diff options
Diffstat (limited to 'ANDROID_3.4.5/drivers/net/bonding')
| -rw-r--r-- | ANDROID_3.4.5/drivers/net/bonding/Makefile | 11 | ||||
| -rw-r--r-- | ANDROID_3.4.5/drivers/net/bonding/bond_3ad.c | 2508 | ||||
| -rw-r--r-- | ANDROID_3.4.5/drivers/net/bonding/bond_3ad.h | 282 | ||||
| -rw-r--r-- | ANDROID_3.4.5/drivers/net/bonding/bond_alb.c | 1722 | ||||
| -rw-r--r-- | ANDROID_3.4.5/drivers/net/bonding/bond_alb.h | 167 | ||||
| -rw-r--r-- | ANDROID_3.4.5/drivers/net/bonding/bond_debugfs.c | 146 | ||||
| -rw-r--r-- | ANDROID_3.4.5/drivers/net/bonding/bond_main.c | 4969 | ||||
| -rw-r--r-- | ANDROID_3.4.5/drivers/net/bonding/bond_procfs.c | 283 | ||||
| -rw-r--r-- | ANDROID_3.4.5/drivers/net/bonding/bond_sysfs.c | 1727 | ||||
| -rw-r--r-- | ANDROID_3.4.5/drivers/net/bonding/bonding.h | 464 |
10 files changed, 12279 insertions, 0 deletions
diff --git a/ANDROID_3.4.5/drivers/net/bonding/Makefile b/ANDROID_3.4.5/drivers/net/bonding/Makefile new file mode 100644 index 00000000..4c21bf6b --- /dev/null +++ b/ANDROID_3.4.5/drivers/net/bonding/Makefile @@ -0,0 +1,11 @@ +# +# Makefile for the Ethernet Bonding driver +# + +obj-$(CONFIG_BONDING) += bonding.o + +bonding-objs := bond_main.o bond_3ad.o bond_alb.o bond_sysfs.o bond_debugfs.o + +proc-$(CONFIG_PROC_FS) += bond_procfs.o +bonding-objs += $(proc-y) + diff --git a/ANDROID_3.4.5/drivers/net/bonding/bond_3ad.c b/ANDROID_3.4.5/drivers/net/bonding/bond_3ad.c new file mode 100644 index 00000000..3463b469 --- /dev/null +++ b/ANDROID_3.4.5/drivers/net/bonding/bond_3ad.c @@ -0,0 +1,2508 @@ +/* + * 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. + * + */ + +#define pr_fmt(fmt) KBUILD_MODNAME ": " fmt + +#include <linux/skbuff.h> +#include <linux/if_ether.h> +#include <linux/netdevice.h> +#include <linux/spinlock.h> +#include <linux/ethtool.h> +#include <linux/etherdevice.h> +#include <linux/if_bonding.h> +#include <linux/pkt_sched.h> +#include <net/net_namespace.h> +#include "bonding.h" +#include "bond_3ad.h" + +// General definitions +#define AD_SHORT_TIMEOUT 1 +#define AD_LONG_TIMEOUT 0 +#define AD_STANDBY 0x2 +#define AD_MAX_TX_IN_SECOND 3 +#define AD_COLLECTOR_MAX_DELAY 0 + +// Timer definitions(43.4.4 in the 802.3ad standard) +#define AD_FAST_PERIODIC_TIME 1 +#define AD_SLOW_PERIODIC_TIME 30 +#define AD_SHORT_TIMEOUT_TIME (3*AD_FAST_PERIODIC_TIME) +#define AD_LONG_TIMEOUT_TIME (3*AD_SLOW_PERIODIC_TIME) +#define AD_CHURN_DETECTION_TIME 60 +#define AD_AGGREGATE_WAIT_TIME 2 + +// Port state definitions(43.4.2.2 in the 802.3ad standard) +#define AD_STATE_LACP_ACTIVITY 0x1 +#define AD_STATE_LACP_TIMEOUT 0x2 +#define AD_STATE_AGGREGATION 0x4 +#define AD_STATE_SYNCHRONIZATION 0x8 +#define AD_STATE_COLLECTING 0x10 +#define AD_STATE_DISTRIBUTING 0x20 +#define AD_STATE_DEFAULTED 0x40 +#define AD_STATE_EXPIRED 0x80 + +// Port Variables definitions used by the State Machines(43.4.7 in the 802.3ad standard) +#define AD_PORT_BEGIN 0x1 +#define AD_PORT_LACP_ENABLED 0x2 +#define AD_PORT_ACTOR_CHURN 0x4 +#define AD_PORT_PARTNER_CHURN 0x8 +#define AD_PORT_READY 0x10 +#define AD_PORT_READY_N 0x20 +#define AD_PORT_MATCHED 0x40 +#define AD_PORT_STANDBY 0x80 +#define AD_PORT_SELECTED 0x100 +#define AD_PORT_MOVED 0x200 + +// Port Key definitions +// key is determined according to the link speed, duplex and +// user key(which is yet not supported) +// ------------------------------------------------------------ +// Port key : | User key | Speed |Duplex| +// ------------------------------------------------------------ +// 16 6 1 0 +#define AD_DUPLEX_KEY_BITS 0x1 +#define AD_SPEED_KEY_BITS 0x3E +#define AD_USER_KEY_BITS 0xFFC0 + +//dalloun +#define AD_LINK_SPEED_BITMASK_1MBPS 0x1 +#define AD_LINK_SPEED_BITMASK_10MBPS 0x2 +#define AD_LINK_SPEED_BITMASK_100MBPS 0x4 +#define AD_LINK_SPEED_BITMASK_1000MBPS 0x8 +#define AD_LINK_SPEED_BITMASK_10000MBPS 0x10 +//endalloun + +// compare MAC addresses +#define MAC_ADDRESS_COMPARE(A, B) memcmp(A, B, ETH_ALEN) + +static struct mac_addr null_mac_addr = { { 0, 0, 0, 0, 0, 0 } }; +static u16 ad_ticks_per_sec; +static const int ad_delta_in_ticks = (AD_TIMER_INTERVAL * HZ) / 1000; + +static const u8 lacpdu_mcast_addr[ETH_ALEN] = MULTICAST_LACPDU_ADDR; + +// ================= main 802.3ad protocol functions ================== +static int ad_lacpdu_send(struct port *port); +static int ad_marker_send(struct port *port, struct bond_marker *marker); +static void ad_mux_machine(struct port *port); +static void ad_rx_machine(struct lacpdu *lacpdu, struct port *port); +static void ad_tx_machine(struct port *port); +static void ad_periodic_machine(struct port *port); +static void ad_port_selection_logic(struct port *port); +static void ad_agg_selection_logic(struct aggregator *aggregator); +static void ad_clear_agg(struct aggregator *aggregator); +static void ad_initialize_agg(struct aggregator *aggregator); +static void ad_initialize_port(struct port *port, int lacp_fast); +static void ad_enable_collecting_distributing(struct port *port); +static void ad_disable_collecting_distributing(struct port *port); +static void ad_marker_info_received(struct bond_marker *marker_info, struct port *port); +static void ad_marker_response_received(struct bond_marker *marker, struct port *port); + + +///////////////////////////////////////////////////////////////////////////////// +// ================= api to bonding and kernel code ================== +///////////////////////////////////////////////////////////////////////////////// + +/** + * __get_bond_by_port - get the port's bonding struct + * @port: the port we're looking at + * + * Return @port's bonding struct, or %NULL if it can't be found. + */ +static inline struct bonding *__get_bond_by_port(struct port *port) +{ + if (port->slave == NULL) + return NULL; + + return bond_get_bond_by_slave(port->slave); +} + +/** + * __get_first_port - get the first port in the bond + * @bond: the bond we're looking at + * + * Return the port of the first slave in @bond, or %NULL if it can't be found. + */ +static inline struct port *__get_first_port(struct bonding *bond) +{ + if (bond->slave_cnt == 0) + return NULL; + + return &(SLAVE_AD_INFO(bond->first_slave).port); +} + +/** + * __get_next_port - get the next port in the bond + * @port: the port we're looking at + * + * Return the port of the slave that is next in line of @port's slave in the + * bond, or %NULL if it can't be found. + */ +static inline struct port *__get_next_port(struct port *port) +{ + struct bonding *bond = __get_bond_by_port(port); + struct slave *slave = port->slave; + + // If there's no bond for this port, or this is the last slave + if ((bond == NULL) || (slave->next == bond->first_slave)) + return NULL; + + return &(SLAVE_AD_INFO(slave->next).port); +} + +/** + * __get_first_agg - get the first aggregator in the bond + * @bond: the bond we're looking at + * + * Return the aggregator of the first slave in @bond, or %NULL if it can't be + * found. + */ +static inline struct aggregator *__get_first_agg(struct port *port) +{ + struct bonding *bond = __get_bond_by_port(port); + + // If there's no bond for this port, or bond has no slaves + if ((bond == NULL) || (bond->slave_cnt == 0)) + return NULL; + + return &(SLAVE_AD_INFO(bond->first_slave).aggregator); +} + +/** + * __get_next_agg - get the next aggregator in the bond + * @aggregator: the aggregator we're looking at + * + * Return the aggregator of the slave that is next in line of @aggregator's + * slave in the bond, or %NULL if it can't be found. + */ +static inline struct aggregator *__get_next_agg(struct aggregator *aggregator) +{ + struct slave *slave = aggregator->slave; + struct bonding *bond = bond_get_bond_by_slave(slave); + + // If there's no bond for this aggregator, or this is the last slave + if ((bond == NULL) || (slave->next == bond->first_slave)) + return NULL; + + return &(SLAVE_AD_INFO(slave->next).aggregator); +} + +/* + * __agg_has_partner + * + * Return nonzero if aggregator has a partner (denoted by a non-zero ether + * address for the partner). Return 0 if not. + */ +static inline int __agg_has_partner(struct aggregator *agg) +{ + return !is_zero_ether_addr(agg->partner_system.mac_addr_value); +} + +/** + * __disable_port - disable the port's slave + * @port: the port we're looking at + * + */ +static inline void __disable_port(struct port *port) +{ + bond_set_slave_inactive_flags(port->slave); +} + +/** + * __enable_port - enable the port's slave, if it's up + * @port: the port we're looking at + * + */ +static inline void __enable_port(struct port *port) +{ + struct slave *slave = port->slave; + + if ((slave->link == BOND_LINK_UP) && IS_UP(slave->dev)) + bond_set_slave_active_flags(slave); +} + +/** + * __port_is_enabled - check if the port's slave is in active state + * @port: the port we're looking at + * + */ +static inline int __port_is_enabled(struct port *port) +{ + return bond_is_active_slave(port->slave); +} + +/** + * __get_agg_selection_mode - get the aggregator selection mode + * @port: the port we're looking at + * + * Get the aggregator selection mode. Can be %STABLE, %BANDWIDTH or %COUNT. + */ +static inline u32 __get_agg_selection_mode(struct port *port) +{ + struct bonding *bond = __get_bond_by_port(port); + + if (bond == NULL) + return BOND_AD_STABLE; + + return bond->params.ad_select; +} + +/** + * __check_agg_selection_timer - check if the selection timer has expired + * @port: the port we're looking at + * + */ +static inline int __check_agg_selection_timer(struct port *port) +{ + struct bonding *bond = __get_bond_by_port(port); + + if (bond == NULL) + return 0; + + return BOND_AD_INFO(bond).agg_select_timer ? 1 : 0; +} + +/** + * __get_state_machine_lock - lock the port's state machines + * @port: the port we're looking at + * + */ +static inline void __get_state_machine_lock(struct port *port) +{ + spin_lock_bh(&(SLAVE_AD_INFO(port->slave).state_machine_lock)); +} + +/** + * __release_state_machine_lock - unlock the port's state machines + * @port: the port we're looking at + * + */ +static inline void __release_state_machine_lock(struct port *port) +{ + spin_unlock_bh(&(SLAVE_AD_INFO(port->slave).state_machine_lock)); +} + +/** + * __get_link_speed - get a port's speed + * @port: the port we're looking at + * + * Return @port's speed in 802.3ad bitmask format. i.e. one of: + * 0, + * %AD_LINK_SPEED_BITMASK_10MBPS, + * %AD_LINK_SPEED_BITMASK_100MBPS, + * %AD_LINK_SPEED_BITMASK_1000MBPS, + * %AD_LINK_SPEED_BITMASK_10000MBPS + */ +static u16 __get_link_speed(struct port *port) +{ + struct slave *slave = port->slave; + u16 speed; + + /* this if covers only a special case: when the configuration starts with + * link down, it sets the speed to 0. + * This is done in spite of the fact that the e100 driver reports 0 to be + * compatible with MVT in the future.*/ + if (slave->link != BOND_LINK_UP) + speed = 0; + else { + switch (slave->speed) { + case SPEED_10: + speed = AD_LINK_SPEED_BITMASK_10MBPS; + break; + + case SPEED_100: + speed = AD_LINK_SPEED_BITMASK_100MBPS; + break; + + case SPEED_1000: + speed = AD_LINK_SPEED_BITMASK_1000MBPS; + break; + + case SPEED_10000: + speed = AD_LINK_SPEED_BITMASK_10000MBPS; + break; + + default: + speed = 0; // unknown speed value from ethtool. shouldn't happen + break; + } + } + + pr_debug("Port %d Received link speed %d update from adapter\n", + port->actor_port_number, speed); + return speed; +} + +/** + * __get_duplex - get a port's duplex + * @port: the port we're looking at + * + * Return @port's duplex in 802.3ad bitmask format. i.e.: + * 0x01 if in full duplex + * 0x00 otherwise + */ +static u8 __get_duplex(struct port *port) +{ + struct slave *slave = port->slave; + + u8 retval; + + // handling a special case: when the configuration starts with + // link down, it sets the duplex to 0. + if (slave->link != BOND_LINK_UP) + retval = 0x0; + else { + switch (slave->duplex) { + case DUPLEX_FULL: + retval = 0x1; + pr_debug("Port %d Received status full duplex update from adapter\n", + port->actor_port_number); + break; + case DUPLEX_HALF: + default: + retval = 0x0; + pr_debug("Port %d Received status NOT full duplex update from adapter\n", + port->actor_port_number); + break; + } + } + return retval; +} + +/** + * __initialize_port_locks - initialize a port's STATE machine spinlock + * @port: the port we're looking at + * + */ +static inline void __initialize_port_locks(struct port *port) +{ + // make sure it isn't called twice + spin_lock_init(&(SLAVE_AD_INFO(port->slave).state_machine_lock)); +} + +//conversions + +/** + * __ad_timer_to_ticks - convert a given timer type to AD module ticks + * @timer_type: which timer to operate + * @par: timer parameter. see below + * + * If @timer_type is %current_while_timer, @par indicates long/short timer. + * If @timer_type is %periodic_timer, @par is one of %FAST_PERIODIC_TIME, + * %SLOW_PERIODIC_TIME. + */ +static u16 __ad_timer_to_ticks(u16 timer_type, u16 par) +{ + u16 retval = 0; /* to silence the compiler */ + + switch (timer_type) { + case AD_CURRENT_WHILE_TIMER: // for rx machine usage + if (par) + retval = (AD_SHORT_TIMEOUT_TIME*ad_ticks_per_sec); // short timeout + else + retval = (AD_LONG_TIMEOUT_TIME*ad_ticks_per_sec); // long timeout + break; + case AD_ACTOR_CHURN_TIMER: // for local churn machine + retval = (AD_CHURN_DETECTION_TIME*ad_ticks_per_sec); + break; + case AD_PERIODIC_TIMER: // for periodic machine + retval = (par*ad_ticks_per_sec); // long timeout + break; + case AD_PARTNER_CHURN_TIMER: // for remote churn machine + retval = (AD_CHURN_DETECTION_TIME*ad_ticks_per_sec); + break; + case AD_WAIT_WHILE_TIMER: // for selection machine + retval = (AD_AGGREGATE_WAIT_TIME*ad_ticks_per_sec); + break; + } + return retval; +} + + +///////////////////////////////////////////////////////////////////////////////// +// ================= ad_rx_machine helper functions ================== +///////////////////////////////////////////////////////////////////////////////// + +/** + * __choose_matched - update a port's matched variable from a received lacpdu + * @lacpdu: the lacpdu we've received + * @port: the port we're looking at + * + * Update the value of the matched variable, using parameter values from a + * newly received lacpdu. Parameter values for the partner carried in the + * received PDU are compared with the corresponding operational parameter + * values for the actor. Matched is set to TRUE if all of these parameters + * match and the PDU parameter partner_state.aggregation has the same value as + * actor_oper_port_state.aggregation and lacp will actively maintain the link + * in the aggregation. Matched is also set to TRUE if the value of + * actor_state.aggregation in the received PDU is set to FALSE, i.e., indicates + * an individual link and lacp will actively maintain the link. Otherwise, + * matched is set to FALSE. LACP is considered to be actively maintaining the + * link if either the PDU's actor_state.lacp_activity variable is TRUE or both + * the actor's actor_oper_port_state.lacp_activity and the PDU's + * partner_state.lacp_activity variables are TRUE. + * + * Note: the AD_PORT_MATCHED "variable" is not specified by 802.3ad; it is + * used here to implement the language from 802.3ad 43.4.9 that requires + * recordPDU to "match" the LACPDU parameters to the stored values. + */ +static void __choose_matched(struct lacpdu *lacpdu, struct port *port) +{ + // check if all parameters are alike + if (((ntohs(lacpdu->partner_port) == port->actor_port_number) && + (ntohs(lacpdu->partner_port_priority) == port->actor_port_priority) && + !MAC_ADDRESS_COMPARE(&(lacpdu->partner_system), &(port->actor_system)) && + (ntohs(lacpdu->partner_system_priority) == port->actor_system_priority) && + (ntohs(lacpdu->partner_key) == port->actor_oper_port_key) && + ((lacpdu->partner_state & AD_STATE_AGGREGATION) == (port->actor_oper_port_state & AD_STATE_AGGREGATION))) || + // or this is individual link(aggregation == FALSE) + ((lacpdu->actor_state & AD_STATE_AGGREGATION) == 0) + ) { + // update the state machine Matched variable + port->sm_vars |= AD_PORT_MATCHED; + } else { + port->sm_vars &= ~AD_PORT_MATCHED; + } +} + +/** + * __record_pdu - record parameters from a received lacpdu + * @lacpdu: the lacpdu we've received + * @port: the port we're looking at + * + * Record the parameter values for the Actor carried in a received lacpdu as + * the current partner operational parameter values and sets + * actor_oper_port_state.defaulted to FALSE. + */ +static void __record_pdu(struct lacpdu *lacpdu, struct port *port) +{ + if (lacpdu && port) { + struct port_params *partner = &port->partner_oper; + + __choose_matched(lacpdu, port); + // record the new parameter values for the partner operational + partner->port_number = ntohs(lacpdu->actor_port); + partner->port_priority = ntohs(lacpdu->actor_port_priority); + partner->system = lacpdu->actor_system; + partner->system_priority = ntohs(lacpdu->actor_system_priority); + partner->key = ntohs(lacpdu->actor_key); + partner->port_state = lacpdu->actor_state; + + // set actor_oper_port_state.defaulted to FALSE + port->actor_oper_port_state &= ~AD_STATE_DEFAULTED; + + // set the partner sync. to on if the partner is sync. and the port is matched + if ((port->sm_vars & AD_PORT_MATCHED) + && (lacpdu->actor_state & AD_STATE_SYNCHRONIZATION)) + partner->port_state |= AD_STATE_SYNCHRONIZATION; + else + partner->port_state &= ~AD_STATE_SYNCHRONIZATION; + } +} + +/** + * __record_default - record default parameters + * @port: the port we're looking at + * + * This function records the default parameter values for the partner carried + * in the Partner Admin parameters as the current partner operational parameter + * values and sets actor_oper_port_state.defaulted to TRUE. + */ +static void __record_default(struct port *port) +{ + if (port) { + // record the partner admin parameters + memcpy(&port->partner_oper, &port->partner_admin, + sizeof(struct port_params)); + + // set actor_oper_port_state.defaulted to true + port->actor_oper_port_state |= AD_STATE_DEFAULTED; + } +} + +/** + * __update_selected - update a port's Selected variable from a received lacpdu + * @lacpdu: the lacpdu we've received + * @port: the port we're looking at + * + * Update the value of the selected variable, using parameter values from a + * newly received lacpdu. The parameter values for the Actor carried in the + * received PDU are compared with the corresponding operational parameter + * values for the ports partner. If one or more of the comparisons shows that + * the value(s) received in the PDU differ from the current operational values, + * then selected is set to FALSE and actor_oper_port_state.synchronization is + * set to out_of_sync. Otherwise, selected remains unchanged. + */ +static void __update_selected(struct lacpdu *lacpdu, struct port *port) +{ + if (lacpdu && port) { + const struct port_params *partner = &port->partner_oper; + + // check if any parameter is different + if (ntohs(lacpdu->actor_port) != partner->port_number || + ntohs(lacpdu->actor_port_priority) != partner->port_priority || + MAC_ADDRESS_COMPARE(&lacpdu->actor_system, &partner->system) || + ntohs(lacpdu->actor_system_priority) != partner->system_priority || + ntohs(lacpdu->actor_key) != partner->key || + (lacpdu->actor_state & AD_STATE_AGGREGATION) != (partner->port_state & AD_STATE_AGGREGATION)) { + // update the state machine Selected variable + port->sm_vars &= ~AD_PORT_SELECTED; + } + } +} + +/** + * __update_default_selected - update a port's Selected variable from Partner + * @port: the port we're looking at + * + * This function updates the value of the selected variable, using the partner + * administrative parameter values. The administrative values are compared with + * the corresponding operational parameter values for the partner. If one or + * more of the comparisons shows that the administrative value(s) differ from + * the current operational values, then Selected is set to FALSE and + * actor_oper_port_state.synchronization is set to OUT_OF_SYNC. Otherwise, + * Selected remains unchanged. + */ +static void __update_default_selected(struct port *port) +{ + if (port) { + const struct port_params *admin = &port->partner_admin; + const struct port_params *oper = &port->partner_oper; + + // check if any parameter is different + if (admin->port_number != oper->port_number || + admin->port_priority != oper->port_priority || + MAC_ADDRESS_COMPARE(&admin->system, &oper->system) || + admin->system_priority != oper->system_priority || + admin->key != oper->key || + (admin->port_state & AD_STATE_AGGREGATION) + != (oper->port_state & AD_STATE_AGGREGATION)) { + // update the state machine Selected variable + port->sm_vars &= ~AD_PORT_SELECTED; + } + } +} + +/** + * __update_ntt - update a port's ntt variable from a received lacpdu + * @lacpdu: the lacpdu we've received + * @port: the port we're looking at + * + * Updates the value of the ntt variable, using parameter values from a newly + * received lacpdu. The parameter values for the partner carried in the + * received PDU are compared with the corresponding operational parameter + * values for the Actor. If one or more of the comparisons shows that the + * value(s) received in the PDU differ from the current operational values, + * then ntt is set to TRUE. Otherwise, ntt remains unchanged. + */ +static void __update_ntt(struct lacpdu *lacpdu, struct port *port) +{ + // validate lacpdu and port + if (lacpdu && port) { + // check if any parameter is different + if ((ntohs(lacpdu->partner_port) != port->actor_port_number) || + (ntohs(lacpdu->partner_port_priority) != port->actor_port_priority) || + MAC_ADDRESS_COMPARE(&(lacpdu->partner_system), &(port->actor_system)) || + (ntohs(lacpdu->partner_system_priority) != port->actor_system_priority) || + (ntohs(lacpdu->partner_key) != port->actor_oper_port_key) || + ((lacpdu->partner_state & AD_STATE_LACP_ACTIVITY) != (port->actor_oper_port_state & AD_STATE_LACP_ACTIVITY)) || + ((lacpdu->partner_state & AD_STATE_LACP_TIMEOUT) != (port->actor_oper_port_state & AD_STATE_LACP_TIMEOUT)) || + ((lacpdu->partner_state & AD_STATE_SYNCHRONIZATION) != (port->actor_oper_port_state & AD_STATE_SYNCHRONIZATION)) || + ((lacpdu->partner_state & AD_STATE_AGGREGATION) != (port->actor_oper_port_state & AD_STATE_AGGREGATION)) + ) { + + port->ntt = true; + } + } +} + +/** + * __attach_bond_to_agg + * @port: the port we're looking at + * + * Handle the attaching of the port's control parser/multiplexer and the + * aggregator. This function does nothing since the parser/multiplexer of the + * receive and the parser/multiplexer of the aggregator are already combined. + */ +static void __attach_bond_to_agg(struct port *port) +{ + port = NULL; /* just to satisfy the compiler */ + // This function does nothing since the parser/multiplexer of the receive + // and the parser/multiplexer of the aggregator are already combined +} + +/** + * __detach_bond_from_agg + * @port: the port we're looking at + * + * Handle the detaching of the port's control parser/multiplexer from the + * aggregator. This function does nothing since the parser/multiplexer of the + * receive and the parser/multiplexer of the aggregator are already combined. + */ +static void __detach_bond_from_agg(struct port *port) +{ + port = NULL; /* just to satisfy the compiler */ + // This function does nothing since the parser/multiplexer of the receive + // and the parser/multiplexer of the aggregator are already combined +} + +/** + * __agg_ports_are_ready - check if all ports in an aggregator are ready + * @aggregator: the aggregator we're looking at + * + */ +static int __agg_ports_are_ready(struct aggregator *aggregator) +{ + struct port *port; + int retval = 1; + + if (aggregator) { + // scan all ports in this aggregator to verfy if they are all ready + for (port = aggregator->lag_ports; + port; + port = port->next_port_in_aggregator) { + if (!(port->sm_vars & AD_PORT_READY_N)) { + retval = 0; + break; + } + } + } + + return retval; +} + +/** + * __set_agg_ports_ready - set value of Ready bit in all ports of an aggregator + * @aggregator: the aggregator we're looking at + * @val: Should the ports' ready bit be set on or off + * + */ +static void __set_agg_ports_ready(struct aggregator *aggregator, int val) +{ + struct port *port; + + for (port = aggregator->lag_ports; port; + port = port->next_port_in_aggregator) { + if (val) + port->sm_vars |= AD_PORT_READY; + else + port->sm_vars &= ~AD_PORT_READY; + } +} + +/** + * __get_agg_bandwidth - get the total bandwidth of an aggregator + * @aggregator: the aggregator we're looking at + * + */ +static u32 __get_agg_bandwidth(struct aggregator *aggregator) +{ + u32 bandwidth = 0; + + if (aggregator->num_of_ports) { + switch (__get_link_speed(aggregator->lag_ports)) { + case AD_LINK_SPEED_BITMASK_1MBPS: + bandwidth = aggregator->num_of_ports; + break; + case AD_LINK_SPEED_BITMASK_10MBPS: + bandwidth = aggregator->num_of_ports * 10; + break; + case AD_LINK_SPEED_BITMASK_100MBPS: + bandwidth = aggregator->num_of_ports * 100; + break; + case AD_LINK_SPEED_BITMASK_1000MBPS: + bandwidth = aggregator->num_of_ports * 1000; + break; + case AD_LINK_SPEED_BITMASK_10000MBPS: + bandwidth = aggregator->num_of_ports * 10000; + break; + default: + bandwidth = 0; /*to silence the compiler ....*/ + } + } + return bandwidth; +} + +/** + * __get_active_agg - get the current active aggregator + * @aggregator: the aggregator we're looking at + * + */ +static struct aggregator *__get_active_agg(struct aggregator *aggregator) +{ + struct aggregator *retval = NULL; + + for (; aggregator; aggregator = __get_next_agg(aggregator)) { + if (aggregator->is_active) { + retval = aggregator; + break; + } + } + + return retval; +} + +/** + * __update_lacpdu_from_port - update a port's lacpdu fields + * @port: the port we're looking at + * + */ +static inline void __update_lacpdu_from_port(struct port *port) +{ + struct lacpdu *lacpdu = &port->lacpdu; + const struct port_params *partner = &port->partner_oper; + + /* update current actual Actor parameters */ + /* lacpdu->subtype initialized + * lacpdu->version_number initialized + * lacpdu->tlv_type_actor_info initialized + * lacpdu->actor_information_length initialized + */ + + lacpdu->actor_system_priority = htons(port->actor_system_priority); + lacpdu->actor_system = port->actor_system; + lacpdu->actor_key = htons(port->actor_oper_port_key); + lacpdu->actor_port_priority = htons(port->actor_port_priority); + lacpdu->actor_port = htons(port->actor_port_number); + lacpdu->actor_state = port->actor_oper_port_state; + + /* lacpdu->reserved_3_1 initialized + * lacpdu->tlv_type_partner_info initialized + * lacpdu->partner_information_length initialized + */ + + lacpdu->partner_system_priority = htons(partner->system_priority); + lacpdu->partner_system = partner->system; + lacpdu->partner_key = htons(partner->key); + lacpdu->partner_port_priority = htons(partner->port_priority); + lacpdu->partner_port = htons(partner->port_number); + lacpdu->partner_state = partner->port_state; + + /* lacpdu->reserved_3_2 initialized + * lacpdu->tlv_type_collector_info initialized + * lacpdu->collector_information_length initialized + * collector_max_delay initialized + * reserved_12[12] initialized + * tlv_type_terminator initialized + * terminator_length initialized + * reserved_50[50] initialized + */ +} + +////////////////////////////////////////////////////////////////////////////////////// +// ================= main 802.3ad protocol code ====================================== +////////////////////////////////////////////////////////////////////////////////////// + +/** + * ad_lacpdu_send - send out a lacpdu packet on a given port + * @port: the port we're looking at + * + * Returns: 0 on success + * < 0 on error + */ +static int ad_lacpdu_send(struct port *port) +{ + struct slave *slave = port->slave; + struct sk_buff *skb; + struct lacpdu_header *lacpdu_header; + int length = sizeof(struct lacpdu_header); + + skb = dev_alloc_skb(length); + if (!skb) + return -ENOMEM; + + skb->dev = slave->dev; + skb_reset_mac_header(skb); + skb->network_header = skb->mac_header + ETH_HLEN; + skb->protocol = PKT_TYPE_LACPDU; + skb->priority = TC_PRIO_CONTROL; + + lacpdu_header = (struct lacpdu_header *)skb_put(skb, length); + + memcpy(lacpdu_header->hdr.h_dest, lacpdu_mcast_addr, ETH_ALEN); + /* Note: source address is set to be the member's PERMANENT address, + because we use it to identify loopback lacpdus in receive. */ + memcpy(lacpdu_header->hdr.h_source, slave->perm_hwaddr, ETH_ALEN); + lacpdu_header->hdr.h_proto = PKT_TYPE_LACPDU; + + lacpdu_header->lacpdu = port->lacpdu; // struct copy + + dev_queue_xmit(skb); + + return 0; +} + +/** + * ad_marker_send - send marker information/response on a given port + * @port: the port we're looking at + * @marker: marker data to send + * + * Returns: 0 on success + * < 0 on error + */ +static int ad_marker_send(struct port *port, struct bond_marker *marker) +{ + struct slave *slave = port->slave; + struct sk_buff *skb; + struct bond_marker_header *marker_header; + int length = sizeof(struct bond_marker_header); + + skb = dev_alloc_skb(length + 16); + if (!skb) + return -ENOMEM; + + skb_reserve(skb, 16); + + skb->dev = slave->dev; + skb_reset_mac_header(skb); + skb->network_header = skb->mac_header + ETH_HLEN; + skb->protocol = PKT_TYPE_LACPDU; + + marker_header = (struct bond_marker_header *)skb_put(skb, length); + + memcpy(marker_header->hdr.h_dest, lacpdu_mcast_addr, ETH_ALEN); + /* Note: source address is set to be the member's PERMANENT address, + because we use it to identify loopback MARKERs in receive. */ + memcpy(marker_header->hdr.h_source, slave->perm_hwaddr, ETH_ALEN); + marker_header->hdr.h_proto = PKT_TYPE_LACPDU; + + marker_header->marker = *marker; // struct copy + + dev_queue_xmit(skb); + + return 0; +} + +/** + * ad_mux_machine - handle a port's mux state machine + * @port: the port we're looking at + * + */ +static void ad_mux_machine(struct port *port) +{ + mux_states_t last_state; + + // keep current State Machine state to compare later if it was changed + last_state = port->sm_mux_state; + + if (port->sm_vars & AD_PORT_BEGIN) { + port->sm_mux_state = AD_MUX_DETACHED; // next state + } else { + switch (port->sm_mux_state) { + case AD_MUX_DETACHED: + if ((port->sm_vars & AD_PORT_SELECTED) + || (port->sm_vars & AD_PORT_STANDBY)) + /* if SELECTED or STANDBY */ + port->sm_mux_state = AD_MUX_WAITING; // next state + break; + case AD_MUX_WAITING: + // if SELECTED == FALSE return to DETACH state + if (!(port->sm_vars & AD_PORT_SELECTED)) { // if UNSELECTED + port->sm_vars &= ~AD_PORT_READY_N; + // in order to withhold the Selection Logic to check all ports READY_N value + // every callback cycle to update ready variable, we check READY_N and update READY here + __set_agg_ports_ready(port->aggregator, __agg_ports_are_ready(port->aggregator)); + port->sm_mux_state = AD_MUX_DETACHED; // next state + break; + } + + // check if the wait_while_timer expired + if (port->sm_mux_timer_counter + && !(--port->sm_mux_timer_counter)) + port->sm_vars |= AD_PORT_READY_N; + + // in order to withhold the selection logic to check all ports READY_N value + // every callback cycle to update ready variable, we check READY_N and update READY here + __set_agg_ports_ready(port->aggregator, __agg_ports_are_ready(port->aggregator)); + + // if the wait_while_timer expired, and the port is in READY state, move to ATTACHED state + if ((port->sm_vars & AD_PORT_READY) + && !port->sm_mux_timer_counter) + port->sm_mux_state = AD_MUX_ATTACHED; // next state + break; + case AD_MUX_ATTACHED: + // check also if agg_select_timer expired(so the edable port will take place only after this timer) + if ((port->sm_vars & AD_PORT_SELECTED) && (port->partner_oper.port_state & AD_STATE_SYNCHRONIZATION) && !__check_agg_selection_timer(port)) { + port->sm_mux_state = AD_MUX_COLLECTING_DISTRIBUTING;// next state + } else if (!(port->sm_vars & AD_PORT_SELECTED) || (port->sm_vars & AD_PORT_STANDBY)) { // if UNSELECTED or STANDBY + port->sm_vars &= ~AD_PORT_READY_N; + // in order to withhold the selection logic to check all ports READY_N value + // every callback cycle to update ready variable, we check READY_N and update READY here + __set_agg_ports_ready(port->aggregator, __agg_ports_are_ready(port->aggregator)); + port->sm_mux_state = AD_MUX_DETACHED;// next state + } + break; + case AD_MUX_COLLECTING_DISTRIBUTING: + if (!(port->sm_vars & AD_PORT_SELECTED) || (port->sm_vars & AD_PORT_STANDBY) || + !(port->partner_oper.port_state & AD_STATE_SYNCHRONIZATION) + ) { + port->sm_mux_state = AD_MUX_ATTACHED;// next state + + } else { + // if port state hasn't changed make + // sure that a collecting distributing + // port in an active aggregator is enabled + if (port->aggregator && + port->aggregator->is_active && + !__port_is_enabled(port)) { + + __enable_port(port); + } + } + break; + default: //to silence the compiler + break; + } + } + + // check if the state machine was changed + if (port->sm_mux_state != last_state) { + pr_debug("Mux Machine: Port=%d, Last State=%d, Curr State=%d\n", + port->actor_port_number, last_state, + port->sm_mux_state); + switch (port->sm_mux_state) { + case AD_MUX_DETACHED: + __detach_bond_from_agg(port); + port->actor_oper_port_state &= ~AD_STATE_SYNCHRONIZATION; + ad_disable_collecting_distributing(port); + port->actor_oper_port_state &= ~AD_STATE_COLLECTING; + port->actor_oper_port_state &= ~AD_STATE_DISTRIBUTING; + port->ntt = true; + break; + case AD_MUX_WAITING: + port->sm_mux_timer_counter = __ad_timer_to_ticks(AD_WAIT_WHILE_TIMER, 0); + break; + case AD_MUX_ATTACHED: + __attach_bond_to_agg(port); + port->actor_oper_port_state |= AD_STATE_SYNCHRONIZATION; + port->actor_oper_port_state &= ~AD_STATE_COLLECTING; + port->actor_oper_port_state &= ~AD_STATE_DISTRIBUTING; + ad_disable_collecting_distributing(port); + port->ntt = true; + break; + case AD_MUX_COLLECTING_DISTRIBUTING: + port->actor_oper_port_state |= AD_STATE_COLLECTING; + port->actor_oper_port_state |= AD_STATE_DISTRIBUTING; + ad_enable_collecting_distributing(port); + port->ntt = true; + break; + default: //to silence the compiler + break; + } + } +} + +/** + * ad_rx_machine - handle a port's rx State Machine + * @lacpdu: the lacpdu we've received + * @port: the port we're looking at + * + * If lacpdu arrived, stop previous timer (if exists) and set the next state as + * CURRENT. If timer expired set the state machine in the proper state. + * In other cases, this function checks if we need to switch to other state. + */ +static void ad_rx_machine(struct lacpdu *lacpdu, struct port *port) +{ + rx_states_t last_state; + + // keep current State Machine state to compare later if it was changed + last_state = port->sm_rx_state; + + // check if state machine should change state + // first, check if port was reinitialized + if (port->sm_vars & AD_PORT_BEGIN) + /* next state */ + port->sm_rx_state = AD_RX_INITIALIZE; + // check if port is not enabled + else if (!(port->sm_vars & AD_PORT_BEGIN) + && !port->is_enabled && !(port->sm_vars & AD_PORT_MOVED)) + /* next state */ + port->sm_rx_state = AD_RX_PORT_DISABLED; + // check if new lacpdu arrived + else if (lacpdu && ((port->sm_rx_state == AD_RX_EXPIRED) || (port->sm_rx_state == AD_RX_DEFAULTED) || (port->sm_rx_state == AD_RX_CURRENT))) { + port->sm_rx_timer_counter = 0; // zero timer + port->sm_rx_state = AD_RX_CURRENT; + } else { + // if timer is on, and if it is expired + if (port->sm_rx_timer_counter && !(--port->sm_rx_timer_counter)) { + switch (port->sm_rx_state) { + case AD_RX_EXPIRED: + port->sm_rx_state = AD_RX_DEFAULTED; // next state + break; + case AD_RX_CURRENT: + port->sm_rx_state = AD_RX_EXPIRED; // next state + break; + default: //to silence the compiler + break; + } + } else { + // if no lacpdu arrived and no timer is on + switch (port->sm_rx_state) { + case AD_RX_PORT_DISABLED: + if (port->sm_vars & AD_PORT_MOVED) + port->sm_rx_state = AD_RX_INITIALIZE; // next state + else if (port->is_enabled + && (port->sm_vars + & AD_PORT_LACP_ENABLED)) + port->sm_rx_state = AD_RX_EXPIRED; // next state + else if (port->is_enabled + && ((port->sm_vars + & AD_PORT_LACP_ENABLED) == 0)) + port->sm_rx_state = AD_RX_LACP_DISABLED; // next state + break; + default: //to silence the compiler + break; + + } + } + } + + // check if the State machine was changed or new lacpdu arrived + if ((port->sm_rx_state != last_state) || (lacpdu)) { + pr_debug("Rx Machine: Port=%d, Last State=%d, Curr State=%d\n", + port->actor_port_number, last_state, + port->sm_rx_state); + switch (port->sm_rx_state) { + case AD_RX_INITIALIZE: + if (!(port->actor_oper_port_key & AD_DUPLEX_KEY_BITS)) + port->sm_vars &= ~AD_PORT_LACP_ENABLED; + else + port->sm_vars |= AD_PORT_LACP_ENABLED; + port->sm_vars &= ~AD_PORT_SELECTED; + __record_default(port); + port->actor_oper_port_state &= ~AD_STATE_EXPIRED; + port->sm_vars &= ~AD_PORT_MOVED; + port->sm_rx_state = AD_RX_PORT_DISABLED; // next state + + /*- Fall Through -*/ + + case AD_RX_PORT_DISABLED: + port->sm_vars &= ~AD_PORT_MATCHED; + break; + case AD_RX_LACP_DISABLED: + port->sm_vars &= ~AD_PORT_SELECTED; + __record_default(port); + port->partner_oper.port_state &= ~AD_STATE_AGGREGATION; + port->sm_vars |= AD_PORT_MATCHED; + port->actor_oper_port_state &= ~AD_STATE_EXPIRED; + break; + case AD_RX_EXPIRED: + //Reset of the Synchronization flag. (Standard 43.4.12) + //This reset cause to disable this port in the COLLECTING_DISTRIBUTING state of the + //mux machine in case of EXPIRED even if LINK_DOWN didn't arrive for the port. + port->partner_oper.port_state &= ~AD_STATE_SYNCHRONIZATION; + port->sm_vars &= ~AD_PORT_MATCHED; + port->partner_oper.port_state |= + AD_STATE_LACP_ACTIVITY; + port->sm_rx_timer_counter = __ad_timer_to_ticks(AD_CURRENT_WHILE_TIMER, (u16)(AD_SHORT_TIMEOUT)); + port->actor_oper_port_state |= AD_STATE_EXPIRED; + break; + case AD_RX_DEFAULTED: + __update_default_selected(port); + __record_default(port); + port->sm_vars |= AD_PORT_MATCHED; + port->actor_oper_port_state &= ~AD_STATE_EXPIRED; + break; + case AD_RX_CURRENT: + // detect loopback situation + if (!MAC_ADDRESS_COMPARE(&(lacpdu->actor_system), &(port->actor_system))) { + // INFO_RECEIVED_LOOPBACK_FRAMES + pr_err("%s: An illegal loopback occurred on adapter (%s).\n" + "Check the configuration to verify that all adapters are connected to 802.3ad compliant switch ports\n", + port->slave->dev->master->name, port->slave->dev->name); + return; + } + __update_selected(lacpdu, port); + __update_ntt(lacpdu, port); + __record_pdu(lacpdu, port); + port->sm_rx_timer_counter = __ad_timer_to_ticks(AD_CURRENT_WHILE_TIMER, (u16)(port->actor_oper_port_state & AD_STATE_LACP_TIMEOUT)); + port->actor_oper_port_state &= ~AD_STATE_EXPIRED; + break; + default: //to silence the compiler + break; + } + } +} + +/** + * ad_tx_machine - handle a port's tx state machine + * @port: the port we're looking at + * + */ +static void ad_tx_machine(struct port *port) +{ + // check if tx timer expired, to verify that we do not send more than 3 packets per second + if (port->sm_tx_timer_counter && !(--port->sm_tx_timer_counter)) { + // check if there is something to send + if (port->ntt && (port->sm_vars & AD_PORT_LACP_ENABLED)) { + __update_lacpdu_from_port(port); + + if (ad_lacpdu_send(port) >= 0) { + pr_debug("Sent LACPDU on port %d\n", + port->actor_port_number); + + /* mark ntt as false, so it will not be sent again until + demanded */ + port->ntt = false; + } + } + // restart tx timer(to verify that we will not exceed AD_MAX_TX_IN_SECOND + port->sm_tx_timer_counter = + ad_ticks_per_sec/AD_MAX_TX_IN_SECOND; + } +} + +/** + * ad_periodic_machine - handle a port's periodic state machine + * @port: the port we're looking at + * + * Turn ntt flag on priodically to perform periodic transmission of lacpdu's. + */ +static void ad_periodic_machine(struct port *port) +{ + periodic_states_t last_state; + + // keep current state machine state to compare later if it was changed + last_state = port->sm_periodic_state; + + // check if port was reinitialized + if (((port->sm_vars & AD_PORT_BEGIN) || !(port->sm_vars & AD_PORT_LACP_ENABLED) || !port->is_enabled) || + (!(port->actor_oper_port_state & AD_STATE_LACP_ACTIVITY) && !(port->partner_oper.port_state & AD_STATE_LACP_ACTIVITY)) + ) { + port->sm_periodic_state = AD_NO_PERIODIC; // next state + } + // check if state machine should change state + else if (port->sm_periodic_timer_counter) { + // check if periodic state machine expired + if (!(--port->sm_periodic_timer_counter)) { + // if expired then do tx + port->sm_periodic_state = AD_PERIODIC_TX; // next state + } else { + // If not expired, check if there is some new timeout parameter from the partner state + switch (port->sm_periodic_state) { + case AD_FAST_PERIODIC: + if (!(port->partner_oper.port_state + & AD_STATE_LACP_TIMEOUT)) + port->sm_periodic_state = AD_SLOW_PERIODIC; // next state + break; + case AD_SLOW_PERIODIC: + if ((port->partner_oper.port_state & AD_STATE_LACP_TIMEOUT)) { + // stop current timer + port->sm_periodic_timer_counter = 0; + port->sm_periodic_state = AD_PERIODIC_TX; // next state + } + break; + default: //to silence the compiler + break; + } + } + } else { + switch (port->sm_periodic_state) { + case AD_NO_PERIODIC: + port->sm_periodic_state = AD_FAST_PERIODIC; // next state + break; + case AD_PERIODIC_TX: + if (!(port->partner_oper.port_state + & AD_STATE_LACP_TIMEOUT)) + port->sm_periodic_state = AD_SLOW_PERIODIC; // next state + else + port->sm_periodic_state = AD_FAST_PERIODIC; // next state + break; + default: //to silence the compiler + break; + } + } + + // check if the state machine was changed + if (port->sm_periodic_state != last_state) { + pr_debug("Periodic Machine: Port=%d, Last State=%d, Curr State=%d\n", + port->actor_port_number, last_state, + port->sm_periodic_state); + switch (port->sm_periodic_state) { + case AD_NO_PERIODIC: + port->sm_periodic_timer_counter = 0; // zero timer + break; + case AD_FAST_PERIODIC: + port->sm_periodic_timer_counter = __ad_timer_to_ticks(AD_PERIODIC_TIMER, (u16)(AD_FAST_PERIODIC_TIME))-1; // decrement 1 tick we lost in the PERIODIC_TX cycle + break; + case AD_SLOW_PERIODIC: + port->sm_periodic_timer_counter = __ad_timer_to_ticks(AD_PERIODIC_TIMER, (u16)(AD_SLOW_PERIODIC_TIME))-1; // decrement 1 tick we lost in the PERIODIC_TX cycle + break; + case AD_PERIODIC_TX: + port->ntt = true; + break; + default: //to silence the compiler + break; + } + } +} + +/** + * ad_port_selection_logic - select aggregation groups + * @port: the port we're looking at + * + * Select aggregation groups, and assign each port for it's aggregetor. The + * selection logic is called in the inititalization (after all the handshkes), + * and after every lacpdu receive (if selected is off). + */ +static void ad_port_selection_logic(struct port *port) +{ + struct aggregator *aggregator, *free_aggregator = NULL, *temp_aggregator; + struct port *last_port = NULL, *curr_port; + int found = 0; + + // if the port is already Selected, do nothing + if (port->sm_vars & AD_PORT_SELECTED) + return; + + // if the port is connected to other aggregator, detach it + if (port->aggregator) { + // detach the port from its former aggregator + temp_aggregator = port->aggregator; + for (curr_port = temp_aggregator->lag_ports; curr_port; + last_port = curr_port, + curr_port = curr_port->next_port_in_aggregator) { + if (curr_port == port) { + temp_aggregator->num_of_ports--; + if (!last_port) {// if it is the first port attached to the aggregator + temp_aggregator->lag_ports = + port->next_port_in_aggregator; + } else {// not the first port attached to the aggregator + last_port->next_port_in_aggregator = + port->next_port_in_aggregator; + } + + // clear the port's relations to this aggregator + port->aggregator = NULL; + port->next_port_in_aggregator = NULL; + port->actor_port_aggregator_identifier = 0; + + pr_debug("Port %d left LAG %d\n", + port->actor_port_number, + temp_aggregator->aggregator_identifier); + // if the aggregator is empty, clear its parameters, and set it ready to be attached + if (!temp_aggregator->lag_ports) + ad_clear_agg(temp_aggregator); + break; + } + } + if (!curr_port) { // meaning: the port was related to an aggregator but was not on the aggregator port list + pr_warning("%s: Warning: Port %d (on %s) was related to aggregator %d but was not on its port list\n", + port->slave->dev->master->name, + port->actor_port_number, + port->slave->dev->name, + port->aggregator->aggregator_identifier); + } + } + // search on all aggregators for a suitable aggregator for this port + for (aggregator = __get_first_agg(port); aggregator; + aggregator = __get_next_agg(aggregator)) { + + // keep a free aggregator for later use(if needed) + if (!aggregator->lag_ports) { + if (!free_aggregator) + free_aggregator = aggregator; + continue; + } + // check if current aggregator suits us + if (((aggregator->actor_oper_aggregator_key == port->actor_oper_port_key) && // if all parameters match AND + !MAC_ADDRESS_COMPARE(&(aggregator->partner_system), &(port->partner_oper.system)) && + (aggregator->partner_system_priority == port->partner_oper.system_priority) && + (aggregator->partner_oper_aggregator_key == port->partner_oper.key) + ) && + ((MAC_ADDRESS_COMPARE(&(port->partner_oper.system), &(null_mac_addr)) && // partner answers + !aggregator->is_individual) // but is not individual OR + ) + ) { + // attach to the founded aggregator + port->aggregator = aggregator; + port->actor_port_aggregator_identifier = + port->aggregator->aggregator_identifier; + port->next_port_in_aggregator = aggregator->lag_ports; + port->aggregator->num_of_ports++; + aggregator->lag_ports = port; + pr_debug("Port %d joined LAG %d(existing LAG)\n", + port->actor_port_number, + port->aggregator->aggregator_identifier); + + // mark this port as selected + port->sm_vars |= AD_PORT_SELECTED; + found = 1; + break; + } + } + + // the port couldn't find an aggregator - attach it to a new aggregator + if (!found) { + if (free_aggregator) { + // assign port a new aggregator + port->aggregator = free_aggregator; + port->actor_port_aggregator_identifier = + port->aggregator->aggregator_identifier; + + // update the new aggregator's parameters + // if port was responsed from the end-user + if (port->actor_oper_port_key & AD_DUPLEX_KEY_BITS) + /* if port is full duplex */ + port->aggregator->is_individual = false; + else + port->aggregator->is_individual = true; + + port->aggregator->actor_admin_aggregator_key = port->actor_admin_port_key; + port->aggregator->actor_oper_aggregator_key = port->actor_oper_port_key; + port->aggregator->partner_system = + port->partner_oper.system; + port->aggregator->partner_system_priority = + port->partner_oper.system_priority; + port->aggregator->partner_oper_aggregator_key = port->partner_oper.key; + port->aggregator->receive_state = 1; + port->aggregator->transmit_state = 1; + port->aggregator->lag_ports = port; + port->aggregator->num_of_ports++; + + // mark this port as selected + port->sm_vars |= AD_PORT_SELECTED; + + pr_debug("Port %d joined LAG %d(new LAG)\n", + port->actor_port_number, + port->aggregator->aggregator_identifier); + } else { + pr_err("%s: Port %d (on %s) did not find a suitable aggregator\n", + port->slave->dev->master->name, + port->actor_port_number, port->slave->dev->name); + } + } + // if all aggregator's ports are READY_N == TRUE, set ready=TRUE in all aggregator's ports + // else set ready=FALSE in all aggregator's ports + __set_agg_ports_ready(port->aggregator, __agg_ports_are_ready(port->aggregator)); + + aggregator = __get_first_agg(port); + ad_agg_selection_logic(aggregator); +} + +/* + * Decide if "agg" is a better choice for the new active aggregator that + * the current best, according to the ad_select policy. + */ +static struct aggregator *ad_agg_selection_test(struct aggregator *best, + struct aggregator *curr) +{ + /* + * 0. If no best, select current. + * + * 1. If the current agg is not individual, and the best is + * individual, select current. + * + * 2. If current agg is individual and the best is not, keep best. + * + * 3. Therefore, current and best are both individual or both not + * individual, so: + * + * 3a. If current agg partner replied, and best agg partner did not, + * select current. + * + * 3b. If current agg partner did not reply and best agg partner + * did reply, keep best. + * + * 4. Therefore, current and best both have partner replies or + * both do not, so perform selection policy: + * + * BOND_AD_COUNT: Select by count of ports. If count is equal, + * select by bandwidth. + * + * BOND_AD_STABLE, BOND_AD_BANDWIDTH: Select by bandwidth. + */ + if (!best) + return curr; + + if (!curr->is_individual && best->is_individual) + return curr; + + if (curr->is_individual && !best->is_individual) + return best; + + if (__agg_has_partner(curr) && !__agg_has_partner(best)) + return curr; + + if (!__agg_has_partner(curr) && __agg_has_partner(best)) + return best; + + switch (__get_agg_selection_mode(curr->lag_ports)) { + case BOND_AD_COUNT: + if (curr->num_of_ports > best->num_of_ports) + return curr; + + if (curr->num_of_ports < best->num_of_ports) + return best; + + /*FALLTHROUGH*/ + case BOND_AD_STABLE: + case BOND_AD_BANDWIDTH: + if (__get_agg_bandwidth(curr) > __get_agg_bandwidth(best)) + return curr; + + break; + + default: + pr_warning("%s: Impossible agg select mode %d\n", + curr->slave->dev->master->name, + __get_agg_selection_mode(curr->lag_ports)); + break; + } + + return best; +} + +static int agg_device_up(const struct aggregator *agg) +{ + struct port *port = agg->lag_ports; + if (!port) + return 0; + return (netif_running(port->slave->dev) && + netif_carrier_ok(port->slave->dev)); +} + +/** + * ad_agg_selection_logic - select an aggregation group for a team + * @aggregator: the aggregator we're looking at + * + * It is assumed that only one aggregator may be selected for a team. + * + * The logic of this function is to select the aggregator according to + * the ad_select policy: + * + * BOND_AD_STABLE: select the aggregator with the most ports attached to + * it, and to reselect the active aggregator only if the previous + * aggregator has no more ports related to it. + * + * BOND_AD_BANDWIDTH: select the aggregator with the highest total + * bandwidth, and reselect whenever a link state change takes place or the + * set of slaves in the bond changes. + * + * BOND_AD_COUNT: select the aggregator with largest number of ports + * (slaves), and reselect whenever a link state change takes place or the + * set of slaves in the bond changes. + * + * FIXME: this function MUST be called with the first agg in the bond, or + * __get_active_agg() won't work correctly. This function should be better + * called with the bond itself, and retrieve the first agg from it. + */ +static void ad_agg_selection_logic(struct aggregator *agg) +{ + struct aggregator *best, *active, *origin; + struct port *port; + + origin = agg; + active = __get_active_agg(agg); + best = (active && agg_device_up(active)) ? active : NULL; + + do { + agg->is_active = 0; + + if (agg->num_of_ports && agg_device_up(agg)) + best = ad_agg_selection_test(best, agg); + + } while ((agg = __get_next_agg(agg))); + + if (best && + __get_agg_selection_mode(best->lag_ports) == BOND_AD_STABLE) { + /* + * For the STABLE policy, don't replace the old active + * aggregator if it's still active (it has an answering + * partner) or if both the best and active don't have an + * answering partner. + */ + if (active && active->lag_ports && + active->lag_ports->is_enabled && + (__agg_has_partner(active) || + (!__agg_has_partner(active) && !__agg_has_partner(best)))) { + if (!(!active->actor_oper_aggregator_key && + best->actor_oper_aggregator_key)) { + best = NULL; + active->is_active = 1; + } + } + } + + if (best && (best == active)) { + best = NULL; + active->is_active = 1; + } + + // if there is new best aggregator, activate it + if (best) { + pr_debug("best Agg=%d; P=%d; a k=%d; p k=%d; Ind=%d; Act=%d\n", + best->aggregator_identifier, best->num_of_ports, + best->actor_oper_aggregator_key, + best->partner_oper_aggregator_key, + best->is_individual, best->is_active); + pr_debug("best ports %p slave %p %s\n", + best->lag_ports, best->slave, + best->slave ? best->slave->dev->name : "NULL"); + + for (agg = __get_first_agg(best->lag_ports); agg; + agg = __get_next_agg(agg)) { + + pr_debug("Agg=%d; P=%d; a k=%d; p k=%d; Ind=%d; Act=%d\n", + agg->aggregator_identifier, agg->num_of_ports, + agg->actor_oper_aggregator_key, + agg->partner_oper_aggregator_key, + agg->is_individual, agg->is_active); + } + + // check if any partner replys + if (best->is_individual) { + pr_warning("%s: Warning: No 802.3ad response from the link partner for any adapters in the bond\n", + best->slave ? best->slave->dev->master->name : "NULL"); + } + + best->is_active = 1; + pr_debug("LAG %d chosen as the active LAG\n", + best->aggregator_identifier); + pr_debug("Agg=%d; P=%d; a k=%d; p k=%d; Ind=%d; Act=%d\n", + best->aggregator_identifier, best->num_of_ports, + best->actor_oper_aggregator_key, + best->partner_oper_aggregator_key, + best->is_individual, best->is_active); + + // disable the ports that were related to the former active_aggregator + if (active) { + for (port = active->lag_ports; port; + port = port->next_port_in_aggregator) { + __disable_port(port); + } + } + } + + /* + * if the selected aggregator is of join individuals + * (partner_system is NULL), enable their ports + */ + active = __get_active_agg(origin); + + if (active) { + if (!__agg_has_partner(active)) { + for (port = active->lag_ports; port; + port = port->next_port_in_aggregator) { + __enable_port(port); + } + } + } + + if (origin->slave) { + struct bonding *bond; + + bond = bond_get_bond_by_slave(origin->slave); + if (bond) + bond_3ad_set_carrier(bond); + } +} + +/** + * ad_clear_agg - clear a given aggregator's parameters + * @aggregator: the aggregator we're looking at + * + */ +static void ad_clear_agg(struct aggregator *aggregator) +{ + if (aggregator) { + aggregator->is_individual = false; + aggregator->actor_admin_aggregator_key = 0; + aggregator->actor_oper_aggregator_key = 0; + aggregator->partner_system = null_mac_addr; + aggregator->partner_system_priority = 0; + aggregator->partner_oper_aggregator_key = 0; + aggregator->receive_state = 0; + aggregator->transmit_state = 0; + aggregator->lag_ports = NULL; + aggregator->is_active = 0; + aggregator->num_of_ports = 0; + pr_debug("LAG %d was cleared\n", + aggregator->aggregator_identifier); + } +} + +/** + * ad_initialize_agg - initialize a given aggregator's parameters + * @aggregator: the aggregator we're looking at + * + */ +static void ad_initialize_agg(struct aggregator *aggregator) +{ + if (aggregator) { + ad_clear_agg(aggregator); + + aggregator->aggregator_mac_address = null_mac_addr; + aggregator->aggregator_identifier = 0; + aggregator->slave = NULL; + } +} + +/** + * ad_initialize_port - initialize a given port's parameters + * @aggregator: the aggregator we're looking at + * @lacp_fast: boolean. whether fast periodic should be used + * + */ +static void ad_initialize_port(struct port *port, int lacp_fast) +{ + static const struct port_params tmpl = { + .system_priority = 0xffff, + .key = 1, + .port_number = 1, + .port_priority = 0xff, + .port_state = 1, + }; + static const struct lacpdu lacpdu = { + .subtype = 0x01, + .version_number = 0x01, + .tlv_type_actor_info = 0x01, + .actor_information_length = 0x14, + .tlv_type_partner_info = 0x02, + .partner_information_length = 0x14, + .tlv_type_collector_info = 0x03, + .collector_information_length = 0x10, + .collector_max_delay = htons(AD_COLLECTOR_MAX_DELAY), + }; + + if (port) { + port->actor_port_number = 1; + port->actor_port_priority = 0xff; + port->actor_system = null_mac_addr; + port->actor_system_priority = 0xffff; + port->actor_port_aggregator_identifier = 0; + port->ntt = false; + port->actor_admin_port_key = 1; + port->actor_oper_port_key = 1; + port->actor_admin_port_state = AD_STATE_AGGREGATION | AD_STATE_LACP_ACTIVITY; + port->actor_oper_port_state = AD_STATE_AGGREGATION | AD_STATE_LACP_ACTIVITY; + + if (lacp_fast) + port->actor_oper_port_state |= AD_STATE_LACP_TIMEOUT; + + memcpy(&port->partner_admin, &tmpl, sizeof(tmpl)); + memcpy(&port->partner_oper, &tmpl, sizeof(tmpl)); + + port->is_enabled = true; + // ****** private parameters ****** + port->sm_vars = 0x3; + port->sm_rx_state = 0; + port->sm_rx_timer_counter = 0; + port->sm_periodic_state = 0; + port->sm_periodic_timer_counter = 0; + port->sm_mux_state = 0; + port->sm_mux_timer_counter = 0; + port->sm_tx_state = 0; + port->sm_tx_timer_counter = 0; + port->slave = NULL; + port->aggregator = NULL; + port->next_port_in_aggregator = NULL; + port->transaction_id = 0; + + memcpy(&port->lacpdu, &lacpdu, sizeof(lacpdu)); + } +} + +/** + * ad_enable_collecting_distributing - enable a port's transmit/receive + * @port: the port we're looking at + * + * Enable @port if it's in an active aggregator + */ +static void ad_enable_collecting_distributing(struct port *port) +{ + if (port->aggregator->is_active) { + pr_debug("Enabling port %d(LAG %d)\n", + port->actor_port_number, + port->aggregator->aggregator_identifier); + __enable_port(port); + } +} + +/** + * ad_disable_collecting_distributing - disable a port's transmit/receive + * @port: the port we're looking at + * + */ +static void ad_disable_collecting_distributing(struct port *port) +{ + if (port->aggregator && MAC_ADDRESS_COMPARE(&(port->aggregator->partner_system), &(null_mac_addr))) { + pr_debug("Disabling port %d(LAG %d)\n", + port->actor_port_number, + port->aggregator->aggregator_identifier); + __disable_port(port); + } +} + +#if 0 +/** + * ad_marker_info_send - send a marker information frame + * @port: the port we're looking at + * + * This function does nothing since we decided not to implement send and handle + * response for marker PDU's, in this stage, but only to respond to marker + * information. + */ +static void ad_marker_info_send(struct port *port) +{ + struct bond_marker marker; + u16 index; + + // fill the marker PDU with the appropriate values + marker.subtype = 0x02; + marker.version_number = 0x01; + marker.tlv_type = AD_MARKER_INFORMATION_SUBTYPE; + marker.marker_length = 0x16; + // convert requester_port to Big Endian + marker.requester_port = (((port->actor_port_number & 0xFF) << 8) |((u16)(port->actor_port_number & 0xFF00) >> 8)); + marker.requester_system = port->actor_system; + // convert requester_port(u32) to Big Endian + marker.requester_transaction_id = + (((++port->transaction_id & 0xFF) << 24) + | ((port->transaction_id & 0xFF00) << 8) + | ((port->transaction_id & 0xFF0000) >> 8) + | ((port->transaction_id & 0xFF000000) >> 24)); + marker.pad = 0; + marker.tlv_type_terminator = 0x00; + marker.terminator_length = 0x00; + for (index = 0; index < 90; index++) + marker.reserved_90[index] = 0; + + // send the marker information + if (ad_marker_send(port, &marker) >= 0) { + pr_debug("Sent Marker Information on port %d\n", + port->actor_port_number); + } +} +#endif + +/** + * ad_marker_info_received - handle receive of a Marker information frame + * @marker_info: Marker info received + * @port: the port we're looking at + * + */ +static void ad_marker_info_received(struct bond_marker *marker_info, + struct port *port) +{ + struct bond_marker marker; + + // copy the received marker data to the response marker + //marker = *marker_info; + memcpy(&marker, marker_info, sizeof(struct bond_marker)); + // change the marker subtype to marker response + marker.tlv_type = AD_MARKER_RESPONSE_SUBTYPE; + // send the marker response + + if (ad_marker_send(port, &marker) >= 0) { + pr_debug("Sent Marker Response on port %d\n", + port->actor_port_number); + } +} + +/** + * ad_marker_response_received - handle receive of a marker response frame + * @marker: marker PDU received + * @port: the port we're looking at + * + * This function does nothing since we decided not to implement send and handle + * response for marker PDU's, in this stage, but only to respond to marker + * information. + */ +static void ad_marker_response_received(struct bond_marker *marker, + struct port *port) +{ + marker = NULL; /* just to satisfy the compiler */ + port = NULL; /* just to satisfy the compiler */ + // DO NOTHING, SINCE WE DECIDED NOT TO IMPLEMENT THIS FEATURE FOR NOW +} + +////////////////////////////////////////////////////////////////////////////////////// +// ================= AD exported functions to the main bonding code ================== +////////////////////////////////////////////////////////////////////////////////////// + +// Check aggregators status in team every T seconds +#define AD_AGGREGATOR_SELECTION_TIMER 8 + +/* + * bond_3ad_initiate_agg_selection(struct bonding *bond) + * + * Set the aggregation selection timer, to initiate an agg selection in + * the very near future. Called during first initialization, and during + * any down to up transitions of the bond. + */ +void bond_3ad_initiate_agg_selection(struct bonding *bond, int timeout) +{ + BOND_AD_INFO(bond).agg_select_timer = timeout; +} + +static u16 aggregator_identifier; + +/** + * bond_3ad_initialize - initialize a bond's 802.3ad parameters and structures + * @bond: bonding struct to work on + * @tick_resolution: tick duration (millisecond resolution) + * + * Can be called only after the mac address of the bond is set. + */ +void bond_3ad_initialize(struct bonding *bond, u16 tick_resolution) +{ + // check that the bond is not initialized yet + if (MAC_ADDRESS_COMPARE(&(BOND_AD_INFO(bond).system.sys_mac_addr), + bond->dev->dev_addr)) { + + aggregator_identifier = 0; + + BOND_AD_INFO(bond).system.sys_priority = 0xFFFF; + BOND_AD_INFO(bond).system.sys_mac_addr = *((struct mac_addr *)bond->dev->dev_addr); + + // initialize how many times this module is called in one second(should be about every 100ms) + ad_ticks_per_sec = tick_resolution; + + bond_3ad_initiate_agg_selection(bond, + AD_AGGREGATOR_SELECTION_TIMER * + ad_ticks_per_sec); + } +} + +/** + * bond_3ad_bind_slave - initialize a slave's port + * @slave: slave struct to work on + * + * Returns: 0 on success + * < 0 on error + */ +int bond_3ad_bind_slave(struct slave *slave) +{ + struct bonding *bond = bond_get_bond_by_slave(slave); + struct port *port; + struct aggregator *aggregator; + + if (bond == NULL) { + pr_err("%s: The slave %s is not attached to its bond\n", + slave->dev->master->name, slave->dev->name); + return -1; + } + + //check that the slave has not been initialized yet. + if (SLAVE_AD_INFO(slave).port.slave != slave) { + + // port initialization + port = &(SLAVE_AD_INFO(slave).port); + + ad_initialize_port(port, bond->params.lacp_fast); + + port->slave = slave; + port->actor_port_number = SLAVE_AD_INFO(slave).id; + // key is determined according to the link speed, duplex and user key(which is yet not supported) + // ------------------------------------------------------------ + // Port key : | User key | Speed |Duplex| + // ------------------------------------------------------------ + // 16 6 1 0 + port->actor_admin_port_key = 0; // initialize this parameter + port->actor_admin_port_key |= __get_duplex(port); + port->actor_admin_port_key |= (__get_link_speed(port) << 1); + port->actor_oper_port_key = port->actor_admin_port_key; + // if the port is not full duplex, then the port should be not lacp Enabled + if (!(port->actor_oper_port_key & AD_DUPLEX_KEY_BITS)) + port->sm_vars &= ~AD_PORT_LACP_ENABLED; + // actor system is the bond's system + port->actor_system = BOND_AD_INFO(bond).system.sys_mac_addr; + // tx timer(to verify that no more than MAX_TX_IN_SECOND lacpdu's are sent in one second) + port->sm_tx_timer_counter = ad_ticks_per_sec/AD_MAX_TX_IN_SECOND; + port->aggregator = NULL; + port->next_port_in_aggregator = NULL; + + __disable_port(port); + __initialize_port_locks(port); + + + // aggregator initialization + aggregator = &(SLAVE_AD_INFO(slave).aggregator); + + ad_initialize_agg(aggregator); + + aggregator->aggregator_mac_address = *((struct mac_addr *)bond->dev->dev_addr); + aggregator->aggregator_identifier = (++aggregator_identifier); + aggregator->slave = slave; + aggregator->is_active = 0; + aggregator->num_of_ports = 0; + } + + return 0; +} + +/** + * bond_3ad_unbind_slave - deinitialize a slave's port + * @slave: slave struct to work on + * + * Search for the aggregator that is related to this port, remove the + * aggregator and assign another aggregator for other port related to it + * (if any), and remove the port. + */ +void bond_3ad_unbind_slave(struct slave *slave) +{ + struct port *port, *prev_port, *temp_port; + struct aggregator *aggregator, *new_aggregator, *temp_aggregator; + int select_new_active_agg = 0; + + // find the aggregator related to this slave + aggregator = &(SLAVE_AD_INFO(slave).aggregator); + + // find the port related to this slave + port = &(SLAVE_AD_INFO(slave).port); + + // if slave is null, the whole port is not initialized + if (!port->slave) { + pr_warning("Warning: %s: Trying to unbind an uninitialized port on %s\n", + slave->dev->master->name, slave->dev->name); + return; + } + + pr_debug("Unbinding Link Aggregation Group %d\n", + aggregator->aggregator_identifier); + + /* Tell the partner that this port is not suitable for aggregation */ + port->actor_oper_port_state &= ~AD_STATE_AGGREGATION; + __update_lacpdu_from_port(port); + ad_lacpdu_send(port); + + // check if this aggregator is occupied + if (aggregator->lag_ports) { + // check if there are other ports related to this aggregator except + // the port related to this slave(thats ensure us that there is a + // reason to search for new aggregator, and that we will find one + if ((aggregator->lag_ports != port) || (aggregator->lag_ports->next_port_in_aggregator)) { + // find new aggregator for the related port(s) + new_aggregator = __get_first_agg(port); + for (; new_aggregator; new_aggregator = __get_next_agg(new_aggregator)) { + // if the new aggregator is empty, or it is connected to our port only + if (!new_aggregator->lag_ports + || ((new_aggregator->lag_ports == port) + && !new_aggregator->lag_ports->next_port_in_aggregator)) + break; + } + // if new aggregator found, copy the aggregator's parameters + // and connect the related lag_ports to the new aggregator + if ((new_aggregator) && ((!new_aggregator->lag_ports) || ((new_aggregator->lag_ports == port) && !new_aggregator->lag_ports->next_port_in_aggregator))) { + pr_debug("Some port(s) related to LAG %d - replaceing with LAG %d\n", + aggregator->aggregator_identifier, + new_aggregator->aggregator_identifier); + + if ((new_aggregator->lag_ports == port) && new_aggregator->is_active) { + pr_info("%s: Removing an active aggregator\n", + aggregator->slave->dev->master->name); + // select new active aggregator + select_new_active_agg = 1; + } + + new_aggregator->is_individual = aggregator->is_individual; + new_aggregator->actor_admin_aggregator_key = aggregator->actor_admin_aggregator_key; + new_aggregator->actor_oper_aggregator_key = aggregator->actor_oper_aggregator_key; + new_aggregator->partner_system = aggregator->partner_system; + new_aggregator->partner_system_priority = aggregator->partner_system_priority; + new_aggregator->partner_oper_aggregator_key = aggregator->partner_oper_aggregator_key; + new_aggregator->receive_state = aggregator->receive_state; + new_aggregator->transmit_state = aggregator->transmit_state; + new_aggregator->lag_ports = aggregator->lag_ports; + new_aggregator->is_active = aggregator->is_active; + new_aggregator->num_of_ports = aggregator->num_of_ports; + + // update the information that is written on the ports about the aggregator + for (temp_port = aggregator->lag_ports; temp_port; + temp_port = temp_port->next_port_in_aggregator) { + temp_port->aggregator = new_aggregator; + temp_port->actor_port_aggregator_identifier = new_aggregator->aggregator_identifier; + } + + // clear the aggregator + ad_clear_agg(aggregator); + + if (select_new_active_agg) + ad_agg_selection_logic(__get_first_agg(port)); + } else { + pr_warning("%s: Warning: unbinding aggregator, and could not find a new aggregator for its ports\n", + slave->dev->master->name); + } + } else { // in case that the only port related to this aggregator is the one we want to remove + select_new_active_agg = aggregator->is_active; + // clear the aggregator + ad_clear_agg(aggregator); + if (select_new_active_agg) { + pr_info("%s: Removing an active aggregator\n", + slave->dev->master->name); + // select new active aggregator + ad_agg_selection_logic(__get_first_agg(port)); + } + } + } + + pr_debug("Unbinding port %d\n", port->actor_port_number); + // find the aggregator that this port is connected to + temp_aggregator = __get_first_agg(port); + for (; temp_aggregator; temp_aggregator = __get_next_agg(temp_aggregator)) { + prev_port = NULL; + // search the port in the aggregator's related ports + for (temp_port = temp_aggregator->lag_ports; temp_port; + prev_port = temp_port, + temp_port = temp_port->next_port_in_aggregator) { + if (temp_port == port) { // the aggregator found - detach the port from this aggregator + if (prev_port) + prev_port->next_port_in_aggregator = temp_port->next_port_in_aggregator; + else + temp_aggregator->lag_ports = temp_port->next_port_in_aggregator; + temp_aggregator->num_of_ports--; + if (temp_aggregator->num_of_ports == 0) { + select_new_active_agg = temp_aggregator->is_active; + // clear the aggregator + ad_clear_agg(temp_aggregator); + if (select_new_active_agg) { + pr_info("%s: Removing an active aggregator\n", + slave->dev->master->name); + // select new active aggregator + ad_agg_selection_logic(__get_first_agg(port)); + } + } + break; + } + } + } + port->slave = NULL; +} + +/** + * bond_3ad_state_machine_handler - handle state machines timeout + * @bond: bonding struct to work on + * + * The state machine handling concept in this module is to check every tick + * which state machine should operate any function. The execution order is + * round robin, so when we have an interaction between state machines, the + * reply of one to each other might be delayed until next tick. + * + * This function also complete the initialization when the agg_select_timer + * times out, and it selects an aggregator for the ports that are yet not + * related to any aggregator, and selects the active aggregator for a bond. + */ +void bond_3ad_state_machine_handler(struct work_struct *work) +{ + struct bonding *bond = container_of(work, struct bonding, + ad_work.work); + struct port *port; + struct aggregator *aggregator; + + read_lock(&bond->lock); + + //check if there are any slaves + if (bond->slave_cnt == 0) + goto re_arm; + + // check if agg_select_timer timer after initialize is timed out + if (BOND_AD_INFO(bond).agg_select_timer && !(--BOND_AD_INFO(bond).agg_select_timer)) { + // select the active aggregator for the bond + if ((port = __get_first_port(bond))) { + if (!port->slave) { + pr_warning("%s: Warning: bond's first port is uninitialized\n", + bond->dev->name); + goto re_arm; + } + + aggregator = __get_first_agg(port); + ad_agg_selection_logic(aggregator); + } + bond_3ad_set_carrier(bond); + } + + // for each port run the state machines + for (port = __get_first_port(bond); port; port = __get_next_port(port)) { + if (!port->slave) { + pr_warning("%s: Warning: Found an uninitialized port\n", + bond->dev->name); + goto re_arm; + } + + /* Lock around state machines to protect data accessed + * by all (e.g., port->sm_vars). ad_rx_machine may run + * concurrently due to incoming LACPDU. + */ + __get_state_machine_lock(port); + + ad_rx_machine(NULL, port); + ad_periodic_machine(port); + ad_port_selection_logic(port); + ad_mux_machine(port); + ad_tx_machine(port); + + // turn off the BEGIN bit, since we already handled it + if (port->sm_vars & AD_PORT_BEGIN) + port->sm_vars &= ~AD_PORT_BEGIN; + + __release_state_machine_lock(port); + } + +re_arm: + queue_delayed_work(bond->wq, &bond->ad_work, ad_delta_in_ticks); + + read_unlock(&bond->lock); +} + +/** + * bond_3ad_rx_indication - handle a received frame + * @lacpdu: received lacpdu + * @slave: slave struct to work on + * @length: length of the data received + * + * It is assumed that frames that were sent on this NIC don't returned as new + * received frames (loopback). Since only the payload is given to this + * function, it check for loopback. + */ +static int bond_3ad_rx_indication(struct lacpdu *lacpdu, struct slave *slave, u16 length) +{ + struct port *port; + int ret = RX_HANDLER_ANOTHER; + + if (length >= sizeof(struct lacpdu)) { + + port = &(SLAVE_AD_INFO(slave).port); + + if (!port->slave) { + pr_warning("%s: Warning: port of slave %s is uninitialized\n", + slave->dev->name, slave->dev->master->name); + return ret; + } + + switch (lacpdu->subtype) { + case AD_TYPE_LACPDU: + ret = RX_HANDLER_CONSUMED; + pr_debug("Received LACPDU on port %d\n", + port->actor_port_number); + /* Protect against concurrent state machines */ + __get_state_machine_lock(port); + ad_rx_machine(lacpdu, port); + __release_state_machine_lock(port); + break; + + case AD_TYPE_MARKER: + ret = RX_HANDLER_CONSUMED; + // No need to convert fields to Little Endian since we don't use the marker's fields. + + switch (((struct bond_marker *)lacpdu)->tlv_type) { + case AD_MARKER_INFORMATION_SUBTYPE: + pr_debug("Received Marker Information on port %d\n", + port->actor_port_number); + ad_marker_info_received((struct bond_marker *)lacpdu, port); + break; + + case AD_MARKER_RESPONSE_SUBTYPE: + pr_debug("Received Marker Response on port %d\n", + port->actor_port_number); + ad_marker_response_received((struct bond_marker *)lacpdu, port); + break; + + default: + pr_debug("Received an unknown Marker subtype on slot %d\n", + port->actor_port_number); + } + } + } + return ret; +} + +/** + * bond_3ad_adapter_speed_changed - handle a slave's speed change indication + * @slave: slave struct to work on + * + * Handle reselection of aggregator (if needed) for this port. + */ +void bond_3ad_adapter_speed_changed(struct slave *slave) +{ + struct port *port; + + port = &(SLAVE_AD_INFO(slave).port); + + // if slave is null, the whole port is not initialized + if (!port->slave) { + pr_warning("Warning: %s: speed changed for uninitialized port on %s\n", + slave->dev->master->name, slave->dev->name); + return; + } + + port->actor_admin_port_key &= ~AD_SPEED_KEY_BITS; + port->actor_oper_port_key = port->actor_admin_port_key |= + (__get_link_speed(port) << 1); + pr_debug("Port %d changed speed\n", port->actor_port_number); + // there is no need to reselect a new aggregator, just signal the + // state machines to reinitialize + port->sm_vars |= AD_PORT_BEGIN; +} + +/** + * bond_3ad_adapter_duplex_changed - handle a slave's duplex change indication + * @slave: slave struct to work on + * + * Handle reselection of aggregator (if needed) for this port. + */ +void bond_3ad_adapter_duplex_changed(struct slave *slave) +{ + struct port *port; + + port = &(SLAVE_AD_INFO(slave).port); + + // if slave is null, the whole port is not initialized + if (!port->slave) { + pr_warning("%s: Warning: duplex changed for uninitialized port on %s\n", + slave->dev->master->name, slave->dev->name); + return; + } + + port->actor_admin_port_key &= ~AD_DUPLEX_KEY_BITS; + port->actor_oper_port_key = port->actor_admin_port_key |= + __get_duplex(port); + pr_debug("Port %d changed duplex\n", port->actor_port_number); + // there is no need to reselect a new aggregator, just signal the + // state machines to reinitialize + port->sm_vars |= AD_PORT_BEGIN; +} + +/** + * bond_3ad_handle_link_change - handle a slave's link status change indication + * @slave: slave struct to work on + * @status: whether the link is now up or down + * + * Handle reselection of aggregator (if needed) for this port. + */ +void bond_3ad_handle_link_change(struct slave *slave, char link) +{ + struct port *port; + + port = &(SLAVE_AD_INFO(slave).port); + + // if slave is null, the whole port is not initialized + if (!port->slave) { + pr_warning("Warning: %s: link status changed for uninitialized port on %s\n", + slave->dev->master->name, slave->dev->name); + return; + } + + // on link down we are zeroing duplex and speed since some of the adaptors(ce1000.lan) report full duplex/speed instead of N/A(duplex) / 0(speed) + // on link up we are forcing recheck on the duplex and speed since some of he adaptors(ce1000.lan) report + if (link == BOND_LINK_UP) { + port->is_enabled = true; + port->actor_admin_port_key &= ~AD_DUPLEX_KEY_BITS; + port->actor_oper_port_key = port->actor_admin_port_key |= + __get_duplex(port); + port->actor_admin_port_key &= ~AD_SPEED_KEY_BITS; + port->actor_oper_port_key = port->actor_admin_port_key |= + (__get_link_speed(port) << 1); + } else { + /* link has failed */ + port->is_enabled = false; + port->actor_admin_port_key &= ~AD_DUPLEX_KEY_BITS; + port->actor_oper_port_key = (port->actor_admin_port_key &= + ~AD_SPEED_KEY_BITS); + } + //BOND_PRINT_DBG(("Port %d changed link status to %s", port->actor_port_number, ((link == BOND_LINK_UP)?"UP":"DOWN"))); + // there is no need to reselect a new aggregator, just signal the + // state machines to reinitialize + port->sm_vars |= AD_PORT_BEGIN; +} + +/* + * set link state for bonding master: if we have an active + * aggregator, we're up, if not, we're down. Presumes that we cannot + * have an active aggregator if there are no slaves with link up. + * + * This behavior complies with IEEE 802.3 section 43.3.9. + * + * Called by bond_set_carrier(). Return zero if carrier state does not + * change, nonzero if it does. + */ +int bond_3ad_set_carrier(struct bonding *bond) +{ + struct aggregator *active; + + active = __get_active_agg(&(SLAVE_AD_INFO(bond->first_slave).aggregator)); + if (active) { + /* are enough slaves available to consider link up? */ + if (active->num_of_ports < bond->params.min_links) { + if (netif_carrier_ok(bond->dev)) { + netif_carrier_off(bond->dev); + return 1; + } + } else if (!netif_carrier_ok(bond->dev)) { + netif_carrier_on(bond->dev); + return 1; + } + return 0; + } + + if (netif_carrier_ok(bond->dev)) { + netif_carrier_off(bond->dev); + return 1; + } + return 0; +} + +/** + * bond_3ad_get_active_agg_info - get information of the active aggregator + * @bond: bonding struct to work on + * @ad_info: ad_info struct to fill with the bond's info + * + * Returns: 0 on success + * < 0 on error + */ +int bond_3ad_get_active_agg_info(struct bonding *bond, struct ad_info *ad_info) +{ + struct aggregator *aggregator = NULL; + struct port *port; + + for (port = __get_first_port(bond); port; port = __get_next_port(port)) { + if (port->aggregator && port->aggregator->is_active) { + aggregator = port->aggregator; + break; + } + } + + if (aggregator) { + ad_info->aggregator_id = aggregator->aggregator_identifier; + ad_info->ports = aggregator->num_of_ports; + ad_info->actor_key = aggregator->actor_oper_aggregator_key; + ad_info->partner_key = aggregator->partner_oper_aggregator_key; + memcpy(ad_info->partner_system, aggregator->partner_system.mac_addr_value, ETH_ALEN); + return 0; + } + + return -1; +} + +int bond_3ad_xmit_xor(struct sk_buff *skb, struct net_device *dev) +{ + struct slave *slave, *start_at; + struct bonding *bond = netdev_priv(dev); + int slave_agg_no; + int slaves_in_agg; + int agg_id; + int i; + struct ad_info ad_info; + int res = 1; + + if (bond_3ad_get_active_agg_info(bond, &ad_info)) { + pr_debug("%s: Error: bond_3ad_get_active_agg_info failed\n", + dev->name); + goto out; + } + + slaves_in_agg = ad_info.ports; + agg_id = ad_info.aggregator_id; + + if (slaves_in_agg == 0) { + /*the aggregator is empty*/ + pr_debug("%s: Error: active aggregator is empty\n", dev->name); + goto out; + } + + slave_agg_no = bond->xmit_hash_policy(skb, slaves_in_agg); + + bond_for_each_slave(bond, slave, i) { + struct aggregator *agg = SLAVE_AD_INFO(slave).port.aggregator; + + if (agg && (agg->aggregator_identifier == agg_id)) { + slave_agg_no--; + if (slave_agg_no < 0) + break; + } + } + + if (slave_agg_no >= 0) { + pr_err("%s: Error: Couldn't find a slave to tx on for aggregator ID %d\n", + dev->name, agg_id); + goto out; + } + + start_at = slave; + + bond_for_each_slave_from(bond, slave, i, start_at) { + int slave_agg_id = 0; + struct aggregator *agg = SLAVE_AD_INFO(slave).port.aggregator; + + if (agg) + slave_agg_id = agg->aggregator_identifier; + + if (SLAVE_IS_OK(slave) && agg && (slave_agg_id == agg_id)) { + res = bond_dev_queue_xmit(bond, skb, slave->dev); + break; + } + } + +out: + if (res) { + /* no suitable interface, frame not sent */ + dev_kfree_skb(skb); + } + + return NETDEV_TX_OK; +} + +int bond_3ad_lacpdu_recv(struct sk_buff *skb, struct bonding *bond, + struct slave *slave) +{ + int ret = RX_HANDLER_ANOTHER; + if (skb->protocol != PKT_TYPE_LACPDU) + return ret; + + if (!pskb_may_pull(skb, sizeof(struct lacpdu))) + return ret; + + read_lock(&bond->lock); + ret = bond_3ad_rx_indication((struct lacpdu *) skb->data, slave, skb->len); + read_unlock(&bond->lock); + return ret; +} + +/* + * When modify lacp_rate parameter via sysfs, + * update actor_oper_port_state of each port. + * + * Hold slave->state_machine_lock, + * so we can modify port->actor_oper_port_state, + * no matter bond is up or down. + */ +void bond_3ad_update_lacp_rate(struct bonding *bond) +{ + int i; + struct slave *slave; + struct port *port = NULL; + int lacp_fast; + + read_lock(&bond->lock); + lacp_fast = bond->params.lacp_fast; + + bond_for_each_slave(bond, slave, i) { + port = &(SLAVE_AD_INFO(slave).port); + __get_state_machine_lock(port); + if (lacp_fast) + port->actor_oper_port_state |= AD_STATE_LACP_TIMEOUT; + else + port->actor_oper_port_state &= ~AD_STATE_LACP_TIMEOUT; + __release_state_machine_lock(port); + } + + read_unlock(&bond->lock); +} diff --git a/ANDROID_3.4.5/drivers/net/bonding/bond_3ad.h b/ANDROID_3.4.5/drivers/net/bonding/bond_3ad.h new file mode 100644 index 00000000..5ee7e3c4 --- /dev/null +++ b/ANDROID_3.4.5/drivers/net/bonding/bond_3ad.h @@ -0,0 +1,282 @@ +/* + * 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 __BOND_3AD_H__ +#define __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 +}; + +struct ad_slave_info { + struct aggregator aggregator; // 802.3ad aggregator structure + struct port port; // 802.3ad port structure + spinlock_t state_machine_lock; /* mutex state machines vs. + incoming LACPDU */ + u16 id; +}; + +// ================= AD Exported functions to the main bonding code ================== +void bond_3ad_initialize(struct bonding *bond, u16 tick_resolution); +int 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_xmit_xor(struct sk_buff *skb, struct net_device *dev); +int bond_3ad_lacpdu_recv(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 //__BOND_3AD_H__ + diff --git a/ANDROID_3.4.5/drivers/net/bonding/bond_alb.c b/ANDROID_3.4.5/drivers/net/bonding/bond_alb.c new file mode 100644 index 00000000..2e1f8066 --- /dev/null +++ b/ANDROID_3.4.5/drivers/net/bonding/bond_alb.c @@ -0,0 +1,1722 @@ +/* + * 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. + * + */ + +#define pr_fmt(fmt) KBUILD_MODNAME ": " fmt + +#include <linux/skbuff.h> +#include <linux/netdevice.h> +#include <linux/etherdevice.h> +#include <linux/pkt_sched.h> +#include <linux/spinlock.h> +#include <linux/slab.h> +#include <linux/timer.h> +#include <linux/ip.h> +#include <linux/ipv6.h> +#include <linux/if_arp.h> +#include <linux/if_ether.h> +#include <linux/if_bonding.h> +#include <linux/if_vlan.h> +#include <linux/in.h> +#include <net/ipx.h> +#include <net/arp.h> +#include <net/ipv6.h> +#include <asm/byteorder.h> +#include "bonding.h" +#include "bond_alb.h" + + + +#ifndef __long_aligned +#define __long_aligned __attribute__((aligned((sizeof(long))))) +#endif +static const u8 mac_bcast[ETH_ALEN] __long_aligned = { + 0xff, 0xff, 0xff, 0xff, 0xff, 0xff +}; +static const u8 mac_v6_allmcast[ETH_ALEN] __long_aligned = { + 0x33, 0x33, 0x00, 0x00, 0x00, 0x01 +}; +static const int alb_delta_in_ticks = HZ / ALB_TIMER_TICKS_PER_SEC; + +#pragma pack(1) +struct learning_pkt { + u8 mac_dst[ETH_ALEN]; + u8 mac_src[ETH_ALEN]; + __be16 type; + u8 padding[ETH_ZLEN - ETH_HLEN]; +}; + +struct arp_pkt { + __be16 hw_addr_space; + __be16 prot_addr_space; + u8 hw_addr_len; + u8 prot_addr_len; + __be16 op_code; + u8 mac_src[ETH_ALEN]; /* sender hardware address */ + __be32 ip_src; /* sender IP address */ + u8 mac_dst[ETH_ALEN]; /* target hardware address */ + __be32 ip_dst; /* target IP address */ +}; +#pragma pack() + +static inline struct arp_pkt *arp_pkt(const struct sk_buff *skb) +{ + return (struct arp_pkt *)skb_network_header(skb); +} + +/* Forward declaration */ +static void alb_send_learning_packets(struct slave *slave, u8 mac_addr[]); + +static inline u8 _simple_hash(const u8 *hash_start, int hash_size) +{ + int i; + u8 hash = 0; + + for (i = 0; i < hash_size; i++) { + hash ^= hash_start[i]; + } + + return hash; +} + +/*********************** tlb specific functions ***************************/ + +static inline void _lock_tx_hashtbl_bh(struct bonding *bond) +{ + spin_lock_bh(&(BOND_ALB_INFO(bond).tx_hashtbl_lock)); +} + +static inline void _unlock_tx_hashtbl_bh(struct bonding *bond) +{ + spin_unlock_bh(&(BOND_ALB_INFO(bond).tx_hashtbl_lock)); +} + +static inline void _lock_tx_hashtbl(struct bonding *bond) +{ + spin_lock(&(BOND_ALB_INFO(bond).tx_hashtbl_lock)); +} + +static inline void _unlock_tx_hashtbl(struct bonding *bond) +{ + spin_unlock(&(BOND_ALB_INFO(bond).tx_hashtbl_lock)); +} + +/* Caller must hold tx_hashtbl lock */ +static inline void tlb_init_table_entry(struct tlb_client_info *entry, int save_load) +{ + if (save_load) { + entry->load_history = 1 + entry->tx_bytes / + BOND_TLB_REBALANCE_INTERVAL; + entry->tx_bytes = 0; + } + + entry->tx_slave = NULL; + entry->next = TLB_NULL_INDEX; + entry->prev = TLB_NULL_INDEX; +} + +static inline void tlb_init_slave(struct slave *slave) +{ + SLAVE_TLB_INFO(slave).load = 0; + SLAVE_TLB_INFO(slave).head = TLB_NULL_INDEX; +} + +/* Caller must hold bond lock for read, BH disabled */ +static void __tlb_clear_slave(struct bonding *bond, struct slave *slave, + int save_load) +{ + struct tlb_client_info *tx_hash_table; + u32 index; + + /* clear slave from tx_hashtbl */ + tx_hash_table = BOND_ALB_INFO(bond).tx_hashtbl; + + /* skip this if we've already freed the tx hash table */ + if (tx_hash_table) { + index = SLAVE_TLB_INFO(slave).head; + while (index != TLB_NULL_INDEX) { + u32 next_index = tx_hash_table[index].next; + tlb_init_table_entry(&tx_hash_table[index], save_load); + index = next_index; + } + } + + tlb_init_slave(slave); +} + +/* Caller must hold bond lock for read */ +static void tlb_clear_slave(struct bonding *bond, struct slave *slave, + int save_load) +{ + _lock_tx_hashtbl_bh(bond); + __tlb_clear_slave(bond, slave, save_load); + _unlock_tx_hashtbl_bh(bond); +} + +/* Must be called before starting the monitor timer */ +static int tlb_initialize(struct bonding *bond) +{ + struct alb_bond_info *bond_info = &(BOND_ALB_INFO(bond)); + int size = TLB_HASH_TABLE_SIZE * sizeof(struct tlb_client_info); + struct tlb_client_info *new_hashtbl; + int i; + + new_hashtbl = kzalloc(size, GFP_KERNEL); + if (!new_hashtbl) + return -1; + + _lock_tx_hashtbl_bh(bond); + + bond_info->tx_hashtbl = new_hashtbl; + + for (i = 0; i < TLB_HASH_TABLE_SIZE; i++) { + tlb_init_table_entry(&bond_info->tx_hashtbl[i], 0); + } + + _unlock_tx_hashtbl_bh(bond); + + return 0; +} + +/* Must be called only after all slaves have been released */ +static void tlb_deinitialize(struct bonding *bond) +{ + struct alb_bond_info *bond_info = &(BOND_ALB_INFO(bond)); + + _lock_tx_hashtbl_bh(bond); + + kfree(bond_info->tx_hashtbl); + bond_info->tx_hashtbl = NULL; + + _unlock_tx_hashtbl_bh(bond); +} + +static long long compute_gap(struct slave *slave) +{ + return (s64) (slave->speed << 20) - /* Convert to Megabit per sec */ + (s64) (SLAVE_TLB_INFO(slave).load << 3); /* Bytes to bits */ +} + +/* Caller must hold bond lock for read */ +static struct slave *tlb_get_least_loaded_slave(struct bonding *bond) +{ + struct slave *slave, *least_loaded; + long long max_gap; + int i; + + least_loaded = NULL; + max_gap = LLONG_MIN; + + /* Find the slave with the largest gap */ + bond_for_each_slave(bond, slave, i) { + if (SLAVE_IS_OK(slave)) { + long long gap = compute_gap(slave); + + if (max_gap < gap) { + least_loaded = slave; + max_gap = gap; + } + } + } + + return least_loaded; +} + +static struct slave *__tlb_choose_channel(struct bonding *bond, u32 hash_index, + u32 skb_len) +{ + struct alb_bond_info *bond_info = &(BOND_ALB_INFO(bond)); + struct tlb_client_info *hash_table; + struct slave *assigned_slave; + + hash_table = bond_info->tx_hashtbl; + assigned_slave = hash_table[hash_index].tx_slave; + if (!assigned_slave) { + assigned_slave = tlb_get_least_loaded_slave(bond); + + if (assigned_slave) { + struct tlb_slave_info *slave_info = + &(SLAVE_TLB_INFO(assigned_slave)); + u32 next_index = slave_info->head; + + hash_table[hash_index].tx_slave = assigned_slave; + hash_table[hash_index].next = next_index; + hash_table[hash_index].prev = TLB_NULL_INDEX; + + if (next_index != TLB_NULL_INDEX) { + hash_table[next_index].prev = hash_index; + } + + slave_info->head = hash_index; + slave_info->load += + hash_table[hash_index].load_history; + } + } + + if (assigned_slave) { + hash_table[hash_index].tx_bytes += skb_len; + } + + return assigned_slave; +} + +/* Caller must hold bond lock for read */ +static struct slave *tlb_choose_channel(struct bonding *bond, u32 hash_index, + u32 skb_len) +{ + struct slave *tx_slave; + /* + * We don't need to disable softirq here, becase + * tlb_choose_channel() is only called by bond_alb_xmit() + * which already has softirq disabled. + */ + _lock_tx_hashtbl(bond); + tx_slave = __tlb_choose_channel(bond, hash_index, skb_len); + _unlock_tx_hashtbl(bond); + return tx_slave; +} + +/*********************** rlb specific functions ***************************/ +static inline void _lock_rx_hashtbl_bh(struct bonding *bond) +{ + spin_lock_bh(&(BOND_ALB_INFO(bond).rx_hashtbl_lock)); +} + +static inline void _unlock_rx_hashtbl_bh(struct bonding *bond) +{ + spin_unlock_bh(&(BOND_ALB_INFO(bond).rx_hashtbl_lock)); +} + +static inline void _lock_rx_hashtbl(struct bonding *bond) +{ + spin_lock(&(BOND_ALB_INFO(bond).rx_hashtbl_lock)); +} + +static inline void _unlock_rx_hashtbl(struct bonding *bond) +{ + spin_unlock(&(BOND_ALB_INFO(bond).rx_hashtbl_lock)); +} + +/* when an ARP REPLY is received from a client update its info + * in the rx_hashtbl + */ +static void rlb_update_entry_from_arp(struct bonding *bond, struct arp_pkt *arp) +{ + struct alb_bond_info *bond_info = &(BOND_ALB_INFO(bond)); + struct rlb_client_info *client_info; + u32 hash_index; + + _lock_rx_hashtbl_bh(bond); + + hash_index = _simple_hash((u8*)&(arp->ip_src), sizeof(arp->ip_src)); + client_info = &(bond_info->rx_hashtbl[hash_index]); + + if ((client_info->assigned) && + (client_info->ip_src == arp->ip_dst) && + (client_info->ip_dst == arp->ip_src) && + (compare_ether_addr_64bits(client_info->mac_dst, arp->mac_src))) { + /* update the clients MAC address */ + memcpy(client_info->mac_dst, arp->mac_src, ETH_ALEN); + client_info->ntt = 1; + bond_info->rx_ntt = 1; + } + + _unlock_rx_hashtbl_bh(bond); +} + +static int rlb_arp_recv(struct sk_buff *skb, struct bonding *bond, + struct slave *slave) +{ + struct arp_pkt *arp; + + if (skb->protocol != cpu_to_be16(ETH_P_ARP)) + goto out; + + arp = (struct arp_pkt *) skb->data; + if (!arp) { + pr_debug("Packet has no ARP data\n"); + goto out; + } + + if (!pskb_may_pull(skb, arp_hdr_len(bond->dev))) + goto out; + + if (skb->len < sizeof(struct arp_pkt)) { + pr_debug("Packet is too small to be an ARP\n"); + goto out; + } + + if (arp->op_code == htons(ARPOP_REPLY)) { + /* update rx hash table for this ARP */ + rlb_update_entry_from_arp(bond, arp); + pr_debug("Server received an ARP Reply from client\n"); + } +out: + return RX_HANDLER_ANOTHER; +} + +/* Caller must hold bond lock for read */ +static struct slave *rlb_next_rx_slave(struct bonding *bond) +{ + struct alb_bond_info *bond_info = &(BOND_ALB_INFO(bond)); + struct slave *rx_slave, *slave, *start_at; + int i = 0; + + if (bond_info->next_rx_slave) { + start_at = bond_info->next_rx_slave; + } else { + start_at = bond->first_slave; + } + + rx_slave = NULL; + + bond_for_each_slave_from(bond, slave, i, start_at) { + if (SLAVE_IS_OK(slave)) { + if (!rx_slave) { + rx_slave = slave; + } else if (slave->speed > rx_slave->speed) { + rx_slave = slave; + } + } + } + + if (rx_slave) { + bond_info->next_rx_slave = rx_slave->next; + } + + return rx_slave; +} + +/* teach the switch the mac of a disabled slave + * on the primary for fault tolerance + * + * Caller must hold bond->curr_slave_lock for write or bond lock for write + */ +static void rlb_teach_disabled_mac_on_primary(struct bonding *bond, u8 addr[]) +{ + if (!bond->curr_active_slave) { + return; + } + + if (!bond->alb_info.primary_is_promisc) { + if (!dev_set_promiscuity(bond->curr_active_slave->dev, 1)) + bond->alb_info.primary_is_promisc = 1; + else + bond->alb_info.primary_is_promisc = 0; + } + + bond->alb_info.rlb_promisc_timeout_counter = 0; + + alb_send_learning_packets(bond->curr_active_slave, addr); +} + +/* slave being removed should not be active at this point + * + * Caller must hold bond lock for read + */ +static void rlb_clear_slave(struct bonding *bond, struct slave *slave) +{ + struct alb_bond_info *bond_info = &(BOND_ALB_INFO(bond)); + struct rlb_client_info *rx_hash_table; + u32 index, next_index; + + /* clear slave from rx_hashtbl */ + _lock_rx_hashtbl_bh(bond); + + rx_hash_table = bond_info->rx_hashtbl; + index = bond_info->rx_hashtbl_head; + for (; index != RLB_NULL_INDEX; index = next_index) { + next_index = rx_hash_table[index].next; + if (rx_hash_table[index].slave == slave) { + struct slave *assigned_slave = rlb_next_rx_slave(bond); + + if (assigned_slave) { + rx_hash_table[index].slave = assigned_slave; + if (compare_ether_addr_64bits(rx_hash_table[index].mac_dst, + mac_bcast)) { + bond_info->rx_hashtbl[index].ntt = 1; + bond_info->rx_ntt = 1; + /* A slave has been removed from the + * table because it is either disabled + * or being released. We must retry the + * update to avoid clients from not + * being updated & disconnecting when + * there is stress + */ + bond_info->rlb_update_retry_counter = + RLB_UPDATE_RETRY; + } + } else { /* there is no active slave */ + rx_hash_table[index].slave = NULL; + } + } + } + + _unlock_rx_hashtbl_bh(bond); + + write_lock_bh(&bond->curr_slave_lock); + + if (slave != bond->curr_active_slave) { + rlb_teach_disabled_mac_on_primary(bond, slave->dev->dev_addr); + } + + write_unlock_bh(&bond->curr_slave_lock); +} + +static void rlb_update_client(struct rlb_client_info *client_info) +{ + int i; + + if (!client_info->slave) { + return; + } + + for (i = 0; i < RLB_ARP_BURST_SIZE; i++) { + struct sk_buff *skb; + + skb = arp_create(ARPOP_REPLY, ETH_P_ARP, + client_info->ip_dst, + client_info->slave->dev, + client_info->ip_src, + client_info->mac_dst, + client_info->slave->dev->dev_addr, + client_info->mac_dst); + if (!skb) { + pr_err("%s: Error: failed to create an ARP packet\n", + client_info->slave->dev->master->name); + continue; + } + + skb->dev = client_info->slave->dev; + + if (client_info->tag) { + skb = vlan_put_tag(skb, client_info->vlan_id); + if (!skb) { + pr_err("%s: Error: failed to insert VLAN tag\n", + client_info->slave->dev->master->name); + continue; + } + } + + arp_xmit(skb); + } +} + +/* sends ARP REPLIES that update the clients that need updating */ +static void rlb_update_rx_clients(struct bonding *bond) +{ + struct alb_bond_info *bond_info = &(BOND_ALB_INFO(bond)); + struct rlb_client_info *client_info; + u32 hash_index; + + _lock_rx_hashtbl_bh(bond); + + hash_index = bond_info->rx_hashtbl_head; + for (; hash_index != RLB_NULL_INDEX; hash_index = client_info->next) { + client_info = &(bond_info->rx_hashtbl[hash_index]); + if (client_info->ntt) { + rlb_update_client(client_info); + if (bond_info->rlb_update_retry_counter == 0) { + client_info->ntt = 0; + } + } + } + + /* do not update the entries again until this counter is zero so that + * not to confuse the clients. + */ + bond_info->rlb_update_delay_counter = RLB_UPDATE_DELAY; + + _unlock_rx_hashtbl_bh(bond); +} + +/* The slave was assigned a new mac address - update the clients */ +static void rlb_req_update_slave_clients(struct bonding *bond, struct slave *slave) +{ + struct alb_bond_info *bond_info = &(BOND_ALB_INFO(bond)); + struct rlb_client_info *client_info; + int ntt = 0; + u32 hash_index; + + _lock_rx_hashtbl_bh(bond); + + hash_index = bond_info->rx_hashtbl_head; + for (; hash_index != RLB_NULL_INDEX; hash_index = client_info->next) { + client_info = &(bond_info->rx_hashtbl[hash_index]); + + if ((client_info->slave == slave) && + compare_ether_addr_64bits(client_info->mac_dst, mac_bcast)) { + client_info->ntt = 1; + ntt = 1; + } + } + + // update the team's flag only after the whole iteration + if (ntt) { + bond_info->rx_ntt = 1; + //fasten the change + bond_info->rlb_update_retry_counter = RLB_UPDATE_RETRY; + } + + _unlock_rx_hashtbl_bh(bond); +} + +/* mark all clients using src_ip to be updated */ +static void rlb_req_update_subnet_clients(struct bonding *bond, __be32 src_ip) +{ + struct alb_bond_info *bond_info = &(BOND_ALB_INFO(bond)); + struct rlb_client_info *client_info; + u32 hash_index; + + _lock_rx_hashtbl(bond); + + hash_index = bond_info->rx_hashtbl_head; + for (; hash_index != RLB_NULL_INDEX; hash_index = client_info->next) { + client_info = &(bond_info->rx_hashtbl[hash_index]); + + if (!client_info->slave) { + pr_err("%s: Error: found a client with no channel in the client's hash table\n", + bond->dev->name); + continue; + } + /*update all clients using this src_ip, that are not assigned + * to the team's address (curr_active_slave) and have a known + * unicast mac address. + */ + if ((client_info->ip_src == src_ip) && + compare_ether_addr_64bits(client_info->slave->dev->dev_addr, + bond->dev->dev_addr) && + compare_ether_addr_64bits(client_info->mac_dst, mac_bcast)) { + client_info->ntt = 1; + bond_info->rx_ntt = 1; + } + } + + _unlock_rx_hashtbl(bond); +} + +/* Caller must hold both bond and ptr locks for read */ +static struct slave *rlb_choose_channel(struct sk_buff *skb, struct bonding *bond) +{ + struct alb_bond_info *bond_info = &(BOND_ALB_INFO(bond)); + struct arp_pkt *arp = arp_pkt(skb); + struct slave *assigned_slave; + struct rlb_client_info *client_info; + u32 hash_index = 0; + + _lock_rx_hashtbl(bond); + + hash_index = _simple_hash((u8 *)&arp->ip_dst, sizeof(arp->ip_dst)); + client_info = &(bond_info->rx_hashtbl[hash_index]); + + if (client_info->assigned) { + if ((client_info->ip_src == arp->ip_src) && + (client_info->ip_dst == arp->ip_dst)) { + /* the entry is already assigned to this client */ + if (compare_ether_addr_64bits(arp->mac_dst, mac_bcast)) { + /* update mac address from arp */ + memcpy(client_info->mac_dst, arp->mac_dst, ETH_ALEN); + } + + assigned_slave = client_info->slave; + if (assigned_slave) { + _unlock_rx_hashtbl(bond); + return assigned_slave; + } + } else { + /* the entry is already assigned to some other client, + * move the old client to primary (curr_active_slave) so + * that the new client can be assigned to this entry. + */ + if (bond->curr_active_slave && + client_info->slave != bond->curr_active_slave) { + client_info->slave = bond->curr_active_slave; + rlb_update_client(client_info); + } + } + } + /* assign a new slave */ + assigned_slave = rlb_next_rx_slave(bond); + + if (assigned_slave) { + client_info->ip_src = arp->ip_src; + client_info->ip_dst = arp->ip_dst; + /* arp->mac_dst is broadcast for arp reqeusts. + * will be updated with clients actual unicast mac address + * upon receiving an arp reply. + */ + memcpy(client_info->mac_dst, arp->mac_dst, ETH_ALEN); + client_info->slave = assigned_slave; + + if (compare_ether_addr_64bits(client_info->mac_dst, mac_bcast)) { + client_info->ntt = 1; + bond->alb_info.rx_ntt = 1; + } else { + client_info->ntt = 0; + } + + if (bond_vlan_used(bond)) { + if (!vlan_get_tag(skb, &client_info->vlan_id)) + client_info->tag = 1; + } + + if (!client_info->assigned) { + u32 prev_tbl_head = bond_info->rx_hashtbl_head; + bond_info->rx_hashtbl_head = hash_index; + client_info->next = prev_tbl_head; + if (prev_tbl_head != RLB_NULL_INDEX) { + bond_info->rx_hashtbl[prev_tbl_head].prev = + hash_index; + } + client_info->assigned = 1; + } + } + + _unlock_rx_hashtbl(bond); + + return assigned_slave; +} + +/* chooses (and returns) transmit channel for arp reply + * does not choose channel for other arp types since they are + * sent on the curr_active_slave + */ +static struct slave *rlb_arp_xmit(struct sk_buff *skb, struct bonding *bond) +{ + struct arp_pkt *arp = arp_pkt(skb); + struct slave *tx_slave = NULL; + + if (arp->op_code == htons(ARPOP_REPLY)) { + /* the arp must be sent on the selected + * rx channel + */ + tx_slave = rlb_choose_channel(skb, bond); + if (tx_slave) { + memcpy(arp->mac_src,tx_slave->dev->dev_addr, ETH_ALEN); + } + pr_debug("Server sent ARP Reply packet\n"); + } else if (arp->op_code == htons(ARPOP_REQUEST)) { + /* Create an entry in the rx_hashtbl for this client as a + * place holder. + * When the arp reply is received the entry will be updated + * with the correct unicast address of the client. + */ + rlb_choose_channel(skb, bond); + + /* The ARP reply packets must be delayed so that + * they can cancel out the influence of the ARP request. + */ + bond->alb_info.rlb_update_delay_counter = RLB_UPDATE_DELAY; + + /* arp requests are broadcast and are sent on the primary + * the arp request will collapse all clients on the subnet to + * the primary slave. We must register these clients to be + * updated with their assigned mac. + */ + rlb_req_update_subnet_clients(bond, arp->ip_src); + pr_debug("Server sent ARP Request packet\n"); + } + + return tx_slave; +} + +/* Caller must hold bond lock for read */ +static void rlb_rebalance(struct bonding *bond) +{ + struct alb_bond_info *bond_info = &(BOND_ALB_INFO(bond)); + struct slave *assigned_slave; + struct rlb_client_info *client_info; + int ntt; + u32 hash_index; + + _lock_rx_hashtbl_bh(bond); + + ntt = 0; + hash_index = bond_info->rx_hashtbl_head; + for (; hash_index != RLB_NULL_INDEX; hash_index = client_info->next) { + client_info = &(bond_info->rx_hashtbl[hash_index]); + assigned_slave = rlb_next_rx_slave(bond); + if (assigned_slave && (client_info->slave != assigned_slave)) { + client_info->slave = assigned_slave; + client_info->ntt = 1; + ntt = 1; + } + } + + /* update the team's flag only after the whole iteration */ + if (ntt) { + bond_info->rx_ntt = 1; + } + _unlock_rx_hashtbl_bh(bond); +} + +/* Caller must hold rx_hashtbl lock */ +static void rlb_init_table_entry(struct rlb_client_info *entry) +{ + memset(entry, 0, sizeof(struct rlb_client_info)); + entry->next = RLB_NULL_INDEX; + entry->prev = RLB_NULL_INDEX; +} + +static int rlb_initialize(struct bonding *bond) +{ + struct alb_bond_info *bond_info = &(BOND_ALB_INFO(bond)); + struct rlb_client_info *new_hashtbl; + int size = RLB_HASH_TABLE_SIZE * sizeof(struct rlb_client_info); + int i; + + new_hashtbl = kmalloc(size, GFP_KERNEL); + if (!new_hashtbl) + return -1; + + _lock_rx_hashtbl_bh(bond); + + bond_info->rx_hashtbl = new_hashtbl; + + bond_info->rx_hashtbl_head = RLB_NULL_INDEX; + + for (i = 0; i < RLB_HASH_TABLE_SIZE; i++) { + rlb_init_table_entry(bond_info->rx_hashtbl + i); + } + + _unlock_rx_hashtbl_bh(bond); + + /* register to receive ARPs */ + bond->recv_probe = rlb_arp_recv; + + return 0; +} + +static void rlb_deinitialize(struct bonding *bond) +{ + struct alb_bond_info *bond_info = &(BOND_ALB_INFO(bond)); + + _lock_rx_hashtbl_bh(bond); + + kfree(bond_info->rx_hashtbl); + bond_info->rx_hashtbl = NULL; + bond_info->rx_hashtbl_head = RLB_NULL_INDEX; + + _unlock_rx_hashtbl_bh(bond); +} + +static void rlb_clear_vlan(struct bonding *bond, unsigned short vlan_id) +{ + struct alb_bond_info *bond_info = &(BOND_ALB_INFO(bond)); + u32 curr_index; + + _lock_rx_hashtbl_bh(bond); + + curr_index = bond_info->rx_hashtbl_head; + while (curr_index != RLB_NULL_INDEX) { + struct rlb_client_info *curr = &(bond_info->rx_hashtbl[curr_index]); + u32 next_index = bond_info->rx_hashtbl[curr_index].next; + u32 prev_index = bond_info->rx_hashtbl[curr_index].prev; + + if (curr->tag && (curr->vlan_id == vlan_id)) { + if (curr_index == bond_info->rx_hashtbl_head) { + bond_info->rx_hashtbl_head = next_index; + } + if (prev_index != RLB_NULL_INDEX) { + bond_info->rx_hashtbl[prev_index].next = next_index; + } + if (next_index != RLB_NULL_INDEX) { + bond_info->rx_hashtbl[next_index].prev = prev_index; + } + + rlb_init_table_entry(curr); + } + + curr_index = next_index; + } + + _unlock_rx_hashtbl_bh(bond); +} + +/*********************** tlb/rlb shared functions *********************/ + +static void alb_send_learning_packets(struct slave *slave, u8 mac_addr[]) +{ + struct bonding *bond = bond_get_bond_by_slave(slave); + struct learning_pkt pkt; + int size = sizeof(struct learning_pkt); + int i; + + memset(&pkt, 0, size); + memcpy(pkt.mac_dst, mac_addr, ETH_ALEN); + memcpy(pkt.mac_src, mac_addr, ETH_ALEN); + pkt.type = cpu_to_be16(ETH_P_LOOP); + + for (i = 0; i < MAX_LP_BURST; i++) { + struct sk_buff *skb; + char *data; + + skb = dev_alloc_skb(size); + if (!skb) { + return; + } + + data = skb_put(skb, size); + memcpy(data, &pkt, size); + + skb_reset_mac_header(skb); + skb->network_header = skb->mac_header + ETH_HLEN; + skb->protocol = pkt.type; + skb->priority = TC_PRIO_CONTROL; + skb->dev = slave->dev; + + if (bond_vlan_used(bond)) { + struct vlan_entry *vlan; + + vlan = bond_next_vlan(bond, + bond->alb_info.current_alb_vlan); + + bond->alb_info.current_alb_vlan = vlan; + if (!vlan) { + kfree_skb(skb); + continue; + } + + skb = vlan_put_tag(skb, vlan->vlan_id); + if (!skb) { + pr_err("%s: Error: failed to insert VLAN tag\n", + bond->dev->name); + continue; + } + } + + dev_queue_xmit(skb); + } +} + +static int alb_set_slave_mac_addr(struct slave *slave, u8 addr[]) +{ + struct net_device *dev = slave->dev; + struct sockaddr s_addr; + + if (slave->bond->params.mode == BOND_MODE_TLB) { + memcpy(dev->dev_addr, addr, dev->addr_len); + return 0; + } + + /* for rlb each slave must have a unique hw mac addresses so that */ + /* each slave will receive packets destined to a different mac */ + memcpy(s_addr.sa_data, addr, dev->addr_len); + s_addr.sa_family = dev->type; + if (dev_set_mac_address(dev, &s_addr)) { + pr_err("%s: Error: dev_set_mac_address of dev %s failed!\n" + "ALB mode requires that the base driver support setting the hw address also when the network device's interface is open\n", + dev->master->name, dev->name); + return -EOPNOTSUPP; + } + return 0; +} + +/* + * Swap MAC addresses between two slaves. + * + * Called with RTNL held, and no other locks. + * + */ + +static void alb_swap_mac_addr(struct bonding *bond, struct slave *slave1, struct slave *slave2) +{ + u8 tmp_mac_addr[ETH_ALEN]; + + memcpy(tmp_mac_addr, slave1->dev->dev_addr, ETH_ALEN); + alb_set_slave_mac_addr(slave1, slave2->dev->dev_addr); + alb_set_slave_mac_addr(slave2, tmp_mac_addr); + +} + +/* + * Send learning packets after MAC address swap. + * + * Called with RTNL and no other locks + */ +static void alb_fasten_mac_swap(struct bonding *bond, struct slave *slave1, + struct slave *slave2) +{ + int slaves_state_differ = (SLAVE_IS_OK(slave1) != SLAVE_IS_OK(slave2)); + struct slave *disabled_slave = NULL; + + ASSERT_RTNL(); + + /* fasten the change in the switch */ + if (SLAVE_IS_OK(slave1)) { + alb_send_learning_packets(slave1, slave1->dev->dev_addr); + if (bond->alb_info.rlb_enabled) { + /* inform the clients that the mac address + * has changed + */ + rlb_req_update_slave_clients(bond, slave1); + } + } else { + disabled_slave = slave1; + } + + if (SLAVE_IS_OK(slave2)) { + alb_send_learning_packets(slave2, slave2->dev->dev_addr); + if (bond->alb_info.rlb_enabled) { + /* inform the clients that the mac address + * has changed + */ + rlb_req_update_slave_clients(bond, slave2); + } + } else { + disabled_slave = slave2; + } + + if (bond->alb_info.rlb_enabled && slaves_state_differ) { + /* A disabled slave was assigned an active mac addr */ + rlb_teach_disabled_mac_on_primary(bond, + disabled_slave->dev->dev_addr); + } +} + +/** + * alb_change_hw_addr_on_detach + * @bond: bonding we're working on + * @slave: the slave that was just detached + * + * We assume that @slave was already detached from the slave list. + * + * If @slave's permanent hw address is different both from its current + * address and from @bond's address, then somewhere in the bond there's + * a slave that has @slave's permanet address as its current address. + * We'll make sure that that slave no longer uses @slave's permanent address. + * + * Caller must hold RTNL and no other locks + */ +static void alb_change_hw_addr_on_detach(struct bonding *bond, struct slave *slave) +{ + int perm_curr_diff; + int perm_bond_diff; + + perm_curr_diff = compare_ether_addr_64bits(slave->perm_hwaddr, + slave->dev->dev_addr); + perm_bond_diff = compare_ether_addr_64bits(slave->perm_hwaddr, + bond->dev->dev_addr); + + if (perm_curr_diff && perm_bond_diff) { + struct slave *tmp_slave; + int i, found = 0; + + bond_for_each_slave(bond, tmp_slave, i) { + if (!compare_ether_addr_64bits(slave->perm_hwaddr, + tmp_slave->dev->dev_addr)) { + found = 1; + break; + } + } + + if (found) { + /* locking: needs RTNL and nothing else */ + alb_swap_mac_addr(bond, slave, tmp_slave); + alb_fasten_mac_swap(bond, slave, tmp_slave); + } + } +} + +/** + * alb_handle_addr_collision_on_attach + * @bond: bonding we're working on + * @slave: the slave that was just attached + * + * checks uniqueness of slave's mac address and handles the case the + * new slave uses the bonds mac address. + * + * If the permanent hw address of @slave is @bond's hw address, we need to + * find a different hw address to give @slave, that isn't in use by any other + * slave in the bond. This address must be, of course, one of the permanent + * addresses of the other slaves. + * + * We go over the slave list, and for each slave there we compare its + * permanent hw address with the current address of all the other slaves. + * If no match was found, then we've found a slave with a permanent address + * that isn't used by any other slave in the bond, so we can assign it to + * @slave. + * + * assumption: this function is called before @slave is attached to the + * bond slave list. + * + * caller must hold the bond lock for write since the mac addresses are compared + * and may be swapped. + */ +static int alb_handle_addr_collision_on_attach(struct bonding *bond, struct slave *slave) +{ + struct slave *tmp_slave1, *tmp_slave2, *free_mac_slave; + struct slave *has_bond_addr = bond->curr_active_slave; + int i, j, found = 0; + + if (bond->slave_cnt == 0) { + /* this is the first slave */ + return 0; + } + + /* if slave's mac address differs from bond's mac address + * check uniqueness of slave's mac address against the other + * slaves in the bond. + */ + if (compare_ether_addr_64bits(slave->perm_hwaddr, bond->dev->dev_addr)) { + bond_for_each_slave(bond, tmp_slave1, i) { + if (!compare_ether_addr_64bits(tmp_slave1->dev->dev_addr, + slave->dev->dev_addr)) { + found = 1; + break; + } + } + + if (!found) + return 0; + + /* Try setting slave mac to bond address and fall-through + to code handling that situation below... */ + alb_set_slave_mac_addr(slave, bond->dev->dev_addr); + } + + /* The slave's address is equal to the address of the bond. + * Search for a spare address in the bond for this slave. + */ + free_mac_slave = NULL; + + bond_for_each_slave(bond, tmp_slave1, i) { + found = 0; + bond_for_each_slave(bond, tmp_slave2, j) { + if (!compare_ether_addr_64bits(tmp_slave1->perm_hwaddr, + tmp_slave2->dev->dev_addr)) { + found = 1; + break; + } + } + + if (!found) { + /* no slave has tmp_slave1's perm addr + * as its curr addr + */ + free_mac_slave = tmp_slave1; + break; + } + + if (!has_bond_addr) { + if (!compare_ether_addr_64bits(tmp_slave1->dev->dev_addr, + bond->dev->dev_addr)) { + + has_bond_addr = tmp_slave1; + } + } + } + + if (free_mac_slave) { + alb_set_slave_mac_addr(slave, free_mac_slave->perm_hwaddr); + + pr_warning("%s: Warning: the hw address of slave %s is in use by the bond; giving it the hw address of %s\n", + bond->dev->name, slave->dev->name, + free_mac_slave->dev->name); + + } else if (has_bond_addr) { + pr_err("%s: Error: the hw address of slave %s is in use by the bond; couldn't find a slave with a free hw address to give it (this should not have happened)\n", + bond->dev->name, slave->dev->name); + return -EFAULT; + } + + return 0; +} + +/** + * alb_set_mac_address + * @bond: + * @addr: + * + * In TLB mode all slaves are configured to the bond's hw address, but set + * their dev_addr field to different addresses (based on their permanent hw + * addresses). + * + * For each slave, this function sets the interface to the new address and then + * changes its dev_addr field to its previous value. + * + * Unwinding assumes bond's mac address has not yet changed. + */ +static int alb_set_mac_address(struct bonding *bond, void *addr) +{ + struct sockaddr sa; + struct slave *slave, *stop_at; + char tmp_addr[ETH_ALEN]; + int res; + int i; + + if (bond->alb_info.rlb_enabled) { + return 0; + } + + bond_for_each_slave(bond, slave, i) { + /* save net_device's current hw address */ + memcpy(tmp_addr, slave->dev->dev_addr, ETH_ALEN); + + res = dev_set_mac_address(slave->dev, addr); + + /* restore net_device's hw address */ + memcpy(slave->dev->dev_addr, tmp_addr, ETH_ALEN); + + if (res) + goto unwind; + } + + return 0; + +unwind: + memcpy(sa.sa_data, bond->dev->dev_addr, bond->dev->addr_len); + sa.sa_family = bond->dev->type; + + /* unwind from head to the slave that failed */ + stop_at = slave; + bond_for_each_slave_from_to(bond, slave, i, bond->first_slave, stop_at) { + memcpy(tmp_addr, slave->dev->dev_addr, ETH_ALEN); + dev_set_mac_address(slave->dev, &sa); + memcpy(slave->dev->dev_addr, tmp_addr, ETH_ALEN); + } + + return res; +} + +/************************ exported alb funcions ************************/ + +int bond_alb_initialize(struct bonding *bond, int rlb_enabled) +{ + int res; + + res = tlb_initialize(bond); + if (res) { + return res; + } + + if (rlb_enabled) { + bond->alb_info.rlb_enabled = 1; + /* initialize rlb */ + res = rlb_initialize(bond); + if (res) { + tlb_deinitialize(bond); + return res; + } + } else { + bond->alb_info.rlb_enabled = 0; + } + + return 0; +} + +void bond_alb_deinitialize(struct bonding *bond) +{ + struct alb_bond_info *bond_info = &(BOND_ALB_INFO(bond)); + + tlb_deinitialize(bond); + + if (bond_info->rlb_enabled) { + rlb_deinitialize(bond); + } +} + +int bond_alb_xmit(struct sk_buff *skb, struct net_device *bond_dev) +{ + struct bonding *bond = netdev_priv(bond_dev); + struct ethhdr *eth_data; + struct alb_bond_info *bond_info = &(BOND_ALB_INFO(bond)); + struct slave *tx_slave = NULL; + static const __be32 ip_bcast = htonl(0xffffffff); + int hash_size = 0; + int do_tx_balance = 1; + u32 hash_index = 0; + const u8 *hash_start = NULL; + int res = 1; + struct ipv6hdr *ip6hdr; + + skb_reset_mac_header(skb); + eth_data = eth_hdr(skb); + + /* make sure that the curr_active_slave do not change during tx + */ + read_lock(&bond->curr_slave_lock); + + switch (ntohs(skb->protocol)) { + case ETH_P_IP: { + const struct iphdr *iph = ip_hdr(skb); + + if (!compare_ether_addr_64bits(eth_data->h_dest, mac_bcast) || + (iph->daddr == ip_bcast) || + (iph->protocol == IPPROTO_IGMP)) { + do_tx_balance = 0; + break; + } + hash_start = (char *)&(iph->daddr); + hash_size = sizeof(iph->daddr); + } + break; + case ETH_P_IPV6: + /* IPv6 doesn't really use broadcast mac address, but leave + * that here just in case. + */ + if (!compare_ether_addr_64bits(eth_data->h_dest, mac_bcast)) { + do_tx_balance = 0; + break; + } + + /* IPv6 uses all-nodes multicast as an equivalent to + * broadcasts in IPv4. + */ + if (!compare_ether_addr_64bits(eth_data->h_dest, mac_v6_allmcast)) { + do_tx_balance = 0; + break; + } + + /* Additianally, DAD probes should not be tx-balanced as that + * will lead to false positives for duplicate addresses and + * prevent address configuration from working. + */ + ip6hdr = ipv6_hdr(skb); + if (ipv6_addr_any(&ip6hdr->saddr)) { + do_tx_balance = 0; + break; + } + + hash_start = (char *)&(ipv6_hdr(skb)->daddr); + hash_size = sizeof(ipv6_hdr(skb)->daddr); + break; + case ETH_P_IPX: + if (ipx_hdr(skb)->ipx_checksum != IPX_NO_CHECKSUM) { + /* something is wrong with this packet */ + do_tx_balance = 0; + break; + } + + if (ipx_hdr(skb)->ipx_type != IPX_TYPE_NCP) { + /* The only protocol worth balancing in + * this family since it has an "ARP" like + * mechanism + */ + do_tx_balance = 0; + break; + } + + hash_start = (char*)eth_data->h_dest; + hash_size = ETH_ALEN; + break; + case ETH_P_ARP: + do_tx_balance = 0; + if (bond_info->rlb_enabled) { + tx_slave = rlb_arp_xmit(skb, bond); + } + break; + default: + do_tx_balance = 0; + break; + } + + if (do_tx_balance) { + hash_index = _simple_hash(hash_start, hash_size); + tx_slave = tlb_choose_channel(bond, hash_index, skb->len); + } + + if (!tx_slave) { + /* unbalanced or unassigned, send through primary */ + tx_slave = bond->curr_active_slave; + bond_info->unbalanced_load += skb->len; + } + + if (tx_slave && SLAVE_IS_OK(tx_slave)) { + if (tx_slave != bond->curr_active_slave) { + memcpy(eth_data->h_source, + tx_slave->dev->dev_addr, + ETH_ALEN); + } + + res = bond_dev_queue_xmit(bond, skb, tx_slave->dev); + } else { + if (tx_slave) { + _lock_tx_hashtbl(bond); + __tlb_clear_slave(bond, tx_slave, 0); + _unlock_tx_hashtbl(bond); + } + } + + if (res) { + /* no suitable interface, frame not sent */ + dev_kfree_skb(skb); + } + read_unlock(&bond->curr_slave_lock); + + return NETDEV_TX_OK; +} + +void bond_alb_monitor(struct work_struct *work) +{ + struct bonding *bond = container_of(work, struct bonding, + alb_work.work); + struct alb_bond_info *bond_info = &(BOND_ALB_INFO(bond)); + struct slave *slave; + int i; + + read_lock(&bond->lock); + + if (bond->slave_cnt == 0) { + bond_info->tx_rebalance_counter = 0; + bond_info->lp_counter = 0; + goto re_arm; + } + + bond_info->tx_rebalance_counter++; + bond_info->lp_counter++; + + /* send learning packets */ + if (bond_info->lp_counter >= BOND_ALB_LP_TICKS) { + /* change of curr_active_slave involves swapping of mac addresses. + * in order to avoid this swapping from happening while + * sending the learning packets, the curr_slave_lock must be held for + * read. + */ + read_lock(&bond->curr_slave_lock); + + bond_for_each_slave(bond, slave, i) { + alb_send_learning_packets(slave, slave->dev->dev_addr); + } + + read_unlock(&bond->curr_slave_lock); + + bond_info->lp_counter = 0; + } + + /* rebalance tx traffic */ + if (bond_info->tx_rebalance_counter >= BOND_TLB_REBALANCE_TICKS) { + + read_lock(&bond->curr_slave_lock); + + bond_for_each_slave(bond, slave, i) { + tlb_clear_slave(bond, slave, 1); + if (slave == bond->curr_active_slave) { + SLAVE_TLB_INFO(slave).load = + bond_info->unbalanced_load / + BOND_TLB_REBALANCE_INTERVAL; + bond_info->unbalanced_load = 0; + } + } + + read_unlock(&bond->curr_slave_lock); + + bond_info->tx_rebalance_counter = 0; + } + + /* handle rlb stuff */ + if (bond_info->rlb_enabled) { + if (bond_info->primary_is_promisc && + (++bond_info->rlb_promisc_timeout_counter >= RLB_PROMISC_TIMEOUT)) { + + /* + * dev_set_promiscuity requires rtnl and + * nothing else. Avoid race with bond_close. + */ + read_unlock(&bond->lock); + if (!rtnl_trylock()) { + read_lock(&bond->lock); + goto re_arm; + } + + bond_info->rlb_promisc_timeout_counter = 0; + + /* If the primary was set to promiscuous mode + * because a slave was disabled then + * it can now leave promiscuous mode. + */ + dev_set_promiscuity(bond->curr_active_slave->dev, -1); + bond_info->primary_is_promisc = 0; + + rtnl_unlock(); + read_lock(&bond->lock); + } + + if (bond_info->rlb_rebalance) { + bond_info->rlb_rebalance = 0; + rlb_rebalance(bond); + } + + /* check if clients need updating */ + if (bond_info->rx_ntt) { + if (bond_info->rlb_update_delay_counter) { + --bond_info->rlb_update_delay_counter; + } else { + rlb_update_rx_clients(bond); + if (bond_info->rlb_update_retry_counter) { + --bond_info->rlb_update_retry_counter; + } else { + bond_info->rx_ntt = 0; + } + } + } + } + +re_arm: + queue_delayed_work(bond->wq, &bond->alb_work, alb_delta_in_ticks); + + read_unlock(&bond->lock); +} + +/* assumption: called before the slave is attached to the bond + * and not locked by the bond lock + */ +int bond_alb_init_slave(struct bonding *bond, struct slave *slave) +{ + int res; + + res = alb_set_slave_mac_addr(slave, slave->perm_hwaddr); + if (res) { + return res; + } + + /* caller must hold the bond lock for write since the mac addresses + * are compared and may be swapped. + */ + read_lock(&bond->lock); + + res = alb_handle_addr_collision_on_attach(bond, slave); + + read_unlock(&bond->lock); + + if (res) { + return res; + } + + tlb_init_slave(slave); + + /* order a rebalance ASAP */ + bond->alb_info.tx_rebalance_counter = BOND_TLB_REBALANCE_TICKS; + + if (bond->alb_info.rlb_enabled) { + bond->alb_info.rlb_rebalance = 1; + } + + return 0; +} + +/* + * Remove slave from tlb and rlb hash tables, and fix up MAC addresses + * if necessary. + * + * Caller must hold RTNL and no other locks + */ +void bond_alb_deinit_slave(struct bonding *bond, struct slave *slave) +{ + if (bond->slave_cnt > 1) { + alb_change_hw_addr_on_detach(bond, slave); + } + + tlb_clear_slave(bond, slave, 0); + + if (bond->alb_info.rlb_enabled) { + bond->alb_info.next_rx_slave = NULL; + rlb_clear_slave(bond, slave); + } +} + +/* Caller must hold bond lock for read */ +void bond_alb_handle_link_change(struct bonding *bond, struct slave *slave, char link) +{ + struct alb_bond_info *bond_info = &(BOND_ALB_INFO(bond)); + + if (link == BOND_LINK_DOWN) { + tlb_clear_slave(bond, slave, 0); + if (bond->alb_info.rlb_enabled) { + rlb_clear_slave(bond, slave); + } + } else if (link == BOND_LINK_UP) { + /* order a rebalance ASAP */ + bond_info->tx_rebalance_counter = BOND_TLB_REBALANCE_TICKS; + if (bond->alb_info.rlb_enabled) { + bond->alb_info.rlb_rebalance = 1; + /* If the updelay module parameter is smaller than the + * forwarding delay of the switch the rebalance will + * not work because the rebalance arp replies will + * not be forwarded to the clients.. + */ + } + } +} + +/** + * bond_alb_handle_active_change - assign new curr_active_slave + * @bond: our bonding struct + * @new_slave: new slave to assign + * + * Set the bond->curr_active_slave to @new_slave and handle + * mac address swapping and promiscuity changes as needed. + * + * If new_slave is NULL, caller must hold curr_slave_lock or + * bond->lock for write. + * + * If new_slave is not NULL, caller must hold RTNL, bond->lock for + * read and curr_slave_lock for write. Processing here may sleep, so + * no other locks may be held. + */ +void bond_alb_handle_active_change(struct bonding *bond, struct slave *new_slave) + __releases(&bond->curr_slave_lock) + __releases(&bond->lock) + __acquires(&bond->lock) + __acquires(&bond->curr_slave_lock) +{ + struct slave *swap_slave; + int i; + + if (bond->curr_active_slave == new_slave) { + return; + } + + if (bond->curr_active_slave && bond->alb_info.primary_is_promisc) { + dev_set_promiscuity(bond->curr_active_slave->dev, -1); + bond->alb_info.primary_is_promisc = 0; + bond->alb_info.rlb_promisc_timeout_counter = 0; + } + + swap_slave = bond->curr_active_slave; + bond->curr_active_slave = new_slave; + + if (!new_slave || (bond->slave_cnt == 0)) { + return; + } + + /* set the new curr_active_slave to the bonds mac address + * i.e. swap mac addresses of old curr_active_slave and new curr_active_slave + */ + if (!swap_slave) { + struct slave *tmp_slave; + /* find slave that is holding the bond's mac address */ + bond_for_each_slave(bond, tmp_slave, i) { + if (!compare_ether_addr_64bits(tmp_slave->dev->dev_addr, + bond->dev->dev_addr)) { + swap_slave = tmp_slave; + break; + } + } + } + + /* + * Arrange for swap_slave and new_slave to temporarily be + * ignored so we can mess with their MAC addresses without + * fear of interference from transmit activity. + */ + if (swap_slave) { + tlb_clear_slave(bond, swap_slave, 1); + } + tlb_clear_slave(bond, new_slave, 1); + + write_unlock_bh(&bond->curr_slave_lock); + read_unlock(&bond->lock); + + ASSERT_RTNL(); + + /* curr_active_slave must be set before calling alb_swap_mac_addr */ + if (swap_slave) { + /* swap mac address */ + alb_swap_mac_addr(bond, swap_slave, new_slave); + } else { + /* set the new_slave to the bond mac address */ + alb_set_slave_mac_addr(new_slave, bond->dev->dev_addr); + } + + if (swap_slave) { + alb_fasten_mac_swap(bond, swap_slave, new_slave); + read_lock(&bond->lock); + } else { + read_lock(&bond->lock); + alb_send_learning_packets(new_slave, bond->dev->dev_addr); + } + + write_lock_bh(&bond->curr_slave_lock); +} + +/* + * Called with RTNL + */ +int bond_alb_set_mac_address(struct net_device *bond_dev, void *addr) + __acquires(&bond->lock) + __releases(&bond->lock) +{ + struct bonding *bond = netdev_priv(bond_dev); + struct sockaddr *sa = addr; + struct slave *slave, *swap_slave; + int res; + int i; + + if (!is_valid_ether_addr(sa->sa_data)) { + return -EADDRNOTAVAIL; + } + + res = alb_set_mac_address(bond, addr); + if (res) { + return res; + } + + memcpy(bond_dev->dev_addr, sa->sa_data, bond_dev->addr_len); + + /* If there is no curr_active_slave there is nothing else to do. + * Otherwise we'll need to pass the new address to it and handle + * duplications. + */ + if (!bond->curr_active_slave) { + return 0; + } + + swap_slave = NULL; + + bond_for_each_slave(bond, slave, i) { + if (!compare_ether_addr_64bits(slave->dev->dev_addr, + bond_dev->dev_addr)) { + swap_slave = slave; + break; + } + } + + if (swap_slave) { + alb_swap_mac_addr(bond, swap_slave, bond->curr_active_slave); + alb_fasten_mac_swap(bond, swap_slave, bond->curr_active_slave); + } else { + alb_set_slave_mac_addr(bond->curr_active_slave, bond_dev->dev_addr); + + read_lock(&bond->lock); + alb_send_learning_packets(bond->curr_active_slave, bond_dev->dev_addr); + if (bond->alb_info.rlb_enabled) { + /* inform clients mac address has changed */ + rlb_req_update_slave_clients(bond, bond->curr_active_slave); + } + read_unlock(&bond->lock); + } + + return 0; +} + +void bond_alb_clear_vlan(struct bonding *bond, unsigned short vlan_id) +{ + if (bond->alb_info.current_alb_vlan && + (bond->alb_info.current_alb_vlan->vlan_id == vlan_id)) { + bond->alb_info.current_alb_vlan = NULL; + } + + if (bond->alb_info.rlb_enabled) { + rlb_clear_vlan(bond, vlan_id); + } +} + diff --git a/ANDROID_3.4.5/drivers/net/bonding/bond_alb.h b/ANDROID_3.4.5/drivers/net/bonding/bond_alb.h new file mode 100644 index 00000000..90f140a2 --- /dev/null +++ b/ANDROID_3.4.5/drivers/net/bonding/bond_alb.h @@ -0,0 +1,167 @@ +/* + * 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 __BOND_ALB_H__ +#define __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_LP_INTERVAL 1 /* 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_ALB_LP_INTERVAL \ + * 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 +#define MAX_LP_BURST 3 + +/* 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 + * ------------------------------------------------------------------------- + */ +struct rlb_client_info { + __be32 ip_src; /* the server IP address */ + __be32 ip_dst; /* the client IP address */ + u8 mac_dst[ETH_ALEN]; /* the client MAC address */ + u32 next; /* The next Hash table entry index */ + u32 prev; /* The previous Hash table entry 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 */ + u8 tag; /* flag - need to tag skb */ + 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 */ + spinlock_t tx_hashtbl_lock; + u32 unbalanced_load; + int tx_rebalance_counter; + int lp_counter; + /* -------- rlb parameters -------- */ + int rlb_enabled; + struct rlb_client_info *rx_hashtbl; /* Receive hash table */ + spinlock_t rx_hashtbl_lock; + u32 rx_hashtbl_head; + u8 rx_ntt; /* flag - need to transmit + * to all rx clients + */ + struct slave *next_rx_slave;/* next slave to be assigned + * to a new rx client for + */ + 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 + */ + struct vlan_entry *current_alb_vlan; +}; + +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); +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 /* __BOND_ALB_H__ */ + diff --git a/ANDROID_3.4.5/drivers/net/bonding/bond_debugfs.c b/ANDROID_3.4.5/drivers/net/bonding/bond_debugfs.c new file mode 100644 index 00000000..3680aa25 --- /dev/null +++ b/ANDROID_3.4.5/drivers/net/bonding/bond_debugfs.c @@ -0,0 +1,146 @@ +#include <linux/kernel.h> +#include <linux/module.h> +#include <linux/device.h> +#include <linux/netdevice.h> + +#include "bonding.h" +#include "bond_alb.h" + +#ifdef CONFIG_DEBUG_FS + +#include <linux/debugfs.h> +#include <linux/seq_file.h> + +static struct dentry *bonding_debug_root; + +/* + * Show RLB hash table + */ +static int bond_debug_rlb_hash_show(struct seq_file *m, void *v) +{ + struct bonding *bond = m->private; + struct alb_bond_info *bond_info = &(BOND_ALB_INFO(bond)); + struct rlb_client_info *client_info; + u32 hash_index; + + if (bond->params.mode != BOND_MODE_ALB) + return 0; + + seq_printf(m, "SourceIP DestinationIP " + "Destination MAC DEV\n"); + + spin_lock_bh(&(BOND_ALB_INFO(bond).rx_hashtbl_lock)); + + hash_index = bond_info->rx_hashtbl_head; + for (; hash_index != RLB_NULL_INDEX; hash_index = client_info->next) { + client_info = &(bond_info->rx_hashtbl[hash_index]); + seq_printf(m, "%-15pI4 %-15pI4 %-17pM %s\n", + &client_info->ip_src, + &client_info->ip_dst, + &client_info->mac_dst, + client_info->slave->dev->name); + } + + spin_unlock_bh(&(BOND_ALB_INFO(bond).rx_hashtbl_lock)); + + return 0; +} + +static int bond_debug_rlb_hash_open(struct inode *inode, struct file *file) +{ + return single_open(file, bond_debug_rlb_hash_show, inode->i_private); +} + +static const struct file_operations bond_debug_rlb_hash_fops = { + .owner = THIS_MODULE, + .open = bond_debug_rlb_hash_open, + .read = seq_read, + .llseek = seq_lseek, + .release = single_release, +}; + +void bond_debug_register(struct bonding *bond) +{ + if (!bonding_debug_root) + return; + + bond->debug_dir = + debugfs_create_dir(bond->dev->name, bonding_debug_root); + + if (!bond->debug_dir) { + pr_warning("%s: Warning: failed to register to debugfs\n", + bond->dev->name); + return; + } + + debugfs_create_file("rlb_hash_table", 0400, bond->debug_dir, + bond, &bond_debug_rlb_hash_fops); +} + +void bond_debug_unregister(struct bonding *bond) +{ + if (!bonding_debug_root) + return; + + debugfs_remove_recursive(bond->debug_dir); +} + +void bond_debug_reregister(struct bonding *bond) +{ + struct dentry *d; + + if (!bonding_debug_root) + return; + + d = debugfs_rename(bonding_debug_root, bond->debug_dir, + bonding_debug_root, bond->dev->name); + if (d) { + bond->debug_dir = d; + } else { + pr_warning("%s: Warning: failed to reregister, " + "so just unregister old one\n", + bond->dev->name); + bond_debug_unregister(bond); + } +} + +void bond_create_debugfs(void) +{ + bonding_debug_root = debugfs_create_dir("bonding", NULL); + + if (!bonding_debug_root) { + pr_warning("Warning: Cannot create bonding directory" + " in debugfs\n"); + } +} + +void bond_destroy_debugfs(void) +{ + debugfs_remove_recursive(bonding_debug_root); + bonding_debug_root = NULL; +} + + +#else /* !CONFIG_DEBUG_FS */ + +void bond_debug_register(struct bonding *bond) +{ +} + +void bond_debug_unregister(struct bonding *bond) +{ +} + +void bond_debug_reregister(struct bonding *bond) +{ +} + +void bond_create_debugfs(void) +{ +} + +void bond_destroy_debugfs(void) +{ +} + +#endif /* CONFIG_DEBUG_FS */ diff --git a/ANDROID_3.4.5/drivers/net/bonding/bond_main.c b/ANDROID_3.4.5/drivers/net/bonding/bond_main.c new file mode 100644 index 00000000..a579a2f5 --- /dev/null +++ b/ANDROID_3.4.5/drivers/net/bonding/bond_main.c @@ -0,0 +1,4969 @@ +/* + * originally based on the dummy device. + * + * Copyright 1999, Thomas Davis, tadavis@lbl.gov. + * Licensed under the GPL. Based on dummy.c, and eql.c devices. + * + * bonding.c: an Ethernet Bonding driver + * + * This is useful to talk to a Cisco EtherChannel compatible equipment: + * Cisco 5500 + * Sun Trunking (Solaris) + * Alteon AceDirector Trunks + * Linux Bonding + * and probably many L2 switches ... + * + * How it works: + * ifconfig bond0 ipaddress netmask up + * will setup a network device, with an ip address. No mac address + * will be assigned at this time. The hw mac address will come from + * the first slave bonded to the channel. All slaves will then use + * this hw mac address. + * + * ifconfig bond0 down + * will release all slaves, marking them as down. + * + * ifenslave bond0 eth0 + * will attach eth0 to bond0 as a slave. eth0 hw mac address will either + * a: be used as initial mac address + * b: if a hw mac address already is there, eth0's hw mac address + * will then be set from bond0. + * + */ + +#define pr_fmt(fmt) KBUILD_MODNAME ": " fmt + +#include <linux/kernel.h> +#include <linux/module.h> +#include <linux/types.h> +#include <linux/fcntl.h> +#include <linux/interrupt.h> +#include <linux/ptrace.h> +#include <linux/ioport.h> +#include <linux/in.h> +#include <net/ip.h> +#include <linux/ip.h> +#include <linux/tcp.h> +#include <linux/udp.h> +#include <linux/slab.h> +#include <linux/string.h> +#include <linux/init.h> +#include <linux/timer.h> +#include <linux/socket.h> +#include <linux/ctype.h> +#include <linux/inet.h> +#include <linux/bitops.h> +#include <linux/io.h> +#include <asm/dma.h> +#include <linux/uaccess.h> +#include <linux/errno.h> +#include <linux/netdevice.h> +#include <linux/inetdevice.h> +#include <linux/igmp.h> +#include <linux/etherdevice.h> +#include <linux/skbuff.h> +#include <net/sock.h> +#include <linux/rtnetlink.h> +#include <linux/smp.h> +#include <linux/if_ether.h> +#include <net/arp.h> +#include <linux/mii.h> +#include <linux/ethtool.h> +#include <linux/if_vlan.h> +#include <linux/if_bonding.h> +#include <linux/jiffies.h> +#include <linux/preempt.h> +#include <net/route.h> +#include <net/net_namespace.h> +#include <net/netns/generic.h> +#include <net/pkt_sched.h> +#include "bonding.h" +#include "bond_3ad.h" +#include "bond_alb.h" + +/*---------------------------- Module parameters ----------------------------*/ + +/* monitor all links that often (in milliseconds). <=0 disables monitoring */ +#define BOND_LINK_MON_INTERV 0 +#define BOND_LINK_ARP_INTERV 0 + +static int max_bonds = BOND_DEFAULT_MAX_BONDS; +static int tx_queues = BOND_DEFAULT_TX_QUEUES; +static int num_peer_notif = 1; +static int miimon = BOND_LINK_MON_INTERV; +static int updelay; +static int downdelay; +static int use_carrier = 1; +static char *mode; +static char *primary; +static char *primary_reselect; +static char *lacp_rate; +static int min_links; +static char *ad_select; +static char *xmit_hash_policy; +static int arp_interval = BOND_LINK_ARP_INTERV; +static char *arp_ip_target[BOND_MAX_ARP_TARGETS]; +static char *arp_validate; +static char *fail_over_mac; +static int all_slaves_active = 0; +static struct bond_params bonding_defaults; +static int resend_igmp = BOND_DEFAULT_RESEND_IGMP; + +module_param(max_bonds, int, 0); +MODULE_PARM_DESC(max_bonds, "Max number of bonded devices"); +module_param(tx_queues, int, 0); +MODULE_PARM_DESC(tx_queues, "Max number of transmit queues (default = 16)"); +module_param_named(num_grat_arp, num_peer_notif, int, 0644); +MODULE_PARM_DESC(num_grat_arp, "Number of peer notifications to send on " + "failover event (alias of num_unsol_na)"); +module_param_named(num_unsol_na, num_peer_notif, int, 0644); +MODULE_PARM_DESC(num_unsol_na, "Number of peer notifications to send on " + "failover event (alias of num_grat_arp)"); +module_param(miimon, int, 0); +MODULE_PARM_DESC(miimon, "Link check interval in milliseconds"); +module_param(updelay, int, 0); +MODULE_PARM_DESC(updelay, "Delay before considering link up, in milliseconds"); +module_param(downdelay, int, 0); +MODULE_PARM_DESC(downdelay, "Delay before considering link down, " + "in milliseconds"); +module_param(use_carrier, int, 0); +MODULE_PARM_DESC(use_carrier, "Use netif_carrier_ok (vs MII ioctls) in miimon; " + "0 for off, 1 for on (default)"); +module_param(mode, charp, 0); +MODULE_PARM_DESC(mode, "Mode of operation; 0 for balance-rr, " + "1 for active-backup, 2 for balance-xor, " + "3 for broadcast, 4 for 802.3ad, 5 for balance-tlb, " + "6 for balance-alb"); +module_param(primary, charp, 0); +MODULE_PARM_DESC(primary, "Primary network device to use"); +module_param(primary_reselect, charp, 0); +MODULE_PARM_DESC(primary_reselect, "Reselect primary slave " + "once it comes up; " + "0 for always (default), " + "1 for only if speed of primary is " + "better, " + "2 for only on active slave " + "failure"); +module_param(lacp_rate, charp, 0); +MODULE_PARM_DESC(lacp_rate, "LACPDU tx rate to request from 802.3ad partner; " + "0 for slow, 1 for fast"); +module_param(ad_select, charp, 0); +MODULE_PARM_DESC(ad_select, "803.ad aggregation selection logic; " + "0 for stable (default), 1 for bandwidth, " + "2 for count"); +module_param(min_links, int, 0); +MODULE_PARM_DESC(min_links, "Minimum number of available links before turning on carrier"); + +module_param(xmit_hash_policy, charp, 0); +MODULE_PARM_DESC(xmit_hash_policy, "balance-xor and 802.3ad hashing method; " + "0 for layer 2 (default), 1 for layer 3+4, " + "2 for layer 2+3"); +module_param(arp_interval, int, 0); +MODULE_PARM_DESC(arp_interval, "arp interval in milliseconds"); +module_param_array(arp_ip_target, charp, NULL, 0); +MODULE_PARM_DESC(arp_ip_target, "arp targets in n.n.n.n form"); +module_param(arp_validate, charp, 0); +MODULE_PARM_DESC(arp_validate, "validate src/dst of ARP probes; " + "0 for none (default), 1 for active, " + "2 for backup, 3 for all"); +module_param(fail_over_mac, charp, 0); +MODULE_PARM_DESC(fail_over_mac, "For active-backup, do not set all slaves to " + "the same MAC; 0 for none (default), " + "1 for active, 2 for follow"); +module_param(all_slaves_active, int, 0); +MODULE_PARM_DESC(all_slaves_active, "Keep all frames received on an interface" + "by setting active flag for all slaves; " + "0 for never (default), 1 for always."); +module_param(resend_igmp, int, 0); +MODULE_PARM_DESC(resend_igmp, "Number of IGMP membership reports to send on " + "link failure"); + +/*----------------------------- Global variables ----------------------------*/ + +#ifdef CONFIG_NET_POLL_CONTROLLER +atomic_t netpoll_block_tx = ATOMIC_INIT(0); +#endif + +int bond_net_id __read_mostly; + +static __be32 arp_target[BOND_MAX_ARP_TARGETS]; +static int arp_ip_count; +static int bond_mode = BOND_MODE_ROUNDROBIN; +static int xmit_hashtype = BOND_XMIT_POLICY_LAYER2; +static int lacp_fast; + +const struct bond_parm_tbl bond_lacp_tbl[] = { +{ "slow", AD_LACP_SLOW}, +{ "fast", AD_LACP_FAST}, +{ NULL, -1}, +}; + +const struct bond_parm_tbl bond_mode_tbl[] = { +{ "balance-rr", BOND_MODE_ROUNDROBIN}, +{ "active-backup", BOND_MODE_ACTIVEBACKUP}, +{ "balance-xor", BOND_MODE_XOR}, +{ "broadcast", BOND_MODE_BROADCAST}, +{ "802.3ad", BOND_MODE_8023AD}, +{ "balance-tlb", BOND_MODE_TLB}, +{ "balance-alb", BOND_MODE_ALB}, +{ NULL, -1}, +}; + +const struct bond_parm_tbl xmit_hashtype_tbl[] = { +{ "layer2", BOND_XMIT_POLICY_LAYER2}, +{ "layer3+4", BOND_XMIT_POLICY_LAYER34}, +{ "layer2+3", BOND_XMIT_POLICY_LAYER23}, +{ NULL, -1}, +}; + +const struct bond_parm_tbl arp_validate_tbl[] = { +{ "none", BOND_ARP_VALIDATE_NONE}, +{ "active", BOND_ARP_VALIDATE_ACTIVE}, +{ "backup", BOND_ARP_VALIDATE_BACKUP}, +{ "all", BOND_ARP_VALIDATE_ALL}, +{ NULL, -1}, +}; + +const struct bond_parm_tbl fail_over_mac_tbl[] = { +{ "none", BOND_FOM_NONE}, +{ "active", BOND_FOM_ACTIVE}, +{ "follow", BOND_FOM_FOLLOW}, +{ NULL, -1}, +}; + +const struct bond_parm_tbl pri_reselect_tbl[] = { +{ "always", BOND_PRI_RESELECT_ALWAYS}, +{ "better", BOND_PRI_RESELECT_BETTER}, +{ "failure", BOND_PRI_RESELECT_FAILURE}, +{ NULL, -1}, +}; + +struct bond_parm_tbl ad_select_tbl[] = { +{ "stable", BOND_AD_STABLE}, +{ "bandwidth", BOND_AD_BANDWIDTH}, +{ "count", BOND_AD_COUNT}, +{ NULL, -1}, +}; + +/*-------------------------- Forward declarations ---------------------------*/ + +static int bond_init(struct net_device *bond_dev); +static void bond_uninit(struct net_device *bond_dev); + +/*---------------------------- General routines -----------------------------*/ + +const char *bond_mode_name(int mode) +{ + static const char *names[] = { + [BOND_MODE_ROUNDROBIN] = "load balancing (round-robin)", + [BOND_MODE_ACTIVEBACKUP] = "fault-tolerance (active-backup)", + [BOND_MODE_XOR] = "load balancing (xor)", + [BOND_MODE_BROADCAST] = "fault-tolerance (broadcast)", + [BOND_MODE_8023AD] = "IEEE 802.3ad Dynamic link aggregation", + [BOND_MODE_TLB] = "transmit load balancing", + [BOND_MODE_ALB] = "adaptive load balancing", + }; + + if (mode < 0 || mode > BOND_MODE_ALB) + return "unknown"; + + return names[mode]; +} + +/*---------------------------------- VLAN -----------------------------------*/ + +/** + * bond_add_vlan - add a new vlan id on bond + * @bond: bond that got the notification + * @vlan_id: the vlan id to add + * + * Returns -ENOMEM if allocation failed. + */ +static int bond_add_vlan(struct bonding *bond, unsigned short vlan_id) +{ + struct vlan_entry *vlan; + + pr_debug("bond: %s, vlan id %d\n", + (bond ? bond->dev->name : "None"), vlan_id); + + vlan = kzalloc(sizeof(struct vlan_entry), GFP_KERNEL); + if (!vlan) + return -ENOMEM; + + INIT_LIST_HEAD(&vlan->vlan_list); + vlan->vlan_id = vlan_id; + + write_lock_bh(&bond->lock); + + list_add_tail(&vlan->vlan_list, &bond->vlan_list); + + write_unlock_bh(&bond->lock); + + pr_debug("added VLAN ID %d on bond %s\n", vlan_id, bond->dev->name); + + return 0; +} + +/** + * bond_del_vlan - delete a vlan id from bond + * @bond: bond that got the notification + * @vlan_id: the vlan id to delete + * + * returns -ENODEV if @vlan_id was not found in @bond. + */ +static int bond_del_vlan(struct bonding *bond, unsigned short vlan_id) +{ + struct vlan_entry *vlan; + int res = -ENODEV; + + pr_debug("bond: %s, vlan id %d\n", bond->dev->name, vlan_id); + + block_netpoll_tx(); + write_lock_bh(&bond->lock); + + list_for_each_entry(vlan, &bond->vlan_list, vlan_list) { + if (vlan->vlan_id == vlan_id) { + list_del(&vlan->vlan_list); + + if (bond_is_lb(bond)) + bond_alb_clear_vlan(bond, vlan_id); + + pr_debug("removed VLAN ID %d from bond %s\n", + vlan_id, bond->dev->name); + + kfree(vlan); + + res = 0; + goto out; + } + } + + pr_debug("couldn't find VLAN ID %d in bond %s\n", + vlan_id, bond->dev->name); + +out: + write_unlock_bh(&bond->lock); + unblock_netpoll_tx(); + return res; +} + +/** + * bond_next_vlan - safely skip to the next item in the vlans list. + * @bond: the bond we're working on + * @curr: item we're advancing from + * + * Returns %NULL if list is empty, bond->next_vlan if @curr is %NULL, + * or @curr->next otherwise (even if it is @curr itself again). + * + * Caller must hold bond->lock + */ +struct vlan_entry *bond_next_vlan(struct bonding *bond, struct vlan_entry *curr) +{ + struct vlan_entry *next, *last; + + if (list_empty(&bond->vlan_list)) + return NULL; + + if (!curr) { + next = list_entry(bond->vlan_list.next, + struct vlan_entry, vlan_list); + } else { + last = list_entry(bond->vlan_list.prev, + struct vlan_entry, vlan_list); + if (last == curr) { + next = list_entry(bond->vlan_list.next, + struct vlan_entry, vlan_list); + } else { + next = list_entry(curr->vlan_list.next, + struct vlan_entry, vlan_list); + } + } + + return next; +} + +/** + * bond_dev_queue_xmit - Prepare skb for xmit. + * + * @bond: bond device that got this skb for tx. + * @skb: hw accel VLAN tagged skb to transmit + * @slave_dev: slave that is supposed to xmit this skbuff + */ +int bond_dev_queue_xmit(struct bonding *bond, struct sk_buff *skb, + struct net_device *slave_dev) +{ + skb->dev = slave_dev; + + BUILD_BUG_ON(sizeof(skb->queue_mapping) != + sizeof(qdisc_skb_cb(skb)->bond_queue_mapping)); + skb->queue_mapping = qdisc_skb_cb(skb)->bond_queue_mapping; + + if (unlikely(netpoll_tx_running(slave_dev))) + bond_netpoll_send_skb(bond_get_slave_by_dev(bond, slave_dev), skb); + else + dev_queue_xmit(skb); + + return 0; +} + +/* + * In the following 2 functions, bond_vlan_rx_add_vid and bond_vlan_rx_kill_vid, + * We don't protect the slave list iteration with a lock because: + * a. This operation is performed in IOCTL context, + * b. The operation is protected by the RTNL semaphore in the 8021q code, + * c. Holding a lock with BH disabled while directly calling a base driver + * entry point is generally a BAD idea. + * + * The design of synchronization/protection for this operation in the 8021q + * module is good for one or more VLAN devices over a single physical device + * and cannot be extended for a teaming solution like bonding, so there is a + * potential race condition here where a net device from the vlan group might + * be referenced (either by a base driver or the 8021q code) while it is being + * removed from the system. However, it turns out we're not making matters + * worse, and if it works for regular VLAN usage it will work here too. +*/ + +/** + * bond_vlan_rx_add_vid - Propagates adding an id to slaves + * @bond_dev: bonding net device that got called + * @vid: vlan id being added + */ +static int bond_vlan_rx_add_vid(struct net_device *bond_dev, uint16_t vid) +{ + struct bonding *bond = netdev_priv(bond_dev); + struct slave *slave, *stop_at; + int i, res; + + bond_for_each_slave(bond, slave, i) { + res = vlan_vid_add(slave->dev, vid); + if (res) + goto unwind; + } + + res = bond_add_vlan(bond, vid); + if (res) { + pr_err("%s: Error: Failed to add vlan id %d\n", + bond_dev->name, vid); + return res; + } + + return 0; + +unwind: + /* unwind from head to the slave that failed */ + stop_at = slave; + bond_for_each_slave_from_to(bond, slave, i, bond->first_slave, stop_at) + vlan_vid_del(slave->dev, vid); + + return res; +} + +/** + * bond_vlan_rx_kill_vid - Propagates deleting an id to slaves + * @bond_dev: bonding net device that got called + * @vid: vlan id being removed + */ +static int bond_vlan_rx_kill_vid(struct net_device *bond_dev, uint16_t vid) +{ + struct bonding *bond = netdev_priv(bond_dev); + struct slave *slave; + int i, res; + + bond_for_each_slave(bond, slave, i) + vlan_vid_del(slave->dev, vid); + + res = bond_del_vlan(bond, vid); + if (res) { + pr_err("%s: Error: Failed to remove vlan id %d\n", + bond_dev->name, vid); + return res; + } + + return 0; +} + +static void bond_add_vlans_on_slave(struct bonding *bond, struct net_device *slave_dev) +{ + struct vlan_entry *vlan; + int res; + + list_for_each_entry(vlan, &bond->vlan_list, vlan_list) { + res = vlan_vid_add(slave_dev, vlan->vlan_id); + if (res) + pr_warning("%s: Failed to add vlan id %d to device %s\n", + bond->dev->name, vlan->vlan_id, + slave_dev->name); + } +} + +static void bond_del_vlans_from_slave(struct bonding *bond, + struct net_device *slave_dev) +{ + struct vlan_entry *vlan; + + list_for_each_entry(vlan, &bond->vlan_list, vlan_list) { + if (!vlan->vlan_id) + continue; + vlan_vid_del(slave_dev, vlan->vlan_id); + } +} + +/*------------------------------- Link status -------------------------------*/ + +/* + * Set the carrier state for the master according to the state of its + * slaves. If any slaves are up, the master is up. In 802.3ad mode, + * do special 802.3ad magic. + * + * Returns zero if carrier state does not change, nonzero if it does. + */ +static int bond_set_carrier(struct bonding *bond) +{ + struct slave *slave; + int i; + + if (bond->slave_cnt == 0) + goto down; + + if (bond->params.mode == BOND_MODE_8023AD) + return bond_3ad_set_carrier(bond); + + bond_for_each_slave(bond, slave, i) { + if (slave->link == BOND_LINK_UP) { + if (!netif_carrier_ok(bond->dev)) { + netif_carrier_on(bond->dev); + return 1; + } + return 0; + } + } + +down: + if (netif_carrier_ok(bond->dev)) { + netif_carrier_off(bond->dev); + return 1; + } + return 0; +} + +/* + * Get link speed and duplex from the slave's base driver + * using ethtool. If for some reason the call fails or the + * values are invalid, set speed and duplex to -1, + * and return error. + */ +static int bond_update_speed_duplex(struct slave *slave) +{ + struct net_device *slave_dev = slave->dev; + struct ethtool_cmd ecmd; + u32 slave_speed; + int res; + + slave->speed = SPEED_UNKNOWN; + slave->duplex = DUPLEX_UNKNOWN; + + res = __ethtool_get_settings(slave_dev, &ecmd); + if (res < 0) + return -1; + + slave_speed = ethtool_cmd_speed(&ecmd); + if (slave_speed == 0 || slave_speed == ((__u32) -1)) + return -1; + + switch (ecmd.duplex) { + case DUPLEX_FULL: + case DUPLEX_HALF: + break; + default: + return -1; + } + + slave->speed = slave_speed; + slave->duplex = ecmd.duplex; + + return 0; +} + +/* + * if <dev> supports MII link status reporting, check its link status. + * + * We either do MII/ETHTOOL ioctls, or check netif_carrier_ok(), + * depending upon the setting of the use_carrier parameter. + * + * Return either BMSR_LSTATUS, meaning that the link is up (or we + * can't tell and just pretend it is), or 0, meaning that the link is + * down. + * + * If reporting is non-zero, instead of faking link up, return -1 if + * both ETHTOOL and MII ioctls fail (meaning the device does not + * support them). If use_carrier is set, return whatever it says. + * It'd be nice if there was a good way to tell if a driver supports + * netif_carrier, but there really isn't. + */ +static int bond_check_dev_link(struct bonding *bond, + struct net_device *slave_dev, int reporting) +{ + const struct net_device_ops *slave_ops = slave_dev->netdev_ops; + int (*ioctl)(struct net_device *, struct ifreq *, int); + struct ifreq ifr; + struct mii_ioctl_data *mii; + + if (!reporting && !netif_running(slave_dev)) + return 0; + + if (bond->params.use_carrier) + return netif_carrier_ok(slave_dev) ? BMSR_LSTATUS : 0; + + /* Try to get link status using Ethtool first. */ + if (slave_dev->ethtool_ops) { + if (slave_dev->ethtool_ops->get_link) { + u32 link; + + link = slave_dev->ethtool_ops->get_link(slave_dev); + + return link ? BMSR_LSTATUS : 0; + } + } + + /* Ethtool can't be used, fallback to MII ioctls. */ + ioctl = slave_ops->ndo_do_ioctl; + if (ioctl) { + /* TODO: set pointer to correct ioctl on a per team member */ + /* bases to make this more efficient. that is, once */ + /* we determine the correct ioctl, we will always */ + /* call it and not the others for that team */ + /* member. */ + + /* + * We cannot assume that SIOCGMIIPHY will also read a + * register; not all network drivers (e.g., e100) + * support that. + */ + + /* Yes, the mii is overlaid on the ifreq.ifr_ifru */ + strncpy(ifr.ifr_name, slave_dev->name, IFNAMSIZ); + mii = if_mii(&ifr); + if (IOCTL(slave_dev, &ifr, SIOCGMIIPHY) == 0) { + mii->reg_num = MII_BMSR; + if (IOCTL(slave_dev, &ifr, SIOCGMIIREG) == 0) + return mii->val_out & BMSR_LSTATUS; + } + } + + /* + * If reporting, report that either there's no dev->do_ioctl, + * or both SIOCGMIIREG and get_link failed (meaning that we + * cannot report link status). If not reporting, pretend + * we're ok. + */ + return reporting ? -1 : BMSR_LSTATUS; +} + +/*----------------------------- Multicast list ------------------------------*/ + +/* + * Push the promiscuity flag down to appropriate slaves + */ +static int bond_set_promiscuity(struct bonding *bond, int inc) +{ + int err = 0; + if (USES_PRIMARY(bond->params.mode)) { + /* write lock already acquired */ + if (bond->curr_active_slave) { + err = dev_set_promiscuity(bond->curr_active_slave->dev, + inc); + } + } else { + struct slave *slave; + int i; + bond_for_each_slave(bond, slave, i) { + err = dev_set_promiscuity(slave->dev, inc); + if (err) + return err; + } + } + return err; +} + +/* + * Push the allmulti flag down to all slaves + */ +static int bond_set_allmulti(struct bonding *bond, int inc) +{ + int err = 0; + if (USES_PRIMARY(bond->params.mode)) { + /* write lock already acquired */ + if (bond->curr_active_slave) { + err = dev_set_allmulti(bond->curr_active_slave->dev, + inc); + } + } else { + struct slave *slave; + int i; + bond_for_each_slave(bond, slave, i) { + err = dev_set_allmulti(slave->dev, inc); + if (err) + return err; + } + } + return err; +} + +/* + * Add a Multicast address to slaves + * according to mode + */ +static void bond_mc_add(struct bonding *bond, void *addr) +{ + if (USES_PRIMARY(bond->params.mode)) { + /* write lock already acquired */ + if (bond->curr_active_slave) + dev_mc_add(bond->curr_active_slave->dev, addr); + } else { + struct slave *slave; + int i; + + bond_for_each_slave(bond, slave, i) + dev_mc_add(slave->dev, addr); + } +} + +/* + * Remove a multicast address from slave + * according to mode + */ +static void bond_mc_del(struct bonding *bond, void *addr) +{ + if (USES_PRIMARY(bond->params.mode)) { + /* write lock already acquired */ + if (bond->curr_active_slave) + dev_mc_del(bond->curr_active_slave->dev, addr); + } else { + struct slave *slave; + int i; + bond_for_each_slave(bond, slave, i) { + dev_mc_del(slave->dev, addr); + } + } +} + + +static void __bond_resend_igmp_join_requests(struct net_device *dev) +{ + struct in_device *in_dev; + + rcu_read_lock(); + in_dev = __in_dev_get_rcu(dev); + if (in_dev) + ip_mc_rejoin_groups(in_dev); + rcu_read_unlock(); +} + +/* + * Retrieve the list of registered multicast addresses for the bonding + * device and retransmit an IGMP JOIN request to the current active + * slave. + */ +static void bond_resend_igmp_join_requests(struct bonding *bond) +{ + struct net_device *bond_dev, *vlan_dev, *master_dev; + struct vlan_entry *vlan; + + read_lock(&bond->lock); + + bond_dev = bond->dev; + + /* rejoin all groups on bond device */ + __bond_resend_igmp_join_requests(bond_dev); + + /* + * if bond is enslaved to a bridge, + * then rejoin all groups on its master + */ + master_dev = bond_dev->master; + if (master_dev) + if ((master_dev->priv_flags & IFF_EBRIDGE) + && (bond_dev->priv_flags & IFF_BRIDGE_PORT)) + __bond_resend_igmp_join_requests(master_dev); + + /* rejoin all groups on vlan devices */ + list_for_each_entry(vlan, &bond->vlan_list, vlan_list) { + rcu_read_lock(); + vlan_dev = __vlan_find_dev_deep(bond_dev, + vlan->vlan_id); + rcu_read_unlock(); + if (vlan_dev) + __bond_resend_igmp_join_requests(vlan_dev); + } + + if (--bond->igmp_retrans > 0) + queue_delayed_work(bond->wq, &bond->mcast_work, HZ/5); + + read_unlock(&bond->lock); +} + +static void bond_resend_igmp_join_requests_delayed(struct work_struct *work) +{ + struct bonding *bond = container_of(work, struct bonding, + mcast_work.work); + bond_resend_igmp_join_requests(bond); +} + +/* + * flush all members of flush->mc_list from device dev->mc_list + */ +static void bond_mc_list_flush(struct net_device *bond_dev, + struct net_device *slave_dev) +{ + struct bonding *bond = netdev_priv(bond_dev); + struct netdev_hw_addr *ha; + + netdev_for_each_mc_addr(ha, bond_dev) + dev_mc_del(slave_dev, ha->addr); + + if (bond->params.mode == BOND_MODE_8023AD) { + /* del lacpdu mc addr from mc list */ + u8 lacpdu_multicast[ETH_ALEN] = MULTICAST_LACPDU_ADDR; + + dev_mc_del(slave_dev, lacpdu_multicast); + } +} + +/*--------------------------- Active slave change ---------------------------*/ + +/* + * Update the mc list and multicast-related flags for the new and + * old active slaves (if any) according to the multicast mode, and + * promiscuous flags unconditionally. + */ +static void bond_mc_swap(struct bonding *bond, struct slave *new_active, + struct slave *old_active) +{ + struct netdev_hw_addr *ha; + + if (!USES_PRIMARY(bond->params.mode)) + /* nothing to do - mc list is already up-to-date on + * all slaves + */ + return; + + if (old_active) { + if (bond->dev->flags & IFF_PROMISC) + dev_set_promiscuity(old_active->dev, -1); + + if (bond->dev->flags & IFF_ALLMULTI) + dev_set_allmulti(old_active->dev, -1); + + netdev_for_each_mc_addr(ha, bond->dev) + dev_mc_del(old_active->dev, ha->addr); + } + + if (new_active) { + /* FIXME: Signal errors upstream. */ + if (bond->dev->flags & IFF_PROMISC) + dev_set_promiscuity(new_active->dev, 1); + + if (bond->dev->flags & IFF_ALLMULTI) + dev_set_allmulti(new_active->dev, 1); + + netdev_for_each_mc_addr(ha, bond->dev) + dev_mc_add(new_active->dev, ha->addr); + } +} + +/* + * bond_do_fail_over_mac + * + * Perform special MAC address swapping for fail_over_mac settings + * + * Called with RTNL, bond->lock for read, curr_slave_lock for write_bh. + */ +static void bond_do_fail_over_mac(struct bonding *bond, + struct slave *new_active, + struct slave *old_active) + __releases(&bond->curr_slave_lock) + __releases(&bond->lock) + __acquires(&bond->lock) + __acquires(&bond->curr_slave_lock) +{ + u8 tmp_mac[ETH_ALEN]; + struct sockaddr saddr; + int rv; + + switch (bond->params.fail_over_mac) { + case BOND_FOM_ACTIVE: + if (new_active) { + memcpy(bond->dev->dev_addr, new_active->dev->dev_addr, + new_active->dev->addr_len); + write_unlock_bh(&bond->curr_slave_lock); + read_unlock(&bond->lock); + call_netdevice_notifiers(NETDEV_CHANGEADDR, bond->dev); + read_lock(&bond->lock); + write_lock_bh(&bond->curr_slave_lock); + } + break; + case BOND_FOM_FOLLOW: + /* + * if new_active && old_active, swap them + * if just old_active, do nothing (going to no active slave) + * if just new_active, set new_active to bond's MAC + */ + if (!new_active) + return; + + write_unlock_bh(&bond->curr_slave_lock); + read_unlock(&bond->lock); + + if (old_active) { + memcpy(tmp_mac, new_active->dev->dev_addr, ETH_ALEN); + memcpy(saddr.sa_data, old_active->dev->dev_addr, + ETH_ALEN); + saddr.sa_family = new_active->dev->type; + } else { + memcpy(saddr.sa_data, bond->dev->dev_addr, ETH_ALEN); + saddr.sa_family = bond->dev->type; + } + + rv = dev_set_mac_address(new_active->dev, &saddr); + if (rv) { + pr_err("%s: Error %d setting MAC of slave %s\n", + bond->dev->name, -rv, new_active->dev->name); + goto out; + } + + if (!old_active) + goto out; + + memcpy(saddr.sa_data, tmp_mac, ETH_ALEN); + saddr.sa_family = old_active->dev->type; + + rv = dev_set_mac_address(old_active->dev, &saddr); + if (rv) + pr_err("%s: Error %d setting MAC of slave %s\n", + bond->dev->name, -rv, new_active->dev->name); +out: + read_lock(&bond->lock); + write_lock_bh(&bond->curr_slave_lock); + break; + default: + pr_err("%s: bond_do_fail_over_mac impossible: bad policy %d\n", + bond->dev->name, bond->params.fail_over_mac); + break; + } + +} + +static bool bond_should_change_active(struct bonding *bond) +{ + struct slave *prim = bond->primary_slave; + struct slave *curr = bond->curr_active_slave; + + if (!prim || !curr || curr->link != BOND_LINK_UP) + return true; + if (bond->force_primary) { + bond->force_primary = false; + return true; + } + if (bond->params.primary_reselect == BOND_PRI_RESELECT_BETTER && + (prim->speed < curr->speed || + (prim->speed == curr->speed && prim->duplex <= curr->duplex))) + return false; + if (bond->params.primary_reselect == BOND_PRI_RESELECT_FAILURE) + return false; + return true; +} + +/** + * find_best_interface - select the best available slave to be the active one + * @bond: our bonding struct + * + * Warning: Caller must hold curr_slave_lock for writing. + */ +static struct slave *bond_find_best_slave(struct bonding *bond) +{ + struct slave *new_active, *old_active; + struct slave *bestslave = NULL; + int mintime = bond->params.updelay; + int i; + + new_active = bond->curr_active_slave; + + if (!new_active) { /* there were no active slaves left */ + if (bond->slave_cnt > 0) /* found one slave */ + new_active = bond->first_slave; + else + return NULL; /* still no slave, return NULL */ + } + + if ((bond->primary_slave) && + bond->primary_slave->link == BOND_LINK_UP && + bond_should_change_active(bond)) { + new_active = bond->primary_slave; + } + + /* remember where to stop iterating over the slaves */ + old_active = new_active; + + bond_for_each_slave_from(bond, new_active, i, old_active) { + if (new_active->link == BOND_LINK_UP) { + return new_active; + } else if (new_active->link == BOND_LINK_BACK && + IS_UP(new_active->dev)) { + /* link up, but waiting for stabilization */ + if (new_active->delay < mintime) { + mintime = new_active->delay; + bestslave = new_active; + } + } + } + + return bestslave; +} + +static bool bond_should_notify_peers(struct bonding *bond) +{ + struct slave *slave = bond->curr_active_slave; + + pr_debug("bond_should_notify_peers: bond %s slave %s\n", + bond->dev->name, slave ? slave->dev->name : "NULL"); + + if (!slave || !bond->send_peer_notif || + test_bit(__LINK_STATE_LINKWATCH_PENDING, &slave->dev->state)) + return false; + + bond->send_peer_notif--; + return true; +} + +/** + * change_active_interface - change the active slave into the specified one + * @bond: our bonding struct + * @new: the new slave to make the active one + * + * Set the new slave to the bond's settings and unset them on the old + * curr_active_slave. + * Setting include flags, mc-list, promiscuity, allmulti, etc. + * + * If @new's link state is %BOND_LINK_BACK we'll set it to %BOND_LINK_UP, + * because it is apparently the best available slave we have, even though its + * updelay hasn't timed out yet. + * + * If new_active is not NULL, caller must hold bond->lock for read and + * curr_slave_lock for write_bh. + */ +void bond_change_active_slave(struct bonding *bond, struct slave *new_active) +{ + struct slave *old_active = bond->curr_active_slave; + + if (old_active == new_active) + return; + + if (new_active) { + new_active->jiffies = jiffies; + + if (new_active->link == BOND_LINK_BACK) { + if (USES_PRIMARY(bond->params.mode)) { + pr_info("%s: making interface %s the new active one %d ms earlier.\n", + bond->dev->name, new_active->dev->name, + (bond->params.updelay - new_active->delay) * bond->params.miimon); + } + + new_active->delay = 0; + new_active->link = BOND_LINK_UP; + + if (bond->params.mode == BOND_MODE_8023AD) + bond_3ad_handle_link_change(new_active, BOND_LINK_UP); + + if (bond_is_lb(bond)) + bond_alb_handle_link_change(bond, new_active, BOND_LINK_UP); + } else { + if (USES_PRIMARY(bond->params.mode)) { + pr_info("%s: making interface %s the new active one.\n", + bond->dev->name, new_active->dev->name); + } + } + } + + if (USES_PRIMARY(bond->params.mode)) + bond_mc_swap(bond, new_active, old_active); + + if (bond_is_lb(bond)) { + bond_alb_handle_active_change(bond, new_active); + if (old_active) + bond_set_slave_inactive_flags(old_active); + if (new_active) + bond_set_slave_active_flags(new_active); + } else { + bond->curr_active_slave = new_active; + } + + if (bond->params.mode == BOND_MODE_ACTIVEBACKUP) { + if (old_active) + bond_set_slave_inactive_flags(old_active); + + if (new_active) { + bool should_notify_peers = false; + + bond_set_slave_active_flags(new_active); + + if (bond->params.fail_over_mac) + bond_do_fail_over_mac(bond, new_active, + old_active); + + if (netif_running(bond->dev)) { + bond->send_peer_notif = + bond->params.num_peer_notif; + should_notify_peers = + bond_should_notify_peers(bond); + } + + write_unlock_bh(&bond->curr_slave_lock); + read_unlock(&bond->lock); + + netdev_bonding_change(bond->dev, NETDEV_BONDING_FAILOVER); + if (should_notify_peers) + netdev_bonding_change(bond->dev, + NETDEV_NOTIFY_PEERS); + + read_lock(&bond->lock); + write_lock_bh(&bond->curr_slave_lock); + } + } + + /* resend IGMP joins since active slave has changed or + * all were sent on curr_active_slave. + * resend only if bond is brought up with the affected + * bonding modes and the retransmission is enabled */ + if (netif_running(bond->dev) && (bond->params.resend_igmp > 0) && + ((USES_PRIMARY(bond->params.mode) && new_active) || + bond->params.mode == BOND_MODE_ROUNDROBIN)) { + bond->igmp_retrans = bond->params.resend_igmp; + queue_delayed_work(bond->wq, &bond->mcast_work, 0); + } +} + +/** + * bond_select_active_slave - select a new active slave, if needed + * @bond: our bonding struct + * + * This functions should be called when one of the following occurs: + * - The old curr_active_slave has been released or lost its link. + * - The primary_slave has got its link back. + * - A slave has got its link back and there's no old curr_active_slave. + * + * Caller must hold bond->lock for read and curr_slave_lock for write_bh. + */ +void bond_select_active_slave(struct bonding *bond) +{ + struct slave *best_slave; + int rv; + + best_slave = bond_find_best_slave(bond); + if (best_slave != bond->curr_active_slave) { + bond_change_active_slave(bond, best_slave); + rv = bond_set_carrier(bond); + if (!rv) + return; + + if (netif_carrier_ok(bond->dev)) { + pr_info("%s: first active interface up!\n", + bond->dev->name); + } else { + pr_info("%s: now running without any active interface !\n", + bond->dev->name); + } + } +} + +/*--------------------------- slave list handling ---------------------------*/ + +/* + * This function attaches the slave to the end of list. + * + * bond->lock held for writing by caller. + */ +static void bond_attach_slave(struct bonding *bond, struct slave *new_slave) +{ + if (bond->first_slave == NULL) { /* attaching the first slave */ + new_slave->next = new_slave; + new_slave->prev = new_slave; + bond->first_slave = new_slave; + } else { + new_slave->next = bond->first_slave; + new_slave->prev = bond->first_slave->prev; + new_slave->next->prev = new_slave; + new_slave->prev->next = new_slave; + } + + bond->slave_cnt++; +} + +/* + * This function detaches the slave from the list. + * WARNING: no check is made to verify if the slave effectively + * belongs to <bond>. + * Nothing is freed on return, structures are just unchained. + * If any slave pointer in bond was pointing to <slave>, + * it should be changed by the calling function. + * + * bond->lock held for writing by caller. + */ +static void bond_detach_slave(struct bonding *bond, struct slave *slave) +{ + if (slave->next) + slave->next->prev = slave->prev; + + if (slave->prev) + slave->prev->next = slave->next; + + if (bond->first_slave == slave) { /* slave is the first slave */ + if (bond->slave_cnt > 1) { /* there are more slave */ + bond->first_slave = slave->next; + } else { + bond->first_slave = NULL; /* slave was the last one */ + } + } + + slave->next = NULL; + slave->prev = NULL; + bond->slave_cnt--; +} + +#ifdef CONFIG_NET_POLL_CONTROLLER +static inline int slave_enable_netpoll(struct slave *slave) +{ + struct netpoll *np; + int err = 0; + + np = kzalloc(sizeof(*np), GFP_KERNEL); + err = -ENOMEM; + if (!np) + goto out; + + np->dev = slave->dev; + strlcpy(np->dev_name, slave->dev->name, IFNAMSIZ); + err = __netpoll_setup(np); + if (err) { + kfree(np); + goto out; + } + slave->np = np; +out: + return err; +} +static inline void slave_disable_netpoll(struct slave *slave) +{ + struct netpoll *np = slave->np; + + if (!np) + return; + + slave->np = NULL; + synchronize_rcu_bh(); + __netpoll_cleanup(np); + kfree(np); +} +static inline bool slave_dev_support_netpoll(struct net_device *slave_dev) +{ + if (slave_dev->priv_flags & IFF_DISABLE_NETPOLL) + return false; + if (!slave_dev->netdev_ops->ndo_poll_controller) + return false; + return true; +} + +static void bond_poll_controller(struct net_device *bond_dev) +{ +} + +static void __bond_netpoll_cleanup(struct bonding *bond) +{ + struct slave *slave; + int i; + + bond_for_each_slave(bond, slave, i) + if (IS_UP(slave->dev)) + slave_disable_netpoll(slave); +} +static void bond_netpoll_cleanup(struct net_device *bond_dev) +{ + struct bonding *bond = netdev_priv(bond_dev); + + read_lock(&bond->lock); + __bond_netpoll_cleanup(bond); + read_unlock(&bond->lock); +} + +static int bond_netpoll_setup(struct net_device *dev, struct netpoll_info *ni) +{ + struct bonding *bond = netdev_priv(dev); + struct slave *slave; + int i, err = 0; + + read_lock(&bond->lock); + bond_for_each_slave(bond, slave, i) { + err = slave_enable_netpoll(slave); + if (err) { + __bond_netpoll_cleanup(bond); + break; + } + } + read_unlock(&bond->lock); + return err; +} + +static struct netpoll_info *bond_netpoll_info(struct bonding *bond) +{ + return bond->dev->npinfo; +} + +#else +static inline int slave_enable_netpoll(struct slave *slave) +{ + return 0; +} +static inline void slave_disable_netpoll(struct slave *slave) +{ +} +static void bond_netpoll_cleanup(struct net_device *bond_dev) +{ +} +#endif + +/*---------------------------------- IOCTL ----------------------------------*/ + +static int bond_sethwaddr(struct net_device *bond_dev, + struct net_device *slave_dev) +{ + pr_debug("bond_dev=%p\n", bond_dev); + pr_debug("slave_dev=%p\n", slave_dev); + pr_debug("slave_dev->addr_len=%d\n", slave_dev->addr_len); + memcpy(bond_dev->dev_addr, slave_dev->dev_addr, slave_dev->addr_len); + return 0; +} + +static netdev_features_t bond_fix_features(struct net_device *dev, + netdev_features_t features) +{ + struct slave *slave; + struct bonding *bond = netdev_priv(dev); + netdev_features_t mask; + int i; + + read_lock(&bond->lock); + + if (!bond->first_slave) { + /* Disable adding VLANs to empty bond. But why? --mq */ + features |= NETIF_F_VLAN_CHALLENGED; + goto out; + } + + mask = features; + features &= ~NETIF_F_ONE_FOR_ALL; + features |= NETIF_F_ALL_FOR_ALL; + + bond_for_each_slave(bond, slave, i) { + features = netdev_increment_features(features, + slave->dev->features, + mask); + } + +out: + read_unlock(&bond->lock); + return features; +} + +#define BOND_VLAN_FEATURES (NETIF_F_ALL_CSUM | NETIF_F_SG | \ + NETIF_F_FRAGLIST | NETIF_F_ALL_TSO | \ + NETIF_F_HIGHDMA | NETIF_F_LRO) + +static void bond_compute_features(struct bonding *bond) +{ + struct slave *slave; + struct net_device *bond_dev = bond->dev; + netdev_features_t vlan_features = BOND_VLAN_FEATURES; + unsigned short max_hard_header_len = ETH_HLEN; + int i; + + read_lock(&bond->lock); + + if (!bond->first_slave) + goto done; + + bond_for_each_slave(bond, slave, i) { + vlan_features = netdev_increment_features(vlan_features, + slave->dev->vlan_features, BOND_VLAN_FEATURES); + + if (slave->dev->hard_header_len > max_hard_header_len) + max_hard_header_len = slave->dev->hard_header_len; + } + +done: + bond_dev->vlan_features = vlan_features; + bond_dev->hard_header_len = max_hard_header_len; + + read_unlock(&bond->lock); + + netdev_change_features(bond_dev); +} + +static void bond_setup_by_slave(struct net_device *bond_dev, + struct net_device *slave_dev) +{ + struct bonding *bond = netdev_priv(bond_dev); + + bond_dev->header_ops = slave_dev->header_ops; + + bond_dev->type = slave_dev->type; + bond_dev->hard_header_len = slave_dev->hard_header_len; + bond_dev->addr_len = slave_dev->addr_len; + + memcpy(bond_dev->broadcast, slave_dev->broadcast, + slave_dev->addr_len); + bond->setup_by_slave = 1; +} + +/* On bonding slaves other than the currently active slave, suppress + * duplicates except for alb non-mcast/bcast. + */ +static bool bond_should_deliver_exact_match(struct sk_buff *skb, + struct slave *slave, + struct bonding *bond) +{ + if (bond_is_slave_inactive(slave)) { + if (bond->params.mode == BOND_MODE_ALB && + skb->pkt_type != PACKET_BROADCAST && + skb->pkt_type != PACKET_MULTICAST) + return false; + return true; + } + return false; +} + +static rx_handler_result_t bond_handle_frame(struct sk_buff **pskb) +{ + struct sk_buff *skb = *pskb; + struct slave *slave; + struct bonding *bond; + int (*recv_probe)(struct sk_buff *, struct bonding *, + struct slave *); + int ret = RX_HANDLER_ANOTHER; + + skb = skb_share_check(skb, GFP_ATOMIC); + if (unlikely(!skb)) + return RX_HANDLER_CONSUMED; + + *pskb = skb; + + slave = bond_slave_get_rcu(skb->dev); + bond = slave->bond; + + if (bond->params.arp_interval) + slave->dev->last_rx = jiffies; + + recv_probe = ACCESS_ONCE(bond->recv_probe); + if (recv_probe) { + struct sk_buff *nskb = skb_clone(skb, GFP_ATOMIC); + + if (likely(nskb)) { + ret = recv_probe(nskb, bond, slave); + dev_kfree_skb(nskb); + if (ret == RX_HANDLER_CONSUMED) { + consume_skb(skb); + return ret; + } + } + } + + if (bond_should_deliver_exact_match(skb, slave, bond)) { + return RX_HANDLER_EXACT; + } + + skb->dev = bond->dev; + + if (bond->params.mode == BOND_MODE_ALB && + bond->dev->priv_flags & IFF_BRIDGE_PORT && + skb->pkt_type == PACKET_HOST) { + + if (unlikely(skb_cow_head(skb, + skb->data - skb_mac_header(skb)))) { + kfree_skb(skb); + return RX_HANDLER_CONSUMED; + } + memcpy(eth_hdr(skb)->h_dest, bond->dev->dev_addr, ETH_ALEN); + } + + return ret; +} + +/* enslave device <slave> to bond device <master> */ +int bond_enslave(struct net_device *bond_dev, struct net_device *slave_dev) +{ + struct bonding *bond = netdev_priv(bond_dev); + const struct net_device_ops *slave_ops = slave_dev->netdev_ops; + struct slave *new_slave = NULL; + struct netdev_hw_addr *ha; + struct sockaddr addr; + int link_reporting; + int res = 0; + + if (!bond->params.use_carrier && slave_dev->ethtool_ops == NULL && + slave_ops->ndo_do_ioctl == NULL) { + pr_warning("%s: Warning: no link monitoring support for %s\n", + bond_dev->name, slave_dev->name); + } + + /* already enslaved */ + if (slave_dev->flags & IFF_SLAVE) { + pr_debug("Error, Device was already enslaved\n"); + return -EBUSY; + } + + /* vlan challenged mutual exclusion */ + /* no need to lock since we're protected by rtnl_lock */ + if (slave_dev->features & NETIF_F_VLAN_CHALLENGED) { + pr_debug("%s: NETIF_F_VLAN_CHALLENGED\n", slave_dev->name); + if (bond_vlan_used(bond)) { + pr_err("%s: Error: cannot enslave VLAN challenged slave %s on VLAN enabled bond %s\n", + bond_dev->name, slave_dev->name, bond_dev->name); + return -EPERM; + } else { + pr_warning("%s: Warning: enslaved VLAN challenged slave %s. Adding VLANs will be blocked as long as %s is part of bond %s\n", + bond_dev->name, slave_dev->name, + slave_dev->name, bond_dev->name); + } + } else { + pr_debug("%s: ! NETIF_F_VLAN_CHALLENGED\n", slave_dev->name); + } + + /* + * Old ifenslave binaries are no longer supported. These can + * be identified with moderate accuracy by the state of the slave: + * the current ifenslave will set the interface down prior to + * enslaving it; the old ifenslave will not. + */ + if ((slave_dev->flags & IFF_UP)) { + pr_err("%s is up. This may be due to an out of date ifenslave.\n", + slave_dev->name); + res = -EPERM; + goto err_undo_flags; + } + + /* set bonding device ether type by slave - bonding netdevices are + * created with ether_setup, so when the slave type is not ARPHRD_ETHER + * there is a need to override some of the type dependent attribs/funcs. + * + * bond ether type mutual exclusion - don't allow slaves of dissimilar + * ether type (eg ARPHRD_ETHER and ARPHRD_INFINIBAND) share the same bond + */ + if (bond->slave_cnt == 0) { + if (bond_dev->type != slave_dev->type) { + pr_debug("%s: change device type from %d to %d\n", + bond_dev->name, + bond_dev->type, slave_dev->type); + + res = netdev_bonding_change(bond_dev, + NETDEV_PRE_TYPE_CHANGE); + res = notifier_to_errno(res); + if (res) { + pr_err("%s: refused to change device type\n", + bond_dev->name); + res = -EBUSY; + goto err_undo_flags; + } + + /* Flush unicast and multicast addresses */ + dev_uc_flush(bond_dev); + dev_mc_flush(bond_dev); + + if (slave_dev->type != ARPHRD_ETHER) + bond_setup_by_slave(bond_dev, slave_dev); + else { + ether_setup(bond_dev); + bond_dev->priv_flags &= ~IFF_TX_SKB_SHARING; + } + + netdev_bonding_change(bond_dev, + NETDEV_POST_TYPE_CHANGE); + } + } else if (bond_dev->type != slave_dev->type) { + pr_err("%s ether type (%d) is different from other slaves (%d), can not enslave it.\n", + slave_dev->name, + slave_dev->type, bond_dev->type); + res = -EINVAL; + goto err_undo_flags; + } + + if (slave_ops->ndo_set_mac_address == NULL) { + if (bond->slave_cnt == 0) { + pr_warning("%s: Warning: The first slave device specified does not support setting the MAC address. Setting fail_over_mac to active.", + bond_dev->name); + bond->params.fail_over_mac = BOND_FOM_ACTIVE; + } else if (bond->params.fail_over_mac != BOND_FOM_ACTIVE) { + pr_err("%s: Error: The slave device specified does not support setting the MAC address, but fail_over_mac is not set to active.\n", + bond_dev->name); + res = -EOPNOTSUPP; + goto err_undo_flags; + } + } + + call_netdevice_notifiers(NETDEV_JOIN, slave_dev); + + /* If this is the first slave, then we need to set the master's hardware + * address to be the same as the slave's. */ + if (is_zero_ether_addr(bond->dev->dev_addr)) + memcpy(bond->dev->dev_addr, slave_dev->dev_addr, + slave_dev->addr_len); + + + new_slave = kzalloc(sizeof(struct slave), GFP_KERNEL); + if (!new_slave) { + res = -ENOMEM; + goto err_undo_flags; + } + + /* + * Set the new_slave's queue_id to be zero. Queue ID mapping + * is set via sysfs or module option if desired. + */ + new_slave->queue_id = 0; + + /* Save slave's original mtu and then set it to match the bond */ + new_slave->original_mtu = slave_dev->mtu; + res = dev_set_mtu(slave_dev, bond->dev->mtu); + if (res) { + pr_debug("Error %d calling dev_set_mtu\n", res); + goto err_free; + } + + /* + * Save slave's original ("permanent") mac address for modes + * that need it, and for restoring it upon release, and then + * set it to the master's address + */ + memcpy(new_slave->perm_hwaddr, slave_dev->dev_addr, ETH_ALEN); + + if (!bond->params.fail_over_mac) { + /* + * Set slave to master's mac address. The application already + * set the master's mac address to that of the first slave + */ + memcpy(addr.sa_data, bond_dev->dev_addr, bond_dev->addr_len); + addr.sa_family = slave_dev->type; + res = dev_set_mac_address(slave_dev, &addr); + if (res) { + pr_debug("Error %d calling set_mac_address\n", res); + goto err_restore_mtu; + } + } + + res = netdev_set_bond_master(slave_dev, bond_dev); + if (res) { + pr_debug("Error %d calling netdev_set_bond_master\n", res); + goto err_restore_mac; + } + + /* open the slave since the application closed it */ + res = dev_open(slave_dev); + if (res) { + pr_debug("Opening slave %s failed\n", slave_dev->name); + goto err_unset_master; + } + + new_slave->bond = bond; + new_slave->dev = slave_dev; + slave_dev->priv_flags |= IFF_BONDING; + + if (bond_is_lb(bond)) { + /* bond_alb_init_slave() must be called before all other stages since + * it might fail and we do not want to have to undo everything + */ + res = bond_alb_init_slave(bond, new_slave); + if (res) + goto err_close; + } + + /* If the mode USES_PRIMARY, then the new slave gets the + * master's promisc (and mc) settings only if it becomes the + * curr_active_slave, and that is taken care of later when calling + * bond_change_active() + */ + if (!USES_PRIMARY(bond->params.mode)) { + /* set promiscuity level to new slave */ + if (bond_dev->flags & IFF_PROMISC) { + res = dev_set_promiscuity(slave_dev, 1); + if (res) + goto err_close; + } + + /* set allmulti level to new slave */ + if (bond_dev->flags & IFF_ALLMULTI) { + res = dev_set_allmulti(slave_dev, 1); + if (res) + goto err_close; + } + + netif_addr_lock_bh(bond_dev); + /* upload master's mc_list to new slave */ + netdev_for_each_mc_addr(ha, bond_dev) + dev_mc_add(slave_dev, ha->addr); + netif_addr_unlock_bh(bond_dev); + } + + if (bond->params.mode == BOND_MODE_8023AD) { + /* add lacpdu mc addr to mc list */ + u8 lacpdu_multicast[ETH_ALEN] = MULTICAST_LACPDU_ADDR; + + dev_mc_add(slave_dev, lacpdu_multicast); + } + + bond_add_vlans_on_slave(bond, slave_dev); + + write_lock_bh(&bond->lock); + + bond_attach_slave(bond, new_slave); + + new_slave->delay = 0; + new_slave->link_failure_count = 0; + + write_unlock_bh(&bond->lock); + + bond_compute_features(bond); + + read_lock(&bond->lock); + + new_slave->last_arp_rx = jiffies; + + if (bond->params.miimon && !bond->params.use_carrier) { + link_reporting = bond_check_dev_link(bond, slave_dev, 1); + + if ((link_reporting == -1) && !bond->params.arp_interval) { + /* + * miimon is set but a bonded network driver + * does not support ETHTOOL/MII and + * arp_interval is not set. Note: if + * use_carrier is enabled, we will never go + * here (because netif_carrier is always + * supported); thus, we don't need to change + * the messages for netif_carrier. + */ + pr_warning("%s: Warning: MII and ETHTOOL support not available for interface %s, and arp_interval/arp_ip_target module parameters not specified, thus bonding will not detect link failures! see bonding.txt for details.\n", + bond_dev->name, slave_dev->name); + } else if (link_reporting == -1) { + /* unable get link status using mii/ethtool */ + pr_warning("%s: Warning: can't get link status from interface %s; the network driver associated with this interface does not support MII or ETHTOOL link status reporting, thus miimon has no effect on this interface.\n", + bond_dev->name, slave_dev->name); + } + } + + /* check for initial state */ + if (!bond->params.miimon || + (bond_check_dev_link(bond, slave_dev, 0) == BMSR_LSTATUS)) { + if (bond->params.updelay) { + pr_debug("Initial state of slave_dev is BOND_LINK_BACK\n"); + new_slave->link = BOND_LINK_BACK; + new_slave->delay = bond->params.updelay; + } else { + pr_debug("Initial state of slave_dev is BOND_LINK_UP\n"); + new_slave->link = BOND_LINK_UP; + } + new_slave->jiffies = jiffies; + } else { + pr_debug("Initial state of slave_dev is BOND_LINK_DOWN\n"); + new_slave->link = BOND_LINK_DOWN; + } + + bond_update_speed_duplex(new_slave); + + if (USES_PRIMARY(bond->params.mode) && bond->params.primary[0]) { + /* if there is a primary slave, remember it */ + if (strcmp(bond->params.primary, new_slave->dev->name) == 0) { + bond->primary_slave = new_slave; + bond->force_primary = true; + } + } + + write_lock_bh(&bond->curr_slave_lock); + + switch (bond->params.mode) { + case BOND_MODE_ACTIVEBACKUP: + bond_set_slave_inactive_flags(new_slave); + bond_select_active_slave(bond); + break; + case BOND_MODE_8023AD: + /* in 802.3ad mode, the internal mechanism + * will activate the slaves in the selected + * aggregator + */ + bond_set_slave_inactive_flags(new_slave); + /* if this is the first slave */ + if (bond->slave_cnt == 1) { + SLAVE_AD_INFO(new_slave).id = 1; + /* Initialize AD with the number of times that the AD timer is called in 1 second + * can be called only after the mac address of the bond is set + */ + bond_3ad_initialize(bond, 1000/AD_TIMER_INTERVAL); + } else { + SLAVE_AD_INFO(new_slave).id = + SLAVE_AD_INFO(new_slave->prev).id + 1; + } + + bond_3ad_bind_slave(new_slave); + break; + case BOND_MODE_TLB: + case BOND_MODE_ALB: + bond_set_active_slave(new_slave); + bond_set_slave_inactive_flags(new_slave); + bond_select_active_slave(bond); + break; + default: + pr_debug("This slave is always active in trunk mode\n"); + + /* always active in trunk mode */ + bond_set_active_slave(new_slave); + + /* In trunking mode there is little meaning to curr_active_slave + * anyway (it holds no special properties of the bond device), + * so we can change it without calling change_active_interface() + */ + if (!bond->curr_active_slave) + bond->curr_active_slave = new_slave; + + break; + } /* switch(bond_mode) */ + + write_unlock_bh(&bond->curr_slave_lock); + + bond_set_carrier(bond); + +#ifdef CONFIG_NET_POLL_CONTROLLER + slave_dev->npinfo = bond_netpoll_info(bond); + if (slave_dev->npinfo) { + if (slave_enable_netpoll(new_slave)) { + read_unlock(&bond->lock); + pr_info("Error, %s: master_dev is using netpoll, " + "but new slave device does not support netpoll.\n", + bond_dev->name); + res = -EBUSY; + goto err_detach; + } + } +#endif + + read_unlock(&bond->lock); + + res = bond_create_slave_symlinks(bond_dev, slave_dev); + if (res) + goto err_detach; + + res = netdev_rx_handler_register(slave_dev, bond_handle_frame, + new_slave); + if (res) { + pr_debug("Error %d calling netdev_rx_handler_register\n", res); + goto err_dest_symlinks; + } + + pr_info("%s: enslaving %s as a%s interface with a%s link.\n", + bond_dev->name, slave_dev->name, + bond_is_active_slave(new_slave) ? "n active" : " backup", + new_slave->link != BOND_LINK_DOWN ? "n up" : " down"); + + /* enslave is successful */ + return 0; + +/* Undo stages on error */ +err_dest_symlinks: + bond_destroy_slave_symlinks(bond_dev, slave_dev); + +err_detach: + write_lock_bh(&bond->lock); + bond_detach_slave(bond, new_slave); + write_unlock_bh(&bond->lock); + +err_close: + dev_close(slave_dev); + +err_unset_master: + netdev_set_bond_master(slave_dev, NULL); + +err_restore_mac: + if (!bond->params.fail_over_mac) { + /* XXX TODO - fom follow mode needs to change master's + * MAC if this slave's MAC is in use by the bond, or at + * least print a warning. + */ + memcpy(addr.sa_data, new_slave->perm_hwaddr, ETH_ALEN); + addr.sa_family = slave_dev->type; + dev_set_mac_address(slave_dev, &addr); + } + +err_restore_mtu: + dev_set_mtu(slave_dev, new_slave->original_mtu); + +err_free: + kfree(new_slave); + +err_undo_flags: + bond_compute_features(bond); + + return res; +} + +/* + * Try to release the slave device <slave> from the bond device <master> + * It is legal to access curr_active_slave without a lock because all the function + * is write-locked. + * + * The rules for slave state should be: + * for Active/Backup: + * Active stays on all backups go down + * for Bonded connections: + * The first up interface should be left on and all others downed. + */ +int bond_release(struct net_device *bond_dev, struct net_device *slave_dev) +{ + struct bonding *bond = netdev_priv(bond_dev); + struct slave *slave, *oldcurrent; + struct sockaddr addr; + netdev_features_t old_features = bond_dev->features; + + /* slave is not a slave or master is not master of this slave */ + if (!(slave_dev->flags & IFF_SLAVE) || + (slave_dev->master != bond_dev)) { + pr_err("%s: Error: cannot release %s.\n", + bond_dev->name, slave_dev->name); + return -EINVAL; + } + + block_netpoll_tx(); + netdev_bonding_change(bond_dev, NETDEV_RELEASE); + write_lock_bh(&bond->lock); + + slave = bond_get_slave_by_dev(bond, slave_dev); + if (!slave) { + /* not a slave of this bond */ + pr_info("%s: %s not enslaved\n", + bond_dev->name, slave_dev->name); + write_unlock_bh(&bond->lock); + unblock_netpoll_tx(); + return -EINVAL; + } + + /* unregister rx_handler early so bond_handle_frame wouldn't be called + * for this slave anymore. + */ + netdev_rx_handler_unregister(slave_dev); + write_unlock_bh(&bond->lock); + synchronize_net(); + write_lock_bh(&bond->lock); + + if (!bond->params.fail_over_mac) { + if (!compare_ether_addr(bond_dev->dev_addr, slave->perm_hwaddr) && + bond->slave_cnt > 1) + pr_warning("%s: Warning: the permanent HWaddr of %s - %pM - is still in use by %s. Set the HWaddr of %s to a different address to avoid conflicts.\n", + bond_dev->name, slave_dev->name, + slave->perm_hwaddr, + bond_dev->name, slave_dev->name); + } + + /* Inform AD package of unbinding of slave. */ + if (bond->params.mode == BOND_MODE_8023AD) { + /* must be called before the slave is + * detached from the list + */ + bond_3ad_unbind_slave(slave); + } + + pr_info("%s: releasing %s interface %s\n", + bond_dev->name, + bond_is_active_slave(slave) ? "active" : "backup", + slave_dev->name); + + oldcurrent = bond->curr_active_slave; + + bond->current_arp_slave = NULL; + + /* release the slave from its bond */ + bond_detach_slave(bond, slave); + + if (bond->primary_slave == slave) + bond->primary_slave = NULL; + + if (oldcurrent == slave) + bond_change_active_slave(bond, NULL); + + if (bond_is_lb(bond)) { + /* Must be called only after the slave has been + * detached from the list and the curr_active_slave + * has been cleared (if our_slave == old_current), + * but before a new active slave is selected. + */ + write_unlock_bh(&bond->lock); + bond_alb_deinit_slave(bond, slave); + write_lock_bh(&bond->lock); + } + + if (oldcurrent == slave) { + /* + * Note that we hold RTNL over this sequence, so there + * is no concern that another slave add/remove event + * will interfere. + */ + write_unlock_bh(&bond->lock); + read_lock(&bond->lock); + write_lock_bh(&bond->curr_slave_lock); + + bond_select_active_slave(bond); + + write_unlock_bh(&bond->curr_slave_lock); + read_unlock(&bond->lock); + write_lock_bh(&bond->lock); + } + + if (bond->slave_cnt == 0) { + bond_set_carrier(bond); + + /* if the last slave was removed, zero the mac address + * of the master so it will be set by the application + * to the mac address of the first slave + */ + memset(bond_dev->dev_addr, 0, bond_dev->addr_len); + + if (bond_vlan_used(bond)) { + pr_warning("%s: Warning: clearing HW address of %s while it still has VLANs.\n", + bond_dev->name, bond_dev->name); + pr_warning("%s: When re-adding slaves, make sure the bond's HW address matches its VLANs'.\n", + bond_dev->name); + } + } + + write_unlock_bh(&bond->lock); + unblock_netpoll_tx(); + + if (bond->slave_cnt == 0) + call_netdevice_notifiers(NETDEV_CHANGEADDR, bond->dev); + + bond_compute_features(bond); + if (!(bond_dev->features & NETIF_F_VLAN_CHALLENGED) && + (old_features & NETIF_F_VLAN_CHALLENGED)) + pr_info("%s: last VLAN challenged slave %s left bond %s. VLAN blocking is removed\n", + bond_dev->name, slave_dev->name, bond_dev->name); + + /* must do this from outside any spinlocks */ + bond_destroy_slave_symlinks(bond_dev, slave_dev); + + bond_del_vlans_from_slave(bond, slave_dev); + + /* If the mode USES_PRIMARY, then we should only remove its + * promisc and mc settings if it was the curr_active_slave, but that was + * already taken care of above when we detached the slave + */ + if (!USES_PRIMARY(bond->params.mode)) { + /* unset promiscuity level from slave */ + if (bond_dev->flags & IFF_PROMISC) + dev_set_promiscuity(slave_dev, -1); + + /* unset allmulti level from slave */ + if (bond_dev->flags & IFF_ALLMULTI) + dev_set_allmulti(slave_dev, -1); + + /* flush master's mc_list from slave */ + netif_addr_lock_bh(bond_dev); + bond_mc_list_flush(bond_dev, slave_dev); + netif_addr_unlock_bh(bond_dev); + } + + netdev_set_bond_master(slave_dev, NULL); + + slave_disable_netpoll(slave); + + /* close slave before restoring its mac address */ + dev_close(slave_dev); + + if (bond->params.fail_over_mac != BOND_FOM_ACTIVE) { + /* restore original ("permanent") mac address */ + memcpy(addr.sa_data, slave->perm_hwaddr, ETH_ALEN); + addr.sa_family = slave_dev->type; + dev_set_mac_address(slave_dev, &addr); + } + + dev_set_mtu(slave_dev, slave->original_mtu); + + slave_dev->priv_flags &= ~IFF_BONDING; + + kfree(slave); + + return 0; /* deletion OK */ +} + +/* +* First release a slave and then destroy the bond if no more slaves are left. +* Must be under rtnl_lock when this function is called. +*/ +static int bond_release_and_destroy(struct net_device *bond_dev, + struct net_device *slave_dev) +{ + struct bonding *bond = netdev_priv(bond_dev); + int ret; + + ret = bond_release(bond_dev, slave_dev); + if ((ret == 0) && (bond->slave_cnt == 0)) { + bond_dev->priv_flags |= IFF_DISABLE_NETPOLL; + pr_info("%s: destroying bond %s.\n", + bond_dev->name, bond_dev->name); + unregister_netdevice(bond_dev); + } + return ret; +} + +/* + * This function releases all slaves. + */ +static int bond_release_all(struct net_device *bond_dev) +{ + struct bonding *bond = netdev_priv(bond_dev); + struct slave *slave; + struct net_device *slave_dev; + struct sockaddr addr; + + write_lock_bh(&bond->lock); + + netif_carrier_off(bond_dev); + + if (bond->slave_cnt == 0) + goto out; + + bond->current_arp_slave = NULL; + bond->primary_slave = NULL; + bond_change_active_slave(bond, NULL); + + while ((slave = bond->first_slave) != NULL) { + /* Inform AD package of unbinding of slave + * before slave is detached from the list. + */ + if (bond->params.mode == BOND_MODE_8023AD) + bond_3ad_unbind_slave(slave); + + slave_dev = slave->dev; + bond_detach_slave(bond, slave); + + /* now that the slave is detached, unlock and perform + * all the undo steps that should not be called from + * within a lock. + */ + write_unlock_bh(&bond->lock); + + /* unregister rx_handler early so bond_handle_frame wouldn't + * be called for this slave anymore. + */ + netdev_rx_handler_unregister(slave_dev); + synchronize_net(); + + if (bond_is_lb(bond)) { + /* must be called only after the slave + * has been detached from the list + */ + bond_alb_deinit_slave(bond, slave); + } + + bond_destroy_slave_symlinks(bond_dev, slave_dev); + bond_del_vlans_from_slave(bond, slave_dev); + + /* If the mode USES_PRIMARY, then we should only remove its + * promisc and mc settings if it was the curr_active_slave, but that was + * already taken care of above when we detached the slave + */ + if (!USES_PRIMARY(bond->params.mode)) { + /* unset promiscuity level from slave */ + if (bond_dev->flags & IFF_PROMISC) + dev_set_promiscuity(slave_dev, -1); + + /* unset allmulti level from slave */ + if (bond_dev->flags & IFF_ALLMULTI) + dev_set_allmulti(slave_dev, -1); + + /* flush master's mc_list from slave */ + netif_addr_lock_bh(bond_dev); + bond_mc_list_flush(bond_dev, slave_dev); + netif_addr_unlock_bh(bond_dev); + } + + netdev_set_bond_master(slave_dev, NULL); + + slave_disable_netpoll(slave); + + /* close slave before restoring its mac address */ + dev_close(slave_dev); + + if (!bond->params.fail_over_mac) { + /* restore original ("permanent") mac address*/ + memcpy(addr.sa_data, slave->perm_hwaddr, ETH_ALEN); + addr.sa_family = slave_dev->type; + dev_set_mac_address(slave_dev, &addr); + } + + kfree(slave); + + /* re-acquire the lock before getting the next slave */ + write_lock_bh(&bond->lock); + } + + /* zero the mac address of the master so it will be + * set by the application to the mac address of the + * first slave + */ + memset(bond_dev->dev_addr, 0, bond_dev->addr_len); + + if (bond_vlan_used(bond)) { + pr_warning("%s: Warning: clearing HW address of %s while it still has VLANs.\n", + bond_dev->name, bond_dev->name); + pr_warning("%s: When re-adding slaves, make sure the bond's HW address matches its VLANs'.\n", + bond_dev->name); + } + + pr_info("%s: released all slaves\n", bond_dev->name); + +out: + write_unlock_bh(&bond->lock); + + bond_compute_features(bond); + + return 0; +} + +/* + * This function changes the active slave to slave <slave_dev>. + * It returns -EINVAL in the following cases. + * - <slave_dev> is not found in the list. + * - There is not active slave now. + * - <slave_dev> is already active. + * - The link state of <slave_dev> is not BOND_LINK_UP. + * - <slave_dev> is not running. + * In these cases, this function does nothing. + * In the other cases, current_slave pointer is changed and 0 is returned. + */ +static int bond_ioctl_change_active(struct net_device *bond_dev, struct net_device *slave_dev) +{ + struct bonding *bond = netdev_priv(bond_dev); + struct slave *old_active = NULL; + struct slave *new_active = NULL; + int res = 0; + + if (!USES_PRIMARY(bond->params.mode)) + return -EINVAL; + + /* Verify that master_dev is indeed the master of slave_dev */ + if (!(slave_dev->flags & IFF_SLAVE) || (slave_dev->master != bond_dev)) + return -EINVAL; + + read_lock(&bond->lock); + + read_lock(&bond->curr_slave_lock); + old_active = bond->curr_active_slave; + read_unlock(&bond->curr_slave_lock); + + new_active = bond_get_slave_by_dev(bond, slave_dev); + + /* + * Changing to the current active: do nothing; return success. + */ + if (new_active && (new_active == old_active)) { + read_unlock(&bond->lock); + return 0; + } + + if ((new_active) && + (old_active) && + (new_active->link == BOND_LINK_UP) && + IS_UP(new_active->dev)) { + block_netpoll_tx(); + write_lock_bh(&bond->curr_slave_lock); + bond_change_active_slave(bond, new_active); + write_unlock_bh(&bond->curr_slave_lock); + unblock_netpoll_tx(); + } else + res = -EINVAL; + + read_unlock(&bond->lock); + + return res; +} + +static int bond_info_query(struct net_device *bond_dev, struct ifbond *info) +{ + struct bonding *bond = netdev_priv(bond_dev); + + info->bond_mode = bond->params.mode; + info->miimon = bond->params.miimon; + + read_lock(&bond->lock); + info->num_slaves = bond->slave_cnt; + read_unlock(&bond->lock); + + return 0; +} + +static int bond_slave_info_query(struct net_device *bond_dev, struct ifslave *info) +{ + struct bonding *bond = netdev_priv(bond_dev); + struct slave *slave; + int i, res = -ENODEV; + + read_lock(&bond->lock); + + bond_for_each_slave(bond, slave, i) { + if (i == (int)info->slave_id) { + res = 0; + strcpy(info->slave_name, slave->dev->name); + info->link = slave->link; + info->state = bond_slave_state(slave); + info->link_failure_count = slave->link_failure_count; + break; + } + } + + read_unlock(&bond->lock); + + return res; +} + +/*-------------------------------- Monitoring -------------------------------*/ + + +static int bond_miimon_inspect(struct bonding *bond) +{ + struct slave *slave; + int i, link_state, commit = 0; + bool ignore_updelay; + + ignore_updelay = !bond->curr_active_slave ? true : false; + + bond_for_each_slave(bond, slave, i) { + slave->new_link = BOND_LINK_NOCHANGE; + + link_state = bond_check_dev_link(bond, slave->dev, 0); + + switch (slave->link) { + case BOND_LINK_UP: + if (link_state) + continue; + + slave->link = BOND_LINK_FAIL; + slave->delay = bond->params.downdelay; + if (slave->delay) { + pr_info("%s: link status down for %sinterface %s, disabling it in %d ms.\n", + bond->dev->name, + (bond->params.mode == + BOND_MODE_ACTIVEBACKUP) ? + (bond_is_active_slave(slave) ? + "active " : "backup ") : "", + slave->dev->name, + bond->params.downdelay * bond->params.miimon); + } + /*FALLTHRU*/ + case BOND_LINK_FAIL: + if (link_state) { + /* + * recovered before downdelay expired + */ + slave->link = BOND_LINK_UP; + slave->jiffies = jiffies; + pr_info("%s: link status up again after %d ms for interface %s.\n", + bond->dev->name, + (bond->params.downdelay - slave->delay) * + bond->params.miimon, + slave->dev->name); + continue; + } + + if (slave->delay <= 0) { + slave->new_link = BOND_LINK_DOWN; + commit++; + continue; + } + + slave->delay--; + break; + + case BOND_LINK_DOWN: + if (!link_state) + continue; + + slave->link = BOND_LINK_BACK; + slave->delay = bond->params.updelay; + + if (slave->delay) { + pr_info("%s: link status up for interface %s, enabling it in %d ms.\n", + bond->dev->name, slave->dev->name, + ignore_updelay ? 0 : + bond->params.updelay * + bond->params.miimon); + } + /*FALLTHRU*/ + case BOND_LINK_BACK: + if (!link_state) { + slave->link = BOND_LINK_DOWN; + pr_info("%s: link status down again after %d ms for interface %s.\n", + bond->dev->name, + (bond->params.updelay - slave->delay) * + bond->params.miimon, + slave->dev->name); + + continue; + } + + if (ignore_updelay) + slave->delay = 0; + + if (slave->delay <= 0) { + slave->new_link = BOND_LINK_UP; + commit++; + ignore_updelay = false; + continue; + } + + slave->delay--; + break; + } + } + + return commit; +} + +static void bond_miimon_commit(struct bonding *bond) +{ + struct slave *slave; + int i; + + bond_for_each_slave(bond, slave, i) { + switch (slave->new_link) { + case BOND_LINK_NOCHANGE: + continue; + + case BOND_LINK_UP: + slave->link = BOND_LINK_UP; + slave->jiffies = jiffies; + + if (bond->params.mode == BOND_MODE_8023AD) { + /* prevent it from being the active one */ + bond_set_backup_slave(slave); + } else if (bond->params.mode != BOND_MODE_ACTIVEBACKUP) { + /* make it immediately active */ + bond_set_active_slave(slave); + } else if (slave != bond->primary_slave) { + /* prevent it from being the active one */ + bond_set_backup_slave(slave); + } + + bond_update_speed_duplex(slave); + + pr_info("%s: link status definitely up for interface %s, %u Mbps %s duplex.\n", + bond->dev->name, slave->dev->name, + slave->speed, slave->duplex ? "full" : "half"); + + /* notify ad that the link status has changed */ + if (bond->params.mode == BOND_MODE_8023AD) + bond_3ad_handle_link_change(slave, BOND_LINK_UP); + + if (bond_is_lb(bond)) + bond_alb_handle_link_change(bond, slave, + BOND_LINK_UP); + + if (!bond->curr_active_slave || + (slave == bond->primary_slave)) + goto do_failover; + + continue; + + case BOND_LINK_DOWN: + if (slave->link_failure_count < UINT_MAX) + slave->link_failure_count++; + + slave->link = BOND_LINK_DOWN; + + if (bond->params.mode == BOND_MODE_ACTIVEBACKUP || + bond->params.mode == BOND_MODE_8023AD) + bond_set_slave_inactive_flags(slave); + + pr_info("%s: link status definitely down for interface %s, disabling it\n", + bond->dev->name, slave->dev->name); + + if (bond->params.mode == BOND_MODE_8023AD) + bond_3ad_handle_link_change(slave, + BOND_LINK_DOWN); + + if (bond_is_lb(bond)) + bond_alb_handle_link_change(bond, slave, + BOND_LINK_DOWN); + + if (slave == bond->curr_active_slave) + goto do_failover; + + continue; + + default: + pr_err("%s: invalid new link %d on slave %s\n", + bond->dev->name, slave->new_link, + slave->dev->name); + slave->new_link = BOND_LINK_NOCHANGE; + + continue; + } + +do_failover: + ASSERT_RTNL(); + block_netpoll_tx(); + write_lock_bh(&bond->curr_slave_lock); + bond_select_active_slave(bond); + write_unlock_bh(&bond->curr_slave_lock); + unblock_netpoll_tx(); + } + + bond_set_carrier(bond); +} + +/* + * bond_mii_monitor + * + * Really a wrapper that splits the mii monitor into two phases: an + * inspection, then (if inspection indicates something needs to be done) + * an acquisition of appropriate locks followed by a commit phase to + * implement whatever link state changes are indicated. + */ +void bond_mii_monitor(struct work_struct *work) +{ + struct bonding *bond = container_of(work, struct bonding, + mii_work.work); + bool should_notify_peers = false; + unsigned long delay; + + read_lock(&bond->lock); + + delay = msecs_to_jiffies(bond->params.miimon); + + if (bond->slave_cnt == 0) + goto re_arm; + + should_notify_peers = bond_should_notify_peers(bond); + + if (bond_miimon_inspect(bond)) { + read_unlock(&bond->lock); + + /* Race avoidance with bond_close cancel of workqueue */ + if (!rtnl_trylock()) { + read_lock(&bond->lock); + delay = 1; + should_notify_peers = false; + goto re_arm; + } + + read_lock(&bond->lock); + + bond_miimon_commit(bond); + + read_unlock(&bond->lock); + rtnl_unlock(); /* might sleep, hold no other locks */ + read_lock(&bond->lock); + } + +re_arm: + if (bond->params.miimon) + queue_delayed_work(bond->wq, &bond->mii_work, delay); + + read_unlock(&bond->lock); + + if (should_notify_peers) { + if (!rtnl_trylock()) { + read_lock(&bond->lock); + bond->send_peer_notif++; + read_unlock(&bond->lock); + return; + } + netdev_bonding_change(bond->dev, NETDEV_NOTIFY_PEERS); + rtnl_unlock(); + } +} + +static int bond_has_this_ip(struct bonding *bond, __be32 ip) +{ + struct vlan_entry *vlan; + struct net_device *vlan_dev; + + if (ip == bond_confirm_addr(bond->dev, 0, ip)) + return 1; + + list_for_each_entry(vlan, &bond->vlan_list, vlan_list) { + rcu_read_lock(); + vlan_dev = __vlan_find_dev_deep(bond->dev, vlan->vlan_id); + rcu_read_unlock(); + if (vlan_dev && ip == bond_confirm_addr(vlan_dev, 0, ip)) + return 1; + } + + return 0; +} + +/* + * We go to the (large) trouble of VLAN tagging ARP frames because + * switches in VLAN mode (especially if ports are configured as + * "native" to a VLAN) might not pass non-tagged frames. + */ +static void bond_arp_send(struct net_device *slave_dev, int arp_op, __be32 dest_ip, __be32 src_ip, unsigned short vlan_id) +{ + struct sk_buff *skb; + + pr_debug("arp %d on slave %s: dst %x src %x vid %d\n", arp_op, + slave_dev->name, dest_ip, src_ip, vlan_id); + + skb = arp_create(arp_op, ETH_P_ARP, dest_ip, slave_dev, src_ip, + NULL, slave_dev->dev_addr, NULL); + + if (!skb) { + pr_err("ARP packet allocation failed\n"); + return; + } + if (vlan_id) { + skb = vlan_put_tag(skb, vlan_id); + if (!skb) { + pr_err("failed to insert VLAN tag\n"); + return; + } + } + arp_xmit(skb); +} + + +static void bond_arp_send_all(struct bonding *bond, struct slave *slave) +{ + int i, vlan_id; + __be32 *targets = bond->params.arp_targets; + struct vlan_entry *vlan; + struct net_device *vlan_dev = NULL; + struct rtable *rt; + + for (i = 0; (i < BOND_MAX_ARP_TARGETS); i++) { + __be32 addr; + if (!targets[i]) + break; + pr_debug("basa: target %x\n", targets[i]); + if (!bond_vlan_used(bond)) { + pr_debug("basa: empty vlan: arp_send\n"); + addr = bond_confirm_addr(bond->dev, targets[i], 0); + bond_arp_send(slave->dev, ARPOP_REQUEST, targets[i], + addr, 0); + continue; + } + + /* + * If VLANs are configured, we do a route lookup to + * determine which VLAN interface would be used, so we + * can tag the ARP with the proper VLAN tag. + */ + rt = ip_route_output(dev_net(bond->dev), targets[i], 0, + RTO_ONLINK, 0); + if (IS_ERR(rt)) { + if (net_ratelimit()) { + pr_warning("%s: no route to arp_ip_target %pI4\n", + bond->dev->name, &targets[i]); + } + continue; + } + + /* + * This target is not on a VLAN + */ + if (rt->dst.dev == bond->dev) { + ip_rt_put(rt); + pr_debug("basa: rtdev == bond->dev: arp_send\n"); + addr = bond_confirm_addr(bond->dev, targets[i], 0); + bond_arp_send(slave->dev, ARPOP_REQUEST, targets[i], + addr, 0); + continue; + } + + vlan_id = 0; + list_for_each_entry(vlan, &bond->vlan_list, vlan_list) { + rcu_read_lock(); + vlan_dev = __vlan_find_dev_deep(bond->dev, + vlan->vlan_id); + rcu_read_unlock(); + if (vlan_dev == rt->dst.dev) { + vlan_id = vlan->vlan_id; + pr_debug("basa: vlan match on %s %d\n", + vlan_dev->name, vlan_id); + break; + } + } + + if (vlan_id && vlan_dev) { + ip_rt_put(rt); + addr = bond_confirm_addr(vlan_dev, targets[i], 0); + bond_arp_send(slave->dev, ARPOP_REQUEST, targets[i], + addr, vlan_id); + continue; + } + + if (net_ratelimit()) { + pr_warning("%s: no path to arp_ip_target %pI4 via rt.dev %s\n", + bond->dev->name, &targets[i], + rt->dst.dev ? rt->dst.dev->name : "NULL"); + } + ip_rt_put(rt); + } +} + +static void bond_validate_arp(struct bonding *bond, struct slave *slave, __be32 sip, __be32 tip) +{ + int i; + __be32 *targets = bond->params.arp_targets; + + for (i = 0; (i < BOND_MAX_ARP_TARGETS) && targets[i]; i++) { + pr_debug("bva: sip %pI4 tip %pI4 t[%d] %pI4 bhti(tip) %d\n", + &sip, &tip, i, &targets[i], + bond_has_this_ip(bond, tip)); + if (sip == targets[i]) { + if (bond_has_this_ip(bond, tip)) + slave->last_arp_rx = jiffies; + return; + } + } +} + +static int bond_arp_rcv(struct sk_buff *skb, struct bonding *bond, + struct slave *slave) +{ + struct arphdr *arp; + unsigned char *arp_ptr; + __be32 sip, tip; + + if (skb->protocol != __cpu_to_be16(ETH_P_ARP)) + return RX_HANDLER_ANOTHER; + + read_lock(&bond->lock); + + pr_debug("bond_arp_rcv: bond %s skb->dev %s\n", + bond->dev->name, skb->dev->name); + + if (!pskb_may_pull(skb, arp_hdr_len(bond->dev))) + goto out_unlock; + + arp = arp_hdr(skb); + if (arp->ar_hln != bond->dev->addr_len || + skb->pkt_type == PACKET_OTHERHOST || + skb->pkt_type == PACKET_LOOPBACK || + arp->ar_hrd != htons(ARPHRD_ETHER) || + arp->ar_pro != htons(ETH_P_IP) || + arp->ar_pln != 4) + goto out_unlock; + + arp_ptr = (unsigned char *)(arp + 1); + arp_ptr += bond->dev->addr_len; + memcpy(&sip, arp_ptr, 4); + arp_ptr += 4 + bond->dev->addr_len; + memcpy(&tip, arp_ptr, 4); + + pr_debug("bond_arp_rcv: %s %s/%d av %d sv %d sip %pI4 tip %pI4\n", + bond->dev->name, slave->dev->name, bond_slave_state(slave), + bond->params.arp_validate, slave_do_arp_validate(bond, slave), + &sip, &tip); + + /* + * Backup slaves won't see the ARP reply, but do come through + * here for each ARP probe (so we swap the sip/tip to validate + * the probe). In a "redundant switch, common router" type of + * configuration, the ARP probe will (hopefully) travel from + * the active, through one switch, the router, then the other + * switch before reaching the backup. + */ + if (bond_is_active_slave(slave)) + bond_validate_arp(bond, slave, sip, tip); + else + bond_validate_arp(bond, slave, tip, sip); + +out_unlock: + read_unlock(&bond->lock); + return RX_HANDLER_ANOTHER; +} + +/* + * this function is called regularly to monitor each slave's link + * ensuring that traffic is being sent and received when arp monitoring + * is used in load-balancing mode. if the adapter has been dormant, then an + * arp is transmitted to generate traffic. see activebackup_arp_monitor for + * arp monitoring in active backup mode. + */ +void bond_loadbalance_arp_mon(struct work_struct *work) +{ + struct bonding *bond = container_of(work, struct bonding, + arp_work.work); + struct slave *slave, *oldcurrent; + int do_failover = 0; + int delta_in_ticks; + int i; + + read_lock(&bond->lock); + + delta_in_ticks = msecs_to_jiffies(bond->params.arp_interval); + + if (bond->slave_cnt == 0) + goto re_arm; + + read_lock(&bond->curr_slave_lock); + oldcurrent = bond->curr_active_slave; + read_unlock(&bond->curr_slave_lock); + + /* see if any of the previous devices are up now (i.e. they have + * xmt and rcv traffic). the curr_active_slave does not come into + * the picture unless it is null. also, slave->jiffies is not needed + * here because we send an arp on each slave and give a slave as + * long as it needs to get the tx/rx within the delta. + * TODO: what about up/down delay in arp mode? it wasn't here before + * so it can wait + */ + bond_for_each_slave(bond, slave, i) { + unsigned long trans_start = dev_trans_start(slave->dev); + + if (slave->link != BOND_LINK_UP) { + if (time_in_range(jiffies, + trans_start - delta_in_ticks, + trans_start + delta_in_ticks) && + time_in_range(jiffies, + slave->dev->last_rx - delta_in_ticks, + slave->dev->last_rx + delta_in_ticks)) { + + slave->link = BOND_LINK_UP; + bond_set_active_slave(slave); + + /* primary_slave has no meaning in round-robin + * mode. the window of a slave being up and + * curr_active_slave being null after enslaving + * is closed. + */ + if (!oldcurrent) { + pr_info("%s: link status definitely up for interface %s, ", + bond->dev->name, + slave->dev->name); + do_failover = 1; + } else { + pr_info("%s: interface %s is now up\n", + bond->dev->name, + slave->dev->name); + } + } + } else { + /* slave->link == BOND_LINK_UP */ + + /* not all switches will respond to an arp request + * when the source ip is 0, so don't take the link down + * if we don't know our ip yet + */ + if (!time_in_range(jiffies, + trans_start - delta_in_ticks, + trans_start + 2 * delta_in_ticks) || + !time_in_range(jiffies, + slave->dev->last_rx - delta_in_ticks, + slave->dev->last_rx + 2 * delta_in_ticks)) { + + slave->link = BOND_LINK_DOWN; + bond_set_backup_slave(slave); + + if (slave->link_failure_count < UINT_MAX) + slave->link_failure_count++; + + pr_info("%s: interface %s is now down.\n", + bond->dev->name, + slave->dev->name); + + if (slave == oldcurrent) + do_failover = 1; + } + } + + /* note: if switch is in round-robin mode, all links + * must tx arp to ensure all links rx an arp - otherwise + * links may oscillate or not come up at all; if switch is + * in something like xor mode, there is nothing we can + * do - all replies will be rx'ed on same link causing slaves + * to be unstable during low/no traffic periods + */ + if (IS_UP(slave->dev)) + bond_arp_send_all(bond, slave); + } + + if (do_failover) { + block_netpoll_tx(); + write_lock_bh(&bond->curr_slave_lock); + + bond_select_active_slave(bond); + + write_unlock_bh(&bond->curr_slave_lock); + unblock_netpoll_tx(); + } + +re_arm: + if (bond->params.arp_interval) + queue_delayed_work(bond->wq, &bond->arp_work, delta_in_ticks); + + read_unlock(&bond->lock); +} + +/* + * Called to inspect slaves for active-backup mode ARP monitor link state + * changes. Sets new_link in slaves to specify what action should take + * place for the slave. Returns 0 if no changes are found, >0 if changes + * to link states must be committed. + * + * Called with bond->lock held for read. + */ +static int bond_ab_arp_inspect(struct bonding *bond, int delta_in_ticks) +{ + struct slave *slave; + int i, commit = 0; + unsigned long trans_start; + + bond_for_each_slave(bond, slave, i) { + slave->new_link = BOND_LINK_NOCHANGE; + + if (slave->link != BOND_LINK_UP) { + if (time_in_range(jiffies, + slave_last_rx(bond, slave) - delta_in_ticks, + slave_last_rx(bond, slave) + delta_in_ticks)) { + + slave->new_link = BOND_LINK_UP; + commit++; + } + + continue; + } + + /* + * Give slaves 2*delta after being enslaved or made + * active. This avoids bouncing, as the last receive + * times need a full ARP monitor cycle to be updated. + */ + if (time_in_range(jiffies, + slave->jiffies - delta_in_ticks, + slave->jiffies + 2 * delta_in_ticks)) + continue; + + /* + * Backup slave is down if: + * - No current_arp_slave AND + * - more than 3*delta since last receive AND + * - the bond has an IP address + * + * Note: a non-null current_arp_slave indicates + * the curr_active_slave went down and we are + * searching for a new one; under this condition + * we only take the curr_active_slave down - this + * gives each slave a chance to tx/rx traffic + * before being taken out + */ + if (!bond_is_active_slave(slave) && + !bond->current_arp_slave && + !time_in_range(jiffies, + slave_last_rx(bond, slave) - delta_in_ticks, + slave_last_rx(bond, slave) + 3 * delta_in_ticks)) { + + slave->new_link = BOND_LINK_DOWN; + commit++; + } + + /* + * Active slave is down if: + * - more than 2*delta since transmitting OR + * - (more than 2*delta since receive AND + * the bond has an IP address) + */ + trans_start = dev_trans_start(slave->dev); + if (bond_is_active_slave(slave) && + (!time_in_range(jiffies, + trans_start - delta_in_ticks, + trans_start + 2 * delta_in_ticks) || + !time_in_range(jiffies, + slave_last_rx(bond, slave) - delta_in_ticks, + slave_last_rx(bond, slave) + 2 * delta_in_ticks))) { + + slave->new_link = BOND_LINK_DOWN; + commit++; + } + } + + return commit; +} + +/* + * Called to commit link state changes noted by inspection step of + * active-backup mode ARP monitor. + * + * Called with RTNL and bond->lock for read. + */ +static void bond_ab_arp_commit(struct bonding *bond, int delta_in_ticks) +{ + struct slave *slave; + int i; + unsigned long trans_start; + + bond_for_each_slave(bond, slave, i) { + switch (slave->new_link) { + case BOND_LINK_NOCHANGE: + continue; + + case BOND_LINK_UP: + trans_start = dev_trans_start(slave->dev); + if ((!bond->curr_active_slave && + time_in_range(jiffies, + trans_start - delta_in_ticks, + trans_start + delta_in_ticks)) || + bond->curr_active_slave != slave) { + slave->link = BOND_LINK_UP; + if (bond->current_arp_slave) { + bond_set_slave_inactive_flags( + bond->current_arp_slave); + bond->current_arp_slave = NULL; + } + + pr_info("%s: link status definitely up for interface %s.\n", + bond->dev->name, slave->dev->name); + + if (!bond->curr_active_slave || + (slave == bond->primary_slave)) + goto do_failover; + + } + + continue; + + case BOND_LINK_DOWN: + if (slave->link_failure_count < UINT_MAX) + slave->link_failure_count++; + + slave->link = BOND_LINK_DOWN; + bond_set_slave_inactive_flags(slave); + + pr_info("%s: link status definitely down for interface %s, disabling it\n", + bond->dev->name, slave->dev->name); + + if (slave == bond->curr_active_slave) { + bond->current_arp_slave = NULL; + goto do_failover; + } + + continue; + + default: + pr_err("%s: impossible: new_link %d on slave %s\n", + bond->dev->name, slave->new_link, + slave->dev->name); + continue; + } + +do_failover: + ASSERT_RTNL(); + block_netpoll_tx(); + write_lock_bh(&bond->curr_slave_lock); + bond_select_active_slave(bond); + write_unlock_bh(&bond->curr_slave_lock); + unblock_netpoll_tx(); + } + + bond_set_carrier(bond); +} + +/* + * Send ARP probes for active-backup mode ARP monitor. + * + * Called with bond->lock held for read. + */ +static void bond_ab_arp_probe(struct bonding *bond) +{ + struct slave *slave; + int i; + + read_lock(&bond->curr_slave_lock); + + if (bond->current_arp_slave && bond->curr_active_slave) + pr_info("PROBE: c_arp %s && cas %s BAD\n", + bond->current_arp_slave->dev->name, + bond->curr_active_slave->dev->name); + + if (bond->curr_active_slave) { + bond_arp_send_all(bond, bond->curr_active_slave); + read_unlock(&bond->curr_slave_lock); + return; + } + + read_unlock(&bond->curr_slave_lock); + + /* if we don't have a curr_active_slave, search for the next available + * backup slave from the current_arp_slave and make it the candidate + * for becoming the curr_active_slave + */ + + if (!bond->current_arp_slave) { + bond->current_arp_slave = bond->first_slave; + if (!bond->current_arp_slave) + return; + } + + bond_set_slave_inactive_flags(bond->current_arp_slave); + + /* search for next candidate */ + bond_for_each_slave_from(bond, slave, i, bond->current_arp_slave->next) { + if (IS_UP(slave->dev)) { + slave->link = BOND_LINK_BACK; + bond_set_slave_active_flags(slave); + bond_arp_send_all(bond, slave); + slave->jiffies = jiffies; + bond->current_arp_slave = slave; + break; + } + + /* if the link state is up at this point, we + * mark it down - this can happen if we have + * simultaneous link failures and + * reselect_active_interface doesn't make this + * one the current slave so it is still marked + * up when it is actually down + */ + if (slave->link == BOND_LINK_UP) { + slave->link = BOND_LINK_DOWN; + if (slave->link_failure_count < UINT_MAX) + slave->link_failure_count++; + + bond_set_slave_inactive_flags(slave); + + pr_info("%s: backup interface %s is now down.\n", + bond->dev->name, slave->dev->name); + } + } +} + +void bond_activebackup_arp_mon(struct work_struct *work) +{ + struct bonding *bond = container_of(work, struct bonding, + arp_work.work); + bool should_notify_peers = false; + int delta_in_ticks; + + read_lock(&bond->lock); + + delta_in_ticks = msecs_to_jiffies(bond->params.arp_interval); + + if (bond->slave_cnt == 0) + goto re_arm; + + should_notify_peers = bond_should_notify_peers(bond); + + if (bond_ab_arp_inspect(bond, delta_in_ticks)) { + read_unlock(&bond->lock); + + /* Race avoidance with bond_close flush of workqueue */ + if (!rtnl_trylock()) { + read_lock(&bond->lock); + delta_in_ticks = 1; + should_notify_peers = false; + goto re_arm; + } + + read_lock(&bond->lock); + + bond_ab_arp_commit(bond, delta_in_ticks); + + read_unlock(&bond->lock); + rtnl_unlock(); + read_lock(&bond->lock); + } + + bond_ab_arp_probe(bond); + +re_arm: + if (bond->params.arp_interval) + queue_delayed_work(bond->wq, &bond->arp_work, delta_in_ticks); + + read_unlock(&bond->lock); + + if (should_notify_peers) { + if (!rtnl_trylock()) { + read_lock(&bond->lock); + bond->send_peer_notif++; + read_unlock(&bond->lock); + return; + } + netdev_bonding_change(bond->dev, NETDEV_NOTIFY_PEERS); + rtnl_unlock(); + } +} + +/*-------------------------- netdev event handling --------------------------*/ + +/* + * Change device name + */ +static int bond_event_changename(struct bonding *bond) +{ + bond_remove_proc_entry(bond); + bond_create_proc_entry(bond); + + bond_debug_reregister(bond); + + return NOTIFY_DONE; +} + +static int bond_master_netdev_event(unsigned long event, + struct net_device *bond_dev) +{ + struct bonding *event_bond = netdev_priv(bond_dev); + + switch (event) { + case NETDEV_CHANGENAME: + return bond_event_changename(event_bond); + default: + break; + } + + return NOTIFY_DONE; +} + +static int bond_slave_netdev_event(unsigned long event, + struct net_device *slave_dev) +{ + struct net_device *bond_dev = slave_dev->master; + struct bonding *bond = netdev_priv(bond_dev); + struct slave *slave = NULL; + + switch (event) { + case NETDEV_UNREGISTER: + if (bond_dev) { + if (bond->setup_by_slave) + bond_release_and_destroy(bond_dev, slave_dev); + else + bond_release(bond_dev, slave_dev); + } + break; + case NETDEV_UP: + case NETDEV_CHANGE: + slave = bond_get_slave_by_dev(bond, slave_dev); + if (slave) { + u32 old_speed = slave->speed; + u8 old_duplex = slave->duplex; + + bond_update_speed_duplex(slave); + + if (bond->params.mode == BOND_MODE_8023AD) { + if (old_speed != slave->speed) + bond_3ad_adapter_speed_changed(slave); + if (old_duplex != slave->duplex) + bond_3ad_adapter_duplex_changed(slave); + } + } + + break; + case NETDEV_DOWN: + /* + * ... Or is it this? + */ + break; + case NETDEV_CHANGEMTU: + /* + * TODO: Should slaves be allowed to + * independently alter their MTU? For + * an active-backup bond, slaves need + * not be the same type of device, so + * MTUs may vary. For other modes, + * slaves arguably should have the + * same MTUs. To do this, we'd need to + * take over the slave's change_mtu + * function for the duration of their + * servitude. + */ + break; + case NETDEV_CHANGENAME: + /* + * TODO: handle changing the primary's name + */ + break; + case NETDEV_FEAT_CHANGE: + bond_compute_features(bond); + break; + default: + break; + } + + return NOTIFY_DONE; +} + +/* + * bond_netdev_event: handle netdev notifier chain events. + * + * This function receives events for the netdev chain. The caller (an + * ioctl handler calling blocking_notifier_call_chain) holds the necessary + * locks for us to safely manipulate the slave devices (RTNL lock, + * dev_probe_lock). + */ +static int bond_netdev_event(struct notifier_block *this, + unsigned long event, void *ptr) +{ + struct net_device *event_dev = (struct net_device *)ptr; + + pr_debug("event_dev: %s, event: %lx\n", + event_dev ? event_dev->name : "None", + event); + + if (!(event_dev->priv_flags & IFF_BONDING)) + return NOTIFY_DONE; + + if (event_dev->flags & IFF_MASTER) { + pr_debug("IFF_MASTER\n"); + return bond_master_netdev_event(event, event_dev); + } + + if (event_dev->flags & IFF_SLAVE) { + pr_debug("IFF_SLAVE\n"); + return bond_slave_netdev_event(event, event_dev); + } + + return NOTIFY_DONE; +} + +static struct notifier_block bond_netdev_notifier = { + .notifier_call = bond_netdev_event, +}; + +/*---------------------------- Hashing Policies -----------------------------*/ + +/* + * Hash for the output device based upon layer 2 and layer 3 data. If + * the packet is not IP mimic bond_xmit_hash_policy_l2() + */ +static int bond_xmit_hash_policy_l23(struct sk_buff *skb, int count) +{ + struct ethhdr *data = (struct ethhdr *)skb->data; + struct iphdr *iph = ip_hdr(skb); + + if (skb->protocol == htons(ETH_P_IP)) { + return ((ntohl(iph->saddr ^ iph->daddr) & 0xffff) ^ + (data->h_dest[5] ^ data->h_source[5])) % count; + } + + return (data->h_dest[5] ^ data->h_source[5]) % count; +} + +/* + * Hash for the output device based upon layer 3 and layer 4 data. If + * the packet is a frag or not TCP or UDP, just use layer 3 data. If it is + * altogether not IP, mimic bond_xmit_hash_policy_l2() + */ +static int bond_xmit_hash_policy_l34(struct sk_buff *skb, int count) +{ + struct ethhdr *data = (struct ethhdr *)skb->data; + struct iphdr *iph = ip_hdr(skb); + __be16 *layer4hdr = (__be16 *)((u32 *)iph + iph->ihl); + int layer4_xor = 0; + + if (skb->protocol == htons(ETH_P_IP)) { + if (!ip_is_fragment(iph) && + (iph->protocol == IPPROTO_TCP || + iph->protocol == IPPROTO_UDP)) { + layer4_xor = ntohs((*layer4hdr ^ *(layer4hdr + 1))); + } + return (layer4_xor ^ + ((ntohl(iph->saddr ^ iph->daddr)) & 0xffff)) % count; + + } + + return (data->h_dest[5] ^ data->h_source[5]) % count; +} + +/* + * Hash for the output device based upon layer 2 data + */ +static int bond_xmit_hash_policy_l2(struct sk_buff *skb, int count) +{ + struct ethhdr *data = (struct ethhdr *)skb->data; + + return (data->h_dest[5] ^ data->h_source[5]) % count; +} + +/*-------------------------- Device entry points ----------------------------*/ + +static int bond_open(struct net_device *bond_dev) +{ + struct bonding *bond = netdev_priv(bond_dev); + struct slave *slave; + int i; + + /* reset slave->backup and slave->inactive */ + read_lock(&bond->lock); + if (bond->slave_cnt > 0) { + read_lock(&bond->curr_slave_lock); + bond_for_each_slave(bond, slave, i) { + if ((bond->params.mode == BOND_MODE_ACTIVEBACKUP) + && (slave != bond->curr_active_slave)) { + bond_set_slave_inactive_flags(slave); + } else { + bond_set_slave_active_flags(slave); + } + } + read_unlock(&bond->curr_slave_lock); + } + read_unlock(&bond->lock); + + INIT_DELAYED_WORK(&bond->mcast_work, bond_resend_igmp_join_requests_delayed); + + if (bond_is_lb(bond)) { + /* bond_alb_initialize must be called before the timer + * is started. + */ + if (bond_alb_initialize(bond, (bond->params.mode == BOND_MODE_ALB))) { + /* something went wrong - fail the open operation */ + return -ENOMEM; + } + + INIT_DELAYED_WORK(&bond->alb_work, bond_alb_monitor); + queue_delayed_work(bond->wq, &bond->alb_work, 0); + } + + if (bond->params.miimon) { /* link check interval, in milliseconds. */ + INIT_DELAYED_WORK(&bond->mii_work, bond_mii_monitor); + queue_delayed_work(bond->wq, &bond->mii_work, 0); + } + + if (bond->params.arp_interval) { /* arp interval, in milliseconds. */ + if (bond->params.mode == BOND_MODE_ACTIVEBACKUP) + INIT_DELAYED_WORK(&bond->arp_work, + bond_activebackup_arp_mon); + else + INIT_DELAYED_WORK(&bond->arp_work, + bond_loadbalance_arp_mon); + + queue_delayed_work(bond->wq, &bond->arp_work, 0); + if (bond->params.arp_validate) + bond->recv_probe = bond_arp_rcv; + } + + if (bond->params.mode == BOND_MODE_8023AD) { + INIT_DELAYED_WORK(&bond->ad_work, bond_3ad_state_machine_handler); + queue_delayed_work(bond->wq, &bond->ad_work, 0); + /* register to receive LACPDUs */ + bond->recv_probe = bond_3ad_lacpdu_recv; + bond_3ad_initiate_agg_selection(bond, 1); + } + + return 0; +} + +static int bond_close(struct net_device *bond_dev) +{ + struct bonding *bond = netdev_priv(bond_dev); + + write_lock_bh(&bond->lock); + + bond->send_peer_notif = 0; + + write_unlock_bh(&bond->lock); + + if (bond->params.miimon) { /* link check interval, in milliseconds. */ + cancel_delayed_work_sync(&bond->mii_work); + } + + if (bond->params.arp_interval) { /* arp interval, in milliseconds. */ + cancel_delayed_work_sync(&bond->arp_work); + } + + switch (bond->params.mode) { + case BOND_MODE_8023AD: + cancel_delayed_work_sync(&bond->ad_work); + break; + case BOND_MODE_TLB: + case BOND_MODE_ALB: + cancel_delayed_work_sync(&bond->alb_work); + break; + default: + break; + } + + if (delayed_work_pending(&bond->mcast_work)) + cancel_delayed_work_sync(&bond->mcast_work); + + if (bond_is_lb(bond)) { + /* Must be called only after all + * slaves have been released + */ + bond_alb_deinitialize(bond); + } + bond->recv_probe = NULL; + + return 0; +} + +static struct rtnl_link_stats64 *bond_get_stats(struct net_device *bond_dev, + struct rtnl_link_stats64 *stats) +{ + struct bonding *bond = netdev_priv(bond_dev); + struct rtnl_link_stats64 temp; + struct slave *slave; + int i; + + memset(stats, 0, sizeof(*stats)); + + read_lock_bh(&bond->lock); + + bond_for_each_slave(bond, slave, i) { + const struct rtnl_link_stats64 *sstats = + dev_get_stats(slave->dev, &temp); + + stats->rx_packets += sstats->rx_packets; + stats->rx_bytes += sstats->rx_bytes; + stats->rx_errors += sstats->rx_errors; + stats->rx_dropped += sstats->rx_dropped; + + stats->tx_packets += sstats->tx_packets; + stats->tx_bytes += sstats->tx_bytes; + stats->tx_errors += sstats->tx_errors; + stats->tx_dropped += sstats->tx_dropped; + + stats->multicast += sstats->multicast; + stats->collisions += sstats->collisions; + + stats->rx_length_errors += sstats->rx_length_errors; + stats->rx_over_errors += sstats->rx_over_errors; + stats->rx_crc_errors += sstats->rx_crc_errors; + stats->rx_frame_errors += sstats->rx_frame_errors; + stats->rx_fifo_errors += sstats->rx_fifo_errors; + stats->rx_missed_errors += sstats->rx_missed_errors; + + stats->tx_aborted_errors += sstats->tx_aborted_errors; + stats->tx_carrier_errors += sstats->tx_carrier_errors; + stats->tx_fifo_errors += sstats->tx_fifo_errors; + stats->tx_heartbeat_errors += sstats->tx_heartbeat_errors; + stats->tx_window_errors += sstats->tx_window_errors; + } + + read_unlock_bh(&bond->lock); + + return stats; +} + +static int bond_do_ioctl(struct net_device *bond_dev, struct ifreq *ifr, int cmd) +{ + struct net_device *slave_dev = NULL; + struct ifbond k_binfo; + struct ifbond __user *u_binfo = NULL; + struct ifslave k_sinfo; + struct ifslave __user *u_sinfo = NULL; + struct mii_ioctl_data *mii = NULL; + int res = 0; + + pr_debug("bond_ioctl: master=%s, cmd=%d\n", bond_dev->name, cmd); + + switch (cmd) { + case SIOCGMIIPHY: + mii = if_mii(ifr); + if (!mii) + return -EINVAL; + + mii->phy_id = 0; + /* Fall Through */ + case SIOCGMIIREG: + /* + * We do this again just in case we were called by SIOCGMIIREG + * instead of SIOCGMIIPHY. + */ + mii = if_mii(ifr); + if (!mii) + return -EINVAL; + + + if (mii->reg_num == 1) { + struct bonding *bond = netdev_priv(bond_dev); + mii->val_out = 0; + read_lock(&bond->lock); + read_lock(&bond->curr_slave_lock); + if (netif_carrier_ok(bond->dev)) + mii->val_out = BMSR_LSTATUS; + + read_unlock(&bond->curr_slave_lock); + read_unlock(&bond->lock); + } + + return 0; + case BOND_INFO_QUERY_OLD: + case SIOCBONDINFOQUERY: + u_binfo = (struct ifbond __user *)ifr->ifr_data; + + if (copy_from_user(&k_binfo, u_binfo, sizeof(ifbond))) + return -EFAULT; + + res = bond_info_query(bond_dev, &k_binfo); + if (res == 0 && + copy_to_user(u_binfo, &k_binfo, sizeof(ifbond))) + return -EFAULT; + + return res; + case BOND_SLAVE_INFO_QUERY_OLD: + case SIOCBONDSLAVEINFOQUERY: + u_sinfo = (struct ifslave __user *)ifr->ifr_data; + + if (copy_from_user(&k_sinfo, u_sinfo, sizeof(ifslave))) + return -EFAULT; + + res = bond_slave_info_query(bond_dev, &k_sinfo); + if (res == 0 && + copy_to_user(u_sinfo, &k_sinfo, sizeof(ifslave))) + return -EFAULT; + + return res; + default: + /* Go on */ + break; + } + + if (!capable(CAP_NET_ADMIN)) + return -EPERM; + + slave_dev = dev_get_by_name(dev_net(bond_dev), ifr->ifr_slave); + + pr_debug("slave_dev=%p:\n", slave_dev); + + if (!slave_dev) + res = -ENODEV; + else { + pr_debug("slave_dev->name=%s:\n", slave_dev->name); + switch (cmd) { + case BOND_ENSLAVE_OLD: + case SIOCBONDENSLAVE: + res = bond_enslave(bond_dev, slave_dev); + break; + case BOND_RELEASE_OLD: + case SIOCBONDRELEASE: + res = bond_release(bond_dev, slave_dev); + break; + case BOND_SETHWADDR_OLD: + case SIOCBONDSETHWADDR: + res = bond_sethwaddr(bond_dev, slave_dev); + break; + case BOND_CHANGE_ACTIVE_OLD: + case SIOCBONDCHANGEACTIVE: + res = bond_ioctl_change_active(bond_dev, slave_dev); + break; + default: + res = -EOPNOTSUPP; + } + + dev_put(slave_dev); + } + + return res; +} + +static bool bond_addr_in_mc_list(unsigned char *addr, + struct netdev_hw_addr_list *list, + int addrlen) +{ + struct netdev_hw_addr *ha; + + netdev_hw_addr_list_for_each(ha, list) + if (!memcmp(ha->addr, addr, addrlen)) + return true; + + return false; +} + +static void bond_change_rx_flags(struct net_device *bond_dev, int change) +{ + struct bonding *bond = netdev_priv(bond_dev); + + if (change & IFF_PROMISC) + bond_set_promiscuity(bond, + bond_dev->flags & IFF_PROMISC ? 1 : -1); + + if (change & IFF_ALLMULTI) + bond_set_allmulti(bond, + bond_dev->flags & IFF_ALLMULTI ? 1 : -1); +} + +static void bond_set_multicast_list(struct net_device *bond_dev) +{ + struct bonding *bond = netdev_priv(bond_dev); + struct netdev_hw_addr *ha; + bool found; + + read_lock(&bond->lock); + + /* looking for addresses to add to slaves' mc list */ + netdev_for_each_mc_addr(ha, bond_dev) { + found = bond_addr_in_mc_list(ha->addr, &bond->mc_list, + bond_dev->addr_len); + if (!found) + bond_mc_add(bond, ha->addr); + } + + /* looking for addresses to delete from slaves' list */ + netdev_hw_addr_list_for_each(ha, &bond->mc_list) { + found = bond_addr_in_mc_list(ha->addr, &bond_dev->mc, + bond_dev->addr_len); + if (!found) + bond_mc_del(bond, ha->addr); + } + + /* save master's multicast list */ + __hw_addr_flush(&bond->mc_list); + __hw_addr_add_multiple(&bond->mc_list, &bond_dev->mc, + bond_dev->addr_len, NETDEV_HW_ADDR_T_MULTICAST); + + read_unlock(&bond->lock); +} + +static int bond_neigh_init(struct neighbour *n) +{ + struct bonding *bond = netdev_priv(n->dev); + struct slave *slave = bond->first_slave; + const struct net_device_ops *slave_ops; + struct neigh_parms parms; + int ret; + + if (!slave) + return 0; + + slave_ops = slave->dev->netdev_ops; + + if (!slave_ops->ndo_neigh_setup) + return 0; + + parms.neigh_setup = NULL; + parms.neigh_cleanup = NULL; + ret = slave_ops->ndo_neigh_setup(slave->dev, &parms); + if (ret) + return ret; + + /* + * Assign slave's neigh_cleanup to neighbour in case cleanup is called + * after the last slave has been detached. Assumes that all slaves + * utilize the same neigh_cleanup (true at this writing as only user + * is ipoib). + */ + n->parms->neigh_cleanup = parms.neigh_cleanup; + + if (!parms.neigh_setup) + return 0; + + return parms.neigh_setup(n); +} + +/* + * The bonding ndo_neigh_setup is called at init time beofre any + * slave exists. So we must declare proxy setup function which will + * be used at run time to resolve the actual slave neigh param setup. + */ +static int bond_neigh_setup(struct net_device *dev, + struct neigh_parms *parms) +{ + parms->neigh_setup = bond_neigh_init; + + return 0; +} + +/* + * Change the MTU of all of a master's slaves to match the master + */ +static int bond_change_mtu(struct net_device *bond_dev, int new_mtu) +{ + struct bonding *bond = netdev_priv(bond_dev); + struct slave *slave, *stop_at; + int res = 0; + int i; + + pr_debug("bond=%p, name=%s, new_mtu=%d\n", bond, + (bond_dev ? bond_dev->name : "None"), new_mtu); + + /* Can't hold bond->lock with bh disabled here since + * some base drivers panic. On the other hand we can't + * hold bond->lock without bh disabled because we'll + * deadlock. The only solution is to rely on the fact + * that we're under rtnl_lock here, and the slaves + * list won't change. This doesn't solve the problem + * of setting the slave's MTU while it is + * transmitting, but the assumption is that the base + * driver can handle that. + * + * TODO: figure out a way to safely iterate the slaves + * list, but without holding a lock around the actual + * call to the base driver. + */ + + bond_for_each_slave(bond, slave, i) { + pr_debug("s %p s->p %p c_m %p\n", + slave, + slave->prev, + slave->dev->netdev_ops->ndo_change_mtu); + + res = dev_set_mtu(slave->dev, new_mtu); + + if (res) { + /* If we failed to set the slave's mtu to the new value + * we must abort the operation even in ACTIVE_BACKUP + * mode, because if we allow the backup slaves to have + * different mtu values than the active slave we'll + * need to change their mtu when doing a failover. That + * means changing their mtu from timer context, which + * is probably not a good idea. + */ + pr_debug("err %d %s\n", res, slave->dev->name); + goto unwind; + } + } + + bond_dev->mtu = new_mtu; + + return 0; + +unwind: + /* unwind from head to the slave that failed */ + stop_at = slave; + bond_for_each_slave_from_to(bond, slave, i, bond->first_slave, stop_at) { + int tmp_res; + + tmp_res = dev_set_mtu(slave->dev, bond_dev->mtu); + if (tmp_res) { + pr_debug("unwind err %d dev %s\n", + tmp_res, slave->dev->name); + } + } + + return res; +} + +/* + * Change HW address + * + * Note that many devices must be down to change the HW address, and + * downing the master releases all slaves. We can make bonds full of + * bonding devices to test this, however. + */ +static int bond_set_mac_address(struct net_device *bond_dev, void *addr) +{ + struct bonding *bond = netdev_priv(bond_dev); + struct sockaddr *sa = addr, tmp_sa; + struct slave *slave, *stop_at; + int res = 0; + int i; + + if (bond->params.mode == BOND_MODE_ALB) + return bond_alb_set_mac_address(bond_dev, addr); + + + pr_debug("bond=%p, name=%s\n", + bond, bond_dev ? bond_dev->name : "None"); + + /* + * If fail_over_mac is set to active, do nothing and return + * success. Returning an error causes ifenslave to fail. + */ + if (bond->params.fail_over_mac == BOND_FOM_ACTIVE) + return 0; + + if (!is_valid_ether_addr(sa->sa_data)) + return -EADDRNOTAVAIL; + + /* Can't hold bond->lock with bh disabled here since + * some base drivers panic. On the other hand we can't + * hold bond->lock without bh disabled because we'll + * deadlock. The only solution is to rely on the fact + * that we're under rtnl_lock here, and the slaves + * list won't change. This doesn't solve the problem + * of setting the slave's hw address while it is + * transmitting, but the assumption is that the base + * driver can handle that. + * + * TODO: figure out a way to safely iterate the slaves + * list, but without holding a lock around the actual + * call to the base driver. + */ + + bond_for_each_slave(bond, slave, i) { + const struct net_device_ops *slave_ops = slave->dev->netdev_ops; + pr_debug("slave %p %s\n", slave, slave->dev->name); + + if (slave_ops->ndo_set_mac_address == NULL) { + res = -EOPNOTSUPP; + pr_debug("EOPNOTSUPP %s\n", slave->dev->name); + goto unwind; + } + + res = dev_set_mac_address(slave->dev, addr); + if (res) { + /* TODO: consider downing the slave + * and retry ? + * User should expect communications + * breakage anyway until ARP finish + * updating, so... + */ + pr_debug("err %d %s\n", res, slave->dev->name); + goto unwind; + } + } + + /* success */ + memcpy(bond_dev->dev_addr, sa->sa_data, bond_dev->addr_len); + return 0; + +unwind: + memcpy(tmp_sa.sa_data, bond_dev->dev_addr, bond_dev->addr_len); + tmp_sa.sa_family = bond_dev->type; + + /* unwind from head to the slave that failed */ + stop_at = slave; + bond_for_each_slave_from_to(bond, slave, i, bond->first_slave, stop_at) { + int tmp_res; + + tmp_res = dev_set_mac_address(slave->dev, &tmp_sa); + if (tmp_res) { + pr_debug("unwind err %d dev %s\n", + tmp_res, slave->dev->name); + } + } + + return res; +} + +static int bond_xmit_roundrobin(struct sk_buff *skb, struct net_device *bond_dev) +{ + struct bonding *bond = netdev_priv(bond_dev); + struct slave *slave, *start_at; + int i, slave_no, res = 1; + struct iphdr *iph = ip_hdr(skb); + + /* + * Start with the curr_active_slave that joined the bond as the + * default for sending IGMP traffic. For failover purposes one + * needs to maintain some consistency for the interface that will + * send the join/membership reports. The curr_active_slave found + * will send all of this type of traffic. + */ + if ((iph->protocol == IPPROTO_IGMP) && + (skb->protocol == htons(ETH_P_IP))) { + + read_lock(&bond->curr_slave_lock); + slave = bond->curr_active_slave; + read_unlock(&bond->curr_slave_lock); + + if (!slave) + goto out; + } else { + /* + * Concurrent TX may collide on rr_tx_counter; we accept + * that as being rare enough not to justify using an + * atomic op here. + */ + slave_no = bond->rr_tx_counter++ % bond->slave_cnt; + + bond_for_each_slave(bond, slave, i) { + slave_no--; + if (slave_no < 0) + break; + } + } + + start_at = slave; + bond_for_each_slave_from(bond, slave, i, start_at) { + if (IS_UP(slave->dev) && + (slave->link == BOND_LINK_UP) && + bond_is_active_slave(slave)) { + res = bond_dev_queue_xmit(bond, skb, slave->dev); + break; + } + } + +out: + if (res) { + /* no suitable interface, frame not sent */ + dev_kfree_skb(skb); + } + + return NETDEV_TX_OK; +} + + +/* + * in active-backup mode, we know that bond->curr_active_slave is always valid if + * the bond has a usable interface. + */ +static int bond_xmit_activebackup(struct sk_buff *skb, struct net_device *bond_dev) +{ + struct bonding *bond = netdev_priv(bond_dev); + int res = 1; + + read_lock(&bond->curr_slave_lock); + + if (bond->curr_active_slave) + res = bond_dev_queue_xmit(bond, skb, + bond->curr_active_slave->dev); + + if (res) + /* no suitable interface, frame not sent */ + dev_kfree_skb(skb); + + read_unlock(&bond->curr_slave_lock); + + return NETDEV_TX_OK; +} + +/* + * In bond_xmit_xor() , we determine the output device by using a pre- + * determined xmit_hash_policy(), If the selected device is not enabled, + * find the next active slave. + */ +static int bond_xmit_xor(struct sk_buff *skb, struct net_device *bond_dev) +{ + struct bonding *bond = netdev_priv(bond_dev); + struct slave *slave, *start_at; + int slave_no; + int i; + int res = 1; + + slave_no = bond->xmit_hash_policy(skb, bond->slave_cnt); + + bond_for_each_slave(bond, slave, i) { + slave_no--; + if (slave_no < 0) + break; + } + + start_at = slave; + + bond_for_each_slave_from(bond, slave, i, start_at) { + if (IS_UP(slave->dev) && + (slave->link == BOND_LINK_UP) && + bond_is_active_slave(slave)) { + res = bond_dev_queue_xmit(bond, skb, slave->dev); + break; + } + } + + if (res) { + /* no suitable interface, frame not sent */ + dev_kfree_skb(skb); + } + + return NETDEV_TX_OK; +} + +/* + * in broadcast mode, we send everything to all usable interfaces. + */ +static int bond_xmit_broadcast(struct sk_buff *skb, struct net_device *bond_dev) +{ + struct bonding *bond = netdev_priv(bond_dev); + struct slave *slave, *start_at; + struct net_device *tx_dev = NULL; + int i; + int res = 1; + + read_lock(&bond->curr_slave_lock); + start_at = bond->curr_active_slave; + read_unlock(&bond->curr_slave_lock); + + if (!start_at) + goto out; + + bond_for_each_slave_from(bond, slave, i, start_at) { + if (IS_UP(slave->dev) && + (slave->link == BOND_LINK_UP) && + bond_is_active_slave(slave)) { + if (tx_dev) { + struct sk_buff *skb2 = skb_clone(skb, GFP_ATOMIC); + if (!skb2) { + pr_err("%s: Error: bond_xmit_broadcast(): skb_clone() failed\n", + bond_dev->name); + continue; + } + + res = bond_dev_queue_xmit(bond, skb2, tx_dev); + if (res) { + dev_kfree_skb(skb2); + continue; + } + } + tx_dev = slave->dev; + } + } + + if (tx_dev) + res = bond_dev_queue_xmit(bond, skb, tx_dev); + +out: + if (res) + /* no suitable interface, frame not sent */ + dev_kfree_skb(skb); + + /* frame sent to all suitable interfaces */ + return NETDEV_TX_OK; +} + +/*------------------------- Device initialization ---------------------------*/ + +static void bond_set_xmit_hash_policy(struct bonding *bond) +{ + switch (bond->params.xmit_policy) { + case BOND_XMIT_POLICY_LAYER23: + bond->xmit_hash_policy = bond_xmit_hash_policy_l23; + break; + case BOND_XMIT_POLICY_LAYER34: + bond->xmit_hash_policy = bond_xmit_hash_policy_l34; + break; + case BOND_XMIT_POLICY_LAYER2: + default: + bond->xmit_hash_policy = bond_xmit_hash_policy_l2; + break; + } +} + +/* + * Lookup the slave that corresponds to a qid + */ +static inline int bond_slave_override(struct bonding *bond, + struct sk_buff *skb) +{ + int i, res = 1; + struct slave *slave = NULL; + struct slave *check_slave; + + if (!skb->queue_mapping) + return 1; + + /* Find out if any slaves have the same mapping as this skb. */ + bond_for_each_slave(bond, check_slave, i) { + if (check_slave->queue_id == skb->queue_mapping) { + slave = check_slave; + break; + } + } + + /* If the slave isn't UP, use default transmit policy. */ + if (slave && slave->queue_id && IS_UP(slave->dev) && + (slave->link == BOND_LINK_UP)) { + res = bond_dev_queue_xmit(bond, skb, slave->dev); + } + + return res; +} + + +static u16 bond_select_queue(struct net_device *dev, struct sk_buff *skb) +{ + /* + * This helper function exists to help dev_pick_tx get the correct + * destination queue. Using a helper function skips a call to + * skb_tx_hash and will put the skbs in the queue we expect on their + * way down to the bonding driver. + */ + u16 txq = skb_rx_queue_recorded(skb) ? skb_get_rx_queue(skb) : 0; + + /* + * Save the original txq to restore before passing to the driver + */ + qdisc_skb_cb(skb)->bond_queue_mapping = skb->queue_mapping; + + if (unlikely(txq >= dev->real_num_tx_queues)) { + do { + txq -= dev->real_num_tx_queues; + } while (txq >= dev->real_num_tx_queues); + } + return txq; +} + +static netdev_tx_t __bond_start_xmit(struct sk_buff *skb, struct net_device *dev) +{ + struct bonding *bond = netdev_priv(dev); + + if (TX_QUEUE_OVERRIDE(bond->params.mode)) { + if (!bond_slave_override(bond, skb)) + return NETDEV_TX_OK; + } + + switch (bond->params.mode) { + case BOND_MODE_ROUNDROBIN: + return bond_xmit_roundrobin(skb, dev); + case BOND_MODE_ACTIVEBACKUP: + return bond_xmit_activebackup(skb, dev); + case BOND_MODE_XOR: + return bond_xmit_xor(skb, dev); + case BOND_MODE_BROADCAST: + return bond_xmit_broadcast(skb, dev); + case BOND_MODE_8023AD: + return bond_3ad_xmit_xor(skb, dev); + case BOND_MODE_ALB: + case BOND_MODE_TLB: + return bond_alb_xmit(skb, dev); + default: + /* Should never happen, mode already checked */ + pr_err("%s: Error: Unknown bonding mode %d\n", + dev->name, bond->params.mode); + WARN_ON_ONCE(1); + dev_kfree_skb(skb); + return NETDEV_TX_OK; + } +} + +static netdev_tx_t bond_start_xmit(struct sk_buff *skb, struct net_device *dev) +{ + struct bonding *bond = netdev_priv(dev); + netdev_tx_t ret = NETDEV_TX_OK; + + /* + * If we risk deadlock from transmitting this in the + * netpoll path, tell netpoll to queue the frame for later tx + */ + if (is_netpoll_tx_blocked(dev)) + return NETDEV_TX_BUSY; + + read_lock(&bond->lock); + + if (bond->slave_cnt) + ret = __bond_start_xmit(skb, dev); + else + dev_kfree_skb(skb); + + read_unlock(&bond->lock); + + return ret; +} + +/* + * set bond mode specific net device operations + */ +void bond_set_mode_ops(struct bonding *bond, int mode) +{ + struct net_device *bond_dev = bond->dev; + + switch (mode) { + case BOND_MODE_ROUNDROBIN: + break; + case BOND_MODE_ACTIVEBACKUP: + break; + case BOND_MODE_XOR: + bond_set_xmit_hash_policy(bond); + break; + case BOND_MODE_BROADCAST: + break; + case BOND_MODE_8023AD: + bond_set_xmit_hash_policy(bond); + break; + case BOND_MODE_ALB: + /* FALLTHRU */ + case BOND_MODE_TLB: + break; + default: + /* Should never happen, mode already checked */ + pr_err("%s: Error: Unknown bonding mode %d\n", + bond_dev->name, mode); + break; + } +} + +static void bond_ethtool_get_drvinfo(struct net_device *bond_dev, + struct ethtool_drvinfo *drvinfo) +{ + strncpy(drvinfo->driver, DRV_NAME, 32); + strncpy(drvinfo->version, DRV_VERSION, 32); + snprintf(drvinfo->fw_version, 32, "%d", BOND_ABI_VERSION); +} + +static const struct ethtool_ops bond_ethtool_ops = { + .get_drvinfo = bond_ethtool_get_drvinfo, + .get_link = ethtool_op_get_link, +}; + +static const struct net_device_ops bond_netdev_ops = { + .ndo_init = bond_init, + .ndo_uninit = bond_uninit, + .ndo_open = bond_open, + .ndo_stop = bond_close, + .ndo_start_xmit = bond_start_xmit, + .ndo_select_queue = bond_select_queue, + .ndo_get_stats64 = bond_get_stats, + .ndo_do_ioctl = bond_do_ioctl, + .ndo_change_rx_flags = bond_change_rx_flags, + .ndo_set_rx_mode = bond_set_multicast_list, + .ndo_change_mtu = bond_change_mtu, + .ndo_set_mac_address = bond_set_mac_address, + .ndo_neigh_setup = bond_neigh_setup, + .ndo_vlan_rx_add_vid = bond_vlan_rx_add_vid, + .ndo_vlan_rx_kill_vid = bond_vlan_rx_kill_vid, +#ifdef CONFIG_NET_POLL_CONTROLLER + .ndo_netpoll_setup = bond_netpoll_setup, + .ndo_netpoll_cleanup = bond_netpoll_cleanup, + .ndo_poll_controller = bond_poll_controller, +#endif + .ndo_add_slave = bond_enslave, + .ndo_del_slave = bond_release, + .ndo_fix_features = bond_fix_features, +}; + +static void bond_destructor(struct net_device *bond_dev) +{ + struct bonding *bond = netdev_priv(bond_dev); + if (bond->wq) + destroy_workqueue(bond->wq); + free_netdev(bond_dev); +} + +static void bond_setup(struct net_device *bond_dev) +{ + struct bonding *bond = netdev_priv(bond_dev); + + /* initialize rwlocks */ + rwlock_init(&bond->lock); + rwlock_init(&bond->curr_slave_lock); + + bond->params = bonding_defaults; + + /* Initialize pointers */ + bond->dev = bond_dev; + INIT_LIST_HEAD(&bond->vlan_list); + + /* Initialize the device entry points */ + ether_setup(bond_dev); + bond_dev->netdev_ops = &bond_netdev_ops; + bond_dev->ethtool_ops = &bond_ethtool_ops; + bond_set_mode_ops(bond, bond->params.mode); + + bond_dev->destructor = bond_destructor; + + /* Initialize the device options */ + bond_dev->tx_queue_len = 0; + bond_dev->flags |= IFF_MASTER|IFF_MULTICAST; + bond_dev->priv_flags |= IFF_BONDING; + bond_dev->priv_flags &= ~(IFF_XMIT_DST_RELEASE | IFF_TX_SKB_SHARING); + + /* At first, we block adding VLANs. That's the only way to + * prevent problems that occur when adding VLANs over an + * empty bond. The block will be removed once non-challenged + * slaves are enslaved. + */ + bond_dev->features |= NETIF_F_VLAN_CHALLENGED; + + /* don't acquire bond device's netif_tx_lock when + * transmitting */ + bond_dev->features |= NETIF_F_LLTX; + + /* By default, we declare the bond to be fully + * VLAN hardware accelerated capable. Special + * care is taken in the various xmit functions + * when there are slaves that are not hw accel + * capable + */ + + bond_dev->hw_features = BOND_VLAN_FEATURES | + NETIF_F_HW_VLAN_TX | + NETIF_F_HW_VLAN_RX | + NETIF_F_HW_VLAN_FILTER; + + bond_dev->hw_features &= ~(NETIF_F_ALL_CSUM & ~NETIF_F_HW_CSUM); + bond_dev->features |= bond_dev->hw_features; +} + +static void bond_work_cancel_all(struct bonding *bond) +{ + if (bond->params.miimon && delayed_work_pending(&bond->mii_work)) + cancel_delayed_work_sync(&bond->mii_work); + + if (bond->params.arp_interval && delayed_work_pending(&bond->arp_work)) + cancel_delayed_work_sync(&bond->arp_work); + + if (bond->params.mode == BOND_MODE_ALB && + delayed_work_pending(&bond->alb_work)) + cancel_delayed_work_sync(&bond->alb_work); + + if (bond->params.mode == BOND_MODE_8023AD && + delayed_work_pending(&bond->ad_work)) + cancel_delayed_work_sync(&bond->ad_work); + + if (delayed_work_pending(&bond->mcast_work)) + cancel_delayed_work_sync(&bond->mcast_work); +} + +/* +* Destroy a bonding device. +* Must be under rtnl_lock when this function is called. +*/ +static void bond_uninit(struct net_device *bond_dev) +{ + struct bonding *bond = netdev_priv(bond_dev); + struct vlan_entry *vlan, *tmp; + + bond_netpoll_cleanup(bond_dev); + + /* Release the bonded slaves */ + bond_release_all(bond_dev); + + list_del(&bond->bond_list); + + bond_work_cancel_all(bond); + + bond_remove_proc_entry(bond); + + bond_debug_unregister(bond); + + __hw_addr_flush(&bond->mc_list); + + list_for_each_entry_safe(vlan, tmp, &bond->vlan_list, vlan_list) { + list_del(&vlan->vlan_list); + kfree(vlan); + } +} + +/*------------------------- Module initialization ---------------------------*/ + +/* + * Convert string input module parms. Accept either the + * number of the mode or its string name. A bit complicated because + * some mode names are substrings of other names, and calls from sysfs + * may have whitespace in the name (trailing newlines, for example). + */ +int bond_parse_parm(const char *buf, const struct bond_parm_tbl *tbl) +{ + int modeint = -1, i, rv; + char *p, modestr[BOND_MAX_MODENAME_LEN + 1] = { 0, }; + + for (p = (char *)buf; *p; p++) + if (!(isdigit(*p) || isspace(*p))) + break; + + if (*p) + rv = sscanf(buf, "%20s", modestr); + else + rv = sscanf(buf, "%d", &modeint); + + if (!rv) + return -1; + + for (i = 0; tbl[i].modename; i++) { + if (modeint == tbl[i].mode) + return tbl[i].mode; + if (strcmp(modestr, tbl[i].modename) == 0) + return tbl[i].mode; + } + + return -1; +} + +static int bond_check_params(struct bond_params *params) +{ + int arp_validate_value, fail_over_mac_value, primary_reselect_value; + + /* + * Convert string parameters. + */ + if (mode) { + bond_mode = bond_parse_parm(mode, bond_mode_tbl); + if (bond_mode == -1) { + pr_err("Error: Invalid bonding mode \"%s\"\n", + mode == NULL ? "NULL" : mode); + return -EINVAL; + } + } + + if (xmit_hash_policy) { + if ((bond_mode != BOND_MODE_XOR) && + (bond_mode != BOND_MODE_8023AD)) { + pr_info("xmit_hash_policy param is irrelevant in mode %s\n", + bond_mode_name(bond_mode)); + } else { + xmit_hashtype = bond_parse_parm(xmit_hash_policy, + xmit_hashtype_tbl); + if (xmit_hashtype == -1) { + pr_err("Error: Invalid xmit_hash_policy \"%s\"\n", + xmit_hash_policy == NULL ? "NULL" : + xmit_hash_policy); + return -EINVAL; + } + } + } + + if (lacp_rate) { + if (bond_mode != BOND_MODE_8023AD) { + pr_info("lacp_rate param is irrelevant in mode %s\n", + bond_mode_name(bond_mode)); + } else { + lacp_fast = bond_parse_parm(lacp_rate, bond_lacp_tbl); + if (lacp_fast == -1) { + pr_err("Error: Invalid lacp rate \"%s\"\n", + lacp_rate == NULL ? "NULL" : lacp_rate); + return -EINVAL; + } + } + } + + if (ad_select) { + params->ad_select = bond_parse_parm(ad_select, ad_select_tbl); + if (params->ad_select == -1) { + pr_err("Error: Invalid ad_select \"%s\"\n", + ad_select == NULL ? "NULL" : ad_select); + return -EINVAL; + } + + if (bond_mode != BOND_MODE_8023AD) { + pr_warning("ad_select param only affects 802.3ad mode\n"); + } + } else { + params->ad_select = BOND_AD_STABLE; + } + + if (max_bonds < 0) { + pr_warning("Warning: max_bonds (%d) not in range %d-%d, so it was reset to BOND_DEFAULT_MAX_BONDS (%d)\n", + max_bonds, 0, INT_MAX, BOND_DEFAULT_MAX_BONDS); + max_bonds = BOND_DEFAULT_MAX_BONDS; + } + + if (miimon < 0) { + pr_warning("Warning: miimon module parameter (%d), not in range 0-%d, so it was reset to %d\n", + miimon, INT_MAX, BOND_LINK_MON_INTERV); + miimon = BOND_LINK_MON_INTERV; + } + + if (updelay < 0) { + pr_warning("Warning: updelay module parameter (%d), not in range 0-%d, so it was reset to 0\n", + updelay, INT_MAX); + updelay = 0; + } + + if (downdelay < 0) { + pr_warning("Warning: downdelay module parameter (%d), not in range 0-%d, so it was reset to 0\n", + downdelay, INT_MAX); + downdelay = 0; + } + + if ((use_carrier != 0) && (use_carrier != 1)) { + pr_warning("Warning: use_carrier module parameter (%d), not of valid value (0/1), so it was set to 1\n", + use_carrier); + use_carrier = 1; + } + + if (num_peer_notif < 0 || num_peer_notif > 255) { + pr_warning("Warning: num_grat_arp/num_unsol_na (%d) not in range 0-255 so it was reset to 1\n", + num_peer_notif); + num_peer_notif = 1; + } + + /* reset values for 802.3ad */ + if (bond_mode == BOND_MODE_8023AD) { + if (!miimon) { + pr_warning("Warning: miimon must be specified, otherwise bonding will not detect link failure, speed and duplex which are essential for 802.3ad operation\n"); + pr_warning("Forcing miimon to 100msec\n"); + miimon = 100; + } + } + + if (tx_queues < 1 || tx_queues > 255) { + pr_warning("Warning: tx_queues (%d) should be between " + "1 and 255, resetting to %d\n", + tx_queues, BOND_DEFAULT_TX_QUEUES); + tx_queues = BOND_DEFAULT_TX_QUEUES; + } + + if ((all_slaves_active != 0) && (all_slaves_active != 1)) { + pr_warning("Warning: all_slaves_active module parameter (%d), " + "not of valid value (0/1), so it was set to " + "0\n", all_slaves_active); + all_slaves_active = 0; + } + + if (resend_igmp < 0 || resend_igmp > 255) { + pr_warning("Warning: resend_igmp (%d) should be between " + "0 and 255, resetting to %d\n", + resend_igmp, BOND_DEFAULT_RESEND_IGMP); + resend_igmp = BOND_DEFAULT_RESEND_IGMP; + } + + /* reset values for TLB/ALB */ + if ((bond_mode == BOND_MODE_TLB) || + (bond_mode == BOND_MODE_ALB)) { + if (!miimon) { + pr_warning("Warning: miimon must be specified, otherwise bonding will not detect link failure and link speed which are essential for TLB/ALB load balancing\n"); + pr_warning("Forcing miimon to 100msec\n"); + miimon = 100; + } + } + + if (bond_mode == BOND_MODE_ALB) { + pr_notice("In ALB mode you might experience client disconnections upon reconnection of a link if the bonding module updelay parameter (%d msec) is incompatible with the forwarding delay time of the switch\n", + updelay); + } + + if (!miimon) { + if (updelay || downdelay) { + /* just warn the user the up/down delay will have + * no effect since miimon is zero... + */ + pr_warning("Warning: miimon module parameter not set and updelay (%d) or downdelay (%d) module parameter is set; updelay and downdelay have no effect unless miimon is set\n", + updelay, downdelay); + } + } else { + /* don't allow arp monitoring */ + if (arp_interval) { + pr_warning("Warning: miimon (%d) and arp_interval (%d) can't be used simultaneously, disabling ARP monitoring\n", + miimon, arp_interval); + arp_interval = 0; + } + + if ((updelay % miimon) != 0) { + pr_warning("Warning: updelay (%d) is not a multiple of miimon (%d), updelay rounded to %d ms\n", + updelay, miimon, + (updelay / miimon) * miimon); + } + + updelay /= miimon; + + if ((downdelay % miimon) != 0) { + pr_warning("Warning: downdelay (%d) is not a multiple of miimon (%d), downdelay rounded to %d ms\n", + downdelay, miimon, + (downdelay / miimon) * miimon); + } + + downdelay /= miimon; + } + + if (arp_interval < 0) { + pr_warning("Warning: arp_interval module parameter (%d) , not in range 0-%d, so it was reset to %d\n", + arp_interval, INT_MAX, BOND_LINK_ARP_INTERV); + arp_interval = BOND_LINK_ARP_INTERV; + } + + for (arp_ip_count = 0; + (arp_ip_count < BOND_MAX_ARP_TARGETS) && arp_ip_target[arp_ip_count]; + arp_ip_count++) { + /* not complete check, but should be good enough to + catch mistakes */ + if (!isdigit(arp_ip_target[arp_ip_count][0])) { + pr_warning("Warning: bad arp_ip_target module parameter (%s), ARP monitoring will not be performed\n", + arp_ip_target[arp_ip_count]); + arp_interval = 0; + } else { + __be32 ip = in_aton(arp_ip_target[arp_ip_count]); + arp_target[arp_ip_count] = ip; + } + } + + if (arp_interval && !arp_ip_count) { + /* don't allow arping if no arp_ip_target given... */ + pr_warning("Warning: arp_interval module parameter (%d) specified without providing an arp_ip_target parameter, arp_interval was reset to 0\n", + arp_interval); + arp_interval = 0; + } + + if (arp_validate) { + if (bond_mode != BOND_MODE_ACTIVEBACKUP) { + pr_err("arp_validate only supported in active-backup mode\n"); + return -EINVAL; + } + if (!arp_interval) { + pr_err("arp_validate requires arp_interval\n"); + return -EINVAL; + } + + arp_validate_value = bond_parse_parm(arp_validate, + arp_validate_tbl); + if (arp_validate_value == -1) { + pr_err("Error: invalid arp_validate \"%s\"\n", + arp_validate == NULL ? "NULL" : arp_validate); + return -EINVAL; + } + } else + arp_validate_value = 0; + + if (miimon) { + pr_info("MII link monitoring set to %d ms\n", miimon); + } else if (arp_interval) { + int i; + + pr_info("ARP monitoring set to %d ms, validate %s, with %d target(s):", + arp_interval, + arp_validate_tbl[arp_validate_value].modename, + arp_ip_count); + + for (i = 0; i < arp_ip_count; i++) + pr_info(" %s", arp_ip_target[i]); + + pr_info("\n"); + + } else if (max_bonds) { + /* miimon and arp_interval not set, we need one so things + * work as expected, see bonding.txt for details + */ + pr_debug("Warning: either miimon or arp_interval and arp_ip_target module parameters must be specified, otherwise bonding will not detect link failures! see bonding.txt for details.\n"); + } + + if (primary && !USES_PRIMARY(bond_mode)) { + /* currently, using a primary only makes sense + * in active backup, TLB or ALB modes + */ + pr_warning("Warning: %s primary device specified but has no effect in %s mode\n", + primary, bond_mode_name(bond_mode)); + primary = NULL; + } + + if (primary && primary_reselect) { + primary_reselect_value = bond_parse_parm(primary_reselect, + pri_reselect_tbl); + if (primary_reselect_value == -1) { + pr_err("Error: Invalid primary_reselect \"%s\"\n", + primary_reselect == + NULL ? "NULL" : primary_reselect); + return -EINVAL; + } + } else { + primary_reselect_value = BOND_PRI_RESELECT_ALWAYS; + } + + if (fail_over_mac) { + fail_over_mac_value = bond_parse_parm(fail_over_mac, + fail_over_mac_tbl); + if (fail_over_mac_value == -1) { + pr_err("Error: invalid fail_over_mac \"%s\"\n", + arp_validate == NULL ? "NULL" : arp_validate); + return -EINVAL; + } + + if (bond_mode != BOND_MODE_ACTIVEBACKUP) + pr_warning("Warning: fail_over_mac only affects active-backup mode.\n"); + } else { + fail_over_mac_value = BOND_FOM_NONE; + } + + /* fill params struct with the proper values */ + params->mode = bond_mode; + params->xmit_policy = xmit_hashtype; + params->miimon = miimon; + params->num_peer_notif = num_peer_notif; + params->arp_interval = arp_interval; + params->arp_validate = arp_validate_value; + params->updelay = updelay; + params->downdelay = downdelay; + params->use_carrier = use_carrier; + params->lacp_fast = lacp_fast; + params->primary[0] = 0; + params->primary_reselect = primary_reselect_value; + params->fail_over_mac = fail_over_mac_value; + params->tx_queues = tx_queues; + params->all_slaves_active = all_slaves_active; + params->resend_igmp = resend_igmp; + params->min_links = min_links; + + if (primary) { + strncpy(params->primary, primary, IFNAMSIZ); + params->primary[IFNAMSIZ - 1] = 0; + } + + memcpy(params->arp_targets, arp_target, sizeof(arp_target)); + + return 0; +} + +static struct lock_class_key bonding_netdev_xmit_lock_key; +static struct lock_class_key bonding_netdev_addr_lock_key; + +static void bond_set_lockdep_class_one(struct net_device *dev, + struct netdev_queue *txq, + void *_unused) +{ + lockdep_set_class(&txq->_xmit_lock, + &bonding_netdev_xmit_lock_key); +} + +static void bond_set_lockdep_class(struct net_device *dev) +{ + lockdep_set_class(&dev->addr_list_lock, + &bonding_netdev_addr_lock_key); + netdev_for_each_tx_queue(dev, bond_set_lockdep_class_one, NULL); +} + +/* + * Called from registration process + */ +static int bond_init(struct net_device *bond_dev) +{ + struct bonding *bond = netdev_priv(bond_dev); + struct bond_net *bn = net_generic(dev_net(bond_dev), bond_net_id); + struct alb_bond_info *bond_info = &(BOND_ALB_INFO(bond)); + + pr_debug("Begin bond_init for %s\n", bond_dev->name); + + /* + * Initialize locks that may be required during + * en/deslave operations. All of the bond_open work + * (of which this is part) should really be moved to + * a phase prior to dev_open + */ + spin_lock_init(&(bond_info->tx_hashtbl_lock)); + spin_lock_init(&(bond_info->rx_hashtbl_lock)); + + bond->wq = create_singlethread_workqueue(bond_dev->name); + if (!bond->wq) + return -ENOMEM; + + bond_set_lockdep_class(bond_dev); + + bond_create_proc_entry(bond); + list_add_tail(&bond->bond_list, &bn->dev_list); + + bond_prepare_sysfs_group(bond); + + bond_debug_register(bond); + + __hw_addr_init(&bond->mc_list); + return 0; +} + +static int bond_validate(struct nlattr *tb[], struct nlattr *data[]) +{ + if (tb[IFLA_ADDRESS]) { + if (nla_len(tb[IFLA_ADDRESS]) != ETH_ALEN) + return -EINVAL; + if (!is_valid_ether_addr(nla_data(tb[IFLA_ADDRESS]))) + return -EADDRNOTAVAIL; + } + return 0; +} + +static int bond_get_tx_queues(struct net *net, struct nlattr *tb[], + unsigned int *num_queues, + unsigned int *real_num_queues) +{ + *num_queues = tx_queues; + return 0; +} + +static struct rtnl_link_ops bond_link_ops __read_mostly = { + .kind = "bond", + .priv_size = sizeof(struct bonding), + .setup = bond_setup, + .validate = bond_validate, + .get_tx_queues = bond_get_tx_queues, +}; + +/* Create a new bond based on the specified name and bonding parameters. + * If name is NULL, obtain a suitable "bond%d" name for us. + * Caller must NOT hold rtnl_lock; we need to release it here before we + * set up our sysfs entries. + */ +int bond_create(struct net *net, const char *name) +{ + struct net_device *bond_dev; + int res; + + rtnl_lock(); + + bond_dev = alloc_netdev_mq(sizeof(struct bonding), + name ? name : "bond%d", + bond_setup, tx_queues); + if (!bond_dev) { + pr_err("%s: eek! can't alloc netdev!\n", name); + rtnl_unlock(); + return -ENOMEM; + } + + dev_net_set(bond_dev, net); + bond_dev->rtnl_link_ops = &bond_link_ops; + + res = register_netdevice(bond_dev); + + netif_carrier_off(bond_dev); + + rtnl_unlock(); + if (res < 0) + bond_destructor(bond_dev); + return res; +} + +static int __net_init bond_net_init(struct net *net) +{ + struct bond_net *bn = net_generic(net, bond_net_id); + + bn->net = net; + INIT_LIST_HEAD(&bn->dev_list); + + bond_create_proc_dir(bn); + bond_create_sysfs(bn); + + return 0; +} + +static void __net_exit bond_net_exit(struct net *net) +{ + struct bond_net *bn = net_generic(net, bond_net_id); + + bond_destroy_sysfs(bn); + bond_destroy_proc_dir(bn); +} + +static struct pernet_operations bond_net_ops = { + .init = bond_net_init, + .exit = bond_net_exit, + .id = &bond_net_id, + .size = sizeof(struct bond_net), +}; + +static int __init bonding_init(void) +{ + int i; + int res; + + pr_info("%s", bond_version); + + res = bond_check_params(&bonding_defaults); + if (res) + goto out; + + res = register_pernet_subsys(&bond_net_ops); + if (res) + goto out; + + res = rtnl_link_register(&bond_link_ops); + if (res) + goto err_link; + + bond_create_debugfs(); + + for (i = 0; i < max_bonds; i++) { + res = bond_create(&init_net, NULL); + if (res) + goto err; + } + + register_netdevice_notifier(&bond_netdev_notifier); +out: + return res; +err: + rtnl_link_unregister(&bond_link_ops); +err_link: + unregister_pernet_subsys(&bond_net_ops); + goto out; + +} + +static void __exit bonding_exit(void) +{ + unregister_netdevice_notifier(&bond_netdev_notifier); + + bond_destroy_debugfs(); + + rtnl_link_unregister(&bond_link_ops); + unregister_pernet_subsys(&bond_net_ops); + +#ifdef CONFIG_NET_POLL_CONTROLLER + /* + * Make sure we don't have an imbalance on our netpoll blocking + */ + WARN_ON(atomic_read(&netpoll_block_tx)); +#endif +} + +module_init(bonding_init); +module_exit(bonding_exit); +MODULE_LICENSE("GPL"); +MODULE_VERSION(DRV_VERSION); +MODULE_DESCRIPTION(DRV_DESCRIPTION ", v" DRV_VERSION); +MODULE_AUTHOR("Thomas Davis, tadavis@lbl.gov and many others"); +MODULE_ALIAS_RTNL_LINK("bond"); diff --git a/ANDROID_3.4.5/drivers/net/bonding/bond_procfs.c b/ANDROID_3.4.5/drivers/net/bonding/bond_procfs.c new file mode 100644 index 00000000..ad284baa --- /dev/null +++ b/ANDROID_3.4.5/drivers/net/bonding/bond_procfs.c @@ -0,0 +1,283 @@ +#include <linux/proc_fs.h> +#include <linux/export.h> +#include <net/net_namespace.h> +#include <net/netns/generic.h> +#include "bonding.h" + + +static void *bond_info_seq_start(struct seq_file *seq, loff_t *pos) + __acquires(RCU) + __acquires(&bond->lock) +{ + struct bonding *bond = seq->private; + loff_t off = 0; + struct slave *slave; + int i; + + /* make sure the bond won't be taken away */ + rcu_read_lock(); + read_lock(&bond->lock); + + if (*pos == 0) + return SEQ_START_TOKEN; + + bond_for_each_slave(bond, slave, i) { + if (++off == *pos) + return slave; + } + + return NULL; +} + +static void *bond_info_seq_next(struct seq_file *seq, void *v, loff_t *pos) +{ + struct bonding *bond = seq->private; + struct slave *slave = v; + + ++*pos; + if (v == SEQ_START_TOKEN) + return bond->first_slave; + + slave = slave->next; + + return (slave == bond->first_slave) ? NULL : slave; +} + +static void bond_info_seq_stop(struct seq_file *seq, void *v) + __releases(&bond->lock) + __releases(RCU) +{ + struct bonding *bond = seq->private; + + read_unlock(&bond->lock); + rcu_read_unlock(); +} + +static void bond_info_show_master(struct seq_file *seq) +{ + struct bonding *bond = seq->private; + struct slave *curr; + int i; + + read_lock(&bond->curr_slave_lock); + curr = bond->curr_active_slave; + read_unlock(&bond->curr_slave_lock); + + seq_printf(seq, "Bonding Mode: %s", + bond_mode_name(bond->params.mode)); + + if (bond->params.mode == BOND_MODE_ACTIVEBACKUP && + bond->params.fail_over_mac) + seq_printf(seq, " (fail_over_mac %s)", + fail_over_mac_tbl[bond->params.fail_over_mac].modename); + + seq_printf(seq, "\n"); + + if (bond->params.mode == BOND_MODE_XOR || + bond->params.mode == BOND_MODE_8023AD) { + seq_printf(seq, "Transmit Hash Policy: %s (%d)\n", + xmit_hashtype_tbl[bond->params.xmit_policy].modename, + bond->params.xmit_policy); + } + + if (USES_PRIMARY(bond->params.mode)) { + seq_printf(seq, "Primary Slave: %s", + (bond->primary_slave) ? + bond->primary_slave->dev->name : "None"); + if (bond->primary_slave) + seq_printf(seq, " (primary_reselect %s)", + pri_reselect_tbl[bond->params.primary_reselect].modename); + + seq_printf(seq, "\nCurrently Active Slave: %s\n", + (curr) ? curr->dev->name : "None"); + } + + seq_printf(seq, "MII Status: %s\n", netif_carrier_ok(bond->dev) ? + "up" : "down"); + seq_printf(seq, "MII Polling Interval (ms): %d\n", bond->params.miimon); + seq_printf(seq, "Up Delay (ms): %d\n", + bond->params.updelay * bond->params.miimon); + seq_printf(seq, "Down Delay (ms): %d\n", + bond->params.downdelay * bond->params.miimon); + + + /* ARP information */ + if (bond->params.arp_interval > 0) { + int printed = 0; + seq_printf(seq, "ARP Polling Interval (ms): %d\n", + bond->params.arp_interval); + + seq_printf(seq, "ARP IP target/s (n.n.n.n form):"); + + for (i = 0; (i < BOND_MAX_ARP_TARGETS); i++) { + if (!bond->params.arp_targets[i]) + break; + if (printed) + seq_printf(seq, ","); + seq_printf(seq, " %pI4", &bond->params.arp_targets[i]); + printed = 1; + } + seq_printf(seq, "\n"); + } + + if (bond->params.mode == BOND_MODE_8023AD) { + struct ad_info ad_info; + + seq_puts(seq, "\n802.3ad info\n"); + seq_printf(seq, "LACP rate: %s\n", + (bond->params.lacp_fast) ? "fast" : "slow"); + seq_printf(seq, "Min links: %d\n", bond->params.min_links); + seq_printf(seq, "Aggregator selection policy (ad_select): %s\n", + ad_select_tbl[bond->params.ad_select].modename); + + if (bond_3ad_get_active_agg_info(bond, &ad_info)) { + seq_printf(seq, "bond %s has no active aggregator\n", + bond->dev->name); + } else { + seq_printf(seq, "Active Aggregator Info:\n"); + + seq_printf(seq, "\tAggregator ID: %d\n", + ad_info.aggregator_id); + seq_printf(seq, "\tNumber of ports: %d\n", + ad_info.ports); + seq_printf(seq, "\tActor Key: %d\n", + ad_info.actor_key); + seq_printf(seq, "\tPartner Key: %d\n", + ad_info.partner_key); + seq_printf(seq, "\tPartner Mac Address: %pM\n", + ad_info.partner_system); + } + } +} + +static void bond_info_show_slave(struct seq_file *seq, + const struct slave *slave) +{ + struct bonding *bond = seq->private; + + seq_printf(seq, "\nSlave Interface: %s\n", slave->dev->name); + seq_printf(seq, "MII Status: %s\n", + (slave->link == BOND_LINK_UP) ? "up" : "down"); + if (slave->speed == SPEED_UNKNOWN) + seq_printf(seq, "Speed: %s\n", "Unknown"); + else + seq_printf(seq, "Speed: %d Mbps\n", slave->speed); + + if (slave->duplex == DUPLEX_UNKNOWN) + seq_printf(seq, "Duplex: %s\n", "Unknown"); + else + seq_printf(seq, "Duplex: %s\n", slave->duplex ? "full" : "half"); + + seq_printf(seq, "Link Failure Count: %u\n", + slave->link_failure_count); + + seq_printf(seq, "Permanent HW addr: %pM\n", slave->perm_hwaddr); + + if (bond->params.mode == BOND_MODE_8023AD) { + const struct aggregator *agg + = SLAVE_AD_INFO(slave).port.aggregator; + + if (agg) + seq_printf(seq, "Aggregator ID: %d\n", + agg->aggregator_identifier); + else + seq_puts(seq, "Aggregator ID: N/A\n"); + } + seq_printf(seq, "Slave queue ID: %d\n", slave->queue_id); +} + +static int bond_info_seq_show(struct seq_file *seq, void *v) +{ + if (v == SEQ_START_TOKEN) { + seq_printf(seq, "%s\n", bond_version); + bond_info_show_master(seq); + } else + bond_info_show_slave(seq, v); + + return 0; +} + +static const struct seq_operations bond_info_seq_ops = { + .start = bond_info_seq_start, + .next = bond_info_seq_next, + .stop = bond_info_seq_stop, + .show = bond_info_seq_show, +}; + +static int bond_info_open(struct inode *inode, struct file *file) +{ + struct seq_file *seq; + struct proc_dir_entry *proc; + int res; + + res = seq_open(file, &bond_info_seq_ops); + if (!res) { + /* recover the pointer buried in proc_dir_entry data */ + seq = file->private_data; + proc = PDE(inode); + seq->private = proc->data; + } + + return res; +} + +static const struct file_operations bond_info_fops = { + .owner = THIS_MODULE, + .open = bond_info_open, + .read = seq_read, + .llseek = seq_lseek, + .release = seq_release, +}; + +void bond_create_proc_entry(struct bonding *bond) +{ + struct net_device *bond_dev = bond->dev; + struct bond_net *bn = net_generic(dev_net(bond_dev), bond_net_id); + + if (bn->proc_dir) { + bond->proc_entry = proc_create_data(bond_dev->name, + S_IRUGO, bn->proc_dir, + &bond_info_fops, bond); + if (bond->proc_entry == NULL) + pr_warning("Warning: Cannot create /proc/net/%s/%s\n", + DRV_NAME, bond_dev->name); + else + memcpy(bond->proc_file_name, bond_dev->name, IFNAMSIZ); + } +} + +void bond_remove_proc_entry(struct bonding *bond) +{ + struct net_device *bond_dev = bond->dev; + struct bond_net *bn = net_generic(dev_net(bond_dev), bond_net_id); + + if (bn->proc_dir && bond->proc_entry) { + remove_proc_entry(bond->proc_file_name, bn->proc_dir); + memset(bond->proc_file_name, 0, IFNAMSIZ); + bond->proc_entry = NULL; + } +} + +/* Create the bonding directory under /proc/net, if doesn't exist yet. + * Caller must hold rtnl_lock. + */ +void __net_init bond_create_proc_dir(struct bond_net *bn) +{ + if (!bn->proc_dir) { + bn->proc_dir = proc_mkdir(DRV_NAME, bn->net->proc_net); + if (!bn->proc_dir) + pr_warning("Warning: cannot create /proc/net/%s\n", + DRV_NAME); + } +} + +/* Destroy the bonding directory under /proc/net, if empty. + * Caller must hold rtnl_lock. + */ +void __net_exit bond_destroy_proc_dir(struct bond_net *bn) +{ + if (bn->proc_dir) { + remove_proc_entry(DRV_NAME, bn->net->proc_net); + bn->proc_dir = NULL; + } +} diff --git a/ANDROID_3.4.5/drivers/net/bonding/bond_sysfs.c b/ANDROID_3.4.5/drivers/net/bonding/bond_sysfs.c new file mode 100644 index 00000000..aef42f04 --- /dev/null +++ b/ANDROID_3.4.5/drivers/net/bonding/bond_sysfs.c @@ -0,0 +1,1727 @@ +/* + * Copyright(c) 2004-2005 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. + * + */ + +#define pr_fmt(fmt) KBUILD_MODNAME ": " fmt + +#include <linux/kernel.h> +#include <linux/module.h> +#include <linux/device.h> +#include <linux/sched.h> +#include <linux/fs.h> +#include <linux/types.h> +#include <linux/string.h> +#include <linux/netdevice.h> +#include <linux/inetdevice.h> +#include <linux/in.h> +#include <linux/sysfs.h> +#include <linux/ctype.h> +#include <linux/inet.h> +#include <linux/rtnetlink.h> +#include <linux/etherdevice.h> +#include <net/net_namespace.h> +#include <net/netns/generic.h> +#include <linux/nsproxy.h> + +#include "bonding.h" + +#define to_dev(obj) container_of(obj, struct device, kobj) +#define to_bond(cd) ((struct bonding *)(netdev_priv(to_net_dev(cd)))) + +/* + * "show" function for the bond_masters attribute. + * The class parameter is ignored. + */ +static ssize_t bonding_show_bonds(struct class *cls, + struct class_attribute *attr, + char *buf) +{ + struct bond_net *bn = + container_of(attr, struct bond_net, class_attr_bonding_masters); + int res = 0; + struct bonding *bond; + + rtnl_lock(); + + list_for_each_entry(bond, &bn->dev_list, bond_list) { + if (res > (PAGE_SIZE - IFNAMSIZ)) { + /* not enough space for another interface name */ + if ((PAGE_SIZE - res) > 10) + res = PAGE_SIZE - 10; + res += sprintf(buf + res, "++more++ "); + break; + } + res += sprintf(buf + res, "%s ", bond->dev->name); + } + if (res) + buf[res-1] = '\n'; /* eat the leftover space */ + + rtnl_unlock(); + return res; +} + +static struct net_device *bond_get_by_name(struct bond_net *bn, const char *ifname) +{ + struct bonding *bond; + + list_for_each_entry(bond, &bn->dev_list, bond_list) { + if (strncmp(bond->dev->name, ifname, IFNAMSIZ) == 0) + return bond->dev; + } + return NULL; +} + +/* + * "store" function for the bond_masters attribute. This is what + * creates and deletes entire bonds. + * + * The class parameter is ignored. + * + */ + +static ssize_t bonding_store_bonds(struct class *cls, + struct class_attribute *attr, + const char *buffer, size_t count) +{ + struct bond_net *bn = + container_of(attr, struct bond_net, class_attr_bonding_masters); + char command[IFNAMSIZ + 1] = {0, }; + char *ifname; + int rv, res = count; + + sscanf(buffer, "%16s", command); /* IFNAMSIZ*/ + ifname = command + 1; + if ((strlen(command) <= 1) || + !dev_valid_name(ifname)) + goto err_no_cmd; + + if (command[0] == '+') { + pr_info("%s is being created...\n", ifname); + rv = bond_create(bn->net, ifname); + if (rv) { + if (rv == -EEXIST) + pr_info("%s already exists.\n", ifname); + else + pr_info("%s creation failed.\n", ifname); + res = rv; + } + } else if (command[0] == '-') { + struct net_device *bond_dev; + + rtnl_lock(); + bond_dev = bond_get_by_name(bn, ifname); + if (bond_dev) { + pr_info("%s is being deleted...\n", ifname); + unregister_netdevice(bond_dev); + } else { + pr_err("unable to delete non-existent %s\n", ifname); + res = -ENODEV; + } + rtnl_unlock(); + } else + goto err_no_cmd; + + /* Always return either count or an error. If you return 0, you'll + * get called forever, which is bad. + */ + return res; + +err_no_cmd: + pr_err("no command found in bonding_masters. Use +ifname or -ifname.\n"); + return -EPERM; +} + +static const void *bonding_namespace(struct class *cls, + const struct class_attribute *attr) +{ + const struct bond_net *bn = + container_of(attr, struct bond_net, class_attr_bonding_masters); + return bn->net; +} + +/* class attribute for bond_masters file. This ends up in /sys/class/net */ +static const struct class_attribute class_attr_bonding_masters = { + .attr = { + .name = "bonding_masters", + .mode = S_IWUSR | S_IRUGO, + }, + .show = bonding_show_bonds, + .store = bonding_store_bonds, + .namespace = bonding_namespace, +}; + +int bond_create_slave_symlinks(struct net_device *master, + struct net_device *slave) +{ + char linkname[IFNAMSIZ+7]; + int ret = 0; + + /* first, create a link from the slave back to the master */ + ret = sysfs_create_link(&(slave->dev.kobj), &(master->dev.kobj), + "master"); + if (ret) + return ret; + /* next, create a link from the master to the slave */ + sprintf(linkname, "slave_%s", slave->name); + ret = sysfs_create_link(&(master->dev.kobj), &(slave->dev.kobj), + linkname); + return ret; + +} + +void bond_destroy_slave_symlinks(struct net_device *master, + struct net_device *slave) +{ + char linkname[IFNAMSIZ+7]; + + sysfs_remove_link(&(slave->dev.kobj), "master"); + sprintf(linkname, "slave_%s", slave->name); + sysfs_remove_link(&(master->dev.kobj), linkname); +} + + +/* + * Show the slaves in the current bond. + */ +static ssize_t bonding_show_slaves(struct device *d, + struct device_attribute *attr, char *buf) +{ + struct slave *slave; + int i, res = 0; + struct bonding *bond = to_bond(d); + + read_lock(&bond->lock); + bond_for_each_slave(bond, slave, i) { + if (res > (PAGE_SIZE - IFNAMSIZ)) { + /* not enough space for another interface name */ + if ((PAGE_SIZE - res) > 10) + res = PAGE_SIZE - 10; + res += sprintf(buf + res, "++more++ "); + break; + } + res += sprintf(buf + res, "%s ", slave->dev->name); + } + read_unlock(&bond->lock); + if (res) + buf[res-1] = '\n'; /* eat the leftover space */ + return res; +} + +/* + * Set the slaves in the current bond. The bond interface must be + * up for this to succeed. + * This is supposed to be only thin wrapper for bond_enslave and bond_release. + * All hard work should be done there. + */ +static ssize_t bonding_store_slaves(struct device *d, + struct device_attribute *attr, + const char *buffer, size_t count) +{ + char command[IFNAMSIZ + 1] = { 0, }; + char *ifname; + int res, ret = count; + struct net_device *dev; + struct bonding *bond = to_bond(d); + + if (!rtnl_trylock()) + return restart_syscall(); + + sscanf(buffer, "%16s", command); /* IFNAMSIZ*/ + ifname = command + 1; + if ((strlen(command) <= 1) || + !dev_valid_name(ifname)) + goto err_no_cmd; + + dev = __dev_get_by_name(dev_net(bond->dev), ifname); + if (!dev) { + pr_info("%s: Interface %s does not exist!\n", + bond->dev->name, ifname); + ret = -ENODEV; + goto out; + } + + switch (command[0]) { + case '+': + pr_info("%s: Adding slave %s.\n", bond->dev->name, dev->name); + res = bond_enslave(bond->dev, dev); + break; + + case '-': + pr_info("%s: Removing slave %s.\n", bond->dev->name, dev->name); + res = bond_release(bond->dev, dev); + break; + + default: + goto err_no_cmd; + } + + if (res) + ret = res; + goto out; + +err_no_cmd: + pr_err("no command found in slaves file for bond %s. Use +ifname or -ifname.\n", + bond->dev->name); + ret = -EPERM; + +out: + rtnl_unlock(); + return ret; +} + +static DEVICE_ATTR(slaves, S_IRUGO | S_IWUSR, bonding_show_slaves, + bonding_store_slaves); + +/* + * Show and set the bonding mode. The bond interface must be down to + * change the mode. + */ +static ssize_t bonding_show_mode(struct device *d, + struct device_attribute *attr, char *buf) +{ + struct bonding *bond = to_bond(d); + + return sprintf(buf, "%s %d\n", + bond_mode_tbl[bond->params.mode].modename, + bond->params.mode); +} + +static ssize_t bonding_store_mode(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 (bond->dev->flags & IFF_UP) { + pr_err("unable to update mode of %s because interface is up.\n", + bond->dev->name); + ret = -EPERM; + goto out; + } + + if (bond->slave_cnt > 0) { + pr_err("unable to update mode of %s because it has slaves.\n", + bond->dev->name); + ret = -EPERM; + goto out; + } + + new_value = bond_parse_parm(buf, bond_mode_tbl); + if (new_value < 0) { + pr_err("%s: Ignoring invalid mode value %.*s.\n", + bond->dev->name, (int)strlen(buf) - 1, buf); + ret = -EINVAL; + goto out; + } + if ((new_value == BOND_MODE_ALB || + new_value == BOND_MODE_TLB) && + bond->params.arp_interval) { + pr_err("%s: %s mode is incompatible with arp monitoring.\n", + bond->dev->name, bond_mode_tbl[new_value].modename); + ret = -EINVAL; + goto out; + } + + bond->params.mode = new_value; + bond_set_mode_ops(bond, bond->params.mode); + pr_info("%s: setting mode to %s (%d).\n", + bond->dev->name, bond_mode_tbl[new_value].modename, + new_value); +out: + return ret; +} +static DEVICE_ATTR(mode, S_IRUGO | S_IWUSR, + bonding_show_mode, bonding_store_mode); + +/* + * Show and set the bonding transmit hash method. + * The bond interface must be down to change the xmit hash policy. + */ +static ssize_t bonding_show_xmit_hash(struct device *d, + struct device_attribute *attr, + char *buf) +{ + struct bonding *bond = to_bond(d); + + return sprintf(buf, "%s %d\n", + xmit_hashtype_tbl[bond->params.xmit_policy].modename, + bond->params.xmit_policy); +} + +static ssize_t bonding_store_xmit_hash(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 (bond->dev->flags & IFF_UP) { + pr_err("%s: Interface is up. Unable to update xmit policy.\n", + bond->dev->name); + ret = -EPERM; + goto out; + } + + new_value = bond_parse_parm(buf, xmit_hashtype_tbl); + if (new_value < 0) { + pr_err("%s: Ignoring invalid xmit hash policy value %.*s.\n", + bond->dev->name, + (int)strlen(buf) - 1, buf); + ret = -EINVAL; + goto out; + } else { + bond->params.xmit_policy = new_value; + bond_set_mode_ops(bond, bond->params.mode); + pr_info("%s: setting xmit hash policy to %s (%d).\n", + bond->dev->name, + xmit_hashtype_tbl[new_value].modename, new_value); + } +out: + return ret; +} +static DEVICE_ATTR(xmit_hash_policy, S_IRUGO | S_IWUSR, + bonding_show_xmit_hash, bonding_store_xmit_hash); + +/* + * Show and set arp_validate. + */ +static ssize_t bonding_show_arp_validate(struct device *d, + struct device_attribute *attr, + char *buf) +{ + struct bonding *bond = to_bond(d); + + return sprintf(buf, "%s %d\n", + arp_validate_tbl[bond->params.arp_validate].modename, + bond->params.arp_validate); +} + +static ssize_t bonding_store_arp_validate(struct device *d, + struct device_attribute *attr, + const char *buf, size_t count) +{ + int new_value; + struct bonding *bond = to_bond(d); + + new_value = bond_parse_parm(buf, arp_validate_tbl); + if (new_value < 0) { + pr_err("%s: Ignoring invalid arp_validate value %s\n", + bond->dev->name, buf); + return -EINVAL; + } + if (new_value && (bond->params.mode != BOND_MODE_ACTIVEBACKUP)) { + pr_err("%s: arp_validate only supported in active-backup mode.\n", + bond->dev->name); + return -EINVAL; + } + pr_info("%s: setting arp_validate to %s (%d).\n", + bond->dev->name, arp_validate_tbl[new_value].modename, + new_value); + + bond->params.arp_validate = new_value; + + return count; +} + +static DEVICE_ATTR(arp_validate, S_IRUGO | S_IWUSR, bonding_show_arp_validate, + bonding_store_arp_validate); + +/* + * Show and store fail_over_mac. User only allowed to change the + * value when there are no slaves. + */ +static ssize_t bonding_show_fail_over_mac(struct device *d, + struct device_attribute *attr, + char *buf) +{ + struct bonding *bond = to_bond(d); + + return sprintf(buf, "%s %d\n", + fail_over_mac_tbl[bond->params.fail_over_mac].modename, + bond->params.fail_over_mac); +} + +static ssize_t bonding_store_fail_over_mac(struct device *d, + struct device_attribute *attr, + const char *buf, size_t count) +{ + int new_value; + struct bonding *bond = to_bond(d); + + if (bond->slave_cnt != 0) { + pr_err("%s: Can't alter fail_over_mac with slaves in bond.\n", + bond->dev->name); + return -EPERM; + } + + new_value = bond_parse_parm(buf, fail_over_mac_tbl); + if (new_value < 0) { + pr_err("%s: Ignoring invalid fail_over_mac value %s.\n", + bond->dev->name, buf); + return -EINVAL; + } + + bond->params.fail_over_mac = new_value; + pr_info("%s: Setting fail_over_mac to %s (%d).\n", + bond->dev->name, fail_over_mac_tbl[new_value].modename, + new_value); + + return count; +} + +static DEVICE_ATTR(fail_over_mac, S_IRUGO | S_IWUSR, + bonding_show_fail_over_mac, bonding_store_fail_over_mac); + +/* + * Show and set the arp timer interval. There are two tricky bits + * here. First, if ARP monitoring is activated, then we must disable + * MII monitoring. Second, if the ARP timer isn't running, we must + * start it. + */ +static ssize_t bonding_show_arp_interval(struct device *d, + struct device_attribute *attr, + char *buf) +{ + struct bonding *bond = to_bond(d); + + return sprintf(buf, "%d\n", bond->params.arp_interval); +} + +static ssize_t bonding_store_arp_interval(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 arp_interval value specified.\n", + bond->dev->name); + ret = -EINVAL; + goto out; + } + if (new_value < 0) { + pr_err("%s: Invalid arp_interval value %d not in range 1-%d; rejected.\n", + bond->dev->name, new_value, INT_MAX); + ret = -EINVAL; + goto out; + } + if (bond->params.mode == BOND_MODE_ALB || + bond->params.mode == BOND_MODE_TLB) { + pr_info("%s: ARP monitoring cannot be used with ALB/TLB. Only MII monitoring is supported on %s.\n", + bond->dev->name, bond->dev->name); + ret = -EINVAL; + goto out; + } + pr_info("%s: Setting ARP monitoring interval to %d.\n", + bond->dev->name, new_value); + bond->params.arp_interval = new_value; + if (bond->params.miimon) { + pr_info("%s: ARP monitoring cannot be used with MII monitoring. %s Disabling MII monitoring.\n", + bond->dev->name, bond->dev->name); + bond->params.miimon = 0; + if (delayed_work_pending(&bond->mii_work)) { + cancel_delayed_work(&bond->mii_work); + flush_workqueue(bond->wq); + } + } + if (!bond->params.arp_targets[0]) { + pr_info("%s: ARP monitoring has been set up, but no ARP targets have been specified.\n", + bond->dev->name); + } + if (bond->dev->flags & IFF_UP) { + /* If the interface is up, we may need to fire off + * the ARP timer. If the interface is down, the + * timer will get fired off when the open function + * is called. + */ + if (!delayed_work_pending(&bond->arp_work)) { + if (bond->params.mode == BOND_MODE_ACTIVEBACKUP) + INIT_DELAYED_WORK(&bond->arp_work, + bond_activebackup_arp_mon); + else + INIT_DELAYED_WORK(&bond->arp_work, + bond_loadbalance_arp_mon); + + queue_delayed_work(bond->wq, &bond->arp_work, 0); + } + } + +out: + return ret; +} +static DEVICE_ATTR(arp_interval, S_IRUGO | S_IWUSR, + bonding_show_arp_interval, bonding_store_arp_interval); + +/* + * Show and set the arp targets. + */ +static ssize_t bonding_show_arp_targets(struct device *d, + struct device_attribute *attr, + char *buf) +{ + int i, res = 0; + struct bonding *bond = to_bond(d); + + for (i = 0; i < BOND_MAX_ARP_TARGETS; i++) { + if (bond->params.arp_targets[i]) + res += sprintf(buf + res, "%pI4 ", + &bond->params.arp_targets[i]); + } + if (res) + buf[res-1] = '\n'; /* eat the leftover space */ + return res; +} + +static ssize_t bonding_store_arp_targets(struct device *d, + struct device_attribute *attr, + const char *buf, size_t count) +{ + __be32 newtarget; + int i = 0, done = 0, ret = count; + struct bonding *bond = to_bond(d); + __be32 *targets; + + targets = bond->params.arp_targets; + newtarget = in_aton(buf + 1); + /* look for adds */ + if (buf[0] == '+') { + if ((newtarget == 0) || (newtarget == htonl(INADDR_BROADCAST))) { + pr_err("%s: invalid ARP target %pI4 specified for addition\n", + bond->dev->name, &newtarget); + ret = -EINVAL; + goto out; + } + /* look for an empty slot to put the target in, and check for dupes */ + for (i = 0; (i < BOND_MAX_ARP_TARGETS) && !done; i++) { + if (targets[i] == newtarget) { /* duplicate */ + pr_err("%s: ARP target %pI4 is already present\n", + bond->dev->name, &newtarget); + ret = -EINVAL; + goto out; + } + if (targets[i] == 0) { + pr_info("%s: adding ARP target %pI4.\n", + bond->dev->name, &newtarget); + done = 1; + targets[i] = newtarget; + } + } + if (!done) { + pr_err("%s: ARP target table is full!\n", + bond->dev->name); + ret = -EINVAL; + goto out; + } + + } else if (buf[0] == '-') { + if ((newtarget == 0) || (newtarget == htonl(INADDR_BROADCAST))) { + pr_err("%s: invalid ARP target %pI4 specified for removal\n", + bond->dev->name, &newtarget); + ret = -EINVAL; + goto out; + } + + for (i = 0; (i < BOND_MAX_ARP_TARGETS) && !done; i++) { + if (targets[i] == newtarget) { + int j; + pr_info("%s: removing ARP target %pI4.\n", + bond->dev->name, &newtarget); + for (j = i; (j < (BOND_MAX_ARP_TARGETS-1)) && targets[j+1]; j++) + targets[j] = targets[j+1]; + + targets[j] = 0; + done = 1; + } + } + if (!done) { + pr_info("%s: unable to remove nonexistent ARP target %pI4.\n", + bond->dev->name, &newtarget); + ret = -EINVAL; + goto out; + } + } else { + pr_err("no command found in arp_ip_targets file for bond %s. Use +<addr> or -<addr>.\n", + bond->dev->name); + ret = -EPERM; + goto out; + } + +out: + return ret; +} +static DEVICE_ATTR(arp_ip_target, S_IRUGO | S_IWUSR , bonding_show_arp_targets, bonding_store_arp_targets); + +/* + * Show and set the up and down delays. These must be multiples of the + * MII monitoring value, and are stored internally as the multiplier. + * Thus, we must translate to MS for the real world. + */ +static ssize_t bonding_show_downdelay(struct device *d, + struct device_attribute *attr, + char *buf) +{ + struct bonding *bond = to_bond(d); + + return sprintf(buf, "%d\n", bond->params.downdelay * bond->params.miimon); +} + +static ssize_t bonding_store_downdelay(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 (!(bond->params.miimon)) { + pr_err("%s: Unable to set down delay as MII monitoring is disabled\n", + bond->dev->name); + ret = -EPERM; + goto out; + } + + if (sscanf(buf, "%d", &new_value) != 1) { + pr_err("%s: no down delay value specified.\n", bond->dev->name); + ret = -EINVAL; + goto out; + } + if (new_value < 0) { + pr_err("%s: Invalid down delay value %d not in range %d-%d; rejected.\n", + bond->dev->name, new_value, 1, INT_MAX); + ret = -EINVAL; + goto out; + } else { + if ((new_value % bond->params.miimon) != 0) { + pr_warning("%s: Warning: down delay (%d) is not a multiple of miimon (%d), delay rounded to %d ms\n", + bond->dev->name, new_value, + bond->params.miimon, + (new_value / bond->params.miimon) * + bond->params.miimon); + } + bond->params.downdelay = new_value / bond->params.miimon; + pr_info("%s: Setting down delay to %d.\n", + bond->dev->name, + bond->params.downdelay * bond->params.miimon); + + } + +out: + return ret; +} +static DEVICE_ATTR(downdelay, S_IRUGO | S_IWUSR, + bonding_show_downdelay, bonding_store_downdelay); + +static ssize_t bonding_show_updelay(struct device *d, + struct device_attribute *attr, + char *buf) +{ + struct bonding *bond = to_bond(d); + + return sprintf(buf, "%d\n", bond->params.updelay * bond->params.miimon); + +} + +static ssize_t bonding_store_updelay(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 (!(bond->params.miimon)) { + pr_err("%s: Unable to set up delay as MII monitoring is disabled\n", + bond->dev->name); + ret = -EPERM; + goto out; + } + + if (sscanf(buf, "%d", &new_value) != 1) { + pr_err("%s: no up delay value specified.\n", + bond->dev->name); + ret = -EINVAL; + goto out; + } + if (new_value < 0) { + pr_err("%s: Invalid down delay value %d not in range %d-%d; rejected.\n", + bond->dev->name, new_value, 1, INT_MAX); + ret = -EINVAL; + goto out; + } else { + if ((new_value % bond->params.miimon) != 0) { + pr_warning("%s: Warning: up delay (%d) is not a multiple of miimon (%d), updelay rounded to %d ms\n", + bond->dev->name, new_value, + bond->params.miimon, + (new_value / bond->params.miimon) * + bond->params.miimon); + } + bond->params.updelay = new_value / bond->params.miimon; + pr_info("%s: Setting up delay to %d.\n", + bond->dev->name, + bond->params.updelay * bond->params.miimon); + } + +out: + return ret; +} +static DEVICE_ATTR(updelay, S_IRUGO | S_IWUSR, + bonding_show_updelay, bonding_store_updelay); + +/* + * Show and set the LACP interval. Interface must be down, and the mode + * must be set to 802.3ad mode. + */ +static ssize_t bonding_show_lacp(struct device *d, + struct device_attribute *attr, + char *buf) +{ + struct bonding *bond = to_bond(d); + + return sprintf(buf, "%s %d\n", + bond_lacp_tbl[bond->params.lacp_fast].modename, + bond->params.lacp_fast); +} + +static ssize_t bonding_store_lacp(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 (bond->dev->flags & IFF_UP) { + pr_err("%s: Unable to update LACP rate because interface is up.\n", + bond->dev->name); + ret = -EPERM; + goto out; + } + + if (bond->params.mode != BOND_MODE_8023AD) { + pr_err("%s: Unable to update LACP rate because bond is not in 802.3ad mode.\n", + bond->dev->name); + ret = -EPERM; + goto out; + } + + new_value = bond_parse_parm(buf, bond_lacp_tbl); + + if ((new_value == 1) || (new_value == 0)) { + bond->params.lacp_fast = new_value; + bond_3ad_update_lacp_rate(bond); + pr_info("%s: Setting LACP rate to %s (%d).\n", + bond->dev->name, bond_lacp_tbl[new_value].modename, + new_value); + } else { + pr_err("%s: Ignoring invalid LACP rate value %.*s.\n", + bond->dev->name, (int)strlen(buf) - 1, buf); + ret = -EINVAL; + } +out: + return ret; +} +static DEVICE_ATTR(lacp_rate, S_IRUGO | S_IWUSR, + bonding_show_lacp, bonding_store_lacp); + +static ssize_t bonding_show_min_links(struct device *d, + struct device_attribute *attr, + char *buf) +{ + struct bonding *bond = to_bond(d); + + return sprintf(buf, "%d\n", bond->params.min_links); +} + +static ssize_t bonding_store_min_links(struct device *d, + struct device_attribute *attr, + const char *buf, size_t count) +{ + struct bonding *bond = to_bond(d); + int ret; + unsigned int new_value; + + ret = kstrtouint(buf, 0, &new_value); + if (ret < 0) { + pr_err("%s: Ignoring invalid min links value %s.\n", + bond->dev->name, buf); + return ret; + } + + pr_info("%s: Setting min links value to %u\n", + bond->dev->name, new_value); + bond->params.min_links = new_value; + return count; +} +static DEVICE_ATTR(min_links, S_IRUGO | S_IWUSR, + bonding_show_min_links, bonding_store_min_links); + +static ssize_t bonding_show_ad_select(struct device *d, + struct device_attribute *attr, + char *buf) +{ + struct bonding *bond = to_bond(d); + + return sprintf(buf, "%s %d\n", + ad_select_tbl[bond->params.ad_select].modename, + bond->params.ad_select); +} + + +static ssize_t bonding_store_ad_select(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 (bond->dev->flags & IFF_UP) { + pr_err("%s: Unable to update ad_select because interface is up.\n", + bond->dev->name); + ret = -EPERM; + goto out; + } + + new_value = bond_parse_parm(buf, ad_select_tbl); + + if (new_value != -1) { + bond->params.ad_select = new_value; + pr_info("%s: Setting ad_select to %s (%d).\n", + bond->dev->name, ad_select_tbl[new_value].modename, + new_value); + } else { + pr_err("%s: Ignoring invalid ad_select value %.*s.\n", + bond->dev->name, (int)strlen(buf) - 1, buf); + ret = -EINVAL; + } +out: + return ret; +} +static DEVICE_ATTR(ad_select, S_IRUGO | S_IWUSR, + bonding_show_ad_select, bonding_store_ad_select); + +/* + * Show and set the number of peer notifications to send after a failover event. + */ +static ssize_t bonding_show_num_peer_notif(struct device *d, + struct device_attribute *attr, + char *buf) +{ + struct bonding *bond = to_bond(d); + return sprintf(buf, "%d\n", bond->params.num_peer_notif); +} + +static ssize_t bonding_store_num_peer_notif(struct device *d, + struct device_attribute *attr, + const char *buf, size_t count) +{ + struct bonding *bond = to_bond(d); + int err = kstrtou8(buf, 10, &bond->params.num_peer_notif); + return err ? err : count; +} +static DEVICE_ATTR(num_grat_arp, S_IRUGO | S_IWUSR, + bonding_show_num_peer_notif, bonding_store_num_peer_notif); +static DEVICE_ATTR(num_unsol_na, S_IRUGO | S_IWUSR, + bonding_show_num_peer_notif, bonding_store_num_peer_notif); + +/* + * 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 + * start it. + */ +static ssize_t bonding_show_miimon(struct device *d, + struct device_attribute *attr, + char *buf) +{ + struct bonding *bond = to_bond(d); + + return sprintf(buf, "%d\n", bond->params.miimon); +} + +static ssize_t bonding_store_miimon(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 miimon value specified.\n", + bond->dev->name); + ret = -EINVAL; + goto out; + } + if (new_value < 0) { + pr_err("%s: Invalid miimon value %d not in range %d-%d; rejected.\n", + bond->dev->name, new_value, 1, INT_MAX); + ret = -EINVAL; + goto out; + } else { + pr_info("%s: Setting MII monitoring interval to %d.\n", + bond->dev->name, new_value); + bond->params.miimon = new_value; + if (bond->params.updelay) + pr_info("%s: Note: Updating updelay (to %d) since it is a multiple of the miimon value.\n", + bond->dev->name, + bond->params.updelay * bond->params.miimon); + if (bond->params.downdelay) + pr_info("%s: Note: Updating downdelay (to %d) since it is a multiple of the miimon value.\n", + bond->dev->name, + bond->params.downdelay * bond->params.miimon); + if (bond->params.arp_interval) { + pr_info("%s: MII monitoring cannot be used with ARP monitoring. Disabling ARP monitoring...\n", + bond->dev->name); + bond->params.arp_interval = 0; + if (bond->params.arp_validate) { + bond->params.arp_validate = + BOND_ARP_VALIDATE_NONE; + } + if (delayed_work_pending(&bond->arp_work)) { + cancel_delayed_work(&bond->arp_work); + flush_workqueue(bond->wq); + } + } + + if (bond->dev->flags & IFF_UP) { + /* If the interface is up, we may need to fire off + * the MII timer. If the interface is down, the + * timer will get fired off when the open function + * is called. + */ + if (!delayed_work_pending(&bond->mii_work)) { + INIT_DELAYED_WORK(&bond->mii_work, + bond_mii_monitor); + queue_delayed_work(bond->wq, + &bond->mii_work, 0); + } + } + } +out: + return ret; +} +static DEVICE_ATTR(miimon, S_IRUGO | S_IWUSR, + bonding_show_miimon, bonding_store_miimon); + +/* + * Show and set the primary slave. The store function is much + * simpler than bonding_store_slaves function because it only needs to + * handle one interface name. + * The bond must be a mode that supports a primary for this be + * set. + */ +static ssize_t bonding_show_primary(struct device *d, + struct device_attribute *attr, + char *buf) +{ + int count = 0; + struct bonding *bond = to_bond(d); + + if (bond->primary_slave) + count = sprintf(buf, "%s\n", bond->primary_slave->dev->name); + + return count; +} + +static ssize_t bonding_store_primary(struct device *d, + struct device_attribute *attr, + const char *buf, size_t count) +{ + int i; + struct slave *slave; + struct bonding *bond = to_bond(d); + char ifname[IFNAMSIZ]; + + if (!rtnl_trylock()) + return restart_syscall(); + block_netpoll_tx(); + read_lock(&bond->lock); + write_lock_bh(&bond->curr_slave_lock); + + if (!USES_PRIMARY(bond->params.mode)) { + pr_info("%s: Unable to set primary slave; %s is in mode %d\n", + bond->dev->name, bond->dev->name, bond->params.mode); + goto out; + } + + sscanf(buf, "%16s", ifname); /* IFNAMSIZ */ + + /* check to see if we are clearing primary */ + if (!strlen(ifname) || buf[0] == '\n') { + pr_info("%s: Setting primary slave to None.\n", + bond->dev->name); + bond->primary_slave = NULL; + bond_select_active_slave(bond); + goto out; + } + + bond_for_each_slave(bond, slave, i) { + if (strncmp(slave->dev->name, ifname, IFNAMSIZ) == 0) { + pr_info("%s: Setting %s as primary slave.\n", + bond->dev->name, slave->dev->name); + bond->primary_slave = slave; + strcpy(bond->params.primary, slave->dev->name); + bond_select_active_slave(bond); + goto out; + } + } + + pr_info("%s: Unable to set %.*s as primary slave.\n", + bond->dev->name, (int)strlen(buf) - 1, buf); +out: + write_unlock_bh(&bond->curr_slave_lock); + read_unlock(&bond->lock); + unblock_netpoll_tx(); + rtnl_unlock(); + + return count; +} +static DEVICE_ATTR(primary, S_IRUGO | S_IWUSR, + bonding_show_primary, bonding_store_primary); + +/* + * Show and set the primary_reselect flag. + */ +static ssize_t bonding_show_primary_reselect(struct device *d, + struct device_attribute *attr, + char *buf) +{ + struct bonding *bond = to_bond(d); + + return sprintf(buf, "%s %d\n", + pri_reselect_tbl[bond->params.primary_reselect].modename, + bond->params.primary_reselect); +} + +static ssize_t bonding_store_primary_reselect(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 (!rtnl_trylock()) + return restart_syscall(); + + new_value = bond_parse_parm(buf, pri_reselect_tbl); + if (new_value < 0) { + pr_err("%s: Ignoring invalid primary_reselect value %.*s.\n", + bond->dev->name, + (int) strlen(buf) - 1, buf); + ret = -EINVAL; + goto out; + } + + bond->params.primary_reselect = new_value; + pr_info("%s: setting primary_reselect to %s (%d).\n", + bond->dev->name, pri_reselect_tbl[new_value].modename, + new_value); + + block_netpoll_tx(); + read_lock(&bond->lock); + write_lock_bh(&bond->curr_slave_lock); + bond_select_active_slave(bond); + write_unlock_bh(&bond->curr_slave_lock); + read_unlock(&bond->lock); + unblock_netpoll_tx(); +out: + rtnl_unlock(); + return ret; +} +static DEVICE_ATTR(primary_reselect, S_IRUGO | S_IWUSR, + bonding_show_primary_reselect, + bonding_store_primary_reselect); + +/* + * Show and set the use_carrier flag. + */ +static ssize_t bonding_show_carrier(struct device *d, + struct device_attribute *attr, + char *buf) +{ + struct bonding *bond = to_bond(d); + + return sprintf(buf, "%d\n", bond->params.use_carrier); +} + +static ssize_t bonding_store_carrier(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 use_carrier value specified.\n", + bond->dev->name); + ret = -EINVAL; + goto out; + } + if ((new_value == 0) || (new_value == 1)) { + bond->params.use_carrier = new_value; + pr_info("%s: Setting use_carrier to %d.\n", + bond->dev->name, new_value); + } else { + pr_info("%s: Ignoring invalid use_carrier value %d.\n", + bond->dev->name, new_value); + } +out: + return ret; +} +static DEVICE_ATTR(use_carrier, S_IRUGO | S_IWUSR, + bonding_show_carrier, bonding_store_carrier); + + +/* + * Show and set currently active_slave. + */ +static ssize_t bonding_show_active_slave(struct device *d, + struct device_attribute *attr, + char *buf) +{ + struct slave *curr; + struct bonding *bond = to_bond(d); + int count = 0; + + read_lock(&bond->curr_slave_lock); + curr = bond->curr_active_slave; + read_unlock(&bond->curr_slave_lock); + + if (USES_PRIMARY(bond->params.mode) && curr) + count = sprintf(buf, "%s\n", curr->dev->name); + return count; +} + +static ssize_t bonding_store_active_slave(struct device *d, + struct device_attribute *attr, + const char *buf, size_t count) +{ + int i; + struct slave *slave; + struct slave *old_active = NULL; + struct slave *new_active = NULL; + struct bonding *bond = to_bond(d); + char ifname[IFNAMSIZ]; + + if (!rtnl_trylock()) + return restart_syscall(); + + block_netpoll_tx(); + read_lock(&bond->lock); + write_lock_bh(&bond->curr_slave_lock); + + if (!USES_PRIMARY(bond->params.mode)) { + pr_info("%s: Unable to change active slave; %s is in mode %d\n", + bond->dev->name, bond->dev->name, bond->params.mode); + goto out; + } + + sscanf(buf, "%16s", ifname); /* IFNAMSIZ */ + + /* check to see if we are clearing active */ + if (!strlen(ifname) || buf[0] == '\n') { + pr_info("%s: Clearing current active slave.\n", + bond->dev->name); + bond->curr_active_slave = NULL; + bond_select_active_slave(bond); + goto out; + } + + bond_for_each_slave(bond, slave, i) { + if (strncmp(slave->dev->name, ifname, IFNAMSIZ) == 0) { + old_active = bond->curr_active_slave; + new_active = slave; + if (new_active == old_active) { + /* do nothing */ + pr_info("%s: %s is already the current" + " active slave.\n", + bond->dev->name, + slave->dev->name); + goto out; + } + else { + if ((new_active) && + (old_active) && + (new_active->link == BOND_LINK_UP) && + IS_UP(new_active->dev)) { + pr_info("%s: Setting %s as active" + " slave.\n", + bond->dev->name, + slave->dev->name); + bond_change_active_slave(bond, + new_active); + } + else { + pr_info("%s: Could not set %s as" + " active slave; either %s is" + " down or the link is down.\n", + bond->dev->name, + slave->dev->name, + slave->dev->name); + } + goto out; + } + } + } + + pr_info("%s: Unable to set %.*s as active slave.\n", + bond->dev->name, (int)strlen(buf) - 1, buf); + out: + write_unlock_bh(&bond->curr_slave_lock); + read_unlock(&bond->lock); + unblock_netpoll_tx(); + + rtnl_unlock(); + + return count; + +} +static DEVICE_ATTR(active_slave, S_IRUGO | S_IWUSR, + bonding_show_active_slave, bonding_store_active_slave); + + +/* + * Show link status of the bond interface. + */ +static ssize_t bonding_show_mii_status(struct device *d, + struct device_attribute *attr, + char *buf) +{ + struct slave *curr; + struct bonding *bond = to_bond(d); + + read_lock(&bond->curr_slave_lock); + curr = bond->curr_active_slave; + read_unlock(&bond->curr_slave_lock); + + return sprintf(buf, "%s\n", curr ? "up" : "down"); +} +static DEVICE_ATTR(mii_status, S_IRUGO, bonding_show_mii_status, NULL); + + +/* + * Show current 802.3ad aggregator ID. + */ +static ssize_t bonding_show_ad_aggregator(struct device *d, + struct device_attribute *attr, + char *buf) +{ + int count = 0; + struct bonding *bond = to_bond(d); + + if (bond->params.mode == BOND_MODE_8023AD) { + struct ad_info ad_info; + count = sprintf(buf, "%d\n", + (bond_3ad_get_active_agg_info(bond, &ad_info)) + ? 0 : ad_info.aggregator_id); + } + + return count; +} +static DEVICE_ATTR(ad_aggregator, S_IRUGO, bonding_show_ad_aggregator, NULL); + + +/* + * Show number of active 802.3ad ports. + */ +static ssize_t bonding_show_ad_num_ports(struct device *d, + struct device_attribute *attr, + char *buf) +{ + int count = 0; + struct bonding *bond = to_bond(d); + + if (bond->params.mode == BOND_MODE_8023AD) { + struct ad_info ad_info; + count = sprintf(buf, "%d\n", + (bond_3ad_get_active_agg_info(bond, &ad_info)) + ? 0 : ad_info.ports); + } + + return count; +} +static DEVICE_ATTR(ad_num_ports, S_IRUGO, bonding_show_ad_num_ports, NULL); + + +/* + * Show current 802.3ad actor key. + */ +static ssize_t bonding_show_ad_actor_key(struct device *d, + struct device_attribute *attr, + char *buf) +{ + int count = 0; + struct bonding *bond = to_bond(d); + + if (bond->params.mode == BOND_MODE_8023AD) { + struct ad_info ad_info; + count = sprintf(buf, "%d\n", + (bond_3ad_get_active_agg_info(bond, &ad_info)) + ? 0 : ad_info.actor_key); + } + + return count; +} +static DEVICE_ATTR(ad_actor_key, S_IRUGO, bonding_show_ad_actor_key, NULL); + + +/* + * Show current 802.3ad partner key. + */ +static ssize_t bonding_show_ad_partner_key(struct device *d, + struct device_attribute *attr, + char *buf) +{ + int count = 0; + struct bonding *bond = to_bond(d); + + if (bond->params.mode == BOND_MODE_8023AD) { + struct ad_info ad_info; + count = sprintf(buf, "%d\n", + (bond_3ad_get_active_agg_info(bond, &ad_info)) + ? 0 : ad_info.partner_key); + } + + return count; +} +static DEVICE_ATTR(ad_partner_key, S_IRUGO, bonding_show_ad_partner_key, NULL); + + +/* + * Show current 802.3ad partner mac. + */ +static ssize_t bonding_show_ad_partner_mac(struct device *d, + struct device_attribute *attr, + char *buf) +{ + int count = 0; + struct bonding *bond = to_bond(d); + + if (bond->params.mode == BOND_MODE_8023AD) { + struct ad_info ad_info; + if (!bond_3ad_get_active_agg_info(bond, &ad_info)) + count = sprintf(buf, "%pM\n", ad_info.partner_system); + } + + return count; +} +static DEVICE_ATTR(ad_partner_mac, S_IRUGO, bonding_show_ad_partner_mac, NULL); + +/* + * Show the queue_ids of the slaves in the current bond. + */ +static ssize_t bonding_show_queue_id(struct device *d, + struct device_attribute *attr, + char *buf) +{ + struct slave *slave; + int i, res = 0; + struct bonding *bond = to_bond(d); + + if (!rtnl_trylock()) + return restart_syscall(); + + read_lock(&bond->lock); + bond_for_each_slave(bond, slave, i) { + if (res > (PAGE_SIZE - IFNAMSIZ - 6)) { + /* not enough space for another interface_name:queue_id pair */ + if ((PAGE_SIZE - res) > 10) + res = PAGE_SIZE - 10; + res += sprintf(buf + res, "++more++ "); + break; + } + res += sprintf(buf + res, "%s:%d ", + slave->dev->name, slave->queue_id); + } + read_unlock(&bond->lock); + if (res) + buf[res-1] = '\n'; /* eat the leftover space */ + rtnl_unlock(); + return res; +} + +/* + * Set the queue_ids of the slaves in the current bond. The bond + * interface must be enslaved for this to work. + */ +static ssize_t bonding_store_queue_id(struct device *d, + struct device_attribute *attr, + const char *buffer, size_t count) +{ + struct slave *slave, *update_slave; + struct bonding *bond = to_bond(d); + u16 qid; + int i, ret = count; + char *delim; + struct net_device *sdev = NULL; + + if (!rtnl_trylock()) + return restart_syscall(); + + /* delim will point to queue id if successful */ + delim = strchr(buffer, ':'); + if (!delim) + goto err_no_cmd; + + /* + * Terminate string that points to device name and bump it + * up one, so we can read the queue id there. + */ + *delim = '\0'; + if (sscanf(++delim, "%hd\n", &qid) != 1) + goto err_no_cmd; + + /* Check buffer length, valid ifname and queue id */ + if (strlen(buffer) > IFNAMSIZ || + !dev_valid_name(buffer) || + qid > bond->params.tx_queues) + goto err_no_cmd; + + /* Get the pointer to that interface if it exists */ + sdev = __dev_get_by_name(dev_net(bond->dev), buffer); + if (!sdev) + goto err_no_cmd; + + read_lock(&bond->lock); + + /* Search for thes slave and check for duplicate qids */ + update_slave = NULL; + bond_for_each_slave(bond, slave, i) { + if (sdev == slave->dev) + /* + * We don't need to check the matching + * slave for dups, since we're overwriting it + */ + update_slave = slave; + else if (qid && qid == slave->queue_id) { + goto err_no_cmd_unlock; + } + } + + if (!update_slave) + goto err_no_cmd_unlock; + + /* Actually set the qids for the slave */ + update_slave->queue_id = qid; + + read_unlock(&bond->lock); +out: + rtnl_unlock(); + return ret; + +err_no_cmd_unlock: + read_unlock(&bond->lock); +err_no_cmd: + pr_info("invalid input for queue_id set for %s.\n", + bond->dev->name); + ret = -EPERM; + goto out; +} + +static DEVICE_ATTR(queue_id, S_IRUGO | S_IWUSR, bonding_show_queue_id, + bonding_store_queue_id); + + +/* + * Show and set the all_slaves_active flag. + */ +static ssize_t bonding_show_slaves_active(struct device *d, + struct device_attribute *attr, + char *buf) +{ + struct bonding *bond = to_bond(d); + + return sprintf(buf, "%d\n", bond->params.all_slaves_active); +} + +static ssize_t bonding_store_slaves_active(struct device *d, + struct device_attribute *attr, + const char *buf, size_t count) +{ + int i, new_value, ret = count; + struct bonding *bond = to_bond(d); + struct slave *slave; + + if (sscanf(buf, "%d", &new_value) != 1) { + pr_err("%s: no all_slaves_active value specified.\n", + bond->dev->name); + ret = -EINVAL; + goto out; + } + + if (new_value == bond->params.all_slaves_active) + goto out; + + if ((new_value == 0) || (new_value == 1)) { + bond->params.all_slaves_active = new_value; + } else { + pr_info("%s: Ignoring invalid all_slaves_active value %d.\n", + bond->dev->name, new_value); + ret = -EINVAL; + goto out; + } + + bond_for_each_slave(bond, slave, i) { + if (!bond_is_active_slave(slave)) { + if (new_value) + slave->inactive = 0; + else + slave->inactive = 1; + } + } +out: + return ret; +} +static DEVICE_ATTR(all_slaves_active, S_IRUGO | S_IWUSR, + bonding_show_slaves_active, bonding_store_slaves_active); + +/* + * Show and set the number of IGMP membership reports to send on link failure + */ +static ssize_t bonding_show_resend_igmp(struct device *d, + struct device_attribute *attr, + char *buf) +{ + struct bonding *bond = to_bond(d); + + return sprintf(buf, "%d\n", bond->params.resend_igmp); +} + +static ssize_t bonding_store_resend_igmp(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 resend_igmp value specified.\n", + bond->dev->name); + ret = -EINVAL; + goto out; + } + + if (new_value < 0 || new_value > 255) { + pr_err("%s: Invalid resend_igmp value %d not in range 0-255; rejected.\n", + bond->dev->name, new_value); + ret = -EINVAL; + goto out; + } + + pr_info("%s: Setting resend_igmp to %d.\n", + bond->dev->name, new_value); + bond->params.resend_igmp = new_value; +out: + return ret; +} + +static DEVICE_ATTR(resend_igmp, S_IRUGO | S_IWUSR, + bonding_show_resend_igmp, bonding_store_resend_igmp); + +static struct attribute *per_bond_attrs[] = { + &dev_attr_slaves.attr, + &dev_attr_mode.attr, + &dev_attr_fail_over_mac.attr, + &dev_attr_arp_validate.attr, + &dev_attr_arp_interval.attr, + &dev_attr_arp_ip_target.attr, + &dev_attr_downdelay.attr, + &dev_attr_updelay.attr, + &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, + &dev_attr_use_carrier.attr, + &dev_attr_active_slave.attr, + &dev_attr_mii_status.attr, + &dev_attr_ad_aggregator.attr, + &dev_attr_ad_num_ports.attr, + &dev_attr_ad_actor_key.attr, + &dev_attr_ad_partner_key.attr, + &dev_attr_ad_partner_mac.attr, + &dev_attr_queue_id.attr, + &dev_attr_all_slaves_active.attr, + &dev_attr_resend_igmp.attr, + &dev_attr_min_links.attr, + NULL, +}; + +static struct attribute_group bonding_group = { + .name = "bonding", + .attrs = per_bond_attrs, +}; + +/* + * Initialize sysfs. This sets up the bonding_masters file in + * /sys/class/net. + */ +int bond_create_sysfs(struct bond_net *bn) +{ + int ret; + + bn->class_attr_bonding_masters = class_attr_bonding_masters; + sysfs_attr_init(&bn->class_attr_bonding_masters.attr); + + ret = netdev_class_create_file(&bn->class_attr_bonding_masters); + /* + * Permit multiple loads of the module by ignoring failures to + * create the bonding_masters sysfs file. Bonding devices + * created by second or subsequent loads of the module will + * not be listed in, or controllable by, bonding_masters, but + * will have the usual "bonding" sysfs directory. + * + * This is done to preserve backwards compatibility for + * initscripts/sysconfig, which load bonding multiple times to + * configure multiple bonding devices. + */ + if (ret == -EEXIST) { + /* Is someone being kinky and naming a device bonding_master? */ + if (__dev_get_by_name(bn->net, + class_attr_bonding_masters.attr.name)) + pr_err("network device named %s already exists in sysfs", + class_attr_bonding_masters.attr.name); + ret = 0; + } + + return ret; + +} + +/* + * Remove /sys/class/net/bonding_masters. + */ +void bond_destroy_sysfs(struct bond_net *bn) +{ + netdev_class_remove_file(&bn->class_attr_bonding_masters); +} + +/* + * Initialize sysfs for each bond. This sets up and registers + * the 'bondctl' directory for each individual bond under /sys/class/net. + */ +void bond_prepare_sysfs_group(struct bonding *bond) +{ + bond->dev->sysfs_groups[0] = &bonding_group; +} + diff --git a/ANDROID_3.4.5/drivers/net/bonding/bonding.h b/ANDROID_3.4.5/drivers/net/bonding/bonding.h new file mode 100644 index 00000000..4581aa5c --- /dev/null +++ b/ANDROID_3.4.5/drivers/net/bonding/bonding.h @@ -0,0 +1,464 @@ +/* + * 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 <linux/inetdevice.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)) + +#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 +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 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; +}; + +struct bond_parm_tbl { + char *modename; + int mode; +}; + +#define BOND_MAX_MODENAME_LEN 20 + +struct vlan_entry { + struct list_head vlan_list; + 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; + 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 */ + int (*recv_probe)(struct sk_buff *, struct bonding *, + struct slave *); + rwlock_t lock; + rwlock_t curr_slave_lock; + 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); + 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 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 */ +}; + +static inline bool bond_vlan_used(struct bonding *bond) +{ + return !list_empty(&bond->vlan_list); +} + +#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; +} + +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(in_dev, dst, local, RT_SCOPE_HOST); + + rcu_read_unlock(); + return addr; +} + +struct bond_net; + +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(struct bond_net *net); +void bond_destroy_sysfs(struct bond_net *net); +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 + struct class_attribute class_attr_bonding_masters; +}; + +#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 */ |