeof(struct vlan_hdr);
-	pkt_reformat = mlx5_packet_reformat_alloc(esw->dev,
-						  &reformat_params,
-						  MLX5_FLOW_NAMESPACE_FDB);
+	pkt_reformat = mlx5_esw_bridge_pkt_reformat_vlan_pop_create(esw);
 	if (IS_ERR(pkt_reformat)) {
 		esw_warn(esw->dev, "Failed to alloc packet reformat REMOVE_HEADER (err=%ld)\n",
 			 PTR_ERR(pkt_reformat));
···
 {
 	mlx5_packet_reformat_dealloc(esw->dev, vlan->pkt_reformat_pop);
 	vlan->pkt_reformat_pop = NULL;
+}
+
+static int
+mlx5_esw_bridge_vlan_push_mark_create(struct mlx5_esw_bridge_vlan *vlan, struct mlx5_eswitch *esw)
+{
+	u8 action[MLX5_UN_SZ_BYTES(set_add_copy_action_in_auto)] = {};
+	struct mlx5_modify_hdr *pkt_mod_hdr;
+
+	MLX5_SET(set_action_in, action, action_type, MLX5_ACTION_TYPE_SET);
+	MLX5_SET(set_action_in, action, field, MLX5_ACTION_IN_FIELD_METADATA_REG_C_1);
+	MLX5_SET(set_action_in, action, offset, 8);
+	MLX5_SET(set_action_in, action, length, ESW_TUN_OPTS_BITS + ESW_TUN_ID_BITS);
+	MLX5_SET(set_action_in, action, data, ESW_TUN_BRIDGE_INGRESS_PUSH_VLAN);
+
+	pkt_mod_hdr = mlx5_modify_header_alloc(esw->dev, MLX5_FLOW_NAMESPACE_FDB, 1, action);
+	if (IS_ERR(pkt_mod_hdr))
+		return PTR_ERR(pkt_mod_hdr);
+
+	vlan->pkt_mod_hdr_push_mark = pkt_mod_hdr;
+	return 0;
+}
+
+static void
+mlx5_esw_bridge_vlan_push_mark_cleanup(struct mlx5_esw_bridge_vlan *vlan, struct mlx5_eswitch *esw)
+{
+	mlx5_modify_header_dealloc(esw->dev, vlan->pkt_mod_hdr_push_mark);
+	vlan->pkt_mod_hdr_push_mark = NULL;
 }
 
 static struct mlx5_esw_bridge_vlan *
···
 		err = mlx5_esw_bridge_vlan_push_create(vlan, esw);
 		if (err)
 			goto err_vlan_push;
+
+		err = mlx5_esw_bridge_vlan_push_mark_create(vlan, esw);
+		if (err)
+			goto err_vlan_push_mark;
 	}
 	if (flags & BRIDGE_VLAN_INFO_UNTAGGED) {
 		err = mlx5_esw_bridge_vlan_pop_create(vlan, esw);
···
 	if (vlan->pkt_reformat_pop)
 		mlx5_esw_bridge_vlan_pop_cleanup(vlan, esw);
 err_vlan_pop:
+	if (vlan->pkt_mod_hdr_push_mark)
+		mlx5_esw_bridge_vlan_push_mark_cleanup(vlan, esw);
+err_vlan_push_mark:
 	if (vlan->pkt_reformat_push)
 		mlx5_esw_bridge_vlan_push_cleanup(vlan, esw);
 err_vlan_push:
···
 static void mlx5_esw_bridge_vlan_flush(struct mlx5_esw_bridge_vlan *vlan,
 				       struct mlx5_esw_bridge *bridge)
 {
+	struct mlx5_eswitch *esw = bridge->br_offloads->esw;
 	struct mlx5_esw_bridge_fdb_entry *entry, *tmp;
 
 	list_for_each_entry_safe(entry, tmp, &vlan->fdb_list, vlan_list) {
···
 	}
 
 	if (vlan->pkt_reformat_pop)
-		mlx5_esw_bridge_vlan_pop_cleanup(vlan, bridge->br_offloads->esw);
+		mlx5_esw_bridge_vlan_pop_cleanup(vlan, esw);
+	if (vlan->pkt_mod_hdr_push_mark)
+		mlx5_esw_bridge_vlan_push_mark_cleanup(vlan, esw);
 	if (vlan->pkt_reformat_push)
-		mlx5_esw_bridge_vlan_push_cleanup(vlan, bridge->br_offloads->esw);
+		mlx5_esw_bridge_vlan_push_cleanup(vlan, esw);
 }
 
 static void mlx5_esw_bridge_vlan_cleanup(struct mlx5_esw_bridge_port *port,

drivers/net/ethernet/mellanox/mlx5/core/esw/bridge_priv.h

···
 	struct list_head fdb_list;
 	struct mlx5_pkt_reformat *pkt_reformat_push;
 	struct mlx5_pkt_reformat *pkt_reformat_pop;
+	struct mlx5_modify_hdr *pkt_mod_hdr_push_mark;
 };
 
 struct mlx5_esw_bridge_port {

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

···
 	MLX5_ESW_ATTR_FLAG_NO_IN_PORT    = BIT(2),
 	MLX5_ESW_ATTR_FLAG_SRC_REWRITE   = BIT(3),
 	MLX5_ESW_ATTR_FLAG_SAMPLE        = BIT(4),
+	MLX5_ESW_ATTR_FLAG_ACCEPT        = BIT(5),
 };
+
+/* Returns true if any of the flags that require skipping further TC/NF processing are set. */
+static inline bool
+mlx5_esw_attr_flags_skip(u32 attr_flags)
+{
+	return attr_flags & (MLX5_ESW_ATTR_FLAG_SLOW_PATH | MLX5_ESW_ATTR_FLAG_ACCEPT);
+}
 
 struct mlx5_esw_flow_attr {
 	struct mlx5_eswitch_rep *in_rep;

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

···
 	} else if (attr->dest_ft) {
 		esw_setup_ft_dest(dest, flow_act, esw, attr, spec, *i);
 		(*i)++;
-	} else if (attr->flags & MLX5_ESW_ATTR_FLAG_SLOW_PATH) {
+	} else if (mlx5_esw_attr_flags_skip(attr->flags)) {
 		esw_setup_slow_path_dest(dest, flow_act, chains, *i);
 		(*i)++;
 	} else if (attr->dest_chain) {
···
 
 	if (attr->dest_ft) {
 		esw_cleanup_decap_indir(esw, attr);
-	} else if (!(attr->flags & MLX5_ESW_ATTR_FLAG_SLOW_PATH)) {
+	} else if (!mlx5_esw_attr_flags_skip(attr->flags)) {
 		if (attr->dest_chain)
 			esw_cleanup_chain_dest(chains, attr->dest_chain, 1, 0);
 		else if (esw_is_indir_table(esw, attr))
···
 
 	mlx5_del_flow_rules(rule);
 
-	if (!(attr->flags & MLX5_ESW_ATTR_FLAG_SLOW_PATH)) {
+	if (!mlx5_esw_attr_flags_skip(attr->flags)) {
 		/* unref the term table */
 		for (i = 0; i < MLX5_MAX_FLOW_FWD_VPORTS; i++) {
 			if (esw_attr->dests[i].termtbl)

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

···
 
 	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_esw_attr_flags_skip(attr->flags) ||
 	    !mlx5_eswitch_offload_is_uplink_port(esw, spec))
 		return false;
 

drivers/net/ethernet/mellanox/mlx5/core/mlx5_irq.h

···
 
 #define MLX5_COMP_EQS_PER_SF 8
 
-#define MLX5_IRQ_EQ_CTRL (0)
-
 struct mlx5_irq;
 
 int mlx5_irq_table_init(struct mlx5_core_dev *dev);

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

···
 	snprintf(name, MLX5_MAX_IRQ_NAME, "%s%d", pool->name, vecidx);
 }
 
-static void irq_set_name(char *name, int vecidx)
+static void irq_set_name(struct mlx5_irq_pool *pool, char *name, int vecidx)
 {
-	if (vecidx == 0) {
+	if (!pool->xa_num_irqs.max) {
+		/* in case we only have a single irq for the device */
+		snprintf(name, MLX5_MAX_IRQ_NAME, "mlx5_combined%d", vecidx);
+		return;
+	}
+
+	if (vecidx == pool->xa_num_irqs.max) {
 		snprintf(name, MLX5_MAX_IRQ_NAME, "mlx5_async%d", vecidx);
 		return;
 	}
 
-	snprintf(name, MLX5_MAX_IRQ_NAME, "mlx5_comp%d",
-		 vecidx - MLX5_IRQ_VEC_COMP_BASE);
+	snprintf(name, MLX5_MAX_IRQ_NAME, "mlx5_comp%d", vecidx);
+}
+
+static bool irq_pool_is_sf_pool(struct mlx5_irq_pool *pool)
+{
+	return !strncmp("mlx5_sf", pool->name, strlen("mlx5_sf"));
 }
 
 static struct mlx5_irq *irq_request(struct mlx5_irq_pool *pool, int i)
···
 	if (!irq)
 		return ERR_PTR(-ENOMEM);
 	irq->irqn = pci_irq_vector(dev->pdev, i);
-	if (!pool->name[0])
-		irq_set_name(name, i);
+	if (!irq_pool_is_sf_pool(pool))
+		irq_set_name(pool, name, i);
 	else
 		irq_sf_set_name(pool, name, i);
 	ATOMIC_INIT_NOTIFIER_HEAD(&irq->nh);
···
 	if (IS_ERR(irq) || !affinity)
 		goto unlock;
 	cpumask_copy(irq->mask, affinity);
+	if (!irq_pool_is_sf_pool(pool) && !pool->xa_num_irqs.max &&
+	    cpumask_empty(irq->mask))
+		cpumask_set_cpu(0, irq->mask);
 	irq_set_affinity_hint(irq->irqn, irq->mask);
 unlock:
 	mutex_unlock(&pool->lock);
···
 	}
 pf_irq:
 	pool = irq_table->pf_pool;
+	vecidx = (vecidx == MLX5_IRQ_EQ_CTRL) ? pool->xa_num_irqs.max : vecidx;
 	irq = irq_pool_request_vector(pool, vecidx, affinity);
 out:
 	if (IS_ERR(irq))
···
 
 int mlx5_irq_table_get_num_comp(struct mlx5_irq_table *table)
 {
+	if (!table->pf_pool->xa_num_irqs.max)
+		return 1;
 	return table->pf_pool->xa_num_irqs.max - table->pf_pool->xa_num_irqs.min;
 }
 
···
 	if (mlx5_core_is_sf(dev))
 		return 0;
 
-	pf_vec = MLX5_CAP_GEN(dev, num_ports) * num_online_cpus() +
-		 MLX5_IRQ_VEC_COMP_BASE;
+	pf_vec = MLX5_CAP_GEN(dev, num_ports) * num_online_cpus() + 1;
 	pf_vec = min_t(int, pf_vec, num_eqs);
-	if (pf_vec <= MLX5_IRQ_VEC_COMP_BASE)
-		return -ENOMEM;
 
 	total_vec = pf_vec;
 	if (mlx5_sf_max_functions(dev))
 		total_vec += MLX5_IRQ_CTRL_SF_MAX +
 			MLX5_COMP_EQS_PER_SF * mlx5_sf_max_functions(dev);
 
-	total_vec = pci_alloc_irq_vectors(dev->pdev, MLX5_IRQ_VEC_COMP_BASE + 1,
-					  total_vec, PCI_IRQ_MSIX);
+	total_vec = pci_alloc_irq_vectors(dev->pdev, 1, total_vec, PCI_IRQ_MSIX);
 	if (total_vec < 0)
 		return total_vec;
 	pf_vec = min(pf_vec, total_vec);

include/linux/mlx5/driver.h

···
 
 #define MLX5_ADEV_NAME "mlx5_core"
 
+#define MLX5_IRQ_EQ_CTRL (U8_MAX)
+
 enum {
 	MLX5_BOARD_ID_LEN = 64,
 };

include/linux/mlx5/eq.h

···
 #ifndef MLX5_CORE_EQ_H
 #define MLX5_CORE_EQ_H
 
-#define MLX5_IRQ_VEC_COMP_BASE 1
 #define MLX5_NUM_CMD_EQE   (32)
 #define MLX5_NUM_ASYNC_EQE (0x1000)
 #define MLX5_NUM_SPARE_EQE (0x80)

include/linux/mlx5/eswitch.h

···
 #define ESW_TUN_OPTS_MASK GENMASK(31 - ESW_TUN_ID_BITS - ESW_RESERVED_BITS, ESW_TUN_OPTS_OFFSET)
 #define ESW_TUN_MASK GENMASK(31 - ESW_RESERVED_BITS, ESW_TUN_OFFSET)
 #define ESW_TUN_ID_SLOW_TABLE_GOTO_VPORT 0 /* 0 is not a valid tunnel id */
+#define ESW_TUN_ID_BRIDGE_INGRESS_PUSH_VLAN ESW_TUN_ID_SLOW_TABLE_GOTO_VPORT
 /* 0x7FF is a reserved mapping */
 #define ESW_TUN_OPTS_SLOW_TABLE_GOTO_VPORT GENMASK(ESW_TUN_OPTS_BITS - 1, 0)
 #define ESW_TUN_SLOW_TABLE_GOTO_VPORT ((ESW_TUN_ID_SLOW_TABLE_GOTO_VPORT << ESW_TUN_OPTS_BITS) | \
 				       ESW_TUN_OPTS_SLOW_TABLE_GOTO_VPORT)
 #define ESW_TUN_SLOW_TABLE_GOTO_VPORT_MARK ESW_TUN_OPTS_MASK
+/* 0x7FE is a reserved mapping for bridge ingress push vlan mark */
+#define ESW_TUN_OPTS_BRIDGE_INGRESS_PUSH_VLAN (ESW_TUN_OPTS_SLOW_TABLE_GOTO_VPORT - 1)
+#define ESW_TUN_BRIDGE_INGRESS_PUSH_VLAN ((ESW_TUN_ID_BRIDGE_INGRESS_PUSH_VLAN << \
+					   ESW_TUN_OPTS_BITS) | \
+					  ESW_TUN_OPTS_BRIDGE_INGRESS_PUSH_VLAN)
+#define ESW_TUN_BRIDGE_INGRESS_PUSH_VLAN_MARK \
+	GENMASK(31 - ESW_TUN_ID_BITS - ESW_RESERVED_BITS, \
+		ESW_TUN_OPTS_OFFSET + 1)
 
 u8 mlx5_eswitch_mode(struct mlx5_core_dev *dev);
 u16 mlx5_eswitch_get_total_vports(const struct mlx5_core_dev *dev);