linux/drivers/net/bonding/bonding.h

446 lines
12 KiB
C
Raw Normal View History

/*
* 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 _LINUX_BONDING_H
#define _LINUX_BONDING_H
#include <linux/timer.h>
#include <linux/proc_fs.h>
#include <linux/if_bonding.h>
#include <linux/cpumask.h>
#include <linux/in6.h>
#include <linux/netpoll.h>
#include "bond_3ad.h"
#include "bond_alb.h"
#define DRV_VERSION "3.7.1"
#define DRV_RELDATE "April 27, 2011"
#define DRV_NAME "bonding"
#define DRV_DESCRIPTION "Ethernet Channel Bonding Driver"
#define bond_version DRV_DESCRIPTION ": v" DRV_VERSION " (" DRV_RELDATE ")\n"
#define BOND_MAX_ARP_TARGETS 16
#define IS_UP(dev) \
((((dev)->flags & IFF_UP) == IFF_UP) && \
netif_running(dev) && \
netif_carrier_ok(dev))
/*
* Checks whether slave is ready for transmit.
*/
#define SLAVE_IS_OK(slave) \
(((slave)->dev->flags & IFF_UP) && \
netif_running((slave)->dev) && \
((slave)->link == BOND_LINK_UP) && \
bond_is_active_slave(slave))
#define USES_PRIMARY(mode) \
(((mode) == BOND_MODE_ACTIVEBACKUP) || \
((mode) == BOND_MODE_TLB) || \
((mode) == BOND_MODE_ALB))
bonding: allow user-controlled output slave selection v2: changed bonding module version, modified to apply on top of changes from previous patch in series, and updated documentation to elaborate on multiqueue awareness that now exists in bonding driver. This patch give the user the ability to control the output slave for round-robin and active-backup bonding. Similar functionality was discussed in the past, but Jay Vosburgh indicated he would rather see a feature like this added to existing modes rather than creating a completely new mode. Jay's thoughts as well as Neil's input surrounding some of the issues with the first implementation pushed us toward a design that relied on the queue_mapping rather than skb marks. Round-robin and active-backup modes were chosen as the first users of this slave selection as they seemed like the most logical choices when considering a multi-switch environment. Round-robin mode works without any modification, but active-backup does require inclusion of the first patch in this series and setting the 'all_slaves_active' flag. This will allow reception of unicast traffic on any of the backup interfaces. This was tested with IPv4-based filters as well as VLAN-based filters with good results. More information as well as a configuration example is available in the patch to Documentation/networking/bonding.txt. Signed-off-by: Andy Gospodarek <andy@greyhouse.net> Signed-off-by: Neil Horman <nhorman@tuxdriver.com> Signed-off-by: David S. Miller <davem@davemloft.net>
2010-06-02 08:40:18 +00:00
#define TX_QUEUE_OVERRIDE(mode) \
(((mode) == BOND_MODE_ACTIVEBACKUP) || \
((mode) == BOND_MODE_ROUNDROBIN))
/*
* 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; })
/**
* bond_for_each_slave_from - iterate the slaves list from a starting point
* @bond: the bond holding this list.
* @pos: current slave.
* @cnt: counter for max number of moves
* @start: starting point.
*
* Caller must hold bond->lock
*/
#define bond_for_each_slave_from(bond, pos, cnt, start) \
for (cnt = 0, pos = start; \
cnt < (bond)->slave_cnt; \
cnt++, pos = (pos)->next)
/**
* bond_for_each_slave_from_to - iterate the slaves list from start point to stop point
* @bond: the bond holding this list.
* @pos: current slave.
* @cnt: counter for number max of moves
* @start: start point.
* @stop: stop point.
*
* Caller must hold bond->lock
*/
#define bond_for_each_slave_from_to(bond, pos, cnt, start, stop) \
for (cnt = 0, pos = start; \
((cnt < (bond)->slave_cnt) && (pos != (stop)->next)); \
cnt++, pos = (pos)->next)
/**
* bond_for_each_slave - iterate the slaves list from head
* @bond: the bond holding this list.
* @pos: current slave.
* @cnt: counter for max number of moves
*
* Caller must hold bond->lock
*/
#define bond_for_each_slave(bond, pos, cnt) \
bond_for_each_slave_from(bond, pos, cnt, (bond)->first_slave)
#ifdef CONFIG_NET_POLL_CONTROLLER
net: Convert netpoll blocking api in bonding driver to be a counter A while back I made some changes to enable netpoll in the bonding driver. Among them was a per-cpu flag that indicated we were in a path that held locks which could cause the netpoll path to block in during tx, and as such the tx path should queue the frame for later use. This appears to have given rise to a regression. If one of those paths on which we hold the per-cpu flag yields the cpu, its possible for us to come back on a different cpu, leading to us clearing a different flag than we set. This results in odd netpoll drops, and BUG backtraces appearing in the log, as we check to make sure that we only clear set bits, and only set clear bits. I had though briefly about changing the offending paths so that they wouldn't sleep, but looking at my origional work more closely, it doesn't appear that a per-cpu flag is warranted. We alrady gate the checking of this flag on IFF_IN_NETPOLL, so we don't hit this in the normal tx case anyway. And practically speaking, the normal use case for netpoll is to only have one client anyway, so we're not going to erroneously queue netpoll frames when its actually safe to do so. As such, lets just convert that per-cpu flag to an atomic counter. It fixes the rescheduling bugs, is equivalent from a performance perspective and actually eliminates some code in the process. Tested by the reporter and myself, successfully Reported-by: Liang Zheng <lzheng@redhat.com> CC: Jay Vosburgh <fubar@us.ibm.com> CC: Andy Gospodarek <andy@greyhouse.net> CC: David S. Miller <davem@davemloft.net> Signed-off-by: Neil Horman <nhorman@tuxdriver.com> Signed-off-by: David S. Miller <davem@davemloft.net>
2010-12-06 09:05:50 +00:00
extern atomic_t netpoll_block_tx;
static inline void block_netpoll_tx(void)
{
net: Convert netpoll blocking api in bonding driver to be a counter A while back I made some changes to enable netpoll in the bonding driver. Among them was a per-cpu flag that indicated we were in a path that held locks which could cause the netpoll path to block in during tx, and as such the tx path should queue the frame for later use. This appears to have given rise to a regression. If one of those paths on which we hold the per-cpu flag yields the cpu, its possible for us to come back on a different cpu, leading to us clearing a different flag than we set. This results in odd netpoll drops, and BUG backtraces appearing in the log, as we check to make sure that we only clear set bits, and only set clear bits. I had though briefly about changing the offending paths so that they wouldn't sleep, but looking at my origional work more closely, it doesn't appear that a per-cpu flag is warranted. We alrady gate the checking of this flag on IFF_IN_NETPOLL, so we don't hit this in the normal tx case anyway. And practically speaking, the normal use case for netpoll is to only have one client anyway, so we're not going to erroneously queue netpoll frames when its actually safe to do so. As such, lets just convert that per-cpu flag to an atomic counter. It fixes the rescheduling bugs, is equivalent from a performance perspective and actually eliminates some code in the process. Tested by the reporter and myself, successfully Reported-by: Liang Zheng <lzheng@redhat.com> CC: Jay Vosburgh <fubar@us.ibm.com> CC: Andy Gospodarek <andy@greyhouse.net> CC: David S. Miller <davem@davemloft.net> Signed-off-by: Neil Horman <nhorman@tuxdriver.com> Signed-off-by: David S. Miller <davem@davemloft.net>
2010-12-06 09:05:50 +00:00
atomic_inc(&netpoll_block_tx);
}
static inline void unblock_netpoll_tx(void)
{
net: Convert netpoll blocking api in bonding driver to be a counter A while back I made some changes to enable netpoll in the bonding driver. Among them was a per-cpu flag that indicated we were in a path that held locks which could cause the netpoll path to block in during tx, and as such the tx path should queue the frame for later use. This appears to have given rise to a regression. If one of those paths on which we hold the per-cpu flag yields the cpu, its possible for us to come back on a different cpu, leading to us clearing a different flag than we set. This results in odd netpoll drops, and BUG backtraces appearing in the log, as we check to make sure that we only clear set bits, and only set clear bits. I had though briefly about changing the offending paths so that they wouldn't sleep, but looking at my origional work more closely, it doesn't appear that a per-cpu flag is warranted. We alrady gate the checking of this flag on IFF_IN_NETPOLL, so we don't hit this in the normal tx case anyway. And practically speaking, the normal use case for netpoll is to only have one client anyway, so we're not going to erroneously queue netpoll frames when its actually safe to do so. As such, lets just convert that per-cpu flag to an atomic counter. It fixes the rescheduling bugs, is equivalent from a performance perspective and actually eliminates some code in the process. Tested by the reporter and myself, successfully Reported-by: Liang Zheng <lzheng@redhat.com> CC: Jay Vosburgh <fubar@us.ibm.com> CC: Andy Gospodarek <andy@greyhouse.net> CC: David S. Miller <davem@davemloft.net> Signed-off-by: Neil Horman <nhorman@tuxdriver.com> Signed-off-by: David S. Miller <davem@davemloft.net>
2010-12-06 09:05:50 +00:00
atomic_dec(&netpoll_block_tx);
}
static inline int is_netpoll_tx_blocked(struct net_device *dev)
{
if (unlikely(netpoll_tx_running(dev)))
net: Convert netpoll blocking api in bonding driver to be a counter A while back I made some changes to enable netpoll in the bonding driver. Among them was a per-cpu flag that indicated we were in a path that held locks which could cause the netpoll path to block in during tx, and as such the tx path should queue the frame for later use. This appears to have given rise to a regression. If one of those paths on which we hold the per-cpu flag yields the cpu, its possible for us to come back on a different cpu, leading to us clearing a different flag than we set. This results in odd netpoll drops, and BUG backtraces appearing in the log, as we check to make sure that we only clear set bits, and only set clear bits. I had though briefly about changing the offending paths so that they wouldn't sleep, but looking at my origional work more closely, it doesn't appear that a per-cpu flag is warranted. We alrady gate the checking of this flag on IFF_IN_NETPOLL, so we don't hit this in the normal tx case anyway. And practically speaking, the normal use case for netpoll is to only have one client anyway, so we're not going to erroneously queue netpoll frames when its actually safe to do so. As such, lets just convert that per-cpu flag to an atomic counter. It fixes the rescheduling bugs, is equivalent from a performance perspective and actually eliminates some code in the process. Tested by the reporter and myself, successfully Reported-by: Liang Zheng <lzheng@redhat.com> CC: Jay Vosburgh <fubar@us.ibm.com> CC: Andy Gospodarek <andy@greyhouse.net> CC: David S. Miller <davem@davemloft.net> Signed-off-by: Neil Horman <nhorman@tuxdriver.com> Signed-off-by: David S. Miller <davem@davemloft.net>
2010-12-06 09:05:50 +00:00
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 use_carrier;
int fail_over_mac;
int updelay;
int downdelay;
int lacp_fast;
int ad_select;
char primary[IFNAMSIZ];
int primary_reselect;
__be32 arp_targets[BOND_MAX_ARP_TARGETS];
bonding: allow user-controlled output slave selection v2: changed bonding module version, modified to apply on top of changes from previous patch in series, and updated documentation to elaborate on multiqueue awareness that now exists in bonding driver. This patch give the user the ability to control the output slave for round-robin and active-backup bonding. Similar functionality was discussed in the past, but Jay Vosburgh indicated he would rather see a feature like this added to existing modes rather than creating a completely new mode. Jay's thoughts as well as Neil's input surrounding some of the issues with the first implementation pushed us toward a design that relied on the queue_mapping rather than skb marks. Round-robin and active-backup modes were chosen as the first users of this slave selection as they seemed like the most logical choices when considering a multi-switch environment. Round-robin mode works without any modification, but active-backup does require inclusion of the first patch in this series and setting the 'all_slaves_active' flag. This will allow reception of unicast traffic on any of the backup interfaces. This was tested with IPv4-based filters as well as VLAN-based filters with good results. More information as well as a configuration example is available in the patch to Documentation/networking/bonding.txt. Signed-off-by: Andy Gospodarek <andy@greyhouse.net> Signed-off-by: Neil Horman <nhorman@tuxdriver.com> Signed-off-by: David S. Miller <davem@davemloft.net>
2010-06-02 08:40:18 +00:00
int tx_queues;
int all_slaves_active;
int resend_igmp;
};
struct bond_parm_tbl {
char *modename;
int mode;
};
#define BOND_MAX_MODENAME_LEN 20
struct vlan_entry {
struct list_head vlan_list;
__be32 vlan_ip;
unsigned short vlan_id;
};
struct slave {
struct net_device *dev; /* first - useful for panic debug */
struct slave *next;
struct slave *prev;
struct bonding *bond; /* our master */
int delay;
unsigned long jiffies;
unsigned long last_arp_rx;
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 */
u8 duplex;
u32 original_mtu;
u32 link_failure_count;
u32 speed;
bonding: allow user-controlled output slave selection v2: changed bonding module version, modified to apply on top of changes from previous patch in series, and updated documentation to elaborate on multiqueue awareness that now exists in bonding driver. This patch give the user the ability to control the output slave for round-robin and active-backup bonding. Similar functionality was discussed in the past, but Jay Vosburgh indicated he would rather see a feature like this added to existing modes rather than creating a completely new mode. Jay's thoughts as well as Neil's input surrounding some of the issues with the first implementation pushed us toward a design that relied on the queue_mapping rather than skb marks. Round-robin and active-backup modes were chosen as the first users of this slave selection as they seemed like the most logical choices when considering a multi-switch environment. Round-robin mode works without any modification, but active-backup does require inclusion of the first patch in this series and setting the 'all_slaves_active' flag. This will allow reception of unicast traffic on any of the backup interfaces. This was tested with IPv4-based filters as well as VLAN-based filters with good results. More information as well as a configuration example is available in the patch to Documentation/networking/bonding.txt. Signed-off-by: Andy Gospodarek <andy@greyhouse.net> Signed-off-by: Neil Horman <nhorman@tuxdriver.com> Signed-off-by: David S. Miller <davem@davemloft.net>
2010-06-02 08:40:18 +00:00
u16 queue_id;
u8 perm_hwaddr[ETH_ALEN];
struct ad_slave_info ad_info; /* HUGE - better to dynamically alloc */
struct tlb_slave_info tlb_info;
#ifdef CONFIG_NET_POLL_CONTROLLER
struct netpoll *np;
#endif
};
/*
* Link pseudo-state only used internally by monitors
*/
#define BOND_LINK_NOCHANGE -1
/*
* Here are the locking policies for the two bonding locks:
*
* 1) Get bond->lock when reading/writing slave list.
* 2) Get bond->curr_slave_lock when reading/writing bond->curr_active_slave.
* (It is unnecessary when the write-lock is put with bond->lock.)
* 3) When we lock with bond->curr_slave_lock, we must lock with bond->lock
* beforehand.
*/
struct bonding {
struct net_device *dev; /* first - useful for panic debug */
struct slave *first_slave;
struct slave *curr_active_slave;
struct slave *current_arp_slave;
struct slave *primary_slave;
bool force_primary;
s32 slave_cnt; /* never change this value outside the attach/detach wrappers */
void (*recv_probe)(struct sk_buff *, struct bonding *,
struct slave *);
rwlock_t lock;
rwlock_t curr_slave_lock;
s8 kill_timers;
u8 send_peer_notif;
s8 setup_by_slave;
s8 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;
struct netdev_hw_addr_list mc_list;
int (*xmit_hash_policy)(struct sk_buff *, int);
__be32 master_ip;
u16 flags;
u16 rr_tx_counter;
struct ad_bond_info ad_info;
struct alb_bond_info alb_info;
struct bond_params params;
struct list_head vlan_list;
struct vlan_group *vlgrp;
struct packet_type arp_mon_pt;
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;
#ifdef CONFIG_DEBUG_FS
/* debugging suport via debugfs */
struct dentry *debug_dir;
#endif /* CONFIG_DEBUG_FS */
};
#define bond_slave_get_rcu(dev) \
((struct slave *) rcu_dereference(dev->rx_handler_data))
/**
* 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)
{
struct slave *slave = NULL;
int i;
bond_for_each_slave(bond, slave, i) {
if (slave->dev == slave_dev) {
return slave;
}
}
return NULL;
}
static inline struct bonding *bond_get_bond_by_slave(struct slave *slave)
{
if (!slave || !slave->dev->master) {
return NULL;
}
return netdev_priv(slave->dev->master);
}
static inline bool bond_is_lb(const struct bonding *bond)
{
return (bond->params.mode == BOND_MODE_TLB ||
bond->params.mode == BOND_MODE_ALB);
}
static inline void bond_set_active_slave(struct slave *slave)
{
slave->backup = 0;
}
static inline void bond_set_backup_slave(struct slave *slave)
{
slave->backup = 1;
}
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);
}
#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_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)
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 unsigned long slave_last_rx(struct bonding *bond,
struct slave *slave)
{
if (slave_do_arp_validate(bond, slave))
return slave->last_arp_rx;
return slave->dev->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)
{
struct bonding *bond = netdev_priv(slave->dev->master);
if (!bond_is_lb(bond))
bond_set_backup_slave(slave);
if (!bond->params.all_slaves_active)
slave->inactive = 1;
}
static inline void bond_set_slave_active_flags(struct slave *slave)
{
bond_set_active_slave(slave);
slave->inactive = 0;
}
static inline bool bond_is_slave_inactive(struct slave *slave)
{
return slave->inactive;
}
struct vlan_entry *bond_next_vlan(struct bonding *bond, struct vlan_entry *curr);
int 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(void);
void bond_destroy_sysfs(void);
void bond_prepare_sysfs_group(struct bonding *bond);
int bond_create_slave_symlinks(struct net_device *master, struct net_device *slave);
void bond_destroy_slave_symlinks(struct net_device *master, struct net_device *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);
void bond_mii_monitor(struct work_struct *);
void bond_loadbalance_arp_mon(struct work_struct *);
void bond_activebackup_arp_mon(struct work_struct *);
void bond_set_mode_ops(struct bonding *bond, int mode);
int bond_parse_parm(const char *mode_arg, const struct bond_parm_tbl *tbl);
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);
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
};
#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
/* 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 bond_mode_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 fail_over_mac_tbl[];
extern const struct bond_parm_tbl pri_reselect_tbl[];
extern struct bond_parm_tbl ad_select_tbl[];
#endif /* _LINUX_BONDING_H */