Commit 3cd336c5 authored by Jakub Kicinski's avatar Jakub Kicinski
Browse files

Merge branch 'mlxsw-add-support-for-nexthop-objects' 

Ido Schimmel says:

====================
mlxsw: Add support for nexthop objects

This patch set adds support for nexthop objects in mlxsw. Nexthop
objects are treated as another front-end for programming nexthops, in
addition to the existing IPv4 and IPv6 front-ends.

Patch #1 registers a listener to the nexthop notification chain and
parses the nexthop information into the existing mlxsw data structures
that are already used by the IPv4 and IPv6 front-ends. Blackhole
nexthops are currently rejected. Support will be added in a follow-up
patch set.

Patch #2 extends mlxsw to resolve its internal nexthop objects from the
nexthop identifier encoded in the FIB info of the notified routes.

Patch #3 finally removes the limitation of rejecting routes that use
nexthop objects.

Patch #4 adds a selftest.

Patches #5-#8 add generic forwarding selftests that can be used with
veth pairs or physical loopbacks.
====================

Link: https://lore.kernel.org/r/20201119130848.407918-1-idosch@idosch.org


Signed-off-by: default avatarJakub Kicinski <kuba@kernel.org>
parents 30abc9cd e035146d

drivers/net/ethernet/mellanox/mlxsw/spectrum_router.c

+484 −14
Original line number Diff line number Diff line
@@ -2873,6 +2873,7 @@ struct mlxsw_sp_nexthop { 
enum mlxsw_sp_nexthop_group_type {

	MLXSW_SP_NEXTHOP_GROUP_TYPE_IPV4,

	MLXSW_SP_NEXTHOP_GROUP_TYPE_IPV6,

	MLXSW_SP_NEXTHOP_GROUP_TYPE_OBJ,

};



struct mlxsw_sp_nexthop_group_info {
@@ -2894,6 +2895,9 @@ struct mlxsw_sp_nexthop_group { 
		struct {

			struct fib_info *fi;

		} ipv4;

		struct {

			u32 id;

		} obj;

	};

	struct mlxsw_sp_nexthop_group_info *nhgi;

	enum mlxsw_sp_nexthop_group_type type;
@@ -3012,6 +3016,7 @@ struct mlxsw_sp_nexthop_group_cmp_arg { 
	union {

		struct fib_info *fi;

		struct mlxsw_sp_fib6_entry *fib6_entry;

		u32 id;

	};

};
@@ -3074,6 +3079,8 @@ mlxsw_sp_nexthop_group_cmp(struct rhashtable_compare_arg *arg, const void *ptr) 
	case MLXSW_SP_NEXTHOP_GROUP_TYPE_IPV6:

		return !mlxsw_sp_nexthop6_group_cmp(nh_grp,

						    cmp_arg->fib6_entry);

	case MLXSW_SP_NEXTHOP_GROUP_TYPE_OBJ:

		return cmp_arg->id != nh_grp->obj.id;

	default:

		WARN_ON(1);

		return 1;
@@ -3100,6 +3107,8 @@ static u32 mlxsw_sp_nexthop_group_hash_obj(const void *data, u32 len, u32 seed) 
			val ^= jhash(&nh->gw_addr, sizeof(nh->gw_addr), seed);

		}

		return jhash(&val, sizeof(val), seed);

	case MLXSW_SP_NEXTHOP_GROUP_TYPE_OBJ:

		return jhash(&nh_grp->obj.id, sizeof(nh_grp->obj.id), seed);

	default:

		WARN_ON(1);

		return 0;
@@ -3134,6 +3143,8 @@ mlxsw_sp_nexthop_group_hash(const void *data, u32 len, u32 seed) 
		return jhash(&cmp_arg->fi, sizeof(cmp_arg->fi), seed);

	case MLXSW_SP_NEXTHOP_GROUP_TYPE_IPV6:

		return mlxsw_sp_nexthop6_group_hash(cmp_arg->fib6_entry, seed);

	case MLXSW_SP_NEXTHOP_GROUP_TYPE_OBJ:

		return jhash(&cmp_arg->id, sizeof(cmp_arg->id), seed);

	default:

		WARN_ON(1);

		return 0;
@@ -3538,6 +3549,25 @@ mlxsw_sp_nexthop6_group_offload_refresh(struct mlxsw_sp *mlxsw_sp, 
		__mlxsw_sp_nexthop6_group_offload_refresh(nh_grp, fib6_entry);

}



static void

mlxsw_sp_nexthop_obj_group_offload_refresh(struct mlxsw_sp *mlxsw_sp,

					   struct mlxsw_sp_nexthop_group *nh_grp)

{

	/* Do not update the flags if the nexthop group is being destroyed

	 * since:

	 * 1. The nexthop objects is being deleted, in which case the flags are

	 * irrelevant.

	 * 2. The nexthop group was replaced by a newer group, in which case

	 * the flags of the nexthop object were already updated based on the

	 * new group.

	 */

	if (nh_grp->can_destroy)

		return;



	nexthop_set_hw_flags(mlxsw_sp_net(mlxsw_sp), nh_grp->obj.id,

			     nh_grp->nhgi->adj_index_valid, false);

}



static void

mlxsw_sp_nexthop_group_offload_refresh(struct mlxsw_sp *mlxsw_sp,

				       struct mlxsw_sp_nexthop_group *nh_grp)
@@ -3549,6 +3579,9 @@ mlxsw_sp_nexthop_group_offload_refresh(struct mlxsw_sp *mlxsw_sp, 
	case MLXSW_SP_NEXTHOP_GROUP_TYPE_IPV6:

		mlxsw_sp_nexthop6_group_offload_refresh(mlxsw_sp, nh_grp);

		break;

	case MLXSW_SP_NEXTHOP_GROUP_TYPE_OBJ:

		mlxsw_sp_nexthop_obj_group_offload_refresh(mlxsw_sp, nh_grp);

		break;

	}

}
@@ -4088,6 +4121,413 @@ static void mlxsw_sp_nexthop_rif_gone_sync(struct mlxsw_sp *mlxsw_sp, 
	}

}



static int

mlxsw_sp_nexthop_obj_single_validate(struct mlxsw_sp *mlxsw_sp,

				     const struct nh_notifier_single_info *nh,

				     struct netlink_ext_ack *extack)

{

	int err = -EINVAL;



	if (nh->is_reject)

		NL_SET_ERR_MSG_MOD(extack, "Blackhole nexthops are not supported");

	else if (nh->is_fdb)

		NL_SET_ERR_MSG_MOD(extack, "FDB nexthops are not supported");

	else if (nh->has_encap)

		NL_SET_ERR_MSG_MOD(extack, "Encapsulating nexthops are not supported");

	else

		err = 0;



	return err;

}



static int

mlxsw_sp_nexthop_obj_group_validate(struct mlxsw_sp *mlxsw_sp,

				    const struct nh_notifier_grp_info *nh_grp,

				    struct netlink_ext_ack *extack)

{

	int i;



	if (nh_grp->is_fdb) {

		NL_SET_ERR_MSG_MOD(extack, "FDB nexthop groups are not supported");

		return -EINVAL;

	}



	for (i = 0; i < nh_grp->num_nh; i++) {

		const struct nh_notifier_single_info *nh;

		int err;



		nh = &nh_grp->nh_entries[i].nh;

		err = mlxsw_sp_nexthop_obj_single_validate(mlxsw_sp, nh,

							   extack);

		if (err)

			return err;



		/* Device only nexthops with an IPIP device are programmed as

		 * encapsulating adjacency entries.

		 */

		if (!nh->gw_family &&

		    !mlxsw_sp_netdev_ipip_type(mlxsw_sp, nh->dev, NULL)) {

			NL_SET_ERR_MSG_MOD(extack, "Nexthop group entry does not have a gateway");

			return -EINVAL;

		}

	}



	return 0;

}



static int mlxsw_sp_nexthop_obj_validate(struct mlxsw_sp *mlxsw_sp,

					 unsigned long event,

					 struct nh_notifier_info *info)

{

	if (event != NEXTHOP_EVENT_REPLACE)

		return 0;



	if (!info->is_grp)

		return mlxsw_sp_nexthop_obj_single_validate(mlxsw_sp, info->nh,

							    info->extack);

	return mlxsw_sp_nexthop_obj_group_validate(mlxsw_sp, info->nh_grp,

						   info->extack);

}



static bool mlxsw_sp_nexthop_obj_is_gateway(struct mlxsw_sp *mlxsw_sp,

					    const struct nh_notifier_info *info)

{

	const struct net_device *dev;



	if (info->is_grp)

		/* Already validated earlier. */

		return true;



	dev = info->nh->dev;

	return info->nh->gw_family ||

	       mlxsw_sp_netdev_ipip_type(mlxsw_sp, dev, NULL);

}



static int

mlxsw_sp_nexthop_obj_init(struct mlxsw_sp *mlxsw_sp,

			  struct mlxsw_sp_nexthop_group *nh_grp,

			  struct mlxsw_sp_nexthop *nh,

			  struct nh_notifier_single_info *nh_obj, int weight)

{

	struct net_device *dev = nh_obj->dev;

	int err;



	nh->nhgi = nh_grp->nhgi;

	nh->nh_weight = weight;



	switch (nh_obj->gw_family) {

	case AF_INET:

		memcpy(&nh->gw_addr, &nh_obj->ipv4, sizeof(nh_obj->ipv4));

		nh->neigh_tbl = &arp_tbl;

		break;

	case AF_INET6:

		memcpy(&nh->gw_addr, &nh_obj->ipv6, sizeof(nh_obj->ipv6));

#if IS_ENABLED(CONFIG_IPV6)

		nh->neigh_tbl = &nd_tbl;

#endif

		break;

	}



	mlxsw_sp_nexthop_counter_alloc(mlxsw_sp, nh);

	list_add_tail(&nh->router_list_node, &mlxsw_sp->router->nexthop_list);

	nh->ifindex = dev->ifindex;



	err = mlxsw_sp_nexthop_type_init(mlxsw_sp, nh, dev);

	if (err)

		goto err_type_init;



	return 0;



err_type_init:

	list_del(&nh->router_list_node);

	mlxsw_sp_nexthop_counter_free(mlxsw_sp, nh);

	return err;

}



static void mlxsw_sp_nexthop_obj_fini(struct mlxsw_sp *mlxsw_sp,

				      struct mlxsw_sp_nexthop *nh)

{

	mlxsw_sp_nexthop_type_fini(mlxsw_sp, nh);

	list_del(&nh->router_list_node);

	mlxsw_sp_nexthop_counter_free(mlxsw_sp, nh);

}



static int

mlxsw_sp_nexthop_obj_group_info_init(struct mlxsw_sp *mlxsw_sp,

				     struct mlxsw_sp_nexthop_group *nh_grp,

				     struct nh_notifier_info *info)

{

	unsigned int nhs = info->is_grp ? info->nh_grp->num_nh : 1;

	struct mlxsw_sp_nexthop_group_info *nhgi;

	struct mlxsw_sp_nexthop *nh;

	int err, i;



	nhgi = kzalloc(struct_size(nhgi, nexthops, nhs), GFP_KERNEL);

	if (!nhgi)

		return -ENOMEM;

	nh_grp->nhgi = nhgi;

	nhgi->nh_grp = nh_grp;

	nhgi->gateway = mlxsw_sp_nexthop_obj_is_gateway(mlxsw_sp, info);

	nhgi->count = nhs;

	for (i = 0; i < nhgi->count; i++) {

		struct nh_notifier_single_info *nh_obj;

		int weight;



		nh = &nhgi->nexthops[i];

		if (info->is_grp) {

			nh_obj = &info->nh_grp->nh_entries[i].nh;

			weight = info->nh_grp->nh_entries[i].weight;

		} else {

			nh_obj = info->nh;

			weight = 1;

		}

		err = mlxsw_sp_nexthop_obj_init(mlxsw_sp, nh_grp, nh, nh_obj,

						weight);

		if (err)

			goto err_nexthop_obj_init;

	}

	err = mlxsw_sp_nexthop_group_refresh(mlxsw_sp, nh_grp);

	if (err) {

		NL_SET_ERR_MSG_MOD(info->extack, "Failed to write adjacency entries to the device");

		goto err_group_refresh;

	}



	return 0;



err_group_refresh:

	i = nhgi->count;

err_nexthop_obj_init:

	for (i--; i >= 0; i--) {

		nh = &nhgi->nexthops[i];

		mlxsw_sp_nexthop_obj_fini(mlxsw_sp, nh);

	}

	kfree(nhgi);

	return err;

}



static void

mlxsw_sp_nexthop_obj_group_info_fini(struct mlxsw_sp *mlxsw_sp,

				     struct mlxsw_sp_nexthop_group *nh_grp)

{

	struct mlxsw_sp_nexthop_group_info *nhgi = nh_grp->nhgi;

	int i;



	for (i = nhgi->count - 1; i >= 0; i--) {

		struct mlxsw_sp_nexthop *nh = &nhgi->nexthops[i];



		mlxsw_sp_nexthop_obj_fini(mlxsw_sp, nh);

	}

	mlxsw_sp_nexthop_group_refresh(mlxsw_sp, nh_grp);

	WARN_ON_ONCE(nhgi->adj_index_valid);

	kfree(nhgi);

}



static struct mlxsw_sp_nexthop_group *

mlxsw_sp_nexthop_obj_group_create(struct mlxsw_sp *mlxsw_sp,

				  struct nh_notifier_info *info)

{

	struct mlxsw_sp_nexthop_group *nh_grp;

	int err;



	nh_grp = kzalloc(sizeof(*nh_grp), GFP_KERNEL);

	if (!nh_grp)

		return ERR_PTR(-ENOMEM);

	INIT_LIST_HEAD(&nh_grp->fib_list);

	nh_grp->type = MLXSW_SP_NEXTHOP_GROUP_TYPE_OBJ;

	nh_grp->obj.id = info->id;



	err = mlxsw_sp_nexthop_obj_group_info_init(mlxsw_sp, nh_grp, info);

	if (err)

		goto err_nexthop_group_info_init;



	nh_grp->can_destroy = false;



	return nh_grp;



err_nexthop_group_info_init:

	kfree(nh_grp);

	return ERR_PTR(err);

}



static void

mlxsw_sp_nexthop_obj_group_destroy(struct mlxsw_sp *mlxsw_sp,

				   struct mlxsw_sp_nexthop_group *nh_grp)

{

	if (!nh_grp->can_destroy)

		return;

	mlxsw_sp_nexthop_obj_group_info_fini(mlxsw_sp, nh_grp);

	WARN_ON_ONCE(!list_empty(&nh_grp->fib_list));

	kfree(nh_grp);

}



static struct mlxsw_sp_nexthop_group *

mlxsw_sp_nexthop_obj_group_lookup(struct mlxsw_sp *mlxsw_sp, u32 id)

{

	struct mlxsw_sp_nexthop_group_cmp_arg cmp_arg;



	cmp_arg.type = MLXSW_SP_NEXTHOP_GROUP_TYPE_OBJ;

	cmp_arg.id = id;

	return rhashtable_lookup_fast(&mlxsw_sp->router->nexthop_group_ht,

				      &cmp_arg,

				      mlxsw_sp_nexthop_group_ht_params);

}



static int mlxsw_sp_nexthop_obj_group_add(struct mlxsw_sp *mlxsw_sp,

					  struct mlxsw_sp_nexthop_group *nh_grp)

{

	return mlxsw_sp_nexthop_group_insert(mlxsw_sp, nh_grp);

}



static int

mlxsw_sp_nexthop_obj_group_replace(struct mlxsw_sp *mlxsw_sp,

				   struct mlxsw_sp_nexthop_group *nh_grp,

				   struct mlxsw_sp_nexthop_group *old_nh_grp,

				   struct netlink_ext_ack *extack)

{

	struct mlxsw_sp_nexthop_group_info *old_nhgi = old_nh_grp->nhgi;

	struct mlxsw_sp_nexthop_group_info *new_nhgi = nh_grp->nhgi;

	int err;



	old_nh_grp->nhgi = new_nhgi;

	new_nhgi->nh_grp = old_nh_grp;

	nh_grp->nhgi = old_nhgi;

	old_nhgi->nh_grp = nh_grp;



	if (old_nhgi->adj_index_valid && new_nhgi->adj_index_valid) {

		/* Both the old adjacency index and the new one are valid.

		 * Routes are currently using the old one. Tell the device to

		 * replace the old adjacency index with the new one.

		 */

		err = mlxsw_sp_adj_index_mass_update(mlxsw_sp, old_nh_grp,

						     old_nhgi->adj_index,

						     old_nhgi->ecmp_size);

		if (err) {

			NL_SET_ERR_MSG_MOD(extack, "Failed to replace old adjacency index with new one");

			goto err_out;

		}

	} else if (old_nhgi->adj_index_valid && !new_nhgi->adj_index_valid) {

		/* The old adjacency index is valid, while the new one is not.

		 * Iterate over all the routes using the group and change them

		 * to trap packets to the CPU.

		 */

		err = mlxsw_sp_nexthop_fib_entries_update(mlxsw_sp, old_nh_grp);

		if (err) {

			NL_SET_ERR_MSG_MOD(extack, "Failed to update routes to trap packets");

			goto err_out;

		}

	} else if (!old_nhgi->adj_index_valid && new_nhgi->adj_index_valid) {

		/* The old adjacency index is invalid, while the new one is.

		 * Iterate over all the routes using the group and change them

		 * to forward packets using the new valid index.

		 */

		err = mlxsw_sp_nexthop_fib_entries_update(mlxsw_sp, old_nh_grp);

		if (err) {

			NL_SET_ERR_MSG_MOD(extack, "Failed to update routes to forward packets");

			goto err_out;

		}

	}



	/* Make sure the flags are set / cleared based on the new nexthop group

	 * information.

	 */

	mlxsw_sp_nexthop_obj_group_offload_refresh(mlxsw_sp, old_nh_grp);



	/* At this point 'nh_grp' is just a shell that is not used by anyone

	 * and its nexthop group info is the old info that was just replaced

	 * with the new one. Remove it.

	 */

	nh_grp->can_destroy = true;

	mlxsw_sp_nexthop_obj_group_destroy(mlxsw_sp, nh_grp);



	return 0;



err_out:

	old_nhgi->nh_grp = old_nh_grp;

	nh_grp->nhgi = new_nhgi;

	new_nhgi->nh_grp = nh_grp;

	old_nh_grp->nhgi = old_nhgi;

	return err;

}



static int mlxsw_sp_nexthop_obj_new(struct mlxsw_sp *mlxsw_sp,

				    struct nh_notifier_info *info)

{

	struct mlxsw_sp_nexthop_group *nh_grp, *old_nh_grp;

	struct netlink_ext_ack *extack = info->extack;

	int err;



	nh_grp = mlxsw_sp_nexthop_obj_group_create(mlxsw_sp, info);

	if (IS_ERR(nh_grp))

		return PTR_ERR(nh_grp);



	old_nh_grp = mlxsw_sp_nexthop_obj_group_lookup(mlxsw_sp, info->id);

	if (!old_nh_grp)

		err = mlxsw_sp_nexthop_obj_group_add(mlxsw_sp, nh_grp);

	else

		err = mlxsw_sp_nexthop_obj_group_replace(mlxsw_sp, nh_grp,

							 old_nh_grp, extack);



	if (err) {

		nh_grp->can_destroy = true;

		mlxsw_sp_nexthop_obj_group_destroy(mlxsw_sp, nh_grp);

	}



	return err;

}



static void mlxsw_sp_nexthop_obj_del(struct mlxsw_sp *mlxsw_sp,

				     struct nh_notifier_info *info)

{

	struct mlxsw_sp_nexthop_group *nh_grp;



	nh_grp = mlxsw_sp_nexthop_obj_group_lookup(mlxsw_sp, info->id);

	if (!nh_grp)

		return;



	nh_grp->can_destroy = true;

	mlxsw_sp_nexthop_group_remove(mlxsw_sp, nh_grp);



	/* If the group still has routes using it, then defer the delete

	 * operation until the last route using it is deleted.

	 */

	if (!list_empty(&nh_grp->fib_list))

		return;

	mlxsw_sp_nexthop_obj_group_destroy(mlxsw_sp, nh_grp);

}



static int mlxsw_sp_nexthop_obj_event(struct notifier_block *nb,

				      unsigned long event, void *ptr)

{

	struct nh_notifier_info *info = ptr;

	struct mlxsw_sp_router *router;

	int err = 0;



	router = container_of(nb, struct mlxsw_sp_router, nexthop_nb);

	err = mlxsw_sp_nexthop_obj_validate(router->mlxsw_sp, event, info);

	if (err)

		goto out;



	mutex_lock(&router->lock);



	ASSERT_RTNL();



	switch (event) {

	case NEXTHOP_EVENT_REPLACE:

		err = mlxsw_sp_nexthop_obj_new(router->mlxsw_sp, info);

		break;

	case NEXTHOP_EVENT_DEL:

		mlxsw_sp_nexthop_obj_del(router->mlxsw_sp, info);

		break;

	default:

		break;

	}



	mutex_unlock(&router->lock);



out:

	return notifier_from_errno(err);

}



static bool mlxsw_sp_fi_is_gateway(const struct mlxsw_sp *mlxsw_sp,

				   struct fib_info *fi)

{
@@ -4208,12 +4648,21 @@ static int mlxsw_sp_nexthop4_group_get(struct mlxsw_sp *mlxsw_sp, 
{

	struct mlxsw_sp_nexthop_group *nh_grp;



	if (fi->nh) {

		nh_grp = mlxsw_sp_nexthop_obj_group_lookup(mlxsw_sp,

							   fi->nh->id);

		if (WARN_ON_ONCE(!nh_grp))

			return -EINVAL;

		goto out;

	}



	nh_grp = mlxsw_sp_nexthop4_group_lookup(mlxsw_sp, fi);

	if (!nh_grp) {

		nh_grp = mlxsw_sp_nexthop4_group_create(mlxsw_sp, fi);

		if (IS_ERR(nh_grp))

			return PTR_ERR(nh_grp);

	}

out:

	list_add_tail(&fib_entry->nexthop_group_node, &nh_grp->fib_list);

	fib_entry->nh_group = nh_grp;

	return 0;
@@ -4227,6 +4676,12 @@ static void mlxsw_sp_nexthop4_group_put(struct mlxsw_sp *mlxsw_sp, 
	list_del(&fib_entry->nexthop_group_node);

	if (!list_empty(&nh_grp->fib_list))

		return;



	if (nh_grp->type == MLXSW_SP_NEXTHOP_GROUP_TYPE_OBJ) {

		mlxsw_sp_nexthop_obj_group_destroy(mlxsw_sp, nh_grp);

		return;

	}



	mlxsw_sp_nexthop4_group_destroy(mlxsw_sp, nh_grp);

}
@@ -5517,8 +5972,17 @@ mlxsw_sp_nexthop6_group_destroy(struct mlxsw_sp *mlxsw_sp, 
static int mlxsw_sp_nexthop6_group_get(struct mlxsw_sp *mlxsw_sp,

				       struct mlxsw_sp_fib6_entry *fib6_entry)

{

	struct fib6_info *rt = mlxsw_sp_fib6_entry_rt(fib6_entry);

	struct mlxsw_sp_nexthop_group *nh_grp;



	if (rt->nh) {

		nh_grp = mlxsw_sp_nexthop_obj_group_lookup(mlxsw_sp,

							   rt->nh->id);

		if (WARN_ON_ONCE(!nh_grp))

			return -EINVAL;

		goto out;

	}



	nh_grp = mlxsw_sp_nexthop6_group_lookup(mlxsw_sp, fib6_entry);

	if (!nh_grp) {

		nh_grp = mlxsw_sp_nexthop6_group_create(mlxsw_sp, fib6_entry);
@@ -5531,6 +5995,7 @@ static int mlxsw_sp_nexthop6_group_get(struct mlxsw_sp *mlxsw_sp, 
	 */

	__mlxsw_sp_nexthop6_group_offload_refresh(nh_grp, fib6_entry);



out:

	list_add_tail(&fib6_entry->common.nexthop_group_node,

		      &nh_grp->fib_list);

	fib6_entry->common.nh_group = nh_grp;
@@ -5546,6 +6011,12 @@ static void mlxsw_sp_nexthop6_group_put(struct mlxsw_sp *mlxsw_sp, 
	list_del(&fib_entry->nexthop_group_node);

	if (!list_empty(&nh_grp->fib_list))

		return;



	if (nh_grp->type == MLXSW_SP_NEXTHOP_GROUP_TYPE_OBJ) {

		mlxsw_sp_nexthop_obj_group_destroy(mlxsw_sp, nh_grp);

		return;

	}



	mlxsw_sp_nexthop6_group_destroy(mlxsw_sp, nh_grp);

}
@@ -6597,20 +7068,6 @@ static int mlxsw_sp_router_fib_event(struct notifier_block *nb, 
				NL_SET_ERR_MSG_MOD(info->extack, "IPv6 gateway with IPv4 route is not supported");

				return notifier_from_errno(-EINVAL);

			}

			if (fen_info->fi->nh) {

				NL_SET_ERR_MSG_MOD(info->extack, "IPv4 route with nexthop objects is not supported");

				return notifier_from_errno(-EINVAL);

			}

		} else if (info->family == AF_INET6) {

			struct fib6_entry_notifier_info *fen6_info;



			fen6_info = container_of(info,

						 struct fib6_entry_notifier_info,

						 info);

			if (fen6_info->rt->nh) {

				NL_SET_ERR_MSG_MOD(info->extack, "IPv6 route with nexthop objects is not supported");

				return notifier_from_errno(-EINVAL);

			}

		}

		break;

	}
@@ -8549,6 +9006,14 @@ int mlxsw_sp_router_init(struct mlxsw_sp *mlxsw_sp, 
	if (err)

		goto err_register_netevent_notifier;



	mlxsw_sp->router->nexthop_nb.notifier_call =

		mlxsw_sp_nexthop_obj_event;

	err = register_nexthop_notifier(mlxsw_sp_net(mlxsw_sp),

					&mlxsw_sp->router->nexthop_nb,

					extack);

	if (err)

		goto err_register_nexthop_notifier;



	mlxsw_sp->router->fib_nb.notifier_call = mlxsw_sp_router_fib_event;

	err = register_fib_notifier(mlxsw_sp_net(mlxsw_sp),

				    &mlxsw_sp->router->fib_nb,
@@ -8559,6 +9024,9 @@ int mlxsw_sp_router_init(struct mlxsw_sp *mlxsw_sp, 
	return 0;



err_register_fib_notifier:

	unregister_nexthop_notifier(mlxsw_sp_net(mlxsw_sp),

				    &mlxsw_sp->router->nexthop_nb);

err_register_nexthop_notifier:

	unregister_netevent_notifier(&mlxsw_sp->router->netevent_nb);

err_register_netevent_notifier:

	unregister_inet6addr_notifier(&router->inet6addr_nb);
@@ -8598,6 +9066,8 @@ void mlxsw_sp_router_fini(struct mlxsw_sp *mlxsw_sp) 
{

	unregister_fib_notifier(mlxsw_sp_net(mlxsw_sp),

				&mlxsw_sp->router->fib_nb);

	unregister_nexthop_notifier(mlxsw_sp_net(mlxsw_sp),

				    &mlxsw_sp->router->nexthop_nb);

	unregister_netevent_notifier(&mlxsw_sp->router->netevent_nb);

	unregister_inet6addr_notifier(&mlxsw_sp->router->inet6addr_nb);

	unregister_inetaddr_notifier(&mlxsw_sp->router->inetaddr_nb);

drivers/net/ethernet/mellanox/mlxsw/spectrum_router.h

+1 −0
Original line number Diff line number Diff line
@@ -58,6 +58,7 @@ struct mlxsw_sp_router { 
	struct list_head nexthop_neighs_list;

	struct list_head ipip_list;

	bool aborted;

	struct notifier_block nexthop_nb;

	struct notifier_block fib_nb;

	struct notifier_block netevent_nb;

	struct notifier_block inetaddr_nb;

tools/testing/selftests/drivers/net/mlxsw/rtnetlink.sh

+189 −0
Original line number Diff line number Diff line
@@ -29,6 +29,10 @@ ALL_TESTS=" 
	bridge_extern_learn_test

	neigh_offload_test

	nexthop_offload_test

	nexthop_obj_invalid_test

	nexthop_obj_offload_test

	nexthop_obj_group_offload_test

	nexthop_obj_route_offload_test

	devlink_reload_test

"

NUM_NETIFS=2
@@ -674,6 +678,191 @@ nexthop_offload_test() 
	sysctl_restore net.ipv6.conf.$swp2.keep_addr_on_down

}



nexthop_obj_invalid_test()

{

	# Test that invalid nexthop object configurations are rejected

	RET=0



	simple_if_init $swp1 192.0.2.1/24 2001:db8:1::1/64

	simple_if_init $swp2 192.0.2.2/24 2001:db8:1::2/64

	setup_wait



	ip nexthop add id 1 via 192.0.2.3 fdb

	check_fail $? "managed to configure an FDB nexthop when should not"



	ip nexthop add id 1 encap mpls 200/300 via 192.0.2.3 dev $swp1

	check_fail $? "managed to configure a nexthop with MPLS encap when should not"



	ip nexthop add id 1 blackhole

	check_fail $? "managed to configure a blackhole nexthop when should not"



	ip nexthop add id 1 dev $swp1

	ip nexthop add id 2 dev $swp1

	ip nexthop add id 10 group 1/2

	check_fail $? "managed to configure a nexthop group with device-only nexthops when should not"



	log_test "nexthop objects - invalid configurations"



	ip nexthop del id 2

	ip nexthop del id 1



	simple_if_fini $swp2 192.0.2.2/24 2001:db8:1::2/64

	simple_if_fini $swp1 192.0.2.1/24 2001:db8:1::1/64

}



nexthop_obj_offload_test()

{

	# Test offload indication of nexthop objects

	RET=0



	simple_if_init $swp1 192.0.2.1/24 2001:db8:1::1/64

	simple_if_init $swp2

	setup_wait



	ip nexthop add id 1 via 192.0.2.2 dev $swp1

	ip neigh replace 192.0.2.2 lladdr 00:11:22:33:44:55 nud reachable \

		dev $swp1



	busywait "$TIMEOUT" wait_for_offload \

		ip nexthop show id 1

	check_err $? "nexthop not marked as offloaded when should"



	ip neigh replace 192.0.2.2 nud failed dev $swp1

	busywait "$TIMEOUT" not wait_for_offload \

		ip nexthop show id 1

	check_err $? "nexthop marked as offloaded after setting neigh to failed state"



	ip neigh replace 192.0.2.2 lladdr 00:11:22:33:44:55 nud reachable \

		dev $swp1

	busywait "$TIMEOUT" wait_for_offload \

		ip nexthop show id 1

	check_err $? "nexthop not marked as offloaded after neigh replace"



	ip nexthop replace id 1 via 192.0.2.3 dev $swp1

	busywait "$TIMEOUT" not wait_for_offload \

		ip nexthop show id 1

	check_err $? "nexthop marked as offloaded after replacing to use an invalid address"



	ip nexthop replace id 1 via 192.0.2.2 dev $swp1

	busywait "$TIMEOUT" wait_for_offload \

		ip nexthop show id 1

	check_err $? "nexthop not marked as offloaded after replacing to use a valid address"



	log_test "nexthop objects offload indication"



	ip neigh del 192.0.2.2 dev $swp1

	ip nexthop del id 1



	simple_if_fini $swp2

	simple_if_fini $swp1 192.0.2.1/24 2001:db8:1::1/64

}



nexthop_obj_group_offload_test()

{

	# Test offload indication of nexthop group objects

	RET=0



	simple_if_init $swp1 192.0.2.1/24 2001:db8:1::1/64

	simple_if_init $swp2

	setup_wait



	ip nexthop add id 1 via 192.0.2.2 dev $swp1

	ip nexthop add id 2 via 2001:db8:1::2 dev $swp1

	ip nexthop add id 10 group 1/2

	ip neigh replace 192.0.2.2 lladdr 00:11:22:33:44:55 nud reachable \

		dev $swp1

	ip neigh replace 192.0.2.3 lladdr 00:11:22:33:44:55 nud reachable \

		dev $swp1

	ip neigh replace 2001:db8:1::2 lladdr 00:11:22:33:44:55 nud reachable \

		dev $swp1



	busywait "$TIMEOUT" wait_for_offload \

		ip nexthop show id 1

	check_err $? "IPv4 nexthop not marked as offloaded when should"

	busywait "$TIMEOUT" wait_for_offload \

		ip nexthop show id 2

	check_err $? "IPv6 nexthop not marked as offloaded when should"

	busywait "$TIMEOUT" wait_for_offload \

		ip nexthop show id 10

	check_err $? "nexthop group not marked as offloaded when should"



	# Invalidate nexthop id 1

	ip neigh replace 192.0.2.2 nud failed dev $swp1

	busywait "$TIMEOUT" not wait_for_offload \

		ip nexthop show id 10

	check_fail $? "nexthop group not marked as offloaded with one valid nexthop"



	# Invalidate nexthop id 2

	ip neigh replace 2001:db8:1::2 nud failed dev $swp1

	busywait "$TIMEOUT" not wait_for_offload \

		ip nexthop show id 10

	check_err $? "nexthop group marked as offloaded when should not"



	# Revalidate nexthop id 1

	ip nexthop replace id 1 via 192.0.2.3 dev $swp1

	busywait "$TIMEOUT" wait_for_offload \

		ip nexthop show id 10

	check_err $? "nexthop group not marked as offloaded after revalidating nexthop"



	log_test "nexthop group objects offload indication"



	ip neigh del 2001:db8:1::2 dev $swp1

	ip neigh del 192.0.2.3 dev $swp1

	ip neigh del 192.0.2.2 dev $swp1

	ip nexthop del id 10

	ip nexthop del id 2

	ip nexthop del id 1



	simple_if_fini $swp2

	simple_if_fini $swp1 192.0.2.1/24 2001:db8:1::1/64

}



nexthop_obj_route_offload_test()

{

	# Test offload indication of routes using nexthop objects

	RET=0



	simple_if_init $swp1 192.0.2.1/24 2001:db8:1::1/64

	simple_if_init $swp2

	setup_wait



	ip nexthop add id 1 via 192.0.2.2 dev $swp1

	ip neigh replace 192.0.2.2 lladdr 00:11:22:33:44:55 nud reachable \

		dev $swp1

	ip neigh replace 192.0.2.3 lladdr 00:11:22:33:44:55 nud reachable \

		dev $swp1



	ip route replace 198.51.100.0/24 nhid 1

	busywait "$TIMEOUT" wait_for_offload \

		ip route show 198.51.100.0/24

	check_err $? "route not marked as offloaded when using valid nexthop"



	ip nexthop replace id 1 via 192.0.2.3 dev $swp1

	busywait "$TIMEOUT" wait_for_offload \

		ip route show 198.51.100.0/24

	check_err $? "route not marked as offloaded after replacing valid nexthop with a valid one"



	ip nexthop replace id 1 via 192.0.2.4 dev $swp1

	busywait "$TIMEOUT" not wait_for_offload \

		ip route show 198.51.100.0/24

	check_err $? "route marked as offloaded after replacing valid nexthop with an invalid one"



	ip nexthop replace id 1 via 192.0.2.2 dev $swp1

	busywait "$TIMEOUT" wait_for_offload \

		ip route show 198.51.100.0/24

	check_err $? "route not marked as offloaded after replacing invalid nexthop with a valid one"



	log_test "routes using nexthop objects offload indication"



	ip route del 198.51.100.0/24

	ip neigh del 192.0.2.3 dev $swp1

	ip neigh del 192.0.2.2 dev $swp1

	ip nexthop del id 1



	simple_if_fini $swp2

	simple_if_fini $swp1 192.0.2.1/24 2001:db8:1::1/64

}



devlink_reload_test()

{

	# Test that after executing all the above configuration tests, a

tools/testing/selftests/net/forwarding/gre_multipath_nh.sh

0 → 100755
+356 −0

File added.

Preview size limit exceeded, changes collapsed.

tools/testing/selftests/net/forwarding/router_mpath_nh.sh

+11 −1
Original line number Diff line number Diff line
@@ -280,6 +280,17 @@ multipath_test() 
	multipath4_test "Weighted MP 2:1" 2 1

	multipath4_test "Weighted MP 11:45" 11 45



	log_info "Running IPv4 multipath tests with IPv6 link-local nexthops"

	ip nexthop replace id 101 via fe80:2::22 dev $rp12

	ip nexthop replace id 102 via fe80:3::23 dev $rp13



	multipath4_test "ECMP" 1 1

	multipath4_test "Weighted MP 2:1" 2 1

	multipath4_test "Weighted MP 11:45" 11 45



	ip nexthop replace id 102 via 169.254.3.23 dev $rp13

	ip nexthop replace id 101 via 169.254.2.22 dev $rp12



	log_info "Running IPv6 multipath tests"

	multipath6_test "ECMP" 1 1

	multipath6_test "Weighted MP 2:1" 2 1
@@ -312,7 +323,6 @@ setup_prepare() 


	router1_create

	router2_create

	routing_nh_obj



	forwarding_enable

}

CRA Git | Maintained and supported by SUSTech CRA and CCSE