diff options
Diffstat (limited to 'drivers/net/bonding')
| -rw-r--r-- | drivers/net/bonding/bond_3ad.c | 52 | ||||
| -rw-r--r-- | drivers/net/bonding/bond_alb.c | 144 | ||||
| -rw-r--r-- | drivers/net/bonding/bond_alb.h | 3 | ||||
| -rw-r--r-- | drivers/net/bonding/bond_main.c | 961 | ||||
| -rw-r--r-- | drivers/net/bonding/bond_procfs.c | 12 | ||||
| -rw-r--r-- | drivers/net/bonding/bond_sysfs.c | 90 | ||||
| -rw-r--r-- | drivers/net/bonding/bonding.h | 96 |
7 files changed, 518 insertions, 840 deletions
diff --git a/drivers/net/bonding/bond_3ad.c b/drivers/net/bonding/bond_3ad.c index 390061d09693..0d8f427ade93 100644 --- a/drivers/net/bonding/bond_3ad.c +++ b/drivers/net/bonding/bond_3ad.c @@ -143,10 +143,9 @@ static inline struct bonding *__get_bond_by_port(struct port *port) */ static inline struct port *__get_first_port(struct bonding *bond) { - if (bond->slave_cnt == 0) - return NULL; + struct slave *first_slave = bond_first_slave(bond); - return &(SLAVE_AD_INFO(bond->first_slave).port); + return first_slave ? &(SLAVE_AD_INFO(first_slave).port) : NULL; } /** @@ -159,13 +158,16 @@ static inline struct port *__get_first_port(struct bonding *bond) static inline struct port *__get_next_port(struct port *port) { struct bonding *bond = __get_bond_by_port(port); - struct slave *slave = port->slave; + struct slave *slave = port->slave, *slave_next; // If there's no bond for this port, or this is the last slave - if ((bond == NULL) || (slave->next == bond->first_slave)) + if (bond == NULL) + return NULL; + slave_next = bond_next_slave(bond, slave); + if (!slave_next || bond_is_first_slave(bond, slave_next)) return NULL; - return &(SLAVE_AD_INFO(slave->next).port); + return &(SLAVE_AD_INFO(slave_next).port); } /** @@ -178,12 +180,14 @@ static inline struct port *__get_next_port(struct port *port) static inline struct aggregator *__get_first_agg(struct port *port) { struct bonding *bond = __get_bond_by_port(port); + struct slave *first_slave; // If there's no bond for this port, or bond has no slaves - if ((bond == NULL) || (bond->slave_cnt == 0)) + if (bond == NULL) return NULL; + first_slave = bond_first_slave(bond); - return &(SLAVE_AD_INFO(bond->first_slave).aggregator); + return first_slave ? &(SLAVE_AD_INFO(first_slave).aggregator) : NULL; } /** @@ -195,14 +199,17 @@ static inline struct aggregator *__get_first_agg(struct port *port) */ static inline struct aggregator *__get_next_agg(struct aggregator *aggregator) { - struct slave *slave = aggregator->slave; + struct slave *slave = aggregator->slave, *slave_next; 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)) + if (bond == NULL) + return NULL; + slave_next = bond_next_slave(bond, slave); + if (!slave_next || bond_is_first_slave(bond, slave_next)) return NULL; - return &(SLAVE_AD_INFO(slave->next).aggregator); + return &(SLAVE_AD_INFO(slave_next).aggregator); } /* @@ -2110,7 +2117,7 @@ void bond_3ad_state_machine_handler(struct work_struct *work) read_lock(&bond->lock); //check if there are any slaves - if (bond->slave_cnt == 0) + if (list_empty(&bond->slave_list)) goto re_arm; // check if agg_select_timer timer after initialize is timed out @@ -2336,8 +2343,12 @@ void bond_3ad_handle_link_change(struct slave *slave, char link) int bond_3ad_set_carrier(struct bonding *bond) { struct aggregator *active; + struct slave *first_slave; - active = __get_active_agg(&(SLAVE_AD_INFO(bond->first_slave).aggregator)); + first_slave = bond_first_slave(bond); + if (!first_slave) + return 0; + 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) { @@ -2415,6 +2426,7 @@ int bond_3ad_xmit_xor(struct sk_buff *skb, struct net_device *dev) struct ad_info ad_info; int res = 1; + read_lock(&bond->lock); if (__bond_3ad_get_active_agg_info(bond, &ad_info)) { pr_debug("%s: Error: __bond_3ad_get_active_agg_info failed\n", dev->name); @@ -2432,7 +2444,7 @@ int bond_3ad_xmit_xor(struct sk_buff *skb, struct net_device *dev) slave_agg_no = bond->xmit_hash_policy(skb, slaves_in_agg); - bond_for_each_slave(bond, slave, i) { + bond_for_each_slave(bond, slave) { struct aggregator *agg = SLAVE_AD_INFO(slave).port.aggregator; if (agg && (agg->aggregator_identifier == agg_id)) { @@ -2464,6 +2476,7 @@ int bond_3ad_xmit_xor(struct sk_buff *skb, struct net_device *dev) } out: + read_unlock(&bond->lock); if (res) { /* no suitable interface, frame not sent */ kfree_skb(skb); @@ -2501,18 +2514,13 @@ int bond_3ad_lacpdu_recv(const struct sk_buff *skb, struct bonding *bond, */ void bond_3ad_update_lacp_rate(struct bonding *bond) { - int i; - struct slave *slave; struct port *port = NULL; + struct slave *slave; int lacp_fast; - write_lock_bh(&bond->lock); lacp_fast = bond->params.lacp_fast; - - bond_for_each_slave(bond, slave, i) { + bond_for_each_slave(bond, slave) { port = &(SLAVE_AD_INFO(slave).port); - if (port->slave == NULL) - continue; __get_state_machine_lock(port); if (lacp_fast) port->actor_oper_port_state |= AD_STATE_LACP_TIMEOUT; @@ -2520,6 +2528,4 @@ void bond_3ad_update_lacp_rate(struct bonding *bond) port->actor_oper_port_state &= ~AD_STATE_LACP_TIMEOUT; __release_state_machine_lock(port); } - - write_unlock_bh(&bond->lock); } diff --git a/drivers/net/bonding/bond_alb.c b/drivers/net/bonding/bond_alb.c index 4ea8ed150d46..91f179d5135c 100644 --- a/drivers/net/bonding/bond_alb.c +++ b/drivers/net/bonding/bond_alb.c @@ -224,13 +224,12 @@ static struct slave *tlb_get_least_loaded_slave(struct bonding *bond) { struct slave *slave, *least_loaded; long long max_gap; - int i; least_loaded = NULL; max_gap = LLONG_MIN; /* Find the slave with the largest gap */ - bond_for_each_slave(bond, slave, i) { + bond_for_each_slave(bond, slave) { if (SLAVE_IS_OK(slave)) { long long gap = compute_gap(slave); @@ -386,11 +385,10 @@ static struct slave *rlb_next_rx_slave(struct bonding *bond) struct slave *rx_slave, *slave, *start_at; int i = 0; - if (bond_info->next_rx_slave) { + if (bond_info->next_rx_slave) start_at = bond_info->next_rx_slave; - } else { - start_at = bond->first_slave; - } + else + start_at = bond_first_slave(bond); rx_slave = NULL; @@ -405,7 +403,8 @@ static struct slave *rlb_next_rx_slave(struct bonding *bond) } if (rx_slave) { - bond_info->next_rx_slave = rx_slave->next; + slave = bond_next_slave(bond, rx_slave); + bond_info->next_rx_slave = slave; } return rx_slave; @@ -513,7 +512,7 @@ static void rlb_update_client(struct rlb_client_info *client_info) skb->dev = client_info->slave->dev; - if (client_info->tag) { + if (client_info->vlan_id) { skb = vlan_put_tag(skb, htons(ETH_P_8021Q), client_info->vlan_id); if (!skb) { pr_err("%s: Error: failed to insert VLAN tag\n", @@ -695,10 +694,8 @@ static struct slave *rlb_choose_channel(struct sk_buff *skb, struct bonding *bon client_info->ntt = 0; } - if (bond_vlan_used(bond)) { - if (!vlan_get_tag(skb, &client_info->vlan_id)) - client_info->tag = 1; - } + 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_used_head; @@ -804,7 +801,7 @@ static void rlb_init_table_entry_dst(struct rlb_client_info *entry) entry->used_prev = RLB_NULL_INDEX; entry->assigned = 0; entry->slave = NULL; - entry->tag = 0; + entry->vlan_id = 0; } static void rlb_init_table_entry_src(struct rlb_client_info *entry) { @@ -961,7 +958,7 @@ static void rlb_clear_vlan(struct bonding *bond, unsigned short vlan_id) struct rlb_client_info *curr = &(bond_info->rx_hashtbl[curr_index]); u32 next_index = bond_info->rx_hashtbl[curr_index].used_next; - if (curr->tag && (curr->vlan_id == vlan_id)) + if (curr->vlan_id == vlan_id) rlb_delete_table_entry(bond, curr_index); curr_index = next_index; @@ -972,58 +969,62 @@ static void rlb_clear_vlan(struct bonding *bond, unsigned short vlan_id) /*********************** 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[], + 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 = cpu_to_be16(ETH_P_LOOP); - for (i = 0; i < MAX_LP_BURST; i++) { - struct sk_buff *skb; - char *data; + skb = dev_alloc_skb(size); + if (!skb) + return; + + data = skb_put(skb, size); + memcpy(data, &pkt, size); + + skb_reset_mac_header(skb); + skb->network_header = skb->mac_header + ETH_HLEN; + skb->protocol = pkt.type; + skb->priority = TC_PRIO_CONTROL; + skb->dev = slave->dev; - skb = dev_alloc_skb(size); + if (vid) { + skb = vlan_put_tag(skb, htons(ETH_P_8021Q), 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_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; + dev_queue_xmit(skb); +} - if (bond_vlan_used(bond)) { - struct vlan_entry *vlan; - vlan = bond_next_vlan(bond, - bond->alb_info.current_alb_vlan); +static void alb_send_learning_packets(struct slave *slave, u8 mac_addr[]) +{ + struct bonding *bond = bond_get_bond_by_slave(slave); + struct net_device *upper; + struct list_head *iter; - bond->alb_info.current_alb_vlan = vlan; - if (!vlan) { - kfree_skb(skb); - continue; - } + /* send untagged */ + alb_send_lp_vid(slave, mac_addr, 0); - skb = vlan_put_tag(skb, htons(ETH_P_8021Q), vlan->vlan_id); - if (!skb) { - pr_err("%s: Error: failed to insert VLAN tag\n", - bond->dev->name); - continue; - } - } - - dev_queue_xmit(skb); + /* loop through vlans and send one packet for each */ + rcu_read_lock(); + netdev_for_each_upper_dev_rcu(bond->dev, upper, iter) { + if (upper->priv_flags & IFF_802_1Q_VLAN) + alb_send_lp_vid(slave, mac_addr, + vlan_dev_vlan_id(upper)); } + rcu_read_unlock(); } static int alb_set_slave_mac_addr(struct slave *slave, u8 addr[]) @@ -1173,9 +1174,8 @@ static int alb_handle_addr_collision_on_attach(struct bonding *bond, struct slav { struct slave *tmp_slave1, *free_mac_slave = NULL; struct slave *has_bond_addr = bond->curr_active_slave; - int i; - if (bond->slave_cnt == 0) { + if (list_empty(&bond->slave_list)) { /* this is the first slave */ return 0; } @@ -1196,7 +1196,7 @@ static int alb_handle_addr_collision_on_attach(struct bonding *bond, struct slav /* The slave's address is equal to the address of the bond. * Search for a spare address in the bond for this slave. */ - bond_for_each_slave(bond, tmp_slave1, i) { + bond_for_each_slave(bond, tmp_slave1) { if (!bond_slave_has_mac(bond, tmp_slave1->perm_hwaddr)) { /* no slave has tmp_slave1's perm addr * as its curr addr @@ -1246,17 +1246,15 @@ 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 sockaddr sa; - struct slave *slave, *stop_at; char tmp_addr[ETH_ALEN]; + struct slave *slave; + struct sockaddr sa; 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) { + bond_for_each_slave(bond, slave) { /* save net_device's current hw address */ memcpy(tmp_addr, slave->dev->dev_addr, ETH_ALEN); @@ -1276,8 +1274,7 @@ 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) { + bond_for_each_slave_continue_reverse(bond, slave) { 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); @@ -1342,6 +1339,7 @@ int bond_alb_xmit(struct sk_buff *skb, struct net_device *bond_dev) /* make sure that the curr_active_slave do not change during tx */ + read_lock(&bond->lock); read_lock(&bond->curr_slave_lock); switch (ntohs(skb->protocol)) { @@ -1446,11 +1444,12 @@ int bond_alb_xmit(struct sk_buff *skb, struct net_device *bond_dev) } read_unlock(&bond->curr_slave_lock); - + read_unlock(&bond->lock); if (res) { /* no suitable interface, frame not sent */ kfree_skb(skb); } + return NETDEV_TX_OK; } @@ -1460,11 +1459,10 @@ void bond_alb_monitor(struct work_struct *work) alb_work.work); struct alb_bond_info *bond_info = &(BOND_ALB_INFO(bond)); struct slave *slave; - int i; read_lock(&bond->lock); - if (bond->slave_cnt == 0) { + if (list_empty(&bond->slave_list)) { bond_info->tx_rebalance_counter = 0; bond_info->lp_counter = 0; goto re_arm; @@ -1482,9 +1480,8 @@ void bond_alb_monitor(struct work_struct *work) */ read_lock(&bond->curr_slave_lock); - bond_for_each_slave(bond, slave, i) { + bond_for_each_slave(bond, slave) alb_send_learning_packets(slave, slave->dev->dev_addr); - } read_unlock(&bond->curr_slave_lock); @@ -1496,7 +1493,7 @@ void bond_alb_monitor(struct work_struct *work) read_lock(&bond->curr_slave_lock); - bond_for_each_slave(bond, slave, i) { + bond_for_each_slave(bond, slave) { tlb_clear_slave(bond, slave, 1); if (slave == bond->curr_active_slave) { SLAVE_TLB_INFO(slave).load = @@ -1602,9 +1599,8 @@ int bond_alb_init_slave(struct bonding *bond, struct slave *slave) */ void bond_alb_deinit_slave(struct bonding *bond, struct slave *slave) { - if (bond->slave_cnt > 1) { + if (!list_empty(&bond->slave_list)) alb_change_hw_addr_on_detach(bond, slave); - } tlb_clear_slave(bond, slave, 0); @@ -1661,9 +1657,8 @@ void bond_alb_handle_active_change(struct bonding *bond, struct slave *new_slave { struct slave *swap_slave; - 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); @@ -1672,11 +1667,10 @@ 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 || list_empty(&bond->slave_list)) 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 @@ -1689,9 +1683,8 @@ void bond_alb_handle_active_change(struct bonding *bond, struct slave *new_slave * ignored so we can mess with their MAC addresses without * fear of interference from transmit activity. */ - if (swap_slave) { + if (swap_slave) tlb_clear_slave(bond, swap_slave, 1); - } tlb_clear_slave(bond, new_slave, 1); write_unlock_bh(&bond->curr_slave_lock); @@ -1768,11 +1761,6 @@ 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) { rlb_clear_vlan(bond, vlan_id); } diff --git a/drivers/net/bonding/bond_alb.h b/drivers/net/bonding/bond_alb.h index e7a5b8b37ea3..28d8e4c7dc06 100644 --- a/drivers/net/bonding/bond_alb.h +++ b/drivers/net/bonding/bond_alb.h @@ -53,7 +53,6 @@ struct slave; #define TLB_NULL_INDEX 0xffffffff -#define MAX_LP_BURST 3 /* rlb defs */ #define RLB_HASH_TABLE_SIZE 256 @@ -126,7 +125,6 @@ struct rlb_client_info { 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 */ }; @@ -170,7 +168,6 @@ 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); diff --git a/drivers/net/bonding/bond_main.c b/drivers/net/bonding/bond_main.c index e48cb339c0c6..39e5b1c7ffe2 100644 --- a/drivers/net/bonding/bond_main.c +++ b/drivers/net/bonding/bond_main.c @@ -77,6 +77,7 @@ #include <net/net_namespace.h> #include <net/netns/generic.h> #include <net/pkt_sched.h> +#include <linux/rculist.h> #include "bonding.h" #include "bond_3ad.h" #include "bond_alb.h" @@ -106,7 +107,7 @@ 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 = 0; +static int all_slaves_active; static struct bond_params bonding_defaults; static int resend_igmp = BOND_DEFAULT_RESEND_IGMP; @@ -273,7 +274,7 @@ const char *bond_mode_name(int mode) [BOND_MODE_ALB] = "adaptive load balancing", }; - if (mode < 0 || mode > BOND_MODE_ALB) + if (mode < BOND_MODE_ROUNDROBIN || mode > BOND_MODE_ALB) return "unknown"; return names[mode]; @@ -282,116 +283,6 @@ const char *bond_mode_name(int mode) /*---------------------------------- VLAN -----------------------------------*/ /** - * bond_add_vlan - add a new vlan id on bond - * @bond: bond that got the notification - * @vlan_id: the vlan id to add - * - * Returns -ENOMEM if allocation failed. - */ -static int bond_add_vlan(struct bonding *bond, unsigned short vlan_id) -{ - struct vlan_entry *vlan; - - pr_debug("bond: %s, vlan id %d\n", - (bond ? bond->dev->name : "None"), vlan_id); - - vlan = kzalloc(sizeof(struct vlan_entry), GFP_KERNEL); - if (!vlan) - return -ENOMEM; - - INIT_LIST_HEAD(&vlan->vlan_list); - vlan->vlan_id = vlan_id; - - write_lock_bh(&bond->lock); - - list_add_tail(&vlan->vlan_list, &bond->vlan_list); - - write_unlock_bh(&bond->lock); - - pr_debug("added VLAN ID %d on bond %s\n", vlan_id, bond->dev->name); - - return 0; -} - -/** - * bond_del_vlan - delete a vlan id from bond - * @bond: bond that got the notification - * @vlan_id: the vlan id to delete - * - * returns -ENODEV if @vlan_id was not found in @bond. - */ -static int bond_del_vlan(struct bonding *bond, unsigned short vlan_id) -{ - struct vlan_entry *vlan; - int res = -ENODEV; - - pr_debug("bond: %s, vlan id %d\n", bond->dev->name, vlan_id); - - block_netpoll_tx(); - write_lock_bh(&bond->lock); - - list_for_each_entry(vlan, &bond->vlan_list, vlan_list) { - if (vlan->vlan_id == vlan_id) { - list_del(&vlan->vlan_list); - - if (bond_is_lb(bond)) - bond_alb_clear_vlan(bond, vlan_id); - - pr_debug("removed VLAN ID %d from bond %s\n", - vlan_id, bond->dev->name); - - kfree(vlan); - - res = 0; - goto out; - } - } - - pr_debug("couldn't find VLAN ID %d in bond %s\n", - vlan_id, bond->dev->name); - -out: - write_unlock_bh(&bond->lock); - unblock_netpoll_tx(); - return res; -} - -/** - * bond_next_vlan - safely skip to the next item in the vlans list. - * @bond: the bond we're working on - * @curr: item we're advancing from - * - * Returns %NULL if list is empty, bond->next_vlan if @curr is %NULL, - * or @curr->next otherwise (even if it is @curr itself again). - * - * Caller must hold bond->lock - */ -struct vlan_entry *bond_next_vlan(struct bonding *bond, struct vlan_entry *curr) -{ - struct vlan_entry *next, *last; - - if (list_empty(&bond->vlan_list)) - return NULL; - - if (!curr) { - next = list_entry(bond->vlan_list.next, - struct vlan_entry, vlan_list); - } else { - last = list_entry(bond->vlan_list.prev, - struct vlan_entry, vlan_list); - if (last == curr) { - next = list_entry(bond->vlan_list.next, - struct vlan_entry, vlan_list); - } else { - next = list_entry(curr->vlan_list.next, - struct vlan_entry, vlan_list); - } - } - - return next; -} - -/** * bond_dev_queue_xmit - Prepare skb for xmit. * * @bond: bond device that got this skb for tx. @@ -441,28 +332,20 @@ static int bond_vlan_rx_add_vid(struct net_device *bond_dev, __be16 proto, u16 vid) { struct bonding *bond = netdev_priv(bond_dev); - struct slave *slave, *stop_at; - int i, res; + struct slave *slave; + int res; - bond_for_each_slave(bond, slave, i) { + bond_for_each_slave(bond, slave) { res = vlan_vid_add(slave->dev, proto, vid); if (res) goto unwind; } - res = bond_add_vlan(bond, vid); - if (res) { - pr_err("%s: Error: Failed to add vlan id %d\n", - bond_dev->name, vid); - return res; - } - return 0; unwind: - /* unwind from head to the slave that failed */ - stop_at = slave; - bond_for_each_slave_from_to(bond, slave, i, bond->first_slave, stop_at) + /* unwind from the slave that failed */ + bond_for_each_slave_continue_reverse(bond, slave) vlan_vid_del(slave->dev, proto, vid); return res; @@ -478,48 +361,16 @@ static int bond_vlan_rx_kill_vid(struct net_device *bond_dev, { struct bonding *bond = netdev_priv(bond_dev); struct slave *slave; - int i, res; - bond_for_each_slave(bond, slave, i) + bond_for_each_slave(bond, slave) vlan_vid_del(slave->dev, proto, vid); - res = bond_del_vlan(bond, vid); - if (res) { - pr_err("%s: Error: Failed to remove vlan id %d\n", - bond_dev->name, vid); - return res; - } + if (bond_is_lb(bond)) + bond_alb_clear_vlan(bond, vid); return 0; } -static void bond_add_vlans_on_slave(struct bonding *bond, struct net_device *slave_dev) -{ - struct vlan_entry *vlan; - int res; - - list_for_each_entry(vlan, &bond->vlan_list, vlan_list) { - res = vlan_vid_add(slave_dev, htons(ETH_P_8021Q), - vlan->vlan_id); - if (res) - pr_warning("%s: Failed to add vlan id %d to device %s\n", - bond->dev->name, vlan->vlan_id, - slave_dev->name); - } -} - -static void bond_del_vlans_from_slave(struct bonding *bond, - struct net_device *slave_dev) -{ - struct vlan_entry *vlan; - - list_for_each_entry(vlan, &bond->vlan_list, vlan_list) { - if (!vlan->vlan_id) - continue; - vlan_vid_del(slave_dev, htons(ETH_P_8021Q), vlan->vlan_id); - } -} - /*------------------------------- Link status -------------------------------*/ /* @@ -532,15 +383,14 @@ static void bond_del_vlans_from_slave(struct bonding *bond, static int bond_set_carrier(struct bonding *bond) { struct slave *slave; - int i; - if (bond->slave_cnt == 0) + if (list_empty(&bond->slave_list)) goto down; if (bond->params.mode == BOND_MODE_8023AD) return bond_3ad_set_carrier(bond); - bond_for_each_slave(bond, slave, i) { + bond_for_each_slave(bond, slave) { if (slave->link == BOND_LINK_UP) { if (!netif_carrier_ok(bond->dev)) { netif_carrier_on(bond->dev); @@ -681,8 +531,8 @@ static int bond_set_promiscuity(struct bonding *bond, int inc) } } else { struct slave *slave; - int i; - bond_for_each_slave(bond, slave, i) { + + bond_for_each_slave(bond, slave) { err = dev_set_promiscuity(slave->dev, inc); if (err) return err; @@ -705,8 +555,8 @@ static int bond_set_allmulti(struct bonding *bond, int inc) } } else { struct slave *slave; - int i; - bond_for_each_slave(bond, slave, i) { + + bond_for_each_slave(bond, slave) { err = dev_set_allmulti(slave->dev, inc); if (err) return err; @@ -715,15 +565,6 @@ static int bond_set_allmulti(struct bonding *bond, int inc) return err; } -static void __bond_resend_igmp_join_requests(struct net_device *dev) -{ - struct in_device *in_dev; - - in_dev = __in_dev_get_rcu(dev); - if (in_dev) - ip_mc_rejoin_groups(in_dev); -} - /* * Retrieve the list of registered multicast addresses for the bonding * device and retransmit an IGMP JOIN request to the current active @@ -731,33 +572,12 @@ static void __bond_resend_igmp_join_requests(struct net_device *dev) */ static void bond_resend_igmp_join_requests(struct bonding *bond) { - struct net_device *bond_dev, *vlan_dev, *upper_dev; - struct vlan_entry *vlan; - - read_lock(&bond->lock); - rcu_read_lock(); - - bond_dev = bond->dev; - - /* rejoin all groups on bond device */ - __bond_resend_igmp_join_requests(bond_dev); - - /* - * if bond is enslaved to a bridge, - * then rejoin all groups on its master - */ - upper_dev = netdev_master_upper_dev_get_rcu(bond_dev); - if (upper_dev && upper_dev->priv_flags & IFF_EBRIDGE) - __bond_resend_igmp_join_requests(upper_dev); - - /* rejoin all groups on vlan devices */ - list_for_each_entry(vlan, &bond->vlan_list, vlan_list) { - vlan_dev = __vlan_find_dev_deep(bond_dev, htons(ETH_P_8021Q), - vlan->vlan_id); - if (vlan_dev) - __bond_resend_igmp_join_requests(vlan_dev); + if (!rtnl_trylock()) { + queue_delayed_work(bond->wq, &bond->mcast_work, 1); + return; } - rcu_read_unlock(); + call_netdevice_notifiers(NETDEV_RESEND_IGMP, bond->dev); + rtnl_unlock(); /* We use curr_slave_lock to protect against concurrent access to * igmp_retrans from multiple running instances of this function and @@ -769,7 +589,6 @@ static void bond_resend_igmp_join_requests(struct bonding *bond) queue_delayed_work(bond->wq, &bond->mcast_work, HZ/5); } write_unlock_bh(&bond->curr_slave_lock); - read_unlock(&bond->lock); } static void bond_resend_igmp_join_requests_delayed(struct work_struct *work) @@ -808,6 +627,8 @@ static void bond_hw_addr_flush(struct net_device *bond_dev, static void bond_hw_addr_swap(struct bonding *bond, struct slave *new_active, struct slave *old_active) { + ASSERT_RTNL(); + if (old_active) { if (bond->dev->flags & IFF_PROMISC) dev_set_promiscuity(old_active->dev, -1); @@ -966,9 +787,8 @@ static struct slave *bond_find_best_slave(struct bonding *bond) new_active = bond->curr_active_slave; if (!new_active) { /* there were no active slaves left */ - if (bond->slave_cnt > 0) /* found one slave */ - new_active = bond->first_slave; - else + new_active = bond_first_slave(bond); + if (!new_active) return NULL; /* still no slave, return NULL */ } @@ -1008,7 +828,6 @@ static bool bond_should_notify_peers(struct bonding *bond) test_bit(__LINK_STATE_LINKWATCH_PENDING, &slave->dev->state)) return false; - bond->send_peer_notif--; return true; } @@ -1071,7 +890,7 @@ void bond_change_active_slave(struct bonding *bond, struct slave *new_active) if (new_active) bond_set_slave_active_flags(new_active); } else { - bond->curr_active_slave = new_active; + rcu_assign_pointer(bond->curr_active_slave, new_active); } if (bond->params.mode == BOND_MODE_ACTIVEBACKUP) { @@ -1115,7 +934,7 @@ void bond_change_active_slave(struct bonding *bond, struct slave *new_active) ((USES_PRIMARY(bond->params.mode) && new_active) || bond->params.mode == BOND_MODE_ROUNDROBIN)) { bond->igmp_retrans = bond->params.resend_igmp; - queue_delayed_work(bond->wq, &bond->mcast_work, 0); + queue_delayed_work(bond->wq, &bond->mcast_work, 1); } } @@ -1161,17 +980,7 @@ void bond_select_active_slave(struct bonding *bond) */ static void bond_attach_slave(struct bonding *bond, struct slave *new_slave) { - if (bond->first_slave == NULL) { /* attaching the first slave */ - new_slave->next = new_slave; - new_slave->prev = new_slave; - bond->first_slave = new_slave; - } else { - new_slave->next = bond->first_slave; - new_slave->prev = bond->first_slave->prev; - new_slave->next->prev = new_slave; - new_slave->prev->next = new_slave; - } - + list_add_tail_rcu(&new_slave->list, &bond->slave_list); bond->slave_cnt++; } @@ -1187,22 +996,7 @@ static void bond_attach_slave(struct bonding *bond, struct slave *new_slave) */ static void bond_detach_slave(struct bonding *bond, struct slave *slave) { - if (slave->next) - slave->next->prev = slave->prev; - - if (slave->prev) - slave->prev->next = slave->next; - - if (bond->first_slave == slave) { /* slave is the first slave */ - if (bond->slave_cnt > 1) { /* there are more slave */ - bond->first_slave = slave->next; - } else { - bond->first_slave = NULL; /* slave was the last one */ - } - } - - slave->next = NULL; - slave->prev = NULL; + list_del_rcu(&slave->list); bond->slave_cnt--; } @@ -1249,47 +1043,31 @@ static void bond_poll_controller(struct net_device *bond_dev) { } -static void __bond_netpoll_cleanup(struct bonding *bond) +static void bond_netpoll_cleanup(struct net_device *bond_dev) { + struct bonding *bond = netdev_priv(bond_dev); struct slave *slave; - int i; - bond_for_each_slave(bond, slave, i) + bond_for_each_slave(bond, slave) 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, gfp_t gfp) { struct bonding *bond = netdev_priv(dev); struct slave *slave; - int i, err = 0; + int err = 0; - read_lock(&bond->lock); - bond_for_each_slave(bond, slave, i) { + bond_for_each_slave(bond, slave) { err = slave_enable_netpoll(slave); if (err) { - __bond_netpoll_cleanup(bond); + bond_netpoll_cleanup(dev); break; } } - read_unlock(&bond->lock); return err; } - -static struct netpoll_info *bond_netpoll_info(struct bonding *bond) -{ - return bond->dev->npinfo; -} - #else static inline int slave_enable_netpoll(struct slave *slave) { @@ -1306,34 +1084,29 @@ static void bond_netpoll_cleanup(struct net_device *bond_dev) /*---------------------------------- IOCTL ----------------------------------*/ static netdev_features_t bond_fix_features(struct net_device *dev, - netdev_features_t features) + netdev_features_t features) { - struct slave *slave; struct bonding *bond = netdev_priv(dev); netdev_features_t mask; - int i; - - read_lock(&bond->lock); + struct slave *slave; - if (!bond->first_slave) { + if (list_empty(&bond->slave_list)) { /* Disable adding VLANs to empty bond. But why? --mq */ features |= NETIF_F_VLAN_CHALLENGED; - goto out; + return features; } mask = features; features &= ~NETIF_F_ONE_FOR_ALL; features |= NETIF_F_ALL_FOR_ALL; - bond_for_each_slave(bond, slave, i) { + bond_for_each_slave(bond, slave) { features = netdev_increment_features(features, slave->dev->features, mask); } features = netdev_add_tso_features(features, mask); -out: - read_unlock(&bond->lock); return features; } @@ -1343,21 +1116,18 @@ out: static void bond_compute_features(struct bonding *bond) { - struct slave *slave; - struct net_device *bond_dev = bond->dev; + unsigned int flags, dst_release_flag = IFF_XMIT_DST_RELEASE; netdev_features_t vlan_features = BOND_VLAN_FEATURES; unsigned short max_hard_header_len = ETH_HLEN; unsigned int gso_max_size = GSO_MAX_SIZE; + struct net_device *bond_dev = bond->dev; u16 gso_max_segs = GSO_MAX_SEGS; - int i; - unsigned int flags, dst_release_flag = IFF_XMIT_DST_RELEASE; - - read_lock(&bond->lock); + struct slave *slave; - if (!bond->first_slave) + if (list_empty(&bond->slave_list)) goto done; - bond_for_each_slave(bond, slave, i) { + bond_for_each_slave(bond, slave) { vlan_features = netdev_increment_features(vlan_features, slave->dev->vlan_features, BOND_VLAN_FEATURES); @@ -1378,8 +1148,6 @@ done: flags = bond_dev->priv_flags & ~IFF_XMIT_DST_RELEASE; bond_dev->priv_flags = flags | dst_release_flag; - read_unlock(&bond->lock); - netdev_change_features(bond_dev); } @@ -1545,7 +1313,7 @@ int bond_enslave(struct net_device *bond_dev, struct net_device *slave_dev) * bond ether type mutual exclusion - don't allow slaves of dissimilar * ether type (eg ARPHRD_ETHER and ARPHRD_INFINIBAND) share the same bond */ - if (bond->slave_cnt == 0) { + if (list_empty(&bond->slave_list)) { if (bond_dev->type != slave_dev->type) { pr_debug("%s: change device type from %d to %d\n", bond_dev->name, @@ -1584,7 +1352,7 @@ int bond_enslave(struct net_device *bond_dev, struct net_device *slave_dev) } if (slave_ops->ndo_set_mac_address == NULL) { - if (bond->slave_cnt == 0) { + if (list_empty(&bond->slave_list)) { pr_warning("%s: Warning: The first slave device specified does not support setting the MAC address. Setting fail_over_mac to active.", bond_dev->name); bond->params.fail_over_mac = BOND_FOM_ACTIVE; @@ -1600,7 +1368,8 @@ 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 && bond->dev->addr_assign_type == NET_ADDR_RANDOM) + if (list_empty(&bond->slave_list) && + bond->dev->addr_assign_type == NET_ADDR_RANDOM) bond_set_dev_addr(bond->dev, slave_dev); new_slave = kzalloc(sizeof(struct slave), GFP_KERNEL); @@ -1608,7 +1377,7 @@ int bond_enslave(struct net_device *bond_dev, struct net_device *slave_dev) res = -ENOMEM; goto err_undo_flags; } - + INIT_LIST_HEAD(&new_slave->list); /* * Set the new_slave's queue_id to be zero. Queue ID mapping * is set via sysfs or module option if desired. @@ -1703,7 +1472,12 @@ int bond_enslave(struct net_device *bond_dev, struct net_device *slave_dev) dev_mc_add(slave_dev, lacpdu_multicast); } - bond_add_vlans_on_slave(bond, slave_dev); + 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; + } write_lock_bh(&bond->lock); @@ -1794,15 +1568,18 @@ int bond_enslave(struct net_device *bond_dev, struct net_device *slave_dev) */ bond_set_slave_inactive_flags(new_slave); /* if this is the first slave */ - if (bond->slave_cnt == 1) { + if (bond_first_slave(bond) == new_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); } else { + struct slave *prev_slave; + + prev_slave = bond_prev_slave(bond, new_slave); SLAVE_AD_INFO(new_slave).id = - SLAVE_AD_INFO(new_slave->prev).id + 1; + SLAVE_AD_INFO(prev_slave).id + 1; } bond_3ad_bind_slave(new_slave); @@ -1824,7 +1601,7 @@ int bond_enslave(struct net_device *bond_dev, struct net_device *slave_dev) * so we can change it without calling change_active_interface() */ if (!bond->curr_active_slave && new_slave->link == BOND_LINK_UP) - bond->curr_active_slave = new_slave; + rcu_assign_pointer(bond->curr_active_slave, new_slave); break; } /* switch(bond_mode) */ @@ -1834,7 +1611,7 @@ int bond_enslave(struct net_device *bond_dev, struct net_device *slave_dev) bond_set_carrier(bond); #ifdef CONFIG_NET_POLL_CONTROLLER - slave_dev->npinfo = bond_netpoll_info(bond); + slave_dev->npinfo = bond->dev->npinfo; if (slave_dev->npinfo) { if (slave_enable_netpoll(new_slave)) { read_unlock(&bond->lock); @@ -1876,7 +1653,7 @@ err_detach: if (!USES_PRIMARY(bond->params.mode)) bond_hw_addr_flush(bond_dev, slave_dev); - bond_del_vlans_from_slave(bond, slave_dev); + vlan_vids_del_by_dev(slave_dev, bond_dev); write_lock_bh(&bond->lock); bond_detach_slave(bond, new_slave); if (bond->primary_slave == new_slave) @@ -1921,7 +1698,7 @@ err_free: err_undo_flags: bond_compute_features(bond); /* Enslave of first slave has failed and we need to fix master's mac */ - if (bond->slave_cnt == 0 && + if (list_empty(&bond->slave_list) && ether_addr_equal(bond_dev->dev_addr, slave_dev->dev_addr)) eth_hw_addr_random(bond_dev); @@ -1977,15 +1754,6 @@ static int __bond_release_one(struct net_device *bond_dev, netdev_rx_handler_unregister(slave_dev); write_lock_bh(&bond->lock); - if (!all && !bond->params.fail_over_mac) { - if (ether_addr_equal(bond_dev->dev_addr, slave->perm_hwaddr) && - bond->slave_cnt > 1) - pr_warning("%s: Warning: the permanent HWaddr of %s - %pM - is still in use by %s. Set the HWaddr of %s to a different address to avoid conflicts.\n", - bond_dev->name, slave_dev->name, - slave->perm_hwaddr, - bond_dev->name, slave_dev->name); - } - /* Inform AD package of unbinding of slave. */ if (bond->params.mode == BOND_MODE_8023AD) { /* must be called before the slave is @@ -2006,6 +1774,15 @@ static int __bond_release_one(struct net_device *bond_dev, /* release the slave from its bond */ bond_detach_slave(bond, slave); + if (!all && !bond->params.fail_over_mac) { + if (ether_addr_equal(bond_dev->dev_addr, slave->perm_hwaddr) && + !list_empty(&bond->slave_list)) + 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) bond->primary_slave = NULL; @@ -2024,7 +1801,7 @@ static int __bond_release_one(struct net_device *bond_dev, } if (all) { - bond->curr_active_slave = NULL; + rcu_assign_pointer(bond->curr_active_slave, NULL); } else if (oldcurrent == slave) { /* * Note that we hold RTNL over this sequence, so there @@ -2042,11 +1819,11 @@ static int __bond_release_one(struct net_device *bond_dev, write_lock_bh(&bond->lock); } - if (bond->slave_cnt == 0) { + if (list_empty(&bond->slave_list)) { bond_set_carrier(bond); eth_hw_addr_random(bond_dev); - if (bond_vlan_used(bond)) { + if (vlan_uses_dev(bond_dev)) { pr_warning("%s: Warning: clearing HW address of %s while it still has VLANs.\n", bond_dev->name, bond_dev->name); pr_warning("%s: When re-adding slaves, make sure the bond's HW address matches its VLANs'.\n", @@ -2056,8 +1833,9 @@ static int __bond_release_one(struct net_device *bond_dev, write_unlock_bh(&bond->lock); unblock_netpoll_tx(); + synchronize_rcu(); - if (bond->slave_cnt == 0) { + if (list_empty(&bond->slave_list)) { call_netdevice_notifiers(NETDEV_CHANGEADDR, bond->dev); call_netdevice_notifiers(NETDEV_RELEASE, bond->dev); } @@ -2071,7 +1849,7 @@ static int __bond_release_one(struct net_device *bond_dev, /* must do this from outside any spinlocks */ bond_destroy_slave_symlinks(bond_dev, slave_dev); - bond_del_vlans_from_slave(bond, slave_dev); + vlan_vids_del_by_dev(slave_dev, bond_dev); /* If the mode USES_PRIMARY, then this cases was handled above by * bond_change_active_slave(..., NULL) @@ -2128,7 +1906,7 @@ static int bond_release_and_destroy(struct net_device *bond_dev, int ret; ret = bond_release(bond_dev, slave_dev); - if ((ret == 0) && (bond->slave_cnt == 0)) { + if (ret == 0 && list_empty(&bond->slave_list)) { bond_dev->priv_flags |= IFF_DISABLE_NETPOLL; pr_info("%s: destroying bond %s.\n", bond_dev->name, bond_dev->name); @@ -2165,23 +1943,19 @@ static int bond_ioctl_change_active(struct net_device *bond_dev, struct net_devi read_lock(&bond->lock); - read_lock(&bond->curr_slave_lock); old_active = bond->curr_active_slave; - read_unlock(&bond->curr_slave_lock); - new_active = bond_get_slave_by_dev(bond, slave_dev); - /* * Changing to the current active: do nothing; return success. */ - if (new_active && (new_active == old_active)) { + if (new_active && new_active == old_active) { read_unlock(&bond->lock); return 0; } - if ((new_active) && - (old_active) && - (new_active->link == BOND_LINK_UP) && + if (new_active && + old_active && + new_active->link == BOND_LINK_UP && IS_UP(new_active->dev)) { block_netpoll_tx(); write_lock_bh(&bond->curr_slave_lock); @@ -2213,13 +1987,12 @@ static int bond_info_query(struct net_device *bond_dev, struct ifbond *info) static int bond_slave_info_query(struct net_device *bond_dev, struct ifslave *info) { struct bonding *bond = netdev_priv(bond_dev); + int i = 0, res = -ENODEV; struct slave *slave; - int i, res = -ENODEV; read_lock(&bond->lock); - - bond_for_each_slave(bond, slave, i) { - if (i == (int)info->slave_id) { + bond_for_each_slave(bond, slave) { + if (i++ == (int)info->slave_id) { res = 0; strcpy(info->slave_name, slave->dev->name); info->link = slave->link; @@ -2228,7 +2001,6 @@ static int bond_slave_info_query(struct net_device *bond_dev, struct ifslave *in break; } } - read_unlock(&bond->lock); return res; @@ -2239,13 +2011,13 @@ static int bond_slave_info_query(struct net_device *bond_dev, struct ifslave *in static int bond_miimon_inspect(struct bonding *bond) { + int link_state, commit = 0; struct slave *slave; - int i, link_state, commit = 0; bool ignore_updelay; ignore_updelay = !bond->curr_active_slave ? true : false; - bond_for_each_slave(bond, slave, i) { + bond_for_each_slave(bond, slave) { slave->new_link = BOND_LINK_NOCHANGE; link_state = bond_check_dev_link(bond, slave->dev, 0); @@ -2340,9 +2112,8 @@ static int bond_miimon_inspect(struct bonding *bond) static void bond_miimon_commit(struct bonding *bond) { struct slave *slave; - int i; - bond_for_each_slave(bond, slave, i) { + bond_for_each_slave(bond, slave) { switch (slave->new_link) { case BOND_LINK_NOCHANGE: continue; @@ -2447,7 +2218,7 @@ void bond_mii_monitor(struct work_struct *work) delay = msecs_to_jiffies(bond->params.miimon); - if (bond->slave_cnt == 0) + if (list_empty(&bond->slave_list)) goto re_arm; should_notify_peers = bond_should_notify_peers(bond); @@ -2479,35 +2250,32 @@ re_arm: read_unlock(&bond->lock); if (should_notify_peers) { - if (!rtnl_trylock()) { - read_lock(&bond->lock); - bond->send_peer_notif++; - read_unlock(&bond->lock); + if (!rtnl_trylock()) return; - } call_netdevice_notifiers(NETDEV_NOTIFY_PEERS, bond->dev); rtnl_unlock(); } } -static int bond_has_this_ip(struct bonding *bond, __be32 ip) +static bool bond_has_this_ip(struct bonding *bond, __be32 ip) { - struct vlan_entry *vlan; - struct net_device *vlan_dev; + struct net_device *upper; + struct list_head *iter; + bool ret = false; if (ip == bond_confirm_addr(bond->dev, 0, ip)) - return 1; + return true; - list_for_each_entry(vlan, &bond->vlan_list, vlan_list) { - rcu_read_lock(); - vlan_dev = __vlan_find_dev_deep(bond->dev, htons(ETH_P_8021Q), - vlan->vlan_id); - rcu_read_unlock(); - if (vlan_dev && ip == bond_confirm_addr(vlan_dev, 0, ip)) - return 1; + rcu_read_lock(); + netdev_for_each_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; } /* @@ -2542,81 +2310,79 @@ 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; - __be32 *targets = bond->params.arp_targets; - struct vlan_entry *vlan; - struct net_device *vlan_dev = NULL; + struct net_device *upper, *vlan_upper; + struct list_head *iter, *vlan_iter; struct rtable *rt; + __be32 *targets = bond->params.arp_targets, addr; + int i, vlan_id; - for (i = 0; (i < BOND_MAX_ARP_TARGETS); i++) { - __be32 addr; - if (!targets[i]) - break; + for (i = 0; i < BOND_MAX_ARP_TARGETS && targets[i]; i++) { pr_debug("basa: target %pI4\n", &targets[i]); - if (!bond_vlan_used(bond)) { - pr_debug("basa: empty vlan: arp_send\n"); - addr = bond_confirm_addr(bond->dev, targets[i], 0); - bond_arp_send(slave->dev, ARPOP_REQUEST, targets[i], - addr, 0); - continue; - } - /* - * If VLANs are configured, we do a route lookup to - * determine which VLAN interface would be used, so we - * can tag the ARP with the proper VLAN tag. - */ + /* 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)) { - if (net_ratelimit()) { - pr_warning("%s: no route to arp_ip_target %pI4\n", - bond->dev->name, &targets[i]); - } + pr_debug("%s: no route to arp_ip_target %pI4\n", + bond->dev->name, &targets[i]); continue; } - /* - * This target is not on a VLAN + vlan_id = 0; + + /* bond device itself */ + if (rt->dst.dev == bond->dev) + goto found; + + rcu_read_lock(); + /* first we search only for vlan devices. for every vlan + * found we verify its upper dev list, searching for the + * rt->dst.dev. If found we save the tag of the vlan and + * proceed to send the packet. + * + * TODO: QinQ? */ - if (rt->dst.dev == bond->dev) { - ip_rt_put(rt); - pr_debug("basa: rtdev == bond->dev: arp_send\n"); - addr = bond_confirm_addr(bond->dev, targets[i], 0); - bond_arp_send(slave->dev, ARPOP_REQUEST, targets[i], - addr, 0); - continue; + netdev_for_each_upper_dev_rcu(bond->dev, vlan_upper, vlan_iter) { + if (!is_vlan_dev(vlan_upper)) + continue; + netdev_for_each_upper_dev_rcu(vlan_upper, upper, iter) { + if (upper == rt->dst.dev) { + vlan_id = vlan_dev_vlan_id(vlan_upper); + rcu_read_unlock(); + goto found; + } + } } - vlan_id = 0; - list_for_each_entry(vlan, &bond->vlan_list, vlan_list) { - rcu_read_lock(); - vlan_dev = __vlan_find_dev_deep(bond->dev, - htons(ETH_P_8021Q), - vlan->vlan_id); - rcu_read_unlock(); - if (vlan_dev == rt->dst.dev) { - vlan_id = vlan->vlan_id; - pr_debug("basa: vlan match on %s %d\n", - vlan_dev->name, vlan_id); - break; + /* if the device we're looking for is not on top of any of + * our upper vlans, then just search for any dev that + * matches, and in case it's a vlan - save the id + */ + netdev_for_each_upper_dev_rcu(bond->dev, upper, iter) { + if (upper == rt->dst.dev) { + /* if it's a vlan - get its VID */ + if (is_vlan_dev(upper)) + vlan_id = vlan_dev_vlan_id(upper); + + rcu_read_unlock(); + goto found; } } + rcu_read_unlock(); - if (vlan_id && vlan_dev) { - ip_rt_put(rt); - addr = bond_confirm_addr(vlan_dev, targets[i], 0); - bond_arp_send(slave->dev, ARPOP_REQUEST, targets[i], - addr, vlan_id); - continue; - } + /* 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 (net_ratelimit()) { - pr_warning("%s: no path to arp_ip_target %pI4 via rt.dev %s\n", - bond->dev->name, &targets[i], - rt->dst.dev ? rt->dst.dev->name : "NULL"); - } ip_rt_put(rt); + continue; + +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, vlan_id); } } @@ -2713,6 +2479,20 @@ out_unlock: 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); +} + /* * this function is called regularly to monitor each slave's link * ensuring that traffic is being sent and received when arp monitoring @@ -2726,21 +2506,13 @@ void bond_loadbalance_arp_mon(struct work_struct *work) arp_work.work); struct slave *slave, *oldcurrent; int do_failover = 0; - int delta_in_ticks, extra_ticks; - int i; read_lock(&bond->lock); - delta_in_ticks = msecs_to_jiffies(bond->params.arp_interval); - extra_ticks = delta_in_ticks / 2; - - if (bond->slave_cnt == 0) + if (list_empty(&bond->slave_list)) goto re_arm; - read_lock(&bond->curr_slave_lock); oldcurrent = bond->curr_active_slave; - read_unlock(&bond->curr_slave_lock); - /* see if any of the previous devices are up now (i.e. they have * xmt and rcv traffic). the curr_active_slave does not come into * the picture unless it is null. also, slave->jiffies is not needed @@ -2749,16 +2521,12 @@ void bond_loadbalance_arp_mon(struct work_struct *work) * 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(bond, slave) { unsigned long trans_start = dev_trans_start(slave->dev); if (slave->link != BOND_LINK_UP) { - if (time_in_range(jiffies, - trans_start - delta_in_ticks, - trans_start + delta_in_ticks + extra_ticks) && - time_in_range(jiffies, - slave->dev->last_rx - delta_in_ticks, - slave->dev->last_rx + delta_in_ticks + extra_ticks)) { + if (bond_time_in_interval(bond, trans_start, 1) && + bond_time_in_interval(bond, slave->dev->last_rx, 1)) { slave->link = BOND_LINK_UP; bond_set_active_slave(slave); @@ -2786,12 +2554,8 @@ void bond_loadbalance_arp_mon(struct work_struct *work) * when the source ip is 0, so don't take the link down * if we don't know our ip yet */ - if (!time_in_range(jiffies, - trans_start - delta_in_ticks, - trans_start + 2 * delta_in_ticks + extra_ticks) || - !time_in_range(jiffies, - slave->dev->last_rx - delta_in_ticks, - slave->dev->last_rx + 2 * delta_in_ticks + extra_ticks)) { + if (!bond_time_in_interval(bond, trans_start, 2) || + !bond_time_in_interval(bond, slave->dev->last_rx, 2)) { slave->link = BOND_LINK_DOWN; bond_set_backup_slave(slave); @@ -2831,7 +2595,8 @@ void bond_loadbalance_arp_mon(struct work_struct *work) re_arm: if (bond->params.arp_interval) - queue_delayed_work(bond->wq, &bond->arp_work, delta_in_ticks); + queue_delayed_work(bond->wq, &bond->arp_work, + msecs_to_jiffies(bond->params.arp_interval)); read_unlock(&bond->lock); } @@ -2844,32 +2609,21 @@ re_arm: * * Called with bond->lock held for read. */ -static int bond_ab_arp_inspect(struct bonding *bond, int delta_in_ticks) +static int bond_ab_arp_inspect(struct bonding *bond) { + unsigned long trans_start, last_rx; struct slave *slave; - int i, commit = 0; - unsigned long trans_start; - int extra_ticks; - - /* All the time comparisons below need some extra time. Otherwise, on - * fast networks the ARP probe/reply may arrive within the same jiffy - * as it was sent. Then, the next time the ARP monitor is run, one - * arp_interval will already have passed in the comparisons. - */ - extra_ticks = delta_in_ticks / 2; + int commit = 0; - bond_for_each_slave(bond, slave, i) { + bond_for_each_slave(bond, slave) { slave->new_link = BOND_LINK_NOCHANGE; + last_rx = slave_last_rx(bond, slave); if (slave->link != BOND_LINK_UP) { - if (time_in_range(jiffies, - slave_last_rx(bond, slave) - delta_in_ticks, - slave_last_rx(bond, slave) + delta_in_ticks + extra_ticks)) { - + if (bond_time_in_interval(bond, last_rx, 1)) { slave->new_link = BOND_LINK_UP; commit++; } - continue; } @@ -2878,9 +2632,7 @@ static int bond_ab_arp_inspect(struct bonding *bond, int delta_in_ticks) * active. This avoids bouncing, as the last receive * times need a full ARP monitor cycle to be updated. */ - if (time_in_range(jiffies, - slave->jiffies - delta_in_ticks, - slave->jiffies + 2 * delta_in_ticks + extra_ticks)) + if (bond_time_in_interval(bond, slave->jiffies, 2)) continue; /* @@ -2898,10 +2650,7 @@ static int bond_ab_arp_inspect(struct bonding *bond, int delta_in_ticks) */ if (!bond_is_active_slave(slave) && !bond->current_arp_slave && - !time_in_range(jiffies, - slave_last_rx(bond, slave) - delta_in_ticks, - slave_last_rx(bond, slave) + 3 * delta_in_ticks + extra_ticks)) { - + !bond_time_in_interval(bond, last_rx, 3)) { slave->new_link = BOND_LINK_DOWN; commit++; } @@ -2914,13 +2663,8 @@ static int bond_ab_arp_inspect(struct bonding *bond, int delta_in_ticks) */ trans_start = dev_trans_start(slave->dev); if (bond_is_active_slave(slave) && - (!time_in_range(jiffies, - trans_start - delta_in_ticks, - trans_start + 2 * delta_in_ticks + extra_ticks) || - !time_in_range(jiffies, - slave_last_rx(bond, slave) - delta_in_ticks, - slave_last_rx(bond, slave) + 2 * delta_in_ticks + extra_ticks))) { - + (!bond_time_in_interval(bond, trans_start, 2) || + !bond_time_in_interval(bond, last_rx, 2))) { slave->new_link = BOND_LINK_DOWN; commit++; } @@ -2935,24 +2679,21 @@ static int bond_ab_arp_inspect(struct bonding *bond, int delta_in_ticks) * * Called with RTNL and bond->lock for read. */ -static void bond_ab_arp_commit(struct bonding *bond, int delta_in_ticks) +static void bond_ab_arp_commit(struct bonding *bond) { - struct slave *slave; - int i; unsigned long trans_start; + struct slave *slave; - bond_for_each_slave(bond, slave, i) { + bond_for_each_slave(bond, slave) { switch (slave->new_link) { case BOND_LINK_NOCHANGE: continue; case BOND_LINK_UP: trans_start = dev_trans_start(slave->dev); - if ((!bond->curr_active_slave && - time_in_range(jiffies, - trans_start - delta_in_ticks, - trans_start + delta_in_ticks + delta_in_ticks / 2)) || - bond->curr_active_slave != slave) { + 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( @@ -3014,7 +2755,7 @@ do_failover: */ static void bond_ab_arp_probe(struct bonding *bond) { - struct slave *slave; + struct slave *slave, *next_slave; int i; read_lock(&bond->curr_slave_lock); @@ -3038,7 +2779,7 @@ static void bond_ab_arp_probe(struct bonding *bond) */ if (!bond->current_arp_slave) { - bond->current_arp_slave = bond->first_slave; + bond->current_arp_slave = bond_first_slave(bond); if (!bond->current_arp_slave) return; } @@ -3046,7 +2787,8 @@ static void bond_ab_arp_probe(struct bonding *bond) 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) { + next_slave = bond_next_slave(bond, bond->current_arp_slave); + bond_for_each_slave_from(bond, slave, i, next_slave) { if (IS_UP(slave->dev)) { slave->link = BOND_LINK_BACK; bond_set_slave_active_flags(slave); @@ -3087,12 +2829,12 @@ void bond_activebackup_arp_mon(struct work_struct *work) delta_in_ticks = msecs_to_jiffies(bond->params.arp_interval); - if (bond->slave_cnt == 0) + if (list_empty(&bond->slave_list)) goto re_arm; should_notify_peers = bond_should_notify_peers(bond); - if (bond_ab_arp_inspect(bond, delta_in_ticks)) { + if (bond_ab_arp_inspect(bond)) { read_unlock(&bond->lock); /* Race avoidance with bond_close flush of workqueue */ @@ -3105,7 +2847,7 @@ void bond_activebackup_arp_mon(struct work_struct *work) read_lock(&bond->lock); - bond_ab_arp_commit(bond, delta_in_ticks); + bond_ab_arp_commit(bond); read_unlock(&bond->lock); rtnl_unlock(); @@ -3121,12 +2863,8 @@ re_arm: read_unlock(&bond->lock); if (should_notify_peers) { - if (!rtnl_trylock()) { - read_lock(&bond->lock); - bond->send_peer_notif++; - read_unlock(&bond->lock); + if (!rtnl_trylock()) return; - } call_netdevice_notifiers(NETDEV_NOTIFY_PEERS, bond->dev); rtnl_unlock(); } @@ -3161,6 +2899,10 @@ static int bond_master_netdev_event(unsigned long event, 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; } @@ -3234,6 +2976,10 @@ static int bond_slave_netdev_event(unsigned long event, 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; } @@ -3403,13 +3149,12 @@ static int bond_open(struct net_device *bond_dev) { struct bonding *bond = netdev_priv(bond_dev); struct slave *slave; - int i; /* reset slave->backup and slave->inactive */ read_lock(&bond->lock); - if (bond->slave_cnt > 0) { + if (!list_empty(&bond->slave_list)) { read_lock(&bond->curr_slave_lock); - bond_for_each_slave(bond, slave, i) { + bond_for_each_slave(bond, slave) { if ((bond->params.mode == BOND_MODE_ACTIVEBACKUP) && (slave != bond->curr_active_slave)) { bond_set_slave_inactive_flags(slave); @@ -3455,17 +3200,10 @@ static int bond_close(struct net_device *bond_dev) { struct bonding *bond = netdev_priv(bond_dev); - write_lock_bh(&bond->lock); - bond->send_peer_notif = 0; - write_unlock_bh(&bond->lock); - bond_work_cancel_all(bond); - if (bond_is_lb(bond)) { - /* Must be called only after all - * slaves have been released - */ + bond->send_peer_notif = 0; + if (bond_is_lb(bond)) bond_alb_deinitialize(bond); - } bond->recv_probe = NULL; return 0; @@ -3477,13 +3215,11 @@ static struct rtnl_link_stats64 *bond_get_stats(struct net_device *bond_dev, struct bonding *bond = netdev_priv(bond_dev); struct rtnl_link_stats64 temp; struct slave *slave; - int i; memset(stats, 0, sizeof(*stats)); read_lock_bh(&bond->lock); - - bond_for_each_slave(bond, slave, i) { + bond_for_each_slave(bond, slave) { const struct rtnl_link_stats64 *sstats = dev_get_stats(slave->dev, &temp); @@ -3513,7 +3249,6 @@ static struct rtnl_link_stats64 *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; @@ -3652,41 +3387,35 @@ static void bond_set_rx_mode(struct net_device *bond_dev) { struct bonding *bond = netdev_priv(bond_dev); struct slave *slave; - int i; - read_lock(&bond->lock); + ASSERT_RTNL(); if (USES_PRIMARY(bond->params.mode)) { - read_lock(&bond->curr_slave_lock); - slave = bond->curr_active_slave; + slave = rtnl_dereference(bond->curr_active_slave); if (slave) { dev_uc_sync(slave->dev, bond_dev); dev_mc_sync(slave->dev, bond_dev); } - read_unlock(&bond->curr_slave_lock); } else { - bond_for_each_slave(bond, slave, i) { + bond_for_each_slave(bond, slave) { dev_uc_sync_multiple(slave->dev, bond_dev); dev_mc_sync_multiple(slave->dev, bond_dev); } } - - read_unlock(&bond->lock); } static int bond_neigh_init(struct neighbour *n) { struct bonding *bond = netdev_priv(n->dev); - struct slave *slave = bond->first_slave; const struct net_device_ops *slave_ops; struct neigh_parms parms; + struct slave *slave; int ret; + slave = bond_first_slave(bond); if (!slave) return 0; - slave_ops = slave->dev->netdev_ops; - if (!slave_ops->ndo_neigh_setup) return 0; @@ -3735,9 +3464,8 @@ static int bond_neigh_setup(struct net_device *dev, static int bond_change_mtu(struct net_device *bond_dev, int new_mtu) { struct bonding *bond = netdev_priv(bond_dev); - struct slave *slave, *stop_at; + struct slave *slave; int res = 0; - int i; pr_debug("bond=%p, name=%s, new_mtu=%d\n", bond, (bond_dev ? bond_dev->name : "None"), new_mtu); @@ -3757,10 +3485,10 @@ 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) { + bond_for_each_slave(bond, slave) { pr_debug("s %p s->p %p c_m %p\n", slave, - slave->prev, + bond_prev_slave(bond, slave), slave->dev->netdev_ops->ndo_change_mtu); res = dev_set_mtu(slave->dev, new_mtu); @@ -3785,8 +3513,7 @@ 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_continue_reverse(bond, slave) { int tmp_res; tmp_res = dev_set_mtu(slave->dev, bond_dev->mtu); @@ -3810,9 +3537,8 @@ static int bond_set_mac_address(struct net_device *bond_dev, void *addr) { struct bonding *bond = netdev_priv(bond_dev); struct sockaddr *sa = addr, tmp_sa; - struct slave *slave, *stop_at; + struct slave *slave; int res = 0; - int i; if (bond->params.mode == BOND_MODE_ALB) return bond_alb_set_mac_address(bond_dev, addr); @@ -3845,7 +3571,7 @@ 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) { + bond_for_each_slave(bond, slave) { const struct net_device_ops *slave_ops = slave->dev->netdev_ops; pr_debug("slave %p %s\n", slave, slave->dev->name); @@ -3877,8 +3603,7 @@ 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_continue_reverse(bond, slave) { int tmp_res; tmp_res = dev_set_mac_address(slave->dev, &tmp_sa); @@ -3891,12 +3616,50 @@ unwind: return res; } +/** + * 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. + */ +void bond_xmit_slave_id(struct bonding *bond, struct sk_buff *skb, int slave_id) +{ + struct slave *slave; + int i = slave_id; + + /* Here we start from the slave with slave_id */ + bond_for_each_slave_rcu(bond, slave) { + if (--i < 0) { + if (slave_can_tx(slave)) { + bond_dev_queue_xmit(bond, skb, slave->dev); + return; + } + } + } + + /* Here we start from the first slave up to slave_id */ + i = slave_id; + bond_for_each_slave_rcu(bond, slave) { + if (--i < 0) + break; + if (slave_can_tx(slave)) { + bond_dev_queue_xmit(bond, skb, slave->dev); + return; + } + } + /* no slave that can tx has been found */ + kfree_skb(skb); +} + static int bond_xmit_roundrobin(struct sk_buff *skb, struct net_device *bond_dev) { struct bonding *bond = netdev_priv(bond_dev); - struct slave *slave, *start_at; - int i, slave_no, res = 1; struct iphdr *iph = ip_hdr(skb); + struct slave *slave; /* * Start with the curr_active_slave that joined the bond as the @@ -3905,50 +3668,20 @@ static int bond_xmit_roundrobin(struct sk_buff *skb, struct net_device *bond_dev * send the join/membership reports. The curr_active_slave found * will send all of this type of traffic. */ - if ((iph->protocol == IPPROTO_IGMP) && - (skb->protocol == htons(ETH_P_IP))) { - - read_lock(&bond->curr_slave_lock); - slave = bond->curr_active_slave; - read_unlock(&bond->curr_slave_lock); - - if (!slave) - goto out; + if (iph->protocol == IPPROTO_IGMP && skb->protocol == htons(ETH_P_IP)) { + slave = rcu_dereference(bond->curr_active_slave); + if (slave && slave_can_tx(slave)) + bond_dev_queue_xmit(bond, skb, slave->dev); + else + bond_xmit_slave_id(bond, skb, 0); } else { - /* - * Concurrent TX may collide on rr_tx_counter; we accept - * that as being rare enough not to justify using an - * atomic op here. - */ - slave_no = bond->rr_tx_counter++ % bond->slave_cnt; - - bond_for_each_slave(bond, slave, i) { - slave_no--; - if (slave_no < 0) - break; - } - } - - start_at = slave; - bond_for_each_slave_from(bond, slave, i, start_at) { - if (IS_UP(slave->dev) && - (slave->link == BOND_LINK_UP) && - bond_is_active_slave(slave)) { - res = bond_dev_queue_xmit(bond, skb, slave->dev); - break; - } - } - -out: - if (res) { - /* no suitable interface, frame not sent */ - kfree_skb(skb); + bond_xmit_slave_id(bond, skb, + bond->rr_tx_counter++ % bond->slave_cnt); } return NETDEV_TX_OK; } - /* * in active-backup mode, we know that bond->curr_active_slave is always valid if * the bond has a usable interface. @@ -3956,18 +3689,12 @@ out: static int bond_xmit_activebackup(struct sk_buff *skb, struct net_device *bond_dev) { struct bonding *bond = netdev_priv(bond_dev); - int res = 1; - - read_lock(&bond->curr_slave_lock); - - if (bond->curr_active_slave) - res = bond_dev_queue_xmit(bond, skb, - bond->curr_active_slave->dev); - - read_unlock(&bond->curr_slave_lock); + struct slave *slave; - if (res) - /* no suitable interface, frame not sent */ + slave = rcu_dereference(bond->curr_active_slave); + if (slave) + bond_dev_queue_xmit(bond, skb, slave->dev); + else kfree_skb(skb); return NETDEV_TX_OK; @@ -3981,87 +3708,39 @@ static int bond_xmit_activebackup(struct sk_buff *skb, struct net_device *bond_d static int bond_xmit_xor(struct sk_buff *skb, struct net_device *bond_dev) { struct bonding *bond = netdev_priv(bond_dev); - struct slave *slave, *start_at; - int slave_no; - int i; - int res = 1; - slave_no = bond->xmit_hash_policy(skb, bond->slave_cnt); - - bond_for_each_slave(bond, slave, i) { - slave_no--; - if (slave_no < 0) - break; - } - - start_at = slave; - - bond_for_each_slave_from(bond, slave, i, start_at) { - if (IS_UP(slave->dev) && - (slave->link == BOND_LINK_UP) && - bond_is_active_slave(slave)) { - res = bond_dev_queue_xmit(bond, skb, slave->dev); - break; - } - } - - if (res) { - /* no suitable interface, frame not sent */ - kfree_skb(skb); - } + bond_xmit_slave_id(bond, skb, + bond->xmit_hash_policy(skb, bond->slave_cnt)); return NETDEV_TX_OK; } -/* - * in broadcast mode, we send everything to all usable interfaces. - */ +/* in broadcast mode, we send everything to all usable interfaces. */ static int bond_xmit_broadcast(struct sk_buff *skb, struct net_device *bond_dev) { struct bonding *bond = netdev_priv(bond_dev); - struct slave *slave, *start_at; - struct net_device *tx_dev = NULL; - int i; - int res = 1; - - read_lock(&bond->curr_slave_lock); - start_at = bond->curr_active_slave; - read_unlock(&bond->curr_slave_lock); - - if (!start_at) - goto out; + struct slave *slave = NULL; - bond_for_each_slave_from(bond, slave, i, start_at) { - if (IS_UP(slave->dev) && - (slave->link == BOND_LINK_UP) && - bond_is_active_slave(slave)) { - if (tx_dev) { - struct sk_buff *skb2 = skb_clone(skb, GFP_ATOMIC); - if (!skb2) { - pr_err("%s: Error: bond_xmit_broadcast(): skb_clone() failed\n", - bond_dev->name); - continue; - } + bond_for_each_slave_rcu(bond, slave) { + if (bond_is_last_slave(bond, slave)) + break; + if (IS_UP(slave->dev) && slave->link == BOND_LINK_UP) { + struct sk_buff *skb2 = skb_clone(skb, GFP_ATOMIC); - res = bond_dev_queue_xmit(bond, skb2, tx_dev); - if (res) { - kfree_skb(skb2); - continue; - } + if (!skb2) { + pr_err("%s: Error: bond_xmit_broadcast(): skb_clone() failed\n", + bond_dev->name); + continue; } - tx_dev = slave->dev; + /* bond_dev_queue_xmit always returns 0 */ + bond_dev_queue_xmit(bond, skb2, slave->dev); } } - - if (tx_dev) - res = bond_dev_queue_xmit(bond, skb, tx_dev); - -out: - if (res) - /* no suitable interface, frame not sent */ + if (slave && IS_UP(slave->dev) && slave->link == BOND_LINK_UP) + bond_dev_queue_xmit(bond, skb, slave->dev); + else kfree_skb(skb); - /* frame sent to all suitable interfaces */ return NETDEV_TX_OK; } @@ -4089,15 +3768,15 @@ static void bond_set_xmit_hash_policy(struct bonding *bond) static inline int bond_slave_override(struct bonding *bond, struct sk_buff *skb) { - int i, res = 1; struct slave *slave = NULL; struct slave *check_slave; + int res = 1; if (!skb->queue_mapping) return 1; /* Find out if any slaves have the same mapping as this skb. */ - bond_for_each_slave(bond, check_slave, i) { + bond_for_each_slave_rcu(bond, check_slave) { if (check_slave->queue_id == skb->queue_mapping) { slave = check_slave; break; @@ -4182,14 +3861,12 @@ static netdev_tx_t bond_start_xmit(struct sk_buff *skb, struct net_device *dev) if (is_netpoll_tx_blocked(dev)) return NETDEV_TX_BUSY; - read_lock(&bond->lock); - - if (bond->slave_cnt) + rcu_read_lock(); + if (!list_empty(&bond->slave_list)) ret = __bond_start_xmit(skb, dev); else kfree_skb(skb); - - read_unlock(&bond->lock); + rcu_read_unlock(); return ret; } @@ -4230,9 +3907,8 @@ static int bond_ethtool_get_settings(struct net_device *bond_dev, struct ethtool_cmd *ecmd) { struct bonding *bond = netdev_priv(bond_dev); - struct slave *slave; - int i; unsigned long speed = 0; + struct slave *slave; ecmd->duplex = DUPLEX_UNKNOWN; ecmd->port = PORT_OTHER; @@ -4243,7 +3919,7 @@ static int bond_ethtool_get_settings(struct net_device *bond_dev, * this is an accurate maximum. */ read_lock(&bond->lock); - bond_for_each_slave(bond, slave, i) { + bond_for_each_slave(bond, slave) { if (SLAVE_IS_OK(slave)) { if (slave->speed != SPEED_UNKNOWN) speed += slave->speed; @@ -4254,6 +3930,7 @@ static int bond_ethtool_get_settings(struct net_device *bond_dev, } ethtool_cmd_speed_set(ecmd, speed ? : SPEED_UNKNOWN); read_unlock(&bond->lock); + return 0; } @@ -4317,12 +3994,11 @@ static void bond_setup(struct net_device *bond_dev) /* initialize rwlocks */ rwlock_init(&bond->lock); rwlock_init(&bond->curr_slave_lock); - + INIT_LIST_HEAD(&bond->slave_list); bond->params = bonding_defaults; /* Initialize pointers */ bond->dev = bond_dev; - INIT_LIST_HEAD(&bond->vlan_list); /* Initialize the device entry points */ ether_setup(bond_dev); @@ -4374,23 +4050,18 @@ static void bond_setup(struct net_device *bond_dev) static void bond_uninit(struct net_device *bond_dev) { struct bonding *bond = netdev_priv(bond_dev); - struct vlan_entry *vlan, *tmp; + struct slave *slave, *tmp_slave; bond_netpoll_cleanup(bond_dev); /* Release the bonded slaves */ - while (bond->first_slave != NULL) - __bond_release_one(bond_dev, bond->first_slave->dev, true); + list_for_each_entry_safe(slave, tmp_slave, &bond->slave_list, list) + __bond_release_one(bond_dev, slave->dev, true); pr_info("%s: released all slaves\n", bond_dev->name); list_del(&bond->bond_list); bond_debug_unregister(bond); - - list_for_each_entry_safe(vlan, tmp, &bond->vlan_list, vlan_list) { - list_del(&vlan->vlan_list); - kfree(vlan); - } } /*------------------------- Module initialization ---------------------------*/ diff --git a/drivers/net/bonding/bond_procfs.c b/drivers/net/bonding/bond_procfs.c index 4060d41f0ee7..20a6ee25bb63 100644 --- a/drivers/net/bonding/bond_procfs.c +++ b/drivers/net/bonding/bond_procfs.c @@ -12,7 +12,6 @@ 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; /* make sure the bond won't be taken away */ rcu_read_lock(); @@ -21,10 +20,9 @@ static void *bond_info_seq_start(struct seq_file *seq, loff_t *pos) if (*pos == 0) return SEQ_START_TOKEN; - bond_for_each_slave(bond, slave, i) { + bond_for_each_slave(bond, slave) if (++off == *pos) return slave; - } return NULL; } @@ -36,11 +34,13 @@ static void *bond_info_seq_next(struct seq_file *seq, void *v, loff_t *pos) ++*pos; if (v == SEQ_START_TOKEN) - return bond->first_slave; + return bond_first_slave(bond); - slave = slave->next; + if (bond_is_last_slave(bond, slave)) + return NULL; + slave = bond_next_slave(bond, slave); - return (slave == bond->first_slave) ? NULL : slave; + return slave; } static void bond_info_seq_stop(struct seq_file *seq, void *v) diff --git a/drivers/net/bonding/bond_sysfs.c b/drivers/net/bonding/bond_sysfs.c index dc36a3d7d9e9..ce4677668e2c 100644 --- a/drivers/net/bonding/bond_sysfs.c +++ b/drivers/net/bonding/bond_sysfs.c @@ -209,12 +209,12 @@ void bond_destroy_slave_symlinks(struct net_device *master, static ssize_t bonding_show_slaves(struct device *d, struct device_attribute *attr, char *buf) { - struct slave *slave; - int i, res = 0; struct bonding *bond = to_bond(d); + struct slave *slave; + int res = 0; read_lock(&bond->lock); - bond_for_each_slave(bond, slave, i) { + bond_for_each_slave(bond, slave) { if (res > (PAGE_SIZE - IFNAMSIZ)) { /* not enough space for another interface name */ if ((PAGE_SIZE - res) > 10) @@ -227,6 +227,7 @@ static ssize_t bonding_show_slaves(struct device *d, read_unlock(&bond->lock); if (res) buf[res-1] = '\n'; /* eat the leftover space */ + return res; } @@ -325,7 +326,7 @@ static ssize_t bonding_store_mode(struct device *d, goto out; } - if (bond->slave_cnt > 0) { + if (!list_empty(&bond->slave_list)) { pr_err("unable to update mode of %s because it has slaves.\n", bond->dev->name); ret = -EPERM; @@ -501,20 +502,25 @@ static ssize_t bonding_store_fail_over_mac(struct device *d, struct device_attribute *attr, const char *buf, size_t count) { - int new_value; + int new_value, ret = count; struct bonding *bond = to_bond(d); - if (bond->slave_cnt != 0) { + if (!rtnl_trylock()) + return restart_syscall(); + + if (!list_empty(&bond->slave_list)) { pr_err("%s: Can't alter fail_over_mac with slaves in bond.\n", bond->dev->name); - return -EPERM; + ret = -EPERM; + goto out; } new_value = bond_parse_parm(buf, fail_over_mac_tbl); if (new_value < 0) { pr_err("%s: Ignoring invalid fail_over_mac value %s.\n", bond->dev->name, buf); - return -EINVAL; + ret = -EINVAL; + goto out; } bond->params.fail_over_mac = new_value; @@ -522,7 +528,9 @@ static ssize_t bonding_store_fail_over_mac(struct device *d, bond->dev->name, fail_over_mac_tbl[new_value].modename, new_value); - return count; +out: + rtnl_unlock(); + return ret; } static DEVICE_ATTR(fail_over_mac, S_IRUGO | S_IWUSR, @@ -661,7 +669,7 @@ static ssize_t bonding_store_arp_targets(struct device *d, &newtarget); /* not to race with bond_arp_rcv */ write_lock_bh(&bond->lock); - bond_for_each_slave(bond, slave, i) + bond_for_each_slave(bond, slave) slave->target_last_arp_rx[ind] = jiffies; targets[ind] = newtarget; write_unlock_bh(&bond->lock); @@ -687,7 +695,7 @@ static ssize_t bonding_store_arp_targets(struct device *d, &newtarget); write_lock_bh(&bond->lock); - bond_for_each_slave(bond, slave, i) { + bond_for_each_slave(bond, slave) { targets_rx = slave->target_last_arp_rx; j = ind; for (; (j < BOND_MAX_ARP_TARGETS-1) && targets[j+1]; j++) @@ -844,8 +852,11 @@ static ssize_t bonding_store_lacp(struct device *d, struct device_attribute *attr, const char *buf, size_t count) { - int new_value, ret = count; struct bonding *bond = to_bond(d); + int new_value, ret = count; + + if (!rtnl_trylock()) + return restart_syscall(); if (bond->dev->flags & IFF_UP) { pr_err("%s: Unable to update LACP rate because interface is up.\n", @@ -875,6 +886,8 @@ static ssize_t bonding_store_lacp(struct device *d, ret = -EINVAL; } out: + rtnl_unlock(); + return ret; } static DEVICE_ATTR(lacp_rate, S_IRUGO | S_IWUSR, @@ -1078,10 +1091,9 @@ static ssize_t bonding_store_primary(struct device *d, struct device_attribute *attr, const char *buf, size_t count) { - int i; - struct slave *slave; struct bonding *bond = to_bond(d); char ifname[IFNAMSIZ]; + struct slave *slave; if (!rtnl_trylock()) return restart_syscall(); @@ -1107,7 +1119,7 @@ static ssize_t bonding_store_primary(struct device *d, goto out; } - bond_for_each_slave(bond, slave, i) { + bond_for_each_slave(bond, slave) { if (strncmp(slave->dev->name, ifname, IFNAMSIZ) == 0) { pr_info("%s: Setting %s as primary slave.\n", bond->dev->name, slave->dev->name); @@ -1236,16 +1248,16 @@ static ssize_t bonding_show_active_slave(struct device *d, struct device_attribute *attr, char *buf) { - struct slave *curr; struct bonding *bond = to_bond(d); + struct slave *curr; int count = 0; - read_lock(&bond->curr_slave_lock); - curr = bond->curr_active_slave; - read_unlock(&bond->curr_slave_lock); - + rcu_read_lock(); + curr = rcu_dereference(bond->curr_active_slave); if (USES_PRIMARY(bond->params.mode) && curr) count = sprintf(buf, "%s\n", curr->dev->name); + rcu_read_unlock(); + return count; } @@ -1253,16 +1265,14 @@ static ssize_t bonding_store_active_slave(struct device *d, struct device_attribute *attr, const char *buf, size_t count) { - int i; - struct slave *slave; - struct slave *old_active = NULL; - struct slave *new_active = NULL; + struct slave *slave, *old_active, *new_active; struct bonding *bond = to_bond(d); char ifname[IFNAMSIZ]; if (!rtnl_trylock()) return restart_syscall(); + old_active = new_active = NULL; block_netpoll_tx(); read_lock(&bond->lock); write_lock_bh(&bond->curr_slave_lock); @@ -1279,12 +1289,12 @@ static ssize_t bonding_store_active_slave(struct device *d, if (!strlen(ifname) || buf[0] == '\n') { pr_info("%s: Clearing current active slave.\n", bond->dev->name); - bond->curr_active_slave = NULL; + rcu_assign_pointer(bond->curr_active_slave, NULL); bond_select_active_slave(bond); goto out; } - bond_for_each_slave(bond, slave, i) { + bond_for_each_slave(bond, slave) { if (strncmp(slave->dev->name, ifname, IFNAMSIZ) == 0) { old_active = bond->curr_active_slave; new_active = slave; @@ -1295,8 +1305,7 @@ static ssize_t bonding_store_active_slave(struct device *d, bond->dev->name, slave->dev->name); goto out; - } - else { + } else { if ((new_active) && (old_active) && (new_active->link == BOND_LINK_UP) && @@ -1307,8 +1316,7 @@ static ssize_t bonding_store_active_slave(struct device *d, slave->dev->name); bond_change_active_slave(bond, new_active); - } - else { + } else { pr_info("%s: Could not set %s as" " active slave; either %s is" " down or the link is down.\n", @@ -1344,14 +1352,9 @@ static ssize_t bonding_show_mii_status(struct device *d, struct device_attribute *attr, char *buf) { - struct slave *curr; struct bonding *bond = to_bond(d); - read_lock(&bond->curr_slave_lock); - curr = bond->curr_active_slave; - read_unlock(&bond->curr_slave_lock); - - return sprintf(buf, "%s\n", curr ? "up" : "down"); + return sprintf(buf, "%s\n", bond->curr_active_slave ? "up" : "down"); } static DEVICE_ATTR(mii_status, S_IRUGO, bonding_show_mii_status, NULL); @@ -1470,15 +1473,15 @@ static ssize_t bonding_show_queue_id(struct device *d, struct device_attribute *attr, char *buf) { - struct slave *slave; - int i, res = 0; struct bonding *bond = to_bond(d); + struct slave *slave; + int res = 0; if (!rtnl_trylock()) return restart_syscall(); read_lock(&bond->lock); - bond_for_each_slave(bond, slave, i) { + bond_for_each_slave(bond, slave) { if (res > (PAGE_SIZE - IFNAMSIZ - 6)) { /* not enough space for another interface_name:queue_id pair */ if ((PAGE_SIZE - res) > 10) @@ -1493,6 +1496,7 @@ static ssize_t bonding_show_queue_id(struct device *d, if (res) buf[res-1] = '\n'; /* eat the leftover space */ rtnl_unlock(); + return res; } @@ -1507,7 +1511,7 @@ static ssize_t bonding_store_queue_id(struct device *d, struct slave *slave, *update_slave; struct bonding *bond = to_bond(d); u16 qid; - int i, ret = count; + int ret = count; char *delim; struct net_device *sdev = NULL; @@ -1542,7 +1546,7 @@ static ssize_t bonding_store_queue_id(struct device *d, /* Search for thes slave and check for duplicate qids */ update_slave = NULL; - bond_for_each_slave(bond, slave, i) { + bond_for_each_slave(bond, slave) { if (sdev == slave->dev) /* * We don't need to check the matching @@ -1594,8 +1598,8 @@ static ssize_t bonding_store_slaves_active(struct device *d, struct device_attribute *attr, const char *buf, size_t count) { - int i, new_value, ret = count; struct bonding *bond = to_bond(d); + int new_value, ret = count; struct slave *slave; if (sscanf(buf, "%d", &new_value) != 1) { @@ -1618,7 +1622,7 @@ static ssize_t bonding_store_slaves_active(struct device *d, } read_lock(&bond->lock); - bond_for_each_slave(bond, slave, i) { + bond_for_each_slave(bond, slave) { if (!bond_is_active_slave(slave)) { if (new_value) slave->inactive = 0; diff --git a/drivers/net/bonding/bonding.h b/drivers/net/bonding/bonding.h index 42d1c6599cba..f7ab16185f68 100644 --- a/drivers/net/bonding/bonding.h +++ b/drivers/net/bonding/bonding.h @@ -71,6 +71,28 @@ set_fs(fs); \ res; }) +/* slave list primitives */ +#define bond_to_slave(ptr) list_entry(ptr, struct slave, list) + +/* IMPORTANT: bond_first/last_slave can return NULL in case of an empty list */ +#define bond_first_slave(bond) \ + list_first_entry_or_null(&(bond)->slave_list, struct slave, list) +#define bond_last_slave(bond) \ + (list_empty(&(bond)->slave_list) ? NULL : \ + bond_to_slave((bond)->slave_list.prev)) + +#define bond_is_first_slave(bond, pos) ((pos)->list.prev == &(bond)->slave_list) +#define bond_is_last_slave(bond, pos) ((pos)->list.next == &(bond)->slave_list) + +/* Since bond_first/last_slave can return NULL, these can return NULL too */ +#define bond_next_slave(bond, pos) \ + (bond_is_last_slave(bond, pos) ? bond_first_slave(bond) : \ + bond_to_slave((pos)->list.next)) + +#define bond_prev_slave(bond, pos) \ + (bond_is_first_slave(bond, pos) ? bond_last_slave(bond) : \ + bond_to_slave((pos)->list.prev)) + /** * bond_for_each_slave_from - iterate the slaves list from a starting point * @bond: the bond holding this list. @@ -80,37 +102,33 @@ * * 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_for_each_slave_from(bond, pos, cnt, start) \ + for (cnt = 0, pos = start; pos && cnt < (bond)->slave_cnt; \ + cnt++, pos = bond_next_slave(bond, pos)) /** - * 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. + * bond_for_each_slave - iterate over all slaves + * @bond: the bond holding this list + * @pos: current slave * * 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) +#define bond_for_each_slave(bond, pos) \ + list_for_each_entry(pos, &(bond)->slave_list, list) + +/* Caller must have rcu_read_lock */ +#define bond_for_each_slave_rcu(bond, pos) \ + list_for_each_entry_rcu(pos, &(bond)->slave_list, list) /** - * 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_reverse - iterate in reverse from a given position + * @bond: the bond holding this list + * @pos: slave to continue from * * 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_continue_reverse(bond, pos) \ + list_for_each_entry_continue_reverse(pos, &(bond)->slave_list, list) #ifdef CONFIG_NET_POLL_CONTROLLER extern atomic_t netpoll_block_tx; @@ -167,15 +185,9 @@ struct bond_parm_tbl { #define BOND_MAX_MODENAME_LEN 20 -struct vlan_entry { - struct list_head vlan_list; - unsigned short vlan_id; -}; - struct slave { struct net_device *dev; /* first - useful for panic debug */ - struct slave *next; - struct slave *prev; + struct list_head list; struct bonding *bond; /* our master */ int delay; unsigned long jiffies; @@ -215,7 +227,7 @@ struct slave { */ struct bonding { struct net_device *dev; /* first - useful for panic debug */ - struct slave *first_slave; + struct list_head slave_list; struct slave *curr_active_slave; struct slave *current_arp_slave; struct slave *primary_slave; @@ -237,7 +249,6 @@ struct bonding { struct ad_bond_info ad_info; struct alb_bond_info alb_info; struct bond_params params; - struct list_head vlan_list; struct workqueue_struct *wq; struct delayed_work mii_work; struct delayed_work arp_work; @@ -250,11 +261,6 @@ struct bonding { #endif /* CONFIG_DEBUG_FS */ }; -static inline bool bond_vlan_used(struct bonding *bond) -{ - return !list_empty(&bond->vlan_list); -} - #define bond_slave_get_rcu(dev) \ ((struct slave *) rcu_dereference(dev->rx_handler_data)) @@ -270,13 +276,10 @@ 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) { + bond_for_each_slave(bond, slave) + if (slave->dev == slave_dev) return slave; - } - } return NULL; } @@ -416,10 +419,20 @@ static inline __be32 bond_confirm_addr(struct net_device *dev, __be32 dst, __be3 return addr; } +static inline bool slave_can_tx(struct slave *slave) +{ + if (IS_UP(slave->dev) && slave->link == BOND_LINK_UP && + bond_is_active_slave(slave)) + return true; + else + return false; +} + struct bond_net; struct vlan_entry *bond_next_vlan(struct bonding *bond, struct vlan_entry *curr); int bond_dev_queue_xmit(struct bonding *bond, struct sk_buff *skb, struct net_device *slave_dev); +void bond_xmit_slave_id(struct bonding *bond, struct sk_buff *skb, int slave_id); 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); @@ -477,10 +490,9 @@ static inline void bond_destroy_proc_dir(struct bond_net *bn) static inline struct slave *bond_slave_has_mac(struct bonding *bond, const u8 *mac) { - int i = 0; struct slave *tmp; - bond_for_each_slave(bond, tmp, i) + bond_for_each_slave(bond, tmp) if (ether_addr_equal_64bits(mac, tmp->dev->dev_addr)) return tmp; |