diff options
Diffstat (limited to 'net')
90 files changed, 978 insertions, 579 deletions
diff --git a/net/802/mrp.c b/net/802/mrp.c index 1eb05d8..3ed6162 100644 --- a/net/802/mrp.c +++ b/net/802/mrp.c @@ -24,6 +24,11 @@ static unsigned int mrp_join_time __read_mostly = 200; module_param(mrp_join_time, uint, 0644); MODULE_PARM_DESC(mrp_join_time, "Join time in ms (default 200ms)"); + +static unsigned int mrp_periodic_time __read_mostly = 1000; +module_param(mrp_periodic_time, uint, 0644); +MODULE_PARM_DESC(mrp_periodic_time, "Periodic time in ms (default 1s)"); + MODULE_LICENSE("GPL"); static const u8 @@ -595,6 +600,24 @@ static void mrp_join_timer(unsigned long data) mrp_join_timer_arm(app); } +static void mrp_periodic_timer_arm(struct mrp_applicant *app) +{ + mod_timer(&app->periodic_timer, + jiffies + msecs_to_jiffies(mrp_periodic_time)); +} + +static void mrp_periodic_timer(unsigned long data) +{ + struct mrp_applicant *app = (struct mrp_applicant *)data; + + spin_lock(&app->lock); + mrp_mad_event(app, MRP_EVENT_PERIODIC); + mrp_pdu_queue(app); + spin_unlock(&app->lock); + + mrp_periodic_timer_arm(app); +} + static int mrp_pdu_parse_end_mark(struct sk_buff *skb, int *offset) { __be16 endmark; @@ -845,6 +868,9 @@ int mrp_init_applicant(struct net_device *dev, struct mrp_application *appl) rcu_assign_pointer(dev->mrp_port->applicants[appl->type], app); setup_timer(&app->join_timer, mrp_join_timer, (unsigned long)app); mrp_join_timer_arm(app); + setup_timer(&app->periodic_timer, mrp_periodic_timer, + (unsigned long)app); + mrp_periodic_timer_arm(app); return 0; err3: @@ -870,6 +896,7 @@ void mrp_uninit_applicant(struct net_device *dev, struct mrp_application *appl) * all pending messages before the applicant is gone. */ del_timer_sync(&app->join_timer); + del_timer_sync(&app->periodic_timer); spin_lock_bh(&app->lock); mrp_mad_event(app, MRP_EVENT_TX); diff --git a/net/8021q/vlan_netlink.c b/net/8021q/vlan_netlink.c index 3091297..c7e634a 100644 --- a/net/8021q/vlan_netlink.c +++ b/net/8021q/vlan_netlink.c @@ -171,7 +171,7 @@ static size_t vlan_get_size(const struct net_device *dev) return nla_total_size(2) + /* IFLA_VLAN_PROTOCOL */ nla_total_size(2) + /* IFLA_VLAN_ID */ - sizeof(struct ifla_vlan_flags) + /* IFLA_VLAN_FLAGS */ + nla_total_size(sizeof(struct ifla_vlan_flags)) + /* IFLA_VLAN_FLAGS */ vlan_qos_map_size(vlan->nr_ingress_mappings) + vlan_qos_map_size(vlan->nr_egress_mappings); } diff --git a/net/batman-adv/main.c b/net/batman-adv/main.c index c72d1bc..1356af6 100644 --- a/net/batman-adv/main.c +++ b/net/batman-adv/main.c @@ -65,6 +65,7 @@ static int __init batadv_init(void) batadv_recv_handler_init(); batadv_iv_init(); + batadv_nc_init(); batadv_event_workqueue = create_singlethread_workqueue("bat_events"); @@ -142,7 +143,7 @@ int batadv_mesh_init(struct net_device *soft_iface) if (ret < 0) goto err; - ret = batadv_nc_init(bat_priv); + ret = batadv_nc_mesh_init(bat_priv); if (ret < 0) goto err; @@ -167,7 +168,7 @@ void batadv_mesh_free(struct net_device *soft_iface) batadv_vis_quit(bat_priv); batadv_gw_node_purge(bat_priv); - batadv_nc_free(bat_priv); + batadv_nc_mesh_free(bat_priv); batadv_dat_free(bat_priv); batadv_bla_free(bat_priv); diff --git a/net/batman-adv/network-coding.c b/net/batman-adv/network-coding.c index a487d46..4ecc0b6 100644 --- a/net/batman-adv/network-coding.c +++ b/net/batman-adv/network-coding.c @@ -35,6 +35,20 @@ static int batadv_nc_recv_coded_packet(struct sk_buff *skb, struct batadv_hard_iface *recv_if); /** + * batadv_nc_init - one-time initialization for network coding + */ +int __init batadv_nc_init(void) +{ + int ret; + + /* Register our packet type */ + ret = batadv_recv_handler_register(BATADV_CODED, + batadv_nc_recv_coded_packet); + + return ret; +} + +/** * batadv_nc_start_timer - initialise the nc periodic worker * @bat_priv: the bat priv with all the soft interface information */ @@ -45,10 +59,10 @@ static void batadv_nc_start_timer(struct batadv_priv *bat_priv) } /** - * batadv_nc_init - initialise coding hash table and start house keeping + * batadv_nc_mesh_init - initialise coding hash table and start house keeping * @bat_priv: the bat priv with all the soft interface information */ -int batadv_nc_init(struct batadv_priv *bat_priv) +int batadv_nc_mesh_init(struct batadv_priv *bat_priv) { bat_priv->nc.timestamp_fwd_flush = jiffies; bat_priv->nc.timestamp_sniffed_purge = jiffies; @@ -70,11 +84,6 @@ int batadv_nc_init(struct batadv_priv *bat_priv) batadv_hash_set_lock_class(bat_priv->nc.coding_hash, &batadv_nc_decoding_hash_lock_class_key); - /* Register our packet type */ - if (batadv_recv_handler_register(BATADV_CODED, - batadv_nc_recv_coded_packet) < 0) - goto err; - INIT_DELAYED_WORK(&bat_priv->nc.work, batadv_nc_worker); batadv_nc_start_timer(bat_priv); @@ -1721,12 +1730,11 @@ free_nc_packet: } /** - * batadv_nc_free - clean up network coding memory + * batadv_nc_mesh_free - clean up network coding memory * @bat_priv: the bat priv with all the soft interface information */ -void batadv_nc_free(struct batadv_priv *bat_priv) +void batadv_nc_mesh_free(struct batadv_priv *bat_priv) { - batadv_recv_handler_unregister(BATADV_CODED); cancel_delayed_work_sync(&bat_priv->nc.work); batadv_nc_purge_paths(bat_priv, bat_priv->nc.coding_hash, NULL); diff --git a/net/batman-adv/network-coding.h b/net/batman-adv/network-coding.h index 85a4ec8..ddfa618 100644 --- a/net/batman-adv/network-coding.h +++ b/net/batman-adv/network-coding.h @@ -22,8 +22,9 @@ #ifdef CONFIG_BATMAN_ADV_NC -int batadv_nc_init(struct batadv_priv *bat_priv); -void batadv_nc_free(struct batadv_priv *bat_priv); +int batadv_nc_init(void); +int batadv_nc_mesh_init(struct batadv_priv *bat_priv); +void batadv_nc_mesh_free(struct batadv_priv *bat_priv); void batadv_nc_update_nc_node(struct batadv_priv *bat_priv, struct batadv_orig_node *orig_node, struct batadv_orig_node *orig_neigh_node, @@ -46,12 +47,17 @@ int batadv_nc_init_debugfs(struct batadv_priv *bat_priv); #else /* ifdef CONFIG_BATMAN_ADV_NC */ -static inline int batadv_nc_init(struct batadv_priv *bat_priv) +static inline int batadv_nc_init(void) { return 0; } -static inline void batadv_nc_free(struct batadv_priv *bat_priv) +static inline int batadv_nc_mesh_init(struct batadv_priv *bat_priv) +{ + return 0; +} + +static inline void batadv_nc_mesh_free(struct batadv_priv *bat_priv) { return; } diff --git a/net/bluetooth/hci_core.c b/net/bluetooth/hci_core.c index 634deba..fb7356f 100644 --- a/net/bluetooth/hci_core.c +++ b/net/bluetooth/hci_core.c @@ -1146,7 +1146,11 @@ int hci_dev_open(__u16 dev) goto done; } - if (hdev->rfkill && rfkill_blocked(hdev->rfkill)) { + /* Check for rfkill but allow the HCI setup stage to proceed + * (which in itself doesn't cause any RF activity). + */ + if (test_bit(HCI_RFKILLED, &hdev->dev_flags) && + !test_bit(HCI_SETUP, &hdev->dev_flags)) { ret = -ERFKILL; goto done; } @@ -1566,10 +1570,13 @@ static int hci_rfkill_set_block(void *data, bool blocked) BT_DBG("%p name %s blocked %d", hdev, hdev->name, blocked); - if (!blocked) - return 0; - - hci_dev_do_close(hdev); + if (blocked) { + set_bit(HCI_RFKILLED, &hdev->dev_flags); + if (!test_bit(HCI_SETUP, &hdev->dev_flags)) + hci_dev_do_close(hdev); + } else { + clear_bit(HCI_RFKILLED, &hdev->dev_flags); + } return 0; } @@ -1591,9 +1598,13 @@ static void hci_power_on(struct work_struct *work) return; } - if (test_bit(HCI_AUTO_OFF, &hdev->dev_flags)) + if (test_bit(HCI_RFKILLED, &hdev->dev_flags)) { + clear_bit(HCI_AUTO_OFF, &hdev->dev_flags); + hci_dev_do_close(hdev); + } else if (test_bit(HCI_AUTO_OFF, &hdev->dev_flags)) { queue_delayed_work(hdev->req_workqueue, &hdev->power_off, HCI_AUTO_OFF_TIMEOUT); + } if (test_and_clear_bit(HCI_SETUP, &hdev->dev_flags)) mgmt_index_added(hdev); @@ -2209,6 +2220,9 @@ int hci_register_dev(struct hci_dev *hdev) } } + if (hdev->rfkill && rfkill_blocked(hdev->rfkill)) + set_bit(HCI_RFKILLED, &hdev->dev_flags); + set_bit(HCI_SETUP, &hdev->dev_flags); if (hdev->dev_type != HCI_AMP) diff --git a/net/bluetooth/hci_event.c b/net/bluetooth/hci_event.c index 94aab73..8db3e89 100644 --- a/net/bluetooth/hci_event.c +++ b/net/bluetooth/hci_event.c @@ -3557,7 +3557,11 @@ static void hci_le_ltk_request_evt(struct hci_dev *hdev, struct sk_buff *skb) cp.handle = cpu_to_le16(conn->handle); if (ltk->authenticated) - conn->sec_level = BT_SECURITY_HIGH; + conn->pending_sec_level = BT_SECURITY_HIGH; + else + conn->pending_sec_level = BT_SECURITY_MEDIUM; + + conn->enc_key_size = ltk->enc_size; hci_send_cmd(hdev, HCI_OP_LE_LTK_REPLY, sizeof(cp), &cp); diff --git a/net/bluetooth/l2cap_core.c b/net/bluetooth/l2cap_core.c index b3bb7bc..63fa111 100644 --- a/net/bluetooth/l2cap_core.c +++ b/net/bluetooth/l2cap_core.c @@ -3755,6 +3755,13 @@ static struct l2cap_chan *l2cap_connect(struct l2cap_conn *conn, sk = chan->sk; + /* For certain devices (ex: HID mouse), support for authentication, + * pairing and bonding is optional. For such devices, inorder to avoid + * the ACL alive for too long after L2CAP disconnection, reset the ACL + * disc_timeout back to HCI_DISCONN_TIMEOUT during L2CAP connect. + */ + conn->hcon->disc_timeout = HCI_DISCONN_TIMEOUT; + bacpy(&bt_sk(sk)->src, conn->src); bacpy(&bt_sk(sk)->dst, conn->dst); chan->psm = psm; diff --git a/net/bluetooth/rfcomm/tty.c b/net/bluetooth/rfcomm/tty.c index 6d126fa..84fcf9f 100644 --- a/net/bluetooth/rfcomm/tty.c +++ b/net/bluetooth/rfcomm/tty.c @@ -569,7 +569,6 @@ static void rfcomm_dev_data_ready(struct rfcomm_dlc *dlc, struct sk_buff *skb) static void rfcomm_dev_state_change(struct rfcomm_dlc *dlc, int err) { struct rfcomm_dev *dev = dlc->owner; - struct tty_struct *tty; if (!dev) return; @@ -581,38 +580,8 @@ static void rfcomm_dev_state_change(struct rfcomm_dlc *dlc, int err) DPM_ORDER_DEV_AFTER_PARENT); wake_up_interruptible(&dev->port.open_wait); - } else if (dlc->state == BT_CLOSED) { - tty = tty_port_tty_get(&dev->port); - if (!tty) { - if (test_bit(RFCOMM_RELEASE_ONHUP, &dev->flags)) { - /* Drop DLC lock here to avoid deadlock - * 1. rfcomm_dev_get will take rfcomm_dev_lock - * but in rfcomm_dev_add there's lock order: - * rfcomm_dev_lock -> dlc lock - * 2. tty_port_put will deadlock if it's - * the last reference - * - * FIXME: when we release the lock anything - * could happen to dev, even its destruction - */ - rfcomm_dlc_unlock(dlc); - if (rfcomm_dev_get(dev->id) == NULL) { - rfcomm_dlc_lock(dlc); - return; - } - - if (!test_and_set_bit(RFCOMM_TTY_RELEASED, - &dev->flags)) - tty_port_put(&dev->port); - - tty_port_put(&dev->port); - rfcomm_dlc_lock(dlc); - } - } else { - tty_hangup(tty); - tty_kref_put(tty); - } - } + } else if (dlc->state == BT_CLOSED) + tty_port_tty_hangup(&dev->port, false); } static void rfcomm_dev_modem_status(struct rfcomm_dlc *dlc, u8 v24_sig) diff --git a/net/bridge/br_fdb.c b/net/bridge/br_fdb.c index ffd5874..33e8f23 100644 --- a/net/bridge/br_fdb.c +++ b/net/bridge/br_fdb.c @@ -700,7 +700,7 @@ int br_fdb_add(struct ndmsg *ndm, struct nlattr *tb[], vid = nla_get_u16(tb[NDA_VLAN]); - if (vid >= VLAN_N_VID) { + if (!vid || vid >= VLAN_VID_MASK) { pr_info("bridge: RTM_NEWNEIGH with invalid vlan id %d\n", vid); return -EINVAL; @@ -794,7 +794,7 @@ int br_fdb_delete(struct ndmsg *ndm, struct nlattr *tb[], vid = nla_get_u16(tb[NDA_VLAN]); - if (vid >= VLAN_N_VID) { + if (!vid || vid >= VLAN_VID_MASK) { pr_info("bridge: RTM_NEWNEIGH with invalid vlan id %d\n", vid); return -EINVAL; diff --git a/net/bridge/br_mdb.c b/net/bridge/br_mdb.c index 85a09bb..b7b1914 100644 --- a/net/bridge/br_mdb.c +++ b/net/bridge/br_mdb.c @@ -453,7 +453,7 @@ static int __br_mdb_del(struct net_bridge *br, struct br_mdb_entry *entry) call_rcu_bh(&p->rcu, br_multicast_free_pg); err = 0; - if (!mp->ports && !mp->mglist && mp->timer_armed && + if (!mp->ports && !mp->mglist && netif_running(br->dev)) mod_timer(&mp->timer, jiffies); break; diff --git a/net/bridge/br_multicast.c b/net/bridge/br_multicast.c index d1c5786..8b0b610 100644 --- a/net/bridge/br_multicast.c +++ b/net/bridge/br_multicast.c @@ -272,7 +272,7 @@ static void br_multicast_del_pg(struct net_bridge *br, del_timer(&p->timer); call_rcu_bh(&p->rcu, br_multicast_free_pg); - if (!mp->ports && !mp->mglist && mp->timer_armed && + if (!mp->ports && !mp->mglist && netif_running(br->dev)) mod_timer(&mp->timer, jiffies); @@ -620,7 +620,6 @@ rehash: mp->br = br; mp->addr = *group; - setup_timer(&mp->timer, br_multicast_group_expired, (unsigned long)mp); @@ -660,6 +659,7 @@ static int br_multicast_add_group(struct net_bridge *br, struct net_bridge_mdb_entry *mp; struct net_bridge_port_group *p; struct net_bridge_port_group __rcu **pp; + unsigned long now = jiffies; int err; spin_lock(&br->multicast_lock); @@ -674,6 +674,7 @@ static int br_multicast_add_group(struct net_bridge *br, if (!port) { mp->mglist = true; + mod_timer(&mp->timer, now + br->multicast_membership_interval); goto out; } @@ -681,7 +682,7 @@ static int br_multicast_add_group(struct net_bridge *br, (p = mlock_dereference(*pp, br)) != NULL; pp = &p->next) { if (p->port == port) - goto out; + goto found; if ((unsigned long)p->port < (unsigned long)port) break; } @@ -692,6 +693,8 @@ static int br_multicast_add_group(struct net_bridge *br, rcu_assign_pointer(*pp, p); br_mdb_notify(br->dev, port, group, RTM_NEWMDB); +found: + mod_timer(&p->timer, now + br->multicast_membership_interval); out: err = 0; @@ -1191,9 +1194,6 @@ static int br_ip4_multicast_query(struct net_bridge *br, if (!mp) goto out; - mod_timer(&mp->timer, now + br->multicast_membership_interval); - mp->timer_armed = true; - max_delay *= br->multicast_last_member_count; if (mp->mglist && @@ -1270,9 +1270,6 @@ static int br_ip6_multicast_query(struct net_bridge *br, if (!mp) goto out; - mod_timer(&mp->timer, now + br->multicast_membership_interval); - mp->timer_armed = true; - max_delay *= br->multicast_last_member_count; if (mp->mglist && (timer_pending(&mp->timer) ? @@ -1358,7 +1355,7 @@ static void br_multicast_leave_group(struct net_bridge *br, call_rcu_bh(&p->rcu, br_multicast_free_pg); br_mdb_notify(br->dev, port, group, RTM_DELMDB); - if (!mp->ports && !mp->mglist && mp->timer_armed && + if (!mp->ports && !mp->mglist && netif_running(br->dev)) mod_timer(&mp->timer, jiffies); } @@ -1370,12 +1367,30 @@ static void br_multicast_leave_group(struct net_bridge *br, br->multicast_last_member_interval; if (!port) { - if (mp->mglist && mp->timer_armed && + if (mp->mglist && (timer_pending(&mp->timer) ? time_after(mp->timer.expires, time) : try_to_del_timer_sync(&mp->timer) >= 0)) { mod_timer(&mp->timer, time); } + + goto out; + } + + for (p = mlock_dereference(mp->ports, br); + p != NULL; + p = mlock_dereference(p->next, br)) { + if (p->port != port) + continue; + + if (!hlist_unhashed(&p->mglist) && + (timer_pending(&p->timer) ? + time_after(p->timer.expires, time) : + try_to_del_timer_sync(&p->timer) >= 0)) { + mod_timer(&p->timer, time); + } + + break; } out: spin_unlock(&br->multicast_lock); @@ -1798,7 +1813,6 @@ void br_multicast_stop(struct net_bridge *br) hlist_for_each_entry_safe(mp, n, &mdb->mhash[i], hlist[ver]) { del_timer(&mp->timer); - mp->timer_armed = false; call_rcu_bh(&mp->rcu, br_multicast_free_group); } } diff --git a/net/bridge/br_netlink.c b/net/bridge/br_netlink.c index e74ddc1..f75d92e 100644 --- a/net/bridge/br_netlink.c +++ b/net/bridge/br_netlink.c @@ -243,7 +243,7 @@ static int br_afspec(struct net_bridge *br, vinfo = nla_data(tb[IFLA_BRIDGE_VLAN_INFO]); - if (vinfo->vid >= VLAN_N_VID) + if (!vinfo->vid || vinfo->vid >= VLAN_VID_MASK) return -EINVAL; switch (cmd) { diff --git a/net/bridge/br_private.h b/net/bridge/br_private.h index efb57d9..e14c33b 100644 --- a/net/bridge/br_private.h +++ b/net/bridge/br_private.h @@ -126,7 +126,6 @@ struct net_bridge_mdb_entry struct timer_list timer; struct br_ip addr; bool mglist; - bool timer_armed; }; struct net_bridge_mdb_htable @@ -643,9 +642,7 @@ static inline u16 br_get_pvid(const struct net_port_vlans *v) * vid wasn't set */ smp_rmb(); - return (v->pvid & VLAN_TAG_PRESENT) ? - (v->pvid & ~VLAN_TAG_PRESENT) : - VLAN_N_VID; + return v->pvid ?: VLAN_N_VID; } #else diff --git a/net/bridge/br_stp_if.c b/net/bridge/br_stp_if.c index 108084a..656a6f3 100644 --- a/net/bridge/br_stp_if.c +++ b/net/bridge/br_stp_if.c @@ -134,7 +134,7 @@ static void br_stp_start(struct net_bridge *br) if (br->bridge_forward_delay < BR_MIN_FORWARD_DELAY) __br_set_forward_delay(br, BR_MIN_FORWARD_DELAY); - else if (br->bridge_forward_delay < BR_MAX_FORWARD_DELAY) + else if (br->bridge_forward_delay > BR_MAX_FORWARD_DELAY) __br_set_forward_delay(br, BR_MAX_FORWARD_DELAY); if (r == 0) { diff --git a/net/bridge/br_vlan.c b/net/bridge/br_vlan.c index 9a9ffe7..53f0990 100644 --- a/net/bridge/br_vlan.c +++ b/net/bridge/br_vlan.c @@ -45,37 +45,34 @@ static int __vlan_add(struct net_port_vlans *v, u16 vid, u16 flags) return 0; } - if (vid) { - if (v->port_idx) { - p = v->parent.port; - br = p->br; - dev = p->dev; - } else { - br = v->parent.br; - dev = br->dev; - } - ops = dev->netdev_ops; - - if (p && (dev->features & NETIF_F_HW_VLAN_CTAG_FILTER)) { - /* Add VLAN to the device filter if it is supported. - * Stricly speaking, this is not necessary now, since - * devices are made promiscuous by the bridge, but if - * that ever changes this code will allow tagged - * traffic to enter the bridge. - */ - err = ops->ndo_vlan_rx_add_vid(dev, htons(ETH_P_8021Q), - vid); - if (err) - return err; - } - - err = br_fdb_insert(br, p, dev->dev_addr, vid); - if (err) { - br_err(br, "failed insert local address into bridge " - "forwarding table\n"); - goto out_filt; - } + if (v->port_idx) { + p = v->parent.port; + br = p->br; + dev = p->dev; + } else { + br = v->parent.br; + dev = br->dev; + } + ops = dev->netdev_ops; + + if (p && (dev->features & NETIF_F_HW_VLAN_CTAG_FILTER)) { + /* Add VLAN to the device filter if it is supported. + * Stricly speaking, this is not necessary now, since + * devices are made promiscuous by the bridge, but if + * that ever changes this code will allow tagged + * traffic to enter the bridge. + */ + err = ops->ndo_vlan_rx_add_vid(dev, htons(ETH_P_8021Q), + vid); + if (err) + return err; + } + err = br_fdb_insert(br, p, dev->dev_addr, vid); + if (err) { + br_err(br, "failed insert local address into bridge " + "forwarding table\n"); + goto out_filt; } set_bit(vid, v->vlan_bitmap); @@ -98,7 +95,7 @@ static int __vlan_del(struct net_port_vlans *v, u16 vid) __vlan_delete_pvid(v, vid); clear_bit(vid, v->untagged_bitmap); - if (v->port_idx && vid) { + if (v->port_idx) { struct net_device *dev = v->parent.port->dev; const struct net_device_ops *ops = dev->netdev_ops; @@ -192,6 +189,8 @@ out: bool br_allowed_ingress(struct net_bridge *br, struct net_port_vlans *v, struct sk_buff *skb, u16 *vid) { + int err; + /* If VLAN filtering is disabled on the bridge, all packets are * permitted. */ @@ -204,20 +203,32 @@ bool br_allowed_ingress(struct net_bridge *br, struct net_port_vlans *v, if (!v) return false; - if (br_vlan_get_tag(skb, vid)) { + err = br_vlan_get_tag(skb, vid); + if (!*vid) { u16 pvid = br_get_pvid(v); - /* Frame did not have a tag. See if pvid is set - * on this port. That tells us which vlan untagged - * traffic belongs to. + /* Frame had a tag with VID 0 or did not have a tag. + * See if pvid is set on this port. That tells us which + * vlan untagged or priority-tagged traffic belongs to. */ if (pvid == VLAN_N_VID) return false; - /* PVID is set on this port. Any untagged ingress - * frame is considered to belong to this vlan. + /* PVID is set on this port. Any untagged or priority-tagged + * ingress frame is considered to belong to this vlan. */ - __vlan_hwaccel_put_tag(skb, htons(ETH_P_8021Q), pvid); + *vid = pvid; + if (likely(err)) + /* Untagged Frame. */ + __vlan_hwaccel_put_tag(skb, htons(ETH_P_8021Q), pvid); + else + /* Priority-tagged Frame. + * At this point, We know that skb->vlan_tci had + * VLAN_TAG_PRESENT bit and its VID field was 0x000. + * We update only VID field and preserve PCP field. + */ + skb->vlan_tci |= pvid; + return true; } @@ -248,7 +259,9 @@ bool br_allowed_egress(struct net_bridge *br, return false; } -/* Must be protected by RTNL */ +/* Must be protected by RTNL. + * Must be called with vid in range from 1 to 4094 inclusive. + */ int br_vlan_add(struct net_bridge *br, u16 vid, u16 flags) { struct net_port_vlans *pv = NULL; @@ -278,7 +291,9 @@ out: return err; } -/* Must be protected by RTNL */ +/* Must be protected by RTNL. + * Must be called with vid in range from 1 to 4094 inclusive. + */ int br_vlan_delete(struct net_bridge *br, u16 vid) { struct net_port_vlans *pv; @@ -289,14 +304,9 @@ int br_vlan_delete(struct net_bridge *br, u16 vid) if (!pv) return -EINVAL; - if (vid) { - /* If the VID !=0 remove fdb for this vid. VID 0 is special - * in that it's the default and is always there in the fdb. - */ - spin_lock_bh(&br->hash_lock); - fdb_delete_by_addr(br, br->dev->dev_addr, vid); - spin_unlock_bh(&br->hash_lock); - } + spin_lock_bh(&br->hash_lock); + fdb_delete_by_addr(br, br->dev->dev_addr, vid); + spin_unlock_bh(&br->hash_lock); __vlan_del(pv, vid); return 0; @@ -329,7 +339,9 @@ unlock: return 0; } -/* Must be protected by RTNL */ +/* Must be protected by RTNL. + * Must be called with vid in range from 1 to 4094 inclusive. + */ int nbp_vlan_add(struct net_bridge_port *port, u16 vid, u16 flags) { struct net_port_vlans *pv = NULL; @@ -363,7 +375,9 @@ clean_up: return err; } -/* Must be protected by RTNL */ +/* Must be protected by RTNL. + * Must be called with vid in range from 1 to 4094 inclusive. + */ int nbp_vlan_delete(struct net_bridge_port *port, u16 vid) { struct net_port_vlans *pv; @@ -374,14 +388,9 @@ int nbp_vlan_delete(struct net_bridge_port *port, u16 vid) if (!pv) return -EINVAL; - if (vid) { - /* If the VID !=0 remove fdb for this vid. VID 0 is special - * in that it's the default and is always there in the fdb. - */ - spin_lock_bh(&port->br->hash_lock); - fdb_delete_by_addr(port->br, port->dev->dev_addr, vid); - spin_unlock_bh(&port->br->hash_lock); - } + spin_lock_bh(&port->br->hash_lock); + fdb_delete_by_addr(port->br, port->dev->dev_addr, vid); + spin_unlock_bh(&port->br->hash_lock); return __vlan_del(pv, vid); } diff --git a/net/compat.c b/net/compat.c index f0a1ba6..8903258 100644 --- a/net/compat.c +++ b/net/compat.c @@ -71,6 +71,8 @@ int get_compat_msghdr(struct msghdr *kmsg, struct compat_msghdr __user *umsg) __get_user(kmsg->msg_controllen, &umsg->msg_controllen) || __get_user(kmsg->msg_flags, &umsg->msg_flags)) return -EFAULT; + if (kmsg->msg_namelen > sizeof(struct sockaddr_storage)) + return -EINVAL; kmsg->msg_name = compat_ptr(tmp1); kmsg->msg_iov = compat_ptr(tmp2); kmsg->msg_control = compat_ptr(tmp3); diff --git a/net/core/dev.c b/net/core/dev.c index 5c713f2..3430b1e 100644 --- a/net/core/dev.c +++ b/net/core/dev.c @@ -1917,7 +1917,8 @@ static struct xps_map *expand_xps_map(struct xps_map *map, return new_map; } -int netif_set_xps_queue(struct net_device *dev, struct cpumask *mask, u16 index) +int netif_set_xps_queue(struct net_device *dev, const struct cpumask *mask, + u16 index) { struct xps_dev_maps *dev_maps, *new_dev_maps = NULL; struct xps_map *map, *new_map; @@ -5247,10 +5248,12 @@ static int dev_new_index(struct net *net) /* Delayed registration/unregisteration */ static LIST_HEAD(net_todo_list); +static DECLARE_WAIT_QUEUE_HEAD(netdev_unregistering_wq); static void net_set_todo(struct net_device *dev) { list_add_tail(&dev->todo_list, &net_todo_list); + dev_net(dev)->dev_unreg_count++; } static void rollback_registered_many(struct list_head *head) @@ -5918,6 +5921,12 @@ void netdev_run_todo(void) if (dev->destructor) dev->destructor(dev); + /* Report a network device has been unregistered */ + rtnl_lock(); + dev_net(dev)->dev_unreg_count--; + __rtnl_unlock(); + wake_up(&netdev_unregistering_wq); + /* Free network device */ kobject_put(&dev->dev.kobj); } @@ -6603,6 +6612,34 @@ static void __net_exit default_device_exit(struct net *net) rtnl_unlock(); } +static void __net_exit rtnl_lock_unregistering(struct list_head *net_list) +{ + /* Return with the rtnl_lock held when there are no network + * devices unregistering in any network namespace in net_list. + */ + struct net *net; + bool unregistering; + DEFINE_WAIT(wait); + + for (;;) { + prepare_to_wait(&netdev_unregistering_wq, &wait, + TASK_UNINTERRUPTIBLE); + unregistering = false; + rtnl_lock(); + list_for_each_entry(net, net_list, exit_list) { + if (net->dev_unreg_count > 0) { + unregistering = true; + break; + } + } + if (!unregistering) + break; + __rtnl_unlock(); + schedule(); + } + finish_wait(&netdev_unregistering_wq, &wait); +} + static void __net_exit default_device_exit_batch(struct list_head *net_list) { /* At exit all network devices most be removed from a network @@ -6614,7 +6651,18 @@ static void __net_exit default_device_exit_batch(struct list_head *net_list) struct net *net; LIST_HEAD(dev_kill_list); - rtnl_lock(); + /* To prevent network device cleanup code from dereferencing + * loopback devices or network devices that have been freed + * wait here for all pending unregistrations to complete, + * before unregistring the loopback device and allowing the + * network namespace be freed. + * + * The netdev todo list containing all network devices + * unregistrations that happen in default_device_exit_batch + * will run in the rtnl_unlock() at the end of + * default_device_exit_batch. + */ + rtnl_lock_unregistering(net_list); list_for_each_entry(net, net_list, exit_list) { for_each_netdev_reverse(net, dev) { if (dev->rtnl_link_ops) diff --git a/net/core/filter.c b/net/core/filter.c index 6438f29..01b7808 100644 --- a/net/core/filter.c +++ b/net/core/filter.c @@ -644,7 +644,6 @@ void sk_filter_release_rcu(struct rcu_head *rcu) struct sk_filter *fp = container_of(rcu, struct sk_filter, rcu); bpf_jit_free(fp); - kfree(fp); } EXPORT_SYMBOL(sk_filter_release_rcu); @@ -683,7 +682,7 @@ int sk_unattached_filter_create(struct sk_filter **pfp, if (fprog->filter == NULL) return -EINVAL; - fp = kmalloc(fsize + sizeof(*fp), GFP_KERNEL); + fp = kmalloc(sk_filter_size(fprog->len), GFP_KERNEL); if (!fp) return -ENOMEM; memcpy(fp->insns, fprog->filter, fsize); @@ -723,6 +722,7 @@ int sk_attach_filter(struct sock_fprog *fprog, struct sock *sk) { struct sk_filter *fp, *old_fp; unsigned int fsize = sizeof(struct sock_filter) * fprog->len; + unsigned int sk_fsize = sk_filter_size(fprog->len); int err; if (sock_flag(sk, SOCK_FILTER_LOCKED)) @@ -732,11 +732,11 @@ int sk_attach_filter(struct sock_fprog *fprog, struct sock *sk) if (fprog->filter == NULL) return -EINVAL; - fp = sock_kmalloc(sk, fsize+sizeof(*fp), GFP_KERNEL); + fp = sock_kmalloc(sk, sk_fsize, GFP_KERNEL); if (!fp) return -ENOMEM; if (copy_from_user(fp->insns, fprog->filter, fsize)) { - sock_kfree_s(sk, fp, fsize+sizeof(*fp)); + sock_kfree_s(sk, fp, sk_fsize); return -EFAULT; } diff --git a/net/core/flow_dissector.c b/net/core/flow_dissector.c index 1929af8..8d7d0dd 100644 --- a/net/core/flow_dissector.c +++ b/net/core/flow_dissector.c @@ -154,8 +154,8 @@ ipv6: if (poff >= 0) { __be32 *ports, _ports; - nhoff += poff; - ports = skb_header_pointer(skb, nhoff, sizeof(_ports), &_ports); + ports = skb_header_pointer(skb, nhoff + poff, + sizeof(_ports), &_ports); if (ports) flow->ports = *ports; } diff --git a/net/core/secure_seq.c b/net/core/secure_seq.c index 6a2f13c..8d9d05e 100644 --- a/net/core/secure_seq.c +++ b/net/core/secure_seq.c @@ -10,12 +10,27 @@ #include <net/secure_seq.h> -static u32 net_secret[MD5_MESSAGE_BYTES / 4] ____cacheline_aligned; +#if IS_ENABLED(CONFIG_IPV6) || IS_ENABLED(CONFIG_INET) +#define NET_SECRET_SIZE (MD5_MESSAGE_BYTES / 4) -void net_secret_init(void) +static u32 net_secret[NET_SECRET_SIZE] ____cacheline_aligned; + +static void net_secret_init(void) { - get_random_bytes(net_secret, sizeof(net_secret)); + u32 tmp; + int i; + + if (likely(net_secret[0])) + return; + + for (i = NET_SECRET_SIZE; i > 0;) { + do { + get_random_bytes(&tmp, sizeof(tmp)); + } while (!tmp); + cmpxchg(&net_secret[--i], 0, tmp); + } } +#endif #ifdef CONFIG_INET static u32 seq_scale(u32 seq) @@ -42,6 +57,7 @@ __u32 secure_tcpv6_sequence_number(const __be32 *saddr, const __be32 *daddr, u32 hash[MD5_DIGEST_WORDS]; u32 i; + net_secret_init(); memcpy(hash, saddr, 16); for (i = 0; i < 4; i++) secret[i] = net_secret[i] + (__force u32)daddr[i]; @@ -63,6 +79,7 @@ u32 secure_ipv6_port_ephemeral(const __be32 *saddr, const __be32 *daddr, u32 hash[MD5_DIGEST_WORDS]; u32 i; + net_secret_init(); memcpy(hash, saddr, 16); for (i = 0; i < 4; i++) secret[i] = net_secret[i] + (__force u32) daddr[i]; @@ -82,6 +99,7 @@ __u32 secure_ip_id(__be32 daddr) { u32 hash[MD5_DIGEST_WORDS]; + net_secret_init(); hash[0] = (__force __u32) daddr; hash[1] = net_secret[13]; hash[2] = net_secret[14]; @@ -96,6 +114,7 @@ __u32 secure_ipv6_id(const __be32 daddr[4]) { __u32 hash[4]; + net_secret_init(); memcpy(hash, daddr, 16); md5_transform(hash, net_secret); @@ -107,6 +126,7 @@ __u32 secure_tcp_sequence_number(__be32 saddr, __be32 daddr, { u32 hash[MD5_DIGEST_WORDS]; + net_secret_init(); hash[0] = (__force u32)saddr; hash[1] = (__force u32)daddr; hash[2] = ((__force u16)sport << 16) + (__force u16)dport; @@ -121,6 +141,7 @@ u32 secure_ipv4_port_ephemeral(__be32 saddr, __be32 daddr, __be16 dport) { u32 hash[MD5_DIGEST_WORDS]; + net_secret_init(); hash[0] = (__force u32)saddr; hash[1] = (__force u32)daddr; hash[2] = (__force u32)dport ^ net_secret[14]; @@ -140,6 +161,7 @@ u64 secure_dccp_sequence_number(__be32 saddr, __be32 daddr, u32 hash[MD5_DIGEST_WORDS]; u64 seq; + net_secret_init(); hash[0] = (__force u32)saddr; hash[1] = (__force u32)daddr; hash[2] = ((__force u16)sport << 16) + (__force u16)dport; @@ -164,6 +186,7 @@ u64 secure_dccpv6_sequence_number(__be32 *saddr, __be32 *daddr, u64 seq; u32 i; + net_secret_init(); memcpy(hash, saddr, 16); for (i = 0; i < 4; i++) secret[i] = net_secret[i] + daddr[i]; diff --git a/net/core/sock.c b/net/core/sock.c index 5b6beba..0b39e7a 100644 --- a/net/core/sock.c +++ b/net/core/sock.c @@ -2319,6 +2319,7 @@ void sock_init_data(struct socket *sock, struct sock *sk) sk->sk_ll_usec = sysctl_net_busy_read; #endif + sk->sk_pacing_rate = ~0U; /* * Before updating sk_refcnt, we must commit prior changes to memory * (Documentation/RCU/rculist_nulls.txt for details) diff --git a/net/ieee802154/6lowpan.c b/net/ieee802154/6lowpan.c index c85e71e..ff41b4d 100644 --- a/net/ieee802154/6lowpan.c +++ b/net/ieee802154/6lowpan.c @@ -1372,6 +1372,8 @@ static int lowpan_newlink(struct net *src_net, struct net_device *dev, real_dev = dev_get_by_index(src_net, nla_get_u32(tb[IFLA_LINK])); if (!real_dev) return -ENODEV; + if (real_dev->type != ARPHRD_IEEE802154) + return -EINVAL; lowpan_dev_info(dev)->real_dev = real_dev; lowpan_dev_info(dev)->fragment_tag = 0; @@ -1386,6 +1388,9 @@ static int lowpan_newlink(struct net *src_net, struct net_device *dev, entry->ldev = dev; + /* Set the lowpan harware address to the wpan hardware address. */ + memcpy(dev->dev_addr, real_dev->dev_addr, IEEE802154_ADDR_LEN); + mutex_lock(&lowpan_dev_info(dev)->dev_list_mtx); INIT_LIST_HEAD(&entry->list); list_add_tail(&entry->list, &lowpan_devices); diff --git a/net/ipv4/af_inet.c b/net/ipv4/af_inet.c index 7a1874b..cfeb85c 100644 --- a/net/ipv4/af_inet.c +++ b/net/ipv4/af_inet.c @@ -263,10 +263,8 @@ void build_ehash_secret(void) get_random_bytes(&rnd, sizeof(rnd)); } while (rnd == 0); - if (cmpxchg(&inet_ehash_secret, 0, rnd) == 0) { + if (cmpxchg(&inet_ehash_secret, 0, rnd) == 0) get_random_bytes(&ipv6_hash_secret, sizeof(ipv6_hash_secret)); - net_secret_init(); - } } EXPORT_SYMBOL(build_ehash_secret); diff --git a/net/ipv4/igmp.c b/net/ipv4/igmp.c index dace87f..7defdc9 100644 --- a/net/ipv4/igmp.c +++ b/net/ipv4/igmp.c @@ -736,7 +736,7 @@ static void igmp_gq_timer_expire(unsigned long data) in_dev->mr_gq_running = 0; igmpv3_send_report(in_dev, NULL); - __in_dev_put(in_dev); + in_dev_put(in_dev); } static void igmp_ifc_timer_expire(unsigned long data) @@ -749,7 +749,7 @@ static void igmp_ifc_timer_expire(unsigned long data) igmp_ifc_start_timer(in_dev, unsolicited_report_interval(in_dev)); } - __in_dev_put(in_dev); + in_dev_put(in_dev); } static void igmp_ifc_event(struct in_device *in_dev) diff --git a/net/ipv4/inet_hashtables.c b/net/ipv4/inet_hashtables.c index 7bd8983..96da9c7 100644 --- a/net/ipv4/inet_hashtables.c +++ b/net/ipv4/inet_hashtables.c @@ -287,7 +287,7 @@ begintw: if (unlikely(!INET_TW_MATCH(sk, net, acookie, saddr, daddr, ports, dif))) { - sock_put(sk); + inet_twsk_put(inet_twsk(sk)); goto begintw; } goto out; diff --git a/net/ipv4/ip_output.c b/net/ipv4/ip_output.c index a04d872..3982eab 100644 --- a/net/ipv4/ip_output.c +++ b/net/ipv4/ip_output.c @@ -772,15 +772,20 @@ static inline int ip_ufo_append_data(struct sock *sk, /* initialize protocol header pointer */ skb->transport_header = skb->network_header + fragheaderlen; - skb->ip_summed = CHECKSUM_PARTIAL; skb->csum = 0; - /* specify the length of each IP datagram fragment */ - skb_shinfo(skb)->gso_size = maxfraglen - fragheaderlen; - skb_shinfo(skb)->gso_type = SKB_GSO_UDP; + __skb_queue_tail(queue, skb); + } else if (skb_is_gso(skb)) { + goto append; } + skb->ip_summed = CHECKSUM_PARTIAL; + /* specify the length of each IP datagram fragment */ + skb_shinfo(skb)->gso_size = maxfraglen - fragheaderlen; + skb_shinfo(skb)->gso_type = SKB_GSO_UDP; + +append: return skb_append_datato_frags(sk, skb, getfrag, from, (length - transhdrlen)); } diff --git a/net/ipv4/ip_tunnel.c b/net/ipv4/ip_tunnel.c index ac9fabe0..63a6d6d 100644 --- a/net/ipv4/ip_tunnel.c +++ b/net/ipv4/ip_tunnel.c @@ -623,6 +623,7 @@ void ip_tunnel_xmit(struct sk_buff *skb, struct net_device *dev, tunnel->err_count = 0; } + tos = ip_tunnel_ecn_encap(tos, inner_iph, skb); ttl = tnl_params->ttl; if (ttl == 0) { if (skb->protocol == htons(ETH_P_IP)) @@ -641,18 +642,17 @@ void ip_tunnel_xmit(struct sk_buff *skb, struct net_device *dev, max_headroom = LL_RESERVED_SPACE(rt->dst.dev) + sizeof(struct iphdr) + rt->dst.header_len; - if (max_headroom > dev->needed_headroom) { + if (max_headroom > dev->needed_headroom) dev->needed_headroom = max_headroom; - if (skb_cow_head(skb, dev->needed_headroom)) { - dev->stats.tx_dropped++; - dev_kfree_skb(skb); - return; - } + + if (skb_cow_head(skb, dev->needed_headroom)) { + dev->stats.tx_dropped++; + dev_kfree_skb(skb); + return; } err = iptunnel_xmit(rt, skb, fl4.saddr, fl4.daddr, protocol, - ip_tunnel_ecn_encap(tos, inner_iph, skb), ttl, df, - !net_eq(tunnel->net, dev_net(dev))); + tos, ttl, df, !net_eq(tunnel->net, dev_net(dev))); iptunnel_xmit_stats(err, &dev->stats, dev->tstats); return; @@ -853,8 +853,10 @@ int ip_tunnel_init_net(struct net *net, int ip_tnl_net_id, /* FB netdevice is special: we have one, and only one per netns. * Allowing to move it to another netns is clearly unsafe. */ - if (!IS_ERR(itn->fb_tunnel_dev)) + if (!IS_ERR(itn->fb_tunnel_dev)) { itn->fb_tunnel_dev->features |= NETIF_F_NETNS_LOCAL; + ip_tunnel_add(itn, netdev_priv(itn->fb_tunnel_dev)); + } rtnl_unlock(); return PTR_RET(itn->fb_tunnel_dev); @@ -884,8 +886,6 @@ static void ip_tunnel_destroy(struct ip_tunnel_net *itn, struct list_head *head, if (!net_eq(dev_net(t->dev), net)) unregister_netdevice_queue(t->dev, head); } - if (itn->fb_tunnel_dev) - unregister_netdevice_queue(itn->fb_tunnel_dev, head); } void ip_tunnel_delete_net(struct ip_tunnel_net *itn, struct rtnl_link_ops *ops) diff --git a/net/ipv4/ip_tunnel_core.c b/net/ipv4/ip_tunnel_core.c index d6c856b..c31e3ad 100644 --- a/net/ipv4/ip_tunnel_core.c +++ b/net/ipv4/ip_tunnel_core.c @@ -61,7 +61,7 @@ int iptunnel_xmit(struct rtable *rt, struct sk_buff *skb, memset(IPCB(skb), 0, sizeof(*IPCB(skb))); /* Push down and install the IP header. */ - __skb_push(skb, sizeof(struct iphdr)); + skb_push(skb, sizeof(struct iphdr)); skb_reset_network_header(skb); iph = ip_hdr(skb); diff --git a/net/ipv4/ip_vti.c b/net/ipv4/ip_vti.c index e805e7b..6e87f85 100644 --- a/net/ipv4/ip_vti.c +++ b/net/ipv4/ip_vti.c @@ -125,8 +125,17 @@ static int vti_rcv(struct sk_buff *skb) iph->saddr, iph->daddr, 0); if (tunnel != NULL) { struct pcpu_tstats *tstats; + u32 oldmark = skb->mark; + int ret; - if (!xfrm4_policy_check(NULL, XFRM_POLICY_IN, skb)) + + /* temporarily mark the skb with the tunnel o_key, to + * only match policies with this mark. + */ + skb->mark = be32_to_cpu(tunnel->parms.o_key); + ret = xfrm4_policy_check(NULL, XFRM_POLICY_IN, skb); + skb->mark = oldmark; + if (!ret) return -1; tstats = this_cpu_ptr(tunnel->dev->tstats); @@ -135,7 +144,6 @@ static int vti_rcv(struct sk_buff *skb) tstats->rx_bytes += skb->len; u64_stats_update_end(&tstats->syncp); - skb->mark = 0; secpath_reset(skb); skb->dev = tunnel->dev; return 1; @@ -167,7 +175,7 @@ static netdev_tx_t vti_tunnel_xmit(struct sk_buff *skb, struct net_device *dev) memset(&fl4, 0, sizeof(fl4)); flowi4_init_output(&fl4, tunnel->parms.link, - be32_to_cpu(tunnel->parms.i_key), RT_TOS(tos), + be32_to_cpu(tunnel->parms.o_key), RT_TOS(tos), RT_SCOPE_UNIVERSE, IPPROTO_IPIP, 0, dst, tiph->saddr, 0, 0); diff --git a/net/ipv4/netfilter/ipt_SYNPROXY.c b/net/ipv4/netfilter/ipt_SYNPROXY.c index 67e17dc..b6346bf 100644 --- a/net/ipv4/netfilter/ipt_SYNPROXY.c +++ b/net/ipv4/netfilter/ipt_SYNPROXY.c @@ -267,7 +267,8 @@ synproxy_tg4(struct sk_buff *skb, const struct xt_action_param *par) if (th == NULL) return NF_DROP; - synproxy_parse_options(skb, par->thoff, th, &opts); + if (!synproxy_parse_options(skb, par->thoff, th, &opts)) + return NF_DROP; if (th->syn && !(th->ack || th->fin || th->rst)) { /* Initial SYN from client */ @@ -350,7 +351,8 @@ static unsigned int ipv4_synproxy_hook(unsigned int hooknum, /* fall through */ case TCP_CONNTRACK_SYN_SENT: - synproxy_parse_options(skb, thoff, th, &opts); + if (!synproxy_parse_options(skb, thoff, th, &opts)) + return NF_DROP; if (!th->syn && th->ack && CTINFO2DIR(ctinfo) == IP_CT_DIR_ORIGINAL) { @@ -373,7 +375,9 @@ static unsigned int ipv4_synproxy_hook(unsigned int hooknum, if (!th->syn || !th->ack) break; - synproxy_parse_options(skb, thoff, th, &opts); + if (!synproxy_parse_options(skb, thoff, th, &opts)) + return NF_DROP; + if (opts.options & XT_SYNPROXY_OPT_TIMESTAMP) synproxy->tsoff = opts.tsval - synproxy->its; diff --git a/net/ipv4/raw.c b/net/ipv4/raw.c index bfec521..193db03 100644 --- a/net/ipv4/raw.c +++ b/net/ipv4/raw.c @@ -218,8 +218,10 @@ static void raw_err(struct sock *sk, struct sk_buff *skb, u32 info) if (type == ICMP_DEST_UNREACH && code == ICMP_FRAG_NEEDED) ipv4_sk_update_pmtu(skb, sk, info); - else if (type == ICMP_REDIRECT) + else if (type == ICMP_REDIRECT) { ipv4_sk_redirect(skb, sk); + return; + } /* Report error on raw socket, if: 1. User requested ip_recverr. diff --git a/net/ipv4/route.c b/net/ipv4/route.c index 727f436..6011615 100644 --- a/net/ipv4/route.c +++ b/net/ipv4/route.c @@ -2072,7 +2072,7 @@ struct rtable *__ip_route_output_key(struct net *net, struct flowi4 *fl4) RT_SCOPE_LINK); goto make_route; } - if (fl4->saddr) { + if (!fl4->saddr) { if (ipv4_is_multicast(fl4->daddr)) fl4->saddr = inet_select_addr(dev_out, 0, fl4->flowi4_scope); diff --git a/net/ipv4/tcp_input.c b/net/ipv4/tcp_input.c index 25a89ea..a16b01b 100644 --- a/net/ipv4/tcp_input.c +++ b/net/ipv4/tcp_input.c @@ -1284,7 +1284,10 @@ static bool tcp_shifted_skb(struct sock *sk, struct sk_buff *skb, tp->lost_cnt_hint -= tcp_skb_pcount(prev); } - TCP_SKB_CB(skb)->tcp_flags |= TCP_SKB_CB(prev)->tcp_flags; + TCP_SKB_CB(prev)->tcp_flags |= TCP_SKB_CB(skb)->tcp_flags; + if (TCP_SKB_CB(skb)->tcp_flags & TCPHDR_FIN) + TCP_SKB_CB(prev)->end_seq++; + if (skb == tcp_highest_sack(sk)) tcp_advance_highest_sack(sk, skb); @@ -3288,7 +3291,7 @@ static void tcp_process_tlp_ack(struct sock *sk, u32 ack, int flag) tcp_init_cwnd_reduction(sk, true); tcp_set_ca_state(sk, TCP_CA_CWR); tcp_end_cwnd_reduction(sk); - tcp_set_ca_state(sk, TCP_CA_Open); + tcp_try_keep_open(sk); NET_INC_STATS_BH(sock_net(sk), LINUX_MIB_TCPLOSSPROBERECOVERY); } @@ -5709,6 +5712,8 @@ int tcp_rcv_state_process(struct sock *sk, struct sk_buff *skb, } else tcp_init_metrics(sk); + tcp_update_pacing_rate(sk); + /* Prevent spurious tcp_cwnd_restart() on first data packet */ tp->lsndtime = tcp_time_stamp; diff --git a/net/ipv4/tcp_output.c b/net/ipv4/tcp_output.c index 7c83cb8..d46f214 100644 --- a/net/ipv4/tcp_output.c +++ b/net/ipv4/tcp_output.c @@ -637,6 +637,8 @@ static unsigned int tcp_established_options(struct sock *sk, struct sk_buff *skb unsigned int size = 0; unsigned int eff_sacks; + opts->options = 0; + #ifdef CONFIG_TCP_MD5SIG *md5 = tp->af_specific->md5_lookup(sk, sk); if (unlikely(*md5)) { @@ -895,8 +897,7 @@ static int tcp_transmit_skb(struct sock *sk, struct sk_buff *skb, int clone_it, skb_orphan(skb); skb->sk = sk; - skb->destructor = (sysctl_tcp_limit_output_bytes > 0) ? - tcp_wfree : sock_wfree; + skb->destructor = tcp_wfree; atomic_add(skb->truesize, &sk->sk_wmem_alloc); /* Build TCP header and checksum it. */ @@ -985,8 +986,10 @@ static void tcp_queue_skb(struct sock *sk, struct sk_buff *skb) static void tcp_set_skb_tso_segs(const struct sock *sk, struct sk_buff *skb, unsigned int mss_now) { - if (skb->len <= mss_now || !sk_can_gso(sk) || - skb->ip_summed == CHECKSUM_NONE) { + /* Make sure we own this skb before messing gso_size/gso_segs */ + WARN_ON_ONCE(skb_cloned(skb)); + + if (skb->len <= mss_now || skb->ip_summed == CHECKSUM_NONE) { /* Avoid the costly divide in the normal * non-TSO case. */ @@ -1066,9 +1069,7 @@ int tcp_fragment(struct sock *sk, struct sk_buff *skb, u32 len, if (nsize < 0) nsize = 0; - if (skb_cloned(skb) && - skb_is_nonlinear(skb) && - pskb_expand_head(skb, 0, 0, GFP_ATOMIC)) + if (skb_unclone(skb, GFP_ATOMIC)) return -ENOMEM; /* Get a new skb... force flag on. */ @@ -1840,7 +1841,6 @@ static bool tcp_write_xmit(struct sock *sk, unsigned int mss_now, int nonagle, while ((skb = tcp_send_head(sk))) { unsigned int limit; - tso_segs = tcp_init_tso_segs(sk, skb, mss_now); BUG_ON(!tso_segs); @@ -1869,13 +1869,20 @@ static bool tcp_write_xmit(struct sock *sk, unsigned int mss_now, int nonagle, break; } - /* TSQ : sk_wmem_alloc accounts skb truesize, - * including skb overhead. But thats OK. + /* TCP Small Queues : + * Control number of packets in qdisc/devices to two packets / or ~1 ms. + * This allows for : + * - better RTT estimation and ACK scheduling + * - faster recovery + * - high rates */ - if (atomic_read(&sk->sk_wmem_alloc) >= sysctl_tcp_limit_output_bytes) { + limit = max(skb->truesize, sk->sk_pacing_rate >> 10); + + if (atomic_read(&sk->sk_wmem_alloc) > limit) { set_bit(TSQ_THROTTLED, &tp->tsq_flags); break; } + limit = mss_now; if (tso_segs > 1 && !tcp_urg_mode(tp)) limit = tcp_mss_split_point(sk, skb, mss_now, @@ -2337,6 +2344,8 @@ int __tcp_retransmit_skb(struct sock *sk, struct sk_buff *skb) int oldpcount = tcp_skb_pcount(skb); if (unlikely(oldpcount > 1)) { + if (skb_unclone(skb, GFP_ATOMIC)) + return -ENOMEM; tcp_init_tso_segs(sk, skb, cur_mss); tcp_adjust_pcount(sk, skb, oldpcount - tcp_skb_pcount(skb)); } diff --git a/net/ipv4/udp.c b/net/ipv4/udp.c index 74d2c95..0ca44df 100644 --- a/net/ipv4/udp.c +++ b/net/ipv4/udp.c @@ -658,7 +658,7 @@ void __udp4_lib_err(struct sk_buff *skb, u32 info, struct udp_table *udptable) break; case ICMP_REDIRECT: ipv4_sk_redirect(skb, sk); - break; + goto out; } /* diff --git a/net/ipv4/xfrm4_policy.c b/net/ipv4/xfrm4_policy.c index 9a459be..ccde542 100644 --- a/net/ipv4/xfrm4_policy.c +++ b/net/ipv4/xfrm4_policy.c @@ -107,6 +107,7 @@ _decode_session4(struct sk_buff *skb, struct flowi *fl, int reverse) memset(fl4, 0, sizeof(struct flowi4)); fl4->flowi4_mark = skb->mark; + fl4->flowi4_oif = skb_dst(skb)->dev->ifindex; if (!ip_is_fragment(iph)) { switch (iph->protocol) { diff --git a/net/ipv6/addrconf.c b/net/ipv6/addrconf.c index d6ff126..cd3fb30 100644 --- a/net/ipv6/addrconf.c +++ b/net/ipv6/addrconf.c @@ -1499,6 +1499,33 @@ static bool ipv6_chk_same_addr(struct net *net, const struct in6_addr *addr, return false; } +/* Compares an address/prefix_len with addresses on device @dev. + * If one is found it returns true. + */ +bool ipv6_chk_custom_prefix(const struct in6_addr *addr, + const unsigned int prefix_len, struct net_device *dev) +{ + struct inet6_dev *idev; + struct inet6_ifaddr *ifa; + bool ret = false; + + rcu_read_lock(); + idev = __in6_dev_get(dev); + if (idev) { + read_lock_bh(&idev->lock); + list_for_each_entry(ifa, &idev->addr_list, if_list) { + ret = ipv6_prefix_equal(addr, &ifa->addr, prefix_len); + if (ret) + break; + } + read_unlock_bh(&idev->lock); + } + rcu_read_unlock(); + + return ret; +} +EXPORT_SYMBOL(ipv6_chk_custom_prefix); + int ipv6_chk_prefix(const struct in6_addr *addr, struct net_device *dev) { struct inet6_dev *idev; @@ -2193,43 +2220,21 @@ ok: else stored_lft = 0; if (!update_lft && !create && stored_lft) { - if (valid_lft > MIN_VALID_LIFETIME || - valid_lft > stored_lft) - update_lft = 1; - else if (stored_lft <= MIN_VALID_LIFETIME) { - /* valid_lft <= stored_lft is always true */ - /* - * RFC 4862 Section 5.5.3e: - * "Note that the preferred lifetime of - * the corresponding address is always - * reset to the Preferred Lifetime in - * the received Prefix Information - * option, regardless of whether the - * valid lifetime is also reset or - * ignored." - * - * So if the preferred lifetime in - * this advertisement is different - * than what we have stored, but the - * valid lifetime is invalid, just - * reset prefered_lft. - * - * We must set the valid lifetime - * to the stored lifetime since we'll - * be updating the timestamp below, - * else we'll set it back to the - * minimum. - */ - if (prefered_lft != ifp->prefered_lft) { - valid_lft = stored_lft; - update_lft = 1; - } - } else { - valid_lft = MIN_VALID_LIFETIME; - if (valid_lft < prefered_lft) - prefered_lft = valid_lft; - update_lft = 1; - } + const u32 minimum_lft = min( + stored_lft, (u32)MIN_VALID_LIFETIME); + valid_lft = max(valid_lft, minimum_lft); + + /* RFC4862 Section 5.5.3e: + * "Note that the preferred lifetime of the + * corresponding address is always reset to + * the Preferred Lifetime in the received + * Prefix Information option, regardless of + * whether the valid lifetime is also reset or + * ignored." + * + * So we should always update prefered_lft here. + */ + update_lft = 1; } if (update_lft) { diff --git a/net/ipv6/ah6.c b/net/ipv6/ah6.c index 73784c3..82e1da3 100644 --- a/net/ipv6/ah6.c +++ b/net/ipv6/ah6.c @@ -618,8 +618,7 @@ static void ah6_err(struct sk_buff *skb, struct inet6_skb_parm *opt, struct ip_auth_hdr *ah = (struct ip_auth_hdr*)(skb->data+offset); struct xfrm_state *x; - if (type != ICMPV6_DEST_UNREACH && - type != ICMPV6_PKT_TOOBIG && + if (type != ICMPV6_PKT_TOOBIG && type != NDISC_REDIRECT) return; diff --git a/net/ipv6/esp6.c b/net/ipv6/esp6.c index d3618a7..e67e63f 100644 --- a/net/ipv6/esp6.c +++ b/net/ipv6/esp6.c @@ -436,8 +436,7 @@ static void esp6_err(struct sk_buff *skb, struct inet6_skb_parm *opt, struct ip_esp_hdr *esph = (struct ip_esp_hdr *)(skb->data + offset); struct xfrm_state *x; - if (type != ICMPV6_DEST_UNREACH && - type != ICMPV6_PKT_TOOBIG && + if (type != ICMPV6_PKT_TOOBIG && type != NDISC_REDIRECT) return; diff --git a/net/ipv6/inet6_hashtables.c b/net/ipv6/inet6_hashtables.c index 32b4a16..066640e 100644 --- a/net/ipv6/inet6_hashtables.c +++ b/net/ipv6/inet6_hashtables.c @@ -116,7 +116,7 @@ begintw: } if (unlikely(!INET6_TW_MATCH(sk, net, saddr, daddr, ports, dif))) { - sock_put(sk); + inet_twsk_put(inet_twsk(sk)); goto begintw; } goto out; diff --git a/net/ipv6/ip6_gre.c b/net/ipv6/ip6_gre.c index 6b26e9f..bf4a9a0 100644 --- a/net/ipv6/ip6_gre.c +++ b/net/ipv6/ip6_gre.c @@ -618,7 +618,7 @@ static netdev_tx_t ip6gre_xmit2(struct sk_buff *skb, struct ip6_tnl *tunnel = netdev_priv(dev); struct net_device *tdev; /* Device to other host */ struct ipv6hdr *ipv6h; /* Our new IP header */ - unsigned int max_headroom; /* The extra header space needed */ + unsigned int max_headroom = 0; /* The extra header space needed */ int gre_hlen; struct ipv6_tel_txoption opt; int mtu; @@ -693,7 +693,7 @@ static netdev_tx_t ip6gre_xmit2(struct sk_buff *skb, skb_scrub_packet(skb, !net_eq(tunnel->net, dev_net(dev))); - max_headroom = LL_RESERVED_SPACE(tdev) + gre_hlen + dst->header_len; + max_headroom += LL_RESERVED_SPACE(tdev) + gre_hlen + dst->header_len; if (skb_headroom(skb) < max_headroom || skb_shared(skb) || (skb_cloned(skb) && !skb_clone_writable(skb, 0))) { @@ -976,6 +976,7 @@ static void ip6gre_tnl_link_config(struct ip6_tnl *t, int set_mtu) if (t->parms.o_flags&GRE_SEQ) addend += 4; } + t->hlen = addend; if (p->flags & IP6_TNL_F_CAP_XMIT) { int strict = (ipv6_addr_type(&p->raddr) & @@ -1002,8 +1003,6 @@ static void ip6gre_tnl_link_config(struct ip6_tnl *t, int set_mtu) } ip6_rt_put(rt); } - - t->hlen = addend; } static int ip6gre_tnl_change(struct ip6_tnl *t, @@ -1173,9 +1172,8 @@ done: static int ip6gre_tunnel_change_mtu(struct net_device *dev, int new_mtu) { - struct ip6_tnl *tunnel = netdev_priv(dev); if (new_mtu < 68 || - new_mtu > 0xFFF8 - dev->hard_header_len - tunnel->hlen) + new_mtu > 0xFFF8 - dev->hard_header_len) return -EINVAL; dev->mtu = new_mtu; return 0; diff --git a/net/ipv6/ip6_output.c b/net/ipv6/ip6_output.c index 3a692d5..91fb4e8 100644 --- a/net/ipv6/ip6_output.c +++ b/net/ipv6/ip6_output.c @@ -105,7 +105,7 @@ static int ip6_finish_output2(struct sk_buff *skb) } rcu_read_lock_bh(); - nexthop = rt6_nexthop((struct rt6_info *)dst, &ipv6_hdr(skb)->daddr); + nexthop = rt6_nexthop((struct rt6_info *)dst); neigh = __ipv6_neigh_lookup_noref(dst->dev, nexthop); if (unlikely(!neigh)) neigh = __neigh_create(&nd_tbl, nexthop, dst->dev, false); @@ -874,7 +874,7 @@ static int ip6_dst_lookup_tail(struct sock *sk, */ rt = (struct rt6_info *) *dst; rcu_read_lock_bh(); - n = __ipv6_neigh_lookup_noref(rt->dst.dev, rt6_nexthop(rt, &fl6->daddr)); + n = __ipv6_neigh_lookup_noref(rt->dst.dev, rt6_nexthop(rt)); err = n && !(n->nud_state & NUD_VALID) ? -EINVAL : 0; rcu_read_unlock_bh(); @@ -1008,6 +1008,7 @@ static inline int ip6_ufo_append_data(struct sock *sk, { struct sk_buff *skb; + struct frag_hdr fhdr; int err; /* There is support for UDP large send offload by network @@ -1034,33 +1035,26 @@ static inline int ip6_ufo_append_data(struct sock *sk, skb->transport_header = skb->network_header + fragheaderlen; skb->protocol = htons(ETH_P_IPV6); - skb->ip_summed = CHECKSUM_PARTIAL; skb->csum = 0; - } - - err = skb_append_datato_frags(sk,skb, getfrag, from, - (length - transhdrlen)); - if (!err) { - struct frag_hdr fhdr; - /* Specify the length of each IPv6 datagram fragment. - * It has to be a multiple of 8. - */ - skb_shinfo(skb)->gso_size = (mtu - fragheaderlen - - sizeof(struct frag_hdr)) & ~7; - skb_shinfo(skb)->gso_type = SKB_GSO_UDP; - ipv6_select_ident(&fhdr, rt); - skb_shinfo(skb)->ip6_frag_id = fhdr.identification; __skb_queue_tail(&sk->sk_write_queue, skb); - - return 0; + } else if (skb_is_gso(skb)) { + goto append; } - /* There is not enough support do UPD LSO, - * so follow normal path - */ - kfree_skb(skb); - return err; + skb->ip_summed = CHECKSUM_PARTIAL; + /* Specify the length of each IPv6 datagram fragment. + * It has to be a multiple of 8. + */ + skb_shinfo(skb)->gso_size = (mtu - fragheaderlen - + sizeof(struct frag_hdr)) & ~7; + skb_shinfo(skb)->gso_type = SKB_GSO_UDP; + ipv6_select_ident(&fhdr, rt); + skb_shinfo(skb)->ip6_frag_id = fhdr.identification; + +append: + return skb_append_datato_frags(sk, skb, getfrag, from, + (length - transhdrlen)); } static inline struct ipv6_opt_hdr *ip6_opt_dup(struct ipv6_opt_hdr *src, @@ -1227,27 +1221,27 @@ int ip6_append_data(struct sock *sk, int getfrag(void *from, char *to, * --yoshfuji */ - cork->length += length; - if (length > mtu) { - int proto = sk->sk_protocol; - if (dontfrag && (proto == IPPROTO_UDP || proto == IPPROTO_RAW)){ - ipv6_local_rxpmtu(sk, fl6, mtu-exthdrlen); - return -EMSGSIZE; - } - - if (proto == IPPROTO_UDP && - (rt->dst.dev->features & NETIF_F_UFO)) { + if ((length > mtu) && dontfrag && (sk->sk_protocol == IPPROTO_UDP || + sk->sk_protocol == IPPROTO_RAW)) { + ipv6_local_rxpmtu(sk, fl6, mtu-exthdrlen); + return -EMSGSIZE; + } - err = ip6_ufo_append_data(sk, getfrag, from, length, - hh_len, fragheaderlen, - transhdrlen, mtu, flags, rt); - if (err) - goto error; - return 0; - } + skb = skb_peek_tail(&sk->sk_write_queue); + cork->length += length; + if (((length > mtu) || + (skb && skb_is_gso(skb))) && + (sk->sk_protocol == IPPROTO_UDP) && + (rt->dst.dev->features & NETIF_F_UFO)) { + err = ip6_ufo_append_data(sk, getfrag, from, length, + hh_len, fragheaderlen, + transhdrlen, mtu, flags, rt); + if (err) + goto error; + return 0; } - if ((skb = skb_peek_tail(&sk->sk_write_queue)) == NULL) + if (!skb) goto alloc_new_skb; while (length > 0) { diff --git a/net/ipv6/ip6_tunnel.c b/net/ipv6/ip6_tunnel.c index 2d8f482..583b77e 100644 --- a/net/ipv6/ip6_tunnel.c +++ b/net/ipv6/ip6_tunnel.c @@ -1430,9 +1430,17 @@ ip6_tnl_ioctl(struct net_device *dev, struct ifreq *ifr, int cmd) static int ip6_tnl_change_mtu(struct net_device *dev, int new_mtu) { - if (new_mtu < IPV6_MIN_MTU) { - return -EINVAL; + struct ip6_tnl *tnl = netdev_priv(dev); + + if (tnl->parms.proto == IPPROTO_IPIP) { + if (new_mtu < 68) + return -EINVAL; + } else { + if (new_mtu < IPV6_MIN_MTU) + return -EINVAL; } + if (new_mtu > 0xFFF8 - dev->hard_header_len) + return -EINVAL; dev->mtu = new_mtu; return 0; } @@ -1731,8 +1739,6 @@ static void __net_exit ip6_tnl_destroy_tunnels(struct ip6_tnl_net *ip6n) } } - t = rtnl_dereference(ip6n->tnls_wc[0]); - unregister_netdevice_queue(t->dev, &list); unregister_netdevice_many(&list); } @@ -1752,6 +1758,7 @@ static int __net_init ip6_tnl_init_net(struct net *net) if (!ip6n->fb_tnl_dev) goto err_alloc_dev; dev_net_set(ip6n->fb_tnl_dev, net); + ip6n->fb_tnl_dev->rtnl_link_ops = &ip6_link_ops; /* FB netdevice is special: we have one, and only one per netns. * Allowing to move it to another netns is clearly unsafe. */ diff --git a/net/ipv6/ipcomp6.c b/net/ipv6/ipcomp6.c index 5636a91..ce507d9 100644 --- a/net/ipv6/ipcomp6.c +++ b/net/ipv6/ipcomp6.c @@ -64,8 +64,7 @@ static void ipcomp6_err(struct sk_buff *skb, struct inet6_skb_parm *opt, (struct ip_comp_hdr *)(skb->data + offset); struct xfrm_state *x; - if (type != ICMPV6_DEST_UNREACH && - type != ICMPV6_PKT_TOOBIG && + if (type != ICMPV6_PKT_TOOBIG && type != NDISC_REDIRECT) return; diff --git a/net/ipv6/mcast.c b/net/ipv6/mcast.c index 096cd67..d18f9f9 100644 --- a/net/ipv6/mcast.c +++ b/net/ipv6/mcast.c @@ -2034,7 +2034,7 @@ static void mld_dad_timer_expire(unsigned long data) if (idev->mc_dad_count) mld_dad_start_timer(idev, idev->mc_maxdelay); } - __in6_dev_put(idev); + in6_dev_put(idev); } static int ip6_mc_del1_src(struct ifmcaddr6 *pmc, int sfmode, @@ -2379,7 +2379,7 @@ static void mld_gq_timer_expire(unsigned long data) idev->mc_gq_running = 0; mld_send_report(idev, NULL); - __in6_dev_put(idev); + in6_dev_put(idev); } static void mld_ifc_timer_expire(unsigned long data) @@ -2392,7 +2392,7 @@ static void mld_ifc_timer_expire(unsigned long data) if (idev->mc_ifc_count) mld_ifc_start_timer(idev, idev->mc_maxdelay); } - __in6_dev_put(idev); + in6_dev_put(idev); } static void mld_ifc_event(struct inet6_dev *idev) diff --git a/net/ipv6/netfilter/ip6t_SYNPROXY.c b/net/ipv6/netfilter/ip6t_SYNPROXY.c index 19cfea8..2748b04 100644 --- a/net/ipv6/netfilter/ip6t_SYNPROXY.c +++ b/net/ipv6/netfilter/ip6t_SYNPROXY.c @@ -282,7 +282,8 @@ synproxy_tg6(struct sk_buff *skb, const struct xt_action_param *par) if (th == NULL) return NF_DROP; - synproxy_parse_options(skb, par->thoff, th, &opts); + if (!synproxy_parse_options(skb, par->thoff, th, &opts)) + return NF_DROP; if (th->syn && !(th->ack || th->fin || th->rst)) { /* Initial SYN from client */ @@ -372,7 +373,8 @@ static unsigned int ipv6_synproxy_hook(unsigned int hooknum, /* fall through */ case TCP_CONNTRACK_SYN_SENT: - synproxy_parse_options(skb, thoff, th, &opts); + if (!synproxy_parse_options(skb, thoff, th, &opts)) + return NF_DROP; if (!th->syn && th->ack && CTINFO2DIR(ctinfo) == IP_CT_DIR_ORIGINAL) { @@ -395,7 +397,9 @@ static unsigned int ipv6_synproxy_hook(unsigned int hooknum, if (!th->syn || !th->ack) break; - synproxy_parse_options(skb, thoff, th, &opts); + if (!synproxy_parse_options(skb, thoff, th, &opts)) + return NF_DROP; + if (opts.options & XT_SYNPROXY_OPT_TIMESTAMP) synproxy->tsoff = opts.tsval - synproxy->its; diff --git a/net/ipv6/raw.c b/net/ipv6/raw.c index 58916bb..a4ed241 100644 --- a/net/ipv6/raw.c +++ b/net/ipv6/raw.c @@ -335,8 +335,10 @@ static void rawv6_err(struct sock *sk, struct sk_buff *skb, ip6_sk_update_pmtu(skb, sk, info); harderr = (np->pmtudisc == IPV6_PMTUDISC_DO); } - if (type == NDISC_REDIRECT) + if (type == NDISC_REDIRECT) { ip6_sk_redirect(skb, sk); + return; + } if (np->recverr) { u8 *payload = skb->data; if (!inet->hdrincl) diff --git a/net/ipv6/route.c b/net/ipv6/route.c index c979dd9..f54e3a1 100644 --- a/net/ipv6/route.c +++ b/net/ipv6/route.c @@ -476,6 +476,24 @@ out: } #ifdef CONFIG_IPV6_ROUTER_PREF +struct __rt6_probe_work { + struct work_struct work; + struct in6_addr target; + struct net_device *dev; +}; + +static void rt6_probe_deferred(struct work_struct *w) +{ + struct in6_addr mcaddr; + struct __rt6_probe_work *work = + container_of(w, struct __rt6_probe_work, work); + + addrconf_addr_solict_mult(&work->target, &mcaddr); + ndisc_send_ns(work->dev, NULL, &work->target, &mcaddr, NULL); + dev_put(work->dev); + kfree(w); +} + static void rt6_probe(struct rt6_info *rt) { struct neighbour *neigh; @@ -499,17 +517,23 @@ static void rt6_probe(struct rt6_info *rt) if (!neigh || time_after(jiffies, neigh->updated + rt->rt6i_idev->cnf.rtr_probe_interval)) { - struct in6_addr mcaddr; - struct in6_addr *target; + struct __rt6_probe_work *work; - if (neigh) { + work = kmalloc(sizeof(*work), GFP_ATOMIC); + + if (neigh && work) neigh->updated = jiffies; + + if (neigh) write_unlock(&neigh->lock); - } - target = (struct in6_addr *)&rt->rt6i_gateway; - addrconf_addr_solict_mult(target, &mcaddr); - ndisc_send_ns(rt->dst.dev, NULL, target, &mcaddr, NULL); + if (work) { + INIT_WORK(&work->work, rt6_probe_deferred); + work->target = rt->rt6i_gateway; + dev_hold(rt->dst.dev); + work->dev = rt->dst.dev; + schedule_work(&work->work); + } } else { out: write_unlock(&neigh->lock); @@ -851,7 +875,6 @@ static struct rt6_info *rt6_alloc_cow(struct rt6_info *ort, if (ort->rt6i_dst.plen != 128 && ipv6_addr_equal(&ort->rt6i_dst.addr, daddr)) rt->rt6i_flags |= RTF_ANYCAST; - rt->rt6i_gateway = *daddr; } rt->rt6i_flags |= RTF_CACHE; @@ -1338,6 +1361,7 @@ struct dst_entry *icmp6_dst_alloc(struct net_device *dev, rt->dst.flags |= DST_HOST; rt->dst.output = ip6_output; atomic_set(&rt->dst.__refcnt, 1); + rt->rt6i_gateway = fl6->daddr; rt->rt6i_dst.addr = fl6->daddr; rt->rt6i_dst.plen = 128; rt->rt6i_idev = idev; @@ -1873,7 +1897,10 @@ static struct rt6_info *ip6_rt_copy(struct rt6_info *ort, in6_dev_hold(rt->rt6i_idev); rt->dst.lastuse = jiffies; - rt->rt6i_gateway = ort->rt6i_gateway; + if (ort->rt6i_flags & RTF_GATEWAY) + rt->rt6i_gateway = ort->rt6i_gateway; + else + rt->rt6i_gateway = *dest; rt->rt6i_flags = ort->rt6i_flags; if ((ort->rt6i_flags & (RTF_DEFAULT | RTF_ADDRCONF)) == (RTF_DEFAULT | RTF_ADDRCONF)) @@ -2160,6 +2187,7 @@ struct rt6_info *addrconf_dst_alloc(struct inet6_dev *idev, else rt->rt6i_flags |= RTF_LOCAL; + rt->rt6i_gateway = *addr; rt->rt6i_dst.addr = *addr; rt->rt6i_dst.plen = 128; rt->rt6i_table = fib6_get_table(net, RT6_TABLE_LOCAL); diff --git a/net/ipv6/sit.c b/net/ipv6/sit.c index 7ee5cb9..1926945 100644 --- a/net/ipv6/sit.c +++ b/net/ipv6/sit.c @@ -566,6 +566,70 @@ static inline bool is_spoofed_6rd(struct ip_tunnel *tunnel, const __be32 v4addr, return false; } +/* Checks if an address matches an address on the tunnel interface. + * Used to detect the NAT of proto 41 packets and let them pass spoofing test. + * Long story: + * This function is called after we considered the packet as spoofed + * in is_spoofed_6rd. + * We may have a router that is doing NAT for proto 41 packets + * for an internal station. Destination a.a.a.a/PREFIX:bbbb:bbbb + * will be translated to n.n.n.n/PREFIX:bbbb:bbbb. And is_spoofed_6rd + * function will return true, dropping the packet. + * But, we can still check if is spoofed against the IP + * addresses associated with the interface. + */ +static bool only_dnatted(const struct ip_tunnel *tunnel, + const struct in6_addr *v6dst) +{ + int prefix_len; + +#ifdef CONFIG_IPV6_SIT_6RD + prefix_len = tunnel->ip6rd.prefixlen + 32 + - tunnel->ip6rd.relay_prefixlen; +#else + prefix_len = 48; +#endif + return ipv6_chk_custom_prefix(v6dst, prefix_len, tunnel->dev); +} + +/* Returns true if a packet is spoofed */ +static bool packet_is_spoofed(struct sk_buff *skb, + const struct iphdr *iph, + struct ip_tunnel *tunnel) +{ + const struct ipv6hdr *ipv6h; + + if (tunnel->dev->priv_flags & IFF_ISATAP) { + if (!isatap_chksrc(skb, iph, tunnel)) + return true; + + return false; + } + + if (tunnel->dev->flags & IFF_POINTOPOINT) + return false; + + ipv6h = ipv6_hdr(skb); + + if (unlikely(is_spoofed_6rd(tunnel, iph->saddr, &ipv6h->saddr))) { + net_warn_ratelimited("Src spoofed %pI4/%pI6c -> %pI4/%pI6c\n", + &iph->saddr, &ipv6h->saddr, + &iph->daddr, &ipv6h->daddr); + return true; + } + + if (likely(!is_spoofed_6rd(tunnel, iph->daddr, &ipv6h->daddr))) + return false; + + if (only_dnatted(tunnel, &ipv6h->daddr)) + return false; + + net_warn_ratelimited("Dst spoofed %pI4/%pI6c -> %pI4/%pI6c\n", + &iph->saddr, &ipv6h->saddr, + &iph->daddr, &ipv6h->daddr); + return true; +} + static int ipip6_rcv(struct sk_buff *skb) { const struct iphdr *iph = ip_hdr(skb); @@ -586,19 +650,9 @@ static int ipip6_rcv(struct sk_buff *skb) IPCB(skb)->flags = 0; skb->protocol = htons(ETH_P_IPV6); - if (tunnel->dev->priv_flags & IFF_ISATAP) { - if (!isatap_chksrc(skb, iph, tunnel)) { - tunnel->dev->stats.rx_errors++; - goto out; - } - } else if (!(tunnel->dev->flags&IFF_POINTOPOINT)) { - if (is_spoofed_6rd(tunnel, iph->saddr, - &ipv6_hdr(skb)->saddr) || - is_spoofed_6rd(tunnel, iph->daddr, - &ipv6_hdr(skb)->daddr)) { - tunnel->dev->stats.rx_errors++; - goto out; - } + if (packet_is_spoofed(skb, iph, tunnel)) { + tunnel->dev->stats.rx_errors++; + goto out; } __skb_tunnel_rx(skb, tunnel->dev, tunnel->net); @@ -748,7 +802,7 @@ static netdev_tx_t ipip6_tunnel_xmit(struct sk_buff *skb, neigh = dst_neigh_lookup(skb_dst(skb), &iph6->daddr); if (neigh == NULL) { - net_dbg_ratelimited("sit: nexthop == NULL\n"); + net_dbg_ratelimited("nexthop == NULL\n"); goto tx_error; } @@ -777,7 +831,7 @@ static netdev_tx_t ipip6_tunnel_xmit(struct sk_buff *skb, neigh = dst_neigh_lookup(skb_dst(skb), &iph6->daddr); if (neigh == NULL) { - net_dbg_ratelimited("sit: nexthop == NULL\n"); + net_dbg_ratelimited("nexthop == NULL\n"); goto tx_error; } @@ -1612,6 +1666,7 @@ static int __net_init sit_init_net(struct net *net) goto err_alloc_dev; } dev_net_set(sitn->fb_tunnel_dev, net); + sitn->fb_tunnel_dev->rtnl_link_ops = &sit_link_ops; /* FB netdevice is special: we have one, and only one per netns. * Allowing to move it to another netns is clearly unsafe. */ @@ -1646,7 +1701,6 @@ static void __net_exit sit_exit_net(struct net *net) rtnl_lock(); sit_destroy_tunnels(sitn, &list); - unregister_netdevice_queue(sitn->fb_tunnel_dev, &list); unregister_netdevice_many(&list); rtnl_unlock(); } diff --git a/net/ipv6/udp.c b/net/ipv6/udp.c index f405815..1878609 100644 --- a/net/ipv6/udp.c +++ b/net/ipv6/udp.c @@ -525,8 +525,10 @@ void __udp6_lib_err(struct sk_buff *skb, struct inet6_skb_parm *opt, if (type == ICMPV6_PKT_TOOBIG) ip6_sk_update_pmtu(skb, sk, info); - if (type == NDISC_REDIRECT) + if (type == NDISC_REDIRECT) { ip6_sk_redirect(skb, sk); + goto out; + } np = inet6_sk(sk); @@ -1223,9 +1225,6 @@ do_udp_sendmsg: if (tclass < 0) tclass = np->tclass; - if (dontfrag < 0) - dontfrag = np->dontfrag; - if (msg->msg_flags&MSG_CONFIRM) goto do_confirm; back_from_confirm: @@ -1244,6 +1243,8 @@ back_from_confirm: up->pending = AF_INET6; do_append_data: + if (dontfrag < 0) + dontfrag = np->dontfrag; up->len += ulen; getfrag = is_udplite ? udplite_getfrag : ip_generic_getfrag; err = ip6_append_data(sk, getfrag, msg->msg_iov, ulen, diff --git a/net/ipv6/xfrm6_policy.c b/net/ipv6/xfrm6_policy.c index 23ed03d..08ed277 100644 --- a/net/ipv6/xfrm6_policy.c +++ b/net/ipv6/xfrm6_policy.c @@ -138,6 +138,7 @@ _decode_session6(struct sk_buff *skb, struct flowi *fl, int reverse) memset(fl6, 0, sizeof(struct flowi6)); fl6->flowi6_mark = skb->mark; + fl6->flowi6_oif = skb_dst(skb)->dev->ifindex; fl6->daddr = reverse ? hdr->saddr : hdr->daddr; fl6->saddr = reverse ? hdr->daddr : hdr->saddr; diff --git a/net/key/af_key.c b/net/key/af_key.c index 9d58537..911ef03 100644 --- a/net/key/af_key.c +++ b/net/key/af_key.c @@ -1098,7 +1098,8 @@ static struct xfrm_state * pfkey_msg2xfrm_state(struct net *net, x->id.proto = proto; x->id.spi = sa->sadb_sa_spi; - x->props.replay_window = sa->sadb_sa_replay; + x->props.replay_window = min_t(unsigned int, sa->sadb_sa_replay, + (sizeof(x->replay.bitmap) * 8)); if (sa->sadb_sa_flags & SADB_SAFLAGS_NOECN) x->props.flags |= XFRM_STATE_NOECN; if (sa->sadb_sa_flags & SADB_SAFLAGS_DECAP_DSCP) diff --git a/net/l2tp/l2tp_core.c b/net/l2tp/l2tp_core.c index feae495..b076e83 100644 --- a/net/l2tp/l2tp_core.c +++ b/net/l2tp/l2tp_core.c @@ -115,6 +115,11 @@ struct l2tp_net { static void l2tp_session_set_header_len(struct l2tp_session *session, int version); static void l2tp_tunnel_free(struct l2tp_tunnel *tunnel); +static inline struct l2tp_tunnel *l2tp_tunnel(struct sock *sk) +{ + return sk->sk_user_data; +} + static inline struct l2tp_net *l2tp_pernet(struct net *net) { BUG_ON(!net); @@ -504,7 +509,7 @@ static inline int l2tp_verify_udp_checksum(struct sock *sk, return 0; #if IS_ENABLED(CONFIG_IPV6) - if (sk->sk_family == PF_INET6) { + if (sk->sk_family == PF_INET6 && !l2tp_tunnel(sk)->v4mapped) { if (!uh->check) { LIMIT_NETDEBUG(KERN_INFO "L2TP: IPv6: checksum is 0\n"); return 1; @@ -1128,7 +1133,7 @@ static int l2tp_xmit_core(struct l2tp_session *session, struct sk_buff *skb, /* Queue the packet to IP for output */ skb->local_df = 1; #if IS_ENABLED(CONFIG_IPV6) - if (skb->sk->sk_family == PF_INET6) + if (skb->sk->sk_family == PF_INET6 && !tunnel->v4mapped) error = inet6_csk_xmit(skb, NULL); else #endif @@ -1255,7 +1260,7 @@ int l2tp_xmit_skb(struct l2tp_session *session, struct sk_buff *skb, int hdr_len /* Calculate UDP checksum if configured to do so */ #if IS_ENABLED(CONFIG_IPV6) - if (sk->sk_family == PF_INET6) + if (sk->sk_family == PF_INET6 && !tunnel->v4mapped) l2tp_xmit_ipv6_csum(sk, skb, udp_len); else #endif @@ -1304,10 +1309,9 @@ EXPORT_SYMBOL_GPL(l2tp_xmit_skb); */ static void l2tp_tunnel_destruct(struct sock *sk) { - struct l2tp_tunnel *tunnel; + struct l2tp_tunnel *tunnel = l2tp_tunnel(sk); struct l2tp_net *pn; - tunnel = sk->sk_user_data; if (tunnel == NULL) goto end; @@ -1675,7 +1679,7 @@ int l2tp_tunnel_create(struct net *net, int fd, int version, u32 tunnel_id, u32 } /* Check if this socket has already been prepped */ - tunnel = (struct l2tp_tunnel *)sk->sk_user_data; + tunnel = l2tp_tunnel(sk); if (tunnel != NULL) { /* This socket has already been prepped */ err = -EBUSY; @@ -1704,6 +1708,24 @@ int l2tp_tunnel_create(struct net *net, int fd, int version, u32 tunnel_id, u32 if (cfg != NULL) tunnel->debug = cfg->debug; +#if IS_ENABLED(CONFIG_IPV6) + if (sk->sk_family == PF_INET6) { + struct ipv6_pinfo *np = inet6_sk(sk); + + if (ipv6_addr_v4mapped(&np->saddr) && + ipv6_addr_v4mapped(&np->daddr)) { + struct inet_sock *inet = inet_sk(sk); + + tunnel->v4mapped = true; + inet->inet_saddr = np->saddr.s6_addr32[3]; + inet->inet_rcv_saddr = np->rcv_saddr.s6_addr32[3]; + inet->inet_daddr = np->daddr.s6_addr32[3]; + } else { + tunnel->v4mapped = false; + } + } +#endif + /* Mark socket as an encapsulation socket. See net/ipv4/udp.c */ tunnel->encap = encap; if (encap == L2TP_ENCAPTYPE_UDP) { @@ -1712,7 +1734,7 @@ int l2tp_tunnel_create(struct net *net, int fd, int version, u32 tunnel_id, u32 udp_sk(sk)->encap_rcv = l2tp_udp_encap_recv; udp_sk(sk)->encap_destroy = l2tp_udp_encap_destroy; #if IS_ENABLED(CONFIG_IPV6) - if (sk->sk_family == PF_INET6) + if (sk->sk_family == PF_INET6 && !tunnel->v4mapped) udpv6_encap_enable(); else #endif diff --git a/net/l2tp/l2tp_core.h b/net/l2tp/l2tp_core.h index 66a559b..6f251cb 100644 --- a/net/l2tp/l2tp_core.h +++ b/net/l2tp/l2tp_core.h @@ -194,6 +194,9 @@ struct l2tp_tunnel { struct sock *sock; /* Parent socket */ int fd; /* Parent fd, if tunnel socket * was created by userspace */ +#if IS_ENABLED(CONFIG_IPV6) + bool v4mapped; +#endif struct work_struct del_work; diff --git a/net/l2tp/l2tp_ppp.c b/net/l2tp/l2tp_ppp.c index 5ebee2d..8c46b27 100644 --- a/net/l2tp/l2tp_ppp.c +++ b/net/l2tp/l2tp_ppp.c @@ -353,7 +353,9 @@ static int pppol2tp_sendmsg(struct kiocb *iocb, struct socket *sock, struct msgh goto error_put_sess_tun; } + local_bh_disable(); l2tp_xmit_skb(session, skb, session->hdr_len); + local_bh_enable(); sock_put(ps->tunnel_sock); sock_put(sk); @@ -422,7 +424,9 @@ static int pppol2tp_xmit(struct ppp_channel *chan, struct sk_buff *skb) skb->data[0] = ppph[0]; skb->data[1] = ppph[1]; + local_bh_disable(); l2tp_xmit_skb(session, skb, session->hdr_len); + local_bh_enable(); sock_put(sk_tun); sock_put(sk); diff --git a/net/lapb/lapb_timer.c b/net/lapb/lapb_timer.c index 54563ad..355cc3b 100644 --- a/net/lapb/lapb_timer.c +++ b/net/lapb/lapb_timer.c @@ -154,6 +154,7 @@ static void lapb_t1timer_expiry(unsigned long param) } else { lapb->n2count++; lapb_requeue_frames(lapb); + lapb_kick(lapb); } break; diff --git a/net/mac80211/cfg.c b/net/mac80211/cfg.c index 2e7855a..629dee7 100644 --- a/net/mac80211/cfg.c +++ b/net/mac80211/cfg.c @@ -3518,7 +3518,7 @@ static int ieee80211_probe_client(struct wiphy *wiphy, struct net_device *dev, return -EINVAL; } band = chanctx_conf->def.chan->band; - sta = sta_info_get(sdata, peer); + sta = sta_info_get_bss(sdata, peer); if (sta) { qos = test_sta_flag(sta, WLAN_STA_WME); } else { diff --git a/net/mac80211/ieee80211_i.h b/net/mac80211/ieee80211_i.h index b618651..611abfc 100644 --- a/net/mac80211/ieee80211_i.h +++ b/net/mac80211/ieee80211_i.h @@ -893,6 +893,8 @@ struct tpt_led_trigger { * that the scan completed. * @SCAN_ABORTED: Set for our scan work function when the driver reported * a scan complete for an aborted scan. + * @SCAN_HW_CANCELLED: Set for our scan work function when the scan is being + * cancelled. */ enum { SCAN_SW_SCANNING, @@ -900,6 +902,7 @@ enum { SCAN_ONCHANNEL_SCANNING, SCAN_COMPLETED, SCAN_ABORTED, + SCAN_HW_CANCELLED, }; /** diff --git a/net/mac80211/offchannel.c b/net/mac80211/offchannel.c index acd1f71..0c2a294 100644 --- a/net/mac80211/offchannel.c +++ b/net/mac80211/offchannel.c @@ -394,6 +394,8 @@ void ieee80211_sw_roc_work(struct work_struct *work) if (started) ieee80211_start_next_roc(local); + else if (list_empty(&local->roc_list)) + ieee80211_run_deferred_scan(local); } out_unlock: diff --git a/net/mac80211/rx.c b/net/mac80211/rx.c index 54395d7..674eac1 100644 --- a/net/mac80211/rx.c +++ b/net/mac80211/rx.c @@ -3056,6 +3056,9 @@ static int prepare_for_handlers(struct ieee80211_rx_data *rx, case NL80211_IFTYPE_ADHOC: if (!bssid) return 0; + if (ether_addr_equal(sdata->vif.addr, hdr->addr2) || + ether_addr_equal(sdata->u.ibss.bssid, hdr->addr2)) + return 0; if (ieee80211_is_beacon(hdr->frame_control)) { return 1; } else if (!ieee80211_bssid_match(bssid, sdata->u.ibss.bssid)) { diff --git a/net/mac80211/scan.c b/net/mac80211/scan.c index 08afe74..d2d17a4 100644 --- a/net/mac80211/scan.c +++ b/net/mac80211/scan.c @@ -238,6 +238,9 @@ static bool ieee80211_prep_hw_scan(struct ieee80211_local *local) enum ieee80211_band band; int i, ielen, n_chans; + if (test_bit(SCAN_HW_CANCELLED, &local->scanning)) + return false; + do { if (local->hw_scan_band == IEEE80211_NUM_BANDS) return false; @@ -940,7 +943,23 @@ void ieee80211_scan_cancel(struct ieee80211_local *local) if (!local->scan_req) goto out; + /* + * We have a scan running and the driver already reported completion, + * but the worker hasn't run yet or is stuck on the mutex - mark it as + * cancelled. + */ + if (test_bit(SCAN_HW_SCANNING, &local->scanning) && + test_bit(SCAN_COMPLETED, &local->scanning)) { + set_bit(SCAN_HW_CANCELLED, &local->scanning); + goto out; + } + if (test_bit(SCAN_HW_SCANNING, &local->scanning)) { + /* + * Make sure that __ieee80211_scan_completed doesn't trigger a + * scan on another band. + */ + set_bit(SCAN_HW_CANCELLED, &local->scanning); if (local->ops->cancel_hw_scan) drv_cancel_hw_scan(local, rcu_dereference_protected(local->scan_sdata, diff --git a/net/mac80211/status.c b/net/mac80211/status.c index 368837f..78dc2e9 100644 --- a/net/mac80211/status.c +++ b/net/mac80211/status.c @@ -180,6 +180,9 @@ static void ieee80211_frame_acked(struct sta_info *sta, struct sk_buff *skb) struct ieee80211_local *local = sta->local; struct ieee80211_sub_if_data *sdata = sta->sdata; + if (local->hw.flags & IEEE80211_HW_REPORTS_TX_ACK_STATUS) + sta->last_rx = jiffies; + if (ieee80211_is_data_qos(mgmt->frame_control)) { struct ieee80211_hdr *hdr = (void *) skb->data; u8 *qc = ieee80211_get_qos_ctl(hdr); diff --git a/net/mac80211/tx.c b/net/mac80211/tx.c index 3456c04..70b5a05 100644 --- a/net/mac80211/tx.c +++ b/net/mac80211/tx.c @@ -1120,7 +1120,8 @@ ieee80211_tx_prepare(struct ieee80211_sub_if_data *sdata, tx->sta = rcu_dereference(sdata->u.vlan.sta); if (!tx->sta && sdata->dev->ieee80211_ptr->use_4addr) return TX_DROP; - } else if (info->flags & IEEE80211_TX_CTL_INJECTED || + } else if (info->flags & (IEEE80211_TX_CTL_INJECTED | + IEEE80211_TX_INTFL_NL80211_FRAME_TX) || tx->sdata->control_port_protocol == tx->skb->protocol) { tx->sta = sta_info_get_bss(sdata, hdr->addr1); } diff --git a/net/mac80211/util.c b/net/mac80211/util.c index e1b34a1..69e4ef5 100644 --- a/net/mac80211/util.c +++ b/net/mac80211/util.c @@ -2103,7 +2103,7 @@ int ieee80211_add_ext_srates_ie(struct ieee80211_sub_if_data *sdata, { struct ieee80211_local *local = sdata->local; struct ieee80211_supported_band *sband; - int rate, skip, shift; + int rate, shift; u8 i, exrates, *pos; u32 basic_rates = sdata->vif.bss_conf.basic_rates; u32 rate_flags; @@ -2131,14 +2131,11 @@ int ieee80211_add_ext_srates_ie(struct ieee80211_sub_if_data *sdata, pos = skb_put(skb, exrates + 2); *pos++ = WLAN_EID_EXT_SUPP_RATES; *pos++ = exrates; - skip = 0; for (i = 8; i < sband->n_bitrates; i++) { u8 basic = 0; if ((rate_flags & sband->bitrates[i].flags) != rate_flags) continue; - if (skip++ < 8) - continue; if (need_basic && basic_rates & BIT(i)) basic = 0x80; rate = DIV_ROUND_UP(sband->bitrates[i].bitrate, @@ -2241,6 +2238,10 @@ u64 ieee80211_calculate_rx_timestamp(struct ieee80211_local *local, } rate = cfg80211_calculate_bitrate(&ri); + if (WARN_ONCE(!rate, + "Invalid bitrate: flags=0x%x, idx=%d, vht_nss=%d\n", + status->flag, status->rate_idx, status->vht_nss)) + return 0; /* rewind from end of MPDU */ if (status->flag & RX_FLAG_MACTIME_END) diff --git a/net/netfilter/ipvs/ip_vs_core.c b/net/netfilter/ipvs/ip_vs_core.c index 4f69e83..74fd00c 100644 --- a/net/netfilter/ipvs/ip_vs_core.c +++ b/net/netfilter/ipvs/ip_vs_core.c @@ -116,6 +116,7 @@ ip_vs_in_stats(struct ip_vs_conn *cp, struct sk_buff *skb) if (dest && (dest->flags & IP_VS_DEST_F_AVAILABLE)) { struct ip_vs_cpu_stats *s; + struct ip_vs_service *svc; s = this_cpu_ptr(dest->stats.cpustats); s->ustats.inpkts++; @@ -123,11 +124,14 @@ ip_vs_in_stats(struct ip_vs_conn *cp, struct sk_buff *skb) s->ustats.inbytes += skb->len; u64_stats_update_end(&s->syncp); - s = this_cpu_ptr(dest->svc->stats.cpustats); + rcu_read_lock(); + svc = rcu_dereference(dest->svc); + s = this_cpu_ptr(svc->stats.cpustats); s->ustats.inpkts++; u64_stats_update_begin(&s->syncp); s->ustats.inbytes += skb->len; u64_stats_update_end(&s->syncp); + rcu_read_unlock(); s = this_cpu_ptr(ipvs->tot_stats.cpustats); s->ustats.inpkts++; @@ -146,6 +150,7 @@ ip_vs_out_stats(struct ip_vs_conn *cp, struct sk_buff *skb) if (dest && (dest->flags & IP_VS_DEST_F_AVAILABLE)) { struct ip_vs_cpu_stats *s; + struct ip_vs_service *svc; s = this_cpu_ptr(dest->stats.cpustats); s->ustats.outpkts++; @@ -153,11 +158,14 @@ ip_vs_out_stats(struct ip_vs_conn *cp, struct sk_buff *skb) s->ustats.outbytes += skb->len; u64_stats_update_end(&s->syncp); - s = this_cpu_ptr(dest->svc->stats.cpustats); + rcu_read_lock(); + svc = rcu_dereference(dest->svc); + s = this_cpu_ptr(svc->stats.cpustats); s->ustats.outpkts++; u64_stats_update_begin(&s->syncp); s->ustats.outbytes += skb->len; u64_stats_update_end(&s->syncp); + rcu_read_unlock(); s = this_cpu_ptr(ipvs->tot_stats.cpustats); s->ustats.outpkts++; diff --git a/net/netfilter/ipvs/ip_vs_ctl.c b/net/netfilter/ipvs/ip_vs_ctl.c index c8148e4..a3df9bd 100644 --- a/net/netfilter/ipvs/ip_vs_ctl.c +++ b/net/netfilter/ipvs/ip_vs_ctl.c @@ -460,7 +460,7 @@ static inline void __ip_vs_bind_svc(struct ip_vs_dest *dest, struct ip_vs_service *svc) { atomic_inc(&svc->refcnt); - dest->svc = svc; + rcu_assign_pointer(dest->svc, svc); } static void ip_vs_service_free(struct ip_vs_service *svc) @@ -470,18 +470,25 @@ static void ip_vs_service_free(struct ip_vs_service *svc) kfree(svc); } -static void -__ip_vs_unbind_svc(struct ip_vs_dest *dest) +static void ip_vs_service_rcu_free(struct rcu_head *head) { - struct ip_vs_service *svc = dest->svc; + struct ip_vs_service *svc; + + svc = container_of(head, struct ip_vs_service, rcu_head); + ip_vs_service_free(svc); +} - dest->svc = NULL; +static void __ip_vs_svc_put(struct ip_vs_service *svc, bool do_delay) +{ if (atomic_dec_and_test(&svc->refcnt)) { IP_VS_DBG_BUF(3, "Removing service %u/%s:%u\n", svc->fwmark, IP_VS_DBG_ADDR(svc->af, &svc->addr), ntohs(svc->port)); - ip_vs_service_free(svc); + if (do_delay) + call_rcu(&svc->rcu_head, ip_vs_service_rcu_free); + else + ip_vs_service_free(svc); } } @@ -667,11 +674,6 @@ ip_vs_trash_get_dest(struct ip_vs_service *svc, const union nf_inet_addr *daddr, IP_VS_DBG_ADDR(svc->af, &dest->addr), ntohs(dest->port), atomic_read(&dest->refcnt)); - /* We can not reuse dest while in grace period - * because conns still can use dest->svc - */ - if (test_bit(IP_VS_DEST_STATE_REMOVING, &dest->state)) - continue; if (dest->af == svc->af && ip_vs_addr_equal(svc->af, &dest->addr, daddr) && dest->port == dport && @@ -697,8 +699,10 @@ out: static void ip_vs_dest_free(struct ip_vs_dest *dest) { + struct ip_vs_service *svc = rcu_dereference_protected(dest->svc, 1); + __ip_vs_dst_cache_reset(dest); - __ip_vs_unbind_svc(dest); + __ip_vs_svc_put(svc, false); free_percpu(dest->stats.cpustats); kfree(dest); } @@ -771,6 +775,7 @@ __ip_vs_update_dest(struct ip_vs_service *svc, struct ip_vs_dest *dest, struct ip_vs_dest_user_kern *udest, int add) { struct netns_ipvs *ipvs = net_ipvs(svc->net); + struct ip_vs_service *old_svc; struct ip_vs_scheduler *sched; int conn_flags; @@ -792,13 +797,14 @@ __ip_vs_update_dest(struct ip_vs_service *svc, struct ip_vs_dest *dest, atomic_set(&dest->conn_flags, conn_flags); /* bind the service */ - if (!dest->svc) { + old_svc = rcu_dereference_protected(dest->svc, 1); + if (!old_svc) { __ip_vs_bind_svc(dest, svc); } else { - if (dest->svc != svc) { - __ip_vs_unbind_svc(dest); + if (old_svc != svc) { ip_vs_zero_stats(&dest->stats); __ip_vs_bind_svc(dest, svc); + __ip_vs_svc_put(old_svc, true); } } @@ -998,16 +1004,6 @@ ip_vs_edit_dest(struct ip_vs_service *svc, struct ip_vs_dest_user_kern *udest) return 0; } -static void ip_vs_dest_wait_readers(struct rcu_head *head) -{ - struct ip_vs_dest *dest = container_of(head, struct ip_vs_dest, - rcu_head); - - /* End of grace period after unlinking */ - clear_bit(IP_VS_DEST_STATE_REMOVING, &dest->state); -} - - /* * Delete a destination (must be already unlinked from the service) */ @@ -1023,20 +1019,16 @@ static void __ip_vs_del_dest(struct net *net, struct ip_vs_dest *dest, */ ip_vs_rs_unhash(dest); - if (!cleanup) { - set_bit(IP_VS_DEST_STATE_REMOVING, &dest->state); - call_rcu(&dest->rcu_head, ip_vs_dest_wait_readers); - } - spin_lock_bh(&ipvs->dest_trash_lock); IP_VS_DBG_BUF(3, "Moving dest %s:%u into trash, dest->refcnt=%d\n", IP_VS_DBG_ADDR(dest->af, &dest->addr), ntohs(dest->port), atomic_read(&dest->refcnt)); if (list_empty(&ipvs->dest_trash) && !cleanup) mod_timer(&ipvs->dest_trash_timer, - jiffies + IP_VS_DEST_TRASH_PERIOD); + jiffies + (IP_VS_DEST_TRASH_PERIOD >> 1)); /* dest lives in trash without reference */ list_add(&dest->t_list, &ipvs->dest_trash); + dest->idle_start = 0; spin_unlock_bh(&ipvs->dest_trash_lock); ip_vs_dest_put(dest); } @@ -1108,24 +1100,30 @@ static void ip_vs_dest_trash_expire(unsigned long data) struct net *net = (struct net *) data; struct netns_ipvs *ipvs = net_ipvs(net); struct ip_vs_dest *dest, *next; + unsigned long now = jiffies; spin_lock(&ipvs->dest_trash_lock); list_for_each_entry_safe(dest, next, &ipvs->dest_trash, t_list) { - /* Skip if dest is in grace period */ - if (test_bit(IP_VS_DEST_STATE_REMOVING, &dest->state)) - continue; if (atomic_read(&dest->refcnt) > 0) continue; + if (dest->idle_start) { + if (time_before(now, dest->idle_start + + IP_VS_DEST_TRASH_PERIOD)) + continue; + } else { + dest->idle_start = max(1UL, now); + continue; + } IP_VS_DBG_BUF(3, "Removing destination %u/%s:%u from trash\n", dest->vfwmark, - IP_VS_DBG_ADDR(dest->svc->af, &dest->addr), + IP_VS_DBG_ADDR(dest->af, &dest->addr), ntohs(dest->port)); list_del(&dest->t_list); ip_vs_dest_free(dest); } if (!list_empty(&ipvs->dest_trash)) mod_timer(&ipvs->dest_trash_timer, - jiffies + IP_VS_DEST_TRASH_PERIOD); + jiffies + (IP_VS_DEST_TRASH_PERIOD >> 1)); spin_unlock(&ipvs->dest_trash_lock); } @@ -1320,14 +1318,6 @@ out: return ret; } -static void ip_vs_service_rcu_free(struct rcu_head *head) -{ - struct ip_vs_service *svc; - - svc = container_of(head, struct ip_vs_service, rcu_head); - ip_vs_service_free(svc); -} - /* * Delete a service from the service list * - The service must be unlinked, unlocked and not referenced! @@ -1376,13 +1366,7 @@ static void __ip_vs_del_service(struct ip_vs_service *svc, bool cleanup) /* * Free the service if nobody refers to it */ - if (atomic_dec_and_test(&svc->refcnt)) { - IP_VS_DBG_BUF(3, "Removing service %u/%s:%u\n", - svc->fwmark, - IP_VS_DBG_ADDR(svc->af, &svc->addr), - ntohs(svc->port)); - call_rcu(&svc->rcu_head, ip_vs_service_rcu_free); - } + __ip_vs_svc_put(svc, true); /* decrease the module use count */ ip_vs_use_count_dec(); diff --git a/net/netfilter/ipvs/ip_vs_est.c b/net/netfilter/ipvs/ip_vs_est.c index 6bee6d0..1425e9a 100644 --- a/net/netfilter/ipvs/ip_vs_est.c +++ b/net/netfilter/ipvs/ip_vs_est.c @@ -59,12 +59,13 @@ static void ip_vs_read_cpu_stats(struct ip_vs_stats_user *sum, struct ip_vs_cpu_stats __percpu *stats) { int i; + bool add = false; for_each_possible_cpu(i) { struct ip_vs_cpu_stats *s = per_cpu_ptr(stats, i); unsigned int start; __u64 inbytes, outbytes; - if (i) { + if (add) { sum->conns += s->ustats.conns; sum->inpkts += s->ustats.inpkts; sum->outpkts += s->ustats.outpkts; @@ -76,6 +77,7 @@ static void ip_vs_read_cpu_stats(struct ip_vs_stats_user *sum, sum->inbytes += inbytes; sum->outbytes += outbytes; } else { + add = true; sum->conns = s->ustats.conns; sum->inpkts = s->ustats.inpkts; sum->outpkts = s->ustats.outpkts; diff --git a/net/netfilter/ipvs/ip_vs_lblc.c b/net/netfilter/ipvs/ip_vs_lblc.c index 1383b0e..eff13c9 100644 --- a/net/netfilter/ipvs/ip_vs_lblc.c +++ b/net/netfilter/ipvs/ip_vs_lblc.c @@ -93,7 +93,7 @@ struct ip_vs_lblc_entry { struct hlist_node list; int af; /* address family */ union nf_inet_addr addr; /* destination IP address */ - struct ip_vs_dest __rcu *dest; /* real server (cache) */ + struct ip_vs_dest *dest; /* real server (cache) */ unsigned long lastuse; /* last used time */ struct rcu_head rcu_head; }; @@ -130,20 +130,21 @@ static struct ctl_table vs_vars_table[] = { }; #endif -static inline void ip_vs_lblc_free(struct ip_vs_lblc_entry *en) +static void ip_vs_lblc_rcu_free(struct rcu_head *head) { - struct ip_vs_dest *dest; + struct ip_vs_lblc_entry *en = container_of(head, + struct ip_vs_lblc_entry, + rcu_head); - hlist_del_rcu(&en->list); - /* - * We don't kfree dest because it is referred either by its service - * or the trash dest list. - */ - dest = rcu_dereference_protected(en->dest, 1); - ip_vs_dest_put(dest); - kfree_rcu(en, rcu_head); + ip_vs_dest_put(en->dest); + kfree(en); } +static inline void ip_vs_lblc_del(struct ip_vs_lblc_entry *en) +{ + hlist_del_rcu(&en->list); + call_rcu(&en->rcu_head, ip_vs_lblc_rcu_free); +} /* * Returns hash value for IPVS LBLC entry @@ -203,30 +204,23 @@ ip_vs_lblc_new(struct ip_vs_lblc_table *tbl, const union nf_inet_addr *daddr, struct ip_vs_lblc_entry *en; en = ip_vs_lblc_get(dest->af, tbl, daddr); - if (!en) { - en = kmalloc(sizeof(*en), GFP_ATOMIC); - if (!en) - return NULL; - - en->af = dest->af; - ip_vs_addr_copy(dest->af, &en->addr, daddr); - en->lastuse = jiffies; + if (en) { + if (en->dest == dest) + return en; + ip_vs_lblc_del(en); + } + en = kmalloc(sizeof(*en), GFP_ATOMIC); + if (!en) + return NULL; - ip_vs_dest_hold(dest); - RCU_INIT_POINTER(en->dest, dest); + en->af = dest->af; + ip_vs_addr_copy(dest->af, &en->addr, daddr); + en->lastuse = jiffies; - ip_vs_lblc_hash(tbl, en); - } else { - struct ip_vs_dest *old_dest; + ip_vs_dest_hold(dest); + en->dest = dest; - old_dest = rcu_dereference_protected(en->dest, 1); - if (old_dest != dest) { - ip_vs_dest_put(old_dest); - ip_vs_dest_hold(dest); - /* No ordering constraints for refcnt */ - RCU_INIT_POINTER(en->dest, dest); - } - } + ip_vs_lblc_hash(tbl, en); return en; } @@ -246,7 +240,7 @@ static void ip_vs_lblc_flush(struct ip_vs_service *svc) tbl->dead = 1; for (i=0; i<IP_VS_LBLC_TAB_SIZE; i++) { hlist_for_each_entry_safe(en, next, &tbl->bucket[i], list) { - ip_vs_lblc_free(en); + ip_vs_lblc_del(en); atomic_dec(&tbl->entries); } } @@ -281,7 +275,7 @@ static inline void ip_vs_lblc_full_check(struct ip_vs_service *svc) sysctl_lblc_expiration(svc))) continue; - ip_vs_lblc_free(en); + ip_vs_lblc_del(en); atomic_dec(&tbl->entries); } spin_unlock(&svc->sched_lock); @@ -335,7 +329,7 @@ static void ip_vs_lblc_check_expire(unsigned long data) if (time_before(now, en->lastuse + ENTRY_TIMEOUT)) continue; - ip_vs_lblc_free(en); + ip_vs_lblc_del(en); atomic_dec(&tbl->entries); goal--; } @@ -443,8 +437,8 @@ __ip_vs_lblc_schedule(struct ip_vs_service *svc) continue; doh = ip_vs_dest_conn_overhead(dest); - if (loh * atomic_read(&dest->weight) > - doh * atomic_read(&least->weight)) { + if ((__s64)loh * atomic_read(&dest->weight) > + (__s64)doh * atomic_read(&least->weight)) { least = dest; loh = doh; } @@ -511,7 +505,7 @@ ip_vs_lblc_schedule(struct ip_vs_service *svc, const struct sk_buff *skb, * free up entries from the trash at any time. */ - dest = rcu_dereference(en->dest); + dest = en->dest; if ((dest->flags & IP_VS_DEST_F_AVAILABLE) && atomic_read(&dest->weight) > 0 && !is_overloaded(dest, svc)) goto out; @@ -631,7 +625,7 @@ static void __exit ip_vs_lblc_cleanup(void) { unregister_ip_vs_scheduler(&ip_vs_lblc_scheduler); unregister_pernet_subsys(&ip_vs_lblc_ops); - synchronize_rcu(); + rcu_barrier(); } diff --git a/net/netfilter/ipvs/ip_vs_lblcr.c b/net/netfilter/ipvs/ip_vs_lblcr.c index 5199448..0b85500 100644 --- a/net/netfilter/ipvs/ip_vs_lblcr.c +++ b/net/netfilter/ipvs/ip_vs_lblcr.c @@ -89,7 +89,7 @@ */ struct ip_vs_dest_set_elem { struct list_head list; /* list link */ - struct ip_vs_dest __rcu *dest; /* destination server */ + struct ip_vs_dest *dest; /* destination server */ struct rcu_head rcu_head; }; @@ -107,11 +107,7 @@ static void ip_vs_dest_set_insert(struct ip_vs_dest_set *set, if (check) { list_for_each_entry(e, &set->list, list) { - struct ip_vs_dest *d; - - d = rcu_dereference_protected(e->dest, 1); - if (d == dest) - /* already existed */ + if (e->dest == dest) return; } } @@ -121,7 +117,7 @@ static void ip_vs_dest_set_insert(struct ip_vs_dest_set *set, return; ip_vs_dest_hold(dest); - RCU_INIT_POINTER(e->dest, dest); + e->dest = dest; list_add_rcu(&e->list, &set->list); atomic_inc(&set->size); @@ -129,22 +125,27 @@ static void ip_vs_dest_set_insert(struct ip_vs_dest_set *set, set->lastmod = jiffies; } +static void ip_vs_lblcr_elem_rcu_free(struct rcu_head *head) +{ + struct ip_vs_dest_set_elem *e; + + e = container_of(head, struct ip_vs_dest_set_elem, rcu_head); + ip_vs_dest_put(e->dest); + kfree(e); +} + static void ip_vs_dest_set_erase(struct ip_vs_dest_set *set, struct ip_vs_dest *dest) { struct ip_vs_dest_set_elem *e; list_for_each_entry(e, &set->list, list) { - struct ip_vs_dest *d; - - d = rcu_dereference_protected(e->dest, 1); - if (d == dest) { + if (e->dest == dest) { /* HIT */ atomic_dec(&set->size); set->lastmod = jiffies; - ip_vs_dest_put(dest); list_del_rcu(&e->list); - kfree_rcu(e, rcu_head); + call_rcu(&e->rcu_head, ip_vs_lblcr_elem_rcu_free); break; } } @@ -155,16 +156,8 @@ static void ip_vs_dest_set_eraseall(struct ip_vs_dest_set *set) struct ip_vs_dest_set_elem *e, *ep; list_for_each_entry_safe(e, ep, &set->list, list) { - struct ip_vs_dest *d; - - d = rcu_dereference_protected(e->dest, 1); - /* - * We don't kfree dest because it is referred either - * by its service or by the trash dest list. - */ - ip_vs_dest_put(d); list_del_rcu(&e->list); - kfree_rcu(e, rcu_head); + call_rcu(&e->rcu_head, ip_vs_lblcr_elem_rcu_free); } } @@ -175,12 +168,9 @@ static inline struct ip_vs_dest *ip_vs_dest_set_min(struct ip_vs_dest_set *set) struct ip_vs_dest *dest, *least; int loh, doh; - if (set == NULL) - return NULL; - /* select the first destination server, whose weight > 0 */ list_for_each_entry_rcu(e, &set->list, list) { - least = rcu_dereference(e->dest); + least = e->dest; if (least->flags & IP_VS_DEST_F_OVERLOAD) continue; @@ -195,13 +185,13 @@ static inline struct ip_vs_dest *ip_vs_dest_set_min(struct ip_vs_dest_set *set) /* find the destination with the weighted least load */ nextstage: list_for_each_entry_continue_rcu(e, &set->list, list) { - dest = rcu_dereference(e->dest); + dest = e->dest; if (dest->flags & IP_VS_DEST_F_OVERLOAD) continue; doh = ip_vs_dest_conn_overhead(dest); - if ((loh * atomic_read(&dest->weight) > - doh * atomic_read(&least->weight)) + if (((__s64)loh * atomic_read(&dest->weight) > + (__s64)doh * atomic_read(&least->weight)) && (dest->flags & IP_VS_DEST_F_AVAILABLE)) { least = dest; loh = doh; @@ -232,7 +222,7 @@ static inline struct ip_vs_dest *ip_vs_dest_set_max(struct ip_vs_dest_set *set) /* select the first destination server, whose weight > 0 */ list_for_each_entry(e, &set->list, list) { - most = rcu_dereference_protected(e->dest, 1); + most = e->dest; if (atomic_read(&most->weight) > 0) { moh = ip_vs_dest_conn_overhead(most); goto nextstage; @@ -243,11 +233,11 @@ static inline struct ip_vs_dest *ip_vs_dest_set_max(struct ip_vs_dest_set *set) /* find the destination with the weighted most load */ nextstage: list_for_each_entry_continue(e, &set->list, list) { - dest = rcu_dereference_protected(e->dest, 1); + dest = e->dest; doh = ip_vs_dest_conn_overhead(dest); /* moh/mw < doh/dw ==> moh*dw < doh*mw, where mw,dw>0 */ - if ((moh * atomic_read(&dest->weight) < - doh * atomic_read(&most->weight)) + if (((__s64)moh * atomic_read(&dest->weight) < + (__s64)doh * atomic_read(&most->weight)) && (atomic_read(&dest->weight) > 0)) { most = dest; moh = doh; @@ -611,8 +601,8 @@ __ip_vs_lblcr_schedule(struct ip_vs_service *svc) continue; doh = ip_vs_dest_conn_overhead(dest); - if (loh * atomic_read(&dest->weight) > - doh * atomic_read(&least->weight)) { + if ((__s64)loh * atomic_read(&dest->weight) > + (__s64)doh * atomic_read(&least->weight)) { least = dest; loh = doh; } @@ -819,7 +809,7 @@ static void __exit ip_vs_lblcr_cleanup(void) { unregister_ip_vs_scheduler(&ip_vs_lblcr_scheduler); unregister_pernet_subsys(&ip_vs_lblcr_ops); - synchronize_rcu(); + rcu_barrier(); } diff --git a/net/netfilter/ipvs/ip_vs_nq.c b/net/netfilter/ipvs/ip_vs_nq.c index d8d9860..961a6de 100644 --- a/net/netfilter/ipvs/ip_vs_nq.c +++ b/net/netfilter/ipvs/ip_vs_nq.c @@ -40,7 +40,7 @@ #include <net/ip_vs.h> -static inline unsigned int +static inline int ip_vs_nq_dest_overhead(struct ip_vs_dest *dest) { /* @@ -59,7 +59,7 @@ ip_vs_nq_schedule(struct ip_vs_service *svc, const struct sk_buff *skb, struct ip_vs_iphdr *iph) { struct ip_vs_dest *dest, *least = NULL; - unsigned int loh = 0, doh; + int loh = 0, doh; IP_VS_DBG(6, "%s(): Scheduling...\n", __func__); @@ -92,8 +92,8 @@ ip_vs_nq_schedule(struct ip_vs_service *svc, const struct sk_buff *skb, } if (!least || - (loh * atomic_read(&dest->weight) > - doh * atomic_read(&least->weight))) { + ((__s64)loh * atomic_read(&dest->weight) > + (__s64)doh * atomic_read(&least->weight))) { least = dest; loh = doh; } diff --git a/net/netfilter/ipvs/ip_vs_sed.c b/net/netfilter/ipvs/ip_vs_sed.c index a5284cc..e446b9f 100644 --- a/net/netfilter/ipvs/ip_vs_sed.c +++ b/net/netfilter/ipvs/ip_vs_sed.c @@ -44,7 +44,7 @@ #include <net/ip_vs.h> -static inline unsigned int +static inline int ip_vs_sed_dest_overhead(struct ip_vs_dest *dest) { /* @@ -63,7 +63,7 @@ ip_vs_sed_schedule(struct ip_vs_service *svc, const struct sk_buff *skb, struct ip_vs_iphdr *iph) { struct ip_vs_dest *dest, *least; - unsigned int loh, doh; + int loh, doh; IP_VS_DBG(6, "%s(): Scheduling...\n", __func__); @@ -99,8 +99,8 @@ ip_vs_sed_schedule(struct ip_vs_service *svc, const struct sk_buff *skb, if (dest->flags & IP_VS_DEST_F_OVERLOAD) continue; doh = ip_vs_sed_dest_overhead(dest); - if (loh * atomic_read(&dest->weight) > - doh * atomic_read(&least->weight)) { + if ((__s64)loh * atomic_read(&dest->weight) > + (__s64)doh * atomic_read(&least->weight)) { least = dest; loh = doh; } diff --git a/net/netfilter/ipvs/ip_vs_wlc.c b/net/netfilter/ipvs/ip_vs_wlc.c index 6dc1fa1..b5b4650 100644 --- a/net/netfilter/ipvs/ip_vs_wlc.c +++ b/net/netfilter/ipvs/ip_vs_wlc.c @@ -35,7 +35,7 @@ ip_vs_wlc_schedule(struct ip_vs_service *svc, const struct sk_buff *skb, struct ip_vs_iphdr *iph) { struct ip_vs_dest *dest, *least; - unsigned int loh, doh; + int loh, doh; IP_VS_DBG(6, "ip_vs_wlc_schedule(): Scheduling...\n"); @@ -71,8 +71,8 @@ ip_vs_wlc_schedule(struct ip_vs_service *svc, const struct sk_buff *skb, if (dest->flags & IP_VS_DEST_F_OVERLOAD) continue; doh = ip_vs_dest_conn_overhead(dest); - if (loh * atomic_read(&dest->weight) > - doh * atomic_read(&least->weight)) { + if ((__s64)loh * atomic_read(&dest->weight) > + (__s64)doh * atomic_read(&least->weight)) { least = dest; loh = doh; } diff --git a/net/netfilter/nf_conntrack_h323_main.c b/net/netfilter/nf_conntrack_h323_main.c index bdebd03..70866d1 100644 --- a/net/netfilter/nf_conntrack_h323_main.c +++ b/net/netfilter/nf_conntrack_h323_main.c @@ -778,8 +778,8 @@ static int callforward_do_filter(const union nf_inet_addr *src, flowi6_to_flowi(&fl1), false)) { if (!afinfo->route(&init_net, (struct dst_entry **)&rt2, flowi6_to_flowi(&fl2), false)) { - if (!memcmp(&rt1->rt6i_gateway, &rt2->rt6i_gateway, - sizeof(rt1->rt6i_gateway)) && + if (ipv6_addr_equal(rt6_nexthop(rt1), + rt6_nexthop(rt2)) && rt1->dst.dev == rt2->dst.dev) ret = 1; dst_release(&rt2->dst); diff --git a/net/netfilter/nf_synproxy_core.c b/net/netfilter/nf_synproxy_core.c index 6fd967c..cdf4567 100644 --- a/net/netfilter/nf_synproxy_core.c +++ b/net/netfilter/nf_synproxy_core.c @@ -24,7 +24,7 @@ int synproxy_net_id; EXPORT_SYMBOL_GPL(synproxy_net_id); -void +bool synproxy_parse_options(const struct sk_buff *skb, unsigned int doff, const struct tcphdr *th, struct synproxy_options *opts) { @@ -32,7 +32,8 @@ synproxy_parse_options(const struct sk_buff *skb, unsigned int doff, u8 buf[40], *ptr; ptr = skb_header_pointer(skb, doff + sizeof(*th), length, buf); - BUG_ON(ptr == NULL); + if (ptr == NULL) + return false; opts->options = 0; while (length > 0) { @@ -41,16 +42,16 @@ synproxy_parse_options(const struct sk_buff *skb, unsigned int doff, switch (opcode) { case TCPOPT_EOL: - return; + return true; case TCPOPT_NOP: length--; continue; default: opsize = *ptr++; if (opsize < 2) - return; + return true; if (opsize > length) - return; + return true; switch (opcode) { case TCPOPT_MSS: @@ -84,6 +85,7 @@ synproxy_parse_options(const struct sk_buff *skb, unsigned int doff, length -= opsize; } } + return true; } EXPORT_SYMBOL_GPL(synproxy_parse_options); diff --git a/net/sched/sch_fq.c b/net/sched/sch_fq.c index 32ad015..a9dfdda 100644 --- a/net/sched/sch_fq.c +++ b/net/sched/sch_fq.c @@ -285,7 +285,7 @@ static struct fq_flow *fq_classify(struct sk_buff *skb, struct fq_sched_data *q) /* remove one skb from head of flow queue */ -static struct sk_buff *fq_dequeue_head(struct fq_flow *flow) +static struct sk_buff *fq_dequeue_head(struct Qdisc *sch, struct fq_flow *flow) { struct sk_buff *skb = flow->head; @@ -293,6 +293,8 @@ static struct sk_buff *fq_dequeue_head(struct fq_flow *flow) flow->head = skb->next; skb->next = NULL; flow->qlen--; + sch->qstats.backlog -= qdisc_pkt_len(skb); + sch->q.qlen--; } return skb; } @@ -418,8 +420,9 @@ static struct sk_buff *fq_dequeue(struct Qdisc *sch) struct fq_flow_head *head; struct sk_buff *skb; struct fq_flow *f; + u32 rate; - skb = fq_dequeue_head(&q->internal); + skb = fq_dequeue_head(sch, &q->internal); if (skb) goto out; fq_check_throttled(q, now); @@ -449,7 +452,7 @@ begin: goto begin; } - skb = fq_dequeue_head(f); + skb = fq_dequeue_head(sch, f); if (!skb) { head->first = f->next; /* force a pass through old_flows to prevent starvation */ @@ -466,43 +469,70 @@ begin: f->time_next_packet = now; f->credit -= qdisc_pkt_len(skb); - if (f->credit <= 0 && - q->rate_enable && - skb->sk && skb->sk->sk_state != TCP_TIME_WAIT) { - u32 rate = skb->sk->sk_pacing_rate ?: q->flow_default_rate; + if (f->credit > 0 || !q->rate_enable) + goto out; - rate = min(rate, q->flow_max_rate); - if (rate) { - u64 len = (u64)qdisc_pkt_len(skb) * NSEC_PER_SEC; + rate = q->flow_max_rate; + if (skb->sk && skb->sk->sk_state != TCP_TIME_WAIT) + rate = min(skb->sk->sk_pacing_rate, rate); - do_div(len, rate); - /* Since socket rate can change later, - * clamp the delay to 125 ms. - * TODO: maybe segment the too big skb, as in commit - * e43ac79a4bc ("sch_tbf: segment too big GSO packets") - */ - if (unlikely(len > 125 * NSEC_PER_MSEC)) { - len = 125 * NSEC_PER_MSEC; - q->stat_pkts_too_long++; - } + if (rate != ~0U) { + u32 plen = max(qdisc_pkt_len(skb), q->quantum); + u64 len = (u64)plen * NSEC_PER_SEC; - f->time_next_packet = now + len; + if (likely(rate)) + do_div(len, rate); + /* Since socket rate can change later, + * clamp the delay to 125 ms. + * TODO: maybe segment the too big skb, as in commit + * e43ac79a4bc ("sch_tbf: segment too big GSO packets") + */ + if (unlikely(len > 125 * NSEC_PER_MSEC)) { + len = 125 * NSEC_PER_MSEC; + q->stat_pkts_too_long++; } + + f->time_next_packet = now + len; } out: - sch->qstats.backlog -= qdisc_pkt_len(skb); qdisc_bstats_update(sch, skb); - sch->q.qlen--; qdisc_unthrottled(sch); return skb; } static void fq_reset(struct Qdisc *sch) { + struct fq_sched_data *q = qdisc_priv(sch); + struct rb_root *root; struct sk_buff *skb; + struct rb_node *p; + struct fq_flow *f; + unsigned int idx; - while ((skb = fq_dequeue(sch)) != NULL) + while ((skb = fq_dequeue_head(sch, &q->internal)) != NULL) kfree_skb(skb); + + if (!q->fq_root) + return; + + for (idx = 0; idx < (1U << q->fq_trees_log); idx++) { + root = &q->fq_root[idx]; + while ((p = rb_first(root)) != NULL) { + f = container_of(p, struct fq_flow, fq_node); + rb_erase(p, root); + + while ((skb = fq_dequeue_head(sch, f)) != NULL) + kfree_skb(skb); + + kmem_cache_free(fq_flow_cachep, f); + } + } + q->new_flows.first = NULL; + q->old_flows.first = NULL; + q->delayed = RB_ROOT; + q->flows = 0; + q->inactive_flows = 0; + q->throttled_flows = 0; } static void fq_rehash(struct fq_sched_data *q, @@ -622,7 +652,7 @@ static int fq_change(struct Qdisc *sch, struct nlattr *opt) q->quantum = nla_get_u32(tb[TCA_FQ_QUANTUM]); if (tb[TCA_FQ_INITIAL_QUANTUM]) - q->quantum = nla_get_u32(tb[TCA_FQ_INITIAL_QUANTUM]); + q->initial_quantum = nla_get_u32(tb[TCA_FQ_INITIAL_QUANTUM]); if (tb[TCA_FQ_FLOW_DEFAULT_RATE]) q->flow_default_rate = nla_get_u32(tb[TCA_FQ_FLOW_DEFAULT_RATE]); @@ -645,6 +675,8 @@ static int fq_change(struct Qdisc *sch, struct nlattr *opt) while (sch->q.qlen > sch->limit) { struct sk_buff *skb = fq_dequeue(sch); + if (!skb) + break; kfree_skb(skb); drop_count++; } @@ -657,21 +689,9 @@ static int fq_change(struct Qdisc *sch, struct nlattr *opt) static void fq_destroy(struct Qdisc *sch) { struct fq_sched_data *q = qdisc_priv(sch); - struct rb_root *root; - struct rb_node *p; - unsigned int idx; - if (q->fq_root) { - for (idx = 0; idx < (1U << q->fq_trees_log); idx++) { - root = &q->fq_root[idx]; - while ((p = rb_first(root)) != NULL) { - rb_erase(p, root); - kmem_cache_free(fq_flow_cachep, - container_of(p, struct fq_flow, fq_node)); - } - } - kfree(q->fq_root); - } + fq_reset(sch); + kfree(q->fq_root); qdisc_watchdog_cancel(&q->watchdog); } @@ -711,12 +731,14 @@ static int fq_dump(struct Qdisc *sch, struct sk_buff *skb) if (opts == NULL) goto nla_put_failure; + /* TCA_FQ_FLOW_DEFAULT_RATE is not used anymore, + * do not bother giving its value + */ if (nla_put_u32(skb, TCA_FQ_PLIMIT, sch->limit) || nla_put_u32(skb, TCA_FQ_FLOW_PLIMIT, q->flow_plimit) || nla_put_u32(skb, TCA_FQ_QUANTUM, q->quantum) || nla_put_u32(skb, TCA_FQ_INITIAL_QUANTUM, q->initial_quantum) || nla_put_u32(skb, TCA_FQ_RATE_ENABLE, q->rate_enable) || - nla_put_u32(skb, TCA_FQ_FLOW_DEFAULT_RATE, q->flow_default_rate) || nla_put_u32(skb, TCA_FQ_FLOW_MAX_RATE, q->flow_max_rate) || nla_put_u32(skb, TCA_FQ_BUCKETS_LOG, q->fq_trees_log)) goto nla_put_failure; diff --git a/net/sched/sch_netem.c b/net/sched/sch_netem.c index a6d788d..b87e83d 100644 --- a/net/sched/sch_netem.c +++ b/net/sched/sch_netem.c @@ -358,6 +358,21 @@ static psched_time_t packet_len_2_sched_time(unsigned int len, struct netem_sche return PSCHED_NS2TICKS(ticks); } +static void tfifo_reset(struct Qdisc *sch) +{ + struct netem_sched_data *q = qdisc_priv(sch); + struct rb_node *p; + + while ((p = rb_first(&q->t_root))) { + struct sk_buff *skb = netem_rb_to_skb(p); + + rb_erase(p, &q->t_root); + skb->next = NULL; + skb->prev = NULL; + kfree_skb(skb); + } +} + static void tfifo_enqueue(struct sk_buff *nskb, struct Qdisc *sch) { struct netem_sched_data *q = qdisc_priv(sch); @@ -520,6 +535,7 @@ static unsigned int netem_drop(struct Qdisc *sch) skb->next = NULL; skb->prev = NULL; len = qdisc_pkt_len(skb); + sch->qstats.backlog -= len; kfree_skb(skb); } } @@ -609,6 +625,7 @@ static void netem_reset(struct Qdisc *sch) struct netem_sched_data *q = qdisc_priv(sch); qdisc_reset_queue(sch); + tfifo_reset(sch); if (q->qdisc) qdisc_reset(q->qdisc); qdisc_watchdog_cancel(&q->watchdog); diff --git a/net/sctp/output.c b/net/sctp/output.c index 0ac3a65..3191373 100644 --- a/net/sctp/output.c +++ b/net/sctp/output.c @@ -536,7 +536,8 @@ int sctp_packet_transmit(struct sctp_packet *packet) * by CRC32-C as described in <draft-ietf-tsvwg-sctpcsum-02.txt>. */ if (!sctp_checksum_disable) { - if (!(dst->dev->features & NETIF_F_SCTP_CSUM)) { + if (!(dst->dev->features & NETIF_F_SCTP_CSUM) || + (dst_xfrm(dst) != NULL) || packet->ipfragok) { __u32 crc32 = sctp_start_cksum((__u8 *)sh, cksum_buf_len); /* 3) Put the resultant value into the checksum field in the diff --git a/net/socket.c b/net/socket.c index ebed4b6..c226ace 100644 --- a/net/socket.c +++ b/net/socket.c @@ -1964,6 +1964,16 @@ struct used_address { unsigned int name_len; }; +static int copy_msghdr_from_user(struct msghdr *kmsg, + struct msghdr __user *umsg) +{ + if (copy_from_user(kmsg, umsg, sizeof(struct msghdr))) + return -EFAULT; + if (kmsg->msg_namelen > sizeof(struct sockaddr_storage)) + return -EINVAL; + return 0; +} + static int ___sys_sendmsg(struct socket *sock, struct msghdr __user *msg, struct msghdr *msg_sys, unsigned int flags, struct used_address *used_address) @@ -1982,8 +1992,11 @@ static int ___sys_sendmsg(struct socket *sock, struct msghdr __user *msg, if (MSG_CMSG_COMPAT & flags) { if (get_compat_msghdr(msg_sys, msg_compat)) return -EFAULT; - } else if (copy_from_user(msg_sys, msg, sizeof(struct msghdr))) - return -EFAULT; + } else { + err = copy_msghdr_from_user(msg_sys, msg); + if (err) + return err; + } if (msg_sys->msg_iovlen > UIO_FASTIOV) { err = -EMSGSIZE; @@ -2191,8 +2204,11 @@ static int ___sys_recvmsg(struct socket *sock, struct msghdr __user *msg, if (MSG_CMSG_COMPAT & flags) { if (get_compat_msghdr(msg_sys, msg_compat)) return -EFAULT; - } else if (copy_from_user(msg_sys, msg, sizeof(struct msghdr))) - return -EFAULT; + } else { + err = copy_msghdr_from_user(msg_sys, msg); + if (err) + return err; + } if (msg_sys->msg_iovlen > UIO_FASTIOV) { err = -EMSGSIZE; diff --git a/net/sysctl_net.c b/net/sysctl_net.c index 9bc6db0..e7000be 100644 --- a/net/sysctl_net.c +++ b/net/sysctl_net.c @@ -47,12 +47,12 @@ static int net_ctl_permissions(struct ctl_table_header *head, /* Allow network administrator to have same access as root. */ if (ns_capable(net->user_ns, CAP_NET_ADMIN) || - uid_eq(root_uid, current_uid())) { + uid_eq(root_uid, current_euid())) { int mode = (table->mode >> 6) & 7; return (mode << 6) | (mode << 3) | mode; } /* Allow netns root group to have the same access as the root group */ - if (gid_eq(root_gid, current_gid())) { + if (in_egroup_p(root_gid)) { int mode = (table->mode >> 3) & 7; return (mode << 3) | mode; } diff --git a/net/unix/af_unix.c b/net/unix/af_unix.c index 86de99a..c1f403b 100644 --- a/net/unix/af_unix.c +++ b/net/unix/af_unix.c @@ -1246,6 +1246,15 @@ static int unix_socketpair(struct socket *socka, struct socket *sockb) return 0; } +static void unix_sock_inherit_flags(const struct socket *old, + struct socket *new) +{ + if (test_bit(SOCK_PASSCRED, &old->flags)) + set_bit(SOCK_PASSCRED, &new->flags); + if (test_bit(SOCK_PASSSEC, &old->flags)) + set_bit(SOCK_PASSSEC, &new->flags); +} + static int unix_accept(struct socket *sock, struct socket *newsock, int flags) { struct sock *sk = sock->sk; @@ -1280,6 +1289,7 @@ static int unix_accept(struct socket *sock, struct socket *newsock, int flags) /* attach accepted sock to socket */ unix_state_lock(tsk); newsock->state = SS_CONNECTED; + unix_sock_inherit_flags(sock, newsock); sock_graft(tsk, newsock); unix_state_unlock(tsk); return 0; diff --git a/net/unix/diag.c b/net/unix/diag.c index d591091..86fa0f3 100644 --- a/net/unix/diag.c +++ b/net/unix/diag.c @@ -124,6 +124,7 @@ static int sk_diag_fill(struct sock *sk, struct sk_buff *skb, struct unix_diag_r rep->udiag_family = AF_UNIX; rep->udiag_type = sk->sk_type; rep->udiag_state = sk->sk_state; + rep->pad = 0; rep->udiag_ino = sk_ino; sock_diag_save_cookie(sk, rep->udiag_cookie); diff --git a/net/wireless/core.c b/net/wireless/core.c index 6715396..aff959e 100644 --- a/net/wireless/core.c +++ b/net/wireless/core.c @@ -566,18 +566,13 @@ int wiphy_register(struct wiphy *wiphy) /* check and set up bitrates */ ieee80211_set_bitrate_flags(wiphy); - + rtnl_lock(); res = device_add(&rdev->wiphy.dev); - if (res) - return res; - - res = rfkill_register(rdev->rfkill); if (res) { - device_del(&rdev->wiphy.dev); + rtnl_unlock(); return res; } - rtnl_lock(); /* set up regulatory info */ wiphy_regulatory_register(wiphy); @@ -606,6 +601,15 @@ int wiphy_register(struct wiphy *wiphy) rdev->wiphy.registered = true; rtnl_unlock(); + + res = rfkill_register(rdev->rfkill); + if (res) { + rfkill_destroy(rdev->rfkill); + rdev->rfkill = NULL; + wiphy_unregister(&rdev->wiphy); + return res; + } + return 0; } EXPORT_SYMBOL(wiphy_register); @@ -640,7 +644,8 @@ void wiphy_unregister(struct wiphy *wiphy) rtnl_unlock(); __count == 0; })); - rfkill_unregister(rdev->rfkill); + if (rdev->rfkill) + rfkill_unregister(rdev->rfkill); rtnl_lock(); rdev->wiphy.registered = false; @@ -953,8 +958,6 @@ static int cfg80211_netdev_notifier_call(struct notifier_block *nb, case NETDEV_PRE_UP: if (!(wdev->wiphy->interface_modes & BIT(wdev->iftype))) return notifier_from_errno(-EOPNOTSUPP); - if (rfkill_blocked(rdev->rfkill)) - return notifier_from_errno(-ERFKILL); ret = cfg80211_can_add_interface(rdev, wdev->iftype); if (ret) return notifier_from_errno(ret); diff --git a/net/wireless/core.h b/net/wireless/core.h index 9ad43c6..3159e9c 100644 --- a/net/wireless/core.h +++ b/net/wireless/core.h @@ -411,6 +411,9 @@ static inline int cfg80211_can_add_interface(struct cfg80211_registered_device *rdev, enum nl80211_iftype iftype) { + if (rfkill_blocked(rdev->rfkill)) + return -ERFKILL; + return cfg80211_can_change_interface(rdev, NULL, iftype); } diff --git a/net/wireless/ibss.c b/net/wireless/ibss.c index 39bff7d..403fe29 100644 --- a/net/wireless/ibss.c +++ b/net/wireless/ibss.c @@ -263,6 +263,8 @@ int cfg80211_ibss_wext_join(struct cfg80211_registered_device *rdev, if (chan->flags & IEEE80211_CHAN_DISABLED) continue; wdev->wext.ibss.chandef.chan = chan; + wdev->wext.ibss.chandef.center_freq1 = + chan->center_freq; break; } @@ -347,6 +349,7 @@ int cfg80211_ibss_wext_siwfreq(struct net_device *dev, if (chan) { wdev->wext.ibss.chandef.chan = chan; wdev->wext.ibss.chandef.width = NL80211_CHAN_WIDTH_20_NOHT; + wdev->wext.ibss.chandef.center_freq1 = freq; wdev->wext.ibss.channel_fixed = true; } else { /* cfg80211_ibss_wext_join will pick one if needed */ diff --git a/net/wireless/nl80211.c b/net/wireless/nl80211.c index af8d84a..626dc3b 100644 --- a/net/wireless/nl80211.c +++ b/net/wireless/nl80211.c @@ -2421,7 +2421,7 @@ static int nl80211_set_interface(struct sk_buff *skb, struct genl_info *info) change = true; } - if (flags && (*flags & NL80211_MNTR_FLAG_ACTIVE) && + if (flags && (*flags & MONITOR_FLAG_ACTIVE) && !(rdev->wiphy.features & NL80211_FEATURE_ACTIVE_MONITOR)) return -EOPNOTSUPP; @@ -2483,7 +2483,7 @@ static int nl80211_new_interface(struct sk_buff *skb, struct genl_info *info) info->attrs[NL80211_ATTR_MNTR_FLAGS] : NULL, &flags); - if (!err && (flags & NL80211_MNTR_FLAG_ACTIVE) && + if (!err && (flags & MONITOR_FLAG_ACTIVE) && !(rdev->wiphy.features & NL80211_FEATURE_ACTIVE_MONITOR)) return -EOPNOTSUPP; diff --git a/net/wireless/radiotap.c b/net/wireless/radiotap.c index 7d604c0..a271c27 100644 --- a/net/wireless/radiotap.c +++ b/net/wireless/radiotap.c @@ -97,6 +97,10 @@ int ieee80211_radiotap_iterator_init( struct ieee80211_radiotap_header *radiotap_header, int max_length, const struct ieee80211_radiotap_vendor_namespaces *vns) { + /* check the radiotap header can actually be present */ + if (max_length < sizeof(struct ieee80211_radiotap_header)) + return -EINVAL; + /* Linux only supports version 0 radiotap format */ if (radiotap_header->it_version) return -EINVAL; @@ -131,7 +135,8 @@ int ieee80211_radiotap_iterator_init( */ if ((unsigned long)iterator->_arg - - (unsigned long)iterator->_rtheader > + (unsigned long)iterator->_rtheader + + sizeof(uint32_t) > (unsigned long)iterator->_max_length) return -EINVAL; } diff --git a/net/xfrm/xfrm_policy.c b/net/xfrm/xfrm_policy.c index ed38d5d..76e1873 100644 --- a/net/xfrm/xfrm_policy.c +++ b/net/xfrm/xfrm_policy.c @@ -334,7 +334,8 @@ static void xfrm_policy_kill(struct xfrm_policy *policy) atomic_inc(&policy->genid); - del_timer(&policy->polq.hold_timer); + if (del_timer(&policy->polq.hold_timer)) + xfrm_pol_put(policy); xfrm_queue_purge(&policy->polq.hold_queue); if (del_timer(&policy->timer)) @@ -589,7 +590,8 @@ static void xfrm_policy_requeue(struct xfrm_policy *old, spin_lock_bh(&pq->hold_queue.lock); skb_queue_splice_init(&pq->hold_queue, &list); - del_timer(&pq->hold_timer); + if (del_timer(&pq->hold_timer)) + xfrm_pol_put(old); spin_unlock_bh(&pq->hold_queue.lock); if (skb_queue_empty(&list)) @@ -600,7 +602,8 @@ static void xfrm_policy_requeue(struct xfrm_policy *old, spin_lock_bh(&pq->hold_queue.lock); skb_queue_splice(&list, &pq->hold_queue); pq->timeout = XFRM_QUEUE_TMO_MIN; - mod_timer(&pq->hold_timer, jiffies); + if (!mod_timer(&pq->hold_timer, jiffies)) + xfrm_pol_hold(new); spin_unlock_bh(&pq->hold_queue.lock); } @@ -1769,6 +1772,10 @@ static void xfrm_policy_queue_process(unsigned long arg) spin_lock(&pq->hold_queue.lock); skb = skb_peek(&pq->hold_queue); + if (!skb) { + spin_unlock(&pq->hold_queue.lock); + goto out; + } dst = skb_dst(skb); sk = skb->sk; xfrm_decode_session(skb, &fl, dst->ops->family); @@ -1787,8 +1794,9 @@ static void xfrm_policy_queue_process(unsigned long arg) goto purge_queue; pq->timeout = pq->timeout << 1; - mod_timer(&pq->hold_timer, jiffies + pq->timeout); - return; + if (!mod_timer(&pq->hold_timer, jiffies + pq->timeout)) + xfrm_pol_hold(pol); + goto out; } dst_release(dst); @@ -1819,11 +1827,14 @@ static void xfrm_policy_queue_process(unsigned long arg) err = dst_output(skb); } +out: + xfrm_pol_put(pol); return; purge_queue: pq->timeout = 0; xfrm_queue_purge(&pq->hold_queue); + xfrm_pol_put(pol); } static int xdst_queue_output(struct sk_buff *skb) @@ -1831,7 +1842,8 @@ static int xdst_queue_output(struct sk_buff *skb) unsigned long sched_next; struct dst_entry *dst = skb_dst(skb); struct xfrm_dst *xdst = (struct xfrm_dst *) dst; - struct xfrm_policy_queue *pq = &xdst->pols[0]->polq; + struct xfrm_policy *pol = xdst->pols[0]; + struct xfrm_policy_queue *pq = &pol->polq; if (pq->hold_queue.qlen > XFRM_MAX_QUEUE_LEN) { kfree_skb(skb); @@ -1850,10 +1862,12 @@ static int xdst_queue_output(struct sk_buff *skb) if (del_timer(&pq->hold_timer)) { if (time_before(pq->hold_timer.expires, sched_next)) sched_next = pq->hold_timer.expires; + xfrm_pol_put(pol); } __skb_queue_tail(&pq->hold_queue, skb); - mod_timer(&pq->hold_timer, sched_next); + if (!mod_timer(&pq->hold_timer, sched_next)) + xfrm_pol_hold(pol); spin_unlock_bh(&pq->hold_queue.lock); diff --git a/net/xfrm/xfrm_replay.c b/net/xfrm/xfrm_replay.c index 8dafe6d3..dab57da 100644 --- a/net/xfrm/xfrm_replay.c +++ b/net/xfrm/xfrm_replay.c @@ -61,9 +61,9 @@ static void xfrm_replay_notify(struct xfrm_state *x, int event) switch (event) { case XFRM_REPLAY_UPDATE: - if (x->replay_maxdiff && - (x->replay.seq - x->preplay.seq < x->replay_maxdiff) && - (x->replay.oseq - x->preplay.oseq < x->replay_maxdiff)) { + if (!x->replay_maxdiff || + ((x->replay.seq - x->preplay.seq < x->replay_maxdiff) && + (x->replay.oseq - x->preplay.oseq < x->replay_maxdiff))) { if (x->xflags & XFRM_TIME_DEFER) event = XFRM_REPLAY_TIMEOUT; else @@ -129,8 +129,7 @@ static int xfrm_replay_check(struct xfrm_state *x, return 0; diff = x->replay.seq - seq; - if (diff >= min_t(unsigned int, x->props.replay_window, - sizeof(x->replay.bitmap) * 8)) { + if (diff >= x->props.replay_window) { x->stats.replay_window++; goto err; } @@ -302,9 +301,10 @@ static void xfrm_replay_notify_bmp(struct xfrm_state *x, int event) switch (event) { case XFRM_REPLAY_UPDATE: - if (x->replay_maxdiff && - (replay_esn->seq - preplay_esn->seq < x->replay_maxdiff) && - (replay_esn->oseq - preplay_esn->oseq < x->replay_maxdiff)) { + if (!x->replay_maxdiff || + ((replay_esn->seq - preplay_esn->seq < x->replay_maxdiff) && + (replay_esn->oseq - preplay_esn->oseq + < x->replay_maxdiff))) { if (x->xflags & XFRM_TIME_DEFER) event = XFRM_REPLAY_TIMEOUT; else @@ -353,28 +353,30 @@ static void xfrm_replay_notify_esn(struct xfrm_state *x, int event) switch (event) { case XFRM_REPLAY_UPDATE: - if (!x->replay_maxdiff) - break; - - if (replay_esn->seq_hi == preplay_esn->seq_hi) - seq_diff = replay_esn->seq - preplay_esn->seq; - else - seq_diff = ~preplay_esn->seq + replay_esn->seq + 1; - - if (replay_esn->oseq_hi == preplay_esn->oseq_hi) - oseq_diff = replay_esn->oseq - preplay_esn->oseq; - else - oseq_diff = ~preplay_esn->oseq + replay_esn->oseq + 1; - - if (seq_diff < x->replay_maxdiff && - oseq_diff < x->replay_maxdiff) { + if (x->replay_maxdiff) { + if (replay_esn->seq_hi == preplay_esn->seq_hi) + seq_diff = replay_esn->seq - preplay_esn->seq; + else + seq_diff = ~preplay_esn->seq + replay_esn->seq + + 1; - if (x->xflags & XFRM_TIME_DEFER) - event = XFRM_REPLAY_TIMEOUT; + if (replay_esn->oseq_hi == preplay_esn->oseq_hi) + oseq_diff = replay_esn->oseq + - preplay_esn->oseq; else - return; + oseq_diff = ~preplay_esn->oseq + + replay_esn->oseq + 1; + + if (seq_diff >= x->replay_maxdiff || + oseq_diff >= x->replay_maxdiff) + break; } + if (x->xflags & XFRM_TIME_DEFER) + event = XFRM_REPLAY_TIMEOUT; + else + return; + break; case XFRM_REPLAY_TIMEOUT: diff --git a/net/xfrm/xfrm_user.c b/net/xfrm/xfrm_user.c index 3f565e4..f964d4c 100644 --- a/net/xfrm/xfrm_user.c +++ b/net/xfrm/xfrm_user.c @@ -446,7 +446,8 @@ static void copy_from_user_state(struct xfrm_state *x, struct xfrm_usersa_info * memcpy(&x->sel, &p->sel, sizeof(x->sel)); memcpy(&x->lft, &p->lft, sizeof(x->lft)); x->props.mode = p->mode; - x->props.replay_window = p->replay_window; + x->props.replay_window = min_t(unsigned int, p->replay_window, + sizeof(x->replay.bitmap) * 8); x->props.reqid = p->reqid; x->props.family = p->family; memcpy(&x->props.saddr, &p->saddr, sizeof(x->props.saddr)); @@ -1856,7 +1857,7 @@ static int xfrm_new_ae(struct sk_buff *skb, struct nlmsghdr *nlh, if (x->km.state != XFRM_STATE_VALID) goto out; - err = xfrm_replay_verify_len(x->replay_esn, rp); + err = xfrm_replay_verify_len(x->replay_esn, re); if (err) goto out; |