/* * originally based on the dummy device. * * Copyright 1999, Thomas Davis, tadavis@lbl.gov. * Licensed under the GPL. Based on dummy.c, and eql.c devices. * * bonding.c: an Ethernet Bonding driver * * This is useful to talk to a Cisco EtherChannel compatible equipment: * Cisco 5500 * Sun Trunking (Solaris) * Alteon AceDirector Trunks * Linux Bonding * and probably many L2 switches ... * * How it works: * ifconfig bond0 ipaddress netmask up * will setup a network device, with an ip address. No mac address * will be assigned at this time. The hw mac address will come from * the first slave bonded to the channel. All slaves will then use * this hw mac address. * * ifconfig bond0 down * will release all slaves, marking them as down. * * ifenslave bond0 eth0 * will attach eth0 to bond0 as a slave. eth0 hw mac address will either * a: be used as initial mac address * b: if a hw mac address already is there, eth0's hw mac address * will then be set from bond0. * */ //#define BONDING_DEBUG 1 #include #include #include #include #include #include #include #include #include #include #include #include #include #include #include #include #include #include #include #include #include #include #include #include #include #include #include #include #include #include #include #include #include #include #include #include #include #include #include #include #include #include #include #include "bonding.h" #include "bond_3ad.h" #include "bond_alb.h" /*---------------------------- Module parameters ----------------------------*/ /* monitor all links that often (in milliseconds). <=0 disables monitoring */ #define BOND_LINK_MON_INTERV 0 #define BOND_LINK_ARP_INTERV 0 static int max_bonds = BOND_DEFAULT_MAX_BONDS; static int miimon = BOND_LINK_MON_INTERV; static int updelay = 0; static int downdelay = 0; static int use_carrier = 1; static char *mode = NULL; static char *primary = NULL; 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, }; struct bond_params bonding_defaults; module_param(max_bonds, int, 0); MODULE_PARM_DESC(max_bonds, "Max number of bonded devices"); module_param(miimon, int, 0); MODULE_PARM_DESC(miimon, "Link check interval in milliseconds"); module_param(updelay, int, 0); MODULE_PARM_DESC(updelay, "Delay before considering link up, in milliseconds"); module_param(downdelay, int, 0); MODULE_PARM_DESC(downdelay, "Delay before considering link down, " "in milliseconds"); module_param(use_carrier, int, 0); MODULE_PARM_DESC(use_carrier, "Use netif_carrier_ok (vs MII ioctls) in miimon; " "0 for off, 1 for on (default)"); module_param(mode, charp, 0); MODULE_PARM_DESC(mode, "Mode of operation : 0 for balance-rr, " "1 for active-backup, 2 for balance-xor, " "3 for broadcast, 4 for 802.3ad, 5 for balance-tlb, " "6 for balance-alb"); module_param(primary, charp, 0); MODULE_PARM_DESC(primary, "Primary network device to use"); module_param(lacp_rate, charp, 0); MODULE_PARM_DESC(lacp_rate, "LACPDU tx rate to request from 802.3ad partner " "(slow/fast)"); module_param(xmit_hash_policy, charp, 0); MODULE_PARM_DESC(xmit_hash_policy, "XOR hashing method: 0 for layer 2 (default)" ", 1 for layer 3+4"); 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"); /*----------------------------- Global variables ----------------------------*/ 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 = NULL; #endif extern struct rw_semaphore bonding_rwsem; static u32 arp_target[BOND_MAX_ARP_TARGETS] = { 0, } ; static int arp_ip_count = 0; static int bond_mode = BOND_MODE_ROUNDROBIN; static int xmit_hashtype= BOND_XMIT_POLICY_LAYER2; static int lacp_fast = 0; struct bond_parm_tbl bond_lacp_tbl[] = { { "slow", AD_LACP_SLOW}, { "fast", AD_LACP_FAST}, { NULL, -1}, }; struct bond_parm_tbl bond_mode_tbl[] = { { "balance-rr", BOND_MODE_ROUNDROBIN}, { "active-backup", BOND_MODE_ACTIVEBACKUP}, { "balance-xor", BOND_MODE_XOR}, { "broadcast", BOND_MODE_BROADCAST}, { "802.3ad", BOND_MODE_8023AD}, { "balance-tlb", BOND_MODE_TLB}, { "balance-alb", BOND_MODE_ALB}, { NULL, -1}, }; struct bond_parm_tbl xmit_hashtype_tbl[] = { { "layer2", BOND_XMIT_POLICY_LAYER2}, { "layer3+4", BOND_XMIT_POLICY_LAYER34}, { NULL, -1}, }; /*-------------------------- Forward declarations ---------------------------*/ static void bond_send_gratuitous_arp(struct bonding *bond); /*---------------------------- General routines -----------------------------*/ const char *bond_mode_name(int mode) { switch (mode) { case BOND_MODE_ROUNDROBIN : return "load balancing (round-robin)"; case BOND_MODE_ACTIVEBACKUP : return "fault-tolerance (active-backup)"; case BOND_MODE_XOR : return "load balancing (xor)"; case BOND_MODE_BROADCAST : return "fault-tolerance (broadcast)"; case BOND_MODE_8023AD: return "IEEE 802.3ad Dynamic link aggregation"; case BOND_MODE_TLB: return "transmit load balancing"; case BOND_MODE_ALB: return "adaptive load balancing"; default: return "unknown"; } } /*---------------------------------- VLAN -----------------------------------*/ /** * bond_add_vlan - add a new vlan id on bond * @bond: bond that got the notification * @vlan_id: the vlan id to add * * Returns -ENOMEM if allocation failed. */ static int bond_add_vlan(struct bonding *bond, unsigned short vlan_id) { struct vlan_entry *vlan; dprintk("bond: %s, vlan id %d\n", (bond ? bond->dev->name: "None"), vlan_id); vlan = kmalloc(sizeof(struct vlan_entry), GFP_KERNEL); if (!vlan) { return -ENOMEM; } INIT_LIST_HEAD(&vlan->vlan_list); vlan->vlan_id = vlan_id; vlan->vlan_ip = 0; write_lock_bh(&bond->lock); list_add_tail(&vlan->vlan_list, &bond->vlan_list); write_unlock_bh(&bond->lock); dprintk("added VLAN ID %d on bond %s\n", vlan_id, bond->dev->name); return 0; } /** * bond_del_vlan - delete a vlan id from bond * @bond: bond that got the notification * @vlan_id: the vlan id to delete * * returns -ENODEV if @vlan_id was not found in @bond. */ static int bond_del_vlan(struct bonding *bond, unsigned short vlan_id) { struct vlan_entry *vlan, *next; int res = -ENODEV; dprintk("bond: %s, vlan id %d\n", bond->dev->name, vlan_id); write_lock_bh(&bond->lock); list_for_each_entry_safe(vlan, next, &bond->vlan_list, vlan_list) { if (vlan->vlan_id == vlan_id) { list_del(&vlan->vlan_list); if ((bond->params.mode == BOND_MODE_TLB) || (bond->params.mode == BOND_MODE_ALB)) { bond_alb_clear_vlan(bond, vlan_id); } dprintk("removed VLAN ID %d from bond %s\n", vlan_id, bond->dev->name); kfree(vlan); if (list_empty(&bond->vlan_list) && (bond->slave_cnt == 0)) { /* Last VLAN removed and no slaves, so * restore block on adding VLANs. This will * be removed once new slaves that are not * VLAN challenged will be added. */ bond->dev->features |= NETIF_F_VLAN_CHALLENGED; } res = 0; goto out; } } dprintk("couldn't find VLAN ID %d in bond %s\n", vlan_id, bond->dev->name); out: write_unlock_bh(&bond->lock); return res; } /** * bond_has_challenged_slaves * @bond: the bond we're working on * * Searches the slave list. Returns 1 if a vlan challenged slave * was found, 0 otherwise. * * Assumes bond->lock is held. */ static int bond_has_challenged_slaves(struct bonding *bond) { struct slave *slave; int i; bond_for_each_slave(bond, slave, i) { if (slave->dev->features & NETIF_F_VLAN_CHALLENGED) { dprintk("found VLAN challenged slave - %s\n", slave->dev->name); return 1; } } dprintk("no VLAN challenged slaves found\n"); return 0; } /** * bond_next_vlan - safely skip to the next item in the vlans list. * @bond: the bond we're working on * @curr: item we're advancing from * * Returns %NULL if list is empty, bond->next_vlan if @curr is %NULL, * or @curr->next otherwise (even if it is @curr itself again). * * Caller must hold bond->lock */ struct vlan_entry *bond_next_vlan(struct bonding *bond, struct vlan_entry *curr) { struct vlan_entry *next, *last; if (list_empty(&bond->vlan_list)) { return NULL; } if (!curr) { next = list_entry(bond->vlan_list.next, struct vlan_entry, vlan_list); } else { last = list_entry(bond->vlan_list.prev, struct vlan_entry, vlan_list); if (last == curr) { next = list_entry(bond->vlan_list.next, struct vlan_entry, vlan_list); } else { next = list_entry(curr->vlan_list.next, struct vlan_entry, vlan_list); } } return next; } /** * bond_dev_queue_xmit - Prepare skb for xmit. * * @bond: bond device that got this skb for tx. * @skb: hw accel VLAN tagged skb to transmit * @slave_dev: slave that is supposed to xmit this skbuff * * When the bond gets an skb to transmit that is * already hardware accelerated VLAN tagged, and it * needs to relay this skb to a slave that is not * hw accel capable, the skb needs to be "unaccelerated", * i.e. strip the hwaccel tag and re-insert it as part * of the payload. */ int bond_dev_queue_xmit(struct bonding *bond, struct sk_buff *skb, struct net_device *slave_dev) { unsigned short vlan_id; if (!list_empty(&bond->vlan_list) && !(slave_dev->features & NETIF_F_HW_VLAN_TX) && vlan_get_tag(skb, &vlan_id) == 0) { skb->dev = slave_dev; skb = vlan_put_tag(skb, vlan_id); if (!skb) { /* vlan_put_tag() frees the skb in case of error, * so return success here so the calling functions * won't attempt to free is again. */ return 0; } } else { skb->dev = slave_dev; } skb->priority = 1; dev_queue_xmit(skb); return 0; } /* * In the following 3 functions, bond_vlan_rx_register(), bond_vlan_rx_add_vid * and bond_vlan_rx_kill_vid, We don't protect the slave list iteration with a * lock because: * a. This operation is performed in IOCTL context, * b. The operation is protected by the RTNL semaphore in the 8021q code, * c. Holding a lock with BH disabled while directly calling a base driver * entry point is generally a BAD idea. * * The design of synchronization/protection for this operation in the 8021q * module is good for one or more VLAN devices over a single physical device * and cannot be extended for a teaming solution like bonding, so there is a * potential race condition here where a net device from the vlan group might * be referenced (either by a base driver or the 8021q code) while it is being * removed from the system. However, it turns out we're not making matters * worse, and if it works for regular VLAN usage it will work here too. */ /** * bond_vlan_rx_register - Propagates registration to slaves * @bond_dev: bonding net device that got called * @grp: vlan group being registered */ static void bond_vlan_rx_register(struct net_device *bond_dev, struct vlan_group *grp) { struct bonding *bond = bond_dev->priv; struct slave *slave; int i; bond->vlgrp = grp; bond_for_each_slave(bond, slave, i) { struct net_device *slave_dev = slave->dev; if ((slave_dev->features & NETIF_F_HW_VLAN_RX) && slave_dev->vlan_rx_register) { slave_dev->vlan_rx_register(slave_dev, grp); } } } /** * bond_vlan_rx_add_vid - Propagates adding an id to slaves * @bond_dev: bonding net device that got called * @vid: vlan id being added */ static void bond_vlan_rx_add_vid(struct net_device *bond_dev, uint16_t vid) { struct bonding *bond = bond_dev->priv; struct slave *slave; int i, res; bond_for_each_slave(bond, slave, i) { struct net_device *slave_dev = slave->dev; if ((slave_dev->features & NETIF_F_HW_VLAN_FILTER) && slave_dev->vlan_rx_add_vid) { slave_dev->vlan_rx_add_vid(slave_dev, vid); } } res = bond_add_vlan(bond, vid); if (res) { printk(KERN_ERR DRV_NAME ": %s: Error: Failed to add vlan id %d\n", bond_dev->name, vid); } } /** * bond_vlan_rx_kill_vid - Propagates deleting an id to slaves * @bond_dev: bonding net device that got called * @vid: vlan id being removed */ static void bond_vlan_rx_kill_vid(struct net_device *bond_dev, uint16_t vid) { struct bonding *bond = bond_dev->priv; struct slave *slave; struct net_device *vlan_dev; int i, res; bond_for_each_slave(bond, slave, i) { struct net_device *slave_dev = slave->dev; if ((slave_dev->features & NETIF_F_HW_VLAN_FILTER) && slave_dev->vlan_rx_kill_vid) { /* Save and then restore vlan_dev in the grp array, * since the slave's driver might clear it. */ vlan_dev = bond->vlgrp->vlan_devices[vid]; slave_dev->vlan_rx_kill_vid(slave_dev, vid); bond->vlgrp->vlan_devices[vid] = vlan_dev; } } res = bond_del_vlan(bond, vid); if (res) { printk(KERN_ERR DRV_NAME ": %s: Error: Failed to remove vlan id %d\n", bond_dev->name, vid); } } static void bond_add_vlans_on_slave(struct bonding *bond, struct net_device *slave_dev) { struct vlan_entry *vlan; write_lock_bh(&bond->lock); if (list_empty(&bond->vlan_list)) { goto out; } if ((slave_dev->features & NETIF_F_HW_VLAN_RX) && slave_dev->vlan_rx_register) { slave_dev->vlan_rx_register(slave_dev, bond->vlgrp); } if (!(slave_dev->features & NETIF_F_HW_VLAN_FILTER) || !(slave_dev->vlan_rx_add_vid)) { goto out; } list_for_each_entry(vlan, &bond->vlan_list, vlan_list) { slave_dev->vlan_rx_add_vid(slave_dev, vlan->vlan_id); } out: write_unlock_bh(&bond->lock); } static void bond_del_vlans_from_slave(struct bonding *bond, struct net_device *slave_dev) { struct vlan_entry *vlan; struct net_device *vlan_dev; write_lock_bh(&bond->lock); if (list_empty(&bond->vlan_list)) { goto out; } if (!(slave_dev->features & NETIF_F_HW_VLAN_FILTER) || !(slave_dev->vlan_rx_kill_vid)) { goto unreg; } list_for_each_entry(vlan, &bond->vlan_list, vlan_list) { /* Save and then restore vlan_dev in the grp array, * since the slave's driver might clear it. */ vlan_dev = bond->vlgrp->vlan_devices[vlan->vlan_id]; slave_dev->vlan_rx_kill_vid(slave_dev, vlan->vlan_id); bond->vlgrp->vlan_devices[vlan->vlan_id] = vlan_dev; } unreg: if ((slave_dev->features & NETIF_F_HW_VLAN_RX) && slave_dev->vlan_rx_register) { slave_dev->vlan_rx_register(slave_dev, NULL); } out: write_unlock_bh(&bond->lock); } /*------------------------------- Link status -------------------------------*/ /* * Set the carrier state for the master according to the state of its * slaves. If any slaves are up, the master is up. In 802.3ad mode, * do special 802.3ad magic. * * Returns zero if carrier state does not change, nonzero if it does. */ static int bond_set_carrier(struct bonding *bond) { struct slave *slave; int i; if (bond->slave_cnt == 0) goto down; if (bond->params.mode == BOND_MODE_8023AD) return bond_3ad_set_carrier(bond); bond_for_each_slave(bond, slave, i) { if (slave->link == BOND_LINK_UP) { if (!netif_carrier_ok(bond->dev)) { netif_carrier_on(bond->dev); return 1; } return 0; } } down: if (netif_carrier_ok(bond->dev)) { netif_carrier_off(bond->dev); return 1; } return 0; } /* * Get link speed and duplex from the slave's base driver * using ethtool. If for some reason the call fails or the * values are invalid, fake speed and duplex to 100/Full * and return error. */ static int bond_update_speed_duplex(struct slave *slave) { struct net_device *slave_dev = slave->dev; static int (* ioctl)(struct net_device *, struct ifreq *, int); struct ifreq ifr; struct ethtool_cmd etool; /* Fake speed and duplex */ slave->speed = SPEED_100; slave->duplex = DUPLEX_FULL; if (slave_dev->ethtool_ops) { int res; if (!slave_dev->ethtool_ops->get_settings) { return -1; } res = slave_dev->ethtool_ops->get_settings(slave_dev, &etool); if (res < 0) { return -1; } goto verify; } ioctl = slave_dev->do_ioctl; strncpy(ifr.ifr_name, slave_dev->name, IFNAMSIZ); etool.cmd = ETHTOOL_GSET; ifr.ifr_data = (char*)&etool; if (!ioctl || (IOCTL(slave_dev, &ifr, SIOCETHTOOL) < 0)) { return -1; } verify: switch (etool.speed) { case SPEED_10: case SPEED_100: case SPEED_1000: break; default: return -1; } switch (etool.duplex) { case DUPLEX_FULL: case DUPLEX_HALF: break; default: return -1; } slave->speed = etool.speed; slave->duplex = etool.duplex; return 0; } /* * if supports MII link status reporting, check its link status. * * We either do MII/ETHTOOL ioctls, or check netif_carrier_ok(), * depening upon the setting of the use_carrier parameter. * * Return either BMSR_LSTATUS, meaning that the link is up (or we * can't tell and just pretend it is), or 0, meaning that the link is * down. * * If reporting is non-zero, instead of faking link up, return -1 if * both ETHTOOL and MII ioctls fail (meaning the device does not * support them). If use_carrier is set, return whatever it says. * It'd be nice if there was a good way to tell if a driver supports * netif_carrier, but there really isn't. */ static int bond_check_dev_link(struct bonding *bond, struct net_device *slave_dev, int reporting) { static int (* ioctl)(struct net_device *, struct ifreq *, int); struct ifreq ifr; struct mii_ioctl_data *mii; struct ethtool_value etool; if (bond->params.use_carrier) { return netif_carrier_ok(slave_dev) ? BMSR_LSTATUS : 0; } ioctl = slave_dev->do_ioctl; if (ioctl) { /* TODO: set pointer to correct ioctl on a per team member */ /* bases to make this more efficient. that is, once */ /* we determine the correct ioctl, we will always */ /* call it and not the others for that team */ /* member. */ /* * We cannot assume that SIOCGMIIPHY will also read a * register; not all network drivers (e.g., e100) * support that. */ /* Yes, the mii is overlaid on the ifreq.ifr_ifru */ strncpy(ifr.ifr_name, slave_dev->name, IFNAMSIZ); mii = if_mii(&ifr); if (IOCTL(slave_dev, &ifr, SIOCGMIIPHY) == 0) { mii->reg_num = MII_BMSR; if (IOCTL(slave_dev, &ifr, SIOCGMIIREG) == 0) { return (mii->val_out & BMSR_LSTATUS); } } } /* try SIOCETHTOOL ioctl, some drivers cache ETHTOOL_GLINK */ /* for a period of time so we attempt to get link status */ /* from it last if the above MII ioctls fail... */ if (slave_dev->ethtool_ops) { if (slave_dev->ethtool_ops->get_link) { u32 link; link = slave_dev->ethtool_ops->get_link(slave_dev); return link ? BMSR_LSTATUS : 0; } } if (ioctl) { strncpy(ifr.ifr_name, slave_dev->name, IFNAMSIZ); etool.cmd = ETHTOOL_GLINK; ifr.ifr_data = (char*)&etool; if (IOCTL(slave_dev, &ifr, SIOCETHTOOL) == 0) { if (etool.data == 1) { return BMSR_LSTATUS; } else { dprintk("SIOCETHTOOL shows link down\n"); return 0; } } } /* * If reporting, report that either there's no dev->do_ioctl, * or both SIOCGMIIREG and SIOCETHTOOL failed (meaning that we * cannot report link status). If not reporting, pretend * we're ok. */ return (reporting ? -1 : BMSR_LSTATUS); } /*----------------------------- Multicast list ------------------------------*/ /* * Returns 0 if dmi1 and dmi2 are the same, non-0 otherwise */ static inline int bond_is_dmi_same(struct dev_mc_list *dmi1, struct dev_mc_list *dmi2) { return memcmp(dmi1->dmi_addr, dmi2->dmi_addr, dmi1->dmi_addrlen) == 0 && dmi1->dmi_addrlen == dmi2->dmi_addrlen; } /* * returns dmi entry if found, NULL otherwise */ static struct dev_mc_list *bond_mc_list_find_dmi(struct dev_mc_list *dmi, struct dev_mc_list *mc_list) { struct dev_mc_list *idmi; for (idmi = mc_list; idmi; idmi = idmi->next) { if (bond_is_dmi_same(dmi, idmi)) { return idmi; } } return NULL; } /* * Push the promiscuity flag down to appropriate slaves */ static void bond_set_promiscuity(struct bonding *bond, int inc) { if (USES_PRIMARY(bond->params.mode)) { /* write lock already acquired */ if (bond->curr_active_slave) { dev_set_promiscuity(bond->curr_active_slave->dev, inc); } } else { struct slave *slave; int i; bond_for_each_slave(bond, slave, i) { dev_set_promiscuity(slave->dev, inc); } } } /* * Push the allmulti flag down to all slaves */ static void bond_set_allmulti(struct bonding *bond, int inc) { if (USES_PRIMARY(bond->params.mode)) { /* write lock already acquired */ if (bond->curr_active_slave) { dev_set_allmulti(bond->curr_active_slave->dev, inc); } } else { struct slave *slave; int i; bond_for_each_slave(bond, slave, i) { dev_set_allmulti(slave->dev, inc); } } } /* * Add a Multicast address to slaves * according to mode */ static void bond_mc_add(struct bonding *bond, void *addr, int alen) { if (USES_PRIMARY(bond->params.mode)) { /* write lock already acquired */ if (bond->curr_active_slave) { dev_mc_add(bond->curr_active_slave->dev, addr, alen, 0); } } else { struct slave *slave; int i; bond_for_each_slave(bond, slave, i) { dev_mc_add(slave->dev, addr, alen, 0); } } } /* * Remove a multicast address from slave * according to mode */ static void bond_mc_delete(struct bonding *bond, void *addr, int alen) { if (USES_PRIMARY(bond->params.mode)) { /* write lock already acquired */ if (bond->curr_active_slave) { dev_mc_delete(bond->curr_active_slave->dev, addr, alen, 0); } } else { struct slave *slave; int i; bond_for_each_slave(bond, slave, i) { dev_mc_delete(slave->dev, addr, alen, 0); } } } /* * Totally destroys the mc_list in bond */ static void bond_mc_list_destroy(struct bonding *bond) { struct dev_mc_list *dmi; dmi = bond->mc_list; while (dmi) { bond->mc_list = dmi->next; kfree(dmi); dmi = bond->mc_list; } } /* * Copy all the Multicast addresses from src to the bonding device dst */ static int bond_mc_list_copy(struct dev_mc_list *mc_list, struct bonding *bond, gfp_t gfp_flag) { struct dev_mc_list *dmi, *new_dmi; for (dmi = mc_list; dmi; dmi = dmi->next) { new_dmi = kmalloc(sizeof(struct dev_mc_list), gfp_flag); if (!new_dmi) { /* FIXME: Potential memory leak !!! */ return -ENOMEM; } new_dmi->next = bond->mc_list; bond->mc_list = new_dmi; new_dmi->dmi_addrlen = dmi->dmi_addrlen; memcpy(new_dmi->dmi_addr, dmi->dmi_addr, dmi->dmi_addrlen); new_dmi->dmi_users = dmi->dmi_users; new_dmi->dmi_gusers = dmi->dmi_gusers; } return 0; } /* * flush all members of flush->mc_list from device dev->mc_list */ static void bond_mc_list_flush(struct net_device *bond_dev, struct net_device *slave_dev) { struct bonding *bond = bond_dev->priv; struct dev_mc_list *dmi; for (dmi = bond_dev->mc_list; dmi; dmi = dmi->next) { dev_mc_delete(slave_dev, dmi->dmi_addr, dmi->dmi_addrlen, 0); } if (bond->params.mode == BOND_MODE_8023AD) { /* del lacpdu mc addr from mc list */ u8 lacpdu_multicast[ETH_ALEN] = MULTICAST_LACPDU_ADDR; dev_mc_delete(slave_dev, lacpdu_multicast, ETH_ALEN, 0); } } /*--------------------------- Active slave change ---------------------------*/ /* * Update the mc list and multicast-related flags for the new and * old active slaves (if any) according to the multicast mode, and * promiscuous flags unconditionally. */ static void bond_mc_swap(struct bonding *bond, struct slave *new_active, struct slave *old_active) { struct dev_mc_list *dmi; if (!USES_PRIMARY(bond->params.mode)) { /* nothing to do - mc list is already up-to-date on * all slaves */ return; } if (old_active) { if (bond->dev->flags & IFF_PROMISC) { dev_set_promiscuity(old_active->dev, -1); } if (bond->dev->flags & IFF_ALLMULTI) { dev_set_allmulti(old_active->dev, -1); } for (dmi = bond->dev->mc_list; dmi; dmi = dmi->next) { dev_mc_delete(old_active->dev, dmi->dmi_addr, dmi->dmi_addrlen, 0); } } if (new_active) { if (bond->dev->flags & IFF_PROMISC) { dev_set_promiscuity(new_active->dev, 1); } if (bond->dev->flags & IFF_ALLMULTI) { dev_set_allmulti(new_active->dev, 1); } for (dmi = bond->dev->mc_list; dmi; dmi = dmi->next) { dev_mc_add(new_active->dev, dmi->dmi_addr, dmi->dmi_addrlen, 0); } } } /** * find_best_interface - select the best available slave to be the active one * @bond: our bonding struct * * Warning: Caller must hold curr_slave_lock for writing. */ static struct slave *bond_find_best_slave(struct bonding *bond) { struct slave *new_active, *old_active; struct slave *bestslave = NULL; int mintime = bond->params.updelay; int i; new_active = old_active = bond->curr_active_slave; if (!new_active) { /* there were no active slaves left */ if (bond->slave_cnt > 0) { /* found one slave */ new_active = bond->first_slave; } else { return NULL; /* still no slave, return NULL */ } } /* first try the primary link; if arping, a link must tx/rx traffic * before it can be considered the curr_active_slave - also, we would skip * slaves between the curr_active_slave and primary_slave that may be up * and able to arp */ if ((bond->primary_slave) && (!bond->params.arp_interval) && (IS_UP(bond->primary_slave->dev))) { new_active = bond->primary_slave; } /* remember where to stop iterating over the slaves */ old_active = new_active; bond_for_each_slave_from(bond, new_active, i, old_active) { if (IS_UP(new_active->dev)) { if (new_active->link == BOND_LINK_UP) { return new_active; } else if (new_active->link == BOND_LINK_BACK) { /* link up, but waiting for stabilization */ if (new_active->delay < mintime) { mintime = new_active->delay; bestslave = new_active; } } } } return bestslave; } /** * change_active_interface - change the active slave into the specified one * @bond: our bonding struct * @new: the new slave to make the active one * * Set the new slave to the bond's settings and unset them on the old * curr_active_slave. * Setting include flags, mc-list, promiscuity, allmulti, etc. * * If @new's link state is %BOND_LINK_BACK we'll set it to %BOND_LINK_UP, * because it is apparently the best available slave we have, even though its * updelay hasn't timed out yet. * * Warning: Caller must hold curr_slave_lock for writing. */ void bond_change_active_slave(struct bonding *bond, struct slave *new_active) { struct slave *old_active = bond->curr_active_slave; if (old_active == new_active) { return; } if (new_active) { if (new_active->link == BOND_LINK_BACK) { if (USES_PRIMARY(bond->params.mode)) { printk(KERN_INFO DRV_NAME ": %s: making interface %s the new " "active one %d ms earlier.\n", bond->dev->name, new_active->dev->name, (bond->params.updelay - new_active->delay) * bond->params.miimon); } new_active->delay = 0; new_active->link = BOND_LINK_UP; new_active->jiffies = jiffies; if (bond->params.mode == BOND_MODE_8023AD) { bond_3ad_handle_link_change(new_active, BOND_LINK_UP); } if ((bond->params.mode == BOND_MODE_TLB) || (bond->params.mode == BOND_MODE_ALB)) { bond_alb_handle_link_change(bond, new_active, BOND_LINK_UP); } } else { if (USES_PRIMARY(bond->params.mode)) { printk(KERN_INFO DRV_NAME ": %s: making interface %s the new " "active one.\n", bond->dev->name, new_active->dev->name); } } } if (USES_PRIMARY(bond->params.mode)) { bond_mc_swap(bond, new_active, old_active); } if ((bond->params.mode == BOND_MODE_TLB) || (bond->params.mode == BOND_MODE_ALB)) { bond_alb_handle_active_change(bond, new_active); if (old_active) bond_set_slave_inactive_flags(old_active); if (new_active) bond_set_slave_active_flags(new_active); } else { bond->curr_active_slave = new_active; } if (bond->params.mode == BOND_MODE_ACTIVEBACKUP) { if (old_active) { bond_set_slave_inactive_flags(old_active); } if (new_active) { bond_set_slave_active_flags(new_active); } bond_send_gratuitous_arp(bond); } } /** * bond_select_active_slave - select a new active slave, if needed * @bond: our bonding struct * * This functions shoud be called when one of the following occurs: * - The old curr_active_slave has been released or lost its link. * - The primary_slave has got its link back. * - A slave has got its link back and there's no old curr_active_slave. * * Warning: Caller must hold curr_slave_lock for writing. */ void bond_select_active_slave(struct bonding *bond) { struct slave *best_slave; int rv; best_slave = bond_find_best_slave(bond); if (best_slave != bond->curr_active_slave) { bond_change_active_slave(bond, best_slave); rv = bond_set_carrier(bond); if (!rv) return; if (netif_carrier_ok(bond->dev)) { printk(KERN_INFO DRV_NAME ": %s: first active interface up!\n", bond->dev->name); } else { printk(KERN_INFO DRV_NAME ": %s: " "now running without any active interface !\n", bond->dev->name); } } } /*--------------------------- slave list handling ---------------------------*/ /* * This function attaches the slave to the end of list. * * bond->lock held for writing by caller. */ static void bond_attach_slave(struct bonding *bond, struct slave *new_slave) { if (bond->first_slave == NULL) { /* attaching the first slave */ new_slave->next = new_slave; new_slave->prev = new_slave; bond->first_slave = new_slave; } else { new_slave->next = bond->first_slave; new_slave->prev = bond->first_slave->prev; new_slave->next->prev = new_slave; new_slave->prev->next = new_slave; } bond->slave_cnt++; } /* * This function detaches the slave from the list. * WARNING: no check is made to verify if the slave effectively * belongs to . * Nothing is freed on return, structures are just unchained. * If any slave pointer in bond was pointing to , * it should be changed by the calling function. * * bond->lock held for writing by caller. */ static void bond_detach_slave(struct bonding *bond, struct slave *slave) { if (slave->next) { slave->next->prev = slave->prev; } if (slave->prev) { slave->prev->next = slave->next; } if (bond->first_slave == slave) { /* slave is the first slave */ if (bond->slave_cnt > 1) { /* there are more slave */ bond->first_slave = slave->next; } else { bond->first_slave = NULL; /* slave was the last one */ } } slave->next = NULL; slave->prev = NULL; bond->slave_cnt--; } /*---------------------------------- IOCTL ----------------------------------*/ int bond_sethwaddr(struct net_device *bond_dev, struct net_device *slave_dev) { dprintk("bond_dev=%p\n", bond_dev); dprintk("slave_dev=%p\n", slave_dev); dprintk("slave_dev->addr_len=%d\n", slave_dev->addr_len); memcpy(bond_dev->dev_addr, slave_dev->dev_addr, slave_dev->addr_len); return 0; } #define BOND_INTERSECT_FEATURES \ (NETIF_F_SG|NETIF_F_IP_CSUM|NETIF_F_NO_CSUM|NETIF_F_HW_CSUM|\ NETIF_F_TSO|NETIF_F_UFO) /* * Compute the common dev->feature set available to all slaves. Some * feature bits are managed elsewhere, so preserve feature bits set on * master device that are not part of the examined set. */ static int bond_compute_features(struct bonding *bond) { unsigned long features = BOND_INTERSECT_FEATURES; struct slave *slave; struct net_device *bond_dev = bond->dev; int i; bond_for_each_slave(bond, slave, i) features &= (slave->dev->features & BOND_INTERSECT_FEATURES); if ((features & NETIF_F_SG) && !(features & (NETIF_F_IP_CSUM | NETIF_F_NO_CSUM | NETIF_F_HW_CSUM))) features &= ~NETIF_F_SG; /* * features will include NETIF_F_TSO (NETIF_F_UFO) iff all * slave devices support NETIF_F_TSO (NETIF_F_UFO), which * implies that all slaves also support scatter-gather * (NETIF_F_SG), which implies that features also includes * NETIF_F_SG. So no need to check whether we have an * illegal combination of NETIF_F_{TSO,UFO} and * !NETIF_F_SG */ features |= (bond_dev->features & ~BOND_INTERSECT_FEATURES); bond_dev->features = features; return 0; } /* enslave device to bond device */ int bond_enslave(struct net_device *bond_dev, struct net_device *slave_dev) { struct bonding *bond = bond_dev->priv; struct slave *new_slave = NULL; struct dev_mc_list *dmi; struct sockaddr addr; int link_reporting; int old_features = bond_dev->features; int res = 0; if (!bond->params.use_carrier && slave_dev->ethtool_ops == NULL && slave_dev->do_ioctl == NULL) { printk(KERN_WARNING DRV_NAME ": %s: Warning: no link monitoring support for %s\n", bond_dev->name, slave_dev->name); } /* bond must be initialized by bond_open() before enslaving */ if (!(bond_dev->flags & IFF_UP)) { dprintk("Error, master_dev is not up\n"); return -EPERM; } /* already enslaved */ if (slave_dev->flags & IFF_SLAVE) { dprintk("Error, Device was already enslaved\n"); return -EBUSY; } /* vlan challenged mutual exclusion */ /* no need to lock since we're protected by rtnl_lock */ if (slave_dev->features & NETIF_F_VLAN_CHALLENGED) { dprintk("%s: NETIF_F_VLAN_CHALLENGED\n", slave_dev->name); if (!list_empty(&bond->vlan_list)) { printk(KERN_ERR DRV_NAME ": %s: Error: cannot enslave VLAN " "challenged slave %s on VLAN enabled " "bond %s\n", bond_dev->name, slave_dev->name, bond_dev->name); return -EPERM; } else { printk(KERN_WARNING DRV_NAME ": %s: Warning: enslaved VLAN challenged " "slave %s. Adding VLANs will be blocked as " "long as %s is part of bond %s\n", bond_dev->name, slave_dev->name, slave_dev->name, bond_dev->name); bond_dev->features |= NETIF_F_VLAN_CHALLENGED; } } else { dprintk("%s: ! NETIF_F_VLAN_CHALLENGED\n", slave_dev->name); if (bond->slave_cnt == 0) { /* First slave, and it is not VLAN challenged, * so remove the block of adding VLANs over the bond. */ bond_dev->features &= ~NETIF_F_VLAN_CHALLENGED; } } /* * Old ifenslave binaries are no longer supported. These can * be identified with moderate accurary by the state of the slave: * the current ifenslave will set the interface down prior to * enslaving it; the old ifenslave will not. */ if ((slave_dev->flags & IFF_UP)) { printk(KERN_ERR DRV_NAME ": %s is up. " "This may be due to an out of date ifenslave.\n", slave_dev->name); res = -EPERM; goto err_undo_flags; } if (slave_dev->set_mac_address == NULL) { printk(KERN_ERR DRV_NAME ": %s: Error: The slave device you specified does " "not support setting the MAC address. " "Your kernel likely does not support slave " "devices.\n", bond_dev->name); res = -EOPNOTSUPP; goto err_undo_flags; } new_slave = kmalloc(sizeof(struct slave), GFP_KERNEL); if (!new_slave) { res = -ENOMEM; goto err_undo_flags; } memset(new_slave, 0, sizeof(struct slave)); /* save slave's original flags before calling * netdev_set_master and dev_open */ new_slave->original_flags = slave_dev->flags; /* * Save slave's original ("permanent") mac address for modes * that need it, and for restoring it upon release, and then * set it to the master's address */ memcpy(new_slave->perm_hwaddr, slave_dev->dev_addr, ETH_ALEN); /* * Set slave to master's mac address. The application already * set the master's mac address to that of the first slave */ memcpy(addr.sa_data, bond_dev->dev_addr, bond_dev->addr_len); addr.sa_family = slave_dev->type; res = dev_set_mac_address(slave_dev, &addr); if (res) { dprintk("Error %d calling set_mac_address\n", res); goto err_free; } /* open the slave since the application closed it */ res = dev_open(slave_dev); if (res) { dprintk("Openning slave %s failed\n", slave_dev->name); goto err_restore_mac; } res = netdev_set_master(slave_dev, bond_dev); if (res) { dprintk("Error %d calling netdev_set_master\n", res); goto err_close; } new_slave->dev = slave_dev; if ((bond->params.mode == BOND_MODE_TLB) || (bond->params.mode == BOND_MODE_ALB)) { /* bond_alb_init_slave() must be called before all other stages since * it might fail and we do not want to have to undo everything */ res = bond_alb_init_slave(bond, new_slave); if (res) { goto err_unset_master; } } /* If the mode USES_PRIMARY, then the new slave gets the * master's promisc (and mc) settings only if it becomes the * curr_active_slave, and that is taken care of later when calling * bond_change_active() */ if (!USES_PRIMARY(bond->params.mode)) { /* set promiscuity level to new slave */ if (bond_dev->flags & IFF_PROMISC) { dev_set_promiscuity(slave_dev, 1); } /* set allmulti level to new slave */ if (bond_dev->flags & IFF_ALLMULTI) { dev_set_allmulti(slave_dev, 1); } /* upload master's mc_list to new slave */ for (dmi = bond_dev->mc_list; dmi; dmi = dmi->next) { dev_mc_add (slave_dev, dmi->dmi_addr, dmi->dmi_addrlen, 0); } } if (bond->params.mode == BOND_MODE_8023AD) { /* add lacpdu mc addr to mc list */ u8 lacpdu_multicast[ETH_ALEN] = MULTICAST_LACPDU_ADDR; dev_mc_add(slave_dev, lacpdu_multicast, ETH_ALEN, 0); } bond_add_vlans_on_slave(bond, slave_dev); write_lock_bh(&bond->lock); bond_attach_slave(bond, new_slave); new_slave->delay = 0; new_slave->link_failure_count = 0; bond_compute_features(bond); if (bond->params.miimon && !bond->params.use_carrier) { link_reporting = bond_check_dev_link(bond, slave_dev, 1); if ((link_reporting == -1) && !bond->params.arp_interval) { /* * miimon is set but a bonded network driver * does not support ETHTOOL/MII and * arp_interval is not set. Note: if * use_carrier is enabled, we will never go * here (because netif_carrier is always * supported); thus, we don't need to change * the messages for netif_carrier. */ printk(KERN_WARNING DRV_NAME ": %s: Warning: MII and ETHTOOL support not " "available for interface %s, and " "arp_interval/arp_ip_target module parameters " "not specified, thus bonding will not detect " "link failures! see bonding.txt for details.\n", bond_dev->name, slave_dev->name); } else if (link_reporting == -1) { /* unable get link status using mii/ethtool */ printk(KERN_WARNING DRV_NAME ": %s: Warning: can't get link status from " "interface %s; the network driver associated " "with this interface does not support MII or " "ETHTOOL link status reporting, thus miimon " "has no effect on this interface.\n", bond_dev->name, slave_dev->name); } } /* check for initial state */ if (!bond->params.miimon || (bond_check_dev_link(bond, slave_dev, 0) == BMSR_LSTATUS)) { if (bond->params.updelay) { dprintk("Initial state of slave_dev is " "BOND_LINK_BACK\n"); new_slave->link = BOND_LINK_BACK; new_slave->delay = bond->params.updelay; } else { dprintk("Initial state of slave_dev is " "BOND_LINK_UP\n"); new_slave->link = BOND_LINK_UP; } new_slave->jiffies = jiffies; } else { dprintk("Initial state of slave_dev is " "BOND_LINK_DOWN\n"); new_slave->link = BOND_LINK_DOWN; } if (bond_update_speed_duplex(new_slave) && (new_slave->link != BOND_LINK_DOWN)) { printk(KERN_WARNING DRV_NAME ": %s: Warning: failed to get speed and duplex from %s, " "assumed to be 100Mb/sec and Full.\n", bond_dev->name, new_slave->dev->name); if (bond->params.mode == BOND_MODE_8023AD) { printk(KERN_WARNING DRV_NAME ": %s: Warning: Operation of 802.3ad mode requires ETHTOOL " "support in base driver for proper aggregator " "selection.\n", bond_dev->name); } } 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) { bond->primary_slave = new_slave; } } 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); } break; case BOND_MODE_8023AD: /* in 802.3ad mode, the internal mechanism * will activate the slaves in the selected * aggregator */ bond_set_slave_inactive_flags(new_slave); /* if this is the first slave */ if (bond->slave_cnt == 1) { SLAVE_AD_INFO(new_slave).id = 1; /* Initialize AD with the number of times that the AD timer is called in 1 second * can be called only after the mac address of the bond is set */ bond_3ad_initialize(bond, 1000/AD_TIMER_INTERVAL, bond->params.lacp_fast); } else { SLAVE_AD_INFO(new_slave).id = SLAVE_AD_INFO(new_slave->prev).id + 1; } bond_3ad_bind_slave(new_slave); break; case BOND_MODE_TLB: case BOND_MODE_ALB: new_slave->state = BOND_STATE_ACTIVE; if ((!bond->curr_active_slave) && (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); } else { bond_set_slave_inactive_flags(new_slave); } break; default: dprintk("This slave is always active in trunk mode\n"); /* always active in trunk mode */ new_slave->state = BOND_STATE_ACTIVE; /* In trunking mode there is little meaning to curr_active_slave * anyway (it holds no special properties of the bond device), * so we can change it without calling change_active_interface() */ if (!bond->curr_active_slave) { bond->curr_active_slave = new_slave; } break; } /* switch(bond_mode) */ bond_set_carrier(bond); write_unlock_bh(&bond->lock); res = bond_create_slave_symlinks(bond_dev, slave_dev); if (res) goto err_unset_master; printk(KERN_INFO DRV_NAME ": %s: enslaving %s as a%s interface with a%s link.\n", bond_dev->name, slave_dev->name, new_slave->state == BOND_STATE_ACTIVE ? "n active" : " backup", new_slave->link != BOND_LINK_DOWN ? "n up" : " down"); /* enslave is successful */ return 0; /* Undo stages on error */ err_unset_master: netdev_set_master(slave_dev, NULL); err_close: dev_close(slave_dev); err_restore_mac: memcpy(addr.sa_data, new_slave->perm_hwaddr, ETH_ALEN); addr.sa_family = slave_dev->type; dev_set_mac_address(slave_dev, &addr); err_free: kfree(new_slave); err_undo_flags: bond_dev->features = old_features; return res; } /* * Try to release the slave device from the bond device * It is legal to access curr_active_slave without a lock because all the function * is write-locked. * * The rules for slave state should be: * for Active/Backup: * Active stays on all backups go down * for Bonded connections: * The first up interface should be left on and all others downed. */ int bond_release(struct net_device *bond_dev, struct net_device *slave_dev) { struct bonding *bond = bond_dev->priv; struct slave *slave, *oldcurrent; struct sockaddr addr; int mac_addr_differ; /* slave is not a slave or master is not master of this slave */ if (!(slave_dev->flags & IFF_SLAVE) || (slave_dev->master != bond_dev)) { printk(KERN_ERR DRV_NAME ": %s: Error: cannot release %s.\n", bond_dev->name, slave_dev->name); return -EINVAL; } write_lock_bh(&bond->lock); slave = bond_get_slave_by_dev(bond, slave_dev); if (!slave) { /* not a slave of this bond */ printk(KERN_INFO DRV_NAME ": %s: %s not enslaved\n", bond_dev->name, slave_dev->name); write_unlock_bh(&bond->lock); return -EINVAL; } mac_addr_differ = memcmp(bond_dev->dev_addr, slave->perm_hwaddr, ETH_ALEN); if (!mac_addr_differ && (bond->slave_cnt > 1)) { printk(KERN_WARNING DRV_NAME ": %s: Warning: the permanent HWaddr of %s " "- %02X:%02X:%02X:%02X:%02X:%02X - is " "still in use by %s. Set the HWaddr of " "%s to a different address to avoid " "conflicts.\n", bond_dev->name, slave_dev->name, slave->perm_hwaddr[0], slave->perm_hwaddr[1], slave->perm_hwaddr[2], slave->perm_hwaddr[3], slave->perm_hwaddr[4], slave->perm_hwaddr[5], bond_dev->name, slave_dev->name); } /* Inform AD package of unbinding of slave. */ if (bond->params.mode == BOND_MODE_8023AD) { /* must be called before the slave is * detached from the list */ bond_3ad_unbind_slave(slave); } printk(KERN_INFO DRV_NAME ": %s: releasing %s interface %s\n", bond_dev->name, (slave->state == BOND_STATE_ACTIVE) ? "active" : "backup", slave_dev->name); oldcurrent = bond->curr_active_slave; bond->current_arp_slave = NULL; /* release the slave from its bond */ bond_detach_slave(bond, slave); bond_compute_features(bond); if (bond->primary_slave == slave) { bond->primary_slave = NULL; } if (oldcurrent == slave) { bond_change_active_slave(bond, NULL); } if ((bond->params.mode == BOND_MODE_TLB) || (bond->params.mode == BOND_MODE_ALB)) { /* Must be called only after the slave has been * detached from the list and the curr_active_slave * has been cleared (if our_slave == old_current), * but before a new active slave is selected. */ bond_alb_deinit_slave(bond, slave); } if (oldcurrent == slave) bond_select_active_slave(bond); if (bond->slave_cnt == 0) { bond_set_carrier(bond); /* if the last slave was removed, zero the mac address * of the master so it will be set by the application * to the mac address of the first slave */ memset(bond_dev->dev_addr, 0, bond_dev->addr_len); if (list_empty(&bond->vlan_list)) { bond_dev->features |= NETIF_F_VLAN_CHALLENGED; } else { printk(KERN_WARNING DRV_NAME ": %s: Warning: clearing HW address of %s while it " "still has VLANs.\n", bond_dev->name, bond_dev->name); printk(KERN_WARNING DRV_NAME ": %s: When re-adding slaves, make sure the bond's " "HW address matches its VLANs'.\n", bond_dev->name); } } else if ((bond_dev->features & NETIF_F_VLAN_CHALLENGED) && !bond_has_challenged_slaves(bond)) { printk(KERN_INFO DRV_NAME ": %s: last VLAN challenged slave %s " "left bond %s. VLAN blocking is removed\n", bond_dev->name, slave_dev->name, bond_dev->name); bond_dev->features &= ~NETIF_F_VLAN_CHALLENGED; } write_unlock_bh(&bond->lock); /* must do this from outside any spinlocks */ bond_destroy_slave_symlinks(bond_dev, slave_dev); bond_del_vlans_from_slave(bond, slave_dev); /* If the mode USES_PRIMARY, then we should only remove its * promisc and mc settings if it was the curr_active_slave, but that was * already taken care of above when we detached the slave */ if (!USES_PRIMARY(bond->params.mode)) { /* unset promiscuity level from slave */ if (bond_dev->flags & IFF_PROMISC) { dev_set_promiscuity(slave_dev, -1); } /* unset allmulti level from slave */ if (bond_dev->flags & IFF_ALLMULTI) { dev_set_allmulti(slave_dev, -1); } /* flush master's mc_list from slave */ bond_mc_list_flush(bond_dev, slave_dev); } netdev_set_master(slave_dev, NULL); /* close slave before restoring its mac address */ dev_close(slave_dev); /* restore original ("permanent") mac address */ memcpy(addr.sa_data, slave->perm_hwaddr, ETH_ALEN); addr.sa_family = slave_dev->type; dev_set_mac_address(slave_dev, &addr); slave_dev->priv_flags &= ~(IFF_MASTER_8023AD | IFF_MASTER_ALB | IFF_SLAVE_INACTIVE); kfree(slave); return 0; /* deletion OK */ } /* * This function releases all slaves. */ static int bond_release_all(struct net_device *bond_dev) { struct bonding *bond = bond_dev->priv; struct slave *slave; struct net_device *slave_dev; struct sockaddr addr; write_lock_bh(&bond->lock); netif_carrier_off(bond_dev); if (bond->slave_cnt == 0) { goto out; } bond->current_arp_slave = NULL; bond->primary_slave = NULL; bond_change_active_slave(bond, NULL); while ((slave = bond->first_slave) != NULL) { /* Inform AD package of unbinding of slave * before slave is detached from the list. */ if (bond->params.mode == BOND_MODE_8023AD) { bond_3ad_unbind_slave(slave); } slave_dev = slave->dev; bond_detach_slave(bond, slave); if ((bond->params.mode == BOND_MODE_TLB) || (bond->params.mode == BOND_MODE_ALB)) { /* must be called only after the slave * has been detached from the list */ bond_alb_deinit_slave(bond, slave); } bond_compute_features(bond); /* now that the slave is detached, unlock and perform * all the undo steps that should not be called from * within a lock. */ write_unlock_bh(&bond->lock); bond_destroy_slave_symlinks(bond_dev, slave_dev); bond_del_vlans_from_slave(bond, slave_dev); /* If the mode USES_PRIMARY, then we should only remove its * promisc and mc settings if it was the curr_active_slave, but that was * already taken care of above when we detached the slave */ if (!USES_PRIMARY(bond->params.mode)) { /* unset promiscuity level from slave */ if (bond_dev->flags & IFF_PROMISC) { dev_set_promiscuity(slave_dev, -1); } /* unset allmulti level from slave */ if (bond_dev->flags & IFF_ALLMULTI) { dev_set_allmulti(slave_dev, -1); } /* flush master's mc_list from slave */ bond_mc_list_flush(bond_dev, slave_dev); } netdev_set_master(slave_dev, NULL); /* close slave before restoring its mac address */ dev_close(slave_dev); /* restore original ("permanent") mac address*/ memcpy(addr.sa_data, slave->perm_hwaddr, ETH_ALEN); addr.sa_family = slave_dev->type; dev_set_mac_address(slave_dev, &addr); slave_dev->priv_flags &= ~(IFF_MASTER_8023AD | IFF_MASTER_ALB | IFF_SLAVE_INACTIVE); kfree(slave); /* re-acquire the lock before getting the next slave */ write_lock_bh(&bond->lock); } /* zero the mac address of the master so it will be * set by the application to the mac address of the * first slave */ memset(bond_dev->dev_addr, 0, bond_dev->addr_len); if (list_empty(&bond->vlan_list)) { bond_dev->features |= NETIF_F_VLAN_CHALLENGED; } else { printk(KERN_WARNING DRV_NAME ": %s: Warning: clearing HW address of %s while it " "still has VLANs.\n", bond_dev->name, bond_dev->name); printk(KERN_WARNING DRV_NAME ": %s: When re-adding slaves, make sure the bond's " "HW address matches its VLANs'.\n", bond_dev->name); } printk(KERN_INFO DRV_NAME ": %s: released all slaves\n", bond_dev->name); out: write_unlock_bh(&bond->lock); return 0; } /* * This function changes the active slave to slave . * It returns -EINVAL in the following cases. * - is not found in the list. * - There is not active slave now. * - is already active. * - The link state of is not BOND_LINK_UP. * - is not running. * In these cases, this fuction does nothing. * In the other cases, currnt_slave pointer is changed and 0 is returned. */ static int bond_ioctl_change_active(struct net_device *bond_dev, struct net_device *slave_dev) { struct bonding *bond = bond_dev->priv; struct slave *old_active = NULL; struct slave *new_active = NULL; int res = 0; if (!USES_PRIMARY(bond->params.mode)) { return -EINVAL; } /* Verify that master_dev is indeed the master of slave_dev */ if (!(slave_dev->flags & IFF_SLAVE) || (slave_dev->master != bond_dev)) { return -EINVAL; } write_lock_bh(&bond->lock); old_active = bond->curr_active_slave; new_active = bond_get_slave_by_dev(bond, slave_dev); /* * Changing to the current active: do nothing; return success. */ if (new_active && (new_active == old_active)) { write_unlock_bh(&bond->lock); return 0; } if ((new_active) && (old_active) && (new_active->link == BOND_LINK_UP) && IS_UP(new_active->dev)) { bond_change_active_slave(bond, new_active); } else { res = -EINVAL; } write_unlock_bh(&bond->lock); return res; } static int bond_info_query(struct net_device *bond_dev, struct ifbond *info) { struct bonding *bond = bond_dev->priv; info->bond_mode = bond->params.mode; info->miimon = bond->params.miimon; read_lock_bh(&bond->lock); info->num_slaves = bond->slave_cnt; read_unlock_bh(&bond->lock); return 0; } static int bond_slave_info_query(struct net_device *bond_dev, struct ifslave *info) { struct bonding *bond = bond_dev->priv; struct slave *slave; int i, found = 0; if (info->slave_id < 0) { return -ENODEV; } read_lock_bh(&bond->lock); bond_for_each_slave(bond, slave, i) { if (i == (int)info->slave_id) { found = 1; break; } } read_unlock_bh(&bond->lock); if (found) { strcpy(info->slave_name, slave->dev->name); info->link = slave->link; info->state = slave->state; info->link_failure_count = slave->link_failure_count; } else { return -ENODEV; } return 0; } /*-------------------------------- Monitoring -------------------------------*/ /* this function is called regularly to monitor each slave's link. */ void bond_mii_monitor(struct net_device *bond_dev) { struct bonding *bond = bond_dev->priv; struct slave *slave, *oldcurrent; int do_failover = 0; int delta_in_ticks; int i; read_lock(&bond->lock); delta_in_ticks = (bond->params.miimon * HZ) / 1000; if (bond->kill_timers) { goto out; } if (bond->slave_cnt == 0) { goto re_arm; } /* we will try to read the link status of each of our slaves, and * set their IFF_RUNNING flag appropriately. For each slave not * supporting MII status, we won't do anything so that a user-space * program could monitor the link itself if needed. */ read_lock(&bond->curr_slave_lock); oldcurrent = bond->curr_active_slave; read_unlock(&bond->curr_slave_lock); bond_for_each_slave(bond, slave, i) { struct net_device *slave_dev = slave->dev; int link_state; u16 old_speed = slave->speed; u8 old_duplex = slave->duplex; link_state = bond_check_dev_link(bond, slave_dev, 0); switch (slave->link) { case BOND_LINK_UP: /* the link was up */ if (link_state == BMSR_LSTATUS) { /* link stays up, nothing more to do */ break; } else { /* link going down */ slave->link = BOND_LINK_FAIL; slave->delay = bond->params.downdelay; if (slave->link_failure_count < UINT_MAX) { slave->link_failure_count++; } if (bond->params.downdelay) { printk(KERN_INFO DRV_NAME ": %s: link status down for %s " "interface %s, disabling it in " "%d ms.\n", bond_dev->name, IS_UP(slave_dev) ? ((bond->params.mode == BOND_MODE_ACTIVEBACKUP) ? ((slave == oldcurrent) ? "active " : "backup ") : "") : "idle ", slave_dev->name, bond->params.downdelay * bond->params.miimon); } } /* no break ! fall through the BOND_LINK_FAIL test to ensure proper action to be taken */ case BOND_LINK_FAIL: /* the link has just gone down */ if (link_state != BMSR_LSTATUS) { /* link stays down */ if (slave->delay <= 0) { /* link down for too long time */ slave->link = BOND_LINK_DOWN; /* in active/backup mode, we must * completely disable this interface */ if ((bond->params.mode == BOND_MODE_ACTIVEBACKUP) || (bond->params.mode == BOND_MODE_8023AD)) { bond_set_slave_inactive_flags(slave); } printk(KERN_INFO DRV_NAME ": %s: link status definitely " "down for interface %s, " "disabling it\n", bond_dev->name, slave_dev->name); /* notify ad that the link status has changed */ if (bond->params.mode == BOND_MODE_8023AD) { bond_3ad_handle_link_change(slave, BOND_LINK_DOWN); } if ((bond->params.mode == BOND_MODE_TLB) || (bond->params.mode == BOND_MODE_ALB)) { bond_alb_handle_link_change(bond, slave, BOND_LINK_DOWN); } if (slave == oldcurrent) { do_failover = 1; } } else { slave->delay--; } } else { /* link up again */ slave->link = BOND_LINK_UP; slave->jiffies = jiffies; printk(KERN_INFO DRV_NAME ": %s: link status up again after %d " "ms for interface %s.\n", bond_dev->name, (bond->params.downdelay - slave->delay) * bond->params.miimon, slave_dev->name); } break; case BOND_LINK_DOWN: /* the link was down */ if (link_state != BMSR_LSTATUS) { /* the link stays down, nothing more to do */ break; } else { /* link going up */ slave->link = BOND_LINK_BACK; slave->delay = bond->params.updelay; if (bond->params.updelay) { /* if updelay == 0, no need to advertise about a 0 ms delay */ printk(KERN_INFO DRV_NAME ": %s: link status up for " "interface %s, enabling it " "in %d ms.\n", bond_dev->name, slave_dev->name, bond->params.updelay * bond->params.miimon); } } /* no break ! fall through the BOND_LINK_BACK state in case there's something to do. */ case BOND_LINK_BACK: /* the link has just come back */ if (link_state != BMSR_LSTATUS) { /* link down again */ slave->link = BOND_LINK_DOWN; printk(KERN_INFO DRV_NAME ": %s: link status down again after %d " "ms for interface %s.\n", bond_dev->name, (bond->params.updelay - slave->delay) * bond->params.miimon, slave_dev->name); } else { /* link stays up */ if (slave->delay == 0) { /* now the link has been up for long time enough */ slave->link = BOND_LINK_UP; slave->jiffies = jiffies; if (bond->params.mode == BOND_MODE_8023AD) { /* prevent it from being the active one */ slave->state = BOND_STATE_BACKUP; } else if (bond->params.mode != BOND_MODE_ACTIVEBACKUP) { /* make it immediately active */ slave->state = BOND_STATE_ACTIVE; } else if (slave != bond->primary_slave) { /* prevent it from being the active one */ slave->state = BOND_STATE_BACKUP; } printk(KERN_INFO DRV_NAME ": %s: link status definitely " "up for interface %s.\n", bond_dev->name, slave_dev->name); /* notify ad that the link status has changed */ if (bond->params.mode == BOND_MODE_8023AD) { bond_3ad_handle_link_change(slave, BOND_LINK_UP); } if ((bond->params.mode == BOND_MODE_TLB) || (bond->params.mode == BOND_MODE_ALB)) { bond_alb_handle_link_change(bond, slave, BOND_LINK_UP); } if ((!oldcurrent) || (slave == bond->primary_slave)) { do_failover = 1; } } else { slave->delay--; } } break; default: /* Should not happen */ printk(KERN_ERR DRV_NAME ": %s: Error: %s Illegal value (link=%d)\n", bond_dev->name, slave->dev->name, slave->link); goto out; } /* end of switch (slave->link) */ bond_update_speed_duplex(slave); if (bond->params.mode == BOND_MODE_8023AD) { if (old_speed != slave->speed) { bond_3ad_adapter_speed_changed(slave); } if (old_duplex != slave->duplex) { bond_3ad_adapter_duplex_changed(slave); } } } /* end of for */ if (do_failover) { write_lock(&bond->curr_slave_lock); bond_select_active_slave(bond); write_unlock(&bond->curr_slave_lock); } else bond_set_carrier(bond); re_arm: if (bond->params.miimon) { mod_timer(&bond->mii_timer, jiffies + delta_in_ticks); } out: read_unlock(&bond->lock); } static u32 bond_glean_dev_ip(struct net_device *dev) { struct in_device *idev; struct in_ifaddr *ifa; u32 addr = 0; if (!dev) return 0; rcu_read_lock(); idev = __in_dev_get_rcu(dev); if (!idev) goto out; ifa = idev->ifa_list; if (!ifa) goto out; addr = ifa->ifa_local; out: rcu_read_unlock(); return addr; } static int bond_has_ip(struct bonding *bond) { struct vlan_entry *vlan, *vlan_next; if (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 (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 * "native" to a VLAN) might not pass non-tagged frames. */ static void bond_arp_send(struct net_device *slave_dev, int arp_op, u32 dest_ip, u32 src_ip, unsigned short vlan_id) { struct sk_buff *skb; dprintk("arp %d on slave %s: dst %x src %x vid %d\n", arp_op, slave_dev->name, dest_ip, src_ip, vlan_id); skb = arp_create(arp_op, ETH_P_ARP, dest_ip, slave_dev, src_ip, NULL, slave_dev->dev_addr, NULL); if (!skb) { printk(KERN_ERR DRV_NAME ": ARP packet allocation failed\n"); return; } if (vlan_id) { skb = vlan_put_tag(skb, vlan_id); if (!skb) { printk(KERN_ERR DRV_NAME ": failed to insert VLAN tag\n"); return; } } arp_xmit(skb); } static void bond_arp_send_all(struct bonding *bond, struct slave *slave) { int i, vlan_id, rv; u32 *targets = bond->params.arp_targets; struct vlan_entry *vlan, *vlan_next; struct net_device *vlan_dev; struct flowi fl; struct rtable *rt; for (i = 0; (i < BOND_MAX_ARP_TARGETS); i++) { if (!targets[i]) continue; dprintk("basa: target %x\n", targets[i]); if (list_empty(&bond->vlan_list)) { dprintk("basa: empty vlan: arp_send\n"); bond_arp_send(slave->dev, ARPOP_REQUEST, targets[i], bond->master_ip, 0); continue; } /* * If VLANs are configured, we do a route lookup to * determine which VLAN interface would be used, so we * can tag the ARP with the proper VLAN tag. */ memset(&fl, 0, sizeof(fl)); fl.fl4_dst = targets[i]; fl.fl4_tos = RTO_ONLINK; rv = ip_route_output_key(&rt, &fl); if (rv) { if (net_ratelimit()) { printk(KERN_WARNING DRV_NAME ": %s: no route to arp_ip_target %u.%u.%u.%u\n", bond->dev->name, NIPQUAD(fl.fl4_dst)); } continue; } /* * This target is not on a VLAN */ if (rt->u.dst.dev == bond->dev) { ip_rt_put(rt); dprintk("basa: rtdev == bond->dev: arp_send\n"); bond_arp_send(slave->dev, ARPOP_REQUEST, targets[i], bond->master_ip, 0); continue; } vlan_id = 0; list_for_each_entry_safe(vlan, vlan_next, &bond->vlan_list, vlan_list) { vlan_dev = bond->vlgrp->vlan_devices[vlan->vlan_id]; if (vlan_dev == rt->u.dst.dev) { vlan_id = vlan->vlan_id; dprintk("basa: vlan match on %s %d\n", vlan_dev->name, vlan_id); break; } } if (vlan