Merge branch 'net-add-struct-nexthop-to-fib-info'

David Ahern says:

====================
net: add struct nexthop to fib{6}_info

Set 10 of 11 to improve route scalability via support for nexthops as
standalone objects for fib entries.
    https://lwn.net/Articles/763950/

This sets adds 'struct nexthop' to fib_info and fib6_info. IPv4
already handles multiple fib_nh entries in a single fib_info, so
the conversion to use a nexthop struct is fairly mechanical. IPv6
using a nexthop struct with a fib6_info impacts a lot of core logic
which is built around the assumption of a single, builtin fib6_nh
per fib6_info. To make this easier to review, this set adds
nexthop to fib6_info and adds checks in most places fib6_info is
used. The next set finishes the IPv6 conversion, walking through
the places that need to consider all fib6_nh within a nexthop struct.

Offload drivers - mlx5, mlxsw and rocker - are changed to fail FIB
entries using nexthop objects. That limitation can be removed once
the drivers are updated to properly support separate nexthops.

This set starts by adding accessors for fib_nh and fib_nhs in a
fib_info. This makes it easier to extract the number of nexthops
in the fib entry and a specific fib_nh once the entry references
a struct nexthop. Patch 2 converts more of IPv4 code to use
fib_nh_common allowing a struct nexthop to use a fib6_nh with an
IPv4 entry.

Patches 3 and 4 add 'struct nexthop' to fib{6}_info and update
references to both take a different path when it is set. New
exported functions are added to the nexthop code to validate a
nexthop struct when configured for use with a fib entry. IPv4
is allowed to use a nexthop with either v4 or v6 entries. IPv6
is limited to v6 entries only. In both cases list_heads track
the fib entries using a nexthop struct for fast correlation on
events (e.g., device events or nexthop events like delete or
replace).

The last 3 patches add hooks to drivers listening for FIB
notificationas. All 3 of them reject the routes as unsupported,
returning an error message to the user via extack. For mlxsw
at least this is a stop gap measure until the driver is updated for
proper support.

Functional tests for nexthops have already been committed. Those tests
will be active after the next patch set which makes the code paths
created by this set and the next one live.

Existing code paths moved to the else branch of 'if (f{6}i->nh)' checks
are covered by existing tests under selftests/net.

v3
- remove ip6_create_rt_rcu from ip6_pol_route in patch 4 and use pcpu
  routes for REJECT routes with the blackhole nexthop (request from Wei)

v2
- no code changes from v1
- commit messages for first 4 patches updated
====================

Signed-off-by: David S. Miller <davem@davemloft.net>

4 files changed, 68 insertions, 27 deletions

diff --git a/drivers/net/ethernet/mellanox/mlx5/core/lag_mp.c b/drivers/net/ethernet/mellanox/mlx5/core/lag_mp.c
index 8212bfd05733..e69766393990 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/lag_mp.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/lag_mp.c
@@ -2,6 +2,7 @@
 /* Copyright (c) 2019 Mellanox Technologies. */
 
 #include <linux/netdevice.h>
+#include <net/nexthop.h>
 #include "lag.h"
 #include "lag_mp.h"
 #include "mlx5_core.h"
@@ -110,6 +111,8 @@ static void mlx5_lag_fib_route_event(struct mlx5_lag *ldev,
 				     struct fib_info *fi)
 {
 	struct lag_mp *mp = &ldev->lag_mp;
+	struct fib_nh *fib_nh0, *fib_nh1;
+	unsigned int nhs;
 
 	/* Handle delete event */
 	if (event == FIB_EVENT_ENTRY_DEL) {
@@ -120,9 +123,11 @@ static void mlx5_lag_fib_route_event(struct mlx5_lag *ldev,
 	}
 
 	/* Handle add/replace event */
-	if (fi->fib_nhs == 1) {
+	nhs = fib_info_num_path(fi);
+	if (nhs == 1) {
 		if (__mlx5_lag_is_active(ldev)) {
-			struct net_device *nh_dev = fi->fib_nh[0].fib_nh_dev;
+			struct fib_nh *nh = fib_info_nh(fi, 0);
+			struct net_device *nh_dev = nh->fib_nh_dev;
 			int i = mlx5_lag_dev_get_netdev_idx(ldev, nh_dev);
 
 			mlx5_lag_set_port_affinity(ldev, ++i);
@@ -130,14 +135,16 @@ static void mlx5_lag_fib_route_event(struct mlx5_lag *ldev,
 		return;
 	}
 
-	if (fi->fib_nhs != 2)
+	if (nhs != 2)
 		return;
 
 	/* Verify next hops are ports of the same hca */
-	if (!(fi->fib_nh[0].fib_nh_dev == ldev->pf[0].netdev &&
-	      fi->fib_nh[1].fib_nh_dev == ldev->pf[1].netdev) &&
-	    !(fi->fib_nh[0].fib_nh_dev == ldev->pf[1].netdev &&
-	      fi->fib_nh[1].fib_nh_dev == ldev->pf[0].netdev)) {
+	fib_nh0 = fib_info_nh(fi, 0);
+	fib_nh1 = fib_info_nh(fi, 1);
+	if (!(fib_nh0->fib_nh_dev == ldev->pf[0].netdev &&
+	      fib_nh1->fib_nh_dev == ldev->pf[1].netdev) &&
+	    !(fib_nh0->fib_nh_dev == ldev->pf[1].netdev &&
+	      fib_nh1->fib_nh_dev == ldev->pf[0].netdev)) {
 		mlx5_core_warn(ldev->pf[0].dev, "Multipath offload require two ports of the same HCA\n");
 		return;
 	}
@@ -174,7 +181,7 @@ static void mlx5_lag_fib_nexthop_event(struct mlx5_lag *ldev,
 			mlx5_lag_set_port_affinity(ldev, i);
 		}
 	} else if (event == FIB_EVENT_NH_ADD &&
-		   fi->fib_nhs == 2) {
+		   fib_info_num_path(fi) == 2) {
 		mlx5_lag_set_port_affinity(ldev, 0);
 	}
 }
@@ -238,6 +245,7 @@ static int mlx5_lag_fib_event(struct notifier_block *nb,
 	struct mlx5_fib_event_work *fib_work;
 	struct fib_entry_notifier_info *fen_info;
 	struct fib_nh_notifier_info *fnh_info;
+	struct net_device *fib_dev;
 	struct fib_info *fi;
 
 	if (info->family != AF_INET)
@@ -254,8 +262,13 @@ static int mlx5_lag_fib_event(struct notifier_block *nb,
 		fen_info = container_of(info, struct fib_entry_notifier_info,
 					info);
 		fi = fen_info->fi;
-		if (fi->fib_dev != ldev->pf[0].netdev &&
-		    fi->fib_dev != ldev->pf[1].netdev) {
+		if (fi->nh) {
+			NL_SET_ERR_MSG_MOD(info->extack, "IPv4 route with nexthop objects is not supported");
+			return notifier_from_errno(-EINVAL);
+		}
+		fib_dev = fib_info_nh(fen_info->fi, 0)->fib_nh_dev;
+		if (fib_dev != ldev->pf[0].netdev &&
+		    fib_dev != ldev->pf[1].netdev) {
 			return NOTIFY_DONE;
 		}
 		fib_work = mlx5_lag_init_fib_work(ldev, event);
diff --git a/drivers/net/ethernet/mellanox/mlxsw/spectrum_router.c b/drivers/net/ethernet/mellanox/mlxsw/spectrum_router.c
index 0ec52be7cc33..23f17ea52061 100644
--- a/drivers/net/ethernet/mellanox/mlxsw/spectrum_router.c
+++ b/drivers/net/ethernet/mellanox/mlxsw/spectrum_router.c
@@ -21,6 +21,7 @@
 #include <net/arp.h>
 #include <net/ip_fib.h>
 #include <net/ip6_fib.h>
+#include <net/nexthop.h>
 #include <net/fib_rules.h>
 #include <net/ip_tunnels.h>
 #include <net/l3mdev.h>
@@ -3816,23 +3817,25 @@ static void mlxsw_sp_nexthop_rif_gone_sync(struct mlxsw_sp *mlxsw_sp,
 }
 
 static bool mlxsw_sp_fi_is_gateway(const struct mlxsw_sp *mlxsw_sp,
-				   const struct fib_info *fi)
+				   struct fib_info *fi)
 {
-	return fi->fib_nh->fib_nh_scope == RT_SCOPE_LINK ||
-	       mlxsw_sp_nexthop4_ipip_type(mlxsw_sp, fi->fib_nh, NULL);
+	const struct fib_nh *nh = fib_info_nh(fi, 0);
+
+	return nh->fib_nh_scope == RT_SCOPE_LINK ||
+	       mlxsw_sp_nexthop4_ipip_type(mlxsw_sp, nh, NULL);
 }
 
 static struct mlxsw_sp_nexthop_group *
 mlxsw_sp_nexthop4_group_create(struct mlxsw_sp *mlxsw_sp, struct fib_info *fi)
 {
+	unsigned int nhs = fib_info_num_path(fi);
 	struct mlxsw_sp_nexthop_group *nh_grp;
 	struct mlxsw_sp_nexthop *nh;
 	struct fib_nh *fib_nh;
 	int i;
 	int err;
 
-	nh_grp = kzalloc(struct_size(nh_grp, nexthops, fi->fib_nhs),
-			 GFP_KERNEL);
+	nh_grp = kzalloc(struct_size(nh_grp, nexthops, nhs), GFP_KERNEL);
 	if (!nh_grp)
 		return ERR_PTR(-ENOMEM);
 	nh_grp->priv = fi;
@@ -3840,11 +3843,11 @@ mlxsw_sp_nexthop4_group_create(struct mlxsw_sp *mlxsw_sp, struct fib_info *fi)
 	nh_grp->neigh_tbl = &arp_tbl;
 
 	nh_grp->gateway = mlxsw_sp_fi_is_gateway(mlxsw_sp, fi);
-	nh_grp->count = fi->fib_nhs;
+	nh_grp->count = nhs;
 	fib_info_hold(fi);
 	for (i = 0; i < nh_grp->count; i++) {
 		nh = &nh_grp->nexthops[i];
-		fib_nh = &fi->fib_nh[i];
+		fib_nh = fib_info_nh(fi, i);
 		err = mlxsw_sp_nexthop4_init(mlxsw_sp, nh_grp, nh, fib_nh);
 		if (err)
 			goto err_nexthop4_init;
@@ -4282,9 +4285,9 @@ mlxsw_sp_fib4_entry_type_set(struct mlxsw_sp *mlxsw_sp,
 			     const struct fib_entry_notifier_info *fen_info,
 			     struct mlxsw_sp_fib_entry *fib_entry)
 {
+	struct net_device *dev = fib_info_nh(fen_info->fi, 0)->fib_nh_dev;
 	union mlxsw_sp_l3addr dip = { .addr4 = htonl(fen_info->dst) };
 	u32 tb_id = mlxsw_sp_fix_tb_id(fen_info->tb_id);
-	struct net_device *dev = fen_info->fi->fib_dev;
 	struct mlxsw_sp_ipip_entry *ipip_entry;
 	struct fib_info *fi = fen_info->fi;
 
@@ -6119,6 +6122,20 @@ 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;
 	}
diff --git a/drivers/net/ethernet/rocker/rocker_main.c b/drivers/net/ethernet/rocker/rocker_main.c
index 7ae6c124bfe9..45b3325c3a38 100644
--- a/drivers/net/ethernet/rocker/rocker_main.c
+++ b/drivers/net/ethernet/rocker/rocker_main.c
@@ -2214,6 +2214,10 @@ static int rocker_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);
+			}
 		}
 
 		memcpy(&fib_work->fen_info, ptr, sizeof(fib_work->fen_info));
diff --git a/drivers/net/ethernet/rocker/rocker_ofdpa.c b/drivers/net/ethernet/rocker/rocker_ofdpa.c
index 30a49802fb51..47ed9d41047f 100644
--- a/drivers/net/ethernet/rocker/rocker_ofdpa.c
+++ b/drivers/net/ethernet/rocker/rocker_ofdpa.c
@@ -22,6 +22,7 @@
 #include <net/neighbour.h>
 #include <net/switchdev.h>
 #include <net/ip_fib.h>
+#include <net/nexthop.h>
 #include <net/arp.h>
 
 #include "rocker.h"
@@ -2286,8 +2287,8 @@ static int ofdpa_port_fib_ipv4(struct ofdpa_port *ofdpa_port,  __be32 dst,
 
 	/* XXX support ECMP */
 
-	nh = fi->fib_nh;
-	nh_on_port = (fi->fib_dev == ofdpa_port->dev);
+	nh = fib_info_nh(fi, 0);
+	nh_on_port = (nh->fib_nh_dev == ofdpa_port->dev);
 	has_gw = !!nh->fib_nh_gw4;
 
 	if (has_gw && nh_on_port) {
@@ -2737,11 +2738,13 @@ static int ofdpa_fib4_add(struct rocker *rocker,
 {
 	struct ofdpa *ofdpa = rocker->wpriv;
 	struct ofdpa_port *ofdpa_port;
+	struct fib_nh *nh;
 	int err;
 
 	if (ofdpa->fib_aborted)
 		return 0;
-	ofdpa_port = ofdpa_port_dev_lower_find(fen_info->fi->fib_dev, rocker);
+	nh = fib_info_nh(fen_info->fi, 0);
+	ofdpa_port = ofdpa_port_dev_lower_find(nh->fib_nh_dev, rocker);
 	if (!ofdpa_port)
 		return 0;
 	err = ofdpa_port_fib_ipv4(ofdpa_port, htonl(fen_info->dst),
@@ -2749,7 +2752,7 @@ static int ofdpa_fib4_add(struct rocker *rocker,
 				  fen_info->tb_id, 0);
 	if (err)
 		return err;
-	fen_info->fi->fib_nh->fib_nh_flags |= RTNH_F_OFFLOAD;
+	nh->fib_nh_flags |= RTNH_F_OFFLOAD;
 	return 0;
 }
 
@@ -2758,13 +2761,15 @@ static int ofdpa_fib4_del(struct rocker *rocker,
 {
 	struct ofdpa *ofdpa = rocker->wpriv;
 	struct ofdpa_port *ofdpa_port;
+	struct fib_nh *nh;
 
 	if (ofdpa->fib_aborted)
 		return 0;
-	ofdpa_port = ofdpa_port_dev_lower_find(fen_info->fi->fib_dev, rocker);
+	nh = fib_info_nh(fen_info->fi, 0);
+	ofdpa_port = ofdpa_port_dev_lower_find(nh->fib_nh_dev, rocker);
 	if (!ofdpa_port)
 		return 0;
-	fen_info->fi->fib_nh->fib_nh_flags &= ~RTNH_F_OFFLOAD;
+	nh->fib_nh_flags &= ~RTNH_F_OFFLOAD;
 	return ofdpa_port_fib_ipv4(ofdpa_port, htonl(fen_info->dst),
 				   fen_info->dst_len, fen_info->fi,
 				   fen_info->tb_id, OFDPA_OP_FLAG_REMOVE);
@@ -2784,14 +2789,16 @@ static void ofdpa_fib4_abort(struct rocker *rocker)
 
 	spin_lock_irqsave(&ofdpa->flow_tbl_lock, flags);
 	hash_for_each_safe(ofdpa->flow_tbl, bkt, tmp, flow_entry, entry) {
+		struct fib_nh *nh;
+
 		if (flow_entry->key.tbl_id !=
 		    ROCKER_OF_DPA_TABLE_ID_UNICAST_ROUTING)
 			continue;
-		ofdpa_port = ofdpa_port_dev_lower_find(flow_entry->fi->fib_dev,
-						       rocker);
+		nh = fib_info_nh(flow_entry->fi, 0);
+		ofdpa_port = ofdpa_port_dev_lower_find(nh->fib_nh_dev, rocker);
 		if (!ofdpa_port)
 			continue;
-		flow_entry->fi->fib_nh->fib_nh_flags &= ~RTNH_F_OFFLOAD;
+		nh->fib_nh_flags &= ~RTNH_F_OFFLOAD;
 		ofdpa_flow_tbl_del(ofdpa_port, OFDPA_OP_FLAG_REMOVE,
 				   flow_entry);
 	}