From mboxrd@z Thu Jan 1 00:00:00 1970 From: Ben Hutchings Subject: [PATCH net-next-2.6 3/3] bonding,ipv4,ipv6,vlan: Handle NETDEV_BONDING_FAILOVER like NETDEV_NOTIFY_PEERS Date: Sat, 16 Apr 2011 00:47:51 +0100 Message-ID: <1302911271.2845.41.camel@bwh-desktop> Mime-Version: 1.0 Content-Type: text/plain; charset="UTF-8" Content-Transfer-Encoding: 7bit Cc: netdev@vger.kernel.org To: David Miller , Jay Vosburgh , Andy Gospodarek , Patrick McHardy Return-path: Received: from mail.solarflare.com ([216.237.3.220]:6808 "EHLO exchange.solarflare.com" rhost-flags-OK-OK-OK-OK) by vger.kernel.org with ESMTP id S1752610Ab1DOXrz (ORCPT ); Fri, 15 Apr 2011 19:47:55 -0400 Sender: netdev-owner@vger.kernel.org List-ID: It is undesirable for the bonding driver to be poking into higher level protocols, and notifiers provide a way to avoid that. This does mean removing the ability to configure reptitition of gratuitous ARPs and unsolicited NAs. Signed-off-by: Ben Hutchings --- drivers/net/bonding/Makefile | 3 - drivers/net/bonding/bond_ipv6.c | 225 -------------------------------------- drivers/net/bonding/bond_main.c | 96 ---------------- drivers/net/bonding/bond_sysfs.c | 80 -------------- drivers/net/bonding/bonding.h | 29 ----- net/8021q/vlan.c | 3 +- net/ipv4/devinet.c | 1 + net/ipv6/ndisc.c | 1 + 8 files changed, 4 insertions(+), 434 deletions(-) delete mode 100644 drivers/net/bonding/bond_ipv6.c diff --git a/drivers/net/bonding/Makefile b/drivers/net/bonding/Makefile index 3c5c014..4c21bf6 100644 --- a/drivers/net/bonding/Makefile +++ b/drivers/net/bonding/Makefile @@ -9,6 +9,3 @@ bonding-objs := bond_main.o bond_3ad.o bond_alb.o bond_sysfs.o bond_debugfs.o proc-$(CONFIG_PROC_FS) += bond_procfs.o bonding-objs += $(proc-y) -ipv6-$(subst m,y,$(CONFIG_IPV6)) += bond_ipv6.o -bonding-objs += $(ipv6-y) - diff --git a/drivers/net/bonding/bond_ipv6.c b/drivers/net/bonding/bond_ipv6.c deleted file mode 100644 index 84fbd4e..0000000 --- a/drivers/net/bonding/bond_ipv6.c +++ /dev/null @@ -1,225 +0,0 @@ -/* - * Copyright(c) 2008 Hewlett-Packard Development Company, L.P. - * - * This program is free software; you can redistribute it and/or modify it - * under the terms of the GNU General Public License as published by the - * Free Software Foundation; either version 2 of the License, or - * (at your option) any later version. - * - * This program is distributed in the hope that it will be useful, but - * WITHOUT ANY WARRANTY; without even the implied warranty of MERCHANTABILITY - * or FITNESS FOR A PARTICULAR PURPOSE. See the GNU General Public License - * for more details. - * - * You should have received a copy of the GNU General Public License along - * with this program; if not, write to the Free Software Foundation, Inc., - * 59 Temple Place - Suite 330, Boston, MA 02111-1307, USA. - * - * The full GNU General Public License is included in this distribution in the - * file called LICENSE. - * - */ - -#define pr_fmt(fmt) KBUILD_MODNAME ": " fmt - -#include -#include -#include -#include -#include -#include -#include "bonding.h" - -/* - * Assign bond->master_ipv6 to the next IPv6 address in the list, or - * zero it out if there are none. - */ -static void bond_glean_dev_ipv6(struct net_device *dev, struct in6_addr *addr) -{ - struct inet6_dev *idev; - - if (!dev) - return; - - idev = in6_dev_get(dev); - if (!idev) - return; - - read_lock_bh(&idev->lock); - if (!list_empty(&idev->addr_list)) { - struct inet6_ifaddr *ifa - = list_first_entry(&idev->addr_list, - struct inet6_ifaddr, if_list); - ipv6_addr_copy(addr, &ifa->addr); - } else - ipv6_addr_set(addr, 0, 0, 0, 0); - - read_unlock_bh(&idev->lock); - - in6_dev_put(idev); -} - -static void bond_na_send(struct net_device *slave_dev, - struct in6_addr *daddr, - int router, - unsigned short vlan_id) -{ - struct in6_addr mcaddr; - struct icmp6hdr icmp6h = { - .icmp6_type = NDISC_NEIGHBOUR_ADVERTISEMENT, - }; - struct sk_buff *skb; - - icmp6h.icmp6_router = router; - icmp6h.icmp6_solicited = 0; - icmp6h.icmp6_override = 1; - - addrconf_addr_solict_mult(daddr, &mcaddr); - - pr_debug("ipv6 na on slave %s: dest %pI6, src %pI6\n", - slave_dev->name, &mcaddr, daddr); - - skb = ndisc_build_skb(slave_dev, &mcaddr, daddr, &icmp6h, daddr, - ND_OPT_TARGET_LL_ADDR); - - if (!skb) { - pr_err("NA packet allocation failed\n"); - return; - } - - if (vlan_id) { - /* The Ethernet header is not present yet, so it is - * too early to insert a VLAN tag. Force use of an - * out-of-line tag here and let dev_hard_start_xmit() - * insert it if the slave hardware can't. - */ - skb = __vlan_hwaccel_put_tag(skb, vlan_id); - if (!skb) { - pr_err("failed to insert VLAN tag\n"); - return; - } - } - - ndisc_send_skb(skb, slave_dev, NULL, &mcaddr, daddr, &icmp6h); -} - -/* - * Kick out an unsolicited Neighbor Advertisement for an IPv6 address on - * the bonding master. This will help the switch learn our address - * if in active-backup mode. - * - * Caller must hold curr_slave_lock for read or better - */ -void bond_send_unsolicited_na(struct bonding *bond) -{ - struct slave *slave = bond->curr_active_slave; - struct vlan_entry *vlan; - struct inet6_dev *idev; - int is_router; - - pr_debug("%s: bond %s slave %s\n", bond->dev->name, - __func__, slave ? slave->dev->name : "NULL"); - - if (!slave || !bond->send_unsol_na || - test_bit(__LINK_STATE_LINKWATCH_PENDING, &slave->dev->state)) - return; - - bond->send_unsol_na--; - - idev = in6_dev_get(bond->dev); - if (!idev) - return; - - is_router = !!idev->cnf.forwarding; - - in6_dev_put(idev); - - if (!ipv6_addr_any(&bond->master_ipv6)) - bond_na_send(slave->dev, &bond->master_ipv6, is_router, 0); - - list_for_each_entry(vlan, &bond->vlan_list, vlan_list) { - if (!ipv6_addr_any(&vlan->vlan_ipv6)) { - bond_na_send(slave->dev, &vlan->vlan_ipv6, is_router, - vlan->vlan_id); - } - } -} - -/* - * bond_inet6addr_event: handle inet6addr notifier chain events. - * - * We keep track of device IPv6 addresses primarily to use as source - * addresses in NS probes. - * - * We track one IPv6 for the main device (if it has one). - */ -static int bond_inet6addr_event(struct notifier_block *this, - unsigned long event, - void *ptr) -{ - struct inet6_ifaddr *ifa = ptr; - struct net_device *vlan_dev, *event_dev = ifa->idev->dev; - struct bonding *bond; - struct vlan_entry *vlan; - struct bond_net *bn = net_generic(dev_net(event_dev), bond_net_id); - - list_for_each_entry(bond, &bn->dev_list, bond_list) { - if (bond->dev == event_dev) { - switch (event) { - case NETDEV_UP: - if (ipv6_addr_any(&bond->master_ipv6)) - ipv6_addr_copy(&bond->master_ipv6, - &ifa->addr); - return NOTIFY_OK; - case NETDEV_DOWN: - if (ipv6_addr_equal(&bond->master_ipv6, - &ifa->addr)) - bond_glean_dev_ipv6(bond->dev, - &bond->master_ipv6); - return NOTIFY_OK; - default: - return NOTIFY_DONE; - } - } - - 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) { - case NETDEV_UP: - if (ipv6_addr_any(&vlan->vlan_ipv6)) - ipv6_addr_copy(&vlan->vlan_ipv6, - &ifa->addr); - return NOTIFY_OK; - case NETDEV_DOWN: - if (ipv6_addr_equal(&vlan->vlan_ipv6, - &ifa->addr)) - bond_glean_dev_ipv6(vlan_dev, - &vlan->vlan_ipv6); - return NOTIFY_OK; - default: - return NOTIFY_DONE; - } - } - } - } - return NOTIFY_DONE; -} - -static struct notifier_block bond_inet6addr_notifier = { - .notifier_call = bond_inet6addr_event, -}; - -void bond_register_ipv6_notifier(void) -{ - register_inet6addr_notifier(&bond_inet6addr_notifier); -} - -void bond_unregister_ipv6_notifier(void) -{ - unregister_inet6addr_notifier(&bond_inet6addr_notifier); -} - diff --git a/drivers/net/bonding/bond_main.c b/drivers/net/bonding/bond_main.c index b51e021..5cd4766 100644 --- a/drivers/net/bonding/bond_main.c +++ b/drivers/net/bonding/bond_main.c @@ -89,8 +89,6 @@ 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; static int updelay; static int downdelay; @@ -113,10 +111,6 @@ 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); -MODULE_PARM_DESC(num_unsol_na, "Number of unsolicited IPv6 Neighbor Advertisements packets to send on failover event"); module_param(miimon, int, 0); MODULE_PARM_DESC(miimon, "Link check interval in milliseconds"); module_param(updelay, int, 0); @@ -234,7 +228,6 @@ struct bond_parm_tbl ad_select_tbl[] = { /*-------------------------- Forward declarations ---------------------------*/ -static void bond_send_gratuitous_arp(struct bonding *bond); static int bond_init(struct net_device *bond_dev); static void bond_uninit(struct net_device *bond_dev); @@ -1160,14 +1153,6 @@ void bond_change_active_slave(struct bonding *bond, struct slave *new_active) bond_do_fail_over_mac(bond, new_active, old_active); - if (netif_running(bond->dev)) { - bond->send_grat_arp = bond->params.num_grat_arp; - bond_send_gratuitous_arp(bond); - - bond->send_unsol_na = bond->params.num_unsol_na; - bond_send_unsolicited_na(bond); - } - write_unlock_bh(&bond->curr_slave_lock); read_unlock(&bond->lock); @@ -2578,18 +2563,6 @@ void bond_mii_monitor(struct work_struct *work) if (bond->slave_cnt == 0) goto re_arm; - if (bond->send_grat_arp) { - read_lock(&bond->curr_slave_lock); - bond_send_gratuitous_arp(bond); - read_unlock(&bond->curr_slave_lock); - } - - if (bond->send_unsol_na) { - read_lock(&bond->curr_slave_lock); - bond_send_unsolicited_na(bond); - read_unlock(&bond->curr_slave_lock); - } - if (bond_miimon_inspect(bond)) { read_unlock(&bond->lock); rtnl_lock(); @@ -2751,44 +2724,6 @@ static void bond_arp_send_all(struct bonding *bond, struct slave *slave) } } -/* - * Kick out a gratuitous ARP for an IP on the bonding master plus one - * for each VLAN above us. - * - * Caller must hold curr_slave_lock for read or better - */ -static void bond_send_gratuitous_arp(struct bonding *bond) -{ - struct slave *slave = bond->curr_active_slave; - struct vlan_entry *vlan; - struct net_device *vlan_dev; - - pr_debug("bond_send_grat_arp: bond %s slave %s\n", - bond->dev->name, slave ? slave->dev->name : "NULL"); - - if (!slave || !bond->send_grat_arp || - test_bit(__LINK_STATE_LINKWATCH_PENDING, &slave->dev->state)) - return; - - bond->send_grat_arp--; - - if (bond->master_ip) { - bond_arp_send(slave->dev, ARPOP_REPLY, bond->master_ip, - bond->master_ip, 0); - } - - 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) { - bond_arp_send(slave->dev, ARPOP_REPLY, vlan->vlan_ip, - vlan->vlan_ip, vlan->vlan_id); - } - } -} - static void bond_validate_arp(struct bonding *bond, struct slave *slave, __be32 sip, __be32 tip) { int i; @@ -3255,18 +3190,6 @@ void bond_activebackup_arp_mon(struct work_struct *work) if (bond->slave_cnt == 0) goto re_arm; - if (bond->send_grat_arp) { - read_lock(&bond->curr_slave_lock); - bond_send_gratuitous_arp(bond); - read_unlock(&bond->curr_slave_lock); - } - - if (bond->send_unsol_na) { - read_lock(&bond->curr_slave_lock); - bond_send_unsolicited_na(bond); - read_unlock(&bond->curr_slave_lock); - } - if (bond_ab_arp_inspect(bond, delta_in_ticks)) { read_unlock(&bond->lock); rtnl_lock(); @@ -3645,9 +3568,6 @@ static int bond_close(struct net_device *bond_dev) write_lock_bh(&bond->lock); - bond->send_grat_arp = 0; - bond->send_unsol_na = 0; - /* signal timers not to re-arm */ bond->kill_timers = 1; @@ -4724,18 +4644,6 @@ static int bond_check_params(struct bond_params *params) use_carrier = 1; } - if (num_grat_arp < 0 || num_grat_arp > 255) { - pr_warning("Warning: num_grat_arp (%d) not in range 0-255 so it was reset to 1\n", - num_grat_arp); - num_grat_arp = 1; - } - - if (num_unsol_na < 0 || num_unsol_na > 255) { - pr_warning("Warning: num_unsol_na (%d) not in range 0-255 so it was reset to 1\n", - num_unsol_na); - num_unsol_na = 1; - } - /* reset values for 802.3ad */ if (bond_mode == BOND_MODE_8023AD) { if (!miimon) { @@ -4925,8 +4833,6 @@ static int bond_check_params(struct bond_params *params) params->mode = bond_mode; params->xmit_policy = xmit_hashtype; params->miimon = miimon; - params->num_grat_arp = num_grat_arp; - params->num_unsol_na = num_unsol_na; params->arp_interval = arp_interval; params->arp_validate = arp_validate_value; params->updelay = updelay; @@ -5121,7 +5027,6 @@ static int __init bonding_init(void) register_netdevice_notifier(&bond_netdev_notifier); register_inetaddr_notifier(&bond_inetaddr_notifier); - bond_register_ipv6_notifier(); out: return res; err: @@ -5136,7 +5041,6 @@ static void __exit bonding_exit(void) { unregister_netdevice_notifier(&bond_netdev_notifier); unregister_inetaddr_notifier(&bond_inetaddr_notifier); - bond_unregister_ipv6_notifier(); bond_destroy_sysfs(); bond_destroy_debugfs(); diff --git a/drivers/net/bonding/bond_sysfs.c b/drivers/net/bonding/bond_sysfs.c index de87aea..259ff32 100644 --- a/drivers/net/bonding/bond_sysfs.c +++ b/drivers/net/bonding/bond_sysfs.c @@ -874,84 +874,6 @@ static DEVICE_ATTR(ad_select, S_IRUGO | S_IWUSR, bonding_show_ad_select, bonding_store_ad_select); /* - * Show and set the number of grat ARP to send after a failover event. - */ -static ssize_t bonding_show_n_grat_arp(struct device *d, - struct device_attribute *attr, - char *buf) -{ - struct bonding *bond = to_bond(d); - - return sprintf(buf, "%d\n", bond->params.num_grat_arp); -} - -static ssize_t bonding_store_n_grat_arp(struct device *d, - struct device_attribute *attr, - const char *buf, size_t count) -{ - int new_value, ret = count; - struct bonding *bond = to_bond(d); - - if (sscanf(buf, "%d", &new_value) != 1) { - pr_err("%s: no num_grat_arp value specified.\n", - bond->dev->name); - ret = -EINVAL; - goto out; - } - if (new_value < 0 || new_value > 255) { - pr_err("%s: Invalid num_grat_arp value %d not in range 0-255; rejected.\n", - bond->dev->name, new_value); - ret = -EINVAL; - goto out; - } else { - bond->params.num_grat_arp = new_value; - } -out: - return ret; -} -static DEVICE_ATTR(num_grat_arp, S_IRUGO | S_IWUSR, - bonding_show_n_grat_arp, bonding_store_n_grat_arp); - -/* - * Show and set the number of unsolicited NA's to send after a failover event. - */ -static ssize_t bonding_show_n_unsol_na(struct device *d, - struct device_attribute *attr, - char *buf) -{ - struct bonding *bond = to_bond(d); - - return sprintf(buf, "%d\n", bond->params.num_unsol_na); -} - -static ssize_t bonding_store_n_unsol_na(struct device *d, - struct device_attribute *attr, - const char *buf, size_t count) -{ - int new_value, ret = count; - struct bonding *bond = to_bond(d); - - if (sscanf(buf, "%d", &new_value) != 1) { - pr_err("%s: no num_unsol_na value specified.\n", - bond->dev->name); - ret = -EINVAL; - goto out; - } - - if (new_value < 0 || new_value > 255) { - pr_err("%s: Invalid num_unsol_na value %d not in range 0-255; rejected.\n", - bond->dev->name, new_value); - ret = -EINVAL; - goto out; - } else - bond->params.num_unsol_na = new_value; -out: - return ret; -} -static DEVICE_ATTR(num_unsol_na, S_IRUGO | S_IWUSR, - bonding_show_n_unsol_na, bonding_store_n_unsol_na); - -/* * Show and set the MII monitor interval. There are two tricky bits * here. First, if MII monitoring is activated, then we must disable * ARP monitoring. Second, if the timer isn't running, we must @@ -1650,8 +1572,6 @@ static struct attribute *per_bond_attrs[] = { &dev_attr_lacp_rate.attr, &dev_attr_ad_select.attr, &dev_attr_xmit_hash_policy.attr, - &dev_attr_num_grat_arp.attr, - &dev_attr_num_unsol_na.attr, &dev_attr_miimon.attr, &dev_attr_primary.attr, &dev_attr_primary_reselect.attr, diff --git a/drivers/net/bonding/bonding.h b/drivers/net/bonding/bonding.h index 90736cb..77180b1 100644 --- a/drivers/net/bonding/bonding.h +++ b/drivers/net/bonding/bonding.h @@ -149,8 +149,6 @@ struct bond_params { int mode; int xmit_policy; int miimon; - int num_grat_arp; - int num_unsol_na; int arp_interval; int arp_validate; int use_carrier; @@ -178,9 +176,6 @@ struct vlan_entry { struct list_head vlan_list; __be32 vlan_ip; unsigned short vlan_id; -#if defined(CONFIG_IPV6) || defined(CONFIG_IPV6_MODULE) - struct in6_addr vlan_ipv6; -#endif }; struct slave { @@ -234,8 +229,6 @@ struct bonding { rwlock_t lock; rwlock_t curr_slave_lock; s8 kill_timers; - s8 send_grat_arp; - s8 send_unsol_na; s8 setup_by_slave; s8 igmp_retrans; #ifdef CONFIG_PROC_FS @@ -260,9 +253,6 @@ struct bonding { struct delayed_work alb_work; struct delayed_work ad_work; struct delayed_work mcast_work; -#if defined(CONFIG_IPV6) || defined(CONFIG_IPV6_MODULE) - struct in6_addr master_ipv6; -#endif #ifdef CONFIG_DEBUG_FS /* debugging suport via debugfs */ struct dentry *debug_dir; @@ -459,23 +449,4 @@ extern const struct bond_parm_tbl fail_over_mac_tbl[]; extern const struct bond_parm_tbl pri_reselect_tbl[]; extern struct bond_parm_tbl ad_select_tbl[]; -#if defined(CONFIG_IPV6) || defined(CONFIG_IPV6_MODULE) -void bond_send_unsolicited_na(struct bonding *bond); -void bond_register_ipv6_notifier(void); -void bond_unregister_ipv6_notifier(void); -#else -static inline void bond_send_unsolicited_na(struct bonding *bond) -{ - return; -} -static inline void bond_register_ipv6_notifier(void) -{ - return; -} -static inline void bond_unregister_ipv6_notifier(void) -{ - return; -} -#endif - #endif /* _LINUX_BONDING_H */ diff --git a/net/8021q/vlan.c b/net/8021q/vlan.c index b2ff70f..969e700 100644 --- a/net/8021q/vlan.c +++ b/net/8021q/vlan.c @@ -501,13 +501,14 @@ static int vlan_device_event(struct notifier_block *unused, unsigned long event, return NOTIFY_BAD; case NETDEV_NOTIFY_PEERS: + case NETDEV_BONDING_FAILOVER: /* Propagate to vlan devices */ for (i = 0; i < VLAN_N_VID; i++) { vlandev = vlan_group_get_device(grp, i); if (!vlandev) continue; - call_netdevice_notifiers(NETDEV_NOTIFY_PEERS, vlandev); + call_netdevice_notifiers(event, vlandev); } break; } diff --git a/net/ipv4/devinet.c b/net/ipv4/devinet.c index 5345b0b..acf553f 100644 --- a/net/ipv4/devinet.c +++ b/net/ipv4/devinet.c @@ -1203,6 +1203,7 @@ static int inetdev_event(struct notifier_block *this, unsigned long event, break; /* fall through */ case NETDEV_NOTIFY_PEERS: + case NETDEV_BONDING_FAILOVER: /* Send gratuitous ARP to notify of link change */ inetdev_send_gratuitous_arp(dev, in_dev); break; diff --git a/net/ipv6/ndisc.c b/net/ipv6/ndisc.c index a51fa74c..6f7d491 100644 --- a/net/ipv6/ndisc.c +++ b/net/ipv6/ndisc.c @@ -1746,6 +1746,7 @@ static int ndisc_netdev_event(struct notifier_block *this, unsigned long event, fib6_run_gc(~0UL, net); break; case NETDEV_NOTIFY_PEERS: + case NETDEV_BONDING_FAILOVER: ndisc_send_unsol_na(dev); break; default: -- 1.7.4 -- Ben Hutchings, Senior Software Engineer, Solarflare Not speaking for my employer; that's the marketing department's job. They asked us to note that Solarflare product names are trademarked.