diff options
Diffstat (limited to 'net')
346 files changed, 13381 insertions, 8345 deletions
diff --git a/net/8021q/vlan.c b/net/8021q/vlan.c index a29c5ab5815c..33f90e7362cc 100644 --- a/net/8021q/vlan.c +++ b/net/8021q/vlan.c @@ -41,7 +41,7 @@ /* Global VLAN variables */ -int vlan_net_id; +int vlan_net_id __read_mostly; /* Our listing of VLAN group(s) */ static struct hlist_head vlan_group_hash[VLAN_GRP_HASH_SIZE]; @@ -140,7 +140,7 @@ static void vlan_rcu_free(struct rcu_head *rcu) vlan_group_free(container_of(rcu, struct vlan_group, rcu)); } -void unregister_vlan_dev(struct net_device *dev) +void unregister_vlan_dev(struct net_device *dev, struct list_head *head) { struct vlan_dev_info *vlan = vlan_dev_info(dev); struct net_device *real_dev = vlan->real_dev; @@ -159,12 +159,13 @@ void unregister_vlan_dev(struct net_device *dev) if (real_dev->features & NETIF_F_HW_VLAN_FILTER) ops->ndo_vlan_rx_kill_vid(real_dev, vlan_id); - vlan_group_set_device(grp, vlan_id, NULL); grp->nr_vlans--; - synchronize_net(); + vlan_group_set_device(grp, vlan_id, NULL); + if (!grp->killall) + synchronize_net(); - unregister_netdevice(dev); + unregister_netdevice_queue(dev, head); /* If the group is now empty, kill off the group. */ if (grp->nr_vlans == 0) { @@ -183,27 +184,6 @@ void unregister_vlan_dev(struct net_device *dev) dev_put(real_dev); } -static void vlan_transfer_operstate(const struct net_device *dev, - struct net_device *vlandev) -{ - /* Have to respect userspace enforced dormant state - * of real device, also must allow supplicant running - * on VLAN device - */ - if (dev->operstate == IF_OPER_DORMANT) - netif_dormant_on(vlandev); - else - netif_dormant_off(vlandev); - - if (netif_carrier_ok(dev)) { - if (!netif_carrier_ok(vlandev)) - netif_carrier_on(vlandev); - } else { - if (netif_carrier_ok(vlandev)) - netif_carrier_off(vlandev); - } -} - int vlan_check_real_dev(struct net_device *real_dev, u16 vlan_id) { const char *name = real_dev->name; @@ -261,7 +241,7 @@ int register_vlan_dev(struct net_device *dev) /* Account for reference in struct vlan_dev_info */ dev_hold(real_dev); - vlan_transfer_operstate(real_dev, dev); + netif_stacked_transfer_operstate(real_dev, dev); linkwatch_fire_event(dev); /* _MUST_ call rfc2863_policy() */ /* So, got the sucker initialized, now lets place @@ -430,6 +410,8 @@ static int vlan_device_event(struct notifier_block *unused, unsigned long event, struct vlan_group *grp; int i, flgs; struct net_device *vlandev; + struct vlan_dev_info *vlan; + LIST_HEAD(list); if (is_vlan_dev(dev)) __vlan_device_event(dev, event); @@ -450,7 +432,7 @@ static int vlan_device_event(struct notifier_block *unused, unsigned long event, if (!vlandev) continue; - vlan_transfer_operstate(dev, vlandev); + netif_stacked_transfer_operstate(dev, vlandev); } break; @@ -505,8 +487,10 @@ static int vlan_device_event(struct notifier_block *unused, unsigned long event, if (!(flgs & IFF_UP)) continue; - dev_change_flags(vlandev, flgs & ~IFF_UP); - vlan_transfer_operstate(dev, vlandev); + vlan = vlan_dev_info(vlandev); + if (!(vlan->flags & VLAN_FLAG_LOOSE_BINDING)) + dev_change_flags(vlandev, flgs & ~IFF_UP); + netif_stacked_transfer_operstate(dev, vlandev); } break; @@ -521,13 +505,17 @@ static int vlan_device_event(struct notifier_block *unused, unsigned long event, if (flgs & IFF_UP) continue; - dev_change_flags(vlandev, flgs | IFF_UP); - vlan_transfer_operstate(dev, vlandev); + vlan = vlan_dev_info(vlandev); + if (!(vlan->flags & VLAN_FLAG_LOOSE_BINDING)) + dev_change_flags(vlandev, flgs | IFF_UP); + netif_stacked_transfer_operstate(dev, vlandev); } break; case NETDEV_UNREGISTER: /* Delete all VLANs for this dev. */ + grp->killall = 1; + for (i = 0; i < VLAN_GROUP_ARRAY_LEN; i++) { vlandev = vlan_group_get_device(grp, i); if (!vlandev) @@ -538,8 +526,9 @@ static int vlan_device_event(struct notifier_block *unused, unsigned long event, if (grp->nr_vlans == 1) i = VLAN_GROUP_ARRAY_LEN; - unregister_vlan_dev(vlandev); + unregister_vlan_dev(vlandev, &list); } + unregister_netdevice_many(&list); break; } @@ -645,7 +634,7 @@ static int vlan_ioctl_handler(struct net *net, void __user *arg) err = -EPERM; if (!capable(CAP_NET_ADMIN)) break; - unregister_vlan_dev(dev); + unregister_vlan_dev(dev, NULL); err = 0; break; @@ -676,47 +665,26 @@ out: static int vlan_init_net(struct net *net) { + struct vlan_net *vn = net_generic(net, vlan_net_id); int err; - struct vlan_net *vn; - - err = -ENOMEM; - vn = kzalloc(sizeof(struct vlan_net), GFP_KERNEL); - if (vn == NULL) - goto err_alloc; - - err = net_assign_generic(net, vlan_net_id, vn); - if (err < 0) - goto err_assign; vn->name_type = VLAN_NAME_TYPE_RAW_PLUS_VID_NO_PAD; err = vlan_proc_init(net); - if (err < 0) - goto err_proc; - - return 0; -err_proc: - /* nothing */ -err_assign: - kfree(vn); -err_alloc: return err; } static void vlan_exit_net(struct net *net) { - struct vlan_net *vn; - - vn = net_generic(net, vlan_net_id); - rtnl_kill_links(net, &vlan_link_ops); vlan_proc_cleanup(net); - kfree(vn); } static struct pernet_operations vlan_net_ops = { .init = vlan_init_net, .exit = vlan_exit_net, + .id = &vlan_net_id, + .size = sizeof(struct vlan_net), }; static int __init vlan_proto_init(void) @@ -726,7 +694,7 @@ static int __init vlan_proto_init(void) pr_info("%s v%s %s\n", vlan_fullname, vlan_version, vlan_copyright); pr_info("All bugs added by %s\n", vlan_buggyright); - err = register_pernet_gen_device(&vlan_net_id, &vlan_net_ops); + err = register_pernet_subsys(&vlan_net_ops); if (err < 0) goto err0; @@ -751,7 +719,7 @@ err4: err3: unregister_netdevice_notifier(&vlan_notifier_block); err2: - unregister_pernet_gen_device(vlan_net_id, &vlan_net_ops); + unregister_pernet_subsys(&vlan_net_ops); err0: return err; } @@ -771,7 +739,7 @@ static void __exit vlan_cleanup_module(void) for (i = 0; i < VLAN_GRP_HASH_SIZE; i++) BUG_ON(!hlist_empty(&vlan_group_hash[i])); - unregister_pernet_gen_device(vlan_net_id, &vlan_net_ops); + unregister_pernet_subsys(&vlan_net_ops); rcu_barrier(); /* Wait for completion of call_rcu()'s */ vlan_gvrp_uninit(); diff --git a/net/8021q/vlan.h b/net/8021q/vlan.h index 82570bc2a180..5685296017e9 100644 --- a/net/8021q/vlan.h +++ b/net/8021q/vlan.h @@ -16,6 +16,21 @@ struct vlan_priority_tci_mapping { struct vlan_priority_tci_mapping *next; }; + +/** + * struct vlan_rx_stats - VLAN percpu rx stats + * @rx_packets: number of received packets + * @rx_bytes: number of received bytes + * @multicast: number of received multicast packets + * @rx_errors: number of errors + */ +struct vlan_rx_stats { + unsigned long rx_packets; + unsigned long rx_bytes; + unsigned long multicast; + unsigned long rx_errors; +}; + /** * struct vlan_dev_info - VLAN private device data * @nr_ingress_mappings: number of ingress priority mappings @@ -29,6 +44,7 @@ struct vlan_priority_tci_mapping { * @dent: proc dir entry * @cnt_inc_headroom_on_tx: statistic - number of skb expansions on TX * @cnt_encap_on_xmit: statistic - number of skb encapsulations on TX + * @vlan_rx_stats: ptr to percpu rx stats */ struct vlan_dev_info { unsigned int nr_ingress_mappings; @@ -45,6 +61,7 @@ struct vlan_dev_info { struct proc_dir_entry *dent; unsigned long cnt_inc_headroom_on_tx; unsigned long cnt_encap_on_xmit; + struct vlan_rx_stats *vlan_rx_stats; }; static inline struct vlan_dev_info *vlan_dev_info(const struct net_device *dev) @@ -82,14 +99,14 @@ void vlan_dev_get_realdev_name(const struct net_device *dev, char *result); int vlan_check_real_dev(struct net_device *real_dev, u16 vlan_id); void vlan_setup(struct net_device *dev); int register_vlan_dev(struct net_device *dev); -void unregister_vlan_dev(struct net_device *dev); +void unregister_vlan_dev(struct net_device *dev, struct list_head *head); static inline u32 vlan_get_ingress_priority(struct net_device *dev, u16 vlan_tci) { struct vlan_dev_info *vip = vlan_dev_info(dev); - return vip->ingress_priority_map[(vlan_tci >> 13) & 0x7]; + return vip->ingress_priority_map[(vlan_tci >> VLAN_PRIO_SHIFT) & 0x7]; } #ifdef CONFIG_VLAN_8021Q_GVRP diff --git a/net/8021q/vlan_core.c b/net/8021q/vlan_core.c index 7f7de1a04de6..e75a2f3b10af 100644 --- a/net/8021q/vlan_core.c +++ b/net/8021q/vlan_core.c @@ -14,7 +14,7 @@ int __vlan_hwaccel_rx(struct sk_buff *skb, struct vlan_group *grp, if (skb_bond_should_drop(skb)) goto drop; - skb->vlan_tci = vlan_tci; + __vlan_hwaccel_put_tag(skb, vlan_tci); skb->dev = vlan_group_get_device(grp, vlan_tci & VLAN_VID_MASK); if (!skb->dev) @@ -31,7 +31,7 @@ EXPORT_SYMBOL(__vlan_hwaccel_rx); int vlan_hwaccel_do_receive(struct sk_buff *skb) { struct net_device *dev = skb->dev; - struct net_device_stats *stats; + struct vlan_rx_stats *rx_stats; skb->dev = vlan_dev_info(dev)->real_dev; netif_nit_deliver(skb); @@ -40,15 +40,17 @@ int vlan_hwaccel_do_receive(struct sk_buff *skb) skb->priority = vlan_get_ingress_priority(dev, skb->vlan_tci); skb->vlan_tci = 0; - stats = &dev->stats; - stats->rx_packets++; - stats->rx_bytes += skb->len; + rx_stats = per_cpu_ptr(vlan_dev_info(dev)->vlan_rx_stats, + smp_processor_id()); + + rx_stats->rx_packets++; + rx_stats->rx_bytes += skb->len; switch (skb->pkt_type) { case PACKET_BROADCAST: break; case PACKET_MULTICAST: - stats->multicast++; + rx_stats->multicast++; break; case PACKET_OTHERHOST: /* Our lower layer thinks this is not local, let's make sure. @@ -74,15 +76,16 @@ u16 vlan_dev_vlan_id(const struct net_device *dev) } EXPORT_SYMBOL(vlan_dev_vlan_id); -static int vlan_gro_common(struct napi_struct *napi, struct vlan_group *grp, - unsigned int vlan_tci, struct sk_buff *skb) +static gro_result_t +vlan_gro_common(struct napi_struct *napi, struct vlan_group *grp, + unsigned int vlan_tci, struct sk_buff *skb) { struct sk_buff *p; if (skb_bond_should_drop(skb)) goto drop; - skb->vlan_tci = vlan_tci; + __vlan_hwaccel_put_tag(skb, vlan_tci); skb->dev = vlan_group_get_device(grp, vlan_tci & VLAN_VID_MASK); if (!skb->dev) @@ -101,11 +104,12 @@ drop: return GRO_DROP; } -int vlan_gro_receive(struct napi_struct *napi, struct vlan_group *grp, - unsigned int vlan_tci, struct sk_buff *skb) +gro_result_t vlan_gro_receive(struct napi_struct *napi, struct vlan_group *grp, + unsigned int vlan_tci, struct sk_buff *skb) { if (netpoll_rx_on(skb)) - return vlan_hwaccel_receive_skb(skb, grp, vlan_tci); + return vlan_hwaccel_receive_skb(skb, grp, vlan_tci) + ? GRO_DROP : GRO_NORMAL; skb_gro_reset_offset(skb); @@ -113,17 +117,18 @@ int vlan_gro_receive(struct napi_struct *napi, struct vlan_group *grp, } EXPORT_SYMBOL(vlan_gro_receive); -int vlan_gro_frags(struct napi_struct *napi, struct vlan_group *grp, - unsigned int vlan_tci) +gro_result_t vlan_gro_frags(struct napi_struct *napi, struct vlan_group *grp, + unsigned int vlan_tci) { struct sk_buff *skb = napi_frags_skb(napi); if (!skb) - return NET_RX_DROP; + return GRO_DROP; if (netpoll_rx_on(skb)) { skb->protocol = eth_type_trans(skb, skb->dev); - return vlan_hwaccel_receive_skb(skb, grp, vlan_tci); + return vlan_hwaccel_receive_skb(skb, grp, vlan_tci) + ? GRO_DROP : GRO_NORMAL; } return napi_frags_finish(napi, skb, diff --git a/net/8021q/vlan_dev.c b/net/8021q/vlan_dev.c index 4198ec5c8abc..b7889782047e 100644 --- a/net/8021q/vlan_dev.c +++ b/net/8021q/vlan_dev.c @@ -140,7 +140,7 @@ int vlan_skb_recv(struct sk_buff *skb, struct net_device *dev, struct packet_type *ptype, struct net_device *orig_dev) { struct vlan_hdr *vhdr; - struct net_device_stats *stats; + struct vlan_rx_stats *rx_stats; u16 vlan_id; u16 vlan_tci; @@ -163,9 +163,10 @@ int vlan_skb_recv(struct sk_buff *skb, struct net_device *dev, goto err_unlock; } - stats = &skb->dev->stats; - stats->rx_packets++; - stats->rx_bytes += skb->len; + rx_stats = per_cpu_ptr(vlan_dev_info(dev)->vlan_rx_stats, + smp_processor_id()); + rx_stats->rx_packets++; + rx_stats->rx_bytes += skb->len; skb_pull_rcsum(skb, VLAN_HLEN); @@ -180,7 +181,7 @@ int vlan_skb_recv(struct sk_buff *skb, struct net_device *dev, break; case PACKET_MULTICAST: - stats->multicast++; + rx_stats->multicast++; break; case PACKET_OTHERHOST: @@ -200,7 +201,7 @@ int vlan_skb_recv(struct sk_buff *skb, struct net_device *dev, skb = vlan_check_reorder_header(skb); if (!skb) { - stats->rx_errors++; + rx_stats->rx_errors++; goto err_unlock; } @@ -332,7 +333,7 @@ static netdev_tx_t vlan_dev_hard_start_xmit(struct sk_buff *skb, } else txq->tx_dropped++; - return NETDEV_TX_OK; + return ret; } static netdev_tx_t vlan_dev_hwaccel_hard_start_xmit(struct sk_buff *skb, @@ -358,7 +359,7 @@ static netdev_tx_t vlan_dev_hwaccel_hard_start_xmit(struct sk_buff *skb, } else txq->tx_dropped++; - return NETDEV_TX_OK; + return ret; } static int vlan_dev_change_mtu(struct net_device *dev, int new_mtu) @@ -393,7 +394,7 @@ int vlan_dev_set_egress_priority(const struct net_device *dev, struct vlan_dev_info *vlan = vlan_dev_info(dev); struct vlan_priority_tci_mapping *mp = NULL; struct vlan_priority_tci_mapping *np; - u32 vlan_qos = (vlan_prio << 13) & 0xE000; + u32 vlan_qos = (vlan_prio << VLAN_PRIO_SHIFT) & VLAN_PRIO_MASK; /* See if a priority mapping exists.. */ mp = vlan->egress_priority_map[skb_prio & 0xF]; @@ -430,7 +431,8 @@ int vlan_dev_change_flags(const struct net_device *dev, u32 flags, u32 mask) struct vlan_dev_info *vlan = vlan_dev_info(dev); u32 old_flags = vlan->flags; - if (mask & ~(VLAN_FLAG_REORDER_HDR | VLAN_FLAG_GVRP)) + if (mask & ~(VLAN_FLAG_REORDER_HDR | VLAN_FLAG_GVRP | + VLAN_FLAG_LOOSE_BINDING)) return -EINVAL; vlan->flags = (old_flags & ~mask) | (flags & mask); @@ -455,7 +457,8 @@ static int vlan_dev_open(struct net_device *dev) struct net_device *real_dev = vlan->real_dev; int err; - if (!(real_dev->flags & IFF_UP)) + if (!(real_dev->flags & IFF_UP) && + !(vlan->flags & VLAN_FLAG_LOOSE_BINDING)) return -ENETDOWN; if (compare_ether_addr(dev->dev_addr, real_dev->dev_addr)) { @@ -626,6 +629,17 @@ static int vlan_dev_fcoe_disable(struct net_device *dev) rc = ops->ndo_fcoe_disable(real_dev); return rc; } + +static int vlan_dev_fcoe_get_wwn(struct net_device *dev, u64 *wwn, int type) +{ + struct net_device *real_dev = vlan_dev_info(dev)->real_dev; + const struct net_device_ops *ops = real_dev->netdev_ops; + int rc = -EINVAL; + + if (ops->ndo_fcoe_get_wwn) + rc = ops->ndo_fcoe_get_wwn(real_dev, wwn, type); + return rc; +} #endif static void vlan_dev_change_rx_flags(struct net_device *dev, int change) @@ -720,6 +734,11 @@ static int vlan_dev_init(struct net_device *dev) subclass = 1; vlan_dev_set_lockdep_class(dev, subclass); + + vlan_dev_info(dev)->vlan_rx_stats = alloc_percpu(struct vlan_rx_stats); + if (!vlan_dev_info(dev)->vlan_rx_stats) + return -ENOMEM; + return 0; } @@ -729,6 +748,8 @@ static void vlan_dev_uninit(struct net_device *dev) struct vlan_dev_info *vlan = vlan_dev_info(dev); int i; + free_percpu(vlan->vlan_rx_stats); + vlan->vlan_rx_stats = NULL; for (i = 0; i < ARRAY_SIZE(vlan->egress_priority_map); i++) { while ((pm = vlan->egress_priority_map[i]) != NULL) { vlan->egress_priority_map[i] = pm->next; @@ -764,6 +785,31 @@ static u32 vlan_ethtool_get_flags(struct net_device *dev) return dev_ethtool_get_flags(vlan->real_dev); } +static struct net_device_stats *vlan_dev_get_stats(struct net_device *dev) +{ + struct net_device_stats *stats = &dev->stats; + + dev_txq_stats_fold(dev, stats); + + if (vlan_dev_info(dev)->vlan_rx_stats) { + struct vlan_rx_stats *p, rx = {0}; + int i; + + for_each_possible_cpu(i) { + p = per_cpu_ptr(vlan_dev_info(dev)->vlan_rx_stats, i); + rx.rx_packets += p->rx_packets; + rx.rx_bytes += p->rx_bytes; + rx.rx_errors += p->rx_errors; + rx.multicast += p->multicast; + } + stats->rx_packets = rx.rx_packets; + stats->rx_bytes = rx.rx_bytes; + stats->rx_errors = rx.rx_errors; + stats->multicast = rx.multicast; + } + return stats; +} + static const struct ethtool_ops vlan_ethtool_ops = { .get_settings = vlan_ethtool_get_settings, .get_drvinfo = vlan_ethtool_get_drvinfo, @@ -786,11 +832,13 @@ static const struct net_device_ops vlan_netdev_ops = { .ndo_change_rx_flags = vlan_dev_change_rx_flags, .ndo_do_ioctl = vlan_dev_ioctl, .ndo_neigh_setup = vlan_dev_neigh_setup, + .ndo_get_stats = vlan_dev_get_stats, #if defined(CONFIG_FCOE) || defined(CONFIG_FCOE_MODULE) .ndo_fcoe_ddp_setup = vlan_dev_fcoe_ddp_setup, .ndo_fcoe_ddp_done = vlan_dev_fcoe_ddp_done, .ndo_fcoe_enable = vlan_dev_fcoe_enable, .ndo_fcoe_disable = vlan_dev_fcoe_disable, + .ndo_fcoe_get_wwn = vlan_dev_fcoe_get_wwn, #endif }; @@ -808,11 +856,13 @@ static const struct net_device_ops vlan_netdev_accel_ops = { .ndo_change_rx_flags = vlan_dev_change_rx_flags, .ndo_do_ioctl = vlan_dev_ioctl, .ndo_neigh_setup = vlan_dev_neigh_setup, + .ndo_get_stats = vlan_dev_get_stats, #if defined(CONFIG_FCOE) || defined(CONFIG_FCOE_MODULE) .ndo_fcoe_ddp_setup = vlan_dev_fcoe_ddp_setup, .ndo_fcoe_ddp_done = vlan_dev_fcoe_ddp_done, .ndo_fcoe_enable = vlan_dev_fcoe_enable, .ndo_fcoe_disable = vlan_dev_fcoe_disable, + .ndo_fcoe_get_wwn = vlan_dev_fcoe_get_wwn, #endif }; diff --git a/net/8021q/vlan_netlink.c b/net/8021q/vlan_netlink.c index a91504850195..ddc105734af7 100644 --- a/net/8021q/vlan_netlink.c +++ b/net/8021q/vlan_netlink.c @@ -60,7 +60,8 @@ static int vlan_validate(struct nlattr *tb[], struct nlattr *data[]) if (data[IFLA_VLAN_FLAGS]) { flags = nla_data(data[IFLA_VLAN_FLAGS]); if ((flags->flags & flags->mask) & - ~(VLAN_FLAG_REORDER_HDR | VLAN_FLAG_GVRP)) + ~(VLAN_FLAG_REORDER_HDR | VLAN_FLAG_GVRP | + VLAN_FLAG_LOOSE_BINDING)) return -EINVAL; } @@ -119,7 +120,7 @@ static int vlan_get_tx_queues(struct net *net, return 0; } -static int vlan_newlink(struct net_device *dev, +static int vlan_newlink(struct net *src_net, struct net_device *dev, struct nlattr *tb[], struct nlattr *data[]) { struct vlan_dev_info *vlan = vlan_dev_info(dev); @@ -131,7 +132,7 @@ static int vlan_newlink(struct net_device *dev, if (!tb[IFLA_LINK]) return -EINVAL; - real_dev = __dev_get_by_index(dev_net(dev), nla_get_u32(tb[IFLA_LINK])); + real_dev = __dev_get_by_index(src_net, nla_get_u32(tb[IFLA_LINK])); if (!real_dev) return -ENODEV; diff --git a/net/8021q/vlanproc.c b/net/8021q/vlanproc.c index 6262c335f3c2..9ec1f057c03a 100644 --- a/net/8021q/vlanproc.c +++ b/net/8021q/vlanproc.c @@ -201,18 +201,17 @@ int vlan_proc_rem_dev(struct net_device *vlandev) /* start read of /proc/net/vlan/config */ static void *vlan_seq_start(struct seq_file *seq, loff_t *pos) - __acquires(dev_base_lock) + __acquires(rcu) { struct net_device *dev; struct net *net = seq_file_net(seq); loff_t i = 1; - read_lock(&dev_base_lock); - + rcu_read_lock(); if (*pos == 0) return SEQ_START_TOKEN; - for_each_netdev(net, dev) { + for_each_netdev_rcu(net, dev) { if (!is_vlan_dev(dev)) continue; @@ -234,7 +233,7 @@ static void *vlan_seq_next(struct seq_file *seq, void *v, loff_t *pos) if (v == SEQ_START_TOKEN) dev = net_device_entry(&net->dev_base_head); - for_each_netdev_continue(net, dev) { + for_each_netdev_continue_rcu(net, dev) { if (!is_vlan_dev(dev)) continue; @@ -245,9 +244,9 @@ static void *vlan_seq_next(struct seq_file *seq, void *v, loff_t *pos) } static void vlan_seq_stop(struct seq_file *seq, void *v) - __releases(dev_base_lock) + __releases(rcu) { - read_unlock(&dev_base_lock); + rcu_read_unlock(); } static int vlan_seq_show(struct seq_file *seq, void *v) diff --git a/net/9p/trans_fd.c b/net/9p/trans_fd.c index 8d934dd7fd54..4dd873e3a1bb 100644 --- a/net/9p/trans_fd.c +++ b/net/9p/trans_fd.c @@ -633,8 +633,8 @@ static void p9_poll_mux(struct p9_conn *m) if (n & POLLOUT) { set_bit(Wpending, &m->wsched); P9_DPRINTK(P9_DEBUG_TRANS, "mux %p can write\n", m); - if ((m->wsize || !list_empty(&m->unsent_req_list)) - && !test_and_set_bit(Wworksched, &m->wsched)) { + if ((m->wsize || !list_empty(&m->unsent_req_list)) && + !test_and_set_bit(Wworksched, &m->wsched)) { P9_DPRINTK(P9_DEBUG_TRANS, "sched write work %p\n", m); queue_work(p9_mux_wq, &m->wq); } diff --git a/net/appletalk/ddp.c b/net/appletalk/ddp.c index b1a4290996b5..9fc4da56fb1d 100644 --- a/net/appletalk/ddp.c +++ b/net/appletalk/ddp.c @@ -56,6 +56,7 @@ #include <linux/if_arp.h> #include <linux/smp_lock.h> #include <linux/termios.h> /* For TIOCOUTQ/INQ */ +#include <linux/compat.h> #include <net/datalink.h> #include <net/psnap.h> #include <net/sock.h> @@ -922,13 +923,8 @@ static unsigned long atalk_sum_partial(const unsigned char *data, { /* This ought to be unwrapped neatly. I'll trust gcc for now */ while (len--) { - sum += *data; - sum <<= 1; - if (sum & 0x10000) { - sum++; - sum &= 0xffff; - } - data++; + sum += *data++; + sum = rol16(sum, 1); } return sum; } @@ -1021,12 +1017,13 @@ static struct proto ddp_proto = { * Create a socket. Initialise the socket, blank the addresses * set the state. */ -static int atalk_create(struct net *net, struct socket *sock, int protocol) +static int atalk_create(struct net *net, struct socket *sock, int protocol, + int kern) { struct sock *sk; int rc = -ESOCKTNOSUPPORT; - if (net != &init_net) + if (!net_eq(net, &init_net)) return -EAFNOSUPPORT; /* @@ -1054,11 +1051,13 @@ static int atalk_release(struct socket *sock) { struct sock *sk = sock->sk; + lock_kernel(); if (sk) { sock_orphan(sk); sock->sk = NULL; atalk_destroy_socket(sk); } + unlock_kernel(); return 0; } @@ -1134,6 +1133,7 @@ static int atalk_bind(struct socket *sock, struct sockaddr *uaddr, int addr_len) struct sockaddr_at *addr = (struct sockaddr_at *)uaddr; struct sock *sk = sock->sk; struct atalk_sock *at = at_sk(sk); + int err; if (!sock_flag(sk, SOCK_ZAPPED) || addr_len != sizeof(struct sockaddr_at)) @@ -1142,37 +1142,44 @@ static int atalk_bind(struct socket *sock, struct sockaddr *uaddr, int addr_len) if (addr->sat_family != AF_APPLETALK) return -EAFNOSUPPORT; + lock_kernel(); if (addr->sat_addr.s_net == htons(ATADDR_ANYNET)) { struct atalk_addr *ap = atalk_find_primary(); + err = -EADDRNOTAVAIL; if (!ap) - return -EADDRNOTAVAIL; + goto out; at->src_net = addr->sat_addr.s_net = ap->s_net; at->src_node = addr->sat_addr.s_node= ap->s_node; } else { + err = -EADDRNOTAVAIL; if (!atalk_find_interface(addr->sat_addr.s_net, addr->sat_addr.s_node)) - return -EADDRNOTAVAIL; + goto out; at->src_net = addr->sat_addr.s_net; at->src_node = addr->sat_addr.s_node; } if (addr->sat_port == ATADDR_ANYPORT) { - int n = atalk_pick_and_bind_port(sk, addr); + err = atalk_pick_and_bind_port(sk, addr); - if (n < 0) - return n; + if (err < 0) + goto out; } else { at->src_port = addr->sat_port; + err = -EADDRINUSE; if (atalk_find_or_insert_socket(sk, addr)) - return -EADDRINUSE; + goto out; } sock_reset_flag(sk, SOCK_ZAPPED); - return 0; + err = 0; +out: + unlock_kernel(); + return err; } /* Set the address we talk to */ @@ -1182,6 +1189,7 @@ static int atalk_connect(struct socket *sock, struct sockaddr *uaddr, struct sock *sk = sock->sk; struct atalk_sock *at = at_sk(sk); struct sockaddr_at *addr; + int err; sk->sk_state = TCP_CLOSE; sock->state = SS_UNCONNECTED; @@ -1206,12 +1214,15 @@ static int atalk_connect(struct socket *sock, struct sockaddr *uaddr, #endif } + lock_kernel(); + err = -EBUSY; if (sock_flag(sk, SOCK_ZAPPED)) if (atalk_autobind(sk) < 0) - return -EBUSY; + goto out; + err = -ENETUNREACH; if (!atrtr_get_dev(&addr->sat_addr)) - return -ENETUNREACH; + goto out; at->dest_port = addr->sat_port; at->dest_net = addr->sat_addr.s_net; @@ -1219,7 +1230,10 @@ static int atalk_connect(struct socket *sock, struct sockaddr *uaddr, sock->state = SS_CONNECTED; sk->sk_state = TCP_ESTABLISHED; - return 0; + err = 0; +out: + unlock_kernel(); + return err; } /* @@ -1232,17 +1246,21 @@ static int atalk_getname(struct socket *sock, struct sockaddr *uaddr, struct sockaddr_at sat; struct sock *sk = sock->sk; struct atalk_sock *at = at_sk(sk); + int err; + lock_kernel(); + err = -ENOBUFS; if (sock_flag(sk, SOCK_ZAPPED)) if (atalk_autobind(sk) < 0) - return -ENOBUFS; + goto out; *uaddr_len = sizeof(struct sockaddr_at); memset(&sat.sat_zero, 0, sizeof(sat.sat_zero)); if (peer) { + err = -ENOTCONN; if (sk->sk_state != TCP_ESTABLISHED) - return -ENOTCONN; + goto out; sat.sat_addr.s_net = at->dest_net; sat.sat_addr.s_node = at->dest_node; @@ -1253,9 +1271,23 @@ static int atalk_getname(struct socket *sock, struct sockaddr *uaddr, sat.sat_port = at->src_port; } + err = 0; sat.sat_family = AF_APPLETALK; memcpy(uaddr, &sat, sizeof(sat)); - return 0; + +out: + unlock_kernel(); + return err; +} + +static unsigned int atalk_poll(struct file *file, struct socket *sock, + poll_table *wait) +{ + int err; + lock_kernel(); + err = datagram_poll(file, sock, wait); + unlock_kernel(); + return err; } #if defined(CONFIG_IPDDP) || defined(CONFIG_IPDDP_MODULE) @@ -1563,23 +1595,28 @@ static int atalk_sendmsg(struct kiocb *iocb, struct socket *sock, struct msghdr if (len > DDP_MAXSZ) return -EMSGSIZE; + lock_kernel(); if (usat) { + err = -EBUSY; if (sock_flag(sk, SOCK_ZAPPED)) if (atalk_autobind(sk) < 0) - return -EBUSY; + goto out; + err = -EINVAL; if (msg->msg_namelen < sizeof(*usat) || usat->sat_family != AF_APPLETALK) - return -EINVAL; + goto out; + err = -EPERM; /* netatalk didn't implement this check */ if (usat->sat_addr.s_node == ATADDR_BCAST && !sock_flag(sk, SOCK_BROADCAST)) { - return -EPERM; + goto out; } } else { + err = -ENOTCONN; if (sk->sk_state != TCP_ESTABLISHED) - return -ENOTCONN; + goto out; usat = &local_satalk; usat->sat_family = AF_APPLETALK; usat->sat_port = at->dest_port; @@ -1603,8 +1640,9 @@ static int atalk_sendmsg(struct kiocb *iocb, struct socket *sock, struct msghdr rt = atrtr_find(&at_hint); } + err = ENETUNREACH; if (!rt) - return -ENETUNREACH; + goto out; dev = rt->dev; @@ -1614,7 +1652,7 @@ static int atalk_sendmsg(struct kiocb *iocb, struct socket *sock, struct msghdr size += dev->hard_header_len; skb = sock_alloc_send_skb(sk, size, (flags & MSG_DONTWAIT), &err); if (!skb) - return err; + goto out; skb->sk = sk; skb_reserve(skb, ddp_dl->header_length); @@ -1637,7 +1675,8 @@ static int atalk_sendmsg(struct kiocb *iocb, struct socket *sock, struct msghdr err = memcpy_fromiovec(skb_put(skb, len), msg->msg_iov, len); if (err) { kfree_skb(skb); - return -EFAULT; + err = -EFAULT; + goto out; } if (sk->sk_no_check == 1) @@ -1676,7 +1715,8 @@ static int atalk_sendmsg(struct kiocb *iocb, struct socket *sock, struct msghdr rt = atrtr_find(&at_lo); if (!rt) { kfree_skb(skb); - return -ENETUNREACH; + err = -ENETUNREACH; + goto out; } dev = rt->dev; skb->dev = dev; @@ -1696,7 +1736,9 @@ static int atalk_sendmsg(struct kiocb *iocb, struct socket *sock, struct msghdr } SOCK_DEBUG(sk, "SK %p: Done write (%Zd).\n", sk, len); - return len; +out: + unlock_kernel(); + return err ? : len; } static int atalk_recvmsg(struct kiocb *iocb, struct socket *sock, struct msghdr *msg, @@ -1708,10 +1750,13 @@ static int atalk_recvmsg(struct kiocb *iocb, struct socket *sock, struct msghdr int copied = 0; int offset = 0; int err = 0; - struct sk_buff *skb = skb_recv_datagram(sk, flags & ~MSG_DONTWAIT, + struct sk_buff *skb; + + lock_kernel(); + skb = skb_recv_datagram(sk, flags & ~MSG_DONTWAIT, flags & MSG_DONTWAIT, &err); if (!skb) - return err; + goto out; /* FIXME: use skb->cb to be able to use shared skbs */ ddp = ddp_hdr(skb); @@ -1739,6 +1784,9 @@ static int atalk_recvmsg(struct kiocb *iocb, struct socket *sock, struct msghdr } skb_free_datagram(sk, skb); /* Free the datagram. */ + +out: + unlock_kernel(); return err ? : copied; } @@ -1810,24 +1858,26 @@ static int atalk_ioctl(struct socket *sock, unsigned int cmd, unsigned long arg) static int atalk_compat_ioctl(struct socket *sock, unsigned int cmd, unsigned long arg) { /* - * All Appletalk ioctls except SIOCATALKDIFADDR are standard. And - * SIOCATALKDIFADDR is handled by upper layer as well, so there is - * nothing to do. Eventually SIOCATALKDIFADDR should be moved - * here so there is no generic SIOCPROTOPRIVATE translation in the - * system. + * SIOCATALKDIFADDR is a SIOCPROTOPRIVATE ioctl number, so we + * cannot handle it in common code. The data we access if ifreq + * here is compatible, so we can simply call the native + * handler. */ + if (cmd == SIOCATALKDIFADDR) + return atalk_ioctl(sock, cmd, (unsigned long)compat_ptr(arg)); + return -ENOIOCTLCMD; } #endif -static struct net_proto_family atalk_family_ops = { +static const struct net_proto_family atalk_family_ops = { .family = PF_APPLETALK, .create = atalk_create, .owner = THIS_MODULE, }; -static const struct proto_ops SOCKOPS_WRAPPED(atalk_dgram_ops) = { +static const struct proto_ops atalk_dgram_ops = { .family = PF_APPLETALK, .owner = THIS_MODULE, .release = atalk_release, @@ -1836,7 +1886,7 @@ static const struct proto_ops SOCKOPS_WRAPPED(atalk_dgram_ops) = { .socketpair = sock_no_socketpair, .accept = sock_no_accept, .getname = atalk_getname, - .poll = datagram_poll, + .poll = atalk_poll, .ioctl = atalk_ioctl, #ifdef CONFIG_COMPAT .compat_ioctl = atalk_compat_ioctl, @@ -1851,8 +1901,6 @@ static const struct proto_ops SOCKOPS_WRAPPED(atalk_dgram_ops) = { .sendpage = sock_no_sendpage, }; -SOCKOPS_WRAP(atalk_dgram, PF_APPLETALK); - static struct notifier_block ddp_notifier = { .notifier_call = ddp_device_event, }; diff --git a/net/atm/common.c b/net/atm/common.c index 950bd16d2383..d61e051e0a3f 100644 --- a/net/atm/common.c +++ b/net/atm/common.c @@ -496,7 +496,7 @@ int vcc_recvmsg(struct kiocb *iocb, struct socket *sock, struct msghdr *msg, error = skb_copy_datagram_iovec(skb, 0, msg->msg_iov, copied); if (error) return error; - sock_recv_timestamp(msg, sk, skb); + sock_recv_ts_and_drops(msg, sk, skb); pr_debug("RcvM %d -= %d\n", atomic_read(&sk->sk_rmem_alloc), skb->truesize); atm_return(vcc, skb->truesize); skb_free_datagram(sk, skb); diff --git a/net/atm/ioctl.c b/net/atm/ioctl.c index 4da8892ced5f..2ea40995dced 100644 --- a/net/atm/ioctl.c +++ b/net/atm/ioctl.c @@ -191,8 +191,181 @@ int vcc_ioctl(struct socket *sock, unsigned int cmd, unsigned long arg) } #ifdef CONFIG_COMPAT -int vcc_compat_ioctl(struct socket *sock, unsigned int cmd, unsigned long arg) +/* + * FIXME: + * The compat_ioctl handling is duplicated, using both these conversion + * routines and the compat argument to the actual handlers. Both + * versions are somewhat incomplete and should be merged, e.g. by + * moving the ioctl number translation into the actual handlers and + * killing the conversion code. + * + * -arnd, November 2009 + */ +#define ATM_GETLINKRATE32 _IOW('a', ATMIOC_ITF+1, struct compat_atmif_sioc) +#define ATM_GETNAMES32 _IOW('a', ATMIOC_ITF+3, struct compat_atm_iobuf) +#define ATM_GETTYPE32 _IOW('a', ATMIOC_ITF+4, struct compat_atmif_sioc) +#define ATM_GETESI32 _IOW('a', ATMIOC_ITF+5, struct compat_atmif_sioc) +#define ATM_GETADDR32 _IOW('a', ATMIOC_ITF+6, struct compat_atmif_sioc) +#define ATM_RSTADDR32 _IOW('a', ATMIOC_ITF+7, struct compat_atmif_sioc) +#define ATM_ADDADDR32 _IOW('a', ATMIOC_ITF+8, struct compat_atmif_sioc) +#define ATM_DELADDR32 _IOW('a', ATMIOC_ITF+9, struct compat_atmif_sioc) +#define ATM_GETCIRANGE32 _IOW('a', ATMIOC_ITF+10, struct compat_atmif_sioc) +#define ATM_SETCIRANGE32 _IOW('a', ATMIOC_ITF+11, struct compat_atmif_sioc) +#define ATM_SETESI32 _IOW('a', ATMIOC_ITF+12, struct compat_atmif_sioc) +#define ATM_SETESIF32 _IOW('a', ATMIOC_ITF+13, struct compat_atmif_sioc) +#define ATM_GETSTAT32 _IOW('a', ATMIOC_SARCOM+0, struct compat_atmif_sioc) +#define ATM_GETSTATZ32 _IOW('a', ATMIOC_SARCOM+1, struct compat_atmif_sioc) +#define ATM_GETLOOP32 _IOW('a', ATMIOC_SARCOM+2, struct compat_atmif_sioc) +#define ATM_SETLOOP32 _IOW('a', ATMIOC_SARCOM+3, struct compat_atmif_sioc) +#define ATM_QUERYLOOP32 _IOW('a', ATMIOC_SARCOM+4, struct compat_atmif_sioc) + +static struct { + unsigned int cmd32; + unsigned int cmd; +} atm_ioctl_map[] = { + { ATM_GETLINKRATE32, ATM_GETLINKRATE }, + { ATM_GETNAMES32, ATM_GETNAMES }, + { ATM_GETTYPE32, ATM_GETTYPE }, + { ATM_GETESI32, ATM_GETESI }, + { ATM_GETADDR32, ATM_GETADDR }, + { ATM_RSTADDR32, ATM_RSTADDR }, + { ATM_ADDADDR32, ATM_ADDADDR }, + { ATM_DELADDR32, ATM_DELADDR }, + { ATM_GETCIRANGE32, ATM_GETCIRANGE }, + { ATM_SETCIRANGE32, ATM_SETCIRANGE }, + { ATM_SETESI32, ATM_SETESI }, + { ATM_SETESIF32, ATM_SETESIF }, + { ATM_GETSTAT32, ATM_GETSTAT }, + { ATM_GETSTATZ32, ATM_GETSTATZ }, + { ATM_GETLOOP32, ATM_GETLOOP }, + { ATM_SETLOOP32, ATM_SETLOOP }, + { ATM_QUERYLOOP32, ATM_QUERYLOOP }, +}; + +#define NR_ATM_IOCTL ARRAY_SIZE(atm_ioctl_map) + +static int do_atm_iobuf(struct socket *sock, unsigned int cmd, + unsigned long arg) +{ + struct atm_iobuf __user *iobuf; + struct compat_atm_iobuf __user *iobuf32; + u32 data; + void __user *datap; + int len, err; + + iobuf = compat_alloc_user_space(sizeof(*iobuf)); + iobuf32 = compat_ptr(arg); + + if (get_user(len, &iobuf32->length) || + get_user(data, &iobuf32->buffer)) + return -EFAULT; + datap = compat_ptr(data); + if (put_user(len, &iobuf->length) || + put_user(datap, &iobuf->buffer)) + return -EFAULT; + + err = do_vcc_ioctl(sock, cmd, (unsigned long) iobuf, 0); + + if (!err) { + if (copy_in_user(&iobuf32->length, &iobuf->length, + sizeof(int))) + err = -EFAULT; + } + + return err; +} + +static int do_atmif_sioc(struct socket *sock, unsigned int cmd, + unsigned long arg) +{ + struct atmif_sioc __user *sioc; + struct compat_atmif_sioc __user *sioc32; + u32 data; + void __user *datap; + int err; + + sioc = compat_alloc_user_space(sizeof(*sioc)); + sioc32 = compat_ptr(arg); + + if (copy_in_user(&sioc->number, &sioc32->number, 2 * sizeof(int)) + || get_user(data, &sioc32->arg)) + return -EFAULT; + datap = compat_ptr(data); + if (put_user(datap, &sioc->arg)) + return -EFAULT; + + err = do_vcc_ioctl(sock, cmd, (unsigned long) sioc, 0); + + if (!err) { + if (copy_in_user(&sioc32->length, &sioc->length, + sizeof(int))) + err = -EFAULT; + } + return err; +} + +static int do_atm_ioctl(struct socket *sock, unsigned int cmd32, + unsigned long arg) +{ + int i; + unsigned int cmd = 0; + + switch (cmd32) { + case SONET_GETSTAT: + case SONET_GETSTATZ: + case SONET_GETDIAG: + case SONET_SETDIAG: + case SONET_CLRDIAG: + case SONET_SETFRAMING: + case SONET_GETFRAMING: + case SONET_GETFRSENSE: + return do_atmif_sioc(sock, cmd32, arg); + } + + for (i = 0; i < NR_ATM_IOCTL; i++) { + if (cmd32 == atm_ioctl_map[i].cmd32) { + cmd = atm_ioctl_map[i].cmd; + break; + } + } + if (i == NR_ATM_IOCTL) + return -EINVAL; + + switch (cmd) { + case ATM_GETNAMES: + return do_atm_iobuf(sock, cmd, arg); + + case ATM_GETLINKRATE: + case ATM_GETTYPE: + case ATM_GETESI: + case ATM_GETADDR: + case ATM_RSTADDR: + case ATM_ADDADDR: + case ATM_DELADDR: + case ATM_GETCIRANGE: + case ATM_SETCIRANGE: + case ATM_SETESI: + case ATM_SETESIF: + case ATM_GETSTAT: + case ATM_GETSTATZ: + case ATM_GETLOOP: + case ATM_SETLOOP: + case ATM_QUERYLOOP: + return do_atmif_sioc(sock, cmd, arg); + } + + return -EINVAL; +} + +int vcc_compat_ioctl(struct socket *sock, unsigned int cmd, + unsigned long arg) { - return do_vcc_ioctl(sock, cmd, arg, 1); + int ret; + + ret = do_vcc_ioctl(sock, cmd, arg, 1); + if (ret != -ENOIOCTLCMD) + return ret; + + return do_atm_ioctl(sock, cmd, arg); } #endif diff --git a/net/atm/pvc.c b/net/atm/pvc.c index d4c024504f99..8d74e62b0d79 100644 --- a/net/atm/pvc.c +++ b/net/atm/pvc.c @@ -127,7 +127,8 @@ static const struct proto_ops pvc_proto_ops = { }; -static int pvc_create(struct net *net, struct socket *sock,int protocol) +static int pvc_create(struct net *net, struct socket *sock, int protocol, + int kern) { if (net != &init_net) return -EAFNOSUPPORT; @@ -137,7 +138,7 @@ static int pvc_create(struct net *net, struct socket *sock,int protocol) } -static struct net_proto_family pvc_family_ops = { +static const struct net_proto_family pvc_family_ops = { .family = PF_ATMPVC, .create = pvc_create, .owner = THIS_MODULE, diff --git a/net/atm/svc.c b/net/atm/svc.c index f90d143c4b25..66e1d9b3e5de 100644 --- a/net/atm/svc.c +++ b/net/atm/svc.c @@ -25,7 +25,7 @@ #include "signaling.h" #include "addr.h" -static int svc_create(struct net *net, struct socket *sock,int protocol); +static int svc_create(struct net *net, struct socket *sock, int protocol, int kern); /* * Note: since all this is still nicely synchronized with the signaling demon, @@ -330,7 +330,7 @@ static int svc_accept(struct socket *sock,struct socket *newsock,int flags) lock_sock(sk); - error = svc_create(sock_net(sk), newsock,0); + error = svc_create(sock_net(sk), newsock, 0, 0); if (error) goto out; @@ -650,11 +650,12 @@ static const struct proto_ops svc_proto_ops = { }; -static int svc_create(struct net *net, struct socket *sock,int protocol) +static int svc_create(struct net *net, struct socket *sock, int protocol, + int kern) { int error; - if (net != &init_net) + if (!net_eq(net, &init_net)) return -EAFNOSUPPORT; sock->ops = &svc_proto_ops; @@ -666,7 +667,7 @@ static int svc_create(struct net *net, struct socket *sock,int protocol) } -static struct net_proto_family svc_family_ops = { +static const struct net_proto_family svc_family_ops = { .family = PF_ATMSVC, .create = svc_create, .owner = THIS_MODULE, diff --git a/net/ax25/af_ax25.c b/net/ax25/af_ax25.c index f45460730371..5588ba69c468 100644 --- a/net/ax25/af_ax25.c +++ b/net/ax25/af_ax25.c @@ -369,6 +369,9 @@ static int ax25_ctl_ioctl(const unsigned int cmd, void __user *arg) if (ax25_ctl.digi_count > AX25_MAX_DIGIS) return -EINVAL; + if (ax25_ctl.arg > ULONG_MAX / HZ && ax25_ctl.cmd != AX25_KILL) + return -EINVAL; + digi.ndigi = ax25_ctl.digi_count; for (k = 0; k < digi.ndigi; k++) digi.calls[k] = ax25_ctl.digi_addr[k]; @@ -418,14 +421,10 @@ static int ax25_ctl_ioctl(const unsigned int cmd, void __user *arg) break; case AX25_T3: - if (ax25_ctl.arg < 0) - goto einval_put; ax25->t3 = ax25_ctl.arg * HZ; break; case AX25_IDLE: - if (ax25_ctl.arg < 0) - goto einval_put; ax25->idle = ax25_ctl.arg * 60 * HZ; break; @@ -800,12 +799,13 @@ static struct proto ax25_proto = { .obj_size = sizeof(struct sock), }; -static int ax25_create(struct net *net, struct socket *sock, int protocol) +static int ax25_create(struct net *net, struct socket *sock, int protocol, + int kern) { struct sock *sk; ax25_cb *ax25; - if (net != &init_net) + if (!net_eq(net, &init_net)) return -EAFNOSUPPORT; switch (sock->type) { @@ -1961,7 +1961,7 @@ static const struct file_operations ax25_info_fops = { #endif -static struct net_proto_family ax25_family_ops = { +static const struct net_proto_family ax25_family_ops = { .family = PF_AX25, .create = ax25_create, .owner = THIS_MODULE, diff --git a/net/bluetooth/af_bluetooth.c b/net/bluetooth/af_bluetooth.c index 8cfb5a849841..087cc51f5927 100644 --- a/net/bluetooth/af_bluetooth.c +++ b/net/bluetooth/af_bluetooth.c @@ -45,7 +45,7 @@ /* Bluetooth sockets */ #define BT_MAX_PROTO 8 -static struct net_proto_family *bt_proto[BT_MAX_PROTO]; +static const struct net_proto_family *bt_proto[BT_MAX_PROTO]; static DEFINE_RWLOCK(bt_proto_lock); static struct lock_class_key bt_lock_key[BT_MAX_PROTO]; @@ -86,7 +86,7 @@ static inline void bt_sock_reclassify_lock(struct socket *sock, int proto) bt_key_strings[proto], &bt_lock_key[proto]); } -int bt_sock_register(int proto, struct net_proto_family *ops) +int bt_sock_register(int proto, const struct net_proto_family *ops) { int err = 0; @@ -126,7 +126,8 @@ int bt_sock_unregister(int proto) } EXPORT_SYMBOL(bt_sock_unregister); -static int bt_sock_create(struct net *net, struct socket *sock, int proto) +static int bt_sock_create(struct net *net, struct socket *sock, int proto, + int kern) { int err; @@ -144,7 +145,7 @@ static int bt_sock_create(struct net *net, struct socket *sock, int proto) read_lock(&bt_proto_lock); if (bt_proto[proto] && try_module_get(bt_proto[proto]->owner)) { - err = bt_proto[proto]->create(net, sock, proto); + err = bt_proto[proto]->create(net, sock, proto, kern); bt_sock_reclassify_lock(sock, proto); module_put(bt_proto[proto]->owner); } @@ -257,7 +258,7 @@ int bt_sock_recvmsg(struct kiocb *iocb, struct socket *sock, skb_reset_transport_header(skb); err = skb_copy_datagram_iovec(skb, 0, msg->msg_iov, copied); if (err == 0) - sock_recv_timestamp(msg, sk, skb); + sock_recv_ts_and_drops(msg, sk, skb); skb_free_datagram(sk, skb); diff --git a/net/bluetooth/bnep/core.c b/net/bluetooth/bnep/core.c index cafe9f54d841..29b1b220d6cf 100644 --- a/net/bluetooth/bnep/core.c +++ b/net/bluetooth/bnep/core.c @@ -230,7 +230,6 @@ static int bnep_rx_control(struct bnep_session *s, void *data, int len) switch (cmd) { case BNEP_CMD_NOT_UNDERSTOOD: - case BNEP_SETUP_CONN_REQ: case BNEP_SETUP_CONN_RSP: case BNEP_FILTER_NET_TYPE_RSP: case BNEP_FILTER_MULTI_ADDR_RSP: @@ -245,6 +244,10 @@ static int bnep_rx_control(struct bnep_session *s, void *data, int len) err = bnep_ctrl_set_mcfilter(s, data, len); break; + case BNEP_SETUP_CONN_REQ: + err = bnep_send_rsp(s, BNEP_SETUP_CONN_RSP, BNEP_CONN_NOT_ALLOWED); + break; + default: { u8 pkt[3]; pkt[0] = BNEP_CONTROL; diff --git a/net/bluetooth/bnep/sock.c b/net/bluetooth/bnep/sock.c index e857628b0b27..2ff6ac7b2ed4 100644 --- a/net/bluetooth/bnep/sock.c +++ b/net/bluetooth/bnep/sock.c @@ -195,7 +195,8 @@ static struct proto bnep_proto = { .obj_size = sizeof(struct bt_sock) }; -static int bnep_sock_create(struct net *net, struct socket *sock, int protocol) +static int bnep_sock_create(struct net *net, struct socket *sock, int protocol, + int kern) { struct sock *sk; @@ -222,7 +223,7 @@ static int bnep_sock_create(struct net *net, struct socket *sock, int protocol) return 0; } -static struct net_proto_family bnep_sock_family_ops = { +static const struct net_proto_family bnep_sock_family_ops = { .family = PF_BLUETOOTH, .owner = THIS_MODULE, .create = bnep_sock_create diff --git a/net/bluetooth/cmtp/sock.c b/net/bluetooth/cmtp/sock.c index 16b0fad74f6e..978cc3a718ad 100644 --- a/net/bluetooth/cmtp/sock.c +++ b/net/bluetooth/cmtp/sock.c @@ -190,7 +190,8 @@ static struct proto cmtp_proto = { .obj_size = sizeof(struct bt_sock) }; -static int cmtp_sock_create(struct net *net, struct socket *sock, int protocol) +static int cmtp_sock_create(struct net *net, struct socket *sock, int protocol, + int kern) { struct sock *sk; @@ -217,7 +218,7 @@ static int cmtp_sock_create(struct net *net, struct socket *sock, int protocol) return 0; } -static struct net_proto_family cmtp_sock_family_ops = { +static const struct net_proto_family cmtp_sock_family_ops = { .family = PF_BLUETOOTH, .owner = THIS_MODULE, .create = cmtp_sock_create diff --git a/net/bluetooth/hci_core.c b/net/bluetooth/hci_core.c index e1da8f68759c..94ba34982021 100644 --- a/net/bluetooth/hci_core.c +++ b/net/bluetooth/hci_core.c @@ -193,8 +193,9 @@ static void hci_init_req(struct hci_dev *hdev, unsigned long opt) while ((skb = skb_dequeue(&hdev->driver_init))) { bt_cb(skb)->pkt_type = HCI_COMMAND_PKT; skb->dev = (void *) hdev; + skb_queue_tail(&hdev->cmd_q, skb); - hci_sched_cmd(hdev); + tasklet_schedule(&hdev->cmd_task); } skb_queue_purge(&hdev->driver_init); @@ -987,6 +988,30 @@ int hci_resume_dev(struct hci_dev *hdev) } EXPORT_SYMBOL(hci_resume_dev); +/* Receive frame from HCI drivers */ +int hci_recv_frame(struct sk_buff *skb) +{ + struct hci_dev *hdev = (struct hci_dev *) skb->dev; + if (!hdev || (!test_bit(HCI_UP, &hdev->flags) + && !test_bit(HCI_INIT, &hdev->flags))) { + kfree_skb(skb); + return -ENXIO; + } + + /* Incomming skb */ + bt_cb(skb)->incoming = 1; + + /* Time stamp */ + __net_timestamp(skb); + + /* Queue frame for rx task */ + skb_queue_tail(&hdev->rx_q, skb); + tasklet_schedule(&hdev->rx_task); + + return 0; +} +EXPORT_SYMBOL(hci_recv_frame); + /* Receive packet type fragment */ #define __reassembly(hdev, type) ((hdev)->reassembly[(type) - 2]) @@ -1193,8 +1218,9 @@ int hci_send_cmd(struct hci_dev *hdev, __u16 opcode, __u32 plen, void *param) bt_cb(skb)->pkt_type = HCI_COMMAND_PKT; skb->dev = (void *) hdev; + skb_queue_tail(&hdev->cmd_q, skb); - hci_sched_cmd(hdev); + tasklet_schedule(&hdev->cmd_task); return 0; } @@ -1271,7 +1297,8 @@ int hci_send_acl(struct hci_conn *conn, struct sk_buff *skb, __u16 flags) spin_unlock_bh(&conn->data_q.lock); } - hci_sched_tx(hdev); + tasklet_schedule(&hdev->tx_task); + return 0; } EXPORT_SYMBOL(hci_send_acl); @@ -1298,8 +1325,10 @@ int hci_send_sco(struct hci_conn *conn, struct sk_buff *skb) skb->dev = (void *) hdev; bt_cb(skb)->pkt_type = HCI_SCODATA_PKT; + skb_queue_tail(&conn->data_q, skb); - hci_sched_tx(hdev); + tasklet_schedule(&hdev->tx_task); + return 0; } EXPORT_SYMBOL(hci_send_sco); @@ -1612,7 +1641,7 @@ static void hci_cmd_task(unsigned long arg) hdev->cmd_last_tx = jiffies; } else { skb_queue_head(&hdev->cmd_q, skb); - hci_sched_cmd(hdev); + tasklet_schedule(&hdev->cmd_task); } } } diff --git a/net/bluetooth/hci_event.c b/net/bluetooth/hci_event.c index e99fe385fba2..28517bad796c 100644 --- a/net/bluetooth/hci_event.c +++ b/net/bluetooth/hci_event.c @@ -1320,7 +1320,7 @@ static inline void hci_cmd_complete_evt(struct hci_dev *hdev, struct sk_buff *sk if (ev->ncmd) { atomic_set(&hdev->cmd_cnt, 1); if (!skb_queue_empty(&hdev->cmd_q)) - hci_sched_cmd(hdev); + tasklet_schedule(&hdev->cmd_task); } } @@ -1386,7 +1386,7 @@ static inline void hci_cmd_status_evt(struct hci_dev *hdev, struct sk_buff *skb) if (ev->ncmd) { atomic_set(&hdev->cmd_cnt, 1); if (!skb_queue_empty(&hdev->cmd_q)) - hci_sched_cmd(hdev); + tasklet_schedule(&hdev->cmd_task); } } @@ -1454,7 +1454,7 @@ static inline void hci_num_comp_pkts_evt(struct hci_dev *hdev, struct sk_buff *s } } - hci_sched_tx(hdev); + tasklet_schedule(&hdev->tx_task); tasklet_enable(&hdev->tx_task); } diff --git a/net/bluetooth/hci_sock.c b/net/bluetooth/hci_sock.c index 75302a986067..688cfebfbee0 100644 --- a/net/bluetooth/hci_sock.c +++ b/net/bluetooth/hci_sock.c @@ -414,6 +414,11 @@ static int hci_sock_sendmsg(struct kiocb *iocb, struct socket *sock, goto done; } + if (!test_bit(HCI_UP, &hdev->flags)) { + err = -ENETDOWN; + goto done; + } + if (!(skb = bt_skb_send_alloc(sk, len, msg->msg_flags & MSG_DONTWAIT, &err))) goto done; @@ -440,10 +445,10 @@ static int hci_sock_sendmsg(struct kiocb *iocb, struct socket *sock, if (test_bit(HCI_RAW, &hdev->flags) || (ogf == 0x3f)) { skb_queue_tail(&hdev->raw_q, skb); - hci_sched_tx(hdev); + tasklet_schedule(&hdev->tx_task); } else { skb_queue_tail(&hdev->cmd_q, skb); - hci_sched_cmd(hdev); + tasklet_schedule(&hdev->cmd_task); } } else { if (!capable(CAP_NET_RAW)) { @@ -452,7 +457,7 @@ static int hci_sock_sendmsg(struct kiocb *iocb, struct socket *sock, } skb_queue_tail(&hdev->raw_q, skb); - hci_sched_tx(hdev); + tasklet_schedule(&hdev->tx_task); } err = len; @@ -621,7 +626,8 @@ static struct proto hci_sk_proto = { .obj_size = sizeof(struct hci_pinfo) }; -static int hci_sock_create(struct net *net, struct socket *sock, int protocol) +static int hci_sock_create(struct net *net, struct socket *sock, int protocol, + int kern) { struct sock *sk; @@ -687,7 +693,7 @@ static int hci_sock_dev_event(struct notifier_block *this, unsigned long event, return NOTIFY_DONE; } -static struct net_proto_family hci_sock_family_ops = { +static const struct net_proto_family hci_sock_family_ops = { .family = PF_BLUETOOTH, .owner = THIS_MODULE, .create = hci_sock_create, diff --git a/net/bluetooth/hidp/core.c b/net/bluetooth/hidp/core.c index 49d8495d69be..569750010fd3 100644 --- a/net/bluetooth/hidp/core.c +++ b/net/bluetooth/hidp/core.c @@ -280,6 +280,13 @@ static int hidp_send_report(struct hidp_session *session, struct hid_report *rep return hidp_queue_report(session, buf, rsize); } +static int hidp_output_raw_report(struct hid_device *hid, unsigned char *data, size_t count) +{ + if (hidp_queue_report(hid->driver_data, data, count)) + return -ENOMEM; + return count; +} + static void hidp_idle_timeout(unsigned long arg) { struct hidp_session *session = (struct hidp_session *) arg; @@ -785,6 +792,8 @@ static int hidp_setup_hid(struct hidp_session *session, hid->dev.parent = hidp_get_device(session); hid->ll_driver = &hidp_hid_driver; + hid->hid_output_raw_report = hidp_output_raw_report; + err = hid_add_device(hid); if (err < 0) goto failed; diff --git a/net/bluetooth/hidp/sock.c b/net/bluetooth/hidp/sock.c index 37c9d7d2e688..9cfef68b9fec 100644 --- a/net/bluetooth/hidp/sock.c +++ b/net/bluetooth/hidp/sock.c @@ -241,7 +241,8 @@ static struct proto hidp_proto = { .obj_size = sizeof(struct bt_sock) }; -static int hidp_sock_create(struct net *net, struct socket *sock, int protocol) +static int hidp_sock_create(struct net *net, struct socket *sock, int protocol, + int kern) { struct sock *sk; @@ -268,7 +269,7 @@ static int hidp_sock_create(struct net *net, struct socket *sock, int protocol) return 0; } -static struct net_proto_family hidp_sock_family_ops = { +static const struct net_proto_family hidp_sock_family_ops = { .family = PF_BLUETOOTH, .owner = THIS_MODULE, .create = hidp_sock_create diff --git a/net/bluetooth/l2cap.c b/net/bluetooth/l2cap.c index 947f8bbb4bb3..5129b88c8e5b 100644 --- a/net/bluetooth/l2cap.c +++ b/net/bluetooth/l2cap.c @@ -54,6 +54,7 @@ #define VERSION "2.14" static int enable_ertm = 0; +static int max_transmit = L2CAP_DEFAULT_MAX_TX; static u32 l2cap_feat_mask = L2CAP_FEAT_FIXED_CHAN; static u8 l2cap_fixed_chan[8] = { 0x02, }; @@ -373,6 +374,8 @@ static inline int l2cap_send_rr_or_rnr(struct l2cap_pinfo *pi, u16 control) else control |= L2CAP_SUPER_RCV_READY; + control |= pi->buffer_seq << L2CAP_CTRL_REQSEQ_SHIFT; + return l2cap_send_sframe(pi, control); } @@ -819,7 +822,8 @@ static struct sock *l2cap_sock_alloc(struct net *net, struct socket *sock, int p return sk; } -static int l2cap_sock_create(struct net *net, struct socket *sock, int protocol) +static int l2cap_sock_create(struct net *net, struct socket *sock, int protocol, + int kern) { struct sock *sk; @@ -831,7 +835,7 @@ static int l2cap_sock_create(struct net *net, struct socket *sock, int protocol) sock->type != SOCK_DGRAM && sock->type != SOCK_RAW) return -ESOCKTNOSUPPORT; - if (sock->type == SOCK_RAW && !capable(CAP_NET_RAW)) + if (sock->type == SOCK_RAW && !kern && !capable(CAP_NET_RAW)) return -EPERM; sock->ops = &l2cap_sock_ops; @@ -1332,7 +1336,7 @@ static int l2cap_retransmit_frame(struct sock *sk, u8 tx_seq) tx_skb = skb_clone(skb, GFP_ATOMIC); bt_cb(skb)->retries++; control = get_unaligned_le16(tx_skb->data + L2CAP_HDR_SIZE); - control |= (pi->req_seq << L2CAP_CTRL_REQSEQ_SHIFT) + control |= (pi->buffer_seq << L2CAP_CTRL_REQSEQ_SHIFT) | (tx_seq << L2CAP_CTRL_TXSEQ_SHIFT); put_unaligned_le16(control, tx_skb->data + L2CAP_HDR_SIZE); @@ -1361,8 +1365,8 @@ static int l2cap_ertm_send(struct sock *sk) if (pi->conn_state & L2CAP_CONN_WAIT_F) return 0; - while ((skb = sk->sk_send_head) && (!l2cap_tx_window_full(sk)) - && !(pi->conn_state & L2CAP_CONN_REMOTE_BUSY)) { + while ((skb = sk->sk_send_head) && (!l2cap_tx_window_full(sk)) && + !(pi->conn_state & L2CAP_CONN_REMOTE_BUSY)) { tx_skb = skb_clone(skb, GFP_ATOMIC); if (pi->remote_max_tx && @@ -1374,7 +1378,7 @@ static int l2cap_ertm_send(struct sock *sk) bt_cb(skb)->retries++; control = get_unaligned_le16(tx_skb->data + L2CAP_HDR_SIZE); - control |= (pi->req_seq << L2CAP_CTRL_REQSEQ_SHIFT) + control |= (pi->buffer_seq << L2CAP_CTRL_REQSEQ_SHIFT) | (pi->next_tx_seq << L2CAP_CTRL_TXSEQ_SHIFT); put_unaligned_le16(control, tx_skb->data + L2CAP_HDR_SIZE); @@ -1603,8 +1607,8 @@ static int l2cap_sock_sendmsg(struct kiocb *iocb, struct socket *sock, struct ms return -EOPNOTSUPP; /* Check outgoing MTU */ - if (sk->sk_type == SOCK_SEQPACKET && pi->mode == L2CAP_MODE_BASIC - && len > pi->omtu) + if (sk->sk_type == SOCK_SEQPACKET && pi->mode == L2CAP_MODE_BASIC && + len > pi->omtu) return -EINVAL; lock_sock(sk); @@ -2172,6 +2176,21 @@ static void l2cap_add_conf_opt(void **ptr, u8 type, u8 len, unsigned long val) *ptr += L2CAP_CONF_OPT_SIZE + len; } +static inline void l2cap_ertm_init(struct sock *sk) +{ + l2cap_pi(sk)->expected_ack_seq = 0; + l2cap_pi(sk)->unacked_frames = 0; + l2cap_pi(sk)->buffer_seq = 0; + l2cap_pi(sk)->num_to_ack = 0; + + setup_timer(&l2cap_pi(sk)->retrans_timer, + l2cap_retrans_timeout, (unsigned long) sk); + setup_timer(&l2cap_pi(sk)->monitor_timer, + l2cap_monitor_timeout, (unsigned long) sk); + + __skb_queue_head_init(SREJ_QUEUE(sk)); +} + static int l2cap_mode_supported(__u8 mode, __u32 feat_mask) { u32 local_feat_mask = l2cap_feat_mask; @@ -2235,7 +2254,7 @@ done: case L2CAP_MODE_ERTM: rfc.mode = L2CAP_MODE_ERTM; rfc.txwin_size = L2CAP_DEFAULT_TX_WINDOW; - rfc.max_transmit = L2CAP_DEFAULT_MAX_TX; + rfc.max_transmit = max_transmit; rfc.retrans_timeout = 0; rfc.monitor_timeout = 0; rfc.max_pdu_size = cpu_to_le16(L2CAP_DEFAULT_MAX_PDU_SIZE); @@ -2755,22 +2774,18 @@ static inline int l2cap_config_req(struct l2cap_conn *conn, struct l2cap_cmd_hdr goto unlock; if (l2cap_pi(sk)->conf_state & L2CAP_CONF_INPUT_DONE) { - if (!(l2cap_pi(sk)->conf_state & L2CAP_CONF_NO_FCS_RECV) - || l2cap_pi(sk)->fcs != L2CAP_FCS_NONE) + if (!(l2cap_pi(sk)->conf_state & L2CAP_CONF_NO_FCS_RECV) || + l2cap_pi(sk)->fcs != L2CAP_FCS_NONE) l2cap_pi(sk)->fcs = L2CAP_FCS_CRC16; sk->sk_state = BT_CONNECTED; - l2cap_pi(sk)->next_tx_seq = 0; - l2cap_pi(sk)->expected_ack_seq = 0; - l2cap_pi(sk)->unacked_frames = 0; - - setup_timer(&l2cap_pi(sk)->retrans_timer, - l2cap_retrans_timeout, (unsigned long) sk); - setup_timer(&l2cap_pi(sk)->monitor_timer, - l2cap_monitor_timeout, (unsigned long) sk); + l2cap_pi(sk)->next_tx_seq = 0; + l2cap_pi(sk)->expected_tx_seq = 0; __skb_queue_head_init(TX_QUEUE(sk)); - __skb_queue_head_init(SREJ_QUEUE(sk)); + if (l2cap_pi(sk)->mode == L2CAP_MODE_ERTM) + l2cap_ertm_init(sk); + l2cap_chan_ready(sk); goto unlock; } @@ -2844,16 +2859,17 @@ static inline int l2cap_config_rsp(struct l2cap_conn *conn, struct l2cap_cmd_hdr l2cap_pi(sk)->conf_state |= L2CAP_CONF_INPUT_DONE; if (l2cap_pi(sk)->conf_state & L2CAP_CONF_OUTPUT_DONE) { - if (!(l2cap_pi(sk)->conf_state & L2CAP_CONF_NO_FCS_RECV) - || l2cap_pi(sk)->fcs != L2CAP_FCS_NONE) + if (!(l2cap_pi(sk)->conf_state & L2CAP_CONF_NO_FCS_RECV) || + l2cap_pi(sk)->fcs != L2CAP_FCS_NONE) l2cap_pi(sk)->fcs = L2CAP_FCS_CRC16; sk->sk_state = BT_CONNECTED; + l2cap_pi(sk)->next_tx_seq = 0; l2cap_pi(sk)->expected_tx_seq = 0; - l2cap_pi(sk)->buffer_seq = 0; - l2cap_pi(sk)->num_to_ack = 0; __skb_queue_head_init(TX_QUEUE(sk)); - __skb_queue_head_init(SREJ_QUEUE(sk)); + if (l2cap_pi(sk)->mode == L2CAP_MODE_ERTM) + l2cap_ertm_init(sk); + l2cap_chan_ready(sk); } @@ -2885,9 +2901,12 @@ static inline int l2cap_disconnect_req(struct l2cap_conn *conn, struct l2cap_cmd sk->sk_shutdown = SHUTDOWN_MASK; skb_queue_purge(TX_QUEUE(sk)); - skb_queue_purge(SREJ_QUEUE(sk)); - del_timer(&l2cap_pi(sk)->retrans_timer); - del_timer(&l2cap_pi(sk)->monitor_timer); + + if (l2cap_pi(sk)->mode == L2CAP_MODE_ERTM) { + skb_queue_purge(SREJ_QUEUE(sk)); + del_timer(&l2cap_pi(sk)->retrans_timer); + del_timer(&l2cap_pi(sk)->monitor_timer); + } l2cap_chan_del(sk, ECONNRESET); bh_unlock_sock(sk); @@ -2912,9 +2931,12 @@ static inline int l2cap_disconnect_rsp(struct l2cap_conn *conn, struct l2cap_cmd return 0; skb_queue_purge(TX_QUEUE(sk)); - skb_queue_purge(SREJ_QUEUE(sk)); - del_timer(&l2cap_pi(sk)->retrans_timer); - del_timer(&l2cap_pi(sk)->monitor_timer); + + if (l2cap_pi(sk)->mode == L2CAP_MODE_ERTM) { + skb_queue_purge(SREJ_QUEUE(sk)); + del_timer(&l2cap_pi(sk)->retrans_timer); + del_timer(&l2cap_pi(sk)->monitor_timer); + } l2cap_chan_del(sk, 0); bh_unlock_sock(sk); @@ -3279,12 +3301,16 @@ static inline int l2cap_data_channel_iframe(struct sock *sk, u16 rx_control, str { struct l2cap_pinfo *pi = l2cap_pi(sk); u8 tx_seq = __get_txseq(rx_control); + u8 req_seq = __get_reqseq(rx_control); u16 tx_control = 0; u8 sar = rx_control >> L2CAP_CTRL_SAR_SHIFT; int err = 0; BT_DBG("sk %p rx_control 0x%4.4x len %d", sk, rx_control, skb->len); + pi->expected_ack_seq = req_seq; + l2cap_drop_acked_frames(sk); + if (tx_seq == pi->expected_tx_seq) goto expected; @@ -3339,6 +3365,16 @@ expected: return 0; } + if (rx_control & L2CAP_CTRL_FINAL) { + if (pi->conn_state & L2CAP_CONN_REJ_ACT) + pi->conn_state &= ~L2CAP_CONN_REJ_ACT; + else { + sk->sk_send_head = TX_QUEUE(sk)->next; + pi->next_tx_seq = pi->expected_ack_seq; + l2cap_ertm_send(sk); + } + } + pi->buffer_seq = (pi->buffer_seq + 1) % 64; err = l2cap_sar_reassembly_sdu(sk, skb, rx_control); @@ -3375,6 +3411,14 @@ static inline int l2cap_data_channel_sframe(struct sock *sk, u16 rx_control, str pi->expected_ack_seq = tx_seq; l2cap_drop_acked_frames(sk); + if (pi->conn_state & L2CAP_CONN_REJ_ACT) + pi->conn_state &= ~L2CAP_CONN_REJ_ACT; + else { + sk->sk_send_head = TX_QUEUE(sk)->next; + pi->next_tx_seq = pi->expected_ack_seq; + l2cap_ertm_send(sk); + } + if (!(pi->conn_state & L2CAP_CONN_WAIT_F)) break; @@ -3387,8 +3431,8 @@ static inline int l2cap_data_channel_sframe(struct sock *sk, u16 rx_control, str pi->expected_ack_seq = tx_seq; l2cap_drop_acked_frames(sk); - if ((pi->conn_state & L2CAP_CONN_REMOTE_BUSY) - && (pi->unacked_frames > 0)) + if ((pi->conn_state & L2CAP_CONN_REMOTE_BUSY) && + (pi->unacked_frames > 0)) __mod_retrans_timer(); l2cap_ertm_send(sk); @@ -3402,10 +3446,24 @@ static inline int l2cap_data_channel_sframe(struct sock *sk, u16 rx_control, str pi->expected_ack_seq = __get_reqseq(rx_control); l2cap_drop_acked_frames(sk); - sk->sk_send_head = TX_QUEUE(sk)->next; - pi->next_tx_seq = pi->expected_ack_seq; + if (rx_control & L2CAP_CTRL_FINAL) { + if (pi->conn_state & L2CAP_CONN_REJ_ACT) + pi->conn_state &= ~L2CAP_CONN_REJ_ACT; + else { + sk->sk_send_head = TX_QUEUE(sk)->next; + pi->next_tx_seq = pi->expected_ack_seq; + l2cap_ertm_send(sk); + } + } else { + sk->sk_send_head = TX_QUEUE(sk)->next; + pi->next_tx_seq = pi->expected_ack_seq; + l2cap_ertm_send(sk); - l2cap_ertm_send(sk); + if (pi->conn_state & L2CAP_CONN_WAIT_F) { + pi->srej_save_reqseq = tx_seq; + pi->conn_state |= L2CAP_CONN_REJ_ACT; + } + } break; @@ -3424,7 +3482,7 @@ static inline int l2cap_data_channel_sframe(struct sock *sk, u16 rx_control, str } else if (rx_control & L2CAP_CTRL_FINAL) { if ((pi->conn_state & L2CAP_CONN_SREJ_ACT) && pi->srej_save_reqseq == tx_seq) - pi->srej_save_reqseq &= ~L2CAP_CONN_SREJ_ACT; + pi->conn_state &= ~L2CAP_CONN_SREJ_ACT; else l2cap_retransmit_frame(sk, tx_seq); } @@ -3924,7 +3982,7 @@ static const struct proto_ops l2cap_sock_ops = { .getsockopt = l2cap_sock_getsockopt }; -static struct net_proto_family l2cap_sock_family_ops = { +static const struct net_proto_family l2cap_sock_family_ops = { .family = PF_BLUETOOTH, .owner = THIS_MODULE, .create = l2cap_sock_create, @@ -4003,6 +4061,9 @@ module_exit(l2cap_exit); module_param(enable_ertm, bool, 0644); MODULE_PARM_DESC(enable_ertm, "Enable enhanced retransmission mode"); +module_param(max_transmit, uint, 0644); +MODULE_PARM_DESC(max_transmit, "Max transmit value (default = 3)"); + MODULE_AUTHOR("Marcel Holtmann <marcel@holtmann.org>"); MODULE_DESCRIPTION("Bluetooth L2CAP ver " VERSION); MODULE_VERSION(VERSION); diff --git a/net/bluetooth/rfcomm/core.c b/net/bluetooth/rfcomm/core.c index 25692bc0a342..fc5ee3296e22 100644 --- a/net/bluetooth/rfcomm/core.c +++ b/net/bluetooth/rfcomm/core.c @@ -51,6 +51,7 @@ static int disable_cfc = 0; static int channel_mtu = -1; static unsigned int l2cap_mtu = RFCOMM_MAX_L2CAP_MTU; +static int l2cap_ertm = 0; static struct task_struct *rfcomm_thread; @@ -702,6 +703,8 @@ static struct rfcomm_session *rfcomm_session_create(bdaddr_t *src, bdaddr_t *dst sk = sock->sk; lock_sock(sk); l2cap_pi(sk)->imtu = l2cap_mtu; + if (l2cap_ertm) + l2cap_pi(sk)->mode = L2CAP_MODE_ERTM; release_sock(sk); s = rfcomm_session_add(sock, BT_BOUND); @@ -2185,6 +2188,9 @@ MODULE_PARM_DESC(channel_mtu, "Default MTU for the RFCOMM channel"); module_param(l2cap_mtu, uint, 0644); MODULE_PARM_DESC(l2cap_mtu, "Default MTU for the L2CAP connection"); +module_param(l2cap_ertm, bool, 0644); +MODULE_PARM_DESC(l2cap_ertm, "Use L2CAP ERTM mode for connection"); + MODULE_AUTHOR("Marcel Holtmann <marcel@holtmann.org>"); MODULE_DESCRIPTION("Bluetooth RFCOMM ver " VERSION); MODULE_VERSION(VERSION); diff --git a/net/bluetooth/rfcomm/sock.c b/net/bluetooth/rfcomm/sock.c index 8a20aaf1f231..4b5968dda673 100644 --- a/net/bluetooth/rfcomm/sock.c +++ b/net/bluetooth/rfcomm/sock.c @@ -323,7 +323,8 @@ static struct sock *rfcomm_sock_alloc(struct net *net, struct socket *sock, int return sk; } -static int rfcomm_sock_create(struct net *net, struct socket *sock, int protocol) +static int rfcomm_sock_create(struct net *net, struct socket *sock, + int protocol, int kern) { struct sock *sk; @@ -703,7 +704,7 @@ static int rfcomm_sock_recvmsg(struct kiocb *iocb, struct socket *sock, copied += chunk; size -= chunk; - sock_recv_timestamp(msg, sk, skb); + sock_recv_ts_and_drops(msg, sk, skb); if (!(flags & MSG_PEEK)) { atomic_sub(chunk, &sk->sk_rmem_alloc); @@ -1101,7 +1102,7 @@ static const struct proto_ops rfcomm_sock_ops = { .mmap = sock_no_mmap }; -static struct net_proto_family rfcomm_sock_family_ops = { +static const struct net_proto_family rfcomm_sock_family_ops = { .family = PF_BLUETOOTH, .owner = THIS_MODULE, .create = rfcomm_sock_create diff --git a/net/bluetooth/sco.c b/net/bluetooth/sco.c index 77f4153bdb5e..dd8f6ec57dce 100644 --- a/net/bluetooth/sco.c +++ b/net/bluetooth/sco.c @@ -430,7 +430,8 @@ static struct sock *sco_sock_alloc(struct net *net, struct socket *sock, int pro return sk; } -static int sco_sock_create(struct net *net, struct socket *sock, int protocol) +static int sco_sock_create(struct net *net, struct socket *sock, int protocol, + int kern) { struct sock *sk; @@ -993,7 +994,7 @@ static const struct proto_ops sco_sock_ops = { .getsockopt = sco_sock_getsockopt }; -static struct net_proto_family sco_sock_family_ops = { +static const struct net_proto_family sco_sock_family_ops = { .family = PF_BLUETOOTH, .owner = THIS_MODULE, .create = sco_sock_create, diff --git a/net/bridge/br_device.c b/net/bridge/br_device.c index 07a07770c8b6..1a99c4e04e85 100644 --- a/net/bridge/br_device.c +++ b/net/bridge/br_device.c @@ -157,6 +157,7 @@ static const struct ethtool_ops br_ethtool_ops = { .get_tso = ethtool_op_get_tso, .set_tso = br_set_tso, .get_ufo = ethtool_op_get_ufo, + .set_ufo = ethtool_op_set_ufo, .get_flags = ethtool_op_get_flags, }; diff --git a/net/bridge/br_fdb.c b/net/bridge/br_fdb.c index 57bf05c353bc..3b8e038ab32c 100644 --- a/net/bridge/br_fdb.c +++ b/net/bridge/br_fdb.c @@ -60,8 +60,8 @@ static inline unsigned long hold_time(const struct net_bridge *br) static inline int has_expired(const struct net_bridge *br, const struct net_bridge_fdb_entry *fdb) { - return !fdb->is_static - && time_before_eq(fdb->ageing_timer + hold_time(br), jiffies); + return !fdb->is_static && + time_before_eq(fdb->ageing_timer + hold_time(br), jiffies); } static inline int br_mac_hash(const unsigned char *mac) diff --git a/net/bridge/br_if.c b/net/bridge/br_if.c index 4a9f52732655..a2cbe61f6e65 100644 --- a/net/bridge/br_if.c +++ b/net/bridge/br_if.c @@ -154,7 +154,7 @@ static void del_nbp(struct net_bridge_port *p) } /* called with RTNL */ -static void del_br(struct net_bridge *br) +static void del_br(struct net_bridge *br, struct list_head *head) { struct net_bridge_port *p, *n; @@ -165,7 +165,7 @@ static void del_br(struct net_bridge *br) del_timer_sync(&br->gc_timer); br_sysfs_delbr(br->dev); - unregister_netdevice(br->dev); + unregister_netdevice_queue(br->dev, head); } static struct net_device *new_bridge_dev(struct net *net, const char *name) @@ -323,7 +323,7 @@ int br_del_bridge(struct net *net, const char *name) } else - del_br(netdev_priv(dev)); + del_br(netdev_priv(dev), NULL); rtnl_unlock(); return ret; @@ -390,6 +390,10 @@ int br_add_if(struct net_bridge *br, struct net_device *dev) if (dev->br_port != NULL) return -EBUSY; + /* No bridging devices that dislike that (e.g. wireless) */ + if (dev->priv_flags & IFF_DONT_BRIDGE) + return -EOPNOTSUPP; + p = new_nbp(br, dev); if (IS_ERR(p)) return PTR_ERR(p); @@ -466,15 +470,14 @@ int br_del_if(struct net_bridge *br, struct net_device *dev) void br_net_exit(struct net *net) { struct net_device *dev; + LIST_HEAD(list); rtnl_lock(); -restart: - for_each_netdev(net, dev) { - if (dev->priv_flags & IFF_EBRIDGE) { - del_br(netdev_priv(dev)); - goto restart; - } - } + for_each_netdev(net, dev) + if (dev->priv_flags & IFF_EBRIDGE) + del_br(netdev_priv(dev), &list); + + unregister_netdevice_many(&list); rtnl_unlock(); } diff --git a/net/bridge/br_ioctl.c b/net/bridge/br_ioctl.c index 6a6433daaf27..2af6e4a90262 100644 --- a/net/bridge/br_ioctl.c +++ b/net/bridge/br_ioctl.c @@ -81,6 +81,7 @@ static int get_fdb_entries(struct net_bridge *br, void __user *userbuf, return num; } +/* called with RTNL */ static int add_del_if(struct net_bridge *br, int ifindex, int isadd) { struct net_device *dev; @@ -89,7 +90,7 @@ static int add_del_if(struct net_bridge *br, int ifindex, int isadd) if (!capable(CAP_NET_ADMIN)) return -EPERM; - dev = dev_get_by_index(dev_net(br->dev), ifindex); + dev = __dev_get_by_index(dev_net(br->dev), ifindex); if (dev == NULL) return -EINVAL; @@ -98,7 +99,6 @@ static int add_del_if(struct net_bridge *br, int ifindex, int isadd) else ret = br_del_if(br, dev); - dev_put(dev); return ret; } diff --git a/net/bridge/br_sysfs_br.c b/net/bridge/br_sysfs_br.c index ee4820aa1843..bee4f300d0c8 100644 --- a/net/bridge/br_sysfs_br.c +++ b/net/bridge/br_sysfs_br.c @@ -316,9 +316,9 @@ static ssize_t store_group_addr(struct device *d, if (new_addr[5] & ~0xf) return -EINVAL; - if (new_addr[5] == 1 /* 802.3x Pause address */ - || new_addr[5] == 2 /* 802.3ad Slow protocols */ - || new_addr[5] == 3) /* 802.1X PAE address */ + if (new_addr[5] == 1 || /* 802.3x Pause address */ + new_addr[5] == 2 || /* 802.3ad Slow protocols */ + new_addr[5] == 3) /* 802.1X PAE address */ return -EINVAL; spin_lock_bh(&br->lock); diff --git a/net/bridge/netfilter/ebt_stp.c b/net/bridge/netfilter/ebt_stp.c index 48527e621626..75e29a9cebda 100644 --- a/net/bridge/netfilter/ebt_stp.c +++ b/net/bridge/netfilter/ebt_stp.c @@ -135,8 +135,8 @@ ebt_stp_mt(const struct sk_buff *skb, const struct xt_match_param *par) if (memcmp(sp, header, sizeof(header))) return false; - if (info->bitmask & EBT_STP_TYPE - && FWINV(info->type != sp->type, EBT_STP_TYPE)) + if (info->bitmask & EBT_STP_TYPE && + FWINV(info->type != sp->type, EBT_STP_TYPE)) return false; if (sp->type == BPDU_TYPE_CONFIG && diff --git a/net/can/af_can.c b/net/can/af_can.c index 606832115674..51adc4c2b860 100644 --- a/net/can/af_can.c +++ b/net/can/af_can.c @@ -114,7 +114,8 @@ static void can_sock_destruct(struct sock *sk) skb_queue_purge(&sk->sk_receive_queue); } -static int can_create(struct net *net, struct socket *sock, int protocol) +static int can_create(struct net *net, struct socket *sock, int protocol, + int kern) { struct sock *sk; struct can_proto *cp; @@ -125,7 +126,7 @@ static int can_create(struct net *net, struct socket *sock, int protocol) if (protocol < 0 || protocol >= CAN_NPROTO) return -EINVAL; - if (net != &init_net) + if (!net_eq(net, &init_net)) return -EAFNOSUPPORT; #ifdef CONFIG_MODULES @@ -160,11 +161,6 @@ static int can_create(struct net *net, struct socket *sock, int protocol) goto errout; } - if (cp->capability >= 0 && !capable(cp->capability)) { - err = -EPERM; - goto errout; - } - sock->ops = cp->ops; sk = sk_alloc(net, PF_CAN, GFP_KERNEL, cp->prot); @@ -379,8 +375,8 @@ static struct hlist_head *find_rcv_list(canid_t *can_id, canid_t *mask, return &d->rx[RX_ALL]; /* extra filterlists for the subscription of a single non-RTR can_id */ - if (((*mask & CAN_EFF_RTR_FLAGS) == CAN_EFF_RTR_FLAGS) - && !(*can_id & CAN_RTR_FLAG)) { + if (((*mask & CAN_EFF_RTR_FLAGS) == CAN_EFF_RTR_FLAGS) && + !(*can_id & CAN_RTR_FLAG)) { if (*can_id & CAN_EFF_FLAG) { if (*mask == (CAN_EFF_MASK | CAN_EFF_RTR_FLAGS)) { @@ -529,8 +525,8 @@ void can_rx_unregister(struct net_device *dev, canid_t can_id, canid_t mask, */ hlist_for_each_entry_rcu(r, next, rl, list) { - if (r->can_id == can_id && r->mask == mask - && r->func == func && r->data == data) + if (r->can_id == can_id && r->mask == mask && + r->func == func && r->data == data) break; } @@ -842,7 +838,7 @@ static struct packet_type can_packet __read_mostly = { .func = can_rcv, }; -static struct net_proto_family can_family_ops __read_mostly = { +static const struct net_proto_family can_family_ops = { .family = PF_CAN, .create = can_create, .owner = THIS_MODULE, diff --git a/net/can/bcm.c b/net/can/bcm.c index e8d58f33fe09..e32af52238a2 100644 --- a/net/can/bcm.c +++ b/net/can/bcm.c @@ -139,13 +139,13 @@ static char *bcm_proc_getifname(char *result, int ifindex) if (!ifindex) return "any"; - read_lock(&dev_base_lock); - dev = __dev_get_by_index(&init_net, ifindex); + rcu_read_lock(); + dev = dev_get_by_index_rcu(&init_net, ifindex); if (dev) strcpy(result, dev->name); else strcpy(result, "???"); - read_unlock(&dev_base_lock); + rcu_read_unlock(); return result; } @@ -1539,7 +1539,7 @@ static int bcm_recvmsg(struct kiocb *iocb, struct socket *sock, return err; } - sock_recv_timestamp(msg, sk, skb); + sock_recv_ts_and_drops(msg, sk, skb); if (msg->msg_name) { msg->msg_namelen = sizeof(struct sockaddr_can); @@ -1581,7 +1581,6 @@ static struct proto bcm_proto __read_mostly = { static struct can_proto bcm_can_proto __read_mostly = { .type = SOCK_DGRAM, .protocol = CAN_BCM, - .capability = -1, .ops = &bcm_ops, .prot = &bcm_proto, }; diff --git a/net/can/raw.c b/net/can/raw.c index b5e897922d32..abca920440b5 100644 --- a/net/can/raw.c +++ b/net/can/raw.c @@ -424,8 +424,6 @@ static int raw_setsockopt(struct socket *sock, int level, int optname, if (level != SOL_CAN_RAW) return -EINVAL; - if (optlen < 0) - return -EINVAL; switch (optname) { @@ -702,7 +700,7 @@ static int raw_recvmsg(struct kiocb *iocb, struct socket *sock, return err; } - sock_recv_timestamp(msg, sk, skb); + sock_recv_ts_and_drops(msg, sk, skb); if (msg->msg_name) { msg->msg_namelen = sizeof(struct sockaddr_can); @@ -744,7 +742,6 @@ static struct proto raw_proto __read_mostly = { static struct can_proto raw_can_proto __read_mostly = { .type = SOCK_RAW, .protocol = CAN_RAW, - .capability = -1, .ops = &raw_ops, .prot = &raw_proto, }; diff --git a/net/compat.c b/net/compat.c index a407c3addbae..e1a56ade803b 100644 --- a/net/compat.c +++ b/net/compat.c @@ -390,9 +390,6 @@ asmlinkage long compat_sys_setsockopt(int fd, int level, int optname, int err; struct socket *sock; - if (optlen < 0) - return -EINVAL; - if ((sock = sockfd_lookup(fd, &err))!=NULL) { err = security_socket_setsockopt(sock,level,optname); @@ -727,10 +724,10 @@ EXPORT_SYMBOL(compat_mc_getsockopt); /* Argument list sizes for compat_sys_socketcall */ #define AL(x) ((x) * sizeof(u32)) -static unsigned char nas[19]={AL(0),AL(3),AL(3),AL(3),AL(2),AL(3), +static unsigned char nas[20]={AL(0),AL(3),AL(3),AL(3),AL(2),AL(3), AL(3),AL(3),AL(4),AL(4),AL(4),AL(6), AL(6),AL(2),AL(5),AL(5),AL(3),AL(3), - AL(4)}; + AL(4),AL(5)}; #undef AL asmlinkage long compat_sys_sendmsg(int fd, struct compat_msghdr __user *msg, unsigned flags) @@ -755,13 +752,40 @@ asmlinkage long compat_sys_recvfrom(int fd, void __user *buf, size_t len, return sys_recvfrom(fd, buf, len, flags | MSG_CMSG_COMPAT, addr, addrlen); } +asmlinkage long compat_sys_recvmmsg(int fd, struct compat_mmsghdr __user *mmsg, + unsigned vlen, unsigned int flags, + struct timespec __user *timeout) +{ + int datagrams; + struct timespec ktspec; + struct compat_timespec __user *utspec; + + if (timeout == NULL) + return __sys_recvmmsg(fd, (struct mmsghdr __user *)mmsg, vlen, + flags | MSG_CMSG_COMPAT, NULL); + + utspec = (struct compat_timespec __user *)timeout; + if (get_user(ktspec.tv_sec, &utspec->tv_sec) || + get_user(ktspec.tv_nsec, &utspec->tv_nsec)) + return -EFAULT; + + datagrams = __sys_recvmmsg(fd, (struct mmsghdr __user *)mmsg, vlen, + flags | MSG_CMSG_COMPAT, &ktspec); + if (datagrams > 0 && + (put_user(ktspec.tv_sec, &utspec->tv_sec) || + put_user(ktspec.tv_nsec, &utspec->tv_nsec))) + datagrams = -EFAULT; + + return datagrams; +} + asmlinkage long compat_sys_socketcall(int call, u32 __user *args) { int ret; u32 a[6]; u32 a0, a1; - if (call < SYS_SOCKET || call > SYS_ACCEPT4) + if (call < SYS_SOCKET || call > SYS_RECVMMSG) return -EINVAL; if (copy_from_user(a, args, nas[call])) return -EFAULT; @@ -823,6 +847,10 @@ asmlinkage long compat_sys_socketcall(int call, u32 __user *args) case SYS_RECVMSG: ret = compat_sys_recvmsg(a0, compat_ptr(a1), a[2]); break; + case SYS_RECVMMSG: + ret = compat_sys_recvmmsg(a0, compat_ptr(a1), a[2], a[3], + compat_ptr(a[4])); + break; case SYS_ACCEPT4: ret = sys_accept4(a0, compat_ptr(a1), compat_ptr(a[2]), a[3]); break; diff --git a/net/core/Makefile b/net/core/Makefile index 796f46eece5f..08791ac3e05a 100644 --- a/net/core/Makefile +++ b/net/core/Makefile @@ -6,7 +6,6 @@ obj-y := sock.o request_sock.o skbuff.o iovec.o datagram.o stream.o scm.o \ gen_stats.o gen_estimator.o net_namespace.o obj-$(CONFIG_SYSCTL) += sysctl_net_core.o -obj-$(CONFIG_HAS_DMA) += skb_dma_map.o obj-y += dev.o ethtool.o dev_mcast.o dst.o netevent.o \ neighbour.o rtnetlink.o utils.o link_watch.o filter.o diff --git a/net/core/datagram.c b/net/core/datagram.c index 4ade3011bb3c..95c2e0840d0d 100644 --- a/net/core/datagram.c +++ b/net/core/datagram.c @@ -271,6 +271,7 @@ int skb_kill_datagram(struct sock *sk, struct sk_buff *skb, unsigned int flags) } kfree_skb(skb); + atomic_inc(&sk->sk_drops); sk_mem_reclaim_partial(sk); return err; diff --git a/net/core/dev.c b/net/core/dev.c index fe10551d3671..c36a17aafcf3 100644 --- a/net/core/dev.c +++ b/net/core/dev.c @@ -79,6 +79,7 @@ #include <linux/cpu.h> #include <linux/types.h> #include <linux/kernel.h> +#include <linux/hash.h> #include <linux/sched.h> #include <linux/mutex.h> #include <linux/string.h> @@ -104,6 +105,7 @@ #include <net/dst.h> #include <net/pkt_sched.h> #include <net/checksum.h> +#include <net/xfrm.h> #include <linux/highmem.h> #include <linux/init.h> #include <linux/kmod.h> @@ -175,7 +177,7 @@ static struct list_head ptype_all __read_mostly; /* Taps */ * The @dev_base_head list is protected by @dev_base_lock and the rtnl * semaphore. * - * Pure readers hold dev_base_lock for reading. + * Pure readers hold dev_base_lock for reading, or rcu_read_lock() * * Writers must hold the rtnl semaphore while they loop through the * dev_base_head list, and hold dev_base_lock for writing when they do the @@ -193,18 +195,15 @@ static struct list_head ptype_all __read_mostly; /* Taps */ DEFINE_RWLOCK(dev_base_lock); EXPORT_SYMBOL(dev_base_lock); -#define NETDEV_HASHBITS 8 -#define NETDEV_HASHENTRIES (1 << NETDEV_HASHBITS) - static inline struct hlist_head *dev_name_hash(struct net *net, const char *name) { unsigned hash = full_name_hash(name, strnlen(name, IFNAMSIZ)); - return &net->dev_name_head[hash & ((1 << NETDEV_HASHBITS) - 1)]; + return &net->dev_name_head[hash_32(hash, NETDEV_HASHBITS)]; } static inline struct hlist_head *dev_index_hash(struct net *net, int ifindex) { - return &net->dev_index_head[ifindex & ((1 << NETDEV_HASHBITS) - 1)]; + return &net->dev_index_head[ifindex & (NETDEV_HASHENTRIES - 1)]; } /* Device list insertion */ @@ -215,23 +214,26 @@ static int list_netdevice(struct net_device *dev) ASSERT_RTNL(); write_lock_bh(&dev_base_lock); - list_add_tail(&dev->dev_list, &net->dev_base_head); - hlist_add_head(&dev->name_hlist, dev_name_hash(net, dev->name)); - hlist_add_head(&dev->index_hlist, dev_index_hash(net, dev->ifindex)); + list_add_tail_rcu(&dev->dev_list, &net->dev_base_head); + hlist_add_head_rcu(&dev->name_hlist, dev_name_hash(net, dev->name)); + hlist_add_head_rcu(&dev->index_hlist, + dev_index_hash(net, dev->ifindex)); write_unlock_bh(&dev_base_lock); return 0; } -/* Device list removal */ +/* Device list removal + * caller must respect a RCU grace period before freeing/reusing dev + */ static void unlist_netdevice(struct net_device *dev) { ASSERT_RTNL(); /* Unlink dev from the device chain */ write_lock_bh(&dev_base_lock); - list_del(&dev->dev_list); - hlist_del(&dev->name_hlist); - hlist_del(&dev->index_hlist); + list_del_rcu(&dev->dev_list); + hlist_del_rcu(&dev->name_hlist); + hlist_del_rcu(&dev->index_hlist); write_unlock_bh(&dev_base_lock); } @@ -587,18 +589,44 @@ __setup("netdev=", netdev_boot_setup); struct net_device *__dev_get_by_name(struct net *net, const char *name) { struct hlist_node *p; + struct net_device *dev; + struct hlist_head *head = dev_name_hash(net, name); - hlist_for_each(p, dev_name_hash(net, name)) { - struct net_device *dev - = hlist_entry(p, struct net_device, name_hlist); + hlist_for_each_entry(dev, p, head, name_hlist) if (!strncmp(dev->name, name, IFNAMSIZ)) return dev; - } + return NULL; } EXPORT_SYMBOL(__dev_get_by_name); /** + * dev_get_by_name_rcu - find a device by its name + * @net: the applicable net namespace + * @name: name to find + * + * Find an interface by name. + * If the name is found a pointer to the device is returned. + * If the name is not found then %NULL is returned. + * The reference counters are not incremented so the caller must be + * careful with locks. The caller must hold RCU lock. + */ + +struct net_device *dev_get_by_name_rcu(struct net *net, const char *name) +{ + struct hlist_node *p; + struct net_device *dev; + struct hlist_head *head = dev_name_hash(net, name); + + hlist_for_each_entry_rcu(dev, p, head, name_hlist) + if (!strncmp(dev->name, name, IFNAMSIZ)) + return dev; + + return NULL; +} +EXPORT_SYMBOL(dev_get_by_name_rcu); + +/** * dev_get_by_name - find a device by its name * @net: the applicable net namespace * @name: name to find @@ -614,11 +642,11 @@ struct net_device *dev_get_by_name(struct net *net, const char *name) { struct net_device *dev; - read_lock(&dev_base_lock); - dev = __dev_get_by_name(net, name); + rcu_read_lock(); + dev = dev_get_by_name_rcu(net, name); if (dev) dev_hold(dev); - read_unlock(&dev_base_lock); + rcu_read_unlock(); return dev; } EXPORT_SYMBOL(dev_get_by_name); @@ -638,17 +666,42 @@ EXPORT_SYMBOL(dev_get_by_name); struct net_device *__dev_get_by_index(struct net *net, int ifindex) { struct hlist_node *p; + struct net_device *dev; + struct hlist_head *head = dev_index_hash(net, ifindex); - hlist_for_each(p, dev_index_hash(net, ifindex)) { - struct net_device *dev - = hlist_entry(p, struct net_device, index_hlist); + hlist_for_each_entry(dev, p, head, index_hlist) if (dev->ifindex == ifindex) return dev; - } + return NULL; } EXPORT_SYMBOL(__dev_get_by_index); +/** + * dev_get_by_index_rcu - find a device by its ifindex + * @net: the applicable net namespace + * @ifindex: index of device + * + * Search for an interface by index. Returns %NULL if the device + * is not found or a pointer to the device. The device has not + * had its reference counter increased so the caller must be careful + * about locking. The caller must hold RCU lock. + */ + +struct net_device *dev_get_by_index_rcu(struct net *net, int ifindex) +{ + struct hlist_node *p; + struct net_device *dev; + struct hlist_head *head = dev_index_hash(net, ifindex); + + hlist_for_each_entry_rcu(dev, p, head, index_hlist) + if (dev->ifindex == ifindex) + return dev; + + return NULL; +} +EXPORT_SYMBOL(dev_get_by_index_rcu); + /** * dev_get_by_index - find a device by its ifindex @@ -665,11 +718,11 @@ struct net_device *dev_get_by_index(struct net *net, int ifindex) { struct net_device *dev; - read_lock(&dev_base_lock); - dev = __dev_get_by_index(net, ifindex); + rcu_read_lock(); + dev = dev_get_by_index_rcu(net, ifindex); if (dev) dev_hold(dev); - read_unlock(&dev_base_lock); + rcu_read_unlock(); return dev; } EXPORT_SYMBOL(dev_get_by_index); @@ -748,15 +801,15 @@ struct net_device *dev_get_by_flags(struct net *net, unsigned short if_flags, struct net_device *dev, *ret; ret = NULL; - read_lock(&dev_base_lock); - for_each_netdev(net, dev) { + rcu_read_lock(); + for_each_netdev_rcu(net, dev) { if (((dev->flags ^ if_flags) & mask) == 0) { dev_hold(dev); ret = dev; break; } } - read_unlock(&dev_base_lock); + rcu_read_unlock(); return ret; } EXPORT_SYMBOL(dev_get_by_flags); @@ -841,7 +894,8 @@ static int __dev_alloc_name(struct net *net, const char *name, char *buf) free_page((unsigned long) inuse); } - snprintf(buf, IFNAMSIZ, name, i); + if (buf != name) + snprintf(buf, IFNAMSIZ, name, i); if (!__dev_get_by_name(net, buf)) return i; @@ -881,6 +935,21 @@ int dev_alloc_name(struct net_device *dev, const char *name) } EXPORT_SYMBOL(dev_alloc_name); +static int dev_get_valid_name(struct net *net, const char *name, char *buf, + bool fmt) +{ + if (!dev_valid_name(name)) + return -EINVAL; + + if (fmt && strchr(name, '%')) + return __dev_alloc_name(net, name, buf); + else if (__dev_get_by_name(net, name)) + return -EEXIST; + else if (buf != name) + strlcpy(buf, name, IFNAMSIZ); + + return 0; +} /** * dev_change_name - change name of a device @@ -904,28 +973,20 @@ int dev_change_name(struct net_device *dev, const char *newname) if (dev->flags & IFF_UP) return -EBUSY; - if (!dev_valid_name(newname)) - return -EINVAL; - if (strncmp(newname, dev->name, IFNAMSIZ) == 0) return 0; memcpy(oldname, dev->name, IFNAMSIZ); - if (strchr(newname, '%')) { - err = dev_alloc_name(dev, newname); - if (err < 0) - return err; - } else if (__dev_get_by_name(net, newname)) - return -EEXIST; - else - strlcpy(dev->name, newname, IFNAMSIZ); + err = dev_get_valid_name(net, newname, dev->name, 1); + if (err < 0) + return err; rollback: /* For now only devices in the initial network namespace * are in sysfs. */ - if (net == &init_net) { + if (net_eq(net, &init_net)) { ret = device_rename(&dev->dev, dev->name); if (ret) { memcpy(dev->name, oldname, IFNAMSIZ); @@ -935,7 +996,12 @@ rollback: write_lock_bh(&dev_base_lock); hlist_del(&dev->name_hlist); - hlist_add_head(&dev->name_hlist, dev_name_hash(net, dev->name)); + write_unlock_bh(&dev_base_lock); + + synchronize_rcu(); + + write_lock_bh(&dev_base_lock); + hlist_add_head_rcu(&dev->name_hlist, dev_name_hash(net, dev->name)); write_unlock_bh(&dev_base_lock); ret = call_netdevice_notifiers(NETDEV_CHANGENAME, dev); @@ -1038,9 +1104,9 @@ void dev_load(struct net *net, const char *name) { struct net_device *dev; - read_lock(&dev_base_lock); - dev = __dev_get_by_name(net, name); - read_unlock(&dev_base_lock); + rcu_read_lock(); + dev = dev_get_by_name_rcu(net, name); + rcu_read_unlock(); if (!dev && capable(CAP_NET_ADMIN)) request_module("%s", name); @@ -1287,6 +1353,7 @@ rollback: nb->notifier_call(nb, NETDEV_DOWN, dev); } nb->notifier_call(nb, NETDEV_UNREGISTER, dev); + nb->notifier_call(nb, NETDEV_UNREGISTER_BATCH, dev); } } @@ -1353,6 +1420,45 @@ static inline void net_timestamp(struct sk_buff *skb) skb->tstamp.tv64 = 0; } +/** + * dev_forward_skb - loopback an skb to another netif + * + * @dev: destination network device + * @skb: buffer to forward + * + * return values: + * NET_RX_SUCCESS (no congestion) + * NET_RX_DROP (packet was dropped) + * + * dev_forward_skb can be used for injecting an skb from the + * start_xmit function of one device into the receive queue + * of another device. + * + * The receiving device may be in another namespace, so + * we have to clear all information in the skb that could + * impact namespace isolation. + */ +int dev_forward_skb(struct net_device *dev, struct sk_buff *skb) +{ + skb_orphan(skb); + + if (!(dev->flags & IFF_UP)) + return NET_RX_DROP; + + if (skb->len > (dev->mtu + dev->hard_header_len)) + return NET_RX_DROP; + + skb_dst_drop(skb); + skb->tstamp.tv64 = 0; + skb->pkt_type = PACKET_HOST; + skb->protocol = eth_type_trans(skb, dev); + skb->mark = 0; + secpath_reset(skb); + nf_reset(skb); + return netif_rx(skb); +} +EXPORT_SYMBOL_GPL(dev_forward_skb); + /* * Support routine. Sends outgoing frames to any network * taps currently in use. @@ -1701,7 +1807,7 @@ int dev_hard_start_xmit(struct sk_buff *skb, struct net_device *dev, struct netdev_queue *txq) { const struct net_device_ops *ops = dev->netdev_ops; - int rc; + int rc = NETDEV_TX_OK; if (likely(!skb->next)) { if (!list_empty(&ptype_all)) @@ -1749,6 +1855,8 @@ gso: nskb->next = NULL; rc = ops->ndo_start_xmit(nskb, dev); if (unlikely(rc != NETDEV_TX_OK)) { + if (rc & ~NETDEV_TX_MASK) + goto out_kfree_gso_skb; nskb->next = skb->next; skb->next = nskb; return rc; @@ -1758,11 +1866,12 @@ gso: return NETDEV_TX_BUSY; } while (skb->next); - skb->destructor = DEV_GSO_CB(skb)->destructor; - +out_kfree_gso_skb: + if (likely(skb->next == NULL)) + skb->destructor = DEV_GSO_CB(skb)->destructor; out_kfree_skb: kfree_skb(skb); - return NETDEV_TX_OK; + return rc; } static u32 skb_tx_hashrnd; @@ -1789,16 +1898,43 @@ u16 skb_tx_hash(const struct net_device *dev, const struct sk_buff *skb) } EXPORT_SYMBOL(skb_tx_hash); +static inline u16 dev_cap_txqueue(struct net_device *dev, u16 queue_index) +{ + if (unlikely(queue_index >= dev->real_num_tx_queues)) { + if (net_ratelimit()) { + WARN(1, "%s selects TX queue %d, but " + "real number of TX queues is %d\n", + dev->name, queue_index, + dev->real_num_tx_queues); + } + return 0; + } + return queue_index; +} + static struct netdev_queue *dev_pick_tx(struct net_device *dev, struct sk_buff *skb) { - const struct net_device_ops *ops = dev->netdev_ops; - u16 queue_index = 0; + u16 queue_index; + struct sock *sk = skb->sk; + + if (sk_tx_queue_recorded(sk)) { + queue_index = sk_tx_queue_get(sk); + } else { + const struct net_device_ops *ops = dev->netdev_ops; - if (ops->ndo_select_queue) - queue_index = ops->ndo_select_queue(dev, skb); - else if (dev->real_num_tx_queues > 1) - queue_index = skb_tx_hash(dev, skb); + if (ops->ndo_select_queue) { + queue_index = ops->ndo_select_queue(dev, skb); + queue_index = dev_cap_txqueue(dev, queue_index); + } else { + queue_index = 0; + if (dev->real_num_tx_queues > 1) + queue_index = skb_tx_hash(dev, skb); + + if (sk && sk->sk_dst_cache) + sk_tx_queue_set(sk, queue_index); + } + } skb_set_queue_mapping(skb, queue_index); return netdev_get_tx_queue(dev, queue_index); @@ -1935,8 +2071,8 @@ gso: HARD_TX_LOCK(dev, txq, cpu); if (!netif_tx_queue_stopped(txq)) { - rc = NET_XMIT_SUCCESS; - if (!dev_hard_start_xmit(skb, dev, txq)) { + rc = dev_hard_start_xmit(skb, dev, txq); + if (dev_xmit_complete(rc)) { HARD_TX_UNLOCK(dev, txq); goto out; } @@ -2191,7 +2327,7 @@ static int ing_filter(struct sk_buff *skb) if (MAX_RED_LOOP < ttl++) { printk(KERN_WARNING "Redir loop detected Dropping packet (%d->%d)\n", - skb->iif, dev->ifindex); + skb->skb_iif, dev->ifindex); return TC_ACT_SHOT; } @@ -2292,15 +2428,15 @@ int netif_receive_skb(struct sk_buff *skb) if (!skb->tstamp.tv64) net_timestamp(skb); - if (skb->vlan_tci && vlan_hwaccel_do_receive(skb)) + if (vlan_tx_tag_present(skb) && vlan_hwaccel_do_receive(skb)) return NET_RX_SUCCESS; /* if we've gotten here through NAPI, check netpoll */ if (netpoll_receive_skb(skb)) return NET_RX_DROP; - if (!skb->iif) - skb->iif = skb->dev->ifindex; + if (!skb->skb_iif) + skb->skb_iif = skb->dev->ifindex; null_or_orig = NULL; orig_dev = skb->dev; @@ -2440,7 +2576,7 @@ void napi_gro_flush(struct napi_struct *napi) } EXPORT_SYMBOL(napi_gro_flush); -int dev_gro_receive(struct napi_struct *napi, struct sk_buff *skb) +enum gro_result dev_gro_receive(struct napi_struct *napi, struct sk_buff *skb) { struct sk_buff **pp = NULL; struct packet_type *ptype; @@ -2448,7 +2584,7 @@ int dev_gro_receive(struct napi_struct *napi, struct sk_buff *skb) struct list_head *head = &ptype_base[ntohs(type) & PTYPE_HASH_MASK]; int same_flow; int mac_len; - int ret; + enum gro_result ret; if (!(skb->dev->features & NETIF_F_GRO)) goto normal; @@ -2532,7 +2668,8 @@ normal: } EXPORT_SYMBOL(dev_gro_receive); -static int __napi_gro_receive(struct napi_struct *napi, struct sk_buff *skb) +static gro_result_t +__napi_gro_receive(struct napi_struct *napi, struct sk_buff *skb) { struct sk_buff *p; @@ -2540,33 +2677,35 @@ static int __napi_gro_receive(struct napi_struct *napi, struct sk_buff *skb) return GRO_NORMAL; for (p = napi->gro_list; p; p = p->next) { - NAPI_GRO_CB(p)->same_flow = (p->dev == skb->dev) - && !compare_ether_header(skb_mac_header(p), - skb_gro_mac_header(skb)); + NAPI_GRO_CB(p)->same_flow = + (p->dev == skb->dev) && + !compare_ether_header(skb_mac_header(p), + skb_gro_mac_header(skb)); NAPI_GRO_CB(p)->flush = 0; } return dev_gro_receive(napi, skb); } -int napi_skb_finish(int ret, struct sk_buff *skb) +gro_result_t napi_skb_finish(gro_result_t ret, struct sk_buff *skb) { - int err = NET_RX_SUCCESS; - switch (ret) { case GRO_NORMAL: - return netif_receive_skb(skb); + if (netif_receive_skb(skb)) + ret = GRO_DROP; + break; case GRO_DROP: - err = NET_RX_DROP; - /* fall through */ - case GRO_MERGED_FREE: kfree_skb(skb); break; + + case GRO_HELD: + case GRO_MERGED: + break; } - return err; + return ret; } EXPORT_SYMBOL(napi_skb_finish); @@ -2586,7 +2725,7 @@ void skb_gro_reset_offset(struct sk_buff *skb) } EXPORT_SYMBOL(skb_gro_reset_offset); -int napi_gro_receive(struct napi_struct *napi, struct sk_buff *skb) +gro_result_t napi_gro_receive(struct napi_struct *napi, struct sk_buff *skb) { skb_gro_reset_offset(skb); @@ -2605,49 +2744,41 @@ EXPORT_SYMBOL(napi_reuse_skb); struct sk_buff *napi_get_frags(struct napi_struct *napi) { - struct net_device *dev = napi->dev; struct sk_buff *skb = napi->skb; if (!skb) { - skb = netdev_alloc_skb(dev, GRO_MAX_HEAD + NET_IP_ALIGN); - if (!skb) - goto out; - - skb_reserve(skb, NET_IP_ALIGN); - - napi->skb = skb; + skb = netdev_alloc_skb_ip_align(napi->dev, GRO_MAX_HEAD); + if (skb) + napi->skb = skb; } - -out: return skb; } EXPORT_SYMBOL(napi_get_frags); -int napi_frags_finish(struct napi_struct *napi, struct sk_buff *skb, int ret) +gro_result_t napi_frags_finish(struct napi_struct *napi, struct sk_buff *skb, + gro_result_t ret) { - int err = NET_RX_SUCCESS; - switch (ret) { case GRO_NORMAL: case GRO_HELD: skb->protocol = eth_type_trans(skb, napi->dev); - if (ret == GRO_NORMAL) - return netif_receive_skb(skb); - - skb_gro_pull(skb, -ETH_HLEN); + if (ret == GRO_HELD) + skb_gro_pull(skb, -ETH_HLEN); + else if (netif_receive_skb(skb)) + ret = GRO_DROP; break; case GRO_DROP: - err = NET_RX_DROP; - /* fall through */ - case GRO_MERGED_FREE: napi_reuse_skb(napi, skb); break; + + case GRO_MERGED: + break; } - return err; + return ret; } EXPORT_SYMBOL(napi_frags_finish); @@ -2688,12 +2819,12 @@ out: } EXPORT_SYMBOL(napi_frags_skb); -int napi_gro_frags(struct napi_struct *napi) +gro_result_t napi_gro_frags(struct napi_struct *napi) { struct sk_buff *skb = napi_frags_skb(napi); if (!skb) - return NET_RX_DROP; + return GRO_DROP; return napi_frags_finish(napi, skb, __napi_gro_receive(napi, skb)); } @@ -2938,15 +3069,15 @@ static int dev_ifname(struct net *net, struct ifreq __user *arg) if (copy_from_user(&ifr, arg, sizeof(struct ifreq))) return -EFAULT; - read_lock(&dev_base_lock); - dev = __dev_get_by_index(net, ifr.ifr_ifindex); + rcu_read_lock(); + dev = dev_get_by_index_rcu(net, ifr.ifr_ifindex); if (!dev) { - read_unlock(&dev_base_lock); + rcu_read_unlock(); return -ENODEV; } strcpy(ifr.ifr_name, dev->name); - read_unlock(&dev_base_lock); + rcu_read_unlock(); if (copy_to_user(arg, &ifr, sizeof(struct ifreq))) return -EFAULT; @@ -3016,18 +3147,18 @@ static int dev_ifconf(struct net *net, char __user *arg) * in detail. */ void *dev_seq_start(struct seq_file *seq, loff_t *pos) - __acquires(dev_base_lock) + __acquires(RCU) { struct net *net = seq_file_net(seq); loff_t off; struct net_device *dev; - read_lock(&dev_base_lock); + rcu_read_lock(); if (!*pos) return SEQ_START_TOKEN; off = 1; - for_each_netdev(net, dev) + for_each_netdev_rcu(net, dev) if (off++ == *pos) return dev; @@ -3036,16 +3167,18 @@ void *dev_seq_start(struct seq_file *seq, loff_t *pos) void *dev_seq_next(struct seq_file *seq, void *v, loff_t *pos) { - struct net *net = seq_file_net(seq); + struct net_device *dev = (v == SEQ_START_TOKEN) ? + first_net_device(seq_file_net(seq)) : + next_net_device((struct net_device *)v); + ++*pos; - return v == SEQ_START_TOKEN ? - first_net_device(net) : next_net_device((struct net_device *)v); + return rcu_dereference(dev); } void dev_seq_stop(struct seq_file *seq, void *v) - __releases(dev_base_lock) + __releases(RCU) { - read_unlock(&dev_base_lock); + rcu_read_unlock(); } static void dev_seq_printf_stats(struct seq_file *seq, struct net_device *dev) @@ -4254,12 +4387,12 @@ int dev_set_mac_address(struct net_device *dev, struct sockaddr *sa) EXPORT_SYMBOL(dev_set_mac_address); /* - * Perform the SIOCxIFxxx calls, inside read_lock(dev_base_lock) + * Perform the SIOCxIFxxx calls, inside rcu_read_lock() */ static int dev_ifsioc_locked(struct net *net, struct ifreq *ifr, unsigned int cmd) { int err; - struct net_device *dev = __dev_get_by_name(net, ifr->ifr_name); + struct net_device *dev = dev_get_by_name_rcu(net, ifr->ifr_name); if (!dev) return -ENODEV; @@ -4491,9 +4624,9 @@ int dev_ioctl(struct net *net, unsigned int cmd, void __user *arg) case SIOCGIFINDEX: case SIOCGIFTXQLEN: dev_load(net, ifr.ifr_name); - read_lock(&dev_base_lock); + rcu_read_lock(); ret = dev_ifsioc_locked(net, &ifr, cmd); - read_unlock(&dev_base_lock); + rcu_read_unlock(); if (!ret) { if (colon) *colon = ':'; @@ -4636,59 +4769,80 @@ static void net_set_todo(struct net_device *dev) list_add_tail(&dev->todo_list, &net_todo_list); } -static void rollback_registered(struct net_device *dev) +static void rollback_registered_many(struct list_head *head) { + struct net_device *dev; + BUG_ON(dev_boot_phase); ASSERT_RTNL(); - /* Some devices call without registering for initialization unwind. */ - if (dev->reg_state == NETREG_UNINITIALIZED) { - printk(KERN_DEBUG "unregister_netdevice: device %s/%p never " - "was registered\n", dev->name, dev); + list_for_each_entry(dev, head, unreg_list) { + /* Some devices call without registering + * for initialization unwind. + */ + if (dev->reg_state == NETREG_UNINITIALIZED) { + pr_debug("unregister_netdevice: device %s/%p never " + "was registered\n", dev->name, dev); - WARN_ON(1); - return; - } + WARN_ON(1); + return; + } - BUG_ON(dev->reg_state != NETREG_REGISTERED); + BUG_ON(dev->reg_state != NETREG_REGISTERED); - /* If device is running, close it first. */ - dev_close(dev); + /* If device is running, close it first. */ + dev_close(dev); - /* And unlink it from device chain. */ - unlist_netdevice(dev); + /* And unlink it from device chain. */ + unlist_netdevice(dev); - dev->reg_state = NETREG_UNREGISTERING; + dev->reg_state = NETREG_UNREGISTERING; + } synchronize_net(); - /* Shutdown queueing discipline. */ - dev_shutdown(dev); + list_for_each_entry(dev, head, unreg_list) { + /* Shutdown queueing discipline. */ + dev_shutdown(dev); - /* Notify protocols, that we are about to destroy - this device. They should clean all the things. - */ - call_netdevice_notifiers(NETDEV_UNREGISTER, dev); + /* Notify protocols, that we are about to destroy + this device. They should clean all the things. + */ + call_netdevice_notifiers(NETDEV_UNREGISTER, dev); - /* - * Flush the unicast and multicast chains - */ - dev_unicast_flush(dev); - dev_addr_discard(dev); + /* + * Flush the unicast and multicast chains + */ + dev_unicast_flush(dev); + dev_addr_discard(dev); - if (dev->netdev_ops->ndo_uninit) - dev->netdev_ops->ndo_uninit(dev); + if (dev->netdev_ops->ndo_uninit) + dev->netdev_ops->ndo_uninit(dev); - /* Notifier chain MUST detach us from master device. */ - WARN_ON(dev->master); + /* Notifier chain MUST detach us from master device. */ + WARN_ON(dev->master); - /* Remove entries from kobject tree */ - netdev_unregister_kobject(dev); + /* Remove entries from kobject tree */ + netdev_unregister_kobject(dev); + } + + /* Process any work delayed until the end of the batch */ + dev = list_entry(head->next, struct net_device, unreg_list); + call_netdevice_notifiers(NETDEV_UNREGISTER_BATCH, dev); synchronize_net(); - dev_put(dev); + list_for_each_entry(dev, head, unreg_list) + dev_put(dev); +} + +static void rollback_registered(struct net_device *dev) +{ + LIST_HEAD(single); + + list_add(&dev->unreg_list, &single); + rollback_registered_many(&single); } static void __netdev_init_queue_locks_one(struct net_device *dev, @@ -4747,6 +4901,33 @@ unsigned long netdev_fix_features(unsigned long features, const char *name) EXPORT_SYMBOL(netdev_fix_features); /** + * netif_stacked_transfer_operstate - transfer operstate + * @rootdev: the root or lower level device to transfer state from + * @dev: the device to transfer operstate to + * + * Transfer operational state from root to device. This is normally + * called when a stacking relationship exists between the root + * device and the device(a leaf device). + */ +void netif_stacked_transfer_operstate(const struct net_device *rootdev, + struct net_device *dev) +{ + if (rootdev->operstate == IF_OPER_DORMANT) + netif_dormant_on(dev); + else + netif_dormant_off(dev); + + if (netif_carrier_ok(rootdev)) { + if (!netif_carrier_ok(dev)) + netif_carrier_on(dev); + } else { + if (netif_carrier_ok(dev)) + netif_carrier_off(dev); + } +} +EXPORT_SYMBOL(netif_stacked_transfer_operstate); + +/** * register_netdevice - register a network device * @dev: device to register * @@ -4765,8 +4946,6 @@ EXPORT_SYMBOL(netdev_fix_features); int register_netdevice(struct net_device *dev) { - struct hlist_head *head; - struct hlist_node *p; int ret; struct net *net = dev_net(dev); @@ -4795,26 +4974,14 @@ int register_netdevice(struct net_device *dev) } } - if (!dev_valid_name(dev->name)) { - ret = -EINVAL; + ret = dev_get_valid_name(net, dev->name, dev->name, 0); + if (ret) goto err_uninit; - } dev->ifindex = dev_new_index(net); if (dev->iflink == -1) dev->iflink = dev->ifindex; - /* Check for existence of name */ - head = dev_name_hash(net, dev->name); - hlist_for_each(p, head) { - struct net_device *d - = hlist_entry(p, struct net_device, name_hlist); - if (!strncmp(d->name, dev->name, IFNAMSIZ)) { - ret = -EEXIST; - goto err_uninit; - } - } - /* Fix illegal checksum combinations */ if ((dev->features & NETIF_F_HW_CSUM) && (dev->features & (NETIF_F_IP_CSUM|NETIF_F_IPV6_CSUM))) { @@ -4837,6 +5004,12 @@ int register_netdevice(struct net_device *dev) dev->features |= NETIF_F_GSO; netdev_initialize_kobject(dev); + + ret = call_netdevice_notifiers(NETDEV_POST_INIT, dev); + ret = notifier_to_errno(ret); + if (ret) + goto err_uninit; + ret = netdev_register_kobject(dev); if (ret) goto err_uninit; @@ -4961,6 +5134,8 @@ static void netdev_wait_allrefs(struct net_device *dev) { unsigned long rebroadcast_time, warning_time; + linkwatch_forget_dev(dev); + rebroadcast_time = warning_time = jiffies; while (atomic_read(&dev->refcnt) != 0) { if (time_after(jiffies, rebroadcast_time + 1 * HZ)) { @@ -4968,6 +5143,8 @@ static void netdev_wait_allrefs(struct net_device *dev) /* Rebroadcast unregister notification */ call_netdevice_notifiers(NETDEV_UNREGISTER, dev); + /* don't resend NETDEV_UNREGISTER_BATCH, _BATCH users + * should have already handle it the first time */ if (test_bit(__LINK_STATE_LINKWATCH_PENDING, &dev->state)) { @@ -5063,6 +5240,32 @@ void netdev_run_todo(void) } /** + * dev_txq_stats_fold - fold tx_queues stats + * @dev: device to get statistics from + * @stats: struct net_device_stats to hold results + */ +void dev_txq_stats_fold(const struct net_device *dev, + struct net_device_stats *stats) +{ + unsigned long tx_bytes = 0, tx_packets = 0, tx_dropped = 0; + unsigned int i; + struct netdev_queue *txq; + + for (i = 0; i < dev->num_tx_queues; i++) { + txq = netdev_get_tx_queue(dev, i); + tx_bytes += txq->tx_bytes; + tx_packets += txq->tx_packets; + tx_dropped += txq->tx_dropped; + } + if (tx_bytes || tx_packets || tx_dropped) { + stats->tx_bytes = tx_bytes; + stats->tx_packets = tx_packets; + stats->tx_dropped = tx_dropped; + } +} +EXPORT_SYMBOL(dev_txq_stats_fold); + +/** * dev_get_stats - get network device statistics * @dev: device to get statistics from * @@ -5076,25 +5279,9 @@ const struct net_device_stats *dev_get_stats(struct net_device *dev) if (ops->ndo_get_stats) return ops->ndo_get_stats(dev); - else { - unsigned long tx_bytes = 0, tx_packets = 0, tx_dropped = 0; - struct net_device_stats *stats = &dev->stats; - unsigned int i; - struct netdev_queue *txq; - - for (i = 0; i < dev->num_tx_queues; i++) { - txq = netdev_get_tx_queue(dev, i); - tx_bytes += txq->tx_bytes; - tx_packets += txq->tx_packets; - tx_dropped += txq->tx_dropped; - } - if (tx_bytes || tx_packets || tx_dropped) { - stats->tx_bytes = tx_bytes; - stats->tx_packets = tx_packets; - stats->tx_dropped = tx_dropped; - } - return stats; - } + + dev_txq_stats_fold(dev, &dev->stats); + return &dev->stats; } EXPORT_SYMBOL(dev_get_stats); @@ -5174,6 +5361,8 @@ struct net_device *alloc_netdev_mq(int sizeof_priv, const char *name, netdev_init_queues(dev); INIT_LIST_HEAD(&dev->napi_list); + INIT_LIST_HEAD(&dev->unreg_list); + INIT_LIST_HEAD(&dev->link_watch_list); dev->priv_flags = IFF_XMIT_DST_RELEASE; setup(dev); strcpy(dev->name, name); @@ -5238,25 +5427,47 @@ void synchronize_net(void) EXPORT_SYMBOL(synchronize_net); /** - * unregister_netdevice - remove device from the kernel + * unregister_netdevice_queue - remove device from the kernel * @dev: device + * @head: list * * This function shuts down a device interface and removes it * from the kernel tables. + * If head not NULL, device is queued to be unregistered later. * * Callers must hold the rtnl semaphore. You may want * unregister_netdev() instead of this. */ -void unregister_netdevice(struct net_device *dev) +void unregister_netdevice_queue(struct net_device *dev, struct list_head *head) { ASSERT_RTNL(); - rollback_registered(dev); - /* Finish processing unregister after unlock */ - net_set_todo(dev); + if (head) { + list_move_tail(&dev->unreg_list, head); + } else { + rollback_registered(dev); + /* Finish processing unregister after unlock */ + net_set_todo(dev); + } } -EXPORT_SYMBOL(unregister_netdevice); +EXPORT_SYMBOL(unregister_netdevice_queue); + +/** + * unregister_netdevice_many - unregister many devices + * @head: list of devices + */ +void unregister_netdevice_many(struct list_head *head) +{ + struct net_device *dev; + + if (!list_empty(head)) { + rollback_registered_many(head); + list_for_each_entry(dev, head, unreg_list) + net_set_todo(dev); + } +} +EXPORT_SYMBOL(unregister_netdevice_many); /** * unregister_netdev - remove device from the kernel @@ -5293,8 +5504,6 @@ EXPORT_SYMBOL(unregister_netdev); int dev_change_net_namespace(struct net_device *dev, struct net *net, const char *pat) { - char buf[IFNAMSIZ]; - const char *destname; int err; ASSERT_RTNL(); @@ -5327,20 +5536,11 @@ int dev_change_net_namespace(struct net_device *dev, struct net *net, const char * we can use it in the destination network namespace. */ err = -EEXIST; - destname = dev->name; - if (__dev_get_by_name(net, destname)) { + if (__dev_get_by_name(net, dev->name)) { /* We get here if we can't use the current device name */ if (!pat) goto out; - if (!dev_valid_name(pat)) - goto out; - if (strchr(pat, '%')) { - if (__dev_alloc_name(net, pat, buf) < 0) - goto out; - destname = buf; - } else - destname = pat; - if (__dev_get_by_name(net, destname)) + if (dev_get_valid_name(net, pat, dev->name, 1)) goto out; } @@ -5364,6 +5564,7 @@ int dev_change_net_namespace(struct net_device *dev, struct net *net, const char this device. They should clean all the things. */ call_netdevice_notifiers(NETDEV_UNREGISTER, dev); + call_netdevice_notifiers(NETDEV_UNREGISTER_BATCH, dev); /* * Flush the unicast and multicast chains @@ -5376,10 +5577,6 @@ int dev_change_net_namespace(struct net_device *dev, struct net *net, const char /* Actually switch the network namespace */ dev_net_set(dev, net); - /* Assign the new device name */ - if (destname != dev->name) - strcpy(dev->name, destname); - /* If there is an ifindex conflict assign a new one */ if (__dev_get_by_index(net, dev->ifindex)) { int iflink = (dev->iflink == dev->ifindex); @@ -5484,7 +5681,7 @@ unsigned long netdev_increment_features(unsigned long all, unsigned long one, one |= NETIF_F_ALL_CSUM; one |= all & NETIF_F_ONE_FOR_ALL; - all &= one | NETIF_F_LLTX | NETIF_F_GSO; + all &= one | NETIF_F_LLTX | NETIF_F_GSO | NETIF_F_UFO; all |= one & mask & NETIF_F_ONE_FOR_ALL; return all; @@ -5566,14 +5763,13 @@ static struct pernet_operations __net_initdata netdev_net_ops = { static void __net_exit default_device_exit(struct net *net) { - struct net_device *dev; + struct net_device *dev, *aux; /* - * Push all migratable of the network devices back to the + * Push all migratable network devices back to the * initial network namespace */ rtnl_lock(); -restart: - for_each_netdev(net, dev) { + for_each_netdev_safe(net, dev, aux) { int err; char fb_name[IFNAMSIZ]; @@ -5581,11 +5777,9 @@ restart: if (dev->features & NETIF_F_NETNS_LOCAL) continue; - /* Delete virtual devices */ - if (dev->rtnl_link_ops && dev->rtnl_link_ops->dellink) { - dev->rtnl_link_ops->dellink(dev); - goto restart; - } + /* Leave virtual devices for the generic cleanup */ + if (dev->rtnl_link_ops) + continue; /* Push remaing network devices to init_net */ snprintf(fb_name, IFNAMSIZ, "dev%d", dev->ifindex); @@ -5595,13 +5789,37 @@ restart: __func__, dev->name, err); BUG(); } - goto restart; } rtnl_unlock(); } +static void __net_exit default_device_exit_batch(struct list_head *net_list) +{ + /* At exit all network devices most be removed from a network + * namespace. Do this in the reverse order of registeration. + * Do this across as many network namespaces as possible to + * improve batching efficiency. + */ + struct net_device *dev; + struct net *net; + LIST_HEAD(dev_kill_list); + + rtnl_lock(); + list_for_each_entry(net, net_list, exit_list) { + for_each_netdev_reverse(net, dev) { + if (dev->rtnl_link_ops) + dev->rtnl_link_ops->dellink(dev, &dev_kill_list); + else + unregister_netdevice_queue(dev, &dev_kill_list); + } + } + unregister_netdevice_many(&dev_kill_list); + rtnl_unlock(); +} + static struct pernet_operations __net_initdata default_device_ops = { .exit = default_device_exit, + .exit_batch = default_device_exit_batch, }; /* diff --git a/net/core/drop_monitor.c b/net/core/drop_monitor.c index 0a113f26bc9f..b8e9d3a86887 100644 --- a/net/core/drop_monitor.c +++ b/net/core/drop_monitor.c @@ -41,7 +41,7 @@ static void send_dm_alert(struct work_struct *unused); * netlink alerts */ static int trace_state = TRACE_OFF; -static spinlock_t trace_state_lock = SPIN_LOCK_UNLOCKED; +static DEFINE_SPINLOCK(trace_state_lock); struct per_cpu_dm_data { struct work_struct dm_alert_work; diff --git a/net/core/ethtool.c b/net/core/ethtool.c index 4c12ddb5f5ee..d8aee584e8d1 100644 --- a/net/core/ethtool.c +++ b/net/core/ethtool.c @@ -198,13 +198,6 @@ static int ethtool_get_drvinfo(struct net_device *dev, void __user *useraddr) rc = ops->get_sset_count(dev, ETH_SS_PRIV_FLAGS); if (rc >= 0) info.n_priv_flags = rc; - } else { - /* code path for obsolete hooks */ - - if (ops->self_test_count) - info.testinfo_len = ops->self_test_count(dev); - if (ops->get_stats_count) - info.n_stats = ops->get_stats_count(dev); } if (ops->get_regs_len) info.regdump_len = ops->get_regs_len(dev); @@ -309,6 +302,26 @@ static int ethtool_get_regs(struct net_device *dev, char __user *useraddr) return ret; } +static int ethtool_reset(struct net_device *dev, char __user *useraddr) +{ + struct ethtool_value reset; + int ret; + + if (!dev->ethtool_ops->reset) + return -EOPNOTSUPP; + + if (copy_from_user(&reset, useraddr, sizeof(reset))) + return -EFAULT; + + ret = dev->ethtool_ops->reset(dev, &reset.data); + if (ret) + return ret; + + if (copy_to_user(useraddr, &reset, sizeof(reset))) + return -EFAULT; + return 0; +} + static int ethtool_get_wol(struct net_device *dev, char __user *useraddr) { struct ethtool_wolinfo wol = { ETHTOOL_GWOL }; @@ -684,16 +697,10 @@ static int ethtool_self_test(struct net_device *dev, char __user *useraddr) u64 *data; int ret, test_len; - if (!ops->self_test) - return -EOPNOTSUPP; - if (!ops->get_sset_count && !ops->self_test_count) + if (!ops->self_test || !ops->get_sset_count) return -EOPNOTSUPP; - if (ops->get_sset_count) - test_len = ops->get_sset_count(dev, ETH_SS_TEST); - else - /* code path for obsolete hook */ - test_len = ops->self_test_count(dev); + test_len = ops->get_sset_count(dev, ETH_SS_TEST); if (test_len < 0) return test_len; WARN_ON(test_len == 0); @@ -728,36 +735,17 @@ static int ethtool_get_strings(struct net_device *dev, void __user *useraddr) u8 *data; int ret; - if (!ops->get_strings) + if (!ops->get_strings || !ops->get_sset_count) return -EOPNOTSUPP; if (copy_from_user(&gstrings, useraddr, sizeof(gstrings))) return -EFAULT; - if (ops->get_sset_count) { - ret = ops->get_sset_count(dev, gstrings.string_set); - if (ret < 0) - return ret; - - gstrings.len = ret; - } else { - /* code path for obsolete hooks */ - - switch (gstrings.string_set) { - case ETH_SS_TEST: - if (!ops->self_test_count) - return -EOPNOTSUPP; - gstrings.len = ops->self_test_count(dev); - break; - case ETH_SS_STATS: - if (!ops->get_stats_count) - return -EOPNOTSUPP; - gstrings.len = ops->get_stats_count(dev); - break; - default: - return -EINVAL; - } - } + ret = ops->get_sset_count(dev, gstrings.string_set); + if (ret < 0) + return ret; + + gstrings.len = ret; data = kmalloc(gstrings.len * ETH_GSTRING_LEN, GFP_USER); if (!data) @@ -798,16 +786,10 @@ static int ethtool_get_stats(struct net_device *dev, void __user *useraddr) u64 *data; int ret, n_stats; - if (!ops->get_ethtool_stats) - return -EOPNOTSUPP; - if (!ops->get_sset_count && !ops->get_stats_count) + if (!ops->get_ethtool_stats || !ops->get_sset_count) return -EOPNOTSUPP; - if (ops->get_sset_count) - n_stats = ops->get_sset_count(dev, ETH_SS_STATS); - else - /* code path for obsolete hook */ - n_stats = ops->get_stats_count(dev); + n_stats = ops->get_sset_count(dev, ETH_SS_STATS); if (n_stats < 0) return n_stats; WARN_ON(n_stats == 0); @@ -1127,6 +1109,9 @@ int dev_ethtool(struct net *net, struct ifreq *ifr) case ETHTOOL_FLASHDEV: rc = ethtool_flash_device(dev, useraddr); break; + case ETHTOOL_RESET: + rc = ethtool_reset(dev, useraddr); + break; default: rc = -EOPNOTSUPP; } diff --git a/net/core/fib_rules.c b/net/core/fib_rules.c index bd309384f8b8..02a3b2c69c1e 100644 --- a/net/core/fib_rules.c +++ b/net/core/fib_rules.c @@ -72,7 +72,7 @@ static void flush_route_cache(struct fib_rules_ops *ops) ops->flush_cache(ops); } -int fib_rules_register(struct fib_rules_ops *ops) +static int __fib_rules_register(struct fib_rules_ops *ops) { int err = -EEXIST; struct fib_rules_ops *o; @@ -102,6 +102,28 @@ errout: return err; } +struct fib_rules_ops * +fib_rules_register(struct fib_rules_ops *tmpl, struct net *net) +{ + struct fib_rules_ops *ops; + int err; + + ops = kmemdup(tmpl, sizeof (*ops), GFP_KERNEL); + if (ops == NULL) + return ERR_PTR(-ENOMEM); + + INIT_LIST_HEAD(&ops->rules_list); + ops->fro_net = net; + + err = __fib_rules_register(ops); + if (err) { + kfree(ops); + ops = ERR_PTR(err); + } + + return ops; +} + EXPORT_SYMBOL_GPL(fib_rules_register); void fib_rules_cleanup_ops(struct fib_rules_ops *ops) @@ -115,6 +137,15 @@ void fib_rules_cleanup_ops(struct fib_rules_ops *ops) } EXPORT_SYMBOL_GPL(fib_rules_cleanup_ops); +static void fib_rules_put_rcu(struct rcu_head *head) +{ + struct fib_rules_ops *ops = container_of(head, struct fib_rules_ops, rcu); + struct net *net = ops->fro_net; + + release_net(net); + kfree(ops); +} + void fib_rules_unregister(struct fib_rules_ops *ops) { struct net *net = ops->fro_net; @@ -124,8 +155,7 @@ void fib_rules_unregister(struct fib_rules_ops *ops) fib_rules_cleanup_ops(ops); spin_unlock(&net->rules_mod_lock); - synchronize_rcu(); - release_net(net); + call_rcu(&ops->rcu, fib_rules_put_rcu); } EXPORT_SYMBOL_GPL(fib_rules_unregister); @@ -135,7 +165,10 @@ static int fib_rule_match(struct fib_rule *rule, struct fib_rules_ops *ops, { int ret = 0; - if (rule->ifindex && (rule->ifindex != fl->iif)) + if (rule->iifindex && (rule->iifindex != fl->iif)) + goto out; + + if (rule->oifindex && (rule->oifindex != fl->oif)) goto out; if ((rule->mark ^ fl->mark) & rule->mark_mask) @@ -248,14 +281,24 @@ static int fib_nl_newrule(struct sk_buff *skb, struct nlmsghdr* nlh, void *arg) if (tb[FRA_PRIORITY]) rule->pref = nla_get_u32(tb[FRA_PRIORITY]); - if (tb[FRA_IFNAME]) { + if (tb[FRA_IIFNAME]) { + struct net_device *dev; + + rule->iifindex = -1; + nla_strlcpy(rule->iifname, tb[FRA_IIFNAME], IFNAMSIZ); + dev = __dev_get_by_name(net, rule->iifname); + if (dev) + rule->iifindex = dev->ifindex; + } + + if (tb[FRA_OIFNAME]) { struct net_device *dev; - rule->ifindex = -1; - nla_strlcpy(rule->ifname, tb[FRA_IFNAME], IFNAMSIZ); - dev = __dev_get_by_name(net, rule->ifname); + rule->oifindex = -1; + nla_strlcpy(rule->oifname, tb[FRA_OIFNAME], IFNAMSIZ); + dev = __dev_get_by_name(net, rule->oifname); if (dev) - rule->ifindex = dev->ifindex; + rule->oifindex = dev->ifindex; } if (tb[FRA_FWMARK]) { @@ -274,7 +317,7 @@ static int fib_nl_newrule(struct sk_buff *skb, struct nlmsghdr* nlh, void *arg) rule->flags = frh->flags; rule->table = frh_get_table(frh, tb); - if (!rule->pref && ops->default_pref) + if (!tb[FRA_PRIORITY] && ops->default_pref) rule->pref = ops->default_pref(ops); err = -EINVAL; @@ -388,8 +431,12 @@ static int fib_nl_delrule(struct sk_buff *skb, struct nlmsghdr* nlh, void *arg) (rule->pref != nla_get_u32(tb[FRA_PRIORITY]))) continue; - if (tb[FRA_IFNAME] && - nla_strcmp(tb[FRA_IFNAME], rule->ifname)) + if (tb[FRA_IIFNAME] && + nla_strcmp(tb[FRA_IIFNAME], rule->iifname)) + continue; + + if (tb[FRA_OIFNAME] && + nla_strcmp(tb[FRA_OIFNAME], rule->oifname)) continue; if (tb[FRA_FWMARK] && @@ -447,7 +494,8 @@ static inline size_t fib_rule_nlmsg_size(struct fib_rules_ops *ops, struct fib_rule *rule) { size_t payload = NLMSG_ALIGN(sizeof(struct fib_rule_hdr)) - + nla_total_size(IFNAMSIZ) /* FRA_IFNAME */ + + nla_total_size(IFNAMSIZ) /* FRA_IIFNAME */ + + nla_total_size(IFNAMSIZ) /* FRA_OIFNAME */ + nla_total_size(4) /* FRA_PRIORITY */ + nla_total_size(4) /* FRA_TABLE */ + nla_total_size(4) /* FRA_FWMARK */ @@ -481,11 +529,18 @@ static int fib_nl_fill_rule(struct sk_buff *skb, struct fib_rule *rule, if (rule->action == FR_ACT_GOTO && rule->ctarget == NULL) frh->flags |= FIB_RULE_UNRESOLVED; - if (rule->ifname[0]) { - NLA_PUT_STRING(skb, FRA_IFNAME, rule->ifname); + if (rule->iifname[0]) { + NLA_PUT_STRING(skb, FRA_IIFNAME, rule->iifname); - if (rule->ifindex == -1) - frh->flags |= FIB_RULE_DEV_DETACHED; + if (rule->iifindex == -1) + frh->flags |= FIB_RULE_IIF_DETACHED; + } + + if (rule->oifname[0]) { + NLA_PUT_STRING(skb, FRA_OIFNAME, rule->oifname); + + if (rule->oifindex == -1) + frh->flags |= FIB_RULE_OIF_DETACHED; } if (rule->pref) @@ -600,9 +655,12 @@ static void attach_rules(struct list_head *rules, struct net_device *dev) struct fib_rule *rule; list_for_each_entry(rule, rules, list) { - if (rule->ifindex == -1 && - strcmp(dev->name, rule->ifname) == 0) - rule->ifindex = dev->ifindex; + if (rule->iifindex == -1 && + strcmp(dev->name, rule->iifname) == 0) + rule->iifindex = dev->ifindex; + if (rule->oifindex == -1 && + strcmp(dev->name, rule->oifname) == 0) + rule->oifindex = dev->ifindex; } } @@ -610,9 +668,12 @@ static void detach_rules(struct list_head *rules, struct net_device *dev) { struct fib_rule *rule; - list_for_each_entry(rule, rules, list) - if (rule->ifindex == dev->ifindex) - rule->ifindex = -1; + list_for_each_entry(rule, rules, list) { + if (rule->iifindex == dev->ifindex) + rule->iifindex = -1; + if (rule->oifindex == dev->ifindex) + rule->oifindex = -1; + } } diff --git a/net/core/filter.c b/net/core/filter.c index d1d779ca096d..08db7b9143a3 100644 --- a/net/core/filter.c +++ b/net/core/filter.c @@ -303,6 +303,12 @@ load_b: case SKF_AD_IFINDEX: A = skb->dev->ifindex; continue; + case SKF_AD_MARK: + A = skb->mark; + continue; + case SKF_AD_QUEUE: + A = skb->queue_mapping; + continue; case SKF_AD_NLATTR: { struct nlattr *nla; diff --git a/net/core/gen_stats.c b/net/core/gen_stats.c index 8569310268ab..393b1d8618e2 100644 --- a/net/core/gen_stats.c +++ b/net/core/gen_stats.c @@ -127,6 +127,7 @@ gnet_stats_copy_basic(struct gnet_dump *d, struct gnet_stats_basic_packed *b) /** * gnet_stats_copy_rate_est - copy rate estimator statistics into statistics TLV * @d: dumping handle + * @b: basic statistics * @r: rate estimator statistics * * Appends the rate estimator statistics to the top level TLV created by @@ -136,8 +137,13 @@ gnet_stats_copy_basic(struct gnet_dump *d, struct gnet_stats_basic_packed *b) * if the room in the socket buffer was not sufficient. */ int -gnet_stats_copy_rate_est(struct gnet_dump *d, struct gnet_stats_rate_est *r) +gnet_stats_copy_rate_est(struct gnet_dump *d, + const struct gnet_stats_basic_packed *b, + struct gnet_stats_rate_est *r) { + if (b && !gen_estimator_active(b, r)) + return 0; + if (d->compat_tc_stats) { d->tc_stats.bps = r->bps; d->tc_stats.pps = r->pps; diff --git a/net/core/link_watch.c b/net/core/link_watch.c index bf8f7af699d7..5910b555a54a 100644 --- a/net/core/link_watch.c +++ b/net/core/link_watch.c @@ -35,7 +35,7 @@ static unsigned long linkwatch_nextevent; static void linkwatch_event(struct work_struct *dummy); static DECLARE_DELAYED_WORK(linkwatch_work, linkwatch_event); -static struct net_device *lweventlist; +static LIST_HEAD(lweventlist); static DEFINE_SPINLOCK(lweventlist_lock); static unsigned char default_operstate(const struct net_device *dev) @@ -89,8 +89,10 @@ static void linkwatch_add_event(struct net_device *dev) unsigned long flags; spin_lock_irqsave(&lweventlist_lock, flags); - dev->link_watch_next = lweventlist; - lweventlist = dev; + if (list_empty(&dev->link_watch_list)) { + list_add_tail(&dev->link_watch_list, &lweventlist); + dev_hold(dev); + } spin_unlock_irqrestore(&lweventlist_lock, flags); } @@ -133,9 +135,35 @@ static void linkwatch_schedule_work(int urgent) } +static void linkwatch_do_dev(struct net_device *dev) +{ + /* + * Make sure the above read is complete since it can be + * rewritten as soon as we clear the bit below. + */ + smp_mb__before_clear_bit(); + + /* We are about to handle this device, + * so new events can be accepted + */ + clear_bit(__LINK_STATE_LINKWATCH_PENDING, &dev->state); + + rfc2863_policy(dev); + if (dev->flags & IFF_UP) { + if (netif_carrier_ok(dev)) + dev_activate(dev); + else + dev_deactivate(dev); + + netdev_state_change(dev); + } + dev_put(dev); +} + static void __linkwatch_run_queue(int urgent_only) { - struct net_device *next; + struct net_device *dev; + LIST_HEAD(wrk); /* * Limit the number of linkwatch events to one @@ -153,46 +181,40 @@ static void __linkwatch_run_queue(int urgent_only) clear_bit(LW_URGENT, &linkwatch_flags); spin_lock_irq(&lweventlist_lock); - next = lweventlist; - lweventlist = NULL; - spin_unlock_irq(&lweventlist_lock); + list_splice_init(&lweventlist, &wrk); - while (next) { - struct net_device *dev = next; + while (!list_empty(&wrk)) { - next = dev->link_watch_next; + dev = list_first_entry(&wrk, struct net_device, link_watch_list); + list_del_init(&dev->link_watch_list); if (urgent_only && !linkwatch_urgent_event(dev)) { - linkwatch_add_event(dev); + list_add_tail(&dev->link_watch_list, &lweventlist); continue; } - - /* - * Make sure the above read is complete since it can be - * rewritten as soon as we clear the bit below. - */ - smp_mb__before_clear_bit(); - - /* We are about to handle this device, - * so new events can be accepted - */ - clear_bit(__LINK_STATE_LINKWATCH_PENDING, &dev->state); - - rfc2863_policy(dev); - if (dev->flags & IFF_UP) { - if (netif_carrier_ok(dev)) - dev_activate(dev); - else - dev_deactivate(dev); - - netdev_state_change(dev); - } - - dev_put(dev); + spin_unlock_irq(&lweventlist_lock); + linkwatch_do_dev(dev); + spin_lock_irq(&lweventlist_lock); } - if (lweventlist) + if (!list_empty(&lweventlist)) linkwatch_schedule_work(0); + spin_unlock_irq(&lweventlist_lock); +} + +void linkwatch_forget_dev(struct net_device *dev) +{ + unsigned long flags; + int clean = 0; + + spin_lock_irqsave(&lweventlist_lock, flags); + if (!list_empty(&dev->link_watch_list)) { + list_del_init(&dev->link_watch_list); + clean = 1; + } + spin_unlock_irqrestore(&lweventlist_lock, flags); + if (clean) + linkwatch_do_dev(dev); } @@ -216,8 +238,6 @@ void linkwatch_fire_event(struct net_device *dev) bool urgent = linkwatch_urgent_event(dev); if (!test_and_set_bit(__LINK_STATE_LINKWATCH_PENDING, &dev->state)) { - dev_hold(dev); - linkwatch_add_event(dev); } else if (!urgent) return; diff --git a/net/core/neighbour.c b/net/core/neighbour.c index 2b54e6c6a7c8..f35377b643e4 100644 --- a/net/core/neighbour.c +++ b/net/core/neighbour.c @@ -2092,7 +2092,7 @@ static int neigh_dump_table(struct neigh_table *tbl, struct sk_buff *skb, if (h > s_h) s_idx = 0; for (n = tbl->hash_buckets[h], idx = 0; n; n = n->next) { - if (dev_net(n->dev) != net) + if (!net_eq(dev_net(n->dev), net)) continue; if (idx < s_idx) goto next; diff --git a/net/core/net-sysfs.c b/net/core/net-sysfs.c index 427ded841224..fbc1c7472c5e 100644 --- a/net/core/net-sysfs.c +++ b/net/core/net-sysfs.c @@ -130,6 +130,48 @@ static ssize_t show_carrier(struct device *dev, return -EINVAL; } +static ssize_t show_speed(struct device *dev, + struct device_attribute *attr, char *buf) +{ + struct net_device *netdev = to_net_dev(dev); + int ret = -EINVAL; + + if (!rtnl_trylock()) + return restart_syscall(); + + if (netif_running(netdev) && + netdev->ethtool_ops && + netdev->ethtool_ops->get_settings) { + struct ethtool_cmd cmd = { ETHTOOL_GSET }; + + if (!netdev->ethtool_ops->get_settings(netdev, &cmd)) + ret = sprintf(buf, fmt_dec, ethtool_cmd_speed(&cmd)); + } + rtnl_unlock(); + return ret; +} + +static ssize_t show_duplex(struct device *dev, + struct device_attribute *attr, char *buf) +{ + struct net_device *netdev = to_net_dev(dev); + int ret = -EINVAL; + + if (!rtnl_trylock()) + return restart_syscall(); + + if (netif_running(netdev) && + netdev->ethtool_ops && + netdev->ethtool_ops->get_settings) { + struct ethtool_cmd cmd = { ETHTOOL_GSET }; + + if (!netdev->ethtool_ops->get_settings(netdev, &cmd)) + ret = sprintf(buf, "%s\n", cmd.duplex ? "full" : "half"); + } + rtnl_unlock(); + return ret; +} + static ssize_t show_dormant(struct device *dev, struct device_attribute *attr, char *buf) { @@ -259,6 +301,8 @@ static struct device_attribute net_class_attributes[] = { __ATTR(address, S_IRUGO, show_address, NULL), __ATTR(broadcast, S_IRUGO, show_broadcast, NULL), __ATTR(carrier, S_IRUGO, show_carrier, NULL), + __ATTR(speed, S_IRUGO, show_speed, NULL), + __ATTR(duplex, S_IRUGO, show_duplex, NULL), __ATTR(dormant, S_IRUGO, show_dormant, NULL), __ATTR(operstate, S_IRUGO, show_operstate, NULL), __ATTR(mtu, S_IRUGO | S_IWUSR, show_mtu, store_mtu), @@ -481,7 +525,7 @@ void netdev_unregister_kobject(struct net_device * net) kobject_get(&dev->kobj); - if (dev_net(net) != &init_net) + if (!net_eq(dev_net(net), &init_net)) return; device_del(dev); @@ -500,15 +544,22 @@ int netdev_register_kobject(struct net_device *net) dev_set_name(dev, "%s", net->name); #ifdef CONFIG_SYSFS - *groups++ = &netstat_group; + /* Allow for a device specific group */ + if (*groups) + groups++; + *groups++ = &netstat_group; #ifdef CONFIG_WIRELESS_EXT_SYSFS - if (net->wireless_handlers || net->ieee80211_ptr) + if (net->ieee80211_ptr) + *groups++ = &wireless_group; +#ifdef CONFIG_WIRELESS_EXT + else if (net->wireless_handlers) *groups++ = &wireless_group; #endif +#endif #endif /* CONFIG_SYSFS */ - if (dev_net(net) != &init_net) + if (!net_eq(dev_net(net), &init_net)) return 0; return device_add(dev); diff --git a/net/core/net_namespace.c b/net/core/net_namespace.c index 1c1af2756f38..bd8c4712ea24 100644 --- a/net/core/net_namespace.c +++ b/net/core/net_namespace.c @@ -27,14 +27,64 @@ EXPORT_SYMBOL(init_net); #define INITIAL_NET_GEN_PTRS 13 /* +1 for len +2 for rcu_head */ +static int ops_init(const struct pernet_operations *ops, struct net *net) +{ + int err; + if (ops->id && ops->size) { + void *data = kzalloc(ops->size, GFP_KERNEL); + if (!data) + return -ENOMEM; + + err = net_assign_generic(net, *ops->id, data); + if (err) { + kfree(data); + return err; + } + } + if (ops->init) + return ops->init(net); + return 0; +} + +static void ops_free(const struct pernet_operations *ops, struct net *net) +{ + if (ops->id && ops->size) { + int id = *ops->id; + kfree(net_generic(net, id)); + } +} + +static void ops_exit_list(const struct pernet_operations *ops, + struct list_head *net_exit_list) +{ + struct net *net; + if (ops->exit) { + list_for_each_entry(net, net_exit_list, exit_list) + ops->exit(net); + } + if (ops->exit_batch) + ops->exit_batch(net_exit_list); +} + +static void ops_free_list(const struct pernet_operations *ops, + struct list_head *net_exit_list) +{ + struct net *net; + if (ops->size && ops->id) { + list_for_each_entry(net, net_exit_list, exit_list) + ops_free(ops, net); + } +} + /* * setup_net runs the initializers for the network namespace object. */ static __net_init int setup_net(struct net *net) { /* Must be called with net_mutex held */ - struct pernet_operations *ops; + const struct pernet_operations *ops, *saved_ops; int error = 0; + LIST_HEAD(net_exit_list); atomic_set(&net->count, 1); @@ -43,11 +93,9 @@ static __net_init int setup_net(struct net *net) #endif list_for_each_entry(ops, &pernet_list, list) { - if (ops->init) { - error = ops->init(net); - if (error < 0) - goto out_undo; - } + error = ops_init(ops, net); + if (error < 0) + goto out_undo; } out: return error; @@ -56,10 +104,14 @@ out_undo: /* Walk through the list backwards calling the exit functions * for the pernet modules whose init functions did not fail. */ - list_for_each_entry_continue_reverse(ops, &pernet_list, list) { - if (ops->exit) - ops->exit(net); - } + list_add(&net->exit_list, &net_exit_list); + saved_ops = ops; + list_for_each_entry_continue_reverse(ops, &pernet_list, list) + ops_exit_list(ops, &net_exit_list); + + ops = saved_ops; + list_for_each_entry_continue_reverse(ops, &pernet_list, list) + ops_free_list(ops, &net_exit_list); rcu_barrier(); goto out; @@ -147,18 +199,29 @@ struct net *copy_net_ns(unsigned long flags, struct net *old_net) return net_create(); } +static DEFINE_SPINLOCK(cleanup_list_lock); +static LIST_HEAD(cleanup_list); /* Must hold cleanup_list_lock to touch */ + static void cleanup_net(struct work_struct *work) { - struct pernet_operations *ops; - struct net *net; + const struct pernet_operations *ops; + struct net *net, *tmp; + LIST_HEAD(net_kill_list); + LIST_HEAD(net_exit_list); - net = container_of(work, struct net, work); + /* Atomically snapshot the list of namespaces to cleanup */ + spin_lock_irq(&cleanup_list_lock); + list_replace_init(&cleanup_list, &net_kill_list); + spin_unlock_irq(&cleanup_list_lock); mutex_lock(&net_mutex); /* Don't let anyone else find us. */ rtnl_lock(); - list_del_rcu(&net->list); + list_for_each_entry(net, &net_kill_list, cleanup_list) { + list_del_rcu(&net->list); + list_add_tail(&net->exit_list, &net_exit_list); + } rtnl_unlock(); /* @@ -169,10 +232,12 @@ static void cleanup_net(struct work_struct *work) synchronize_rcu(); /* Run all of the network namespace exit methods */ - list_for_each_entry_reverse(ops, &pernet_list, list) { - if (ops->exit) - ops->exit(net); - } + list_for_each_entry_reverse(ops, &pernet_list, list) + ops_exit_list(ops, &net_exit_list); + + /* Free the net generic variables */ + list_for_each_entry_reverse(ops, &pernet_list, list) + ops_free_list(ops, &net_exit_list); mutex_unlock(&net_mutex); @@ -182,14 +247,23 @@ static void cleanup_net(struct work_struct *work) rcu_barrier(); /* Finally it is safe to free my network namespace structure */ - net_free(net); + list_for_each_entry_safe(net, tmp, &net_exit_list, exit_list) { + list_del_init(&net->exit_list); + net_free(net); + } } +static DECLARE_WORK(net_cleanup_work, cleanup_net); void __put_net(struct net *net) { /* Cleanup the network namespace in process context */ - INIT_WORK(&net->work, cleanup_net); - queue_work(netns_wq, &net->work); + unsigned long flags; + + spin_lock_irqsave(&cleanup_list_lock, flags); + list_add(&net->cleanup_list, &cleanup_list); + spin_unlock_irqrestore(&cleanup_list_lock, flags); + + queue_work(netns_wq, &net_cleanup_work); } EXPORT_SYMBOL_GPL(__put_net); @@ -259,18 +333,20 @@ static int __init net_ns_init(void) pure_initcall(net_ns_init); #ifdef CONFIG_NET_NS -static int register_pernet_operations(struct list_head *list, - struct pernet_operations *ops) +static int __register_pernet_operations(struct list_head *list, + struct pernet_operations *ops) { - struct net *net, *undo_net; + struct net *net; int error; + LIST_HEAD(net_exit_list); list_add_tail(&ops->list, list); - if (ops->init) { + if (ops->init || (ops->id && ops->size)) { for_each_net(net) { - error = ops->init(net); + error = ops_init(ops, net); if (error) goto out_undo; + list_add_tail(&net->exit_list, &net_exit_list); } } return 0; @@ -278,45 +354,82 @@ static int register_pernet_operations(struct list_head *list, out_undo: /* If I have an error cleanup all namespaces I initialized */ list_del(&ops->list); - if (ops->exit) { - for_each_net(undo_net) { - if (undo_net == net) - goto undone; - ops->exit(undo_net); - } - } -undone: + ops_exit_list(ops, &net_exit_list); + ops_free_list(ops, &net_exit_list); return error; } -static void unregister_pernet_operations(struct pernet_operations *ops) +static void __unregister_pernet_operations(struct pernet_operations *ops) { struct net *net; + LIST_HEAD(net_exit_list); list_del(&ops->list); - if (ops->exit) - for_each_net(net) - ops->exit(net); + for_each_net(net) + list_add_tail(&net->exit_list, &net_exit_list); + ops_exit_list(ops, &net_exit_list); + ops_free_list(ops, &net_exit_list); } #else +static int __register_pernet_operations(struct list_head *list, + struct pernet_operations *ops) +{ + int err = 0; + err = ops_init(ops, &init_net); + if (err) + ops_free(ops, &init_net); + return err; + +} + +static void __unregister_pernet_operations(struct pernet_operations *ops) +{ + LIST_HEAD(net_exit_list); + list_add(&init_net.exit_list, &net_exit_list); + ops_exit_list(ops, &net_exit_list); + ops_free_list(ops, &net_exit_list); +} + +#endif /* CONFIG_NET_NS */ + +static DEFINE_IDA(net_generic_ids); + static int register_pernet_operations(struct list_head *list, struct pernet_operations *ops) { - if (ops->init == NULL) - return 0; - return ops->init(&init_net); + int error; + + if (ops->id) { +again: + error = ida_get_new_above(&net_generic_ids, 1, ops->id); + if (error < 0) { + if (error == -EAGAIN) { + ida_pre_get(&net_generic_ids, GFP_KERNEL); + goto again; + } + return error; + } + } + error = __register_pernet_operations(list, ops); + if (error) { + rcu_barrier(); + if (ops->id) + ida_remove(&net_generic_ids, *ops->id); + } + + return error; } static void unregister_pernet_operations(struct pernet_operations *ops) { - if (ops->exit) - ops->exit(&init_net); + + __unregister_pernet_operations(ops); + rcu_barrier(); + if (ops->id) + ida_remove(&net_generic_ids, *ops->id); } -#endif - -static DEFINE_IDA(net_generic_ids); /** * register_pernet_subsys - register a network namespace subsystem @@ -364,38 +477,6 @@ void unregister_pernet_subsys(struct pernet_operations *module) } EXPORT_SYMBOL_GPL(unregister_pernet_subsys); -int register_pernet_gen_subsys(int *id, struct pernet_operations *ops) -{ - int rv; - - mutex_lock(&net_mutex); -again: - rv = ida_get_new_above(&net_generic_ids, 1, id); - if (rv < 0) { - if (rv == -EAGAIN) { - ida_pre_get(&net_generic_ids, GFP_KERNEL); - goto again; - } - goto out; - } - rv = register_pernet_operations(first_device, ops); - if (rv < 0) - ida_remove(&net_generic_ids, *id); -out: - mutex_unlock(&net_mutex); - return rv; -} -EXPORT_SYMBOL_GPL(register_pernet_gen_subsys); - -void unregister_pernet_gen_subsys(int id, struct pernet_operations *ops) -{ - mutex_lock(&net_mutex); - unregister_pernet_operations(ops); - ida_remove(&net_generic_ids, id); - mutex_unlock(&net_mutex); -} -EXPORT_SYMBOL_GPL(unregister_pernet_gen_subsys); - /** * register_pernet_device - register a network namespace device * @ops: pernet operations structure for the subsystem @@ -427,30 +508,6 @@ int register_pernet_device(struct pernet_operations *ops) } EXPORT_SYMBOL_GPL(register_pernet_device); -int register_pernet_gen_device(int *id, struct pernet_operations *ops) -{ - int error; - mutex_lock(&net_mutex); -again: - error = ida_get_new_above(&net_generic_ids, 1, id); - if (error) { - if (error == -EAGAIN) { - ida_pre_get(&net_generic_ids, GFP_KERNEL); - goto again; - } - goto out; - } - error = register_pernet_operations(&pernet_list, ops); - if (error) - ida_remove(&net_generic_ids, *id); - else if (first_device == &pernet_list) - first_device = &ops->list; -out: - mutex_unlock(&net_mutex); - return error; -} -EXPORT_SYMBOL_GPL(register_pernet_gen_device); - /** * unregister_pernet_device - unregister a network namespace netdevice * @ops: pernet operations structure to manipulate @@ -470,17 +527,6 @@ void unregister_pernet_device(struct pernet_operations *ops) } EXPORT_SYMBOL_GPL(unregister_pernet_device); -void unregister_pernet_gen_device(int id, struct pernet_operations *ops) -{ - mutex_lock(&net_mutex); - if (&ops->list == first_device) - first_device = first_device->next; - unregister_pernet_operations(ops); - ida_remove(&net_generic_ids, id); - mutex_unlock(&net_mutex); -} -EXPORT_SYMBOL_GPL(unregister_pernet_gen_device); - static void net_generic_release(struct rcu_head *rcu) { struct net_generic *ng; diff --git a/net/core/pktgen.c b/net/core/pktgen.c index 6e79e96cb4f2..a23b45f08ec9 100644 --- a/net/core/pktgen.c +++ b/net/core/pktgen.c @@ -340,6 +340,7 @@ struct pktgen_dev { __u16 cur_udp_src; __u16 cur_queue_map; __u32 cur_pkt_size; + __u32 last_pkt_size; __u8 hh[14]; /* = { @@ -2051,9 +2052,8 @@ static void pktgen_setup_inject(struct pktgen_dev *pkt_dev) read_lock_bh(&idev->lock); for (ifp = idev->addr_list; ifp; ifp = ifp->if_next) { - if (ifp->scope == IFA_LINK - && !(ifp-> - flags & IFA_F_TENTATIVE)) { + if (ifp->scope == IFA_LINK && + !(ifp->flags & IFA_F_TENTATIVE)) { ipv6_addr_copy(&pkt_dev-> cur_in6_saddr, &ifp->addr); @@ -3436,7 +3436,7 @@ static void pktgen_xmit(struct pktgen_dev *pkt_dev) pkt_dev->clone_count--; /* back out increment, OOM */ return; } - + pkt_dev->last_pkt_size = pkt_dev->skb->len; pkt_dev->allocated_skbs++; pkt_dev->clone_count = 0; /* reset counter */ } @@ -3448,12 +3448,14 @@ static void pktgen_xmit(struct pktgen_dev *pkt_dev) txq = netdev_get_tx_queue(odev, queue_map); __netif_tx_lock_bh(txq); - atomic_inc(&(pkt_dev->skb->users)); - if (unlikely(netif_tx_queue_stopped(txq) || netif_tx_queue_frozen(txq))) + if (unlikely(netif_tx_queue_stopped(txq) || netif_tx_queue_frozen(txq))) { ret = NETDEV_TX_BUSY; - else - ret = (*xmit)(pkt_dev->skb, odev); + pkt_dev->last_ok = 0; + goto unlock; + } + atomic_inc(&(pkt_dev->skb->users)); + ret = (*xmit)(pkt_dev->skb, odev); switch (ret) { case NETDEV_TX_OK: @@ -3461,7 +3463,7 @@ static void pktgen_xmit(struct pktgen_dev *pkt_dev) pkt_dev->last_ok = 1; pkt_dev->sofar++; pkt_dev->seq_num++; - pkt_dev->tx_bytes += pkt_dev->cur_pkt_size; + pkt_dev->tx_bytes += pkt_dev->last_pkt_size; break; default: /* Drivers are not supposed to return other values! */ if (net_ratelimit()) @@ -3475,6 +3477,7 @@ static void pktgen_xmit(struct pktgen_dev *pkt_dev) atomic_dec(&(pkt_dev->skb->users)); pkt_dev->last_ok = 0; } +unlock: __netif_tx_unlock_bh(txq); /* If pkt_dev->count is zero, then run forever */ @@ -3622,6 +3625,7 @@ static int pktgen_add_device(struct pktgen_thread *t, const char *ifname) { struct pktgen_dev *pkt_dev; int err; + int node = cpu_to_node(t->cpu); /* We don't allow a device to be on several threads */ @@ -3631,12 +3635,13 @@ static int pktgen_add_device(struct pktgen_thread *t, const char *ifname) return -EBUSY; } - pkt_dev = kzalloc(sizeof(struct pktgen_dev), GFP_KERNEL); + pkt_dev = kzalloc_node(sizeof(struct pktgen_dev), GFP_KERNEL, node); if (!pkt_dev) return -ENOMEM; strcpy(pkt_dev->odevname, ifname); - pkt_dev->flows = vmalloc(MAX_CFLOWS * sizeof(struct flow_state)); + pkt_dev->flows = vmalloc_node(MAX_CFLOWS * sizeof(struct flow_state), + node); if (pkt_dev->flows == NULL) { kfree(pkt_dev); return -ENOMEM; @@ -3698,7 +3703,8 @@ static int __init pktgen_create_thread(int cpu) struct proc_dir_entry *pe; struct task_struct *p; - t = kzalloc(sizeof(struct pktgen_thread), GFP_KERNEL); + t = kzalloc_node(sizeof(struct pktgen_thread), GFP_KERNEL, + cpu_to_node(cpu)); if (!t) { printk(KERN_ERR "pktgen: ERROR: out of memory, can't " "create new thread.\n"); diff --git a/net/core/rtnetlink.c b/net/core/rtnetlink.c index eb42873f2a3a..33148a568199 100644 --- a/net/core/rtnetlink.c +++ b/net/core/rtnetlink.c @@ -38,7 +38,6 @@ #include <asm/uaccess.h> #include <asm/system.h> -#include <asm/string.h> #include <linux/inet.h> #include <linux/netdevice.h> @@ -53,8 +52,7 @@ #include <net/rtnetlink.h> #include <net/net_namespace.h> -struct rtnl_link -{ +struct rtnl_link { rtnl_doit_func doit; rtnl_dumpit_func dumpit; }; @@ -65,6 +63,7 @@ void rtnl_lock(void) { mutex_lock(&rtnl_mutex); } +EXPORT_SYMBOL(rtnl_lock); void __rtnl_unlock(void) { @@ -76,16 +75,19 @@ void rtnl_unlock(void) /* This fellow will unlock it for us. */ netdev_run_todo(); } +EXPORT_SYMBOL(rtnl_unlock); int rtnl_trylock(void) { return mutex_trylock(&rtnl_mutex); } +EXPORT_SYMBOL(rtnl_trylock); int rtnl_is_locked(void) { return mutex_is_locked(&rtnl_mutex); } +EXPORT_SYMBOL(rtnl_is_locked); static struct rtnl_link *rtnl_msg_handlers[NPROTO]; @@ -168,7 +170,6 @@ int __rtnl_register(int protocol, int msgtype, return 0; } - EXPORT_SYMBOL_GPL(__rtnl_register); /** @@ -188,7 +189,6 @@ void rtnl_register(int protocol, int msgtype, "protocol = %d, message type = %d\n", protocol, msgtype); } - EXPORT_SYMBOL_GPL(rtnl_register); /** @@ -213,7 +213,6 @@ int rtnl_unregister(int protocol, int msgtype) return 0; } - EXPORT_SYMBOL_GPL(rtnl_unregister); /** @@ -230,7 +229,6 @@ void rtnl_unregister_all(int protocol) kfree(rtnl_msg_handlers[protocol]); rtnl_msg_handlers[protocol] = NULL; } - EXPORT_SYMBOL_GPL(rtnl_unregister_all); static LIST_HEAD(link_ops); @@ -248,12 +246,11 @@ static LIST_HEAD(link_ops); int __rtnl_link_register(struct rtnl_link_ops *ops) { if (!ops->dellink) - ops->dellink = unregister_netdevice; + ops->dellink = unregister_netdevice_queue; list_add_tail(&ops->list, &link_ops); return 0; } - EXPORT_SYMBOL_GPL(__rtnl_link_register); /** @@ -271,19 +268,18 @@ int rtnl_link_register(struct rtnl_link_ops *ops) rtnl_unlock(); return err; } - EXPORT_SYMBOL_GPL(rtnl_link_register); static void __rtnl_kill_links(struct net *net, struct rtnl_link_ops *ops) { struct net_device *dev; -restart: + LIST_HEAD(list_kill); + for_each_netdev(net, dev) { - if (dev->rtnl_link_ops == ops) { - ops->dellink(dev); - goto restart; - } + if (dev->rtnl_link_ops == ops) + ops->dellink(dev, &list_kill); } + unregister_netdevice_many(&list_kill); } void rtnl_kill_links(struct net *net, struct rtnl_link_ops *ops) @@ -309,7 +305,6 @@ void __rtnl_link_unregister(struct rtnl_link_ops *ops) } list_del(&ops->list); } - EXPORT_SYMBOL_GPL(__rtnl_link_unregister); /** @@ -322,7 +317,6 @@ void rtnl_link_unregister(struct rtnl_link_ops *ops) __rtnl_link_unregister(ops); rtnl_unlock(); } - EXPORT_SYMBOL_GPL(rtnl_link_unregister); static const struct rtnl_link_ops *rtnl_link_ops_get(const char *kind) @@ -427,12 +421,13 @@ void __rta_fill(struct sk_buff *skb, int attrtype, int attrlen, const void *data struct rtattr *rta; int size = RTA_LENGTH(attrlen); - rta = (struct rtattr*)skb_put(skb, RTA_ALIGN(size)); + rta = (struct rtattr *)skb_put(skb, RTA_ALIGN(size)); rta->rta_type = attrtype; rta->rta_len = size; memcpy(RTA_DATA(rta), data, attrlen); memset(RTA_DATA(rta) + attrlen, 0, RTA_ALIGN(size) - size); } +EXPORT_SYMBOL(__rta_fill); int rtnetlink_send(struct sk_buff *skb, struct net *net, u32 pid, unsigned group, int echo) { @@ -454,6 +449,7 @@ int rtnl_unicast(struct sk_buff *skb, struct net *net, u32 pid) return nlmsg_unicast(rtnl, skb, pid); } +EXPORT_SYMBOL(rtnl_unicast); void rtnl_notify(struct sk_buff *skb, struct net *net, u32 pid, u32 group, struct nlmsghdr *nlh, gfp_t flags) @@ -466,6 +462,7 @@ void rtnl_notify(struct sk_buff *skb, struct net *net, u32 pid, u32 group, nlmsg_notify(rtnl, skb, pid, group, report, flags); } +EXPORT_SYMBOL(rtnl_notify); void rtnl_set_sk_err(struct net *net, u32 group, int error) { @@ -473,6 +470,7 @@ void rtnl_set_sk_err(struct net *net, u32 group, int error) netlink_set_err(rtnl, 0, group, error); } +EXPORT_SYMBOL(rtnl_set_sk_err); int rtnetlink_put_metrics(struct sk_buff *skb, u32 *metrics) { @@ -501,6 +499,7 @@ nla_put_failure: nla_nest_cancel(skb, mx); return -EMSGSIZE; } +EXPORT_SYMBOL(rtnetlink_put_metrics); int rtnl_put_cacheinfo(struct sk_buff *skb, struct dst_entry *dst, u32 id, u32 ts, u32 tsage, long expires, u32 error) @@ -520,14 +519,13 @@ int rtnl_put_cacheinfo(struct sk_buff *skb, struct dst_entry *dst, u32 id, return nla_put(skb, RTA_CACHEINFO, sizeof(ci), &ci); } - EXPORT_SYMBOL_GPL(rtnl_put_cacheinfo); static void set_operstate(struct net_device *dev, unsigned char transition) { unsigned char operstate = dev->operstate; - switch(transition) { + switch (transition) { case IF_OPER_UP: if ((operstate == IF_OPER_DORMANT || operstate == IF_OPER_UNKNOWN) && @@ -682,22 +680,33 @@ nla_put_failure: static int rtnl_dump_ifinfo(struct sk_buff *skb, struct netlink_callback *cb) { struct net *net = sock_net(skb->sk); - int idx; - int s_idx = cb->args[0]; + int h, s_h; + int idx = 0, s_idx; struct net_device *dev; - - idx = 0; - for_each_netdev(net, dev) { - if (idx < s_idx) - goto cont; - if (rtnl_fill_ifinfo(skb, dev, RTM_NEWLINK, - NETLINK_CB(cb->skb).pid, - cb->nlh->nlmsg_seq, 0, NLM_F_MULTI) <= 0) - break; + struct hlist_head *head; + struct hlist_node *node; + + s_h = cb->args[0]; + s_idx = cb->args[1]; + + for (h = s_h; h < NETDEV_HASHENTRIES; h++, s_idx = 0) { + idx = 0; + head = &net->dev_index_head[h]; + hlist_for_each_entry(dev, node, head, index_hlist) { + if (idx < s_idx) + goto cont; + if (rtnl_fill_ifinfo(skb, dev, RTM_NEWLINK, + NETLINK_CB(cb->skb).pid, + cb->nlh->nlmsg_seq, 0, + NLM_F_MULTI) <= 0) + goto out; cont: - idx++; + idx++; + } } - cb->args[0] = idx; +out: + cb->args[1] = idx; + cb->args[0] = h; return skb->len; } @@ -717,12 +726,27 @@ const struct nla_policy ifla_policy[IFLA_MAX+1] = { [IFLA_NET_NS_PID] = { .type = NLA_U32 }, [IFLA_IFALIAS] = { .type = NLA_STRING, .len = IFALIASZ-1 }, }; +EXPORT_SYMBOL(ifla_policy); static const struct nla_policy ifla_info_policy[IFLA_INFO_MAX+1] = { [IFLA_INFO_KIND] = { .type = NLA_STRING }, [IFLA_INFO_DATA] = { .type = NLA_NESTED }, }; +struct net *rtnl_link_get_net(struct net *src_net, struct nlattr *tb[]) +{ + struct net *net; + /* Examine the link attributes and figure out which + * network namespace we are talking about. + */ + if (tb[IFLA_NET_NS_PID]) + net = get_net_ns_by_pid(nla_get_u32(tb[IFLA_NET_NS_PID])); + else + net = get_net(src_net); + return net; +} +EXPORT_SYMBOL(rtnl_link_get_net); + static int validate_linkmsg(struct net_device *dev, struct nlattr *tb[]) { if (dev) { @@ -746,8 +770,7 @@ static int do_setlink(struct net_device *dev, struct ifinfomsg *ifm, int err; if (tb[IFLA_NET_NS_PID]) { - struct net *net; - net = get_net_ns_by_pid(nla_get_u32(tb[IFLA_NET_NS_PID])); + struct net *net = rtnl_link_get_net(dev_net(dev), tb); if (IS_ERR(net)) { err = PTR_ERR(net); goto errout; @@ -910,9 +933,9 @@ static int rtnl_setlink(struct sk_buff *skb, struct nlmsghdr *nlh, void *arg) err = -EINVAL; ifm = nlmsg_data(nlh); if (ifm->ifi_index > 0) - dev = dev_get_by_index(net, ifm->ifi_index); + dev = __dev_get_by_index(net, ifm->ifi_index); else if (tb[IFLA_IFNAME]) - dev = dev_get_by_name(net, ifname); + dev = __dev_get_by_name(net, ifname); else goto errout; @@ -921,12 +944,11 @@ static int rtnl_setlink(struct sk_buff *skb, struct nlmsghdr *nlh, void *arg) goto errout; } - if ((err = validate_linkmsg(dev, tb)) < 0) - goto errout_dev; + err = validate_linkmsg(dev, tb); + if (err < 0) + goto errout; err = do_setlink(dev, ifm, tb, ifname, 0); -errout_dev: - dev_put(dev); errout: return err; } @@ -963,12 +985,12 @@ static int rtnl_dellink(struct sk_buff *skb, struct nlmsghdr *nlh, void *arg) if (!ops) return -EOPNOTSUPP; - ops->dellink(dev); + ops->dellink(dev, NULL); return 0; } -struct net_device *rtnl_create_link(struct net *net, char *ifname, - const struct rtnl_link_ops *ops, struct nlattr *tb[]) +struct net_device *rtnl_create_link(struct net *src_net, struct net *net, + char *ifname, const struct rtnl_link_ops *ops, struct nlattr *tb[]) { int err; struct net_device *dev; @@ -976,7 +998,8 @@ struct net_device *rtnl_create_link(struct net *net, char *ifname, unsigned int real_num_queues = 1; if (ops->get_tx_queues) { - err = ops->get_tx_queues(net, tb, &num_queues, &real_num_queues); + err = ops->get_tx_queues(src_net, tb, &num_queues, + &real_num_queues); if (err) goto err; } @@ -985,16 +1008,16 @@ struct net_device *rtnl_create_link(struct net *net, char *ifname, if (!dev) goto err; + dev_net_set(dev, net); + dev->rtnl_link_ops = ops; dev->real_num_tx_queues = real_num_queues; + if (strchr(dev->name, '%')) { err = dev_alloc_name(dev, dev->name); if (err < 0) goto err_free; } - dev_net_set(dev, net); - dev->rtnl_link_ops = ops; - if (tb[IFLA_MTU]) dev->mtu = nla_get_u32(tb[IFLA_MTU]); if (tb[IFLA_ADDRESS]) @@ -1017,6 +1040,7 @@ err_free: err: return ERR_PTR(err); } +EXPORT_SYMBOL(rtnl_create_link); static int rtnl_newlink(struct sk_buff *skb, struct nlmsghdr *nlh, void *arg) { @@ -1050,7 +1074,8 @@ replay: else dev = NULL; - if ((err = validate_linkmsg(dev, tb)) < 0) + err = validate_linkmsg(dev, tb); + if (err < 0) return err; if (tb[IFLA_LINKINFO]) { @@ -1071,6 +1096,7 @@ replay: if (1) { struct nlattr *attr[ops ? ops->maxtype + 1 : 0], **data = NULL; + struct net *dest_net; if (ops) { if (ops->maxtype && linkinfo[IFLA_INFO_DATA]) { @@ -1135,17 +1161,19 @@ replay: if (!ifname[0]) snprintf(ifname, IFNAMSIZ, "%s%%d", ops->kind); - dev = rtnl_create_link(net, ifname, ops, tb); + dest_net = rtnl_link_get_net(net, tb); + dev = rtnl_create_link(net, dest_net, ifname, ops, tb); if (IS_ERR(dev)) err = PTR_ERR(dev); else if (ops->newlink) - err = ops->newlink(dev, tb, data); + err = ops->newlink(net, dev, tb, data); else err = register_netdevice(dev); - if (err < 0 && !IS_ERR(dev)) free_netdev(dev); + + put_net(dest_net); return err; } } @@ -1154,6 +1182,7 @@ static int rtnl_getlink(struct sk_buff *skb, struct nlmsghdr* nlh, void *arg) { struct net *net = sock_net(skb->sk); struct ifinfomsg *ifm; + char ifname[IFNAMSIZ]; struct nlattr *tb[IFLA_MAX+1]; struct net_device *dev = NULL; struct sk_buff *nskb; @@ -1163,19 +1192,23 @@ static int rtnl_getlink(struct sk_buff *skb, struct nlmsghdr* nlh, void *arg) if (err < 0) return err; + if (tb[IFLA_IFNAME]) + nla_strlcpy(ifname, tb[IFLA_IFNAME], IFNAMSIZ); + ifm = nlmsg_data(nlh); - if (ifm->ifi_index > 0) { - dev = dev_get_by_index(net, ifm->ifi_index); - if (dev == NULL) - return -ENODEV; - } else + if (ifm->ifi_index > 0) + dev = __dev_get_by_index(net, ifm->ifi_index); + else if (tb[IFLA_IFNAME]) + dev = __dev_get_by_name(net, ifname); + else return -EINVAL; + if (dev == NULL) + return -ENODEV; + nskb = nlmsg_new(if_nlmsg_size(dev), GFP_KERNEL); - if (nskb == NULL) { - err = -ENOBUFS; - goto errout; - } + if (nskb == NULL) + return -ENOBUFS; err = rtnl_fill_ifinfo(nskb, dev, RTM_NEWLINK, NETLINK_CB(skb).pid, nlh->nlmsg_seq, 0, 0); @@ -1183,11 +1216,8 @@ static int rtnl_getlink(struct sk_buff *skb, struct nlmsghdr* nlh, void *arg) /* -EMSGSIZE implies BUG in if_nlmsg_size */ WARN_ON(err == -EMSGSIZE); kfree_skb(nskb); - goto errout; - } - err = rtnl_unicast(nskb, net, NETLINK_CB(skb).pid); -errout: - dev_put(dev); + } else + err = rtnl_unicast(nskb, net, NETLINK_CB(skb).pid); return err; } @@ -1199,7 +1229,7 @@ static int rtnl_dump_all(struct sk_buff *skb, struct netlink_callback *cb) if (s_idx == 0) s_idx = 1; - for (idx=1; idx<NPROTO; idx++) { + for (idx = 1; idx < NPROTO; idx++) { int type = cb->nlh->nlmsg_type-RTM_BASE; if (idx < s_idx || idx == PF_PACKET) continue; @@ -1266,7 +1296,7 @@ static int rtnetlink_rcv_msg(struct sk_buff *skb, struct nlmsghdr *nlh) if (nlh->nlmsg_len < NLMSG_LENGTH(sizeof(struct rtgenmsg))) return 0; - family = ((struct rtgenmsg*)NLMSG_DATA(nlh))->rtgen_family; + family = ((struct rtgenmsg *)NLMSG_DATA(nlh))->rtgen_family; if (family >= NPROTO) return -EAFNOSUPPORT; @@ -1299,7 +1329,7 @@ static int rtnetlink_rcv_msg(struct sk_buff *skb, struct nlmsghdr *nlh) if (nlh->nlmsg_len > min_len) { int attrlen = nlh->nlmsg_len - NLMSG_ALIGN(min_len); - struct rtattr *attr = (void*)nlh + NLMSG_ALIGN(min_len); + struct rtattr *attr = (void *)nlh + NLMSG_ALIGN(min_len); while (RTA_OK(attr, attrlen)) { unsigned flavor = attr->rta_type; @@ -1405,14 +1435,3 @@ void __init rtnetlink_init(void) rtnl_register(PF_UNSPEC, RTM_GETROUTE, NULL, rtnl_dump_all); } -EXPORT_SYMBOL(__rta_fill); -EXPORT_SYMBOL(rtnetlink_put_metrics); -EXPORT_SYMBOL(rtnl_lock); -EXPORT_SYMBOL(rtnl_trylock); -EXPORT_SYMBOL(rtnl_unlock); -EXPORT_SYMBOL(rtnl_is_locked); -EXPORT_SYMBOL(rtnl_unicast); -EXPORT_SYMBOL(rtnl_notify); -EXPORT_SYMBOL(rtnl_set_sk_err); -EXPORT_SYMBOL(rtnl_create_link); -EXPORT_SYMBOL(ifla_policy); diff --git a/net/core/skb_dma_map.c b/net/core/skb_dma_map.c deleted file mode 100644 index 79687dfd6957..000000000000 --- a/net/core/skb_dma_map.c +++ /dev/null @@ -1,65 +0,0 @@ -/* skb_dma_map.c: DMA mapping helpers for socket buffers. - * - * Copyright (C) David S. Miller <davem@davemloft.net> - */ - -#include <linux/kernel.h> -#include <linux/module.h> -#include <linux/dma-mapping.h> -#include <linux/skbuff.h> - -int skb_dma_map(struct device *dev, struct sk_buff *skb, - enum dma_data_direction dir) -{ - struct skb_shared_info *sp = skb_shinfo(skb); - dma_addr_t map; - int i; - - map = dma_map_single(dev, skb->data, - skb_headlen(skb), dir); - if (dma_mapping_error(dev, map)) - goto out_err; - - sp->dma_head = map; - for (i = 0; i < sp->nr_frags; i++) { - skb_frag_t *fp = &sp->frags[i]; - - map = dma_map_page(dev, fp->page, fp->page_offset, - fp->size, dir); - if (dma_mapping_error(dev, map)) - goto unwind; - sp->dma_maps[i] = map; - } - - return 0; - -unwind: - while (--i >= 0) { - skb_frag_t *fp = &sp->frags[i]; - - dma_unmap_page(dev, sp->dma_maps[i], - fp->size, dir); - } - dma_unmap_single(dev, sp->dma_head, - skb_headlen(skb), dir); -out_err: - return -ENOMEM; -} -EXPORT_SYMBOL(skb_dma_map); - -void skb_dma_unmap(struct device *dev, struct sk_buff *skb, - enum dma_data_direction dir) -{ - struct skb_shared_info *sp = skb_shinfo(skb); - int i; - - dma_unmap_single(dev, sp->dma_head, - skb_headlen(skb), dir); - for (i = 0; i < sp->nr_frags; i++) { - skb_frag_t *fp = &sp->frags[i]; - - dma_unmap_page(dev, sp->dma_maps[i], - fp->size, dir); - } -} -EXPORT_SYMBOL(skb_dma_unmap); diff --git a/net/core/skbuff.c b/net/core/skbuff.c index ec85681a7dd8..bfa3e7865a8c 100644 --- a/net/core/skbuff.c +++ b/net/core/skbuff.c @@ -493,6 +493,9 @@ int skb_recycle_check(struct sk_buff *skb, int skb_size) { struct skb_shared_info *shinfo; + if (irqs_disabled()) + return 0; + if (skb_is_nonlinear(skb) || skb->fclone != SKB_FCLONE_UNAVAILABLE) return 0; @@ -546,7 +549,7 @@ static void __copy_skb_header(struct sk_buff *new, const struct sk_buff *old) #endif new->protocol = old->protocol; new->mark = old->mark; - new->iif = old->iif; + new->skb_iif = old->skb_iif; __nf_copy(new, old); #if defined(CONFIG_NETFILTER_XT_TARGET_TRACE) || \ defined(CONFIG_NETFILTER_XT_TARGET_TRACE_MODULE) diff --git a/net/core/sock.c b/net/core/sock.c index 7626b6aacd68..76ff58d43e26 100644 --- a/net/core/sock.c +++ b/net/core/sock.c @@ -274,25 +274,27 @@ static void sock_disable_timestamp(struct sock *sk, int flag) int sock_queue_rcv_skb(struct sock *sk, struct sk_buff *skb) { - int err = 0; + int err; int skb_len; + unsigned long flags; + struct sk_buff_head *list = &sk->sk_receive_queue; /* Cast sk->rcvbuf to unsigned... It's pointless, but reduces number of warnings when compiling with -W --ANK */ if (atomic_read(&sk->sk_rmem_alloc) + skb->truesize >= (unsigned)sk->sk_rcvbuf) { - err = -ENOMEM; - goto out; + atomic_inc(&sk->sk_drops); + return -ENOMEM; } err = sk_filter(sk, skb); if (err) - goto out; + return err; if (!sk_rmem_schedule(sk, skb->truesize)) { - err = -ENOBUFS; - goto out; + atomic_inc(&sk->sk_drops); + return -ENOBUFS; } skb->dev = NULL; @@ -305,12 +307,14 @@ int sock_queue_rcv_skb(struct sock *sk, struct sk_buff *skb) */ skb_len = skb->len; - skb_queue_tail(&sk->sk_receive_queue, skb); + spin_lock_irqsave(&list->lock, flags); + skb->dropcount = atomic_read(&sk->sk_drops); + __skb_queue_tail(list, skb); + spin_unlock_irqrestore(&list->lock, flags); if (!sock_flag(sk, SOCK_DEAD)) sk->sk_data_ready(sk, skb_len); -out: - return err; + return 0; } EXPORT_SYMBOL(sock_queue_rcv_skb); @@ -348,11 +352,18 @@ discard_and_relse: } EXPORT_SYMBOL(sk_receive_skb); +void sk_reset_txq(struct sock *sk) +{ + sk_tx_queue_clear(sk); +} +EXPORT_SYMBOL(sk_reset_txq); + struct dst_entry *__sk_dst_check(struct sock *sk, u32 cookie) { struct dst_entry *dst = sk->sk_dst_cache; if (dst && dst->obsolete && dst->ops->check(dst, cookie) == NULL) { + sk_tx_queue_clear(sk); sk->sk_dst_cache = NULL; dst_release(dst); return NULL; @@ -406,17 +417,18 @@ static int sock_bindtodevice(struct sock *sk, char __user *optval, int optlen) if (copy_from_user(devname, optval, optlen)) goto out; - if (devname[0] == '\0') { - index = 0; - } else { - struct net_device *dev = dev_get_by_name(net, devname); + index = 0; + if (devname[0] != '\0') { + struct net_device *dev; + rcu_read_lock(); + dev = dev_get_by_name_rcu(net, devname); + if (dev) + index = dev->ifindex; + rcu_read_unlock(); ret = -ENODEV; if (!dev) goto out; - - index = dev->ifindex; - dev_put(dev); } lock_sock(sk); @@ -702,6 +714,12 @@ set_rcvbuf: /* We implement the SO_SNDLOWAT etc to not be settable (1003.1g 5.3) */ + case SO_RXQ_OVFL: + if (valbool) + sock_set_flag(sk, SOCK_RXQ_OVFL); + else + sock_reset_flag(sk, SOCK_RXQ_OVFL); + break; default: ret = -ENOPROTOOPT; break; @@ -901,6 +919,10 @@ int sock_getsockopt(struct socket *sock, int level, int optname, v.val = sk->sk_mark; break; + case SO_RXQ_OVFL: + v.val = !!sock_flag(sk, SOCK_RXQ_OVFL); + break; + default: return -ENOPROTOOPT; } @@ -939,7 +961,8 @@ static void sock_copy(struct sock *nsk, const struct sock *osk) void *sptr = nsk->sk_security; #endif BUILD_BUG_ON(offsetof(struct sock, sk_copy_start) != - sizeof(osk->sk_node) + sizeof(osk->sk_refcnt)); + sizeof(osk->sk_node) + sizeof(osk->sk_refcnt) + + sizeof(osk->sk_tx_queue_mapping)); memcpy(&nsk->sk_copy_start, &osk->sk_copy_start, osk->sk_prot->obj_size - offsetof(struct sock, sk_copy_start)); #ifdef CONFIG_SECURITY_NETWORK @@ -983,6 +1006,7 @@ static struct sock *sk_prot_alloc(struct proto *prot, gfp_t priority, if (!try_module_get(prot->owner)) goto out_free_sec; + sk_tx_queue_clear(sk); } return sk; diff --git a/net/core/sysctl_net_core.c b/net/core/sysctl_net_core.c index 267314664813..06124872af5b 100644 --- a/net/core/sysctl_net_core.c +++ b/net/core/sysctl_net_core.c @@ -123,7 +123,7 @@ static __net_init int sysctl_core_net_init(struct net *net) net->core.sysctl_somaxconn = SOMAXCONN; tbl = netns_core_table; - if (net != &init_net) { + if (!net_eq(net, &init_net)) { tbl = kmemdup(tbl, sizeof(netns_core_table), GFP_KERNEL); if (tbl == NULL) goto err_dup; diff --git a/net/dcb/dcbnl.c b/net/dcb/dcbnl.c index ac1205df6c86..db9f5b39388f 100644 --- a/net/dcb/dcbnl.c +++ b/net/dcb/dcbnl.c @@ -1085,8 +1085,8 @@ static int dcbnl_bcn_setcfg(struct net_device *netdev, struct nlattr **tb, u8 value_byte; u32 value_int; - if (!tb[DCB_ATTR_BCN] || !netdev->dcbnl_ops->setbcncfg - || !netdev->dcbnl_ops->setbcnrp) + if (!tb[DCB_ATTR_BCN] || !netdev->dcbnl_ops->setbcncfg || + !netdev->dcbnl_ops->setbcnrp) return ret; ret = nla_parse_nested(data, DCB_BCN_ATTR_MAX, @@ -1126,7 +1126,7 @@ static int dcb_doit(struct sk_buff *skb, struct nlmsghdr *nlh, void *arg) u32 pid = skb ? NETLINK_CB(skb).pid : 0; int ret = -EINVAL; - if (net != &init_net) + if (!net_eq(net, &init_net)) return -EINVAL; ret = nlmsg_parse(nlh, sizeof(*dcb), tb, DCB_ATTR_MAX, diff --git a/net/dccp/ccids/ccid2.c b/net/dccp/ccids/ccid2.c index e8cf99e880b0..a47a8c918ee8 100644 --- a/net/dccp/ccids/ccid2.c +++ b/net/dccp/ccids/ccid2.c @@ -33,20 +33,20 @@ static int ccid2_debug; #define ccid2_pr_debug(format, a...) DCCP_PR_DEBUG(ccid2_debug, format, ##a) -static void ccid2_hc_tx_check_sanity(const struct ccid2_hc_tx_sock *hctx) +static void ccid2_hc_tx_check_sanity(const struct ccid2_hc_tx_sock *hc) { int len = 0; int pipe = 0; - struct ccid2_seq *seqp = hctx->ccid2hctx_seqh; + struct ccid2_seq *seqp = hc->tx_seqh; /* there is data in the chain */ - if (seqp != hctx->ccid2hctx_seqt) { + if (seqp != hc->tx_seqt) { seqp = seqp->ccid2s_prev; len++; if (!seqp->ccid2s_acked) pipe++; - while (seqp != hctx->ccid2hctx_seqt) { + while (seqp != hc->tx_seqt) { struct ccid2_seq *prev = seqp->ccid2s_prev; len++; @@ -63,30 +63,30 @@ static void ccid2_hc_tx_check_sanity(const struct ccid2_hc_tx_sock *hctx) } } - BUG_ON(pipe != hctx->ccid2hctx_pipe); + BUG_ON(pipe != hc->tx_pipe); ccid2_pr_debug("len of chain=%d\n", len); do { seqp = seqp->ccid2s_prev; len++; - } while (seqp != hctx->ccid2hctx_seqh); + } while (seqp != hc->tx_seqh); ccid2_pr_debug("total len=%d\n", len); - BUG_ON(len != hctx->ccid2hctx_seqbufc * CCID2_SEQBUF_LEN); + BUG_ON(len != hc->tx_seqbufc * CCID2_SEQBUF_LEN); } #else #define ccid2_pr_debug(format, a...) -#define ccid2_hc_tx_check_sanity(hctx) +#define ccid2_hc_tx_check_sanity(hc) #endif -static int ccid2_hc_tx_alloc_seq(struct ccid2_hc_tx_sock *hctx) +static int ccid2_hc_tx_alloc_seq(struct ccid2_hc_tx_sock *hc) { struct ccid2_seq *seqp; int i; /* check if we have space to preserve the pointer to the buffer */ - if (hctx->ccid2hctx_seqbufc >= (sizeof(hctx->ccid2hctx_seqbuf) / - sizeof(struct ccid2_seq*))) + if (hc->tx_seqbufc >= (sizeof(hc->tx_seqbuf) / + sizeof(struct ccid2_seq *))) return -ENOMEM; /* allocate buffer and initialize linked list */ @@ -102,29 +102,29 @@ static int ccid2_hc_tx_alloc_seq(struct ccid2_hc_tx_sock *hctx) seqp->ccid2s_prev = &seqp[CCID2_SEQBUF_LEN - 1]; /* This is the first allocation. Initiate the head and tail. */ - if (hctx->ccid2hctx_seqbufc == 0) - hctx->ccid2hctx_seqh = hctx->ccid2hctx_seqt = seqp; + if (hc->tx_seqbufc == 0) + hc->tx_seqh = hc->tx_seqt = seqp; else { /* link the existing list with the one we just created */ - hctx->ccid2hctx_seqh->ccid2s_next = seqp; - seqp->ccid2s_prev = hctx->ccid2hctx_seqh; + hc->tx_seqh->ccid2s_next = seqp; + seqp->ccid2s_prev = hc->tx_seqh; - hctx->ccid2hctx_seqt->ccid2s_prev = &seqp[CCID2_SEQBUF_LEN - 1]; - seqp[CCID2_SEQBUF_LEN - 1].ccid2s_next = hctx->ccid2hctx_seqt; + hc->tx_seqt->ccid2s_prev = &seqp[CCID2_SEQBUF_LEN - 1]; + seqp[CCID2_SEQBUF_LEN - 1].ccid2s_next = hc->tx_seqt; } /* store the original pointer to the buffer so we can free it */ - hctx->ccid2hctx_seqbuf[hctx->ccid2hctx_seqbufc] = seqp; - hctx->ccid2hctx_seqbufc++; + hc->tx_seqbuf[hc->tx_seqbufc] = seqp; + hc->tx_seqbufc++; return 0; } static int ccid2_hc_tx_send_packet(struct sock *sk, struct sk_buff *skb) { - struct ccid2_hc_tx_sock *hctx = ccid2_hc_tx_sk(sk); + struct ccid2_hc_tx_sock *hc = ccid2_hc_tx_sk(sk); - if (hctx->ccid2hctx_pipe < hctx->ccid2hctx_cwnd) + if (hc->tx_pipe < hc->tx_cwnd) return 0; return 1; /* XXX CCID should dequeue when ready instead of polling */ @@ -133,7 +133,7 @@ static int ccid2_hc_tx_send_packet(struct sock *sk, struct sk_buff *skb) static void ccid2_change_l_ack_ratio(struct sock *sk, u32 val) { struct dccp_sock *dp = dccp_sk(sk); - u32 max_ratio = DIV_ROUND_UP(ccid2_hc_tx_sk(sk)->ccid2hctx_cwnd, 2); + u32 max_ratio = DIV_ROUND_UP(ccid2_hc_tx_sk(sk)->tx_cwnd, 2); /* * Ensure that Ack Ratio does not exceed ceil(cwnd/2), which is (2) from @@ -155,10 +155,10 @@ static void ccid2_change_l_ack_ratio(struct sock *sk, u32 val) dp->dccps_l_ack_ratio = val; } -static void ccid2_change_srtt(struct ccid2_hc_tx_sock *hctx, long val) +static void ccid2_change_srtt(struct ccid2_hc_tx_sock *hc, long val) { ccid2_pr_debug("change SRTT to %ld\n", val); - hctx->ccid2hctx_srtt = val; + hc->tx_srtt = val; } static void ccid2_start_rto_timer(struct sock *sk); @@ -166,45 +166,44 @@ static void ccid2_start_rto_timer(struct sock *sk); static void ccid2_hc_tx_rto_expire(unsigned long data) { struct sock *sk = (struct sock *)data; - struct ccid2_hc_tx_sock *hctx = ccid2_hc_tx_sk(sk); + struct ccid2_hc_tx_sock *hc = ccid2_hc_tx_sk(sk); long s; bh_lock_sock(sk); if (sock_owned_by_user(sk)) { - sk_reset_timer(sk, &hctx->ccid2hctx_rtotimer, - jiffies + HZ / 5); + sk_reset_timer(sk, &hc->tx_rtotimer, jiffies + HZ / 5); goto out; } ccid2_pr_debug("RTO_EXPIRE\n"); - ccid2_hc_tx_check_sanity(hctx); + ccid2_hc_tx_check_sanity(hc); /* back-off timer */ - hctx->ccid2hctx_rto <<= 1; + hc->tx_rto <<= 1; - s = hctx->ccid2hctx_rto / HZ; + s = hc->tx_rto / HZ; if (s > 60) - hctx->ccid2hctx_rto = 60 * HZ; + hc->tx_rto = 60 * HZ; ccid2_start_rto_timer(sk); /* adjust pipe, cwnd etc */ - hctx->ccid2hctx_ssthresh = hctx->ccid2hctx_cwnd / 2; - if (hctx->ccid2hctx_ssthresh < 2) - hctx->ccid2hctx_ssthresh = 2; - hctx->ccid2hctx_cwnd = 1; - hctx->ccid2hctx_pipe = 0; + hc->tx_ssthresh = hc->tx_cwnd / 2; + if (hc->tx_ssthresh < 2) + hc->tx_ssthresh = 2; + hc->tx_cwnd = 1; + hc->tx_pipe = 0; /* clear state about stuff we sent */ - hctx->ccid2hctx_seqt = hctx->ccid2hctx_seqh; - hctx->ccid2hctx_packets_acked = 0; + hc->tx_seqt = hc->tx_seqh; + hc->tx_packets_acked = 0; /* clear ack ratio state. */ - hctx->ccid2hctx_rpseq = 0; - hctx->ccid2hctx_rpdupack = -1; + hc->tx_rpseq = 0; + hc->tx_rpdupack = -1; ccid2_change_l_ack_ratio(sk, 1); - ccid2_hc_tx_check_sanity(hctx); + ccid2_hc_tx_check_sanity(hc); out: bh_unlock_sock(sk); sock_put(sk); @@ -212,42 +211,40 @@ out: static void ccid2_start_rto_timer(struct sock *sk) { - struct ccid2_hc_tx_sock *hctx = ccid2_hc_tx_sk(sk); + struct ccid2_hc_tx_sock *hc = ccid2_hc_tx_sk(sk); - ccid2_pr_debug("setting RTO timeout=%ld\n", hctx->ccid2hctx_rto); + ccid2_pr_debug("setting RTO timeout=%ld\n", hc->tx_rto); - BUG_ON(timer_pending(&hctx->ccid2hctx_rtotimer)); - sk_reset_timer(sk, &hctx->ccid2hctx_rtotimer, - jiffies + hctx->ccid2hctx_rto); + BUG_ON(timer_pending(&hc->tx_rtotimer)); + sk_reset_timer(sk, &hc->tx_rtotimer, jiffies + hc->tx_rto); } static void ccid2_hc_tx_packet_sent(struct sock *sk, int more, unsigned int len) { struct dccp_sock *dp = dccp_sk(sk); - struct ccid2_hc_tx_sock *hctx = ccid2_hc_tx_sk(sk); + struct ccid2_hc_tx_sock *hc = ccid2_hc_tx_sk(sk); struct ccid2_seq *next; - hctx->ccid2hctx_pipe++; + hc->tx_pipe++; - hctx->ccid2hctx_seqh->ccid2s_seq = dp->dccps_gss; - hctx->ccid2hctx_seqh->ccid2s_acked = 0; - hctx->ccid2hctx_seqh->ccid2s_sent = jiffies; + hc->tx_seqh->ccid2s_seq = dp->dccps_gss; + hc->tx_seqh->ccid2s_acked = 0; + hc->tx_seqh->ccid2s_sent = jiffies; - next = hctx->ccid2hctx_seqh->ccid2s_next; + next = hc->tx_seqh->ccid2s_next; /* check if we need to alloc more space */ - if (next == hctx->ccid2hctx_seqt) { - if (ccid2_hc_tx_alloc_seq(hctx)) { + if (next == hc->tx_seqt) { + if (ccid2_hc_tx_alloc_seq(hc)) { DCCP_CRIT("packet history - out of memory!"); /* FIXME: find a more graceful way to bail out */ return; } - next = hctx->ccid2hctx_seqh->ccid2s_next; - BUG_ON(next == hctx->ccid2hctx_seqt); + next = hc->tx_seqh->ccid2s_next; + BUG_ON(next == hc->tx_seqt); } - hctx->ccid2hctx_seqh = next; + hc->tx_seqh = next; - ccid2_pr_debug("cwnd=%d pipe=%d\n", hctx->ccid2hctx_cwnd, - hctx->ccid2hctx_pipe); + ccid2_pr_debug("cwnd=%d pipe=%d\n", hc->tx_cwnd, hc->tx_pipe); /* * FIXME: The code below is broken and the variables have been removed @@ -270,12 +267,12 @@ static void ccid2_hc_tx_packet_sent(struct sock *sk, int more, unsigned int len) */ #if 0 /* Ack Ratio. Need to maintain a concept of how many windows we sent */ - hctx->ccid2hctx_arsent++; + hc->tx_arsent++; /* We had an ack loss in this window... */ - if (hctx->ccid2hctx_ackloss) { - if (hctx->ccid2hctx_arsent >= hctx->ccid2hctx_cwnd) { - hctx->ccid2hctx_arsent = 0; - hctx->ccid2hctx_ackloss = 0; + if (hc->tx_ackloss) { + if (hc->tx_arsent >= hc->tx_cwnd) { + hc->tx_arsent = 0; + hc->tx_ackloss = 0; } } else { /* No acks lost up to now... */ @@ -285,28 +282,28 @@ static void ccid2_hc_tx_packet_sent(struct sock *sk, int more, unsigned int len) int denom = dp->dccps_l_ack_ratio * dp->dccps_l_ack_ratio - dp->dccps_l_ack_ratio; - denom = hctx->ccid2hctx_cwnd * hctx->ccid2hctx_cwnd / denom; + denom = hc->tx_cwnd * hc->tx_cwnd / denom; - if (hctx->ccid2hctx_arsent >= denom) { + if (hc->tx_arsent >= denom) { ccid2_change_l_ack_ratio(sk, dp->dccps_l_ack_ratio - 1); - hctx->ccid2hctx_arsent = 0; + hc->tx_arsent = 0; } } else { /* we can't increase ack ratio further [1] */ - hctx->ccid2hctx_arsent = 0; /* or maybe set it to cwnd*/ + hc->tx_arsent = 0; /* or maybe set it to cwnd*/ } } #endif /* setup RTO timer */ - if (!timer_pending(&hctx->ccid2hctx_rtotimer)) + if (!timer_pending(&hc->tx_rtotimer)) ccid2_start_rto_timer(sk); #ifdef CONFIG_IP_DCCP_CCID2_DEBUG do { - struct ccid2_seq *seqp = hctx->ccid2hctx_seqt; + struct ccid2_seq *seqp = hc->tx_seqt; - while (seqp != hctx->ccid2hctx_seqh) { + while (seqp != hc->tx_seqh) { ccid2_pr_debug("out seq=%llu acked=%d time=%lu\n", (unsigned long long)seqp->ccid2s_seq, seqp->ccid2s_acked, seqp->ccid2s_sent); @@ -314,7 +311,7 @@ static void ccid2_hc_tx_packet_sent(struct sock *sk, int more, unsigned int len) } } while (0); ccid2_pr_debug("=========\n"); - ccid2_hc_tx_check_sanity(hctx); + ccid2_hc_tx_check_sanity(hc); #endif } @@ -382,9 +379,9 @@ out_invalid_option: static void ccid2_hc_tx_kill_rto_timer(struct sock *sk) { - struct ccid2_hc_tx_sock *hctx = ccid2_hc_tx_sk(sk); + struct ccid2_hc_tx_sock *hc = ccid2_hc_tx_sk(sk); - sk_stop_timer(sk, &hctx->ccid2hctx_rtotimer); + sk_stop_timer(sk, &hc->tx_rtotimer); ccid2_pr_debug("deleted RTO timer\n"); } @@ -392,75 +389,75 @@ static inline void ccid2_new_ack(struct sock *sk, struct ccid2_seq *seqp, unsigned int *maxincr) { - struct ccid2_hc_tx_sock *hctx = ccid2_hc_tx_sk(sk); + struct ccid2_hc_tx_sock *hc = ccid2_hc_tx_sk(sk); - if (hctx->ccid2hctx_cwnd < hctx->ccid2hctx_ssthresh) { - if (*maxincr > 0 && ++hctx->ccid2hctx_packets_acked == 2) { - hctx->ccid2hctx_cwnd += 1; - *maxincr -= 1; - hctx->ccid2hctx_packets_acked = 0; + if (hc->tx_cwnd < hc->tx_ssthresh) { + if (*maxincr > 0 && ++hc->tx_packets_acked == 2) { + hc->tx_cwnd += 1; + *maxincr -= 1; + hc->tx_packets_acked = 0; } - } else if (++hctx->ccid2hctx_packets_acked >= hctx->ccid2hctx_cwnd) { - hctx->ccid2hctx_cwnd += 1; - hctx->ccid2hctx_packets_acked = 0; + } else if (++hc->tx_packets_acked >= hc->tx_cwnd) { + hc->tx_cwnd += 1; + hc->tx_packets_acked = 0; } /* update RTO */ - if (hctx->ccid2hctx_srtt == -1 || - time_after(jiffies, hctx->ccid2hctx_lastrtt + hctx->ccid2hctx_srtt)) { + if (hc->tx_srtt == -1 || + time_after(jiffies, hc->tx_lastrtt + hc->tx_srtt)) { unsigned long r = (long)jiffies - (long)seqp->ccid2s_sent; int s; /* first measurement */ - if (hctx->ccid2hctx_srtt == -1) { + if (hc->tx_srtt == -1) { ccid2_pr_debug("R: %lu Time=%lu seq=%llu\n", r, jiffies, (unsigned long long)seqp->ccid2s_seq); - ccid2_change_srtt(hctx, r); - hctx->ccid2hctx_rttvar = r >> 1; + ccid2_change_srtt(hc, r); + hc->tx_rttvar = r >> 1; } else { /* RTTVAR */ - long tmp = hctx->ccid2hctx_srtt - r; + long tmp = hc->tx_srtt - r; long srtt; if (tmp < 0) tmp *= -1; tmp >>= 2; - hctx->ccid2hctx_rttvar *= 3; - hctx->ccid2hctx_rttvar >>= 2; - hctx->ccid2hctx_rttvar += tmp; + hc->tx_rttvar *= 3; + hc->tx_rttvar >>= 2; + hc->tx_rttvar += tmp; /* SRTT */ - srtt = hctx->ccid2hctx_srtt; + srtt = hc->tx_srtt; srtt *= 7; srtt >>= 3; tmp = r >> 3; srtt += tmp; - ccid2_change_srtt(hctx, srtt); + ccid2_change_srtt(hc, srtt); } - s = hctx->ccid2hctx_rttvar << 2; + s = hc->tx_rttvar << 2; /* clock granularity is 1 when based on jiffies */ if (!s) s = 1; - hctx->ccid2hctx_rto = hctx->ccid2hctx_srtt + s; + hc->tx_rto = hc->tx_srtt + s; /* must be at least a second */ - s = hctx->ccid2hctx_rto / HZ; + s = hc->tx_rto / HZ; /* DCCP doesn't require this [but I like it cuz my code sux] */ #if 1 if (s < 1) - hctx->ccid2hctx_rto = HZ; + hc->tx_rto = HZ; #endif /* max 60 seconds */ if (s > 60) - hctx->ccid2hctx_rto = HZ * 60; + hc->tx_rto = HZ * 60; - hctx->ccid2hctx_lastrtt = jiffies; + hc->tx_lastrtt = jiffies; ccid2_pr_debug("srtt: %ld rttvar: %ld rto: %ld (HZ=%d) R=%lu\n", - hctx->ccid2hctx_srtt, hctx->ccid2hctx_rttvar, - hctx->ccid2hctx_rto, HZ, r); + hc->tx_srtt, hc->tx_rttvar, + hc->tx_rto, HZ, r); } /* we got a new ack, so re-start RTO timer */ @@ -470,40 +467,40 @@ static inline void ccid2_new_ack(struct sock *sk, static void ccid2_hc_tx_dec_pipe(struct sock *sk) { - struct ccid2_hc_tx_sock *hctx = ccid2_hc_tx_sk(sk); + struct ccid2_hc_tx_sock *hc = ccid2_hc_tx_sk(sk); - if (hctx->ccid2hctx_pipe == 0) + if (hc->tx_pipe == 0) DCCP_BUG("pipe == 0"); else - hctx->ccid2hctx_pipe--; + hc->tx_pipe--; - if (hctx->ccid2hctx_pipe == 0) + if (hc->tx_pipe == 0) ccid2_hc_tx_kill_rto_timer(sk); } static void ccid2_congestion_event(struct sock *sk, struct ccid2_seq *seqp) { - struct ccid2_hc_tx_sock *hctx = ccid2_hc_tx_sk(sk); + struct ccid2_hc_tx_sock *hc = ccid2_hc_tx_sk(sk); - if (time_before(seqp->ccid2s_sent, hctx->ccid2hctx_last_cong)) { + if (time_before(seqp->ccid2s_sent, hc->tx_last_cong)) { ccid2_pr_debug("Multiple losses in an RTT---treating as one\n"); return; } - hctx->ccid2hctx_last_cong = jiffies; + hc->tx_last_cong = jiffies; - hctx->ccid2hctx_cwnd = hctx->ccid2hctx_cwnd / 2 ? : 1U; - hctx->ccid2hctx_ssthresh = max(hctx->ccid2hctx_cwnd, 2U); + hc->tx_cwnd = hc->tx_cwnd / 2 ? : 1U; + hc->tx_ssthresh = max(hc->tx_cwnd, 2U); /* Avoid spurious timeouts resulting from Ack Ratio > cwnd */ - if (dccp_sk(sk)->dccps_l_ack_ratio > hctx->ccid2hctx_cwnd) - ccid2_change_l_ack_ratio(sk, hctx->ccid2hctx_cwnd); + if (dccp_sk(sk)->dccps_l_ack_ratio > hc->tx_cwnd) + ccid2_change_l_ack_ratio(sk, hc->tx_cwnd); } static void ccid2_hc_tx_packet_recv(struct sock *sk, struct sk_buff *skb) { struct dccp_sock *dp = dccp_sk(sk); - struct ccid2_hc_tx_sock *hctx = ccid2_hc_tx_sk(sk); + struct ccid2_hc_tx_sock *hc = ccid2_hc_tx_sk(sk); u64 ackno, seqno; struct ccid2_seq *seqp; unsigned char *vector; @@ -512,7 +509,7 @@ static void ccid2_hc_tx_packet_recv(struct sock *sk, struct sk_buff *skb) int done = 0; unsigned int maxincr = 0; - ccid2_hc_tx_check_sanity(hctx); + ccid2_hc_tx_check_sanity(hc); /* check reverse path congestion */ seqno = DCCP_SKB_CB(skb)->dccpd_seq; @@ -521,21 +518,21 @@ static void ccid2_hc_tx_packet_recv(struct sock *sk, struct sk_buff *skb) * -sorbo. */ /* need to bootstrap */ - if (hctx->ccid2hctx_rpdupack == -1) { - hctx->ccid2hctx_rpdupack = 0; - hctx->ccid2hctx_rpseq = seqno; + if (hc->tx_rpdupack == -1) { + hc->tx_rpdupack = 0; + hc->tx_rpseq = seqno; } else { /* check if packet is consecutive */ - if (dccp_delta_seqno(hctx->ccid2hctx_rpseq, seqno) == 1) - hctx->ccid2hctx_rpseq = seqno; + if (dccp_delta_seqno(hc->tx_rpseq, seqno) == 1) + hc->tx_rpseq = seqno; /* it's a later packet */ - else if (after48(seqno, hctx->ccid2hctx_rpseq)) { - hctx->ccid2hctx_rpdupack++; + else if (after48(seqno, hc->tx_rpseq)) { + hc->tx_rpdupack++; /* check if we got enough dupacks */ - if (hctx->ccid2hctx_rpdupack >= NUMDUPACK) { - hctx->ccid2hctx_rpdupack = -1; /* XXX lame */ - hctx->ccid2hctx_rpseq = 0; + if (hc->tx_rpdupack >= NUMDUPACK) { + hc->tx_rpdupack = -1; /* XXX lame */ + hc->tx_rpseq = 0; ccid2_change_l_ack_ratio(sk, 2 * dp->dccps_l_ack_ratio); } @@ -544,7 +541,7 @@ static void ccid2_hc_tx_packet_recv(struct sock *sk, struct sk_buff *skb) /* check forward path congestion */ /* still didn't send out new data packets */ - if (hctx->ccid2hctx_seqh == hctx->ccid2hctx_seqt) + if (hc->tx_seqh == hc->tx_seqt) return; switch (DCCP_SKB_CB(skb)->dccpd_type) { @@ -556,14 +553,14 @@ static void ccid2_hc_tx_packet_recv(struct sock *sk, struct sk_buff *skb) } ackno = DCCP_SKB_CB(skb)->dccpd_ack_seq; - if (after48(ackno, hctx->ccid2hctx_high_ack)) - hctx->ccid2hctx_high_ack = ackno; + if (after48(ackno, hc->tx_high_ack)) + hc->tx_high_ack = ackno; - seqp = hctx->ccid2hctx_seqt; + seqp = hc->tx_seqt; while (before48(seqp->ccid2s_seq, ackno)) { seqp = seqp->ccid2s_next; - if (seqp == hctx->ccid2hctx_seqh) { - seqp = hctx->ccid2hctx_seqh->ccid2s_prev; + if (seqp == hc->tx_seqh) { + seqp = hc->tx_seqh->ccid2s_prev; break; } } @@ -573,7 +570,7 @@ static void ccid2_hc_tx_packet_recv(struct sock *sk, struct sk_buff *skb) * packets per acknowledgement. Rounding up avoids that cwnd is not * advanced when Ack Ratio is 1 and gives a slight edge otherwise. */ - if (hctx->ccid2hctx_cwnd < hctx->ccid2hctx_ssthresh) + if (hc->tx_cwnd < hc->tx_ssthresh) maxincr = DIV_ROUND_UP(dp->dccps_l_ack_ratio, 2); /* go through all ack vectors */ @@ -592,7 +589,7 @@ static void ccid2_hc_tx_packet_recv(struct sock *sk, struct sk_buff *skb) * seqnos. */ while (after48(seqp->ccid2s_seq, ackno)) { - if (seqp == hctx->ccid2hctx_seqt) { + if (seqp == hc->tx_seqt) { done = 1; break; } @@ -624,7 +621,7 @@ static void ccid2_hc_tx_packet_recv(struct sock *sk, struct sk_buff *skb) (unsigned long long)seqp->ccid2s_seq); ccid2_hc_tx_dec_pipe(sk); } - if (seqp == hctx->ccid2hctx_seqt) { + if (seqp == hc->tx_seqt) { done = 1; break; } @@ -643,11 +640,11 @@ static void ccid2_hc_tx_packet_recv(struct sock *sk, struct sk_buff *skb) /* The state about what is acked should be correct now * Check for NUMDUPACK */ - seqp = hctx->ccid2hctx_seqt; - while (before48(seqp->ccid2s_seq, hctx->ccid2hctx_high_ack)) { + seqp = hc->tx_seqt; + while (before48(seqp->ccid2s_seq, hc->tx_high_ack)) { seqp = seqp->ccid2s_next; - if (seqp == hctx->ccid2hctx_seqh) { - seqp = hctx->ccid2hctx_seqh->ccid2s_prev; + if (seqp == hc->tx_seqh) { + seqp = hc->tx_seqh->ccid2s_prev; break; } } @@ -658,7 +655,7 @@ static void ccid2_hc_tx_packet_recv(struct sock *sk, struct sk_buff *skb) if (done == NUMDUPACK) break; } - if (seqp == hctx->ccid2hctx_seqt) + if (seqp == hc->tx_seqt) break; seqp = seqp->ccid2s_prev; } @@ -681,86 +678,86 @@ static void ccid2_hc_tx_packet_recv(struct sock *sk, struct sk_buff *skb) ccid2_congestion_event(sk, seqp); ccid2_hc_tx_dec_pipe(sk); } - if (seqp == hctx->ccid2hctx_seqt) + if (seqp == hc->tx_seqt) break; seqp = seqp->ccid2s_prev; } - hctx->ccid2hctx_seqt = last_acked; + hc->tx_seqt = last_acked; } /* trim acked packets in tail */ - while (hctx->ccid2hctx_seqt != hctx->ccid2hctx_seqh) { - if (!hctx->ccid2hctx_seqt->ccid2s_acked) + while (hc->tx_seqt != hc->tx_seqh) { + if (!hc->tx_seqt->ccid2s_acked) break; - hctx->ccid2hctx_seqt = hctx->ccid2hctx_seqt->ccid2s_next; + hc->tx_seqt = hc->tx_seqt->ccid2s_next; } - ccid2_hc_tx_check_sanity(hctx); + ccid2_hc_tx_check_sanity(hc); } static int ccid2_hc_tx_init(struct ccid *ccid, struct sock *sk) { - struct ccid2_hc_tx_sock *hctx = ccid_priv(ccid); + struct ccid2_hc_tx_sock *hc = ccid_priv(ccid); struct dccp_sock *dp = dccp_sk(sk); u32 max_ratio; /* RFC 4341, 5: initialise ssthresh to arbitrarily high (max) value */ - hctx->ccid2hctx_ssthresh = ~0U; + hc->tx_ssthresh = ~0U; /* * RFC 4341, 5: "The cwnd parameter is initialized to at most four * packets for new connections, following the rules from [RFC3390]". * We need to convert the bytes of RFC3390 into the packets of RFC 4341. */ - hctx->ccid2hctx_cwnd = clamp(4380U / dp->dccps_mss_cache, 2U, 4U); + hc->tx_cwnd = clamp(4380U / dp->dccps_mss_cache, 2U, 4U); /* Make sure that Ack Ratio is enabled and within bounds. */ - max_ratio = DIV_ROUND_UP(hctx->ccid2hctx_cwnd, 2); + max_ratio = DIV_ROUND_UP(hc->tx_cwnd, 2); if (dp->dccps_l_ack_ratio == 0 || dp->dccps_l_ack_ratio > max_ratio) dp->dccps_l_ack_ratio = max_ratio; /* XXX init ~ to window size... */ - if (ccid2_hc_tx_alloc_seq(hctx)) + if (ccid2_hc_tx_alloc_seq(hc)) return -ENOMEM; - hctx->ccid2hctx_rto = 3 * HZ; - ccid2_change_srtt(hctx, -1); - hctx->ccid2hctx_rttvar = -1; - hctx->ccid2hctx_rpdupack = -1; - hctx->ccid2hctx_last_cong = jiffies; - setup_timer(&hctx->ccid2hctx_rtotimer, ccid2_hc_tx_rto_expire, + hc->tx_rto = 3 * HZ; + ccid2_change_srtt(hc, -1); + hc->tx_rttvar = -1; + hc->tx_rpdupack = -1; + hc->tx_last_cong = jiffies; + setup_timer(&hc->tx_rtotimer, ccid2_hc_tx_rto_expire, (unsigned long)sk); - ccid2_hc_tx_check_sanity(hctx); + ccid2_hc_tx_check_sanity(hc); return 0; } static void ccid2_hc_tx_exit(struct sock *sk) { - struct ccid2_hc_tx_sock *hctx = ccid2_hc_tx_sk(sk); + struct ccid2_hc_tx_sock *hc = ccid2_hc_tx_sk(sk); int i; ccid2_hc_tx_kill_rto_timer(sk); - for (i = 0; i < hctx->ccid2hctx_seqbufc; i++) - kfree(hctx->ccid2hctx_seqbuf[i]); - hctx->ccid2hctx_seqbufc = 0; + for (i = 0; i < hc->tx_seqbufc; i++) + kfree(hc->tx_seqbuf[i]); + hc->tx_seqbufc = 0; } static void ccid2_hc_rx_packet_recv(struct sock *sk, struct sk_buff *skb) { const struct dccp_sock *dp = dccp_sk(sk); - struct ccid2_hc_rx_sock *hcrx = ccid2_hc_rx_sk(sk); + struct ccid2_hc_rx_sock *hc = ccid2_hc_rx_sk(sk); switch (DCCP_SKB_CB(skb)->dccpd_type) { case DCCP_PKT_DATA: case DCCP_PKT_DATAACK: - hcrx->ccid2hcrx_data++; - if (hcrx->ccid2hcrx_data >= dp->dccps_r_ack_ratio) { + hc->rx_data++; + if (hc->rx_data >= dp->dccps_r_ack_ratio) { dccp_send_ack(sk); - hcrx->ccid2hcrx_data = 0; + hc->rx_data = 0; } break; } diff --git a/net/dccp/ccids/ccid2.h b/net/dccp/ccids/ccid2.h index 326ac90fb909..1ec6a30103bb 100644 --- a/net/dccp/ccids/ccid2.h +++ b/net/dccp/ccids/ccid2.h @@ -40,34 +40,34 @@ struct ccid2_seq { /** * struct ccid2_hc_tx_sock - CCID2 TX half connection - * @ccid2hctx_{cwnd,ssthresh,pipe}: as per RFC 4341, section 5 - * @ccid2hctx_packets_acked - Ack counter for deriving cwnd growth (RFC 3465) - * @ccid2hctx_lastrtt -time RTT was last measured - * @ccid2hctx_rpseq - last consecutive seqno - * @ccid2hctx_rpdupack - dupacks since rpseq + * @tx_{cwnd,ssthresh,pipe}: as per RFC 4341, section 5 + * @tx_packets_acked: Ack counter for deriving cwnd growth (RFC 3465) + * @tx_lastrtt: time RTT was last measured + * @tx_rpseq: last consecutive seqno + * @tx_rpdupack: dupacks since rpseq */ struct ccid2_hc_tx_sock { - u32 ccid2hctx_cwnd; - u32 ccid2hctx_ssthresh; - u32 ccid2hctx_pipe; - u32 ccid2hctx_packets_acked; - struct ccid2_seq *ccid2hctx_seqbuf[CCID2_SEQBUF_MAX]; - int ccid2hctx_seqbufc; - struct ccid2_seq *ccid2hctx_seqh; - struct ccid2_seq *ccid2hctx_seqt; - long ccid2hctx_rto; - long ccid2hctx_srtt; - long ccid2hctx_rttvar; - unsigned long ccid2hctx_lastrtt; - struct timer_list ccid2hctx_rtotimer; - u64 ccid2hctx_rpseq; - int ccid2hctx_rpdupack; - unsigned long ccid2hctx_last_cong; - u64 ccid2hctx_high_ack; + u32 tx_cwnd; + u32 tx_ssthresh; + u32 tx_pipe; + u32 tx_packets_acked; + struct ccid2_seq *tx_seqbuf[CCID2_SEQBUF_MAX]; + int tx_seqbufc; + struct ccid2_seq *tx_seqh; + struct ccid2_seq *tx_seqt; + long tx_rto; + long tx_srtt; + long tx_rttvar; + unsigned long tx_lastrtt; + struct timer_list tx_rtotimer; + u64 tx_rpseq; + int tx_rpdupack; + unsigned long tx_last_cong; + u64 tx_high_ack; }; struct ccid2_hc_rx_sock { - int ccid2hcrx_data; + int rx_data; }; static inline struct ccid2_hc_tx_sock *ccid2_hc_tx_sk(const struct sock *sk) diff --git a/net/dccp/ccids/ccid3.c b/net/dccp/ccids/ccid3.c index 34dcc798c457..bcd7632299f5 100644 --- a/net/dccp/ccids/ccid3.c +++ b/net/dccp/ccids/ccid3.c @@ -64,14 +64,14 @@ static const char *ccid3_tx_state_name(enum ccid3_hc_tx_states state) static void ccid3_hc_tx_set_state(struct sock *sk, enum ccid3_hc_tx_states state) { - struct ccid3_hc_tx_sock *hctx = ccid3_hc_tx_sk(sk); - enum ccid3_hc_tx_states oldstate = hctx->ccid3hctx_state; + struct ccid3_hc_tx_sock *hc = ccid3_hc_tx_sk(sk); + enum ccid3_hc_tx_states oldstate = hc->tx_state; ccid3_pr_debug("%s(%p) %-8.8s -> %s\n", dccp_role(sk), sk, ccid3_tx_state_name(oldstate), ccid3_tx_state_name(state)); WARN_ON(state == oldstate); - hctx->ccid3hctx_state = state; + hc->tx_state = state; } /* @@ -85,37 +85,32 @@ static void ccid3_hc_tx_set_state(struct sock *sk, */ static inline u64 rfc3390_initial_rate(struct sock *sk) { - const struct ccid3_hc_tx_sock *hctx = ccid3_hc_tx_sk(sk); - const __u32 w_init = clamp_t(__u32, 4380U, - 2 * hctx->ccid3hctx_s, 4 * hctx->ccid3hctx_s); + const struct ccid3_hc_tx_sock *hc = ccid3_hc_tx_sk(sk); + const __u32 w_init = clamp_t(__u32, 4380U, 2 * hc->tx_s, 4 * hc->tx_s); - return scaled_div(w_init << 6, hctx->ccid3hctx_rtt); + return scaled_div(w_init << 6, hc->tx_rtt); } /* * Recalculate t_ipi and delta (should be called whenever X changes) */ -static void ccid3_update_send_interval(struct ccid3_hc_tx_sock *hctx) +static void ccid3_update_send_interval(struct ccid3_hc_tx_sock *hc) { /* Calculate new t_ipi = s / X_inst (X_inst is in 64 * bytes/second) */ - hctx->ccid3hctx_t_ipi = scaled_div32(((u64)hctx->ccid3hctx_s) << 6, - hctx->ccid3hctx_x); + hc->tx_t_ipi = scaled_div32(((u64)hc->tx_s) << 6, hc->tx_x); /* Calculate new delta by delta = min(t_ipi / 2, t_gran / 2) */ - hctx->ccid3hctx_delta = min_t(u32, hctx->ccid3hctx_t_ipi / 2, - TFRC_OPSYS_HALF_TIME_GRAN); - - ccid3_pr_debug("t_ipi=%u, delta=%u, s=%u, X=%u\n", - hctx->ccid3hctx_t_ipi, hctx->ccid3hctx_delta, - hctx->ccid3hctx_s, (unsigned)(hctx->ccid3hctx_x >> 6)); + hc->tx_delta = min_t(u32, hc->tx_t_ipi / 2, TFRC_OPSYS_HALF_TIME_GRAN); + ccid3_pr_debug("t_ipi=%u, delta=%u, s=%u, X=%u\n", hc->tx_t_ipi, + hc->tx_delta, hc->tx_s, (unsigned)(hc->tx_x >> 6)); } -static u32 ccid3_hc_tx_idle_rtt(struct ccid3_hc_tx_sock *hctx, ktime_t now) +static u32 ccid3_hc_tx_idle_rtt(struct ccid3_hc_tx_sock *hc, ktime_t now) { - u32 delta = ktime_us_delta(now, hctx->ccid3hctx_t_last_win_count); + u32 delta = ktime_us_delta(now, hc->tx_t_last_win_count); - return delta / hctx->ccid3hctx_rtt; + return delta / hc->tx_rtt; } /** @@ -130,9 +125,9 @@ static u32 ccid3_hc_tx_idle_rtt(struct ccid3_hc_tx_sock *hctx, ktime_t now) */ static void ccid3_hc_tx_update_x(struct sock *sk, ktime_t *stamp) { - struct ccid3_hc_tx_sock *hctx = ccid3_hc_tx_sk(sk); - __u64 min_rate = 2 * hctx->ccid3hctx_x_recv; - const __u64 old_x = hctx->ccid3hctx_x; + struct ccid3_hc_tx_sock *hc = ccid3_hc_tx_sk(sk); + __u64 min_rate = 2 * hc->tx_x_recv; + const __u64 old_x = hc->tx_x; ktime_t now = stamp ? *stamp : ktime_get_real(); /* @@ -141,37 +136,31 @@ static void ccid3_hc_tx_update_x(struct sock *sk, ktime_t *stamp) * a sender is idle if it has not sent anything over a 2-RTT-period. * For consistency with X and X_recv, min_rate is also scaled by 2^6. */ - if (ccid3_hc_tx_idle_rtt(hctx, now) >= 2) { + if (ccid3_hc_tx_idle_rtt(hc, now) >= 2) { min_rate = rfc3390_initial_rate(sk); - min_rate = max(min_rate, 2 * hctx->ccid3hctx_x_recv); + min_rate = max(min_rate, 2 * hc->tx_x_recv); } - if (hctx->ccid3hctx_p > 0) { + if (hc->tx_p > 0) { - hctx->ccid3hctx_x = min(((__u64)hctx->ccid3hctx_x_calc) << 6, - min_rate); - hctx->ccid3hctx_x = max(hctx->ccid3hctx_x, - (((__u64)hctx->ccid3hctx_s) << 6) / - TFRC_T_MBI); + hc->tx_x = min(((__u64)hc->tx_x_calc) << 6, min_rate); + hc->tx_x = max(hc->tx_x, (((__u64)hc->tx_s) << 6) / TFRC_T_MBI); - } else if (ktime_us_delta(now, hctx->ccid3hctx_t_ld) - - (s64)hctx->ccid3hctx_rtt >= 0) { + } else if (ktime_us_delta(now, hc->tx_t_ld) - (s64)hc->tx_rtt >= 0) { - hctx->ccid3hctx_x = min(2 * hctx->ccid3hctx_x, min_rate); - hctx->ccid3hctx_x = max(hctx->ccid3hctx_x, - scaled_div(((__u64)hctx->ccid3hctx_s) << 6, - hctx->ccid3hctx_rtt)); - hctx->ccid3hctx_t_ld = now; + hc->tx_x = min(2 * hc->tx_x, min_rate); + hc->tx_x = max(hc->tx_x, + scaled_div(((__u64)hc->tx_s) << 6, hc->tx_rtt)); + hc->tx_t_ld = now; } - if (hctx->ccid3hctx_x != old_x) { + if (hc->tx_x != old_x) { ccid3_pr_debug("X_prev=%u, X_now=%u, X_calc=%u, " "X_recv=%u\n", (unsigned)(old_x >> 6), - (unsigned)(hctx->ccid3hctx_x >> 6), - hctx->ccid3hctx_x_calc, - (unsigned)(hctx->ccid3hctx_x_recv >> 6)); + (unsigned)(hc->tx_x >> 6), hc->tx_x_calc, + (unsigned)(hc->tx_x_recv >> 6)); - ccid3_update_send_interval(hctx); + ccid3_update_send_interval(hc); } } @@ -179,37 +168,37 @@ static void ccid3_hc_tx_update_x(struct sock *sk, ktime_t *stamp) * Track the mean packet size `s' (cf. RFC 4342, 5.3 and RFC 3448, 4.1) * @len: DCCP packet payload size in bytes */ -static inline void ccid3_hc_tx_update_s(struct ccid3_hc_tx_sock *hctx, int len) +static inline void ccid3_hc_tx_update_s(struct ccid3_hc_tx_sock *hc, int len) { - const u16 old_s = hctx->ccid3hctx_s; + const u16 old_s = hc->tx_s; - hctx->ccid3hctx_s = tfrc_ewma(hctx->ccid3hctx_s, len, 9); + hc->tx_s = tfrc_ewma(hc->tx_s, len, 9); - if (hctx->ccid3hctx_s != old_s) - ccid3_update_send_interval(hctx); + if (hc->tx_s != old_s) + ccid3_update_send_interval(hc); } /* * Update Window Counter using the algorithm from [RFC 4342, 8.1]. * As elsewhere, RTT > 0 is assumed by using dccp_sample_rtt(). */ -static inline void ccid3_hc_tx_update_win_count(struct ccid3_hc_tx_sock *hctx, +static inline void ccid3_hc_tx_update_win_count(struct ccid3_hc_tx_sock *hc, ktime_t now) { - u32 delta = ktime_us_delta(now, hctx->ccid3hctx_t_last_win_count), - quarter_rtts = (4 * delta) / hctx->ccid3hctx_rtt; + u32 delta = ktime_us_delta(now, hc->tx_t_last_win_count), + quarter_rtts = (4 * delta) / hc->tx_rtt; if (quarter_rtts > 0) { - hctx->ccid3hctx_t_last_win_count = now; - hctx->ccid3hctx_last_win_count += min(quarter_rtts, 5U); - hctx->ccid3hctx_last_win_count &= 0xF; /* mod 16 */ + hc->tx_t_last_win_count = now; + hc->tx_last_win_count += min(quarter_rtts, 5U); + hc->tx_last_win_count &= 0xF; /* mod 16 */ } } static void ccid3_hc_tx_no_feedback_timer(unsigned long data) { struct sock *sk = (struct sock *)data; - struct ccid3_hc_tx_sock *hctx = ccid3_hc_tx_sk(sk); + struct ccid3_hc_tx_sock *hc = ccid3_hc_tx_sk(sk); unsigned long t_nfb = USEC_PER_SEC / 5; bh_lock_sock(sk); @@ -220,24 +209,23 @@ static void ccid3_hc_tx_no_feedback_timer(unsigned long data) } ccid3_pr_debug("%s(%p, state=%s) - entry \n", dccp_role(sk), sk, - ccid3_tx_state_name(hctx->ccid3hctx_state)); + ccid3_tx_state_name(hc->tx_state)); - if (hctx->ccid3hctx_state == TFRC_SSTATE_FBACK) + if (hc->tx_state == TFRC_SSTATE_FBACK) ccid3_hc_tx_set_state(sk, TFRC_SSTATE_NO_FBACK); - else if (hctx->ccid3hctx_state != TFRC_SSTATE_NO_FBACK) + else if (hc->tx_state != TFRC_SSTATE_NO_FBACK) goto out; /* * Determine new allowed sending rate X as per draft rfc3448bis-00, 4.4 */ - if (hctx->ccid3hctx_t_rto == 0 || /* no feedback received yet */ - hctx->ccid3hctx_p == 0) { + if (hc->tx_t_rto == 0 || /* no feedback received yet */ + hc->tx_p == 0) { /* halve send rate directly */ - hctx->ccid3hctx_x = max(hctx->ccid3hctx_x / 2, - (((__u64)hctx->ccid3hctx_s) << 6) / - TFRC_T_MBI); - ccid3_update_send_interval(hctx); + hc->tx_x = max(hc->tx_x / 2, + (((__u64)hc->tx_s) << 6) / TFRC_T_MBI); + ccid3_update_send_interval(hc); } else { /* * Modify the cached value of X_recv @@ -249,33 +237,32 @@ static void ccid3_hc_tx_no_feedback_timer(unsigned long data) * * Note that X_recv is scaled by 2^6 while X_calc is not */ - BUG_ON(hctx->ccid3hctx_p && !hctx->ccid3hctx_x_calc); + BUG_ON(hc->tx_p && !hc->tx_x_calc); - if (hctx->ccid3hctx_x_calc > (hctx->ccid3hctx_x_recv >> 5)) - hctx->ccid3hctx_x_recv = - max(hctx->ccid3hctx_x_recv / 2, - (((__u64)hctx->ccid3hctx_s) << 6) / - (2 * TFRC_T_MBI)); + if (hc->tx_x_calc > (hc->tx_x_recv >> 5)) + hc->tx_x_recv = + max(hc->tx_x_recv / 2, + (((__u64)hc->tx_s) << 6) / (2*TFRC_T_MBI)); else { - hctx->ccid3hctx_x_recv = hctx->ccid3hctx_x_calc; - hctx->ccid3hctx_x_recv <<= 4; + hc->tx_x_recv = hc->tx_x_calc; + hc->tx_x_recv <<= 4; } ccid3_hc_tx_update_x(sk, NULL); } ccid3_pr_debug("Reduced X to %llu/64 bytes/sec\n", - (unsigned long long)hctx->ccid3hctx_x); + (unsigned long long)hc->tx_x); /* * Set new timeout for the nofeedback timer. * See comments in packet_recv() regarding the value of t_RTO. */ - if (unlikely(hctx->ccid3hctx_t_rto == 0)) /* no feedback yet */ + if (unlikely(hc->tx_t_rto == 0)) /* no feedback yet */ t_nfb = TFRC_INITIAL_TIMEOUT; else - t_nfb = max(hctx->ccid3hctx_t_rto, 2 * hctx->ccid3hctx_t_ipi); + t_nfb = max(hc->tx_t_rto, 2 * hc->tx_t_ipi); restart_timer: - sk_reset_timer(sk, &hctx->ccid3hctx_no_feedback_timer, + sk_reset_timer(sk, &hc->tx_no_feedback_timer, jiffies + usecs_to_jiffies(t_nfb)); out: bh_unlock_sock(sk); @@ -291,7 +278,7 @@ out: static int ccid3_hc_tx_send_packet(struct sock *sk, struct sk_buff *skb) { struct dccp_sock *dp = dccp_sk(sk); - struct ccid3_hc_tx_sock *hctx = ccid3_hc_tx_sk(sk); + struct ccid3_hc_tx_sock *hc = ccid3_hc_tx_sk(sk); ktime_t now = ktime_get_real(); s64 delay; @@ -303,18 +290,17 @@ static int ccid3_hc_tx_send_packet(struct sock *sk, struct sk_buff *skb) if (unlikely(skb->len == 0)) return -EBADMSG; - switch (hctx->ccid3hctx_state) { + switch (hc->tx_state) { case TFRC_SSTATE_NO_SENT: - sk_reset_timer(sk, &hctx->ccid3hctx_no_feedback_timer, - (jiffies + - usecs_to_jiffies(TFRC_INITIAL_TIMEOUT))); - hctx->ccid3hctx_last_win_count = 0; - hctx->ccid3hctx_t_last_win_count = now; + sk_reset_timer(sk, &hc->tx_no_feedback_timer, (jiffies + + usecs_to_jiffies(TFRC_INITIAL_TIMEOUT))); + hc->tx_last_win_count = 0; + hc->tx_t_last_win_count = now; /* Set t_0 for initial packet */ - hctx->ccid3hctx_t_nom = now; + hc->tx_t_nom = now; - hctx->ccid3hctx_s = skb->len; + hc->tx_s = skb->len; /* * Use initial RTT sample when available: recommended by erratum @@ -323,9 +309,9 @@ static int ccid3_hc_tx_send_packet(struct sock *sk, struct sk_buff *skb) */ if (dp->dccps_syn_rtt) { ccid3_pr_debug("SYN RTT = %uus\n", dp->dccps_syn_rtt); - hctx->ccid3hctx_rtt = dp->dccps_syn_rtt; - hctx->ccid3hctx_x = rfc3390_initial_rate(sk); - hctx->ccid3hctx_t_ld = now; + hc->tx_rtt = dp->dccps_syn_rtt; + hc->tx_x = rfc3390_initial_rate(sk); + hc->tx_t_ld = now; } else { /* * Sender does not have RTT sample: @@ -333,17 +319,17 @@ static int ccid3_hc_tx_send_packet(struct sock *sk, struct sk_buff *skb) * is needed in several parts (e.g. window counter); * - set sending rate X_pps = 1pps as per RFC 3448, 4.2. */ - hctx->ccid3hctx_rtt = DCCP_FALLBACK_RTT; - hctx->ccid3hctx_x = hctx->ccid3hctx_s; - hctx->ccid3hctx_x <<= 6; + hc->tx_rtt = DCCP_FALLBACK_RTT; + hc->tx_x = hc->tx_s; + hc->tx_x <<= 6; } - ccid3_update_send_interval(hctx); + ccid3_update_send_interval(hc); ccid3_hc_tx_set_state(sk, TFRC_SSTATE_NO_FBACK); break; case TFRC_SSTATE_NO_FBACK: case TFRC_SSTATE_FBACK: - delay = ktime_us_delta(hctx->ccid3hctx_t_nom, now); + delay = ktime_us_delta(hc->tx_t_nom, now); ccid3_pr_debug("delay=%ld\n", (long)delay); /* * Scheduling of packet transmissions [RFC 3448, 4.6] @@ -353,10 +339,10 @@ static int ccid3_hc_tx_send_packet(struct sock *sk, struct sk_buff *skb) * else * // send the packet in (t_nom - t_now) milliseconds. */ - if (delay - (s64)hctx->ccid3hctx_delta >= 1000) + if (delay - (s64)hc->tx_delta >= 1000) return (u32)delay / 1000L; - ccid3_hc_tx_update_win_count(hctx, now); + ccid3_hc_tx_update_win_count(hc, now); break; case TFRC_SSTATE_TERM: DCCP_BUG("%s(%p) - Illegal state TERM", dccp_role(sk), sk); @@ -365,28 +351,27 @@ static int ccid3_hc_tx_send_packet(struct sock *sk, struct sk_buff *skb) /* prepare to send now (add options etc.) */ dp->dccps_hc_tx_insert_options = 1; - DCCP_SKB_CB(skb)->dccpd_ccval = hctx->ccid3hctx_last_win_count; + DCCP_SKB_CB(skb)->dccpd_ccval = hc->tx_last_win_count; /* set the nominal send time for the next following packet */ - hctx->ccid3hctx_t_nom = ktime_add_us(hctx->ccid3hctx_t_nom, - hctx->ccid3hctx_t_ipi); + hc->tx_t_nom = ktime_add_us(hc->tx_t_nom, hc->tx_t_ipi); return 0; } static void ccid3_hc_tx_packet_sent(struct sock *sk, int more, unsigned int len) { - struct ccid3_hc_tx_sock *hctx = ccid3_hc_tx_sk(sk); + struct ccid3_hc_tx_sock *hc = ccid3_hc_tx_sk(sk); - ccid3_hc_tx_update_s(hctx, len); + ccid3_hc_tx_update_s(hc, len); - if (tfrc_tx_hist_add(&hctx->ccid3hctx_hist, dccp_sk(sk)->dccps_gss)) + if (tfrc_tx_hist_add(&hc->tx_hist, dccp_sk(sk)->dccps_gss)) DCCP_CRIT("packet history - out of memory!"); } static void ccid3_hc_tx_packet_recv(struct sock *sk, struct sk_buff *skb) { - struct ccid3_hc_tx_sock *hctx = ccid3_hc_tx_sk(sk); + struct ccid3_hc_tx_sock *hc = ccid3_hc_tx_sk(sk); struct ccid3_options_received *opt_recv; ktime_t now; unsigned long t_nfb; @@ -397,15 +382,15 @@ static void ccid3_hc_tx_packet_recv(struct sock *sk, struct sk_buff *skb) DCCP_SKB_CB(skb)->dccpd_type == DCCP_PKT_DATAACK)) return; /* ... and only in the established state */ - if (hctx->ccid3hctx_state != TFRC_SSTATE_FBACK && - hctx->ccid3hctx_state != TFRC_SSTATE_NO_FBACK) + if (hc->tx_state != TFRC_SSTATE_FBACK && + hc->tx_state != TFRC_SSTATE_NO_FBACK) return; - opt_recv = &hctx->ccid3hctx_options_received; + opt_recv = &hc->tx_options_received; now = ktime_get_real(); /* Estimate RTT from history if ACK number is valid */ - r_sample = tfrc_tx_hist_rtt(hctx->ccid3hctx_hist, + r_sample = tfrc_tx_hist_rtt(hc->tx_hist, DCCP_SKB_CB(skb)->dccpd_ack_seq, now); if (r_sample == 0) { DCCP_WARN("%s(%p): %s with bogus ACK-%llu\n", dccp_role(sk), sk, @@ -415,37 +400,37 @@ static void ccid3_hc_tx_packet_recv(struct sock *sk, struct sk_buff *skb) } /* Update receive rate in units of 64 * bytes/second */ - hctx->ccid3hctx_x_recv = opt_recv->ccid3or_receive_rate; - hctx->ccid3hctx_x_recv <<= 6; + hc->tx_x_recv = opt_recv->ccid3or_receive_rate; + hc->tx_x_recv <<= 6; /* Update loss event rate (which is scaled by 1e6) */ pinv = opt_recv->ccid3or_loss_event_rate; if (pinv == ~0U || pinv == 0) /* see RFC 4342, 8.5 */ - hctx->ccid3hctx_p = 0; + hc->tx_p = 0; else /* can not exceed 100% */ - hctx->ccid3hctx_p = scaled_div(1, pinv); + hc->tx_p = scaled_div(1, pinv); /* * Validate new RTT sample and update moving average */ r_sample = dccp_sample_rtt(sk, r_sample); - hctx->ccid3hctx_rtt = tfrc_ewma(hctx->ccid3hctx_rtt, r_sample, 9); + hc->tx_rtt = tfrc_ewma(hc->tx_rtt, r_sample, 9); /* * Update allowed sending rate X as per draft rfc3448bis-00, 4.2/3 */ - if (hctx->ccid3hctx_state == TFRC_SSTATE_NO_FBACK) { + if (hc->tx_state == TFRC_SSTATE_NO_FBACK) { ccid3_hc_tx_set_state(sk, TFRC_SSTATE_FBACK); - if (hctx->ccid3hctx_t_rto == 0) { + if (hc->tx_t_rto == 0) { /* * Initial feedback packet: Larger Initial Windows (4.2) */ - hctx->ccid3hctx_x = rfc3390_initial_rate(sk); - hctx->ccid3hctx_t_ld = now; + hc->tx_x = rfc3390_initial_rate(sk); + hc->tx_t_ld = now; - ccid3_update_send_interval(hctx); + ccid3_update_send_interval(hc); goto done_computing_x; - } else if (hctx->ccid3hctx_p == 0) { + } else if (hc->tx_p == 0) { /* * First feedback after nofeedback timer expiry (4.3) */ @@ -454,25 +439,20 @@ static void ccid3_hc_tx_packet_recv(struct sock *sk, struct sk_buff *skb) } /* Update sending rate (step 4 of [RFC 3448, 4.3]) */ - if (hctx->ccid3hctx_p > 0) - hctx->ccid3hctx_x_calc = - tfrc_calc_x(hctx->ccid3hctx_s, - hctx->ccid3hctx_rtt, - hctx->ccid3hctx_p); + if (hc->tx_p > 0) + hc->tx_x_calc = tfrc_calc_x(hc->tx_s, hc->tx_rtt, hc->tx_p); ccid3_hc_tx_update_x(sk, &now); done_computing_x: ccid3_pr_debug("%s(%p), RTT=%uus (sample=%uus), s=%u, " "p=%u, X_calc=%u, X_recv=%u, X=%u\n", - dccp_role(sk), - sk, hctx->ccid3hctx_rtt, r_sample, - hctx->ccid3hctx_s, hctx->ccid3hctx_p, - hctx->ccid3hctx_x_calc, - (unsigned)(hctx->ccid3hctx_x_recv >> 6), - (unsigned)(hctx->ccid3hctx_x >> 6)); + dccp_role(sk), sk, hc->tx_rtt, r_sample, + hc->tx_s, hc->tx_p, hc->tx_x_calc, + (unsigned)(hc->tx_x_recv >> 6), + (unsigned)(hc->tx_x >> 6)); /* unschedule no feedback timer */ - sk_stop_timer(sk, &hctx->ccid3hctx_no_feedback_timer); + sk_stop_timer(sk, &hc->tx_no_feedback_timer); /* * As we have calculated new ipi, delta, t_nom it is possible @@ -486,21 +466,19 @@ done_computing_x: * This can help avoid triggering the nofeedback timer too * often ('spinning') on LANs with small RTTs. */ - hctx->ccid3hctx_t_rto = max_t(u32, 4 * hctx->ccid3hctx_rtt, - (CONFIG_IP_DCCP_CCID3_RTO * - (USEC_PER_SEC / 1000))); + hc->tx_t_rto = max_t(u32, 4 * hc->tx_rtt, (CONFIG_IP_DCCP_CCID3_RTO * + (USEC_PER_SEC / 1000))); /* * Schedule no feedback timer to expire in * max(t_RTO, 2 * s/X) = max(t_RTO, 2 * t_ipi) */ - t_nfb = max(hctx->ccid3hctx_t_rto, 2 * hctx->ccid3hctx_t_ipi); + t_nfb = max(hc->tx_t_rto, 2 * hc->tx_t_ipi); ccid3_pr_debug("%s(%p), Scheduled no feedback timer to " "expire in %lu jiffies (%luus)\n", - dccp_role(sk), - sk, usecs_to_jiffies(t_nfb), t_nfb); + dccp_role(sk), sk, usecs_to_jiffies(t_nfb), t_nfb); - sk_reset_timer(sk, &hctx->ccid3hctx_no_feedback_timer, + sk_reset_timer(sk, &hc->tx_no_feedback_timer, jiffies + usecs_to_jiffies(t_nfb)); } @@ -510,11 +488,11 @@ static int ccid3_hc_tx_parse_options(struct sock *sk, unsigned char option, { int rc = 0; const struct dccp_sock *dp = dccp_sk(sk); - struct ccid3_hc_tx_sock *hctx = ccid3_hc_tx_sk(sk); + struct ccid3_hc_tx_sock *hc = ccid3_hc_tx_sk(sk); struct ccid3_options_received *opt_recv; __be32 opt_val; - opt_recv = &hctx->ccid3hctx_options_received; + opt_recv = &hc->tx_options_received; if (opt_recv->ccid3or_seqno != dp->dccps_gsr) { opt_recv->ccid3or_seqno = dp->dccps_gsr; @@ -568,56 +546,55 @@ static int ccid3_hc_tx_parse_options(struct sock *sk, unsigned char option, static int ccid3_hc_tx_init(struct ccid *ccid, struct sock *sk) { - struct ccid3_hc_tx_sock *hctx = ccid_priv(ccid); + struct ccid3_hc_tx_sock *hc = ccid_priv(ccid); - hctx->ccid3hctx_state = TFRC_SSTATE_NO_SENT; - hctx->ccid3hctx_hist = NULL; - setup_timer(&hctx->ccid3hctx_no_feedback_timer, + hc->tx_state = TFRC_SSTATE_NO_SENT; + hc->tx_hist = NULL; + setup_timer(&hc->tx_no_feedback_timer, ccid3_hc_tx_no_feedback_timer, (unsigned long)sk); - return 0; } static void ccid3_hc_tx_exit(struct sock *sk) { - struct ccid3_hc_tx_sock *hctx = ccid3_hc_tx_sk(sk); + struct ccid3_hc_tx_sock *hc = ccid3_hc_tx_sk(sk); ccid3_hc_tx_set_state(sk, TFRC_SSTATE_TERM); - sk_stop_timer(sk, &hctx->ccid3hctx_no_feedback_timer); + sk_stop_timer(sk, &hc->tx_no_feedback_timer); - tfrc_tx_hist_purge(&hctx->ccid3hctx_hist); + tfrc_tx_hist_purge(&hc->tx_hist); } static void ccid3_hc_tx_get_info(struct sock *sk, struct tcp_info *info) { - struct ccid3_hc_tx_sock *hctx; + struct ccid3_hc_tx_sock *hc; /* Listen socks doesn't have a private CCID block */ if (sk->sk_state == DCCP_LISTEN) return; - hctx = ccid3_hc_tx_sk(sk); - info->tcpi_rto = hctx->ccid3hctx_t_rto; - info->tcpi_rtt = hctx->ccid3hctx_rtt; + hc = ccid3_hc_tx_sk(sk); + info->tcpi_rto = hc->tx_t_rto; + info->tcpi_rtt = hc->tx_rtt; } static int ccid3_hc_tx_getsockopt(struct sock *sk, const int optname, int len, u32 __user *optval, int __user *optlen) { - const struct ccid3_hc_tx_sock *hctx; + const struct ccid3_hc_tx_sock *hc; const void *val; /* Listen socks doesn't have a private CCID block */ if (sk->sk_state == DCCP_LISTEN) return -EINVAL; - hctx = ccid3_hc_tx_sk(sk); + hc = ccid3_hc_tx_sk(sk); switch (optname) { case DCCP_SOCKOPT_CCID_TX_INFO: - if (len < sizeof(hctx->ccid3hctx_tfrc)) + if (len < sizeof(hc->tx_tfrc)) return -EINVAL; - len = sizeof(hctx->ccid3hctx_tfrc); - val = &hctx->ccid3hctx_tfrc; + len = sizeof(hc->tx_tfrc); + val = &hc->tx_tfrc; break; default: return -ENOPROTOOPT; @@ -657,34 +634,34 @@ static const char *ccid3_rx_state_name(enum ccid3_hc_rx_states state) static void ccid3_hc_rx_set_state(struct sock *sk, enum ccid3_hc_rx_states state) { - struct ccid3_hc_rx_sock *hcrx = ccid3_hc_rx_sk(sk); - enum ccid3_hc_rx_states oldstate = hcrx->ccid3hcrx_state; + struct ccid3_hc_rx_sock *hc = ccid3_hc_rx_sk(sk); + enum ccid3_hc_rx_states oldstate = hc->rx_state; ccid3_pr_debug("%s(%p) %-8.8s -> %s\n", dccp_role(sk), sk, ccid3_rx_state_name(oldstate), ccid3_rx_state_name(state)); WARN_ON(state == oldstate); - hcrx->ccid3hcrx_state = state; + hc->rx_state = state; } static void ccid3_hc_rx_send_feedback(struct sock *sk, const struct sk_buff *skb, enum ccid3_fback_type fbtype) { - struct ccid3_hc_rx_sock *hcrx = ccid3_hc_rx_sk(sk); + struct ccid3_hc_rx_sock *hc = ccid3_hc_rx_sk(sk); struct dccp_sock *dp = dccp_sk(sk); ktime_t now; s64 delta = 0; - if (unlikely(hcrx->ccid3hcrx_state == TFRC_RSTATE_TERM)) + if (unlikely(hc->rx_state == TFRC_RSTATE_TERM)) return; now = ktime_get_real(); switch (fbtype) { case CCID3_FBACK_INITIAL: - hcrx->ccid3hcrx_x_recv = 0; - hcrx->ccid3hcrx_pinv = ~0U; /* see RFC 4342, 8.5 */ + hc->rx_x_recv = 0; + hc->rx_pinv = ~0U; /* see RFC 4342, 8.5 */ break; case CCID3_FBACK_PARAM_CHANGE: /* @@ -697,27 +674,26 @@ static void ccid3_hc_rx_send_feedback(struct sock *sk, * the number of bytes since last feedback. * This is a safe fallback, since X is bounded above by X_calc. */ - if (hcrx->ccid3hcrx_x_recv > 0) + if (hc->rx_x_recv > 0) break; /* fall through */ case CCID3_FBACK_PERIODIC: - delta = ktime_us_delta(now, hcrx->ccid3hcrx_tstamp_last_feedback); + delta = ktime_us_delta(now, hc->rx_tstamp_last_feedback); if (delta <= 0) DCCP_BUG("delta (%ld) <= 0", (long)delta); else - hcrx->ccid3hcrx_x_recv = - scaled_div32(hcrx->ccid3hcrx_bytes_recv, delta); + hc->rx_x_recv = scaled_div32(hc->rx_bytes_recv, delta); break; default: return; } ccid3_pr_debug("Interval %ldusec, X_recv=%u, 1/p=%u\n", (long)delta, - hcrx->ccid3hcrx_x_recv, hcrx->ccid3hcrx_pinv); + hc->rx_x_recv, hc->rx_pinv); - hcrx->ccid3hcrx_tstamp_last_feedback = now; - hcrx->ccid3hcrx_last_counter = dccp_hdr(skb)->dccph_ccval; - hcrx->ccid3hcrx_bytes_recv = 0; + hc->rx_tstamp_last_feedback = now; + hc->rx_last_counter = dccp_hdr(skb)->dccph_ccval; + hc->rx_bytes_recv = 0; dp->dccps_hc_rx_insert_options = 1; dccp_send_ack(sk); @@ -725,19 +701,19 @@ static void ccid3_hc_rx_send_feedback(struct sock *sk, static int ccid3_hc_rx_insert_options(struct sock *sk, struct sk_buff *skb) { - const struct ccid3_hc_rx_sock *hcrx; + const struct ccid3_hc_rx_sock *hc; __be32 x_recv, pinv; if (!(sk->sk_state == DCCP_OPEN || sk->sk_state == DCCP_PARTOPEN)) return 0; - hcrx = ccid3_hc_rx_sk(sk); + hc = ccid3_hc_rx_sk(sk); if (dccp_packet_without_ack(skb)) return 0; - x_recv = htonl(hcrx->ccid3hcrx_x_recv); - pinv = htonl(hcrx->ccid3hcrx_pinv); + x_recv = htonl(hc->rx_x_recv); + pinv = htonl(hc->rx_pinv); if (dccp_insert_option(sk, skb, TFRC_OPT_LOSS_EVENT_RATE, &pinv, sizeof(pinv)) || @@ -760,26 +736,26 @@ static int ccid3_hc_rx_insert_options(struct sock *sk, struct sk_buff *skb) */ static u32 ccid3_first_li(struct sock *sk) { - struct ccid3_hc_rx_sock *hcrx = ccid3_hc_rx_sk(sk); + struct ccid3_hc_rx_sock *hc = ccid3_hc_rx_sk(sk); u32 x_recv, p, delta; u64 fval; - if (hcrx->ccid3hcrx_rtt == 0) { + if (hc->rx_rtt == 0) { DCCP_WARN("No RTT estimate available, using fallback RTT\n"); - hcrx->ccid3hcrx_rtt = DCCP_FALLBACK_RTT; + hc->rx_rtt = DCCP_FALLBACK_RTT; } - delta = ktime_to_us(net_timedelta(hcrx->ccid3hcrx_tstamp_last_feedback)); - x_recv = scaled_div32(hcrx->ccid3hcrx_bytes_recv, delta); + delta = ktime_to_us(net_timedelta(hc->rx_tstamp_last_feedback)); + x_recv = scaled_div32(hc->rx_bytes_recv, delta); if (x_recv == 0) { /* would also trigger divide-by-zero */ DCCP_WARN("X_recv==0\n"); - if ((x_recv = hcrx->ccid3hcrx_x_recv) == 0) { + if ((x_recv = hc->rx_x_recv) == 0) { DCCP_BUG("stored value of X_recv is zero"); return ~0U; } } - fval = scaled_div(hcrx->ccid3hcrx_s, hcrx->ccid3hcrx_rtt); + fval = scaled_div(hc->rx_s, hc->rx_rtt); fval = scaled_div32(fval, x_recv); p = tfrc_calc_x_reverse_lookup(fval); @@ -791,19 +767,19 @@ static u32 ccid3_first_li(struct sock *sk) static void ccid3_hc_rx_packet_recv(struct sock *sk, struct sk_buff *skb) { - struct ccid3_hc_rx_sock *hcrx = ccid3_hc_rx_sk(sk); + struct ccid3_hc_rx_sock *hc = ccid3_hc_rx_sk(sk); enum ccid3_fback_type do_feedback = CCID3_FBACK_NONE; const u64 ndp = dccp_sk(sk)->dccps_options_received.dccpor_ndp; const bool is_data_packet = dccp_data_packet(skb); - if (unlikely(hcrx->ccid3hcrx_state == TFRC_RSTATE_NO_DATA)) { + if (unlikely(hc->rx_state == TFRC_RSTATE_NO_DATA)) { if (is_data_packet) { const u32 payload = skb->len - dccp_hdr(skb)->dccph_doff * 4; do_feedback = CCID3_FBACK_INITIAL; ccid3_hc_rx_set_state(sk, TFRC_RSTATE_DATA); - hcrx->ccid3hcrx_s = payload; + hc->rx_s = payload; /* - * Not necessary to update ccid3hcrx_bytes_recv here, + * Not necessary to update rx_bytes_recv here, * since X_recv = 0 for the first feedback packet (cf. * RFC 3448, 6.3) -- gerrit */ @@ -811,7 +787,7 @@ static void ccid3_hc_rx_packet_recv(struct sock *sk, struct sk_buff *skb) goto update_records; } - if (tfrc_rx_hist_duplicate(&hcrx->ccid3hcrx_hist, skb)) + if (tfrc_rx_hist_duplicate(&hc->rx_hist, skb)) return; /* done receiving */ if (is_data_packet) { @@ -819,20 +795,20 @@ static void ccid3_hc_rx_packet_recv(struct sock *sk, struct sk_buff *skb) /* * Update moving-average of s and the sum of received payload bytes */ - hcrx->ccid3hcrx_s = tfrc_ewma(hcrx->ccid3hcrx_s, payload, 9); - hcrx->ccid3hcrx_bytes_recv += payload; + hc->rx_s = tfrc_ewma(hc->rx_s, payload, 9); + hc->rx_bytes_recv += payload; } /* * Perform loss detection and handle pending losses */ - if (tfrc_rx_handle_loss(&hcrx->ccid3hcrx_hist, &hcrx->ccid3hcrx_li_hist, + if (tfrc_rx_handle_loss(&hc->rx_hist, &hc->rx_li_hist, skb, ndp, ccid3_first_li, sk)) { do_feedback = CCID3_FBACK_PARAM_CHANGE; goto done_receiving; } - if (tfrc_rx_hist_loss_pending(&hcrx->ccid3hcrx_hist)) + if (tfrc_rx_hist_loss_pending(&hc->rx_hist)) return; /* done receiving */ /* @@ -841,17 +817,17 @@ static void ccid3_hc_rx_packet_recv(struct sock *sk, struct sk_buff *skb) if (unlikely(!is_data_packet)) goto update_records; - if (!tfrc_lh_is_initialised(&hcrx->ccid3hcrx_li_hist)) { - const u32 sample = tfrc_rx_hist_sample_rtt(&hcrx->ccid3hcrx_hist, skb); + if (!tfrc_lh_is_initialised(&hc->rx_li_hist)) { + const u32 sample = tfrc_rx_hist_sample_rtt(&hc->rx_hist, skb); /* * Empty loss history: no loss so far, hence p stays 0. * Sample RTT values, since an RTT estimate is required for the * computation of p when the first loss occurs; RFC 3448, 6.3.1. */ if (sample != 0) - hcrx->ccid3hcrx_rtt = tfrc_ewma(hcrx->ccid3hcrx_rtt, sample, 9); + hc->rx_rtt = tfrc_ewma(hc->rx_rtt, sample, 9); - } else if (tfrc_lh_update_i_mean(&hcrx->ccid3hcrx_li_hist, skb)) { + } else if (tfrc_lh_update_i_mean(&hc->rx_li_hist, skb)) { /* * Step (3) of [RFC 3448, 6.1]: Recompute I_mean and, if I_mean * has decreased (resp. p has increased), send feedback now. @@ -862,11 +838,11 @@ static void ccid3_hc_rx_packet_recv(struct sock *sk, struct sk_buff *skb) /* * Check if the periodic once-per-RTT feedback is due; RFC 4342, 10.3 */ - if (SUB16(dccp_hdr(skb)->dccph_ccval, hcrx->ccid3hcrx_last_counter) > 3) + if (SUB16(dccp_hdr(skb)->dccph_ccval, hc->rx_last_counter) > 3) do_feedback = CCID3_FBACK_PERIODIC; update_records: - tfrc_rx_hist_add_packet(&hcrx->ccid3hcrx_hist, skb, ndp); + tfrc_rx_hist_add_packet(&hc->rx_hist, skb, ndp); done_receiving: if (do_feedback) @@ -875,41 +851,41 @@ done_receiving: static int ccid3_hc_rx_init(struct ccid *ccid, struct sock *sk) { - struct ccid3_hc_rx_sock *hcrx = ccid_priv(ccid); + struct ccid3_hc_rx_sock *hc = ccid_priv(ccid); - hcrx->ccid3hcrx_state = TFRC_RSTATE_NO_DATA; - tfrc_lh_init(&hcrx->ccid3hcrx_li_hist); - return tfrc_rx_hist_alloc(&hcrx->ccid3hcrx_hist); + hc->rx_state = TFRC_RSTATE_NO_DATA; + tfrc_lh_init(&hc->rx_li_hist); + return tfrc_rx_hist_alloc(&hc->rx_hist); } static void ccid3_hc_rx_exit(struct sock *sk) { - struct ccid3_hc_rx_sock *hcrx = ccid3_hc_rx_sk(sk); + struct ccid3_hc_rx_sock *hc = ccid3_hc_rx_sk(sk); ccid3_hc_rx_set_state(sk, TFRC_RSTATE_TERM); - tfrc_rx_hist_purge(&hcrx->ccid3hcrx_hist); - tfrc_lh_cleanup(&hcrx->ccid3hcrx_li_hist); + tfrc_rx_hist_purge(&hc->rx_hist); + tfrc_lh_cleanup(&hc->rx_li_hist); } static void ccid3_hc_rx_get_info(struct sock *sk, struct tcp_info *info) { - const struct ccid3_hc_rx_sock *hcrx; + const struct ccid3_hc_rx_sock *hc; /* Listen socks doesn't have a private CCID block */ if (sk->sk_state == DCCP_LISTEN) return; - hcrx = ccid3_hc_rx_sk(sk); - info->tcpi_ca_state = hcrx->ccid3hcrx_state; + hc = ccid3_hc_rx_sk(sk); + info->tcpi_ca_state = hc->rx_state; info->tcpi_options |= TCPI_OPT_TIMESTAMPS; - info->tcpi_rcv_rtt = hcrx->ccid3hcrx_rtt; + info->tcpi_rcv_rtt = hc->rx_rtt; } static int ccid3_hc_rx_getsockopt(struct sock *sk, const int optname, int len, u32 __user *optval, int __user *optlen) { - const struct ccid3_hc_rx_sock *hcrx; + const struct ccid3_hc_rx_sock *hc; struct tfrc_rx_info rx_info; const void *val; @@ -917,15 +893,15 @@ static int ccid3_hc_rx_getsockopt(struct sock *sk, const int optname, int len, if (sk->sk_state == DCCP_LISTEN) return -EINVAL; - hcrx = ccid3_hc_rx_sk(sk); + hc = ccid3_hc_rx_sk(sk); switch (optname) { case DCCP_SOCKOPT_CCID_RX_INFO: if (len < sizeof(rx_info)) return -EINVAL; - rx_info.tfrcrx_x_recv = hcrx->ccid3hcrx_x_recv; - rx_info.tfrcrx_rtt = hcrx->ccid3hcrx_rtt; - rx_info.tfrcrx_p = hcrx->ccid3hcrx_pinv == 0 ? ~0U : - scaled_div(1, hcrx->ccid3hcrx_pinv); + rx_info.tfrcrx_x_recv = hc->rx_x_recv; + rx_info.tfrcrx_rtt = hc->rx_rtt; + rx_info.tfrcrx_p = hc->rx_pinv == 0 ? ~0U : + scaled_div(1, hc->rx_pinv); len = sizeof(rx_info); val = &rx_info; break; diff --git a/net/dccp/ccids/ccid3.h b/net/dccp/ccids/ccid3.h index e5a244143846..032635776653 100644 --- a/net/dccp/ccids/ccid3.h +++ b/net/dccp/ccids/ccid3.h @@ -75,44 +75,44 @@ enum ccid3_hc_tx_states { /** * struct ccid3_hc_tx_sock - CCID3 sender half-connection socket - * @ccid3hctx_x - Current sending rate in 64 * bytes per second - * @ccid3hctx_x_recv - Receive rate in 64 * bytes per second - * @ccid3hctx_x_calc - Calculated rate in bytes per second - * @ccid3hctx_rtt - Estimate of current round trip time in usecs - * @ccid3hctx_p - Current loss event rate (0-1) scaled by 1000000 - * @ccid3hctx_s - Packet size in bytes - * @ccid3hctx_t_rto - Nofeedback Timer setting in usecs - * @ccid3hctx_t_ipi - Interpacket (send) interval (RFC 3448, 4.6) in usecs - * @ccid3hctx_state - Sender state, one of %ccid3_hc_tx_states - * @ccid3hctx_last_win_count - Last window counter sent - * @ccid3hctx_t_last_win_count - Timestamp of earliest packet - * with last_win_count value sent - * @ccid3hctx_no_feedback_timer - Handle to no feedback timer - * @ccid3hctx_t_ld - Time last doubled during slow start - * @ccid3hctx_t_nom - Nominal send time of next packet - * @ccid3hctx_delta - Send timer delta (RFC 3448, 4.6) in usecs - * @ccid3hctx_hist - Packet history - * @ccid3hctx_options_received - Parsed set of retrieved options + * @tx_x: Current sending rate in 64 * bytes per second + * @tx_x_recv: Receive rate in 64 * bytes per second + * @tx_x_calc: Calculated rate in bytes per second + * @tx_rtt: Estimate of current round trip time in usecs + * @tx_p: Current loss event rate (0-1) scaled by 1000000 + * @tx_s: Packet size in bytes + * @tx_t_rto: Nofeedback Timer setting in usecs + * @tx_t_ipi: Interpacket (send) interval (RFC 3448, 4.6) in usecs + * @tx_state: Sender state, one of %ccid3_hc_tx_states + * @tx_last_win_count: Last window counter sent + * @tx_t_last_win_count: Timestamp of earliest packet + * with last_win_count value sent + * @tx_no_feedback_timer: Handle to no feedback timer + * @tx_t_ld: Time last doubled during slow start + * @tx_t_nom: Nominal send time of next packet + * @tx_delta: Send timer delta (RFC 3448, 4.6) in usecs + * @tx_hist: Packet history + * @tx_options_received: Parsed set of retrieved options */ struct ccid3_hc_tx_sock { - struct tfrc_tx_info ccid3hctx_tfrc; -#define ccid3hctx_x ccid3hctx_tfrc.tfrctx_x -#define ccid3hctx_x_recv ccid3hctx_tfrc.tfrctx_x_recv -#define ccid3hctx_x_calc ccid3hctx_tfrc.tfrctx_x_calc -#define ccid3hctx_rtt ccid3hctx_tfrc.tfrctx_rtt -#define ccid3hctx_p ccid3hctx_tfrc.tfrctx_p -#define ccid3hctx_t_rto ccid3hctx_tfrc.tfrctx_rto -#define ccid3hctx_t_ipi ccid3hctx_tfrc.tfrctx_ipi - u16 ccid3hctx_s; - enum ccid3_hc_tx_states ccid3hctx_state:8; - u8 ccid3hctx_last_win_count; - ktime_t ccid3hctx_t_last_win_count; - struct timer_list ccid3hctx_no_feedback_timer; - ktime_t ccid3hctx_t_ld; - ktime_t ccid3hctx_t_nom; - u32 ccid3hctx_delta; - struct tfrc_tx_hist_entry *ccid3hctx_hist; - struct ccid3_options_received ccid3hctx_options_received; + struct tfrc_tx_info tx_tfrc; +#define tx_x tx_tfrc.tfrctx_x +#define tx_x_recv tx_tfrc.tfrctx_x_recv +#define tx_x_calc tx_tfrc.tfrctx_x_calc +#define tx_rtt tx_tfrc.tfrctx_rtt +#define tx_p tx_tfrc.tfrctx_p +#define tx_t_rto tx_tfrc.tfrctx_rto +#define tx_t_ipi tx_tfrc.tfrctx_ipi + u16 tx_s; + enum ccid3_hc_tx_states tx_state:8; + u8 tx_last_win_count; + ktime_t tx_t_last_win_count; + struct timer_list tx_no_feedback_timer; + ktime_t tx_t_ld; + ktime_t tx_t_nom; + u32 tx_delta; + struct tfrc_tx_hist_entry *tx_hist; + struct ccid3_options_received tx_options_received; }; static inline struct ccid3_hc_tx_sock *ccid3_hc_tx_sk(const struct sock *sk) @@ -131,32 +131,32 @@ enum ccid3_hc_rx_states { /** * struct ccid3_hc_rx_sock - CCID3 receiver half-connection socket - * @ccid3hcrx_x_recv - Receiver estimate of send rate (RFC 3448 4.3) - * @ccid3hcrx_rtt - Receiver estimate of rtt (non-standard) - * @ccid3hcrx_p - Current loss event rate (RFC 3448 5.4) - * @ccid3hcrx_last_counter - Tracks window counter (RFC 4342, 8.1) - * @ccid3hcrx_state - Receiver state, one of %ccid3_hc_rx_states - * @ccid3hcrx_bytes_recv - Total sum of DCCP payload bytes - * @ccid3hcrx_x_recv - Receiver estimate of send rate (RFC 3448, sec. 4.3) - * @ccid3hcrx_rtt - Receiver estimate of RTT - * @ccid3hcrx_tstamp_last_feedback - Time at which last feedback was sent - * @ccid3hcrx_tstamp_last_ack - Time at which last feedback was sent - * @ccid3hcrx_hist - Packet history (loss detection + RTT sampling) - * @ccid3hcrx_li_hist - Loss Interval database - * @ccid3hcrx_s - Received packet size in bytes - * @ccid3hcrx_pinv - Inverse of Loss Event Rate (RFC 4342, sec. 8.5) + * @rx_x_recv: Receiver estimate of send rate (RFC 3448 4.3) + * @rx_rtt: Receiver estimate of rtt (non-standard) + * @rx_p: Current loss event rate (RFC 3448 5.4) + * @rx_last_counter: Tracks window counter (RFC 4342, 8.1) + * @rx_state: Receiver state, one of %ccid3_hc_rx_states + * @rx_bytes_recv: Total sum of DCCP payload bytes + * @rx_x_recv: Receiver estimate of send rate (RFC 3448, sec. 4.3) + * @rx_rtt: Receiver estimate of RTT + * @rx_tstamp_last_feedback: Time at which last feedback was sent + * @rx_tstamp_last_ack: Time at which last feedback was sent + * @rx_hist: Packet history (loss detection + RTT sampling) + * @rx_li_hist: Loss Interval database + * @rx_s: Received packet size in bytes + * @rx_pinv: Inverse of Loss Event Rate (RFC 4342, sec. 8.5) */ struct ccid3_hc_rx_sock { - u8 ccid3hcrx_last_counter:4; - enum ccid3_hc_rx_states ccid3hcrx_state:8; - u32 ccid3hcrx_bytes_recv; - u32 ccid3hcrx_x_recv; - u32 ccid3hcrx_rtt; - ktime_t ccid3hcrx_tstamp_last_feedback; - struct tfrc_rx_hist ccid3hcrx_hist; - struct tfrc_loss_hist ccid3hcrx_li_hist; - u16 ccid3hcrx_s; -#define ccid3hcrx_pinv ccid3hcrx_li_hist.i_mean + u8 rx_last_counter:4; + enum ccid3_hc_rx_states rx_state:8; + u32 rx_bytes_recv; + u32 rx_x_recv; + u32 rx_rtt; + ktime_t rx_tstamp_last_feedback; + struct tfrc_rx_hist rx_hist; + struct tfrc_loss_hist rx_li_hist; + u16 rx_s; +#define rx_pinv rx_li_hist.i_mean }; static inline struct ccid3_hc_rx_sock *ccid3_hc_rx_sk(const struct sock *sk) diff --git a/net/dccp/ipv4.c b/net/dccp/ipv4.c index 7302e1498d46..efbcfdc12796 100644 --- a/net/dccp/ipv4.c +++ b/net/dccp/ipv4.c @@ -62,10 +62,10 @@ int dccp_v4_connect(struct sock *sk, struct sockaddr *uaddr, int addr_len) nexthop = inet->opt->faddr; } - tmp = ip_route_connect(&rt, nexthop, inet->saddr, + tmp = ip_route_connect(&rt, nexthop, inet->inet_saddr, RT_CONN_FLAGS(sk), sk->sk_bound_dev_if, IPPROTO_DCCP, - inet->sport, usin->sin_port, sk, 1); + inet->inet_sport, usin->sin_port, sk, 1); if (tmp < 0) return tmp; @@ -77,12 +77,12 @@ int dccp_v4_connect(struct sock *sk, struct sockaddr *uaddr, int addr_len) if (inet->opt == NULL || !inet->opt->srr) daddr = rt->rt_dst; - if (inet->saddr == 0) - inet->saddr = rt->rt_src; - inet->rcv_saddr = inet->saddr; + if (inet->inet_saddr == 0) + inet->inet_saddr = rt->rt_src; + inet->inet_rcv_saddr = inet->inet_saddr; - inet->dport = usin->sin_port; - inet->daddr = daddr; + inet->inet_dport = usin->sin_port; + inet->inet_daddr = daddr; inet_csk(sk)->icsk_ext_hdr_len = 0; if (inet->opt != NULL) @@ -98,17 +98,19 @@ int dccp_v4_connect(struct sock *sk, struct sockaddr *uaddr, int addr_len) if (err != 0) goto failure; - err = ip_route_newports(&rt, IPPROTO_DCCP, inet->sport, inet->dport, - sk); + err = ip_route_newports(&rt, IPPROTO_DCCP, inet->inet_sport, + inet->inet_dport, sk); if (err != 0) goto failure; /* OK, now commit destination to socket. */ sk_setup_caps(sk, &rt->u.dst); - dp->dccps_iss = secure_dccp_sequence_number(inet->saddr, inet->daddr, - inet->sport, inet->dport); - inet->id = dp->dccps_iss ^ jiffies; + dp->dccps_iss = secure_dccp_sequence_number(inet->inet_saddr, + inet->inet_daddr, + inet->inet_sport, + inet->inet_dport); + inet->inet_id = dp->dccps_iss ^ jiffies; err = dccp_connect(sk); rt = NULL; @@ -123,7 +125,7 @@ failure: dccp_set_state(sk, DCCP_CLOSED); ip_rt_put(rt); sk->sk_route_caps = 0; - inet->dport = 0; + inet->inet_dport = 0; goto out; } @@ -352,7 +354,9 @@ void dccp_v4_send_check(struct sock *sk, int unused, struct sk_buff *skb) struct dccp_hdr *dh = dccp_hdr(skb); dccp_csum_outgoing(skb); - dh->dccph_checksum = dccp_v4_csum_finish(skb, inet->saddr, inet->daddr); + dh->dccph_checksum = dccp_v4_csum_finish(skb, + inet->inet_saddr, + inet->inet_daddr); } EXPORT_SYMBOL_GPL(dccp_v4_send_check); @@ -393,14 +397,14 @@ struct sock *dccp_v4_request_recv_sock(struct sock *sk, struct sk_buff *skb, newinet = inet_sk(newsk); ireq = inet_rsk(req); - newinet->daddr = ireq->rmt_addr; - newinet->rcv_saddr = ireq->loc_addr; - newinet->saddr = ireq->loc_addr; + newinet->inet_daddr = ireq->rmt_addr; + newinet->inet_rcv_saddr = ireq->loc_addr; + newinet->inet_saddr = ireq->loc_addr; newinet->opt = ireq->opt; ireq->opt = NULL; newinet->mc_index = inet_iif(skb); newinet->mc_ttl = ip_hdr(skb)->ttl; - newinet->id = jiffies; + newinet->inet_id = jiffies; dccp_sync_mss(newsk, dst_mtu(dst)); @@ -473,7 +477,8 @@ static struct dst_entry* dccp_v4_route_skb(struct net *net, struct sock *sk, return &rt->u.dst; } -static int dccp_v4_send_response(struct sock *sk, struct request_sock *req) +static int dccp_v4_send_response(struct sock *sk, struct request_sock *req, + struct request_values *rv_unused) { int err = -1; struct sk_buff *skb; @@ -622,7 +627,7 @@ int dccp_v4_conn_request(struct sock *sk, struct sk_buff *skb) dreq->dreq_iss = dccp_v4_init_sequence(skb); dreq->dreq_service = service; - if (dccp_v4_send_response(sk, req)) + if (dccp_v4_send_response(sk, req, NULL)) goto drop_and_free; inet_csk_reqsk_queue_hash_add(sk, req, DCCP_TIMEOUT_INIT); @@ -987,7 +992,6 @@ static struct inet_protosw dccp_v4_protosw = { .protocol = IPPROTO_DCCP, .prot = &dccp_v4_prot, .ops = &inet_dccp_ops, - .capability = -1, .no_check = 0, .flags = INET_PROTOSW_ICSK, }; diff --git a/net/dccp/ipv6.c b/net/dccp/ipv6.c index e48ca5d45658..6574215a1f51 100644 --- a/net/dccp/ipv6.c +++ b/net/dccp/ipv6.c @@ -158,8 +158,8 @@ static void dccp_v6_err(struct sk_buff *skb, struct inet6_skb_parm *opt, ipv6_addr_copy(&fl.fl6_dst, &np->daddr); ipv6_addr_copy(&fl.fl6_src, &np->saddr); fl.oif = sk->sk_bound_dev_if; - fl.fl_ip_dport = inet->dport; - fl.fl_ip_sport = inet->sport; + fl.fl_ip_dport = inet->inet_dport; + fl.fl_ip_sport = inet->inet_sport; security_sk_classify_flow(sk, &fl); err = ip6_dst_lookup(sk, &dst, &fl); @@ -241,7 +241,8 @@ out: } -static int dccp_v6_send_response(struct sock *sk, struct request_sock *req) +static int dccp_v6_send_response(struct sock *sk, struct request_sock *req, + struct request_values *rv_unused) { struct inet6_request_sock *ireq6 = inet6_rsk(req); struct ipv6_pinfo *np = inet6_sk(sk); @@ -468,7 +469,7 @@ static int dccp_v6_conn_request(struct sock *sk, struct sk_buff *skb) dreq->dreq_iss = dccp_v6_init_sequence(skb); dreq->dreq_service = service; - if (dccp_v6_send_response(sk, req)) + if (dccp_v6_send_response(sk, req, NULL)) goto drop_and_free; inet6_csk_reqsk_queue_hash_add(sk, req, DCCP_TIMEOUT_INIT); @@ -510,11 +511,9 @@ static struct sock *dccp_v6_request_recv_sock(struct sock *sk, memcpy(newnp, np, sizeof(struct ipv6_pinfo)); - ipv6_addr_set(&newnp->daddr, 0, 0, htonl(0x0000FFFF), - newinet->daddr); + ipv6_addr_set_v4mapped(newinet->inet_daddr, &newnp->daddr); - ipv6_addr_set(&newnp->saddr, 0, 0, htonl(0x0000FFFF), - newinet->saddr); + ipv6_addr_set_v4mapped(newinet->inet_saddr, &newnp->saddr); ipv6_addr_copy(&newnp->rcv_saddr, &newnp->saddr); @@ -642,7 +641,8 @@ static struct sock *dccp_v6_request_recv_sock(struct sock *sk, dccp_sync_mss(newsk, dst_mtu(dst)); - newinet->daddr = newinet->saddr = newinet->rcv_saddr = LOOPBACK4_IPV6; + newinet->inet_daddr = newinet->inet_saddr = LOOPBACK4_IPV6; + newinet->inet_rcv_saddr = LOOPBACK4_IPV6; __inet6_hash(newsk); __inet_inherit_port(sk, newsk); @@ -970,12 +970,9 @@ static int dccp_v6_connect(struct sock *sk, struct sockaddr *uaddr, icsk->icsk_af_ops = &dccp_ipv6_af_ops; sk->sk_backlog_rcv = dccp_v6_do_rcv; goto failure; - } else { - ipv6_addr_set(&np->saddr, 0, 0, htonl(0x0000FFFF), - inet->saddr); - ipv6_addr_set(&np->rcv_saddr, 0, 0, htonl(0x0000FFFF), - inet->rcv_saddr); } + ipv6_addr_set_v4mapped(inet->inet_saddr, &np->saddr); + ipv6_addr_set_v4mapped(inet->inet_rcv_saddr, &np->rcv_saddr); return err; } @@ -988,7 +985,7 @@ static int dccp_v6_connect(struct sock *sk, struct sockaddr *uaddr, ipv6_addr_copy(&fl.fl6_src, saddr ? saddr : &np->saddr); fl.oif = sk->sk_bound_dev_if; fl.fl_ip_dport = usin->sin6_port; - fl.fl_ip_sport = inet->sport; + fl.fl_ip_sport = inet->inet_sport; security_sk_classify_flow(sk, &fl); if (np->opt != NULL && np->opt->srcrt != NULL) { @@ -1021,7 +1018,7 @@ static int dccp_v6_connect(struct sock *sk, struct sockaddr *uaddr, /* set the source address */ ipv6_addr_copy(&np->saddr, saddr); - inet->rcv_saddr = LOOPBACK4_IPV6; + inet->inet_rcv_saddr = LOOPBACK4_IPV6; __ip6_dst_store(sk, dst, NULL, NULL); @@ -1030,7 +1027,7 @@ static int dccp_v6_connect(struct sock *sk, struct sockaddr *uaddr, icsk->icsk_ext_hdr_len = (np->opt->opt_flen + np->opt->opt_nflen); - inet->dport = usin->sin6_port; + inet->inet_dport = usin->sin6_port; dccp_set_state(sk, DCCP_REQUESTING); err = inet6_hash_connect(&dccp_death_row, sk); @@ -1039,7 +1036,8 @@ static int dccp_v6_connect(struct sock *sk, struct sockaddr *uaddr, dp->dccps_iss = secure_dccpv6_sequence_number(np->saddr.s6_addr32, np->daddr.s6_addr32, - inet->sport, inet->dport); + inet->inet_sport, + inet->inet_dport); err = dccp_connect(sk); if (err) goto late_failure; @@ -1050,7 +1048,7 @@ late_failure: dccp_set_state(sk, DCCP_CLOSED); __sk_dst_reset(sk); failure: - inet->dport = 0; + inet->inet_dport = 0; sk->sk_route_caps = 0; return err; } @@ -1188,7 +1186,6 @@ static struct inet_protosw dccp_v6_protosw = { .protocol = IPPROTO_DCCP, .prot = &dccp_v6_prot, .ops = &inet6_dccp_ops, - .capability = -1, .flags = INET_PROTOSW_ICSK, }; diff --git a/net/dccp/minisocks.c b/net/dccp/minisocks.c index 5ca49cec95f5..af226a063141 100644 --- a/net/dccp/minisocks.c +++ b/net/dccp/minisocks.c @@ -184,7 +184,7 @@ struct sock *dccp_check_req(struct sock *sk, struct sk_buff *skb, * counter (backoff, monitored by dccp_response_timer). */ req->retrans++; - req->rsk_ops->rtx_syn_ack(sk, req); + req->rsk_ops->rtx_syn_ack(sk, req, NULL); } /* Network Duplicate, discard packet */ return NULL; diff --git a/net/dccp/output.c b/net/dccp/output.c index c96119fda688..d6bb753bf6ad 100644 --- a/net/dccp/output.c +++ b/net/dccp/output.c @@ -99,8 +99,8 @@ static int dccp_transmit_skb(struct sock *sk, struct sk_buff *skb) /* Build DCCP header and checksum it. */ dh = dccp_zeroed_hdr(skb, dccp_header_size); dh->dccph_type = dcb->dccpd_type; - dh->dccph_sport = inet->sport; - dh->dccph_dport = inet->dport; + dh->dccph_sport = inet->inet_sport; + dh->dccph_dport = inet->inet_dport; dh->dccph_doff = (dccp_header_size + dcb->dccpd_opt_len) / 4; dh->dccph_ccval = dcb->dccpd_ccval; dh->dccph_cscov = dp->dccps_pcslen; diff --git a/net/dccp/probe.c b/net/dccp/probe.c index 37731da41481..dc328425fa20 100644 --- a/net/dccp/probe.c +++ b/net/dccp/probe.c @@ -75,26 +75,25 @@ static int jdccp_sendmsg(struct kiocb *iocb, struct sock *sk, struct msghdr *msg, size_t size) { const struct inet_sock *inet = inet_sk(sk); - struct ccid3_hc_tx_sock *hctx = NULL; + struct ccid3_hc_tx_sock *hc = NULL; if (ccid_get_current_tx_ccid(dccp_sk(sk)) == DCCPC_CCID3) - hctx = ccid3_hc_tx_sk(sk); - - if (port == 0 || ntohs(inet->dport) == port || - ntohs(inet->sport) == port) { - if (hctx) - printl("%pI4:%u %pI4:%u %d %d %d %d %u " - "%llu %llu %d\n", - &inet->saddr, ntohs(inet->sport), - &inet->daddr, ntohs(inet->dport), size, - hctx->ccid3hctx_s, hctx->ccid3hctx_rtt, - hctx->ccid3hctx_p, hctx->ccid3hctx_x_calc, - hctx->ccid3hctx_x_recv >> 6, - hctx->ccid3hctx_x >> 6, hctx->ccid3hctx_t_ipi); + hc = ccid3_hc_tx_sk(sk); + + if (port == 0 || ntohs(inet->inet_dport) == port || + ntohs(inet->inet_sport) == port) { + if (hc) + printl("%pI4:%u %pI4:%u %d %d %d %d %u %llu %llu %d\n", + &inet->inet_saddr, ntohs(inet->inet_sport), + &inet->inet_daddr, ntohs(inet->inet_dport), size, + hc->tx_s, hc->tx_rtt, hc->tx_p, + hc->tx_x_calc, hc->tx_x_recv >> 6, + hc->tx_x >> 6, hc->tx_t_ipi); else printl("%pI4:%u %pI4:%u %d\n", - &inet->saddr, ntohs(inet->sport), - &inet->daddr, ntohs(inet->dport), size); + &inet->inet_saddr, ntohs(inet->inet_sport), + &inet->inet_daddr, ntohs(inet->inet_dport), + size); } jprobe_return(); diff --git a/net/dccp/proto.c b/net/dccp/proto.c index a156319fd0ac..671cd1413d59 100644 --- a/net/dccp/proto.c +++ b/net/dccp/proto.c @@ -278,7 +278,7 @@ int dccp_disconnect(struct sock *sk, int flags) sk->sk_send_head = NULL; } - inet->dport = 0; + inet->inet_dport = 0; if (!(sk->sk_userlocks & SOCK_BINDADDR_LOCK)) inet_reset_saddr(sk); @@ -290,7 +290,7 @@ int dccp_disconnect(struct sock *sk, int flags) inet_csk_delack_init(sk); __sk_dst_reset(sk); - WARN_ON(inet->num && !icsk->icsk_bind_hash); + WARN_ON(inet->inet_num && !icsk->icsk_bind_hash); sk->sk_error_report(sk); return err; @@ -1060,11 +1060,12 @@ static int __init dccp_init(void) for (ehash_order = 0; (1UL << ehash_order) < goal; ehash_order++) ; do { - dccp_hashinfo.ehash_size = (1UL << ehash_order) * PAGE_SIZE / + unsigned long hash_size = (1UL << ehash_order) * PAGE_SIZE / sizeof(struct inet_ehash_bucket); - while (dccp_hashinfo.ehash_size & - (dccp_hashinfo.ehash_size - 1)) - dccp_hashinfo.ehash_size--; + + while (hash_size & (hash_size - 1)) + hash_size--; + dccp_hashinfo.ehash_mask = hash_size - 1; dccp_hashinfo.ehash = (struct inet_ehash_bucket *) __get_free_pages(GFP_ATOMIC|__GFP_NOWARN, ehash_order); } while (!dccp_hashinfo.ehash && --ehash_order > 0); @@ -1074,7 +1075,7 @@ static int __init dccp_init(void) goto out_free_bind_bucket_cachep; } - for (i = 0; i < dccp_hashinfo.ehash_size; i++) { + for (i = 0; i <= dccp_hashinfo.ehash_mask; i++) { INIT_HLIST_NULLS_HEAD(&dccp_hashinfo.ehash[i].chain, i); INIT_HLIST_NULLS_HEAD(&dccp_hashinfo.ehash[i].twchain, i); } @@ -1153,7 +1154,7 @@ static void __exit dccp_fini(void) get_order(dccp_hashinfo.bhash_size * sizeof(struct inet_bind_hashbucket))); free_pages((unsigned long)dccp_hashinfo.ehash, - get_order(dccp_hashinfo.ehash_size * + get_order((dccp_hashinfo.ehash_mask + 1) * sizeof(struct inet_ehash_bucket))); inet_ehash_locks_free(&dccp_hashinfo); kmem_cache_destroy(dccp_hashinfo.bind_bucket_cachep); diff --git a/net/dccp/timer.c b/net/dccp/timer.c index 162d1e683c39..bbfeb5eae46a 100644 --- a/net/dccp/timer.c +++ b/net/dccp/timer.c @@ -38,7 +38,7 @@ static int dccp_write_timeout(struct sock *sk) if (sk->sk_state == DCCP_REQUESTING || sk->sk_state == DCCP_PARTOPEN) { if (icsk->icsk_retransmits != 0) - dst_negative_advice(&sk->sk_dst_cache); + dst_negative_advice(&sk->sk_dst_cache, sk); retry_until = icsk->icsk_syn_retries ? : sysctl_dccp_request_retries; } else { @@ -63,7 +63,7 @@ static int dccp_write_timeout(struct sock *sk) Golden words :-). */ - dst_negative_advice(&sk->sk_dst_cache); + dst_negative_advice(&sk->sk_dst_cache, sk); } retry_until = sysctl_dccp_retries2; diff --git a/net/decnet/af_decnet.c b/net/decnet/af_decnet.c index 7a58c87baf17..2b494fac9468 100644 --- a/net/decnet/af_decnet.c +++ b/net/decnet/af_decnet.c @@ -675,11 +675,12 @@ char *dn_addr2asc(__u16 addr, char *buf) -static int dn_create(struct net *net, struct socket *sock, int protocol) +static int dn_create(struct net *net, struct socket *sock, int protocol, + int kern) { struct sock *sk; - if (net != &init_net) + if (!net_eq(net, &init_net)) return -EAFNOSUPPORT; switch(sock->type) { @@ -749,9 +750,9 @@ static int dn_bind(struct socket *sock, struct sockaddr *uaddr, int addr_len) if (!(saddr->sdn_flags & SDF_WILD)) { if (le16_to_cpu(saddr->sdn_nodeaddrl)) { - read_lock(&dev_base_lock); + rcu_read_lock(); ldev = NULL; - for_each_netdev(&init_net, dev) { + for_each_netdev_rcu(&init_net, dev) { if (!dev->dn_ptr) continue; if (dn_dev_islocal(dev, dn_saddr2dn(saddr))) { @@ -759,7 +760,7 @@ static int dn_bind(struct socket *sock, struct sockaddr *uaddr, int addr_len) break; } } - read_unlock(&dev_base_lock); + rcu_read_unlock(); if (ldev == NULL) return -EADDRNOTAVAIL; } @@ -1955,7 +1956,7 @@ static int dn_sendmsg(struct kiocb *iocb, struct socket *sock, } if ((flags & MSG_TRYHARD) && sk->sk_dst_cache) - dst_negative_advice(&sk->sk_dst_cache); + dst_negative_advice(&sk->sk_dst_cache, sk); mss = scp->segsize_rem; fctype = scp->services_rem & NSP_FC_MASK; @@ -2325,7 +2326,7 @@ static const struct file_operations dn_socket_seq_fops = { }; #endif -static struct net_proto_family dn_family_ops = { +static const struct net_proto_family dn_family_ops = { .family = AF_DECnet, .create = dn_create, .owner = THIS_MODULE, diff --git a/net/decnet/dn_dev.c b/net/decnet/dn_dev.c index 1b1daeb151f2..238af093495b 100644 --- a/net/decnet/dn_dev.c +++ b/net/decnet/dn_dev.c @@ -68,7 +68,7 @@ extern struct neigh_table dn_neigh_table; */ __le16 decnet_address = 0; -static DEFINE_RWLOCK(dndev_lock); +static DEFINE_SPINLOCK(dndev_lock); static struct net_device *decnet_default_device; static BLOCKING_NOTIFIER_HEAD(dnaddr_chain); @@ -499,7 +499,8 @@ rarok: struct net_device *dn_dev_get_default(void) { struct net_device *dev; - read_lock(&dndev_lock); + + spin_lock(&dndev_lock); dev = decnet_default_device; if (dev) { if (dev->dn_ptr) @@ -507,7 +508,8 @@ struct net_device *dn_dev_get_default(void) else dev = NULL; } - read_unlock(&dndev_lock); + spin_unlock(&dndev_lock); + return dev; } @@ -517,13 +519,15 @@ int dn_dev_set_default(struct net_device *dev, int force) int rv = -EBUSY; if (!dev->dn_ptr) return -ENODEV; - write_lock(&dndev_lock); + + spin_lock(&dndev_lock); if (force || decnet_default_device == NULL) { old = decnet_default_device; decnet_default_device = dev; rv = 0; } - write_unlock(&dndev_lock); + spin_unlock(&dndev_lock); + if (old) dev_put(old); return rv; @@ -531,26 +535,29 @@ int dn_dev_set_default(struct net_device *dev, int force) static void dn_dev_check_default(struct net_device *dev) { - write_lock(&dndev_lock); + spin_lock(&dndev_lock); if (dev == decnet_default_device) { decnet_default_device = NULL; } else { dev = NULL; } - write_unlock(&dndev_lock); + spin_unlock(&dndev_lock); + if (dev) dev_put(dev); } +/* + * Called with RTNL + */ static struct dn_dev *dn_dev_by_index(int ifindex) { struct net_device *dev; struct dn_dev *dn_dev = NULL; - dev = dev_get_by_index(&init_net, ifindex); - if (dev) { + + dev = __dev_get_by_index(&init_net, ifindex); + if (dev) dn_dev = dev->dn_ptr; - dev_put(dev); - } return dn_dev; } @@ -571,7 +578,7 @@ static int dn_nl_deladdr(struct sk_buff *skb, struct nlmsghdr *nlh, void *arg) struct dn_ifaddr *ifa, **ifap; int err = -EINVAL; - if (net != &init_net) + if (!net_eq(net, &init_net)) goto errout; err = nlmsg_parse(nlh, sizeof(*ifm), tb, IFA_MAX, dn_ifa_policy); @@ -610,7 +617,7 @@ static int dn_nl_newaddr(struct sk_buff *skb, struct nlmsghdr *nlh, void *arg) struct dn_ifaddr *ifa; int err; - if (net != &init_net) + if (!net_eq(net, &init_net)) return -EINVAL; err = nlmsg_parse(nlh, sizeof(*ifm), tb, IFA_MAX, dn_ifa_policy); @@ -724,7 +731,7 @@ static int dn_nl_dump_ifaddr(struct sk_buff *skb, struct netlink_callback *cb) struct dn_dev *dn_db; struct dn_ifaddr *ifa; - if (net != &init_net) + if (!net_eq(net, &init_net)) return 0; skip_ndevs = cb->args[0]; @@ -768,13 +775,17 @@ static int dn_dev_get_first(struct net_device *dev, __le16 *addr) struct dn_dev *dn_db = (struct dn_dev *)dev->dn_ptr; struct dn_ifaddr *ifa; int rv = -ENODEV; + if (dn_db == NULL) goto out; + + rtnl_lock(); ifa = dn_db->ifa_list; if (ifa != NULL) { *addr = ifa->ifa_local; rv = 0; } + rtnl_unlock(); out: return rv; } @@ -796,9 +807,7 @@ int dn_dev_bind_default(__le16 *addr) dev = dn_dev_get_default(); last_chance: if (dev) { - read_lock(&dev_base_lock); rv = dn_dev_get_first(dev, addr); - read_unlock(&dev_base_lock); dev_put(dev); if (rv == 0 || dev == init_net.loopback_dev) return rv; @@ -1263,18 +1272,18 @@ static inline int is_dn_dev(struct net_device *dev) } static void *dn_dev_seq_start(struct seq_file *seq, loff_t *pos) - __acquires(&dev_base_lock) + __acquires(rcu) { int i; struct net_device *dev; - read_lock(&dev_base_lock); + rcu_read_lock(); if (*pos == 0) return SEQ_START_TOKEN; i = 1; - for_each_netdev(&init_net, dev) { + for_each_netdev_rcu(&init_net, dev) { if (!is_dn_dev(dev)) continue; @@ -1295,7 +1304,7 @@ static void *dn_dev_seq_next(struct seq_file *seq, void *v, loff_t *pos) if (v == SEQ_START_TOKEN) dev = net_device_entry(&init_net.dev_base_head); - for_each_netdev_continue(&init_net, dev) { + for_each_netdev_continue_rcu(&init_net, dev) { if (!is_dn_dev(dev)) continue; @@ -1306,9 +1315,9 @@ static void *dn_dev_seq_next(struct seq_file *seq, void *v, loff_t *pos) } static void dn_dev_seq_stop(struct seq_file *seq, void *v) - __releases(&dev_base_lock) + __releases(rcu) { - read_unlock(&dev_base_lock); + rcu_read_unlock(); } static char *dn_type2asc(char type) diff --git a/net/decnet/dn_fib.c b/net/decnet/dn_fib.c index 27ea2e9b080a..e9d48700e83a 100644 --- a/net/decnet/dn_fib.c +++ b/net/decnet/dn_fib.c @@ -509,7 +509,7 @@ static int dn_fib_rtm_delroute(struct sk_buff *skb, struct nlmsghdr *nlh, void * struct rtattr **rta = arg; struct rtmsg *r = NLMSG_DATA(nlh); - if (net != &init_net) + if (!net_eq(net, &init_net)) return -EINVAL; if (dn_fib_check_attr(r, rta)) @@ -529,7 +529,7 @@ static int dn_fib_rtm_newroute(struct sk_buff *skb, struct nlmsghdr *nlh, void * struct rtattr **rta = arg; struct rtmsg *r = NLMSG_DATA(nlh); - if (net != &init_net) + if (!net_eq(net, &init_net)) return -EINVAL; if (dn_fib_check_attr(r, rta)) @@ -607,8 +607,8 @@ static void dn_fib_del_ifaddr(struct dn_ifaddr *ifa) ASSERT_RTNL(); /* Scan device list */ - read_lock(&dev_base_lock); - for_each_netdev(&init_net, dev) { + rcu_read_lock(); + for_each_netdev_rcu(&init_net, dev) { dn_db = dev->dn_ptr; if (dn_db == NULL) continue; @@ -619,7 +619,7 @@ static void dn_fib_del_ifaddr(struct dn_ifaddr *ifa) } } } - read_unlock(&dev_base_lock); + rcu_read_unlock(); if (found_it == 0) { fib_magic(RTM_DELROUTE, RTN_LOCAL, ifa->ifa_local, 16, ifa); diff --git a/net/decnet/dn_route.c b/net/decnet/dn_route.c index 57662cabaf9b..a03284061a31 100644 --- a/net/decnet/dn_route.c +++ b/net/decnet/dn_route.c @@ -908,8 +908,8 @@ static int dn_route_output_slow(struct dst_entry **pprt, const struct flowi *old dev_put(dev_out); goto out; } - read_lock(&dev_base_lock); - for_each_netdev(&init_net, dev) { + rcu_read_lock(); + for_each_netdev_rcu(&init_net, dev) { if (!dev->dn_ptr) continue; if (!dn_dev_islocal(dev, oldflp->fld_src)) @@ -922,7 +922,7 @@ static int dn_route_output_slow(struct dst_entry **pprt, const struct flowi *old dev_out = dev; break; } - read_unlock(&dev_base_lock); + rcu_read_unlock(); if (dev_out == NULL) goto out; dev_hold(dev_out); @@ -1517,7 +1517,7 @@ static int dn_cache_getroute(struct sk_buff *in_skb, struct nlmsghdr *nlh, void struct sk_buff *skb; struct flowi fl; - if (net != &init_net) + if (!net_eq(net, &init_net)) return -EINVAL; memset(&fl, 0, sizeof(fl)); @@ -1602,7 +1602,7 @@ int dn_cache_dump(struct sk_buff *skb, struct netlink_callback *cb) int h, s_h; int idx, s_idx; - if (net != &init_net) + if (!net_eq(net, &init_net)) return 0; if (NLMSG_PAYLOAD(cb->nlh, 0) < sizeof(struct rtmsg)) diff --git a/net/decnet/dn_rules.c b/net/decnet/dn_rules.c index 72495f25269f..7466c546f286 100644 --- a/net/decnet/dn_rules.c +++ b/net/decnet/dn_rules.c @@ -33,7 +33,7 @@ #include <net/dn_dev.h> #include <net/dn_route.h> -static struct fib_rules_ops dn_fib_rules_ops; +static struct fib_rules_ops *dn_fib_rules_ops; struct dn_fib_rule { @@ -56,7 +56,7 @@ int dn_fib_lookup(struct flowi *flp, struct dn_fib_res *res) }; int err; - err = fib_rules_lookup(&dn_fib_rules_ops, flp, 0, &arg); + err = fib_rules_lookup(dn_fib_rules_ops, flp, 0, &arg); res->r = arg.rule; return err; @@ -217,9 +217,9 @@ static u32 dn_fib_rule_default_pref(struct fib_rules_ops *ops) struct list_head *pos; struct fib_rule *rule; - if (!list_empty(&dn_fib_rules_ops.rules_list)) { - pos = dn_fib_rules_ops.rules_list.next; - if (pos->next != &dn_fib_rules_ops.rules_list) { + if (!list_empty(&dn_fib_rules_ops->rules_list)) { + pos = dn_fib_rules_ops->rules_list.next; + if (pos->next != &dn_fib_rules_ops->rules_list) { rule = list_entry(pos->next, struct fib_rule, list); if (rule->pref) return rule->pref - 1; @@ -234,7 +234,7 @@ static void dn_fib_rule_flush_cache(struct fib_rules_ops *ops) dn_rt_cache_flush(-1); } -static struct fib_rules_ops dn_fib_rules_ops = { +static struct fib_rules_ops dn_fib_rules_ops_template = { .family = AF_DECnet, .rule_size = sizeof(struct dn_fib_rule), .addr_size = sizeof(u16), @@ -247,21 +247,23 @@ static struct fib_rules_ops dn_fib_rules_ops = { .flush_cache = dn_fib_rule_flush_cache, .nlgroup = RTNLGRP_DECnet_RULE, .policy = dn_fib_rule_policy, - .rules_list = LIST_HEAD_INIT(dn_fib_rules_ops.rules_list), .owner = THIS_MODULE, .fro_net = &init_net, }; void __init dn_fib_rules_init(void) { - BUG_ON(fib_default_rule_add(&dn_fib_rules_ops, 0x7fff, + dn_fib_rules_ops = + fib_rules_register(&dn_fib_rules_ops_template, &init_net); + BUG_ON(IS_ERR(dn_fib_rules_ops)); + BUG_ON(fib_default_rule_add(dn_fib_rules_ops, 0x7fff, RT_TABLE_MAIN, 0)); - fib_rules_register(&dn_fib_rules_ops); } void __exit dn_fib_rules_cleanup(void) { - fib_rules_unregister(&dn_fib_rules_ops); + fib_rules_unregister(dn_fib_rules_ops); + rcu_barrier(); } diff --git a/net/decnet/dn_table.c b/net/decnet/dn_table.c index 67054b0d550f..b9a33bb5e9cc 100644 --- a/net/decnet/dn_table.c +++ b/net/decnet/dn_table.c @@ -471,7 +471,7 @@ int dn_fib_dump(struct sk_buff *skb, struct netlink_callback *cb) struct hlist_node *node; int dumped = 0; - if (net != &init_net) + if (!net_eq(net, &init_net)) return 0; if (NLMSG_PAYLOAD(cb->nlh, 0) >= sizeof(struct rtmsg) && @@ -581,8 +581,9 @@ static int dn_fib_table_insert(struct dn_fib_table *tb, struct rtmsg *r, struct DN_FIB_SCAN_KEY(f, fp, key) { if (fi->fib_priority != DN_FIB_INFO(f)->fib_priority) break; - if (f->fn_type == type && f->fn_scope == r->rtm_scope - && DN_FIB_INFO(f) == fi) + if (f->fn_type == type && + f->fn_scope == r->rtm_scope && + DN_FIB_INFO(f) == fi) goto out; } diff --git a/net/econet/af_econet.c b/net/econet/af_econet.c index 0e0254fd767d..29b4931aae52 100644 --- a/net/econet/af_econet.c +++ b/net/econet/af_econet.c @@ -457,15 +457,15 @@ static int econet_sendmsg(struct kiocb *iocb, struct socket *sock, iov[0].iov_len = size; for (i = 0; i < msg->msg_iovlen; i++) { void __user *base = msg->msg_iov[i].iov_base; - size_t len = msg->msg_iov[i].iov_len; + size_t iov_len = msg->msg_iov[i].iov_len; /* Check it now since we switch to KERNEL_DS later. */ - if (!access_ok(VERIFY_READ, base, len)) { + if (!access_ok(VERIFY_READ, base, iov_len)) { mutex_unlock(&econet_mutex); return -EFAULT; } iov[i+1].iov_base = base; - iov[i+1].iov_len = len; - size += len; + iov[i+1].iov_len = iov_len; + size += iov_len; } /* Get a skbuff (no data, just holds our cb information) */ @@ -605,13 +605,14 @@ static struct proto econet_proto = { * Create an Econet socket */ -static int econet_create(struct net *net, struct socket *sock, int protocol) +static int econet_create(struct net *net, struct socket *sock, int protocol, + int kern) { struct sock *sk; struct econet_sock *eo; int err; - if (net != &init_net) + if (!net_eq(net, &init_net)) return -EAFNOSUPPORT; /* Econet only provides datagram services. */ @@ -742,7 +743,7 @@ static int econet_ioctl(struct socket *sock, unsigned int cmd, unsigned long arg return 0; } -static struct net_proto_family econet_family_ops = { +static const struct net_proto_family econet_family_ops = { .family = PF_ECONET, .create = econet_create, .owner = THIS_MODULE, diff --git a/net/ethernet/eth.c b/net/ethernet/eth.c index 5a883affecd3..dd3db88f8f0a 100644 --- a/net/ethernet/eth.c +++ b/net/ethernet/eth.c @@ -393,10 +393,3 @@ ssize_t sysfs_format_mac(char *buf, const unsigned char *addr, int len) return ((ssize_t) l); } EXPORT_SYMBOL(sysfs_format_mac); - -char *print_mac(char *buf, const unsigned char *addr) -{ - _format_mac_addr(buf, MAC_BUF_SIZE, addr, ETH_ALEN); - return buf; -} -EXPORT_SYMBOL(print_mac); diff --git a/net/ieee802154/Makefile b/net/ieee802154/Makefile index 4068a9f5113e..ce2d33582859 100644 --- a/net/ieee802154/Makefile +++ b/net/ieee802154/Makefile @@ -1,5 +1,5 @@ -obj-$(CONFIG_IEEE802154) += nl802154.o af_802154.o wpan-class.o -nl802154-y := netlink.o nl_policy.o +obj-$(CONFIG_IEEE802154) += ieee802154.o af_802154.o +ieee802154-y := netlink.o nl-mac.o nl-phy.o nl_policy.o wpan-class.o af_802154-y := af_ieee802154.o raw.o dgram.o ccflags-y += -Wall -DDEBUG diff --git a/net/ieee802154/af_ieee802154.c b/net/ieee802154/af_ieee802154.c index cd949d5e451b..bad1c49fd960 100644 --- a/net/ieee802154/af_ieee802154.c +++ b/net/ieee802154/af_ieee802154.c @@ -234,14 +234,14 @@ static const struct proto_ops ieee802154_dgram_ops = { * set the state. */ static int ieee802154_create(struct net *net, struct socket *sock, - int protocol) + int protocol, int kern) { struct sock *sk; int rc; struct proto *proto; const struct proto_ops *ops; - if (net != &init_net) + if (!net_eq(net, &init_net)) return -EAFNOSUPPORT; switch (sock->type) { @@ -285,7 +285,7 @@ out: return rc; } -static struct net_proto_family ieee802154_family_ops = { +static const struct net_proto_family ieee802154_family_ops = { .family = PF_IEEE802154, .create = ieee802154_create, .owner = THIS_MODULE, diff --git a/net/ieee802154/dgram.c b/net/ieee802154/dgram.c index a413b1bf4465..9aac5aee1575 100644 --- a/net/ieee802154/dgram.c +++ b/net/ieee802154/dgram.c @@ -303,7 +303,7 @@ static int dgram_recvmsg(struct kiocb *iocb, struct sock *sk, if (err) goto done; - sock_recv_timestamp(msg, sk, skb); + sock_recv_ts_and_drops(msg, sk, skb); if (flags & MSG_TRUNC) copied = skb->len; @@ -318,7 +318,6 @@ out: static int dgram_rcv_skb(struct sock *sk, struct sk_buff *skb) { if (sock_queue_rcv_skb(sk, skb) < 0) { - atomic_inc(&sk->sk_drops); kfree_skb(skb); return NET_RX_DROP; } diff --git a/net/ieee802154/ieee802154.h b/net/ieee802154/ieee802154.h new file mode 100644 index 000000000000..aadec428e6ec --- /dev/null +++ b/net/ieee802154/ieee802154.h @@ -0,0 +1,53 @@ +/* + * Copyright (C) 2007, 2008, 2009 Siemens AG + * + * This program is free software; you can redistribute it and/or modify + * it under the terms of the GNU General Public License version 2 + * as published by the Free Software Foundation. + * + * This program is distributed in the hope that it will be useful, + * but WITHOUT ANY WARRANTY; without even the implied warranty of + * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the + * GNU General Public License for more details. + * + * You should have received a copy of the GNU General Public License along + * with this program; if not, write to the Free Software Foundation, Inc., + * 51 Franklin Street, Fifth Floor, Boston, MA 02110-1301 USA. + * + */ +#ifndef IEEE_802154_LOCAL_H +#define IEEE_802154_LOCAL_H + +int __init ieee802154_nl_init(void); +void __exit ieee802154_nl_exit(void); + +#define IEEE802154_OP(_cmd, _func) \ + { \ + .cmd = _cmd, \ + .policy = ieee802154_policy, \ + .doit = _func, \ + .dumpit = NULL, \ + .flags = GENL_ADMIN_PERM, \ + } + +#define IEEE802154_DUMP(_cmd, _func, _dump) \ + { \ + .cmd = _cmd, \ + .policy = ieee802154_policy, \ + .doit = _func, \ + .dumpit = _dump, \ + } + +struct genl_info; + +struct sk_buff *ieee802154_nl_create(int flags, u8 req); +int ieee802154_nl_mcast(struct sk_buff *msg, unsigned int group); +struct sk_buff *ieee802154_nl_new_reply(struct genl_info *info, + int flags, u8 req); +int ieee802154_nl_reply(struct sk_buff *msg, struct genl_info *info); + +extern struct genl_family nl802154_family; +int nl802154_mac_register(void); +int nl802154_phy_register(void); + +#endif diff --git a/net/ieee802154/netlink.c b/net/ieee802154/netlink.c index ca767bde17a4..33137b99e471 100644 --- a/net/ieee802154/netlink.c +++ b/net/ieee802154/netlink.c @@ -23,21 +23,15 @@ */ #include <linux/kernel.h> -#include <linux/if_arp.h> -#include <linux/netdevice.h> -#include <net/netlink.h> #include <net/genetlink.h> -#include <net/sock.h> #include <linux/nl802154.h> -#include <net/af_ieee802154.h> -#include <net/nl802154.h> -#include <net/ieee802154.h> -#include <net/ieee802154_netdev.h> + +#include "ieee802154.h" static unsigned int ieee802154_seq_num; static DEFINE_SPINLOCK(ieee802154_seq_lock); -static struct genl_family ieee802154_coordinator_family = { +struct genl_family nl802154_family = { .id = GENL_ID_GENERATE, .hdrsize = 0, .name = IEEE802154_NL_NAME, @@ -45,16 +39,8 @@ static struct genl_family ieee802154_coordinator_family = { .maxattr = IEEE802154_ATTR_MAX, }; -static struct genl_multicast_group ieee802154_coord_mcgrp = { - .name = IEEE802154_MCAST_COORD_NAME, -}; - -static struct genl_multicast_group ieee802154_beacon_mcgrp = { - .name = IEEE802154_MCAST_BEACON_NAME, -}; - /* Requests to userspace */ -static struct sk_buff *ieee802154_nl_create(int flags, u8 req) +struct sk_buff *ieee802154_nl_create(int flags, u8 req) { void *hdr; struct sk_buff *msg = nlmsg_new(NLMSG_GOODSIZE, GFP_ATOMIC); @@ -65,7 +51,7 @@ static struct sk_buff *ieee802154_nl_create(int flags, u8 req) spin_lock_irqsave(&ieee802154_seq_lock, f); hdr = genlmsg_put(msg, 0, ieee802154_seq_num++, - &ieee802154_coordinator_family, flags, req); + &nl802154_family, flags, req); spin_unlock_irqrestore(&ieee802154_seq_lock, f); if (!hdr) { nlmsg_free(msg); @@ -75,7 +61,7 @@ static struct sk_buff *ieee802154_nl_create(int flags, u8 req) return msg; } -static int ieee802154_nl_finish(struct sk_buff *msg) +int ieee802154_nl_mcast(struct sk_buff *msg, unsigned int group) { /* XXX: nlh is right at the start of msg */ void *hdr = genlmsg_data(NLMSG_DATA(msg->data)); @@ -83,607 +69,70 @@ static int ieee802154_nl_finish(struct sk_buff *msg) if (genlmsg_end(msg, hdr) < 0) goto out; - return genlmsg_multicast(msg, 0, ieee802154_coord_mcgrp.id, - GFP_ATOMIC); + return genlmsg_multicast(msg, 0, group, GFP_ATOMIC); out: nlmsg_free(msg); return -ENOBUFS; } -int ieee802154_nl_assoc_indic(struct net_device *dev, - struct ieee802154_addr *addr, u8 cap) -{ - struct sk_buff *msg; - - pr_debug("%s\n", __func__); - - if (addr->addr_type != IEEE802154_ADDR_LONG) { - pr_err("%s: received non-long source address!\n", __func__); - return -EINVAL; - } - - msg = ieee802154_nl_create(0, IEEE802154_ASSOCIATE_INDIC); - if (!msg) - return -ENOBUFS; - - NLA_PUT_STRING(msg, IEEE802154_ATTR_DEV_NAME, dev->name); - NLA_PUT_U32(msg, IEEE802154_ATTR_DEV_INDEX, dev->ifindex); - NLA_PUT(msg, IEEE802154_ATTR_HW_ADDR, IEEE802154_ADDR_LEN, - dev->dev_addr); - - NLA_PUT(msg, IEEE802154_ATTR_SRC_HW_ADDR, IEEE802154_ADDR_LEN, - addr->hwaddr); - - NLA_PUT_U8(msg, IEEE802154_ATTR_CAPABILITY, cap); - - return ieee802154_nl_finish(msg); - -nla_put_failure: - nlmsg_free(msg); - return -ENOBUFS; -} -EXPORT_SYMBOL(ieee802154_nl_assoc_indic); - -int ieee802154_nl_assoc_confirm(struct net_device *dev, u16 short_addr, - u8 status) -{ - struct sk_buff *msg; - - pr_debug("%s\n", __func__); - - msg = ieee802154_nl_create(0, IEEE802154_ASSOCIATE_CONF); - if (!msg) - return -ENOBUFS; - - NLA_PUT_STRING(msg, IEEE802154_ATTR_DEV_NAME, dev->name); - NLA_PUT_U32(msg, IEEE802154_ATTR_DEV_INDEX, dev->ifindex); - NLA_PUT(msg, IEEE802154_ATTR_HW_ADDR, IEEE802154_ADDR_LEN, - dev->dev_addr); - - NLA_PUT_U16(msg, IEEE802154_ATTR_SHORT_ADDR, short_addr); - NLA_PUT_U8(msg, IEEE802154_ATTR_STATUS, status); - - return ieee802154_nl_finish(msg); - -nla_put_failure: - nlmsg_free(msg); - return -ENOBUFS; -} -EXPORT_SYMBOL(ieee802154_nl_assoc_confirm); - -int ieee802154_nl_disassoc_indic(struct net_device *dev, - struct ieee802154_addr *addr, u8 reason) -{ - struct sk_buff *msg; - - pr_debug("%s\n", __func__); - - msg = ieee802154_nl_create(0, IEEE802154_DISASSOCIATE_INDIC); - if (!msg) - return -ENOBUFS; - - NLA_PUT_STRING(msg, IEEE802154_ATTR_DEV_NAME, dev->name); - NLA_PUT_U32(msg, IEEE802154_ATTR_DEV_INDEX, dev->ifindex); - NLA_PUT(msg, IEEE802154_ATTR_HW_ADDR, IEEE802154_ADDR_LEN, - dev->dev_addr); - - if (addr->addr_type == IEEE802154_ADDR_LONG) - NLA_PUT(msg, IEEE802154_ATTR_SRC_HW_ADDR, IEEE802154_ADDR_LEN, - addr->hwaddr); - else - NLA_PUT_U16(msg, IEEE802154_ATTR_SRC_SHORT_ADDR, - addr->short_addr); - - NLA_PUT_U8(msg, IEEE802154_ATTR_REASON, reason); - - return ieee802154_nl_finish(msg); - -nla_put_failure: - nlmsg_free(msg); - return -ENOBUFS; -} -EXPORT_SYMBOL(ieee802154_nl_disassoc_indic); - -int ieee802154_nl_disassoc_confirm(struct net_device *dev, u8 status) -{ - struct sk_buff *msg; - - pr_debug("%s\n", __func__); - - msg = ieee802154_nl_create(0, IEEE802154_DISASSOCIATE_CONF); - if (!msg) - return -ENOBUFS; - - NLA_PUT_STRING(msg, IEEE802154_ATTR_DEV_NAME, dev->name); - NLA_PUT_U32(msg, IEEE802154_ATTR_DEV_INDEX, dev->ifindex); - NLA_PUT(msg, IEEE802154_ATTR_HW_ADDR, IEEE802154_ADDR_LEN, - dev->dev_addr); - - NLA_PUT_U8(msg, IEEE802154_ATTR_STATUS, status); - - return ieee802154_nl_finish(msg); - -nla_put_failure: - nlmsg_free(msg); - return -ENOBUFS; -} -EXPORT_SYMBOL(ieee802154_nl_disassoc_confirm); - -int ieee802154_nl_beacon_indic(struct net_device *dev, - u16 panid, u16 coord_addr) -{ - struct sk_buff *msg; - - pr_debug("%s\n", __func__); - - msg = ieee802154_nl_create(0, IEEE802154_BEACON_NOTIFY_INDIC); - if (!msg) - return -ENOBUFS; - - NLA_PUT_STRING(msg, IEEE802154_ATTR_DEV_NAME, dev->name); - NLA_PUT_U32(msg, IEEE802154_ATTR_DEV_INDEX, dev->ifindex); - NLA_PUT(msg, IEEE802154_ATTR_HW_ADDR, IEEE802154_ADDR_LEN, - dev->dev_addr); - NLA_PUT_U16(msg, IEEE802154_ATTR_COORD_SHORT_ADDR, coord_addr); - NLA_PUT_U16(msg, IEEE802154_ATTR_COORD_PAN_ID, panid); - - return ieee802154_nl_finish(msg); - -nla_put_failure: - nlmsg_free(msg); - return -ENOBUFS; -} -EXPORT_SYMBOL(ieee802154_nl_beacon_indic); - -int ieee802154_nl_scan_confirm(struct net_device *dev, - u8 status, u8 scan_type, u32 unscanned, u8 page, - u8 *edl/* , struct list_head *pan_desc_list */) -{ - struct sk_buff *msg; - - pr_debug("%s\n", __func__); - - msg = ieee802154_nl_create(0, IEEE802154_SCAN_CONF); - if (!msg) - return -ENOBUFS; - - NLA_PUT_STRING(msg, IEEE802154_ATTR_DEV_NAME, dev->name); - NLA_PUT_U32(msg, IEEE802154_ATTR_DEV_INDEX, dev->ifindex); - NLA_PUT(msg, IEEE802154_ATTR_HW_ADDR, IEEE802154_ADDR_LEN, - dev->dev_addr); - - NLA_PUT_U8(msg, IEEE802154_ATTR_STATUS, status); - NLA_PUT_U8(msg, IEEE802154_ATTR_SCAN_TYPE, scan_type); - NLA_PUT_U32(msg, IEEE802154_ATTR_CHANNELS, unscanned); - NLA_PUT_U8(msg, IEEE802154_ATTR_PAGE, page); - - if (edl) - NLA_PUT(msg, IEEE802154_ATTR_ED_LIST, 27, edl); - - return ieee802154_nl_finish(msg); - -nla_put_failure: - nlmsg_free(msg); - return -ENOBUFS; -} -EXPORT_SYMBOL(ieee802154_nl_scan_confirm); - -int ieee802154_nl_start_confirm(struct net_device *dev, u8 status) -{ - struct sk_buff *msg; - - pr_debug("%s\n", __func__); - - msg = ieee802154_nl_create(0, IEEE802154_START_CONF); - if (!msg) - return -ENOBUFS; - - NLA_PUT_STRING(msg, IEEE802154_ATTR_DEV_NAME, dev->name); - NLA_PUT_U32(msg, IEEE802154_ATTR_DEV_INDEX, dev->ifindex); - NLA_PUT(msg, IEEE802154_ATTR_HW_ADDR, IEEE802154_ADDR_LEN, - dev->dev_addr); - - NLA_PUT_U8(msg, IEEE802154_ATTR_STATUS, status); - - return ieee802154_nl_finish(msg); - -nla_put_failure: - nlmsg_free(msg); - return -ENOBUFS; -} -EXPORT_SYMBOL(ieee802154_nl_start_confirm); - -static int ieee802154_nl_fill_iface(struct sk_buff *msg, u32 pid, - u32 seq, int flags, struct net_device *dev) +struct sk_buff *ieee802154_nl_new_reply(struct genl_info *info, + int flags, u8 req) { void *hdr; + struct sk_buff *msg = nlmsg_new(NLMSG_GOODSIZE, GFP_ATOMIC); - pr_debug("%s\n", __func__); - - hdr = genlmsg_put(msg, 0, seq, &ieee802154_coordinator_family, flags, - IEEE802154_LIST_IFACE); - if (!hdr) - goto out; - - NLA_PUT_STRING(msg, IEEE802154_ATTR_DEV_NAME, dev->name); - NLA_PUT_U32(msg, IEEE802154_ATTR_DEV_INDEX, dev->ifindex); - - NLA_PUT(msg, IEEE802154_ATTR_HW_ADDR, IEEE802154_ADDR_LEN, - dev->dev_addr); - NLA_PUT_U16(msg, IEEE802154_ATTR_SHORT_ADDR, - ieee802154_mlme_ops(dev)->get_short_addr(dev)); - NLA_PUT_U16(msg, IEEE802154_ATTR_PAN_ID, - ieee802154_mlme_ops(dev)->get_pan_id(dev)); - return genlmsg_end(msg, hdr); - -nla_put_failure: - genlmsg_cancel(msg, hdr); -out: - return -EMSGSIZE; -} - -/* Requests from userspace */ -static struct net_device *ieee802154_nl_get_dev(struct genl_info *info) -{ - struct net_device *dev; - - if (info->attrs[IEEE802154_ATTR_DEV_NAME]) { - char name[IFNAMSIZ + 1]; - nla_strlcpy(name, info->attrs[IEEE802154_ATTR_DEV_NAME], - sizeof(name)); - dev = dev_get_by_name(&init_net, name); - } else if (info->attrs[IEEE802154_ATTR_DEV_INDEX]) - dev = dev_get_by_index(&init_net, - nla_get_u32(info->attrs[IEEE802154_ATTR_DEV_INDEX])); - else - return NULL; - - if (!dev) + if (!msg) return NULL; - if (dev->type != ARPHRD_IEEE802154) { - dev_put(dev); + hdr = genlmsg_put_reply(msg, info, + &nl802154_family, flags, req); + if (!hdr) { + nlmsg_free(msg); return NULL; } - return dev; -} - -static int ieee802154_associate_req(struct sk_buff *skb, - struct genl_info *info) -{ - struct net_device *dev; - struct ieee802154_addr addr; - u8 page; - int ret = -EINVAL; - - if (!info->attrs[IEEE802154_ATTR_CHANNEL] || - !info->attrs[IEEE802154_ATTR_COORD_PAN_ID] || - (!info->attrs[IEEE802154_ATTR_COORD_HW_ADDR] && - !info->attrs[IEEE802154_ATTR_COORD_SHORT_ADDR]) || - !info->attrs[IEEE802154_ATTR_CAPABILITY]) - return -EINVAL; - - dev = ieee802154_nl_get_dev(info); - if (!dev) - return -ENODEV; - - if (info->attrs[IEEE802154_ATTR_COORD_HW_ADDR]) { - addr.addr_type = IEEE802154_ADDR_LONG; - nla_memcpy(addr.hwaddr, - info->attrs[IEEE802154_ATTR_COORD_HW_ADDR], - IEEE802154_ADDR_LEN); - } else { - addr.addr_type = IEEE802154_ADDR_SHORT; - addr.short_addr = nla_get_u16( - info->attrs[IEEE802154_ATTR_COORD_SHORT_ADDR]); - } - addr.pan_id = nla_get_u16(info->attrs[IEEE802154_ATTR_COORD_PAN_ID]); - - if (info->attrs[IEEE802154_ATTR_PAGE]) - page = nla_get_u8(info->attrs[IEEE802154_ATTR_PAGE]); - else - page = 0; - - ret = ieee802154_mlme_ops(dev)->assoc_req(dev, &addr, - nla_get_u8(info->attrs[IEEE802154_ATTR_CHANNEL]), - page, - nla_get_u8(info->attrs[IEEE802154_ATTR_CAPABILITY])); - - dev_put(dev); - return ret; -} - -static int ieee802154_associate_resp(struct sk_buff *skb, - struct genl_info *info) -{ - struct net_device *dev; - struct ieee802154_addr addr; - int ret = -EINVAL; - - if (!info->attrs[IEEE802154_ATTR_STATUS] || - !info->attrs[IEEE802154_ATTR_DEST_HW_ADDR] || - !info->attrs[IEEE802154_ATTR_DEST_SHORT_ADDR]) - return -EINVAL; - - dev = ieee802154_nl_get_dev(info); - if (!dev) - return -ENODEV; - - addr.addr_type = IEEE802154_ADDR_LONG; - nla_memcpy(addr.hwaddr, info->attrs[IEEE802154_ATTR_DEST_HW_ADDR], - IEEE802154_ADDR_LEN); - addr.pan_id = ieee802154_mlme_ops(dev)->get_pan_id(dev); - - - ret = ieee802154_mlme_ops(dev)->assoc_resp(dev, &addr, - nla_get_u16(info->attrs[IEEE802154_ATTR_DEST_SHORT_ADDR]), - nla_get_u8(info->attrs[IEEE802154_ATTR_STATUS])); - - dev_put(dev); - return ret; -} - -static int ieee802154_disassociate_req(struct sk_buff *skb, - struct genl_info *info) -{ - struct net_device *dev; - struct ieee802154_addr addr; - int ret = -EINVAL; - - if ((!info->attrs[IEEE802154_ATTR_DEST_HW_ADDR] && - !info->attrs[IEEE802154_ATTR_DEST_SHORT_ADDR]) || - !info->attrs[IEEE802154_ATTR_REASON]) - return -EINVAL; - - dev = ieee802154_nl_get_dev(info); - if (!dev) - return -ENODEV; - - if (info->attrs[IEEE802154_ATTR_DEST_HW_ADDR]) { - addr.addr_type = IEEE802154_ADDR_LONG; - nla_memcpy(addr.hwaddr, - info->attrs[IEEE802154_ATTR_DEST_HW_ADDR], - IEEE802154_ADDR_LEN); - } else { - addr.addr_type = IEEE802154_ADDR_SHORT; - addr.short_addr = nla_get_u16( - info->attrs[IEEE802154_ATTR_DEST_SHORT_ADDR]); - } - addr.pan_id = ieee802154_mlme_ops(dev)->get_pan_id(dev); - - ret = ieee802154_mlme_ops(dev)->disassoc_req(dev, &addr, - nla_get_u8(info->attrs[IEEE802154_ATTR_REASON])); - - dev_put(dev); - return ret; -} - -/* - * PANid, channel, beacon_order = 15, superframe_order = 15, - * PAN_coordinator, battery_life_extension = 0, - * coord_realignment = 0, security_enable = 0 -*/ -static int ieee802154_start_req(struct sk_buff *skb, struct genl_info *info) -{ - struct net_device *dev; - struct ieee802154_addr addr; - - u8 channel, bcn_ord, sf_ord; - u8 page; - int pan_coord, blx, coord_realign; - int ret; - - if (!info->attrs[IEEE802154_ATTR_COORD_PAN_ID] || - !info->attrs[IEEE802154_ATTR_COORD_SHORT_ADDR] || - !info->attrs[IEEE802154_ATTR_CHANNEL] || - !info->attrs[IEEE802154_ATTR_BCN_ORD] || - !info->attrs[IEEE802154_ATTR_SF_ORD] || - !info->attrs[IEEE802154_ATTR_PAN_COORD] || - !info->attrs[IEEE802154_ATTR_BAT_EXT] || - !info->attrs[IEEE802154_ATTR_COORD_REALIGN] - ) - return -EINVAL; - - dev = ieee802154_nl_get_dev(info); - if (!dev) - return -ENODEV; - - addr.addr_type = IEEE802154_ADDR_SHORT; - addr.short_addr = nla_get_u16( - info->attrs[IEEE802154_ATTR_COORD_SHORT_ADDR]); - addr.pan_id = nla_get_u16(info->attrs[IEEE802154_ATTR_COORD_PAN_ID]); - - channel = nla_get_u8(info->attrs[IEEE802154_ATTR_CHANNEL]); - bcn_ord = nla_get_u8(info->attrs[IEEE802154_ATTR_BCN_ORD]); - sf_ord = nla_get_u8(info->attrs[IEEE802154_ATTR_SF_ORD]); - pan_coord = nla_get_u8(info->attrs[IEEE802154_ATTR_PAN_COORD]); - blx = nla_get_u8(info->attrs[IEEE802154_ATTR_BAT_EXT]); - coord_realign = nla_get_u8(info->attrs[IEEE802154_ATTR_COORD_REALIGN]); - - if (info->attrs[IEEE802154_ATTR_PAGE]) - page = nla_get_u8(info->attrs[IEEE802154_ATTR_PAGE]); - else - page = 0; - - - if (addr.short_addr == IEEE802154_ADDR_BROADCAST) { - ieee802154_nl_start_confirm(dev, IEEE802154_NO_SHORT_ADDRESS); - dev_put(dev); - return -EINVAL; - } - - ret = ieee802154_mlme_ops(dev)->start_req(dev, &addr, channel, page, - bcn_ord, sf_ord, pan_coord, blx, coord_realign); - - dev_put(dev); - return ret; -} - -static int ieee802154_scan_req(struct sk_buff *skb, struct genl_info *info) -{ - struct net_device *dev; - int ret; - u8 type; - u32 channels; - u8 duration; - u8 page; - - if (!info->attrs[IEEE802154_ATTR_SCAN_TYPE] || - !info->attrs[IEEE802154_ATTR_CHANNELS] || - !info->attrs[IEEE802154_ATTR_DURATION]) - return -EINVAL; - - dev = ieee802154_nl_get_dev(info); - if (!dev) - return -ENODEV; - - type = nla_get_u8(info->attrs[IEEE802154_ATTR_SCAN_TYPE]); - channels = nla_get_u32(info->attrs[IEEE802154_ATTR_CHANNELS]); - duration = nla_get_u8(info->attrs[IEEE802154_ATTR_DURATION]); - - if (info->attrs[IEEE802154_ATTR_PAGE]) - page = nla_get_u8(info->attrs[IEEE802154_ATTR_PAGE]); - else - page = 0; - - - ret = ieee802154_mlme_ops(dev)->scan_req(dev, type, channels, page, - duration); - - dev_put(dev); - return ret; + return msg; } -static int ieee802154_list_iface(struct sk_buff *skb, - struct genl_info *info) +int ieee802154_nl_reply(struct sk_buff *msg, struct genl_info *info) { - /* Request for interface name, index, type, IEEE address, - PAN Id, short address */ - struct sk_buff *msg; - struct net_device *dev = NULL; - int rc = -ENOBUFS; - - pr_debug("%s\n", __func__); - - dev = ieee802154_nl_get_dev(info); - if (!dev) - return -ENODEV; - - msg = nlmsg_new(NLMSG_GOODSIZE, GFP_KERNEL); - if (!msg) - goto out_dev; - - rc = ieee802154_nl_fill_iface(msg, info->snd_pid, info->snd_seq, - 0, dev); - if (rc < 0) - goto out_free; + /* XXX: nlh is right at the start of msg */ + void *hdr = genlmsg_data(NLMSG_DATA(msg->data)); - dev_put(dev); + if (genlmsg_end(msg, hdr) < 0) + goto out; - return genlmsg_unicast(&init_net, msg, info->snd_pid); -out_free: + return genlmsg_reply(msg, info); +out: nlmsg_free(msg); -out_dev: - dev_put(dev); - return rc; - -} - -static int ieee802154_dump_iface(struct sk_buff *skb, - struct netlink_callback *cb) -{ - struct net *net = sock_net(skb->sk); - struct net_device *dev; - int idx; - int s_idx = cb->args[0]; - - pr_debug("%s\n", __func__); - - idx = 0; - for_each_netdev(net, dev) { - if (idx < s_idx || (dev->type != ARPHRD_IEEE802154)) - goto cont; - - if (ieee802154_nl_fill_iface(skb, NETLINK_CB(cb->skb).pid, - cb->nlh->nlmsg_seq, NLM_F_MULTI, dev) < 0) - break; -cont: - idx++; - } - cb->args[0] = idx; - - return skb->len; + return -ENOBUFS; } -#define IEEE802154_OP(_cmd, _func) \ - { \ - .cmd = _cmd, \ - .policy = ieee802154_policy, \ - .doit = _func, \ - .dumpit = NULL, \ - .flags = GENL_ADMIN_PERM, \ - } - -#define IEEE802154_DUMP(_cmd, _func, _dump) \ - { \ - .cmd = _cmd, \ - .policy = ieee802154_policy, \ - .doit = _func, \ - .dumpit = _dump, \ - } - -static struct genl_ops ieee802154_coordinator_ops[] = { - IEEE802154_OP(IEEE802154_ASSOCIATE_REQ, ieee802154_associate_req), - IEEE802154_OP(IEEE802154_ASSOCIATE_RESP, ieee802154_associate_resp), - IEEE802154_OP(IEEE802154_DISASSOCIATE_REQ, ieee802154_disassociate_req), - IEEE802154_OP(IEEE802154_SCAN_REQ, ieee802154_scan_req), - IEEE802154_OP(IEEE802154_START_REQ, ieee802154_start_req), - IEEE802154_DUMP(IEEE802154_LIST_IFACE, ieee802154_list_iface, - ieee802154_dump_iface), -}; - -static int __init ieee802154_nl_init(void) +int __init ieee802154_nl_init(void) { int rc; - int i; - rc = genl_register_family(&ieee802154_coordinator_family); + rc = genl_register_family(&nl802154_family); if (rc) goto fail; - rc = genl_register_mc_group(&ieee802154_coordinator_family, - &ieee802154_coord_mcgrp); + rc = nl802154_mac_register(); if (rc) goto fail; - rc = genl_register_mc_group(&ieee802154_coordinator_family, - &ieee802154_beacon_mcgrp); + rc = nl802154_phy_register(); if (rc) goto fail; - - for (i = 0; i < ARRAY_SIZE(ieee802154_coordinator_ops); i++) { - rc = genl_register_ops(&ieee802154_coordinator_family, - &ieee802154_coordinator_ops[i]); - if (rc) - goto fail; - } - return 0; fail: - genl_unregister_family(&ieee802154_coordinator_family); + genl_unregister_family(&nl802154_family); return rc; } -module_init(ieee802154_nl_init); -static void __exit ieee802154_nl_exit(void) +void __exit ieee802154_nl_exit(void) { - genl_unregister_family(&ieee802154_coordinator_family); + genl_unregister_family(&nl802154_family); } -module_exit(ieee802154_nl_exit); - -MODULE_LICENSE("GPL v2"); -MODULE_DESCRIPTION("ieee 802.15.4 configuration interface"); diff --git a/net/ieee802154/nl-mac.c b/net/ieee802154/nl-mac.c new file mode 100644 index 000000000000..135c1678fb11 --- /dev/null +++ b/net/ieee802154/nl-mac.c @@ -0,0 +1,617 @@ +/* + * Netlink inteface for IEEE 802.15.4 stack + * + * Copyright 2007, 2008 Siemens AG + * + * This program is free software; you can redistribute it and/or modify + * it under the terms of the GNU General Public License version 2 + * as published by the Free Software Foundation. + * + * This program is distributed in the hope that it will be useful, + * but WITHOUT ANY WARRANTY; without even the implied warranty of + * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the + * GNU General Public License for more details. + * + * You should have received a copy of the GNU General Public License along + * with this program; if not, write to the Free Software Foundation, Inc., + * 51 Franklin Street, Fifth Floor, Boston, MA 02110-1301 USA. + * + * Written by: + * Sergey Lapin <slapin@ossfans.org> + * Dmitry Eremin-Solenikov <dbaryshkov@gmail.com> + * Maxim Osipov <maxim.osipov@siemens.com> + */ + +#include <linux/kernel.h> +#include <linux/if_arp.h> +#include <linux/netdevice.h> +#include <net/netlink.h> +#include <net/genetlink.h> +#include <net/sock.h> +#include <linux/nl802154.h> +#include <net/af_ieee802154.h> +#include <net/nl802154.h> +#include <net/ieee802154.h> +#include <net/ieee802154_netdev.h> +#include <net/wpan-phy.h> + +#include "ieee802154.h" + +static struct genl_multicast_group ieee802154_coord_mcgrp = { + .name = IEEE802154_MCAST_COORD_NAME, +}; + +static struct genl_multicast_group ieee802154_beacon_mcgrp = { + .name = IEEE802154_MCAST_BEACON_NAME, +}; + +int ieee802154_nl_assoc_indic(struct net_device *dev, + struct ieee802154_addr *addr, u8 cap) +{ + struct sk_buff *msg; + + pr_debug("%s\n", __func__); + + if (addr->addr_type != IEEE802154_ADDR_LONG) { + pr_err("%s: received non-long source address!\n", __func__); + return -EINVAL; + } + + msg = ieee802154_nl_create(0, IEEE802154_ASSOCIATE_INDIC); + if (!msg) + return -ENOBUFS; + + NLA_PUT_STRING(msg, IEEE802154_ATTR_DEV_NAME, dev->name); + NLA_PUT_U32(msg, IEEE802154_ATTR_DEV_INDEX, dev->ifindex); + NLA_PUT(msg, IEEE802154_ATTR_HW_ADDR, IEEE802154_ADDR_LEN, + dev->dev_addr); + + NLA_PUT(msg, IEEE802154_ATTR_SRC_HW_ADDR, IEEE802154_ADDR_LEN, + addr->hwaddr); + + NLA_PUT_U8(msg, IEEE802154_ATTR_CAPABILITY, cap); + + return ieee802154_nl_mcast(msg, ieee802154_coord_mcgrp.id); + +nla_put_failure: + nlmsg_free(msg); + return -ENOBUFS; +} +EXPORT_SYMBOL(ieee802154_nl_assoc_indic); + +int ieee802154_nl_assoc_confirm(struct net_device *dev, u16 short_addr, + u8 status) +{ + struct sk_buff *msg; + + pr_debug("%s\n", __func__); + + msg = ieee802154_nl_create(0, IEEE802154_ASSOCIATE_CONF); + if (!msg) + return -ENOBUFS; + + NLA_PUT_STRING(msg, IEEE802154_ATTR_DEV_NAME, dev->name); + NLA_PUT_U32(msg, IEEE802154_ATTR_DEV_INDEX, dev->ifindex); + NLA_PUT(msg, IEEE802154_ATTR_HW_ADDR, IEEE802154_ADDR_LEN, + dev->dev_addr); + + NLA_PUT_U16(msg, IEEE802154_ATTR_SHORT_ADDR, short_addr); + NLA_PUT_U8(msg, IEEE802154_ATTR_STATUS, status); + + return ieee802154_nl_mcast(msg, ieee802154_coord_mcgrp.id); + +nla_put_failure: + nlmsg_free(msg); + return -ENOBUFS; +} +EXPORT_SYMBOL(ieee802154_nl_assoc_confirm); + +int ieee802154_nl_disassoc_indic(struct net_device *dev, + struct ieee802154_addr *addr, u8 reason) +{ + struct sk_buff *msg; + + pr_debug("%s\n", __func__); + + msg = ieee802154_nl_create(0, IEEE802154_DISASSOCIATE_INDIC); + if (!msg) + return -ENOBUFS; + + NLA_PUT_STRING(msg, IEEE802154_ATTR_DEV_NAME, dev->name); + NLA_PUT_U32(msg, IEEE802154_ATTR_DEV_INDEX, dev->ifindex); + NLA_PUT(msg, IEEE802154_ATTR_HW_ADDR, IEEE802154_ADDR_LEN, + dev->dev_addr); + + if (addr->addr_type == IEEE802154_ADDR_LONG) + NLA_PUT(msg, IEEE802154_ATTR_SRC_HW_ADDR, IEEE802154_ADDR_LEN, + addr->hwaddr); + else + NLA_PUT_U16(msg, IEEE802154_ATTR_SRC_SHORT_ADDR, + addr->short_addr); + + NLA_PUT_U8(msg, IEEE802154_ATTR_REASON, reason); + + return ieee802154_nl_mcast(msg, ieee802154_coord_mcgrp.id); + +nla_put_failure: + nlmsg_free(msg); + return -ENOBUFS; +} +EXPORT_SYMBOL(ieee802154_nl_disassoc_indic); + +int ieee802154_nl_disassoc_confirm(struct net_device *dev, u8 status) +{ + struct sk_buff *msg; + + pr_debug("%s\n", __func__); + + msg = ieee802154_nl_create(0, IEEE802154_DISASSOCIATE_CONF); + if (!msg) + return -ENOBUFS; + + NLA_PUT_STRING(msg, IEEE802154_ATTR_DEV_NAME, dev->name); + NLA_PUT_U32(msg, IEEE802154_ATTR_DEV_INDEX, dev->ifindex); + NLA_PUT(msg, IEEE802154_ATTR_HW_ADDR, IEEE802154_ADDR_LEN, + dev->dev_addr); + + NLA_PUT_U8(msg, IEEE802154_ATTR_STATUS, status); + + return ieee802154_nl_mcast(msg, ieee802154_coord_mcgrp.id); + +nla_put_failure: + nlmsg_free(msg); + return -ENOBUFS; +} +EXPORT_SYMBOL(ieee802154_nl_disassoc_confirm); + +int ieee802154_nl_beacon_indic(struct net_device *dev, + u16 panid, u16 coord_addr) +{ + struct sk_buff *msg; + + pr_debug("%s\n", __func__); + + msg = ieee802154_nl_create(0, IEEE802154_BEACON_NOTIFY_INDIC); + if (!msg) + return -ENOBUFS; + + NLA_PUT_STRING(msg, IEEE802154_ATTR_DEV_NAME, dev->name); + NLA_PUT_U32(msg, IEEE802154_ATTR_DEV_INDEX, dev->ifindex); + NLA_PUT(msg, IEEE802154_ATTR_HW_ADDR, IEEE802154_ADDR_LEN, + dev->dev_addr); + NLA_PUT_U16(msg, IEEE802154_ATTR_COORD_SHORT_ADDR, coord_addr); + NLA_PUT_U16(msg, IEEE802154_ATTR_COORD_PAN_ID, panid); + + return ieee802154_nl_mcast(msg, ieee802154_coord_mcgrp.id); + +nla_put_failure: + nlmsg_free(msg); + return -ENOBUFS; +} +EXPORT_SYMBOL(ieee802154_nl_beacon_indic); + +int ieee802154_nl_scan_confirm(struct net_device *dev, + u8 status, u8 scan_type, u32 unscanned, u8 page, + u8 *edl/* , struct list_head *pan_desc_list */) +{ + struct sk_buff *msg; + + pr_debug("%s\n", __func__); + + msg = ieee802154_nl_create(0, IEEE802154_SCAN_CONF); + if (!msg) + return -ENOBUFS; + + NLA_PUT_STRING(msg, IEEE802154_ATTR_DEV_NAME, dev->name); + NLA_PUT_U32(msg, IEEE802154_ATTR_DEV_INDEX, dev->ifindex); + NLA_PUT(msg, IEEE802154_ATTR_HW_ADDR, IEEE802154_ADDR_LEN, + dev->dev_addr); + + NLA_PUT_U8(msg, IEEE802154_ATTR_STATUS, status); + NLA_PUT_U8(msg, IEEE802154_ATTR_SCAN_TYPE, scan_type); + NLA_PUT_U32(msg, IEEE802154_ATTR_CHANNELS, unscanned); + NLA_PUT_U8(msg, IEEE802154_ATTR_PAGE, page); + + if (edl) + NLA_PUT(msg, IEEE802154_ATTR_ED_LIST, 27, edl); + + return ieee802154_nl_mcast(msg, ieee802154_coord_mcgrp.id); + +nla_put_failure: + nlmsg_free(msg); + return -ENOBUFS; +} +EXPORT_SYMBOL(ieee802154_nl_scan_confirm); + +int ieee802154_nl_start_confirm(struct net_device *dev, u8 status) +{ + struct sk_buff *msg; + + pr_debug("%s\n", __func__); + + msg = ieee802154_nl_create(0, IEEE802154_START_CONF); + if (!msg) + return -ENOBUFS; + + NLA_PUT_STRING(msg, IEEE802154_ATTR_DEV_NAME, dev->name); + NLA_PUT_U32(msg, IEEE802154_ATTR_DEV_INDEX, dev->ifindex); + NLA_PUT(msg, IEEE802154_ATTR_HW_ADDR, IEEE802154_ADDR_LEN, + dev->dev_addr); + + NLA_PUT_U8(msg, IEEE802154_ATTR_STATUS, status); + + return ieee802154_nl_mcast(msg, ieee802154_coord_mcgrp.id); + +nla_put_failure: + nlmsg_free(msg); + return -ENOBUFS; +} +EXPORT_SYMBOL(ieee802154_nl_start_confirm); + +static int ieee802154_nl_fill_iface(struct sk_buff *msg, u32 pid, + u32 seq, int flags, struct net_device *dev) +{ + void *hdr; + struct wpan_phy *phy; + + pr_debug("%s\n", __func__); + + hdr = genlmsg_put(msg, 0, seq, &nl802154_family, flags, + IEEE802154_LIST_IFACE); + if (!hdr) + goto out; + + phy = ieee802154_mlme_ops(dev)->get_phy(dev); + BUG_ON(!phy); + + NLA_PUT_STRING(msg, IEEE802154_ATTR_DEV_NAME, dev->name); + NLA_PUT_STRING(msg, IEEE802154_ATTR_PHY_NAME, wpan_phy_name(phy)); + NLA_PUT_U32(msg, IEEE802154_ATTR_DEV_INDEX, dev->ifindex); + + NLA_PUT(msg, IEEE802154_ATTR_HW_ADDR, IEEE802154_ADDR_LEN, + dev->dev_addr); + NLA_PUT_U16(msg, IEEE802154_ATTR_SHORT_ADDR, + ieee802154_mlme_ops(dev)->get_short_addr(dev)); + NLA_PUT_U16(msg, IEEE802154_ATTR_PAN_ID, + ieee802154_mlme_ops(dev)->get_pan_id(dev)); + wpan_phy_put(phy); + return genlmsg_end(msg, hdr); + +nla_put_failure: + wpan_phy_put(phy); + genlmsg_cancel(msg, hdr); +out: + return -EMSGSIZE; +} + +/* Requests from userspace */ +static struct net_device *ieee802154_nl_get_dev(struct genl_info *info) +{ + struct net_device *dev; + + if (info->attrs[IEEE802154_ATTR_DEV_NAME]) { + char name[IFNAMSIZ + 1]; + nla_strlcpy(name, info->attrs[IEEE802154_ATTR_DEV_NAME], + sizeof(name)); + dev = dev_get_by_name(&init_net, name); + } else if (info->attrs[IEEE802154_ATTR_DEV_INDEX]) + dev = dev_get_by_index(&init_net, + nla_get_u32(info->attrs[IEEE802154_ATTR_DEV_INDEX])); + else + return NULL; + + if (!dev) + return NULL; + + if (dev->type != ARPHRD_IEEE802154) { + dev_put(dev); + return NULL; + } + + return dev; +} + +static int ieee802154_associate_req(struct sk_buff *skb, + struct genl_info *info) +{ + struct net_device *dev; + struct ieee802154_addr addr; + u8 page; + int ret = -EINVAL; + + if (!info->attrs[IEEE802154_ATTR_CHANNEL] || + !info->attrs[IEEE802154_ATTR_COORD_PAN_ID] || + (!info->attrs[IEEE802154_ATTR_COORD_HW_ADDR] && + !info->attrs[IEEE802154_ATTR_COORD_SHORT_ADDR]) || + !info->attrs[IEEE802154_ATTR_CAPABILITY]) + return -EINVAL; + + dev = ieee802154_nl_get_dev(info); + if (!dev) + return -ENODEV; + + if (info->attrs[IEEE802154_ATTR_COORD_HW_ADDR]) { + addr.addr_type = IEEE802154_ADDR_LONG; + nla_memcpy(addr.hwaddr, + info->attrs[IEEE802154_ATTR_COORD_HW_ADDR], + IEEE802154_ADDR_LEN); + } else { + addr.addr_type = IEEE802154_ADDR_SHORT; + addr.short_addr = nla_get_u16( + info->attrs[IEEE802154_ATTR_COORD_SHORT_ADDR]); + } + addr.pan_id = nla_get_u16(info->attrs[IEEE802154_ATTR_COORD_PAN_ID]); + + if (info->attrs[IEEE802154_ATTR_PAGE]) + page = nla_get_u8(info->attrs[IEEE802154_ATTR_PAGE]); + else + page = 0; + + ret = ieee802154_mlme_ops(dev)->assoc_req(dev, &addr, + nla_get_u8(info->attrs[IEEE802154_ATTR_CHANNEL]), + page, + nla_get_u8(info->attrs[IEEE802154_ATTR_CAPABILITY])); + + dev_put(dev); + return ret; +} + +static int ieee802154_associate_resp(struct sk_buff *skb, + struct genl_info *info) +{ + struct net_device *dev; + struct ieee802154_addr addr; + int ret = -EINVAL; + + if (!info->attrs[IEEE802154_ATTR_STATUS] || + !info->attrs[IEEE802154_ATTR_DEST_HW_ADDR] || + !info->attrs[IEEE802154_ATTR_DEST_SHORT_ADDR]) + return -EINVAL; + + dev = ieee802154_nl_get_dev(info); + if (!dev) + return -ENODEV; + + addr.addr_type = IEEE802154_ADDR_LONG; + nla_memcpy(addr.hwaddr, info->attrs[IEEE802154_ATTR_DEST_HW_ADDR], + IEEE802154_ADDR_LEN); + addr.pan_id = ieee802154_mlme_ops(dev)->get_pan_id(dev); + + + ret = ieee802154_mlme_ops(dev)->assoc_resp(dev, &addr, + nla_get_u16(info->attrs[IEEE802154_ATTR_DEST_SHORT_ADDR]), + nla_get_u8(info->attrs[IEEE802154_ATTR_STATUS])); + + dev_put(dev); + return ret; +} + +static int ieee802154_disassociate_req(struct sk_buff *skb, + struct genl_info *info) +{ + struct net_device *dev; + struct ieee802154_addr addr; + int ret = -EINVAL; + + if ((!info->attrs[IEEE802154_ATTR_DEST_HW_ADDR] && + !info->attrs[IEEE802154_ATTR_DEST_SHORT_ADDR]) || + !info->attrs[IEEE802154_ATTR_REASON]) + return -EINVAL; + + dev = ieee802154_nl_get_dev(info); + if (!dev) + return -ENODEV; + + if (info->attrs[IEEE802154_ATTR_DEST_HW_ADDR]) { + addr.addr_type = IEEE802154_ADDR_LONG; + nla_memcpy(addr.hwaddr, + info->attrs[IEEE802154_ATTR_DEST_HW_ADDR], + IEEE802154_ADDR_LEN); + } else { + addr.addr_type = IEEE802154_ADDR_SHORT; + addr.short_addr = nla_get_u16( + info->attrs[IEEE802154_ATTR_DEST_SHORT_ADDR]); + } + addr.pan_id = ieee802154_mlme_ops(dev)->get_pan_id(dev); + + ret = ieee802154_mlme_ops(dev)->disassoc_req(dev, &addr, + nla_get_u8(info->attrs[IEEE802154_ATTR_REASON])); + + dev_put(dev); + return ret; +} + +/* + * PANid, channel, beacon_order = 15, superframe_order = 15, + * PAN_coordinator, battery_life_extension = 0, + * coord_realignment = 0, security_enable = 0 +*/ +static int ieee802154_start_req(struct sk_buff *skb, struct genl_info *info) +{ + struct net_device *dev; + struct ieee802154_addr addr; + + u8 channel, bcn_ord, sf_ord; + u8 page; + int pan_coord, blx, coord_realign; + int ret; + + if (!info->attrs[IEEE802154_ATTR_COORD_PAN_ID] || + !info->attrs[IEEE802154_ATTR_COORD_SHORT_ADDR] || + !info->attrs[IEEE802154_ATTR_CHANNEL] || + !info->attrs[IEEE802154_ATTR_BCN_ORD] || + !info->attrs[IEEE802154_ATTR_SF_ORD] || + !info->attrs[IEEE802154_ATTR_PAN_COORD] || + !info->attrs[IEEE802154_ATTR_BAT_EXT] || + !info->attrs[IEEE802154_ATTR_COORD_REALIGN] + ) + return -EINVAL; + + dev = ieee802154_nl_get_dev(info); + if (!dev) + return -ENODEV; + + addr.addr_type = IEEE802154_ADDR_SHORT; + addr.short_addr = nla_get_u16( + info->attrs[IEEE802154_ATTR_COORD_SHORT_ADDR]); + addr.pan_id = nla_get_u16(info->attrs[IEEE802154_ATTR_COORD_PAN_ID]); + + channel = nla_get_u8(info->attrs[IEEE802154_ATTR_CHANNEL]); + bcn_ord = nla_get_u8(info->attrs[IEEE802154_ATTR_BCN_ORD]); + sf_ord = nla_get_u8(info->attrs[IEEE802154_ATTR_SF_ORD]); + pan_coord = nla_get_u8(info->attrs[IEEE802154_ATTR_PAN_COORD]); + blx = nla_get_u8(info->attrs[IEEE802154_ATTR_BAT_EXT]); + coord_realign = nla_get_u8(info->attrs[IEEE802154_ATTR_COORD_REALIGN]); + + if (info->attrs[IEEE802154_ATTR_PAGE]) + page = nla_get_u8(info->attrs[IEEE802154_ATTR_PAGE]); + else + page = 0; + + + if (addr.short_addr == IEEE802154_ADDR_BROADCAST) { + ieee802154_nl_start_confirm(dev, IEEE802154_NO_SHORT_ADDRESS); + dev_put(dev); + return -EINVAL; + } + + ret = ieee802154_mlme_ops(dev)->start_req(dev, &addr, channel, page, + bcn_ord, sf_ord, pan_coord, blx, coord_realign); + + dev_put(dev); + return ret; +} + +static int ieee802154_scan_req(struct sk_buff *skb, struct genl_info *info) +{ + struct net_device *dev; + int ret; + u8 type; + u32 channels; + u8 duration; + u8 page; + + if (!info->attrs[IEEE802154_ATTR_SCAN_TYPE] || + !info->attrs[IEEE802154_ATTR_CHANNELS] || + !info->attrs[IEEE802154_ATTR_DURATION]) + return -EINVAL; + + dev = ieee802154_nl_get_dev(info); + if (!dev) + return -ENODEV; + + type = nla_get_u8(info->attrs[IEEE802154_ATTR_SCAN_TYPE]); + channels = nla_get_u32(info->attrs[IEEE802154_ATTR_CHANNELS]); + duration = nla_get_u8(info->attrs[IEEE802154_ATTR_DURATION]); + + if (info->attrs[IEEE802154_ATTR_PAGE]) + page = nla_get_u8(info->attrs[IEEE802154_ATTR_PAGE]); + else + page = 0; + + + ret = ieee802154_mlme_ops(dev)->scan_req(dev, type, channels, page, + duration); + + dev_put(dev); + return ret; +} + +static int ieee802154_list_iface(struct sk_buff *skb, + struct genl_info *info) +{ + /* Request for interface name, index, type, IEEE address, + PAN Id, short address */ + struct sk_buff *msg; + struct net_device *dev = NULL; + int rc = -ENOBUFS; + + pr_debug("%s\n", __func__); + + dev = ieee802154_nl_get_dev(info); + if (!dev) + return -ENODEV; + + msg = nlmsg_new(NLMSG_GOODSIZE, GFP_KERNEL); + if (!msg) + goto out_dev; + + rc = ieee802154_nl_fill_iface(msg, info->snd_pid, info->snd_seq, + 0, dev); + if (rc < 0) + goto out_free; + + dev_put(dev); + + return genlmsg_reply(msg, info); +out_free: + nlmsg_free(msg); +out_dev: + dev_put(dev); + return rc; + +} + +static int ieee802154_dump_iface(struct sk_buff *skb, + struct netlink_callback *cb) +{ + struct net *net = sock_net(skb->sk); + struct net_device *dev; + int idx; + int s_idx = cb->args[0]; + + pr_debug("%s\n", __func__); + + idx = 0; + for_each_netdev(net, dev) { + if (idx < s_idx || (dev->type != ARPHRD_IEEE802154)) + goto cont; + + if (ieee802154_nl_fill_iface(skb, NETLINK_CB(cb->skb).pid, + cb->nlh->nlmsg_seq, NLM_F_MULTI, dev) < 0) + break; +cont: + idx++; + } + cb->args[0] = idx; + + return skb->len; +} + +static struct genl_ops ieee802154_coordinator_ops[] = { + IEEE802154_OP(IEEE802154_ASSOCIATE_REQ, ieee802154_associate_req), + IEEE802154_OP(IEEE802154_ASSOCIATE_RESP, ieee802154_associate_resp), + IEEE802154_OP(IEEE802154_DISASSOCIATE_REQ, ieee802154_disassociate_req), + IEEE802154_OP(IEEE802154_SCAN_REQ, ieee802154_scan_req), + IEEE802154_OP(IEEE802154_START_REQ, ieee802154_start_req), + IEEE802154_DUMP(IEEE802154_LIST_IFACE, ieee802154_list_iface, + ieee802154_dump_iface), +}; + +/* + * No need to unregister as family unregistration will do it. + */ +int nl802154_mac_register(void) +{ + int i; + int rc; + + rc = genl_register_mc_group(&nl802154_family, + &ieee802154_coord_mcgrp); + if (rc) + return rc; + + rc = genl_register_mc_group(&nl802154_family, + &ieee802154_beacon_mcgrp); + if (rc) + return rc; + + for (i = 0; i < ARRAY_SIZE(ieee802154_coordinator_ops); i++) { + rc = genl_register_ops(&nl802154_family, + &ieee802154_coordinator_ops[i]); + if (rc) + return rc; + } + + return 0; +} diff --git a/net/ieee802154/nl-phy.c b/net/ieee802154/nl-phy.c new file mode 100644 index 000000000000..199a2d9d12f9 --- /dev/null +++ b/net/ieee802154/nl-phy.c @@ -0,0 +1,344 @@ +/* + * Netlink inteface for IEEE 802.15.4 stack + * + * Copyright 2007, 2008 Siemens AG + * + * This program is free software; you can redistribute it and/or modify + * it under the terms of the GNU General Public License version 2 + * as published by the Free Software Foundation. + * + * This program is distributed in the hope that it will be useful, + * but WITHOUT ANY WARRANTY; without even the implied warranty of + * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the + * GNU General Public License for more details. + * + * You should have received a copy of the GNU General Public License along + * with this program; if not, write to the Free Software Foundation, Inc., + * 51 Franklin Street, Fifth Floor, Boston, MA 02110-1301 USA. + * + * Written by: + * Sergey Lapin <slapin@ossfans.org> + * Dmitry Eremin-Solenikov <dbaryshkov@gmail.com> + * Maxim Osipov <maxim.osipov@siemens.com> + */ + +#include <linux/kernel.h> +#include <net/netlink.h> +#include <net/genetlink.h> +#include <net/wpan-phy.h> +#include <net/af_ieee802154.h> +#include <net/ieee802154_netdev.h> +#include <net/rtnetlink.h> /* for rtnl_{un,}lock */ +#include <linux/nl802154.h> + +#include "ieee802154.h" + +static int ieee802154_nl_fill_phy(struct sk_buff *msg, u32 pid, + u32 seq, int flags, struct wpan_phy *phy) +{ + void *hdr; + int i, pages = 0; + uint32_t *buf = kzalloc(32 * sizeof(uint32_t), GFP_KERNEL); + + pr_debug("%s\n", __func__); + + if (!buf) + goto out; + + hdr = genlmsg_put(msg, 0, seq, &nl802154_family, flags, + IEEE802154_LIST_PHY); + if (!hdr) + goto out; + + mutex_lock(&phy->pib_lock); + NLA_PUT_STRING(msg, IEEE802154_ATTR_PHY_NAME, wpan_phy_name(phy)); + + NLA_PUT_U8(msg, IEEE802154_ATTR_PAGE, phy->current_page); + NLA_PUT_U8(msg, IEEE802154_ATTR_CHANNEL, phy->current_channel); + for (i = 0; i < 32; i++) { + if (phy->channels_supported[i]) + buf[pages++] = phy->channels_supported[i] | (i << 27); + } + if (pages) + NLA_PUT(msg, IEEE802154_ATTR_CHANNEL_PAGE_LIST, + pages * sizeof(uint32_t), buf); + + mutex_unlock(&phy->pib_lock); + return genlmsg_end(msg, hdr); + +nla_put_failure: + mutex_unlock(&phy->pib_lock); + genlmsg_cancel(msg, hdr); +out: + kfree(buf); + return -EMSGSIZE; +} + +static int ieee802154_list_phy(struct sk_buff *skb, + struct genl_info *info) +{ + /* Request for interface name, index, type, IEEE address, + PAN Id, short address */ + struct sk_buff *msg; + struct wpan_phy *phy; + const char *name; + int rc = -ENOBUFS; + + pr_debug("%s\n", __func__); + + if (!info->attrs[IEEE802154_ATTR_PHY_NAME]) + return -EINVAL; + + name = nla_data(info->attrs[IEEE802154_ATTR_PHY_NAME]); + if (name[nla_len(info->attrs[IEEE802154_ATTR_PHY_NAME]) - 1] != '\0') + return -EINVAL; /* phy name should be null-terminated */ + + + phy = wpan_phy_find(name); + if (!phy) + return -ENODEV; + + msg = nlmsg_new(NLMSG_GOODSIZE, GFP_KERNEL); + if (!msg) + goto out_dev; + + rc = ieee802154_nl_fill_phy(msg, info->snd_pid, info->snd_seq, + 0, phy); + if (rc < 0) + goto out_free; + + wpan_phy_put(phy); + + return genlmsg_reply(msg, info); +out_free: + nlmsg_free(msg); +out_dev: + wpan_phy_put(phy); + return rc; + +} + +struct dump_phy_data { + struct sk_buff *skb; + struct netlink_callback *cb; + int idx, s_idx; +}; + +static int ieee802154_dump_phy_iter(struct wpan_phy *phy, void *_data) +{ + int rc; + struct dump_phy_data *data = _data; + + pr_debug("%s\n", __func__); + + if (data->idx++ < data->s_idx) + return 0; + + rc = ieee802154_nl_fill_phy(data->skb, + NETLINK_CB(data->cb->skb).pid, + data->cb->nlh->nlmsg_seq, + NLM_F_MULTI, + phy); + + if (rc < 0) { + data->idx--; + return rc; + } + + return 0; +} + +static int ieee802154_dump_phy(struct sk_buff *skb, + struct netlink_callback *cb) +{ + struct dump_phy_data data = { + .cb = cb, + .skb = skb, + .s_idx = cb->args[0], + .idx = 0, + }; + + pr_debug("%s\n", __func__); + + wpan_phy_for_each(ieee802154_dump_phy_iter, &data); + + cb->args[0] = data.idx; + + return skb->len; +} + +static int ieee802154_add_iface(struct sk_buff *skb, + struct genl_info *info) +{ + struct sk_buff *msg; + struct wpan_phy *phy; + const char *name; + const char *devname; + int rc = -ENOBUFS; + struct net_device *dev; + + pr_debug("%s\n", __func__); + + if (!info->attrs[IEEE802154_ATTR_PHY_NAME]) + return -EINVAL; + + name = nla_data(info->attrs[IEEE802154_ATTR_PHY_NAME]); + if (name[nla_len(info->attrs[IEEE802154_ATTR_PHY_NAME]) - 1] != '\0') + return -EINVAL; /* phy name should be null-terminated */ + + if (info->attrs[IEEE802154_ATTR_DEV_NAME]) { + devname = nla_data(info->attrs[IEEE802154_ATTR_DEV_NAME]); + if (devname[nla_len(info->attrs[IEEE802154_ATTR_DEV_NAME]) - 1] + != '\0') + return -EINVAL; /* phy name should be null-terminated */ + } else { + devname = "wpan%d"; + } + + if (strlen(devname) >= IFNAMSIZ) + return -ENAMETOOLONG; + + phy = wpan_phy_find(name); + if (!phy) + return -ENODEV; + + msg = ieee802154_nl_new_reply(info, 0, IEEE802154_ADD_IFACE); + if (!msg) + goto out_dev; + + if (!phy->add_iface) { + rc = -EINVAL; + goto nla_put_failure; + } + + dev = phy->add_iface(phy, devname); + if (IS_ERR(dev)) { + rc = PTR_ERR(dev); + goto nla_put_failure; + } + + NLA_PUT_STRING(msg, IEEE802154_ATTR_PHY_NAME, wpan_phy_name(phy)); + NLA_PUT_STRING(msg, IEEE802154_ATTR_DEV_NAME, dev->name); + + dev_put(dev); + + wpan_phy_put(phy); + + return ieee802154_nl_reply(msg, info); + +nla_put_failure: + nlmsg_free(msg); +out_dev: + wpan_phy_put(phy); + return rc; +} + +static int ieee802154_del_iface(struct sk_buff *skb, + struct genl_info *info) +{ + struct sk_buff *msg; + struct wpan_phy *phy; + const char *name; + int rc; + struct net_device *dev; + + pr_debug("%s\n", __func__); + + if (!info->attrs[IEEE802154_ATTR_DEV_NAME]) + return -EINVAL; + + name = nla_data(info->attrs[IEEE802154_ATTR_DEV_NAME]); + if (name[nla_len(info->attrs[IEEE802154_ATTR_DEV_NAME]) - 1] != '\0') + return -EINVAL; /* name should be null-terminated */ + + dev = dev_get_by_name(genl_info_net(info), name); + if (!dev) + return -ENODEV; + + phy = ieee802154_mlme_ops(dev)->get_phy(dev); + BUG_ON(!phy); + + rc = -EINVAL; + /* phy name is optional, but should be checked if it's given */ + if (info->attrs[IEEE802154_ATTR_PHY_NAME]) { + struct wpan_phy *phy2; + + const char *pname = + nla_data(info->attrs[IEEE802154_ATTR_PHY_NAME]); + if (pname[nla_len(info->attrs[IEEE802154_ATTR_PHY_NAME]) - 1] + != '\0') + /* name should be null-terminated */ + goto out_dev; + + phy2 = wpan_phy_find(pname); + if (!phy2) + goto out_dev; + + if (phy != phy2) { + wpan_phy_put(phy2); + goto out_dev; + } + } + + rc = -ENOBUFS; + + msg = ieee802154_nl_new_reply(info, 0, IEEE802154_DEL_IFACE); + if (!msg) + goto out_dev; + + if (!phy->del_iface) { + rc = -EINVAL; + goto nla_put_failure; + } + + rtnl_lock(); + phy->del_iface(phy, dev); + + /* We don't have device anymore */ + dev_put(dev); + dev = NULL; + + rtnl_unlock(); + + + NLA_PUT_STRING(msg, IEEE802154_ATTR_PHY_NAME, wpan_phy_name(phy)); + NLA_PUT_STRING(msg, IEEE802154_ATTR_DEV_NAME, name); + + wpan_phy_put(phy); + + return ieee802154_nl_reply(msg, info); + +nla_put_failure: + nlmsg_free(msg); +out_dev: + wpan_phy_put(phy); + if (dev) + dev_put(dev); + + return rc; +} + +static struct genl_ops ieee802154_phy_ops[] = { + IEEE802154_DUMP(IEEE802154_LIST_PHY, ieee802154_list_phy, + ieee802154_dump_phy), + IEEE802154_OP(IEEE802154_ADD_IFACE, ieee802154_add_iface), + IEEE802154_OP(IEEE802154_DEL_IFACE, ieee802154_del_iface), +}; + +/* + * No need to unregister as family unregistration will do it. + */ +int nl802154_phy_register(void) +{ + int i; + int rc; + + for (i = 0; i < ARRAY_SIZE(ieee802154_phy_ops); i++) { + rc = genl_register_ops(&nl802154_family, + &ieee802154_phy_ops[i]); + if (rc) + return rc; + } + + return 0; +} diff --git a/net/ieee802154/nl_policy.c b/net/ieee802154/nl_policy.c index 2363ebee02e7..6adda4d46f95 100644 --- a/net/ieee802154/nl_policy.c +++ b/net/ieee802154/nl_policy.c @@ -27,6 +27,7 @@ const struct nla_policy ieee802154_policy[IEEE802154_ATTR_MAX + 1] = { [IEEE802154_ATTR_DEV_NAME] = { .type = NLA_STRING, }, [IEEE802154_ATTR_DEV_INDEX] = { .type = NLA_U32, }, + [IEEE802154_ATTR_PHY_NAME] = { .type = NLA_STRING, }, [IEEE802154_ATTR_STATUS] = { .type = NLA_U8, }, [IEEE802154_ATTR_SHORT_ADDR] = { .type = NLA_U16, }, @@ -50,5 +51,6 @@ const struct nla_policy ieee802154_policy[IEEE802154_ATTR_MAX + 1] = { [IEEE802154_ATTR_CHANNELS] = { .type = NLA_U32, }, [IEEE802154_ATTR_DURATION] = { .type = NLA_U8, }, [IEEE802154_ATTR_ED_LIST] = { .len = 27 }, + [IEEE802154_ATTR_CHANNEL_PAGE_LIST] = { .len = 32 * 4, }, }; diff --git a/net/ieee802154/raw.c b/net/ieee802154/raw.c index 30e74eee07d6..9c9b85c00033 100644 --- a/net/ieee802154/raw.c +++ b/net/ieee802154/raw.c @@ -191,7 +191,7 @@ static int raw_recvmsg(struct kiocb *iocb, struct sock *sk, struct msghdr *msg, if (err) goto done; - sock_recv_timestamp(msg, sk, skb); + sock_recv_ts_and_drops(msg, sk, skb); if (flags & MSG_TRUNC) copied = skb->len; @@ -206,7 +206,6 @@ out: static int raw_rcv_skb(struct sock *sk, struct sk_buff *skb) { if (sock_queue_rcv_skb(sk, skb) < 0) { - atomic_inc(&sk->sk_drops); kfree_skb(skb); return NET_RX_DROP; } diff --git a/net/ieee802154/wpan-class.c b/net/ieee802154/wpan-class.c index f306604da67a..268691256a6d 100644 --- a/net/ieee802154/wpan-class.c +++ b/net/ieee802154/wpan-class.c @@ -22,6 +22,8 @@ #include <net/wpan-phy.h> +#include "ieee802154.h" + #define MASTER_SHOW_COMPLEX(name, format_string, args...) \ static ssize_t name ## _show(struct device *dev, \ struct device_attribute *attr, char *buf) \ @@ -30,7 +32,7 @@ static ssize_t name ## _show(struct device *dev, \ int ret; \ \ mutex_lock(&phy->pib_lock); \ - ret = sprintf(buf, format_string "\n", args); \ + ret = snprintf(buf, PAGE_SIZE, format_string "\n", args); \ mutex_unlock(&phy->pib_lock); \ return ret; \ } @@ -40,12 +42,30 @@ static ssize_t name ## _show(struct device *dev, \ MASTER_SHOW(current_channel, "%d"); MASTER_SHOW(current_page, "%d"); -MASTER_SHOW(channels_supported, "%#x"); MASTER_SHOW_COMPLEX(transmit_power, "%d +- %d dB", ((signed char) (phy->transmit_power << 2)) >> 2, (phy->transmit_power >> 6) ? (phy->transmit_power >> 6) * 3 : 1 ); MASTER_SHOW(cca_mode, "%d"); +static ssize_t channels_supported_show(struct device *dev, + struct device_attribute *attr, char *buf) +{ + struct wpan_phy *phy = container_of(dev, struct wpan_phy, dev); + int ret; + int i, len = 0; + + mutex_lock(&phy->pib_lock); + for (i = 0; i < 32; i++) { + ret = snprintf(buf + len, PAGE_SIZE - len, + "%#09x\n", phy->channels_supported[i]); + if (ret < 0) + break; + len += ret; + } + mutex_unlock(&phy->pib_lock); + return len; +} + static struct device_attribute pmib_attrs[] = { __ATTR_RO(current_channel), __ATTR_RO(current_page), @@ -91,6 +111,31 @@ struct wpan_phy *wpan_phy_find(const char *str) } EXPORT_SYMBOL(wpan_phy_find); +struct wpan_phy_iter_data { + int (*fn)(struct wpan_phy *phy, void *data); + void *data; +}; + +static int wpan_phy_iter(struct device *dev, void *_data) +{ + struct wpan_phy_iter_data *wpid = _data; + struct wpan_phy *phy = container_of(dev, struct wpan_phy, dev); + return wpid->fn(phy, wpid->data); +} + +int wpan_phy_for_each(int (*fn)(struct wpan_phy *phy, void *data), + void *data) +{ + struct wpan_phy_iter_data wpid = { + .fn = fn, + .data = data, + }; + + return class_for_each_device(&wpan_phy_class, NULL, + &wpid, wpan_phy_iter); +} +EXPORT_SYMBOL(wpan_phy_for_each); + static int wpan_phy_idx_valid(int idx) { return idx >= 0; @@ -118,14 +163,15 @@ struct wpan_phy *wpan_phy_alloc(size_t priv_size) phy->dev.class = &wpan_phy_class; + phy->current_channel = -1; /* not initialised */ + phy->current_page = 0; /* for compatibility */ + return phy; } EXPORT_SYMBOL(wpan_phy_alloc); -int wpan_phy_register(struct device *parent, struct wpan_phy *phy) +int wpan_phy_register(struct wpan_phy *phy) { - phy->dev.parent = parent; - return device_add(&phy->dev); } EXPORT_SYMBOL(wpan_phy_register); @@ -144,16 +190,31 @@ EXPORT_SYMBOL(wpan_phy_free); static int __init wpan_phy_class_init(void) { - return class_register(&wpan_phy_class); + int rc; + rc = class_register(&wpan_phy_class); + if (rc) + goto err; + + rc = ieee802154_nl_init(); + if (rc) + goto err_nl; + + return 0; +err_nl: + class_unregister(&wpan_phy_class); +err: + return rc; } subsys_initcall(wpan_phy_class_init); static void __exit wpan_phy_class_exit(void) { + ieee802154_nl_exit(); class_unregister(&wpan_phy_class); } module_exit(wpan_phy_class_exit); -MODULE_DESCRIPTION("IEEE 802.15.4 device class"); MODULE_LICENSE("GPL v2"); +MODULE_DESCRIPTION("IEEE 802.15.4 configuration interface"); +MODULE_AUTHOR("Dmitry Eremin-Solenikov"); diff --git a/net/ipv4/af_inet.c b/net/ipv4/af_inet.c index 57737b8d1711..7d12c6a9b19b 100644 --- a/net/ipv4/af_inet.c +++ b/net/ipv4/af_inet.c @@ -174,12 +174,12 @@ static int inet_autobind(struct sock *sk) /* We may need to bind the socket. */ lock_sock(sk); inet = inet_sk(sk); - if (!inet->num) { + if (!inet->inet_num) { if (sk->sk_prot->get_port(sk, 0)) { release_sock(sk); return -EAGAIN; } - inet->sport = htons(inet->num); + inet->inet_sport = htons(inet->inet_num); } release_sock(sk); return 0; @@ -262,7 +262,8 @@ static inline int inet_netns_ok(struct net *net, int protocol) * Create an inet socket. */ -static int inet_create(struct net *net, struct socket *sock, int protocol) +static int inet_create(struct net *net, struct socket *sock, int protocol, + int kern) { struct sock *sk; struct inet_protosw *answer; @@ -325,7 +326,7 @@ lookup_protocol: } err = -EPERM; - if (answer->capability > 0 && !capable(answer->capability)) + if (sock->type == SOCK_RAW && !kern && !capable(CAP_NET_RAW)) goto out_rcu_unlock; err = -EAFNOSUPPORT; @@ -354,7 +355,7 @@ lookup_protocol: inet->is_icsk = (INET_PROTOSW_ICSK & answer_flags) != 0; if (SOCK_RAW == sock->type) { - inet->num = protocol; + inet->inet_num = protocol; if (IPPROTO_RAW == protocol) inet->hdrincl = 1; } @@ -364,7 +365,7 @@ lookup_protocol: else inet->pmtudisc = IP_PMTUDISC_WANT; - inet->id = 0; + inet->inet_id = 0; sock_init_data(sock, sk); @@ -381,13 +382,13 @@ lookup_protocol: sk_refcnt_debug_inc(sk); - if (inet->num) { + if (inet->inet_num) { /* It assumes that any protocol which allows * the user to assign a number at socket * creation time automatically * shares. */ - inet->sport = htons(inet->num); + inet->inet_sport = htons(inet->inet_num); /* Add to protocol hash chains. */ sk->sk_prot->hash(sk); } @@ -494,27 +495,27 @@ int inet_bind(struct socket *sock, struct sockaddr *uaddr, int addr_len) /* Check these errors (active socket, double bind). */ err = -EINVAL; - if (sk->sk_state != TCP_CLOSE || inet->num) + if (sk->sk_state != TCP_CLOSE || inet->inet_num) goto out_release_sock; - inet->rcv_saddr = inet->saddr = addr->sin_addr.s_addr; + inet->inet_rcv_saddr = inet->inet_saddr = addr->sin_addr.s_addr; if (chk_addr_ret == RTN_MULTICAST || chk_addr_ret == RTN_BROADCAST) - inet->saddr = 0; /* Use device */ + inet->inet_saddr = 0; /* Use device */ /* Make sure we are allowed to bind here. */ if (sk->sk_prot->get_port(sk, snum)) { - inet->saddr = inet->rcv_saddr = 0; + inet->inet_saddr = inet->inet_rcv_saddr = 0; err = -EADDRINUSE; goto out_release_sock; } - if (inet->rcv_saddr) + if (inet->inet_rcv_saddr) sk->sk_userlocks |= SOCK_BINDADDR_LOCK; if (snum) sk->sk_userlocks |= SOCK_BINDPORT_LOCK; - inet->sport = htons(inet->num); - inet->daddr = 0; - inet->dport = 0; + inet->inet_sport = htons(inet->inet_num); + inet->inet_daddr = 0; + inet->inet_dport = 0; sk_dst_reset(sk); err = 0; out_release_sock: @@ -532,7 +533,7 @@ int inet_dgram_connect(struct socket *sock, struct sockaddr * uaddr, if (uaddr->sa_family == AF_UNSPEC) return sk->sk_prot->disconnect(sk, flags); - if (!inet_sk(sk)->num && inet_autobind(sk)) + if (!inet_sk(sk)->inet_num && inet_autobind(sk)) return -EAGAIN; return sk->sk_prot->connect(sk, (struct sockaddr *)uaddr, addr_len); } @@ -685,21 +686,21 @@ int inet_getname(struct socket *sock, struct sockaddr *uaddr, { struct sock *sk = sock->sk; struct inet_sock *inet = inet_sk(sk); - struct sockaddr_in *sin = (struct sockaddr_in *)uaddr; + DECLARE_SOCKADDR(struct sockaddr_in *, sin, uaddr); sin->sin_family = AF_INET; if (peer) { - if (!inet->dport || + if (!inet->inet_dport || (((1 << sk->sk_state) & (TCPF_CLOSE | TCPF_SYN_SENT)) && peer == 1)) return -ENOTCONN; - sin->sin_port = inet->dport; - sin->sin_addr.s_addr = inet->daddr; + sin->sin_port = inet->inet_dport; + sin->sin_addr.s_addr = inet->inet_daddr; } else { - __be32 addr = inet->rcv_saddr; + __be32 addr = inet->inet_rcv_saddr; if (!addr) - addr = inet->saddr; - sin->sin_port = inet->sport; + addr = inet->inet_saddr; + sin->sin_port = inet->inet_sport; sin->sin_addr.s_addr = addr; } memset(sin->sin_zero, 0, sizeof(sin->sin_zero)); @@ -714,7 +715,7 @@ int inet_sendmsg(struct kiocb *iocb, struct socket *sock, struct msghdr *msg, struct sock *sk = sock->sk; /* We may need to bind the socket. */ - if (!inet_sk(sk)->num && inet_autobind(sk)) + if (!inet_sk(sk)->inet_num && inet_autobind(sk)) return -EAGAIN; return sk->sk_prot->sendmsg(iocb, sk, msg, size); @@ -728,7 +729,7 @@ static ssize_t inet_sendpage(struct socket *sock, struct page *page, int offset, struct sock *sk = sock->sk; /* We may need to bind the socket. */ - if (!inet_sk(sk)->num && inet_autobind(sk)) + if (!inet_sk(sk)->inet_num && inet_autobind(sk)) return -EAGAIN; if (sk->sk_prot->sendpage) @@ -931,7 +932,7 @@ static const struct proto_ops inet_sockraw_ops = { #endif }; -static struct net_proto_family inet_family_ops = { +static const struct net_proto_family inet_family_ops = { .family = PF_INET, .create = inet_create, .owner = THIS_MODULE, @@ -947,7 +948,6 @@ static struct inet_protosw inetsw_array[] = .protocol = IPPROTO_TCP, .prot = &tcp_prot, .ops = &inet_stream_ops, - .capability = -1, .no_check = 0, .flags = INET_PROTOSW_PERMANENT | INET_PROTOSW_ICSK, @@ -958,7 +958,6 @@ static struct inet_protosw inetsw_array[] = .protocol = IPPROTO_UDP, .prot = &udp_prot, .ops = &inet_dgram_ops, - .capability = -1, .no_check = UDP_CSUM_DEFAULT, .flags = INET_PROTOSW_PERMANENT, }, @@ -969,7 +968,6 @@ static struct inet_protosw inetsw_array[] = .protocol = IPPROTO_IP, /* wild card */ .prot = &raw_prot, .ops = &inet_sockraw_ops, - .capability = CAP_NET_RAW, .no_check = UDP_CSUM_DEFAULT, .flags = INET_PROTOSW_REUSE, } @@ -1059,9 +1057,9 @@ static int inet_sk_reselect_saddr(struct sock *sk) struct inet_sock *inet = inet_sk(sk); int err; struct rtable *rt; - __be32 old_saddr = inet->saddr; + __be32 old_saddr = inet->inet_saddr; __be32 new_saddr; - __be32 daddr = inet->daddr; + __be32 daddr = inet->inet_daddr; if (inet->opt && inet->opt->srr) daddr = inet->opt->faddr; @@ -1071,7 +1069,7 @@ static int inet_sk_reselect_saddr(struct sock *sk) RT_CONN_FLAGS(sk), sk->sk_bound_dev_if, sk->sk_protocol, - inet->sport, inet->dport, sk, 0); + inet->inet_sport, inet->inet_dport, sk, 0); if (err) return err; @@ -1087,7 +1085,7 @@ static int inet_sk_reselect_saddr(struct sock *sk) __func__, &old_saddr, &new_saddr); } - inet->saddr = inet->rcv_saddr = new_saddr; + inet->inet_saddr = inet->inet_rcv_saddr = new_saddr; /* * XXX The only one ugly spot where we need to @@ -1113,7 +1111,7 @@ int inet_sk_rebuild_header(struct sock *sk) return 0; /* Reroute. */ - daddr = inet->daddr; + daddr = inet->inet_daddr; if (inet->opt && inet->opt->srr) daddr = inet->opt->faddr; { @@ -1123,7 +1121,7 @@ int inet_sk_rebuild_header(struct sock *sk) .nl_u = { .ip4_u = { .daddr = daddr, - .saddr = inet->saddr, + .saddr = inet->inet_saddr, .tos = RT_CONN_FLAGS(sk), }, }, @@ -1131,8 +1129,8 @@ int inet_sk_rebuild_header(struct sock *sk) .flags = inet_sk_flowi_flags(sk), .uli_u = { .ports = { - .sport = inet->sport, - .dport = inet->dport, + .sport = inet->inet_sport, + .dport = inet->inet_dport, }, }, }; diff --git a/net/ipv4/ah4.c b/net/ipv4/ah4.c index 5c662703eb1e..7ed3e4ae93ae 100644 --- a/net/ipv4/ah4.c +++ b/net/ipv4/ah4.c @@ -1,3 +1,4 @@ +#include <crypto/hash.h> #include <linux/err.h> #include <linux/module.h> #include <net/ip.h> @@ -5,10 +6,67 @@ #include <net/ah.h> #include <linux/crypto.h> #include <linux/pfkeyv2.h> -#include <linux/spinlock.h> +#include <linux/scatterlist.h> #include <net/icmp.h> #include <net/protocol.h> +struct ah_skb_cb { + struct xfrm_skb_cb xfrm; + void *tmp; +}; + +#define AH_SKB_CB(__skb) ((struct ah_skb_cb *)&((__skb)->cb[0])) + +static void *ah_alloc_tmp(struct crypto_ahash *ahash, int nfrags, + unsigned int size) +{ + unsigned int len; + + len = size + crypto_ahash_digestsize(ahash) + + (crypto_ahash_alignmask(ahash) & + ~(crypto_tfm_ctx_alignment() - 1)); + + len = ALIGN(len, crypto_tfm_ctx_alignment()); + + len += sizeof(struct ahash_request) + crypto_ahash_reqsize(ahash); + len = ALIGN(len, __alignof__(struct scatterlist)); + + len += sizeof(struct scatterlist) * nfrags; + + return kmalloc(len, GFP_ATOMIC); +} + +static inline u8 *ah_tmp_auth(void *tmp, unsigned int offset) +{ + return tmp + offset; +} + +static inline u8 *ah_tmp_icv(struct crypto_ahash *ahash, void *tmp, + unsigned int offset) +{ + return PTR_ALIGN((u8 *)tmp + offset, crypto_ahash_alignmask(ahash) + 1); +} + +static inline struct ahash_request *ah_tmp_req(struct crypto_ahash *ahash, + u8 *icv) +{ + struct ahash_request *req; + + req = (void *)PTR_ALIGN(icv + crypto_ahash_digestsize(ahash), + crypto_tfm_ctx_alignment()); + + ahash_request_set_tfm(req, ahash); + + return req; +} + +static inline struct scatterlist *ah_req_sg(struct crypto_ahash *ahash, + struct ahash_request *req) +{ + return (void *)ALIGN((unsigned long)(req + 1) + + crypto_ahash_reqsize(ahash), + __alignof__(struct scatterlist)); +} /* Clear mutable options and find final destination to substitute * into IP header for icv calculation. Options are already checked @@ -54,20 +112,72 @@ static int ip_clear_mutable_options(struct iphdr *iph, __be32 *daddr) return 0; } +static void ah_output_done(struct crypto_async_request *base, int err) +{ + u8 *icv; + struct iphdr *iph; + struct sk_buff *skb = base->data; + struct xfrm_state *x = skb_dst(skb)->xfrm; + struct ah_data *ahp = x->data; + struct iphdr *top_iph = ip_hdr(skb); + struct ip_auth_hdr *ah = ip_auth_hdr(skb); + int ihl = ip_hdrlen(skb); + + iph = AH_SKB_CB(skb)->tmp; + icv = ah_tmp_icv(ahp->ahash, iph, ihl); + memcpy(ah->auth_data, icv, ahp->icv_trunc_len); + + top_iph->tos = iph->tos; + top_iph->ttl = iph->ttl; + top_iph->frag_off = iph->frag_off; + if (top_iph->ihl != 5) { + top_iph->daddr = iph->daddr; + memcpy(top_iph+1, iph+1, top_iph->ihl*4 - sizeof(struct iphdr)); + } + + err = ah->nexthdr; + + kfree(AH_SKB_CB(skb)->tmp); + xfrm_output_resume(skb, err); +} + static int ah_output(struct xfrm_state *x, struct sk_buff *skb) { int err; + int nfrags; + int ihl; + u8 *icv; + struct sk_buff *trailer; + struct crypto_ahash *ahash; + struct ahash_request *req; + struct scatterlist *sg; struct iphdr *iph, *top_iph; struct ip_auth_hdr *ah; struct ah_data *ahp; - union { - struct iphdr iph; - char buf[60]; - } tmp_iph; + + ahp = x->data; + ahash = ahp->ahash; + + if ((err = skb_cow_data(skb, 0, &trailer)) < 0) + goto out; + nfrags = err; skb_push(skb, -skb_network_offset(skb)); + ah = ip_auth_hdr(skb); + ihl = ip_hdrlen(skb); + + err = -ENOMEM; + iph = ah_alloc_tmp(ahash, nfrags, ihl); + if (!iph) + goto out; + + icv = ah_tmp_icv(ahash, iph, ihl); + req = ah_tmp_req(ahash, icv); + sg = ah_req_sg(ahash, req); + + memset(ah->auth_data, 0, ahp->icv_trunc_len); + top_iph = ip_hdr(skb); - iph = &tmp_iph.iph; iph->tos = top_iph->tos; iph->ttl = top_iph->ttl; @@ -78,10 +188,9 @@ static int ah_output(struct xfrm_state *x, struct sk_buff *skb) memcpy(iph+1, top_iph+1, top_iph->ihl*4 - sizeof(struct iphdr)); err = ip_clear_mutable_options(top_iph, &top_iph->daddr); if (err) - goto error; + goto out_free; } - ah = ip_auth_hdr(skb); ah->nexthdr = *skb_mac_header(skb); *skb_mac_header(skb) = IPPROTO_AH; @@ -91,20 +200,31 @@ static int ah_output(struct xfrm_state *x, struct sk_buff *skb) top_iph->ttl = 0; top_iph->check = 0; - ahp = x->data; ah->hdrlen = (XFRM_ALIGN8(sizeof(*ah) + ahp->icv_trunc_len) >> 2) - 2; ah->reserved = 0; ah->spi = x->id.spi; ah->seq_no = htonl(XFRM_SKB_CB(skb)->seq.output); - spin_lock_bh(&x->lock); - err = ah_mac_digest(ahp, skb, ah->auth_data); - memcpy(ah->auth_data, ahp->work_icv, ahp->icv_trunc_len); - spin_unlock_bh(&x->lock); + sg_init_table(sg, nfrags); + skb_to_sgvec(skb, sg, 0, skb->len); - if (err) - goto error; + ahash_request_set_crypt(req, sg, icv, skb->len); + ahash_request_set_callback(req, 0, ah_output_done, skb); + + AH_SKB_CB(skb)->tmp = iph; + + err = crypto_ahash_digest(req); + if (err) { + if (err == -EINPROGRESS) + goto out; + + if (err == -EBUSY) + err = NET_XMIT_DROP; + goto out_free; + } + + memcpy(ah->auth_data, icv, ahp->icv_trunc_len); top_iph->tos = iph->tos; top_iph->ttl = iph->ttl; @@ -114,28 +234,67 @@ static int ah_output(struct xfrm_state *x, struct sk_buff *skb) memcpy(top_iph+1, iph+1, top_iph->ihl*4 - sizeof(struct iphdr)); } - err = 0; - -error: +out_free: + kfree(iph); +out: return err; } +static void ah_input_done(struct crypto_async_request *base, int err) +{ + u8 *auth_data; + u8 *icv; + struct iphdr *work_iph; + struct sk_buff *skb = base->data; + struct xfrm_state *x = xfrm_input_state(skb); + struct ah_data *ahp = x->data; + struct ip_auth_hdr *ah = ip_auth_hdr(skb); + int ihl = ip_hdrlen(skb); + int ah_hlen = (ah->hdrlen + 2) << 2; + + work_iph = AH_SKB_CB(skb)->tmp; + auth_data = ah_tmp_auth(work_iph, ihl); + icv = ah_tmp_icv(ahp->ahash, auth_data, ahp->icv_trunc_len); + + err = memcmp(icv, auth_data, ahp->icv_trunc_len) ? -EBADMSG: 0; + if (err) + goto out; + + skb->network_header += ah_hlen; + memcpy(skb_network_header(skb), work_iph, ihl); + __skb_pull(skb, ah_hlen + ihl); + skb_set_transport_header(skb, -ihl); + + err = ah->nexthdr; +out: + kfree(AH_SKB_CB(skb)->tmp); + xfrm_input_resume(skb, err); +} + static int ah_input(struct xfrm_state *x, struct sk_buff *skb) { int ah_hlen; int ihl; int nexthdr; - int err = -EINVAL; - struct iphdr *iph; + int nfrags; + u8 *auth_data; + u8 *icv; + struct sk_buff *trailer; + struct crypto_ahash *ahash; + struct ahash_request *req; + struct scatterlist *sg; + struct iphdr *iph, *work_iph; struct ip_auth_hdr *ah; struct ah_data *ahp; - char work_buf[60]; + int err = -ENOMEM; if (!pskb_may_pull(skb, sizeof(*ah))) goto out; ah = (struct ip_auth_hdr *)skb->data; ahp = x->data; + ahash = ahp->ahash; + nexthdr = ah->nexthdr; ah_hlen = (ah->hdrlen + 2) << 2; @@ -156,9 +315,24 @@ static int ah_input(struct xfrm_state *x, struct sk_buff *skb) ah = (struct ip_auth_hdr *)skb->data; iph = ip_hdr(skb); + ihl = ip_hdrlen(skb); + + if ((err = skb_cow_data(skb, 0, &trailer)) < 0) + goto out; + nfrags = err; + + work_iph = ah_alloc_tmp(ahash, nfrags, ihl + ahp->icv_trunc_len); + if (!work_iph) + goto out; + + auth_data = ah_tmp_auth(work_iph, ihl); + icv = ah_tmp_icv(ahash, auth_data, ahp->icv_trunc_len); + req = ah_tmp_req(ahash, icv); + sg = ah_req_sg(ahash, req); - ihl = skb->data - skb_network_header(skb); - memcpy(work_buf, iph, ihl); + memcpy(work_iph, iph, ihl); + memcpy(auth_data, ah->auth_data, ahp->icv_trunc_len); + memset(ah->auth_data, 0, ahp->icv_trunc_len); iph->ttl = 0; iph->tos = 0; @@ -166,35 +340,44 @@ static int ah_input(struct xfrm_state *x, struct sk_buff *skb) iph->check = 0; if (ihl > sizeof(*iph)) { __be32 dummy; - if (ip_clear_mutable_options(iph, &dummy)) - goto out; + err = ip_clear_mutable_options(iph, &dummy); + if (err) + goto out_free; } - spin_lock(&x->lock); - { - u8 auth_data[MAX_AH_AUTH_LEN]; + skb_push(skb, ihl); - memcpy(auth_data, ah->auth_data, ahp->icv_trunc_len); - skb_push(skb, ihl); - err = ah_mac_digest(ahp, skb, ah->auth_data); - if (err) - goto unlock; - if (memcmp(ahp->work_icv, auth_data, ahp->icv_trunc_len)) - err = -EBADMSG; + sg_init_table(sg, nfrags); + skb_to_sgvec(skb, sg, 0, skb->len); + + ahash_request_set_crypt(req, sg, icv, skb->len); + ahash_request_set_callback(req, 0, ah_input_done, skb); + + AH_SKB_CB(skb)->tmp = work_iph; + + err = crypto_ahash_digest(req); + if (err) { + if (err == -EINPROGRESS) + goto out; + + if (err == -EBUSY) + err = NET_XMIT_DROP; + goto out_free; } -unlock: - spin_unlock(&x->lock); + err = memcmp(icv, auth_data, ahp->icv_trunc_len) ? -EBADMSG: 0; if (err) - goto out; + goto out_free; skb->network_header += ah_hlen; - memcpy(skb_network_header(skb), work_buf, ihl); - skb->transport_header = skb->network_header; + memcpy(skb_network_header(skb), work_iph, ihl); __skb_pull(skb, ah_hlen + ihl); + skb_set_transport_header(skb, -ihl); - return nexthdr; + err = nexthdr; +out_free: + kfree (work_iph); out: return err; } @@ -222,7 +405,7 @@ static int ah_init_state(struct xfrm_state *x) { struct ah_data *ahp = NULL; struct xfrm_algo_desc *aalg_desc; - struct crypto_hash *tfm; + struct crypto_ahash *ahash; if (!x->aalg) goto error; @@ -231,44 +414,40 @@ static int ah_init_state(struct xfrm_state *x) goto error; ahp = kzalloc(sizeof(*ahp), GFP_KERNEL); - if (ahp == NULL) + if (!ahp) return -ENOMEM; - tfm = crypto_alloc_hash(x->aalg->alg_name, 0, CRYPTO_ALG_ASYNC); - if (IS_ERR(tfm)) + ahash = crypto_alloc_ahash(x->aalg->alg_name, 0, 0); + if (IS_ERR(ahash)) goto error; - ahp->tfm = tfm; - if (crypto_hash_setkey(tfm, x->aalg->alg_key, - (x->aalg->alg_key_len + 7) / 8)) + ahp->ahash = ahash; + if (crypto_ahash_setkey(ahash, x->aalg->alg_key, + (x->aalg->alg_key_len + 7) / 8)) goto error; /* * Lookup the algorithm description maintained by xfrm_algo, * verify crypto transform properties, and store information * we need for AH processing. This lookup cannot fail here - * after a successful crypto_alloc_hash(). + * after a successful crypto_alloc_ahash(). */ aalg_desc = xfrm_aalg_get_byname(x->aalg->alg_name, 0); BUG_ON(!aalg_desc); if (aalg_desc->uinfo.auth.icv_fullbits/8 != - crypto_hash_digestsize(tfm)) { + crypto_ahash_digestsize(ahash)) { printk(KERN_INFO "AH: %s digestsize %u != %hu\n", - x->aalg->alg_name, crypto_hash_digestsize(tfm), + x->aalg->alg_name, crypto_ahash_digestsize(ahash), aalg_desc->uinfo.auth.icv_fullbits/8); goto error; } ahp->icv_full_len = aalg_desc->uinfo.auth.icv_fullbits/8; - ahp->icv_trunc_len = aalg_desc->uinfo.auth.icv_truncbits/8; + ahp->icv_trunc_len = x->aalg->alg_trunc_len/8; BUG_ON(ahp->icv_trunc_len > MAX_AH_AUTH_LEN); - ahp->work_icv = kmalloc(ahp->icv_full_len, GFP_KERNEL); - if (!ahp->work_icv) - goto error; - x->props.header_len = XFRM_ALIGN8(sizeof(struct ip_auth_hdr) + ahp->icv_trunc_len); if (x->props.mode == XFRM_MODE_TUNNEL) @@ -279,8 +458,7 @@ static int ah_init_state(struct xfrm_state *x) error: if (ahp) { - kfree(ahp->work_icv); - crypto_free_hash(ahp->tfm); + crypto_free_ahash(ahp->ahash); kfree(ahp); } return -EINVAL; @@ -293,8 +471,7 @@ static void ah_destroy(struct xfrm_state *x) if (!ahp) return; - kfree(ahp->work_icv); - crypto_free_hash(ahp->tfm); + crypto_free_ahash(ahp->ahash); kfree(ahp); } diff --git a/net/ipv4/cipso_ipv4.c b/net/ipv4/cipso_ipv4.c index 039cc1ffe977..1e029dc75455 100644 --- a/net/ipv4/cipso_ipv4.c +++ b/net/ipv4/cipso_ipv4.c @@ -2017,7 +2017,7 @@ req_setattr_failure: * values on failure. * */ -int cipso_v4_delopt(struct ip_options **opt_ptr) +static int cipso_v4_delopt(struct ip_options **opt_ptr) { int hdr_delta = 0; struct ip_options *opt = *opt_ptr; diff --git a/net/ipv4/datagram.c b/net/ipv4/datagram.c index 5e6c5a0f3fde..fb2465811b48 100644 --- a/net/ipv4/datagram.c +++ b/net/ipv4/datagram.c @@ -39,7 +39,7 @@ int ip4_datagram_connect(struct sock *sk, struct sockaddr *uaddr, int addr_len) sk_dst_reset(sk); oif = sk->sk_bound_dev_if; - saddr = inet->saddr; + saddr = inet->inet_saddr; if (ipv4_is_multicast(usin->sin_addr.s_addr)) { if (!oif) oif = inet->mc_index; @@ -49,7 +49,7 @@ int ip4_datagram_connect(struct sock *sk, struct sockaddr *uaddr, int addr_len) err = ip_route_connect(&rt, usin->sin_addr.s_addr, saddr, RT_CONN_FLAGS(sk), oif, sk->sk_protocol, - inet->sport, usin->sin_port, sk, 1); + inet->inet_sport, usin->sin_port, sk, 1); if (err) { if (err == -ENETUNREACH) IP_INC_STATS_BH(sock_net(sk), IPSTATS_MIB_OUTNOROUTES); @@ -60,14 +60,14 @@ int ip4_datagram_connect(struct sock *sk, struct sockaddr *uaddr, int addr_len) ip_rt_put(rt); return -EACCES; } - if (!inet->saddr) - inet->saddr = rt->rt_src; /* Update source address */ - if (!inet->rcv_saddr) - inet->rcv_saddr = rt->rt_src; - inet->daddr = rt->rt_dst; - inet->dport = usin->sin_port; + if (!inet->inet_saddr) + inet->inet_saddr = rt->rt_src; /* Update source address */ + if (!inet->inet_rcv_saddr) + inet->inet_rcv_saddr = rt->rt_src; + inet->inet_daddr = rt->rt_dst; + inet->inet_dport = usin->sin_port; sk->sk_state = TCP_ESTABLISHED; - inet->id = jiffies; + inet->inet_id = jiffies; sk_dst_set(sk, &rt->u.dst); return(0); diff --git a/net/ipv4/devinet.c b/net/ipv4/devinet.c index e049da8311b5..5cdbc102a418 100644 --- a/net/ipv4/devinet.c +++ b/net/ipv4/devinet.c @@ -140,11 +140,11 @@ void in_dev_finish_destroy(struct in_device *idev) #endif dev_put(dev); if (!idev->dead) - printk("Freeing alive in_device %p\n", idev); - else { + pr_err("Freeing alive in_device %p\n", idev); + else kfree(idev); - } } +EXPORT_SYMBOL(in_dev_finish_destroy); static struct in_device *inetdev_init(struct net_device *dev) { @@ -159,7 +159,8 @@ static struct in_device *inetdev_init(struct net_device *dev) sizeof(in_dev->cnf)); in_dev->cnf.sysctl = NULL; in_dev->dev = dev; - if ((in_dev->arp_parms = neigh_parms_alloc(dev, &arp_tbl)) == NULL) + in_dev->arp_parms = neigh_parms_alloc(dev, &arp_tbl); + if (!in_dev->arp_parms) goto out_kfree; if (IPV4_DEVCONF(in_dev->cnf, FORWARDING)) dev_disable_lro(dev); @@ -405,13 +406,15 @@ struct in_device *inetdev_by_index(struct net *net, int ifindex) { struct net_device *dev; struct in_device *in_dev = NULL; - read_lock(&dev_base_lock); - dev = __dev_get_by_index(net, ifindex); + + rcu_read_lock(); + dev = dev_get_by_index_rcu(net, ifindex); if (dev) in_dev = in_dev_get(dev); - read_unlock(&dev_base_lock); + rcu_read_unlock(); return in_dev; } +EXPORT_SYMBOL(inetdev_by_index); /* Called only from RTNL semaphored context. No locks. */ @@ -557,7 +560,7 @@ static int inet_rtm_newaddr(struct sk_buff *skb, struct nlmsghdr *nlh, void *arg * Determine a default network mask, based on the IP address. */ -static __inline__ int inet_abc_len(__be32 addr) +static inline int inet_abc_len(__be32 addr) { int rc = -1; /* Something else, probably a multicast. */ @@ -646,13 +649,15 @@ int devinet_ioctl(struct net *net, unsigned int cmd, void __user *arg) rtnl_lock(); ret = -ENODEV; - if ((dev = __dev_get_by_name(net, ifr.ifr_name)) == NULL) + dev = __dev_get_by_name(net, ifr.ifr_name); + if (!dev) goto done; if (colon) *colon = ':'; - if ((in_dev = __in_dev_get_rtnl(dev)) != NULL) { + in_dev = __in_dev_get_rtnl(dev); + if (in_dev) { if (tryaddrmatch) { /* Matthias Andree */ /* compare label and address (4.4BSD style) */ @@ -720,7 +725,8 @@ int devinet_ioctl(struct net *net, unsigned int cmd, void __user *arg) if (!ifa) { ret = -ENOBUFS; - if ((ifa = inet_alloc_ifa()) == NULL) + ifa = inet_alloc_ifa(); + if (!ifa) break; if (colon) memcpy(ifa->ifa_label, ifr.ifr_name, IFNAMSIZ); @@ -822,10 +828,10 @@ static int inet_gifconf(struct net_device *dev, char __user *buf, int len) struct ifreq ifr; int done = 0; - if (!in_dev || (ifa = in_dev->ifa_list) == NULL) + if (!in_dev) goto out; - for (; ifa; ifa = ifa->ifa_next) { + for (ifa = in_dev->ifa_list; ifa; ifa = ifa->ifa_next) { if (!buf) { done += sizeof(ifr); continue; @@ -875,36 +881,33 @@ __be32 inet_select_addr(const struct net_device *dev, __be32 dst, int scope) if (!addr) addr = ifa->ifa_local; } endfor_ifa(in_dev); -no_in_dev: - rcu_read_unlock(); if (addr) - goto out; + goto out_unlock; +no_in_dev: /* Not loopback addresses on loopback should be preferred in this case. It is importnat that lo is the first interface in dev_base list. */ - read_lock(&dev_base_lock); - rcu_read_lock(); - for_each_netdev(net, dev) { - if ((in_dev = __in_dev_get_rcu(dev)) == NULL) + for_each_netdev_rcu(net, dev) { + in_dev = __in_dev_get_rcu(dev); + if (!in_dev) continue; for_primary_ifa(in_dev) { if (ifa->ifa_scope != RT_SCOPE_LINK && ifa->ifa_scope <= scope) { addr = ifa->ifa_local; - goto out_unlock_both; + goto out_unlock; } } endfor_ifa(in_dev); } -out_unlock_both: - read_unlock(&dev_base_lock); +out_unlock: rcu_read_unlock(); -out: return addr; } +EXPORT_SYMBOL(inet_select_addr); static __be32 confirm_addr_indev(struct in_device *in_dev, __be32 dst, __be32 local, int scope) @@ -940,7 +943,7 @@ static __be32 confirm_addr_indev(struct in_device *in_dev, __be32 dst, } } endfor_ifa(in_dev); - return same? addr : 0; + return same ? addr : 0; } /* @@ -961,17 +964,16 @@ __be32 inet_confirm_addr(struct in_device *in_dev, return confirm_addr_indev(in_dev, dst, local, scope); net = dev_net(in_dev->dev); - read_lock(&dev_base_lock); rcu_read_lock(); - for_each_netdev(net, dev) { - if ((in_dev = __in_dev_get_rcu(dev))) { + for_each_netdev_rcu(net, dev) { + in_dev = __in_dev_get_rcu(dev); + if (in_dev) { addr = confirm_addr_indev(in_dev, dst, local, scope); if (addr) break; } } rcu_read_unlock(); - read_unlock(&dev_base_lock); return addr; } @@ -984,14 +986,16 @@ int register_inetaddr_notifier(struct notifier_block *nb) { return blocking_notifier_chain_register(&inetaddr_chain, nb); } +EXPORT_SYMBOL(register_inetaddr_notifier); int unregister_inetaddr_notifier(struct notifier_block *nb) { return blocking_notifier_chain_unregister(&inetaddr_chain, nb); } +EXPORT_SYMBOL(unregister_inetaddr_notifier); -/* Rename ifa_labels for a device name change. Make some effort to preserve existing - * alias numbering and to create unique labels if possible. +/* Rename ifa_labels for a device name change. Make some effort to preserve + * existing alias numbering and to create unique labels if possible. */ static void inetdev_changename(struct net_device *dev, struct in_device *in_dev) { @@ -1010,11 +1014,10 @@ static void inetdev_changename(struct net_device *dev, struct in_device *in_dev) sprintf(old, ":%d", named); dot = old; } - if (strlen(dot) + strlen(dev->name) < IFNAMSIZ) { + if (strlen(dot) + strlen(dev->name) < IFNAMSIZ) strcat(ifa->ifa_label, dot); - } else { + else strcpy(ifa->ifa_label + (IFNAMSIZ - strlen(dot) - 1), dot); - } skip: rtmsg_ifa(RTM_NEWADDR, ifa, NULL, 0); } @@ -1061,8 +1064,9 @@ static int inetdev_event(struct notifier_block *this, unsigned long event, if (!inetdev_valid_mtu(dev->mtu)) break; if (dev->flags & IFF_LOOPBACK) { - struct in_ifaddr *ifa; - if ((ifa = inet_alloc_ifa()) != NULL) { + struct in_ifaddr *ifa = inet_alloc_ifa(); + + if (ifa) { ifa->ifa_local = ifa->ifa_address = htonl(INADDR_LOOPBACK); ifa->ifa_prefixlen = 8; @@ -1170,38 +1174,54 @@ nla_put_failure: static int inet_dump_ifaddr(struct sk_buff *skb, struct netlink_callback *cb) { struct net *net = sock_net(skb->sk); - int idx, ip_idx; + int h, s_h; + int idx, s_idx; + int ip_idx, s_ip_idx; struct net_device *dev; struct in_device *in_dev; struct in_ifaddr *ifa; - int s_ip_idx, s_idx = cb->args[0]; + struct hlist_head *head; + struct hlist_node *node; - s_ip_idx = ip_idx = cb->args[1]; - idx = 0; - for_each_netdev(net, dev) { - if (idx < s_idx) - goto cont; - if (idx > s_idx) - s_ip_idx = 0; - if ((in_dev = __in_dev_get_rtnl(dev)) == NULL) - goto cont; - - for (ifa = in_dev->ifa_list, ip_idx = 0; ifa; - ifa = ifa->ifa_next, ip_idx++) { - if (ip_idx < s_ip_idx) - continue; - if (inet_fill_ifaddr(skb, ifa, NETLINK_CB(cb->skb).pid, + s_h = cb->args[0]; + s_idx = idx = cb->args[1]; + s_ip_idx = ip_idx = cb->args[2]; + + for (h = s_h; h < NETDEV_HASHENTRIES; h++, s_idx = 0) { + idx = 0; + head = &net->dev_index_head[h]; + rcu_read_lock(); + hlist_for_each_entry_rcu(dev, node, head, index_hlist) { + if (idx < s_idx) + goto cont; + if (idx > s_idx) + s_ip_idx = 0; + in_dev = __in_dev_get_rcu(dev); + if (!in_dev) + goto cont; + + for (ifa = in_dev->ifa_list, ip_idx = 0; ifa; + ifa = ifa->ifa_next, ip_idx++) { + if (ip_idx < s_ip_idx) + continue; + if (inet_fill_ifaddr(skb, ifa, + NETLINK_CB(cb->skb).pid, cb->nlh->nlmsg_seq, - RTM_NEWADDR, NLM_F_MULTI) <= 0) - goto done; - } + RTM_NEWADDR, NLM_F_MULTI) <= 0) { + rcu_read_unlock(); + goto done; + } + } cont: - idx++; + idx++; + } + rcu_read_unlock(); } done: - cb->args[0] = idx; - cb->args[1] = ip_idx; + cb->args[0] = h; + cb->args[1] = idx; + cb->args[2] = ip_idx; return skb->len; } @@ -1239,18 +1259,18 @@ static void devinet_copy_dflt_conf(struct net *net, int i) { struct net_device *dev; - read_lock(&dev_base_lock); - for_each_netdev(net, dev) { + rcu_read_lock(); + for_each_netdev_rcu(net, dev) { struct in_device *in_dev; - rcu_read_lock(); + in_dev = __in_dev_get_rcu(dev); if (in_dev && !test_bit(i, in_dev->cnf.state)) in_dev->cnf.data[i] = net->ipv4.devconf_dflt->data[i]; - rcu_read_unlock(); } - read_unlock(&dev_base_lock); + rcu_read_unlock(); } +/* called with RTNL locked */ static void inet_forward_change(struct net *net) { struct net_device *dev; @@ -1259,7 +1279,6 @@ static void inet_forward_change(struct net *net) IPV4_DEVCONF_ALL(net, ACCEPT_REDIRECTS) = !on; IPV4_DEVCONF_DFLT(net, FORWARDING) = on; - read_lock(&dev_base_lock); for_each_netdev(net, dev) { struct in_device *in_dev; if (on) @@ -1270,7 +1289,6 @@ static void inet_forward_change(struct net *net) IN_DEV_CONF_SET(in_dev, FORWARDING, on); rcu_read_unlock(); } - read_unlock(&dev_base_lock); } static int devinet_conf_proc(ctl_table *ctl, int write, @@ -1378,6 +1396,7 @@ static struct devinet_sysctl_table { DEVINET_SYSCTL_RW_ENTRY(SEND_REDIRECTS, "send_redirects"), DEVINET_SYSCTL_RW_ENTRY(ACCEPT_SOURCE_ROUTE, "accept_source_route"), + DEVINET_SYSCTL_RW_ENTRY(ACCEPT_LOCAL, "accept_local"), DEVINET_SYSCTL_RW_ENTRY(PROXY_ARP, "proxy_arp"), DEVINET_SYSCTL_RW_ENTRY(MEDIUM_ID, "medium_id"), DEVINET_SYSCTL_RW_ENTRY(BOOTP_RELAY, "bootp_relay"), @@ -1512,7 +1531,7 @@ static __net_init int devinet_init_net(struct net *net) all = &ipv4_devconf; dflt = &ipv4_devconf_dflt; - if (net != &init_net) { + if (!net_eq(net, &init_net)) { all = kmemdup(all, sizeof(ipv4_devconf), GFP_KERNEL); if (all == NULL) goto err_alloc_all; @@ -1603,8 +1622,3 @@ void __init devinet_init(void) rtnl_register(PF_INET, RTM_GETADDR, NULL, inet_dump_ifaddr); } -EXPORT_SYMBOL(in_dev_finish_destroy); -EXPORT_SYMBOL(inet_select_addr); -EXPORT_SYMBOL(inetdev_by_index); -EXPORT_SYMBOL(register_inetaddr_notifier); -EXPORT_SYMBOL(unregister_inetaddr_notifier); diff --git a/net/ipv4/esp4.c b/net/ipv4/esp4.c index 12f7287e902d..1948895beb6d 100644 --- a/net/ipv4/esp4.c +++ b/net/ipv4/esp4.c @@ -530,7 +530,7 @@ static int esp_init_authenc(struct xfrm_state *x) } err = crypto_aead_setauthsize( - aead, aalg_desc->uinfo.auth.icv_truncbits / 8); + aead, x->aalg->alg_trunc_len / 8); if (err) goto free_key; } diff --git a/net/ipv4/fib_frontend.c b/net/ipv4/fib_frontend.c index aa00398be80e..3323168ee52d 100644 --- a/net/ipv4/fib_frontend.c +++ b/net/ipv4/fib_frontend.c @@ -125,7 +125,7 @@ void fib_select_default(struct net *net, #endif tb = fib_get_table(net, table); if (FIB_RES_GW(*res) && FIB_RES_NH(*res).nh_scope == RT_SCOPE_LINK) - tb->tb_select_default(tb, flp, res); + fib_table_select_default(tb, flp, res); } static void fib_flush(struct net *net) @@ -139,7 +139,7 @@ static void fib_flush(struct net *net) for (h = 0; h < FIB_TABLE_HASHSZ; h++) { head = &net->ipv4.fib_table_hash[h]; hlist_for_each_entry(tb, node, head, tb_hlist) - flushed += tb->tb_flush(tb); + flushed += fib_table_flush(tb); } if (flushed) @@ -162,7 +162,7 @@ struct net_device * ip_dev_find(struct net *net, __be32 addr) #endif local_table = fib_get_table(net, RT_TABLE_LOCAL); - if (!local_table || local_table->tb_lookup(local_table, &fl, &res)) + if (!local_table || fib_table_lookup(local_table, &fl, &res)) return NULL; if (res.type != RTN_LOCAL) goto out; @@ -200,7 +200,7 @@ static inline unsigned __inet_dev_addr_type(struct net *net, local_table = fib_get_table(net, RT_TABLE_LOCAL); if (local_table) { ret = RTN_UNICAST; - if (!local_table->tb_lookup(local_table, &fl, &res)) { + if (!fib_table_lookup(local_table, &fl, &res)) { if (!dev || dev == res.fi->fib_dev) ret = res.type; fib_res_put(&res); @@ -241,16 +241,17 @@ int fib_validate_source(__be32 src, __be32 dst, u8 tos, int oif, .iif = oif }; struct fib_result res; - int no_addr, rpf; + int no_addr, rpf, accept_local; int ret; struct net *net; - no_addr = rpf = 0; + no_addr = rpf = accept_local = 0; rcu_read_lock(); in_dev = __in_dev_get_rcu(dev); if (in_dev) { no_addr = in_dev->ifa_list == NULL; rpf = IN_DEV_RPFILTER(in_dev); + accept_local = IN_DEV_ACCEPT_LOCAL(in_dev); } rcu_read_unlock(); @@ -260,8 +261,10 @@ int fib_validate_source(__be32 src, __be32 dst, u8 tos, int oif, net = dev_net(dev); if (fib_lookup(net, &fl, &res)) goto last_resort; - if (res.type != RTN_UNICAST) - goto e_inval_res; + if (res.type != RTN_UNICAST) { + if (res.type != RTN_LOCAL || !accept_local) + goto e_inval_res; + } *spec_dst = FIB_RES_PREFSRC(res); fib_combine_itag(itag, &res); #ifdef CONFIG_IP_ROUTE_MULTIPATH @@ -476,13 +479,13 @@ int ip_rt_ioctl(struct net *net, unsigned int cmd, void __user *arg) if (cmd == SIOCDELRT) { tb = fib_get_table(net, cfg.fc_table); if (tb) - err = tb->tb_delete(tb, &cfg); + err = fib_table_delete(tb, &cfg); else err = -ESRCH; } else { tb = fib_new_table(net, cfg.fc_table); if (tb) - err = tb->tb_insert(tb, &cfg); + err = fib_table_insert(tb, &cfg); else err = -ENOBUFS; } @@ -597,7 +600,7 @@ static int inet_rtm_delroute(struct sk_buff *skb, struct nlmsghdr *nlh, void *ar goto errout; } - err = tb->tb_delete(tb, &cfg); + err = fib_table_delete(tb, &cfg); errout: return err; } @@ -619,7 +622,7 @@ static int inet_rtm_newroute(struct sk_buff *skb, struct nlmsghdr *nlh, void *ar goto errout; } - err = tb->tb_insert(tb, &cfg); + err = fib_table_insert(tb, &cfg); errout: return err; } @@ -650,7 +653,7 @@ static int inet_dump_fib(struct sk_buff *skb, struct netlink_callback *cb) if (dumped) memset(&cb->args[2], 0, sizeof(cb->args) - 2 * sizeof(cb->args[0])); - if (tb->tb_dump(tb, skb, cb) < 0) + if (fib_table_dump(tb, skb, cb) < 0) goto out; dumped = 1; next: @@ -704,9 +707,9 @@ static void fib_magic(int cmd, int type, __be32 dst, int dst_len, struct in_ifad cfg.fc_scope = RT_SCOPE_HOST; if (cmd == RTM_NEWROUTE) - tb->tb_insert(tb, &cfg); + fib_table_insert(tb, &cfg); else - tb->tb_delete(tb, &cfg); + fib_table_delete(tb, &cfg); } void fib_add_ifaddr(struct in_ifaddr *ifa) @@ -835,7 +838,7 @@ static void nl_fib_lookup(struct fib_result_nl *frn, struct fib_table *tb ) local_bh_disable(); frn->tb_id = tb->tb_id; - frn->err = tb->tb_lookup(tb, &fl, &res); + frn->err = fib_table_lookup(tb, &fl, &res); if (!frn->err) { frn->prefixlen = res.prefixlen; @@ -895,11 +898,11 @@ static void nl_fib_lookup_exit(struct net *net) net->ipv4.fibnl = NULL; } -static void fib_disable_ip(struct net_device *dev, int force) +static void fib_disable_ip(struct net_device *dev, int force, int delay) { if (fib_sync_down_dev(dev, force)) fib_flush(dev_net(dev)); - rt_cache_flush(dev_net(dev), 0); + rt_cache_flush(dev_net(dev), delay); arp_ifdown(dev); } @@ -922,7 +925,7 @@ static int fib_inetaddr_event(struct notifier_block *this, unsigned long event, /* Last address was deleted from this interface. Disable IP. */ - fib_disable_ip(dev, 1); + fib_disable_ip(dev, 1, 0); } else { rt_cache_flush(dev_net(dev), -1); } @@ -937,7 +940,7 @@ static int fib_netdev_event(struct notifier_block *this, unsigned long event, vo struct in_device *in_dev = __in_dev_get_rtnl(dev); if (event == NETDEV_UNREGISTER) { - fib_disable_ip(dev, 2); + fib_disable_ip(dev, 2, -1); return NOTIFY_DONE; } @@ -955,12 +958,15 @@ static int fib_netdev_event(struct notifier_block *this, unsigned long event, vo rt_cache_flush(dev_net(dev), -1); break; case NETDEV_DOWN: - fib_disable_ip(dev, 0); + fib_disable_ip(dev, 0, 0); break; case NETDEV_CHANGEMTU: case NETDEV_CHANGE: rt_cache_flush(dev_net(dev), 0); break; + case NETDEV_UNREGISTER_BATCH: + rt_cache_flush_batch(); + break; } return NOTIFY_DONE; } @@ -1012,7 +1018,7 @@ static void __net_exit ip_fib_net_exit(struct net *net) head = &net->ipv4.fib_table_hash[i]; hlist_for_each_entry_safe(tb, node, tmp, head, tb_hlist) { hlist_del(node); - tb->tb_flush(tb); + fib_table_flush(tb); kfree(tb); } } diff --git a/net/ipv4/fib_hash.c b/net/ipv4/fib_hash.c index ecd39454235c..14972017b9c2 100644 --- a/net/ipv4/fib_hash.c +++ b/net/ipv4/fib_hash.c @@ -242,8 +242,8 @@ fn_new_zone(struct fn_hash *table, int z) return fz; } -static int -fn_hash_lookup(struct fib_table *tb, const struct flowi *flp, struct fib_result *res) +int fib_table_lookup(struct fib_table *tb, + const struct flowi *flp, struct fib_result *res) { int err; struct fn_zone *fz; @@ -274,8 +274,8 @@ out: return err; } -static void -fn_hash_select_default(struct fib_table *tb, const struct flowi *flp, struct fib_result *res) +void fib_table_select_default(struct fib_table *tb, + const struct flowi *flp, struct fib_result *res) { int order, last_idx; struct hlist_node *node; @@ -366,7 +366,7 @@ static struct fib_node *fib_find_node(struct fn_zone *fz, __be32 key) return NULL; } -static int fn_hash_insert(struct fib_table *tb, struct fib_config *cfg) +int fib_table_insert(struct fib_table *tb, struct fib_config *cfg) { struct fn_hash *table = (struct fn_hash *) tb->tb_data; struct fib_node *new_f = NULL; @@ -544,8 +544,7 @@ out: return err; } - -static int fn_hash_delete(struct fib_table *tb, struct fib_config *cfg) +int fib_table_delete(struct fib_table *tb, struct fib_config *cfg) { struct fn_hash *table = (struct fn_hash *)tb->tb_data; struct fib_node *f; @@ -662,7 +661,7 @@ static int fn_flush_list(struct fn_zone *fz, int idx) return found; } -static int fn_hash_flush(struct fib_table *tb) +int fib_table_flush(struct fib_table *tb) { struct fn_hash *table = (struct fn_hash *) tb->tb_data; struct fn_zone *fz; @@ -743,7 +742,8 @@ fn_hash_dump_zone(struct sk_buff *skb, struct netlink_callback *cb, return skb->len; } -static int fn_hash_dump(struct fib_table *tb, struct sk_buff *skb, struct netlink_callback *cb) +int fib_table_dump(struct fib_table *tb, struct sk_buff *skb, + struct netlink_callback *cb) { int m, s_m; struct fn_zone *fz; @@ -787,12 +787,7 @@ struct fib_table *fib_hash_table(u32 id) tb->tb_id = id; tb->tb_default = -1; - tb->tb_lookup = fn_hash_lookup; - tb->tb_insert = fn_hash_insert; - tb->tb_delete = fn_hash_delete; - tb->tb_flush = fn_hash_flush; - tb->tb_select_default = fn_hash_select_default; - tb->tb_dump = fn_hash_dump; + memset(tb->tb_data, 0, sizeof(struct fn_hash)); return tb; } diff --git a/net/ipv4/fib_rules.c b/net/ipv4/fib_rules.c index 92d9d97ec5e3..ca2d07b1c706 100644 --- a/net/ipv4/fib_rules.c +++ b/net/ipv4/fib_rules.c @@ -94,7 +94,7 @@ static int fib4_rule_action(struct fib_rule *rule, struct flowi *flp, if ((tbl = fib_get_table(rule->fr_net, rule->table)) == NULL) goto errout; - err = tbl->tb_lookup(tbl, flp, (struct fib_result *) arg->result); + err = fib_table_lookup(tbl, flp, (struct fib_result *) arg->result); if (err > 0) err = -EAGAIN; errout: @@ -284,7 +284,7 @@ static int fib_default_rules_init(struct fib_rules_ops *ops) { int err; - err = fib_default_rule_add(ops, 0, RT_TABLE_LOCAL, FIB_RULE_PERMANENT); + err = fib_default_rule_add(ops, 0, RT_TABLE_LOCAL, 0); if (err < 0) return err; err = fib_default_rule_add(ops, 0x7FFE, RT_TABLE_MAIN, 0); @@ -301,13 +301,9 @@ int __net_init fib4_rules_init(struct net *net) int err; struct fib_rules_ops *ops; - ops = kmemdup(&fib4_rules_ops_template, sizeof(*ops), GFP_KERNEL); - if (ops == NULL) - return -ENOMEM; - INIT_LIST_HEAD(&ops->rules_list); - ops->fro_net = net; - - fib_rules_register(ops); + ops = fib_rules_register(&fib4_rules_ops_template, net); + if (IS_ERR(ops)) + return PTR_ERR(ops); err = fib_default_rules_init(ops); if (err < 0) @@ -318,12 +314,10 @@ int __net_init fib4_rules_init(struct net *net) fail: /* also cleans all rules already added */ fib_rules_unregister(ops); - kfree(ops); return err; } void __net_exit fib4_rules_exit(struct net *net) { fib_rules_unregister(net->ipv4.rules_ops); - kfree(net->ipv4.rules_ops); } diff --git a/net/ipv4/fib_semantics.c b/net/ipv4/fib_semantics.c index 9b096d6ff3f2..ed19aa6919c2 100644 --- a/net/ipv4/fib_semantics.c +++ b/net/ipv4/fib_semantics.c @@ -228,7 +228,7 @@ static struct fib_info *fib_find_info(const struct fib_info *nfi) head = &fib_info_hash[hash]; hlist_for_each_entry(fi, node, head, fib_hash) { - if (fi->fib_net != nfi->fib_net) + if (!net_eq(fi->fib_net, nfi->fib_net)) continue; if (fi->fib_nhs != nfi->fib_nhs) continue; @@ -1047,7 +1047,7 @@ int fib_sync_down_addr(struct net *net, __be32 local) return 0; hlist_for_each_entry(fi, node, head, fib_lhash) { - if (fi->fib_net != net) + if (!net_eq(fi->fib_net, net)) continue; if (fi->fib_prefsrc == local) { fi->fib_flags |= RTNH_F_DEAD; diff --git a/net/ipv4/fib_trie.c b/net/ipv4/fib_trie.c index 291bdf50a21f..af5d89792860 100644 --- a/net/ipv4/fib_trie.c +++ b/net/ipv4/fib_trie.c @@ -1174,7 +1174,7 @@ done: /* * Caller must hold RTNL. */ -static int fn_trie_insert(struct fib_table *tb, struct fib_config *cfg) +int fib_table_insert(struct fib_table *tb, struct fib_config *cfg) { struct trie *t = (struct trie *) tb->tb_data; struct fib_alias *fa, *new_fa; @@ -1373,8 +1373,8 @@ static int check_leaf(struct trie *t, struct leaf *l, return 1; } -static int fn_trie_lookup(struct fib_table *tb, const struct flowi *flp, - struct fib_result *res) +int fib_table_lookup(struct fib_table *tb, const struct flowi *flp, + struct fib_result *res) { struct trie *t = (struct trie *) tb->tb_data; int ret; @@ -1595,7 +1595,7 @@ static void trie_leaf_remove(struct trie *t, struct leaf *l) /* * Caller must hold RTNL. */ -static int fn_trie_delete(struct fib_table *tb, struct fib_config *cfg) +int fib_table_delete(struct fib_table *tb, struct fib_config *cfg) { struct trie *t = (struct trie *) tb->tb_data; u32 key, mask; @@ -1786,7 +1786,7 @@ static struct leaf *trie_leafindex(struct trie *t, int index) /* * Caller must hold RTNL. */ -static int fn_trie_flush(struct fib_table *tb) +int fib_table_flush(struct fib_table *tb) { struct trie *t = (struct trie *) tb->tb_data; struct leaf *l, *ll = NULL; @@ -1807,9 +1807,9 @@ static int fn_trie_flush(struct fib_table *tb) return found; } -static void fn_trie_select_default(struct fib_table *tb, - const struct flowi *flp, - struct fib_result *res) +void fib_table_select_default(struct fib_table *tb, + const struct flowi *flp, + struct fib_result *res) { struct trie *t = (struct trie *) tb->tb_data; int order, last_idx; @@ -1952,8 +1952,8 @@ static int fn_trie_dump_leaf(struct leaf *l, struct fib_table *tb, return skb->len; } -static int fn_trie_dump(struct fib_table *tb, struct sk_buff *skb, - struct netlink_callback *cb) +int fib_table_dump(struct fib_table *tb, struct sk_buff *skb, + struct netlink_callback *cb) { struct leaf *l; struct trie *t = (struct trie *) tb->tb_data; @@ -2020,12 +2020,6 @@ struct fib_table *fib_hash_table(u32 id) tb->tb_id = id; tb->tb_default = -1; - tb->tb_lookup = fn_trie_lookup; - tb->tb_insert = fn_trie_insert; - tb->tb_delete = fn_trie_delete; - tb->tb_flush = fn_trie_flush; - tb->tb_select_default = fn_trie_select_default; - tb->tb_dump = fn_trie_dump; t = (struct trie *) tb->tb_data; memset(t, 0, sizeof(*t)); diff --git a/net/ipv4/icmp.c b/net/ipv4/icmp.c index 5bc13fe816d1..fe11f60ce41b 100644 --- a/net/ipv4/icmp.c +++ b/net/ipv4/icmp.c @@ -501,15 +501,16 @@ void icmp_send(struct sk_buff *skb_in, int type, int code, __be32 info) if (!(rt->rt_flags & RTCF_LOCAL)) { struct net_device *dev = NULL; + rcu_read_lock(); if (rt->fl.iif && net->ipv4.sysctl_icmp_errors_use_inbound_ifaddr) - dev = dev_get_by_index(net, rt->fl.iif); + dev = dev_get_by_index_rcu(net, rt->fl.iif); - if (dev) { + if (dev) saddr = inet_select_addr(dev, 0, RT_SCOPE_LINK); - dev_put(dev); - } else + else saddr = 0; + rcu_read_unlock(); } tos = icmp_pointers[type].error ? ((iph->tos & IPTOS_TOS_MASK) | @@ -1165,6 +1166,10 @@ static int __net_init icmp_sk_init(struct net *net) sk->sk_sndbuf = (2 * ((64 * 1024) + sizeof(struct sk_buff))); + /* + * Speedup sock_wfree() + */ + sock_set_flag(sk, SOCK_USE_WRITE_QUEUE); inet_sk(sk)->pmtudisc = IP_PMTUDISC_DONT; } diff --git a/net/ipv4/igmp.c b/net/ipv4/igmp.c index d41e5de79a82..76c08402c933 100644 --- a/net/ipv4/igmp.c +++ b/net/ipv4/igmp.c @@ -1899,8 +1899,9 @@ int ip_mc_source(int add, int omode, struct sock *sk, struct err = -EADDRNOTAVAIL; for (pmc=inet->mc_list; pmc; pmc=pmc->next) { - if (pmc->multi.imr_multiaddr.s_addr == imr.imr_multiaddr.s_addr - && pmc->multi.imr_ifindex == imr.imr_ifindex) + if ((pmc->multi.imr_multiaddr.s_addr == + imr.imr_multiaddr.s_addr) && + (pmc->multi.imr_ifindex == imr.imr_ifindex)) break; } if (!pmc) { /* must have a prior join */ @@ -2311,9 +2312,10 @@ static inline struct ip_mc_list *igmp_mc_get_first(struct seq_file *seq) struct igmp_mc_iter_state *state = igmp_mc_seq_private(seq); state->in_dev = NULL; - for_each_netdev(net, state->dev) { + for_each_netdev_rcu(net, state->dev) { struct in_device *in_dev; - in_dev = in_dev_get(state->dev); + + in_dev = __in_dev_get_rcu(state->dev); if (!in_dev) continue; read_lock(&in_dev->mc_list_lock); @@ -2323,7 +2325,6 @@ static inline struct ip_mc_list *igmp_mc_get_first(struct seq_file *seq) break; } read_unlock(&in_dev->mc_list_lock); - in_dev_put(in_dev); } return im; } @@ -2333,16 +2334,15 @@ static struct ip_mc_list *igmp_mc_get_next(struct seq_file *seq, struct ip_mc_li struct igmp_mc_iter_state *state = igmp_mc_seq_private(seq); im = im->next; while (!im) { - if (likely(state->in_dev != NULL)) { + if (likely(state->in_dev != NULL)) read_unlock(&state->in_dev->mc_list_lock); - in_dev_put(state->in_dev); - } - state->dev = next_net_device(state->dev); + + state->dev = next_net_device_rcu(state->dev); if (!state->dev) { state->in_dev = NULL; break; } - state->in_dev = in_dev_get(state->dev); + state->in_dev = __in_dev_get_rcu(state->dev); if (!state->in_dev) continue; read_lock(&state->in_dev->mc_list_lock); @@ -2361,9 +2361,9 @@ static struct ip_mc_list *igmp_mc_get_idx(struct seq_file *seq, loff_t pos) } static void *igmp_mc_seq_start(struct seq_file *seq, loff_t *pos) - __acquires(dev_base_lock) + __acquires(rcu) { - read_lock(&dev_base_lock); + rcu_read_lock(); return *pos ? igmp_mc_get_idx(seq, *pos - 1) : SEQ_START_TOKEN; } @@ -2379,16 +2379,15 @@ static void *igmp_mc_seq_next(struct seq_file *seq, void *v, loff_t *pos) } static void igmp_mc_seq_stop(struct seq_file *seq, void *v) - __releases(dev_base_lock) + __releases(rcu) { struct igmp_mc_iter_state *state = igmp_mc_seq_private(seq); if (likely(state->in_dev != NULL)) { read_unlock(&state->in_dev->mc_list_lock); - in_dev_put(state->in_dev); state->in_dev = NULL; } state->dev = NULL; - read_unlock(&dev_base_lock); + rcu_read_unlock(); } static int igmp_mc_seq_show(struct seq_file *seq, void *v) @@ -2462,9 +2461,9 @@ static inline struct ip_sf_list *igmp_mcf_get_first(struct seq_file *seq) state->idev = NULL; state->im = NULL; - for_each_netdev(net, state->dev) { + for_each_netdev_rcu(net, state->dev) { struct in_device *idev; - idev = in_dev_get(state->dev); + idev = __in_dev_get_rcu(state->dev); if (unlikely(idev == NULL)) continue; read_lock(&idev->mc_list_lock); @@ -2480,7 +2479,6 @@ static inline struct ip_sf_list *igmp_mcf_get_first(struct seq_file *seq) spin_unlock_bh(&im->lock); } read_unlock(&idev->mc_list_lock); - in_dev_put(idev); } return psf; } @@ -2494,16 +2492,15 @@ static struct ip_sf_list *igmp_mcf_get_next(struct seq_file *seq, struct ip_sf_l spin_unlock_bh(&state->im->lock); state->im = state->im->next; while (!state->im) { - if (likely(state->idev != NULL)) { + if (likely(state->idev != NULL)) read_unlock(&state->idev->mc_list_lock); - in_dev_put(state->idev); - } - state->dev = next_net_device(state->dev); + + state->dev = next_net_device_rcu(state->dev); if (!state->dev) { state->idev = NULL; goto out; } - state->idev = in_dev_get(state->dev); + state->idev = __in_dev_get_rcu(state->dev); if (!state->idev) continue; read_lock(&state->idev->mc_list_lock); @@ -2528,8 +2525,9 @@ static struct ip_sf_list *igmp_mcf_get_idx(struct seq_file *seq, loff_t pos) } static void *igmp_mcf_seq_start(struct seq_file *seq, loff_t *pos) + __acquires(rcu) { - read_lock(&dev_base_lock); + rcu_read_lock(); return *pos ? igmp_mcf_get_idx(seq, *pos - 1) : SEQ_START_TOKEN; } @@ -2545,6 +2543,7 @@ static void *igmp_mcf_seq_next(struct seq_file *seq, void *v, loff_t *pos) } static void igmp_mcf_seq_stop(struct seq_file *seq, void *v) + __releases(rcu) { struct igmp_mcf_iter_state *state = igmp_mcf_seq_private(seq); if (likely(state->im != NULL)) { @@ -2553,11 +2552,10 @@ static void igmp_mcf_seq_stop(struct seq_file *seq, void *v) } if (likely(state->idev != NULL)) { read_unlock(&state->idev->mc_list_lock); - in_dev_put(state->idev); state->idev = NULL; } state->dev = NULL; - read_unlock(&dev_base_lock); + rcu_read_unlock(); } static int igmp_mcf_seq_show(struct seq_file *seq, void *v) diff --git a/net/ipv4/inet_connection_sock.c b/net/ipv4/inet_connection_sock.c index 537731b3bcb3..ee16475f8fc3 100644 --- a/net/ipv4/inet_connection_sock.c +++ b/net/ipv4/inet_connection_sock.c @@ -112,7 +112,7 @@ again: hashinfo->bhash_size)]; spin_lock(&head->lock); inet_bind_bucket_for_each(tb, node, &head->chain) - if (ib_net(tb) == net && tb->port == rover) { + if (net_eq(ib_net(tb), net) && tb->port == rover) { if (tb->fastreuse > 0 && sk->sk_reuse && sk->sk_state != TCP_LISTEN && @@ -158,7 +158,7 @@ have_snum: hashinfo->bhash_size)]; spin_lock(&head->lock); inet_bind_bucket_for_each(tb, node, &head->chain) - if (ib_net(tb) == net && tb->port == snum) + if (net_eq(ib_net(tb), net) && tb->port == snum) goto tb_found; } tb = NULL; @@ -358,6 +358,7 @@ struct dst_entry *inet_csk_route_req(struct sock *sk, const struct inet_request_sock *ireq = inet_rsk(req); struct ip_options *opt = inet_rsk(req)->opt; struct flowi fl = { .oif = sk->sk_bound_dev_if, + .mark = sk->sk_mark, .nl_u = { .ip4_u = { .daddr = ((opt && opt->srr) ? opt->faddr : @@ -367,7 +368,7 @@ struct dst_entry *inet_csk_route_req(struct sock *sk, .proto = sk->sk_protocol, .flags = inet_sk_flowi_flags(sk), .uli_u = { .ports = - { .sport = inet_sk(sk)->sport, + { .sport = inet_sk(sk)->inet_sport, .dport = ireq->rmt_port } } }; struct net *net = sock_net(sk); @@ -530,7 +531,7 @@ void inet_csk_reqsk_queue_prune(struct sock *parent, &expire, &resend); if (!expire && (!resend || - !req->rsk_ops->rtx_syn_ack(parent, req) || + !req->rsk_ops->rtx_syn_ack(parent, req, NULL) || inet_rsk(req)->acked)) { unsigned long timeo; @@ -574,9 +575,9 @@ struct sock *inet_csk_clone(struct sock *sk, const struct request_sock *req, newsk->sk_state = TCP_SYN_RECV; newicsk->icsk_bind_hash = NULL; - inet_sk(newsk)->dport = inet_rsk(req)->rmt_port; - inet_sk(newsk)->num = ntohs(inet_rsk(req)->loc_port); - inet_sk(newsk)->sport = inet_rsk(req)->loc_port; + inet_sk(newsk)->inet_dport = inet_rsk(req)->rmt_port; + inet_sk(newsk)->inet_num = ntohs(inet_rsk(req)->loc_port); + inet_sk(newsk)->inet_sport = inet_rsk(req)->loc_port; newsk->sk_write_space = sk_stream_write_space; newicsk->icsk_retransmits = 0; @@ -607,8 +608,8 @@ void inet_csk_destroy_sock(struct sock *sk) /* It cannot be in hash table! */ WARN_ON(!sk_unhashed(sk)); - /* If it has not 0 inet_sk(sk)->num, it must be bound */ - WARN_ON(inet_sk(sk)->num && !inet_csk(sk)->icsk_bind_hash); + /* If it has not 0 inet_sk(sk)->inet_num, it must be bound */ + WARN_ON(inet_sk(sk)->inet_num && !inet_csk(sk)->icsk_bind_hash); sk->sk_prot->destroy(sk); @@ -643,8 +644,8 @@ int inet_csk_listen_start(struct sock *sk, const int nr_table_entries) * after validation is complete. */ sk->sk_state = TCP_LISTEN; - if (!sk->sk_prot->get_port(sk, inet->num)) { - inet->sport = htons(inet->num); + if (!sk->sk_prot->get_port(sk, inet->inet_num)) { + inet->inet_sport = htons(inet->inet_num); sk_dst_reset(sk); sk->sk_prot->hash(sk); @@ -720,8 +721,8 @@ void inet_csk_addr2sockaddr(struct sock *sk, struct sockaddr *uaddr) const struct inet_sock *inet = inet_sk(sk); sin->sin_family = AF_INET; - sin->sin_addr.s_addr = inet->daddr; - sin->sin_port = inet->dport; + sin->sin_addr.s_addr = inet->inet_daddr; + sin->sin_port = inet->inet_dport; } EXPORT_SYMBOL_GPL(inet_csk_addr2sockaddr); diff --git a/net/ipv4/inet_diag.c b/net/ipv4/inet_diag.c index a706a47f4dbb..bdb78dd180ce 100644 --- a/net/ipv4/inet_diag.c +++ b/net/ipv4/inet_diag.c @@ -116,10 +116,10 @@ static int inet_csk_diag_fill(struct sock *sk, r->id.idiag_cookie[0] = (u32)(unsigned long)sk; r->id.idiag_cookie[1] = (u32)(((unsigned long)sk >> 31) >> 1); - r->id.idiag_sport = inet->sport; - r->id.idiag_dport = inet->dport; - r->id.idiag_src[0] = inet->rcv_saddr; - r->id.idiag_dst[0] = inet->daddr; + r->id.idiag_sport = inet->inet_sport; + r->id.idiag_dport = inet->inet_dport; + r->id.idiag_src[0] = inet->inet_rcv_saddr; + r->id.idiag_dst[0] = inet->inet_daddr; #if defined(CONFIG_IPV6) || defined (CONFIG_IPV6_MODULE) if (r->idiag_family == AF_INET6) { @@ -504,11 +504,11 @@ static int inet_csk_diag_dump(struct sock *sk, } else #endif { - entry.saddr = &inet->rcv_saddr; - entry.daddr = &inet->daddr; + entry.saddr = &inet->inet_rcv_saddr; + entry.daddr = &inet->inet_daddr; } - entry.sport = inet->num; - entry.dport = ntohs(inet->dport); + entry.sport = inet->inet_num; + entry.dport = ntohs(inet->inet_dport); entry.userlocks = sk->sk_userlocks; if (!inet_diag_bc_run(RTA_DATA(bc), RTA_PAYLOAD(bc), &entry)) @@ -584,7 +584,7 @@ static int inet_diag_fill_req(struct sk_buff *skb, struct sock *sk, if (tmo < 0) tmo = 0; - r->id.idiag_sport = inet->sport; + r->id.idiag_sport = inet->inet_sport; r->id.idiag_dport = ireq->rmt_port; r->id.idiag_src[0] = ireq->loc_addr; r->id.idiag_dst[0] = ireq->rmt_addr; @@ -639,7 +639,7 @@ static int inet_diag_dump_reqs(struct sk_buff *skb, struct sock *sk, if (cb->nlh->nlmsg_len > 4 + NLMSG_SPACE(sizeof(*r))) { bc = (struct rtattr *)(r + 1); - entry.sport = inet->num; + entry.sport = inet->inet_num; entry.userlocks = sk->sk_userlocks; } @@ -732,7 +732,7 @@ static int inet_diag_dump(struct sk_buff *skb, struct netlink_callback *cb) continue; } - if (r->id.idiag_sport != inet->sport && + if (r->id.idiag_sport != inet->inet_sport && r->id.idiag_sport) goto next_listen; @@ -774,7 +774,7 @@ skip_listen_ht: if (!(r->idiag_states & ~(TCPF_LISTEN | TCPF_SYN_RECV))) goto unlock; - for (i = s_i; i < hashinfo->ehash_size; i++) { + for (i = s_i; i <= hashinfo->ehash_mask; i++) { struct inet_ehash_bucket *head = &hashinfo->ehash[i]; spinlock_t *lock = inet_ehash_lockp(hashinfo, i); struct sock *sk; @@ -797,10 +797,10 @@ skip_listen_ht: goto next_normal; if (!(r->idiag_states & (1 << sk->sk_state))) goto next_normal; - if (r->id.idiag_sport != inet->sport && + if (r->id.idiag_sport != inet->inet_sport && r->id.idiag_sport) goto next_normal; - if (r->id.idiag_dport != inet->dport && + if (r->id.idiag_dport != inet->inet_dport && r->id.idiag_dport) goto next_normal; if (inet_csk_diag_dump(sk, skb, cb) < 0) { diff --git a/net/ipv4/inet_hashtables.c b/net/ipv4/inet_hashtables.c index 625cc5f64c94..21e5e32d8c60 100644 --- a/net/ipv4/inet_hashtables.c +++ b/net/ipv4/inet_hashtables.c @@ -64,7 +64,7 @@ void inet_bind_hash(struct sock *sk, struct inet_bind_bucket *tb, atomic_inc(&hashinfo->bsockets); - inet_sk(sk)->num = snum; + inet_sk(sk)->inet_num = snum; sk_add_bind_node(sk, &tb->owners); tb->num_owners++; inet_csk(sk)->icsk_bind_hash = tb; @@ -76,7 +76,7 @@ void inet_bind_hash(struct sock *sk, struct inet_bind_bucket *tb, static void __inet_put_port(struct sock *sk) { struct inet_hashinfo *hashinfo = sk->sk_prot->h.hashinfo; - const int bhash = inet_bhashfn(sock_net(sk), inet_sk(sk)->num, + const int bhash = inet_bhashfn(sock_net(sk), inet_sk(sk)->inet_num, hashinfo->bhash_size); struct inet_bind_hashbucket *head = &hashinfo->bhash[bhash]; struct inet_bind_bucket *tb; @@ -88,7 +88,7 @@ static void __inet_put_port(struct sock *sk) __sk_del_bind_node(sk); tb->num_owners--; inet_csk(sk)->icsk_bind_hash = NULL; - inet_sk(sk)->num = 0; + inet_sk(sk)->inet_num = 0; inet_bind_bucket_destroy(hashinfo->bind_bucket_cachep, tb); spin_unlock(&head->lock); } @@ -105,7 +105,7 @@ EXPORT_SYMBOL(inet_put_port); void __inet_inherit_port(struct sock *sk, struct sock *child) { struct inet_hashinfo *table = sk->sk_prot->h.hashinfo; - const int bhash = inet_bhashfn(sock_net(sk), inet_sk(child)->num, + const int bhash = inet_bhashfn(sock_net(sk), inet_sk(child)->inet_num, table->bhash_size); struct inet_bind_hashbucket *head = &table->bhash[bhash]; struct inet_bind_bucket *tb; @@ -126,9 +126,9 @@ static inline int compute_score(struct sock *sk, struct net *net, int score = -1; struct inet_sock *inet = inet_sk(sk); - if (net_eq(sock_net(sk), net) && inet->num == hnum && + if (net_eq(sock_net(sk), net) && inet->inet_num == hnum && !ipv6_only_sock(sk)) { - __be32 rcv_saddr = inet->rcv_saddr; + __be32 rcv_saddr = inet->inet_rcv_saddr; score = sk->sk_family == PF_INET ? 1 : 0; if (rcv_saddr) { if (rcv_saddr != daddr) @@ -209,7 +209,7 @@ struct sock * __inet_lookup_established(struct net *net, * have wildcards anyways. */ unsigned int hash = inet_ehashfn(net, daddr, hnum, saddr, sport); - unsigned int slot = hash & (hashinfo->ehash_size - 1); + unsigned int slot = hash & hashinfo->ehash_mask; struct inet_ehash_bucket *head = &hashinfo->ehash[slot]; rcu_read_lock(); @@ -273,18 +273,20 @@ static int __inet_check_established(struct inet_timewait_death_row *death_row, { struct inet_hashinfo *hinfo = death_row->hashinfo; struct inet_sock *inet = inet_sk(sk); - __be32 daddr = inet->rcv_saddr; - __be32 saddr = inet->daddr; + __be32 daddr = inet->inet_rcv_saddr; + __be32 saddr = inet->inet_daddr; int dif = sk->sk_bound_dev_if; INET_ADDR_COOKIE(acookie, saddr, daddr) - const __portpair ports = INET_COMBINED_PORTS(inet->dport, lport); + const __portpair ports = INET_COMBINED_PORTS(inet->inet_dport, lport); struct net *net = sock_net(sk); - unsigned int hash = inet_ehashfn(net, daddr, lport, saddr, inet->dport); + unsigned int hash = inet_ehashfn(net, daddr, lport, + saddr, inet->inet_dport); struct inet_ehash_bucket *head = inet_ehash_bucket(hinfo, hash); spinlock_t *lock = inet_ehash_lockp(hinfo, hash); struct sock *sk2; const struct hlist_nulls_node *node; struct inet_timewait_sock *tw; + int twrefcnt = 0; spin_lock(lock); @@ -312,25 +314,28 @@ static int __inet_check_established(struct inet_timewait_death_row *death_row, unique: /* Must record num and sport now. Otherwise we will see * in hash table socket with a funny identity. */ - inet->num = lport; - inet->sport = htons(lport); + inet->inet_num = lport; + inet->inet_sport = htons(lport); sk->sk_hash = hash; WARN_ON(!sk_unhashed(sk)); __sk_nulls_add_node_rcu(sk, &head->chain); + if (tw) { + twrefcnt = inet_twsk_unhash(tw); + NET_INC_STATS_BH(net, LINUX_MIB_TIMEWAITRECYCLED); + } spin_unlock(lock); + if (twrefcnt) + inet_twsk_put(tw); sock_prot_inuse_add(sock_net(sk), sk->sk_prot, 1); if (twp) { *twp = tw; - NET_INC_STATS_BH(net, LINUX_MIB_TIMEWAITRECYCLED); } else if (tw) { /* Silly. Should hash-dance instead... */ inet_twsk_deschedule(tw, death_row); - NET_INC_STATS_BH(net, LINUX_MIB_TIMEWAITRECYCLED); inet_twsk_put(tw); } - return 0; not_unique: @@ -341,8 +346,9 @@ not_unique: static inline u32 inet_sk_port_offset(const struct sock *sk) { const struct inet_sock *inet = inet_sk(sk); - return secure_ipv4_port_ephemeral(inet->rcv_saddr, inet->daddr, - inet->dport); + return secure_ipv4_port_ephemeral(inet->inet_rcv_saddr, + inet->inet_daddr, + inet->inet_dport); } void __inet_hash_nolisten(struct sock *sk) @@ -424,7 +430,7 @@ int __inet_hash_connect(struct inet_timewait_death_row *death_row, void (*hash)(struct sock *sk)) { struct inet_hashinfo *hinfo = death_row->hashinfo; - const unsigned short snum = inet_sk(sk)->num; + const unsigned short snum = inet_sk(sk)->inet_num; struct inet_bind_hashbucket *head; struct inet_bind_bucket *tb; int ret; @@ -452,7 +458,8 @@ int __inet_hash_connect(struct inet_timewait_death_row *death_row, * unique enough. */ inet_bind_bucket_for_each(tb, node, &head->chain) { - if (ib_net(tb) == net && tb->port == port) { + if (net_eq(ib_net(tb), net) && + tb->port == port) { if (tb->fastreuse >= 0) goto next_port; WARN_ON(hlist_empty(&tb->owners)); @@ -485,7 +492,7 @@ ok: /* Head lock still held and bh's disabled */ inet_bind_hash(sk, tb, port); if (sk_unhashed(sk)) { - inet_sk(sk)->sport = htons(port); + inet_sk(sk)->inet_sport = htons(port); hash(sk); } spin_unlock(&head->lock); diff --git a/net/ipv4/inet_lro.c b/net/ipv4/inet_lro.c index 6a667dae315e..47038cb6c138 100644 --- a/net/ipv4/inet_lro.c +++ b/net/ipv4/inet_lro.c @@ -64,15 +64,15 @@ static int lro_tcp_ip_check(struct iphdr *iph, struct tcphdr *tcph, if (iph->ihl != IPH_LEN_WO_OPTIONS) return -1; - if (tcph->cwr || tcph->ece || tcph->urg || !tcph->ack - || tcph->rst || tcph->syn || tcph->fin) + if (tcph->cwr || tcph->ece || tcph->urg || !tcph->ack || + tcph->rst || tcph->syn || tcph->fin) return -1; if (INET_ECN_is_ce(ipv4_get_dsfield(iph))) return -1; - if (tcph->doff != TCPH_LEN_WO_OPTIONS - && tcph->doff != TCPH_LEN_W_TIMESTAMP) + if (tcph->doff != TCPH_LEN_WO_OPTIONS && + tcph->doff != TCPH_LEN_W_TIMESTAMP) return -1; /* check tcp options (only timestamp allowed) */ @@ -262,10 +262,10 @@ static int lro_check_tcp_conn(struct net_lro_desc *lro_desc, struct iphdr *iph, struct tcphdr *tcph) { - if ((lro_desc->iph->saddr != iph->saddr) - || (lro_desc->iph->daddr != iph->daddr) - || (lro_desc->tcph->source != tcph->source) - || (lro_desc->tcph->dest != tcph->dest)) + if ((lro_desc->iph->saddr != iph->saddr) || + (lro_desc->iph->daddr != iph->daddr) || + (lro_desc->tcph->source != tcph->source) || + (lro_desc->tcph->dest != tcph->dest)) return -1; return 0; } @@ -339,9 +339,9 @@ static int __lro_proc_skb(struct net_lro_mgr *lro_mgr, struct sk_buff *skb, u64 flags; int vlan_hdr_len = 0; - if (!lro_mgr->get_skb_header - || lro_mgr->get_skb_header(skb, (void *)&iph, (void *)&tcph, - &flags, priv)) + if (!lro_mgr->get_skb_header || + lro_mgr->get_skb_header(skb, (void *)&iph, (void *)&tcph, + &flags, priv)) goto out; if (!(flags & LRO_IPV4) || !(flags & LRO_TCP)) @@ -351,8 +351,8 @@ static int __lro_proc_skb(struct net_lro_mgr *lro_mgr, struct sk_buff *skb, if (!lro_desc) goto out; - if ((skb->protocol == htons(ETH_P_8021Q)) - && !(lro_mgr->features & LRO_F_EXTRACT_VLAN_ID)) + if ((skb->protocol == htons(ETH_P_8021Q)) && + !(lro_mgr->features & LRO_F_EXTRACT_VLAN_ID)) vlan_hdr_len = VLAN_HLEN; if (!lro_desc->active) { /* start new lro session */ @@ -446,9 +446,9 @@ static struct sk_buff *__lro_proc_segment(struct net_lro_mgr *lro_mgr, int hdr_len = LRO_MAX_PG_HLEN; int vlan_hdr_len = 0; - if (!lro_mgr->get_frag_header - || lro_mgr->get_frag_header(frags, (void *)&mac_hdr, (void *)&iph, - (void *)&tcph, &flags, priv)) { + if (!lro_mgr->get_frag_header || + lro_mgr->get_frag_header(frags, (void *)&mac_hdr, (void *)&iph, + (void *)&tcph, &flags, priv)) { mac_hdr = page_address(frags->page) + frags->page_offset; goto out1; } @@ -472,8 +472,8 @@ static struct sk_buff *__lro_proc_segment(struct net_lro_mgr *lro_mgr, if (!skb) goto out; - if ((skb->protocol == htons(ETH_P_8021Q)) - && !(lro_mgr->features & LRO_F_EXTRACT_VLAN_ID)) + if ((skb->protocol == htons(ETH_P_8021Q)) && + !(lro_mgr->features & LRO_F_EXTRACT_VLAN_ID)) vlan_hdr_len = VLAN_HLEN; iph = (void *)(skb->data + vlan_hdr_len); diff --git a/net/ipv4/inet_timewait_sock.c b/net/ipv4/inet_timewait_sock.c index 13f0781f35cd..0fdf45e4c90c 100644 --- a/net/ipv4/inet_timewait_sock.c +++ b/net/ipv4/inet_timewait_sock.c @@ -14,22 +14,33 @@ #include <net/inet_timewait_sock.h> #include <net/ip.h> + +/* + * unhash a timewait socket from established hash + * lock must be hold by caller + */ +int inet_twsk_unhash(struct inet_timewait_sock *tw) +{ + if (hlist_nulls_unhashed(&tw->tw_node)) + return 0; + + hlist_nulls_del_rcu(&tw->tw_node); + sk_nulls_node_init(&tw->tw_node); + return 1; +} + /* Must be called with locally disabled BHs. */ static void __inet_twsk_kill(struct inet_timewait_sock *tw, struct inet_hashinfo *hashinfo) { struct inet_bind_hashbucket *bhead; struct inet_bind_bucket *tb; + int refcnt; /* Unlink from established hashes. */ spinlock_t *lock = inet_ehash_lockp(hashinfo, tw->tw_hash); spin_lock(lock); - if (hlist_nulls_unhashed(&tw->tw_node)) { - spin_unlock(lock); - return; - } - hlist_nulls_del_rcu(&tw->tw_node); - sk_nulls_node_init(&tw->tw_node); + refcnt = inet_twsk_unhash(tw); spin_unlock(lock); /* Disassociate with bind bucket. */ @@ -37,9 +48,12 @@ static void __inet_twsk_kill(struct inet_timewait_sock *tw, hashinfo->bhash_size)]; spin_lock(&bhead->lock); tb = tw->tw_tb; - __hlist_del(&tw->tw_bind_node); - tw->tw_tb = NULL; - inet_bind_bucket_destroy(hashinfo->bind_bucket_cachep, tb); + if (tb) { + __hlist_del(&tw->tw_bind_node); + tw->tw_tb = NULL; + inet_bind_bucket_destroy(hashinfo->bind_bucket_cachep, tb); + refcnt++; + } spin_unlock(&bhead->lock); #ifdef SOCK_REFCNT_DEBUG if (atomic_read(&tw->tw_refcnt) != 1) { @@ -47,7 +61,10 @@ static void __inet_twsk_kill(struct inet_timewait_sock *tw, tw->tw_prot->name, tw, atomic_read(&tw->tw_refcnt)); } #endif - inet_twsk_put(tw); + while (refcnt) { + inet_twsk_put(tw); + refcnt--; + } } static noinline void inet_twsk_free(struct inet_timewait_sock *tw) @@ -86,7 +103,7 @@ void __inet_twsk_hashdance(struct inet_timewait_sock *tw, struct sock *sk, Note, that any socket with inet->num != 0 MUST be bound in binding cache, even if it is closed. */ - bhead = &hashinfo->bhash[inet_bhashfn(twsk_net(tw), inet->num, + bhead = &hashinfo->bhash[inet_bhashfn(twsk_net(tw), inet->inet_num, hashinfo->bhash_size)]; spin_lock(&bhead->lock); tw->tw_tb = icsk->icsk_bind_hash; @@ -101,13 +118,22 @@ void __inet_twsk_hashdance(struct inet_timewait_sock *tw, struct sock *sk, * Should be done before removing sk from established chain * because readers are lockless and search established first. */ - atomic_inc(&tw->tw_refcnt); inet_twsk_add_node_rcu(tw, &ehead->twchain); /* Step 3: Remove SK from established hash. */ if (__sk_nulls_del_node_init_rcu(sk)) sock_prot_inuse_add(sock_net(sk), sk->sk_prot, -1); + /* + * Notes : + * - We initially set tw_refcnt to 0 in inet_twsk_alloc() + * - We add one reference for the bhash link + * - We add one reference for the ehash link + * - We want this refcnt update done before allowing other + * threads to find this tw in ehash chain. + */ + atomic_add(1 + 1 + 1, &tw->tw_refcnt); + spin_unlock(lock); } @@ -124,14 +150,14 @@ struct inet_timewait_sock *inet_twsk_alloc(const struct sock *sk, const int stat kmemcheck_annotate_bitfield(tw, flags); /* Give us an identity. */ - tw->tw_daddr = inet->daddr; - tw->tw_rcv_saddr = inet->rcv_saddr; + tw->tw_daddr = inet->inet_daddr; + tw->tw_rcv_saddr = inet->inet_rcv_saddr; tw->tw_bound_dev_if = sk->sk_bound_dev_if; - tw->tw_num = inet->num; + tw->tw_num = inet->inet_num; tw->tw_state = TCP_TIME_WAIT; tw->tw_substate = state; - tw->tw_sport = inet->sport; - tw->tw_dport = inet->dport; + tw->tw_sport = inet->inet_sport; + tw->tw_dport = inet->inet_dport; tw->tw_family = sk->sk_family; tw->tw_reuse = sk->sk_reuse; tw->tw_hash = sk->sk_hash; @@ -139,7 +165,12 @@ struct inet_timewait_sock *inet_twsk_alloc(const struct sock *sk, const int stat tw->tw_transparent = inet->transparent; tw->tw_prot = sk->sk_prot_creator; twsk_net_set(tw, hold_net(sock_net(sk))); - atomic_set(&tw->tw_refcnt, 1); + /* + * Because we use RCU lookups, we should not set tw_refcnt + * to a non null value before everything is setup for this + * timewait socket. + */ + atomic_set(&tw->tw_refcnt, 0); inet_twsk_dead_node_init(tw); __module_get(tw->tw_prot->owner); } @@ -421,37 +452,46 @@ out: EXPORT_SYMBOL_GPL(inet_twdr_twcal_tick); -void inet_twsk_purge(struct net *net, struct inet_hashinfo *hashinfo, +void inet_twsk_purge(struct inet_hashinfo *hashinfo, struct inet_timewait_death_row *twdr, int family) { struct inet_timewait_sock *tw; struct sock *sk; struct hlist_nulls_node *node; - int h; + unsigned int slot; - local_bh_disable(); - for (h = 0; h < (hashinfo->ehash_size); h++) { - struct inet_ehash_bucket *head = - inet_ehash_bucket(hashinfo, h); - spinlock_t *lock = inet_ehash_lockp(hashinfo, h); + for (slot = 0; slot <= hashinfo->ehash_mask; slot++) { + struct inet_ehash_bucket *head = &hashinfo->ehash[slot]; +restart_rcu: + rcu_read_lock(); restart: - spin_lock(lock); - sk_nulls_for_each(sk, node, &head->twchain) { - + sk_nulls_for_each_rcu(sk, node, &head->twchain) { tw = inet_twsk(sk); - if (!net_eq(twsk_net(tw), net) || - tw->tw_family != family) + if ((tw->tw_family != family) || + atomic_read(&twsk_net(tw)->count)) + continue; + + if (unlikely(!atomic_inc_not_zero(&tw->tw_refcnt))) continue; - atomic_inc(&tw->tw_refcnt); - spin_unlock(lock); + if (unlikely((tw->tw_family != family) || + atomic_read(&twsk_net(tw)->count))) { + inet_twsk_put(tw); + goto restart; + } + + rcu_read_unlock(); inet_twsk_deschedule(tw, twdr); inet_twsk_put(tw); - - goto restart; + goto restart_rcu; } - spin_unlock(lock); + /* If the nulls value we got at the end of this lookup is + * not the expected one, we must restart lookup. + * We probably met an item that was moved to another chain. + */ + if (get_nulls_value(node) != slot) + goto restart; + rcu_read_unlock(); } - local_bh_enable(); } EXPORT_SYMBOL_GPL(inet_twsk_purge); diff --git a/net/ipv4/inetpeer.c b/net/ipv4/inetpeer.c index b1fbe18feb5a..6bcfe52a9c87 100644 --- a/net/ipv4/inetpeer.c +++ b/net/ipv4/inetpeer.c @@ -67,9 +67,6 @@ * ip_id_count: idlock */ -/* Exported for inet_getid inline function. */ -DEFINE_SPINLOCK(inet_peer_idlock); - static struct kmem_cache *peer_cachep __read_mostly; #define node_height(x) x->avl_height @@ -390,7 +387,7 @@ struct inet_peer *inet_getpeer(__be32 daddr, int create) n->v4daddr = daddr; atomic_set(&n->refcnt, 1); atomic_set(&n->rid, 0); - n->ip_id_count = secure_ip_id(daddr); + atomic_set(&n->ip_id_count, secure_ip_id(daddr)); n->tcp_ts_stamp = 0; write_lock_bh(&peer_pool_lock); diff --git a/net/ipv4/ip_fragment.c b/net/ipv4/ip_fragment.c index 301a389fa7fa..86964b353c31 100644 --- a/net/ipv4/ip_fragment.c +++ b/net/ipv4/ip_fragment.c @@ -206,10 +206,11 @@ static void ip_expire(unsigned long arg) struct sk_buff *head = qp->q.fragments; /* Send an ICMP "Fragment Reassembly Timeout" message. */ - if ((head->dev = dev_get_by_index(net, qp->iif)) != NULL) { + rcu_read_lock(); + head->dev = dev_get_by_index_rcu(net, qp->iif); + if (head->dev) icmp_send(head, ICMP_TIME_EXCEEDED, ICMP_EXC_FRAGTIME, 0); - dev_put(head->dev); - } + rcu_read_unlock(); } out: spin_unlock(&qp->q.lock); @@ -651,7 +652,7 @@ static int ip4_frags_ns_ctl_register(struct net *net) struct ctl_table_header *hdr; table = ip4_frags_ns_ctl_table; - if (net != &init_net) { + if (!net_eq(net, &init_net)) { table = kmemdup(table, sizeof(ip4_frags_ns_ctl_table), GFP_KERNEL); if (table == NULL) goto err_alloc; @@ -669,7 +670,7 @@ static int ip4_frags_ns_ctl_register(struct net *net) return 0; err_reg: - if (net != &init_net) + if (!net_eq(net, &init_net)) kfree(table); err_alloc: return -ENOMEM; diff --git a/net/ipv4/ip_gre.c b/net/ipv4/ip_gre.c index 143333852624..f36ce156cac6 100644 --- a/net/ipv4/ip_gre.c +++ b/net/ipv4/ip_gre.c @@ -125,7 +125,7 @@ static int ipgre_tunnel_bind_dev(struct net_device *dev); #define HASH_SIZE 16 -static int ipgre_net_id; +static int ipgre_net_id __read_mostly; struct ipgre_net { struct ip_tunnel *tunnels[4][HASH_SIZE]; @@ -156,8 +156,13 @@ struct ipgre_net { #define tunnels_r tunnels[2] #define tunnels_l tunnels[1] #define tunnels_wc tunnels[0] +/* + * Locking : hash tables are protected by RCU and a spinlock + */ +static DEFINE_SPINLOCK(ipgre_lock); -static DEFINE_RWLOCK(ipgre_lock); +#define for_each_ip_tunnel_rcu(start) \ + for (t = rcu_dereference(start); t; t = rcu_dereference(t->next)) /* Given src, dst and key, find appropriate for input tunnel. */ @@ -175,7 +180,7 @@ static struct ip_tunnel * ipgre_tunnel_lookup(struct net_device *dev, ARPHRD_ETHER : ARPHRD_IPGRE; int score, cand_score = 4; - for (t = ign->tunnels_r_l[h0^h1]; t; t = t->next) { + for_each_ip_tunnel_rcu(ign->tunnels_r_l[h0 ^ h1]) { if (local != t->parms.iph.saddr || remote != t->parms.iph.daddr || key != t->parms.i_key || @@ -200,7 +205,7 @@ static struct ip_tunnel * ipgre_tunnel_lookup(struct net_device *dev, } } - for (t = ign->tunnels_r[h0^h1]; t; t = t->next) { + for_each_ip_tunnel_rcu(ign->tunnels_r[h0 ^ h1]) { if (remote != t->parms.iph.daddr || key != t->parms.i_key || !(t->dev->flags & IFF_UP)) @@ -224,7 +229,7 @@ static struct ip_tunnel * ipgre_tunnel_lookup(struct net_device *dev, } } - for (t = ign->tunnels_l[h1]; t; t = t->next) { + for_each_ip_tunnel_rcu(ign->tunnels_l[h1]) { if ((local != t->parms.iph.saddr && (local != t->parms.iph.daddr || !ipv4_is_multicast(local))) || @@ -250,7 +255,7 @@ static struct ip_tunnel * ipgre_tunnel_lookup(struct net_device *dev, } } - for (t = ign->tunnels_wc[h1]; t; t = t->next) { + for_each_ip_tunnel_rcu(ign->tunnels_wc[h1]) { if (t->parms.i_key != key || !(t->dev->flags & IFF_UP)) continue; @@ -276,8 +281,9 @@ static struct ip_tunnel * ipgre_tunnel_lookup(struct net_device *dev, if (cand != NULL) return cand; - if (ign->fb_tunnel_dev->flags & IFF_UP) - return netdev_priv(ign->fb_tunnel_dev); + dev = ign->fb_tunnel_dev; + if (dev->flags & IFF_UP) + return netdev_priv(dev); return NULL; } @@ -311,10 +317,10 @@ static void ipgre_tunnel_link(struct ipgre_net *ign, struct ip_tunnel *t) { struct ip_tunnel **tp = ipgre_bucket(ign, t); + spin_lock_bh(&ipgre_lock); t->next = *tp; - write_lock_bh(&ipgre_lock); - *tp = t; - write_unlock_bh(&ipgre_lock); + rcu_assign_pointer(*tp, t); + spin_unlock_bh(&ipgre_lock); } static void ipgre_tunnel_unlink(struct ipgre_net *ign, struct ip_tunnel *t) @@ -323,9 +329,9 @@ static void ipgre_tunnel_unlink(struct ipgre_net *ign, struct ip_tunnel *t) for (tp = ipgre_bucket(ign, t); *tp; tp = &(*tp)->next) { if (t == *tp) { - write_lock_bh(&ipgre_lock); + spin_lock_bh(&ipgre_lock); *tp = t->next; - write_unlock_bh(&ipgre_lock); + spin_unlock_bh(&ipgre_lock); break; } } @@ -476,7 +482,7 @@ static void ipgre_err(struct sk_buff *skb, u32 info) break; } - read_lock(&ipgre_lock); + rcu_read_lock(); t = ipgre_tunnel_lookup(skb->dev, iph->daddr, iph->saddr, flags & GRE_KEY ? *(((__be32 *)p) + (grehlen / 4) - 1) : 0, @@ -494,7 +500,7 @@ static void ipgre_err(struct sk_buff *skb, u32 info) t->err_count = 1; t->err_time = jiffies; out: - read_unlock(&ipgre_lock); + rcu_read_unlock(); return; } @@ -573,7 +579,7 @@ static int ipgre_rcv(struct sk_buff *skb) gre_proto = *(__be16 *)(h + 2); - read_lock(&ipgre_lock); + rcu_read_lock(); if ((tunnel = ipgre_tunnel_lookup(skb->dev, iph->saddr, iph->daddr, key, gre_proto))) { @@ -647,13 +653,13 @@ static int ipgre_rcv(struct sk_buff *skb) ipgre_ecn_decapsulate(iph, skb); netif_rx(skb); - read_unlock(&ipgre_lock); + rcu_read_unlock(); return(0); } icmp_send(skb, ICMP_DEST_UNREACH, ICMP_PORT_UNREACH, 0); drop: - read_unlock(&ipgre_lock); + rcu_read_unlock(); drop_nolock: kfree_skb(skb); return(0); @@ -662,7 +668,8 @@ drop_nolock: static netdev_tx_t ipgre_tunnel_xmit(struct sk_buff *skb, struct net_device *dev) { struct ip_tunnel *tunnel = netdev_priv(dev); - struct net_device_stats *stats = &tunnel->dev->stats; + struct net_device_stats *stats = &dev->stats; + struct netdev_queue *txq = netdev_get_tx_queue(dev, 0); struct iphdr *old_iph = ip_hdr(skb); struct iphdr *tiph; u8 tos; @@ -810,7 +817,7 @@ static netdev_tx_t ipgre_tunnel_xmit(struct sk_buff *skb, struct net_device *dev struct sk_buff *new_skb = skb_realloc_headroom(skb, max_headroom); if (!new_skb) { ip_rt_put(rt); - stats->tx_dropped++; + txq->tx_dropped++; dev_kfree_skb(skb); return NETDEV_TX_OK; } @@ -1283,33 +1290,27 @@ static const struct net_protocol ipgre_protocol = { .netns_ok = 1, }; -static void ipgre_destroy_tunnels(struct ipgre_net *ign) +static void ipgre_destroy_tunnels(struct ipgre_net *ign, struct list_head *head) { int prio; for (prio = 0; prio < 4; prio++) { int h; for (h = 0; h < HASH_SIZE; h++) { - struct ip_tunnel *t; - while ((t = ign->tunnels[prio][h]) != NULL) - unregister_netdevice(t->dev); + struct ip_tunnel *t = ign->tunnels[prio][h]; + + while (t != NULL) { + unregister_netdevice_queue(t->dev, head); + t = t->next; + } } } } static int ipgre_init_net(struct net *net) { + struct ipgre_net *ign = net_generic(net, ipgre_net_id); int err; - struct ipgre_net *ign; - - err = -ENOMEM; - ign = kzalloc(sizeof(struct ipgre_net), GFP_KERNEL); - if (ign == NULL) - goto err_alloc; - - err = net_assign_generic(net, ipgre_net_id, ign); - if (err < 0) - goto err_assign; ign->fb_tunnel_dev = alloc_netdev(sizeof(struct ip_tunnel), "gre0", ipgre_tunnel_setup); @@ -1330,27 +1331,26 @@ static int ipgre_init_net(struct net *net) err_reg_dev: free_netdev(ign->fb_tunnel_dev); err_alloc_dev: - /* nothing */ -err_assign: - kfree(ign); -err_alloc: return err; } static void ipgre_exit_net(struct net *net) { struct ipgre_net *ign; + LIST_HEAD(list); ign = net_generic(net, ipgre_net_id); rtnl_lock(); - ipgre_destroy_tunnels(ign); + ipgre_destroy_tunnels(ign, &list); + unregister_netdevice_many(&list); rtnl_unlock(); - kfree(ign); } static struct pernet_operations ipgre_net_ops = { .init = ipgre_init_net, .exit = ipgre_exit_net, + .id = &ipgre_net_id, + .size = sizeof(struct ipgre_net), }; static int ipgre_tunnel_validate(struct nlattr *tb[], struct nlattr *data[]) @@ -1471,7 +1471,7 @@ static void ipgre_tap_setup(struct net_device *dev) dev->features |= NETIF_F_NETNS_LOCAL; } -static int ipgre_newlink(struct net_device *dev, struct nlattr *tb[], +static int ipgre_newlink(struct net *src_net, struct net_device *dev, struct nlattr *tb[], struct nlattr *data[]) { struct ip_tunnel *nt; @@ -1670,7 +1670,7 @@ static int __init ipgre_init(void) return -EAGAIN; } - err = register_pernet_gen_device(&ipgre_net_id, &ipgre_net_ops); + err = register_pernet_device(&ipgre_net_ops); if (err < 0) goto gen_device_failed; @@ -1688,7 +1688,7 @@ out: tap_ops_failed: rtnl_link_unregister(&ipgre_link_ops); rtnl_link_failed: - unregister_pernet_gen_device(ipgre_net_id, &ipgre_net_ops); + unregister_pernet_device(&ipgre_net_ops); gen_device_failed: inet_del_protocol(&ipgre_protocol, IPPROTO_GRE); goto out; @@ -1698,7 +1698,7 @@ static void __exit ipgre_fini(void) { rtnl_link_unregister(&ipgre_tap_ops); rtnl_link_unregister(&ipgre_link_ops); - unregister_pernet_gen_device(ipgre_net_id, &ipgre_net_ops); + unregister_pernet_device(&ipgre_net_ops); if (inet_del_protocol(&ipgre_protocol, IPPROTO_GRE) < 0) printk(KERN_INFO "ipgre close: can't remove protocol\n"); } diff --git a/net/ipv4/ip_input.c b/net/ipv4/ip_input.c index 6c98b43badf4..c29de9879fda 100644 --- a/net/ipv4/ip_input.c +++ b/net/ipv4/ip_input.c @@ -161,10 +161,10 @@ int ip_call_ra_chain(struct sk_buff *skb) /* If socket is bound to an interface, only report * the packet if it came from that interface. */ - if (sk && inet_sk(sk)->num == protocol && + if (sk && inet_sk(sk)->inet_num == protocol && (!sk->sk_bound_dev_if || sk->sk_bound_dev_if == dev->ifindex) && - sock_net(sk) == dev_net(dev)) { + net_eq(sock_net(sk), dev_net(dev))) { if (ip_hdr(skb)->frag_off & htons(IP_MF | IP_OFFSET)) { if (ip_defrag(skb, IP_DEFRAG_CALL_RA_CHAIN)) { read_unlock(&ip_ra_lock); diff --git a/net/ipv4/ip_output.c b/net/ipv4/ip_output.c index f9895180f481..e34013a78ef4 100644 --- a/net/ipv4/ip_output.c +++ b/net/ipv4/ip_output.c @@ -264,9 +264,11 @@ int ip_mc_output(struct sk_buff *skb) This check is duplicated in ip_mr_input at the moment. */ - && ((rt->rt_flags&RTCF_LOCAL) || !(IPCB(skb)->flags&IPSKB_FORWARDED)) + && + ((rt->rt_flags & RTCF_LOCAL) || + !(IPCB(skb)->flags & IPSKB_FORWARDED)) #endif - ) { + ) { struct sk_buff *newskb = skb_clone(skb, GFP_ATOMIC); if (newskb) NF_HOOK(PF_INET, NF_INET_POST_ROUTING, newskb, @@ -329,7 +331,7 @@ int ip_queue_xmit(struct sk_buff *skb, int ipfragok) __be32 daddr; /* Use correct destination address if we have options. */ - daddr = inet->daddr; + daddr = inet->inet_daddr; if(opt && opt->srr) daddr = opt->faddr; @@ -338,13 +340,13 @@ int ip_queue_xmit(struct sk_buff *skb, int ipfragok) .mark = sk->sk_mark, .nl_u = { .ip4_u = { .daddr = daddr, - .saddr = inet->saddr, + .saddr = inet->inet_saddr, .tos = RT_CONN_FLAGS(sk) } }, .proto = sk->sk_protocol, .flags = inet_sk_flowi_flags(sk), .uli_u = { .ports = - { .sport = inet->sport, - .dport = inet->dport } } }; + { .sport = inet->inet_sport, + .dport = inet->inet_dport } } }; /* If this fails, retransmit mechanism of transport layer will * keep trying until route appears or the connection times @@ -379,7 +381,7 @@ packet_routed: if (opt && opt->optlen) { iph->ihl += opt->optlen >> 2; - ip_options_build(skb, opt, inet->daddr, rt, 0); + ip_options_build(skb, opt, inet->inet_daddr, rt, 0); } ip_select_ident_more(iph, &rt->u.dst, sk, @@ -501,8 +503,8 @@ int ip_fragment(struct sk_buff *skb, int (*output)(struct sk_buff *)) if (skb->sk) { frag->sk = skb->sk; frag->destructor = sock_wfree; - truesizes += frag->truesize; } + truesizes += frag->truesize; } /* Everything is OK. Generate! */ @@ -846,7 +848,8 @@ int ip_append_data(struct sock *sk, maxfraglen = ((mtu - fragheaderlen) & ~7) + fragheaderlen; if (inet->cork.length + length > 0xFFFF - fragheaderlen) { - ip_local_error(sk, EMSGSIZE, rt->rt_dst, inet->dport, mtu-exthdrlen); + ip_local_error(sk, EMSGSIZE, rt->rt_dst, inet->inet_dport, + mtu-exthdrlen); return -EMSGSIZE; } @@ -1100,7 +1103,7 @@ ssize_t ip_append_page(struct sock *sk, struct page *page, maxfraglen = ((mtu - fragheaderlen) & ~7) + fragheaderlen; if (inet->cork.length + size > 0xFFFF - fragheaderlen) { - ip_local_error(sk, EMSGSIZE, rt->rt_dst, inet->dport, mtu); + ip_local_error(sk, EMSGSIZE, rt->rt_dst, inet->inet_dport, mtu); return -EMSGSIZE; } diff --git a/net/ipv4/ip_sockglue.c b/net/ipv4/ip_sockglue.c index e982b5c1ee17..cafad9baff03 100644 --- a/net/ipv4/ip_sockglue.c +++ b/net/ipv4/ip_sockglue.c @@ -245,7 +245,7 @@ int ip_ra_control(struct sock *sk, unsigned char on, { struct ip_ra_chain *ra, *new_ra, **rap; - if (sk->sk_type != SOCK_RAW || inet_sk(sk)->num == IPPROTO_RAW) + if (sk->sk_type != SOCK_RAW || inet_sk(sk)->inet_num == IPPROTO_RAW) return -EINVAL; new_ra = on ? kmalloc(sizeof(*new_ra), GFP_KERNEL) : NULL; @@ -480,7 +480,7 @@ static int do_ip_setsockopt(struct sock *sk, int level, case IP_OPTIONS: { struct ip_options *opt = NULL; - if (optlen > 40 || optlen < 0) + if (optlen > 40) goto e_inval; err = ip_options_get_from_user(sock_net(sk), &opt, optval, optlen); @@ -492,7 +492,7 @@ static int do_ip_setsockopt(struct sock *sk, int level, if (sk->sk_family == PF_INET || (!((1 << sk->sk_state) & (TCPF_LISTEN | TCPF_CLOSE)) && - inet->daddr != LOOPBACK4_IPV6)) { + inet->inet_daddr != LOOPBACK4_IPV6)) { #endif if (inet->opt) icsk->icsk_ext_hdr_len -= inet->opt->optlen; @@ -575,7 +575,7 @@ static int do_ip_setsockopt(struct sock *sk, int level, inet->hdrincl = val ? 1 : 0; break; case IP_MTU_DISCOVER: - if (val < 0 || val > 3) + if (val < IP_PMTUDISC_DONT || val > IP_PMTUDISC_PROBE) goto e_inval; inet->pmtudisc = val; break; @@ -1180,8 +1180,8 @@ static int do_ip_getsockopt(struct sock *sk, int level, int optname, if (inet->cmsg_flags & IP_CMSG_PKTINFO) { struct in_pktinfo info; - info.ipi_addr.s_addr = inet->rcv_saddr; - info.ipi_spec_dst.s_addr = inet->rcv_saddr; + info.ipi_addr.s_addr = inet->inet_rcv_saddr; + info.ipi_spec_dst.s_addr = inet->inet_rcv_saddr; info.ipi_ifindex = inet->mc_index; put_cmsg(&msg, SOL_IP, IP_PKTINFO, sizeof(info), &info); } diff --git a/net/ipv4/ipconfig.c b/net/ipv4/ipconfig.c index f8d04c256454..4e08b7f2331c 100644 --- a/net/ipv4/ipconfig.c +++ b/net/ipv4/ipconfig.c @@ -1172,10 +1172,9 @@ static int __init ic_dynamic(void) schedule_timeout_uninterruptible(1); #ifdef IPCONFIG_DHCP /* DHCP isn't done until we get a DHCPACK. */ - if ((ic_got_reply & IC_BOOTP) - && (ic_proto_enabled & IC_USE_DHCP) - && ic_dhcp_msgtype != DHCPACK) - { + if ((ic_got_reply & IC_BOOTP) && + (ic_proto_enabled & IC_USE_DHCP) && + ic_dhcp_msgtype != DHCPACK) { ic_got_reply = 0; printk(","); continue; @@ -1344,9 +1343,9 @@ static int __init ip_auto_config(void) */ if (ic_myaddr == NONE || #ifdef CONFIG_ROOT_NFS - (root_server_addr == NONE - && ic_servaddr == NONE - && ROOT_DEV == Root_NFS) || + (root_server_addr == NONE && + ic_servaddr == NONE && + ROOT_DEV == Root_NFS) || #endif ic_first_dev->next) { #ifdef IPCONFIG_DYNAMIC diff --git a/net/ipv4/ipip.c b/net/ipv4/ipip.c index ae40ed1ba560..eda04fed3379 100644 --- a/net/ipv4/ipip.c +++ b/net/ipv4/ipip.c @@ -119,7 +119,7 @@ #define HASH_SIZE 16 #define HASH(addr) (((__force u32)addr^((__force u32)addr>>4))&0xF) -static int ipip_net_id; +static int ipip_net_id __read_mostly; struct ipip_net { struct ip_tunnel *tunnels_r_l[HASH_SIZE]; struct ip_tunnel *tunnels_r[HASH_SIZE]; @@ -134,7 +134,13 @@ static void ipip_fb_tunnel_init(struct net_device *dev); static void ipip_tunnel_init(struct net_device *dev); static void ipip_tunnel_setup(struct net_device *dev); -static DEFINE_RWLOCK(ipip_lock); +/* + * Locking : hash tables are protected by RCU and a spinlock + */ +static DEFINE_SPINLOCK(ipip_lock); + +#define for_each_ip_tunnel_rcu(start) \ + for (t = rcu_dereference(start); t; t = rcu_dereference(t->next)) static struct ip_tunnel * ipip_tunnel_lookup(struct net *net, __be32 remote, __be32 local) @@ -144,20 +150,21 @@ static struct ip_tunnel * ipip_tunnel_lookup(struct net *net, struct ip_tunnel *t; struct ipip_net *ipn = net_generic(net, ipip_net_id); - for (t = ipn->tunnels_r_l[h0^h1]; t; t = t->next) { + for_each_ip_tunnel_rcu(ipn->tunnels_r_l[h0 ^ h1]) if (local == t->parms.iph.saddr && remote == t->parms.iph.daddr && (t->dev->flags&IFF_UP)) return t; - } - for (t = ipn->tunnels_r[h0]; t; t = t->next) { + + for_each_ip_tunnel_rcu(ipn->tunnels_r[h0]) if (remote == t->parms.iph.daddr && (t->dev->flags&IFF_UP)) return t; - } - for (t = ipn->tunnels_l[h1]; t; t = t->next) { + + for_each_ip_tunnel_rcu(ipn->tunnels_l[h1]) if (local == t->parms.iph.saddr && (t->dev->flags&IFF_UP)) return t; - } - if ((t = ipn->tunnels_wc[0]) != NULL && (t->dev->flags&IFF_UP)) + + t = rcu_dereference(ipn->tunnels_wc[0]); + if (t && (t->dev->flags&IFF_UP)) return t; return NULL; } @@ -193,9 +200,9 @@ static void ipip_tunnel_unlink(struct ipip_net *ipn, struct ip_tunnel *t) for (tp = ipip_bucket(ipn, t); *tp; tp = &(*tp)->next) { if (t == *tp) { - write_lock_bh(&ipip_lock); + spin_lock_bh(&ipip_lock); *tp = t->next; - write_unlock_bh(&ipip_lock); + spin_unlock_bh(&ipip_lock); break; } } @@ -205,10 +212,10 @@ static void ipip_tunnel_link(struct ipip_net *ipn, struct ip_tunnel *t) { struct ip_tunnel **tp = ipip_bucket(ipn, t); + spin_lock_bh(&ipip_lock); t->next = *tp; - write_lock_bh(&ipip_lock); - *tp = t; - write_unlock_bh(&ipip_lock); + rcu_assign_pointer(*tp, t); + spin_unlock_bh(&ipip_lock); } static struct ip_tunnel * ipip_tunnel_locate(struct net *net, @@ -267,9 +274,9 @@ static void ipip_tunnel_uninit(struct net_device *dev) struct ipip_net *ipn = net_generic(net, ipip_net_id); if (dev == ipn->fb_tunnel_dev) { - write_lock_bh(&ipip_lock); + spin_lock_bh(&ipip_lock); ipn->tunnels_wc[0] = NULL; - write_unlock_bh(&ipip_lock); + spin_unlock_bh(&ipip_lock); } else ipip_tunnel_unlink(ipn, netdev_priv(dev)); dev_put(dev); @@ -318,7 +325,7 @@ static int ipip_err(struct sk_buff *skb, u32 info) err = -ENOENT; - read_lock(&ipip_lock); + rcu_read_lock(); t = ipip_tunnel_lookup(dev_net(skb->dev), iph->daddr, iph->saddr); if (t == NULL || t->parms.iph.daddr == 0) goto out; @@ -333,7 +340,7 @@ static int ipip_err(struct sk_buff *skb, u32 info) t->err_count = 1; t->err_time = jiffies; out: - read_unlock(&ipip_lock); + rcu_read_unlock(); return err; } @@ -351,11 +358,11 @@ static int ipip_rcv(struct sk_buff *skb) struct ip_tunnel *tunnel; const struct iphdr *iph = ip_hdr(skb); - read_lock(&ipip_lock); + rcu_read_lock(); if ((tunnel = ipip_tunnel_lookup(dev_net(skb->dev), iph->saddr, iph->daddr)) != NULL) { if (!xfrm4_policy_check(NULL, XFRM_POLICY_IN, skb)) { - read_unlock(&ipip_lock); + rcu_read_unlock(); kfree_skb(skb); return 0; } @@ -374,10 +381,10 @@ static int ipip_rcv(struct sk_buff *skb) nf_reset(skb); ipip_ecn_decapsulate(iph, skb); netif_rx(skb); - read_unlock(&ipip_lock); + rcu_read_unlock(); return 0; } - read_unlock(&ipip_lock); + rcu_read_unlock(); return -1; } @@ -390,7 +397,8 @@ static int ipip_rcv(struct sk_buff *skb) static netdev_tx_t ipip_tunnel_xmit(struct sk_buff *skb, struct net_device *dev) { struct ip_tunnel *tunnel = netdev_priv(dev); - struct net_device_stats *stats = &tunnel->dev->stats; + struct net_device_stats *stats = &dev->stats; + struct netdev_queue *txq = netdev_get_tx_queue(dev, 0); struct iphdr *tiph = &tunnel->parms.iph; u8 tos = tunnel->parms.iph.tos; __be16 df = tiph->frag_off; @@ -480,7 +488,7 @@ static netdev_tx_t ipip_tunnel_xmit(struct sk_buff *skb, struct net_device *dev) struct sk_buff *new_skb = skb_realloc_headroom(skb, max_headroom); if (!new_skb) { ip_rt_put(rt); - stats->tx_dropped++; + txq->tx_dropped++; dev_kfree_skb(skb); return NETDEV_TX_OK; } @@ -748,33 +756,27 @@ static struct xfrm_tunnel ipip_handler = { static const char banner[] __initconst = KERN_INFO "IPv4 over IPv4 tunneling driver\n"; -static void ipip_destroy_tunnels(struct ipip_net *ipn) +static void ipip_destroy_tunnels(struct ipip_net *ipn, struct list_head *head) { int prio; for (prio = 1; prio < 4; prio++) { int h; for (h = 0; h < HASH_SIZE; h++) { - struct ip_tunnel *t; - while ((t = ipn->tunnels[prio][h]) != NULL) - unregister_netdevice(t->dev); + struct ip_tunnel *t = ipn->tunnels[prio][h]; + + while (t != NULL) { + unregister_netdevice_queue(t->dev, head); + t = t->next; + } } } } static int ipip_init_net(struct net *net) { + struct ipip_net *ipn = net_generic(net, ipip_net_id); int err; - struct ipip_net *ipn; - - err = -ENOMEM; - ipn = kzalloc(sizeof(struct ipip_net), GFP_KERNEL); - if (ipn == NULL) - goto err_alloc; - - err = net_assign_generic(net, ipip_net_id, ipn); - if (err < 0) - goto err_assign; ipn->tunnels[0] = ipn->tunnels_wc; ipn->tunnels[1] = ipn->tunnels_l; @@ -801,27 +803,26 @@ err_reg_dev: free_netdev(ipn->fb_tunnel_dev); err_alloc_dev: /* nothing */ -err_assign: - kfree(ipn); -err_alloc: return err; } static void ipip_exit_net(struct net *net) { - struct ipip_net *ipn; + struct ipip_net *ipn = net_generic(net, ipip_net_id); + LIST_HEAD(list); - ipn = net_generic(net, ipip_net_id); rtnl_lock(); - ipip_destroy_tunnels(ipn); - unregister_netdevice(ipn->fb_tunnel_dev); + ipip_destroy_tunnels(ipn, &list); + unregister_netdevice_queue(ipn->fb_tunnel_dev, &list); + unregister_netdevice_many(&list); rtnl_unlock(); - kfree(ipn); } static struct pernet_operations ipip_net_ops = { .init = ipip_init_net, .exit = ipip_exit_net, + .id = &ipip_net_id, + .size = sizeof(struct ipip_net), }; static int __init ipip_init(void) @@ -835,7 +836,7 @@ static int __init ipip_init(void) return -EAGAIN; } - err = register_pernet_gen_device(&ipip_net_id, &ipip_net_ops); + err = register_pernet_device(&ipip_net_ops); if (err) xfrm4_tunnel_deregister(&ipip_handler, AF_INET); @@ -847,7 +848,7 @@ static void __exit ipip_fini(void) if (xfrm4_tunnel_deregister(&ipip_handler, AF_INET)) printk(KERN_INFO "ipip close: can't deregister tunnel\n"); - unregister_pernet_gen_device(ipip_net_id, &ipip_net_ops); + unregister_pernet_device(&ipip_net_ops); } module_init(ipip_init); diff --git a/net/ipv4/ipmr.c b/net/ipv4/ipmr.c index 99508d66a642..54596f73eff5 100644 --- a/net/ipv4/ipmr.c +++ b/net/ipv4/ipmr.c @@ -275,7 +275,8 @@ failure: * @notify: Set to 1, if the caller is a notifier_call */ -static int vif_delete(struct net *net, int vifi, int notify) +static int vif_delete(struct net *net, int vifi, int notify, + struct list_head *head) { struct vif_device *v; struct net_device *dev; @@ -319,7 +320,7 @@ static int vif_delete(struct net *net, int vifi, int notify) } if (v->flags&(VIFF_TUNNEL|VIFF_REGISTER) && !notify) - unregister_netdevice(dev); + unregister_netdevice_queue(dev, head); dev_put(dev); return 0; @@ -469,8 +470,18 @@ static int vif_add(struct net *net, struct vifctl *vifc, int mrtsock) return err; } break; + + case VIFF_USE_IFINDEX: case 0: - dev = ip_dev_find(net, vifc->vifc_lcl_addr.s_addr); + if (vifc->vifc_flags == VIFF_USE_IFINDEX) { + dev = dev_get_by_index(net, vifc->vifc_lcl_ifindex); + if (dev && dev->ip_ptr == NULL) { + dev_put(dev); + return -EADDRNOTAVAIL; + } + } else + dev = ip_dev_find(net, vifc->vifc_lcl_addr.s_addr); + if (!dev) return -EADDRNOTAVAIL; err = dev_set_allmulti(dev, 1); @@ -862,14 +873,16 @@ static int ipmr_mfc_add(struct net *net, struct mfcctl *mfc, int mrtsock) static void mroute_clean_tables(struct net *net) { int i; + LIST_HEAD(list); /* * Shut down all active vif entries */ for (i = 0; i < net->ipv4.maxvif; i++) { if (!(net->ipv4.vif_table[i].flags&VIFF_STATIC)) - vif_delete(net, i, 0); + vif_delete(net, i, 0, &list); } + unregister_netdevice_many(&list); /* * Wipe the cache @@ -948,7 +961,7 @@ int ip_mroute_setsockopt(struct sock *sk, int optname, char __user *optval, unsi switch (optname) { case MRT_INIT: if (sk->sk_type != SOCK_RAW || - inet_sk(sk)->num != IPPROTO_IGMP) + inet_sk(sk)->inet_num != IPPROTO_IGMP) return -EOPNOTSUPP; if (optlen != sizeof(int)) return -ENOPROTOOPT; @@ -985,7 +998,7 @@ int ip_mroute_setsockopt(struct sock *sk, int optname, char __user *optval, unsi if (optname == MRT_ADD_VIF) { ret = vif_add(net, &vif, sk == net->ipv4.mroute_sk); } else { - ret = vif_delete(net, vif.vifc_vifi, 0); + ret = vif_delete(net, vif.vifc_vifi, 0, NULL); } rtnl_unlock(); return ret; @@ -1148,6 +1161,7 @@ static int ipmr_device_event(struct notifier_block *this, unsigned long event, v struct net *net = dev_net(dev); struct vif_device *v; int ct; + LIST_HEAD(list); if (!net_eq(dev_net(dev), net)) return NOTIFY_DONE; @@ -1157,8 +1171,9 @@ static int ipmr_device_event(struct notifier_block *this, unsigned long event, v v = &net->ipv4.vif_table[0]; for (ct = 0; ct < net->ipv4.maxvif; ct++, v++) { if (v->dev == dev) - vif_delete(net, ct, 1); + vif_delete(net, ct, 1, &list); } + unregister_netdevice_many(&list); return NOTIFY_DONE; } diff --git a/net/ipv4/netfilter.c b/net/ipv4/netfilter.c index db52c0cb0c11..c14623fc4d5e 100644 --- a/net/ipv4/netfilter.c +++ b/net/ipv4/netfilter.c @@ -155,10 +155,10 @@ static int nf_ip_reroute(struct sk_buff *skb, if (entry->hook == NF_INET_LOCAL_OUT) { const struct iphdr *iph = ip_hdr(skb); - if (!(iph->tos == rt_info->tos - && skb->mark == rt_info->mark - && iph->daddr == rt_info->daddr - && iph->saddr == rt_info->saddr)) + if (!(iph->tos == rt_info->tos && + skb->mark == rt_info->mark && + iph->daddr == rt_info->daddr && + iph->saddr == rt_info->saddr)) return ip_route_me_harder(skb, RTN_UNSPEC); } return 0; diff --git a/net/ipv4/netfilter/arp_tables.c b/net/ipv4/netfilter/arp_tables.c index 27774c99d888..06632762ba5f 100644 --- a/net/ipv4/netfilter/arp_tables.c +++ b/net/ipv4/netfilter/arp_tables.c @@ -384,11 +384,11 @@ static int mark_source_chains(struct xt_table_info *newinfo, |= ((1 << hook) | (1 << NF_ARP_NUMHOOKS)); /* Unconditional return/END. */ - if ((e->target_offset == sizeof(struct arpt_entry) - && (strcmp(t->target.u.user.name, - ARPT_STANDARD_TARGET) == 0) - && t->verdict < 0 - && unconditional(&e->arp)) || visited) { + if ((e->target_offset == sizeof(struct arpt_entry) && + (strcmp(t->target.u.user.name, + ARPT_STANDARD_TARGET) == 0) && + t->verdict < 0 && unconditional(&e->arp)) || + visited) { unsigned int oldpos, size; if ((strcmp(t->target.u.user.name, @@ -427,8 +427,8 @@ static int mark_source_chains(struct xt_table_info *newinfo, int newpos = t->verdict; if (strcmp(t->target.u.user.name, - ARPT_STANDARD_TARGET) == 0 - && newpos >= 0) { + ARPT_STANDARD_TARGET) == 0 && + newpos >= 0) { if (newpos > newinfo->size - sizeof(struct arpt_entry)) { duprintf("mark_source_chains: " @@ -559,8 +559,8 @@ static inline int check_entry_size_and_hooks(struct arpt_entry *e, { unsigned int h; - if ((unsigned long)e % __alignof__(struct arpt_entry) != 0 - || (unsigned char *)e + sizeof(struct arpt_entry) >= limit) { + if ((unsigned long)e % __alignof__(struct arpt_entry) != 0 || + (unsigned char *)e + sizeof(struct arpt_entry) >= limit) { duprintf("Bad offset %p\n", e); return -EINVAL; } @@ -1251,8 +1251,8 @@ check_compat_entry_size_and_hooks(struct compat_arpt_entry *e, int ret, off, h; duprintf("check_compat_entry_size_and_hooks %p\n", e); - if ((unsigned long)e % __alignof__(struct compat_arpt_entry) != 0 - || (unsigned char *)e + sizeof(struct compat_arpt_entry) >= limit) { + if ((unsigned long)e % __alignof__(struct compat_arpt_entry) != 0 || + (unsigned char *)e + sizeof(struct compat_arpt_entry) >= limit) { duprintf("Bad offset %p, limit = %p\n", e, limit); return -EINVAL; } diff --git a/net/ipv4/netfilter/ip_queue.c b/net/ipv4/netfilter/ip_queue.c index c9f90e8c5191..2855f1f38cbc 100644 --- a/net/ipv4/netfilter/ip_queue.c +++ b/net/ipv4/netfilter/ip_queue.c @@ -497,10 +497,9 @@ ipq_rcv_nl_event(struct notifier_block *this, { struct netlink_notify *n = ptr; - if (event == NETLINK_URELEASE && - n->protocol == NETLINK_FIREWALL && n->pid) { + if (event == NETLINK_URELEASE && n->protocol == NETLINK_FIREWALL) { write_lock_bh(&queue_lock); - if ((n->net == &init_net) && (n->pid == peer_pid)) + if ((net_eq(n->net, &init_net)) && (n->pid == peer_pid)) __ipq_reset(); write_unlock_bh(&queue_lock); } @@ -621,7 +620,7 @@ cleanup_netlink_notifier: static void __exit ip_queue_fini(void) { nf_unregister_queue_handlers(&nfqh); - synchronize_net(); + ipq_flush(NULL, 0); #ifdef CONFIG_SYSCTL diff --git a/net/ipv4/netfilter/ip_tables.c b/net/ipv4/netfilter/ip_tables.c index cde755d5eeab..572330a552ef 100644 --- a/net/ipv4/netfilter/ip_tables.c +++ b/net/ipv4/netfilter/ip_tables.c @@ -89,9 +89,9 @@ ip_packet_match(const struct iphdr *ip, #define FWINV(bool, invflg) ((bool) ^ !!(ipinfo->invflags & (invflg))) if (FWINV((ip->saddr&ipinfo->smsk.s_addr) != ipinfo->src.s_addr, - IPT_INV_SRCIP) - || FWINV((ip->daddr&ipinfo->dmsk.s_addr) != ipinfo->dst.s_addr, - IPT_INV_DSTIP)) { + IPT_INV_SRCIP) || + FWINV((ip->daddr&ipinfo->dmsk.s_addr) != ipinfo->dst.s_addr, + IPT_INV_DSTIP)) { dprintf("Source or dest mismatch.\n"); dprintf("SRC: %pI4. Mask: %pI4. Target: %pI4.%s\n", @@ -122,8 +122,8 @@ ip_packet_match(const struct iphdr *ip, } /* Check specific protocol */ - if (ipinfo->proto - && FWINV(ip->protocol != ipinfo->proto, IPT_INV_PROTO)) { + if (ipinfo->proto && + FWINV(ip->protocol != ipinfo->proto, IPT_INV_PROTO)) { dprintf("Packet protocol %hi does not match %hi.%s\n", ip->protocol, ipinfo->proto, ipinfo->invflags&IPT_INV_PROTO ? " (INV)":""); @@ -246,11 +246,11 @@ get_chainname_rulenum(struct ipt_entry *s, struct ipt_entry *e, } else if (s == e) { (*rulenum)++; - if (s->target_offset == sizeof(struct ipt_entry) - && strcmp(t->target.u.kernel.target->name, - IPT_STANDARD_TARGET) == 0 - && t->verdict < 0 - && unconditional(&s->ip)) { + if (s->target_offset == sizeof(struct ipt_entry) && + strcmp(t->target.u.kernel.target->name, + IPT_STANDARD_TARGET) == 0 && + t->verdict < 0 && + unconditional(&s->ip)) { /* Tail of chains: STANDARD target (return/policy) */ *comment = *chainname == hookname ? comments[NF_IP_TRACE_COMMENT_POLICY] @@ -388,8 +388,8 @@ ipt_do_table(struct sk_buff *skb, back = get_entry(table_base, back->comefrom); continue; } - if (table_base + v != ipt_next_entry(e) - && !(e->ip.flags & IPT_F_GOTO)) { + if (table_base + v != ipt_next_entry(e) && + !(e->ip.flags & IPT_F_GOTO)) { /* Save old back ptr in next entry */ struct ipt_entry *next = ipt_next_entry(e); next->comefrom = (void *)back - table_base; @@ -473,11 +473,11 @@ mark_source_chains(struct xt_table_info *newinfo, e->comefrom |= ((1 << hook) | (1 << NF_INET_NUMHOOKS)); /* Unconditional return/END. */ - if ((e->target_offset == sizeof(struct ipt_entry) - && (strcmp(t->target.u.user.name, - IPT_STANDARD_TARGET) == 0) - && t->verdict < 0 - && unconditional(&e->ip)) || visited) { + if ((e->target_offset == sizeof(struct ipt_entry) && + (strcmp(t->target.u.user.name, + IPT_STANDARD_TARGET) == 0) && + t->verdict < 0 && unconditional(&e->ip)) || + visited) { unsigned int oldpos, size; if ((strcmp(t->target.u.user.name, @@ -524,8 +524,8 @@ mark_source_chains(struct xt_table_info *newinfo, int newpos = t->verdict; if (strcmp(t->target.u.user.name, - IPT_STANDARD_TARGET) == 0 - && newpos >= 0) { + IPT_STANDARD_TARGET) == 0 && + newpos >= 0) { if (newpos > newinfo->size - sizeof(struct ipt_entry)) { duprintf("mark_source_chains: " @@ -735,8 +735,8 @@ check_entry_size_and_hooks(struct ipt_entry *e, { unsigned int h; - if ((unsigned long)e % __alignof__(struct ipt_entry) != 0 - || (unsigned char *)e + sizeof(struct ipt_entry) >= limit) { + if ((unsigned long)e % __alignof__(struct ipt_entry) != 0 || + (unsigned char *)e + sizeof(struct ipt_entry) >= limit) { duprintf("Bad offset %p\n", e); return -EINVAL; } @@ -1548,8 +1548,8 @@ check_compat_entry_size_and_hooks(struct compat_ipt_entry *e, int ret, off, h; duprintf("check_compat_entry_size_and_hooks %p\n", e); - if ((unsigned long)e % __alignof__(struct compat_ipt_entry) != 0 - || (unsigned char *)e + sizeof(struct compat_ipt_entry) >= limit) { + if ((unsigned long)e % __alignof__(struct compat_ipt_entry) != 0 || + (unsigned char *)e + sizeof(struct compat_ipt_entry) >= limit) { duprintf("Bad offset %p, limit = %p\n", e, limit); return -EINVAL; } diff --git a/net/ipv4/netfilter/ipt_CLUSTERIP.c b/net/ipv4/netfilter/ipt_CLUSTERIP.c index 2e4f98b85524..40ca2d240abb 100644 --- a/net/ipv4/netfilter/ipt_CLUSTERIP.c +++ b/net/ipv4/netfilter/ipt_CLUSTERIP.c @@ -303,9 +303,9 @@ clusterip_tg(struct sk_buff *skb, const struct xt_target_param *par) /* special case: ICMP error handling. conntrack distinguishes between * error messages (RELATED) and information requests (see below) */ - if (ip_hdr(skb)->protocol == IPPROTO_ICMP - && (ctinfo == IP_CT_RELATED - || ctinfo == IP_CT_RELATED+IP_CT_IS_REPLY)) + if (ip_hdr(skb)->protocol == IPPROTO_ICMP && + (ctinfo == IP_CT_RELATED || + ctinfo == IP_CT_RELATED + IP_CT_IS_REPLY)) return XT_CONTINUE; /* ip_conntrack_icmp guarantees us that we only have ICMP_ECHO, @@ -362,8 +362,8 @@ static bool clusterip_tg_check(const struct xt_tgchk_param *par) return false; } - if (e->ip.dmsk.s_addr != htonl(0xffffffff) - || e->ip.dst.s_addr == 0) { + if (e->ip.dmsk.s_addr != htonl(0xffffffff) || + e->ip.dst.s_addr == 0) { printk(KERN_ERR "CLUSTERIP: Please specify destination IP\n"); return false; } @@ -495,14 +495,14 @@ arp_mangle(unsigned int hook, struct clusterip_config *c; /* we don't care about non-ethernet and non-ipv4 ARP */ - if (arp->ar_hrd != htons(ARPHRD_ETHER) - || arp->ar_pro != htons(ETH_P_IP) - || arp->ar_pln != 4 || arp->ar_hln != ETH_ALEN) + if (arp->ar_hrd != htons(ARPHRD_ETHER) || + arp->ar_pro != htons(ETH_P_IP) || + arp->ar_pln != 4 || arp->ar_hln != ETH_ALEN) return NF_ACCEPT; /* we only want to mangle arp requests and replies */ - if (arp->ar_op != htons(ARPOP_REPLY) - && arp->ar_op != htons(ARPOP_REQUEST)) + if (arp->ar_op != htons(ARPOP_REPLY) && + arp->ar_op != htons(ARPOP_REQUEST)) return NF_ACCEPT; payload = (void *)(arp+1); diff --git a/net/ipv4/netfilter/ipt_ECN.c b/net/ipv4/netfilter/ipt_ECN.c index f7e2fa0974dc..549e206cdd42 100644 --- a/net/ipv4/netfilter/ipt_ECN.c +++ b/net/ipv4/netfilter/ipt_ECN.c @@ -85,8 +85,8 @@ ecn_tg(struct sk_buff *skb, const struct xt_target_param *par) if (!set_ect_ip(skb, einfo)) return NF_DROP; - if (einfo->operation & (IPT_ECN_OP_SET_ECE | IPT_ECN_OP_SET_CWR) - && ip_hdr(skb)->protocol == IPPROTO_TCP) + if (einfo->operation & (IPT_ECN_OP_SET_ECE | IPT_ECN_OP_SET_CWR) && + ip_hdr(skb)->protocol == IPPROTO_TCP) if (!set_ect_tcp(skb, einfo)) return NF_DROP; @@ -108,8 +108,8 @@ static bool ecn_tg_check(const struct xt_tgchk_param *par) einfo->ip_ect); return false; } - if ((einfo->operation & (IPT_ECN_OP_SET_ECE|IPT_ECN_OP_SET_CWR)) - && (e->ip.proto != IPPROTO_TCP || (e->ip.invflags & XT_INV_PROTO))) { + if ((einfo->operation & (IPT_ECN_OP_SET_ECE|IPT_ECN_OP_SET_CWR)) && + (e->ip.proto != IPPROTO_TCP || (e->ip.invflags & XT_INV_PROTO))) { printk(KERN_WARNING "ECN: cannot use TCP operations on a " "non-tcp rule\n"); return false; diff --git a/net/ipv4/netfilter/ipt_LOG.c b/net/ipv4/netfilter/ipt_LOG.c index acc44c69eb68..ee128efa1c8d 100644 --- a/net/ipv4/netfilter/ipt_LOG.c +++ b/net/ipv4/netfilter/ipt_LOG.c @@ -74,8 +74,8 @@ static void dump_packet(const struct nf_loginfo *info, if (ntohs(ih->frag_off) & IP_OFFSET) printk("FRAG:%u ", ntohs(ih->frag_off) & IP_OFFSET); - if ((logflags & IPT_LOG_IPOPT) - && ih->ihl * 4 > sizeof(struct iphdr)) { + if ((logflags & IPT_LOG_IPOPT) && + ih->ihl * 4 > sizeof(struct iphdr)) { const unsigned char *op; unsigned char _opt[4 * 15 - sizeof(struct iphdr)]; unsigned int i, optsize; @@ -146,8 +146,8 @@ static void dump_packet(const struct nf_loginfo *info, /* Max length: 11 "URGP=65535 " */ printk("URGP=%u ", ntohs(th->urg_ptr)); - if ((logflags & IPT_LOG_TCPOPT) - && th->doff * 4 > sizeof(struct tcphdr)) { + if ((logflags & IPT_LOG_TCPOPT) && + th->doff * 4 > sizeof(struct tcphdr)) { unsigned char _opt[4 * 15 - sizeof(struct tcphdr)]; const unsigned char *op; unsigned int i, optsize; @@ -238,9 +238,9 @@ static void dump_packet(const struct nf_loginfo *info, printk("TYPE=%u CODE=%u ", ich->type, ich->code); /* Max length: 25 "INCOMPLETE [65535 bytes] " */ - if (ich->type <= NR_ICMP_TYPES - && required_len[ich->type] - && skb->len-iphoff-ih->ihl*4 < required_len[ich->type]) { + if (ich->type <= NR_ICMP_TYPES && + required_len[ich->type] && + skb->len-iphoff-ih->ihl*4 < required_len[ich->type]) { printk("INCOMPLETE [%u bytes] ", skb->len - iphoff - ih->ihl*4); break; @@ -276,8 +276,8 @@ static void dump_packet(const struct nf_loginfo *info, } /* Max length: 10 "MTU=65535 " */ - if (ich->type == ICMP_DEST_UNREACH - && ich->code == ICMP_FRAG_NEEDED) + if (ich->type == ICMP_DEST_UNREACH && + ich->code == ICMP_FRAG_NEEDED) printk("MTU=%u ", ntohs(ich->un.frag.mtu)); } break; @@ -407,8 +407,8 @@ ipt_log_packet(u_int8_t pf, if (in && !out) { /* MAC logging for input chain only. */ printk("MAC="); - if (skb->dev && skb->dev->hard_header_len - && skb->mac_header != skb->network_header) { + if (skb->dev && skb->dev->hard_header_len && + skb->mac_header != skb->network_header) { int i; const unsigned char *p = skb_mac_header(skb); for (i = 0; i < skb->dev->hard_header_len; i++,p++) diff --git a/net/ipv4/netfilter/ipt_MASQUERADE.c b/net/ipv4/netfilter/ipt_MASQUERADE.c index dada0863946d..650b54042b01 100644 --- a/net/ipv4/netfilter/ipt_MASQUERADE.c +++ b/net/ipv4/netfilter/ipt_MASQUERADE.c @@ -59,8 +59,8 @@ masquerade_tg(struct sk_buff *skb, const struct xt_target_param *par) ct = nf_ct_get(skb, &ctinfo); nat = nfct_nat(ct); - NF_CT_ASSERT(ct && (ctinfo == IP_CT_NEW || ctinfo == IP_CT_RELATED - || ctinfo == IP_CT_RELATED + IP_CT_IS_REPLY)); + NF_CT_ASSERT(ct && (ctinfo == IP_CT_NEW || ctinfo == IP_CT_RELATED || + ctinfo == IP_CT_RELATED + IP_CT_IS_REPLY)); /* Source address is 0.0.0.0 - locally generated packet that is * probably not supposed to be masqueraded. diff --git a/net/ipv4/netfilter/ipt_REJECT.c b/net/ipv4/netfilter/ipt_REJECT.c index c93ae44bff2a..5113b8f1a379 100644 --- a/net/ipv4/netfilter/ipt_REJECT.c +++ b/net/ipv4/netfilter/ipt_REJECT.c @@ -184,8 +184,8 @@ static bool reject_tg_check(const struct xt_tgchk_param *par) return false; } else if (rejinfo->with == IPT_TCP_RESET) { /* Must specify that it's a TCP packet */ - if (e->ip.proto != IPPROTO_TCP - || (e->ip.invflags & XT_INV_PROTO)) { + if (e->ip.proto != IPPROTO_TCP || + (e->ip.invflags & XT_INV_PROTO)) { printk("ipt_REJECT: TCP_RESET invalid for non-tcp\n"); return false; } diff --git a/net/ipv4/netfilter/ipt_ULOG.c b/net/ipv4/netfilter/ipt_ULOG.c index d32cc4bb328a..399061c3fd7d 100644 --- a/net/ipv4/netfilter/ipt_ULOG.c +++ b/net/ipv4/netfilter/ipt_ULOG.c @@ -226,9 +226,9 @@ static void ipt_ulog_packet(unsigned int hooknum, else *(pm->prefix) = '\0'; - if (in && in->hard_header_len > 0 - && skb->mac_header != skb->network_header - && in->hard_header_len <= ULOG_MAC_LEN) { + if (in && in->hard_header_len > 0 && + skb->mac_header != skb->network_header && + in->hard_header_len <= ULOG_MAC_LEN) { memcpy(pm->mac, skb_mac_header(skb), in->hard_header_len); pm->mac_len = in->hard_header_len; } else diff --git a/net/ipv4/netfilter/ipt_ecn.c b/net/ipv4/netfilter/ipt_ecn.c index 6289b64144c6..2a1e56b71908 100644 --- a/net/ipv4/netfilter/ipt_ecn.c +++ b/net/ipv4/netfilter/ipt_ecn.c @@ -96,8 +96,8 @@ static bool ecn_mt_check(const struct xt_mtchk_param *par) if (info->invert & IPT_ECN_OP_MATCH_MASK) return false; - if (info->operation & (IPT_ECN_OP_MATCH_ECE|IPT_ECN_OP_MATCH_CWR) - && ip->proto != IPPROTO_TCP) { + if (info->operation & (IPT_ECN_OP_MATCH_ECE|IPT_ECN_OP_MATCH_CWR) && + ip->proto != IPPROTO_TCP) { printk(KERN_WARNING "ipt_ecn: can't match TCP bits in rule for" " non-tcp packets\n"); return false; diff --git a/net/ipv4/netfilter/iptable_mangle.c b/net/ipv4/netfilter/iptable_mangle.c index 036047f9b0f2..fae78c3076c4 100644 --- a/net/ipv4/netfilter/iptable_mangle.c +++ b/net/ipv4/netfilter/iptable_mangle.c @@ -130,8 +130,8 @@ ipt_local_hook(unsigned int hook, u_int32_t mark; /* root is playing with raw sockets. */ - if (skb->len < sizeof(struct iphdr) - || ip_hdrlen(skb) < sizeof(struct iphdr)) + if (skb->len < sizeof(struct iphdr) || + ip_hdrlen(skb) < sizeof(struct iphdr)) return NF_ACCEPT; /* Save things which could affect route */ diff --git a/net/ipv4/netfilter/iptable_security.c b/net/ipv4/netfilter/iptable_security.c index 99eb76c65d25..3bd3d6388da5 100644 --- a/net/ipv4/netfilter/iptable_security.c +++ b/net/ipv4/netfilter/iptable_security.c @@ -94,8 +94,8 @@ ipt_local_out_hook(unsigned int hook, int (*okfn)(struct sk_buff *)) { /* Somebody is playing with raw sockets. */ - if (skb->len < sizeof(struct iphdr) - || ip_hdrlen(skb) < sizeof(struct iphdr)) + if (skb->len < sizeof(struct iphdr) || + ip_hdrlen(skb) < sizeof(struct iphdr)) return NF_ACCEPT; return ipt_do_table(skb, hook, in, out, dev_net(out)->ipv4.iptable_security); diff --git a/net/ipv4/netfilter/nf_conntrack_l3proto_ipv4.c b/net/ipv4/netfilter/nf_conntrack_l3proto_ipv4.c index 092d68f916e6..d171b123a656 100644 --- a/net/ipv4/netfilter/nf_conntrack_l3proto_ipv4.c +++ b/net/ipv4/netfilter/nf_conntrack_l3proto_ipv4.c @@ -247,10 +247,10 @@ getorigdst(struct sock *sk, int optval, void __user *user, int *len) struct nf_conntrack_tuple tuple; memset(&tuple, 0, sizeof(tuple)); - tuple.src.u3.ip = inet->rcv_saddr; - tuple.src.u.tcp.port = inet->sport; - tuple.dst.u3.ip = inet->daddr; - tuple.dst.u.tcp.port = inet->dport; + tuple.src.u3.ip = inet->inet_rcv_saddr; + tuple.src.u.tcp.port = inet->inet_sport; + tuple.dst.u3.ip = inet->inet_daddr; + tuple.dst.u.tcp.port = inet->inet_dport; tuple.src.l3num = PF_INET; tuple.dst.protonum = sk->sk_protocol; diff --git a/net/ipv4/netfilter/nf_conntrack_proto_icmp.c b/net/ipv4/netfilter/nf_conntrack_proto_icmp.c index 9072058778b8..7afd39b5b781 100644 --- a/net/ipv4/netfilter/nf_conntrack_proto_icmp.c +++ b/net/ipv4/netfilter/nf_conntrack_proto_icmp.c @@ -54,8 +54,8 @@ static const u_int8_t invmap[] = { static bool icmp_invert_tuple(struct nf_conntrack_tuple *tuple, const struct nf_conntrack_tuple *orig) { - if (orig->dst.u.icmp.type >= sizeof(invmap) - || !invmap[orig->dst.u.icmp.type]) + if (orig->dst.u.icmp.type >= sizeof(invmap) || + !invmap[orig->dst.u.icmp.type]) return false; tuple->src.u.icmp.id = orig->src.u.icmp.id; @@ -101,8 +101,8 @@ static bool icmp_new(struct nf_conn *ct, const struct sk_buff *skb, [ICMP_ADDRESS] = 1 }; - if (ct->tuplehash[0].tuple.dst.u.icmp.type >= sizeof(valid_new) - || !valid_new[ct->tuplehash[0].tuple.dst.u.icmp.type]) { + if (ct->tuplehash[0].tuple.dst.u.icmp.type >= sizeof(valid_new) || + !valid_new[ct->tuplehash[0].tuple.dst.u.icmp.type]) { /* Can't create a new ICMP `conn' with this. */ pr_debug("icmp: can't create new conn with type %u\n", ct->tuplehash[0].tuple.dst.u.icmp.type); @@ -201,11 +201,11 @@ icmp_error(struct net *net, struct sk_buff *skb, unsigned int dataoff, } /* Need to track icmp error message? */ - if (icmph->type != ICMP_DEST_UNREACH - && icmph->type != ICMP_SOURCE_QUENCH - && icmph->type != ICMP_TIME_EXCEEDED - && icmph->type != ICMP_PARAMETERPROB - && icmph->type != ICMP_REDIRECT) + if (icmph->type != ICMP_DEST_UNREACH && + icmph->type != ICMP_SOURCE_QUENCH && + icmph->type != ICMP_TIME_EXCEEDED && + icmph->type != ICMP_PARAMETERPROB && + icmph->type != ICMP_REDIRECT) return NF_ACCEPT; return icmp_error_message(net, skb, ctinfo, hooknum); @@ -238,17 +238,17 @@ static const struct nla_policy icmp_nla_policy[CTA_PROTO_MAX+1] = { static int icmp_nlattr_to_tuple(struct nlattr *tb[], struct nf_conntrack_tuple *tuple) { - if (!tb[CTA_PROTO_ICMP_TYPE] - || !tb[CTA_PROTO_ICMP_CODE] - || !tb[CTA_PROTO_ICMP_ID]) + if (!tb[CTA_PROTO_ICMP_TYPE] || + !tb[CTA_PROTO_ICMP_CODE] || + !tb[CTA_PROTO_ICMP_ID]) return -EINVAL; tuple->dst.u.icmp.type = nla_get_u8(tb[CTA_PROTO_ICMP_TYPE]); tuple->dst.u.icmp.code = nla_get_u8(tb[CTA_PROTO_ICMP_CODE]); tuple->src.u.icmp.id = nla_get_be16(tb[CTA_PROTO_ICMP_ID]); - if (tuple->dst.u.icmp.type >= sizeof(invmap) - || !invmap[tuple->dst.u.icmp.type]) + if (tuple->dst.u.icmp.type >= sizeof(invmap) || + !invmap[tuple->dst.u.icmp.type]) return -EINVAL; return 0; diff --git a/net/ipv4/netfilter/nf_nat_helper.c b/net/ipv4/netfilter/nf_nat_helper.c index f9520fa3aba9..7f10a6be0191 100644 --- a/net/ipv4/netfilter/nf_nat_helper.c +++ b/net/ipv4/netfilter/nf_nat_helper.c @@ -41,18 +41,14 @@ adjust_tcp_sequence(u32 seq, struct nf_conn *ct, enum ip_conntrack_info ctinfo) { - int dir; - struct nf_nat_seq *this_way, *other_way; + enum ip_conntrack_dir dir = CTINFO2DIR(ctinfo); struct nf_conn_nat *nat = nfct_nat(ct); + struct nf_nat_seq *this_way = &nat->seq[dir]; - pr_debug("adjust_tcp_sequence: seq = %u, sizediff = %d\n", seq, seq); - - dir = CTINFO2DIR(ctinfo); - - this_way = &nat->seq[dir]; - other_way = &nat->seq[!dir]; + pr_debug("adjust_tcp_sequence: seq = %u, sizediff = %d\n", + seq, sizediff); - pr_debug("nf_nat_resize_packet: Seq_offset before: "); + pr_debug("adjust_tcp_sequence: Seq_offset before: "); DUMP_OFFSET(this_way); spin_lock_bh(&nf_nat_seqofs_lock); @@ -63,13 +59,13 @@ adjust_tcp_sequence(u32 seq, * retransmit */ if (this_way->offset_before == this_way->offset_after || before(this_way->correction_pos, seq)) { - this_way->correction_pos = seq; - this_way->offset_before = this_way->offset_after; - this_way->offset_after += sizediff; + this_way->correction_pos = seq; + this_way->offset_before = this_way->offset_after; + this_way->offset_after += sizediff; } spin_unlock_bh(&nf_nat_seqofs_lock); - pr_debug("nf_nat_resize_packet: Seq_offset after: "); + pr_debug("adjust_tcp_sequence: Seq_offset after: "); DUMP_OFFSET(this_way); } diff --git a/net/ipv4/netfilter/nf_nat_standalone.c b/net/ipv4/netfilter/nf_nat_standalone.c index 5f41d017ddd8..5678e9562c15 100644 --- a/net/ipv4/netfilter/nf_nat_standalone.c +++ b/net/ipv4/netfilter/nf_nat_standalone.c @@ -197,11 +197,11 @@ nf_nat_out(unsigned int hooknum, (ct = nf_ct_get(skb, &ctinfo)) != NULL) { enum ip_conntrack_dir dir = CTINFO2DIR(ctinfo); - if (ct->tuplehash[dir].tuple.src.u3.ip != - ct->tuplehash[!dir].tuple.dst.u3.ip - || ct->tuplehash[dir].tuple.src.u.all != - ct->tuplehash[!dir].tuple.dst.u.all - ) + if ((ct->tuplehash[dir].tuple.src.u3.ip != + ct->tuplehash[!dir].tuple.dst.u3.ip) || + (ct->tuplehash[dir].tuple.src.u.all != + ct->tuplehash[!dir].tuple.dst.u.all) + ) return ip_xfrm_me_harder(skb) == 0 ? ret : NF_DROP; } #endif diff --git a/net/ipv4/raw.c b/net/ipv4/raw.c index ab996f9c0fe0..ce154b47f1da 100644 --- a/net/ipv4/raw.c +++ b/net/ipv4/raw.c @@ -87,7 +87,7 @@ void raw_hash_sk(struct sock *sk) struct raw_hashinfo *h = sk->sk_prot->h.raw_hash; struct hlist_head *head; - head = &h->ht[inet_sk(sk)->num & (RAW_HTABLE_SIZE - 1)]; + head = &h->ht[inet_sk(sk)->inet_num & (RAW_HTABLE_SIZE - 1)]; write_lock_bh(&h->lock); sk_add_node(sk, head); @@ -115,9 +115,9 @@ static struct sock *__raw_v4_lookup(struct net *net, struct sock *sk, sk_for_each_from(sk, node) { struct inet_sock *inet = inet_sk(sk); - if (net_eq(sock_net(sk), net) && inet->num == num && - !(inet->daddr && inet->daddr != raddr) && - !(inet->rcv_saddr && inet->rcv_saddr != laddr) && + if (net_eq(sock_net(sk), net) && inet->inet_num == num && + !(inet->inet_daddr && inet->inet_daddr != raddr) && + !(inet->inet_rcv_saddr && inet->inet_rcv_saddr != laddr) && !(sk->sk_bound_dev_if && sk->sk_bound_dev_if != dif)) goto found; /* gotcha */ } @@ -292,7 +292,6 @@ static int raw_rcv_skb(struct sock * sk, struct sk_buff * skb) /* Charge it to the socket. */ if (sock_queue_rcv_skb(sk, skb) < 0) { - atomic_inc(&sk->sk_drops); kfree_skb(skb); return NET_RX_DROP; } @@ -327,7 +326,7 @@ static int raw_send_hdrinc(struct sock *sk, void *from, size_t length, int err; if (length > rt->u.dst.dev->mtu) { - ip_local_error(sk, EMSGSIZE, rt->rt_dst, inet->dport, + ip_local_error(sk, EMSGSIZE, rt->rt_dst, inet->inet_dport, rt->u.dst.dev->mtu); return -EMSGSIZE; } @@ -500,10 +499,10 @@ static int raw_sendmsg(struct kiocb *iocb, struct sock *sk, struct msghdr *msg, err = -EDESTADDRREQ; if (sk->sk_state != TCP_ESTABLISHED) goto out; - daddr = inet->daddr; + daddr = inet->inet_daddr; } - ipc.addr = inet->saddr; + ipc.addr = inet->inet_saddr; ipc.opt = NULL; ipc.shtx.flags = 0; ipc.oif = sk->sk_bound_dev_if; @@ -645,9 +644,9 @@ static int raw_bind(struct sock *sk, struct sockaddr *uaddr, int addr_len) if (addr->sin_addr.s_addr && chk_addr_ret != RTN_LOCAL && chk_addr_ret != RTN_MULTICAST && chk_addr_ret != RTN_BROADCAST) goto out; - inet->rcv_saddr = inet->saddr = addr->sin_addr.s_addr; + inet->inet_rcv_saddr = inet->inet_saddr = addr->sin_addr.s_addr; if (chk_addr_ret == RTN_MULTICAST || chk_addr_ret == RTN_BROADCAST) - inet->saddr = 0; /* Use device */ + inet->inet_saddr = 0; /* Use device */ sk_dst_reset(sk); ret = 0; out: return ret; @@ -692,7 +691,7 @@ static int raw_recvmsg(struct kiocb *iocb, struct sock *sk, struct msghdr *msg, if (err) goto done; - sock_recv_timestamp(msg, sk, skb); + sock_recv_ts_and_drops(msg, sk, skb); /* Copy the address. */ if (sin) { @@ -717,7 +716,7 @@ static int raw_init(struct sock *sk) { struct raw_sock *rp = raw_sk(sk); - if (inet_sk(sk)->num == IPPROTO_ICMP) + if (inet_sk(sk)->inet_num == IPPROTO_ICMP) memset(&rp->filter, 0, sizeof(rp->filter)); return 0; } @@ -754,7 +753,7 @@ static int do_raw_setsockopt(struct sock *sk, int level, int optname, char __user *optval, unsigned int optlen) { if (optname == ICMP_FILTER) { - if (inet_sk(sk)->num != IPPROTO_ICMP) + if (inet_sk(sk)->inet_num != IPPROTO_ICMP) return -EOPNOTSUPP; else return raw_seticmpfilter(sk, optval, optlen); @@ -784,7 +783,7 @@ static int do_raw_getsockopt(struct sock *sk, int level, int optname, char __user *optval, int __user *optlen) { if (optname == ICMP_FILTER) { - if (inet_sk(sk)->num != IPPROTO_ICMP) + if (inet_sk(sk)->inet_num != IPPROTO_ICMP) return -EOPNOTSUPP; else return raw_geticmpfilter(sk, optval, optlen); @@ -943,10 +942,10 @@ EXPORT_SYMBOL_GPL(raw_seq_stop); static void raw_sock_seq_show(struct seq_file *seq, struct sock *sp, int i) { struct inet_sock *inet = inet_sk(sp); - __be32 dest = inet->daddr, - src = inet->rcv_saddr; + __be32 dest = inet->inet_daddr, + src = inet->inet_rcv_saddr; __u16 destp = 0, - srcp = inet->num; + srcp = inet->inet_num; seq_printf(seq, "%4d: %08X:%04X %08X:%04X" " %02X %08X:%08X %02X:%08lX %08X %5d %8d %lu %d %p %d\n", diff --git a/net/ipv4/route.c b/net/ipv4/route.c index 0d9f584a3811..e446496f564f 100644 --- a/net/ipv4/route.c +++ b/net/ipv4/route.c @@ -513,43 +513,42 @@ static const struct file_operations rt_cpu_seq_fops = { }; #ifdef CONFIG_NET_CLS_ROUTE -static int ip_rt_acct_read(char *buffer, char **start, off_t offset, - int length, int *eof, void *data) -{ - unsigned int i; - - if ((offset & 3) || (length & 3)) - return -EIO; - - if (offset >= sizeof(struct ip_rt_acct) * 256) { - *eof = 1; - return 0; - } - - if (offset + length >= sizeof(struct ip_rt_acct) * 256) { - length = sizeof(struct ip_rt_acct) * 256 - offset; - *eof = 1; +static int rt_acct_proc_show(struct seq_file *m, void *v) +{ + struct ip_rt_acct *dst, *src; + unsigned int i, j; + + dst = kcalloc(256, sizeof(struct ip_rt_acct), GFP_KERNEL); + if (!dst) + return -ENOMEM; + + for_each_possible_cpu(i) { + src = (struct ip_rt_acct *)per_cpu_ptr(ip_rt_acct, i); + for (j = 0; j < 256; j++) { + dst[j].o_bytes += src[j].o_bytes; + dst[j].o_packets += src[j].o_packets; + dst[j].i_bytes += src[j].i_bytes; + dst[j].i_packets += src[j].i_packets; + } } - offset /= sizeof(u32); - - if (length > 0) { - u32 *dst = (u32 *) buffer; - - *start = buffer; - memset(dst, 0, length); - - for_each_possible_cpu(i) { - unsigned int j; - u32 *src; + seq_write(m, dst, 256 * sizeof(struct ip_rt_acct)); + kfree(dst); + return 0; +} - src = ((u32 *) per_cpu_ptr(ip_rt_acct, i)) + offset; - for (j = 0; j < length/4; j++) - dst[j] += src[j]; - } - } - return length; +static int rt_acct_proc_open(struct inode *inode, struct file *file) +{ + return single_open(file, rt_acct_proc_show, NULL); } + +static const struct file_operations rt_acct_proc_fops = { + .owner = THIS_MODULE, + .open = rt_acct_proc_open, + .read = seq_read, + .llseek = seq_lseek, + .release = single_release, +}; #endif static int __net_init ip_rt_do_proc_init(struct net *net) @@ -567,8 +566,7 @@ static int __net_init ip_rt_do_proc_init(struct net *net) goto err2; #ifdef CONFIG_NET_CLS_ROUTE - pde = create_proc_read_entry("rt_acct", 0, net->proc_net, - ip_rt_acct_read, NULL); + pde = proc_create("rt_acct", 0, net->proc_net, &rt_acct_proc_fops); if (!pde) goto err3; #endif @@ -703,7 +701,7 @@ static inline int compare_keys(struct flowi *fl1, struct flowi *fl2) static inline int compare_netns(struct rtable *rt1, struct rtable *rt2) { - return dev_net(rt1->u.dst.dev) == dev_net(rt2->u.dst.dev); + return net_eq(dev_net(rt1->u.dst.dev), dev_net(rt2->u.dst.dev)); } static inline int rt_is_expired(struct rtable *rth) @@ -902,6 +900,12 @@ void rt_cache_flush(struct net *net, int delay) rt_do_flush(!in_softirq()); } +/* Flush previous cache invalidated entries from the cache */ +void rt_cache_flush_batch(void) +{ + rt_do_flush(!in_softirq()); +} + /* * We change rt_genid and let gc do the cleanup */ @@ -1346,9 +1350,9 @@ void ip_rt_redirect(__be32 old_gw, __be32 daddr, __be32 new_gw, return; net = dev_net(dev); - if (new_gw == old_gw || !IN_DEV_RX_REDIRECTS(in_dev) - || ipv4_is_multicast(new_gw) || ipv4_is_lbcast(new_gw) - || ipv4_is_zeronet(new_gw)) + if (new_gw == old_gw || !IN_DEV_RX_REDIRECTS(in_dev) || + ipv4_is_multicast(new_gw) || ipv4_is_lbcast(new_gw) || + ipv4_is_zeronet(new_gw)) goto reject_redirect; if (!rt_caching(net)) @@ -1628,9 +1632,6 @@ unsigned short ip_rt_frag_needed(struct net *net, struct iphdr *iph, __be32 daddr = iph->daddr; unsigned short est_mtu = 0; - if (ipv4_config.no_pmtu_disc) - return 0; - for (k = 0; k < 2; k++) { for (i = 0; i < 2; i++) { unsigned hash = rt_hash(daddr, skeys[i], ikeys[k], @@ -2314,10 +2315,11 @@ skip_cache: ip_hdr(skb)->protocol); if (our #ifdef CONFIG_IP_MROUTE - || (!ipv4_is_local_multicast(daddr) && - IN_DEV_MFORWARD(in_dev)) + || + (!ipv4_is_local_multicast(daddr) && + IN_DEV_MFORWARD(in_dev)) #endif - ) { + ) { rcu_read_unlock(); return ip_route_input_mc(skb, daddr, saddr, tos, dev, our); @@ -2514,9 +2516,9 @@ static int ip_route_output_slow(struct net *net, struct rtable **rp, of another iface. --ANK */ - if (oldflp->oif == 0 - && (ipv4_is_multicast(oldflp->fl4_dst) || - oldflp->fl4_dst == htonl(0xFFFFFFFF))) { + if (oldflp->oif == 0 && + (ipv4_is_multicast(oldflp->fl4_dst) || + oldflp->fl4_dst == htonl(0xFFFFFFFF))) { /* It is equivalent to inet_addr_type(saddr) == RTN_LOCAL */ dev_out = ip_dev_find(net, oldflp->fl4_src); if (dev_out == NULL) @@ -2855,7 +2857,7 @@ static int rt_fill_info(struct net *net, error = rt->u.dst.error; expires = rt->u.dst.expires ? rt->u.dst.expires - jiffies : 0; if (rt->peer) { - id = rt->peer->ip_id_count; + id = atomic_read(&rt->peer->ip_id_count) & 0xffff; if (rt->peer->tcp_ts_stamp) { ts = rt->peer->tcp_ts; tsage = get_seconds() - rt->peer->tcp_ts_stamp; @@ -3257,7 +3259,7 @@ static __net_init int sysctl_route_net_init(struct net *net) struct ctl_table *tbl; tbl = ipv4_route_flush_table; - if (net != &init_net) { + if (!net_eq(net, &init_net)) { tbl = kmemdup(tbl, sizeof(ipv4_route_flush_table), GFP_KERNEL); if (tbl == NULL) goto err_dup; diff --git a/net/ipv4/syncookies.c b/net/ipv4/syncookies.c index a6e0e077ac33..26399ad2a289 100644 --- a/net/ipv4/syncookies.c +++ b/net/ipv4/syncookies.c @@ -253,6 +253,8 @@ EXPORT_SYMBOL(cookie_check_timestamp); struct sock *cookie_v4_check(struct sock *sk, struct sk_buff *skb, struct ip_options *opt) { + struct tcp_options_received tcp_opt; + u8 *hash_location; struct inet_request_sock *ireq; struct tcp_request_sock *treq; struct tcp_sock *tp = tcp_sk(sk); @@ -263,7 +265,6 @@ struct sock *cookie_v4_check(struct sock *sk, struct sk_buff *skb, int mss; struct rtable *rt; __u8 rcv_wscale; - struct tcp_options_received tcp_opt; if (!sysctl_tcp_syncookies || !th->ack) goto out; @@ -276,13 +277,6 @@ struct sock *cookie_v4_check(struct sock *sk, struct sk_buff *skb, NET_INC_STATS_BH(sock_net(sk), LINUX_MIB_SYNCOOKIESRECV); - /* check for timestamp cookie support */ - memset(&tcp_opt, 0, sizeof(tcp_opt)); - tcp_parse_options(skb, &tcp_opt, 0); - - if (tcp_opt.saw_tstamp) - cookie_check_timestamp(&tcp_opt); - ret = NULL; req = inet_reqsk_alloc(&tcp_request_sock_ops); /* for safety */ if (!req) @@ -298,12 +292,6 @@ struct sock *cookie_v4_check(struct sock *sk, struct sk_buff *skb, ireq->loc_addr = ip_hdr(skb)->daddr; ireq->rmt_addr = ip_hdr(skb)->saddr; ireq->ecn_ok = 0; - ireq->snd_wscale = tcp_opt.snd_wscale; - ireq->rcv_wscale = tcp_opt.rcv_wscale; - ireq->sack_ok = tcp_opt.sack_ok; - ireq->wscale_ok = tcp_opt.wscale_ok; - ireq->tstamp_ok = tcp_opt.saw_tstamp; - req->ts_recent = tcp_opt.saw_tstamp ? tcp_opt.rcv_tsval : 0; /* We throwed the options of the initial SYN away, so we hope * the ACK carries the same options again (see RFC1122 4.2.3.8) @@ -333,7 +321,8 @@ struct sock *cookie_v4_check(struct sock *sk, struct sk_buff *skb, * no easy way to do this. */ { - struct flowi fl = { .nl_u = { .ip4_u = + struct flowi fl = { .mark = sk->sk_mark, + .nl_u = { .ip4_u = { .daddr = ((opt && opt->srr) ? opt->faddr : ireq->rmt_addr), @@ -351,6 +340,20 @@ struct sock *cookie_v4_check(struct sock *sk, struct sk_buff *skb, } } + /* check for timestamp cookie support */ + memset(&tcp_opt, 0, sizeof(tcp_opt)); + tcp_parse_options(skb, &tcp_opt, &hash_location, 0, &rt->u.dst); + + if (tcp_opt.saw_tstamp) + cookie_check_timestamp(&tcp_opt); + + ireq->snd_wscale = tcp_opt.snd_wscale; + ireq->rcv_wscale = tcp_opt.rcv_wscale; + ireq->sack_ok = tcp_opt.sack_ok; + ireq->wscale_ok = tcp_opt.wscale_ok; + ireq->tstamp_ok = tcp_opt.saw_tstamp; + req->ts_recent = tcp_opt.saw_tstamp ? tcp_opt.rcv_tsval : 0; + /* Try to redo what tcp_v4_send_synack did. */ req->window_clamp = tp->window_clamp ? :dst_metric(&rt->u.dst, RTAX_WINDOW); diff --git a/net/ipv4/sysctl_net_ipv4.c b/net/ipv4/sysctl_net_ipv4.c index 300056732953..7e3712ce3994 100644 --- a/net/ipv4/sysctl_net_ipv4.c +++ b/net/ipv4/sysctl_net_ipv4.c @@ -569,6 +569,13 @@ static struct ctl_table ipv4_table[] = { .proc_handler = proc_dointvec, }, { + .procname = "tcp_cookie_size", + .data = &sysctl_tcp_cookie_size, + .maxlen = sizeof(int), + .mode = 0644, + .proc_handler = proc_dointvec + }, + { .procname = "udp_mem", .data = &sysctl_udp_mem, .maxlen = sizeof(sysctl_udp_mem), @@ -660,7 +667,7 @@ static __net_init int ipv4_sysctl_init_net(struct net *net) struct ctl_table *table; table = ipv4_net_table; - if (net != &init_net) { + if (!net_eq(net, &init_net)) { table = kmemdup(table, sizeof(ipv4_net_table), GFP_KERNEL); if (table == NULL) goto err_alloc; @@ -691,7 +698,7 @@ static __net_init int ipv4_sysctl_init_net(struct net *net) return 0; err_reg: - if (net != &init_net) + if (!net_eq(net, &init_net)) kfree(table); err_alloc: return -ENOMEM; diff --git a/net/ipv4/tcp.c b/net/ipv4/tcp.c index f1813bc71088..c8666b70cde0 100644 --- a/net/ipv4/tcp.c +++ b/net/ipv4/tcp.c @@ -264,6 +264,7 @@ #include <linux/cache.h> #include <linux/err.h> #include <linux/crypto.h> +#include <linux/time.h> #include <net/icmp.h> #include <net/tcp.h> @@ -2042,7 +2043,7 @@ int tcp_disconnect(struct sock *sk, int flags) __skb_queue_purge(&sk->sk_async_wait_queue); #endif - inet->dport = 0; + inet->inet_dport = 0; if (!(sk->sk_userlocks & SOCK_BINDADDR_LOCK)) inet_reset_saddr(sk); @@ -2059,6 +2060,7 @@ int tcp_disconnect(struct sock *sk, int flags) tp->snd_ssthresh = TCP_INFINITE_SSTHRESH; tp->snd_cwnd_cnt = 0; tp->bytes_acked = 0; + tp->window_clamp = 0; tcp_set_ca_state(sk, TCP_CA_Open); tcp_clear_retrans(tp); inet_csk_delack_init(sk); @@ -2066,7 +2068,7 @@ int tcp_disconnect(struct sock *sk, int flags) memset(&tp->rx_opt, 0, sizeof(tp->rx_opt)); __sk_dst_reset(sk); - WARN_ON(inet->num && !icsk->icsk_bind_hash); + WARN_ON(inet->inet_num && !icsk->icsk_bind_hash); sk->sk_error_report(sk); return err; @@ -2083,8 +2085,9 @@ static int do_tcp_setsockopt(struct sock *sk, int level, int val; int err = 0; - /* This is a string value all the others are int's */ - if (optname == TCP_CONGESTION) { + /* These are data/string values, all the others are ints */ + switch (optname) { + case TCP_CONGESTION: { char name[TCP_CA_NAME_MAX]; if (optlen < 1) @@ -2101,6 +2104,93 @@ static int do_tcp_setsockopt(struct sock *sk, int level, release_sock(sk); return err; } + case TCP_COOKIE_TRANSACTIONS: { + struct tcp_cookie_transactions ctd; + struct tcp_cookie_values *cvp = NULL; + + if (sizeof(ctd) > optlen) + return -EINVAL; + if (copy_from_user(&ctd, optval, sizeof(ctd))) + return -EFAULT; + + if (ctd.tcpct_used > sizeof(ctd.tcpct_value) || + ctd.tcpct_s_data_desired > TCP_MSS_DESIRED) + return -EINVAL; + + if (ctd.tcpct_cookie_desired == 0) { + /* default to global value */ + } else if ((0x1 & ctd.tcpct_cookie_desired) || + ctd.tcpct_cookie_desired > TCP_COOKIE_MAX || + ctd.tcpct_cookie_desired < TCP_COOKIE_MIN) { + return -EINVAL; + } + + if (TCP_COOKIE_OUT_NEVER & ctd.tcpct_flags) { + /* Supercedes all other values */ + lock_sock(sk); + if (tp->cookie_values != NULL) { + kref_put(&tp->cookie_values->kref, + tcp_cookie_values_release); + tp->cookie_values = NULL; + } + tp->rx_opt.cookie_in_always = 0; /* false */ + tp->rx_opt.cookie_out_never = 1; /* true */ + release_sock(sk); + return err; + } + + /* Allocate ancillary memory before locking. + */ + if (ctd.tcpct_used > 0 || + (tp->cookie_values == NULL && + (sysctl_tcp_cookie_size > 0 || + ctd.tcpct_cookie_desired > 0 || + ctd.tcpct_s_data_desired > 0))) { + cvp = kzalloc(sizeof(*cvp) + ctd.tcpct_used, + GFP_KERNEL); + if (cvp == NULL) + return -ENOMEM; + } + lock_sock(sk); + tp->rx_opt.cookie_in_always = + (TCP_COOKIE_IN_ALWAYS & ctd.tcpct_flags); + tp->rx_opt.cookie_out_never = 0; /* false */ + + if (tp->cookie_values != NULL) { + if (cvp != NULL) { + /* Changed values are recorded by a changed + * pointer, ensuring the cookie will differ, + * without separately hashing each value later. + */ + kref_put(&tp->cookie_values->kref, + tcp_cookie_values_release); + kref_init(&cvp->kref); + tp->cookie_values = cvp; + } else { + cvp = tp->cookie_values; + } + } + if (cvp != NULL) { + cvp->cookie_desired = ctd.tcpct_cookie_desired; + + if (ctd.tcpct_used > 0) { + memcpy(cvp->s_data_payload, ctd.tcpct_value, + ctd.tcpct_used); + cvp->s_data_desired = ctd.tcpct_used; + cvp->s_data_constant = 1; /* true */ + } else { + /* No constant payload data. */ + cvp->s_data_desired = ctd.tcpct_s_data_desired; + cvp->s_data_constant = 0; /* false */ + } + } + release_sock(sk); + return err; + } + default: + /* fallthru */ + break; + }; if (optlen < sizeof(int)) return -EINVAL; @@ -2425,6 +2515,47 @@ static int do_tcp_getsockopt(struct sock *sk, int level, if (copy_to_user(optval, icsk->icsk_ca_ops->name, len)) return -EFAULT; return 0; + + case TCP_COOKIE_TRANSACTIONS: { + struct tcp_cookie_transactions ctd; + struct tcp_cookie_values *cvp = tp->cookie_values; + + if (get_user(len, optlen)) + return -EFAULT; + if (len < sizeof(ctd)) + return -EINVAL; + + memset(&ctd, 0, sizeof(ctd)); + ctd.tcpct_flags = (tp->rx_opt.cookie_in_always ? + TCP_COOKIE_IN_ALWAYS : 0) + | (tp->rx_opt.cookie_out_never ? + TCP_COOKIE_OUT_NEVER : 0); + + if (cvp != NULL) { + ctd.tcpct_flags |= (cvp->s_data_in ? + TCP_S_DATA_IN : 0) + | (cvp->s_data_out ? + TCP_S_DATA_OUT : 0); + + ctd.tcpct_cookie_desired = cvp->cookie_desired; + ctd.tcpct_s_data_desired = cvp->s_data_desired; + + /* Cookie(s) saved, return as nonce */ + if (sizeof(ctd.tcpct_value) < cvp->cookie_pair_size) { + /* impossible? */ + return -EINVAL; + } + memcpy(&ctd.tcpct_value[0], &cvp->cookie_pair[0], + cvp->cookie_pair_size); + ctd.tcpct_used = cvp->cookie_pair_size; + } + + if (put_user(sizeof(ctd), optlen)) + return -EFAULT; + if (copy_to_user(optval, &ctd, sizeof(ctd))) + return -EFAULT; + return 0; + } default: return -ENOPROTOOPT; } @@ -2847,6 +2978,135 @@ EXPORT_SYMBOL(tcp_md5_hash_key); #endif +/** + * Each Responder maintains up to two secret values concurrently for + * efficient secret rollover. Each secret value has 4 states: + * + * Generating. (tcp_secret_generating != tcp_secret_primary) + * Generates new Responder-Cookies, but not yet used for primary + * verification. This is a short-term state, typically lasting only + * one round trip time (RTT). + * + * Primary. (tcp_secret_generating == tcp_secret_primary) + * Used both for generation and primary verification. + * + * Retiring. (tcp_secret_retiring != tcp_secret_secondary) + * Used for verification, until the first failure that can be + * verified by the newer Generating secret. At that time, this + * cookie's state is changed to Secondary, and the Generating + * cookie's state is changed to Primary. This is a short-term state, + * typically lasting only one round trip time (RTT). + * + * Secondary. (tcp_secret_retiring == tcp_secret_secondary) + * Used for secondary verification, after primary verification + * failures. This state lasts no more than twice the Maximum Segment + * Lifetime (2MSL). Then, the secret is discarded. + */ +struct tcp_cookie_secret { + /* The secret is divided into two parts. The digest part is the + * equivalent of previously hashing a secret and saving the state, + * and serves as an initialization vector (IV). The message part + * serves as the trailing secret. + */ + u32 secrets[COOKIE_WORKSPACE_WORDS]; + unsigned long expires; +}; + +#define TCP_SECRET_1MSL (HZ * TCP_PAWS_MSL) +#define TCP_SECRET_2MSL (HZ * TCP_PAWS_MSL * 2) +#define TCP_SECRET_LIFE (HZ * 600) + +static struct tcp_cookie_secret tcp_secret_one; +static struct tcp_cookie_secret tcp_secret_two; + +/* Essentially a circular list, without dynamic allocation. */ +static struct tcp_cookie_secret *tcp_secret_generating; +static struct tcp_cookie_secret *tcp_secret_primary; +static struct tcp_cookie_secret *tcp_secret_retiring; +static struct tcp_cookie_secret *tcp_secret_secondary; + +static DEFINE_SPINLOCK(tcp_secret_locker); + +/* Select a pseudo-random word in the cookie workspace. + */ +static inline u32 tcp_cookie_work(const u32 *ws, const int n) +{ + return ws[COOKIE_DIGEST_WORDS + ((COOKIE_MESSAGE_WORDS-1) & ws[n])]; +} + +/* Fill bakery[COOKIE_WORKSPACE_WORDS] with generator, updating as needed. + * Called in softirq context. + * Returns: 0 for success. + */ +int tcp_cookie_generator(u32 *bakery) +{ + unsigned long jiffy = jiffies; + + if (unlikely(time_after_eq(jiffy, tcp_secret_generating->expires))) { + spin_lock_bh(&tcp_secret_locker); + if (!time_after_eq(jiffy, tcp_secret_generating->expires)) { + /* refreshed by another */ + memcpy(bakery, + &tcp_secret_generating->secrets[0], + COOKIE_WORKSPACE_WORDS); + } else { + /* still needs refreshing */ + get_random_bytes(bakery, COOKIE_WORKSPACE_WORDS); + + /* The first time, paranoia assumes that the + * randomization function isn't as strong. But, + * this secret initialization is delayed until + * the last possible moment (packet arrival). + * Although that time is observable, it is + * unpredictably variable. Mash in the most + * volatile clock bits available, and expire the + * secret extra quickly. + */ + if (unlikely(tcp_secret_primary->expires == + tcp_secret_secondary->expires)) { + struct timespec tv; + + getnstimeofday(&tv); + bakery[COOKIE_DIGEST_WORDS+0] ^= + (u32)tv.tv_nsec; + + tcp_secret_secondary->expires = jiffy + + TCP_SECRET_1MSL + + (0x0f & tcp_cookie_work(bakery, 0)); + } else { + tcp_secret_secondary->expires = jiffy + + TCP_SECRET_LIFE + + (0xff & tcp_cookie_work(bakery, 1)); + tcp_secret_primary->expires = jiffy + + TCP_SECRET_2MSL + + (0x1f & tcp_cookie_work(bakery, 2)); + } + memcpy(&tcp_secret_secondary->secrets[0], + bakery, COOKIE_WORKSPACE_WORDS); + + rcu_assign_pointer(tcp_secret_generating, + tcp_secret_secondary); + rcu_assign_pointer(tcp_secret_retiring, + tcp_secret_primary); + /* + * Neither call_rcu() nor synchronize_rcu() needed. + * Retiring data is not freed. It is replaced after + * further (locked) pointer updates, and a quiet time + * (minimum 1MSL, maximum LIFE - 2MSL). + */ + } + spin_unlock_bh(&tcp_secret_locker); + } else { + rcu_read_lock_bh(); + memcpy(bakery, + &rcu_dereference(tcp_secret_generating)->secrets[0], + COOKIE_WORKSPACE_WORDS); + rcu_read_unlock_bh(); + } + return 0; +} +EXPORT_SYMBOL(tcp_cookie_generator); + void tcp_done(struct sock *sk) { if (sk->sk_state == TCP_SYN_SENT || sk->sk_state == TCP_SYN_RECV) @@ -2881,6 +3141,7 @@ void __init tcp_init(void) struct sk_buff *skb = NULL; unsigned long nr_pages, limit; int order, i, max_share; + unsigned long jiffy = jiffies; BUILD_BUG_ON(sizeof(struct tcp_skb_cb) > sizeof(skb->cb)); @@ -2903,11 +3164,10 @@ void __init tcp_init(void) (totalram_pages >= 128 * 1024) ? 13 : 15, 0, - &tcp_hashinfo.ehash_size, NULL, + &tcp_hashinfo.ehash_mask, thash_entries ? 0 : 512 * 1024); - tcp_hashinfo.ehash_size = 1 << tcp_hashinfo.ehash_size; - for (i = 0; i < tcp_hashinfo.ehash_size; i++) { + for (i = 0; i <= tcp_hashinfo.ehash_mask; i++) { INIT_HLIST_NULLS_HEAD(&tcp_hashinfo.ehash[i].chain, i); INIT_HLIST_NULLS_HEAD(&tcp_hashinfo.ehash[i].twchain, i); } @@ -2916,7 +3176,7 @@ void __init tcp_init(void) tcp_hashinfo.bhash = alloc_large_system_hash("TCP bind", sizeof(struct inet_bind_hashbucket), - tcp_hashinfo.ehash_size, + tcp_hashinfo.ehash_mask + 1, (totalram_pages >= 128 * 1024) ? 13 : 15, 0, @@ -2971,10 +3231,19 @@ void __init tcp_init(void) sysctl_tcp_rmem[2] = max(87380, max_share); printk(KERN_INFO "TCP: Hash tables configured " - "(established %d bind %d)\n", - tcp_hashinfo.ehash_size, tcp_hashinfo.bhash_size); + "(established %u bind %u)\n", + tcp_hashinfo.ehash_mask + 1, tcp_hashinfo.bhash_size); tcp_register_congestion_control(&tcp_reno); + + memset(&tcp_secret_one.secrets[0], 0, sizeof(tcp_secret_one.secrets)); + memset(&tcp_secret_two.secrets[0], 0, sizeof(tcp_secret_two.secrets)); + tcp_secret_one.expires = jiffy; /* past due */ + tcp_secret_two.expires = jiffy; /* past due */ + tcp_secret_generating = &tcp_secret_one; + tcp_secret_primary = &tcp_secret_one; + tcp_secret_retiring = &tcp_secret_two; + tcp_secret_secondary = &tcp_secret_two; } EXPORT_SYMBOL(tcp_close); diff --git a/net/ipv4/tcp_diag.c b/net/ipv4/tcp_diag.c index fcbcd4ff6c5f..939edb3b8e4d 100644 --- a/net/ipv4/tcp_diag.c +++ b/net/ipv4/tcp_diag.c @@ -27,7 +27,7 @@ static void tcp_diag_get_info(struct sock *sk, struct inet_diag_msg *r, r->idiag_rqueue = sk->sk_ack_backlog; r->idiag_wqueue = sk->sk_max_ack_backlog; } else { - r->idiag_rqueue = tp->rcv_nxt - tp->copied_seq; + r->idiag_rqueue = max_t(int, tp->rcv_nxt - tp->copied_seq, 0); r->idiag_wqueue = tp->write_seq - tp->snd_una; } if (info != NULL) diff --git a/net/ipv4/tcp_htcp.c b/net/ipv4/tcp_htcp.c index 26d5c7fc7de5..7c94a4955416 100644 --- a/net/ipv4/tcp_htcp.c +++ b/net/ipv4/tcp_htcp.c @@ -92,8 +92,8 @@ static inline void measure_rtt(struct sock *sk, u32 srtt) if (icsk->icsk_ca_state == TCP_CA_Open) { if (ca->maxRTT < ca->minRTT) ca->maxRTT = ca->minRTT; - if (ca->maxRTT < srtt - && srtt <= ca->maxRTT + msecs_to_jiffies(20)) + if (ca->maxRTT < srtt && + srtt <= ca->maxRTT + msecs_to_jiffies(20)) ca->maxRTT = srtt; } } @@ -123,9 +123,9 @@ static void measure_achieved_throughput(struct sock *sk, u32 pkts_acked, s32 rtt ca->packetcount += pkts_acked; - if (ca->packetcount >= tp->snd_cwnd - (ca->alpha >> 7 ? : 1) - && now - ca->lasttime >= ca->minRTT - && ca->minRTT > 0) { + if (ca->packetcount >= tp->snd_cwnd - (ca->alpha >> 7 ? : 1) && + now - ca->lasttime >= ca->minRTT && + ca->minRTT > 0) { __u32 cur_Bi = ca->packetcount * HZ / (now - ca->lasttime); if (htcp_ccount(ca) <= 3) { diff --git a/net/ipv4/tcp_input.c b/net/ipv4/tcp_input.c index d86784be7ab3..57ae96a04220 100644 --- a/net/ipv4/tcp_input.c +++ b/net/ipv4/tcp_input.c @@ -140,7 +140,7 @@ static void tcp_measure_rcv_mss(struct sock *sk, const struct sk_buff *skb) * "len" is invariant segment length, including TCP header. */ len += skb->data - skb_transport_header(skb); - if (len >= TCP_MIN_RCVMSS + sizeof(struct tcphdr) || + if (len >= TCP_MSS_DEFAULT + sizeof(struct tcphdr) || /* If PSH is not set, packet should be * full sized, provided peer TCP is not badly broken. * This observation (if it is correct 8)) allows @@ -411,7 +411,7 @@ void tcp_initialize_rcv_mss(struct sock *sk) unsigned int hint = min_t(unsigned int, tp->advmss, tp->mss_cache); hint = min(hint, tp->rcv_wnd / 2); - hint = min(hint, TCP_MIN_RCVMSS); + hint = min(hint, TCP_MSS_DEFAULT); hint = max(hint, TCP_MIN_MSS); inet_csk(sk)->icsk_ack.rcv_mss = hint; @@ -2300,7 +2300,7 @@ static inline int tcp_fackets_out(struct tcp_sock *tp) * they differ. Since neither occurs due to loss, TCP should really * ignore them. */ -static inline int tcp_dupack_heurestics(struct tcp_sock *tp) +static inline int tcp_dupack_heuristics(struct tcp_sock *tp) { return tcp_is_fack(tp) ? tp->fackets_out : tp->sacked_out + 1; } @@ -2425,7 +2425,7 @@ static int tcp_time_to_recover(struct sock *sk) return 1; /* Not-A-Trick#2 : Classic rule... */ - if (tcp_dupack_heurestics(tp) > tp->reordering) + if (tcp_dupack_heuristics(tp) > tp->reordering) return 1; /* Trick#3 : when we use RFC2988 timer restart, fast @@ -3698,7 +3698,7 @@ old_ack: * the fast version below fails. */ void tcp_parse_options(struct sk_buff *skb, struct tcp_options_received *opt_rx, - int estab) + u8 **hvpp, int estab, struct dst_entry *dst) { unsigned char *ptr; struct tcphdr *th = tcp_hdr(skb); @@ -3737,7 +3737,8 @@ void tcp_parse_options(struct sk_buff *skb, struct tcp_options_received *opt_rx, break; case TCPOPT_WINDOW: if (opsize == TCPOLEN_WINDOW && th->syn && - !estab && sysctl_tcp_window_scaling) { + !estab && sysctl_tcp_window_scaling && + !dst_feature(dst, RTAX_FEATURE_NO_WSCALE)) { __u8 snd_wscale = *(__u8 *)ptr; opt_rx->wscale_ok = 1; if (snd_wscale > 14) { @@ -3753,7 +3754,8 @@ void tcp_parse_options(struct sk_buff *skb, struct tcp_options_received *opt_rx, case TCPOPT_TIMESTAMP: if ((opsize == TCPOLEN_TIMESTAMP) && ((estab && opt_rx->tstamp_ok) || - (!estab && sysctl_tcp_timestamps))) { + (!estab && sysctl_tcp_timestamps && + !dst_feature(dst, RTAX_FEATURE_NO_TSTAMP)))) { opt_rx->saw_tstamp = 1; opt_rx->rcv_tsval = get_unaligned_be32(ptr); opt_rx->rcv_tsecr = get_unaligned_be32(ptr + 4); @@ -3761,7 +3763,8 @@ void tcp_parse_options(struct sk_buff *skb, struct tcp_options_received *opt_rx, break; case TCPOPT_SACK_PERM: if (opsize == TCPOLEN_SACK_PERM && th->syn && - !estab && sysctl_tcp_sack) { + !estab && sysctl_tcp_sack && + !dst_feature(dst, RTAX_FEATURE_NO_SACK)) { opt_rx->sack_ok = 1; tcp_sack_reset(opt_rx); } @@ -3782,7 +3785,30 @@ void tcp_parse_options(struct sk_buff *skb, struct tcp_options_received *opt_rx, */ break; #endif - } + case TCPOPT_COOKIE: + /* This option is variable length. + */ + switch (opsize) { + case TCPOLEN_COOKIE_BASE: + /* not yet implemented */ + break; + case TCPOLEN_COOKIE_PAIR: + /* not yet implemented */ + break; + case TCPOLEN_COOKIE_MIN+0: + case TCPOLEN_COOKIE_MIN+2: + case TCPOLEN_COOKIE_MIN+4: + case TCPOLEN_COOKIE_MIN+6: + case TCPOLEN_COOKIE_MAX: + /* 16-bit multiple */ + opt_rx->cookie_plus = opsize; + *hvpp = ptr; + default: + /* ignore option */ + break; + }; + break; + }; ptr += opsize-2; length -= opsize; @@ -3810,17 +3836,20 @@ static int tcp_parse_aligned_timestamp(struct tcp_sock *tp, struct tcphdr *th) * If it is wrong it falls back on tcp_parse_options(). */ static int tcp_fast_parse_options(struct sk_buff *skb, struct tcphdr *th, - struct tcp_sock *tp) + struct tcp_sock *tp, u8 **hvpp) { - if (th->doff == sizeof(struct tcphdr) >> 2) { + /* In the spirit of fast parsing, compare doff directly to constant + * values. Because equality is used, short doff can be ignored here. + */ + if (th->doff == (sizeof(*th) / 4)) { tp->rx_opt.saw_tstamp = 0; return 0; } else if (tp->rx_opt.tstamp_ok && - th->doff == (sizeof(struct tcphdr)>>2)+(TCPOLEN_TSTAMP_ALIGNED>>2)) { + th->doff == ((sizeof(*th) + TCPOLEN_TSTAMP_ALIGNED) / 4)) { if (tcp_parse_aligned_timestamp(tp, th)) return 1; } - tcp_parse_options(skb, &tp->rx_opt, 1); + tcp_parse_options(skb, &tp->rx_opt, hvpp, 1, NULL); return 1; } @@ -4075,8 +4104,10 @@ static inline int tcp_sack_extend(struct tcp_sack_block *sp, u32 seq, static void tcp_dsack_set(struct sock *sk, u32 seq, u32 end_seq) { struct tcp_sock *tp = tcp_sk(sk); + struct dst_entry *dst = __sk_dst_get(sk); - if (tcp_is_sack(tp) && sysctl_tcp_dsack) { + if (tcp_is_sack(tp) && sysctl_tcp_dsack && + !dst_feature(dst, RTAX_FEATURE_NO_DSACK)) { int mib_idx; if (before(seq, tp->rcv_nxt)) @@ -4105,13 +4136,15 @@ static void tcp_dsack_extend(struct sock *sk, u32 seq, u32 end_seq) static void tcp_send_dupack(struct sock *sk, struct sk_buff *skb) { struct tcp_sock *tp = tcp_sk(sk); + struct dst_entry *dst = __sk_dst_get(sk); if (TCP_SKB_CB(skb)->end_seq != TCP_SKB_CB(skb)->seq && before(TCP_SKB_CB(skb)->seq, tp->rcv_nxt)) { NET_INC_STATS_BH(sock_net(sk), LINUX_MIB_DELAYEDACKLOST); tcp_enter_quickack_mode(sk); - if (tcp_is_sack(tp) && sysctl_tcp_dsack) { + if (tcp_is_sack(tp) && sysctl_tcp_dsack && + !dst_feature(dst, RTAX_FEATURE_NO_DSACK)) { u32 end_seq = TCP_SKB_CB(skb)->end_seq; if (after(TCP_SKB_CB(skb)->end_seq, tp->rcv_nxt)) @@ -4845,11 +4878,11 @@ static void __tcp_ack_snd_check(struct sock *sk, int ofo_possible) struct tcp_sock *tp = tcp_sk(sk); /* More than one full frame received... */ - if (((tp->rcv_nxt - tp->rcv_wup) > inet_csk(sk)->icsk_ack.rcv_mss + if (((tp->rcv_nxt - tp->rcv_wup) > inet_csk(sk)->icsk_ack.rcv_mss && /* ... and right edge of window advances far enough. * (tcp_recvmsg() will send ACK otherwise). Or... */ - && __tcp_select_window(sk) >= tp->rcv_wnd) || + __tcp_select_window(sk) >= tp->rcv_wnd) || /* We ACK each frame or... */ tcp_in_quickack_mode(sk) || /* We have out of order data. */ @@ -5070,10 +5103,12 @@ out: static int tcp_validate_incoming(struct sock *sk, struct sk_buff *skb, struct tcphdr *th, int syn_inerr) { + u8 *hash_location; struct tcp_sock *tp = tcp_sk(sk); /* RFC1323: H1. Apply PAWS check first. */ - if (tcp_fast_parse_options(skb, th, tp) && tp->rx_opt.saw_tstamp && + if (tcp_fast_parse_options(skb, th, tp, &hash_location) && + tp->rx_opt.saw_tstamp && tcp_paws_discard(sk, skb)) { if (!th->rst) { NET_INC_STATS_BH(sock_net(sk), LINUX_MIB_PAWSESTABREJECTED); @@ -5361,11 +5396,14 @@ discard: static int tcp_rcv_synsent_state_process(struct sock *sk, struct sk_buff *skb, struct tcphdr *th, unsigned len) { - struct tcp_sock *tp = tcp_sk(sk); + u8 *hash_location; struct inet_connection_sock *icsk = inet_csk(sk); + struct tcp_sock *tp = tcp_sk(sk); + struct dst_entry *dst = __sk_dst_get(sk); + struct tcp_cookie_values *cvp = tp->cookie_values; int saved_clamp = tp->rx_opt.mss_clamp; - tcp_parse_options(skb, &tp->rx_opt, 0); + tcp_parse_options(skb, &tp->rx_opt, &hash_location, 0, dst); if (th->ack) { /* rfc793: @@ -5462,6 +5500,31 @@ static int tcp_rcv_synsent_state_process(struct sock *sk, struct sk_buff *skb, * Change state from SYN-SENT only after copied_seq * is initialized. */ tp->copied_seq = tp->rcv_nxt; + + if (cvp != NULL && + cvp->cookie_pair_size > 0 && + tp->rx_opt.cookie_plus > 0) { + int cookie_size = tp->rx_opt.cookie_plus + - TCPOLEN_COOKIE_BASE; + int cookie_pair_size = cookie_size + + cvp->cookie_desired; + + /* A cookie extension option was sent and returned. + * Note that each incoming SYNACK replaces the + * Responder cookie. The initial exchange is most + * fragile, as protection against spoofing relies + * entirely upon the sequence and timestamp (above). + * This replacement strategy allows the correct pair to + * pass through, while any others will be filtered via + * Responder verification later. + */ + if (sizeof(cvp->cookie_pair) >= cookie_pair_size) { + memcpy(&cvp->cookie_pair[cvp->cookie_desired], + hash_location, cookie_size); + cvp->cookie_pair_size = cookie_pair_size; + } + } + smp_mb(); tcp_set_state(sk, TCP_ESTABLISHED); diff --git a/net/ipv4/tcp_ipv4.c b/net/ipv4/tcp_ipv4.c index 7cda24b53f61..29002ab26e0d 100644 --- a/net/ipv4/tcp_ipv4.c +++ b/net/ipv4/tcp_ipv4.c @@ -165,10 +165,10 @@ int tcp_v4_connect(struct sock *sk, struct sockaddr *uaddr, int addr_len) nexthop = inet->opt->faddr; } - tmp = ip_route_connect(&rt, nexthop, inet->saddr, + tmp = ip_route_connect(&rt, nexthop, inet->inet_saddr, RT_CONN_FLAGS(sk), sk->sk_bound_dev_if, IPPROTO_TCP, - inet->sport, usin->sin_port, sk, 1); + inet->inet_sport, usin->sin_port, sk, 1); if (tmp < 0) { if (tmp == -ENETUNREACH) IP_INC_STATS_BH(sock_net(sk), IPSTATS_MIB_OUTNOROUTES); @@ -183,11 +183,11 @@ int tcp_v4_connect(struct sock *sk, struct sockaddr *uaddr, int addr_len) if (!inet->opt || !inet->opt->srr) daddr = rt->rt_dst; - if (!inet->saddr) - inet->saddr = rt->rt_src; - inet->rcv_saddr = inet->saddr; + if (!inet->inet_saddr) + inet->inet_saddr = rt->rt_src; + inet->inet_rcv_saddr = inet->inet_saddr; - if (tp->rx_opt.ts_recent_stamp && inet->daddr != daddr) { + if (tp->rx_opt.ts_recent_stamp && inet->inet_daddr != daddr) { /* Reset inherited state */ tp->rx_opt.ts_recent = 0; tp->rx_opt.ts_recent_stamp = 0; @@ -204,20 +204,20 @@ int tcp_v4_connect(struct sock *sk, struct sockaddr *uaddr, int addr_len) * when trying new connection. */ if (peer != NULL && - peer->tcp_ts_stamp + TCP_PAWS_MSL >= get_seconds()) { + (u32)get_seconds() - peer->tcp_ts_stamp <= TCP_PAWS_MSL) { tp->rx_opt.ts_recent_stamp = peer->tcp_ts_stamp; tp->rx_opt.ts_recent = peer->tcp_ts; } } - inet->dport = usin->sin_port; - inet->daddr = daddr; + inet->inet_dport = usin->sin_port; + inet->inet_daddr = daddr; inet_csk(sk)->icsk_ext_hdr_len = 0; if (inet->opt) inet_csk(sk)->icsk_ext_hdr_len = inet->opt->optlen; - tp->rx_opt.mss_clamp = 536; + tp->rx_opt.mss_clamp = TCP_MSS_DEFAULT; /* Socket identity is still unknown (sport may be zero). * However we set state to SYN-SENT and not releasing socket @@ -230,7 +230,7 @@ int tcp_v4_connect(struct sock *sk, struct sockaddr *uaddr, int addr_len) goto failure; err = ip_route_newports(&rt, IPPROTO_TCP, - inet->sport, inet->dport, sk); + inet->inet_sport, inet->inet_dport, sk); if (err) goto failure; @@ -239,12 +239,12 @@ int tcp_v4_connect(struct sock *sk, struct sockaddr *uaddr, int addr_len) sk_setup_caps(sk, &rt->u.dst); if (!tp->write_seq) - tp->write_seq = secure_tcp_sequence_number(inet->saddr, - inet->daddr, - inet->sport, + tp->write_seq = secure_tcp_sequence_number(inet->inet_saddr, + inet->inet_daddr, + inet->inet_sport, usin->sin_port); - inet->id = tp->write_seq ^ jiffies; + inet->inet_id = tp->write_seq ^ jiffies; err = tcp_connect(sk); rt = NULL; @@ -261,7 +261,7 @@ failure: tcp_set_state(sk, TCP_CLOSE); ip_rt_put(rt); sk->sk_route_caps = 0; - inet->dport = 0; + inet->inet_dport = 0; return err; } @@ -520,12 +520,13 @@ void tcp_v4_send_check(struct sock *sk, int len, struct sk_buff *skb) struct tcphdr *th = tcp_hdr(skb); if (skb->ip_summed == CHECKSUM_PARTIAL) { - th->check = ~tcp_v4_check(len, inet->saddr, - inet->daddr, 0); + th->check = ~tcp_v4_check(len, inet->inet_saddr, + inet->inet_daddr, 0); skb->csum_start = skb_transport_header(skb) - skb->head; skb->csum_offset = offsetof(struct tcphdr, check); } else { - th->check = tcp_v4_check(len, inet->saddr, inet->daddr, + th->check = tcp_v4_check(len, inet->inet_saddr, + inet->inet_daddr, csum_partial(th, th->doff << 2, skb->csum)); @@ -741,8 +742,9 @@ static void tcp_v4_reqsk_send_ack(struct sock *sk, struct sk_buff *skb, * This still operates on a request_sock only, not on a big * socket. */ -static int __tcp_v4_send_synack(struct sock *sk, struct request_sock *req, - struct dst_entry *dst) +static int __tcp_v4_send_synack(struct sock *sk, struct dst_entry *dst, + struct request_sock *req, + struct request_values *rvp) { const struct inet_request_sock *ireq = inet_rsk(req); int err = -1; @@ -752,7 +754,7 @@ static int __tcp_v4_send_synack(struct sock *sk, struct request_sock *req, if (!dst && (dst = inet_csk_route_req(sk, req)) == NULL) return -1; - skb = tcp_make_synack(sk, dst, req); + skb = tcp_make_synack(sk, dst, req, rvp); if (skb) { struct tcphdr *th = tcp_hdr(skb); @@ -773,9 +775,10 @@ static int __tcp_v4_send_synack(struct sock *sk, struct request_sock *req, return err; } -static int tcp_v4_send_synack(struct sock *sk, struct request_sock *req) +static int tcp_v4_send_synack(struct sock *sk, struct request_sock *req, + struct request_values *rvp) { - return __tcp_v4_send_synack(sk, req, NULL); + return __tcp_v4_send_synack(sk, NULL, req, rvp); } /* @@ -848,7 +851,7 @@ static struct tcp_md5sig_key * struct tcp_md5sig_key *tcp_v4_md5_lookup(struct sock *sk, struct sock *addr_sk) { - return tcp_v4_md5_do_lookup(sk, inet_sk(addr_sk)->daddr); + return tcp_v4_md5_do_lookup(sk, inet_sk(addr_sk)->inet_daddr); } EXPORT_SYMBOL(tcp_v4_md5_lookup); @@ -923,7 +926,7 @@ EXPORT_SYMBOL(tcp_v4_md5_do_add); static int tcp_v4_md5_add_func(struct sock *sk, struct sock *addr_sk, u8 *newkey, u8 newkeylen) { - return tcp_v4_md5_do_add(sk, inet_sk(addr_sk)->daddr, + return tcp_v4_md5_do_add(sk, inet_sk(addr_sk)->inet_daddr, newkey, newkeylen); } @@ -1089,8 +1092,8 @@ int tcp_v4_md5_hash_skb(char *md5_hash, struct tcp_md5sig_key *key, __be32 saddr, daddr; if (sk) { - saddr = inet_sk(sk)->saddr; - daddr = inet_sk(sk)->daddr; + saddr = inet_sk(sk)->inet_saddr; + daddr = inet_sk(sk)->inet_daddr; } else if (req) { saddr = inet_rsk(req)->loc_addr; daddr = inet_rsk(req)->rmt_addr; @@ -1210,13 +1213,16 @@ static struct timewait_sock_ops tcp_timewait_sock_ops = { int tcp_v4_conn_request(struct sock *sk, struct sk_buff *skb) { - struct inet_request_sock *ireq; + struct tcp_extend_values tmp_ext; struct tcp_options_received tmp_opt; + u8 *hash_location; struct request_sock *req; + struct inet_request_sock *ireq; + struct tcp_sock *tp = tcp_sk(sk); + struct dst_entry *dst = NULL; __be32 saddr = ip_hdr(skb)->saddr; __be32 daddr = ip_hdr(skb)->daddr; __u32 isn = TCP_SKB_CB(skb)->when; - struct dst_entry *dst = NULL; #ifdef CONFIG_SYN_COOKIES int want_cookie = 0; #else @@ -1256,27 +1262,65 @@ int tcp_v4_conn_request(struct sock *sk, struct sk_buff *skb) tcp_rsk(req)->af_specific = &tcp_request_sock_ipv4_ops; #endif + ireq = inet_rsk(req); + ireq->loc_addr = daddr; + ireq->rmt_addr = saddr; + ireq->no_srccheck = inet_sk(sk)->transparent; + ireq->opt = tcp_v4_save_options(sk, skb); + + dst = inet_csk_route_req(sk, req); + if(!dst) + goto drop_and_free; + tcp_clear_options(&tmp_opt); - tmp_opt.mss_clamp = 536; - tmp_opt.user_mss = tcp_sk(sk)->rx_opt.user_mss; + tmp_opt.mss_clamp = TCP_MSS_DEFAULT; + tmp_opt.user_mss = tp->rx_opt.user_mss; + tcp_parse_options(skb, &tmp_opt, &hash_location, 0, dst); + + if (tmp_opt.cookie_plus > 0 && + tmp_opt.saw_tstamp && + !tp->rx_opt.cookie_out_never && + (sysctl_tcp_cookie_size > 0 || + (tp->cookie_values != NULL && + tp->cookie_values->cookie_desired > 0))) { + u8 *c; + u32 *mess = &tmp_ext.cookie_bakery[COOKIE_DIGEST_WORDS]; + int l = tmp_opt.cookie_plus - TCPOLEN_COOKIE_BASE; + + if (tcp_cookie_generator(&tmp_ext.cookie_bakery[0]) != 0) + goto drop_and_release; + + /* Secret recipe starts with IP addresses */ + *mess++ ^= daddr; + *mess++ ^= saddr; - tcp_parse_options(skb, &tmp_opt, 0); + /* plus variable length Initiator Cookie */ + c = (u8 *)mess; + while (l-- > 0) + *c++ ^= *hash_location++; + +#ifdef CONFIG_SYN_COOKIES + want_cookie = 0; /* not our kind of cookie */ +#endif + tmp_ext.cookie_out_never = 0; /* false */ + tmp_ext.cookie_plus = tmp_opt.cookie_plus; + } else if (!tp->rx_opt.cookie_in_always) { + /* redundant indications, but ensure initialization. */ + tmp_ext.cookie_out_never = 1; /* true */ + tmp_ext.cookie_plus = 0; + } else { + goto drop_and_release; + } + tmp_ext.cookie_in_always = tp->rx_opt.cookie_in_always; if (want_cookie && !tmp_opt.saw_tstamp) tcp_clear_options(&tmp_opt); tmp_opt.tstamp_ok = tmp_opt.saw_tstamp; - tcp_openreq_init(req, &tmp_opt, skb); - ireq = inet_rsk(req); - ireq->loc_addr = daddr; - ireq->rmt_addr = saddr; - ireq->no_srccheck = inet_sk(sk)->transparent; - ireq->opt = tcp_v4_save_options(sk, skb); - if (security_inet_conn_request(sk, skb, req)) - goto drop_and_free; + goto drop_and_release; if (!want_cookie) TCP_ECN_create_request(req, tcp_hdr(skb)); @@ -1301,10 +1345,9 @@ int tcp_v4_conn_request(struct sock *sk, struct sk_buff *skb) */ if (tmp_opt.saw_tstamp && tcp_death_row.sysctl_tw_recycle && - (dst = inet_csk_route_req(sk, req)) != NULL && (peer = rt_get_peer((struct rtable *)dst)) != NULL && peer->v4daddr == saddr) { - if (get_seconds() < peer->tcp_ts_stamp + TCP_PAWS_MSL && + if ((u32)get_seconds() - peer->tcp_ts_stamp < TCP_PAWS_MSL && (s32)(peer->tcp_ts - req->ts_recent) > TCP_PAWS_WINDOW) { NET_INC_STATS_BH(sock_net(sk), LINUX_MIB_PAWSPASSIVEREJECTED); @@ -1333,7 +1376,9 @@ int tcp_v4_conn_request(struct sock *sk, struct sk_buff *skb) } tcp_rsk(req)->snt_isn = isn; - if (__tcp_v4_send_synack(sk, req, dst) || want_cookie) + if (__tcp_v4_send_synack(sk, dst, req, + (struct request_values *)&tmp_ext) || + want_cookie) goto drop_and_free; inet_csk_reqsk_queue_hash_add(sk, req, TCP_TIMEOUT_INIT); @@ -1380,9 +1425,9 @@ struct sock *tcp_v4_syn_recv_sock(struct sock *sk, struct sk_buff *skb, newtp = tcp_sk(newsk); newinet = inet_sk(newsk); ireq = inet_rsk(req); - newinet->daddr = ireq->rmt_addr; - newinet->rcv_saddr = ireq->loc_addr; - newinet->saddr = ireq->loc_addr; + newinet->inet_daddr = ireq->rmt_addr; + newinet->inet_rcv_saddr = ireq->loc_addr; + newinet->inet_saddr = ireq->loc_addr; newinet->opt = ireq->opt; ireq->opt = NULL; newinet->mc_index = inet_iif(skb); @@ -1390,7 +1435,7 @@ struct sock *tcp_v4_syn_recv_sock(struct sock *sk, struct sk_buff *skb, inet_csk(newsk)->icsk_ext_hdr_len = 0; if (newinet->opt) inet_csk(newsk)->icsk_ext_hdr_len = newinet->opt->optlen; - newinet->id = newtp->write_seq ^ jiffies; + newinet->inet_id = newtp->write_seq ^ jiffies; tcp_mtup_init(newsk); tcp_sync_mss(newsk, dst_mtu(dst)); @@ -1403,7 +1448,8 @@ struct sock *tcp_v4_syn_recv_sock(struct sock *sk, struct sk_buff *skb, #ifdef CONFIG_TCP_MD5SIG /* Copy over the MD5 key from the original socket */ - if ((key = tcp_v4_md5_do_lookup(sk, newinet->daddr)) != NULL) { + key = tcp_v4_md5_do_lookup(sk, newinet->inet_daddr); + if (key != NULL) { /* * We're using one, so create a matching key * on the newsk structure. If we fail to get @@ -1412,7 +1458,7 @@ struct sock *tcp_v4_syn_recv_sock(struct sock *sk, struct sk_buff *skb, */ char *newkey = kmemdup(key->key, key->keylen, GFP_ATOMIC); if (newkey != NULL) - tcp_v4_md5_do_add(newsk, newinet->daddr, + tcp_v4_md5_do_add(newsk, newinet->inet_daddr, newkey, key->keylen); newsk->sk_route_caps &= ~NETIF_F_GSO_MASK; } @@ -1711,8 +1757,8 @@ int tcp_v4_remember_stamp(struct sock *sk) struct inet_peer *peer = NULL; int release_it = 0; - if (!rt || rt->rt_dst != inet->daddr) { - peer = inet_getpeer(inet->daddr, 1); + if (!rt || rt->rt_dst != inet->inet_daddr) { + peer = inet_getpeer(inet->inet_daddr, 1); release_it = 1; } else { if (!rt->peer) @@ -1722,9 +1768,9 @@ int tcp_v4_remember_stamp(struct sock *sk) if (peer) { if ((s32)(peer->tcp_ts - tp->rx_opt.ts_recent) <= 0 || - (peer->tcp_ts_stamp + TCP_PAWS_MSL < get_seconds() && - peer->tcp_ts_stamp <= tp->rx_opt.ts_recent_stamp)) { - peer->tcp_ts_stamp = tp->rx_opt.ts_recent_stamp; + ((u32)get_seconds() - peer->tcp_ts_stamp > TCP_PAWS_MSL && + peer->tcp_ts_stamp <= (u32)tp->rx_opt.ts_recent_stamp)) { + peer->tcp_ts_stamp = (u32)tp->rx_opt.ts_recent_stamp; peer->tcp_ts = tp->rx_opt.ts_recent; } if (release_it) @@ -1743,9 +1789,9 @@ int tcp_v4_tw_remember_stamp(struct inet_timewait_sock *tw) const struct tcp_timewait_sock *tcptw = tcp_twsk((struct sock *)tw); if ((s32)(peer->tcp_ts - tcptw->tw_ts_recent) <= 0 || - (peer->tcp_ts_stamp + TCP_PAWS_MSL < get_seconds() && - peer->tcp_ts_stamp <= tcptw->tw_ts_recent_stamp)) { - peer->tcp_ts_stamp = tcptw->tw_ts_recent_stamp; + ((u32)get_seconds() - peer->tcp_ts_stamp > TCP_PAWS_MSL && + peer->tcp_ts_stamp <= (u32)tcptw->tw_ts_recent_stamp)) { + peer->tcp_ts_stamp = (u32)tcptw->tw_ts_recent_stamp; peer->tcp_ts = tcptw->tw_ts_recent; } inet_putpeer(peer); @@ -1810,7 +1856,7 @@ static int tcp_v4_init_sock(struct sock *sk) */ tp->snd_ssthresh = TCP_INFINITE_SSTHRESH; tp->snd_cwnd_clamp = ~0; - tp->mss_cache = 536; + tp->mss_cache = TCP_MSS_DEFAULT; tp->reordering = sysctl_tcp_reordering; icsk->icsk_ca_ops = &tcp_init_congestion_ops; @@ -1826,6 +1872,19 @@ static int tcp_v4_init_sock(struct sock *sk) tp->af_specific = &tcp_sock_ipv4_specific; #endif + /* TCP Cookie Transactions */ + if (sysctl_tcp_cookie_size > 0) { + /* Default, cookies without s_data_payload. */ + tp->cookie_values = + kzalloc(sizeof(*tp->cookie_values), + sk->sk_allocation); + if (tp->cookie_values != NULL) + kref_init(&tp->cookie_values->kref); + } + /* Presumed zeroed, in order of appearance: + * cookie_in_always, cookie_out_never, + * s_data_constant, s_data_in, s_data_out + */ sk->sk_sndbuf = sysctl_tcp_wmem[1]; sk->sk_rcvbuf = sysctl_tcp_rmem[1]; @@ -1879,6 +1938,13 @@ void tcp_v4_destroy_sock(struct sock *sk) sk->sk_sndmsg_page = NULL; } + /* TCP Cookie Transactions */ + if (tp->cookie_values != NULL) { + kref_put(&tp->cookie_values->kref, + tcp_cookie_values_release); + tp->cookie_values = NULL; + } + percpu_counter_dec(&tcp_sockets_allocated); } @@ -2000,7 +2066,7 @@ static void *established_get_first(struct seq_file *seq) struct net *net = seq_file_net(seq); void *rc = NULL; - for (st->bucket = 0; st->bucket < tcp_hashinfo.ehash_size; ++st->bucket) { + for (st->bucket = 0; st->bucket <= tcp_hashinfo.ehash_mask; ++st->bucket) { struct sock *sk; struct hlist_nulls_node *node; struct inet_timewait_sock *tw; @@ -2061,10 +2127,10 @@ get_tw: st->state = TCP_SEQ_STATE_ESTABLISHED; /* Look for next non empty bucket */ - while (++st->bucket < tcp_hashinfo.ehash_size && + while (++st->bucket <= tcp_hashinfo.ehash_mask && empty_bucket(st)) ; - if (st->bucket >= tcp_hashinfo.ehash_size) + if (st->bucket > tcp_hashinfo.ehash_mask) return NULL; spin_lock_bh(inet_ehash_lockp(&tcp_hashinfo, st->bucket)); @@ -2225,7 +2291,7 @@ static void get_openreq4(struct sock *sk, struct request_sock *req, " %02X %08X:%08X %02X:%08lX %08X %5d %8d %u %d %p%n", i, ireq->loc_addr, - ntohs(inet_sk(sk)->sport), + ntohs(inet_sk(sk)->inet_sport), ireq->rmt_addr, ntohs(ireq->rmt_port), TCP_SYN_RECV, @@ -2248,10 +2314,11 @@ static void get_tcp4_sock(struct sock *sk, struct seq_file *f, int i, int *len) struct tcp_sock *tp = tcp_sk(sk); const struct inet_connection_sock *icsk = inet_csk(sk); struct inet_sock *inet = inet_sk(sk); - __be32 dest = inet->daddr; - __be32 src = inet->rcv_saddr; - __u16 destp = ntohs(inet->dport); - __u16 srcp = ntohs(inet->sport); + __be32 dest = inet->inet_daddr; + __be32 src = inet->inet_rcv_saddr; + __u16 destp = ntohs(inet->inet_dport); + __u16 srcp = ntohs(inet->inet_sport); + int rx_queue; if (icsk->icsk_pending == ICSK_TIME_RETRANS) { timer_active = 1; @@ -2267,12 +2334,19 @@ static void get_tcp4_sock(struct sock *sk, struct seq_file *f, int i, int *len) timer_expires = jiffies; } + if (sk->sk_state == TCP_LISTEN) + rx_queue = sk->sk_ack_backlog; + else + /* + * because we dont lock socket, we might find a transient negative value + */ + rx_queue = max_t(int, tp->rcv_nxt - tp->copied_seq, 0); + seq_printf(f, "%4d: %08X:%04X %08X:%04X %02X %08X:%08X %02X:%08lX " "%08X %5d %8d %lu %d %p %lu %lu %u %u %d%n", i, src, srcp, dest, destp, sk->sk_state, tp->write_seq - tp->snd_una, - sk->sk_state == TCP_LISTEN ? sk->sk_ack_backlog : - (tp->rcv_nxt - tp->copied_seq), + rx_queue, timer_active, jiffies_to_clock_t(timer_expires - jiffies), icsk->icsk_retransmits, @@ -2463,12 +2537,17 @@ static int __net_init tcp_sk_init(struct net *net) static void __net_exit tcp_sk_exit(struct net *net) { inet_ctl_sock_destroy(net->ipv4.tcp_sock); - inet_twsk_purge(net, &tcp_hashinfo, &tcp_death_row, AF_INET); +} + +static void __net_exit tcp_sk_exit_batch(struct list_head *net_exit_list) +{ + inet_twsk_purge(&tcp_hashinfo, &tcp_death_row, AF_INET); } static struct pernet_operations __net_initdata tcp_sk_ops = { - .init = tcp_sk_init, - .exit = tcp_sk_exit, + .init = tcp_sk_init, + .exit = tcp_sk_exit, + .exit_batch = tcp_sk_exit_batch, }; void __init tcp_v4_init(void) diff --git a/net/ipv4/tcp_lp.c b/net/ipv4/tcp_lp.c index ce3c41ff50b2..de870377fbba 100644 --- a/net/ipv4/tcp_lp.c +++ b/net/ipv4/tcp_lp.c @@ -143,8 +143,8 @@ static u32 tcp_lp_remote_hz_estimator(struct sock *sk) goto out; /* we can't calc remote HZ with no different!! */ - if (tp->rx_opt.rcv_tsval == lp->remote_ref_time - || tp->rx_opt.rcv_tsecr == lp->local_ref_time) + if (tp->rx_opt.rcv_tsval == lp->remote_ref_time || + tp->rx_opt.rcv_tsecr == lp->local_ref_time) goto out; m = HZ * (tp->rx_opt.rcv_tsval - diff --git a/net/ipv4/tcp_minisocks.c b/net/ipv4/tcp_minisocks.c index 4c03598ed924..87accec8d097 100644 --- a/net/ipv4/tcp_minisocks.c +++ b/net/ipv4/tcp_minisocks.c @@ -26,13 +26,7 @@ #include <net/inet_common.h> #include <net/xfrm.h> -#ifdef CONFIG_SYSCTL -#define SYNC_INIT 0 /* let the user enable it */ -#else -#define SYNC_INIT 1 -#endif - -int sysctl_tcp_syncookies __read_mostly = SYNC_INIT; +int sysctl_tcp_syncookies __read_mostly = 1; EXPORT_SYMBOL(sysctl_tcp_syncookies); int sysctl_tcp_abort_on_overflow __read_mostly; @@ -96,13 +90,14 @@ enum tcp_tw_status tcp_timewait_state_process(struct inet_timewait_sock *tw, struct sk_buff *skb, const struct tcphdr *th) { - struct tcp_timewait_sock *tcptw = tcp_twsk((struct sock *)tw); struct tcp_options_received tmp_opt; + u8 *hash_location; + struct tcp_timewait_sock *tcptw = tcp_twsk((struct sock *)tw); int paws_reject = 0; - tmp_opt.saw_tstamp = 0; if (th->doff > (sizeof(*th) >> 2) && tcptw->tw_ts_recent_stamp) { - tcp_parse_options(skb, &tmp_opt, 0); + tmp_opt.tstamp_ok = 1; + tcp_parse_options(skb, &tmp_opt, &hash_location, 1, NULL); if (tmp_opt.saw_tstamp) { tmp_opt.ts_recent = tcptw->tw_ts_recent; @@ -389,14 +384,43 @@ struct sock *tcp_create_openreq_child(struct sock *sk, struct request_sock *req, const struct inet_request_sock *ireq = inet_rsk(req); struct tcp_request_sock *treq = tcp_rsk(req); struct inet_connection_sock *newicsk = inet_csk(newsk); - struct tcp_sock *newtp; + struct tcp_sock *newtp = tcp_sk(newsk); + struct tcp_sock *oldtp = tcp_sk(sk); + struct tcp_cookie_values *oldcvp = oldtp->cookie_values; + + /* TCP Cookie Transactions require space for the cookie pair, + * as it differs for each connection. There is no need to + * copy any s_data_payload stored at the original socket. + * Failure will prevent resuming the connection. + * + * Presumed copied, in order of appearance: + * cookie_in_always, cookie_out_never + */ + if (oldcvp != NULL) { + struct tcp_cookie_values *newcvp = + kzalloc(sizeof(*newtp->cookie_values), + GFP_ATOMIC); + + if (newcvp != NULL) { + kref_init(&newcvp->kref); + newcvp->cookie_desired = + oldcvp->cookie_desired; + newtp->cookie_values = newcvp; + } else { + /* Not Yet Implemented */ + newtp->cookie_values = NULL; + } + } /* Now setup tcp_sock */ - newtp = tcp_sk(newsk); newtp->pred_flags = 0; - newtp->rcv_wup = newtp->copied_seq = newtp->rcv_nxt = treq->rcv_isn + 1; - newtp->snd_sml = newtp->snd_una = newtp->snd_nxt = treq->snt_isn + 1; - newtp->snd_up = treq->snt_isn + 1; + + newtp->rcv_wup = newtp->copied_seq = + newtp->rcv_nxt = treq->rcv_isn + 1; + + newtp->snd_sml = newtp->snd_una = + newtp->snd_nxt = newtp->snd_up = + treq->snt_isn + 1 + tcp_s_data_size(oldtp); tcp_prequeue_init(newtp); @@ -429,8 +453,8 @@ struct sock *tcp_create_openreq_child(struct sock *sk, struct request_sock *req, tcp_set_ca_state(newsk, TCP_CA_Open); tcp_init_xmit_timers(newsk); skb_queue_head_init(&newtp->out_of_order_queue); - newtp->write_seq = treq->snt_isn + 1; - newtp->pushed_seq = newtp->write_seq; + newtp->write_seq = newtp->pushed_seq = + treq->snt_isn + 1 + tcp_s_data_size(oldtp); newtp->rx_opt.saw_tstamp = 0; @@ -476,7 +500,7 @@ struct sock *tcp_create_openreq_child(struct sock *sk, struct request_sock *req, if (newtp->af_specific->md5_lookup(sk, newsk)) newtp->tcp_header_len += TCPOLEN_MD5SIG_ALIGNED; #endif - if (skb->len >= TCP_MIN_RCVMSS+newtp->tcp_header_len) + if (skb->len >= TCP_MSS_DEFAULT + newtp->tcp_header_len) newicsk->icsk_ack.last_seg_size = skb->len - newtp->tcp_header_len; newtp->rx_opt.mss_clamp = req->mss; TCP_ECN_openreq_child(newtp, req); @@ -495,15 +519,16 @@ struct sock *tcp_check_req(struct sock *sk, struct sk_buff *skb, struct request_sock *req, struct request_sock **prev) { + struct tcp_options_received tmp_opt; + u8 *hash_location; + struct sock *child; const struct tcphdr *th = tcp_hdr(skb); __be32 flg = tcp_flag_word(th) & (TCP_FLAG_RST|TCP_FLAG_SYN|TCP_FLAG_ACK); int paws_reject = 0; - struct tcp_options_received tmp_opt; - struct sock *child; - tmp_opt.saw_tstamp = 0; - if (th->doff > (sizeof(struct tcphdr)>>2)) { - tcp_parse_options(skb, &tmp_opt, 0); + if ((th->doff > (sizeof(*th) >> 2)) && (req->ts_recent)) { + tmp_opt.tstamp_ok = 1; + tcp_parse_options(skb, &tmp_opt, &hash_location, 1, NULL); if (tmp_opt.saw_tstamp) { tmp_opt.ts_recent = req->ts_recent; @@ -537,7 +562,7 @@ struct sock *tcp_check_req(struct sock *sk, struct sk_buff *skb, * Enforce "SYN-ACK" according to figure 8, figure 6 * of RFC793, fixed by RFC1122. */ - req->rsk_ops->rtx_syn_ack(sk, req); + req->rsk_ops->rtx_syn_ack(sk, req, NULL); return NULL; } @@ -596,7 +621,8 @@ struct sock *tcp_check_req(struct sock *sk, struct sk_buff *skb, * Invalid ACK: reset will be sent by listening socket */ if ((flg & TCP_FLAG_ACK) && - (TCP_SKB_CB(skb)->ack_seq != tcp_rsk(req)->snt_isn + 1)) + (TCP_SKB_CB(skb)->ack_seq != + tcp_rsk(req)->snt_isn + 1 + tcp_s_data_size(tcp_sk(sk)))) return sk; /* Also, it would be not so bad idea to check rcv_tsecr, which diff --git a/net/ipv4/tcp_output.c b/net/ipv4/tcp_output.c index fcd278a7080e..93316a96d820 100644 --- a/net/ipv4/tcp_output.c +++ b/net/ipv4/tcp_output.c @@ -59,6 +59,10 @@ int sysctl_tcp_base_mss __read_mostly = 512; /* By default, RFC2861 behavior. */ int sysctl_tcp_slow_start_after_idle __read_mostly = 1; +int sysctl_tcp_cookie_size __read_mostly = 0; /* TCP_COOKIE_MAX */ +EXPORT_SYMBOL_GPL(sysctl_tcp_cookie_size); + + /* Account for new data that has been sent to the network. */ static void tcp_event_new_data_sent(struct sock *sk, struct sk_buff *skb) { @@ -362,15 +366,45 @@ static inline int tcp_urg_mode(const struct tcp_sock *tp) #define OPTION_TS (1 << 1) #define OPTION_MD5 (1 << 2) #define OPTION_WSCALE (1 << 3) +#define OPTION_COOKIE_EXTENSION (1 << 4) struct tcp_out_options { u8 options; /* bit field of OPTION_* */ u8 ws; /* window scale, 0 to disable */ u8 num_sack_blocks; /* number of SACK blocks to include */ + u8 hash_size; /* bytes in hash_location */ u16 mss; /* 0 to disable */ __u32 tsval, tsecr; /* need to include OPTION_TS */ + __u8 *hash_location; /* temporary pointer, overloaded */ }; +/* The sysctl int routines are generic, so check consistency here. + */ +static u8 tcp_cookie_size_check(u8 desired) +{ + if (desired > 0) { + /* previously specified */ + return desired; + } + if (sysctl_tcp_cookie_size <= 0) { + /* no default specified */ + return 0; + } + if (sysctl_tcp_cookie_size <= TCP_COOKIE_MIN) { + /* value too small, specify minimum */ + return TCP_COOKIE_MIN; + } + if (sysctl_tcp_cookie_size >= TCP_COOKIE_MAX) { + /* value too large, specify maximum */ + return TCP_COOKIE_MAX; + } + if (0x1 & sysctl_tcp_cookie_size) { + /* 8-bit multiple, illegal, fix it */ + return (u8)(sysctl_tcp_cookie_size + 0x1); + } + return (u8)sysctl_tcp_cookie_size; +} + /* Write previously computed TCP options to the packet. * * Beware: Something in the Internet is very sensitive to the ordering of @@ -385,17 +419,34 @@ struct tcp_out_options { * (but it may well be that other scenarios fail similarly). */ static void tcp_options_write(__be32 *ptr, struct tcp_sock *tp, - const struct tcp_out_options *opts, - __u8 **md5_hash) { - if (unlikely(OPTION_MD5 & opts->options)) { - *ptr++ = htonl((TCPOPT_NOP << 24) | - (TCPOPT_NOP << 16) | - (TCPOPT_MD5SIG << 8) | - TCPOLEN_MD5SIG); - *md5_hash = (__u8 *)ptr; + struct tcp_out_options *opts) +{ + u8 options = opts->options; /* mungable copy */ + + /* Having both authentication and cookies for security is redundant, + * and there's certainly not enough room. Instead, the cookie-less + * extension variant is proposed. + * + * Consider the pessimal case with authentication. The options + * could look like: + * COOKIE|MD5(20) + MSS(4) + SACK|TS(12) + WSCALE(4) == 40 + */ + if (unlikely(OPTION_MD5 & options)) { + if (unlikely(OPTION_COOKIE_EXTENSION & options)) { + *ptr++ = htonl((TCPOPT_COOKIE << 24) | + (TCPOLEN_COOKIE_BASE << 16) | + (TCPOPT_MD5SIG << 8) | + TCPOLEN_MD5SIG); + } else { + *ptr++ = htonl((TCPOPT_NOP << 24) | + (TCPOPT_NOP << 16) | + (TCPOPT_MD5SIG << 8) | + TCPOLEN_MD5SIG); + } + options &= ~OPTION_COOKIE_EXTENSION; + /* overload cookie hash location */ + opts->hash_location = (__u8 *)ptr; ptr += 4; - } else { - *md5_hash = NULL; } if (unlikely(opts->mss)) { @@ -404,12 +455,13 @@ static void tcp_options_write(__be32 *ptr, struct tcp_sock *tp, opts->mss); } - if (likely(OPTION_TS & opts->options)) { - if (unlikely(OPTION_SACK_ADVERTISE & opts->options)) { + if (likely(OPTION_TS & options)) { + if (unlikely(OPTION_SACK_ADVERTISE & options)) { *ptr++ = htonl((TCPOPT_SACK_PERM << 24) | (TCPOLEN_SACK_PERM << 16) | (TCPOPT_TIMESTAMP << 8) | TCPOLEN_TIMESTAMP); + options &= ~OPTION_SACK_ADVERTISE; } else { *ptr++ = htonl((TCPOPT_NOP << 24) | (TCPOPT_NOP << 16) | @@ -420,15 +472,52 @@ static void tcp_options_write(__be32 *ptr, struct tcp_sock *tp, *ptr++ = htonl(opts->tsecr); } - if (unlikely(OPTION_SACK_ADVERTISE & opts->options && - !(OPTION_TS & opts->options))) { + /* Specification requires after timestamp, so do it now. + * + * Consider the pessimal case without authentication. The options + * could look like: + * MSS(4) + SACK|TS(12) + COOKIE(20) + WSCALE(4) == 40 + */ + if (unlikely(OPTION_COOKIE_EXTENSION & options)) { + __u8 *cookie_copy = opts->hash_location; + u8 cookie_size = opts->hash_size; + + /* 8-bit multiple handled in tcp_cookie_size_check() above, + * and elsewhere. + */ + if (0x2 & cookie_size) { + __u8 *p = (__u8 *)ptr; + + /* 16-bit multiple */ + *p++ = TCPOPT_COOKIE; + *p++ = TCPOLEN_COOKIE_BASE + cookie_size; + *p++ = *cookie_copy++; + *p++ = *cookie_copy++; + ptr++; + cookie_size -= 2; + } else { + /* 32-bit multiple */ + *ptr++ = htonl(((TCPOPT_NOP << 24) | + (TCPOPT_NOP << 16) | + (TCPOPT_COOKIE << 8) | + TCPOLEN_COOKIE_BASE) + + cookie_size); + } + + if (cookie_size > 0) { + memcpy(ptr, cookie_copy, cookie_size); + ptr += (cookie_size / 4); + } + } + + if (unlikely(OPTION_SACK_ADVERTISE & options)) { *ptr++ = htonl((TCPOPT_NOP << 24) | (TCPOPT_NOP << 16) | (TCPOPT_SACK_PERM << 8) | TCPOLEN_SACK_PERM); } - if (unlikely(OPTION_WSCALE & opts->options)) { + if (unlikely(OPTION_WSCALE & options)) { *ptr++ = htonl((TCPOPT_NOP << 24) | (TCPOPT_WINDOW << 16) | (TCPOLEN_WINDOW << 8) | @@ -463,13 +552,18 @@ static unsigned tcp_syn_options(struct sock *sk, struct sk_buff *skb, struct tcp_out_options *opts, struct tcp_md5sig_key **md5) { struct tcp_sock *tp = tcp_sk(sk); - unsigned size = 0; + struct tcp_cookie_values *cvp = tp->cookie_values; + struct dst_entry *dst = __sk_dst_get(sk); + unsigned remaining = MAX_TCP_OPTION_SPACE; + u8 cookie_size = (!tp->rx_opt.cookie_out_never && cvp != NULL) ? + tcp_cookie_size_check(cvp->cookie_desired) : + 0; #ifdef CONFIG_TCP_MD5SIG *md5 = tp->af_specific->md5_lookup(sk, sk); if (*md5) { opts->options |= OPTION_MD5; - size += TCPOLEN_MD5SIG_ALIGNED; + remaining -= TCPOLEN_MD5SIG_ALIGNED; } #else *md5 = NULL; @@ -485,26 +579,76 @@ static unsigned tcp_syn_options(struct sock *sk, struct sk_buff *skb, * SACKs don't matter, we never delay an ACK when we have any of those * going out. */ opts->mss = tcp_advertise_mss(sk); - size += TCPOLEN_MSS_ALIGNED; + remaining -= TCPOLEN_MSS_ALIGNED; - if (likely(sysctl_tcp_timestamps && *md5 == NULL)) { + if (likely(sysctl_tcp_timestamps && + !dst_feature(dst, RTAX_FEATURE_NO_TSTAMP) && + *md5 == NULL)) { opts->options |= OPTION_TS; opts->tsval = TCP_SKB_CB(skb)->when; opts->tsecr = tp->rx_opt.t |