linux/net/core/link_watch.c
Willy Tarreau 6922110d15 net: linkwatch: fix failure to restore device state across suspend/resume
After migrating my laptop from 4.19-LTS to 5.4-LTS a while ago I noticed
that my Ethernet port to which a bond and a VLAN interface are attached
appeared to remain up after resuming from suspend with the cable unplugged
(and that problem still persists with 5.10-LTS).

It happens that the following happens:

  - the network driver (e1000e here) prepares to suspend, calls e1000e_down()
    which calls netif_carrier_off() to signal that the link is going down.
  - netif_carrier_off() adds a link_watch event to the list of events for
    this device
  - the device is completely stopped.
  - the machine suspends
  - the cable is unplugged and the machine brought to another location
  - the machine is resumed
  - the queued linkwatch events are processed for the device
  - the device doesn't yet have the __LINK_STATE_PRESENT bit and its events
    are silently dropped
  - the device is resumed with its link down
  - the upper VLAN and bond interfaces are never notified that the link had
    been turned down and remain up
  - the only way to provoke a change is to physically connect the machine
    to a port and possibly unplug it.

The state after resume looks like this:
  $ ip -br li | egrep 'bond|eth'
  bond0            UP             e8:6a:64:64:64:64 <BROADCAST,MULTICAST,MASTER,UP,LOWER_UP>
  eth0             DOWN           e8:6a:64:64:64:64 <NO-CARRIER,BROADCAST,MULTICAST,SLAVE,UP>
  eth0.2@eth0      UP             e8:6a:64:64:64:64 <BROADCAST,MULTICAST,SLAVE,UP,LOWER_UP>

Placing an explicit call to netdev_state_change() either in the suspend
or the resume code in the NIC driver worked around this but the solution
is not satisfying.

The issue in fact really is in link_watch that loses events while it
ought not to. It happens that the test for the device being present was
added by commit 124eee3f69 ("net: linkwatch: add check for netdevice
being present to linkwatch_do_dev") in 4.20 to avoid an access to
devices that are not present.

Instead of dropping events, this patch proceeds slightly differently by
postponing their handling so that they happen after the device is fully
resumed.

Fixes: 124eee3f69 ("net: linkwatch: add check for netdevice being present to linkwatch_do_dev")
Link: https://lists.openwall.net/netdev/2018/03/15/62
Cc: Heiner Kallweit <hkallweit1@gmail.com>
Cc: Geert Uytterhoeven <geert+renesas@glider.be>
Cc: Florian Fainelli <f.fainelli@gmail.com>
Signed-off-by: Willy Tarreau <w@1wt.eu>
Link: https://lore.kernel.org/r/20210809160628.22623-1-w@1wt.eu
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
2021-08-11 14:43:16 -07:00

269 lines
5.8 KiB
C

// SPDX-License-Identifier: GPL-2.0-or-later
/*
* Linux network device link state notification
*
* Author:
* Stefan Rompf <sux@loplof.de>
*/
#include <linux/module.h>
#include <linux/netdevice.h>
#include <linux/if.h>
#include <net/sock.h>
#include <net/pkt_sched.h>
#include <linux/rtnetlink.h>
#include <linux/jiffies.h>
#include <linux/spinlock.h>
#include <linux/workqueue.h>
#include <linux/bitops.h>
#include <linux/types.h>
enum lw_bits {
LW_URGENT = 0,
};
static unsigned long linkwatch_flags;
static unsigned long linkwatch_nextevent;
static void linkwatch_event(struct work_struct *dummy);
static DECLARE_DELAYED_WORK(linkwatch_work, linkwatch_event);
static LIST_HEAD(lweventlist);
static DEFINE_SPINLOCK(lweventlist_lock);
static unsigned char default_operstate(const struct net_device *dev)
{
if (netif_testing(dev))
return IF_OPER_TESTING;
if (!netif_carrier_ok(dev))
return (dev->ifindex != dev_get_iflink(dev) ?
IF_OPER_LOWERLAYERDOWN : IF_OPER_DOWN);
if (netif_dormant(dev))
return IF_OPER_DORMANT;
return IF_OPER_UP;
}
static void rfc2863_policy(struct net_device *dev)
{
unsigned char operstate = default_operstate(dev);
if (operstate == dev->operstate)
return;
write_lock_bh(&dev_base_lock);
switch(dev->link_mode) {
case IF_LINK_MODE_TESTING:
if (operstate == IF_OPER_UP)
operstate = IF_OPER_TESTING;
break;
case IF_LINK_MODE_DORMANT:
if (operstate == IF_OPER_UP)
operstate = IF_OPER_DORMANT;
break;
case IF_LINK_MODE_DEFAULT:
default:
break;
}
dev->operstate = operstate;
write_unlock_bh(&dev_base_lock);
}
void linkwatch_init_dev(struct net_device *dev)
{
/* Handle pre-registration link state changes */
if (!netif_carrier_ok(dev) || netif_dormant(dev) ||
netif_testing(dev))
rfc2863_policy(dev);
}
static bool linkwatch_urgent_event(struct net_device *dev)
{
if (!netif_running(dev))
return false;
if (dev->ifindex != dev_get_iflink(dev))
return true;
if (netif_is_lag_port(dev) || netif_is_lag_master(dev))
return true;
return netif_carrier_ok(dev) && qdisc_tx_changing(dev);
}
static void linkwatch_add_event(struct net_device *dev)
{
unsigned long flags;
spin_lock_irqsave(&lweventlist_lock, flags);
if (list_empty(&dev->link_watch_list)) {
list_add_tail(&dev->link_watch_list, &lweventlist);
dev_hold(dev);
}
spin_unlock_irqrestore(&lweventlist_lock, flags);
}
static void linkwatch_schedule_work(int urgent)
{
unsigned long delay = linkwatch_nextevent - jiffies;
if (test_bit(LW_URGENT, &linkwatch_flags))
return;
/* Minimise down-time: drop delay for up event. */
if (urgent) {
if (test_and_set_bit(LW_URGENT, &linkwatch_flags))
return;
delay = 0;
}
/* If we wrap around we'll delay it by at most HZ. */
if (delay > HZ)
delay = 0;
/*
* If urgent, schedule immediate execution; otherwise, don't
* override the existing timer.
*/
if (test_bit(LW_URGENT, &linkwatch_flags))
mod_delayed_work(system_wq, &linkwatch_work, 0);
else
schedule_delayed_work(&linkwatch_work, delay);
}
static void linkwatch_do_dev(struct net_device *dev)
{
/*
* Make sure the above read is complete since it can be
* rewritten as soon as we clear the bit below.
*/
smp_mb__before_atomic();
/* We are about to handle this device,
* so new events can be accepted
*/
clear_bit(__LINK_STATE_LINKWATCH_PENDING, &dev->state);
rfc2863_policy(dev);
if (dev->flags & IFF_UP) {
if (netif_carrier_ok(dev))
dev_activate(dev);
else
dev_deactivate(dev);
netdev_state_change(dev);
}
dev_put(dev);
}
static void __linkwatch_run_queue(int urgent_only)
{
#define MAX_DO_DEV_PER_LOOP 100
int do_dev = MAX_DO_DEV_PER_LOOP;
struct net_device *dev;
LIST_HEAD(wrk);
/* Give urgent case more budget */
if (urgent_only)
do_dev += MAX_DO_DEV_PER_LOOP;
/*
* Limit the number of linkwatch events to one
* per second so that a runaway driver does not
* cause a storm of messages on the netlink
* socket. This limit does not apply to up events
* while the device qdisc is down.
*/
if (!urgent_only)
linkwatch_nextevent = jiffies + HZ;
/* Limit wrap-around effect on delay. */
else if (time_after(linkwatch_nextevent, jiffies + HZ))
linkwatch_nextevent = jiffies;
clear_bit(LW_URGENT, &linkwatch_flags);
spin_lock_irq(&lweventlist_lock);
list_splice_init(&lweventlist, &wrk);
while (!list_empty(&wrk) && do_dev > 0) {
dev = list_first_entry(&wrk, struct net_device, link_watch_list);
list_del_init(&dev->link_watch_list);
if (!netif_device_present(dev) ||
(urgent_only && !linkwatch_urgent_event(dev))) {
list_add_tail(&dev->link_watch_list, &lweventlist);
continue;
}
spin_unlock_irq(&lweventlist_lock);
linkwatch_do_dev(dev);
do_dev--;
spin_lock_irq(&lweventlist_lock);
}
/* Add the remaining work back to lweventlist */
list_splice_init(&wrk, &lweventlist);
if (!list_empty(&lweventlist))
linkwatch_schedule_work(0);
spin_unlock_irq(&lweventlist_lock);
}
void linkwatch_forget_dev(struct net_device *dev)
{
unsigned long flags;
int clean = 0;
spin_lock_irqsave(&lweventlist_lock, flags);
if (!list_empty(&dev->link_watch_list)) {
list_del_init(&dev->link_watch_list);
clean = 1;
}
spin_unlock_irqrestore(&lweventlist_lock, flags);
if (clean)
linkwatch_do_dev(dev);
}
/* Must be called with the rtnl semaphore held */
void linkwatch_run_queue(void)
{
__linkwatch_run_queue(0);
}
static void linkwatch_event(struct work_struct *dummy)
{
rtnl_lock();
__linkwatch_run_queue(time_after(linkwatch_nextevent, jiffies));
rtnl_unlock();
}
void linkwatch_fire_event(struct net_device *dev)
{
bool urgent = linkwatch_urgent_event(dev);
if (!test_and_set_bit(__LINK_STATE_LINKWATCH_PENDING, &dev->state)) {
linkwatch_add_event(dev);
} else if (!urgent)
return;
linkwatch_schedule_work(urgent);
}
EXPORT_SYMBOL(linkwatch_fire_event);