diff options
Diffstat (limited to 'drivers/net/bonding')
| -rw-r--r-- | drivers/net/bonding/Makefile | 5 | ||||
| -rw-r--r-- | drivers/net/bonding/bond_3ad.c | 2332 | ||||
| -rw-r--r-- | drivers/net/bonding/bond_3ad.h | 293 | ||||
| -rw-r--r-- | drivers/net/bonding/bond_alb.c | 1373 | ||||
| -rw-r--r-- | drivers/net/bonding/bond_alb.h | 91 | ||||
| -rw-r--r-- | drivers/net/bonding/bond_debugfs.c | 145 | ||||
| -rw-r--r-- | drivers/net/bonding/bond_main.c | 5929 | ||||
| -rw-r--r-- | drivers/net/bonding/bond_netlink.c | 573 | ||||
| -rw-r--r-- | drivers/net/bonding/bond_options.c | 1394 | ||||
| -rw-r--r-- | drivers/net/bonding/bond_options.h | 130 | ||||
| -rw-r--r-- | drivers/net/bonding/bond_procfs.c | 296 | ||||
| -rw-r--r-- | drivers/net/bonding/bond_sysfs.c | 1586 | ||||
| -rw-r--r-- | drivers/net/bonding/bond_sysfs_slave.c | 144 | ||||
| -rw-r--r-- | drivers/net/bonding/bonding.h | 629 |
14 files changed, 8840 insertions, 6080 deletions
diff --git a/drivers/net/bonding/Makefile b/drivers/net/bonding/Makefile index 5cdae2bc055..6f4e80853ed 100644 --- a/drivers/net/bonding/Makefile +++ b/drivers/net/bonding/Makefile @@ -4,5 +4,8 @@ obj-$(CONFIG_BONDING) += bonding.o -bonding-objs := bond_main.o bond_3ad.o bond_alb.o bond_sysfs.o +bonding-objs := bond_main.o bond_3ad.o bond_alb.o bond_sysfs.o bond_sysfs_slave.o bond_debugfs.o bond_netlink.o bond_options.o + +proc-$(CONFIG_PROC_FS) += bond_procfs.o +bonding-objs += $(proc-y) diff --git a/drivers/net/bonding/bond_3ad.c b/drivers/net/bonding/bond_3ad.c index f3f5825469d..0dfeaf5da3f 100644 --- a/drivers/net/bonding/bond_3ad.c +++ b/drivers/net/bonding/bond_3ad.c @@ -20,26 +20,28 @@ * */ -//#define BONDING_DEBUG 1 +#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 +/* 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) +/* 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) @@ -47,7 +49,7 @@ #define AD_CHURN_DETECTION_TIME 60 #define AD_AGGREGATE_WAIT_TIME 2 -// Port state definitions(43.4.2.2 in the 802.3ad standard) +/* 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 @@ -57,7 +59,9 @@ #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) +/* 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 @@ -69,63 +73,37 @@ #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 +/* 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 -//endalloun +#define AD_LINK_SPEED_BITMASK_10000MBPS 0x10 -// compare MAC addresses -#define MAC_ADDRESS_COMPARE(A, B) memcmp(A, B, ETH_ALEN) +/* compare MAC addresses */ +#define MAC_ADDRESS_EQUAL(A, B) \ + ether_addr_equal_64bits((const u8 *)A, (const u8 *)B) -static struct mac_addr null_mac_addr = {{0, 0, 0, 0, 0, 0}}; +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; -// ================= 3AD api to bonding and kernel code ================== -static u16 __get_link_speed(struct port *port); -static u8 __get_duplex(struct port *port); -static inline void __initialize_port_locks(struct port *port); -//conversions -static void __ntohs_lacpdu(struct lacpdu *lacpdu); -static u16 __ad_timer_to_ticks(u16 timer_type, u16 Par); - - -// ================= ad code helper functions ================== -//needed by ad_rx_machine(...) -static void __record_pdu(struct lacpdu *lacpdu, struct port *port); -static void __record_default(struct port *port); -static void __update_selected(struct lacpdu *lacpdu, struct port *port); -static void __update_default_selected(struct port *port); -static void __choose_matched(struct lacpdu *lacpdu, struct port *port); -static void __update_ntt(struct lacpdu *lacpdu, struct port *port); - -//needed for ad_mux_machine(..) -static void __attach_bond_to_agg(struct port *port); -static void __detach_bond_from_agg(struct port *port); -static int __agg_ports_are_ready(struct aggregator *aggregator); -static void __set_agg_ports_ready(struct aggregator *aggregator, int val); - -//needed for ad_agg_selection_logic(...) -static u32 __get_agg_bandwidth(struct aggregator *aggregator); -static struct aggregator *__get_active_agg(struct aggregator *aggregator); - +static const u8 lacpdu_mcast_addr[ETH_ALEN] = MULTICAST_LACPDU_ADDR; -// ================= main 802.3ad protocol functions ================== +/* ================= main 802.3ad protocol functions ================== */ static int ad_lacpdu_send(struct port *port); -static int ad_marker_send(struct port *port, struct marker *marker); +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); @@ -135,16 +113,15 @@ 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_initialize_lacpdu(struct lacpdu *Lacpdu); 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 marker *marker_info, struct port *port); -static void ad_marker_response_received(struct marker *marker, 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 ================== -///////////////////////////////////////////////////////////////////////////////// +/* ================= api to bonding and kernel code ================== */ /** * __get_bond_by_port - get the port's bonding struct @@ -154,172 +131,126 @@ static void ad_marker_response_received(struct marker *marker, struct port *port */ static inline struct bonding *__get_bond_by_port(struct port *port) { - if (port->slave == NULL) { + 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. + * The caller must hold RCU or RTNL lock. */ static inline struct aggregator *__get_first_agg(struct port *port) { struct bonding *bond = __get_bond_by_port(port); + struct slave *first_slave; + struct aggregator *agg; - // If there's no bond for this port, or bond has no slaves - if ((bond == NULL) || (bond->slave_cnt == 0)) { + /* If there's no bond for this port, or bond has no slaves */ + if (bond == NULL) return NULL; - } - return &(SLAVE_AD_INFO(bond->first_slave).aggregator); + rcu_read_lock(); + first_slave = bond_first_slave_rcu(bond); + agg = first_slave ? &(SLAVE_AD_INFO(first_slave)->aggregator) : NULL; + rcu_read_unlock(); + + return agg; } /** - * __get_next_agg - get the next aggregator in the bond - * @aggregator: the aggregator we're looking at + * __agg_has_partner - see if we have a partner + * @agg: the agregator 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. + * Return nonzero if aggregator has a partner (denoted by a non-zero ether + * address for the partner). Return 0 if not. */ -static inline struct aggregator *__get_next_agg(struct aggregator *aggregator) +static inline int __agg_has_partner(struct aggregator *agg) { - 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); + 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); + bond_set_slave_inactive_flags(port->slave, BOND_SLAVE_NOTIFY_LATER); } /** * __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); - } + if ((slave->link == BOND_LINK_UP) && bond_slave_is_up(slave)) + bond_set_slave_active_flags(slave, BOND_SLAVE_NOTIFY_LATER); } /** * __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(port->slave->state == BOND_STATE_ACTIVE); + 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 %BANDWIDTH or %COUNT. + * 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 AD_BANDWIDTH; - } + if (bond == NULL) + return BOND_AD_STABLE; - return BOND_AD_INFO(bond).agg_select_mode; + 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) { + if (bond == NULL) return 0; - } return BOND_AD_INFO(bond).agg_select_timer ? 1 : 0; } /** - * __get_rx_machine_lock - lock the port's RX machine + * __get_state_machine_lock - lock the port's state machines * @port: the port we're looking at - * */ -static inline void __get_rx_machine_lock(struct port *port) +static inline void __get_state_machine_lock(struct port *port) { - spin_lock(&(SLAVE_AD_INFO(port->slave).rx_machine_lock)); + spin_lock_bh(&(SLAVE_AD_INFO(port->slave)->state_machine_lock)); } /** - * __release_rx_machine_lock - unlock the port's RX machine + * __release_state_machine_lock - unlock the port's state machines * @port: the port we're looking at - * */ -static inline void __release_rx_machine_lock(struct port *port) +static inline void __release_state_machine_lock(struct port *port) { - spin_unlock(&(SLAVE_AD_INFO(port->slave).rx_machine_lock)); + spin_unlock_bh(&(SLAVE_AD_INFO(port->slave)->state_machine_lock)); } /** @@ -330,20 +261,22 @@ static inline void __release_rx_machine_lock(struct port *port) * 0, * %AD_LINK_SPEED_BITMASK_10MBPS, * %AD_LINK_SPEED_BITMASK_100MBPS, - * %AD_LINK_SPEED_BITMASK_1000MBPS + * %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 { + /* 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; @@ -357,13 +290,19 @@ static u16 __get_link_speed(struct port *port) 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 + /* unknown speed value from ethtool. shouldn't happen */ + speed = 0; break; } } - dprintk("Port %d Received link speed %d update from adapter\n", port->actor_port_number, speed); + pr_debug("Port %d Received link speed %d update from adapter\n", + port->actor_port_number, speed); return speed; } @@ -381,20 +320,23 @@ static u8 __get_duplex(struct port *port) 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 { + /* 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; - dprintk("Port %d Received status full duplex update from adapter\n", port->actor_port_number); + 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; - dprintk("Port %d Received status NOT full duplex update from adapter\n", port->actor_port_number); + retval = 0x0; + pr_debug("Port %d Received status NOT full duplex update from adapter\n", + port->actor_port_number); break; } } @@ -402,37 +344,16 @@ static u8 __get_duplex(struct port *port) } /** - * __initialize_port_locks - initialize a port's RX machine spinlock - * @port: the port we're looking at - * + * __initialize_port_locks - initialize a port's STATE machine spinlock + * @port: the slave of the port we're looking at */ -static inline void __initialize_port_locks(struct port *port) +static inline void __initialize_port_locks(struct slave *slave) { - // make sure it isn't called twice - spin_lock_init(&(SLAVE_AD_INFO(port->slave).rx_machine_lock)); + /* make sure it isn't called twice */ + spin_lock_init(&(SLAVE_AD_INFO(slave)->state_machine_lock)); } -//conversions -/** - * __ntohs_lacpdu - convert the contents of a LACPDU to host byte order - * @lacpdu: the speicifed lacpdu - * - * For each multi-byte field in the lacpdu, convert its content - */ -static void __ntohs_lacpdu(struct lacpdu *lacpdu) -{ - if (lacpdu) { - lacpdu->actor_system_priority = ntohs(lacpdu->actor_system_priority); - lacpdu->actor_key = ntohs(lacpdu->actor_key); - lacpdu->actor_port_priority = ntohs(lacpdu->actor_port_priority); - lacpdu->actor_port = ntohs(lacpdu->actor_port); - lacpdu->partner_system_priority = ntohs(lacpdu->partner_system_priority); - lacpdu->partner_key = ntohs(lacpdu->partner_key); - lacpdu->partner_port_priority = ntohs(lacpdu->partner_port_priority); - lacpdu->partner_port = ntohs(lacpdu->partner_port); - lacpdu->collector_max_delay = ntohs(lacpdu->collector_max_delay); - } -} +/* Conversions */ /** * __ad_timer_to_ticks - convert a given timer type to AD module ticks @@ -441,40 +362,81 @@ static void __ntohs_lacpdu(struct lacpdu *lacpdu) * * 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. + * %SLOW_PERIODIC_TIME. */ static u16 __ad_timer_to_ticks(u16 timer_type, u16 par) { - u16 retval=0; //to silence the compiler + u16 retval = 0; /* to silence the compiler */ switch (timer_type) { - case AD_CURRENT_WHILE_TIMER: // for rx machine usage - if (par) { // for short or long timeout - retval = (AD_SHORT_TIMEOUT_TIME*ad_ticks_per_sec); // short timeout - } else { - retval = (AD_LONG_TIMEOUT_TIME*ad_ticks_per_sec); // long timeout - } + case AD_CURRENT_WHILE_TIMER: /* for rx machine usage */ + if (par) + retval = (AD_SHORT_TIMEOUT_TIME*ad_ticks_per_sec); + else + retval = (AD_LONG_TIMEOUT_TIME*ad_ticks_per_sec); break; - case AD_ACTOR_CHURN_TIMER: // for local churn machine + 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 + 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 + 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 + 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 ================== -///////////////////////////////////////////////////////////////////////////////// +/* ================= 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 + * or this is individual link(aggregation == FALSE) + * then update the state machine Matched variable. + */ + if (((ntohs(lacpdu->partner_port) == port->actor_port_number) && + (ntohs(lacpdu->partner_port_priority) == port->actor_port_priority) && + MAC_ADDRESS_EQUAL(&(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))) || + ((lacpdu->actor_state & AD_STATE_AGGREGATION) == 0) + ) { + port->sm_vars |= AD_PORT_MATCHED; + } else { + port->sm_vars &= ~AD_PORT_MATCHED; + } +} /** * __record_pdu - record parameters from a received lacpdu @@ -487,34 +449,31 @@ static u16 __ad_timer_to_ticks(u16 timer_type, u16 par) */ static void __record_pdu(struct lacpdu *lacpdu, struct port *port) { - // validate lacpdu and port if (lacpdu && port) { - // record the new parameter values for the partner operational - port->partner_oper_port_number = lacpdu->actor_port; - port->partner_oper_port_priority = lacpdu->actor_port_priority; - port->partner_oper_system = lacpdu->actor_system; - port->partner_oper_system_priority = lacpdu->actor_system_priority; - port->partner_oper_key = lacpdu->actor_key; - // zero partener's lase states - port->partner_oper_port_state = 0; - port->partner_oper_port_state |= (lacpdu->actor_state & AD_STATE_LACP_ACTIVITY); - port->partner_oper_port_state |= (lacpdu->actor_state & AD_STATE_LACP_TIMEOUT); - port->partner_oper_port_state |= (lacpdu->actor_state & AD_STATE_AGGREGATION); - port->partner_oper_port_state |= (lacpdu->actor_state & AD_STATE_SYNCHRONIZATION); - port->partner_oper_port_state |= (lacpdu->actor_state & AD_STATE_COLLECTING); - port->partner_oper_port_state |= (lacpdu->actor_state & AD_STATE_DISTRIBUTING); - port->partner_oper_port_state |= (lacpdu->actor_state & AD_STATE_DEFAULTED); - port->partner_oper_port_state |= (lacpdu->actor_state & AD_STATE_EXPIRED); - - // set actor_oper_port_state.defaulted to FALSE + 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)) { - port->partner_oper_port_state |= AD_STATE_SYNCHRONIZATION; - } else { - port->partner_oper_port_state &= ~AD_STATE_SYNCHRONIZATION; - } + /* 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; } } @@ -528,17 +487,12 @@ static void __record_pdu(struct lacpdu *lacpdu, struct port *port) */ static void __record_default(struct port *port) { - // validate the port if (port) { - // record the partner admin parameters - port->partner_oper_port_number = port->partner_admin_port_number; - port->partner_oper_port_priority = port->partner_admin_port_priority; - port->partner_oper_system = port->partner_admin_system; - port->partner_oper_system_priority = port->partner_admin_system_priority; - port->partner_oper_key = port->partner_admin_key; - port->partner_oper_port_state = port->partner_admin_port_state; - - // set actor_oper_port_state.defaulted to true + /* 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; } } @@ -558,17 +512,18 @@ static void __record_default(struct port *port) */ static void __update_selected(struct lacpdu *lacpdu, struct port *port) { - // validate lacpdu and port if (lacpdu && port) { - // check if any parameter is different - if ((lacpdu->actor_port != port->partner_oper_port_number) || - (lacpdu->actor_port_priority != port->partner_oper_port_priority) || - MAC_ADDRESS_COMPARE(&(lacpdu->actor_system), &(port->partner_oper_system)) || - (lacpdu->actor_system_priority != port->partner_oper_system_priority) || - (lacpdu->actor_key != port->partner_oper_key) || - ((lacpdu->actor_state & AD_STATE_AGGREGATION) != (port->partner_oper_port_state & AD_STATE_AGGREGATION)) - ) { - // update the state machine Selected variable + const struct port_params *partner = &port->partner_oper; + + /* check if any parameter is different then + * update the state machine selected variable. + */ + if (ntohs(lacpdu->actor_port) != partner->port_number || + ntohs(lacpdu->actor_port_priority) != partner->port_priority || + !MAC_ADDRESS_EQUAL(&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)) { port->sm_vars &= ~AD_PORT_SELECTED; } } @@ -588,64 +543,26 @@ static void __update_selected(struct lacpdu *lacpdu, struct port *port) */ static void __update_default_selected(struct port *port) { - // validate the port if (port) { - // check if any parameter is different - if ((port->partner_admin_port_number != port->partner_oper_port_number) || - (port->partner_admin_port_priority != port->partner_oper_port_priority) || - MAC_ADDRESS_COMPARE(&(port->partner_admin_system), &(port->partner_oper_system)) || - (port->partner_admin_system_priority != port->partner_oper_system_priority) || - (port->partner_admin_key != port->partner_oper_key) || - ((port->partner_admin_port_state & AD_STATE_AGGREGATION) != (port->partner_oper_port_state & AD_STATE_AGGREGATION)) - ) { - // update the state machine Selected variable + const struct port_params *admin = &port->partner_admin; + const struct port_params *oper = &port->partner_oper; + + /* check if any parameter is different then + * update the state machine selected variable. + */ + if (admin->port_number != oper->port_number || + admin->port_priority != oper->port_priority || + !MAC_ADDRESS_EQUAL(&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)) { port->sm_vars &= ~AD_PORT_SELECTED; } } } /** - * __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. - */ -static void __choose_matched(struct lacpdu *lacpdu, struct port *port) -{ - // validate lacpdu and port - if (lacpdu && port) { - // check if all parameters are alike - if (((lacpdu->partner_port == port->actor_port_number) && - (lacpdu->partner_port_priority == port->actor_port_priority) && - !MAC_ADDRESS_COMPARE(&(lacpdu->partner_system), &(port->actor_system)) && - (lacpdu->partner_system_priority == port->actor_system_priority) && - (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; - } - } -} - -/** * __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 @@ -659,56 +576,27 @@ static void __choose_matched(struct lacpdu *lacpdu, struct port *port) */ static void __update_ntt(struct lacpdu *lacpdu, struct port *port) { - // validate lacpdu and port + /* validate lacpdu and port */ if (lacpdu && port) { - // check if any parameter is different - if ((lacpdu->partner_port != port->actor_port_number) || - (lacpdu->partner_port_priority != port->actor_port_priority) || - MAC_ADDRESS_COMPARE(&(lacpdu->partner_system), &(port->actor_system)) || - (lacpdu->partner_system_priority != port->actor_system_priority) || - (lacpdu->partner_key != port->actor_oper_port_key) || + /* check if any parameter is different then + * update the port->ntt. + */ + if ((ntohs(lacpdu->partner_port) != port->actor_port_number) || + (ntohs(lacpdu->partner_port_priority) != port->actor_port_priority) || + !MAC_ADDRESS_EQUAL(&(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)) ) { - // set ntt to be TRUE - port->ntt = 1; + 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 sience 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 * @@ -719,8 +607,12 @@ static int __agg_ports_are_ready(struct aggregator *aggregator) 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) { + /* 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; @@ -741,12 +633,12 @@ 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) { + for (port = aggregator->lag_ports; port; + port = port->next_port_in_aggregator) { + if (val) port->sm_vars |= AD_PORT_READY; - } else { + else port->sm_vars &= ~AD_PORT_READY; - } } } @@ -757,12 +649,10 @@ static void __set_agg_ports_ready(struct aggregator *aggregator, int val) */ static u32 __get_agg_bandwidth(struct aggregator *aggregator) { - u32 bandwidth=0; - u32 basic_speed; + u32 bandwidth = 0; if (aggregator->num_of_ports) { - basic_speed = __get_link_speed(aggregator->lag_ports); - switch (basic_speed) { + switch (__get_link_speed(aggregator->lag_ports)) { case AD_LINK_SPEED_BITMASK_1MBPS: bandwidth = aggregator->num_of_ports; break; @@ -775,8 +665,11 @@ static u32 __get_agg_bandwidth(struct aggregator *aggregator) 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 silent the compilor .... + bandwidth = 0; /* to silence the compiler */ } } return bandwidth; @@ -786,42 +679,42 @@ static u32 __get_agg_bandwidth(struct aggregator *aggregator) * __get_active_agg - get the current active aggregator * @aggregator: the aggregator we're looking at * + * Caller must hold RCU lock. */ static struct aggregator *__get_active_agg(struct aggregator *aggregator) { - struct aggregator *retval = NULL; + struct bonding *bond = aggregator->slave->bond; + struct list_head *iter; + struct slave *slave; - for (; aggregator; aggregator = __get_next_agg(aggregator)) { - if (aggregator->is_active) { - retval = aggregator; - break; - } - } + bond_for_each_slave_rcu(bond, slave, iter) + if (SLAVE_AD_INFO(slave)->aggregator.is_active) + return &(SLAVE_AD_INFO(slave)->aggregator); - return retval; + return NULL; } /** * __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 + /* 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 = port->actor_system_priority; + lacpdu->actor_system_priority = htons(port->actor_system_priority); lacpdu->actor_system = port->actor_system; - lacpdu->actor_key = port->actor_oper_port_key; - lacpdu->actor_port_priority = port->actor_port_priority; - lacpdu->actor_port = port->actor_port_number; + 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 @@ -829,12 +722,12 @@ static inline void __update_lacpdu_from_port(struct port *port) * lacpdu->partner_information_length initialized */ - lacpdu->partner_system_priority = port->partner_oper_system_priority; - lacpdu->partner_system = port->partner_oper_system; - lacpdu->partner_key = port->partner_oper_key; - lacpdu->partner_port_priority = port->partner_oper_port_priority; - lacpdu->partner_port = port->partner_oper_port_number; - lacpdu->partner_state = port->partner_oper_port_state; + 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 @@ -845,14 +738,9 @@ static inline void __update_lacpdu_from_port(struct port *port) * terminator_length initialized * reserved_50[50] initialized */ - - /* Convert all non u8 parameters to Big Endian for transmit */ - __ntohs_lacpdu(lacpdu); } -////////////////////////////////////////////////////////////////////////////////////// -// ================= main 802.3ad protocol code ====================================== -////////////////////////////////////////////////////////////////////////////////////// +/* ================= main 802.3ad protocol code ========================= */ /** * ad_lacpdu_send - send out a lacpdu packet on a given port @@ -867,28 +755,27 @@ static int ad_lacpdu_send(struct port *port) struct sk_buff *skb; struct lacpdu_header *lacpdu_header; int length = sizeof(struct lacpdu_header); - struct mac_addr lacpdu_multicast_address = AD_MULTICAST_LACPDU_ADDR; skb = dev_alloc_skb(length); - if (!skb) { + if (!skb) return -ENOMEM; - } skb->dev = slave->dev; - skb->mac.raw = skb->data; - skb->nh.raw = skb->data + ETH_HLEN; + 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); - lacpdu_header->ad_header.destination_address = lacpdu_multicast_address; - /* Note: source addres is set to be the member's PERMANENT address, because we use it - to identify loopback lacpdus in receive. */ - lacpdu_header->ad_header.source_address = *((struct mac_addr *)(slave->perm_hwaddr)); - lacpdu_header->ad_header.length_type = PKT_TYPE_LACPDU; + ether_addr_copy(lacpdu_header->hdr.h_dest, lacpdu_mcast_addr); + /* Note: source address is set to be the member's PERMANENT address, + * because we use it to identify loopback lacpdus in receive. + */ + ether_addr_copy(lacpdu_header->hdr.h_source, slave->perm_hwaddr); + lacpdu_header->hdr.h_proto = PKT_TYPE_LACPDU; - lacpdu_header->lacpdu = port->lacpdu; // struct copy + lacpdu_header->lacpdu = port->lacpdu; dev_queue_xmit(skb); @@ -903,35 +790,34 @@ static int ad_lacpdu_send(struct port *port) * Returns: 0 on success * < 0 on error */ -static int ad_marker_send(struct port *port, struct marker *marker) +static int ad_marker_send(struct port *port, struct bond_marker *marker) { struct slave *slave = port->slave; struct sk_buff *skb; - struct marker_header *marker_header; - int length = sizeof(struct marker_header); - struct mac_addr lacpdu_multicast_address = AD_MULTICAST_LACPDU_ADDR; + struct bond_marker_header *marker_header; + int length = sizeof(struct bond_marker_header); skb = dev_alloc_skb(length + 16); - if (!skb) { + if (!skb) return -ENOMEM; - } skb_reserve(skb, 16); skb->dev = slave->dev; - skb->mac.raw = skb->data; - skb->nh.raw = skb->data + ETH_HLEN; + skb_reset_mac_header(skb); + skb->network_header = skb->mac_header + ETH_HLEN; skb->protocol = PKT_TYPE_LACPDU; - marker_header = (struct marker_header *)skb_put(skb, length); + marker_header = (struct bond_marker_header *)skb_put(skb, length); - marker_header->ad_header.destination_address = lacpdu_multicast_address; - /* Note: source addres is set to be the member's PERMANENT address, because we use it - to identify loopback MARKERs in receive. */ - marker_header->ad_header.source_address = *((struct mac_addr *)(slave->perm_hwaddr)); - marker_header->ad_header.length_type = PKT_TYPE_LACPDU; + ether_addr_copy(marker_header->hdr.h_dest, lacpdu_mcast_addr); + /* Note: source address is set to be the member's PERMANENT address, + * because we use it to identify loopback MARKERs in receive. + */ + ether_addr_copy(marker_header->hdr.h_source, slave->perm_hwaddr); + marker_header->hdr.h_proto = PKT_TYPE_LACPDU; - marker_header->marker = *marker; // struct copy + marker_header->marker = *marker; dev_queue_xmit(skb); @@ -941,71 +827,90 @@ static int ad_marker_send(struct port *port, struct marker *marker) /** * 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 + /* 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 + port->sm_mux_state = AD_MUX_DETACHED; } 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 - } + if ((port->sm_vars & AD_PORT_SELECTED) + || (port->sm_vars & AD_PORT_STANDBY)) + /* if SELECTED or STANDBY */ + port->sm_mux_state = AD_MUX_WAITING; break; case AD_MUX_WAITING: - // if SELECTED == FALSE return to DETACH state - if (!(port->sm_vars & AD_PORT_SELECTED)) { // if UNSELECTED + /* if SELECTED == FALSE return to DETACH state */ + if (!(port->sm_vars & AD_PORT_SELECTED)) { 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 + /* 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 + port->sm_mux_state = AD_MUX_DETACHED; break; } - // check if the wait_while_timer expired - if (port->sm_mux_timer_counter && !(--port->sm_mux_timer_counter)) { + /* 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 + /* 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 - } + /* 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; 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 + /* 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; + } 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 + /* 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 + port->sm_mux_state = AD_MUX_DETACHED; } 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 - + 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; } else { - // if port state hasn't changed make - // sure that a collecting distributing - // port in an active aggregator is enabled + /* 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)) { @@ -1014,41 +919,41 @@ static void ad_mux_machine(struct port *port) } } break; - default: //to silence the compiler + default: break; } } - // check if the state machine was changed + /* check if the state machine was changed */ if (port->sm_mux_state != last_state) { - dprintk("Mux Machine: Port=%d, Last State=%d, Curr State=%d\n", port->actor_port_number, last_state, port->sm_mux_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 = 1; + 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 = 1; + 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 = 1; + port->ntt = true; break; - default: //to silence the compiler + default: break; } } @@ -1067,92 +972,100 @@ static void ad_rx_machine(struct lacpdu *lacpdu, struct port *port) { rx_states_t last_state; - // Lock to prevent 2 instances of this function to run simultaneously(rx interrupt and periodic machine callback) - __get_rx_machine_lock(port); - - // keep current State Machine state to compare later if it was changed + /* 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) { - port->sm_rx_state = AD_RX_INITIALIZE; // next state - } - // check if port is not enabled - else if (!(port->sm_vars & AD_PORT_BEGIN) && !port->is_enabled && !(port->sm_vars & AD_PORT_MOVED)) { - port->sm_rx_state = AD_RX_PORT_DISABLED; // next state - } - // 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 + /* check if state machine should change state */ + + /* first, check if port was reinitialized */ + if (port->sm_vars & AD_PORT_BEGIN) + 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)) + 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; 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)) { + /* 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 + port->sm_rx_state = AD_RX_DEFAULTED; break; case AD_RX_CURRENT: - port->sm_rx_state = AD_RX_EXPIRED; // next state + port->sm_rx_state = AD_RX_EXPIRED; break; - default: //to silence the compiler + default: break; } } else { - // if no lacpdu arrived and no timer is on + /* 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 - } + if (port->sm_vars & AD_PORT_MOVED) + port->sm_rx_state = AD_RX_INITIALIZE; + else if (port->is_enabled + && (port->sm_vars + & AD_PORT_LACP_ENABLED)) + port->sm_rx_state = AD_RX_EXPIRED; + else if (port->is_enabled + && ((port->sm_vars + & AD_PORT_LACP_ENABLED) == 0)) + port->sm_rx_state = AD_RX_LACP_DISABLED; break; - default: //to silence the compiler + default: break; } } } - // check if the State machine was changed or new lacpdu arrived + /* check if the State machine was changed or new lacpdu arrived */ if ((port->sm_rx_state != last_state) || (lacpdu)) { - dprintk("Rx Machine: Port=%d, Last State=%d, Curr State=%d\n", port->actor_port_number, last_state, port->sm_rx_state); + 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)) { + if (!(port->actor_oper_port_key & AD_DUPLEX_KEY_BITS)) port->sm_vars &= ~AD_PORT_LACP_ENABLED; - } else { + 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 -*/ + port->sm_rx_state = AD_RX_PORT_DISABLED; + /* 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->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; + /* 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_SHORT_TIMEOUT; + 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; @@ -1163,57 +1076,55 @@ static void ad_rx_machine(struct lacpdu *lacpdu, struct port *port) 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 - printk(KERN_ERR DRV_NAME ": %s: An illegal loopback occurred on " - "adapter (%s). 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); - __release_rx_machine_lock(port); + /* detect loopback situation */ + if (MAC_ADDRESS_EQUAL(&(lacpdu->actor_system), + &(port->actor_system))) { + 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->bond->dev->name, + port->slave->dev->name); return; } __update_selected(lacpdu, port); __update_ntt(lacpdu, port); __record_pdu(lacpdu, port); - __choose_matched(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; - // verify that if the aggregator is enabled, the port is enabled too. - //(because if the link goes down for a short time, the 802.3ad will not - // catch it, and the port will continue to be disabled) - if (port->aggregator && port->aggregator->is_active && !__port_is_enabled(port)) { - __enable_port(port); - } break; - default: //to silence the compiler + default: break; } } - __release_rx_machine_lock(port); } /** * 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 + /* 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 + /* check if there is something to send */ if (port->ntt && (port->sm_vars & AD_PORT_LACP_ENABLED)) { __update_lacpdu_from_port(port); - // send the lacpdu + if (ad_lacpdu_send(port) >= 0) { - dprintk("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 = 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; + /* 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; } } @@ -1227,74 +1138,79 @@ 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 + /* keep current state machine state to compare later if it was changed */ last_state = port->sm_periodic_state; - // check if port was reinitialized + /* 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->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 + port->sm_periodic_state = AD_NO_PERIODIC; } - // check if state machine should change state + /* check if state machine should change state */ else if (port->sm_periodic_timer_counter) { - // check if periodic state machine expired + /* 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 + /* if expired then do tx */ + port->sm_periodic_state = AD_PERIODIC_TX; } else { - // If not expired, check if there is some new timeout parameter from the partner state + /* 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 - } + if (!(port->partner_oper.port_state + & AD_STATE_LACP_TIMEOUT)) + port->sm_periodic_state = AD_SLOW_PERIODIC; break; case AD_SLOW_PERIODIC: - if ((port->partner_oper_port_state & AD_STATE_LACP_TIMEOUT)) { - // stop current timer + if ((port->partner_oper.port_state & AD_STATE_LACP_TIMEOUT)) { port->sm_periodic_timer_counter = 0; - port->sm_periodic_state = AD_PERIODIC_TX; // next state + port->sm_periodic_state = AD_PERIODIC_TX; } break; - default: //to silence the compiler + default: break; } } } else { switch (port->sm_periodic_state) { case AD_NO_PERIODIC: - port->sm_periodic_state = AD_FAST_PERIODIC; // next state + port->sm_periodic_state = AD_FAST_PERIODIC; 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 - } + if (!(port->partner_oper.port_state & + AD_STATE_LACP_TIMEOUT)) + port->sm_periodic_state = AD_SLOW_PERIODIC; + else + port->sm_periodic_state = AD_FAST_PERIODIC; break; - default: //to silence the compiler + default: break; } } - // check if the state machine was changed + /* check if the state machine was changed */ if (port->sm_periodic_state != last_state) { - dprintk("Periodic Machine: Port=%d, Last State=%d, Curr State=%d\n", port->actor_port_number, last_state, port->sm_periodic_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 + port->sm_periodic_timer_counter = 0; 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 + /* decrement 1 tick we lost in the PERIODIC_TX cycle */ + port->sm_periodic_timer_counter = __ad_timer_to_ticks(AD_PERIODIC_TIMER, (u16)(AD_FAST_PERIODIC_TIME))-1; 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 + /* decrement 1 tick we lost in the PERIODIC_TX cycle */ + port->sm_periodic_timer_counter = __ad_timer_to_ticks(AD_PERIODIC_TIMER, (u16)(AD_SLOW_PERIODIC_TIME))-1; break; case AD_PERIODIC_TX: - port->ntt = 1; + port->ntt = true; break; - default: //to silence the compiler + default: break; } } @@ -1312,125 +1228,241 @@ static void ad_port_selection_logic(struct port *port) { struct aggregator *aggregator, *free_aggregator = NULL, *temp_aggregator; struct port *last_port = NULL, *curr_port; + struct list_head *iter; + struct bonding *bond; + struct slave *slave; int found = 0; - // if the port is already Selected, do nothing - if (port->sm_vars & AD_PORT_SELECTED) { + /* 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 + bond = __get_bond_by_port(port); + + /* 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) { + /* 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; + /* if it is the first port attached to the + * aggregator + */ + if (!last_port) { + 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 + /* clear the port's relations to this + * aggregator + */ port->aggregator = NULL; - port->next_port_in_aggregator=NULL; - port->actor_port_aggregator_identifier=0; - - dprintk("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) { + 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 - printk(KERN_WARNING DRV_NAME ": %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); + if (!curr_port) { + /* meaning: the port was related to an aggregator + * but was not on the aggregator port list + */ + pr_warn_ratelimited("%s: Warning: Port %d (on %s) was related to aggregator %d but was not on its port list\n", + port->slave->bond->dev->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)) { + /* search on all aggregators for a suitable aggregator for this port */ + bond_for_each_slave(bond, slave, iter) { + aggregator = &(SLAVE_AD_INFO(slave)->aggregator); - // keep a free aggregator for later use(if needed) + /* keep a free aggregator for later use(if needed) */ if (!aggregator->lag_ports) { - if (!free_aggregator) { - free_aggregator=aggregator; - } + 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) + /* check if current aggregator suits us */ + if (((aggregator->actor_oper_aggregator_key == port->actor_oper_port_key) && /* if all parameters match AND */ + MAC_ADDRESS_EQUAL(&(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 + ((!MAC_ADDRESS_EQUAL(&(port->partner_oper.system), &(null_mac_addr)) && /* partner answers */ + !aggregator->is_individual) /* but is not individual OR */ ) ) { - // attach to the founded aggregator + /* 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->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; - dprintk("Port %d joined LAG %d(existing LAG)\n", port->actor_port_number, port->aggregator->aggregator_identifier); + 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 + /* 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 + /* the port couldn't find an aggregator - attach it to a new + * aggregator + */ if (!found) { if (free_aggregator) { - // assign port a new 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 = 0; - } else { - port->aggregator->is_individual = 1; - } + 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->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 + /* mark this port as selected */ port->sm_vars |= AD_PORT_SELECTED; - dprintk("Port %d joined LAG %d(new LAG)\n", port->actor_port_number, port->aggregator->aggregator_identifier); + pr_debug("Port %d joined LAG %d(new LAG)\n", + port->actor_port_number, + port->aggregator->aggregator_identifier); } else { - printk(KERN_ERR DRV_NAME ": %s: Port %d (on %s) did not find a suitable aggregator\n", - port->slave->dev->master->name, + pr_err("%s: Port %d (on %s) did not find a suitable aggregator\n", + port->slave->bond->dev->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)); + /* 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; - if (!__check_agg_selection_timer(port) && (aggregator = __get_first_agg(port))) { - ad_agg_selection_logic(aggregator); + /*FALLTHROUGH*/ + case BOND_AD_STABLE: + case BOND_AD_BANDWIDTH: + if (__get_agg_bandwidth(curr) > __get_agg_bandwidth(best)) + return curr; + + break; + + default: + pr_warn_ratelimited("%s: Impossible agg select mode %d\n", + curr->slave->bond->dev->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); } /** @@ -1438,167 +1470,148 @@ static void ad_port_selection_logic(struct port *port) * @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 (at first time) 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. + * + * 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 *aggregator) +static void ad_agg_selection_logic(struct aggregator *agg) { - struct aggregator *best_aggregator = NULL, *active_aggregator = NULL; - struct aggregator *last_active_aggregator = NULL, *origin_aggregator; + struct aggregator *best, *active, *origin; + struct bonding *bond = agg->slave->bond; + struct list_head *iter; + struct slave *slave; struct port *port; - u16 num_of_aggs=0; - - origin_aggregator = aggregator; - //get current active aggregator - last_active_aggregator = __get_active_agg(aggregator); - - // search for the aggregator with the most ports attached to it. - do { - // count how many candidate lag's we have - if (aggregator->lag_ports) { - num_of_aggs++; - } - if (aggregator->is_active && !aggregator->is_individual && // if current aggregator is the active aggregator - MAC_ADDRESS_COMPARE(&(aggregator->partner_system), &(null_mac_addr))) { // and partner answers to 802.3ad PDUs - if (aggregator->num_of_ports) { // if any ports attached to the current aggregator - best_aggregator=NULL; // disregard the best aggregator that was chosen by now - break; // stop the selection of other aggregator if there are any ports attached to this active aggregator - } else { // no ports attached to this active aggregator - aggregator->is_active = 0; // mark this aggregator as not active anymore - } - } - if (aggregator->num_of_ports) { // if any ports attached - if (best_aggregator) { // if there is a candidte aggregator - //The reasons for choosing new best aggregator: - // 1. if current agg is NOT individual and the best agg chosen so far is individual OR - // current and best aggs are both individual or both not individual, AND - // 2a. current agg partner reply but best agg partner do not reply OR - // 2b. current agg partner reply OR current agg partner do not reply AND best agg partner also do not reply AND - // current has more ports/bandwidth, or same amount of ports but current has faster ports, THEN - // current agg become best agg so far - - //if current agg is NOT individual and the best agg chosen so far is individual change best_aggregator - if (!aggregator->is_individual && best_aggregator->is_individual) { - best_aggregator=aggregator; - } - // current and best aggs are both individual or both not individual - else if ((aggregator->is_individual && best_aggregator->is_individual) || - (!aggregator->is_individual && !best_aggregator->is_individual)) { - // current and best aggs are both individual or both not individual AND - // current agg partner reply but best agg partner do not reply - if ((MAC_ADDRESS_COMPARE(&(aggregator->partner_system), &(null_mac_addr)) && - !MAC_ADDRESS_COMPARE(&(best_aggregator->partner_system), &(null_mac_addr)))) { - best_aggregator=aggregator; - } - // current agg partner reply OR current agg partner do not reply AND best agg partner also do not reply - else if (! (!MAC_ADDRESS_COMPARE(&(aggregator->partner_system), &(null_mac_addr)) && - MAC_ADDRESS_COMPARE(&(best_aggregator->partner_system), &(null_mac_addr)))) { - if ((__get_agg_selection_mode(aggregator->lag_ports) == AD_BANDWIDTH)&& - (__get_agg_bandwidth(aggregator) > __get_agg_bandwidth(best_aggregator))) { - best_aggregator=aggregator; - } else if (__get_agg_selection_mode(aggregator->lag_ports) == AD_COUNT) { - if (((aggregator->num_of_ports > best_aggregator->num_of_ports) && - (aggregator->actor_oper_aggregator_key & AD_SPEED_KEY_BITS))|| - ((aggregator->num_of_ports == best_aggregator->num_of_ports) && - ((u16)(aggregator->actor_oper_aggregator_key & AD_SPEED_KEY_BITS) > - (u16)(best_aggregator->actor_oper_aggregator_key & AD_SPEED_KEY_BITS)))) { - best_aggregator=aggregator; - } - } - } - } - } else { - best_aggregator=aggregator; + rcu_read_lock(); + origin = agg; + active = __get_active_agg(agg); + best = (active && agg_device_up(active)) ? active : NULL; + + bond_for_each_slave_rcu(bond, slave, iter) { + agg = &(SLAVE_AD_INFO(slave)->aggregator); + + agg->is_active = 0; + + if (agg->num_of_ports && agg_device_up(agg)) + best = ad_agg_selection_test(best, 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; } } - aggregator->is_active = 0; // mark all aggregators as not active anymore - } while ((aggregator = __get_next_agg(aggregator))); - - // if we have new aggregator selected, don't replace the old aggregator if it has an answering partner, - // or if both old aggregator and new aggregator don't have answering partner - if (best_aggregator) { - if (last_active_aggregator && last_active_aggregator->lag_ports && last_active_aggregator->lag_ports->is_enabled && - (MAC_ADDRESS_COMPARE(&(last_active_aggregator->partner_system), &(null_mac_addr)) || // partner answers OR - (!MAC_ADDRESS_COMPARE(&(last_active_aggregator->partner_system), &(null_mac_addr)) && // both old and new - !MAC_ADDRESS_COMPARE(&(best_aggregator->partner_system), &(null_mac_addr)))) // partner do not answer - ) { - // if new aggregator has link, and old aggregator does not, replace old aggregator.(do nothing) - // -> don't replace otherwise. - if (!(!last_active_aggregator->actor_oper_aggregator_key && best_aggregator->actor_oper_aggregator_key)) { - best_aggregator=NULL; - last_active_aggregator->is_active = 1; // don't replace good old aggregator + } - } - } + if (best && (best == active)) { + best = NULL; + active->is_active = 1; } - // if there is new best aggregator, activate it - if (best_aggregator) { - for (aggregator = __get_first_agg(best_aggregator->lag_ports); - aggregator; - aggregator = __get_next_agg(aggregator)) { + /* 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"); - dprintk("Agg=%d; Ports=%d; a key=%d; p key=%d; Indiv=%d; Active=%d\n", - aggregator->aggregator_identifier, aggregator->num_of_ports, - aggregator->actor_oper_aggregator_key, aggregator->partner_oper_aggregator_key, - aggregator->is_individual, aggregator->is_active); - } + bond_for_each_slave_rcu(bond, slave, iter) { + agg = &(SLAVE_AD_INFO(slave)->aggregator); - // check if any partner replys - if (best_aggregator->is_individual) { - printk(KERN_WARNING DRV_NAME ": %s: Warning: No 802.3ad response from " - "the link partner for any adapters in the bond\n", - best_aggregator->slave->dev->master->name); + 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 there are more than one aggregator - if (num_of_aggs > 1) { - dprintk("Warning: More than one Link Aggregation Group was " - "found in the bond. Only one group will function in the bond\n"); + /* check if any partner replys */ + if (best->is_individual) { + pr_warn_ratelimited("%s: Warning: No 802.3ad response from the link partner for any adapters in the bond\n", + best->slave ? + best->slave->bond->dev->name : "NULL"); } - best_aggregator->is_active = 1; - dprintk("LAG %d choosed as the active LAG\n", best_aggregator->aggregator_identifier); - dprintk("Agg=%d; Ports=%d; a key=%d; p key=%d; Indiv=%d; Active=%d\n", - best_aggregator->aggregator_identifier, best_aggregator->num_of_ports, - best_aggregator->actor_oper_aggregator_key, best_aggregator->partner_oper_aggregator_key, - best_aggregator->is_individual, best_aggregator->is_active); - - // disable the ports that were related to the former active_aggregator - if (last_active_aggregator) { - for (port=last_active_aggregator->lag_ports; port; port=port->next_port_in_aggregator) { + 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_aggregator = __get_active_agg(origin_aggregator); + /* if the selected aggregator is of join individuals + * (partner_system is NULL), enable their ports + */ + active = __get_active_agg(origin); - if (active_aggregator) { - if (!MAC_ADDRESS_COMPARE(&(active_aggregator->partner_system), &(null_mac_addr))) { - for (port=active_aggregator->lag_ports; port; port=port->next_port_in_aggregator) { + if (active) { + if (!__agg_has_partner(active)) { + for (port = active->lag_ports; port; + port = port->next_port_in_aggregator) { __enable_port(port); } } } + + rcu_read_unlock(); + + 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 = 0; + aggregator->is_individual = false; aggregator->actor_admin_aggregator_key = 0; aggregator->actor_oper_aggregator_key = 0; aggregator->partner_system = null_mac_addr; @@ -1609,14 +1622,14 @@ static void ad_clear_agg(struct aggregator *aggregator) aggregator->lag_ports = NULL; aggregator->is_active = 0; aggregator->num_of_ports = 0; - dprintk("LAG %d was cleared\n", aggregator->aggregator_identifier); + 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) { @@ -1633,40 +1646,50 @@ static void ad_initialize_agg(struct aggregator *aggregator) * 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 = 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; + 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) { + if (lacp_fast) port->actor_oper_port_state |= AD_STATE_LACP_TIMEOUT; - } - port->partner_admin_system = null_mac_addr; - port->partner_oper_system = null_mac_addr; - port->partner_admin_system_priority = 0xffff; - port->partner_oper_system_priority = 0xffff; - port->partner_admin_key = 1; - port->partner_oper_key = 1; - port->partner_admin_port_number = 1; - port->partner_oper_port_number = 1; - port->partner_admin_port_priority = 0xff; - port->partner_oper_port_priority = 0xff; - port->partner_admin_port_state = 1; - port->partner_oper_port_state = 1; - port->is_enabled = 1; - // ****** private parameters ****** + 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; @@ -1681,7 +1704,7 @@ static void ad_initialize_port(struct port *port, int lacp_fast) port->next_port_in_aggregator = NULL; port->transaction_id = 0; - ad_initialize_lacpdu(&(port->lacpdu)); + memcpy(&port->lacpdu, &lacpdu, sizeof(lacpdu)); } } @@ -1694,7 +1717,9 @@ static void ad_initialize_port(struct port *port, int lacp_fast) static void ad_enable_collecting_distributing(struct port *port) { if (port->aggregator->is_active) { - dprintk("Enabling port %d(LAG %d)\n", port->actor_port_number, port->aggregator->aggregator_identifier); + pr_debug("Enabling port %d(LAG %d)\n", + port->actor_port_number, + port->aggregator->aggregator_identifier); __enable_port(port); } } @@ -1702,73 +1727,38 @@ static void ad_enable_collecting_distributing(struct 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))) { - dprintk("Disabling port %d(LAG %d)\n", port->actor_port_number, port->aggregator->aggregator_identifier); + if (port->aggregator && + !MAC_ADDRESS_EQUAL(&(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 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) { - dprintk("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 marker *marker_info,struct port *port) +static void ad_marker_info_received(struct bond_marker *marker_info, + struct port *port) { - struct marker marker; + struct bond_marker marker; - // copy the received marker data to the response marker - //marker = *marker_info; - memcpy(&marker, marker_info, sizeof(struct marker)); - // change the marker subtype to marker response - marker.tlv_type=AD_MARKER_RESPONSE_SUBTYPE; - // send the marker response + /* copy the received marker data to the response marker */ + 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) { - dprintk("Sent Marker Response on port %d\n", port->actor_port_number); + pr_debug("Sent Marker Response on port %d\n", + port->actor_port_number); } } @@ -1781,94 +1771,58 @@ static void ad_marker_info_received(struct marker *marker_info,struct port *port * response for marker PDU's, in this stage, but only to respond to marker * information. */ -static void ad_marker_response_received(struct marker *marker, struct port *port) +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 + marker = NULL; + port = NULL; + /* 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 + /** - * ad_initialize_lacpdu - initialize a given lacpdu structure - * @lacpdu: lacpdu structure to initialize + * bond_3ad_initiate_agg_selection - initate aggregator selection + * @bond: bonding struct * + * 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. */ -static void ad_initialize_lacpdu(struct lacpdu *lacpdu) +void bond_3ad_initiate_agg_selection(struct bonding *bond, int timeout) { - u16 index; - - // initialize lacpdu data - lacpdu->subtype = 0x01; - lacpdu->version_number = 0x01; - lacpdu->tlv_type_actor_info = 0x01; - lacpdu->actor_information_length = 0x14; - // lacpdu->actor_system_priority updated on send - // lacpdu->actor_system updated on send - // lacpdu->actor_key updated on send - // lacpdu->actor_port_priority updated on send - // lacpdu->actor_port updated on send - // lacpdu->actor_state updated on send - lacpdu->tlv_type_partner_info = 0x02; - lacpdu->partner_information_length = 0x14; - for (index=0; index<=2; index++) { - lacpdu->reserved_3_1[index]=0; - } - // lacpdu->partner_system_priority updated on send - // lacpdu->partner_system updated on send - // lacpdu->partner_key updated on send - // lacpdu->partner_port_priority updated on send - // lacpdu->partner_port updated on send - // lacpdu->partner_state updated on send - for (index=0; index<=2; index++) { - lacpdu->reserved_3_2[index]=0; - } - lacpdu->tlv_type_collector_info = 0x03; - lacpdu->collector_information_length= 0x10; - lacpdu->collector_max_delay = AD_COLLECTOR_MAX_DELAY; - for (index=0; index<=11; index++) { - lacpdu->reserved_12[index]=0; - } - lacpdu->tlv_type_terminator = 0x00; - lacpdu->terminator_length = 0; - for (index=0; index<=49; index++) { - lacpdu->reserved_50[index]=0; - } + BOND_AD_INFO(bond).agg_select_timer = timeout; } -////////////////////////////////////////////////////////////////////////////////////// -// ================= AD exported functions to the main bonding code ================== -////////////////////////////////////////////////////////////////////////////////////// - -// Check aggregators status in team every T seconds -#define AD_AGGREGATOR_SELECTION_TIMER 8 - -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) - * @lacp_fast: boolean. whether fast periodic should be used * * Can be called only after the mac address of the bond is set. */ -void bond_3ad_initialize(struct bonding *bond, u16 tick_resolution, int lacp_fast) -{ - // check that the bond is not initialized yet - if (MAC_ADDRESS_COMPARE(&(BOND_AD_INFO(bond).system.sys_mac_addr), &(bond->dev->dev_addr))) { +void bond_3ad_initialize(struct bonding *bond, u16 tick_resolution) +{ + /* check that the bond is not initialized yet */ + if (!MAC_ADDRESS_EQUAL(&(BOND_AD_INFO(bond).system.sys_mac_addr), + bond->dev->dev_addr)) { - aggregator_identifier = 0; + BOND_AD_INFO(bond).aggregator_identifier = 0; - BOND_AD_INFO(bond).lacp_fast = lacp_fast; 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) + /* initialize how many times this module is called in one + * second (should be about every 100ms) + */ ad_ticks_per_sec = tick_resolution; - // initialize the aggregator selection timer(to activate an aggregation selection after initialize) - BOND_AD_INFO(bond).agg_select_timer = (AD_AGGREGATOR_SELECTION_TIMER * ad_ticks_per_sec); - BOND_AD_INFO(bond).agg_select_mode = AD_BANDWIDTH; + bond_3ad_initiate_agg_selection(bond, + AD_AGGREGATOR_SELECTION_TIMER * + ad_ticks_per_sec); } } @@ -1879,65 +1833,57 @@ void bond_3ad_initialize(struct bonding *bond, u16 tick_resolution, int lacp_fas * Returns: 0 on success * < 0 on error */ -int bond_3ad_bind_slave(struct slave *slave) +void 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) { - printk(KERN_ERR DRV_NAME ": %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 intialized yet. - if (SLAVE_AD_INFO(slave).port.slave != slave) { + /* 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); + /* port initialization */ + port = &(SLAVE_AD_INFO(slave)->port); - ad_initialize_port(port, BOND_AD_INFO(bond).lacp_fast); + ad_initialize_port(port, bond->params.lacp_fast); + __initialize_port_locks(slave); 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_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->actor_admin_port_key = 0; 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)) { + /* 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 + /* 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) + /* 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); + /* 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->aggregator_identifier = ++BOND_AD_INFO(bond).aggregator_identifier; aggregator->slave = slave; aggregator->is_active = 0; aggregator->num_of_ports = 0; } - - return 0; } /** @@ -1953,51 +1899,64 @@ 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); + struct bonding *bond = slave->bond; + struct slave *slave_iter; + struct list_head *iter; - // find the port related to this slave - port = &(SLAVE_AD_INFO(slave).port); + aggregator = &(SLAVE_AD_INFO(slave)->aggregator); + port = &(SLAVE_AD_INFO(slave)->port); - // if slave is null, the whole port is not initialized + /* if slave is null, the whole port is not initialized */ if (!port->slave) { - printk(KERN_WARNING DRV_NAME ": Warning: %s: Trying to " - "unbind an uninitialized port on %s\n", - slave->dev->master->name, slave->dev->name); + pr_warn("Warning: %s: Trying to unbind an uninitialized port on %s\n", + slave->bond->dev->name, slave->dev->name); return; } - dprintk("Unbinding Link Aggregation Group %d\n", aggregator->aggregator_identifier); + 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 + /* 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 connected to to our port only - if (!new_aggregator->lag_ports || ((new_aggregator->lag_ports == port) && !new_aggregator->lag_ports->next_port_in_aggregator)) { + /* 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) */ + bond_for_each_slave(bond, slave_iter, iter) { + new_aggregator = &(SLAVE_AD_INFO(slave_iter)->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))) { - dprintk("Some port(s) related to LAG %d - replaceing with LAG %d\n", aggregator->aggregator_identifier, new_aggregator->aggregator_identifier); + if (!slave_iter) + new_aggregator = NULL; - if ((new_aggregator->lag_ports == port) && new_aggregator->is_active) { - printk(KERN_INFO DRV_NAME ": %s: Removing an active aggregator\n", - aggregator->slave->dev->master->name); - // select new active aggregator + /* 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 - replacing 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->bond->dev->name); select_new_active_agg = 1; } @@ -2013,58 +1972,66 @@ void bond_3ad_unbind_slave(struct slave *slave) 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; + /* 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) { + + if (select_new_active_agg) ad_agg_selection_logic(__get_first_agg(port)); - } } else { - printk(KERN_WARNING DRV_NAME ": %s: Warning: unbinding aggregator, " - "and could not find a new aggregator for its ports\n", - slave->dev->master->name); + pr_warn("%s: Warning: unbinding aggregator, and could not find a new aggregator for its ports\n", + slave->bond->dev->name); } - } else { // in case that the only port related to this aggregator is the one we want to remove + } 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) { - printk(KERN_INFO DRV_NAME ": %s: Removing an active aggregator\n", - slave->dev->master->name); - // select new active aggregator - ad_agg_selection_logic(__get_first_agg(port)); + pr_info("%s: Removing an active aggregator\n", + slave->bond->dev->name); + /* select new active aggregator */ + temp_aggregator = __get_first_agg(port); + if (temp_aggregator) + ad_agg_selection_logic(temp_aggregator); } } } - dprintk("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)) { + pr_debug("Unbinding port %d\n", port->actor_port_number); + + /* find the aggregator that this port is connected to */ + bond_for_each_slave(bond, slave_iter, iter) { + temp_aggregator = &(SLAVE_AD_INFO(slave_iter)->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) { + /* 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 { + else temp_aggregator->lag_ports = temp_port->next_port_in_aggregator; - } temp_aggregator->num_of_ports--; - if (temp_aggregator->num_of_ports==0) { + 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) { - printk(KERN_INFO DRV_NAME ": %s: Removing an active aggregator\n", - slave->dev->master->name); - // select new active aggregator + pr_info("%s: Removing an active aggregator\n", + slave->bond->dev->name); + /* select new active aggregator */ ad_agg_selection_logic(__get_first_agg(port)); } } @@ -2072,7 +2039,7 @@ void bond_3ad_unbind_slave(struct slave *slave) } } } - port->slave=NULL; + port->slave = NULL; } /** @@ -2088,61 +2055,86 @@ void bond_3ad_unbind_slave(struct slave *slave) * 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 bonding *bond) +void bond_3ad_state_machine_handler(struct work_struct *work) { - struct port *port; + struct bonding *bond = container_of(work, struct bonding, + ad_work.work); struct aggregator *aggregator; + struct list_head *iter; + struct slave *slave; + struct port *port; + bool should_notify_rtnl = BOND_SLAVE_NOTIFY_LATER; read_lock(&bond->lock); + rcu_read_lock(); - if (bond->kill_timers) { - goto out; - } - - //check if there are any slaves - if (bond->slave_cnt == 0) { + /* check if there are any slaves */ + if (!bond_has_slaves(bond)) 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))) { + /* 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)) { + slave = bond_first_slave_rcu(bond); + port = slave ? &(SLAVE_AD_INFO(slave)->port) : NULL; + + /* select the active aggregator for the bond */ + if (port) { if (!port->slave) { - printk(KERN_WARNING DRV_NAME ": %s: Warning: bond's first port is " - "uninitialized\n", bond->dev->name); + pr_warn_ratelimited("%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)) { + /* for each port run the state machines */ + bond_for_each_slave_rcu(bond, slave, iter) { + port = &(SLAVE_AD_INFO(slave)->port); if (!port->slave) { - printk(KERN_WARNING DRV_NAME ": %s: Warning: Found an uninitialized " - "port\n", bond->dev->name); + pr_warn_ratelimited("%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) { + /* 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: - mod_timer(&(BOND_AD_INFO(bond).ad_timer), jiffies + ad_delta_in_ticks); -out: + bond_for_each_slave_rcu(bond, slave, iter) { + if (slave->should_notify) { + should_notify_rtnl = BOND_SLAVE_NOTIFY_NOW; + break; + } + } + rcu_read_unlock(); read_unlock(&bond->lock); + + if (should_notify_rtnl && rtnl_trylock()) { + bond_slave_state_notify(bond); + rtnl_unlock(); + } + queue_delayed_work(bond->wq, &bond->ad_work, ad_delta_in_ticks); } /** @@ -2155,46 +2147,59 @@ out: * received frames (loopback). Since only the payload is given to this * function, it check for loopback. */ -static void bond_3ad_rx_indication(struct lacpdu *lacpdu, struct slave *slave, u16 length) +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); + port = &(SLAVE_AD_INFO(slave)->port); if (!port->slave) { - printk(KERN_WARNING DRV_NAME ": %s: Warning: port of slave %s is " - "uninitialized\n", slave->dev->name, slave->dev->master->name); - return; + pr_warn_ratelimited("%s: Warning: port of slave %s is uninitialized\n", + slave->dev->name, slave->bond->dev->name); + return ret; } switch (lacpdu->subtype) { case AD_TYPE_LACPDU: - __ntohs_lacpdu(lacpdu); - dprintk("Received LACPDU on port %d\n", port->actor_port_number); + 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: - // No need to convert fields to Little Endian since we don't use the marker's fields. + ret = RX_HANDLER_CONSUMED; + /* No need to convert fields to Little Endian since we + * don't use the marker's fields. + */ - switch (((struct marker *)lacpdu)->tlv_type) { + switch (((struct bond_marker *)lacpdu)->tlv_type) { case AD_MARKER_INFORMATION_SUBTYPE: - dprintk("Received Marker Information on port %d\n", port->actor_port_number); - ad_marker_info_received((struct marker *)lacpdu, port); + 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: - dprintk("Received Marker Response on port %d\n", port->actor_port_number); - ad_marker_response_received((struct marker *)lacpdu, port); + pr_debug("Received Marker Response on port %d\n", + port->actor_port_number); + ad_marker_response_received((struct bond_marker *)lacpdu, port); break; default: - dprintk("Received an unknown Marker subtype on slot %d\n", port->actor_port_number); + pr_debug("Received an unknown Marker subtype on slot %d\n", + port->actor_port_number); } } } + return ret; } /** @@ -2207,22 +2212,27 @@ void bond_3ad_adapter_speed_changed(struct slave *slave) { struct port *port; - port = &(SLAVE_AD_INFO(slave).port); + port = &(SLAVE_AD_INFO(slave)->port); - // if slave is null, the whole port is not initialized + /* if slave is null, the whole port is not initialized */ if (!port->slave) { - printk(KERN_WARNING DRV_NAME ": Warning: %s: speed " - "changed for uninitialized port on %s\n", - slave->dev->master->name, slave->dev->name); + pr_warn("Warning: %s: speed changed for uninitialized port on %s\n", + slave->bond->dev->name, slave->dev->name); return; } + __get_state_machine_lock(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); - dprintk("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->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; + + __release_state_machine_lock(port); } /** @@ -2235,22 +2245,27 @@ void bond_3ad_adapter_duplex_changed(struct slave *slave) { struct port *port; - port=&(SLAVE_AD_INFO(slave).port); + port = &(SLAVE_AD_INFO(slave)->port); - // if slave is null, the whole port is not initialized + /* if slave is null, the whole port is not initialized */ if (!port->slave) { - printk(KERN_WARNING DRV_NAME ": %s: Warning: duplex changed " - "for uninitialized port on %s\n", - slave->dev->master->name, slave->dev->name); + pr_warn("%s: Warning: duplex changed for uninitialized port on %s\n", + slave->bond->dev->name, slave->dev->name); return; } + __get_state_machine_lock(port); + port->actor_admin_port_key &= ~AD_DUPLEX_KEY_BITS; - port->actor_oper_port_key=port->actor_admin_port_key |= __get_duplex(port); - dprintk("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->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; + + __release_state_machine_lock(port); } /** @@ -2264,172 +2279,255 @@ void bond_3ad_handle_link_change(struct slave *slave, char link) { struct port *port; - port = &(SLAVE_AD_INFO(slave).port); + port = &(SLAVE_AD_INFO(slave)->port); - // if slave is null, the whole port is not initialized + /* if slave is null, the whole port is not initialized */ if (!port->slave) { - printk(KERN_WARNING DRV_NAME ": Warning: %s: link status changed for " - "uninitialized port on %s\n", - slave->dev->master->name, slave->dev->name); + pr_warn("Warning: %s: link status changed for uninitialized port on %s\n", + slave->bond->dev->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 + __get_state_machine_lock(port); + /* 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 = 1; + 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_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); + port->actor_oper_port_key = port->actor_admin_port_key |= + (__get_link_speed(port) << 1); } else { /* link has failed */ - port->is_enabled = 0; + 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->actor_oper_port_key = (port->actor_admin_port_key &= + ~AD_SPEED_KEY_BITS); + } + pr_debug("Port %d changed link status to %s\n", + 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; + + __release_state_machine_lock(port); } /** - * bond_3ad_get_active_agg_info - get information of the active aggregator + * bond_3ad_set_carrier - set link state for bonding master + * @bond - bonding structure + * + * 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; + struct slave *first_slave; + int ret = 1; + + rcu_read_lock(); + first_slave = bond_first_slave_rcu(bond); + if (!first_slave) { + ret = 0; + goto out; + } + active = __get_active_agg(&(SLAVE_AD_INFO(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); + goto out; + } + } else if (!netif_carrier_ok(bond->dev)) { + netif_carrier_on(bond->dev); + goto out; + } + } else if (netif_carrier_ok(bond->dev)) { + netif_carrier_off(bond->dev); + } +out: + rcu_read_unlock(); + return ret; +} + +/** + * __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) +int __bond_3ad_get_active_agg_info(struct bonding *bond, + struct ad_info *ad_info) { struct aggregator *aggregator = NULL; + struct list_head *iter; + struct slave *slave; struct port *port; - for (port = __get_first_port(bond); port; port = __get_next_port(port)) { + bond_for_each_slave_rcu(bond, slave, iter) { + port = &(SLAVE_AD_INFO(slave)->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; - } + if (!aggregator) + return -1; - return -1; + 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; + ether_addr_copy(ad_info->partner_system, + aggregator->partner_system.mac_addr_value); + return 0; +} + +/* Wrapper used to hold bond->lock so no slave manipulation can occur */ +int bond_3ad_get_active_agg_info(struct bonding *bond, struct ad_info *ad_info) +{ + int ret; + + rcu_read_lock(); + ret = __bond_3ad_get_active_agg_info(bond, ad_info); + rcu_read_unlock(); + + return ret; } int bond_3ad_xmit_xor(struct sk_buff *skb, struct net_device *dev) { - struct slave *slave, *start_at; - struct bonding *bond = dev->priv; - int slave_agg_no; + struct bonding *bond = netdev_priv(dev); + struct slave *slave, *first_ok_slave; + struct aggregator *agg; + struct ad_info ad_info; + struct list_head *iter; int slaves_in_agg; + int slave_agg_no; int agg_id; - int i; - struct ad_info ad_info; - int res = 1; - - /* make sure that the slaves list will - * not change during tx - */ - read_lock(&bond->lock); - if (!BOND_IS_OK(bond)) { - goto out; - } - - if (bond_3ad_get_active_agg_info(bond, &ad_info)) { - printk(KERN_DEBUG DRV_NAME ": %s: Error: " - "bond_3ad_get_active_agg_info failed\n", dev->name); - goto out; + 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 err_free; } slaves_in_agg = ad_info.ports; agg_id = ad_info.aggregator_id; if (slaves_in_agg == 0) { - /*the aggregator is empty*/ - printk(KERN_DEBUG DRV_NAME ": %s: Error: active " - "aggregator is empty\n", - dev->name); - goto out; + pr_debug("%s: Error: active aggregator is empty\n", dev->name); + goto err_free; } - slave_agg_no = bond->xmit_hash_policy(skb, dev, slaves_in_agg); + slave_agg_no = bond_xmit_hash(bond, skb) % slaves_in_agg; + first_ok_slave = NULL; - bond_for_each_slave(bond, slave, i) { - struct aggregator *agg = SLAVE_AD_INFO(slave).port.aggregator; + bond_for_each_slave_rcu(bond, slave, iter) { + agg = SLAVE_AD_INFO(slave)->port.aggregator; + if (!agg || agg->aggregator_identifier != agg_id) + continue; - if (agg && (agg->aggregator_identifier == agg_id)) { + if (slave_agg_no >= 0) { + if (!first_ok_slave && bond_slave_can_tx(slave)) + first_ok_slave = slave; slave_agg_no--; - if (slave_agg_no < 0) { - break; - } + continue; + } + + if (bond_slave_can_tx(slave)) { + bond_dev_queue_xmit(bond, skb, slave->dev); + goto out; } } if (slave_agg_no >= 0) { - printk(KERN_ERR DRV_NAME ": %s: Error: Couldn't find a slave to tx on " - "for aggregator ID %d\n", dev->name, agg_id); - goto out; + pr_err("%s: Error: Couldn't find a slave to tx on for aggregator ID %d\n", + dev->name, agg_id); + goto err_free; } - 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; - } - } + /* we couldn't find any suitable slave after the agg_no, so use the + * first suitable found, if found. + */ + if (first_ok_slave) + bond_dev_queue_xmit(bond, skb, first_ok_slave->dev); + else + goto err_free; out: - if (res) { - /* no suitable interface, frame not sent */ - dev_kfree_skb(skb); - } - read_unlock(&bond->lock); - return 0; + return NETDEV_TX_OK; +err_free: + /* no suitable interface, frame not sent */ + dev_kfree_skb_any(skb); + goto out; } -int bond_3ad_lacpdu_recv(struct sk_buff *skb, struct net_device *dev, struct packet_type* ptype, struct net_device *orig_dev) +int bond_3ad_lacpdu_recv(const struct sk_buff *skb, struct bonding *bond, + struct slave *slave) { - struct bonding *bond = dev->priv; - struct slave *slave = NULL; - int ret = NET_RX_DROP; - - if (!(dev->flags & IFF_MASTER)) - goto out; - - read_lock(&bond->lock); - slave = bond_get_slave_by_dev((struct bonding *)dev->priv, orig_dev); - if (!slave) - goto out_unlock; + int ret = RX_HANDLER_ANOTHER; + struct lacpdu *lacpdu, _lacpdu; - bond_3ad_rx_indication((struct lacpdu *) skb->data, slave, skb->len); + if (skb->protocol != PKT_TYPE_LACPDU) + return ret; - ret = NET_RX_SUCCESS; + lacpdu = skb_header_pointer(skb, 0, sizeof(_lacpdu), &_lacpdu); + if (!lacpdu) + return ret; -out_unlock: + read_lock(&bond->lock); + ret = bond_3ad_rx_indication(lacpdu, slave, skb->len); read_unlock(&bond->lock); -out: - dev_kfree_skb(skb); - return ret; } +/** + * bond_3ad_update_lacp_rate - change the lacp rate + * @bond - bonding struct + * + * 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) +{ + struct port *port = NULL; + struct list_head *iter; + struct slave *slave; + int lacp_fast; + + lacp_fast = bond->params.lacp_fast; + bond_for_each_slave(bond, slave, iter) { + 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); + } +} diff --git a/drivers/net/bonding/bond_3ad.h b/drivers/net/bonding/bond_3ad.h index 5ee2cef5b03..bb03b1df2f3 100644 --- a/drivers/net/bonding/bond_3ad.h +++ b/drivers/net/bonding/bond_3ad.h @@ -26,75 +26,75 @@ #include <asm/byteorder.h> #include <linux/skbuff.h> #include <linux/netdevice.h> +#include <linux/if_ether.h> -// General definitions -#define BOND_ETH_P_LACPDU 0x8809 -#define PKT_TYPE_LACPDU __constant_htons(BOND_ETH_P_LACPDU) +/* 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_MULTICAST_LACPDU_ADDR {MULTICAST_LACPDU_ADDR} #define AD_LACP_SLOW 0 #define AD_LACP_FAST 1 typedef struct mac_addr { u8 mac_addr_value[ETH_ALEN]; -} mac_addr_t; +} __packed mac_addr_t; -typedef enum { - AD_BANDWIDTH = 0, - AD_COUNT -} agg_selection_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) +/* 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 + 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) +/* 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 + 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) +/* 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 + 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) +/* tx machine states(43.4.15 in the 802.3ad standard) */ typedef enum { AD_TX_DUMMY, - AD_TRANSMIT // tx Machine + AD_TRANSMIT /* tx Machine */ } tx_states_t; -// rx indication types +/* rx indication types */ typedef enum { - AD_TYPE_LACPDU = 1, // type lacpdu - AD_TYPE_MARKER // type marker + AD_TYPE_LACPDU = 1, /* type lacpdu */ + AD_TYPE_MARKER /* type marker */ } pdu_type_t; -// rx marker indication types +/* rx marker indication types */ typedef enum { - AD_MARKER_INFORMATION_SUBTYPE = 1, // marker imformation subtype - AD_MARKER_RESPONSE_SUBTYPE // marker response subtype -} marker_subtype_t; + 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) +/* timers types(43.4.9 in the 802.3ad standard) */ typedef enum { AD_CURRENT_WHILE_TIMER, AD_ACTOR_CHURN_TIMER, @@ -105,68 +105,62 @@ typedef enum { #pragma pack(1) -typedef struct ad_header { - struct mac_addr destination_address; - struct mac_addr source_address; - u16 length_type; -} ad_header_t; - -// Link Aggregation Control Protocol(LACP) data unit structure(43.4.2.2 in the 802.3ad standard) +/* 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 subtype; /* = LACP(= 0x01) */ u8 version_number; - u8 tlv_type_actor_info; // = actor information(type/length/value) - u8 actor_information_length; // = 20 - u16 actor_system_priority; + u8 tlv_type_actor_info; /* = actor information(type/length/value) */ + u8 actor_information_length; /* = 20 */ + __be16 actor_system_priority; struct mac_addr actor_system; - u16 actor_key; - u16 actor_port_priority; - u16 actor_port; + __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 - u16 partner_system_priority; + 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; - u16 partner_key; - u16 partner_port_priority; - u16 partner_port; + __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 - u16 collector_max_delay; + 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 -} lacpdu_t; + u8 tlv_type_terminator; /* = terminator */ + u8 terminator_length; /* = 0 */ + u8 reserved_50[50]; /* = 0 */ +} __packed lacpdu_t; typedef struct lacpdu_header { - struct ad_header ad_header; + struct ethhdr hdr; struct lacpdu lacpdu; -} lacpdu_header_t; - -// Marker Protocol Data Unit(PDU) structure(43.5.3.2 in the 802.3ad standard) -typedef struct 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 -} marker_t; - -typedef struct marker_header { - struct ad_header ad_header; - struct marker marker; -} marker_header_t; +} __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() @@ -179,109 +173,112 @@ struct port; #pragma pack(8) #endif -// aggregator structure(43.4.5 in the 802.3ad standard) +/* aggregator structure(43.4.5 in the 802.3ad standard) */ typedef struct aggregator { struct mac_addr aggregator_mac_address; u16 aggregator_identifier; - u16 is_individual; // BOOLEAN + 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 + 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 + /* ****** 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; -// port structure(43.4.6 in the 802.3ad standard) +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 + 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; - u16 ntt; // BOOLEAN + bool ntt; u16 actor_admin_port_key; u16 actor_oper_port_key; u8 actor_admin_port_state; u8 actor_oper_port_state; - struct mac_addr partner_admin_system; - struct mac_addr partner_oper_system; - u16 partner_admin_system_priority; - u16 partner_oper_system_priority; - u16 partner_admin_key; - u16 partner_oper_key; - u16 partner_admin_port_number; - u16 partner_oper_port_number; - u16 partner_admin_port_priority; - u16 partner_oper_port_priority; - u8 partner_admin_port_state; - u8 partner_oper_port_state; - u16 is_enabled; // BOOLEAN - // ****** 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 + + 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 -typedef struct ad_system { +/* system structure */ +struct ad_system { u16 sys_priority; struct mac_addr sys_mac_addr; -} ad_system_t; +}; #ifdef __ia64__ #pragma pack() #endif -// ================= AD Exported structures to the main bonding code ================== +/* ========== 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 { - ad_system_t system; // 802.3ad system structure - u32 agg_select_timer; // Timer to select aggregator after all adapter's hand shakes - u32 agg_select_mode; // Mode of selection of active aggregator(bandwidth/count) - int lacp_fast; /* whether fast periodic tx should be - * requested - */ - struct timer_list ad_timer; - struct packet_type ad_pkt_type; + struct ad_system system; /* 802.3ad system structure */ + u32 agg_select_timer; /* Timer to select aggregator after all adapter's hand shakes */ + u16 aggregator_identifier; }; struct ad_slave_info { - struct aggregator aggregator; // 802.3ad aggregator structure - struct port port; // 802.3ad port structure - spinlock_t rx_machine_lock; // To avoid race condition between callback and receive interrupt + 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 lacp_fast); -int bond_3ad_bind_slave(struct slave *slave); +/* ========== AD Exported functions to the main bonding code ========== */ +void bond_3ad_initialize(struct bonding *bond, u16 tick_resolution); +void bond_3ad_bind_slave(struct slave *slave); void bond_3ad_unbind_slave(struct slave *slave); -void bond_3ad_state_machine_handler(struct bonding *bond); +void bond_3ad_state_machine_handler(struct work_struct *); +void bond_3ad_initiate_agg_selection(struct bonding *bond, int timeout); void bond_3ad_adapter_speed_changed(struct slave *slave); void bond_3ad_adapter_duplex_changed(struct slave *slave); void bond_3ad_handle_link_change(struct slave *slave, char link); int bond_3ad_get_active_agg_info(struct bonding *bond, struct ad_info *ad_info); +int __bond_3ad_get_active_agg_info(struct bonding *bond, + struct ad_info *ad_info); int bond_3ad_xmit_xor(struct sk_buff *skb, struct net_device *dev); -int bond_3ad_lacpdu_recv(struct sk_buff *skb, struct net_device *dev, struct packet_type* ptype, struct net_device *orig_dev); -#endif //__BOND_3AD_H__ +int bond_3ad_lacpdu_recv(const struct sk_buff *skb, struct bonding *bond, + struct slave *slave); +int bond_3ad_set_carrier(struct bonding *bond); +void bond_3ad_update_lacp_rate(struct bonding *bond); +#endif /* __BOND_3AD_H__ */ diff --git a/drivers/net/bonding/bond_alb.c b/drivers/net/bonding/bond_alb.c index f2a63186ae0..76c0dade233 100644 --- a/drivers/net/bonding/bond_alb.c +++ b/drivers/net/bonding/bond_alb.c @@ -12,15 +12,14 @@ * 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. + * with this program; if not, see <http://www.gnu.org/licenses/>. * * The full GNU General Public License is included in this distribution in the * file called LICENSE. * */ -//#define BONDING_DEBUG 1 +#define pr_fmt(fmt) KBUILD_MODNAME ": " fmt #include <linux/skbuff.h> #include <linux/netdevice.h> @@ -38,89 +37,81 @@ #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" -#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 - -static const u8 mac_bcast[ETH_ALEN] = {0xff,0xff,0xff,0xff,0xff,0xff}; +#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]; - u16 type; + __be16 type; u8 padding[ETH_ZLEN - ETH_HLEN]; }; struct arp_pkt { - u16 hw_addr_space; - u16 prot_addr_space; + __be16 hw_addr_space; + __be16 prot_addr_space; u8 hw_addr_len; u8 prot_addr_len; - u16 op_code; + __be16 op_code; u8 mac_src[ETH_ALEN]; /* sender hardware address */ - u32 ip_src; /* sender IP address */ + __be32 ip_src; /* sender IP address */ u8 mac_dst[ETH_ALEN]; /* target hardware address */ - u32 ip_dst; /* target IP address */ + __be32 ip_dst; /* target IP address */ }; #pragma pack() -/* Forward declaration */ -static void alb_send_learning_packets(struct slave *slave, u8 mac_addr[]); +static inline struct arp_pkt *arp_pkt(const struct sk_buff *skb) +{ + return (struct arp_pkt *)skb_network_header(skb); +} -static inline u8 _simple_hash(u8 *hash_start, int hash_size) +/* Forward declaration */ +static void alb_send_learning_packets(struct slave *slave, u8 mac_addr[], + bool strict_match); +static void rlb_purge_src_ip(struct bonding *bond, struct arp_pkt *arp); +static void rlb_src_unlink(struct bonding *bond, u32 index); +static void rlb_src_link(struct bonding *bond, u32 ip_src_hash, + u32 ip_dst_hash); + +static inline u8 _simple_hash(const u8 *hash_start, int hash_size) { int i; u8 hash = 0; - for (i = 0; i < hash_size; i++) { + 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)); @@ -151,27 +142,36 @@ static inline void tlb_init_slave(struct slave *slave) SLAVE_TLB_INFO(slave).head = TLB_NULL_INDEX; } -/* Caller must hold bond lock for read */ -static void tlb_clear_slave(struct bonding *bond, struct slave *slave, int save_load) +/* 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; - _lock_tx_hashtbl(bond); - /* clear slave from tx_hashtbl */ tx_hash_table = BOND_ALB_INFO(bond).tx_hashtbl; - 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; + /* 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); +} - _unlock_tx_hashtbl(bond); +/* 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 */ @@ -182,26 +182,18 @@ static int tlb_initialize(struct bonding *bond) struct tlb_client_info *new_hashtbl; int i; - spin_lock_init(&(bond_info->tx_hashtbl_lock)); - - new_hashtbl = kmalloc(size, GFP_KERNEL); - if (!new_hashtbl) { - printk(KERN_ERR DRV_NAME - ": %s: Error: Failed to allocate TLB hash table\n", - bond->dev->name); + new_hashtbl = kzalloc(size, GFP_KERNEL); + if (!new_hashtbl) return -1; - } - _lock_tx_hashtbl(bond); - bond_info->tx_hashtbl = new_hashtbl; + _lock_tx_hashtbl_bh(bond); - memset(bond_info->tx_hashtbl, 0, size); + bond_info->tx_hashtbl = new_hashtbl; - for (i = 0; i < TLB_HASH_TABLE_SIZE; i++) { - tlb_init_table_entry(&bond_info->tx_hashtbl[i], 1); - } + for (i = 0; i < TLB_HASH_TABLE_SIZE; i++) + tlb_init_table_entry(&bond_info->tx_hashtbl[i], 0); - _unlock_tx_hashtbl(bond); + _unlock_tx_hashtbl_bh(bond); return 0; } @@ -211,42 +203,35 @@ static void tlb_deinitialize(struct bonding *bond) { struct alb_bond_info *bond_info = &(BOND_ALB_INFO(bond)); - _lock_tx_hashtbl(bond); + _lock_tx_hashtbl_bh(bond); kfree(bond_info->tx_hashtbl); bond_info->tx_hashtbl = NULL; - _unlock_tx_hashtbl(bond); + _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; - s64 max_gap; - int i, found = 0; - - /* Find the first enabled slave */ - bond_for_each_slave(bond, slave, i) { - if (SLAVE_IS_OK(slave)) { - found = 1; - break; - } - } - - if (!found) { - return NULL; - } + struct list_head *iter; + long long max_gap; - least_loaded = slave; - max_gap = (s64)(slave->speed << 20) - /* Convert to Megabit per sec */ - (s64)(SLAVE_TLB_INFO(slave).load << 3); /* Bytes to bits */ + least_loaded = NULL; + max_gap = LLONG_MIN; /* Find the slave with the largest gap */ - bond_for_each_slave_from(bond, slave, i, least_loaded) { - if (SLAVE_IS_OK(slave)) { - s64 gap = (s64)(slave->speed << 20) - - (s64)(SLAVE_TLB_INFO(slave).load << 3); + bond_for_each_slave_rcu(bond, slave, iter) { + if (bond_slave_can_tx(slave)) { + long long gap = compute_gap(slave); + if (max_gap < gap) { least_loaded = slave; max_gap = gap; @@ -257,15 +242,13 @@ static struct slave *tlb_get_least_loaded_slave(struct bonding *bond) return least_loaded; } -/* Caller must hold bond lock for read */ -static struct slave *tlb_choose_channel(struct bonding *bond, u32 hash_index, u32 skb_len) +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; - _lock_tx_hashtbl(bond); - hash_table = bond_info->tx_hashtbl; assigned_slave = hash_table[hash_index].tx_slave; if (!assigned_slave) { @@ -280,9 +263,8 @@ static struct slave *tlb_choose_channel(struct bonding *bond, u32 hash_index, u3 hash_table[hash_index].next = next_index; hash_table[hash_index].prev = TLB_NULL_INDEX; - if (next_index != TLB_NULL_INDEX) { + if (next_index != TLB_NULL_INDEX) hash_table[next_index].prev = hash_index; - } slave_info->head = hash_index; slave_info->load += @@ -290,16 +272,39 @@ static struct slave *tlb_choose_channel(struct bonding *bond, u32 hash_index, u3 } } - if (assigned_slave) { + if (assigned_slave) hash_table[hash_index].tx_bytes += skb_len; - } - - _unlock_tx_hashtbl(bond); 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)); @@ -319,84 +324,119 @@ static void rlb_update_entry_from_arp(struct bonding *bond, struct arp_pkt *arp) struct rlb_client_info *client_info; u32 hash_index; - _lock_rx_hashtbl(bond); + _lock_rx_hashtbl_bh(bond); - hash_index = _simple_hash((u8*)&(arp->ip_src), sizeof(arp->ip_src)); + 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)) { + (client_info->ip_dst == arp->ip_src) && + (!ether_addr_equal_64bits(client_info->mac_dst, arp->mac_src))) { /* update the clients MAC address */ - memcpy(client_info->mac_dst, arp->mac_src, ETH_ALEN); + ether_addr_copy(client_info->mac_dst, arp->mac_src); client_info->ntt = 1; bond_info->rx_ntt = 1; } - _unlock_rx_hashtbl(bond); + _unlock_rx_hashtbl_bh(bond); } -static int rlb_arp_recv(struct sk_buff *skb, struct net_device *bond_dev, struct packet_type *ptype, struct net_device *orig_dev) +static int rlb_arp_recv(const struct sk_buff *skb, struct bonding *bond, + struct slave *slave) { - struct bonding *bond = bond_dev->priv; - struct arp_pkt *arp = (struct arp_pkt *)skb->data; - int res = NET_RX_DROP; + struct arp_pkt *arp, _arp; - if (!(bond_dev->flags & IFF_MASTER)) + if (skb->protocol != cpu_to_be16(ETH_P_ARP)) goto out; - if (!arp) { - dprintk("Packet has no ARP data\n"); + arp = skb_header_pointer(skb, 0, sizeof(_arp), &_arp); + if (!arp) goto out; - } - if (skb->len < sizeof(struct arp_pkt)) { - dprintk("Packet is too small to be an ARP\n"); - goto out; - } + /* We received an ARP from arp->ip_src. + * We might have used this IP address previously (on the bonding host + * itself or on a system that is bridged together with the bond). + * However, if arp->mac_src is different than what is stored in + * rx_hashtbl, some other host is now using the IP and we must prevent + * sending out client updates with this IP address and the old MAC + * address. + * Clean up all hash table entries that have this address as ip_src but + * have a different mac_src. + */ + rlb_purge_src_ip(bond, arp); if (arp->op_code == htons(ARPOP_REPLY)) { /* update rx hash table for this ARP */ rlb_update_entry_from_arp(bond, arp); - dprintk("Server received an ARP Reply from client\n"); + pr_debug("Server received an ARP Reply from client\n"); } - - res = NET_RX_SUCCESS; - out: - dev_kfree_skb(skb); - - return res; + 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; + struct slave *before = NULL, *rx_slave = NULL, *slave; + struct list_head *iter; + bool found = false; - if (bond_info->next_rx_slave) { - start_at = bond_info->next_rx_slave; - } else { - start_at = bond->first_slave; + bond_for_each_slave(bond, slave, iter) { + if (!bond_slave_can_tx(slave)) + continue; + if (!found) { + if (!before || before->speed < slave->speed) + before = slave; + } else { + if (!rx_slave || rx_slave->speed < slave->speed) + rx_slave = slave; + } + if (slave == bond_info->rx_slave) + found = true; } + /* we didn't find anything after the current or we have something + * better before and up to the current slave + */ + if (!rx_slave || (before && rx_slave->speed < before->speed)) + rx_slave = before; - rx_slave = NULL; + if (rx_slave) + bond_info->rx_slave = rx_slave; - 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) { + return rx_slave; +} + +/* Caller must hold rcu_read_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 *before = NULL, *rx_slave = NULL, *slave; + struct list_head *iter; + bool found = false; + + bond_for_each_slave_rcu(bond, slave, iter) { + if (!bond_slave_can_tx(slave)) + continue; + if (!found) { + if (!before || before->speed < slave->speed) + before = slave; + } else { + if (!rx_slave || rx_slave->speed < slave->speed) rx_slave = slave; - } } + if (slave == bond_info->rx_slave) + found = true; } + /* we didn't find anything after the current or we have something + * better before and up to the current slave + */ + if (!rx_slave || (before && rx_slave->speed < before->speed)) + rx_slave = before; - if (rx_slave) { - bond_info->next_rx_slave = rx_slave->next; - } + if (rx_slave) + bond_info->rx_slave = rx_slave; return rx_slave; } @@ -408,23 +448,24 @@ static struct slave *rlb_next_rx_slave(struct bonding *bond) */ static void rlb_teach_disabled_mac_on_primary(struct bonding *bond, u8 addr[]) { - if (!bond->curr_active_slave) { + if (!bond->curr_active_slave) return; - } if (!bond->alb_info.primary_is_promisc) { - bond->alb_info.primary_is_promisc = 1; - dev_set_promiscuity(bond->curr_active_slave->dev, 1); + 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); + alb_send_learning_packets(bond->curr_active_slave, addr, true); } /* slave being removed should not be active at this point * - * Caller must hold bond lock for read + * Caller must hold rtnl. */ static void rlb_clear_slave(struct bonding *bond, struct slave *slave) { @@ -433,19 +474,19 @@ static void rlb_clear_slave(struct bonding *bond, struct slave *slave) u32 index, next_index; /* clear slave from rx_hashtbl */ - _lock_rx_hashtbl(bond); + _lock_rx_hashtbl_bh(bond); rx_hash_table = bond_info->rx_hashtbl; - index = bond_info->rx_hashtbl_head; + index = bond_info->rx_hashtbl_used_head; for (; index != RLB_NULL_INDEX; index = next_index) { - next_index = rx_hash_table[index].next; + next_index = rx_hash_table[index].used_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 (memcmp(rx_hash_table[index].mac_dst, - mac_bcast, ETH_ALEN)) { + if (!ether_addr_equal_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 @@ -464,24 +505,22 @@ static void rlb_clear_slave(struct bonding *bond, struct slave *slave) } } - _unlock_rx_hashtbl(bond); + _unlock_rx_hashtbl_bh(bond); - write_lock(&bond->curr_slave_lock); + write_lock_bh(&bond->curr_slave_lock); - if (slave != bond->curr_active_slave) { + if (slave != bond->curr_active_slave) rlb_teach_disabled_mac_on_primary(bond, slave->dev->dev_addr); - } - write_unlock(&bond->curr_slave_lock); + write_unlock_bh(&bond->curr_slave_lock); } static void rlb_update_client(struct rlb_client_info *client_info) { int i; - if (!client_info->slave) { + if (!client_info->slave) return; - } for (i = 0; i < RLB_ARP_BURST_SIZE; i++) { struct sk_buff *skb; @@ -494,20 +533,18 @@ static void rlb_update_client(struct rlb_client_info *client_info) client_info->slave->dev->dev_addr, client_info->mac_dst); if (!skb) { - printk(KERN_ERR DRV_NAME - ": %s: Error: failed to create an ARP packet\n", - client_info->slave->dev->master->name); + pr_err("%s: Error: failed to create an ARP packet\n", + client_info->slave->bond->dev->name); continue; } skb->dev = client_info->slave->dev; - if (client_info->tag) { - skb = vlan_put_tag(skb, client_info->vlan_id); + if (client_info->vlan_id) { + skb = vlan_put_tag(skb, htons(ETH_P_8021Q), client_info->vlan_id); if (!skb) { - printk(KERN_ERR DRV_NAME - ": %s: Error: failed to insert VLAN tag\n", - client_info->slave->dev->master->name); + pr_err("%s: Error: failed to insert VLAN tag\n", + client_info->slave->bond->dev->name); continue; } } @@ -523,25 +560,25 @@ static void rlb_update_rx_clients(struct bonding *bond) struct rlb_client_info *client_info; u32 hash_index; - _lock_rx_hashtbl(bond); + _lock_rx_hashtbl_bh(bond); - hash_index = bond_info->rx_hashtbl_head; - for (; hash_index != RLB_NULL_INDEX; hash_index = client_info->next) { + hash_index = bond_info->rx_hashtbl_used_head; + for (; hash_index != RLB_NULL_INDEX; + hash_index = client_info->used_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) { + if (bond_info->rlb_update_retry_counter == 0) client_info->ntt = 0; - } } } - /* do not update the entries again untill this counter is zero so that + /* 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(bond); + _unlock_rx_hashtbl_bh(bond); } /* The slave was assigned a new mac address - update the clients */ @@ -552,31 +589,32 @@ static void rlb_req_update_slave_clients(struct bonding *bond, struct slave *sla int ntt = 0; u32 hash_index; - _lock_rx_hashtbl(bond); + _lock_rx_hashtbl_bh(bond); - hash_index = bond_info->rx_hashtbl_head; - for (; hash_index != RLB_NULL_INDEX; hash_index = client_info->next) { + hash_index = bond_info->rx_hashtbl_used_head; + for (; hash_index != RLB_NULL_INDEX; + hash_index = client_info->used_next) { client_info = &(bond_info->rx_hashtbl[hash_index]); if ((client_info->slave == slave) && - memcmp(client_info->mac_dst, mac_bcast, ETH_ALEN)) { + !ether_addr_equal_64bits(client_info->mac_dst, mac_bcast)) { client_info->ntt = 1; ntt = 1; } } - // update the team's flag only after the whole iteration + /* update the team's flag only after the whole iteration */ if (ntt) { bond_info->rx_ntt = 1; - //fasten the change + /* fasten the change */ bond_info->rlb_update_retry_counter = RLB_UPDATE_RETRY; } - _unlock_rx_hashtbl(bond); + _unlock_rx_hashtbl_bh(bond); } /* mark all clients using src_ip to be updated */ -static void rlb_req_update_subnet_clients(struct bonding *bond, u32 src_ip) +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; @@ -584,14 +622,13 @@ static void rlb_req_update_subnet_clients(struct bonding *bond, u32 src_ip) _lock_rx_hashtbl(bond); - hash_index = bond_info->rx_hashtbl_head; - for (; hash_index != RLB_NULL_INDEX; hash_index = client_info->next) { + hash_index = bond_info->rx_hashtbl_used_head; + for (; hash_index != RLB_NULL_INDEX; + hash_index = client_info->used_next) { client_info = &(bond_info->rx_hashtbl[hash_index]); if (!client_info->slave) { - printk(KERN_ERR DRV_NAME - ": %s: Error: found a client with no channel in " - "the client's hash table\n", + pr_err("%s: Error: found a client with no channel in the client's hash table\n", bond->dev->name); continue; } @@ -600,9 +637,9 @@ static void rlb_req_update_subnet_clients(struct bonding *bond, u32 src_ip) * unicast mac address. */ if ((client_info->ip_src == src_ip) && - memcmp(client_info->slave->dev->dev_addr, - bond->dev->dev_addr, ETH_ALEN) && - memcmp(client_info->mac_dst, mac_bcast, ETH_ALEN)) { + !ether_addr_equal_64bits(client_info->slave->dev->dev_addr, + bond->dev->dev_addr) && + !ether_addr_equal_64bits(client_info->mac_dst, mac_bcast)) { client_info->ntt = 1; bond_info->rx_ntt = 1; } @@ -615,24 +652,27 @@ static void rlb_req_update_subnet_clients(struct bonding *bond, u32 src_ip) 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 = (struct arp_pkt *)skb->nh.raw; - struct slave *assigned_slave; + struct arp_pkt *arp = arp_pkt(skb); + struct slave *assigned_slave, *curr_active_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_src)); + curr_active_slave = rcu_dereference(bond->curr_active_slave); + + 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 (memcmp(arp->mac_dst, mac_bcast, ETH_ALEN)) { + if (!ether_addr_equal_64bits(arp->mac_dst, mac_bcast)) { /* update mac address from arp */ - memcpy(client_info->mac_dst, arp->mac_dst, ETH_ALEN); + ether_addr_copy(client_info->mac_dst, arp->mac_dst); } + ether_addr_copy(client_info->mac_src, arp->mac_src); assigned_slave = client_info->slave; if (assigned_slave) { @@ -645,47 +685,53 @@ static struct slave *rlb_choose_channel(struct sk_buff *skb, struct bonding *bon * 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; + client_info->slave != curr_active_slave) { + client_info->slave = curr_active_slave; rlb_update_client(client_info); } } } /* assign a new slave */ - assigned_slave = rlb_next_rx_slave(bond); + assigned_slave = __rlb_next_rx_slave(bond); if (assigned_slave) { + if (!(client_info->assigned && + client_info->ip_src == arp->ip_src)) { + /* ip_src is going to be updated, + * fix the src hash list + */ + u32 hash_src = _simple_hash((u8 *)&arp->ip_src, + sizeof(arp->ip_src)); + rlb_src_unlink(bond, hash_index); + rlb_src_link(bond, hash_src, hash_index); + } + 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); + ether_addr_copy(client_info->mac_dst, arp->mac_dst); + ether_addr_copy(client_info->mac_src, arp->mac_src); client_info->slave = assigned_slave; - if (memcmp(client_info->mac_dst, mac_bcast, ETH_ALEN)) { + if (!ether_addr_equal_64bits(client_info->mac_dst, mac_bcast)) { client_info->ntt = 1; bond->alb_info.rx_ntt = 1; } else { client_info->ntt = 0; } - if (!list_empty(&bond->vlan_list)) { - unsigned short vlan_id; - int res = vlan_get_tag(skb, &vlan_id); - if (!res) { - client_info->tag = 1; - client_info->vlan_id = vlan_id; - } - } + if (vlan_get_tag(skb, &client_info->vlan_id)) + client_info->vlan_id = 0; 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; + u32 prev_tbl_head = bond_info->rx_hashtbl_used_head; + bond_info->rx_hashtbl_used_head = hash_index; + client_info->used_next = prev_tbl_head; if (prev_tbl_head != RLB_NULL_INDEX) { - bond_info->rx_hashtbl[prev_tbl_head].prev = + bond_info->rx_hashtbl[prev_tbl_head].used_prev = hash_index; } client_info->assigned = 1; @@ -703,19 +749,24 @@ static struct slave *rlb_choose_channel(struct sk_buff *skb, struct bonding *bon */ static struct slave *rlb_arp_xmit(struct sk_buff *skb, struct bonding *bond) { - struct arp_pkt *arp = (struct arp_pkt *)skb->nh.raw; + struct arp_pkt *arp = arp_pkt(skb); struct slave *tx_slave = NULL; - if (arp->op_code == __constant_htons(ARPOP_REPLY)) { + /* Don't modify or load balance ARPs that do not originate locally + * (e.g.,arrive via a bridge). + */ + if (!bond_slave_has_mac_rx(bond, arp->mac_src)) + return 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); - } - dprintk("Server sent ARP Reply packet\n"); - } else if (arp->op_code == __constant_htons(ARPOP_REQUEST)) { + if (tx_slave) + ether_addr_copy(arp->mac_src, tx_slave->dev->dev_addr); + 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 @@ -723,7 +774,7 @@ static struct slave *rlb_arp_xmit(struct sk_buff *skb, struct bonding *bond) */ rlb_choose_channel(skb, bond); - /* The ARP relpy packets must be delayed so that + /* 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; @@ -734,7 +785,7 @@ static struct slave *rlb_arp_xmit(struct sk_buff *skb, struct bonding *bond) * updated with their assigned mac. */ rlb_req_update_subnet_clients(bond, arp->ip_src); - dprintk("Server sent ARP Request packet\n"); + pr_debug("Server sent ARP Request packet\n"); } return tx_slave; @@ -749,13 +800,14 @@ static void rlb_rebalance(struct bonding *bond) int ntt; u32 hash_index; - _lock_rx_hashtbl(bond); + _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) { + hash_index = bond_info->rx_hashtbl_used_head; + for (; hash_index != RLB_NULL_INDEX; + hash_index = client_info->used_next) { client_info = &(bond_info->rx_hashtbl[hash_index]); - assigned_slave = rlb_next_rx_slave(bond); + assigned_slave = __rlb_next_rx_slave(bond); if (assigned_slave && (client_info->slave != assigned_slave)) { client_info->slave = assigned_slave; client_info->ntt = 1; @@ -764,56 +816,145 @@ static void rlb_rebalance(struct bonding *bond) } /* update the team's flag only after the whole iteration */ - if (ntt) { + if (ntt) bond_info->rx_ntt = 1; - } - _unlock_rx_hashtbl(bond); + _unlock_rx_hashtbl_bh(bond); } /* Caller must hold rx_hashtbl lock */ +static void rlb_init_table_entry_dst(struct rlb_client_info *entry) +{ + entry->used_next = RLB_NULL_INDEX; + entry->used_prev = RLB_NULL_INDEX; + entry->assigned = 0; + entry->slave = NULL; + entry->vlan_id = 0; +} +static void rlb_init_table_entry_src(struct rlb_client_info *entry) +{ + entry->src_first = RLB_NULL_INDEX; + entry->src_prev = RLB_NULL_INDEX; + entry->src_next = RLB_NULL_INDEX; +} + 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; + rlb_init_table_entry_dst(entry); + rlb_init_table_entry_src(entry); +} + +static void rlb_delete_table_entry_dst(struct bonding *bond, u32 index) +{ + struct alb_bond_info *bond_info = &(BOND_ALB_INFO(bond)); + u32 next_index = bond_info->rx_hashtbl[index].used_next; + u32 prev_index = bond_info->rx_hashtbl[index].used_prev; + + if (index == bond_info->rx_hashtbl_used_head) + bond_info->rx_hashtbl_used_head = next_index; + if (prev_index != RLB_NULL_INDEX) + bond_info->rx_hashtbl[prev_index].used_next = next_index; + if (next_index != RLB_NULL_INDEX) + bond_info->rx_hashtbl[next_index].used_prev = prev_index; +} + +/* unlink a rlb hash table entry from the src list */ +static void rlb_src_unlink(struct bonding *bond, u32 index) +{ + struct alb_bond_info *bond_info = &(BOND_ALB_INFO(bond)); + u32 next_index = bond_info->rx_hashtbl[index].src_next; + u32 prev_index = bond_info->rx_hashtbl[index].src_prev; + + bond_info->rx_hashtbl[index].src_next = RLB_NULL_INDEX; + bond_info->rx_hashtbl[index].src_prev = RLB_NULL_INDEX; + + if (next_index != RLB_NULL_INDEX) + bond_info->rx_hashtbl[next_index].src_prev = prev_index; + + if (prev_index == RLB_NULL_INDEX) + return; + + /* is prev_index pointing to the head of this list? */ + if (bond_info->rx_hashtbl[prev_index].src_first == index) + bond_info->rx_hashtbl[prev_index].src_first = next_index; + else + bond_info->rx_hashtbl[prev_index].src_next = next_index; + +} + +static void rlb_delete_table_entry(struct bonding *bond, u32 index) +{ + struct alb_bond_info *bond_info = &(BOND_ALB_INFO(bond)); + struct rlb_client_info *entry = &(bond_info->rx_hashtbl[index]); + + rlb_delete_table_entry_dst(bond, index); + rlb_init_table_entry_dst(entry); + + rlb_src_unlink(bond, index); +} + +/* add the rx_hashtbl[ip_dst_hash] entry to the list + * of entries with identical ip_src_hash + */ +static void rlb_src_link(struct bonding *bond, u32 ip_src_hash, u32 ip_dst_hash) +{ + struct alb_bond_info *bond_info = &(BOND_ALB_INFO(bond)); + u32 next; + + bond_info->rx_hashtbl[ip_dst_hash].src_prev = ip_src_hash; + next = bond_info->rx_hashtbl[ip_src_hash].src_first; + bond_info->rx_hashtbl[ip_dst_hash].src_next = next; + if (next != RLB_NULL_INDEX) + bond_info->rx_hashtbl[next].src_prev = ip_dst_hash; + bond_info->rx_hashtbl[ip_src_hash].src_first = ip_dst_hash; +} + +/* deletes all rx_hashtbl entries with arp->ip_src if their mac_src does + * not match arp->mac_src */ +static void rlb_purge_src_ip(struct bonding *bond, struct arp_pkt *arp) +{ + struct alb_bond_info *bond_info = &(BOND_ALB_INFO(bond)); + u32 ip_src_hash = _simple_hash((u8 *)&(arp->ip_src), sizeof(arp->ip_src)); + u32 index; + + _lock_rx_hashtbl_bh(bond); + + index = bond_info->rx_hashtbl[ip_src_hash].src_first; + while (index != RLB_NULL_INDEX) { + struct rlb_client_info *entry = &(bond_info->rx_hashtbl[index]); + u32 next_index = entry->src_next; + if (entry->ip_src == arp->ip_src && + !ether_addr_equal_64bits(arp->mac_src, entry->mac_src)) + rlb_delete_table_entry(bond, index); + index = next_index; + } + _unlock_rx_hashtbl_bh(bond); } static int rlb_initialize(struct bonding *bond) { struct alb_bond_info *bond_info = &(BOND_ALB_INFO(bond)); - struct packet_type *pk_type = &(BOND_ALB_INFO(bond).rlb_pkt_type); struct rlb_client_info *new_hashtbl; int size = RLB_HASH_TABLE_SIZE * sizeof(struct rlb_client_info); int i; - spin_lock_init(&(bond_info->rx_hashtbl_lock)); - new_hashtbl = kmalloc(size, GFP_KERNEL); - if (!new_hashtbl) { - printk(KERN_ERR DRV_NAME - ": %s: Error: Failed to allocate RLB hash table\n", - bond->dev->name); + if (!new_hashtbl) return -1; - } - _lock_rx_hashtbl(bond); + + _lock_rx_hashtbl_bh(bond); bond_info->rx_hashtbl = new_hashtbl; - bond_info->rx_hashtbl_head = RLB_NULL_INDEX; + bond_info->rx_hashtbl_used_head = RLB_NULL_INDEX; - for (i = 0; i < RLB_HASH_TABLE_SIZE; i++) { + for (i = 0; i < RLB_HASH_TABLE_SIZE; i++) rlb_init_table_entry(bond_info->rx_hashtbl + i); - } - - _unlock_rx_hashtbl(bond); - /*initialize packet type*/ - pk_type->type = __constant_htons(ETH_P_ARP); - pk_type->dev = bond->dev; - pk_type->func = rlb_arp_recv; + _unlock_rx_hashtbl_bh(bond); /* register to receive ARPs */ - dev_add_pack(pk_type); + bond->recv_probe = rlb_arp_recv; return 0; } @@ -822,15 +963,13 @@ static void rlb_deinitialize(struct bonding *bond) { struct alb_bond_info *bond_info = &(BOND_ALB_INFO(bond)); - dev_remove_pack(&(bond_info->rlb_pkt_type)); - - _lock_rx_hashtbl(bond); + _lock_rx_hashtbl_bh(bond); kfree(bond_info->rx_hashtbl); bond_info->rx_hashtbl = NULL; - bond_info->rx_hashtbl_head = RLB_NULL_INDEX; + bond_info->rx_hashtbl_used_head = RLB_NULL_INDEX; - _unlock_rx_hashtbl(bond); + _unlock_rx_hashtbl_bh(bond); } static void rlb_clear_vlan(struct bonding *bond, unsigned short vlan_id) @@ -838,101 +977,111 @@ 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(bond); + _lock_rx_hashtbl_bh(bond); - curr_index = bond_info->rx_hashtbl_head; + curr_index = bond_info->rx_hashtbl_used_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; - } + u32 next_index = bond_info->rx_hashtbl[curr_index].used_next; - rlb_init_table_entry(curr); - } + if (curr->vlan_id == vlan_id) + rlb_delete_table_entry(bond, curr_index); curr_index = next_index; } - _unlock_rx_hashtbl(bond); + _unlock_rx_hashtbl_bh(bond); } /*********************** tlb/rlb shared functions *********************/ -static void alb_send_learning_packets(struct slave *slave, u8 mac_addr[]) +static void alb_send_lp_vid(struct slave *slave, u8 mac_addr[], + __be16 vlan_proto, u16 vid) { - struct bonding *bond = bond_get_bond_by_slave(slave); struct learning_pkt pkt; + struct sk_buff *skb; int size = sizeof(struct learning_pkt); - int i; + char *data; memset(&pkt, 0, size); - memcpy(pkt.mac_dst, mac_addr, ETH_ALEN); - memcpy(pkt.mac_src, mac_addr, ETH_ALEN); - pkt.type = __constant_htons(ETH_P_LOOP); + ether_addr_copy(pkt.mac_dst, mac_addr); + ether_addr_copy(pkt.mac_src, mac_addr); + pkt.type = cpu_to_be16(ETH_P_LOOPBACK); - for (i = 0; i < MAX_LP_BURST; i++) { - struct sk_buff *skb; - char *data; + skb = dev_alloc_skb(size); + if (!skb) + return; - skb = dev_alloc_skb(size); + 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 (vid) { + skb = vlan_put_tag(skb, vlan_proto, vid); if (!skb) { + pr_err("%s: Error: failed to insert VLAN tag\n", + slave->bond->dev->name); return; } + } - data = skb_put(skb, size); - memcpy(data, &pkt, size); - - skb->mac.raw = data; - skb->nh.raw = data + ETH_HLEN; - skb->protocol = pkt.type; - skb->priority = TC_PRIO_CONTROL; - skb->dev = slave->dev; + dev_queue_xmit(skb); +} - if (!list_empty(&bond->vlan_list)) { - struct vlan_entry *vlan; +static void alb_send_learning_packets(struct slave *slave, u8 mac_addr[], + bool strict_match) +{ + struct bonding *bond = bond_get_bond_by_slave(slave); + struct net_device *upper; + struct list_head *iter; + struct bond_vlan_tag tags[BOND_MAX_VLAN_ENCAP]; - vlan = bond_next_vlan(bond, - bond->alb_info.current_alb_vlan); + /* send untagged */ + alb_send_lp_vid(slave, mac_addr, 0, 0); - bond->alb_info.current_alb_vlan = vlan; - if (!vlan) { - kfree_skb(skb); - continue; - } - - skb = vlan_put_tag(skb, vlan->vlan_id); - if (!skb) { - printk(KERN_ERR DRV_NAME - ": %s: Error: failed to insert VLAN tag\n", - bond->dev->name); - continue; + /* loop through all devices and see if we need to send a packet + * for that device. + */ + rcu_read_lock(); + netdev_for_each_all_upper_dev_rcu(bond->dev, upper, iter) { + if (is_vlan_dev(upper) && vlan_get_encap_level(upper) == 0) { + if (strict_match && + ether_addr_equal_64bits(mac_addr, + upper->dev_addr)) { + alb_send_lp_vid(slave, mac_addr, + vlan_dev_vlan_proto(upper), + vlan_dev_vlan_id(upper)); + } else if (!strict_match) { + alb_send_lp_vid(slave, upper->dev_addr, + vlan_dev_vlan_proto(upper), + vlan_dev_vlan_id(upper)); } } - dev_queue_xmit(skb); + /* If this is a macvlan device, then only send updates + * when strict_match is turned off. + */ + if (netif_is_macvlan(upper) && !strict_match) { + memset(tags, 0, sizeof(tags)); + bond_verify_device_path(bond->dev, upper, tags); + alb_send_lp_vid(slave, upper->dev_addr, + tags[0].vlan_proto, tags[0].vlan_id); + } } + rcu_read_unlock(); } -/* hw is a boolean parameter that determines whether we should try and - * set the hw address of the device as well as the hw address of the - * net_device - */ -static int alb_set_slave_mac_addr(struct slave *slave, u8 addr[], int hw) +static int alb_set_slave_mac_addr(struct slave *slave, u8 addr[]) { struct net_device *dev = slave->dev; struct sockaddr s_addr; - if (!hw) { + if (BOND_MODE(slave->bond) == BOND_MODE_TLB) { memcpy(dev->dev_addr, addr, dev->addr_len); return 0; } @@ -942,33 +1091,47 @@ static int alb_set_slave_mac_addr(struct slave *slave, u8 addr[], int hw) memcpy(s_addr.sa_data, addr, dev->addr_len); s_addr.sa_family = dev->type; if (dev_set_mac_address(dev, &s_addr)) { - printk(KERN_ERR DRV_NAME - ": %s: Error: dev_set_mac_address of dev %s failed! 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); + 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", + slave->bond->dev->name, dev->name); return -EOPNOTSUPP; } return 0; } -/* Caller must hold bond lock for write or curr_slave_lock for write*/ -static void alb_swap_mac_addr(struct bonding *bond, struct slave *slave1, struct slave *slave2) +/* + * Swap MAC addresses between two slaves. + * + * Called with RTNL held, and no other locks. + * + */ + +static void alb_swap_mac_addr(struct slave *slave1, struct slave *slave2) { - struct slave *disabled_slave = NULL; u8 tmp_mac_addr[ETH_ALEN]; - int slaves_state_differ; - slaves_state_differ = (SLAVE_IS_OK(slave1) != SLAVE_IS_OK(slave2)); + ether_addr_copy(tmp_mac_addr, slave1->dev->dev_addr); + alb_set_slave_mac_addr(slave1, slave2->dev->dev_addr); + alb_set_slave_mac_addr(slave2, tmp_mac_addr); - memcpy(tmp_mac_addr, slave1->dev->dev_addr, ETH_ALEN); - alb_set_slave_mac_addr(slave1, slave2->dev->dev_addr, bond->alb_info.rlb_enabled); - alb_set_slave_mac_addr(slave2, tmp_mac_addr, bond->alb_info.rlb_enabled); +} + +/* + * 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 = (bond_slave_can_tx(slave1) != bond_slave_can_tx(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_slave_can_tx(slave1)) { + alb_send_learning_packets(slave1, slave1->dev->dev_addr, false); if (bond->alb_info.rlb_enabled) { /* inform the clients that the mac address * has changed @@ -979,8 +1142,8 @@ static void alb_swap_mac_addr(struct bonding *bond, struct slave *slave1, struct disabled_slave = slave1; } - if (SLAVE_IS_OK(slave2)) { - alb_send_learning_packets(slave2, slave2->dev->dev_addr); + if (bond_slave_can_tx(slave2)) { + alb_send_learning_packets(slave2, slave2->dev->dev_addr, false); if (bond->alb_info.rlb_enabled) { /* inform the clients that the mac address * has changed @@ -1010,35 +1173,26 @@ static void alb_swap_mac_addr(struct bonding *bond, struct slave *slave1, struct * 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 bond lock + * 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; + struct slave *found_slave; - perm_curr_diff = memcmp(slave->perm_hwaddr, - slave->dev->dev_addr, - ETH_ALEN); - perm_bond_diff = memcmp(slave->perm_hwaddr, - bond->dev->dev_addr, - ETH_ALEN); + perm_curr_diff = !ether_addr_equal_64bits(slave->perm_hwaddr, + slave->dev->dev_addr); + perm_bond_diff = !ether_addr_equal_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 (!memcmp(slave->perm_hwaddr, - tmp_slave->dev->dev_addr, - ETH_ALEN)) { - found = 1; - break; - } - } + found_slave = bond_slave_has_mac(bond, slave->perm_hwaddr); - if (found) { - alb_swap_mac_addr(bond, slave, tmp_slave); + if (found_slave) { + /* locking: needs RTNL and nothing else */ + alb_swap_mac_addr(slave, found_slave); + alb_fasten_mac_swap(bond, slave, found_slave); } } } @@ -1053,7 +1207,7 @@ static void alb_change_hw_addr_on_detach(struct bonding *bond, struct slave *sla * * 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 premanent + * 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 @@ -1063,18 +1217,15 @@ static void alb_change_hw_addr_on_detach(struct bonding *bond, struct slave *sla * @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. + * bond slave list. */ 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; + struct slave *tmp_slave1, *free_mac_slave = NULL; + struct list_head *iter; - if (bond->slave_cnt == 0) { + if (!bond_has_slaves(bond)) { /* this is the first slave */ return 0; } @@ -1083,41 +1234,20 @@ static int alb_handle_addr_collision_on_attach(struct bonding *bond, struct slav * check uniqueness of slave's mac address against the other * slaves in the bond. */ - if (memcmp(slave->perm_hwaddr, bond->dev->dev_addr, ETH_ALEN)) { - bond_for_each_slave(bond, tmp_slave1, i) { - if (!memcmp(tmp_slave1->dev->dev_addr, slave->dev->dev_addr, - ETH_ALEN)) { - found = 1; - break; - } - } - - if (!found) + if (!ether_addr_equal_64bits(slave->perm_hwaddr, bond->dev->dev_addr)) { + if (!bond_slave_has_mac(bond, slave->dev->dev_addr)) 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, - bond->alb_info.rlb_enabled); + 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 (!memcmp(tmp_slave1->perm_hwaddr, - tmp_slave2->dev->dev_addr, - ETH_ALEN)) { - found = 1; - break; - } - } - - if (!found) { + bond_for_each_slave(bond, tmp_slave1, iter) { + if (!bond_slave_has_mac(bond, tmp_slave1->perm_hwaddr)) { /* no slave has tmp_slave1's perm addr * as its curr addr */ @@ -1126,9 +1256,8 @@ static int alb_handle_addr_collision_on_attach(struct bonding *bond, struct slav } if (!has_bond_addr) { - if (!memcmp(tmp_slave1->dev->dev_addr, - bond->dev->dev_addr, - ETH_ALEN)) { + if (ether_addr_equal_64bits(tmp_slave1->dev->dev_addr, + bond->dev->dev_addr)) { has_bond_addr = tmp_slave1; } @@ -1136,19 +1265,14 @@ static int alb_handle_addr_collision_on_attach(struct bonding *bond, struct slav } if (free_mac_slave) { - alb_set_slave_mac_addr(slave, free_mac_slave->perm_hwaddr, - bond->alb_info.rlb_enabled); + alb_set_slave_mac_addr(slave, free_mac_slave->perm_hwaddr); - printk(KERN_WARNING DRV_NAME - ": %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); + pr_warn("%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) { - printk(KERN_ERR DRV_NAME - ": %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", + 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; } @@ -1172,33 +1296,26 @@ static int alb_handle_addr_collision_on_attach(struct bonding *bond, struct slav */ static int alb_set_mac_address(struct bonding *bond, void *addr) { + struct slave *slave, *rollback_slave; + struct list_head *iter; struct sockaddr sa; - struct slave *slave, *stop_at; char tmp_addr[ETH_ALEN]; int res; - int i; - if (bond->alb_info.rlb_enabled) { + if (bond->alb_info.rlb_enabled) return 0; - } - - bond_for_each_slave(bond, slave, i) { - if (slave->dev->set_mac_address == NULL) { - res = -EOPNOTSUPP; - goto unwind; - } + bond_for_each_slave(bond, slave, iter) { /* save net_device's current hw address */ - memcpy(tmp_addr, slave->dev->dev_addr, ETH_ALEN); + ether_addr_copy(tmp_addr, slave->dev->dev_addr); res = dev_set_mac_address(slave->dev, addr); /* restore net_device's hw address */ - memcpy(slave->dev->dev_addr, tmp_addr, ETH_ALEN); + ether_addr_copy(slave->dev->dev_addr, tmp_addr); - if (res) { + if (res) goto unwind; - } } return 0; @@ -1208,11 +1325,12 @@ unwind: 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); + bond_for_each_slave(bond, rollback_slave, iter) { + if (rollback_slave == slave) + break; + ether_addr_copy(tmp_addr, rollback_slave->dev->dev_addr); + dev_set_mac_address(rollback_slave->dev, &sa); + ether_addr_copy(rollback_slave->dev->dev_addr, tmp_addr); } return res; @@ -1225,9 +1343,8 @@ int bond_alb_initialize(struct bonding *bond, int rlb_enabled) int res; res = tlb_initialize(bond); - if (res) { + if (res) return res; - } if (rlb_enabled) { bond->alb_info.rlb_enabled = 1; @@ -1250,62 +1367,145 @@ void bond_alb_deinitialize(struct bonding *bond) tlb_deinitialize(bond); - if (bond_info->rlb_enabled) { + if (bond_info->rlb_enabled) rlb_deinitialize(bond); +} + +static int bond_do_alb_xmit(struct sk_buff *skb, struct bonding *bond, + struct slave *tx_slave) +{ + struct alb_bond_info *bond_info = &(BOND_ALB_INFO(bond)); + struct ethhdr *eth_data = eth_hdr(skb); + + if (!tx_slave) { + /* unbalanced or unassigned, send through primary */ + tx_slave = rcu_dereference(bond->curr_active_slave); + if (bond->params.tlb_dynamic_lb) + bond_info->unbalanced_load += skb->len; + } + + if (tx_slave && bond_slave_can_tx(tx_slave)) { + if (tx_slave != rcu_dereference(bond->curr_active_slave)) { + ether_addr_copy(eth_data->h_source, + tx_slave->dev->dev_addr); + } + + bond_dev_queue_xmit(bond, skb, tx_slave->dev); + goto out; } + + if (tx_slave && bond->params.tlb_dynamic_lb) { + _lock_tx_hashtbl(bond); + __tlb_clear_slave(bond, tx_slave, 0); + _unlock_tx_hashtbl(bond); + } + + /* no suitable interface, frame not sent */ + dev_kfree_skb_any(skb); +out: + return NETDEV_TX_OK; +} + +int bond_tlb_xmit(struct sk_buff *skb, struct net_device *bond_dev) +{ + struct bonding *bond = netdev_priv(bond_dev); + struct ethhdr *eth_data; + struct slave *tx_slave = NULL; + u32 hash_index; + + skb_reset_mac_header(skb); + eth_data = eth_hdr(skb); + + /* Do not TX balance any multicast or broadcast */ + if (!is_multicast_ether_addr(eth_data->h_dest)) { + switch (skb->protocol) { + case htons(ETH_P_IP): + case htons(ETH_P_IPX): + /* In case of IPX, it will falback to L2 hash */ + case htons(ETH_P_IPV6): + hash_index = bond_xmit_hash(bond, skb); + if (bond->params.tlb_dynamic_lb) { + tx_slave = tlb_choose_channel(bond, + hash_index & 0xFF, + skb->len); + } else { + struct list_head *iter; + int idx = hash_index % bond->slave_cnt; + + bond_for_each_slave_rcu(bond, tx_slave, iter) + if (--idx < 0) + break; + } + break; + } + } + return bond_do_alb_xmit(skb, bond, tx_slave); } int bond_alb_xmit(struct sk_buff *skb, struct net_device *bond_dev) { - struct bonding *bond = bond_dev->priv; + 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 u32 ip_bcast = 0xffffffff; + static const __be32 ip_bcast = htonl(0xffffffff); int hash_size = 0; - int do_tx_balance = 1; + bool do_tx_balance = true; u32 hash_index = 0; - u8 *hash_start = NULL; - int res = 1; + const u8 *hash_start = NULL; + struct ipv6hdr *ip6hdr; - skb->mac.raw = (unsigned char *)skb->data; + skb_reset_mac_header(skb); eth_data = eth_hdr(skb); - /* make sure that the curr_active_slave and the slaves list do - * not change during tx - */ - read_lock(&bond->lock); - read_lock(&bond->curr_slave_lock); - - if (!BOND_IS_OK(bond)) { - goto out; - } - switch (ntohs(skb->protocol)) { - case ETH_P_IP: - if ((memcmp(eth_data->h_dest, mac_bcast, ETH_ALEN) == 0) || - (skb->nh.iph->daddr == ip_bcast) || - (skb->nh.iph->protocol == IPPROTO_IGMP)) { - do_tx_balance = 0; + case ETH_P_IP: { + const struct iphdr *iph = ip_hdr(skb); + + if (ether_addr_equal_64bits(eth_data->h_dest, mac_bcast) || + (iph->daddr == ip_bcast) || + (iph->protocol == IPPROTO_IGMP)) { + do_tx_balance = false; break; } - hash_start = (char*)&(skb->nh.iph->daddr); - hash_size = sizeof(skb->nh.iph->daddr); + hash_start = (char *)&(iph->daddr); + hash_size = sizeof(iph->daddr); + } break; case ETH_P_IPV6: - if (memcmp(eth_data->h_dest, mac_bcast, ETH_ALEN) == 0) { - do_tx_balance = 0; + /* IPv6 doesn't really use broadcast mac address, but leave + * that here just in case. + */ + if (ether_addr_equal_64bits(eth_data->h_dest, mac_bcast)) { + do_tx_balance = false; + break; + } + + /* IPv6 uses all-nodes multicast as an equivalent to + * broadcasts in IPv4. + */ + if (ether_addr_equal_64bits(eth_data->h_dest, mac_v6_allmcast)) { + do_tx_balance = false; break; } - hash_start = (char*)&(skb->nh.ipv6h->daddr); - hash_size = sizeof(skb->nh.ipv6h->daddr); + /* 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 = false; + 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 != - __constant_htons(IPX_NO_CHECKSUM)) { + if (ipx_hdr(skb)->ipx_checksum != IPX_NO_CHECKSUM) { /* something is wrong with this packet */ - do_tx_balance = 0; + do_tx_balance = false; break; } @@ -1314,21 +1514,20 @@ int bond_alb_xmit(struct sk_buff *skb, struct net_device *bond_dev) * this family since it has an "ARP" like * mechanism */ - do_tx_balance = 0; + do_tx_balance = false; break; } - hash_start = (char*)eth_data->h_dest; + 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) { + do_tx_balance = false; + if (bond_info->rlb_enabled) tx_slave = rlb_arp_xmit(skb, bond); - } break; default: - do_tx_balance = 0; + do_tx_balance = false; break; } @@ -1337,59 +1536,32 @@ int bond_alb_xmit(struct sk_buff *skb, struct net_device *bond_dev) 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) { - tlb_clear_slave(bond, tx_slave, 0); - } - } - -out: - if (res) { - /* no suitable interface, frame not sent */ - dev_kfree_skb(skb); - } - read_unlock(&bond->curr_slave_lock); - read_unlock(&bond->lock); - return 0; + return bond_do_alb_xmit(skb, bond, tx_slave); } -void bond_alb_monitor(struct bonding *bond) +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 list_head *iter; struct slave *slave; - int i; - - read_lock(&bond->lock); - - if (bond->kill_timers) { - goto out; - } - if (bond->slave_cnt == 0) { + if (!bond_has_slaves(bond)) { bond_info->tx_rebalance_counter = 0; bond_info->lp_counter = 0; goto re_arm; } + rcu_read_lock(); + bond_info->tx_rebalance_counter++; bond_info->lp_counter++; /* send learning packets */ - if (bond_info->lp_counter >= BOND_ALB_LP_TICKS) { + if (bond_info->lp_counter >= BOND_ALB_LP_TICKS(bond)) { + bool strict_match; + /* 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 @@ -1397,8 +1569,16 @@ void bond_alb_monitor(struct bonding *bond) */ read_lock(&bond->curr_slave_lock); - bond_for_each_slave(bond, slave, i) { - alb_send_learning_packets(slave, slave->dev->dev_addr); + bond_for_each_slave_rcu(bond, slave, iter) { + /* If updating current_active, use all currently + * user mac addreses (!strict_match). Otherwise, only + * use mac of the slave device. + * In RLB mode, we always use strict matches. + */ + strict_match = (slave != bond->curr_active_slave || + bond_info->rlb_enabled); + alb_send_learning_packets(slave, slave->dev->dev_addr, + strict_match); } read_unlock(&bond->curr_slave_lock); @@ -1411,7 +1591,7 @@ void bond_alb_monitor(struct bonding *bond) read_lock(&bond->curr_slave_lock); - bond_for_each_slave(bond, slave, i) { + bond_for_each_slave_rcu(bond, slave, iter) { tlb_clear_slave(bond, slave, 1); if (slave == bond->curr_active_slave) { SLAVE_TLB_INFO(slave).load = @@ -1428,16 +1608,17 @@ void bond_alb_monitor(struct bonding *bond) /* handle rlb stuff */ if (bond_info->rlb_enabled) { - /* the following code changes the promiscuity of the - * the curr_active_slave. It needs to be locked with a - * write lock to protect from other code that also - * sets the promiscuity. - */ - write_lock(&bond->curr_slave_lock); - 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. + */ + rcu_read_unlock(); + if (!rtnl_trylock()) + goto re_arm; + bond_info->rlb_promisc_timeout_counter = 0; /* If the primary was set to promiscuous mode @@ -1446,9 +1627,10 @@ void bond_alb_monitor(struct bonding *bond) */ dev_set_promiscuity(bond->curr_active_slave->dev, -1); bond_info->primary_is_promisc = 0; - } - write_unlock(&bond->curr_slave_lock); + rtnl_unlock(); + rcu_read_lock(); + } if (bond_info->rlb_rebalance) { bond_info->rlb_rebalance = 0; @@ -1461,19 +1643,16 @@ void bond_alb_monitor(struct bonding *bond) --bond_info->rlb_update_delay_counter; } else { rlb_update_rx_clients(bond); - if (bond_info->rlb_update_retry_counter) { + if (bond_info->rlb_update_retry_counter) --bond_info->rlb_update_retry_counter; - } else { + else bond_info->rx_ntt = 0; - } } } } - + rcu_read_unlock(); re_arm: - mod_timer(&(bond_info->alb_timer), jiffies + alb_delta_in_ticks); -out: - read_unlock(&bond->lock); + queue_delayed_work(bond->wq, &bond->alb_work, alb_delta_in_ticks); } /* assumption: called before the slave is attached to the bond @@ -1483,48 +1662,40 @@ int bond_alb_init_slave(struct bonding *bond, struct slave *slave) { int res; - res = alb_set_slave_mac_addr(slave, slave->perm_hwaddr, - bond->alb_info.rlb_enabled); - if (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. - */ - write_lock_bh(&bond->lock); res = alb_handle_addr_collision_on_attach(bond, slave); - - write_unlock_bh(&bond->lock); - - if (res) { + 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) { + if (bond->alb_info.rlb_enabled) bond->alb_info.rlb_rebalance = 1; - } return 0; } -/* Caller must hold bond lock for write */ +/* + * 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) { + if (bond_has_slaves(bond)) 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; + bond->alb_info.rx_slave = NULL; rlb_clear_slave(bond, slave); } } @@ -1536,9 +1707,8 @@ void bond_alb_handle_link_change(struct bonding *bond, struct slave *slave, char if (link == BOND_LINK_DOWN) { tlb_clear_slave(bond, slave, 0); - if (bond->alb_info.rlb_enabled) { + 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; @@ -1561,16 +1731,20 @@ void bond_alb_handle_link_change(struct bonding *bond, struct slave *slave, char * Set the bond->curr_active_slave to @new_slave and handle * mac address swapping and promiscuity changes as needed. * - * Caller must hold bond curr_slave_lock for write (or bond lock for write) + * 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, 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) + __acquires(&bond->curr_slave_lock) { struct slave *swap_slave; - int i; - if (bond->curr_active_slave == new_slave) { + 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); @@ -1579,56 +1753,80 @@ void bond_alb_handle_active_change(struct bonding *bond, struct slave *new_slave } swap_slave = bond->curr_active_slave; - bond->curr_active_slave = new_slave; + rcu_assign_pointer(bond->curr_active_slave, new_slave); - if (!new_slave || (bond->slave_cnt == 0)) { + if (!new_slave || !bond_has_slaves(bond)) 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 (!memcmp(tmp_slave->dev->dev_addr, - bond->dev->dev_addr, ETH_ALEN)) { - swap_slave = tmp_slave; - break; - } - } + if (!swap_slave) + swap_slave = bond_slave_has_mac(bond, bond->dev->dev_addr); + + /* + * 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); + + ASSERT_RTNL(); + + /* in TLB mode, the slave might flip down/up with the old dev_addr, + * and thus filter bond->dev_addr's packets, so force bond's mac + */ + if (BOND_MODE(bond) == BOND_MODE_TLB) { + struct sockaddr sa; + u8 tmp_addr[ETH_ALEN]; + + ether_addr_copy(tmp_addr, new_slave->dev->dev_addr); + + memcpy(sa.sa_data, bond->dev->dev_addr, bond->dev->addr_len); + sa.sa_family = bond->dev->type; + /* we don't care if it can't change its mac, best effort */ + dev_set_mac_address(new_slave->dev, &sa); + + ether_addr_copy(new_slave->dev->dev_addr, tmp_addr); } /* 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); + alb_swap_mac_addr(swap_slave, new_slave); + alb_fasten_mac_swap(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, - bond->alb_info.rlb_enabled); - /* fasten bond mac on new current slave */ - alb_send_learning_packets(new_slave, bond->dev->dev_addr); + alb_set_slave_mac_addr(new_slave, bond->dev->dev_addr); + alb_send_learning_packets(new_slave, bond->dev->dev_addr, + false); } + + 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 = bond_dev->priv; + struct bonding *bond = netdev_priv(bond_dev); struct sockaddr *sa = addr; - struct slave *slave, *swap_slave; + struct slave *swap_slave; int res; - int i; - if (!is_valid_ether_addr(sa->sa_data)) { + if (!is_valid_ether_addr(sa->sa_data)) return -EADDRNOTAVAIL; - } res = alb_set_mac_address(bond, addr); - if (res) { + if (res) return res; - } memcpy(bond_dev->dev_addr, sa->sa_data, bond_dev->addr_len); @@ -1636,30 +1834,25 @@ int bond_alb_set_mac_address(struct net_device *bond_dev, void *addr) * Otherwise we'll need to pass the new address to it and handle * duplications. */ - if (!bond->curr_active_slave) { + if (!bond->curr_active_slave) return 0; - } - swap_slave = NULL; - - bond_for_each_slave(bond, slave, i) { - if (!memcmp(slave->dev->dev_addr, bond_dev->dev_addr, ETH_ALEN)) { - swap_slave = slave; - break; - } - } + swap_slave = bond_slave_has_mac(bond, bond_dev->dev_addr); if (swap_slave) { - alb_swap_mac_addr(bond, swap_slave, bond->curr_active_slave); + alb_swap_mac_addr(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, - bond->alb_info.rlb_enabled); + alb_set_slave_mac_addr(bond->curr_active_slave, bond_dev->dev_addr); - alb_send_learning_packets(bond->curr_active_slave, bond_dev->dev_addr); + read_lock(&bond->lock); + alb_send_learning_packets(bond->curr_active_slave, + bond_dev->dev_addr, false); 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; @@ -1667,13 +1860,7 @@ 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) { - 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) { + if (bond->alb_info.rlb_enabled) rlb_clear_vlan(bond, vlan_id); - } } diff --git a/drivers/net/bonding/bond_alb.h b/drivers/net/bonding/bond_alb.h index 28f2a2fd1b5..5fc76c01636 100644 --- a/drivers/net/bonding/bond_alb.h +++ b/drivers/net/bonding/bond_alb.h @@ -12,8 +12,7 @@ * 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. + * with this program; if not, see <http://www.gnu.org/licenses/>. * * The full GNU General Public License is included in this distribution in the * file called LICENSE. @@ -31,14 +30,52 @@ struct slave; #define BOND_ALB_INFO(bond) ((bond)->alb_info) #define SLAVE_TLB_INFO(slave) ((slave)->tlb_info) +#define ALB_TIMER_TICKS_PER_SEC 10 /* should be a divisor of HZ */ +#define BOND_TLB_REBALANCE_INTERVAL 10 /* In seconds, periodic re-balancing. + * Used for division - never set + * to zero !!! + */ +#define BOND_ALB_DEFAULT_LP_INTERVAL 1 +#define BOND_ALB_LP_INTERVAL(bond) (bond->params.lp_interval) /* In seconds, periodic send of + * learning packets to the switch + */ + +#define BOND_TLB_REBALANCE_TICKS (BOND_TLB_REBALANCE_INTERVAL \ + * ALB_TIMER_TICKS_PER_SEC) + +#define BOND_ALB_LP_TICKS(bond) (BOND_ALB_LP_INTERVAL(bond) \ + * ALB_TIMER_TICKS_PER_SEC) + +#define TLB_HASH_TABLE_SIZE 256 /* The size of the clients hash table. + * Note that this value MUST NOT be smaller + * because the key hash table is BYTE wide ! + */ + + +#define TLB_NULL_INDEX 0xffffffff + +/* rlb defs */ +#define RLB_HASH_TABLE_SIZE 256 +#define RLB_NULL_INDEX 0xffffffff +#define RLB_UPDATE_DELAY (2*ALB_TIMER_TICKS_PER_SEC) /* 2 seconds */ +#define RLB_ARP_BURST_SIZE 2 +#define RLB_UPDATE_RETRY 3 /* 3-ticks - must be smaller than the rlb + * rebalance interval (5 min). + */ +/* RLB_PROMISC_TIMEOUT = 10 sec equals the time that the current slave is + * promiscuous after failover + */ +#define RLB_PROMISC_TIMEOUT (10*ALB_TIMER_TICKS_PER_SEC) + + struct tlb_client_info { struct slave *tx_slave; /* A pointer to slave used for transmiting * packets to a Client that the Hash function * gave this entry index. */ - u32 tx_bytes; /* Each Client acumulates the BytesTx that - * were tranmitted to it, and after each - * CallBack the LoadHistory is devided + 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 @@ -56,19 +93,38 @@ struct tlb_client_info { /* ------------------------------------------------------------------------- * struct rlb_client_info contains all info related to a specific rx client - * connection. This is the Clients Hash Table entry struct + * connection. This is the Clients Hash Table entry struct. + * Note that this is not a proper hash table; if a new client's IP address + * hash collides with an existing client entry, the old entry is replaced. + * + * There is a linked list (linked by the used_next and used_prev members) + * linking all the used entries of the hash table. This allows updating + * all the clients without walking over all the unused elements of the table. + * + * There are also linked lists of entries with identical hash(ip_src). These + * allow cleaning up the table from ip_src<->mac_src associations that have + * become outdated and would cause sending out invalid ARP updates to the + * network. These are linked by the (src_next and src_prev members). * ------------------------------------------------------------------------- */ struct rlb_client_info { - u32 ip_src; /* the server IP address */ - u32 ip_dst; /* the client IP address */ + __be32 ip_src; /* the server IP address */ + __be32 ip_dst; /* the client IP address */ + u8 mac_src[ETH_ALEN]; /* the server MAC address */ u8 mac_dst[ETH_ALEN]; /* the client MAC address */ - u32 next; /* The next Hash table entry index */ - u32 prev; /* The previous Hash table entry index */ + + /* list of used hash table entries, starting at rx_hashtbl_used_head */ + u32 used_next; + u32 used_prev; + + /* ip_src based hashing */ + u32 src_next; /* next entry with same hash(ip_src) */ + u32 src_prev; /* prev entry with same hash(ip_src) */ + u32 src_first; /* first entry with hash(ip_src) == this entry's index */ + u8 assigned; /* checking whether this entry is assigned */ u8 ntt; /* flag - need to transmit client info */ struct slave *slave; /* the slave assigned to this client */ - u8 tag; /* flag - need to tag skb */ unsigned short vlan_id; /* VLAN tag associated with IP address */ }; @@ -84,7 +140,6 @@ struct tlb_slave_info { }; struct alb_bond_info { - struct timer_list alb_timer; struct tlb_client_info *tx_hashtbl; /* Dynamically allocated */ spinlock_t tx_hashtbl_lock; u32 unbalanced_load; @@ -92,17 +147,13 @@ struct alb_bond_info { int lp_counter; /* -------- rlb parameters -------- */ int rlb_enabled; - struct packet_type rlb_pkt_type; struct rlb_client_info *rx_hashtbl; /* Receive hash table */ spinlock_t rx_hashtbl_lock; - u32 rx_hashtbl_head; + u32 rx_hashtbl_used_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 - */ - u32 rlb_interval_counter; + struct slave *rx_slave;/* last slave to xmit from */ u8 primary_is_promisc; /* boolean */ u32 rlb_promisc_timeout_counter;/* counts primary * promiscuity time @@ -115,7 +166,6 @@ struct alb_bond_info { * rx traffic should be * rebalanced */ - struct vlan_entry *current_alb_vlan; }; int bond_alb_initialize(struct bonding *bond, int rlb_enabled); @@ -125,7 +175,8 @@ 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 bonding *bond); +int bond_tlb_xmit(struct sk_buff *skb, struct net_device *bond_dev); +void bond_alb_monitor(struct work_struct *); int bond_alb_set_mac_address(struct net_device *bond_dev, void *addr); void bond_alb_clear_vlan(struct bonding *bond, unsigned short vlan_id); #endif /* __BOND_ALB_H__ */ diff --git a/drivers/net/bonding/bond_debugfs.c b/drivers/net/bonding/bond_debugfs.c new file mode 100644 index 00000000000..658e761c456 --- /dev/null +++ b/drivers/net/bonding/bond_debugfs.c @@ -0,0 +1,145 @@ +#include <linux/kernel.h> +#include <linux/module.h> +#include <linux/device.h> +#include <linux/netdevice.h> + +#include "bonding.h" +#include "bond_alb.h" + +#if defined(CONFIG_DEBUG_FS) && !defined(CONFIG_NET_NS) + +#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_MODE(bond) != 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_used_head; + for (; hash_index != RLB_NULL_INDEX; + hash_index = client_info->used_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_warn("%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_warn("%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_warn("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/drivers/net/bonding/bond_main.c b/drivers/net/bonding/bond_main.c index 2582d98ef5c..701f86cd599 100644 --- a/drivers/net/bonding/bond_main.c +++ b/drivers/net/bonding/bond_main.c @@ -31,12 +31,10 @@ * */ -//#define BONDING_DEBUG 1 +#define pr_fmt(fmt) KBUILD_MODNAME ": " fmt -#include <linux/config.h> #include <linux/kernel.h> #include <linux/module.h> -#include <linux/sched.h> #include <linux/types.h> #include <linux/fcntl.h> #include <linux/interrupt.h> @@ -55,19 +53,17 @@ #include <linux/ctype.h> #include <linux/inet.h> #include <linux/bitops.h> -#include <asm/system.h> -#include <asm/io.h> +#include <linux/io.h> #include <asm/dma.h> -#include <asm/uaccess.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/proc_fs.h> -#include <linux/seq_file.h> #include <linux/smp.h> #include <linux/if_ether.h> #include <net/arp.h> @@ -75,7 +71,14 @@ #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 <linux/rculist.h> +#include <net/flow_keys.h> #include "bonding.h" #include "bond_3ad.h" #include "bond_alb.h" @@ -83,24 +86,42 @@ /*---------------------------- 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 miimon = BOND_LINK_MON_INTERV; -static int updelay = 0; -static int downdelay = 0; +static int tx_queues = BOND_DEFAULT_TX_QUEUES; +static int num_peer_notif = 1; +static int miimon; +static int updelay; +static int downdelay; static int use_carrier = 1; -static char *mode = NULL; -static char *primary = NULL; -static char *lacp_rate = NULL; -static char *xmit_hash_policy = NULL; -static int arp_interval = BOND_LINK_ARP_INTERV; -static char *arp_ip_target[BOND_MAX_ARP_TARGETS] = { NULL, }; -struct bond_params bonding_defaults; +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; +static char *arp_ip_target[BOND_MAX_ARP_TARGETS]; +static char *arp_validate; +static char *arp_all_targets; +static char *fail_over_mac; +static int all_slaves_active; +static struct bond_params bonding_defaults; +static int resend_igmp = BOND_DEFAULT_RESEND_IGMP; +static int packets_per_slave = 1; +static int lp_interval = BOND_ALB_DEFAULT_LP_INTERVAL; 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); @@ -112,293 +133,136 @@ 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, " +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 " - "(slow/fast)"); +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, "XOR hashing method: 0 for layer 2 (default)" - ", 1 for layer 3+4"); +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, 3 for encap layer 2+3, " + "4 for encap layer 3+4"); 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(arp_all_targets, charp, 0); +MODULE_PARM_DESC(arp_all_targets, "fail on any/all arp targets timeout; 0 for any (default), 1 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"); +module_param(packets_per_slave, int, 0); +MODULE_PARM_DESC(packets_per_slave, "Packets to send per slave in balance-rr " + "mode; 0 for a random slave, 1 packet per " + "slave (default), >1 packets per slave."); +module_param(lp_interval, uint, 0); +MODULE_PARM_DESC(lp_interval, "The number of seconds between instances where " + "the bonding driver sends learning packets to " + "each slaves peer switch. The default is 1."); /*----------------------------- Global variables ----------------------------*/ -static const char *version = - DRV_DESCRIPTION ": v" DRV_VERSION " (" DRV_RELDATE ")\n"; - -LIST_HEAD(bond_dev_list); - -#ifdef CONFIG_PROC_FS -static struct proc_dir_entry *bond_proc_dir = NULL; +#ifdef CONFIG_NET_POLL_CONTROLLER +atomic_t netpoll_block_tx = ATOMIC_INIT(0); #endif -extern struct rw_semaphore bonding_rwsem; -static u32 arp_target[BOND_MAX_ARP_TARGETS] = { 0, } ; -static int arp_ip_count = 0; -static int bond_mode = BOND_MODE_ROUNDROBIN; -static int xmit_hashtype= BOND_XMIT_POLICY_LAYER2; -static int lacp_fast = 0; - - -struct bond_parm_tbl bond_lacp_tbl[] = { -{ "slow", AD_LACP_SLOW}, -{ "fast", AD_LACP_FAST}, -{ NULL, -1}, -}; +int bond_net_id __read_mostly; -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}, -}; - -struct bond_parm_tbl xmit_hashtype_tbl[] = { -{ "layer2", BOND_XMIT_POLICY_LAYER2}, -{ "layer3+4", BOND_XMIT_POLICY_LAYER34}, -{ NULL, -1}, -}; +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; /*-------------------------- Forward declarations ---------------------------*/ -static void bond_send_gratuitous_arp(struct bonding *bond); +static int bond_init(struct net_device *bond_dev); +static void bond_uninit(struct net_device *bond_dev); /*---------------------------- General routines -----------------------------*/ const char *bond_mode_name(int mode) { - switch (mode) { - case BOND_MODE_ROUNDROBIN : - return "load balancing (round-robin)"; - case BOND_MODE_ACTIVEBACKUP : - return "fault-tolerance (active-backup)"; - case BOND_MODE_XOR : - return "load balancing (xor)"; - case BOND_MODE_BROADCAST : - return "fault-tolerance (broadcast)"; - case BOND_MODE_8023AD: - return "IEEE 802.3ad Dynamic link aggregation"; - case BOND_MODE_TLB: - return "transmit load balancing"; - case BOND_MODE_ALB: - return "adaptive load balancing"; - default: + 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 < BOND_MODE_ROUNDROBIN || mode > BOND_MODE_ALB) return "unknown"; - } -} -/*---------------------------------- 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; - - dprintk("bond: %s, vlan id %d\n", - (bond ? bond->dev->name: "None"), vlan_id); - - vlan = kmalloc(sizeof(struct vlan_entry), GFP_KERNEL); - if (!vlan) { - return -ENOMEM; - } - - INIT_LIST_HEAD(&vlan->vlan_list); - vlan->vlan_id = vlan_id; - vlan->vlan_ip = 0; - - write_lock_bh(&bond->lock); - - list_add_tail(&vlan->vlan_list, &bond->vlan_list); - - write_unlock_bh(&bond->lock); - - dprintk("added VLAN ID %d on bond %s\n", vlan_id, bond->dev->name); - - return 0; + return names[mode]; } -/** - * 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, *next; - int res = -ENODEV; - - dprintk("bond: %s, vlan id %d\n", bond->dev->name, vlan_id); - - write_lock_bh(&bond->lock); - - list_for_each_entry_safe(vlan, next, &bond->vlan_list, vlan_list) { - if (vlan->vlan_id == vlan_id) { - list_del(&vlan->vlan_list); - - if ((bond->params.mode == BOND_MODE_TLB) || - (bond->params.mode == BOND_MODE_ALB)) { - bond_alb_clear_vlan(bond, vlan_id); - } - - dprintk("removed VLAN ID %d from bond %s\n", vlan_id, - bond->dev->name); - - kfree(vlan); - - if (list_empty(&bond->vlan_list) && - (bond->slave_cnt == 0)) { - /* Last VLAN removed and no slaves, so - * restore block on adding VLANs. This will - * be removed once new slaves that are not - * VLAN challenged will be added. - */ - bond->dev->features |= NETIF_F_VLAN_CHALLENGED; - } - - res = 0; - goto out; - } - } - - dprintk("couldn't find VLAN ID %d in bond %s\n", vlan_id, - bond->dev->name); - -out: - write_unlock_bh(&bond->lock); - return res; -} - -/** - * bond_has_challenged_slaves - * @bond: the bond we're working on - * - * Searches the slave list. Returns 1 if a vlan challenged slave - * was found, 0 otherwise. - * - * Assumes bond->lock is held. - */ -static int bond_has_challenged_slaves(struct bonding *bond) -{ - struct slave *slave; - int i; - - bond_for_each_slave(bond, slave, i) { - if (slave->dev->features & NETIF_F_VLAN_CHALLENGED) { - dprintk("found VLAN challenged slave - %s\n", - slave->dev->name); - return 1; - } - } - - dprintk("no VLAN challenged slaves found\n"); - return 0; -} - -/** - * 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; -} +/*---------------------------------- VLAN -----------------------------------*/ /** * 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 - * - * When the bond gets an skb to transmit that is - * already hardware accelerated VLAN tagged, and it - * needs to relay this skb to a slave that is not - * hw accel capable, the skb needs to be "unaccelerated", - * i.e. strip the hwaccel tag and re-insert it as part - * of the payload. */ -int bond_dev_queue_xmit(struct bonding *bond, struct sk_buff *skb, struct net_device *slave_dev) +void bond_dev_queue_xmit(struct bonding *bond, struct sk_buff *skb, + struct net_device *slave_dev) { - unsigned short vlan_id; - - if (!list_empty(&bond->vlan_list) && - !(slave_dev->features & NETIF_F_HW_VLAN_TX) && - vlan_get_tag(skb, &vlan_id) == 0) { - skb->dev = slave_dev; - skb = vlan_put_tag(skb, vlan_id); - if (!skb) { - /* vlan_put_tag() frees the skb in case of error, - * so return success here so the calling functions - * won't attempt to free is again. - */ - return 0; - } - } else { - skb->dev = slave_dev; - } + skb->dev = slave_dev; - skb->priority = 1; - dev_queue_xmit(skb); + BUILD_BUG_ON(sizeof(skb->queue_mapping) != + sizeof(qdisc_skb_cb(skb)->slave_dev_queue_mapping)); + skb->queue_mapping = qdisc_skb_cb(skb)->slave_dev_queue_mapping; - return 0; + if (unlikely(netpoll_tx_running(bond->dev))) + bond_netpoll_send_skb(bond_get_slave_by_dev(bond, slave_dev), skb); + else + dev_queue_xmit(skb); } /* - * In the following 3 functions, bond_vlan_rx_register(), bond_vlan_rx_add_vid - * and bond_vlan_rx_kill_vid, We don't protect the slave list iteration with a - * lock because: + * 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 @@ -409,54 +273,36 @@ int bond_dev_queue_xmit(struct bonding *bond, struct sk_buff *skb, struct net_de */ /** - * bond_vlan_rx_register - Propagates registration to slaves + * bond_vlan_rx_add_vid - Propagates adding an id to slaves * @bond_dev: bonding net device that got called - * @grp: vlan group being registered + * @vid: vlan id being added */ -static void bond_vlan_rx_register(struct net_device *bond_dev, struct vlan_group *grp) +static int bond_vlan_rx_add_vid(struct net_device *bond_dev, + __be16 proto, u16 vid) { - struct bonding *bond = bond_dev->priv; - struct slave *slave; - int i; - - bond->vlgrp = grp; - - bond_for_each_slave(bond, slave, i) { - struct net_device *slave_dev = slave->dev; + struct bonding *bond = netdev_priv(bond_dev); + struct slave *slave, *rollback_slave; + struct list_head *iter; + int res; - if ((slave_dev->features & NETIF_F_HW_VLAN_RX) && - slave_dev->vlan_rx_register) { - slave_dev->vlan_rx_register(slave_dev, grp); - } + bond_for_each_slave(bond, slave, iter) { + res = vlan_vid_add(slave->dev, proto, vid); + if (res) + goto unwind; } -} -/** - * 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 void bond_vlan_rx_add_vid(struct net_device *bond_dev, uint16_t vid) -{ - struct bonding *bond = bond_dev->priv; - struct slave *slave; - int i, res; + return 0; - bond_for_each_slave(bond, slave, i) { - struct net_device *slave_dev = slave->dev; +unwind: + /* unwind to the slave that failed */ + bond_for_each_slave(bond, rollback_slave, iter) { + if (rollback_slave == slave) + break; - if ((slave_dev->features & NETIF_F_HW_VLAN_FILTER) && - slave_dev->vlan_rx_add_vid) { - slave_dev->vlan_rx_add_vid(slave_dev, vid); - } + vlan_vid_del(rollback_slave->dev, proto, vid); } - res = bond_add_vlan(bond, vid); - if (res) { - printk(KERN_ERR DRV_NAME - ": %s: Error: Failed to add vlan id %d\n", - bond_dev->name, vid); - } + return res; } /** @@ -464,169 +310,119 @@ static void bond_vlan_rx_add_vid(struct net_device *bond_dev, uint16_t vid) * @bond_dev: bonding net device that got called * @vid: vlan id being removed */ -static void bond_vlan_rx_kill_vid(struct net_device *bond_dev, uint16_t vid) +static int bond_vlan_rx_kill_vid(struct net_device *bond_dev, + __be16 proto, u16 vid) { - struct bonding *bond = bond_dev->priv; + struct bonding *bond = netdev_priv(bond_dev); + struct list_head *iter; struct slave *slave; - struct net_device *vlan_dev; - int i, res; - bond_for_each_slave(bond, slave, i) { - struct net_device *slave_dev = slave->dev; + bond_for_each_slave(bond, slave, iter) + vlan_vid_del(slave->dev, proto, vid); - if ((slave_dev->features & NETIF_F_HW_VLAN_FILTER) && - slave_dev->vlan_rx_kill_vid) { - /* Save and then restore vlan_dev in the grp array, - * since the slave's driver might clear it. - */ - vlan_dev = bond->vlgrp->vlan_devices[vid]; - slave_dev->vlan_rx_kill_vid(slave_dev, vid); - bond->vlgrp->vlan_devices[vid] = vlan_dev; - } - } + if (bond_is_lb(bond)) + bond_alb_clear_vlan(bond, vid); - res = bond_del_vlan(bond, vid); - if (res) { - printk(KERN_ERR DRV_NAME - ": %s: Error: Failed to remove vlan id %d\n", - bond_dev->name, vid); - } + return 0; } -static void bond_add_vlans_on_slave(struct bonding *bond, struct net_device *slave_dev) -{ - struct vlan_entry *vlan; - - write_lock_bh(&bond->lock); - - if (list_empty(&bond->vlan_list)) { - goto out; - } - - if ((slave_dev->features & NETIF_F_HW_VLAN_RX) && - slave_dev->vlan_rx_register) { - slave_dev->vlan_rx_register(slave_dev, bond->vlgrp); - } - - if (!(slave_dev->features & NETIF_F_HW_VLAN_FILTER) || - !(slave_dev->vlan_rx_add_vid)) { - goto out; - } - - list_for_each_entry(vlan, &bond->vlan_list, vlan_list) { - slave_dev->vlan_rx_add_vid(slave_dev, vlan->vlan_id); - } - -out: - write_unlock_bh(&bond->lock); -} +/*------------------------------- Link status -------------------------------*/ -static void bond_del_vlans_from_slave(struct bonding *bond, struct net_device *slave_dev) +/* + * 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 vlan_entry *vlan; - struct net_device *vlan_dev; + struct list_head *iter; + struct slave *slave; - write_lock_bh(&bond->lock); + if (!bond_has_slaves(bond)) + goto down; - if (list_empty(&bond->vlan_list)) { - goto out; - } - - if (!(slave_dev->features & NETIF_F_HW_VLAN_FILTER) || - !(slave_dev->vlan_rx_kill_vid)) { - goto unreg; - } + if (BOND_MODE(bond) == BOND_MODE_8023AD) + return bond_3ad_set_carrier(bond); - list_for_each_entry(vlan, &bond->vlan_list, vlan_list) { - /* Save and then restore vlan_dev in the grp array, - * since the slave's driver might clear it. - */ - vlan_dev = bond->vlgrp->vlan_devices[vlan->vlan_id]; - slave_dev->vlan_rx_kill_vid(slave_dev, vlan->vlan_id); - bond->vlgrp->vlan_devices[vlan->vlan_id] = vlan_dev; + bond_for_each_slave(bond, slave, iter) { + if (slave->link == BOND_LINK_UP) { + if (!netif_carrier_ok(bond->dev)) { + netif_carrier_on(bond->dev); + return 1; + } + return 0; + } } -unreg: - if ((slave_dev->features & NETIF_F_HW_VLAN_RX) && - slave_dev->vlan_rx_register) { - slave_dev->vlan_rx_register(slave_dev, NULL); +down: + if (netif_carrier_ok(bond->dev)) { + netif_carrier_off(bond->dev); + return 1; } - -out: - write_unlock_bh(&bond->lock); + return 0; } -/*------------------------------- Link status -------------------------------*/ - /* * 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, fake speed and duplex to 100/Full - * and return error. + * values are invalid, set speed and duplex to -1, + * and return. */ -static int bond_update_speed_duplex(struct slave *slave) +static void bond_update_speed_duplex(struct slave *slave) { struct net_device *slave_dev = slave->dev; - static int (* ioctl)(struct net_device *, struct ifreq *, int); - struct ifreq ifr; - struct ethtool_cmd etool; - - /* Fake speed and duplex */ - slave->speed = SPEED_100; - slave->duplex = DUPLEX_FULL; - - if (slave_dev->ethtool_ops) { - u32 res; - - if (!slave_dev->ethtool_ops->get_settings) { - return -1; - } + struct ethtool_cmd ecmd; + u32 slave_speed; + int res; - res = slave_dev->ethtool_ops->get_settings(slave_dev, &etool); - if (res < 0) { - return -1; - } + slave->speed = SPEED_UNKNOWN; + slave->duplex = DUPLEX_UNKNOWN; - goto verify; - } - - ioctl = slave_dev->do_ioctl; - strncpy(ifr.ifr_name, slave_dev->name, IFNAMSIZ); - etool.cmd = ETHTOOL_GSET; - ifr.ifr_data = (char*)&etool; - if (!ioctl || (IOCTL(slave_dev, &ifr, SIOCETHTOOL) < 0)) { - return -1; - } + res = __ethtool_get_settings(slave_dev, &ecmd); + if (res < 0) + return; -verify: - switch (etool.speed) { - case SPEED_10: - case SPEED_100: - case SPEED_1000: - break; - default: - return -1; - } + slave_speed = ethtool_cmd_speed(&ecmd); + if (slave_speed == 0 || slave_speed == ((__u32) -1)) + return; - switch (etool.duplex) { + switch (ecmd.duplex) { case DUPLEX_FULL: case DUPLEX_HALF: break; default: - return -1; + return; } - slave->speed = etool.speed; - slave->duplex = etool.duplex; + slave->speed = slave_speed; + slave->duplex = ecmd.duplex; - return 0; + return; +} + +const char *bond_slave_link_status(s8 link) +{ + switch (link) { + case BOND_LINK_UP: + return "up"; + case BOND_LINK_FAIL: + return "going down"; + case BOND_LINK_DOWN: + return "down"; + case BOND_LINK_BACK: + return "going back"; + default: + return "unknown"; + } } /* * if <dev> supports MII link status reporting, check its link status. * * We either do MII/ETHTOOL ioctls, or check netif_carrier_ok(), - * depening upon the setting of the use_carrier parameter. + * 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 @@ -638,18 +434,27 @@ verify: * 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) +static int bond_check_dev_link(struct bonding *bond, + struct net_device *slave_dev, int reporting) { - static int (* ioctl)(struct net_device *, struct ifreq *, int); + 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; - struct ethtool_value etool; - if (bond->params.use_carrier) { + if (!reporting && !netif_running(slave_dev)) + return 0; + + if (bond->params.use_carrier) return netif_carrier_ok(slave_dev) ? BMSR_LSTATUS : 0; - } - ioctl = slave_dev->do_ioctl; + /* Try to get link status using Ethtool first. */ + if (slave_dev->ethtool_ops->get_link) + return slave_dev->ethtool_ops->get_link(slave_dev) ? + 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 */ @@ -668,316 +473,308 @@ static int bond_check_dev_link(struct bonding *bond, struct net_device *slave_de 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); - } - } - } - - /* try SIOCETHTOOL ioctl, some drivers cache ETHTOOL_GLINK */ - /* for a period of time so we attempt to get link status */ - /* from it last if the above MII ioctls fail... */ - 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; - } - } - - if (ioctl) { - strncpy(ifr.ifr_name, slave_dev->name, IFNAMSIZ); - etool.cmd = ETHTOOL_GLINK; - ifr.ifr_data = (char*)&etool; - if (IOCTL(slave_dev, &ifr, SIOCETHTOOL) == 0) { - if (etool.data == 1) { - return BMSR_LSTATUS; - } else { - dprintk("SIOCETHTOOL shows link down\n"); - return 0; - } + 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 SIOCETHTOOL failed (meaning that we + * 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); + return reporting ? -1 : BMSR_LSTATUS; } /*----------------------------- Multicast list ------------------------------*/ /* - * Returns 0 if dmi1 and dmi2 are the same, non-0 otherwise - */ -static inline int bond_is_dmi_same(struct dev_mc_list *dmi1, struct dev_mc_list *dmi2) -{ - return memcmp(dmi1->dmi_addr, dmi2->dmi_addr, dmi1->dmi_addrlen) == 0 && - dmi1->dmi_addrlen == dmi2->dmi_addrlen; -} - -/* - * returns dmi entry if found, NULL otherwise - */ -static struct dev_mc_list *bond_mc_list_find_dmi(struct dev_mc_list *dmi, struct dev_mc_list *mc_list) -{ - struct dev_mc_list *idmi; - - for (idmi = mc_list; idmi; idmi = idmi->next) { - if (bond_is_dmi_same(dmi, idmi)) { - return idmi; - } - } - - return NULL; -} - -/* * Push the promiscuity flag down to appropriate slaves */ -static void bond_set_promiscuity(struct bonding *bond, int inc) +static int bond_set_promiscuity(struct bonding *bond, int inc) { - if (USES_PRIMARY(bond->params.mode)) { + struct list_head *iter; + int err = 0; + + if (bond_uses_primary(bond)) { /* write lock already acquired */ if (bond->curr_active_slave) { - dev_set_promiscuity(bond->curr_active_slave->dev, inc); + err = dev_set_promiscuity(bond->curr_active_slave->dev, + inc); } } else { struct slave *slave; - int i; - bond_for_each_slave(bond, slave, i) { - dev_set_promiscuity(slave->dev, inc); + + bond_for_each_slave(bond, slave, iter) { + err = dev_set_promiscuity(slave->dev, inc); + if (err) + return err; } } + return err; } /* * Push the allmulti flag down to all slaves */ -static void bond_set_allmulti(struct bonding *bond, int inc) +static int bond_set_allmulti(struct bonding *bond, int inc) { - if (USES_PRIMARY(bond->params.mode)) { - /* write lock already acquired */ - if (bond->curr_active_slave) { - dev_set_allmulti(bond->curr_active_slave->dev, inc); - } - } else { - struct slave *slave; - int i; - bond_for_each_slave(bond, slave, i) { - dev_set_allmulti(slave->dev, inc); - } - } -} + struct list_head *iter; + int err = 0; -/* - * Add a Multicast address to slaves - * according to mode - */ -static void bond_mc_add(struct bonding *bond, void *addr, int alen) -{ - if (USES_PRIMARY(bond->params.mode)) { + if (bond_uses_primary(bond)) { /* write lock already acquired */ if (bond->curr_active_slave) { - dev_mc_add(bond->curr_active_slave->dev, addr, alen, 0); + err = dev_set_allmulti(bond->curr_active_slave->dev, + inc); } } else { struct slave *slave; - int i; - bond_for_each_slave(bond, slave, i) { - dev_mc_add(slave->dev, addr, alen, 0); - } - } -} -/* - * Remove a multicast address from slave - * according to mode - */ -static void bond_mc_delete(struct bonding *bond, void *addr, int alen) -{ - if (USES_PRIMARY(bond->params.mode)) { - /* write lock already acquired */ - if (bond->curr_active_slave) { - dev_mc_delete(bond->curr_active_slave->dev, addr, alen, 0); - } - } else { - struct slave *slave; - int i; - bond_for_each_slave(bond, slave, i) { - dev_mc_delete(slave->dev, addr, alen, 0); + bond_for_each_slave(bond, slave, iter) { + err = dev_set_allmulti(slave->dev, inc); + if (err) + return err; } } + return err; } /* - * Totally destroys the mc_list in bond + * 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_mc_list_destroy(struct bonding *bond) +static void bond_resend_igmp_join_requests_delayed(struct work_struct *work) { - struct dev_mc_list *dmi; + struct bonding *bond = container_of(work, struct bonding, + mcast_work.work); - dmi = bond->mc_list; - while (dmi) { - bond->mc_list = dmi->next; - kfree(dmi); - dmi = bond->mc_list; + if (!rtnl_trylock()) { + queue_delayed_work(bond->wq, &bond->mcast_work, 1); + return; } -} - -/* - * Copy all the Multicast addresses from src to the bonding device dst - */ -static int bond_mc_list_copy(struct dev_mc_list *mc_list, struct bonding *bond, - gfp_t gfp_flag) -{ - struct dev_mc_list *dmi, *new_dmi; + call_netdevice_notifiers(NETDEV_RESEND_IGMP, bond->dev); - for (dmi = mc_list; dmi; dmi = dmi->next) { - new_dmi = kmalloc(sizeof(struct dev_mc_list), gfp_flag); - - if (!new_dmi) { - /* FIXME: Potential memory leak !!! */ - return -ENOMEM; - } - - new_dmi->next = bond->mc_list; - bond->mc_list = new_dmi; - new_dmi->dmi_addrlen = dmi->dmi_addrlen; - memcpy(new_dmi->dmi_addr, dmi->dmi_addr, dmi->dmi_addrlen); - new_dmi->dmi_users = dmi->dmi_users; - new_dmi->dmi_gusers = dmi->dmi_gusers; + if (bond->igmp_retrans > 1) { + bond->igmp_retrans--; + queue_delayed_work(bond->wq, &bond->mcast_work, HZ/5); } - - return 0; + rtnl_unlock(); } -/* - * flush all members of flush->mc_list from device dev->mc_list +/* Flush bond's hardware addresses from slave */ -static void bond_mc_list_flush(struct net_device *bond_dev, struct net_device *slave_dev) +static void bond_hw_addr_flush(struct net_device *bond_dev, + struct net_device *slave_dev) { - struct bonding *bond = bond_dev->priv; - struct dev_mc_list *dmi; + struct bonding *bond = netdev_priv(bond_dev); - for (dmi = bond_dev->mc_list; dmi; dmi = dmi->next) { - dev_mc_delete(slave_dev, dmi->dmi_addr, dmi->dmi_addrlen, 0); - } + dev_uc_unsync(slave_dev, bond_dev); + dev_mc_unsync(slave_dev, bond_dev); - if (bond->params.mode == BOND_MODE_8023AD) { + if (BOND_MODE(bond) == BOND_MODE_8023AD) { /* del lacpdu mc addr from mc list */ u8 lacpdu_multicast[ETH_ALEN] = MULTICAST_LACPDU_ADDR; - dev_mc_delete(slave_dev, lacpdu_multicast, ETH_ALEN, 0); + 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. +/* Update the hardware address list and promisc/allmulti for the new and + * old active slaves (if any). Modes that are not using primary keep all + * slaves up date at all times; only the modes that use primary need to call + * this function to swap these settings during a failover. */ -static void bond_mc_swap(struct bonding *bond, struct slave *new_active, struct slave *old_active) +static void bond_hw_addr_swap(struct bonding *bond, struct slave *new_active, + struct slave *old_active) { - struct dev_mc_list *dmi; - - if (!USES_PRIMARY(bond->params.mode)) { - /* nothing to do - mc list is already up-to-date on - * all slaves - */ - return; - } + ASSERT_RTNL(); if (old_active) { - if (bond->dev->flags & IFF_PROMISC) { + if (bond->dev->flags & IFF_PROMISC) dev_set_promiscuity(old_active->dev, -1); - } - if (bond->dev->flags & IFF_ALLMULTI) { + if (bond->dev->flags & IFF_ALLMULTI) dev_set_allmulti(old_active->dev, -1); - } - for (dmi = bond->dev->mc_list; dmi; dmi = dmi->next) { - dev_mc_delete(old_active->dev, dmi->dmi_addr, dmi->dmi_addrlen, 0); - } + bond_hw_addr_flush(bond->dev, old_active->dev); } if (new_active) { - if (bond->dev->flags & IFF_PROMISC) { + /* FIXME: Signal errors upstream. */ + if (bond->dev->flags & IFF_PROMISC) dev_set_promiscuity(new_active->dev, 1); - } - if (bond->dev->flags & IFF_ALLMULTI) { + if (bond->dev->flags & IFF_ALLMULTI) dev_set_allmulti(new_active->dev, 1); + + netif_addr_lock_bh(bond->dev); + dev_uc_sync(new_active->dev, bond->dev); + dev_mc_sync(new_active->dev, bond->dev); + netif_addr_unlock_bh(bond->dev); + } +} + +/** + * bond_set_dev_addr - clone slave's address to bond + * @bond_dev: bond net device + * @slave_dev: slave net device + * + * Should be called with RTNL held. + */ +static void bond_set_dev_addr(struct net_device *bond_dev, + struct net_device *slave_dev) +{ + pr_debug("bond_dev=%p slave_dev=%p slave_dev->addr_len=%d\n", + bond_dev, slave_dev, slave_dev->addr_len); + memcpy(bond_dev->dev_addr, slave_dev->dev_addr, slave_dev->addr_len); + bond_dev->addr_assign_type = NET_ADDR_STOLEN; + call_netdevice_notifiers(NETDEV_CHANGEADDR, bond_dev); +} + +/* + * bond_do_fail_over_mac + * + * Perform special MAC address swapping for fail_over_mac settings + * + * Called with RTNL, 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) + __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) { + write_unlock_bh(&bond->curr_slave_lock); + bond_set_dev_addr(bond->dev, new_active->dev); + 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); + + if (old_active) { + ether_addr_copy(tmp_mac, new_active->dev->dev_addr); + ether_addr_copy(saddr.sa_data, + old_active->dev->dev_addr); + saddr.sa_family = new_active->dev->type; + } else { + ether_addr_copy(saddr.sa_data, bond->dev->dev_addr); + saddr.sa_family = bond->dev->type; } - for (dmi = bond->dev->mc_list; dmi; dmi = dmi->next) { - dev_mc_add(new_active->dev, dmi->dmi_addr, dmi->dmi_addrlen, 0); + 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; + + ether_addr_copy(saddr.sa_data, tmp_mac); + 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: + 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; + struct slave *slave, *bestslave = NULL; + struct list_head *iter; int mintime = bond->params.updelay; - int i; - - new_active = old_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)) + return bond->primary_slave; - /* first try the primary link; if arping, a link must tx/rx traffic - * before it can be considered the curr_active_slave - also, we would skip - * slaves between the curr_active_slave and primary_slave that may be up - * and able to arp - */ - if ((bond->primary_slave) && - (!bond->params.arp_interval) && - (IS_UP(bond->primary_slave->dev))) { - 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 (IS_UP(new_active->dev)) { - if (new_active->link == BOND_LINK_UP) { - return new_active; - } else if (new_active->link == BOND_LINK_BACK) { - /* link up, but waiting for stabilization */ - if (new_active->delay < mintime) { - mintime = new_active->delay; - bestslave = new_active; - } - } + bond_for_each_slave(bond, slave, iter) { + if (slave->link == BOND_LINK_UP) + return slave; + if (slave->link == BOND_LINK_BACK && bond_slave_is_up(slave) && + slave->delay < mintime) { + mintime = slave->delay; + bestslave = slave; } } return bestslave; } +static bool bond_should_notify_peers(struct bonding *bond) +{ + struct slave *slave; + + rcu_read_lock(); + slave = rcu_dereference(bond->curr_active_slave); + rcu_read_unlock(); + + 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; + + return true; +} + /** * change_active_interface - change the active slave into the specified one * @bond: our bonding struct @@ -991,68 +788,98 @@ static struct slave *bond_find_best_slave(struct bonding *bond) * because it is apparently the best available slave we have, even though its * updelay hasn't timed out yet. * - * Warning: Caller must hold curr_slave_lock for writing. + * If new_active is not NULL, caller must hold 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) { + if (old_active == new_active) return; - } if (new_active) { + new_active->last_link_up = jiffies; + if (new_active->link == BOND_LINK_BACK) { - if (USES_PRIMARY(bond->params.mode)) { - printk(KERN_INFO DRV_NAME - ": %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); + if (bond_uses_primary(bond)) { + 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; - new_active->jiffies = jiffies; - if (bond->params.mode == BOND_MODE_8023AD) { + if (BOND_MODE(bond) == BOND_MODE_8023AD) bond_3ad_handle_link_change(new_active, BOND_LINK_UP); - } - if ((bond->params.mode == BOND_MODE_TLB) || - (bond->params.mode == BOND_MODE_ALB)) { + if (bond_is_lb(bond)) bond_alb_handle_link_change(bond, new_active, BOND_LINK_UP); - } } else { - if (USES_PRIMARY(bond->params.mode)) { - printk(KERN_INFO DRV_NAME - ": %s: making interface %s the new " - "active one.\n", - bond->dev->name, new_active->dev->name); + if (bond_uses_primary(bond)) { + 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_uses_primary(bond)) + bond_hw_addr_swap(bond, new_active, old_active); - if ((bond->params.mode == BOND_MODE_TLB) || - (bond->params.mode == BOND_MODE_ALB)) { + if (bond_is_lb(bond)) { bond_alb_handle_active_change(bond, new_active); + if (old_active) + bond_set_slave_inactive_flags(old_active, + BOND_SLAVE_NOTIFY_NOW); + if (new_active) + bond_set_slave_active_flags(new_active, + BOND_SLAVE_NOTIFY_NOW); } else { - bond->curr_active_slave = new_active; + rcu_assign_pointer(bond->curr_active_slave, new_active); } - if (bond->params.mode == BOND_MODE_ACTIVEBACKUP) { - if (old_active) { - bond_set_slave_inactive_flags(old_active); - } + if (BOND_MODE(bond) == BOND_MODE_ACTIVEBACKUP) { + if (old_active) + bond_set_slave_inactive_flags(old_active, + BOND_SLAVE_NOTIFY_NOW); if (new_active) { - bond_set_slave_active_flags(new_active); + bool should_notify_peers = false; + + bond_set_slave_active_flags(new_active, + BOND_SLAVE_NOTIFY_NOW); + + 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); + + call_netdevice_notifiers(NETDEV_BONDING_FAILOVER, bond->dev); + if (should_notify_peers) + call_netdevice_notifiers(NETDEV_NOTIFY_PEERS, + bond->dev); + + write_lock_bh(&bond->curr_slave_lock); } - bond_send_gratuitous_arp(bond); + } + + /* 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) && + ((bond_uses_primary(bond) && new_active) || + BOND_MODE(bond) == BOND_MODE_ROUNDROBIN)) { + bond->igmp_retrans = bond->params.resend_igmp; + queue_delayed_work(bond->wq, &bond->mcast_work, 1); } } @@ -1060,301 +887,560 @@ void bond_change_active_slave(struct bonding *bond, struct slave *new_active) * bond_select_active_slave - select a new active slave, if needed * @bond: our bonding struct * - * This functions shoud be called when one of the following occurs: + * 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. * - * Warning: Caller must hold curr_slave_lock for writing. + * Caller must hold 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) +#ifdef CONFIG_NET_POLL_CONTROLLER +static inline int slave_enable_netpoll(struct slave *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; + struct netpoll *np; + int err = 0; + + np = kzalloc(sizeof(*np), GFP_KERNEL); + err = -ENOMEM; + if (!np) + goto out; + + err = __netpoll_setup(np, slave->dev); + 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; - bond->slave_cnt++; + if (!np) + return; + + slave->np = NULL; + __netpoll_free_async(np); } -/* - * 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) +static void bond_poll_controller(struct net_device *bond_dev) +{ +} + +static void bond_netpoll_cleanup(struct net_device *bond_dev) { - if (slave->next) { - slave->next->prev = slave->prev; + struct bonding *bond = netdev_priv(bond_dev); + struct list_head *iter; + struct slave *slave; + + bond_for_each_slave(bond, slave, iter) + if (bond_slave_is_up(slave)) + slave_disable_netpoll(slave); +} + +static int bond_netpoll_setup(struct net_device *dev, struct netpoll_info *ni) +{ + struct bonding *bond = netdev_priv(dev); + struct list_head *iter; + struct slave *slave; + int err = 0; + + bond_for_each_slave(bond, slave, iter) { + err = slave_enable_netpoll(slave); + if (err) { + bond_netpoll_cleanup(dev); + break; + } } + return err; +} +#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 netdev_features_t bond_fix_features(struct net_device *dev, + netdev_features_t features) +{ + struct bonding *bond = netdev_priv(dev); + struct list_head *iter; + netdev_features_t mask; + struct slave *slave; - if (slave->prev) { - slave->prev->next = slave->next; + if (!bond_has_slaves(bond)) { + /* Disable adding VLANs to empty bond. But why? --mq */ + features |= NETIF_F_VLAN_CHALLENGED; + return features; } - 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 */ - } + mask = features; + features &= ~NETIF_F_ONE_FOR_ALL; + features |= NETIF_F_ALL_FOR_ALL; + + bond_for_each_slave(bond, slave, iter) { + features = netdev_increment_features(features, + slave->dev->features, + mask); } + features = netdev_add_tso_features(features, mask); - slave->next = NULL; - slave->prev = NULL; - bond->slave_cnt--; + return features; } -/*---------------------------------- IOCTL ----------------------------------*/ +#define BOND_VLAN_FEATURES (NETIF_F_ALL_CSUM | NETIF_F_SG | \ + NETIF_F_FRAGLIST | NETIF_F_ALL_TSO | \ + NETIF_F_HIGHDMA | NETIF_F_LRO) -int bond_sethwaddr(struct net_device *bond_dev, struct net_device *slave_dev) +#define BOND_ENC_FEATURES (NETIF_F_ALL_CSUM | NETIF_F_SG | NETIF_F_RXCSUM |\ + NETIF_F_TSO | NETIF_F_GSO_UDP_TUNNEL) + +static void bond_compute_features(struct bonding *bond) { - dprintk("bond_dev=%p\n", bond_dev); - dprintk("slave_dev=%p\n", slave_dev); - dprintk("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; + unsigned int flags, dst_release_flag = IFF_XMIT_DST_RELEASE; + netdev_features_t vlan_features = BOND_VLAN_FEATURES; + netdev_features_t enc_features = BOND_ENC_FEATURES; + struct net_device *bond_dev = bond->dev; + struct list_head *iter; + struct slave *slave; + unsigned short max_hard_header_len = ETH_HLEN; + unsigned int gso_max_size = GSO_MAX_SIZE; + u16 gso_max_segs = GSO_MAX_SEGS; + + if (!bond_has_slaves(bond)) + goto done; + vlan_features &= NETIF_F_ALL_FOR_ALL; + + bond_for_each_slave(bond, slave, iter) { + vlan_features = netdev_increment_features(vlan_features, + slave->dev->vlan_features, BOND_VLAN_FEATURES); + + enc_features = netdev_increment_features(enc_features, + slave->dev->hw_enc_features, + BOND_ENC_FEATURES); + dst_release_flag &= slave->dev->priv_flags; + if (slave->dev->hard_header_len > max_hard_header_len) + max_hard_header_len = slave->dev->hard_header_len; + + gso_max_size = min(gso_max_size, slave->dev->gso_max_size); + gso_max_segs = min(gso_max_segs, slave->dev->gso_max_segs); + } + +done: + bond_dev->vlan_features = vlan_features; + bond_dev->hw_enc_features = enc_features; + bond_dev->hard_header_len = max_hard_header_len; + bond_dev->gso_max_segs = gso_max_segs; + netif_set_gso_max_size(bond_dev, gso_max_size); + + flags = bond_dev->priv_flags & ~IFF_XMIT_DST_RELEASE; + bond_dev->priv_flags = flags | dst_release_flag; + + netdev_change_features(bond_dev); } -#define BOND_INTERSECT_FEATURES \ - (NETIF_F_SG|NETIF_F_IP_CSUM|NETIF_F_NO_CSUM|NETIF_F_HW_CSUM) +static void bond_setup_by_slave(struct net_device *bond_dev, + struct net_device *slave_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; -/* - * Compute the common dev->feature set available to all slaves. Some - * feature bits are managed elsewhere, so preserve feature bits set on - * master device that are not part of the examined set. + memcpy(bond_dev->broadcast, slave_dev->broadcast, + slave_dev->addr_len); +} + +/* On bonding slaves other than the currently active slave, suppress + * duplicates except for alb non-mcast/bcast. */ -static int bond_compute_features(struct bonding *bond) +static bool bond_should_deliver_exact_match(struct sk_buff *skb, + struct slave *slave, + struct bonding *bond) { - unsigned long features = BOND_INTERSECT_FEATURES; + if (bond_is_slave_inactive(slave)) { + if (BOND_MODE(bond) == 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 net_device *bond_dev = bond->dev; - int i; + struct bonding *bond; + int (*recv_probe)(const 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; + + recv_probe = ACCESS_ONCE(bond->recv_probe); + if (recv_probe) { + ret = recv_probe(skb, bond, slave); + if (ret == RX_HANDLER_CONSUMED) { + consume_skb(skb); + return ret; + } + } - bond_for_each_slave(bond, slave, i) - features &= (slave->dev->features & BOND_INTERSECT_FEATURES); + if (bond_should_deliver_exact_match(skb, slave, bond)) { + return RX_HANDLER_EXACT; + } - if ((features & NETIF_F_SG) && - !(features & (NETIF_F_IP_CSUM | - NETIF_F_NO_CSUM | - NETIF_F_HW_CSUM))) - features &= ~NETIF_F_SG; + skb->dev = bond->dev; - features |= (bond_dev->features & ~BOND_INTERSECT_FEATURES); - bond_dev->features = features; + if (BOND_MODE(bond) == 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; + } + ether_addr_copy(eth_hdr(skb)->h_dest, bond->dev->dev_addr); + } + + return ret; +} + +static int bond_master_upper_dev_link(struct net_device *bond_dev, + struct net_device *slave_dev, + struct slave *slave) +{ + int err; + + err = netdev_master_upper_dev_link_private(slave_dev, bond_dev, slave); + if (err) + return err; + slave_dev->flags |= IFF_SLAVE; + rtmsg_ifinfo(RTM_NEWLINK, slave_dev, IFF_SLAVE, GFP_KERNEL); return 0; } +static void bond_upper_dev_unlink(struct net_device *bond_dev, + struct net_device *slave_dev) +{ + netdev_upper_dev_unlink(slave_dev, bond_dev); + slave_dev->flags &= ~IFF_SLAVE; + rtmsg_ifinfo(RTM_NEWLINK, slave_dev, IFF_SLAVE, GFP_KERNEL); +} + +static struct slave *bond_alloc_slave(struct bonding *bond) +{ + struct slave *slave = NULL; + + slave = kzalloc(sizeof(struct slave), GFP_KERNEL); + if (!slave) + return NULL; + + if (BOND_MODE(bond) == BOND_MODE_8023AD) { + SLAVE_AD_INFO(slave) = kzalloc(sizeof(struct ad_slave_info), + GFP_KERNEL); + if (!SLAVE_AD_INFO(slave)) { + kfree(slave); + return NULL; + } + } + return slave; +} + +static void bond_free_slave(struct slave *slave) +{ + struct bonding *bond = bond_get_bond_by_slave(slave); + + if (BOND_MODE(bond) == BOND_MODE_8023AD) + kfree(SLAVE_AD_INFO(slave)); + + kfree(slave); +} + /* enslave device <slave> to bond device <master> */ int bond_enslave(struct net_device *bond_dev, struct net_device *slave_dev) { - struct bonding *bond = bond_dev->priv; - struct slave *new_slave = NULL; - struct dev_mc_list *dmi; + struct bonding *bond = netdev_priv(bond_dev); + const struct net_device_ops *slave_ops = slave_dev->netdev_ops; + struct slave *new_slave = NULL, *prev_slave; struct sockaddr addr; int link_reporting; - int old_features = bond_dev->features; - int res = 0; - - if (!bond->params.use_carrier && slave_dev->ethtool_ops == NULL && - slave_dev->do_ioctl == NULL) { - printk(KERN_WARNING DRV_NAME - ": %s: Warning: no link monitoring support for %s\n", - bond_dev->name, slave_dev->name); - } + int res = 0, i; - /* bond must be initialized by bond_open() before enslaving */ - if (!(bond_dev->flags & IFF_UP)) { - dprintk("Error, master_dev is not up\n"); - return -EPERM; + if (!bond->params.use_carrier && + slave_dev->ethtool_ops->get_link == NULL && + slave_ops->ndo_do_ioctl == NULL) { + pr_warn("%s: Warning: no link monitoring support for %s\n", + bond_dev->name, slave_dev->name); } /* already enslaved */ if (slave_dev->flags & IFF_SLAVE) { - dprintk("Error, Device was already enslaved\n"); + pr_debug("Error: Device was already enslaved\n"); return -EBUSY; } + if (bond_dev == slave_dev) { + pr_err("%s: cannot enslave bond to itself.\n", bond_dev->name); + return -EPERM; + } + /* vlan challenged mutual exclusion */ /* no need to lock since we're protected by rtnl_lock */ if (slave_dev->features & NETIF_F_VLAN_CHALLENGED) { - dprintk("%s: NETIF_F_VLAN_CHALLENGED\n", slave_dev->name); - if (!list_empty(&bond->vlan_list)) { - printk(KERN_ERR DRV_NAME - ": %s: Error: cannot enslave VLAN " - "challenged slave %s on VLAN enabled " - "bond %s\n", bond_dev->name, slave_dev->name, - bond_dev->name); + pr_debug("%s: NETIF_F_VLAN_CHALLENGED\n", slave_dev->name); + if (vlan_uses_dev(bond_dev)) { + 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 { - printk(KERN_WARNING DRV_NAME - ": %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); - bond_dev->features |= NETIF_F_VLAN_CHALLENGED; + pr_warn("%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 { - dprintk("%s: ! NETIF_F_VLAN_CHALLENGED\n", slave_dev->name); - if (bond->slave_cnt == 0) { - /* First slave, and it is not VLAN challenged, - * so remove the block of adding VLANs over the bond. - */ - bond_dev->features &= ~NETIF_F_VLAN_CHALLENGED; - } + pr_debug("%s: ! NETIF_F_VLAN_CHALLENGED\n", slave_dev->name); } /* * Old ifenslave binaries are no longer supported. These can - * be identified with moderate accurary by the state of the slave: + * 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)) { - printk(KERN_ERR DRV_NAME ": %s is up. " - "This may be due to an out of date ifenslave.\n", + 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; } - if (slave_dev->set_mac_address == NULL) { - printk(KERN_ERR DRV_NAME - ": %s: Error: The slave device you specified does " - "not support setting the MAC address. " - "Your kernel likely does not support slave " - "devices.\n", bond_dev->name); - res = -EOPNOTSUPP; + /* 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_has_slaves(bond)) { + 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 = call_netdevice_notifiers(NETDEV_PRE_TYPE_CHANGE, + bond_dev); + 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; + } + + call_netdevice_notifiers(NETDEV_POST_TYPE_CHANGE, + bond_dev); + } + } 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; } - new_slave = kmalloc(sizeof(struct slave), GFP_KERNEL); + if (slave_ops->ndo_set_mac_address == NULL) { + if (!bond_has_slaves(bond)) { + pr_warn("%s: Warning: The first slave device specified does not support setting the MAC address\n", + bond_dev->name); + if (BOND_MODE(bond) == BOND_MODE_ACTIVEBACKUP) { + bond->params.fail_over_mac = BOND_FOM_ACTIVE; + pr_warn("%s: Setting fail_over_mac to active for active-backup mode\n", + bond_dev->name); + } + } 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 (!bond_has_slaves(bond) && + bond->dev->addr_assign_type == NET_ADDR_RANDOM) + bond_set_dev_addr(bond->dev, slave_dev); + + new_slave = bond_alloc_slave(bond); if (!new_slave) { res = -ENOMEM; goto err_undo_flags; } - memset(new_slave, 0, sizeof(struct slave)); - - /* save slave's original flags before calling - * netdev_set_master and dev_open + new_slave->bond = bond; + new_slave->dev = slave_dev; + /* + * Set the new_slave's queue_id to be zero. Queue ID mapping + * is set via sysfs or module option if desired. */ - new_slave->original_flags = slave_dev->flags; + 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); + ether_addr_copy(new_slave->perm_hwaddr, slave_dev->dev_addr); - /* - * 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) { - dprintk("Error %d calling set_mac_address\n", res); - goto err_free; + if (!bond->params.fail_over_mac || + BOND_MODE(bond) != BOND_MODE_ACTIVEBACKUP) { + /* + * 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; + } } /* open the slave since the application closed it */ res = dev_open(slave_dev); if (res) { - dprintk("Openning slave %s failed\n", slave_dev->name); + pr_debug("Opening slave %s failed\n", slave_dev->name); goto err_restore_mac; } - res = netdev_set_master(slave_dev, bond_dev); - if (res) { - dprintk("Error %d calling netdev_set_master\n", res); - goto err_close; - } - - new_slave->dev = slave_dev; + slave_dev->priv_flags |= IFF_BONDING; - if ((bond->params.mode == BOND_MODE_TLB) || - (bond->params.mode == BOND_MODE_ALB)) { + 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_unset_master; - } + 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 the mode uses primary, then the following is handled by + * bond_change_active_slave(). */ - if (!USES_PRIMARY(bond->params.mode)) { + if (!bond_uses_primary(bond)) { /* set promiscuity level to new slave */ if (bond_dev->flags & IFF_PROMISC) { - dev_set_promiscuity(slave_dev, 1); + res = dev_set_promiscuity(slave_dev, 1); + if (res) + goto err_close; } /* set allmulti level to new slave */ if (bond_dev->flags & IFF_ALLMULTI) { - dev_set_allmulti(slave_dev, 1); + res = dev_set_allmulti(slave_dev, 1); + if (res) + goto err_close; } - /* upload master's mc_list to new slave */ - for (dmi = bond_dev->mc_list; dmi; dmi = dmi->next) { - dev_mc_add (slave_dev, dmi->dmi_addr, dmi->dmi_addrlen, 0); - } + netif_addr_lock_bh(bond_dev); + + dev_mc_sync_multiple(slave_dev, bond_dev); + dev_uc_sync_multiple(slave_dev, bond_dev); + + netif_addr_unlock_bh(bond_dev); } - if (bond->params.mode == BOND_MODE_8023AD) { + if (BOND_MODE(bond) == 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, ETH_ALEN, 0); + dev_mc_add(slave_dev, lacpdu_multicast); } - bond_add_vlans_on_slave(bond, slave_dev); - - write_lock_bh(&bond->lock); + res = vlan_vids_add_by_dev(slave_dev, bond_dev); + if (res) { + pr_err("%s: Error: Couldn't add bond vlan ids to %s\n", + bond_dev->name, slave_dev->name); + goto err_close; + } - bond_attach_slave(bond, new_slave); + prev_slave = bond_last_slave(bond); new_slave->delay = 0; new_slave->link_failure_count = 0; - bond_compute_features(bond); + bond_update_speed_duplex(new_slave); + + new_slave->last_rx = jiffies - + (msecs_to_jiffies(bond->params.arp_interval) + 1); + for (i = 0; i < BOND_MAX_ARP_TARGETS; i++) + new_slave->target_last_arp_rx[i] = new_slave->last_rx; if (bond->params.miimon && !bond->params.use_carrier) { link_reporting = bond_check_dev_link(bond, slave_dev, 1); @@ -1369,176 +1455,205 @@ int bond_enslave(struct net_device *bond_dev, struct net_device *slave_dev) * supported); thus, we don't need to change * the messages for netif_carrier. */ - printk(KERN_WARNING DRV_NAME - ": %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); + pr_warn("%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 */ - printk(KERN_WARNING DRV_NAME - ": %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); + pr_warn("%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) { - dprintk("Initial state of slave_dev is " - "BOND_LINK_BACK\n"); - new_slave->link = BOND_LINK_BACK; - new_slave->delay = bond->params.updelay; + if (bond->params.miimon) { + if (bond_check_dev_link(bond, slave_dev, 0) == BMSR_LSTATUS) { + if (bond->params.updelay) { + new_slave->link = BOND_LINK_BACK; + new_slave->delay = bond->params.updelay; + } else { + new_slave->link = BOND_LINK_UP; + } } else { - dprintk("Initial state of slave_dev is " - "BOND_LINK_UP\n"); - new_slave->link = BOND_LINK_UP; + new_slave->link = BOND_LINK_DOWN; } - new_slave->jiffies = jiffies; + } else if (bond->params.arp_interval) { + new_slave->link = (netif_carrier_ok(slave_dev) ? + BOND_LINK_UP : BOND_LINK_DOWN); } else { - dprintk("Initial state of slave_dev is " - "BOND_LINK_DOWN\n"); - new_slave->link = BOND_LINK_DOWN; - } - - if (bond_update_speed_duplex(new_slave) && - (new_slave->link != BOND_LINK_DOWN)) { - printk(KERN_WARNING DRV_NAME - ": %s: Warning: failed to get speed and duplex from %s, " - "assumed to be 100Mb/sec and Full.\n", - bond_dev->name, new_slave->dev->name); - - if (bond->params.mode == BOND_MODE_8023AD) { - printk(KERN_WARNING DRV_NAME - ": %s: Warning: Operation of 802.3ad mode requires ETHTOOL " - "support in base driver for proper aggregator " - "selection.\n", bond_dev->name); - } + new_slave->link = BOND_LINK_UP; } - if (USES_PRIMARY(bond->params.mode) && bond->params.primary[0]) { + if (new_slave->link != BOND_LINK_DOWN) + new_slave->last_link_up = jiffies; + pr_debug("Initial state of slave_dev is BOND_LINK_%s\n", + new_slave->link == BOND_LINK_DOWN ? "DOWN" : + (new_slave->link == BOND_LINK_UP ? "UP" : "BACK")); + + if (bond_uses_primary(bond) && 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; } } - switch (bond->params.mode) { + switch (BOND_MODE(bond)) { case BOND_MODE_ACTIVEBACKUP: - /* if we're in active-backup mode, we need one and only one active - * interface. The backup interfaces will have their NOARP flag set - * because we need them to be completely deaf and not to respond to - * any ARP request on the network to avoid fooling a switch. Thus, - * since we guarantee that curr_active_slave always point to the last - * usable interface, we just have to verify this interface's flag. - */ - if (((!bond->curr_active_slave) || - (bond->curr_active_slave->dev->flags & IFF_NOARP)) && - (new_slave->link != BOND_LINK_DOWN)) { - dprintk("This is the first active slave\n"); - /* first slave or no active slave yet, and this link - is OK, so make this interface the active one */ - bond_change_active_slave(bond, new_slave); - } else { - dprintk("This is just a backup slave\n"); - bond_set_slave_inactive_flags(new_slave); - } + bond_set_slave_inactive_flags(new_slave, + BOND_SLAVE_NOTIFY_NOW); 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); + bond_set_slave_inactive_flags(new_slave, BOND_SLAVE_NOTIFY_NOW); /* if this is the first slave */ - if (bond->slave_cnt == 1) { - SLAVE_AD_INFO(new_slave).id = 1; + if (!prev_slave) { + 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, - bond->params.lacp_fast); + bond_3ad_initialize(bond, 1000/AD_TIMER_INTERVAL); } else { - SLAVE_AD_INFO(new_slave).id = - SLAVE_AD_INFO(new_slave->prev).id + 1; + SLAVE_AD_INFO(new_slave)->id = + SLAVE_AD_INFO(prev_slave)->id + 1; } bond_3ad_bind_slave(new_slave); break; case BOND_MODE_TLB: case BOND_MODE_ALB: - new_slave->state = BOND_STATE_ACTIVE; - if ((!bond->curr_active_slave) && - (new_slave->link != BOND_LINK_DOWN)) { - /* first slave or no active slave yet, and this link - * is OK, so make this interface the active one - */ - bond_change_active_slave(bond, new_slave); - } + bond_set_active_slave(new_slave); + bond_set_slave_inactive_flags(new_slave, BOND_SLAVE_NOTIFY_NOW); break; default: - dprintk("This slave is always active in trunk mode\n"); + pr_debug("This slave is always active in trunk mode\n"); /* always active in trunk mode */ - new_slave->state = BOND_STATE_ACTIVE; + 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; - } + if (!bond->curr_active_slave && new_slave->link == BOND_LINK_UP) + rcu_assign_pointer(bond->curr_active_slave, new_slave); + break; } /* switch(bond_mode) */ - write_unlock_bh(&bond->lock); +#ifdef CONFIG_NET_POLL_CONTROLLER + slave_dev->npinfo = bond->dev->npinfo; + if (slave_dev->npinfo) { + if (slave_enable_netpoll(new_slave)) { + 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 - res = bond_create_slave_symlinks(bond_dev, slave_dev); - if (res) - goto err_unset_master; + 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_detach; + } + + res = bond_master_upper_dev_link(bond_dev, slave_dev, new_slave); + if (res) { + pr_debug("Error %d calling bond_master_upper_dev_link\n", res); + goto err_unregister; + } + + res = bond_sysfs_slave_add(new_slave); + if (res) { + pr_debug("Error %d calling bond_sysfs_slave_add\n", res); + goto err_upper_unlink; + } + + bond->slave_cnt++; + bond_compute_features(bond); + bond_set_carrier(bond); + + if (bond_uses_primary(bond)) { + 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(); + } - printk(KERN_INFO DRV_NAME - ": %s: enslaving %s as a%s interface with a%s link.\n", - bond_dev->name, slave_dev->name, - new_slave->state == BOND_STATE_ACTIVE ? "n active" : " backup", - new_slave->link != BOND_LINK_DOWN ? "n up" : " down"); + pr_info("%s: Enslaving %s as %s interface with %s link\n", + bond_dev->name, slave_dev->name, + bond_is_active_slave(new_slave) ? "an active" : "a backup", + new_slave->link != BOND_LINK_DOWN ? "an up" : "a down"); /* enslave is successful */ return 0; /* Undo stages on error */ -err_unset_master: - netdev_set_master(slave_dev, NULL); +err_upper_unlink: + bond_upper_dev_unlink(bond_dev, slave_dev); + +err_unregister: + netdev_rx_handler_unregister(slave_dev); + +err_detach: + if (!bond_uses_primary(bond)) + bond_hw_addr_flush(bond_dev, slave_dev); + + vlan_vids_del_by_dev(slave_dev, bond_dev); + if (bond->primary_slave == new_slave) + bond->primary_slave = NULL; + if (bond->curr_active_slave == new_slave) { + block_netpoll_tx(); + write_lock_bh(&bond->curr_slave_lock); + bond_change_active_slave(bond, NULL); + bond_select_active_slave(bond); + write_unlock_bh(&bond->curr_slave_lock); + unblock_netpoll_tx(); + } + slave_disable_netpoll(new_slave); err_close: + slave_dev->priv_flags &= ~IFF_BONDING; dev_close(slave_dev); err_restore_mac: - memcpy(addr.sa_data, new_slave->perm_hwaddr, ETH_ALEN); - addr.sa_family = slave_dev->type; - dev_set_mac_address(slave_dev, &addr); + if (!bond->params.fail_over_mac || + BOND_MODE(bond) != BOND_MODE_ACTIVEBACKUP) { + /* 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. + */ + ether_addr_copy(addr.sa_data, new_slave->perm_hwaddr); + 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); + bond_free_slave(new_slave); err_undo_flags: - bond_dev->features = old_features; - + /* Enslave of first slave has failed and we need to fix master's mac */ + if (!bond_has_slaves(bond) && + ether_addr_equal_64bits(bond_dev->dev_addr, slave_dev->dev_addr)) + eth_hw_addr_random(bond_dev); + 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. + * is write-locked. If "all" is true it means that the function is being called + * while destroying a bond interface and all slaves are being released. * * The rules for slave state should be: * for Active/Backup: @@ -1546,89 +1661,79 @@ err_undo_flags: * 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) +static int __bond_release_one(struct net_device *bond_dev, + struct net_device *slave_dev, + bool all) { - struct bonding *bond = bond_dev->priv; + struct bonding *bond = netdev_priv(bond_dev); struct slave *slave, *oldcurrent; struct sockaddr addr; - int mac_addr_differ; + int old_flags = bond_dev->flags; + 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)) { - printk(KERN_ERR DRV_NAME - ": %s: Error: cannot release %s.\n", + !netdev_has_upper_dev(slave_dev, bond_dev)) { + pr_err("%s: Error: cannot release %s\n", bond_dev->name, slave_dev->name); return -EINVAL; } - write_lock_bh(&bond->lock); + block_netpoll_tx(); slave = bond_get_slave_by_dev(bond, slave_dev); if (!slave) { /* not a slave of this bond */ - printk(KERN_INFO DRV_NAME - ": %s: %s not enslaved\n", - bond_dev->name, slave_dev->name); + pr_info("%s: %s not enslaved\n", + bond_dev->name, slave_dev->name); + unblock_netpoll_tx(); return -EINVAL; } - mac_addr_differ = memcmp(bond_dev->dev_addr, - slave->perm_hwaddr, - ETH_ALEN); - if (!mac_addr_differ && (bond->slave_cnt > 1)) { - printk(KERN_WARNING DRV_NAME - ": %s: Warning: the permanent HWaddr of %s " - "- %02X:%02X:%02X:%02X:%02X:%02X - 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[0], - slave->perm_hwaddr[1], - slave->perm_hwaddr[2], - slave->perm_hwaddr[3], - slave->perm_hwaddr[4], - slave->perm_hwaddr[5], - bond_dev->name, - slave_dev->name); - } + bond_sysfs_slave_del(slave); + + bond_upper_dev_unlink(bond_dev, slave_dev); + /* unregister rx_handler early so bond_handle_frame wouldn't be called + * for this slave anymore. + */ + netdev_rx_handler_unregister(slave_dev); + write_lock_bh(&bond->lock); /* 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 - */ + if (BOND_MODE(bond) == BOND_MODE_8023AD) bond_3ad_unbind_slave(slave); - } - printk(KERN_INFO DRV_NAME - ": %s: releasing %s interface %s\n", - bond_dev->name, - (slave->state == BOND_STATE_ACTIVE) - ? "active" : "backup", - slave_dev->name); + write_unlock_bh(&bond->lock); + + 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); - - bond_compute_features(bond); + if (!all && (!bond->params.fail_over_mac || + BOND_MODE(bond) != BOND_MODE_ACTIVEBACKUP)) { + if (ether_addr_equal_64bits(bond_dev->dev_addr, slave->perm_hwaddr) && + bond_has_slaves(bond)) + pr_warn("%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); + } - if (bond->primary_slave == slave) { + if (bond->primary_slave == slave) bond->primary_slave = NULL; - } if (oldcurrent == slave) { + write_lock_bh(&bond->curr_slave_lock); bond_change_active_slave(bond, NULL); + write_unlock_bh(&bond->curr_slave_lock); } - if ((bond->params.mode == BOND_MODE_TLB) || - (bond->params.mode == BOND_MODE_ALB)) { + 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), @@ -1637,606 +1742,420 @@ int bond_release(struct net_device *bond_dev, struct net_device *slave_dev) bond_alb_deinit_slave(bond, slave); } - if (oldcurrent == slave) { + if (all) { + RCU_INIT_POINTER(bond->curr_active_slave, NULL); + } else 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_lock_bh(&bond->curr_slave_lock); + bond_select_active_slave(bond); - if (!bond->curr_active_slave) { - printk(KERN_INFO DRV_NAME - ": %s: now running without any active " - "interface !\n", - bond_dev->name); - } + write_unlock_bh(&bond->curr_slave_lock); } - if (bond->slave_cnt == 0) { - /* 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_has_slaves(bond)) { + bond_set_carrier(bond); + eth_hw_addr_random(bond_dev); - if (list_empty(&bond->vlan_list)) { - bond_dev->features |= NETIF_F_VLAN_CHALLENGED; - } else { - printk(KERN_WARNING DRV_NAME - ": %s: Warning: clearing HW address of %s while it " - "still has VLANs.\n", - bond_dev->name, bond_dev->name); - printk(KERN_WARNING DRV_NAME - ": %s: When re-adding slaves, make sure the bond's " - "HW address matches its VLANs'.\n", - bond_dev->name); + if (vlan_uses_dev(bond_dev)) { + pr_warn("%s: Warning: clearing HW address of %s while it still has VLANs\n", + bond_dev->name, bond_dev->name); + pr_warn("%s: When re-adding slaves, make sure the bond's HW address matches its VLANs\n", + bond_dev->name); } - } else if ((bond_dev->features & NETIF_F_VLAN_CHALLENGED) && - !bond_has_challenged_slaves(bond)) { - printk(KERN_INFO DRV_NAME - ": %s: last VLAN challenged slave %s " - "left bond %s. VLAN blocking is removed\n", - bond_dev->name, slave_dev->name, bond_dev->name); - bond_dev->features &= ~NETIF_F_VLAN_CHALLENGED; } - write_unlock_bh(&bond->lock); + unblock_netpoll_tx(); + synchronize_rcu(); + bond->slave_cnt--; - /* must do this from outside any spinlocks */ - bond_destroy_slave_symlinks(bond_dev, slave_dev); + if (!bond_has_slaves(bond)) { + call_netdevice_notifiers(NETDEV_CHANGEADDR, bond->dev); + call_netdevice_notifiers(NETDEV_RELEASE, bond->dev); + } - bond_del_vlans_from_slave(bond, slave_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 */ + vlan_vids_del_by_dev(slave_dev, bond_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 the mode uses primary, then this cases was handled above by + * bond_change_active_slave(..., NULL) */ - if (!USES_PRIMARY(bond->params.mode)) { - /* unset promiscuity level from slave */ - if (bond_dev->flags & IFF_PROMISC) { + if (!bond_uses_primary(bond)) { + /* unset promiscuity level from slave + * NOTE: The NETDEV_CHANGEADDR call above may change the value + * of the IFF_PROMISC flag in the bond_dev, but we need the + * value of that flag before that change, as that was the value + * when this slave was attached, so we cache at the start of the + * function and use it here. Same goes for ALLMULTI below + */ + if (old_flags & IFF_PROMISC) dev_set_promiscuity(slave_dev, -1); - } /* unset allmulti level from slave */ - if (bond_dev->flags & IFF_ALLMULTI) { + if (old_flags & IFF_ALLMULTI) dev_set_allmulti(slave_dev, -1); - } - /* flush master's mc_list from slave */ - bond_mc_list_flush(bond_dev, slave_dev); + bond_hw_addr_flush(bond_dev, slave_dev); } - netdev_set_master(slave_dev, NULL); + slave_disable_netpoll(slave); /* close slave before restoring its mac address */ dev_close(slave_dev); - /* 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); - - /* restore the original state of the - * IFF_NOARP flag that might have been - * set by bond_set_slave_inactive_flags() - */ - if ((slave->original_flags & IFF_NOARP) == 0) { - slave_dev->flags &= ~IFF_NOARP; - } - - kfree(slave); - - return 0; /* deletion OK */ -} - -/* - * This function releases all slaves. - */ -static int bond_release_all(struct net_device *bond_dev) -{ - struct bonding *bond = bond_dev->priv; - struct slave *slave; - struct net_device *slave_dev; - struct sockaddr addr; - - write_lock_bh(&bond->lock); - - 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); - - if ((bond->params.mode == BOND_MODE_TLB) || - (bond->params.mode == BOND_MODE_ALB)) { - /* must be called only after the slave - * has been detached from the list - */ - bond_alb_deinit_slave(bond, slave); - } - - bond_compute_features(bond); - - /* 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); - - 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 */ - bond_mc_list_flush(bond_dev, slave_dev); - } - - netdev_set_master(slave_dev, NULL); - - /* close slave before restoring its mac address */ - dev_close(slave_dev); - - /* restore original ("permanent") mac address*/ - memcpy(addr.sa_data, slave->perm_hwaddr, ETH_ALEN); + if (bond->params.fail_over_mac != BOND_FOM_ACTIVE || + BOND_MODE(bond) != BOND_MODE_ACTIVEBACKUP) { + /* restore original ("permanent") mac address */ + ether_addr_copy(addr.sa_data, slave->perm_hwaddr); addr.sa_family = slave_dev->type; dev_set_mac_address(slave_dev, &addr); - - /* restore the original state of the IFF_NOARP flag that might have - * been set by bond_set_slave_inactive_flags() - */ - if ((slave->original_flags & IFF_NOARP) == 0) { - slave_dev->flags &= ~IFF_NOARP; - } - - 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); + dev_set_mtu(slave_dev, slave->original_mtu); - if (list_empty(&bond->vlan_list)) { - bond_dev->features |= NETIF_F_VLAN_CHALLENGED; - } else { - printk(KERN_WARNING DRV_NAME - ": %s: Warning: clearing HW address of %s while it " - "still has VLANs.\n", - bond_dev->name, bond_dev->name); - printk(KERN_WARNING DRV_NAME - ": %s: When re-adding slaves, make sure the bond's " - "HW address matches its VLANs'.\n", - bond_dev->name); - } + slave_dev->priv_flags &= ~IFF_BONDING; - printk(KERN_INFO DRV_NAME - ": %s: released all slaves\n", - bond_dev->name); + bond_free_slave(slave); -out: - write_unlock_bh(&bond->lock); + return 0; /* deletion OK */ +} - return 0; +/* A wrapper used because of ndo_del_link */ +int bond_release(struct net_device *bond_dev, struct net_device *slave_dev) +{ + return __bond_release_one(bond_dev, slave_dev, false); } /* - * 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 fuction does nothing. - * In the other cases, currnt_slave pointer is changed and 0 is returned. - */ -static int bond_ioctl_change_active(struct net_device *bond_dev, struct net_device *slave_dev) +* 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 = bond_dev->priv; - 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; - } - - write_lock_bh(&bond->lock); - - old_active = bond->curr_active_slave; - 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)) { - write_unlock_bh(&bond->lock); - return 0; - } - - if ((new_active) && - (old_active) && - (new_active->link == BOND_LINK_UP) && - IS_UP(new_active->dev)) { - bond_change_active_slave(bond, new_active); - } else { - res = -EINVAL; + struct bonding *bond = netdev_priv(bond_dev); + int ret; + + ret = bond_release(bond_dev, slave_dev); + if (ret == 0 && !bond_has_slaves(bond)) { + bond_dev->priv_flags |= IFF_DISABLE_NETPOLL; + pr_info("%s: Destroying bond %s\n", + bond_dev->name, bond_dev->name); + unregister_netdevice(bond_dev); } - - write_unlock_bh(&bond->lock); - - return res; + return ret; } static int bond_info_query(struct net_device *bond_dev, struct ifbond *info) { - struct bonding *bond = bond_dev->priv; + struct bonding *bond = netdev_priv(bond_dev); - info->bond_mode = bond->params.mode; + info->bond_mode = BOND_MODE(bond); info->miimon = bond->params.miimon; - read_lock_bh(&bond->lock); info->num_slaves = bond->slave_cnt; - read_unlock_bh(&bond->lock); return 0; } static int bond_slave_info_query(struct net_device *bond_dev, struct ifslave *info) { - struct bonding *bond = bond_dev->priv; + struct bonding *bond = netdev_priv(bond_dev); + struct list_head *iter; + int i = 0, res = -ENODEV; struct slave *slave; - int i, found = 0; - if (info->slave_id < 0) { - return -ENODEV; - } - - read_lock_bh(&bond->lock); - - bond_for_each_slave(bond, slave, i) { - if (i == (int)info->slave_id) { - found = 1; + bond_for_each_slave(bond, slave, iter) { + 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_bh(&bond->lock); - - if (found) { - strcpy(info->slave_name, slave->dev->name); - info->link = slave->link; - info->state = slave->state; - info->link_failure_count = slave->link_failure_count; - } else { - return -ENODEV; - } - - return 0; + return res; } /*-------------------------------- Monitoring -------------------------------*/ -/* this function is called regularly to monitor each slave's link. */ -void bond_mii_monitor(struct net_device *bond_dev) + +static int bond_miimon_inspect(struct bonding *bond) { - struct bonding *bond = bond_dev->priv; - struct slave *slave, *oldcurrent; - int do_failover = 0; - int delta_in_ticks; - int i; + int link_state, commit = 0; + struct list_head *iter; + struct slave *slave; + bool ignore_updelay; - read_lock(&bond->lock); + ignore_updelay = !bond->curr_active_slave ? true : false; - delta_in_ticks = (bond->params.miimon * HZ) / 1000; + bond_for_each_slave_rcu(bond, slave, iter) { + slave->new_link = BOND_LINK_NOCHANGE; - if (bond->kill_timers) { - goto out; - } + link_state = bond_check_dev_link(bond, slave->dev, 0); - if (bond->slave_cnt == 0) { - goto re_arm; - } + switch (slave->link) { + case BOND_LINK_UP: + if (link_state) + continue; - /* we will try to read the link status of each of our slaves, and - * set their IFF_RUNNING flag appropriately. For each slave not - * supporting MII status, we won't do anything so that a user-space - * program could monitor the link itself if needed. - */ + 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_MODE(bond) == + 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->last_link_up = 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; + } - read_lock(&bond->curr_slave_lock); - oldcurrent = bond->curr_active_slave; - read_unlock(&bond->curr_slave_lock); + if (slave->delay <= 0) { + slave->new_link = BOND_LINK_DOWN; + commit++; + continue; + } - bond_for_each_slave(bond, slave, i) { - struct net_device *slave_dev = slave->dev; - int link_state; - u16 old_speed = slave->speed; - u8 old_duplex = slave->duplex; + slave->delay--; + break; - link_state = bond_check_dev_link(bond, slave_dev, 0); + case BOND_LINK_DOWN: + if (!link_state) + continue; - switch (slave->link) { - case BOND_LINK_UP: /* the link was up */ - if (link_state == BMSR_LSTATUS) { - /* link stays up, nothing more to do */ - break; - } else { /* link going down */ - slave->link = BOND_LINK_FAIL; - slave->delay = bond->params.downdelay; - - if (slave->link_failure_count < UINT_MAX) { - slave->link_failure_count++; - } + slave->link = BOND_LINK_BACK; + slave->delay = bond->params.updelay; - if (bond->params.downdelay) { - printk(KERN_INFO DRV_NAME - ": %s: link status down for %s " - "interface %s, disabling it in " - "%d ms.\n", - bond_dev->name, - IS_UP(slave_dev) - ? ((bond->params.mode == BOND_MODE_ACTIVEBACKUP) - ? ((slave == oldcurrent) - ? "active " : "backup ") - : "") - : "idle ", - slave_dev->name, - bond->params.downdelay * bond->params.miimon); - } + 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); } - /* no break ! fall through the BOND_LINK_FAIL test to - ensure proper action to be taken - */ - case BOND_LINK_FAIL: /* the link has just gone down */ - if (link_state != BMSR_LSTATUS) { - /* link stays down */ - if (slave->delay <= 0) { - /* link down for too long time */ - slave->link = BOND_LINK_DOWN; - - /* in active/backup mode, we must - * completely disable this interface - */ - if ((bond->params.mode == BOND_MODE_ACTIVEBACKUP) || - (bond->params.mode == BOND_MODE_8023AD)) { - bond_set_slave_inactive_flags(slave); - } - - printk(KERN_INFO DRV_NAME - ": %s: link status definitely " - "down for interface %s, " - "disabling it\n", - bond_dev->name, - slave_dev->name); - - /* notify ad that the link status has changed */ - if (bond->params.mode == BOND_MODE_8023AD) { - bond_3ad_handle_link_change(slave, BOND_LINK_DOWN); - } - - if ((bond->params.mode == BOND_MODE_TLB) || - (bond->params.mode == BOND_MODE_ALB)) { - bond_alb_handle_link_change(bond, slave, BOND_LINK_DOWN); - } - - if (slave == oldcurrent) { - do_failover = 1; - } - } else { - slave->delay--; - } - } else { - /* link up again */ - slave->link = BOND_LINK_UP; - slave->jiffies = jiffies; - printk(KERN_INFO DRV_NAME - ": %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); - } - break; - case BOND_LINK_DOWN: /* the link was down */ - if (link_state != BMSR_LSTATUS) { - /* the link stays down, nothing more to do */ - break; - } else { /* link going up */ - slave->link = BOND_LINK_BACK; - slave->delay = bond->params.updelay; - - if (bond->params.updelay) { - /* if updelay == 0, no need to - advertise about a 0 ms delay */ - printk(KERN_INFO DRV_NAME - ": %s: link status up for " - "interface %s, enabling it " - "in %d ms.\n", - bond_dev->name, - slave_dev->name, - 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; } - /* no break ! fall through the BOND_LINK_BACK state in - case there's something to do. - */ - case BOND_LINK_BACK: /* the link has just come back */ - if (link_state != BMSR_LSTATUS) { - /* link down again */ - slave->link = BOND_LINK_DOWN; - printk(KERN_INFO DRV_NAME - ": %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); - } else { - /* link stays up */ - if (slave->delay == 0) { - /* now the link has been up for long time enough */ - slave->link = BOND_LINK_UP; - slave->jiffies = jiffies; - - if (bond->params.mode == BOND_MODE_8023AD) { - /* prevent it from being the active one */ - slave->state = BOND_STATE_BACKUP; - } else if (bond->params.mode != BOND_MODE_ACTIVEBACKUP) { - /* make it immediately active */ - slave->state = BOND_STATE_ACTIVE; - } else if (slave != bond->primary_slave) { - /* prevent it from being the active one */ - slave->state = BOND_STATE_BACKUP; - } - - printk(KERN_INFO DRV_NAME - ": %s: link status definitely " - "up for interface %s.\n", - bond_dev->name, - slave_dev->name); - - /* 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->params.mode == BOND_MODE_TLB) || - (bond->params.mode == BOND_MODE_ALB)) { - bond_alb_handle_link_change(bond, slave, BOND_LINK_UP); - } - - if ((!oldcurrent) || - (slave == bond->primary_slave)) { - do_failover = 1; - } - } else { - slave->delay--; - } + if (ignore_updelay) + slave->delay = 0; + + if (slave->delay <= 0) { + slave->new_link = BOND_LINK_UP; + commit++; + ignore_updelay = false; + continue; } + + slave->delay--; break; - default: - /* Should not happen */ - printk(KERN_ERR DRV_NAME - ": %s: Error: %s Illegal value (link=%d)\n", - bond_dev->name, - slave->dev->name, - slave->link); - goto out; - } /* end of switch (slave->link) */ + } + } - bond_update_speed_duplex(slave); + return commit; +} - if (bond->params.mode == BOND_MODE_8023AD) { - if (old_speed != slave->speed) { - bond_3ad_adapter_speed_changed(slave); - } +static void bond_miimon_commit(struct bonding *bond) +{ + struct list_head *iter; + struct slave *slave; - if (old_duplex != slave->duplex) { - bond_3ad_adapter_duplex_changed(slave); + bond_for_each_slave(bond, slave, iter) { + switch (slave->new_link) { + case BOND_LINK_NOCHANGE: + continue; + + case BOND_LINK_UP: + slave->link = BOND_LINK_UP; + slave->last_link_up = jiffies; + + if (BOND_MODE(bond) == BOND_MODE_8023AD) { + /* prevent it from being the active one */ + bond_set_backup_slave(slave); + } else if (BOND_MODE(bond) != 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); } - } - } /* end of for */ + pr_info("%s: link status definitely up for interface %s, %u Mbps %s duplex\n", + bond->dev->name, slave->dev->name, + slave->speed == SPEED_UNKNOWN ? 0 : slave->speed, + slave->duplex ? "full" : "half"); - if (do_failover) { - write_lock(&bond->curr_slave_lock); + /* notify ad that the link status has changed */ + if (BOND_MODE(bond) == BOND_MODE_8023AD) + bond_3ad_handle_link_change(slave, BOND_LINK_UP); - bond_select_active_slave(bond); + if (bond_is_lb(bond)) + bond_alb_handle_link_change(bond, slave, + BOND_LINK_UP); - if (oldcurrent && !bond->curr_active_slave) { - printk(KERN_INFO DRV_NAME - ": %s: now running without any active " - "interface !\n", - bond_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; + + if (BOND_MODE(bond) == BOND_MODE_ACTIVEBACKUP || + BOND_MODE(bond) == BOND_MODE_8023AD) + bond_set_slave_inactive_flags(slave, + BOND_SLAVE_NOTIFY_NOW); + + pr_info("%s: link status definitely down for interface %s, disabling it\n", + bond->dev->name, slave->dev->name); + + if (BOND_MODE(bond) == 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; } - write_unlock(&bond->curr_slave_lock); +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(); } -re_arm: - if (bond->params.miimon) { - mod_timer(&bond->mii_timer, jiffies + delta_in_ticks); - } -out: - read_unlock(&bond->lock); + bond_set_carrier(bond); } - -static u32 bond_glean_dev_ip(struct net_device *dev) +/* + * 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. + */ +static void bond_mii_monitor(struct work_struct *work) { - struct in_device *idev; - struct in_ifaddr *ifa; - u32 addr = 0; + struct bonding *bond = container_of(work, struct bonding, + mii_work.work); + bool should_notify_peers = false; + unsigned long delay; - if (!dev) - return 0; + delay = msecs_to_jiffies(bond->params.miimon); + + if (!bond_has_slaves(bond)) + goto re_arm; rcu_read_lock(); - idev = __in_dev_get_rcu(dev); - if (!idev) - goto out; - ifa = idev->ifa_list; - if (!ifa) - goto out; + should_notify_peers = bond_should_notify_peers(bond); - addr = ifa->ifa_local; -out: - rcu_read_unlock(); - return addr; + if (bond_miimon_inspect(bond)) { + rcu_read_unlock(); + + /* Race avoidance with bond_close cancel of workqueue */ + if (!rtnl_trylock()) { + delay = 1; + should_notify_peers = false; + goto re_arm; + } + + bond_miimon_commit(bond); + + rtnl_unlock(); /* might sleep, hold no other locks */ + } else + rcu_read_unlock(); + +re_arm: + if (bond->params.miimon) + queue_delayed_work(bond->wq, &bond->mii_work, delay); + + if (should_notify_peers) { + if (!rtnl_trylock()) + return; + call_netdevice_notifiers(NETDEV_NOTIFY_PEERS, bond->dev); + rtnl_unlock(); + } } -static int bond_has_ip(struct bonding *bond) +static bool bond_has_this_ip(struct bonding *bond, __be32 ip) { - struct vlan_entry *vlan, *vlan_next; + struct net_device *upper; + struct list_head *iter; + bool ret = false; - if (bond->master_ip) - return 1; - - if (list_empty(&bond->vlan_list)) - return 0; + if (ip == bond_confirm_addr(bond->dev, 0, ip)) + return true; - list_for_each_entry_safe(vlan, vlan_next, &bond->vlan_list, - vlan_list) { - if (vlan->vlan_ip) - return 1; + rcu_read_lock(); + netdev_for_each_all_upper_dev_rcu(bond->dev, upper, iter) { + if (ip == bond_confirm_addr(upper, 0, ip)) { + ret = true; + break; + } } + rcu_read_unlock(); - return 0; + return ret; } /* @@ -2244,137 +2163,250 @@ static int bond_has_ip(struct bonding *bond) * 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, u32 dest_ip, u32 src_ip, unsigned short vlan_id) +static void bond_arp_send(struct net_device *slave_dev, int arp_op, + __be32 dest_ip, __be32 src_ip, + struct bond_vlan_tag *tags) { struct sk_buff *skb; + int i; + + pr_debug("arp %d on slave %s: dst %pI4 src %pI4\n", + arp_op, slave_dev->name, &dest_ip, &src_ip); - dprintk("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) { - printk(KERN_ERR DRV_NAME ": ARP packet allocation failed\n"); + net_err_ratelimited("ARP packet allocation failed\n"); return; } - if (vlan_id) { - skb = vlan_put_tag(skb, vlan_id); + + /* Go through all the tags backwards and add them to the packet */ + for (i = BOND_MAX_VLAN_ENCAP - 1; i > 0; i--) { + if (!tags[i].vlan_id) + continue; + + pr_debug("inner tag: proto %X vid %X\n", + ntohs(tags[i].vlan_proto), tags[i].vlan_id); + skb = __vlan_put_tag(skb, tags[i].vlan_proto, + tags[i].vlan_id); if (!skb) { - printk(KERN_ERR DRV_NAME ": failed to insert VLAN tag\n"); + net_err_ratelimited("failed to insert inner VLAN tag\n"); + return; + } + } + /* Set the outer tag */ + if (tags[0].vlan_id) { + pr_debug("outer tag: proto %X vid %X\n", + ntohs(tags[0].vlan_proto), tags[0].vlan_id); + skb = vlan_put_tag(skb, tags[0].vlan_proto, tags[0].vlan_id); + if (!skb) { + net_err_ratelimited("failed to insert outer VLAN tag\n"); return; } } arp_xmit(skb); } +/* Validate the device path between the @start_dev and the @end_dev. + * The path is valid if the @end_dev is reachable through device + * stacking. + * When the path is validated, collect any vlan information in the + * path. + */ +bool bond_verify_device_path(struct net_device *start_dev, + struct net_device *end_dev, + struct bond_vlan_tag *tags) +{ + struct net_device *upper; + struct list_head *iter; + int idx; + + if (start_dev == end_dev) + return true; + + netdev_for_each_upper_dev_rcu(start_dev, upper, iter) { + if (bond_verify_device_path(upper, end_dev, tags)) { + if (is_vlan_dev(upper)) { + idx = vlan_get_encap_level(upper); + if (idx >= BOND_MAX_VLAN_ENCAP) + return false; + + tags[idx].vlan_proto = + vlan_dev_vlan_proto(upper); + tags[idx].vlan_id = vlan_dev_vlan_id(upper); + } + return true; + } + } + + return false; +} static void bond_arp_send_all(struct bonding *bond, struct slave *slave) { - int i, vlan_id, rv; - u32 *targets = bond->params.arp_targets; - struct vlan_entry *vlan, *vlan_next; - struct net_device *vlan_dev; - struct flowi fl; struct rtable *rt; - - for (i = 0; (i < BOND_MAX_ARP_TARGETS); i++) { - if (!targets[i]) - continue; - dprintk("basa: target %x\n", targets[i]); - if (list_empty(&bond->vlan_list)) { - dprintk("basa: empty vlan: arp_send\n"); + struct bond_vlan_tag tags[BOND_MAX_VLAN_ENCAP]; + __be32 *targets = bond->params.arp_targets, addr; + int i; + bool ret; + + for (i = 0; i < BOND_MAX_ARP_TARGETS && targets[i]; i++) { + pr_debug("basa: target %pI4\n", &targets[i]); + memset(tags, 0, sizeof(tags)); + + /* Find out through which dev should the packet go */ + rt = ip_route_output(dev_net(bond->dev), targets[i], 0, + RTO_ONLINK, 0); + if (IS_ERR(rt)) { + /* there's no route to target - try to send arp + * probe to generate any traffic (arp_validate=0) + */ + if (bond->params.arp_validate) + net_warn_ratelimited("%s: no route to arp_ip_target %pI4 and arp_validate is set\n", + bond->dev->name, + &targets[i]); bond_arp_send(slave->dev, ARPOP_REQUEST, targets[i], - bond->master_ip, 0); + 0, tags); 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. - */ - memset(&fl, 0, sizeof(fl)); - fl.fl4_dst = targets[i]; - fl.fl4_tos = RTO_ONLINK; + /* bond device itself */ + if (rt->dst.dev == bond->dev) + goto found; - rv = ip_route_output_key(&rt, &fl); - if (rv) { - if (net_ratelimit()) { - printk(KERN_WARNING DRV_NAME - ": %s: no route to arp_ip_target %u.%u.%u.%u\n", - bond->dev->name, NIPQUAD(fl.fl4_dst)); - } - continue; - } + rcu_read_lock(); + ret = bond_verify_device_path(bond->dev, rt->dst.dev, tags); + rcu_read_unlock(); - /* - * This target is not on a VLAN - */ - if (rt->u.dst.dev == bond->dev) { - ip_rt_put(rt); - dprintk("basa: rtdev == bond->dev: arp_send\n"); - bond_arp_send(slave->dev, ARPOP_REQUEST, targets[i], - bond->master_ip, 0); - continue; - } + if (ret) + goto found; - vlan_id = 0; - list_for_each_entry_safe(vlan, vlan_next, &bond->vlan_list, - vlan_list) { - vlan_dev = bond->vlgrp->vlan_devices[vlan->vlan_id]; - if (vlan_dev == rt->u.dst.dev) { - vlan_id = vlan->vlan_id; - dprintk("basa: vlan match on %s %d\n", - vlan_dev->name, vlan_id); - break; - } - } + /* Not our device - skip */ + pr_debug("%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"); - if (vlan_id) { - ip_rt_put(rt); - bond_arp_send(slave->dev, ARPOP_REQUEST, targets[i], - vlan->vlan_ip, vlan_id); - continue; - } + ip_rt_put(rt); + continue; - if (net_ratelimit()) { - printk(KERN_WARNING DRV_NAME - ": %s: no path to arp_ip_target %u.%u.%u.%u via rt.dev %s\n", - bond->dev->name, NIPQUAD(fl.fl4_dst), - rt->u.dst.dev ? rt->u.dst.dev->name : "NULL"); - } +found: + addr = bond_confirm_addr(rt->dst.dev, targets[i], 0); ip_rt_put(rt); + bond_arp_send(slave->dev, ARPOP_REQUEST, targets[i], + addr, tags); } } -/* - * Kick out a gratuitous ARP for an IP on the bonding master plus one - * for each VLAN above us. - */ -static void bond_send_gratuitous_arp(struct bonding *bond) +static void bond_validate_arp(struct bonding *bond, struct slave *slave, __be32 sip, __be32 tip) { - struct slave *slave = bond->curr_active_slave; - struct vlan_entry *vlan; - struct net_device *vlan_dev; + int i; - dprintk("bond_send_grat_arp: bond %s slave %s\n", bond->dev->name, - slave ? slave->dev->name : "NULL"); - if (!slave) + if (!sip || !bond_has_this_ip(bond, tip)) { + pr_debug("bva: sip %pI4 tip %pI4 not found\n", &sip, &tip); return; - - if (bond->master_ip) { - bond_arp_send(slave->dev, ARPOP_REPLY, bond->master_ip, - bond->master_ip, 0); } - list_for_each_entry(vlan, &bond->vlan_list, vlan_list) { - vlan_dev = bond->vlgrp->vlan_devices[vlan->vlan_id]; - if (vlan->vlan_ip) { - bond_arp_send(slave->dev, ARPOP_REPLY, vlan->vlan_ip, - vlan->vlan_ip, vlan->vlan_id); - } + i = bond_get_targets_ip(bond->params.arp_targets, sip); + if (i == -1) { + pr_debug("bva: sip %pI4 not found in targets\n", &sip); + return; } + slave->last_rx = jiffies; + slave->target_last_arp_rx[i] = jiffies; +} + +int bond_arp_rcv(const struct sk_buff *skb, struct bonding *bond, + struct slave *slave) +{ + struct arphdr *arp = (struct arphdr *)skb->data; + struct slave *curr_active_slave; + unsigned char *arp_ptr; + __be32 sip, tip; + int alen, is_arp = skb->protocol == __cpu_to_be16(ETH_P_ARP); + + if (!slave_do_arp_validate(bond, slave)) { + if ((slave_do_arp_validate_only(bond) && is_arp) || + !slave_do_arp_validate_only(bond)) + slave->last_rx = jiffies; + return RX_HANDLER_ANOTHER; + } else if (!is_arp) { + return RX_HANDLER_ANOTHER; + } + + alen = arp_hdr_len(bond->dev); + + pr_debug("bond_arp_rcv: bond %s skb->dev %s\n", + bond->dev->name, skb->dev->name); + + if (alen > skb_headlen(skb)) { + arp = kmalloc(alen, GFP_ATOMIC); + if (!arp) + goto out_unlock; + if (skb_copy_bits(skb, 0, arp, alen) < 0) + goto out_unlock; + } + + 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); + + curr_active_slave = rcu_dereference(bond->curr_active_slave); + + /* + * 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. + * + * We 'trust' the arp requests if there is an active slave and + * it received valid arp reply(s) after it became active. This + * is done to avoid endless looping when we can't reach the + * arp_ip_target and fool ourselves with our own arp requests. + */ + + if (bond_is_active_slave(slave)) + bond_validate_arp(bond, slave, sip, tip); + else if (curr_active_slave && + time_after(slave_last_rx(bond, curr_active_slave), + curr_active_slave->last_link_up)) + bond_validate_arp(bond, slave, tip, sip); + +out_unlock: + if (arp != (struct arphdr *)skb->data) + kfree(arp); + return RX_HANDLER_ANOTHER; +} + +/* function to verify if we're in the arp_interval timeslice, returns true if + * (last_act - arp_interval) <= jiffies <= (last_act + mod * arp_interval + + * arp_interval/2) . the arp_interval/2 is needed for really fast networks. + */ +static bool bond_time_in_interval(struct bonding *bond, unsigned long last_act, + int mod) +{ + int delta_in_ticks = msecs_to_jiffies(bond->params.arp_interval); + + return time_in_range(jiffies, + last_act - delta_in_ticks, + last_act + mod * delta_in_ticks + delta_in_ticks/2); } /* @@ -2384,45 +2416,37 @@ static void bond_send_gratuitous_arp(struct bonding *bond) * arp is transmitted to generate traffic. see activebackup_arp_monitor for * arp monitoring in active backup mode. */ -void bond_loadbalance_arp_mon(struct net_device *bond_dev) +static void bond_loadbalance_arp_mon(struct work_struct *work) { - struct bonding *bond = bond_dev->priv; + 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 = (bond->params.arp_interval * HZ) / 1000; - - if (bond->kill_timers) { - goto out; - } + struct list_head *iter; + int do_failover = 0, slave_state_changed = 0; - if (bond->slave_cnt == 0) { + if (!bond_has_slaves(bond)) goto re_arm; - } - read_lock(&bond->curr_slave_lock); - oldcurrent = bond->curr_active_slave; - read_unlock(&bond->curr_slave_lock); + rcu_read_lock(); + oldcurrent = ACCESS_ONCE(bond->curr_active_slave); /* 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. + * the picture unless it is null. also, slave->last_link_up 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) { + bond_for_each_slave_rcu(bond, slave, iter) { + unsigned long trans_start = dev_trans_start(slave->dev); + if (slave->link != BOND_LINK_UP) { - if (((jiffies - slave->dev->trans_start) <= delta_in_ticks) && - ((jiffies - slave->dev->last_rx) <= delta_in_ticks)) { + if (bond_time_in_interval(bond, trans_start, 1) && + bond_time_in_interval(bond, slave->last_rx, 1)) { slave->link = BOND_LINK_UP; - slave->state = BOND_STATE_ACTIVE; + slave_state_changed = 1; /* primary_slave has no meaning in round-robin * mode. the window of a slave being up and @@ -2430,17 +2454,14 @@ void bond_loadbalance_arp_mon(struct net_device *bond_dev) * is closed. */ if (!oldcurrent) { - printk(KERN_INFO DRV_NAME - ": %s: link status definitely " - "up for interface %s, ", - bond_dev->name, - slave->dev->name); + pr_info("%s: link status definitely up for interface %s\n", + bond->dev->name, + slave->dev->name); do_failover = 1; } else { - printk(KERN_INFO DRV_NAME - ": %s: interface %s is now up\n", - bond_dev->name, - slave->dev->name); + pr_info("%s: interface %s is now up\n", + bond->dev->name, + slave->dev->name); } } } else { @@ -2450,25 +2471,20 @@ void bond_loadbalance_arp_mon(struct net_device *bond_dev) * when the source ip is 0, so don't take the link down * if we don't know our ip yet */ - if (((jiffies - slave->dev->trans_start) >= (2*delta_in_ticks)) || - (((jiffies - slave->dev->last_rx) >= (2*delta_in_ticks)) && - bond_has_ip(bond))) { + if (!bond_time_in_interval(bond, trans_start, 2) || + !bond_time_in_interval(bond, slave->last_rx, 2)) { slave->link = BOND_LINK_DOWN; - slave->state = BOND_STATE_BACKUP; + slave_state_changed = 1; - if (slave->link_failure_count < UINT_MAX) { + if (slave->link_failure_count < UINT_MAX) slave->link_failure_count++; - } - printk(KERN_INFO DRV_NAME - ": %s: interface %s is now down.\n", - bond_dev->name, - slave->dev->name); + pr_info("%s: interface %s is now down\n", + bond->dev->name, slave->dev->name); - if (slave == oldcurrent) { + if (slave == oldcurrent) do_failover = 1; - } } } @@ -2479,582 +2495,330 @@ void bond_loadbalance_arp_mon(struct net_device *bond_dev) * 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)) { + if (bond_slave_is_up(slave)) bond_arp_send_all(bond, slave); - } } - if (do_failover) { - write_lock(&bond->curr_slave_lock); + rcu_read_unlock(); - bond_select_active_slave(bond); + if (do_failover || slave_state_changed) { + if (!rtnl_trylock()) + goto re_arm; - if (oldcurrent && !bond->curr_active_slave) { - printk(KERN_INFO DRV_NAME - ": %s: now running without any active " - "interface !\n", - bond_dev->name); - } + if (slave_state_changed) { + bond_slave_state_change(bond); + } else if (do_failover) { + /* the bond_select_active_slave must hold RTNL + * and curr_slave_lock for write. + */ + block_netpoll_tx(); + write_lock_bh(&bond->curr_slave_lock); + + bond_select_active_slave(bond); - write_unlock(&bond->curr_slave_lock); + write_unlock_bh(&bond->curr_slave_lock); + unblock_netpoll_tx(); + } + rtnl_unlock(); } re_arm: - if (bond->params.arp_interval) { - mod_timer(&bond->arp_timer, jiffies + delta_in_ticks); - } -out: - read_unlock(&bond->lock); + if (bond->params.arp_interval) + queue_delayed_work(bond->wq, &bond->arp_work, + msecs_to_jiffies(bond->params.arp_interval)); } /* - * When using arp monitoring in active-backup mode, this function is - * called to determine if any backup slaves have went down or a new - * current slave needs to be found. - * The backup slaves never generate traffic, they are considered up by merely - * receiving traffic. If the current slave goes down, each backup slave will - * be given the opportunity to tx/rx an arp before being taken down - this - * prevents all slaves from being taken down due to the current slave not - * sending any traffic for the backups to receive. The arps are not necessarily - * necessary, any tx and rx traffic will keep the current slave up. While any - * rx traffic will keep the backup slaves up, the current slave is responsible - * for generating traffic to keep them up regardless of any other traffic they - * may have received. - * see loadbalance_arp_monitor for arp monitoring in load balancing mode + * 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 rcu_read_lock hold. */ -void bond_activebackup_arp_mon(struct net_device *bond_dev) +static int bond_ab_arp_inspect(struct bonding *bond) { - struct bonding *bond = bond_dev->priv; + unsigned long trans_start, last_rx; + struct list_head *iter; struct slave *slave; - int delta_in_ticks; - int i; - - read_lock(&bond->lock); + int commit = 0; - delta_in_ticks = (bond->params.arp_interval * HZ) / 1000; + bond_for_each_slave_rcu(bond, slave, iter) { + slave->new_link = BOND_LINK_NOCHANGE; + last_rx = slave_last_rx(bond, slave); - if (bond->kill_timers) { - goto out; - } - - if (bond->slave_cnt == 0) { - goto re_arm; - } - - /* determine if any slave has come up or any backup slave has - * gone down - * 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) { if (slave->link != BOND_LINK_UP) { - if ((jiffies - slave->dev->last_rx) <= delta_in_ticks) { - - slave->link = BOND_LINK_UP; - - write_lock(&bond->curr_slave_lock); - - if ((!bond->curr_active_slave) && - ((jiffies - slave->dev->trans_start) <= delta_in_ticks)) { - bond_change_active_slave(bond, slave); - bond->current_arp_slave = NULL; - } else if (bond->curr_active_slave != slave) { - /* this slave has just come up but we - * already have a current slave; this - * can also happen if bond_enslave adds - * a new slave that is up while we are - * searching for a new slave - */ - bond_set_slave_inactive_flags(slave); - bond->current_arp_slave = NULL; - } - - if (slave == bond->curr_active_slave) { - printk(KERN_INFO DRV_NAME - ": %s: %s is up and now the " - "active interface\n", - bond_dev->name, - slave->dev->name); - } else { - printk(KERN_INFO DRV_NAME - ": %s: backup interface %s is " - "now up\n", - bond_dev->name, - slave->dev->name); - } - - write_unlock(&bond->curr_slave_lock); - } - } else { - read_lock(&bond->curr_slave_lock); - - if ((slave != bond->curr_active_slave) && - (!bond->current_arp_slave) && - (((jiffies - slave->dev->last_rx) >= 3*delta_in_ticks) && - bond_has_ip(bond))) { - /* a backup slave has gone down; three times - * the delta allows the current slave to be - * taken out before the backup slave. - * 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 - */ - - read_unlock(&bond->curr_slave_lock); - - slave->link = BOND_LINK_DOWN; - - if (slave->link_failure_count < UINT_MAX) { - slave->link_failure_count++; - } - - bond_set_slave_inactive_flags(slave); - - printk(KERN_INFO DRV_NAME - ": %s: backup interface %s is now down\n", - bond_dev->name, - slave->dev->name); - } else { - read_unlock(&bond->curr_slave_lock); + if (bond_time_in_interval(bond, last_rx, 1)) { + slave->new_link = BOND_LINK_UP; + commit++; } + continue; } - } - - read_lock(&bond->curr_slave_lock); - slave = bond->curr_active_slave; - read_unlock(&bond->curr_slave_lock); - if (slave) { - /* if we have sent traffic in the past 2*arp_intervals but - * haven't xmit and rx traffic in that time interval, select - * a different slave. slave->jiffies is only updated when - * a slave first becomes the curr_active_slave - not necessarily - * after every arp; this ensures the slave has a full 2*delta - * before being taken out. if a primary is being used, check - * if it is up and needs to take over as the curr_active_slave + /* + * 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 ((((jiffies - slave->dev->trans_start) >= (2*delta_in_ticks)) || - (((jiffies - slave->dev->last_rx) >= (2*delta_in_ticks)) && - bond_has_ip(bond))) && - ((jiffies - slave->jiffies) >= 2*delta_in_ticks)) { - - slave->link = BOND_LINK_DOWN; - - if (slave->link_failure_count < UINT_MAX) { - slave->link_failure_count++; - } - - printk(KERN_INFO DRV_NAME - ": %s: link status down for active interface " - "%s, disabling it\n", - bond_dev->name, - slave->dev->name); - - write_lock(&bond->curr_slave_lock); - - bond_select_active_slave(bond); - slave = bond->curr_active_slave; - - write_unlock(&bond->curr_slave_lock); - - bond->current_arp_slave = slave; + if (bond_time_in_interval(bond, slave->last_link_up, 2)) + continue; - if (slave) { - slave->jiffies = jiffies; - } - } else if ((bond->primary_slave) && - (bond->primary_slave != slave) && - (bond->primary_slave->link == BOND_LINK_UP)) { - /* at this point, slave is the curr_active_slave */ - printk(KERN_INFO DRV_NAME - ": %s: changing from interface %s to primary " - "interface %s\n", - bond_dev->name, - slave->dev->name, - bond->primary_slave->dev->name); - - /* primary is up so switch to it */ - write_lock(&bond->curr_slave_lock); - bond_change_active_slave(bond, bond->primary_slave); - write_unlock(&bond->curr_slave_lock); - - slave = bond->primary_slave; - slave->jiffies = jiffies; - } else { - bond->current_arp_slave = NULL; + /* + * 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 && + !bond_time_in_interval(bond, last_rx, 3)) { + slave->new_link = BOND_LINK_DOWN; + commit++; } - /* the current slave must tx an arp to ensure backup slaves - * rx traffic + /* + * 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) */ - if (slave && bond_has_ip(bond)) { - bond_arp_send_all(bond, slave); + trans_start = dev_trans_start(slave->dev); + if (bond_is_active_slave(slave) && + (!bond_time_in_interval(bond, trans_start, 2) || + !bond_time_in_interval(bond, last_rx, 2))) { + slave->new_link = BOND_LINK_DOWN; + commit++; } } - /* 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 (!slave) { - if (!bond->current_arp_slave) { - bond->current_arp_slave = bond->first_slave; - } + return commit; +} - if (bond->current_arp_slave) { - 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; - } +/* + * Called to commit link state changes noted by inspection step of + * active-backup mode ARP monitor. + * + * Called with RTNL hold. + */ +static void bond_ab_arp_commit(struct bonding *bond) +{ + unsigned long trans_start; + struct list_head *iter; + struct slave *slave; - /* 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); - - printk(KERN_INFO DRV_NAME - ": %s: backup interface %s is " - "now down.\n", - bond_dev->name, - slave->dev->name); + bond_for_each_slave(bond, slave, iter) { + 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 != slave || + (!bond->curr_active_slave && + bond_time_in_interval(bond, trans_start, 1))) { + slave->link = BOND_LINK_UP; + if (bond->current_arp_slave) { + bond_set_slave_inactive_flags( + bond->current_arp_slave, + BOND_SLAVE_NOTIFY_NOW); + bond->current_arp_slave = NULL; } - } - } - } -re_arm: - if (bond->params.arp_interval) { - mod_timer(&bond->arp_timer, jiffies + delta_in_ticks); - } -out: - read_unlock(&bond->lock); -} + pr_info("%s: link status definitely up for interface %s\n", + bond->dev->name, slave->dev->name); -/*------------------------------ proc/seq_file-------------------------------*/ + if (!bond->curr_active_slave || + (slave == bond->primary_slave)) + goto do_failover; -#ifdef CONFIG_PROC_FS + } -#define SEQ_START_TOKEN ((void *)1) + continue; -static void *bond_info_seq_start(struct seq_file *seq, loff_t *pos) -{ - struct bonding *bond = seq->private; - loff_t off = 0; - struct slave *slave; - int i; + case BOND_LINK_DOWN: + if (slave->link_failure_count < UINT_MAX) + slave->link_failure_count++; - /* make sure the bond won't be taken away */ - read_lock(&dev_base_lock); - read_lock_bh(&bond->lock); + slave->link = BOND_LINK_DOWN; + bond_set_slave_inactive_flags(slave, + BOND_SLAVE_NOTIFY_NOW); - if (*pos == 0) { - return SEQ_START_TOKEN; - } + pr_info("%s: link status definitely down for interface %s, disabling it\n", + bond->dev->name, slave->dev->name); - bond_for_each_slave(bond, slave, i) { - if (++off == *pos) { - return slave; - } - } + if (slave == bond->curr_active_slave) { + bond->current_arp_slave = NULL; + goto do_failover; + } - return NULL; -} + continue; -static void *bond_info_seq_next(struct seq_file *seq, void *v, loff_t *pos) -{ - struct bonding *bond = seq->private; - struct slave *slave = v; + default: + pr_err("%s: impossible: new_link %d on slave %s\n", + bond->dev->name, slave->new_link, + slave->dev->name); + continue; + } - ++*pos; - if (v == SEQ_START_TOKEN) { - return bond->first_slave; +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(); } - slave = slave->next; - - return (slave == bond->first_slave) ? NULL : slave; + bond_set_carrier(bond); } -static void bond_info_seq_stop(struct seq_file *seq, void *v) -{ - struct bonding *bond = seq->private; - - read_unlock_bh(&bond->lock); - read_unlock(&dev_base_lock); -} - -static void bond_info_show_master(struct seq_file *seq) +/* + * Send ARP probes for active-backup mode ARP monitor. + * + * Called with rcu_read_lock hold. + */ +static bool bond_ab_arp_probe(struct bonding *bond) { - struct bonding *bond = seq->private; - struct slave *curr; - int i; - u32 target; - - read_lock(&bond->curr_slave_lock); - curr = bond->curr_active_slave; - read_unlock(&bond->curr_slave_lock); + struct slave *slave, *before = NULL, *new_slave = NULL, + *curr_arp_slave = rcu_dereference(bond->current_arp_slave), + *curr_active_slave = rcu_dereference(bond->curr_active_slave); + struct list_head *iter; + bool found = false; + bool should_notify_rtnl = BOND_SLAVE_NOTIFY_LATER; - seq_printf(seq, "Bonding Mode: %s\n", - bond_mode_name(bond->params.mode)); + if (curr_arp_slave && curr_active_slave) + pr_info("PROBE: c_arp %s && cas %s BAD\n", + curr_arp_slave->dev->name, + curr_active_slave->dev->name); - 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 (curr_active_slave) { + bond_arp_send_all(bond, curr_active_slave); + return should_notify_rtnl; } - if (USES_PRIMARY(bond->params.mode)) { - seq_printf(seq, "Primary Slave: %s\n", - (bond->primary_slave) ? - bond->primary_slave->dev->name : "None"); + /* 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 + */ - seq_printf(seq, "Currently Active Slave: %s\n", - (curr) ? curr->dev->name : "None"); + if (!curr_arp_slave) { + curr_arp_slave = bond_first_slave_rcu(bond); + if (!curr_arp_slave) + return should_notify_rtnl; } - seq_printf(seq, "MII Status: %s\n", (curr) ? "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); + bond_set_slave_inactive_flags(curr_arp_slave, BOND_SLAVE_NOTIFY_LATER); + bond_for_each_slave_rcu(bond, slave, iter) { + if (!found && !before && bond_slave_is_up(slave)) + before = slave; - /* ARP information */ - if(bond->params.arp_interval > 0) { - int printed=0; - seq_printf(seq, "ARP Polling Interval (ms): %d\n", - bond->params.arp_interval); + if (found && !new_slave && bond_slave_is_up(slave)) + new_slave = slave; + /* 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 (!bond_slave_is_up(slave) && slave->link == BOND_LINK_UP) { + slave->link = BOND_LINK_DOWN; + if (slave->link_failure_count < UINT_MAX) + slave->link_failure_count++; - seq_printf(seq, "ARP IP target/s (n.n.n.n form):"); + bond_set_slave_inactive_flags(slave, + BOND_SLAVE_NOTIFY_LATER); - for(i = 0; (i < BOND_MAX_ARP_TARGETS) ;i++) { - if (!bond->params.arp_targets[i]) - continue; - if (printed) - seq_printf(seq, ","); - target = ntohl(bond->params.arp_targets[i]); - seq_printf(seq, " %d.%d.%d.%d", HIPQUAD(target)); - printed = 1; + pr_info("%s: backup interface %s is now down\n", + bond->dev->name, slave->dev->name); } - seq_printf(seq, "\n"); + if (slave == curr_arp_slave) + found = true; } - if (bond->params.mode == BOND_MODE_8023AD) { - struct ad_info ad_info; + if (!new_slave && before) + new_slave = before; - seq_puts(seq, "\n802.3ad info\n"); - seq_printf(seq, "LACP rate: %s\n", - (bond->params.lacp_fast) ? "fast" : "slow"); + if (!new_slave) + goto check_state; - 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: %02x:%02x:%02x:%02x:%02x:%02x\n", - ad_info.partner_system[0], - ad_info.partner_system[1], - ad_info.partner_system[2], - ad_info.partner_system[3], - ad_info.partner_system[4], - ad_info.partner_system[5]); - } - } -} + new_slave->link = BOND_LINK_BACK; + bond_set_slave_active_flags(new_slave, BOND_SLAVE_NOTIFY_LATER); + bond_arp_send_all(bond, new_slave); + new_slave->last_link_up = jiffies; + rcu_assign_pointer(bond->current_arp_slave, new_slave); -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"); - seq_printf(seq, "Link Failure Count: %d\n", - slave->link_failure_count); - - seq_printf(seq, - "Permanent HW addr: %02x:%02x:%02x:%02x:%02x:%02x\n", - slave->perm_hwaddr[0], slave->perm_hwaddr[1], - slave->perm_hwaddr[2], slave->perm_hwaddr[3], - slave->perm_hwaddr[4], slave->perm_hwaddr[5]); - - 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"); +check_state: + bond_for_each_slave_rcu(bond, slave, iter) { + if (slave->should_notify) { + should_notify_rtnl = BOND_SLAVE_NOTIFY_NOW; + break; } } + return should_notify_rtnl; } -static int bond_info_seq_show(struct seq_file *seq, void *v) +static void bond_activebackup_arp_mon(struct work_struct *work) { - if (v == SEQ_START_TOKEN) { - seq_printf(seq, "%s\n", version); - bond_info_show_master(seq); - } else { - bond_info_show_slave(seq, v); - } - - return 0; -} - -static 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, -}; + struct bonding *bond = container_of(work, struct bonding, + arp_work.work); + bool should_notify_peers = false; + bool should_notify_rtnl = false; + int delta_in_ticks; -static int bond_info_open(struct inode *inode, struct file *file) -{ - struct seq_file *seq; - struct proc_dir_entry *proc; - int res; + delta_in_ticks = msecs_to_jiffies(bond->params.arp_interval); - 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; - } + if (!bond_has_slaves(bond)) + goto re_arm; - return res; -} + rcu_read_lock(); -static struct file_operations bond_info_fops = { - .owner = THIS_MODULE, - .open = bond_info_open, - .read = seq_read, - .llseek = seq_lseek, - .release = seq_release, -}; + should_notify_peers = bond_should_notify_peers(bond); -static int bond_create_proc_entry(struct bonding *bond) -{ - struct net_device *bond_dev = bond->dev; + if (bond_ab_arp_inspect(bond)) { + rcu_read_unlock(); - if (bond_proc_dir) { - bond->proc_entry = create_proc_entry(bond_dev->name, - S_IRUGO, - bond_proc_dir); - if (bond->proc_entry == NULL) { - printk(KERN_WARNING DRV_NAME - ": Warning: Cannot create /proc/net/%s/%s\n", - DRV_NAME, bond_dev->name); - } else { - bond->proc_entry->data = bond; - bond->proc_entry->proc_fops = &bond_info_fops; - bond->proc_entry->owner = THIS_MODULE; - memcpy(bond->proc_file_name, bond_dev->name, IFNAMSIZ); + /* Race avoidance with bond_close flush of workqueue */ + if (!rtnl_trylock()) { + delta_in_ticks = 1; + should_notify_peers = false; + goto re_arm; } - } - - return 0; -} -static void bond_remove_proc_entry(struct bonding *bond) -{ - if (bond_proc_dir && bond->proc_entry) { - remove_proc_entry(bond->proc_file_name, bond_proc_dir); - memset(bond->proc_file_name, 0, IFNAMSIZ); - bond->proc_entry = NULL; - } -} + bond_ab_arp_commit(bond); -/* Create the bonding directory under /proc/net, if doesn't exist yet. - * Caller must hold rtnl_lock. - */ -static void bond_create_proc_dir(void) -{ - int len = strlen(DRV_NAME); - - for (bond_proc_dir = proc_net->subdir; bond_proc_dir; - bond_proc_dir = bond_proc_dir->next) { - if ((bond_proc_dir->namelen == len) && - !memcmp(bond_proc_dir->name, DRV_NAME, len)) { - break; - } + rtnl_unlock(); + rcu_read_lock(); } - if (!bond_proc_dir) { - bond_proc_dir = proc_mkdir(DRV_NAME, proc_net); - if (bond_proc_dir) { - bond_proc_dir->owner = THIS_MODULE; - } else { - printk(KERN_WARNING DRV_NAME - ": Warning: cannot create /proc/net/%s\n", - DRV_NAME); - } - } -} + should_notify_rtnl = bond_ab_arp_probe(bond); + rcu_read_unlock(); -/* Destroy the bonding directory under /proc/net, if empty. - * Caller must hold rtnl_lock. - */ -static void bond_destroy_proc_dir(void) -{ - struct proc_dir_entry *de; +re_arm: + if (bond->params.arp_interval) + queue_delayed_work(bond->wq, &bond->arp_work, delta_in_ticks); - if (!bond_proc_dir) { - return; - } + if (should_notify_peers || should_notify_rtnl) { + if (!rtnl_trylock()) + return; - /* verify that the /proc dir is empty */ - for (de = bond_proc_dir->subdir; de; de = de->next) { - /* ignore . and .. */ - if (*(de->name) != '.') { - break; - } - } + if (should_notify_peers) + call_netdevice_notifiers(NETDEV_NOTIFY_PEERS, + bond->dev); + if (should_notify_rtnl) + bond_slave_state_notify(bond); - if (de) { - if (bond_proc_dir->owner == THIS_MODULE) { - bond_proc_dir->owner = NULL; - } - } else { - remove_proc_entry(DRV_NAME, proc_net); - bond_proc_dir = NULL; + rtnl_unlock(); } } -#endif /* CONFIG_PROC_FS */ /*-------------------------- netdev event handling --------------------------*/ @@ -3063,28 +2827,31 @@ static void bond_destroy_proc_dir(void) */ static int bond_event_changename(struct bonding *bond) { -#ifdef CONFIG_PROC_FS bond_remove_proc_entry(bond); bond_create_proc_entry(bond); -#endif - down_write(&(bonding_rwsem)); - bond_destroy_sysfs_entry(bond); - bond_create_sysfs_entry(bond); - up_write(&(bonding_rwsem)); + + bond_debug_reregister(bond); + return NOTIFY_DONE; } -static int bond_master_netdev_event(unsigned long event, struct net_device *bond_dev) +static int bond_master_netdev_event(unsigned long event, + struct net_device *bond_dev) { - struct bonding *event_bond = bond_dev->priv; + struct bonding *event_bond = netdev_priv(bond_dev); switch (event) { case NETDEV_CHANGENAME: return bond_event_changename(event_bond); case NETDEV_UNREGISTER: - /* - * TODO: remove a bond from the list? - */ + bond_remove_proc_entry(event_bond); + break; + case NETDEV_REGISTER: + bond_create_proc_entry(event_bond); + break; + case NETDEV_NOTIFY_PEERS: + if (event_bond->send_peer_notif) + event_bond->send_peer_notif--; break; default: break; @@ -3093,23 +2860,44 @@ static int bond_master_netdev_event(unsigned long event, struct net_device *bond return NOTIFY_DONE; } -static int bond_slave_netdev_event(unsigned long event, struct net_device *slave_dev) +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 = bond_dev->priv; + struct slave *slave = bond_slave_get_rtnl(slave_dev); + struct bonding *bond; + struct net_device *bond_dev; + u32 old_speed; + u8 old_duplex; + + /* A netdev event can be generated while enslaving a device + * before netdev_rx_handler_register is called in which case + * slave will be NULL + */ + if (!slave) + return NOTIFY_DONE; + bond_dev = slave->bond->dev; + bond = slave->bond; switch (event) { case NETDEV_UNREGISTER: - if (bond_dev) { + if (bond_dev->type != ARPHRD_ETHER) + bond_release_and_destroy(bond_dev, slave_dev); + else bond_release(bond_dev, slave_dev); - } break; + case NETDEV_UP: case NETDEV_CHANGE: - /* - * TODO: is this what we get if somebody - * sets up a hierarchical bond, then rmmod's - * one of the slave bonding devices? - */ + old_speed = slave->speed; + old_duplex = slave->duplex; + + bond_update_speed_duplex(slave); + + if (BOND_MODE(bond) == 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: /* @@ -3131,13 +2919,38 @@ static int bond_slave_netdev_event(unsigned long event, struct net_device *slave */ break; case NETDEV_CHANGENAME: - /* - * TODO: handle changing the primary's name - */ + /* we don't care if we don't have primary set */ + if (!bond_uses_primary(bond) || + !bond->params.primary[0]) + break; + + if (slave == bond->primary_slave) { + /* slave's name changed - he's no longer primary */ + bond->primary_slave = NULL; + } else if (!strcmp(slave_dev->name, bond->params.primary)) { + /* we have a new primary slave */ + bond->primary_slave = slave; + } else { /* we didn't change primary - exit */ + break; + } + + pr_info("%s: Primary slave changed to %s, reselecting active slave\n", + bond->dev->name, + bond->primary_slave ? slave_dev->name : "none"); + + 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(); break; case NETDEV_FEAT_CHANGE: bond_compute_features(bond); break; + case NETDEV_RESEND_IGMP: + /* Propagate to master device */ + call_netdevice_notifiers(event, slave->bond->dev); + break; default: break; } @@ -3149,212 +2962,192 @@ static int bond_slave_netdev_event(unsigned long event, struct net_device *slave * bond_netdev_event: handle netdev notifier chain events. * * This function receives events for the netdev chain. The caller (an - * ioctl handler calling notifier_call_chain) holds the necessary + * 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) +static int bond_netdev_event(struct notifier_block *this, + unsigned long event, void *ptr) { - struct net_device *event_dev = (struct net_device *)ptr; + struct net_device *event_dev = netdev_notifier_info_to_dev(ptr); + + pr_debug("event_dev: %s, event: %lx\n", + event_dev ? event_dev->name : "None", event); - dprintk("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) { - dprintk("IFF_MASTER\n"); + pr_debug("IFF_MASTER\n"); return bond_master_netdev_event(event, event_dev); } if (event_dev->flags & IFF_SLAVE) { - dprintk("IFF_SLAVE\n"); + pr_debug("IFF_SLAVE\n"); return bond_slave_netdev_event(event, event_dev); } return NOTIFY_DONE; } -/* - * bond_inetaddr_event: handle inetaddr notifier chain events. - * - * We keep track of device IPs primarily to use as source addresses in - * ARP monitor probes (rather than spewing out broadcasts all the time). - * - * We track one IP for the main device (if it has one), plus one per VLAN. - */ -static int bond_inetaddr_event(struct notifier_block *this, unsigned long event, void *ptr) -{ - struct in_ifaddr *ifa = ptr; - struct net_device *vlan_dev, *event_dev = ifa->ifa_dev->dev; - struct bonding *bond, *bond_next; - struct vlan_entry *vlan, *vlan_next; - - list_for_each_entry_safe(bond, bond_next, &bond_dev_list, bond_list) { - if (bond->dev == event_dev) { - switch (event) { - case NETDEV_UP: - bond->master_ip = ifa->ifa_local; - return NOTIFY_OK; - case NETDEV_DOWN: - bond->master_ip = bond_glean_dev_ip(bond->dev); - return NOTIFY_OK; - default: - return NOTIFY_DONE; - } - } - - if (list_empty(&bond->vlan_list)) - continue; - - list_for_each_entry_safe(vlan, vlan_next, &bond->vlan_list, - vlan_list) { - vlan_dev = bond->vlgrp->vlan_devices[vlan->vlan_id]; - if (vlan_dev == event_dev) { - switch (event) { - case NETDEV_UP: - vlan->vlan_ip = ifa->ifa_local; - return NOTIFY_OK; - case NETDEV_DOWN: - vlan->vlan_ip = - bond_glean_dev_ip(vlan_dev); - return NOTIFY_OK; - default: - return NOTIFY_DONE; - } - } - } - } - return NOTIFY_DONE; -} - static struct notifier_block bond_netdev_notifier = { .notifier_call = bond_netdev_event, }; -static struct notifier_block bond_inetaddr_notifier = { - .notifier_call = bond_inetaddr_event, -}; - -/*-------------------------- Packet type handling ---------------------------*/ +/*---------------------------- Hashing Policies -----------------------------*/ -/* register to receive lacpdus on a bond */ -static void bond_register_lacpdu(struct bonding *bond) +/* L2 hash helper */ +static inline u32 bond_eth_hash(struct sk_buff *skb) { - struct packet_type *pk_type = &(BOND_AD_INFO(bond).ad_pkt_type); + struct ethhdr *data = (struct ethhdr *)skb->data; - /* initialize packet type */ - pk_type->type = PKT_TYPE_LACPDU; - pk_type->dev = bond->dev; - pk_type->func = bond_3ad_lacpdu_recv; + if (skb_headlen(skb) >= offsetof(struct ethhdr, h_proto)) + return data->h_dest[5] ^ data->h_source[5]; - dev_add_pack(pk_type); + return 0; } -/* unregister to receive lacpdus on a bond */ -static void bond_unregister_lacpdu(struct bonding *bond) +/* Extract the appropriate headers based on bond's xmit policy */ +static bool bond_flow_dissect(struct bonding *bond, struct sk_buff *skb, + struct flow_keys *fk) { - dev_remove_pack(&(BOND_AD_INFO(bond).ad_pkt_type)); -} + const struct ipv6hdr *iph6; + const struct iphdr *iph; + int noff, proto = -1; + + if (bond->params.xmit_policy > BOND_XMIT_POLICY_LAYER23) + return skb_flow_dissect(skb, fk); + + fk->ports = 0; + noff = skb_network_offset(skb); + if (skb->protocol == htons(ETH_P_IP)) { + if (unlikely(!pskb_may_pull(skb, noff + sizeof(*iph)))) + return false; + iph = ip_hdr(skb); + fk->src = iph->saddr; + fk->dst = iph->daddr; + noff += iph->ihl << 2; + if (!ip_is_fragment(iph)) + proto = iph->protocol; + } else if (skb->protocol == htons(ETH_P_IPV6)) { + if (unlikely(!pskb_may_pull(skb, noff + sizeof(*iph6)))) + return false; + iph6 = ipv6_hdr(skb); + fk->src = (__force __be32)ipv6_addr_hash(&iph6->saddr); + fk->dst = (__force __be32)ipv6_addr_hash(&iph6->daddr); + noff += sizeof(*iph6); + proto = iph6->nexthdr; + } else { + return false; + } + if (bond->params.xmit_policy == BOND_XMIT_POLICY_LAYER34 && proto >= 0) + fk->ports = skb_flow_get_ports(skb, noff, proto); -/*---------------------------- Hashing Policies -----------------------------*/ + return true; +} -/* - * Hash for the 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() +/** + * bond_xmit_hash - generate a hash value based on the xmit policy + * @bond: bonding device + * @skb: buffer to use for headers + * + * This function will extract the necessary headers from the skb buffer and use + * them to generate a hash based on the xmit_policy set in the bonding device */ -static int bond_xmit_hash_policy_l34(struct sk_buff *skb, - struct net_device *bond_dev, int count) +u32 bond_xmit_hash(struct bonding *bond, struct sk_buff *skb) { - struct ethhdr *data = (struct ethhdr *)skb->data; - struct iphdr *iph = skb->nh.iph; - u16 *layer4hdr = (u16 *)((u32 *)iph + iph->ihl); - int layer4_xor = 0; - - if (skb->protocol == __constant_htons(ETH_P_IP)) { - if (!(iph->frag_off & __constant_htons(IP_MF|IP_OFFSET)) && - (iph->protocol == IPPROTO_TCP || - iph->protocol == IPPROTO_UDP)) { - layer4_xor = htons((*layer4hdr ^ *(layer4hdr + 1))); - } - return (layer4_xor ^ - ((ntohl(iph->saddr ^ iph->daddr)) & 0xffff)) % count; + struct flow_keys flow; + u32 hash; + + if (bond->params.xmit_policy == BOND_XMIT_POLICY_LAYER2 || + !bond_flow_dissect(bond, skb, &flow)) + return bond_eth_hash(skb); + + if (bond->params.xmit_policy == BOND_XMIT_POLICY_LAYER23 || + bond->params.xmit_policy == BOND_XMIT_POLICY_ENCAP23) + hash = bond_eth_hash(skb); + else + hash = (__force u32)flow.ports; + hash ^= (__force u32)flow.dst ^ (__force u32)flow.src; + hash ^= (hash >> 16); + hash ^= (hash >> 8); + + return hash; +} - } +/*-------------------------- Device entry points ----------------------------*/ - return (data->h_dest[5] ^ bond_dev->dev_addr[5]) % count; +static void bond_work_init_all(struct bonding *bond) +{ + INIT_DELAYED_WORK(&bond->mcast_work, + bond_resend_igmp_join_requests_delayed); + INIT_DELAYED_WORK(&bond->alb_work, bond_alb_monitor); + INIT_DELAYED_WORK(&bond->mii_work, bond_mii_monitor); + if (BOND_MODE(bond) == BOND_MODE_ACTIVEBACKUP) + INIT_DELAYED_WORK(&bond->arp_work, bond_activebackup_arp_mon); + else + INIT_DELAYED_WORK(&bond->arp_work, bond_loadbalance_arp_mon); + INIT_DELAYED_WORK(&bond->ad_work, bond_3ad_state_machine_handler); } -/* - * Hash for the output device based upon layer 2 data - */ -static int bond_xmit_hash_policy_l2(struct sk_buff *skb, - struct net_device *bond_dev, int count) +static void bond_work_cancel_all(struct bonding *bond) { - struct ethhdr *data = (struct ethhdr *)skb->data; - - return (data->h_dest[5] ^ bond_dev->dev_addr[5]) % count; + cancel_delayed_work_sync(&bond->mii_work); + cancel_delayed_work_sync(&bond->arp_work); + cancel_delayed_work_sync(&bond->alb_work); + cancel_delayed_work_sync(&bond->ad_work); + cancel_delayed_work_sync(&bond->mcast_work); } -/*-------------------------- Device entry points ----------------------------*/ - static int bond_open(struct net_device *bond_dev) { - struct bonding *bond = bond_dev->priv; - struct timer_list *mii_timer = &bond->mii_timer; - struct timer_list *arp_timer = &bond->arp_timer; + struct bonding *bond = netdev_priv(bond_dev); + struct list_head *iter; + struct slave *slave; - bond->kill_timers = 0; + /* reset slave->backup and slave->inactive */ + read_lock(&bond->lock); + if (bond_has_slaves(bond)) { + read_lock(&bond->curr_slave_lock); + bond_for_each_slave(bond, slave, iter) { + if (bond_uses_primary(bond) + && (slave != bond->curr_active_slave)) { + bond_set_slave_inactive_flags(slave, + BOND_SLAVE_NOTIFY_NOW); + } else { + bond_set_slave_active_flags(slave, + BOND_SLAVE_NOTIFY_NOW); + } + } + read_unlock(&bond->curr_slave_lock); + } + read_unlock(&bond->lock); - if ((bond->params.mode == BOND_MODE_TLB) || - (bond->params.mode == BOND_MODE_ALB)) { - struct timer_list *alb_timer = &(BOND_ALB_INFO(bond).alb_timer); + bond_work_init_all(bond); + 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 -1; - } - - init_timer(alb_timer); - alb_timer->expires = jiffies + 1; - alb_timer->data = (unsigned long)bond; - alb_timer->function = (void *)&bond_alb_monitor; - add_timer(alb_timer); + if (bond_alb_initialize(bond, (BOND_MODE(bond) == BOND_MODE_ALB))) + return -ENOMEM; + if (bond->params.tlb_dynamic_lb) + queue_delayed_work(bond->wq, &bond->alb_work, 0); } - if (bond->params.miimon) { /* link check interval, in milliseconds. */ - init_timer(mii_timer); - mii_timer->expires = jiffies + 1; - mii_timer->data = (unsigned long)bond_dev; - mii_timer->function = (void *)&bond_mii_monitor; - add_timer(mii_timer); - } + if (bond->params.miimon) /* link check interval, in milliseconds. */ + queue_delayed_work(bond->wq, &bond->mii_work, 0); if (bond->params.arp_interval) { /* arp interval, in milliseconds. */ - init_timer(arp_timer); - arp_timer->expires = jiffies + 1; - arp_timer->data = (unsigned long)bond_dev; - if (bond->params.mode == BOND_MODE_ACTIVEBACKUP) { - arp_timer->function = (void *)&bond_activebackup_arp_mon; - } else { - arp_timer->function = (void *)&bond_loadbalance_arp_mon; - } - add_timer(arp_timer); + queue_delayed_work(bond->wq, &bond->arp_work, 0); + bond->recv_probe = bond_arp_rcv; } - if (bond->params.mode == BOND_MODE_8023AD) { - struct timer_list *ad_timer = &(BOND_AD_INFO(bond).ad_timer); - init_timer(ad_timer); - ad_timer->expires = jiffies + 1; - ad_timer->data = (unsigned long)bond; - ad_timer->function = (void *)&bond_3ad_state_machine_handler; - add_timer(ad_timer); - + if (BOND_MODE(bond) == BOND_MODE_8023AD) { + queue_delayed_work(bond->wq, &bond->ad_work, 0); /* register to receive LACPDUs */ - bond_register_lacpdu(bond); + bond->recv_probe = bond_3ad_lacpdu_recv; + bond_3ad_initiate_agg_selection(bond, 1); } return 0; @@ -3362,73 +3155,31 @@ static int bond_open(struct net_device *bond_dev) static int bond_close(struct net_device *bond_dev) { - struct bonding *bond = bond_dev->priv; - - if (bond->params.mode == BOND_MODE_8023AD) { - /* Unregister the receive of LACPDUs */ - bond_unregister_lacpdu(bond); - } - - write_lock_bh(&bond->lock); - - bond_mc_list_destroy(bond); - - /* signal timers not to re-arm */ - bond->kill_timers = 1; - - write_unlock_bh(&bond->lock); - - /* del_timer_sync must run without holding the bond->lock - * because a running timer might be trying to hold it too - */ - - if (bond->params.miimon) { /* link check interval, in milliseconds. */ - del_timer_sync(&bond->mii_timer); - } - - if (bond->params.arp_interval) { /* arp interval, in milliseconds. */ - del_timer_sync(&bond->arp_timer); - } - - switch (bond->params.mode) { - case BOND_MODE_8023AD: - del_timer_sync(&(BOND_AD_INFO(bond).ad_timer)); - break; - case BOND_MODE_TLB: - case BOND_MODE_ALB: - del_timer_sync(&(BOND_ALB_INFO(bond).alb_timer)); - break; - default: - break; - } - - /* Release the bonded slaves */ - bond_release_all(bond_dev); + struct bonding *bond = netdev_priv(bond_dev); - if ((bond->params.mode == BOND_MODE_TLB) || - (bond->params.mode == BOND_MODE_ALB)) { - /* Must be called only after all - * slaves have been released - */ + bond_work_cancel_all(bond); + bond->send_peer_notif = 0; + if (bond_is_lb(bond)) bond_alb_deinitialize(bond); - } + bond->recv_probe = NULL; return 0; } -static struct net_device_stats *bond_get_stats(struct net_device *bond_dev) +static struct rtnl_link_stats64 *bond_get_stats(struct net_device *bond_dev, + struct rtnl_link_stats64 *stats) { - struct bonding *bond = bond_dev->priv; - struct net_device_stats *stats = &(bond->stats), *sstats; + struct bonding *bond = netdev_priv(bond_dev); + struct rtnl_link_stats64 temp; + struct list_head *iter; struct slave *slave; - int i; - memset(stats, 0, sizeof(struct net_device_stats)); + memset(stats, 0, sizeof(*stats)); read_lock_bh(&bond->lock); - - bond_for_each_slave(bond, slave, i) { - sstats = slave->dev->get_stats(slave->dev); + bond_for_each_slave(bond, slave, iter) { + const struct rtnl_link_stats64 *sstats = + dev_get_stats(slave->dev, &temp); stats->rx_packets += sstats->rx_packets; stats->rx_bytes += sstats->rx_bytes; @@ -3456,7 +3207,6 @@ static struct net_device_stats *bond_get_stats(struct net_device *bond_dev) stats->tx_heartbeat_errors += sstats->tx_heartbeat_errors; stats->tx_window_errors += sstats->tx_window_errors; } - read_unlock_bh(&bond->lock); return stats; @@ -3464,23 +3214,25 @@ static struct net_device_stats *bond_get_stats(struct net_device *bond_dev) static int bond_do_ioctl(struct net_device *bond_dev, struct ifreq *ifr, int cmd) { + struct bonding *bond = netdev_priv(bond_dev); 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; + struct bond_opt_value newval; + struct net *net; int res = 0; - dprintk("bond_ioctl: master=%s, cmd=%d\n", - bond_dev->name, cmd); + pr_debug("bond_ioctl: master=%s, cmd=%d\n", bond_dev->name, cmd); switch (cmd) { case SIOCGMIIPHY: mii = if_mii(ifr); - if (!mii) { + if (!mii) return -EINVAL; - } + mii->phy_id = 0; /* Fall Through */ case SIOCGMIIREG: @@ -3489,20 +3241,19 @@ static int bond_do_ioctl(struct net_device *bond_dev, struct ifreq *ifr, int cmd * instead of SIOCGMIIPHY. */ mii = if_mii(ifr); - if (!mii) { + if (!mii) return -EINVAL; - } + if (mii->reg_num == 1) { - struct bonding *bond = bond_dev->priv; mii->val_out = 0; - read_lock_bh(&bond->lock); + read_lock(&bond->lock); read_lock(&bond->curr_slave_lock); - if (bond->curr_active_slave) { + if (netif_carrier_ok(bond->dev)) mii->val_out = BMSR_LSTATUS; - } + read_unlock(&bond->curr_slave_lock); - read_unlock_bh(&bond->lock); + read_unlock(&bond->lock); } return 0; @@ -3510,32 +3261,26 @@ static int bond_do_ioctl(struct net_device *bond_dev, struct ifreq *ifr, int cmd case SIOCBONDINFOQUERY: u_binfo = (struct ifbond __user *)ifr->ifr_data; - if (copy_from_user(&k_binfo, u_binfo, sizeof(ifbond))) { + if (copy_from_user(&k_binfo, u_binfo, sizeof(ifbond))) return -EFAULT; - } res = bond_info_query(bond_dev, &k_binfo); - if (res == 0) { - if (copy_to_user(u_binfo, &k_binfo, sizeof(ifbond))) { - return -EFAULT; - } - } + 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))) { + if (copy_from_user(&k_sinfo, u_sinfo, sizeof(ifslave))) return -EFAULT; - } res = bond_slave_info_query(bond_dev, &k_sinfo); - if (res == 0) { - if (copy_to_user(u_sinfo, &k_sinfo, sizeof(ifslave))) { - return -EFAULT; - } - } + if (res == 0 && + copy_to_user(u_sinfo, &k_sinfo, sizeof(ifslave))) + return -EFAULT; return res; default: @@ -3543,95 +3288,133 @@ static int bond_do_ioctl(struct net_device *bond_dev, struct ifreq *ifr, int cmd break; } - if (!capable(CAP_NET_ADMIN)) { + net = dev_net(bond_dev); + + if (!ns_capable(net->user_ns, CAP_NET_ADMIN)) return -EPERM; - } - down_write(&(bonding_rwsem)); - slave_dev = dev_get_by_name(ifr->ifr_slave); + slave_dev = __dev_get_by_name(net, ifr->ifr_slave); - dprintk("slave_dev=%p: \n", slave_dev); + pr_debug("slave_dev=%p:\n", slave_dev); - if (!slave_dev) { - res = -ENODEV; - } else { - dprintk("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; - } + if (!slave_dev) + return -ENODEV; - dev_put(slave_dev); + 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: + bond_set_dev_addr(bond_dev, slave_dev); + res = 0; + break; + case BOND_CHANGE_ACTIVE_OLD: + case SIOCBONDCHANGEACTIVE: + bond_opt_initstr(&newval, slave_dev->name); + res = __bond_opt_set(bond, BOND_OPT_ACTIVE_SLAVE, &newval); + break; + default: + res = -EOPNOTSUPP; } - up_write(&(bonding_rwsem)); return res; } -static void bond_set_multicast_list(struct net_device *bond_dev) +static void bond_change_rx_flags(struct net_device *bond_dev, int change) { - struct bonding *bond = bond_dev->priv; - struct dev_mc_list *dmi; + struct bonding *bond = netdev_priv(bond_dev); - write_lock_bh(&bond->lock); + if (change & IFF_PROMISC) + bond_set_promiscuity(bond, + bond_dev->flags & IFF_PROMISC ? 1 : -1); - /* - * Do promisc before checking multicast_mode - */ - if ((bond_dev->flags & IFF_PROMISC) && !(bond->flags & IFF_PROMISC)) { - bond_set_promiscuity(bond, 1); - } + if (change & IFF_ALLMULTI) + bond_set_allmulti(bond, + bond_dev->flags & IFF_ALLMULTI ? 1 : -1); +} - if (!(bond_dev->flags & IFF_PROMISC) && (bond->flags & IFF_PROMISC)) { - bond_set_promiscuity(bond, -1); - } +static void bond_set_rx_mode(struct net_device *bond_dev) +{ + struct bonding *bond = netdev_priv(bond_dev); + struct list_head *iter; + struct slave *slave; - /* set allmulti flag to slaves */ - if ((bond_dev->flags & IFF_ALLMULTI) && !(bond->flags & IFF_ALLMULTI)) { - bond_set_allmulti(bond, 1); - } - if (!(bond_dev->flags & IFF_ALLMULTI) && (bond->flags & IFF_ALLMULTI)) { - bond_set_allmulti(bond, -1); + rcu_read_lock(); + if (bond_uses_primary(bond)) { + slave = rcu_dereference(bond->curr_active_slave); + if (slave) { + dev_uc_sync(slave->dev, bond_dev); + dev_mc_sync(slave->dev, bond_dev); + } + } else { + bond_for_each_slave_rcu(bond, slave, iter) { + dev_uc_sync_multiple(slave->dev, bond_dev); + dev_mc_sync_multiple(slave->dev, bond_dev); + } } + rcu_read_unlock(); +} - bond->flags = bond_dev->flags; +static int bond_neigh_init(struct neighbour *n) +{ + struct bonding *bond = netdev_priv(n->dev); + const struct net_device_ops *slave_ops; + struct neigh_parms parms; + struct slave *slave; + int ret; - /* looking for addresses to add to slaves' mc list */ - for (dmi = bond_dev->mc_list; dmi; dmi = dmi->next) { - if (!bond_mc_list_find_dmi(dmi, bond->mc_list)) { - bond_mc_add(bond, dmi->dmi_addr, dmi->dmi_addrlen); - } - } + slave = bond_first_slave(bond); + if (!slave) + return 0; + slave_ops = slave->dev->netdev_ops; + if (!slave_ops->ndo_neigh_setup) + return 0; - /* looking for addresses to delete from slaves' list */ - for (dmi = bond->mc_list; dmi; dmi = dmi->next) { - if (!bond_mc_list_find_dmi(dmi, bond_dev->mc_list)) { - bond_mc_delete(bond, dmi->dmi_addr, dmi->dmi_addrlen); - } - } + parms.neigh_setup = NULL; + parms.neigh_cleanup = NULL; + ret = slave_ops->ndo_neigh_setup(slave->dev, &parms); + if (ret) + return ret; - /* save master's multicast list */ - bond_mc_list_destroy(bond); - bond_mc_list_copy(bond_dev->mc_list, bond, GFP_ATOMIC); + /* + * 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; - write_unlock_bh(&bond->lock); + 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. + * + * It's also called by master devices (such as vlans) to setup their + * underlying devices. In that case - do nothing, we're already set up from + * our init. + */ +static int bond_neigh_setup(struct net_device *dev, + struct neigh_parms *parms) +{ + /* modify only our neigh_parms */ + if (parms->dev == dev) + parms->neigh_setup = bond_neigh_init; + + return 0; } /* @@ -3639,13 +3422,13 @@ static void bond_set_multicast_list(struct net_device *bond_dev) */ static int bond_change_mtu(struct net_device *bond_dev, int new_mtu) { - struct bonding *bond = bond_dev->priv; - struct slave *slave, *stop_at; + struct bonding *bond = netdev_priv(bond_dev); + struct slave *slave, *rollback_slave; + struct list_head *iter; int res = 0; - int i; - dprintk("bond=%p, name=%s, new_mtu=%d\n", bond, - (bond_dev ? bond_dev->name : "None"), new_mtu); + 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 @@ -3662,9 +3445,9 @@ static int bond_change_mtu(struct net_device *bond_dev, int new_mtu) * call to the base driver. */ - bond_for_each_slave(bond, slave, i) { - dprintk("s %p s->p %p c_m %p\n", slave, - slave->prev, slave->dev->change_mtu); + bond_for_each_slave(bond, slave, iter) { + pr_debug("s %p c_m %p\n", + slave, slave->dev->netdev_ops->ndo_change_mtu); res = dev_set_mtu(slave->dev, new_mtu); @@ -3677,7 +3460,7 @@ static int bond_change_mtu(struct net_device *bond_dev, int new_mtu) * means changing their mtu from timer context, which * is probably not a good idea. */ - dprintk("err %d %s\n", res, slave->dev->name); + pr_debug("err %d %s\n", res, slave->dev->name); goto unwind; } } @@ -3688,14 +3471,16 @@ static int bond_change_mtu(struct net_device *bond_dev, int new_mtu) 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) { + bond_for_each_slave(bond, rollback_slave, iter) { int tmp_res; - tmp_res = dev_set_mtu(slave->dev, bond_dev->mtu); + if (rollback_slave == slave) + break; + + tmp_res = dev_set_mtu(rollback_slave->dev, bond_dev->mtu); if (tmp_res) { - dprintk("unwind err %d dev %s\n", tmp_res, - slave->dev->name); + pr_debug("unwind err %d dev %s\n", + tmp_res, rollback_slave->dev->name); } } @@ -3711,17 +3496,28 @@ unwind: */ static int bond_set_mac_address(struct net_device *bond_dev, void *addr) { - struct bonding *bond = bond_dev->priv; + struct bonding *bond = netdev_priv(bond_dev); + struct slave *slave, *rollback_slave; struct sockaddr *sa = addr, tmp_sa; - struct slave *slave, *stop_at; + struct list_head *iter; int res = 0; - int i; - dprintk("bond=%p, name=%s\n", bond, (bond_dev ? bond_dev->name : "None")); + if (BOND_MODE(bond) == 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 enabled, do nothing and return success. + * Returning an error causes ifenslave to fail. + */ + if (bond->params.fail_over_mac && + BOND_MODE(bond) == BOND_MODE_ACTIVEBACKUP) + return 0; - if (!is_valid_ether_addr(sa->sa_data)) { + 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 @@ -3738,15 +3534,8 @@ static int bond_set_mac_address(struct net_device *bond_dev, void *addr) * call to the base driver. */ - bond_for_each_slave(bond, slave, i) { - dprintk("slave %p %s\n", slave, slave->dev->name); - - if (slave->dev->set_mac_address == NULL) { - res = -EOPNOTSUPP; - dprintk("EOPNOTSUPP %s\n", slave->dev->name); - goto unwind; - } - + bond_for_each_slave(bond, slave, iter) { + pr_debug("slave %p %s\n", slave, slave->dev->name); res = dev_set_mac_address(slave->dev, addr); if (res) { /* TODO: consider downing the slave @@ -3755,7 +3544,7 @@ static int bond_set_mac_address(struct net_device *bond_dev, void *addr) * breakage anyway until ARP finish * updating, so... */ - dprintk("err %d %s\n", res, slave->dev->name); + pr_debug("err %d %s\n", res, slave->dev->name); goto unwind; } } @@ -3769,100 +3558,120 @@ unwind: 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) { + bond_for_each_slave(bond, rollback_slave, iter) { int tmp_res; - tmp_res = dev_set_mac_address(slave->dev, &tmp_sa); + if (rollback_slave == slave) + break; + + tmp_res = dev_set_mac_address(rollback_slave->dev, &tmp_sa); if (tmp_res) { - dprintk("unwind err %d dev %s\n", tmp_res, - slave->dev->name); + pr_debug("unwind err %d dev %s\n", + tmp_res, rollback_slave->dev->name); } } return res; } -static int bond_xmit_roundrobin(struct sk_buff *skb, struct net_device *bond_dev) +/** + * bond_xmit_slave_id - transmit skb through slave with slave_id + * @bond: bonding device that is transmitting + * @skb: buffer to transmit + * @slave_id: slave id up to slave_cnt-1 through which to transmit + * + * This function tries to transmit through slave with slave_id but in case + * it fails, it tries to find the first available slave for transmission. + * The skb is consumed in all cases, thus the function is void. + */ +static void bond_xmit_slave_id(struct bonding *bond, struct sk_buff *skb, int slave_id) { - struct bonding *bond = bond_dev->priv; - struct slave *slave, *start_at; - int i; - int res = 1; - - read_lock(&bond->lock); - - if (!BOND_IS_OK(bond)) { - goto out; - } - - read_lock(&bond->curr_slave_lock); - slave = start_at = bond->curr_active_slave; - read_unlock(&bond->curr_slave_lock); - - if (!slave) { - goto out; + struct list_head *iter; + struct slave *slave; + int i = slave_id; + + /* Here we start from the slave with slave_id */ + bond_for_each_slave_rcu(bond, slave, iter) { + if (--i < 0) { + if (bond_slave_can_tx(slave)) { + bond_dev_queue_xmit(bond, skb, slave->dev); + return; + } + } } - bond_for_each_slave_from(bond, slave, i, start_at) { - if (IS_UP(slave->dev) && - (slave->link == BOND_LINK_UP) && - (slave->state == BOND_STATE_ACTIVE)) { - res = bond_dev_queue_xmit(bond, skb, slave->dev); - - write_lock(&bond->curr_slave_lock); - bond->curr_active_slave = slave->next; - write_unlock(&bond->curr_slave_lock); - + /* Here we start from the first slave up to slave_id */ + i = slave_id; + bond_for_each_slave_rcu(bond, slave, iter) { + if (--i < 0) break; + if (bond_slave_can_tx(slave)) { + bond_dev_queue_xmit(bond, skb, slave->dev); + return; } } - - -out: - if (res) { - /* no suitable interface, frame not sent */ - dev_kfree_skb(skb); - } - read_unlock(&bond->lock); - return 0; + /* no slave that can tx has been found */ + dev_kfree_skb_any(skb); } -static void bond_activebackup_xmit_copy(struct sk_buff *skb, - struct bonding *bond, - struct slave *slave) +/** + * bond_rr_gen_slave_id - generate slave id based on packets_per_slave + * @bond: bonding device to use + * + * Based on the value of the bonding device's packets_per_slave parameter + * this function generates a slave id, which is usually used as the next + * slave to transmit through. + */ +static u32 bond_rr_gen_slave_id(struct bonding *bond) { - struct sk_buff *skb2 = skb_copy(skb, GFP_ATOMIC); - struct ethhdr *eth_data; - u8 *hwaddr; - int res; + u32 slave_id; + struct reciprocal_value reciprocal_packets_per_slave; + int packets_per_slave = bond->params.packets_per_slave; - if (!skb2) { - printk(KERN_ERR DRV_NAME ": Error: " - "bond_activebackup_xmit_copy(): skb_copy() failed\n"); - return; + switch (packets_per_slave) { + case 0: + slave_id = prandom_u32(); + break; + case 1: + slave_id = bond->rr_tx_counter; + break; + default: + reciprocal_packets_per_slave = + bond->params.reciprocal_packets_per_slave; + slave_id = reciprocal_divide(bond->rr_tx_counter, + reciprocal_packets_per_slave); + break; } + bond->rr_tx_counter++; - skb2->mac.raw = (unsigned char *)skb2->data; - eth_data = eth_hdr(skb2); - - /* Pick an appropriate source MAC address - * -- use slave's perm MAC addr, unless used by bond - * -- otherwise, borrow active slave's perm MAC addr - * since that will not be used - */ - hwaddr = slave->perm_hwaddr; - if (!memcmp(eth_data->h_source, hwaddr, ETH_ALEN)) - hwaddr = bond->curr_active_slave->perm_hwaddr; + return slave_id; +} - /* Set source MAC address appropriately */ - memcpy(eth_data->h_source, hwaddr, ETH_ALEN); +static int bond_xmit_roundrobin(struct sk_buff *skb, struct net_device *bond_dev) +{ + struct bonding *bond = netdev_priv(bond_dev); + struct iphdr *iph = ip_hdr(skb); + struct slave *slave; + u32 slave_id; - res = bond_dev_queue_xmit(bond, skb2, slave->dev); - if (res) - dev_kfree_skb(skb2); + /* 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)) { + slave = rcu_dereference(bond->curr_active_slave); + if (slave && bond_slave_can_tx(slave)) + bond_dev_queue_xmit(bond, skb, slave->dev); + else + bond_xmit_slave_id(bond, skb, 0); + } else { + slave_id = bond_rr_gen_slave_id(bond); + bond_xmit_slave_id(bond, skb, slave_id % bond->slave_cnt); + } - return; + return NETDEV_TX_OK; } /* @@ -3871,260 +3680,281 @@ static void bond_activebackup_xmit_copy(struct sk_buff *skb, */ static int bond_xmit_activebackup(struct sk_buff *skb, struct net_device *bond_dev) { - struct bonding *bond = bond_dev->priv; - int res = 1; - - read_lock(&bond->lock); - read_lock(&bond->curr_slave_lock); - - if (!BOND_IS_OK(bond)) { - goto out; - } - - if (!bond->curr_active_slave) - goto out; - - /* Xmit IGMP frames on all slaves to ensure rapid fail-over - for multicast traffic on snooping switches */ - if (skb->protocol == __constant_htons(ETH_P_IP) && - skb->nh.iph->protocol == IPPROTO_IGMP) { - struct slave *slave, *active_slave; - int i; - - active_slave = bond->curr_active_slave; - bond_for_each_slave_from_to(bond, slave, i, active_slave->next, - active_slave->prev) - if (IS_UP(slave->dev) && - (slave->link == BOND_LINK_UP)) - bond_activebackup_xmit_copy(skb, bond, slave); - } + struct bonding *bond = netdev_priv(bond_dev); + struct slave *slave; - res = bond_dev_queue_xmit(bond, skb, bond->curr_active_slave->dev); + slave = rcu_dereference(bond->curr_active_slave); + if (slave) + bond_dev_queue_xmit(bond, skb, slave->dev); + else + dev_kfree_skb_any(skb); -out: - if (res) { - /* no suitable interface, frame not sent */ - dev_kfree_skb(skb); - } - read_unlock(&bond->curr_slave_lock); - read_unlock(&bond->lock); - return 0; + return NETDEV_TX_OK; } -/* - * In bond_xmit_xor() , we determine the output device by using a pre- +/* 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 = bond_dev->priv; - struct slave *slave, *start_at; - int slave_no; - int i; - int res = 1; + struct bonding *bond = netdev_priv(bond_dev); - read_lock(&bond->lock); + bond_xmit_slave_id(bond, skb, bond_xmit_hash(bond, skb) % bond->slave_cnt); - if (!BOND_IS_OK(bond)) { - goto out; - } + return NETDEV_TX_OK; +} - slave_no = bond->xmit_hash_policy(skb, bond_dev, bond->slave_cnt); +/* 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 = NULL; + struct list_head *iter; - bond_for_each_slave(bond, slave, i) { - slave_no--; - if (slave_no < 0) { + bond_for_each_slave_rcu(bond, slave, iter) { + if (bond_is_last_slave(bond, slave)) break; - } - } - - start_at = slave; + if (bond_slave_is_up(slave) && slave->link == BOND_LINK_UP) { + struct sk_buff *skb2 = skb_clone(skb, GFP_ATOMIC); - bond_for_each_slave_from(bond, slave, i, start_at) { - if (IS_UP(slave->dev) && - (slave->link == BOND_LINK_UP) && - (slave->state == BOND_STATE_ACTIVE)) { - res = bond_dev_queue_xmit(bond, skb, slave->dev); - break; + if (!skb2) { + net_err_ratelimited("%s: Error: %s: skb_clone() failed\n", + bond_dev->name, __func__); + continue; + } + /* bond_dev_queue_xmit always returns 0 */ + bond_dev_queue_xmit(bond, skb2, slave->dev); } } + if (slave && bond_slave_is_up(slave) && slave->link == BOND_LINK_UP) + bond_dev_queue_xmit(bond, skb, slave->dev); + else + dev_kfree_skb_any(skb); -out: - if (res) { - /* no suitable interface, frame not sent */ - dev_kfree_skb(skb); - } - read_unlock(&bond->lock); - return 0; + return NETDEV_TX_OK; } +/*------------------------- Device initialization ---------------------------*/ + /* - * in broadcast mode, we send everything to all usable interfaces. + * Lookup the slave that corresponds to a qid */ -static int bond_xmit_broadcast(struct sk_buff *skb, struct net_device *bond_dev) +static inline int bond_slave_override(struct bonding *bond, + struct sk_buff *skb) { - struct bonding *bond = bond_dev->priv; - struct slave *slave, *start_at; - struct net_device *tx_dev = NULL; - int i; - int res = 1; + struct slave *slave = NULL; + struct list_head *iter; - read_lock(&bond->lock); + if (!skb->queue_mapping) + return 1; - if (!BOND_IS_OK(bond)) { - goto out; + /* Find out if any slaves have the same mapping as this skb. */ + bond_for_each_slave_rcu(bond, slave, iter) { + if (slave->queue_id == skb->queue_mapping) { + if (bond_slave_can_tx(slave)) { + bond_dev_queue_xmit(bond, skb, slave->dev); + return 0; + } + /* If the slave isn't UP, use default transmit policy. */ + break; + } } - read_lock(&bond->curr_slave_lock); - start_at = bond->curr_active_slave; - read_unlock(&bond->curr_slave_lock); - - if (!start_at) { - goto out; - } + return 1; +} - bond_for_each_slave_from(bond, slave, i, start_at) { - if (IS_UP(slave->dev) && - (slave->link == BOND_LINK_UP) && - (slave->state == BOND_STATE_ACTIVE)) { - if (tx_dev) { - struct sk_buff *skb2 = skb_clone(skb, GFP_ATOMIC); - if (!skb2) { - printk(KERN_ERR DRV_NAME - ": %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; - } - } +static u16 bond_select_queue(struct net_device *dev, struct sk_buff *skb, + void *accel_priv, select_queue_fallback_t fallback) +{ + /* + * 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; - if (tx_dev) { - res = bond_dev_queue_xmit(bond, skb, tx_dev); - } + /* + * Save the original txq to restore before passing to the driver + */ + qdisc_skb_cb(skb)->slave_dev_queue_mapping = skb->queue_mapping; -out: - if (res) { - /* no suitable interface, frame not sent */ - dev_kfree_skb(skb); + if (unlikely(txq >= dev->real_num_tx_queues)) { + do { + txq -= dev->real_num_tx_queues; + } while (txq >= dev->real_num_tx_queues); } - /* frame sent to all suitable interfaces */ - read_unlock(&bond->lock); - return 0; + return txq; } -/*------------------------- Device initialization ---------------------------*/ - -/* - * set bond mode specific net device operations - */ -void bond_set_mode_ops(struct bonding *bond, int mode) +static netdev_tx_t __bond_start_xmit(struct sk_buff *skb, struct net_device *dev) { - struct net_device *bond_dev = bond->dev; + struct bonding *bond = netdev_priv(dev); + + if (bond_should_override_tx_queue(bond) && + !bond_slave_override(bond, skb)) + return NETDEV_TX_OK; - switch (mode) { + switch (BOND_MODE(bond)) { case BOND_MODE_ROUNDROBIN: - bond_dev->hard_start_xmit = bond_xmit_roundrobin; - break; + return bond_xmit_roundrobin(skb, dev); case BOND_MODE_ACTIVEBACKUP: - bond_dev->hard_start_xmit = bond_xmit_activebackup; - break; + return bond_xmit_activebackup(skb, dev); case BOND_MODE_XOR: - bond_dev->hard_start_xmit = bond_xmit_xor; - if (bond->params.xmit_policy == BOND_XMIT_POLICY_LAYER34) - bond->xmit_hash_policy = bond_xmit_hash_policy_l34; - else - bond->xmit_hash_policy = bond_xmit_hash_policy_l2; - break; + return bond_xmit_xor(skb, dev); case BOND_MODE_BROADCAST: - bond_dev->hard_start_xmit = bond_xmit_broadcast; - break; + return bond_xmit_broadcast(skb, dev); case BOND_MODE_8023AD: - bond_dev->hard_start_xmit = bond_3ad_xmit_xor; - if (bond->params.xmit_policy == BOND_XMIT_POLICY_LAYER34) - bond->xmit_hash_policy = bond_xmit_hash_policy_l34; - else - bond->xmit_hash_policy = bond_xmit_hash_policy_l2; - break; - case BOND_MODE_TLB: + return bond_3ad_xmit_xor(skb, dev); case BOND_MODE_ALB: - bond_dev->hard_start_xmit = bond_alb_xmit; - bond_dev->set_mac_address = bond_alb_set_mac_address; - break; + return bond_alb_xmit(skb, dev); + case BOND_MODE_TLB: + return bond_tlb_xmit(skb, dev); default: /* Should never happen, mode already checked */ - printk(KERN_ERR DRV_NAME - ": %s: Error: Unknown bonding mode %d\n", - bond_dev->name, - mode); - break; + pr_err("%s: Error: Unknown bonding mode %d\n", + dev->name, BOND_MODE(bond)); + WARN_ON_ONCE(1); + dev_kfree_skb_any(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 (unlikely(is_netpoll_tx_blocked(dev))) + return NETDEV_TX_BUSY; + + rcu_read_lock(); + if (bond_has_slaves(bond)) + ret = __bond_start_xmit(skb, dev); + else + dev_kfree_skb_any(skb); + rcu_read_unlock(); + + return ret; +} + +static int bond_ethtool_get_settings(struct net_device *bond_dev, + struct ethtool_cmd *ecmd) +{ + struct bonding *bond = netdev_priv(bond_dev); + unsigned long speed = 0; + struct list_head *iter; + struct slave *slave; + + ecmd->duplex = DUPLEX_UNKNOWN; + ecmd->port = PORT_OTHER; + + /* Since bond_slave_can_tx returns false for all inactive or down slaves, we + * do not need to check mode. Though link speed might not represent + * the true receive or transmit bandwidth (not all modes are symmetric) + * this is an accurate maximum. + */ + read_lock(&bond->lock); + bond_for_each_slave(bond, slave, iter) { + if (bond_slave_can_tx(slave)) { + if (slave->speed != SPEED_UNKNOWN) + speed += slave->speed; + if (ecmd->duplex == DUPLEX_UNKNOWN && + slave->duplex != DUPLEX_UNKNOWN) + ecmd->duplex = slave->duplex; + } } + ethtool_cmd_speed_set(ecmd, speed ? : SPEED_UNKNOWN); + read_unlock(&bond->lock); + + return 0; } static void bond_ethtool_get_drvinfo(struct net_device *bond_dev, - struct ethtool_drvinfo *drvinfo) + 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); + strlcpy(drvinfo->driver, DRV_NAME, sizeof(drvinfo->driver)); + strlcpy(drvinfo->version, DRV_VERSION, sizeof(drvinfo->version)); + snprintf(drvinfo->fw_version, sizeof(drvinfo->fw_version), "%d", + BOND_ABI_VERSION); } -static struct ethtool_ops bond_ethtool_ops = { - .get_tx_csum = ethtool_op_get_tx_csum, - .get_sg = ethtool_op_get_sg, +static const struct ethtool_ops bond_ethtool_ops = { .get_drvinfo = bond_ethtool_get_drvinfo, + .get_settings = bond_ethtool_get_settings, + .get_link = ethtool_op_get_link, }; -/* - * Does not allocate but creates a /proc entry. - * Allowed to fail. - */ -static int bond_init(struct net_device *bond_dev, struct bond_params *params) +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_rx_mode, + .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 const struct device_type bond_type = { + .name = "bond", +}; + +static void bond_destructor(struct net_device *bond_dev) { - struct bonding *bond = bond_dev->priv; + struct bonding *bond = netdev_priv(bond_dev); + if (bond->wq) + destroy_workqueue(bond->wq); + free_netdev(bond_dev); +} - dprintk("Begin bond_init for %s\n", bond_dev->name); +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 = *params; /* copy params struct */ + bond->params = bonding_defaults; /* Initialize pointers */ - bond->first_slave = NULL; - bond->curr_active_slave = NULL; - bond->current_arp_slave = NULL; - bond->primary_slave = NULL; bond->dev = bond_dev; - INIT_LIST_HEAD(&bond->vlan_list); /* Initialize the device entry points */ - bond_dev->open = bond_open; - bond_dev->stop = bond_close; - bond_dev->get_stats = bond_get_stats; - bond_dev->do_ioctl = bond_do_ioctl; + ether_setup(bond_dev); + bond_dev->netdev_ops = &bond_netdev_ops; bond_dev->ethtool_ops = &bond_ethtool_ops; - bond_dev->set_multicast_list = bond_set_multicast_list; - bond_dev->change_mtu = bond_change_mtu; - bond_dev->set_mac_address = bond_set_mac_address; - bond_set_mode_ops(bond, bond->params.mode); + bond_dev->destructor = bond_destructor; - bond_dev->destructor = free_netdev; + SET_NETDEV_DEVTYPE(bond_dev, &bond_type); /* Initialize the device options */ bond_dev->tx_queue_len = 0; bond_dev->flags |= IFF_MASTER|IFF_MULTICAST; + bond_dev->priv_flags |= IFF_BONDING | IFF_UNICAST_FLT; + 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 @@ -4133,7 +3963,7 @@ static int bond_init(struct net_device *bond_dev, struct bond_params *params) */ bond_dev->features |= NETIF_F_VLAN_CHALLENGED; - /* don't acquire bond device's xmit_lock when + /* don't acquire bond device's netif_tx_lock when * transmitting */ bond_dev->features |= NETIF_F_LLTX; @@ -4143,202 +3973,188 @@ static int bond_init(struct net_device *bond_dev, struct bond_params *params) * when there are slaves that are not hw accel * capable */ - bond_dev->vlan_rx_register = bond_vlan_rx_register; - bond_dev->vlan_rx_add_vid = bond_vlan_rx_add_vid; - bond_dev->vlan_rx_kill_vid = bond_vlan_rx_kill_vid; - bond_dev->features |= (NETIF_F_HW_VLAN_TX | - NETIF_F_HW_VLAN_RX | - NETIF_F_HW_VLAN_FILTER); - -#ifdef CONFIG_PROC_FS - bond_create_proc_entry(bond); -#endif - list_add_tail(&bond->bond_list, &bond_dev_list); - - return 0; -} - -/* De-initialize device specific data. - * Caller must hold rtnl_lock. - */ -void bond_deinit(struct net_device *bond_dev) -{ - struct bonding *bond = bond_dev->priv; + /* Don't allow bond devices to change network namespaces. */ + bond_dev->features |= NETIF_F_NETNS_LOCAL; - list_del(&bond->bond_list); + bond_dev->hw_features = BOND_VLAN_FEATURES | + NETIF_F_HW_VLAN_CTAG_TX | + NETIF_F_HW_VLAN_CTAG_RX | + NETIF_F_HW_VLAN_CTAG_FILTER; -#ifdef CONFIG_PROC_FS - bond_remove_proc_entry(bond); -#endif + bond_dev->hw_features &= ~(NETIF_F_ALL_CSUM & ~NETIF_F_HW_CSUM); + bond_dev->hw_features |= NETIF_F_GSO_UDP_TUNNEL; + bond_dev->features |= bond_dev->hw_features; } -/* Unregister and free all bond devices. - * Caller must hold rtnl_lock. - */ -static void bond_free_all(void) +/* +* 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, *nxt; + struct bonding *bond = netdev_priv(bond_dev); + struct list_head *iter; + struct slave *slave; - list_for_each_entry_safe(bond, nxt, &bond_dev_list, bond_list) { - struct net_device *bond_dev = bond->dev; + bond_netpoll_cleanup(bond_dev); - unregister_netdevice(bond_dev); - bond_deinit(bond_dev); - } + /* Release the bonded slaves */ + bond_for_each_slave(bond, slave, iter) + __bond_release_one(bond_dev, slave->dev, true); + pr_info("%s: Released all slaves\n", bond_dev->name); -#ifdef CONFIG_PROC_FS - bond_destroy_proc_dir(); -#endif + list_del(&bond->bond_list); + + bond_debug_unregister(bond); } /*------------------------- Module initialization ---------------------------*/ -/* - * Convert string input module parms. Accept either the - * number of the mode or its string name. - */ -int bond_parse_parm(char *mode_arg, struct bond_parm_tbl *tbl) -{ - int i; - - for (i = 0; tbl[i].modename; i++) { - if ((isdigit(*mode_arg) && - tbl[i].mode == simple_strtol(mode_arg, NULL, 0)) || - (strncmp(mode_arg, tbl[i].modename, - strlen(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, i; + struct bond_opt_value newval; + const struct bond_opt_value *valptr; + int arp_all_targets_value; + /* * Convert string parameters. */ if (mode) { - bond_mode = bond_parse_parm(mode, bond_mode_tbl); - if (bond_mode == -1) { - printk(KERN_ERR DRV_NAME - ": Error: Invalid bonding mode \"%s\"\n", - mode == NULL ? "NULL" : mode); + bond_opt_initstr(&newval, mode); + valptr = bond_opt_parse(bond_opt_get(BOND_OPT_MODE), &newval); + if (!valptr) { + pr_err("Error: Invalid bonding mode \"%s\"\n", mode); return -EINVAL; } + bond_mode = valptr->value; } if (xmit_hash_policy) { if ((bond_mode != BOND_MODE_XOR) && - (bond_mode != BOND_MODE_8023AD)) { - printk(KERN_INFO DRV_NAME - ": xor_mode param is irrelevant in mode %s\n", - bond_mode_name(bond_mode)); + (bond_mode != BOND_MODE_8023AD) && + (bond_mode != BOND_MODE_TLB)) { + 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) { - printk(KERN_ERR DRV_NAME - ": Error: Invalid xmit_hash_policy \"%s\"\n", - xmit_hash_policy == NULL ? "NULL" : + bond_opt_initstr(&newval, xmit_hash_policy); + valptr = bond_opt_parse(bond_opt_get(BOND_OPT_XMIT_HASH), + &newval); + if (!valptr) { + pr_err("Error: Invalid xmit_hash_policy \"%s\"\n", xmit_hash_policy); return -EINVAL; } + xmit_hashtype = valptr->value; } } if (lacp_rate) { if (bond_mode != BOND_MODE_8023AD) { - printk(KERN_INFO DRV_NAME - ": lacp_rate param is irrelevant in mode %s\n", - bond_mode_name(bond_mode)); + 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) { - printk(KERN_ERR DRV_NAME - ": Error: Invalid lacp rate \"%s\"\n", - lacp_rate == NULL ? "NULL" : lacp_rate); + bond_opt_initstr(&newval, lacp_rate); + valptr = bond_opt_parse(bond_opt_get(BOND_OPT_LACP_RATE), + &newval); + if (!valptr) { + pr_err("Error: Invalid lacp rate \"%s\"\n", + lacp_rate); return -EINVAL; } + lacp_fast = valptr->value; + } + } + + if (ad_select) { + bond_opt_initstr(&newval, ad_select); + valptr = bond_opt_parse(bond_opt_get(BOND_OPT_AD_SELECT), + &newval); + if (!valptr) { + pr_err("Error: Invalid ad_select \"%s\"\n", ad_select); + return -EINVAL; } + params->ad_select = valptr->value; + if (bond_mode != BOND_MODE_8023AD) + pr_warn("ad_select param only affects 802.3ad mode\n"); + } else { + params->ad_select = BOND_AD_STABLE; } - if (max_bonds < 1 || max_bonds > INT_MAX) { - printk(KERN_WARNING DRV_NAME - ": Warning: max_bonds (%d) not in range %d-%d, so it " - "was reset to BOND_DEFAULT_MAX_BONDS (%d)\n", - max_bonds, 1, INT_MAX, BOND_DEFAULT_MAX_BONDS); + if (max_bonds < 0) { + pr_warn("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) { - printk(KERN_WARNING DRV_NAME - ": 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; + pr_warn("Warning: miimon module parameter (%d), not in range 0-%d, so it was reset to 0\n", + miimon, INT_MAX); + miimon = 0; } if (updelay < 0) { - printk(KERN_WARNING DRV_NAME - ": Warning: updelay module parameter (%d), " - "not in range 0-%d, so it was reset to 0\n", - updelay, INT_MAX); + pr_warn("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) { - printk(KERN_WARNING DRV_NAME - ": Warning: downdelay module parameter (%d), " - "not in range 0-%d, so it was reset to 0\n", - downdelay, INT_MAX); + pr_warn("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)) { - printk(KERN_WARNING DRV_NAME - ": Warning: use_carrier module parameter (%d), " - "not of valid value (0/1), so it was set to 1\n", - use_carrier); + pr_warn("Warning: use_carrier module parameter (%d), not of valid value (0/1), so it was set to 1\n", + use_carrier); use_carrier = 1; } - /* reset values for 802.3ad */ - if (bond_mode == BOND_MODE_8023AD) { - if (!miimon) { - printk(KERN_WARNING DRV_NAME - ": Warning: miimon must be specified, " - "otherwise bonding will not detect link " - "failure, speed and duplex which are " - "essential for 802.3ad operation\n"); - printk(KERN_WARNING "Forcing miimon to 100msec\n"); - miimon = 100; - } + if (num_peer_notif < 0 || num_peer_notif > 255) { + pr_warn("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 TLB/ALB */ - if ((bond_mode == BOND_MODE_TLB) || - (bond_mode == BOND_MODE_ALB)) { + /* reset values for 802.3ad/TLB/ALB */ + if (!bond_mode_uses_arp(bond_mode)) { if (!miimon) { - printk(KERN_WARNING DRV_NAME - ": Warning: miimon must be specified, " - "otherwise bonding will not detect link " - "failure and link speed which are essential " - "for TLB/ALB load balancing\n"); - printk(KERN_WARNING "Forcing miimon to 100msec\n"); - miimon = 100; + pr_warn("Warning: miimon must be specified, otherwise bonding will not detect link failure, speed and duplex which are essential for 802.3ad operation\n"); + pr_warn("Forcing miimon to 100msec\n"); + miimon = BOND_DEFAULT_MIIMON; } } + if (tx_queues < 1 || tx_queues > 255) { + pr_warn("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_warn("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_warn("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; + } + + bond_opt_initval(&newval, packets_per_slave); + if (!bond_opt_parse(bond_opt_get(BOND_OPT_PACKETS_PER_SLAVE), &newval)) { + pr_warn("Warning: packets_per_slave (%d) should be between 0 and %u resetting to 1\n", + packets_per_slave, USHRT_MAX); + packets_per_slave = 1; + } + if (bond_mode == BOND_MODE_ALB) { - printk(KERN_NOTICE DRV_NAME - ": 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); + 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) { @@ -4346,127 +4162,195 @@ static int bond_check_params(struct bond_params *params) /* just warn the user the up/down delay will have * no effect since miimon is zero... */ - printk(KERN_WARNING DRV_NAME - ": 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); + pr_warn("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) { - printk(KERN_WARNING DRV_NAME - ": Warning: miimon (%d) and arp_interval (%d) " - "can't be used simultaneously, disabling ARP " - "monitoring\n", - miimon, arp_interval); + pr_warn("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) { - printk(KERN_WARNING DRV_NAME - ": Warning: updelay (%d) is not a multiple " - "of miimon (%d), updelay rounded to %d ms\n", - updelay, miimon, (updelay / miimon) * miimon); + pr_warn("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) { - printk(KERN_WARNING DRV_NAME - ": Warning: downdelay (%d) is not a multiple " - "of miimon (%d), downdelay rounded to %d ms\n", - downdelay, miimon, - (downdelay / miimon) * miimon); + pr_warn("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) { - printk(KERN_WARNING DRV_NAME - ": 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; + pr_warn("Warning: arp_interval module parameter (%d), not in range 0-%d, so it was reset to 0\n", + arp_interval, INT_MAX); + arp_interval = 0; } - for (arp_ip_count = 0; - (arp_ip_count < BOND_MAX_ARP_TARGETS) && arp_ip_target[arp_ip_count]; - arp_ip_count++) { + for (arp_ip_count = 0, i = 0; + (arp_ip_count < BOND_MAX_ARP_TARGETS) && arp_ip_target[i]; i++) { /* not complete check, but should be good enough to catch mistakes */ - if (!isdigit(arp_ip_target[arp_ip_count][0])) { - printk(KERN_WARNING DRV_NAME - ": Warning: bad arp_ip_target module parameter " - "(%s), ARP monitoring will not be performed\n", - arp_ip_target[arp_ip_count]); + __be32 ip; + if (!in4_pton(arp_ip_target[i], -1, (u8 *)&ip, -1, NULL) || + !bond_is_ip_target_ok(ip)) { + pr_warn("Warning: bad arp_ip_target module parameter (%s), ARP monitoring will not be performed\n", + arp_ip_target[i]); arp_interval = 0; } else { - u32 ip = in_aton(arp_ip_target[arp_ip_count]); - arp_target[arp_ip_count] = ip; + if (bond_get_targets_ip(arp_target, ip) == -1) + arp_target[arp_ip_count++] = ip; + else + pr_warn("Warning: duplicate address %pI4 in arp_ip_target, skipping\n", + &ip); } } if (arp_interval && !arp_ip_count) { /* don't allow arping if no arp_ip_target given... */ - printk(KERN_WARNING DRV_NAME - ": Warning: arp_interval module parameter (%d) " - "specified without providing an arp_ip_target " - "parameter, arp_interval was reset to 0\n", - arp_interval); + pr_warn("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 (!arp_interval) { + pr_err("arp_validate requires arp_interval\n"); + return -EINVAL; + } + + bond_opt_initstr(&newval, arp_validate); + valptr = bond_opt_parse(bond_opt_get(BOND_OPT_ARP_VALIDATE), + &newval); + if (!valptr) { + pr_err("Error: invalid arp_validate \"%s\"\n", + arp_validate); + return -EINVAL; + } + arp_validate_value = valptr->value; + } else { + arp_validate_value = 0; + } + + arp_all_targets_value = 0; + if (arp_all_targets) { + bond_opt_initstr(&newval, arp_all_targets); + valptr = bond_opt_parse(bond_opt_get(BOND_OPT_ARP_ALL_TARGETS), + &newval); + if (!valptr) { + pr_err("Error: invalid arp_all_targets_value \"%s\"\n", + arp_all_targets); + arp_all_targets_value = 0; + } else { + arp_all_targets_value = valptr->value; + } + } + if (miimon) { - printk(KERN_INFO DRV_NAME - ": MII link monitoring set to %d ms\n", - miimon); + pr_info("MII link monitoring set to %d ms\n", miimon); } else if (arp_interval) { - int i; - - printk(KERN_INFO DRV_NAME - ": ARP monitoring set to %d ms with %d target(s):", - arp_interval, arp_ip_count); + valptr = bond_opt_get_val(BOND_OPT_ARP_VALIDATE, + arp_validate_value); + pr_info("ARP monitoring set to %d ms, validate %s, with %d target(s):", + arp_interval, valptr->string, arp_ip_count); for (i = 0; i < arp_ip_count; i++) - printk (" %s", arp_ip_target[i]); + pr_cont(" %s", arp_ip_target[i]); - printk("\n"); + pr_cont("\n"); - } else { + } else if (max_bonds) { /* miimon and arp_interval not set, we need one so things * work as expected, see bonding.txt for details */ - printk(KERN_WARNING DRV_NAME - ": 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"); + 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)) { + if (primary && !bond_mode_uses_primary(bond_mode)) { /* currently, using a primary only makes sense * in active backup, TLB or ALB modes */ - printk(KERN_WARNING DRV_NAME - ": Warning: %s primary device specified but has no " - "effect in %s mode\n", - primary, bond_mode_name(bond_mode)); + pr_warn("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) { + bond_opt_initstr(&newval, primary_reselect); + valptr = bond_opt_parse(bond_opt_get(BOND_OPT_PRIMARY_RESELECT), + &newval); + if (!valptr) { + pr_err("Error: Invalid primary_reselect \"%s\"\n", + primary_reselect); + return -EINVAL; + } + primary_reselect_value = valptr->value; + } else { + primary_reselect_value = BOND_PRI_RESELECT_ALWAYS; + } + + if (fail_over_mac) { + bond_opt_initstr(&newval, fail_over_mac); + valptr = bond_opt_parse(bond_opt_get(BOND_OPT_FAIL_OVER_MAC), + &newval); + if (!valptr) { + pr_err("Error: invalid fail_over_mac \"%s\"\n", + fail_over_mac); + return -EINVAL; + } + fail_over_mac_value = valptr->value; + if (bond_mode != BOND_MODE_ACTIVEBACKUP) + pr_warn("Warning: fail_over_mac only affects active-backup mode\n"); + } else { + fail_over_mac_value = BOND_FOM_NONE; + } + + if (lp_interval == 0) { + pr_warn("Warning: ip_interval must be between 1 and %d, so it was reset to %d\n", + INT_MAX, BOND_ALB_DEFAULT_LP_INTERVAL); + lp_interval = BOND_ALB_DEFAULT_LP_INTERVAL; + } + /* 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->arp_all_targets = arp_all_targets_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; + params->lp_interval = lp_interval; + params->packets_per_slave = packets_per_slave; + params->tlb_dynamic_lb = 1; /* Default value */ + if (packets_per_slave > 0) { + params->reciprocal_packets_per_slave = + reciprocal_value(packets_per_slave); + } else { + /* reciprocal_packets_per_slave is unused if + * packets_per_slave is 0 or 1, just initialize it + */ + params->reciprocal_packets_per_slave = + (struct reciprocal_value) { 0 }; + } if (primary) { strncpy(params->primary, primary, IFNAMSIZ); @@ -4478,107 +4362,196 @@ static int bond_check_params(struct bond_params *params) return 0; } +static struct lock_class_key bonding_netdev_xmit_lock_key; +static struct lock_class_key bonding_netdev_addr_lock_key; +static struct lock_class_key bonding_tx_busylock_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); + dev->qdisc_tx_busylock = &bonding_tx_busylock_key; +} + +/* + * 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); + + list_add_tail(&bond->bond_list, &bn->dev_list); + + bond_prepare_sysfs_group(bond); + + bond_debug_register(bond); + + /* Ensure valid dev_addr */ + if (is_zero_ether_addr(bond_dev->dev_addr) && + bond_dev->addr_assign_type == NET_ADDR_PERM) + eth_hw_addr_random(bond_dev); + + return 0; +} + +unsigned int bond_get_num_tx_queues(void) +{ + return 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(char *name, struct bond_params *params, struct bonding **newbond) +int bond_create(struct net *net, const char *name) { struct net_device *bond_dev; int res; rtnl_lock(); - bond_dev = alloc_netdev(sizeof(struct bonding), name, ether_setup); + + bond_dev = alloc_netdev_mq(sizeof(struct bonding), + name ? name : "bond%d", + bond_setup, tx_queues); if (!bond_dev) { - printk(KERN_ERR DRV_NAME - ": %s: eek! can't alloc netdev!\n", - name); - res = -ENOMEM; - goto out_rtnl; + pr_err("%s: eek! can't alloc netdev!\n", name); + rtnl_unlock(); + return -ENOMEM; } - /* bond_init() must be called after dev_alloc_name() (for the - * /proc files), but before register_netdevice(), because we - * need to set function pointers. - */ + dev_net_set(bond_dev, net); + bond_dev->rtnl_link_ops = &bond_link_ops; - res = bond_init(bond_dev, params); - if (res < 0) { - goto out_netdev; - } + res = register_netdevice(bond_dev); - SET_MODULE_OWNER(bond_dev); + netif_carrier_off(bond_dev); - res = register_netdevice(bond_dev); - if (res < 0) { - goto out_bond; - } - if (newbond) - *newbond = bond_dev->priv; - - rtnl_unlock(); /* allows sysfs registration of net device */ - res = bond_create_sysfs_entry(bond_dev->priv); - goto done; -out_bond: - bond_deinit(bond_dev); -out_netdev: - free_netdev(bond_dev); -out_rtnl: rtnl_unlock(); -done: + 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); + struct bonding *bond, *tmp_bond; + LIST_HEAD(list); + + bond_destroy_sysfs(bn); + bond_destroy_proc_dir(bn); + + /* Kill off any bonds created after unregistering bond rtnl ops */ + rtnl_lock(); + list_for_each_entry_safe(bond, tmp_bond, &bn->dev_list, bond_list) + unregister_netdevice_queue(bond->dev, &list); + unregister_netdevice_many(&list); + rtnl_unlock(); +} + +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; - char new_bond_name[8]; /* Enough room for 999 bonds at init. */ - printk(KERN_INFO "%s", version); + pr_info("%s", bond_version); res = bond_check_params(&bonding_defaults); - if (res) { + if (res) goto out; - } -#ifdef CONFIG_PROC_FS - bond_create_proc_dir(); -#endif + res = register_pernet_subsys(&bond_net_ops); + if (res) + goto out; + + res = bond_netlink_init(); + if (res) + goto err_link; + + bond_create_debugfs(); + for (i = 0; i < max_bonds; i++) { - sprintf(new_bond_name, "bond%d",i); - res = bond_create(new_bond_name,&bonding_defaults, NULL); + res = bond_create(&init_net, NULL); if (res) goto err; } - res = bond_create_sysfs(); - if (res) - goto err; - register_netdevice_notifier(&bond_netdev_notifier); - register_inetaddr_notifier(&bond_inetaddr_notifier); - - goto out; -err: - rtnl_lock(); - bond_free_all(); - bond_destroy_sysfs(); - rtnl_unlock(); out: return res; +err: + bond_destroy_debugfs(); + bond_netlink_fini(); +err_link: + unregister_pernet_subsys(&bond_net_ops); + goto out; } static void __exit bonding_exit(void) { unregister_netdevice_notifier(&bond_netdev_notifier); - unregister_inetaddr_notifier(&bond_inetaddr_notifier); - rtnl_lock(); - bond_free_all(); - bond_destroy_sysfs(); - rtnl_unlock(); + bond_destroy_debugfs(); + + bond_netlink_fini(); + 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); @@ -4587,13 +4560,3 @@ 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_SUPPORTED_DEVICE("most ethernet devices"); - -/* - * Local variables: - * c-indent-level: 8 - * c-basic-offset: 8 - * tab-width: 8 - * End: - */ - diff --git a/drivers/net/bonding/bond_netlink.c b/drivers/net/bonding/bond_netlink.c new file mode 100644 index 00000000000..5ab3c1847e6 --- /dev/null +++ b/drivers/net/bonding/bond_netlink.c @@ -0,0 +1,573 @@ +/* + * drivers/net/bond/bond_netlink.c - Netlink interface for bonding + * Copyright (c) 2013 Jiri Pirko <jiri@resnulli.us> + * Copyright (c) 2013 Scott Feldman <sfeldma@cumulusnetworks.com> + * + * This program is free software; you can redistribute it and/or modify + * it under the terms of the GNU General Public License as published by + * the Free Software Foundation; either version 2 of the License, or + * (at your option) any later version. + */ + +#define pr_fmt(fmt) KBUILD_MODNAME ": " fmt + +#include <linux/module.h> +#include <linux/errno.h> +#include <linux/netdevice.h> +#include <linux/etherdevice.h> +#include <linux/if_link.h> +#include <linux/if_ether.h> +#include <net/netlink.h> +#include <net/rtnetlink.h> +#include "bonding.h" + +static size_t bond_get_slave_size(const struct net_device *bond_dev, + const struct net_device *slave_dev) +{ + return nla_total_size(sizeof(u8)) + /* IFLA_BOND_SLAVE_STATE */ + nla_total_size(sizeof(u8)) + /* IFLA_BOND_SLAVE_MII_STATUS */ + nla_total_size(sizeof(u32)) + /* IFLA_BOND_SLAVE_LINK_FAILURE_COUNT */ + nla_total_size(MAX_ADDR_LEN) + /* IFLA_BOND_SLAVE_PERM_HWADDR */ + nla_total_size(sizeof(u16)) + /* IFLA_BOND_SLAVE_QUEUE_ID */ + nla_total_size(sizeof(u16)) + /* IFLA_BOND_SLAVE_AD_AGGREGATOR_ID */ + 0; +} + +static int bond_fill_slave_info(struct sk_buff *skb, + const struct net_device *bond_dev, + const struct net_device *slave_dev) +{ + struct slave *slave = bond_slave_get_rtnl(slave_dev); + + if (nla_put_u8(skb, IFLA_BOND_SLAVE_STATE, bond_slave_state(slave))) + goto nla_put_failure; + + if (nla_put_u8(skb, IFLA_BOND_SLAVE_MII_STATUS, slave->link)) + goto nla_put_failure; + + if (nla_put_u32(skb, IFLA_BOND_SLAVE_LINK_FAILURE_COUNT, + slave->link_failure_count)) + goto nla_put_failure; + + if (nla_put(skb, IFLA_BOND_SLAVE_PERM_HWADDR, + slave_dev->addr_len, slave->perm_hwaddr)) + goto nla_put_failure; + + if (nla_put_u16(skb, IFLA_BOND_SLAVE_QUEUE_ID, slave->queue_id)) + goto nla_put_failure; + + if (BOND_MODE(slave->bond) == BOND_MODE_8023AD) { + const struct aggregator *agg; + + agg = SLAVE_AD_INFO(slave)->port.aggregator; + if (agg) + if (nla_put_u16(skb, IFLA_BOND_SLAVE_AD_AGGREGATOR_ID, + agg->aggregator_identifier)) + goto nla_put_failure; + } + + return 0; + +nla_put_failure: + return -EMSGSIZE; +} + +static const struct nla_policy bond_policy[IFLA_BOND_MAX + 1] = { + [IFLA_BOND_MODE] = { .type = NLA_U8 }, + [IFLA_BOND_ACTIVE_SLAVE] = { .type = NLA_U32 }, + [IFLA_BOND_MIIMON] = { .type = NLA_U32 }, + [IFLA_BOND_UPDELAY] = { .type = NLA_U32 }, + [IFLA_BOND_DOWNDELAY] = { .type = NLA_U32 }, + [IFLA_BOND_USE_CARRIER] = { .type = NLA_U8 }, + [IFLA_BOND_ARP_INTERVAL] = { .type = NLA_U32 }, + [IFLA_BOND_ARP_IP_TARGET] = { .type = NLA_NESTED }, + [IFLA_BOND_ARP_VALIDATE] = { .type = NLA_U32 }, + [IFLA_BOND_ARP_ALL_TARGETS] = { .type = NLA_U32 }, + [IFLA_BOND_PRIMARY] = { .type = NLA_U32 }, + [IFLA_BOND_PRIMARY_RESELECT] = { .type = NLA_U8 }, + [IFLA_BOND_FAIL_OVER_MAC] = { .type = NLA_U8 }, + [IFLA_BOND_XMIT_HASH_POLICY] = { .type = NLA_U8 }, + [IFLA_BOND_RESEND_IGMP] = { .type = NLA_U32 }, + [IFLA_BOND_NUM_PEER_NOTIF] = { .type = NLA_U8 }, + [IFLA_BOND_ALL_SLAVES_ACTIVE] = { .type = NLA_U8 }, + [IFLA_BOND_MIN_LINKS] = { .type = NLA_U32 }, + [IFLA_BOND_LP_INTERVAL] = { .type = NLA_U32 }, + [IFLA_BOND_PACKETS_PER_SLAVE] = { .type = NLA_U32 }, + [IFLA_BOND_AD_LACP_RATE] = { .type = NLA_U8 }, + [IFLA_BOND_AD_SELECT] = { .type = NLA_U8 }, + [IFLA_BOND_AD_INFO] = { .type = NLA_NESTED }, +}; + +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_changelink(struct net_device *bond_dev, + struct nlattr *tb[], struct nlattr *data[]) +{ + struct bonding *bond = netdev_priv(bond_dev); + struct bond_opt_value newval; + int miimon = 0; + int err; + + if (!data) + return 0; + + if (data[IFLA_BOND_MODE]) { + int mode = nla_get_u8(data[IFLA_BOND_MODE]); + + bond_opt_initval(&newval, mode); + err = __bond_opt_set(bond, BOND_OPT_MODE, &newval); + if (err) + return err; + } + if (data[IFLA_BOND_ACTIVE_SLAVE]) { + int ifindex = nla_get_u32(data[IFLA_BOND_ACTIVE_SLAVE]); + struct net_device *slave_dev; + char *active_slave = ""; + + if (ifindex != 0) { + slave_dev = __dev_get_by_index(dev_net(bond_dev), + ifindex); + if (!slave_dev) + return -ENODEV; + active_slave = slave_dev->name; + } + bond_opt_initstr(&newval, active_slave); + err = __bond_opt_set(bond, BOND_OPT_ACTIVE_SLAVE, &newval); + if (err) + return err; + } + if (data[IFLA_BOND_MIIMON]) { + miimon = nla_get_u32(data[IFLA_BOND_MIIMON]); + + bond_opt_initval(&newval, miimon); + err = __bond_opt_set(bond, BOND_OPT_MIIMON, &newval); + if (err) + return err; + } + if (data[IFLA_BOND_UPDELAY]) { + int updelay = nla_get_u32(data[IFLA_BOND_UPDELAY]); + + bond_opt_initval(&newval, updelay); + err = __bond_opt_set(bond, BOND_OPT_UPDELAY, &newval); + if (err) + return err; + } + if (data[IFLA_BOND_DOWNDELAY]) { + int downdelay = nla_get_u32(data[IFLA_BOND_DOWNDELAY]); + + bond_opt_initval(&newval, downdelay); + err = __bond_opt_set(bond, BOND_OPT_DOWNDELAY, &newval); + if (err) + return err; + } + if (data[IFLA_BOND_USE_CARRIER]) { + int use_carrier = nla_get_u8(data[IFLA_BOND_USE_CARRIER]); + + bond_opt_initval(&newval, use_carrier); + err = __bond_opt_set(bond, BOND_OPT_USE_CARRIER, &newval); + if (err) + return err; + } + if (data[IFLA_BOND_ARP_INTERVAL]) { + int arp_interval = nla_get_u32(data[IFLA_BOND_ARP_INTERVAL]); + + if (arp_interval && miimon) { + pr_err("%s: ARP monitoring cannot be used with MII monitoring\n", + bond->dev->name); + return -EINVAL; + } + + bond_opt_initval(&newval, arp_interval); + err = __bond_opt_set(bond, BOND_OPT_ARP_INTERVAL, &newval); + if (err) + return err; + } + if (data[IFLA_BOND_ARP_IP_TARGET]) { + struct nlattr *attr; + int i = 0, rem; + + bond_option_arp_ip_targets_clear(bond); + nla_for_each_nested(attr, data[IFLA_BOND_ARP_IP_TARGET], rem) { + __be32 target = nla_get_be32(attr); + + bond_opt_initval(&newval, (__force u64)target); + err = __bond_opt_set(bond, BOND_OPT_ARP_TARGETS, + &newval); + if (err) + break; + i++; + } + if (i == 0 && bond->params.arp_interval) + pr_warn("%s: Removing last arp target with arp_interval on\n", + bond->dev->name); + if (err) + return err; + } + if (data[IFLA_BOND_ARP_VALIDATE]) { + int arp_validate = nla_get_u32(data[IFLA_BOND_ARP_VALIDATE]); + + if (arp_validate && miimon) { + pr_err("%s: ARP validating cannot be used with MII monitoring\n", + bond->dev->name); + return -EINVAL; + } + + bond_opt_initval(&newval, arp_validate); + err = __bond_opt_set(bond, BOND_OPT_ARP_VALIDATE, &newval); + if (err) + return err; + } + if (data[IFLA_BOND_ARP_ALL_TARGETS]) { + int arp_all_targets = + nla_get_u32(data[IFLA_BOND_ARP_ALL_TARGETS]); + + bond_opt_initval(&newval, arp_all_targets); + err = __bond_opt_set(bond, BOND_OPT_ARP_ALL_TARGETS, &newval); + if (err) + return err; + } + if (data[IFLA_BOND_PRIMARY]) { + int ifindex = nla_get_u32(data[IFLA_BOND_PRIMARY]); + struct net_device *dev; + char *primary = ""; + + dev = __dev_get_by_index(dev_net(bond_dev), ifindex); + if (dev) + primary = dev->name; + + bond_opt_initstr(&newval, primary); + err = __bond_opt_set(bond, BOND_OPT_PRIMARY, &newval); + if (err) + return err; + } + if (data[IFLA_BOND_PRIMARY_RESELECT]) { + int primary_reselect = + nla_get_u8(data[IFLA_BOND_PRIMARY_RESELECT]); + + bond_opt_initval(&newval, primary_reselect); + err = __bond_opt_set(bond, BOND_OPT_PRIMARY_RESELECT, &newval); + if (err) + return err; + } + if (data[IFLA_BOND_FAIL_OVER_MAC]) { + int fail_over_mac = + nla_get_u8(data[IFLA_BOND_FAIL_OVER_MAC]); + + bond_opt_initval(&newval, fail_over_mac); + err = __bond_opt_set(bond, BOND_OPT_FAIL_OVER_MAC, &newval); + if (err) + return err; + } + if (data[IFLA_BOND_XMIT_HASH_POLICY]) { + int xmit_hash_policy = + nla_get_u8(data[IFLA_BOND_XMIT_HASH_POLICY]); + + bond_opt_initval(&newval, xmit_hash_policy); + err = __bond_opt_set(bond, BOND_OPT_XMIT_HASH, &newval); + if (err) + return err; + } + if (data[IFLA_BOND_RESEND_IGMP]) { + int resend_igmp = + nla_get_u32(data[IFLA_BOND_RESEND_IGMP]); + + bond_opt_initval(&newval, resend_igmp); + err = __bond_opt_set(bond, BOND_OPT_RESEND_IGMP, &newval); + if (err) + return err; + } + if (data[IFLA_BOND_NUM_PEER_NOTIF]) { + int num_peer_notif = + nla_get_u8(data[IFLA_BOND_NUM_PEER_NOTIF]); + + bond_opt_initval(&newval, num_peer_notif); + err = __bond_opt_set(bond, BOND_OPT_NUM_PEER_NOTIF, &newval); + if (err) + return err; + } + if (data[IFLA_BOND_ALL_SLAVES_ACTIVE]) { + int all_slaves_active = + nla_get_u8(data[IFLA_BOND_ALL_SLAVES_ACTIVE]); + + bond_opt_initval(&newval, all_slaves_active); + err = __bond_opt_set(bond, BOND_OPT_ALL_SLAVES_ACTIVE, &newval); + if (err) + return err; + } + if (data[IFLA_BOND_MIN_LINKS]) { + int min_links = + nla_get_u32(data[IFLA_BOND_MIN_LINKS]); + + bond_opt_initval(&newval, min_links); + err = __bond_opt_set(bond, BOND_OPT_MINLINKS, &newval); + if (err) + return err; + } + if (data[IFLA_BOND_LP_INTERVAL]) { + int lp_interval = + nla_get_u32(data[IFLA_BOND_LP_INTERVAL]); + + bond_opt_initval(&newval, lp_interval); + err = __bond_opt_set(bond, BOND_OPT_LP_INTERVAL, &newval); + if (err) + return err; + } + if (data[IFLA_BOND_PACKETS_PER_SLAVE]) { + int packets_per_slave = + nla_get_u32(data[IFLA_BOND_PACKETS_PER_SLAVE]); + + bond_opt_initval(&newval, packets_per_slave); + err = __bond_opt_set(bond, BOND_OPT_PACKETS_PER_SLAVE, &newval); + if (err) + return err; + } + if (data[IFLA_BOND_AD_LACP_RATE]) { + int lacp_rate = + nla_get_u8(data[IFLA_BOND_AD_LACP_RATE]); + + bond_opt_initval(&newval, lacp_rate); + err = __bond_opt_set(bond, BOND_OPT_LACP_RATE, &newval); + if (err) + return err; + } + if (data[IFLA_BOND_AD_SELECT]) { + int ad_select = + nla_get_u8(data[IFLA_BOND_AD_SELECT]); + + bond_opt_initval(&newval, ad_select); + err = __bond_opt_set(bond, BOND_OPT_AD_SELECT, &newval); + if (err) + return err; + } + return 0; +} + +static int bond_newlink(struct net *src_net, struct net_device *bond_dev, + struct nlattr *tb[], struct nlattr *data[]) +{ + int err; + + err = bond_changelink(bond_dev, tb, data); + if (err < 0) + return err; + + return register_netdevice(bond_dev); +} + +static size_t bond_get_size(const struct net_device *bond_dev) +{ + return nla_total_size(sizeof(u8)) + /* IFLA_BOND_MODE */ + nla_total_size(sizeof(u32)) + /* IFLA_BOND_ACTIVE_SLAVE */ + nla_total_size(sizeof(u32)) + /* IFLA_BOND_MIIMON */ + nla_total_size(sizeof(u32)) + /* IFLA_BOND_UPDELAY */ + nla_total_size(sizeof(u32)) + /* IFLA_BOND_DOWNDELAY */ + nla_total_size(sizeof(u8)) + /* IFLA_BOND_USE_CARRIER */ + nla_total_size(sizeof(u32)) + /* IFLA_BOND_ARP_INTERVAL */ + /* IFLA_BOND_ARP_IP_TARGET */ + nla_total_size(sizeof(struct nlattr)) + + nla_total_size(sizeof(u32)) * BOND_MAX_ARP_TARGETS + + nla_total_size(sizeof(u32)) + /* IFLA_BOND_ARP_VALIDATE */ + nla_total_size(sizeof(u32)) + /* IFLA_BOND_ARP_ALL_TARGETS */ + nla_total_size(sizeof(u32)) + /* IFLA_BOND_PRIMARY */ + nla_total_size(sizeof(u8)) + /* IFLA_BOND_PRIMARY_RESELECT */ + nla_total_size(sizeof(u8)) + /* IFLA_BOND_FAIL_OVER_MAC */ + nla_total_size(sizeof(u8)) + /* IFLA_BOND_XMIT_HASH_POLICY */ + nla_total_size(sizeof(u32)) + /* IFLA_BOND_RESEND_IGMP */ + nla_total_size(sizeof(u8)) + /* IFLA_BOND_NUM_PEER_NOTIF */ + nla_total_size(sizeof(u8)) + /* IFLA_BOND_ALL_SLAVES_ACTIVE */ + nla_total_size(sizeof(u32)) + /* IFLA_BOND_MIN_LINKS */ + nla_total_size(sizeof(u32)) + /* IFLA_BOND_LP_INTERVAL */ + nla_total_size(sizeof(u32)) + /* IFLA_BOND_PACKETS_PER_SLAVE */ + nla_total_size(sizeof(u8)) + /* IFLA_BOND_AD_LACP_RATE */ + nla_total_size(sizeof(u8)) + /* IFLA_BOND_AD_SELECT */ + nla_total_size(sizeof(struct nlattr)) + /* IFLA_BOND_AD_INFO */ + nla_total_size(sizeof(u16)) + /* IFLA_BOND_AD_INFO_AGGREGATOR */ + nla_total_size(sizeof(u16)) + /* IFLA_BOND_AD_INFO_NUM_PORTS */ + nla_total_size(sizeof(u16)) + /* IFLA_BOND_AD_INFO_ACTOR_KEY */ + nla_total_size(sizeof(u16)) + /* IFLA_BOND_AD_INFO_PARTNER_KEY*/ + nla_total_size(ETH_ALEN) + /* IFLA_BOND_AD_INFO_PARTNER_MAC*/ + 0; +} + +static int bond_fill_info(struct sk_buff *skb, + const struct net_device *bond_dev) +{ + struct bonding *bond = netdev_priv(bond_dev); + struct net_device *slave_dev = bond_option_active_slave_get(bond); + struct nlattr *targets; + unsigned int packets_per_slave; + int i, targets_added; + + if (nla_put_u8(skb, IFLA_BOND_MODE, BOND_MODE(bond))) + goto nla_put_failure; + + if (slave_dev && + nla_put_u32(skb, IFLA_BOND_ACTIVE_SLAVE, slave_dev->ifindex)) + goto nla_put_failure; + + if (nla_put_u32(skb, IFLA_BOND_MIIMON, bond->params.miimon)) + goto nla_put_failure; + + if (nla_put_u32(skb, IFLA_BOND_UPDELAY, + bond->params.updelay * bond->params.miimon)) + goto nla_put_failure; + + if (nla_put_u32(skb, IFLA_BOND_DOWNDELAY, + bond->params.downdelay * bond->params.miimon)) + goto nla_put_failure; + + if (nla_put_u8(skb, IFLA_BOND_USE_CARRIER, bond->params.use_carrier)) + goto nla_put_failure; + + if (nla_put_u32(skb, IFLA_BOND_ARP_INTERVAL, bond->params.arp_interval)) + goto nla_put_failure; + + targets = nla_nest_start(skb, IFLA_BOND_ARP_IP_TARGET); + if (!targets) + goto nla_put_failure; + + targets_added = 0; + for (i = 0; i < BOND_MAX_ARP_TARGETS; i++) { + if (bond->params.arp_targets[i]) { + nla_put_be32(skb, i, bond->params.arp_targets[i]); + targets_added = 1; + } + } + + if (targets_added) + nla_nest_end(skb, targets); + else + nla_nest_cancel(skb, targets); + + if (nla_put_u32(skb, IFLA_BOND_ARP_VALIDATE, bond->params.arp_validate)) + goto nla_put_failure; + + if (nla_put_u32(skb, IFLA_BOND_ARP_ALL_TARGETS, + bond->params.arp_all_targets)) + goto nla_put_failure; + + if (bond->primary_slave && + nla_put_u32(skb, IFLA_BOND_PRIMARY, + bond->primary_slave->dev->ifindex)) + goto nla_put_failure; + + if (nla_put_u8(skb, IFLA_BOND_PRIMARY_RESELECT, + bond->params.primary_reselect)) + goto nla_put_failure; + + if (nla_put_u8(skb, IFLA_BOND_FAIL_OVER_MAC, + bond->params.fail_over_mac)) + goto nla_put_failure; + + if (nla_put_u8(skb, IFLA_BOND_XMIT_HASH_POLICY, + bond->params.xmit_policy)) + goto nla_put_failure; + + if (nla_put_u32(skb, IFLA_BOND_RESEND_IGMP, + bond->params.resend_igmp)) + goto nla_put_failure; + + if (nla_put_u8(skb, IFLA_BOND_NUM_PEER_NOTIF, + bond->params.num_peer_notif)) + goto nla_put_failure; + + if (nla_put_u8(skb, IFLA_BOND_ALL_SLAVES_ACTIVE, + bond->params.all_slaves_active)) + goto nla_put_failure; + + if (nla_put_u32(skb, IFLA_BOND_MIN_LINKS, + bond->params.min_links)) + goto nla_put_failure; + + if (nla_put_u32(skb, IFLA_BOND_LP_INTERVAL, + bond->params.lp_interval)) + goto nla_put_failure; + + packets_per_slave = bond->params.packets_per_slave; + if (nla_put_u32(skb, IFLA_BOND_PACKETS_PER_SLAVE, + packets_per_slave)) + goto nla_put_failure; + + if (nla_put_u8(skb, IFLA_BOND_AD_LACP_RATE, + bond->params.lacp_fast)) + goto nla_put_failure; + + if (nla_put_u8(skb, IFLA_BOND_AD_SELECT, + bond->params.ad_select)) + goto nla_put_failure; + + if (BOND_MODE(bond) == BOND_MODE_8023AD) { + struct ad_info info; + + if (!bond_3ad_get_active_agg_info(bond, &info)) { + struct nlattr *nest; + + nest = nla_nest_start(skb, IFLA_BOND_AD_INFO); + if (!nest) + goto nla_put_failure; + + if (nla_put_u16(skb, IFLA_BOND_AD_INFO_AGGREGATOR, + info.aggregator_id)) + goto nla_put_failure; + if (nla_put_u16(skb, IFLA_BOND_AD_INFO_NUM_PORTS, + info.ports)) + goto nla_put_failure; + if (nla_put_u16(skb, IFLA_BOND_AD_INFO_ACTOR_KEY, + info.actor_key)) + goto nla_put_failure; + if (nla_put_u16(skb, IFLA_BOND_AD_INFO_PARTNER_KEY, + info.partner_key)) + goto nla_put_failure; + if (nla_put(skb, IFLA_BOND_AD_INFO_PARTNER_MAC, + sizeof(info.partner_system), + &info.partner_system)) + goto nla_put_failure; + + nla_nest_end(skb, nest); + } + } + + return 0; + +nla_put_failure: + return -EMSGSIZE; +} + +struct rtnl_link_ops bond_link_ops __read_mostly = { + .kind = "bond", + .priv_size = sizeof(struct bonding), + .setup = bond_setup, + .maxtype = IFLA_BOND_MAX, + .policy = bond_policy, + .validate = bond_validate, + .newlink = bond_newlink, + .changelink = bond_changelink, + .get_size = bond_get_size, + .fill_info = bond_fill_info, + .get_num_tx_queues = bond_get_num_tx_queues, + .get_num_rx_queues = bond_get_num_tx_queues, /* Use the same number + as for TX queues */ + .get_slave_size = bond_get_slave_size, + .fill_slave_info = bond_fill_slave_info, +}; + +int __init bond_netlink_init(void) +{ + return rtnl_link_register(&bond_link_ops); +} + +void bond_netlink_fini(void) +{ + rtnl_link_unregister(&bond_link_ops); +} + +MODULE_ALIAS_RTNL_LINK("bond"); diff --git a/drivers/net/bonding/bond_options.c b/drivers/net/bonding/bond_options.c new file mode 100644 index 00000000000..540e0167bf2 --- /dev/null +++ b/drivers/net/bonding/bond_options.c @@ -0,0 +1,1394 @@ +/* + * drivers/net/bond/bond_options.c - bonding options + * Copyright (c) 2013 Jiri Pirko <jiri@resnulli.us> + * Copyright (c) 2013 Scott Feldman <sfeldma@cumulusnetworks.com> + * + * This program is free software; you can redistribute it and/or modify + * it under the terms of the GNU General Public License as published by + * the Free Software Foundation; either version 2 of the License, or + * (at your option) any later version. + */ + +#define pr_fmt(fmt) KBUILD_MODNAME ": " fmt + +#include <linux/errno.h> +#include <linux/if.h> +#include <linux/netdevice.h> +#include <linux/spinlock.h> +#include <linux/rcupdate.h> +#include <linux/ctype.h> +#include <linux/inet.h> +#include "bonding.h" + +static int bond_option_active_slave_set(struct bonding *bond, + const struct bond_opt_value *newval); +static int bond_option_miimon_set(struct bonding *bond, + const struct bond_opt_value *newval); +static int bond_option_updelay_set(struct bonding *bond, + const struct bond_opt_value *newval); +static int bond_option_downdelay_set(struct bonding *bond, + const struct bond_opt_value *newval); +static int bond_option_use_carrier_set(struct bonding *bond, + const struct bond_opt_value *newval); +static int bond_option_arp_interval_set(struct bonding *bond, + const struct bond_opt_value *newval); +static int bond_option_arp_ip_target_add(struct bonding *bond, __be32 target); +static int bond_option_arp_ip_target_rem(struct bonding *bond, __be32 target); +static int bond_option_arp_ip_targets_set(struct bonding *bond, + const struct bond_opt_value *newval); +static int bond_option_arp_validate_set(struct bonding *bond, + const struct bond_opt_value *newval); +static int bond_option_arp_all_targets_set(struct bonding *bond, + const struct bond_opt_value *newval); +static int bond_option_primary_set(struct bonding *bond, + const struct bond_opt_value *newval); +static int bond_option_primary_reselect_set(struct bonding *bond, + const struct bond_opt_value *newval); +static int bond_option_fail_over_mac_set(struct bonding *bond, + const struct bond_opt_value *newval); +static int bond_option_xmit_hash_policy_set(struct bonding *bond, + const struct bond_opt_value *newval); +static int bond_option_resend_igmp_set(struct bonding *bond, + const struct bond_opt_value *newval); +static int bond_option_num_peer_notif_set(struct bonding *bond, + const struct bond_opt_value *newval); +static int bond_option_all_slaves_active_set(struct bonding *bond, + const struct bond_opt_value *newval); +static int bond_option_min_links_set(struct bonding *bond, + const struct bond_opt_value *newval); +static int bond_option_lp_interval_set(struct bonding *bond, + const struct bond_opt_value *newval); +static int bond_option_pps_set(struct bonding *bond, + const struct bond_opt_value *newval); +static int bond_option_lacp_rate_set(struct bonding *bond, + const struct bond_opt_value *newval); +static int bond_option_ad_select_set(struct bonding *bond, + const struct bond_opt_value *newval); +static int bond_option_queue_id_set(struct bonding *bond, + const struct bond_opt_value *newval); +static int bond_option_mode_set(struct bonding *bond, + const struct bond_opt_value *newval); +static int bond_option_slaves_set(struct bonding *bond, + const struct bond_opt_value *newval); +static int bond_option_tlb_dynamic_lb_set(struct bonding *bond, + const struct bond_opt_value *newval); + + +static const struct bond_opt_value bond_mode_tbl[] = { + { "balance-rr", BOND_MODE_ROUNDROBIN, BOND_VALFLAG_DEFAULT}, + { "active-backup", BOND_MODE_ACTIVEBACKUP, 0}, + { "balance-xor", BOND_MODE_XOR, 0}, + { "broadcast", BOND_MODE_BROADCAST, 0}, + { "802.3ad", BOND_MODE_8023AD, 0}, + { "balance-tlb", BOND_MODE_TLB, 0}, + { "balance-alb", BOND_MODE_ALB, 0}, + { NULL, -1, 0}, +}; + +static const struct bond_opt_value bond_pps_tbl[] = { + { "default", 1, BOND_VALFLAG_DEFAULT}, + { "maxval", USHRT_MAX, BOND_VALFLAG_MAX}, + { NULL, -1, 0}, +}; + +static const struct bond_opt_value bond_xmit_hashtype_tbl[] = { + { "layer2", BOND_XMIT_POLICY_LAYER2, BOND_VALFLAG_DEFAULT}, + { "layer3+4", BOND_XMIT_POLICY_LAYER34, 0}, + { "layer2+3", BOND_XMIT_POLICY_LAYER23, 0}, + { "encap2+3", BOND_XMIT_POLICY_ENCAP23, 0}, + { "encap3+4", BOND_XMIT_POLICY_ENCAP34, 0}, + { NULL, -1, 0}, +}; + +static const struct bond_opt_value bond_arp_validate_tbl[] = { + { "none", BOND_ARP_VALIDATE_NONE, BOND_VALFLAG_DEFAULT}, + { "active", BOND_ARP_VALIDATE_ACTIVE, 0}, + { "backup", BOND_ARP_VALIDATE_BACKUP, 0}, + { "all", BOND_ARP_VALIDATE_ALL, 0}, + { "filter", BOND_ARP_FILTER, 0}, + { "filter_active", BOND_ARP_FILTER_ACTIVE, 0}, + { "filter_backup", BOND_ARP_FILTER_BACKUP, 0}, + { NULL, -1, 0}, +}; + +static const struct bond_opt_value bond_arp_all_targets_tbl[] = { + { "any", BOND_ARP_TARGETS_ANY, BOND_VALFLAG_DEFAULT}, + { "all", BOND_ARP_TARGETS_ALL, 0}, + { NULL, -1, 0}, +}; + +static const struct bond_opt_value bond_fail_over_mac_tbl[] = { + { "none", BOND_FOM_NONE, BOND_VALFLAG_DEFAULT}, + { "active", BOND_FOM_ACTIVE, 0}, + { "follow", BOND_FOM_FOLLOW, 0}, + { NULL, -1, 0}, +}; + +static const struct bond_opt_value bond_intmax_tbl[] = { + { "off", 0, BOND_VALFLAG_DEFAULT}, + { "maxval", INT_MAX, BOND_VALFLAG_MAX}, + { NULL, -1, 0} +}; + +static const struct bond_opt_value bond_lacp_rate_tbl[] = { + { "slow", AD_LACP_SLOW, 0}, + { "fast", AD_LACP_FAST, 0}, + { NULL, -1, 0}, +}; + +static const struct bond_opt_value bond_ad_select_tbl[] = { + { "stable", BOND_AD_STABLE, BOND_VALFLAG_DEFAULT}, + { "bandwidth", BOND_AD_BANDWIDTH, 0}, + { "count", BOND_AD_COUNT, 0}, + { NULL, -1, 0}, +}; + +static const struct bond_opt_value bond_num_peer_notif_tbl[] = { + { "off", 0, 0}, + { "maxval", 255, BOND_VALFLAG_MAX}, + { "default", 1, BOND_VALFLAG_DEFAULT}, + { NULL, -1, 0} +}; + +static const struct bond_opt_value bond_primary_reselect_tbl[] = { + { "always", BOND_PRI_RESELECT_ALWAYS, BOND_VALFLAG_DEFAULT}, + { "better", BOND_PRI_RESELECT_BETTER, 0}, + { "failure", BOND_PRI_RESELECT_FAILURE, 0}, + { NULL, -1}, +}; + +static const struct bond_opt_value bond_use_carrier_tbl[] = { + { "off", 0, 0}, + { "on", 1, BOND_VALFLAG_DEFAULT}, + { NULL, -1, 0} +}; + +static const struct bond_opt_value bond_all_slaves_active_tbl[] = { + { "off", 0, BOND_VALFLAG_DEFAULT}, + { "on", 1, 0}, + { NULL, -1, 0} +}; + +static const struct bond_opt_value bond_resend_igmp_tbl[] = { + { "off", 0, 0}, + { "maxval", 255, BOND_VALFLAG_MAX}, + { "default", 1, BOND_VALFLAG_DEFAULT}, + { NULL, -1, 0} +}; + +static const struct bond_opt_value bond_lp_interval_tbl[] = { + { "minval", 1, BOND_VALFLAG_MIN | BOND_VALFLAG_DEFAULT}, + { "maxval", INT_MAX, BOND_VALFLAG_MAX}, + { NULL, -1, 0}, +}; + +static const struct bond_opt_value bond_tlb_dynamic_lb_tbl[] = { + { "off", 0, 0}, + { "on", 1, BOND_VALFLAG_DEFAULT}, + { NULL, -1, 0} +}; + +static const struct bond_option bond_opts[] = { + [BOND_OPT_MODE] = { + .id = BOND_OPT_MODE, + .name = "mode", + .desc = "bond device mode", + .flags = BOND_OPTFLAG_NOSLAVES | BOND_OPTFLAG_IFDOWN, + .values = bond_mode_tbl, + .set = bond_option_mode_set + }, + [BOND_OPT_PACKETS_PER_SLAVE] = { + .id = BOND_OPT_PACKETS_PER_SLAVE, + .name = "packets_per_slave", + .desc = "Packets to send per slave in RR mode", + .unsuppmodes = BOND_MODE_ALL_EX(BIT(BOND_MODE_ROUNDROBIN)), + .values = bond_pps_tbl, + .set = bond_option_pps_set + }, + [BOND_OPT_XMIT_HASH] = { + .id = BOND_OPT_XMIT_HASH, + .name = "xmit_hash_policy", + .desc = "balance-xor, 802.3ad, and tlb hashing method", + .values = bond_xmit_hashtype_tbl, + .set = bond_option_xmit_hash_policy_set + }, + [BOND_OPT_ARP_VALIDATE] = { + .id = BOND_OPT_ARP_VALIDATE, + .name = "arp_validate", + .desc = "validate src/dst of ARP probes", + .unsuppmodes = BIT(BOND_MODE_8023AD) | BIT(BOND_MODE_TLB) | + BIT(BOND_MODE_ALB), + .values = bond_arp_validate_tbl, + .set = bond_option_arp_validate_set + }, + [BOND_OPT_ARP_ALL_TARGETS] = { + .id = BOND_OPT_ARP_ALL_TARGETS, + .name = "arp_all_targets", + .desc = "fail on any/all arp targets timeout", + .values = bond_arp_all_targets_tbl, + .set = bond_option_arp_all_targets_set + }, + [BOND_OPT_FAIL_OVER_MAC] = { + .id = BOND_OPT_FAIL_OVER_MAC, + .name = "fail_over_mac", + .desc = "For active-backup, do not set all slaves to the same MAC", + .flags = BOND_OPTFLAG_NOSLAVES, + .values = bond_fail_over_mac_tbl, + .set = bond_option_fail_over_mac_set + }, + [BOND_OPT_ARP_INTERVAL] = { + .id = BOND_OPT_ARP_INTERVAL, + .name = "arp_interval", + .desc = "arp interval in milliseconds", + .unsuppmodes = BIT(BOND_MODE_8023AD) | BIT(BOND_MODE_TLB) | + BIT(BOND_MODE_ALB), + .values = bond_intmax_tbl, + .set = bond_option_arp_interval_set + }, + [BOND_OPT_ARP_TARGETS] = { + .id = BOND_OPT_ARP_TARGETS, + .name = "arp_ip_target", + .desc = "arp targets in n.n.n.n form", + .flags = BOND_OPTFLAG_RAWVAL, + .set = bond_option_arp_ip_targets_set + }, + [BOND_OPT_DOWNDELAY] = { + .id = BOND_OPT_DOWNDELAY, + .name = "downdelay", + .desc = "Delay before considering link down, in milliseconds", + .values = bond_intmax_tbl, + .set = bond_option_downdelay_set + }, + [BOND_OPT_UPDELAY] = { + .id = BOND_OPT_UPDELAY, + .name = "updelay", + .desc = "Delay before considering link up, in milliseconds", + .values = bond_intmax_tbl, + .set = bond_option_updelay_set + }, + [BOND_OPT_LACP_RATE] = { + .id = BOND_OPT_LACP_RATE, + .name = "lacp_rate", + .desc = "LACPDU tx rate to request from 802.3ad partner", + .flags = BOND_OPTFLAG_IFDOWN, + .unsuppmodes = BOND_MODE_ALL_EX(BIT(BOND_MODE_8023AD)), + .values = bond_lacp_rate_tbl, + .set = bond_option_lacp_rate_set + }, + [BOND_OPT_MINLINKS] = { + .id = BOND_OPT_MINLINKS, + .name = "min_links", + .desc = "Minimum number of available links before turning on carrier", + .values = bond_intmax_tbl, + .set = bond_option_min_links_set + }, + [BOND_OPT_AD_SELECT] = { + .id = BOND_OPT_AD_SELECT, + .name = "ad_select", + .desc = "803.ad aggregation selection logic", + .flags = BOND_OPTFLAG_IFDOWN, + .values = bond_ad_select_tbl, + .set = bond_option_ad_select_set + }, + [BOND_OPT_NUM_PEER_NOTIF] = { + .id = BOND_OPT_NUM_PEER_NOTIF, + .name = "num_unsol_na", + .desc = "Number of peer notifications to send on failover event", + .values = bond_num_peer_notif_tbl, + .set = bond_option_num_peer_notif_set + }, + [BOND_OPT_MIIMON] = { + .id = BOND_OPT_MIIMON, + .name = "miimon", + .desc = "Link check interval in milliseconds", + .values = bond_intmax_tbl, + .set = bond_option_miimon_set + }, + [BOND_OPT_PRIMARY] = { + .id = BOND_OPT_PRIMARY, + .name = "primary", + .desc = "Primary network device to use", + .flags = BOND_OPTFLAG_RAWVAL, + .unsuppmodes = BOND_MODE_ALL_EX(BIT(BOND_MODE_ACTIVEBACKUP) | + BIT(BOND_MODE_TLB) | + BIT(BOND_MODE_ALB)), + .set = bond_option_primary_set + }, + [BOND_OPT_PRIMARY_RESELECT] = { + .id = BOND_OPT_PRIMARY_RESELECT, + .name = "primary_reselect", + .desc = "Reselect primary slave once it comes up", + .values = bond_primary_reselect_tbl, + .set = bond_option_primary_reselect_set + }, + [BOND_OPT_USE_CARRIER] = { + .id = BOND_OPT_USE_CARRIER, + .name = "use_carrier", + .desc = "Use netif_carrier_ok (vs MII ioctls) in miimon", + .values = bond_use_carrier_tbl, + .set = bond_option_use_carrier_set + }, + [BOND_OPT_ACTIVE_SLAVE] = { + .id = BOND_OPT_ACTIVE_SLAVE, + .name = "active_slave", + .desc = "Currently active slave", + .flags = BOND_OPTFLAG_RAWVAL, + .unsuppmodes = BOND_MODE_ALL_EX(BIT(BOND_MODE_ACTIVEBACKUP) | + BIT(BOND_MODE_TLB) | + BIT(BOND_MODE_ALB)), + .set = bond_option_active_slave_set + }, + [BOND_OPT_QUEUE_ID] = { + .id = BOND_OPT_QUEUE_ID, + .name = "queue_id", + .desc = "Set queue id of a slave", + .flags = BOND_OPTFLAG_RAWVAL, + .set = bond_option_queue_id_set + }, + [BOND_OPT_ALL_SLAVES_ACTIVE] = { + .id = BOND_OPT_ALL_SLAVES_ACTIVE, + .name = "all_slaves_active", + .desc = "Keep all frames received on an interface by setting active flag for all slaves", + .values = bond_all_slaves_active_tbl, + .set = bond_option_all_slaves_active_set + }, + [BOND_OPT_RESEND_IGMP] = { + .id = BOND_OPT_RESEND_IGMP, + .name = "resend_igmp", + .desc = "Number of IGMP membership reports to send on link failure", + .values = bond_resend_igmp_tbl, + .set = bond_option_resend_igmp_set + }, + [BOND_OPT_LP_INTERVAL] = { + .id = BOND_OPT_LP_INTERVAL, + .name = "lp_interval", + .desc = "The number of seconds between instances where the bonding driver sends learning packets to each slave's peer switch", + .values = bond_lp_interval_tbl, + .set = bond_option_lp_interval_set + }, + [BOND_OPT_SLAVES] = { + .id = BOND_OPT_SLAVES, + .name = "slaves", + .desc = "Slave membership management", + .flags = BOND_OPTFLAG_RAWVAL, + .set = bond_option_slaves_set + }, + [BOND_OPT_TLB_DYNAMIC_LB] = { + .id = BOND_OPT_TLB_DYNAMIC_LB, + .name = "tlb_dynamic_lb", + .desc = "Enable dynamic flow shuffling", + .unsuppmodes = BOND_MODE_ALL_EX(BIT(BOND_MODE_TLB)), + .values = bond_tlb_dynamic_lb_tbl, + .flags = BOND_OPTFLAG_IFDOWN, + .set = bond_option_tlb_dynamic_lb_set, + }, + { } +}; + +/* Searches for an option by name */ +const struct bond_option *bond_opt_get_by_name(const char *name) +{ + const struct bond_option *opt; + int option; + + for (option = 0; option < BOND_OPT_LAST; option++) { + opt = bond_opt_get(option); + if (opt && !strcmp(opt->name, name)) + return opt; + } + + return NULL; +} + +/* Searches for a value in opt's values[] table */ +const struct bond_opt_value *bond_opt_get_val(unsigned int option, u64 val) +{ + const struct bond_option *opt; + int i; + + opt = bond_opt_get(option); + if (WARN_ON(!opt)) + return NULL; + for (i = 0; opt->values && opt->values[i].string; i++) + if (opt->values[i].value == val) + return &opt->values[i]; + + return NULL; +} + +/* Searches for a value in opt's values[] table which matches the flagmask */ +static const struct bond_opt_value *bond_opt_get_flags(const struct bond_option *opt, + u32 flagmask) +{ + int i; + + for (i = 0; opt->values && opt->values[i].string; i++) + if (opt->values[i].flags & flagmask) + return &opt->values[i]; + + return NULL; +} + +/* If maxval is missing then there's no range to check. In case minval is + * missing then it's considered to be 0. + */ +static bool bond_opt_check_range(const struct bond_option *opt, u64 val) +{ + const struct bond_opt_value *minval, *maxval; + + minval = bond_opt_get_flags(opt, BOND_VALFLAG_MIN); + maxval = bond_opt_get_flags(opt, BOND_VALFLAG_MAX); + if (!maxval || (minval && val < minval->value) || val > maxval->value) + return false; + + return true; +} + +/** + * bond_opt_parse - parse option value + * @opt: the option to parse against + * @val: value to parse + * + * This function tries to extract the value from @val and check if it's + * a possible match for the option and returns NULL if a match isn't found, + * or the struct_opt_value that matched. It also strips the new line from + * @val->string if it's present. + */ +const struct bond_opt_value *bond_opt_parse(const struct bond_option *opt, + struct bond_opt_value *val) +{ + char *p, valstr[BOND_OPT_MAX_NAMELEN + 1] = { 0, }; + const struct bond_opt_value *tbl; + const struct bond_opt_value *ret = NULL; + bool checkval; + int i, rv; + + /* No parsing if the option wants a raw val */ + if (opt->flags & BOND_OPTFLAG_RAWVAL) + return val; + + tbl = opt->values; + if (!tbl) + goto out; + + /* ULLONG_MAX is used to bypass string processing */ + checkval = val->value != ULLONG_MAX; + if (!checkval) { + if (!val->string) + goto out; + p = strchr(val->string, '\n'); + if (p) + *p = '\0'; + for (p = val->string; *p; p++) + if (!(isdigit(*p) || isspace(*p))) + break; + /* The following code extracts the string to match or the value + * and sets checkval appropriately + */ + if (*p) { + rv = sscanf(val->string, "%32s", valstr); + } else { + rv = sscanf(val->string, "%llu", &val->value); + checkval = true; + } + if (!rv) + goto out; + } + + for (i = 0; tbl[i].string; i++) { + /* Check for exact match */ + if (checkval) { + if (val->value == tbl[i].value) + ret = &tbl[i]; + } else { + if (!strcmp(valstr, "default") && + (tbl[i].flags & BOND_VALFLAG_DEFAULT)) + ret = &tbl[i]; + + if (!strcmp(valstr, tbl[i].string)) + ret = &tbl[i]; + } + /* Found an exact match */ + if (ret) + goto out; + } + /* Possible range match */ + if (checkval && bond_opt_check_range(opt, val->value)) + ret = val; +out: + return ret; +} + +/* Check opt's dependencies against bond mode and currently set options */ +static int bond_opt_check_deps(struct bonding *bond, + const struct bond_option *opt) +{ + struct bond_params *params = &bond->params; + + if (test_bit(params->mode, &opt->unsuppmodes)) + return -EACCES; + if ((opt->flags & BOND_OPTFLAG_NOSLAVES) && bond_has_slaves(bond)) + return -ENOTEMPTY; + if ((opt->flags & BOND_OPTFLAG_IFDOWN) && (bond->dev->flags & IFF_UP)) + return -EBUSY; + + return 0; +} + +static void bond_opt_dep_print(struct bonding *bond, + const struct bond_option *opt) +{ + const struct bond_opt_value *modeval; + struct bond_params *params; + + params = &bond->params; + modeval = bond_opt_get_val(BOND_OPT_MODE, params->mode); + if (test_bit(params->mode, &opt->unsuppmodes)) + pr_err("%s: option %s: mode dependency failed, not supported in mode %s(%llu)\n", + bond->dev->name, opt->name, + modeval->string, modeval->value); +} + +static void bond_opt_error_interpret(struct bonding *bond, + const struct bond_option *opt, + int error, const struct bond_opt_value *val) +{ + const struct bond_opt_value *minval, *maxval; + char *p; + + switch (error) { + case -EINVAL: + if (val) { + if (val->string) { + /* sometimes RAWVAL opts may have new lines */ + p = strchr(val->string, '\n'); + if (p) + *p = '\0'; + pr_err("%s: option %s: invalid value (%s)\n", + bond->dev->name, opt->name, val->string); + } else { + pr_err("%s: option %s: invalid value (%llu)\n", + bond->dev->name, opt->name, val->value); + } + } + minval = bond_opt_get_flags(opt, BOND_VALFLAG_MIN); + maxval = bond_opt_get_flags(opt, BOND_VALFLAG_MAX); + if (!maxval) + break; + pr_err("%s: option %s: allowed values %llu - %llu\n", + bond->dev->name, opt->name, minval ? minval->value : 0, + maxval->value); + break; + case -EACCES: + bond_opt_dep_print(bond, opt); + break; + case -ENOTEMPTY: + pr_err("%s: option %s: unable to set because the bond device has slaves\n", + bond->dev->name, opt->name); + break; + case -EBUSY: + pr_err("%s: option %s: unable to set because the bond device is up\n", + bond->dev->name, opt->name); + break; + default: + break; + } +} + +/** + * __bond_opt_set - set a bonding option + * @bond: target bond device + * @option: option to set + * @val: value to set it to + * + * This function is used to change the bond's option value, it can be + * used for both enabling/changing an option and for disabling it. RTNL lock + * must be obtained before calling this function. + */ +int __bond_opt_set(struct bonding *bond, + unsigned int option, struct bond_opt_value *val) +{ + const struct bond_opt_value *retval = NULL; + const struct bond_option *opt; + int ret = -ENOENT; + + ASSERT_RTNL(); + + opt = bond_opt_get(option); + if (WARN_ON(!val) || WARN_ON(!opt)) + goto out; + ret = bond_opt_check_deps(bond, opt); + if (ret) + goto out; + retval = bond_opt_parse(opt, val); + if (!retval) { + ret = -EINVAL; + goto out; + } + ret = opt->set(bond, retval); +out: + if (ret) + bond_opt_error_interpret(bond, opt, ret, val); + + return ret; +} + +/** + * bond_opt_tryset_rtnl - try to acquire rtnl and call __bond_opt_set + * @bond: target bond device + * @option: option to set + * @buf: value to set it to + * + * This function tries to acquire RTNL without blocking and if successful + * calls __bond_opt_set. It is mainly used for sysfs option manipulation. + */ +int bond_opt_tryset_rtnl(struct bonding *bond, unsigned int option, char *buf) +{ + struct bond_opt_value optval; + int ret; + + if (!rtnl_trylock()) + return restart_syscall(); + bond_opt_initstr(&optval, buf); + ret = __bond_opt_set(bond, option, &optval); + rtnl_unlock(); + + return ret; +} + +/** + * bond_opt_get - get a pointer to an option + * @option: option for which to return a pointer + * + * This function checks if option is valid and if so returns a pointer + * to its entry in the bond_opts[] option array. + */ +const struct bond_option *bond_opt_get(unsigned int option) +{ + if (!BOND_OPT_VALID(option)) + return NULL; + + return &bond_opts[option]; +} + +int bond_option_mode_set(struct bonding *bond, const struct bond_opt_value *newval) +{ + if (!bond_mode_uses_arp(newval->value) && bond->params.arp_interval) { + pr_info("%s: %s mode is incompatible with arp monitoring, start mii monitoring\n", + bond->dev->name, newval->string); + /* disable arp monitoring */ + bond->params.arp_interval = 0; + /* set miimon to default value */ + bond->params.miimon = BOND_DEFAULT_MIIMON; + pr_info("%s: Setting MII monitoring interval to %d\n", + bond->dev->name, bond->params.miimon); + } + + /* don't cache arp_validate between modes */ + bond->params.arp_validate = BOND_ARP_VALIDATE_NONE; + bond->params.mode = newval->value; + + return 0; +} + +static struct net_device *__bond_option_active_slave_get(struct bonding *bond, + struct slave *slave) +{ + return bond_uses_primary(bond) && slave ? slave->dev : NULL; +} + +struct net_device *bond_option_active_slave_get_rcu(struct bonding *bond) +{ + struct slave *slave = rcu_dereference(bond->curr_active_slave); + + return __bond_option_active_slave_get(bond, slave); +} + +struct net_device *bond_option_active_slave_get(struct bonding *bond) +{ + return __bond_option_active_slave_get(bond, bond->curr_active_slave); +} + +static int bond_option_active_slave_set(struct bonding *bond, + const struct bond_opt_value *newval) +{ + char ifname[IFNAMSIZ] = { 0, }; + struct net_device *slave_dev; + int ret = 0; + + sscanf(newval->string, "%15s", ifname); /* IFNAMSIZ */ + if (!strlen(ifname) || newval->string[0] == '\n') { + slave_dev = NULL; + } else { + slave_dev = __dev_get_by_name(dev_net(bond->dev), ifname); + if (!slave_dev) + return -ENODEV; + } + + if (slave_dev) { + if (!netif_is_bond_slave(slave_dev)) { + pr_err("Device %s is not bonding slave\n", + slave_dev->name); + return -EINVAL; + } + + if (bond->dev != netdev_master_upper_dev_get(slave_dev)) { + pr_err("%s: Device %s is not our slave\n", + bond->dev->name, slave_dev->name); + return -EINVAL; + } + } + + block_netpoll_tx(); + write_lock_bh(&bond->curr_slave_lock); + + /* check to see if we are clearing active */ + if (!slave_dev) { + pr_info("%s: Clearing current active slave\n", bond->dev->name); + RCU_INIT_POINTER(bond->curr_active_slave, NULL); + bond_select_active_slave(bond); + } else { + struct slave *old_active = bond->curr_active_slave; + struct slave *new_active = bond_slave_get_rtnl(slave_dev); + + BUG_ON(!new_active); + + if (new_active == old_active) { + /* do nothing */ + pr_info("%s: %s is already the current active slave\n", + bond->dev->name, new_active->dev->name); + } else { + if (old_active && (new_active->link == BOND_LINK_UP) && + bond_slave_is_up(new_active)) { + pr_info("%s: Setting %s as active slave\n", + bond->dev->name, new_active->dev->name); + bond_change_active_slave(bond, new_active); + } else { + pr_err("%s: Could not set %s as active slave; either %s is down or the link is down\n", + bond->dev->name, new_active->dev->name, + new_active->dev->name); + ret = -EINVAL; + } + } + } + + write_unlock_bh(&bond->curr_slave_lock); + unblock_netpoll_tx(); + + return ret; +} + +/* 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 int bond_option_miimon_set(struct bonding *bond, + const struct bond_opt_value *newval) +{ + pr_info("%s: Setting MII monitoring interval to %llu\n", + bond->dev->name, newval->value); + bond->params.miimon = newval->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 (newval->value && 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 (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 (!newval->value) { + cancel_delayed_work_sync(&bond->mii_work); + } else { + cancel_delayed_work_sync(&bond->arp_work); + queue_delayed_work(bond->wq, &bond->mii_work, 0); + } + } + + return 0; +} + +/* Set 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 int bond_option_updelay_set(struct bonding *bond, + const struct bond_opt_value *newval) +{ + int value = newval->value; + + if (!bond->params.miimon) { + pr_err("%s: Unable to set up delay as MII monitoring is disabled\n", + bond->dev->name); + return -EPERM; + } + if ((value % bond->params.miimon) != 0) { + pr_warn("%s: Warning: up delay (%d) is not a multiple of miimon (%d), updelay rounded to %d ms\n", + bond->dev->name, value, + bond->params.miimon, + (value / bond->params.miimon) * + bond->params.miimon); + } + bond->params.updelay = value / bond->params.miimon; + pr_info("%s: Setting up delay to %d\n", + bond->dev->name, bond->params.updelay * bond->params.miimon); + + return 0; +} + +static int bond_option_downdelay_set(struct bonding *bond, + const struct bond_opt_value *newval) +{ + int value = newval->value; + + if (!bond->params.miimon) { + pr_err("%s: Unable to set down delay as MII monitoring is disabled\n", + bond->dev->name); + return -EPERM; + } + if ((value % bond->params.miimon) != 0) { + pr_warn("%s: Warning: down delay (%d) is not a multiple of miimon (%d), delay rounded to %d ms\n", + bond->dev->name, value, + bond->params.miimon, + (value / bond->params.miimon) * + bond->params.miimon); + } + bond->params.downdelay = value / bond->params.miimon; + pr_info("%s: Setting down delay to %d\n", + bond->dev->name, bond->params.downdelay * bond->params.miimon); + + return 0; +} + +static int bond_option_use_carrier_set(struct bonding *bond, + const struct bond_opt_value *newval) +{ + pr_info("%s: Setting use_carrier to %llu\n", + bond->dev->name, newval->value); + bond->params.use_carrier = newval->value; + + return 0; +} + +/* 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 int bond_option_arp_interval_set(struct bonding *bond, + const struct bond_opt_value *newval) +{ + pr_info("%s: Setting ARP monitoring interval to %llu\n", + bond->dev->name, newval->value); + bond->params.arp_interval = newval->value; + if (newval->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 (!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 (!newval->value) { + if (bond->params.arp_validate) + bond->recv_probe = NULL; + cancel_delayed_work_sync(&bond->arp_work); + } else { + /* arp_validate can be set only in active-backup mode */ + bond->recv_probe = bond_arp_rcv; + cancel_delayed_work_sync(&bond->mii_work); + queue_delayed_work(bond->wq, &bond->arp_work, 0); + } + } + + return 0; +} + +static void _bond_options_arp_ip_target_set(struct bonding *bond, int slot, + __be32 target, + unsigned long last_rx) +{ + __be32 *targets = bond->params.arp_targets; + struct list_head *iter; + struct slave *slave; + + if (slot >= 0 && slot < BOND_MAX_ARP_TARGETS) { + bond_for_each_slave(bond, slave, iter) + slave->target_last_arp_rx[slot] = last_rx; + targets[slot] = target; + } +} + +static int _bond_option_arp_ip_target_add(struct bonding *bond, __be32 target) +{ + __be32 *targets = bond->params.arp_targets; + int ind; + + if (!bond_is_ip_target_ok(target)) { + pr_err("%s: invalid ARP target %pI4 specified for addition\n", + bond->dev->name, &target); + return -EINVAL; + } + + if (bond_get_targets_ip(targets, target) != -1) { /* dup */ + pr_err("%s: ARP target %pI4 is already present\n", + bond->dev->name, &target); + return -EINVAL; + } + + ind = bond_get_targets_ip(targets, 0); /* first free slot */ + if (ind == -1) { + pr_err("%s: ARP target table is full!\n", bond->dev->name); + return -EINVAL; + } + + pr_info("%s: Adding ARP target %pI4\n", bond->dev->name, &target); + + _bond_options_arp_ip_target_set(bond, ind, target, jiffies); + + return 0; +} + +static int bond_option_arp_ip_target_add(struct bonding *bond, __be32 target) +{ + int ret; + + /* not to race with bond_arp_rcv */ + write_lock_bh(&bond->lock); + ret = _bond_option_arp_ip_target_add(bond, target); + write_unlock_bh(&bond->lock); + + return ret; +} + +static int bond_option_arp_ip_target_rem(struct bonding *bond, __be32 target) +{ + __be32 *targets = bond->params.arp_targets; + struct list_head *iter; + struct slave *slave; + unsigned long *targets_rx; + int ind, i; + + if (!bond_is_ip_target_ok(target)) { + pr_err("%s: invalid ARP target %pI4 specified for removal\n", + bond->dev->name, &target); + return -EINVAL; + } + + ind = bond_get_targets_ip(targets, target); + if (ind == -1) { + pr_err("%s: unable to remove nonexistent ARP target %pI4\n", + bond->dev->name, &target); + return -EINVAL; + } + + if (ind == 0 && !targets[1] && bond->params.arp_interval) + pr_warn("%s: Removing last arp target with arp_interval on\n", + bond->dev->name); + + pr_info("%s: Removing ARP target %pI4\n", bond->dev->name, &target); + + /* not to race with bond_arp_rcv */ + write_lock_bh(&bond->lock); + + bond_for_each_slave(bond, slave, iter) { + targets_rx = slave->target_last_arp_rx; + for (i = ind; (i < BOND_MAX_ARP_TARGETS-1) && targets[i+1]; i++) + targets_rx[i] = targets_rx[i+1]; + targets_rx[i] = 0; + } + for (i = ind; (i < BOND_MAX_ARP_TARGETS-1) && targets[i+1]; i++) + targets[i] = targets[i+1]; + targets[i] = 0; + + write_unlock_bh(&bond->lock); + + return 0; +} + +void bond_option_arp_ip_targets_clear(struct bonding *bond) +{ + int i; + + /* not to race with bond_arp_rcv */ + write_lock_bh(&bond->lock); + for (i = 0; i < BOND_MAX_ARP_TARGETS; i++) + _bond_options_arp_ip_target_set(bond, i, 0, 0); + write_unlock_bh(&bond->lock); +} + +static int bond_option_arp_ip_targets_set(struct bonding *bond, + const struct bond_opt_value *newval) +{ + int ret = -EPERM; + __be32 target; + + if (newval->string) { + if (!in4_pton(newval->string+1, -1, (u8 *)&target, -1, NULL)) { + pr_err("%s: invalid ARP target %pI4 specified\n", + bond->dev->name, &target); + return ret; + } + if (newval->string[0] == '+') + ret = bond_option_arp_ip_target_add(bond, target); + else if (newval->string[0] == '-') + ret = bond_option_arp_ip_target_rem(bond, target); + else + pr_err("no command found in arp_ip_targets file for bond %s - use +<addr> or -<addr>\n", + bond->dev->name); + } else { + target = newval->value; + ret = bond_option_arp_ip_target_add(bond, target); + } + + return ret; +} + +static int bond_option_arp_validate_set(struct bonding *bond, + const struct bond_opt_value *newval) +{ + pr_info("%s: Setting arp_validate to %s (%llu)\n", + bond->dev->name, newval->string, newval->value); + + if (bond->dev->flags & IFF_UP) { + if (!newval->value) + bond->recv_probe = NULL; + else if (bond->params.arp_interval) + bond->recv_probe = bond_arp_rcv; + } + bond->params.arp_validate = newval->value; + + return 0; +} + +static int bond_option_arp_all_targets_set(struct bonding *bond, + const struct bond_opt_value *newval) +{ + pr_info("%s: Setting arp_all_targets to %s (%llu)\n", + bond->dev->name, newval->string, newval->value); + bond->params.arp_all_targets = newval->value; + + return 0; +} + +static int bond_option_primary_set(struct bonding *bond, + const struct bond_opt_value *newval) +{ + char *p, *primary = newval->string; + struct list_head *iter; + struct slave *slave; + + block_netpoll_tx(); + read_lock(&bond->lock); + write_lock_bh(&bond->curr_slave_lock); + + p = strchr(primary, '\n'); + if (p) + *p = '\0'; + /* check to see if we are clearing primary */ + if (!strlen(primary)) { + pr_info("%s: Setting primary slave to None\n", bond->dev->name); + bond->primary_slave = NULL; + memset(bond->params.primary, 0, sizeof(bond->params.primary)); + bond_select_active_slave(bond); + goto out; + } + + bond_for_each_slave(bond, slave, iter) { + if (strncmp(slave->dev->name, primary, 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; + } + } + + if (bond->primary_slave) { + pr_info("%s: Setting primary slave to None\n", bond->dev->name); + bond->primary_slave = NULL; + bond_select_active_slave(bond); + } + strncpy(bond->params.primary, primary, IFNAMSIZ); + bond->params.primary[IFNAMSIZ - 1] = 0; + + pr_info("%s: Recording %s as primary, but it has not been enslaved to %s yet\n", + bond->dev->name, primary, bond->dev->name); + +out: + write_unlock_bh(&bond->curr_slave_lock); + read_unlock(&bond->lock); + unblock_netpoll_tx(); + + return 0; +} + +static int bond_option_primary_reselect_set(struct bonding *bond, + const struct bond_opt_value *newval) +{ + pr_info("%s: Setting primary_reselect to %s (%llu)\n", + bond->dev->name, newval->string, newval->value); + bond->params.primary_reselect = newval->value; + + 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(); + + return 0; +} + +static int bond_option_fail_over_mac_set(struct bonding *bond, + const struct bond_opt_value *newval) +{ + pr_info("%s: Setting fail_over_mac to %s (%llu)\n", + bond->dev->name, newval->string, newval->value); + bond->params.fail_over_mac = newval->value; + + return 0; +} + +static int bond_option_xmit_hash_policy_set(struct bonding *bond, + const struct bond_opt_value *newval) +{ + pr_info("%s: Setting xmit hash policy to %s (%llu)\n", + bond->dev->name, newval->string, newval->value); + bond->params.xmit_policy = newval->value; + + return 0; +} + +static int bond_option_resend_igmp_set(struct bonding *bond, + const struct bond_opt_value *newval) +{ + pr_info("%s: Setting resend_igmp to %llu\n", + bond->dev->name, newval->value); + bond->params.resend_igmp = newval->value; + + return 0; +} + +static int bond_option_num_peer_notif_set(struct bonding *bond, + const struct bond_opt_value *newval) +{ + bond->params.num_peer_notif = newval->value; + + return 0; +} + +static int bond_option_all_slaves_active_set(struct bonding *bond, + const struct bond_opt_value *newval) +{ + struct list_head *iter; + struct slave *slave; + + if (newval->value == bond->params.all_slaves_active) + return 0; + bond->params.all_slaves_active = newval->value; + bond_for_each_slave(bond, slave, iter) { + if (!bond_is_active_slave(slave)) { + if (newval->value) + slave->inactive = 0; + else + slave->inactive = 1; + } + } + + return 0; +} + +static int bond_option_min_links_set(struct bonding *bond, + const struct bond_opt_value *newval) +{ + pr_info("%s: Setting min links value to %llu\n", + bond->dev->name, newval->value); + bond->params.min_links = newval->value; + + return 0; +} + +static int bond_option_lp_interval_set(struct bonding *bond, + const struct bond_opt_value *newval) +{ + bond->params.lp_interval = newval->value; + + return 0; +} + +static int bond_option_pps_set(struct bonding *bond, + const struct bond_opt_value *newval) +{ + bond->params.packets_per_slave = newval->value; + if (newval->value > 0) { + bond->params.reciprocal_packets_per_slave = + reciprocal_value(newval->value); + } else { + /* reciprocal_packets_per_slave is unused if + * packets_per_slave is 0 or 1, just initialize it + */ + bond->params.reciprocal_packets_per_slave = + (struct reciprocal_value) { 0 }; + } + + return 0; +} + +static int bond_option_lacp_rate_set(struct bonding *bond, + const struct bond_opt_value *newval) +{ + pr_info("%s: Setting LACP rate to %s (%llu)\n", + bond->dev->name, newval->string, newval->value); + bond->params.lacp_fast = newval->value; + bond_3ad_update_lacp_rate(bond); + + return 0; +} + +static int bond_option_ad_select_set(struct bonding *bond, + const struct bond_opt_value *newval) +{ + pr_info("%s: Setting ad_select to %s (%llu)\n", + bond->dev->name, newval->string, newval->value); + bond->params.ad_select = newval->value; + + return 0; +} + +static int bond_option_queue_id_set(struct bonding *bond, + const struct bond_opt_value *newval) +{ + struct slave *slave, *update_slave; + struct net_device *sdev; + struct list_head *iter; + char *delim; + int ret = 0; + u16 qid; + + /* delim will point to queue id if successful */ + delim = strchr(newval->string, ':'); + 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 (!dev_valid_name(newval->string) || + qid > bond->dev->real_num_tx_queues) + goto err_no_cmd; + + /* Get the pointer to that interface if it exists */ + sdev = __dev_get_by_name(dev_net(bond->dev), newval->string); + if (!sdev) + goto err_no_cmd; + + /* Search for thes slave and check for duplicate qids */ + update_slave = NULL; + bond_for_each_slave(bond, slave, iter) { + 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; + } + } + + if (!update_slave) + goto err_no_cmd; + + /* Actually set the qids for the slave */ + update_slave->queue_id = qid; + +out: + return ret; + +err_no_cmd: + pr_info("invalid input for queue_id set for %s\n", bond->dev->name); + ret = -EPERM; + goto out; + +} + +static int bond_option_slaves_set(struct bonding *bond, + const struct bond_opt_value *newval) +{ + char command[IFNAMSIZ + 1] = { 0, }; + struct net_device *dev; + char *ifname; + int ret; + + sscanf(newval->string, "%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); + ret = bond_enslave(bond->dev, dev); + break; + + case '-': + pr_info("%s: Removing slave %s\n", bond->dev->name, dev->name); + ret = bond_release(bond->dev, dev); + break; + + default: + goto err_no_cmd; + } + +out: + return ret; + +err_no_cmd: + pr_err("no command found in slaves file for bond %s - use +ifname or -ifname\n", + bond->dev->name); + ret = -EPERM; + goto out; +} + +static int bond_option_tlb_dynamic_lb_set(struct bonding *bond, + const struct bond_opt_value *newval) +{ + pr_info("%s: Setting dynamic-lb to %s (%llu)\n", + bond->dev->name, newval->string, newval->value); + bond->params.tlb_dynamic_lb = newval->value; + + return 0; +} diff --git a/drivers/net/bonding/bond_options.h b/drivers/net/bonding/bond_options.h new file mode 100644 index 00000000000..17ded5b2917 --- /dev/null +++ b/drivers/net/bonding/bond_options.h @@ -0,0 +1,130 @@ +/* + * drivers/net/bond/bond_options.h - bonding options + * Copyright (c) 2013 Nikolay Aleksandrov <nikolay@redhat.com> + * + * This program is free software; you can redistribute it and/or modify + * it under the terms of the GNU General Public License as published by + * the Free Software Foundation; either version 2 of the License, or + * (at your option) any later version. + */ + +#ifndef _BOND_OPTIONS_H +#define _BOND_OPTIONS_H + +#define BOND_OPT_MAX_NAMELEN 32 +#define BOND_OPT_VALID(opt) ((opt) < BOND_OPT_LAST) +#define BOND_MODE_ALL_EX(x) (~(x)) + +/* Option flags: + * BOND_OPTFLAG_NOSLAVES - check if the bond device is empty before setting + * BOND_OPTFLAG_IFDOWN - check if the bond device is down before setting + * BOND_OPTFLAG_RAWVAL - the option parses the value itself + */ +enum { + BOND_OPTFLAG_NOSLAVES = BIT(0), + BOND_OPTFLAG_IFDOWN = BIT(1), + BOND_OPTFLAG_RAWVAL = BIT(2) +}; + +/* Value type flags: + * BOND_VALFLAG_DEFAULT - mark the value as default + * BOND_VALFLAG_(MIN|MAX) - mark the value as min/max + */ +enum { + BOND_VALFLAG_DEFAULT = BIT(0), + BOND_VALFLAG_MIN = BIT(1), + BOND_VALFLAG_MAX = BIT(2) +}; + +/* Option IDs, their bit positions correspond to their IDs */ +enum { + BOND_OPT_MODE, + BOND_OPT_PACKETS_PER_SLAVE, + BOND_OPT_XMIT_HASH, + BOND_OPT_ARP_VALIDATE, + BOND_OPT_ARP_ALL_TARGETS, + BOND_OPT_FAIL_OVER_MAC, + BOND_OPT_ARP_INTERVAL, + BOND_OPT_ARP_TARGETS, + BOND_OPT_DOWNDELAY, + BOND_OPT_UPDELAY, + BOND_OPT_LACP_RATE, + BOND_OPT_MINLINKS, + BOND_OPT_AD_SELECT, + BOND_OPT_NUM_PEER_NOTIF, + BOND_OPT_MIIMON, + BOND_OPT_PRIMARY, + BOND_OPT_PRIMARY_RESELECT, + BOND_OPT_USE_CARRIER, + BOND_OPT_ACTIVE_SLAVE, + BOND_OPT_QUEUE_ID, + BOND_OPT_ALL_SLAVES_ACTIVE, + BOND_OPT_RESEND_IGMP, + BOND_OPT_LP_INTERVAL, + BOND_OPT_SLAVES, + BOND_OPT_TLB_DYNAMIC_LB, + BOND_OPT_LAST +}; + +/* This structure is used for storing option values and for passing option + * values when changing an option. The logic when used as an arg is as follows: + * - if string != NULL -> parse it, if the opt is RAW type then return it, else + * return the parse result + * - if string == NULL -> parse value + */ +struct bond_opt_value { + char *string; + u64 value; + u32 flags; +}; + +struct bonding; + +struct bond_option { + int id; + const char *name; + const char *desc; + u32 flags; + + /* unsuppmodes is used to denote modes in which the option isn't + * supported. + */ + unsigned long unsuppmodes; + /* supported values which this option can have, can be a subset of + * BOND_OPTVAL_RANGE's value range + */ + const struct bond_opt_value *values; + + int (*set)(struct bonding *bond, const struct bond_opt_value *val); +}; + +int __bond_opt_set(struct bonding *bond, unsigned int option, + struct bond_opt_value *val); +int bond_opt_tryset_rtnl(struct bonding *bond, unsigned int option, char *buf); + +const struct bond_opt_value *bond_opt_parse(const struct bond_option *opt, + struct bond_opt_value *val); +const struct bond_option *bond_opt_get(unsigned int option); +const struct bond_option *bond_opt_get_by_name(const char *name); +const struct bond_opt_value *bond_opt_get_val(unsigned int option, u64 val); + +/* This helper is used to initialize a bond_opt_value structure for parameter + * passing. There should be either a valid string or value, but not both. + * When value is ULLONG_MAX then string will be used. + */ +static inline void __bond_opt_init(struct bond_opt_value *optval, + char *string, u64 value) +{ + memset(optval, 0, sizeof(*optval)); + optval->value = ULLONG_MAX; + if (value == ULLONG_MAX) + optval->string = string; + else + optval->value = value; +} +#define bond_opt_initval(optval, value) __bond_opt_init(optval, NULL, value) +#define bond_opt_initstr(optval, str) __bond_opt_init(optval, str, ULLONG_MAX) + +void bond_option_arp_ip_targets_clear(struct bonding *bond); + +#endif /* _BOND_OPTIONS_H */ diff --git a/drivers/net/bonding/bond_procfs.c b/drivers/net/bonding/bond_procfs.c new file mode 100644 index 00000000000..b215b479bb3 --- /dev/null +++ b/drivers/net/bonding/bond_procfs.c @@ -0,0 +1,296 @@ +#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; + struct list_head *iter; + struct slave *slave; + loff_t off = 0; + + /* 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, iter) + 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 list_head *iter; + struct slave *slave; + bool found = false; + + ++*pos; + if (v == SEQ_START_TOKEN) + return bond_first_slave(bond); + + if (bond_is_last_slave(bond, v)) + return NULL; + + bond_for_each_slave(bond, slave, iter) { + if (found) + return slave; + if (slave == v) + found = true; + } + + return NULL; +} + +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; + const struct bond_opt_value *optval; + struct slave *curr; + int i; + + curr = rcu_dereference(bond->curr_active_slave); + + seq_printf(seq, "Bonding Mode: %s", + bond_mode_name(BOND_MODE(bond))); + + if (BOND_MODE(bond) == BOND_MODE_ACTIVEBACKUP && + bond->params.fail_over_mac) { + optval = bond_opt_get_val(BOND_OPT_FAIL_OVER_MAC, + bond->params.fail_over_mac); + seq_printf(seq, " (fail_over_mac %s)", optval->string); + } + + seq_printf(seq, "\n"); + + if (BOND_MODE(bond) == BOND_MODE_XOR || + BOND_MODE(bond) == BOND_MODE_8023AD) { + optval = bond_opt_get_val(BOND_OPT_XMIT_HASH, + bond->params.xmit_policy); + seq_printf(seq, "Transmit Hash Policy: %s (%d)\n", + optval->string, bond->params.xmit_policy); + } + + if (bond_uses_primary(bond)) { + seq_printf(seq, "Primary Slave: %s", + (bond->primary_slave) ? + bond->primary_slave->dev->name : "None"); + if (bond->primary_slave) { + optval = bond_opt_get_val(BOND_OPT_PRIMARY_RESELECT, + bond->params.primary_reselect); + seq_printf(seq, " (primary_reselect %s)", + optval->string); + } + + 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_MODE(bond) == 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); + optval = bond_opt_get_val(BOND_OPT_AD_SELECT, + bond->params.ad_select); + seq_printf(seq, "Aggregator selection policy (ad_select): %s\n", + optval->string); + + 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", bond_slave_link_status(slave->link)); + 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_MODE(bond) == 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; + 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; + seq->private = PDE_DATA(inode); + } + + 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_warn("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_warn("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/drivers/net/bonding/bond_sysfs.c b/drivers/net/bonding/bond_sysfs.c index 32d13da43a0..daed52f68ce 100644 --- a/drivers/net/bonding/bond_sysfs.c +++ b/drivers/net/bonding/bond_sysfs.c @@ -1,4 +1,3 @@ - /* * Copyright(c) 2004-2005 Intel Corporation. All rights reserved. * @@ -13,19 +12,19 @@ * 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. + * with this program; if not, see <http://www.gnu.org/licenses/>. * * The full GNU General Public License is included in this distribution in the * file called LICENSE. * */ -#include <linux/config.h> + +#define pr_fmt(fmt) KBUILD_MODNAME ": " fmt + #include <linux/kernel.h> #include <linux/module.h> -#include <linux/sched.h> #include <linux/device.h> -#include <linux/sysdev.h> +#include <linux/sched.h> #include <linux/fs.h> #include <linux/types.h> #include <linux/string.h> @@ -33,90 +32,77 @@ #include <linux/inetdevice.h> #include <linux/in.h> #include <linux/sysfs.h> -#include <linux/string.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> -/* #define BONDING_DEBUG 1 */ #include "bonding.h" -#define to_class_dev(obj) container_of(obj,struct class_device,kobj) -#define to_net_dev(class) container_of(class, struct net_device, class_dev) -#define to_bond(cd) ((struct bonding *)(to_net_dev(cd)->priv)) - -/*---------------------------- Declarations -------------------------------*/ - - -extern struct list_head bond_dev_list; -extern struct bond_params bonding_defaults; -extern struct bond_parm_tbl bond_mode_tbl[]; -extern struct bond_parm_tbl bond_lacp_tbl[]; -extern struct bond_parm_tbl xmit_hashtype_tbl[]; -static int expected_refcount = -1; -static struct class *netdev_class; -/*--------------------------- Data Structures -----------------------------*/ +#define to_dev(obj) container_of(obj, struct device, kobj) +#define to_bond(cd) ((struct bonding *)(netdev_priv(to_net_dev(cd)))) -/* Bonding sysfs lock. Why can't we just use the subsytem lock? - * Because kobject_register tries to acquire the subsystem lock. If - * we already hold the lock (which we would if the user was creating - * a new bond through the sysfs interface), we deadlock. - * This lock is only needed when deleting a bond - we need to make sure - * that we don't collide with an ongoing ioctl. - */ - -struct rw_semaphore bonding_rwsem; - - - - -/*------------------------------ Functions --------------------------------*/ - -/* - * "show" function for the bond_masters attribute. +/* "show" function for the bond_masters attribute. * The class parameter is ignored. */ -static ssize_t bonding_show_bonds(struct class *cls, char *buffer) +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; - down_read(&(bonding_rwsem)); + rtnl_lock(); - list_for_each_entry(bond, &bond_dev_list, bond_list) { + 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(buffer + res, "++more++"); + res += sprintf(buf + res, "++more++ "); break; } - res += sprintf(buffer + res, "%s ", - bond->dev->name); + res += sprintf(buf + res, "%s ", bond->dev->name); } - res += sprintf(buffer + res, "\n"); - res++; - up_read(&(bonding_rwsem)); + if (res) + buf[res-1] = '\n'; /* eat the leftover space */ + + rtnl_unlock(); return res; } -/* - * "store" function for the bond_masters attribute. This is what +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, const char *buffer, size_t count) +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 res = count; - struct bonding *bond; - struct bonding *nxt; + int rv, res = count; - down_write(&(bonding_rwsem)); sscanf(buffer, "%16s", command); /* IFNAMSIZ*/ ifname = command + 1; if ((strlen(command) <= 1) || @@ -124,1166 +110,617 @@ static ssize_t bonding_store_bonds(struct class *cls, const char *buffer, size_t goto err_no_cmd; if (command[0] == '+') { - - /* Check to see if the bond already exists. */ - list_for_each_entry_safe(bond, nxt, &bond_dev_list, bond_list) - if (strnicmp(bond->dev->name, ifname, IFNAMSIZ) == 0) { - printk(KERN_ERR DRV_NAME - ": cannot add bond %s; it already exists\n", - ifname); - res = -EPERM; - goto out; - } - - printk(KERN_INFO DRV_NAME - ": %s is being created...\n", ifname); - if (bond_create(ifname, &bonding_defaults, &bond)) { - printk(KERN_INFO DRV_NAME - ": %s interface already exists. Bond creation failed.\n", - ifname); - res = -EPERM; + 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; } - goto out; - } + } else if (command[0] == '-') { + struct net_device *bond_dev; - if (command[0] == '-') { - list_for_each_entry_safe(bond, nxt, &bond_dev_list, bond_list) - if (strnicmp(bond->dev->name, ifname, IFNAMSIZ) == 0) { - rtnl_lock(); - /* check the ref count on the bond's kobject. - * If it's > expected, then there's a file open, - * and we have to fail. - */ - if (atomic_read(&bond->dev->class_dev.kobj.kref.refcount) - > expected_refcount){ - rtnl_unlock(); - printk(KERN_INFO DRV_NAME - ": Unable remove bond %s due to open references.\n", - ifname); - res = -EPERM; - goto out; - } - printk(KERN_INFO DRV_NAME - ": %s is being deleted...\n", - bond->dev->name); - unregister_netdevice(bond->dev); - bond_deinit(bond->dev); - bond_destroy_sysfs_entry(bond); - rtnl_unlock(); - goto out; - } - - printk(KERN_ERR DRV_NAME - ": unable to delete non-existent bond %s\n", ifname); - res = -ENODEV; - goto out; - } - -err_no_cmd: - printk(KERN_ERR DRV_NAME - ": no command found in bonding_masters. Use +ifname or -ifname.\n"); - res = -EPERM; + 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. */ -out: - up_write(&(bonding_rwsem)); return res; + +err_no_cmd: + pr_err("no command found in bonding_masters - use +ifname or -ifname\n"); + return -EPERM; } + /* class attribute for bond_masters file. This ends up in /sys/class/net */ -static CLASS_ATTR(bonding_masters, S_IWUSR | S_IRUGO, - bonding_show_bonds, bonding_store_bonds); +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, +}; -int bond_create_slave_symlinks(struct net_device *master, struct net_device *slave) +/* Generic "store" method for bonding sysfs option setting */ +static ssize_t bonding_sysfs_store_option(struct device *d, + struct device_attribute *attr, + const char *buffer, size_t count) { - char linkname[IFNAMSIZ+7]; - int ret = 0; - - /* first, create a link from the slave back to the master */ - ret = sysfs_create_link(&(slave->class_dev.kobj), &(master->class_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->class_dev.kobj), &(slave->class_dev.kobj), - linkname); - return ret; + struct bonding *bond = to_bond(d); + const struct bond_option *opt; + int ret; -} - -void bond_destroy_slave_symlinks(struct net_device *master, struct net_device *slave) -{ - char linkname[IFNAMSIZ+7]; + opt = bond_opt_get_by_name(attr->attr.name); + if (WARN_ON(!opt)) + return -ENOENT; + ret = bond_opt_tryset_rtnl(bond, opt->id, (char *)buffer); + if (!ret) + ret = count; - sysfs_remove_link(&(slave->class_dev.kobj), "master"); - sprintf(linkname,"slave_%s",slave->name); - sysfs_remove_link(&(master->class_dev.kobj), linkname); + return ret; } - -/* - * Show the slaves in the current bond. - */ -static ssize_t bonding_show_slaves(struct class_device *cd, char *buf) +/* Show the slaves in the current bond. */ +static ssize_t bonding_show_slaves(struct device *d, + struct device_attribute *attr, char *buf) { + struct bonding *bond = to_bond(d); + struct list_head *iter; struct slave *slave; - int i, res = 0; - struct bonding *bond = to_bond(cd); + int res = 0; + + if (!rtnl_trylock()) + return restart_syscall(); - read_lock_bh(&bond->lock); - bond_for_each_slave(bond, slave, i) { + bond_for_each_slave(bond, slave, iter) { 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++"); + res += sprintf(buf + res, "++more++ "); break; } res += sprintf(buf + res, "%s ", slave->dev->name); } - read_unlock_bh(&bond->lock); - res += sprintf(buf + res, "\n"); - res++; - return res; -} - -/* - * Set the slaves in the current bond. The bond interface must be - * up for this to succeed. - * This function is largely the same flow as bonding_update_bonds(). - */ -static ssize_t bonding_store_slaves(struct class_device *cd, const char *buffer, size_t count) -{ - char command[IFNAMSIZ + 1] = { 0, }; - char *ifname; - int i, res, found, ret = count; - struct slave *slave; - struct net_device *dev = 0; - struct bonding *bond = to_bond(cd); - - /* Quick sanity check -- is the bond interface up? */ - if (!(bond->dev->flags & IFF_UP)) { - printk(KERN_ERR DRV_NAME - ": %s: Unable to update slaves because interface is down.\n", - bond->dev->name); - ret = -EPERM; - goto out; - } - - /* Note: We can't hold bond->lock here, as bond_create grabs it. */ - - sscanf(buffer, "%16s", command); /* IFNAMSIZ*/ - ifname = command + 1; - if ((strlen(command) <= 1) || - !dev_valid_name(ifname)) - goto err_no_cmd; - - if (command[0] == '+') { - - /* Got a slave name in ifname. Is it already in the list? */ - found = 0; - read_lock_bh(&bond->lock); - bond_for_each_slave(bond, slave, i) - if (strnicmp(slave->dev->name, ifname, IFNAMSIZ) == 0) { - printk(KERN_ERR DRV_NAME - ": %s: Interface %s is already enslaved!\n", - bond->dev->name, ifname); - ret = -EPERM; - read_unlock_bh(&bond->lock); - goto out; - } - - read_unlock_bh(&bond->lock); - printk(KERN_INFO DRV_NAME ": %s: Adding slave %s.\n", - bond->dev->name, ifname); - dev = dev_get_by_name(ifname); - if (!dev) { - printk(KERN_INFO DRV_NAME - ": %s: Interface %s does not exist!\n", - bond->dev->name, ifname); - ret = -EPERM; - goto out; - } - else - dev_put(dev); - - if (dev->flags & IFF_UP) { - printk(KERN_ERR DRV_NAME - ": %s: Error: Unable to enslave %s " - "because it is already up.\n", - bond->dev->name, dev->name); - ret = -EPERM; - goto out; - } - /* 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 (!(*((u32 *) & (bond->dev->dev_addr[0])))) { - memcpy(bond->dev->dev_addr, dev->dev_addr, - dev->addr_len); - } - - /* Set the slave's MTU to match the bond */ - if (dev->mtu != bond->dev->mtu) { - if (dev->change_mtu) { - res = dev->change_mtu(dev, - bond->dev->mtu); - if (res) { - ret = res; - goto out; - } - } else { - dev->mtu = bond->dev->mtu; - } - } - rtnl_lock(); - res = bond_enslave(bond->dev, dev); - rtnl_unlock(); - if (res) { - ret = res; - } - goto out; - } - if (command[0] == '-') { - dev = NULL; - bond_for_each_slave(bond, slave, i) - if (strnicmp(slave->dev->name, ifname, IFNAMSIZ) == 0) { - dev = slave->dev; - break; - } - if (dev) { - printk(KERN_INFO DRV_NAME ": %s: Removing slave %s\n", - bond->dev->name, dev->name); - rtnl_lock(); - res = bond_release(bond->dev, dev); - rtnl_unlock(); - if (res) { - ret = res; - goto out; - } - /* set the slave MTU to the default */ - if (dev->change_mtu) { - dev->change_mtu(dev, 1500); - } else { - dev->mtu = 1500; - } - } - else { - printk(KERN_ERR DRV_NAME ": unable to remove non-existent slave %s for bond %s.\n", - ifname, bond->dev->name); - ret = -ENODEV; - } - goto out; - } + rtnl_unlock(); -err_no_cmd: - printk(KERN_ERR DRV_NAME ": no command found in slaves file for bond %s. Use +ifname or -ifname.\n", bond->dev->name); - ret = -EPERM; + if (res) + buf[res-1] = '\n'; /* eat the leftover space */ -out: - return ret; + return res; } +static DEVICE_ATTR(slaves, S_IRUGO | S_IWUSR, bonding_show_slaves, + bonding_sysfs_store_option); -static CLASS_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 class_device *cd, char *buf) +/* Show the bonding mode. */ +static ssize_t bonding_show_mode(struct device *d, + struct device_attribute *attr, char *buf) { - struct bonding *bond = to_bond(cd); + struct bonding *bond = to_bond(d); + const struct bond_opt_value *val; - return sprintf(buf, "%s %d\n", - bond_mode_tbl[bond->params.mode].modename, - bond->params.mode) + 1; + val = bond_opt_get_val(BOND_OPT_MODE, BOND_MODE(bond)); + + return sprintf(buf, "%s %d\n", val->string, BOND_MODE(bond)); } +static DEVICE_ATTR(mode, S_IRUGO | S_IWUSR, + bonding_show_mode, bonding_sysfs_store_option); -static ssize_t bonding_store_mode(struct class_device *cd, const char *buf, size_t count) +/* Show the bonding transmit hash method. */ +static ssize_t bonding_show_xmit_hash(struct device *d, + struct device_attribute *attr, + char *buf) { - int new_value, ret = count; - struct bonding *bond = to_bond(cd); - - if (bond->dev->flags & IFF_UP) { - printk(KERN_ERR DRV_NAME - ": unable to update mode of %s because interface is up.\n", - bond->dev->name); - ret = -EPERM; - goto out; - } + struct bonding *bond = to_bond(d); + const struct bond_opt_value *val; - new_value = bond_parse_parm((char *)buf, bond_mode_tbl); - if (new_value < 0) { - printk(KERN_ERR DRV_NAME - ": %s: Ignoring invalid mode value %.*s.\n", - bond->dev->name, - (int)strlen(buf) - 1, buf); - ret = -EINVAL; - goto out; - } else { - bond->params.mode = new_value; - bond_set_mode_ops(bond, bond->params.mode); - printk(KERN_INFO DRV_NAME ": %s: setting mode to %s (%d).\n", - bond->dev->name, bond_mode_tbl[new_value].modename, new_value); - } -out: - return ret; + val = bond_opt_get_val(BOND_OPT_XMIT_HASH, bond->params.xmit_policy); + + return sprintf(buf, "%s %d\n", val->string, bond->params.xmit_policy); } -static CLASS_DEVICE_ATTR(mode, S_IRUGO | S_IWUSR, bonding_show_mode, bonding_store_mode); +static DEVICE_ATTR(xmit_hash_policy, S_IRUGO | S_IWUSR, + bonding_show_xmit_hash, bonding_sysfs_store_option); -/* - * 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 class_device *cd, char *buf) +/* Show arp_validate. */ +static ssize_t bonding_show_arp_validate(struct device *d, + struct device_attribute *attr, + char *buf) { - int count; - struct bonding *bond = to_bond(cd); - - if ((bond->params.mode != BOND_MODE_XOR) && - (bond->params.mode != BOND_MODE_8023AD)) { - // Not Applicable - count = sprintf(buf, "NA\n") + 1; - } else { - count = sprintf(buf, "%s %d\n", - xmit_hashtype_tbl[bond->params.xmit_policy].modename, - bond->params.xmit_policy) + 1; - } + struct bonding *bond = to_bond(d); + const struct bond_opt_value *val; - return count; + val = bond_opt_get_val(BOND_OPT_ARP_VALIDATE, + bond->params.arp_validate); + + return sprintf(buf, "%s %d\n", val->string, bond->params.arp_validate); } +static DEVICE_ATTR(arp_validate, S_IRUGO | S_IWUSR, bonding_show_arp_validate, + bonding_sysfs_store_option); -static ssize_t bonding_store_xmit_hash(struct class_device *cd, const char *buf, size_t count) +/* Show arp_all_targets. */ +static ssize_t bonding_show_arp_all_targets(struct device *d, + struct device_attribute *attr, + char *buf) { - int new_value, ret = count; - struct bonding *bond = to_bond(cd); - - if (bond->dev->flags & IFF_UP) { - printk(KERN_ERR DRV_NAME - "%s: Interface is up. Unable to update xmit policy.\n", - bond->dev->name); - ret = -EPERM; - goto out; - } + struct bonding *bond = to_bond(d); + const struct bond_opt_value *val; - if ((bond->params.mode != BOND_MODE_XOR) && - (bond->params.mode != BOND_MODE_8023AD)) { - printk(KERN_ERR DRV_NAME - "%s: Transmit hash policy is irrelevant in this mode.\n", - bond->dev->name); - ret = -EPERM; - goto out; - } - - new_value = bond_parse_parm((char *)buf, xmit_hashtype_tbl); - if (new_value < 0) { - printk(KERN_ERR DRV_NAME - ": %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); - printk(KERN_INFO DRV_NAME ": %s: setting xmit hash policy to %s (%d).\n", - bond->dev->name, xmit_hashtype_tbl[new_value].modename, new_value); - } -out: - return ret; + val = bond_opt_get_val(BOND_OPT_ARP_ALL_TARGETS, + bond->params.arp_all_targets); + return sprintf(buf, "%s %d\n", + val->string, bond->params.arp_all_targets); } -static CLASS_DEVICE_ATTR(xmit_hash_policy, S_IRUGO | S_IWUSR, bonding_show_xmit_hash, bonding_store_xmit_hash); +static DEVICE_ATTR(arp_all_targets, S_IRUGO | S_IWUSR, + bonding_show_arp_all_targets, bonding_sysfs_store_option); -/* - * 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 class_device *cd, char *buf) +/* Show fail_over_mac. */ +static ssize_t bonding_show_fail_over_mac(struct device *d, + struct device_attribute *attr, + char *buf) { - struct bonding *bond = to_bond(cd); + struct bonding *bond = to_bond(d); + const struct bond_opt_value *val; - return sprintf(buf, "%d\n", bond->params.arp_interval) + 1; + val = bond_opt_get_val(BOND_OPT_FAIL_OVER_MAC, + bond->params.fail_over_mac); + + return sprintf(buf, "%s %d\n", val->string, bond->params.fail_over_mac); } +static DEVICE_ATTR(fail_over_mac, S_IRUGO | S_IWUSR, + bonding_show_fail_over_mac, bonding_sysfs_store_option); -static ssize_t bonding_store_arp_interval(struct class_device *cd, const char *buf, size_t count) +/* Show the arp timer interval. */ +static ssize_t bonding_show_arp_interval(struct device *d, + struct device_attribute *attr, + char *buf) { - int new_value, ret = count; - struct bonding *bond = to_bond(cd); - - if (sscanf(buf, "%d", &new_value) != 1) { - printk(KERN_ERR DRV_NAME - ": %s: no arp_interval value specified.\n", - bond->dev->name); - ret = -EINVAL; - goto out; - } - if (new_value < 0) { - printk(KERN_ERR DRV_NAME - ": %s: Invalid arp_interval value %d not in range 1-%d; rejected.\n", - bond->dev->name, new_value, INT_MAX); - ret = -EINVAL; - goto out; - } + struct bonding *bond = to_bond(d); - printk(KERN_INFO DRV_NAME - ": %s: Setting ARP monitoring interval to %d.\n", - bond->dev->name, new_value); - bond->params.arp_interval = new_value; - if (bond->params.miimon) { - printk(KERN_INFO DRV_NAME - ": %s: ARP monitoring cannot be used with MII monitoring. " - "%s Disabling MII monitoring.\n", - bond->dev->name, bond->dev->name); - bond->params.miimon = 0; - /* Kill MII timer, else it brings bond's link down */ - if (bond->arp_timer.function) { - printk(KERN_INFO DRV_NAME - ": %s: Kill MII timer, else it brings bond's link down...\n", - bond->dev->name); - del_timer_sync(&bond->mii_timer); - } - } - if (!bond->params.arp_targets[0]) { - printk(KERN_INFO DRV_NAME - ": %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 (bond->arp_timer.function) { - /* The timer's already set up, so fire it off */ - mod_timer(&bond->arp_timer, jiffies + 1); - } else { - /* Set up the timer. */ - init_timer(&bond->arp_timer); - bond->arp_timer.expires = jiffies + 1; - bond->arp_timer.data = - (unsigned long) bond->dev; - if (bond->params.mode == BOND_MODE_ACTIVEBACKUP) { - bond->arp_timer.function = - (void *) - &bond_activebackup_arp_mon; - } else { - bond->arp_timer.function = - (void *) - &bond_loadbalance_arp_mon; - } - add_timer(&bond->arp_timer); - } - } - -out: - return ret; + return sprintf(buf, "%d\n", bond->params.arp_interval); } -static CLASS_DEVICE_ATTR(arp_interval, S_IRUGO | S_IWUSR , bonding_show_arp_interval, bonding_store_arp_interval); +static DEVICE_ATTR(arp_interval, S_IRUGO | S_IWUSR, + bonding_show_arp_interval, bonding_sysfs_store_option); -/* - * Show and set the arp targets. - */ -static ssize_t bonding_show_arp_targets(struct class_device *cd, char *buf) +/* Show the arp targets. */ +static ssize_t bonding_show_arp_targets(struct device *d, + struct device_attribute *attr, + char *buf) { + struct bonding *bond = to_bond(d); int i, res = 0; - struct bonding *bond = to_bond(cd); for (i = 0; i < BOND_MAX_ARP_TARGETS; i++) { if (bond->params.arp_targets[i]) - res += sprintf(buf + res, "%u.%u.%u.%u ", - NIPQUAD(bond->params.arp_targets[i])); + res += sprintf(buf + res, "%pI4 ", + &bond->params.arp_targets[i]); } if (res) - res--; /* eat the leftover space */ - res += sprintf(buf + res, "\n"); - res++; + buf[res-1] = '\n'; /* eat the leftover space */ + return res; } +static DEVICE_ATTR(arp_ip_target, S_IRUGO | S_IWUSR, + bonding_show_arp_targets, bonding_sysfs_store_option); -static ssize_t bonding_store_arp_targets(struct class_device *cd, const char *buf, size_t count) +/* Show the up and down delays. */ +static ssize_t bonding_show_downdelay(struct device *d, + struct device_attribute *attr, + char *buf) { - u32 newtarget; - int i = 0, done = 0, ret = count; - struct bonding *bond = to_bond(cd); - u32 *targets; - - targets = bond->params.arp_targets; - newtarget = in_aton(buf + 1); - /* look for adds */ - if (buf[0] == '+') { - if ((newtarget == 0) || (newtarget == INADDR_BROADCAST)) { - printk(KERN_ERR DRV_NAME - ": %s: invalid ARP target %u.%u.%u.%u specified for addition\n", - bond->dev->name, NIPQUAD(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); i++) { - if (targets[i] == newtarget) { /* duplicate */ - printk(KERN_ERR DRV_NAME - ": %s: ARP target %u.%u.%u.%u is already present\n", - bond->dev->name, NIPQUAD(newtarget)); - if (done) - targets[i] = 0; - ret = -EINVAL; - goto out; - } - if (targets[i] == 0 && !done) { - printk(KERN_INFO DRV_NAME - ": %s: adding ARP target %d.%d.%d.%d.\n", - bond->dev->name, NIPQUAD(newtarget)); - done = 1; - targets[i] = newtarget; - } - } - if (!done) { - printk(KERN_ERR DRV_NAME - ": %s: ARP target table is full!\n", - bond->dev->name); - ret = -EINVAL; - goto out; - } - - } - else if (buf[0] == '-') { - if ((newtarget == 0) || (newtarget == INADDR_BROADCAST)) { - printk(KERN_ERR DRV_NAME - ": %s: invalid ARP target %d.%d.%d.%d specified for removal\n", - bond->dev->name, NIPQUAD(newtarget)); - ret = -EINVAL; - goto out; - } - - for (i = 0; (i < BOND_MAX_ARP_TARGETS); i++) { - if (targets[i] == newtarget) { - printk(KERN_INFO DRV_NAME - ": %s: removing ARP target %d.%d.%d.%d.\n", - bond->dev->name, NIPQUAD(newtarget)); - targets[i] = 0; - done = 1; - } - } - if (!done) { - printk(KERN_INFO DRV_NAME - ": %s: unable to remove nonexistent ARP target %d.%d.%d.%d.\n", - bond->dev->name, NIPQUAD(newtarget)); - ret = -EINVAL; - goto out; - } - } - else { - printk(KERN_ERR DRV_NAME ": no command found in arp_ip_targets file for bond %s. Use +<addr> or -<addr>.\n", - bond->dev->name); - ret = -EPERM; - goto out; - } + struct bonding *bond = to_bond(d); -out: - return ret; + return sprintf(buf, "%d\n", bond->params.downdelay * bond->params.miimon); } -static CLASS_DEVICE_ATTR(arp_ip_target, S_IRUGO | S_IWUSR , bonding_show_arp_targets, bonding_store_arp_targets); +static DEVICE_ATTR(downdelay, S_IRUGO | S_IWUSR, + bonding_show_downdelay, bonding_sysfs_store_option); -/* - * 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 class_device *cd, char *buf) +static ssize_t bonding_show_updelay(struct device *d, + struct device_attribute *attr, + char *buf) { - struct bonding *bond = to_bond(cd); + struct bonding *bond = to_bond(d); + + return sprintf(buf, "%d\n", bond->params.updelay * bond->params.miimon); - return sprintf(buf, "%d\n", bond->params.downdelay * bond->params.miimon) + 1; } +static DEVICE_ATTR(updelay, S_IRUGO | S_IWUSR, + bonding_show_updelay, bonding_sysfs_store_option); -static ssize_t bonding_store_downdelay(struct class_device *cd, const char *buf, size_t count) +/* Show the LACP interval. */ +static ssize_t bonding_show_lacp(struct device *d, + struct device_attribute *attr, + char *buf) { - int new_value, ret = count; - struct bonding *bond = to_bond(cd); - - if (!(bond->params.miimon)) { - printk(KERN_ERR DRV_NAME - ": %s: Unable to set down delay as MII monitoring is disabled\n", - bond->dev->name); - ret = -EPERM; - goto out; - } + struct bonding *bond = to_bond(d); + const struct bond_opt_value *val; - if (sscanf(buf, "%d", &new_value) != 1) { - printk(KERN_ERR DRV_NAME - ": %s: no down delay value specified.\n", - bond->dev->name); - ret = -EINVAL; - goto out; - } - if (new_value < 0) { - printk(KERN_ERR DRV_NAME - ": %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) { - printk(KERN_WARNING DRV_NAME - ": %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; - printk(KERN_INFO DRV_NAME ": %s: Setting down delay to %d.\n", - bond->dev->name, bond->params.downdelay * bond->params.miimon); + val = bond_opt_get_val(BOND_OPT_LACP_RATE, bond->params.lacp_fast); - } - -out: - return ret; + return sprintf(buf, "%s %d\n", val->string, bond->params.lacp_fast); } -static CLASS_DEVICE_ATTR(downdelay, S_IRUGO | S_IWUSR , bonding_show_downdelay, bonding_store_downdelay); +static DEVICE_ATTR(lacp_rate, S_IRUGO | S_IWUSR, + bonding_show_lacp, bonding_sysfs_store_option); -static ssize_t bonding_show_updelay(struct class_device *cd, char *buf) +static ssize_t bonding_show_min_links(struct device *d, + struct device_attribute *attr, + char *buf) { - struct bonding *bond = to_bond(cd); - - return sprintf(buf, "%d\n", bond->params.updelay * bond->params.miimon) + 1; + struct bonding *bond = to_bond(d); + return sprintf(buf, "%u\n", bond->params.min_links); } +static DEVICE_ATTR(min_links, S_IRUGO | S_IWUSR, + bonding_show_min_links, bonding_sysfs_store_option); -static ssize_t bonding_store_updelay(struct class_device *cd, const char *buf, size_t count) +static ssize_t bonding_show_ad_select(struct device *d, + struct device_attribute *attr, + char *buf) { - int new_value, ret = count; - struct bonding *bond = to_bond(cd); - - if (!(bond->params.miimon)) { - printk(KERN_ERR DRV_NAME - ": %s: Unable to set up delay as MII monitoring is disabled\n", - bond->dev->name); - ret = -EPERM; - goto out; - } + struct bonding *bond = to_bond(d); + const struct bond_opt_value *val; - if (sscanf(buf, "%d", &new_value) != 1) { - printk(KERN_ERR DRV_NAME - ": %s: no up delay value specified.\n", - bond->dev->name); - ret = -EINVAL; - goto out; - } - if (new_value < 0) { - printk(KERN_ERR DRV_NAME - ": %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) { - printk(KERN_WARNING DRV_NAME - ": %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; - printk(KERN_INFO DRV_NAME ": %s: Setting up delay to %d.\n", - bond->dev->name, bond->params.updelay * bond->params.miimon); - - } + val = bond_opt_get_val(BOND_OPT_AD_SELECT, bond->params.ad_select); -out: - return ret; + return sprintf(buf, "%s %d\n", val->string, bond->params.ad_select); } -static CLASS_DEVICE_ATTR(updelay, S_IRUGO | S_IWUSR , bonding_show_updelay, bonding_store_updelay); +static DEVICE_ATTR(ad_select, S_IRUGO | S_IWUSR, + bonding_show_ad_select, bonding_sysfs_store_option); -/* - * 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 class_device *cd, char *buf) +/* 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(cd); - - return sprintf(buf, "%s %d\n", - bond_lacp_tbl[bond->params.lacp_fast].modename, - bond->params.lacp_fast) + 1; + struct bonding *bond = to_bond(d); + return sprintf(buf, "%d\n", bond->params.num_peer_notif); } -static ssize_t bonding_store_lacp(struct class_device *cd, const char *buf, size_t count) +static ssize_t bonding_store_num_peer_notif(struct device *d, + struct device_attribute *attr, + const char *buf, size_t count) { - int new_value, ret = count; - struct bonding *bond = to_bond(cd); - - if (bond->dev->flags & IFF_UP) { - printk(KERN_ERR DRV_NAME - ": %s: Unable to update LACP rate because interface is up.\n", - bond->dev->name); - ret = -EPERM; - goto out; - } + struct bonding *bond = to_bond(d); + int ret; - if (bond->params.mode != BOND_MODE_8023AD) { - printk(KERN_ERR DRV_NAME - ": %s: Unable to update LACP rate because bond is not in 802.3ad mode.\n", - bond->dev->name); - ret = -EPERM; - goto out; - } + ret = bond_opt_tryset_rtnl(bond, BOND_OPT_NUM_PEER_NOTIF, (char *)buf); + if (!ret) + ret = count; - new_value = bond_parse_parm((char *)buf, bond_lacp_tbl); - - if ((new_value == 1) || (new_value == 0)) { - bond->params.lacp_fast = new_value; - printk(KERN_INFO DRV_NAME - ": %s: Setting LACP rate to %s (%d).\n", - bond->dev->name, bond_lacp_tbl[new_value].modename, new_value); - } else { - printk(KERN_ERR DRV_NAME - ": %s: Ignoring invalid LACP rate value %.*s.\n", - bond->dev->name, (int)strlen(buf) - 1, buf); - ret = -EINVAL; - } -out: return ret; } -static CLASS_DEVICE_ATTR(lacp_rate, S_IRUGO | S_IWUSR, bonding_show_lacp, bonding_store_lacp); +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 class_device *cd, char *buf) +/* Show the MII monitor interval. */ +static ssize_t bonding_show_miimon(struct device *d, + struct device_attribute *attr, + char *buf) { - struct bonding *bond = to_bond(cd); + struct bonding *bond = to_bond(d); - return sprintf(buf, "%d\n", bond->params.miimon) + 1; + return sprintf(buf, "%d\n", bond->params.miimon); } +static DEVICE_ATTR(miimon, S_IRUGO | S_IWUSR, + bonding_show_miimon, bonding_sysfs_store_option); -static ssize_t bonding_store_miimon(struct class_device *cd, const char *buf, size_t count) -{ - int new_value, ret = count; - struct bonding *bond = to_bond(cd); - - if (sscanf(buf, "%d", &new_value) != 1) { - printk(KERN_ERR DRV_NAME - ": %s: no miimon value specified.\n", - bond->dev->name); - ret = -EINVAL; - goto out; - } - if (new_value < 0) { - printk(KERN_ERR DRV_NAME - ": %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 { - printk(KERN_INFO DRV_NAME - ": %s: Setting MII monitoring interval to %d.\n", - bond->dev->name, new_value); - bond->params.miimon = new_value; - if(bond->params.updelay) - printk(KERN_INFO DRV_NAME - ": %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) - printk(KERN_INFO DRV_NAME - ": %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) { - printk(KERN_INFO DRV_NAME - ": %s: MII monitoring cannot be used with " - "ARP monitoring. Disabling ARP monitoring...\n", - bond->dev->name); - bond->params.arp_interval = 0; - /* Kill ARP timer, else it brings bond's link down */ - if (bond->mii_timer.function) { - printk(KERN_INFO DRV_NAME - ": %s: Kill ARP timer, else it brings bond's link down...\n", - bond->dev->name); - del_timer_sync(&bond->arp_timer); - } - } - - 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 (bond->mii_timer.function) { - /* The timer's already set up, so fire it off */ - mod_timer(&bond->mii_timer, jiffies + 1); - } else { - /* Set up the timer. */ - init_timer(&bond->mii_timer); - bond->mii_timer.expires = jiffies + 1; - bond->mii_timer.data = - (unsigned long) bond->dev; - bond->mii_timer.function = - (void *) &bond_mii_monitor; - add_timer(&bond->mii_timer); - } - } - } -out: - return ret; -} -static CLASS_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 class_device *cd, char *buf) +/* Show the primary slave. */ +static ssize_t bonding_show_primary(struct device *d, + struct device_attribute *attr, + char *buf) { int count = 0; - struct bonding *bond = to_bond(cd); + struct bonding *bond = to_bond(d); if (bond->primary_slave) - count = sprintf(buf, "%s\n", bond->primary_slave->dev->name) + 1; - else - count = sprintf(buf, "\n") + 1; + count = sprintf(buf, "%s\n", bond->primary_slave->dev->name); return count; } +static DEVICE_ATTR(primary, S_IRUGO | S_IWUSR, + bonding_show_primary, bonding_sysfs_store_option); -static ssize_t bonding_store_primary(struct class_device *cd, const char *buf, size_t count) +/* Show the primary_reselect flag. */ +static ssize_t bonding_show_primary_reselect(struct device *d, + struct device_attribute *attr, + char *buf) { - int i; - struct slave *slave; - struct bonding *bond = to_bond(cd); - - write_lock_bh(&bond->lock); - if (!USES_PRIMARY(bond->params.mode)) { - printk(KERN_INFO DRV_NAME - ": %s: Unable to set primary slave; %s is in mode %d\n", - bond->dev->name, bond->dev->name, bond->params.mode); - } else { - bond_for_each_slave(bond, slave, i) { - if (strnicmp - (slave->dev->name, buf, - strlen(slave->dev->name)) == 0) { - printk(KERN_INFO DRV_NAME - ": %s: Setting %s as primary slave.\n", - bond->dev->name, slave->dev->name); - bond->primary_slave = slave; - bond_select_active_slave(bond); - goto out; - } - } + struct bonding *bond = to_bond(d); + const struct bond_opt_value *val; - /* if we got here, then we didn't match the name of any slave */ + val = bond_opt_get_val(BOND_OPT_PRIMARY_RESELECT, + bond->params.primary_reselect); - if (strlen(buf) == 0 || buf[0] == '\n') { - printk(KERN_INFO DRV_NAME - ": %s: Setting primary slave to None.\n", - bond->dev->name); - bond->primary_slave = 0; - bond_select_active_slave(bond); - } else { - printk(KERN_INFO DRV_NAME - ": %s: Unable to set %.*s as primary slave as it is not a slave.\n", - bond->dev->name, (int)strlen(buf) - 1, buf); - } - } -out: - write_unlock_bh(&bond->lock); - return count; + return sprintf(buf, "%s %d\n", + val->string, bond->params.primary_reselect); } -static CLASS_DEVICE_ATTR(primary, S_IRUGO | S_IWUSR, bonding_show_primary, bonding_store_primary); +static DEVICE_ATTR(primary_reselect, S_IRUGO | S_IWUSR, + bonding_show_primary_reselect, bonding_sysfs_store_option); -/* - * Show and set the use_carrier flag. - */ -static ssize_t bonding_show_carrier(struct class_device *cd, char *buf) +/* Show the use_carrier flag. */ +static ssize_t bonding_show_carrier(struct device *d, + struct device_attribute *attr, + char *buf) { - struct bonding *bond = to_bond(cd); + struct bonding *bond = to_bond(d); - return sprintf(buf, "%d\n", bond->params.use_carrier) + 1; + return sprintf(buf, "%d\n", bond->params.use_carrier); } +static DEVICE_ATTR(use_carrier, S_IRUGO | S_IWUSR, + bonding_show_carrier, bonding_sysfs_store_option); -static ssize_t bonding_store_carrier(struct class_device *cd, const char *buf, size_t count) + +/* Show currently active_slave. */ +static ssize_t bonding_show_active_slave(struct device *d, + struct device_attribute *attr, + char *buf) { - int new_value, ret = count; - struct bonding *bond = to_bond(cd); + struct bonding *bond = to_bond(d); + struct net_device *slave_dev; + int count = 0; + rcu_read_lock(); + slave_dev = bond_option_active_slave_get_rcu(bond); + if (slave_dev) + count = sprintf(buf, "%s\n", slave_dev->name); + rcu_read_unlock(); - if (sscanf(buf, "%d", &new_value) != 1) { - printk(KERN_ERR DRV_NAME - ": %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; - printk(KERN_INFO DRV_NAME ": %s: Setting use_carrier to %d.\n", - bond->dev->name, new_value); - } else { - printk(KERN_INFO DRV_NAME - ": %s: Ignoring invalid use_carrier value %d.\n", - bond->dev->name, new_value); - } -out: return count; } -static CLASS_DEVICE_ATTR(use_carrier, S_IRUGO | S_IWUSR, bonding_show_carrier, bonding_store_carrier); +static DEVICE_ATTR(active_slave, S_IRUGO | S_IWUSR, + bonding_show_active_slave, bonding_sysfs_store_option); - -/* - * Show and set currently active_slave. - */ -static ssize_t bonding_show_active_slave(struct class_device *cd, char *buf) +/* 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(cd); - int count; - + struct bonding *bond = to_bond(d); - 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) + 1; - else - count = sprintf(buf, "\n") + 1; - return count; + return sprintf(buf, "%s\n", bond->curr_active_slave ? "up" : "down"); } +static DEVICE_ATTR(mii_status, S_IRUGO, bonding_show_mii_status, NULL); -static ssize_t bonding_store_active_slave(struct class_device *cd, const char *buf, size_t count) +/* Show current 802.3ad aggregator ID. */ +static ssize_t bonding_show_ad_aggregator(struct device *d, + struct device_attribute *attr, + char *buf) { - int i; - struct slave *slave; - struct slave *old_active = NULL; - struct slave *new_active = NULL; - struct bonding *bond = to_bond(cd); - - write_lock_bh(&bond->lock); - if (!USES_PRIMARY(bond->params.mode)) { - printk(KERN_INFO DRV_NAME - ": %s: Unable to change active slave; %s is in mode %d\n", - bond->dev->name, bond->dev->name, bond->params.mode); - } else { - bond_for_each_slave(bond, slave, i) { - if (strnicmp - (slave->dev->name, buf, - strlen(slave->dev->name)) == 0) { - old_active = bond->curr_active_slave; - new_active = slave; - if (new_active && (new_active == old_active)) { - /* do nothing */ - printk(KERN_INFO DRV_NAME - ": %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)) { - printk(KERN_INFO DRV_NAME - ": %s: Setting %s as active slave.\n", - bond->dev->name, slave->dev->name); - bond_change_active_slave(bond, new_active); - } - else { - printk(KERN_INFO DRV_NAME - ": %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; - } - } - } - - /* if we got here, then we didn't match the name of any slave */ + int count = 0; + struct bonding *bond = to_bond(d); - if (strlen(buf) == 0 || buf[0] == '\n') { - printk(KERN_INFO DRV_NAME - ": %s: Setting active slave to None.\n", - bond->dev->name); - bond->primary_slave = 0; - bond_select_active_slave(bond); - } else { - printk(KERN_INFO DRV_NAME - ": %s: Unable to set %.*s as active slave as it is not a slave.\n", - bond->dev->name, (int)strlen(buf) - 1, buf); - } + if (BOND_MODE(bond) == 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); } -out: - write_unlock_bh(&bond->lock); - return count; + return count; } -static CLASS_DEVICE_ATTR(active_slave, S_IRUGO | S_IWUSR, bonding_show_active_slave, bonding_store_active_slave); +static DEVICE_ATTR(ad_aggregator, S_IRUGO, bonding_show_ad_aggregator, NULL); -/* - * Show link status of the bond interface. - */ -static ssize_t bonding_show_mii_status(struct class_device *cd, char *buf) +/* Show number of active 802.3ad ports. */ +static ssize_t bonding_show_ad_num_ports(struct device *d, + struct device_attribute *attr, + char *buf) { - struct slave *curr; - struct bonding *bond = to_bond(cd); + int count = 0; + struct bonding *bond = to_bond(d); - read_lock(&bond->curr_slave_lock); - curr = bond->curr_active_slave; - read_unlock(&bond->curr_slave_lock); + if (BOND_MODE(bond) == 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 sprintf(buf, "%s\n", (curr) ? "up" : "down") + 1; + return count; } -static CLASS_DEVICE_ATTR(mii_status, S_IRUGO, bonding_show_mii_status, NULL); +static DEVICE_ATTR(ad_num_ports, S_IRUGO, bonding_show_ad_num_ports, NULL); -/* - * Show current 802.3ad aggregator ID. - */ -static ssize_t bonding_show_ad_aggregator(struct class_device *cd, char *buf) +/* 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(cd); + struct bonding *bond = to_bond(d); - if (bond->params.mode == BOND_MODE_8023AD) { + if (BOND_MODE(bond) == 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) + 1; + count = sprintf(buf, "%d\n", + bond_3ad_get_active_agg_info(bond, &ad_info) + ? 0 : ad_info.actor_key); } - else - count = sprintf(buf, "\n") + 1; return count; } -static CLASS_DEVICE_ATTR(ad_aggregator, S_IRUGO, bonding_show_ad_aggregator, NULL); +static DEVICE_ATTR(ad_actor_key, S_IRUGO, bonding_show_ad_actor_key, NULL); -/* - * Show number of active 802.3ad ports. - */ -static ssize_t bonding_show_ad_num_ports(struct class_device *cd, char *buf) +/* 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(cd); + struct bonding *bond = to_bond(d); - if (bond->params.mode == BOND_MODE_8023AD) { + if (BOND_MODE(bond) == 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) + 1; + count = sprintf(buf, "%d\n", + bond_3ad_get_active_agg_info(bond, &ad_info) + ? 0 : ad_info.partner_key); } - else - count = sprintf(buf, "\n") + 1; return count; } -static CLASS_DEVICE_ATTR(ad_num_ports, S_IRUGO, bonding_show_ad_num_ports, NULL); +static DEVICE_ATTR(ad_partner_key, S_IRUGO, bonding_show_ad_partner_key, NULL); -/* - * Show current 802.3ad actor key. - */ -static ssize_t bonding_show_ad_actor_key(struct class_device *cd, char *buf) +/* 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(cd); + struct bonding *bond = to_bond(d); - if (bond->params.mode == BOND_MODE_8023AD) { + if (BOND_MODE(bond) == 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) + 1; + if (!bond_3ad_get_active_agg_info(bond, &ad_info)) + count = sprintf(buf, "%pM\n", ad_info.partner_system); } - else - count = sprintf(buf, "\n") + 1; return count; } -static CLASS_DEVICE_ATTR(ad_actor_key, S_IRUGO, bonding_show_ad_actor_key, NULL); +static DEVICE_ATTR(ad_partner_mac, S_IRUGO, bonding_show_ad_partner_mac, NULL); - -/* - * Show current 802.3ad partner key. - */ -static ssize_t bonding_show_ad_partner_key(struct class_device *cd, char *buf) +/* 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) { - int count = 0; - struct bonding *bond = to_bond(cd); + struct bonding *bond = to_bond(d); + struct list_head *iter; + struct slave *slave; + int res = 0; - 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) + 1; + if (!rtnl_trylock()) + return restart_syscall(); + + bond_for_each_slave(bond, slave, iter) { + 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); } - else - count = sprintf(buf, "\n") + 1; + if (res) + buf[res-1] = '\n'; /* eat the leftover space */ - return count; + rtnl_unlock(); + + return res; } -static CLASS_DEVICE_ATTR(ad_partner_key, S_IRUGO, bonding_show_ad_partner_key, NULL); +static DEVICE_ATTR(queue_id, S_IRUGO | S_IWUSR, bonding_show_queue_id, + bonding_sysfs_store_option); -/* - * Show current 802.3ad partner mac. - */ -static ssize_t bonding_show_ad_partner_mac(struct class_device *cd, char *buf) +/* Show the all_slaves_active flag. */ +static ssize_t bonding_show_slaves_active(struct device *d, + struct device_attribute *attr, + char *buf) { - int count = 0; - struct bonding *bond = to_bond(cd); + 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,"%02x:%02x:%02x:%02x:%02x:%02x\n", - ad_info.partner_system[0], - ad_info.partner_system[1], - ad_info.partner_system[2], - ad_info.partner_system[3], - ad_info.partner_system[4], - ad_info.partner_system[5]) + 1; - } - } - else - count = sprintf(buf, "\n") + 1; + return sprintf(buf, "%d\n", bond->params.all_slaves_active); +} +static DEVICE_ATTR(all_slaves_active, S_IRUGO | S_IWUSR, + bonding_show_slaves_active, bonding_sysfs_store_option); - return count; +/* Show 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 CLASS_DEVICE_ATTR(ad_partner_mac, S_IRUGO, bonding_show_ad_partner_mac, NULL); +static DEVICE_ATTR(resend_igmp, S_IRUGO | S_IWUSR, + bonding_show_resend_igmp, bonding_sysfs_store_option); +static ssize_t bonding_show_lp_interval(struct device *d, + struct device_attribute *attr, + char *buf) +{ + struct bonding *bond = to_bond(d); + + return sprintf(buf, "%d\n", bond->params.lp_interval); +} +static DEVICE_ATTR(lp_interval, S_IRUGO | S_IWUSR, + bonding_show_lp_interval, bonding_sysfs_store_option); + +static ssize_t bonding_show_tlb_dynamic_lb(struct device *d, + struct device_attribute *attr, + char *buf) +{ + struct bonding *bond = to_bond(d); + return sprintf(buf, "%d\n", bond->params.tlb_dynamic_lb); +} +static DEVICE_ATTR(tlb_dynamic_lb, S_IRUGO | S_IWUSR, + bonding_show_tlb_dynamic_lb, bonding_sysfs_store_option); + +static ssize_t bonding_show_packets_per_slave(struct device *d, + struct device_attribute *attr, + char *buf) +{ + struct bonding *bond = to_bond(d); + unsigned int packets_per_slave = bond->params.packets_per_slave; + + return sprintf(buf, "%u\n", packets_per_slave); +} +static DEVICE_ATTR(packets_per_slave, S_IRUGO | S_IWUSR, + bonding_show_packets_per_slave, bonding_sysfs_store_option); static struct attribute *per_bond_attrs[] = { - &class_device_attr_slaves.attr, - &class_device_attr_mode.attr, - &class_device_attr_arp_interval.attr, - &class_device_attr_arp_ip_target.attr, - &class_device_attr_downdelay.attr, - &class_device_attr_updelay.attr, - &class_device_attr_lacp_rate.attr, - &class_device_attr_xmit_hash_policy.attr, - &class_device_attr_miimon.attr, - &class_device_attr_primary.attr, - &class_device_attr_use_carrier.attr, - &class_device_attr_active_slave.attr, - &class_device_attr_mii_status.attr, - &class_device_attr_ad_aggregator.attr, - &class_device_attr_ad_num_ports.attr, - &class_device_attr_ad_actor_key.attr, - &class_device_attr_ad_partner_key.attr, - &class_device_attr_ad_partner_mac.attr, + &dev_attr_slaves.attr, + &dev_attr_mode.attr, + &dev_attr_fail_over_mac.attr, + &dev_attr_arp_validate.attr, + &dev_attr_arp_all_targets.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, + &dev_attr_lp_interval.attr, + &dev_attr_packets_per_slave.attr, + &dev_attr_tlb_dynamic_lb.attr, NULL, }; @@ -1292,67 +729,52 @@ static struct attribute_group bonding_group = { .attrs = per_bond_attrs, }; -/* - * Initialize sysfs. This sets up the bonding_masters file in +/* Initialize sysfs. This sets up the bonding_masters file in * /sys/class/net. */ -int bond_create_sysfs(void) -{ - int ret = 0; - struct bonding *firstbond; - - init_rwsem(&bonding_rwsem); - - /* get the netdev class pointer */ - firstbond = container_of(bond_dev_list.next, struct bonding, bond_list); - if (!firstbond) - return -ENODEV; - - netdev_class = firstbond->dev->class_dev.class; - if (!netdev_class) - return -ENODEV; - - ret = class_create_file(netdev_class, &class_attr_bonding_masters); +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_ns(&bn->class_attr_bonding_masters, + bn->net); + /* 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\n", + class_attr_bonding_masters.attr.name); + ret = 0; + } return ret; } -/* - * Remove /sys/class/net/bonding_masters. - */ -void bond_destroy_sysfs(void) +/* Remove /sys/class/net/bonding_masters. */ +void bond_destroy_sysfs(struct bond_net *bn) { - if (netdev_class) - class_remove_file(netdev_class, &class_attr_bonding_masters); + netdev_class_remove_file_ns(&bn->class_attr_bonding_masters, bn->net); } -/* - * Initialize sysfs for each bond. This sets up and registers +/* Initialize sysfs for each bond. This sets up and registers * the 'bondctl' directory for each individual bond under /sys/class/net. */ -int bond_create_sysfs_entry(struct bonding *bond) -{ - struct net_device *dev = bond->dev; - int err; - - err = sysfs_create_group(&(dev->class_dev.kobj), &bonding_group); - if (err) { - printk(KERN_EMERG "eek! didn't create group!\n"); - } - - if (expected_refcount < 1) - expected_refcount = atomic_read(&bond->dev->class_dev.kobj.kref.refcount); - - return err; -} -/* - * Remove sysfs entries for each bond. - */ -void bond_destroy_sysfs_entry(struct bonding *bond) +void bond_prepare_sysfs_group(struct bonding *bond) { - struct net_device *dev = bond->dev; - - sysfs_remove_group(&(dev->class_dev.kobj), &bonding_group); + bond->dev->sysfs_groups[0] = &bonding_group; } diff --git a/drivers/net/bonding/bond_sysfs_slave.c b/drivers/net/bonding/bond_sysfs_slave.c new file mode 100644 index 00000000000..198677f58ce --- /dev/null +++ b/drivers/net/bonding/bond_sysfs_slave.c @@ -0,0 +1,144 @@ +/* Sysfs attributes of bond slaves + * + * Copyright (c) 2014 Scott Feldman <sfeldma@cumulusnetworks.com> + * + * This program is free software; you can redistribute it and/or + * modify it under the terms of the GNU General Public License + * as published by the Free Software Foundation; either version + * 2 of the License, or (at your option) any later version. + */ + +#include <linux/capability.h> +#include <linux/kernel.h> +#include <linux/netdevice.h> + +#include "bonding.h" + +struct slave_attribute { + struct attribute attr; + ssize_t (*show)(struct slave *, char *); +}; + +#define SLAVE_ATTR(_name, _mode, _show) \ +const struct slave_attribute slave_attr_##_name = { \ + .attr = {.name = __stringify(_name), \ + .mode = _mode }, \ + .show = _show, \ +}; +#define SLAVE_ATTR_RO(_name) \ + SLAVE_ATTR(_name, S_IRUGO, _name##_show) + +static ssize_t state_show(struct slave *slave, char *buf) +{ + switch (bond_slave_state(slave)) { + case BOND_STATE_ACTIVE: + return sprintf(buf, "active\n"); + case BOND_STATE_BACKUP: + return sprintf(buf, "backup\n"); + default: + return sprintf(buf, "UNKONWN\n"); + } +} +static SLAVE_ATTR_RO(state); + +static ssize_t mii_status_show(struct slave *slave, char *buf) +{ + return sprintf(buf, "%s\n", bond_slave_link_status(slave->link)); +} +static SLAVE_ATTR_RO(mii_status); + +static ssize_t link_failure_count_show(struct slave *slave, char *buf) +{ + return sprintf(buf, "%d\n", slave->link_failure_count); +} +static SLAVE_ATTR_RO(link_failure_count); + +static ssize_t perm_hwaddr_show(struct slave *slave, char *buf) +{ + return sprintf(buf, "%pM\n", slave->perm_hwaddr); +} +static SLAVE_ATTR_RO(perm_hwaddr); + +static ssize_t queue_id_show(struct slave *slave, char *buf) +{ + return sprintf(buf, "%d\n", slave->queue_id); +} +static SLAVE_ATTR_RO(queue_id); + +static ssize_t ad_aggregator_id_show(struct slave *slave, char *buf) +{ + const struct aggregator *agg; + + if (BOND_MODE(slave->bond) == BOND_MODE_8023AD) { + agg = SLAVE_AD_INFO(slave)->port.aggregator; + if (agg) + return sprintf(buf, "%d\n", + agg->aggregator_identifier); + } + + return sprintf(buf, "N/A\n"); +} +static SLAVE_ATTR_RO(ad_aggregator_id); + +static const struct slave_attribute *slave_attrs[] = { + &slave_attr_state, + &slave_attr_mii_status, + &slave_attr_link_failure_count, + &slave_attr_perm_hwaddr, + &slave_attr_queue_id, + &slave_attr_ad_aggregator_id, + NULL +}; + +#define to_slave_attr(_at) container_of(_at, struct slave_attribute, attr) +#define to_slave(obj) container_of(obj, struct slave, kobj) + +static ssize_t slave_show(struct kobject *kobj, + struct attribute *attr, char *buf) +{ + struct slave_attribute *slave_attr = to_slave_attr(attr); + struct slave *slave = to_slave(kobj); + + return slave_attr->show(slave, buf); +} + +static const struct sysfs_ops slave_sysfs_ops = { + .show = slave_show, +}; + +static struct kobj_type slave_ktype = { +#ifdef CONFIG_SYSFS + .sysfs_ops = &slave_sysfs_ops, +#endif +}; + +int bond_sysfs_slave_add(struct slave *slave) +{ + const struct slave_attribute **a; + int err; + + err = kobject_init_and_add(&slave->kobj, &slave_ktype, + &(slave->dev->dev.kobj), "bonding_slave"); + if (err) + return err; + + for (a = slave_attrs; *a; ++a) { + err = sysfs_create_file(&slave->kobj, &((*a)->attr)); + if (err) { + kobject_del(&slave->kobj); + return err; + } + } + + return 0; +} + +void bond_sysfs_slave_del(struct slave *slave) +{ + const struct slave_attribute **a; + + for (a = slave_attrs; *a; ++a) + sysfs_remove_file(&slave->kobj, &((*a)->attr)); + + kobject_del(&slave->kobj); +} diff --git a/drivers/net/bonding/bonding.h b/drivers/net/bonding/bonding.h index 3dd78d048c3..0b4d9cde0b0 100644 --- a/drivers/net/bonding/bonding.h +++ b/drivers/net/bonding/bonding.h @@ -18,54 +18,28 @@ #include <linux/timer.h> #include <linux/proc_fs.h> #include <linux/if_bonding.h> -#include <linux/kobject.h> +#include <linux/cpumask.h> +#include <linux/in6.h> +#include <linux/netpoll.h> +#include <linux/inetdevice.h> +#include <linux/etherdevice.h> +#include <linux/reciprocal_div.h> + #include "bond_3ad.h" #include "bond_alb.h" +#include "bond_options.h" -#define DRV_VERSION "3.0.1" -#define DRV_RELDATE "January 9, 2006" +#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_MAX_ARP_TARGETS 16 - -#ifdef BONDING_DEBUG -#define dprintk(fmt, args...) \ - printk(KERN_DEBUG \ - DRV_NAME ": %s() %d: " fmt, __FUNCTION__, __LINE__ , ## args ) -#else -#define dprintk(fmt, args...) -#endif /* BONDING_DEBUG */ - -#define IS_UP(dev) \ - ((((dev)->flags & IFF_UP) == IFF_UP) && \ - netif_running(dev) && \ - netif_carrier_ok(dev)) - -/* - * Checks whether bond is ready for transmit. - * - * Caller must hold bond->lock - */ -#define BOND_IS_OK(bond) \ - (((bond)->dev->flags & IFF_UP) && \ - netif_running((bond)->dev) && \ - ((bond)->slave_cnt > 0)) - -/* - * 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) && \ - ((slave)->state == BOND_STATE_ACTIVE)) +#define bond_version DRV_DESCRIPTION ": v" DRV_VERSION " (" DRV_RELDATE ")\n" +#define BOND_MAX_VLAN_ENCAP 2 +#define BOND_MAX_ARP_TARGETS 16 -#define USES_PRIMARY(mode) \ - (((mode) == BOND_MODE_ACTIVEBACKUP) || \ - ((mode) == BOND_MODE_TLB) || \ - ((mode) == BOND_MODE_ALB)) +#define BOND_DEFAULT_MIIMON 100 /* * Less bad way to call ioctl from within the kernel; this needs to be @@ -80,58 +54,95 @@ 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) +#define BOND_MODE(bond) ((bond)->params.mode) -/** - * 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) +/* slave list primitives */ +#define bond_slave_list(bond) (&(bond)->dev->adj_list.lower) + +#define bond_has_slaves(bond) !list_empty(bond_slave_list(bond)) + +/* IMPORTANT: bond_first/last_slave can return NULL in case of an empty list */ +#define bond_first_slave(bond) \ + (bond_has_slaves(bond) ? \ + netdev_adjacent_get_private(bond_slave_list(bond)->next) : \ + NULL) +#define bond_last_slave(bond) \ + (bond_has_slaves(bond) ? \ + netdev_adjacent_get_private(bond_slave_list(bond)->prev) : \ + NULL) + +/* Caller must have rcu_read_lock */ +#define bond_first_slave_rcu(bond) \ + netdev_lower_get_first_private_rcu(bond->dev) + +#define bond_is_first_slave(bond, pos) (pos == bond_first_slave(bond)) +#define bond_is_last_slave(bond, pos) (pos == bond_last_slave(bond)) /** - * bond_for_each_slave - iterate the slaves list from head - * @bond: the bond holding this list. - * @pos: current slave. - * @cnt: counter for max number of moves + * bond_for_each_slave - iterate over all slaves + * @bond: the bond holding this list + * @pos: current slave + * @iter: list_head * iterator * * Caller must hold bond->lock */ -#define bond_for_each_slave(bond, pos, cnt) \ - bond_for_each_slave_from(bond, pos, cnt, (bond)->first_slave) +#define bond_for_each_slave(bond, pos, iter) \ + netdev_for_each_lower_private((bond)->dev, pos, iter) + +/* Caller must have rcu_read_lock */ +#define bond_for_each_slave_rcu(bond, pos, iter) \ + netdev_for_each_lower_private_rcu((bond)->dev, pos, iter) + +#ifdef CONFIG_NET_POLL_CONTROLLER +extern atomic_t netpoll_block_tx; + +static inline void block_netpoll_tx(void) +{ + atomic_inc(&netpoll_block_tx); +} +static inline void unblock_netpoll_tx(void) +{ + atomic_dec(&netpoll_block_tx); +} + +static inline int is_netpoll_tx_blocked(struct net_device *dev) +{ + if (unlikely(netpoll_tx_running(dev))) + return atomic_read(&netpoll_block_tx); + return 0; +} +#else +#define block_netpoll_tx() +#define unblock_netpoll_tx() +#define is_netpoll_tx_blocked(dev) (0) +#endif struct bond_params { int mode; int xmit_policy; int miimon; + u8 num_peer_notif; int arp_interval; + int arp_validate; + int arp_all_targets; int use_carrier; + int fail_over_mac; int updelay; int downdelay; int lacp_fast; + unsigned int min_links; + int ad_select; char primary[IFNAMSIZ]; - u32 arp_targets[BOND_MAX_ARP_TARGETS]; + int primary_reselect; + __be32 arp_targets[BOND_MAX_ARP_TARGETS]; + int tx_queues; + int all_slaves_active; + int resend_igmp; + int lp_interval; + int packets_per_slave; + int tlb_dynamic_lb; + struct reciprocal_value reciprocal_packets_per_slave; }; struct bond_parm_tbl { @@ -139,30 +150,40 @@ struct bond_parm_tbl { int mode; }; -struct vlan_entry { - struct list_head vlan_list; - u32 vlan_ip; - unsigned short vlan_id; -}; - struct slave { struct net_device *dev; /* first - useful for panic debug */ - struct slave *next; - struct slave *prev; - s16 delay; - u32 jiffies; + struct bonding *bond; /* our master */ + int delay; + /* all three in jiffies */ + unsigned long last_link_up; + unsigned long last_rx; + unsigned long target_last_arp_rx[BOND_MAX_ARP_TARGETS]; s8 link; /* one of BOND_LINK_XXXX */ - s8 state; /* one of BOND_STATE_XXXX */ - u32 original_flags; - u32 link_failure_count; - u16 speed; + s8 new_link; + u8 backup:1, /* indicates backup slave. Value corresponds with + BOND_STATE_ACTIVE and BOND_STATE_BACKUP */ + inactive:1, /* indicates inactive slave */ + should_notify:1; /* indicateds whether the state changed */ u8 duplex; + u32 original_mtu; + u32 link_failure_count; + u32 speed; + u16 queue_id; u8 perm_hwaddr[ETH_ALEN]; - struct ad_slave_info ad_info; /* HUGE - better to dynamically alloc */ + struct ad_slave_info *ad_info; struct tlb_slave_info tlb_info; +#ifdef CONFIG_NET_POLL_CONTROLLER + struct netpoll *np; +#endif + struct kobject kobj; }; /* + * 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. @@ -173,31 +194,47 @@ struct slave { */ 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)(const struct sk_buff *, struct bonding *, + struct slave *); rwlock_t lock; rwlock_t curr_slave_lock; - struct timer_list mii_timer; - struct timer_list arp_timer; - s8 kill_timers; - struct net_device_stats stats; + u8 send_peer_notif; + u8 igmp_retrans; #ifdef CONFIG_PROC_FS struct proc_dir_entry *proc_entry; char proc_file_name[IFNAMSIZ]; #endif /* CONFIG_PROC_FS */ struct list_head bond_list; - struct dev_mc_list *mc_list; - int (*xmit_hash_policy)(struct sk_buff *, struct net_device *, int); - u32 master_ip; - u16 flags; + u32 rr_tx_counter; struct ad_bond_info ad_info; struct alb_bond_info alb_info; struct bond_params params; - struct list_head vlan_list; - struct vlan_group *vlgrp; + struct 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 support via debugfs */ + struct dentry *debug_dir; +#endif /* CONFIG_DEBUG_FS */ +}; + +#define bond_slave_get_rcu(dev) \ + ((struct slave *) rcu_dereference(dev->rx_handler_data)) + +#define bond_slave_get_rtnl(dev) \ + ((struct slave *) rtnl_dereference(dev->rx_handler_data)) + +struct bond_vlan_tag { + __be16 vlan_proto; + unsigned short vlan_id; }; /** @@ -205,62 +242,382 @@ struct bonding { * * Caller must hold bond lock for read */ -static inline struct slave *bond_get_slave_by_dev(struct bonding *bond, struct net_device *slave_dev) +static inline struct slave *bond_get_slave_by_dev(struct bonding *bond, + struct net_device *slave_dev) { - struct slave *slave = NULL; - int i; + return netdev_lower_dev_get_private(bond->dev, slave_dev); +} - bond_for_each_slave(bond, slave, i) { - if (slave->dev == slave_dev) { - break; - } +static inline struct bonding *bond_get_bond_by_slave(struct slave *slave) +{ + return slave->bond; +} + +static inline bool bond_should_override_tx_queue(struct bonding *bond) +{ + return BOND_MODE(bond) == BOND_MODE_ACTIVEBACKUP || + BOND_MODE(bond) == BOND_MODE_ROUNDROBIN; +} + +static inline bool bond_is_lb(const struct bonding *bond) +{ + return BOND_MODE(bond) == BOND_MODE_TLB || + BOND_MODE(bond) == BOND_MODE_ALB; +} + +static inline bool bond_mode_uses_arp(int mode) +{ + return mode != BOND_MODE_8023AD && mode != BOND_MODE_TLB && + mode != BOND_MODE_ALB; +} + +static inline bool bond_mode_uses_primary(int mode) +{ + return mode == BOND_MODE_ACTIVEBACKUP || mode == BOND_MODE_TLB || + mode == BOND_MODE_ALB; +} + +static inline bool bond_uses_primary(struct bonding *bond) +{ + return bond_mode_uses_primary(BOND_MODE(bond)); +} + +static inline bool bond_slave_is_up(struct slave *slave) +{ + return netif_running(slave->dev) && netif_carrier_ok(slave->dev); +} + +static inline void bond_set_active_slave(struct slave *slave) +{ + if (slave->backup) { + slave->backup = 0; + rtmsg_ifinfo(RTM_NEWLINK, slave->dev, 0, GFP_ATOMIC); } +} - return slave; +static inline void bond_set_backup_slave(struct slave *slave) +{ + if (!slave->backup) { + slave->backup = 1; + rtmsg_ifinfo(RTM_NEWLINK, slave->dev, 0, GFP_ATOMIC); + } } -static inline struct bonding *bond_get_bond_by_slave(struct slave *slave) +static inline void bond_set_slave_state(struct slave *slave, + int slave_state, bool notify) { - if (!slave || !slave->dev->master) { - return NULL; + if (slave->backup == slave_state) + return; + + slave->backup = slave_state; + if (notify) { + rtmsg_ifinfo(RTM_NEWLINK, slave->dev, 0, GFP_ATOMIC); + slave->should_notify = 0; + } else { + if (slave->should_notify) + slave->should_notify = 0; + else + slave->should_notify = 1; } +} - return (struct bonding *)slave->dev->master->priv; +static inline void bond_slave_state_change(struct bonding *bond) +{ + struct list_head *iter; + struct slave *tmp; + + bond_for_each_slave(bond, tmp, iter) { + if (tmp->link == BOND_LINK_UP) + bond_set_active_slave(tmp); + else if (tmp->link == BOND_LINK_DOWN) + bond_set_backup_slave(tmp); + } +} + +static inline void bond_slave_state_notify(struct bonding *bond) +{ + struct list_head *iter; + struct slave *tmp; + + bond_for_each_slave(bond, tmp, iter) { + if (tmp->should_notify) { + rtmsg_ifinfo(RTM_NEWLINK, tmp->dev, 0, GFP_ATOMIC); + tmp->should_notify = 0; + } + } +} + +static inline int bond_slave_state(struct slave *slave) +{ + return slave->backup; } -static inline void bond_set_slave_inactive_flags(struct slave *slave) +static inline bool bond_is_active_slave(struct slave *slave) { - slave->state = BOND_STATE_BACKUP; - slave->dev->flags |= IFF_NOARP; + return !bond_slave_state(slave); } -static inline void bond_set_slave_active_flags(struct slave *slave) +static inline bool bond_slave_can_tx(struct slave *slave) { - slave->state = BOND_STATE_ACTIVE; - slave->dev->flags &= ~IFF_NOARP; + return bond_slave_is_up(slave) && slave->link == BOND_LINK_UP && + bond_is_active_slave(slave); } -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(char *name, struct bond_params *params, struct bonding **newbond); -void bond_deinit(struct net_device *bond_dev); -int bond_create_sysfs(void); -void bond_destroy_sysfs(void); -void bond_destroy_sysfs_entry(struct bonding *bond); -int bond_create_sysfs_entry(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); +#define BOND_PRI_RESELECT_ALWAYS 0 +#define BOND_PRI_RESELECT_BETTER 1 +#define BOND_PRI_RESELECT_FAILURE 2 + +#define BOND_FOM_NONE 0 +#define BOND_FOM_ACTIVE 1 +#define BOND_FOM_FOLLOW 2 + +#define BOND_ARP_TARGETS_ANY 0 +#define BOND_ARP_TARGETS_ALL 1 + +#define BOND_ARP_VALIDATE_NONE 0 +#define BOND_ARP_VALIDATE_ACTIVE (1 << BOND_STATE_ACTIVE) +#define BOND_ARP_VALIDATE_BACKUP (1 << BOND_STATE_BACKUP) +#define BOND_ARP_VALIDATE_ALL (BOND_ARP_VALIDATE_ACTIVE | \ + BOND_ARP_VALIDATE_BACKUP) +#define BOND_ARP_FILTER (BOND_ARP_VALIDATE_ALL + 1) +#define BOND_ARP_FILTER_ACTIVE (BOND_ARP_VALIDATE_ACTIVE | \ + BOND_ARP_FILTER) +#define BOND_ARP_FILTER_BACKUP (BOND_ARP_VALIDATE_BACKUP | \ + BOND_ARP_FILTER) + +#define BOND_SLAVE_NOTIFY_NOW true +#define BOND_SLAVE_NOTIFY_LATER false + +static inline int slave_do_arp_validate(struct bonding *bond, + struct slave *slave) +{ + return bond->params.arp_validate & (1 << bond_slave_state(slave)); +} + +static inline int slave_do_arp_validate_only(struct bonding *bond) +{ + return bond->params.arp_validate & BOND_ARP_FILTER; +} + +static inline int bond_is_ip_target_ok(__be32 addr) +{ + return !ipv4_is_lbcast(addr) && !ipv4_is_zeronet(addr); +} + +/* Get the oldest arp which we've received on this slave for bond's + * arp_targets. + */ +static inline unsigned long slave_oldest_target_arp_rx(struct bonding *bond, + struct slave *slave) +{ + int i = 1; + unsigned long ret = slave->target_last_arp_rx[0]; + + for (; (i < BOND_MAX_ARP_TARGETS) && bond->params.arp_targets[i]; i++) + if (time_before(slave->target_last_arp_rx[i], ret)) + ret = slave->target_last_arp_rx[i]; + + return ret; +} + +static inline unsigned long slave_last_rx(struct bonding *bond, + struct slave *slave) +{ + if (bond->params.arp_all_targets == BOND_ARP_TARGETS_ALL) + return slave_oldest_target_arp_rx(bond, slave); + + return slave->last_rx; +} + +#ifdef CONFIG_NET_POLL_CONTROLLER +static inline void bond_netpoll_send_skb(const struct slave *slave, + struct sk_buff *skb) +{ + struct netpoll *np = slave->np; + + if (np) + netpoll_send_skb(np, skb); +} +#else +static inline void bond_netpoll_send_skb(const struct slave *slave, + struct sk_buff *skb) +{ +} +#endif + +static inline void bond_set_slave_inactive_flags(struct slave *slave, + bool notify) +{ + if (!bond_is_lb(slave->bond)) + bond_set_slave_state(slave, BOND_STATE_BACKUP, notify); + if (!slave->bond->params.all_slaves_active) + slave->inactive = 1; +} + +static inline void bond_set_slave_active_flags(struct slave *slave, + bool notify) +{ + bond_set_slave_state(slave, BOND_STATE_ACTIVE, notify); + slave->inactive = 0; +} + +static inline bool bond_is_slave_inactive(struct slave *slave) +{ + return slave->inactive; +} + +static inline __be32 bond_confirm_addr(struct net_device *dev, __be32 dst, __be32 local) +{ + struct in_device *in_dev; + __be32 addr = 0; + + rcu_read_lock(); + in_dev = __in_dev_get_rcu(dev); + + if (in_dev) + addr = inet_confirm_addr(dev_net(dev), in_dev, dst, local, + RT_SCOPE_HOST); + rcu_read_unlock(); + return addr; +} + +struct bond_net { + struct net *net; /* Associated network namespace */ + struct list_head dev_list; +#ifdef CONFIG_PROC_FS + struct proc_dir_entry *proc_dir; +#endif + struct class_attribute class_attr_bonding_masters; +}; + +int bond_arp_rcv(const struct sk_buff *skb, struct bonding *bond, struct slave *slave); +void bond_dev_queue_xmit(struct bonding *bond, struct sk_buff *skb, struct net_device *slave_dev); +int bond_create(struct net *net, const char *name); +int bond_create_sysfs(struct bond_net *net); +void bond_destroy_sysfs(struct bond_net *net); +void bond_prepare_sysfs_group(struct bonding *bond); +int bond_sysfs_slave_add(struct slave *slave); +void bond_sysfs_slave_del(struct slave *slave); int bond_enslave(struct net_device *bond_dev, struct net_device *slave_dev); int bond_release(struct net_device *bond_dev, struct net_device *slave_dev); -int bond_sethwaddr(struct net_device *bond_dev, struct net_device *slave_dev); -void bond_mii_monitor(struct net_device *bond_dev); -void bond_loadbalance_arp_mon(struct net_device *bond_dev); -void bond_activebackup_arp_mon(struct net_device *bond_dev); -void bond_set_mode_ops(struct bonding *bond, int mode); -int bond_parse_parm(char *mode_arg, struct bond_parm_tbl *tbl); -const char *bond_mode_name(int mode); +u32 bond_xmit_hash(struct bonding *bond, struct sk_buff *skb); void bond_select_active_slave(struct bonding *bond); void bond_change_active_slave(struct bonding *bond, struct slave *new_active); +void bond_create_debugfs(void); +void bond_destroy_debugfs(void); +void bond_debug_register(struct bonding *bond); +void bond_debug_unregister(struct bonding *bond); +void bond_debug_reregister(struct bonding *bond); +const char *bond_mode_name(int mode); +void bond_setup(struct net_device *bond_dev); +unsigned int bond_get_num_tx_queues(void); +int bond_netlink_init(void); +void bond_netlink_fini(void); +struct net_device *bond_option_active_slave_get_rcu(struct bonding *bond); +struct net_device *bond_option_active_slave_get(struct bonding *bond); +const char *bond_slave_link_status(s8 link); +bool bond_verify_device_path(struct net_device *start_dev, + struct net_device *end_dev, + struct bond_vlan_tag *tags); -#endif /* _LINUX_BONDING_H */ +#ifdef CONFIG_PROC_FS +void bond_create_proc_entry(struct bonding *bond); +void bond_remove_proc_entry(struct bonding *bond); +void bond_create_proc_dir(struct bond_net *bn); +void bond_destroy_proc_dir(struct bond_net *bn); +#else +static inline void bond_create_proc_entry(struct bonding *bond) +{ +} + +static inline void bond_remove_proc_entry(struct bonding *bond) +{ +} + +static inline void bond_create_proc_dir(struct bond_net *bn) +{ +} + +static inline void bond_destroy_proc_dir(struct bond_net *bn) +{ +} +#endif + +static inline struct slave *bond_slave_has_mac(struct bonding *bond, + const u8 *mac) +{ + struct list_head *iter; + struct slave *tmp; + + bond_for_each_slave(bond, tmp, iter) + if (ether_addr_equal_64bits(mac, tmp->dev->dev_addr)) + return tmp; + + return NULL; +} +/* Caller must hold rcu_read_lock() for read */ +static inline struct slave *bond_slave_has_mac_rcu(struct bonding *bond, + const u8 *mac) +{ + struct list_head *iter; + struct slave *tmp; + + bond_for_each_slave_rcu(bond, tmp, iter) + if (ether_addr_equal_64bits(mac, tmp->dev->dev_addr)) + return tmp; + + return NULL; +} + +/* Caller must hold rcu_read_lock() for read */ +static inline bool bond_slave_has_mac_rx(struct bonding *bond, const u8 *mac) +{ + struct list_head *iter; + struct slave *tmp; + struct netdev_hw_addr *ha; + + bond_for_each_slave_rcu(bond, tmp, iter) + if (ether_addr_equal_64bits(mac, tmp->dev->dev_addr)) + return true; + + if (netdev_uc_empty(bond->dev)) + return false; + + netdev_for_each_uc_addr(ha, bond->dev) + if (ether_addr_equal_64bits(mac, ha->addr)) + return true; + + return false; +} + +/* Check if the ip is present in arp ip list, or first free slot if ip == 0 + * Returns -1 if not found, index if found + */ +static inline int bond_get_targets_ip(__be32 *targets, __be32 ip) +{ + int i; + + for (i = 0; i < BOND_MAX_ARP_TARGETS; i++) + if (targets[i] == ip) + return i; + else if (targets[i] == 0) + break; + + return -1; +} + +/* exported from bond_main.c */ +extern int bond_net_id; +extern const struct bond_parm_tbl bond_lacp_tbl[]; +extern const struct bond_parm_tbl xmit_hashtype_tbl[]; +extern const struct bond_parm_tbl arp_validate_tbl[]; +extern const struct bond_parm_tbl arp_all_targets_tbl[]; +extern const struct bond_parm_tbl fail_over_mac_tbl[]; +extern const struct bond_parm_tbl pri_reselect_tbl[]; +extern struct bond_parm_tbl ad_select_tbl[]; + +/* exported from bond_netlink.c */ +extern struct rtnl_link_ops bond_link_ops; + +#endif /* _LINUX_BONDING_H */ |