2019-05-27 14:55:01 +08:00
|
|
|
// SPDX-License-Identifier: GPL-2.0-or-later
|
2017-02-04 02:20:20 +08:00
|
|
|
/*
|
|
|
|
|
* Handling of a single switch chip, part of a switch fabric
|
|
|
|
|
*
|
2017-03-29 03:10:36 +08:00
|
|
|
* Copyright (c) 2017 Savoir-faire Linux Inc.
|
|
|
|
|
* Vivien Didelot <vivien.didelot@savoirfairelinux.com>
|
2017-02-04 02:20:20 +08:00
|
|
|
*/
|
|
|
|
|
|
net: dsa: Unset vlan_filtering when ports leave the bridge
When ports are standalone (after they left the bridge), they should have
no VLAN filtering semantics (they should pass all traffic to the CPU).
Currently this is not true for switchdev drivers, because the bridge
"forgets" to unset that.
Normally one would think that doing this at the bridge layer would be a
better idea, i.e. call br_vlan_filter_toggle() from br_del_if(), similar
to how nbp_vlan_init() is called from br_add_if().
However what complicates that approach, and makes this one preferable,
is the fact that for the bridge core, vlan_filtering is a per-bridge
setting, whereas for switchdev/DSA it is per-port. Also there are
switches where the setting is per the entire device, and unsetting
vlan_filtering one by one, for each leaving port, would not be possible
from the bridge core without a certain level of awareness. So do this in
DSA and let drivers be unaware of it.
Signed-off-by: Vladimir Oltean <olteanv@gmail.com>
Reviewed-by: Andrew Lunn <andrew@lunn.ch>
Reviewed-by: Florian Fainelli <f.fainelli@gmail.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
2019-04-29 02:45:46 +08:00
|
|
|
#include <linux/if_bridge.h>
|
2017-02-04 02:20:20 +08:00
|
|
|
#include <linux/netdevice.h>
|
|
|
|
|
#include <linux/notifier.h>
|
2019-02-21 06:35:39 +08:00
|
|
|
#include <linux/if_vlan.h>
|
2017-05-20 05:00:52 +08:00
|
|
|
#include <net/switchdev.h>
|
2017-05-18 03:46:03 +08:00
|
|
|
|
|
|
|
|
#include "dsa_priv.h"
|
2017-02-04 02:20:20 +08:00
|
|
|
|
2017-05-20 05:00:52 +08:00
|
|
|
static unsigned int dsa_switch_fastest_ageing_time(struct dsa_switch *ds,
|
|
|
|
|
unsigned int ageing_time)
|
|
|
|
|
{
|
|
|
|
|
int i;
|
|
|
|
|
|
|
|
|
|
for (i = 0; i < ds->num_ports; ++i) {
|
2019-10-22 04:51:15 +08:00
|
|
|
struct dsa_port *dp = dsa_to_port(ds, i);
|
2017-05-20 05:00:52 +08:00
|
|
|
|
|
|
|
|
if (dp->ageing_time && dp->ageing_time < ageing_time)
|
|
|
|
|
ageing_time = dp->ageing_time;
|
|
|
|
|
}
|
|
|
|
|
|
|
|
|
|
return ageing_time;
|
|
|
|
|
}
|
|
|
|
|
|
|
|
|
|
static int dsa_switch_ageing_time(struct dsa_switch *ds,
|
|
|
|
|
struct dsa_notifier_ageing_time_info *info)
|
|
|
|
|
{
|
|
|
|
|
unsigned int ageing_time = info->ageing_time;
|
2021-01-09 08:01:51 +08:00
|
|
|
|
|
|
|
|
if (ds->ageing_time_min && ageing_time < ds->ageing_time_min)
|
|
|
|
|
return -ERANGE;
|
|
|
|
|
|
|
|
|
|
if (ds->ageing_time_max && ageing_time > ds->ageing_time_max)
|
|
|
|
|
return -ERANGE;
|
2017-05-20 05:00:52 +08:00
|
|
|
|
|
|
|
|
/* Program the fastest ageing time in case of multiple bridges */
|
|
|
|
|
ageing_time = dsa_switch_fastest_ageing_time(ds, ageing_time);
|
|
|
|
|
|
|
|
|
|
if (ds->ops->set_ageing_time)
|
|
|
|
|
return ds->ops->set_ageing_time(ds, ageing_time);
|
|
|
|
|
|
|
|
|
|
return 0;
|
|
|
|
|
}
|
|
|
|
|
|
net: dsa: configure the MTU for switch ports
It is useful be able to configure port policers on a switch to accept
frames of various sizes:
- Increase the MTU for better throughput from the default of 1500 if it
is known that there is no 10/100 Mbps device in the network.
- Decrease the MTU to limit the latency of high-priority frames under
congestion, or work around various network segments that add extra
headers to packets which can't be fragmented.
For DSA slave ports, this is mostly a pass-through callback, called
through the regular ndo ops and at probe time (to ensure consistency
across all supported switches).
The CPU port is called with an MTU equal to the largest configured MTU
of the slave ports. The assumption is that the user might want to
sustain a bidirectional conversation with a partner over any switch
port.
The DSA master is configured the same as the CPU port, plus the tagger
overhead. Since the MTU is by definition L2 payload (sans Ethernet
header), it is up to each individual driver to figure out if it needs to
do anything special for its frame tags on the CPU port (it shouldn't
except in special cases). So the MTU does not contain the tagger
overhead on the CPU port.
However the MTU of the DSA master, minus the tagger overhead, is used as
a proxy for the MTU of the CPU port, which does not have a net device.
This is to avoid uselessly calling the .change_mtu function on the CPU
port when nothing should change.
So it is safe to assume that the DSA master and the CPU port MTUs are
apart by exactly the tagger's overhead in bytes.
Some changes were made around dsa_master_set_mtu(), function which was
now removed, for 2 reasons:
- dev_set_mtu() already calls dev_validate_mtu(), so it's redundant to
do the same thing in DSA
- __dev_set_mtu() returns 0 if ops->ndo_change_mtu is an absent method
That is to say, there's no need for this function in DSA, we can safely
call dev_set_mtu() directly, take the rtnl lock when necessary, and just
propagate whatever errors get reported (since the user probably wants to
be informed).
Some inspiration (mainly in the MTU DSA notifier) was taken from a
vaguely similar patch from Murali and Florian, who are credited as
co-developers down below.
Co-developed-by: Murali Krishna Policharla <murali.policharla@broadcom.com>
Signed-off-by: Murali Krishna Policharla <murali.policharla@broadcom.com>
Co-developed-by: Florian Fainelli <f.fainelli@gmail.com>
Signed-off-by: Florian Fainelli <f.fainelli@gmail.com>
Signed-off-by: Vladimir Oltean <vladimir.oltean@nxp.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
2020-03-28 03:55:42 +08:00
|
|
|
static bool dsa_switch_mtu_match(struct dsa_switch *ds, int port,
|
|
|
|
|
struct dsa_notifier_mtu_info *info)
|
|
|
|
|
{
|
net: dsa: targeted MTU notifiers should only match on one port
dsa_slave_change_mtu() calls dsa_port_mtu_change() twice:
- it sends a cross-chip notifier with the MTU of the CPU port which is
used to update the DSA links.
- it sends one targeted MTU notifier which is supposed to only match the
user port on which we are changing the MTU. The "propagate_upstream"
variable is used here to bypass the cross-chip notifier system from
switch.c
But due to a mistake, the second, targeted notifier matches not only on
the user port, but also on the DSA link which is a member of the same
switch, if that exists.
And because the DSA links of the entire dst were programmed in a
previous round to the largest_mtu via a "propagate_upstream == true"
notification, then the dsa_port_mtu_change(propagate_upstream == false)
call that is immediately upcoming will break the MTU on the one DSA link
which is chip-wise local to the dp whose MTU is changing right now.
Example given this daisy chain topology:
sw0p0 sw0p1 sw0p2 sw0p3 sw0p4
[ cpu ] [ user ] [ user ] [ dsa ] [ user ]
[ x ] [ ] [ ] [ x ] [ ]
|
+---------+
|
sw1p0 sw1p1 sw1p2 sw1p3 sw1p4
[ user ] [ user ] [ user ] [ dsa ] [ dsa ]
[ ] [ ] [ ] [ ] [ x ]
ip link set sw0p1 mtu 9000
ip link set sw1p1 mtu 9000 # at this stage, sw0p1 and sw1p1 can talk
# to one another using jumbo frames
ip link set sw0p2 mtu 1500 # this programs the sw0p3 DSA link first to
# the largest_mtu of 9000, then reprograms it to
# 1500 with the "propagate_upstream == false"
# notifier, breaking communication between
# sw0p1 and sw1p1
To escape from this situation, make the targeted match really match on a
single port - the user port, and rename the "propagate_upstream"
variable to "targeted_match" to clarify the intention and avoid future
issues.
Signed-off-by: Vladimir Oltean <vladimir.oltean@nxp.com>
Reviewed-by: Florian Fainelli <f.fainelli@gmail.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
2021-06-22 00:42:18 +08:00
|
|
|
if (ds->index == info->sw_index && port == info->port)
|
|
|
|
|
return true;
|
net: dsa: configure the MTU for switch ports
It is useful be able to configure port policers on a switch to accept
frames of various sizes:
- Increase the MTU for better throughput from the default of 1500 if it
is known that there is no 10/100 Mbps device in the network.
- Decrease the MTU to limit the latency of high-priority frames under
congestion, or work around various network segments that add extra
headers to packets which can't be fragmented.
For DSA slave ports, this is mostly a pass-through callback, called
through the regular ndo ops and at probe time (to ensure consistency
across all supported switches).
The CPU port is called with an MTU equal to the largest configured MTU
of the slave ports. The assumption is that the user might want to
sustain a bidirectional conversation with a partner over any switch
port.
The DSA master is configured the same as the CPU port, plus the tagger
overhead. Since the MTU is by definition L2 payload (sans Ethernet
header), it is up to each individual driver to figure out if it needs to
do anything special for its frame tags on the CPU port (it shouldn't
except in special cases). So the MTU does not contain the tagger
overhead on the CPU port.
However the MTU of the DSA master, minus the tagger overhead, is used as
a proxy for the MTU of the CPU port, which does not have a net device.
This is to avoid uselessly calling the .change_mtu function on the CPU
port when nothing should change.
So it is safe to assume that the DSA master and the CPU port MTUs are
apart by exactly the tagger's overhead in bytes.
Some changes were made around dsa_master_set_mtu(), function which was
now removed, for 2 reasons:
- dev_set_mtu() already calls dev_validate_mtu(), so it's redundant to
do the same thing in DSA
- __dev_set_mtu() returns 0 if ops->ndo_change_mtu is an absent method
That is to say, there's no need for this function in DSA, we can safely
call dev_set_mtu() directly, take the rtnl lock when necessary, and just
propagate whatever errors get reported (since the user probably wants to
be informed).
Some inspiration (mainly in the MTU DSA notifier) was taken from a
vaguely similar patch from Murali and Florian, who are credited as
co-developers down below.
Co-developed-by: Murali Krishna Policharla <murali.policharla@broadcom.com>
Signed-off-by: Murali Krishna Policharla <murali.policharla@broadcom.com>
Co-developed-by: Florian Fainelli <f.fainelli@gmail.com>
Signed-off-by: Florian Fainelli <f.fainelli@gmail.com>
Signed-off-by: Vladimir Oltean <vladimir.oltean@nxp.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
2020-03-28 03:55:42 +08:00
|
|
|
|
net: dsa: targeted MTU notifiers should only match on one port
dsa_slave_change_mtu() calls dsa_port_mtu_change() twice:
- it sends a cross-chip notifier with the MTU of the CPU port which is
used to update the DSA links.
- it sends one targeted MTU notifier which is supposed to only match the
user port on which we are changing the MTU. The "propagate_upstream"
variable is used here to bypass the cross-chip notifier system from
switch.c
But due to a mistake, the second, targeted notifier matches not only on
the user port, but also on the DSA link which is a member of the same
switch, if that exists.
And because the DSA links of the entire dst were programmed in a
previous round to the largest_mtu via a "propagate_upstream == true"
notification, then the dsa_port_mtu_change(propagate_upstream == false)
call that is immediately upcoming will break the MTU on the one DSA link
which is chip-wise local to the dp whose MTU is changing right now.
Example given this daisy chain topology:
sw0p0 sw0p1 sw0p2 sw0p3 sw0p4
[ cpu ] [ user ] [ user ] [ dsa ] [ user ]
[ x ] [ ] [ ] [ x ] [ ]
|
+---------+
|
sw1p0 sw1p1 sw1p2 sw1p3 sw1p4
[ user ] [ user ] [ user ] [ dsa ] [ dsa ]
[ ] [ ] [ ] [ ] [ x ]
ip link set sw0p1 mtu 9000
ip link set sw1p1 mtu 9000 # at this stage, sw0p1 and sw1p1 can talk
# to one another using jumbo frames
ip link set sw0p2 mtu 1500 # this programs the sw0p3 DSA link first to
# the largest_mtu of 9000, then reprograms it to
# 1500 with the "propagate_upstream == false"
# notifier, breaking communication between
# sw0p1 and sw1p1
To escape from this situation, make the targeted match really match on a
single port - the user port, and rename the "propagate_upstream"
variable to "targeted_match" to clarify the intention and avoid future
issues.
Signed-off-by: Vladimir Oltean <vladimir.oltean@nxp.com>
Reviewed-by: Florian Fainelli <f.fainelli@gmail.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
2021-06-22 00:42:18 +08:00
|
|
|
/* Do not propagate to other switches in the tree if the notifier was
|
|
|
|
|
* targeted for a single switch.
|
|
|
|
|
*/
|
|
|
|
|
if (info->targeted_match)
|
net: dsa: configure the MTU for switch ports
It is useful be able to configure port policers on a switch to accept
frames of various sizes:
- Increase the MTU for better throughput from the default of 1500 if it
is known that there is no 10/100 Mbps device in the network.
- Decrease the MTU to limit the latency of high-priority frames under
congestion, or work around various network segments that add extra
headers to packets which can't be fragmented.
For DSA slave ports, this is mostly a pass-through callback, called
through the regular ndo ops and at probe time (to ensure consistency
across all supported switches).
The CPU port is called with an MTU equal to the largest configured MTU
of the slave ports. The assumption is that the user might want to
sustain a bidirectional conversation with a partner over any switch
port.
The DSA master is configured the same as the CPU port, plus the tagger
overhead. Since the MTU is by definition L2 payload (sans Ethernet
header), it is up to each individual driver to figure out if it needs to
do anything special for its frame tags on the CPU port (it shouldn't
except in special cases). So the MTU does not contain the tagger
overhead on the CPU port.
However the MTU of the DSA master, minus the tagger overhead, is used as
a proxy for the MTU of the CPU port, which does not have a net device.
This is to avoid uselessly calling the .change_mtu function on the CPU
port when nothing should change.
So it is safe to assume that the DSA master and the CPU port MTUs are
apart by exactly the tagger's overhead in bytes.
Some changes were made around dsa_master_set_mtu(), function which was
now removed, for 2 reasons:
- dev_set_mtu() already calls dev_validate_mtu(), so it's redundant to
do the same thing in DSA
- __dev_set_mtu() returns 0 if ops->ndo_change_mtu is an absent method
That is to say, there's no need for this function in DSA, we can safely
call dev_set_mtu() directly, take the rtnl lock when necessary, and just
propagate whatever errors get reported (since the user probably wants to
be informed).
Some inspiration (mainly in the MTU DSA notifier) was taken from a
vaguely similar patch from Murali and Florian, who are credited as
co-developers down below.
Co-developed-by: Murali Krishna Policharla <murali.policharla@broadcom.com>
Signed-off-by: Murali Krishna Policharla <murali.policharla@broadcom.com>
Co-developed-by: Florian Fainelli <f.fainelli@gmail.com>
Signed-off-by: Florian Fainelli <f.fainelli@gmail.com>
Signed-off-by: Vladimir Oltean <vladimir.oltean@nxp.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
2020-03-28 03:55:42 +08:00
|
|
|
return false;
|
|
|
|
|
|
|
|
|
|
if (dsa_is_dsa_port(ds, port) || dsa_is_cpu_port(ds, port))
|
|
|
|
|
return true;
|
|
|
|
|
|
|
|
|
|
return false;
|
|
|
|
|
}
|
|
|
|
|
|
|
|
|
|
static int dsa_switch_mtu(struct dsa_switch *ds,
|
|
|
|
|
struct dsa_notifier_mtu_info *info)
|
|
|
|
|
{
|
|
|
|
|
int port, ret;
|
|
|
|
|
|
|
|
|
|
if (!ds->ops->port_change_mtu)
|
|
|
|
|
return -EOPNOTSUPP;
|
|
|
|
|
|
|
|
|
|
for (port = 0; port < ds->num_ports; port++) {
|
|
|
|
|
if (dsa_switch_mtu_match(ds, port, info)) {
|
|
|
|
|
ret = ds->ops->port_change_mtu(ds, port, info->mtu);
|
|
|
|
|
if (ret)
|
|
|
|
|
return ret;
|
|
|
|
|
}
|
|
|
|
|
}
|
|
|
|
|
|
|
|
|
|
return 0;
|
|
|
|
|
}
|
|
|
|
|
|
2017-02-04 02:20:21 +08:00
|
|
|
static int dsa_switch_bridge_join(struct dsa_switch *ds,
|
|
|
|
|
struct dsa_notifier_bridge_info *info)
|
|
|
|
|
{
|
net: dsa: permit cross-chip bridging between all trees in the system
One way of utilizing DSA is by cascading switches which do not all have
compatible taggers. Consider the following real-life topology:
+---------------------------------------------------------------+
| LS1028A |
| +------------------------------+ |
| | DSA master for Felix | |
| |(internal ENETC port 2: eno2))| |
| +------------+------------------------------+-------------+ |
| | Felix embedded L2 switch | |
| | | |
| | +--------------+ +--------------+ +--------------+ | |
| | |DSA master for| |DSA master for| |DSA master for| | |
| | | SJA1105 1 | | SJA1105 2 | | SJA1105 3 | | |
| | |(Felix port 1)| |(Felix port 2)| |(Felix port 3)| | |
+--+-+--------------+---+--------------+---+--------------+--+--+
+-----------------------+ +-----------------------+ +-----------------------+
| SJA1105 switch 1 | | SJA1105 switch 2 | | SJA1105 switch 3 |
+-----+-----+-----+-----+ +-----+-----+-----+-----+ +-----+-----+-----+-----+
|sw1p0|sw1p1|sw1p2|sw1p3| |sw2p0|sw2p1|sw2p2|sw2p3| |sw3p0|sw3p1|sw3p2|sw3p3|
+-----+-----+-----+-----+ +-----+-----+-----+-----+ +-----+-----+-----+-----+
The above can be described in the device tree as follows (obviously not
complete):
mscc_felix {
dsa,member = <0 0>;
ports {
port@4 {
ethernet = <&enetc_port2>;
};
};
};
sja1105_switch1 {
dsa,member = <1 1>;
ports {
port@4 {
ethernet = <&mscc_felix_port1>;
};
};
};
sja1105_switch2 {
dsa,member = <2 2>;
ports {
port@4 {
ethernet = <&mscc_felix_port2>;
};
};
};
sja1105_switch3 {
dsa,member = <3 3>;
ports {
port@4 {
ethernet = <&mscc_felix_port3>;
};
};
};
Basically we instantiate one DSA switch tree for every hardware switch
in the system, but we still give them globally unique switch IDs (will
come back to that later). Having 3 disjoint switch trees makes the
tagger drivers "just work", because net devices are registered for the
3 Felix DSA master ports, and they are also DSA slave ports to the ENETC
port. So packets received on the ENETC port are stripped of their
stacked DSA tags one by one.
Currently, hardware bridging between ports on the same sja1105 chip is
possible, but switching between sja1105 ports on different chips is
handled by the software bridge. This is fine, but we can do better.
In fact, the dsa_8021q tag used by sja1105 is compatible with cascading.
In other words, a sja1105 switch can correctly parse and route a packet
containing a dsa_8021q tag. So if we could enable hardware bridging on
the Felix DSA master ports, cross-chip bridging could be completely
offloaded.
Such as system would be used as follows:
ip link add dev br0 type bridge && ip link set dev br0 up
for port in sw0p0 sw0p1 sw0p2 sw0p3 \
sw1p0 sw1p1 sw1p2 sw1p3 \
sw2p0 sw2p1 sw2p2 sw2p3; do
ip link set dev $port master br0
done
The above makes switching between ports on the same row be performed in
hardware, and between ports on different rows in software. Now assume
the Felix switch ports are called swp0, swp1, swp2. By running the
following extra commands:
ip link add dev br1 type bridge && ip link set dev br1 up
for port in swp0 swp1 swp2; do
ip link set dev $port master br1
done
the CPU no longer sees packets which traverse sja1105 switch boundaries
and can be forwarded directly by Felix. The br1 bridge would not be used
for any sort of traffic termination.
For this to work, we need to give drivers an opportunity to listen for
bridging events on DSA trees other than their own, and pass that other
tree index as argument. I have made the assumption, for the moment, that
the other existing DSA notifiers don't need to be broadcast to other
trees. That assumption might turn out to be incorrect. But in the
meantime, introduce a dsa_broadcast function, similar in purpose to
dsa_port_notify, which is used only by the bridging notifiers.
Signed-off-by: Vladimir Oltean <vladimir.oltean@nxp.com>
Reviewed-by: Florian Fainelli <f.fainelli@gmail.com>
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
2020-05-11 00:37:41 +08:00
|
|
|
struct dsa_switch_tree *dst = ds->dst;
|
net: dsa: tag_8021q: manage RX VLANs dynamically at bridge join/leave time
There has been at least one wasted opportunity for tag_8021q to be used
by a driver:
https://patchwork.ozlabs.org/project/netdev/patch/20200710113611.3398-3-kurt@linutronix.de/#2484272
because of a design decision: the declared purpose of tag_8021q is to
offer source port/switch identification for a tagging driver for packets
coming from a switch with no hardware DSA tagging support. It is not
intended to provide VLAN-based port isolation, because its first user,
sja1105, had another mechanism for bridging domain isolation, the L2
Forwarding Table. So even if 2 ports are in the same VLAN but they are
separated via the L2 Forwarding Table, they will not communicate with
one another. The L2 Forwarding Table is managed by the
sja1105_bridge_join() and sja1105_bridge_leave() methods.
As a consequence, today tag_8021q does not bother too much with hooking
into .port_bridge_join() and .port_bridge_leave() because that would
introduce yet another degree of freedom, it just iterates statically
through all ports of a switch and adds the RX VLAN of one port to all
the others. In this way, whenever .port_bridge_join() is called,
bridging will magically work because the RX VLANs are already installed
everywhere they need to be.
This is not to say that the reason for the change in this patch is to
satisfy the hellcreek and similar use cases, that is merely a nice side
effect. Instead it is to make sja1105 cross-chip links work properly
over a DSA link.
For context, sja1105 today supports a degenerate form of cross-chip
bridging, where the switches are interconnected through their CPU ports
("disjoint trees" topology). There is some code which has been
generalized into dsa_8021q_crosschip_link_{add,del}, but it is not
enough, and frankly it is impossible to build upon that.
Real multi-switch DSA trees, like daisy chains or H trees, which have
actual DSA links, do not work.
The problem is that sja1105 is unlike mv88e6xxx, and does not have a PVT
for cross-chip bridging, which is a table by which the local switch can
select the forwarding domain for packets from a certain ingress switch
ID and source port. The sja1105 switches cannot parse their own DSA
tags, because, well, they don't really have support for DSA tags, it's
all VLANs.
So to make something like cross-chip bridging between sw0p0 and sw1p0 to
work over the sw0p3/sw1p3 DSA link to work with sja1105 in the topology
below:
| |
sw0p0 sw0p1 sw0p2 sw0p3 sw1p3 sw1p2 sw1p1 sw1p0
[ user ] [ user ] [ cpu ] [ dsa ] ---- [ dsa ] [ cpu ] [ user ] [ user ]
we need to ask ourselves 2 questions:
(1) how should the L2 Forwarding Table be managed?
(2) how should the VLAN Lookup Table be managed?
i.e. what should prevent packets from going to unwanted ports?
Since as mentioned, there is no PVT, the L2 Forwarding Table only
contains forwarding rules for local ports. So we can say "all user ports
are allowed to forward to all CPU ports and all DSA links".
If we allow forwarding to DSA links unconditionally, this means we must
prevent forwarding using the VLAN Lookup Table. This is in fact
asymmetric with what we do for tag_8021q on ports local to the same
switch, and it matters because now that we are making tag_8021q a core
DSA feature, we need to hook into .crosschip_bridge_join() to add/remove
the tag_8021q VLANs. So for symmetry it makes sense to manage the VLANs
for local forwarding in the same way as cross-chip forwarding.
Note that there is a very precise reason why tag_8021q hooks into
dsa_switch_bridge_join() which acts at the cross-chip notifier level,
and not at a higher level such as dsa_port_bridge_join(). We need to
install the RX VLAN of the newly joining port into the VLAN table of all
the existing ports across the tree that are part of the same bridge, and
the notifier already does the iteration through the switches for us.
Signed-off-by: Vladimir Oltean <vladimir.oltean@nxp.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
2021-07-20 01:14:51 +08:00
|
|
|
int err;
|
net: dsa: permit cross-chip bridging between all trees in the system
One way of utilizing DSA is by cascading switches which do not all have
compatible taggers. Consider the following real-life topology:
+---------------------------------------------------------------+
| LS1028A |
| +------------------------------+ |
| | DSA master for Felix | |
| |(internal ENETC port 2: eno2))| |
| +------------+------------------------------+-------------+ |
| | Felix embedded L2 switch | |
| | | |
| | +--------------+ +--------------+ +--------------+ | |
| | |DSA master for| |DSA master for| |DSA master for| | |
| | | SJA1105 1 | | SJA1105 2 | | SJA1105 3 | | |
| | |(Felix port 1)| |(Felix port 2)| |(Felix port 3)| | |
+--+-+--------------+---+--------------+---+--------------+--+--+
+-----------------------+ +-----------------------+ +-----------------------+
| SJA1105 switch 1 | | SJA1105 switch 2 | | SJA1105 switch 3 |
+-----+-----+-----+-----+ +-----+-----+-----+-----+ +-----+-----+-----+-----+
|sw1p0|sw1p1|sw1p2|sw1p3| |sw2p0|sw2p1|sw2p2|sw2p3| |sw3p0|sw3p1|sw3p2|sw3p3|
+-----+-----+-----+-----+ +-----+-----+-----+-----+ +-----+-----+-----+-----+
The above can be described in the device tree as follows (obviously not
complete):
mscc_felix {
dsa,member = <0 0>;
ports {
port@4 {
ethernet = <&enetc_port2>;
};
};
};
sja1105_switch1 {
dsa,member = <1 1>;
ports {
port@4 {
ethernet = <&mscc_felix_port1>;
};
};
};
sja1105_switch2 {
dsa,member = <2 2>;
ports {
port@4 {
ethernet = <&mscc_felix_port2>;
};
};
};
sja1105_switch3 {
dsa,member = <3 3>;
ports {
port@4 {
ethernet = <&mscc_felix_port3>;
};
};
};
Basically we instantiate one DSA switch tree for every hardware switch
in the system, but we still give them globally unique switch IDs (will
come back to that later). Having 3 disjoint switch trees makes the
tagger drivers "just work", because net devices are registered for the
3 Felix DSA master ports, and they are also DSA slave ports to the ENETC
port. So packets received on the ENETC port are stripped of their
stacked DSA tags one by one.
Currently, hardware bridging between ports on the same sja1105 chip is
possible, but switching between sja1105 ports on different chips is
handled by the software bridge. This is fine, but we can do better.
In fact, the dsa_8021q tag used by sja1105 is compatible with cascading.
In other words, a sja1105 switch can correctly parse and route a packet
containing a dsa_8021q tag. So if we could enable hardware bridging on
the Felix DSA master ports, cross-chip bridging could be completely
offloaded.
Such as system would be used as follows:
ip link add dev br0 type bridge && ip link set dev br0 up
for port in sw0p0 sw0p1 sw0p2 sw0p3 \
sw1p0 sw1p1 sw1p2 sw1p3 \
sw2p0 sw2p1 sw2p2 sw2p3; do
ip link set dev $port master br0
done
The above makes switching between ports on the same row be performed in
hardware, and between ports on different rows in software. Now assume
the Felix switch ports are called swp0, swp1, swp2. By running the
following extra commands:
ip link add dev br1 type bridge && ip link set dev br1 up
for port in swp0 swp1 swp2; do
ip link set dev $port master br1
done
the CPU no longer sees packets which traverse sja1105 switch boundaries
and can be forwarded directly by Felix. The br1 bridge would not be used
for any sort of traffic termination.
For this to work, we need to give drivers an opportunity to listen for
bridging events on DSA trees other than their own, and pass that other
tree index as argument. I have made the assumption, for the moment, that
the other existing DSA notifiers don't need to be broadcast to other
trees. That assumption might turn out to be incorrect. But in the
meantime, introduce a dsa_broadcast function, similar in purpose to
dsa_port_notify, which is used only by the bridging notifiers.
Signed-off-by: Vladimir Oltean <vladimir.oltean@nxp.com>
Reviewed-by: Florian Fainelli <f.fainelli@gmail.com>
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
2020-05-11 00:37:41 +08:00
|
|
|
|
|
|
|
|
if (dst->index == info->tree_index && ds->index == info->sw_index &&
|
net: dsa: tag_8021q: manage RX VLANs dynamically at bridge join/leave time
There has been at least one wasted opportunity for tag_8021q to be used
by a driver:
https://patchwork.ozlabs.org/project/netdev/patch/20200710113611.3398-3-kurt@linutronix.de/#2484272
because of a design decision: the declared purpose of tag_8021q is to
offer source port/switch identification for a tagging driver for packets
coming from a switch with no hardware DSA tagging support. It is not
intended to provide VLAN-based port isolation, because its first user,
sja1105, had another mechanism for bridging domain isolation, the L2
Forwarding Table. So even if 2 ports are in the same VLAN but they are
separated via the L2 Forwarding Table, they will not communicate with
one another. The L2 Forwarding Table is managed by the
sja1105_bridge_join() and sja1105_bridge_leave() methods.
As a consequence, today tag_8021q does not bother too much with hooking
into .port_bridge_join() and .port_bridge_leave() because that would
introduce yet another degree of freedom, it just iterates statically
through all ports of a switch and adds the RX VLAN of one port to all
the others. In this way, whenever .port_bridge_join() is called,
bridging will magically work because the RX VLANs are already installed
everywhere they need to be.
This is not to say that the reason for the change in this patch is to
satisfy the hellcreek and similar use cases, that is merely a nice side
effect. Instead it is to make sja1105 cross-chip links work properly
over a DSA link.
For context, sja1105 today supports a degenerate form of cross-chip
bridging, where the switches are interconnected through their CPU ports
("disjoint trees" topology). There is some code which has been
generalized into dsa_8021q_crosschip_link_{add,del}, but it is not
enough, and frankly it is impossible to build upon that.
Real multi-switch DSA trees, like daisy chains or H trees, which have
actual DSA links, do not work.
The problem is that sja1105 is unlike mv88e6xxx, and does not have a PVT
for cross-chip bridging, which is a table by which the local switch can
select the forwarding domain for packets from a certain ingress switch
ID and source port. The sja1105 switches cannot parse their own DSA
tags, because, well, they don't really have support for DSA tags, it's
all VLANs.
So to make something like cross-chip bridging between sw0p0 and sw1p0 to
work over the sw0p3/sw1p3 DSA link to work with sja1105 in the topology
below:
| |
sw0p0 sw0p1 sw0p2 sw0p3 sw1p3 sw1p2 sw1p1 sw1p0
[ user ] [ user ] [ cpu ] [ dsa ] ---- [ dsa ] [ cpu ] [ user ] [ user ]
we need to ask ourselves 2 questions:
(1) how should the L2 Forwarding Table be managed?
(2) how should the VLAN Lookup Table be managed?
i.e. what should prevent packets from going to unwanted ports?
Since as mentioned, there is no PVT, the L2 Forwarding Table only
contains forwarding rules for local ports. So we can say "all user ports
are allowed to forward to all CPU ports and all DSA links".
If we allow forwarding to DSA links unconditionally, this means we must
prevent forwarding using the VLAN Lookup Table. This is in fact
asymmetric with what we do for tag_8021q on ports local to the same
switch, and it matters because now that we are making tag_8021q a core
DSA feature, we need to hook into .crosschip_bridge_join() to add/remove
the tag_8021q VLANs. So for symmetry it makes sense to manage the VLANs
for local forwarding in the same way as cross-chip forwarding.
Note that there is a very precise reason why tag_8021q hooks into
dsa_switch_bridge_join() which acts at the cross-chip notifier level,
and not at a higher level such as dsa_port_bridge_join(). We need to
install the RX VLAN of the newly joining port into the VLAN table of all
the existing ports across the tree that are part of the same bridge, and
the notifier already does the iteration through the switches for us.
Signed-off-by: Vladimir Oltean <vladimir.oltean@nxp.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
2021-07-20 01:14:51 +08:00
|
|
|
ds->ops->port_bridge_join) {
|
|
|
|
|
err = ds->ops->port_bridge_join(ds, info->port, info->br);
|
|
|
|
|
if (err)
|
|
|
|
|
return err;
|
|
|
|
|
}
|
2017-02-04 02:20:21 +08:00
|
|
|
|
net: dsa: permit cross-chip bridging between all trees in the system
One way of utilizing DSA is by cascading switches which do not all have
compatible taggers. Consider the following real-life topology:
+---------------------------------------------------------------+
| LS1028A |
| +------------------------------+ |
| | DSA master for Felix | |
| |(internal ENETC port 2: eno2))| |
| +------------+------------------------------+-------------+ |
| | Felix embedded L2 switch | |
| | | |
| | +--------------+ +--------------+ +--------------+ | |
| | |DSA master for| |DSA master for| |DSA master for| | |
| | | SJA1105 1 | | SJA1105 2 | | SJA1105 3 | | |
| | |(Felix port 1)| |(Felix port 2)| |(Felix port 3)| | |
+--+-+--------------+---+--------------+---+--------------+--+--+
+-----------------------+ +-----------------------+ +-----------------------+
| SJA1105 switch 1 | | SJA1105 switch 2 | | SJA1105 switch 3 |
+-----+-----+-----+-----+ +-----+-----+-----+-----+ +-----+-----+-----+-----+
|sw1p0|sw1p1|sw1p2|sw1p3| |sw2p0|sw2p1|sw2p2|sw2p3| |sw3p0|sw3p1|sw3p2|sw3p3|
+-----+-----+-----+-----+ +-----+-----+-----+-----+ +-----+-----+-----+-----+
The above can be described in the device tree as follows (obviously not
complete):
mscc_felix {
dsa,member = <0 0>;
ports {
port@4 {
ethernet = <&enetc_port2>;
};
};
};
sja1105_switch1 {
dsa,member = <1 1>;
ports {
port@4 {
ethernet = <&mscc_felix_port1>;
};
};
};
sja1105_switch2 {
dsa,member = <2 2>;
ports {
port@4 {
ethernet = <&mscc_felix_port2>;
};
};
};
sja1105_switch3 {
dsa,member = <3 3>;
ports {
port@4 {
ethernet = <&mscc_felix_port3>;
};
};
};
Basically we instantiate one DSA switch tree for every hardware switch
in the system, but we still give them globally unique switch IDs (will
come back to that later). Having 3 disjoint switch trees makes the
tagger drivers "just work", because net devices are registered for the
3 Felix DSA master ports, and they are also DSA slave ports to the ENETC
port. So packets received on the ENETC port are stripped of their
stacked DSA tags one by one.
Currently, hardware bridging between ports on the same sja1105 chip is
possible, but switching between sja1105 ports on different chips is
handled by the software bridge. This is fine, but we can do better.
In fact, the dsa_8021q tag used by sja1105 is compatible with cascading.
In other words, a sja1105 switch can correctly parse and route a packet
containing a dsa_8021q tag. So if we could enable hardware bridging on
the Felix DSA master ports, cross-chip bridging could be completely
offloaded.
Such as system would be used as follows:
ip link add dev br0 type bridge && ip link set dev br0 up
for port in sw0p0 sw0p1 sw0p2 sw0p3 \
sw1p0 sw1p1 sw1p2 sw1p3 \
sw2p0 sw2p1 sw2p2 sw2p3; do
ip link set dev $port master br0
done
The above makes switching between ports on the same row be performed in
hardware, and between ports on different rows in software. Now assume
the Felix switch ports are called swp0, swp1, swp2. By running the
following extra commands:
ip link add dev br1 type bridge && ip link set dev br1 up
for port in swp0 swp1 swp2; do
ip link set dev $port master br1
done
the CPU no longer sees packets which traverse sja1105 switch boundaries
and can be forwarded directly by Felix. The br1 bridge would not be used
for any sort of traffic termination.
For this to work, we need to give drivers an opportunity to listen for
bridging events on DSA trees other than their own, and pass that other
tree index as argument. I have made the assumption, for the moment, that
the other existing DSA notifiers don't need to be broadcast to other
trees. That assumption might turn out to be incorrect. But in the
meantime, introduce a dsa_broadcast function, similar in purpose to
dsa_port_notify, which is used only by the bridging notifiers.
Signed-off-by: Vladimir Oltean <vladimir.oltean@nxp.com>
Reviewed-by: Florian Fainelli <f.fainelli@gmail.com>
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
2020-05-11 00:37:41 +08:00
|
|
|
if ((dst->index != info->tree_index || ds->index != info->sw_index) &&
|
net: dsa: tag_8021q: manage RX VLANs dynamically at bridge join/leave time
There has been at least one wasted opportunity for tag_8021q to be used
by a driver:
https://patchwork.ozlabs.org/project/netdev/patch/20200710113611.3398-3-kurt@linutronix.de/#2484272
because of a design decision: the declared purpose of tag_8021q is to
offer source port/switch identification for a tagging driver for packets
coming from a switch with no hardware DSA tagging support. It is not
intended to provide VLAN-based port isolation, because its first user,
sja1105, had another mechanism for bridging domain isolation, the L2
Forwarding Table. So even if 2 ports are in the same VLAN but they are
separated via the L2 Forwarding Table, they will not communicate with
one another. The L2 Forwarding Table is managed by the
sja1105_bridge_join() and sja1105_bridge_leave() methods.
As a consequence, today tag_8021q does not bother too much with hooking
into .port_bridge_join() and .port_bridge_leave() because that would
introduce yet another degree of freedom, it just iterates statically
through all ports of a switch and adds the RX VLAN of one port to all
the others. In this way, whenever .port_bridge_join() is called,
bridging will magically work because the RX VLANs are already installed
everywhere they need to be.
This is not to say that the reason for the change in this patch is to
satisfy the hellcreek and similar use cases, that is merely a nice side
effect. Instead it is to make sja1105 cross-chip links work properly
over a DSA link.
For context, sja1105 today supports a degenerate form of cross-chip
bridging, where the switches are interconnected through their CPU ports
("disjoint trees" topology). There is some code which has been
generalized into dsa_8021q_crosschip_link_{add,del}, but it is not
enough, and frankly it is impossible to build upon that.
Real multi-switch DSA trees, like daisy chains or H trees, which have
actual DSA links, do not work.
The problem is that sja1105 is unlike mv88e6xxx, and does not have a PVT
for cross-chip bridging, which is a table by which the local switch can
select the forwarding domain for packets from a certain ingress switch
ID and source port. The sja1105 switches cannot parse their own DSA
tags, because, well, they don't really have support for DSA tags, it's
all VLANs.
So to make something like cross-chip bridging between sw0p0 and sw1p0 to
work over the sw0p3/sw1p3 DSA link to work with sja1105 in the topology
below:
| |
sw0p0 sw0p1 sw0p2 sw0p3 sw1p3 sw1p2 sw1p1 sw1p0
[ user ] [ user ] [ cpu ] [ dsa ] ---- [ dsa ] [ cpu ] [ user ] [ user ]
we need to ask ourselves 2 questions:
(1) how should the L2 Forwarding Table be managed?
(2) how should the VLAN Lookup Table be managed?
i.e. what should prevent packets from going to unwanted ports?
Since as mentioned, there is no PVT, the L2 Forwarding Table only
contains forwarding rules for local ports. So we can say "all user ports
are allowed to forward to all CPU ports and all DSA links".
If we allow forwarding to DSA links unconditionally, this means we must
prevent forwarding using the VLAN Lookup Table. This is in fact
asymmetric with what we do for tag_8021q on ports local to the same
switch, and it matters because now that we are making tag_8021q a core
DSA feature, we need to hook into .crosschip_bridge_join() to add/remove
the tag_8021q VLANs. So for symmetry it makes sense to manage the VLANs
for local forwarding in the same way as cross-chip forwarding.
Note that there is a very precise reason why tag_8021q hooks into
dsa_switch_bridge_join() which acts at the cross-chip notifier level,
and not at a higher level such as dsa_port_bridge_join(). We need to
install the RX VLAN of the newly joining port into the VLAN table of all
the existing ports across the tree that are part of the same bridge, and
the notifier already does the iteration through the switches for us.
Signed-off-by: Vladimir Oltean <vladimir.oltean@nxp.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
2021-07-20 01:14:51 +08:00
|
|
|
ds->ops->crosschip_bridge_join) {
|
|
|
|
|
err = ds->ops->crosschip_bridge_join(ds, info->tree_index,
|
|
|
|
|
info->sw_index,
|
|
|
|
|
info->port, info->br);
|
|
|
|
|
if (err)
|
|
|
|
|
return err;
|
|
|
|
|
}
|
2017-02-04 02:20:21 +08:00
|
|
|
|
net: dsa: tag_8021q: manage RX VLANs dynamically at bridge join/leave time
There has been at least one wasted opportunity for tag_8021q to be used
by a driver:
https://patchwork.ozlabs.org/project/netdev/patch/20200710113611.3398-3-kurt@linutronix.de/#2484272
because of a design decision: the declared purpose of tag_8021q is to
offer source port/switch identification for a tagging driver for packets
coming from a switch with no hardware DSA tagging support. It is not
intended to provide VLAN-based port isolation, because its first user,
sja1105, had another mechanism for bridging domain isolation, the L2
Forwarding Table. So even if 2 ports are in the same VLAN but they are
separated via the L2 Forwarding Table, they will not communicate with
one another. The L2 Forwarding Table is managed by the
sja1105_bridge_join() and sja1105_bridge_leave() methods.
As a consequence, today tag_8021q does not bother too much with hooking
into .port_bridge_join() and .port_bridge_leave() because that would
introduce yet another degree of freedom, it just iterates statically
through all ports of a switch and adds the RX VLAN of one port to all
the others. In this way, whenever .port_bridge_join() is called,
bridging will magically work because the RX VLANs are already installed
everywhere they need to be.
This is not to say that the reason for the change in this patch is to
satisfy the hellcreek and similar use cases, that is merely a nice side
effect. Instead it is to make sja1105 cross-chip links work properly
over a DSA link.
For context, sja1105 today supports a degenerate form of cross-chip
bridging, where the switches are interconnected through their CPU ports
("disjoint trees" topology). There is some code which has been
generalized into dsa_8021q_crosschip_link_{add,del}, but it is not
enough, and frankly it is impossible to build upon that.
Real multi-switch DSA trees, like daisy chains or H trees, which have
actual DSA links, do not work.
The problem is that sja1105 is unlike mv88e6xxx, and does not have a PVT
for cross-chip bridging, which is a table by which the local switch can
select the forwarding domain for packets from a certain ingress switch
ID and source port. The sja1105 switches cannot parse their own DSA
tags, because, well, they don't really have support for DSA tags, it's
all VLANs.
So to make something like cross-chip bridging between sw0p0 and sw1p0 to
work over the sw0p3/sw1p3 DSA link to work with sja1105 in the topology
below:
| |
sw0p0 sw0p1 sw0p2 sw0p3 sw1p3 sw1p2 sw1p1 sw1p0
[ user ] [ user ] [ cpu ] [ dsa ] ---- [ dsa ] [ cpu ] [ user ] [ user ]
we need to ask ourselves 2 questions:
(1) how should the L2 Forwarding Table be managed?
(2) how should the VLAN Lookup Table be managed?
i.e. what should prevent packets from going to unwanted ports?
Since as mentioned, there is no PVT, the L2 Forwarding Table only
contains forwarding rules for local ports. So we can say "all user ports
are allowed to forward to all CPU ports and all DSA links".
If we allow forwarding to DSA links unconditionally, this means we must
prevent forwarding using the VLAN Lookup Table. This is in fact
asymmetric with what we do for tag_8021q on ports local to the same
switch, and it matters because now that we are making tag_8021q a core
DSA feature, we need to hook into .crosschip_bridge_join() to add/remove
the tag_8021q VLANs. So for symmetry it makes sense to manage the VLANs
for local forwarding in the same way as cross-chip forwarding.
Note that there is a very precise reason why tag_8021q hooks into
dsa_switch_bridge_join() which acts at the cross-chip notifier level,
and not at a higher level such as dsa_port_bridge_join(). We need to
install the RX VLAN of the newly joining port into the VLAN table of all
the existing ports across the tree that are part of the same bridge, and
the notifier already does the iteration through the switches for us.
Signed-off-by: Vladimir Oltean <vladimir.oltean@nxp.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
2021-07-20 01:14:51 +08:00
|
|
|
return dsa_tag_8021q_bridge_join(ds, info);
|
2017-02-04 02:20:21 +08:00
|
|
|
}
|
|
|
|
|
|
|
|
|
|
static int dsa_switch_bridge_leave(struct dsa_switch *ds,
|
|
|
|
|
struct dsa_notifier_bridge_info *info)
|
|
|
|
|
{
|
net: dsa: Unset vlan_filtering when ports leave the bridge
When ports are standalone (after they left the bridge), they should have
no VLAN filtering semantics (they should pass all traffic to the CPU).
Currently this is not true for switchdev drivers, because the bridge
"forgets" to unset that.
Normally one would think that doing this at the bridge layer would be a
better idea, i.e. call br_vlan_filter_toggle() from br_del_if(), similar
to how nbp_vlan_init() is called from br_add_if().
However what complicates that approach, and makes this one preferable,
is the fact that for the bridge core, vlan_filtering is a per-bridge
setting, whereas for switchdev/DSA it is per-port. Also there are
switches where the setting is per the entire device, and unsetting
vlan_filtering one by one, for each leaving port, would not be possible
from the bridge core without a certain level of awareness. So do this in
DSA and let drivers be unaware of it.
Signed-off-by: Vladimir Oltean <olteanv@gmail.com>
Reviewed-by: Andrew Lunn <andrew@lunn.ch>
Reviewed-by: Florian Fainelli <f.fainelli@gmail.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
2019-04-29 02:45:46 +08:00
|
|
|
bool unset_vlan_filtering = br_vlan_enabled(info->br);
|
net: dsa: permit cross-chip bridging between all trees in the system
One way of utilizing DSA is by cascading switches which do not all have
compatible taggers. Consider the following real-life topology:
+---------------------------------------------------------------+
| LS1028A |
| +------------------------------+ |
| | DSA master for Felix | |
| |(internal ENETC port 2: eno2))| |
| +------------+------------------------------+-------------+ |
| | Felix embedded L2 switch | |
| | | |
| | +--------------+ +--------------+ +--------------+ | |
| | |DSA master for| |DSA master for| |DSA master for| | |
| | | SJA1105 1 | | SJA1105 2 | | SJA1105 3 | | |
| | |(Felix port 1)| |(Felix port 2)| |(Felix port 3)| | |
+--+-+--------------+---+--------------+---+--------------+--+--+
+-----------------------+ +-----------------------+ +-----------------------+
| SJA1105 switch 1 | | SJA1105 switch 2 | | SJA1105 switch 3 |
+-----+-----+-----+-----+ +-----+-----+-----+-----+ +-----+-----+-----+-----+
|sw1p0|sw1p1|sw1p2|sw1p3| |sw2p0|sw2p1|sw2p2|sw2p3| |sw3p0|sw3p1|sw3p2|sw3p3|
+-----+-----+-----+-----+ +-----+-----+-----+-----+ +-----+-----+-----+-----+
The above can be described in the device tree as follows (obviously not
complete):
mscc_felix {
dsa,member = <0 0>;
ports {
port@4 {
ethernet = <&enetc_port2>;
};
};
};
sja1105_switch1 {
dsa,member = <1 1>;
ports {
port@4 {
ethernet = <&mscc_felix_port1>;
};
};
};
sja1105_switch2 {
dsa,member = <2 2>;
ports {
port@4 {
ethernet = <&mscc_felix_port2>;
};
};
};
sja1105_switch3 {
dsa,member = <3 3>;
ports {
port@4 {
ethernet = <&mscc_felix_port3>;
};
};
};
Basically we instantiate one DSA switch tree for every hardware switch
in the system, but we still give them globally unique switch IDs (will
come back to that later). Having 3 disjoint switch trees makes the
tagger drivers "just work", because net devices are registered for the
3 Felix DSA master ports, and they are also DSA slave ports to the ENETC
port. So packets received on the ENETC port are stripped of their
stacked DSA tags one by one.
Currently, hardware bridging between ports on the same sja1105 chip is
possible, but switching between sja1105 ports on different chips is
handled by the software bridge. This is fine, but we can do better.
In fact, the dsa_8021q tag used by sja1105 is compatible with cascading.
In other words, a sja1105 switch can correctly parse and route a packet
containing a dsa_8021q tag. So if we could enable hardware bridging on
the Felix DSA master ports, cross-chip bridging could be completely
offloaded.
Such as system would be used as follows:
ip link add dev br0 type bridge && ip link set dev br0 up
for port in sw0p0 sw0p1 sw0p2 sw0p3 \
sw1p0 sw1p1 sw1p2 sw1p3 \
sw2p0 sw2p1 sw2p2 sw2p3; do
ip link set dev $port master br0
done
The above makes switching between ports on the same row be performed in
hardware, and between ports on different rows in software. Now assume
the Felix switch ports are called swp0, swp1, swp2. By running the
following extra commands:
ip link add dev br1 type bridge && ip link set dev br1 up
for port in swp0 swp1 swp2; do
ip link set dev $port master br1
done
the CPU no longer sees packets which traverse sja1105 switch boundaries
and can be forwarded directly by Felix. The br1 bridge would not be used
for any sort of traffic termination.
For this to work, we need to give drivers an opportunity to listen for
bridging events on DSA trees other than their own, and pass that other
tree index as argument. I have made the assumption, for the moment, that
the other existing DSA notifiers don't need to be broadcast to other
trees. That assumption might turn out to be incorrect. But in the
meantime, introduce a dsa_broadcast function, similar in purpose to
dsa_port_notify, which is used only by the bridging notifiers.
Signed-off-by: Vladimir Oltean <vladimir.oltean@nxp.com>
Reviewed-by: Florian Fainelli <f.fainelli@gmail.com>
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
2020-05-11 00:37:41 +08:00
|
|
|
struct dsa_switch_tree *dst = ds->dst;
|
2021-02-14 04:43:19 +08:00
|
|
|
struct netlink_ext_ack extack = {0};
|
2021-03-24 17:56:39 +08:00
|
|
|
int err, port;
|
net: dsa: Unset vlan_filtering when ports leave the bridge
When ports are standalone (after they left the bridge), they should have
no VLAN filtering semantics (they should pass all traffic to the CPU).
Currently this is not true for switchdev drivers, because the bridge
"forgets" to unset that.
Normally one would think that doing this at the bridge layer would be a
better idea, i.e. call br_vlan_filter_toggle() from br_del_if(), similar
to how nbp_vlan_init() is called from br_add_if().
However what complicates that approach, and makes this one preferable,
is the fact that for the bridge core, vlan_filtering is a per-bridge
setting, whereas for switchdev/DSA it is per-port. Also there are
switches where the setting is per the entire device, and unsetting
vlan_filtering one by one, for each leaving port, would not be possible
from the bridge core without a certain level of awareness. So do this in
DSA and let drivers be unaware of it.
Signed-off-by: Vladimir Oltean <olteanv@gmail.com>
Reviewed-by: Andrew Lunn <andrew@lunn.ch>
Reviewed-by: Florian Fainelli <f.fainelli@gmail.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
2019-04-29 02:45:46 +08:00
|
|
|
|
net: dsa: permit cross-chip bridging between all trees in the system
One way of utilizing DSA is by cascading switches which do not all have
compatible taggers. Consider the following real-life topology:
+---------------------------------------------------------------+
| LS1028A |
| +------------------------------+ |
| | DSA master for Felix | |
| |(internal ENETC port 2: eno2))| |
| +------------+------------------------------+-------------+ |
| | Felix embedded L2 switch | |
| | | |
| | +--------------+ +--------------+ +--------------+ | |
| | |DSA master for| |DSA master for| |DSA master for| | |
| | | SJA1105 1 | | SJA1105 2 | | SJA1105 3 | | |
| | |(Felix port 1)| |(Felix port 2)| |(Felix port 3)| | |
+--+-+--------------+---+--------------+---+--------------+--+--+
+-----------------------+ +-----------------------+ +-----------------------+
| SJA1105 switch 1 | | SJA1105 switch 2 | | SJA1105 switch 3 |
+-----+-----+-----+-----+ +-----+-----+-----+-----+ +-----+-----+-----+-----+
|sw1p0|sw1p1|sw1p2|sw1p3| |sw2p0|sw2p1|sw2p2|sw2p3| |sw3p0|sw3p1|sw3p2|sw3p3|
+-----+-----+-----+-----+ +-----+-----+-----+-----+ +-----+-----+-----+-----+
The above can be described in the device tree as follows (obviously not
complete):
mscc_felix {
dsa,member = <0 0>;
ports {
port@4 {
ethernet = <&enetc_port2>;
};
};
};
sja1105_switch1 {
dsa,member = <1 1>;
ports {
port@4 {
ethernet = <&mscc_felix_port1>;
};
};
};
sja1105_switch2 {
dsa,member = <2 2>;
ports {
port@4 {
ethernet = <&mscc_felix_port2>;
};
};
};
sja1105_switch3 {
dsa,member = <3 3>;
ports {
port@4 {
ethernet = <&mscc_felix_port3>;
};
};
};
Basically we instantiate one DSA switch tree for every hardware switch
in the system, but we still give them globally unique switch IDs (will
come back to that later). Having 3 disjoint switch trees makes the
tagger drivers "just work", because net devices are registered for the
3 Felix DSA master ports, and they are also DSA slave ports to the ENETC
port. So packets received on the ENETC port are stripped of their
stacked DSA tags one by one.
Currently, hardware bridging between ports on the same sja1105 chip is
possible, but switching between sja1105 ports on different chips is
handled by the software bridge. This is fine, but we can do better.
In fact, the dsa_8021q tag used by sja1105 is compatible with cascading.
In other words, a sja1105 switch can correctly parse and route a packet
containing a dsa_8021q tag. So if we could enable hardware bridging on
the Felix DSA master ports, cross-chip bridging could be completely
offloaded.
Such as system would be used as follows:
ip link add dev br0 type bridge && ip link set dev br0 up
for port in sw0p0 sw0p1 sw0p2 sw0p3 \
sw1p0 sw1p1 sw1p2 sw1p3 \
sw2p0 sw2p1 sw2p2 sw2p3; do
ip link set dev $port master br0
done
The above makes switching between ports on the same row be performed in
hardware, and between ports on different rows in software. Now assume
the Felix switch ports are called swp0, swp1, swp2. By running the
following extra commands:
ip link add dev br1 type bridge && ip link set dev br1 up
for port in swp0 swp1 swp2; do
ip link set dev $port master br1
done
the CPU no longer sees packets which traverse sja1105 switch boundaries
and can be forwarded directly by Felix. The br1 bridge would not be used
for any sort of traffic termination.
For this to work, we need to give drivers an opportunity to listen for
bridging events on DSA trees other than their own, and pass that other
tree index as argument. I have made the assumption, for the moment, that
the other existing DSA notifiers don't need to be broadcast to other
trees. That assumption might turn out to be incorrect. But in the
meantime, introduce a dsa_broadcast function, similar in purpose to
dsa_port_notify, which is used only by the bridging notifiers.
Signed-off-by: Vladimir Oltean <vladimir.oltean@nxp.com>
Reviewed-by: Florian Fainelli <f.fainelli@gmail.com>
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
2020-05-11 00:37:41 +08:00
|
|
|
if (dst->index == info->tree_index && ds->index == info->sw_index &&
|
2021-07-13 17:40:21 +08:00
|
|
|
ds->ops->port_bridge_leave)
|
2017-02-04 02:20:21 +08:00
|
|
|
ds->ops->port_bridge_leave(ds, info->port, info->br);
|
|
|
|
|
|
net: dsa: permit cross-chip bridging between all trees in the system
One way of utilizing DSA is by cascading switches which do not all have
compatible taggers. Consider the following real-life topology:
+---------------------------------------------------------------+
| LS1028A |
| +------------------------------+ |
| | DSA master for Felix | |
| |(internal ENETC port 2: eno2))| |
| +------------+------------------------------+-------------+ |
| | Felix embedded L2 switch | |
| | | |
| | +--------------+ +--------------+ +--------------+ | |
| | |DSA master for| |DSA master for| |DSA master for| | |
| | | SJA1105 1 | | SJA1105 2 | | SJA1105 3 | | |
| | |(Felix port 1)| |(Felix port 2)| |(Felix port 3)| | |
+--+-+--------------+---+--------------+---+--------------+--+--+
+-----------------------+ +-----------------------+ +-----------------------+
| SJA1105 switch 1 | | SJA1105 switch 2 | | SJA1105 switch 3 |
+-----+-----+-----+-----+ +-----+-----+-----+-----+ +-----+-----+-----+-----+
|sw1p0|sw1p1|sw1p2|sw1p3| |sw2p0|sw2p1|sw2p2|sw2p3| |sw3p0|sw3p1|sw3p2|sw3p3|
+-----+-----+-----+-----+ +-----+-----+-----+-----+ +-----+-----+-----+-----+
The above can be described in the device tree as follows (obviously not
complete):
mscc_felix {
dsa,member = <0 0>;
ports {
port@4 {
ethernet = <&enetc_port2>;
};
};
};
sja1105_switch1 {
dsa,member = <1 1>;
ports {
port@4 {
ethernet = <&mscc_felix_port1>;
};
};
};
sja1105_switch2 {
dsa,member = <2 2>;
ports {
port@4 {
ethernet = <&mscc_felix_port2>;
};
};
};
sja1105_switch3 {
dsa,member = <3 3>;
ports {
port@4 {
ethernet = <&mscc_felix_port3>;
};
};
};
Basically we instantiate one DSA switch tree for every hardware switch
in the system, but we still give them globally unique switch IDs (will
come back to that later). Having 3 disjoint switch trees makes the
tagger drivers "just work", because net devices are registered for the
3 Felix DSA master ports, and they are also DSA slave ports to the ENETC
port. So packets received on the ENETC port are stripped of their
stacked DSA tags one by one.
Currently, hardware bridging between ports on the same sja1105 chip is
possible, but switching between sja1105 ports on different chips is
handled by the software bridge. This is fine, but we can do better.
In fact, the dsa_8021q tag used by sja1105 is compatible with cascading.
In other words, a sja1105 switch can correctly parse and route a packet
containing a dsa_8021q tag. So if we could enable hardware bridging on
the Felix DSA master ports, cross-chip bridging could be completely
offloaded.
Such as system would be used as follows:
ip link add dev br0 type bridge && ip link set dev br0 up
for port in sw0p0 sw0p1 sw0p2 sw0p3 \
sw1p0 sw1p1 sw1p2 sw1p3 \
sw2p0 sw2p1 sw2p2 sw2p3; do
ip link set dev $port master br0
done
The above makes switching between ports on the same row be performed in
hardware, and between ports on different rows in software. Now assume
the Felix switch ports are called swp0, swp1, swp2. By running the
following extra commands:
ip link add dev br1 type bridge && ip link set dev br1 up
for port in swp0 swp1 swp2; do
ip link set dev $port master br1
done
the CPU no longer sees packets which traverse sja1105 switch boundaries
and can be forwarded directly by Felix. The br1 bridge would not be used
for any sort of traffic termination.
For this to work, we need to give drivers an opportunity to listen for
bridging events on DSA trees other than their own, and pass that other
tree index as argument. I have made the assumption, for the moment, that
the other existing DSA notifiers don't need to be broadcast to other
trees. That assumption might turn out to be incorrect. But in the
meantime, introduce a dsa_broadcast function, similar in purpose to
dsa_port_notify, which is used only by the bridging notifiers.
Signed-off-by: Vladimir Oltean <vladimir.oltean@nxp.com>
Reviewed-by: Florian Fainelli <f.fainelli@gmail.com>
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
2020-05-11 00:37:41 +08:00
|
|
|
if ((dst->index != info->tree_index || ds->index != info->sw_index) &&
|
2021-07-13 17:40:21 +08:00
|
|
|
ds->ops->crosschip_bridge_leave)
|
net: dsa: permit cross-chip bridging between all trees in the system
One way of utilizing DSA is by cascading switches which do not all have
compatible taggers. Consider the following real-life topology:
+---------------------------------------------------------------+
| LS1028A |
| +------------------------------+ |
| | DSA master for Felix | |
| |(internal ENETC port 2: eno2))| |
| +------------+------------------------------+-------------+ |
| | Felix embedded L2 switch | |
| | | |
| | +--------------+ +--------------+ +--------------+ | |
| | |DSA master for| |DSA master for| |DSA master for| | |
| | | SJA1105 1 | | SJA1105 2 | | SJA1105 3 | | |
| | |(Felix port 1)| |(Felix port 2)| |(Felix port 3)| | |
+--+-+--------------+---+--------------+---+--------------+--+--+
+-----------------------+ +-----------------------+ +-----------------------+
| SJA1105 switch 1 | | SJA1105 switch 2 | | SJA1105 switch 3 |
+-----+-----+-----+-----+ +-----+-----+-----+-----+ +-----+-----+-----+-----+
|sw1p0|sw1p1|sw1p2|sw1p3| |sw2p0|sw2p1|sw2p2|sw2p3| |sw3p0|sw3p1|sw3p2|sw3p3|
+-----+-----+-----+-----+ +-----+-----+-----+-----+ +-----+-----+-----+-----+
The above can be described in the device tree as follows (obviously not
complete):
mscc_felix {
dsa,member = <0 0>;
ports {
port@4 {
ethernet = <&enetc_port2>;
};
};
};
sja1105_switch1 {
dsa,member = <1 1>;
ports {
port@4 {
ethernet = <&mscc_felix_port1>;
};
};
};
sja1105_switch2 {
dsa,member = <2 2>;
ports {
port@4 {
ethernet = <&mscc_felix_port2>;
};
};
};
sja1105_switch3 {
dsa,member = <3 3>;
ports {
port@4 {
ethernet = <&mscc_felix_port3>;
};
};
};
Basically we instantiate one DSA switch tree for every hardware switch
in the system, but we still give them globally unique switch IDs (will
come back to that later). Having 3 disjoint switch trees makes the
tagger drivers "just work", because net devices are registered for the
3 Felix DSA master ports, and they are also DSA slave ports to the ENETC
port. So packets received on the ENETC port are stripped of their
stacked DSA tags one by one.
Currently, hardware bridging between ports on the same sja1105 chip is
possible, but switching between sja1105 ports on different chips is
handled by the software bridge. This is fine, but we can do better.
In fact, the dsa_8021q tag used by sja1105 is compatible with cascading.
In other words, a sja1105 switch can correctly parse and route a packet
containing a dsa_8021q tag. So if we could enable hardware bridging on
the Felix DSA master ports, cross-chip bridging could be completely
offloaded.
Such as system would be used as follows:
ip link add dev br0 type bridge && ip link set dev br0 up
for port in sw0p0 sw0p1 sw0p2 sw0p3 \
sw1p0 sw1p1 sw1p2 sw1p3 \
sw2p0 sw2p1 sw2p2 sw2p3; do
ip link set dev $port master br0
done
The above makes switching between ports on the same row be performed in
hardware, and between ports on different rows in software. Now assume
the Felix switch ports are called swp0, swp1, swp2. By running the
following extra commands:
ip link add dev br1 type bridge && ip link set dev br1 up
for port in swp0 swp1 swp2; do
ip link set dev $port master br1
done
the CPU no longer sees packets which traverse sja1105 switch boundaries
and can be forwarded directly by Felix. The br1 bridge would not be used
for any sort of traffic termination.
For this to work, we need to give drivers an opportunity to listen for
bridging events on DSA trees other than their own, and pass that other
tree index as argument. I have made the assumption, for the moment, that
the other existing DSA notifiers don't need to be broadcast to other
trees. That assumption might turn out to be incorrect. But in the
meantime, introduce a dsa_broadcast function, similar in purpose to
dsa_port_notify, which is used only by the bridging notifiers.
Signed-off-by: Vladimir Oltean <vladimir.oltean@nxp.com>
Reviewed-by: Florian Fainelli <f.fainelli@gmail.com>
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
2020-05-11 00:37:41 +08:00
|
|
|
ds->ops->crosschip_bridge_leave(ds, info->tree_index,
|
|
|
|
|
info->sw_index, info->port,
|
2017-03-31 05:37:14 +08:00
|
|
|
info->br);
|
2017-02-04 02:20:21 +08:00
|
|
|
|
net: dsa: Unset vlan_filtering when ports leave the bridge
When ports are standalone (after they left the bridge), they should have
no VLAN filtering semantics (they should pass all traffic to the CPU).
Currently this is not true for switchdev drivers, because the bridge
"forgets" to unset that.
Normally one would think that doing this at the bridge layer would be a
better idea, i.e. call br_vlan_filter_toggle() from br_del_if(), similar
to how nbp_vlan_init() is called from br_add_if().
However what complicates that approach, and makes this one preferable,
is the fact that for the bridge core, vlan_filtering is a per-bridge
setting, whereas for switchdev/DSA it is per-port. Also there are
switches where the setting is per the entire device, and unsetting
vlan_filtering one by one, for each leaving port, would not be possible
from the bridge core without a certain level of awareness. So do this in
DSA and let drivers be unaware of it.
Signed-off-by: Vladimir Oltean <olteanv@gmail.com>
Reviewed-by: Andrew Lunn <andrew@lunn.ch>
Reviewed-by: Florian Fainelli <f.fainelli@gmail.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
2019-04-29 02:45:46 +08:00
|
|
|
/* If the bridge was vlan_filtering, the bridge core doesn't trigger an
|
|
|
|
|
* event for changing vlan_filtering setting upon slave ports leaving
|
|
|
|
|
* it. That is a good thing, because that lets us handle it and also
|
|
|
|
|
* handle the case where the switch's vlan_filtering setting is global
|
|
|
|
|
* (not per port). When that happens, the correct moment to trigger the
|
2021-03-24 17:56:39 +08:00
|
|
|
* vlan_filtering callback is only when the last port leaves the last
|
|
|
|
|
* VLAN-aware bridge.
|
net: dsa: Unset vlan_filtering when ports leave the bridge
When ports are standalone (after they left the bridge), they should have
no VLAN filtering semantics (they should pass all traffic to the CPU).
Currently this is not true for switchdev drivers, because the bridge
"forgets" to unset that.
Normally one would think that doing this at the bridge layer would be a
better idea, i.e. call br_vlan_filter_toggle() from br_del_if(), similar
to how nbp_vlan_init() is called from br_add_if().
However what complicates that approach, and makes this one preferable,
is the fact that for the bridge core, vlan_filtering is a per-bridge
setting, whereas for switchdev/DSA it is per-port. Also there are
switches where the setting is per the entire device, and unsetting
vlan_filtering one by one, for each leaving port, would not be possible
from the bridge core without a certain level of awareness. So do this in
DSA and let drivers be unaware of it.
Signed-off-by: Vladimir Oltean <olteanv@gmail.com>
Reviewed-by: Andrew Lunn <andrew@lunn.ch>
Reviewed-by: Florian Fainelli <f.fainelli@gmail.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
2019-04-29 02:45:46 +08:00
|
|
|
*/
|
|
|
|
|
if (unset_vlan_filtering && ds->vlan_filtering_is_global) {
|
2021-03-24 17:56:39 +08:00
|
|
|
for (port = 0; port < ds->num_ports; port++) {
|
|
|
|
|
struct net_device *bridge_dev;
|
|
|
|
|
|
|
|
|
|
bridge_dev = dsa_to_port(ds, port)->bridge_dev;
|
|
|
|
|
|
|
|
|
|
if (bridge_dev && br_vlan_enabled(bridge_dev)) {
|
net: dsa: Unset vlan_filtering when ports leave the bridge
When ports are standalone (after they left the bridge), they should have
no VLAN filtering semantics (they should pass all traffic to the CPU).
Currently this is not true for switchdev drivers, because the bridge
"forgets" to unset that.
Normally one would think that doing this at the bridge layer would be a
better idea, i.e. call br_vlan_filter_toggle() from br_del_if(), similar
to how nbp_vlan_init() is called from br_add_if().
However what complicates that approach, and makes this one preferable,
is the fact that for the bridge core, vlan_filtering is a per-bridge
setting, whereas for switchdev/DSA it is per-port. Also there are
switches where the setting is per the entire device, and unsetting
vlan_filtering one by one, for each leaving port, would not be possible
from the bridge core without a certain level of awareness. So do this in
DSA and let drivers be unaware of it.
Signed-off-by: Vladimir Oltean <olteanv@gmail.com>
Reviewed-by: Andrew Lunn <andrew@lunn.ch>
Reviewed-by: Florian Fainelli <f.fainelli@gmail.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
2019-04-29 02:45:46 +08:00
|
|
|
unset_vlan_filtering = false;
|
|
|
|
|
break;
|
|
|
|
|
}
|
|
|
|
|
}
|
|
|
|
|
}
|
|
|
|
|
if (unset_vlan_filtering) {
|
2019-10-22 04:51:15 +08:00
|
|
|
err = dsa_port_vlan_filtering(dsa_to_port(ds, info->port),
|
2021-02-14 04:43:19 +08:00
|
|
|
false, &extack);
|
|
|
|
|
if (extack._msg)
|
|
|
|
|
dev_err(ds->dev, "port %d: %s\n", info->port,
|
|
|
|
|
extack._msg);
|
net: dsa: Unset vlan_filtering when ports leave the bridge
When ports are standalone (after they left the bridge), they should have
no VLAN filtering semantics (they should pass all traffic to the CPU).
Currently this is not true for switchdev drivers, because the bridge
"forgets" to unset that.
Normally one would think that doing this at the bridge layer would be a
better idea, i.e. call br_vlan_filter_toggle() from br_del_if(), similar
to how nbp_vlan_init() is called from br_add_if().
However what complicates that approach, and makes this one preferable,
is the fact that for the bridge core, vlan_filtering is a per-bridge
setting, whereas for switchdev/DSA it is per-port. Also there are
switches where the setting is per the entire device, and unsetting
vlan_filtering one by one, for each leaving port, would not be possible
from the bridge core without a certain level of awareness. So do this in
DSA and let drivers be unaware of it.
Signed-off-by: Vladimir Oltean <olteanv@gmail.com>
Reviewed-by: Andrew Lunn <andrew@lunn.ch>
Reviewed-by: Florian Fainelli <f.fainelli@gmail.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
2019-04-29 02:45:46 +08:00
|
|
|
if (err && err != EOPNOTSUPP)
|
|
|
|
|
return err;
|
|
|
|
|
}
|
net: dsa: tag_8021q: manage RX VLANs dynamically at bridge join/leave time
There has been at least one wasted opportunity for tag_8021q to be used
by a driver:
https://patchwork.ozlabs.org/project/netdev/patch/20200710113611.3398-3-kurt@linutronix.de/#2484272
because of a design decision: the declared purpose of tag_8021q is to
offer source port/switch identification for a tagging driver for packets
coming from a switch with no hardware DSA tagging support. It is not
intended to provide VLAN-based port isolation, because its first user,
sja1105, had another mechanism for bridging domain isolation, the L2
Forwarding Table. So even if 2 ports are in the same VLAN but they are
separated via the L2 Forwarding Table, they will not communicate with
one another. The L2 Forwarding Table is managed by the
sja1105_bridge_join() and sja1105_bridge_leave() methods.
As a consequence, today tag_8021q does not bother too much with hooking
into .port_bridge_join() and .port_bridge_leave() because that would
introduce yet another degree of freedom, it just iterates statically
through all ports of a switch and adds the RX VLAN of one port to all
the others. In this way, whenever .port_bridge_join() is called,
bridging will magically work because the RX VLANs are already installed
everywhere they need to be.
This is not to say that the reason for the change in this patch is to
satisfy the hellcreek and similar use cases, that is merely a nice side
effect. Instead it is to make sja1105 cross-chip links work properly
over a DSA link.
For context, sja1105 today supports a degenerate form of cross-chip
bridging, where the switches are interconnected through their CPU ports
("disjoint trees" topology). There is some code which has been
generalized into dsa_8021q_crosschip_link_{add,del}, but it is not
enough, and frankly it is impossible to build upon that.
Real multi-switch DSA trees, like daisy chains or H trees, which have
actual DSA links, do not work.
The problem is that sja1105 is unlike mv88e6xxx, and does not have a PVT
for cross-chip bridging, which is a table by which the local switch can
select the forwarding domain for packets from a certain ingress switch
ID and source port. The sja1105 switches cannot parse their own DSA
tags, because, well, they don't really have support for DSA tags, it's
all VLANs.
So to make something like cross-chip bridging between sw0p0 and sw1p0 to
work over the sw0p3/sw1p3 DSA link to work with sja1105 in the topology
below:
| |
sw0p0 sw0p1 sw0p2 sw0p3 sw1p3 sw1p2 sw1p1 sw1p0
[ user ] [ user ] [ cpu ] [ dsa ] ---- [ dsa ] [ cpu ] [ user ] [ user ]
we need to ask ourselves 2 questions:
(1) how should the L2 Forwarding Table be managed?
(2) how should the VLAN Lookup Table be managed?
i.e. what should prevent packets from going to unwanted ports?
Since as mentioned, there is no PVT, the L2 Forwarding Table only
contains forwarding rules for local ports. So we can say "all user ports
are allowed to forward to all CPU ports and all DSA links".
If we allow forwarding to DSA links unconditionally, this means we must
prevent forwarding using the VLAN Lookup Table. This is in fact
asymmetric with what we do for tag_8021q on ports local to the same
switch, and it matters because now that we are making tag_8021q a core
DSA feature, we need to hook into .crosschip_bridge_join() to add/remove
the tag_8021q VLANs. So for symmetry it makes sense to manage the VLANs
for local forwarding in the same way as cross-chip forwarding.
Note that there is a very precise reason why tag_8021q hooks into
dsa_switch_bridge_join() which acts at the cross-chip notifier level,
and not at a higher level such as dsa_port_bridge_join(). We need to
install the RX VLAN of the newly joining port into the VLAN table of all
the existing ports across the tree that are part of the same bridge, and
the notifier already does the iteration through the switches for us.
Signed-off-by: Vladimir Oltean <vladimir.oltean@nxp.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
2021-07-20 01:14:51 +08:00
|
|
|
|
|
|
|
|
return dsa_tag_8021q_bridge_leave(ds, info);
|
2017-02-04 02:20:21 +08:00
|
|
|
}
|
|
|
|
|
|
net: dsa: introduce a separate cross-chip notifier type for host MDBs
Commit abd49535c380 ("net: dsa: execute dsa_switch_mdb_add only for
routing port in cross-chip topologies") does a surprisingly good job
even for the SWITCHDEV_OBJ_ID_HOST_MDB use case, where DSA simply
translates a switchdev object received on dp into a cross-chip notifier
for dp->cpu_dp.
To visualize how that works, imagine the daisy chain topology below and
consider a SWITCHDEV_OBJ_ID_HOST_MDB object emitted on sw2p0. How does
the cross-chip notifier know to match on all the right ports (sw0p4, the
dedicated CPU port, sw1p4, an upstream DSA link, and sw2p4, another
upstream DSA link)?
|
sw0p0 sw0p1 sw0p2 sw0p3 sw0p4
[ user ] [ user ] [ user ] [ dsa ] [ cpu ]
[ ] [ ] [ ] [ ] [ x ]
|
+---------+
|
sw1p0 sw1p1 sw1p2 sw1p3 sw1p4
[ user ] [ user ] [ user ] [ dsa ] [ dsa ]
[ ] [ ] [ ] [ ] [ x ]
|
+---------+
|
sw2p0 sw2p1 sw2p2 sw2p3 sw2p4
[ user ] [ user ] [ user ] [ user ] [ dsa ]
[ ] [ ] [ ] [ ] [ x ]
The answer is simple: the dedicated CPU port of sw2p0 is sw0p4, and
dsa_routing_port returns the upstream port for all switches.
That is fine, but there are other topologies where this does not work as
well. There are trees with "H" topologies in the wild, where there are 2
or more switches with DSA links between them, but every switch has its
dedicated CPU port. For these topologies, it seems stupid for the neighbor
switches to install an MDB entry on the routing port, since these
multicast addresses are fundamentally different than the usual ones we
support (and that is the justification for this patch, to introduce the
concept of a termination plane multicast MAC address, as opposed to a
forwarding plane multicast MAC address).
For example, when a SWITCHDEV_OBJ_ID_HOST_MDB would get added to sw0p0,
without this patch, it would get treated as a regular port MDB on sw0p2
and it would match on the ports below (including the sw1p3 routing port).
| |
sw0p0 sw0p1 sw0p2 sw0p3 sw1p3 sw1p2 sw1p1 sw1p0
[ user ] [ user ] [ cpu ] [ dsa ] [ dsa ] [ cpu ] [ user ] [ user ]
[ ] [ ] [ x ] [ ] ---- [ x ] [ ] [ ] [ ]
With the patch, the host MDB notifier on sw0p0 matches only on the local
switch, which is what we want for a termination plane address.
| |
sw0p0 sw0p1 sw0p2 sw0p3 sw1p3 sw1p2 sw1p1 sw1p0
[ user ] [ user ] [ cpu ] [ dsa ] [ dsa ] [ cpu ] [ user ] [ user ]
[ ] [ ] [ x ] [ ] ---- [ ] [ ] [ ] [ ]
Name this new matching function "dsa_switch_host_address_match" since we
will be reusing it soon for host FDB entries as well.
Signed-off-by: Vladimir Oltean <vladimir.oltean@nxp.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
2021-06-29 22:06:49 +08:00
|
|
|
/* Matches for all upstream-facing ports (the CPU port and all upstream-facing
|
|
|
|
|
* DSA links) that sit between the targeted port on which the notifier was
|
|
|
|
|
* emitted and its dedicated CPU port.
|
|
|
|
|
*/
|
|
|
|
|
static bool dsa_switch_host_address_match(struct dsa_switch *ds, int port,
|
|
|
|
|
int info_sw_index, int info_port)
|
|
|
|
|
{
|
|
|
|
|
struct dsa_port *targeted_dp, *cpu_dp;
|
|
|
|
|
struct dsa_switch *targeted_ds;
|
|
|
|
|
|
|
|
|
|
targeted_ds = dsa_switch_find(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(ds, targeted_ds))
|
|
|
|
|
return port == dsa_towards_port(ds, cpu_dp->ds->index,
|
|
|
|
|
cpu_dp->index);
|
|
|
|
|
|
|
|
|
|
return false;
|
|
|
|
|
}
|
|
|
|
|
|
net: dsa: reference count the MDB entries at the cross-chip notifier level
Ever since the cross-chip notifiers were introduced, the design was
meant to be simplistic and just get the job done without worrying too
much about dangling resources left behind.
For example, somebody installs an MDB entry on sw0p0 in this daisy chain
topology. It gets installed using ds->ops->port_mdb_add() on sw0p0,
sw1p4 and sw2p4.
|
sw0p0 sw0p1 sw0p2 sw0p3 sw0p4
[ user ] [ user ] [ user ] [ dsa ] [ cpu ]
[ x ] [ ] [ ] [ ] [ ]
|
+---------+
|
sw1p0 sw1p1 sw1p2 sw1p3 sw1p4
[ user ] [ user ] [ user ] [ dsa ] [ dsa ]
[ ] [ ] [ ] [ ] [ x ]
|
+---------+
|
sw2p0 sw2p1 sw2p2 sw2p3 sw2p4
[ user ] [ user ] [ user ] [ user ] [ dsa ]
[ ] [ ] [ ] [ ] [ x ]
Then the same person deletes that MDB entry. The cross-chip notifier for
deletion only matches sw0p0:
|
sw0p0 sw0p1 sw0p2 sw0p3 sw0p4
[ user ] [ user ] [ user ] [ dsa ] [ cpu ]
[ x ] [ ] [ ] [ ] [ ]
|
+---------+
|
sw1p0 sw1p1 sw1p2 sw1p3 sw1p4
[ user ] [ user ] [ user ] [ dsa ] [ dsa ]
[ ] [ ] [ ] [ ] [ ]
|
+---------+
|
sw2p0 sw2p1 sw2p2 sw2p3 sw2p4
[ user ] [ user ] [ user ] [ user ] [ dsa ]
[ ] [ ] [ ] [ ] [ ]
Why?
Because the DSA links are 'trunk' ports, if we just go ahead and delete
the MDB from sw1p4 and sw2p4 directly, we might delete those multicast
entries when they are still needed. Just consider the fact that somebody
does:
- add a multicast MAC address towards sw0p0 [ via the cross-chip
notifiers it gets installed on the DSA links too ]
- add the same multicast MAC address towards sw0p1 (another port of that
same switch)
- delete the same multicast MAC address from sw0p0.
At this point, if we deleted the MAC address from the DSA links, it
would be flooded, even though there is still an entry on switch 0 which
needs it not to.
So that is why deletions only match the targeted source port and nothing
on DSA links. Of course, dangling resources means that the hardware
tables will eventually run out given enough additions/removals, but hey,
at least it's simple.
But there is a bigger concern which needs to be addressed, and that is
our support for SWITCHDEV_OBJ_ID_HOST_MDB. DSA simply translates such an
object into a dsa_port_host_mdb_add() which ends up as ds->ops->port_mdb_add()
on the upstream port, and a similar thing happens on deletion:
dsa_port_host_mdb_del() will trigger ds->ops->port_mdb_del() on the
upstream port.
When there are 2 VLAN-unaware bridges spanning the same switch (which is
a use case DSA proudly supports), each bridge will install its own
SWITCHDEV_OBJ_ID_HOST_MDB entries. But upon deletion, DSA goes ahead and
emits a DSA_NOTIFIER_MDB_DEL for dp->cpu_dp, which is shared between the
user ports enslaved to br0 and the user ports enslaved to br1. Not good.
The host-trapped multicast addresses installed by br1 will be deleted
when any state changes in br0 (IGMP timers expire, or ports leave, etc).
To avoid this, we could of course go the route of the zero-sum game and
delete the DSA_NOTIFIER_MDB_DEL call for dp->cpu_dp. But the better
design is to just admit that on shared ports like DSA links and CPU
ports, we should be reference counting calls, even if this consumes some
dynamic memory which DSA has traditionally avoided. On the flip side,
the hardware tables of switches are limited in size, so it would be good
if the OS managed them properly instead of having them eventually
overflow.
To address the memory usage concern, we only apply the refcounting of
MDB entries on ports that are really shared (CPU ports and DSA links)
and not on user ports. In a typical single-switch setup, this means only
the CPU port (and the host MDB entries are not that many, really).
The name of the newly introduced data structures (dsa_mac_addr) is
chosen in such a way that will be reusable for host FDB entries (next
patch).
With this change, we can finally have the same matching logic for the
MDB additions and deletions, as well as for their host-trapped variants.
Signed-off-by: Vladimir Oltean <vladimir.oltean@nxp.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
2021-06-29 22:06:50 +08:00
|
|
|
static struct dsa_mac_addr *dsa_mac_addr_find(struct list_head *addr_list,
|
|
|
|
|
const unsigned char *addr,
|
|
|
|
|
u16 vid)
|
|
|
|
|
{
|
|
|
|
|
struct dsa_mac_addr *a;
|
|
|
|
|
|
|
|
|
|
list_for_each_entry(a, addr_list, list)
|
|
|
|
|
if (ether_addr_equal(a->addr, addr) && a->vid == vid)
|
|
|
|
|
return a;
|
|
|
|
|
|
|
|
|
|
return NULL;
|
|
|
|
|
}
|
|
|
|
|
|
|
|
|
|
static int dsa_switch_do_mdb_add(struct dsa_switch *ds, int port,
|
|
|
|
|
const struct switchdev_obj_port_mdb *mdb)
|
|
|
|
|
{
|
|
|
|
|
struct dsa_port *dp = dsa_to_port(ds, port);
|
|
|
|
|
struct dsa_mac_addr *a;
|
|
|
|
|
int err;
|
|
|
|
|
|
|
|
|
|
/* No need to bother with refcounting for user ports */
|
|
|
|
|
if (!(dsa_port_is_cpu(dp) || dsa_port_is_dsa(dp)))
|
|
|
|
|
return ds->ops->port_mdb_add(ds, port, mdb);
|
|
|
|
|
|
|
|
|
|
a = dsa_mac_addr_find(&dp->mdbs, mdb->addr, mdb->vid);
|
|
|
|
|
if (a) {
|
|
|
|
|
refcount_inc(&a->refcount);
|
|
|
|
|
return 0;
|
|
|
|
|
}
|
|
|
|
|
|
|
|
|
|
a = kzalloc(sizeof(*a), GFP_KERNEL);
|
|
|
|
|
if (!a)
|
|
|
|
|
return -ENOMEM;
|
|
|
|
|
|
|
|
|
|
err = ds->ops->port_mdb_add(ds, port, mdb);
|
|
|
|
|
if (err) {
|
|
|
|
|
kfree(a);
|
|
|
|
|
return err;
|
|
|
|
|
}
|
|
|
|
|
|
|
|
|
|
ether_addr_copy(a->addr, mdb->addr);
|
|
|
|
|
a->vid = mdb->vid;
|
|
|
|
|
refcount_set(&a->refcount, 1);
|
|
|
|
|
list_add_tail(&a->list, &dp->mdbs);
|
|
|
|
|
|
|
|
|
|
return 0;
|
|
|
|
|
}
|
|
|
|
|
|
|
|
|
|
static int dsa_switch_do_mdb_del(struct dsa_switch *ds, int port,
|
|
|
|
|
const struct switchdev_obj_port_mdb *mdb)
|
|
|
|
|
{
|
|
|
|
|
struct dsa_port *dp = dsa_to_port(ds, port);
|
|
|
|
|
struct dsa_mac_addr *a;
|
|
|
|
|
int err;
|
|
|
|
|
|
|
|
|
|
/* No need to bother with refcounting for user ports */
|
|
|
|
|
if (!(dsa_port_is_cpu(dp) || dsa_port_is_dsa(dp)))
|
|
|
|
|
return ds->ops->port_mdb_del(ds, port, mdb);
|
|
|
|
|
|
|
|
|
|
a = dsa_mac_addr_find(&dp->mdbs, mdb->addr, mdb->vid);
|
|
|
|
|
if (!a)
|
|
|
|
|
return -ENOENT;
|
|
|
|
|
|
|
|
|
|
if (!refcount_dec_and_test(&a->refcount))
|
|
|
|
|
return 0;
|
|
|
|
|
|
|
|
|
|
err = ds->ops->port_mdb_del(ds, port, mdb);
|
|
|
|
|
if (err) {
|
|
|
|
|
refcount_inc(&a->refcount);
|
|
|
|
|
return err;
|
|
|
|
|
}
|
|
|
|
|
|
|
|
|
|
list_del(&a->list);
|
|
|
|
|
kfree(a);
|
|
|
|
|
|
|
|
|
|
return 0;
|
|
|
|
|
}
|
|
|
|
|
|
2021-06-29 22:06:52 +08:00
|
|
|
static int dsa_switch_do_fdb_add(struct dsa_switch *ds, int port,
|
|
|
|
|
const unsigned char *addr, u16 vid)
|
|
|
|
|
{
|
|
|
|
|
struct dsa_port *dp = dsa_to_port(ds, port);
|
|
|
|
|
struct dsa_mac_addr *a;
|
|
|
|
|
int err;
|
|
|
|
|
|
|
|
|
|
/* No need to bother with refcounting for user ports */
|
|
|
|
|
if (!(dsa_port_is_cpu(dp) || dsa_port_is_dsa(dp)))
|
|
|
|
|
return ds->ops->port_fdb_add(ds, port, addr, vid);
|
|
|
|
|
|
|
|
|
|
a = dsa_mac_addr_find(&dp->fdbs, addr, vid);
|
|
|
|
|
if (a) {
|
|
|
|
|
refcount_inc(&a->refcount);
|
|
|
|
|
return 0;
|
|
|
|
|
}
|
|
|
|
|
|
|
|
|
|
a = kzalloc(sizeof(*a), GFP_KERNEL);
|
|
|
|
|
if (!a)
|
|
|
|
|
return -ENOMEM;
|
|
|
|
|
|
|
|
|
|
err = ds->ops->port_fdb_add(ds, port, addr, vid);
|
|
|
|
|
if (err) {
|
|
|
|
|
kfree(a);
|
|
|
|
|
return err;
|
|
|
|
|
}
|
|
|
|
|
|
|
|
|
|
ether_addr_copy(a->addr, addr);
|
|
|
|
|
a->vid = vid;
|
|
|
|
|
refcount_set(&a->refcount, 1);
|
|
|
|
|
list_add_tail(&a->list, &dp->fdbs);
|
|
|
|
|
|
|
|
|
|
return 0;
|
|
|
|
|
}
|
|
|
|
|
|
|
|
|
|
static int dsa_switch_do_fdb_del(struct dsa_switch *ds, int port,
|
|
|
|
|
const unsigned char *addr, u16 vid)
|
|
|
|
|
{
|
|
|
|
|
struct dsa_port *dp = dsa_to_port(ds, port);
|
|
|
|
|
struct dsa_mac_addr *a;
|
|
|
|
|
int err;
|
|
|
|
|
|
|
|
|
|
/* No need to bother with refcounting for user ports */
|
|
|
|
|
if (!(dsa_port_is_cpu(dp) || dsa_port_is_dsa(dp)))
|
|
|
|
|
return ds->ops->port_fdb_del(ds, port, addr, vid);
|
|
|
|
|
|
|
|
|
|
a = dsa_mac_addr_find(&dp->fdbs, addr, vid);
|
|
|
|
|
if (!a)
|
|
|
|
|
return -ENOENT;
|
|
|
|
|
|
|
|
|
|
if (!refcount_dec_and_test(&a->refcount))
|
|
|
|
|
return 0;
|
|
|
|
|
|
|
|
|
|
err = ds->ops->port_fdb_del(ds, port, addr, vid);
|
|
|
|
|
if (err) {
|
|
|
|
|
refcount_inc(&a->refcount);
|
|
|
|
|
return err;
|
|
|
|
|
}
|
|
|
|
|
|
|
|
|
|
list_del(&a->list);
|
|
|
|
|
kfree(a);
|
|
|
|
|
|
|
|
|
|
return 0;
|
|
|
|
|
}
|
|
|
|
|
|
2021-06-29 22:06:51 +08:00
|
|
|
static int dsa_switch_host_fdb_add(struct dsa_switch *ds,
|
|
|
|
|
struct dsa_notifier_fdb_info *info)
|
|
|
|
|
{
|
|
|
|
|
int err = 0;
|
|
|
|
|
int port;
|
|
|
|
|
|
|
|
|
|
if (!ds->ops->port_fdb_add)
|
|
|
|
|
return -EOPNOTSUPP;
|
|
|
|
|
|
|
|
|
|
for (port = 0; port < ds->num_ports; port++) {
|
|
|
|
|
if (dsa_switch_host_address_match(ds, port, info->sw_index,
|
|
|
|
|
info->port)) {
|
2021-06-29 22:06:52 +08:00
|
|
|
err = dsa_switch_do_fdb_add(ds, port, info->addr,
|
2021-06-29 22:06:51 +08:00
|
|
|
info->vid);
|
|
|
|
|
if (err)
|
|
|
|
|
break;
|
|
|
|
|
}
|
|
|
|
|
}
|
|
|
|
|
|
|
|
|
|
return err;
|
|
|
|
|
}
|
|
|
|
|
|
|
|
|
|
static int dsa_switch_host_fdb_del(struct dsa_switch *ds,
|
|
|
|
|
struct dsa_notifier_fdb_info *info)
|
|
|
|
|
{
|
2021-06-29 22:06:52 +08:00
|
|
|
int err = 0;
|
|
|
|
|
int port;
|
|
|
|
|
|
2021-06-29 22:06:51 +08:00
|
|
|
if (!ds->ops->port_fdb_del)
|
|
|
|
|
return -EOPNOTSUPP;
|
|
|
|
|
|
2021-06-29 22:06:52 +08:00
|
|
|
for (port = 0; port < ds->num_ports; port++) {
|
|
|
|
|
if (dsa_switch_host_address_match(ds, port, info->sw_index,
|
|
|
|
|
info->port)) {
|
|
|
|
|
err = dsa_switch_do_fdb_del(ds, port, info->addr,
|
|
|
|
|
info->vid);
|
|
|
|
|
if (err)
|
|
|
|
|
break;
|
|
|
|
|
}
|
|
|
|
|
}
|
2021-06-29 22:06:51 +08:00
|
|
|
|
2021-06-29 22:06:52 +08:00
|
|
|
return err;
|
2021-06-29 22:06:51 +08:00
|
|
|
}
|
|
|
|
|
|
2017-05-20 05:00:53 +08:00
|
|
|
static int dsa_switch_fdb_add(struct dsa_switch *ds,
|
|
|
|
|
struct dsa_notifier_fdb_info *info)
|
|
|
|
|
{
|
2017-12-01 01:56:43 +08:00
|
|
|
int port = dsa_towards_port(ds, info->sw_index, info->port);
|
2017-05-20 05:00:53 +08:00
|
|
|
|
2017-08-06 21:15:40 +08:00
|
|
|
if (!ds->ops->port_fdb_add)
|
|
|
|
|
return -EOPNOTSUPP;
|
2017-05-20 05:00:53 +08:00
|
|
|
|
2021-06-29 22:06:52 +08:00
|
|
|
return dsa_switch_do_fdb_add(ds, port, info->addr, info->vid);
|
2017-05-20 05:00:53 +08:00
|
|
|
}
|
|
|
|
|
|
|
|
|
|
static int dsa_switch_fdb_del(struct dsa_switch *ds,
|
|
|
|
|
struct dsa_notifier_fdb_info *info)
|
|
|
|
|
{
|
2017-12-01 01:56:43 +08:00
|
|
|
int port = dsa_towards_port(ds, info->sw_index, info->port);
|
2017-05-20 05:00:53 +08:00
|
|
|
|
|
|
|
|
if (!ds->ops->port_fdb_del)
|
|
|
|
|
return -EOPNOTSUPP;
|
|
|
|
|
|
2021-06-29 22:06:52 +08:00
|
|
|
return dsa_switch_do_fdb_del(ds, port, info->addr, info->vid);
|
2017-05-20 05:00:53 +08:00
|
|
|
}
|
|
|
|
|
|
2021-02-10 09:02:12 +08:00
|
|
|
static int dsa_switch_hsr_join(struct dsa_switch *ds,
|
|
|
|
|
struct dsa_notifier_hsr_info *info)
|
|
|
|
|
{
|
|
|
|
|
if (ds->index == info->sw_index && ds->ops->port_hsr_join)
|
|
|
|
|
return ds->ops->port_hsr_join(ds, info->port, info->hsr);
|
|
|
|
|
|
|
|
|
|
return -EOPNOTSUPP;
|
|
|
|
|
}
|
|
|
|
|
|
|
|
|
|
static int dsa_switch_hsr_leave(struct dsa_switch *ds,
|
|
|
|
|
struct dsa_notifier_hsr_info *info)
|
|
|
|
|
{
|
|
|
|
|
if (ds->index == info->sw_index && ds->ops->port_hsr_leave)
|
|
|
|
|
return ds->ops->port_hsr_leave(ds, info->port, info->hsr);
|
|
|
|
|
|
|
|
|
|
return -EOPNOTSUPP;
|
|
|
|
|
}
|
|
|
|
|
|
2021-01-13 16:42:53 +08:00
|
|
|
static int dsa_switch_lag_change(struct dsa_switch *ds,
|
|
|
|
|
struct dsa_notifier_lag_info *info)
|
|
|
|
|
{
|
|
|
|
|
if (ds->index == info->sw_index && ds->ops->port_lag_change)
|
|
|
|
|
return ds->ops->port_lag_change(ds, info->port);
|
|
|
|
|
|
|
|
|
|
if (ds->index != info->sw_index && ds->ops->crosschip_lag_change)
|
|
|
|
|
return ds->ops->crosschip_lag_change(ds, info->sw_index,
|
|
|
|
|
info->port);
|
|
|
|
|
|
|
|
|
|
return 0;
|
|
|
|
|
}
|
|
|
|
|
|
|
|
|
|
static int dsa_switch_lag_join(struct dsa_switch *ds,
|
|
|
|
|
struct dsa_notifier_lag_info *info)
|
|
|
|
|
{
|
|
|
|
|
if (ds->index == info->sw_index && ds->ops->port_lag_join)
|
|
|
|
|
return ds->ops->port_lag_join(ds, info->port, info->lag,
|
|
|
|
|
info->info);
|
|
|
|
|
|
|
|
|
|
if (ds->index != info->sw_index && ds->ops->crosschip_lag_join)
|
|
|
|
|
return ds->ops->crosschip_lag_join(ds, info->sw_index,
|
|
|
|
|
info->port, info->lag,
|
|
|
|
|
info->info);
|
|
|
|
|
|
2021-06-30 04:32:15 +08:00
|
|
|
return -EOPNOTSUPP;
|
2021-01-13 16:42:53 +08:00
|
|
|
}
|
|
|
|
|
|
|
|
|
|
static int dsa_switch_lag_leave(struct dsa_switch *ds,
|
|
|
|
|
struct dsa_notifier_lag_info *info)
|
|
|
|
|
{
|
|
|
|
|
if (ds->index == info->sw_index && ds->ops->port_lag_leave)
|
|
|
|
|
return ds->ops->port_lag_leave(ds, info->port, info->lag);
|
|
|
|
|
|
|
|
|
|
if (ds->index != info->sw_index && ds->ops->crosschip_lag_leave)
|
|
|
|
|
return ds->ops->crosschip_lag_leave(ds, info->sw_index,
|
|
|
|
|
info->port, info->lag);
|
|
|
|
|
|
2021-06-30 04:32:15 +08:00
|
|
|
return -EOPNOTSUPP;
|
2021-01-13 16:42:53 +08:00
|
|
|
}
|
|
|
|
|
|
net: switchdev: remove the transaction structure from port object notifiers
Since the introduction of the switchdev API, port objects were
transmitted to drivers for offloading using a two-step transactional
model, with a prepare phase that was supposed to catch all errors, and a
commit phase that was supposed to never fail.
Some classes of failures can never be avoided, like hardware access, or
memory allocation. In the latter case, merely attempting to move the
memory allocation to the preparation phase makes it impossible to avoid
memory leaks, since commit 91cf8eceffc1 ("switchdev: Remove unused
transaction item queue") which has removed the unused mechanism of
passing on the allocated memory between one phase and another.
It is time we admit that separating the preparation from the commit
phase is something that is best left for the driver to decide, and not
something that should be baked into the API, especially since there are
no switchdev callers that depend on this.
This patch removes the struct switchdev_trans member from switchdev port
object notifier structures, and converts drivers to not look at this
member.
Where driver conversion is trivial (like in the case of the Marvell
Prestera driver, NXP DPAA2 switch, TI CPSW, and Rocker drivers), it is
done in this patch.
Where driver conversion needs more attention (DSA, Mellanox Spectrum),
the conversion is left for subsequent patches and here we only fake the
prepare/commit phases at a lower level, just not in the switchdev
notifier itself.
Where the code has a natural structure that is best left alone as a
preparation and a commit phase (as in the case of the Ocelot switch),
that structure is left in place, just made to not depend upon the
switchdev transactional model.
Signed-off-by: Vladimir Oltean <vladimir.oltean@nxp.com>
Reviewed-by: Florian Fainelli <f.fainelli@gmail.com>
Acked-by: Linus Walleij <linus.walleij@linaro.org>
Acked-by: Jiri Pirko <jiri@nvidia.com>
Reviewed-by: Ido Schimmel <idosch@nvidia.com>
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
2021-01-09 08:01:48 +08:00
|
|
|
static int dsa_switch_mdb_add(struct dsa_switch *ds,
|
|
|
|
|
struct dsa_notifier_mdb_info *info)
|
2017-12-01 00:24:00 +08:00
|
|
|
{
|
net: dsa: execute dsa_switch_mdb_add only for routing port in cross-chip topologies
Currently, the notifier for adding a multicast MAC address matches on
the targeted port and on all DSA links in the system, be they upstream
or downstream links.
This leads to a considerable amount of useless traffic.
Consider this daisy chain topology, and a MDB add notifier emitted on
sw0p0. It matches on sw0p0, sw0p3, sw1p3 and sw2p4.
sw0p0 sw0p1 sw0p2 sw0p3 sw0p4
[ user ] [ user ] [ user ] [ dsa ] [ cpu ]
[ x ] [ ] [ ] [ x ] [ ]
|
+---------+
|
sw1p0 sw1p1 sw1p2 sw1p3 sw1p4
[ user ] [ user ] [ user ] [ dsa ] [ dsa ]
[ ] [ ] [ ] [ x ] [ x ]
|
+---------+
|
sw2p0 sw2p1 sw2p2 sw2p3 sw2p4
[ user ] [ user ] [ user ] [ user ] [ dsa ]
[ ] [ ] [ ] [ ] [ x ]
But switch 0 has no reason to send the multicast traffic for that MAC
address on sw0p3, which is how it reaches switches 1 and 2. Those
switches don't expect, according to the user configuration, to receive
this multicast address from switch 1, and they will drop it anyway,
because the only valid destination is the port they received it on.
They only need to configure themselves to deliver that multicast address
_towards_ switch 1, where the MDB entry is installed.
Similarly, switch 1 should not send this multicast traffic towards
sw1p3, because that is how it reaches switch 2.
With this change, the heat map for this MDB notifier changes as follows:
sw0p0 sw0p1 sw0p2 sw0p3 sw0p4
[ user ] [ user ] [ user ] [ dsa ] [ cpu ]
[ x ] [ ] [ ] [ ] [ ]
|
+---------+
|
sw1p0 sw1p1 sw1p2 sw1p3 sw1p4
[ user ] [ user ] [ user ] [ dsa ] [ dsa ]
[ ] [ ] [ ] [ ] [ x ]
|
+---------+
|
sw2p0 sw2p1 sw2p2 sw2p3 sw2p4
[ user ] [ user ] [ user ] [ user ] [ dsa ]
[ ] [ ] [ ] [ ] [ x ]
Now the mdb notifier behaves the same as the fdb notifier.
Signed-off-by: Vladimir Oltean <vladimir.oltean@nxp.com>
Reviewed-by: Florian Fainelli <f.fainelli@gmail.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
2021-06-22 00:42:16 +08:00
|
|
|
int port = dsa_towards_port(ds, info->sw_index, info->port);
|
2017-12-01 00:24:00 +08:00
|
|
|
|
2021-01-09 08:01:52 +08:00
|
|
|
if (!ds->ops->port_mdb_add)
|
2017-12-01 00:24:00 +08:00
|
|
|
return -EOPNOTSUPP;
|
|
|
|
|
|
net: dsa: reference count the MDB entries at the cross-chip notifier level
Ever since the cross-chip notifiers were introduced, the design was
meant to be simplistic and just get the job done without worrying too
much about dangling resources left behind.
For example, somebody installs an MDB entry on sw0p0 in this daisy chain
topology. It gets installed using ds->ops->port_mdb_add() on sw0p0,
sw1p4 and sw2p4.
|
sw0p0 sw0p1 sw0p2 sw0p3 sw0p4
[ user ] [ user ] [ user ] [ dsa ] [ cpu ]
[ x ] [ ] [ ] [ ] [ ]
|
+---------+
|
sw1p0 sw1p1 sw1p2 sw1p3 sw1p4
[ user ] [ user ] [ user ] [ dsa ] [ dsa ]
[ ] [ ] [ ] [ ] [ x ]
|
+---------+
|
sw2p0 sw2p1 sw2p2 sw2p3 sw2p4
[ user ] [ user ] [ user ] [ user ] [ dsa ]
[ ] [ ] [ ] [ ] [ x ]
Then the same person deletes that MDB entry. The cross-chip notifier for
deletion only matches sw0p0:
|
sw0p0 sw0p1 sw0p2 sw0p3 sw0p4
[ user ] [ user ] [ user ] [ dsa ] [ cpu ]
[ x ] [ ] [ ] [ ] [ ]
|
+---------+
|
sw1p0 sw1p1 sw1p2 sw1p3 sw1p4
[ user ] [ user ] [ user ] [ dsa ] [ dsa ]
[ ] [ ] [ ] [ ] [ ]
|
+---------+
|
sw2p0 sw2p1 sw2p2 sw2p3 sw2p4
[ user ] [ user ] [ user ] [ user ] [ dsa ]
[ ] [ ] [ ] [ ] [ ]
Why?
Because the DSA links are 'trunk' ports, if we just go ahead and delete
the MDB from sw1p4 and sw2p4 directly, we might delete those multicast
entries when they are still needed. Just consider the fact that somebody
does:
- add a multicast MAC address towards sw0p0 [ via the cross-chip
notifiers it gets installed on the DSA links too ]
- add the same multicast MAC address towards sw0p1 (another port of that
same switch)
- delete the same multicast MAC address from sw0p0.
At this point, if we deleted the MAC address from the DSA links, it
would be flooded, even though there is still an entry on switch 0 which
needs it not to.
So that is why deletions only match the targeted source port and nothing
on DSA links. Of course, dangling resources means that the hardware
tables will eventually run out given enough additions/removals, but hey,
at least it's simple.
But there is a bigger concern which needs to be addressed, and that is
our support for SWITCHDEV_OBJ_ID_HOST_MDB. DSA simply translates such an
object into a dsa_port_host_mdb_add() which ends up as ds->ops->port_mdb_add()
on the upstream port, and a similar thing happens on deletion:
dsa_port_host_mdb_del() will trigger ds->ops->port_mdb_del() on the
upstream port.
When there are 2 VLAN-unaware bridges spanning the same switch (which is
a use case DSA proudly supports), each bridge will install its own
SWITCHDEV_OBJ_ID_HOST_MDB entries. But upon deletion, DSA goes ahead and
emits a DSA_NOTIFIER_MDB_DEL for dp->cpu_dp, which is shared between the
user ports enslaved to br0 and the user ports enslaved to br1. Not good.
The host-trapped multicast addresses installed by br1 will be deleted
when any state changes in br0 (IGMP timers expire, or ports leave, etc).
To avoid this, we could of course go the route of the zero-sum game and
delete the DSA_NOTIFIER_MDB_DEL call for dp->cpu_dp. But the better
design is to just admit that on shared ports like DSA links and CPU
ports, we should be reference counting calls, even if this consumes some
dynamic memory which DSA has traditionally avoided. On the flip side,
the hardware tables of switches are limited in size, so it would be good
if the OS managed them properly instead of having them eventually
overflow.
To address the memory usage concern, we only apply the refcounting of
MDB entries on ports that are really shared (CPU ports and DSA links)
and not on user ports. In a typical single-switch setup, this means only
the CPU port (and the host MDB entries are not that many, really).
The name of the newly introduced data structures (dsa_mac_addr) is
chosen in such a way that will be reusable for host FDB entries (next
patch).
With this change, we can finally have the same matching logic for the
MDB additions and deletions, as well as for their host-trapped variants.
Signed-off-by: Vladimir Oltean <vladimir.oltean@nxp.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
2021-06-29 22:06:50 +08:00
|
|
|
return dsa_switch_do_mdb_add(ds, port, info->mdb);
|
2017-05-20 05:00:54 +08:00
|
|
|
}
|
|
|
|
|
|
|
|
|
|
static int dsa_switch_mdb_del(struct dsa_switch *ds,
|
|
|
|
|
struct dsa_notifier_mdb_info *info)
|
|
|
|
|
{
|
net: dsa: reference count the MDB entries at the cross-chip notifier level
Ever since the cross-chip notifiers were introduced, the design was
meant to be simplistic and just get the job done without worrying too
much about dangling resources left behind.
For example, somebody installs an MDB entry on sw0p0 in this daisy chain
topology. It gets installed using ds->ops->port_mdb_add() on sw0p0,
sw1p4 and sw2p4.
|
sw0p0 sw0p1 sw0p2 sw0p3 sw0p4
[ user ] [ user ] [ user ] [ dsa ] [ cpu ]
[ x ] [ ] [ ] [ ] [ ]
|
+---------+
|
sw1p0 sw1p1 sw1p2 sw1p3 sw1p4
[ user ] [ user ] [ user ] [ dsa ] [ dsa ]
[ ] [ ] [ ] [ ] [ x ]
|
+---------+
|
sw2p0 sw2p1 sw2p2 sw2p3 sw2p4
[ user ] [ user ] [ user ] [ user ] [ dsa ]
[ ] [ ] [ ] [ ] [ x ]
Then the same person deletes that MDB entry. The cross-chip notifier for
deletion only matches sw0p0:
|
sw0p0 sw0p1 sw0p2 sw0p3 sw0p4
[ user ] [ user ] [ user ] [ dsa ] [ cpu ]
[ x ] [ ] [ ] [ ] [ ]
|
+---------+
|
sw1p0 sw1p1 sw1p2 sw1p3 sw1p4
[ user ] [ user ] [ user ] [ dsa ] [ dsa ]
[ ] [ ] [ ] [ ] [ ]
|
+---------+
|
sw2p0 sw2p1 sw2p2 sw2p3 sw2p4
[ user ] [ user ] [ user ] [ user ] [ dsa ]
[ ] [ ] [ ] [ ] [ ]
Why?
Because the DSA links are 'trunk' ports, if we just go ahead and delete
the MDB from sw1p4 and sw2p4 directly, we might delete those multicast
entries when they are still needed. Just consider the fact that somebody
does:
- add a multicast MAC address towards sw0p0 [ via the cross-chip
notifiers it gets installed on the DSA links too ]
- add the same multicast MAC address towards sw0p1 (another port of that
same switch)
- delete the same multicast MAC address from sw0p0.
At this point, if we deleted the MAC address from the DSA links, it
would be flooded, even though there is still an entry on switch 0 which
needs it not to.
So that is why deletions only match the targeted source port and nothing
on DSA links. Of course, dangling resources means that the hardware
tables will eventually run out given enough additions/removals, but hey,
at least it's simple.
But there is a bigger concern which needs to be addressed, and that is
our support for SWITCHDEV_OBJ_ID_HOST_MDB. DSA simply translates such an
object into a dsa_port_host_mdb_add() which ends up as ds->ops->port_mdb_add()
on the upstream port, and a similar thing happens on deletion:
dsa_port_host_mdb_del() will trigger ds->ops->port_mdb_del() on the
upstream port.
When there are 2 VLAN-unaware bridges spanning the same switch (which is
a use case DSA proudly supports), each bridge will install its own
SWITCHDEV_OBJ_ID_HOST_MDB entries. But upon deletion, DSA goes ahead and
emits a DSA_NOTIFIER_MDB_DEL for dp->cpu_dp, which is shared between the
user ports enslaved to br0 and the user ports enslaved to br1. Not good.
The host-trapped multicast addresses installed by br1 will be deleted
when any state changes in br0 (IGMP timers expire, or ports leave, etc).
To avoid this, we could of course go the route of the zero-sum game and
delete the DSA_NOTIFIER_MDB_DEL call for dp->cpu_dp. But the better
design is to just admit that on shared ports like DSA links and CPU
ports, we should be reference counting calls, even if this consumes some
dynamic memory which DSA has traditionally avoided. On the flip side,
the hardware tables of switches are limited in size, so it would be good
if the OS managed them properly instead of having them eventually
overflow.
To address the memory usage concern, we only apply the refcounting of
MDB entries on ports that are really shared (CPU ports and DSA links)
and not on user ports. In a typical single-switch setup, this means only
the CPU port (and the host MDB entries are not that many, really).
The name of the newly introduced data structures (dsa_mac_addr) is
chosen in such a way that will be reusable for host FDB entries (next
patch).
With this change, we can finally have the same matching logic for the
MDB additions and deletions, as well as for their host-trapped variants.
Signed-off-by: Vladimir Oltean <vladimir.oltean@nxp.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
2021-06-29 22:06:50 +08:00
|
|
|
int port = dsa_towards_port(ds, info->sw_index, info->port);
|
|
|
|
|
|
2017-05-20 05:00:54 +08:00
|
|
|
if (!ds->ops->port_mdb_del)
|
|
|
|
|
return -EOPNOTSUPP;
|
|
|
|
|
|
net: dsa: reference count the MDB entries at the cross-chip notifier level
Ever since the cross-chip notifiers were introduced, the design was
meant to be simplistic and just get the job done without worrying too
much about dangling resources left behind.
For example, somebody installs an MDB entry on sw0p0 in this daisy chain
topology. It gets installed using ds->ops->port_mdb_add() on sw0p0,
sw1p4 and sw2p4.
|
sw0p0 sw0p1 sw0p2 sw0p3 sw0p4
[ user ] [ user ] [ user ] [ dsa ] [ cpu ]
[ x ] [ ] [ ] [ ] [ ]
|
+---------+
|
sw1p0 sw1p1 sw1p2 sw1p3 sw1p4
[ user ] [ user ] [ user ] [ dsa ] [ dsa ]
[ ] [ ] [ ] [ ] [ x ]
|
+---------+
|
sw2p0 sw2p1 sw2p2 sw2p3 sw2p4
[ user ] [ user ] [ user ] [ user ] [ dsa ]
[ ] [ ] [ ] [ ] [ x ]
Then the same person deletes that MDB entry. The cross-chip notifier for
deletion only matches sw0p0:
|
sw0p0 sw0p1 sw0p2 sw0p3 sw0p4
[ user ] [ user ] [ user ] [ dsa ] [ cpu ]
[ x ] [ ] [ ] [ ] [ ]
|
+---------+
|
sw1p0 sw1p1 sw1p2 sw1p3 sw1p4
[ user ] [ user ] [ user ] [ dsa ] [ dsa ]
[ ] [ ] [ ] [ ] [ ]
|
+---------+
|
sw2p0 sw2p1 sw2p2 sw2p3 sw2p4
[ user ] [ user ] [ user ] [ user ] [ dsa ]
[ ] [ ] [ ] [ ] [ ]
Why?
Because the DSA links are 'trunk' ports, if we just go ahead and delete
the MDB from sw1p4 and sw2p4 directly, we might delete those multicast
entries when they are still needed. Just consider the fact that somebody
does:
- add a multicast MAC address towards sw0p0 [ via the cross-chip
notifiers it gets installed on the DSA links too ]
- add the same multicast MAC address towards sw0p1 (another port of that
same switch)
- delete the same multicast MAC address from sw0p0.
At this point, if we deleted the MAC address from the DSA links, it
would be flooded, even though there is still an entry on switch 0 which
needs it not to.
So that is why deletions only match the targeted source port and nothing
on DSA links. Of course, dangling resources means that the hardware
tables will eventually run out given enough additions/removals, but hey,
at least it's simple.
But there is a bigger concern which needs to be addressed, and that is
our support for SWITCHDEV_OBJ_ID_HOST_MDB. DSA simply translates such an
object into a dsa_port_host_mdb_add() which ends up as ds->ops->port_mdb_add()
on the upstream port, and a similar thing happens on deletion:
dsa_port_host_mdb_del() will trigger ds->ops->port_mdb_del() on the
upstream port.
When there are 2 VLAN-unaware bridges spanning the same switch (which is
a use case DSA proudly supports), each bridge will install its own
SWITCHDEV_OBJ_ID_HOST_MDB entries. But upon deletion, DSA goes ahead and
emits a DSA_NOTIFIER_MDB_DEL for dp->cpu_dp, which is shared between the
user ports enslaved to br0 and the user ports enslaved to br1. Not good.
The host-trapped multicast addresses installed by br1 will be deleted
when any state changes in br0 (IGMP timers expire, or ports leave, etc).
To avoid this, we could of course go the route of the zero-sum game and
delete the DSA_NOTIFIER_MDB_DEL call for dp->cpu_dp. But the better
design is to just admit that on shared ports like DSA links and CPU
ports, we should be reference counting calls, even if this consumes some
dynamic memory which DSA has traditionally avoided. On the flip side,
the hardware tables of switches are limited in size, so it would be good
if the OS managed them properly instead of having them eventually
overflow.
To address the memory usage concern, we only apply the refcounting of
MDB entries on ports that are really shared (CPU ports and DSA links)
and not on user ports. In a typical single-switch setup, this means only
the CPU port (and the host MDB entries are not that many, really).
The name of the newly introduced data structures (dsa_mac_addr) is
chosen in such a way that will be reusable for host FDB entries (next
patch).
With this change, we can finally have the same matching logic for the
MDB additions and deletions, as well as for their host-trapped variants.
Signed-off-by: Vladimir Oltean <vladimir.oltean@nxp.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
2021-06-29 22:06:50 +08:00
|
|
|
return dsa_switch_do_mdb_del(ds, port, info->mdb);
|
2017-05-20 05:00:54 +08:00
|
|
|
}
|
|
|
|
|
|
net: dsa: introduce a separate cross-chip notifier type for host MDBs
Commit abd49535c380 ("net: dsa: execute dsa_switch_mdb_add only for
routing port in cross-chip topologies") does a surprisingly good job
even for the SWITCHDEV_OBJ_ID_HOST_MDB use case, where DSA simply
translates a switchdev object received on dp into a cross-chip notifier
for dp->cpu_dp.
To visualize how that works, imagine the daisy chain topology below and
consider a SWITCHDEV_OBJ_ID_HOST_MDB object emitted on sw2p0. How does
the cross-chip notifier know to match on all the right ports (sw0p4, the
dedicated CPU port, sw1p4, an upstream DSA link, and sw2p4, another
upstream DSA link)?
|
sw0p0 sw0p1 sw0p2 sw0p3 sw0p4
[ user ] [ user ] [ user ] [ dsa ] [ cpu ]
[ ] [ ] [ ] [ ] [ x ]
|
+---------+
|
sw1p0 sw1p1 sw1p2 sw1p3 sw1p4
[ user ] [ user ] [ user ] [ dsa ] [ dsa ]
[ ] [ ] [ ] [ ] [ x ]
|
+---------+
|
sw2p0 sw2p1 sw2p2 sw2p3 sw2p4
[ user ] [ user ] [ user ] [ user ] [ dsa ]
[ ] [ ] [ ] [ ] [ x ]
The answer is simple: the dedicated CPU port of sw2p0 is sw0p4, and
dsa_routing_port returns the upstream port for all switches.
That is fine, but there are other topologies where this does not work as
well. There are trees with "H" topologies in the wild, where there are 2
or more switches with DSA links between them, but every switch has its
dedicated CPU port. For these topologies, it seems stupid for the neighbor
switches to install an MDB entry on the routing port, since these
multicast addresses are fundamentally different than the usual ones we
support (and that is the justification for this patch, to introduce the
concept of a termination plane multicast MAC address, as opposed to a
forwarding plane multicast MAC address).
For example, when a SWITCHDEV_OBJ_ID_HOST_MDB would get added to sw0p0,
without this patch, it would get treated as a regular port MDB on sw0p2
and it would match on the ports below (including the sw1p3 routing port).
| |
sw0p0 sw0p1 sw0p2 sw0p3 sw1p3 sw1p2 sw1p1 sw1p0
[ user ] [ user ] [ cpu ] [ dsa ] [ dsa ] [ cpu ] [ user ] [ user ]
[ ] [ ] [ x ] [ ] ---- [ x ] [ ] [ ] [ ]
With the patch, the host MDB notifier on sw0p0 matches only on the local
switch, which is what we want for a termination plane address.
| |
sw0p0 sw0p1 sw0p2 sw0p3 sw1p3 sw1p2 sw1p1 sw1p0
[ user ] [ user ] [ cpu ] [ dsa ] [ dsa ] [ cpu ] [ user ] [ user ]
[ ] [ ] [ x ] [ ] ---- [ ] [ ] [ ] [ ]
Name this new matching function "dsa_switch_host_address_match" since we
will be reusing it soon for host FDB entries as well.
Signed-off-by: Vladimir Oltean <vladimir.oltean@nxp.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
2021-06-29 22:06:49 +08:00
|
|
|
static int dsa_switch_host_mdb_add(struct dsa_switch *ds,
|
|
|
|
|
struct dsa_notifier_mdb_info *info)
|
|
|
|
|
{
|
|
|
|
|
int err = 0;
|
|
|
|
|
int port;
|
|
|
|
|
|
|
|
|
|
if (!ds->ops->port_mdb_add)
|
|
|
|
|
return -EOPNOTSUPP;
|
|
|
|
|
|
|
|
|
|
for (port = 0; port < ds->num_ports; port++) {
|
|
|
|
|
if (dsa_switch_host_address_match(ds, port, info->sw_index,
|
|
|
|
|
info->port)) {
|
net: dsa: reference count the MDB entries at the cross-chip notifier level
Ever since the cross-chip notifiers were introduced, the design was
meant to be simplistic and just get the job done without worrying too
much about dangling resources left behind.
For example, somebody installs an MDB entry on sw0p0 in this daisy chain
topology. It gets installed using ds->ops->port_mdb_add() on sw0p0,
sw1p4 and sw2p4.
|
sw0p0 sw0p1 sw0p2 sw0p3 sw0p4
[ user ] [ user ] [ user ] [ dsa ] [ cpu ]
[ x ] [ ] [ ] [ ] [ ]
|
+---------+
|
sw1p0 sw1p1 sw1p2 sw1p3 sw1p4
[ user ] [ user ] [ user ] [ dsa ] [ dsa ]
[ ] [ ] [ ] [ ] [ x ]
|
+---------+
|
sw2p0 sw2p1 sw2p2 sw2p3 sw2p4
[ user ] [ user ] [ user ] [ user ] [ dsa ]
[ ] [ ] [ ] [ ] [ x ]
Then the same person deletes that MDB entry. The cross-chip notifier for
deletion only matches sw0p0:
|
sw0p0 sw0p1 sw0p2 sw0p3 sw0p4
[ user ] [ user ] [ user ] [ dsa ] [ cpu ]
[ x ] [ ] [ ] [ ] [ ]
|
+---------+
|
sw1p0 sw1p1 sw1p2 sw1p3 sw1p4
[ user ] [ user ] [ user ] [ dsa ] [ dsa ]
[ ] [ ] [ ] [ ] [ ]
|
+---------+
|
sw2p0 sw2p1 sw2p2 sw2p3 sw2p4
[ user ] [ user ] [ user ] [ user ] [ dsa ]
[ ] [ ] [ ] [ ] [ ]
Why?
Because the DSA links are 'trunk' ports, if we just go ahead and delete
the MDB from sw1p4 and sw2p4 directly, we might delete those multicast
entries when they are still needed. Just consider the fact that somebody
does:
- add a multicast MAC address towards sw0p0 [ via the cross-chip
notifiers it gets installed on the DSA links too ]
- add the same multicast MAC address towards sw0p1 (another port of that
same switch)
- delete the same multicast MAC address from sw0p0.
At this point, if we deleted the MAC address from the DSA links, it
would be flooded, even though there is still an entry on switch 0 which
needs it not to.
So that is why deletions only match the targeted source port and nothing
on DSA links. Of course, dangling resources means that the hardware
tables will eventually run out given enough additions/removals, but hey,
at least it's simple.
But there is a bigger concern which needs to be addressed, and that is
our support for SWITCHDEV_OBJ_ID_HOST_MDB. DSA simply translates such an
object into a dsa_port_host_mdb_add() which ends up as ds->ops->port_mdb_add()
on the upstream port, and a similar thing happens on deletion:
dsa_port_host_mdb_del() will trigger ds->ops->port_mdb_del() on the
upstream port.
When there are 2 VLAN-unaware bridges spanning the same switch (which is
a use case DSA proudly supports), each bridge will install its own
SWITCHDEV_OBJ_ID_HOST_MDB entries. But upon deletion, DSA goes ahead and
emits a DSA_NOTIFIER_MDB_DEL for dp->cpu_dp, which is shared between the
user ports enslaved to br0 and the user ports enslaved to br1. Not good.
The host-trapped multicast addresses installed by br1 will be deleted
when any state changes in br0 (IGMP timers expire, or ports leave, etc).
To avoid this, we could of course go the route of the zero-sum game and
delete the DSA_NOTIFIER_MDB_DEL call for dp->cpu_dp. But the better
design is to just admit that on shared ports like DSA links and CPU
ports, we should be reference counting calls, even if this consumes some
dynamic memory which DSA has traditionally avoided. On the flip side,
the hardware tables of switches are limited in size, so it would be good
if the OS managed them properly instead of having them eventually
overflow.
To address the memory usage concern, we only apply the refcounting of
MDB entries on ports that are really shared (CPU ports and DSA links)
and not on user ports. In a typical single-switch setup, this means only
the CPU port (and the host MDB entries are not that many, really).
The name of the newly introduced data structures (dsa_mac_addr) is
chosen in such a way that will be reusable for host FDB entries (next
patch).
With this change, we can finally have the same matching logic for the
MDB additions and deletions, as well as for their host-trapped variants.
Signed-off-by: Vladimir Oltean <vladimir.oltean@nxp.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
2021-06-29 22:06:50 +08:00
|
|
|
err = dsa_switch_do_mdb_add(ds, port, info->mdb);
|
net: dsa: introduce a separate cross-chip notifier type for host MDBs
Commit abd49535c380 ("net: dsa: execute dsa_switch_mdb_add only for
routing port in cross-chip topologies") does a surprisingly good job
even for the SWITCHDEV_OBJ_ID_HOST_MDB use case, where DSA simply
translates a switchdev object received on dp into a cross-chip notifier
for dp->cpu_dp.
To visualize how that works, imagine the daisy chain topology below and
consider a SWITCHDEV_OBJ_ID_HOST_MDB object emitted on sw2p0. How does
the cross-chip notifier know to match on all the right ports (sw0p4, the
dedicated CPU port, sw1p4, an upstream DSA link, and sw2p4, another
upstream DSA link)?
|
sw0p0 sw0p1 sw0p2 sw0p3 sw0p4
[ user ] [ user ] [ user ] [ dsa ] [ cpu ]
[ ] [ ] [ ] [ ] [ x ]
|
+---------+
|
sw1p0 sw1p1 sw1p2 sw1p3 sw1p4
[ user ] [ user ] [ user ] [ dsa ] [ dsa ]
[ ] [ ] [ ] [ ] [ x ]
|
+---------+
|
sw2p0 sw2p1 sw2p2 sw2p3 sw2p4
[ user ] [ user ] [ user ] [ user ] [ dsa ]
[ ] [ ] [ ] [ ] [ x ]
The answer is simple: the dedicated CPU port of sw2p0 is sw0p4, and
dsa_routing_port returns the upstream port for all switches.
That is fine, but there are other topologies where this does not work as
well. There are trees with "H" topologies in the wild, where there are 2
or more switches with DSA links between them, but every switch has its
dedicated CPU port. For these topologies, it seems stupid for the neighbor
switches to install an MDB entry on the routing port, since these
multicast addresses are fundamentally different than the usual ones we
support (and that is the justification for this patch, to introduce the
concept of a termination plane multicast MAC address, as opposed to a
forwarding plane multicast MAC address).
For example, when a SWITCHDEV_OBJ_ID_HOST_MDB would get added to sw0p0,
without this patch, it would get treated as a regular port MDB on sw0p2
and it would match on the ports below (including the sw1p3 routing port).
| |
sw0p0 sw0p1 sw0p2 sw0p3 sw1p3 sw1p2 sw1p1 sw1p0
[ user ] [ user ] [ cpu ] [ dsa ] [ dsa ] [ cpu ] [ user ] [ user ]
[ ] [ ] [ x ] [ ] ---- [ x ] [ ] [ ] [ ]
With the patch, the host MDB notifier on sw0p0 matches only on the local
switch, which is what we want for a termination plane address.
| |
sw0p0 sw0p1 sw0p2 sw0p3 sw1p3 sw1p2 sw1p1 sw1p0
[ user ] [ user ] [ cpu ] [ dsa ] [ dsa ] [ cpu ] [ user ] [ user ]
[ ] [ ] [ x ] [ ] ---- [ ] [ ] [ ] [ ]
Name this new matching function "dsa_switch_host_address_match" since we
will be reusing it soon for host FDB entries as well.
Signed-off-by: Vladimir Oltean <vladimir.oltean@nxp.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
2021-06-29 22:06:49 +08:00
|
|
|
if (err)
|
|
|
|
|
break;
|
|
|
|
|
}
|
|
|
|
|
}
|
|
|
|
|
|
|
|
|
|
return err;
|
|
|
|
|
}
|
|
|
|
|
|
|
|
|
|
static int dsa_switch_host_mdb_del(struct dsa_switch *ds,
|
|
|
|
|
struct dsa_notifier_mdb_info *info)
|
|
|
|
|
{
|
net: dsa: reference count the MDB entries at the cross-chip notifier level
Ever since the cross-chip notifiers were introduced, the design was
meant to be simplistic and just get the job done without worrying too
much about dangling resources left behind.
For example, somebody installs an MDB entry on sw0p0 in this daisy chain
topology. It gets installed using ds->ops->port_mdb_add() on sw0p0,
sw1p4 and sw2p4.
|
sw0p0 sw0p1 sw0p2 sw0p3 sw0p4
[ user ] [ user ] [ user ] [ dsa ] [ cpu ]
[ x ] [ ] [ ] [ ] [ ]
|
+---------+
|
sw1p0 sw1p1 sw1p2 sw1p3 sw1p4
[ user ] [ user ] [ user ] [ dsa ] [ dsa ]
[ ] [ ] [ ] [ ] [ x ]
|
+---------+
|
sw2p0 sw2p1 sw2p2 sw2p3 sw2p4
[ user ] [ user ] [ user ] [ user ] [ dsa ]
[ ] [ ] [ ] [ ] [ x ]
Then the same person deletes that MDB entry. The cross-chip notifier for
deletion only matches sw0p0:
|
sw0p0 sw0p1 sw0p2 sw0p3 sw0p4
[ user ] [ user ] [ user ] [ dsa ] [ cpu ]
[ x ] [ ] [ ] [ ] [ ]
|
+---------+
|
sw1p0 sw1p1 sw1p2 sw1p3 sw1p4
[ user ] [ user ] [ user ] [ dsa ] [ dsa ]
[ ] [ ] [ ] [ ] [ ]
|
+---------+
|
sw2p0 sw2p1 sw2p2 sw2p3 sw2p4
[ user ] [ user ] [ user ] [ user ] [ dsa ]
[ ] [ ] [ ] [ ] [ ]
Why?
Because the DSA links are 'trunk' ports, if we just go ahead and delete
the MDB from sw1p4 and sw2p4 directly, we might delete those multicast
entries when they are still needed. Just consider the fact that somebody
does:
- add a multicast MAC address towards sw0p0 [ via the cross-chip
notifiers it gets installed on the DSA links too ]
- add the same multicast MAC address towards sw0p1 (another port of that
same switch)
- delete the same multicast MAC address from sw0p0.
At this point, if we deleted the MAC address from the DSA links, it
would be flooded, even though there is still an entry on switch 0 which
needs it not to.
So that is why deletions only match the targeted source port and nothing
on DSA links. Of course, dangling resources means that the hardware
tables will eventually run out given enough additions/removals, but hey,
at least it's simple.
But there is a bigger concern which needs to be addressed, and that is
our support for SWITCHDEV_OBJ_ID_HOST_MDB. DSA simply translates such an
object into a dsa_port_host_mdb_add() which ends up as ds->ops->port_mdb_add()
on the upstream port, and a similar thing happens on deletion:
dsa_port_host_mdb_del() will trigger ds->ops->port_mdb_del() on the
upstream port.
When there are 2 VLAN-unaware bridges spanning the same switch (which is
a use case DSA proudly supports), each bridge will install its own
SWITCHDEV_OBJ_ID_HOST_MDB entries. But upon deletion, DSA goes ahead and
emits a DSA_NOTIFIER_MDB_DEL for dp->cpu_dp, which is shared between the
user ports enslaved to br0 and the user ports enslaved to br1. Not good.
The host-trapped multicast addresses installed by br1 will be deleted
when any state changes in br0 (IGMP timers expire, or ports leave, etc).
To avoid this, we could of course go the route of the zero-sum game and
delete the DSA_NOTIFIER_MDB_DEL call for dp->cpu_dp. But the better
design is to just admit that on shared ports like DSA links and CPU
ports, we should be reference counting calls, even if this consumes some
dynamic memory which DSA has traditionally avoided. On the flip side,
the hardware tables of switches are limited in size, so it would be good
if the OS managed them properly instead of having them eventually
overflow.
To address the memory usage concern, we only apply the refcounting of
MDB entries on ports that are really shared (CPU ports and DSA links)
and not on user ports. In a typical single-switch setup, this means only
the CPU port (and the host MDB entries are not that many, really).
The name of the newly introduced data structures (dsa_mac_addr) is
chosen in such a way that will be reusable for host FDB entries (next
patch).
With this change, we can finally have the same matching logic for the
MDB additions and deletions, as well as for their host-trapped variants.
Signed-off-by: Vladimir Oltean <vladimir.oltean@nxp.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
2021-06-29 22:06:50 +08:00
|
|
|
int err = 0;
|
|
|
|
|
int port;
|
|
|
|
|
|
net: dsa: introduce a separate cross-chip notifier type for host MDBs
Commit abd49535c380 ("net: dsa: execute dsa_switch_mdb_add only for
routing port in cross-chip topologies") does a surprisingly good job
even for the SWITCHDEV_OBJ_ID_HOST_MDB use case, where DSA simply
translates a switchdev object received on dp into a cross-chip notifier
for dp->cpu_dp.
To visualize how that works, imagine the daisy chain topology below and
consider a SWITCHDEV_OBJ_ID_HOST_MDB object emitted on sw2p0. How does
the cross-chip notifier know to match on all the right ports (sw0p4, the
dedicated CPU port, sw1p4, an upstream DSA link, and sw2p4, another
upstream DSA link)?
|
sw0p0 sw0p1 sw0p2 sw0p3 sw0p4
[ user ] [ user ] [ user ] [ dsa ] [ cpu ]
[ ] [ ] [ ] [ ] [ x ]
|
+---------+
|
sw1p0 sw1p1 sw1p2 sw1p3 sw1p4
[ user ] [ user ] [ user ] [ dsa ] [ dsa ]
[ ] [ ] [ ] [ ] [ x ]
|
+---------+
|
sw2p0 sw2p1 sw2p2 sw2p3 sw2p4
[ user ] [ user ] [ user ] [ user ] [ dsa ]
[ ] [ ] [ ] [ ] [ x ]
The answer is simple: the dedicated CPU port of sw2p0 is sw0p4, and
dsa_routing_port returns the upstream port for all switches.
That is fine, but there are other topologies where this does not work as
well. There are trees with "H" topologies in the wild, where there are 2
or more switches with DSA links between them, but every switch has its
dedicated CPU port. For these topologies, it seems stupid for the neighbor
switches to install an MDB entry on the routing port, since these
multicast addresses are fundamentally different than the usual ones we
support (and that is the justification for this patch, to introduce the
concept of a termination plane multicast MAC address, as opposed to a
forwarding plane multicast MAC address).
For example, when a SWITCHDEV_OBJ_ID_HOST_MDB would get added to sw0p0,
without this patch, it would get treated as a regular port MDB on sw0p2
and it would match on the ports below (including the sw1p3 routing port).
| |
sw0p0 sw0p1 sw0p2 sw0p3 sw1p3 sw1p2 sw1p1 sw1p0
[ user ] [ user ] [ cpu ] [ dsa ] [ dsa ] [ cpu ] [ user ] [ user ]
[ ] [ ] [ x ] [ ] ---- [ x ] [ ] [ ] [ ]
With the patch, the host MDB notifier on sw0p0 matches only on the local
switch, which is what we want for a termination plane address.
| |
sw0p0 sw0p1 sw0p2 sw0p3 sw1p3 sw1p2 sw1p1 sw1p0
[ user ] [ user ] [ cpu ] [ dsa ] [ dsa ] [ cpu ] [ user ] [ user ]
[ ] [ ] [ x ] [ ] ---- [ ] [ ] [ ] [ ]
Name this new matching function "dsa_switch_host_address_match" since we
will be reusing it soon for host FDB entries as well.
Signed-off-by: Vladimir Oltean <vladimir.oltean@nxp.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
2021-06-29 22:06:49 +08:00
|
|
|
if (!ds->ops->port_mdb_del)
|
|
|
|
|
return -EOPNOTSUPP;
|
|
|
|
|
|
net: dsa: reference count the MDB entries at the cross-chip notifier level
Ever since the cross-chip notifiers were introduced, the design was
meant to be simplistic and just get the job done without worrying too
much about dangling resources left behind.
For example, somebody installs an MDB entry on sw0p0 in this daisy chain
topology. It gets installed using ds->ops->port_mdb_add() on sw0p0,
sw1p4 and sw2p4.
|
sw0p0 sw0p1 sw0p2 sw0p3 sw0p4
[ user ] [ user ] [ user ] [ dsa ] [ cpu ]
[ x ] [ ] [ ] [ ] [ ]
|
+---------+
|
sw1p0 sw1p1 sw1p2 sw1p3 sw1p4
[ user ] [ user ] [ user ] [ dsa ] [ dsa ]
[ ] [ ] [ ] [ ] [ x ]
|
+---------+
|
sw2p0 sw2p1 sw2p2 sw2p3 sw2p4
[ user ] [ user ] [ user ] [ user ] [ dsa ]
[ ] [ ] [ ] [ ] [ x ]
Then the same person deletes that MDB entry. The cross-chip notifier for
deletion only matches sw0p0:
|
sw0p0 sw0p1 sw0p2 sw0p3 sw0p4
[ user ] [ user ] [ user ] [ dsa ] [ cpu ]
[ x ] [ ] [ ] [ ] [ ]
|
+---------+
|
sw1p0 sw1p1 sw1p2 sw1p3 sw1p4
[ user ] [ user ] [ user ] [ dsa ] [ dsa ]
[ ] [ ] [ ] [ ] [ ]
|
+---------+
|
sw2p0 sw2p1 sw2p2 sw2p3 sw2p4
[ user ] [ user ] [ user ] [ user ] [ dsa ]
[ ] [ ] [ ] [ ] [ ]
Why?
Because the DSA links are 'trunk' ports, if we just go ahead and delete
the MDB from sw1p4 and sw2p4 directly, we might delete those multicast
entries when they are still needed. Just consider the fact that somebody
does:
- add a multicast MAC address towards sw0p0 [ via the cross-chip
notifiers it gets installed on the DSA links too ]
- add the same multicast MAC address towards sw0p1 (another port of that
same switch)
- delete the same multicast MAC address from sw0p0.
At this point, if we deleted the MAC address from the DSA links, it
would be flooded, even though there is still an entry on switch 0 which
needs it not to.
So that is why deletions only match the targeted source port and nothing
on DSA links. Of course, dangling resources means that the hardware
tables will eventually run out given enough additions/removals, but hey,
at least it's simple.
But there is a bigger concern which needs to be addressed, and that is
our support for SWITCHDEV_OBJ_ID_HOST_MDB. DSA simply translates such an
object into a dsa_port_host_mdb_add() which ends up as ds->ops->port_mdb_add()
on the upstream port, and a similar thing happens on deletion:
dsa_port_host_mdb_del() will trigger ds->ops->port_mdb_del() on the
upstream port.
When there are 2 VLAN-unaware bridges spanning the same switch (which is
a use case DSA proudly supports), each bridge will install its own
SWITCHDEV_OBJ_ID_HOST_MDB entries. But upon deletion, DSA goes ahead and
emits a DSA_NOTIFIER_MDB_DEL for dp->cpu_dp, which is shared between the
user ports enslaved to br0 and the user ports enslaved to br1. Not good.
The host-trapped multicast addresses installed by br1 will be deleted
when any state changes in br0 (IGMP timers expire, or ports leave, etc).
To avoid this, we could of course go the route of the zero-sum game and
delete the DSA_NOTIFIER_MDB_DEL call for dp->cpu_dp. But the better
design is to just admit that on shared ports like DSA links and CPU
ports, we should be reference counting calls, even if this consumes some
dynamic memory which DSA has traditionally avoided. On the flip side,
the hardware tables of switches are limited in size, so it would be good
if the OS managed them properly instead of having them eventually
overflow.
To address the memory usage concern, we only apply the refcounting of
MDB entries on ports that are really shared (CPU ports and DSA links)
and not on user ports. In a typical single-switch setup, this means only
the CPU port (and the host MDB entries are not that many, really).
The name of the newly introduced data structures (dsa_mac_addr) is
chosen in such a way that will be reusable for host FDB entries (next
patch).
With this change, we can finally have the same matching logic for the
MDB additions and deletions, as well as for their host-trapped variants.
Signed-off-by: Vladimir Oltean <vladimir.oltean@nxp.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
2021-06-29 22:06:50 +08:00
|
|
|
for (port = 0; port < ds->num_ports; port++) {
|
|
|
|
|
if (dsa_switch_host_address_match(ds, port, info->sw_index,
|
|
|
|
|
info->port)) {
|
|
|
|
|
err = dsa_switch_do_mdb_del(ds, port, info->mdb);
|
|
|
|
|
if (err)
|
|
|
|
|
break;
|
|
|
|
|
}
|
|
|
|
|
}
|
net: dsa: introduce a separate cross-chip notifier type for host MDBs
Commit abd49535c380 ("net: dsa: execute dsa_switch_mdb_add only for
routing port in cross-chip topologies") does a surprisingly good job
even for the SWITCHDEV_OBJ_ID_HOST_MDB use case, where DSA simply
translates a switchdev object received on dp into a cross-chip notifier
for dp->cpu_dp.
To visualize how that works, imagine the daisy chain topology below and
consider a SWITCHDEV_OBJ_ID_HOST_MDB object emitted on sw2p0. How does
the cross-chip notifier know to match on all the right ports (sw0p4, the
dedicated CPU port, sw1p4, an upstream DSA link, and sw2p4, another
upstream DSA link)?
|
sw0p0 sw0p1 sw0p2 sw0p3 sw0p4
[ user ] [ user ] [ user ] [ dsa ] [ cpu ]
[ ] [ ] [ ] [ ] [ x ]
|
+---------+
|
sw1p0 sw1p1 sw1p2 sw1p3 sw1p4
[ user ] [ user ] [ user ] [ dsa ] [ dsa ]
[ ] [ ] [ ] [ ] [ x ]
|
+---------+
|
sw2p0 sw2p1 sw2p2 sw2p3 sw2p4
[ user ] [ user ] [ user ] [ user ] [ dsa ]
[ ] [ ] [ ] [ ] [ x ]
The answer is simple: the dedicated CPU port of sw2p0 is sw0p4, and
dsa_routing_port returns the upstream port for all switches.
That is fine, but there are other topologies where this does not work as
well. There are trees with "H" topologies in the wild, where there are 2
or more switches with DSA links between them, but every switch has its
dedicated CPU port. For these topologies, it seems stupid for the neighbor
switches to install an MDB entry on the routing port, since these
multicast addresses are fundamentally different than the usual ones we
support (and that is the justification for this patch, to introduce the
concept of a termination plane multicast MAC address, as opposed to a
forwarding plane multicast MAC address).
For example, when a SWITCHDEV_OBJ_ID_HOST_MDB would get added to sw0p0,
without this patch, it would get treated as a regular port MDB on sw0p2
and it would match on the ports below (including the sw1p3 routing port).
| |
sw0p0 sw0p1 sw0p2 sw0p3 sw1p3 sw1p2 sw1p1 sw1p0
[ user ] [ user ] [ cpu ] [ dsa ] [ dsa ] [ cpu ] [ user ] [ user ]
[ ] [ ] [ x ] [ ] ---- [ x ] [ ] [ ] [ ]
With the patch, the host MDB notifier on sw0p0 matches only on the local
switch, which is what we want for a termination plane address.
| |
sw0p0 sw0p1 sw0p2 sw0p3 sw1p3 sw1p2 sw1p1 sw1p0
[ user ] [ user ] [ cpu ] [ dsa ] [ dsa ] [ cpu ] [ user ] [ user ]
[ ] [ ] [ x ] [ ] ---- [ ] [ ] [ ] [ ]
Name this new matching function "dsa_switch_host_address_match" since we
will be reusing it soon for host FDB entries as well.
Signed-off-by: Vladimir Oltean <vladimir.oltean@nxp.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
2021-06-29 22:06:49 +08:00
|
|
|
|
net: dsa: reference count the MDB entries at the cross-chip notifier level
Ever since the cross-chip notifiers were introduced, the design was
meant to be simplistic and just get the job done without worrying too
much about dangling resources left behind.
For example, somebody installs an MDB entry on sw0p0 in this daisy chain
topology. It gets installed using ds->ops->port_mdb_add() on sw0p0,
sw1p4 and sw2p4.
|
sw0p0 sw0p1 sw0p2 sw0p3 sw0p4
[ user ] [ user ] [ user ] [ dsa ] [ cpu ]
[ x ] [ ] [ ] [ ] [ ]
|
+---------+
|
sw1p0 sw1p1 sw1p2 sw1p3 sw1p4
[ user ] [ user ] [ user ] [ dsa ] [ dsa ]
[ ] [ ] [ ] [ ] [ x ]
|
+---------+
|
sw2p0 sw2p1 sw2p2 sw2p3 sw2p4
[ user ] [ user ] [ user ] [ user ] [ dsa ]
[ ] [ ] [ ] [ ] [ x ]
Then the same person deletes that MDB entry. The cross-chip notifier for
deletion only matches sw0p0:
|
sw0p0 sw0p1 sw0p2 sw0p3 sw0p4
[ user ] [ user ] [ user ] [ dsa ] [ cpu ]
[ x ] [ ] [ ] [ ] [ ]
|
+---------+
|
sw1p0 sw1p1 sw1p2 sw1p3 sw1p4
[ user ] [ user ] [ user ] [ dsa ] [ dsa ]
[ ] [ ] [ ] [ ] [ ]
|
+---------+
|
sw2p0 sw2p1 sw2p2 sw2p3 sw2p4
[ user ] [ user ] [ user ] [ user ] [ dsa ]
[ ] [ ] [ ] [ ] [ ]
Why?
Because the DSA links are 'trunk' ports, if we just go ahead and delete
the MDB from sw1p4 and sw2p4 directly, we might delete those multicast
entries when they are still needed. Just consider the fact that somebody
does:
- add a multicast MAC address towards sw0p0 [ via the cross-chip
notifiers it gets installed on the DSA links too ]
- add the same multicast MAC address towards sw0p1 (another port of that
same switch)
- delete the same multicast MAC address from sw0p0.
At this point, if we deleted the MAC address from the DSA links, it
would be flooded, even though there is still an entry on switch 0 which
needs it not to.
So that is why deletions only match the targeted source port and nothing
on DSA links. Of course, dangling resources means that the hardware
tables will eventually run out given enough additions/removals, but hey,
at least it's simple.
But there is a bigger concern which needs to be addressed, and that is
our support for SWITCHDEV_OBJ_ID_HOST_MDB. DSA simply translates such an
object into a dsa_port_host_mdb_add() which ends up as ds->ops->port_mdb_add()
on the upstream port, and a similar thing happens on deletion:
dsa_port_host_mdb_del() will trigger ds->ops->port_mdb_del() on the
upstream port.
When there are 2 VLAN-unaware bridges spanning the same switch (which is
a use case DSA proudly supports), each bridge will install its own
SWITCHDEV_OBJ_ID_HOST_MDB entries. But upon deletion, DSA goes ahead and
emits a DSA_NOTIFIER_MDB_DEL for dp->cpu_dp, which is shared between the
user ports enslaved to br0 and the user ports enslaved to br1. Not good.
The host-trapped multicast addresses installed by br1 will be deleted
when any state changes in br0 (IGMP timers expire, or ports leave, etc).
To avoid this, we could of course go the route of the zero-sum game and
delete the DSA_NOTIFIER_MDB_DEL call for dp->cpu_dp. But the better
design is to just admit that on shared ports like DSA links and CPU
ports, we should be reference counting calls, even if this consumes some
dynamic memory which DSA has traditionally avoided. On the flip side,
the hardware tables of switches are limited in size, so it would be good
if the OS managed them properly instead of having them eventually
overflow.
To address the memory usage concern, we only apply the refcounting of
MDB entries on ports that are really shared (CPU ports and DSA links)
and not on user ports. In a typical single-switch setup, this means only
the CPU port (and the host MDB entries are not that many, really).
The name of the newly introduced data structures (dsa_mac_addr) is
chosen in such a way that will be reusable for host FDB entries (next
patch).
With this change, we can finally have the same matching logic for the
MDB additions and deletions, as well as for their host-trapped variants.
Signed-off-by: Vladimir Oltean <vladimir.oltean@nxp.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
2021-06-29 22:06:50 +08:00
|
|
|
return err;
|
net: dsa: introduce a separate cross-chip notifier type for host MDBs
Commit abd49535c380 ("net: dsa: execute dsa_switch_mdb_add only for
routing port in cross-chip topologies") does a surprisingly good job
even for the SWITCHDEV_OBJ_ID_HOST_MDB use case, where DSA simply
translates a switchdev object received on dp into a cross-chip notifier
for dp->cpu_dp.
To visualize how that works, imagine the daisy chain topology below and
consider a SWITCHDEV_OBJ_ID_HOST_MDB object emitted on sw2p0. How does
the cross-chip notifier know to match on all the right ports (sw0p4, the
dedicated CPU port, sw1p4, an upstream DSA link, and sw2p4, another
upstream DSA link)?
|
sw0p0 sw0p1 sw0p2 sw0p3 sw0p4
[ user ] [ user ] [ user ] [ dsa ] [ cpu ]
[ ] [ ] [ ] [ ] [ x ]
|
+---------+
|
sw1p0 sw1p1 sw1p2 sw1p3 sw1p4
[ user ] [ user ] [ user ] [ dsa ] [ dsa ]
[ ] [ ] [ ] [ ] [ x ]
|
+---------+
|
sw2p0 sw2p1 sw2p2 sw2p3 sw2p4
[ user ] [ user ] [ user ] [ user ] [ dsa ]
[ ] [ ] [ ] [ ] [ x ]
The answer is simple: the dedicated CPU port of sw2p0 is sw0p4, and
dsa_routing_port returns the upstream port for all switches.
That is fine, but there are other topologies where this does not work as
well. There are trees with "H" topologies in the wild, where there are 2
or more switches with DSA links between them, but every switch has its
dedicated CPU port. For these topologies, it seems stupid for the neighbor
switches to install an MDB entry on the routing port, since these
multicast addresses are fundamentally different than the usual ones we
support (and that is the justification for this patch, to introduce the
concept of a termination plane multicast MAC address, as opposed to a
forwarding plane multicast MAC address).
For example, when a SWITCHDEV_OBJ_ID_HOST_MDB would get added to sw0p0,
without this patch, it would get treated as a regular port MDB on sw0p2
and it would match on the ports below (including the sw1p3 routing port).
| |
sw0p0 sw0p1 sw0p2 sw0p3 sw1p3 sw1p2 sw1p1 sw1p0
[ user ] [ user ] [ cpu ] [ dsa ] [ dsa ] [ cpu ] [ user ] [ user ]
[ ] [ ] [ x ] [ ] ---- [ x ] [ ] [ ] [ ]
With the patch, the host MDB notifier on sw0p0 matches only on the local
switch, which is what we want for a termination plane address.
| |
sw0p0 sw0p1 sw0p2 sw0p3 sw1p3 sw1p2 sw1p1 sw1p0
[ user ] [ user ] [ cpu ] [ dsa ] [ dsa ] [ cpu ] [ user ] [ user ]
[ ] [ ] [ x ] [ ] ---- [ ] [ ] [ ] [ ]
Name this new matching function "dsa_switch_host_address_match" since we
will be reusing it soon for host FDB entries as well.
Signed-off-by: Vladimir Oltean <vladimir.oltean@nxp.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
2021-06-29 22:06:49 +08:00
|
|
|
}
|
|
|
|
|
|
net: dsa: remove bitmap operations
The bitmap operations were introduced to simplify the switch drivers
in the future, since most of them could implement the common VLAN and
MDB operations (add, del, dump) with simple functions taking all target
ports at once, and thus limiting the number of hardware accesses.
Programming an MDB or VLAN this way in a single operation would clearly
simplify the drivers a lot but would require a new get-set interface
in DSA. The usage of such bitmap from the stack also raised concerned
in the past, leading to the dynamic allocation of a new ds->_bitmap
member in the dsa_switch structure. So let's get rid of them for now.
This commit nicely wraps the ds->ops->port_{mdb,vlan}_{prepare,add}
switch operations into new dsa_switch_{mdb,vlan}_{prepare,add}
variants not using any bitmap argument anymore.
New dsa_switch_{mdb,vlan}_match helpers have been introduced to make
clear which local port of a switch must be programmed with the target
object. While the targeted user port is an obvious candidate, the
DSA links must also be programmed, as well as the CPU port for VLANs.
While at it, also remove local variables that are only used once.
Signed-off-by: Vivien Didelot <vivien.didelot@gmail.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
2019-08-26 01:25:15 +08:00
|
|
|
static bool dsa_switch_vlan_match(struct dsa_switch *ds, int port,
|
|
|
|
|
struct dsa_notifier_vlan_info *info)
|
|
|
|
|
{
|
|
|
|
|
if (ds->index == info->sw_index && port == info->port)
|
|
|
|
|
return true;
|
|
|
|
|
|
2019-08-26 01:25:19 +08:00
|
|
|
if (dsa_is_dsa_port(ds, port))
|
net: dsa: remove bitmap operations
The bitmap operations were introduced to simplify the switch drivers
in the future, since most of them could implement the common VLAN and
MDB operations (add, del, dump) with simple functions taking all target
ports at once, and thus limiting the number of hardware accesses.
Programming an MDB or VLAN this way in a single operation would clearly
simplify the drivers a lot but would require a new get-set interface
in DSA. The usage of such bitmap from the stack also raised concerned
in the past, leading to the dynamic allocation of a new ds->_bitmap
member in the dsa_switch structure. So let's get rid of them for now.
This commit nicely wraps the ds->ops->port_{mdb,vlan}_{prepare,add}
switch operations into new dsa_switch_{mdb,vlan}_{prepare,add}
variants not using any bitmap argument anymore.
New dsa_switch_{mdb,vlan}_match helpers have been introduced to make
clear which local port of a switch must be programmed with the target
object. While the targeted user port is an obvious candidate, the
DSA links must also be programmed, as well as the CPU port for VLANs.
While at it, also remove local variables that are only used once.
Signed-off-by: Vivien Didelot <vivien.didelot@gmail.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
2019-08-26 01:25:15 +08:00
|
|
|
return true;
|
|
|
|
|
|
|
|
|
|
return false;
|
|
|
|
|
}
|
|
|
|
|
|
net: switchdev: remove the transaction structure from port object notifiers
Since the introduction of the switchdev API, port objects were
transmitted to drivers for offloading using a two-step transactional
model, with a prepare phase that was supposed to catch all errors, and a
commit phase that was supposed to never fail.
Some classes of failures can never be avoided, like hardware access, or
memory allocation. In the latter case, merely attempting to move the
memory allocation to the preparation phase makes it impossible to avoid
memory leaks, since commit 91cf8eceffc1 ("switchdev: Remove unused
transaction item queue") which has removed the unused mechanism of
passing on the allocated memory between one phase and another.
It is time we admit that separating the preparation from the commit
phase is something that is best left for the driver to decide, and not
something that should be baked into the API, especially since there are
no switchdev callers that depend on this.
This patch removes the struct switchdev_trans member from switchdev port
object notifier structures, and converts drivers to not look at this
member.
Where driver conversion is trivial (like in the case of the Marvell
Prestera driver, NXP DPAA2 switch, TI CPSW, and Rocker drivers), it is
done in this patch.
Where driver conversion needs more attention (DSA, Mellanox Spectrum),
the conversion is left for subsequent patches and here we only fake the
prepare/commit phases at a lower level, just not in the switchdev
notifier itself.
Where the code has a natural structure that is best left alone as a
preparation and a commit phase (as in the case of the Ocelot switch),
that structure is left in place, just made to not depend upon the
switchdev transactional model.
Signed-off-by: Vladimir Oltean <vladimir.oltean@nxp.com>
Reviewed-by: Florian Fainelli <f.fainelli@gmail.com>
Acked-by: Linus Walleij <linus.walleij@linaro.org>
Acked-by: Jiri Pirko <jiri@nvidia.com>
Reviewed-by: Ido Schimmel <idosch@nvidia.com>
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
2021-01-09 08:01:48 +08:00
|
|
|
static int dsa_switch_vlan_add(struct dsa_switch *ds,
|
|
|
|
|
struct dsa_notifier_vlan_info *info)
|
2017-12-01 00:23:59 +08:00
|
|
|
{
|
|
|
|
|
int port, err;
|
|
|
|
|
|
2021-01-09 08:01:53 +08:00
|
|
|
if (!ds->ops->port_vlan_add)
|
2017-12-01 00:23:59 +08:00
|
|
|
return -EOPNOTSUPP;
|
|
|
|
|
|
net: dsa: remove bitmap operations
The bitmap operations were introduced to simplify the switch drivers
in the future, since most of them could implement the common VLAN and
MDB operations (add, del, dump) with simple functions taking all target
ports at once, and thus limiting the number of hardware accesses.
Programming an MDB or VLAN this way in a single operation would clearly
simplify the drivers a lot but would require a new get-set interface
in DSA. The usage of such bitmap from the stack also raised concerned
in the past, leading to the dynamic allocation of a new ds->_bitmap
member in the dsa_switch structure. So let's get rid of them for now.
This commit nicely wraps the ds->ops->port_{mdb,vlan}_{prepare,add}
switch operations into new dsa_switch_{mdb,vlan}_{prepare,add}
variants not using any bitmap argument anymore.
New dsa_switch_{mdb,vlan}_match helpers have been introduced to make
clear which local port of a switch must be programmed with the target
object. While the targeted user port is an obvious candidate, the
DSA links must also be programmed, as well as the CPU port for VLANs.
While at it, also remove local variables that are only used once.
Signed-off-by: Vivien Didelot <vivien.didelot@gmail.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
2019-08-26 01:25:15 +08:00
|
|
|
for (port = 0; port < ds->num_ports; port++) {
|
|
|
|
|
if (dsa_switch_vlan_match(ds, port, info)) {
|
2021-02-14 04:43:18 +08:00
|
|
|
err = ds->ops->port_vlan_add(ds, port, info->vlan,
|
|
|
|
|
info->extack);
|
net: dsa: remove bitmap operations
The bitmap operations were introduced to simplify the switch drivers
in the future, since most of them could implement the common VLAN and
MDB operations (add, del, dump) with simple functions taking all target
ports at once, and thus limiting the number of hardware accesses.
Programming an MDB or VLAN this way in a single operation would clearly
simplify the drivers a lot but would require a new get-set interface
in DSA. The usage of such bitmap from the stack also raised concerned
in the past, leading to the dynamic allocation of a new ds->_bitmap
member in the dsa_switch structure. So let's get rid of them for now.
This commit nicely wraps the ds->ops->port_{mdb,vlan}_{prepare,add}
switch operations into new dsa_switch_{mdb,vlan}_{prepare,add}
variants not using any bitmap argument anymore.
New dsa_switch_{mdb,vlan}_match helpers have been introduced to make
clear which local port of a switch must be programmed with the target
object. While the targeted user port is an obvious candidate, the
DSA links must also be programmed, as well as the CPU port for VLANs.
While at it, also remove local variables that are only used once.
Signed-off-by: Vivien Didelot <vivien.didelot@gmail.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
2019-08-26 01:25:15 +08:00
|
|
|
if (err)
|
|
|
|
|
return err;
|
|
|
|
|
}
|
2017-12-01 00:23:59 +08:00
|
|
|
}
|
|
|
|
|
|
2017-05-20 05:00:55 +08:00
|
|
|
return 0;
|
|
|
|
|
}
|
|
|
|
|
|
|
|
|
|
static int dsa_switch_vlan_del(struct dsa_switch *ds,
|
|
|
|
|
struct dsa_notifier_vlan_info *info)
|
|
|
|
|
{
|
|
|
|
|
if (!ds->ops->port_vlan_del)
|
|
|
|
|
return -EOPNOTSUPP;
|
|
|
|
|
|
2017-06-08 06:12:14 +08:00
|
|
|
if (ds->index == info->sw_index)
|
net: dsa: remove bitmap operations
The bitmap operations were introduced to simplify the switch drivers
in the future, since most of them could implement the common VLAN and
MDB operations (add, del, dump) with simple functions taking all target
ports at once, and thus limiting the number of hardware accesses.
Programming an MDB or VLAN this way in a single operation would clearly
simplify the drivers a lot but would require a new get-set interface
in DSA. The usage of such bitmap from the stack also raised concerned
in the past, leading to the dynamic allocation of a new ds->_bitmap
member in the dsa_switch structure. So let's get rid of them for now.
This commit nicely wraps the ds->ops->port_{mdb,vlan}_{prepare,add}
switch operations into new dsa_switch_{mdb,vlan}_{prepare,add}
variants not using any bitmap argument anymore.
New dsa_switch_{mdb,vlan}_match helpers have been introduced to make
clear which local port of a switch must be programmed with the target
object. While the targeted user port is an obvious candidate, the
DSA links must also be programmed, as well as the CPU port for VLANs.
While at it, also remove local variables that are only used once.
Signed-off-by: Vivien Didelot <vivien.didelot@gmail.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
2019-08-26 01:25:15 +08:00
|
|
|
return ds->ops->port_vlan_del(ds, info->port, info->vlan);
|
2017-06-08 06:12:14 +08:00
|
|
|
|
2019-08-26 01:25:19 +08:00
|
|
|
/* Do not deprogram the DSA links as they may be used as conduit
|
|
|
|
|
* for other VLAN members in the fabric.
|
|
|
|
|
*/
|
2017-06-08 06:12:14 +08:00
|
|
|
return 0;
|
2017-05-20 05:00:55 +08:00
|
|
|
}
|
|
|
|
|
|
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 98cdb4807123 ("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: Vladimir Oltean <vladimir.oltean@nxp.com>
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
2021-01-29 09:00:06 +08:00
|
|
|
static int dsa_switch_change_tag_proto(struct dsa_switch *ds,
|
|
|
|
|
struct dsa_notifier_tag_proto_info *info)
|
|
|
|
|
{
|
|
|
|
|
const struct dsa_device_ops *tag_ops = info->tag_ops;
|
|
|
|
|
int port, err;
|
|
|
|
|
|
|
|
|
|
if (!ds->ops->change_tag_protocol)
|
|
|
|
|
return -EOPNOTSUPP;
|
|
|
|
|
|
|
|
|
|
ASSERT_RTNL();
|
|
|
|
|
|
|
|
|
|
for (port = 0; port < ds->num_ports; port++) {
|
2021-04-21 02:53:09 +08:00
|
|
|
if (!dsa_is_cpu_port(ds, port))
|
|
|
|
|
continue;
|
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 98cdb4807123 ("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: Vladimir Oltean <vladimir.oltean@nxp.com>
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
2021-01-29 09:00:06 +08:00
|
|
|
|
2021-04-21 02:53:09 +08:00
|
|
|
err = ds->ops->change_tag_protocol(ds, port, tag_ops->proto);
|
|
|
|
|
if (err)
|
|
|
|
|
return err;
|
|
|
|
|
|
|
|
|
|
dsa_port_set_tag_protocol(dsa_to_port(ds, port), tag_ops);
|
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 98cdb4807123 ("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: Vladimir Oltean <vladimir.oltean@nxp.com>
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
2021-01-29 09:00:06 +08:00
|
|
|
}
|
|
|
|
|
|
|
|
|
|
/* Now that changing the tag protocol can no longer fail, let's update
|
|
|
|
|
* the remaining bits which are "duplicated for faster access", and the
|
|
|
|
|
* bits that depend on the tagger, such as the MTU.
|
|
|
|
|
*/
|
|
|
|
|
for (port = 0; port < ds->num_ports; port++) {
|
|
|
|
|
if (dsa_is_user_port(ds, port)) {
|
|
|
|
|
struct net_device *slave;
|
|
|
|
|
|
|
|
|
|
slave = dsa_to_port(ds, port)->slave;
|
|
|
|
|
dsa_slave_setup_tagger(slave);
|
|
|
|
|
|
|
|
|
|
/* rtnl_mutex is held in dsa_tree_change_tag_proto */
|
|
|
|
|
dsa_slave_change_mtu(slave, slave->mtu);
|
|
|
|
|
}
|
|
|
|
|
}
|
|
|
|
|
|
|
|
|
|
return 0;
|
|
|
|
|
}
|
|
|
|
|
|
2021-02-17 05:42:04 +08:00
|
|
|
static int dsa_switch_mrp_add(struct dsa_switch *ds,
|
|
|
|
|
struct dsa_notifier_mrp_info *info)
|
|
|
|
|
{
|
|
|
|
|
if (!ds->ops->port_mrp_add)
|
|
|
|
|
return -EOPNOTSUPP;
|
|
|
|
|
|
2021-06-22 00:42:19 +08:00
|
|
|
if (ds->index == info->sw_index)
|
|
|
|
|
return ds->ops->port_mrp_add(ds, info->port, info->mrp);
|
2021-02-17 05:42:04 +08:00
|
|
|
|
2021-06-22 00:42:19 +08:00
|
|
|
return 0;
|
2021-02-17 05:42:04 +08:00
|
|
|
}
|
|
|
|
|
|
|
|
|
|
static int dsa_switch_mrp_del(struct dsa_switch *ds,
|
|
|
|
|
struct dsa_notifier_mrp_info *info)
|
|
|
|
|
{
|
|
|
|
|
if (!ds->ops->port_mrp_del)
|
|
|
|
|
return -EOPNOTSUPP;
|
|
|
|
|
|
|
|
|
|
if (ds->index == info->sw_index)
|
|
|
|
|
return ds->ops->port_mrp_del(ds, info->port, info->mrp);
|
|
|
|
|
|
|
|
|
|
return 0;
|
|
|
|
|
}
|
|
|
|
|
|
|
|
|
|
static int
|
|
|
|
|
dsa_switch_mrp_add_ring_role(struct dsa_switch *ds,
|
|
|
|
|
struct dsa_notifier_mrp_ring_role_info *info)
|
|
|
|
|
{
|
|
|
|
|
if (!ds->ops->port_mrp_add)
|
|
|
|
|
return -EOPNOTSUPP;
|
|
|
|
|
|
2021-06-22 00:42:19 +08:00
|
|
|
if (ds->index == info->sw_index)
|
|
|
|
|
return ds->ops->port_mrp_add_ring_role(ds, info->port,
|
|
|
|
|
info->mrp);
|
2021-02-17 05:42:04 +08:00
|
|
|
|
2021-06-22 00:42:19 +08:00
|
|
|
return 0;
|
2021-02-17 05:42:04 +08:00
|
|
|
}
|
|
|
|
|
|
|
|
|
|
static int
|
|
|
|
|
dsa_switch_mrp_del_ring_role(struct dsa_switch *ds,
|
|
|
|
|
struct dsa_notifier_mrp_ring_role_info *info)
|
|
|
|
|
{
|
|
|
|
|
if (!ds->ops->port_mrp_del)
|
|
|
|
|
return -EOPNOTSUPP;
|
|
|
|
|
|
|
|
|
|
if (ds->index == info->sw_index)
|
|
|
|
|
return ds->ops->port_mrp_del_ring_role(ds, info->port,
|
|
|
|
|
info->mrp);
|
|
|
|
|
|
|
|
|
|
return 0;
|
|
|
|
|
}
|
|
|
|
|
|
2017-02-04 02:20:20 +08:00
|
|
|
static int dsa_switch_event(struct notifier_block *nb,
|
|
|
|
|
unsigned long event, void *info)
|
|
|
|
|
{
|
|
|
|
|
struct dsa_switch *ds = container_of(nb, struct dsa_switch, nb);
|
|
|
|
|
int err;
|
|
|
|
|
|
|
|
|
|
switch (event) {
|
2017-05-20 05:00:52 +08:00
|
|
|
case DSA_NOTIFIER_AGEING_TIME:
|
|
|
|
|
err = dsa_switch_ageing_time(ds, info);
|
|
|
|
|
break;
|
2017-02-04 02:20:21 +08:00
|
|
|
case DSA_NOTIFIER_BRIDGE_JOIN:
|
|
|
|
|
err = dsa_switch_bridge_join(ds, info);
|
|
|
|
|
break;
|
|
|
|
|
case DSA_NOTIFIER_BRIDGE_LEAVE:
|
|
|
|
|
err = dsa_switch_bridge_leave(ds, info);
|
|
|
|
|
break;
|
2017-05-20 05:00:53 +08:00
|
|
|
case DSA_NOTIFIER_FDB_ADD:
|
|
|
|
|
err = dsa_switch_fdb_add(ds, info);
|
|
|
|
|
break;
|
|
|
|
|
case DSA_NOTIFIER_FDB_DEL:
|
|
|
|
|
err = dsa_switch_fdb_del(ds, info);
|
|
|
|
|
break;
|
2021-06-29 22:06:51 +08:00
|
|
|
case DSA_NOTIFIER_HOST_FDB_ADD:
|
|
|
|
|
err = dsa_switch_host_fdb_add(ds, info);
|
|
|
|
|
break;
|
|
|
|
|
case DSA_NOTIFIER_HOST_FDB_DEL:
|
|
|
|
|
err = dsa_switch_host_fdb_del(ds, info);
|
|
|
|
|
break;
|
2021-02-10 09:02:12 +08:00
|
|
|
case DSA_NOTIFIER_HSR_JOIN:
|
|
|
|
|
err = dsa_switch_hsr_join(ds, info);
|
|
|
|
|
break;
|
|
|
|
|
case DSA_NOTIFIER_HSR_LEAVE:
|
|
|
|
|
err = dsa_switch_hsr_leave(ds, info);
|
|
|
|
|
break;
|
2021-01-13 16:42:53 +08:00
|
|
|
case DSA_NOTIFIER_LAG_CHANGE:
|
|
|
|
|
err = dsa_switch_lag_change(ds, info);
|
|
|
|
|
break;
|
|
|
|
|
case DSA_NOTIFIER_LAG_JOIN:
|
|
|
|
|
err = dsa_switch_lag_join(ds, info);
|
|
|
|
|
break;
|
|
|
|
|
case DSA_NOTIFIER_LAG_LEAVE:
|
|
|
|
|
err = dsa_switch_lag_leave(ds, info);
|
|
|
|
|
break;
|
2017-05-20 05:00:54 +08:00
|
|
|
case DSA_NOTIFIER_MDB_ADD:
|
|
|
|
|
err = dsa_switch_mdb_add(ds, info);
|
|
|
|
|
break;
|
|
|
|
|
case DSA_NOTIFIER_MDB_DEL:
|
|
|
|
|
err = dsa_switch_mdb_del(ds, info);
|
|
|
|
|
break;
|
net: dsa: introduce a separate cross-chip notifier type for host MDBs
Commit abd49535c380 ("net: dsa: execute dsa_switch_mdb_add only for
routing port in cross-chip topologies") does a surprisingly good job
even for the SWITCHDEV_OBJ_ID_HOST_MDB use case, where DSA simply
translates a switchdev object received on dp into a cross-chip notifier
for dp->cpu_dp.
To visualize how that works, imagine the daisy chain topology below and
consider a SWITCHDEV_OBJ_ID_HOST_MDB object emitted on sw2p0. How does
the cross-chip notifier know to match on all the right ports (sw0p4, the
dedicated CPU port, sw1p4, an upstream DSA link, and sw2p4, another
upstream DSA link)?
|
sw0p0 sw0p1 sw0p2 sw0p3 sw0p4
[ user ] [ user ] [ user ] [ dsa ] [ cpu ]
[ ] [ ] [ ] [ ] [ x ]
|
+---------+
|
sw1p0 sw1p1 sw1p2 sw1p3 sw1p4
[ user ] [ user ] [ user ] [ dsa ] [ dsa ]
[ ] [ ] [ ] [ ] [ x ]
|
+---------+
|
sw2p0 sw2p1 sw2p2 sw2p3 sw2p4
[ user ] [ user ] [ user ] [ user ] [ dsa ]
[ ] [ ] [ ] [ ] [ x ]
The answer is simple: the dedicated CPU port of sw2p0 is sw0p4, and
dsa_routing_port returns the upstream port for all switches.
That is fine, but there are other topologies where this does not work as
well. There are trees with "H" topologies in the wild, where there are 2
or more switches with DSA links between them, but every switch has its
dedicated CPU port. For these topologies, it seems stupid for the neighbor
switches to install an MDB entry on the routing port, since these
multicast addresses are fundamentally different than the usual ones we
support (and that is the justification for this patch, to introduce the
concept of a termination plane multicast MAC address, as opposed to a
forwarding plane multicast MAC address).
For example, when a SWITCHDEV_OBJ_ID_HOST_MDB would get added to sw0p0,
without this patch, it would get treated as a regular port MDB on sw0p2
and it would match on the ports below (including the sw1p3 routing port).
| |
sw0p0 sw0p1 sw0p2 sw0p3 sw1p3 sw1p2 sw1p1 sw1p0
[ user ] [ user ] [ cpu ] [ dsa ] [ dsa ] [ cpu ] [ user ] [ user ]
[ ] [ ] [ x ] [ ] ---- [ x ] [ ] [ ] [ ]
With the patch, the host MDB notifier on sw0p0 matches only on the local
switch, which is what we want for a termination plane address.
| |
sw0p0 sw0p1 sw0p2 sw0p3 sw1p3 sw1p2 sw1p1 sw1p0
[ user ] [ user ] [ cpu ] [ dsa ] [ dsa ] [ cpu ] [ user ] [ user ]
[ ] [ ] [ x ] [ ] ---- [ ] [ ] [ ] [ ]
Name this new matching function "dsa_switch_host_address_match" since we
will be reusing it soon for host FDB entries as well.
Signed-off-by: Vladimir Oltean <vladimir.oltean@nxp.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
2021-06-29 22:06:49 +08:00
|
|
|
case DSA_NOTIFIER_HOST_MDB_ADD:
|
|
|
|
|
err = dsa_switch_host_mdb_add(ds, info);
|
|
|
|
|
break;
|
|
|
|
|
case DSA_NOTIFIER_HOST_MDB_DEL:
|
|
|
|
|
err = dsa_switch_host_mdb_del(ds, info);
|
|
|
|
|
break;
|
2017-05-20 05:00:55 +08:00
|
|
|
case DSA_NOTIFIER_VLAN_ADD:
|
|
|
|
|
err = dsa_switch_vlan_add(ds, info);
|
|
|
|
|
break;
|
|
|
|
|
case DSA_NOTIFIER_VLAN_DEL:
|
|
|
|
|
err = dsa_switch_vlan_del(ds, info);
|
|
|
|
|
break;
|
net: dsa: configure the MTU for switch ports
It is useful be able to configure port policers on a switch to accept
frames of various sizes:
- Increase the MTU for better throughput from the default of 1500 if it
is known that there is no 10/100 Mbps device in the network.
- Decrease the MTU to limit the latency of high-priority frames under
congestion, or work around various network segments that add extra
headers to packets which can't be fragmented.
For DSA slave ports, this is mostly a pass-through callback, called
through the regular ndo ops and at probe time (to ensure consistency
across all supported switches).
The CPU port is called with an MTU equal to the largest configured MTU
of the slave ports. The assumption is that the user might want to
sustain a bidirectional conversation with a partner over any switch
port.
The DSA master is configured the same as the CPU port, plus the tagger
overhead. Since the MTU is by definition L2 payload (sans Ethernet
header), it is up to each individual driver to figure out if it needs to
do anything special for its frame tags on the CPU port (it shouldn't
except in special cases). So the MTU does not contain the tagger
overhead on the CPU port.
However the MTU of the DSA master, minus the tagger overhead, is used as
a proxy for the MTU of the CPU port, which does not have a net device.
This is to avoid uselessly calling the .change_mtu function on the CPU
port when nothing should change.
So it is safe to assume that the DSA master and the CPU port MTUs are
apart by exactly the tagger's overhead in bytes.
Some changes were made around dsa_master_set_mtu(), function which was
now removed, for 2 reasons:
- dev_set_mtu() already calls dev_validate_mtu(), so it's redundant to
do the same thing in DSA
- __dev_set_mtu() returns 0 if ops->ndo_change_mtu is an absent method
That is to say, there's no need for this function in DSA, we can safely
call dev_set_mtu() directly, take the rtnl lock when necessary, and just
propagate whatever errors get reported (since the user probably wants to
be informed).
Some inspiration (mainly in the MTU DSA notifier) was taken from a
vaguely similar patch from Murali and Florian, who are credited as
co-developers down below.
Co-developed-by: Murali Krishna Policharla <murali.policharla@broadcom.com>
Signed-off-by: Murali Krishna Policharla <murali.policharla@broadcom.com>
Co-developed-by: Florian Fainelli <f.fainelli@gmail.com>
Signed-off-by: Florian Fainelli <f.fainelli@gmail.com>
Signed-off-by: Vladimir Oltean <vladimir.oltean@nxp.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
2020-03-28 03:55:42 +08:00
|
|
|
case DSA_NOTIFIER_MTU:
|
|
|
|
|
err = dsa_switch_mtu(ds, info);
|
|
|
|
|
break;
|
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 98cdb4807123 ("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: Vladimir Oltean <vladimir.oltean@nxp.com>
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
2021-01-29 09:00:06 +08:00
|
|
|
case DSA_NOTIFIER_TAG_PROTO:
|
|
|
|
|
err = dsa_switch_change_tag_proto(ds, info);
|
|
|
|
|
break;
|
2021-02-17 05:42:04 +08:00
|
|
|
case DSA_NOTIFIER_MRP_ADD:
|
|
|
|
|
err = dsa_switch_mrp_add(ds, info);
|
|
|
|
|
break;
|
|
|
|
|
case DSA_NOTIFIER_MRP_DEL:
|
|
|
|
|
err = dsa_switch_mrp_del(ds, info);
|
|
|
|
|
break;
|
|
|
|
|
case DSA_NOTIFIER_MRP_ADD_RING_ROLE:
|
|
|
|
|
err = dsa_switch_mrp_add_ring_role(ds, info);
|
|
|
|
|
break;
|
|
|
|
|
case DSA_NOTIFIER_MRP_DEL_RING_ROLE:
|
|
|
|
|
err = dsa_switch_mrp_del_ring_role(ds, info);
|
|
|
|
|
break;
|
net: dsa: tag_8021q: add proper cross-chip notifier support
The big problem which mandates cross-chip notifiers for tag_8021q is
this:
|
sw0p0 sw0p1 sw0p2 sw0p3 sw0p4
[ user ] [ user ] [ user ] [ dsa ] [ cpu ]
|
+---------+
|
sw1p0 sw1p1 sw1p2 sw1p3 sw1p4
[ user ] [ user ] [ user ] [ dsa ] [ dsa ]
|
+---------+
|
sw2p0 sw2p1 sw2p2 sw2p3 sw2p4
[ user ] [ user ] [ user ] [ dsa ] [ dsa ]
When the user runs:
ip link add br0 type bridge
ip link set sw0p0 master br0
ip link set sw2p0 master br0
It doesn't work.
This is because dsa_8021q_crosschip_bridge_join() assumes that "ds" and
"other_ds" are at most 1 hop away from each other, so it is sufficient
to add the RX VLAN of {ds, port} into {other_ds, other_port} and vice
versa and presto, the cross-chip link works. When there is another
switch in the middle, such as in this case switch 1 with its DSA links
sw1p3 and sw1p4, somebody needs to tell it about these VLANs too.
Which is exactly why the problem is quadratic: when a port joins a
bridge, for each port in the tree that's already in that same bridge we
notify a tag_8021q VLAN addition of that port's RX VLAN to the entire
tree. It is a very complicated web of VLANs.
It must be mentioned that currently we install tag_8021q VLANs on too
many ports (DSA links - to be precise, on all of them). For example,
when sw2p0 joins br0, and assuming sw1p0 was part of br0 too, we add the
RX VLAN of sw2p0 on the DSA links of switch 0 too, even though there
isn't any port of switch 0 that is a member of br0 (at least yet).
In theory we could notify only the switches which sit in between the
port joining the bridge and the port reacting to that bridge_join event.
But in practice that is impossible, because of the way 'link' properties
are described in the device tree. The DSA bindings require DT writers to
list out not only the real/physical DSA links, but in fact the entire
routing table, like for example switch 0 above will have:
sw0p3: port@3 {
link = <&sw1p4 &sw2p4>;
};
This was done because:
/* TODO: ideally DSA ports would have a single dp->link_dp member,
* and no dst->rtable nor this struct dsa_link would be needed,
* but this would require some more complex tree walking,
* so keep it stupid at the moment and list them all.
*/
but it is a perfect example of a situation where too much information is
actively detrimential, because we are now in the position where we
cannot distinguish a real DSA link from one that is put there to avoid
the 'complex tree walking'. And because DT is ABI, there is not much we
can change.
And because we do not know which DSA links are real and which ones
aren't, we can't really know if DSA switch A is in the data path between
switches B and C, in the general case.
So this is why tag_8021q RX VLANs are added on all DSA links, and
probably why it will never change.
On the other hand, at least the number of additions/deletions is well
balanced, and this means that once we implement reference counting at
the cross-chip notifier level a la fdb/mdb, there is absolutely zero
need for a struct dsa_8021q_crosschip_link, it's all self-managing.
In fact, with the tag_8021q notifiers emitted from the bridge join
notifiers, it becomes so generic that sja1105 does not need to do
anything anymore, we can just delete its implementation of the
.crosschip_bridge_{join,leave} methods.
Among other things we can simply delete is the home-grown implementation
of sja1105_notify_crosschip_switches(). The reason why that is wrong is
because it is not quadratic - it only covers remote switches to which we
have a cross-chip bridging link and that does not cover in-between
switches. This deletion is part of the same patch because sja1105 used
to poke deep inside the guts of the tag_8021q context in order to do
that. Because the cross-chip links went away, so needs the sja1105 code.
Last but not least, dsa_8021q_setup_port() is simplified (and also
renamed). Because our TAG_8021Q_VLAN_ADD notifier is designed to react
on the CPU port too, the four dsa_8021q_vid_apply() calls:
- 1 for RX VLAN on user port
- 1 for the user port's RX VLAN on the CPU port
- 1 for TX VLAN on user port
- 1 for the user port's TX VLAN on the CPU port
now get squashed into only 2 notifier calls via
dsa_port_tag_8021q_vlan_add.
And because the notifiers to add and to delete a tag_8021q VLAN are
distinct, now we finally break up the port setup and teardown into
separate functions instead of relying on a "bool enabled" flag which
tells us what to do. Arguably it should have been this way from the
get go.
Signed-off-by: Vladimir Oltean <vladimir.oltean@nxp.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
2021-07-20 01:14:52 +08:00
|
|
|
case DSA_NOTIFIER_TAG_8021Q_VLAN_ADD:
|
|
|
|
|
err = dsa_switch_tag_8021q_vlan_add(ds, info);
|
|
|
|
|
break;
|
|
|
|
|
case DSA_NOTIFIER_TAG_8021Q_VLAN_DEL:
|
|
|
|
|
err = dsa_switch_tag_8021q_vlan_del(ds, info);
|
|
|
|
|
break;
|
2017-02-04 02:20:20 +08:00
|
|
|
default:
|
|
|
|
|
err = -EOPNOTSUPP;
|
|
|
|
|
break;
|
|
|
|
|
}
|
|
|
|
|
|
|
|
|
|
if (err)
|
|
|
|
|
dev_dbg(ds->dev, "breaking chain for DSA event %lu (%d)\n",
|
|
|
|
|
event, err);
|
|
|
|
|
|
|
|
|
|
return notifier_from_errno(err);
|
|
|
|
|
}
|
|
|
|
|
|
|
|
|
|
int dsa_switch_register_notifier(struct dsa_switch *ds)
|
|
|
|
|
{
|
|
|
|
|
ds->nb.notifier_call = dsa_switch_event;
|
|
|
|
|
|
|
|
|
|
return raw_notifier_chain_register(&ds->dst->nh, &ds->nb);
|
|
|
|
|
}
|
|
|
|
|
|
|
|
|
|
void dsa_switch_unregister_notifier(struct dsa_switch *ds)
|
|
|
|
|
{
|
|
|
|
|
int err;
|
|
|
|
|
|
|
|
|
|
err = raw_notifier_chain_unregister(&ds->dst->nh, &ds->nb);
|
|
|
|
|
if (err)
|
|
|
|
|
dev_err(ds->dev, "failed to unregister notifier (%d)\n", err);
|
|
|
|
|
}
|