1 files changed, 112 insertions, 225 deletions

diff --git a/drivers/net/ethernet/mellanox/mlx5/core/eswitch_offloads.c b/drivers/net/ethernet/mellanox/mlx5/core/eswitch_offloads.c
index c981fa77f439..2a98375a0abf 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/eswitch_offloads.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/eswitch_offloads.c
@@ -179,15 +179,14 @@ mlx5_eswitch_set_rule_source_port(struct mlx5_eswitch *esw,
 
 static int
 esw_setup_decap_indir(struct mlx5_eswitch *esw,
-		      struct mlx5_flow_attr *attr,
-		      struct mlx5_flow_spec *spec)
+		      struct mlx5_flow_attr *attr)
 {
 	struct mlx5_flow_table *ft;
 
 	if (!(attr->flags & MLX5_ATTR_FLAG_SRC_REWRITE))
 		return -EOPNOTSUPP;
 
-	ft = mlx5_esw_indir_table_get(esw, attr, spec,
+	ft = mlx5_esw_indir_table_get(esw, attr,
 				      mlx5_esw_indir_table_decap_vport(attr), true);
 	return PTR_ERR_OR_ZERO(ft);
 }
@@ -197,7 +196,7 @@ esw_cleanup_decap_indir(struct mlx5_eswitch *esw,
 			struct mlx5_flow_attr *attr)
 {
 	if (mlx5_esw_indir_table_decap_vport(attr))
-		mlx5_esw_indir_table_put(esw, attr,
+		mlx5_esw_indir_table_put(esw,
 					 mlx5_esw_indir_table_decap_vport(attr),
 					 true);
 }
@@ -235,7 +234,6 @@ esw_setup_ft_dest(struct mlx5_flow_destination *dest,
 		  struct mlx5_flow_act *flow_act,
 		  struct mlx5_eswitch *esw,
 		  struct mlx5_flow_attr *attr,
-		  struct mlx5_flow_spec *spec,
 		  int i)
 {
 	flow_act->flags |= FLOW_ACT_IGNORE_FLOW_LEVEL;
@@ -243,7 +241,7 @@ esw_setup_ft_dest(struct mlx5_flow_destination *dest,
 	dest[i].ft = attr->dest_ft;
 
 	if (mlx5_esw_indir_table_decap_vport(attr))
-		return esw_setup_decap_indir(esw, attr, spec);
+		return esw_setup_decap_indir(esw, attr);
 	return 0;
 }
 
@@ -298,7 +296,7 @@ static void esw_put_dest_tables_loop(struct mlx5_eswitch *esw, struct mlx5_flow_
 			mlx5_chains_put_table(chains, 0, 1, 0);
 		else if (mlx5_esw_indir_table_needed(esw, attr, esw_attr->dests[i].rep->vport,
 						     esw_attr->dests[i].mdev))
-			mlx5_esw_indir_table_put(esw, attr, esw_attr->dests[i].rep->vport,
+			mlx5_esw_indir_table_put(esw, esw_attr->dests[i].rep->vport,
 						 false);
 }
 
@@ -384,7 +382,6 @@ esw_setup_indir_table(struct mlx5_flow_destination *dest,
 		      struct mlx5_flow_act *flow_act,
 		      struct mlx5_eswitch *esw,
 		      struct mlx5_flow_attr *attr,
-		      struct mlx5_flow_spec *spec,
 		      bool ignore_flow_lvl,
 		      int *i)
 {
@@ -399,7 +396,7 @@ esw_setup_indir_table(struct mlx5_flow_destination *dest,
 			flow_act->flags |= FLOW_ACT_IGNORE_FLOW_LEVEL;
 		dest[*i].type = MLX5_FLOW_DESTINATION_TYPE_FLOW_TABLE;
 
-		dest[*i].ft = mlx5_esw_indir_table_get(esw, attr, spec,
+		dest[*i].ft = mlx5_esw_indir_table_get(esw, attr,
 						       esw_attr->dests[j].rep->vport, false);
 		if (IS_ERR(dest[*i].ft)) {
 			err = PTR_ERR(dest[*i].ft);
@@ -408,7 +405,7 @@ esw_setup_indir_table(struct mlx5_flow_destination *dest,
 	}
 
 	if (mlx5_esw_indir_table_decap_vport(attr)) {
-		err = esw_setup_decap_indir(esw, attr, spec);
+		err = esw_setup_decap_indir(esw, attr);
 		if (err)
 			goto err_indir_tbl_get;
 	}
@@ -446,7 +443,7 @@ esw_setup_vport_dest(struct mlx5_flow_destination *dest, struct mlx5_flow_act *f
 			MLX5_CAP_GEN(esw_attr->dests[attr_idx].mdev, vhca_id);
 		dest[dest_idx].vport.flags |= MLX5_FLOW_DEST_VPORT_VHCA_ID;
 		if (dest[dest_idx].vport.num == MLX5_VPORT_UPLINK &&
-		    mlx5_lag_mpesw_is_activated(esw->dev))
+		    mlx5_lag_is_mpesw(esw->dev))
 			dest[dest_idx].type = MLX5_FLOW_DESTINATION_TYPE_UPLINK;
 	}
 	if (esw_attr->dests[attr_idx].flags & MLX5_ESW_DEST_ENCAP_VALID) {
@@ -511,14 +508,14 @@ esw_setup_dests(struct mlx5_flow_destination *dest,
 		err = esw_setup_mtu_dest(dest, &attr->meter_attr, *i);
 		(*i)++;
 	} else if (esw_is_indir_table(esw, attr)) {
-		err = esw_setup_indir_table(dest, flow_act, esw, attr, spec, true, i);
+		err = esw_setup_indir_table(dest, flow_act, esw, attr, true, i);
 	} else if (esw_is_chain_src_port_rewrite(esw, esw_attr)) {
 		err = esw_setup_chain_src_port_rewrite(dest, flow_act, esw, chains, attr, i);
 	} else {
 		*i = esw_setup_vport_dests(dest, flow_act, esw, esw_attr, *i);
 
 		if (attr->dest_ft) {
-			err = esw_setup_ft_dest(dest, flow_act, esw, attr, spec, *i);
+			err = esw_setup_ft_dest(dest, flow_act, esw, attr, *i);
 			(*i)++;
 		} else if (attr->dest_chain) {
 			err = esw_setup_chain_dest(dest, flow_act, chains, attr->dest_chain,
@@ -582,16 +579,16 @@ mlx5_eswitch_add_offloaded_rule(struct mlx5_eswitch *esw,
 	if (esw->mode != MLX5_ESWITCH_OFFLOADS)
 		return ERR_PTR(-EOPNOTSUPP);
 
+	if (!mlx5_eswitch_vlan_actions_supported(esw->dev, 1))
+		return ERR_PTR(-EOPNOTSUPP);
+
 	dest = kcalloc(MLX5_MAX_FLOW_FWD_VPORTS + 1, sizeof(*dest), GFP_KERNEL);
 	if (!dest)
 		return ERR_PTR(-ENOMEM);
 
 	flow_act.action = attr->action;
-	/* if per flow vlan pop/push is emulated, don't set that into the firmware */
-	if (!mlx5_eswitch_vlan_actions_supported(esw->dev, 1))
-		flow_act.action &= ~(MLX5_FLOW_CONTEXT_ACTION_VLAN_PUSH |
-				     MLX5_FLOW_CONTEXT_ACTION_VLAN_POP);
-	else if (flow_act.action & MLX5_FLOW_CONTEXT_ACTION_VLAN_PUSH) {
+
+	if (flow_act.action & MLX5_FLOW_CONTEXT_ACTION_VLAN_PUSH) {
 		flow_act.vlan[0].ethtype = ntohs(esw_attr->vlan_proto[0]);
 		flow_act.vlan[0].vid = esw_attr->vlan_vid[0];
 		flow_act.vlan[0].prio = esw_attr->vlan_prio[0];
@@ -727,7 +724,7 @@ mlx5_eswitch_add_fwd_rule(struct mlx5_eswitch *esw,
 	flow_act.action = MLX5_FLOW_CONTEXT_ACTION_FWD_DEST;
 	for (i = 0; i < esw_attr->split_count; i++) {
 		if (esw_is_indir_table(esw, attr))
-			err = esw_setup_indir_table(dest, &flow_act, esw, attr, spec, false, &i);
+			err = esw_setup_indir_table(dest, &flow_act, esw, attr, false, &i);
 		else if (esw_is_chain_src_port_rewrite(esw, esw_attr))
 			err = esw_setup_chain_src_port_rewrite(dest, &flow_act, esw, chains, attr,
 							       &i);
@@ -832,204 +829,6 @@ mlx5_eswitch_del_fwd_rule(struct mlx5_eswitch *esw,
 	__mlx5_eswitch_del_rule(esw, rule, attr, true);
 }
 
-static int esw_set_global_vlan_pop(struct mlx5_eswitch *esw, u8 val)
-{
-	struct mlx5_eswitch_rep *rep;
-	unsigned long i;
-	int err = 0;
-
-	esw_debug(esw->dev, "%s applying global %s policy\n", __func__, val ? "pop" : "none");
-	mlx5_esw_for_each_host_func_vport(esw, i, rep, esw->esw_funcs.num_vfs) {
-		if (atomic_read(&rep->rep_data[REP_ETH].state) != REP_LOADED)
-			continue;
-
-		err = __mlx5_eswitch_set_vport_vlan(esw, rep->vport, 0, 0, val);
-		if (err)
-			goto out;
-	}
-
-out:
-	return err;
-}
-
-static struct mlx5_eswitch_rep *
-esw_vlan_action_get_vport(struct mlx5_esw_flow_attr *attr, bool push, bool pop)
-{
-	struct mlx5_eswitch_rep *in_rep, *out_rep, *vport = NULL;
-
-	in_rep  = attr->in_rep;
-	out_rep = attr->dests[0].rep;
-
-	if (push)
-		vport = in_rep;
-	else if (pop)
-		vport = out_rep;
-	else
-		vport = in_rep;
-
-	return vport;
-}
-
-static int esw_add_vlan_action_check(struct mlx5_esw_flow_attr *attr,
-				     bool push, bool pop, bool fwd)
-{
-	struct mlx5_eswitch_rep *in_rep, *out_rep;
-
-	if ((push || pop) && !fwd)
-		goto out_notsupp;
-
-	in_rep  = attr->in_rep;
-	out_rep = attr->dests[0].rep;
-
-	if (push && in_rep->vport == MLX5_VPORT_UPLINK)
-		goto out_notsupp;
-
-	if (pop && out_rep->vport == MLX5_VPORT_UPLINK)
-		goto out_notsupp;
-
-	/* vport has vlan push configured, can't offload VF --> wire rules w.o it */
-	if (!push && !pop && fwd)
-		if (in_rep->vlan && out_rep->vport == MLX5_VPORT_UPLINK)
-			goto out_notsupp;
-
-	/* protects against (1) setting rules with different vlans to push and
-	 * (2) setting rules w.o vlans (attr->vlan = 0) && w. vlans to push (!= 0)
-	 */
-	if (push && in_rep->vlan_refcount && (in_rep->vlan != attr->vlan_vid[0]))
-		goto out_notsupp;
-
-	return 0;
-
-out_notsupp:
-	return -EOPNOTSUPP;
-}
-
-int mlx5_eswitch_add_vlan_action(struct mlx5_eswitch *esw,
-				 struct mlx5_flow_attr *attr)
-{
-	struct offloads_fdb *offloads = &esw->fdb_table.offloads;
-	struct mlx5_esw_flow_attr *esw_attr = attr->esw_attr;
-	struct mlx5_eswitch_rep *vport = NULL;
-	bool push, pop, fwd;
-	int err = 0;
-
-	/* nop if we're on the vlan push/pop non emulation mode */
-	if (mlx5_eswitch_vlan_actions_supported(esw->dev, 1))
-		return 0;
-
-	push = !!(attr->action & MLX5_FLOW_CONTEXT_ACTION_VLAN_PUSH);
-	pop  = !!(attr->action & MLX5_FLOW_CONTEXT_ACTION_VLAN_POP);
-	fwd  = !!((attr->action & MLX5_FLOW_CONTEXT_ACTION_FWD_DEST) &&
-		   !attr->dest_chain);
-
-	mutex_lock(&esw->state_lock);
-
-	err = esw_add_vlan_action_check(esw_attr, push, pop, fwd);
-	if (err)
-		goto unlock;
-
-	attr->flags &= ~MLX5_ATTR_FLAG_VLAN_HANDLED;
-
-	vport = esw_vlan_action_get_vport(esw_attr, push, pop);
-
-	if (!push && !pop && fwd) {
-		/* tracks VF --> wire rules without vlan push action */
-		if (esw_attr->dests[0].rep->vport == MLX5_VPORT_UPLINK) {
-			vport->vlan_refcount++;
-			attr->flags |= MLX5_ATTR_FLAG_VLAN_HANDLED;
-		}
-
-		goto unlock;
-	}
-
-	if (!push && !pop)
-		goto unlock;
-
-	if (!(offloads->vlan_push_pop_refcount)) {
-		/* it's the 1st vlan rule, apply global vlan pop policy */
-		err = esw_set_global_vlan_pop(esw, SET_VLAN_STRIP);
-		if (err)
-			goto out;
-	}
-	offloads->vlan_push_pop_refcount++;
-
-	if (push) {
-		if (vport->vlan_refcount)
-			goto skip_set_push;
-
-		err = __mlx5_eswitch_set_vport_vlan(esw, vport->vport, esw_attr->vlan_vid[0],
-						    0, SET_VLAN_INSERT | SET_VLAN_STRIP);
-		if (err)
-			goto out;
-		vport->vlan = esw_attr->vlan_vid[0];
-skip_set_push:
-		vport->vlan_refcount++;
-	}
-out:
-	if (!err)
-		attr->flags |= MLX5_ATTR_FLAG_VLAN_HANDLED;
-unlock:
-	mutex_unlock(&esw->state_lock);
-	return err;
-}
-
-int mlx5_eswitch_del_vlan_action(struct mlx5_eswitch *esw,
-				 struct mlx5_flow_attr *attr)
-{
-	struct offloads_fdb *offloads = &esw->fdb_table.offloads;
-	struct mlx5_esw_flow_attr *esw_attr = attr->esw_attr;
-	struct mlx5_eswitch_rep *vport = NULL;
-	bool push, pop, fwd;
-	int err = 0;
-
-	/* nop if we're on the vlan push/pop non emulation mode */
-	if (mlx5_eswitch_vlan_actions_supported(esw->dev, 1))
-		return 0;
-
-	if (!(attr->flags & MLX5_ATTR_FLAG_VLAN_HANDLED))
-		return 0;
-
-	push = !!(attr->action & MLX5_FLOW_CONTEXT_ACTION_VLAN_PUSH);
-	pop  = !!(attr->action & MLX5_FLOW_CONTEXT_ACTION_VLAN_POP);
-	fwd  = !!(attr->action & MLX5_FLOW_CONTEXT_ACTION_FWD_DEST);
-
-	mutex_lock(&esw->state_lock);
-
-	vport = esw_vlan_action_get_vport(esw_attr, push, pop);
-
-	if (!push && !pop && fwd) {
-		/* tracks VF --> wire rules without vlan push action */
-		if (esw_attr->dests[0].rep->vport == MLX5_VPORT_UPLINK)
-			vport->vlan_refcount--;
-
-		goto out;
-	}
-
-	if (push) {
-		vport->vlan_refcount--;
-		if (vport->vlan_refcount)
-			goto skip_unset_push;
-
-		vport->vlan = 0;
-		err = __mlx5_eswitch_set_vport_vlan(esw, vport->vport,
-						    0, 0, SET_VLAN_STRIP);
-		if (err)
-			goto out;
-	}
-
-skip_unset_push:
-	offloads->vlan_push_pop_refcount--;
-	if (offloads->vlan_push_pop_refcount)
-		goto out;
-
-	/* no more vlan rules, stop global vlan pop policy */
-	err = esw_set_global_vlan_pop(esw, 0);
-
-out:
-	mutex_unlock(&esw->state_lock);
-	return err;
-}
-
 struct mlx5_flow_handle *
 mlx5_eswitch_add_send_to_vport_rule(struct mlx5_eswitch *on_esw,
 				    struct mlx5_eswitch *from_esw,
@@ -2406,7 +2205,7 @@ static void mlx5_esw_offloads_rep_cleanup(struct mlx5_eswitch *esw,
 	kfree(rep);
 }
 
-void esw_offloads_cleanup_reps(struct mlx5_eswitch *esw)
+static void esw_offloads_cleanup_reps(struct mlx5_eswitch *esw)
 {
 	struct mlx5_eswitch_rep *rep;
 	unsigned long i;
@@ -2416,7 +2215,7 @@ void esw_offloads_cleanup_reps(struct mlx5_eswitch *esw)
 	xa_destroy(&esw->offloads.vport_reps);
 }
 
-int esw_offloads_init_reps(struct mlx5_eswitch *esw)
+static int esw_offloads_init_reps(struct mlx5_eswitch *esw)
 {
 	struct mlx5_vport *vport;
 	unsigned long i;
@@ -2436,6 +2235,94 @@ err:
 	return err;
 }
 
+static int esw_port_metadata_set(struct devlink *devlink, u32 id,
+				 struct devlink_param_gset_ctx *ctx)
+{
+	struct mlx5_core_dev *dev = devlink_priv(devlink);
+	struct mlx5_eswitch *esw = dev->priv.eswitch;
+	int err = 0;
+
+	down_write(&esw->mode_lock);
+	if (mlx5_esw_is_fdb_created(esw)) {
+		err = -EBUSY;
+		goto done;
+	}
+	if (!mlx5_esw_vport_match_metadata_supported(esw)) {
+		err = -EOPNOTSUPP;
+		goto done;
+	}
+	if (ctx->val.vbool)
+		esw->flags |= MLX5_ESWITCH_VPORT_MATCH_METADATA;
+	else
+		esw->flags &= ~MLX5_ESWITCH_VPORT_MATCH_METADATA;
+done:
+	up_write(&esw->mode_lock);
+	return err;
+}
+
+static int esw_port_metadata_get(struct devlink *devlink, u32 id,
+				 struct devlink_param_gset_ctx *ctx)
+{
+	struct mlx5_core_dev *dev = devlink_priv(devlink);
+
+	ctx->val.vbool = mlx5_eswitch_vport_match_metadata_enabled(dev->priv.eswitch);
+	return 0;
+}
+
+static int esw_port_metadata_validate(struct devlink *devlink, u32 id,
+				      union devlink_param_value val,
+				      struct netlink_ext_ack *extack)
+{
+	struct mlx5_core_dev *dev = devlink_priv(devlink);
+	u8 esw_mode;
+
+	esw_mode = mlx5_eswitch_mode(dev);
+	if (esw_mode == MLX5_ESWITCH_OFFLOADS) {
+		NL_SET_ERR_MSG_MOD(extack,
+				   "E-Switch must either disabled or non switchdev mode");
+		return -EBUSY;
+	}
+	return 0;
+}
+
+static const struct devlink_param esw_devlink_params[] = {
+	DEVLINK_PARAM_DRIVER(MLX5_DEVLINK_PARAM_ID_ESW_PORT_METADATA,
+			     "esw_port_metadata", DEVLINK_PARAM_TYPE_BOOL,
+			     BIT(DEVLINK_PARAM_CMODE_RUNTIME),
+			     esw_port_metadata_get,
+			     esw_port_metadata_set,
+			     esw_port_metadata_validate),
+};
+
+int esw_offloads_init(struct mlx5_eswitch *esw)
+{
+	int err;
+
+	err = esw_offloads_init_reps(esw);
+	if (err)
+		return err;
+
+	err = devl_params_register(priv_to_devlink(esw->dev),
+				   esw_devlink_params,
+				   ARRAY_SIZE(esw_devlink_params));
+	if (err)
+		goto err_params;
+
+	return 0;
+
+err_params:
+	esw_offloads_cleanup_reps(esw);
+	return err;
+}
+
+void esw_offloads_cleanup(struct mlx5_eswitch *esw)
+{
+	devl_params_unregister(priv_to_devlink(esw->dev),
+			       esw_devlink_params,
+			       ARRAY_SIZE(esw_devlink_params));
+	esw_offloads_cleanup_reps(esw);
+}
+
 static void __esw_offloads_unload_rep(struct mlx5_eswitch *esw,
 				      struct mlx5_eswitch_rep *rep, u8 rep_type)
 {
@@ -3575,9 +3462,9 @@ int mlx5_devlink_eswitch_mode_get(struct devlink *devlink, u16 *mode)
 	if (IS_ERR(esw))
 		return PTR_ERR(esw);
 
-	down_write(&esw->mode_lock);
+	down_read(&esw->mode_lock);
 	err = esw_mode_to_devlink(esw->mode, mode);
-	up_write(&esw->mode_lock);
+	up_read(&esw->mode_lock);
 	return err;
 }
 
@@ -3675,9 +3562,9 @@ int mlx5_devlink_eswitch_inline_mode_get(struct devlink *devlink, u8 *mode)
 	if (IS_ERR(esw))
 		return PTR_ERR(esw);
 
-	down_write(&esw->mode_lock);
+	down_read(&esw->mode_lock);
 	err = esw_inline_mode_to_devlink(esw->offloads.inline_mode, mode);
-	up_write(&esw->mode_lock);
+	up_read(&esw->mode_lock);
 	return err;
 }
 
@@ -3749,9 +3636,9 @@ int mlx5_devlink_eswitch_encap_mode_get(struct devlink *devlink,
 	if (IS_ERR(esw))
 		return PTR_ERR(esw);
 
-	down_write(&esw->mode_lock);
+	down_read(&esw->mode_lock);
 	*encap = esw->offloads.encap;
-	up_write(&esw->mode_lock);
+	up_read(&esw->mode_lock);
 	return 0;
 }