From b2bc58d41fde91951334254c4231f75ea8a21a2b Mon Sep 17 00:00:00 2001
From: Vladimir Oltean <vladimir.oltean@nxp.com>
Date: Tue, 15 Feb 2022 19:02:08 +0200
Subject: net: bridge: vlan: check early for lack of BRENTRY flag in
 br_vlan_add_existing

When a VLAN is added to a bridge port, a master VLAN gets created on the
bridge for context, but it doesn't have the BRENTRY flag.

Then, when the same VLAN is added to the bridge itself, that enters
through the br_vlan_add_existing() code path and gains the BRENTRY flag,
thus it becomes "existing".

It seems natural to check for this condition early, because the current
code flow is to notify switchdev of the addition of a VLAN that isn't a
brentry, just to delete it immediately afterwards.

Signed-off-by: Vladimir Oltean <vladimir.oltean@nxp.com>
Acked-by: Nikolay Aleksandrov <nikolay@nvidia.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/bridge/br_vlan.c | 10 ++++------
 1 file changed, 4 insertions(+), 6 deletions(-)

diff --git a/net/bridge/br_vlan.c b/net/bridge/br_vlan.c
index 6315e43a7a3e..7e99f84afb87 100644
--- a/net/bridge/br_vlan.c
+++ b/net/bridge/br_vlan.c
@@ -679,16 +679,15 @@ static int br_vlan_add_existing(struct net_bridge *br,
 {
 	int err;
 
+	/* Trying to change flags of non-existent bridge vlan */
+	if (!br_vlan_is_brentry(vlan) && !(flags & BRIDGE_VLAN_INFO_BRENTRY))
+		return -EINVAL;
+
 	err = br_switchdev_port_vlan_add(br->dev, vlan->vid, flags, extack);
 	if (err && err != -EOPNOTSUPP)
 		return err;
 
 	if (!br_vlan_is_brentry(vlan)) {
-		/* Trying to change flags of non-existent bridge vlan */
-		if (!(flags & BRIDGE_VLAN_INFO_BRENTRY)) {
-			err = -EINVAL;
-			goto err_flags;
-		}
 		/* It was only kept for port vlans, now make it real */
 		err = br_fdb_add_local(br, NULL, br->dev->dev_addr, vlan->vid);
 		if (err) {
@@ -709,7 +708,6 @@ static int br_vlan_add_existing(struct net_bridge *br,
 	return 0;
 
 err_fdb_insert:
-err_flags:
 	br_switchdev_port_vlan_del(br->dev, vlan->vid);
 	return err;
 }
-- 
cgit v1.3-7-g2ca7


From 3116ad0696dd2bf3f53c672f44f77e0d1c2da8ca Mon Sep 17 00:00:00 2001
From: Vladimir Oltean <vladimir.oltean@nxp.com>
Date: Tue, 15 Feb 2022 19:02:09 +0200
Subject: net: bridge: vlan: don't notify to switchdev master VLANs without
 BRENTRY flag

When a VLAN is added to a bridge port and it doesn't exist on the bridge
device yet, it gets created for the multicast context, but it is
'hidden', since it doesn't have the BRENTRY flag yet:

ip link add br0 type bridge && ip link set swp0 master br0
bridge vlan add dev swp0 vid 100 # the master VLAN 100 gets created
bridge vlan add dev br0 vid 100 self # that VLAN becomes brentry just now

All switchdev drivers ignore switchdev notifiers for VLAN entries which
have the BRENTRY unset, and for good reason: these are merely private
data structures used by the bridge driver. So we might just as well not
notify those at all.

Cleanup in the switchdev drivers that check for the BRENTRY flag is now
possible, and will be handled separately, since those checks just became
dead code.

Signed-off-by: Vladimir Oltean <vladimir.oltean@nxp.com>
Acked-by: Nikolay Aleksandrov <nikolay@nvidia.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/bridge/br_vlan.c | 9 ++++++---
 1 file changed, 6 insertions(+), 3 deletions(-)

diff --git a/net/bridge/br_vlan.c b/net/bridge/br_vlan.c
index 7e99f84afb87..33c879c1ecf3 100644
--- a/net/bridge/br_vlan.c
+++ b/net/bridge/br_vlan.c
@@ -284,9 +284,12 @@ static int __vlan_add(struct net_bridge_vlan *v, u16 flags,
 		}
 		br_multicast_port_ctx_init(p, v, &v->port_mcast_ctx);
 	} else {
-		err = br_switchdev_port_vlan_add(dev, v->vid, flags, extack);
-		if (err && err != -EOPNOTSUPP)
-			goto out;
+		if (br_vlan_should_use(v)) {
+			err = br_switchdev_port_vlan_add(dev, v->vid, flags,
+							 extack);
+			if (err && err != -EOPNOTSUPP)
+				goto out;
+		}
 		br_multicast_ctx_init(br, v, &v->br_mcast_ctx);
 		v->priv_flags |= BR_VLFLAG_GLOBAL_MCAST_ENABLED;
 	}
-- 
cgit v1.3-7-g2ca7


From cab2cd77005187828273adfec04f3ad18a63cb3d Mon Sep 17 00:00:00 2001
From: Vladimir Oltean <vladimir.oltean@nxp.com>
Date: Tue, 15 Feb 2022 19:02:10 +0200
Subject: net: bridge: vlan: make __vlan_add_flags react only to PVID and
 UNTAGGED

Currently there is a very subtle aspect to the behavior of
__vlan_add_flags(): it changes the struct net_bridge_vlan flags and
pvid, yet it returns true ("changed") even if none of those changed,
just a transition of br_vlan_is_brentry(v) took place from false to
true.

This can be seen in br_vlan_add_existing(), however we do not actually
rely on this subtle behavior, since the "if" condition that checks that
the vlan wasn't a brentry before had a useless (until now) assignment:

	*changed = true;

Make things more obvious by actually making __vlan_add_flags() do what's
written on the box, and be more specific about what is actually written
on the box. This is needed because further transformations will be done
to __vlan_add_flags().

Signed-off-by: Vladimir Oltean <vladimir.oltean@nxp.com>
Acked-by: Nikolay Aleksandrov <nikolay@nvidia.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/bridge/br_vlan.c | 6 ++++--
 1 file changed, 4 insertions(+), 2 deletions(-)

diff --git a/net/bridge/br_vlan.c b/net/bridge/br_vlan.c
index 33c879c1ecf3..f9c0e034c5b4 100644
--- a/net/bridge/br_vlan.c
+++ b/net/bridge/br_vlan.c
@@ -58,7 +58,9 @@ static bool __vlan_delete_pvid(struct net_bridge_vlan_group *vg, u16 vid)
 	return true;
 }
 
-/* return true if anything changed, false otherwise */
+/* Returns true if the BRIDGE_VLAN_INFO_PVID and BRIDGE_VLAN_INFO_UNTAGGED bits
+ * of @flags produced any change onto @v, false otherwise
+ */
 static bool __vlan_add_flags(struct net_bridge_vlan *v, u16 flags)
 {
 	struct net_bridge_vlan_group *vg;
@@ -80,7 +82,7 @@ static bool __vlan_add_flags(struct net_bridge_vlan *v, u16 flags)
 	else
 		v->flags &= ~BRIDGE_VLAN_INFO_UNTAGGED;
 
-	return ret || !!(old_flags ^ v->flags);
+	return ret || !!((old_flags ^ v->flags) & BRIDGE_VLAN_INFO_UNTAGGED);
 }
 
 static int __vlan_vid_add(struct net_device *dev, struct net_bridge *br,
-- 
cgit v1.3-7-g2ca7


From 27c5f74c7ba7b782f9694589ae733ca2ca8f76cc Mon Sep 17 00:00:00 2001
From: Vladimir Oltean <vladimir.oltean@nxp.com>
Date: Tue, 15 Feb 2022 19:02:11 +0200
Subject: net: bridge: vlan: notify switchdev only when something changed

Currently, when a VLAN entry is added multiple times in a row to a
bridge port, nbp_vlan_add() calls br_switchdev_port_vlan_add() each
time, even if the VLAN already exists and nothing about it has changed:

bridge vlan add dev lan12 vid 100 master static

Similarly, when a VLAN is added multiple times in a row to a bridge,
br_vlan_add_existing() doesn't filter at all the calls to
br_switchdev_port_vlan_add():

bridge vlan add dev br0 vid 100 self

This behavior makes driver-level accounting of VLANs impossible, since
it is enough for a single deletion event to remove a VLAN, but the
addition event can be emitted an unlimited number of times.

The cause for this can be identified as follows: we rely on
__vlan_add_flags() to retroactively tell us whether it has changed
anything about the VLAN flags or VLAN group pvid. So we'd first have to
call __vlan_add_flags() before calling br_switchdev_port_vlan_add(), in
order to have access to the "bool *changed" information. But we don't
want to change the event ordering, because we'd have to revert the
struct net_bridge_vlan changes we've made if switchdev returns an error.

So to solve this, we need another function that tells us whether any
change is going to occur in the VLAN or VLAN group, _prior_ to calling
__vlan_add_flags().

Split __vlan_add_flags() into a precommit and a commit stage, and rename
it to __vlan_flags_update(). The precommit stage,
__vlan_flags_would_change(), will determine whether there is any reason
to notify switchdev due to a change of flags (note: the BRENTRY flag
transition from false to true is treated separately: as a new switchdev
entry, because we skipped notifying the master VLAN when it wasn't a
brentry yet, and therefore not as a change of flags).

With this lookahead/precommit function in place, we can avoid notifying
switchdev if nothing changed for the VLAN and VLAN group.

Signed-off-by: Vladimir Oltean <vladimir.oltean@nxp.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/bridge/br_vlan.c | 95 +++++++++++++++++++++++++++++++++++-----------------
 1 file changed, 65 insertions(+), 30 deletions(-)

diff --git a/net/bridge/br_vlan.c b/net/bridge/br_vlan.c
index f9c0e034c5b4..0ad55a1add0e 100644
--- a/net/bridge/br_vlan.c
+++ b/net/bridge/br_vlan.c
@@ -34,55 +34,70 @@ static struct net_bridge_vlan *br_vlan_lookup(struct rhashtable *tbl, u16 vid)
 	return rhashtable_lookup_fast(tbl, &vid, br_vlan_rht_params);
 }
 
-static bool __vlan_add_pvid(struct net_bridge_vlan_group *vg,
+static void __vlan_add_pvid(struct net_bridge_vlan_group *vg,
 			    const struct net_bridge_vlan *v)
 {
 	if (vg->pvid == v->vid)
-		return false;
+		return;
 
 	smp_wmb();
 	br_vlan_set_pvid_state(vg, v->state);
 	vg->pvid = v->vid;
-
-	return true;
 }
 
-static bool __vlan_delete_pvid(struct net_bridge_vlan_group *vg, u16 vid)
+static void __vlan_delete_pvid(struct net_bridge_vlan_group *vg, u16 vid)
 {
 	if (vg->pvid != vid)
-		return false;
+		return;
 
 	smp_wmb();
 	vg->pvid = 0;
-
-	return true;
 }
 
-/* Returns true if the BRIDGE_VLAN_INFO_PVID and BRIDGE_VLAN_INFO_UNTAGGED bits
- * of @flags produced any change onto @v, false otherwise
+/* Update the BRIDGE_VLAN_INFO_PVID and BRIDGE_VLAN_INFO_UNTAGGED flags of @v.
+ * If @commit is false, return just whether the BRIDGE_VLAN_INFO_PVID and
+ * BRIDGE_VLAN_INFO_UNTAGGED bits of @flags would produce any change onto @v.
  */
-static bool __vlan_add_flags(struct net_bridge_vlan *v, u16 flags)
+static bool __vlan_flags_update(struct net_bridge_vlan *v, u16 flags,
+				bool commit)
 {
 	struct net_bridge_vlan_group *vg;
-	u16 old_flags = v->flags;
-	bool ret;
+	bool change;
 
 	if (br_vlan_is_master(v))
 		vg = br_vlan_group(v->br);
 	else
 		vg = nbp_vlan_group(v->port);
 
+	/* check if anything would be changed on commit */
+	change = !!(flags & BRIDGE_VLAN_INFO_PVID) == !!(vg->pvid != v->vid) ||
+		 ((flags ^ v->flags) & BRIDGE_VLAN_INFO_UNTAGGED);
+
+	if (!commit)
+		goto out;
+
 	if (flags & BRIDGE_VLAN_INFO_PVID)
-		ret = __vlan_add_pvid(vg, v);
+		__vlan_add_pvid(vg, v);
 	else
-		ret = __vlan_delete_pvid(vg, v->vid);
+		__vlan_delete_pvid(vg, v->vid);
 
 	if (flags & BRIDGE_VLAN_INFO_UNTAGGED)
 		v->flags |= BRIDGE_VLAN_INFO_UNTAGGED;
 	else
 		v->flags &= ~BRIDGE_VLAN_INFO_UNTAGGED;
 
-	return ret || !!((old_flags ^ v->flags) & BRIDGE_VLAN_INFO_UNTAGGED);
+out:
+	return change;
+}
+
+static bool __vlan_flags_would_change(struct net_bridge_vlan *v, u16 flags)
+{
+	return __vlan_flags_update(v, flags, false);
+}
+
+static void __vlan_flags_commit(struct net_bridge_vlan *v, u16 flags)
+{
+	__vlan_flags_update(v, flags, true);
 }
 
 static int __vlan_vid_add(struct net_device *dev, struct net_bridge *br,
@@ -315,7 +330,7 @@ static int __vlan_add(struct net_bridge_vlan *v, u16 flags,
 		goto out_fdb_insert;
 
 	__vlan_add_list(v);
-	__vlan_add_flags(v, flags);
+	__vlan_flags_commit(v, flags);
 	br_multicast_toggle_one_vlan(v, true);
 
 	if (p)
@@ -682,17 +697,29 @@ static int br_vlan_add_existing(struct net_bridge *br,
 				u16 flags, bool *changed,
 				struct netlink_ext_ack *extack)
 {
+	bool would_change = __vlan_flags_would_change(vlan, flags);
+	bool becomes_brentry = false;
 	int err;
 
-	/* Trying to change flags of non-existent bridge vlan */
-	if (!br_vlan_is_brentry(vlan) && !(flags & BRIDGE_VLAN_INFO_BRENTRY))
-		return -EINVAL;
+	if (!br_vlan_is_brentry(vlan)) {
+		/* Trying to change flags of non-existent bridge vlan */
+		if (!(flags & BRIDGE_VLAN_INFO_BRENTRY))
+			return -EINVAL;
 
-	err = br_switchdev_port_vlan_add(br->dev, vlan->vid, flags, extack);
-	if (err && err != -EOPNOTSUPP)
-		return err;
+		becomes_brentry = true;
+	}
 
-	if (!br_vlan_is_brentry(vlan)) {
+	/* Master VLANs that aren't brentries weren't notified before,
+	 * time to notify them now.
+	 */
+	if (becomes_brentry || would_change) {
+		err = br_switchdev_port_vlan_add(br->dev, vlan->vid, flags,
+						 extack);
+		if (err && err != -EOPNOTSUPP)
+			return err;
+	}
+
+	if (becomes_brentry) {
 		/* It was only kept for port vlans, now make it real */
 		err = br_fdb_add_local(br, NULL, br->dev->dev_addr, vlan->vid);
 		if (err) {
@@ -707,7 +734,8 @@ static int br_vlan_add_existing(struct net_bridge *br,
 		br_multicast_toggle_one_vlan(vlan, true);
 	}
 
-	if (__vlan_add_flags(vlan, flags))
+	__vlan_flags_commit(vlan, flags);
+	if (would_change)
 		*changed = true;
 
 	return 0;
@@ -1257,11 +1285,18 @@ int nbp_vlan_add(struct net_bridge_port *port, u16 vid, u16 flags,
 	*changed = false;
 	vlan = br_vlan_find(nbp_vlan_group(port), vid);
 	if (vlan) {
-		/* Pass the flags to the hardware bridge */
-		ret = br_switchdev_port_vlan_add(port->dev, vid, flags, extack);
-		if (ret && ret != -EOPNOTSUPP)
-			return ret;
-		*changed = __vlan_add_flags(vlan, flags);
+		bool would_change = __vlan_flags_would_change(vlan, flags);
+
+		if (would_change) {
+			/* Pass the flags to the hardware bridge */
+			ret = br_switchdev_port_vlan_add(port->dev, vid,
+							 flags, extack);
+			if (ret && ret != -EOPNOTSUPP)
+				return ret;
+		}
+
+		__vlan_flags_commit(vlan, flags);
+		*changed = would_change;
 
 		return 0;
 	}
-- 
cgit v1.3-7-g2ca7


From 8d23a54f5beea59b560855fb571e5d73d783e0b4 Mon Sep 17 00:00:00 2001
From: Vladimir Oltean <vladimir.oltean@nxp.com>
Date: Tue, 15 Feb 2022 19:02:12 +0200
Subject: net: bridge: switchdev: differentiate new VLANs from changed ones

br_switchdev_port_vlan_add() currently emits a SWITCHDEV_PORT_OBJ_ADD
event with a SWITCHDEV_OBJ_ID_PORT_VLAN for 2 distinct cases:

- a struct net_bridge_vlan got created
- an existing struct net_bridge_vlan was modified

This makes it impossible for switchdev drivers to properly balance
PORT_OBJ_ADD with PORT_OBJ_DEL events, so if we want to allow that to
happen, we must provide a way for drivers to distinguish between a
VLAN with changed flags and a new one.

Annotate struct switchdev_obj_port_vlan with a "bool changed" that
distinguishes the 2 cases above.

Signed-off-by: Vladimir Oltean <vladimir.oltean@nxp.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 include/net/switchdev.h   |  7 +++++++
 net/bridge/br_private.h   |  6 +++---
 net/bridge/br_switchdev.c |  3 ++-
 net/bridge/br_vlan.c      | 10 +++++-----
 4 files changed, 17 insertions(+), 9 deletions(-)

diff --git a/include/net/switchdev.h b/include/net/switchdev.h
index d353793dfeb5..92cc763991e9 100644
--- a/include/net/switchdev.h
+++ b/include/net/switchdev.h
@@ -81,6 +81,13 @@ struct switchdev_obj_port_vlan {
 	struct switchdev_obj obj;
 	u16 flags;
 	u16 vid;
+	/* If set, the notifier signifies a change of one of the following
+	 * flags for a VLAN that already exists:
+	 * - BRIDGE_VLAN_INFO_PVID
+	 * - BRIDGE_VLAN_INFO_UNTAGGED
+	 * Entries with BRIDGE_VLAN_INFO_BRENTRY unset are not notified at all.
+	 */
+	bool changed;
 };
 
 #define SWITCHDEV_OBJ_PORT_VLAN(OBJ) \
diff --git a/net/bridge/br_private.h b/net/bridge/br_private.h
index 2661dda1a92b..48bc61ebc211 100644
--- a/net/bridge/br_private.h
+++ b/net/bridge/br_private.h
@@ -1985,7 +1985,7 @@ void br_switchdev_mdb_notify(struct net_device *dev,
 			     struct net_bridge_port_group *pg,
 			     int type);
 int br_switchdev_port_vlan_add(struct net_device *dev, u16 vid, u16 flags,
-			       struct netlink_ext_ack *extack);
+			       bool changed, struct netlink_ext_ack *extack);
 int br_switchdev_port_vlan_del(struct net_device *dev, u16 vid);
 void br_switchdev_init(struct net_bridge *br);
 
@@ -2052,8 +2052,8 @@ static inline int br_switchdev_set_port_flag(struct net_bridge_port *p,
 	return 0;
 }
 
-static inline int br_switchdev_port_vlan_add(struct net_device *dev,
-					     u16 vid, u16 flags,
+static inline int br_switchdev_port_vlan_add(struct net_device *dev, u16 vid,
+					     u16 flags, bool changed,
 					     struct netlink_ext_ack *extack)
 {
 	return -EOPNOTSUPP;
diff --git a/net/bridge/br_switchdev.c b/net/bridge/br_switchdev.c
index f8fbaaa7c501..fb5115387d82 100644
--- a/net/bridge/br_switchdev.c
+++ b/net/bridge/br_switchdev.c
@@ -160,13 +160,14 @@ br_switchdev_fdb_notify(struct net_bridge *br,
 }
 
 int br_switchdev_port_vlan_add(struct net_device *dev, u16 vid, u16 flags,
-			       struct netlink_ext_ack *extack)
+			       bool changed, struct netlink_ext_ack *extack)
 {
 	struct switchdev_obj_port_vlan v = {
 		.obj.orig_dev = dev,
 		.obj.id = SWITCHDEV_OBJ_ID_PORT_VLAN,
 		.flags = flags,
 		.vid = vid,
+		.changed = changed,
 	};
 
 	return switchdev_port_obj_add(dev, &v.obj, extack);
diff --git a/net/bridge/br_vlan.c b/net/bridge/br_vlan.c
index 0ad55a1add0e..7557e90b60e1 100644
--- a/net/bridge/br_vlan.c
+++ b/net/bridge/br_vlan.c
@@ -109,7 +109,7 @@ static int __vlan_vid_add(struct net_device *dev, struct net_bridge *br,
 	/* Try switchdev op first. In case it is not supported, fallback to
 	 * 8021q add.
 	 */
-	err = br_switchdev_port_vlan_add(dev, v->vid, flags, extack);
+	err = br_switchdev_port_vlan_add(dev, v->vid, flags, false, extack);
 	if (err == -EOPNOTSUPP)
 		return vlan_vid_add(dev, br->vlan_proto, v->vid);
 	v->priv_flags |= BR_VLFLAG_ADDED_BY_SWITCHDEV;
@@ -303,7 +303,7 @@ static int __vlan_add(struct net_bridge_vlan *v, u16 flags,
 	} else {
 		if (br_vlan_should_use(v)) {
 			err = br_switchdev_port_vlan_add(dev, v->vid, flags,
-							 extack);
+							 false, extack);
 			if (err && err != -EOPNOTSUPP)
 				goto out;
 		}
@@ -714,7 +714,7 @@ static int br_vlan_add_existing(struct net_bridge *br,
 	 */
 	if (becomes_brentry || would_change) {
 		err = br_switchdev_port_vlan_add(br->dev, vlan->vid, flags,
-						 extack);
+						 would_change, extack);
 		if (err && err != -EOPNOTSUPP)
 			return err;
 	}
@@ -1289,8 +1289,8 @@ int nbp_vlan_add(struct net_bridge_port *port, u16 vid, u16 flags,
 
 		if (would_change) {
 			/* Pass the flags to the hardware bridge */
-			ret = br_switchdev_port_vlan_add(port->dev, vid,
-							 flags, extack);
+			ret = br_switchdev_port_vlan_add(port->dev, vid, flags,
+							 true, extack);
 			if (ret && ret != -EOPNOTSUPP)
 				return ret;
 		}
-- 
cgit v1.3-7-g2ca7


From 263029ae317298a3719d2cd88a818c3a29a80e15 Mon Sep 17 00:00:00 2001
From: Vladimir Oltean <vladimir.oltean@nxp.com>
Date: Tue, 15 Feb 2022 19:02:13 +0200
Subject: net: bridge: make nbp_switchdev_unsync_objs() follow reverse order of
 sync()

There may be switchdev drivers that can add/remove a FDB or MDB entry
only as long as the VLAN it's in has been notified and offloaded first.
The nbp_switchdev_sync_objs() method satisfies this requirement on
addition, but nbp_switchdev_unsync_objs() first deletes VLANs, then
deletes MDBs and FDBs. Reverse the order of the function calls to cater
to this requirement.

Signed-off-by: Vladimir Oltean <vladimir.oltean@nxp.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/bridge/br_switchdev.c | 4 ++--
 1 file changed, 2 insertions(+), 2 deletions(-)

diff --git a/net/bridge/br_switchdev.c b/net/bridge/br_switchdev.c
index fb5115387d82..b7c13f8cfce5 100644
--- a/net/bridge/br_switchdev.c
+++ b/net/bridge/br_switchdev.c
@@ -707,11 +707,11 @@ static void nbp_switchdev_unsync_objs(struct net_bridge_port *p,
 	struct net_device *br_dev = p->br->dev;
 	struct net_device *dev = p->dev;
 
-	br_switchdev_vlan_replay(br_dev, dev, ctx, false, blocking_nb, NULL);
+	br_switchdev_fdb_replay(br_dev, ctx, false, atomic_nb);
 
 	br_switchdev_mdb_replay(br_dev, dev, ctx, false, blocking_nb, NULL);
 
-	br_switchdev_fdb_replay(br_dev, ctx, false, atomic_nb);
+	br_switchdev_vlan_replay(br_dev, dev, ctx, false, blocking_nb, NULL);
 }
 
 /* Let the bridge know that this port is offloaded, so that it can assign a
-- 
cgit v1.3-7-g2ca7


From b28d580e2939544ea0c56ca7aed7aacef1da466e Mon Sep 17 00:00:00 2001
From: Vladimir Oltean <vladimir.oltean@nxp.com>
Date: Tue, 15 Feb 2022 19:02:14 +0200
Subject: net: bridge: switchdev: replay all VLAN groups

The major user of replayed switchdev objects is DSA, and so far it
hasn't needed information about anything other than bridge port VLANs,
so this is all that br_switchdev_vlan_replay() knows to handle.

DSA has managed to get by through replicating every VLAN addition on a
user port such that the same VLAN is also added on all DSA and CPU
ports, but there is a corner case where this does not work.

The mv88e6xxx DSA driver currently prints this error message as soon as
the first port of a switch joins a bridge:

mv88e6085 0x0000000008b96000:00: port 0 failed to add a6:ef:77:c8:5f:3d vid 1 to fdb: -95

where a6:ef:77:c8:5f:3d vid 1 is a local FDB entry corresponding to the
bridge MAC address in the default_pvid.

The -EOPNOTSUPP is returned by mv88e6xxx_port_db_load_purge() because it
tries to map VID 1 to a FID (the ATU is indexed by FID not VID), but
fails to do so. This is because ->port_fdb_add() is called before
->port_vlan_add() for VID 1.

The abridged timeline of the calls is:

br_add_if
-> netdev_master_upper_dev_link
   -> dsa_port_bridge_join
      -> switchdev_bridge_port_offload
         -> br_switchdev_vlan_replay (*)
         -> br_switchdev_fdb_replay
            -> mv88e6xxx_port_fdb_add
-> nbp_vlan_init
   -> nbp_vlan_add
      -> mv88e6xxx_port_vlan_add

and the issue is that at the time of (*), the bridge port isn't in VID 1
(nbp_vlan_init hasn't been called), therefore br_switchdev_vlan_replay()
won't have anything to replay, therefore VID 1 won't be in the VTU by
the time mv88e6xxx_port_fdb_add() is called.

This happens only when the first port of a switch joins. For further
ports, the initial mv88e6xxx_port_vlan_add() is sufficient for VID 1 to
be loaded in the VTU (which is switch-wide, not per port).

The problem is somewhat unique to mv88e6xxx by chance, because most
other drivers offload an FDB entry by VID, so FDBs and VLANs can be
added asynchronously with respect to each other, but addressing the
issue at the bridge layer makes sense, since what mv88e6xxx requires
isn't absurd.

To fix this problem, we need to recognize that it isn't the VLAN group
of the port that we're interested in, but the VLAN group of the bridge
itself (so it isn't a timing issue, but rather insufficient information
being passed from switchdev to drivers).

As mentioned, currently nbp_switchdev_sync_objs() only calls
br_switchdev_vlan_replay() for VLANs corresponding to the port, but the
VLANs corresponding to the bridge itself, for local termination, also
need to be replayed. In this case, VID 1 is not (yet) present in the
port's VLAN group but is present in the bridge's VLAN group.

So to fix this bug, DSA is now obligated to explicitly handle VLANs
pointing towards the bridge in order to "close this race" (which isn't
really a race). As Tobias Waldekranz notices, this also implies that it
must explicitly handle port VLANs on foreign interfaces, something that
worked implicitly before:
https://patchwork.kernel.org/project/netdevbpf/patch/20220209213044.2353153-6-vladimir.oltean@nxp.com/#24735260

So in the end, br_switchdev_vlan_replay() must replay all VLANs from all
VLAN groups: all the ports, and the bridge itself.

Signed-off-by: Vladimir Oltean <vladimir.oltean@nxp.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/bridge/br_switchdev.c | 90 ++++++++++++++++++++++++++---------------------
 1 file changed, 49 insertions(+), 41 deletions(-)

diff --git a/net/bridge/br_switchdev.c b/net/bridge/br_switchdev.c
index b7c13f8cfce5..59fcabd08ef1 100644
--- a/net/bridge/br_switchdev.c
+++ b/net/bridge/br_switchdev.c
@@ -352,51 +352,19 @@ br_switchdev_vlan_replay_one(struct notifier_block *nb,
 	return notifier_to_errno(err);
 }
 
-static int br_switchdev_vlan_replay(struct net_device *br_dev,
-				    struct net_device *dev,
-				    const void *ctx, bool adding,
-				    struct notifier_block *nb,
-				    struct netlink_ext_ack *extack)
+static int br_switchdev_vlan_replay_group(struct notifier_block *nb,
+					  struct net_device *dev,
+					  struct net_bridge_vlan_group *vg,
+					  const void *ctx, unsigned long action,
+					  struct netlink_ext_ack *extack)
 {
-	struct net_bridge_vlan_group *vg;
 	struct net_bridge_vlan *v;
-	struct net_bridge_port *p;
-	struct net_bridge *br;
-	unsigned long action;
 	int err = 0;
 	u16 pvid;
 
-	ASSERT_RTNL();
-
-	if (!nb)
-		return 0;
-
-	if (!netif_is_bridge_master(br_dev))
-		return -EINVAL;
-
-	if (!netif_is_bridge_master(dev) && !netif_is_bridge_port(dev))
-		return -EINVAL;
-
-	if (netif_is_bridge_master(dev)) {
-		br = netdev_priv(dev);
-		vg = br_vlan_group(br);
-		p = NULL;
-	} else {
-		p = br_port_get_rtnl(dev);
-		if (WARN_ON(!p))
-			return -EINVAL;
-		vg = nbp_vlan_group(p);
-		br = p->br;
-	}
-
 	if (!vg)
 		return 0;
 
-	if (adding)
-		action = SWITCHDEV_PORT_OBJ_ADD;
-	else
-		action = SWITCHDEV_PORT_OBJ_DEL;
-
 	pvid = br_get_pvid(vg);
 
 	list_for_each_entry(v, &vg->vlan_list, vlist) {
@@ -416,7 +384,48 @@ static int br_switchdev_vlan_replay(struct net_device *br_dev,
 			return err;
 	}
 
-	return err;
+	return 0;
+}
+
+static int br_switchdev_vlan_replay(struct net_device *br_dev,
+				    const void *ctx, bool adding,
+				    struct notifier_block *nb,
+				    struct netlink_ext_ack *extack)
+{
+	struct net_bridge *br = netdev_priv(br_dev);
+	struct net_bridge_port *p;
+	unsigned long action;
+	int err;
+
+	ASSERT_RTNL();
+
+	if (!nb)
+		return 0;
+
+	if (!netif_is_bridge_master(br_dev))
+		return -EINVAL;
+
+	if (adding)
+		action = SWITCHDEV_PORT_OBJ_ADD;
+	else
+		action = SWITCHDEV_PORT_OBJ_DEL;
+
+	err = br_switchdev_vlan_replay_group(nb, br_dev, br_vlan_group(br),
+					     ctx, action, extack);
+	if (err)
+		return err;
+
+	list_for_each_entry(p, &br->port_list, list) {
+		struct net_device *dev = p->dev;
+
+		err = br_switchdev_vlan_replay_group(nb, dev,
+						     nbp_vlan_group(p),
+						     ctx, action, extack);
+		if (err)
+			return err;
+	}
+
+	return 0;
 }
 
 #ifdef CONFIG_BRIDGE_IGMP_SNOOPING
@@ -682,8 +691,7 @@ static int nbp_switchdev_sync_objs(struct net_bridge_port *p, const void *ctx,
 	struct net_device *dev = p->dev;
 	int err;
 
-	err = br_switchdev_vlan_replay(br_dev, dev, ctx, true, blocking_nb,
-				       extack);
+	err = br_switchdev_vlan_replay(br_dev, ctx, true, blocking_nb, extack);
 	if (err && err != -EOPNOTSUPP)
 		return err;
 
@@ -711,7 +719,7 @@ static void nbp_switchdev_unsync_objs(struct net_bridge_port *p,
 
 	br_switchdev_mdb_replay(br_dev, dev, ctx, false, blocking_nb, NULL);
 
-	br_switchdev_vlan_replay(br_dev, dev, ctx, false, blocking_nb, NULL);
+	br_switchdev_vlan_replay(br_dev, ctx, false, blocking_nb, NULL);
 }
 
 /* Let the bridge know that this port is offloaded, so that it can assign a
-- 
cgit v1.3-7-g2ca7


From 7b465f4cf39ea1f5df7f425b843578b60f673155 Mon Sep 17 00:00:00 2001
From: Vladimir Oltean <vladimir.oltean@nxp.com>
Date: Tue, 15 Feb 2022 19:02:15 +0200
Subject: net: switchdev: rename switchdev_lower_dev_find to
 switchdev_lower_dev_find_rcu

switchdev_lower_dev_find() assumes RCU read-side critical section
calling context, since it uses netdev_walk_all_lower_dev_rcu().

Rename it appropriately, in preparation of adding a similar iterator
that assumes writer-side rtnl_mutex protection.

Signed-off-by: Vladimir Oltean <vladimir.oltean@nxp.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/switchdev/switchdev.c | 18 +++++++++---------
 1 file changed, 9 insertions(+), 9 deletions(-)

diff --git a/net/switchdev/switchdev.c b/net/switchdev/switchdev.c
index 12e6b4146bfb..d53f364870a5 100644
--- a/net/switchdev/switchdev.c
+++ b/net/switchdev/switchdev.c
@@ -409,10 +409,10 @@ static int switchdev_lower_dev_walk(struct net_device *lower_dev,
 }
 
 static struct net_device *
-switchdev_lower_dev_find(struct net_device *dev,
-			 bool (*check_cb)(const struct net_device *dev),
-			 bool (*foreign_dev_check_cb)(const struct net_device *dev,
-						      const struct net_device *foreign_dev))
+switchdev_lower_dev_find_rcu(struct net_device *dev,
+			     bool (*check_cb)(const struct net_device *dev),
+			     bool (*foreign_dev_check_cb)(const struct net_device *dev,
+							  const struct net_device *foreign_dev))
 {
 	struct switchdev_nested_priv switchdev_priv = {
 		.check_cb = check_cb,
@@ -451,7 +451,7 @@ static int __switchdev_handle_fdb_event_to_device(struct net_device *dev,
 		return mod_cb(dev, orig_dev, event, info->ctx, fdb_info);
 
 	if (netif_is_lag_master(dev)) {
-		if (!switchdev_lower_dev_find(dev, check_cb, foreign_dev_check_cb))
+		if (!switchdev_lower_dev_find_rcu(dev, check_cb, foreign_dev_check_cb))
 			goto maybe_bridged_with_us;
 
 		/* This is a LAG interface that we offload */
@@ -465,7 +465,7 @@ static int __switchdev_handle_fdb_event_to_device(struct net_device *dev,
 	 * towards a bridge device.
 	 */
 	if (netif_is_bridge_master(dev)) {
-		if (!switchdev_lower_dev_find(dev, check_cb, foreign_dev_check_cb))
+		if (!switchdev_lower_dev_find_rcu(dev, check_cb, foreign_dev_check_cb))
 			return 0;
 
 		/* This is a bridge interface that we offload */
@@ -478,8 +478,8 @@ static int __switchdev_handle_fdb_event_to_device(struct net_device *dev,
 			 * that we offload.
 			 */
 			if (!check_cb(lower_dev) &&
-			    !switchdev_lower_dev_find(lower_dev, check_cb,
-						      foreign_dev_check_cb))
+			    !switchdev_lower_dev_find_rcu(lower_dev, check_cb,
+							  foreign_dev_check_cb))
 				continue;
 
 			err = __switchdev_handle_fdb_event_to_device(lower_dev, orig_dev,
@@ -501,7 +501,7 @@ maybe_bridged_with_us:
 	if (!br || !netif_is_bridge_master(br))
 		return 0;
 
-	if (!switchdev_lower_dev_find(br, check_cb, foreign_dev_check_cb))
+	if (!switchdev_lower_dev_find_rcu(br, check_cb, foreign_dev_check_cb))
 		return 0;
 
 	return __switchdev_handle_fdb_event_to_device(br, orig_dev, event, fdb_info,
-- 
cgit v1.3-7-g2ca7


From c4076cdd21f8d68a96f1e7124bd8915c7e31a474 Mon Sep 17 00:00:00 2001
From: Vladimir Oltean <vladimir.oltean@nxp.com>
Date: Tue, 15 Feb 2022 19:02:16 +0200
Subject: net: switchdev: introduce switchdev_handle_port_obj_{add,del} for
 foreign interfaces

The switchdev_handle_port_obj_add() helper is good for replicating a
port object on the lower interfaces of @dev, if that object was emitted
on a bridge, or on a bridge port that is a LAG.

However, drivers that use this helper limit themselves to a box from
which they can no longer intercept port objects notified on neighbor
ports ("foreign interfaces").

One such driver is DSA, where software bridging with foreign interfaces
such as standalone NICs or Wi-Fi APs is an important use case. There, a
VLAN installed on a neighbor bridge port roughly corresponds to a
forwarding VLAN installed on the DSA switch's CPU port.

To support this use case while also making use of the benefits of the
switchdev_handle_* replication helper for port objects, introduce a new
variant of these functions that crawls through the neighbor ports of
@dev, in search of potentially compatible switchdev ports that are
interested in the event.

The strategy is identical to switchdev_handle_fdb_event_to_device():
if @dev wasn't a switchdev interface, then go one step upper, and
recursively call this function on the bridge that this port belongs to.
At the next recursion step, __switchdev_handle_port_obj_add() will
iterate through the bridge's lower interfaces. Among those, some will be
switchdev interfaces, and one will be the original @dev that we came
from. To prevent infinite recursion, we must suppress reentry into the
original @dev, and just call the @add_cb for the switchdev_interfaces.

It looks like this:

                br0
               / | \
              /  |  \
             /   |   \
           swp0 swp1 eth0

1. __switchdev_handle_port_obj_add(eth0)
   -> check_cb(eth0) returns false
   -> eth0 has no lower interfaces
   -> eth0's bridge is br0
   -> switchdev_lower_dev_find(br0, check_cb, foreign_dev_check_cb))
      finds br0

2. __switchdev_handle_port_obj_add(br0)
   -> check_cb(br0) returns false
   -> netdev_for_each_lower_dev
      -> check_cb(swp0) returns true, so we don't skip this interface

3. __switchdev_handle_port_obj_add(swp0)
   -> check_cb(swp0) returns true, so we call add_cb(swp0)

(back to netdev_for_each_lower_dev from 2)
      -> check_cb(swp1) returns true, so we don't skip this interface

4. __switchdev_handle_port_obj_add(swp1)
   -> check_cb(swp1) returns true, so we call add_cb(swp1)

(back to netdev_for_each_lower_dev from 2)
      -> check_cb(eth0) returns false, so we skip this interface to
         avoid infinite recursion

Note: eth0 could have been a LAG, and we don't want to suppress the
recursion through its lowers if those exist, so when check_cb() returns
false, we still call switchdev_lower_dev_find() to estimate whether
there's anything worth a recursion beneath that LAG. Using check_cb()
and foreign_dev_check_cb(), switchdev_lower_dev_find() not only figures
out whether the lowers of the LAG are switchdev, but also whether they
actively offload the LAG or not (whether the LAG is "foreign" to the
switchdev interface or not).

The port_obj_info->orig_dev is preserved across recursive calls, so
switchdev drivers still know on which device was this notification
originally emitted.

Signed-off-by: Vladimir Oltean <vladimir.oltean@nxp.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 include/net/switchdev.h   |  39 +++++++++++++
 net/switchdev/switchdev.c | 140 +++++++++++++++++++++++++++++++++++++++++++---
 2 files changed, 171 insertions(+), 8 deletions(-)

diff --git a/include/net/switchdev.h b/include/net/switchdev.h
index 92cc763991e9..c32e1c8f79ec 100644
--- a/include/net/switchdev.h
+++ b/include/net/switchdev.h
@@ -324,11 +324,26 @@ int switchdev_handle_port_obj_add(struct net_device *dev,
 			int (*add_cb)(struct net_device *dev, const void *ctx,
 				      const struct switchdev_obj *obj,
 				      struct netlink_ext_ack *extack));
+int switchdev_handle_port_obj_add_foreign(struct net_device *dev,
+			struct switchdev_notifier_port_obj_info *port_obj_info,
+			bool (*check_cb)(const struct net_device *dev),
+			bool (*foreign_dev_check_cb)(const struct net_device *dev,
+						     const struct net_device *foreign_dev),
+			int (*add_cb)(struct net_device *dev, const void *ctx,
+				      const struct switchdev_obj *obj,
+				      struct netlink_ext_ack *extack));
 int switchdev_handle_port_obj_del(struct net_device *dev,
 			struct switchdev_notifier_port_obj_info *port_obj_info,
 			bool (*check_cb)(const struct net_device *dev),
 			int (*del_cb)(struct net_device *dev, const void *ctx,
 				      const struct switchdev_obj *obj));
+int switchdev_handle_port_obj_del_foreign(struct net_device *dev,
+			struct switchdev_notifier_port_obj_info *port_obj_info,
+			bool (*check_cb)(const struct net_device *dev),
+			bool (*foreign_dev_check_cb)(const struct net_device *dev,
+						     const struct net_device *foreign_dev),
+			int (*del_cb)(struct net_device *dev, const void *ctx,
+				      const struct switchdev_obj *obj));
 
 int switchdev_handle_port_attr_set(struct net_device *dev,
 			struct switchdev_notifier_port_attr_info *port_attr_info,
@@ -447,6 +462,18 @@ switchdev_handle_port_obj_add(struct net_device *dev,
 	return 0;
 }
 
+static inline int switchdev_handle_port_obj_add_foreign(struct net_device *dev,
+			struct switchdev_notifier_port_obj_info *port_obj_info,
+			bool (*check_cb)(const struct net_device *dev),
+			bool (*foreign_dev_check_cb)(const struct net_device *dev,
+						     const struct net_device *foreign_dev),
+			int (*add_cb)(struct net_device *dev, const void *ctx,
+				      const struct switchdev_obj *obj,
+				      struct netlink_ext_ack *extack))
+{
+	return 0;
+}
+
 static inline int
 switchdev_handle_port_obj_del(struct net_device *dev,
 			struct switchdev_notifier_port_obj_info *port_obj_info,
@@ -457,6 +484,18 @@ switchdev_handle_port_obj_del(struct net_device *dev,
 	return 0;
 }
 
+static inline int
+switchdev_handle_port_obj_del_foreign(struct net_device *dev,
+			struct switchdev_notifier_port_obj_info *port_obj_info,
+			bool (*check_cb)(const struct net_device *dev),
+			bool (*foreign_dev_check_cb)(const struct net_device *dev,
+						     const struct net_device *foreign_dev),
+			int (*del_cb)(struct net_device *dev, const void *ctx,
+				      const struct switchdev_obj *obj))
+{
+	return 0;
+}
+
 static inline int
 switchdev_handle_port_attr_set(struct net_device *dev,
 			struct switchdev_notifier_port_attr_info *port_attr_info,
diff --git a/net/switchdev/switchdev.c b/net/switchdev/switchdev.c
index d53f364870a5..6a00c390547b 100644
--- a/net/switchdev/switchdev.c
+++ b/net/switchdev/switchdev.c
@@ -429,6 +429,27 @@ switchdev_lower_dev_find_rcu(struct net_device *dev,
 	return switchdev_priv.lower_dev;
 }
 
+static struct net_device *
+switchdev_lower_dev_find(struct net_device *dev,
+			 bool (*check_cb)(const struct net_device *dev),
+			 bool (*foreign_dev_check_cb)(const struct net_device *dev,
+						      const struct net_device *foreign_dev))
+{
+	struct switchdev_nested_priv switchdev_priv = {
+		.check_cb = check_cb,
+		.foreign_dev_check_cb = foreign_dev_check_cb,
+		.dev = dev,
+		.lower_dev = NULL,
+	};
+	struct netdev_nested_priv priv = {
+		.data = &switchdev_priv,
+	};
+
+	netdev_walk_all_lower_dev(dev, switchdev_lower_dev_walk, &priv);
+
+	return switchdev_priv.lower_dev;
+}
+
 static int __switchdev_handle_fdb_event_to_device(struct net_device *dev,
 		struct net_device *orig_dev, unsigned long event,
 		const struct switchdev_notifier_fdb_info *fdb_info,
@@ -536,13 +557,15 @@ EXPORT_SYMBOL_GPL(switchdev_handle_fdb_event_to_device);
 static int __switchdev_handle_port_obj_add(struct net_device *dev,
 			struct switchdev_notifier_port_obj_info *port_obj_info,
 			bool (*check_cb)(const struct net_device *dev),
+			bool (*foreign_dev_check_cb)(const struct net_device *dev,
+						     const struct net_device *foreign_dev),
 			int (*add_cb)(struct net_device *dev, const void *ctx,
 				      const struct switchdev_obj *obj,
 				      struct netlink_ext_ack *extack))
 {
 	struct switchdev_notifier_info *info = &port_obj_info->info;
+	struct net_device *br, *lower_dev;
 	struct netlink_ext_ack *extack;
-	struct net_device *lower_dev;
 	struct list_head *iter;
 	int err = -EOPNOTSUPP;
 
@@ -566,15 +589,42 @@ static int __switchdev_handle_port_obj_add(struct net_device *dev,
 		if (netif_is_bridge_master(lower_dev))
 			continue;
 
+		/* When searching for switchdev interfaces that are neighbors
+		 * of foreign ones, and @dev is a bridge, do not recurse on the
+		 * foreign interface again, it was already visited.
+		 */
+		if (foreign_dev_check_cb && !check_cb(lower_dev) &&
+		    !switchdev_lower_dev_find(lower_dev, check_cb, foreign_dev_check_cb))
+			continue;
+
 		err = __switchdev_handle_port_obj_add(lower_dev, port_obj_info,
-						      check_cb, add_cb);
+						      check_cb, foreign_dev_check_cb,
+						      add_cb);
 		if (err && err != -EOPNOTSUPP)
 			return err;
 	}
 
-	return err;
+	/* Event is neither on a bridge nor a LAG. Check whether it is on an
+	 * interface that is in a bridge with us.
+	 */
+	if (!foreign_dev_check_cb)
+		return err;
+
+	br = netdev_master_upper_dev_get(dev);
+	if (!br || !netif_is_bridge_master(br))
+		return err;
+
+	if (!switchdev_lower_dev_find(br, check_cb, foreign_dev_check_cb))
+		return err;
+
+	return __switchdev_handle_port_obj_add(br, port_obj_info, check_cb,
+					       foreign_dev_check_cb, add_cb);
 }
 
+/* Pass through a port object addition, if @dev passes @check_cb, or replicate
+ * it towards all lower interfaces of @dev that pass @check_cb, if @dev is a
+ * bridge or a LAG.
+ */
 int switchdev_handle_port_obj_add(struct net_device *dev,
 			struct switchdev_notifier_port_obj_info *port_obj_info,
 			bool (*check_cb)(const struct net_device *dev),
@@ -585,21 +635,46 @@ int switchdev_handle_port_obj_add(struct net_device *dev,
 	int err;
 
 	err = __switchdev_handle_port_obj_add(dev, port_obj_info, check_cb,
-					      add_cb);
+					      NULL, add_cb);
 	if (err == -EOPNOTSUPP)
 		err = 0;
 	return err;
 }
 EXPORT_SYMBOL_GPL(switchdev_handle_port_obj_add);
 
+/* Same as switchdev_handle_port_obj_add(), except if object is notified on a
+ * @dev that passes @foreign_dev_check_cb, it is replicated towards all devices
+ * that pass @check_cb and are in the same bridge as @dev.
+ */
+int switchdev_handle_port_obj_add_foreign(struct net_device *dev,
+			struct switchdev_notifier_port_obj_info *port_obj_info,
+			bool (*check_cb)(const struct net_device *dev),
+			bool (*foreign_dev_check_cb)(const struct net_device *dev,
+						     const struct net_device *foreign_dev),
+			int (*add_cb)(struct net_device *dev, const void *ctx,
+				      const struct switchdev_obj *obj,
+				      struct netlink_ext_ack *extack))
+{
+	int err;
+
+	err = __switchdev_handle_port_obj_add(dev, port_obj_info, check_cb,
+					      foreign_dev_check_cb, add_cb);
+	if (err == -EOPNOTSUPP)
+		err = 0;
+	return err;
+}
+EXPORT_SYMBOL_GPL(switchdev_handle_port_obj_add_foreign);
+
 static int __switchdev_handle_port_obj_del(struct net_device *dev,
 			struct switchdev_notifier_port_obj_info *port_obj_info,
 			bool (*check_cb)(const struct net_device *dev),
+			bool (*foreign_dev_check_cb)(const struct net_device *dev,
+						     const struct net_device *foreign_dev),
 			int (*del_cb)(struct net_device *dev, const void *ctx,
 				      const struct switchdev_obj *obj))
 {
 	struct switchdev_notifier_info *info = &port_obj_info->info;
-	struct net_device *lower_dev;
+	struct net_device *br, *lower_dev;
 	struct list_head *iter;
 	int err = -EOPNOTSUPP;
 
@@ -621,15 +696,42 @@ static int __switchdev_handle_port_obj_del(struct net_device *dev,
 		if (netif_is_bridge_master(lower_dev))
 			continue;
 
+		/* When searching for switchdev interfaces that are neighbors
+		 * of foreign ones, and @dev is a bridge, do not recurse on the
+		 * foreign interface again, it was already visited.
+		 */
+		if (foreign_dev_check_cb && !check_cb(lower_dev) &&
+		    !switchdev_lower_dev_find(lower_dev, check_cb, foreign_dev_check_cb))
+			continue;
+
 		err = __switchdev_handle_port_obj_del(lower_dev, port_obj_info,
-						      check_cb, del_cb);
+						      check_cb, foreign_dev_check_cb,
+						      del_cb);
 		if (err && err != -EOPNOTSUPP)
 			return err;
 	}
 
-	return err;
+	/* Event is neither on a bridge nor a LAG. Check whether it is on an
+	 * interface that is in a bridge with us.
+	 */
+	if (!foreign_dev_check_cb)
+		return err;
+
+	br = netdev_master_upper_dev_get(dev);
+	if (!br || !netif_is_bridge_master(br))
+		return err;
+
+	if (!switchdev_lower_dev_find(br, check_cb, foreign_dev_check_cb))
+		return err;
+
+	return __switchdev_handle_port_obj_del(br, port_obj_info, check_cb,
+					       foreign_dev_check_cb, del_cb);
 }
 
+/* Pass through a port object deletion, if @dev passes @check_cb, or replicate
+ * it towards all lower interfaces of @dev that pass @check_cb, if @dev is a
+ * bridge or a LAG.
+ */
 int switchdev_handle_port_obj_del(struct net_device *dev,
 			struct switchdev_notifier_port_obj_info *port_obj_info,
 			bool (*check_cb)(const struct net_device *dev),
@@ -639,13 +741,35 @@ int switchdev_handle_port_obj_del(struct net_device *dev,
 	int err;
 
 	err = __switchdev_handle_port_obj_del(dev, port_obj_info, check_cb,
-					      del_cb);
+					      NULL, del_cb);
 	if (err == -EOPNOTSUPP)
 		err = 0;
 	return err;
 }
 EXPORT_SYMBOL_GPL(switchdev_handle_port_obj_del);
 
+/* Same as switchdev_handle_port_obj_del(), except if object is notified on a
+ * @dev that passes @foreign_dev_check_cb, it is replicated towards all devices
+ * that pass @check_cb and are in the same bridge as @dev.
+ */
+int switchdev_handle_port_obj_del_foreign(struct net_device *dev,
+			struct switchdev_notifier_port_obj_info *port_obj_info,
+			bool (*check_cb)(const struct net_device *dev),
+			bool (*foreign_dev_check_cb)(const struct net_device *dev,
+						     const struct net_device *foreign_dev),
+			int (*del_cb)(struct net_device *dev, const void *ctx,
+				      const struct switchdev_obj *obj))
+{
+	int err;
+
+	err = __switchdev_handle_port_obj_del(dev, port_obj_info, check_cb,
+					      foreign_dev_check_cb, del_cb);
+	if (err == -EOPNOTSUPP)
+		err = 0;
+	return err;
+}
+EXPORT_SYMBOL_GPL(switchdev_handle_port_obj_del_foreign);
+
 static int __switchdev_handle_port_attr_set(struct net_device *dev,
 			struct switchdev_notifier_port_attr_info *port_attr_info,
 			bool (*check_cb)(const struct net_device *dev),
-- 
cgit v1.3-7-g2ca7


From 134ef2388e7f3271d13223decdb5e45b0f84489f Mon Sep 17 00:00:00 2001
From: Vladimir Oltean <vladimir.oltean@nxp.com>
Date: Tue, 15 Feb 2022 19:02:17 +0200
Subject: net: dsa: add explicit support for host bridge VLANs

Currently, DSA programs VLANs on shared (DSA and CPU) ports each time it
does so on user ports. This is good for basic functionality but has
several limitations:

- the VLAN group which must reach the CPU may be radically different
  from the VLAN group that must be autonomously forwarded by the switch.
  In other words, the admin may want to isolate noisy stations and avoid
  traffic from them going to the control processor of the switch, where
  it would just waste useless cycles. The bridge already supports
  independent control of VLAN groups on bridge ports and on the bridge
  itself, and when VLAN-aware, it will drop packets in software anyway
  if their VID isn't added as a 'self' entry towards the bridge device.

- Replaying host FDB entries may depend, for some drivers like mv88e6xxx,
  on replaying the host VLANs as well. The 2 VLAN groups are
  approximately the same in most regular cases, but there are corner
  cases when timing matters, and DSA's approximation of replicating
  VLANs on shared ports simply does not work.

- If a user makes the bridge (implicitly the CPU port) join a VLAN by
  accident, there is no way for the CPU port to isolate itself from that
  noisy VLAN except by rebooting the system. This is because for each
  VLAN added on a user port, DSA will add it on shared ports too, but
  for each VLAN deletion on a user port, it will remain installed on
  shared ports, since DSA has no good indication of whether the VLAN is
  still in use or not.

Now that the bridge driver emits well-balanced SWITCHDEV_OBJ_ID_PORT_VLAN
addition and removal events, DSA has a simple and straightforward task
of separating the bridge port VLANs (these have an orig_dev which is a
DSA slave interface, or a LAG interface) from the host VLANs (these have
an orig_dev which is a bridge interface), and to keep a simple reference
count of each VID on each shared port.

Forwarding VLANs must be installed on the bridge ports and on all DSA
ports interconnecting them. We don't have a good view of the exact
topology, so we simply install forwarding VLANs on all DSA ports, which
is what has been done until now.

Host VLANs must be installed primarily on the dedicated CPU port of each
bridge port. More subtly, they must also be installed on upstream-facing
and downstream-facing DSA ports that are connecting the bridge ports and
the CPU. This ensures that the mv88e6xxx's problem (VID of host FDB
entry may be absent from VTU) is still addressed even if that switch is
in a cross-chip setup, and it has no local CPU port.

Therefore:
- user ports contain only bridge port (forwarding) VLANs, and no
  refcounting is necessary
- DSA ports contain both forwarding and host VLANs. Refcounting is
  necessary among these 2 types.
- CPU ports contain only host VLANs. Refcounting is also necessary.

Signed-off-by: Vladimir Oltean <vladimir.oltean@nxp.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 include/net/dsa.h  |  10 +++
 net/dsa/dsa2.c     |   2 +
 net/dsa/dsa_priv.h |   7 ++
 net/dsa/port.c     |  42 ++++++++++++
 net/dsa/slave.c    |  97 +++++++++++++++------------
 net/dsa/switch.c   | 187 +++++++++++++++++++++++++++++++++++++++++++++++++++--
 6 files changed, 298 insertions(+), 47 deletions(-)

diff --git a/include/net/dsa.h b/include/net/dsa.h
index fd1f62a6e0a8..85cb9aed4c51 100644
--- a/include/net/dsa.h
+++ b/include/net/dsa.h
@@ -312,6 +312,10 @@ struct dsa_port {
 	struct mutex		addr_lists_lock;
 	struct list_head	fdbs;
 	struct list_head	mdbs;
+
+	/* List of VLANs that CPU and DSA ports are members of. */
+	struct mutex		vlans_lock;
+	struct list_head	vlans;
 };
 
 /* TODO: ideally DSA ports would have a single dp->link_dp member,
@@ -332,6 +336,12 @@ struct dsa_mac_addr {
 	struct list_head list;
 };
 
+struct dsa_vlan {
+	u16 vid;
+	refcount_t refcount;
+	struct list_head list;
+};
+
 struct dsa_switch {
 	struct device *dev;
 
diff --git a/net/dsa/dsa2.c b/net/dsa/dsa2.c
index e498c927c3d0..1df8c2356463 100644
--- a/net/dsa/dsa2.c
+++ b/net/dsa/dsa2.c
@@ -453,8 +453,10 @@ static int dsa_port_setup(struct dsa_port *dp)
 		return 0;
 
 	mutex_init(&dp->addr_lists_lock);
+	mutex_init(&dp->vlans_lock);
 	INIT_LIST_HEAD(&dp->fdbs);
 	INIT_LIST_HEAD(&dp->mdbs);
+	INIT_LIST_HEAD(&dp->vlans);
 
 	if (ds->ops->port_setup) {
 		err = ds->ops->port_setup(ds, dp->index);
diff --git a/net/dsa/dsa_priv.h b/net/dsa/dsa_priv.h
index 2bbfa9efe9f8..6a3878157b0a 100644
--- a/net/dsa/dsa_priv.h
+++ b/net/dsa/dsa_priv.h
@@ -34,6 +34,8 @@ enum {
 	DSA_NOTIFIER_HOST_MDB_DEL,
 	DSA_NOTIFIER_VLAN_ADD,
 	DSA_NOTIFIER_VLAN_DEL,
+	DSA_NOTIFIER_HOST_VLAN_ADD,
+	DSA_NOTIFIER_HOST_VLAN_DEL,
 	DSA_NOTIFIER_MTU,
 	DSA_NOTIFIER_TAG_PROTO,
 	DSA_NOTIFIER_TAG_PROTO_CONNECT,
@@ -234,6 +236,11 @@ int dsa_port_vlan_add(struct dsa_port *dp,
 		      struct netlink_ext_ack *extack);
 int dsa_port_vlan_del(struct dsa_port *dp,
 		      const struct switchdev_obj_port_vlan *vlan);
+int dsa_port_host_vlan_add(struct dsa_port *dp,
+			   const struct switchdev_obj_port_vlan *vlan,
+			   struct netlink_ext_ack *extack);
+int dsa_port_host_vlan_del(struct dsa_port *dp,
+			   const struct switchdev_obj_port_vlan *vlan);
 int dsa_port_mrp_add(const struct dsa_port *dp,
 		     const struct switchdev_obj_mrp *mrp);
 int dsa_port_mrp_del(const struct dsa_port *dp,
diff --git a/net/dsa/port.c b/net/dsa/port.c
index bd78192e0e47..cca5cf686f74 100644
--- a/net/dsa/port.c
+++ b/net/dsa/port.c
@@ -904,6 +904,48 @@ int dsa_port_vlan_del(struct dsa_port *dp,
 	return dsa_port_notify(dp, DSA_NOTIFIER_VLAN_DEL, &info);
 }
 
+int dsa_port_host_vlan_add(struct dsa_port *dp,
+			   const struct switchdev_obj_port_vlan *vlan,
+			   struct netlink_ext_ack *extack)
+{
+	struct dsa_notifier_vlan_info info = {
+		.sw_index = dp->ds->index,
+		.port = dp->index,
+		.vlan = vlan,
+		.extack = extack,
+	};
+	struct dsa_port *cpu_dp = dp->cpu_dp;
+	int err;
+
+	err = dsa_port_notify(dp, DSA_NOTIFIER_HOST_VLAN_ADD, &info);
+	if (err && err != -EOPNOTSUPP)
+		return err;
+
+	vlan_vid_add(cpu_dp->master, htons(ETH_P_8021Q), vlan->vid);
+
+	return err;
+}
+
+int dsa_port_host_vlan_del(struct dsa_port *dp,
+			   const struct switchdev_obj_port_vlan *vlan)
+{
+	struct dsa_notifier_vlan_info info = {
+		.sw_index = dp->ds->index,
+		.port = dp->index,
+		.vlan = vlan,
+	};
+	struct dsa_port *cpu_dp = dp->cpu_dp;
+	int err;
+
+	err = dsa_port_notify(dp, DSA_NOTIFIER_HOST_VLAN_DEL, &info);
+	if (err && err != -EOPNOTSUPP)
+		return err;
+
+	vlan_vid_del(cpu_dp->master, htons(ETH_P_8021Q), vlan->vid);
+
+	return err;
+}
+
 int dsa_port_mrp_add(const struct dsa_port *dp,
 		     const struct switchdev_obj_mrp *mrp)
 {
diff --git a/net/dsa/slave.c b/net/dsa/slave.c
index 2f6caf5d037e..734c381f89ca 100644
--- a/net/dsa/slave.c
+++ b/net/dsa/slave.c
@@ -348,9 +348,8 @@ static int dsa_slave_vlan_add(struct net_device *dev,
 			      const struct switchdev_obj *obj,
 			      struct netlink_ext_ack *extack)
 {
-	struct net_device *master = dsa_slave_to_master(dev);
 	struct dsa_port *dp = dsa_slave_to_port(dev);
-	struct switchdev_obj_port_vlan vlan;
+	struct switchdev_obj_port_vlan *vlan;
 	int err;
 
 	if (dsa_port_skip_vlan_configuration(dp)) {
@@ -358,14 +357,14 @@ static int dsa_slave_vlan_add(struct net_device *dev,
 		return 0;
 	}
 
-	vlan = *SWITCHDEV_OBJ_PORT_VLAN(obj);
+	vlan = SWITCHDEV_OBJ_PORT_VLAN(obj);
 
 	/* Deny adding a bridge VLAN when there is already an 802.1Q upper with
 	 * the same VID.
 	 */
 	if (br_vlan_enabled(dsa_port_bridge_dev_get(dp))) {
 		rcu_read_lock();
-		err = dsa_slave_vlan_check_for_8021q_uppers(dev, &vlan);
+		err = dsa_slave_vlan_check_for_8021q_uppers(dev, vlan);
 		rcu_read_unlock();
 		if (err) {
 			NL_SET_ERR_MSG_MOD(extack,
@@ -374,21 +373,29 @@ static int dsa_slave_vlan_add(struct net_device *dev,
 		}
 	}
 
-	err = dsa_port_vlan_add(dp, &vlan, extack);
-	if (err)
-		return err;
+	return dsa_port_vlan_add(dp, vlan, extack);
+}
 
-	/* We need the dedicated CPU port to be a member of the VLAN as well.
-	 * Even though drivers often handle CPU membership in special ways,
+static int dsa_slave_host_vlan_add(struct net_device *dev,
+				   const struct switchdev_obj *obj,
+				   struct netlink_ext_ack *extack)
+{
+	struct dsa_port *dp = dsa_slave_to_port(dev);
+	struct switchdev_obj_port_vlan vlan;
+
+	if (dsa_port_skip_vlan_configuration(dp)) {
+		NL_SET_ERR_MSG_MOD(extack, "skipping configuration of VLAN");
+		return 0;
+	}
+
+	vlan = *SWITCHDEV_OBJ_PORT_VLAN(obj);
+
+	/* Even though drivers often handle CPU membership in special ways,
 	 * it doesn't make sense to program a PVID, so clear this flag.
 	 */
 	vlan.flags &= ~BRIDGE_VLAN_INFO_PVID;
 
-	err = dsa_port_vlan_add(dp->cpu_dp, &vlan, extack);
-	if (err)
-		return err;
-
-	return vlan_vid_add(master, htons(ETH_P_8021Q), vlan.vid);
+	return dsa_port_host_vlan_add(dp, &vlan, extack);
 }
 
 static int dsa_slave_port_obj_add(struct net_device *dev, const void *ctx,
@@ -415,10 +422,17 @@ static int dsa_slave_port_obj_add(struct net_device *dev, const void *ctx,
 		err = dsa_port_host_mdb_add(dp, SWITCHDEV_OBJ_PORT_MDB(obj));
 		break;
 	case SWITCHDEV_OBJ_ID_PORT_VLAN:
-		if (!dsa_port_offloads_bridge_port(dp, obj->orig_dev))
-			return -EOPNOTSUPP;
+		if (netif_is_bridge_master(obj->orig_dev)) {
+			if (!dsa_port_offloads_bridge_dev(dp, obj->orig_dev))
+				return -EOPNOTSUPP;
+
+			err = dsa_slave_host_vlan_add(dev, obj, extack);
+		} else {
+			if (!dsa_port_offloads_bridge_port(dp, obj->orig_dev))
+				return -EOPNOTSUPP;
 
-		err = dsa_slave_vlan_add(dev, obj, extack);
+			err = dsa_slave_vlan_add(dev, obj, extack);
+		}
 		break;
 	case SWITCHDEV_OBJ_ID_MRP:
 		if (!dsa_port_offloads_bridge_dev(dp, obj->orig_dev))
@@ -444,26 +458,29 @@ static int dsa_slave_port_obj_add(struct net_device *dev, const void *ctx,
 static int dsa_slave_vlan_del(struct net_device *dev,
 			      const struct switchdev_obj *obj)
 {
-	struct net_device *master = dsa_slave_to_master(dev);
 	struct dsa_port *dp = dsa_slave_to_port(dev);
 	struct switchdev_obj_port_vlan *vlan;
-	int err;
 
 	if (dsa_port_skip_vlan_configuration(dp))
 		return 0;
 
 	vlan = SWITCHDEV_OBJ_PORT_VLAN(obj);
 
-	/* Do not deprogram the CPU port as it may be shared with other user
-	 * ports which can be members of this VLAN as well.
-	 */
-	err = dsa_port_vlan_del(dp, vlan);
-	if (err)
-		return err;
+	return dsa_port_vlan_del(dp, vlan);
+}
 
-	vlan_vid_del(master, htons(ETH_P_8021Q), vlan->vid);
+static int dsa_slave_host_vlan_del(struct net_device *dev,
+				   const struct switchdev_obj *obj)
+{
+	struct dsa_port *dp = dsa_slave_to_port(dev);
+	struct switchdev_obj_port_vlan *vlan;
 
-	return 0;
+	if (dsa_port_skip_vlan_configuration(dp))
+		return 0;
+
+	vlan = SWITCHDEV_OBJ_PORT_VLAN(obj);
+
+	return dsa_port_host_vlan_del(dp, vlan);
 }
 
 static int dsa_slave_port_obj_del(struct net_device *dev, const void *ctx,
@@ -489,10 +506,17 @@ static int dsa_slave_port_obj_del(struct net_device *dev, const void *ctx,
 		err = dsa_port_host_mdb_del(dp, SWITCHDEV_OBJ_PORT_MDB(obj));
 		break;
 	case SWITCHDEV_OBJ_ID_PORT_VLAN:
-		if (!dsa_port_offloads_bridge_port(dp, obj->orig_dev))
-			return -EOPNOTSUPP;
+		if (netif_is_bridge_master(obj->orig_dev)) {
+			if (!dsa_port_offloads_bridge_dev(dp, obj->orig_dev))
+				return -EOPNOTSUPP;
 
-		err = dsa_slave_vlan_del(dev, obj);
+			err = dsa_slave_host_vlan_del(dev, obj);
+		} else {
+			if (!dsa_port_offloads_bridge_port(dp, obj->orig_dev))
+				return -EOPNOTSUPP;
+
+			err = dsa_slave_vlan_del(dev, obj);
+		}
 		break;
 	case SWITCHDEV_OBJ_ID_MRP:
 		if (!dsa_port_offloads_bridge_dev(dp, obj->orig_dev))
@@ -1347,7 +1371,6 @@ static int dsa_slave_get_ts_info(struct net_device *dev,
 static int dsa_slave_vlan_rx_add_vid(struct net_device *dev, __be16 proto,
 				     u16 vid)
 {
-	struct net_device *master = dsa_slave_to_master(dev);
 	struct dsa_port *dp = dsa_slave_to_port(dev);
 	struct switchdev_obj_port_vlan vlan = {
 		.obj.id = SWITCHDEV_OBJ_ID_PORT_VLAN,
@@ -1367,7 +1390,7 @@ static int dsa_slave_vlan_rx_add_vid(struct net_device *dev, __be16 proto,
 	}
 
 	/* And CPU port... */
-	ret = dsa_port_vlan_add(dp->cpu_dp, &vlan, &extack);
+	ret = dsa_port_host_vlan_add(dp, &vlan, &extack);
 	if (ret) {
 		if (extack._msg)
 			netdev_err(dev, "CPU port %d: %s\n", dp->cpu_dp->index,
@@ -1375,13 +1398,12 @@ static int dsa_slave_vlan_rx_add_vid(struct net_device *dev, __be16 proto,
 		return ret;
 	}
 
-	return vlan_vid_add(master, proto, vid);
+	return 0;
 }
 
 static int dsa_slave_vlan_rx_kill_vid(struct net_device *dev, __be16 proto,
 				      u16 vid)
 {
-	struct net_device *master = dsa_slave_to_master(dev);
 	struct dsa_port *dp = dsa_slave_to_port(dev);
 	struct switchdev_obj_port_vlan vlan = {
 		.vid = vid,
@@ -1390,16 +1412,11 @@ static int dsa_slave_vlan_rx_kill_vid(struct net_device *dev, __be16 proto,
 	};
 	int err;
 
-	/* Do not deprogram the CPU port as it may be shared with other user
-	 * ports which can be members of this VLAN as well.
-	 */
 	err = dsa_port_vlan_del(dp, &vlan);
 	if (err)
 		return err;
 
-	vlan_vid_del(master, proto, vid);
-
-	return 0;
+	return dsa_port_host_vlan_del(dp, &vlan);
 }
 
 static int dsa_slave_restore_vlan(struct net_device *vdev, int vid, void *arg)
diff --git a/net/dsa/switch.c b/net/dsa/switch.c
index 4866b58649e4..0bb3987bd4e6 100644
--- a/net/dsa/switch.c
+++ b/net/dsa/switch.c
@@ -558,6 +558,7 @@ static int dsa_switch_host_mdb_del(struct dsa_switch *ds,
 	return err;
 }
 
+/* Port VLANs match on the targeted port and on all DSA ports */
 static bool dsa_port_vlan_match(struct dsa_port *dp,
 				struct dsa_notifier_vlan_info *info)
 {
@@ -570,6 +571,126 @@ static bool dsa_port_vlan_match(struct dsa_port *dp,
 	return false;
 }
 
+/* Host VLANs match on the targeted port's CPU port, and on all DSA ports
+ * (upstream and downstream) of that switch and its upstream switches.
+ */
+static bool dsa_port_host_vlan_match(struct dsa_port *dp,
+				     struct dsa_notifier_vlan_info *info)
+{
+	struct dsa_port *targeted_dp, *cpu_dp;
+	struct dsa_switch *targeted_ds;
+
+	targeted_ds = dsa_switch_find(dp->ds->dst->index, info->sw_index);
+	targeted_dp = dsa_to_port(targeted_ds, info->port);
+	cpu_dp = targeted_dp->cpu_dp;
+
+	if (dsa_switch_is_upstream_of(dp->ds, targeted_ds))
+		return dsa_port_is_dsa(dp) || dp == cpu_dp;
+
+	return false;
+}
+
+static struct dsa_vlan *dsa_vlan_find(struct list_head *vlan_list,
+				      const struct switchdev_obj_port_vlan *vlan)
+{
+	struct dsa_vlan *v;
+
+	list_for_each_entry(v, vlan_list, list)
+		if (v->vid == vlan->vid)
+			return v;
+
+	return NULL;
+}
+
+static int dsa_port_do_vlan_add(struct dsa_port *dp,
+				const struct switchdev_obj_port_vlan *vlan,
+				struct netlink_ext_ack *extack)
+{
+	struct dsa_switch *ds = dp->ds;
+	int port = dp->index;
+	struct dsa_vlan *v;
+	int err = 0;
+
+	/* No need to bother with refcounting for user ports. */
+	if (!(dsa_port_is_cpu(dp) || dsa_port_is_dsa(dp)))
+		return ds->ops->port_vlan_add(ds, port, vlan, extack);
+
+	/* No need to propagate on shared ports the existing VLANs that were
+	 * re-notified after just the flags have changed. This would cause a
+	 * refcount bump which we need to avoid, since it unbalances the
+	 * additions with the deletions.
+	 */
+	if (vlan->changed)
+		return 0;
+
+	mutex_lock(&dp->vlans_lock);
+
+	v = dsa_vlan_find(&dp->vlans, vlan);
+	if (v) {
+		refcount_inc(&v->refcount);
+		goto out;
+	}
+
+	v = kzalloc(sizeof(*v), GFP_KERNEL);
+	if (!v) {
+		err = -ENOMEM;
+		goto out;
+	}
+
+	err = ds->ops->port_vlan_add(ds, port, vlan, extack);
+	if (err) {
+		kfree(v);
+		goto out;
+	}
+
+	v->vid = vlan->vid;
+	refcount_set(&v->refcount, 1);
+	list_add_tail(&v->list, &dp->vlans);
+
+out:
+	mutex_unlock(&dp->vlans_lock);
+
+	return err;
+}
+
+static int dsa_port_do_vlan_del(struct dsa_port *dp,
+				const struct switchdev_obj_port_vlan *vlan)
+{
+	struct dsa_switch *ds = dp->ds;
+	int port = dp->index;
+	struct dsa_vlan *v;
+	int err = 0;
+
+	/* No need to bother with refcounting for user ports */
+	if (!(dsa_port_is_cpu(dp) || dsa_port_is_dsa(dp)))
+		return ds->ops->port_vlan_del(ds, port, vlan);
+
+	mutex_lock(&dp->vlans_lock);
+
+	v = dsa_vlan_find(&dp->vlans, vlan);
+	if (!v) {
+		err = -ENOENT;
+		goto out;
+	}
+
+	if (!refcount_dec_and_test(&v->refcount))
+		goto out;
+
+	err = ds->ops->port_vlan_del(ds, port, vlan);
+	if (err) {
+		refcount_set(&v->refcount, 1);
+		goto out;
+	}
+
+	list_del(&v->list);
+	kfree(v);
+
+out:
+	mutex_unlock(&dp->vlans_lock);
+
+	return err;
+}
+
 static int dsa_switch_vlan_add(struct dsa_switch *ds,
 			       struct dsa_notifier_vlan_info *info)
 {
@@ -581,8 +702,8 @@ static int dsa_switch_vlan_add(struct dsa_switch *ds,
 
 	dsa_switch_for_each_port(dp, ds) {
 		if (dsa_port_vlan_match(dp, info)) {
-			err = ds->ops->port_vlan_add(ds, dp->index, info->vlan,
-						     info->extack);
+			err = dsa_port_do_vlan_add(dp, info->vlan,
+						   info->extack);
 			if (err)
 				return err;
 		}
@@ -594,15 +715,61 @@ static int dsa_switch_vlan_add(struct dsa_switch *ds,
 static int dsa_switch_vlan_del(struct dsa_switch *ds,
 			       struct dsa_notifier_vlan_info *info)
 {
+	struct dsa_port *dp;
+	int err;
+
 	if (!ds->ops->port_vlan_del)
 		return -EOPNOTSUPP;
 
-	if (ds->index == info->sw_index)
-		return ds->ops->port_vlan_del(ds, info->port, info->vlan);
+	dsa_switch_for_each_port(dp, ds) {
+		if (dsa_port_vlan_match(dp, info)) {
+			err = dsa_port_do_vlan_del(dp, info->vlan);
+			if (err)
+				return err;
+		}
+	}
+
+	return 0;
+}
+
+static int dsa_switch_host_vlan_add(struct dsa_switch *ds,
+				    struct dsa_notifier_vlan_info *info)
+{
+	struct dsa_port *dp;
+	int err;
+
+	if (!ds->ops->port_vlan_add)
+		return -EOPNOTSUPP;
+
+	dsa_switch_for_each_port(dp, ds) {
+		if (dsa_port_host_vlan_match(dp, info)) {
+			err = dsa_port_do_vlan_add(dp, info->vlan,
+						   info->extack);
+			if (err)
+				return err;
+		}
+	}
+
+	return 0;
+}
+
+static int dsa_switch_host_vlan_del(struct dsa_switch *ds,
+				    struct dsa_notifier_vlan_info *info)
+{
+	struct dsa_port *dp;
+	int err;
+
+	if (!ds->ops->port_vlan_del)
+		return -EOPNOTSUPP;
+
+	dsa_switch_for_each_port(dp, ds) {
+		if (dsa_port_host_vlan_match(dp, info)) {
+			err = dsa_port_do_vlan_del(dp, info->vlan);
+			if (err)
+				return err;
+		}
+	}
 
-	/* Do not deprogram the DSA links as they may be used as conduit
-	 * for other VLAN members in the fabric.
-	 */
 	return 0;
 }
 
@@ -764,6 +931,12 @@ static int dsa_switch_event(struct notifier_block *nb,
 	case DSA_NOTIFIER_VLAN_DEL:
 		err = dsa_switch_vlan_del(ds, info);
 		break;
+	case DSA_NOTIFIER_HOST_VLAN_ADD:
+		err = dsa_switch_host_vlan_add(ds, info);
+		break;
+	case DSA_NOTIFIER_HOST_VLAN_DEL:
+		err = dsa_switch_host_vlan_del(ds, info);
+		break;
 	case DSA_NOTIFIER_MTU:
 		err = dsa_switch_mtu(ds, info);
 		break;
-- 
cgit v1.3-7-g2ca7


From 164f861bd40ccc3ed10a59ee72437b93670a525a Mon Sep 17 00:00:00 2001
From: Vladimir Oltean <vladimir.oltean@nxp.com>
Date: Tue, 15 Feb 2022 19:02:18 +0200
Subject: net: dsa: offload bridge port VLANs on foreign interfaces

DSA now explicitly handles VLANs installed with the 'self' flag on the
bridge as host VLANs, instead of just replicating every bridge port VLAN
also on the CPU port and never deleting it, which is what it did before.

However, this leaves a corner case uncovered, as explained by
Tobias Waldekranz:
https://patchwork.kernel.org/project/netdevbpf/patch/20220209213044.2353153-6-vladimir.oltean@nxp.com/#24735260

Forwarding towards a bridge port VLAN installed on a bridge port foreign
to DSA (separate NIC, Wi-Fi AP) used to work by virtue of the fact that
DSA itself needed to have at least one port in that VLAN (therefore, it
also had the CPU port in said VLAN). However, now that the CPU port may
not be member of all VLANs that user ports are members of, we need to
ensure this isn't the case if software forwarding to a foreign interface
is required.

The solution is to treat bridge port VLANs on standalone interfaces in
the exact same way as host VLANs. From DSA's perspective, there is no
difference between local termination and software forwarding; packets in
that VLAN must reach the CPU in both cases.

Signed-off-by: Vladimir Oltean <vladimir.oltean@nxp.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/dsa/dsa2.c  |  6 ++++++
 net/dsa/slave.c | 51 +++++++++++++++++++++++++--------------------------
 2 files changed, 31 insertions(+), 26 deletions(-)

diff --git a/net/dsa/dsa2.c b/net/dsa/dsa2.c
index 1df8c2356463..408b79a28cd4 100644
--- a/net/dsa/dsa2.c
+++ b/net/dsa/dsa2.c
@@ -565,6 +565,7 @@ static void dsa_port_teardown(struct dsa_port *dp)
 	struct dsa_switch *ds = dp->ds;
 	struct dsa_mac_addr *a, *tmp;
 	struct net_device *slave;
+	struct dsa_vlan *v, *n;
 
 	if (!dp->setup)
 		return;
@@ -605,6 +606,11 @@ static void dsa_port_teardown(struct dsa_port *dp)
 		kfree(a);
 	}
 
+	list_for_each_entry_safe(v, n, &dp->vlans, list) {
+		list_del(&v->list);
+		kfree(v);
+	}
+
 	dp->setup = false;
 }
 
diff --git a/net/dsa/slave.c b/net/dsa/slave.c
index 734c381f89ca..f61e6b72ffbb 100644
--- a/net/dsa/slave.c
+++ b/net/dsa/slave.c
@@ -376,6 +376,9 @@ static int dsa_slave_vlan_add(struct net_device *dev,
 	return dsa_port_vlan_add(dp, vlan, extack);
 }
 
+/* Offload a VLAN installed on the bridge or on a foreign interface by
+ * installing it as a VLAN towards the CPU port.
+ */
 static int dsa_slave_host_vlan_add(struct net_device *dev,
 				   const struct switchdev_obj *obj,
 				   struct netlink_ext_ack *extack)
@@ -383,6 +386,10 @@ static int dsa_slave_host_vlan_add(struct net_device *dev,
 	struct dsa_port *dp = dsa_slave_to_port(dev);
 	struct switchdev_obj_port_vlan vlan;
 
+	/* Do nothing if this is a software bridge */
+	if (!dp->bridge)
+		return -EOPNOTSUPP;
+
 	if (dsa_port_skip_vlan_configuration(dp)) {
 		NL_SET_ERR_MSG_MOD(extack, "skipping configuration of VLAN");
 		return 0;
@@ -422,17 +429,10 @@ static int dsa_slave_port_obj_add(struct net_device *dev, const void *ctx,
 		err = dsa_port_host_mdb_add(dp, SWITCHDEV_OBJ_PORT_MDB(obj));
 		break;
 	case SWITCHDEV_OBJ_ID_PORT_VLAN:
-		if (netif_is_bridge_master(obj->orig_dev)) {
-			if (!dsa_port_offloads_bridge_dev(dp, obj->orig_dev))
-				return -EOPNOTSUPP;
-
-			err = dsa_slave_host_vlan_add(dev, obj, extack);
-		} else {
-			if (!dsa_port_offloads_bridge_port(dp, obj->orig_dev))
-				return -EOPNOTSUPP;
-
+		if (dsa_port_offloads_bridge_port(dp, obj->orig_dev))
 			err = dsa_slave_vlan_add(dev, obj, extack);
-		}
+		else
+			err = dsa_slave_host_vlan_add(dev, obj, extack);
 		break;
 	case SWITCHDEV_OBJ_ID_MRP:
 		if (!dsa_port_offloads_bridge_dev(dp, obj->orig_dev))
@@ -475,6 +475,10 @@ static int dsa_slave_host_vlan_del(struct net_device *dev,
 	struct dsa_port *dp = dsa_slave_to_port(dev);
 	struct switchdev_obj_port_vlan *vlan;
 
+	/* Do nothing if this is a software bridge */
+	if (!dp->bridge)
+		return -EOPNOTSUPP;
+
 	if (dsa_port_skip_vlan_configuration(dp))
 		return 0;
 
@@ -506,17 +510,10 @@ static int dsa_slave_port_obj_del(struct net_device *dev, const void *ctx,
 		err = dsa_port_host_mdb_del(dp, SWITCHDEV_OBJ_PORT_MDB(obj));
 		break;
 	case SWITCHDEV_OBJ_ID_PORT_VLAN:
-		if (netif_is_bridge_master(obj->orig_dev)) {
-			if (!dsa_port_offloads_bridge_dev(dp, obj->orig_dev))
-				return -EOPNOTSUPP;
-
-			err = dsa_slave_host_vlan_del(dev, obj);
-		} else {
-			if (!dsa_port_offloads_bridge_port(dp, obj->orig_dev))
-				return -EOPNOTSUPP;
-
+		if (dsa_port_offloads_bridge_port(dp, obj->orig_dev))
 			err = dsa_slave_vlan_del(dev, obj);
-		}
+		else
+			err = dsa_slave_host_vlan_del(dev, obj);
 		break;
 	case SWITCHDEV_OBJ_ID_MRP:
 		if (!dsa_port_offloads_bridge_dev(dp, obj->orig_dev))
@@ -2547,14 +2544,16 @@ static int dsa_slave_switchdev_blocking_event(struct notifier_block *unused,
 
 	switch (event) {
 	case SWITCHDEV_PORT_OBJ_ADD:
-		err = switchdev_handle_port_obj_add(dev, ptr,
-						    dsa_slave_dev_check,
-						    dsa_slave_port_obj_add);
+		err = switchdev_handle_port_obj_add_foreign(dev, ptr,
+							    dsa_slave_dev_check,
+							    dsa_foreign_dev_check,
+							    dsa_slave_port_obj_add);
 		return notifier_from_errno(err);
 	case SWITCHDEV_PORT_OBJ_DEL:
-		err = switchdev_handle_port_obj_del(dev, ptr,
-						    dsa_slave_dev_check,
-						    dsa_slave_port_obj_del);
+		err = switchdev_handle_port_obj_del_foreign(dev, ptr,
+							    dsa_slave_dev_check,
+							    dsa_foreign_dev_check,
+							    dsa_slave_port_obj_del);
 		return notifier_from_errno(err);
 	case SWITCHDEV_PORT_ATTR_SET:
 		err = switchdev_handle_port_attr_set(dev, ptr,
-- 
cgit v1.3-7-g2ca7