bonding: add an option to fail when any of arp_ip_target is inaccessible

Currently, we fail only when all of the ips in arp_ip_target are gone.
However, in some situations we might need to fail if even one host from
arp_ip_target becomes unavailable.

All situations, obviously, rely on the idea that we need *completely*
functional network, with all interfaces/addresses working correctly.

One real world example might be:
vlans on top on bond (hybrid port). If bond and vlans have ips assigned
and we have their peers monitored via arp_ip_target - in case of switch
misconfiguration (trunk/access port), slave driver malfunction or
tagged/untagged traffic dropped on the way - we will be able to switch
to another slave.

Though any other configuration needs that if we need to have access to all
arp_ip_targets.

This patch adds this possibility by adding a new parameter -
arp_all_targets (both as a module parameter and as a sysfs knob). It can be
set to:

	0 or any (the default) - which works exactly as it's working now -
	the slave is up if any of the arp_ip_targets are up.

	1 or all - the slave is up if all of the arp_ip_targets are up.

This parameter can be changed on the fly (via sysfs), and requires the mode
to be active-backup and arp_validate to be enabled (it obeys the
arp_validate config on which slaves to validate).

Internally it's done through:

1) Add target_last_arp_rx[BOND_MAX_ARP_TARGETS] array to slave struct. It's
   an array of jiffies, meaning that slave->target_last_arp_rx[i] is the
   last time we've received arp from bond->params.arp_targets[i] on this
   slave.

2) If we successfully validate an arp from bond->params.arp_targets[i] in
   bond_validate_arp() - update the slave->target_last_arp_rx[i] with the
   current jiffies value.

3) When getting slave's last_rx via slave_last_rx(), we return the oldest
   time when we've received an arp from any address in
   bond->params.arp_targets[].

If the value of arp_all_targets == 0 - we still work the same way as
before.

Also, update the documentation to reflect the new parameter.

v3->v4:
Kill the forgotten rtnl_unlock(), rephrase the documentation part to be
more clear, don't fail setting arp_all_targets if arp_validate is not set -
it has no effect anyway but can be easier to set up. Also, print a warning
if the last arp_ip_target is removed while the arp_interval is on, but not
the arp_validate.

v2->v3:
Use _bh spinlock, remove useless rtnl_lock() and use jiffies for new
arp_ip_target last arp, instead of slave_last_rx(). On bond_enslave(),
use the same initialization value for target_last_arp_rx[] as is used
for the default last_arp_rx, to avoid useless interface flaps.

Also, instead of failing to remove the last arp_ip_target just print a
warning - otherwise it might break existing scripts.

v1->v2:
Correctly handle adding/removing hosts in arp_ip_target - we need to
shift/initialize all slave's target_last_arp_rx. Also, don't fail module
loading on arp_all_targets misconfiguration, just disable it, and some
minor style fixes.

Signed-off-by: Veaceslav Falico <vfalico@redhat.com>
Signed-off-by: David S. Miller <davem@davemloft.net>

1 files changed, 31 insertions, 2 deletions

diff --git a/drivers/net/bonding/bond_main.c b/drivers/net/bonding/bond_main.c
index d3a70c0d0edd..142d55dc526e 100644
--- a/drivers/net/bonding/bond_main.c
+++ b/drivers/net/bonding/bond_main.c
@@ -104,6 +104,7 @@ static char *xmit_hash_policy;
 static int arp_interval = BOND_LINK_ARP_INTERV;
 static char *arp_ip_target[BOND_MAX_ARP_TARGETS];
 static char *arp_validate;
+static char *arp_all_targets;
 static char *fail_over_mac;
 static int all_slaves_active = 0;
 static struct bond_params bonding_defaults;
@@ -166,6 +167,8 @@ module_param(arp_validate, charp, 0);
 MODULE_PARM_DESC(arp_validate, "validate src/dst of ARP probes; "
 			       "0 for none (default), 1 for active, "
 			       "2 for backup, 3 for all");
+module_param(arp_all_targets, charp, 0);
+MODULE_PARM_DESC(arp_all_targets, "fail on any/all arp targets timeout; 0 for any (default), 1 for all");
 module_param(fail_over_mac, charp, 0);
 MODULE_PARM_DESC(fail_over_mac, "For active-backup, do not set all slaves to "
 				"the same MAC; 0 for none (default), "
@@ -216,6 +219,12 @@ const struct bond_parm_tbl xmit_hashtype_tbl[] = {
 {	NULL,			-1},
 };
 
+const struct bond_parm_tbl arp_all_targets_tbl[] = {
+{	"any",			BOND_ARP_TARGETS_ANY},
+{	"all",			BOND_ARP_TARGETS_ALL},
+{	NULL,			-1},
+};
+
 const struct bond_parm_tbl arp_validate_tbl[] = {
 {	"none",			BOND_ARP_VALIDATE_NONE},
 {	"active",		BOND_ARP_VALIDATE_ACTIVE},
@@ -1483,7 +1492,7 @@ int bond_enslave(struct net_device *bond_dev, struct net_device *slave_dev)
 	struct slave *new_slave = NULL;
 	struct sockaddr addr;
 	int link_reporting;
-	int res = 0;
+	int res = 0, i;
 
 	if (!bond->params.use_carrier &&
 	    slave_dev->ethtool_ops->get_link == NULL &&
@@ -1712,6 +1721,8 @@ int bond_enslave(struct net_device *bond_dev, struct net_device *slave_dev)
 
 	new_slave->last_arp_rx = jiffies -
 		(msecs_to_jiffies(bond->params.arp_interval) + 1);
+	for (i = 0; i < BOND_MAX_ARP_TARGETS; i++)
+		new_slave->target_last_arp_rx[i] = new_slave->last_arp_rx;
 
 	if (bond->params.miimon && !bond->params.use_carrier) {
 		link_reporting = bond_check_dev_link(bond, slave_dev, 1);
@@ -2610,16 +2621,20 @@ static void bond_arp_send_all(struct bonding *bond, struct slave *slave)
 
 static void bond_validate_arp(struct bonding *bond, struct slave *slave, __be32 sip, __be32 tip)
 {
+	int i;
+
 	if (!sip || !bond_has_this_ip(bond, tip)) {
 		pr_debug("bva: sip %pI4 tip %pI4 not found\n", &sip, &tip);
 		return;
 	}
 
-	if (bond_get_targets_ip(bond->params.arp_targets, sip) == -1) {
+	i = bond_get_targets_ip(bond->params.arp_targets, sip);
+	if (i == -1) {
 		pr_debug("bva: sip %pI4 not found in targets\n", &sip);
 		return;
 	}
 	slave->last_arp_rx = jiffies;
+	slave->target_last_arp_rx[i] = jiffies;
 }
 
 static int bond_arp_rcv(const struct sk_buff *skb, struct bonding *bond,
@@ -4409,6 +4424,7 @@ int bond_parse_parm(const char *buf, const struct bond_parm_tbl *tbl)
 static int bond_check_params(struct bond_params *params)
 {
 	int arp_validate_value, fail_over_mac_value, primary_reselect_value, i;
+	int arp_all_targets_value;
 
 	/*
 	 * Convert string parameters.
@@ -4634,6 +4650,18 @@ static int bond_check_params(struct bond_params *params)
 	} else
 		arp_validate_value = 0;
 
+	arp_all_targets_value = 0;
+	if (arp_all_targets) {
+		arp_all_targets_value = bond_parse_parm(arp_all_targets,
+							arp_all_targets_tbl);
+
+		if (arp_all_targets_value == -1) {
+			pr_err("Error: invalid arp_all_targets_value \"%s\"\n",
+			       arp_all_targets);
+			arp_all_targets_value = 0;
+		}
+	}
+
 	if (miimon) {
 		pr_info("MII link monitoring set to %d ms\n", miimon);
 	} else if (arp_interval) {
@@ -4698,6 +4726,7 @@ static int bond_check_params(struct bond_params *params)
 	params->num_peer_notif = num_peer_notif;
 	params->arp_interval = arp_interval;
 	params->arp_validate = arp_validate_value;
+	params->arp_all_targets = arp_all_targets_value;
 	params->updelay = updelay;
 	params->downdelay = downdelay;
 	params->use_carrier = use_carrier;