From: Ido Schimmel <idosch@mellanox.com>
Date: Tue, 11 Jun 2019 10:19:41 +0300
Subject: mlxsw: spectrum_router: Refresh nexthop neighbour when it becomes
 dead
Patch-mainline: v5.2-rc6
Git-commit: 83d5782681cc12b3d485a83cb34c46b2445f510c
References: git-fixes

The driver tries to periodically refresh neighbours that are used to
reach nexthops. This is done by periodically calling neigh_event_send().

However, if the neighbour becomes dead, there is nothing we can do to
return it to a connected state and the above function call is basically
a NOP.

This results in the nexthop never being written to the device's
adjacency table and therefore never used to forward packets.

Fix this by dropping our reference from the dead neighbour and
associating the nexthop with a new neigbhour which we will try to
refresh.

Fixes: a7ff87acd995 ("mlxsw: spectrum_router: Implement next-hop routing")
Signed-off-by: Ido Schimmel <idosch@mellanox.com>
Reported-by: Alex Veber <alexve@mellanox.com>
Tested-by: Alex Veber <alexve@mellanox.com>
Acked-by: Jiri Pirko <jiri@mellanox.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
Acked-by: Thomas Bogendoerfer <tbogendoerfer@suse.de>
---
 drivers/net/ethernet/mellanox/mlxsw/spectrum_router.c |   73 +++++++++++++++++-
 1 file changed, 70 insertions(+), 3 deletions(-)

--- a/drivers/net/ethernet/mellanox/mlxsw/spectrum_router.c
+++ b/drivers/net/ethernet/mellanox/mlxsw/spectrum_router.c
@@ -2355,7 +2355,7 @@ static void mlxsw_sp_router_probe_unreso
 static void
 mlxsw_sp_nexthop_neigh_update(struct mlxsw_sp *mlxsw_sp,
 			      struct mlxsw_sp_neigh_entry *neigh_entry,
-			      bool removing);
+			      bool removing, bool dead);
 
 static enum mlxsw_reg_rauht_op mlxsw_sp_rauht_op(bool adding)
 {
@@ -2486,7 +2486,8 @@ static void mlxsw_sp_router_neigh_event_
 
 	memcpy(neigh_entry->ha, ha, ETH_ALEN);
 	mlxsw_sp_neigh_entry_update(mlxsw_sp, neigh_entry, entry_connected);
-	mlxsw_sp_nexthop_neigh_update(mlxsw_sp, neigh_entry, !entry_connected);
+	mlxsw_sp_nexthop_neigh_update(mlxsw_sp, neigh_entry, !entry_connected,
+				      dead);
 
 	if (!neigh_entry->connected && list_empty(&neigh_entry->nexthop_list))
 		mlxsw_sp_neigh_entry_destroy(mlxsw_sp, neigh_entry);
@@ -3431,13 +3432,79 @@ static void __mlxsw_sp_nexthop_neigh_upd
 	nh->update = 1;
 }
 
+static int
+mlxsw_sp_nexthop_dead_neigh_replace(struct mlxsw_sp *mlxsw_sp,
+				    struct mlxsw_sp_neigh_entry *neigh_entry)
+{
+	struct neighbour *n, *old_n = neigh_entry->key.n;
+	struct mlxsw_sp_nexthop *nh;
+	bool entry_connected;
+	u8 nud_state, dead;
+	int err;
+
+	nh = list_first_entry(&neigh_entry->nexthop_list,
+			      struct mlxsw_sp_nexthop, neigh_list_node);
+
+	n = neigh_lookup(nh->nh_grp->neigh_tbl, &nh->gw_addr, nh->rif->dev);
+	if (!n) {
+		n = neigh_create(nh->nh_grp->neigh_tbl, &nh->gw_addr,
+				 nh->rif->dev);
+		if (IS_ERR(n))
+			return PTR_ERR(n);
+		neigh_event_send(n, NULL);
+	}
+
+	mlxsw_sp_neigh_entry_remove(mlxsw_sp, neigh_entry);
+	neigh_entry->key.n = n;
+	err = mlxsw_sp_neigh_entry_insert(mlxsw_sp, neigh_entry);
+	if (err)
+		goto err_neigh_entry_insert;
+
+	read_lock_bh(&n->lock);
+	nud_state = n->nud_state;
+	dead = n->dead;
+	read_unlock_bh(&n->lock);
+	entry_connected = nud_state & NUD_VALID && !dead;
+
+	list_for_each_entry(nh, &neigh_entry->nexthop_list,
+			    neigh_list_node) {
+		neigh_release(old_n);
+		neigh_clone(n);
+		__mlxsw_sp_nexthop_neigh_update(nh, !entry_connected);
+		mlxsw_sp_nexthop_group_refresh(mlxsw_sp, nh->nh_grp);
+	}
+
+	neigh_release(n);
+
+	return 0;
+
+err_neigh_entry_insert:
+	neigh_entry->key.n = old_n;
+	mlxsw_sp_neigh_entry_insert(mlxsw_sp, neigh_entry);
+	neigh_release(n);
+	return err;
+}
+
 static void
 mlxsw_sp_nexthop_neigh_update(struct mlxsw_sp *mlxsw_sp,
 			      struct mlxsw_sp_neigh_entry *neigh_entry,
-			      bool removing)
+			      bool removing, bool dead)
 {
 	struct mlxsw_sp_nexthop *nh;
 
+	if (list_empty(&neigh_entry->nexthop_list))
+		return;
+
+	if (dead) {
+		int err;
+
+		err = mlxsw_sp_nexthop_dead_neigh_replace(mlxsw_sp,
+							  neigh_entry);
+		if (err)
+			dev_err(mlxsw_sp->bus_info->dev, "Failed to replace dead neigh\n");
+		return;
+	}
+
 	list_for_each_entry(nh, &neigh_entry->nexthop_list,
 			    neigh_list_node) {
 		__mlxsw_sp_nexthop_neigh_update(nh, removing);