bonding: improve link-status update in mii-monitoring

The primary issue is that mii-inspect phase updates link-state and
expects changes to be committed during the mii-commit phase. After
the inspect phase if it fails to acquire rtnl-mutex, the commit
phase (bond_mii_commit) doesn't get to run. This partially updated
state stays and makes the internal-state inconsistent.

e.g. setup bond0 => slaves: eth1, eth2
eth1 goes DOWN -> UP
   mii_monitor()
	mii-inspect()
	    bond_set_slave_link_state(eth1, UP, DontNotify)
	rtnl_trylock() <- fails!

Next mii-monitor round
eth1: No change
   mii_monitor()
	mii-inspect()
	    eth1->link == current-status (ethtool_ops->get_link)
	    no-change-detected

End result:
    eth1:
      Link = BOND_LINK_UP
      Speed = 0xfffff  [SpeedUnknown]
      Duplex = 0xff    [DuplexUnknown]

This doesn't always happen but for some unlucky machines in a large set
of machines it creates problems.

The fix for this is to avoid making changes during inspect phase and
postpone them until acquiring the rtnl-mutex / invoking commit phase.

Signed-off-by: Mahesh Bandewar <maheshb@google.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
This commit is contained in:
Mahesh Bandewar 2017-03-27 11:37:33 -07:00 коммит произвёл David S. Miller
Родитель f307668bfc
Коммит de77ecd4ef
1 изменённых файлов: 9 добавлений и 9 удалений

Просмотреть файл

@ -2033,8 +2033,7 @@ static int bond_miimon_inspect(struct bonding *bond)
if (link_state)
continue;
bond_set_slave_link_state(slave, BOND_LINK_FAIL,
BOND_SLAVE_NOTIFY_LATER);
bond_propose_link_state(slave, BOND_LINK_FAIL);
slave->delay = bond->params.downdelay;
if (slave->delay) {
netdev_info(bond->dev, "link status down for %sinterface %s, disabling it in %d ms\n",
@ -2049,8 +2048,7 @@ static int bond_miimon_inspect(struct bonding *bond)
case BOND_LINK_FAIL:
if (link_state) {
/* recovered before downdelay expired */
bond_set_slave_link_state(slave, BOND_LINK_UP,
BOND_SLAVE_NOTIFY_LATER);
bond_propose_link_state(slave, BOND_LINK_UP);
slave->last_link_up = jiffies;
netdev_info(bond->dev, "link status up again after %d ms for interface %s\n",
(bond->params.downdelay - slave->delay) *
@ -2072,8 +2070,7 @@ static int bond_miimon_inspect(struct bonding *bond)
if (!link_state)
continue;
bond_set_slave_link_state(slave, BOND_LINK_BACK,
BOND_SLAVE_NOTIFY_LATER);
bond_propose_link_state(slave, BOND_LINK_BACK);
slave->delay = bond->params.updelay;
if (slave->delay) {
@ -2086,9 +2083,7 @@ static int bond_miimon_inspect(struct bonding *bond)
/*FALLTHRU*/
case BOND_LINK_BACK:
if (!link_state) {
bond_set_slave_link_state(slave,
BOND_LINK_DOWN,
BOND_SLAVE_NOTIFY_LATER);
bond_propose_link_state(slave, BOND_LINK_DOWN);
netdev_info(bond->dev, "link status down again after %d ms for interface %s\n",
(bond->params.updelay - slave->delay) *
bond->params.miimon,
@ -2225,6 +2220,8 @@ static void bond_mii_monitor(struct work_struct *work)
mii_work.work);
bool should_notify_peers = false;
unsigned long delay;
struct slave *slave;
struct list_head *iter;
delay = msecs_to_jiffies(bond->params.miimon);
@ -2245,6 +2242,9 @@ static void bond_mii_monitor(struct work_struct *work)
goto re_arm;
}
bond_for_each_slave(bond, slave, iter) {
bond_commit_link_state(slave, BOND_SLAVE_NOTIFY_LATER);
}
bond_miimon_commit(bond);
rtnl_unlock(); /* might sleep, hold no other locks */