ipv4: fib: Replay events when registering FIB notifier

Commit b90eb7549499 ("fib: introduce FIB notification infrastructure")
introduced a new notification chain to notify listeners (f.e., switchdev
drivers) about addition and deletion of routes.

However, upon registration to the chain the FIB tables can already be
populated, which means potential listeners will have an incomplete view
of the tables.

Solve that by dumping the FIB tables and replaying the events to the
passed notification block. The dump itself is done using RCU in order
not to starve consumers that need RTNL to make progress.

The integrity of the dump is ensured by reading the FIB change sequence
counter before and after the dump under RTNL. This allows us to avoid
the problematic situation in which the dumping process sends a ENTRY_ADD
notification following ENTRY_DEL generated by another process holding
RTNL.

Callers of the registration function may pass a callback that is
executed in case the dump was inconsistent with current FIB tables.

The number of retries until a consistent dump is achieved is set to a
fixed number to prevent callers from looping for long periods of time.
In case current limit proves to be problematic in the future, it can be
easily converted to be configurable using a sysctl.

Signed-off-by: Ido Schimmel <idosch@mellanox.com>
Signed-off-by: Jiri Pirko <jiri@mellanox.com>
Signed-off-by: David S. Miller <davem@davemloft.net>

2 files changed, 26 insertions, 2 deletions

diff --git a/drivers/net/ethernet/mellanox/mlxsw/spectrum_router.c b/drivers/net/ethernet/mellanox/mlxsw/spectrum_router.c
index 14bed1d10b72..53126bf68ea9 100644
--- a/drivers/net/ethernet/mellanox/mlxsw/spectrum_router.c
+++ b/drivers/net/ethernet/mellanox/mlxsw/spectrum_router.c
@@ -2027,6 +2027,18 @@ static int mlxsw_sp_router_fib_event(struct notifier_block *nb,
 	return NOTIFY_DONE;
 }
 
+static void mlxsw_sp_router_fib_dump_flush(struct notifier_block *nb)
+{
+	struct mlxsw_sp *mlxsw_sp = container_of(nb, struct mlxsw_sp, fib_nb);
+
+	/* Flush pending FIB notifications and then flush the device's
+	 * table before requesting another dump. The FIB notification
+	 * block is unregistered, so no need to take RTNL.
+	 */
+	mlxsw_core_flush_owq();
+	mlxsw_sp_router_fib_flush(mlxsw_sp);
+}
+
 int mlxsw_sp_router_init(struct mlxsw_sp *mlxsw_sp)
 {
 	int err;
@@ -2047,9 +2059,15 @@ int mlxsw_sp_router_init(struct mlxsw_sp *mlxsw_sp)
 		goto err_neigh_init;
 
 	mlxsw_sp->fib_nb.notifier_call = mlxsw_sp_router_fib_event;
-	register_fib_notifier(&mlxsw_sp->fib_nb);
+	err = register_fib_notifier(&mlxsw_sp->fib_nb,
+				    mlxsw_sp_router_fib_dump_flush);
+	if (err)
+		goto err_register_fib_notifier;
+
 	return 0;
 
+err_register_fib_notifier:
+	mlxsw_sp_neigh_fini(mlxsw_sp);
 err_neigh_init:
 	mlxsw_sp_vrs_fini(mlxsw_sp);
 err_vrs_init:
diff --git a/drivers/net/ethernet/rocker/rocker_main.c b/drivers/net/ethernet/rocker/rocker_main.c
index 8c9c90ae8962..7c450b5a1138 100644
--- a/drivers/net/ethernet/rocker/rocker_main.c
+++ b/drivers/net/ethernet/rocker/rocker_main.c
@@ -2804,8 +2804,13 @@ static int rocker_probe(struct pci_dev *pdev, const struct pci_device_id *id)
 		goto err_alloc_ordered_workqueue;
 	}
 
+	/* Only FIBs pointing to our own netdevs are programmed into
+	 * the device, so no need to pass a callback.
+	 */
 	rocker->fib_nb.notifier_call = rocker_router_fib_event;
-	register_fib_notifier(&rocker->fib_nb);
+	err = register_fib_notifier(&rocker->fib_nb, NULL);
+	if (err)
+		goto err_register_fib_notifier;
 
 	rocker->hw.id = rocker_read64(rocker, SWITCH_ID);
 
@@ -2822,6 +2827,7 @@ static int rocker_probe(struct pci_dev *pdev, const struct pci_device_id *id)
 
 err_probe_ports:
 	unregister_fib_notifier(&rocker->fib_nb);
+err_register_fib_notifier:
 	destroy_workqueue(rocker->rocker_owq);
 err_alloc_ordered_workqueue:
 	free_irq(rocker_msix_vector(rocker, ROCKER_MSIX_VEC_EVENT), rocker);