Merge branch 'switchdev-blocking-notifiers'

Petr Machata says:

====================
switchdev: Convert switchdev_port_obj_{add,del}() to notifiers

An offloading driver may need to have access to switchdev events on
ports that aren't directly under its control. An example is a VXLAN port
attached to a bridge offloaded by a driver. The driver needs to know
about VLANs configured on the VXLAN device. However the VXLAN device
isn't stashed between the bridge and a front-panel-port device (such as
is the case e.g. for LAG devices), so the usual switchdev ops don't
reach the driver.

VXLAN is likely not the only device type like this: in theory any L2
tunnel device that needs offloading will prompt requirement of this
sort.

A way to fix this is to give up the notion of port object addition /
deletion as a switchdev operation, which assumes somewhat tight coupling
between the message producer and consumer. And instead send the message
over a notifier chain.

The series starts with a clean-up patch #1, where
SWITCHDEV_OBJ_PORT_{VLAN, MDB}() are fixed up to lift the constraint
that the passed-in argument be a simple variable named "obj".

switchdev_port_obj_add and _del are invoked in a context that permits
blocking. Not only that, at least for the VLAN notification, being able
to signal failure is actually important. Therefore introduce a new
blocking notifier chain that the new events will be sent on. That's done
in patch #2. Retain the current (atomic) notifier chain for the
preexisting notifications.

In patch #3, introduce two new switchdev notifier types,
SWITCHDEV_PORT_OBJ_ADD and SWITCHDEV_PORT_OBJ_DEL. These notifier types
communicate the same event as the corresponding switchdev op, except in
a form of a notification. struct switchdev_notifier_port_obj_info was
added to carry the fields that correspond to the switchdev op arguments.
An additional field, handled, will be used to communicate back to
switchdev that the event has reached an interested party, which will be
important for the two-phase commit.

In patches #4, #5, and #7, rocker, DSA resp. ethsw are updated to
subscribe to the switchdev blocking notifier chain, and handle the new
notifier types. #6 introduces a helper to determine whether a
netdevice corresponds to a front panel port.

What these three drivers have in common is that their ports don't
support any uppers besides bridge. That makes it possible to ignore any
notifiers that don't reference a front-panel port device, because they
are certainly out of scope.

Unlike the previous three, mlxsw and ocelot drivers admit stacked
devices as uppers. While the current switchdev code recursively descends
through layers of lower devices, eventually calling the op on a
front-panel port device, the notifier would reference a stacking device
that's one of front-panel ports uppers. The filtering is thus more
complex.

For ocelot, such iteration is currently pretty much required, because
there's no bookkeeping of LAG devices. mlxsw does keep the list of LAGs,
however it iterates the lower devices anyway when deciding whether an
event on a tunnel device pertains to the driver or not.

Therefore this patch set instead introduces, in patch #8, a helper to
iterate through lowers, much like the current switchdev code does,
looking for devices that match a given predicate.

Then in patches #9 and #10, first mlxsw and then ocelot are updated to
dispatch the newly-added notifier types to the preexisting
port_obj_add/_del handlers. The dispatch is done via the new helper, to
recursively descend through lower devices.

Finally in patch #11, the actual switch is made, retiring the current
SDO-based code in favor of a notifier.

Now that the event is distributed through a notifier, the explicit
netdevice check in rocker, DSA and ethsw doesn't let through any events
except those done on a front-panel port itself. It is therefore
unnecessary to check in VLAN-handling code whether a VLAN was added to
the bridge itself: such events will simply be ignored much sooner.
Therefore remove it in patch #12.
====================

Signed-off-by: David S. Miller <davem@davemloft.net>

1 files changed, 74 insertions, 13 deletions

diff --git a/include/net/switchdev.h b/include/net/switchdev.h
index 7b371e7c4bc6..866b6d148b77 100644
--- a/include/net/switchdev.h
+++ b/include/net/switchdev.h
@@ -95,8 +95,8 @@ struct switchdev_obj_port_vlan {
 	u16 vid_end;
 };
 
-#define SWITCHDEV_OBJ_PORT_VLAN(obj) \
-	container_of(obj, struct switchdev_obj_port_vlan, obj)
+#define SWITCHDEV_OBJ_PORT_VLAN(OBJ) \
+	container_of((OBJ), struct switchdev_obj_port_vlan, obj)
 
 /* SWITCHDEV_OBJ_ID_PORT_MDB */
 struct switchdev_obj_port_mdb {
@@ -105,8 +105,8 @@ struct switchdev_obj_port_mdb {
 	u16 vid;
 };
 
-#define SWITCHDEV_OBJ_PORT_MDB(obj) \
-	container_of(obj, struct switchdev_obj_port_mdb, obj)
+#define SWITCHDEV_OBJ_PORT_MDB(OBJ) \
+	container_of((OBJ), struct switchdev_obj_port_mdb, obj)
 
 void switchdev_trans_item_enqueue(struct switchdev_trans *trans,
 				  void *data, void (*destructor)(void const *),
@@ -121,10 +121,6 @@ typedef int switchdev_obj_dump_cb_t(struct switchdev_obj *obj);
  * @switchdev_port_attr_get: Get a port attribute (see switchdev_attr).
  *
  * @switchdev_port_attr_set: Set a port attribute (see switchdev_attr).
- *
- * @switchdev_port_obj_add: Add an object to port (see switchdev_obj_*).
- *
- * @switchdev_port_obj_del: Delete an object from port (see switchdev_obj_*).
  */
 struct switchdev_ops {
 	int	(*switchdev_port_attr_get)(struct net_device *dev,
@@ -132,11 +128,6 @@ struct switchdev_ops {
 	int	(*switchdev_port_attr_set)(struct net_device *dev,
 					   const struct switchdev_attr *attr,
 					   struct switchdev_trans *trans);
-	int	(*switchdev_port_obj_add)(struct net_device *dev,
-					  const struct switchdev_obj *obj,
-					  struct switchdev_trans *trans);
-	int	(*switchdev_port_obj_del)(struct net_device *dev,
-					  const struct switchdev_obj *obj);
 };
 
 enum switchdev_notifier_type {
@@ -146,6 +137,9 @@ enum switchdev_notifier_type {
 	SWITCHDEV_FDB_DEL_TO_DEVICE,
 	SWITCHDEV_FDB_OFFLOADED,
 
+	SWITCHDEV_PORT_OBJ_ADD, /* Blocking. */
+	SWITCHDEV_PORT_OBJ_DEL, /* Blocking. */
+
 	SWITCHDEV_VXLAN_FDB_ADD_TO_BRIDGE,
 	SWITCHDEV_VXLAN_FDB_DEL_TO_BRIDGE,
 	SWITCHDEV_VXLAN_FDB_ADD_TO_DEVICE,
@@ -165,6 +159,13 @@ struct switchdev_notifier_fdb_info {
 	   offloaded:1;
 };
 
+struct switchdev_notifier_port_obj_info {
+	struct switchdev_notifier_info info; /* must be first */
+	const struct switchdev_obj *obj;
+	struct switchdev_trans *trans;
+	bool handled;
+};
+
 static inline struct net_device *
 switchdev_notifier_info_to_dev(const struct switchdev_notifier_info *info)
 {
@@ -182,10 +183,17 @@ int switchdev_port_obj_add(struct net_device *dev,
 			   const struct switchdev_obj *obj);
 int switchdev_port_obj_del(struct net_device *dev,
 			   const struct switchdev_obj *obj);
+
 int register_switchdev_notifier(struct notifier_block *nb);
 int unregister_switchdev_notifier(struct notifier_block *nb);
 int call_switchdev_notifiers(unsigned long val, struct net_device *dev,
 			     struct switchdev_notifier_info *info);
+
+int register_switchdev_blocking_notifier(struct notifier_block *nb);
+int unregister_switchdev_blocking_notifier(struct notifier_block *nb);
+int call_switchdev_blocking_notifiers(unsigned long val, struct net_device *dev,
+				      struct switchdev_notifier_info *info);
+
 void switchdev_port_fwd_mark_set(struct net_device *dev,
 				 struct net_device *group_dev,
 				 bool joining);
@@ -193,6 +201,18 @@ void switchdev_port_fwd_mark_set(struct net_device *dev,
 bool switchdev_port_same_parent_id(struct net_device *a,
 				   struct net_device *b);
 
+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),
+			int (*add_cb)(struct net_device *dev,
+				      const struct switchdev_obj *obj,
+				      struct switchdev_trans *trans));
+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 struct switchdev_obj *obj));
+
 #define SWITCHDEV_SET_OPS(netdev, ops) ((netdev)->switchdev_ops = (ops))
 #else
 
@@ -241,12 +261,53 @@ static inline int call_switchdev_notifiers(unsigned long val,
 	return NOTIFY_DONE;
 }
 
+static inline int
+register_switchdev_blocking_notifier(struct notifier_block *nb)
+{
+	return 0;
+}
+
+static inline int
+unregister_switchdev_blocking_notifier(struct notifier_block *nb)
+{
+	return 0;
+}
+
+static inline int
+call_switchdev_blocking_notifiers(unsigned long val,
+				  struct net_device *dev,
+				  struct switchdev_notifier_info *info)
+{
+	return NOTIFY_DONE;
+}
+
 static inline bool switchdev_port_same_parent_id(struct net_device *a,
 						 struct net_device *b)
 {
 	return false;
 }
 
+static inline 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),
+			int (*add_cb)(struct net_device *dev,
+				      const struct switchdev_obj *obj,
+				      struct switchdev_trans *trans))
+{
+	return 0;
+}
+
+static inline 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 struct switchdev_obj *obj))
+{
+	return 0;
+}
+
 #define SWITCHDEV_SET_OPS(netdev, ops) do {} while (0)
 
 #endif