#include <linux/jiffies.h>
#include <net/route.h>
#include <net/net_namespace.h>
+#include <net/netns/generic.h>
#include "bonding.h"
#include "bond_3ad.h"
#include "bond_alb.h"
static int use_carrier = 1;
static char *mode;
static char *primary;
+static char *primary_reselect;
static char *lacp_rate;
static char *ad_select;
static char *xmit_hash_policy;
"6 for balance-alb");
module_param(primary, charp, 0);
MODULE_PARM_DESC(primary, "Primary network device to use");
+module_param(primary_reselect, charp, 0);
+MODULE_PARM_DESC(primary_reselect, "Reselect primary slave "
+ "once it comes up; "
+ "0 for always (default), "
+ "1 for only if speed of primary is "
+ "better, "
+ "2 for only on active slave "
+ "failure");
module_param(lacp_rate, charp, 0);
MODULE_PARM_DESC(lacp_rate, "LACPDU tx rate to request from 802.3ad partner "
"(slow/fast)");
static const char * const version =
DRV_DESCRIPTION ": v" DRV_VERSION " (" DRV_RELDATE ")\n";
-LIST_HEAD(bond_dev_list);
-
-#ifdef CONFIG_PROC_FS
-static struct proc_dir_entry *bond_proc_dir;
-#endif
+int bond_net_id __read_mostly;
static __be32 arp_target[BOND_MAX_ARP_TARGETS];
static int arp_ip_count;
{ NULL, -1},
};
+const struct bond_parm_tbl pri_reselect_tbl[] = {
+{ "always", BOND_PRI_RESELECT_ALWAYS},
+{ "better", BOND_PRI_RESELECT_BETTER},
+{ "failure", BOND_PRI_RESELECT_FAILURE},
+{ NULL, -1},
+};
+
struct bond_parm_tbl ad_select_tbl[] = {
{ "stable", BOND_AD_STABLE},
{ "bandwidth", BOND_AD_BANDWIDTH},
static void bond_send_gratuitous_arp(struct bonding *bond);
static int bond_init(struct net_device *bond_dev);
-static void bond_deinit(struct net_device *bond_dev);
+static void bond_uninit(struct net_device *bond_dev);
/*---------------------------- General routines -----------------------------*/
}
+static bool bond_should_change_active(struct bonding *bond)
+{
+ struct slave *prim = bond->primary_slave;
+ struct slave *curr = bond->curr_active_slave;
+
+ if (!prim || !curr || curr->link != BOND_LINK_UP)
+ return true;
+ if (bond->force_primary) {
+ bond->force_primary = false;
+ return true;
+ }
+ if (bond->params.primary_reselect == BOND_PRI_RESELECT_BETTER &&
+ (prim->speed < curr->speed ||
+ (prim->speed == curr->speed && prim->duplex <= curr->duplex)))
+ return false;
+ if (bond->params.primary_reselect == BOND_PRI_RESELECT_FAILURE)
+ return false;
+ return true;
+}
/**
* find_best_interface - select the best available slave to be the active one
int mintime = bond->params.updelay;
int i;
- new_active = old_active = bond->curr_active_slave;
+ new_active = bond->curr_active_slave;
if (!new_active) { /* there were no active slaves left */
if (bond->slave_cnt > 0) /* found one slave */
}
if ((bond->primary_slave) &&
- bond->primary_slave->link == BOND_LINK_UP) {
+ bond->primary_slave->link == BOND_LINK_UP &&
+ bond_should_change_active(bond)) {
new_active = bond->primary_slave;
}
if (USES_PRIMARY(bond->params.mode) && bond->params.primary[0]) {
/* if there is a primary slave, remember it */
- if (strcmp(bond->params.primary, new_slave->dev->name) == 0)
+ if (strcmp(bond->params.primary, new_slave->dev->name) == 0) {
bond->primary_slave = new_slave;
+ bond->force_primary = true;
+ }
}
write_lock_bh(&bond->curr_slave_lock);
return 0; /* deletion OK */
}
-/*
-* Destroy a bonding device.
-* Must be under rtnl_lock when this function is called.
-*/
-static void bond_uninit(struct net_device *bond_dev)
-{
- struct bonding *bond = netdev_priv(bond_dev);
-
- bond_deinit(bond_dev);
- bond_destroy_sysfs_entry(bond);
-
- if (bond->wq)
- destroy_workqueue(bond->wq);
-
- netif_addr_lock_bh(bond_dev);
- bond_mc_list_destroy(bond);
- netif_addr_unlock_bh(bond_dev);
-}
-
/*
* First release a slave and than destroy the bond if no more slaves are left.
* Must be under rtnl_lock when this function is called.
fl.fl4_dst = targets[i];
fl.fl4_tos = RTO_ONLINK;
- rv = ip_route_output_key(&init_net, &rt, &fl);
+ rv = ip_route_output_key(dev_net(bond->dev), &rt, &fl);
if (rv) {
if (net_ratelimit()) {
pr_warning(DRV_NAME
unsigned char *arp_ptr;
__be32 sip, tip;
- if (dev_net(dev) != &init_net)
- goto out;
-
if (!(dev->priv_flags & IFF_BONDING) || !(dev->flags & IFF_MASTER))
goto out;
}
if (USES_PRIMARY(bond->params.mode)) {
- seq_printf(seq, "Primary Slave: %s\n",
+ seq_printf(seq, "Primary Slave: %s",
(bond->primary_slave) ?
bond->primary_slave->dev->name : "None");
+ if (bond->primary_slave)
+ seq_printf(seq, " (primary_reselect %s)",
+ pri_reselect_tbl[bond->params.primary_reselect].modename);
- seq_printf(seq, "Currently Active Slave: %s\n",
+ seq_printf(seq, "\nCurrently Active Slave: %s\n",
(curr) ? curr->dev->name : "None");
}
.release = seq_release,
};
-static int bond_create_proc_entry(struct bonding *bond)
+static void bond_create_proc_entry(struct bonding *bond)
{
struct net_device *bond_dev = bond->dev;
+ struct bond_net *bn = net_generic(dev_net(bond_dev), bond_net_id);
- if (bond_proc_dir) {
+ if (bn->proc_dir) {
bond->proc_entry = proc_create_data(bond_dev->name,
- S_IRUGO, bond_proc_dir,
+ S_IRUGO, bn->proc_dir,
&bond_info_fops, bond);
if (bond->proc_entry == NULL)
pr_warning(DRV_NAME
else
memcpy(bond->proc_file_name, bond_dev->name, IFNAMSIZ);
}
-
- return 0;
}
static void bond_remove_proc_entry(struct bonding *bond)
{
- if (bond_proc_dir && bond->proc_entry) {
- remove_proc_entry(bond->proc_file_name, bond_proc_dir);
+ struct net_device *bond_dev = bond->dev;
+ struct bond_net *bn = net_generic(dev_net(bond_dev), bond_net_id);
+
+ if (bn->proc_dir && bond->proc_entry) {
+ remove_proc_entry(bond->proc_file_name, bn->proc_dir);
memset(bond->proc_file_name, 0, IFNAMSIZ);
bond->proc_entry = NULL;
}
/* Create the bonding directory under /proc/net, if doesn't exist yet.
* Caller must hold rtnl_lock.
*/
-static void bond_create_proc_dir(void)
+static void bond_create_proc_dir(struct bond_net *bn)
{
- if (!bond_proc_dir) {
- bond_proc_dir = proc_mkdir(DRV_NAME, init_net.proc_net);
- if (!bond_proc_dir)
+ if (!bn->proc_dir) {
+ bn->proc_dir = proc_mkdir(DRV_NAME, bn->net->proc_net);
+ if (!bn->proc_dir)
pr_warning(DRV_NAME
": Warning: cannot create /proc/net/%s\n",
DRV_NAME);
/* Destroy the bonding directory under /proc/net, if empty.
* Caller must hold rtnl_lock.
*/
-static void bond_destroy_proc_dir(void)
+static void bond_destroy_proc_dir(struct bond_net *bn)
{
- if (bond_proc_dir) {
- remove_proc_entry(DRV_NAME, init_net.proc_net);
- bond_proc_dir = NULL;
+ if (bn->proc_dir) {
+ remove_proc_entry(DRV_NAME, bn->net->proc_net);
+ bn->proc_dir = NULL;
}
}
#else /* !CONFIG_PROC_FS */
-static int bond_create_proc_entry(struct bonding *bond)
+static void bond_create_proc_entry(struct bonding *bond)
{
}
{
}
-static void bond_create_proc_dir(void)
+static void bond_create_proc_dir(struct bond_net *bn)
{
}
-static void bond_destroy_proc_dir(void)
+static void bond_destroy_proc_dir(struct bond_net *bn)
{
}
bond_remove_proc_entry(bond);
bond_create_proc_entry(bond);
- bond_destroy_sysfs_entry(bond);
- bond_create_sysfs_entry(bond);
-
return NOTIFY_DONE;
}
switch (event) {
case NETDEV_CHANGENAME:
return bond_event_changename(event_bond);
- case NETDEV_UNREGISTER:
- bond_release_all(event_bond->dev);
- break;
default:
break;
}
{
struct net_device *event_dev = (struct net_device *)ptr;
- if (dev_net(event_dev) != &init_net)
- return NOTIFY_DONE;
-
pr_debug("event_dev: %s, event: %lx\n",
(event_dev ? event_dev->name : "None"),
event);
{
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;
- if (dev_net(ifa->ifa_dev->dev) != &init_net)
- return NOTIFY_DONE;
-
- list_for_each_entry(bond, &bond_dev_list, bond_list) {
+ list_for_each_entry(bond, &bn->dev_list, bond_list) {
if (bond->dev == event_dev) {
switch (event) {
case NETDEV_UP:
* Hash for the output device based upon layer 2 and layer 3 data. If
* the packet is not IP mimic bond_xmit_hash_policy_l2()
*/
-static int bond_xmit_hash_policy_l23(struct sk_buff *skb,
- struct net_device *bond_dev, int count)
+static int bond_xmit_hash_policy_l23(struct sk_buff *skb, int count)
{
struct ethhdr *data = (struct ethhdr *)skb->data;
struct iphdr *iph = ip_hdr(skb);
* the packet is a frag or not TCP or UDP, just use layer 3 data. If it is
* altogether not IP, mimic bond_xmit_hash_policy_l2()
*/
-static int bond_xmit_hash_policy_l34(struct sk_buff *skb,
- struct net_device *bond_dev, int count)
+static int bond_xmit_hash_policy_l34(struct sk_buff *skb, int count)
{
struct ethhdr *data = (struct ethhdr *)skb->data;
struct iphdr *iph = ip_hdr(skb);
/*
* Hash for the output device based upon layer 2 data
*/
-static int bond_xmit_hash_policy_l2(struct sk_buff *skb,
- struct net_device *bond_dev, int count)
+static int bond_xmit_hash_policy_l2(struct sk_buff *skb, int count)
{
struct ethhdr *data = (struct ethhdr *)skb->data;
if (!capable(CAP_NET_ADMIN))
return -EPERM;
- slave_dev = dev_get_by_name(&init_net, ifr->ifr_slave);
+ slave_dev = dev_get_by_name(dev_net(bond_dev), ifr->ifr_slave);
pr_debug("slave_dev=%p: \n", slave_dev);
if (!BOND_IS_OK(bond))
goto out;
- slave_no = bond->xmit_hash_policy(skb, bond_dev, bond->slave_cnt);
+ slave_no = bond->xmit_hash_policy(skb, bond->slave_cnt);
bond_for_each_slave(bond, slave, i) {
slave_no--;
cancel_delayed_work(&bond->ad_work);
}
-/* De-initialize device specific data.
- * Caller must hold rtnl_lock.
- */
-static void bond_deinit(struct net_device *bond_dev)
+/*
+* Destroy a bonding device.
+* Must be under rtnl_lock when this function is called.
+*/
+static void bond_uninit(struct net_device *bond_dev)
{
struct bonding *bond = netdev_priv(bond_dev);
+ /* Release the bonded slaves */
+ bond_release_all(bond_dev);
+
list_del(&bond->bond_list);
bond_work_cancel_all(bond);
bond_remove_proc_entry(bond);
-}
-
-/* Unregister and free all bond devices.
- * Caller must hold rtnl_lock.
- */
-static void bond_free_all(void)
-{
- struct bonding *bond, *nxt;
- list_for_each_entry_safe(bond, nxt, &bond_dev_list, bond_list) {
- struct net_device *bond_dev = bond->dev;
-
- bond_work_cancel_all(bond);
- /* Release the bonded slaves */
- bond_release_all(bond_dev);
- unregister_netdevice(bond_dev);
- }
+ if (bond->wq)
+ destroy_workqueue(bond->wq);
- bond_destroy_proc_dir();
+ netif_addr_lock_bh(bond_dev);
+ bond_mc_list_destroy(bond);
+ netif_addr_unlock_bh(bond_dev);
}
/*------------------------- Module initialization ---------------------------*/
static int bond_check_params(struct bond_params *params)
{
- int arp_validate_value, fail_over_mac_value;
+ int arp_validate_value, fail_over_mac_value, primary_reselect_value;
/*
* Convert string parameters.
if ((bond_mode != BOND_MODE_XOR) &&
(bond_mode != BOND_MODE_8023AD)) {
pr_info(DRV_NAME
- ": xor_mode param is irrelevant in mode %s\n",
+ ": xmit_hash_policy param is irrelevant in"
+ " mode %s\n",
bond_mode_name(bond_mode));
} else {
xmit_hashtype = bond_parse_parm(xmit_hash_policy,
primary = NULL;
}
+ if (primary && primary_reselect) {
+ primary_reselect_value = bond_parse_parm(primary_reselect,
+ pri_reselect_tbl);
+ if (primary_reselect_value == -1) {
+ pr_err(DRV_NAME
+ ": Error: Invalid primary_reselect \"%s\"\n",
+ primary_reselect ==
+ NULL ? "NULL" : primary_reselect);
+ return -EINVAL;
+ }
+ } else {
+ primary_reselect_value = BOND_PRI_RESELECT_ALWAYS;
+ }
+
if (fail_over_mac) {
fail_over_mac_value = bond_parse_parm(fail_over_mac,
fail_over_mac_tbl);
params->use_carrier = use_carrier;
params->lacp_fast = lacp_fast;
params->primary[0] = 0;
+ params->primary_reselect = primary_reselect_value;
params->fail_over_mac = fail_over_mac_value;
if (primary) {
static int bond_init(struct net_device *bond_dev)
{
struct bonding *bond = netdev_priv(bond_dev);
+ struct bond_net *bn = net_generic(dev_net(bond_dev), bond_net_id);
pr_debug("Begin bond_init for %s\n", bond_dev->name);
netif_carrier_off(bond_dev);
bond_create_proc_entry(bond);
- list_add_tail(&bond->bond_list, &bond_dev_list);
+ list_add_tail(&bond->bond_list, &bn->dev_list);
+ bond_prepare_sysfs_group(bond);
+ return 0;
+}
+
+static int bond_validate(struct nlattr *tb[], struct nlattr *data[])
+{
+ if (tb[IFLA_ADDRESS]) {
+ if (nla_len(tb[IFLA_ADDRESS]) != ETH_ALEN)
+ return -EINVAL;
+ if (!is_valid_ether_addr(nla_data(tb[IFLA_ADDRESS])))
+ return -EADDRNOTAVAIL;
+ }
return 0;
}
+static struct rtnl_link_ops bond_link_ops __read_mostly = {
+ .kind = "bond",
+ .priv_size = sizeof(struct bonding),
+ .setup = bond_setup,
+ .validate = bond_validate,
+};
+
/* Create a new bond based on the specified name and bonding parameters.
* If name is NULL, obtain a suitable "bond%d" name for us.
* Caller must NOT hold rtnl_lock; we need to release it here before we
* set up our sysfs entries.
*/
-int bond_create(const char *name)
+int bond_create(struct net *net, const char *name)
{
struct net_device *bond_dev;
int res;
rtnl_lock();
- /* Check to see if the bond already exists. */
- /* FIXME: pass netns from caller */
- if (name && __dev_get_by_name(&init_net, name)) {
- pr_err(DRV_NAME ": cannot add bond %s; already exists\n",
- name);
- res = -EEXIST;
- goto out_rtnl;
- }
bond_dev = alloc_netdev(sizeof(struct bonding), name ? name : "",
bond_setup);
pr_err(DRV_NAME ": %s: eek! can't alloc netdev!\n",
name);
res = -ENOMEM;
- goto out_rtnl;
+ goto out;
}
+ dev_net_set(bond_dev, net);
+ bond_dev->rtnl_link_ops = &bond_link_ops;
+
if (!name) {
res = dev_alloc_name(bond_dev, "bond%d");
if (res < 0)
}
res = register_netdevice(bond_dev);
- if (res < 0)
- goto out_bond;
-
- res = bond_create_sysfs_entry(netdev_priv(bond_dev));
- if (res < 0)
- goto out_unreg;
+out:
rtnl_unlock();
- return 0;
-
-out_unreg:
- unregister_netdevice(bond_dev);
-out_bond:
- bond_deinit(bond_dev);
+ return res;
out_netdev:
free_netdev(bond_dev);
-out_rtnl:
- rtnl_unlock();
- return res;
+ goto out;
+}
+
+static int bond_net_init(struct net *net)
+{
+ struct bond_net *bn = net_generic(net, bond_net_id);
+
+ bn->net = net;
+ INIT_LIST_HEAD(&bn->dev_list);
+
+ bond_create_proc_dir(bn);
+
+ return 0;
}
+static void bond_net_exit(struct net *net)
+{
+ struct bond_net *bn = net_generic(net, bond_net_id);
+
+ bond_destroy_proc_dir(bn);
+}
+
+static struct pernet_operations bond_net_ops = {
+ .init = bond_net_init,
+ .exit = bond_net_exit,
+ .id = &bond_net_id,
+ .size = sizeof(struct bond_net),
+};
+
static int __init bonding_init(void)
{
int i;
if (res)
goto out;
- bond_create_proc_dir();
+ res = register_pernet_subsys(&bond_net_ops);
+ if (res)
+ goto out;
+
+ res = rtnl_link_register(&bond_link_ops);
+ if (res)
+ goto err_link;
for (i = 0; i < max_bonds; i++) {
- res = bond_create(NULL);
+ res = bond_create(&init_net, NULL);
if (res)
goto err;
}
register_netdevice_notifier(&bond_netdev_notifier);
register_inetaddr_notifier(&bond_inetaddr_notifier);
bond_register_ipv6_notifier();
-
- goto out;
-err:
- rtnl_lock();
- bond_free_all();
- rtnl_unlock();
out:
return res;
+err:
+ rtnl_link_unregister(&bond_link_ops);
+err_link:
+ unregister_pernet_subsys(&bond_net_ops);
+ goto out;
}
bond_destroy_sysfs();
- rtnl_lock();
- bond_free_all();
- rtnl_unlock();
+ rtnl_link_unregister(&bond_link_ops);
+ unregister_pernet_subsys(&bond_net_ops);
}
module_init(bonding_init);
MODULE_VERSION(DRV_VERSION);
MODULE_DESCRIPTION(DRV_DESCRIPTION ", v" DRV_VERSION);
MODULE_AUTHOR("Thomas Davis, tadavis@lbl.gov and many others");
+MODULE_ALIAS_RTNL_LINK("bond");
git.openpandora.org / pandora-kernel.git / blobdiff