linux/drivers/net/bonding/bond_debugfs.c
Jiri Bohac e53665c6ea bonding: delete migrated IP addresses from the rlb hash table
Bonding in balance-alb mode records information from ARP packets
passing through the bond in a hash table (rx_hashtbl).

At certain situations (e.g. link change of a slave),
rlb_update_rx_clients() will send out ARP packets to update ARP
caches of other hosts on the network to achieve RX load
balancing.

The problem is that once an IP address is recorded in the hash
table, it stays there indefinitely. If this IP address is
migrated to a different host in the network, bonding still sends
out ARP packets that poison other systems' ARP caches with
invalid information.

This patch solves this by looking at all incoming ARP packets,
and checking if the source IP address is one of the source
addresses stored in the rx_hashtbl. If it is, but the MAC
addresses differ, the corresponding hash table entries are
removed. Thus, when an IP address is migrated, the first ARP
broadcast by its new owner will purge the offending entries of
rx_hashtbl.

The hash table is hashed by ip_dst. To be able to do the above
check efficiently (not walking the whole hash table), we need a
reverse mapping (by ip_src).

I added three new members in struct rlb_client_info:
   rx_hashtbl[x].src_first will point to the start of a list of
      entries for which hash(ip_src) == x.
   The list is linked with src_next and src_prev.

When an incoming ARP packet arrives at rlb_arp_recv()
rlb_purge_src_ip() can quickly walk only the entries on the
corresponding lists, i.e. the entries that are likely to contain
the offending IP address.

To avoid confusion, I renamed these existing fields of struct
rlb_client_info:
	next -> used_next
	prev -> used_prev
	rx_hashtbl_head -> rx_hashtbl_used_head

(The current linked list is _not_ a list of hash table
entries with colliding ip_dst. It's a list of entries that are
being used; its purpose is to avoid walking the whole hash table
when looking for used entries.)

Signed-off-by: Jiri Bohac <jbohac@suse.cz>
Signed-off-by: Jay Vosburgh <fubar@us.ibm.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
2012-11-30 12:07:27 -05:00

148 lines
3.0 KiB
C

#include <linux/kernel.h>
#include <linux/module.h>
#include <linux/device.h>
#include <linux/netdevice.h>
#include "bonding.h"
#include "bond_alb.h"
#if defined(CONFIG_DEBUG_FS) && !defined(CONFIG_NET_NS)
#include <linux/debugfs.h>
#include <linux/seq_file.h>
static struct dentry *bonding_debug_root;
/*
* Show RLB hash table
*/
static int bond_debug_rlb_hash_show(struct seq_file *m, void *v)
{
struct bonding *bond = m->private;
struct alb_bond_info *bond_info = &(BOND_ALB_INFO(bond));
struct rlb_client_info *client_info;
u32 hash_index;
if (bond->params.mode != BOND_MODE_ALB)
return 0;
seq_printf(m, "SourceIP DestinationIP "
"Destination MAC DEV\n");
spin_lock_bh(&(BOND_ALB_INFO(bond).rx_hashtbl_lock));
hash_index = bond_info->rx_hashtbl_used_head;
for (; hash_index != RLB_NULL_INDEX;
hash_index = client_info->used_next) {
client_info = &(bond_info->rx_hashtbl[hash_index]);
seq_printf(m, "%-15pI4 %-15pI4 %-17pM %s\n",
&client_info->ip_src,
&client_info->ip_dst,
&client_info->mac_dst,
client_info->slave->dev->name);
}
spin_unlock_bh(&(BOND_ALB_INFO(bond).rx_hashtbl_lock));
return 0;
}
static int bond_debug_rlb_hash_open(struct inode *inode, struct file *file)
{
return single_open(file, bond_debug_rlb_hash_show, inode->i_private);
}
static const struct file_operations bond_debug_rlb_hash_fops = {
.owner = THIS_MODULE,
.open = bond_debug_rlb_hash_open,
.read = seq_read,
.llseek = seq_lseek,
.release = single_release,
};
void bond_debug_register(struct bonding *bond)
{
if (!bonding_debug_root)
return;
bond->debug_dir =
debugfs_create_dir(bond->dev->name, bonding_debug_root);
if (!bond->debug_dir) {
pr_warning("%s: Warning: failed to register to debugfs\n",
bond->dev->name);
return;
}
debugfs_create_file("rlb_hash_table", 0400, bond->debug_dir,
bond, &bond_debug_rlb_hash_fops);
}
void bond_debug_unregister(struct bonding *bond)
{
if (!bonding_debug_root)
return;
debugfs_remove_recursive(bond->debug_dir);
}
void bond_debug_reregister(struct bonding *bond)
{
struct dentry *d;
if (!bonding_debug_root)
return;
d = debugfs_rename(bonding_debug_root, bond->debug_dir,
bonding_debug_root, bond->dev->name);
if (d) {
bond->debug_dir = d;
} else {
pr_warning("%s: Warning: failed to reregister, "
"so just unregister old one\n",
bond->dev->name);
bond_debug_unregister(bond);
}
}
void bond_create_debugfs(void)
{
bonding_debug_root = debugfs_create_dir("bonding", NULL);
if (!bonding_debug_root) {
pr_warning("Warning: Cannot create bonding directory"
" in debugfs\n");
}
}
void bond_destroy_debugfs(void)
{
debugfs_remove_recursive(bonding_debug_root);
bonding_debug_root = NULL;
}
#else /* !CONFIG_DEBUG_FS */
void bond_debug_register(struct bonding *bond)
{
}
void bond_debug_unregister(struct bonding *bond)
{
}
void bond_debug_reregister(struct bonding *bond)
{
}
void bond_create_debugfs(void)
{
}
void bond_destroy_debugfs(void)
{
}
#endif /* CONFIG_DEBUG_FS */