linux/net/core/link_watch.c
Ben Hutchings 8f4cccbbd9 net: Set device operstate at registration time
The operstate of a device is initially IF_OPER_UNKNOWN and is updated
asynchronously by linkwatch after each change of carrier state
reported by the driver.  The default carrier state of a net device is
on, and this will never be changed on drivers that do not support
carrier detection, thus the operstate remains IF_OPER_UNKNOWN.

For devices that do support carrier detection, the driver must set the
carrier state to off initially, then poll the hardware state when the
device is opened.  However, we must not activate linkwatch for a
unregistered device, and commit b473001 ('net: Do not fire linkwatch
events until the device is registered.') ensured that we don't.  But
this means that the operstate for many devices that support carrier
detection remains IF_OPER_UNKNOWN when it should be IF_OPER_DOWN.

The same issue exists with the dormant state.

The proper initialisation sequence, avoiding a race with opening of
the device, is:

        rtnl_lock();
        rc = register_netdevice(dev);
        if (rc)
                goto out_unlock;
        netif_carrier_off(dev); /* or netif_dormant_on(dev) */
        rtnl_unlock();

but it seems silly that this should have to be repeated in so many
drivers.  Further, the operstate seen immediately after opening the
device may still be IF_OPER_UNKNOWN due to the asynchronous nature of
linkwatch.

Commit 22604c8 ('net: Fix for initial link state in 2.6.28') attempted
to fix this by setting the operstate synchronously, but it was
reverted as it could lead to deadlock.

This initialises the operstate synchronously at registration time
only.

Signed-off-by: Ben Hutchings <bhutchings@solarflare.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
2012-08-24 12:46:13 -04:00

260 lines
5.7 KiB
C

/*
* Linux network device link state notification
*
* Author:
* Stefan Rompf <sux@loplof.de>
*
* This program is free software; you can redistribute it and/or
* modify it under the terms of the GNU General Public License
* as published by the Free Software Foundation; either version
* 2 of the License, or (at your option) any later version.
*
*/
#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 <asm/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_carrier_ok(dev))
return (dev->ifindex != dev->iflink ?
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_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))
rfc2863_policy(dev);
}
static bool linkwatch_urgent_event(struct net_device *dev)
{
if (!netif_running(dev))
return false;
if (dev->ifindex != dev->iflink)
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;
/*
* This is true if we've scheduled it immeditately or if we don't
* need an immediate execution and it's already pending.
*/
if (schedule_delayed_work(&linkwatch_work, delay) == !delay)
return;
/* Don't bother if there is nothing urgent. */
if (!test_bit(LW_URGENT, &linkwatch_flags))
return;
/* It's already running which is good enough. */
if (!__cancel_delayed_work(&linkwatch_work))
return;
/* Otherwise we reschedule it again for immediate execution. */
schedule_delayed_work(&linkwatch_work, 0);
}
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_clear_bit();
/* 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)
{
struct net_device *dev;
LIST_HEAD(wrk);
/*
* 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)) {
dev = list_first_entry(&wrk, struct net_device, link_watch_list);
list_del_init(&dev->link_watch_list);
if (urgent_only && !linkwatch_urgent_event(dev)) {
list_add_tail(&dev->link_watch_list, &lweventlist);
continue;
}
spin_unlock_irq(&lweventlist_lock);
linkwatch_do_dev(dev);
spin_lock_irq(&lweventlist_lock);
}
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);