[PATCH net-next 0/8] mlxsw: Add support for nexthop objects

[PATCH net-next 0/8] mlxsw: Add support for nexthop objects

[Ido Schimmel]

From: Ido Schimmel <idosch@nvidia.com>

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.

Ido Schimmel (8):
  mlxsw: spectrum_router: Add support for nexthop objects
  mlxsw: spectrum_router: Enable resolution of nexthop groups from
    nexthop objects
  mlxsw: spectrum_router: Allow programming routes with nexthop objects
  selftests: mlxsw: Add nexthop objects configuration tests
  selftests: forwarding: Do not configure nexthop objects twice
  selftests: forwarding: Test IPv4 routes with IPv6 link-local nexthops
  selftests: forwarding: Add device-only nexthop test
  selftests: forwarding: Add multipath tunneling nexthop test

 .../ethernet/mellanox/mlxsw/spectrum_router.c | 498 +++++++++++++++++-
 .../ethernet/mellanox/mlxsw/spectrum_router.h |   1 +
 .../selftests/drivers/net/mlxsw/rtnetlink.sh  | 189 +++++++
 .../net/forwarding/gre_multipath_nh.sh        | 356 +++++++++++++
 .../net/forwarding/router_mpath_nh.sh         |  12 +-
 .../selftests/net/forwarding/router_nh.sh     | 160 ++++++
 6 files changed, 1201 insertions(+), 15 deletions(-)
 create mode 100755 tools/testing/selftests/net/forwarding/gre_multipath_nh.sh
 create mode 100755 tools/testing/selftests/net/forwarding/router_nh.sh

-- 
2.28.0

[PATCH net-next 1/8] mlxsw: spectrum_router: Add support for nexthop objects

[Ido Schimmel]

From: Ido Schimmel <idosch@nvidia.com>

Register a listener to the nexthop notification chain and parse notified
nexthop objects into the existing mlxsw nexthop data structures.

Signed-off-by: Ido Schimmel <idosch@nvidia.com>
Reviewed-by: Jiri Pirko <jiri@nvidia.com>
---
 .../ethernet/mellanox/mlxsw/spectrum_router.c | 453 ++++++++++++++++++
 .../ethernet/mellanox/mlxsw/spectrum_router.h |   1 +
 2 files changed, 454 insertions(+)

diff --git a/drivers/net/ethernet/mellanox/mlxsw/spectrum_router.c b/drivers/net/ethernet/mellanox/mlxsw/spectrum_router.c
index 147dd8fab2af..480d47ef9362 100644
--- a/drivers/net/ethernet/mellanox/mlxsw/spectrum_router.c
+++ b/drivers/net/ethernet/mellanox/mlxsw/spectrum_router.c
@@ -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)
 {
@@ -8549,6 +8989,14 @@ 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 +9007,9 @@ 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 +9049,8 @@ 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);
diff --git a/drivers/net/ethernet/mellanox/mlxsw/spectrum_router.h b/drivers/net/ethernet/mellanox/mlxsw/spectrum_router.h
index 8230f6ff02ed..023f70827db0 100644
--- a/drivers/net/ethernet/mellanox/mlxsw/spectrum_router.h
+++ b/drivers/net/ethernet/mellanox/mlxsw/spectrum_router.h
@@ -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;
-- 
2.28.0

[PATCH net-next 2/8] mlxsw: spectrum_router: Enable resolution of nexthop groups from nexthop objects

[Ido Schimmel]

From: Ido Schimmel <idosch@nvidia.com>

If the FIB info (i.e, 'struct fib_info', 'struct fib6_info') uses a
nexthop object, then use the object's identifier to resolve the nexthop
group.

Signed-off-by: Ido Schimmel <idosch@nvidia.com>
Reviewed-by: Jiri Pirko <jiri@nvidia.com>
---
 .../ethernet/mellanox/mlxsw/spectrum_router.c | 31 +++++++++++++++++++
 1 file changed, 31 insertions(+)

diff --git a/drivers/net/ethernet/mellanox/mlxsw/spectrum_router.c b/drivers/net/ethernet/mellanox/mlxsw/spectrum_router.c
index 480d47ef9362..ad335d5b8d66 100644
--- a/drivers/net/ethernet/mellanox/mlxsw/spectrum_router.c
+++ b/drivers/net/ethernet/mellanox/mlxsw/spectrum_router.c
@@ -4648,12 +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;
@@ -4667,6 +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);
 }
 
@@ -5957,8 +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);
@@ -5971,6 +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;
@@ -5986,6 +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);
 }
 
-- 
2.28.0

[PATCH net-next 3/8] mlxsw: spectrum_router: Allow programming routes with nexthop objects

[Ido Schimmel]

From: Ido Schimmel <idosch@nvidia.com>

Now that the driver supports nexthop objects, the check is no longer
necessary. Remove it.

Signed-off-by: Ido Schimmel <idosch@nvidia.com>
Reviewed-by: Jiri Pirko <jiri@nvidia.com>
---
 .../net/ethernet/mellanox/mlxsw/spectrum_router.c  | 14 --------------
 1 file changed, 14 deletions(-)

diff --git a/drivers/net/ethernet/mellanox/mlxsw/spectrum_router.c b/drivers/net/ethernet/mellanox/mlxsw/spectrum_router.c
index ad335d5b8d66..42a7bec3fd88 100644
--- a/drivers/net/ethernet/mellanox/mlxsw/spectrum_router.c
+++ b/drivers/net/ethernet/mellanox/mlxsw/spectrum_router.c
@@ -7068,20 +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;
 	}
-- 
2.28.0

[PATCH net-next 4/8] selftests: mlxsw: Add nexthop objects configuration tests

[Ido Schimmel]

From: Ido Schimmel <idosch@nvidia.com>

Test that unsupported nexthop objects are rejected and that offload
indication is correctly set on: nexthop objects, nexthop group objects
and routes associated these objects.

Signed-off-by: Ido Schimmel <idosch@nvidia.com>
---
 .../selftests/drivers/net/mlxsw/rtnetlink.sh  | 189 ++++++++++++++++++
 1 file changed, 189 insertions(+)

diff --git a/tools/testing/selftests/drivers/net/mlxsw/rtnetlink.sh b/tools/testing/selftests/drivers/net/mlxsw/rtnetlink.sh
index f4031002d5e9..5de47d72f8c9 100755
--- a/tools/testing/selftests/drivers/net/mlxsw/rtnetlink.sh
+++ b/tools/testing/selftests/drivers/net/mlxsw/rtnetlink.sh
@@ -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
-- 
2.28.0

[PATCH net-next 5/8] selftests: forwarding: Do not configure nexthop objects twice

[Ido Schimmel]

From: Ido Schimmel <idosch@nvidia.com>

routing_nh_obj() is used to configure the nexthop objects employed by
the test, but it is called twice resulting in "RTNETLINK answers: File
exists" messages.

Remove the first call, so that the function is only called after
setup_wait(), when all the interfaces are up and ready.

Signed-off-by: Ido Schimmel <idosch@nvidia.com>
---
 tools/testing/selftests/net/forwarding/router_mpath_nh.sh | 1 -
 1 file changed, 1 deletion(-)

diff --git a/tools/testing/selftests/net/forwarding/router_mpath_nh.sh b/tools/testing/selftests/net/forwarding/router_mpath_nh.sh
index cf3d26c233e8..6067477ff326 100755
--- a/tools/testing/selftests/net/forwarding/router_mpath_nh.sh
+++ b/tools/testing/selftests/net/forwarding/router_mpath_nh.sh
@@ -312,7 +312,6 @@ setup_prepare()
 
 	router1_create
 	router2_create
-	routing_nh_obj
 
 	forwarding_enable
 }
-- 
2.28.0

[PATCH net-next 6/8] selftests: forwarding: Test IPv4 routes with IPv6 link-local nexthops

[Ido Schimmel]

From: Ido Schimmel <idosch@nvidia.com>

In addition to IPv4 multipath tests with IPv4 nexthops, also test IPv4
multipath with nexthops that use IPv6 link-local addresses.

Signed-off-by: Ido Schimmel <idosch@nvidia.com>
---
 .../selftests/net/forwarding/router_mpath_nh.sh       | 11 +++++++++++
 1 file changed, 11 insertions(+)

diff --git a/tools/testing/selftests/net/forwarding/router_mpath_nh.sh b/tools/testing/selftests/net/forwarding/router_mpath_nh.sh
index 6067477ff326..e8c2573d5232 100755
--- a/tools/testing/selftests/net/forwarding/router_mpath_nh.sh
+++ b/tools/testing/selftests/net/forwarding/router_mpath_nh.sh
@@ -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
-- 
2.28.0

[PATCH net-next 7/8] selftests: forwarding: Add device-only nexthop test

[Ido Schimmel]

From: Ido Schimmel <idosch@nvidia.com>

In a similar fashion to router_multipath.sh and its nexthop objects
version router_mpath_nh.sh, create a nexthop objects version of
router.sh.

It reuses the same topology, but uses device-only nexthop objects
instead of legacy ones.

Signed-off-by: Ido Schimmel <idosch@nvidia.com>
---
 .../selftests/net/forwarding/router_nh.sh     | 160 ++++++++++++++++++
 1 file changed, 160 insertions(+)
 create mode 100755 tools/testing/selftests/net/forwarding/router_nh.sh

diff --git a/tools/testing/selftests/net/forwarding/router_nh.sh b/tools/testing/selftests/net/forwarding/router_nh.sh
new file mode 100755
index 000000000000..f3a53738bdcc
--- /dev/null
+++ b/tools/testing/selftests/net/forwarding/router_nh.sh
@@ -0,0 +1,160 @@
+#!/bin/bash
+# SPDX-License-Identifier: GPL-2.0
+
+ALL_TESTS="
+	ping_ipv4
+	ping_ipv6
+"
+
+NUM_NETIFS=4
+source lib.sh
+source tc_common.sh
+
+h1_create()
+{
+	vrf_create "vrf-h1"
+	ip link set dev $h1 master vrf-h1
+
+	ip link set dev vrf-h1 up
+	ip link set dev $h1 up
+
+	ip address add 192.0.2.2/24 dev $h1
+	ip address add 2001:db8:1::2/64 dev $h1
+
+	ip route add 198.51.100.0/24 vrf vrf-h1 nexthop via 192.0.2.1
+	ip route add 2001:db8:2::/64 vrf vrf-h1 nexthop via 2001:db8:1::1
+}
+
+h1_destroy()
+{
+	ip route del 2001:db8:2::/64 vrf vrf-h1
+	ip route del 198.51.100.0/24 vrf vrf-h1
+
+	ip address del 2001:db8:1::2/64 dev $h1
+	ip address del 192.0.2.2/24 dev $h1
+
+	ip link set dev $h1 down
+	vrf_destroy "vrf-h1"
+}
+
+h2_create()
+{
+	vrf_create "vrf-h2"
+	ip link set dev $h2 master vrf-h2
+
+	ip link set dev vrf-h2 up
+	ip link set dev $h2 up
+
+	ip address add 198.51.100.2/24 dev $h2
+	ip address add 2001:db8:2::2/64 dev $h2
+
+	ip route add 192.0.2.0/24 vrf vrf-h2 nexthop via 198.51.100.1
+	ip route add 2001:db8:1::/64 vrf vrf-h2 nexthop via 2001:db8:2::1
+}
+
+h2_destroy()
+{
+	ip route del 2001:db8:1::/64 vrf vrf-h2
+	ip route del 192.0.2.0/24 vrf vrf-h2
+
+	ip address del 2001:db8:2::2/64 dev $h2
+	ip address del 198.51.100.2/24 dev $h2
+
+	ip link set dev $h2 down
+	vrf_destroy "vrf-h2"
+}
+
+router_create()
+{
+	ip link set dev $rp1 up
+	ip link set dev $rp2 up
+
+	tc qdisc add dev $rp2 clsact
+
+	ip address add 192.0.2.1/24 dev $rp1
+	ip address add 2001:db8:1::1/64 dev $rp1
+
+	ip address add 198.51.100.1/24 dev $rp2
+	ip address add 2001:db8:2::1/64 dev $rp2
+}
+
+router_destroy()
+{
+	ip address del 2001:db8:2::1/64 dev $rp2
+	ip address del 198.51.100.1/24 dev $rp2
+
+	ip address del 2001:db8:1::1/64 dev $rp1
+	ip address del 192.0.2.1/24 dev $rp1
+
+	tc qdisc del dev $rp2 clsact
+
+	ip link set dev $rp2 down
+	ip link set dev $rp1 down
+}
+
+routing_nh_obj()
+{
+	# Create the nexthops as AF_INET6, so that IPv4 and IPv6 routes could
+	# use them.
+	ip -6 nexthop add id 101 dev $rp1
+	ip -6 nexthop add id 102 dev $rp2
+
+	ip route replace 192.0.2.0/24 nhid 101
+	ip route replace 2001:db8:1::/64 nhid 101
+	ip route replace 198.51.100.0/24 nhid 102
+	ip route replace 2001:db8:2::/64 nhid 102
+}
+
+setup_prepare()
+{
+	h1=${NETIFS[p1]}
+	rp1=${NETIFS[p2]}
+
+	rp2=${NETIFS[p3]}
+	h2=${NETIFS[p4]}
+
+	rp1mac=$(mac_get $rp1)
+
+	vrf_prepare
+
+	h1_create
+	h2_create
+
+	router_create
+
+	forwarding_enable
+}
+
+cleanup()
+{
+	pre_cleanup
+
+	forwarding_restore
+
+	router_destroy
+
+	h2_destroy
+	h1_destroy
+
+	vrf_cleanup
+}
+
+ping_ipv4()
+{
+	ping_test $h1 198.51.100.2
+}
+
+ping_ipv6()
+{
+	ping6_test $h1 2001:db8:2::2
+}
+
+trap cleanup EXIT
+
+setup_prepare
+setup_wait
+routing_nh_obj
+
+tests_run
+
+exit $EXIT_STATUS
-- 
2.28.0

[PATCH net-next 8/8] selftests: forwarding: Add multipath tunneling nexthop test

[Ido Schimmel]

From: Ido Schimmel <idosch@nvidia.com>

Add a nexthop objects version of gre_multipath.sh. Unlike the original
test, it also tests IPv6 overlay which is not possible with the legacy
nexthop implementation. See commit 9a2ad3623868 ("selftests: forwarding:
gre_multipath: Drop IPv6 tests") for more info.

Signed-off-by: Ido Schimmel <idosch@nvidia.com>
---
 .../net/forwarding/gre_multipath_nh.sh        | 356 ++++++++++++++++++
 1 file changed, 356 insertions(+)
 create mode 100755 tools/testing/selftests/net/forwarding/gre_multipath_nh.sh

diff --git a/tools/testing/selftests/net/forwarding/gre_multipath_nh.sh b/tools/testing/selftests/net/forwarding/gre_multipath_nh.sh
new file mode 100755
index 000000000000..d03aa2cab9fd
--- /dev/null
+++ b/tools/testing/selftests/net/forwarding/gre_multipath_nh.sh
@@ -0,0 +1,356 @@
+#!/bin/bash
+# SPDX-License-Identifier: GPL-2.0
+
+# Test traffic distribution when a wECMP route forwards traffic to two GRE
+# tunnels.
+#
+# +-------------------------+
+# | H1                      |
+# |               $h1 +     |
+# |      192.0.2.1/28 |     |
+# |  2001:db8:1::1/64 |     |
+# +-------------------|-----+
+#                     |
+# +-------------------|------------------------+
+# | SW1               |                        |
+# |              $ol1 +                        |
+# |      192.0.2.2/28                          |
+# |  2001:db8:1::2/64                          |
+# |                                            |
+# |  + g1a (gre)          + g1b (gre)          |
+# |    loc=192.0.2.65       loc=192.0.2.81     |
+# |    rem=192.0.2.66 --.   rem=192.0.2.82 --. |
+# |    tos=inherit      |   tos=inherit      | |
+# |  .------------------'                    | |
+# |  |                    .------------------' |
+# |  v                    v                    |
+# |  + $ul1.111 (vlan)    + $ul1.222 (vlan)    |
+# |  | 192.0.2.129/28     | 192.0.2.145/28     |
+# |   \                  /                     |
+# |    \________________/                      |
+# |            |                               |
+# |            + $ul1                          |
+# +------------|-------------------------------+
+#              |
+# +------------|-------------------------------+
+# | SW2        + $ul2                          |
+# |     _______|________                       |
+# |    /                \                      |
+# |   /                  \                     |
+# |  + $ul2.111 (vlan)    + $ul2.222 (vlan)    |
+# |  ^ 192.0.2.130/28     ^ 192.0.2.146/28     |
+# |  |                    |                    |
+# |  |                    '------------------. |
+# |  '------------------.                    | |
+# |  + g2a (gre)        | + g2b (gre)        | |
+# |    loc=192.0.2.66   |   loc=192.0.2.82   | |
+# |    rem=192.0.2.65 --'   rem=192.0.2.81 --' |
+# |    tos=inherit          tos=inherit        |
+# |                                            |
+# |              $ol2 +                        |
+# |     192.0.2.17/28 |                        |
+# |  2001:db8:2::1/64 |                        |
+# +-------------------|------------------------+
+#                     |
+# +-------------------|-----+
+# | H2                |     |
+# |               $h2 +     |
+# |     192.0.2.18/28       |
+# |  2001:db8:2::2/64       |
+# +-------------------------+
+
+ALL_TESTS="
+	ping_ipv4
+	ping_ipv6
+	multipath_ipv4
+	multipath_ipv6
+	multipath_ipv6_l4
+"
+
+NUM_NETIFS=6
+source lib.sh
+
+h1_create()
+{
+	simple_if_init $h1 192.0.2.1/28 2001:db8:1::1/64
+	ip route add vrf v$h1 192.0.2.16/28 via 192.0.2.2
+	ip route add vrf v$h1 2001:db8:2::/64 via 2001:db8:1::2
+}
+
+h1_destroy()
+{
+	ip route del vrf v$h1 2001:db8:2::/64 via 2001:db8:1::2
+	ip route del vrf v$h1 192.0.2.16/28 via 192.0.2.2
+	simple_if_fini $h1 192.0.2.1/28
+}
+
+sw1_create()
+{
+	simple_if_init $ol1 192.0.2.2/28 2001:db8:1::2/64
+	__simple_if_init $ul1 v$ol1
+	vlan_create $ul1 111 v$ol1 192.0.2.129/28
+	vlan_create $ul1 222 v$ol1 192.0.2.145/28
+
+	tunnel_create g1a gre 192.0.2.65 192.0.2.66 tos inherit dev v$ol1
+	__simple_if_init g1a v$ol1 192.0.2.65/32
+	ip route add vrf v$ol1 192.0.2.66/32 via 192.0.2.130
+
+	tunnel_create g1b gre 192.0.2.81 192.0.2.82 tos inherit dev v$ol1
+	__simple_if_init g1b v$ol1 192.0.2.81/32
+	ip route add vrf v$ol1 192.0.2.82/32 via 192.0.2.146
+
+	ip -6 nexthop add id 101 dev g1a
+	ip -6 nexthop add id 102 dev g1b
+	ip nexthop add id 103 group 101/102
+
+	ip route add vrf v$ol1 192.0.2.16/28 nhid 103
+	ip route add vrf v$ol1 2001:db8:2::/64 nhid 103
+}
+
+sw1_destroy()
+{
+	ip route del vrf v$ol1 2001:db8:2::/64
+	ip route del vrf v$ol1 192.0.2.16/28
+
+	ip nexthop del id 103
+	ip -6 nexthop del id 102
+	ip -6 nexthop del id 101
+
+	ip route del vrf v$ol1 192.0.2.82/32 via 192.0.2.146
+	__simple_if_fini g1b 192.0.2.81/32
+	tunnel_destroy g1b
+
+	ip route del vrf v$ol1 192.0.2.66/32 via 192.0.2.130
+	__simple_if_fini g1a 192.0.2.65/32
+	tunnel_destroy g1a
+
+	vlan_destroy $ul1 222
+	vlan_destroy $ul1 111
+	__simple_if_fini $ul1
+	simple_if_fini $ol1 192.0.2.2/28 2001:db8:1::2/64
+}
+
+sw2_create()
+{
+	simple_if_init $ol2 192.0.2.17/28 2001:db8:2::1/64
+	__simple_if_init $ul2 v$ol2
+	vlan_create $ul2 111 v$ol2 192.0.2.130/28
+	vlan_create $ul2 222 v$ol2 192.0.2.146/28
+
+	tunnel_create g2a gre 192.0.2.66 192.0.2.65 tos inherit dev v$ol2
+	__simple_if_init g2a v$ol2 192.0.2.66/32
+	ip route add vrf v$ol2 192.0.2.65/32 via 192.0.2.129
+
+	tunnel_create g2b gre 192.0.2.82 192.0.2.81 tos inherit dev v$ol2
+	__simple_if_init g2b v$ol2 192.0.2.82/32
+	ip route add vrf v$ol2 192.0.2.81/32 via 192.0.2.145
+
+	ip -6 nexthop add id 201 dev g2a
+	ip -6 nexthop add id 202 dev g2b
+	ip nexthop add id 203 group 201/202
+
+	ip route add vrf v$ol2 192.0.2.0/28 nhid 203
+	ip route add vrf v$ol2 2001:db8:1::/64 nhid 203
+
+	tc qdisc add dev $ul2 clsact
+	tc filter add dev $ul2 ingress pref 111 prot 802.1Q \
+	   flower vlan_id 111 action pass
+	tc filter add dev $ul2 ingress pref 222 prot 802.1Q \
+	   flower vlan_id 222 action pass
+}
+
+sw2_destroy()
+{
+	tc qdisc del dev $ul2 clsact
+
+	ip route del vrf v$ol2 2001:db8:1::/64
+	ip route del vrf v$ol2 192.0.2.0/28
+
+	ip nexthop del id 203
+	ip -6 nexthop del id 202
+	ip -6 nexthop del id 201
+
+	ip route del vrf v$ol2 192.0.2.81/32 via 192.0.2.145
+	__simple_if_fini g2b 192.0.2.82/32
+	tunnel_destroy g2b
+
+	ip route del vrf v$ol2 192.0.2.65/32 via 192.0.2.129
+	__simple_if_fini g2a 192.0.2.66/32
+	tunnel_destroy g2a
+
+	vlan_destroy $ul2 222
+	vlan_destroy $ul2 111
+	__simple_if_fini $ul2
+	simple_if_fini $ol2 192.0.2.17/28 2001:db8:2::1/64
+}
+
+h2_create()
+{
+	simple_if_init $h2 192.0.2.18/28 2001:db8:2::2/64
+	ip route add vrf v$h2 192.0.2.0/28 via 192.0.2.17
+	ip route add vrf v$h2 2001:db8:1::/64 via 2001:db8:2::1
+}
+
+h2_destroy()
+{
+	ip route del vrf v$h2 2001:db8:1::/64 via 2001:db8:2::1
+	ip route del vrf v$h2 192.0.2.0/28 via 192.0.2.17
+	simple_if_fini $h2 192.0.2.18/28 2001:db8:2::2/64
+}
+
+setup_prepare()
+{
+	h1=${NETIFS[p1]}
+	ol1=${NETIFS[p2]}
+
+	ul1=${NETIFS[p3]}
+	ul2=${NETIFS[p4]}
+
+	ol2=${NETIFS[p5]}
+	h2=${NETIFS[p6]}
+
+	vrf_prepare
+	h1_create
+	sw1_create
+	sw2_create
+	h2_create
+
+	forwarding_enable
+}
+
+cleanup()
+{
+	pre_cleanup
+
+	forwarding_restore
+
+	h2_destroy
+	sw2_destroy
+	sw1_destroy
+	h1_destroy
+	vrf_cleanup
+}
+
+multipath4_test()
+{
+	local what=$1; shift
+	local weight1=$1; shift
+	local weight2=$1; shift
+
+	sysctl_set net.ipv4.fib_multipath_hash_policy 1
+	ip nexthop replace id 103 group 101,$weight1/102,$weight2
+
+	local t0_111=$(tc_rule_stats_get $ul2 111 ingress)
+	local t0_222=$(tc_rule_stats_get $ul2 222 ingress)
+
+	ip vrf exec v$h1 \
+	   $MZ $h1 -q -p 64 -A 192.0.2.1 -B 192.0.2.18 \
+	       -d 1msec -t udp "sp=1024,dp=0-32768"
+
+	local t1_111=$(tc_rule_stats_get $ul2 111 ingress)
+	local t1_222=$(tc_rule_stats_get $ul2 222 ingress)
+
+	local d111=$((t1_111 - t0_111))
+	local d222=$((t1_222 - t0_222))
+	multipath_eval "$what" $weight1 $weight2 $d111 $d222
+
+	ip nexthop replace id 103 group 101/102
+	sysctl_restore net.ipv4.fib_multipath_hash_policy
+}
+
+multipath6_test()
+{
+	local what=$1; shift
+	local weight1=$1; shift
+	local weight2=$1; shift
+
+	sysctl_set net.ipv6.fib_multipath_hash_policy 0
+	ip nexthop replace id 103 group 101,$weight1/102,$weight2
+
+	local t0_111=$(tc_rule_stats_get $ul2 111 ingress)
+	local t0_222=$(tc_rule_stats_get $ul2 222 ingress)
+
+	# Generate 16384 echo requests, each with a random flow label.
+	for ((i=0; i < 16384; ++i)); do
+		ip vrf exec v$h1 $PING6 2001:db8:2::2 -F 0 -c 1 -q &> /dev/null
+	done
+
+	local t1_111=$(tc_rule_stats_get $ul2 111 ingress)
+	local t1_222=$(tc_rule_stats_get $ul2 222 ingress)
+
+	local d111=$((t1_111 - t0_111))
+	local d222=$((t1_222 - t0_222))
+	multipath_eval "$what" $weight1 $weight2 $d111 $d222
+
+	ip nexthop replace id 103 group 101/102
+	sysctl_restore net.ipv6.fib_multipath_hash_policy
+}
+
+multipath6_l4_test()
+{
+	local what=$1; shift
+	local weight1=$1; shift
+	local weight2=$1; shift
+
+	sysctl_set net.ipv6.fib_multipath_hash_policy 1
+	ip nexthop replace id 103 group 101,$weight1/102,$weight2
+
+	local t0_111=$(tc_rule_stats_get $ul2 111 ingress)
+	local t0_222=$(tc_rule_stats_get $ul2 222 ingress)
+
+	ip vrf exec v$h1 \
+		$MZ $h1 -6 -q -p 64 -A 2001:db8:1::1 -B 2001:db8:2::2 \
+		-d 1msec -t udp "sp=1024,dp=0-32768"
+
+	local t1_111=$(tc_rule_stats_get $ul2 111 ingress)
+	local t1_222=$(tc_rule_stats_get $ul2 222 ingress)
+
+	local d111=$((t1_111 - t0_111))
+	local d222=$((t1_222 - t0_222))
+	multipath_eval "$what" $weight1 $weight2 $d111 $d222
+
+	ip nexthop replace id 103 group 101/102
+	sysctl_restore net.ipv6.fib_multipath_hash_policy
+}
+
+ping_ipv4()
+{
+	ping_test $h1 192.0.2.18
+}
+
+ping_ipv6()
+{
+	ping6_test $h1 2001:db8:2::2
+}
+
+multipath_ipv4()
+{
+	log_info "Running IPv4 multipath tests"
+	multipath4_test "ECMP" 1 1
+	multipath4_test "Weighted MP 2:1" 2 1
+	multipath4_test "Weighted MP 11:45" 11 45
+}
+
+multipath_ipv6()
+{
+	log_info "Running IPv6 multipath tests"
+	multipath6_test "ECMP" 1 1
+	multipath6_test "Weighted MP 2:1" 2 1
+	multipath6_test "Weighted MP 11:45" 11 45
+}
+
+multipath_ipv6_l4()
+{
+	log_info "Running IPv6 L4 hash multipath tests"
+	multipath6_l4_test "ECMP" 1 1
+	multipath6_l4_test "Weighted MP 2:1" 2 1
+	multipath6_l4_test "Weighted MP 11:45" 11 45
+}
+
+trap cleanup EXIT
+
+setup_prepare
+setup_wait
+tests_run
+
+exit $EXIT_STATUS
-- 
2.28.0

Re: [PATCH net-next 0/8] mlxsw: Add support for nexthop objects

[patchwork-bot+netdevbpf]

Hello:

This series was applied to netdev/net-next.git (refs/heads/master):

On Thu, 19 Nov 2020 15:08:40 +0200 you wrote:
> From: Ido Schimmel <idosch@nvidia.com>
> 
> 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.
> 
> [...]

Here is the summary with links:
  - [net-next,1/8] mlxsw: spectrum_router: Add support for nexthop objects
    https://git.kernel.org/netdev/net-next/c/2a014b200bbd
  - [net-next,2/8] mlxsw: spectrum_router: Enable resolution of nexthop groups from nexthop objects
    https://git.kernel.org/netdev/net-next/c/c25db3a77f61
  - [net-next,3/8] mlxsw: spectrum_router: Allow programming routes with nexthop objects
    https://git.kernel.org/netdev/net-next/c/cdd6cfc54c64
  - [net-next,4/8] selftests: mlxsw: Add nexthop objects configuration tests
    https://git.kernel.org/netdev/net-next/c/20ac8f869053
  - [net-next,5/8] selftests: forwarding: Do not configure nexthop objects twice
    https://git.kernel.org/netdev/net-next/c/ffb721515bf3
  - [net-next,6/8] selftests: forwarding: Test IPv4 routes with IPv6 link-local nexthops
    https://git.kernel.org/netdev/net-next/c/3600f29ad139
  - [net-next,7/8] selftests: forwarding: Add device-only nexthop test
    https://git.kernel.org/netdev/net-next/c/e96fa54bbd90
  - [net-next,8/8] selftests: forwarding: Add multipath tunneling nexthop test
    https://git.kernel.org/netdev/net-next/c/e035146d6560

You are awesome, thank you!
--
Deet-doot-dot, I am a bot.
https://korg.docs.kernel.org/patchwork/pwbot.html