diff options
Diffstat (limited to 'drivers/net/bonding/bond_main.c')
| -rw-r--r-- | drivers/net/bonding/bond_main.c | 3441 |
1 files changed, 1524 insertions, 1917 deletions
diff --git a/drivers/net/bonding/bond_main.c b/drivers/net/bonding/bond_main.c index 435984ad8b2..701f86cd599 100644 --- a/drivers/net/bonding/bond_main.c +++ b/drivers/net/bonding/bond_main.c @@ -54,7 +54,6 @@ #include <linux/inet.h> #include <linux/bitops.h> #include <linux/io.h> -#include <asm/system.h> #include <asm/dma.h> #include <linux/uaccess.h> #include <linux/errno.h> @@ -77,6 +76,9 @@ #include <net/route.h> #include <net/net_namespace.h> #include <net/netns/generic.h> +#include <net/pkt_sched.h> +#include <linux/rculist.h> +#include <net/flow_keys.h> #include "bonding.h" #include "bond_3ad.h" #include "bond_alb.h" @@ -84,13 +86,11 @@ /*---------------------------- Module parameters ----------------------------*/ /* monitor all links that often (in milliseconds). <=0 disables monitoring */ -#define BOND_LINK_MON_INTERV 0 -#define BOND_LINK_ARP_INTERV 0 static int max_bonds = BOND_DEFAULT_MAX_BONDS; static int tx_queues = BOND_DEFAULT_TX_QUEUES; static int num_peer_notif = 1; -static int miimon = BOND_LINK_MON_INTERV; +static int miimon; static int updelay; static int downdelay; static int use_carrier = 1; @@ -101,13 +101,16 @@ static char *lacp_rate; static int min_links; static char *ad_select; static char *xmit_hash_policy; -static int arp_interval = BOND_LINK_ARP_INTERV; +static int arp_interval; static char *arp_ip_target[BOND_MAX_ARP_TARGETS]; static char *arp_validate; +static char *arp_all_targets; static char *fail_over_mac; -static int all_slaves_active = 0; +static int all_slaves_active; static struct bond_params bonding_defaults; static int resend_igmp = BOND_DEFAULT_RESEND_IGMP; +static int packets_per_slave = 1; +static int lp_interval = BOND_ALB_DEFAULT_LP_INTERVAL; module_param(max_bonds, int, 0); MODULE_PARM_DESC(max_bonds, "Max number of bonded devices"); @@ -157,7 +160,8 @@ MODULE_PARM_DESC(min_links, "Minimum number of available links before turning on module_param(xmit_hash_policy, charp, 0); MODULE_PARM_DESC(xmit_hash_policy, "balance-xor and 802.3ad hashing method; " "0 for layer 2 (default), 1 for layer 3+4, " - "2 for layer 2+3"); + "2 for layer 2+3, 3 for encap layer 2+3, " + "4 for encap layer 3+4"); module_param(arp_interval, int, 0); MODULE_PARM_DESC(arp_interval, "arp interval in milliseconds"); module_param_array(arp_ip_target, charp, NULL, 0); @@ -166,6 +170,8 @@ module_param(arp_validate, charp, 0); MODULE_PARM_DESC(arp_validate, "validate src/dst of ARP probes; " "0 for none (default), 1 for active, " "2 for backup, 3 for all"); +module_param(arp_all_targets, charp, 0); +MODULE_PARM_DESC(arp_all_targets, "fail on any/all arp targets timeout; 0 for any (default), 1 for all"); 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; 0 for none (default), " @@ -177,6 +183,14 @@ MODULE_PARM_DESC(all_slaves_active, "Keep all frames received on an interface" module_param(resend_igmp, int, 0); MODULE_PARM_DESC(resend_igmp, "Number of IGMP membership reports to send on " "link failure"); +module_param(packets_per_slave, int, 0); +MODULE_PARM_DESC(packets_per_slave, "Packets to send per slave in balance-rr " + "mode; 0 for a random slave, 1 packet per " + "slave (default), >1 packets per slave."); +module_param(lp_interval, uint, 0); +MODULE_PARM_DESC(lp_interval, "The number of seconds between instances where " + "the bonding driver sends learning packets to " + "each slaves peer switch. The default is 1."); /*----------------------------- Global variables ----------------------------*/ @@ -192,59 +206,6 @@ static int bond_mode = BOND_MODE_ROUNDROBIN; static int xmit_hashtype = BOND_XMIT_POLICY_LAYER2; static int lacp_fast; -const struct bond_parm_tbl bond_lacp_tbl[] = { -{ "slow", AD_LACP_SLOW}, -{ "fast", AD_LACP_FAST}, -{ NULL, -1}, -}; - -const struct bond_parm_tbl bond_mode_tbl[] = { -{ "balance-rr", BOND_MODE_ROUNDROBIN}, -{ "active-backup", BOND_MODE_ACTIVEBACKUP}, -{ "balance-xor", BOND_MODE_XOR}, -{ "broadcast", BOND_MODE_BROADCAST}, -{ "802.3ad", BOND_MODE_8023AD}, -{ "balance-tlb", BOND_MODE_TLB}, -{ "balance-alb", BOND_MODE_ALB}, -{ NULL, -1}, -}; - -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}, -}; - -const struct bond_parm_tbl arp_validate_tbl[] = { -{ "none", BOND_ARP_VALIDATE_NONE}, -{ "active", BOND_ARP_VALIDATE_ACTIVE}, -{ "backup", BOND_ARP_VALIDATE_BACKUP}, -{ "all", BOND_ARP_VALIDATE_ALL}, -{ NULL, -1}, -}; - -const struct bond_parm_tbl fail_over_mac_tbl[] = { -{ "none", BOND_FOM_NONE}, -{ "active", BOND_FOM_ACTIVE}, -{ "follow", BOND_FOM_FOLLOW}, -{ NULL, -1}, -}; - -const struct bond_parm_tbl pri_reselect_tbl[] = { -{ "always", BOND_PRI_RESELECT_ALWAYS}, -{ "better", BOND_PRI_RESELECT_BETTER}, -{ "failure", BOND_PRI_RESELECT_FAILURE}, -{ NULL, -1}, -}; - -struct bond_parm_tbl ad_select_tbl[] = { -{ "stable", BOND_AD_STABLE}, -{ "bandwidth", BOND_AD_BANDWIDTH}, -{ "count", BOND_AD_COUNT}, -{ NULL, -1}, -}; - /*-------------------------- Forward declarations ---------------------------*/ static int bond_init(struct net_device *bond_dev); @@ -264,7 +225,7 @@ const char *bond_mode_name(int mode) [BOND_MODE_ALB] = "adaptive load balancing", }; - if (mode < 0 || mode > BOND_MODE_ALB) + if (mode < BOND_MODE_ROUNDROBIN || mode > BOND_MODE_ALB) return "unknown"; return names[mode]; @@ -273,137 +234,25 @@ const char *bond_mode_name(int mode) /*---------------------------------- VLAN -----------------------------------*/ /** - * bond_add_vlan - add a new vlan id on bond - * @bond: bond that got the notification - * @vlan_id: the vlan id to add - * - * Returns -ENOMEM if allocation failed. - */ -static int bond_add_vlan(struct bonding *bond, unsigned short vlan_id) -{ - struct vlan_entry *vlan; - - pr_debug("bond: %s, vlan id %d\n", - (bond ? bond->dev->name : "None"), vlan_id); - - vlan = kzalloc(sizeof(struct vlan_entry), GFP_KERNEL); - if (!vlan) - return -ENOMEM; - - INIT_LIST_HEAD(&vlan->vlan_list); - vlan->vlan_id = vlan_id; - - write_lock_bh(&bond->lock); - - list_add_tail(&vlan->vlan_list, &bond->vlan_list); - - write_unlock_bh(&bond->lock); - - pr_debug("added VLAN ID %d on bond %s\n", vlan_id, bond->dev->name); - - return 0; -} - -/** - * bond_del_vlan - delete a vlan id from bond - * @bond: bond that got the notification - * @vlan_id: the vlan id to delete - * - * returns -ENODEV if @vlan_id was not found in @bond. - */ -static int bond_del_vlan(struct bonding *bond, unsigned short vlan_id) -{ - struct vlan_entry *vlan; - int res = -ENODEV; - - pr_debug("bond: %s, vlan id %d\n", bond->dev->name, vlan_id); - - block_netpoll_tx(); - write_lock_bh(&bond->lock); - - list_for_each_entry(vlan, &bond->vlan_list, vlan_list) { - if (vlan->vlan_id == vlan_id) { - list_del(&vlan->vlan_list); - - if (bond_is_lb(bond)) - bond_alb_clear_vlan(bond, vlan_id); - - pr_debug("removed VLAN ID %d from bond %s\n", - vlan_id, bond->dev->name); - - kfree(vlan); - - res = 0; - goto out; - } - } - - pr_debug("couldn't find VLAN ID %d in bond %s\n", - vlan_id, bond->dev->name); - -out: - write_unlock_bh(&bond->lock); - unblock_netpoll_tx(); - return res; -} - -/** - * bond_next_vlan - safely skip to the next item in the vlans list. - * @bond: the bond we're working on - * @curr: item we're advancing from - * - * Returns %NULL if list is empty, bond->next_vlan if @curr is %NULL, - * or @curr->next otherwise (even if it is @curr itself again). - * - * Caller must hold bond->lock - */ -struct vlan_entry *bond_next_vlan(struct bonding *bond, struct vlan_entry *curr) -{ - struct vlan_entry *next, *last; - - if (list_empty(&bond->vlan_list)) - return NULL; - - if (!curr) { - next = list_entry(bond->vlan_list.next, - struct vlan_entry, vlan_list); - } else { - last = list_entry(bond->vlan_list.prev, - struct vlan_entry, vlan_list); - if (last == curr) { - next = list_entry(bond->vlan_list.next, - struct vlan_entry, vlan_list); - } else { - next = list_entry(curr->vlan_list.next, - struct vlan_entry, vlan_list); - } - } - - return next; -} - -#define bond_queue_mapping(skb) (*(u16 *)((skb)->cb)) - -/** * 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 */ -int bond_dev_queue_xmit(struct bonding *bond, struct sk_buff *skb, +void bond_dev_queue_xmit(struct bonding *bond, struct sk_buff *skb, struct net_device *slave_dev) { skb->dev = slave_dev; - skb->queue_mapping = bond_queue_mapping(skb); + BUILD_BUG_ON(sizeof(skb->queue_mapping) != + sizeof(qdisc_skb_cb(skb)->slave_dev_queue_mapping)); + skb->queue_mapping = qdisc_skb_cb(skb)->slave_dev_queue_mapping; - if (unlikely(netpoll_tx_running(slave_dev))) + if (unlikely(netpoll_tx_running(bond->dev))) bond_netpoll_send_skb(bond_get_slave_by_dev(bond, slave_dev), skb); else dev_queue_xmit(skb); - - return 0; } /* @@ -428,32 +277,30 @@ int bond_dev_queue_xmit(struct bonding *bond, struct sk_buff *skb, * @bond_dev: bonding net device that got called * @vid: vlan id being added */ -static int bond_vlan_rx_add_vid(struct net_device *bond_dev, uint16_t vid) +static int bond_vlan_rx_add_vid(struct net_device *bond_dev, + __be16 proto, u16 vid) { struct bonding *bond = netdev_priv(bond_dev); - struct slave *slave, *stop_at; - int i, res; + struct slave *slave, *rollback_slave; + struct list_head *iter; + int res; - bond_for_each_slave(bond, slave, i) { - res = vlan_vid_add(slave->dev, vid); + bond_for_each_slave(bond, slave, iter) { + res = vlan_vid_add(slave->dev, proto, vid); if (res) goto unwind; } - res = bond_add_vlan(bond, vid); - if (res) { - pr_err("%s: Error: Failed to add vlan id %d\n", - bond_dev->name, vid); - return res; - } - return 0; unwind: - /* unwind from head to the slave that failed */ - stop_at = slave; - bond_for_each_slave_from_to(bond, slave, i, bond->first_slave, stop_at) - vlan_vid_del(slave->dev, vid); + /* unwind to the slave that failed */ + bond_for_each_slave(bond, rollback_slave, iter) { + if (rollback_slave == slave) + break; + + vlan_vid_del(rollback_slave->dev, proto, vid); + } return res; } @@ -463,51 +310,22 @@ unwind: * @bond_dev: bonding net device that got called * @vid: vlan id being removed */ -static int bond_vlan_rx_kill_vid(struct net_device *bond_dev, uint16_t vid) +static int bond_vlan_rx_kill_vid(struct net_device *bond_dev, + __be16 proto, u16 vid) { struct bonding *bond = netdev_priv(bond_dev); + struct list_head *iter; struct slave *slave; - int i, res; - bond_for_each_slave(bond, slave, i) - vlan_vid_del(slave->dev, vid); + bond_for_each_slave(bond, slave, iter) + vlan_vid_del(slave->dev, proto, vid); - res = bond_del_vlan(bond, vid); - if (res) { - pr_err("%s: Error: Failed to remove vlan id %d\n", - bond_dev->name, vid); - return res; - } + if (bond_is_lb(bond)) + bond_alb_clear_vlan(bond, vid); return 0; } -static void bond_add_vlans_on_slave(struct bonding *bond, struct net_device *slave_dev) -{ - struct vlan_entry *vlan; - int res; - - list_for_each_entry(vlan, &bond->vlan_list, vlan_list) { - res = vlan_vid_add(slave_dev, vlan->vlan_id); - if (res) - pr_warning("%s: Failed to add vlan id %d to device %s\n", - bond->dev->name, vlan->vlan_id, - slave_dev->name); - } -} - -static void bond_del_vlans_from_slave(struct bonding *bond, - struct net_device *slave_dev) -{ - struct vlan_entry *vlan; - - list_for_each_entry(vlan, &bond->vlan_list, vlan_list) { - if (!vlan->vlan_id) - continue; - vlan_vid_del(slave_dev, vlan->vlan_id); - } -} - /*------------------------------- Link status -------------------------------*/ /* @@ -519,16 +337,16 @@ static void bond_del_vlans_from_slave(struct bonding *bond, */ static int bond_set_carrier(struct bonding *bond) { + struct list_head *iter; struct slave *slave; - int i; - if (bond->slave_cnt == 0) + if (!bond_has_slaves(bond)) goto down; - if (bond->params.mode == BOND_MODE_8023AD) + if (BOND_MODE(bond) == BOND_MODE_8023AD) return bond_3ad_set_carrier(bond); - bond_for_each_slave(bond, slave, i) { + bond_for_each_slave(bond, slave, iter) { if (slave->link == BOND_LINK_UP) { if (!netif_carrier_ok(bond->dev)) { netif_carrier_on(bond->dev); @@ -550,9 +368,9 @@ down: * Get link speed and duplex from the slave's base driver * using ethtool. If for some reason the call fails or the * values are invalid, set speed and duplex to -1, - * and return error. + * and return. */ -static int bond_update_speed_duplex(struct slave *slave) +static void bond_update_speed_duplex(struct slave *slave) { struct net_device *slave_dev = slave->dev; struct ethtool_cmd ecmd; @@ -564,24 +382,40 @@ static int bond_update_speed_duplex(struct slave *slave) res = __ethtool_get_settings(slave_dev, &ecmd); if (res < 0) - return -1; + return; slave_speed = ethtool_cmd_speed(&ecmd); if (slave_speed == 0 || slave_speed == ((__u32) -1)) - return -1; + return; switch (ecmd.duplex) { case DUPLEX_FULL: case DUPLEX_HALF: break; default: - return -1; + return; } slave->speed = slave_speed; slave->duplex = ecmd.duplex; - return 0; + return; +} + +const char *bond_slave_link_status(s8 link) +{ + switch (link) { + case BOND_LINK_UP: + return "up"; + case BOND_LINK_FAIL: + return "going down"; + case BOND_LINK_DOWN: + return "down"; + case BOND_LINK_BACK: + return "going back"; + default: + return "unknown"; + } } /* @@ -615,15 +449,9 @@ static int bond_check_dev_link(struct bonding *bond, 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; - } - } + if (slave_dev->ethtool_ops->get_link) + return slave_dev->ethtool_ops->get_link(slave_dev) ? + BMSR_LSTATUS : 0; /* Ethtool can't be used, fallback to MII ioctls. */ ioctl = slave_ops->ndo_do_ioctl; @@ -666,8 +494,10 @@ static int bond_check_dev_link(struct bonding *bond, */ static int bond_set_promiscuity(struct bonding *bond, int inc) { + struct list_head *iter; int err = 0; - if (USES_PRIMARY(bond->params.mode)) { + + if (bond_uses_primary(bond)) { /* write lock already acquired */ if (bond->curr_active_slave) { err = dev_set_promiscuity(bond->curr_active_slave->dev, @@ -675,8 +505,8 @@ static int bond_set_promiscuity(struct bonding *bond, int inc) } } else { struct slave *slave; - int i; - bond_for_each_slave(bond, slave, i) { + + bond_for_each_slave(bond, slave, iter) { err = dev_set_promiscuity(slave->dev, inc); if (err) return err; @@ -690,8 +520,10 @@ static int bond_set_promiscuity(struct bonding *bond, int inc) */ static int bond_set_allmulti(struct bonding *bond, int inc) { + struct list_head *iter; int err = 0; - if (USES_PRIMARY(bond->params.mode)) { + + if (bond_uses_primary(bond)) { /* write lock already acquired */ if (bond->curr_active_slave) { err = dev_set_allmulti(bond->curr_active_slave->dev, @@ -699,8 +531,8 @@ static int bond_set_allmulti(struct bonding *bond, int inc) } } else { struct slave *slave; - int i; - bond_for_each_slave(bond, slave, i) { + + bond_for_each_slave(bond, slave, iter) { err = dev_set_allmulti(slave->dev, inc); if (err) return err; @@ -710,106 +542,39 @@ static int bond_set_allmulti(struct bonding *bond, int inc) } /* - * Add a Multicast address to slaves - * according to mode - */ -static void bond_mc_add(struct bonding *bond, void *addr) -{ - if (USES_PRIMARY(bond->params.mode)) { - /* write lock already acquired */ - if (bond->curr_active_slave) - dev_mc_add(bond->curr_active_slave->dev, addr); - } else { - struct slave *slave; - int i; - - bond_for_each_slave(bond, slave, i) - dev_mc_add(slave->dev, addr); - } -} - -/* - * Remove a multicast address from slave - * according to mode - */ -static void bond_mc_del(struct bonding *bond, void *addr) -{ - if (USES_PRIMARY(bond->params.mode)) { - /* write lock already acquired */ - if (bond->curr_active_slave) - dev_mc_del(bond->curr_active_slave->dev, addr); - } else { - struct slave *slave; - int i; - bond_for_each_slave(bond, slave, i) { - dev_mc_del(slave->dev, addr); - } - } -} - - -static void __bond_resend_igmp_join_requests(struct net_device *dev) -{ - struct in_device *in_dev; - - rcu_read_lock(); - in_dev = __in_dev_get_rcu(dev); - if (in_dev) - ip_mc_rejoin_groups(in_dev); - rcu_read_unlock(); -} - -/* * Retrieve the list of registered multicast addresses for the bonding * device and retransmit an IGMP JOIN request to the current active * slave. */ -static void bond_resend_igmp_join_requests(struct bonding *bond) +static void bond_resend_igmp_join_requests_delayed(struct work_struct *work) { - struct net_device *vlan_dev; - struct vlan_entry *vlan; - - read_lock(&bond->lock); - - /* rejoin all groups on bond device */ - __bond_resend_igmp_join_requests(bond->dev); + struct bonding *bond = container_of(work, struct bonding, + mcast_work.work); - /* rejoin all groups on vlan devices */ - list_for_each_entry(vlan, &bond->vlan_list, vlan_list) { - rcu_read_lock(); - vlan_dev = __vlan_find_dev_deep(bond->dev, - vlan->vlan_id); - rcu_read_unlock(); - if (vlan_dev) - __bond_resend_igmp_join_requests(vlan_dev); + if (!rtnl_trylock()) { + queue_delayed_work(bond->wq, &bond->mcast_work, 1); + return; } + call_netdevice_notifiers(NETDEV_RESEND_IGMP, bond->dev); - if (--bond->igmp_retrans > 0) + if (bond->igmp_retrans > 1) { + bond->igmp_retrans--; queue_delayed_work(bond->wq, &bond->mcast_work, HZ/5); - - read_unlock(&bond->lock); -} - -static void bond_resend_igmp_join_requests_delayed(struct work_struct *work) -{ - struct bonding *bond = container_of(work, struct bonding, - mcast_work.work); - bond_resend_igmp_join_requests(bond); + } + rtnl_unlock(); } -/* - * flush all members of flush->mc_list from device dev->mc_list +/* Flush bond's hardware addresses from slave */ -static void bond_mc_list_flush(struct net_device *bond_dev, +static void bond_hw_addr_flush(struct net_device *bond_dev, struct net_device *slave_dev) { struct bonding *bond = netdev_priv(bond_dev); - struct netdev_hw_addr *ha; - netdev_for_each_mc_addr(ha, bond_dev) - dev_mc_del(slave_dev, ha->addr); + dev_uc_unsync(slave_dev, bond_dev); + dev_mc_unsync(slave_dev, bond_dev); - if (bond->params.mode == BOND_MODE_8023AD) { + if (BOND_MODE(bond) == BOND_MODE_8023AD) { /* del lacpdu mc addr from mc list */ u8 lacpdu_multicast[ETH_ALEN] = MULTICAST_LACPDU_ADDR; @@ -819,21 +584,15 @@ static void bond_mc_list_flush(struct net_device *bond_dev, /*--------------------------- Active slave change ---------------------------*/ -/* - * Update the mc list and multicast-related flags for the new and - * old active slaves (if any) according to the multicast mode, and - * promiscuous flags unconditionally. +/* Update the hardware address list and promisc/allmulti for the new and + * old active slaves (if any). Modes that are not using primary keep all + * slaves up date at all times; only the modes that use primary need to call + * this function to swap these settings during a failover. */ -static void bond_mc_swap(struct bonding *bond, struct slave *new_active, - struct slave *old_active) +static void bond_hw_addr_swap(struct bonding *bond, struct slave *new_active, + struct slave *old_active) { - struct netdev_hw_addr *ha; - - if (!USES_PRIMARY(bond->params.mode)) - /* nothing to do - mc list is already up-to-date on - * all slaves - */ - return; + ASSERT_RTNL(); if (old_active) { if (bond->dev->flags & IFF_PROMISC) @@ -842,8 +601,7 @@ static void bond_mc_swap(struct bonding *bond, struct slave *new_active, if (bond->dev->flags & IFF_ALLMULTI) dev_set_allmulti(old_active->dev, -1); - netdev_for_each_mc_addr(ha, bond->dev) - dev_mc_del(old_active->dev, ha->addr); + bond_hw_addr_flush(bond->dev, old_active->dev); } if (new_active) { @@ -854,24 +612,41 @@ static void bond_mc_swap(struct bonding *bond, struct slave *new_active, if (bond->dev->flags & IFF_ALLMULTI) dev_set_allmulti(new_active->dev, 1); - netdev_for_each_mc_addr(ha, bond->dev) - dev_mc_add(new_active->dev, ha->addr); + netif_addr_lock_bh(bond->dev); + dev_uc_sync(new_active->dev, bond->dev); + dev_mc_sync(new_active->dev, bond->dev); + netif_addr_unlock_bh(bond->dev); } } +/** + * bond_set_dev_addr - clone slave's address to bond + * @bond_dev: bond net device + * @slave_dev: slave net device + * + * Should be called with RTNL held. + */ +static void bond_set_dev_addr(struct net_device *bond_dev, + struct net_device *slave_dev) +{ + pr_debug("bond_dev=%p slave_dev=%p slave_dev->addr_len=%d\n", + bond_dev, slave_dev, slave_dev->addr_len); + memcpy(bond_dev->dev_addr, slave_dev->dev_addr, slave_dev->addr_len); + bond_dev->addr_assign_type = NET_ADDR_STOLEN; + call_netdevice_notifiers(NETDEV_CHANGEADDR, bond_dev); +} + /* * 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. + * Called with RTNL, 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]; @@ -880,9 +655,11 @@ static void bond_do_fail_over_mac(struct bonding *bond, 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); + if (new_active) { + write_unlock_bh(&bond->curr_slave_lock); + bond_set_dev_addr(bond->dev, new_active->dev); + write_lock_bh(&bond->curr_slave_lock); + } break; case BOND_FOM_FOLLOW: /* @@ -894,15 +671,14 @@ static void bond_do_fail_over_mac(struct bonding *bond, 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); + ether_addr_copy(tmp_mac, new_active->dev->dev_addr); + ether_addr_copy(saddr.sa_data, + old_active->dev->dev_addr); saddr.sa_family = new_active->dev->type; } else { - memcpy(saddr.sa_data, bond->dev->dev_addr, ETH_ALEN); + ether_addr_copy(saddr.sa_data, bond->dev->dev_addr); saddr.sa_family = bond->dev->type; } @@ -916,7 +692,7 @@ static void bond_do_fail_over_mac(struct bonding *bond, if (!old_active) goto out; - memcpy(saddr.sa_data, tmp_mac, ETH_ALEN); + ether_addr_copy(saddr.sa_data, tmp_mac); saddr.sa_family = old_active->dev->type; rv = dev_set_mac_address(old_active->dev, &saddr); @@ -924,7 +700,6 @@ static void bond_do_fail_over_mac(struct bonding *bond, pr_err("%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: @@ -958,44 +733,24 @@ static bool bond_should_change_active(struct bonding *bond) /** * find_best_interface - select the best available slave to be the active one * @bond: our bonding struct - * - * Warning: Caller must hold curr_slave_lock for writing. */ static struct slave *bond_find_best_slave(struct bonding *bond) { - struct slave *new_active, *old_active; - struct slave *bestslave = NULL; + struct slave *slave, *bestslave = NULL; + struct list_head *iter; int mintime = bond->params.updelay; - int i; - - new_active = bond->curr_active_slave; - - if (!new_active) { /* there were no active slaves left */ - if (bond->slave_cnt > 0) /* found one slave */ - new_active = bond->first_slave; - else - return NULL; /* still no slave, return NULL */ - } - - if ((bond->primary_slave) && - bond->primary_slave->link == BOND_LINK_UP && - bond_should_change_active(bond)) { - new_active = bond->primary_slave; - } - - /* remember where to stop iterating over the slaves */ - old_active = new_active; - bond_for_each_slave_from(bond, new_active, i, old_active) { - if (new_active->link == BOND_LINK_UP) { - return new_active; - } else if (new_active->link == BOND_LINK_BACK && - IS_UP(new_active->dev)) { - /* link up, but waiting for stabilization */ - if (new_active->delay < mintime) { - mintime = new_active->delay; - bestslave = new_active; - } + if (bond->primary_slave && bond->primary_slave->link == BOND_LINK_UP && + bond_should_change_active(bond)) + return bond->primary_slave; + + bond_for_each_slave(bond, slave, iter) { + if (slave->link == BOND_LINK_UP) + return slave; + if (slave->link == BOND_LINK_BACK && bond_slave_is_up(slave) && + slave->delay < mintime) { + mintime = slave->delay; + bestslave = slave; } } @@ -1004,7 +759,11 @@ static struct slave *bond_find_best_slave(struct bonding *bond) static bool bond_should_notify_peers(struct bonding *bond) { - struct slave *slave = bond->curr_active_slave; + struct slave *slave; + + rcu_read_lock(); + slave = rcu_dereference(bond->curr_active_slave); + rcu_read_unlock(); pr_debug("bond_should_notify_peers: bond %s slave %s\n", bond->dev->name, slave ? slave->dev->name : "NULL"); @@ -1013,7 +772,6 @@ static bool bond_should_notify_peers(struct bonding *bond) test_bit(__LINK_STATE_LINKWATCH_PENDING, &slave->dev->state)) return false; - bond->send_peer_notif--; return true; } @@ -1030,8 +788,7 @@ static bool bond_should_notify_peers(struct bonding *bond) * because it is apparently the best available slave we have, even though its * updelay hasn't timed out yet. * - * If new_active is not NULL, caller must hold bond->lock for read and - * curr_slave_lock for write_bh. + * If new_active is not NULL, caller must hold curr_slave_lock for write_bh. */ void bond_change_active_slave(struct bonding *bond, struct slave *new_active) { @@ -1041,11 +798,11 @@ void bond_change_active_slave(struct bonding *bond, struct slave *new_active) return; if (new_active) { - new_active->jiffies = jiffies; + new_active->last_link_up = jiffies; if (new_active->link == BOND_LINK_BACK) { - if (USES_PRIMARY(bond->params.mode)) { - pr_info("%s: making interface %s the new active one %d ms earlier.\n", + if (bond_uses_primary(bond)) { + pr_info("%s: making interface %s the new active one %d ms earlier\n", bond->dev->name, new_active->dev->name, (bond->params.updelay - new_active->delay) * bond->params.miimon); } @@ -1053,40 +810,44 @@ void bond_change_active_slave(struct bonding *bond, struct slave *new_active) new_active->delay = 0; new_active->link = BOND_LINK_UP; - if (bond->params.mode == BOND_MODE_8023AD) + if (BOND_MODE(bond) == BOND_MODE_8023AD) bond_3ad_handle_link_change(new_active, BOND_LINK_UP); if (bond_is_lb(bond)) bond_alb_handle_link_change(bond, new_active, BOND_LINK_UP); } else { - if (USES_PRIMARY(bond->params.mode)) { - pr_info("%s: making interface %s the new active one.\n", + if (bond_uses_primary(bond)) { + pr_info("%s: making interface %s the new active one\n", bond->dev->name, new_active->dev->name); } } } - if (USES_PRIMARY(bond->params.mode)) - bond_mc_swap(bond, new_active, old_active); + if (bond_uses_primary(bond)) + bond_hw_addr_swap(bond, new_active, old_active); if (bond_is_lb(bond)) { bond_alb_handle_active_change(bond, new_active); if (old_active) - bond_set_slave_inactive_flags(old_active); + bond_set_slave_inactive_flags(old_active, + BOND_SLAVE_NOTIFY_NOW); if (new_active) - bond_set_slave_active_flags(new_active); + bond_set_slave_active_flags(new_active, + BOND_SLAVE_NOTIFY_NOW); } else { - bond->curr_active_slave = new_active; + rcu_assign_pointer(bond->curr_active_slave, new_active); } - if (bond->params.mode == BOND_MODE_ACTIVEBACKUP) { + if (BOND_MODE(bond) == BOND_MODE_ACTIVEBACKUP) { if (old_active) - bond_set_slave_inactive_flags(old_active); + bond_set_slave_inactive_flags(old_active, + BOND_SLAVE_NOTIFY_NOW); if (new_active) { bool should_notify_peers = false; - bond_set_slave_active_flags(new_active); + bond_set_slave_active_flags(new_active, + BOND_SLAVE_NOTIFY_NOW); if (bond->params.fail_over_mac) bond_do_fail_over_mac(bond, new_active, @@ -1100,14 +861,12 @@ void bond_change_active_slave(struct bonding *bond, struct slave *new_active) } write_unlock_bh(&bond->curr_slave_lock); - read_unlock(&bond->lock); - netdev_bonding_change(bond->dev, NETDEV_BONDING_FAILOVER); + call_netdevice_notifiers(NETDEV_BONDING_FAILOVER, bond->dev); if (should_notify_peers) - netdev_bonding_change(bond->dev, - NETDEV_NOTIFY_PEERS); + call_netdevice_notifiers(NETDEV_NOTIFY_PEERS, + bond->dev); - read_lock(&bond->lock); write_lock_bh(&bond->curr_slave_lock); } } @@ -1117,10 +876,10 @@ void bond_change_active_slave(struct bonding *bond, struct slave *new_active) * resend only if bond is brought up with the affected * bonding modes and the retransmission is enabled */ if (netif_running(bond->dev) && (bond->params.resend_igmp > 0) && - ((USES_PRIMARY(bond->params.mode) && new_active) || - bond->params.mode == BOND_MODE_ROUNDROBIN)) { + ((bond_uses_primary(bond) && new_active) || + BOND_MODE(bond) == BOND_MODE_ROUNDROBIN)) { bond->igmp_retrans = bond->params.resend_igmp; - queue_delayed_work(bond->wq, &bond->mcast_work, 0); + queue_delayed_work(bond->wq, &bond->mcast_work, 1); } } @@ -1133,7 +892,7 @@ void bond_change_active_slave(struct bonding *bond, struct slave *new_active) * - The primary_slave has got its link back. * - A slave has got its link back and there's no old curr_active_slave. * - * Caller must hold bond->lock for read and curr_slave_lock for write_bh. + * Caller must hold curr_slave_lock for write_bh. */ void bond_select_active_slave(struct bonding *bond) { @@ -1151,66 +910,12 @@ void bond_select_active_slave(struct bonding *bond) pr_info("%s: first active interface up!\n", bond->dev->name); } else { - pr_info("%s: now running without any active interface !\n", + pr_info("%s: now running without any active interface!\n", bond->dev->name); } } } -/*--------------------------- slave list handling ---------------------------*/ - -/* - * This function attaches the slave to the end of list. - * - * bond->lock held for writing by caller. - */ -static void bond_attach_slave(struct bonding *bond, struct slave *new_slave) -{ - if (bond->first_slave == NULL) { /* attaching the first slave */ - new_slave->next = new_slave; - new_slave->prev = new_slave; - bond->first_slave = new_slave; - } else { - new_slave->next = bond->first_slave; - new_slave->prev = bond->first_slave->prev; - new_slave->next->prev = new_slave; - new_slave->prev->next = new_slave; - } - - bond->slave_cnt++; -} - -/* - * This function detaches the slave from the list. - * WARNING: no check is made to verify if the slave effectively - * belongs to <bond>. - * Nothing is freed on return, structures are just unchained. - * If any slave pointer in bond was pointing to <slave>, - * it should be changed by the calling function. - * - * bond->lock held for writing by caller. - */ -static void bond_detach_slave(struct bonding *bond, struct slave *slave) -{ - if (slave->next) - slave->next->prev = slave->prev; - - if (slave->prev) - slave->prev->next = slave->next; - - if (bond->first_slave == slave) { /* slave is the first slave */ - if (bond->slave_cnt > 1) { /* there are more slave */ - bond->first_slave = slave->next; - } else { - bond->first_slave = NULL; /* slave was the last one */ - } - } - - slave->next = NULL; - slave->prev = NULL; - bond->slave_cnt--; -} - #ifdef CONFIG_NET_POLL_CONTROLLER static inline int slave_enable_netpoll(struct slave *slave) { @@ -1222,9 +927,7 @@ static inline int slave_enable_netpoll(struct slave *slave) if (!np) goto out; - np->dev = slave->dev; - strlcpy(np->dev_name, slave->dev->name, IFNAMSIZ); - err = __netpoll_setup(np); + err = __netpoll_setup(np, slave->dev); if (err) { kfree(np); goto out; @@ -1241,64 +944,40 @@ static inline void slave_disable_netpoll(struct slave *slave) return; slave->np = NULL; - synchronize_rcu_bh(); - __netpoll_cleanup(np); - kfree(np); -} -static inline bool slave_dev_support_netpoll(struct net_device *slave_dev) -{ - if (slave_dev->priv_flags & IFF_DISABLE_NETPOLL) - return false; - if (!slave_dev->netdev_ops->ndo_poll_controller) - return false; - return true; + __netpoll_free_async(np); } static void bond_poll_controller(struct net_device *bond_dev) { } -static void __bond_netpoll_cleanup(struct bonding *bond) -{ - struct slave *slave; - int i; - - bond_for_each_slave(bond, slave, i) - if (IS_UP(slave->dev)) - slave_disable_netpoll(slave); -} static void bond_netpoll_cleanup(struct net_device *bond_dev) { struct bonding *bond = netdev_priv(bond_dev); + struct list_head *iter; + struct slave *slave; - read_lock(&bond->lock); - __bond_netpoll_cleanup(bond); - read_unlock(&bond->lock); + bond_for_each_slave(bond, slave, iter) + if (bond_slave_is_up(slave)) + slave_disable_netpoll(slave); } static int bond_netpoll_setup(struct net_device *dev, struct netpoll_info *ni) { struct bonding *bond = netdev_priv(dev); + struct list_head *iter; struct slave *slave; - int i, err = 0; + int err = 0; - read_lock(&bond->lock); - bond_for_each_slave(bond, slave, i) { + bond_for_each_slave(bond, slave, iter) { err = slave_enable_netpoll(slave); if (err) { - __bond_netpoll_cleanup(bond); + bond_netpoll_cleanup(dev); break; } } - read_unlock(&bond->lock); return err; } - -static struct netpoll_info *bond_netpoll_info(struct bonding *bond) -{ - return bond->dev->npinfo; -} - #else static inline int slave_enable_netpoll(struct slave *slave) { @@ -1314,44 +993,31 @@ static void bond_netpoll_cleanup(struct net_device *bond_dev) /*---------------------------------- IOCTL ----------------------------------*/ -static int bond_sethwaddr(struct net_device *bond_dev, - struct net_device *slave_dev) -{ - 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; -} - static netdev_features_t bond_fix_features(struct net_device *dev, - netdev_features_t features) + netdev_features_t features) { - struct slave *slave; struct bonding *bond = netdev_priv(dev); + struct list_head *iter; netdev_features_t mask; - int i; - - read_lock(&bond->lock); + struct slave *slave; - if (!bond->first_slave) { + if (!bond_has_slaves(bond)) { /* Disable adding VLANs to empty bond. But why? --mq */ features |= NETIF_F_VLAN_CHALLENGED; - goto out; + return features; } mask = features; features &= ~NETIF_F_ONE_FOR_ALL; features |= NETIF_F_ALL_FOR_ALL; - bond_for_each_slave(bond, slave, i) { + bond_for_each_slave(bond, slave, iter) { features = netdev_increment_features(features, slave->dev->features, mask); } + features = netdev_add_tso_features(features, mask); -out: - read_unlock(&bond->lock); return features; } @@ -1359,32 +1025,49 @@ out: NETIF_F_FRAGLIST | NETIF_F_ALL_TSO | \ NETIF_F_HIGHDMA | NETIF_F_LRO) +#define BOND_ENC_FEATURES (NETIF_F_ALL_CSUM | NETIF_F_SG | NETIF_F_RXCSUM |\ + NETIF_F_TSO | NETIF_F_GSO_UDP_TUNNEL) + static void bond_compute_features(struct bonding *bond) { - struct slave *slave; - struct net_device *bond_dev = bond->dev; + unsigned int flags, dst_release_flag = IFF_XMIT_DST_RELEASE; netdev_features_t vlan_features = BOND_VLAN_FEATURES; + netdev_features_t enc_features = BOND_ENC_FEATURES; + struct net_device *bond_dev = bond->dev; + struct list_head *iter; + struct slave *slave; unsigned short max_hard_header_len = ETH_HLEN; - int i; + unsigned int gso_max_size = GSO_MAX_SIZE; + u16 gso_max_segs = GSO_MAX_SEGS; - read_lock(&bond->lock); - - if (!bond->first_slave) + if (!bond_has_slaves(bond)) goto done; + vlan_features &= NETIF_F_ALL_FOR_ALL; - bond_for_each_slave(bond, slave, i) { + bond_for_each_slave(bond, slave, iter) { vlan_features = netdev_increment_features(vlan_features, slave->dev->vlan_features, BOND_VLAN_FEATURES); + enc_features = netdev_increment_features(enc_features, + slave->dev->hw_enc_features, + BOND_ENC_FEATURES); + dst_release_flag &= slave->dev->priv_flags; if (slave->dev->hard_header_len > max_hard_header_len) max_hard_header_len = slave->dev->hard_header_len; + + gso_max_size = min(gso_max_size, slave->dev->gso_max_size); + gso_max_segs = min(gso_max_segs, slave->dev->gso_max_segs); } done: bond_dev->vlan_features = vlan_features; + bond_dev->hw_enc_features = enc_features; bond_dev->hard_header_len = max_hard_header_len; + bond_dev->gso_max_segs = gso_max_segs; + netif_set_gso_max_size(bond_dev, gso_max_size); - read_unlock(&bond->lock); + flags = bond_dev->priv_flags & ~IFF_XMIT_DST_RELEASE; + bond_dev->priv_flags = flags | dst_release_flag; netdev_change_features(bond_dev); } @@ -1392,8 +1075,6 @@ done: static void bond_setup_by_slave(struct net_device *bond_dev, struct net_device *slave_dev) { - struct bonding *bond = netdev_priv(bond_dev); - bond_dev->header_ops = slave_dev->header_ops; bond_dev->type = slave_dev->type; @@ -1402,7 +1083,6 @@ static void bond_setup_by_slave(struct net_device *bond_dev, memcpy(bond_dev->broadcast, slave_dev->broadcast, slave_dev->addr_len); - bond->setup_by_slave = 1; } /* On bonding slaves other than the currently active slave, suppress @@ -1413,7 +1093,7 @@ static bool bond_should_deliver_exact_match(struct sk_buff *skb, struct bonding *bond) { if (bond_is_slave_inactive(slave)) { - if (bond->params.mode == BOND_MODE_ALB && + if (BOND_MODE(bond) == BOND_MODE_ALB && skb->pkt_type != PACKET_BROADCAST && skb->pkt_type != PACKET_MULTICAST) return false; @@ -1427,8 +1107,9 @@ static rx_handler_result_t bond_handle_frame(struct sk_buff **pskb) struct sk_buff *skb = *pskb; struct slave *slave; struct bonding *bond; - void (*recv_probe)(struct sk_buff *, struct bonding *, - struct slave *); + int (*recv_probe)(const struct sk_buff *, struct bonding *, + struct slave *); + int ret = RX_HANDLER_ANOTHER; skb = skb_share_check(skb, GFP_ATOMIC); if (unlikely(!skb)) @@ -1439,16 +1120,12 @@ static rx_handler_result_t bond_handle_frame(struct sk_buff **pskb) slave = bond_slave_get_rcu(skb->dev); bond = slave->bond; - if (bond->params.arp_interval) - slave->dev->last_rx = jiffies; - recv_probe = ACCESS_ONCE(bond->recv_probe); if (recv_probe) { - struct sk_buff *nskb = skb_clone(skb, GFP_ATOMIC); - - if (likely(nskb)) { - recv_probe(nskb, bond, slave); - dev_kfree_skb(nskb); + ret = recv_probe(skb, bond, slave); + if (ret == RX_HANDLER_CONSUMED) { + consume_skb(skb); + return ret; } } @@ -1458,7 +1135,7 @@ static rx_handler_result_t bond_handle_frame(struct sk_buff **pskb) skb->dev = bond->dev; - if (bond->params.mode == BOND_MODE_ALB && + if (BOND_MODE(bond) == BOND_MODE_ALB && bond->dev->priv_flags & IFF_BRIDGE_PORT && skb->pkt_type == PACKET_HOST) { @@ -1467,10 +1144,61 @@ static rx_handler_result_t bond_handle_frame(struct sk_buff **pskb) kfree_skb(skb); return RX_HANDLER_CONSUMED; } - memcpy(eth_hdr(skb)->h_dest, bond->dev->dev_addr, ETH_ALEN); + ether_addr_copy(eth_hdr(skb)->h_dest, bond->dev->dev_addr); } - return RX_HANDLER_ANOTHER; + return ret; +} + +static int bond_master_upper_dev_link(struct net_device *bond_dev, + struct net_device *slave_dev, + struct slave *slave) +{ + int err; + + err = netdev_master_upper_dev_link_private(slave_dev, bond_dev, slave); + if (err) + return err; + slave_dev->flags |= IFF_SLAVE; + rtmsg_ifinfo(RTM_NEWLINK, slave_dev, IFF_SLAVE, GFP_KERNEL); + return 0; +} + +static void bond_upper_dev_unlink(struct net_device *bond_dev, + struct net_device *slave_dev) +{ + netdev_upper_dev_unlink(slave_dev, bond_dev); + slave_dev->flags &= ~IFF_SLAVE; + rtmsg_ifinfo(RTM_NEWLINK, slave_dev, IFF_SLAVE, GFP_KERNEL); +} + +static struct slave *bond_alloc_slave(struct bonding *bond) +{ + struct slave *slave = NULL; + + slave = kzalloc(sizeof(struct slave), GFP_KERNEL); + if (!slave) + return NULL; + + if (BOND_MODE(bond) == BOND_MODE_8023AD) { + SLAVE_AD_INFO(slave) = kzalloc(sizeof(struct ad_slave_info), + GFP_KERNEL); + if (!SLAVE_AD_INFO(slave)) { + kfree(slave); + return NULL; + } + } + return slave; +} + +static void bond_free_slave(struct slave *slave) +{ + struct bonding *bond = bond_get_bond_by_slave(slave); + + if (BOND_MODE(bond) == BOND_MODE_8023AD) + kfree(SLAVE_AD_INFO(slave)); + + kfree(slave); } /* enslave device <slave> to bond device <master> */ @@ -1478,36 +1206,41 @@ int bond_enslave(struct net_device *bond_dev, struct net_device *slave_dev) { struct bonding *bond = netdev_priv(bond_dev); const struct net_device_ops *slave_ops = slave_dev->netdev_ops; - struct slave *new_slave = NULL; - struct netdev_hw_addr *ha; + struct slave *new_slave = NULL, *prev_slave; struct sockaddr addr; int link_reporting; - int res = 0; + int res = 0, i; - if (!bond->params.use_carrier && slave_dev->ethtool_ops == NULL && - slave_ops->ndo_do_ioctl == NULL) { - pr_warning("%s: Warning: no link monitoring support for %s\n", - bond_dev->name, slave_dev->name); + if (!bond->params.use_carrier && + slave_dev->ethtool_ops->get_link == NULL && + slave_ops->ndo_do_ioctl == NULL) { + pr_warn("%s: Warning: no link monitoring support for %s\n", + bond_dev->name, slave_dev->name); } /* already enslaved */ if (slave_dev->flags & IFF_SLAVE) { - pr_debug("Error, Device was already enslaved\n"); + pr_debug("Error: Device was already enslaved\n"); return -EBUSY; } + if (bond_dev == slave_dev) { + pr_err("%s: cannot enslave bond to itself.\n", bond_dev->name); + return -EPERM; + } + /* vlan challenged mutual exclusion */ /* no need to lock since we're protected by rtnl_lock */ if (slave_dev->features & NETIF_F_VLAN_CHALLENGED) { pr_debug("%s: NETIF_F_VLAN_CHALLENGED\n", slave_dev->name); - if (bond_vlan_used(bond)) { + if (vlan_uses_dev(bond_dev)) { pr_err("%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 { - pr_warning("%s: Warning: enslaved VLAN challenged slave %s. Adding VLANs will be blocked as long as %s is part of bond %s\n", - bond_dev->name, slave_dev->name, - slave_dev->name, bond_dev->name); + pr_warn("%s: Warning: enslaved VLAN challenged slave %s. Adding VLANs will be blocked as long as %s is part of bond %s\n", + bond_dev->name, slave_dev->name, + slave_dev->name, bond_dev->name); } } else { pr_debug("%s: ! NETIF_F_VLAN_CHALLENGED\n", slave_dev->name); @@ -1520,7 +1253,7 @@ int bond_enslave(struct net_device *bond_dev, struct net_device *slave_dev) * enslaving it; the old ifenslave will not. */ if ((slave_dev->flags & IFF_UP)) { - pr_err("%s is up. This may be due to an out of date ifenslave.\n", + pr_err("%s is up - this may be due to an out of date ifenslave\n", slave_dev->name); res = -EPERM; goto err_undo_flags; @@ -1533,14 +1266,14 @@ int bond_enslave(struct net_device *bond_dev, struct net_device *slave_dev) * bond ether type mutual exclusion - don't allow slaves of dissimilar * ether type (eg ARPHRD_ETHER and ARPHRD_INFINIBAND) share the same bond */ - if (bond->slave_cnt == 0) { + if (!bond_has_slaves(bond)) { if (bond_dev->type != slave_dev->type) { pr_debug("%s: change device type from %d to %d\n", bond_dev->name, bond_dev->type, slave_dev->type); - res = netdev_bonding_change(bond_dev, - NETDEV_PRE_TYPE_CHANGE); + res = call_netdevice_notifiers(NETDEV_PRE_TYPE_CHANGE, + bond_dev); res = notifier_to_errno(res); if (res) { pr_err("%s: refused to change device type\n", @@ -1560,24 +1293,27 @@ int bond_enslave(struct net_device *bond_dev, struct net_device *slave_dev) bond_dev->priv_flags &= ~IFF_TX_SKB_SHARING; } - netdev_bonding_change(bond_dev, - NETDEV_POST_TYPE_CHANGE); + call_netdevice_notifiers(NETDEV_POST_TYPE_CHANGE, + bond_dev); } } else if (bond_dev->type != slave_dev->type) { - pr_err("%s ether type (%d) is different from other slaves (%d), can not enslave it.\n", - slave_dev->name, - slave_dev->type, bond_dev->type); + pr_err("%s ether type (%d) is different from other slaves (%d), can not enslave it\n", + slave_dev->name, slave_dev->type, bond_dev->type); res = -EINVAL; goto err_undo_flags; } if (slave_ops->ndo_set_mac_address == NULL) { - if (bond->slave_cnt == 0) { - pr_warning("%s: Warning: The first slave device specified does not support setting the MAC address. Setting fail_over_mac to active.", - bond_dev->name); - bond->params.fail_over_mac = BOND_FOM_ACTIVE; + if (!bond_has_slaves(bond)) { + pr_warn("%s: Warning: The first slave device specified does not support setting the MAC address\n", + bond_dev->name); + if (BOND_MODE(bond) == BOND_MODE_ACTIVEBACKUP) { + bond->params.fail_over_mac = BOND_FOM_ACTIVE; + pr_warn("%s: Setting fail_over_mac to active for active-backup mode\n", + bond_dev->name); + } } else if (bond->params.fail_over_mac != BOND_FOM_ACTIVE) { - pr_err("%s: Error: The slave device specified does not support setting the MAC address, but fail_over_mac is not set to active.\n", + pr_err("%s: Error: The slave device specified does not support setting the MAC address, but fail_over_mac is not set to active\n", bond_dev->name); res = -EOPNOTSUPP; goto err_undo_flags; @@ -1588,17 +1324,18 @@ int bond_enslave(struct net_device *bond_dev, struct net_device *slave_dev) /* If this is the first slave, then we need to set the master's hardware * address to be the same as the slave's. */ - if (is_zero_ether_addr(bond->dev->dev_addr)) - memcpy(bond->dev->dev_addr, slave_dev->dev_addr, - slave_dev->addr_len); + if (!bond_has_slaves(bond) && + bond->dev->addr_assign_type == NET_ADDR_RANDOM) + bond_set_dev_addr(bond->dev, slave_dev); - - new_slave = kzalloc(sizeof(struct slave), GFP_KERNEL); + new_slave = bond_alloc_slave(bond); if (!new_slave) { res = -ENOMEM; goto err_undo_flags; } + new_slave->bond = bond; + new_slave->dev = slave_dev; /* * Set the new_slave's queue_id to be zero. Queue ID mapping * is set via sysfs or module option if desired. @@ -1618,9 +1355,10 @@ int bond_enslave(struct net_device *bond_dev, struct net_device *slave_dev) * that need it, and for restoring it upon release, and then * set it to the master's address */ - memcpy(new_slave->perm_hwaddr, slave_dev->dev_addr, ETH_ALEN); + ether_addr_copy(new_slave->perm_hwaddr, slave_dev->dev_addr); - if (!bond->params.fail_over_mac) { + if (!bond->params.fail_over_mac || + BOND_MODE(bond) != BOND_MODE_ACTIVEBACKUP) { /* * Set slave to master's mac address. The application already * set the master's mac address to that of the first slave @@ -1634,21 +1372,13 @@ int bond_enslave(struct net_device *bond_dev, struct net_device *slave_dev) } } - res = netdev_set_bond_master(slave_dev, bond_dev); - if (res) { - pr_debug("Error %d calling netdev_set_bond_master\n", res); - goto err_restore_mac; - } - /* open the slave since the application closed it */ res = dev_open(slave_dev); if (res) { pr_debug("Opening slave %s failed\n", slave_dev->name); - goto err_unset_master; + goto err_restore_mac; } - new_slave->bond = bond; - new_slave->dev = slave_dev; slave_dev->priv_flags |= IFF_BONDING; if (bond_is_lb(bond)) { @@ -1660,12 +1390,10 @@ int bond_enslave(struct net_device *bond_dev, struct net_device *slave_dev) goto err_close; } - /* If the mode USES_PRIMARY, then the new slave gets the - * master's promisc (and mc) settings only if it becomes the - * curr_active_slave, and that is taken care of later when calling - * bond_change_active() + /* If the mode uses primary, then the following is handled by + * bond_change_active_slave(). */ - if (!USES_PRIMARY(bond->params.mode)) { + if (!bond_uses_primary(bond)) { /* set promiscuity level to new slave */ if (bond_dev->flags & IFF_PROMISC) { res = dev_set_promiscuity(slave_dev, 1); @@ -1681,35 +1409,38 @@ int bond_enslave(struct net_device *bond_dev, struct net_device *slave_dev) } netif_addr_lock_bh(bond_dev); - /* upload master's mc_list to new slave */ - netdev_for_each_mc_addr(ha, bond_dev) - dev_mc_add(slave_dev, ha->addr); + + dev_mc_sync_multiple(slave_dev, bond_dev); + dev_uc_sync_multiple(slave_dev, bond_dev); + netif_addr_unlock_bh(bond_dev); } - if (bond->params.mode == BOND_MODE_8023AD) { + if (BOND_MODE(bond) == BOND_MODE_8023AD) { /* add lacpdu mc addr to mc list */ u8 lacpdu_multicast[ETH_ALEN] = MULTICAST_LACPDU_ADDR; dev_mc_add(slave_dev, lacpdu_multicast); } - bond_add_vlans_on_slave(bond, slave_dev); - - write_lock_bh(&bond->lock); + res = vlan_vids_add_by_dev(slave_dev, bond_dev); + if (res) { + pr_err("%s: Error: Couldn't add bond vlan ids to %s\n", + bond_dev->name, slave_dev->name); + goto err_close; + } - bond_attach_slave(bond, new_slave); + prev_slave = bond_last_slave(bond); new_slave->delay = 0; new_slave->link_failure_count = 0; - write_unlock_bh(&bond->lock); - - bond_compute_features(bond); - - read_lock(&bond->lock); + bond_update_speed_duplex(new_slave); - new_slave->last_arp_rx = jiffies; + new_slave->last_rx = jiffies - + (msecs_to_jiffies(bond->params.arp_interval) + 1); + for (i = 0; i < BOND_MAX_ARP_TARGETS; i++) + new_slave->target_last_arp_rx[i] = new_slave->last_rx; if (bond->params.miimon && !bond->params.use_carrier) { link_reporting = bond_check_dev_link(bond, slave_dev, 1); @@ -1724,35 +1455,41 @@ 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. */ - pr_warning("%s: Warning: MII and ETHTOOL support not available for interface %s, and arp_interval/arp_ip_target module parameters not specified, thus bonding will not detect link failures! see bonding.txt for details.\n", - bond_dev->name, slave_dev->name); + pr_warn("%s: Warning: MII and ETHTOOL support not available for interface %s, and arp_interval/arp_ip_target module parameters not specified, thus bonding will not detect link failures! see bonding.txt for details\n", + bond_dev->name, slave_dev->name); } else if (link_reporting == -1) { /* unable get link status using mii/ethtool */ - pr_warning("%s: Warning: can't get link status from interface %s; the network driver associated with this interface does not support MII or ETHTOOL link status reporting, thus miimon has no effect on this interface.\n", - bond_dev->name, slave_dev->name); + pr_warn("%s: Warning: can't get link status from interface %s; the network driver associated with this interface does not support MII or ETHTOOL link status reporting, thus miimon has no effect on this interface\n", + bond_dev->name, slave_dev->name); } } /* check for initial state */ - if (!bond->params.miimon || - (bond_check_dev_link(bond, slave_dev, 0) == BMSR_LSTATUS)) { - if (bond->params.updelay) { - pr_debug("Initial state of slave_dev is BOND_LINK_BACK\n"); - new_slave->link = BOND_LINK_BACK; - new_slave->delay = bond->params.updelay; + if (bond->params.miimon) { + if (bond_check_dev_link(bond, slave_dev, 0) == BMSR_LSTATUS) { + if (bond->params.updelay) { + new_slave->link = BOND_LINK_BACK; + new_slave->delay = bond->params.updelay; + } else { + new_slave->link = BOND_LINK_UP; + } } else { - pr_debug("Initial state of slave_dev is BOND_LINK_UP\n"); - new_slave->link = BOND_LINK_UP; + new_slave->link = BOND_LINK_DOWN; } - new_slave->jiffies = jiffies; + } else if (bond->params.arp_interval) { + new_slave->link = (netif_carrier_ok(slave_dev) ? + BOND_LINK_UP : BOND_LINK_DOWN); } else { - pr_debug("Initial state of slave_dev is BOND_LINK_DOWN\n"); - new_slave->link = BOND_LINK_DOWN; + new_slave->link = BOND_LINK_UP; } - bond_update_speed_duplex(new_slave); + if (new_slave->link != BOND_LINK_DOWN) + new_slave->last_link_up = jiffies; + pr_debug("Initial state of slave_dev is BOND_LINK_%s\n", + new_slave->link == BOND_LINK_DOWN ? "DOWN" : + (new_slave->link == BOND_LINK_UP ? "UP" : "BACK")); - if (USES_PRIMARY(bond->params.mode) && bond->params.primary[0]) { + if (bond_uses_primary(bond) && bond->params.primary[0]) { /* if there is a primary slave, remember it */ if (strcmp(bond->params.primary, new_slave->dev->name) == 0) { bond->primary_slave = new_slave; @@ -1760,29 +1497,27 @@ int bond_enslave(struct net_device *bond_dev, struct net_device *slave_dev) } } - write_lock_bh(&bond->curr_slave_lock); - - switch (bond->params.mode) { + switch (BOND_MODE(bond)) { case BOND_MODE_ACTIVEBACKUP: - bond_set_slave_inactive_flags(new_slave); - bond_select_active_slave(bond); + bond_set_slave_inactive_flags(new_slave, + BOND_SLAVE_NOTIFY_NOW); break; case BOND_MODE_8023AD: /* in 802.3ad mode, the internal mechanism * will activate the slaves in the selected * aggregator */ - bond_set_slave_inactive_flags(new_slave); + bond_set_slave_inactive_flags(new_slave, BOND_SLAVE_NOTIFY_NOW); /* if this is the first slave */ - if (bond->slave_cnt == 1) { - SLAVE_AD_INFO(new_slave).id = 1; + if (!prev_slave) { + SLAVE_AD_INFO(new_slave)->id = 1; /* Initialize AD with the number of times that the AD timer is called in 1 second * can be called only after the mac address of the bond is set */ bond_3ad_initialize(bond, 1000/AD_TIMER_INTERVAL); } else { - SLAVE_AD_INFO(new_slave).id = - SLAVE_AD_INFO(new_slave->prev).id + 1; + SLAVE_AD_INFO(new_slave)->id = + SLAVE_AD_INFO(prev_slave)->id + 1; } bond_3ad_bind_slave(new_slave); @@ -1790,8 +1525,7 @@ int bond_enslave(struct net_device *bond_dev, struct net_device *slave_dev) case BOND_MODE_TLB: case BOND_MODE_ALB: bond_set_active_slave(new_slave); - bond_set_slave_inactive_flags(new_slave); - bond_select_active_slave(bond); + bond_set_slave_inactive_flags(new_slave, BOND_SLAVE_NOTIFY_NOW); break; default: pr_debug("This slave is always active in trunk mode\n"); @@ -1803,73 +1537,99 @@ 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) - bond->curr_active_slave = new_slave; + if (!bond->curr_active_slave && new_slave->link == BOND_LINK_UP) + rcu_assign_pointer(bond->curr_active_slave, new_slave); break; } /* switch(bond_mode) */ - write_unlock_bh(&bond->curr_slave_lock); - - bond_set_carrier(bond); - #ifdef CONFIG_NET_POLL_CONTROLLER - slave_dev->npinfo = bond_netpoll_info(bond); + slave_dev->npinfo = bond->dev->npinfo; if (slave_dev->npinfo) { if (slave_enable_netpoll(new_slave)) { - read_unlock(&bond->lock); - pr_info("Error, %s: master_dev is using netpoll, " - "but new slave device does not support netpoll.\n", - bond_dev->name); + pr_info("Error, %s: master_dev is using netpoll, but new slave device does not support netpoll\n", + bond_dev->name); res = -EBUSY; goto err_detach; } } #endif - read_unlock(&bond->lock); - - res = bond_create_slave_symlinks(bond_dev, slave_dev); - if (res) - goto err_detach; - res = netdev_rx_handler_register(slave_dev, bond_handle_frame, new_slave); if (res) { pr_debug("Error %d calling netdev_rx_handler_register\n", res); - goto err_dest_symlinks; + goto err_detach; } - pr_info("%s: enslaving %s as a%s interface with a%s link.\n", + res = bond_master_upper_dev_link(bond_dev, slave_dev, new_slave); + if (res) { + pr_debug("Error %d calling bond_master_upper_dev_link\n", res); + goto err_unregister; + } + + res = bond_sysfs_slave_add(new_slave); + if (res) { + pr_debug("Error %d calling bond_sysfs_slave_add\n", res); + goto err_upper_unlink; + } + + bond->slave_cnt++; + bond_compute_features(bond); + bond_set_carrier(bond); + + if (bond_uses_primary(bond)) { + block_netpoll_tx(); + write_lock_bh(&bond->curr_slave_lock); + bond_select_active_slave(bond); + write_unlock_bh(&bond->curr_slave_lock); + unblock_netpoll_tx(); + } + + pr_info("%s: Enslaving %s as %s interface with %s link\n", bond_dev->name, slave_dev->name, - bond_is_active_slave(new_slave) ? "n active" : " backup", - new_slave->link != BOND_LINK_DOWN ? "n up" : " down"); + bond_is_active_slave(new_slave) ? "an active" : "a backup", + new_slave->link != BOND_LINK_DOWN ? "an up" : "a down"); /* enslave is successful */ return 0; /* Undo stages on error */ -err_dest_symlinks: - bond_destroy_slave_symlinks(bond_dev, slave_dev); +err_upper_unlink: + bond_upper_dev_unlink(bond_dev, slave_dev); + +err_unregister: + netdev_rx_handler_unregister(slave_dev); err_detach: - write_lock_bh(&bond->lock); - bond_detach_slave(bond, new_slave); - write_unlock_bh(&bond->lock); + if (!bond_uses_primary(bond)) + bond_hw_addr_flush(bond_dev, slave_dev); + + vlan_vids_del_by_dev(slave_dev, bond_dev); + if (bond->primary_slave == new_slave) + bond->primary_slave = NULL; + if (bond->curr_active_slave == new_slave) { + block_netpoll_tx(); + write_lock_bh(&bond->curr_slave_lock); + bond_change_active_slave(bond, NULL); + bond_select_active_slave(bond); + write_unlock_bh(&bond->curr_slave_lock); + unblock_netpoll_tx(); + } + slave_disable_netpoll(new_slave); err_close: + slave_dev->priv_flags &= ~IFF_BONDING; dev_close(slave_dev); -err_unset_master: - netdev_set_bond_master(slave_dev, NULL); - err_restore_mac: - if (!bond->params.fail_over_mac) { + if (!bond->params.fail_over_mac || + BOND_MODE(bond) != BOND_MODE_ACTIVEBACKUP) { /* 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); + ether_addr_copy(addr.sa_data, new_slave->perm_hwaddr); addr.sa_family = slave_dev->type; dev_set_mac_address(slave_dev, &addr); } @@ -1878,10 +1638,13 @@ err_restore_mtu: dev_set_mtu(slave_dev, new_slave->original_mtu); err_free: - kfree(new_slave); + bond_free_slave(new_slave); err_undo_flags: - bond_compute_features(bond); + /* Enslave of first slave has failed and we need to fix master's mac */ + if (!bond_has_slaves(bond) && + ether_addr_equal_64bits(bond_dev->dev_addr, slave_dev->dev_addr)) + eth_hw_addr_random(bond_dev); return res; } @@ -1889,7 +1652,8 @@ err_undo_flags: /* * Try to release the slave device <slave> from the bond device <master> * It is legal to access curr_active_slave without a lock because all the function - * is write-locked. + * is write-locked. If "all" is true it means that the function is being called + * while destroying a bond interface and all slaves are being released. * * The rules for slave state should be: * for Active/Backup: @@ -1897,61 +1661,51 @@ err_undo_flags: * for Bonded connections: * The first up interface should be left on and all others downed. */ -int bond_release(struct net_device *bond_dev, struct net_device *slave_dev) +static int __bond_release_one(struct net_device *bond_dev, + struct net_device *slave_dev, + bool all) { struct bonding *bond = netdev_priv(bond_dev); struct slave *slave, *oldcurrent; struct sockaddr addr; + int old_flags = bond_dev->flags; netdev_features_t old_features = bond_dev->features; /* slave is not a slave or master is not master of this slave */ if (!(slave_dev->flags & IFF_SLAVE) || - (slave_dev->master != bond_dev)) { - pr_err("%s: Error: cannot release %s.\n", + !netdev_has_upper_dev(slave_dev, bond_dev)) { + pr_err("%s: Error: cannot release %s\n", bond_dev->name, slave_dev->name); return -EINVAL; } block_netpoll_tx(); - netdev_bonding_change(bond_dev, NETDEV_RELEASE); - write_lock_bh(&bond->lock); slave = bond_get_slave_by_dev(bond, slave_dev); if (!slave) { /* not a slave of this bond */ pr_info("%s: %s not enslaved\n", bond_dev->name, slave_dev->name); - write_unlock_bh(&bond->lock); unblock_netpoll_tx(); return -EINVAL; } + bond_sysfs_slave_del(slave); + + bond_upper_dev_unlink(bond_dev, slave_dev); /* unregister rx_handler early so bond_handle_frame wouldn't be called * for this slave anymore. */ netdev_rx_handler_unregister(slave_dev); - write_unlock_bh(&bond->lock); - synchronize_net(); write_lock_bh(&bond->lock); - if (!bond->params.fail_over_mac) { - if (!compare_ether_addr(bond_dev->dev_addr, slave->perm_hwaddr) && - bond->slave_cnt > 1) - pr_warning("%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. */ - if (bond->params.mode == BOND_MODE_8023AD) { - /* must be called before the slave is - * detached from the list - */ + if (BOND_MODE(bond) == BOND_MODE_8023AD) bond_3ad_unbind_slave(slave); - } - pr_info("%s: releasing %s interface %s\n", + write_unlock_bh(&bond->lock); + + pr_info("%s: Releasing %s interface %s\n", bond_dev->name, bond_is_active_slave(slave) ? "active" : "backup", slave_dev->name); @@ -1960,14 +1714,24 @@ int bond_release(struct net_device *bond_dev, struct net_device *slave_dev) bond->current_arp_slave = NULL; - /* release the slave from its bond */ - bond_detach_slave(bond, slave); + if (!all && (!bond->params.fail_over_mac || + BOND_MODE(bond) != BOND_MODE_ACTIVEBACKUP)) { + if (ether_addr_equal_64bits(bond_dev->dev_addr, slave->perm_hwaddr) && + bond_has_slaves(bond)) + pr_warn("%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); + } if (bond->primary_slave == slave) bond->primary_slave = NULL; - if (oldcurrent == slave) + if (oldcurrent == slave) { + write_lock_bh(&bond->curr_slave_lock); bond_change_active_slave(bond, NULL); + write_unlock_bh(&bond->curr_slave_lock); + } if (bond_is_lb(bond)) { /* Must be called only after the slave has been @@ -1975,88 +1739,84 @@ int bond_release(struct net_device *bond_dev, struct net_device *slave_dev) * has been cleared (if our_slave == old_current), * but before a new active slave is selected. */ - write_unlock_bh(&bond->lock); bond_alb_deinit_slave(bond, slave); - write_lock_bh(&bond->lock); } - if (oldcurrent == slave) { + if (all) { + RCU_INIT_POINTER(bond->curr_active_slave, NULL); + } else if (oldcurrent == slave) { /* * Note that we hold RTNL over this sequence, so there * is no concern that another slave add/remove event * will interfere. */ - write_unlock_bh(&bond->lock); - read_lock(&bond->lock); write_lock_bh(&bond->curr_slave_lock); bond_select_active_slave(bond); write_unlock_bh(&bond->curr_slave_lock); - read_unlock(&bond->lock); - write_lock_bh(&bond->lock); } - if (bond->slave_cnt == 0) { + if (!bond_has_slaves(bond)) { bond_set_carrier(bond); + eth_hw_addr_random(bond_dev); - /* if the last slave was removed, zero the mac address - * of the master so it will be set by the application - * to the mac address of the first slave - */ - memset(bond_dev->dev_addr, 0, bond_dev->addr_len); - - if (bond_vlan_used(bond)) { - pr_warning("%s: Warning: clearing HW address of %s while it still has VLANs.\n", - bond_dev->name, bond_dev->name); - pr_warning("%s: When re-adding slaves, make sure the bond's HW address matches its VLANs'.\n", - bond_dev->name); + if (vlan_uses_dev(bond_dev)) { + pr_warn("%s: Warning: clearing HW address of %s while it still has VLANs\n", + bond_dev->name, bond_dev->name); + pr_warn("%s: When re-adding slaves, make sure the bond's HW address matches its VLANs\n", + bond_dev->name); } } - write_unlock_bh(&bond->lock); unblock_netpoll_tx(); + synchronize_rcu(); + bond->slave_cnt--; + + if (!bond_has_slaves(bond)) { + call_netdevice_notifiers(NETDEV_CHANGEADDR, bond->dev); + call_netdevice_notifiers(NETDEV_RELEASE, bond->dev); + } bond_compute_features(bond); if (!(bond_dev->features & NETIF_F_VLAN_CHALLENGED) && (old_features & NETIF_F_VLAN_CHALLENGED)) - pr_info("%s: last VLAN challenged slave %s left bond %s. VLAN blocking is removed\n", + pr_info("%s: last VLAN challenged slave %s left bond %s - VLAN blocking is removed\n", bond_dev->name, slave_dev->name, bond_dev->name); /* must do this from outside any spinlocks */ - bond_destroy_slave_symlinks(bond_dev, slave_dev); - - bond_del_vlans_from_slave(bond, slave_dev); + vlan_vids_del_by_dev(slave_dev, bond_dev); - /* If the mode USES_PRIMARY, then we should only remove its - * promisc and mc settings if it was the curr_active_slave, but that was - * already taken care of above when we detached the slave + /* If the mode uses primary, then this cases was handled above by + * bond_change_active_slave(..., NULL) */ - if (!USES_PRIMARY(bond->params.mode)) { - /* unset promiscuity level from slave */ - if (bond_dev->flags & IFF_PROMISC) + if (!bond_uses_primary(bond)) { + /* unset promiscuity level from slave + * NOTE: The NETDEV_CHANGEADDR call above may change the value + * of the IFF_PROMISC flag in the bond_dev, but we need the + * value of that flag before that change, as that was the value + * when this slave was attached, so we cache at the start of the + * function and use it here. Same goes for ALLMULTI below + */ + if (old_flags & IFF_PROMISC) dev_set_promiscuity(slave_dev, -1); /* unset allmulti level from slave */ - if (bond_dev->flags & IFF_ALLMULTI) + if (old_flags & IFF_ALLMULTI) dev_set_allmulti(slave_dev, -1); - /* flush master's mc_list from slave */ - netif_addr_lock_bh(bond_dev); - bond_mc_list_flush(bond_dev, slave_dev); - netif_addr_unlock_bh(bond_dev); + bond_hw_addr_flush(bond_dev, slave_dev); } - netdev_set_bond_master(slave_dev, NULL); - slave_disable_netpoll(slave); /* close slave before restoring its mac address */ dev_close(slave_dev); - if (bond->params.fail_over_mac != BOND_FOM_ACTIVE) { + if (bond->params.fail_over_mac != BOND_FOM_ACTIVE || + BOND_MODE(bond) != BOND_MODE_ACTIVEBACKUP) { /* restore original ("permanent") mac address */ - memcpy(addr.sa_data, slave->perm_hwaddr, ETH_ALEN); + ether_addr_copy(addr.sa_data, slave->perm_hwaddr); addr.sa_family = slave_dev->type; dev_set_mac_address(slave_dev, &addr); } @@ -2065,11 +1825,17 @@ int bond_release(struct net_device *bond_dev, struct net_device *slave_dev) slave_dev->priv_flags &= ~IFF_BONDING; - kfree(slave); + bond_free_slave(slave); return 0; /* deletion OK */ } +/* A wrapper used because of ndo_del_link */ +int bond_release(struct net_device *bond_dev, struct net_device *slave_dev) +{ + return __bond_release_one(bond_dev, slave_dev, false); +} + /* * First release a slave and then destroy the bond if no more slaves are left. * Must be under rtnl_lock when this function is called. @@ -2081,198 +1847,23 @@ static int bond_release_and_destroy(struct net_device *bond_dev, int ret; ret = bond_release(bond_dev, slave_dev); - if ((ret == 0) && (bond->slave_cnt == 0)) { + if (ret == 0 && !bond_has_slaves(bond)) { bond_dev->priv_flags |= IFF_DISABLE_NETPOLL; - pr_info("%s: destroying bond %s.\n", + pr_info("%s: Destroying bond %s\n", bond_dev->name, bond_dev->name); unregister_netdevice(bond_dev); } return ret; } -/* - * This function releases all slaves. - */ -static int bond_release_all(struct net_device *bond_dev) -{ - struct bonding *bond = netdev_priv(bond_dev); - struct slave *slave; - struct net_device *slave_dev; - struct sockaddr addr; - - write_lock_bh(&bond->lock); - - netif_carrier_off(bond_dev); - - if (bond->slave_cnt == 0) - goto out; - - bond->current_arp_slave = NULL; - bond->primary_slave = NULL; - bond_change_active_slave(bond, NULL); - - while ((slave = bond->first_slave) != NULL) { - /* Inform AD package of unbinding of slave - * before slave is detached from the list. - */ - if (bond->params.mode == BOND_MODE_8023AD) - bond_3ad_unbind_slave(slave); - - slave_dev = slave->dev; - bond_detach_slave(bond, slave); - - /* now that the slave is detached, unlock and perform - * all the undo steps that should not be called from - * within a lock. - */ - write_unlock_bh(&bond->lock); - - /* unregister rx_handler early so bond_handle_frame wouldn't - * be called for this slave anymore. - */ - netdev_rx_handler_unregister(slave_dev); - synchronize_net(); - - if (bond_is_lb(bond)) { - /* must be called only after the slave - * has been detached from the list - */ - bond_alb_deinit_slave(bond, slave); - } - - bond_destroy_slave_symlinks(bond_dev, slave_dev); - bond_del_vlans_from_slave(bond, slave_dev); - - /* If the mode USES_PRIMARY, then we should only remove its - * promisc and mc settings if it was the curr_active_slave, but that was - * already taken care of above when we detached the slave - */ - if (!USES_PRIMARY(bond->params.mode)) { - /* unset promiscuity level from slave */ - if (bond_dev->flags & IFF_PROMISC) - dev_set_promiscuity(slave_dev, -1); - - /* unset allmulti level from slave */ - if (bond_dev->flags & IFF_ALLMULTI) - dev_set_allmulti(slave_dev, -1); - - /* flush master's mc_list from slave */ - netif_addr_lock_bh(bond_dev); - bond_mc_list_flush(bond_dev, slave_dev); - netif_addr_unlock_bh(bond_dev); - } - - netdev_set_bond_master(slave_dev, NULL); - - slave_disable_netpoll(slave); - - /* close slave before restoring its mac address */ - dev_close(slave_dev); - - if (!bond->params.fail_over_mac) { - /* restore original ("permanent") mac address*/ - memcpy(addr.sa_data, slave->perm_hwaddr, ETH_ALEN); - addr.sa_family = slave_dev->type; - dev_set_mac_address(slave_dev, &addr); - } - - kfree(slave); - - /* re-acquire the lock before getting the next slave */ - write_lock_bh(&bond->lock); - } - - /* zero the mac address of the master so it will be - * set by the application to the mac address of the - * first slave - */ - memset(bond_dev->dev_addr, 0, bond_dev->addr_len); - - if (bond_vlan_used(bond)) { - pr_warning("%s: Warning: clearing HW address of %s while it still has VLANs.\n", - bond_dev->name, bond_dev->name); - pr_warning("%s: When re-adding slaves, make sure the bond's HW address matches its VLANs'.\n", - bond_dev->name); - } - - pr_info("%s: released all slaves\n", bond_dev->name); - -out: - write_unlock_bh(&bond->lock); - - bond_compute_features(bond); - - return 0; -} - -/* - * This function changes the active slave to slave <slave_dev>. - * It returns -EINVAL in the following cases. - * - <slave_dev> is not found in the list. - * - There is not active slave now. - * - <slave_dev> is already active. - * - The link state of <slave_dev> is not BOND_LINK_UP. - * - <slave_dev> is not running. - * 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 = netdev_priv(bond_dev); - struct slave *old_active = NULL; - struct slave *new_active = NULL; - int res = 0; - - if (!USES_PRIMARY(bond->params.mode)) - return -EINVAL; - - /* Verify that master_dev is indeed the master of slave_dev */ - if (!(slave_dev->flags & IFF_SLAVE) || (slave_dev->master != bond_dev)) - return -EINVAL; - - read_lock(&bond->lock); - - read_lock(&bond->curr_slave_lock); - old_active = bond->curr_active_slave; - read_unlock(&bond->curr_slave_lock); - - new_active = bond_get_slave_by_dev(bond, slave_dev); - - /* - * Changing to the current active: do nothing; return success. - */ - if (new_active && (new_active == old_active)) { - read_unlock(&bond->lock); - return 0; - } - - if ((new_active) && - (old_active) && - (new_active->link == BOND_LINK_UP) && - IS_UP(new_active->dev)) { - block_netpoll_tx(); - write_lock_bh(&bond->curr_slave_lock); - bond_change_active_slave(bond, new_active); - write_unlock_bh(&bond->curr_slave_lock); - unblock_netpoll_tx(); - } else - res = -EINVAL; - - read_unlock(&bond->lock); - - return res; -} - static int bond_info_query(struct net_device *bond_dev, struct ifbond *info) { struct bonding *bond = netdev_priv(bond_dev); - info->bond_mode = bond->params.mode; + info->bond_mode = BOND_MODE(bond); info->miimon = bond->params.miimon; - read_lock(&bond->lock); info->num_slaves = bond->slave_cnt; - read_unlock(&bond->lock); return 0; } @@ -2280,13 +1871,12 @@ 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 = netdev_priv(bond_dev); + struct list_head *iter; + int i = 0, res = -ENODEV; struct slave *slave; - int i, res = -ENODEV; - read_lock(&bond->lock); - - bond_for_each_slave(bond, slave, i) { - if (i == (int)info->slave_id) { + bond_for_each_slave(bond, slave, iter) { + if (i++ == (int)info->slave_id) { res = 0; strcpy(info->slave_name, slave->dev->name); info->link = slave->link; @@ -2296,8 +1886,6 @@ static int bond_slave_info_query(struct net_device *bond_dev, struct ifslave *in } } - read_unlock(&bond->lock); - return res; } @@ -2306,13 +1894,14 @@ static int bond_slave_info_query(struct net_device *bond_dev, struct ifslave *in static int bond_miimon_inspect(struct bonding *bond) { + int link_state, commit = 0; + struct list_head *iter; struct slave *slave; - int i, link_state, commit = 0; bool ignore_updelay; ignore_updelay = !bond->curr_active_slave ? true : false; - bond_for_each_slave(bond, slave, i) { + bond_for_each_slave_rcu(bond, slave, iter) { slave->new_link = BOND_LINK_NOCHANGE; link_state = bond_check_dev_link(bond, slave->dev, 0); @@ -2325,9 +1914,9 @@ static int bond_miimon_inspect(struct bonding *bond) slave->link = BOND_LINK_FAIL; slave->delay = bond->params.downdelay; if (slave->delay) { - pr_info("%s: link status down for %sinterface %s, disabling it in %d ms.\n", + pr_info("%s: link status down for %sinterface %s, disabling it in %d ms\n", bond->dev->name, - (bond->params.mode == + (BOND_MODE(bond) == BOND_MODE_ACTIVEBACKUP) ? (bond_is_active_slave(slave) ? "active " : "backup ") : "", @@ -2341,8 +1930,8 @@ static int bond_miimon_inspect(struct bonding *bond) * recovered before downdelay expired */ slave->link = BOND_LINK_UP; - slave->jiffies = jiffies; - pr_info("%s: link status up again after %d ms for interface %s.\n", + slave->last_link_up = jiffies; + pr_info("%s: link status up again after %d ms for interface %s\n", bond->dev->name, (bond->params.downdelay - slave->delay) * bond->params.miimon, @@ -2367,7 +1956,7 @@ static int bond_miimon_inspect(struct bonding *bond) slave->delay = bond->params.updelay; if (slave->delay) { - pr_info("%s: link status up for interface %s, enabling it in %d ms.\n", + pr_info("%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 * @@ -2377,7 +1966,7 @@ static int bond_miimon_inspect(struct bonding *bond) case BOND_LINK_BACK: if (!link_state) { slave->link = BOND_LINK_DOWN; - pr_info("%s: link status down again after %d ms for interface %s.\n", + pr_info("%s: link status down again after %d ms for interface %s\n", bond->dev->name, (bond->params.updelay - slave->delay) * bond->params.miimon, @@ -2406,22 +1995,22 @@ static int bond_miimon_inspect(struct bonding *bond) static void bond_miimon_commit(struct bonding *bond) { + struct list_head *iter; struct slave *slave; - int i; - bond_for_each_slave(bond, slave, i) { + bond_for_each_slave(bond, slave, iter) { switch (slave->new_link) { case BOND_LINK_NOCHANGE: continue; case BOND_LINK_UP: slave->link = BOND_LINK_UP; - slave->jiffies = jiffies; + slave->last_link_up = jiffies; - if (bond->params.mode == BOND_MODE_8023AD) { + if (BOND_MODE(bond) == BOND_MODE_8023AD) { /* prevent it from being the active one */ bond_set_backup_slave(slave); - } else if (bond->params.mode != BOND_MODE_ACTIVEBACKUP) { + } else if (BOND_MODE(bond) != BOND_MODE_ACTIVEBACKUP) { /* make it immediately active */ bond_set_active_slave(slave); } else if (slave != bond->primary_slave) { @@ -2429,14 +2018,13 @@ static void bond_miimon_commit(struct bonding *bond) bond_set_backup_slave(slave); } - bond_update_speed_duplex(slave); - - pr_info("%s: link status definitely up for interface %s, %u Mbps %s duplex.\n", + pr_info("%s: link status definitely up for interface %s, %u Mbps %s duplex\n", bond->dev->name, slave->dev->name, - slave->speed, slave->duplex ? "full" : "half"); + slave->speed == SPEED_UNKNOWN ? 0 : slave->speed, + slave->duplex ? "full" : "half"); /* notify ad that the link status has changed */ - if (bond->params.mode == BOND_MODE_8023AD) + if (BOND_MODE(bond) == BOND_MODE_8023AD) bond_3ad_handle_link_change(slave, BOND_LINK_UP); if (bond_is_lb(bond)) @@ -2455,14 +2043,15 @@ static void bond_miimon_commit(struct bonding *bond) slave->link = BOND_LINK_DOWN; - if (bond->params.mode == BOND_MODE_ACTIVEBACKUP || - bond->params.mode == BOND_MODE_8023AD) - bond_set_slave_inactive_flags(slave); + if (BOND_MODE(bond) == BOND_MODE_ACTIVEBACKUP || + BOND_MODE(bond) == BOND_MODE_8023AD) + bond_set_slave_inactive_flags(slave, + BOND_SLAVE_NOTIFY_NOW); pr_info("%s: link status definitely down for interface %s, disabling it\n", bond->dev->name, slave->dev->name); - if (bond->params.mode == BOND_MODE_8023AD) + if (BOND_MODE(bond) == BOND_MODE_8023AD) bond_3ad_handle_link_change(slave, BOND_LINK_DOWN); @@ -2504,73 +2093,69 @@ do_failover: * 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) +static void bond_mii_monitor(struct work_struct *work) { struct bonding *bond = container_of(work, struct bonding, mii_work.work); bool should_notify_peers = false; unsigned long delay; - read_lock(&bond->lock); - delay = msecs_to_jiffies(bond->params.miimon); - if (bond->slave_cnt == 0) + if (!bond_has_slaves(bond)) goto re_arm; + rcu_read_lock(); + should_notify_peers = bond_should_notify_peers(bond); if (bond_miimon_inspect(bond)) { - read_unlock(&bond->lock); + rcu_read_unlock(); /* Race avoidance with bond_close cancel of workqueue */ if (!rtnl_trylock()) { - read_lock(&bond->lock); delay = 1; should_notify_peers = false; goto re_arm; } - read_lock(&bond->lock); - bond_miimon_commit(bond); - read_unlock(&bond->lock); rtnl_unlock(); /* might sleep, hold no other locks */ - read_lock(&bond->lock); - } + } else + rcu_read_unlock(); re_arm: if (bond->params.miimon) queue_delayed_work(bond->wq, &bond->mii_work, delay); - read_unlock(&bond->lock); - if (should_notify_peers) { - if (!rtnl_trylock()) { - read_lock(&bond->lock); - bond->send_peer_notif++; - read_unlock(&bond->lock); + if (!rtnl_trylock()) return; - } - netdev_bonding_change(bond->dev, NETDEV_NOTIFY_PEERS); + call_netdevice_notifiers(NETDEV_NOTIFY_PEERS, bond->dev); rtnl_unlock(); } } -static int bond_has_this_ip(struct bonding *bond, __be32 ip) +static bool bond_has_this_ip(struct bonding *bond, __be32 ip) { - struct vlan_entry *vlan; + struct net_device *upper; + struct list_head *iter; + bool ret = false; - if (ip == bond->master_ip) - return 1; + if (ip == bond_confirm_addr(bond->dev, 0, ip)) + return true; - list_for_each_entry(vlan, &bond->vlan_list, vlan_list) { - if (ip == vlan->vlan_ip) - return 1; + rcu_read_lock(); + netdev_for_each_all_upper_dev_rcu(bond->dev, upper, iter) { + if (ip == bond_confirm_addr(upper, 0, ip)) { + ret = true; + break; + } } + rcu_read_unlock(); - return 0; + return ret; } /* @@ -2578,142 +2163,190 @@ static int bond_has_this_ip(struct bonding *bond, __be32 ip) * switches in VLAN mode (especially if ports are configured as * "native" to a VLAN) might not pass non-tagged frames. */ -static void bond_arp_send(struct net_device *slave_dev, int arp_op, __be32 dest_ip, __be32 src_ip, unsigned short vlan_id) +static void bond_arp_send(struct net_device *slave_dev, int arp_op, + __be32 dest_ip, __be32 src_ip, + struct bond_vlan_tag *tags) { struct sk_buff *skb; + int i; - 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); + pr_debug("arp %d on slave %s: dst %pI4 src %pI4\n", + arp_op, slave_dev->name, &dest_ip, &src_ip); skb = arp_create(arp_op, ETH_P_ARP, dest_ip, slave_dev, src_ip, NULL, slave_dev->dev_addr, NULL); if (!skb) { - pr_err("ARP packet allocation failed\n"); + net_err_ratelimited("ARP packet allocation failed\n"); return; } - if (vlan_id) { - skb = vlan_put_tag(skb, vlan_id); + + /* Go through all the tags backwards and add them to the packet */ + for (i = BOND_MAX_VLAN_ENCAP - 1; i > 0; i--) { + if (!tags[i].vlan_id) + continue; + + pr_debug("inner tag: proto %X vid %X\n", + ntohs(tags[i].vlan_proto), tags[i].vlan_id); + skb = __vlan_put_tag(skb, tags[i].vlan_proto, + tags[i].vlan_id); + if (!skb) { + net_err_ratelimited("failed to insert inner VLAN tag\n"); + return; + } + } + /* Set the outer tag */ + if (tags[0].vlan_id) { + pr_debug("outer tag: proto %X vid %X\n", + ntohs(tags[0].vlan_proto), tags[0].vlan_id); + skb = vlan_put_tag(skb, tags[0].vlan_proto, tags[0].vlan_id); if (!skb) { - pr_err("failed to insert VLAN tag\n"); + net_err_ratelimited("failed to insert outer VLAN tag\n"); return; } } arp_xmit(skb); } +/* Validate the device path between the @start_dev and the @end_dev. + * The path is valid if the @end_dev is reachable through device + * stacking. + * When the path is validated, collect any vlan information in the + * path. + */ +bool bond_verify_device_path(struct net_device *start_dev, + struct net_device *end_dev, + struct bond_vlan_tag *tags) +{ + struct net_device *upper; + struct list_head *iter; + int idx; + + if (start_dev == end_dev) + return true; + + netdev_for_each_upper_dev_rcu(start_dev, upper, iter) { + if (bond_verify_device_path(upper, end_dev, tags)) { + if (is_vlan_dev(upper)) { + idx = vlan_get_encap_level(upper); + if (idx >= BOND_MAX_VLAN_ENCAP) + return false; + + tags[idx].vlan_proto = + vlan_dev_vlan_proto(upper); + tags[idx].vlan_id = vlan_dev_vlan_id(upper); + } + return true; + } + } + + return false; +} static void bond_arp_send_all(struct bonding *bond, struct slave *slave) { - int i, vlan_id; - __be32 *targets = bond->params.arp_targets; - struct vlan_entry *vlan; - struct net_device *vlan_dev; struct rtable *rt; + struct bond_vlan_tag tags[BOND_MAX_VLAN_ENCAP]; + __be32 *targets = bond->params.arp_targets, addr; + int i; + bool ret; - for (i = 0; (i < BOND_MAX_ARP_TARGETS); i++) { - if (!targets[i]) - break; - pr_debug("basa: target %x\n", targets[i]); - if (!bond_vlan_used(bond)) { - pr_debug("basa: empty vlan: arp_send\n"); - bond_arp_send(slave->dev, ARPOP_REQUEST, targets[i], - bond->master_ip, 0); - continue; - } + for (i = 0; i < BOND_MAX_ARP_TARGETS && targets[i]; i++) { + pr_debug("basa: target %pI4\n", &targets[i]); + memset(tags, 0, sizeof(tags)); - /* - * If VLANs are configured, we do a route lookup to - * determine which VLAN interface would be used, so we - * can tag the ARP with the proper VLAN tag. - */ + /* Find out through which dev should the packet go */ rt = ip_route_output(dev_net(bond->dev), targets[i], 0, RTO_ONLINK, 0); if (IS_ERR(rt)) { - if (net_ratelimit()) { - pr_warning("%s: no route to arp_ip_target %pI4\n", - bond->dev->name, &targets[i]); - } - continue; - } - - /* - * This target is not on a VLAN - */ - if (rt->dst.dev == bond->dev) { - ip_rt_put(rt); - pr_debug("basa: rtdev == bond->dev: arp_send\n"); + /* there's no route to target - try to send arp + * probe to generate any traffic (arp_validate=0) + */ + if (bond->params.arp_validate) + net_warn_ratelimited("%s: no route to arp_ip_target %pI4 and arp_validate is set\n", + bond->dev->name, + &targets[i]); bond_arp_send(slave->dev, ARPOP_REQUEST, targets[i], - bond->master_ip, 0); + 0, tags); continue; } - vlan_id = 0; - list_for_each_entry(vlan, &bond->vlan_list, vlan_list) { - rcu_read_lock(); - vlan_dev = __vlan_find_dev_deep(bond->dev, - vlan->vlan_id); - rcu_read_unlock(); - if (vlan_dev == rt->dst.dev) { - vlan_id = vlan->vlan_id; - pr_debug("basa: vlan match on %s %d\n", - vlan_dev->name, vlan_id); - break; - } - } + /* bond device itself */ + if (rt->dst.dev == bond->dev) + goto found; - if (vlan_id) { - ip_rt_put(rt); - bond_arp_send(slave->dev, ARPOP_REQUEST, targets[i], - vlan->vlan_ip, vlan_id); - continue; - } + rcu_read_lock(); + ret = bond_verify_device_path(bond->dev, rt->dst.dev, tags); + rcu_read_unlock(); + + if (ret) + goto found; + + /* Not our device - skip */ + pr_debug("%s: no path to arp_ip_target %pI4 via rt.dev %s\n", + bond->dev->name, &targets[i], + rt->dst.dev ? rt->dst.dev->name : "NULL"); - if (net_ratelimit()) { - pr_warning("%s: no path to arp_ip_target %pI4 via rt.dev %s\n", - bond->dev->name, &targets[i], - rt->dst.dev ? rt->dst.dev->name : "NULL"); - } ip_rt_put(rt); + continue; + +found: + addr = bond_confirm_addr(rt->dst.dev, targets[i], 0); + ip_rt_put(rt); + bond_arp_send(slave->dev, ARPOP_REQUEST, targets[i], + addr, tags); } } static void bond_validate_arp(struct bonding *bond, struct slave *slave, __be32 sip, __be32 tip) { int i; - __be32 *targets = bond->params.arp_targets; - - for (i = 0; (i < BOND_MAX_ARP_TARGETS) && targets[i]; i++) { - 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; - return; - } + + if (!sip || !bond_has_this_ip(bond, tip)) { + pr_debug("bva: sip %pI4 tip %pI4 not found\n", &sip, &tip); + return; + } + + i = bond_get_targets_ip(bond->params.arp_targets, sip); + if (i == -1) { + pr_debug("bva: sip %pI4 not found in targets\n", &sip); + return; } + slave->last_rx = jiffies; + slave->target_last_arp_rx[i] = jiffies; } -static void bond_arp_rcv(struct sk_buff *skb, struct bonding *bond, - struct slave *slave) +int bond_arp_rcv(const struct sk_buff *skb, struct bonding *bond, + struct slave *slave) { - struct arphdr *arp; + struct arphdr *arp = (struct arphdr *)skb->data; + struct slave *curr_active_slave; unsigned char *arp_ptr; __be32 sip, tip; + int alen, is_arp = skb->protocol == __cpu_to_be16(ETH_P_ARP); - if (skb->protocol != __cpu_to_be16(ETH_P_ARP)) - return; + if (!slave_do_arp_validate(bond, slave)) { + if ((slave_do_arp_validate_only(bond) && is_arp) || + !slave_do_arp_validate_only(bond)) + slave->last_rx = jiffies; + return RX_HANDLER_ANOTHER; + } else if (!is_arp) { + return RX_HANDLER_ANOTHER; + } - read_lock(&bond->lock); + alen = arp_hdr_len(bond->dev); pr_debug("bond_arp_rcv: bond %s skb->dev %s\n", bond->dev->name, skb->dev->name); - if (!pskb_may_pull(skb, arp_hdr_len(bond->dev))) - goto out_unlock; + if (alen > skb_headlen(skb)) { + arp = kmalloc(alen, GFP_ATOMIC); + if (!arp) + goto out_unlock; + if (skb_copy_bits(skb, 0, arp, alen) < 0) + goto out_unlock; + } - arp = arp_hdr(skb); if (arp->ar_hln != bond->dev->addr_len || skb->pkt_type == PACKET_OTHERHOST || skb->pkt_type == PACKET_LOOPBACK || @@ -2733,6 +2366,8 @@ static void bond_arp_rcv(struct sk_buff *skb, struct bonding *bond, bond->params.arp_validate, slave_do_arp_validate(bond, slave), &sip, &tip); + curr_active_slave = rcu_dereference(bond->curr_active_slave); + /* * Backup slaves won't see the ARP reply, but do come through * here for each ARP probe (so we swap the sip/tip to validate @@ -2740,14 +2375,38 @@ static void bond_arp_rcv(struct sk_buff *skb, struct bonding *bond, * configuration, the ARP probe will (hopefully) travel from * the active, through one switch, the router, then the other * switch before reaching the backup. + * + * We 'trust' the arp requests if there is an active slave and + * it received valid arp reply(s) after it became active. This + * is done to avoid endless looping when we can't reach the + * arp_ip_target and fool ourselves with our own arp requests. */ + if (bond_is_active_slave(slave)) bond_validate_arp(bond, slave, sip, tip); - else + else if (curr_active_slave && + time_after(slave_last_rx(bond, curr_active_slave), + curr_active_slave->last_link_up)) bond_validate_arp(bond, slave, tip, sip); out_unlock: - read_unlock(&bond->lock); + if (arp != (struct arphdr *)skb->data) + kfree(arp); + return RX_HANDLER_ANOTHER; +} + +/* function to verify if we're in the arp_interval timeslice, returns true if + * (last_act - arp_interval) <= jiffies <= (last_act + mod * arp_interval + + * arp_interval/2) . the arp_interval/2 is needed for really fast networks. + */ +static bool bond_time_in_interval(struct bonding *bond, unsigned long last_act, + int mod) +{ + int delta_in_ticks = msecs_to_jiffies(bond->params.arp_interval); + + return time_in_range(jiffies, + last_act - delta_in_ticks, + last_act + mod * delta_in_ticks + delta_in_ticks/2); } /* @@ -2757,47 +2416,37 @@ out_unlock: * arp is transmitted to generate traffic. see activebackup_arp_monitor for * arp monitoring in active backup mode. */ -void bond_loadbalance_arp_mon(struct work_struct *work) +static void bond_loadbalance_arp_mon(struct work_struct *work) { struct bonding *bond = container_of(work, struct bonding, arp_work.work); struct slave *slave, *oldcurrent; - int do_failover = 0; - int delta_in_ticks; - int i; - - read_lock(&bond->lock); - - delta_in_ticks = msecs_to_jiffies(bond->params.arp_interval); + struct list_head *iter; + int do_failover = 0, slave_state_changed = 0; - if (bond->slave_cnt == 0) + if (!bond_has_slaves(bond)) goto re_arm; - read_lock(&bond->curr_slave_lock); - oldcurrent = bond->curr_active_slave; - read_unlock(&bond->curr_slave_lock); + rcu_read_lock(); + oldcurrent = ACCESS_ONCE(bond->curr_active_slave); /* see if any of the previous devices are up now (i.e. they have * xmt and rcv traffic). the curr_active_slave does not come into - * the picture unless it is null. also, slave->jiffies is not needed - * here because we send an arp on each slave and give a slave as - * long as it needs to get the tx/rx within the delta. + * the picture unless it is null. also, slave->last_link_up is not + * needed here because we send an arp on each slave and give a slave + * as long as it needs to get the tx/rx within the delta. * TODO: what about up/down delay in arp mode? it wasn't here before * so it can wait */ - bond_for_each_slave(bond, slave, i) { + bond_for_each_slave_rcu(bond, slave, iter) { unsigned long trans_start = dev_trans_start(slave->dev); if (slave->link != BOND_LINK_UP) { - if (time_in_range(jiffies, - trans_start - delta_in_ticks, - trans_start + delta_in_ticks) && - time_in_range(jiffies, - slave->dev->last_rx - delta_in_ticks, - slave->dev->last_rx + delta_in_ticks)) { + if (bond_time_in_interval(bond, trans_start, 1) && + bond_time_in_interval(bond, slave->last_rx, 1)) { slave->link = BOND_LINK_UP; - bond_set_active_slave(slave); + slave_state_changed = 1; /* primary_slave has no meaning in round-robin * mode. the window of a slave being up and @@ -2805,7 +2454,7 @@ void bond_loadbalance_arp_mon(struct work_struct *work) * is closed. */ if (!oldcurrent) { - pr_info("%s: link status definitely up for interface %s, ", + pr_info("%s: link status definitely up for interface %s\n", bond->dev->name, slave->dev->name); do_failover = 1; @@ -2822,22 +2471,17 @@ 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_in_range(jiffies, - trans_start - delta_in_ticks, - trans_start + 2 * delta_in_ticks) || - !time_in_range(jiffies, - slave->dev->last_rx - delta_in_ticks, - slave->dev->last_rx + 2 * delta_in_ticks)) { + if (!bond_time_in_interval(bond, trans_start, 2) || + !bond_time_in_interval(bond, slave->last_rx, 2)) { slave->link = BOND_LINK_DOWN; - bond_set_backup_slave(slave); + slave_state_changed = 1; if (slave->link_failure_count < UINT_MAX) slave->link_failure_count++; - pr_info("%s: interface %s is now down.\n", - bond->dev->name, - slave->dev->name); + pr_info("%s: interface %s is now down\n", + bond->dev->name, slave->dev->name); if (slave == oldcurrent) do_failover = 1; @@ -2851,25 +2495,37 @@ 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 (bond_slave_is_up(slave)) bond_arp_send_all(bond, slave); } - if (do_failover) { - block_netpoll_tx(); - write_lock_bh(&bond->curr_slave_lock); + rcu_read_unlock(); - bond_select_active_slave(bond); + if (do_failover || slave_state_changed) { + if (!rtnl_trylock()) + goto re_arm; - write_unlock_bh(&bond->curr_slave_lock); - unblock_netpoll_tx(); + if (slave_state_changed) { + bond_slave_state_change(bond); + } else if (do_failover) { + /* the bond_select_active_slave must hold RTNL + * and curr_slave_lock for write. + */ + block_netpoll_tx(); + write_lock_bh(&bond->curr_slave_lock); + + bond_select_active_slave(bond); + + write_unlock_bh(&bond->curr_slave_lock); + unblock_netpoll_tx(); + } + rtnl_unlock(); } re_arm: if (bond->params.arp_interval) - queue_delayed_work(bond->wq, &bond->arp_work, delta_in_ticks); - - read_unlock(&bond->lock); + queue_delayed_work(bond->wq, &bond->arp_work, + msecs_to_jiffies(bond->params.arp_interval)); } /* @@ -2878,26 +2534,24 @@ re_arm: * 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. + * Called with rcu_read_lock hold. */ -static int bond_ab_arp_inspect(struct bonding *bond, int delta_in_ticks) +static int bond_ab_arp_inspect(struct bonding *bond) { + unsigned long trans_start, last_rx; + struct list_head *iter; struct slave *slave; - int i, commit = 0; - unsigned long trans_start; + int commit = 0; - bond_for_each_slave(bond, slave, i) { + bond_for_each_slave_rcu(bond, slave, iter) { slave->new_link = BOND_LINK_NOCHANGE; + last_rx = slave_last_rx(bond, slave); if (slave->link != BOND_LINK_UP) { - if (time_in_range(jiffies, - slave_last_rx(bond, slave) - delta_in_ticks, - slave_last_rx(bond, slave) + delta_in_ticks)) { - + if (bond_time_in_interval(bond, last_rx, 1)) { slave->new_link = BOND_LINK_UP; commit++; } - continue; } @@ -2906,9 +2560,7 @@ static int bond_ab_arp_inspect(struct bonding *bond, int delta_in_ticks) * active. This avoids bouncing, as the last receive * times need a full ARP monitor cycle to be updated. */ - if (time_in_range(jiffies, - slave->jiffies - delta_in_ticks, - slave->jiffies + 2 * delta_in_ticks)) + if (bond_time_in_interval(bond, slave->last_link_up, 2)) continue; /* @@ -2926,10 +2578,7 @@ static int bond_ab_arp_inspect(struct bonding *bond, int delta_in_ticks) */ if (!bond_is_active_slave(slave) && !bond->current_arp_slave && - !time_in_range(jiffies, - slave_last_rx(bond, slave) - delta_in_ticks, - slave_last_rx(bond, slave) + 3 * delta_in_ticks)) { - + !bond_time_in_interval(bond, last_rx, 3)) { slave->new_link = BOND_LINK_DOWN; commit++; } @@ -2942,13 +2591,8 @@ static int bond_ab_arp_inspect(struct bonding *bond, int delta_in_ticks) */ trans_start = dev_trans_start(slave->dev); if (bond_is_active_slave(slave) && - (!time_in_range(jiffies, - trans_start - delta_in_ticks, - trans_start + 2 * delta_in_ticks) || - !time_in_range(jiffies, - slave_last_rx(bond, slave) - delta_in_ticks, - slave_last_rx(bond, slave) + 2 * delta_in_ticks))) { - + (!bond_time_in_interval(bond, trans_start, 2) || + !bond_time_in_interval(bond, last_rx, 2))) { slave->new_link = BOND_LINK_DOWN; commit++; } @@ -2961,30 +2605,33 @@ static int bond_ab_arp_inspect(struct bonding *bond, int delta_in_ticks) * Called to commit link state changes noted by inspection step of * active-backup mode ARP monitor. * - * Called with RTNL and bond->lock for read. + * Called with RTNL hold. */ -static void bond_ab_arp_commit(struct bonding *bond, int delta_in_ticks) +static void bond_ab_arp_commit(struct bonding *bond) { - struct slave *slave; - int i; unsigned long trans_start; + struct list_head *iter; + struct slave *slave; - bond_for_each_slave(bond, slave, i) { + bond_for_each_slave(bond, slave, iter) { switch (slave->new_link) { case BOND_LINK_NOCHANGE: continue; case BOND_LINK_UP: trans_start = dev_trans_start(slave->dev); - if ((!bond->curr_active_slave && - time_in_range(jiffies, - trans_start - delta_in_ticks, - trans_start + delta_in_ticks)) || - bond->curr_active_slave != slave) { + if (bond->curr_active_slave != slave || + (!bond->curr_active_slave && + bond_time_in_interval(bond, trans_start, 1))) { slave->link = BOND_LINK_UP; - bond->current_arp_slave = NULL; + if (bond->current_arp_slave) { + bond_set_slave_inactive_flags( + bond->current_arp_slave, + BOND_SLAVE_NOTIFY_NOW); + bond->current_arp_slave = NULL; + } - pr_info("%s: link status definitely up for interface %s.\n", + pr_info("%s: link status definitely up for interface %s\n", bond->dev->name, slave->dev->name); if (!bond->curr_active_slave || @@ -3000,7 +2647,8 @@ static void bond_ab_arp_commit(struct bonding *bond, int delta_in_ticks) slave->link_failure_count++; slave->link = BOND_LINK_DOWN; - bond_set_slave_inactive_flags(slave); + bond_set_slave_inactive_flags(slave, + BOND_SLAVE_NOTIFY_NOW); pr_info("%s: link status definitely down for interface %s, disabling it\n", bond->dev->name, slave->dev->name); @@ -3034,52 +2682,46 @@ do_failover: /* * Send ARP probes for active-backup mode ARP monitor. * - * Called with bond->lock held for read. + * Called with rcu_read_lock hold. */ -static void bond_ab_arp_probe(struct bonding *bond) +static bool bond_ab_arp_probe(struct bonding *bond) { - struct slave *slave; - int i; - - read_lock(&bond->curr_slave_lock); - - if (bond->current_arp_slave && bond->curr_active_slave) + struct slave *slave, *before = NULL, *new_slave = NULL, + *curr_arp_slave = rcu_dereference(bond->current_arp_slave), + *curr_active_slave = rcu_dereference(bond->curr_active_slave); + struct list_head *iter; + bool found = false; + bool should_notify_rtnl = BOND_SLAVE_NOTIFY_LATER; + + if (curr_arp_slave && curr_active_slave) pr_info("PROBE: c_arp %s && cas %s BAD\n", - bond->current_arp_slave->dev->name, - bond->curr_active_slave->dev->name); + curr_arp_slave->dev->name, + curr_active_slave->dev->name); - if (bond->curr_active_slave) { - bond_arp_send_all(bond, bond->curr_active_slave); - read_unlock(&bond->curr_slave_lock); - return; + if (curr_active_slave) { + bond_arp_send_all(bond, curr_active_slave); + return should_notify_rtnl; } - read_unlock(&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 */ - if (!bond->current_arp_slave) { - bond->current_arp_slave = bond->first_slave; - if (!bond->current_arp_slave) - return; + if (!curr_arp_slave) { + curr_arp_slave = bond_first_slave_rcu(bond); + if (!curr_arp_slave) + return should_notify_rtnl; } - bond_set_slave_inactive_flags(bond->current_arp_slave); + bond_set_slave_inactive_flags(curr_arp_slave, BOND_SLAVE_NOTIFY_LATER); - /* 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; - } + bond_for_each_slave_rcu(bond, slave, iter) { + if (!found && !before && bond_slave_is_up(slave)) + before = slave; + if (found && !new_slave && bond_slave_is_up(slave)) + new_slave = slave; /* if the link state is up at this point, we * mark it down - this can happen if we have * simultaneous link failures and @@ -3087,71 +2729,93 @@ static void bond_ab_arp_probe(struct bonding *bond) * one the current slave so it is still marked * up when it is actually down */ - if (slave->link == BOND_LINK_UP) { + if (!bond_slave_is_up(slave) && 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); + bond_set_slave_inactive_flags(slave, + BOND_SLAVE_NOTIFY_LATER); - pr_info("%s: backup interface %s is now down.\n", + pr_info("%s: backup interface %s is now down\n", bond->dev->name, slave->dev->name); } + if (slave == curr_arp_slave) + found = true; } + + if (!new_slave && before) + new_slave = before; + + if (!new_slave) + goto check_state; + + new_slave->link = BOND_LINK_BACK; + bond_set_slave_active_flags(new_slave, BOND_SLAVE_NOTIFY_LATER); + bond_arp_send_all(bond, new_slave); + new_slave->last_link_up = jiffies; + rcu_assign_pointer(bond->current_arp_slave, new_slave); + +check_state: + bond_for_each_slave_rcu(bond, slave, iter) { + if (slave->should_notify) { + should_notify_rtnl = BOND_SLAVE_NOTIFY_NOW; + break; + } + } + return should_notify_rtnl; } -void bond_activebackup_arp_mon(struct work_struct *work) +static void bond_activebackup_arp_mon(struct work_struct *work) { struct bonding *bond = container_of(work, struct bonding, arp_work.work); bool should_notify_peers = false; + bool should_notify_rtnl = false; int delta_in_ticks; - read_lock(&bond->lock); - delta_in_ticks = msecs_to_jiffies(bond->params.arp_interval); - if (bond->slave_cnt == 0) + if (!bond_has_slaves(bond)) goto re_arm; + rcu_read_lock(); + should_notify_peers = bond_should_notify_peers(bond); - if (bond_ab_arp_inspect(bond, delta_in_ticks)) { - read_unlock(&bond->lock); + if (bond_ab_arp_inspect(bond)) { + rcu_read_unlock(); /* Race avoidance with bond_close flush of workqueue */ if (!rtnl_trylock()) { - read_lock(&bond->lock); delta_in_ticks = 1; should_notify_peers = false; goto re_arm; } - read_lock(&bond->lock); - - bond_ab_arp_commit(bond, delta_in_ticks); + bond_ab_arp_commit(bond); - read_unlock(&bond->lock); rtnl_unlock(); - read_lock(&bond->lock); + rcu_read_lock(); } - bond_ab_arp_probe(bond); + should_notify_rtnl = bond_ab_arp_probe(bond); + rcu_read_unlock(); re_arm: if (bond->params.arp_interval) queue_delayed_work(bond->wq, &bond->arp_work, delta_in_ticks); - read_unlock(&bond->lock); - - if (should_notify_peers) { - if (!rtnl_trylock()) { - read_lock(&bond->lock); - bond->send_peer_notif++; - read_unlock(&bond->lock); + if (should_notify_peers || should_notify_rtnl) { + if (!rtnl_trylock()) return; - } - netdev_bonding_change(bond->dev, NETDEV_NOTIFY_PEERS); + + if (should_notify_peers) + call_netdevice_notifiers(NETDEV_NOTIFY_PEERS, + bond->dev); + if (should_notify_rtnl) + bond_slave_state_notify(bond); + rtnl_unlock(); } } @@ -3179,6 +2843,16 @@ static int bond_master_netdev_event(unsigned long event, switch (event) { case NETDEV_CHANGENAME: return bond_event_changename(event_bond); + case NETDEV_UNREGISTER: + bond_remove_proc_entry(event_bond); + break; + case NETDEV_REGISTER: + bond_create_proc_entry(event_bond); + break; + case NETDEV_NOTIFY_PEERS: + if (event_bond->send_peer_notif) + event_bond->send_peer_notif--; + break; default: break; } @@ -3189,36 +2863,41 @@ static int bond_master_netdev_event(unsigned long event, 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 = netdev_priv(bond_dev); - struct slave *slave = NULL; + struct slave *slave = bond_slave_get_rtnl(slave_dev); + struct bonding *bond; + struct net_device *bond_dev; + u32 old_speed; + u8 old_duplex; + + /* A netdev event can be generated while enslaving a device + * before netdev_rx_handler_register is called in which case + * slave will be NULL + */ + if (!slave) + return NOTIFY_DONE; + bond_dev = slave->bond->dev; + bond = slave->bond; switch (event) { case NETDEV_UNREGISTER: - if (bond_dev) { - if (bond->setup_by_slave) - bond_release_and_destroy(bond_dev, slave_dev); - else - bond_release(bond_dev, slave_dev); - } + if (bond_dev->type != ARPHRD_ETHER) + bond_release_and_destroy(bond_dev, slave_dev); + else + bond_release(bond_dev, slave_dev); break; case NETDEV_UP: case NETDEV_CHANGE: - slave = bond_get_slave_by_dev(bond, slave_dev); - if (slave) { - u32 old_speed = slave->speed; - u8 old_duplex = slave->duplex; + old_speed = slave->speed; + old_duplex = slave->duplex; - bond_update_speed_duplex(slave); + bond_update_speed_duplex(slave); - if (bond->params.mode == BOND_MODE_8023AD) { - if (old_speed != slave->speed) - bond_3ad_adapter_speed_changed(slave); - if (old_duplex != slave->duplex) - bond_3ad_adapter_duplex_changed(slave); - } + if (BOND_MODE(bond) == BOND_MODE_8023AD) { + if (old_speed != slave->speed) + bond_3ad_adapter_speed_changed(slave); + if (old_duplex != slave->duplex) + bond_3ad_adapter_duplex_changed(slave); } - break; case NETDEV_DOWN: /* @@ -3240,13 +2919,38 @@ static int bond_slave_netdev_event(unsigned long event, */ break; case NETDEV_CHANGENAME: - /* - * TODO: handle changing the primary's name - */ + /* we don't care if we don't have primary set */ + if (!bond_uses_primary(bond) || + !bond->params.primary[0]) + break; + + if (slave == bond->primary_slave) { + /* slave's name changed - he's no longer primary */ + bond->primary_slave = NULL; + } else if (!strcmp(slave_dev->name, bond->params.primary)) { + /* we have a new primary slave */ + bond->primary_slave = slave; + } else { /* we didn't change primary - exit */ + break; + } + + pr_info("%s: Primary slave changed to %s, reselecting active slave\n", + bond->dev->name, + bond->primary_slave ? slave_dev->name : "none"); + + block_netpoll_tx(); + write_lock_bh(&bond->curr_slave_lock); + bond_select_active_slave(bond); + write_unlock_bh(&bond->curr_slave_lock); + unblock_netpoll_tx(); break; case NETDEV_FEAT_CHANGE: bond_compute_features(bond); break; + case NETDEV_RESEND_IGMP: + /* Propagate to master device */ + call_netdevice_notifiers(event, slave->bond->dev); + break; default: break; } @@ -3265,11 +2969,10 @@ static int bond_slave_netdev_event(unsigned long event, static int bond_netdev_event(struct notifier_block *this, unsigned long event, void *ptr) { - struct net_device *event_dev = (struct net_device *)ptr; + struct net_device *event_dev = netdev_notifier_info_to_dev(ptr); pr_debug("event_dev: %s, event: %lx\n", - event_dev ? event_dev->name : "None", - event); + event_dev ? event_dev->name : "None", event); if (!(event_dev->priv_flags & IFF_BONDING)) return NOTIFY_DONE; @@ -3287,182 +2990,160 @@ static int bond_netdev_event(struct notifier_block *this, return NOTIFY_DONE; } -/* - * bond_inetaddr_event: handle inetaddr notifier chain events. - * - * We keep track of device IPs primarily to use as source addresses in - * ARP monitor probes (rather than spewing out broadcasts all the time). - * - * We track one IP for the main device (if it has one), plus one per VLAN. - */ -static int bond_inetaddr_event(struct notifier_block *this, unsigned long event, void *ptr) -{ - struct in_ifaddr *ifa = ptr; - struct net_device *vlan_dev, *event_dev = ifa->ifa_dev->dev; - struct bond_net *bn = net_generic(dev_net(event_dev), bond_net_id); - struct bonding *bond; - struct vlan_entry *vlan; - - /* we only care about primary address */ - if(ifa->ifa_flags & IFA_F_SECONDARY) - return NOTIFY_DONE; - - list_for_each_entry(bond, &bn->dev_list, bond_list) { - if (bond->dev == event_dev) { - switch (event) { - case NETDEV_UP: - bond->master_ip = ifa->ifa_local; - return NOTIFY_OK; - case NETDEV_DOWN: - bond->master_ip = 0; - return NOTIFY_OK; - default: - return NOTIFY_DONE; - } - } - - list_for_each_entry(vlan, &bond->vlan_list, vlan_list) { - vlan_dev = __vlan_find_dev_deep(bond->dev, - vlan->vlan_id); - if (vlan_dev == event_dev) { - switch (event) { - case NETDEV_UP: - vlan->vlan_ip = ifa->ifa_local; - return NOTIFY_OK; - case NETDEV_DOWN: - vlan->vlan_ip = 0; - return NOTIFY_OK; - default: - return NOTIFY_DONE; - } - } - } - } - return NOTIFY_DONE; -} - static struct notifier_block bond_netdev_notifier = { .notifier_call = bond_netdev_event, }; -static struct notifier_block bond_inetaddr_notifier = { - .notifier_call = bond_inetaddr_event, -}; - /*---------------------------- Hashing Policies -----------------------------*/ -/* - * Hash for the output device based upon layer 2 and layer 3 data. If - * the packet is not IP mimic bond_xmit_hash_policy_l2() - */ -static int bond_xmit_hash_policy_l23(struct sk_buff *skb, int count) +/* L2 hash helper */ +static inline u32 bond_eth_hash(struct sk_buff *skb) { struct ethhdr *data = (struct ethhdr *)skb->data; - struct iphdr *iph = ip_hdr(skb); - if (skb->protocol == htons(ETH_P_IP)) { - return ((ntohl(iph->saddr ^ iph->daddr) & 0xffff) ^ - (data->h_dest[5] ^ data->h_source[5])) % count; - } + if (skb_headlen(skb) >= offsetof(struct ethhdr, h_proto)) + return data->h_dest[5] ^ data->h_source[5]; - return (data->h_dest[5] ^ data->h_source[5]) % count; + return 0; } -/* - * Hash for the output device based upon layer 3 and layer 4 data. If - * the packet is a frag or not TCP or UDP, just use layer 3 data. If it is - * altogether not IP, mimic bond_xmit_hash_policy_l2() - */ -static int bond_xmit_hash_policy_l34(struct sk_buff *skb, int count) +/* Extract the appropriate headers based on bond's xmit policy */ +static bool bond_flow_dissect(struct bonding *bond, struct sk_buff *skb, + struct flow_keys *fk) { - struct ethhdr *data = (struct ethhdr *)skb->data; - struct iphdr *iph = ip_hdr(skb); - __be16 *layer4hdr = (__be16 *)((u32 *)iph + iph->ihl); - int layer4_xor = 0; + const struct ipv6hdr *iph6; + const struct iphdr *iph; + int noff, proto = -1; - if (skb->protocol == htons(ETH_P_IP)) { - if (!ip_is_fragment(iph) && - (iph->protocol == IPPROTO_TCP || - iph->protocol == IPPROTO_UDP)) { - layer4_xor = ntohs((*layer4hdr ^ *(layer4hdr + 1))); - } - return (layer4_xor ^ - ((ntohl(iph->saddr ^ iph->daddr)) & 0xffff)) % count; + if (bond->params.xmit_policy > BOND_XMIT_POLICY_LAYER23) + return skb_flow_dissect(skb, fk); + fk->ports = 0; + noff = skb_network_offset(skb); + if (skb->protocol == htons(ETH_P_IP)) { + if (unlikely(!pskb_may_pull(skb, noff + sizeof(*iph)))) + return false; + iph = ip_hdr(skb); + fk->src = iph->saddr; + fk->dst = iph->daddr; + noff += iph->ihl << 2; + if (!ip_is_fragment(iph)) + proto = iph->protocol; + } else if (skb->protocol == htons(ETH_P_IPV6)) { + if (unlikely(!pskb_may_pull(skb, noff + sizeof(*iph6)))) + return false; + iph6 = ipv6_hdr(skb); + fk->src = (__force __be32)ipv6_addr_hash(&iph6->saddr); + fk->dst = (__force __be32)ipv6_addr_hash(&iph6->daddr); + noff += sizeof(*iph6); + proto = iph6->nexthdr; + } else { + return false; } + if (bond->params.xmit_policy == BOND_XMIT_POLICY_LAYER34 && proto >= 0) + fk->ports = skb_flow_get_ports(skb, noff, proto); - return (data->h_dest[5] ^ data->h_source[5]) % count; + return true; } -/* - * Hash for the output device based upon layer 2 data +/** + * bond_xmit_hash - generate a hash value based on the xmit policy + * @bond: bonding device + * @skb: buffer to use for headers + * + * This function will extract the necessary headers from the skb buffer and use + * them to generate a hash based on the xmit_policy set in the bonding device */ -static int bond_xmit_hash_policy_l2(struct sk_buff *skb, int count) +u32 bond_xmit_hash(struct bonding *bond, struct sk_buff *skb) { - struct ethhdr *data = (struct ethhdr *)skb->data; + struct flow_keys flow; + u32 hash; + + if (bond->params.xmit_policy == BOND_XMIT_POLICY_LAYER2 || + !bond_flow_dissect(bond, skb, &flow)) + return bond_eth_hash(skb); + + if (bond->params.xmit_policy == BOND_XMIT_POLICY_LAYER23 || + bond->params.xmit_policy == BOND_XMIT_POLICY_ENCAP23) + hash = bond_eth_hash(skb); + else + hash = (__force u32)flow.ports; + hash ^= (__force u32)flow.dst ^ (__force u32)flow.src; + hash ^= (hash >> 16); + hash ^= (hash >> 8); - return (data->h_dest[5] ^ data->h_source[5]) % count; + return hash; } /*-------------------------- Device entry points ----------------------------*/ +static void bond_work_init_all(struct bonding *bond) +{ + INIT_DELAYED_WORK(&bond->mcast_work, + bond_resend_igmp_join_requests_delayed); + INIT_DELAYED_WORK(&bond->alb_work, bond_alb_monitor); + INIT_DELAYED_WORK(&bond->mii_work, bond_mii_monitor); + if (BOND_MODE(bond) == BOND_MODE_ACTIVEBACKUP) + INIT_DELAYED_WORK(&bond->arp_work, bond_activebackup_arp_mon); + else + INIT_DELAYED_WORK(&bond->arp_work, bond_loadbalance_arp_mon); + INIT_DELAYED_WORK(&bond->ad_work, bond_3ad_state_machine_handler); +} + +static void bond_work_cancel_all(struct bonding *bond) +{ + cancel_delayed_work_sync(&bond->mii_work); + cancel_delayed_work_sync(&bond->arp_work); + cancel_delayed_work_sync(&bond->alb_work); + cancel_delayed_work_sync(&bond->ad_work); + cancel_delayed_work_sync(&bond->mcast_work); +} + static int bond_open(struct net_device *bond_dev) { struct bonding *bond = netdev_priv(bond_dev); + struct list_head *iter; struct slave *slave; - int i; /* reset slave->backup and slave->inactive */ read_lock(&bond->lock); - if (bond->slave_cnt > 0) { + if (bond_has_slaves(bond)) { read_lock(&bond->curr_slave_lock); - bond_for_each_slave(bond, slave, i) { - if ((bond->params.mode == BOND_MODE_ACTIVEBACKUP) + bond_for_each_slave(bond, slave, iter) { + if (bond_uses_primary(bond) && (slave != bond->curr_active_slave)) { - bond_set_slave_inactive_flags(slave); + bond_set_slave_inactive_flags(slave, + BOND_SLAVE_NOTIFY_NOW); } else { - bond_set_slave_active_flags(slave); + bond_set_slave_active_flags(slave, + BOND_SLAVE_NOTIFY_NOW); } } read_unlock(&bond->curr_slave_lock); } read_unlock(&bond->lock); - INIT_DELAYED_WORK(&bond->mcast_work, bond_resend_igmp_join_requests_delayed); + bond_work_init_all(bond); if (bond_is_lb(bond)) { /* bond_alb_initialize must be called before the timer * is started. */ - if (bond_alb_initialize(bond, (bond->params.mode == BOND_MODE_ALB))) { - /* something went wrong - fail the open operation */ + if (bond_alb_initialize(bond, (BOND_MODE(bond) == BOND_MODE_ALB))) return -ENOMEM; - } - - INIT_DELAYED_WORK(&bond->alb_work, bond_alb_monitor); - queue_delayed_work(bond->wq, &bond->alb_work, 0); + if (bond->params.tlb_dynamic_lb) + queue_delayed_work(bond->wq, &bond->alb_work, 0); } - if (bond->params.miimon) { /* link check interval, in milliseconds. */ - INIT_DELAYED_WORK(&bond->mii_work, bond_mii_monitor); + if (bond->params.miimon) /* link check interval, in milliseconds. */ queue_delayed_work(bond->wq, &bond->mii_work, 0); - } if (bond->params.arp_interval) { /* arp interval, in milliseconds. */ - if (bond->params.mode == BOND_MODE_ACTIVEBACKUP) - INIT_DELAYED_WORK(&bond->arp_work, - bond_activebackup_arp_mon); - else - INIT_DELAYED_WORK(&bond->arp_work, - bond_loadbalance_arp_mon); - queue_delayed_work(bond->wq, &bond->arp_work, 0); - if (bond->params.arp_validate) - bond->recv_probe = bond_arp_rcv; + bond->recv_probe = bond_arp_rcv; } - if (bond->params.mode == BOND_MODE_8023AD) { - INIT_DELAYED_WORK(&bond->ad_work, bond_3ad_state_machine_handler); + if (BOND_MODE(bond) == BOND_MODE_8023AD) { queue_delayed_work(bond->wq, &bond->ad_work, 0); /* register to receive LACPDUs */ bond->recv_probe = bond_3ad_lacpdu_recv; @@ -3476,41 +3157,10 @@ static int bond_close(struct net_device *bond_dev) { struct bonding *bond = netdev_priv(bond_dev); - write_lock_bh(&bond->lock); - + bond_work_cancel_all(bond); bond->send_peer_notif = 0; - - write_unlock_bh(&bond->lock); - - if (bond->params.miimon) { /* link check interval, in milliseconds. */ - cancel_delayed_work_sync(&bond->mii_work); - } - - if (bond->params.arp_interval) { /* arp interval, in milliseconds. */ - cancel_delayed_work_sync(&bond->arp_work); - } - - switch (bond->params.mode) { - case BOND_MODE_8023AD: - cancel_delayed_work_sync(&bond->ad_work); - break; - case BOND_MODE_TLB: - case BOND_MODE_ALB: - cancel_delayed_work_sync(&bond->alb_work); - break; - default: - break; - } - - if (delayed_work_pending(&bond->mcast_work)) - cancel_delayed_work_sync(&bond->mcast_work); - - if (bond_is_lb(bond)) { - /* Must be called only after all - * slaves have been released - */ + if (bond_is_lb(bond)) bond_alb_deinitialize(bond); - } bond->recv_probe = NULL; return 0; @@ -3521,14 +3171,13 @@ static struct rtnl_link_stats64 *bond_get_stats(struct net_device *bond_dev, { struct bonding *bond = netdev_priv(bond_dev); struct rtnl_link_stats64 temp; + struct list_head *iter; struct slave *slave; - int i; memset(stats, 0, sizeof(*stats)); read_lock_bh(&bond->lock); - - bond_for_each_slave(bond, slave, i) { + bond_for_each_slave(bond, slave, iter) { const struct rtnl_link_stats64 *sstats = dev_get_stats(slave->dev, &temp); @@ -3558,7 +3207,6 @@ static struct rtnl_link_stats64 *bond_get_stats(struct net_device *bond_dev, stats->tx_heartbeat_errors += sstats->tx_heartbeat_errors; stats->tx_window_errors += sstats->tx_window_errors; } - read_unlock_bh(&bond->lock); return stats; @@ -3566,12 +3214,15 @@ static struct rtnl_link_stats64 *bond_get_stats(struct net_device *bond_dev, static int bond_do_ioctl(struct net_device *bond_dev, struct ifreq *ifr, int cmd) { + struct bonding *bond = netdev_priv(bond_dev); struct net_device *slave_dev = NULL; struct ifbond k_binfo; struct ifbond __user *u_binfo = NULL; struct ifslave k_sinfo; struct ifslave __user *u_sinfo = NULL; struct mii_ioctl_data *mii = NULL; + struct bond_opt_value newval; + struct net *net; int res = 0; pr_debug("bond_ioctl: master=%s, cmd=%d\n", bond_dev->name, cmd); @@ -3595,7 +3246,6 @@ static int bond_do_ioctl(struct net_device *bond_dev, struct ifreq *ifr, int cmd if (mii->reg_num == 1) { - struct bonding *bond = netdev_priv(bond_dev); mii->val_out = 0; read_lock(&bond->lock); read_lock(&bond->curr_slave_lock); @@ -3638,57 +3288,45 @@ static int bond_do_ioctl(struct net_device *bond_dev, struct ifreq *ifr, int cmd break; } - if (!capable(CAP_NET_ADMIN)) + net = dev_net(bond_dev); + + if (!ns_capable(net->user_ns, CAP_NET_ADMIN)) return -EPERM; - slave_dev = dev_get_by_name(dev_net(bond_dev), ifr->ifr_slave); + slave_dev = __dev_get_by_name(net, ifr->ifr_slave); pr_debug("slave_dev=%p:\n", slave_dev); if (!slave_dev) - res = -ENODEV; - else { - pr_debug("slave_dev->name=%s:\n", slave_dev->name); - switch (cmd) { - case BOND_ENSLAVE_OLD: - case SIOCBONDENSLAVE: - res = bond_enslave(bond_dev, slave_dev); - break; - case BOND_RELEASE_OLD: - case SIOCBONDRELEASE: - res = bond_release(bond_dev, slave_dev); - break; - case BOND_SETHWADDR_OLD: - case SIOCBONDSETHWADDR: - res = bond_sethwaddr(bond_dev, slave_dev); - break; - case BOND_CHANGE_ACTIVE_OLD: - case SIOCBONDCHANGEACTIVE: - res = bond_ioctl_change_active(bond_dev, slave_dev); - break; - default: - res = -EOPNOTSUPP; - } + return -ENODEV; - dev_put(slave_dev); + pr_debug("slave_dev->name=%s:\n", slave_dev->name); + switch (cmd) { + case BOND_ENSLAVE_OLD: + case SIOCBONDENSLAVE: + res = bond_enslave(bond_dev, slave_dev); + break; + case BOND_RELEASE_OLD: + case SIOCBONDRELEASE: + res = bond_release(bond_dev, slave_dev); + break; + case BOND_SETHWADDR_OLD: + case SIOCBONDSETHWADDR: + bond_set_dev_addr(bond_dev, slave_dev); + res = 0; + break; + case BOND_CHANGE_ACTIVE_OLD: + case SIOCBONDCHANGEACTIVE: + bond_opt_initstr(&newval, slave_dev->name); + res = __bond_opt_set(bond, BOND_OPT_ACTIVE_SLAVE, &newval); + break; + default: + res = -EOPNOTSUPP; } return res; } -static bool bond_addr_in_mc_list(unsigned char *addr, - struct netdev_hw_addr_list *list, - int addrlen) -{ - struct netdev_hw_addr *ha; - - netdev_hw_addr_list_for_each(ha, list) - if (!memcmp(ha->addr, addr, addrlen)) - return true; - - return false; -} - static void bond_change_rx_flags(struct net_device *bond_dev, int change) { struct bonding *bond = netdev_priv(bond_dev); @@ -3702,49 +3340,80 @@ static void bond_change_rx_flags(struct net_device *bond_dev, int change) bond_dev->flags & IFF_ALLMULTI ? 1 : -1); } -static void bond_set_multicast_list(struct net_device *bond_dev) +static void bond_set_rx_mode(struct net_device *bond_dev) { struct bonding *bond = netdev_priv(bond_dev); - struct netdev_hw_addr *ha; - bool found; + struct list_head *iter; + struct slave *slave; - read_lock(&bond->lock); - /* looking for addresses to add to slaves' mc list */ - netdev_for_each_mc_addr(ha, bond_dev) { - found = bond_addr_in_mc_list(ha->addr, &bond->mc_list, - bond_dev->addr_len); - if (!found) - bond_mc_add(bond, ha->addr); + rcu_read_lock(); + if (bond_uses_primary(bond)) { + slave = rcu_dereference(bond->curr_active_slave); + if (slave) { + dev_uc_sync(slave->dev, bond_dev); + dev_mc_sync(slave->dev, bond_dev); + } + } else { + bond_for_each_slave_rcu(bond, slave, iter) { + dev_uc_sync_multiple(slave->dev, bond_dev); + dev_mc_sync_multiple(slave->dev, bond_dev); + } } + rcu_read_unlock(); +} - /* looking for addresses to delete from slaves' list */ - netdev_hw_addr_list_for_each(ha, &bond->mc_list) { - found = bond_addr_in_mc_list(ha->addr, &bond_dev->mc, - bond_dev->addr_len); - if (!found) - bond_mc_del(bond, ha->addr); - } +static int bond_neigh_init(struct neighbour *n) +{ + struct bonding *bond = netdev_priv(n->dev); + const struct net_device_ops *slave_ops; + struct neigh_parms parms; + struct slave *slave; + int ret; + + slave = bond_first_slave(bond); + if (!slave) + return 0; + slave_ops = slave->dev->netdev_ops; + if (!slave_ops->ndo_neigh_setup) + return 0; - /* save master's multicast list */ - __hw_addr_flush(&bond->mc_list); - __hw_addr_add_multiple(&bond->mc_list, &bond_dev->mc, - bond_dev->addr_len, NETDEV_HW_ADDR_T_MULTICAST); + parms.neigh_setup = NULL; + parms.neigh_cleanup = NULL; + ret = slave_ops->ndo_neigh_setup(slave->dev, &parms); + if (ret) + return ret; - read_unlock(&bond->lock); + /* + * Assign slave's neigh_cleanup to neighbour in case cleanup is called + * after the last slave has been detached. Assumes that all slaves + * utilize the same neigh_cleanup (true at this writing as only user + * is ipoib). + */ + n->parms->neigh_cleanup = parms.neigh_cleanup; + + if (!parms.neigh_setup) + return 0; + + return parms.neigh_setup(n); } -static int bond_neigh_setup(struct net_device *dev, struct neigh_parms *parms) +/* + * The bonding ndo_neigh_setup is called at init time beofre any + * slave exists. So we must declare proxy setup function which will + * be used at run time to resolve the actual slave neigh param setup. + * + * It's also called by master devices (such as vlans) to setup their + * underlying devices. In that case - do nothing, we're already set up from + * our init. + */ +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; + /* modify only our neigh_parms */ + if (parms->dev == dev) + parms->neigh_setup = bond_neigh_init; - 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; } @@ -3754,12 +3423,12 @@ static int bond_neigh_setup(struct net_device *dev, struct neigh_parms *parms) static int bond_change_mtu(struct net_device *bond_dev, int new_mtu) { struct bonding *bond = netdev_priv(bond_dev); - struct slave *slave, *stop_at; + struct slave *slave, *rollback_slave; + struct list_head *iter; int res = 0; - int i; - pr_debug("bond=%p, name=%s, new_mtu=%d\n", bond, - (bond_dev ? bond_dev->name : "None"), new_mtu); + 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 * some base drivers panic. On the other hand we can't @@ -3776,11 +3445,9 @@ static int bond_change_mtu(struct net_device *bond_dev, int new_mtu) * call to the base driver. */ - bond_for_each_slave(bond, slave, i) { - pr_debug("s %p s->p %p c_m %p\n", - slave, - slave->prev, - slave->dev->netdev_ops->ndo_change_mtu); + bond_for_each_slave(bond, slave, iter) { + pr_debug("s %p c_m %p\n", + slave, slave->dev->netdev_ops->ndo_change_mtu); res = dev_set_mtu(slave->dev, new_mtu); @@ -3804,14 +3471,16 @@ static int bond_change_mtu(struct net_device *bond_dev, int new_mtu) unwind: /* unwind from head to the slave that failed */ - stop_at = slave; - bond_for_each_slave_from_to(bond, slave, i, bond->first_slave, stop_at) { + bond_for_each_slave(bond, rollback_slave, iter) { int tmp_res; - tmp_res = dev_set_mtu(slave->dev, bond_dev->mtu); + if (rollback_slave == slave) + break; + + tmp_res = dev_set_mtu(rollback_slave->dev, bond_dev->mtu); if (tmp_res) { pr_debug("unwind err %d dev %s\n", - tmp_res, slave->dev->name); + tmp_res, rollback_slave->dev->name); } } @@ -3828,23 +3497,23 @@ unwind: static int bond_set_mac_address(struct net_device *bond_dev, void *addr) { struct bonding *bond = netdev_priv(bond_dev); + struct slave *slave, *rollback_slave; struct sockaddr *sa = addr, tmp_sa; - struct slave *slave, *stop_at; + struct list_head *iter; int res = 0; - int i; - if (bond->params.mode == BOND_MODE_ALB) + if (BOND_MODE(bond) == 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 set to active, do nothing and return - * success. Returning an error causes ifenslave to fail. + /* If fail_over_mac is enabled, do nothing and return success. + * Returning an error causes ifenslave to fail. */ - if (bond->params.fail_over_mac == BOND_FOM_ACTIVE) + if (bond->params.fail_over_mac && + BOND_MODE(bond) == BOND_MODE_ACTIVEBACKUP) return 0; if (!is_valid_ether_addr(sa->sa_data)) @@ -3865,16 +3534,8 @@ static int bond_set_mac_address(struct net_device *bond_dev, void *addr) * call to the base driver. */ - bond_for_each_slave(bond, slave, i) { - const struct net_device_ops *slave_ops = slave->dev->netdev_ops; + bond_for_each_slave(bond, slave, iter) { pr_debug("slave %p %s\n", slave, slave->dev->name); - - if (slave_ops->ndo_set_mac_address == NULL) { - res = -EOPNOTSUPP; - pr_debug("EOPNOTSUPP %s\n", slave->dev->name); - goto unwind; - } - res = dev_set_mac_address(slave->dev, addr); if (res) { /* TODO: consider downing the slave @@ -3897,78 +3558,122 @@ unwind: tmp_sa.sa_family = bond_dev->type; /* unwind from head to the slave that failed */ - stop_at = slave; - bond_for_each_slave_from_to(bond, slave, i, bond->first_slave, stop_at) { + bond_for_each_slave(bond, rollback_slave, iter) { int tmp_res; - tmp_res = dev_set_mac_address(slave->dev, &tmp_sa); + if (rollback_slave == slave) + break; + + tmp_res = dev_set_mac_address(rollback_slave->dev, &tmp_sa); if (tmp_res) { pr_debug("unwind err %d dev %s\n", - tmp_res, slave->dev->name); + tmp_res, rollback_slave->dev->name); } } return res; } +/** + * bond_xmit_slave_id - transmit skb through slave with slave_id + * @bond: bonding device that is transmitting + * @skb: buffer to transmit + * @slave_id: slave id up to slave_cnt-1 through which to transmit + * + * This function tries to transmit through slave with slave_id but in case + * it fails, it tries to find the first available slave for transmission. + * The skb is consumed in all cases, thus the function is void. + */ +static void bond_xmit_slave_id(struct bonding *bond, struct sk_buff *skb, int slave_id) +{ + struct list_head *iter; + struct slave *slave; + int i = slave_id; + + /* Here we start from the slave with slave_id */ + bond_for_each_slave_rcu(bond, slave, iter) { + if (--i < 0) { + if (bond_slave_can_tx(slave)) { + bond_dev_queue_xmit(bond, skb, slave->dev); + return; + } + } + } + + /* Here we start from the first slave up to slave_id */ + i = slave_id; + bond_for_each_slave_rcu(bond, slave, iter) { + if (--i < 0) + break; + if (bond_slave_can_tx(slave)) { + bond_dev_queue_xmit(bond, skb, slave->dev); + return; + } + } + /* no slave that can tx has been found */ + dev_kfree_skb_any(skb); +} + +/** + * bond_rr_gen_slave_id - generate slave id based on packets_per_slave + * @bond: bonding device to use + * + * Based on the value of the bonding device's packets_per_slave parameter + * this function generates a slave id, which is usually used as the next + * slave to transmit through. + */ +static u32 bond_rr_gen_slave_id(struct bonding *bond) +{ + u32 slave_id; + struct reciprocal_value reciprocal_packets_per_slave; + int packets_per_slave = bond->params.packets_per_slave; + + switch (packets_per_slave) { + case 0: + slave_id = prandom_u32(); + break; + case 1: + slave_id = bond->rr_tx_counter; + break; + default: + reciprocal_packets_per_slave = + bond->params.reciprocal_packets_per_slave; + slave_id = reciprocal_divide(bond->rr_tx_counter, + reciprocal_packets_per_slave); + break; + } + bond->rr_tx_counter++; + + return slave_id; +} + static int bond_xmit_roundrobin(struct sk_buff *skb, struct net_device *bond_dev) { struct bonding *bond = netdev_priv(bond_dev); - struct slave *slave, *start_at; - int i, slave_no, res = 1; struct iphdr *iph = ip_hdr(skb); + struct slave *slave; + u32 slave_id; - /* - * Start with the curr_active_slave that joined the bond as the + /* Start with the curr_active_slave that joined the bond as the * default for sending IGMP traffic. For failover purposes one * needs to maintain some consistency for the interface that will * send the join/membership reports. The curr_active_slave found * will send all of this type of traffic. */ - if ((iph->protocol == IPPROTO_IGMP) && - (skb->protocol == htons(ETH_P_IP))) { - - read_lock(&bond->curr_slave_lock); - slave = bond->curr_active_slave; - read_unlock(&bond->curr_slave_lock); - - if (!slave) - goto out; + if (iph->protocol == IPPROTO_IGMP && skb->protocol == htons(ETH_P_IP)) { + slave = rcu_dereference(bond->curr_active_slave); + if (slave && bond_slave_can_tx(slave)) + bond_dev_queue_xmit(bond, skb, slave->dev); + else + bond_xmit_slave_id(bond, skb, 0); } else { - /* - * Concurrent TX may collide on rr_tx_counter; we accept - * that as being rare enough not to justify using an - * atomic op here. - */ - slave_no = bond->rr_tx_counter++ % bond->slave_cnt; - - bond_for_each_slave(bond, slave, i) { - slave_no--; - if (slave_no < 0) - break; - } - } - - start_at = slave; - bond_for_each_slave_from(bond, slave, i, start_at) { - if (IS_UP(slave->dev) && - (slave->link == BOND_LINK_UP) && - bond_is_active_slave(slave)) { - res = bond_dev_queue_xmit(bond, skb, slave->dev); - break; - } - } - -out: - if (res) { - /* no suitable interface, frame not sent */ - dev_kfree_skb(skb); + slave_id = bond_rr_gen_slave_id(bond); + bond_xmit_slave_id(bond, skb, slave_id % bond->slave_cnt); } return NETDEV_TX_OK; } - /* * in active-backup mode, we know that bond->curr_active_slave is always valid if * the bond has a usable interface. @@ -3976,165 +3681,92 @@ out: static int bond_xmit_activebackup(struct sk_buff *skb, struct net_device *bond_dev) { struct bonding *bond = netdev_priv(bond_dev); - int res = 1; - - read_lock(&bond->curr_slave_lock); - - if (bond->curr_active_slave) - res = bond_dev_queue_xmit(bond, skb, - bond->curr_active_slave->dev); - - if (res) - /* no suitable interface, frame not sent */ - dev_kfree_skb(skb); + struct slave *slave; - read_unlock(&bond->curr_slave_lock); + slave = rcu_dereference(bond->curr_active_slave); + if (slave) + bond_dev_queue_xmit(bond, skb, slave->dev); + else + dev_kfree_skb_any(skb); return NETDEV_TX_OK; } -/* - * In bond_xmit_xor() , we determine the output device by using a pre- +/* In bond_xmit_xor() , we determine the output device by using a pre- * determined xmit_hash_policy(), If the selected device is not enabled, * find the next active slave. */ static int bond_xmit_xor(struct sk_buff *skb, struct net_device *bond_dev) { struct bonding *bond = netdev_priv(bond_dev); - struct slave *slave, *start_at; - int slave_no; - int i; - int res = 1; - slave_no = bond->xmit_hash_policy(skb, bond->slave_cnt); - - bond_for_each_slave(bond, slave, i) { - slave_no--; - if (slave_no < 0) - break; - } - - start_at = slave; - - bond_for_each_slave_from(bond, slave, i, start_at) { - if (IS_UP(slave->dev) && - (slave->link == BOND_LINK_UP) && - bond_is_active_slave(slave)) { - res = bond_dev_queue_xmit(bond, skb, slave->dev); - break; - } - } - - if (res) { - /* no suitable interface, frame not sent */ - dev_kfree_skb(skb); - } + bond_xmit_slave_id(bond, skb, bond_xmit_hash(bond, skb) % bond->slave_cnt); return NETDEV_TX_OK; } -/* - * in broadcast mode, we send everything to all usable interfaces. - */ +/* in broadcast mode, we send everything to all usable interfaces. */ static int bond_xmit_broadcast(struct sk_buff *skb, struct net_device *bond_dev) { struct bonding *bond = netdev_priv(bond_dev); - struct slave *slave, *start_at; - struct net_device *tx_dev = NULL; - int i; - int res = 1; - - read_lock(&bond->curr_slave_lock); - start_at = bond->curr_active_slave; - read_unlock(&bond->curr_slave_lock); - - if (!start_at) - goto out; + struct slave *slave = NULL; + struct list_head *iter; - bond_for_each_slave_from(bond, slave, i, start_at) { - if (IS_UP(slave->dev) && - (slave->link == BOND_LINK_UP) && - bond_is_active_slave(slave)) { - if (tx_dev) { - struct sk_buff *skb2 = skb_clone(skb, GFP_ATOMIC); - if (!skb2) { - pr_err("%s: Error: bond_xmit_broadcast(): skb_clone() failed\n", - bond_dev->name); - continue; - } + bond_for_each_slave_rcu(bond, slave, iter) { + if (bond_is_last_slave(bond, slave)) + break; + if (bond_slave_is_up(slave) && slave->link == BOND_LINK_UP) { + struct sk_buff *skb2 = skb_clone(skb, GFP_ATOMIC); - res = bond_dev_queue_xmit(bond, skb2, tx_dev); - if (res) { - dev_kfree_skb(skb2); - continue; - } + if (!skb2) { + net_err_ratelimited("%s: Error: %s: skb_clone() failed\n", + bond_dev->name, __func__); + continue; } - tx_dev = slave->dev; + /* bond_dev_queue_xmit always returns 0 */ + bond_dev_queue_xmit(bond, skb2, slave->dev); } } + if (slave && bond_slave_is_up(slave) && slave->link == BOND_LINK_UP) + bond_dev_queue_xmit(bond, skb, slave->dev); + else + dev_kfree_skb_any(skb); - if (tx_dev) - res = bond_dev_queue_xmit(bond, skb, tx_dev); - -out: - if (res) - /* no suitable interface, frame not sent */ - dev_kfree_skb(skb); - - /* frame sent to all suitable interfaces */ return NETDEV_TX_OK; } /*------------------------- Device initialization ---------------------------*/ -static void bond_set_xmit_hash_policy(struct bonding *bond) -{ - switch (bond->params.xmit_policy) { - case BOND_XMIT_POLICY_LAYER23: - bond->xmit_hash_policy = bond_xmit_hash_policy_l23; - break; - case BOND_XMIT_POLICY_LAYER34: - bond->xmit_hash_policy = bond_xmit_hash_policy_l34; - break; - case BOND_XMIT_POLICY_LAYER2: - default: - bond->xmit_hash_policy = bond_xmit_hash_policy_l2; - break; - } -} - /* * Lookup the slave that corresponds to a qid */ static inline int bond_slave_override(struct bonding *bond, struct sk_buff *skb) { - int i, res = 1; struct slave *slave = NULL; - struct slave *check_slave; + struct list_head *iter; if (!skb->queue_mapping) return 1; /* Find out if any slaves have the same mapping as this skb. */ - bond_for_each_slave(bond, check_slave, i) { - if (check_slave->queue_id == skb->queue_mapping) { - slave = check_slave; + bond_for_each_slave_rcu(bond, slave, iter) { + if (slave->queue_id == skb->queue_mapping) { + if (bond_slave_can_tx(slave)) { + bond_dev_queue_xmit(bond, skb, slave->dev); + return 0; + } + /* If the slave isn't UP, use default transmit policy. */ break; } } - /* If the slave isn't UP, use default transmit policy. */ - if (slave && slave->queue_id && IS_UP(slave->dev) && - (slave->link == BOND_LINK_UP)) { - res = bond_dev_queue_xmit(bond, skb, slave->dev); - } - - return res; + return 1; } -static u16 bond_select_queue(struct net_device *dev, struct sk_buff *skb) +static u16 bond_select_queue(struct net_device *dev, struct sk_buff *skb, + void *accel_priv, select_queue_fallback_t fallback) { /* * This helper function exists to help dev_pick_tx get the correct @@ -4147,7 +3779,7 @@ static u16 bond_select_queue(struct net_device *dev, struct sk_buff *skb) /* * Save the original txq to restore before passing to the driver */ - bond_queue_mapping(skb) = skb->queue_mapping; + qdisc_skb_cb(skb)->slave_dev_queue_mapping = skb->queue_mapping; if (unlikely(txq >= dev->real_num_tx_queues)) { do { @@ -4161,12 +3793,11 @@ static netdev_tx_t __bond_start_xmit(struct sk_buff *skb, struct net_device *dev { struct bonding *bond = netdev_priv(dev); - if (TX_QUEUE_OVERRIDE(bond->params.mode)) { - if (!bond_slave_override(bond, skb)) - return NETDEV_TX_OK; - } + if (bond_should_override_tx_queue(bond) && + !bond_slave_override(bond, skb)) + return NETDEV_TX_OK; - switch (bond->params.mode) { + switch (BOND_MODE(bond)) { case BOND_MODE_ROUNDROBIN: return bond_xmit_roundrobin(skb, dev); case BOND_MODE_ACTIVEBACKUP: @@ -4178,14 +3809,15 @@ static netdev_tx_t __bond_start_xmit(struct sk_buff *skb, struct net_device *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); + case BOND_MODE_TLB: + return bond_tlb_xmit(skb, dev); default: /* Should never happen, mode already checked */ pr_err("%s: Error: Unknown bonding mode %d\n", - dev->name, bond->params.mode); + dev->name, BOND_MODE(bond)); WARN_ON_ONCE(1); - dev_kfree_skb(skb); + dev_kfree_skb_any(skb); return NETDEV_TX_OK; } } @@ -4199,63 +3831,63 @@ static netdev_tx_t bond_start_xmit(struct sk_buff *skb, struct net_device *dev) * If we risk deadlock from transmitting this in the * netpoll path, tell netpoll to queue the frame for later tx */ - if (is_netpoll_tx_blocked(dev)) + if (unlikely(is_netpoll_tx_blocked(dev))) return NETDEV_TX_BUSY; - read_lock(&bond->lock); - - if (bond->slave_cnt) + rcu_read_lock(); + if (bond_has_slaves(bond)) ret = __bond_start_xmit(skb, dev); else - dev_kfree_skb(skb); - - read_unlock(&bond->lock); + dev_kfree_skb_any(skb); + rcu_read_unlock(); return ret; } -/* - * set bond mode specific net device operations - */ -void bond_set_mode_ops(struct bonding *bond, int mode) +static int bond_ethtool_get_settings(struct net_device *bond_dev, + struct ethtool_cmd *ecmd) { - struct net_device *bond_dev = bond->dev; + struct bonding *bond = netdev_priv(bond_dev); + unsigned long speed = 0; + struct list_head *iter; + struct slave *slave; - switch (mode) { - case BOND_MODE_ROUNDROBIN: - break; - case BOND_MODE_ACTIVEBACKUP: - break; - case BOND_MODE_XOR: - bond_set_xmit_hash_policy(bond); - break; - case BOND_MODE_BROADCAST: - break; - case BOND_MODE_8023AD: - bond_set_xmit_hash_policy(bond); - break; - case BOND_MODE_ALB: - /* FALLTHRU */ - case BOND_MODE_TLB: - break; - default: - /* Should never happen, mode already checked */ - pr_err("%s: Error: Unknown bonding mode %d\n", - bond_dev->name, mode); - break; + ecmd->duplex = DUPLEX_UNKNOWN; + ecmd->port = PORT_OTHER; + + /* Since bond_slave_can_tx returns false for all inactive or down slaves, we + * do not need to check mode. Though link speed might not represent + * the true receive or transmit bandwidth (not all modes are symmetric) + * this is an accurate maximum. + */ + read_lock(&bond->lock); + bond_for_each_slave(bond, slave, iter) { + if (bond_slave_can_tx(slave)) { + if (slave->speed != SPEED_UNKNOWN) + speed += slave->speed; + if (ecmd->duplex == DUPLEX_UNKNOWN && + slave->duplex != DUPLEX_UNKNOWN) + ecmd->duplex = slave->duplex; + } } + ethtool_cmd_speed_set(ecmd, speed ? : SPEED_UNKNOWN); + read_unlock(&bond->lock); + + return 0; } static void bond_ethtool_get_drvinfo(struct net_device *bond_dev, - struct ethtool_drvinfo *drvinfo) + struct ethtool_drvinfo *drvinfo) { - strncpy(drvinfo->driver, DRV_NAME, 32); - strncpy(drvinfo->version, DRV_VERSION, 32); - snprintf(drvinfo->fw_version, 32, "%d", BOND_ABI_VERSION); + strlcpy(drvinfo->driver, DRV_NAME, sizeof(drvinfo->driver)); + strlcpy(drvinfo->version, DRV_VERSION, sizeof(drvinfo->version)); + snprintf(drvinfo->fw_version, sizeof(drvinfo->fw_version), "%d", + BOND_ABI_VERSION); } static const struct ethtool_ops bond_ethtool_ops = { .get_drvinfo = bond_ethtool_get_drvinfo, + .get_settings = bond_ethtool_get_settings, .get_link = ethtool_op_get_link, }; @@ -4269,7 +3901,7 @@ static const struct net_device_ops bond_netdev_ops = { .ndo_get_stats64 = bond_get_stats, .ndo_do_ioctl = bond_do_ioctl, .ndo_change_rx_flags = bond_change_rx_flags, - .ndo_set_rx_mode = bond_set_multicast_list, + .ndo_set_rx_mode = bond_set_rx_mode, .ndo_change_mtu = bond_change_mtu, .ndo_set_mac_address = bond_set_mac_address, .ndo_neigh_setup = bond_neigh_setup, @@ -4285,6 +3917,10 @@ static const struct net_device_ops bond_netdev_ops = { .ndo_fix_features = bond_fix_features, }; +static const struct device_type bond_type = { + .name = "bond", +}; + static void bond_destructor(struct net_device *bond_dev) { struct bonding *bond = netdev_priv(bond_dev); @@ -4293,32 +3929,31 @@ static void bond_destructor(struct net_device *bond_dev) free_netdev(bond_dev); } -static void bond_setup(struct net_device *bond_dev) +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 = bonding_defaults; /* Initialize pointers */ bond->dev = bond_dev; - INIT_LIST_HEAD(&bond->vlan_list); /* Initialize the device entry points */ ether_setup(bond_dev); bond_dev->netdev_ops = &bond_netdev_ops; bond_dev->ethtool_ops = &bond_ethtool_ops; - bond_set_mode_ops(bond, bond->params.mode); bond_dev->destructor = bond_destructor; + SET_NETDEV_DEVTYPE(bond_dev, &bond_type); + /* Initialize the device options */ bond_dev->tx_queue_len = 0; bond_dev->flags |= IFF_MASTER|IFF_MULTICAST; - bond_dev->priv_flags |= IFF_BONDING; + bond_dev->priv_flags |= IFF_BONDING | IFF_UNICAST_FLT; bond_dev->priv_flags &= ~(IFF_XMIT_DST_RELEASE | IFF_TX_SKB_SHARING); /* At first, we block adding VLANs. That's the only way to @@ -4339,35 +3974,19 @@ static void bond_setup(struct net_device *bond_dev) * capable */ + /* Don't allow bond devices to change network namespaces. */ + bond_dev->features |= NETIF_F_NETNS_LOCAL; + bond_dev->hw_features = BOND_VLAN_FEATURES | - NETIF_F_HW_VLAN_TX | - NETIF_F_HW_VLAN_RX | - NETIF_F_HW_VLAN_FILTER; + NETIF_F_HW_VLAN_CTAG_TX | + NETIF_F_HW_VLAN_CTAG_RX | + NETIF_F_HW_VLAN_CTAG_FILTER; bond_dev->hw_features &= ~(NETIF_F_ALL_CSUM & ~NETIF_F_HW_CSUM); + bond_dev->hw_features |= NETIF_F_GSO_UDP_TUNNEL; bond_dev->features |= bond_dev->hw_features; } -static void bond_work_cancel_all(struct bonding *bond) -{ - if (bond->params.miimon && delayed_work_pending(&bond->mii_work)) - cancel_delayed_work_sync(&bond->mii_work); - - if (bond->params.arp_interval && delayed_work_pending(&bond->arp_work)) - cancel_delayed_work_sync(&bond->arp_work); - - if (bond->params.mode == BOND_MODE_ALB && - delayed_work_pending(&bond->alb_work)) - cancel_delayed_work_sync(&bond->alb_work); - - if (bond->params.mode == BOND_MODE_8023AD && - delayed_work_pending(&bond->ad_work)) - cancel_delayed_work_sync(&bond->ad_work); - - if (delayed_work_pending(&bond->mcast_work)) - cancel_delayed_work_sync(&bond->mcast_work); -} - /* * Destroy a bonding device. * Must be under rtnl_lock when this function is called. @@ -4375,94 +3994,59 @@ static void bond_work_cancel_all(struct bonding *bond) static void bond_uninit(struct net_device *bond_dev) { struct bonding *bond = netdev_priv(bond_dev); - struct vlan_entry *vlan, *tmp; + struct list_head *iter; + struct slave *slave; bond_netpoll_cleanup(bond_dev); /* Release the bonded slaves */ - bond_release_all(bond_dev); + bond_for_each_slave(bond, slave, iter) + __bond_release_one(bond_dev, slave->dev, true); + pr_info("%s: Released all slaves\n", bond_dev->name); list_del(&bond->bond_list); - bond_work_cancel_all(bond); - - bond_remove_proc_entry(bond); - bond_debug_unregister(bond); - - __hw_addr_flush(&bond->mc_list); - - list_for_each_entry_safe(vlan, tmp, &bond->vlan_list, vlan_list) { - list_del(&vlan->vlan_list); - kfree(vlan); - } } /*------------------------- Module initialization ---------------------------*/ -/* - * Convert string input module parms. Accept either the - * number of the mode or its string name. A bit complicated because - * 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, const struct bond_parm_tbl *tbl) -{ - int modeint = -1, i, rv; - char *p, modestr[BOND_MAX_MODENAME_LEN + 1] = { 0, }; - - for (p = (char *)buf; *p; p++) - if (!(isdigit(*p) || isspace(*p))) - break; - - if (*p) - rv = sscanf(buf, "%20s", modestr); - else - rv = sscanf(buf, "%d", &modeint); - - if (!rv) - return -1; - - for (i = 0; tbl[i].modename; i++) { - if (modeint == tbl[i].mode) - return tbl[i].mode; - if (strcmp(modestr, tbl[i].modename) == 0) - return tbl[i].mode; - } - - return -1; -} - static int bond_check_params(struct bond_params *params) { - int arp_validate_value, fail_over_mac_value, primary_reselect_value; + int arp_validate_value, fail_over_mac_value, primary_reselect_value, i; + struct bond_opt_value newval; + const struct bond_opt_value *valptr; + int arp_all_targets_value; /* * Convert string parameters. */ if (mode) { - bond_mode = bond_parse_parm(mode, bond_mode_tbl); - if (bond_mode == -1) { - pr_err("Error: Invalid bonding mode \"%s\"\n", - mode == NULL ? "NULL" : mode); + bond_opt_initstr(&newval, mode); + valptr = bond_opt_parse(bond_opt_get(BOND_OPT_MODE), &newval); + if (!valptr) { + pr_err("Error: Invalid bonding mode \"%s\"\n", mode); return -EINVAL; } + bond_mode = valptr->value; } if (xmit_hash_policy) { if ((bond_mode != BOND_MODE_XOR) && - (bond_mode != BOND_MODE_8023AD)) { + (bond_mode != BOND_MODE_8023AD) && + (bond_mode != BOND_MODE_TLB)) { pr_info("xmit_hash_policy param is irrelevant in mode %s\n", - bond_mode_name(bond_mode)); + bond_mode_name(bond_mode)); } else { - xmit_hashtype = bond_parse_parm(xmit_hash_policy, - xmit_hashtype_tbl); - if (xmit_hashtype == -1) { + bond_opt_initstr(&newval, xmit_hash_policy); + valptr = bond_opt_parse(bond_opt_get(BOND_OPT_XMIT_HASH), + &newval); + if (!valptr) { pr_err("Error: Invalid xmit_hash_policy \"%s\"\n", - xmit_hash_policy == NULL ? "NULL" : xmit_hash_policy); return -EINVAL; } + xmit_hashtype = valptr->value; } } @@ -4471,104 +4055,101 @@ static int bond_check_params(struct bond_params *params) pr_info("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) { + bond_opt_initstr(&newval, lacp_rate); + valptr = bond_opt_parse(bond_opt_get(BOND_OPT_LACP_RATE), + &newval); + if (!valptr) { pr_err("Error: Invalid lacp rate \"%s\"\n", - lacp_rate == NULL ? "NULL" : lacp_rate); + lacp_rate); return -EINVAL; } + lacp_fast = valptr->value; } } if (ad_select) { - params->ad_select = bond_parse_parm(ad_select, ad_select_tbl); - if (params->ad_select == -1) { - pr_err("Error: Invalid ad_select \"%s\"\n", - ad_select == NULL ? "NULL" : ad_select); + bond_opt_initstr(&newval, ad_select); + valptr = bond_opt_parse(bond_opt_get(BOND_OPT_AD_SELECT), + &newval); + if (!valptr) { + pr_err("Error: Invalid ad_select \"%s\"\n", ad_select); return -EINVAL; } - - if (bond_mode != BOND_MODE_8023AD) { - pr_warning("ad_select param only affects 802.3ad mode\n"); - } + params->ad_select = valptr->value; + if (bond_mode != BOND_MODE_8023AD) + pr_warn("ad_select param only affects 802.3ad mode\n"); } else { params->ad_select = BOND_AD_STABLE; } if (max_bonds < 0) { - pr_warning("Warning: max_bonds (%d) not in range %d-%d, so it was reset to BOND_DEFAULT_MAX_BONDS (%d)\n", - max_bonds, 0, INT_MAX, BOND_DEFAULT_MAX_BONDS); + pr_warn("Warning: max_bonds (%d) not in range %d-%d, so it was reset to BOND_DEFAULT_MAX_BONDS (%d)\n", + max_bonds, 0, INT_MAX, BOND_DEFAULT_MAX_BONDS); max_bonds = BOND_DEFAULT_MAX_BONDS; } if (miimon < 0) { - pr_warning("Warning: miimon module parameter (%d), not in range 0-%d, so it was reset to %d\n", - miimon, INT_MAX, BOND_LINK_MON_INTERV); - miimon = BOND_LINK_MON_INTERV; + pr_warn("Warning: miimon module parameter (%d), not in range 0-%d, so it was reset to 0\n", + miimon, INT_MAX); + miimon = 0; } if (updelay < 0) { - pr_warning("Warning: updelay module parameter (%d), not in range 0-%d, so it was reset to 0\n", - updelay, INT_MAX); + pr_warn("Warning: updelay module parameter (%d), not in range 0-%d, so it was reset to 0\n", + updelay, INT_MAX); updelay = 0; } if (downdelay < 0) { - pr_warning("Warning: downdelay module parameter (%d), not in range 0-%d, so it was reset to 0\n", - downdelay, INT_MAX); + pr_warn("Warning: downdelay module parameter (%d), not in range 0-%d, so it was reset to 0\n", + downdelay, INT_MAX); downdelay = 0; } if ((use_carrier != 0) && (use_carrier != 1)) { - pr_warning("Warning: use_carrier module parameter (%d), not of valid value (0/1), so it was set to 1\n", - use_carrier); + pr_warn("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_peer_notif < 0 || num_peer_notif > 255) { - pr_warning("Warning: num_grat_arp/num_unsol_na (%d) not in range 0-255 so it was reset to 1\n", - num_peer_notif); + pr_warn("Warning: num_grat_arp/num_unsol_na (%d) not in range 0-255 so it was reset to 1\n", + num_peer_notif); num_peer_notif = 1; } - /* reset values for 802.3ad */ - if (bond_mode == BOND_MODE_8023AD) { + /* reset values for 802.3ad/TLB/ALB */ + if (!bond_mode_uses_arp(bond_mode)) { if (!miimon) { - pr_warning("Warning: miimon must be specified, otherwise bonding will not detect link failure, speed and duplex which are essential for 802.3ad operation\n"); - pr_warning("Forcing miimon to 100msec\n"); - miimon = 100; + pr_warn("Warning: miimon must be specified, otherwise bonding will not detect link failure, speed and duplex which are essential for 802.3ad operation\n"); + pr_warn("Forcing miimon to 100msec\n"); + miimon = BOND_DEFAULT_MIIMON; } } if (tx_queues < 1 || tx_queues > 255) { - pr_warning("Warning: tx_queues (%d) should be between " - "1 and 255, resetting to %d\n", - tx_queues, BOND_DEFAULT_TX_QUEUES); + pr_warn("Warning: tx_queues (%d) should be between 1 and 255, resetting to %d\n", + tx_queues, BOND_DEFAULT_TX_QUEUES); tx_queues = BOND_DEFAULT_TX_QUEUES; } if ((all_slaves_active != 0) && (all_slaves_active != 1)) { - pr_warning("Warning: all_slaves_active module parameter (%d), " - "not of valid value (0/1), so it was set to " - "0\n", all_slaves_active); + pr_warn("Warning: all_slaves_active module parameter (%d), not of valid value (0/1), so it was set to 0\n", + all_slaves_active); all_slaves_active = 0; } if (resend_igmp < 0 || resend_igmp > 255) { - pr_warning("Warning: resend_igmp (%d) should be between " - "0 and 255, resetting to %d\n", - resend_igmp, BOND_DEFAULT_RESEND_IGMP); + pr_warn("Warning: resend_igmp (%d) should be between 0 and 255, resetting to %d\n", + resend_igmp, BOND_DEFAULT_RESEND_IGMP); resend_igmp = BOND_DEFAULT_RESEND_IGMP; } - /* reset values for TLB/ALB */ - if ((bond_mode == BOND_MODE_TLB) || - (bond_mode == BOND_MODE_ALB)) { - if (!miimon) { - pr_warning("Warning: miimon must be specified, otherwise bonding will not detect link failure and link speed which are essential for TLB/ALB load balancing\n"); - pr_warning("Forcing miimon to 100msec\n"); - miimon = 100; - } + bond_opt_initval(&newval, packets_per_slave); + if (!bond_opt_parse(bond_opt_get(BOND_OPT_PACKETS_PER_SLAVE), &newval)) { + pr_warn("Warning: packets_per_slave (%d) should be between 0 and %u resetting to 1\n", + packets_per_slave, USHRT_MAX); + packets_per_slave = 1; } if (bond_mode == BOND_MODE_ALB) { @@ -4581,141 +4162,163 @@ 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... */ - pr_warning("Warning: miimon module parameter not set and updelay (%d) or downdelay (%d) module parameter is set; updelay and downdelay have no effect unless miimon is set\n", - updelay, downdelay); + pr_warn("Warning: miimon module parameter not set and updelay (%d) or downdelay (%d) module parameter is set; updelay and downdelay have no effect unless miimon is set\n", + updelay, downdelay); } } else { /* don't allow arp monitoring */ if (arp_interval) { - pr_warning("Warning: miimon (%d) and arp_interval (%d) can't be used simultaneously, disabling ARP monitoring\n", - miimon, arp_interval); + pr_warn("Warning: miimon (%d) and arp_interval (%d) can't be used simultaneously, disabling ARP monitoring\n", + miimon, arp_interval); arp_interval = 0; } if ((updelay % miimon) != 0) { - pr_warning("Warning: updelay (%d) is not a multiple of miimon (%d), updelay rounded to %d ms\n", - updelay, miimon, - (updelay / miimon) * miimon); + pr_warn("Warning: updelay (%d) is not a multiple of miimon (%d), updelay rounded to %d ms\n", + updelay, miimon, (updelay / miimon) * miimon); } updelay /= miimon; if ((downdelay % miimon) != 0) { - pr_warning("Warning: downdelay (%d) is not a multiple of miimon (%d), downdelay rounded to %d ms\n", - downdelay, miimon, - (downdelay / miimon) * miimon); + pr_warn("Warning: downdelay (%d) is not a multiple of miimon (%d), downdelay rounded to %d ms\n", + downdelay, miimon, + (downdelay / miimon) * miimon); } downdelay /= miimon; } if (arp_interval < 0) { - pr_warning("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); - arp_interval = BOND_LINK_ARP_INTERV; + pr_warn("Warning: arp_interval module parameter (%d), not in range 0-%d, so it was reset to 0\n", + arp_interval, INT_MAX); + arp_interval = 0; } - for (arp_ip_count = 0; - (arp_ip_count < BOND_MAX_ARP_TARGETS) && arp_ip_target[arp_ip_count]; - arp_ip_count++) { + for (arp_ip_count = 0, i = 0; + (arp_ip_count < BOND_MAX_ARP_TARGETS) && arp_ip_target[i]; i++) { /* not complete check, but should be good enough to catch mistakes */ - if (!isdigit(arp_ip_target[arp_ip_count][0])) { - pr_warning("Warning: bad arp_ip_target module parameter (%s), ARP monitoring will not be performed\n", - arp_ip_target[arp_ip_count]); + __be32 ip; + if (!in4_pton(arp_ip_target[i], -1, (u8 *)&ip, -1, NULL) || + !bond_is_ip_target_ok(ip)) { + pr_warn("Warning: bad arp_ip_target module parameter (%s), ARP monitoring will not be performed\n", + arp_ip_target[i]); arp_interval = 0; } else { - __be32 ip = in_aton(arp_ip_target[arp_ip_count]); - arp_target[arp_ip_count] = ip; + if (bond_get_targets_ip(arp_target, ip) == -1) + arp_target[arp_ip_count++] = ip; + else + pr_warn("Warning: duplicate address %pI4 in arp_ip_target, skipping\n", + &ip); } } if (arp_interval && !arp_ip_count) { /* don't allow arping if no arp_ip_target given... */ - pr_warning("Warning: arp_interval module parameter (%d) specified without providing an arp_ip_target parameter, arp_interval was reset to 0\n", - arp_interval); + pr_warn("Warning: arp_interval module parameter (%d) specified without providing an arp_ip_target parameter, arp_interval was reset to 0\n", + arp_interval); arp_interval = 0; } if (arp_validate) { - if (bond_mode != BOND_MODE_ACTIVEBACKUP) { - pr_err("arp_validate only supported in active-backup mode\n"); - return -EINVAL; - } if (!arp_interval) { pr_err("arp_validate requires arp_interval\n"); return -EINVAL; } - arp_validate_value = bond_parse_parm(arp_validate, - arp_validate_tbl); - if (arp_validate_value == -1) { + bond_opt_initstr(&newval, arp_validate); + valptr = bond_opt_parse(bond_opt_get(BOND_OPT_ARP_VALIDATE), + &newval); + if (!valptr) { pr_err("Error: invalid arp_validate \"%s\"\n", - arp_validate == NULL ? "NULL" : arp_validate); + arp_validate); return -EINVAL; } - } else + arp_validate_value = valptr->value; + } else { arp_validate_value = 0; + } + + arp_all_targets_value = 0; + if (arp_all_targets) { + bond_opt_initstr(&newval, arp_all_targets); + valptr = bond_opt_parse(bond_opt_get(BOND_OPT_ARP_ALL_TARGETS), + &newval); + if (!valptr) { + pr_err("Error: invalid arp_all_targets_value \"%s\"\n", + arp_all_targets); + arp_all_targets_value = 0; + } else { + arp_all_targets_value = valptr->value; + } + } if (miimon) { pr_info("MII link monitoring set to %d ms\n", miimon); } else if (arp_interval) { - int i; - + valptr = bond_opt_get_val(BOND_OPT_ARP_VALIDATE, + arp_validate_value); pr_info("ARP monitoring set to %d ms, validate %s, with %d target(s):", - arp_interval, - arp_validate_tbl[arp_validate_value].modename, - arp_ip_count); + arp_interval, valptr->string, arp_ip_count); for (i = 0; i < arp_ip_count; i++) - pr_info(" %s", arp_ip_target[i]); + pr_cont(" %s", arp_ip_target[i]); - pr_info("\n"); + pr_cont("\n"); } else if (max_bonds) { /* miimon and arp_interval not set, we need one so things * work as expected, see bonding.txt for details */ - pr_debug("Warning: either miimon or arp_interval and arp_ip_target module parameters must be specified, otherwise bonding will not detect link failures! see bonding.txt for details.\n"); + pr_debug("Warning: either miimon or arp_interval and arp_ip_target module parameters must be specified, otherwise bonding will not detect link failures! see bonding.txt for details\n"); } - if (primary && !USES_PRIMARY(bond_mode)) { + if (primary && !bond_mode_uses_primary(bond_mode)) { /* currently, using a primary only makes sense * in active backup, TLB or ALB modes */ - pr_warning("Warning: %s primary device specified but has no effect in %s mode\n", - primary, bond_mode_name(bond_mode)); + pr_warn("Warning: %s primary device specified but has no effect in %s mode\n", + primary, bond_mode_name(bond_mode)); primary = NULL; } if (primary && primary_reselect) { - primary_reselect_value = bond_parse_parm(primary_reselect, - pri_reselect_tbl); - if (primary_reselect_value == -1) { + bond_opt_initstr(&newval, primary_reselect); + valptr = bond_opt_parse(bond_opt_get(BOND_OPT_PRIMARY_RESELECT), + &newval); + if (!valptr) { pr_err("Error: Invalid primary_reselect \"%s\"\n", - primary_reselect == - NULL ? "NULL" : primary_reselect); + primary_reselect); return -EINVAL; } + primary_reselect_value = valptr->value; } else { primary_reselect_value = BOND_PRI_RESELECT_ALWAYS; } if (fail_over_mac) { - fail_over_mac_value = bond_parse_parm(fail_over_mac, - fail_over_mac_tbl); - if (fail_over_mac_value == -1) { + bond_opt_initstr(&newval, fail_over_mac); + valptr = bond_opt_parse(bond_opt_get(BOND_OPT_FAIL_OVER_MAC), + &newval); + if (!valptr) { pr_err("Error: invalid fail_over_mac \"%s\"\n", - arp_validate == NULL ? "NULL" : arp_validate); + fail_over_mac); return -EINVAL; } - + fail_over_mac_value = valptr->value; if (bond_mode != BOND_MODE_ACTIVEBACKUP) - pr_warning("Warning: fail_over_mac only affects active-backup mode.\n"); + pr_warn("Warning: fail_over_mac only affects active-backup mode\n"); } else { fail_over_mac_value = BOND_FOM_NONE; } + if (lp_interval == 0) { + pr_warn("Warning: ip_interval must be between 1 and %d, so it was reset to %d\n", + INT_MAX, BOND_ALB_DEFAULT_LP_INTERVAL); + lp_interval = BOND_ALB_DEFAULT_LP_INTERVAL; + } + /* fill params struct with the proper values */ params->mode = bond_mode; params->xmit_policy = xmit_hashtype; @@ -4723,6 +4326,7 @@ static int bond_check_params(struct bond_params *params) params->num_peer_notif = num_peer_notif; params->arp_interval = arp_interval; params->arp_validate = arp_validate_value; + params->arp_all_targets = arp_all_targets_value; params->updelay = updelay; params->downdelay = downdelay; params->use_carrier = use_carrier; @@ -4734,6 +4338,19 @@ static int bond_check_params(struct bond_params *params) params->all_slaves_active = all_slaves_active; params->resend_igmp = resend_igmp; params->min_links = min_links; + params->lp_interval = lp_interval; + params->packets_per_slave = packets_per_slave; + params->tlb_dynamic_lb = 1; /* Default value */ + if (packets_per_slave > 0) { + params->reciprocal_packets_per_slave = + reciprocal_value(packets_per_slave); + } else { + /* reciprocal_packets_per_slave is unused if + * packets_per_slave is 0 or 1, just initialize it + */ + params->reciprocal_packets_per_slave = + (struct reciprocal_value) { 0 }; + } if (primary) { strncpy(params->primary, primary, IFNAMSIZ); @@ -4747,6 +4364,7 @@ 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 struct lock_class_key bonding_tx_busylock_key; static void bond_set_lockdep_class_one(struct net_device *dev, struct netdev_queue *txq, @@ -4761,6 +4379,7 @@ 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); + dev->qdisc_tx_busylock = &bonding_tx_busylock_key; } /* @@ -4789,44 +4408,25 @@ static int bond_init(struct net_device *bond_dev) bond_set_lockdep_class(bond_dev); - bond_create_proc_entry(bond); list_add_tail(&bond->bond_list, &bn->dev_list); bond_prepare_sysfs_group(bond); bond_debug_register(bond); - __hw_addr_init(&bond->mc_list); - return 0; -} + /* Ensure valid dev_addr */ + if (is_zero_ether_addr(bond_dev->dev_addr) && + bond_dev->addr_assign_type == NET_ADDR_PERM) + eth_hw_addr_random(bond_dev); -static int bond_validate(struct nlattr *tb[], struct nlattr *data[]) -{ - if (tb[IFLA_ADDRESS]) { - if (nla_len(tb[IFLA_ADDRESS]) != ETH_ALEN) - return -EINVAL; - if (!is_valid_ether_addr(nla_data(tb[IFLA_ADDRESS]))) - return -EADDRNOTAVAIL; - } return 0; } -static int bond_get_tx_queues(struct net *net, struct nlattr *tb[], - unsigned int *num_queues, - unsigned int *real_num_queues) +unsigned int bond_get_num_tx_queues(void) { - *num_queues = tx_queues; - return 0; + return tx_queues; } -static struct rtnl_link_ops bond_link_ops __read_mostly = { - .kind = "bond", - .priv_size = sizeof(struct bonding), - .setup = bond_setup, - .validate = bond_validate, - .get_tx_queues = bond_get_tx_queues, -}; - /* 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 @@ -4870,16 +4470,25 @@ static int __net_init bond_net_init(struct net *net) bond_create_proc_dir(bn); bond_create_sysfs(bn); - + return 0; } static void __net_exit bond_net_exit(struct net *net) { struct bond_net *bn = net_generic(net, bond_net_id); + struct bonding *bond, *tmp_bond; + LIST_HEAD(list); bond_destroy_sysfs(bn); bond_destroy_proc_dir(bn); + + /* Kill off any bonds created after unregistering bond rtnl ops */ + rtnl_lock(); + list_for_each_entry_safe(bond, tmp_bond, &bn->dev_list, bond_list) + unregister_netdevice_queue(bond->dev, &list); + unregister_netdevice_many(&list); + rtnl_unlock(); } static struct pernet_operations bond_net_ops = { @@ -4904,7 +4513,7 @@ static int __init bonding_init(void) if (res) goto out; - res = rtnl_link_register(&bond_link_ops); + res = bond_netlink_init(); if (res) goto err_link; @@ -4917,11 +4526,11 @@ static int __init bonding_init(void) } register_netdevice_notifier(&bond_netdev_notifier); - register_inetaddr_notifier(&bond_inetaddr_notifier); out: return res; err: - rtnl_link_unregister(&bond_link_ops); + bond_destroy_debugfs(); + bond_netlink_fini(); err_link: unregister_pernet_subsys(&bond_net_ops); goto out; @@ -4931,11 +4540,10 @@ err_link: static void __exit bonding_exit(void) { unregister_netdevice_notifier(&bond_netdev_notifier); - unregister_inetaddr_notifier(&bond_inetaddr_notifier); bond_destroy_debugfs(); - rtnl_link_unregister(&bond_link_ops); + bond_netlink_fini(); unregister_pernet_subsys(&bond_net_ops); #ifdef CONFIG_NET_POLL_CONTROLLER @@ -4952,4 +4560,3 @@ 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_ALIAS_RTNL_LINK("bond"); |