mlxsw: spectrum_router: Do not destroy RIFs based on FID's reference count

Currently, when a RIF is constructed on top of a FID, the RIF increments
the FID's reference count and the RIF is destroyed when the FID's
reference count drops to 1. This effectively means that when no local
ports are member in the FID, the FID is destroyed regardless if the
router port is a member in the FID or not.

The above can lead to the unexpected behavior in which routes using a
VLAN interface as their nexthop device are no longer offloaded after the
last local port leaves the corresponding VLAN (FID).

Example:
# ip -4 route show dev br0.10
192.0.2.0/24 proto kernel scope link src 192.0.2.1 offload
# bridge vlan del vid 10 dev swp3
# ip -4 route show dev br0.10
192.0.2.0/24 proto kernel scope link src 192.0.2.1

After the patch, the route is offloaded before and after the VLAN is
removed from local port 'swp3', as the RIF corresponding to 'br0.10'
continues to exists.

In order to remove RIFs' reliance on the underlying FID's reference
count, we need to add a reference count to sub-port RIFs, which are RIFs
that correspond to physical ports and their uppers (e.g., LAG devices).

In this case, each {Port, VID} ('struct mlxsw_sp_port_vlan') needs to
hold a reference on the RIF. For example:

                       bond0.10
                          |
                        bond0
                          |
                      +-------+
                      |       |
                    swp1    swp2

Both {Port 1, VID 10} and {Port 2, VID 10} will hold a reference on the
RIF corresponding to 'bond0.10'. When the last reference is dropped, the
RIF will be destroyed.

Signed-off-by: Ido Schimmel <idosch@mellanox.com>
Reviewed-by: Petr Machata <petrm@mellanox.com>
Signed-off-by: David S. Miller <davem@davemloft.net>

1 files changed, 49 insertions, 21 deletions

diff --git a/drivers/net/ethernet/mellanox/mlxsw/spectrum_router.c b/drivers/net/ethernet/mellanox/mlxsw/spectrum_router.c
index b33ba8b66861..8a0011a610d6 100644
--- a/drivers/net/ethernet/mellanox/mlxsw/spectrum_router.c
+++ b/drivers/net/ethernet/mellanox/mlxsw/spectrum_router.c
@@ -15,6 +15,7 @@
 #include <linux/gcd.h>
 #include <linux/random.h>
 #include <linux/if_macvlan.h>
+#include <linux/refcount.h>
 #include <net/netevent.h>
 #include <net/neighbour.h>
 #include <net/arp.h>
@@ -104,6 +105,7 @@ struct mlxsw_sp_rif_params {
 
 struct mlxsw_sp_rif_subport {
 	struct mlxsw_sp_rif common;
+	refcount_t ref_count;
 	union {
 		u16 system_port;
 		u16 lag_id;
@@ -136,6 +138,7 @@ struct mlxsw_sp_rif_ops {
 	void (*fdb_del)(struct mlxsw_sp_rif *rif, const char *mac);
 };
 
+static void mlxsw_sp_rif_destroy(struct mlxsw_sp_rif *rif);
 static void mlxsw_sp_lpm_tree_hold(struct mlxsw_sp_lpm_tree *lpm_tree);
 static void mlxsw_sp_lpm_tree_put(struct mlxsw_sp *mlxsw_sp,
 				  struct mlxsw_sp_lpm_tree *lpm_tree);
@@ -6343,7 +6346,7 @@ err_rif_index_alloc:
 	return ERR_PTR(err);
 }
 
-void mlxsw_sp_rif_destroy(struct mlxsw_sp_rif *rif)
+static void mlxsw_sp_rif_destroy(struct mlxsw_sp_rif *rif)
 {
 	const struct mlxsw_sp_rif_ops *ops = rif->ops;
 	struct mlxsw_sp *mlxsw_sp = rif->mlxsw_sp;
@@ -6392,6 +6395,40 @@ mlxsw_sp_rif_subport_params_init(struct mlxsw_sp_rif_params *params,
 		params->system_port = mlxsw_sp_port->local_port;
 }
 
+static struct mlxsw_sp_rif_subport *
+mlxsw_sp_rif_subport_rif(const struct mlxsw_sp_rif *rif)
+{
+	return container_of(rif, struct mlxsw_sp_rif_subport, common);
+}
+
+static struct mlxsw_sp_rif *
+mlxsw_sp_rif_subport_get(struct mlxsw_sp *mlxsw_sp,
+			 const struct mlxsw_sp_rif_params *params,
+			 struct netlink_ext_ack *extack)
+{
+	struct mlxsw_sp_rif_subport *rif_subport;
+	struct mlxsw_sp_rif *rif;
+
+	rif = mlxsw_sp_rif_find_by_dev(mlxsw_sp, params->dev);
+	if (!rif)
+		return mlxsw_sp_rif_create(mlxsw_sp, params, extack);
+
+	rif_subport = mlxsw_sp_rif_subport_rif(rif);
+	refcount_inc(&rif_subport->ref_count);
+	return rif;
+}
+
+static void mlxsw_sp_rif_subport_put(struct mlxsw_sp_rif *rif)
+{
+	struct mlxsw_sp_rif_subport *rif_subport;
+
+	rif_subport = mlxsw_sp_rif_subport_rif(rif);
+	if (!refcount_dec_and_test(&rif_subport->ref_count))
+		return;
+
+	mlxsw_sp_rif_destroy(rif);
+}
+
 static int
 mlxsw_sp_port_vlan_router_join(struct mlxsw_sp_port_vlan *mlxsw_sp_port_vlan,
 			       struct net_device *l3_dev,
@@ -6399,22 +6436,18 @@ mlxsw_sp_port_vlan_router_join(struct mlxsw_sp_port_vlan *mlxsw_sp_port_vlan,
 {
 	struct mlxsw_sp_port *mlxsw_sp_port = mlxsw_sp_port_vlan->mlxsw_sp_port;
 	struct mlxsw_sp *mlxsw_sp = mlxsw_sp_port->mlxsw_sp;
+	struct mlxsw_sp_rif_params params = {
+		.dev = l3_dev,
+	};
 	u16 vid = mlxsw_sp_port_vlan->vid;
 	struct mlxsw_sp_rif *rif;
 	struct mlxsw_sp_fid *fid;
 	int err;
 
-	rif = mlxsw_sp_rif_find_by_dev(mlxsw_sp, l3_dev);
-	if (!rif) {
-		struct mlxsw_sp_rif_params params = {
-			.dev = l3_dev,
-		};
-
-		mlxsw_sp_rif_subport_params_init(&params, mlxsw_sp_port_vlan);
-		rif = mlxsw_sp_rif_create(mlxsw_sp, &params, extack);
-		if (IS_ERR(rif))
-			return PTR_ERR(rif);
-	}
+	mlxsw_sp_rif_subport_params_init(&params, mlxsw_sp_port_vlan);
+	rif = mlxsw_sp_rif_subport_get(mlxsw_sp, &params, extack);
+	if (IS_ERR(rif))
+		return PTR_ERR(rif);
 
 	/* FID was already created, just take a reference */
 	fid = rif->ops->fid_get(rif, extack);
@@ -6441,6 +6474,7 @@ err_port_vid_learning_set:
 	mlxsw_sp_fid_port_vid_unmap(fid, mlxsw_sp_port, vid);
 err_fid_port_vid_map:
 	mlxsw_sp_fid_put(fid);
+	mlxsw_sp_rif_subport_put(rif);
 	return err;
 }
 
@@ -6449,6 +6483,7 @@ mlxsw_sp_port_vlan_router_leave(struct mlxsw_sp_port_vlan *mlxsw_sp_port_vlan)
 {
 	struct mlxsw_sp_port *mlxsw_sp_port = mlxsw_sp_port_vlan->mlxsw_sp_port;
 	struct mlxsw_sp_fid *fid = mlxsw_sp_port_vlan->fid;
+	struct mlxsw_sp_rif *rif = mlxsw_sp_fid_rif(fid);
 	u16 vid = mlxsw_sp_port_vlan->vid;
 
 	if (WARN_ON(mlxsw_sp_fid_type(fid) != MLXSW_SP_FID_TYPE_RFID))
@@ -6458,10 +6493,8 @@ mlxsw_sp_port_vlan_router_leave(struct mlxsw_sp_port_vlan *mlxsw_sp_port_vlan)
 	mlxsw_sp_port_vid_stp_set(mlxsw_sp_port, vid, BR_STATE_BLOCKING);
 	mlxsw_sp_port_vid_learning_set(mlxsw_sp_port, vid, true);
 	mlxsw_sp_fid_port_vid_unmap(fid, mlxsw_sp_port, vid);
-	/* If router port holds the last reference on the rFID, then the
-	 * associated Sub-port RIF will be destroyed.
-	 */
 	mlxsw_sp_fid_put(fid);
+	mlxsw_sp_rif_subport_put(rif);
 }
 
 static int mlxsw_sp_inetaddr_port_vlan_event(struct net_device *l3_dev,
@@ -7064,18 +7097,13 @@ static int mlxsw_sp_rif_macvlan_flush(struct mlxsw_sp_rif *rif)
 					     __mlxsw_sp_rif_macvlan_flush, rif);
 }
 
-static struct mlxsw_sp_rif_subport *
-mlxsw_sp_rif_subport_rif(const struct mlxsw_sp_rif *rif)
-{
-	return container_of(rif, struct mlxsw_sp_rif_subport, common);
-}
-
 static void mlxsw_sp_rif_subport_setup(struct mlxsw_sp_rif *rif,
 				       const struct mlxsw_sp_rif_params *params)
 {
 	struct mlxsw_sp_rif_subport *rif_subport;
 
 	rif_subport = mlxsw_sp_rif_subport_rif(rif);
+	refcount_set(&rif_subport->ref_count, 1);
 	rif_subport->vid = params->vid;
 	rif_subport->lag = params->lag;
 	if (params->lag)