diff options
author | David S. Miller <davem@davemloft.net> | 2013-09-26 16:02:19 -0400 |
---|---|---|
committer | David S. Miller <davem@davemloft.net> | 2013-09-26 16:02:19 -0400 |
commit | aae8c287e664d49df4aa315ad263c33b9a2af3e1 (patch) | |
tree | dc71bea5d018fdcc1f68af27ea8af52be02628e5 | |
parent | 4ed377e36ec2f385484d12e516faf88516fad31c (diff) | |
parent | 5831d66e8097aedfa3bc35941cf265ada2352317 (diff) | |
download | op-kernel-dev-aae8c287e664d49df4aa315ad263c33b9a2af3e1.zip op-kernel-dev-aae8c287e664d49df4aa315ad263c33b9a2af3e1.tar.gz |
Merge branch 'bonding_neighbours'
bonding: use neighbours instead of own lists
Veaceslav Falico says:
====================
This patchset introduces all the needed infrastructure, on top of current
adjacent lists, to be able to remove bond's slave_list/slave->list. The
overhead in memory/CPU is minimal, and after the patchset bonding can rely
on its slave-related functions, given the proper locking. I've done some
netperf benchmarks on a vm, and the delta was about 0.1gbps for 35gbps as a
whole, so no speed fluctuations.
It also automatically creates lower/upper and master symlinks in dev's
sysfs directory.
====================
Signed-off-by: David S. Miller <davem@davemloft.net>
-rw-r--r-- | drivers/net/bonding/bond_3ad.c | 54 | ||||
-rw-r--r-- | drivers/net/bonding/bond_alb.c | 81 | ||||
-rw-r--r-- | drivers/net/bonding/bond_alb.h | 4 | ||||
-rw-r--r-- | drivers/net/bonding/bond_main.c | 296 | ||||
-rw-r--r-- | drivers/net/bonding/bond_procfs.c | 5 | ||||
-rw-r--r-- | drivers/net/bonding/bond_sysfs.c | 62 | ||||
-rw-r--r-- | drivers/net/bonding/bonding.h | 100 | ||||
-rw-r--r-- | drivers/net/ethernet/chelsio/cxgb4/cxgb4_main.c | 3 | ||||
-rw-r--r-- | include/linux/netdevice.h | 55 | ||||
-rw-r--r-- | net/8021q/vlan.c | 18 | ||||
-rw-r--r-- | net/core/dev.c | 404 |
11 files changed, 638 insertions, 444 deletions
diff --git a/drivers/net/bonding/bond_3ad.c b/drivers/net/bonding/bond_3ad.c index 0d8f427..1337eaf 100644 --- a/drivers/net/bonding/bond_3ad.c +++ b/drivers/net/bonding/bond_3ad.c @@ -2117,7 +2117,7 @@ void bond_3ad_state_machine_handler(struct work_struct *work) read_lock(&bond->lock); //check if there are any slaves - if (list_empty(&bond->slave_list)) + if (!bond_has_slaves(bond)) goto re_arm; // check if agg_select_timer timer after initialize is timed out @@ -2417,14 +2417,15 @@ int bond_3ad_get_active_agg_info(struct bonding *bond, struct ad_info *ad_info) int bond_3ad_xmit_xor(struct sk_buff *skb, struct net_device *dev) { - struct slave *slave, *start_at; struct bonding *bond = netdev_priv(dev); - int slave_agg_no; - int slaves_in_agg; - int agg_id; - int i; + struct slave *slave, *first_ok_slave; + struct aggregator *agg; struct ad_info ad_info; + struct list_head *iter; + int slaves_in_agg; + int slave_agg_no; int res = 1; + int agg_id; read_lock(&bond->lock); if (__bond_3ad_get_active_agg_info(bond, &ad_info)) { @@ -2437,20 +2438,28 @@ int bond_3ad_xmit_xor(struct sk_buff *skb, struct net_device *dev) agg_id = ad_info.aggregator_id; if (slaves_in_agg == 0) { - /*the aggregator is empty*/ pr_debug("%s: Error: active aggregator is empty\n", dev->name); goto out; } slave_agg_no = bond->xmit_hash_policy(skb, slaves_in_agg); + first_ok_slave = NULL; - bond_for_each_slave(bond, slave) { - struct aggregator *agg = SLAVE_AD_INFO(slave).port.aggregator; + bond_for_each_slave(bond, slave, iter) { + agg = SLAVE_AD_INFO(slave).port.aggregator; + if (!agg || agg->aggregator_identifier != agg_id) + continue; - if (agg && (agg->aggregator_identifier == agg_id)) { + if (slave_agg_no >= 0) { + if (!first_ok_slave && SLAVE_IS_OK(slave)) + first_ok_slave = slave; slave_agg_no--; - if (slave_agg_no < 0) - break; + continue; + } + + if (SLAVE_IS_OK(slave)) { + res = bond_dev_queue_xmit(bond, skb, slave->dev); + goto out; } } @@ -2460,20 +2469,10 @@ int bond_3ad_xmit_xor(struct sk_buff *skb, struct net_device *dev) goto out; } - start_at = slave; - - bond_for_each_slave_from(bond, slave, i, start_at) { - int slave_agg_id = 0; - struct aggregator *agg = SLAVE_AD_INFO(slave).port.aggregator; - - if (agg) - slave_agg_id = agg->aggregator_identifier; - - if (SLAVE_IS_OK(slave) && agg && (slave_agg_id == agg_id)) { - res = bond_dev_queue_xmit(bond, skb, slave->dev); - break; - } - } + /* we couldn't find any suitable slave after the agg_no, so use the + * first suitable found, if found. */ + if (first_ok_slave) + res = bond_dev_queue_xmit(bond, skb, first_ok_slave->dev); out: read_unlock(&bond->lock); @@ -2515,11 +2514,12 @@ int bond_3ad_lacpdu_recv(const struct sk_buff *skb, struct bonding *bond, void bond_3ad_update_lacp_rate(struct bonding *bond) { struct port *port = NULL; + struct list_head *iter; struct slave *slave; int lacp_fast; lacp_fast = bond->params.lacp_fast; - bond_for_each_slave(bond, slave) { + bond_for_each_slave(bond, slave, iter) { port = &(SLAVE_AD_INFO(slave).port); __get_state_machine_lock(port); if (lacp_fast) diff --git a/drivers/net/bonding/bond_alb.c b/drivers/net/bonding/bond_alb.c index f428ef57..e960418 100644 --- a/drivers/net/bonding/bond_alb.c +++ b/drivers/net/bonding/bond_alb.c @@ -223,13 +223,14 @@ static long long compute_gap(struct slave *slave) static struct slave *tlb_get_least_loaded_slave(struct bonding *bond) { struct slave *slave, *least_loaded; + struct list_head *iter; long long max_gap; least_loaded = NULL; max_gap = LLONG_MIN; /* Find the slave with the largest gap */ - bond_for_each_slave(bond, slave) { + bond_for_each_slave(bond, slave, iter) { if (SLAVE_IS_OK(slave)) { long long gap = compute_gap(slave); @@ -382,30 +383,31 @@ out: static struct slave *rlb_next_rx_slave(struct bonding *bond) { struct alb_bond_info *bond_info = &(BOND_ALB_INFO(bond)); - struct slave *rx_slave, *slave, *start_at; - int i = 0; - - if (bond_info->next_rx_slave) - start_at = bond_info->next_rx_slave; - else - start_at = bond_first_slave(bond); - - rx_slave = NULL; + struct slave *before = NULL, *rx_slave = NULL, *slave; + struct list_head *iter; + bool found = false; - bond_for_each_slave_from(bond, slave, i, start_at) { - if (SLAVE_IS_OK(slave)) { - if (!rx_slave) { - rx_slave = slave; - } else if (slave->speed > rx_slave->speed) { + bond_for_each_slave(bond, slave, iter) { + if (!SLAVE_IS_OK(slave)) + continue; + if (!found) { + if (!before || before->speed < slave->speed) + before = slave; + } else { + if (!rx_slave || rx_slave->speed < slave->speed) rx_slave = slave; - } } + if (slave == bond_info->rx_slave) + found = true; } + /* we didn't find anything after the current or we have something + * better before and up to the current slave + */ + if (!rx_slave || (before && rx_slave->speed < before->speed)) + rx_slave = before; - if (rx_slave) { - slave = bond_next_slave(bond, rx_slave); - bond_info->next_rx_slave = slave; - } + if (rx_slave) + bond_info->rx_slave = rx_slave; return rx_slave; } @@ -1019,7 +1021,7 @@ static void alb_send_learning_packets(struct slave *slave, u8 mac_addr[]) /* loop through vlans and send one packet for each */ rcu_read_lock(); - netdev_for_each_upper_dev_rcu(bond->dev, upper, iter) { + netdev_for_each_all_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)); @@ -1172,10 +1174,11 @@ static void alb_change_hw_addr_on_detach(struct bonding *bond, struct slave *sla */ static int alb_handle_addr_collision_on_attach(struct bonding *bond, struct slave *slave) { - struct slave *tmp_slave1, *free_mac_slave = NULL; struct slave *has_bond_addr = bond->curr_active_slave; + struct slave *tmp_slave1, *free_mac_slave = NULL; + struct list_head *iter; - if (list_empty(&bond->slave_list)) { + if (!bond_has_slaves(bond)) { /* this is the first slave */ return 0; } @@ -1196,7 +1199,7 @@ 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) { + bond_for_each_slave(bond, tmp_slave1, iter) { if (!bond_slave_has_mac(bond, tmp_slave1->perm_hwaddr)) { /* no slave has tmp_slave1's perm addr * as its curr addr @@ -1246,15 +1249,16 @@ static int alb_handle_addr_collision_on_attach(struct bonding *bond, struct slav */ static int alb_set_mac_address(struct bonding *bond, void *addr) { - char tmp_addr[ETH_ALEN]; - struct slave *slave; + struct slave *slave, *rollback_slave; + struct list_head *iter; struct sockaddr sa; + char tmp_addr[ETH_ALEN]; int res; if (bond->alb_info.rlb_enabled) return 0; - bond_for_each_slave(bond, slave) { + bond_for_each_slave(bond, slave, iter) { /* save net_device's current hw address */ memcpy(tmp_addr, slave->dev->dev_addr, ETH_ALEN); @@ -1274,10 +1278,12 @@ unwind: sa.sa_family = bond->dev->type; /* unwind from head to the slave that failed */ - 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); + bond_for_each_slave(bond, rollback_slave, iter) { + if (rollback_slave == slave) + break; + memcpy(tmp_addr, rollback_slave->dev->dev_addr, ETH_ALEN); + dev_set_mac_address(rollback_slave->dev, &sa); + memcpy(rollback_slave->dev->dev_addr, tmp_addr, ETH_ALEN); } return res; @@ -1458,11 +1464,12 @@ void bond_alb_monitor(struct work_struct *work) struct bonding *bond = container_of(work, struct bonding, alb_work.work); struct alb_bond_info *bond_info = &(BOND_ALB_INFO(bond)); + struct list_head *iter; struct slave *slave; read_lock(&bond->lock); - if (list_empty(&bond->slave_list)) { + if (!bond_has_slaves(bond)) { bond_info->tx_rebalance_counter = 0; bond_info->lp_counter = 0; goto re_arm; @@ -1480,7 +1487,7 @@ void bond_alb_monitor(struct work_struct *work) */ read_lock(&bond->curr_slave_lock); - bond_for_each_slave(bond, slave) + bond_for_each_slave(bond, slave, iter) alb_send_learning_packets(slave, slave->dev->dev_addr); read_unlock(&bond->curr_slave_lock); @@ -1493,7 +1500,7 @@ void bond_alb_monitor(struct work_struct *work) read_lock(&bond->curr_slave_lock); - bond_for_each_slave(bond, slave) { + bond_for_each_slave(bond, slave, iter) { tlb_clear_slave(bond, slave, 1); if (slave == bond->curr_active_slave) { SLAVE_TLB_INFO(slave).load = @@ -1599,13 +1606,13 @@ int bond_alb_init_slave(struct bonding *bond, struct slave *slave) */ void bond_alb_deinit_slave(struct bonding *bond, struct slave *slave) { - if (!list_empty(&bond->slave_list)) + if (bond_has_slaves(bond)) alb_change_hw_addr_on_detach(bond, slave); tlb_clear_slave(bond, slave, 0); if (bond->alb_info.rlb_enabled) { - bond->alb_info.next_rx_slave = NULL; + bond->alb_info.rx_slave = NULL; rlb_clear_slave(bond, slave); } } @@ -1669,7 +1676,7 @@ void bond_alb_handle_active_change(struct bonding *bond, struct slave *new_slave swap_slave = bond->curr_active_slave; rcu_assign_pointer(bond->curr_active_slave, new_slave); - if (!new_slave || list_empty(&bond->slave_list)) + if (!new_slave || !bond_has_slaves(bond)) return; /* set the new curr_active_slave to the bonds mac address diff --git a/drivers/net/bonding/bond_alb.h b/drivers/net/bonding/bond_alb.h index c5eff5d..4226044 100644 --- a/drivers/net/bonding/bond_alb.h +++ b/drivers/net/bonding/bond_alb.h @@ -154,9 +154,7 @@ struct alb_bond_info { u8 rx_ntt; /* flag - need to transmit * to all rx clients */ - struct slave *next_rx_slave;/* next slave to be assigned - * to a new rx client for - */ + struct slave *rx_slave;/* last slave to xmit from */ u8 primary_is_promisc; /* boolean */ u32 rlb_promisc_timeout_counter;/* counts primary * promiscuity time diff --git a/drivers/net/bonding/bond_main.c b/drivers/net/bonding/bond_main.c index 55bbb8b..d5c3153 100644 --- a/drivers/net/bonding/bond_main.c +++ b/drivers/net/bonding/bond_main.c @@ -332,10 +332,11 @@ 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; + struct slave *slave, *rollback_slave; + struct list_head *iter; int res; - bond_for_each_slave(bond, slave) { + bond_for_each_slave(bond, slave, iter) { res = vlan_vid_add(slave->dev, proto, vid); if (res) goto unwind; @@ -344,9 +345,13 @@ static int bond_vlan_rx_add_vid(struct net_device *bond_dev, return 0; unwind: - /* unwind from the slave that failed */ - bond_for_each_slave_continue_reverse(bond, slave) - vlan_vid_del(slave->dev, proto, vid); + /* unwind to the slave that failed */ + bond_for_each_slave(bond, rollback_slave, iter) { + if (rollback_slave == slave) + break; + + vlan_vid_del(rollback_slave->dev, proto, vid); + } return res; } @@ -360,9 +365,10 @@ static int bond_vlan_rx_kill_vid(struct net_device *bond_dev, __be16 proto, u16 vid) { struct bonding *bond = netdev_priv(bond_dev); + struct list_head *iter; struct slave *slave; - bond_for_each_slave(bond, slave) + bond_for_each_slave(bond, slave, iter) vlan_vid_del(slave->dev, proto, vid); if (bond_is_lb(bond)) @@ -382,15 +388,16 @@ static int bond_vlan_rx_kill_vid(struct net_device *bond_dev, */ static int bond_set_carrier(struct bonding *bond) { + struct list_head *iter; struct slave *slave; - if (list_empty(&bond->slave_list)) + if (!bond_has_slaves(bond)) goto down; if (bond->params.mode == BOND_MODE_8023AD) return bond_3ad_set_carrier(bond); - bond_for_each_slave(bond, slave) { + bond_for_each_slave(bond, slave, iter) { if (slave->link == BOND_LINK_UP) { if (!netif_carrier_ok(bond->dev)) { netif_carrier_on(bond->dev); @@ -522,7 +529,9 @@ static int bond_check_dev_link(struct bonding *bond, */ static int bond_set_promiscuity(struct bonding *bond, int inc) { + struct list_head *iter; int err = 0; + if (USES_PRIMARY(bond->params.mode)) { /* write lock already acquired */ if (bond->curr_active_slave) { @@ -532,7 +541,7 @@ static int bond_set_promiscuity(struct bonding *bond, int inc) } else { struct slave *slave; - bond_for_each_slave(bond, slave) { + bond_for_each_slave(bond, slave, iter) { err = dev_set_promiscuity(slave->dev, inc); if (err) return err; @@ -546,7 +555,9 @@ static int bond_set_promiscuity(struct bonding *bond, int inc) */ static int bond_set_allmulti(struct bonding *bond, int inc) { + struct list_head *iter; int err = 0; + if (USES_PRIMARY(bond->params.mode)) { /* write lock already acquired */ if (bond->curr_active_slave) { @@ -556,7 +567,7 @@ static int bond_set_allmulti(struct bonding *bond, int inc) } else { struct slave *slave; - bond_for_each_slave(bond, slave) { + bond_for_each_slave(bond, slave, iter) { err = dev_set_allmulti(slave->dev, inc); if (err) return err; @@ -774,43 +785,24 @@ static bool bond_should_change_active(struct bonding *bond) /** * find_best_interface - select the best available slave to be the active one * @bond: our bonding struct - * - * Warning: Caller must hold curr_slave_lock for writing. */ static struct slave *bond_find_best_slave(struct bonding *bond) { - struct slave *new_active, *old_active; - struct slave *bestslave = NULL; + struct slave *slave, *bestslave = NULL; + struct list_head *iter; int mintime = bond->params.updelay; - int i; - new_active = bond->curr_active_slave; - - if (!new_active) { /* there were no active slaves left */ - new_active = bond_first_slave(bond); - if (!new_active) - return NULL; /* still no slave, return NULL */ - } - - if ((bond->primary_slave) && - bond->primary_slave->link == BOND_LINK_UP && - bond_should_change_active(bond)) { - new_active = bond->primary_slave; - } - - /* remember where to stop iterating over the slaves */ - old_active = new_active; - - bond_for_each_slave_from(bond, new_active, i, old_active) { - if (new_active->link == BOND_LINK_UP) { - return new_active; - } else if (new_active->link == BOND_LINK_BACK && - IS_UP(new_active->dev)) { - /* link up, but waiting for stabilization */ - if (new_active->delay < mintime) { - mintime = new_active->delay; - bestslave = new_active; - } + if (bond->primary_slave && bond->primary_slave->link == BOND_LINK_UP && + bond_should_change_active(bond)) + return bond->primary_slave; + + bond_for_each_slave(bond, slave, iter) { + if (slave->link == BOND_LINK_UP) + return slave; + if (slave->link == BOND_LINK_BACK && IS_UP(slave->dev) && + slave->delay < mintime) { + mintime = slave->delay; + bestslave = slave; } } @@ -980,7 +972,6 @@ void bond_select_active_slave(struct bonding *bond) */ static void bond_attach_slave(struct bonding *bond, struct slave *new_slave) { - list_add_tail_rcu(&new_slave->list, &bond->slave_list); bond->slave_cnt++; } @@ -996,7 +987,6 @@ static void bond_attach_slave(struct bonding *bond, struct slave *new_slave) */ static void bond_detach_slave(struct bonding *bond, struct slave *slave) { - list_del_rcu(&slave->list); bond->slave_cnt--; } @@ -1046,9 +1036,10 @@ static void bond_poll_controller(struct net_device *bond_dev) static void bond_netpoll_cleanup(struct net_device *bond_dev) { struct bonding *bond = netdev_priv(bond_dev); + struct list_head *iter; struct slave *slave; - bond_for_each_slave(bond, slave) + bond_for_each_slave(bond, slave, iter) if (IS_UP(slave->dev)) slave_disable_netpoll(slave); } @@ -1056,10 +1047,11 @@ static void bond_netpoll_cleanup(struct net_device *bond_dev) static int bond_netpoll_setup(struct net_device *dev, struct netpoll_info *ni, gfp_t gfp) { struct bonding *bond = netdev_priv(dev); + struct list_head *iter; struct slave *slave; int err = 0; - bond_for_each_slave(bond, slave) { + bond_for_each_slave(bond, slave, iter) { err = slave_enable_netpoll(slave); if (err) { bond_netpoll_cleanup(dev); @@ -1087,10 +1079,11 @@ static netdev_features_t bond_fix_features(struct net_device *dev, netdev_features_t features) { struct bonding *bond = netdev_priv(dev); + struct list_head *iter; netdev_features_t mask; struct slave *slave; - if (list_empty(&bond->slave_list)) { + if (!bond_has_slaves(bond)) { /* Disable adding VLANs to empty bond. But why? --mq */ features |= NETIF_F_VLAN_CHALLENGED; return features; @@ -1100,7 +1093,7 @@ static netdev_features_t bond_fix_features(struct net_device *dev, features &= ~NETIF_F_ONE_FOR_ALL; features |= NETIF_F_ALL_FOR_ALL; - bond_for_each_slave(bond, slave) { + bond_for_each_slave(bond, slave, iter) { features = netdev_increment_features(features, slave->dev->features, mask); @@ -1118,16 +1111,17 @@ static void bond_compute_features(struct bonding *bond) { unsigned int flags, dst_release_flag = IFF_XMIT_DST_RELEASE; netdev_features_t vlan_features = BOND_VLAN_FEATURES; + struct net_device *bond_dev = bond->dev; + struct list_head *iter; + struct slave *slave; unsigned short max_hard_header_len = ETH_HLEN; unsigned int gso_max_size = GSO_MAX_SIZE; - struct net_device *bond_dev = bond->dev; u16 gso_max_segs = GSO_MAX_SEGS; - struct slave *slave; - if (list_empty(&bond->slave_list)) + if (!bond_has_slaves(bond)) goto done; - bond_for_each_slave(bond, slave) { + bond_for_each_slave(bond, slave, iter) { vlan_features = netdev_increment_features(vlan_features, slave->dev->vlan_features, BOND_VLAN_FEATURES); @@ -1233,11 +1227,12 @@ static rx_handler_result_t bond_handle_frame(struct sk_buff **pskb) } static int bond_master_upper_dev_link(struct net_device *bond_dev, - struct net_device *slave_dev) + struct net_device *slave_dev, + struct slave *slave) { int err; - err = netdev_master_upper_dev_link(slave_dev, bond_dev); + err = netdev_master_upper_dev_link_private(slave_dev, bond_dev, slave); if (err) return err; slave_dev->flags |= IFF_SLAVE; @@ -1258,7 +1253,7 @@ int bond_enslave(struct net_device *bond_dev, struct net_device *slave_dev) { struct bonding *bond = netdev_priv(bond_dev); const struct net_device_ops *slave_ops = slave_dev->netdev_ops; - struct slave *new_slave = NULL; + struct slave *new_slave = NULL, *prev_slave; struct sockaddr addr; int link_reporting; int res = 0, i; @@ -1313,7 +1308,7 @@ 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 (list_empty(&bond->slave_list)) { + if (!bond_has_slaves(bond)) { if (bond_dev->type != slave_dev->type) { pr_debug("%s: change device type from %d to %d\n", bond_dev->name, @@ -1352,7 +1347,7 @@ int bond_enslave(struct net_device *bond_dev, struct net_device *slave_dev) } if (slave_ops->ndo_set_mac_address == NULL) { - if (list_empty(&bond->slave_list)) { + if (!bond_has_slaves(bond)) { 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; @@ -1368,7 +1363,7 @@ 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 (list_empty(&bond->slave_list) && + if (!bond_has_slaves(bond) && bond->dev->addr_assign_type == NET_ADDR_RANDOM) bond_set_dev_addr(bond->dev, slave_dev); @@ -1377,7 +1372,6 @@ 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. @@ -1413,17 +1407,11 @@ int bond_enslave(struct net_device *bond_dev, struct net_device *slave_dev) } } - res = bond_master_upper_dev_link(bond_dev, slave_dev); - if (res) { - pr_debug("Error %d calling bond_master_upper_dev_link\n", res); - goto err_restore_mac; - } - /* open the slave since the application closed it */ res = dev_open(slave_dev); if (res) { pr_debug("Opening slave %s failed\n", slave_dev->name); - goto err_unset_master; + goto err_restore_mac; } new_slave->bond = bond; @@ -1481,6 +1469,7 @@ int bond_enslave(struct net_device *bond_dev, struct net_device *slave_dev) write_lock_bh(&bond->lock); + prev_slave = bond_last_slave(bond); bond_attach_slave(bond, new_slave); new_slave->delay = 0; @@ -1575,9 +1564,6 @@ int bond_enslave(struct net_device *bond_dev, struct net_device *slave_dev) */ 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(prev_slave).id + 1; } @@ -1626,17 +1612,20 @@ int bond_enslave(struct net_device *bond_dev, struct net_device *slave_dev) read_unlock(&bond->lock); - res = bond_create_slave_symlinks(bond_dev, slave_dev); - if (res) - goto err_detach; - res = netdev_rx_handler_register(slave_dev, bond_handle_frame, new_slave); if (res) { pr_debug("Error %d calling netdev_rx_handler_register\n", res); - goto err_dest_symlinks; + goto err_detach; + } + + res = bond_master_upper_dev_link(bond_dev, slave_dev, new_slave); + if (res) { + pr_debug("Error %d calling bond_master_upper_dev_link\n", res); + goto err_unregister; } + pr_info("%s: enslaving %s as a%s interface with a%s link.\n", bond_dev->name, slave_dev->name, bond_is_active_slave(new_slave) ? "n active" : " backup", @@ -1646,8 +1635,8 @@ int bond_enslave(struct net_device *bond_dev, struct net_device *slave_dev) return 0; /* Undo stages on error */ -err_dest_symlinks: - bond_destroy_slave_symlinks(bond_dev, slave_dev); +err_unregister: + netdev_rx_handler_unregister(slave_dev); err_detach: if (!USES_PRIMARY(bond->params.mode)) @@ -1675,9 +1664,6 @@ err_close: slave_dev->priv_flags &= ~IFF_BONDING; dev_close(slave_dev); -err_unset_master: - bond_upper_dev_unlink(bond_dev, slave_dev); - err_restore_mac: if (!bond->params.fail_over_mac) { /* XXX TODO - fom follow mode needs to change master's @@ -1698,7 +1684,7 @@ err_free: err_undo_flags: bond_compute_features(bond); /* Enslave of first slave has failed and we need to fix master's mac */ - if (list_empty(&bond->slave_list) && + if (!bond_has_slaves(bond) && ether_addr_equal(bond_dev->dev_addr, slave_dev->dev_addr)) eth_hw_addr_random(bond_dev); @@ -1748,6 +1734,8 @@ static int __bond_release_one(struct net_device *bond_dev, } write_unlock_bh(&bond->lock); + + bond_upper_dev_unlink(bond_dev, slave_dev); /* unregister rx_handler early so bond_handle_frame wouldn't be called * for this slave anymore. */ @@ -1776,7 +1764,7 @@ static int __bond_release_one(struct net_device *bond_dev, if (!all && !bond->params.fail_over_mac) { if (ether_addr_equal(bond_dev->dev_addr, slave->perm_hwaddr) && - !list_empty(&bond->slave_list)) + bond_has_slaves(bond)) pr_warn("%s: Warning: the permanent HWaddr of %s - %pM - is still in use by %s. Set the HWaddr of %s to a different address to avoid conflicts.\n", bond_dev->name, slave_dev->name, slave->perm_hwaddr, @@ -1819,7 +1807,7 @@ static int __bond_release_one(struct net_device *bond_dev, write_lock_bh(&bond->lock); } - if (list_empty(&bond->slave_list)) { + if (!bond_has_slaves(bond)) { bond_set_carrier(bond); eth_hw_addr_random(bond_dev); @@ -1835,7 +1823,7 @@ static int __bond_release_one(struct net_device *bond_dev, unblock_netpoll_tx(); synchronize_rcu(); - if (list_empty(&bond->slave_list)) { + if (!bond_has_slaves(bond)) { call_netdevice_notifiers(NETDEV_CHANGEADDR, bond->dev); call_netdevice_notifiers(NETDEV_RELEASE, bond->dev); } @@ -1847,8 +1835,6 @@ static int __bond_release_one(struct net_device *bond_dev, bond_dev->name, slave_dev->name, bond_dev->name); /* must do this from outside any spinlocks */ - bond_destroy_slave_symlinks(bond_dev, slave_dev); - vlan_vids_del_by_dev(slave_dev, bond_dev); /* If the mode USES_PRIMARY, then this cases was handled above by @@ -1866,8 +1852,6 @@ static int __bond_release_one(struct net_device *bond_dev, bond_hw_addr_flush(bond_dev, slave_dev); } - bond_upper_dev_unlink(bond_dev, slave_dev); - slave_disable_netpoll(slave); /* close slave before restoring its mac address */ @@ -1906,7 +1890,7 @@ static int bond_release_and_destroy(struct net_device *bond_dev, int ret; ret = bond_release(bond_dev, slave_dev); - if (ret == 0 && list_empty(&bond->slave_list)) { + if (ret == 0 && !bond_has_slaves(bond)) { bond_dev->priv_flags |= IFF_DISABLE_NETPOLL; pr_info("%s: destroying bond %s.\n", bond_dev->name, bond_dev->name); @@ -1987,11 +1971,12 @@ 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); + struct list_head *iter; int i = 0, res = -ENODEV; struct slave *slave; read_lock(&bond->lock); - bond_for_each_slave(bond, slave) { + bond_for_each_slave(bond, slave, iter) { if (i++ == (int)info->slave_id) { res = 0; strcpy(info->slave_name, slave->dev->name); @@ -2012,12 +1997,13 @@ 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 list_head *iter; struct slave *slave; bool ignore_updelay; ignore_updelay = !bond->curr_active_slave ? true : false; - bond_for_each_slave(bond, slave) { + bond_for_each_slave(bond, slave, iter) { slave->new_link = BOND_LINK_NOCHANGE; link_state = bond_check_dev_link(bond, slave->dev, 0); @@ -2111,9 +2097,10 @@ static int bond_miimon_inspect(struct bonding *bond) static void bond_miimon_commit(struct bonding *bond) { + struct list_head *iter; struct slave *slave; - bond_for_each_slave(bond, slave) { + bond_for_each_slave(bond, slave, iter) { switch (slave->new_link) { case BOND_LINK_NOCHANGE: continue; @@ -2218,7 +2205,7 @@ void bond_mii_monitor(struct work_struct *work) delay = msecs_to_jiffies(bond->params.miimon); - if (list_empty(&bond->slave_list)) + if (!bond_has_slaves(bond)) goto re_arm; should_notify_peers = bond_should_notify_peers(bond); @@ -2267,7 +2254,7 @@ static bool bond_has_this_ip(struct bonding *bond, __be32 ip) return true; rcu_read_lock(); - netdev_for_each_upper_dev_rcu(bond->dev, upper, iter) { + netdev_for_each_all_upper_dev_rcu(bond->dev, upper, iter) { if (ip == bond_confirm_addr(upper, 0, ip)) { ret = true; break; @@ -2342,10 +2329,12 @@ static void bond_arp_send_all(struct bonding *bond, struct slave *slave) * * TODO: QinQ? */ - netdev_for_each_upper_dev_rcu(bond->dev, vlan_upper, vlan_iter) { + netdev_for_each_all_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) { + netdev_for_each_all_upper_dev_rcu(vlan_upper, upper, + iter) { if (upper == rt->dst.dev) { vlan_id = vlan_dev_vlan_id(vlan_upper); rcu_read_unlock(); @@ -2358,7 +2347,7 @@ static void bond_arp_send_all(struct bonding *bond, struct slave *slave) * 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) { + netdev_for_each_all_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)) @@ -2505,11 +2494,12 @@ void bond_loadbalance_arp_mon(struct work_struct *work) struct bonding *bond = container_of(work, struct bonding, arp_work.work); struct slave *slave, *oldcurrent; + struct list_head *iter; int do_failover = 0; read_lock(&bond->lock); - if (list_empty(&bond->slave_list)) + if (!bond_has_slaves(bond)) goto re_arm; oldcurrent = bond->curr_active_slave; @@ -2521,7 +2511,7 @@ 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) { + bond_for_each_slave(bond, slave, iter) { unsigned long trans_start = dev_trans_start(slave->dev); if (slave->link != BOND_LINK_UP) { @@ -2612,10 +2602,11 @@ re_arm: static int bond_ab_arp_inspect(struct bonding *bond) { unsigned long trans_start, last_rx; + struct list_head *iter; struct slave *slave; int commit = 0; - bond_for_each_slave(bond, slave) { + bond_for_each_slave(bond, slave, iter) { slave->new_link = BOND_LINK_NOCHANGE; last_rx = slave_last_rx(bond, slave); @@ -2682,9 +2673,10 @@ static int bond_ab_arp_inspect(struct bonding *bond) static void bond_ab_arp_commit(struct bonding *bond) { unsigned long trans_start; + struct list_head *iter; struct slave *slave; - bond_for_each_slave(bond, slave) { + bond_for_each_slave(bond, slave, iter) { switch (slave->new_link) { case BOND_LINK_NOCHANGE: continue; @@ -2755,8 +2747,9 @@ do_failover: */ static void bond_ab_arp_probe(struct bonding *bond) { - struct slave *slave, *next_slave; - int i; + struct slave *slave, *before = NULL, *new_slave = NULL; + struct list_head *iter; + bool found = false; read_lock(&bond->curr_slave_lock); @@ -2786,18 +2779,12 @@ static void bond_ab_arp_probe(struct bonding *bond) bond_set_slave_inactive_flags(bond->current_arp_slave); - /* search for next candidate */ - 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); - bond_arp_send_all(bond, slave); - slave->jiffies = jiffies; - bond->current_arp_slave = slave; - break; - } + bond_for_each_slave(bond, slave, iter) { + if (!found && !before && IS_UP(slave->dev)) + before = slave; + if (found && !new_slave && IS_UP(slave->dev)) + new_slave = slave; /* if the link state is up at this point, we * mark it down - this can happen if we have * simultaneous link failures and @@ -2805,7 +2792,7 @@ static void bond_ab_arp_probe(struct bonding *bond) * one the current slave so it is still marked * up when it is actually down */ - if (slave->link == BOND_LINK_UP) { + if (!IS_UP(slave->dev) && slave->link == BOND_LINK_UP) { slave->link = BOND_LINK_DOWN; if (slave->link_failure_count < UINT_MAX) slave->link_failure_count++; @@ -2815,7 +2802,22 @@ static void bond_ab_arp_probe(struct bonding *bond) pr_info("%s: backup interface %s is now down.\n", bond->dev->name, slave->dev->name); } + if (slave == bond->current_arp_slave) + found = true; } + + if (!new_slave && before) + new_slave = before; + + if (!new_slave) + return; + + new_slave->link = BOND_LINK_BACK; + bond_set_slave_active_flags(new_slave); + bond_arp_send_all(bond, new_slave); + new_slave->jiffies = jiffies; + bond->current_arp_slave = new_slave; + } void bond_activebackup_arp_mon(struct work_struct *work) @@ -2829,7 +2831,7 @@ void bond_activebackup_arp_mon(struct work_struct *work) delta_in_ticks = msecs_to_jiffies(bond->params.arp_interval); - if (list_empty(&bond->slave_list)) + if (!bond_has_slaves(bond)) goto re_arm; should_notify_peers = bond_should_notify_peers(bond); @@ -3148,13 +3150,14 @@ static void bond_work_cancel_all(struct bonding *bond) static int bond_open(struct net_device *bond_dev) { struct bonding *bond = netdev_priv(bond_dev); + struct list_head *iter; struct slave *slave; /* reset slave->backup and slave->inactive */ read_lock(&bond->lock); - if (!list_empty(&bond->slave_list)) { + if (bond_has_slaves(bond)) { read_lock(&bond->curr_slave_lock); - bond_for_each_slave(bond, slave) { + bond_for_each_slave(bond, slave, iter) { if ((bond->params.mode == BOND_MODE_ACTIVEBACKUP) && (slave != bond->curr_active_slave)) { bond_set_slave_inactive_flags(slave); @@ -3214,12 +3217,13 @@ 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 list_head *iter; struct slave *slave; memset(stats, 0, sizeof(*stats)); read_lock_bh(&bond->lock); - bond_for_each_slave(bond, slave) { + bond_for_each_slave(bond, slave, iter) { const struct rtnl_link_stats64 *sstats = dev_get_stats(slave->dev, &temp); @@ -3386,6 +3390,7 @@ static void bond_change_rx_flags(struct net_device *bond_dev, int change) static void bond_set_rx_mode(struct net_device *bond_dev) { struct bonding *bond = netdev_priv(bond_dev); + struct list_head *iter; struct slave *slave; ASSERT_RTNL(); @@ -3397,7 +3402,7 @@ static void bond_set_rx_mode(struct net_device *bond_dev) dev_mc_sync(slave->dev, bond_dev); } } else { - bond_for_each_slave(bond, slave) { + bond_for_each_slave(bond, slave, iter) { dev_uc_sync_multiple(slave->dev, bond_dev); dev_mc_sync_multiple(slave->dev, bond_dev); } @@ -3464,7 +3469,8 @@ 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; + struct slave *slave, *rollback_slave; + struct list_head *iter; int res = 0; pr_debug("bond=%p, name=%s, new_mtu=%d\n", bond, @@ -3485,10 +3491,9 @@ static int bond_change_mtu(struct net_device *bond_dev, int new_mtu) * call to the base driver. */ - bond_for_each_slave(bond, slave) { - pr_debug("s %p s->p %p c_m %p\n", + bond_for_each_slave(bond, slave, iter) { + pr_debug("s %p c_m %p\n", slave, - bond_prev_slave(bond, slave), slave->dev->netdev_ops->ndo_change_mtu); res = dev_set_mtu(slave->dev, new_mtu); @@ -3513,13 +3518,16 @@ static int bond_change_mtu(struct net_device *bond_dev, int new_mtu) unwind: /* unwind from head to the slave that failed */ - bond_for_each_slave_continue_reverse(bond, slave) { + bond_for_each_slave(bond, rollback_slave, iter) { int tmp_res; - tmp_res = dev_set_mtu(slave->dev, bond_dev->mtu); + if (rollback_slave == slave) + break; + + tmp_res = dev_set_mtu(rollback_slave->dev, bond_dev->mtu); if (tmp_res) { pr_debug("unwind err %d dev %s\n", - tmp_res, slave->dev->name); + tmp_res, rollback_slave->dev->name); } } @@ -3536,8 +3544,9 @@ unwind: static int bond_set_mac_address(struct net_device *bond_dev, void *addr) { struct bonding *bond = netdev_priv(bond_dev); + struct slave *slave, *rollback_slave; struct sockaddr *sa = addr, tmp_sa; - struct slave *slave; + struct list_head *iter; int res = 0; if (bond->params.mode == BOND_MODE_ALB) @@ -3571,7 +3580,7 @@ static int bond_set_mac_address(struct net_device *bond_dev, void *addr) * call to the base driver. */ - bond_for_each_slave(bond, slave) { + bond_for_each_slave(bond, slave, iter) { const struct net_device_ops *slave_ops = slave->dev->netdev_ops; pr_debug("slave %p %s\n", slave, slave->dev->name); @@ -3603,13 +3612,16 @@ unwind: tmp_sa.sa_family = bond_dev->type; /* unwind from head to the slave that failed */ - bond_for_each_slave_continue_reverse(bond, slave) { + bond_for_each_slave(bond, rollback_slave, iter) { int tmp_res; - tmp_res = dev_set_mac_address(slave->dev, &tmp_sa); + if (rollback_slave == slave) + break; + + tmp_res = dev_set_mac_address(rollback_slave->dev, &tmp_sa); if (tmp_res) { pr_debug("unwind err %d dev %s\n", - tmp_res, slave->dev->name); + tmp_res, rollback_slave->dev->name); } } @@ -3628,11 +3640,12 @@ unwind: */ void bond_xmit_slave_id(struct bonding *bond, struct sk_buff *skb, int slave_id) { + struct list_head *iter; struct slave *slave; int i = slave_id; /* Here we start from the slave with slave_id */ - bond_for_each_slave_rcu(bond, slave) { + bond_for_each_slave_rcu(bond, slave, iter) { if (--i < 0) { if (slave_can_tx(slave)) { bond_dev_queue_xmit(bond, skb, slave->dev); @@ -3643,7 +3656,7 @@ void bond_xmit_slave_id(struct bonding *bond, struct sk_buff *skb, int slave_id) /* Here we start from the first slave up to slave_id */ i = slave_id; - bond_for_each_slave_rcu(bond, slave) { + bond_for_each_slave_rcu(bond, slave, iter) { if (--i < 0) break; if (slave_can_tx(slave)) { @@ -3720,8 +3733,9 @@ static int bond_xmit_broadcast(struct sk_buff *skb, struct net_device *bond_dev) { struct bonding *bond = netdev_priv(bond_dev); struct slave *slave = NULL; + struct list_head *iter; - bond_for_each_slave_rcu(bond, slave) { + bond_for_each_slave_rcu(bond, slave, iter) { if (bond_is_last_slave(bond, slave)) break; if (IS_UP(slave->dev) && slave->link == BOND_LINK_UP) { @@ -3770,13 +3784,14 @@ static inline int bond_slave_override(struct bonding *bond, { struct slave *slave = NULL; struct slave *check_slave; + struct list_head *iter; 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_rcu(bond, check_slave) { + bond_for_each_slave_rcu(bond, check_slave, iter) { if (check_slave->queue_id == skb->queue_mapping) { slave = check_slave; break; @@ -3862,7 +3877,7 @@ static netdev_tx_t bond_start_xmit(struct sk_buff *skb, struct net_device *dev) return NETDEV_TX_BUSY; rcu_read_lock(); - if (!list_empty(&bond->slave_list)) + if (bond_has_slaves(bond)) ret = __bond_start_xmit(skb, dev); else kfree_skb(skb); @@ -3908,6 +3923,7 @@ static int bond_ethtool_get_settings(struct net_device *bond_dev, { struct bonding *bond = netdev_priv(bond_dev); unsigned long speed = 0; + struct list_head *iter; struct slave *slave; ecmd->duplex = DUPLEX_UNKNOWN; @@ -3919,7 +3935,7 @@ 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) { + bond_for_each_slave(bond, slave, iter) { if (SLAVE_IS_OK(slave)) { if (slave->speed != SPEED_UNKNOWN) speed += slave->speed; @@ -3994,7 +4010,6 @@ 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 */ @@ -4050,12 +4065,13 @@ 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 slave *slave, *tmp_slave; + struct list_head *iter; + struct slave *slave; bond_netpoll_cleanup(bond_dev); /* Release the bonded slaves */ - list_for_each_entry_safe(slave, tmp_slave, &bond->slave_list, list) + bond_for_each_slave(bond, slave, iter) __bond_release_one(bond_dev, slave->dev, true); pr_info("%s: released all slaves\n", bond_dev->name); diff --git a/drivers/net/bonding/bond_procfs.c b/drivers/net/bonding/bond_procfs.c index 20a6ee2..7af5646 100644 --- a/drivers/net/bonding/bond_procfs.c +++ b/drivers/net/bonding/bond_procfs.c @@ -10,8 +10,9 @@ static void *bond_info_seq_start(struct seq_file *seq, loff_t *pos) __acquires(&bond->lock) { struct bonding *bond = seq->private; - loff_t off = 0; + struct list_head *iter; struct slave *slave; + loff_t off = 0; /* make sure the bond won't be taken away */ rcu_read_lock(); @@ -20,7 +21,7 @@ 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) + bond_for_each_slave(bond, slave, iter) if (++off == *pos) return slave; diff --git a/drivers/net/bonding/bond_sysfs.c b/drivers/net/bonding/bond_sysfs.c index c29b836..e06c644 100644 --- a/drivers/net/bonding/bond_sysfs.c +++ b/drivers/net/bonding/bond_sysfs.c @@ -168,41 +168,6 @@ static const struct class_attribute class_attr_bonding_masters = { .namespace = bonding_namespace, }; -int bond_create_slave_symlinks(struct net_device *master, - struct net_device *slave) -{ - char linkname[IFNAMSIZ+7]; - int ret = 0; - - /* first, create a link from the slave back to the master */ - ret = sysfs_create_link(&(slave->dev.kobj), &(master->dev.kobj), - "master"); - if (ret) - return ret; - /* next, create a link from the master to the slave */ - sprintf(linkname, "slave_%s", slave->name); - ret = sysfs_create_link(&(master->dev.kobj), &(slave->dev.kobj), - linkname); - - /* free the master link created earlier in case of error */ - if (ret) - sysfs_remove_link(&(slave->dev.kobj), "master"); - - return ret; - -} - -void bond_destroy_slave_symlinks(struct net_device *master, - struct net_device *slave) -{ - char linkname[IFNAMSIZ+7]; - - sysfs_remove_link(&(slave->dev.kobj), "master"); - sprintf(linkname, "slave_%s", slave->name); - sysfs_remove_link(&(master->dev.kobj), linkname); -} - - /* * Show the slaves in the current bond. */ @@ -210,11 +175,12 @@ static ssize_t bonding_show_slaves(struct device *d, struct device_attribute *attr, char *buf) { struct bonding *bond = to_bond(d); + struct list_head *iter; struct slave *slave; int res = 0; read_lock(&bond->lock); - bond_for_each_slave(bond, slave) { + bond_for_each_slave(bond, slave, iter) { if (res > (PAGE_SIZE - IFNAMSIZ)) { /* not enough space for another interface name */ if ((PAGE_SIZE - res) > 10) @@ -326,7 +292,7 @@ static ssize_t bonding_store_mode(struct device *d, goto out; } - if (!list_empty(&bond->slave_list)) { + if (bond_has_slaves(bond)) { pr_err("unable to update mode of %s because it has slaves.\n", bond->dev->name); ret = -EPERM; @@ -522,7 +488,7 @@ static ssize_t bonding_store_fail_over_mac(struct device *d, if (!rtnl_trylock()) return restart_syscall(); - if (!list_empty(&bond->slave_list)) { + if (bond_has_slaves(bond)) { pr_err("%s: Can't alter fail_over_mac with slaves in bond.\n", bond->dev->name); ret = -EPERM; @@ -656,6 +622,7 @@ static ssize_t bonding_store_arp_targets(struct device *d, const char *buf, size_t count) { struct bonding *bond = to_bond(d); + struct list_head *iter; struct slave *slave; __be32 newtarget, *targets; unsigned long *targets_rx; @@ -688,7 +655,7 @@ 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) + bond_for_each_slave(bond, slave, iter) slave->target_last_arp_rx[ind] = jiffies; targets[ind] = newtarget; write_unlock_bh(&bond->lock); @@ -714,7 +681,7 @@ static ssize_t bonding_store_arp_targets(struct device *d, &newtarget); write_lock_bh(&bond->lock); - bond_for_each_slave(bond, slave) { + bond_for_each_slave(bond, slave, iter) { targets_rx = slave->target_last_arp_rx; j = ind; for (; (j < BOND_MAX_ARP_TARGETS-1) && targets[j+1]; j++) @@ -1111,6 +1078,7 @@ static ssize_t bonding_store_primary(struct device *d, const char *buf, size_t count) { struct bonding *bond = to_bond(d); + struct list_head *iter; char ifname[IFNAMSIZ]; struct slave *slave; @@ -1138,7 +1106,7 @@ static ssize_t bonding_store_primary(struct device *d, goto out; } - bond_for_each_slave(bond, slave) { + bond_for_each_slave(bond, slave, iter) { if (strncmp(slave->dev->name, ifname, IFNAMSIZ) == 0) { pr_info("%s: Setting %s as primary slave.\n", bond->dev->name, slave->dev->name); @@ -1286,6 +1254,7 @@ static ssize_t bonding_store_active_slave(struct device *d, { struct slave *slave, *old_active, *new_active; struct bonding *bond = to_bond(d); + struct list_head *iter; char ifname[IFNAMSIZ]; if (!rtnl_trylock()) @@ -1313,7 +1282,7 @@ static ssize_t bonding_store_active_slave(struct device *d, goto out; } - bond_for_each_slave(bond, slave) { + bond_for_each_slave(bond, slave, iter) { if (strncmp(slave->dev->name, ifname, IFNAMSIZ) == 0) { old_active = bond->curr_active_slave; new_active = slave; @@ -1493,6 +1462,7 @@ static ssize_t bonding_show_queue_id(struct device *d, char *buf) { struct bonding *bond = to_bond(d); + struct list_head *iter; struct slave *slave; int res = 0; @@ -1500,7 +1470,7 @@ static ssize_t bonding_show_queue_id(struct device *d, return restart_syscall(); read_lock(&bond->lock); - bond_for_each_slave(bond, slave) { + bond_for_each_slave(bond, slave, iter) { if (res > (PAGE_SIZE - IFNAMSIZ - 6)) { /* not enough space for another interface_name:queue_id pair */ if ((PAGE_SIZE - res) > 10) @@ -1529,6 +1499,7 @@ static ssize_t bonding_store_queue_id(struct device *d, { struct slave *slave, *update_slave; struct bonding *bond = to_bond(d); + struct list_head *iter; u16 qid; int ret = count; char *delim; @@ -1565,7 +1536,7 @@ 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) { + bond_for_each_slave(bond, slave, iter) { if (sdev == slave->dev) /* * We don't need to check the matching @@ -1619,6 +1590,7 @@ static ssize_t bonding_store_slaves_active(struct device *d, { struct bonding *bond = to_bond(d); int new_value, ret = count; + struct list_head *iter; struct slave *slave; if (sscanf(buf, "%d", &new_value) != 1) { @@ -1641,7 +1613,7 @@ static ssize_t bonding_store_slaves_active(struct device *d, } read_lock(&bond->lock); - bond_for_each_slave(bond, slave) { + bond_for_each_slave(bond, slave, iter) { 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 03cf3fd..5b71601 100644 --- a/drivers/net/bonding/bonding.h +++ b/drivers/net/bonding/bonding.h @@ -72,63 +72,40 @@ res; }) /* slave list primitives */ -#define bond_to_slave(ptr) list_entry(ptr, struct slave, list) +#define bond_slave_list(bond) (&(bond)->dev->adj_list.lower) + +#define bond_has_slaves(bond) !list_empty(bond_slave_list(bond)) /* IMPORTANT: bond_first/last_slave can return NULL in case of an empty list */ #define bond_first_slave(bond) \ - list_first_entry_or_null(&(bond)->slave_list, struct slave, list) + (bond_has_slaves(bond) ? \ + netdev_adjacent_get_private(bond_slave_list(bond)->next) : \ + NULL) #define bond_last_slave(bond) \ - (list_empty(&(bond)->slave_list) ? NULL : \ - bond_to_slave((bond)->slave_list.prev)) + (bond_has_slaves(bond) ? \ + netdev_adjacent_get_private(bond_slave_list(bond)->prev) : \ + NULL) -#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) +#define bond_is_first_slave(bond, pos) (pos == bond_first_slave(bond)) +#define bond_is_last_slave(bond, pos) (pos == bond_last_slave(bond)) /* 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. - * @pos: current slave. - * @cnt: counter for max number of moves - * @start: starting point. - * - * Caller must hold bond->lock - */ -#define bond_for_each_slave_from(bond, pos, cnt, start) \ - for (cnt = 0, pos = start; pos && cnt < (bond)->slave_cnt; \ - cnt++, pos = bond_next_slave(bond, pos)) +#define bond_next_slave(bond, pos) __bond_next_slave(bond, pos) /** * bond_for_each_slave - iterate over all slaves * @bond: the bond holding this list * @pos: current slave + * @iter: list_head * iterator * * Caller must hold bond->lock */ -#define bond_for_each_slave(bond, pos) \ - list_for_each_entry(pos, &(bond)->slave_list, list) +#define bond_for_each_slave(bond, pos, iter) \ + netdev_for_each_lower_private((bond)->dev, pos, iter) /* Caller must have rcu_read_lock */ -#define bond_for_each_slave_rcu(bond, pos) \ - list_for_each_entry_rcu(pos, &(bond)->slave_list, list) - -/** - * 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_continue_reverse(bond, pos) \ - list_for_each_entry_continue_reverse(pos, &(bond)->slave_list, list) +#define bond_for_each_slave_rcu(bond, pos, iter) \ + netdev_for_each_lower_private_rcu((bond)->dev, pos, iter) #ifdef CONFIG_NET_POLL_CONTROLLER extern atomic_t netpoll_block_tx; @@ -188,7 +165,6 @@ struct bond_parm_tbl { struct slave { struct net_device *dev; /* first - useful for panic debug */ - struct list_head list; struct bonding *bond; /* our master */ int delay; unsigned long jiffies; @@ -228,7 +204,6 @@ struct slave { */ struct bonding { struct net_device *dev; /* first - useful for panic debug */ - struct list_head slave_list; struct slave *curr_active_slave; struct slave *current_arp_slave; struct slave *primary_slave; @@ -269,6 +244,34 @@ struct bonding { ((struct slave *) rtnl_dereference(dev->rx_handler_data)) /** + * __bond_next_slave - get the next slave after the one provided + * @bond - bonding struct + * @slave - the slave provided + * + * Returns the next slave after the slave provided, first slave if the + * slave provided is the last slave and NULL if slave is not found + */ +static inline struct slave *__bond_next_slave(struct bonding *bond, + struct slave *slave) +{ + struct slave *slave_iter; + struct list_head *iter; + bool found = false; + + netdev_for_each_lower_private(bond->dev, slave_iter, iter) { + if (found) + return slave_iter; + if (slave_iter == slave) + found = true; + } + + if (found) + return bond_first_slave(bond); + + return NULL; +} + +/** * Returns NULL if the net_device does not belong to any of the bond's slaves * * Caller must hold bond lock for read @@ -276,13 +279,7 @@ struct bonding { static inline struct slave *bond_get_slave_by_dev(struct bonding *bond, struct net_device *slave_dev) { - struct slave *slave = NULL; - - bond_for_each_slave(bond, slave) - if (slave->dev == slave_dev) - return slave; - - return NULL; + return netdev_lower_dev_get_private(bond->dev, slave_dev); } static inline struct bonding *bond_get_bond_by_slave(struct slave *slave) @@ -439,8 +436,6 @@ int bond_create(struct net *net, const char *name); int bond_create_sysfs(struct bond_net *net); void bond_destroy_sysfs(struct bond_net *net); void bond_prepare_sysfs_group(struct bonding *bond); -int bond_create_slave_symlinks(struct net_device *master, struct net_device *slave); -void bond_destroy_slave_symlinks(struct net_device *master, struct net_device *slave); int bond_enslave(struct net_device *bond_dev, struct net_device *slave_dev); int bond_release(struct net_device *bond_dev, struct net_device *slave_dev); void bond_mii_monitor(struct work_struct *); @@ -492,9 +487,10 @@ 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) { + struct list_head *iter; struct slave *tmp; - bond_for_each_slave(bond, tmp) + bond_for_each_slave(bond, tmp, iter) if (ether_addr_equal_64bits(mac, tmp->dev->dev_addr)) return tmp; diff --git a/drivers/net/ethernet/chelsio/cxgb4/cxgb4_main.c b/drivers/net/ethernet/chelsio/cxgb4/cxgb4_main.c index c73cabd..85d0cda 100644 --- a/drivers/net/ethernet/chelsio/cxgb4/cxgb4_main.c +++ b/drivers/net/ethernet/chelsio/cxgb4/cxgb4_main.c @@ -3983,6 +3983,7 @@ static int cxgb4_inet6addr_handler(struct notifier_block *this, struct net_device *event_dev; int ret = NOTIFY_DONE; struct bonding *bond = netdev_priv(ifa->idev->dev); + struct list_head *iter; struct slave *slave; struct pci_dev *first_pdev = NULL; @@ -3995,7 +3996,7 @@ static int cxgb4_inet6addr_handler(struct notifier_block *this, * in all of them only once. */ read_lock(&bond->lock); - bond_for_each_slave(bond, slave) { + bond_for_each_slave(bond, slave, iter) { if (!first_pdev) { ret = clip_add(slave->dev, ifa, event); /* If clip_add is success then only initialize diff --git a/include/linux/netdevice.h b/include/linux/netdevice.h index 3de49ac..b4cfb63 100644 --- a/include/linux/netdevice.h +++ b/include/linux/netdevice.h @@ -1143,8 +1143,18 @@ struct net_device { struct list_head dev_list; struct list_head napi_list; struct list_head unreg_list; - struct list_head upper_dev_list; /* List of upper devices */ - struct list_head lower_dev_list; + + /* directly linked devices, like slaves for bonding */ + struct { + struct list_head upper; + struct list_head lower; + } adj_list; + + /* all linked devices, *including* neighbours */ + struct { + struct list_head upper; + struct list_head lower; + } all_adj_list; /* currently active device features */ @@ -2813,24 +2823,49 @@ extern int bpf_jit_enable; extern bool netdev_has_upper_dev(struct net_device *dev, struct net_device *upper_dev); extern bool netdev_has_any_upper_dev(struct net_device *dev); -extern struct net_device *netdev_upper_get_next_dev_rcu(struct net_device *dev, - struct list_head **iter); +extern struct net_device *netdev_all_upper_get_next_dev_rcu(struct net_device *dev, + struct list_head **iter); /* iterate through upper list, must be called under RCU read lock */ -#define netdev_for_each_upper_dev_rcu(dev, upper, iter) \ - for (iter = &(dev)->upper_dev_list, \ - upper = netdev_upper_get_next_dev_rcu(dev, &(iter)); \ - upper; \ - upper = netdev_upper_get_next_dev_rcu(dev, &(iter))) - +#define netdev_for_each_all_upper_dev_rcu(dev, updev, iter) \ + for (iter = &(dev)->all_adj_list.upper, \ + updev = netdev_all_upper_get_next_dev_rcu(dev, &(iter)); \ + updev; \ + updev = netdev_all_upper_get_next_dev_rcu(dev, &(iter))) + +extern void *netdev_lower_get_next_private(struct net_device *dev, + struct list_head **iter); +extern void *netdev_lower_get_next_private_rcu(struct net_device *dev, + struct list_head **iter); + +#define netdev_for_each_lower_private(dev, priv, iter) \ + for (iter = (dev)->adj_list.lower.next, \ + priv = netdev_lower_get_next_private(dev, &(iter)); \ + priv; \ + priv = netdev_lower_get_next_private(dev, &(iter))) + +#define netdev_for_each_lower_private_rcu(dev, priv, iter) \ + for (iter = &(dev)->adj_list.lower, \ + priv = netdev_lower_get_next_private_rcu(dev, &(iter)); \ + priv; \ + priv = netdev_lower_get_next_private_rcu(dev, &(iter))) + +extern void *netdev_adjacent_get_private(struct list_head *adj_list); extern struct net_device *netdev_master_upper_dev_get(struct net_device *dev); extern struct net_device *netdev_master_upper_dev_get_rcu(struct net_device *dev); extern int netdev_upper_dev_link(struct net_device *dev, struct net_device *upper_dev); extern int netdev_master_upper_dev_link(struct net_device *dev, struct net_device *upper_dev); +extern int netdev_master_upper_dev_link_private(struct net_device *dev, + struct net_device *upper_dev, + void *private); extern void netdev_upper_dev_unlink(struct net_device *dev, struct net_device *upper_dev); +extern void *netdev_lower_dev_get_private_rcu(struct net_device *dev, + struct net_device *lower_dev); +extern void *netdev_lower_dev_get_private(struct net_device *dev, + struct net_device *lower_dev); extern int skb_checksum_help(struct sk_buff *skb); extern struct sk_buff *__skb_gso_segment(struct sk_buff *skb, netdev_features_t features, bool tx_path); diff --git a/net/8021q/vlan.c b/net/8021q/vlan.c index 61fc573..b3d17d1 100644 --- a/net/8021q/vlan.c +++ b/net/8021q/vlan.c @@ -98,14 +98,14 @@ void unregister_vlan_dev(struct net_device *dev, struct list_head *head) vlan_gvrp_request_leave(dev); vlan_group_set_device(grp, vlan->vlan_proto, vlan_id, NULL); + + netdev_upper_dev_unlink(real_dev, dev); /* Because unregister_netdevice_queue() makes sure at least one rcu * grace period is respected before device freeing, * we dont need to call synchronize_net() here. */ unregister_netdevice_queue(dev, head); - netdev_upper_dev_unlink(real_dev, dev); - if (grp->nr_vlan_devs == 0) { vlan_mvrp_uninit_applicant(real_dev); vlan_gvrp_uninit_applicant(real_dev); @@ -169,13 +169,13 @@ int register_vlan_dev(struct net_device *dev) if (err < 0) goto out_uninit_mvrp; - err = netdev_upper_dev_link(real_dev, dev); - if (err) - goto out_uninit_mvrp; - err = register_netdevice(dev); if (err < 0) - goto out_upper_dev_unlink; + goto out_uninit_mvrp; + + err = netdev_upper_dev_link(real_dev, dev); + if (err) + goto out_unregister_netdev; /* Account for reference in struct vlan_dev_priv */ dev_hold(real_dev); @@ -191,8 +191,8 @@ int register_vlan_dev(struct net_device *dev) return 0; -out_upper_dev_unlink: - netdev_upper_dev_unlink(real_dev, dev); +out_unregister_netdev: + unregister_netdevice(dev); out_uninit_mvrp: if (grp->nr_vlan_devs == 0) vlan_mvrp_uninit_applicant(real_dev); diff --git a/net/core/dev.c b/net/core/dev.c index 5c713f2..25ab6fe 100644 --- a/net/core/dev.c +++ b/net/core/dev.c @@ -4373,42 +4373,40 @@ struct netdev_adjacent { /* upper master flag, there can only be one master device per list */ bool master; - /* indicates that this dev is our first-level lower/upper device */ - bool neighbour; - /* counter for the number of times this device was added to us */ u16 ref_nr; + /* private field for the users */ + void *private; + struct list_head list; struct rcu_head rcu; }; -static struct netdev_adjacent *__netdev_find_adj(struct net_device *dev, - struct net_device *adj_dev, - bool upper) +static struct netdev_adjacent *__netdev_find_adj_rcu(struct net_device *dev, + struct net_device *adj_dev, + struct list_head *adj_list) { struct netdev_adjacent *adj; - struct list_head *dev_list; - dev_list = upper ? &dev->upper_dev_list : &dev->lower_dev_list; - - list_for_each_entry(adj, dev_list, list) { + list_for_each_entry_rcu(adj, adj_list, list) { if (adj->dev == adj_dev) return adj; } return NULL; } -static inline struct netdev_adjacent *__netdev_find_upper(struct net_device *dev, - struct net_device *udev) +static struct netdev_adjacent *__netdev_find_adj(struct net_device *dev, + struct net_device *adj_dev, + struct list_head *adj_list) { - return __netdev_find_adj(dev, udev, true); -} + struct netdev_adjacent *adj; -static inline struct netdev_adjacent *__netdev_find_lower(struct net_device *dev, - struct net_device *ldev) -{ - return __netdev_find_adj(dev, ldev, false); + list_for_each_entry(adj, adj_list, list) { + if (adj->dev == adj_dev) + return adj; + } + return NULL; } /** @@ -4425,7 +4423,7 @@ bool netdev_has_upper_dev(struct net_device *dev, { ASSERT_RTNL(); - return __netdev_find_upper(dev, upper_dev); + return __netdev_find_adj(dev, upper_dev, &dev->all_adj_list.upper); } EXPORT_SYMBOL(netdev_has_upper_dev); @@ -4440,7 +4438,7 @@ bool netdev_has_any_upper_dev(struct net_device *dev) { ASSERT_RTNL(); - return !list_empty(&dev->upper_dev_list); + return !list_empty(&dev->all_adj_list.upper); } EXPORT_SYMBOL(netdev_has_any_upper_dev); @@ -4457,10 +4455,10 @@ struct net_device *netdev_master_upper_dev_get(struct net_device *dev) ASSERT_RTNL(); - if (list_empty(&dev->upper_dev_list)) + if (list_empty(&dev->adj_list.upper)) return NULL; - upper = list_first_entry(&dev->upper_dev_list, + upper = list_first_entry(&dev->adj_list.upper, struct netdev_adjacent, list); if (likely(upper->master)) return upper->dev; @@ -4468,15 +4466,26 @@ struct net_device *netdev_master_upper_dev_get(struct net_device *dev) } EXPORT_SYMBOL(netdev_master_upper_dev_get); -/* netdev_upper_get_next_dev_rcu - Get the next dev from upper list +void *netdev_adjacent_get_private(struct list_head *adj_list) +{ + struct netdev_adjacent *adj; + + adj = list_entry(adj_list, struct netdev_adjacent, list); + + return adj->private; +} +EXPORT_SYMBOL(netdev_adjacent_get_private); + +/** + * netdev_all_upper_get_next_dev_rcu - Get the next dev from upper list * @dev: device * @iter: list_head ** of the current position * * Gets the next device from the dev's upper list, starting from iter * position. The caller must hold RCU read lock. */ -struct net_device *netdev_upper_get_next_dev_rcu(struct net_device *dev, - struct list_head **iter) +struct net_device *netdev_all_upper_get_next_dev_rcu(struct net_device *dev, + struct list_head **iter) { struct netdev_adjacent *upper; @@ -4484,14 +4493,71 @@ struct net_device *netdev_upper_get_next_dev_rcu(struct net_device *dev, upper = list_entry_rcu((*iter)->next, struct netdev_adjacent, list); - if (&upper->list == &dev->upper_dev_list) + if (&upper->list == &dev->all_adj_list.upper) return NULL; *iter = &upper->list; return upper->dev; } -EXPORT_SYMBOL(netdev_upper_get_next_dev_rcu); +EXPORT_SYMBOL(netdev_all_upper_get_next_dev_rcu); + +/** + * netdev_lower_get_next_private - Get the next ->private from the + * lower neighbour list + * @dev: device + * @iter: list_head ** of the current position + * + * Gets the next netdev_adjacent->private from the dev's lower neighbour + * list, starting from iter position. The caller must hold either hold the + * RTNL lock or its own locking that guarantees that the neighbour lower + * list will remain unchainged. + */ +void *netdev_lower_get_next_private(struct net_device *dev, + struct list_head **iter) +{ + struct netdev_adjacent *lower; + + lower = list_entry(*iter, struct netdev_adjacent, list); + + if (&lower->list == &dev->adj_list.lower) + return NULL; + + if (iter) + *iter = lower->list.next; + + return lower->private; +} +EXPORT_SYMBOL(netdev_lower_get_next_private); + +/** + * netdev_lower_get_next_private_rcu - Get the next ->private from the + * lower neighbour list, RCU + * variant + * @dev: device + * @iter: list_head ** of the current position + * + * Gets the next netdev_adjacent->private from the dev's lower neighbour + * list, starting from iter position. The caller must hold RCU read lock. + */ +void *netdev_lower_get_next_private_rcu(struct net_device *dev, + struct list_head **iter) +{ + struct netdev_adjacent *lower; + + WARN_ON_ONCE(!rcu_read_lock_held()); + + lower = list_entry_rcu((*iter)->next, struct netdev_adjacent, list); + + if (&lower->list == &dev->adj_list.lower) + return NULL; + + if (iter) + *iter = &lower->list; + + return lower->private; +} +EXPORT_SYMBOL(netdev_lower_get_next_private_rcu); /** * netdev_master_upper_dev_get_rcu - Get master upper device @@ -4504,7 +4570,7 @@ struct net_device *netdev_master_upper_dev_get_rcu(struct net_device *dev) { struct netdev_adjacent *upper; - upper = list_first_or_null_rcu(&dev->upper_dev_list, + upper = list_first_or_null_rcu(&dev->adj_list.upper, struct netdev_adjacent, list); if (upper && likely(upper->master)) return upper->dev; @@ -4514,15 +4580,16 @@ EXPORT_SYMBOL(netdev_master_upper_dev_get_rcu); static int __netdev_adjacent_dev_insert(struct net_device *dev, struct net_device *adj_dev, - bool neighbour, bool master, - bool upper) + struct list_head *dev_list, + void *private, bool master) { struct netdev_adjacent *adj; + char linkname[IFNAMSIZ+7]; + int ret; - adj = __netdev_find_adj(dev, adj_dev, upper); + adj = __netdev_find_adj(dev, adj_dev, dev_list); if (adj) { - BUG_ON(neighbour); adj->ref_nr++; return 0; } @@ -4533,124 +4600,178 @@ static int __netdev_adjacent_dev_insert(struct net_device *dev, adj->dev = adj_dev; adj->master = master; - adj->neighbour = neighbour; adj->ref_nr = 1; - + adj->private = private; dev_hold(adj_dev); - pr_debug("dev_hold for %s, because of %s link added from %s to %s\n", - adj_dev->name, upper ? "upper" : "lower", dev->name, - adj_dev->name); - if (!upper) { - list_add_tail_rcu(&adj->list, &dev->lower_dev_list); - return 0; + pr_debug("dev_hold for %s, because of link added from %s to %s\n", + adj_dev->name, dev->name, adj_dev->name); + + if (dev_list == &dev->adj_list.lower) { + sprintf(linkname, "lower_%s", adj_dev->name); + ret = sysfs_create_link(&(dev->dev.kobj), + &(adj_dev->dev.kobj), linkname); + if (ret) + goto free_adj; + } else if (dev_list == &dev->adj_list.upper) { + sprintf(linkname, "upper_%s", adj_dev->name); + ret = sysfs_create_link(&(dev->dev.kobj), + &(adj_dev->dev.kobj), linkname); + if (ret) + goto free_adj; } - /* Ensure that master upper link is always the first item in list. */ - if (master) - list_add_rcu(&adj->list, &dev->upper_dev_list); - else - list_add_tail_rcu(&adj->list, &dev->upper_dev_list); + /* Ensure that master link is always the first item in list. */ + if (master) { + ret = sysfs_create_link(&(dev->dev.kobj), + &(adj_dev->dev.kobj), "master"); + if (ret) + goto remove_symlinks; + + list_add_rcu(&adj->list, dev_list); + } else { + list_add_tail_rcu(&adj->list, dev_list); + } return 0; -} -static inline int __netdev_upper_dev_insert(struct net_device *dev, - struct net_device *udev, - bool master, bool neighbour) -{ - return __netdev_adjacent_dev_insert(dev, udev, neighbour, master, - true); -} +remove_symlinks: + if (dev_list == &dev->adj_list.lower) { + sprintf(linkname, "lower_%s", adj_dev->name); + sysfs_remove_link(&(dev->dev.kobj), linkname); + } else if (dev_list == &dev->adj_list.upper) { + sprintf(linkname, "upper_%s", adj_dev->name); + sysfs_remove_link(&(dev->dev.kobj), linkname); + } -static inline int __netdev_lower_dev_insert(struct net_device *dev, - struct net_device *ldev, - bool neighbour) -{ - return __netdev_adjacent_dev_insert(dev, ldev, neighbour, false, - false); +free_adj: + kfree(adj); + + return ret; } void __netdev_adjacent_dev_remove(struct net_device *dev, - struct net_device *adj_dev, bool upper) + struct net_device *adj_dev, + struct list_head *dev_list) { struct netdev_adjacent *adj; + char linkname[IFNAMSIZ+7]; - if (upper) - adj = __netdev_find_upper(dev, adj_dev); - else - adj = __netdev_find_lower(dev, adj_dev); + adj = __netdev_find_adj(dev, adj_dev, dev_list); - if (!adj) + if (!adj) { + pr_err("tried to remove device %s from %s\n", + dev->name, adj_dev->name); BUG(); + } if (adj->ref_nr > 1) { + pr_debug("%s to %s ref_nr-- = %d\n", dev->name, adj_dev->name, + adj->ref_nr-1); adj->ref_nr--; return; } + if (adj->master) + sysfs_remove_link(&(dev->dev.kobj), "master"); + + if (dev_list == &dev->adj_list.lower) { + sprintf(linkname, "lower_%s", adj_dev->name); + sysfs_remove_link(&(dev->dev.kobj), linkname); + } else if (dev_list == &dev->adj_list.upper) { + sprintf(linkname, "upper_%s", adj_dev->name); + sysfs_remove_link(&(dev->dev.kobj), linkname); + } + list_del_rcu(&adj->list); - pr_debug("dev_put for %s, because of %s link removed from %s to %s\n", - adj_dev->name, upper ? "upper" : "lower", dev->name, - adj_dev->name); + pr_debug("dev_put for %s, because link removed from %s to %s\n", + adj_dev->name, dev->name, adj_dev->name); dev_put(adj_dev); kfree_rcu(adj, rcu); } -static inline void __netdev_upper_dev_remove(struct net_device *dev, - struct net_device *udev) -{ - return __netdev_adjacent_dev_remove(dev, udev, true); -} - -static inline void __netdev_lower_dev_remove(struct net_device *dev, - struct net_device *ldev) -{ - return __netdev_adjacent_dev_remove(dev, ldev, false); -} - -int __netdev_adjacent_dev_insert_link(struct net_device *dev, - struct net_device *upper_dev, - bool master, bool neighbour) +int __netdev_adjacent_dev_link_lists(struct net_device *dev, + struct net_device *upper_dev, + struct list_head *up_list, + struct list_head *down_list, + void *private, bool master) { int ret; - ret = __netdev_upper_dev_insert(dev, upper_dev, master, neighbour); + ret = __netdev_adjacent_dev_insert(dev, upper_dev, up_list, private, + master); if (ret) return ret; - ret = __netdev_lower_dev_insert(upper_dev, dev, neighbour); + ret = __netdev_adjacent_dev_insert(upper_dev, dev, down_list, private, + false); if (ret) { - __netdev_upper_dev_remove(dev, upper_dev); + __netdev_adjacent_dev_remove(dev, upper_dev, up_list); return ret; } return 0; } -static inline int __netdev_adjacent_dev_link(struct net_device *dev, - struct net_device *udev) +int __netdev_adjacent_dev_link(struct net_device *dev, + struct net_device *upper_dev) { - return __netdev_adjacent_dev_insert_link(dev, udev, false, false); + return __netdev_adjacent_dev_link_lists(dev, upper_dev, + &dev->all_adj_list.upper, + &upper_dev->all_adj_list.lower, + NULL, false); } -static inline int __netdev_adjacent_dev_link_neighbour(struct net_device *dev, - struct net_device *udev, - bool master) +void __netdev_adjacent_dev_unlink_lists(struct net_device *dev, + struct net_device *upper_dev, + struct list_head *up_list, + struct list_head *down_list) { - return __netdev_adjacent_dev_insert_link(dev, udev, master, true); + __netdev_adjacent_dev_remove(dev, upper_dev, up_list); + __netdev_adjacent_dev_remove(upper_dev, dev, down_list); } void __netdev_adjacent_dev_unlink(struct net_device *dev, struct net_device *upper_dev) { - __netdev_upper_dev_remove(dev, upper_dev); - __netdev_lower_dev_remove(upper_dev, dev); + __netdev_adjacent_dev_unlink_lists(dev, upper_dev, + &dev->all_adj_list.upper, + &upper_dev->all_adj_list.lower); +} + +int __netdev_adjacent_dev_link_neighbour(struct net_device *dev, + struct net_device *upper_dev, + void *private, bool master) +{ + int ret = __netdev_adjacent_dev_link(dev, upper_dev); + + if (ret) + return ret; + + ret = __netdev_adjacent_dev_link_lists(dev, upper_dev, + &dev->adj_list.upper, + &upper_dev->adj_list.lower, + private, master); + if (ret) { + __netdev_adjacent_dev_unlink(dev, upper_dev); + return ret; + } + + return 0; } +void __netdev_adjacent_dev_unlink_neighbour(struct net_device *dev, + struct net_device *upper_dev) +{ + __netdev_adjacent_dev_unlink(dev, upper_dev); + __netdev_adjacent_dev_unlink_lists(dev, upper_dev, + &dev->adj_list.upper, + &upper_dev->adj_list.lower); +} static int __netdev_upper_dev_link(struct net_device *dev, - struct net_device *upper_dev, bool master) + struct net_device *upper_dev, bool master, + void *private) { struct netdev_adjacent *i, *j, *to_i, *to_j; int ret = 0; @@ -4661,26 +4782,29 @@ static int __netdev_upper_dev_link(struct net_device *dev, return -EBUSY; /* To prevent loops, check if dev is not upper device to upper_dev. */ - if (__netdev_find_upper(upper_dev, dev)) + if (__netdev_find_adj(upper_dev, dev, &upper_dev->all_adj_list.upper)) return -EBUSY; - if (__netdev_find_upper(dev, upper_dev)) + if (__netdev_find_adj(dev, upper_dev, &dev->all_adj_list.upper)) return -EEXIST; if (master && netdev_master_upper_dev_get(dev)) return -EBUSY; - ret = __netdev_adjacent_dev_link_neighbour(dev, upper_dev, master); + ret = __netdev_adjacent_dev_link_neighbour(dev, upper_dev, private, + master); if (ret) return ret; /* Now that we linked these devs, make all the upper_dev's - * upper_dev_list visible to every dev's lower_dev_list and vice + * all_adj_list.upper visible to every dev's all_adj_list.lower an * versa, and don't forget the devices itself. All of these * links are non-neighbours. */ - list_for_each_entry(i, &dev->lower_dev_list, list) { - list_for_each_entry(j, &upper_dev->upper_dev_list, list) { + list_for_each_entry(i, &dev->all_adj_list.lower, list) { + list_for_each_entry(j, &upper_dev->all_adj_list.upper, list) { + pr_debug("Interlinking %s with %s, non-neighbour\n", + i->dev->name, j->dev->name); ret = __netdev_adjacent_dev_link(i->dev, j->dev); if (ret) goto rollback_mesh; @@ -4688,14 +4812,18 @@ static int __netdev_upper_dev_link(struct net_device *dev, } /* add dev to every upper_dev's upper device */ - list_for_each_entry(i, &upper_dev->upper_dev_list, list) { + list_for_each_entry(i, &upper_dev->all_adj_list.upper, list) { + pr_debug("linking %s's upper device %s with %s\n", + upper_dev->name, i->dev->name, dev->name); ret = __netdev_adjacent_dev_link(dev, i->dev); if (ret) goto rollback_upper_mesh; } /* add upper_dev to every dev's lower device */ - list_for_each_entry(i, &dev->lower_dev_list, list) { + list_for_each_entry(i, &dev->all_adj_list.lower, list) { + pr_debug("linking %s's lower device %s with %s\n", dev->name, + i->dev->name, upper_dev->name); ret = __netdev_adjacent_dev_link(i->dev, upper_dev); if (ret) goto rollback_lower_mesh; @@ -4706,7 +4834,7 @@ static int __netdev_upper_dev_link(struct net_device *dev, rollback_lower_mesh: to_i = i; - list_for_each_entry(i, &dev->lower_dev_list, list) { + list_for_each_entry(i, &dev->all_adj_list.lower, list) { if (i == to_i) break; __netdev_adjacent_dev_unlink(i->dev, upper_dev); @@ -4716,7 +4844,7 @@ rollback_lower_mesh: rollback_upper_mesh: to_i = i; - list_for_each_entry(i, &upper_dev->upper_dev_list, list) { + list_for_each_entry(i, &upper_dev->all_adj_list.upper, list) { if (i == to_i) break; __netdev_adjacent_dev_unlink(dev, i->dev); @@ -4727,8 +4855,8 @@ rollback_upper_mesh: rollback_mesh: to_i = i; to_j = j; - list_for_each_entry(i, &dev->lower_dev_list, list) { - list_for_each_entry(j, &upper_dev->upper_dev_list, list) { + list_for_each_entry(i, &dev->all_adj_list.lower, list) { + list_for_each_entry(j, &upper_dev->all_adj_list.upper, list) { if (i == to_i && j == to_j) break; __netdev_adjacent_dev_unlink(i->dev, j->dev); @@ -4737,7 +4865,7 @@ rollback_mesh: break; } - __netdev_adjacent_dev_unlink(dev, upper_dev); + __netdev_adjacent_dev_unlink_neighbour(dev, upper_dev); return ret; } @@ -4755,7 +4883,7 @@ rollback_mesh: int netdev_upper_dev_link(struct net_device *dev, struct net_device *upper_dev) { - return __netdev_upper_dev_link(dev, upper_dev, false); + return __netdev_upper_dev_link(dev, upper_dev, false, NULL); } EXPORT_SYMBOL(netdev_upper_dev_link); @@ -4773,10 +4901,18 @@ EXPORT_SYMBOL(netdev_upper_dev_link); int netdev_master_upper_dev_link(struct net_device *dev, struct net_device *upper_dev) { - return __netdev_upper_dev_link(dev, upper_dev, true); + return __netdev_upper_dev_link(dev, upper_dev, true, NULL); } EXPORT_SYMBOL(netdev_master_upper_dev_link); +int netdev_master_upper_dev_link_private(struct net_device *dev, + struct net_device *upper_dev, + void *private) +{ + return __netdev_upper_dev_link(dev, upper_dev, true, private); +} +EXPORT_SYMBOL(netdev_master_upper_dev_link_private); + /** * netdev_upper_dev_unlink - Removes a link to upper device * @dev: device @@ -4791,29 +4927,59 @@ void netdev_upper_dev_unlink(struct net_device *dev, struct netdev_adjacent *i, *j; ASSERT_RTNL(); - __netdev_adjacent_dev_unlink(dev, upper_dev); + __netdev_adjacent_dev_unlink_neighbour(dev, upper_dev); /* Here is the tricky part. We must remove all dev's lower * devices from all upper_dev's upper devices and vice * versa, to maintain the graph relationship. */ - list_for_each_entry(i, &dev->lower_dev_list, list) - list_for_each_entry(j, &upper_dev->upper_dev_list, list) + list_for_each_entry(i, &dev->all_adj_list.lower, list) + list_for_each_entry(j, &upper_dev->all_adj_list.upper, list) __netdev_adjacent_dev_unlink(i->dev, j->dev); /* remove also the devices itself from lower/upper device * list */ - list_for_each_entry(i, &dev->lower_dev_list, list) + list_for_each_entry(i, &dev->all_adj_list.lower, list) __netdev_adjacent_dev_unlink(i->dev, upper_dev); - list_for_each_entry(i, &upper_dev->upper_dev_list, list) + list_for_each_entry(i, &upper_dev->all_adj_list.upper, list) __netdev_adjacent_dev_unlink(dev, i->dev); call_netdevice_notifiers(NETDEV_CHANGEUPPER, dev); } EXPORT_SYMBOL(netdev_upper_dev_unlink); +void *netdev_lower_dev_get_private_rcu(struct net_device *dev, + struct net_device *lower_dev) +{ + struct netdev_adjacent *lower; + + if (!lower_dev) + return NULL; + lower = __netdev_find_adj_rcu(dev, lower_dev, &dev->adj_list.lower); + if (!lower) + return NULL; + + return lower->private; +} +EXPORT_SYMBOL(netdev_lower_dev_get_private_rcu); + +void *netdev_lower_dev_get_private(struct net_device *dev, + struct net_device *lower_dev) +{ + struct netdev_adjacent *lower; + + if (!lower_dev) + return NULL; + lower = __netdev_find_adj(dev, lower_dev, &dev->adj_list.lower); + if (!lower) + return NULL; + + return lower->private; +} +EXPORT_SYMBOL(netdev_lower_dev_get_private); + static void dev_change_rx_flags(struct net_device *dev, int flags) { const struct net_device_ops *ops = dev->netdev_ops; @@ -6069,8 +6235,10 @@ struct net_device *alloc_netdev_mqs(int sizeof_priv, const char *name, INIT_LIST_HEAD(&dev->napi_list); INIT_LIST_HEAD(&dev->unreg_list); INIT_LIST_HEAD(&dev->link_watch_list); - INIT_LIST_HEAD(&dev->upper_dev_list); - INIT_LIST_HEAD(&dev->lower_dev_list); + INIT_LIST_HEAD(&dev->adj_list.upper); + INIT_LIST_HEAD(&dev->adj_list.lower); + INIT_LIST_HEAD(&dev->all_adj_list.upper); + INIT_LIST_HEAD(&dev->all_adj_list.lower); dev->priv_flags = IFF_XMIT_DST_RELEASE; setup(dev); |