summaryrefslogtreecommitdiff
path: root/drivers/net/ethernet/mscc/ocelot_net.c
diff options
context:
space:
mode:
authorVladimir Oltean <vladimir.oltean@nxp.com>2021-07-21 19:24:03 +0300
committerDavid S. Miller <davem@davemloft.net>2021-07-22 00:26:23 -0700
commit4e51bf44a03af6fa19a39a36ea8fedfacb8ccadf (patch)
tree7b96ee8eb9215b1f74b0fa1befba2a2b54c78509 /drivers/net/ethernet/mscc/ocelot_net.c
parent7105b50b7eecae62cf6175507f9ea9ff60a55816 (diff)
net: bridge: move the switchdev object replay helpers to "push" mode
Starting with commit 4f2673b3a2b6 ("net: bridge: add helper to replay port and host-joined mdb entries"), DSA has introduced some bridge helpers that replay switchdev events (FDB/MDB/VLAN additions and deletions) that can be lost by the switchdev drivers in a variety of circumstances: - an IP multicast group was host-joined on the bridge itself before any switchdev port joined the bridge, leading to the host MDB entries missing in the hardware database. - during the bridge creation process, the MAC address of the bridge was added to the FDB as an entry pointing towards the bridge device itself, but with no switchdev ports being part of the bridge yet, this local FDB entry would remain unknown to the switchdev hardware database. - a VLAN/FDB/MDB was added to a bridge port that is a LAG interface, before any switchdev port joined that LAG, leading to the hardware database missing those entries. - a switchdev port left a LAG that is a bridge port, while the LAG remained part of the bridge, and all FDB/MDB/VLAN entries remained installed in the hardware database of the switchdev port. Also, since commit 0d2cfbd41c4a ("net: bridge: ignore switchdev events for LAG ports which didn't request replay"), DSA introduced a method, based on a const void *ctx, to ensure that two switchdev ports under the same LAG that is a bridge port do not see the same MDB/VLAN entry being replayed twice by the bridge, once for every bridge port that joins the LAG. With so many ordering corner cases being possible, it seems unreasonable to expect a switchdev driver writer to get it right from the first try. Therefore, now that DSA has experimented with the bridge replay helpers for a little bit, we can move the code to the bridge driver where it is more readily available to all switchdev drivers. To convert the switchdev object replay helpers from "pull mode" (where the driver asks for them) to a "push mode" (where the bridge offers them automatically), the biggest problem is that the bridge needs to be aware when a switchdev port joins and leaves, even when the switchdev is only indirectly a bridge port (for example when the bridge port is a LAG upper of the switchdev). Luckily, we already have a hook for that, in the form of the newly introduced switchdev_bridge_port_offload() and switchdev_bridge_port_unoffload() calls. These offer a natural place for hooking the object addition and deletion replays. Extend the above 2 functions with: - pointers to the switchdev atomic notifier (for FDB replays) and the blocking notifier (for MDB and VLAN replays). - the "const void *ctx" argument required for drivers to be able to disambiguate between which port is targeted, when multiple ports are lowers of the same LAG that is a bridge port. Most of the drivers pass NULL to this argument, except the ones that support LAG offload and have the proper context check already in place in the switchdev blocking notifier handler. Also unexport the replay helpers, since nobody except the bridge calls them directly now. Note that: (a) we abuse the terminology slightly, because FDB entries are not "switchdev objects", but we count them as objects nonetheless. With no direct way to prove it, I think they are not modeled as switchdev objects because those can only be installed by the bridge to the hardware (as opposed to FDB entries which can be propagated in the other direction too). This is merely an abuse of terms, FDB entries are replayed too, despite not being objects. (b) the bridge does not attempt to sync port attributes to newly joined ports, just the countable stuff (the objects). The reason for this is simple: no universal and symmetric way to sync and unsync them is known. For example, VLAN filtering: what to do on unsync, disable or leave it enabled? Similarly, STP state, ageing timer, etc etc. What a switchdev port does when it becomes standalone again is not really up to the bridge's competence, and the driver should deal with it. On the other hand, replaying deletions of switchdev objects can be seen a matter of cleanup and therefore be treated by the bridge, hence this patch. We make the replay helpers opt-in for drivers, because they might not bring immediate benefits for them: - nbp_vlan_init() is called _after_ netdev_master_upper_dev_link(), so br_vlan_replay() should not do anything for the new drivers on which we call it. The existing drivers where there was even a slight possibility for there to exist a VLAN on a bridge port before they join it are already guarded against this: mlxsw and prestera deny joining LAG interfaces that are members of a bridge. - br_fdb_replay() should now notify of local FDB entries, but I patched all drivers except DSA to ignore these new entries in commit 2c4eca3ef716 ("net: bridge: switchdev: include local flag in FDB notifications"). Driver authors can lift this restriction as they wish, and when they do, they can also opt into the FDB replay functionality. - br_mdb_replay() should fix a real issue which is described in commit 4f2673b3a2b6 ("net: bridge: add helper to replay port and host-joined mdb entries"). However most drivers do not offload the SWITCHDEV_OBJ_ID_HOST_MDB to see this issue: only cpsw and am65_cpsw offload this switchdev object, and I don't completely understand the way in which they offload this switchdev object anyway. So I'll leave it up to these drivers' respective maintainers to opt into br_mdb_replay(). So most of the drivers pass NULL notifier blocks for the replay helpers, except: - dpaa2-switch which was already acked/regression-tested with the helpers enabled (and there isn't much of a downside in having them) - ocelot which already had replay logic in "pull" mode - DSA which already had replay logic in "pull" mode An important observation is that the drivers which don't currently request bridge event replays don't even have the switchdev_bridge_port_{offload,unoffload} calls placed in proper places right now. This was done to avoid unnecessary rework for drivers which might never even add support for this. For driver writers who wish to add replay support, this can be used as a tentative placement guide: https://patchwork.kernel.org/project/netdevbpf/patch/20210720134655.892334-11-vladimir.oltean@nxp.com/ Cc: Vadym Kochan <vkochan@marvell.com> Cc: Taras Chornyi <tchornyi@marvell.com> Cc: Ioana Ciornei <ioana.ciornei@nxp.com> Cc: Lars Povlsen <lars.povlsen@microchip.com> Cc: Steen Hegelund <Steen.Hegelund@microchip.com> Cc: UNGLinuxDriver@microchip.com Cc: Claudiu Manoil <claudiu.manoil@nxp.com> Cc: Alexandre Belloni <alexandre.belloni@bootlin.com> Cc: Grygorii Strashko <grygorii.strashko@ti.com> Signed-off-by: Vladimir Oltean <vladimir.oltean@nxp.com> Acked-by: Ioana Ciornei <ioana.ciornei@nxp.com> # dpaa2-switch Signed-off-by: David S. Miller <davem@davemloft.net>
Diffstat (limited to 'drivers/net/ethernet/mscc/ocelot_net.c')
-rw-r--r--drivers/net/ethernet/mscc/ocelot_net.c45
1 files changed, 18 insertions, 27 deletions
diff --git a/drivers/net/ethernet/mscc/ocelot_net.c b/drivers/net/ethernet/mscc/ocelot_net.c
index 76b7b9536bf7..3558ee8d9212 100644
--- a/drivers/net/ethernet/mscc/ocelot_net.c
+++ b/drivers/net/ethernet/mscc/ocelot_net.c
@@ -1154,38 +1154,19 @@ static int ocelot_switchdev_sync(struct ocelot *ocelot, int port,
struct net_device *bridge_dev,
struct netlink_ext_ack *extack)
{
- struct ocelot_port *ocelot_port = ocelot->ports[port];
- struct ocelot_port_private *priv;
clock_t ageing_time;
u8 stp_state;
- int err;
-
- priv = container_of(ocelot_port, struct ocelot_port_private, port);
ocelot_inherit_brport_flags(ocelot, port, brport_dev);
stp_state = br_port_get_stp_state(brport_dev);
ocelot_bridge_stp_state_set(ocelot, port, stp_state);
- err = ocelot_port_vlan_filtering(ocelot, port,
- br_vlan_enabled(bridge_dev));
- if (err)
- return err;
-
ageing_time = br_get_ageing_time(bridge_dev);
ocelot_port_attr_ageing_set(ocelot, port, ageing_time);
- err = br_mdb_replay(bridge_dev, brport_dev, priv, true,
- &ocelot_switchdev_blocking_nb, extack);
- if (err && err != -EOPNOTSUPP)
- return err;
-
- err = br_vlan_replay(bridge_dev, brport_dev, priv, true,
- &ocelot_switchdev_blocking_nb, extack);
- if (err && err != -EOPNOTSUPP)
- return err;
-
- return 0;
+ return ocelot_port_vlan_filtering(ocelot, port,
+ br_vlan_enabled(bridge_dev));
}
static int ocelot_switchdev_unsync(struct ocelot *ocelot, int port)
@@ -1216,7 +1197,10 @@ static int ocelot_netdevice_bridge_join(struct net_device *dev,
ocelot_port_bridge_join(ocelot, port, bridge);
- err = switchdev_bridge_port_offload(brport_dev, dev, extack);
+ err = switchdev_bridge_port_offload(brport_dev, dev, priv,
+ &ocelot_netdevice_nb,
+ &ocelot_switchdev_blocking_nb,
+ extack);
if (err)
goto err_switchdev_offload;
@@ -1227,15 +1211,22 @@ static int ocelot_netdevice_bridge_join(struct net_device *dev,
return 0;
err_switchdev_sync:
- switchdev_bridge_port_unoffload(brport_dev);
+ switchdev_bridge_port_unoffload(brport_dev, priv,
+ &ocelot_netdevice_nb,
+ &ocelot_switchdev_blocking_nb);
err_switchdev_offload:
ocelot_port_bridge_leave(ocelot, port, bridge);
return err;
}
-static void ocelot_netdevice_pre_bridge_leave(struct net_device *brport_dev)
+static void ocelot_netdevice_pre_bridge_leave(struct net_device *dev,
+ struct net_device *brport_dev)
{
- switchdev_bridge_port_unoffload(brport_dev);
+ struct ocelot_port_private *priv = netdev_priv(dev);
+
+ switchdev_bridge_port_unoffload(brport_dev, priv,
+ &ocelot_netdevice_nb,
+ &ocelot_switchdev_blocking_nb);
}
static int ocelot_netdevice_bridge_leave(struct net_device *dev,
@@ -1299,7 +1290,7 @@ static void ocelot_netdevice_pre_lag_leave(struct net_device *dev,
if (!bridge_dev || !netif_is_bridge_master(bridge_dev))
return;
- ocelot_netdevice_pre_bridge_leave(bond);
+ ocelot_netdevice_pre_bridge_leave(dev, bond);
}
static int ocelot_netdevice_lag_leave(struct net_device *dev,
@@ -1384,7 +1375,7 @@ ocelot_netdevice_prechangeupper(struct net_device *dev,
struct netdev_notifier_changeupper_info *info)
{
if (netif_is_bridge_master(info->upper_dev) && !info->linking)
- ocelot_netdevice_pre_bridge_leave(brport_dev);
+ ocelot_netdevice_pre_bridge_leave(dev, brport_dev);
if (netif_is_lag_master(info->upper_dev) && !info->linking)
ocelot_netdevice_pre_lag_leave(dev, info->upper_dev);