X-Git-Url: http://ftp.safe.ca/?a=blobdiff_plain;f=drivers%2Fnet%2Fbonding%2Fbond_main.c;h=aa1be1feceedad372f01d082904b66470f55273e;hb=e36b9d16c6a6d0f59803b3ef04ff3c22c3844c10;hp=0942d82f7cbf721f62c364941a13b31373668c5b;hpb=21c9d8d73dd1a152c49b4e3176193a099849d4c9;p=safe%2Fjmp%2Flinux-2.6 diff --git a/drivers/net/bonding/bond_main.c b/drivers/net/bonding/bond_main.c index 0942d82..aa1be1f 100644 --- a/drivers/net/bonding/bond_main.c +++ b/drivers/net/bonding/bond_main.c @@ -31,8 +31,6 @@ * */ -//#define BONDING_DEBUG 1 - #include #include #include @@ -53,10 +51,10 @@ #include #include #include +#include #include -#include #include -#include +#include #include #include #include @@ -88,22 +86,29 @@ #define BOND_LINK_ARP_INTERV 0 static int max_bonds = BOND_DEFAULT_MAX_BONDS; +static int num_grat_arp = 1; +static int num_unsol_na = 1; static int miimon = BOND_LINK_MON_INTERV; -static int updelay = 0; -static int downdelay = 0; +static int updelay; +static int downdelay; 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 char *mode; +static char *primary; +static char *lacp_rate; +static char *ad_select; +static char *xmit_hash_policy; static int arp_interval = BOND_LINK_ARP_INTERV; -static char *arp_ip_target[BOND_MAX_ARP_TARGETS] = { NULL, }; -static char *arp_validate = NULL; -static int fail_over_mac = 0; -struct bond_params bonding_defaults; +static char *arp_ip_target[BOND_MAX_ARP_TARGETS]; +static char *arp_validate; +static char *fail_over_mac; +static struct bond_params bonding_defaults; module_param(max_bonds, int, 0); MODULE_PARM_DESC(max_bonds, "Max number of bonded devices"); +module_param(num_grat_arp, int, 0644); +MODULE_PARM_DESC(num_grat_arp, "Number of gratuitous ARP packets to send on failover event"); +module_param(num_unsol_na, int, 0644); +MODULE_PARM_DESC(num_unsol_na, "Number of unsolicited IPv6 Neighbor Advertisements packets to send on failover event"); module_param(miimon, int, 0); MODULE_PARM_DESC(miimon, "Link check interval in milliseconds"); module_param(updelay, int, 0); @@ -124,6 +129,8 @@ 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(ad_select, charp, 0); +MODULE_PARM_DESC(ad_select, "803.ad aggregation selection logic: stable (0, default), bandwidth (1), count (2)"); 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"); @@ -133,8 +140,8 @@ 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"); -module_param(fail_over_mac, int, 0); -MODULE_PARM_DESC(fail_over_mac, "For active-backup, do not set all slaves to the same MAC. 0 of off (default), 1 for on."); +module_param(fail_over_mac, charp, 0); +MODULE_PARM_DESC(fail_over_mac, "For active-backup, do not set all slaves to the same MAC. none (default), active or follow"); /*----------------------------- Global variables ----------------------------*/ @@ -144,24 +151,23 @@ static const char * const version = LIST_HEAD(bond_dev_list); #ifdef CONFIG_PROC_FS -static struct proc_dir_entry *bond_proc_dir = NULL; +static struct proc_dir_entry *bond_proc_dir; #endif -extern struct rw_semaphore bonding_rwsem; -static __be32 arp_target[BOND_MAX_ARP_TARGETS] = { 0, } ; -static int arp_ip_count = 0; +static __be32 arp_target[BOND_MAX_ARP_TARGETS]; +static int arp_ip_count; static int bond_mode = BOND_MODE_ROUNDROBIN; -static int xmit_hashtype= BOND_XMIT_POLICY_LAYER2; -static int lacp_fast = 0; +static int xmit_hashtype = BOND_XMIT_POLICY_LAYER2; +static int lacp_fast; -struct bond_parm_tbl bond_lacp_tbl[] = { +const struct bond_parm_tbl bond_lacp_tbl[] = { { "slow", AD_LACP_SLOW}, { "fast", AD_LACP_FAST}, { NULL, -1}, }; -struct bond_parm_tbl bond_mode_tbl[] = { +const struct bond_parm_tbl bond_mode_tbl[] = { { "balance-rr", BOND_MODE_ROUNDROBIN}, { "active-backup", BOND_MODE_ACTIVEBACKUP}, { "balance-xor", BOND_MODE_XOR}, @@ -172,14 +178,14 @@ struct bond_parm_tbl bond_mode_tbl[] = { { NULL, -1}, }; -struct bond_parm_tbl xmit_hashtype_tbl[] = { +const struct bond_parm_tbl xmit_hashtype_tbl[] = { { "layer2", BOND_XMIT_POLICY_LAYER2}, { "layer3+4", BOND_XMIT_POLICY_LAYER34}, { "layer2+3", BOND_XMIT_POLICY_LAYER23}, { NULL, -1}, }; -struct bond_parm_tbl arp_validate_tbl[] = { +const struct bond_parm_tbl arp_validate_tbl[] = { { "none", BOND_ARP_VALIDATE_NONE}, { "active", BOND_ARP_VALIDATE_ACTIVE}, { "backup", BOND_ARP_VALIDATE_BACKUP}, @@ -187,33 +193,44 @@ struct bond_parm_tbl arp_validate_tbl[] = { { NULL, -1}, }; +const struct bond_parm_tbl fail_over_mac_tbl[] = { +{ "none", BOND_FOM_NONE}, +{ "active", BOND_FOM_ACTIVE}, +{ "follow", BOND_FOM_FOLLOW}, +{ NULL, -1}, +}; + +struct bond_parm_tbl ad_select_tbl[] = { +{ "stable", BOND_AD_STABLE}, +{ "bandwidth", BOND_AD_BANDWIDTH}, +{ "count", BOND_AD_COUNT}, +{ NULL, -1}, +}; + /*-------------------------- Forward declarations ---------------------------*/ 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); /*---------------------------- General routines -----------------------------*/ static 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: + static const char *names[] = { + [BOND_MODE_ROUNDROBIN] = "load balancing (round-robin)", + [BOND_MODE_ACTIVEBACKUP] = "fault-tolerance (active-backup)", + [BOND_MODE_XOR] = "load balancing (xor)", + [BOND_MODE_BROADCAST] = "fault-tolerance (broadcast)", + [BOND_MODE_8023AD] = "IEEE 802.3ad Dynamic link aggregation", + [BOND_MODE_TLB] = "transmit load balancing", + [BOND_MODE_ALB] = "adaptive load balancing", + }; + + if (mode < 0 || mode > BOND_MODE_ALB) return "unknown"; - } + + return names[mode]; } /*---------------------------------- VLAN -----------------------------------*/ @@ -229,17 +246,15 @@ 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); + pr_debug("bond: %s, vlan id %d\n", + (bond ? bond->dev->name : "None"), vlan_id); - vlan = kmalloc(sizeof(struct vlan_entry), GFP_KERNEL); - if (!vlan) { + vlan = kzalloc(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); @@ -247,7 +262,7 @@ static int bond_add_vlan(struct bonding *bond, unsigned short vlan_id) write_unlock_bh(&bond->lock); - dprintk("added VLAN ID %d on bond %s\n", vlan_id, bond->dev->name); + pr_debug("added VLAN ID %d on bond %s\n", vlan_id, bond->dev->name); return 0; } @@ -261,23 +276,21 @@ static int bond_add_vlan(struct bonding *bond, unsigned short vlan_id) */ static int bond_del_vlan(struct bonding *bond, unsigned short vlan_id) { - struct vlan_entry *vlan, *next; + struct vlan_entry *vlan; int res = -ENODEV; - dprintk("bond: %s, vlan id %d\n", bond->dev->name, vlan_id); + pr_debug("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) { + list_for_each_entry(vlan, &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)) { + if (bond_is_lb(bond)) bond_alb_clear_vlan(bond, vlan_id); - } - dprintk("removed VLAN ID %d from bond %s\n", vlan_id, + pr_debug("removed VLAN ID %d from bond %s\n", vlan_id, bond->dev->name); kfree(vlan); @@ -297,7 +310,7 @@ static int bond_del_vlan(struct bonding *bond, unsigned short vlan_id) } } - dprintk("couldn't find VLAN ID %d in bond %s\n", vlan_id, + pr_debug("couldn't find VLAN ID %d in bond %s\n", vlan_id, bond->dev->name); out: @@ -321,13 +334,13 @@ static int bond_has_challenged_slaves(struct bonding *bond) bond_for_each_slave(bond, slave, i) { if (slave->dev->features & NETIF_F_VLAN_CHALLENGED) { - dprintk("found VLAN challenged slave - %s\n", + pr_debug("found VLAN challenged slave - %s\n", slave->dev->name); return 1; } } - dprintk("no VLAN challenged slaves found\n"); + pr_debug("no VLAN challenged slaves found\n"); return 0; } @@ -338,16 +351,15 @@ static int bond_has_challenged_slaves(struct bonding *bond) * * 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)) { + if (list_empty(&bond->vlan_list)) return NULL; - } if (!curr) { next = list_entry(bond->vlan_list.next, @@ -369,11 +381,11 @@ struct vlan_entry *bond_next_vlan(struct bonding *bond, struct vlan_entry *curr) /** * 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 @@ -381,9 +393,10 @@ struct vlan_entry *bond_next_vlan(struct bonding *bond, struct vlan_entry *curr) * 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) +int bond_dev_queue_xmit(struct bonding *bond, struct sk_buff *skb, + struct net_device *slave_dev) { - unsigned short vlan_id; + unsigned short uninitialized_var(vlan_id); if (!list_empty(&bond->vlan_list) && !(slave_dev->features & NETIF_F_HW_VLAN_TX) && @@ -415,7 +428,7 @@ int bond_dev_queue_xmit(struct bonding *bond, struct sk_buff *skb, struct net_de * 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 @@ -430,9 +443,10 @@ int bond_dev_queue_xmit(struct bonding *bond, struct sk_buff *skb, struct net_de * @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) +static void bond_vlan_rx_register(struct net_device *bond_dev, + struct vlan_group *grp) { - struct bonding *bond = bond_dev->priv; + struct bonding *bond = netdev_priv(bond_dev); struct slave *slave; int i; @@ -440,10 +454,11 @@ static void bond_vlan_rx_register(struct net_device *bond_dev, struct vlan_group bond_for_each_slave(bond, slave, i) { struct net_device *slave_dev = slave->dev; + const struct net_device_ops *slave_ops = slave_dev->netdev_ops; if ((slave_dev->features & NETIF_F_HW_VLAN_RX) && - slave_dev->vlan_rx_register) { - slave_dev->vlan_rx_register(slave_dev, grp); + slave_ops->ndo_vlan_rx_register) { + slave_ops->ndo_vlan_rx_register(slave_dev, grp); } } } @@ -455,22 +470,23 @@ static void bond_vlan_rx_register(struct net_device *bond_dev, struct vlan_group */ static void bond_vlan_rx_add_vid(struct net_device *bond_dev, uint16_t vid) { - struct bonding *bond = bond_dev->priv; + struct bonding *bond = netdev_priv(bond_dev); struct slave *slave; int i, res; bond_for_each_slave(bond, slave, i) { struct net_device *slave_dev = slave->dev; + const struct net_device_ops *slave_ops = slave_dev->netdev_ops; if ((slave_dev->features & NETIF_F_HW_VLAN_FILTER) && - slave_dev->vlan_rx_add_vid) { - slave_dev->vlan_rx_add_vid(slave_dev, vid); + slave_ops->ndo_vlan_rx_add_vid) { + slave_ops->ndo_vlan_rx_add_vid(slave_dev, vid); } } res = bond_add_vlan(bond, vid); if (res) { - printk(KERN_ERR DRV_NAME + pr_err(DRV_NAME ": %s: Error: Failed to add vlan id %d\n", bond_dev->name, vid); } @@ -483,28 +499,29 @@ static void bond_vlan_rx_add_vid(struct net_device *bond_dev, uint16_t vid) */ static void bond_vlan_rx_kill_vid(struct net_device *bond_dev, uint16_t vid) { - struct bonding *bond = bond_dev->priv; + struct bonding *bond = netdev_priv(bond_dev); 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; + const struct net_device_ops *slave_ops = slave_dev->netdev_ops; if ((slave_dev->features & NETIF_F_HW_VLAN_FILTER) && - slave_dev->vlan_rx_kill_vid) { + slave_ops->ndo_vlan_rx_kill_vid) { /* Save and then restore vlan_dev in the grp array, * since the slave's driver might clear it. */ vlan_dev = vlan_group_get_device(bond->vlgrp, vid); - slave_dev->vlan_rx_kill_vid(slave_dev, vid); + slave_ops->ndo_vlan_rx_kill_vid(slave_dev, vid); vlan_group_set_device(bond->vlgrp, vid, vlan_dev); } } res = bond_del_vlan(bond, vid); if (res) { - printk(KERN_ERR DRV_NAME + pr_err(DRV_NAME ": %s: Error: Failed to remove vlan id %d\n", bond_dev->name, vid); } @@ -513,61 +530,57 @@ static void bond_vlan_rx_kill_vid(struct net_device *bond_dev, uint16_t vid) static void bond_add_vlans_on_slave(struct bonding *bond, struct net_device *slave_dev) { struct vlan_entry *vlan; + const struct net_device_ops *slave_ops = slave_dev->netdev_ops; write_lock_bh(&bond->lock); - if (list_empty(&bond->vlan_list)) { + 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); - } + slave_ops->ndo_vlan_rx_register) + slave_ops->ndo_vlan_rx_register(slave_dev, bond->vlgrp); if (!(slave_dev->features & NETIF_F_HW_VLAN_FILTER) || - !(slave_dev->vlan_rx_add_vid)) { + !(slave_ops->ndo_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); - } + list_for_each_entry(vlan, &bond->vlan_list, vlan_list) + slave_ops->ndo_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) +static void bond_del_vlans_from_slave(struct bonding *bond, + struct net_device *slave_dev) { + const struct net_device_ops *slave_ops = slave_dev->netdev_ops; struct vlan_entry *vlan; struct net_device *vlan_dev; write_lock_bh(&bond->lock); - if (list_empty(&bond->vlan_list)) { + if (list_empty(&bond->vlan_list)) goto out; - } if (!(slave_dev->features & NETIF_F_HW_VLAN_FILTER) || - !(slave_dev->vlan_rx_kill_vid)) { + !(slave_ops->ndo_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 = vlan_group_get_device(bond->vlgrp, vlan->vlan_id); - slave_dev->vlan_rx_kill_vid(slave_dev, vlan->vlan_id); + slave_ops->ndo_vlan_rx_kill_vid(slave_dev, vlan->vlan_id); vlan_group_set_device(bond->vlgrp, 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); - } + slave_ops->ndo_vlan_rx_register) + slave_ops->ndo_vlan_rx_register(slave_dev, NULL); out: write_unlock_bh(&bond->lock); @@ -662,7 +675,7 @@ static int bond_update_speed_duplex(struct slave *slave) * 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. + * depending 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 @@ -674,17 +687,30 @@ static int bond_update_speed_duplex(struct slave *slave) * 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 bond_check_dev_link(struct bonding *bond, + struct net_device *slave_dev, int reporting) { - static int (* ioctl)(struct net_device *, struct ifreq *, int); + const struct net_device_ops *slave_ops = slave_dev->netdev_ops; + static int (*ioctl)(struct net_device *, struct ifreq *, int); struct ifreq ifr; struct mii_ioctl_data *mii; - if (bond->params.use_carrier) { + if (bond->params.use_carrier) return netif_carrier_ok(slave_dev) ? BMSR_LSTATUS : 0; + + /* Try to get link status using Ethtool first. */ + 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; + } } - ioctl = slave_dev->do_ioctl; + /* Ethtool can't be used, fallback to MII ioctls. */ + ioctl = slave_ops->ndo_do_ioctl; if (ioctl) { /* TODO: set pointer to correct ioctl on a per team member */ /* bases to make this more efficient. that is, once */ @@ -703,23 +729,8 @@ static int bond_check_dev_link(struct bonding *bond, struct net_device *slave_de 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); - } - } - } - - /* - * Some drivers cache ETHTOOL_GLINK for a period of time so we only - * attempt to get link status from it 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(slave_dev, &ifr, SIOCGMIIREG) == 0) + return mii->val_out & BMSR_LSTATUS; } } @@ -729,7 +740,7 @@ static int bond_check_dev_link(struct bonding *bond, struct net_device *slave_de * cannot report link status). If not reporting, pretend * we're ok. */ - return (reporting ? -1 : BMSR_LSTATUS); + return reporting ? -1 : BMSR_LSTATUS; } /*----------------------------- Multicast list ------------------------------*/ @@ -737,7 +748,8 @@ static int bond_check_dev_link(struct bonding *bond, struct net_device *slave_de /* * 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) +static inline int bond_is_dmi_same(const struct dev_mc_list *dmi1, + const struct dev_mc_list *dmi2) { return memcmp(dmi1->dmi_addr, dmi2->dmi_addr, dmi1->dmi_addrlen) == 0 && dmi1->dmi_addrlen == dmi2->dmi_addrlen; @@ -746,14 +758,14 @@ static inline int bond_is_dmi_same(struct dev_mc_list *dmi1, struct dev_mc_list /* * 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) +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)) { + if (bond_is_dmi_same(dmi, idmi)) return idmi; - } } return NULL; @@ -762,39 +774,49 @@ static struct dev_mc_list *bond_mc_list_find_dmi(struct dev_mc_list *dmi, struct /* * Push the promiscuity flag down to appropriate slaves */ -static void bond_set_promiscuity(struct bonding *bond, int inc) +static int bond_set_promiscuity(struct bonding *bond, int inc) { + int err = 0; if (USES_PRIMARY(bond->params.mode)) { /* write lock already acquired */ if (bond->curr_active_slave) { - dev_set_promiscuity(bond->curr_active_slave->dev, inc); + err = 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); + err = dev_set_promiscuity(slave->dev, inc); + if (err) + return err; } } + return err; } /* * Push the allmulti flag down to all slaves */ -static void bond_set_allmulti(struct bonding *bond, int inc) +static int bond_set_allmulti(struct bonding *bond, int inc) { + int err = 0; if (USES_PRIMARY(bond->params.mode)) { /* write lock already acquired */ if (bond->curr_active_slave) { - dev_set_allmulti(bond->curr_active_slave->dev, inc); + err = 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); + err = dev_set_allmulti(slave->dev, inc); + if (err) + return err; } } + return err; } /* @@ -805,15 +827,14 @@ 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) { + 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) { + + bond_for_each_slave(bond, slave, i) dev_mc_add(slave->dev, addr, alen, 0); - } } } @@ -825,9 +846,9 @@ 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); - } + if (bond->curr_active_slave) + dev_mc_delete(bond->curr_active_slave->dev, addr, + alen, 0); } else { struct slave *slave; int i; @@ -851,9 +872,8 @@ static void bond_resend_igmp_join_requests(struct bonding *bond) rcu_read_lock(); in_dev = __in_dev_get_rcu(bond->dev); if (in_dev) { - for (im = in_dev->mc_list; im; im = im->next) { + for (im = in_dev->mc_list; im; im = im->next) ip_mc_rejoin_group(im); - } } rcu_read_unlock(); @@ -872,7 +892,8 @@ static void bond_mc_list_destroy(struct bonding *bond) kfree(dmi); dmi = bond->mc_list; } - bond->mc_list = NULL; + + bond->mc_list = NULL; } /* @@ -905,14 +926,14 @@ static int bond_mc_list_copy(struct dev_mc_list *mc_list, struct bonding *bond, /* * 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) +static void bond_mc_list_flush(struct net_device *bond_dev, + struct net_device *slave_dev) { - struct bonding *bond = bond_dev->priv; + struct bonding *bond = netdev_priv(bond_dev); struct dev_mc_list *dmi; - for (dmi = bond_dev->mc_list; dmi; dmi = dmi->next) { + 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 */ @@ -929,47 +950,124 @@ static void bond_mc_list_flush(struct net_device *bond_dev, struct net_device *s * 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) +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)) { + 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) { + if (bond->dev->flags & IFF_PROMISC) dev_set_promiscuity(old_active->dev, -1); - } - if (bond->dev->flags & IFF_ALLMULTI) { + 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); - } + 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) { + /* FIXME: Signal errors upstream. */ + if (bond->dev->flags & IFF_PROMISC) dev_set_promiscuity(new_active->dev, 1); - } - if (bond->dev->flags & IFF_ALLMULTI) { + 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); + bond_resend_igmp_join_requests(bond); + } +} + +/* + * bond_do_fail_over_mac + * + * Perform special MAC address swapping for fail_over_mac settings + * + * Called with RTNL, bond->lock for read, curr_slave_lock for write_bh. + */ +static void bond_do_fail_over_mac(struct bonding *bond, + struct slave *new_active, + struct slave *old_active) + __releases(&bond->curr_slave_lock) + __releases(&bond->lock) + __acquires(&bond->lock) + __acquires(&bond->curr_slave_lock) +{ + u8 tmp_mac[ETH_ALEN]; + struct sockaddr saddr; + int rv; + + switch (bond->params.fail_over_mac) { + case BOND_FOM_ACTIVE: + if (new_active) + memcpy(bond->dev->dev_addr, new_active->dev->dev_addr, + new_active->dev->addr_len); + break; + case BOND_FOM_FOLLOW: + /* + * if new_active && old_active, swap them + * if just old_active, do nothing (going to no active slave) + * if just new_active, set new_active to bond's MAC + */ + if (!new_active) + return; + + write_unlock_bh(&bond->curr_slave_lock); + read_unlock(&bond->lock); + + if (old_active) { + memcpy(tmp_mac, new_active->dev->dev_addr, ETH_ALEN); + memcpy(saddr.sa_data, old_active->dev->dev_addr, + ETH_ALEN); + saddr.sa_family = new_active->dev->type; + } else { + memcpy(saddr.sa_data, bond->dev->dev_addr, ETH_ALEN); + saddr.sa_family = bond->dev->type; } - for (dmi = bond->dev->mc_list; dmi; dmi = dmi->next) { - dev_mc_add(new_active->dev, dmi->dmi_addr, dmi->dmi_addrlen, 0); + rv = dev_set_mac_address(new_active->dev, &saddr); + if (rv) { + pr_err(DRV_NAME + ": %s: Error %d setting MAC of slave %s\n", + bond->dev->name, -rv, new_active->dev->name); + goto out; } - bond_resend_igmp_join_requests(bond); + + if (!old_active) + goto out; + + memcpy(saddr.sa_data, tmp_mac, ETH_ALEN); + saddr.sa_family = old_active->dev->type; + + rv = dev_set_mac_address(old_active->dev, &saddr); + if (rv) + pr_err(DRV_NAME + ": %s: Error %d setting MAC of slave %s\n", + bond->dev->name, -rv, new_active->dev->name); +out: + read_lock(&bond->lock); + write_lock_bh(&bond->curr_slave_lock); + break; + default: + pr_err(DRV_NAME + ": %s: bond_do_fail_over_mac impossible: bad policy %d\n", + bond->dev->name, bond->params.fail_over_mac); + break; } + } + /** * find_best_interface - select the best available slave to be the active one * @bond: our bonding struct @@ -986,17 +1084,17 @@ static struct slave *bond_find_best_slave(struct bonding *bond) 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 */ + if (bond->slave_cnt > 0) /* found one slave */ new_active = bond->first_slave; - } else { + 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 + /* + * 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) && @@ -1037,20 +1135,22 @@ static struct slave *bond_find_best_slave(struct bonding *bond) * 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. + * If new_active is not NULL, caller must hold bond->lock for read and + * curr_slave_lock for write_bh. */ 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) { + if (old_active == new_active) return; - } if (new_active) { + new_active->jiffies = jiffies; + if (new_active->link == BOND_LINK_BACK) { if (USES_PRIMARY(bond->params.mode)) { - printk(KERN_INFO DRV_NAME + pr_info(DRV_NAME ": %s: making interface %s the new " "active one %d ms earlier.\n", bond->dev->name, new_active->dev->name, @@ -1059,19 +1159,15 @@ void bond_change_active_slave(struct bonding *bond, struct slave *new_active) new_active->delay = 0; new_active->link = BOND_LINK_UP; - new_active->jiffies = jiffies; - if (bond->params.mode == BOND_MODE_8023AD) { + 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)) { + if (bond_is_lb(bond)) bond_alb_handle_link_change(bond, new_active, BOND_LINK_UP); - } } else { if (USES_PRIMARY(bond->params.mode)) { - printk(KERN_INFO DRV_NAME + pr_info(DRV_NAME ": %s: making interface %s the new " "active one.\n", bond->dev->name, new_active->dev->name); @@ -1079,12 +1175,10 @@ void bond_change_active_slave(struct bonding *bond, struct slave *new_active) } } - if (USES_PRIMARY(bond->params.mode)) { + 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)) { + if (bond_is_lb(bond)) { bond_alb_handle_active_change(bond, new_active); if (old_active) bond_set_slave_inactive_flags(old_active); @@ -1095,28 +1189,30 @@ void bond_change_active_slave(struct bonding *bond, struct slave *new_active) } if (bond->params.mode == BOND_MODE_ACTIVEBACKUP) { - if (old_active) { + if (old_active) bond_set_slave_inactive_flags(old_active); - } if (new_active) { bond_set_slave_active_flags(new_active); - } - /* when bonding does not set the slave MAC address, the bond MAC - * address is the one of the active slave. - */ - if (new_active && bond->params.fail_over_mac) - memcpy(bond->dev->dev_addr, new_active->dev->dev_addr, - new_active->dev->addr_len); - if (bond->curr_active_slave && - test_bit(__LINK_STATE_LINKWATCH_PENDING, - &bond->curr_active_slave->dev->state)) { - dprintk("delaying gratuitous arp on %s\n", - bond->curr_active_slave->dev->name); - bond->send_grat_arp = 1; - } else + if (bond->params.fail_over_mac) + bond_do_fail_over_mac(bond, new_active, + old_active); + + bond->send_grat_arp = bond->params.num_grat_arp; bond_send_gratuitous_arp(bond); + + bond->send_unsol_na = bond->params.num_unsol_na; + bond_send_unsolicited_na(bond); + + write_unlock_bh(&bond->curr_slave_lock); + read_unlock(&bond->lock); + + netdev_bonding_change(bond->dev); + + read_lock(&bond->lock); + write_lock_bh(&bond->curr_slave_lock); + } } } @@ -1124,12 +1220,12 @@ void bond_change_active_slave(struct bonding *bond, struct slave *new_active) * 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: + * This functions should 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. + * Caller must hold bond->lock for read and curr_slave_lock for write_bh. */ void bond_select_active_slave(struct bonding *bond) { @@ -1144,11 +1240,11 @@ void bond_select_active_slave(struct bonding *bond) return; if (netif_carrier_ok(bond->dev)) { - printk(KERN_INFO DRV_NAME + pr_info(DRV_NAME ": %s: first active interface up!\n", bond->dev->name); } else { - printk(KERN_INFO DRV_NAME ": %s: " + pr_info(DRV_NAME ": %s: " "now running without any active interface !\n", bond->dev->name); } @@ -1190,13 +1286,11 @@ static void bond_attach_slave(struct bonding *bond, struct slave *new_slave) */ static void bond_detach_slave(struct bonding *bond, struct slave *slave) { - if (slave->next) { + if (slave->next) slave->next->prev = slave->prev; - } - if (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 */ @@ -1216,9 +1310,9 @@ static void bond_detach_slave(struct bonding *bond, struct slave *slave) static 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); + pr_debug("bond_dev=%p\n", bond_dev); + pr_debug("slave_dev=%p\n", slave_dev); + pr_debug("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; } @@ -1227,7 +1321,7 @@ static int bond_sethwaddr(struct net_device *bond_dev, (NETIF_F_VLAN_CHALLENGED | NETIF_F_HW_VLAN_RX | NETIF_F_HW_VLAN_TX | \ NETIF_F_HW_VLAN_FILTER) -/* +/* * Compute the common dev->feature set available to all slaves. Some * feature bits are managed elsewhere, so preserve those feature bits * on the master device. @@ -1242,31 +1336,35 @@ static int bond_compute_features(struct bonding *bond) int i; features &= ~(NETIF_F_ALL_CSUM | BOND_VLAN_FEATURES); - features |= NETIF_F_SG | NETIF_F_FRAGLIST | NETIF_F_HIGHDMA | - NETIF_F_GSO_MASK | NETIF_F_NO_CSUM; + features |= NETIF_F_GSO_MASK | NETIF_F_NO_CSUM; + + if (!bond->first_slave) + goto done; + + features &= ~NETIF_F_ONE_FOR_ALL; bond_for_each_slave(bond, slave, i) { - features = netdev_compute_features(features, - slave->dev->features); + features = netdev_increment_features(features, + slave->dev->features, + NETIF_F_ONE_FOR_ALL); if (slave->dev->hard_header_len > max_hard_header_len) max_hard_header_len = slave->dev->hard_header_len; } +done: features |= (bond_dev->features & BOND_VLAN_FEATURES); - bond_dev->features = features; + bond_dev->features = netdev_fix_features(features, NULL); bond_dev->hard_header_len = max_hard_header_len; return 0; } - static void bond_setup_by_slave(struct net_device *bond_dev, struct net_device *slave_dev) { - struct bonding *bond = bond_dev->priv; + struct bonding *bond = netdev_priv(bond_dev); - bond_dev->neigh_setup = slave_dev->neigh_setup; - bond_dev->header_ops = slave_dev->header_ops; + bond_dev->header_ops = slave_dev->header_ops; bond_dev->type = slave_dev->type; bond_dev->hard_header_len = slave_dev->hard_header_len; @@ -1280,7 +1378,8 @@ static void bond_setup_by_slave(struct net_device *bond_dev, /* 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 bonding *bond = netdev_priv(bond_dev); + const struct net_device_ops *slave_ops = slave_dev->netdev_ops; struct slave *new_slave = NULL; struct dev_mc_list *dmi; struct sockaddr addr; @@ -1289,38 +1388,38 @@ int bond_enslave(struct net_device *bond_dev, struct net_device *slave_dev) int res = 0; if (!bond->params.use_carrier && slave_dev->ethtool_ops == NULL && - slave_dev->do_ioctl == NULL) { - printk(KERN_WARNING DRV_NAME + slave_ops->ndo_do_ioctl == NULL) { + pr_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)) { - printk(KERN_WARNING DRV_NAME + pr_warning(DRV_NAME " %s: master_dev is not up in bond_enslave\n", bond_dev->name); } /* already enslaved */ if (slave_dev->flags & IFF_SLAVE) { - dprintk("Error, Device was already enslaved\n"); + pr_debug("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); + pr_debug("%s: NETIF_F_VLAN_CHALLENGED\n", slave_dev->name); if (!list_empty(&bond->vlan_list)) { - printk(KERN_ERR DRV_NAME + pr_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 + pr_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", @@ -1329,7 +1428,7 @@ int bond_enslave(struct net_device *bond_dev, struct net_device *slave_dev) bond_dev->features |= NETIF_F_VLAN_CHALLENGED; } } else { - dprintk("%s: ! NETIF_F_VLAN_CHALLENGED\n", slave_dev->name); + pr_debug("%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. @@ -1340,12 +1439,12 @@ int bond_enslave(struct net_device *bond_dev, struct net_device *slave_dev) /* * Old ifenslave binaries are no longer supported. These can - * be identified with moderate accurary by the state of the slave: + * be identified with moderate accuracy 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. " + pr_err(DRV_NAME ": %s is up. " "This may be due to an out of date ifenslave.\n", slave_dev->name); res = -EPERM; @@ -1360,10 +1459,18 @@ int bond_enslave(struct net_device *bond_dev, struct net_device *slave_dev) * ether type (eg ARPHRD_ETHER and ARPHRD_INFINIBAND) share the same bond */ if (bond->slave_cnt == 0) { - if (slave_dev->type != ARPHRD_ETHER) - bond_setup_by_slave(bond_dev, slave_dev); + if (bond_dev->type != slave_dev->type) { + dev_close(bond_dev); + pr_debug("%s: change device type from %d to %d\n", + bond_dev->name, bond_dev->type, slave_dev->type); + if (slave_dev->type != ARPHRD_ETHER) + bond_setup_by_slave(bond_dev, slave_dev); + else + ether_setup(bond_dev); + dev_open(bond_dev); + } } else if (bond_dev->type != slave_dev->type) { - printk(KERN_ERR DRV_NAME ": %s ether type (%d) is different " + pr_err(DRV_NAME ": %s ether type (%d) is different " "from other slaves (%d), can not enslave it.\n", slave_dev->name, slave_dev->type, bond_dev->type); @@ -1371,19 +1478,19 @@ int bond_enslave(struct net_device *bond_dev, struct net_device *slave_dev) goto err_undo_flags; } - if (slave_dev->set_mac_address == NULL) { + if (slave_ops->ndo_set_mac_address == NULL) { if (bond->slave_cnt == 0) { - printk(KERN_WARNING DRV_NAME + pr_warning(DRV_NAME ": %s: Warning: The first slave device " "specified does not support setting the MAC " - "address. Enabling the fail_over_mac option.", + "address. Setting fail_over_mac to active.", bond_dev->name); - bond->params.fail_over_mac = 1; - } else if (!bond->params.fail_over_mac) { - printk(KERN_ERR DRV_NAME + bond->params.fail_over_mac = BOND_FOM_ACTIVE; + } else if (bond->params.fail_over_mac != BOND_FOM_ACTIVE) { + pr_err(DRV_NAME ": %s: Error: The slave device specified " "does not support setting the MAC address, " - "but fail_over_mac is not enabled.\n" + "but fail_over_mac is not set to active.\n" , bond_dev->name); res = -EOPNOTSUPP; goto err_undo_flags; @@ -1417,35 +1524,33 @@ int bond_enslave(struct net_device *bond_dev, struct net_device *slave_dev) 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); + pr_debug("Error %d calling set_mac_address\n", res); goto err_free; } } res = netdev_set_master(slave_dev, bond_dev); if (res) { - dprintk("Error %d calling netdev_set_master\n", res); - goto err_close; + pr_debug("Error %d calling netdev_set_master\n", res); + goto err_restore_mac; } /* 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; + pr_debug("Opening slave %s failed\n", slave_dev->name); + goto err_unset_master; } new_slave->dev = slave_dev; slave_dev->priv_flags |= IFF_BONDING; - if ((bond->params.mode == BOND_MODE_TLB) || - (bond->params.mode == BOND_MODE_ALB)) { + if (bond_is_lb(bond)) { /* 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 (res) + goto err_close; } /* If the mode USES_PRIMARY, then the new slave gets the @@ -1456,20 +1561,24 @@ int bond_enslave(struct net_device *bond_dev, struct net_device *slave_dev) if (!USES_PRIMARY(bond->params.mode)) { /* set promiscuity level to new slave */ if (bond_dev->flags & IFF_PROMISC) { - dev_set_promiscuity(slave_dev, 1); + res = dev_set_promiscuity(slave_dev, 1); + if (res) + goto err_close; } /* set allmulti level to new slave */ if (bond_dev->flags & IFF_ALLMULTI) { - dev_set_allmulti(slave_dev, 1); + res = dev_set_allmulti(slave_dev, 1); + if (res) + goto err_close; } - netif_tx_lock_bh(bond_dev); + netif_addr_lock_bh(bond_dev); /* 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); - } - netif_tx_unlock_bh(bond_dev); + for (dmi = bond_dev->mc_list; dmi; dmi = dmi->next) + dev_mc_add(slave_dev, dmi->dmi_addr, + dmi->dmi_addrlen, 0); + netif_addr_unlock_bh(bond_dev); } if (bond->params.mode == BOND_MODE_8023AD) { @@ -1490,6 +1599,10 @@ int bond_enslave(struct net_device *bond_dev, struct net_device *slave_dev) bond_compute_features(bond); + write_unlock_bh(&bond->lock); + + read_lock(&bond->lock); + new_slave->last_arp_rx = jiffies; if (bond->params.miimon && !bond->params.use_carrier) { @@ -1505,7 +1618,7 @@ int bond_enslave(struct net_device *bond_dev, struct net_device *slave_dev) * supported); thus, we don't need to change * the messages for netif_carrier. */ - printk(KERN_WARNING DRV_NAME + pr_warning(DRV_NAME ": %s: Warning: MII and ETHTOOL support not " "available for interface %s, and " "arp_interval/arp_ip_target module parameters " @@ -1514,7 +1627,7 @@ int bond_enslave(struct net_device *bond_dev, struct net_device *slave_dev) bond_dev->name, slave_dev->name); } else if (link_reporting == -1) { /* unable get link status using mii/ethtool */ - printk(KERN_WARNING DRV_NAME + pr_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 " @@ -1528,31 +1641,31 @@ int bond_enslave(struct net_device *bond_dev, struct net_device *slave_dev) 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 " + pr_debug("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 " + pr_debug("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 " + pr_debug("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 + pr_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 + pr_warning(DRV_NAME ": %s: Warning: Operation of 802.3ad mode requires ETHTOOL " "support in base driver for proper aggregator " "selection.\n", bond_dev->name); @@ -1561,11 +1674,12 @@ int bond_enslave(struct net_device *bond_dev, struct net_device *slave_dev) 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; - } } + write_lock_bh(&bond->curr_slave_lock); + switch (bond->params.mode) { case BOND_MODE_ACTIVEBACKUP: bond_set_slave_inactive_flags(new_slave); @@ -1596,9 +1710,10 @@ int bond_enslave(struct net_device *bond_dev, struct net_device *slave_dev) case BOND_MODE_ALB: new_slave->state = BOND_STATE_ACTIVE; bond_set_slave_inactive_flags(new_slave); + bond_select_active_slave(bond); break; default: - dprintk("This slave is always active in trunk mode\n"); + pr_debug("This slave is always active in trunk mode\n"); /* always active in trunk mode */ new_slave->state = BOND_STATE_ACTIVE; @@ -1607,21 +1722,23 @@ int bond_enslave(struct net_device *bond_dev, struct net_device *slave_dev) * 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) { + if (!bond->curr_active_slave) bond->curr_active_slave = new_slave; - } + break; } /* switch(bond_mode) */ + write_unlock_bh(&bond->curr_slave_lock); + bond_set_carrier(bond); - write_unlock_bh(&bond->lock); + read_unlock(&bond->lock); res = bond_create_slave_symlinks(bond_dev, slave_dev); if (res) - goto err_unset_master; + goto err_close; - printk(KERN_INFO DRV_NAME + pr_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", @@ -1631,14 +1748,18 @@ int bond_enslave(struct net_device *bond_dev, struct net_device *slave_dev) return 0; /* Undo stages on error */ -err_unset_master: - netdev_set_master(slave_dev, NULL); - err_close: dev_close(slave_dev); +err_unset_master: + netdev_set_master(slave_dev, NULL); + err_restore_mac: if (!bond->params.fail_over_mac) { + /* XXX TODO - fom follow mode needs to change master's + * MAC if this slave's MAC is in use by the bond, or at + * least print a warning. + */ memcpy(addr.sa_data, new_slave->perm_hwaddr, ETH_ALEN); addr.sa_family = slave_dev->type; dev_set_mac_address(slave_dev, &addr); @@ -1649,7 +1770,7 @@ err_free: err_undo_flags: bond_dev->features = old_features; - + return res; } @@ -1666,16 +1787,15 @@ err_undo_flags: */ int bond_release(struct net_device *bond_dev, struct net_device *slave_dev) { - struct bonding *bond = bond_dev->priv; + struct bonding *bond = netdev_priv(bond_dev); struct slave *slave, *oldcurrent; struct sockaddr addr; int mac_addr_differ; - DECLARE_MAC_BUF(mac); /* 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 + pr_err(DRV_NAME ": %s: Error: cannot release %s.\n", bond_dev->name, slave_dev->name); return -EINVAL; @@ -1686,27 +1806,25 @@ int bond_release(struct net_device *bond_dev, struct net_device *slave_dev) slave = bond_get_slave_by_dev(bond, slave_dev); if (!slave) { /* not a slave of this bond */ - printk(KERN_INFO DRV_NAME + pr_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 - " - "%s - 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, - print_mac(mac, slave->perm_hwaddr), - bond_dev->name, - slave_dev->name); + if (!bond->params.fail_over_mac) { + mac_addr_differ = memcmp(bond_dev->dev_addr, slave->perm_hwaddr, + ETH_ALEN); + if (!mac_addr_differ && (bond->slave_cnt > 1)) + pr_warning(DRV_NAME + ": %s: Warning: the permanent HWaddr of %s - " + "%pM - 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, + bond_dev->name, slave_dev->name); } /* Inform AD package of unbinding of slave. */ @@ -1717,7 +1835,7 @@ int bond_release(struct net_device *bond_dev, struct net_device *slave_dev) bond_3ad_unbind_slave(slave); } - printk(KERN_INFO DRV_NAME + pr_info(DRV_NAME ": %s: releasing %s interface %s\n", bond_dev->name, (slave->state == BOND_STATE_ACTIVE) @@ -1733,16 +1851,13 @@ int bond_release(struct net_device *bond_dev, struct net_device *slave_dev) bond_compute_features(bond); - if (bond->primary_slave == slave) { + if (bond->primary_slave == slave) bond->primary_slave = NULL; - } - if (oldcurrent == slave) { + if (oldcurrent == slave) bond_change_active_slave(bond, NULL); - } - if ((bond->params.mode == BOND_MODE_TLB) || - (bond->params.mode == BOND_MODE_ALB)) { + if (bond_is_lb(bond)) { /* 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), @@ -1782,18 +1897,18 @@ int bond_release(struct net_device *bond_dev, struct net_device *slave_dev) if (list_empty(&bond->vlan_list)) { bond_dev->features |= NETIF_F_VLAN_CHALLENGED; } else { - printk(KERN_WARNING DRV_NAME + pr_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 + pr_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 + pr_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); @@ -1813,19 +1928,17 @@ int bond_release(struct net_device *bond_dev, struct net_device *slave_dev) */ if (!USES_PRIMARY(bond->params.mode)) { /* unset promiscuity level from slave */ - if (bond_dev->flags & IFF_PROMISC) { + if (bond_dev->flags & IFF_PROMISC) dev_set_promiscuity(slave_dev, -1); - } /* unset allmulti level from slave */ - if (bond_dev->flags & IFF_ALLMULTI) { + if (bond_dev->flags & IFF_ALLMULTI) dev_set_allmulti(slave_dev, -1); - } /* flush master's mc_list from slave */ - netif_tx_lock_bh(bond_dev); + netif_addr_lock_bh(bond_dev); bond_mc_list_flush(bond_dev, slave_dev); - netif_tx_unlock_bh(bond_dev); + netif_addr_unlock_bh(bond_dev); } netdev_set_master(slave_dev, NULL); @@ -1833,7 +1946,7 @@ int bond_release(struct net_device *bond_dev, struct net_device *slave_dev) /* close slave before restoring its mac address */ dev_close(slave_dev); - if (!bond->params.fail_over_mac) { + if (bond->params.fail_over_mac != BOND_FOM_ACTIVE) { /* restore original ("permanent") mac address */ memcpy(addr.sa_data, slave->perm_hwaddr, ETH_ALEN); addr.sa_family = slave_dev->type; @@ -1853,27 +1966,36 @@ int bond_release(struct net_device *bond_dev, struct net_device *slave_dev) * Destroy a bonding device. * Must be under rtnl_lock when this function is called. */ -void bond_destroy(struct bonding *bond) +static void bond_uninit(struct net_device *bond_dev) { - bond_deinit(bond->dev); + struct bonding *bond = netdev_priv(bond_dev); + + bond_deinit(bond_dev); bond_destroy_sysfs_entry(bond); - unregister_netdevice(bond->dev); + + 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 iare left. +* 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. */ -int bond_release_and_destroy(struct net_device *bond_dev, struct net_device *slave_dev) +int bond_release_and_destroy(struct net_device *bond_dev, + struct net_device *slave_dev) { - struct bonding *bond = bond_dev->priv; + struct bonding *bond = netdev_priv(bond_dev); int ret; ret = bond_release(bond_dev, slave_dev); if ((ret == 0) && (bond->slave_cnt == 0)) { - printk(KERN_INFO DRV_NAME ": %s: destroying bond %s.\n", + pr_info(DRV_NAME ": %s: destroying bond %s.\n", bond_dev->name, bond_dev->name); - bond_destroy(bond); + unregister_netdevice(bond_dev); } return ret; } @@ -1883,7 +2005,7 @@ int bond_release_and_destroy(struct net_device *bond_dev, struct net_device *sl */ static int bond_release_all(struct net_device *bond_dev) { - struct bonding *bond = bond_dev->priv; + struct bonding *bond = netdev_priv(bond_dev); struct slave *slave; struct net_device *slave_dev; struct sockaddr addr; @@ -1892,9 +2014,8 @@ static int bond_release_all(struct net_device *bond_dev) netif_carrier_off(bond_dev); - if (bond->slave_cnt == 0) { + if (bond->slave_cnt == 0) goto out; - } bond->current_arp_slave = NULL; bond->primary_slave = NULL; @@ -1904,9 +2025,8 @@ static int bond_release_all(struct net_device *bond_dev) /* Inform AD package of unbinding of slave * before slave is detached from the list. */ - if (bond->params.mode == BOND_MODE_8023AD) { + if (bond->params.mode == BOND_MODE_8023AD) bond_3ad_unbind_slave(slave); - } slave_dev = slave->dev; bond_detach_slave(bond, slave); @@ -1917,8 +2037,7 @@ static int bond_release_all(struct net_device *bond_dev) */ write_unlock_bh(&bond->lock); - if ((bond->params.mode == BOND_MODE_TLB) || - (bond->params.mode == BOND_MODE_ALB)) { + if (bond_is_lb(bond)) { /* must be called only after the slave * has been detached from the list */ @@ -1936,19 +2055,17 @@ static int bond_release_all(struct net_device *bond_dev) */ if (!USES_PRIMARY(bond->params.mode)) { /* unset promiscuity level from slave */ - if (bond_dev->flags & IFF_PROMISC) { + if (bond_dev->flags & IFF_PROMISC) dev_set_promiscuity(slave_dev, -1); - } /* unset allmulti level from slave */ - if (bond_dev->flags & IFF_ALLMULTI) { + if (bond_dev->flags & IFF_ALLMULTI) dev_set_allmulti(slave_dev, -1); - } /* flush master's mc_list from slave */ - netif_tx_lock_bh(bond_dev); + netif_addr_lock_bh(bond_dev); bond_mc_list_flush(bond_dev, slave_dev); - netif_tx_unlock_bh(bond_dev); + netif_addr_unlock_bh(bond_dev); } netdev_set_master(slave_dev, NULL); @@ -1978,20 +2095,20 @@ static int bond_release_all(struct net_device *bond_dev) */ memset(bond_dev->dev_addr, 0, bond_dev->addr_len); - if (list_empty(&bond->vlan_list)) { + if (list_empty(&bond->vlan_list)) bond_dev->features |= NETIF_F_VLAN_CHALLENGED; - } else { - printk(KERN_WARNING DRV_NAME + else { + pr_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 + pr_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 + pr_info(DRV_NAME ": %s: released all slaves\n", bond_dev->name); @@ -2009,25 +2126,22 @@ out: * - 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. + * In these cases, this function does nothing. + * In the other cases, current_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 bonding *bond = netdev_priv(bond_dev); struct slave *old_active = NULL; struct slave *new_active = NULL; int res = 0; - if (!USES_PRIMARY(bond->params.mode)) { + 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)) { + if (!(slave_dev->flags & IFF_SLAVE) || (slave_dev->master != bond_dev)) return -EINVAL; - } read_lock(&bond->lock); @@ -2052,9 +2166,8 @@ static int bond_ioctl_change_active(struct net_device *bond_dev, struct net_devi write_lock_bh(&bond->curr_slave_lock); bond_change_active_slave(bond, new_active); write_unlock_bh(&bond->curr_slave_lock); - } else { + } else res = -EINVAL; - } read_unlock(&bond->lock); @@ -2063,7 +2176,7 @@ static int bond_ioctl_change_active(struct net_device *bond_dev, struct net_devi static int bond_info_query(struct net_device *bond_dev, struct ifbond *info) { - struct bonding *bond = bond_dev->priv; + struct bonding *bond = netdev_priv(bond_dev); info->bond_mode = bond->params.mode; info->miimon = bond->params.miimon; @@ -2077,329 +2190,281 @@ static int bond_info_query(struct net_device *bond_dev, struct ifbond *info) static int bond_slave_info_query(struct net_device *bond_dev, struct ifslave *info) { - struct bonding *bond = bond_dev->priv; + struct bonding *bond = netdev_priv(bond_dev); struct slave *slave; - int i, found = 0; - - if (info->slave_id < 0) { - return -ENODEV; - } + int i, res = -ENODEV; read_lock(&bond->lock); bond_for_each_slave(bond, slave, i) { if (i == (int)info->slave_id) { - found = 1; + res = 0; + strcpy(info->slave_name, slave->dev->name); + info->link = slave->link; + info->state = slave->state; + info->link_failure_count = slave->link_failure_count; break; } } read_unlock(&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; + return res; } /*-------------------------------- Monitoring -------------------------------*/ -/* - * if !have_locks, return nonzero if a failover is necessary. if - * have_locks, do whatever failover activities are needed. - * - * This is to separate the inspection and failover steps for locking - * purposes; failover requires rtnl, but acquiring it for every - * inspection is undesirable, so a wrapper first does inspection, and - * the acquires the necessary locks and calls again to perform - * failover if needed. Since all locks are dropped, a complete - * restart is needed between calls. - */ -static int __bond_mii_monitor(struct bonding *bond, int have_locks) -{ - struct slave *slave, *oldcurrent; - int do_failover = 0; - int i; - - if (bond->slave_cnt == 0) - goto out; - /* 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. - */ +static int bond_miimon_inspect(struct bonding *bond) +{ + struct slave *slave; + int i, link_state, commit = 0; + bool ignore_updelay; - if (bond->send_grat_arp) { - if (bond->curr_active_slave && test_bit(__LINK_STATE_LINKWATCH_PENDING, - &bond->curr_active_slave->dev->state)) - dprintk("Needs to send gratuitous arp but not yet\n"); - else { - dprintk("sending delayed gratuitous arp on on %s\n", - bond->curr_active_slave->dev->name); - bond_send_gratuitous_arp(bond); - bond->send_grat_arp = 0; - } - } - read_lock(&bond->curr_slave_lock); - oldcurrent = bond->curr_active_slave; - read_unlock(&bond->curr_slave_lock); + ignore_updelay = !bond->curr_active_slave ? true : false; 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; + slave->new_link = BOND_LINK_NOCHANGE; - link_state = bond_check_dev_link(bond, slave_dev, 0); + 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) { - if (!oldcurrent) { - if (!have_locks) - return 1; - do_failover = 1; - } - 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++; - } + case BOND_LINK_UP: + if (link_state) + continue; - 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); - } + slave->link = BOND_LINK_FAIL; + slave->delay = bond->params.downdelay; + if (slave->delay) { + pr_info(DRV_NAME + ": %s: link status down for %s" + "interface %s, disabling it in %d ms.\n", + bond->dev->name, + (bond->params.mode == + BOND_MODE_ACTIVEBACKUP) ? + ((slave->state == BOND_STATE_ACTIVE) ? + "active " : "backup ") : "", + 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) { - if (!have_locks) - return 1; - - /* 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; + /*FALLTHRU*/ + case BOND_LINK_FAIL: + if (link_state) { + /* + * recovered before downdelay expired + */ + slave->link = BOND_LINK_UP; slave->jiffies = jiffies; - printk(KERN_INFO DRV_NAME + pr_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); + (bond->params.downdelay - slave->delay) * + bond->params.miimon, + slave->dev->name); + continue; } - 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); - } + + if (slave->delay <= 0) { + slave->new_link = BOND_LINK_DOWN; + commit++; + continue; } - /* 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 + slave->delay--; + break; + + case BOND_LINK_DOWN: + if (!link_state) + continue; + + slave->link = BOND_LINK_BACK; + slave->delay = bond->params.updelay; + + if (slave->delay) { + pr_info(DRV_NAME + ": %s: link status up for " + "interface %s, enabling it in %d ms.\n", + bond->dev->name, slave->dev->name, + ignore_updelay ? 0 : + bond->params.updelay * + bond->params.miimon); + } + /*FALLTHRU*/ + case BOND_LINK_BACK: + if (!link_state) { + slave->link = BOND_LINK_DOWN; + pr_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) { - if (!have_locks) - return 1; - - /* 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--; - } + (bond->params.updelay - slave->delay) * + bond->params.miimon, + slave->dev->name); + + continue; } - 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 (ignore_updelay) + slave->delay = 0; - if (bond->params.mode == BOND_MODE_8023AD) { - if (old_speed != slave->speed) { - bond_3ad_adapter_speed_changed(slave); + if (slave->delay <= 0) { + slave->new_link = BOND_LINK_UP; + commit++; + ignore_updelay = false; + continue; } - if (old_duplex != slave->duplex) { - bond_3ad_adapter_duplex_changed(slave); - } + slave->delay--; + break; } + } - } /* end of for */ + return commit; +} - if (do_failover) { - ASSERT_RTNL(); +static void bond_miimon_commit(struct bonding *bond) +{ + struct slave *slave; + int i; - write_lock_bh(&bond->curr_slave_lock); + bond_for_each_slave(bond, slave, i) { + switch (slave->new_link) { + case BOND_LINK_NOCHANGE: + continue; - bond_select_active_slave(bond); + case BOND_LINK_UP: + slave->link = BOND_LINK_UP; + slave->jiffies = jiffies; - write_unlock_bh(&bond->curr_slave_lock); + 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; + } - } else - bond_set_carrier(bond); + pr_info(DRV_NAME + ": %s: link status definitely " + "up for interface %s.\n", + bond->dev->name, slave->dev->name); -out: - return 0; + /* 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_is_lb(bond)) + bond_alb_handle_link_change(bond, slave, + BOND_LINK_UP); + + if (!bond->curr_active_slave || + (slave == bond->primary_slave)) + goto do_failover; + + continue; + + case BOND_LINK_DOWN: + if (slave->link_failure_count < UINT_MAX) + slave->link_failure_count++; + + slave->link = BOND_LINK_DOWN; + + if (bond->params.mode == BOND_MODE_ACTIVEBACKUP || + bond->params.mode == BOND_MODE_8023AD) + bond_set_slave_inactive_flags(slave); + + pr_info(DRV_NAME + ": %s: link status definitely down for " + "interface %s, disabling it\n", + bond->dev->name, slave->dev->name); + + if (bond->params.mode == BOND_MODE_8023AD) + bond_3ad_handle_link_change(slave, + BOND_LINK_DOWN); + + if (bond_is_lb(bond)) + bond_alb_handle_link_change(bond, slave, + BOND_LINK_DOWN); + + if (slave == bond->curr_active_slave) + goto do_failover; + + continue; + + default: + pr_err(DRV_NAME + ": %s: invalid new link %d on slave %s\n", + bond->dev->name, slave->new_link, + slave->dev->name); + slave->new_link = BOND_LINK_NOCHANGE; + + continue; + } + +do_failover: + ASSERT_RTNL(); + write_lock_bh(&bond->curr_slave_lock); + bond_select_active_slave(bond); + write_unlock_bh(&bond->curr_slave_lock); + } + + bond_set_carrier(bond); } /* * bond_mii_monitor * * Really a wrapper that splits the mii monitor into two phases: an - * inspection, then (if inspection indicates something needs to be - * done) an acquisition of appropriate locks followed by another pass - * to implement whatever link state changes are indicated. + * inspection, then (if inspection indicates something needs to be done) + * an acquisition of appropriate locks followed by a commit phase to + * implement whatever link state changes are indicated. */ void bond_mii_monitor(struct work_struct *work) { struct bonding *bond = container_of(work, struct bonding, mii_work.work); - unsigned long delay; read_lock(&bond->lock); - if (bond->kill_timers) { - read_unlock(&bond->lock); - return; + if (bond->kill_timers) + goto out; + + if (bond->slave_cnt == 0) + goto re_arm; + + if (bond->send_grat_arp) { + read_lock(&bond->curr_slave_lock); + bond_send_gratuitous_arp(bond); + read_unlock(&bond->curr_slave_lock); + } + + if (bond->send_unsol_na) { + read_lock(&bond->curr_slave_lock); + bond_send_unsolicited_na(bond); + read_unlock(&bond->curr_slave_lock); } - if (__bond_mii_monitor(bond, 0)) { + + if (bond_miimon_inspect(bond)) { read_unlock(&bond->lock); rtnl_lock(); read_lock(&bond->lock); - __bond_mii_monitor(bond, 1); + + bond_miimon_commit(bond); + read_unlock(&bond->lock); rtnl_unlock(); /* might sleep, hold no other locks */ read_lock(&bond->lock); } - delay = ((bond->params.miimon * HZ) / 1000) ? : 1; +re_arm: + if (bond->params.miimon) + queue_delayed_work(bond->wq, &bond->mii_work, + msecs_to_jiffies(bond->params.miimon)); +out: read_unlock(&bond->lock); - queue_delayed_work(bond->wq, &bond->mii_work, delay); } static __be32 bond_glean_dev_ip(struct net_device *dev) @@ -2426,37 +2491,14 @@ out: 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; -} - static int bond_has_this_ip(struct bonding *bond, __be32 ip) { - struct vlan_entry *vlan, *vlan_next; + struct vlan_entry *vlan; 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) { + list_for_each_entry(vlan, &bond->vlan_list, vlan_list) { if (ip == vlan->vlan_ip) return 1; } @@ -2473,20 +2515,20 @@ static void bond_arp_send(struct net_device *slave_dev, int arp_op, __be32 dest_ { struct sk_buff *skb; - dprintk("arp %d on slave %s: dst %x src %x vid %d\n", arp_op, + pr_debug("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"); + pr_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"); + pr_err(DRV_NAME ": failed to insert VLAN tag\n"); return; } } @@ -2498,17 +2540,17 @@ static void bond_arp_send_all(struct bonding *bond, struct slave *slave) { int i, vlan_id, rv; __be32 *targets = bond->params.arp_targets; - struct vlan_entry *vlan, *vlan_next; + struct vlan_entry *vlan; 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]); + break; + pr_debug("basa: target %x\n", targets[i]); if (list_empty(&bond->vlan_list)) { - dprintk("basa: empty vlan: arp_send\n"); + pr_debug("basa: empty vlan: arp_send\n"); bond_arp_send(slave->dev, ARPOP_REQUEST, targets[i], bond->master_ip, 0); continue; @@ -2526,9 +2568,9 @@ static void bond_arp_send_all(struct bonding *bond, struct slave *slave) rv = ip_route_output_key(&init_net, &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)); + pr_warning(DRV_NAME + ": %s: no route to arp_ip_target %pI4\n", + bond->dev->name, &fl.fl4_dst); } continue; } @@ -2538,19 +2580,18 @@ static void bond_arp_send_all(struct bonding *bond, struct slave *slave) */ if (rt->u.dst.dev == bond->dev) { ip_rt_put(rt); - dprintk("basa: rtdev == bond->dev: arp_send\n"); + pr_debug("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) { + list_for_each_entry(vlan, &bond->vlan_list, vlan_list) { vlan_dev = vlan_group_get_device(bond->vlgrp, vlan->vlan_id); if (vlan_dev == rt->u.dst.dev) { vlan_id = vlan->vlan_id; - dprintk("basa: vlan match on %s %d\n", + pr_debug("basa: vlan match on %s %d\n", vlan_dev->name, vlan_id); break; } @@ -2564,9 +2605,9 @@ static void bond_arp_send_all(struct bonding *bond, struct slave *slave) } if (net_ratelimit()) { - printk(KERN_WARNING DRV_NAME - ": %s: no path to arp_ip_target %u.%u.%u.%u via rt.dev %s\n", - bond->dev->name, NIPQUAD(fl.fl4_dst), + pr_warning(DRV_NAME + ": %s: no path to arp_ip_target %pI4 via rt.dev %s\n", + bond->dev->name, &fl.fl4_dst, rt->u.dst.dev ? rt->u.dst.dev->name : "NULL"); } ip_rt_put(rt); @@ -2576,6 +2617,8 @@ static void bond_arp_send_all(struct bonding *bond, struct slave *slave) /* * Kick out a gratuitous ARP for an IP on the bonding master plus one * for each VLAN above us. + * + * Caller must hold curr_slave_lock for read or better */ static void bond_send_gratuitous_arp(struct bonding *bond) { @@ -2583,11 +2626,15 @@ static void bond_send_gratuitous_arp(struct bonding *bond) struct vlan_entry *vlan; struct net_device *vlan_dev; - dprintk("bond_send_grat_arp: bond %s slave %s\n", bond->dev->name, + pr_debug("bond_send_grat_arp: bond %s slave %s\n", bond->dev->name, slave ? slave->dev->name : "NULL"); - if (!slave) + + if (!slave || !bond->send_grat_arp || + test_bit(__LINK_STATE_LINKWATCH_PENDING, &slave->dev->state)) return; + bond->send_grat_arp--; + if (bond->master_ip) { bond_arp_send(slave->dev, ARPOP_REPLY, bond->master_ip, bond->master_ip, 0); @@ -2607,12 +2654,9 @@ static void bond_validate_arp(struct bonding *bond, struct slave *slave, __be32 int i; __be32 *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)); + pr_debug("bva: sip %pI4 tip %pI4 t[%d] %pI4 bhti(tip) %d\n", + &sip, &tip, i, &targets[i], bond_has_this_ip(bond, tip)); if (sip == targets[i]) { if (bond_has_this_ip(bond, tip)) slave->last_arp_rx = jiffies; @@ -2629,16 +2673,16 @@ static int bond_arp_rcv(struct sk_buff *skb, struct net_device *dev, struct pack unsigned char *arp_ptr; __be32 sip, tip; - if (dev->nd_net != &init_net) + if (dev_net(dev) != &init_net) goto out; if (!(dev->priv_flags & IFF_BONDING) || !(dev->flags & IFF_MASTER)) goto out; - bond = dev->priv; + bond = netdev_priv(dev); read_lock(&bond->lock); - dprintk("bond_arp_rcv: bond %s skb->dev %s orig_dev %s\n", + pr_debug("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"); @@ -2646,10 +2690,7 @@ static int bond_arp_rcv(struct sk_buff *skb, struct net_device *dev, struct pack 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))))) + if (!pskb_may_pull(skb, arp_hdr_len(dev))) goto out_unlock; arp = arp_hdr(skb); @@ -2667,10 +2708,10 @@ static int bond_arp_rcv(struct sk_buff *skb, struct net_device *dev, struct pack 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)); + pr_debug("bond_arp_rcv: %s %s/%d av %d sv %d sip %pI4 tip %pI4\n", + bond->dev->name, slave->dev->name, slave->state, + bond->params.arp_validate, slave_do_arp_validate(bond, slave), + &sip, &tip); /* * Backup slaves won't see the ARP reply, but do come through @@ -2710,15 +2751,13 @@ void bond_loadbalance_arp_mon(struct work_struct *work) read_lock(&bond->lock); - delta_in_ticks = (bond->params.arp_interval * HZ) / 1000; + delta_in_ticks = msecs_to_jiffies(bond->params.arp_interval); - if (bond->kill_timers) { + if (bond->kill_timers) goto out; - } - if (bond->slave_cnt == 0) { + if (bond->slave_cnt == 0) goto re_arm; - } read_lock(&bond->curr_slave_lock); oldcurrent = bond->curr_active_slave; @@ -2734,7 +2773,7 @@ void bond_loadbalance_arp_mon(struct work_struct *work) */ bond_for_each_slave(bond, slave, i) { if (slave->link != BOND_LINK_UP) { - if (time_before_eq(jiffies, slave->dev->trans_start + delta_in_ticks) && + if (time_before_eq(jiffies, dev_trans_start(slave->dev) + delta_in_ticks) && time_before_eq(jiffies, slave->dev->last_rx + delta_in_ticks)) { slave->link = BOND_LINK_UP; @@ -2746,14 +2785,14 @@ void bond_loadbalance_arp_mon(struct work_struct *work) * is closed. */ if (!oldcurrent) { - printk(KERN_INFO DRV_NAME + pr_info(DRV_NAME ": %s: link status definitely " "up for interface %s, ", bond->dev->name, slave->dev->name); do_failover = 1; } else { - printk(KERN_INFO DRV_NAME + pr_info(DRV_NAME ": %s: interface %s is now up\n", bond->dev->name, slave->dev->name); @@ -2766,25 +2805,22 @@ void bond_loadbalance_arp_mon(struct work_struct *work) * when the source ip is 0, so don't take the link down * if we don't know our ip yet */ - if (time_after_eq(jiffies, slave->dev->trans_start + 2*delta_in_ticks) || - (time_after_eq(jiffies, slave->dev->last_rx + 2*delta_in_ticks) && - bond_has_ip(bond))) { + if (time_after_eq(jiffies, dev_trans_start(slave->dev) + 2*delta_in_ticks) || + (time_after_eq(jiffies, slave->dev->last_rx + 2*delta_in_ticks))) { slave->link = BOND_LINK_DOWN; slave->state = BOND_STATE_BACKUP; - if (slave->link_failure_count < UINT_MAX) { + if (slave->link_failure_count < UINT_MAX) slave->link_failure_count++; - } - printk(KERN_INFO DRV_NAME + pr_info(DRV_NAME ": %s: interface %s is now down.\n", bond->dev->name, slave->dev->name); - if (slave == oldcurrent) { + if (slave == oldcurrent) do_failover = 1; - } } } @@ -2795,9 +2831,8 @@ void bond_loadbalance_arp_mon(struct work_struct *work) * do - all replies will be rx'ed on same link causing slaves * to be unstable during low/no traffic periods */ - if (IS_UP(slave->dev)) { + if (IS_UP(slave->dev)) bond_arp_send_all(bond, slave); - } } if (do_failover) { @@ -2816,250 +2851,314 @@ out: } /* - * When using arp monitoring in active-backup mode, this function is - * called to determine if any backup slaves have went down or a new - * current slave needs to be found. - * The backup slaves never generate traffic, they are considered up by merely - * receiving traffic. If the current slave goes down, each backup slave will - * be given the opportunity to tx/rx an arp before being taken down - this - * prevents all slaves from being taken down due to the current slave not - * sending any traffic for the backups to receive. The arps are not necessarily - * necessary, any tx and rx traffic will keep the current slave up. While any - * rx traffic will keep the backup slaves up, the current slave is responsible - * for generating traffic to keep them up regardless of any other traffic they - * may have received. - * see loadbalance_arp_monitor for arp monitoring in load balancing mode + * Called to inspect slaves for active-backup mode ARP monitor link state + * changes. Sets new_link in slaves to specify what action should take + * place for the slave. Returns 0 if no changes are found, >0 if changes + * to link states must be committed. + * + * Called with bond->lock held for read. */ -void bond_activebackup_arp_mon(struct work_struct *work) +static int bond_ab_arp_inspect(struct bonding *bond, int delta_in_ticks) { - struct bonding *bond = container_of(work, struct bonding, - arp_work.work); struct slave *slave; - int delta_in_ticks; - int i; + int i, commit = 0; - read_lock(&bond->lock); + bond_for_each_slave(bond, slave, i) { + slave->new_link = BOND_LINK_NOCHANGE; - delta_in_ticks = (bond->params.arp_interval * HZ) / 1000; + if (slave->link != BOND_LINK_UP) { + if (time_before_eq(jiffies, slave_last_rx(bond, slave) + + delta_in_ticks)) { + slave->new_link = BOND_LINK_UP; + commit++; + } - if (bond->kill_timers) { - goto out; - } + continue; + } - if (bond->slave_cnt == 0) { - goto re_arm; + /* + * Give slaves 2*delta after being enslaved or made + * active. This avoids bouncing, as the last receive + * times need a full ARP monitor cycle to be updated. + */ + if (!time_after_eq(jiffies, slave->jiffies + + 2 * delta_in_ticks)) + continue; + + /* + * Backup slave is down if: + * - No current_arp_slave AND + * - more than 3*delta since last receive AND + * - the bond has an IP address + * + * Note: a non-null current_arp_slave indicates + * the curr_active_slave went down and we are + * searching for a new one; under this condition + * we only take the curr_active_slave down - this + * gives each slave a chance to tx/rx traffic + * before being taken out + */ + if (slave->state == BOND_STATE_BACKUP && + !bond->current_arp_slave && + time_after(jiffies, slave_last_rx(bond, slave) + + 3 * delta_in_ticks)) { + slave->new_link = BOND_LINK_DOWN; + commit++; + } + + /* + * Active slave is down if: + * - more than 2*delta since transmitting OR + * - (more than 2*delta since receive AND + * the bond has an IP address) + */ + if ((slave->state == BOND_STATE_ACTIVE) && + (time_after_eq(jiffies, dev_trans_start(slave->dev) + + 2 * delta_in_ticks) || + (time_after_eq(jiffies, slave_last_rx(bond, slave) + + 2 * delta_in_ticks)))) { + slave->new_link = BOND_LINK_DOWN; + commit++; + } } - /* determine if any slave has come up or any backup slave has - * gone down - * TODO: what about up/down delay in arp mode? it wasn't here before - * so it can wait + read_lock(&bond->curr_slave_lock); + + /* + * Trigger a commit if the primary option setting has changed. */ - bond_for_each_slave(bond, slave, i) { - if (slave->link != BOND_LINK_UP) { - if (time_before_eq(jiffies, - slave_last_rx(bond, slave) + delta_in_ticks)) { + if (bond->primary_slave && + (bond->primary_slave != bond->curr_active_slave) && + (bond->primary_slave->link == BOND_LINK_UP)) + commit++; - slave->link = BOND_LINK_UP; + read_unlock(&bond->curr_slave_lock); - write_lock_bh(&bond->curr_slave_lock); + return commit; +} - if ((!bond->curr_active_slave) && - time_before_eq(jiffies, slave->dev->trans_start + delta_in_ticks)) { - bond_change_active_slave(bond, slave); - bond->current_arp_slave = NULL; - } else if (bond->curr_active_slave != slave) { - /* this slave has just come up but we - * already have a current slave; this - * can also happen if bond_enslave adds - * a new slave that is up while we are - * searching for a new slave - */ - bond_set_slave_inactive_flags(slave); - bond->current_arp_slave = NULL; - } +/* + * Called to commit link state changes noted by inspection step of + * active-backup mode ARP monitor. + * + * Called with RTNL and bond->lock for read. + */ +static void bond_ab_arp_commit(struct bonding *bond, int delta_in_ticks) +{ + struct slave *slave; + int i; - bond_set_carrier(bond); + bond_for_each_slave(bond, slave, i) { + switch (slave->new_link) { + case BOND_LINK_NOCHANGE: + continue; - if (slave == bond->curr_active_slave) { - printk(KERN_INFO DRV_NAME - ": %s: %s is up and now the " - "active interface\n", - bond->dev->name, - slave->dev->name); - netif_carrier_on(bond->dev); - } else { - printk(KERN_INFO DRV_NAME - ": %s: backup interface %s is " - "now up\n", - bond->dev->name, - slave->dev->name); - } + case BOND_LINK_UP: + write_lock_bh(&bond->curr_slave_lock); - write_unlock_bh(&bond->curr_slave_lock); + if (!bond->curr_active_slave && + time_before_eq(jiffies, dev_trans_start(slave->dev) + + delta_in_ticks)) { + slave->link = BOND_LINK_UP; + bond_change_active_slave(bond, slave); + bond->current_arp_slave = NULL; + + pr_info(DRV_NAME + ": %s: %s is up and now the " + "active interface\n", + bond->dev->name, slave->dev->name); + + } else if (bond->curr_active_slave != slave) { + /* this slave has just come up but we + * already have a current slave; this can + * also happen if bond_enslave adds a new + * slave that is up while we are searching + * for a new slave + */ + slave->link = BOND_LINK_UP; + bond_set_slave_inactive_flags(slave); + bond->current_arp_slave = NULL; + + pr_info(DRV_NAME + ": %s: backup interface %s is now up\n", + bond->dev->name, slave->dev->name); } - } else { - read_lock(&bond->curr_slave_lock); - if ((slave != bond->curr_active_slave) && - (!bond->current_arp_slave) && - (time_after_eq(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 - * taken out before the backup slave. - * note: a non-null current_arp_slave indicates - * the curr_active_slave went down and we are - * searching for a new one; under this - * condition we only take the curr_active_slave - * down - this gives each slave a chance to - * tx/rx traffic before being taken out - */ + write_unlock_bh(&bond->curr_slave_lock); - read_unlock(&bond->curr_slave_lock); + break; - slave->link = BOND_LINK_DOWN; + case BOND_LINK_DOWN: + if (slave->link_failure_count < UINT_MAX) + slave->link_failure_count++; - if (slave->link_failure_count < UINT_MAX) { - slave->link_failure_count++; - } + slave->link = BOND_LINK_DOWN; + + if (slave == bond->curr_active_slave) { + pr_info(DRV_NAME + ": %s: link status down for active " + "interface %s, disabling it\n", + bond->dev->name, slave->dev->name); bond_set_slave_inactive_flags(slave); - printk(KERN_INFO DRV_NAME + write_lock_bh(&bond->curr_slave_lock); + + bond_select_active_slave(bond); + if (bond->curr_active_slave) + bond->curr_active_slave->jiffies = + jiffies; + + write_unlock_bh(&bond->curr_slave_lock); + + bond->current_arp_slave = NULL; + + } else if (slave->state == BOND_STATE_BACKUP) { + pr_info(DRV_NAME ": %s: backup interface %s is now down\n", - bond->dev->name, - slave->dev->name); - } else { - read_unlock(&bond->curr_slave_lock); + bond->dev->name, slave->dev->name); + + bond_set_slave_inactive_flags(slave); } + break; + + default: + pr_err(DRV_NAME + ": %s: impossible: new_link %d on slave %s\n", + bond->dev->name, slave->new_link, + slave->dev->name); } } - read_lock(&bond->curr_slave_lock); - slave = bond->curr_active_slave; - read_unlock(&bond->curr_slave_lock); + /* + * No race with changes to primary via sysfs, as we hold rtnl. + */ + if (bond->primary_slave && + (bond->primary_slave != bond->curr_active_slave) && + (bond->primary_slave->link == BOND_LINK_UP)) { + write_lock_bh(&bond->curr_slave_lock); + bond_change_active_slave(bond, bond->primary_slave); + write_unlock_bh(&bond->curr_slave_lock); + } - if (slave) { - /* if we have sent traffic in the past 2*arp_intervals but - * haven't xmit and rx traffic in that time interval, select - * a different slave. slave->jiffies is only updated when - * a slave first becomes the curr_active_slave - not necessarily - * after every arp; this ensures the slave has a full 2*delta - * before being taken out. if a primary is being used, check - * if it is up and needs to take over as the curr_active_slave - */ - if ((time_after_eq(jiffies, slave->dev->trans_start + 2*delta_in_ticks) || - (time_after_eq(jiffies, slave_last_rx(bond, slave) + 2*delta_in_ticks) && - bond_has_ip(bond))) && - time_after_eq(jiffies, slave->jiffies + 2*delta_in_ticks)) { + bond_set_carrier(bond); +} - slave->link = BOND_LINK_DOWN; +/* + * Send ARP probes for active-backup mode ARP monitor. + * + * Called with bond->lock held for read. + */ +static void bond_ab_arp_probe(struct bonding *bond) +{ + struct slave *slave; + int i; - if (slave->link_failure_count < UINT_MAX) { - slave->link_failure_count++; - } + read_lock(&bond->curr_slave_lock); - printk(KERN_INFO DRV_NAME - ": %s: link status down for active interface " - "%s, disabling it\n", - bond->dev->name, - slave->dev->name); + if (bond->current_arp_slave && bond->curr_active_slave) + pr_info(DRV_NAME "PROBE: c_arp %s && cas %s BAD\n", + bond->current_arp_slave->dev->name, + bond->curr_active_slave->dev->name); - write_lock_bh(&bond->curr_slave_lock); + if (bond->curr_active_slave) { + bond_arp_send_all(bond, bond->curr_active_slave); + read_unlock(&bond->curr_slave_lock); + return; + } - bond_select_active_slave(bond); - slave = bond->curr_active_slave; + read_unlock(&bond->curr_slave_lock); - write_unlock_bh(&bond->curr_slave_lock); + /* if we don't have a curr_active_slave, search for the next available + * backup slave from the current_arp_slave and make it the candidate + * for becoming the curr_active_slave + */ - bond->current_arp_slave = slave; + if (!bond->current_arp_slave) { + bond->current_arp_slave = bond->first_slave; + if (!bond->current_arp_slave) + return; + } - if (slave) { - slave->jiffies = jiffies; - } - } else if ((bond->primary_slave) && - (bond->primary_slave != slave) && - (bond->primary_slave->link == BOND_LINK_UP)) { - /* at this point, slave is the curr_active_slave */ - printk(KERN_INFO DRV_NAME - ": %s: changing from interface %s to primary " - "interface %s\n", - bond->dev->name, - slave->dev->name, - bond->primary_slave->dev->name); - - /* primary is up so switch to it */ - write_lock_bh(&bond->curr_slave_lock); - bond_change_active_slave(bond, bond->primary_slave); - write_unlock_bh(&bond->curr_slave_lock); + bond_set_slave_inactive_flags(bond->current_arp_slave); - slave = bond->primary_slave; + /* search for next candidate */ + bond_for_each_slave_from(bond, slave, i, bond->current_arp_slave->next) { + if (IS_UP(slave->dev)) { + slave->link = BOND_LINK_BACK; + bond_set_slave_active_flags(slave); + bond_arp_send_all(bond, slave); slave->jiffies = jiffies; - } else { - bond->current_arp_slave = NULL; + bond->current_arp_slave = slave; + break; } - /* the current slave must tx an arp to ensure backup slaves - * rx traffic + /* if the link state is up at this point, we + * mark it down - this can happen if we have + * simultaneous link failures and + * reselect_active_interface doesn't make this + * one the current slave so it is still marked + * up when it is actually down */ - if (slave && bond_has_ip(bond)) { - bond_arp_send_all(bond, slave); + if (slave->link == BOND_LINK_UP) { + slave->link = BOND_LINK_DOWN; + if (slave->link_failure_count < UINT_MAX) + slave->link_failure_count++; + + bond_set_slave_inactive_flags(slave); + + pr_info(DRV_NAME + ": %s: backup interface %s is now down.\n", + bond->dev->name, slave->dev->name); } } +} - /* if we don't have a curr_active_slave, search for the next available - * backup slave from the current_arp_slave and make it the candidate - * for becoming the curr_active_slave - */ - if (!slave) { - if (!bond->current_arp_slave) { - bond->current_arp_slave = bond->first_slave; - } +void bond_activebackup_arp_mon(struct work_struct *work) +{ + struct bonding *bond = container_of(work, struct bonding, + arp_work.work); + int delta_in_ticks; - if (bond->current_arp_slave) { - bond_set_slave_inactive_flags(bond->current_arp_slave); - - /* search for next candidate */ - bond_for_each_slave_from(bond, slave, i, bond->current_arp_slave->next) { - if (IS_UP(slave->dev)) { - slave->link = BOND_LINK_BACK; - bond_set_slave_active_flags(slave); - bond_arp_send_all(bond, slave); - slave->jiffies = jiffies; - bond->current_arp_slave = slave; - break; - } + read_lock(&bond->lock); - /* if the link state is up at this point, we - * mark it down - this can happen if we have - * simultaneous link failures and - * reselect_active_interface doesn't make this - * one the current slave so it is still marked - * up when it is actually down - */ - if (slave->link == BOND_LINK_UP) { - slave->link = BOND_LINK_DOWN; - if (slave->link_failure_count < UINT_MAX) { - slave->link_failure_count++; - } + if (bond->kill_timers) + goto out; - bond_set_slave_inactive_flags(slave); + delta_in_ticks = msecs_to_jiffies(bond->params.arp_interval); - printk(KERN_INFO DRV_NAME - ": %s: backup interface %s is " - "now down.\n", - bond->dev->name, - slave->dev->name); - } - } - } + if (bond->slave_cnt == 0) + goto re_arm; + + if (bond->send_grat_arp) { + read_lock(&bond->curr_slave_lock); + bond_send_gratuitous_arp(bond); + read_unlock(&bond->curr_slave_lock); + } + + if (bond->send_unsol_na) { + read_lock(&bond->curr_slave_lock); + bond_send_unsolicited_na(bond); + read_unlock(&bond->curr_slave_lock); + } + + if (bond_ab_arp_inspect(bond, delta_in_ticks)) { + read_unlock(&bond->lock); + rtnl_lock(); + read_lock(&bond->lock); + + bond_ab_arp_commit(bond, delta_in_ticks); + + read_unlock(&bond->lock); + rtnl_unlock(); + read_lock(&bond->lock); } + bond_ab_arp_probe(bond); + re_arm: - if (bond->params.arp_interval) { + if (bond->params.arp_interval) queue_delayed_work(bond->wq, &bond->arp_work, delta_in_ticks); - } out: read_unlock(&bond->lock); } @@ -3068,9 +3167,9 @@ out: #ifdef CONFIG_PROC_FS -#define SEQ_START_TOKEN ((void *)1) - static void *bond_info_seq_start(struct seq_file *seq, loff_t *pos) + __acquires(&dev_base_lock) + __acquires(&bond->lock) { struct bonding *bond = seq->private; loff_t off = 0; @@ -3081,14 +3180,12 @@ static void *bond_info_seq_start(struct seq_file *seq, loff_t *pos) read_lock(&dev_base_lock); read_lock(&bond->lock); - if (*pos == 0) { + if (*pos == 0) return SEQ_START_TOKEN; - } bond_for_each_slave(bond, slave, i) { - if (++off == *pos) { + if (++off == *pos) return slave; - } } return NULL; @@ -3100,9 +3197,8 @@ static void *bond_info_seq_next(struct seq_file *seq, void *v, loff_t *pos) struct slave *slave = v; ++*pos; - if (v == SEQ_START_TOKEN) { + if (v == SEQ_START_TOKEN) return bond->first_slave; - } slave = slave->next; @@ -3110,6 +3206,8 @@ static void *bond_info_seq_next(struct seq_file *seq, void *v, loff_t *pos) } static void bond_info_seq_stop(struct seq_file *seq, void *v) + __releases(&bond->lock) + __releases(&dev_base_lock) { struct bonding *bond = seq->private; @@ -3122,7 +3220,6 @@ static void bond_info_show_master(struct seq_file *seq) struct bonding *bond = seq->private; struct slave *curr; int i; - u32 target; read_lock(&bond->curr_slave_lock); curr = bond->curr_active_slave; @@ -3133,7 +3230,8 @@ static void bond_info_show_master(struct seq_file *seq) if (bond->params.mode == BOND_MODE_ACTIVEBACKUP && bond->params.fail_over_mac) - seq_printf(seq, " (fail_over_mac)"); + seq_printf(seq, " (fail_over_mac %s)", + fail_over_mac_tbl[bond->params.fail_over_mac].modename); seq_printf(seq, "\n"); @@ -3163,20 +3261,19 @@ static void bond_info_show_master(struct seq_file *seq) /* ARP information */ - if(bond->params.arp_interval > 0) { - int printed=0; + if (bond->params.arp_interval > 0) { + int printed = 0; seq_printf(seq, "ARP Polling Interval (ms): %d\n", bond->params.arp_interval); seq_printf(seq, "ARP IP target/s (n.n.n.n form):"); - for(i = 0; (i < BOND_MAX_ARP_TARGETS) ;i++) { + for (i = 0; (i < BOND_MAX_ARP_TARGETS); i++) { if (!bond->params.arp_targets[i]) - continue; + break; if (printed) seq_printf(seq, ","); - target = ntohl(bond->params.arp_targets[i]); - seq_printf(seq, " %d.%d.%d.%d", HIPQUAD(target)); + seq_printf(seq, " %pI4", &bond->params.arp_targets[i]); printed = 1; } seq_printf(seq, "\n"); @@ -3184,11 +3281,12 @@ static void bond_info_show_master(struct seq_file *seq) if (bond->params.mode == BOND_MODE_8023AD) { struct ad_info ad_info; - DECLARE_MAC_BUF(mac); seq_puts(seq, "\n802.3ad info\n"); seq_printf(seq, "LACP rate: %s\n", (bond->params.lacp_fast) ? "fast" : "slow"); + seq_printf(seq, "Aggregator selection policy (ad_select): %s\n", + ad_select_tbl[bond->params.ad_select].modename); if (bond_3ad_get_active_agg_info(bond, &ad_info)) { seq_printf(seq, "bond %s has no active aggregator\n", @@ -3204,16 +3302,16 @@ static void bond_info_show_master(struct seq_file *seq) ad_info.actor_key); seq_printf(seq, "\tPartner Key: %d\n", ad_info.partner_key); - seq_printf(seq, "\tPartner Mac Address: %s\n", - print_mac(mac, ad_info.partner_system)); + seq_printf(seq, "\tPartner Mac Address: %pM\n", + ad_info.partner_system); } } } -static void bond_info_show_slave(struct seq_file *seq, const struct slave *slave) +static void bond_info_show_slave(struct seq_file *seq, + const struct slave *slave) { struct bonding *bond = seq->private; - DECLARE_MAC_BUF(mac); seq_printf(seq, "\nSlave Interface: %s\n", slave->dev->name); seq_printf(seq, "MII Status: %s\n", @@ -3221,20 +3319,17 @@ static void bond_info_show_slave(struct seq_file *seq, const struct slave *slave seq_printf(seq, "Link Failure Count: %u\n", slave->link_failure_count); - seq_printf(seq, - "Permanent HW addr: %s\n", - print_mac(mac, slave->perm_hwaddr)); + seq_printf(seq, "Permanent HW addr: %pM\n", slave->perm_hwaddr); if (bond->params.mode == BOND_MODE_8023AD) { const struct aggregator *agg = SLAVE_AD_INFO(slave).port.aggregator; - if (agg) { + if (agg) seq_printf(seq, "Aggregator ID: %d\n", agg->aggregator_identifier); - } else { + else seq_puts(seq, "Aggregator ID: N/A\n"); - } } } @@ -3243,14 +3338,13 @@ static int bond_info_seq_show(struct seq_file *seq, void *v) if (v == SEQ_START_TOKEN) { seq_printf(seq, "%s\n", version); bond_info_show_master(seq); - } else { + } else bond_info_show_slave(seq, v); - } return 0; } -static struct seq_operations bond_info_seq_ops = { +static const struct seq_operations bond_info_seq_ops = { .start = bond_info_seq_start, .next = bond_info_seq_next, .stop = bond_info_seq_stop, @@ -3287,19 +3381,15 @@ static int bond_create_proc_entry(struct bonding *bond) struct net_device *bond_dev = bond->dev; if (bond_proc_dir) { - bond->proc_entry = create_proc_entry(bond_dev->name, - S_IRUGO, - bond_proc_dir); - if (bond->proc_entry == NULL) { - printk(KERN_WARNING DRV_NAME + bond->proc_entry = proc_create_data(bond_dev->name, + S_IRUGO, bond_proc_dir, + &bond_info_fops, bond); + if (bond->proc_entry == NULL) + pr_warning(DRV_NAME ": Warning: Cannot create /proc/net/%s/%s\n", DRV_NAME, bond_dev->name); - } else { - bond->proc_entry->data = bond; - bond->proc_entry->proc_fops = &bond_info_fops; - bond->proc_entry->owner = THIS_MODULE; + else memcpy(bond->proc_file_name, bond_dev->name, IFNAMSIZ); - } } return 0; @@ -3319,58 +3409,47 @@ static void bond_remove_proc_entry(struct bonding *bond) */ static void bond_create_proc_dir(void) { - int len = strlen(DRV_NAME); - - for (bond_proc_dir = init_net.proc_net->subdir; bond_proc_dir; - bond_proc_dir = bond_proc_dir->next) { - if ((bond_proc_dir->namelen == len) && - !memcmp(bond_proc_dir->name, DRV_NAME, len)) { - break; - } - } - if (!bond_proc_dir) { bond_proc_dir = proc_mkdir(DRV_NAME, init_net.proc_net); - if (bond_proc_dir) { - bond_proc_dir->owner = THIS_MODULE; - } else { - printk(KERN_WARNING DRV_NAME + if (!bond_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) +/* Destroy the bonding directory under /proc/net, if empty. + * Caller must hold rtnl_lock. + */ +static void bond_destroy_proc_dir(void) +{ + if (bond_proc_dir) { + remove_proc_entry(DRV_NAME, init_net.proc_net); + bond_proc_dir = NULL; + } +} + +#else /* !CONFIG_PROC_FS */ + +static int bond_create_proc_entry(struct bonding *bond) { - struct proc_dir_entry *de; +} - if (!bond_proc_dir) { - return; - } +static void bond_remove_proc_entry(struct bonding *bond) +{ +} - /* verify that the /proc dir is empty */ - for (de = bond_proc_dir->subdir; de; de = de->next) { - /* ignore . and .. */ - if (*(de->name) != '.') { - break; - } - } +static void bond_create_proc_dir(void) +{ +} - if (de) { - if (bond_proc_dir->owner == THIS_MODULE) { - bond_proc_dir->owner = NULL; - } - } else { - remove_proc_entry(DRV_NAME, init_net.proc_net); - bond_proc_dir = NULL; - } +static void bond_destroy_proc_dir(void) +{ } + #endif /* CONFIG_PROC_FS */ + /*-------------------------- netdev event handling --------------------------*/ /* @@ -3378,20 +3457,19 @@ static void bond_destroy_proc_dir(void) */ static int bond_event_changename(struct bonding *bond) { -#ifdef CONFIG_PROC_FS bond_remove_proc_entry(bond); bond_create_proc_entry(bond); -#endif - down_write(&(bonding_rwsem)); - bond_destroy_sysfs_entry(bond); - bond_create_sysfs_entry(bond); - up_write(&(bonding_rwsem)); + + bond_destroy_sysfs_entry(bond); + bond_create_sysfs_entry(bond); + return NOTIFY_DONE; } -static int bond_master_netdev_event(unsigned long event, struct net_device *bond_dev) +static int bond_master_netdev_event(unsigned long event, + struct net_device *bond_dev) { - struct bonding *event_bond = bond_dev->priv; + struct bonding *event_bond = netdev_priv(bond_dev); switch (event) { case NETDEV_CHANGENAME: @@ -3406,10 +3484,11 @@ static int bond_master_netdev_event(unsigned long event, struct net_device *bond return NOTIFY_DONE; } -static int bond_slave_netdev_event(unsigned long event, struct net_device *slave_dev) +static int bond_slave_netdev_event(unsigned long event, + struct net_device *slave_dev) { struct net_device *bond_dev = slave_dev->master; - struct bonding *bond = bond_dev->priv; + struct bonding *bond = netdev_priv(bond_dev); switch (event) { case NETDEV_UNREGISTER: @@ -3421,11 +3500,26 @@ static int bond_slave_netdev_event(unsigned long event, struct net_device *slave } break; case NETDEV_CHANGE: - /* - * TODO: is this what we get if somebody - * sets up a hierarchical bond, then rmmod's - * one of the slave bonding devices? - */ + if (bond->params.mode == BOND_MODE_8023AD || bond_is_lb(bond)) { + struct slave *slave; + + slave = bond_get_slave_by_dev(bond, slave_dev); + if (slave) { + u16 old_speed = slave->speed; + u16 old_duplex = slave->duplex; + + bond_update_speed_duplex(slave); + + if (bond_is_lb(bond)) + break; + + if (old_speed != slave->speed) + bond_3ad_adapter_speed_changed(slave); + if (old_duplex != slave->duplex) + bond_3ad_adapter_duplex_changed(slave); + } + } + break; case NETDEV_DOWN: /* @@ -3469,14 +3563,15 @@ static int bond_slave_netdev_event(unsigned long event, struct net_device *slave * locks for us to safely manipulate the slave devices (RTNL lock, * dev_probe_lock). */ -static int bond_netdev_event(struct notifier_block *this, unsigned long event, void *ptr) +static int bond_netdev_event(struct notifier_block *this, + unsigned long event, void *ptr) { struct net_device *event_dev = (struct net_device *)ptr; - if (event_dev->nd_net != &init_net) + if (dev_net(event_dev) != &init_net) return NOTIFY_DONE; - dprintk("event_dev: %s, event: %lx\n", + pr_debug("event_dev: %s, event: %lx\n", (event_dev ? event_dev->name : "None"), event); @@ -3484,12 +3579,12 @@ static int bond_netdev_event(struct notifier_block *this, unsigned long event, v return NOTIFY_DONE; if (event_dev->flags & IFF_MASTER) { - dprintk("IFF_MASTER\n"); + pr_debug("IFF_MASTER\n"); return bond_master_netdev_event(event, event_dev); } if (event_dev->flags & IFF_SLAVE) { - dprintk("IFF_SLAVE\n"); + pr_debug("IFF_SLAVE\n"); return bond_slave_netdev_event(event, event_dev); } @@ -3508,10 +3603,13 @@ static int bond_inetaddr_event(struct notifier_block *this, unsigned long event, { struct in_ifaddr *ifa = ptr; struct net_device *vlan_dev, *event_dev = ifa->ifa_dev->dev; - struct bonding *bond, *bond_next; - struct vlan_entry *vlan, *vlan_next; + struct bonding *bond; + struct vlan_entry *vlan; + + if (dev_net(ifa->ifa_dev->dev) != &init_net) + return NOTIFY_DONE; - list_for_each_entry_safe(bond, bond_next, &bond_dev_list, bond_list) { + list_for_each_entry(bond, &bond_dev_list, bond_list) { if (bond->dev == event_dev) { switch (event) { case NETDEV_UP: @@ -3525,11 +3623,7 @@ static int bond_inetaddr_event(struct notifier_block *this, unsigned long event, } } - if (list_empty(&bond->vlan_list)) - continue; - - list_for_each_entry_safe(vlan, vlan_next, &bond->vlan_list, - vlan_list) { + list_for_each_entry(vlan, &bond->vlan_list, vlan_list) { vlan_dev = vlan_group_get_device(bond->vlgrp, vlan->vlan_id); if (vlan_dev == event_dev) { switch (event) { @@ -3611,7 +3705,7 @@ static int bond_xmit_hash_policy_l23(struct sk_buff *skb, struct ethhdr *data = (struct ethhdr *)skb->data; struct iphdr *iph = ip_hdr(skb); - if (skb->protocol == __constant_htons(ETH_P_IP)) { + if (skb->protocol == htons(ETH_P_IP)) { return ((ntohl(iph->saddr ^ iph->daddr) & 0xffff) ^ (data->h_dest[5] ^ bond_dev->dev_addr[5])) % count; } @@ -3632,8 +3726,8 @@ static int bond_xmit_hash_policy_l34(struct sk_buff *skb, __be16 *layer4hdr = (__be16 *)((u32 *)iph + iph->ihl); int layer4_xor = 0; - if (skb->protocol == __constant_htons(ETH_P_IP)) { - if (!(iph->frag_off & __constant_htons(IP_MF|IP_OFFSET)) && + if (skb->protocol == htons(ETH_P_IP)) { + if (!(iph->frag_off & htons(IP_MF|IP_OFFSET)) && (iph->protocol == IPPROTO_TCP || iph->protocol == IPPROTO_UDP)) { layer4_xor = ntohs((*layer4hdr ^ *(layer4hdr + 1))); @@ -3661,12 +3755,11 @@ static int bond_xmit_hash_policy_l2(struct sk_buff *skb, static int bond_open(struct net_device *bond_dev) { - struct bonding *bond = bond_dev->priv; + struct bonding *bond = netdev_priv(bond_dev); bond->kill_timers = 0; - if ((bond->params.mode == BOND_MODE_TLB) || - (bond->params.mode == BOND_MODE_ALB)) { + if (bond_is_lb(bond)) { /* bond_alb_initialize must be called before the timer * is started. */ @@ -3702,6 +3795,7 @@ static int bond_open(struct net_device *bond_dev) queue_delayed_work(bond->wq, &bond->ad_work, 0); /* register to receive LACPDUs */ bond_register_lacpdu(bond); + bond_3ad_initiate_agg_selection(bond, 1); } return 0; @@ -3709,7 +3803,7 @@ static int bond_open(struct net_device *bond_dev) static int bond_close(struct net_device *bond_dev) { - struct bonding *bond = bond_dev->priv; + struct bonding *bond = netdev_priv(bond_dev); if (bond->params.mode == BOND_MODE_8023AD) { /* Unregister the receive of LACPDUs */ @@ -3721,6 +3815,8 @@ static int bond_close(struct net_device *bond_dev) write_lock_bh(&bond->lock); + bond->send_grat_arp = 0; + bond->send_unsol_na = 0; /* signal timers not to re-arm */ bond->kill_timers = 1; @@ -3748,8 +3844,7 @@ static int bond_close(struct net_device *bond_dev) } - if ((bond->params.mode == BOND_MODE_TLB) || - (bond->params.mode == BOND_MODE_ALB)) { + if (bond_is_lb(bond)) { /* Must be called only after all * slaves have been released */ @@ -3761,8 +3856,8 @@ static int bond_close(struct net_device *bond_dev) static struct net_device_stats *bond_get_stats(struct net_device *bond_dev) { - struct bonding *bond = bond_dev->priv; - struct net_device_stats *stats = &(bond->stats), *sstats; + struct bonding *bond = netdev_priv(bond_dev); + struct net_device_stats *stats = &bond->stats; struct net_device_stats local_stats; struct slave *slave; int i; @@ -3772,7 +3867,8 @@ static struct net_device_stats *bond_get_stats(struct net_device *bond_dev) read_lock_bh(&bond->lock); bond_for_each_slave(bond, slave, i) { - sstats = slave->dev->get_stats(slave->dev); + const struct net_device_stats *sstats = dev_get_stats(slave->dev); + local_stats.rx_packets += sstats->rx_packets; local_stats.rx_bytes += sstats->rx_bytes; local_stats.rx_errors += sstats->rx_errors; @@ -3817,15 +3913,15 @@ static int bond_do_ioctl(struct net_device *bond_dev, struct ifreq *ifr, int cmd struct mii_ioctl_data *mii = NULL; int res = 0; - dprintk("bond_ioctl: master=%s, cmd=%d\n", + pr_debug("bond_ioctl: master=%s, cmd=%d\n", bond_dev->name, cmd); switch (cmd) { case SIOCGMIIPHY: mii = if_mii(ifr); - if (!mii) { + if (!mii) return -EINVAL; - } + mii->phy_id = 0; /* Fall Through */ case SIOCGMIIREG: @@ -3834,18 +3930,18 @@ static int bond_do_ioctl(struct net_device *bond_dev, struct ifreq *ifr, int cmd * instead of SIOCGMIIPHY. */ mii = if_mii(ifr); - if (!mii) { + if (!mii) return -EINVAL; - } + if (mii->reg_num == 1) { - struct bonding *bond = bond_dev->priv; + struct bonding *bond = netdev_priv(bond_dev); mii->val_out = 0; read_lock(&bond->lock); read_lock(&bond->curr_slave_lock); - if (netif_carrier_ok(bond->dev)) { + if (netif_carrier_ok(bond->dev)) mii->val_out = BMSR_LSTATUS; - } + read_unlock(&bond->curr_slave_lock); read_unlock(&bond->lock); } @@ -3855,32 +3951,26 @@ static int bond_do_ioctl(struct net_device *bond_dev, struct ifreq *ifr, int cmd case SIOCBONDINFOQUERY: u_binfo = (struct ifbond __user *)ifr->ifr_data; - if (copy_from_user(&k_binfo, u_binfo, sizeof(ifbond))) { + if (copy_from_user(&k_binfo, u_binfo, sizeof(ifbond))) return -EFAULT; - } res = bond_info_query(bond_dev, &k_binfo); - if (res == 0) { - if (copy_to_user(u_binfo, &k_binfo, sizeof(ifbond))) { - return -EFAULT; - } - } + if (res == 0 && + copy_to_user(u_binfo, &k_binfo, sizeof(ifbond))) + return -EFAULT; return res; case BOND_SLAVE_INFO_QUERY_OLD: case SIOCBONDSLAVEINFOQUERY: u_sinfo = (struct ifslave __user *)ifr->ifr_data; - if (copy_from_user(&k_sinfo, u_sinfo, sizeof(ifslave))) { + if (copy_from_user(&k_sinfo, u_sinfo, sizeof(ifslave))) return -EFAULT; - } res = bond_slave_info_query(bond_dev, &k_sinfo); - if (res == 0) { - if (copy_to_user(u_sinfo, &k_sinfo, sizeof(ifslave))) { - return -EFAULT; - } - } + if (res == 0 && + copy_to_user(u_sinfo, &k_sinfo, sizeof(ifslave))) + return -EFAULT; return res; default: @@ -3888,19 +3978,17 @@ static int bond_do_ioctl(struct net_device *bond_dev, struct ifreq *ifr, int cmd break; } - if (!capable(CAP_NET_ADMIN)) { + if (!capable(CAP_NET_ADMIN)) return -EPERM; - } - down_write(&(bonding_rwsem)); slave_dev = dev_get_by_name(&init_net, ifr->ifr_slave); - dprintk("slave_dev=%p: \n", slave_dev); + pr_debug("slave_dev=%p: \n", slave_dev); - if (!slave_dev) { + if (!slave_dev) res = -ENODEV; - } else { - dprintk("slave_dev->name=%s: \n", slave_dev->name); + else { + pr_debug("slave_dev->name=%s: \n", slave_dev->name); switch (cmd) { case BOND_ENSLAVE_OLD: case SIOCBONDENSLAVE: @@ -3925,34 +4013,41 @@ static int bond_do_ioctl(struct net_device *bond_dev, struct ifreq *ifr, int cmd dev_put(slave_dev); } - up_write(&(bonding_rwsem)); return res; } static void bond_set_multicast_list(struct net_device *bond_dev) { - struct bonding *bond = bond_dev->priv; + struct bonding *bond = netdev_priv(bond_dev); struct dev_mc_list *dmi; /* * Do promisc before checking multicast_mode */ - if ((bond_dev->flags & IFF_PROMISC) && !(bond->flags & IFF_PROMISC)) { + if ((bond_dev->flags & IFF_PROMISC) && !(bond->flags & IFF_PROMISC)) + /* + * FIXME: Need to handle the error when one of the multi-slaves + * encounters error. + */ bond_set_promiscuity(bond, 1); - } - if (!(bond_dev->flags & IFF_PROMISC) && (bond->flags & IFF_PROMISC)) { + + if (!(bond_dev->flags & IFF_PROMISC) && (bond->flags & IFF_PROMISC)) bond_set_promiscuity(bond, -1); - } + /* set allmulti flag to slaves */ - if ((bond_dev->flags & IFF_ALLMULTI) && !(bond->flags & IFF_ALLMULTI)) { + if ((bond_dev->flags & IFF_ALLMULTI) && !(bond->flags & IFF_ALLMULTI)) + /* + * FIXME: Need to handle the error when one of the multi-slaves + * encounters error. + */ bond_set_allmulti(bond, 1); - } - if (!(bond_dev->flags & IFF_ALLMULTI) && (bond->flags & IFF_ALLMULTI)) { + + if (!(bond_dev->flags & IFF_ALLMULTI) && (bond->flags & IFF_ALLMULTI)) bond_set_allmulti(bond, -1); - } + read_lock(&bond->lock); @@ -3960,16 +4055,14 @@ static void bond_set_multicast_list(struct net_device *bond_dev) /* looking for addresses to add to slaves' mc list */ for (dmi = bond_dev->mc_list; dmi; dmi = dmi->next) { - if (!bond_mc_list_find_dmi(dmi, bond->mc_list)) { + if (!bond_mc_list_find_dmi(dmi, bond->mc_list)) bond_mc_add(bond, dmi->dmi_addr, dmi->dmi_addrlen); - } } /* looking for addresses to delete from slaves' list */ for (dmi = bond->mc_list; dmi; dmi = dmi->next) { - if (!bond_mc_list_find_dmi(dmi, bond_dev->mc_list)) { + if (!bond_mc_list_find_dmi(dmi, bond_dev->mc_list)) bond_mc_delete(bond, dmi->dmi_addr, dmi->dmi_addrlen); - } } /* save master's multicast list */ @@ -3979,17 +4072,31 @@ static void bond_set_multicast_list(struct net_device *bond_dev) read_unlock(&bond->lock); } +static int bond_neigh_setup(struct net_device *dev, struct neigh_parms *parms) +{ + struct bonding *bond = netdev_priv(dev); + struct slave *slave = bond->first_slave; + + if (slave) { + const struct net_device_ops *slave_ops + = slave->dev->netdev_ops; + if (slave_ops->ndo_neigh_setup) + return slave_ops->ndo_neigh_setup(slave->dev, parms); + } + return 0; +} + /* * Change the MTU of all of a master's slaves to match the master */ static int bond_change_mtu(struct net_device *bond_dev, int new_mtu) { - struct bonding *bond = bond_dev->priv; + struct bonding *bond = netdev_priv(bond_dev); struct slave *slave, *stop_at; int res = 0; int i; - dprintk("bond=%p, name=%s, new_mtu=%d\n", bond, + pr_debug("bond=%p, name=%s, new_mtu=%d\n", bond, (bond_dev ? bond_dev->name : "None"), new_mtu); /* Can't hold bond->lock with bh disabled here since @@ -4008,8 +4115,8 @@ static int bond_change_mtu(struct net_device *bond_dev, int new_mtu) */ bond_for_each_slave(bond, slave, i) { - dprintk("s %p s->p %p c_m %p\n", slave, - slave->prev, slave->dev->change_mtu); + pr_debug("s %p s->p %p c_m %p\n", slave, + slave->prev, slave->dev->netdev_ops->ndo_change_mtu); res = dev_set_mtu(slave->dev, new_mtu); @@ -4022,7 +4129,7 @@ static int bond_change_mtu(struct net_device *bond_dev, int new_mtu) * means changing their mtu from timer context, which * is probably not a good idea. */ - dprintk("err %d %s\n", res, slave->dev->name); + pr_debug("err %d %s\n", res, slave->dev->name); goto unwind; } } @@ -4039,7 +4146,7 @@ unwind: tmp_res = dev_set_mtu(slave->dev, bond_dev->mtu); if (tmp_res) { - dprintk("unwind err %d dev %s\n", tmp_res, + pr_debug("unwind err %d dev %s\n", tmp_res, slave->dev->name); } } @@ -4056,24 +4163,27 @@ unwind: */ static int bond_set_mac_address(struct net_device *bond_dev, void *addr) { - struct bonding *bond = bond_dev->priv; + struct bonding *bond = netdev_priv(bond_dev); struct sockaddr *sa = addr, tmp_sa; struct slave *slave, *stop_at; int res = 0; int i; - dprintk("bond=%p, name=%s\n", bond, (bond_dev ? bond_dev->name : "None")); + if (bond->params.mode == BOND_MODE_ALB) + return bond_alb_set_mac_address(bond_dev, addr); + + + pr_debug("bond=%p, name=%s\n", bond, (bond_dev ? bond_dev->name : "None")); /* - * If fail_over_mac is enabled, do nothing and return success. - * Returning an error causes ifenslave to fail. + * If fail_over_mac is set to active, do nothing and return + * success. Returning an error causes ifenslave to fail. */ - if (bond->params.fail_over_mac) + if (bond->params.fail_over_mac == BOND_FOM_ACTIVE) return 0; - if (!is_valid_ether_addr(sa->sa_data)) { + if (!is_valid_ether_addr(sa->sa_data)) return -EADDRNOTAVAIL; - } /* Can't hold bond->lock with bh disabled here since * some base drivers panic. On the other hand we can't @@ -4091,11 +4201,12 @@ static int bond_set_mac_address(struct net_device *bond_dev, void *addr) */ bond_for_each_slave(bond, slave, i) { - dprintk("slave %p %s\n", slave, slave->dev->name); + const struct net_device_ops *slave_ops = slave->dev->netdev_ops; + pr_debug("slave %p %s\n", slave, slave->dev->name); - if (slave->dev->set_mac_address == NULL) { + if (slave_ops->ndo_set_mac_address == NULL) { res = -EOPNOTSUPP; - dprintk("EOPNOTSUPP %s\n", slave->dev->name); + pr_debug("EOPNOTSUPP %s\n", slave->dev->name); goto unwind; } @@ -4107,7 +4218,7 @@ static int bond_set_mac_address(struct net_device *bond_dev, void *addr) * breakage anyway until ARP finish * updating, so... */ - dprintk("err %d %s\n", res, slave->dev->name); + pr_debug("err %d %s\n", res, slave->dev->name); goto unwind; } } @@ -4127,7 +4238,7 @@ unwind: tmp_res = dev_set_mac_address(slave->dev, &tmp_sa); if (tmp_res) { - dprintk("unwind err %d dev %s\n", tmp_res, + pr_debug("unwind err %d dev %s\n", tmp_res, slave->dev->name); } } @@ -4137,15 +4248,14 @@ unwind: static int bond_xmit_roundrobin(struct sk_buff *skb, struct net_device *bond_dev) { - struct bonding *bond = bond_dev->priv; + struct bonding *bond = netdev_priv(bond_dev); struct slave *slave, *start_at; int i, slave_no, res = 1; read_lock(&bond->lock); - if (!BOND_IS_OK(bond)) { + if (!BOND_IS_OK(bond)) goto out; - } /* * Concurrent TX may collide on rr_tx_counter; we accept that @@ -4155,9 +4265,8 @@ static int bond_xmit_roundrobin(struct sk_buff *skb, struct net_device *bond_dev bond_for_each_slave(bond, slave, i) { slave_no--; - if (slave_no < 0) { + if (slave_no < 0) break; - } } start_at = slave; @@ -4186,15 +4295,14 @@ out: */ static int bond_xmit_activebackup(struct sk_buff *skb, struct net_device *bond_dev) { - struct bonding *bond = bond_dev->priv; + struct bonding *bond = netdev_priv(bond_dev); int res = 1; read_lock(&bond->lock); read_lock(&bond->curr_slave_lock); - if (!BOND_IS_OK(bond)) { + if (!BOND_IS_OK(bond)) goto out; - } if (!bond->curr_active_slave) goto out; @@ -4202,10 +4310,10 @@ static int bond_xmit_activebackup(struct sk_buff *skb, struct net_device *bond_d res = bond_dev_queue_xmit(bond, skb, bond->curr_active_slave->dev); out: - if (res) { + if (res) /* no suitable interface, frame not sent */ dev_kfree_skb(skb); - } + read_unlock(&bond->curr_slave_lock); read_unlock(&bond->lock); return 0; @@ -4218,7 +4326,7 @@ out: */ static int bond_xmit_xor(struct sk_buff *skb, struct net_device *bond_dev) { - struct bonding *bond = bond_dev->priv; + struct bonding *bond = netdev_priv(bond_dev); struct slave *slave, *start_at; int slave_no; int i; @@ -4226,17 +4334,15 @@ static int bond_xmit_xor(struct sk_buff *skb, struct net_device *bond_dev) read_lock(&bond->lock); - if (!BOND_IS_OK(bond)) { + if (!BOND_IS_OK(bond)) goto out; - } slave_no = bond->xmit_hash_policy(skb, bond_dev, bond->slave_cnt); bond_for_each_slave(bond, slave, i) { slave_no--; - if (slave_no < 0) { + if (slave_no < 0) break; - } } start_at = slave; @@ -4264,7 +4370,7 @@ out: */ static int bond_xmit_broadcast(struct sk_buff *skb, struct net_device *bond_dev) { - struct bonding *bond = bond_dev->priv; + struct bonding *bond = netdev_priv(bond_dev); struct slave *slave, *start_at; struct net_device *tx_dev = NULL; int i; @@ -4272,17 +4378,15 @@ static int bond_xmit_broadcast(struct sk_buff *skb, struct net_device *bond_dev) read_lock(&bond->lock); - if (!BOND_IS_OK(bond)) { + if (!BOND_IS_OK(bond)) goto out; - } read_lock(&bond->curr_slave_lock); start_at = bond->curr_active_slave; read_unlock(&bond->curr_slave_lock); - if (!start_at) { + if (!start_at) goto out; - } bond_for_each_slave_from(bond, slave, i, start_at) { if (IS_UP(slave->dev) && @@ -4291,7 +4395,7 @@ static int bond_xmit_broadcast(struct sk_buff *skb, struct net_device *bond_dev) if (tx_dev) { struct sk_buff *skb2 = skb_clone(skb, GFP_ATOMIC); if (!skb2) { - printk(KERN_ERR DRV_NAME + pr_err(DRV_NAME ": %s: Error: bond_xmit_broadcast(): " "skb_clone() failed\n", bond_dev->name); @@ -4308,15 +4412,14 @@ static int bond_xmit_broadcast(struct sk_buff *skb, struct net_device *bond_dev) } } - if (tx_dev) { + if (tx_dev) res = bond_dev_queue_xmit(bond, skb, tx_dev); - } out: - if (res) { + if (res) /* no suitable interface, frame not sent */ dev_kfree_skb(skb); - } + /* frame sent to all suitable interfaces */ read_unlock(&bond->lock); return 0; @@ -4340,6 +4443,35 @@ static void bond_set_xmit_hash_policy(struct bonding *bond) } } +static int bond_start_xmit(struct sk_buff *skb, struct net_device *dev) +{ + const struct bonding *bond = netdev_priv(dev); + + switch (bond->params.mode) { + case BOND_MODE_ROUNDROBIN: + return bond_xmit_roundrobin(skb, dev); + case BOND_MODE_ACTIVEBACKUP: + return bond_xmit_activebackup(skb, dev); + case BOND_MODE_XOR: + return bond_xmit_xor(skb, dev); + case BOND_MODE_BROADCAST: + return bond_xmit_broadcast(skb, dev); + case BOND_MODE_8023AD: + return bond_3ad_xmit_xor(skb, dev); + case BOND_MODE_ALB: + case BOND_MODE_TLB: + return bond_alb_xmit(skb, dev); + default: + /* Should never happen, mode already checked */ + pr_err(DRV_NAME ": %s: Error: Unknown bonding mode %d\n", + dev->name, bond->params.mode); + WARN_ON_ONCE(1); + dev_kfree_skb(skb); + return NETDEV_TX_OK; + } +} + + /* * set bond mode specific net device operations */ @@ -4349,33 +4481,26 @@ void bond_set_mode_ops(struct bonding *bond, int mode) switch (mode) { case BOND_MODE_ROUNDROBIN: - bond_dev->hard_start_xmit = bond_xmit_roundrobin; break; case BOND_MODE_ACTIVEBACKUP: - bond_dev->hard_start_xmit = bond_xmit_activebackup; break; case BOND_MODE_XOR: - bond_dev->hard_start_xmit = bond_xmit_xor; bond_set_xmit_hash_policy(bond); break; case BOND_MODE_BROADCAST: - bond_dev->hard_start_xmit = bond_xmit_broadcast; break; case BOND_MODE_8023AD: bond_set_master_3ad_flags(bond); - bond_dev->hard_start_xmit = bond_3ad_xmit_xor; bond_set_xmit_hash_policy(bond); break; case BOND_MODE_ALB: bond_set_master_alb_flags(bond); /* FALLTHRU */ case BOND_MODE_TLB: - bond_dev->hard_start_xmit = bond_alb_xmit; - bond_dev->set_mac_address = bond_alb_set_mac_address; break; default: /* Should never happen, mode already checked */ - printk(KERN_ERR DRV_NAME + pr_err(DRV_NAME ": %s: Error: Unknown bonding mode %d\n", bond_dev->name, mode); @@ -4393,49 +4518,49 @@ static void bond_ethtool_get_drvinfo(struct net_device *bond_dev, static const struct ethtool_ops bond_ethtool_ops = { .get_drvinfo = bond_ethtool_get_drvinfo, + .get_link = ethtool_op_get_link, + .get_tx_csum = ethtool_op_get_tx_csum, + .get_sg = ethtool_op_get_sg, + .get_tso = ethtool_op_get_tso, + .get_ufo = ethtool_op_get_ufo, + .get_flags = ethtool_op_get_flags, }; -/* - * Does not allocate but creates a /proc entry. - * Allowed to fail. - */ -static int bond_init(struct net_device *bond_dev, struct bond_params *params) -{ - struct bonding *bond = bond_dev->priv; +static const struct net_device_ops bond_netdev_ops = { + .ndo_init = bond_init, + .ndo_uninit = bond_uninit, + .ndo_open = bond_open, + .ndo_stop = bond_close, + .ndo_start_xmit = bond_start_xmit, + .ndo_get_stats = bond_get_stats, + .ndo_do_ioctl = bond_do_ioctl, + .ndo_set_multicast_list = bond_set_multicast_list, + .ndo_change_mtu = bond_change_mtu, + .ndo_set_mac_address = bond_set_mac_address, + .ndo_neigh_setup = bond_neigh_setup, + .ndo_vlan_rx_register = bond_vlan_rx_register, + .ndo_vlan_rx_add_vid = bond_vlan_rx_add_vid, + .ndo_vlan_rx_kill_vid = bond_vlan_rx_kill_vid, +}; - dprintk("Begin bond_init for %s\n", bond_dev->name); +static void bond_setup(struct net_device *bond_dev) +{ + struct bonding *bond = netdev_priv(bond_dev); /* initialize rwlocks */ rwlock_init(&bond->lock); rwlock_init(&bond->curr_slave_lock); - bond->params = *params; /* copy params struct */ - - bond->wq = create_singlethread_workqueue(bond_dev->name); - if (!bond->wq) - return -ENOMEM; + bond->params = bonding_defaults; /* Initialize pointers */ - bond->first_slave = NULL; - bond->curr_active_slave = NULL; - bond->current_arp_slave = NULL; - bond->primary_slave = NULL; bond->dev = bond_dev; - bond->send_grat_arp = 0; - bond->setup_by_slave = 0; INIT_LIST_HEAD(&bond->vlan_list); /* Initialize the device entry points */ - bond_dev->open = bond_open; - bond_dev->stop = bond_close; - bond_dev->get_stats = bond_get_stats; - bond_dev->do_ioctl = bond_do_ioctl; + ether_setup(bond_dev); + bond_dev->netdev_ops = &bond_netdev_ops; bond_dev->ethtool_ops = &bond_ethtool_ops; - bond_dev->set_multicast_list = bond_set_multicast_list; - bond_dev->change_mtu = bond_change_mtu; - bond_dev->set_mac_address = bond_set_mac_address; - bond_dev->validate_addr = NULL; - bond_set_mode_ops(bond, bond->params.mode); bond_dev->destructor = free_netdev; @@ -4444,6 +4569,10 @@ static int bond_init(struct net_device *bond_dev, struct bond_params *params) bond_dev->tx_queue_len = 0; bond_dev->flags |= IFF_MASTER|IFF_MULTICAST; bond_dev->priv_flags |= IFF_BONDING; + bond_dev->priv_flags &= ~IFF_XMIT_DST_RELEASE; + + if (bond->params.arp_interval) + bond_dev->priv_flags |= IFF_MASTER_ARPMON; /* At first, we block adding VLANs. That's the only way to * prevent problems that occur when adding VLANs over an @@ -4462,33 +4591,10 @@ static int bond_init(struct net_device *bond_dev, struct bond_params *params) * when there are slaves that are not hw accel * capable */ - bond_dev->vlan_rx_register = bond_vlan_rx_register; - bond_dev->vlan_rx_add_vid = bond_vlan_rx_add_vid; - bond_dev->vlan_rx_kill_vid = bond_vlan_rx_kill_vid; bond_dev->features |= (NETIF_F_HW_VLAN_TX | NETIF_F_HW_VLAN_RX | NETIF_F_HW_VLAN_FILTER); -#ifdef CONFIG_PROC_FS - bond_create_proc_entry(bond); -#endif - list_add_tail(&bond->bond_list, &bond_dev_list); - - return 0; -} - -/* De-initialize device specific data. - * Caller must hold rtnl_lock. - */ -static void bond_deinit(struct net_device *bond_dev) -{ - struct bonding *bond = bond_dev->priv; - - list_del(&bond->bond_list); - -#ifdef CONFIG_PROC_FS - bond_remove_proc_entry(bond); -#endif } static void bond_work_cancel_all(struct bonding *bond) @@ -4512,6 +4618,20 @@ static void bond_work_cancel_all(struct bonding *bond) 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) +{ + struct bonding *bond = netdev_priv(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. */ @@ -4523,18 +4643,12 @@ static void bond_free_all(void) struct net_device *bond_dev = bond->dev; bond_work_cancel_all(bond); - netif_tx_lock_bh(bond_dev); - bond_mc_list_destroy(bond); - netif_tx_unlock_bh(bond_dev); /* Release the bonded slaves */ bond_release_all(bond_dev); - bond_deinit(bond_dev); unregister_netdevice(bond_dev); } -#ifdef CONFIG_PROC_FS bond_destroy_proc_dir(); -#endif } /*------------------------- Module initialization ---------------------------*/ @@ -4545,9 +4659,9 @@ static void bond_free_all(void) * some mode names are substrings of other names, and calls from sysfs * may have whitespace in the name (trailing newlines, for example). */ -int bond_parse_parm(const char *buf, struct bond_parm_tbl *tbl) +int bond_parse_parm(const char *buf, const struct bond_parm_tbl *tbl) { - int mode = -1, i, rv; + int modeint = -1, i, rv; char *p, modestr[BOND_MAX_MODENAME_LEN + 1] = { 0, }; for (p = (char *)buf; *p; p++) @@ -4557,13 +4671,13 @@ int bond_parse_parm(const char *buf, struct bond_parm_tbl *tbl) if (*p) rv = sscanf(buf, "%20s", modestr); else - rv = sscanf(buf, "%d", &mode); + rv = sscanf(buf, "%d", &modeint); if (!rv) return -1; for (i = 0; tbl[i].modename; i++) { - if (mode == tbl[i].mode) + if (modeint == tbl[i].mode) return tbl[i].mode; if (strcmp(modestr, tbl[i].modename) == 0) return tbl[i].mode; @@ -4574,7 +4688,7 @@ int bond_parse_parm(const char *buf, struct bond_parm_tbl *tbl) static int bond_check_params(struct bond_params *params) { - int arp_validate_value; + int arp_validate_value, fail_over_mac_value; /* * Convert string parameters. @@ -4582,7 +4696,7 @@ static int bond_check_params(struct bond_params *params) if (mode) { bond_mode = bond_parse_parm(mode, bond_mode_tbl); if (bond_mode == -1) { - printk(KERN_ERR DRV_NAME + pr_err(DRV_NAME ": Error: Invalid bonding mode \"%s\"\n", mode == NULL ? "NULL" : mode); return -EINVAL; @@ -4592,16 +4706,16 @@ static int bond_check_params(struct bond_params *params) if (xmit_hash_policy) { if ((bond_mode != BOND_MODE_XOR) && (bond_mode != BOND_MODE_8023AD)) { - printk(KERN_INFO DRV_NAME + pr_info(DRV_NAME ": xor_mode param is irrelevant in mode %s\n", bond_mode_name(bond_mode)); } else { xmit_hashtype = bond_parse_parm(xmit_hash_policy, xmit_hashtype_tbl); if (xmit_hashtype == -1) { - printk(KERN_ERR DRV_NAME - ": Error: Invalid xmit_hash_policy \"%s\"\n", - xmit_hash_policy == NULL ? "NULL" : + pr_err(DRV_NAME + ": Error: Invalid xmit_hash_policy \"%s\"\n", + xmit_hash_policy == NULL ? "NULL" : xmit_hash_policy); return -EINVAL; } @@ -4610,13 +4724,13 @@ static int bond_check_params(struct bond_params *params) if (lacp_rate) { if (bond_mode != BOND_MODE_8023AD) { - printk(KERN_INFO DRV_NAME + pr_info(DRV_NAME ": lacp_rate param is irrelevant in mode %s\n", bond_mode_name(bond_mode)); } else { lacp_fast = bond_parse_parm(lacp_rate, bond_lacp_tbl); if (lacp_fast == -1) { - printk(KERN_ERR DRV_NAME + pr_err(DRV_NAME ": Error: Invalid lacp rate \"%s\"\n", lacp_rate == NULL ? "NULL" : lacp_rate); return -EINVAL; @@ -4624,16 +4738,33 @@ static int bond_check_params(struct bond_params *params) } } - if (max_bonds < 1 || max_bonds > INT_MAX) { - printk(KERN_WARNING DRV_NAME + if (ad_select) { + params->ad_select = bond_parse_parm(ad_select, ad_select_tbl); + if (params->ad_select == -1) { + pr_err(DRV_NAME + ": Error: Invalid ad_select \"%s\"\n", + ad_select == NULL ? "NULL" : ad_select); + return -EINVAL; + } + + if (bond_mode != BOND_MODE_8023AD) { + pr_warning(DRV_NAME + ": ad_select param only affects 802.3ad mode\n"); + } + } else { + params->ad_select = BOND_AD_STABLE; + } + + if (max_bonds < 0 || max_bonds > INT_MAX) { + pr_warning(DRV_NAME ": Warning: max_bonds (%d) not in range %d-%d, so it " "was reset to BOND_DEFAULT_MAX_BONDS (%d)\n", - max_bonds, 1, INT_MAX, BOND_DEFAULT_MAX_BONDS); + max_bonds, 0, INT_MAX, BOND_DEFAULT_MAX_BONDS); max_bonds = BOND_DEFAULT_MAX_BONDS; } if (miimon < 0) { - printk(KERN_WARNING DRV_NAME + pr_warning(DRV_NAME ": Warning: miimon module parameter (%d), " "not in range 0-%d, so it was reset to %d\n", miimon, INT_MAX, BOND_LINK_MON_INTERV); @@ -4641,7 +4772,7 @@ static int bond_check_params(struct bond_params *params) } if (updelay < 0) { - printk(KERN_WARNING DRV_NAME + pr_warning(DRV_NAME ": Warning: updelay module parameter (%d), " "not in range 0-%d, so it was reset to 0\n", updelay, INT_MAX); @@ -4649,7 +4780,7 @@ static int bond_check_params(struct bond_params *params) } if (downdelay < 0) { - printk(KERN_WARNING DRV_NAME + pr_warning(DRV_NAME ": Warning: downdelay module parameter (%d), " "not in range 0-%d, so it was reset to 0\n", downdelay, INT_MAX); @@ -4657,22 +4788,36 @@ static int bond_check_params(struct bond_params *params) } if ((use_carrier != 0) && (use_carrier != 1)) { - printk(KERN_WARNING DRV_NAME + pr_warning(DRV_NAME ": Warning: use_carrier module parameter (%d), " "not of valid value (0/1), so it was set to 1\n", use_carrier); use_carrier = 1; } + if (num_grat_arp < 0 || num_grat_arp > 255) { + pr_warning(DRV_NAME + ": Warning: num_grat_arp (%d) not in range 0-255 so it " + "was reset to 1 \n", num_grat_arp); + num_grat_arp = 1; + } + + if (num_unsol_na < 0 || num_unsol_na > 255) { + pr_warning(DRV_NAME + ": Warning: num_unsol_na (%d) not in range 0-255 so it " + "was reset to 1 \n", num_unsol_na); + num_unsol_na = 1; + } + /* reset values for 802.3ad */ if (bond_mode == BOND_MODE_8023AD) { if (!miimon) { - printk(KERN_WARNING DRV_NAME + pr_warning(DRV_NAME ": Warning: miimon must be specified, " "otherwise bonding will not detect link " "failure, speed and duplex which are " "essential for 802.3ad operation\n"); - printk(KERN_WARNING "Forcing miimon to 100msec\n"); + pr_warning("Forcing miimon to 100msec\n"); miimon = 100; } } @@ -4681,12 +4826,12 @@ static int bond_check_params(struct bond_params *params) if ((bond_mode == BOND_MODE_TLB) || (bond_mode == BOND_MODE_ALB)) { if (!miimon) { - printk(KERN_WARNING DRV_NAME + pr_warning(DRV_NAME ": Warning: miimon must be specified, " "otherwise bonding will not detect link " "failure and link speed which are essential " "for TLB/ALB load balancing\n"); - printk(KERN_WARNING "Forcing miimon to 100msec\n"); + pr_warning("Forcing miimon to 100msec\n"); miimon = 100; } } @@ -4706,7 +4851,7 @@ static int bond_check_params(struct bond_params *params) /* just warn the user the up/down delay will have * no effect since miimon is zero... */ - printk(KERN_WARNING DRV_NAME + pr_warning(DRV_NAME ": Warning: miimon module parameter not set " "and updelay (%d) or downdelay (%d) module " "parameter is set; updelay and downdelay have " @@ -4716,7 +4861,7 @@ static int bond_check_params(struct bond_params *params) } else { /* don't allow arp monitoring */ if (arp_interval) { - printk(KERN_WARNING DRV_NAME + pr_warning(DRV_NAME ": Warning: miimon (%d) and arp_interval (%d) " "can't be used simultaneously, disabling ARP " "monitoring\n", @@ -4725,7 +4870,7 @@ static int bond_check_params(struct bond_params *params) } if ((updelay % miimon) != 0) { - printk(KERN_WARNING DRV_NAME + pr_warning(DRV_NAME ": Warning: updelay (%d) is not a multiple " "of miimon (%d), updelay rounded to %d ms\n", updelay, miimon, (updelay / miimon) * miimon); @@ -4734,7 +4879,7 @@ static int bond_check_params(struct bond_params *params) updelay /= miimon; if ((downdelay % miimon) != 0) { - printk(KERN_WARNING DRV_NAME + pr_warning(DRV_NAME ": Warning: downdelay (%d) is not a multiple " "of miimon (%d), downdelay rounded to %d ms\n", downdelay, miimon, @@ -4745,7 +4890,7 @@ static int bond_check_params(struct bond_params *params) } if (arp_interval < 0) { - printk(KERN_WARNING DRV_NAME + pr_warning(DRV_NAME ": Warning: arp_interval module parameter (%d) " ", not in range 0-%d, so it was reset to %d\n", arp_interval, INT_MAX, BOND_LINK_ARP_INTERV); @@ -4758,7 +4903,7 @@ static int bond_check_params(struct bond_params *params) /* not complete check, but should be good enough to catch mistakes */ if (!isdigit(arp_ip_target[arp_ip_count][0])) { - printk(KERN_WARNING DRV_NAME + pr_warning(DRV_NAME ": Warning: bad arp_ip_target module parameter " "(%s), ARP monitoring will not be performed\n", arp_ip_target[arp_ip_count]); @@ -4771,7 +4916,7 @@ static int bond_check_params(struct bond_params *params) if (arp_interval && !arp_ip_count) { /* don't allow arping if no arp_ip_target given... */ - printk(KERN_WARNING DRV_NAME + pr_warning(DRV_NAME ": Warning: arp_interval module parameter (%d) " "specified without providing an arp_ip_target " "parameter, arp_interval was reset to 0\n", @@ -4781,12 +4926,12 @@ static int bond_check_params(struct bond_params *params) if (arp_validate) { if (bond_mode != BOND_MODE_ACTIVEBACKUP) { - printk(KERN_ERR DRV_NAME - ": arp_validate only supported in active-backup mode\n"); + pr_err(DRV_NAME + ": arp_validate only supported in active-backup mode\n"); return -EINVAL; } if (!arp_interval) { - printk(KERN_ERR DRV_NAME + pr_err(DRV_NAME ": arp_validate requires arp_interval\n"); return -EINVAL; } @@ -4794,7 +4939,7 @@ static int bond_check_params(struct bond_params *params) arp_validate_value = bond_parse_parm(arp_validate, arp_validate_tbl); if (arp_validate_value == -1) { - printk(KERN_ERR DRV_NAME + pr_err(DRV_NAME ": Error: invalid arp_validate \"%s\"\n", arp_validate == NULL ? "NULL" : arp_validate); return -EINVAL; @@ -4803,28 +4948,28 @@ static int bond_check_params(struct bond_params *params) arp_validate_value = 0; if (miimon) { - printk(KERN_INFO DRV_NAME + pr_info(DRV_NAME ": MII link monitoring set to %d ms\n", miimon); } else if (arp_interval) { int i; - printk(KERN_INFO DRV_NAME - ": ARP monitoring set to %d ms, validate %s, with %d target(s):", + pr_info(DRV_NAME ": 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]); + printk(" %s", arp_ip_target[i]); printk("\n"); - } else { + } else if (max_bonds) { /* miimon and arp_interval not set, we need one so things * work as expected, see bonding.txt for details */ - printk(KERN_WARNING DRV_NAME + pr_warning(DRV_NAME ": Warning: either miimon or arp_interval and " "arp_ip_target module parameters must be specified, " "otherwise bonding will not detect link failures! see " @@ -4835,22 +4980,37 @@ static int bond_check_params(struct bond_params *params) /* currently, using a primary only makes sense * in active backup, TLB or ALB modes */ - printk(KERN_WARNING DRV_NAME + pr_warning(DRV_NAME ": Warning: %s primary device specified but has no " "effect in %s mode\n", primary, bond_mode_name(bond_mode)); primary = NULL; } - if (fail_over_mac && (bond_mode != BOND_MODE_ACTIVEBACKUP)) - printk(KERN_WARNING DRV_NAME - ": Warning: fail_over_mac only affects " - "active-backup mode.\n"); + if (fail_over_mac) { + fail_over_mac_value = bond_parse_parm(fail_over_mac, + fail_over_mac_tbl); + if (fail_over_mac_value == -1) { + pr_err(DRV_NAME + ": Error: invalid fail_over_mac \"%s\"\n", + arp_validate == NULL ? "NULL" : arp_validate); + return -EINVAL; + } + + if (bond_mode != BOND_MODE_ACTIVEBACKUP) + pr_warning(DRV_NAME + ": Warning: fail_over_mac only affects " + "active-backup mode.\n"); + } else { + fail_over_mac_value = BOND_FOM_NONE; + } /* fill params struct with the proper values */ params->mode = bond_mode; params->xmit_policy = xmit_hashtype; params->miimon = miimon; + params->num_grat_arp = num_grat_arp; + params->num_unsol_na = num_unsol_na; params->arp_interval = arp_interval; params->arp_validate = arp_validate_value; params->updelay = updelay; @@ -4858,7 +5018,7 @@ static int bond_check_params(struct bond_params *params) params->use_carrier = use_carrier; params->lacp_fast = lacp_fast; params->primary[0] = 0; - params->fail_over_mac = fail_over_mac; + params->fail_over_mac = fail_over_mac_value; if (primary) { strncpy(params->primary, primary, IFNAMSIZ); @@ -4871,38 +5031,70 @@ static int bond_check_params(struct bond_params *params) } static struct lock_class_key bonding_netdev_xmit_lock_key; +static struct lock_class_key bonding_netdev_addr_lock_key; + +static void bond_set_lockdep_class_one(struct net_device *dev, + struct netdev_queue *txq, + void *_unused) +{ + lockdep_set_class(&txq->_xmit_lock, + &bonding_netdev_xmit_lock_key); +} + +static void bond_set_lockdep_class(struct net_device *dev) +{ + lockdep_set_class(&dev->addr_list_lock, + &bonding_netdev_addr_lock_key); + netdev_for_each_tx_queue(dev, bond_set_lockdep_class_one, NULL); +} + +/* + * Called from registration process + */ +static int bond_init(struct net_device *bond_dev) +{ + struct bonding *bond = netdev_priv(bond_dev); + + pr_debug("Begin bond_init for %s\n", bond_dev->name); + + bond->wq = create_singlethread_workqueue(bond_dev->name); + if (!bond->wq) + return -ENOMEM; + + bond_set_lockdep_class(bond_dev); + + netif_carrier_off(bond_dev); + + bond_create_proc_entry(bond); + list_add_tail(&bond->bond_list, &bond_dev_list); + + return 0; +} /* 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(char *name, struct bond_params *params, struct bonding **newbond) +int bond_create(const char *name) { struct net_device *bond_dev; - struct bonding *bond, *nxt; int res; rtnl_lock(); - down_write(&bonding_rwsem); - /* Check to see if the bond already exists. */ - if (name) { - list_for_each_entry_safe(bond, nxt, &bond_dev_list, bond_list) - if (strnicmp(bond->dev->name, name, IFNAMSIZ) == 0) { - printk(KERN_ERR DRV_NAME - ": cannot add bond %s; it already exists\n", - name); - res = -EPERM; - goto out_rtnl; - } + /* 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 : "", - ether_setup); + bond_setup); if (!bond_dev) { - printk(KERN_ERR DRV_NAME - ": %s: eek! can't alloc netdev!\n", + pr_err(DRV_NAME ": %s: eek! can't alloc netdev!\n", name); res = -ENOMEM; goto out_rtnl; @@ -4914,45 +5106,24 @@ int bond_create(char *name, struct bond_params *params, struct bonding **newbond goto out_netdev; } - /* bond_init() must be called after dev_alloc_name() (for the - * /proc files), but before register_netdevice(), because we - * need to set function pointers. - */ - - res = bond_init(bond_dev, params); - if (res < 0) { - goto out_netdev; - } - res = register_netdevice(bond_dev); - if (res < 0) { + if (res < 0) goto out_bond; - } - - lockdep_set_class(&bond_dev->_xmit_lock, &bonding_netdev_xmit_lock_key); - if (newbond) - *newbond = bond_dev->priv; - - netif_carrier_off(bond_dev); - - up_write(&bonding_rwsem); - rtnl_unlock(); /* allows sysfs registration of net device */ - res = bond_create_sysfs_entry(bond_dev->priv); - if (res < 0) { - rtnl_lock(); - down_write(&bonding_rwsem); - goto out_bond; - } + res = bond_create_sysfs_entry(netdev_priv(bond_dev)); + if (res < 0) + goto out_unreg; + rtnl_unlock(); return 0; +out_unreg: + unregister_netdevice(bond_dev); out_bond: bond_deinit(bond_dev); out_netdev: free_netdev(bond_dev); out_rtnl: - up_write(&bonding_rwsem); rtnl_unlock(); return res; } @@ -4961,23 +5132,17 @@ static int __init bonding_init(void) { int i; int res; - struct bonding *bond, *nxt; - printk(KERN_INFO "%s", version); + pr_info("%s", version); res = bond_check_params(&bonding_defaults); - if (res) { + if (res) goto out; - } -#ifdef CONFIG_PROC_FS bond_create_proc_dir(); -#endif - - init_rwsem(&bonding_rwsem); for (i = 0; i < max_bonds; i++) { - res = bond_create(NULL, &bonding_defaults, NULL); + res = bond_create(NULL); if (res) goto err; } @@ -4988,17 +5153,12 @@ static int __init bonding_init(void) register_netdevice_notifier(&bond_netdev_notifier); register_inetaddr_notifier(&bond_inetaddr_notifier); + bond_register_ipv6_notifier(); goto out; err: - list_for_each_entry_safe(bond, nxt, &bond_dev_list, bond_list) { - bond_work_cancel_all(bond); - destroy_workqueue(bond->wq); - } - rtnl_lock(); bond_free_all(); - bond_destroy_sysfs(); rtnl_unlock(); out: return res; @@ -5009,10 +5169,12 @@ static void __exit bonding_exit(void) { unregister_netdevice_notifier(&bond_netdev_notifier); unregister_inetaddr_notifier(&bond_inetaddr_notifier); + bond_unregister_ipv6_notifier(); + + bond_destroy_sysfs(); rtnl_lock(); bond_free_all(); - bond_destroy_sysfs(); rtnl_unlock(); } @@ -5022,13 +5184,3 @@ MODULE_LICENSE("GPL"); MODULE_VERSION(DRV_VERSION); MODULE_DESCRIPTION(DRV_DESCRIPTION ", v" DRV_VERSION); MODULE_AUTHOR("Thomas Davis, tadavis@lbl.gov and many others"); -MODULE_SUPPORTED_DEVICE("most ethernet devices"); - -/* - * Local variables: - * c-indent-level: 8 - * c-basic-offset: 8 - * tab-width: 8 - * End: - */ -