mirror of
https://git.kernel.org/pub/scm/linux/kernel/git/stable/linux.git
synced 2024-08-23 09:19:51 +00:00
![Si-Wei Liu](/assets/img/avatar_default.png)
When a netdev appears through hot plug then gets enslaved by a failover
master that is already up and running, the slave will be opened
right away after getting enslaved. Today there's a race that userspace
(udev) may fail to rename the slave if the kernel (net_failover)
opens the slave earlier than when the userspace rename happens.
Unlike bond or team, the primary slave of failover can't be renamed by
userspace ahead of time, since the kernel initiated auto-enslavement is
unable to, or rather, is never meant to be synchronized with the rename
request from userspace.
As the failover slave interfaces are not designed to be operated
directly by userspace apps: IP configuration, filter rules with
regard to network traffic passing and etc., should all be done on master
interface. In general, userspace apps only care about the
name of master interface, while slave names are less important as long
as admin users can see reliable names that may carry
other information describing the netdev. For e.g., they can infer that
"ens3nsby" is a standby slave of "ens3", while for a
name like "eth0" they can't tell which master it belongs to.
Historically the name of IFF_UP interface can't be changed because
there might be admin script or management software that is already
relying on such behavior and assumes that the slave name can't be
changed once UP. But failover is special: with the in-kernel
auto-enslavement mechanism, the userspace expectation for device
enumeration and bring-up order is already broken. Previously initramfs
and various userspace config tools were modified to bypass failover
slaves because of auto-enslavement and duplicate MAC address. Similarly,
in case that users care about seeing reliable slave name, the new type
of failover slaves needs to be taken care of specifically in userspace
anyway.
It's less risky to lift up the rename restriction on failover slave
which is already UP. Although it's possible this change may potentially
break userspace component (most likely configuration scripts or
management software) that assumes slave name can't be changed while
UP, it's relatively a limited and controllable set among all userspace
components, which can be fixed specifically to listen for the rename
events on failover slaves. Userspace component interacting with slaves
is expected to be changed to operate on failover master interface
instead, as the failover slave is dynamic in nature which may come and
go at any point. The goal is to make the role of failover slaves less
relevant, and userspace components should only deal with failover master
in the long run.
Fixes: 30c8bd5aa8
("net: Introduce generic failover module")
Signed-off-by: Si-Wei Liu <si-wei.liu@oracle.com>
Reviewed-by: Liran Alon <liran.alon@oracle.com>
Acked-by: Sridhar Samudrala <sridhar.samudrala@intel.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
315 lines
7.4 KiB
C
315 lines
7.4 KiB
C
// SPDX-License-Identifier: GPL-2.0
|
|
/* Copyright (c) 2018, Intel Corporation. */
|
|
|
|
/* A common module to handle registrations and notifications for paravirtual
|
|
* drivers to enable accelerated datapath and support VF live migration.
|
|
*
|
|
* The notifier and event handling code is based on netvsc driver.
|
|
*/
|
|
|
|
#include <linux/module.h>
|
|
#include <linux/etherdevice.h>
|
|
#include <uapi/linux/if_arp.h>
|
|
#include <linux/rtnetlink.h>
|
|
#include <linux/if_vlan.h>
|
|
#include <net/failover.h>
|
|
|
|
static LIST_HEAD(failover_list);
|
|
static DEFINE_SPINLOCK(failover_lock);
|
|
|
|
static struct net_device *failover_get_bymac(u8 *mac, struct failover_ops **ops)
|
|
{
|
|
struct net_device *failover_dev;
|
|
struct failover *failover;
|
|
|
|
spin_lock(&failover_lock);
|
|
list_for_each_entry(failover, &failover_list, list) {
|
|
failover_dev = rtnl_dereference(failover->failover_dev);
|
|
if (ether_addr_equal(failover_dev->perm_addr, mac)) {
|
|
*ops = rtnl_dereference(failover->ops);
|
|
spin_unlock(&failover_lock);
|
|
return failover_dev;
|
|
}
|
|
}
|
|
spin_unlock(&failover_lock);
|
|
return NULL;
|
|
}
|
|
|
|
/**
|
|
* failover_slave_register - Register a slave netdev
|
|
*
|
|
* @slave_dev: slave netdev that is being registered
|
|
*
|
|
* Registers a slave device to a failover instance. Only ethernet devices
|
|
* are supported.
|
|
*/
|
|
static int failover_slave_register(struct net_device *slave_dev)
|
|
{
|
|
struct netdev_lag_upper_info lag_upper_info;
|
|
struct net_device *failover_dev;
|
|
struct failover_ops *fops;
|
|
int err;
|
|
|
|
if (slave_dev->type != ARPHRD_ETHER)
|
|
goto done;
|
|
|
|
ASSERT_RTNL();
|
|
|
|
failover_dev = failover_get_bymac(slave_dev->perm_addr, &fops);
|
|
if (!failover_dev)
|
|
goto done;
|
|
|
|
if (fops && fops->slave_pre_register &&
|
|
fops->slave_pre_register(slave_dev, failover_dev))
|
|
goto done;
|
|
|
|
err = netdev_rx_handler_register(slave_dev, fops->slave_handle_frame,
|
|
failover_dev);
|
|
if (err) {
|
|
netdev_err(slave_dev, "can not register failover rx handler (err = %d)\n",
|
|
err);
|
|
goto done;
|
|
}
|
|
|
|
lag_upper_info.tx_type = NETDEV_LAG_TX_TYPE_ACTIVEBACKUP;
|
|
err = netdev_master_upper_dev_link(slave_dev, failover_dev, NULL,
|
|
&lag_upper_info, NULL);
|
|
if (err) {
|
|
netdev_err(slave_dev, "can not set failover device %s (err = %d)\n",
|
|
failover_dev->name, err);
|
|
goto err_upper_link;
|
|
}
|
|
|
|
slave_dev->priv_flags |= (IFF_FAILOVER_SLAVE | IFF_LIVE_RENAME_OK);
|
|
|
|
if (fops && fops->slave_register &&
|
|
!fops->slave_register(slave_dev, failover_dev))
|
|
return NOTIFY_OK;
|
|
|
|
netdev_upper_dev_unlink(slave_dev, failover_dev);
|
|
slave_dev->priv_flags &= ~(IFF_FAILOVER_SLAVE | IFF_LIVE_RENAME_OK);
|
|
err_upper_link:
|
|
netdev_rx_handler_unregister(slave_dev);
|
|
done:
|
|
return NOTIFY_DONE;
|
|
}
|
|
|
|
/**
|
|
* failover_slave_unregister - Unregister a slave netdev
|
|
*
|
|
* @slave_dev: slave netdev that is being unregistered
|
|
*
|
|
* Unregisters a slave device from a failover instance.
|
|
*/
|
|
int failover_slave_unregister(struct net_device *slave_dev)
|
|
{
|
|
struct net_device *failover_dev;
|
|
struct failover_ops *fops;
|
|
|
|
if (!netif_is_failover_slave(slave_dev))
|
|
goto done;
|
|
|
|
ASSERT_RTNL();
|
|
|
|
failover_dev = failover_get_bymac(slave_dev->perm_addr, &fops);
|
|
if (!failover_dev)
|
|
goto done;
|
|
|
|
if (fops && fops->slave_pre_unregister &&
|
|
fops->slave_pre_unregister(slave_dev, failover_dev))
|
|
goto done;
|
|
|
|
netdev_rx_handler_unregister(slave_dev);
|
|
netdev_upper_dev_unlink(slave_dev, failover_dev);
|
|
slave_dev->priv_flags &= ~(IFF_FAILOVER_SLAVE | IFF_LIVE_RENAME_OK);
|
|
|
|
if (fops && fops->slave_unregister &&
|
|
!fops->slave_unregister(slave_dev, failover_dev))
|
|
return NOTIFY_OK;
|
|
|
|
done:
|
|
return NOTIFY_DONE;
|
|
}
|
|
EXPORT_SYMBOL_GPL(failover_slave_unregister);
|
|
|
|
static int failover_slave_link_change(struct net_device *slave_dev)
|
|
{
|
|
struct net_device *failover_dev;
|
|
struct failover_ops *fops;
|
|
|
|
if (!netif_is_failover_slave(slave_dev))
|
|
goto done;
|
|
|
|
ASSERT_RTNL();
|
|
|
|
failover_dev = failover_get_bymac(slave_dev->perm_addr, &fops);
|
|
if (!failover_dev)
|
|
goto done;
|
|
|
|
if (!netif_running(failover_dev))
|
|
goto done;
|
|
|
|
if (fops && fops->slave_link_change &&
|
|
!fops->slave_link_change(slave_dev, failover_dev))
|
|
return NOTIFY_OK;
|
|
|
|
done:
|
|
return NOTIFY_DONE;
|
|
}
|
|
|
|
static int failover_slave_name_change(struct net_device *slave_dev)
|
|
{
|
|
struct net_device *failover_dev;
|
|
struct failover_ops *fops;
|
|
|
|
if (!netif_is_failover_slave(slave_dev))
|
|
goto done;
|
|
|
|
ASSERT_RTNL();
|
|
|
|
failover_dev = failover_get_bymac(slave_dev->perm_addr, &fops);
|
|
if (!failover_dev)
|
|
goto done;
|
|
|
|
if (!netif_running(failover_dev))
|
|
goto done;
|
|
|
|
if (fops && fops->slave_name_change &&
|
|
!fops->slave_name_change(slave_dev, failover_dev))
|
|
return NOTIFY_OK;
|
|
|
|
done:
|
|
return NOTIFY_DONE;
|
|
}
|
|
|
|
static int
|
|
failover_event(struct notifier_block *this, unsigned long event, void *ptr)
|
|
{
|
|
struct net_device *event_dev = netdev_notifier_info_to_dev(ptr);
|
|
|
|
/* Skip parent events */
|
|
if (netif_is_failover(event_dev))
|
|
return NOTIFY_DONE;
|
|
|
|
switch (event) {
|
|
case NETDEV_REGISTER:
|
|
return failover_slave_register(event_dev);
|
|
case NETDEV_UNREGISTER:
|
|
return failover_slave_unregister(event_dev);
|
|
case NETDEV_UP:
|
|
case NETDEV_DOWN:
|
|
case NETDEV_CHANGE:
|
|
return failover_slave_link_change(event_dev);
|
|
case NETDEV_CHANGENAME:
|
|
return failover_slave_name_change(event_dev);
|
|
default:
|
|
return NOTIFY_DONE;
|
|
}
|
|
}
|
|
|
|
static struct notifier_block failover_notifier = {
|
|
.notifier_call = failover_event,
|
|
};
|
|
|
|
static void
|
|
failover_existing_slave_register(struct net_device *failover_dev)
|
|
{
|
|
struct net *net = dev_net(failover_dev);
|
|
struct net_device *dev;
|
|
|
|
rtnl_lock();
|
|
for_each_netdev(net, dev) {
|
|
if (netif_is_failover(dev))
|
|
continue;
|
|
if (ether_addr_equal(failover_dev->perm_addr, dev->perm_addr))
|
|
failover_slave_register(dev);
|
|
}
|
|
rtnl_unlock();
|
|
}
|
|
|
|
/**
|
|
* failover_register - Register a failover instance
|
|
*
|
|
* @dev: failover netdev
|
|
* @ops: failover ops
|
|
*
|
|
* Allocate and register a failover instance for a failover netdev. ops
|
|
* provides handlers for slave device register/unregister/link change/
|
|
* name change events.
|
|
*
|
|
* Return: pointer to failover instance
|
|
*/
|
|
struct failover *failover_register(struct net_device *dev,
|
|
struct failover_ops *ops)
|
|
{
|
|
struct failover *failover;
|
|
|
|
if (dev->type != ARPHRD_ETHER)
|
|
return ERR_PTR(-EINVAL);
|
|
|
|
failover = kzalloc(sizeof(*failover), GFP_KERNEL);
|
|
if (!failover)
|
|
return ERR_PTR(-ENOMEM);
|
|
|
|
rcu_assign_pointer(failover->ops, ops);
|
|
dev_hold(dev);
|
|
dev->priv_flags |= IFF_FAILOVER;
|
|
rcu_assign_pointer(failover->failover_dev, dev);
|
|
|
|
spin_lock(&failover_lock);
|
|
list_add_tail(&failover->list, &failover_list);
|
|
spin_unlock(&failover_lock);
|
|
|
|
netdev_info(dev, "failover master:%s registered\n", dev->name);
|
|
|
|
failover_existing_slave_register(dev);
|
|
|
|
return failover;
|
|
}
|
|
EXPORT_SYMBOL_GPL(failover_register);
|
|
|
|
/**
|
|
* failover_unregister - Unregister a failover instance
|
|
*
|
|
* @failover: pointer to failover instance
|
|
*
|
|
* Unregisters and frees a failover instance.
|
|
*/
|
|
void failover_unregister(struct failover *failover)
|
|
{
|
|
struct net_device *failover_dev;
|
|
|
|
failover_dev = rcu_dereference(failover->failover_dev);
|
|
|
|
netdev_info(failover_dev, "failover master:%s unregistered\n",
|
|
failover_dev->name);
|
|
|
|
failover_dev->priv_flags &= ~IFF_FAILOVER;
|
|
dev_put(failover_dev);
|
|
|
|
spin_lock(&failover_lock);
|
|
list_del(&failover->list);
|
|
spin_unlock(&failover_lock);
|
|
|
|
kfree(failover);
|
|
}
|
|
EXPORT_SYMBOL_GPL(failover_unregister);
|
|
|
|
static __init int
|
|
failover_init(void)
|
|
{
|
|
register_netdevice_notifier(&failover_notifier);
|
|
|
|
return 0;
|
|
}
|
|
module_init(failover_init);
|
|
|
|
static __exit
|
|
void failover_exit(void)
|
|
{
|
|
unregister_netdevice_notifier(&failover_notifier);
|
|
}
|
|
module_exit(failover_exit);
|
|
|
|
MODULE_DESCRIPTION("Generic failover infrastructure/interface");
|
|
MODULE_LICENSE("GPL v2");
|