diff options
author | Steven Whitehouse <swhiteho@redhat.com> | 2006-09-28 08:29:59 -0400 |
---|---|---|
committer | Steven Whitehouse <swhiteho@redhat.com> | 2006-09-28 08:29:59 -0400 |
commit | 185a257f2f73bcd89050ad02da5bedbc28fc43fa (patch) | |
tree | 5e32586114534ed3f2165614cba3d578f5d87307 /drivers/net/bonding/bond_main.c | |
parent | 3f1a9aaeffd8d1cbc5ab9776c45cbd66af1c9699 (diff) | |
parent | a77c64c1a641950626181b4857abb701d8f38ccc (diff) | |
download | op-kernel-dev-185a257f2f73bcd89050ad02da5bedbc28fc43fa.zip op-kernel-dev-185a257f2f73bcd89050ad02da5bedbc28fc43fa.tar.gz |
Merge branch 'master' into gfs2
Diffstat (limited to 'drivers/net/bonding/bond_main.c')
-rw-r--r-- | drivers/net/bonding/bond_main.c | 228 |
1 files changed, 194 insertions, 34 deletions
diff --git a/drivers/net/bonding/bond_main.c b/drivers/net/bonding/bond_main.c index 850aae2..0fb5f65 100644 --- a/drivers/net/bonding/bond_main.c +++ b/drivers/net/bonding/bond_main.c @@ -96,6 +96,7 @@ static char *lacp_rate = NULL; static char *xmit_hash_policy = NULL; static int arp_interval = BOND_LINK_ARP_INTERV; static char *arp_ip_target[BOND_MAX_ARP_TARGETS] = { NULL, }; +static char *arp_validate = NULL; struct bond_params bonding_defaults; module_param(max_bonds, int, 0); @@ -127,6 +128,8 @@ module_param(arp_interval, int, 0); MODULE_PARM_DESC(arp_interval, "arp interval in milliseconds"); module_param_array(arp_ip_target, charp, NULL, 0); MODULE_PARM_DESC(arp_ip_target, "arp targets in n.n.n.n form"); +module_param(arp_validate, charp, 0); +MODULE_PARM_DESC(arp_validate, "validate src/dst of ARP probes: none (default), active, backup or all"); /*----------------------------- Global variables ----------------------------*/ @@ -170,6 +173,14 @@ struct bond_parm_tbl xmit_hashtype_tbl[] = { { NULL, -1}, }; +struct bond_parm_tbl arp_validate_tbl[] = { +{ "none", BOND_ARP_VALIDATE_NONE}, +{ "active", BOND_ARP_VALIDATE_ACTIVE}, +{ "backup", BOND_ARP_VALIDATE_BACKUP}, +{ "all", BOND_ARP_VALIDATE_ALL}, +{ NULL, -1}, +}; + /*-------------------------- Forward declarations ---------------------------*/ static void bond_send_gratuitous_arp(struct bonding *bond); @@ -638,6 +649,7 @@ verify: case SPEED_10: case SPEED_100: case SPEED_1000: + case SPEED_10000: break; default: return -1; @@ -1210,10 +1222,14 @@ static int bond_compute_features(struct bonding *bond) unsigned long features = BOND_INTERSECT_FEATURES; struct slave *slave; struct net_device *bond_dev = bond->dev; + unsigned short max_hard_header_len = ETH_HLEN; int i; - bond_for_each_slave(bond, slave, i) + bond_for_each_slave(bond, slave, i) { features &= (slave->dev->features & BOND_INTERSECT_FEATURES); + if (slave->dev->hard_header_len > max_hard_header_len) + max_hard_header_len = slave->dev->hard_header_len; + } if ((features & NETIF_F_SG) && !(features & NETIF_F_ALL_CSUM)) @@ -1231,6 +1247,7 @@ static int bond_compute_features(struct bonding *bond) features |= (bond_dev->features & ~BOND_INTERSECT_FEATURES); bond_dev->features = features; + bond_dev->hard_header_len = max_hard_header_len; return 0; } @@ -1365,6 +1382,7 @@ int bond_enslave(struct net_device *bond_dev, struct net_device *slave_dev) } new_slave->dev = slave_dev; + slave_dev->priv_flags |= IFF_BONDING; if ((bond->params.mode == BOND_MODE_TLB) || (bond->params.mode == BOND_MODE_ALB)) { @@ -1417,6 +1435,8 @@ int bond_enslave(struct net_device *bond_dev, struct net_device *slave_dev) bond_compute_features(bond); + new_slave->last_arp_rx = jiffies; + if (bond->params.miimon && !bond->params.use_carrier) { link_reporting = bond_check_dev_link(bond, slave_dev, 1); @@ -1493,29 +1513,8 @@ int bond_enslave(struct net_device *bond_dev, struct net_device *slave_dev) switch (bond->params.mode) { case BOND_MODE_ACTIVEBACKUP: - /* if we're in active-backup mode, we need one and - * only one active interface. The backup interfaces - * will have their SLAVE_INACTIVE flag set because we - * need them to be drop all packets. Thus, since we - * guarantee that curr_active_slave always point to - * the last usable interface, we just have to verify - * this interface's flag. - */ - if (((!bond->curr_active_slave) || - (bond->curr_active_slave->dev->priv_flags & IFF_SLAVE_INACTIVE)) && - (new_slave->link != BOND_LINK_DOWN)) { - /* first slave or no active slave yet, and this link - is OK, so make this interface the active one */ - bond_change_active_slave(bond, new_slave); - printk(KERN_INFO DRV_NAME - ": %s: first active interface up!\n", - bond->dev->name); - netif_carrier_on(bond->dev); - - } else { - dprintk("This is just a backup slave\n"); - bond_set_slave_inactive_flags(new_slave); - } + bond_set_slave_inactive_flags(new_slave); + bond_select_active_slave(bond); break; case BOND_MODE_8023AD: /* in 802.3ad mode, the internal mechanism @@ -1778,7 +1777,8 @@ int bond_release(struct net_device *bond_dev, struct net_device *slave_dev) dev_set_mac_address(slave_dev, &addr); slave_dev->priv_flags &= ~(IFF_MASTER_8023AD | IFF_MASTER_ALB | - IFF_SLAVE_INACTIVE); + IFF_SLAVE_INACTIVE | IFF_BONDING | + IFF_SLAVE_NEEDARP); kfree(slave); @@ -2291,6 +2291,25 @@ static int bond_has_ip(struct bonding *bond) return 0; } +static int bond_has_this_ip(struct bonding *bond, u32 ip) +{ + struct vlan_entry *vlan, *vlan_next; + + if (ip == bond->master_ip) + return 1; + + if (list_empty(&bond->vlan_list)) + return 0; + + list_for_each_entry_safe(vlan, vlan_next, &bond->vlan_list, + vlan_list) { + if (ip == vlan->vlan_ip) + return 1; + } + + return 0; +} + /* * We go to the (large) trouble of VLAN tagging ARP frames because * switches in VLAN mode (especially if ports are configured as @@ -2429,6 +2448,93 @@ static void bond_send_gratuitous_arp(struct bonding *bond) } } +static void bond_validate_arp(struct bonding *bond, struct slave *slave, u32 sip, u32 tip) +{ + int i; + u32 *targets = bond->params.arp_targets; + + targets = bond->params.arp_targets; + for (i = 0; (i < BOND_MAX_ARP_TARGETS) && targets[i]; i++) { + dprintk("bva: sip %u.%u.%u.%u tip %u.%u.%u.%u t[%d] " + "%u.%u.%u.%u bhti(tip) %d\n", + NIPQUAD(sip), NIPQUAD(tip), i, NIPQUAD(targets[i]), + bond_has_this_ip(bond, tip)); + if (sip == targets[i]) { + if (bond_has_this_ip(bond, tip)) + slave->last_arp_rx = jiffies; + return; + } + } +} + +static int bond_arp_rcv(struct sk_buff *skb, struct net_device *dev, struct packet_type *pt, struct net_device *orig_dev) +{ + struct arphdr *arp; + struct slave *slave; + struct bonding *bond; + unsigned char *arp_ptr; + u32 sip, tip; + + if (!(dev->priv_flags & IFF_BONDING) || !(dev->flags & IFF_MASTER)) + goto out; + + bond = dev->priv; + read_lock(&bond->lock); + + dprintk("bond_arp_rcv: bond %s skb->dev %s orig_dev %s\n", + bond->dev->name, skb->dev ? skb->dev->name : "NULL", + orig_dev ? orig_dev->name : "NULL"); + + slave = bond_get_slave_by_dev(bond, orig_dev); + if (!slave || !slave_do_arp_validate(bond, slave)) + goto out_unlock; + + /* ARP header, plus 2 device addresses, plus 2 IP addresses. */ + if (!pskb_may_pull(skb, (sizeof(struct arphdr) + + (2 * dev->addr_len) + + (2 * sizeof(u32))))) + goto out_unlock; + + arp = skb->nh.arph; + if (arp->ar_hln != dev->addr_len || + skb->pkt_type == PACKET_OTHERHOST || + skb->pkt_type == PACKET_LOOPBACK || + arp->ar_hrd != htons(ARPHRD_ETHER) || + arp->ar_pro != htons(ETH_P_IP) || + arp->ar_pln != 4) + goto out_unlock; + + arp_ptr = (unsigned char *)(arp + 1); + arp_ptr += dev->addr_len; + memcpy(&sip, arp_ptr, 4); + arp_ptr += 4 + dev->addr_len; + memcpy(&tip, arp_ptr, 4); + + dprintk("bond_arp_rcv: %s %s/%d av %d sv %d sip %u.%u.%u.%u" + " tip %u.%u.%u.%u\n", bond->dev->name, slave->dev->name, + slave->state, bond->params.arp_validate, + slave_do_arp_validate(bond, slave), NIPQUAD(sip), NIPQUAD(tip)); + + /* + * Backup slaves won't see the ARP reply, but do come through + * here for each ARP probe (so we swap the sip/tip to validate + * the probe). In a "redundant switch, common router" type of + * configuration, the ARP probe will (hopefully) travel from + * the active, through one switch, the router, then the other + * switch before reaching the backup. + */ + if (slave->state == BOND_STATE_ACTIVE) + bond_validate_arp(bond, slave, sip, tip); + else + bond_validate_arp(bond, slave, tip, sip); + +out_unlock: + read_unlock(&bond->lock); +out: + dev_kfree_skb(skb); + return NET_RX_SUCCESS; +} + /* * this function is called regularly to monitor each slave's link * ensuring that traffic is being sent and received when arp monitoring @@ -2593,7 +2699,8 @@ void bond_activebackup_arp_mon(struct net_device *bond_dev) */ bond_for_each_slave(bond, slave, i) { if (slave->link != BOND_LINK_UP) { - if ((jiffies - slave->dev->last_rx) <= delta_in_ticks) { + if ((jiffies - slave_last_rx(bond, slave)) <= + delta_in_ticks) { slave->link = BOND_LINK_UP; @@ -2638,7 +2745,7 @@ void bond_activebackup_arp_mon(struct net_device *bond_dev) if ((slave != bond->curr_active_slave) && (!bond->current_arp_slave) && - (((jiffies - slave->dev->last_rx) >= 3*delta_in_ticks) && + (((jiffies - slave_last_rx(bond, slave)) >= 3*delta_in_ticks) && bond_has_ip(bond))) { /* a backup slave has gone down; three times * the delta allows the current slave to be @@ -2685,7 +2792,7 @@ void bond_activebackup_arp_mon(struct net_device *bond_dev) * if it is up and needs to take over as the curr_active_slave */ if ((((jiffies - slave->dev->trans_start) >= (2*delta_in_ticks)) || - (((jiffies - slave->dev->last_rx) >= (2*delta_in_ticks)) && + (((jiffies - slave_last_rx(bond, slave)) >= (2*delta_in_ticks)) && bond_has_ip(bond))) && ((jiffies - slave->jiffies) >= 2*delta_in_ticks)) { @@ -2950,7 +3057,7 @@ static void bond_info_show_slave(struct seq_file *seq, const struct slave *slave seq_printf(seq, "\nSlave Interface: %s\n", slave->dev->name); seq_printf(seq, "MII Status: %s\n", (slave->link == BOND_LINK_UP) ? "up" : "down"); - seq_printf(seq, "Link Failure Count: %d\n", + seq_printf(seq, "Link Failure Count: %u\n", slave->link_failure_count); seq_printf(seq, @@ -3210,6 +3317,9 @@ static int bond_netdev_event(struct notifier_block *this, unsigned long event, v (event_dev ? event_dev->name : "None"), event); + if (!(event_dev->priv_flags & IFF_BONDING)) + return NOTIFY_DONE; + if (event_dev->flags & IFF_MASTER) { dprintk("IFF_MASTER\n"); return bond_master_netdev_event(event, event_dev); @@ -3305,6 +3415,21 @@ static void bond_unregister_lacpdu(struct bonding *bond) dev_remove_pack(&(BOND_AD_INFO(bond).ad_pkt_type)); } +void bond_register_arp(struct bonding *bond) +{ + struct packet_type *pt = &bond->arp_mon_pt; + + pt->type = htons(ETH_P_ARP); + pt->dev = NULL; /*bond->dev;XXX*/ + pt->func = bond_arp_rcv; + dev_add_pack(pt); +} + +void bond_unregister_arp(struct bonding *bond) +{ + dev_remove_pack(&bond->arp_mon_pt); +} + /*---------------------------- Hashing Policies -----------------------------*/ /* @@ -3391,6 +3516,9 @@ static int bond_open(struct net_device *bond_dev) } else { arp_timer->function = (void *)&bond_loadbalance_arp_mon; } + if (bond->params.arp_validate) + bond_register_arp(bond); + add_timer(arp_timer); } @@ -3418,9 +3546,11 @@ static int bond_close(struct net_device *bond_dev) bond_unregister_lacpdu(bond); } + if (bond->params.arp_validate) + bond_unregister_arp(bond); + write_lock_bh(&bond->lock); - bond_mc_list_destroy(bond); /* signal timers not to re-arm */ bond->kill_timers = 1; @@ -3451,8 +3581,6 @@ static int bond_close(struct net_device *bond_dev) break; } - /* Release the bonded slaves */ - bond_release_all(bond_dev); if ((bond->params.mode == BOND_MODE_TLB) || (bond->params.mode == BOND_MODE_ALB)) { @@ -4179,6 +4307,7 @@ static int bond_init(struct net_device *bond_dev, struct bond_params *params) /* Initialize the device options */ bond_dev->tx_queue_len = 0; bond_dev->flags |= IFF_MASTER|IFF_MULTICAST; + bond_dev->priv_flags |= IFF_BONDING; /* At first, we block adding VLANs. That's the only way to * prevent problems that occur when adding VLANs over an @@ -4237,6 +4366,9 @@ static void bond_free_all(void) list_for_each_entry_safe(bond, nxt, &bond_dev_list, bond_list) { struct net_device *bond_dev = bond->dev; + bond_mc_list_destroy(bond); + /* Release the bonded slaves */ + bond_release_all(bond_dev); unregister_netdevice(bond_dev); bond_deinit(bond_dev); } @@ -4270,6 +4402,8 @@ int bond_parse_parm(char *mode_arg, struct bond_parm_tbl *tbl) static int bond_check_params(struct bond_params *params) { + int arp_validate_value; + /* * Convert string parameters. */ @@ -4473,6 +4607,29 @@ static int bond_check_params(struct bond_params *params) arp_interval = 0; } + if (arp_validate) { + if (bond_mode != BOND_MODE_ACTIVEBACKUP) { + printk(KERN_ERR DRV_NAME + ": arp_validate only supported in active-backup mode\n"); + return -EINVAL; + } + if (!arp_interval) { + printk(KERN_ERR DRV_NAME + ": arp_validate requires arp_interval\n"); + return -EINVAL; + } + + arp_validate_value = bond_parse_parm(arp_validate, + arp_validate_tbl); + if (arp_validate_value == -1) { + printk(KERN_ERR DRV_NAME + ": Error: invalid arp_validate \"%s\"\n", + arp_validate == NULL ? "NULL" : arp_validate); + return -EINVAL; + } + } else + arp_validate_value = 0; + if (miimon) { printk(KERN_INFO DRV_NAME ": MII link monitoring set to %d ms\n", @@ -4481,8 +4638,10 @@ static int bond_check_params(struct bond_params *params) int i; printk(KERN_INFO DRV_NAME - ": ARP monitoring set to %d ms with %d target(s):", - arp_interval, arp_ip_count); + ": ARP monitoring set to %d ms, validate %s, with %d target(s):", + arp_interval, + arp_validate_tbl[arp_validate_value].modename, + arp_ip_count); for (i = 0; i < arp_ip_count; i++) printk (" %s", arp_ip_target[i]); @@ -4516,6 +4675,7 @@ static int bond_check_params(struct bond_params *params) params->xmit_policy = xmit_hashtype; params->miimon = miimon; params->arp_interval = arp_interval; + params->arp_validate = arp_validate_value; params->updelay = updelay; params->downdelay = downdelay; params->use_carrier = use_carrier; |