From 57f0f512b273f60d52568b8c6b77e17f5636edc0 Mon Sep 17 00:00:00 2001 From: =?UTF-8?q?Andr=C3=A9=20Fabian=20Silva=20Delgado?= Date: Wed, 5 Aug 2015 17:04:01 -0300 Subject: Initial import --- include/net/bonding.h | 665 ++++++++++++++++++++++++++++++++++++++++++++++++++ 1 file changed, 665 insertions(+) create mode 100644 include/net/bonding.h (limited to 'include/net/bonding.h') diff --git a/include/net/bonding.h b/include/net/bonding.h new file mode 100644 index 000000000..78ed135e9 --- /dev/null +++ b/include/net/bonding.h @@ -0,0 +1,665 @@ +/* + * Bond several ethernet interfaces into a Cisco, running 'Etherchannel'. + * + * Portions are (c) Copyright 1995 Simon "Guru Aleph-Null" Janes + * NCM: Network and Communications Management, Inc. + * + * BUT, I'm the one who modified it for ethernet, so: + * (c) Copyright 1999, Thomas Davis, tadavis@lbl.gov + * + * This software may be used and distributed according to the terms + * of the GNU Public License, incorporated herein by reference. + * + */ + +#ifndef _NET_BONDING_H +#define _NET_BONDING_H + +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include + +#include +#include +#include + +#define BOND_MAX_ARP_TARGETS 16 + +#define BOND_DEFAULT_MIIMON 100 + +/* + * Less bad way to call ioctl from within the kernel; this needs to be + * done some other way to get the call out of interrupt context. + * Needs "ioctl" variable to be supplied by calling context. + */ +#define IOCTL(dev, arg, cmd) ({ \ + int res = 0; \ + mm_segment_t fs = get_fs(); \ + set_fs(get_ds()); \ + res = ioctl(dev, arg, cmd); \ + set_fs(fs); \ + res; }) + +#define BOND_MODE(bond) ((bond)->params.mode) + +/* slave list primitives */ +#define bond_slave_list(bond) (&(bond)->dev->adj_list.lower) + +#define bond_has_slaves(bond) !list_empty(bond_slave_list(bond)) + +/* IMPORTANT: bond_first/last_slave can return NULL in case of an empty list */ +#define bond_first_slave(bond) \ + (bond_has_slaves(bond) ? \ + netdev_adjacent_get_private(bond_slave_list(bond)->next) : \ + NULL) +#define bond_last_slave(bond) \ + (bond_has_slaves(bond) ? \ + netdev_adjacent_get_private(bond_slave_list(bond)->prev) : \ + NULL) + +/* Caller must have rcu_read_lock */ +#define bond_first_slave_rcu(bond) \ + netdev_lower_get_first_private_rcu(bond->dev) + +#define bond_is_first_slave(bond, pos) (pos == bond_first_slave(bond)) +#define bond_is_last_slave(bond, pos) (pos == bond_last_slave(bond)) + +/** + * bond_for_each_slave - iterate over all slaves + * @bond: the bond holding this list + * @pos: current slave + * @iter: list_head * iterator + * + * Caller must hold RTNL + */ +#define bond_for_each_slave(bond, pos, iter) \ + netdev_for_each_lower_private((bond)->dev, pos, iter) + +/* Caller must have rcu_read_lock */ +#define bond_for_each_slave_rcu(bond, pos, iter) \ + netdev_for_each_lower_private_rcu((bond)->dev, pos, iter) + +#ifdef CONFIG_NET_POLL_CONTROLLER +extern atomic_t netpoll_block_tx; + +static inline void block_netpoll_tx(void) +{ + atomic_inc(&netpoll_block_tx); +} + +static inline void unblock_netpoll_tx(void) +{ + atomic_dec(&netpoll_block_tx); +} + +static inline int is_netpoll_tx_blocked(struct net_device *dev) +{ + if (unlikely(netpoll_tx_running(dev))) + return atomic_read(&netpoll_block_tx); + return 0; +} +#else +#define block_netpoll_tx() +#define unblock_netpoll_tx() +#define is_netpoll_tx_blocked(dev) (0) +#endif + +struct bond_params { + int mode; + int xmit_policy; + int miimon; + u8 num_peer_notif; + int arp_interval; + int arp_validate; + int arp_all_targets; + int use_carrier; + int fail_over_mac; + int updelay; + int downdelay; + int lacp_fast; + unsigned int min_links; + int ad_select; + char primary[IFNAMSIZ]; + int primary_reselect; + __be32 arp_targets[BOND_MAX_ARP_TARGETS]; + int tx_queues; + int all_slaves_active; + int resend_igmp; + int lp_interval; + int packets_per_slave; + int tlb_dynamic_lb; + struct reciprocal_value reciprocal_packets_per_slave; +}; + +struct bond_parm_tbl { + char *modename; + int mode; +}; + +struct netdev_notify_work { + struct delayed_work work; + struct net_device *dev; + struct netdev_bonding_info bonding_info; +}; + +struct slave { + struct net_device *dev; /* first - useful for panic debug */ + struct bonding *bond; /* our master */ + int delay; + /* all three in jiffies */ + unsigned long last_link_up; + unsigned long last_rx; + unsigned long target_last_arp_rx[BOND_MAX_ARP_TARGETS]; + s8 link; /* one of BOND_LINK_XXXX */ + s8 new_link; + u8 backup:1, /* indicates backup slave. Value corresponds with + BOND_STATE_ACTIVE and BOND_STATE_BACKUP */ + inactive:1, /* indicates inactive slave */ + should_notify:1; /* indicateds whether the state changed */ + u8 duplex; + u32 original_mtu; + u32 link_failure_count; + u32 speed; + u16 queue_id; + u8 perm_hwaddr[ETH_ALEN]; + struct ad_slave_info *ad_info; + struct tlb_slave_info tlb_info; +#ifdef CONFIG_NET_POLL_CONTROLLER + struct netpoll *np; +#endif + struct kobject kobj; + struct rtnl_link_stats64 slave_stats; +}; + +struct bond_up_slave { + unsigned int count; + struct rcu_head rcu; + struct slave *arr[0]; +}; + +/* + * Link pseudo-state only used internally by monitors + */ +#define BOND_LINK_NOCHANGE -1 + +/* + * Here are the locking policies for the two bonding locks: + * Get rcu_read_lock when reading or RTNL when writing slave list. + */ +struct bonding { + struct net_device *dev; /* first - useful for panic debug */ + struct slave __rcu *curr_active_slave; + struct slave __rcu *current_arp_slave; + struct slave __rcu *primary_slave; + struct bond_up_slave __rcu *slave_arr; /* Array of usable slaves */ + bool force_primary; + s32 slave_cnt; /* never change this value outside the attach/detach wrappers */ + int (*recv_probe)(const struct sk_buff *, struct bonding *, + struct slave *); + /* mode_lock is used for mode-specific locking needs, currently used by: + * 3ad mode (4) - protect against running bond_3ad_unbind_slave() and + * bond_3ad_state_machine_handler() concurrently and also + * the access to the state machine shared variables. + * TLB mode (5) - to sync the use and modifications of its hash table + * ALB mode (6) - to sync the use and modifications of its hash table + */ + spinlock_t mode_lock; + u8 send_peer_notif; + u8 igmp_retrans; +#ifdef CONFIG_PROC_FS + struct proc_dir_entry *proc_entry; + char proc_file_name[IFNAMSIZ]; +#endif /* CONFIG_PROC_FS */ + struct list_head bond_list; + u32 rr_tx_counter; + struct ad_bond_info ad_info; + struct alb_bond_info alb_info; + struct bond_params params; + struct workqueue_struct *wq; + struct delayed_work mii_work; + struct delayed_work arp_work; + struct delayed_work alb_work; + struct delayed_work ad_work; + struct delayed_work mcast_work; + struct delayed_work slave_arr_work; +#ifdef CONFIG_DEBUG_FS + /* debugging support via debugfs */ + struct dentry *debug_dir; +#endif /* CONFIG_DEBUG_FS */ + struct rtnl_link_stats64 bond_stats; +}; + +#define bond_slave_get_rcu(dev) \ + ((struct slave *) rcu_dereference(dev->rx_handler_data)) + +#define bond_slave_get_rtnl(dev) \ + ((struct slave *) rtnl_dereference(dev->rx_handler_data)) + +void bond_queue_slave_event(struct slave *slave); + +struct bond_vlan_tag { + __be16 vlan_proto; + unsigned short vlan_id; +}; + +/** + * Returns NULL if the net_device does not belong to any of the bond's slaves + * + * Caller must hold bond lock for read + */ +static inline struct slave *bond_get_slave_by_dev(struct bonding *bond, + struct net_device *slave_dev) +{ + return netdev_lower_dev_get_private(bond->dev, slave_dev); +} + +static inline struct bonding *bond_get_bond_by_slave(struct slave *slave) +{ + return slave->bond; +} + +static inline bool bond_should_override_tx_queue(struct bonding *bond) +{ + return BOND_MODE(bond) == BOND_MODE_ACTIVEBACKUP || + BOND_MODE(bond) == BOND_MODE_ROUNDROBIN; +} + +static inline bool bond_is_lb(const struct bonding *bond) +{ + return BOND_MODE(bond) == BOND_MODE_TLB || + BOND_MODE(bond) == BOND_MODE_ALB; +} + +static inline bool bond_is_nondyn_tlb(const struct bonding *bond) +{ + return (BOND_MODE(bond) == BOND_MODE_TLB) && + (bond->params.tlb_dynamic_lb == 0); +} + +static inline bool bond_mode_uses_xmit_hash(const struct bonding *bond) +{ + return (BOND_MODE(bond) == BOND_MODE_8023AD || + BOND_MODE(bond) == BOND_MODE_XOR || + bond_is_nondyn_tlb(bond)); +} + +static inline bool bond_mode_uses_arp(int mode) +{ + return mode != BOND_MODE_8023AD && mode != BOND_MODE_TLB && + mode != BOND_MODE_ALB; +} + +static inline bool bond_mode_uses_primary(int mode) +{ + return mode == BOND_MODE_ACTIVEBACKUP || mode == BOND_MODE_TLB || + mode == BOND_MODE_ALB; +} + +static inline bool bond_uses_primary(struct bonding *bond) +{ + return bond_mode_uses_primary(BOND_MODE(bond)); +} + +static inline bool bond_slave_is_up(struct slave *slave) +{ + return netif_running(slave->dev) && netif_carrier_ok(slave->dev); +} + +static inline void bond_set_active_slave(struct slave *slave) +{ + if (slave->backup) { + slave->backup = 0; + bond_queue_slave_event(slave); + rtmsg_ifinfo(RTM_NEWLINK, slave->dev, 0, GFP_ATOMIC); + } +} + +static inline void bond_set_backup_slave(struct slave *slave) +{ + if (!slave->backup) { + slave->backup = 1; + bond_queue_slave_event(slave); + rtmsg_ifinfo(RTM_NEWLINK, slave->dev, 0, GFP_ATOMIC); + } +} + +static inline void bond_set_slave_state(struct slave *slave, + int slave_state, bool notify) +{ + if (slave->backup == slave_state) + return; + + slave->backup = slave_state; + if (notify) { + rtmsg_ifinfo(RTM_NEWLINK, slave->dev, 0, GFP_ATOMIC); + bond_queue_slave_event(slave); + slave->should_notify = 0; + } else { + if (slave->should_notify) + slave->should_notify = 0; + else + slave->should_notify = 1; + } +} + +static inline void bond_slave_state_change(struct bonding *bond) +{ + struct list_head *iter; + struct slave *tmp; + + bond_for_each_slave(bond, tmp, iter) { + if (tmp->link == BOND_LINK_UP) + bond_set_active_slave(tmp); + else if (tmp->link == BOND_LINK_DOWN) + bond_set_backup_slave(tmp); + } +} + +static inline void bond_slave_state_notify(struct bonding *bond) +{ + struct list_head *iter; + struct slave *tmp; + + bond_for_each_slave(bond, tmp, iter) { + if (tmp->should_notify) { + rtmsg_ifinfo(RTM_NEWLINK, tmp->dev, 0, GFP_ATOMIC); + tmp->should_notify = 0; + } + } +} + +static inline int bond_slave_state(struct slave *slave) +{ + return slave->backup; +} + +static inline bool bond_is_active_slave(struct slave *slave) +{ + return !bond_slave_state(slave); +} + +static inline bool bond_slave_can_tx(struct slave *slave) +{ + return bond_slave_is_up(slave) && slave->link == BOND_LINK_UP && + bond_is_active_slave(slave); +} + +#define BOND_PRI_RESELECT_ALWAYS 0 +#define BOND_PRI_RESELECT_BETTER 1 +#define BOND_PRI_RESELECT_FAILURE 2 + +#define BOND_FOM_NONE 0 +#define BOND_FOM_ACTIVE 1 +#define BOND_FOM_FOLLOW 2 + +#define BOND_ARP_TARGETS_ANY 0 +#define BOND_ARP_TARGETS_ALL 1 + +#define BOND_ARP_VALIDATE_NONE 0 +#define BOND_ARP_VALIDATE_ACTIVE (1 << BOND_STATE_ACTIVE) +#define BOND_ARP_VALIDATE_BACKUP (1 << BOND_STATE_BACKUP) +#define BOND_ARP_VALIDATE_ALL (BOND_ARP_VALIDATE_ACTIVE | \ + BOND_ARP_VALIDATE_BACKUP) +#define BOND_ARP_FILTER (BOND_ARP_VALIDATE_ALL + 1) +#define BOND_ARP_FILTER_ACTIVE (BOND_ARP_VALIDATE_ACTIVE | \ + BOND_ARP_FILTER) +#define BOND_ARP_FILTER_BACKUP (BOND_ARP_VALIDATE_BACKUP | \ + BOND_ARP_FILTER) + +#define BOND_SLAVE_NOTIFY_NOW true +#define BOND_SLAVE_NOTIFY_LATER false + +static inline int slave_do_arp_validate(struct bonding *bond, + struct slave *slave) +{ + return bond->params.arp_validate & (1 << bond_slave_state(slave)); +} + +static inline int slave_do_arp_validate_only(struct bonding *bond) +{ + return bond->params.arp_validate & BOND_ARP_FILTER; +} + +static inline int bond_is_ip_target_ok(__be32 addr) +{ + return !ipv4_is_lbcast(addr) && !ipv4_is_zeronet(addr); +} + +/* Get the oldest arp which we've received on this slave for bond's + * arp_targets. + */ +static inline unsigned long slave_oldest_target_arp_rx(struct bonding *bond, + struct slave *slave) +{ + int i = 1; + unsigned long ret = slave->target_last_arp_rx[0]; + + for (; (i < BOND_MAX_ARP_TARGETS) && bond->params.arp_targets[i]; i++) + if (time_before(slave->target_last_arp_rx[i], ret)) + ret = slave->target_last_arp_rx[i]; + + return ret; +} + +static inline unsigned long slave_last_rx(struct bonding *bond, + struct slave *slave) +{ + if (bond->params.arp_all_targets == BOND_ARP_TARGETS_ALL) + return slave_oldest_target_arp_rx(bond, slave); + + return slave->last_rx; +} + +#ifdef CONFIG_NET_POLL_CONTROLLER +static inline void bond_netpoll_send_skb(const struct slave *slave, + struct sk_buff *skb) +{ + struct netpoll *np = slave->np; + + if (np) + netpoll_send_skb(np, skb); +} +#else +static inline void bond_netpoll_send_skb(const struct slave *slave, + struct sk_buff *skb) +{ +} +#endif + +static inline void bond_set_slave_inactive_flags(struct slave *slave, + bool notify) +{ + if (!bond_is_lb(slave->bond)) + bond_set_slave_state(slave, BOND_STATE_BACKUP, notify); + if (!slave->bond->params.all_slaves_active) + slave->inactive = 1; +} + +static inline void bond_set_slave_active_flags(struct slave *slave, + bool notify) +{ + bond_set_slave_state(slave, BOND_STATE_ACTIVE, notify); + slave->inactive = 0; +} + +static inline bool bond_is_slave_inactive(struct slave *slave) +{ + return slave->inactive; +} + +static inline void bond_set_slave_link_state(struct slave *slave, int state) +{ + slave->link = state; + bond_queue_slave_event(slave); +} + +static inline __be32 bond_confirm_addr(struct net_device *dev, __be32 dst, __be32 local) +{ + struct in_device *in_dev; + __be32 addr = 0; + + rcu_read_lock(); + in_dev = __in_dev_get_rcu(dev); + + if (in_dev) + addr = inet_confirm_addr(dev_net(dev), in_dev, dst, local, + RT_SCOPE_HOST); + rcu_read_unlock(); + return addr; +} + +struct bond_net { + struct net *net; /* Associated network namespace */ + struct list_head dev_list; +#ifdef CONFIG_PROC_FS + struct proc_dir_entry *proc_dir; +#endif + struct class_attribute class_attr_bonding_masters; +}; + +int bond_arp_rcv(const struct sk_buff *skb, struct bonding *bond, struct slave *slave); +void bond_dev_queue_xmit(struct bonding *bond, struct sk_buff *skb, struct net_device *slave_dev); +int bond_create(struct net *net, const char *name); +int bond_create_sysfs(struct bond_net *net); +void bond_destroy_sysfs(struct bond_net *net); +void bond_prepare_sysfs_group(struct bonding *bond); +int bond_sysfs_slave_add(struct slave *slave); +void bond_sysfs_slave_del(struct slave *slave); +int bond_enslave(struct net_device *bond_dev, struct net_device *slave_dev); +int bond_release(struct net_device *bond_dev, struct net_device *slave_dev); +u32 bond_xmit_hash(struct bonding *bond, struct sk_buff *skb); +int bond_set_carrier(struct bonding *bond); +void bond_select_active_slave(struct bonding *bond); +void bond_change_active_slave(struct bonding *bond, struct slave *new_active); +void bond_create_debugfs(void); +void bond_destroy_debugfs(void); +void bond_debug_register(struct bonding *bond); +void bond_debug_unregister(struct bonding *bond); +void bond_debug_reregister(struct bonding *bond); +const char *bond_mode_name(int mode); +void bond_setup(struct net_device *bond_dev); +unsigned int bond_get_num_tx_queues(void); +int bond_netlink_init(void); +void bond_netlink_fini(void); +struct net_device *bond_option_active_slave_get_rcu(struct bonding *bond); +const char *bond_slave_link_status(s8 link); +struct bond_vlan_tag *bond_verify_device_path(struct net_device *start_dev, + struct net_device *end_dev, + int level); +int bond_update_slave_arr(struct bonding *bond, struct slave *skipslave); +void bond_slave_arr_work_rearm(struct bonding *bond, unsigned long delay); + +#ifdef CONFIG_PROC_FS +void bond_create_proc_entry(struct bonding *bond); +void bond_remove_proc_entry(struct bonding *bond); +void bond_create_proc_dir(struct bond_net *bn); +void bond_destroy_proc_dir(struct bond_net *bn); +#else +static inline void bond_create_proc_entry(struct bonding *bond) +{ +} + +static inline void bond_remove_proc_entry(struct bonding *bond) +{ +} + +static inline void bond_create_proc_dir(struct bond_net *bn) +{ +} + +static inline void bond_destroy_proc_dir(struct bond_net *bn) +{ +} +#endif + +static inline struct slave *bond_slave_has_mac(struct bonding *bond, + const u8 *mac) +{ + struct list_head *iter; + struct slave *tmp; + + bond_for_each_slave(bond, tmp, iter) + if (ether_addr_equal_64bits(mac, tmp->dev->dev_addr)) + return tmp; + + return NULL; +} + +/* Caller must hold rcu_read_lock() for read */ +static inline struct slave *bond_slave_has_mac_rcu(struct bonding *bond, + const u8 *mac) +{ + struct list_head *iter; + struct slave *tmp; + + bond_for_each_slave_rcu(bond, tmp, iter) + if (ether_addr_equal_64bits(mac, tmp->dev->dev_addr)) + return tmp; + + return NULL; +} + +/* Caller must hold rcu_read_lock() for read */ +static inline bool bond_slave_has_mac_rx(struct bonding *bond, const u8 *mac) +{ + struct list_head *iter; + struct slave *tmp; + struct netdev_hw_addr *ha; + + bond_for_each_slave_rcu(bond, tmp, iter) + if (ether_addr_equal_64bits(mac, tmp->dev->dev_addr)) + return true; + + if (netdev_uc_empty(bond->dev)) + return false; + + netdev_for_each_uc_addr(ha, bond->dev) + if (ether_addr_equal_64bits(mac, ha->addr)) + return true; + + return false; +} + +/* Check if the ip is present in arp ip list, or first free slot if ip == 0 + * Returns -1 if not found, index if found + */ +static inline int bond_get_targets_ip(__be32 *targets, __be32 ip) +{ + int i; + + for (i = 0; i < BOND_MAX_ARP_TARGETS; i++) + if (targets[i] == ip) + return i; + else if (targets[i] == 0) + break; + + return -1; +} + +/* exported from bond_main.c */ +extern int bond_net_id; +extern const struct bond_parm_tbl bond_lacp_tbl[]; +extern const struct bond_parm_tbl xmit_hashtype_tbl[]; +extern const struct bond_parm_tbl arp_validate_tbl[]; +extern const struct bond_parm_tbl arp_all_targets_tbl[]; +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[]; + +/* exported from bond_netlink.c */ +extern struct rtnl_link_ops bond_link_ops; + +static inline void bond_tx_drop(struct net_device *dev, struct sk_buff *skb) +{ + atomic_long_inc(&dev->tx_dropped); + dev_kfree_skb_any(skb); +} + +#endif /* _NET_BONDING_H */ -- cgit v1.2.3