Commit 53da0eba authored by Vladimir Oltean's avatar Vladimir Oltean Committed by Jakub Kicinski
Browse files

net: dsa: allow changing the tag protocol via the "tagging" device attribute 



Currently DSA exposes the following sysfs:
$ cat /sys/class/net/eno2/dsa/tagging
ocelot

which is a read-only device attribute, introduced in the kernel as
commit 98cdb480 ("net: dsa: Expose tagging protocol to user-space"),
and used by libpcap since its commit 993db3800d7d ("Add support for DSA
link-layer types").

It would be nice if we could extend this device attribute by making it
writable:
$ echo ocelot-8021q > /sys/class/net/eno2/dsa/tagging

This is useful with DSA switches that can make use of more than one
tagging protocol. It may be useful in dsa_loop in the future too, to
perform offline testing of various taggers, or for changing between dsa
and edsa on Marvell switches, if that is desirable.

In terms of implementation, drivers can support this feature by
implementing .change_tag_protocol, which should always leave the switch
in a consistent state: either with the new protocol if things went well,
or with the old one if something failed. Teardown of the old protocol,
if necessary, must be handled by the driver.

Some things remain as before:
- The .get_tag_protocol is currently only called at probe time, to load
  the initial tagging protocol driver. Nonetheless, new drivers should
  report the tagging protocol in current use now.
- The driver should manage by itself the initial setup of tagging
  protocol, no later than the .setup() method, as well as destroying
  resources used by the last tagger in use, no earlier than the
  .teardown() method.

For multi-switch DSA trees, error handling is a bit more complicated,
since e.g. the 5th out of 7 switches may fail to change the tag
protocol. When that happens, a revert to the original tag protocol is
attempted, but that may fail too, leaving the tree in an inconsistent
state despite each individual switch implementing .change_tag_protocol
transactionally. Since the intersection between drivers that implement
.change_tag_protocol and drivers that support D in DSA is currently the
empty set, the possibility for this error to happen is ignored for now.

Testing:

$ insmod mscc_felix.ko
[   79.549784] mscc_felix 0000:00:00.5: Adding to iommu group 14
[   79.565712] mscc_felix 0000:00:00.5: Failed to register DSA switch: -517
$ insmod tag_ocelot.ko
$ rmmod mscc_felix.ko
$ insmod mscc_felix.ko
[   97.261724] libphy: VSC9959 internal MDIO bus: probed
[   97.267363] mscc_felix 0000:00:00.5: Found PCS at internal MDIO address 0
[   97.274998] mscc_felix 0000:00:00.5: Found PCS at internal MDIO address 1
[   97.282561] mscc_felix 0000:00:00.5: Found PCS at internal MDIO address 2
[   97.289700] mscc_felix 0000:00:00.5: Found PCS at internal MDIO address 3
[   97.599163] mscc_felix 0000:00:00.5 swp0 (uninitialized): PHY [0000:00:00.3:10] driver [Microsemi GE VSC8514 SyncE] (irq=POLL)
[   97.862034] mscc_felix 0000:00:00.5 swp1 (uninitialized): PHY [0000:00:00.3:11] driver [Microsemi GE VSC8514 SyncE] (irq=POLL)
[   97.950731] mscc_felix 0000:00:00.5 swp0: configuring for inband/qsgmii link mode
[   97.964278] 8021q: adding VLAN 0 to HW filter on device swp0
[   98.146161] mscc_felix 0000:00:00.5 swp2 (uninitialized): PHY [0000:00:00.3:12] driver [Microsemi GE VSC8514 SyncE] (irq=POLL)
[   98.238649] mscc_felix 0000:00:00.5 swp1: configuring for inband/qsgmii link mode
[   98.251845] 8021q: adding VLAN 0 to HW filter on device swp1
[   98.433916] mscc_felix 0000:00:00.5 swp3 (uninitialized): PHY [0000:00:00.3:13] driver [Microsemi GE VSC8514 SyncE] (irq=POLL)
[   98.485542] mscc_felix 0000:00:00.5: configuring for fixed/internal link mode
[   98.503584] mscc_felix 0000:00:00.5: Link is Up - 2.5Gbps/Full - flow control rx/tx
[   98.527948] device eno2 entered promiscuous mode
[   98.544755] DSA: tree 0 setup

$ ping 10.0.0.1
PING 10.0.0.1 (10.0.0.1): 56 data bytes
64 bytes from 10.0.0.1: seq=0 ttl=64 time=2.337 ms
64 bytes from 10.0.0.1: seq=1 ttl=64 time=0.754 ms
^C
 -  10.0.0.1 ping statistics  -
2 packets transmitted, 2 packets received, 0% packet loss
round-trip min/avg/max = 0.754/1.545/2.337 ms

$ cat /sys/class/net/eno2/dsa/tagging
ocelot
$ cat ./test_ocelot_8021q.sh
        #!/bin/bash

        ip link set swp0 down
        ip link set swp1 down
        ip link set swp2 down
        ip link set swp3 down
        ip link set swp5 down
        ip link set eno2 down
        echo ocelot-8021q > /sys/class/net/eno2/dsa/tagging
        ip link set eno2 up
        ip link set swp0 up
        ip link set swp1 up
        ip link set swp2 up
        ip link set swp3 up
        ip link set swp5 up
$ ./test_ocelot_8021q.sh
./test_ocelot_8021q.sh: line 9: echo: write error: Protocol not available
$ rmmod tag_ocelot.ko
rmmod: can't unload module 'tag_ocelot': Resource temporarily unavailable
$ insmod tag_ocelot_8021q.ko
$ ./test_ocelot_8021q.sh
$ cat /sys/class/net/eno2/dsa/tagging
ocelot-8021q
$ rmmod tag_ocelot.ko
$ rmmod tag_ocelot_8021q.ko
rmmod: can't unload module 'tag_ocelot_8021q': Resource temporarily unavailable
$ ping 10.0.0.1
PING 10.0.0.1 (10.0.0.1): 56 data bytes
64 bytes from 10.0.0.1: seq=0 ttl=64 time=0.953 ms
64 bytes from 10.0.0.1: seq=1 ttl=64 time=0.787 ms
64 bytes from 10.0.0.1: seq=2 ttl=64 time=0.771 ms
$ rmmod mscc_felix.ko
[  645.544426] mscc_felix 0000:00:00.5: Link is Down
[  645.838608] DSA: tree 0 torn down
$ rmmod tag_ocelot_8021q.ko

Signed-off-by: default avatarVladimir Oltean <vladimir.oltean@nxp.com>
Signed-off-by: default avatarJakub Kicinski <kuba@kernel.org>
parent 357f203b

Documentation/ABI/testing/sysfs-class-net-dsa

+9 −2
Original line number Diff line number Diff line
@@ -3,5 +3,12 @@ Date: August 2018 
KernelVersion:	4.20

Contact:	netdev@vger.kernel.org

Description:

		String indicating the type of tagging protocol used by the

		DSA slave network device.
 
		On read, this file returns a string indicating the type of

		tagging protocol used by the DSA network devices that are

		attached to this master interface.

		On write, this file changes the tagging protocol of the

		attached DSA switches, if this operation is supported by the

		driver. Changing the tagging protocol must be done with the DSA

		interfaces and the master interface all administratively down.

		See the "name" field of each registered struct dsa_device_ops

		for a list of valid values.

include/net/dsa.h

+9 −0
Original line number Diff line number Diff line
@@ -485,9 +485,18 @@ static inline bool dsa_port_is_vlan_filtering(const struct dsa_port *dp) 
typedef int dsa_fdb_dump_cb_t(const unsigned char *addr, u16 vid,

			      bool is_static, void *data);

struct dsa_switch_ops {

	/*

	 * Tagging protocol helpers called for the CPU ports and DSA links.

	 * @get_tag_protocol retrieves the initial tagging protocol and is

	 * mandatory. Switches which can operate using multiple tagging

	 * protocols should implement @change_tag_protocol and report in

	 * @get_tag_protocol the tagger in current use.

	 */

	enum dsa_tag_protocol (*get_tag_protocol)(struct dsa_switch *ds,

						  int port,

						  enum dsa_tag_protocol mprot);

	int	(*change_tag_protocol)(struct dsa_switch *ds, int port,

				       enum dsa_tag_protocol proto);



	int	(*setup)(struct dsa_switch *ds);

	void	(*teardown)(struct dsa_switch *ds);

net/dsa/dsa.c

+26 −0
Original line number Diff line number Diff line
@@ -84,6 +84,32 @@ const char *dsa_tag_protocol_to_str(const struct dsa_device_ops *ops) 
	return ops->name;

};



/* Function takes a reference on the module owning the tagger,

 * so dsa_tag_driver_put must be called afterwards.

 */

const struct dsa_device_ops *dsa_find_tagger_by_name(const char *buf)

{

	const struct dsa_device_ops *ops = ERR_PTR(-ENOPROTOOPT);

	struct dsa_tag_driver *dsa_tag_driver;



	mutex_lock(&dsa_tag_drivers_lock);

	list_for_each_entry(dsa_tag_driver, &dsa_tag_drivers_list, list) {

		const struct dsa_device_ops *tmp = dsa_tag_driver->ops;



		if (!sysfs_streq(buf, tmp->name))

			continue;



		if (!try_module_get(dsa_tag_driver->owner))

			break;



		ops = tmp;

		break;

	}

	mutex_unlock(&dsa_tag_drivers_lock);



	return ops;

}



const struct dsa_device_ops *dsa_tag_driver_get(int tag_protocol)

{

	struct dsa_tag_driver *dsa_tag_driver;

net/dsa/dsa2.c

+52 −3
Original line number Diff line number Diff line
@@ -942,6 +942,57 @@ static void dsa_tree_teardown(struct dsa_switch_tree *dst) 
	dst->setup = false;

}



/* Since the dsa/tagging sysfs device attribute is per master, the assumption

 * is that all DSA switches within a tree share the same tagger, otherwise

 * they would have formed disjoint trees (different "dsa,member" values).

 */

int dsa_tree_change_tag_proto(struct dsa_switch_tree *dst,

			      struct net_device *master,

			      const struct dsa_device_ops *tag_ops,

			      const struct dsa_device_ops *old_tag_ops)

{

	struct dsa_notifier_tag_proto_info info;

	struct dsa_port *dp;

	int err = -EBUSY;



	if (!rtnl_trylock())

		return restart_syscall();



	/* At the moment we don't allow changing the tag protocol under

	 * traffic. The rtnl_mutex also happens to serialize concurrent

	 * attempts to change the tagging protocol. If we ever lift the IFF_UP

	 * restriction, there needs to be another mutex which serializes this.

	 */

	if (master->flags & IFF_UP)

		goto out_unlock;



	list_for_each_entry(dp, &dst->ports, list) {

		if (!dsa_is_user_port(dp->ds, dp->index))

			continue;



		if (dp->slave->flags & IFF_UP)

			goto out_unlock;

	}



	info.tag_ops = tag_ops;

	err = dsa_tree_notify(dst, DSA_NOTIFIER_TAG_PROTO, &info);

	if (err)

		goto out_unwind_tagger;



	dst->tag_ops = tag_ops;



	rtnl_unlock();



	return 0;



out_unwind_tagger:

	info.tag_ops = old_tag_ops;

	dsa_tree_notify(dst, DSA_NOTIFIER_TAG_PROTO, &info);

out_unlock:

	rtnl_unlock();

	return err;

}



static struct dsa_port *dsa_port_touch(struct dsa_switch *ds, int index)

{

	struct dsa_switch_tree *dst = ds->dst;
@@ -1038,9 +1089,7 @@ static int dsa_port_parse_cpu(struct dsa_port *dp, struct net_device *master) 


	dp->master = master;

	dp->type = DSA_PORT_TYPE_CPU;

	dp->filter = dst->tag_ops->filter;

	dp->rcv = dst->tag_ops->rcv;

	dp->tag_ops = dst->tag_ops;

	dsa_port_set_tag_protocol(dp, dst->tag_ops);

	dp->dst = dst;



	return 0;

net/dsa/dsa_priv.h

+15 −0
Original line number Diff line number Diff line
@@ -28,6 +28,7 @@ enum { 
	DSA_NOTIFIER_VLAN_ADD,

	DSA_NOTIFIER_VLAN_DEL,

	DSA_NOTIFIER_MTU,

	DSA_NOTIFIER_TAG_PROTO,

};



/* DSA_NOTIFIER_AGEING_TIME */
@@ -82,6 +83,11 @@ struct dsa_notifier_mtu_info { 
	int mtu;

};



/* DSA_NOTIFIER_TAG_PROTO_* */

struct dsa_notifier_tag_proto_info {

	const struct dsa_device_ops *tag_ops;

};



struct dsa_switchdev_event_work {

	struct dsa_switch *ds;

	int port;
@@ -115,6 +121,7 @@ struct dsa_slave_priv { 
/* dsa.c */

const struct dsa_device_ops *dsa_tag_driver_get(int tag_protocol);

void dsa_tag_driver_put(const struct dsa_device_ops *ops);

const struct dsa_device_ops *dsa_find_tagger_by_name(const char *buf);



bool dsa_schedule_work(struct work_struct *work);

const char *dsa_tag_protocol_to_str(const struct dsa_device_ops *ops);
@@ -139,6 +146,8 @@ static inline struct net_device *dsa_master_find_slave(struct net_device *dev, 
}



/* port.c */

void dsa_port_set_tag_protocol(struct dsa_port *cpu_dp,

			       const struct dsa_device_ops *tag_ops);

int dsa_port_set_state(struct dsa_port *dp, u8 state);

int dsa_port_enable_rt(struct dsa_port *dp, struct phy_device *phy);

int dsa_port_enable(struct dsa_port *dp, struct phy_device *phy);
@@ -201,6 +210,8 @@ int dsa_slave_suspend(struct net_device *slave_dev); 
int dsa_slave_resume(struct net_device *slave_dev);

int dsa_slave_register_notifier(void);

void dsa_slave_unregister_notifier(void);

void dsa_slave_setup_tagger(struct net_device *slave);

int dsa_slave_change_mtu(struct net_device *dev, int new_mtu);



static inline struct dsa_port *dsa_slave_to_port(const struct net_device *dev)

{
@@ -285,6 +296,10 @@ void dsa_lag_map(struct dsa_switch_tree *dst, struct net_device *lag); 
void dsa_lag_unmap(struct dsa_switch_tree *dst, struct net_device *lag);

int dsa_tree_notify(struct dsa_switch_tree *dst, unsigned long e, void *v);

int dsa_broadcast(unsigned long e, void *v);

int dsa_tree_change_tag_proto(struct dsa_switch_tree *dst,

			      struct net_device *master,

			      const struct dsa_device_ops *tag_ops,

			      const struct dsa_device_ops *old_tag_ops);



extern struct list_head dsa_tree_list;