diff options
Diffstat (limited to 'drivers/net/bonding/bond_main.c')
| -rw-r--r-- | drivers/net/bonding/bond_main.c | 516 |
1 files changed, 396 insertions, 120 deletions
diff --git a/drivers/net/bonding/bond_main.c b/drivers/net/bonding/bond_main.c index 2e70e43c5df5..84ecbc6fa0ff 100644 --- a/drivers/net/bonding/bond_main.c +++ b/drivers/net/bonding/bond_main.c @@ -79,6 +79,7 @@ #include <net/pkt_sched.h> #include <linux/rculist.h> #include <net/flow_dissector.h> +#include <net/xfrm.h> #include <net/bonding.h> #include <net/bond_3ad.h> #include <net/bond_alb.h> @@ -278,8 +279,6 @@ const char *bond_mode_name(int mode) return names[mode]; } -/*---------------------------------- VLAN -----------------------------------*/ - /** * bond_dev_queue_xmit - Prepare skb for xmit. * @@ -287,7 +286,7 @@ const char *bond_mode_name(int mode) * @skb: hw accel VLAN tagged skb to transmit * @slave_dev: slave that is supposed to xmit this skbuff */ -void bond_dev_queue_xmit(struct bonding *bond, struct sk_buff *skb, +netdev_tx_t bond_dev_queue_xmit(struct bonding *bond, struct sk_buff *skb, struct net_device *slave_dev) { skb->dev = slave_dev; @@ -297,11 +296,13 @@ void bond_dev_queue_xmit(struct bonding *bond, struct sk_buff *skb, skb_set_queue_mapping(skb, qdisc_skb_cb(skb)->slave_dev_queue_mapping); if (unlikely(netpoll_tx_running(bond->dev))) - bond_netpoll_send_skb(bond_get_slave_by_dev(bond, slave_dev), skb); - else - dev_queue_xmit(skb); + return bond_netpoll_send_skb(bond_get_slave_by_dev(bond, slave_dev), skb); + + return dev_queue_xmit(skb); } +/*---------------------------------- VLAN -----------------------------------*/ + /* In the following 2 functions, bond_vlan_rx_add_vid and bond_vlan_rx_kill_vid, * We don't protect the slave list iteration with a lock because: * a. This operation is performed in IOCTL context, @@ -321,6 +322,7 @@ void bond_dev_queue_xmit(struct bonding *bond, struct sk_buff *skb, /** * bond_vlan_rx_add_vid - Propagates adding an id to slaves * @bond_dev: bonding net device that got called + * @proto: network protocol ID * @vid: vlan id being added */ static int bond_vlan_rx_add_vid(struct net_device *bond_dev, @@ -354,6 +356,7 @@ unwind: /** * bond_vlan_rx_kill_vid - Propagates deleting an id to slaves * @bond_dev: bonding net device that got called + * @proto: network protocol ID * @vid: vlan id being removed */ static int bond_vlan_rx_kill_vid(struct net_device *bond_dev, @@ -372,6 +375,98 @@ static int bond_vlan_rx_kill_vid(struct net_device *bond_dev, return 0; } +/*---------------------------------- XFRM -----------------------------------*/ + +#ifdef CONFIG_XFRM_OFFLOAD +/** + * bond_ipsec_add_sa - program device with a security association + * @xs: pointer to transformer state struct + **/ +static int bond_ipsec_add_sa(struct xfrm_state *xs) +{ + struct net_device *bond_dev = xs->xso.dev; + struct bonding *bond; + struct slave *slave; + + if (!bond_dev) + return -EINVAL; + + bond = netdev_priv(bond_dev); + slave = rcu_dereference(bond->curr_active_slave); + xs->xso.real_dev = slave->dev; + bond->xs = xs; + + if (!(slave->dev->xfrmdev_ops + && slave->dev->xfrmdev_ops->xdo_dev_state_add)) { + slave_warn(bond_dev, slave->dev, "Slave does not support ipsec offload\n"); + return -EINVAL; + } + + return slave->dev->xfrmdev_ops->xdo_dev_state_add(xs); +} + +/** + * bond_ipsec_del_sa - clear out this specific SA + * @xs: pointer to transformer state struct + **/ +static void bond_ipsec_del_sa(struct xfrm_state *xs) +{ + struct net_device *bond_dev = xs->xso.dev; + struct bonding *bond; + struct slave *slave; + + if (!bond_dev) + return; + + bond = netdev_priv(bond_dev); + slave = rcu_dereference(bond->curr_active_slave); + + if (!slave) + return; + + xs->xso.real_dev = slave->dev; + + if (!(slave->dev->xfrmdev_ops + && slave->dev->xfrmdev_ops->xdo_dev_state_delete)) { + slave_warn(bond_dev, slave->dev, "%s: no slave xdo_dev_state_delete\n", __func__); + return; + } + + slave->dev->xfrmdev_ops->xdo_dev_state_delete(xs); +} + +/** + * bond_ipsec_offload_ok - can this packet use the xfrm hw offload + * @skb: current data packet + * @xs: pointer to transformer state struct + **/ +static bool bond_ipsec_offload_ok(struct sk_buff *skb, struct xfrm_state *xs) +{ + struct net_device *bond_dev = xs->xso.dev; + struct bonding *bond = netdev_priv(bond_dev); + struct slave *curr_active = rcu_dereference(bond->curr_active_slave); + struct net_device *slave_dev = curr_active->dev; + + if (BOND_MODE(bond) != BOND_MODE_ACTIVEBACKUP) + return true; + + if (!(slave_dev->xfrmdev_ops + && slave_dev->xfrmdev_ops->xdo_dev_offload_ok)) { + slave_warn(bond_dev, slave_dev, "%s: no slave xdo_dev_offload_ok\n", __func__); + return false; + } + + xs->xso.real_dev = slave_dev; + return slave_dev->xfrmdev_ops->xdo_dev_offload_ok(skb, xs); +} + +static const struct xfrmdev_ops bond_xfrmdev_ops = { + .xdo_dev_state_add = bond_ipsec_add_sa, + .xdo_dev_state_delete = bond_ipsec_del_sa, + .xdo_dev_offload_ok = bond_ipsec_offload_ok, +}; +#endif /* CONFIG_XFRM_OFFLOAD */ + /*------------------------------- Link status -------------------------------*/ /* Set the carrier state for the master according to the state of its @@ -855,7 +950,7 @@ static bool bond_should_notify_peers(struct bonding *bond) /** * change_active_interface - change the active slave into the specified one * @bond: our bonding struct - * @new: the new slave to make the active one + * @new_active: the new slave to make the active one * * Set the new slave to the bond's settings and unset them on the old * curr_active_slave. @@ -878,6 +973,11 @@ void bond_change_active_slave(struct bonding *bond, struct slave *new_active) if (old_active == new_active) return; +#ifdef CONFIG_XFRM_OFFLOAD + if (old_active && bond->xs) + bond_ipsec_del_sa(bond->xs); +#endif /* CONFIG_XFRM_OFFLOAD */ + if (new_active) { new_active->last_link_up = jiffies; @@ -950,6 +1050,13 @@ void bond_change_active_slave(struct bonding *bond, struct slave *new_active) } } +#ifdef CONFIG_XFRM_OFFLOAD + if (new_active && bond->xs) { + xfrm_dev_state_flush(dev_net(bond->dev), bond->dev, true); + bond_ipsec_add_sa(bond->xs); + } +#endif /* CONFIG_XFRM_OFFLOAD */ + /* resend IGMP joins since active slave has changed or * all were sent on curr_active_slave. * resend only if bond is brought up with the affected @@ -1130,12 +1237,16 @@ static netdev_features_t bond_fix_features(struct net_device *dev, #define BOND_MPLS_FEATURES (NETIF_F_HW_CSUM | NETIF_F_SG | \ NETIF_F_ALL_TSO) + static void bond_compute_features(struct bonding *bond) { unsigned int dst_release_flag = IFF_XMIT_DST_RELEASE | IFF_XMIT_DST_RELEASE_PERM; netdev_features_t vlan_features = BOND_VLAN_FEATURES; netdev_features_t enc_features = BOND_ENC_FEATURES; +#ifdef CONFIG_XFRM_OFFLOAD + netdev_features_t xfrm_features = BOND_XFRM_FEATURES; +#endif /* CONFIG_XFRM_OFFLOAD */ netdev_features_t mpls_features = BOND_MPLS_FEATURES; struct net_device *bond_dev = bond->dev; struct list_head *iter; @@ -1157,6 +1268,12 @@ static void bond_compute_features(struct bonding *bond) slave->dev->hw_enc_features, BOND_ENC_FEATURES); +#ifdef CONFIG_XFRM_OFFLOAD + xfrm_features = netdev_increment_features(xfrm_features, + slave->dev->hw_enc_features, + BOND_XFRM_FEATURES); +#endif /* CONFIG_XFRM_OFFLOAD */ + mpls_features = netdev_increment_features(mpls_features, slave->dev->mpls_features, BOND_MPLS_FEATURES); @@ -1176,6 +1293,9 @@ done: NETIF_F_HW_VLAN_CTAG_TX | NETIF_F_HW_VLAN_STAG_TX | NETIF_F_GSO_UDP_L4; +#ifdef CONFIG_XFRM_OFFLOAD + bond_dev->hw_enc_features |= xfrm_features; +#endif /* CONFIG_XFRM_OFFLOAD */ bond_dev->mpls_features = mpls_features; bond_dev->gso_max_segs = gso_max_segs; netif_set_gso_max_size(bond_dev, gso_max_size); @@ -1195,6 +1315,7 @@ static void bond_setup_by_slave(struct net_device *bond_dev, bond_dev->type = slave_dev->type; bond_dev->hard_header_len = slave_dev->hard_header_len; + bond_dev->needed_headroom = slave_dev->needed_headroom; bond_dev->addr_len = slave_dev->addr_len; memcpy(bond_dev->broadcast, slave_dev->broadcast, @@ -1464,6 +1585,9 @@ int bond_enslave(struct net_device *bond_dev, struct net_device *slave_dev, slave_dbg(bond_dev, slave_dev, "is !NETIF_F_VLAN_CHALLENGED\n"); } + if (slave_dev->features & NETIF_F_HW_ESP) + slave_dbg(bond_dev, slave_dev, "is esp-hw-offload capable\n"); + /* Old ifenslave binaries are no longer supported. These can * be identified with moderate accuracy by the state of the slave: * the current ifenslave will set the interface down prior to @@ -2084,7 +2208,8 @@ static int bond_release_and_destroy(struct net_device *bond_dev, int ret; ret = __bond_release_one(bond_dev, slave_dev, false, true); - if (ret == 0 && !bond_has_slaves(bond)) { + if (ret == 0 && !bond_has_slaves(bond) && + bond_dev->reg_state != NETREG_UNREGISTERING) { bond_dev->priv_flags |= IFF_DISABLE_NETPOLL; netdev_info(bond_dev, "Destroying bond\n"); bond_remove_proc_entry(bond); @@ -2150,7 +2275,7 @@ static int bond_miimon_inspect(struct bonding *bond) "active " : "backup ") : "", bond->params.downdelay * bond->params.miimon); } - /*FALLTHRU*/ + fallthrough; case BOND_LINK_FAIL: if (link_state) { /* recovered before downdelay expired */ @@ -2186,7 +2311,7 @@ static int bond_miimon_inspect(struct bonding *bond) bond->params.updelay * bond->params.miimon); } - /*FALLTHRU*/ + fallthrough; case BOND_LINK_BACK: if (!link_state) { bond_propose_link_state(slave, BOND_LINK_DOWN); @@ -2386,22 +2511,26 @@ re_arm: } } -static int bond_upper_dev_walk(struct net_device *upper, void *data) +static int bond_upper_dev_walk(struct net_device *upper, + struct netdev_nested_priv *priv) { - __be32 ip = *((__be32 *)data); + __be32 ip = *(__be32 *)priv->data; return ip == bond_confirm_addr(upper, 0, ip); } static bool bond_has_this_ip(struct bonding *bond, __be32 ip) { + struct netdev_nested_priv priv = { + .data = (void *)&ip, + }; bool ret = false; if (ip == bond_confirm_addr(bond->dev, 0, ip)) return true; rcu_read_lock(); - if (netdev_walk_all_upper_dev_rcu(bond->dev, bond_upper_dev_walk, &ip)) + if (netdev_walk_all_upper_dev_rcu(bond->dev, bond_upper_dev_walk, &priv)) ret = true; rcu_read_unlock(); @@ -2824,6 +2953,9 @@ static int bond_ab_arp_inspect(struct bonding *bond) if (bond_time_in_interval(bond, last_rx, 1)) { bond_propose_link_state(slave, BOND_LINK_UP); commit++; + } else if (slave->link == BOND_LINK_BACK) { + bond_propose_link_state(slave, BOND_LINK_FAIL); + commit++; } continue; } @@ -2932,6 +3064,19 @@ static void bond_ab_arp_commit(struct bonding *bond) continue; + case BOND_LINK_FAIL: + bond_set_slave_link_state(slave, BOND_LINK_FAIL, + BOND_SLAVE_NOTIFY_NOW); + bond_set_slave_inactive_flags(slave, + BOND_SLAVE_NOTIFY_NOW); + + /* A slave has just been enslaved and has become + * the current active slave. + */ + if (rtnl_dereference(bond->curr_active_slave)) + RCU_INIT_POINTER(bond->current_arp_slave, NULL); + continue; + default: slave_err(bond->dev, slave->dev, "impossible: link_new_state %d on slave\n", @@ -2982,8 +3127,6 @@ static bool bond_ab_arp_probe(struct bonding *bond) return should_notify_rtnl; } - bond_set_slave_inactive_flags(curr_arp_slave, BOND_SLAVE_NOTIFY_LATER); - bond_for_each_slave_rcu(bond, slave, iter) { if (!found && !before && bond_slave_is_up(slave)) before = slave; @@ -3184,7 +3327,7 @@ static int bond_slave_netdev_event(unsigned long event, if (BOND_MODE(bond) == BOND_MODE_8023AD) bond_3ad_adapter_speed_duplex_changed(slave); - /* Fallthrough */ + fallthrough; case NETDEV_DOWN: /* Refresh slave-array if applicable! * If the setup does not use miimon or arpmon (mode-specific!), @@ -3622,7 +3765,7 @@ static int bond_do_ioctl(struct net_device *bond_dev, struct ifreq *ifr, int cmd return -EINVAL; mii->phy_id = 0; - /* Fall Through */ + fallthrough; case SIOCGMIIREG: /* We do this again just in case we were called by SIOCGMIIREG * instead of SIOCGMIIPHY. @@ -3687,8 +3830,6 @@ static int bond_do_ioctl(struct net_device *bond_dev, struct ifreq *ifr, int cmd case BOND_RELEASE_OLD: case SIOCBONDRELEASE: res = bond_release(bond_dev, slave_dev); - if (!res) - netdev_update_lockdep_key(slave_dev); break; case BOND_SETHWADDR_OLD: case SIOCBONDSETHWADDR: @@ -3923,16 +4064,15 @@ unwind: } /** - * bond_xmit_slave_id - transmit skb through slave with slave_id + * bond_get_slave_by_id - get xmit 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 + * This function tries to get slave with slave_id but in case * it fails, it tries to find the first available slave for transmission. - * The skb is consumed in all cases, thus the function is void. */ -static void bond_xmit_slave_id(struct bonding *bond, struct sk_buff *skb, int slave_id) +static struct slave *bond_get_slave_by_id(struct bonding *bond, + int slave_id) { struct list_head *iter; struct slave *slave; @@ -3941,10 +4081,8 @@ static void bond_xmit_slave_id(struct bonding *bond, struct sk_buff *skb, int sl /* Here we start from the slave with slave_id */ bond_for_each_slave_rcu(bond, slave, iter) { if (--i < 0) { - if (bond_slave_can_tx(slave)) { - bond_dev_queue_xmit(bond, skb, slave->dev); - return; - } + if (bond_slave_can_tx(slave)) + return slave; } } @@ -3953,13 +4091,11 @@ static void bond_xmit_slave_id(struct bonding *bond, struct sk_buff *skb, int sl bond_for_each_slave_rcu(bond, slave, iter) { if (--i < 0) break; - if (bond_slave_can_tx(slave)) { - bond_dev_queue_xmit(bond, skb, slave->dev); - return; - } + if (bond_slave_can_tx(slave)) + return slave; } /* no slave that can tx has been found */ - bond_tx_drop(bond->dev, skb); + return NULL; } /** @@ -3995,10 +4131,9 @@ static u32 bond_rr_gen_slave_id(struct bonding *bond) return slave_id; } -static netdev_tx_t bond_xmit_roundrobin(struct sk_buff *skb, - struct net_device *bond_dev) +static struct slave *bond_xmit_roundrobin_slave_get(struct bonding *bond, + struct sk_buff *skb) { - struct bonding *bond = netdev_priv(bond_dev); struct slave *slave; int slave_cnt; u32 slave_id; @@ -4020,22 +4155,37 @@ static netdev_tx_t bond_xmit_roundrobin(struct sk_buff *skb, if (iph->protocol == IPPROTO_IGMP) { slave = rcu_dereference(bond->curr_active_slave); if (slave) - bond_dev_queue_xmit(bond, skb, slave->dev); - else - bond_xmit_slave_id(bond, skb, 0); - return NETDEV_TX_OK; + return slave; + return bond_get_slave_by_id(bond, 0); } } non_igmp: slave_cnt = READ_ONCE(bond->slave_cnt); if (likely(slave_cnt)) { - slave_id = bond_rr_gen_slave_id(bond); - bond_xmit_slave_id(bond, skb, slave_id % slave_cnt); - } else { - bond_tx_drop(bond_dev, skb); + slave_id = bond_rr_gen_slave_id(bond) % slave_cnt; + return bond_get_slave_by_id(bond, slave_id); } - return NETDEV_TX_OK; + return NULL; +} + +static netdev_tx_t bond_xmit_roundrobin(struct sk_buff *skb, + struct net_device *bond_dev) +{ + struct bonding *bond = netdev_priv(bond_dev); + struct slave *slave; + + slave = bond_xmit_roundrobin_slave_get(bond, skb); + if (likely(slave)) + return bond_dev_queue_xmit(bond, skb, slave->dev); + + return bond_tx_drop(bond_dev, skb); +} + +static struct slave *bond_xmit_activebackup_slave_get(struct bonding *bond, + struct sk_buff *skb) +{ + return rcu_dereference(bond->curr_active_slave); } /* In active-backup mode, we know that bond->curr_active_slave is always valid if @@ -4047,13 +4197,11 @@ static netdev_tx_t bond_xmit_activebackup(struct sk_buff *skb, struct bonding *bond = netdev_priv(bond_dev); struct slave *slave; - slave = rcu_dereference(bond->curr_active_slave); + slave = bond_xmit_activebackup_slave_get(bond, skb); if (slave) - bond_dev_queue_xmit(bond, skb, slave->dev); - else - bond_tx_drop(bond_dev, skb); + return bond_dev_queue_xmit(bond, skb, slave->dev); - return NETDEV_TX_OK; + return bond_tx_drop(bond_dev, skb); } /* Use this to update slave_array when (a) it's not appropriate to update @@ -4087,6 +4235,61 @@ err: bond_slave_arr_work_rearm(bond, 1); } +static void bond_skip_slave(struct bond_up_slave *slaves, + struct slave *skipslave) +{ + int idx; + + /* Rare situation where caller has asked to skip a specific + * slave but allocation failed (most likely!). BTW this is + * only possible when the call is initiated from + * __bond_release_one(). In this situation; overwrite the + * skipslave entry in the array with the last entry from the + * array to avoid a situation where the xmit path may choose + * this to-be-skipped slave to send a packet out. + */ + for (idx = 0; slaves && idx < slaves->count; idx++) { + if (skipslave == slaves->arr[idx]) { + slaves->arr[idx] = + slaves->arr[slaves->count - 1]; + slaves->count--; + break; + } + } +} + +static void bond_set_slave_arr(struct bonding *bond, + struct bond_up_slave *usable_slaves, + struct bond_up_slave *all_slaves) +{ + struct bond_up_slave *usable, *all; + + usable = rtnl_dereference(bond->usable_slaves); + rcu_assign_pointer(bond->usable_slaves, usable_slaves); + kfree_rcu(usable, rcu); + + all = rtnl_dereference(bond->all_slaves); + rcu_assign_pointer(bond->all_slaves, all_slaves); + kfree_rcu(all, rcu); +} + +static void bond_reset_slave_arr(struct bonding *bond) +{ + struct bond_up_slave *usable, *all; + + usable = rtnl_dereference(bond->usable_slaves); + if (usable) { + RCU_INIT_POINTER(bond->usable_slaves, NULL); + kfree_rcu(usable, rcu); + } + + all = rtnl_dereference(bond->all_slaves); + if (all) { + RCU_INIT_POINTER(bond->all_slaves, NULL); + kfree_rcu(all, rcu); + } +} + /* Build the usable slaves array in control path for modes that use xmit-hash * to determine the slave interface - * (a) BOND_MODE_8023AD @@ -4097,9 +4300,9 @@ err: */ int bond_update_slave_arr(struct bonding *bond, struct slave *skipslave) { + struct bond_up_slave *usable_slaves = NULL, *all_slaves = NULL; struct slave *slave; struct list_head *iter; - struct bond_up_slave *new_arr, *old_arr; int agg_id = 0; int ret = 0; @@ -4107,11 +4310,12 @@ int bond_update_slave_arr(struct bonding *bond, struct slave *skipslave) WARN_ON(lockdep_is_held(&bond->mode_lock)); #endif - new_arr = kzalloc(offsetof(struct bond_up_slave, arr[bond->slave_cnt]), - GFP_KERNEL); - if (!new_arr) { + usable_slaves = kzalloc(struct_size(usable_slaves, arr, + bond->slave_cnt), GFP_KERNEL); + all_slaves = kzalloc(struct_size(all_slaves, arr, + bond->slave_cnt), GFP_KERNEL); + if (!usable_slaves || !all_slaves) { ret = -ENOMEM; - pr_err("Failed to build slave-array.\n"); goto out; } if (BOND_MODE(bond) == BOND_MODE_8023AD) { @@ -4119,20 +4323,19 @@ int bond_update_slave_arr(struct bonding *bond, struct slave *skipslave) if (bond_3ad_get_active_agg_info(bond, &ad_info)) { pr_debug("bond_3ad_get_active_agg_info failed\n"); - kfree_rcu(new_arr, rcu); /* No active aggragator means it's not safe to use * the previous array. */ - old_arr = rtnl_dereference(bond->slave_arr); - if (old_arr) { - RCU_INIT_POINTER(bond->slave_arr, NULL); - kfree_rcu(old_arr, rcu); - } + bond_reset_slave_arr(bond); goto out; } agg_id = ad_info.aggregator_id; } bond_for_each_slave(bond, slave, iter) { + if (skipslave == slave) + continue; + + all_slaves->arr[all_slaves->count++] = slave; if (BOND_MODE(bond) == BOND_MODE_8023AD) { struct aggregator *agg; @@ -4142,44 +4345,45 @@ int bond_update_slave_arr(struct bonding *bond, struct slave *skipslave) } if (!bond_slave_can_tx(slave)) continue; - if (skipslave == slave) - continue; slave_dbg(bond->dev, slave->dev, "Adding slave to tx hash array[%d]\n", - new_arr->count); + usable_slaves->count); - new_arr->arr[new_arr->count++] = slave; + usable_slaves->arr[usable_slaves->count++] = slave; } - old_arr = rtnl_dereference(bond->slave_arr); - rcu_assign_pointer(bond->slave_arr, new_arr); - if (old_arr) - kfree_rcu(old_arr, rcu); + bond_set_slave_arr(bond, usable_slaves, all_slaves); + return ret; out: if (ret != 0 && skipslave) { - int idx; - - /* Rare situation where caller has asked to skip a specific - * slave but allocation failed (most likely!). BTW this is - * only possible when the call is initiated from - * __bond_release_one(). In this situation; overwrite the - * skipslave entry in the array with the last entry from the - * array to avoid a situation where the xmit path may choose - * this to-be-skipped slave to send a packet out. - */ - old_arr = rtnl_dereference(bond->slave_arr); - for (idx = 0; old_arr != NULL && idx < old_arr->count; idx++) { - if (skipslave == old_arr->arr[idx]) { - old_arr->arr[idx] = - old_arr->arr[old_arr->count-1]; - old_arr->count--; - break; - } - } + bond_skip_slave(rtnl_dereference(bond->all_slaves), + skipslave); + bond_skip_slave(rtnl_dereference(bond->usable_slaves), + skipslave); } + kfree_rcu(all_slaves, rcu); + kfree_rcu(usable_slaves, rcu); + return ret; } +static struct slave *bond_xmit_3ad_xor_slave_get(struct bonding *bond, + struct sk_buff *skb, + struct bond_up_slave *slaves) +{ + struct slave *slave; + unsigned int count; + u32 hash; + + hash = bond_xmit_hash(bond, skb); + count = slaves ? READ_ONCE(slaves->count) : 0; + if (unlikely(!count)) + return NULL; + + slave = slaves->arr[hash % count]; + return slave; +} + /* Use this Xmit function for 3AD as well as XOR modes. The current * usable slave array is formed in the control path. The xmit function * just calculates hash and sends the packet out. @@ -4188,20 +4392,15 @@ static netdev_tx_t bond_3ad_xor_xmit(struct sk_buff *skb, struct net_device *dev) { struct bonding *bond = netdev_priv(dev); - struct slave *slave; struct bond_up_slave *slaves; - unsigned int count; + struct slave *slave; - slaves = rcu_dereference(bond->slave_arr); - count = slaves ? READ_ONCE(slaves->count) : 0; - if (likely(count)) { - slave = slaves->arr[bond_xmit_hash(bond, skb) % count]; - bond_dev_queue_xmit(bond, skb, slave->dev); - } else { - bond_tx_drop(dev, skb); - } + slaves = rcu_dereference(bond->usable_slaves); + slave = bond_xmit_3ad_xor_slave_get(bond, skb, slaves); + if (likely(slave)) + return bond_dev_queue_xmit(bond, skb, slave->dev); - return NETDEV_TX_OK; + return bond_tx_drop(dev, skb); } /* in broadcast mode, we send everything to all usable interfaces. */ @@ -4227,11 +4426,9 @@ static netdev_tx_t bond_xmit_broadcast(struct sk_buff *skb, } } if (slave && bond_slave_is_up(slave) && slave->link == BOND_LINK_UP) - bond_dev_queue_xmit(bond, skb, slave->dev); - else - bond_tx_drop(bond_dev, skb); + return bond_dev_queue_xmit(bond, skb, slave->dev); - return NETDEV_TX_OK; + return bond_tx_drop(bond_dev, skb); } /*------------------------- Device initialization ---------------------------*/ @@ -4284,6 +4481,48 @@ static u16 bond_select_queue(struct net_device *dev, struct sk_buff *skb, return txq; } +static struct net_device *bond_xmit_get_slave(struct net_device *master_dev, + struct sk_buff *skb, + bool all_slaves) +{ + struct bonding *bond = netdev_priv(master_dev); + struct bond_up_slave *slaves; + struct slave *slave = NULL; + + switch (BOND_MODE(bond)) { + case BOND_MODE_ROUNDROBIN: + slave = bond_xmit_roundrobin_slave_get(bond, skb); + break; + case BOND_MODE_ACTIVEBACKUP: + slave = bond_xmit_activebackup_slave_get(bond, skb); + break; + case BOND_MODE_8023AD: + case BOND_MODE_XOR: + if (all_slaves) + slaves = rcu_dereference(bond->all_slaves); + else + slaves = rcu_dereference(bond->usable_slaves); + slave = bond_xmit_3ad_xor_slave_get(bond, skb, slaves); + break; + case BOND_MODE_BROADCAST: + break; + case BOND_MODE_ALB: + slave = bond_xmit_alb_slave_get(bond, skb); + break; + case BOND_MODE_TLB: + slave = bond_xmit_tlb_slave_get(bond, skb); + break; + default: + /* Should never happen, mode already checked */ + WARN_ONCE(true, "Unknown bonding mode"); + break; + } + + if (slave) + return slave->dev; + return NULL; +} + static netdev_tx_t __bond_start_xmit(struct sk_buff *skb, struct net_device *dev) { struct bonding *bond = netdev_priv(dev); @@ -4310,8 +4549,7 @@ static netdev_tx_t __bond_start_xmit(struct sk_buff *skb, struct net_device *dev /* Should never happen, mode already checked */ netdev_err(dev, "Unknown bonding mode %d\n", BOND_MODE(bond)); WARN_ON_ONCE(1); - bond_tx_drop(dev, skb); - return NETDEV_TX_OK; + return bond_tx_drop(dev, skb); } } @@ -4330,19 +4568,29 @@ static netdev_tx_t bond_start_xmit(struct sk_buff *skb, struct net_device *dev) if (bond_has_slaves(bond)) ret = __bond_start_xmit(skb, dev); else - bond_tx_drop(dev, skb); + ret = bond_tx_drop(dev, skb); rcu_read_unlock(); return ret; } +static u32 bond_mode_bcast_speed(struct slave *slave, u32 speed) +{ + if (speed == 0 || speed == SPEED_UNKNOWN) + speed = slave->speed; + else + speed = min(speed, slave->speed); + + return speed; +} + static int bond_ethtool_get_link_ksettings(struct net_device *bond_dev, struct ethtool_link_ksettings *cmd) { struct bonding *bond = netdev_priv(bond_dev); - unsigned long speed = 0; struct list_head *iter; struct slave *slave; + u32 speed = 0; cmd->base.duplex = DUPLEX_UNKNOWN; cmd->base.port = PORT_OTHER; @@ -4354,8 +4602,13 @@ static int bond_ethtool_get_link_ksettings(struct net_device *bond_dev, */ bond_for_each_slave(bond, slave, iter) { if (bond_slave_can_tx(slave)) { - if (slave->speed != SPEED_UNKNOWN) - speed += slave->speed; + if (slave->speed != SPEED_UNKNOWN) { + if (BOND_MODE(bond) == BOND_MODE_BROADCAST) + speed = bond_mode_bcast_speed(slave, + speed); + else + speed += slave->speed; + } if (cmd->base.duplex == DUPLEX_UNKNOWN && slave->duplex != DUPLEX_UNKNOWN) cmd->base.duplex = slave->duplex; @@ -4405,6 +4658,7 @@ static const struct net_device_ops bond_netdev_ops = { .ndo_del_slave = bond_release, .ndo_fix_features = bond_fix_features, .ndo_features_check = passthru_features_check, + .ndo_get_xmit_slave = bond_xmit_get_slave, }; static const struct device_type bond_type = { @@ -4444,6 +4698,12 @@ void bond_setup(struct net_device *bond_dev) bond_dev->priv_flags |= IFF_BONDING | IFF_UNICAST_FLT | IFF_NO_QUEUE; bond_dev->priv_flags &= ~(IFF_XMIT_DST_RELEASE | IFF_TX_SKB_SHARING); +#ifdef CONFIG_XFRM_OFFLOAD + /* set up xfrm device ops (only supported in active-backup right now) */ + bond_dev->xfrmdev_ops = &bond_xfrmdev_ops; + bond->xs = NULL; +#endif /* CONFIG_XFRM_OFFLOAD */ + /* don't acquire bond device's netif_tx_lock when transmitting */ bond_dev->features |= NETIF_F_LLTX; @@ -4462,8 +4722,16 @@ void bond_setup(struct net_device *bond_dev) NETIF_F_HW_VLAN_CTAG_FILTER; bond_dev->hw_features |= NETIF_F_GSO_ENCAP_ALL | NETIF_F_GSO_UDP_L4; +#ifdef CONFIG_XFRM_OFFLOAD + bond_dev->hw_features |= BOND_XFRM_FEATURES; +#endif /* CONFIG_XFRM_OFFLOAD */ bond_dev->features |= bond_dev->hw_features; bond_dev->features |= NETIF_F_HW_VLAN_CTAG_TX | NETIF_F_HW_VLAN_STAG_TX; +#ifdef CONFIG_XFRM_OFFLOAD + /* Disable XFRM features if this isn't an active-backup config */ + if (BOND_MODE(bond) != BOND_MODE_ACTIVEBACKUP) + bond_dev->features &= ~BOND_XFRM_FEATURES; +#endif /* CONFIG_XFRM_OFFLOAD */ } /* Destroy a bonding device. @@ -4472,9 +4740,9 @@ 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 bond_up_slave *usable, *all; struct list_head *iter; struct slave *slave; - struct bond_up_slave *arr; bond_netpoll_cleanup(bond_dev); @@ -4483,15 +4751,20 @@ static void bond_uninit(struct net_device *bond_dev) __bond_release_one(bond_dev, slave->dev, true, true); netdev_info(bond_dev, "Released all slaves\n"); - arr = rtnl_dereference(bond->slave_arr); - if (arr) { - RCU_INIT_POINTER(bond->slave_arr, NULL); - kfree_rcu(arr, rcu); + usable = rtnl_dereference(bond->usable_slaves); + if (usable) { + RCU_INIT_POINTER(bond->usable_slaves, NULL); + kfree_rcu(usable, rcu); + } + + all = rtnl_dereference(bond->all_slaves); + if (all) { + RCU_INIT_POINTER(bond->all_slaves, NULL); + kfree_rcu(all, rcu); } list_del(&bond->bond_list); - lockdep_unregister_key(&bond->stats_lock_key); bond_debug_unregister(bond); } @@ -4896,8 +5169,7 @@ static int bond_init(struct net_device *bond_dev) return -ENOMEM; spin_lock_init(&bond->stats_lock); - lockdep_register_key(&bond->stats_lock_key); - lockdep_set_class(&bond->stats_lock, &bond->stats_lock_key); + netdev_lockdep_set_classes(bond_dev); list_add_tail(&bond->bond_list, &bn->dev_list); @@ -4953,15 +5225,19 @@ int bond_create(struct net *net, const char *name) bond_dev->rtnl_link_ops = &bond_link_ops; res = register_netdevice(bond_dev); + if (res < 0) { + free_netdev(bond_dev); + rtnl_unlock(); + + return res; + } netif_carrier_off(bond_dev); bond_work_init_all(bond); rtnl_unlock(); - if (res < 0) - free_netdev(bond_dev); - return res; + return 0; } static int __net_init bond_net_init(struct net *net) |