diff options
author | David S. Miller <davem@davemloft.net> | 2014-11-10 13:27:49 -0500 |
---|---|---|
committer | David S. Miller <davem@davemloft.net> | 2014-11-10 13:27:49 -0500 |
commit | 1ef8019be8799c39f316a772ffdd705c46029752 (patch) | |
tree | 1f235f10cd035d076f240c9a84f3c93f22c489e6 /include | |
parent | 4483589f7123a73955095d8bb1e31390a48c7568 (diff) |
net: Move bonding headers under include/net
This ways drivers like cxgb4 don't need to do ugly relative includes.
Reported-by: Joe Perches <joe@perches.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
Diffstat (limited to 'include')
-rw-r--r-- | include/net/bond_3ad.h | 283 | ||||
-rw-r--r-- | include/net/bond_alb.h | 181 | ||||
-rw-r--r-- | include/net/bond_options.h | 130 | ||||
-rw-r--r-- | include/net/bonding.h | 654 |
4 files changed, 1248 insertions, 0 deletions
diff --git a/include/net/bond_3ad.h b/include/net/bond_3ad.h new file mode 100644 index 000000000000..e01d903633ef --- /dev/null +++ b/include/net/bond_3ad.h @@ -0,0 +1,283 @@ +/* + * Copyright(c) 1999 - 2004 Intel Corporation. All rights reserved. + * + * 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. + * + */ + +#ifndef _NET_BOND_3AD_H +#define _NET_BOND_3AD_H + +#include <asm/byteorder.h> +#include <linux/skbuff.h> +#include <linux/netdevice.h> +#include <linux/if_ether.h> + +/* General definitions */ +#define PKT_TYPE_LACPDU cpu_to_be16(ETH_P_SLOW) +#define AD_TIMER_INTERVAL 100 /*msec*/ + +#define MULTICAST_LACPDU_ADDR {0x01, 0x80, 0xC2, 0x00, 0x00, 0x02} + +#define AD_LACP_SLOW 0 +#define AD_LACP_FAST 1 + +typedef struct mac_addr { + u8 mac_addr_value[ETH_ALEN]; +} __packed mac_addr_t; + +enum { + BOND_AD_STABLE = 0, + BOND_AD_BANDWIDTH = 1, + BOND_AD_COUNT = 2, +}; + +/* rx machine states(43.4.11 in the 802.3ad standard) */ +typedef enum { + AD_RX_DUMMY, + AD_RX_INITIALIZE, /* rx Machine */ + AD_RX_PORT_DISABLED, /* rx Machine */ + AD_RX_LACP_DISABLED, /* rx Machine */ + AD_RX_EXPIRED, /* rx Machine */ + AD_RX_DEFAULTED, /* rx Machine */ + AD_RX_CURRENT /* rx Machine */ +} rx_states_t; + +/* periodic machine states(43.4.12 in the 802.3ad standard) */ +typedef enum { + AD_PERIODIC_DUMMY, + AD_NO_PERIODIC, /* periodic machine */ + AD_FAST_PERIODIC, /* periodic machine */ + AD_SLOW_PERIODIC, /* periodic machine */ + AD_PERIODIC_TX /* periodic machine */ +} periodic_states_t; + +/* mux machine states(43.4.13 in the 802.3ad standard) */ +typedef enum { + AD_MUX_DUMMY, + AD_MUX_DETACHED, /* mux machine */ + AD_MUX_WAITING, /* mux machine */ + AD_MUX_ATTACHED, /* mux machine */ + AD_MUX_COLLECTING_DISTRIBUTING /* mux machine */ +} mux_states_t; + +/* tx machine states(43.4.15 in the 802.3ad standard) */ +typedef enum { + AD_TX_DUMMY, + AD_TRANSMIT /* tx Machine */ +} tx_states_t; + +/* rx indication types */ +typedef enum { + AD_TYPE_LACPDU = 1, /* type lacpdu */ + AD_TYPE_MARKER /* type marker */ +} pdu_type_t; + +/* rx marker indication types */ +typedef enum { + AD_MARKER_INFORMATION_SUBTYPE = 1, /* marker imformation subtype */ + AD_MARKER_RESPONSE_SUBTYPE /* marker response subtype */ +} bond_marker_subtype_t; + +/* timers types(43.4.9 in the 802.3ad standard) */ +typedef enum { + AD_CURRENT_WHILE_TIMER, + AD_ACTOR_CHURN_TIMER, + AD_PERIODIC_TIMER, + AD_PARTNER_CHURN_TIMER, + AD_WAIT_WHILE_TIMER +} ad_timers_t; + +#pragma pack(1) + +/* Link Aggregation Control Protocol(LACP) data unit structure(43.4.2.2 in the 802.3ad standard) */ +typedef struct lacpdu { + u8 subtype; /* = LACP(= 0x01) */ + u8 version_number; + u8 tlv_type_actor_info; /* = actor information(type/length/value) */ + u8 actor_information_length; /* = 20 */ + __be16 actor_system_priority; + struct mac_addr actor_system; + __be16 actor_key; + __be16 actor_port_priority; + __be16 actor_port; + u8 actor_state; + u8 reserved_3_1[3]; /* = 0 */ + u8 tlv_type_partner_info; /* = partner information */ + u8 partner_information_length; /* = 20 */ + __be16 partner_system_priority; + struct mac_addr partner_system; + __be16 partner_key; + __be16 partner_port_priority; + __be16 partner_port; + u8 partner_state; + u8 reserved_3_2[3]; /* = 0 */ + u8 tlv_type_collector_info; /* = collector information */ + u8 collector_information_length;/* = 16 */ + __be16 collector_max_delay; + u8 reserved_12[12]; + u8 tlv_type_terminator; /* = terminator */ + u8 terminator_length; /* = 0 */ + u8 reserved_50[50]; /* = 0 */ +} __packed lacpdu_t; + +typedef struct lacpdu_header { + struct ethhdr hdr; + struct lacpdu lacpdu; +} __packed lacpdu_header_t; + +/* Marker Protocol Data Unit(PDU) structure(43.5.3.2 in the 802.3ad standard) */ +typedef struct bond_marker { + u8 subtype; /* = 0x02 (marker PDU) */ + u8 version_number; /* = 0x01 */ + u8 tlv_type; /* = 0x01 (marker information) */ + /* = 0x02 (marker response information) */ + u8 marker_length; /* = 0x16 */ + u16 requester_port; /* The number assigned to the port by the requester */ + struct mac_addr requester_system; /* The requester's system id */ + u32 requester_transaction_id; /* The transaction id allocated by the requester, */ + u16 pad; /* = 0 */ + u8 tlv_type_terminator; /* = 0x00 */ + u8 terminator_length; /* = 0x00 */ + u8 reserved_90[90]; /* = 0 */ +} __packed bond_marker_t; + +typedef struct bond_marker_header { + struct ethhdr hdr; + struct bond_marker marker; +} __packed bond_marker_header_t; + +#pragma pack() + +struct slave; +struct bonding; +struct ad_info; +struct port; + +#ifdef __ia64__ +#pragma pack(8) +#endif + +/* aggregator structure(43.4.5 in the 802.3ad standard) */ +typedef struct aggregator { + struct mac_addr aggregator_mac_address; + u16 aggregator_identifier; + bool is_individual; + u16 actor_admin_aggregator_key; + u16 actor_oper_aggregator_key; + struct mac_addr partner_system; + u16 partner_system_priority; + u16 partner_oper_aggregator_key; + u16 receive_state; /* BOOLEAN */ + u16 transmit_state; /* BOOLEAN */ + struct port *lag_ports; + /* ****** PRIVATE PARAMETERS ****** */ + struct slave *slave; /* pointer to the bond slave that this aggregator belongs to */ + u16 is_active; /* BOOLEAN. Indicates if this aggregator is active */ + u16 num_of_ports; +} aggregator_t; + +struct port_params { + struct mac_addr system; + u16 system_priority; + u16 key; + u16 port_number; + u16 port_priority; + u16 port_state; +}; + +/* port structure(43.4.6 in the 802.3ad standard) */ +typedef struct port { + u16 actor_port_number; + u16 actor_port_priority; + struct mac_addr actor_system; /* This parameter is added here although it is not specified in the standard, just for simplification */ + u16 actor_system_priority; /* This parameter is added here although it is not specified in the standard, just for simplification */ + u16 actor_port_aggregator_identifier; + bool ntt; + u16 actor_admin_port_key; + u16 actor_oper_port_key; + u8 actor_admin_port_state; + u8 actor_oper_port_state; + + struct port_params partner_admin; + struct port_params partner_oper; + + bool is_enabled; + + /* ****** PRIVATE PARAMETERS ****** */ + u16 sm_vars; /* all state machines variables for this port */ + rx_states_t sm_rx_state; /* state machine rx state */ + u16 sm_rx_timer_counter; /* state machine rx timer counter */ + periodic_states_t sm_periodic_state; /* state machine periodic state */ + u16 sm_periodic_timer_counter; /* state machine periodic timer counter */ + mux_states_t sm_mux_state; /* state machine mux state */ + u16 sm_mux_timer_counter; /* state machine mux timer counter */ + tx_states_t sm_tx_state; /* state machine tx state */ + u16 sm_tx_timer_counter; /* state machine tx timer counter(allways on - enter to transmit state 3 time per second) */ + struct slave *slave; /* pointer to the bond slave that this port belongs to */ + struct aggregator *aggregator; /* pointer to an aggregator that this port related to */ + struct port *next_port_in_aggregator; /* Next port on the linked list of the parent aggregator */ + u32 transaction_id; /* continuous number for identification of Marker PDU's; */ + struct lacpdu lacpdu; /* the lacpdu that will be sent for this port */ +} port_t; + +/* system structure */ +struct ad_system { + u16 sys_priority; + struct mac_addr sys_mac_addr; +}; + +#ifdef __ia64__ +#pragma pack() +#endif + +/* ========== AD Exported structures to the main bonding code ========== */ +#define BOND_AD_INFO(bond) ((bond)->ad_info) +#define SLAVE_AD_INFO(slave) ((slave)->ad_info) + +struct ad_bond_info { + struct ad_system system; /* 802.3ad system structure */ + u32 agg_select_timer; /* Timer to select aggregator after all adapter's hand shakes */ + u16 aggregator_identifier; +}; + +struct ad_slave_info { + struct aggregator aggregator; /* 802.3ad aggregator structure */ + struct port port; /* 802.3ad port structure */ + u16 id; +}; + +/* ========== AD Exported functions to the main bonding code ========== */ +void bond_3ad_initialize(struct bonding *bond, u16 tick_resolution); +void bond_3ad_bind_slave(struct slave *slave); +void bond_3ad_unbind_slave(struct slave *slave); +void bond_3ad_state_machine_handler(struct work_struct *); +void bond_3ad_initiate_agg_selection(struct bonding *bond, int timeout); +void bond_3ad_adapter_speed_changed(struct slave *slave); +void bond_3ad_adapter_duplex_changed(struct slave *slave); +void bond_3ad_handle_link_change(struct slave *slave, char link); +int bond_3ad_get_active_agg_info(struct bonding *bond, struct ad_info *ad_info); +int __bond_3ad_get_active_agg_info(struct bonding *bond, + struct ad_info *ad_info); +int bond_3ad_xmit_xor(struct sk_buff *skb, struct net_device *dev); +int bond_3ad_lacpdu_recv(const struct sk_buff *skb, struct bonding *bond, + struct slave *slave); +int bond_3ad_set_carrier(struct bonding *bond); +void bond_3ad_update_lacp_rate(struct bonding *bond); +#endif /* _NET_BOND_3AD_H */ + diff --git a/include/net/bond_alb.h b/include/net/bond_alb.h new file mode 100644 index 000000000000..313a8d3b3069 --- /dev/null +++ b/include/net/bond_alb.h @@ -0,0 +1,181 @@ +/* + * Copyright(c) 1999 - 2004 Intel Corporation. All rights reserved. + * + * 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, see <http://www.gnu.org/licenses/>. + * + * The full GNU General Public License is included in this distribution in the + * file called LICENSE. + * + */ + +#ifndef _NET_BOND_ALB_H +#define _NET_BOND_ALB_H + +#include <linux/if_ether.h> + +struct bonding; +struct slave; + +#define BOND_ALB_INFO(bond) ((bond)->alb_info) +#define SLAVE_TLB_INFO(slave) ((slave)->tlb_info) + +#define ALB_TIMER_TICKS_PER_SEC 10 /* should be a divisor of HZ */ +#define BOND_TLB_REBALANCE_INTERVAL 10 /* In seconds, periodic re-balancing. + * Used for division - never set + * to zero !!! + */ +#define BOND_ALB_DEFAULT_LP_INTERVAL 1 +#define BOND_ALB_LP_INTERVAL(bond) (bond->params.lp_interval) /* In seconds, periodic send of + * learning packets to the switch + */ + +#define BOND_TLB_REBALANCE_TICKS (BOND_TLB_REBALANCE_INTERVAL \ + * ALB_TIMER_TICKS_PER_SEC) + +#define BOND_ALB_LP_TICKS(bond) (BOND_ALB_LP_INTERVAL(bond) \ + * ALB_TIMER_TICKS_PER_SEC) + +#define TLB_HASH_TABLE_SIZE 256 /* The size of the clients hash table. + * Note that this value MUST NOT be smaller + * because the key hash table is BYTE wide ! + */ + + +#define TLB_NULL_INDEX 0xffffffff + +/* rlb defs */ +#define RLB_HASH_TABLE_SIZE 256 +#define RLB_NULL_INDEX 0xffffffff +#define RLB_UPDATE_DELAY (2*ALB_TIMER_TICKS_PER_SEC) /* 2 seconds */ +#define RLB_ARP_BURST_SIZE 2 +#define RLB_UPDATE_RETRY 3 /* 3-ticks - must be smaller than the rlb + * rebalance interval (5 min). + */ +/* RLB_PROMISC_TIMEOUT = 10 sec equals the time that the current slave is + * promiscuous after failover + */ +#define RLB_PROMISC_TIMEOUT (10*ALB_TIMER_TICKS_PER_SEC) + + +struct tlb_client_info { + struct slave *tx_slave; /* A pointer to slave used for transmiting + * packets to a Client that the Hash function + * gave this entry index. + */ + u32 tx_bytes; /* Each Client accumulates the BytesTx that + * were transmitted to it, and after each + * CallBack the LoadHistory is divided + * by the balance interval + */ + u32 load_history; /* This field contains the amount of Bytes + * that were transmitted to this client by + * the server on the previous balance + * interval in Bps. + */ + u32 next; /* The next Hash table entry index, assigned + * to use the same adapter for transmit. + */ + u32 prev; /* The previous Hash table entry index, + * assigned to use the same + */ +}; + +/* ------------------------------------------------------------------------- + * struct rlb_client_info contains all info related to a specific rx client + * connection. This is the Clients Hash Table entry struct. + * Note that this is not a proper hash table; if a new client's IP address + * hash collides with an existing client entry, the old entry is replaced. + * + * There is a linked list (linked by the used_next and used_prev members) + * linking all the used entries of the hash table. This allows updating + * all the clients without walking over all the unused elements of the table. + * + * There are also linked lists of entries with identical hash(ip_src). These + * allow cleaning up the table from ip_src<->mac_src associations that have + * become outdated and would cause sending out invalid ARP updates to the + * network. These are linked by the (src_next and src_prev members). + * ------------------------------------------------------------------------- + */ +struct rlb_client_info { + __be32 ip_src; /* the server IP address */ + __be32 ip_dst; /* the client IP address */ + u8 mac_src[ETH_ALEN]; /* the server MAC address */ + u8 mac_dst[ETH_ALEN]; /* the client MAC address */ + + /* list of used hash table entries, starting at rx_hashtbl_used_head */ + u32 used_next; + u32 used_prev; + + /* ip_src based hashing */ + u32 src_next; /* next entry with same hash(ip_src) */ + u32 src_prev; /* prev entry with same hash(ip_src) */ + u32 src_first; /* first entry with hash(ip_src) == this entry's index */ + + u8 assigned; /* checking whether this entry is assigned */ + u8 ntt; /* flag - need to transmit client info */ + struct slave *slave; /* the slave assigned to this client */ + unsigned short vlan_id; /* VLAN tag associated with IP address */ +}; + +struct tlb_slave_info { + u32 head; /* Index to the head of the bi-directional clients + * hash table entries list. The entries in the list + * are the entries that were assigned to use this + * slave for transmit. + */ + u32 load; /* Each slave sums the loadHistory of all clients + * assigned to it + */ +}; + +struct alb_bond_info { + struct tlb_client_info *tx_hashtbl; /* Dynamically allocated */ + u32 unbalanced_load; + int tx_rebalance_counter; + int lp_counter; + /* -------- rlb parameters -------- */ + int rlb_enabled; + struct rlb_client_info *rx_hashtbl; /* Receive hash table */ + u32 rx_hashtbl_used_head; + u8 rx_ntt; /* flag - need to transmit + * to all rx clients + */ + struct slave *rx_slave;/* last slave to xmit from */ + u8 primary_is_promisc; /* boolean */ + u32 rlb_promisc_timeout_counter;/* counts primary + * promiscuity time + */ + u32 rlb_update_delay_counter; + u32 rlb_update_retry_counter;/* counter of retries + * of client update + */ + u8 rlb_rebalance; /* flag - indicates that the + * rx traffic should be + * rebalanced + */ +}; + +int bond_alb_initialize(struct bonding *bond, int rlb_enabled); +void bond_alb_deinitialize(struct bonding *bond); +int bond_alb_init_slave(struct bonding *bond, struct slave *slave); +void bond_alb_deinit_slave(struct bonding *bond, struct slave *slave); +void bond_alb_handle_link_change(struct bonding *bond, struct slave *slave, char link); +void bond_alb_handle_active_change(struct bonding *bond, struct slave *new_slave); +int bond_alb_xmit(struct sk_buff *skb, struct net_device *bond_dev); +int bond_tlb_xmit(struct sk_buff *skb, struct net_device *bond_dev); +void bond_alb_monitor(struct work_struct *); +int bond_alb_set_mac_address(struct net_device *bond_dev, void *addr); +void bond_alb_clear_vlan(struct bonding *bond, unsigned short vlan_id); +#endif /* _NET_BOND_ALB_H */ + diff --git a/include/net/bond_options.h b/include/net/bond_options.h new file mode 100644 index 000000000000..ea6546d2c946 --- /dev/null +++ b/include/net/bond_options.h @@ -0,0 +1,130 @@ +/* + * drivers/net/bond/bond_options.h - bonding options + * Copyright (c) 2013 Nikolay Aleksandrov <nikolay@redhat.com> + * + * 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. + */ + +#ifndef _NET_BOND_OPTIONS_H +#define _NET_BOND_OPTIONS_H + +#define BOND_OPT_MAX_NAMELEN 32 +#define BOND_OPT_VALID(opt) ((opt) < BOND_OPT_LAST) +#define BOND_MODE_ALL_EX(x) (~(x)) + +/* Option flags: + * BOND_OPTFLAG_NOSLAVES - check if the bond device is empty before setting + * BOND_OPTFLAG_IFDOWN - check if the bond device is down before setting + * BOND_OPTFLAG_RAWVAL - the option parses the value itself + */ +enum { + BOND_OPTFLAG_NOSLAVES = BIT(0), + BOND_OPTFLAG_IFDOWN = BIT(1), + BOND_OPTFLAG_RAWVAL = BIT(2) +}; + +/* Value type flags: + * BOND_VALFLAG_DEFAULT - mark the value as default + * BOND_VALFLAG_(MIN|MAX) - mark the value as min/max + */ +enum { + BOND_VALFLAG_DEFAULT = BIT(0), + BOND_VALFLAG_MIN = BIT(1), + BOND_VALFLAG_MAX = BIT(2) +}; + +/* Option IDs, their bit positions correspond to their IDs */ +enum { + BOND_OPT_MODE, + BOND_OPT_PACKETS_PER_SLAVE, + BOND_OPT_XMIT_HASH, + BOND_OPT_ARP_VALIDATE, + BOND_OPT_ARP_ALL_TARGETS, + BOND_OPT_FAIL_OVER_MAC, + BOND_OPT_ARP_INTERVAL, + BOND_OPT_ARP_TARGETS, + BOND_OPT_DOWNDELAY, + BOND_OPT_UPDELAY, + BOND_OPT_LACP_RATE, + BOND_OPT_MINLINKS, + BOND_OPT_AD_SELECT, + BOND_OPT_NUM_PEER_NOTIF, + BOND_OPT_MIIMON, + BOND_OPT_PRIMARY, + BOND_OPT_PRIMARY_RESELECT, + BOND_OPT_USE_CARRIER, + BOND_OPT_ACTIVE_SLAVE, + BOND_OPT_QUEUE_ID, + BOND_OPT_ALL_SLAVES_ACTIVE, + BOND_OPT_RESEND_IGMP, + BOND_OPT_LP_INTERVAL, + BOND_OPT_SLAVES, + BOND_OPT_TLB_DYNAMIC_LB, + BOND_OPT_LAST +}; + +/* This structure is used for storing option values and for passing option + * values when changing an option. The logic when used as an arg is as follows: + * - if string != NULL -> parse it, if the opt is RAW type then return it, else + * return the parse result + * - if string == NULL -> parse value + */ +struct bond_opt_value { + char *string; + u64 value; + u32 flags; +}; + +struct bonding; + +struct bond_option { + int id; + const char *name; + const char *desc; + u32 flags; + + /* unsuppmodes is used to denote modes in which the option isn't + * supported. + */ + unsigned long unsuppmodes; + /* supported values which this option can have, can be a subset of + * BOND_OPTVAL_RANGE's value range + */ + const struct bond_opt_value *values; + + int (*set)(struct bonding *bond, const struct bond_opt_value *val); +}; + +int __bond_opt_set(struct bonding *bond, unsigned int option, + struct bond_opt_value *val); +int bond_opt_tryset_rtnl(struct bonding *bond, unsigned int option, char *buf); + +const struct bond_opt_value *bond_opt_parse(const struct bond_option *opt, + struct bond_opt_value *val); +const struct bond_option *bond_opt_get(unsigned int option); +const struct bond_option *bond_opt_get_by_name(const char *name); +const struct bond_opt_value *bond_opt_get_val(unsigned int option, u64 val); + +/* This helper is used to initialize a bond_opt_value structure for parameter + * passing. There should be either a valid string or value, but not both. + * When value is ULLONG_MAX then string will be used. + */ +static inline void __bond_opt_init(struct bond_opt_value *optval, + char *string, u64 value) +{ + memset(optval, 0, sizeof(*optval)); + optval->value = ULLONG_MAX; + if (value == ULLONG_MAX) + optval->string = string; + else + optval->value = value; +} +#define bond_opt_initval(optval, value) __bond_opt_init(optval, NULL, value) +#define bond_opt_initstr(optval, str) __bond_opt_init(optval, str, ULLONG_MAX) + +void bond_option_arp_ip_targets_clear(struct bonding *bond); + +#endif /* _NET_BOND_OPTIONS_H */ diff --git a/include/net/bonding.h b/include/net/bonding.h new file mode 100644 index 000000000000..983a94b86b95 --- /dev/null +++ b/include/net/bonding.h @@ -0,0 +1,654 @@ +/* + * 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 <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 <linux/inetdevice.h> +#include <linux/etherdevice.h> +#include <linux/reciprocal_div.h> +#include <linux/if_link.h> + +#include <net/bond_3ad.h> +#include <net/bond_alb.h> +#include <net/bond_options.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 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 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)) + +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; + 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; + 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); + 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 __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); +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 */ |