linux/net/bridge/br.c

476 lines
11 KiB
C
Raw Normal View History

// SPDX-License-Identifier: GPL-2.0-or-later
/*
* Generic parts
* Linux ethernet bridge
*
* Authors:
* Lennert Buytenhek <buytenh@gnu.org>
*/
#include <linux/module.h>
#include <linux/kernel.h>
#include <linux/netdevice.h>
#include <linux/etherdevice.h>
#include <linux/init.h>
#include <linux/llc.h>
#include <net/llc.h>
#include <net/stp.h>
#include <net/switchdev.h>
#include "br_private.h"
/*
* Handle changes in state of network devices enslaved to a bridge.
*
* Note: don't care about up/down if bridge itself is down, because
* port state is checked when bridge is brought up.
*/
static int br_device_event(struct notifier_block *unused, unsigned long event, void *ptr)
{
struct netlink_ext_ack *extack = netdev_notifier_info_to_extack(ptr);
struct netdev_notifier_pre_changeaddr_info *prechaddr_info;
struct net_device *dev = netdev_notifier_info_to_dev(ptr);
struct net_bridge_port *p;
struct net_bridge *br;
bool notified = false;
bool changed_addr;
int err;
if (netif_is_bridge_master(dev)) {
net: bridge: move default pvid init/deinit to NETDEV_REGISTER/UNREGISTER Most of the bridge device's vlan init bugs come from the fact that its default pvid is created at the wrong time, way too early in ndo_init() before the device is even assigned an ifindex. It introduces a bug when the bridge's dev_addr is added as fdb during the initial default pvid creation the notification has ifindex/NDA_MASTER both equal to 0 (see example below) which really makes no sense for user-space[0] and is wrong. Usually user-space software would ignore such entries, but they are actually valid and will eventually have all necessary attributes. It makes much more sense to send a notification *after* the device has registered and has a proper ifindex allocated rather than before when there's a chance that the registration might still fail or to receive it with ifindex/NDA_MASTER == 0. Note that we can remove the fdb flush from br_vlan_flush() since that case can no longer happen. At NETDEV_REGISTER br->default_pvid is always == 1 as it's initialized by br_vlan_init() before that and at NETDEV_UNREGISTER it can be anything depending why it was called (if called due to NETDEV_REGISTER error it'll still be == 1, otherwise it could be any value changed during the device life time). For the demonstration below a small change to iproute2 for printing all fdb notifications is added, because it contained a workaround not to show entries with ifindex == 0. Command executed while monitoring: $ ip l add br0 type bridge Before (both ifindex and master == 0): $ bridge monitor fdb 36:7e:8a:b3:56:ba dev * vlan 1 master * permanent After (proper br0 ifindex): $ bridge monitor fdb e6:2a:ae:7a:b7:48 dev br0 vlan 1 master br0 permanent v4: move only the default pvid init/deinit to NETDEV_REGISTER/UNREGISTER v3: send the correct v2 patch with all changes (stub should return 0) v2: on error in br_vlan_init set br->vlgrp to NULL and return 0 in the br_vlan_bridge_event stub when bridge vlans are disabled [0] https://bugzilla.kernel.org/show_bug.cgi?id=204389 Reported-by: michael-dev <michael-dev@fami-braun.de> Fixes: 5be5a2df40f0 ("bridge: Add filtering support for default_pvid") Signed-off-by: Nikolay Aleksandrov <nikolay@cumulusnetworks.com> Acked-by: Roopa Prabhu <roopa@cumulusnetworks.com> Signed-off-by: David S. Miller <davem@davemloft.net>
2019-08-02 18:57:36 +08:00
err = br_vlan_bridge_event(dev, event, ptr);
if (err)
return notifier_from_errno(err);
if (event == NETDEV_REGISTER) {
/* register of bridge completed, add sysfs entries */
net: bridge: Fix a warning when del bridge sysfs I got a warining report: br_sysfs_addbr: can't create group bridge4/bridge ------------[ cut here ]------------ sysfs group 'bridge' not found for kobject 'bridge4' WARNING: CPU: 2 PID: 9004 at fs/sysfs/group.c:279 sysfs_remove_group fs/sysfs/group.c:279 [inline] WARNING: CPU: 2 PID: 9004 at fs/sysfs/group.c:279 sysfs_remove_group+0x153/0x1b0 fs/sysfs/group.c:270 Modules linked in: iptable_nat ... Call Trace: br_dev_delete+0x112/0x190 net/bridge/br_if.c:384 br_dev_newlink net/bridge/br_netlink.c:1381 [inline] br_dev_newlink+0xdb/0x100 net/bridge/br_netlink.c:1362 __rtnl_newlink+0xe11/0x13f0 net/core/rtnetlink.c:3441 rtnl_newlink+0x64/0xa0 net/core/rtnetlink.c:3500 rtnetlink_rcv_msg+0x385/0x980 net/core/rtnetlink.c:5562 netlink_rcv_skb+0x134/0x3d0 net/netlink/af_netlink.c:2494 netlink_unicast_kernel net/netlink/af_netlink.c:1304 [inline] netlink_unicast+0x4a0/0x6a0 net/netlink/af_netlink.c:1330 netlink_sendmsg+0x793/0xc80 net/netlink/af_netlink.c:1919 sock_sendmsg_nosec net/socket.c:651 [inline] sock_sendmsg+0x139/0x170 net/socket.c:671 ____sys_sendmsg+0x658/0x7d0 net/socket.c:2353 ___sys_sendmsg+0xf8/0x170 net/socket.c:2407 __sys_sendmsg+0xd3/0x190 net/socket.c:2440 do_syscall_64+0x33/0x40 arch/x86/entry/common.c:46 entry_SYSCALL_64_after_hwframe+0x44/0xa9 In br_device_event(), if the bridge sysfs fails to be added, br_device_event() should return error. This can prevent warining when removing bridge sysfs that do not exist. Fixes: bb900b27a2f4 ("bridge: allow creating bridge devices with netlink") Reported-by: Hulk Robot <hulkci@huawei.com> Signed-off-by: Wang Hai <wanghai38@huawei.com> Tested-by: Nikolay Aleksandrov <nikolay@nvidia.com> Acked-by: Nikolay Aleksandrov <nikolay@nvidia.com> Link: https://lore.kernel.org/r/20201211122921.40386-1-wanghai38@huawei.com Signed-off-by: Jakub Kicinski <kuba@kernel.org>
2020-12-11 20:29:21 +08:00
err = br_sysfs_addbr(dev);
if (err)
return notifier_from_errno(err);
return NOTIFY_DONE;
}
}
/* not a port of a bridge */
p = br_port_get_rtnl(dev);
if (!p)
return NOTIFY_DONE;
br = p->br;
switch (event) {
case NETDEV_CHANGEMTU:
br_mtu_auto_adjust(br);
break;
case NETDEV_PRE_CHANGEADDR:
if (br->dev->addr_assign_type == NET_ADDR_SET)
break;
prechaddr_info = ptr;
err = dev_pre_changeaddr_notify(br->dev,
prechaddr_info->dev_addr,
extack);
if (err)
return notifier_from_errno(err);
break;
case NETDEV_CHANGEADDR:
spin_lock_bh(&br->lock);
br_fdb_changeaddr(p, dev->dev_addr);
changed_addr = br_stp_recalculate_bridge_id(br);
spin_unlock_bh(&br->lock);
if (changed_addr)
call_netdevice_notifiers(NETDEV_CHANGEADDR, br->dev);
break;
case NETDEV_CHANGE:
br_port_carrier_check(p, &notified);
break;
case NETDEV_FEAT_CHANGE:
netdev_update_features(br->dev);
break;
case NETDEV_DOWN:
spin_lock_bh(&br->lock);
if (br->dev->flags & IFF_UP) {
br_stp_disable_port(p);
notified = true;
}
spin_unlock_bh(&br->lock);
break;
case NETDEV_UP:
if (netif_running(br->dev) && netif_oper_up(dev)) {
spin_lock_bh(&br->lock);
br_stp_enable_port(p);
notified = true;
spin_unlock_bh(&br->lock);
}
break;
case NETDEV_UNREGISTER:
br_del_if(br, dev);
break;
case NETDEV_CHANGENAME:
err = br_sysfs_renameif(p);
if (err)
return notifier_from_errno(err);
break;
case NETDEV_PRE_TYPE_CHANGE:
/* Forbid underlying device to change its type. */
return NOTIFY_BAD;
case NETDEV_RESEND_IGMP:
/* Propagate to master device */
call_netdevice_notifiers(event, br->dev);
break;
}
bridge: Fix possible use-after-free when deleting bridge port When a bridge port is being deleted, do not dereference it later in br_vlan_port_event() as it can result in a use-after-free [1] if the RCU callback was executed before invoking the function. [1] [ 129.638551] ================================================================== [ 129.646904] BUG: KASAN: use-after-free in br_vlan_port_event+0x53c/0x5fd [ 129.654406] Read of size 8 at addr ffff8881e4aa1ae8 by task ip/483 [ 129.663008] CPU: 0 PID: 483 Comm: ip Not tainted 5.1.0-rc5-custom-02265-ga946bd73daac #1383 [ 129.672359] Hardware name: Mellanox Technologies Ltd. MSN2100-CB2FO/SA001017, BIOS 5.6.5 06/07/2016 [ 129.682484] Call Trace: [ 129.685242] dump_stack+0xa9/0x10e [ 129.689068] print_address_description.cold.2+0x9/0x25e [ 129.694930] kasan_report.cold.3+0x78/0x9d [ 129.704420] br_vlan_port_event+0x53c/0x5fd [ 129.728300] br_device_event+0x2c7/0x7a0 [ 129.741505] notifier_call_chain+0xb5/0x1c0 [ 129.746202] rollback_registered_many+0x895/0xe90 [ 129.793119] unregister_netdevice_many+0x48/0x210 [ 129.803384] rtnl_delete_link+0xe1/0x140 [ 129.815906] rtnl_dellink+0x2a3/0x820 [ 129.844166] rtnetlink_rcv_msg+0x397/0x910 [ 129.868517] netlink_rcv_skb+0x137/0x3a0 [ 129.882013] netlink_unicast+0x49b/0x660 [ 129.900019] netlink_sendmsg+0x755/0xc90 [ 129.915758] ___sys_sendmsg+0x761/0x8e0 [ 129.966315] __sys_sendmsg+0xf0/0x1c0 [ 129.988918] do_syscall_64+0xa4/0x470 [ 129.993032] entry_SYSCALL_64_after_hwframe+0x49/0xbe [ 129.998696] RIP: 0033:0x7ff578104b58 ... [ 130.073811] Allocated by task 479: [ 130.077633] __kasan_kmalloc.constprop.5+0xc1/0xd0 [ 130.083008] kmem_cache_alloc_trace+0x152/0x320 [ 130.088090] br_add_if+0x39c/0x1580 [ 130.092005] do_set_master+0x1aa/0x210 [ 130.096211] do_setlink+0x985/0x3100 [ 130.100224] __rtnl_newlink+0xc52/0x1380 [ 130.104625] rtnl_newlink+0x6b/0xa0 [ 130.108541] rtnetlink_rcv_msg+0x397/0x910 [ 130.113136] netlink_rcv_skb+0x137/0x3a0 [ 130.117538] netlink_unicast+0x49b/0x660 [ 130.121939] netlink_sendmsg+0x755/0xc90 [ 130.126340] ___sys_sendmsg+0x761/0x8e0 [ 130.130645] __sys_sendmsg+0xf0/0x1c0 [ 130.134753] do_syscall_64+0xa4/0x470 [ 130.138864] entry_SYSCALL_64_after_hwframe+0x49/0xbe [ 130.146195] Freed by task 0: [ 130.149421] __kasan_slab_free+0x125/0x170 [ 130.154016] kfree+0xf3/0x310 [ 130.157349] kobject_put+0x1a8/0x4c0 [ 130.161363] rcu_core+0x859/0x19b0 [ 130.165175] __do_softirq+0x250/0xa26 [ 130.170956] The buggy address belongs to the object at ffff8881e4aa1ae8 which belongs to the cache kmalloc-1k of size 1024 [ 130.184972] The buggy address is located 0 bytes inside of 1024-byte region [ffff8881e4aa1ae8, ffff8881e4aa1ee8) Fixes: 9c0ec2e7182a ("bridge: support binding vlan dev link state to vlan member bridge ports") Signed-off-by: Ido Schimmel <idosch@mellanox.com> Cc: Mike Manning <mmanning@vyatta.att-mail.com> Acked-by: Nikolay Aleksandrov <nikolay@cumulusnetworks.com> Acked-by: Mike Manning <mmanning@vyatta.att-mail.com> Signed-off-by: David S. Miller <davem@davemloft.net>
2019-04-22 17:33:19 +08:00
if (event != NETDEV_UNREGISTER)
br_vlan_port_event(p, event);
/* Events that may cause spanning tree to refresh */
if (!notified && (event == NETDEV_CHANGEADDR || event == NETDEV_UP ||
event == NETDEV_CHANGE || event == NETDEV_DOWN))
br_ifinfo_notify(RTM_NEWLINK, NULL, p);
return NOTIFY_DONE;
}
static struct notifier_block br_device_notifier = {
.notifier_call = br_device_event
};
/* called with RTNL or RCU */
static int br_switchdev_event(struct notifier_block *unused,
unsigned long event, void *ptr)
{
struct net_device *dev = switchdev_notifier_info_to_dev(ptr);
struct net_bridge_port *p;
struct net_bridge *br;
struct switchdev_notifier_fdb_info *fdb_info;
int err = NOTIFY_DONE;
p = br_port_get_rtnl_rcu(dev);
if (!p)
goto out;
br = p->br;
switch (event) {
case SWITCHDEV_FDB_ADD_TO_BRIDGE:
fdb_info = ptr;
err = br_fdb_external_learn_add(br, p, fdb_info->addr,
bridge: switchdev: Allow device drivers to install locked FDB entries When the bridge is offloaded to hardware, FDB entries are learned and aged-out by the hardware. Some device drivers synchronize the hardware and software FDBs by generating switchdev events towards the bridge. When a port is locked, the hardware must not learn autonomously, as otherwise any host will blindly gain authorization. Instead, the hardware should generate events regarding hosts that are trying to gain authorization and their MAC addresses should be notified by the device driver as locked FDB entries towards the bridge driver. Allow device drivers to notify the bridge driver about such entries by extending the 'switchdev_notifier_fdb_info' structure with the 'locked' bit. The bit can only be set by device drivers and not by the bridge driver. Prevent a locked entry from being installed if MAB is not enabled on the bridge port. If an entry already exists in the bridge driver, reject the locked entry if the current entry does not have the "locked" flag set or if it points to a different port. The same semantics are implemented in the software data path. Signed-off-by: Hans J. Schultz <netdev@kapio-technology.com> Signed-off-by: Ido Schimmel <idosch@nvidia.com> Reviewed-by: Petr Machata <petrm@nvidia.com> Signed-off-by: Petr Machata <petrm@nvidia.com> Reviewed-by: Vladimir Oltean <vladimir.oltean@nxp.com> Acked-by: Nikolay Aleksandrov <razor@blackwall.org> Signed-off-by: Jakub Kicinski <kuba@kernel.org>
2022-11-08 18:47:08 +08:00
fdb_info->vid,
fdb_info->locked, false);
if (err) {
err = notifier_from_errno(err);
break;
}
br_fdb_offloaded_set(br, p, fdb_info->addr,
fdb_info->vid, fdb_info->offloaded);
break;
case SWITCHDEV_FDB_DEL_TO_BRIDGE:
fdb_info = ptr;
err = br_fdb_external_learn_del(br, p, fdb_info->addr,
fdb_info->vid, false);
if (err)
err = notifier_from_errno(err);
break;
case SWITCHDEV_FDB_OFFLOADED:
fdb_info = ptr;
br_fdb_offloaded_set(br, p, fdb_info->addr,
fdb_info->vid, fdb_info->offloaded);
break;
case SWITCHDEV_FDB_FLUSH_TO_BRIDGE:
fdb_info = ptr;
/* Don't delete static entries */
br_fdb_delete_by_port(br, p, fdb_info->vid, 0);
break;
}
out:
return err;
}
static struct notifier_block br_switchdev_notifier = {
.notifier_call = br_switchdev_event,
};
net: make switchdev_bridge_port_{,unoffload} loosely coupled with the bridge With the introduction of explicit offloading API in switchdev in commit 2f5dc00f7a3e ("net: bridge: switchdev: let drivers inform which bridge ports are offloaded"), we started having Ethernet switch drivers calling directly into a function exported by net/bridge/br_switchdev.c, which is a function exported by the bridge driver. This means that drivers that did not have an explicit dependency on the bridge before, like cpsw and am65-cpsw, now do - otherwise it is not possible to call a symbol exported by a driver that can be built as module unless you are a module too. There was an attempt to solve the dependency issue in the form of commit b0e81817629a ("net: build all switchdev drivers as modules when the bridge is a module"). Grygorii Strashko, however, says about it: | In my opinion, the problem is a bit bigger here than just fixing the | build :( | | In case, of ^cpsw the switchdev mode is kinda optional and in many | cases (especially for testing purposes, NFS) the multi-mac mode is | still preferable mode. | | There were no such tight dependency between switchdev drivers and | bridge core before and switchdev serviced as independent, notification | based layer between them, so ^cpsw still can be "Y" and bridge can be | "M". Now for mostly every kernel build configuration the CONFIG_BRIDGE | will need to be set as "Y", or we will have to update drivers to | support build with BRIDGE=n and maintain separate builds for | networking vs non-networking testing. But is this enough? Wouldn't | it cause 'chain reaction' required to add more and more "Y" options | (like CONFIG_VLAN_8021Q)? | | PS. Just to be sure we on the same page - ARM builds will be forced | (with this patch) to have CONFIG_TI_CPSW_SWITCHDEV=m and so all our | automation testing will just fail with omap2plus_defconfig. In the light of this, it would be desirable for some configurations to avoid dependencies between switchdev drivers and the bridge, and have the switchdev mode as completely optional within the driver. Arnd Bergmann also tried to write a patch which better expressed the build time dependency for Ethernet switch drivers where the switchdev support is optional, like cpsw/am65-cpsw, and this made the drivers follow the bridge (compile as module if the bridge is a module) only if the optional switchdev support in the driver was enabled in the first place: https://patchwork.kernel.org/project/netdevbpf/patch/20210802144813.1152762-1-arnd@kernel.org/ but this still did not solve the fact that cpsw and am65-cpsw now must be built as modules when the bridge is a module - it just expressed correctly that optional dependency. But the new behavior is an apparent regression from Grygorii's perspective. So to support the use case where the Ethernet driver is built-in, NET_SWITCHDEV (a bool option) is enabled, and the bridge is a module, we need a framework that can handle the possible absence of the bridge from the running system, i.e. runtime bloatware as opposed to build-time bloatware. Luckily we already have this framework, since switchdev has been using it extensively. Events from the bridge side are transmitted to the driver side using notifier chains - this was originally done so that unrelated drivers could snoop for events emitted by the bridge towards ports that are implemented by other drivers (think of a switch driver with LAG offload that listens for switchdev events on a bonding/team interface that it offloads). There are also events which are transmitted from the driver side to the bridge side, which again are modeled using notifiers. SWITCHDEV_FDB_ADD_TO_BRIDGE is an example of this, and deals with notifying the bridge that a MAC address has been dynamically learned. So there is a precedent we can use for modeling the new framework. The difference compared to SWITCHDEV_FDB_ADD_TO_BRIDGE is that the work that the bridge needs to do when a port becomes offloaded is blocking in its nature: replay VLANs, MDBs etc. The calling context is indeed blocking (we are under rtnl_mutex), but the existing switchdev notification chain that the bridge is subscribed to is only the atomic one. So we need to subscribe the bridge to the blocking switchdev notification chain too. This patch: - keeps the driver-side perception of the switchdev_bridge_port_{,un}offload unchanged - moves the implementation of switchdev_bridge_port_{,un}offload from the bridge module into the switchdev module. - makes everybody that is subscribed to the switchdev blocking notifier chain "hear" offload & unoffload events - makes the bridge driver subscribe and handle those events - moves the bridge driver's handling of those events into 2 new functions called br_switchdev_port_{,un}offload. These functions contain in fact the core of the logic that was previously in switchdev_bridge_port_{,un}offload, just that now we go through an extra indirection layer to reach them. Unlike all the other switchdev notification structures, the structure used to carry the bridge port information, struct switchdev_notifier_brport_info, does not contain a "bool handled". This is because in the current usage pattern, we always know that a switchdev bridge port offloading event will be handled by the bridge, because the switchdev_bridge_port_offload() call was initiated by a NETDEV_CHANGEUPPER event in the first place, where info->upper_dev is a bridge. So if the bridge wasn't loaded, then the CHANGEUPPER event couldn't have happened. Signed-off-by: Vladimir Oltean <vladimir.oltean@nxp.com> Tested-by: Grygorii Strashko <grygorii.strashko@ti.com> Signed-off-by: David S. Miller <davem@davemloft.net>
2021-08-04 04:34:08 +08:00
/* called under rtnl_mutex */
static int br_switchdev_blocking_event(struct notifier_block *nb,
unsigned long event, void *ptr)
{
struct netlink_ext_ack *extack = netdev_notifier_info_to_extack(ptr);
struct net_device *dev = switchdev_notifier_info_to_dev(ptr);
struct switchdev_notifier_brport_info *brport_info;
const struct switchdev_brport *b;
struct net_bridge_port *p;
int err = NOTIFY_DONE;
p = br_port_get_rtnl(dev);
if (!p)
goto out;
switch (event) {
case SWITCHDEV_BRPORT_OFFLOADED:
brport_info = ptr;
b = &brport_info->brport;
err = br_switchdev_port_offload(p, b->dev, b->ctx,
b->atomic_nb, b->blocking_nb,
b->tx_fwd_offload, extack);
err = notifier_from_errno(err);
break;
case SWITCHDEV_BRPORT_UNOFFLOADED:
brport_info = ptr;
b = &brport_info->brport;
br_switchdev_port_unoffload(p, b->ctx, b->atomic_nb,
b->blocking_nb);
break;
case SWITCHDEV_BRPORT_REPLAY:
brport_info = ptr;
b = &brport_info->brport;
err = br_switchdev_port_replay(p, b->dev, b->ctx, b->atomic_nb,
b->blocking_nb, extack);
err = notifier_from_errno(err);
break;
net: make switchdev_bridge_port_{,unoffload} loosely coupled with the bridge With the introduction of explicit offloading API in switchdev in commit 2f5dc00f7a3e ("net: bridge: switchdev: let drivers inform which bridge ports are offloaded"), we started having Ethernet switch drivers calling directly into a function exported by net/bridge/br_switchdev.c, which is a function exported by the bridge driver. This means that drivers that did not have an explicit dependency on the bridge before, like cpsw and am65-cpsw, now do - otherwise it is not possible to call a symbol exported by a driver that can be built as module unless you are a module too. There was an attempt to solve the dependency issue in the form of commit b0e81817629a ("net: build all switchdev drivers as modules when the bridge is a module"). Grygorii Strashko, however, says about it: | In my opinion, the problem is a bit bigger here than just fixing the | build :( | | In case, of ^cpsw the switchdev mode is kinda optional and in many | cases (especially for testing purposes, NFS) the multi-mac mode is | still preferable mode. | | There were no such tight dependency between switchdev drivers and | bridge core before and switchdev serviced as independent, notification | based layer between them, so ^cpsw still can be "Y" and bridge can be | "M". Now for mostly every kernel build configuration the CONFIG_BRIDGE | will need to be set as "Y", or we will have to update drivers to | support build with BRIDGE=n and maintain separate builds for | networking vs non-networking testing. But is this enough? Wouldn't | it cause 'chain reaction' required to add more and more "Y" options | (like CONFIG_VLAN_8021Q)? | | PS. Just to be sure we on the same page - ARM builds will be forced | (with this patch) to have CONFIG_TI_CPSW_SWITCHDEV=m and so all our | automation testing will just fail with omap2plus_defconfig. In the light of this, it would be desirable for some configurations to avoid dependencies between switchdev drivers and the bridge, and have the switchdev mode as completely optional within the driver. Arnd Bergmann also tried to write a patch which better expressed the build time dependency for Ethernet switch drivers where the switchdev support is optional, like cpsw/am65-cpsw, and this made the drivers follow the bridge (compile as module if the bridge is a module) only if the optional switchdev support in the driver was enabled in the first place: https://patchwork.kernel.org/project/netdevbpf/patch/20210802144813.1152762-1-arnd@kernel.org/ but this still did not solve the fact that cpsw and am65-cpsw now must be built as modules when the bridge is a module - it just expressed correctly that optional dependency. But the new behavior is an apparent regression from Grygorii's perspective. So to support the use case where the Ethernet driver is built-in, NET_SWITCHDEV (a bool option) is enabled, and the bridge is a module, we need a framework that can handle the possible absence of the bridge from the running system, i.e. runtime bloatware as opposed to build-time bloatware. Luckily we already have this framework, since switchdev has been using it extensively. Events from the bridge side are transmitted to the driver side using notifier chains - this was originally done so that unrelated drivers could snoop for events emitted by the bridge towards ports that are implemented by other drivers (think of a switch driver with LAG offload that listens for switchdev events on a bonding/team interface that it offloads). There are also events which are transmitted from the driver side to the bridge side, which again are modeled using notifiers. SWITCHDEV_FDB_ADD_TO_BRIDGE is an example of this, and deals with notifying the bridge that a MAC address has been dynamically learned. So there is a precedent we can use for modeling the new framework. The difference compared to SWITCHDEV_FDB_ADD_TO_BRIDGE is that the work that the bridge needs to do when a port becomes offloaded is blocking in its nature: replay VLANs, MDBs etc. The calling context is indeed blocking (we are under rtnl_mutex), but the existing switchdev notification chain that the bridge is subscribed to is only the atomic one. So we need to subscribe the bridge to the blocking switchdev notification chain too. This patch: - keeps the driver-side perception of the switchdev_bridge_port_{,un}offload unchanged - moves the implementation of switchdev_bridge_port_{,un}offload from the bridge module into the switchdev module. - makes everybody that is subscribed to the switchdev blocking notifier chain "hear" offload & unoffload events - makes the bridge driver subscribe and handle those events - moves the bridge driver's handling of those events into 2 new functions called br_switchdev_port_{,un}offload. These functions contain in fact the core of the logic that was previously in switchdev_bridge_port_{,un}offload, just that now we go through an extra indirection layer to reach them. Unlike all the other switchdev notification structures, the structure used to carry the bridge port information, struct switchdev_notifier_brport_info, does not contain a "bool handled". This is because in the current usage pattern, we always know that a switchdev bridge port offloading event will be handled by the bridge, because the switchdev_bridge_port_offload() call was initiated by a NETDEV_CHANGEUPPER event in the first place, where info->upper_dev is a bridge. So if the bridge wasn't loaded, then the CHANGEUPPER event couldn't have happened. Signed-off-by: Vladimir Oltean <vladimir.oltean@nxp.com> Tested-by: Grygorii Strashko <grygorii.strashko@ti.com> Signed-off-by: David S. Miller <davem@davemloft.net>
2021-08-04 04:34:08 +08:00
}
out:
return err;
}
static struct notifier_block br_switchdev_blocking_notifier = {
.notifier_call = br_switchdev_blocking_event,
};
net: bridge: add support for user-controlled bool options We have been adding many new bridge options, a big number of which are boolean but still take up netlink attribute ids and waste space in the skb. Recently we discussed learning from link-local packets[1] and decided yet another new boolean option will be needed, thus introducing this API to save some bridge nl space. The API supports changing the value of multiple boolean options at once via the br_boolopt_multi struct which has an optmask (which options to set, bit per opt) and optval (options' new values). Future boolean options will only be added to the br_boolopt_id enum and then will have to be handled in br_boolopt_toggle/get. The API will automatically add the ability to change and export them via netlink, sysfs can use the single boolopt function versions to do the same. The behaviour with failing/succeeding is the same as with normal netlink option changing. If an option requires mapping to internal kernel flag or needs special configuration to be enabled then it should be handled in br_boolopt_toggle. It should also be able to retrieve an option's current state via br_boolopt_get. v2: WARN_ON() on unsupported option as that shouldn't be possible and also will help catch people who add new options without handling them for both set and get. Pass down extack so if an option desires it could set it on error and be more user-friendly. [1] https://www.spinics.net/lists/netdev/msg532698.html Signed-off-by: Nikolay Aleksandrov <nikolay@cumulusnetworks.com> Reviewed-by: Andrew Lunn <andrew@lunn.ch> Signed-off-by: David S. Miller <davem@davemloft.net>
2018-11-24 10:34:20 +08:00
/* br_boolopt_toggle - change user-controlled boolean option
*
* @br: bridge device
* @opt: id of the option to change
* @on: new option value
* @extack: extack for error messages
*
* Changes the value of the respective boolean option to @on taking care of
* any internal option value mapping and configuration.
*/
int br_boolopt_toggle(struct net_bridge *br, enum br_boolopt_id opt, bool on,
struct netlink_ext_ack *extack)
{
int err = 0;
net: bridge: add support for user-controlled bool options We have been adding many new bridge options, a big number of which are boolean but still take up netlink attribute ids and waste space in the skb. Recently we discussed learning from link-local packets[1] and decided yet another new boolean option will be needed, thus introducing this API to save some bridge nl space. The API supports changing the value of multiple boolean options at once via the br_boolopt_multi struct which has an optmask (which options to set, bit per opt) and optval (options' new values). Future boolean options will only be added to the br_boolopt_id enum and then will have to be handled in br_boolopt_toggle/get. The API will automatically add the ability to change and export them via netlink, sysfs can use the single boolopt function versions to do the same. The behaviour with failing/succeeding is the same as with normal netlink option changing. If an option requires mapping to internal kernel flag or needs special configuration to be enabled then it should be handled in br_boolopt_toggle. It should also be able to retrieve an option's current state via br_boolopt_get. v2: WARN_ON() on unsupported option as that shouldn't be possible and also will help catch people who add new options without handling them for both set and get. Pass down extack so if an option desires it could set it on error and be more user-friendly. [1] https://www.spinics.net/lists/netdev/msg532698.html Signed-off-by: Nikolay Aleksandrov <nikolay@cumulusnetworks.com> Reviewed-by: Andrew Lunn <andrew@lunn.ch> Signed-off-by: David S. Miller <davem@davemloft.net>
2018-11-24 10:34:20 +08:00
switch (opt) {
case BR_BOOLOPT_NO_LL_LEARN:
br_opt_toggle(br, BROPT_NO_LL_LEARN, on);
break;
case BR_BOOLOPT_MCAST_VLAN_SNOOPING:
err = br_multicast_toggle_vlan_snooping(br, on, extack);
break;
case BR_BOOLOPT_MST_ENABLE:
err = br_mst_set_enabled(br, on, extack);
break;
net: bridge: add support for user-controlled bool options We have been adding many new bridge options, a big number of which are boolean but still take up netlink attribute ids and waste space in the skb. Recently we discussed learning from link-local packets[1] and decided yet another new boolean option will be needed, thus introducing this API to save some bridge nl space. The API supports changing the value of multiple boolean options at once via the br_boolopt_multi struct which has an optmask (which options to set, bit per opt) and optval (options' new values). Future boolean options will only be added to the br_boolopt_id enum and then will have to be handled in br_boolopt_toggle/get. The API will automatically add the ability to change and export them via netlink, sysfs can use the single boolopt function versions to do the same. The behaviour with failing/succeeding is the same as with normal netlink option changing. If an option requires mapping to internal kernel flag or needs special configuration to be enabled then it should be handled in br_boolopt_toggle. It should also be able to retrieve an option's current state via br_boolopt_get. v2: WARN_ON() on unsupported option as that shouldn't be possible and also will help catch people who add new options without handling them for both set and get. Pass down extack so if an option desires it could set it on error and be more user-friendly. [1] https://www.spinics.net/lists/netdev/msg532698.html Signed-off-by: Nikolay Aleksandrov <nikolay@cumulusnetworks.com> Reviewed-by: Andrew Lunn <andrew@lunn.ch> Signed-off-by: David S. Miller <davem@davemloft.net>
2018-11-24 10:34:20 +08:00
default:
/* shouldn't be called with unsupported options */
WARN_ON(1);
break;
}
return err;
net: bridge: add support for user-controlled bool options We have been adding many new bridge options, a big number of which are boolean but still take up netlink attribute ids and waste space in the skb. Recently we discussed learning from link-local packets[1] and decided yet another new boolean option will be needed, thus introducing this API to save some bridge nl space. The API supports changing the value of multiple boolean options at once via the br_boolopt_multi struct which has an optmask (which options to set, bit per opt) and optval (options' new values). Future boolean options will only be added to the br_boolopt_id enum and then will have to be handled in br_boolopt_toggle/get. The API will automatically add the ability to change and export them via netlink, sysfs can use the single boolopt function versions to do the same. The behaviour with failing/succeeding is the same as with normal netlink option changing. If an option requires mapping to internal kernel flag or needs special configuration to be enabled then it should be handled in br_boolopt_toggle. It should also be able to retrieve an option's current state via br_boolopt_get. v2: WARN_ON() on unsupported option as that shouldn't be possible and also will help catch people who add new options without handling them for both set and get. Pass down extack so if an option desires it could set it on error and be more user-friendly. [1] https://www.spinics.net/lists/netdev/msg532698.html Signed-off-by: Nikolay Aleksandrov <nikolay@cumulusnetworks.com> Reviewed-by: Andrew Lunn <andrew@lunn.ch> Signed-off-by: David S. Miller <davem@davemloft.net>
2018-11-24 10:34:20 +08:00
}
int br_boolopt_get(const struct net_bridge *br, enum br_boolopt_id opt)
{
switch (opt) {
case BR_BOOLOPT_NO_LL_LEARN:
return br_opt_get(br, BROPT_NO_LL_LEARN);
case BR_BOOLOPT_MCAST_VLAN_SNOOPING:
return br_opt_get(br, BROPT_MCAST_VLAN_SNOOPING_ENABLED);
case BR_BOOLOPT_MST_ENABLE:
return br_opt_get(br, BROPT_MST_ENABLED);
net: bridge: add support for user-controlled bool options We have been adding many new bridge options, a big number of which are boolean but still take up netlink attribute ids and waste space in the skb. Recently we discussed learning from link-local packets[1] and decided yet another new boolean option will be needed, thus introducing this API to save some bridge nl space. The API supports changing the value of multiple boolean options at once via the br_boolopt_multi struct which has an optmask (which options to set, bit per opt) and optval (options' new values). Future boolean options will only be added to the br_boolopt_id enum and then will have to be handled in br_boolopt_toggle/get. The API will automatically add the ability to change and export them via netlink, sysfs can use the single boolopt function versions to do the same. The behaviour with failing/succeeding is the same as with normal netlink option changing. If an option requires mapping to internal kernel flag or needs special configuration to be enabled then it should be handled in br_boolopt_toggle. It should also be able to retrieve an option's current state via br_boolopt_get. v2: WARN_ON() on unsupported option as that shouldn't be possible and also will help catch people who add new options without handling them for both set and get. Pass down extack so if an option desires it could set it on error and be more user-friendly. [1] https://www.spinics.net/lists/netdev/msg532698.html Signed-off-by: Nikolay Aleksandrov <nikolay@cumulusnetworks.com> Reviewed-by: Andrew Lunn <andrew@lunn.ch> Signed-off-by: David S. Miller <davem@davemloft.net>
2018-11-24 10:34:20 +08:00
default:
/* shouldn't be called with unsupported options */
WARN_ON(1);
break;
}
return 0;
}
int br_boolopt_multi_toggle(struct net_bridge *br,
struct br_boolopt_multi *bm,
struct netlink_ext_ack *extack)
{
unsigned long bitmap = bm->optmask;
int err = 0;
int opt_id;
for_each_set_bit(opt_id, &bitmap, BR_BOOLOPT_MAX) {
bool on = !!(bm->optval & BIT(opt_id));
err = br_boolopt_toggle(br, opt_id, on, extack);
if (err) {
br_debug(br, "boolopt multi-toggle error: option: %d current: %d new: %d error: %d\n",
opt_id, br_boolopt_get(br, opt_id), on, err);
break;
}
}
return err;
}
void br_boolopt_multi_get(const struct net_bridge *br,
struct br_boolopt_multi *bm)
{
u32 optval = 0;
int opt_id;
for (opt_id = 0; opt_id < BR_BOOLOPT_MAX; opt_id++)
optval |= (br_boolopt_get(br, opt_id) << opt_id);
bm->optval = optval;
bm->optmask = GENMASK((BR_BOOLOPT_MAX - 1), 0);
net: bridge: add support for user-controlled bool options We have been adding many new bridge options, a big number of which are boolean but still take up netlink attribute ids and waste space in the skb. Recently we discussed learning from link-local packets[1] and decided yet another new boolean option will be needed, thus introducing this API to save some bridge nl space. The API supports changing the value of multiple boolean options at once via the br_boolopt_multi struct which has an optmask (which options to set, bit per opt) and optval (options' new values). Future boolean options will only be added to the br_boolopt_id enum and then will have to be handled in br_boolopt_toggle/get. The API will automatically add the ability to change and export them via netlink, sysfs can use the single boolopt function versions to do the same. The behaviour with failing/succeeding is the same as with normal netlink option changing. If an option requires mapping to internal kernel flag or needs special configuration to be enabled then it should be handled in br_boolopt_toggle. It should also be able to retrieve an option's current state via br_boolopt_get. v2: WARN_ON() on unsupported option as that shouldn't be possible and also will help catch people who add new options without handling them for both set and get. Pass down extack so if an option desires it could set it on error and be more user-friendly. [1] https://www.spinics.net/lists/netdev/msg532698.html Signed-off-by: Nikolay Aleksandrov <nikolay@cumulusnetworks.com> Reviewed-by: Andrew Lunn <andrew@lunn.ch> Signed-off-by: David S. Miller <davem@davemloft.net>
2018-11-24 10:34:20 +08:00
}
/* private bridge options, controlled by the kernel */
void br_opt_toggle(struct net_bridge *br, enum net_bridge_opts opt, bool on)
{
bool cur = !!br_opt_get(br, opt);
br_debug(br, "toggle option: %d state: %d -> %d\n",
opt, cur, on);
if (cur == on)
return;
if (on)
set_bit(opt, &br->options);
else
clear_bit(opt, &br->options);
}
static void __net_exit br_net_exit_batch_rtnl(struct list_head *net_list,
struct list_head *dev_to_kill)
{
struct net_device *dev;
struct net *net;
ASSERT_RTNL();
list_for_each_entry(net, net_list, exit_list)
for_each_netdev(net, dev)
if (netif_is_bridge_master(dev))
br_dev_delete(dev, dev_to_kill);
}
static struct pernet_operations br_net_ops = {
.exit_batch_rtnl = br_net_exit_batch_rtnl,
};
static const struct stp_proto br_stp_proto = {
.rcv = br_stp_rcv,
};
static int __init br_init(void)
{
int err;
BUILD_BUG_ON(sizeof(struct br_input_skb_cb) > sizeof_field(struct sk_buff, cb));
err = stp_proto_register(&br_stp_proto);
if (err < 0) {
pr_err("bridge: can't register sap for STP\n");
return err;
}
err = br_fdb_init();
if (err)
goto err_out;
err = register_pernet_subsys(&br_net_ops);
if (err)
goto err_out1;
err = br_nf_core_init();
if (err)
goto err_out2;
err = register_netdevice_notifier(&br_device_notifier);
if (err)
goto err_out3;
err = register_switchdev_notifier(&br_switchdev_notifier);
if (err)
goto err_out4;
net: make switchdev_bridge_port_{,unoffload} loosely coupled with the bridge With the introduction of explicit offloading API in switchdev in commit 2f5dc00f7a3e ("net: bridge: switchdev: let drivers inform which bridge ports are offloaded"), we started having Ethernet switch drivers calling directly into a function exported by net/bridge/br_switchdev.c, which is a function exported by the bridge driver. This means that drivers that did not have an explicit dependency on the bridge before, like cpsw and am65-cpsw, now do - otherwise it is not possible to call a symbol exported by a driver that can be built as module unless you are a module too. There was an attempt to solve the dependency issue in the form of commit b0e81817629a ("net: build all switchdev drivers as modules when the bridge is a module"). Grygorii Strashko, however, says about it: | In my opinion, the problem is a bit bigger here than just fixing the | build :( | | In case, of ^cpsw the switchdev mode is kinda optional and in many | cases (especially for testing purposes, NFS) the multi-mac mode is | still preferable mode. | | There were no such tight dependency between switchdev drivers and | bridge core before and switchdev serviced as independent, notification | based layer between them, so ^cpsw still can be "Y" and bridge can be | "M". Now for mostly every kernel build configuration the CONFIG_BRIDGE | will need to be set as "Y", or we will have to update drivers to | support build with BRIDGE=n and maintain separate builds for | networking vs non-networking testing. But is this enough? Wouldn't | it cause 'chain reaction' required to add more and more "Y" options | (like CONFIG_VLAN_8021Q)? | | PS. Just to be sure we on the same page - ARM builds will be forced | (with this patch) to have CONFIG_TI_CPSW_SWITCHDEV=m and so all our | automation testing will just fail with omap2plus_defconfig. In the light of this, it would be desirable for some configurations to avoid dependencies between switchdev drivers and the bridge, and have the switchdev mode as completely optional within the driver. Arnd Bergmann also tried to write a patch which better expressed the build time dependency for Ethernet switch drivers where the switchdev support is optional, like cpsw/am65-cpsw, and this made the drivers follow the bridge (compile as module if the bridge is a module) only if the optional switchdev support in the driver was enabled in the first place: https://patchwork.kernel.org/project/netdevbpf/patch/20210802144813.1152762-1-arnd@kernel.org/ but this still did not solve the fact that cpsw and am65-cpsw now must be built as modules when the bridge is a module - it just expressed correctly that optional dependency. But the new behavior is an apparent regression from Grygorii's perspective. So to support the use case where the Ethernet driver is built-in, NET_SWITCHDEV (a bool option) is enabled, and the bridge is a module, we need a framework that can handle the possible absence of the bridge from the running system, i.e. runtime bloatware as opposed to build-time bloatware. Luckily we already have this framework, since switchdev has been using it extensively. Events from the bridge side are transmitted to the driver side using notifier chains - this was originally done so that unrelated drivers could snoop for events emitted by the bridge towards ports that are implemented by other drivers (think of a switch driver with LAG offload that listens for switchdev events on a bonding/team interface that it offloads). There are also events which are transmitted from the driver side to the bridge side, which again are modeled using notifiers. SWITCHDEV_FDB_ADD_TO_BRIDGE is an example of this, and deals with notifying the bridge that a MAC address has been dynamically learned. So there is a precedent we can use for modeling the new framework. The difference compared to SWITCHDEV_FDB_ADD_TO_BRIDGE is that the work that the bridge needs to do when a port becomes offloaded is blocking in its nature: replay VLANs, MDBs etc. The calling context is indeed blocking (we are under rtnl_mutex), but the existing switchdev notification chain that the bridge is subscribed to is only the atomic one. So we need to subscribe the bridge to the blocking switchdev notification chain too. This patch: - keeps the driver-side perception of the switchdev_bridge_port_{,un}offload unchanged - moves the implementation of switchdev_bridge_port_{,un}offload from the bridge module into the switchdev module. - makes everybody that is subscribed to the switchdev blocking notifier chain "hear" offload & unoffload events - makes the bridge driver subscribe and handle those events - moves the bridge driver's handling of those events into 2 new functions called br_switchdev_port_{,un}offload. These functions contain in fact the core of the logic that was previously in switchdev_bridge_port_{,un}offload, just that now we go through an extra indirection layer to reach them. Unlike all the other switchdev notification structures, the structure used to carry the bridge port information, struct switchdev_notifier_brport_info, does not contain a "bool handled". This is because in the current usage pattern, we always know that a switchdev bridge port offloading event will be handled by the bridge, because the switchdev_bridge_port_offload() call was initiated by a NETDEV_CHANGEUPPER event in the first place, where info->upper_dev is a bridge. So if the bridge wasn't loaded, then the CHANGEUPPER event couldn't have happened. Signed-off-by: Vladimir Oltean <vladimir.oltean@nxp.com> Tested-by: Grygorii Strashko <grygorii.strashko@ti.com> Signed-off-by: David S. Miller <davem@davemloft.net>
2021-08-04 04:34:08 +08:00
err = register_switchdev_blocking_notifier(&br_switchdev_blocking_notifier);
if (err)
goto err_out5;
net: make switchdev_bridge_port_{,unoffload} loosely coupled with the bridge With the introduction of explicit offloading API in switchdev in commit 2f5dc00f7a3e ("net: bridge: switchdev: let drivers inform which bridge ports are offloaded"), we started having Ethernet switch drivers calling directly into a function exported by net/bridge/br_switchdev.c, which is a function exported by the bridge driver. This means that drivers that did not have an explicit dependency on the bridge before, like cpsw and am65-cpsw, now do - otherwise it is not possible to call a symbol exported by a driver that can be built as module unless you are a module too. There was an attempt to solve the dependency issue in the form of commit b0e81817629a ("net: build all switchdev drivers as modules when the bridge is a module"). Grygorii Strashko, however, says about it: | In my opinion, the problem is a bit bigger here than just fixing the | build :( | | In case, of ^cpsw the switchdev mode is kinda optional and in many | cases (especially for testing purposes, NFS) the multi-mac mode is | still preferable mode. | | There were no such tight dependency between switchdev drivers and | bridge core before and switchdev serviced as independent, notification | based layer between them, so ^cpsw still can be "Y" and bridge can be | "M". Now for mostly every kernel build configuration the CONFIG_BRIDGE | will need to be set as "Y", or we will have to update drivers to | support build with BRIDGE=n and maintain separate builds for | networking vs non-networking testing. But is this enough? Wouldn't | it cause 'chain reaction' required to add more and more "Y" options | (like CONFIG_VLAN_8021Q)? | | PS. Just to be sure we on the same page - ARM builds will be forced | (with this patch) to have CONFIG_TI_CPSW_SWITCHDEV=m and so all our | automation testing will just fail with omap2plus_defconfig. In the light of this, it would be desirable for some configurations to avoid dependencies between switchdev drivers and the bridge, and have the switchdev mode as completely optional within the driver. Arnd Bergmann also tried to write a patch which better expressed the build time dependency for Ethernet switch drivers where the switchdev support is optional, like cpsw/am65-cpsw, and this made the drivers follow the bridge (compile as module if the bridge is a module) only if the optional switchdev support in the driver was enabled in the first place: https://patchwork.kernel.org/project/netdevbpf/patch/20210802144813.1152762-1-arnd@kernel.org/ but this still did not solve the fact that cpsw and am65-cpsw now must be built as modules when the bridge is a module - it just expressed correctly that optional dependency. But the new behavior is an apparent regression from Grygorii's perspective. So to support the use case where the Ethernet driver is built-in, NET_SWITCHDEV (a bool option) is enabled, and the bridge is a module, we need a framework that can handle the possible absence of the bridge from the running system, i.e. runtime bloatware as opposed to build-time bloatware. Luckily we already have this framework, since switchdev has been using it extensively. Events from the bridge side are transmitted to the driver side using notifier chains - this was originally done so that unrelated drivers could snoop for events emitted by the bridge towards ports that are implemented by other drivers (think of a switch driver with LAG offload that listens for switchdev events on a bonding/team interface that it offloads). There are also events which are transmitted from the driver side to the bridge side, which again are modeled using notifiers. SWITCHDEV_FDB_ADD_TO_BRIDGE is an example of this, and deals with notifying the bridge that a MAC address has been dynamically learned. So there is a precedent we can use for modeling the new framework. The difference compared to SWITCHDEV_FDB_ADD_TO_BRIDGE is that the work that the bridge needs to do when a port becomes offloaded is blocking in its nature: replay VLANs, MDBs etc. The calling context is indeed blocking (we are under rtnl_mutex), but the existing switchdev notification chain that the bridge is subscribed to is only the atomic one. So we need to subscribe the bridge to the blocking switchdev notification chain too. This patch: - keeps the driver-side perception of the switchdev_bridge_port_{,un}offload unchanged - moves the implementation of switchdev_bridge_port_{,un}offload from the bridge module into the switchdev module. - makes everybody that is subscribed to the switchdev blocking notifier chain "hear" offload & unoffload events - makes the bridge driver subscribe and handle those events - moves the bridge driver's handling of those events into 2 new functions called br_switchdev_port_{,un}offload. These functions contain in fact the core of the logic that was previously in switchdev_bridge_port_{,un}offload, just that now we go through an extra indirection layer to reach them. Unlike all the other switchdev notification structures, the structure used to carry the bridge port information, struct switchdev_notifier_brport_info, does not contain a "bool handled". This is because in the current usage pattern, we always know that a switchdev bridge port offloading event will be handled by the bridge, because the switchdev_bridge_port_offload() call was initiated by a NETDEV_CHANGEUPPER event in the first place, where info->upper_dev is a bridge. So if the bridge wasn't loaded, then the CHANGEUPPER event couldn't have happened. Signed-off-by: Vladimir Oltean <vladimir.oltean@nxp.com> Tested-by: Grygorii Strashko <grygorii.strashko@ti.com> Signed-off-by: David S. Miller <davem@davemloft.net>
2021-08-04 04:34:08 +08:00
err = br_netlink_init();
if (err)
goto err_out6;
brioctl_set(br_ioctl_stub);
#if IS_ENABLED(CONFIG_ATM_LANE)
br_fdb_test_addr_hook = br_fdb_test_addr;
#endif
#if IS_MODULE(CONFIG_BRIDGE_NETFILTER)
pr_info("bridge: filtering via arp/ip/ip6tables is no longer available "
"by default. Update your scripts to load br_netfilter if you "
"need this.\n");
#endif
return 0;
net: make switchdev_bridge_port_{,unoffload} loosely coupled with the bridge With the introduction of explicit offloading API in switchdev in commit 2f5dc00f7a3e ("net: bridge: switchdev: let drivers inform which bridge ports are offloaded"), we started having Ethernet switch drivers calling directly into a function exported by net/bridge/br_switchdev.c, which is a function exported by the bridge driver. This means that drivers that did not have an explicit dependency on the bridge before, like cpsw and am65-cpsw, now do - otherwise it is not possible to call a symbol exported by a driver that can be built as module unless you are a module too. There was an attempt to solve the dependency issue in the form of commit b0e81817629a ("net: build all switchdev drivers as modules when the bridge is a module"). Grygorii Strashko, however, says about it: | In my opinion, the problem is a bit bigger here than just fixing the | build :( | | In case, of ^cpsw the switchdev mode is kinda optional and in many | cases (especially for testing purposes, NFS) the multi-mac mode is | still preferable mode. | | There were no such tight dependency between switchdev drivers and | bridge core before and switchdev serviced as independent, notification | based layer between them, so ^cpsw still can be "Y" and bridge can be | "M". Now for mostly every kernel build configuration the CONFIG_BRIDGE | will need to be set as "Y", or we will have to update drivers to | support build with BRIDGE=n and maintain separate builds for | networking vs non-networking testing. But is this enough? Wouldn't | it cause 'chain reaction' required to add more and more "Y" options | (like CONFIG_VLAN_8021Q)? | | PS. Just to be sure we on the same page - ARM builds will be forced | (with this patch) to have CONFIG_TI_CPSW_SWITCHDEV=m and so all our | automation testing will just fail with omap2plus_defconfig. In the light of this, it would be desirable for some configurations to avoid dependencies between switchdev drivers and the bridge, and have the switchdev mode as completely optional within the driver. Arnd Bergmann also tried to write a patch which better expressed the build time dependency for Ethernet switch drivers where the switchdev support is optional, like cpsw/am65-cpsw, and this made the drivers follow the bridge (compile as module if the bridge is a module) only if the optional switchdev support in the driver was enabled in the first place: https://patchwork.kernel.org/project/netdevbpf/patch/20210802144813.1152762-1-arnd@kernel.org/ but this still did not solve the fact that cpsw and am65-cpsw now must be built as modules when the bridge is a module - it just expressed correctly that optional dependency. But the new behavior is an apparent regression from Grygorii's perspective. So to support the use case where the Ethernet driver is built-in, NET_SWITCHDEV (a bool option) is enabled, and the bridge is a module, we need a framework that can handle the possible absence of the bridge from the running system, i.e. runtime bloatware as opposed to build-time bloatware. Luckily we already have this framework, since switchdev has been using it extensively. Events from the bridge side are transmitted to the driver side using notifier chains - this was originally done so that unrelated drivers could snoop for events emitted by the bridge towards ports that are implemented by other drivers (think of a switch driver with LAG offload that listens for switchdev events on a bonding/team interface that it offloads). There are also events which are transmitted from the driver side to the bridge side, which again are modeled using notifiers. SWITCHDEV_FDB_ADD_TO_BRIDGE is an example of this, and deals with notifying the bridge that a MAC address has been dynamically learned. So there is a precedent we can use for modeling the new framework. The difference compared to SWITCHDEV_FDB_ADD_TO_BRIDGE is that the work that the bridge needs to do when a port becomes offloaded is blocking in its nature: replay VLANs, MDBs etc. The calling context is indeed blocking (we are under rtnl_mutex), but the existing switchdev notification chain that the bridge is subscribed to is only the atomic one. So we need to subscribe the bridge to the blocking switchdev notification chain too. This patch: - keeps the driver-side perception of the switchdev_bridge_port_{,un}offload unchanged - moves the implementation of switchdev_bridge_port_{,un}offload from the bridge module into the switchdev module. - makes everybody that is subscribed to the switchdev blocking notifier chain "hear" offload & unoffload events - makes the bridge driver subscribe and handle those events - moves the bridge driver's handling of those events into 2 new functions called br_switchdev_port_{,un}offload. These functions contain in fact the core of the logic that was previously in switchdev_bridge_port_{,un}offload, just that now we go through an extra indirection layer to reach them. Unlike all the other switchdev notification structures, the structure used to carry the bridge port information, struct switchdev_notifier_brport_info, does not contain a "bool handled". This is because in the current usage pattern, we always know that a switchdev bridge port offloading event will be handled by the bridge, because the switchdev_bridge_port_offload() call was initiated by a NETDEV_CHANGEUPPER event in the first place, where info->upper_dev is a bridge. So if the bridge wasn't loaded, then the CHANGEUPPER event couldn't have happened. Signed-off-by: Vladimir Oltean <vladimir.oltean@nxp.com> Tested-by: Grygorii Strashko <grygorii.strashko@ti.com> Signed-off-by: David S. Miller <davem@davemloft.net>
2021-08-04 04:34:08 +08:00
err_out6:
unregister_switchdev_blocking_notifier(&br_switchdev_blocking_notifier);
err_out5:
unregister_switchdev_notifier(&br_switchdev_notifier);
err_out4:
unregister_netdevice_notifier(&br_device_notifier);
err_out3:
br_nf_core_fini();
err_out2:
unregister_pernet_subsys(&br_net_ops);
err_out1:
br_fdb_fini();
err_out:
stp_proto_unregister(&br_stp_proto);
return err;
}
static void __exit br_deinit(void)
{
stp_proto_unregister(&br_stp_proto);
br_netlink_fini();
net: make switchdev_bridge_port_{,unoffload} loosely coupled with the bridge With the introduction of explicit offloading API in switchdev in commit 2f5dc00f7a3e ("net: bridge: switchdev: let drivers inform which bridge ports are offloaded"), we started having Ethernet switch drivers calling directly into a function exported by net/bridge/br_switchdev.c, which is a function exported by the bridge driver. This means that drivers that did not have an explicit dependency on the bridge before, like cpsw and am65-cpsw, now do - otherwise it is not possible to call a symbol exported by a driver that can be built as module unless you are a module too. There was an attempt to solve the dependency issue in the form of commit b0e81817629a ("net: build all switchdev drivers as modules when the bridge is a module"). Grygorii Strashko, however, says about it: | In my opinion, the problem is a bit bigger here than just fixing the | build :( | | In case, of ^cpsw the switchdev mode is kinda optional and in many | cases (especially for testing purposes, NFS) the multi-mac mode is | still preferable mode. | | There were no such tight dependency between switchdev drivers and | bridge core before and switchdev serviced as independent, notification | based layer between them, so ^cpsw still can be "Y" and bridge can be | "M". Now for mostly every kernel build configuration the CONFIG_BRIDGE | will need to be set as "Y", or we will have to update drivers to | support build with BRIDGE=n and maintain separate builds for | networking vs non-networking testing. But is this enough? Wouldn't | it cause 'chain reaction' required to add more and more "Y" options | (like CONFIG_VLAN_8021Q)? | | PS. Just to be sure we on the same page - ARM builds will be forced | (with this patch) to have CONFIG_TI_CPSW_SWITCHDEV=m and so all our | automation testing will just fail with omap2plus_defconfig. In the light of this, it would be desirable for some configurations to avoid dependencies between switchdev drivers and the bridge, and have the switchdev mode as completely optional within the driver. Arnd Bergmann also tried to write a patch which better expressed the build time dependency for Ethernet switch drivers where the switchdev support is optional, like cpsw/am65-cpsw, and this made the drivers follow the bridge (compile as module if the bridge is a module) only if the optional switchdev support in the driver was enabled in the first place: https://patchwork.kernel.org/project/netdevbpf/patch/20210802144813.1152762-1-arnd@kernel.org/ but this still did not solve the fact that cpsw and am65-cpsw now must be built as modules when the bridge is a module - it just expressed correctly that optional dependency. But the new behavior is an apparent regression from Grygorii's perspective. So to support the use case where the Ethernet driver is built-in, NET_SWITCHDEV (a bool option) is enabled, and the bridge is a module, we need a framework that can handle the possible absence of the bridge from the running system, i.e. runtime bloatware as opposed to build-time bloatware. Luckily we already have this framework, since switchdev has been using it extensively. Events from the bridge side are transmitted to the driver side using notifier chains - this was originally done so that unrelated drivers could snoop for events emitted by the bridge towards ports that are implemented by other drivers (think of a switch driver with LAG offload that listens for switchdev events on a bonding/team interface that it offloads). There are also events which are transmitted from the driver side to the bridge side, which again are modeled using notifiers. SWITCHDEV_FDB_ADD_TO_BRIDGE is an example of this, and deals with notifying the bridge that a MAC address has been dynamically learned. So there is a precedent we can use for modeling the new framework. The difference compared to SWITCHDEV_FDB_ADD_TO_BRIDGE is that the work that the bridge needs to do when a port becomes offloaded is blocking in its nature: replay VLANs, MDBs etc. The calling context is indeed blocking (we are under rtnl_mutex), but the existing switchdev notification chain that the bridge is subscribed to is only the atomic one. So we need to subscribe the bridge to the blocking switchdev notification chain too. This patch: - keeps the driver-side perception of the switchdev_bridge_port_{,un}offload unchanged - moves the implementation of switchdev_bridge_port_{,un}offload from the bridge module into the switchdev module. - makes everybody that is subscribed to the switchdev blocking notifier chain "hear" offload & unoffload events - makes the bridge driver subscribe and handle those events - moves the bridge driver's handling of those events into 2 new functions called br_switchdev_port_{,un}offload. These functions contain in fact the core of the logic that was previously in switchdev_bridge_port_{,un}offload, just that now we go through an extra indirection layer to reach them. Unlike all the other switchdev notification structures, the structure used to carry the bridge port information, struct switchdev_notifier_brport_info, does not contain a "bool handled". This is because in the current usage pattern, we always know that a switchdev bridge port offloading event will be handled by the bridge, because the switchdev_bridge_port_offload() call was initiated by a NETDEV_CHANGEUPPER event in the first place, where info->upper_dev is a bridge. So if the bridge wasn't loaded, then the CHANGEUPPER event couldn't have happened. Signed-off-by: Vladimir Oltean <vladimir.oltean@nxp.com> Tested-by: Grygorii Strashko <grygorii.strashko@ti.com> Signed-off-by: David S. Miller <davem@davemloft.net>
2021-08-04 04:34:08 +08:00
unregister_switchdev_blocking_notifier(&br_switchdev_blocking_notifier);
unregister_switchdev_notifier(&br_switchdev_notifier);
unregister_netdevice_notifier(&br_device_notifier);
brioctl_set(NULL);
unregister_pernet_subsys(&br_net_ops);
rcu_barrier(); /* Wait for completion of call_rcu()'s */
br_nf_core_fini();
#if IS_ENABLED(CONFIG_ATM_LANE)
br_fdb_test_addr_hook = NULL;
#endif
br_fdb_fini();
}
module_init(br_init)
module_exit(br_deinit)
MODULE_LICENSE("GPL");
MODULE_VERSION(BR_VERSION);
MODULE_ALIAS_RTNL_LINK("bridge");
MODULE_DESCRIPTION("Ethernet bridge driver");