diff options
Diffstat (limited to 'drivers/net/bonding/bond_main.c')
| -rw-r--r-- | drivers/net/bonding/bond_main.c | 464 |
1 files changed, 345 insertions, 119 deletions
diff --git a/drivers/net/bonding/bond_main.c b/drivers/net/bonding/bond_main.c index c3d98dde2f86..bdb68a600382 100644 --- a/drivers/net/bonding/bond_main.c +++ b/drivers/net/bonding/bond_main.c @@ -76,6 +76,7 @@ #include <linux/if_vlan.h> #include <linux/if_bonding.h> #include <linux/jiffies.h> +#include <linux/preempt.h> #include <net/route.h> #include <net/net_namespace.h> #include <net/netns/generic.h> @@ -90,6 +91,7 @@ #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_grat_arp = 1; static int num_unsol_na = 1; static int miimon = BOND_LINK_MON_INTERV; @@ -106,10 +108,14 @@ static int arp_interval = BOND_LINK_ARP_INTERV; static char *arp_ip_target[BOND_MAX_ARP_TARGETS]; static char *arp_validate; static char *fail_over_mac; +static int all_slaves_active = 0; static struct bond_params bonding_defaults; +static int resend_igmp = BOND_DEFAULT_RESEND_IGMP; module_param(max_bonds, int, 0); MODULE_PARM_DESC(max_bonds, "Max number of bonded devices"); +module_param(tx_queues, int, 0); +MODULE_PARM_DESC(tx_queues, "Max number of transmit queues (default = 16)"); module_param(num_grat_arp, int, 0644); MODULE_PARM_DESC(num_grat_arp, "Number of gratuitous ARP packets to send on failover event"); module_param(num_unsol_na, int, 0644); @@ -155,9 +161,19 @@ module_param(arp_validate, charp, 0); MODULE_PARM_DESC(arp_validate, "validate src/dst of ARP probes: none (default), active, backup or all"); module_param(fail_over_mac, charp, 0); MODULE_PARM_DESC(fail_over_mac, "For active-backup, do not set all slaves to the same MAC. none (default), active or follow"); +module_param(all_slaves_active, int, 0); +MODULE_PARM_DESC(all_slaves_active, "Keep all frames received on an interface" + "by setting active flag for all slaves. " + "0 for never (default), 1 for always."); +module_param(resend_igmp, int, 0); +MODULE_PARM_DESC(resend_igmp, "Number of IGMP membership reports to send on link failure"); /*----------------------------- Global variables ----------------------------*/ +#ifdef CONFIG_NET_POLL_CONTROLLER +cpumask_var_t netpoll_block_tx; +#endif + static const char * const version = DRV_DESCRIPTION ": v" DRV_VERSION " (" DRV_RELDATE ")\n"; @@ -168,7 +184,6 @@ static int arp_ip_count; static int bond_mode = BOND_MODE_ROUNDROBIN; static int xmit_hashtype = BOND_XMIT_POLICY_LAYER2; static int lacp_fast; -static int disable_netpoll = 1; const struct bond_parm_tbl bond_lacp_tbl[] = { { "slow", AD_LACP_SLOW}, @@ -297,6 +312,7 @@ static int bond_del_vlan(struct bonding *bond, unsigned short vlan_id) 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) { @@ -331,6 +347,7 @@ static int bond_del_vlan(struct bonding *bond, unsigned short vlan_id) out: write_unlock_bh(&bond->lock); + unblock_netpoll_tx(); return res; } @@ -414,6 +431,7 @@ int bond_dev_queue_xmit(struct bonding *bond, struct sk_buff *skb, { unsigned short uninitialized_var(vlan_id); + /* Test vlan_list not vlgrp to catch and handle 802.1p tags */ if (!list_empty(&bond->vlan_list) && !(slave_dev->features & NETIF_F_HW_VLAN_TX) && vlan_get_tag(skb, &vlan_id) == 0) { @@ -435,11 +453,9 @@ int bond_dev_queue_xmit(struct bonding *bond, struct sk_buff *skb, if (unlikely(bond->dev->priv_flags & IFF_IN_NETPOLL)) { struct netpoll *np = bond->dev->npinfo->netpoll; slave_dev->npinfo = bond->dev->npinfo; - np->real_dev = np->dev = skb->dev; slave_dev->priv_flags |= IFF_IN_NETPOLL; - netpoll_send_skb(np, skb); + netpoll_send_skb_on_dev(np, skb, slave_dev); slave_dev->priv_flags &= ~IFF_IN_NETPOLL; - np->dev = bond->dev; } else #endif dev_queue_xmit(skb); @@ -477,7 +493,9 @@ static void bond_vlan_rx_register(struct net_device *bond_dev, struct slave *slave; int i; + write_lock_bh(&bond->lock); bond->vlgrp = grp; + write_unlock_bh(&bond->lock); bond_for_each_slave(bond, slave, i) { struct net_device *slave_dev = slave->dev; @@ -557,10 +575,8 @@ static void bond_add_vlans_on_slave(struct bonding *bond, struct net_device *sla struct vlan_entry *vlan; const struct net_device_ops *slave_ops = slave_dev->netdev_ops; - write_lock_bh(&bond->lock); - - if (list_empty(&bond->vlan_list)) - goto out; + if (!bond->vlgrp) + return; if ((slave_dev->features & NETIF_F_HW_VLAN_RX) && slave_ops->ndo_vlan_rx_register) @@ -568,13 +584,10 @@ static void bond_add_vlans_on_slave(struct bonding *bond, struct net_device *sla if (!(slave_dev->features & NETIF_F_HW_VLAN_FILTER) || !(slave_ops->ndo_vlan_rx_add_vid)) - goto out; + return; list_for_each_entry(vlan, &bond->vlan_list, vlan_list) slave_ops->ndo_vlan_rx_add_vid(slave_dev, vlan->vlan_id); - -out: - write_unlock_bh(&bond->lock); } static void bond_del_vlans_from_slave(struct bonding *bond, @@ -584,16 +597,16 @@ static void bond_del_vlans_from_slave(struct bonding *bond, struct vlan_entry *vlan; struct net_device *vlan_dev; - write_lock_bh(&bond->lock); - - if (list_empty(&bond->vlan_list)) - goto out; + if (!bond->vlgrp) + return; if (!(slave_dev->features & NETIF_F_HW_VLAN_FILTER) || !(slave_ops->ndo_vlan_rx_kill_vid)) goto unreg; list_for_each_entry(vlan, &bond->vlan_list, vlan_list) { + if (!vlan->vlan_id) + continue; /* Save and then restore vlan_dev in the grp array, * since the slave's driver might clear it. */ @@ -606,9 +619,6 @@ unreg: if ((slave_dev->features & NETIF_F_HW_VLAN_RX) && slave_ops->ndo_vlan_rx_register) slave_ops->ndo_vlan_rx_register(slave_dev, NULL); - -out: - write_unlock_bh(&bond->lock); } /*------------------------------- Link status -------------------------------*/ @@ -860,18 +870,13 @@ static void bond_mc_del(struct bonding *bond, void *addr) } -/* - * 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(struct net_device *dev) { struct in_device *in_dev; struct ip_mc_list *im; rcu_read_lock(); - in_dev = __in_dev_get_rcu(bond->dev); + in_dev = __in_dev_get_rcu(dev); if (in_dev) { for (im = in_dev->mc_list; im; im = im->next) ip_mc_rejoin_group(im); @@ -881,6 +886,44 @@ static void bond_resend_igmp_join_requests(struct bonding *bond) } /* + * 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) +{ + 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); + + /* rejoin all groups on vlan devices */ + if (bond->vlgrp) { + list_for_each_entry(vlan, &bond->vlan_list, vlan_list) { + vlan_dev = vlan_group_get_device(bond->vlgrp, + vlan->vlan_id); + if (vlan_dev) + __bond_resend_igmp_join_requests(vlan_dev); + } + } + + if (--bond->igmp_retrans > 0) + 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); +} + +/* * flush all members of flush->mc_list from device dev->mc_list */ static void bond_mc_list_flush(struct net_device *bond_dev, @@ -939,7 +982,6 @@ static void bond_mc_swap(struct bonding *bond, struct slave *new_active, netdev_for_each_mc_addr(ha, bond->dev) dev_mc_add(new_active->dev, ha->addr); - bond_resend_igmp_join_requests(bond); } } @@ -1175,9 +1217,12 @@ void bond_change_active_slave(struct bonding *bond, struct slave *new_active) } } - /* resend IGMP joins since all were sent on curr_active_slave */ - if (bond->params.mode == BOND_MODE_ROUNDROBIN) { - bond_resend_igmp_join_requests(bond); + /* resend IGMP joins since active slave has changed or + * all were sent on curr_active_slave */ + if ((USES_PRIMARY(bond->params.mode) && new_active) || + bond->params.mode == BOND_MODE_ROUNDROBIN) { + bond->igmp_retrans = bond->params.resend_igmp; + queue_delayed_work(bond->wq, &bond->mcast_work, 0); } } @@ -1289,9 +1334,14 @@ static bool slaves_support_netpoll(struct net_device *bond_dev) static void bond_poll_controller(struct net_device *bond_dev) { - struct net_device *dev = bond_dev->npinfo->netpoll->real_dev; - if (dev != bond_dev) - netpoll_poll_dev(dev); + struct bonding *bond = netdev_priv(bond_dev); + struct slave *slave; + int i; + + bond_for_each_slave(bond, slave, i) { + if (slave->dev && IS_UP(slave->dev)) + netpoll_poll_dev(slave->dev); + } } static void bond_netpoll_cleanup(struct net_device *bond_dev) @@ -1433,7 +1483,7 @@ int bond_enslave(struct net_device *bond_dev, struct net_device *slave_dev) /* 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 (!list_empty(&bond->vlan_list)) { + if (bond->vlgrp) { 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; @@ -1522,16 +1572,32 @@ 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 (bond->slave_cnt == 0) + memcpy(bond->dev->dev_addr, slave_dev->dev_addr, + slave_dev->addr_len); + + new_slave = kzalloc(sizeof(struct slave), GFP_KERNEL); if (!new_slave) { res = -ENOMEM; goto err_undo_flags; } - /* save slave's original flags before calling - * netdev_set_master and dev_open + /* + * Set the new_slave's queue_id to be zero. Queue ID mapping + * is set via sysfs or module option if desired. */ - new_slave->original_flags = slave_dev->flags; + new_slave->queue_id = 0; + + /* Save slave's original mtu and then set it to match the bond */ + new_slave->original_mtu = slave_dev->mtu; + res = dev_set_mtu(slave_dev, bond->dev->mtu); + if (res) { + pr_debug("Error %d calling dev_set_mtu\n", res); + goto err_free; + } /* * Save slave's original ("permanent") mac address for modes @@ -1550,7 +1616,7 @@ int bond_enslave(struct net_device *bond_dev, struct net_device *slave_dev) res = dev_set_mac_address(slave_dev, &addr); if (res) { pr_debug("Error %d calling set_mac_address\n", res); - goto err_free; + goto err_restore_mtu; } } @@ -1742,23 +1808,15 @@ int bond_enslave(struct net_device *bond_dev, struct net_device *slave_dev) bond_set_carrier(bond); #ifdef CONFIG_NET_POLL_CONTROLLER - /* - * Netpoll and bonding is broken, make sure it is not initialized - * until it is fixed. - */ - if (disable_netpoll) { + if (slaves_support_netpoll(bond_dev)) { + bond_dev->priv_flags &= ~IFF_DISABLE_NETPOLL; + if (bond_dev->npinfo) + slave_dev->npinfo = bond_dev->npinfo; + } else if (!(bond_dev->priv_flags & IFF_DISABLE_NETPOLL)) { bond_dev->priv_flags |= IFF_DISABLE_NETPOLL; - } else { - if (slaves_support_netpoll(bond_dev)) { - bond_dev->priv_flags &= ~IFF_DISABLE_NETPOLL; - if (bond_dev->npinfo) - slave_dev->npinfo = bond_dev->npinfo; - } else if (!(bond_dev->priv_flags & IFF_DISABLE_NETPOLL)) { - bond_dev->priv_flags |= IFF_DISABLE_NETPOLL; - pr_info("New slave device %s does not support netpoll\n", - slave_dev->name); - pr_info("Disabling netpoll support for %s\n", bond_dev->name); - } + pr_info("New slave device %s does not support netpoll\n", + slave_dev->name); + pr_info("Disabling netpoll support for %s\n", bond_dev->name); } #endif read_unlock(&bond->lock); @@ -1793,6 +1851,9 @@ err_restore_mac: dev_set_mac_address(slave_dev, &addr); } +err_restore_mtu: + dev_set_mtu(slave_dev, new_slave->original_mtu); + err_free: kfree(new_slave); @@ -1827,6 +1888,7 @@ int bond_release(struct net_device *bond_dev, struct net_device *slave_dev) return -EINVAL; } + block_netpoll_tx(); netdev_bonding_change(bond_dev, NETDEV_BONDING_DESLAVE); write_lock_bh(&bond->lock); @@ -1836,6 +1898,7 @@ int bond_release(struct net_device *bond_dev, struct net_device *slave_dev) pr_info("%s: %s not enslaved\n", bond_dev->name, slave_dev->name); write_unlock_bh(&bond->lock); + unblock_netpoll_tx(); return -EINVAL; } @@ -1913,7 +1976,7 @@ int bond_release(struct net_device *bond_dev, struct net_device *slave_dev) */ memset(bond_dev->dev_addr, 0, bond_dev->addr_len); - if (list_empty(&bond->vlan_list)) { + if (!bond->vlgrp) { bond_dev->features |= NETIF_F_VLAN_CHALLENGED; } else { pr_warning("%s: Warning: clearing HW address of %s while it still has VLANs.\n", @@ -1929,6 +1992,7 @@ int bond_release(struct net_device *bond_dev, struct net_device *slave_dev) } write_unlock_bh(&bond->lock); + unblock_netpoll_tx(); /* must do this from outside any spinlocks */ bond_destroy_slave_symlinks(bond_dev, slave_dev); @@ -1959,10 +2023,8 @@ int bond_release(struct net_device *bond_dev, struct net_device *slave_dev) #ifdef CONFIG_NET_POLL_CONTROLLER read_lock_bh(&bond->lock); - /* Make sure netpoll over stays disabled until fixed. */ - if (!disable_netpoll) - if (slaves_support_netpoll(bond_dev)) - bond_dev->priv_flags &= ~IFF_DISABLE_NETPOLL; + if (slaves_support_netpoll(bond_dev)) + bond_dev->priv_flags &= ~IFF_DISABLE_NETPOLL; read_unlock_bh(&bond->lock); if (slave_dev->netdev_ops->ndo_netpoll_cleanup) slave_dev->netdev_ops->ndo_netpoll_cleanup(slave_dev); @@ -1980,6 +2042,8 @@ int bond_release(struct net_device *bond_dev, struct net_device *slave_dev) dev_set_mac_address(slave_dev, &addr); } + dev_set_mtu(slave_dev, slave->original_mtu); + slave_dev->priv_flags &= ~(IFF_MASTER_8023AD | IFF_MASTER_ALB | IFF_SLAVE_INACTIVE | IFF_BONDING | IFF_SLAVE_NEEDARP); @@ -1993,8 +2057,8 @@ int bond_release(struct net_device *bond_dev, struct net_device *slave_dev) * First release a slave and than destroy the bond if no more slaves are left. * Must be under rtnl_lock when this function is called. */ -int bond_release_and_destroy(struct net_device *bond_dev, - struct net_device *slave_dev) +static int bond_release_and_destroy(struct net_device *bond_dev, + struct net_device *slave_dev) { struct bonding *bond = netdev_priv(bond_dev); int ret; @@ -2103,9 +2167,9 @@ static int bond_release_all(struct net_device *bond_dev) */ memset(bond_dev->dev_addr, 0, bond_dev->addr_len); - if (list_empty(&bond->vlan_list)) + if (!bond->vlgrp) { bond_dev->features |= NETIF_F_VLAN_CHALLENGED; - else { + } else { 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", @@ -2116,7 +2180,6 @@ static int bond_release_all(struct net_device *bond_dev) out: write_unlock_bh(&bond->lock); - return 0; } @@ -2165,9 +2228,11 @@ static int bond_ioctl_change_active(struct net_device *bond_dev, struct net_devi (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; @@ -2342,8 +2407,11 @@ static void bond_miimon_commit(struct bonding *bond) slave->state = BOND_STATE_BACKUP; } - pr_info("%s: link status definitely up for interface %s.\n", - bond->dev->name, slave->dev->name); + bond_update_speed_duplex(slave); + + pr_info("%s: link status definitely up for interface %s, %d Mbps %s duplex.\n", + bond->dev->name, slave->dev->name, + slave->speed, slave->duplex ? "full" : "half"); /* notify ad that the link status has changed */ if (bond->params.mode == BOND_MODE_8023AD) @@ -2396,9 +2464,11 @@ static void bond_miimon_commit(struct bonding *bond) do_failover: ASSERT_RTNL(); + 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(); } bond_set_carrier(bond); @@ -2538,7 +2608,7 @@ static void bond_arp_send_all(struct bonding *bond, struct slave *slave) if (!targets[i]) break; pr_debug("basa: target %x\n", targets[i]); - if (list_empty(&bond->vlan_list)) { + if (!bond->vlgrp) { pr_debug("basa: empty vlan: arp_send\n"); bond_arp_send(slave->dev, ARPOP_REQUEST, targets[i], bond->master_ip, 0); @@ -2566,7 +2636,7 @@ static void bond_arp_send_all(struct bonding *bond, struct slave *slave) /* * This target is not on a VLAN */ - if (rt->u.dst.dev == bond->dev) { + if (rt->dst.dev == bond->dev) { ip_rt_put(rt); pr_debug("basa: rtdev == bond->dev: arp_send\n"); bond_arp_send(slave->dev, ARPOP_REQUEST, targets[i], @@ -2577,7 +2647,7 @@ static void bond_arp_send_all(struct bonding *bond, struct slave *slave) vlan_id = 0; list_for_each_entry(vlan, &bond->vlan_list, vlan_list) { vlan_dev = vlan_group_get_device(bond->vlgrp, vlan->vlan_id); - if (vlan_dev == rt->u.dst.dev) { + 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); @@ -2595,7 +2665,7 @@ static void bond_arp_send_all(struct bonding *bond, struct slave *slave) if (net_ratelimit()) { pr_warning("%s: no path to arp_ip_target %pI4 via rt.dev %s\n", bond->dev->name, &fl.fl4_dst, - rt->u.dst.dev ? rt->u.dst.dev->name : "NULL"); + rt->dst.dev ? rt->dst.dev->name : "NULL"); } ip_rt_put(rt); } @@ -2627,6 +2697,9 @@ static void bond_send_gratuitous_arp(struct bonding *bond) bond->master_ip, 0); } + if (!bond->vlgrp) + return; + list_for_each_entry(vlan, &bond->vlan_list, vlan_list) { vlan_dev = vlan_group_get_device(bond->vlgrp, vlan->vlan_id); if (vlan->vlan_ip) { @@ -2768,9 +2841,15 @@ void bond_loadbalance_arp_mon(struct work_struct *work) * so it can wait */ bond_for_each_slave(bond, slave, i) { + unsigned long trans_start = dev_trans_start(slave->dev); + if (slave->link != BOND_LINK_UP) { - if (time_before_eq(jiffies, dev_trans_start(slave->dev) + delta_in_ticks) && - time_before_eq(jiffies, slave->dev->last_rx + delta_in_ticks)) { + 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)) { slave->link = BOND_LINK_UP; slave->state = BOND_STATE_ACTIVE; @@ -2798,8 +2877,12 @@ void bond_loadbalance_arp_mon(struct work_struct *work) * when the source ip is 0, so don't take the link down * if we don't know our ip yet */ - if (time_after_eq(jiffies, dev_trans_start(slave->dev) + 2*delta_in_ticks) || - (time_after_eq(jiffies, slave->dev->last_rx + 2*delta_in_ticks))) { + 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)) { slave->link = BOND_LINK_DOWN; slave->state = BOND_STATE_BACKUP; @@ -2828,11 +2911,13 @@ void bond_loadbalance_arp_mon(struct work_struct *work) } if (do_failover) { + 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(); } re_arm: @@ -2854,13 +2939,16 @@ static int bond_ab_arp_inspect(struct bonding *bond, int delta_in_ticks) { struct slave *slave; int i, commit = 0; + unsigned long trans_start; bond_for_each_slave(bond, slave, i) { slave->new_link = BOND_LINK_NOCHANGE; if (slave->link != BOND_LINK_UP) { - if (time_before_eq(jiffies, slave_last_rx(bond, slave) + - delta_in_ticks)) { + if (time_in_range(jiffies, + slave_last_rx(bond, slave) - delta_in_ticks, + slave_last_rx(bond, slave) + delta_in_ticks)) { + slave->new_link = BOND_LINK_UP; commit++; } @@ -2873,8 +2961,9 @@ 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_after_eq(jiffies, slave->jiffies + - 2 * delta_in_ticks)) + if (time_in_range(jiffies, + slave->jiffies - delta_in_ticks, + slave->jiffies + 2 * delta_in_ticks)) continue; /* @@ -2892,8 +2981,10 @@ static int bond_ab_arp_inspect(struct bonding *bond, int delta_in_ticks) */ if (slave->state == BOND_STATE_BACKUP && !bond->current_arp_slave && - time_after(jiffies, slave_last_rx(bond, slave) + - 3 * delta_in_ticks)) { + !time_in_range(jiffies, + slave_last_rx(bond, slave) - delta_in_ticks, + slave_last_rx(bond, slave) + 3 * delta_in_ticks)) { + slave->new_link = BOND_LINK_DOWN; commit++; } @@ -2904,11 +2995,15 @@ static int bond_ab_arp_inspect(struct bonding *bond, int delta_in_ticks) * - (more than 2*delta since receive AND * the bond has an IP address) */ + trans_start = dev_trans_start(slave->dev); if ((slave->state == BOND_STATE_ACTIVE) && - (time_after_eq(jiffies, dev_trans_start(slave->dev) + - 2 * delta_in_ticks) || - (time_after_eq(jiffies, slave_last_rx(bond, slave) - + 2 * delta_in_ticks)))) { + (!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))) { + slave->new_link = BOND_LINK_DOWN; commit++; } @@ -2927,6 +3022,7 @@ static void bond_ab_arp_commit(struct bonding *bond, int delta_in_ticks) { struct slave *slave; int i; + unsigned long trans_start; bond_for_each_slave(bond, slave, i) { switch (slave->new_link) { @@ -2934,10 +3030,11 @@ static void bond_ab_arp_commit(struct bonding *bond, int delta_in_ticks) continue; case BOND_LINK_UP: + trans_start = dev_trans_start(slave->dev); if ((!bond->curr_active_slave && - time_before_eq(jiffies, - dev_trans_start(slave->dev) + - delta_in_ticks)) || + time_in_range(jiffies, + trans_start - delta_in_ticks, + trans_start + delta_in_ticks)) || bond->curr_active_slave != slave) { slave->link = BOND_LINK_UP; bond->current_arp_slave = NULL; @@ -2979,9 +3076,11 @@ static void bond_ab_arp_commit(struct bonding *bond, int delta_in_ticks) do_failover: ASSERT_RTNL(); + 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(); } bond_set_carrier(bond); @@ -3261,6 +3360,8 @@ static void bond_info_show_slave(struct seq_file *seq, seq_printf(seq, "\nSlave Interface: %s\n", slave->dev->name); seq_printf(seq, "MII Status: %s\n", (slave->link == BOND_LINK_UP) ? "up" : "down"); + seq_printf(seq, "Speed: %d Mbps\n", slave->speed); + seq_printf(seq, "Duplex: %s\n", slave->duplex ? "full" : "half"); seq_printf(seq, "Link Failure Count: %u\n", slave->link_failure_count); @@ -3276,6 +3377,7 @@ static void bond_info_show_slave(struct seq_file *seq, else seq_puts(seq, "Aggregator ID: N/A\n"); } + seq_printf(seq, "Slave queue ID: %d\n", slave->queue_id); } static int bond_info_seq_show(struct seq_file *seq, void *v) @@ -3558,6 +3660,8 @@ static int bond_inetaddr_event(struct notifier_block *this, unsigned long event, } list_for_each_entry(vlan, &bond->vlan_list, vlan_list) { + if (!bond->vlgrp) + continue; vlan_dev = vlan_group_get_device(bond->vlgrp, vlan->vlan_id); if (vlan_dev == event_dev) { switch (event) { @@ -3690,6 +3794,8 @@ static int bond_open(struct net_device *bond_dev) bond->kill_timers = 0; + INIT_DELAYED_WORK(&bond->mcast_work, bond_resend_igmp_join_requests_delayed); + if (bond_is_lb(bond)) { /* bond_alb_initialize must be called before the timer * is started. @@ -3774,6 +3880,8 @@ static int bond_close(struct net_device *bond_dev) break; } + if (delayed_work_pending(&bond->mcast_work)) + cancel_delayed_work(&bond->mcast_work); if (bond_is_lb(bond)) { /* Must be called only after all @@ -3785,50 +3893,49 @@ static int bond_close(struct net_device *bond_dev) return 0; } -static struct net_device_stats *bond_get_stats(struct net_device *bond_dev) +static struct rtnl_link_stats64 *bond_get_stats(struct net_device *bond_dev, + struct rtnl_link_stats64 *stats) { struct bonding *bond = netdev_priv(bond_dev); - struct net_device_stats *stats = &bond_dev->stats; - struct net_device_stats local_stats; + struct rtnl_link_stats64 temp; struct slave *slave; int i; - memset(&local_stats, 0, sizeof(struct net_device_stats)); + memset(stats, 0, sizeof(*stats)); read_lock_bh(&bond->lock); bond_for_each_slave(bond, slave, i) { - const struct net_device_stats *sstats = dev_get_stats(slave->dev); + const struct rtnl_link_stats64 *sstats = + dev_get_stats(slave->dev, &temp); - local_stats.rx_packets += sstats->rx_packets; - local_stats.rx_bytes += sstats->rx_bytes; - local_stats.rx_errors += sstats->rx_errors; - local_stats.rx_dropped += sstats->rx_dropped; + stats->rx_packets += sstats->rx_packets; + stats->rx_bytes += sstats->rx_bytes; + stats->rx_errors += sstats->rx_errors; + stats->rx_dropped += sstats->rx_dropped; - local_stats.tx_packets += sstats->tx_packets; - local_stats.tx_bytes += sstats->tx_bytes; - local_stats.tx_errors += sstats->tx_errors; - local_stats.tx_dropped += sstats->tx_dropped; + stats->tx_packets += sstats->tx_packets; + stats->tx_bytes += sstats->tx_bytes; + stats->tx_errors += sstats->tx_errors; + stats->tx_dropped += sstats->tx_dropped; - local_stats.multicast += sstats->multicast; - local_stats.collisions += sstats->collisions; + stats->multicast += sstats->multicast; + stats->collisions += sstats->collisions; - local_stats.rx_length_errors += sstats->rx_length_errors; - local_stats.rx_over_errors += sstats->rx_over_errors; - local_stats.rx_crc_errors += sstats->rx_crc_errors; - local_stats.rx_frame_errors += sstats->rx_frame_errors; - local_stats.rx_fifo_errors += sstats->rx_fifo_errors; - local_stats.rx_missed_errors += sstats->rx_missed_errors; + stats->rx_length_errors += sstats->rx_length_errors; + stats->rx_over_errors += sstats->rx_over_errors; + stats->rx_crc_errors += sstats->rx_crc_errors; + stats->rx_frame_errors += sstats->rx_frame_errors; + stats->rx_fifo_errors += sstats->rx_fifo_errors; + stats->rx_missed_errors += sstats->rx_missed_errors; - local_stats.tx_aborted_errors += sstats->tx_aborted_errors; - local_stats.tx_carrier_errors += sstats->tx_carrier_errors; - local_stats.tx_fifo_errors += sstats->tx_fifo_errors; - local_stats.tx_heartbeat_errors += sstats->tx_heartbeat_errors; - local_stats.tx_window_errors += sstats->tx_window_errors; + stats->tx_aborted_errors += sstats->tx_aborted_errors; + stats->tx_carrier_errors += sstats->tx_carrier_errors; + stats->tx_fifo_errors += sstats->tx_fifo_errors; + stats->tx_heartbeat_errors += sstats->tx_heartbeat_errors; + stats->tx_window_errors += sstats->tx_window_errors; } - memcpy(stats, &local_stats, sizeof(struct net_device_stats)); - read_unlock_bh(&bond->lock); return stats; @@ -4412,9 +4519,66 @@ static void bond_set_xmit_hash_policy(struct bonding *bond) } } +/* + * 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; + + read_lock(&bond->lock); + + if (!BOND_IS_OK(bond) || !skb->queue_mapping) + goto out; + + /* 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; + 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); + } + +out: + read_unlock(&bond->lock); + return res; +} + +static u16 bond_select_queue(struct net_device *dev, struct sk_buff *skb) +{ + /* + * This helper function exists to help dev_pick_tx get the correct + * destination queue. Using a helper function skips the a call to + * skb_tx_hash and will put the skbs in the queue we expect on their + * way down to the bonding driver. + */ + return skb->queue_mapping; +} + static netdev_tx_t bond_start_xmit(struct sk_buff *skb, struct net_device *dev) { - const struct bonding *bond = netdev_priv(dev); + struct bonding *bond = netdev_priv(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)) + return NETDEV_TX_BUSY; + + if (TX_QUEUE_OVERRIDE(bond->params.mode)) { + if (!bond_slave_override(bond, skb)) + return NETDEV_TX_OK; + } switch (bond->params.mode) { case BOND_MODE_ROUNDROBIN: @@ -4499,7 +4663,8 @@ static const struct net_device_ops bond_netdev_ops = { .ndo_open = bond_open, .ndo_stop = bond_close, .ndo_start_xmit = bond_start_xmit, - .ndo_get_stats = bond_get_stats, + .ndo_select_queue = bond_select_queue, + .ndo_get_stats64 = bond_get_stats, .ndo_do_ioctl = bond_do_ioctl, .ndo_set_multicast_list = bond_set_multicast_list, .ndo_change_mtu = bond_change_mtu, @@ -4574,6 +4739,10 @@ static void bond_setup(struct net_device *bond_dev) NETIF_F_HW_VLAN_RX | NETIF_F_HW_VLAN_FILTER); + /* By default, we enable GRO on bonding devices. + * Actual support requires lowlevel drivers are GRO ready. + */ + bond_dev->features |= NETIF_F_GRO; } static void bond_work_cancel_all(struct bonding *bond) @@ -4595,6 +4764,9 @@ static void bond_work_cancel_all(struct bonding *bond) if (bond->params.mode == BOND_MODE_8023AD && delayed_work_pending(&bond->ad_work)) cancel_delayed_work(&bond->ad_work); + + if (delayed_work_pending(&bond->mcast_work)) + cancel_delayed_work(&bond->mcast_work); } /* @@ -4604,6 +4776,7 @@ 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; bond_netpoll_cleanup(bond_dev); @@ -4617,6 +4790,11 @@ static void bond_uninit(struct net_device *bond_dev) bond_remove_proc_entry(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 ---------------------------*/ @@ -4767,6 +4945,27 @@ static int bond_check_params(struct bond_params *params) } } + 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); + 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); + 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); + resend_igmp = BOND_DEFAULT_RESEND_IGMP; + } + /* reset values for TLB/ALB */ if ((bond_mode == BOND_MODE_TLB) || (bond_mode == BOND_MODE_ALB)) { @@ -4937,6 +5136,9 @@ static int bond_check_params(struct bond_params *params) params->primary[0] = 0; params->primary_reselect = primary_reselect_value; params->fail_over_mac = fail_over_mac_value; + params->tx_queues = tx_queues; + params->all_slaves_active = all_slaves_active; + params->resend_igmp = resend_igmp; if (primary) { strncpy(params->primary, primary, IFNAMSIZ); @@ -5023,8 +5225,8 @@ int bond_create(struct net *net, const char *name) rtnl_lock(); - bond_dev = alloc_netdev(sizeof(struct bonding), name ? name : "", - bond_setup); + bond_dev = alloc_netdev_mq(sizeof(struct bonding), name ? name : "", + bond_setup, tx_queues); if (!bond_dev) { pr_err("%s: eek! can't alloc netdev!\n", name); rtnl_unlock(); @@ -5038,6 +5240,15 @@ int bond_create(struct net *net, const char *name) res = dev_alloc_name(bond_dev, "bond%d"); if (res < 0) goto out; + } else { + /* + * If we're given a name to register + * we need to ensure that its not already + * registered + */ + res = -EEXIST; + if (__dev_get_by_name(net, name) != NULL) + goto out; } res = register_netdevice(bond_dev); @@ -5086,6 +5297,13 @@ static int __init bonding_init(void) if (res) goto out; +#ifdef CONFIG_NET_POLL_CONTROLLER + if (!alloc_cpumask_var(&netpoll_block_tx, GFP_KERNEL)) { + res = -ENOMEM; + goto out; + } +#endif + res = register_pernet_subsys(&bond_net_ops); if (res) goto out; @@ -5104,6 +5322,7 @@ static int __init bonding_init(void) if (res) goto err; + register_netdevice_notifier(&bond_netdev_notifier); register_inetaddr_notifier(&bond_inetaddr_notifier); bond_register_ipv6_notifier(); @@ -5113,6 +5332,9 @@ err: rtnl_link_unregister(&bond_link_ops); err_link: unregister_pernet_subsys(&bond_net_ops); +#ifdef CONFIG_NET_POLL_CONTROLLER + free_cpumask_var(netpoll_block_tx); +#endif goto out; } @@ -5127,6 +5349,10 @@ static void __exit bonding_exit(void) rtnl_link_unregister(&bond_link_ops); unregister_pernet_subsys(&bond_net_ops); + +#ifdef CONFIG_NET_POLL_CONTROLLER + free_cpumask_var(netpoll_block_tx); +#endif } module_init(bonding_init); |