aboutsummaryrefslogtreecommitdiffstats
diff options
context:
space:
mode:
authorJiri Wiesner <jwiesner@suse.com>2020-08-16 20:52:44 +0200
committerGreg Kroah-Hartman <gregkh@linuxfoundation.org>2020-08-26 10:41:05 +0200
commitf4ed9ede3441ebaf43cad08407a35e8dffa32419 (patch)
tree24ca3a8ac38febdaf96518ca2d1ea2c956e19566
parent542a493c8c5ecf42d73aba110bcd25195b02daf5 (diff)
downloadlinux-yocto-f4ed9ede3441ebaf43cad08407a35e8dffa32419.tar.gz
linux-yocto-f4ed9ede3441ebaf43cad08407a35e8dffa32419.tar.bz2
linux-yocto-f4ed9ede3441ebaf43cad08407a35e8dffa32419.zip
bonding: fix active-backup failover for current ARP slave
[ Upstream commit 0410d07190961ac526f05085765a8d04d926545b ] When the ARP monitor is used for link detection, ARP replies are validated for all slaves (arp_validate=3) and fail_over_mac is set to active, two slaves of an active-backup bond may get stuck in a state where both of them are active and pass packets that they receive to the bond. This state makes IPv6 duplicate address detection fail. The state is reached thus: 1. The current active slave goes down because the ARP target is not reachable. 2. The current ARP slave is chosen and made active. 3. A new slave is enslaved. This new slave becomes the current active slave and can reach the ARP target. As a result, the current ARP slave stays active after the enslave action has finished and the log is littered with "PROBE BAD" messages: > bond0: PROBE: c_arp ens10 && cas ens11 BAD The workaround is to remove the slave with "going back" status from the bond and re-enslave it. This issue was encountered when DPDK PMD interfaces were being enslaved to an active-backup bond. I would be possible to fix the issue in bond_enslave() or bond_change_active_slave() but the ARP monitor was fixed instead to keep most of the actions changing the current ARP slave in the ARP monitor code. The current ARP slave is set as inactive and backup during the commit phase. A new state, BOND_LINK_FAIL, has been introduced for slaves in the context of the ARP monitor. This allows administrators to see how slaves are rotated for sending ARP requests and attempts are made to find a new active slave. Fixes: b2220cad583c9 ("bonding: refactor ARP active-backup monitor") Signed-off-by: Jiri Wiesner <jwiesner@suse.com> Signed-off-by: David S. Miller <davem@davemloft.net> Signed-off-by: Sasha Levin <sashal@kernel.org>
-rw-r--r--drivers/net/bonding/bond_main.c18
1 files changed, 16 insertions, 2 deletions
diff --git a/drivers/net/bonding/bond_main.c b/drivers/net/bonding/bond_main.c
index ce829a7a9210..0d7a173f8e61 100644
--- a/drivers/net/bonding/bond_main.c
+++ b/drivers/net/bonding/bond_main.c
@@ -2778,6 +2778,9 @@ static int bond_ab_arp_inspect(struct bonding *bond)
if (bond_time_in_interval(bond, last_rx, 1)) {
bond_propose_link_state(slave, BOND_LINK_UP);
commit++;
+ } else if (slave->link == BOND_LINK_BACK) {
+ bond_propose_link_state(slave, BOND_LINK_FAIL);
+ commit++;
}
continue;
}
@@ -2886,6 +2889,19 @@ static void bond_ab_arp_commit(struct bonding *bond)
continue;
+ case BOND_LINK_FAIL:
+ bond_set_slave_link_state(slave, BOND_LINK_FAIL,
+ BOND_SLAVE_NOTIFY_NOW);
+ bond_set_slave_inactive_flags(slave,
+ BOND_SLAVE_NOTIFY_NOW);
+
+ /* A slave has just been enslaved and has become
+ * the current active slave.
+ */
+ if (rtnl_dereference(bond->curr_active_slave))
+ RCU_INIT_POINTER(bond->current_arp_slave, NULL);
+ continue;
+
default:
slave_err(bond->dev, slave->dev,
"impossible: link_new_state %d on slave\n",
@@ -2936,8 +2952,6 @@ static bool bond_ab_arp_probe(struct bonding *bond)
return should_notify_rtnl;
}
- bond_set_slave_inactive_flags(curr_arp_slave, BOND_SLAVE_NOTIFY_LATER);
-
bond_for_each_slave_rcu(bond, slave, iter) {
if (!found && !before && bond_slave_is_up(slave))
before = slave;