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 | 47 | ||||
-rw-r--r-- | drivers/net/bonding/bond_3ad.h | 3 | ||||
-rw-r--r-- | drivers/net/bonding/bond_alb.c | 42 | ||||
-rw-r--r-- | drivers/net/bonding/bond_alb.h | 38 | ||||
-rw-r--r-- | drivers/net/bonding/bond_debugfs.c | 146 | ||||
-rw-r--r-- | drivers/net/bonding/bond_ipv6.c | 7 | ||||
-rw-r--r-- | drivers/net/bonding/bond_main.c | 723 | ||||
-rw-r--r-- | drivers/net/bonding/bond_procfs.c | 275 | ||||
-rw-r--r-- | drivers/net/bonding/bond_sysfs.c | 23 | ||||
-rw-r--r-- | drivers/net/bonding/bonding.h | 137 |
11 files changed, 867 insertions, 579 deletions
diff --git a/drivers/net/bonding/Makefile b/drivers/net/bonding/Makefile index 6f9c6faef24c..3c5c014e82b2 100644 --- a/drivers/net/bonding/Makefile +++ b/drivers/net/bonding/Makefile @@ -4,7 +4,10 @@ obj-$(CONFIG_BONDING) += bonding.o -bonding-objs := bond_main.o bond_3ad.o bond_alb.o bond_sysfs.o +bonding-objs := bond_main.o bond_3ad.o bond_alb.o bond_sysfs.o bond_debugfs.o + +proc-$(CONFIG_PROC_FS) += bond_procfs.o +bonding-objs += $(proc-y) ipv6-$(subst m,y,$(CONFIG_IPV6)) += bond_ipv6.o bonding-objs += $(ipv6-y) diff --git a/drivers/net/bonding/bond_3ad.c b/drivers/net/bonding/bond_3ad.c index 881914bc4e9c..494bf960442d 100644 --- a/drivers/net/bonding/bond_3ad.c +++ b/drivers/net/bonding/bond_3ad.c @@ -246,7 +246,7 @@ static inline void __enable_port(struct port *port) */ static inline int __port_is_enabled(struct port *port) { - return port->slave->state == BOND_STATE_ACTIVE; + return bond_is_active_slave(port->slave); } /** @@ -281,23 +281,23 @@ static inline int __check_agg_selection_timer(struct port *port) } /** - * __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_bh(&(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_bh(&(SLAVE_AD_INFO(port->slave).rx_machine_lock)); + spin_unlock_bh(&(SLAVE_AD_INFO(port->slave).state_machine_lock)); } /** @@ -388,14 +388,14 @@ static u8 __get_duplex(struct port *port) } /** - * __initialize_port_locks - initialize a port's RX machine spinlock + * __initialize_port_locks - initialize a port's STATE machine spinlock * @port: the port we're looking at * */ static inline void __initialize_port_locks(struct port *port) { // make sure it isn't called twice - spin_lock_init(&(SLAVE_AD_INFO(port->slave).rx_machine_lock)); + spin_lock_init(&(SLAVE_AD_INFO(port->slave).state_machine_lock)); } //conversions @@ -840,7 +840,7 @@ static int ad_lacpdu_send(struct port *port) lacpdu_header = (struct lacpdu_header *)skb_put(skb, length); memcpy(lacpdu_header->hdr.h_dest, lacpdu_mcast_addr, ETH_ALEN); - /* Note: source addres is set to be the member's PERMANENT address, + /* Note: source address is set to be the member's PERMANENT address, because we use it to identify loopback lacpdus in receive. */ memcpy(lacpdu_header->hdr.h_source, slave->perm_hwaddr, ETH_ALEN); lacpdu_header->hdr.h_proto = PKT_TYPE_LACPDU; @@ -881,7 +881,7 @@ static int ad_marker_send(struct port *port, struct bond_marker *marker) marker_header = (struct bond_marker_header *)skb_put(skb, length); memcpy(marker_header->hdr.h_dest, lacpdu_mcast_addr, ETH_ALEN); - /* Note: source addres is set to be the member's PERMANENT address, + /* Note: source address is set to be the member's PERMANENT address, because we use it to identify loopback MARKERs in receive. */ memcpy(marker_header->hdr.h_source, slave->perm_hwaddr, ETH_ALEN); marker_header->hdr.h_proto = PKT_TYPE_LACPDU; @@ -1025,9 +1025,6 @@ 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 last_state = port->sm_rx_state; @@ -1133,7 +1130,6 @@ static void ad_rx_machine(struct lacpdu *lacpdu, struct port *port) pr_err("%s: An illegal loopback occurred on adapter (%s).\n" "Check the configuration to verify that all adapters are connected to 802.3ad compliant switch ports\n", port->slave->dev->master->name, port->slave->dev->name); - __release_rx_machine_lock(port); return; } __update_selected(lacpdu, port); @@ -1153,7 +1149,6 @@ static void ad_rx_machine(struct lacpdu *lacpdu, struct port *port) break; } } - __release_rx_machine_lock(port); } /** @@ -1916,7 +1911,7 @@ int bond_3ad_bind_slave(struct slave *slave) return -1; } - //check that the slave has not been intialized yet. + //check that the slave has not been initialized yet. if (SLAVE_AD_INFO(slave).port.slave != slave) { // port initialization @@ -2155,6 +2150,12 @@ void bond_3ad_state_machine_handler(struct work_struct *work) 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); @@ -2164,6 +2165,8 @@ void bond_3ad_state_machine_handler(struct work_struct *work) // 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: @@ -2200,7 +2203,10 @@ static void bond_3ad_rx_indication(struct lacpdu *lacpdu, struct slave *slave, u case AD_TYPE_LACPDU: 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: @@ -2470,12 +2476,15 @@ int bond_3ad_lacpdu_recv(struct sk_buff *skb, struct net_device *dev, struct pac if (!(dev->flags & IFF_MASTER)) goto out; + skb = skb_share_check(skb, GFP_ATOMIC); + if (!skb) + goto out; + if (!pskb_may_pull(skb, sizeof(struct lacpdu))) goto out; read_lock(&bond->lock); - slave = bond_get_slave_by_dev((struct bonding *)netdev_priv(dev), - orig_dev); + slave = bond_get_slave_by_dev(netdev_priv(dev), orig_dev); if (!slave) goto out_unlock; diff --git a/drivers/net/bonding/bond_3ad.h b/drivers/net/bonding/bond_3ad.h index 2c46a154f2c6..b28baff70864 100644 --- a/drivers/net/bonding/bond_3ad.h +++ b/drivers/net/bonding/bond_3ad.h @@ -264,7 +264,8 @@ struct ad_bond_info { 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 + spinlock_t state_machine_lock; /* mutex state machines vs. + incoming LACPDU */ u16 id; }; diff --git a/drivers/net/bonding/bond_alb.c b/drivers/net/bonding/bond_alb.c index 26bb118c4533..9bc5de3e04a8 100644 --- a/drivers/net/bonding/bond_alb.c +++ b/drivers/net/bonding/bond_alb.c @@ -44,42 +44,6 @@ #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 #ifndef __long_aligned #define __long_aligned __attribute__((aligned((sizeof(long))))) @@ -362,6 +326,10 @@ static int rlb_arp_recv(struct sk_buff *skb, struct net_device *bond_dev, struct goto out; } + skb = skb_share_check(skb, GFP_ATOMIC); + if (!skb) + goto out; + if (!pskb_may_pull(skb, arp_hdr_len(bond_dev))) goto out; @@ -636,7 +604,7 @@ static struct slave *rlb_choose_channel(struct sk_buff *skb, struct bonding *bon _lock_rx_hashtbl(bond); - hash_index = _simple_hash((u8 *)&arp->ip_dst, sizeof(arp->ip_src)); + hash_index = _simple_hash((u8 *)&arp->ip_dst, sizeof(arp->ip_dst)); client_info = &(bond_info->rx_hashtbl[hash_index]); if (client_info->assigned) { diff --git a/drivers/net/bonding/bond_alb.h b/drivers/net/bonding/bond_alb.h index 50968f8196cf..118c28aa471e 100644 --- a/drivers/net/bonding/bond_alb.h +++ b/drivers/net/bonding/bond_alb.h @@ -31,6 +31,44 @@ struct slave; #define BOND_ALB_INFO(bond) ((bond)->alb_info) #define SLAVE_TLB_INFO(slave) ((slave)->tlb_info) +#define ALB_TIMER_TICKS_PER_SEC 10 /* should be a divisor of HZ */ +#define BOND_TLB_REBALANCE_INTERVAL 10 /* In seconds, periodic re-balancing. + * Used for division - never set + * to zero !!! + */ +#define BOND_ALB_LP_INTERVAL 1 /* In seconds, periodic send of + * learning packets to the switch + */ + +#define BOND_TLB_REBALANCE_TICKS (BOND_TLB_REBALANCE_INTERVAL \ + * ALB_TIMER_TICKS_PER_SEC) + +#define BOND_ALB_LP_TICKS (BOND_ALB_LP_INTERVAL \ + * ALB_TIMER_TICKS_PER_SEC) + +#define TLB_HASH_TABLE_SIZE 256 /* The size of the clients hash table. + * Note that this value MUST NOT be smaller + * because the key hash table is BYTE wide ! + */ + + +#define TLB_NULL_INDEX 0xffffffff +#define MAX_LP_BURST 3 + +/* rlb defs */ +#define RLB_HASH_TABLE_SIZE 256 +#define RLB_NULL_INDEX 0xffffffff +#define RLB_UPDATE_DELAY (2*ALB_TIMER_TICKS_PER_SEC) /* 2 seconds */ +#define RLB_ARP_BURST_SIZE 2 +#define RLB_UPDATE_RETRY 3 /* 3-ticks - must be smaller than the rlb + * rebalance interval (5 min). + */ +/* RLB_PROMISC_TIMEOUT = 10 sec equals the time that the current slave is + * promiscuous after failover + */ +#define RLB_PROMISC_TIMEOUT (10*ALB_TIMER_TICKS_PER_SEC) + + struct tlb_client_info { struct slave *tx_slave; /* A pointer to slave used for transmiting * packets to a Client that the Hash function diff --git a/drivers/net/bonding/bond_debugfs.c b/drivers/net/bonding/bond_debugfs.c new file mode 100644 index 000000000000..3680aa251dea --- /dev/null +++ b/drivers/net/bonding/bond_debugfs.c @@ -0,0 +1,146 @@ +#include <linux/kernel.h> +#include <linux/module.h> +#include <linux/device.h> +#include <linux/netdevice.h> + +#include "bonding.h" +#include "bond_alb.h" + +#ifdef CONFIG_DEBUG_FS + +#include <linux/debugfs.h> +#include <linux/seq_file.h> + +static struct dentry *bonding_debug_root; + +/* + * Show RLB hash table + */ +static int bond_debug_rlb_hash_show(struct seq_file *m, void *v) +{ + struct bonding *bond = m->private; + struct alb_bond_info *bond_info = &(BOND_ALB_INFO(bond)); + struct rlb_client_info *client_info; + u32 hash_index; + + if (bond->params.mode != BOND_MODE_ALB) + return 0; + + seq_printf(m, "SourceIP DestinationIP " + "Destination MAC DEV\n"); + + spin_lock_bh(&(BOND_ALB_INFO(bond).rx_hashtbl_lock)); + + hash_index = bond_info->rx_hashtbl_head; + for (; hash_index != RLB_NULL_INDEX; hash_index = client_info->next) { + client_info = &(bond_info->rx_hashtbl[hash_index]); + seq_printf(m, "%-15pI4 %-15pI4 %-17pM %s\n", + &client_info->ip_src, + &client_info->ip_dst, + &client_info->mac_dst, + client_info->slave->dev->name); + } + + spin_unlock_bh(&(BOND_ALB_INFO(bond).rx_hashtbl_lock)); + + return 0; +} + +static int bond_debug_rlb_hash_open(struct inode *inode, struct file *file) +{ + return single_open(file, bond_debug_rlb_hash_show, inode->i_private); +} + +static const struct file_operations bond_debug_rlb_hash_fops = { + .owner = THIS_MODULE, + .open = bond_debug_rlb_hash_open, + .read = seq_read, + .llseek = seq_lseek, + .release = single_release, +}; + +void bond_debug_register(struct bonding *bond) +{ + if (!bonding_debug_root) + return; + + bond->debug_dir = + debugfs_create_dir(bond->dev->name, bonding_debug_root); + + if (!bond->debug_dir) { + pr_warning("%s: Warning: failed to register to debugfs\n", + bond->dev->name); + return; + } + + debugfs_create_file("rlb_hash_table", 0400, bond->debug_dir, + bond, &bond_debug_rlb_hash_fops); +} + +void bond_debug_unregister(struct bonding *bond) +{ + if (!bonding_debug_root) + return; + + debugfs_remove_recursive(bond->debug_dir); +} + +void bond_debug_reregister(struct bonding *bond) +{ + struct dentry *d; + + if (!bonding_debug_root) + return; + + d = debugfs_rename(bonding_debug_root, bond->debug_dir, + bonding_debug_root, bond->dev->name); + if (d) { + bond->debug_dir = d; + } else { + pr_warning("%s: Warning: failed to reregister, " + "so just unregister old one\n", + bond->dev->name); + bond_debug_unregister(bond); + } +} + +void bond_create_debugfs(void) +{ + bonding_debug_root = debugfs_create_dir("bonding", NULL); + + if (!bonding_debug_root) { + pr_warning("Warning: Cannot create bonding directory" + " in debugfs\n"); + } +} + +void bond_destroy_debugfs(void) +{ + debugfs_remove_recursive(bonding_debug_root); + bonding_debug_root = NULL; +} + + +#else /* !CONFIG_DEBUG_FS */ + +void bond_debug_register(struct bonding *bond) +{ +} + +void bond_debug_unregister(struct bonding *bond) +{ +} + +void bond_debug_reregister(struct bonding *bond) +{ +} + +void bond_create_debugfs(void) +{ +} + +void bond_destroy_debugfs(void) +{ +} + +#endif /* CONFIG_DEBUG_FS */ diff --git a/drivers/net/bonding/bond_ipv6.c b/drivers/net/bonding/bond_ipv6.c index 121b073a6c3f..84fbd4ebd778 100644 --- a/drivers/net/bonding/bond_ipv6.c +++ b/drivers/net/bonding/bond_ipv6.c @@ -88,7 +88,12 @@ static void bond_na_send(struct net_device *slave_dev, } if (vlan_id) { - skb = vlan_put_tag(skb, vlan_id); + /* The Ethernet header is not present yet, so it is + * too early to insert a VLAN tag. Force use of an + * out-of-line tag here and let dev_hard_start_xmit() + * insert it if the slave hardware can't. + */ + skb = __vlan_hwaccel_put_tag(skb, vlan_id); if (!skb) { pr_err("failed to insert VLAN tag\n"); return; diff --git a/drivers/net/bonding/bond_main.c b/drivers/net/bonding/bond_main.c index 71a169740d05..1a6e9eb7af43 100644 --- a/drivers/net/bonding/bond_main.c +++ b/drivers/net/bonding/bond_main.c @@ -59,15 +59,12 @@ #include <linux/uaccess.h> #include <linux/errno.h> #include <linux/netdevice.h> -#include <linux/netpoll.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> @@ -171,12 +168,9 @@ MODULE_PARM_DESC(resend_igmp, "Number of IGMP membership reports to send on link /*----------------------------- Global variables ----------------------------*/ #ifdef CONFIG_NET_POLL_CONTROLLER -cpumask_var_t netpoll_block_tx; +atomic_t netpoll_block_tx = ATOMIC_INIT(0); #endif -static const char * const version = - DRV_DESCRIPTION ": v" DRV_VERSION " (" DRV_RELDATE ")\n"; - int bond_net_id __read_mostly; static __be32 arp_target[BOND_MAX_ARP_TARGETS]; @@ -246,7 +240,7 @@ static void bond_uninit(struct net_device *bond_dev); /*---------------------------- General routines -----------------------------*/ -static const char *bond_mode_name(int mode) +const char *bond_mode_name(int mode) { static const char *names[] = { [BOND_MODE_ROUNDROBIN] = "load balancing (round-robin)", @@ -418,46 +412,15 @@ struct vlan_entry *bond_next_vlan(struct bonding *bond, struct vlan_entry *curr) * @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) { - unsigned short uninitialized_var(vlan_id); - - /* Test vlan_list not vlgrp to catch and handle 802.1p tags */ - 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; -#ifdef CONFIG_NET_POLL_CONTROLLER - if (unlikely(bond->dev->priv_flags & IFF_IN_NETPOLL)) { - struct netpoll *np = bond->dev->npinfo->netpoll; - slave_dev->npinfo = bond->dev->npinfo; - slave_dev->priv_flags |= IFF_IN_NETPOLL; - netpoll_send_skb_on_dev(np, skb, slave_dev); - slave_dev->priv_flags &= ~IFF_IN_NETPOLL; - } else -#endif + if (unlikely(netpoll_tx_running(slave_dev))) + bond_netpoll_send_skb(bond_get_slave_by_dev(bond, slave_dev), skb); + else dev_queue_xmit(skb); return 0; @@ -873,17 +836,11 @@ static void bond_mc_del(struct bonding *bond, void *addr) static void __bond_resend_igmp_join_requests(struct net_device *dev) { struct in_device *in_dev; - struct ip_mc_list *im; rcu_read_lock(); in_dev = __in_dev_get_rcu(dev); - if (in_dev) { - read_lock(&in_dev->mc_list_lock); - for (im = in_dev->mc_list; im; im = im->next) - ip_mc_rejoin_group(im); - read_unlock(&in_dev->mc_list_lock); - } - + if (in_dev) + ip_mc_rejoin_groups(in_dev); rcu_read_unlock(); } @@ -1203,11 +1160,13 @@ void bond_change_active_slave(struct bonding *bond, struct slave *new_active) bond_do_fail_over_mac(bond, new_active, old_active); - bond->send_grat_arp = bond->params.num_grat_arp; - bond_send_gratuitous_arp(bond); + if (netif_running(bond->dev)) { + bond->send_grat_arp = bond->params.num_grat_arp; + bond_send_gratuitous_arp(bond); - bond->send_unsol_na = bond->params.num_unsol_na; - bond_send_unsolicited_na(bond); + bond->send_unsol_na = bond->params.num_unsol_na; + bond_send_unsolicited_na(bond); + } write_unlock_bh(&bond->curr_slave_lock); read_unlock(&bond->lock); @@ -1221,8 +1180,9 @@ void bond_change_active_slave(struct bonding *bond, struct slave *new_active) /* resend IGMP joins since active slave has changed or * all were sent on curr_active_slave */ - if ((USES_PRIMARY(bond->params.mode) && new_active) || - bond->params.mode == BOND_MODE_ROUNDROBIN) { + if (((USES_PRIMARY(bond->params.mode) && new_active) || + bond->params.mode == BOND_MODE_ROUNDROBIN) && + netif_running(bond->dev)) { bond->igmp_retrans = bond->params.resend_igmp; queue_delayed_work(bond->wq, &bond->mcast_work, 0); } @@ -1316,63 +1276,103 @@ static void bond_detach_slave(struct bonding *bond, struct slave *slave) } #ifdef CONFIG_NET_POLL_CONTROLLER -/* - * You must hold read lock on bond->lock before calling this. - */ -static bool slaves_support_netpoll(struct net_device *bond_dev) +static inline int slave_enable_netpoll(struct slave *slave) { - struct bonding *bond = netdev_priv(bond_dev); - struct slave *slave; - int i = 0; - bool ret = true; + struct netpoll *np; + int err = 0; - bond_for_each_slave(bond, slave, i) { - if ((slave->dev->priv_flags & IFF_DISABLE_NETPOLL) || - !slave->dev->netdev_ops->ndo_poll_controller) - ret = false; + np = kzalloc(sizeof(*np), GFP_KERNEL); + err = -ENOMEM; + if (!np) + goto out; + + np->dev = slave->dev; + err = __netpoll_setup(np); + if (err) { + kfree(np); + goto out; } - return i != 0 && ret; + slave->np = np; +out: + return err; +} +static inline void slave_disable_netpoll(struct slave *slave) +{ + struct netpoll *np = slave->np; + + if (!np) + return; + + slave->np = NULL; + synchronize_rcu_bh(); + __netpoll_cleanup(np); + kfree(np); +} +static inline bool slave_dev_support_netpoll(struct net_device *slave_dev) +{ + if (slave_dev->priv_flags & IFF_DISABLE_NETPOLL) + return false; + if (!slave_dev->netdev_ops->ndo_poll_controller) + return false; + return true; } static void bond_poll_controller(struct net_device *bond_dev) { - struct bonding *bond = netdev_priv(bond_dev); +} + +static void __bond_netpoll_cleanup(struct bonding *bond) +{ struct slave *slave; int i; - bond_for_each_slave(bond, slave, i) { - if (slave->dev && IS_UP(slave->dev)) - netpoll_poll_dev(slave->dev); - } + bond_for_each_slave(bond, slave, i) + if (IS_UP(slave->dev)) + slave_disable_netpoll(slave); } - static void bond_netpoll_cleanup(struct net_device *bond_dev) { struct bonding *bond = netdev_priv(bond_dev); + + read_lock(&bond->lock); + __bond_netpoll_cleanup(bond); + read_unlock(&bond->lock); +} + +static int bond_netpoll_setup(struct net_device *dev, struct netpoll_info *ni) +{ + struct bonding *bond = netdev_priv(dev); struct slave *slave; - const struct net_device_ops *ops; - int i; + int i, err = 0; read_lock(&bond->lock); - bond_dev->npinfo = NULL; bond_for_each_slave(bond, slave, i) { - if (slave->dev) { - ops = slave->dev->netdev_ops; - if (ops->ndo_netpoll_cleanup) - ops->ndo_netpoll_cleanup(slave->dev); - else - slave->dev->npinfo = NULL; + err = slave_enable_netpoll(slave); + if (err) { + __bond_netpoll_cleanup(bond); + break; } } read_unlock(&bond->lock); + return err; } -#else +static struct netpoll_info *bond_netpoll_info(struct bonding *bond) +{ + return bond->dev->npinfo; +} +#else +static inline int slave_enable_netpoll(struct slave *slave) +{ + return 0; +} +static inline void slave_disable_netpoll(struct slave *slave) +{ +} static void bond_netpoll_cleanup(struct net_device *bond_dev) { } - #endif /*---------------------------------- IOCTL ----------------------------------*/ @@ -1400,8 +1400,8 @@ static int bond_compute_features(struct bonding *bond) { struct slave *slave; struct net_device *bond_dev = bond->dev; - unsigned long features = bond_dev->features; - unsigned long vlan_features = 0; + u32 features = bond_dev->features; + u32 vlan_features = 0; unsigned short max_hard_header_len = max((u16)ETH_HLEN, bond_dev->hard_header_len); int i; @@ -1428,8 +1428,8 @@ static int bond_compute_features(struct bonding *bond) done: features |= (bond_dev->features & BOND_VLAN_FEATURES); - bond_dev->features = netdev_fix_features(features, NULL); - bond_dev->vlan_features = netdev_fix_features(vlan_features, NULL); + bond_dev->features = netdev_fix_features(bond_dev, features); + bond_dev->vlan_features = netdev_fix_features(bond_dev, vlan_features); bond_dev->hard_header_len = max_hard_header_len; return 0; @@ -1451,6 +1451,77 @@ static void bond_setup_by_slave(struct net_device *bond_dev, bond->setup_by_slave = 1; } +/* On bonding slaves other than the currently active slave, suppress + * duplicates except for 802.3ad ETH_P_SLOW, alb non-mcast/bcast, and + * ARP on active-backup slaves with arp_validate enabled. + */ +static bool bond_should_deliver_exact_match(struct sk_buff *skb, + struct slave *slave, + struct bonding *bond) +{ + if (bond_is_slave_inactive(slave)) { + if (slave_do_arp_validate(bond, slave) && + skb->protocol == __cpu_to_be16(ETH_P_ARP)) + return false; + + if (bond->params.mode == BOND_MODE_ALB && + skb->pkt_type != PACKET_BROADCAST && + skb->pkt_type != PACKET_MULTICAST) + return false; + + if (bond->params.mode == BOND_MODE_8023AD && + skb->protocol == __cpu_to_be16(ETH_P_SLOW)) + 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; + struct bonding *bond; + + slave = bond_slave_get_rcu(skb->dev); + bond_dev = ACCESS_ONCE(slave->dev->master); + if (unlikely(!bond_dev)) + return RX_HANDLER_PASS; + + skb = skb_share_check(skb, GFP_ATOMIC); + if (unlikely(!skb)) + return RX_HANDLER_CONSUMED; + + *pskb = skb; + + bond = netdev_priv(bond_dev); + + if (bond->params.arp_interval) + slave->dev->last_rx = jiffies; + + if (bond_should_deliver_exact_match(skb, slave, bond)) { + return RX_HANDLER_EXACT; + } + + skb->dev = bond_dev; + + if (bond->params.mode == BOND_MODE_ALB && + bond_dev->priv_flags & IFF_BRIDGE_PORT && + skb->pkt_type == PACKET_HOST) { + + if (unlikely(skb_cow_head(skb, + skb->data - skb_mac_header(skb)))) { + kfree_skb(skb); + return RX_HANDLER_CONSUMED; + } + memcpy(eth_hdr(skb)->h_dest, bond_dev->dev_addr, ETH_ALEN); + } + + return RX_HANDLER_ANOTHER; +} + /* enslave device <slave> to bond device <master> */ int bond_enslave(struct net_device *bond_dev, struct net_device *slave_dev) { @@ -1576,7 +1647,7 @@ int bond_enslave(struct net_device *bond_dev, struct net_device *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->slave_cnt == 0) + if (is_zero_ether_addr(bond->dev->dev_addr)) memcpy(bond->dev->dev_addr, slave_dev->dev_addr, slave_dev->addr_len); @@ -1622,16 +1693,23 @@ int bond_enslave(struct net_device *bond_dev, struct net_device *slave_dev) } } - res = netdev_set_master(slave_dev, bond_dev); + res = netdev_set_bond_master(slave_dev, bond_dev); if (res) { - pr_debug("Error %d calling netdev_set_master\n", res); + pr_debug("Error %d calling netdev_set_bond_master\n", res); goto err_restore_mac; } + 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_unset_master; + } + /* open the slave since the application closed it */ res = dev_open(slave_dev); if (res) { pr_debug("Opening slave %s failed\n", slave_dev->name); - goto err_unset_master; + goto err_unreg_rxhandler; } new_slave->dev = slave_dev; @@ -1785,7 +1863,7 @@ int bond_enslave(struct net_device *bond_dev, struct net_device *slave_dev) break; case BOND_MODE_TLB: case BOND_MODE_ALB: - new_slave->state = BOND_STATE_ACTIVE; + bond_set_active_slave(new_slave); bond_set_slave_inactive_flags(new_slave); bond_select_active_slave(bond); break; @@ -1793,7 +1871,7 @@ int bond_enslave(struct net_device *bond_dev, struct net_device *slave_dev) 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), @@ -1810,17 +1888,19 @@ int bond_enslave(struct net_device *bond_dev, struct net_device *slave_dev) bond_set_carrier(bond); #ifdef CONFIG_NET_POLL_CONTROLLER - if (slaves_support_netpoll(bond_dev)) { - bond_dev->priv_flags &= ~IFF_DISABLE_NETPOLL; - if (bond_dev->npinfo) - slave_dev->npinfo = bond_dev->npinfo; - } else if (!(bond_dev->priv_flags & IFF_DISABLE_NETPOLL)) { - bond_dev->priv_flags |= IFF_DISABLE_NETPOLL; - pr_info("New slave device %s does not support netpoll\n", - slave_dev->name); - pr_info("Disabling netpoll support for %s\n", bond_dev->name); + slave_dev->npinfo = bond_netpoll_info(bond); + if (slave_dev->npinfo) { + if (slave_enable_netpoll(new_slave)) { + read_unlock(&bond->lock); + pr_info("Error, %s: master_dev is using netpoll, " + "but new slave device does not support netpoll.\n", + bond_dev->name); + res = -EBUSY; + goto err_close; + } } #endif + read_unlock(&bond->lock); res = bond_create_slave_symlinks(bond_dev, slave_dev); @@ -1829,7 +1909,7 @@ int bond_enslave(struct net_device *bond_dev, struct net_device *slave_dev) pr_info("%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", + bond_is_active_slave(new_slave) ? "n active" : " backup", new_slave->link != BOND_LINK_DOWN ? "n up" : " down"); /* enslave is successful */ @@ -1839,8 +1919,12 @@ int bond_enslave(struct net_device *bond_dev, struct net_device *slave_dev) err_close: dev_close(slave_dev); +err_unreg_rxhandler: + netdev_rx_handler_unregister(slave_dev); + synchronize_net(); + err_unset_master: - netdev_set_master(slave_dev, NULL); + netdev_set_bond_master(slave_dev, NULL); err_restore_mac: if (!bond->params.fail_over_mac) { @@ -1923,7 +2007,7 @@ int bond_release(struct net_device *bond_dev, struct net_device *slave_dev) pr_info("%s: releasing %s interface %s\n", bond_dev->name, - (slave->state == BOND_STATE_ACTIVE) ? "active" : "backup", + bond_is_active_slave(slave) ? "active" : "backup", slave_dev->name); oldcurrent = bond->curr_active_slave; @@ -2020,19 +2104,11 @@ int bond_release(struct net_device *bond_dev, struct net_device *slave_dev) netif_addr_unlock_bh(bond_dev); } - netdev_set_master(slave_dev, NULL); + netdev_rx_handler_unregister(slave_dev); + synchronize_net(); + netdev_set_bond_master(slave_dev, NULL); -#ifdef CONFIG_NET_POLL_CONTROLLER - read_lock_bh(&bond->lock); - - if (slaves_support_netpoll(bond_dev)) - bond_dev->priv_flags &= ~IFF_DISABLE_NETPOLL; - read_unlock_bh(&bond->lock); - if (slave_dev->netdev_ops->ndo_netpoll_cleanup) - slave_dev->netdev_ops->ndo_netpoll_cleanup(slave_dev); - else - slave_dev->npinfo = NULL; -#endif + slave_disable_netpoll(slave); /* close slave before restoring its mac address */ dev_close(slave_dev); @@ -2046,9 +2122,7 @@ int bond_release(struct net_device *bond_dev, struct net_device *slave_dev) dev_set_mtu(slave_dev, slave->original_mtu); - slave_dev->priv_flags &= ~(IFF_MASTER_8023AD | IFF_MASTER_ALB | - IFF_SLAVE_INACTIVE | IFF_BONDING | - IFF_SLAVE_NEEDARP); + slave_dev->priv_flags &= ~IFF_BONDING; kfree(slave); @@ -2067,6 +2141,7 @@ static int bond_release_and_destroy(struct net_device *bond_dev, ret = bond_release(bond_dev, slave_dev); if ((ret == 0) && (bond->slave_cnt == 0)) { + bond_dev->priv_flags |= IFF_DISABLE_NETPOLL; pr_info("%s: destroying bond %s.\n", bond_dev->name, bond_dev->name); unregister_netdevice(bond_dev); @@ -2142,7 +2217,11 @@ static int bond_release_all(struct net_device *bond_dev) netif_addr_unlock_bh(bond_dev); } - netdev_set_master(slave_dev, NULL); + netdev_rx_handler_unregister(slave_dev); + synchronize_net(); + netdev_set_bond_master(slave_dev, NULL); + + slave_disable_netpoll(slave); /* close slave before restoring its mac address */ dev_close(slave_dev); @@ -2154,9 +2233,6 @@ static int bond_release_all(struct net_device *bond_dev) dev_set_mac_address(slave_dev, &addr); } - slave_dev->priv_flags &= ~(IFF_MASTER_8023AD | IFF_MASTER_ALB | - IFF_SLAVE_INACTIVE); - kfree(slave); /* re-acquire the lock before getting the next slave */ @@ -2270,7 +2346,7 @@ static int bond_slave_info_query(struct net_device *bond_dev, struct ifslave *in res = 0; strcpy(info->slave_name, slave->dev->name); info->link = slave->link; - info->state = slave->state; + info->state = bond_slave_state(slave); info->link_failure_count = slave->link_failure_count; break; } @@ -2309,7 +2385,7 @@ static int bond_miimon_inspect(struct bonding *bond) bond->dev->name, (bond->params.mode == BOND_MODE_ACTIVEBACKUP) ? - ((slave->state == BOND_STATE_ACTIVE) ? + (bond_is_active_slave(slave) ? "active " : "backup ") : "", slave->dev->name, bond->params.downdelay * bond->params.miimon); @@ -2400,13 +2476,13 @@ static void bond_miimon_commit(struct bonding *bond) if (bond->params.mode == BOND_MODE_8023AD) { /* prevent it from being the active one */ - slave->state = BOND_STATE_BACKUP; + bond_set_backup_slave(slave); } else if (bond->params.mode != BOND_MODE_ACTIVEBACKUP) { /* make it immediately active */ - slave->state = BOND_STATE_ACTIVE; + bond_set_active_slave(slave); } else if (slave != bond->primary_slave) { /* prevent it from being the active one */ - slave->state = BOND_STATE_BACKUP; + bond_set_backup_slave(slave); } bond_update_speed_duplex(slave); @@ -2599,11 +2675,10 @@ static void bond_arp_send(struct net_device *slave_dev, int arp_op, __be32 dest_ static void bond_arp_send_all(struct bonding *bond, struct slave *slave) { - int i, vlan_id, rv; + int i, vlan_id; __be32 *targets = bond->params.arp_targets; struct vlan_entry *vlan; struct net_device *vlan_dev; - struct flowi fl; struct rtable *rt; for (i = 0; (i < BOND_MAX_ARP_TARGETS); i++) { @@ -2622,15 +2697,12 @@ static void bond_arp_send_all(struct bonding *bond, struct slave *slave) * 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; - - rv = ip_route_output_key(dev_net(bond->dev), &rt, &fl); - if (rv) { + rt = ip_route_output(dev_net(bond->dev), targets[i], 0, + RTO_ONLINK, 0); + if (IS_ERR(rt)) { if (net_ratelimit()) { pr_warning("%s: no route to arp_ip_target %pI4\n", - bond->dev->name, &fl.fl4_dst); + bond->dev->name, &targets[i]); } continue; } @@ -2666,7 +2738,7 @@ static void bond_arp_send_all(struct bonding *bond, struct slave *slave) if (net_ratelimit()) { pr_warning("%s: no path to arp_ip_target %pI4 via rt.dev %s\n", - bond->dev->name, &fl.fl4_dst, + bond->dev->name, &targets[i], rt->dst.dev ? rt->dst.dev->name : "NULL"); } ip_rt_put(rt); @@ -2761,6 +2833,10 @@ static int bond_arp_rcv(struct sk_buff *skb, struct net_device *dev, struct pack if (!slave || !slave_do_arp_validate(bond, slave)) goto out_unlock; + skb = skb_share_check(skb, GFP_ATOMIC); + if (!skb) + goto out_unlock; + if (!pskb_may_pull(skb, arp_hdr_len(dev))) goto out_unlock; @@ -2780,7 +2856,7 @@ static int bond_arp_rcv(struct sk_buff *skb, struct net_device *dev, struct pack 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, slave->state, + bond->dev->name, slave->dev->name, bond_slave_state(slave), bond->params.arp_validate, slave_do_arp_validate(bond, slave), &sip, &tip); @@ -2792,7 +2868,7 @@ static int bond_arp_rcv(struct sk_buff *skb, struct net_device *dev, struct pack * the active, through one switch, the router, then the other * switch before reaching the backup. */ - if (slave->state == BOND_STATE_ACTIVE) + if (bond_is_active_slave(slave)) bond_validate_arp(bond, slave, sip, tip); else bond_validate_arp(bond, slave, tip, sip); @@ -2854,7 +2930,7 @@ void bond_loadbalance_arp_mon(struct work_struct *work) slave->dev->last_rx + delta_in_ticks)) { slave->link = BOND_LINK_UP; - slave->state = BOND_STATE_ACTIVE; + bond_set_active_slave(slave); /* primary_slave has no meaning in round-robin * mode. the window of a slave being up and @@ -2887,7 +2963,7 @@ void bond_loadbalance_arp_mon(struct work_struct *work) slave->dev->last_rx + 2 * delta_in_ticks)) { slave->link = BOND_LINK_DOWN; - slave->state = BOND_STATE_BACKUP; + bond_set_backup_slave(slave); if (slave->link_failure_count < UINT_MAX) slave->link_failure_count++; @@ -2981,7 +3057,7 @@ static int bond_ab_arp_inspect(struct bonding *bond, int delta_in_ticks) * gives each slave a chance to tx/rx traffic * before being taken out */ - if (slave->state == BOND_STATE_BACKUP && + if (!bond_is_active_slave(slave) && !bond->current_arp_slave && !time_in_range(jiffies, slave_last_rx(bond, slave) - delta_in_ticks, @@ -2998,7 +3074,7 @@ static int bond_ab_arp_inspect(struct bonding *bond, int delta_in_ticks) * the bond has an IP address) */ trans_start = dev_trans_start(slave->dev); - if ((slave->state == BOND_STATE_ACTIVE) && + if (bond_is_active_slave(slave) && (!time_in_range(jiffies, trans_start - delta_in_ticks, trans_start + 2 * delta_in_ticks) || @@ -3206,299 +3282,6 @@ out: read_unlock(&bond->lock); } -/*------------------------------ proc/seq_file-------------------------------*/ - -#ifdef CONFIG_PROC_FS - -static void *bond_info_seq_start(struct seq_file *seq, loff_t *pos) - __acquires(&dev_base_lock) - __acquires(&bond->lock) -{ - struct bonding *bond = seq->private; - loff_t off = 0; - struct slave *slave; - int i; - - /* make sure the bond won't be taken away */ - read_lock(&dev_base_lock); - read_lock(&bond->lock); - - if (*pos == 0) - return SEQ_START_TOKEN; - - bond_for_each_slave(bond, slave, i) { - if (++off == *pos) - return slave; - } - - return NULL; -} - -static void *bond_info_seq_next(struct seq_file *seq, void *v, loff_t *pos) -{ - struct bonding *bond = seq->private; - struct slave *slave = v; - - ++*pos; - if (v == SEQ_START_TOKEN) - return bond->first_slave; - - slave = slave->next; - - return (slave == bond->first_slave) ? NULL : slave; -} - -static void bond_info_seq_stop(struct seq_file *seq, void *v) - __releases(&bond->lock) - __releases(&dev_base_lock) -{ - struct bonding *bond = seq->private; - - read_unlock(&bond->lock); - read_unlock(&dev_base_lock); -} - -static void bond_info_show_master(struct seq_file *seq) -{ - struct bonding *bond = seq->private; - struct slave *curr; - int i; - - read_lock(&bond->curr_slave_lock); - curr = bond->curr_active_slave; - read_unlock(&bond->curr_slave_lock); - - seq_printf(seq, "Bonding Mode: %s", - bond_mode_name(bond->params.mode)); - - if (bond->params.mode == BOND_MODE_ACTIVEBACKUP && - bond->params.fail_over_mac) - seq_printf(seq, " (fail_over_mac %s)", - fail_over_mac_tbl[bond->params.fail_over_mac].modename); - - seq_printf(seq, "\n"); - - if (bond->params.mode == BOND_MODE_XOR || - bond->params.mode == BOND_MODE_8023AD) { - seq_printf(seq, "Transmit Hash Policy: %s (%d)\n", - xmit_hashtype_tbl[bond->params.xmit_policy].modename, - bond->params.xmit_policy); - } - - if (USES_PRIMARY(bond->params.mode)) { - seq_printf(seq, "Primary Slave: %s", - (bond->primary_slave) ? - bond->primary_slave->dev->name : "None"); - if (bond->primary_slave) - seq_printf(seq, " (primary_reselect %s)", - pri_reselect_tbl[bond->params.primary_reselect].modename); - - seq_printf(seq, "\nCurrently Active Slave: %s\n", - (curr) ? curr->dev->name : "None"); - } - - seq_printf(seq, "MII Status: %s\n", netif_carrier_ok(bond->dev) ? - "up" : "down"); - seq_printf(seq, "MII Polling Interval (ms): %d\n", bond->params.miimon); - seq_printf(seq, "Up Delay (ms): %d\n", - bond->params.updelay * bond->params.miimon); - seq_printf(seq, "Down Delay (ms): %d\n", - bond->params.downdelay * bond->params.miimon); - - - /* ARP information */ - if (bond->params.arp_interval > 0) { - int printed = 0; - seq_printf(seq, "ARP Polling Interval (ms): %d\n", - bond->params.arp_interval); - - seq_printf(seq, "ARP IP target/s (n.n.n.n form):"); - - for (i = 0; (i < BOND_MAX_ARP_TARGETS); i++) { - if (!bond->params.arp_targets[i]) - break; - if (printed) - seq_printf(seq, ","); - seq_printf(seq, " %pI4", &bond->params.arp_targets[i]); - printed = 1; - } - seq_printf(seq, "\n"); - } - - if (bond->params.mode == BOND_MODE_8023AD) { - struct ad_info ad_info; - - seq_puts(seq, "\n802.3ad info\n"); - seq_printf(seq, "LACP rate: %s\n", - (bond->params.lacp_fast) ? "fast" : "slow"); - seq_printf(seq, "Aggregator selection policy (ad_select): %s\n", - ad_select_tbl[bond->params.ad_select].modename); - - if (bond_3ad_get_active_agg_info(bond, &ad_info)) { - seq_printf(seq, "bond %s has no active aggregator\n", - bond->dev->name); - } else { - seq_printf(seq, "Active Aggregator Info:\n"); - - seq_printf(seq, "\tAggregator ID: %d\n", - ad_info.aggregator_id); - seq_printf(seq, "\tNumber of ports: %d\n", - ad_info.ports); - seq_printf(seq, "\tActor Key: %d\n", - ad_info.actor_key); - seq_printf(seq, "\tPartner Key: %d\n", - ad_info.partner_key); - seq_printf(seq, "\tPartner Mac Address: %pM\n", - ad_info.partner_system); - } - } -} - -static void bond_info_show_slave(struct seq_file *seq, - const struct slave *slave) -{ - struct bonding *bond = seq->private; - - seq_printf(seq, "\nSlave Interface: %s\n", slave->dev->name); - seq_printf(seq, "MII Status: %s\n", - (slave->link == BOND_LINK_UP) ? "up" : "down"); - seq_printf(seq, "Speed: %d Mbps\n", slave->speed); - seq_printf(seq, "Duplex: %s\n", slave->duplex ? "full" : "half"); - seq_printf(seq, "Link Failure Count: %u\n", - slave->link_failure_count); - - seq_printf(seq, "Permanent HW addr: %pM\n", slave->perm_hwaddr); - - if (bond->params.mode == BOND_MODE_8023AD) { - const struct aggregator *agg - = SLAVE_AD_INFO(slave).port.aggregator; - - if (agg) - seq_printf(seq, "Aggregator ID: %d\n", - agg->aggregator_identifier); - else - seq_puts(seq, "Aggregator ID: N/A\n"); - } - seq_printf(seq, "Slave queue ID: %d\n", slave->queue_id); -} - -static int bond_info_seq_show(struct seq_file *seq, void *v) -{ - if (v == SEQ_START_TOKEN) { - seq_printf(seq, "%s\n", version); - bond_info_show_master(seq); - } else - bond_info_show_slave(seq, v); - - return 0; -} - -static const struct seq_operations bond_info_seq_ops = { - .start = bond_info_seq_start, - .next = bond_info_seq_next, - .stop = bond_info_seq_stop, - .show = bond_info_seq_show, -}; - -static int bond_info_open(struct inode *inode, struct file *file) -{ - struct seq_file *seq; - struct proc_dir_entry *proc; - int res; - - res = seq_open(file, &bond_info_seq_ops); - if (!res) { - /* recover the pointer buried in proc_dir_entry data */ - seq = file->private_data; - proc = PDE(inode); - seq->private = proc->data; - } - - return res; -} - -static const struct file_operations bond_info_fops = { - .owner = THIS_MODULE, - .open = bond_info_open, - .read = seq_read, - .llseek = seq_lseek, - .release = seq_release, -}; - -static void bond_create_proc_entry(struct bonding *bond) -{ - struct net_device *bond_dev = bond->dev; - struct bond_net *bn = net_generic(dev_net(bond_dev), bond_net_id); - - if (bn->proc_dir) { - bond->proc_entry = proc_create_data(bond_dev->name, - S_IRUGO, bn->proc_dir, - &bond_info_fops, bond); - if (bond->proc_entry == NULL) - pr_warning("Warning: Cannot create /proc/net/%s/%s\n", - DRV_NAME, bond_dev->name); - else - memcpy(bond->proc_file_name, bond_dev->name, IFNAMSIZ); - } -} - -static 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. - */ -static void __net_init bond_create_proc_dir(struct bond_net *bn) -{ - if (!bn->proc_dir) { - bn->proc_dir = proc_mkdir(DRV_NAME, bn->net->proc_net); - if (!bn->proc_dir) - pr_warning("Warning: cannot create /proc/net/%s\n", - DRV_NAME); - } -} - -/* Destroy the bonding directory under /proc/net, if empty. - * Caller must hold rtnl_lock. - */ -static 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; - } -} - -#else /* !CONFIG_PROC_FS */ - -static void bond_create_proc_entry(struct bonding *bond) -{ -} - -static 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 /* CONFIG_PROC_FS */ - - /*-------------------------- netdev event handling --------------------------*/ /* @@ -3509,6 +3292,8 @@ static int bond_event_changename(struct bonding *bond) bond_remove_proc_entry(bond); bond_create_proc_entry(bond); + bond_debug_reregister(bond); + return NOTIFY_DONE; } @@ -4353,7 +4138,7 @@ static int bond_xmit_roundrobin(struct sk_buff *skb, struct net_device *bond_dev 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)) { + bond_is_active_slave(slave)) { res = bond_dev_queue_xmit(bond, skb, slave->dev); break; } @@ -4430,7 +4215,7 @@ static int bond_xmit_xor(struct sk_buff *skb, struct net_device *bond_dev) 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)) { + bond_is_active_slave(slave)) { res = bond_dev_queue_xmit(bond, skb, slave->dev); break; } @@ -4471,7 +4256,7 @@ static int bond_xmit_broadcast(struct sk_buff *skb, struct net_device *bond_dev) 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)) { + bond_is_active_slave(slave)) { if (tx_dev) { struct sk_buff *skb2 = skb_clone(skb, GFP_ATOMIC); if (!skb2) { @@ -4559,11 +4344,18 @@ static u16 bond_select_queue(struct net_device *dev, struct sk_buff *skb) { /* * This helper function exists to help dev_pick_tx get the correct - * destination queue. Using a helper function skips the a call to + * 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. */ - return skb->queue_mapping; + u16 txq = skb_rx_queue_recorded(skb) ? skb_get_rx_queue(skb) : 0; + + if (unlikely(txq >= dev->real_num_tx_queues)) { + do + txq -= dev->real_num_tx_queues; + while (txq >= dev->real_num_tx_queues); + } + return txq; } static netdev_tx_t bond_start_xmit(struct sk_buff *skb, struct net_device *dev) @@ -4625,11 +4417,9 @@ void bond_set_mode_ops(struct bonding *bond, int mode) case BOND_MODE_BROADCAST: break; case BOND_MODE_8023AD: - bond_set_master_3ad_flags(bond); bond_set_xmit_hash_policy(bond); break; case BOND_MODE_ALB: - bond_set_master_alb_flags(bond); /* FALLTHRU */ case BOND_MODE_TLB: break; @@ -4676,9 +4466,12 @@ static const struct net_device_ops bond_netdev_ops = { .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, }; static void bond_destructor(struct net_device *bond_dev) @@ -4717,9 +4510,6 @@ static void bond_setup(struct net_device *bond_dev) bond_dev->priv_flags |= IFF_BONDING; bond_dev->priv_flags &= ~IFF_XMIT_DST_RELEASE; - if (bond->params.arp_interval) - bond_dev->priv_flags |= IFF_MASTER_ARPMON; - /* At first, we block adding VLANs. That's the only way to * prevent problems that occur when adding VLANs over an * empty bond. The block will be removed once non-challenged @@ -4791,6 +4581,8 @@ static void bond_uninit(struct net_device *bond_dev) bond_remove_proc_entry(bond); + bond_debug_unregister(bond); + __hw_addr_flush(&bond->mc_list); list_for_each_entry_safe(vlan, tmp, &bond->vlan_list, vlan_list) { @@ -5186,13 +4978,13 @@ static int bond_init(struct net_device *bond_dev) bond_set_lockdep_class(bond_dev); - netif_carrier_off(bond_dev); - bond_create_proc_entry(bond); list_add_tail(&bond->bond_list, &bn->dev_list); bond_prepare_sysfs_group(bond); + bond_debug_register(bond); + __hw_addr_init(&bond->mc_list); return 0; } @@ -5255,6 +5047,8 @@ int bond_create(struct net *net, const char *name) res = register_netdevice(bond_dev); + netif_carrier_off(bond_dev); + out: rtnl_unlock(); if (res < 0) @@ -5293,19 +5087,12 @@ static int __init bonding_init(void) int i; int res; - pr_info("%s", version); + pr_info("%s", bond_version); res = bond_check_params(&bonding_defaults); if (res) goto out; -#ifdef CONFIG_NET_POLL_CONTROLLER - if (!alloc_cpumask_var(&netpoll_block_tx, GFP_KERNEL)) { - res = -ENOMEM; - goto out; - } -#endif - res = register_pernet_subsys(&bond_net_ops); if (res) goto out; @@ -5314,6 +5101,8 @@ static int __init bonding_init(void) if (res) goto err_link; + bond_create_debugfs(); + for (i = 0; i < max_bonds; i++) { res = bond_create(&init_net, NULL); if (res) @@ -5324,7 +5113,6 @@ static int __init bonding_init(void) if (res) goto err; - register_netdevice_notifier(&bond_netdev_notifier); register_inetaddr_notifier(&bond_inetaddr_notifier); bond_register_ipv6_notifier(); @@ -5334,9 +5122,6 @@ err: rtnl_link_unregister(&bond_link_ops); err_link: unregister_pernet_subsys(&bond_net_ops); -#ifdef CONFIG_NET_POLL_CONTROLLER - free_cpumask_var(netpoll_block_tx); -#endif goto out; } @@ -5348,12 +5133,16 @@ static void __exit bonding_exit(void) bond_unregister_ipv6_notifier(); bond_destroy_sysfs(); + bond_destroy_debugfs(); rtnl_link_unregister(&bond_link_ops); unregister_pernet_subsys(&bond_net_ops); #ifdef CONFIG_NET_POLL_CONTROLLER - free_cpumask_var(netpoll_block_tx); + /* + * Make sure we don't have an imbalance on our netpoll blocking + */ + WARN_ON(atomic_read(&netpoll_block_tx)); #endif } diff --git a/drivers/net/bonding/bond_procfs.c b/drivers/net/bonding/bond_procfs.c new file mode 100644 index 000000000000..c32ff55a34c1 --- /dev/null +++ b/drivers/net/bonding/bond_procfs.c @@ -0,0 +1,275 @@ +#include <linux/proc_fs.h> +#include <net/net_namespace.h> +#include <net/netns/generic.h> +#include "bonding.h" + + +extern const char *bond_mode_name(int mode); + +static void *bond_info_seq_start(struct seq_file *seq, loff_t *pos) + __acquires(RCU) + __acquires(&bond->lock) +{ + struct bonding *bond = seq->private; + loff_t off = 0; + struct slave *slave; + int i; + + /* make sure the bond won't be taken away */ + rcu_read_lock(); + read_lock(&bond->lock); + + if (*pos == 0) + return SEQ_START_TOKEN; + + bond_for_each_slave(bond, slave, i) { + if (++off == *pos) + return slave; + } + + return NULL; +} + +static void *bond_info_seq_next(struct seq_file *seq, void *v, loff_t *pos) +{ + struct bonding *bond = seq->private; + struct slave *slave = v; + + ++*pos; + if (v == SEQ_START_TOKEN) + return bond->first_slave; + + slave = slave->next; + + return (slave == bond->first_slave) ? NULL : slave; +} + +static void bond_info_seq_stop(struct seq_file *seq, void *v) + __releases(&bond->lock) + __releases(RCU) +{ + struct bonding *bond = seq->private; + + read_unlock(&bond->lock); + rcu_read_unlock(); +} + +static void bond_info_show_master(struct seq_file *seq) +{ + struct bonding *bond = seq->private; + struct slave *curr; + int i; + + read_lock(&bond->curr_slave_lock); + curr = bond->curr_active_slave; + read_unlock(&bond->curr_slave_lock); + + seq_printf(seq, "Bonding Mode: %s", + bond_mode_name(bond->params.mode)); + + if (bond->params.mode == BOND_MODE_ACTIVEBACKUP && + bond->params.fail_over_mac) + seq_printf(seq, " (fail_over_mac %s)", + fail_over_mac_tbl[bond->params.fail_over_mac].modename); + + seq_printf(seq, "\n"); + + if (bond->params.mode == BOND_MODE_XOR || + bond->params.mode == BOND_MODE_8023AD) { + seq_printf(seq, "Transmit Hash Policy: %s (%d)\n", + xmit_hashtype_tbl[bond->params.xmit_policy].modename, + bond->params.xmit_policy); + } + + if (USES_PRIMARY(bond->params.mode)) { + seq_printf(seq, "Primary Slave: %s", + (bond->primary_slave) ? + bond->primary_slave->dev->name : "None"); + if (bond->primary_slave) + seq_printf(seq, " (primary_reselect %s)", + pri_reselect_tbl[bond->params.primary_reselect].modename); + + seq_printf(seq, "\nCurrently Active Slave: %s\n", + (curr) ? curr->dev->name : "None"); + } + + seq_printf(seq, "MII Status: %s\n", netif_carrier_ok(bond->dev) ? + "up" : "down"); + seq_printf(seq, "MII Polling Interval (ms): %d\n", bond->params.miimon); + seq_printf(seq, "Up Delay (ms): %d\n", + bond->params.updelay * bond->params.miimon); + seq_printf(seq, "Down Delay (ms): %d\n", + bond->params.downdelay * bond->params.miimon); + + + /* ARP information */ + if (bond->params.arp_interval > 0) { + int printed = 0; + seq_printf(seq, "ARP Polling Interval (ms): %d\n", + bond->params.arp_interval); + + seq_printf(seq, "ARP IP target/s (n.n.n.n form):"); + + for (i = 0; (i < BOND_MAX_ARP_TARGETS); i++) { + if (!bond->params.arp_targets[i]) + break; + if (printed) + seq_printf(seq, ","); + seq_printf(seq, " %pI4", &bond->params.arp_targets[i]); + printed = 1; + } + seq_printf(seq, "\n"); + } + + if (bond->params.mode == BOND_MODE_8023AD) { + struct ad_info ad_info; + + seq_puts(seq, "\n802.3ad info\n"); + seq_printf(seq, "LACP rate: %s\n", + (bond->params.lacp_fast) ? "fast" : "slow"); + seq_printf(seq, "Aggregator selection policy (ad_select): %s\n", + ad_select_tbl[bond->params.ad_select].modename); + + if (bond_3ad_get_active_agg_info(bond, &ad_info)) { + seq_printf(seq, "bond %s has no active aggregator\n", + bond->dev->name); + } else { + seq_printf(seq, "Active Aggregator Info:\n"); + + seq_printf(seq, "\tAggregator ID: %d\n", + ad_info.aggregator_id); + seq_printf(seq, "\tNumber of ports: %d\n", + ad_info.ports); + seq_printf(seq, "\tActor Key: %d\n", + ad_info.actor_key); + seq_printf(seq, "\tPartner Key: %d\n", + ad_info.partner_key); + seq_printf(seq, "\tPartner Mac Address: %pM\n", + ad_info.partner_system); + } + } +} + +static void bond_info_show_slave(struct seq_file *seq, + const struct slave *slave) +{ + struct bonding *bond = seq->private; + + seq_printf(seq, "\nSlave Interface: %s\n", slave->dev->name); + seq_printf(seq, "MII Status: %s\n", + (slave->link == BOND_LINK_UP) ? "up" : "down"); + seq_printf(seq, "Speed: %d Mbps\n", slave->speed); + seq_printf(seq, "Duplex: %s\n", slave->duplex ? "full" : "half"); + seq_printf(seq, "Link Failure Count: %u\n", + slave->link_failure_count); + + seq_printf(seq, "Permanent HW addr: %pM\n", slave->perm_hwaddr); + + if (bond->params.mode == BOND_MODE_8023AD) { + const struct aggregator *agg + = SLAVE_AD_INFO(slave).port.aggregator; + + if (agg) + seq_printf(seq, "Aggregator ID: %d\n", + agg->aggregator_identifier); + else + seq_puts(seq, "Aggregator ID: N/A\n"); + } + seq_printf(seq, "Slave queue ID: %d\n", slave->queue_id); +} + +static int bond_info_seq_show(struct seq_file *seq, void *v) +{ + if (v == SEQ_START_TOKEN) { + seq_printf(seq, "%s\n", bond_version); + bond_info_show_master(seq); + } else + bond_info_show_slave(seq, v); + + return 0; +} + +static const struct seq_operations bond_info_seq_ops = { + .start = bond_info_seq_start, + .next = bond_info_seq_next, + .stop = bond_info_seq_stop, + .show = bond_info_seq_show, +}; + +static int bond_info_open(struct inode *inode, struct file *file) +{ + struct seq_file *seq; + struct proc_dir_entry *proc; + int res; + + res = seq_open(file, &bond_info_seq_ops); + if (!res) { + /* recover the pointer buried in proc_dir_entry data */ + seq = file->private_data; + proc = PDE(inode); + seq->private = proc->data; + } + + return res; +} + +static const struct file_operations bond_info_fops = { + .owner = THIS_MODULE, + .open = bond_info_open, + .read = seq_read, + .llseek = seq_lseek, + .release = seq_release, +}; + +void bond_create_proc_entry(struct bonding *bond) +{ + struct net_device *bond_dev = bond->dev; + struct bond_net *bn = net_generic(dev_net(bond_dev), bond_net_id); + + if (bn->proc_dir) { + bond->proc_entry = proc_create_data(bond_dev->name, + S_IRUGO, bn->proc_dir, + &bond_info_fops, bond); + if (bond->proc_entry == NULL) + pr_warning("Warning: Cannot create /proc/net/%s/%s\n", + DRV_NAME, bond_dev->name); + else + memcpy(bond->proc_file_name, bond_dev->name, IFNAMSIZ); + } +} + +void bond_remove_proc_entry(struct bonding *bond) +{ + struct net_device *bond_dev = bond->dev; + struct bond_net *bn = net_generic(dev_net(bond_dev), bond_net_id); + + if (bn->proc_dir && bond->proc_entry) { + remove_proc_entry(bond->proc_file_name, bn->proc_dir); + memset(bond->proc_file_name, 0, IFNAMSIZ); + bond->proc_entry = NULL; + } +} + +/* Create the bonding directory under /proc/net, if doesn't exist yet. + * Caller must hold rtnl_lock. + */ +void __net_init bond_create_proc_dir(struct bond_net *bn) +{ + if (!bn->proc_dir) { + bn->proc_dir = proc_mkdir(DRV_NAME, bn->net->proc_net); + if (!bn->proc_dir) + pr_warning("Warning: cannot create /proc/net/%s\n", + DRV_NAME); + } +} + +/* Destroy the bonding directory under /proc/net, if empty. + * Caller must hold rtnl_lock. + */ +void __net_exit bond_destroy_proc_dir(struct bond_net *bn) +{ + if (bn->proc_dir) { + remove_proc_entry(DRV_NAME, bn->net->proc_net); + bn->proc_dir = NULL; + } +} diff --git a/drivers/net/bonding/bond_sysfs.c b/drivers/net/bonding/bond_sysfs.c index 8fd0174c5380..de87aea6d01a 100644 --- a/drivers/net/bonding/bond_sysfs.c +++ b/drivers/net/bonding/bond_sysfs.c @@ -118,7 +118,10 @@ static ssize_t bonding_store_bonds(struct class *cls, pr_info("%s is being created...\n", ifname); rv = bond_create(net, ifname); if (rv) { - pr_info("Bond creation failed.\n"); + if (rv == -EEXIST) + pr_info("%s already exists.\n", ifname); + else + pr_info("%s creation failed.\n", ifname); res = rv; } } else if (command[0] == '-') { @@ -322,11 +325,6 @@ static ssize_t bonding_store_mode(struct device *d, ret = -EINVAL; goto out; } - if (bond->params.mode == BOND_MODE_8023AD) - bond_unset_master_3ad_flags(bond); - - if (bond->params.mode == BOND_MODE_ALB) - bond_unset_master_alb_flags(bond); bond->params.mode = new_value; bond_set_mode_ops(bond, bond->params.mode); @@ -527,8 +525,6 @@ static ssize_t bonding_store_arp_interval(struct device *d, pr_info("%s: Setting ARP monitoring interval to %d.\n", bond->dev->name, new_value); bond->params.arp_interval = new_value; - if (bond->params.arp_interval) - bond->dev->priv_flags |= IFF_MASTER_ARPMON; 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); @@ -1004,7 +1000,6 @@ static ssize_t bonding_store_miimon(struct device *d, pr_info("%s: MII monitoring cannot be used with ARP monitoring. Disabling ARP monitoring...\n", bond->dev->name); bond->params.arp_interval = 0; - bond->dev->priv_flags &= ~IFF_MASTER_ARPMON; if (bond->params.arp_validate) { bond_unregister_arp(bond); bond->params.arp_validate = @@ -1198,7 +1193,7 @@ static ssize_t bonding_store_carrier(struct device *d, bond->dev->name, new_value); } out: - return count; + return ret; } static DEVICE_ATTR(use_carrier, S_IRUGO | S_IWUSR, bonding_show_carrier, bonding_store_carrier); @@ -1587,15 +1582,15 @@ static ssize_t bonding_store_slaves_active(struct device *d, } bond_for_each_slave(bond, slave, i) { - if (slave->state == BOND_STATE_BACKUP) { + if (!bond_is_active_slave(slave)) { if (new_value) - slave->dev->priv_flags &= ~IFF_SLAVE_INACTIVE; + slave->inactive = 0; else - slave->dev->priv_flags |= IFF_SLAVE_INACTIVE; + slave->inactive = 1; } } out: - return count; + return ret; } static DEVICE_ATTR(all_slaves_active, S_IRUGO | S_IWUSR, bonding_show_slaves_active, bonding_store_slaves_active); diff --git a/drivers/net/bonding/bonding.h b/drivers/net/bonding/bonding.h index 4eedb12df6ca..6b26962fd0ec 100644 --- a/drivers/net/bonding/bonding.h +++ b/drivers/net/bonding/bonding.h @@ -18,9 +18,9 @@ #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 "bond_3ad.h" #include "bond_alb.h" @@ -29,6 +29,8 @@ #define DRV_NAME "bonding" #define DRV_DESCRIPTION "Ethernet Channel Bonding Driver" +#define bond_version DRV_DESCRIPTION ": v" DRV_VERSION " (" DRV_RELDATE ")\n" + #define BOND_MAX_ARP_TARGETS 16 #define IS_UP(dev) \ @@ -53,7 +55,7 @@ (((slave)->dev->flags & IFF_UP) && \ netif_running((slave)->dev) && \ ((slave)->link == BOND_LINK_UP) && \ - ((slave)->state == BOND_STATE_ACTIVE)) + bond_is_active_slave(slave)) #define USES_PRIMARY(mode) \ @@ -119,26 +121,22 @@ #ifdef CONFIG_NET_POLL_CONTROLLER -extern cpumask_var_t netpoll_block_tx; +extern atomic_t netpoll_block_tx; static inline void block_netpoll_tx(void) { - preempt_disable(); - BUG_ON(cpumask_test_and_set_cpu(smp_processor_id(), - netpoll_block_tx)); + atomic_inc(&netpoll_block_tx); } static inline void unblock_netpoll_tx(void) { - BUG_ON(!cpumask_test_and_clear_cpu(smp_processor_id(), - netpoll_block_tx)); - preempt_enable(); + atomic_dec(&netpoll_block_tx); } static inline int is_netpoll_tx_blocked(struct net_device *dev) { - if (unlikely(dev->priv_flags & IFF_IN_NETPOLL)) - return cpumask_test_cpu(smp_processor_id(), netpoll_block_tx); + if (unlikely(netpoll_tx_running(dev))) + return atomic_read(&netpoll_block_tx); return 0; } #else @@ -194,7 +192,9 @@ struct slave { unsigned long last_arp_rx; s8 link; /* one of BOND_LINK_XXXX */ s8 new_link; - s8 state; /* one of BOND_STATE_XXXX */ + u8 backup:1, /* indicates backup slave. Value corresponds with + BOND_STATE_ACTIVE and BOND_STATE_BACKUP */ + inactive:1; /* indicates inactive slave */ u32 original_mtu; u32 link_failure_count; u8 perm_hwaddr[ETH_ALEN]; @@ -203,6 +203,9 @@ struct slave { u16 queue_id; struct ad_slave_info ad_info; /* HUGE - better to dynamically alloc */ struct tlb_slave_info tlb_info; +#ifdef CONFIG_NET_POLL_CONTROLLER + struct netpoll *np; +#endif }; /* @@ -259,25 +262,33 @@ struct bonding { #if defined(CONFIG_IPV6) || defined(CONFIG_IPV6_MODULE) struct in6_addr master_ipv6; #endif +#ifdef CONFIG_DEBUG_FS + /* debugging suport via debugfs */ + struct dentry *debug_dir; +#endif /* CONFIG_DEBUG_FS */ }; +#define bond_slave_get_rcu(dev) \ + ((struct slave *) rcu_dereference(dev->rx_handler_data)) + /** * Returns NULL if the net_device does not belong to any of the bond's slaves * * Caller must hold bond lock for read */ -static inline struct slave *bond_get_slave_by_dev(struct bonding *bond, struct net_device *slave_dev) +static inline struct slave *bond_get_slave_by_dev(struct bonding *bond, + struct net_device *slave_dev) { struct slave *slave = NULL; int i; bond_for_each_slave(bond, slave, i) { if (slave->dev == slave_dev) { - break; + return slave; } } - return slave; + return NULL; } static inline struct bonding *bond_get_bond_by_slave(struct slave *slave) @@ -286,7 +297,7 @@ static inline struct bonding *bond_get_bond_by_slave(struct slave *slave) return NULL; } - return (struct bonding *)netdev_priv(slave->dev->master); + return netdev_priv(slave->dev->master); } static inline bool bond_is_lb(const struct bonding *bond) @@ -295,6 +306,26 @@ static inline bool bond_is_lb(const struct bonding *bond) bond->params.mode == BOND_MODE_ALB); } +static inline void bond_set_active_slave(struct slave *slave) +{ + slave->backup = 0; +} + +static inline void bond_set_backup_slave(struct slave *slave) +{ + slave->backup = 1; +} + +static inline int bond_slave_state(struct slave *slave) +{ + return slave->backup; +} + +static inline bool bond_is_active_slave(struct slave *slave) +{ + return !bond_slave_state(slave); +} + #define BOND_PRI_RESELECT_ALWAYS 0 #define BOND_PRI_RESELECT_BETTER 1 #define BOND_PRI_RESELECT_FAILURE 2 @@ -312,7 +343,7 @@ static inline bool bond_is_lb(const struct bonding *bond) static inline int slave_do_arp_validate(struct bonding *bond, struct slave *slave) { - return bond->params.arp_validate & (1 << slave->state); + return bond->params.arp_validate & (1 << bond_slave_state(slave)); } static inline unsigned long slave_last_rx(struct bonding *bond, @@ -324,41 +355,40 @@ static inline unsigned long slave_last_rx(struct bonding *bond, return slave->dev->last_rx; } -static inline void bond_set_slave_inactive_flags(struct slave *slave) +#ifdef CONFIG_NET_POLL_CONTROLLER +static inline void bond_netpoll_send_skb(const struct slave *slave, + struct sk_buff *skb) { - struct bonding *bond = netdev_priv(slave->dev->master); - if (!bond_is_lb(bond)) - slave->state = BOND_STATE_BACKUP; - if (!bond->params.all_slaves_active) - slave->dev->priv_flags |= IFF_SLAVE_INACTIVE; - if (slave_do_arp_validate(bond, slave)) - slave->dev->priv_flags |= IFF_SLAVE_NEEDARP; -} + struct netpoll *np = slave->np; -static inline void bond_set_slave_active_flags(struct slave *slave) -{ - slave->state = BOND_STATE_ACTIVE; - slave->dev->priv_flags &= ~(IFF_SLAVE_INACTIVE | IFF_SLAVE_NEEDARP); + if (np) + netpoll_send_skb(np, skb); } - -static inline void bond_set_master_3ad_flags(struct bonding *bond) +#else +static inline void bond_netpoll_send_skb(const struct slave *slave, + struct sk_buff *skb) { - bond->dev->priv_flags |= IFF_MASTER_8023AD; } +#endif -static inline void bond_unset_master_3ad_flags(struct bonding *bond) +static inline void bond_set_slave_inactive_flags(struct slave *slave) { - bond->dev->priv_flags &= ~IFF_MASTER_8023AD; + struct bonding *bond = netdev_priv(slave->dev->master); + if (!bond_is_lb(bond)) + bond_set_backup_slave(slave); + if (!bond->params.all_slaves_active) + slave->inactive = 1; } -static inline void bond_set_master_alb_flags(struct bonding *bond) +static inline void bond_set_slave_active_flags(struct slave *slave) { - bond->dev->priv_flags |= IFF_MASTER_ALB; + bond_set_active_slave(slave); + slave->inactive = 0; } -static inline void bond_unset_master_alb_flags(struct bonding *bond) +static inline bool bond_is_slave_inactive(struct slave *slave) { - bond->dev->priv_flags &= ~IFF_MASTER_ALB; + return slave->inactive; } struct vlan_entry *bond_next_vlan(struct bonding *bond, struct vlan_entry *curr); @@ -380,6 +410,11 @@ void bond_select_active_slave(struct bonding *bond); void bond_change_active_slave(struct bonding *bond, struct slave *new_active); void bond_register_arp(struct bonding *); void bond_unregister_arp(struct bonding *); +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); struct bond_net { struct net * net; /* Associated network namespace */ @@ -389,6 +424,30 @@ struct bond_net { #endif }; +#ifdef CONFIG_PROC_FS +void bond_create_proc_entry(struct bonding *bond); +void bond_remove_proc_entry(struct bonding *bond); +void bond_create_proc_dir(struct bond_net *bn); +void bond_destroy_proc_dir(struct bond_net *bn); +#else +static inline void bond_create_proc_entry(struct bonding *bond) +{ +} + +static inline void bond_remove_proc_entry(struct bonding *bond) +{ +} + +static inline void bond_create_proc_dir(struct bond_net *bn) +{ +} + +static inline void bond_destroy_proc_dir(struct bond_net *bn) +{ +} +#endif + + /* exported from bond_main.c */ extern int bond_net_id; extern const struct bond_parm_tbl bond_lacp_tbl[]; |