Commit eaddcd76 authored by Andy Gospodarek's avatar Andy Gospodarek Committed by David S. Miller

bonding: remove entries for master_ip and vlan_ip and query devices instead

The following patch aimed to resolve an issue where secondary, tertiary,
etc. addresses added to bond interfaces could overwrite the
bond->master_ip and vlan_ip values.

        commit 917fbdb3
        Author: Henrik Saavedra Persson <henrik.e.persson@ericsson.com>
        Date:   Wed Nov 23 23:37:15 2011 +0000

            bonding: only use primary address for ARP

That patch was good because it prevented bonds using ARP monitoring from
sending frames with an invalid source IP address.  Unfortunately, it
didn't always work as expected.

When using an ioctl (like ifconfig does) to set the IP address and
netmask, 2 separate ioctls are actually called to set the IP and netmask
if the mask chosen doesn't match the standard mask for that class of
address.  The first ioctl did not have a mask that matched the one in
the primary address and would still cause the device address to be
overwritten.  The second ioctl that was called to set the mask would
then detect as secondary and ignored, but the damage was already done.

This was not an issue when using an application that used netlink
sockets as the setting of IP and netmask came down at once.  The
inconsistent behavior between those two interfaces was something that
needed to be resolved.

While I was thinking about how I wanted to resolve this, Ralf Zeidler
came with a patch that resolved this on a RHEL kernel by keeping a full
shadow of the entries in dev->ifa_list for the bonding device and vlan
devices in the bonding driver.  I didn't like the duplication of the
list as I want to see the 'bonding' struct and code shrink rather than
grow, but liked the general idea.

As the Subject indicates this patch drops the master_ip and vlan_ip
elements from the 'bonding' and 'vlan_entry' structs, respectively.
This can be done because a device's address-list is now traversed to
determine the optimal source IP address for ARP requests and for checks
to see if the bonding device has a particular IP address.  This code
could have all be contained inside the bonding driver, but it made more
sense to me to EXPORT and call inet_confirm_addr since it did exactly
what was needed.

I tested this and a backported patch and everything works as expected.
Ralf also helped with verification of the backported patch.

Thanks to Ralf for all his help on this.

v2: Whitespace and organizational changes based on suggestions from Jay
Vosburgh and Dave Miller.

v3: Fixup incorrect usage of rcu_read_unlock based on Dave Miller's
suggestion.
Signed-off-by: default avatarAndy Gospodarek <andy@greyhouse.net>
CC: Ralf Zeidler <ralf.zeidler@nsn.com>
Signed-off-by: default avatarDavid S. Miller <davem@davemloft.net>
parent 523f610e
...@@ -2573,12 +2573,16 @@ void bond_mii_monitor(struct work_struct *work) ...@@ -2573,12 +2573,16 @@ void bond_mii_monitor(struct work_struct *work)
static int bond_has_this_ip(struct bonding *bond, __be32 ip) static int bond_has_this_ip(struct bonding *bond, __be32 ip)
{ {
struct vlan_entry *vlan; struct vlan_entry *vlan;
struct net_device *vlan_dev;
if (ip == bond->master_ip) if (ip == bond_confirm_addr(bond->dev, 0, ip))
return 1; return 1;
list_for_each_entry(vlan, &bond->vlan_list, vlan_list) { list_for_each_entry(vlan, &bond->vlan_list, vlan_list) {
if (ip == vlan->vlan_ip) rcu_read_lock();
vlan_dev = __vlan_find_dev_deep(bond->dev, vlan->vlan_id);
rcu_read_unlock();
if (vlan_dev && ip == bond_confirm_addr(vlan_dev, 0, ip))
return 1; return 1;
} }
...@@ -2620,17 +2624,19 @@ static void bond_arp_send_all(struct bonding *bond, struct slave *slave) ...@@ -2620,17 +2624,19 @@ static void bond_arp_send_all(struct bonding *bond, struct slave *slave)
int i, vlan_id; int i, vlan_id;
__be32 *targets = bond->params.arp_targets; __be32 *targets = bond->params.arp_targets;
struct vlan_entry *vlan; struct vlan_entry *vlan;
struct net_device *vlan_dev; struct net_device *vlan_dev = NULL;
struct rtable *rt; struct rtable *rt;
for (i = 0; (i < BOND_MAX_ARP_TARGETS); i++) { for (i = 0; (i < BOND_MAX_ARP_TARGETS); i++) {
__be32 addr;
if (!targets[i]) if (!targets[i])
break; break;
pr_debug("basa: target %x\n", targets[i]); pr_debug("basa: target %x\n", targets[i]);
if (!bond_vlan_used(bond)) { if (!bond_vlan_used(bond)) {
pr_debug("basa: empty vlan: arp_send\n"); pr_debug("basa: empty vlan: arp_send\n");
addr = bond_confirm_addr(bond->dev, targets[i], 0);
bond_arp_send(slave->dev, ARPOP_REQUEST, targets[i], bond_arp_send(slave->dev, ARPOP_REQUEST, targets[i],
bond->master_ip, 0); addr, 0);
continue; continue;
} }
...@@ -2655,8 +2661,9 @@ static void bond_arp_send_all(struct bonding *bond, struct slave *slave) ...@@ -2655,8 +2661,9 @@ static void bond_arp_send_all(struct bonding *bond, struct slave *slave)
if (rt->dst.dev == bond->dev) { if (rt->dst.dev == bond->dev) {
ip_rt_put(rt); ip_rt_put(rt);
pr_debug("basa: rtdev == bond->dev: arp_send\n"); pr_debug("basa: rtdev == bond->dev: arp_send\n");
addr = bond_confirm_addr(bond->dev, targets[i], 0);
bond_arp_send(slave->dev, ARPOP_REQUEST, targets[i], bond_arp_send(slave->dev, ARPOP_REQUEST, targets[i],
bond->master_ip, 0); addr, 0);
continue; continue;
} }
...@@ -2674,10 +2681,11 @@ static void bond_arp_send_all(struct bonding *bond, struct slave *slave) ...@@ -2674,10 +2681,11 @@ static void bond_arp_send_all(struct bonding *bond, struct slave *slave)
} }
} }
if (vlan_id) { if (vlan_id && vlan_dev) {
ip_rt_put(rt); ip_rt_put(rt);
addr = bond_confirm_addr(vlan_dev, targets[i], 0);
bond_arp_send(slave->dev, ARPOP_REQUEST, targets[i], bond_arp_send(slave->dev, ARPOP_REQUEST, targets[i],
vlan->vlan_ip, vlan_id); addr, vlan_id);
continue; continue;
} }
...@@ -3299,68 +3307,10 @@ static int bond_netdev_event(struct notifier_block *this, ...@@ -3299,68 +3307,10 @@ static int bond_netdev_event(struct notifier_block *this,
return NOTIFY_DONE; return NOTIFY_DONE;
} }
/*
* bond_inetaddr_event: handle inetaddr notifier chain events.
*
* We keep track of device IPs primarily to use as source addresses in
* ARP monitor probes (rather than spewing out broadcasts all the time).
*
* We track one IP for the main device (if it has one), plus one per VLAN.
*/
static int bond_inetaddr_event(struct notifier_block *this, unsigned long event, void *ptr)
{
struct in_ifaddr *ifa = ptr;
struct net_device *vlan_dev, *event_dev = ifa->ifa_dev->dev;
struct bond_net *bn = net_generic(dev_net(event_dev), bond_net_id);
struct bonding *bond;
struct vlan_entry *vlan;
/* we only care about primary address */
if(ifa->ifa_flags & IFA_F_SECONDARY)
return NOTIFY_DONE;
list_for_each_entry(bond, &bn->dev_list, bond_list) {
if (bond->dev == event_dev) {
switch (event) {
case NETDEV_UP:
bond->master_ip = ifa->ifa_local;
return NOTIFY_OK;
case NETDEV_DOWN:
bond->master_ip = 0;
return NOTIFY_OK;
default:
return NOTIFY_DONE;
}
}
list_for_each_entry(vlan, &bond->vlan_list, vlan_list) {
vlan_dev = __vlan_find_dev_deep(bond->dev,
vlan->vlan_id);
if (vlan_dev == event_dev) {
switch (event) {
case NETDEV_UP:
vlan->vlan_ip = ifa->ifa_local;
return NOTIFY_OK;
case NETDEV_DOWN:
vlan->vlan_ip = 0;
return NOTIFY_OK;
default:
return NOTIFY_DONE;
}
}
}
}
return NOTIFY_DONE;
}
static struct notifier_block bond_netdev_notifier = { static struct notifier_block bond_netdev_notifier = {
.notifier_call = bond_netdev_event, .notifier_call = bond_netdev_event,
}; };
static struct notifier_block bond_inetaddr_notifier = {
.notifier_call = bond_inetaddr_event,
};
/*---------------------------- Hashing Policies -----------------------------*/ /*---------------------------- Hashing Policies -----------------------------*/
/* /*
...@@ -4929,7 +4879,6 @@ static int __init bonding_init(void) ...@@ -4929,7 +4879,6 @@ static int __init bonding_init(void)
} }
register_netdevice_notifier(&bond_netdev_notifier); register_netdevice_notifier(&bond_netdev_notifier);
register_inetaddr_notifier(&bond_inetaddr_notifier);
out: out:
return res; return res;
err: err:
...@@ -4943,7 +4892,6 @@ static int __init bonding_init(void) ...@@ -4943,7 +4892,6 @@ static int __init bonding_init(void)
static void __exit bonding_exit(void) static void __exit bonding_exit(void)
{ {
unregister_netdevice_notifier(&bond_netdev_notifier); unregister_netdevice_notifier(&bond_netdev_notifier);
unregister_inetaddr_notifier(&bond_inetaddr_notifier);
bond_destroy_debugfs(); bond_destroy_debugfs();
......
...@@ -21,6 +21,7 @@ ...@@ -21,6 +21,7 @@
#include <linux/cpumask.h> #include <linux/cpumask.h>
#include <linux/in6.h> #include <linux/in6.h>
#include <linux/netpoll.h> #include <linux/netpoll.h>
#include <linux/inetdevice.h>
#include "bond_3ad.h" #include "bond_3ad.h"
#include "bond_alb.h" #include "bond_alb.h"
...@@ -166,7 +167,6 @@ struct bond_parm_tbl { ...@@ -166,7 +167,6 @@ struct bond_parm_tbl {
struct vlan_entry { struct vlan_entry {
struct list_head vlan_list; struct list_head vlan_list;
__be32 vlan_ip;
unsigned short vlan_id; unsigned short vlan_id;
}; };
...@@ -232,7 +232,6 @@ struct bonding { ...@@ -232,7 +232,6 @@ struct bonding {
struct list_head bond_list; struct list_head bond_list;
struct netdev_hw_addr_list mc_list; struct netdev_hw_addr_list mc_list;
int (*xmit_hash_policy)(struct sk_buff *, int); int (*xmit_hash_policy)(struct sk_buff *, int);
__be32 master_ip;
u16 rr_tx_counter; u16 rr_tx_counter;
struct ad_bond_info ad_info; struct ad_bond_info ad_info;
struct alb_bond_info alb_info; struct alb_bond_info alb_info;
...@@ -378,6 +377,21 @@ static inline bool bond_is_slave_inactive(struct slave *slave) ...@@ -378,6 +377,21 @@ static inline bool bond_is_slave_inactive(struct slave *slave)
return slave->inactive; return slave->inactive;
} }
static inline __be32 bond_confirm_addr(struct net_device *dev, __be32 dst, __be32 local)
{
struct in_device *in_dev;
__be32 addr = 0;
rcu_read_lock();
in_dev = __in_dev_get_rcu(dev);
if (in_dev)
addr = inet_confirm_addr(in_dev, dst, local, RT_SCOPE_HOST);
rcu_read_unlock();
return addr;
}
struct bond_net; struct bond_net;
struct vlan_entry *bond_next_vlan(struct bonding *bond, struct vlan_entry *curr); struct vlan_entry *bond_next_vlan(struct bonding *bond, struct vlan_entry *curr);
......
...@@ -1079,6 +1079,7 @@ __be32 inet_confirm_addr(struct in_device *in_dev, ...@@ -1079,6 +1079,7 @@ __be32 inet_confirm_addr(struct in_device *in_dev,
return addr; return addr;
} }
EXPORT_SYMBOL(inet_confirm_addr);
/* /*
* Device notifier * Device notifier
......
Markdown is supported
0%
or
You are about to add 0 people to the discussion. Proceed with caution.
Finish editing this message first!
Please register or to comment