diff mbox series

[v4,net-next,04/11] net: bridge: add helper to replay port and local fdb entries

Message ID 20210322235152.268695-5-olteanv@gmail.com (mailing list archive)
State New
Headers show
Series Better support for sandwiched LAGs with bridge and DSA | expand

Commit Message

Vladimir Oltean March 22, 2021, 11:51 p.m. UTC
From: Vladimir Oltean <vladimir.oltean@nxp.com>

When a switchdev port starts offloading a LAG that is already in a
bridge and has an FDB entry pointing to it:

ip link set bond0 master br0
bridge fdb add dev bond0 00:01:02:03:04:05 master static
ip link set swp0 master bond0

the switchdev driver will have no idea that this FDB entry is there,
because it missed the switchdev event emitted at its creation.

Ido Schimmel pointed this out during a discussion about challenges with
switchdev offloading of stacked interfaces between the physical port and
the bridge, and recommended to just catch that condition and deny the
CHANGEUPPER event:
https://lore.kernel.org/netdev/20210210105949.GB287766@shredder.lan/

But in fact, we might need to deal with the hard thing anyway, which is
to replay all FDB addresses relevant to this port, because it isn't just
static FDB entries, but also local addresses (ones that are not
forwarded but terminated by the bridge). There, we can't just say 'oh
yeah, there was an upper already so I'm not joining that'.

So, similar to the logic for replaying MDB entries, add a function that
must be called by individual switchdev drivers and replays local FDB
entries as well as ones pointing towards a bridge port. This time, we
use the atomic switchdev notifier block, since that's what FDB entries
expect for some reason.

Reported-by: Ido Schimmel <idosch@idosch.org>
Signed-off-by: Vladimir Oltean <vladimir.oltean@nxp.com>
---
 include/linux/if_bridge.h |  9 +++++++
 net/bridge/br_fdb.c       | 50 +++++++++++++++++++++++++++++++++++++++
 2 files changed, 59 insertions(+)

Comments

Nikolay Aleksandrov March 23, 2021, 11:12 a.m. UTC | #1
On 23/03/2021 01:51, Vladimir Oltean wrote:
> From: Vladimir Oltean <vladimir.oltean@nxp.com>
> 
> When a switchdev port starts offloading a LAG that is already in a
> bridge and has an FDB entry pointing to it:
> 
> ip link set bond0 master br0
> bridge fdb add dev bond0 00:01:02:03:04:05 master static
> ip link set swp0 master bond0
> 
> the switchdev driver will have no idea that this FDB entry is there,
> because it missed the switchdev event emitted at its creation.
> 
> Ido Schimmel pointed this out during a discussion about challenges with
> switchdev offloading of stacked interfaces between the physical port and
> the bridge, and recommended to just catch that condition and deny the
> CHANGEUPPER event:
> https://lore.kernel.org/netdev/20210210105949.GB287766@shredder.lan/
> 
> But in fact, we might need to deal with the hard thing anyway, which is
> to replay all FDB addresses relevant to this port, because it isn't just
> static FDB entries, but also local addresses (ones that are not
> forwarded but terminated by the bridge). There, we can't just say 'oh
> yeah, there was an upper already so I'm not joining that'.
> 
> So, similar to the logic for replaying MDB entries, add a function that
> must be called by individual switchdev drivers and replays local FDB
> entries as well as ones pointing towards a bridge port. This time, we
> use the atomic switchdev notifier block, since that's what FDB entries
> expect for some reason.
> 

I get the reason to have both bridge and bridge port devices (although the bridge
is really unnecessary as it can be inferred from the port), but it looks kind of
weird at first glance, I mean we get all of the port's fdbs and all of the bridge
fdbs every time (dst == NULL). The code itself is correct and the alternative
to take only 1 net_device and act based on its type would add another
step to the process per-port which also doesn't sound good...
There are a few minor const nits below too, again if there is another version
please take care of them, for the patch:

Acked-by: Nikolay Aleksandrov <nikolay@nvidia.com>

> Reported-by: Ido Schimmel <idosch@idosch.org>
> Signed-off-by: Vladimir Oltean <vladimir.oltean@nxp.com>
> ---
>  include/linux/if_bridge.h |  9 +++++++
>  net/bridge/br_fdb.c       | 50 +++++++++++++++++++++++++++++++++++++++
>  2 files changed, 59 insertions(+)
> 
> diff --git a/include/linux/if_bridge.h b/include/linux/if_bridge.h
> index f6472969bb44..b564c4486a45 100644
> --- a/include/linux/if_bridge.h
> +++ b/include/linux/if_bridge.h
> @@ -147,6 +147,8 @@ void br_fdb_clear_offload(const struct net_device *dev, u16 vid);
>  bool br_port_flag_is_set(const struct net_device *dev, unsigned long flag);
>  u8 br_port_get_stp_state(const struct net_device *dev);
>  clock_t br_get_ageing_time(struct net_device *br_dev);
> +int br_fdb_replay(struct net_device *br_dev, struct net_device *dev,
> +		  struct notifier_block *nb);
>  #else
>  static inline struct net_device *
>  br_fdb_find_port(const struct net_device *br_dev,
> @@ -175,6 +177,13 @@ static inline clock_t br_get_ageing_time(struct net_device *br_dev)
>  {
>  	return 0;
>  }
> +
> +static inline int br_fdb_replay(struct net_device *br_dev,
> +				struct net_device *dev,
> +				struct notifier_block *nb)
> +{
> +	return -EOPNOTSUPP;
> +}
>  #endif
>  
>  #endif
> diff --git a/net/bridge/br_fdb.c b/net/bridge/br_fdb.c
> index b7490237f3fc..698b79747d32 100644
> --- a/net/bridge/br_fdb.c
> +++ b/net/bridge/br_fdb.c
> @@ -726,6 +726,56 @@ static inline size_t fdb_nlmsg_size(void)
>  		+ nla_total_size(sizeof(u8)); /* NFEA_ACTIVITY_NOTIFY */
>  }
>  
> +static int br_fdb_replay_one(struct notifier_block *nb,
> +			     struct net_bridge_fdb_entry *fdb,
> +			     struct net_device *dev)
> +{
> +	struct switchdev_notifier_fdb_info item;
> +	int err;
> +
> +	item.addr = fdb->key.addr.addr;
> +	item.vid = fdb->key.vlan_id;
> +	item.added_by_user = test_bit(BR_FDB_ADDED_BY_USER, &fdb->flags);
> +	item.offloaded = test_bit(BR_FDB_OFFLOADED, &fdb->flags);
> +	item.info.dev = dev;
> +
> +	err = nb->notifier_call(nb, SWITCHDEV_FDB_ADD_TO_DEVICE, &item);
> +	return notifier_to_errno(err);
> +}
> +
> +int br_fdb_replay(struct net_device *br_dev, struct net_device *dev,
> +		  struct notifier_block *nb)

The devices can be const

> +{
> +	struct net_bridge_fdb_entry *fdb;
> +	struct net_bridge *br;
> +	int err = 0;
> +
> +	if (!netif_is_bridge_master(br_dev) || !netif_is_bridge_port(dev))
> +		return -EINVAL;
> +
> +	br = netdev_priv(br_dev);
> +
> +	rcu_read_lock();
> +
> +	hlist_for_each_entry_rcu(fdb, &br->fdb_list, fdb_node) {
> +		struct net_bridge_port *dst = READ_ONCE(fdb->dst);

const

> +		struct net_device *dst_dev;
> +
> +		dst_dev = dst ? dst->dev : br->dev;
> +		if (dst_dev != br_dev && dst_dev != dev)
> +			continue;
> +
> +		err = br_fdb_replay_one(nb, fdb, dst_dev);
> +		if (err)
> +			break;
> +	}
> +
> +	rcu_read_unlock();
> +
> +	return err;
> +}
> +EXPORT_SYMBOL_GPL(br_fdb_replay);
> +
>  static void fdb_notify(struct net_bridge *br,
>  		       const struct net_bridge_fdb_entry *fdb, int type,
>  		       bool swdev_notify)
>
Vladimir Oltean March 23, 2021, 6:11 p.m. UTC | #2
On Tue, Mar 23, 2021 at 01:12:33PM +0200, Nikolay Aleksandrov wrote:
> On 23/03/2021 01:51, Vladimir Oltean wrote:
> > From: Vladimir Oltean <vladimir.oltean@nxp.com>
> > 
> > When a switchdev port starts offloading a LAG that is already in a
> > bridge and has an FDB entry pointing to it:
> > 
> > ip link set bond0 master br0
> > bridge fdb add dev bond0 00:01:02:03:04:05 master static
> > ip link set swp0 master bond0
> > 
> > the switchdev driver will have no idea that this FDB entry is there,
> > because it missed the switchdev event emitted at its creation.
> > 
> > Ido Schimmel pointed this out during a discussion about challenges with
> > switchdev offloading of stacked interfaces between the physical port and
> > the bridge, and recommended to just catch that condition and deny the
> > CHANGEUPPER event:
> > https://lore.kernel.org/netdev/20210210105949.GB287766@shredder.lan/
> > 
> > But in fact, we might need to deal with the hard thing anyway, which is
> > to replay all FDB addresses relevant to this port, because it isn't just
> > static FDB entries, but also local addresses (ones that are not
> > forwarded but terminated by the bridge). There, we can't just say 'oh
> > yeah, there was an upper already so I'm not joining that'.
> > 
> > So, similar to the logic for replaying MDB entries, add a function that
> > must be called by individual switchdev drivers and replays local FDB
> > entries as well as ones pointing towards a bridge port. This time, we
> > use the atomic switchdev notifier block, since that's what FDB entries
> > expect for some reason.
> > 
> 
> I get the reason to have both bridge and bridge port devices (although the bridge
> is really unnecessary as it can be inferred from the port), but it looks kind of
> weird at first glance, I mean we get all of the port's fdbs and all of the bridge
> fdbs every time (dst == NULL). The code itself is correct and the alternative
> to take only 1 net_device and act based on its type would add another
> step to the process per-port which also doesn't sound good...
> There are a few minor const nits below too, again if there is another version
> please take care of them, for the patch:
> 
> Acked-by: Nikolay Aleksandrov <nikolay@nvidia.com>

Thanks for the review. For host MDB entries, those are already offloaded
to every bridge port (which yes, is still giving me headaches), so
replaying them for every port that calls br_mdb_replay is at least
consistent with that. For br_fdb_replay, honestly I am not yet sure
because mainline DSA does not yet handle local FDBs, I might end up
touching things up a little when I come back to the "RX filtering in
DSA" series (I need to address Ido's feedback by then too).  I would
just like to get something started. It's even possible that by the end
of the kernel development cycle, the end result might not even look
anything remotely similar to what we have here - this is just what I
deemed as "good enough as a small first step".

If nobody has objections or sees problems with the current series, I
think I'd prefer to send a follow-up with the const conversions, so I
can spam less people with another 11 emails.
diff mbox series

Patch

diff --git a/include/linux/if_bridge.h b/include/linux/if_bridge.h
index f6472969bb44..b564c4486a45 100644
--- a/include/linux/if_bridge.h
+++ b/include/linux/if_bridge.h
@@ -147,6 +147,8 @@  void br_fdb_clear_offload(const struct net_device *dev, u16 vid);
 bool br_port_flag_is_set(const struct net_device *dev, unsigned long flag);
 u8 br_port_get_stp_state(const struct net_device *dev);
 clock_t br_get_ageing_time(struct net_device *br_dev);
+int br_fdb_replay(struct net_device *br_dev, struct net_device *dev,
+		  struct notifier_block *nb);
 #else
 static inline struct net_device *
 br_fdb_find_port(const struct net_device *br_dev,
@@ -175,6 +177,13 @@  static inline clock_t br_get_ageing_time(struct net_device *br_dev)
 {
 	return 0;
 }
+
+static inline int br_fdb_replay(struct net_device *br_dev,
+				struct net_device *dev,
+				struct notifier_block *nb)
+{
+	return -EOPNOTSUPP;
+}
 #endif
 
 #endif
diff --git a/net/bridge/br_fdb.c b/net/bridge/br_fdb.c
index b7490237f3fc..698b79747d32 100644
--- a/net/bridge/br_fdb.c
+++ b/net/bridge/br_fdb.c
@@ -726,6 +726,56 @@  static inline size_t fdb_nlmsg_size(void)
 		+ nla_total_size(sizeof(u8)); /* NFEA_ACTIVITY_NOTIFY */
 }
 
+static int br_fdb_replay_one(struct notifier_block *nb,
+			     struct net_bridge_fdb_entry *fdb,
+			     struct net_device *dev)
+{
+	struct switchdev_notifier_fdb_info item;
+	int err;
+
+	item.addr = fdb->key.addr.addr;
+	item.vid = fdb->key.vlan_id;
+	item.added_by_user = test_bit(BR_FDB_ADDED_BY_USER, &fdb->flags);
+	item.offloaded = test_bit(BR_FDB_OFFLOADED, &fdb->flags);
+	item.info.dev = dev;
+
+	err = nb->notifier_call(nb, SWITCHDEV_FDB_ADD_TO_DEVICE, &item);
+	return notifier_to_errno(err);
+}
+
+int br_fdb_replay(struct net_device *br_dev, struct net_device *dev,
+		  struct notifier_block *nb)
+{
+	struct net_bridge_fdb_entry *fdb;
+	struct net_bridge *br;
+	int err = 0;
+
+	if (!netif_is_bridge_master(br_dev) || !netif_is_bridge_port(dev))
+		return -EINVAL;
+
+	br = netdev_priv(br_dev);
+
+	rcu_read_lock();
+
+	hlist_for_each_entry_rcu(fdb, &br->fdb_list, fdb_node) {
+		struct net_bridge_port *dst = READ_ONCE(fdb->dst);
+		struct net_device *dst_dev;
+
+		dst_dev = dst ? dst->dev : br->dev;
+		if (dst_dev != br_dev && dst_dev != dev)
+			continue;
+
+		err = br_fdb_replay_one(nb, fdb, dst_dev);
+		if (err)
+			break;
+	}
+
+	rcu_read_unlock();
+
+	return err;
+}
+EXPORT_SYMBOL_GPL(br_fdb_replay);
+
 static void fdb_notify(struct net_bridge *br,
 		       const struct net_bridge_fdb_entry *fdb, int type,
 		       bool swdev_notify)