diff options
Diffstat (limited to 'net')
154 files changed, 4229 insertions, 2960 deletions
diff --git a/net/8021q/vlan.c b/net/8021q/vlan.c index 8836575f9d7..511afe72af3 100644 --- a/net/8021q/vlan.c +++ b/net/8021q/vlan.c @@ -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(); - - unregister_netdevice(dev); + if (!grp->killall) { + vlan_group_set_device(grp, vlan_id, NULL); + synchronize_net(); + } + unregister_netdevice_queue(dev, head); /* If the group is now empty, kill off the group. */ if (grp->nr_vlans == 0) { @@ -183,6 +184,34 @@ void unregister_vlan_dev(struct net_device *dev) dev_put(real_dev); } +void unregister_vlan_dev_alls(struct vlan_group *grp) +{ + LIST_HEAD(list); + int i; + struct net_device *vlandev; + struct vlan_group save; + + memcpy(&save, grp, sizeof(save)); + memset(&grp->vlan_devices_arrays, 0, sizeof(grp->vlan_devices_arrays)); + grp->killall = 1; + + synchronize_net(); + + /* Delete all VLANs for this dev. */ + for (i = 0; i < VLAN_GROUP_ARRAY_LEN; i++) { + vlandev = vlan_group_get_device(&save, i); + if (!vlandev) + continue; + + unregister_vlan_dev(vlandev, &list); + if (grp->nr_vlans == 0) + break; + } + unregister_netdevice_many(&list); + for (i = 0; i < VLAN_GROUP_ARRAY_SPLIT_PARTS; i++) + kfree(save.vlan_devices_arrays[i]); +} + static void vlan_transfer_operstate(const struct net_device *dev, struct net_device *vlandev) { @@ -524,19 +553,7 @@ static int vlan_device_event(struct notifier_block *unused, unsigned long event, break; case NETDEV_UNREGISTER: - /* Delete all VLANs for this dev. */ - for (i = 0; i < VLAN_GROUP_ARRAY_LEN; i++) { - vlandev = vlan_group_get_device(grp, i); - if (!vlandev) - continue; - - /* unregistration of last vlan destroys group, abort - * afterwards */ - if (grp->nr_vlans == 1) - i = VLAN_GROUP_ARRAY_LEN; - - unregister_vlan_dev(vlandev); - } + unregister_vlan_dev_alls(grp); break; } @@ -642,7 +659,7 @@ 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; diff --git a/net/8021q/vlan.h b/net/8021q/vlan.h index 82570bc2a18..68f9290e683 100644 --- a/net/8021q/vlan.h +++ b/net/8021q/vlan.h @@ -82,14 +82,14 @@ 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_dev.c b/net/8021q/vlan_dev.c index 4198ec5c8ab..790fd55ec31 100644 --- a/net/8021q/vlan_dev.c +++ b/net/8021q/vlan_dev.c @@ -393,7 +393,7 @@ 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]; @@ -626,6 +626,17 @@ 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) @@ -791,6 +802,7 @@ static const struct net_device_ops vlan_netdev_ops = { .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 }; @@ -813,6 +825,7 @@ static const struct net_device_ops vlan_netdev_accel_ops = { .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/appletalk/ddp.c b/net/appletalk/ddp.c index b1a4290996b..abe38014b7f 100644 --- a/net/appletalk/ddp.c +++ b/net/appletalk/ddp.c @@ -1821,7 +1821,7 @@ static int atalk_compat_ioctl(struct socket *sock, unsigned int cmd, unsigned lo #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, diff --git a/net/atm/common.c b/net/atm/common.c index 950bd16d238..d61e051e0a3 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/pvc.c b/net/atm/pvc.c index d4c024504f9..a6e1fdbae87 100644 --- a/net/atm/pvc.c +++ b/net/atm/pvc.c @@ -137,7 +137,7 @@ 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 f90d143c4b2..81935423331 100644 --- a/net/atm/svc.c +++ b/net/atm/svc.c @@ -666,7 +666,7 @@ 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 f4546073037..f05306f168f 100644 --- a/net/ax25/af_ax25.c +++ b/net/ax25/af_ax25.c @@ -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 8cfb5a84984..399e59c9c6c 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; @@ -257,7 +257,7 @@ 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/sock.c b/net/bluetooth/bnep/sock.c index e857628b0b2..0a2c5460bb4 100644 --- a/net/bluetooth/bnep/sock.c +++ b/net/bluetooth/bnep/sock.c @@ -222,7 +222,7 @@ 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 16b0fad74f6..de7c8040bc5 100644 --- a/net/bluetooth/cmtp/sock.c +++ b/net/bluetooth/cmtp/sock.c @@ -217,7 +217,7 @@ 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_sock.c b/net/bluetooth/hci_sock.c index 75302a98606..e7395f23198 100644 --- a/net/bluetooth/hci_sock.c +++ b/net/bluetooth/hci_sock.c @@ -687,7 +687,7 @@ 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/sock.c b/net/bluetooth/hidp/sock.c index 37c9d7d2e68..4beb6a7a295 100644 --- a/net/bluetooth/hidp/sock.c +++ b/net/bluetooth/hidp/sock.c @@ -268,7 +268,7 @@ 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 77e9fb130ad..d65101d92ee 100644 --- a/net/bluetooth/l2cap.c +++ b/net/bluetooth/l2cap.c @@ -3919,7 +3919,7 @@ 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, diff --git a/net/bluetooth/rfcomm/sock.c b/net/bluetooth/rfcomm/sock.c index 8a20aaf1f23..d3bfc1b0afb 100644 --- a/net/bluetooth/rfcomm/sock.c +++ b/net/bluetooth/rfcomm/sock.c @@ -703,7 +703,7 @@ 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 +1101,7 @@ 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 77f4153bdb5..694a65541b7 100644 --- a/net/bluetooth/sco.c +++ b/net/bluetooth/sco.c @@ -993,7 +993,7 @@ 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 07a07770c8b..1a99c4e04e8 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_if.c b/net/bridge/br_if.c index b1b3b0fbf41..2117e5ba24c 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; @@ -462,15 +462,14 @@ 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/can/af_can.c b/net/can/af_can.c index 60683211567..3f2eb27e1ff 100644 --- a/net/can/af_can.c +++ b/net/can/af_can.c @@ -842,7 +842,7 @@ 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 597da4f8f88..2f47039c79d 100644 --- a/net/can/bcm.c +++ b/net/can/bcm.c @@ -1534,7 +1534,7 @@ 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); diff --git a/net/can/raw.c b/net/can/raw.c index b5e897922d3..6e77db58b9e 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); diff --git a/net/compat.c b/net/compat.c index a407c3addba..6a2f75fb3f4 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 +752,36 @@ 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 = + (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 +843,10 @@ 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/datagram.c b/net/core/datagram.c index 1c6cf3a1a4f..4d57f5e12b0 100644 --- a/net/core/datagram.c +++ b/net/core/datagram.c @@ -262,6 +262,7 @@ 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 b8f74cfb1bf..68a1bb68b5a 100644 --- a/net/core/dev.c +++ b/net/core/dev.c @@ -193,18 +193,15 @@ 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 & (NETDEV_HASHENTRIES - 1)]; } 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 */ @@ -217,12 +214,15 @@ static int list_netdevice(struct net_device *dev) 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)); + 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(); @@ -231,7 +231,7 @@ static void unlist_netdevice(struct net_device *dev) write_lock_bh(&dev_base_lock); list_del(&dev->dev_list); hlist_del(&dev->name_hlist); - hlist_del(&dev->index_hlist); + hlist_del_rcu(&dev->index_hlist); write_unlock_bh(&dev_base_lock); } @@ -649,6 +649,31 @@ struct net_device *__dev_get_by_index(struct net *net, int ifindex) } 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 +690,11 @@ 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); @@ -1791,13 +1816,25 @@ EXPORT_SYMBOL(skb_tx_hash); 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 { + queue_index = 0; + 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); - else 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); @@ -2291,7 +2328,7 @@ 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 */ @@ -2604,20 +2641,13 @@ 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); @@ -2937,15 +2967,15 @@ 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; @@ -4635,59 +4665,76 @@ 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); + } 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, @@ -4836,6 +4883,12 @@ 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; @@ -5237,25 +5290,48 @@ 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_add_tail(&dev->unreg_list, head); + } else { + rollback_registered(dev); + /* Finish processing unregister after unlock */ + net_set_todo(dev); + } +} +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); +EXPORT_SYMBOL(unregister_netdevice_many); /** * unregister_netdev - remove device from the kernel @@ -5483,7 +5559,7 @@ 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; @@ -5582,7 +5658,7 @@ restart: /* Delete virtual devices */ if (dev->rtnl_link_ops && dev->rtnl_link_ops->dellink) { - dev->rtnl_link_ops->dellink(dev); + dev->rtnl_link_ops->dellink(dev, NULL); goto restart; } diff --git a/net/core/ethtool.c b/net/core/ethtool.c index 4c12ddb5f5e..d8aee584e8d 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/filter.c b/net/core/filter.c index d1d779ca096..08db7b9143a 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 8569310268a..393b1d8618e 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/net-sysfs.c b/net/core/net-sysfs.c index 427ded84122..89de182353b 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), @@ -503,9 +547,13 @@ int netdev_register_kobject(struct net_device *net) *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) diff --git a/net/core/pktgen.c b/net/core/pktgen.c index 6eb8d47cbf3..5ce017bf4af 100644 --- a/net/core/pktgen.c +++ b/net/core/pktgen.c @@ -3446,12 +3446,14 @@ 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: @@ -3473,6 +3475,7 @@ 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 */ diff --git a/net/core/rtnetlink.c b/net/core/rtnetlink.c index eb42873f2a3..391a62cd9df 100644 --- a/net/core/rtnetlink.c +++ b/net/core/rtnetlink.c @@ -248,7 +248,7 @@ 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; @@ -277,13 +277,13 @@ 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) @@ -682,22 +682,33 @@ 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; } @@ -910,9 +921,9 @@ 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; @@ -922,11 +933,9 @@ static int rtnl_setlink(struct sk_buff *skb, struct nlmsghdr *nlh, void *arg) } if ((err = validate_linkmsg(dev, tb)) < 0) - goto errout_dev; + goto errout; err = do_setlink(dev, ifm, tb, ifname, 0); -errout_dev: - dev_put(dev); errout: return err; } @@ -963,7 +972,7 @@ 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; } @@ -1154,6 +1163,7 @@ 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 +1173,23 @@ 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 +1197,8 @@ 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; } diff --git a/net/core/sock.c b/net/core/sock.c index 7626b6aacd6..5a51512f638 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; @@ -702,6 +713,12 @@ 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 +918,10 @@ 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 +960,8 @@ 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 +1005,7 @@ 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/dccp/ccids/ccid2.c b/net/dccp/ccids/ccid2.c index e8cf99e880b..a47a8c918ee 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 326ac90fb90..1ec6a30103b 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 34dcc798c45..bcd7632299f 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 e5a24414384..03263577665 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 7302e1498d4..00028d4b09d 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)); diff --git a/net/dccp/ipv6.c b/net/dccp/ipv6.c index e48ca5d4565..6d89f9f7d5d 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); @@ -510,11 +510,9 @@ 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 +640,8 @@ 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 +969,9 @@ 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 +984,7 @@ 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 +1017,7 @@ 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 +1026,7 @@ 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 +1035,8 @@ 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 +1047,7 @@ 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; } diff --git a/net/dccp/output.c b/net/dccp/output.c index c96119fda68..d6bb753bf6a 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 37731da4148..dc328425fa2 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 a156319fd0a..671cd1413d5 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 162d1e683c3..bbfeb5eae46 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 7a58c87baf1..664965c87e1 100644 --- a/net/decnet/af_decnet.c +++ b/net/decnet/af_decnet.c @@ -1955,7 +1955,7 @@ 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 +2325,7 @@ 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/econet/af_econet.c b/net/econet/af_econet.c index 0e0254fd767..5e9426a11c3 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) */ @@ -742,7 +742,7 @@ 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/ieee802154/af_ieee802154.c b/net/ieee802154/af_ieee802154.c index cd949d5e451..309348fba72 100644 --- a/net/ieee802154/af_ieee802154.c +++ b/net/ieee802154/af_ieee802154.c @@ -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 a413b1bf446..9aac5aee157 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/raw.c b/net/ieee802154/raw.c index 30e74eee07d..9c9b85c0003 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/ipv4/af_inet.c b/net/ipv4/af_inet.c index 57737b8d171..538e84d0bcb 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; @@ -354,7 +354,7 @@ 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 +364,7 @@ lookup_protocol: else inet->pmtudisc = IP_PMTUDISC_WANT; - inet->id = 0; + inet->inet_id = 0; sock_init_data(sock, sk); @@ -381,13 +381,13 @@ 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 +494,27 @@ 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 +532,7 @@ 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 +685,21 @@ 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 +714,7 @@ 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 +728,7 @@ 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 +931,7 @@ 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, @@ -1059,9 +1059,9 @@ 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 +1071,7 @@ 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 +1087,7 @@ 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 +1113,7 @@ 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 +1123,7 @@ 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 +1131,8 @@ 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 5c662703eb1..d07b0c1dd35 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; @@ -231,31 +414,31 @@ 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; } @@ -265,10 +448,6 @@ static int ah_init_state(struct xfrm_state *x) 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 039cc1ffe97..1e029dc7545 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 5e6c5a0f3fd..fb2465811b4 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/fib_frontend.c b/net/ipv4/fib_frontend.c index e2f95059256..f73dbed0f0d 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); @@ -473,13 +473,13 @@ 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; } @@ -594,7 +594,7 @@ 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; } @@ -616,7 +616,7 @@ 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; } @@ -647,7 +647,7 @@ 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: @@ -701,9 +701,9 @@ 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) @@ -832,7 +832,7 @@ 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; @@ -1009,7 +1009,7 @@ 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 ecd39454235..14972017b9c 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 92d9d97ec5e..835262c2b86 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: diff --git a/net/ipv4/fib_trie.c b/net/ipv4/fib_trie.c index 291bdf50a21..af5d8979286 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 5bc13fe816d..84adb5754c9 100644 --- a/net/ipv4/icmp.c +++ b/net/ipv4/icmp.c @@ -1165,6 +1165,10 @@ 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/inet_connection_sock.c b/net/ipv4/inet_connection_sock.c index 537731b3bcb..26fb50e9131 100644 --- a/net/ipv4/inet_connection_sock.c +++ b/net/ipv4/inet_connection_sock.c @@ -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); @@ -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 a706a47f4db..bdb78dd180c 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 625cc5f64c9..47ad7aab51e 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(); @@ -273,13 +273,14 @@ 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; @@ -312,8 +313,8 @@ 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); @@ -341,8 +342,9 @@ 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 +426,7 @@ 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; @@ -485,7 +487,7 @@ 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_timewait_sock.c b/net/ipv4/inet_timewait_sock.c index 13f0781f35c..1f5d508bb18 100644 --- a/net/ipv4/inet_timewait_sock.c +++ b/net/ipv4/inet_timewait_sock.c @@ -86,7 +86,7 @@ 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; @@ -124,14 +124,14 @@ 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; @@ -430,7 +430,7 @@ void inet_twsk_purge(struct net *net, struct inet_hashinfo *hashinfo, int h; local_bh_disable(); - for (h = 0; h < (hashinfo->ehash_size); h++) { + for (h = 0; h <= hashinfo->ehash_mask; h++) { struct inet_ehash_bucket *head = inet_ehash_bucket(hashinfo, h); spinlock_t *lock = inet_ehash_lockp(hashinfo, h); diff --git a/net/ipv4/ip_gre.c b/net/ipv4/ip_gre.c index 41ada9904d3..a77807d449e 100644 --- a/net/ipv4/ip_gre.c +++ b/net/ipv4/ip_gre.c @@ -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; } @@ -1283,16 +1290,19 @@ 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; + } } } } @@ -1340,10 +1350,12 @@ err_alloc: 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); } diff --git a/net/ipv4/ip_input.c b/net/ipv4/ip_input.c index 6c98b43badf..fdf51badc8e 100644 --- a/net/ipv4/ip_input.c +++ b/net/ipv4/ip_input.c @@ -161,7 +161,7 @@ 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)) { diff --git a/net/ipv4/ip_output.c b/net/ipv4/ip_output.c index f9895180f48..322b40864ac 100644 --- a/net/ipv4/ip_output.c +++ b/net/ipv4/ip_output.c @@ -329,7 +329,7 @@ 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 +338,13 @@ 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 +379,7 @@ 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, @@ -846,7 +846,8 @@ 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 +1101,7 @@ 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 e982b5c1ee1..cafad9baff0 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/ipip.c b/net/ipv4/ipip.c index 08ccd344de7..a2ca53da437 100644 --- a/net/ipv4/ipip.c +++ b/net/ipv4/ipip.c @@ -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; @@ -478,7 +486,7 @@ 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; } @@ -746,16 +754,19 @@ 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; + } } } } @@ -808,11 +819,13 @@ err_alloc: static void ipip_exit_net(struct net *net) { struct ipip_net *ipn; + 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); } diff --git a/net/ipv4/ipmr.c b/net/ipv4/ipmr.c index 630a56df7b4..ef4ee45b928 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); @@ -860,14 +871,16 @@ 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 @@ -946,7 +959,7 @@ 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; @@ -983,7 +996,7 @@ 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; @@ -1146,6 +1159,7 @@ 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; @@ -1155,8 +1169,9 @@ 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/nf_conntrack_l3proto_ipv4.c b/net/ipv4/netfilter/nf_conntrack_l3proto_ipv4.c index aa95bb82ee6..9cd423ffafa 100644 --- a/net/ipv4/netfilter/nf_conntrack_l3proto_ipv4.c +++ b/net/ipv4/netfilter/nf_conntrack_l3proto_ipv4.c @@ -255,10 +255,10 @@ 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/raw.c b/net/ipv4/raw.c index ab996f9c0fe..ce154b47f1d 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 bb419925202..68fb2270205 100644 --- a/net/ipv4/route.c +++ b/net/ipv4/route.c @@ -1628,9 +1628,6 @@ 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], diff --git a/net/ipv4/syncookies.c b/net/ipv4/syncookies.c index a6e0e077ac3..3146cc40174 100644 --- a/net/ipv4/syncookies.c +++ b/net/ipv4/syncookies.c @@ -276,13 +276,6 @@ 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 +291,6 @@ 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 +320,8 @@ 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 +339,20 @@ 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, 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/tcp.c b/net/ipv4/tcp.c index 98440ad8255..e0cfa633680 100644 --- a/net/ipv4/tcp.c +++ b/net/ipv4/tcp.c @@ -2037,7 +2037,7 @@ 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); @@ -2061,7 +2061,7 @@ 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; @@ -2898,11 +2898,10 @@ 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); } @@ -2911,7 +2910,7 @@ 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, @@ -2966,8 +2965,8 @@ 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); } diff --git a/net/ipv4/tcp_input.c b/net/ipv4/tcp_input.c index d86784be7ab..ba0eab65fe8 100644 --- a/net/ipv4/tcp_input.c +++ b/net/ipv4/tcp_input.c @@ -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 @@ -3698,12 +3698,14 @@ old_ack: * the fast version below fails. */ void tcp_parse_options(struct sk_buff *skb, struct tcp_options_received *opt_rx, - int estab) + int estab, struct dst_entry *dst) { unsigned char *ptr; struct tcphdr *th = tcp_hdr(skb); int length = (th->doff * 4) - sizeof(struct tcphdr); + BUG_ON(!estab && !dst); + ptr = (unsigned char *)(th + 1); opt_rx->saw_tstamp = 0; @@ -3737,7 +3739,8 @@ 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 +3756,8 @@ 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 +3765,8 @@ 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); } @@ -3820,7 +3825,7 @@ static int tcp_fast_parse_options(struct sk_buff *skb, struct tcphdr *th, if (tcp_parse_aligned_timestamp(tp, th)) return 1; } - tcp_parse_options(skb, &tp->rx_opt, 1); + tcp_parse_options(skb, &tp->rx_opt, 1, NULL); return 1; } @@ -4075,8 +4080,10 @@ 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 +4112,15 @@ 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)) @@ -5364,8 +5373,9 @@ static int tcp_rcv_synsent_state_process(struct sock *sk, struct sk_buff *skb, struct tcp_sock *tp = tcp_sk(sk); struct inet_connection_sock *icsk = inet_csk(sk); int saved_clamp = tp->rx_opt.mss_clamp; + struct dst_entry *dst = __sk_dst_get(sk); - tcp_parse_options(skb, &tp->rx_opt, 0); + tcp_parse_options(skb, &tp->rx_opt, 0, dst); if (th->ack) { /* rfc793: diff --git a/net/ipv4/tcp_ipv4.c b/net/ipv4/tcp_ipv4.c index 7cda24b53f6..657ae334f12 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; @@ -210,8 +210,8 @@ int tcp_v4_connect(struct sock *sk, struct sockaddr *uaddr, int addr_len) } } - 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) @@ -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)); @@ -848,7 +849,7 @@ 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 +924,7 @@ 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 +1090,8 @@ 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; @@ -1256,11 +1257,21 @@ 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; - tcp_parse_options(skb, &tmp_opt, 0); + tcp_parse_options(skb, &tmp_opt, 0, dst); if (want_cookie && !tmp_opt.saw_tstamp) tcp_clear_options(&tmp_opt); @@ -1269,14 +1280,8 @@ int tcp_v4_conn_request(struct sock *sk, struct sk_buff *skb) 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)); @@ -1301,7 +1306,6 @@ 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 && @@ -1380,9 +1384,9 @@ 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 +1394,7 @@ 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 +1407,8 @@ 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 +1417,7 @@ 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 +1716,8 @@ 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) @@ -2000,7 +2005,7 @@ 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 +2066,10 @@ 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 +2230,7 @@ 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 +2253,10 @@ 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); if (icsk->icsk_pending == ICSK_TIME_RETRANS) { timer_active = 1; diff --git a/net/ipv4/tcp_minisocks.c b/net/ipv4/tcp_minisocks.c index 4c03598ed92..463d51b53d3 100644 --- a/net/ipv4/tcp_minisocks.c +++ b/net/ipv4/tcp_minisocks.c @@ -100,9 +100,9 @@ tcp_timewait_state_process(struct inet_timewait_sock *tw, struct sk_buff *skb, struct tcp_options_received tmp_opt; 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, 1, NULL); if (tmp_opt.saw_tstamp) { tmp_opt.ts_recent = tcptw->tw_ts_recent; @@ -500,10 +500,11 @@ struct sock *tcp_check_req(struct sock *sk, struct sk_buff *skb, int paws_reject = 0; struct tcp_options_received tmp_opt; struct sock *child; + struct dst_entry *dst = inet_csk_route_req(sk, req); tmp_opt.saw_tstamp = 0; if (th->doff > (sizeof(struct tcphdr)>>2)) { - tcp_parse_options(skb, &tmp_opt, 0); + tcp_parse_options(skb, &tmp_opt, 0, dst); if (tmp_opt.saw_tstamp) { tmp_opt.ts_recent = req->ts_recent; @@ -516,6 +517,8 @@ struct sock *tcp_check_req(struct sock *sk, struct sk_buff *skb, } } + dst_release(dst); + /* Check for pure retransmitted SYN. */ if (TCP_SKB_CB(skb)->seq == tcp_rsk(req)->rcv_isn && flg == TCP_FLAG_SYN && diff --git a/net/ipv4/tcp_output.c b/net/ipv4/tcp_output.c index fcd278a7080..616c686ca25 100644 --- a/net/ipv4/tcp_output.c +++ b/net/ipv4/tcp_output.c @@ -464,6 +464,7 @@ static unsigned tcp_syn_options(struct sock *sk, struct sk_buff *skb, struct tcp_md5sig_key **md5) { struct tcp_sock *tp = tcp_sk(sk); unsigned size = 0; + struct dst_entry *dst = __sk_dst_get(sk); #ifdef CONFIG_TCP_MD5SIG *md5 = tp->af_specific->md5_lookup(sk, sk); @@ -487,18 +488,22 @@ static unsigned tcp_syn_options(struct sock *sk, struct sk_buff *skb, opts->mss = tcp_advertise_mss(sk); size += 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.ts_recent; size += TCPOLEN_TSTAMP_ALIGNED; } - if (likely(sysctl_tcp_window_scaling)) { + if (likely(sysctl_tcp_window_scaling && + !dst_feature(dst, RTAX_FEATURE_NO_WSCALE))) { opts->ws = tp->rx_opt.rcv_wscale; opts->options |= OPTION_WSCALE; size += TCPOLEN_WSCALE_ALIGNED; } - if (likely(sysctl_tcp_sack)) { + if (likely(sysctl_tcp_sack && + !dst_feature(dst, RTAX_FEATURE_NO_SACK))) { opts->options |= OPTION_SACK_ADVERTISE; if (unlikely(!(OPTION_TS & opts->options))) size += TCPOLEN_SACKPERM_ALIGNED; @@ -661,8 +666,8 @@ static int tcp_transmit_skb(struct sock *sk, struct sk_buff *skb, int clone_it, /* Build TCP header and checksum it. */ th = tcp_hdr(skb); - th->source = inet->sport; - th->dest = inet->dport; + th->source = inet->inet_sport; + th->dest = inet->inet_dport; th->seq = htonl(tcb->seq); th->ack_seq = htonl(tp->rcv_nxt); *(((__be16 *)th) + 6) = htons(((tcp_header_size >> 2) << 12) | @@ -2315,7 +2320,9 @@ static void tcp_connect_init(struct sock *sk) * See tcp_input.c:tcp_rcv_state_process case TCP_SYN_SENT. */ tp->tcp_header_len = sizeof(struct tcphdr) + - (sysctl_tcp_timestamps ? TCPOLEN_TSTAMP_ALIGNED : 0); + (sysctl_tcp_timestamps && + (!dst_feature(dst, RTAX_FEATURE_NO_TSTAMP) ? + TCPOLEN_TSTAMP_ALIGNED : 0)); #ifdef CONFIG_TCP_MD5SIG if (tp->af_specific->md5_lookup(sk, sk) != NULL) @@ -2341,7 +2348,8 @@ static void tcp_connect_init(struct sock *sk) tp->advmss - (tp->rx_opt.ts_recent_stamp ? tp->tcp_header_len - sizeof(struct tcphdr) : 0), &tp->rcv_wnd, &tp->window_clamp, - sysctl_tcp_window_scaling, + (sysctl_tcp_window_scaling && + !dst_feature(dst, RTAX_FEATURE_NO_WSCALE)), &rcv_wscale); tp->rx_opt.rcv_wscale = rcv_wscale; diff --git a/net/ipv4/tcp_probe.c b/net/ipv4/tcp_probe.c index 59f5b5e7c56..7a3cc2ffad8 100644 --- a/net/ipv4/tcp_probe.c +++ b/net/ipv4/tcp_probe.c @@ -94,7 +94,8 @@ static int jtcp_rcv_established(struct sock *sk, struct sk_buff *skb, const struct inet_sock *inet = inet_sk(sk); /* Only update if port matches */ - if ((port == 0 || ntohs(inet->dport) == port || ntohs(inet->sport) == port) + if ((port == 0 || ntohs(inet->inet_dport) == port || + ntohs(inet->inet_sport) == port) && (full || tp->snd_cwnd != tcp_probe.lastcwnd)) { spin_lock(&tcp_probe.lock); @@ -103,10 +104,10 @@ static int jtcp_rcv_established(struct sock *sk, struct sk_buff *skb, struct tcp_log *p = tcp_probe.log + tcp_probe.head; p->tstamp = ktime_get(); - p->saddr = inet->saddr; - p->sport = inet->sport; - p->daddr = inet->daddr; - p->dport = inet->dport; + p->saddr = inet->inet_saddr; + p->sport = inet->inet_sport; + p->daddr = inet->inet_daddr; + p->dport = inet->inet_dport; p->length = skb->len; p->snd_nxt = tp->snd_nxt; p->snd_una = tp->snd_una; diff --git a/net/ipv4/tcp_timer.c b/net/ipv4/tcp_timer.c index cdb2ca7684d..8353a538cd4 100644 --- a/net/ipv4/tcp_timer.c +++ b/net/ipv4/tcp_timer.c @@ -141,14 +141,14 @@ static int tcp_write_timeout(struct sock *sk) if ((1 << sk->sk_state) & (TCPF_SYN_SENT | TCPF_SYN_RECV)) { if (icsk->icsk_retransmits) - dst_negative_advice(&sk->sk_dst_cache); + dst_negative_advice(&sk->sk_dst_cache, sk); retry_until = icsk->icsk_syn_retries ? : sysctl_tcp_syn_retries; } else { if (retransmits_timed_out(sk, sysctl_tcp_retries1)) { /* Black hole detection */ tcp_mtu_probing(icsk, sk); - dst_negative_advice(&sk->sk_dst_cache); + dst_negative_advice(&sk->sk_dst_cache, sk); } retry_until = sysctl_tcp_retries2; @@ -303,15 +303,15 @@ void tcp_retransmit_timer(struct sock *sk) struct inet_sock *inet = inet_sk(sk); if (sk->sk_family == AF_INET) { LIMIT_NETDEBUG(KERN_DEBUG "TCP: Peer %pI4:%u/%u unexpectedly shrunk window %u:%u (repaired)\n", - &inet->daddr, ntohs(inet->dport), - inet->num, tp->snd_una, tp->snd_nxt); + &inet->inet_daddr, ntohs(inet->inet_dport), + inet->inet_num, tp->snd_una, tp->snd_nxt); } #if defined(CONFIG_IPV6) || defined(CONFIG_IPV6_MODULE) else if (sk->sk_family == AF_INET6) { struct ipv6_pinfo *np = inet6_sk(sk); LIMIT_NETDEBUG(KERN_DEBUG "TCP: Peer %pI6:%u/%u unexpectedly shrunk window %u:%u (repaired)\n", - &np->daddr, ntohs(inet->dport), - inet->num, tp->snd_una, tp->snd_nxt); + &np->daddr, ntohs(inet->inet_dport), + inet->inet_num, tp->snd_una, tp->snd_nxt); } #endif #endif diff --git a/net/ipv4/udp.c b/net/ipv4/udp.c index d0d436d6216..4274c1cc78f 100644 --- a/net/ipv4/udp.c +++ b/net/ipv4/udp.c @@ -106,7 +106,7 @@ #include <net/xfrm.h> #include "udp_impl.h" -struct udp_table udp_table; +struct udp_table udp_table __read_mostly; EXPORT_SYMBOL(udp_table); int sysctl_udp_mem[3] __read_mostly; @@ -121,14 +121,16 @@ EXPORT_SYMBOL(sysctl_udp_wmem_min); atomic_t udp_memory_allocated; EXPORT_SYMBOL(udp_memory_allocated); -#define PORTS_PER_CHAIN (65536 / UDP_HTABLE_SIZE) +#define MAX_UDP_PORTS 65536 +#define PORTS_PER_CHAIN (MAX_UDP_PORTS / UDP_HTABLE_SIZE_MIN) static int udp_lib_lport_inuse(struct net *net, __u16 num, const struct udp_hslot *hslot, unsigned long *bitmap, struct sock *sk, int (*saddr_comp)(const struct sock *sk1, - const struct sock *sk2)) + const struct sock *sk2), + unsigned int log) { struct sock *sk2; struct hlist_nulls_node *node; @@ -142,8 +144,7 @@ static int udp_lib_lport_inuse(struct net *net, __u16 num, || sk2->sk_bound_dev_if == sk->sk_bound_dev_if) && (*saddr_comp)(sk, sk2)) { if (bitmap) - __set_bit(sk2->sk_hash / UDP_HTABLE_SIZE, - bitmap); + __set_bit(sk2->sk_hash >> log, bitmap); else return 1; } @@ -180,13 +181,15 @@ int udp_lib_get_port(struct sock *sk, unsigned short snum, /* * force rand to be an odd multiple of UDP_HTABLE_SIZE */ - rand = (rand | 1) * UDP_HTABLE_SIZE; - for (last = first + UDP_HTABLE_SIZE; first != last; first++) { - hslot = &udptable->hash[udp_hashfn(net, first)]; + rand = (rand | 1) * (udptable->mask + 1); + for (last = first + udptable->mask + 1; + first != last; + first++) { + hslot = udp_hashslot(udptable, net, first); bitmap_zero(bitmap, PORTS_PER_CHAIN); spin_lock_bh(&hslot->lock); udp_lib_lport_inuse(net, snum, hslot, bitmap, sk, - saddr_comp); + saddr_comp, udptable->log); snum = first; /* @@ -196,7 +199,7 @@ int udp_lib_get_port(struct sock *sk, unsigned short snum, */ do { if (low <= snum && snum <= high && - !test_bit(snum / UDP_HTABLE_SIZE, bitmap)) + !test_bit(snum >> udptable->log, bitmap)) goto found; snum += rand; } while (snum != first); @@ -204,13 +207,14 @@ int udp_lib_get_port(struct sock *sk, unsigned short snum, } goto fail; } else { - hslot = &udptable->hash[udp_hashfn(net, snum)]; + hslot = udp_hashslot(udptable, net, snum); spin_lock_bh(&hslot->lock); - if (udp_lib_lport_inuse(net, snum, hslot, NULL, sk, saddr_comp)) + if (udp_lib_lport_inuse(net, snum, hslot, NULL, sk, + saddr_comp, 0)) goto fail_unlock; } found: - inet_sk(sk)->num = snum; + inet_sk(sk)->inet_num = snum; sk->sk_hash = snum; if (sk_unhashed(sk)) { sk_nulls_add_node_rcu(sk, &hslot->head); @@ -229,8 +233,8 @@ static int ipv4_rcv_saddr_equal(const struct sock *sk1, const struct sock *sk2) struct inet_sock *inet1 = inet_sk(sk1), *inet2 = inet_sk(sk2); return (!ipv6_only_sock(sk2) && - (!inet1->rcv_saddr || !inet2->rcv_saddr || - inet1->rcv_saddr == inet2->rcv_saddr)); + (!inet1->inet_rcv_saddr || !inet2->inet_rcv_saddr || + inet1->inet_rcv_saddr == inet2->inet_rcv_saddr)); } int udp_v4_get_port(struct sock *sk, unsigned short snum) @@ -249,18 +253,18 @@ static inline int compute_score(struct sock *sk, struct net *net, __be32 saddr, struct inet_sock *inet = inet_sk(sk); score = (sk->sk_family == PF_INET ? 1 : 0); - if (inet->rcv_saddr) { - if (inet->rcv_saddr != daddr) + if (inet->inet_rcv_saddr) { + if (inet->inet_rcv_saddr != daddr) return -1; score += 2; } - if (inet->daddr) { - if (inet->daddr != saddr) + if (inet->inet_daddr) { + if (inet->inet_daddr != saddr) return -1; score += 2; } - if (inet->dport) { - if (inet->dport != sport) + if (inet->inet_dport) { + if (inet->inet_dport != sport) return -1; score += 2; } @@ -283,7 +287,7 @@ static struct sock *__udp4_lib_lookup(struct net *net, __be32 saddr, struct sock *sk, *result; struct hlist_nulls_node *node; unsigned short hnum = ntohs(dport); - unsigned int hash = udp_hashfn(net, hnum); + unsigned int hash = udp_hashfn(net, hnum, udptable->mask); struct udp_hslot *hslot = &udptable->hash[hash]; int score, badness; @@ -356,9 +360,10 @@ static inline struct sock *udp_v4_mcast_next(struct net *net, struct sock *sk, if (!net_eq(sock_net(s), net) || s->sk_hash != hnum || - (inet->daddr && inet->daddr != rmt_addr) || - (inet->dport != rmt_port && inet->dport) || - (inet->rcv_saddr && inet->rcv_saddr != loc_addr) || + (inet->inet_daddr && inet->inet_daddr != rmt_addr) || + (inet->inet_dport != rmt_port && inet->inet_dport) || + (inet->inet_rcv_saddr && + inet->inet_rcv_saddr != loc_addr) || ipv6_only_sock(s) || (s->sk_bound_dev_if && s->sk_bound_dev_if != dif)) continue; @@ -642,14 +647,14 @@ int udp_sendmsg(struct kiocb *iocb, struct sock *sk, struct msghdr *msg, } else { if (sk->sk_state != TCP_ESTABLISHED) return -EDESTADDRREQ; - daddr = inet->daddr; - dport = inet->dport; + daddr = inet->inet_daddr; + dport = inet->inet_dport; /* Open fast path for connected socket. Route will not be used, if at least one option is set. */ connected = 1; } - ipc.addr = inet->saddr; + ipc.addr = inet->inet_saddr; ipc.oif = sk->sk_bound_dev_if; err = sock_tx_timestamp(msg, sk, &ipc.shtx); @@ -704,7 +709,7 @@ int udp_sendmsg(struct kiocb *iocb, struct sock *sk, struct msghdr *msg, .proto = sk->sk_protocol, .flags = inet_sk_flowi_flags(sk), .uli_u = { .ports = - { .sport = inet->sport, + { .sport = inet->inet_sport, .dport = dport } } }; struct net *net = sock_net(sk); @@ -748,7 +753,7 @@ back_from_confirm: inet->cork.fl.fl4_dst = daddr; inet->cork.fl.fl_ip_dport = dport; inet->cork.fl.fl4_src = saddr; - inet->cork.fl.fl_ip_sport = inet->sport; + inet->cork.fl.fl_ip_sport = inet->inet_sport; up->pending = AF_INET; do_append_data: @@ -862,6 +867,7 @@ static unsigned int first_packet_length(struct sock *sk) udp_lib_checksum_complete(skb)) { UDP_INC_STATS_BH(sock_net(sk), UDP_MIB_INERRORS, IS_UDPLITE(sk)); + atomic_inc(&sk->sk_drops); __skb_unlink(skb, rcvq); __skb_queue_tail(&list_kill, skb); } @@ -982,7 +988,7 @@ try_again: UDP_INC_STATS_USER(sock_net(sk), UDP_MIB_INDATAGRAMS, is_udplite); - sock_recv_timestamp(msg, sk, skb); + sock_recv_ts_and_drops(msg, sk, skb); /* Copy the address. */ if (sin) { @@ -1025,15 +1031,15 @@ int udp_disconnect(struct sock *sk, int flags) */ sk->sk_state = TCP_CLOSE; - inet->daddr = 0; - inet->dport = 0; + inet->inet_daddr = 0; + inet->inet_dport = 0; sk->sk_bound_dev_if = 0; if (!(sk->sk_userlocks & SOCK_BINDADDR_LOCK)) inet_reset_saddr(sk); if (!(sk->sk_userlocks & SOCK_BINDPORT_LOCK)) { sk->sk_prot->unhash(sk); - inet->sport = 0; + inet->inet_sport = 0; } sk_dst_reset(sk); return 0; @@ -1044,12 +1050,12 @@ void udp_lib_unhash(struct sock *sk) { if (sk_hashed(sk)) { struct udp_table *udptable = sk->sk_prot->h.udp_table; - unsigned int hash = udp_hashfn(sock_net(sk), sk->sk_hash); - struct udp_hslot *hslot = &udptable->hash[hash]; + struct udp_hslot *hslot = udp_hashslot(udptable, sock_net(sk), + sk->sk_hash); spin_lock_bh(&hslot->lock); if (sk_nulls_del_node_init_rcu(sk)) { - inet_sk(sk)->num = 0; + inet_sk(sk)->inet_num = 0; sock_prot_inuse_add(sock_net(sk), sk->sk_prot, -1); } spin_unlock_bh(&hslot->lock); @@ -1059,25 +1065,22 @@ EXPORT_SYMBOL(udp_lib_unhash); static int __udp_queue_rcv_skb(struct sock *sk, struct sk_buff *skb) { - int is_udplite = IS_UDPLITE(sk); - int rc; + int rc = sock_queue_rcv_skb(sk, skb); + + if (rc < 0) { + int is_udplite = IS_UDPLITE(sk); - if ((rc = sock_queue_rcv_skb(sk, skb)) < 0) { /* Note that an ENOMEM error is charged twice */ - if (rc == -ENOMEM) { + if (rc == -ENOMEM) UDP_INC_STATS_BH(sock_net(sk), UDP_MIB_RCVBUFERRORS, is_udplite); - atomic_inc(&sk->sk_drops); - } - goto drop; + UDP_INC_STATS_BH(sock_net(sk), UDP_MIB_INERRORS, is_udplite); + kfree_skb(skb); + return -1; } return 0; -drop: - UDP_INC_STATS_BH(sock_net(sk), UDP_MIB_INERRORS, is_udplite); - kfree_skb(skb); - return -1; } /* returns: @@ -1184,6 +1187,7 @@ int udp_queue_rcv_skb(struct sock *sk, struct sk_buff *skb) drop: UDP_INC_STATS_BH(sock_net(sk), UDP_MIB_INERRORS, is_udplite); + atomic_inc(&sk->sk_drops); kfree_skb(skb); return -1; } @@ -1200,7 +1204,7 @@ static int __udp4_lib_mcast_deliver(struct net *net, struct sk_buff *skb, struct udp_table *udptable) { struct sock *sk; - struct udp_hslot *hslot = &udptable->hash[udp_hashfn(net, ntohs(uh->dest))]; + struct udp_hslot *hslot = udp_hashslot(udptable, net, ntohs(uh->dest)); int dif; spin_lock(&hslot->lock); @@ -1622,9 +1626,14 @@ static struct sock *udp_get_first(struct seq_file *seq, int start) struct udp_iter_state *state = seq->private; struct net *net = seq_file_net(seq); - for (state->bucket = start; state->bucket < UDP_HTABLE_SIZE; ++state->bucket) { + for (state->bucket = start; state->bucket <= state->udp_table->mask; + ++state->bucket) { struct hlist_nulls_node *node; struct udp_hslot *hslot = &state->udp_table->hash[state->bucket]; + + if (hlist_nulls_empty(&hslot->head)) + continue; + spin_lock_bh(&hslot->lock); sk_nulls_for_each(sk, node, &hslot->head) { if (!net_eq(sock_net(sk), net)) @@ -1649,7 +1658,7 @@ static struct sock *udp_get_next(struct seq_file *seq, struct sock *sk) } while (sk && (!net_eq(sock_net(sk), net) || sk->sk_family != state->family)); if (!sk) { - if (state->bucket < UDP_HTABLE_SIZE) + if (state->bucket <= state->udp_table->mask) spin_unlock_bh(&state->udp_table->hash[state->bucket].lock); return udp_get_first(seq, state->bucket + 1); } @@ -1669,7 +1678,7 @@ static struct sock *udp_get_idx(struct seq_file *seq, loff_t pos) static void *udp_seq_start(struct seq_file *seq, loff_t *pos) { struct udp_iter_state *state = seq->private; - state->bucket = UDP_HTABLE_SIZE; + state->bucket = MAX_UDP_PORTS; return *pos ? udp_get_idx(seq, *pos-1) : SEQ_START_TOKEN; } @@ -1691,7 +1700,7 @@ static void udp_seq_stop(struct seq_file *seq, void *v) { struct udp_iter_state *state = seq->private; - if (state->bucket < UDP_HTABLE_SIZE) + if (state->bucket <= state->udp_table->mask) spin_unlock_bh(&state->udp_table->hash[state->bucket].lock); } @@ -1746,12 +1755,12 @@ static void udp4_format_sock(struct sock *sp, struct seq_file *f, int bucket, int *len) { struct inet_sock *inet = inet_sk(sp); - __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); - seq_printf(f, "%4d: %08X:%04X %08X:%04X" + seq_printf(f, "%5d: %08X:%04X %08X:%04X" " %02X %08X:%08X %02X:%08lX %08X %5d %8d %lu %d %p %d%n", bucket, src, srcp, dest, destp, sp->sk_state, sk_wmem_alloc_get(sp), @@ -1817,11 +1826,43 @@ void udp4_proc_exit(void) } #endif /* CONFIG_PROC_FS */ -void __init udp_table_init(struct udp_table *table) +static __initdata unsigned long uhash_entries; +static int __init set_uhash_entries(char *str) { - int i; + if (!str) + return 0; + uhash_entries = simple_strtoul(str, &str, 0); + if (uhash_entries && uhash_entries < UDP_HTABLE_SIZE_MIN) + uhash_entries = UDP_HTABLE_SIZE_MIN; + return 1; +} +__setup("uhash_entries=", set_uhash_entries); - for (i = 0; i < UDP_HTABLE_SIZE; i++) { +void __init udp_table_init(struct udp_table *table, const char *name) +{ + unsigned int i; + + if (!CONFIG_BASE_SMALL) + table->hash = alloc_large_system_hash(name, + sizeof(struct udp_hslot), + uhash_entries, + 21, /* one slot per 2 MB */ + 0, + &table->log, + &table->mask, + 64 * 1024); + /* + * Make sure hash table has the minimum size + */ + if (CONFIG_BASE_SMALL || table->mask < UDP_HTABLE_SIZE_MIN - 1) { + table->hash = kmalloc(UDP_HTABLE_SIZE_MIN * + sizeof(struct udp_hslot), GFP_KERNEL); + if (!table->hash) + panic(name); + table->log = ilog2(UDP_HTABLE_SIZE_MIN); + table->mask = UDP_HTABLE_SIZE_MIN - 1; + } + for (i = 0; i <= table->mask; i++) { INIT_HLIST_NULLS_HEAD(&table->hash[i].head, i); spin_lock_init(&table->hash[i].lock); } @@ -1831,7 +1872,7 @@ void __init udp_init(void) { unsigned long nr_pages, limit; - udp_table_init(&udp_table); + udp_table_init(&udp_table, "UDP"); /* Set the pressure threshold up by the same strategy of TCP. It is a * fraction of global memory that is up to 1/2 at 256 MB, decreasing * toward zero with the amount of memory, with a floor of 128 pages. diff --git a/net/ipv4/udplite.c b/net/ipv4/udplite.c index 95248d7f75e..470c504b955 100644 --- a/net/ipv4/udplite.c +++ b/net/ipv4/udplite.c @@ -12,7 +12,7 @@ */ #include "udp_impl.h" -struct udp_table udplite_table; +struct udp_table udplite_table __read_mostly; EXPORT_SYMBOL(udplite_table); static int udplite_rcv(struct sk_buff *skb) @@ -110,7 +110,7 @@ static inline int udplite4_proc_init(void) void __init udplite4_register(void) { - udp_table_init(&udplite_table); + udp_table_init(&udplite_table, "UDP-Lite"); if (proto_register(&udplite_prot, 1)) goto out_register_err; diff --git a/net/ipv6/Kconfig b/net/ipv6/Kconfig index ead6c7a42f4..a578096152a 100644 --- a/net/ipv6/Kconfig +++ b/net/ipv6/Kconfig @@ -170,6 +170,25 @@ config IPV6_SIT Saying M here will produce a module called sit. If unsure, say Y. +config IPV6_SIT_6RD + bool "IPv6: IPv6 Rapid Deployment (6RD) (EXPERIMENTAL)" + depends on IPV6_SIT && EXPERIMENTAL + default n + ---help--- + IPv6 Rapid Deployment (6rd; draft-ietf-softwire-ipv6-6rd) builds upon + mechanisms of 6to4 (RFC3056) to enable a service provider to rapidly + deploy IPv6 unicast service to IPv4 sites to which it provides + customer premise equipment. Like 6to4, it utilizes stateless IPv6 in + IPv4 encapsulation in order to transit IPv4-only network + infrastructure. Unlike 6to4, a 6rd service provider uses an IPv6 + prefix of its own in place of the fixed 6to4 prefix. + + With this option enabled, the SIT driver offers 6rd functionality by + providing additional ioctl API to configure the IPv6 Prefix for in + stead of static 2002::/16 for 6to4. + + If unsure, say N. + config IPV6_NDISC_NODETYPE bool diff --git a/net/ipv6/addrconf.c b/net/ipv6/addrconf.c index 1fd0a3d775d..91864840961 100644 --- a/net/ipv6/addrconf.c +++ b/net/ipv6/addrconf.c @@ -3708,6 +3708,7 @@ static inline void ipv6_store_devconf(struct ipv6_devconf *cnf, #endif array[DEVCONF_DISABLE_IPV6] = cnf->disable_ipv6; array[DEVCONF_ACCEPT_DAD] = cnf->accept_dad; + array[DEVCONF_FORCE_TLLAO] = cnf->force_tllao; } static inline size_t inet6_if_nlmsg_size(void) @@ -4353,6 +4354,14 @@ static struct addrconf_sysctl_table .proc_handler = proc_dointvec, }, { + .ctl_name = CTL_UNNUMBERED, + .procname = "force_tllao", + .data = &ipv6_devconf.force_tllao, + .maxlen = sizeof(int), + .mode = 0644, + .proc_handler = proc_dointvec + }, + { .ctl_name = 0, /* sentinel */ } }, diff --git a/net/ipv6/af_inet6.c b/net/ipv6/af_inet6.c index e127a32f954..b6d05881867 100644 --- a/net/ipv6/af_inet6.c +++ b/net/ipv6/af_inet6.c @@ -185,7 +185,7 @@ 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; } @@ -228,12 +228,12 @@ 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); sk->sk_prot->hash(sk); } if (sk->sk_prot->init) { @@ -281,7 +281,7 @@ int inet6_bind(struct socket *sock, struct sockaddr *uaddr, int addr_len) lock_sock(sk); /* Check these errors (active socket, double bind). */ - if (sk->sk_state != TCP_CLOSE || inet->num) { + if (sk->sk_state != TCP_CLOSE || inet->inet_num) { err = -EINVAL; goto out; } @@ -353,8 +353,8 @@ int inet6_bind(struct socket *sock, struct sockaddr *uaddr, int addr_len) } } - inet->rcv_saddr = v4addr; - inet->saddr = v4addr; + inet->inet_rcv_saddr = v4addr; + inet->inet_saddr = v4addr; ipv6_addr_copy(&np->rcv_saddr, &addr->sin6_addr); @@ -375,9 +375,9 @@ int inet6_bind(struct socket *sock, struct sockaddr *uaddr, int addr_len) } if (snum) sk->sk_userlocks |= SOCK_BINDPORT_LOCK; - inet->sport = htons(inet->num); - inet->dport = 0; - inet->daddr = 0; + inet->inet_sport = htons(inet->inet_num); + inet->inet_dport = 0; + inet->inet_daddr = 0; out: release_sock(sk); return err; @@ -441,12 +441,12 @@ int inet6_getname(struct socket *sock, struct sockaddr *uaddr, sin->sin6_flowinfo = 0; sin->sin6_scope_id = 0; if (peer) { - if (!inet->dport) + if (!inet->inet_dport) return -ENOTCONN; if (((1 << sk->sk_state) & (TCPF_CLOSE | TCPF_SYN_SENT)) && peer == 1) return -ENOTCONN; - sin->sin6_port = inet->dport; + sin->sin6_port = inet->inet_dport; ipv6_addr_copy(&sin->sin6_addr, &np->daddr); if (np->sndflow) sin->sin6_flowinfo = np->flow_label; @@ -456,7 +456,7 @@ int inet6_getname(struct socket *sock, struct sockaddr *uaddr, else ipv6_addr_copy(&sin->sin6_addr, &np->rcv_saddr); - sin->sin6_port = inet->sport; + sin->sin6_port = inet->inet_sport; } if (ipv6_addr_type(&sin->sin6_addr) & IPV6_ADDR_LINKLOCAL) sin->sin6_scope_id = sk->sk_bound_dev_if; @@ -552,7 +552,7 @@ const struct proto_ops inet6_dgram_ops = { #endif }; -static struct net_proto_family inet6_family_ops = { +static const struct net_proto_family inet6_family_ops = { .family = PF_INET6, .create = inet6_create, .owner = THIS_MODULE, @@ -654,8 +654,9 @@ int inet6_sk_rebuild_header(struct sock *sk) ipv6_addr_copy(&fl.fl6_src, &np->saddr); fl.fl6_flowlabel = np->flow_label; fl.oif = sk->sk_bound_dev_if; - fl.fl_ip_dport = inet->dport; - fl.fl_ip_sport = inet->sport; + fl.mark = sk->sk_mark; + fl.fl_ip_dport = inet->inet_dport; + fl.fl_ip_sport = inet->inet_sport; security_sk_classify_flow(sk, &fl); if (np->opt && np->opt->srcrt) { diff --git a/net/ipv6/ah6.c b/net/ipv6/ah6.c index c1589e2f1dc..0f526f8ea51 100644 --- a/net/ipv6/ah6.c +++ b/net/ipv6/ah6.c @@ -24,18 +24,92 @@ * This file is derived from net/ipv4/ah.c. */ +#include <crypto/hash.h> #include <linux/module.h> #include <net/ip.h> #include <net/ah.h> #include <linux/crypto.h> #include <linux/pfkeyv2.h> -#include <linux/spinlock.h> #include <linux/string.h> +#include <linux/scatterlist.h> #include <net/icmp.h> #include <net/ipv6.h> #include <net/protocol.h> #include <net/xfrm.h> +#define IPV6HDR_BASELEN 8 + +struct tmp_ext { +#if defined(CONFIG_IPV6_MIP6) || defined(CONFIG_IPV6_MIP6_MODULE) + struct in6_addr saddr; +#endif + struct in6_addr daddr; + char hdrs[0]; +}; + +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 struct tmp_ext *ah_tmp_ext(void *base) +{ + return base + IPV6HDR_BASELEN; +} + +static inline u8 *ah_tmp_auth(u8 *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)); +} + static int zero_out_mutable_opts(struct ipv6_opt_hdr *opthdr) { u8 *opt = (u8 *)opthdr; @@ -218,24 +292,85 @@ static int ipv6_clear_mutable_options(struct ipv6hdr *iph, int len, int dir) return 0; } +static void ah6_output_done(struct crypto_async_request *base, int err) +{ + int extlen; + u8 *iph_base; + u8 *icv; + struct sk_buff *skb = base->data; + struct xfrm_state *x = skb_dst(skb)->xfrm; + struct ah_data *ahp = x->data; + struct ipv6hdr *top_iph = ipv6_hdr(skb); + struct ip_auth_hdr *ah = ip_auth_hdr(skb); + struct tmp_ext *iph_ext; + + extlen = skb_network_header_len(skb) - sizeof(struct ipv6hdr); + if (extlen) + extlen += sizeof(*iph_ext); + + iph_base = AH_SKB_CB(skb)->tmp; + iph_ext = ah_tmp_ext(iph_base); + icv = ah_tmp_icv(ahp->ahash, iph_ext, extlen); + + memcpy(ah->auth_data, icv, ahp->icv_trunc_len); + memcpy(top_iph, iph_base, IPV6HDR_BASELEN); + + if (extlen) { +#if defined(CONFIG_IPV6_MIP6) || defined(CONFIG_IPV6_MIP6_MODULE) + memcpy(&top_iph->saddr, iph_ext, extlen); +#else + memcpy(&top_iph->daddr, iph_ext, extlen); +#endif + } + + err = ah->nexthdr; + + kfree(AH_SKB_CB(skb)->tmp); + xfrm_output_resume(skb, err); +} + static int ah6_output(struct xfrm_state *x, struct sk_buff *skb) { int err; + int nfrags; int extlen; + u8 *iph_base; + u8 *icv; + u8 nexthdr; + struct sk_buff *trailer; + struct crypto_ahash *ahash; + struct ahash_request *req; + struct scatterlist *sg; struct ipv6hdr *top_iph; struct ip_auth_hdr *ah; struct ah_data *ahp; - u8 nexthdr; - char tmp_base[8]; - struct { -#if defined(CONFIG_IPV6_MIP6) || defined(CONFIG_IPV6_MIP6_MODULE) - struct in6_addr saddr; -#endif - struct in6_addr daddr; - char hdrs[0]; - } *tmp_ext; + struct tmp_ext *iph_ext; + + 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)); + extlen = skb_network_header_len(skb) - sizeof(struct ipv6hdr); + if (extlen) + extlen += sizeof(*iph_ext); + + err = -ENOMEM; + iph_base = ah_alloc_tmp(ahash, nfrags, IPV6HDR_BASELEN + extlen); + if (!iph_base) + goto out; + + iph_ext = ah_tmp_ext(iph_base); + icv = ah_tmp_icv(ahash, iph_ext, extlen); + req = ah_tmp_req(ahash, icv); + sg = ah_req_sg(ahash, req); + + ah = ip_auth_hdr(skb); + memset(ah->auth_data, 0, ahp->icv_trunc_len); + top_iph = ipv6_hdr(skb); top_iph->payload_len = htons(skb->len - sizeof(*top_iph)); @@ -245,31 +380,22 @@ static int ah6_output(struct xfrm_state *x, struct sk_buff *skb) /* When there are no extension headers, we only need to save the first * 8 bytes of the base IP header. */ - memcpy(tmp_base, top_iph, sizeof(tmp_base)); + memcpy(iph_base, top_iph, IPV6HDR_BASELEN); - tmp_ext = NULL; - extlen = skb_transport_offset(skb) - sizeof(struct ipv6hdr); if (extlen) { - extlen += sizeof(*tmp_ext); - tmp_ext = kmalloc(extlen, GFP_ATOMIC); - if (!tmp_ext) { - err = -ENOMEM; - goto error; - } #if defined(CONFIG_IPV6_MIP6) || defined(CONFIG_IPV6_MIP6_MODULE) - memcpy(tmp_ext, &top_iph->saddr, extlen); + memcpy(iph_ext, &top_iph->saddr, extlen); #else - memcpy(tmp_ext, &top_iph->daddr, extlen); + memcpy(iph_ext, &top_iph->daddr, extlen); #endif err = ipv6_clear_mutable_options(top_iph, - extlen - sizeof(*tmp_ext) + + extlen - sizeof(*iph_ext) + sizeof(*top_iph), XFRM_POLICY_OUT); if (err) - goto error_free_iph; + goto out_free; } - ah = ip_auth_hdr(skb); ah->nexthdr = nexthdr; top_iph->priority = 0; @@ -278,36 +404,80 @@ static int ah6_output(struct xfrm_state *x, struct sk_buff *skb) top_iph->flow_lbl[2] = 0; top_iph->hop_limit = 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_free_iph; + ahash_request_set_crypt(req, sg, icv, skb->len); + ahash_request_set_callback(req, 0, ah6_output_done, skb); + + AH_SKB_CB(skb)->tmp = iph_base; - memcpy(top_iph, tmp_base, sizeof(tmp_base)); - if (tmp_ext) { + 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); + memcpy(top_iph, iph_base, IPV6HDR_BASELEN); + + if (extlen) { #if defined(CONFIG_IPV6_MIP6) || defined(CONFIG_IPV6_MIP6_MODULE) - memcpy(&top_iph->saddr, tmp_ext, extlen); + memcpy(&top_iph->saddr, iph_ext, extlen); #else - memcpy(&top_iph->daddr, tmp_ext, extlen); + memcpy(&top_iph->daddr, iph_ext, extlen); #endif -error_free_iph: - kfree(tmp_ext); } -error: +out_free: + kfree(iph_base); +out: return err; } +static void ah6_input_done(struct crypto_async_request *base, int err) +{ + u8 *auth_data; + u8 *icv; + u8 *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 hdr_len = skb_network_header_len(skb); + int ah_hlen = (ah->hdrlen + 2) << 2; + + work_iph = AH_SKB_CB(skb)->tmp; + auth_data = ah_tmp_auth(work_iph, hdr_len); + 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, hdr_len); + __skb_pull(skb, ah_hlen + hdr_len); + skb_set_transport_header(skb, -hdr_len); + + err = ah->nexthdr; +out: + kfree(AH_SKB_CB(skb)->tmp); + xfrm_input_resume(skb, err); +} + + + static int ah6_input(struct xfrm_state *x, struct sk_buff *skb) { /* @@ -325,14 +495,21 @@ static int ah6_input(struct xfrm_state *x, struct sk_buff *skb) * There is offset of AH before IPv6 header after the process. */ + u8 *auth_data; + u8 *icv; + u8 *work_iph; + struct sk_buff *trailer; + struct crypto_ahash *ahash; + struct ahash_request *req; + struct scatterlist *sg; struct ip_auth_hdr *ah; struct ipv6hdr *ip6h; struct ah_data *ahp; - unsigned char *tmp_hdr = NULL; u16 hdr_len; u16 ah_hlen; int nexthdr; - int err = -EINVAL; + int nfrags; + int err = -ENOMEM; if (!pskb_may_pull(skb, sizeof(struct ip_auth_hdr))) goto out; @@ -345,9 +522,11 @@ static int ah6_input(struct xfrm_state *x, struct sk_buff *skb) skb->ip_summed = CHECKSUM_NONE; - hdr_len = skb->data - skb_network_header(skb); + hdr_len = skb_network_header_len(skb); ah = (struct ip_auth_hdr *)skb->data; ahp = x->data; + ahash = ahp->ahash; + nexthdr = ah->nexthdr; ah_hlen = (ah->hdrlen + 2) << 2; @@ -358,48 +537,67 @@ static int ah6_input(struct xfrm_state *x, struct sk_buff *skb) if (!pskb_may_pull(skb, ah_hlen)) goto out; - tmp_hdr = kmemdup(skb_network_header(skb), hdr_len, GFP_ATOMIC); - if (!tmp_hdr) - goto out; ip6h = ipv6_hdr(skb); + + skb_push(skb, hdr_len); + + if ((err = skb_cow_data(skb, 0, &trailer)) < 0) + goto out; + nfrags = err; + + work_iph = ah_alloc_tmp(ahash, nfrags, hdr_len + ahp->icv_trunc_len); + if (!work_iph) + goto out; + + auth_data = ah_tmp_auth(work_iph, hdr_len); + icv = ah_tmp_icv(ahash, auth_data, ahp->icv_trunc_len); + req = ah_tmp_req(ahash, icv); + sg = ah_req_sg(ahash, req); + + memcpy(work_iph, ip6h, hdr_len); + memcpy(auth_data, ah->auth_data, ahp->icv_trunc_len); + memset(ah->auth_data, 0, ahp->icv_trunc_len); + if (ipv6_clear_mutable_options(ip6h, hdr_len, XFRM_POLICY_IN)) - goto free_out; + goto out_free; + ip6h->priority = 0; ip6h->flow_lbl[0] = 0; ip6h->flow_lbl[1] = 0; ip6h->flow_lbl[2] = 0; ip6h->hop_limit = 0; - spin_lock(&x->lock); - { - u8 auth_data[MAX_AH_AUTH_LEN]; + sg_init_table(sg, nfrags); + skb_to_sgvec(skb, sg, 0, skb->len); - memcpy(auth_data, ah->auth_data, ahp->icv_trunc_len); - memset(ah->auth_data, 0, ahp->icv_trunc_len); - skb_push(skb, hdr_len); - 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; + ahash_request_set_crypt(req, sg, icv, skb->len); + ahash_request_set_callback(req, 0, ah6_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 free_out; + goto out_free; skb->network_header += ah_hlen; - memcpy(skb_network_header(skb), tmp_hdr, hdr_len); + memcpy(skb_network_header(skb), work_iph, hdr_len); skb->transport_header = skb->network_header; __skb_pull(skb, ah_hlen + hdr_len); - kfree(tmp_hdr); + err = nexthdr; - return nexthdr; - -free_out: - kfree(tmp_hdr); +out_free: + kfree(work_iph); out: return err; } @@ -430,7 +628,7 @@ static int ah6_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; @@ -442,12 +640,12 @@ static int ah6_init_state(struct xfrm_state *x) if (ahp == NULL) 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, + ahp->ahash = ahash; + if (crypto_ahash_setkey(ahash, x->aalg->alg_key, (x->aalg->alg_key_len + 7) / 8)) goto error; @@ -461,9 +659,9 @@ static int ah6_init_state(struct xfrm_state *x) 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; } @@ -473,10 +671,6 @@ static int ah6_init_state(struct xfrm_state *x) 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); switch (x->props.mode) { @@ -495,8 +689,7 @@ static int ah6_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; @@ -509,8 +702,7 @@ static void ah6_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/ipv6/datagram.c b/net/ipv6/datagram.c index e2bdc6d83a4..9f70452a69e 100644 --- a/net/ipv6/datagram.c +++ b/net/ipv6/datagram.c @@ -98,17 +98,15 @@ ipv4_connected: if (err) goto out; - ipv6_addr_set(&np->daddr, 0, 0, htonl(0x0000ffff), inet->daddr); + ipv6_addr_set_v4mapped(inet->inet_daddr, &np->daddr); - if (ipv6_addr_any(&np->saddr)) { - ipv6_addr_set(&np->saddr, 0, 0, htonl(0x0000ffff), - inet->saddr); - } + if (ipv6_addr_any(&np->saddr)) + ipv6_addr_set_v4mapped(inet->inet_saddr, &np->saddr); + + if (ipv6_addr_any(&np->rcv_saddr)) + ipv6_addr_set_v4mapped(inet->inet_rcv_saddr, + &np->rcv_saddr); - if (ipv6_addr_any(&np->rcv_saddr)) { - ipv6_addr_set(&np->rcv_saddr, 0, 0, htonl(0x0000ffff), - inet->rcv_saddr); - } goto out; } @@ -136,7 +134,7 @@ ipv4_connected: ipv6_addr_copy(&np->daddr, daddr); np->flow_label = fl.fl6_flowlabel; - inet->dport = usin->sin6_port; + inet->inet_dport = usin->sin6_port; /* * Check for a route to destination an obtain the @@ -147,8 +145,9 @@ ipv4_connected: 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.mark = sk->sk_mark; + fl.fl_ip_dport = inet->inet_dport; + fl.fl_ip_sport = inet->inet_sport; if (!fl.oif && (addr_type&IPV6_ADDR_MULTICAST)) fl.oif = np->mcast_oif; @@ -190,7 +189,7 @@ ipv4_connected: if (ipv6_addr_any(&np->rcv_saddr)) { ipv6_addr_copy(&np->rcv_saddr, &fl.fl6_src); - inet->rcv_saddr = LOOPBACK4_IPV6; + inet->inet_rcv_saddr = LOOPBACK4_IPV6; } ip6_dst_store(sk, dst, @@ -329,9 +328,8 @@ int ipv6_recv_error(struct sock *sk, struct msghdr *msg, int len) if (ipv6_addr_type(&sin->sin6_addr) & IPV6_ADDR_LINKLOCAL) sin->sin6_scope_id = IP6CB(skb)->iif; } else { - ipv6_addr_set(&sin->sin6_addr, 0, 0, - htonl(0xffff), - *(__be32 *)(nh + serr->addr_offset)); + ipv6_addr_set_v4mapped(*(__be32 *)(nh + serr->addr_offset), + &sin->sin6_addr); } } @@ -351,8 +349,8 @@ int ipv6_recv_error(struct sock *sk, struct msghdr *msg, int len) } else { struct inet_sock *inet = inet_sk(sk); - ipv6_addr_set(&sin->sin6_addr, 0, 0, - htonl(0xffff), ip_hdr(skb)->saddr); + ipv6_addr_set_v4mapped(ip_hdr(skb)->saddr, + &sin->sin6_addr); if (inet->cmsg_flags) ip_cmsg_recv(msg, skb); } diff --git a/net/ipv6/inet6_connection_sock.c b/net/ipv6/inet6_connection_sock.c index cc4797dd832..3516e6fe2e5 100644 --- a/net/ipv6/inet6_connection_sock.c +++ b/net/ipv6/inet6_connection_sock.c @@ -132,7 +132,7 @@ void inet6_csk_addr2sockaddr(struct sock *sk, struct sockaddr * uaddr) sin6->sin6_family = AF_INET6; ipv6_addr_copy(&sin6->sin6_addr, &np->daddr); - sin6->sin6_port = inet_sk(sk)->dport; + sin6->sin6_port = inet_sk(sk)->inet_dport; /* We do not store received flowlabel for TCP */ sin6->sin6_flowinfo = 0; sin6->sin6_scope_id = 0; @@ -168,8 +168,7 @@ struct dst_entry *__inet6_csk_dst_check(struct sock *sk, u32 cookie) if (dst) { struct rt6_info *rt = (struct rt6_info *)dst; if (rt->rt6i_flow_cache_genid != atomic_read(&flow_cache_genid)) { - sk->sk_dst_cache = NULL; - dst_release(dst); + __sk_dst_reset(sk); dst = NULL; } } @@ -194,8 +193,9 @@ int inet6_csk_xmit(struct sk_buff *skb, int ipfragok) fl.fl6_flowlabel = np->flow_label; IP6_ECN_flow_xmit(sk, fl.fl6_flowlabel); fl.oif = sk->sk_bound_dev_if; - fl.fl_ip_sport = inet->sport; - fl.fl_ip_dport = inet->dport; + fl.mark = sk->sk_mark; + fl.fl_ip_sport = inet->inet_sport; + fl.fl_ip_dport = inet->inet_dport; security_sk_classify_flow(sk, &fl); if (np->opt && np->opt->srcrt) { diff --git a/net/ipv6/inet6_hashtables.c b/net/ipv6/inet6_hashtables.c index 1bcc3431859..00c6a3e6cdd 100644 --- a/net/ipv6/inet6_hashtables.c +++ b/net/ipv6/inet6_hashtables.c @@ -73,7 +73,7 @@ struct sock *__inet6_lookup_established(struct net *net, * have wildcards anyways. */ unsigned int hash = inet6_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]; @@ -125,7 +125,7 @@ static int inline compute_score(struct sock *sk, struct net *net, { int score = -1; - if (net_eq(sock_net(sk), net) && inet_sk(sk)->num == hnum && + if (net_eq(sock_net(sk), net) && inet_sk(sk)->inet_num == hnum && sk->sk_family == PF_INET6) { const struct ipv6_pinfo *np = inet6_sk(sk); @@ -214,10 +214,10 @@ static int __inet6_check_established(struct inet_timewait_death_row *death_row, const struct in6_addr *daddr = &np->rcv_saddr; const struct in6_addr *saddr = &np->daddr; const int dif = sk->sk_bound_dev_if; - 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); const unsigned int hash = inet6_ehashfn(net, daddr, lport, saddr, - inet->dport); + inet->inet_dport); struct inet_ehash_bucket *head = inet_ehash_bucket(hinfo, hash); spinlock_t *lock = inet_ehash_lockp(hinfo, hash); struct sock *sk2; @@ -248,8 +248,8 @@ static int __inet6_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); WARN_ON(!sk_unhashed(sk)); __sk_nulls_add_node_rcu(sk, &head->chain); sk->sk_hash = hash; @@ -279,7 +279,7 @@ static inline u32 inet6_sk_port_offset(const struct sock *sk) const struct ipv6_pinfo *np = inet6_sk(sk); return secure_ipv6_port_ephemeral(np->rcv_saddr.s6_addr32, np->daddr.s6_addr32, - inet->dport); + inet->inet_dport); } int inet6_hash_connect(struct inet_timewait_death_row *death_row, diff --git a/net/ipv6/ip6_tunnel.c b/net/ipv6/ip6_tunnel.c index c595bbe1ed9..6c1b5c98e81 100644 --- a/net/ipv6/ip6_tunnel.c +++ b/net/ipv6/ip6_tunnel.c @@ -88,8 +88,10 @@ struct ip6_tnl_net { struct ip6_tnl **tnls[2]; }; -/* lock for the tunnel lists */ -static DEFINE_RWLOCK(ip6_tnl_lock); +/* + * Locking : hash tables are protected by RCU and a spinlock + */ +static DEFINE_SPINLOCK(ip6_tnl_lock); static inline struct dst_entry *ip6_tnl_dst_check(struct ip6_tnl *t) { @@ -130,6 +132,9 @@ static inline void ip6_tnl_dst_store(struct ip6_tnl *t, struct dst_entry *dst) * else %NULL **/ +#define for_each_ip6_tunnel_rcu(start) \ + for (t = rcu_dereference(start); t; t = rcu_dereference(t->next)) + static struct ip6_tnl * ip6_tnl_lookup(struct net *net, struct in6_addr *remote, struct in6_addr *local) { @@ -138,13 +143,14 @@ ip6_tnl_lookup(struct net *net, struct in6_addr *remote, struct in6_addr *local) struct ip6_tnl *t; struct ip6_tnl_net *ip6n = net_generic(net, ip6_tnl_net_id); - for (t = ip6n->tnls_r_l[h0 ^ h1]; t; t = t->next) { + for_each_ip6_tunnel_rcu(ip6n->tnls_r_l[h0 ^ h1]) { if (ipv6_addr_equal(local, &t->parms.laddr) && ipv6_addr_equal(remote, &t->parms.raddr) && (t->dev->flags & IFF_UP)) return t; } - if ((t = ip6n->tnls_wc[0]) != NULL && (t->dev->flags & IFF_UP)) + t = rcu_dereference(ip6n->tnls_wc[0]); + if (t && (t->dev->flags & IFF_UP)) return t; return NULL; @@ -186,10 +192,10 @@ ip6_tnl_link(struct ip6_tnl_net *ip6n, struct ip6_tnl *t) { struct ip6_tnl **tp = ip6_tnl_bucket(ip6n, &t->parms); + spin_lock_bh(&ip6_tnl_lock); t->next = *tp; - write_lock_bh(&ip6_tnl_lock); - *tp = t; - write_unlock_bh(&ip6_tnl_lock); + rcu_assign_pointer(*tp, t); + spin_unlock_bh(&ip6_tnl_lock); } /** @@ -204,9 +210,9 @@ ip6_tnl_unlink(struct ip6_tnl_net *ip6n, struct ip6_tnl *t) for (tp = ip6_tnl_bucket(ip6n, &t->parms); *tp; tp = &(*tp)->next) { if (t == *tp) { - write_lock_bh(&ip6_tnl_lock); + spin_lock_bh(&ip6_tnl_lock); *tp = t->next; - write_unlock_bh(&ip6_tnl_lock); + spin_unlock_bh(&ip6_tnl_lock); break; } } @@ -313,9 +319,9 @@ ip6_tnl_dev_uninit(struct net_device *dev) struct ip6_tnl_net *ip6n = net_generic(net, ip6_tnl_net_id); if (dev == ip6n->fb_tnl_dev) { - write_lock_bh(&ip6_tnl_lock); + spin_lock_bh(&ip6_tnl_lock); ip6n->tnls_wc[0] = NULL; - write_unlock_bh(&ip6_tnl_lock); + spin_unlock_bh(&ip6_tnl_lock); } else { ip6_tnl_unlink(ip6n, t); } @@ -409,7 +415,7 @@ ip6_tnl_err(struct sk_buff *skb, __u8 ipproto, struct inet6_skb_parm *opt, in trouble since we might need the source address for further processing of the error. */ - read_lock(&ip6_tnl_lock); + rcu_read_lock(); if ((t = ip6_tnl_lookup(dev_net(skb->dev), &ipv6h->daddr, &ipv6h->saddr)) == NULL) goto out; @@ -482,7 +488,7 @@ ip6_tnl_err(struct sk_buff *skb, __u8 ipproto, struct inet6_skb_parm *opt, *msg = rel_msg; out: - read_unlock(&ip6_tnl_lock); + rcu_read_unlock(); return err; } @@ -693,23 +699,23 @@ static int ip6_tnl_rcv(struct sk_buff *skb, __u16 protocol, struct ip6_tnl *t; struct ipv6hdr *ipv6h = ipv6_hdr(skb); - read_lock(&ip6_tnl_lock); + rcu_read_lock(); if ((t = ip6_tnl_lookup(dev_net(skb->dev), &ipv6h->saddr, &ipv6h->daddr)) != NULL) { if (t->parms.proto != ipproto && t->parms.proto != 0) { - read_unlock(&ip6_tnl_lock); + rcu_read_unlock(); goto discard; } if (!xfrm6_policy_check(NULL, XFRM_POLICY_IN, skb)) { - read_unlock(&ip6_tnl_lock); + rcu_read_unlock(); goto discard; } if (!ip6_tnl_rcv_ctl(t)) { t->dev->stats.rx_dropped++; - read_unlock(&ip6_tnl_lock); + rcu_read_unlock(); goto discard; } secpath_reset(skb); @@ -727,10 +733,10 @@ static int ip6_tnl_rcv(struct sk_buff *skb, __u16 protocol, t->dev->stats.rx_packets++; t->dev->stats.rx_bytes += skb->len; netif_rx(skb); - read_unlock(&ip6_tnl_lock); + rcu_read_unlock(); return 0; } - read_unlock(&ip6_tnl_lock); + rcu_read_unlock(); return 1; discard: @@ -1387,14 +1393,19 @@ static void ip6_tnl_destroy_tunnels(struct ip6_tnl_net *ip6n) { int h; struct ip6_tnl *t; + LIST_HEAD(list); for (h = 0; h < HASH_SIZE; h++) { - while ((t = ip6n->tnls_r_l[h]) != NULL) - unregister_netdevice(t->dev); + t = ip6n->tnls_r_l[h]; + while (t != NULL) { + unregister_netdevice_queue(t->dev, &list); + t = t->next; + } } t = ip6n->tnls_wc[0]; - unregister_netdevice(t->dev); + unregister_netdevice_queue(t->dev, &list); + unregister_netdevice_many(&list); } static int ip6_tnl_init_net(struct net *net) diff --git a/net/ipv6/ip6mr.c b/net/ipv6/ip6mr.c index 716153941fc..52e0f74fdfe 100644 --- a/net/ipv6/ip6mr.c +++ b/net/ipv6/ip6mr.c @@ -477,7 +477,7 @@ failure: * Delete a VIF entry */ -static int mif6_delete(struct net *net, int vifi) +static int mif6_delete(struct net *net, int vifi, struct list_head *head) { struct mif_device *v; struct net_device *dev; @@ -519,7 +519,7 @@ static int mif6_delete(struct net *net, int vifi) in6_dev->cnf.mc_forwarding--; if (v->flags & MIFF_REGISTER) - unregister_netdevice(dev); + unregister_netdevice_queue(dev, head); dev_put(dev); return 0; @@ -976,6 +976,7 @@ static int ip6mr_device_event(struct notifier_block *this, struct net *net = dev_net(dev); struct mif_device *v; int ct; + LIST_HEAD(list); if (event != NETDEV_UNREGISTER) return NOTIFY_DONE; @@ -983,8 +984,10 @@ static int ip6mr_device_event(struct notifier_block *this, v = &net->ipv6.vif6_table[0]; for (ct = 0; ct < net->ipv6.maxvif; ct++, v++) { if (v->dev == dev) - mif6_delete(net, ct); + mif6_delete(net, ct, &list); } + unregister_netdevice_many(&list); + return NOTIFY_DONE; } @@ -1188,14 +1191,16 @@ static int ip6mr_mfc_add(struct net *net, struct mf6cctl *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->ipv6.maxvif; i++) { if (!(net->ipv6.vif6_table[i].flags & VIFF_STATIC)) - mif6_delete(net, i); + mif6_delete(net, i, &list); } + unregister_netdevice_many(&list); /* * Wipe the cache @@ -1297,7 +1302,7 @@ int ip6_mroute_setsockopt(struct sock *sk, int optname, char __user *optval, uns switch (optname) { case MRT6_INIT: if (sk->sk_type != SOCK_RAW || - inet_sk(sk)->num != IPPROTO_ICMPV6) + inet_sk(sk)->inet_num != IPPROTO_ICMPV6) return -EOPNOTSUPP; if (optlen < sizeof(int)) return -EINVAL; @@ -1325,7 +1330,7 @@ int ip6_mroute_setsockopt(struct sock *sk, int optname, char __user *optval, uns if (copy_from_user(&mifi, optval, sizeof(mifi_t))) return -EFAULT; rtnl_lock(); - ret = mif6_delete(net, mifi); + ret = mif6_delete(net, mifi, NULL); rtnl_unlock(); return ret; diff --git a/net/ipv6/ipv6_sockglue.c b/net/ipv6/ipv6_sockglue.c index 4f7aaf6996a..430454ee5ea 100644 --- a/net/ipv6/ipv6_sockglue.c +++ b/net/ipv6/ipv6_sockglue.c @@ -64,7 +64,7 @@ int ip6_ra_control(struct sock *sk, int sel) struct ip6_ra_chain *ra, *new_ra, **rap; /* RA packet may be delivered ONLY to IPPROTO_RAW socket */ - 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 -ENOPROTOOPT; new_ra = (sel>=0) ? kmalloc(sizeof(*new_ra), GFP_KERNEL) : NULL; @@ -106,7 +106,7 @@ struct ipv6_txoptions *ipv6_update_options(struct sock *sk, if (inet_sk(sk)->is_icsk) { if (opt && !((1 << sk->sk_state) & (TCPF_LISTEN | TCPF_CLOSE)) && - inet_sk(sk)->daddr != LOOPBACK4_IPV6) { + inet_sk(sk)->inet_daddr != LOOPBACK4_IPV6) { struct inet_connection_sock *icsk = inet_csk(sk); icsk->icsk_ext_hdr_len = opt->opt_flen + opt->opt_nflen; icsk->icsk_sync_mss(sk, icsk->icsk_pmtu_cookie); @@ -234,7 +234,7 @@ static int do_ipv6_setsockopt(struct sock *sk, int level, int optname, case IPV6_V6ONLY: if (optlen < sizeof(int) || - inet_sk(sk)->num) + inet_sk(sk)->inet_num) goto e_inval; np->ipv6only = valbool; retv = 0; @@ -424,6 +424,7 @@ sticky_done: fl.fl6_flowlabel = 0; fl.oif = sk->sk_bound_dev_if; + fl.mark = sk->sk_mark; if (optlen == 0) goto update; @@ -665,7 +666,7 @@ done: case IPV6_MTU_DISCOVER: if (optlen < sizeof(int)) goto e_inval; - if (val<0 || val>3) + if (val < IP_PMTUDISC_DONT || val > IP_PMTUDISC_PROBE) goto e_inval; np->pmtudisc = val; retv = 0; diff --git a/net/ipv6/ndisc.c b/net/ipv6/ndisc.c index f74e4e2cdd0..3507cfe1e7a 100644 --- a/net/ipv6/ndisc.c +++ b/net/ipv6/ndisc.c @@ -598,6 +598,7 @@ static void ndisc_send_na(struct net_device *dev, struct neighbour *neigh, icmp6h.icmp6_solicited = solicited; icmp6h.icmp6_override = override; + inc_opt |= ifp->idev->cnf.force_tllao; __ndisc_send(dev, neigh, daddr, src_addr, &icmp6h, solicited_addr, inc_opt ? ND_OPT_TARGET_LL_ADDR : 0); diff --git a/net/ipv6/raw.c b/net/ipv6/raw.c index 4f24570b086..cb834ab7f07 100644 --- a/net/ipv6/raw.c +++ b/net/ipv6/raw.c @@ -72,7 +72,7 @@ static struct sock *__raw_v6_lookup(struct net *net, struct sock *sk, int is_multicast = ipv6_addr_is_multicast(loc_addr); sk_for_each_from(sk, node) - if (inet_sk(sk)->num == num) { + if (inet_sk(sk)->inet_num == num) { struct ipv6_pinfo *np = inet6_sk(sk); if (!net_eq(sock_net(sk), net)) @@ -298,7 +298,7 @@ static int rawv6_bind(struct sock *sk, struct sockaddr *uaddr, int addr_len) dev_put(dev); } - inet->rcv_saddr = inet->saddr = v4addr; + inet->inet_rcv_saddr = inet->inet_saddr = v4addr; ipv6_addr_copy(&np->rcv_saddr, &addr->sin6_addr); if (!(addr_type & IPV6_ADDR_MULTICAST)) ipv6_addr_copy(&np->saddr, &addr->sin6_addr); @@ -381,8 +381,7 @@ static inline int rawv6_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); + if (sock_queue_rcv_skb(sk, skb) < 0) { kfree_skb(skb); return NET_RX_DROP; } @@ -416,14 +415,14 @@ int rawv6_rcv(struct sock *sk, struct sk_buff *skb) skb_network_header_len(skb)); if (!csum_ipv6_magic(&ipv6_hdr(skb)->saddr, &ipv6_hdr(skb)->daddr, - skb->len, inet->num, skb->csum)) + skb->len, inet->inet_num, skb->csum)) skb->ip_summed = CHECKSUM_UNNECESSARY; } if (!skb_csum_unnecessary(skb)) skb->csum = ~csum_unfold(csum_ipv6_magic(&ipv6_hdr(skb)->saddr, &ipv6_hdr(skb)->daddr, skb->len, - inet->num, 0)); + inet->inet_num, 0)); if (inet->hdrincl) { if (skb_checksum_complete(skb)) { @@ -497,7 +496,7 @@ static int rawv6_recvmsg(struct kiocb *iocb, struct sock *sk, sin6->sin6_scope_id = IP6CB(skb)->iif; } - sock_recv_timestamp(msg, sk, skb); + sock_recv_ts_and_drops(msg, sk, skb); if (np->rxopt.all) datagram_recv_ctl(sk, msg, skb); @@ -518,7 +517,6 @@ csum_copy_err: as some normal condition. */ err = (flags&MSG_DONTWAIT) ? -EAGAIN : -EHOSTUNREACH; - atomic_inc(&sk->sk_drops); goto out; } @@ -766,8 +764,8 @@ static int rawv6_sendmsg(struct kiocb *iocb, struct sock *sk, proto = ntohs(sin6->sin6_port); if (!proto) - proto = inet->num; - else if (proto != inet->num) + proto = inet->inet_num; + else if (proto != inet->inet_num) return(-EINVAL); if (proto > 255) @@ -800,7 +798,7 @@ static int rawv6_sendmsg(struct kiocb *iocb, struct sock *sk, if (sk->sk_state != TCP_ESTABLISHED) return -EDESTADDRREQ; - proto = inet->num; + proto = inet->inet_num; daddr = &np->daddr; fl.fl6_flowlabel = np->flow_label; } @@ -967,7 +965,7 @@ static int do_rawv6_setsockopt(struct sock *sk, int level, int optname, switch (optname) { case IPV6_CHECKSUM: - if (inet_sk(sk)->num == IPPROTO_ICMPV6 && + if (inet_sk(sk)->inet_num == IPPROTO_ICMPV6 && level == IPPROTO_IPV6) { /* * RFC3542 tells that IPV6_CHECKSUM socket @@ -1007,7 +1005,7 @@ static int rawv6_setsockopt(struct sock *sk, int level, int optname, break; case SOL_ICMPV6: - if (inet_sk(sk)->num != IPPROTO_ICMPV6) + if (inet_sk(sk)->inet_num != IPPROTO_ICMPV6) return -EOPNOTSUPP; return rawv6_seticmpfilter(sk, level, optname, optval, optlen); @@ -1030,7 +1028,7 @@ static int compat_rawv6_setsockopt(struct sock *sk, int level, int optname, case SOL_RAW: break; case SOL_ICMPV6: - if (inet_sk(sk)->num != IPPROTO_ICMPV6) + if (inet_sk(sk)->inet_num != IPPROTO_ICMPV6) return -EOPNOTSUPP; return rawv6_seticmpfilter(sk, level, optname, optval, optlen); case SOL_IPV6: @@ -1087,7 +1085,7 @@ static int rawv6_getsockopt(struct sock *sk, int level, int optname, break; case SOL_ICMPV6: - if (inet_sk(sk)->num != IPPROTO_ICMPV6) + if (inet_sk(sk)->inet_num != IPPROTO_ICMPV6) return -EOPNOTSUPP; return rawv6_geticmpfilter(sk, level, optname, optval, optlen); @@ -1110,7 +1108,7 @@ static int compat_rawv6_getsockopt(struct sock *sk, int level, int optname, case SOL_RAW: break; case SOL_ICMPV6: - if (inet_sk(sk)->num != IPPROTO_ICMPV6) + if (inet_sk(sk)->inet_num != IPPROTO_ICMPV6) return -EOPNOTSUPP; return rawv6_geticmpfilter(sk, level, optname, optval, optlen); case SOL_IPV6: @@ -1157,7 +1155,7 @@ static int rawv6_ioctl(struct sock *sk, int cmd, unsigned long arg) static void rawv6_close(struct sock *sk, long timeout) { - if (inet_sk(sk)->num == IPPROTO_RAW) + if (inet_sk(sk)->inet_num == IPPROTO_RAW) ip6_ra_control(sk, -1); ip6mr_sk_done(sk); sk_common_release(sk); @@ -1176,7 +1174,7 @@ static int rawv6_init_sk(struct sock *sk) { struct raw6_sock *rp = raw6_sk(sk); - switch (inet_sk(sk)->num) { + switch (inet_sk(sk)->inet_num) { case IPPROTO_ICMPV6: rp->checksum = 1; rp->offset = 2; @@ -1226,7 +1224,7 @@ static void raw6_sock_seq_show(struct seq_file *seq, struct sock *sp, int i) dest = &np->daddr; src = &np->rcv_saddr; destp = 0; - srcp = inet_sk(sp)->num; + srcp = inet_sk(sp)->inet_num; seq_printf(seq, "%4d: %08X%08X%08X%08X:%04X %08X%08X%08X%08X:%04X " "%02X %08X:%08X %02X:%08lX %08X %5d %8d %lu %d %p %d\n", diff --git a/net/ipv6/route.c b/net/ipv6/route.c index d6fe7646a8f..df9432a46ff 100644 --- a/net/ipv6/route.c +++ b/net/ipv6/route.c @@ -1471,9 +1471,10 @@ static struct rt6_info *ip6_route_redirect(struct in6_addr *dest, }, }, }, - .gateway = *gateway, }; + ipv6_addr_copy(&rdfl.gateway, gateway); + if (rt6_need_strict(dest)) flags |= RT6_LOOKUP_F_IFACE; diff --git a/net/ipv6/sit.c b/net/ipv6/sit.c index dbd19a78ca7..2362a3397e9 100644 --- a/net/ipv6/sit.c +++ b/net/ipv6/sit.c @@ -77,8 +77,17 @@ struct sit_net { struct net_device *fb_tunnel_dev; }; -static DEFINE_RWLOCK(ipip6_lock); +/* + * Locking : hash tables are protected by RCU and a spinlock + */ +static DEFINE_SPINLOCK(ipip6_lock); +#define for_each_ip_tunnel_rcu(start) \ + for (t = rcu_dereference(start); t; t = rcu_dereference(t->next)) + +/* + * Must be invoked with rcu_read_lock + */ static struct ip_tunnel * ipip6_tunnel_lookup(struct net *net, struct net_device *dev, __be32 remote, __be32 local) { @@ -87,26 +96,26 @@ static struct ip_tunnel * ipip6_tunnel_lookup(struct net *net, struct ip_tunnel *t; struct sit_net *sitn = net_generic(net, sit_net_id); - for (t = sitn->tunnels_r_l[h0^h1]; t; t = t->next) { + for_each_ip_tunnel_rcu(sitn->tunnels_r_l[h0 ^ h1]) { if (local == t->parms.iph.saddr && remote == t->parms.iph.daddr && (!dev || !t->parms.link || dev->iflink == t->parms.link) && (t->dev->flags & IFF_UP)) return t; } - for (t = sitn->tunnels_r[h0]; t; t = t->next) { + for_each_ip_tunnel_rcu(sitn->tunnels_r[h0]) { if (remote == t->parms.iph.daddr && (!dev || !t->parms.link || dev->iflink == t->parms.link) && (t->dev->flags & IFF_UP)) return t; } - for (t = sitn->tunnels_l[h1]; t; t = t->next) { + for_each_ip_tunnel_rcu(sitn->tunnels_l[h1]) { if (local == t->parms.iph.saddr && (!dev || !t->parms.link || dev->iflink == t->parms.link) && (t->dev->flags & IFF_UP)) return t; } - t = sitn->tunnels_wc[0]; + t = rcu_dereference(sitn->tunnels_wc[0]); if ((t != NULL) && (t->dev->flags & IFF_UP)) return t; return NULL; @@ -143,9 +152,9 @@ static void ipip6_tunnel_unlink(struct sit_net *sitn, struct ip_tunnel *t) for (tp = ipip6_bucket(sitn, t); *tp; tp = &(*tp)->next) { if (t == *tp) { - write_lock_bh(&ipip6_lock); + spin_lock_bh(&ipip6_lock); *tp = t->next; - write_unlock_bh(&ipip6_lock); + spin_unlock_bh(&ipip6_lock); break; } } @@ -155,10 +164,27 @@ static void ipip6_tunnel_link(struct sit_net *sitn, struct ip_tunnel *t) { struct ip_tunnel **tp = ipip6_bucket(sitn, t); + spin_lock_bh(&ipip6_lock); t->next = *tp; - write_lock_bh(&ipip6_lock); - *tp = t; - write_unlock_bh(&ipip6_lock); + rcu_assign_pointer(*tp, t); + spin_unlock_bh(&ipip6_lock); +} + +static void ipip6_tunnel_clone_6rd(struct net_device *dev, struct sit_net *sitn) +{ +#ifdef CONFIG_IPV6_SIT_6RD + struct ip_tunnel *t = netdev_priv(dev); + + if (t->dev == sitn->fb_tunnel_dev) { + ipv6_addr_set(&t->ip6rd.prefix, htonl(0x20020000), 0, 0, 0); + t->ip6rd.relay_prefix = 0; + t->ip6rd.prefixlen = 16; + t->ip6rd.relay_prefixlen = 0; + } else { + struct ip_tunnel *t0 = netdev_priv(sitn->fb_tunnel_dev); + memcpy(&t->ip6rd, &t0->ip6rd, sizeof(t->ip6rd)); + } +#endif } static struct ip_tunnel * ipip6_tunnel_locate(struct net *net, @@ -204,6 +230,7 @@ static struct ip_tunnel * ipip6_tunnel_locate(struct net *net, nt->parms = *parms; ipip6_tunnel_init(dev); + ipip6_tunnel_clone_6rd(dev, sitn); if (parms->i_flags & SIT_ISATAP) dev->priv_flags |= IFF_ISATAP; @@ -222,15 +249,22 @@ failed: return NULL; } +static DEFINE_SPINLOCK(ipip6_prl_lock); + +#define for_each_prl_rcu(start) \ + for (prl = rcu_dereference(start); \ + prl; \ + prl = rcu_dereference(prl->next)) + static struct ip_tunnel_prl_entry * __ipip6_tunnel_locate_prl(struct ip_tunnel *t, __be32 addr) { - struct ip_tunnel_prl_entry *p = (struct ip_tunnel_prl_entry *)NULL; + struct ip_tunnel_prl_entry *prl; - for (p = t->prl; p; p = p->next) - if (p->addr == addr) + for_each_prl_rcu(t->prl) + if (prl->addr == addr) break; - return p; + return prl; } @@ -255,7 +289,7 @@ static int ipip6_tunnel_get_prl(struct ip_tunnel *t, kcalloc(cmax, sizeof(*kp), GFP_KERNEL) : NULL; - read_lock(&ipip6_lock); + rcu_read_lock(); ca = t->prl_count < cmax ? t->prl_count : cmax; @@ -273,7 +307,7 @@ static int ipip6_tunnel_get_prl(struct ip_tunnel *t, } c = 0; - for (prl = t->prl; prl; prl = prl->next) { + for_each_prl_rcu(t->prl) { if (c >= cmax) break; if (kprl.addr != htonl(INADDR_ANY) && prl->addr != kprl.addr) @@ -285,7 +319,7 @@ static int ipip6_tunnel_get_prl(struct ip_tunnel *t, break; } out: - read_unlock(&ipip6_lock); + rcu_read_unlock(); len = sizeof(*kp) * c; ret = 0; @@ -306,12 +340,14 @@ ipip6_tunnel_add_prl(struct ip_tunnel *t, struct ip_tunnel_prl *a, int chg) if (a->addr == htonl(INADDR_ANY)) return -EINVAL; - write_lock(&ipip6_lock); + spin_lock(&ipip6_prl_lock); for (p = t->prl; p; p = p->next) { if (p->addr == a->addr) { - if (chg) - goto update; + if (chg) { + p->flags = a->flags; + goto out; + } err = -EEXIST; goto out; } @@ -328,46 +364,63 @@ ipip6_tunnel_add_prl(struct ip_tunnel *t, struct ip_tunnel_prl *a, int chg) goto out; } + INIT_RCU_HEAD(&p->rcu_head); p->next = t->prl; - t->prl = p; - t->prl_count++; -update: p->addr = a->addr; p->flags = a->flags; + t->prl_count++; + rcu_assign_pointer(t->prl, p); out: - write_unlock(&ipip6_lock); + spin_unlock(&ipip6_prl_lock); return err; } +static void prl_entry_destroy_rcu(struct rcu_head *head) +{ + kfree(container_of(head, struct ip_tunnel_prl_entry, rcu_head)); +} + +static void prl_list_destroy_rcu(struct rcu_head *head) +{ + struct ip_tunnel_prl_entry *p, *n; + + p = container_of(head, struct ip_tunnel_prl_entry, rcu_head); + do { + n = p->next; + kfree(p); + p = n; + } while (p); +} + static int ipip6_tunnel_del_prl(struct ip_tunnel *t, struct ip_tunnel_prl *a) { struct ip_tunnel_prl_entry *x, **p; int err = 0; - write_lock(&ipip6_lock); + spin_lock(&ipip6_prl_lock); if (a && a->addr != htonl(INADDR_ANY)) { for (p = &t->prl; *p; p = &(*p)->next) { if ((*p)->addr == a->addr) { x = *p; *p = x->next; - kfree(x); + call_rcu(&x->rcu_head, prl_entry_destroy_rcu); t->prl_count--; goto out; } } err = -ENXIO; } else { - while (t->prl) { + if (t->prl) { + t->prl_count = 0; x = t->prl; - t->prl = t->prl->next; - kfree(x); - t->prl_count--; + call_rcu(&x->rcu_head, prl_list_destroy_rcu); + t->prl = NULL; } } out: - write_unlock(&ipip6_lock); + spin_unlock(&ipip6_prl_lock); return err; } @@ -377,7 +430,7 @@ isatap_chksrc(struct sk_buff *skb, struct iphdr *iph, struct ip_tunnel *t) struct ip_tunnel_prl_entry *p; int ok = 1; - read_lock(&ipip6_lock); + rcu_read_lock(); p = __ipip6_tunnel_locate_prl(t, iph->saddr); if (p) { if (p->flags & PRL_DEFAULT) @@ -393,7 +446,7 @@ isatap_chksrc(struct sk_buff *skb, struct iphdr *iph, struct ip_tunnel *t) else ok = 0; } - read_unlock(&ipip6_lock); + rcu_read_unlock(); return ok; } @@ -403,9 +456,9 @@ static void ipip6_tunnel_uninit(struct net_device *dev) struct sit_net *sitn = net_generic(net, sit_net_id); if (dev == sitn->fb_tunnel_dev) { - write_lock_bh(&ipip6_lock); + spin_lock_bh(&ipip6_lock); sitn->tunnels_wc[0] = NULL; - write_unlock_bh(&ipip6_lock); + spin_unlock_bh(&ipip6_lock); dev_put(dev); } else { ipip6_tunnel_unlink(sitn, netdev_priv(dev)); @@ -458,7 +511,7 @@ static int ipip6_err(struct sk_buff *skb, u32 info) err = -ENOENT; - read_lock(&ipip6_lock); + rcu_read_lock(); t = ipip6_tunnel_lookup(dev_net(skb->dev), skb->dev, iph->daddr, @@ -476,7 +529,7 @@ static int ipip6_err(struct sk_buff *skb, u32 info) t->err_count = 1; t->err_time = jiffies; out: - read_unlock(&ipip6_lock); + rcu_read_unlock(); return err; } @@ -496,7 +549,7 @@ static int ipip6_rcv(struct sk_buff *skb) iph = ip_hdr(skb); - read_lock(&ipip6_lock); + rcu_read_lock(); tunnel = ipip6_tunnel_lookup(dev_net(skb->dev), skb->dev, iph->saddr, iph->daddr); if (tunnel != NULL) { @@ -510,7 +563,7 @@ static int ipip6_rcv(struct sk_buff *skb) if ((tunnel->dev->priv_flags & IFF_ISATAP) && !isatap_chksrc(skb, iph, tunnel)) { tunnel->dev->stats.rx_errors++; - read_unlock(&ipip6_lock); + rcu_read_unlock(); kfree_skb(skb); return 0; } @@ -521,28 +574,52 @@ static int ipip6_rcv(struct sk_buff *skb) nf_reset(skb); ipip6_ecn_decapsulate(iph, skb); netif_rx(skb); - read_unlock(&ipip6_lock); + rcu_read_unlock(); return 0; } icmp_send(skb, ICMP_DEST_UNREACH, ICMP_PORT_UNREACH, 0); - read_unlock(&ipip6_lock); + rcu_read_unlock(); out: kfree_skb(skb); return 0; } -/* Returns the embedded IPv4 address if the IPv6 address - comes from 6to4 (RFC 3056) addr space */ - -static inline __be32 try_6to4(struct in6_addr *v6dst) +/* + * Returns the embedded IPv4 address if the IPv6 address + * comes from 6rd / 6to4 (RFC 3056) addr space. + */ +static inline +__be32 try_6rd(struct in6_addr *v6dst, struct ip_tunnel *tunnel) { __be32 dst = 0; +#ifdef CONFIG_IPV6_SIT_6RD + if (ipv6_prefix_equal(v6dst, &tunnel->ip6rd.prefix, + tunnel->ip6rd.prefixlen)) { + unsigned pbw0, pbi0; + int pbi1; + u32 d; + + pbw0 = tunnel->ip6rd.prefixlen >> 5; + pbi0 = tunnel->ip6rd.prefixlen & 0x1f; + + d = (ntohl(v6dst->s6_addr32[pbw0]) << pbi0) >> + tunnel->ip6rd.relay_prefixlen; + + pbi1 = pbi0 - tunnel->ip6rd.relay_prefixlen; + if (pbi1 > 0) + d |= ntohl(v6dst->s6_addr32[pbw0 + 1]) >> + (32 - pbi1); + + dst = tunnel->ip6rd.relay_prefix | htonl(d); + } +#else if (v6dst->s6_addr16[0] == htons(0x2002)) { /* 6to4 v6 addr has 16 bits prefix, 32 v4addr, 16 SLA, ... */ memcpy(&dst, &v6dst->s6_addr16[1], 4); } +#endif return dst; } @@ -555,7 +632,8 @@ static netdev_tx_t ipip6_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; struct ipv6hdr *iph6 = ipv6_hdr(skb); u8 tos = tunnel->parms.iph.tos; @@ -595,7 +673,7 @@ static netdev_tx_t ipip6_tunnel_xmit(struct sk_buff *skb, } if (!dst) - dst = try_6to4(&iph6->daddr); + dst = try_6rd(&iph6->daddr, tunnel); if (!dst) { struct neighbour *neigh = NULL; @@ -688,7 +766,7 @@ static netdev_tx_t ipip6_tunnel_xmit(struct sk_buff *skb, 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; } @@ -785,9 +863,15 @@ ipip6_tunnel_ioctl (struct net_device *dev, struct ifreq *ifr, int cmd) struct ip_tunnel *t; struct net *net = dev_net(dev); struct sit_net *sitn = net_generic(net, sit_net_id); +#ifdef CONFIG_IPV6_SIT_6RD + struct ip_tunnel_6rd ip6rd; +#endif switch (cmd) { case SIOCGETTUNNEL: +#ifdef CONFIG_IPV6_SIT_6RD + case SIOCGET6RD: +#endif t = NULL; if (dev == sitn->fb_tunnel_dev) { if (copy_from_user(&p, ifr->ifr_ifru.ifru_data, sizeof(p))) { @@ -798,9 +882,25 @@ ipip6_tunnel_ioctl (struct net_device *dev, struct ifreq *ifr, int cmd) } if (t == NULL) t = netdev_priv(dev); - memcpy(&p, &t->parms, sizeof(p)); - if (copy_to_user(ifr->ifr_ifru.ifru_data, &p, sizeof(p))) - err = -EFAULT; + + err = -EFAULT; + if (cmd == SIOCGETTUNNEL) { + memcpy(&p, &t->parms, sizeof(p)); + if (copy_to_user(ifr->ifr_ifru.ifru_data, &p, + sizeof(p))) + goto done; +#ifdef CONFIG_IPV6_SIT_6RD + } else { + ipv6_addr_copy(&ip6rd.prefix, &t->ip6rd.prefix); + ip6rd.relay_prefix = t->ip6rd.relay_prefix; + ip6rd.prefixlen = t->ip6rd.prefixlen; + ip6rd.relay_prefixlen = t->ip6rd.relay_prefixlen; + if (copy_to_user(ifr->ifr_ifru.ifru_data, &ip6rd, + sizeof(ip6rd))) + goto done; +#endif + } + err = 0; break; case SIOCADDTUNNEL: @@ -921,6 +1021,54 @@ ipip6_tunnel_ioctl (struct net_device *dev, struct ifreq *ifr, int cmd) netdev_state_change(dev); break; +#ifdef CONFIG_IPV6_SIT_6RD + case SIOCADD6RD: + case SIOCCHG6RD: + case SIOCDEL6RD: + err = -EPERM; + if (!capable(CAP_NET_ADMIN)) + goto done; + + err = -EFAULT; + if (copy_from_user(&ip6rd, ifr->ifr_ifru.ifru_data, + sizeof(ip6rd))) + goto done; + + t = netdev_priv(dev); + + if (cmd != SIOCDEL6RD) { + struct in6_addr prefix; + __be32 relay_prefix; + + err = -EINVAL; + if (ip6rd.relay_prefixlen > 32 || + ip6rd.prefixlen + (32 - ip6rd.relay_prefixlen) > 64) + goto done; + + ipv6_addr_prefix(&prefix, &ip6rd.prefix, + ip6rd.prefixlen); + if (!ipv6_addr_equal(&prefix, &ip6rd.prefix)) + goto done; + if (ip6rd.relay_prefixlen) + relay_prefix = ip6rd.relay_prefix & + htonl(0xffffffffUL << + (32 - ip6rd.relay_prefixlen)); + else + relay_prefix = 0; + if (relay_prefix != ip6rd.relay_prefix) + goto done; + + ipv6_addr_copy(&t->ip6rd.prefix, &prefix); + t->ip6rd.relay_prefix = relay_prefix; + t->ip6rd.prefixlen = ip6rd.prefixlen; + t->ip6rd.relay_prefixlen = ip6rd.relay_prefixlen; + } else + ipip6_tunnel_clone_6rd(dev, sitn); + + err = 0; + break; +#endif + default: err = -EINVAL; } @@ -997,16 +1145,19 @@ static struct xfrm_tunnel sit_handler = { .priority = 1, }; -static void sit_destroy_tunnels(struct sit_net *sitn) +static void sit_destroy_tunnels(struct sit_net *sitn, 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 = sitn->tunnels[prio][h]) != NULL) - unregister_netdevice(t->dev); + struct ip_tunnel *t = sitn->tunnels[prio][h]; + + while (t != NULL) { + unregister_netdevice_queue(t->dev, head); + t = t->next; + } } } } @@ -1039,6 +1190,7 @@ static int sit_init_net(struct net *net) dev_net_set(sitn->fb_tunnel_dev, net); ipip6_fb_tunnel_init(sitn->fb_tunnel_dev); + ipip6_tunnel_clone_6rd(sitn->fb_tunnel_dev, sitn); if ((err = register_netdev(sitn->fb_tunnel_dev))) goto err_reg_dev; @@ -1059,11 +1211,13 @@ err_alloc: static void sit_exit_net(struct net *net) { struct sit_net *sitn; + LIST_HEAD(list); sitn = net_generic(net, sit_net_id); rtnl_lock(); - sit_destroy_tunnels(sitn); - unregister_netdevice(sitn->fb_tunnel_dev); + sit_destroy_tunnels(sitn, &list); + unregister_netdevice_queue(sitn->fb_tunnel_dev, &list); + unregister_netdevice_many(&list); rtnl_unlock(); kfree(sitn); } @@ -1078,6 +1232,7 @@ static void __exit sit_cleanup(void) xfrm4_tunnel_deregister(&sit_handler, AF_INET6); unregister_pernet_gen_device(sit_net_id, &sit_net_ops); + rcu_barrier(); /* Wait for completion of call_rcu()'s */ } static int __init sit_init(void) diff --git a/net/ipv6/syncookies.c b/net/ipv6/syncookies.c index 6b6ae913b5d..612fc53e0bb 100644 --- a/net/ipv6/syncookies.c +++ b/net/ipv6/syncookies.c @@ -184,13 +184,6 @@ struct sock *cookie_v6_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 = inet6_reqsk_alloc(&tcp6_request_sock_ops); if (!req) @@ -224,12 +217,6 @@ struct sock *cookie_v6_check(struct sock *sk, struct sk_buff *skb) req->expires = 0UL; req->retrans = 0; 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; treq->rcv_isn = ntohl(th->seq) - 1; treq->snt_isn = cookie; @@ -252,8 +239,9 @@ struct sock *cookie_v6_check(struct sock *sk, struct sk_buff *skb) } ipv6_addr_copy(&fl.fl6_src, &ireq6->loc_addr); fl.oif = sk->sk_bound_dev_if; + fl.mark = sk->sk_mark; fl.fl_ip_dport = inet_rsk(req)->rmt_port; - fl.fl_ip_sport = inet_sk(sk)->sport; + fl.fl_ip_sport = inet_sk(sk)->inet_sport; security_req_classify_flow(req, &fl); if (ip6_dst_lookup(sk, &dst, &fl)) goto out_free; @@ -264,6 +252,21 @@ struct sock *cookie_v6_check(struct sock *sk, struct sk_buff *skb) goto out_free; } + /* check for timestamp cookie support */ + memset(&tcp_opt, 0, sizeof(tcp_opt)); + tcp_parse_options(skb, &tcp_opt, 0, dst); + + if (tcp_opt.saw_tstamp) + cookie_check_timestamp(&tcp_opt); + + req->ts_recent = tcp_opt.saw_tstamp ? tcp_opt.rcv_tsval : 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->window_clamp = tp->window_clamp ? :dst_metric(dst, RTAX_WINDOW); tcp_select_initial_window(tcp_full_space(sk), req->mss, &req->rcv_wnd, &req->window_clamp, diff --git a/net/ipv6/tcp_ipv6.c b/net/ipv6/tcp_ipv6.c index 21d100b68b1..34925f089e0 100644 --- a/net/ipv6/tcp_ipv6.c +++ b/net/ipv6/tcp_ipv6.c @@ -226,10 +226,9 @@ static int tcp_v6_connect(struct sock *sk, struct sockaddr *uaddr, #endif 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; @@ -243,8 +242,9 @@ static int tcp_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.mark = sk->sk_mark; fl.fl_ip_dport = usin->sin6_port; - fl.fl_ip_sport = inet->sport; + fl.fl_ip_sport = inet->inet_sport; if (np->opt && np->opt->srcrt) { struct rt0_hdr *rt0 = (struct rt0_hdr *)np->opt->srcrt; @@ -276,7 +276,7 @@ static int tcp_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; sk->sk_gso_type = SKB_GSO_TCPV6; __ip6_dst_store(sk, dst, NULL, NULL); @@ -288,7 +288,7 @@ static int tcp_v6_connect(struct sock *sk, struct sockaddr *uaddr, tp->rx_opt.mss_clamp = IPV6_MIN_MTU - sizeof(struct tcphdr) - sizeof(struct ipv6hdr); - inet->dport = usin->sin6_port; + inet->inet_dport = usin->sin6_port; tcp_set_state(sk, TCP_SYN_SENT); err = inet6_hash_connect(&tcp_death_row, sk); @@ -298,8 +298,8 @@ static int tcp_v6_connect(struct sock *sk, struct sockaddr *uaddr, if (!tp->write_seq) tp->write_seq = secure_tcpv6_sequence_number(np->saddr.s6_addr32, np->daddr.s6_addr32, - inet->sport, - inet->dport); + inet->inet_sport, + inet->inet_dport); err = tcp_connect(sk); if (err) @@ -311,7 +311,7 @@ late_failure: tcp_set_state(sk, TCP_CLOSE); __sk_dst_reset(sk); failure: - inet->dport = 0; + inet->inet_dport = 0; sk->sk_route_caps = 0; return err; } @@ -383,8 +383,9 @@ static void tcp_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.mark = sk->sk_mark; + fl.fl_ip_dport = inet->inet_dport; + fl.fl_ip_sport = inet->inet_sport; security_skb_classify_flow(skb, &fl); if ((err = ip6_dst_lookup(sk, &dst, &fl))) { @@ -477,6 +478,7 @@ static int tcp_v6_send_synack(struct sock *sk, struct request_sock *req) ipv6_addr_copy(&fl.fl6_src, &treq->loc_addr); fl.fl6_flowlabel = 0; fl.oif = treq->iif; + fl.mark = sk->sk_mark; fl.fl_ip_dport = inet_rsk(req)->rmt_port; fl.fl_ip_sport = inet_rsk(req)->loc_port; security_req_classify_flow(req, &fl); @@ -1165,6 +1167,7 @@ static int tcp_v6_conn_request(struct sock *sk, struct sk_buff *skb) struct tcp_sock *tp = tcp_sk(sk); struct request_sock *req = NULL; __u32 isn = TCP_SKB_CB(skb)->when; + struct dst_entry *dst = __sk_dst_get(sk); #ifdef CONFIG_SYN_COOKIES int want_cookie = 0; #else @@ -1203,7 +1206,7 @@ static int tcp_v6_conn_request(struct sock *sk, struct sk_buff *skb) tmp_opt.mss_clamp = IPV6_MIN_MTU - sizeof(struct tcphdr) - sizeof(struct ipv6hdr); tmp_opt.user_mss = tp->rx_opt.user_mss; - tcp_parse_options(skb, &tmp_opt, 0); + tcp_parse_options(skb, &tmp_opt, 0, dst); if (want_cookie && !tmp_opt.saw_tstamp) tcp_clear_options(&tmp_opt); @@ -1290,11 +1293,9 @@ static struct sock * tcp_v6_syn_recv_sock(struct sock *sk, struct sk_buff *skb, 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); @@ -1345,6 +1346,7 @@ static struct sock * tcp_v6_syn_recv_sock(struct sock *sk, struct sk_buff *skb, } ipv6_addr_copy(&fl.fl6_src, &treq->loc_addr); fl.oif = sk->sk_bound_dev_if; + fl.mark = sk->sk_mark; fl.fl_ip_dport = inet_rsk(req)->rmt_port; fl.fl_ip_sport = inet_rsk(req)->loc_port; security_req_classify_flow(req, &fl); @@ -1431,7 +1433,8 @@ static struct sock * tcp_v6_syn_recv_sock(struct sock *sk, struct sk_buff *skb, newtp->advmss = dst_metric(dst, RTAX_ADVMSS); tcp_initialize_rcv_mss(newsk); - newinet->daddr = newinet->saddr = newinet->rcv_saddr = LOOPBACK4_IPV6; + newinet->inet_daddr = newinet->inet_saddr = LOOPBACK4_IPV6; + newinet->inet_rcv_saddr = LOOPBACK4_IPV6; #ifdef CONFIG_TCP_MD5SIG /* Copy over the MD5 key from the original socket */ @@ -1931,8 +1934,8 @@ static void get_tcp6_sock(struct seq_file *seq, struct sock *sp, int i) dest = &np->daddr; src = &np->rcv_saddr; - destp = ntohs(inet->dport); - srcp = ntohs(inet->sport); + destp = ntohs(inet->inet_dport); + srcp = ntohs(inet->inet_sport); if (icsk->icsk_pending == ICSK_TIME_RETRANS) { timer_active = 1; diff --git a/net/ipv6/udp.c b/net/ipv6/udp.c index 3a60f12b34e..d3b59d73f50 100644 --- a/net/ipv6/udp.c +++ b/net/ipv6/udp.c @@ -53,7 +53,7 @@ int ipv6_rcv_saddr_equal(const struct sock *sk, const struct sock *sk2) { const struct in6_addr *sk_rcv_saddr6 = &inet6_sk(sk)->rcv_saddr; const struct in6_addr *sk2_rcv_saddr6 = inet6_rcv_saddr(sk2); - __be32 sk_rcv_saddr = inet_sk(sk)->rcv_saddr; + __be32 sk1_rcv_saddr = inet_sk(sk)->inet_rcv_saddr; __be32 sk2_rcv_saddr = inet_rcv_saddr(sk2); int sk_ipv6only = ipv6_only_sock(sk); int sk2_ipv6only = inet_v6_ipv6only(sk2); @@ -63,8 +63,8 @@ int ipv6_rcv_saddr_equal(const struct sock *sk, const struct sock *sk2) /* if both are mapped, treat as IPv4 */ if (addr_type == IPV6_ADDR_MAPPED && addr_type2 == IPV6_ADDR_MAPPED) return (!sk2_ipv6only && - (!sk_rcv_saddr || !sk2_rcv_saddr || - sk_rcv_saddr == sk2_rcv_saddr)); + (!sk1_rcv_saddr || !sk2_rcv_saddr || + sk1_rcv_saddr == sk2_rcv_saddr)); if (addr_type2 == IPV6_ADDR_ANY && !(sk2_ipv6only && addr_type == IPV6_ADDR_MAPPED)) @@ -100,8 +100,8 @@ static inline int compute_score(struct sock *sk, struct net *net, struct inet_sock *inet = inet_sk(sk); score = 0; - if (inet->dport) { - if (inet->dport != sport) + if (inet->inet_dport) { + if (inet->inet_dport != sport) return -1; score++; } @@ -132,7 +132,7 @@ static struct sock *__udp6_lib_lookup(struct net *net, struct sock *sk, *result; struct hlist_nulls_node *node; unsigned short hnum = ntohs(dport); - unsigned int hash = udp_hashfn(net, hnum); + unsigned int hash = udp_hashfn(net, hnum, udptable->mask); struct udp_hslot *hslot = &udptable->hash[hash]; int score, badness; @@ -252,7 +252,7 @@ try_again: UDP_MIB_INDATAGRAMS, is_udplite); } - sock_recv_timestamp(msg, sk, skb); + sock_recv_ts_and_drops(msg, sk, skb); /* Copy the address. */ if (msg->msg_name) { @@ -265,8 +265,8 @@ try_again: sin6->sin6_scope_id = 0; if (is_udp4) - ipv6_addr_set(&sin6->sin6_addr, 0, 0, - htonl(0xffff), ip_hdr(skb)->saddr); + ipv6_addr_set_v4mapped(ip_hdr(skb)->saddr, + &sin6->sin6_addr); else { ipv6_addr_copy(&sin6->sin6_addr, &ipv6_hdr(skb)->saddr); @@ -385,18 +385,18 @@ int udpv6_queue_rcv_skb(struct sock * sk, struct sk_buff *skb) goto drop; } - if ((rc = sock_queue_rcv_skb(sk,skb)) < 0) { + if ((rc = sock_queue_rcv_skb(sk, skb)) < 0) { /* Note that an ENOMEM error is charged twice */ - if (rc == -ENOMEM) { + if (rc == -ENOMEM) UDP6_INC_STATS_BH(sock_net(sk), UDP_MIB_RCVBUFERRORS, is_udplite); - atomic_inc(&sk->sk_drops); - } - goto drop; + goto drop_no_sk_drops_inc; } return 0; drop: + atomic_inc(&sk->sk_drops); +drop_no_sk_drops_inc: UDP6_INC_STATS_BH(sock_net(sk), UDP_MIB_INERRORS, is_udplite); kfree_skb(skb); return -1; @@ -419,8 +419,8 @@ static struct sock *udp_v6_mcast_next(struct net *net, struct sock *sk, if (s->sk_hash == num && s->sk_family == PF_INET6) { struct ipv6_pinfo *np = inet6_sk(s); - if (inet->dport) { - if (inet->dport != rmt_port) + if (inet->inet_dport) { + if (inet->inet_dport != rmt_port) continue; } if (!ipv6_addr_any(&np->daddr) && @@ -452,7 +452,7 @@ static int __udp6_lib_mcast_deliver(struct net *net, struct sk_buff *skb, { struct sock *sk, *sk2; const struct udphdr *uh = udp_hdr(skb); - struct udp_hslot *hslot = &udptable->hash[udp_hashfn(net, ntohs(uh->dest))]; + struct udp_hslot *hslot = udp_hashslot(udptable, net, ntohs(uh->dest)); int dif; spin_lock(&hslot->lock); @@ -794,7 +794,7 @@ int udpv6_sendmsg(struct kiocb *iocb, struct sock *sk, if (ipv6_addr_v4mapped(daddr)) { struct sockaddr_in sin; sin.sin_family = AF_INET; - sin.sin_port = sin6 ? sin6->sin6_port : inet->dport; + sin.sin_port = sin6 ? sin6->sin6_port : inet->inet_dport; sin.sin_addr.s_addr = daddr->s6_addr32[3]; msg->msg_name = &sin; msg->msg_namelen = sizeof(sin); @@ -867,7 +867,7 @@ do_udp_sendmsg: if (sk->sk_state != TCP_ESTABLISHED) return -EDESTADDRREQ; - fl.fl_ip_dport = inet->dport; + fl.fl_ip_dport = inet->inet_dport; daddr = &np->daddr; fl.fl6_flowlabel = np->flow_label; connected = 1; @@ -879,6 +879,8 @@ do_udp_sendmsg: if (!fl.oif) fl.oif = np->sticky_pktinfo.ipi6_ifindex; + fl.mark = sk->sk_mark; + if (msg->msg_controllen) { opt = &opt_space; memset(opt, 0, sizeof(struct ipv6_txoptions)); @@ -911,7 +913,7 @@ do_udp_sendmsg: fl.fl6_dst.s6_addr[15] = 0x1; /* :: means loopback (BSD'ism) */ if (ipv6_addr_any(&fl.fl6_src) && !ipv6_addr_any(&np->saddr)) ipv6_addr_copy(&fl.fl6_src, &np->saddr); - fl.fl_ip_sport = inet->sport; + fl.fl_ip_sport = inet->inet_sport; /* merge ip6_build_xmit from ip6_output */ if (opt && opt->srcrt) { @@ -1192,10 +1194,10 @@ static void udp6_sock_seq_show(struct seq_file *seq, struct sock *sp, int bucket dest = &np->daddr; src = &np->rcv_saddr; - destp = ntohs(inet->dport); - srcp = ntohs(inet->sport); + destp = ntohs(inet->inet_dport); + srcp = ntohs(inet->inet_sport); seq_printf(seq, - "%4d: %08X%08X%08X%08X:%04X %08X%08X%08X%08X:%04X " + "%5d: %08X%08X%08X%08X:%04X %08X%08X%08X%08X:%04X " "%02X %08X:%08X %02X:%08lX %08X %5d %8d %lu %d %p %d\n", bucket, src->s6_addr32[0], src->s6_addr32[1], diff --git a/net/ipv6/xfrm6_tunnel.c b/net/ipv6/xfrm6_tunnel.c index 81a95c00e50..438831d3359 100644 --- a/net/ipv6/xfrm6_tunnel.c +++ b/net/ipv6/xfrm6_tunnel.c @@ -23,7 +23,7 @@ */ #include <linux/module.h> #include <linux/xfrm.h> -#include <linux/list.h> +#include <linux/rculist.h> #include <net/ip.h> #include <net/xfrm.h> #include <net/ipv6.h> @@ -36,14 +36,15 @@ * per xfrm_address_t. */ struct xfrm6_tunnel_spi { - struct hlist_node list_byaddr; - struct hlist_node list_byspi; - xfrm_address_t addr; - u32 spi; - atomic_t refcnt; + struct hlist_node list_byaddr; + struct hlist_node list_byspi; + xfrm_address_t addr; + u32 spi; + atomic_t refcnt; + struct rcu_head rcu_head; }; -static DEFINE_RWLOCK(xfrm6_tunnel_spi_lock); +static DEFINE_SPINLOCK(xfrm6_tunnel_spi_lock); static u32 xfrm6_tunnel_spi; @@ -107,6 +108,7 @@ static void xfrm6_tunnel_spi_fini(void) if (!hlist_empty(&xfrm6_tunnel_spi_byspi[i])) return; } + rcu_barrier(); kmem_cache_destroy(xfrm6_tunnel_spi_kmem); xfrm6_tunnel_spi_kmem = NULL; } @@ -116,7 +118,7 @@ static struct xfrm6_tunnel_spi *__xfrm6_tunnel_spi_lookup(xfrm_address_t *saddr) struct xfrm6_tunnel_spi *x6spi; struct hlist_node *pos; - hlist_for_each_entry(x6spi, pos, + hlist_for_each_entry_rcu(x6spi, pos, &xfrm6_tunnel_spi_byaddr[xfrm6_tunnel_spi_hash_byaddr(saddr)], list_byaddr) { if (memcmp(&x6spi->addr, saddr, sizeof(x6spi->addr)) == 0) @@ -131,10 +133,10 @@ __be32 xfrm6_tunnel_spi_lookup(xfrm_address_t *saddr) struct xfrm6_tunnel_spi *x6spi; u32 spi; - read_lock_bh(&xfrm6_tunnel_spi_lock); + rcu_read_lock_bh(); x6spi = __xfrm6_tunnel_spi_lookup(saddr); spi = x6spi ? x6spi->spi : 0; - read_unlock_bh(&xfrm6_tunnel_spi_lock); + rcu_read_unlock_bh(); return htonl(spi); } @@ -185,14 +187,15 @@ alloc_spi: if (!x6spi) goto out; + INIT_RCU_HEAD(&x6spi->rcu_head); memcpy(&x6spi->addr, saddr, sizeof(x6spi->addr)); x6spi->spi = spi; atomic_set(&x6spi->refcnt, 1); - hlist_add_head(&x6spi->list_byspi, &xfrm6_tunnel_spi_byspi[index]); + hlist_add_head_rcu(&x6spi->list_byspi, &xfrm6_tunnel_spi_byspi[index]); index = xfrm6_tunnel_spi_hash_byaddr(saddr); - hlist_add_head(&x6spi->list_byaddr, &xfrm6_tunnel_spi_byaddr[index]); + hlist_add_head_rcu(&x6spi->list_byaddr, &xfrm6_tunnel_spi_byaddr[index]); out: return spi; } @@ -202,26 +205,32 @@ __be32 xfrm6_tunnel_alloc_spi(xfrm_address_t *saddr) struct xfrm6_tunnel_spi *x6spi; u32 spi; - write_lock_bh(&xfrm6_tunnel_spi_lock); + spin_lock_bh(&xfrm6_tunnel_spi_lock); x6spi = __xfrm6_tunnel_spi_lookup(saddr); if (x6spi) { atomic_inc(&x6spi->refcnt); spi = x6spi->spi; } else spi = __xfrm6_tunnel_alloc_spi(saddr); - write_unlock_bh(&xfrm6_tunnel_spi_lock); + spin_unlock_bh(&xfrm6_tunnel_spi_lock); return htonl(spi); } EXPORT_SYMBOL(xfrm6_tunnel_alloc_spi); +static void x6spi_destroy_rcu(struct rcu_head *head) +{ + kmem_cache_free(xfrm6_tunnel_spi_kmem, + container_of(head, struct xfrm6_tunnel_spi, rcu_head)); +} + void xfrm6_tunnel_free_spi(xfrm_address_t *saddr) { struct xfrm6_tunnel_spi *x6spi; struct hlist_node *pos, *n; - write_lock_bh(&xfrm6_tunnel_spi_lock); + spin_lock_bh(&xfrm6_tunnel_spi_lock); hlist_for_each_entry_safe(x6spi, pos, n, &xfrm6_tunnel_spi_byaddr[xfrm6_tunnel_spi_hash_byaddr(saddr)], @@ -229,14 +238,14 @@ void xfrm6_tunnel_free_spi(xfrm_address_t *saddr) { if (memcmp(&x6spi->addr, saddr, sizeof(x6spi->addr)) == 0) { if (atomic_dec_and_test(&x6spi->refcnt)) { - hlist_del(&x6spi->list_byaddr); - hlist_del(&x6spi->list_byspi); - kmem_cache_free(xfrm6_tunnel_spi_kmem, x6spi); + hlist_del_rcu(&x6spi->list_byaddr); + hlist_del_rcu(&x6spi->list_byspi); + call_rcu(&x6spi->rcu_head, x6spi_destroy_rcu); break; } } } - write_unlock_bh(&xfrm6_tunnel_spi_lock); + spin_unlock_bh(&xfrm6_tunnel_spi_lock); } EXPORT_SYMBOL(xfrm6_tunnel_free_spi); diff --git a/net/ipx/af_ipx.c b/net/ipx/af_ipx.c index 66c7a20011f..6481ee4bdf7 100644 --- a/net/ipx/af_ipx.c +++ b/net/ipx/af_ipx.c @@ -1927,7 +1927,7 @@ static int ipx_compat_ioctl(struct socket *sock, unsigned int cmd, unsigned long * Socket family declarations */ -static struct net_proto_family ipx_family_ops = { +static const struct net_proto_family ipx_family_ops = { .family = PF_IPX, .create = ipx_create, .owner = THIS_MODULE, diff --git a/net/irda/af_irda.c b/net/irda/af_irda.c index dd35641835f..9429e4002bc 100644 --- a/net/irda/af_irda.c +++ b/net/irda/af_irda.c @@ -2463,7 +2463,7 @@ bed: return 0; } -static struct net_proto_family irda_family_ops = { +static const struct net_proto_family irda_family_ops = { .family = PF_IRDA, .create = irda_create, .owner = THIS_MODULE, diff --git a/net/iucv/af_iucv.c b/net/iucv/af_iucv.c index bada1b9c670..3aebabb158a 100644 --- a/net/iucv/af_iucv.c +++ b/net/iucv/af_iucv.c @@ -428,7 +428,6 @@ static void iucv_sock_close(struct sock *sk) break; default: - sock_set_flag(sk, SOCK_ZAPPED); /* nothing to do here */ break; } @@ -536,7 +535,7 @@ void iucv_accept_enqueue(struct sock *parent, struct sock *sk) list_add_tail(&iucv_sk(sk)->accept_q, &par->accept_q); spin_unlock_irqrestore(&par->accept_q_lock, flags); iucv_sk(sk)->parent = parent; - parent->sk_ack_backlog++; + sk_acceptq_added(parent); } void iucv_accept_unlink(struct sock *sk) @@ -547,7 +546,7 @@ void iucv_accept_unlink(struct sock *sk) spin_lock_irqsave(&par->accept_q_lock, flags); list_del_init(&iucv_sk(sk)->accept_q); spin_unlock_irqrestore(&par->accept_q_lock, flags); - iucv_sk(sk)->parent->sk_ack_backlog--; + sk_acceptq_removed(iucv_sk(sk)->parent); iucv_sk(sk)->parent = NULL; sock_put(sk); } @@ -1715,7 +1714,7 @@ static const struct proto_ops iucv_sock_ops = { .getsockopt = iucv_sock_getsockopt, }; -static struct net_proto_family iucv_sock_family_ops = { +static const struct net_proto_family iucv_sock_family_ops = { .family = AF_IUCV, .owner = THIS_MODULE, .create = iucv_sock_create, diff --git a/net/key/af_key.c b/net/key/af_key.c index 4e98193dfa0..472f6594184 100644 --- a/net/key/af_key.c +++ b/net/key/af_key.c @@ -3606,7 +3606,7 @@ static int pfkey_recvmsg(struct kiocb *kiocb, if (err) goto out_free; - sock_recv_timestamp(msg, sk, skb); + sock_recv_ts_and_drops(msg, sk, skb); err = (flags & MSG_TRUNC) ? skb->len : copied; @@ -3644,7 +3644,7 @@ static const struct proto_ops pfkey_ops = { .recvmsg = pfkey_recvmsg, }; -static struct net_proto_family pfkey_family_ops = { +static const struct net_proto_family pfkey_family_ops = { .family = PF_KEY, .create = pfkey_create, .owner = THIS_MODULE, diff --git a/net/llc/af_llc.c b/net/llc/af_llc.c index 7aa4fd17010..4866b4fb0c2 100644 --- a/net/llc/af_llc.c +++ b/net/llc/af_llc.c @@ -1092,7 +1092,7 @@ out: return rc; } -static struct net_proto_family llc_ui_family_ops = { +static const struct net_proto_family llc_ui_family_ops = { .family = PF_LLC, .create = llc_ui_create, .owner = THIS_MODULE, diff --git a/net/mac80211/iface.c b/net/mac80211/iface.c index b8295cbd7e8..14f10eb91c5 100644 --- a/net/mac80211/iface.c +++ b/net/mac80211/iface.c @@ -184,10 +184,12 @@ static int ieee80211_open(struct net_device *dev) * No need to check netif_running since we do not allow * it to start up with this invalid address. */ - if (compare_ether_addr(null_addr, ndev->dev_addr) == 0) + if (compare_ether_addr(null_addr, ndev->dev_addr) == 0) { memcpy(ndev->dev_addr, local->hw.wiphy->perm_addr, ETH_ALEN); + memcpy(ndev->perm_addr, ndev->dev_addr, ETH_ALEN); + } } /* @@ -312,7 +314,7 @@ static int ieee80211_open(struct net_device *dev) if (sdata->vif.type == NL80211_IFTYPE_STATION) ieee80211_queue_work(&local->hw, &sdata->u.mgd.work); - netif_tx_start_all_queues(dev); + netif_start_queue(dev); return 0; err_del_interface: @@ -341,7 +343,7 @@ static int ieee80211_stop(struct net_device *dev) /* * Stop TX on this interface first. */ - netif_tx_stop_all_queues(dev); + netif_stop_queue(dev); /* * Now delete all active aggregation sessions. @@ -754,10 +756,6 @@ int ieee80211_if_change_type(struct ieee80211_sub_if_data *sdata, return 0; } -static struct device_type wiphy_type = { - .name = "wlan", -}; - int ieee80211_if_add(struct ieee80211_local *local, const char *name, struct net_device **new_dev, enum nl80211_iftype type, struct vif_params *params) @@ -788,8 +786,8 @@ int ieee80211_if_add(struct ieee80211_local *local, const char *name, goto fail; memcpy(ndev->dev_addr, local->hw.wiphy->perm_addr, ETH_ALEN); + memcpy(ndev->perm_addr, ndev->dev_addr, ETH_ALEN); SET_NETDEV_DEV(ndev, wiphy_dev(local->hw.wiphy)); - SET_NETDEV_DEVTYPE(ndev, &wiphy_type); /* don't use IEEE80211_DEV_TO_SUB_IF because it checks too much */ sdata = netdev_priv(ndev); diff --git a/net/mac80211/mesh.c b/net/mac80211/mesh.c index f7364e56f1e..9a733890eb4 100644 --- a/net/mac80211/mesh.c +++ b/net/mac80211/mesh.c @@ -50,7 +50,7 @@ static void ieee80211_mesh_housekeeping_timer(unsigned long data) struct ieee80211_local *local = sdata->local; struct ieee80211_if_mesh *ifmsh = &sdata->u.mesh; - ifmsh->wrkq_flags |= MESH_WORK_HOUSEKEEPING; + set_bit(MESH_WORK_HOUSEKEEPING, &ifmsh->wrkq_flags); if (local->quiescing) { set_bit(TMR_RUNNING_HK, &ifmsh->timers_running); @@ -480,7 +480,7 @@ void ieee80211_start_mesh(struct ieee80211_sub_if_data *sdata) struct ieee80211_if_mesh *ifmsh = &sdata->u.mesh; struct ieee80211_local *local = sdata->local; - ifmsh->wrkq_flags |= MESH_WORK_HOUSEKEEPING; + set_bit(MESH_WORK_HOUSEKEEPING, &ifmsh->wrkq_flags); ieee80211_queue_work(&local->hw, &ifmsh->work); sdata->vif.bss_conf.beacon_int = MESH_DEFAULT_BEACON_INTERVAL; ieee80211_bss_info_change_notify(sdata, BSS_CHANGED_BEACON | diff --git a/net/mac80211/mlme.c b/net/mac80211/mlme.c index dc5049d58c5..dcc14e99227 100644 --- a/net/mac80211/mlme.c +++ b/net/mac80211/mlme.c @@ -458,9 +458,15 @@ static void ieee80211_send_deauth_disassoc(struct ieee80211_sub_if_data *sdata, mgmt->u.deauth.reason_code = cpu_to_le16(reason); if (stype == IEEE80211_STYPE_DEAUTH) - cfg80211_send_deauth(sdata->dev, (u8 *)mgmt, skb->len, cookie); + if (cookie) + __cfg80211_send_deauth(sdata->dev, (u8 *)mgmt, skb->len); + else + cfg80211_send_deauth(sdata->dev, (u8 *)mgmt, skb->len); else - cfg80211_send_disassoc(sdata->dev, (u8 *)mgmt, skb->len, cookie); + if (cookie) + __cfg80211_send_disassoc(sdata->dev, (u8 *)mgmt, skb->len); + else + cfg80211_send_disassoc(sdata->dev, (u8 *)mgmt, skb->len); ieee80211_tx_skb(sdata, skb, ifmgd->flags & IEEE80211_STA_MFP_ENABLED); } @@ -923,7 +929,7 @@ static void ieee80211_set_associated(struct ieee80211_sub_if_data *sdata, ieee80211_recalc_ps(local, -1); mutex_unlock(&local->iflist_mtx); - netif_tx_start_all_queues(sdata->dev); + netif_start_queue(sdata->dev); netif_carrier_on(sdata->dev); } @@ -1055,7 +1061,7 @@ static void ieee80211_set_disassoc(struct ieee80211_sub_if_data *sdata, * time -- we don't want the scan code to enable queues. */ - netif_tx_stop_all_queues(sdata->dev); + netif_stop_queue(sdata->dev); netif_carrier_off(sdata->dev); rcu_read_lock(); @@ -1958,12 +1964,10 @@ static void ieee80211_sta_rx_queued_mgmt(struct ieee80211_sub_if_data *sdata, /* no action */ break; case RX_MGMT_CFG80211_DEAUTH: - cfg80211_send_deauth(sdata->dev, (u8 *)mgmt, skb->len, - NULL); + cfg80211_send_deauth(sdata->dev, (u8 *)mgmt, skb->len); break; case RX_MGMT_CFG80211_DISASSOC: - cfg80211_send_disassoc(sdata->dev, (u8 *)mgmt, skb->len, - NULL); + cfg80211_send_disassoc(sdata->dev, (u8 *)mgmt, skb->len); break; default: WARN(1, "unexpected: %d", rma); @@ -2018,7 +2022,7 @@ static void ieee80211_sta_rx_queued_mgmt(struct ieee80211_sub_if_data *sdata, cfg80211_send_rx_assoc(sdata->dev, (u8 *) mgmt, skb->len); break; case RX_MGMT_CFG80211_DEAUTH: - cfg80211_send_deauth(sdata->dev, (u8 *)mgmt, skb->len, NULL); + cfg80211_send_deauth(sdata->dev, (u8 *)mgmt, skb->len); break; default: WARN(1, "unexpected: %d", rma); diff --git a/net/mac80211/rx.c b/net/mac80211/rx.c index 7170bf4565a..5c385e3c1d1 100644 --- a/net/mac80211/rx.c +++ b/net/mac80211/rx.c @@ -1504,19 +1504,28 @@ ieee80211_rx_h_mesh_fwding(struct ieee80211_rx_data *rx) /* illegal frame */ return RX_DROP_MONITOR; - if (!is_multicast_ether_addr(hdr->addr1) && - (mesh_hdr->flags & MESH_FLAGS_AE_A5_A6)) { + if (mesh_hdr->flags & MESH_FLAGS_AE) { struct mesh_path *mppath; + char *proxied_addr; + char *mpp_addr; + + if (is_multicast_ether_addr(hdr->addr1)) { + mpp_addr = hdr->addr3; + proxied_addr = mesh_hdr->eaddr1; + } else { + mpp_addr = hdr->addr4; + proxied_addr = mesh_hdr->eaddr2; + } rcu_read_lock(); - mppath = mpp_path_lookup(mesh_hdr->eaddr2, sdata); + mppath = mpp_path_lookup(proxied_addr, sdata); if (!mppath) { - mpp_path_add(mesh_hdr->eaddr2, hdr->addr4, sdata); + mpp_path_add(proxied_addr, mpp_addr, sdata); } else { spin_lock_bh(&mppath->state_lock); mppath->exp_time = jiffies; - if (compare_ether_addr(mppath->mpp, hdr->addr4) != 0) - memcpy(mppath->mpp, hdr->addr4, ETH_ALEN); + if (compare_ether_addr(mppath->mpp, mpp_addr) != 0) + memcpy(mppath->mpp, mpp_addr, ETH_ALEN); spin_unlock_bh(&mppath->state_lock); } rcu_read_unlock(); diff --git a/net/mac80211/scan.c b/net/mac80211/scan.c index 71e10cabf81..7a350d2690a 100644 --- a/net/mac80211/scan.c +++ b/net/mac80211/scan.c @@ -306,10 +306,10 @@ void ieee80211_scan_completed(struct ieee80211_hw *hw, bool aborted) if (sdata->vif.type == NL80211_IFTYPE_STATION) { if (sdata->u.mgd.associated) { ieee80211_scan_ps_disable(sdata); - netif_tx_wake_all_queues(sdata->dev); + netif_wake_queue(sdata->dev); } } else - netif_tx_wake_all_queues(sdata->dev); + netif_wake_queue(sdata->dev); /* re-enable beaconing */ if (sdata->vif.type == NL80211_IFTYPE_AP || @@ -364,7 +364,7 @@ static int ieee80211_start_sw_scan(struct ieee80211_local *local) * are handled in the scan state machine */ if (sdata->vif.type != NL80211_IFTYPE_STATION) - netif_tx_stop_all_queues(sdata->dev); + netif_stop_queue(sdata->dev); } mutex_unlock(&local->iflist_mtx); @@ -523,7 +523,7 @@ static void ieee80211_scan_state_leave_oper_channel(struct ieee80211_local *loca continue; if (sdata->vif.type == NL80211_IFTYPE_STATION) { - netif_tx_stop_all_queues(sdata->dev); + netif_stop_queue(sdata->dev); if (sdata->u.mgd.associated) ieee80211_scan_ps_enable(sdata); } @@ -558,7 +558,7 @@ static void ieee80211_scan_state_enter_oper_channel(struct ieee80211_local *loca if (sdata->vif.type == NL80211_IFTYPE_STATION) { if (sdata->u.mgd.associated) ieee80211_scan_ps_disable(sdata); - netif_tx_wake_all_queues(sdata->dev); + netif_wake_queue(sdata->dev); } } mutex_unlock(&local->iflist_mtx); diff --git a/net/netfilter/xt_socket.c b/net/netfilter/xt_socket.c index ebf00ad5b19..362afbd60a9 100644 --- a/net/netfilter/xt_socket.c +++ b/net/netfilter/xt_socket.c @@ -149,7 +149,7 @@ socket_match(const struct sk_buff *skb, const struct xt_match_param *par, /* Ignore sockets listening on INADDR_ANY */ wildcard = (sk->sk_state != TCP_TIME_WAIT && - inet_sk(sk)->rcv_saddr == 0); + inet_sk(sk)->inet_rcv_saddr == 0); /* Ignore non-transparent sockets, if XT_SOCKET_TRANSPARENT is used */ diff --git a/net/netlink/af_netlink.c b/net/netlink/af_netlink.c index 19e98007691..0cd2d882931 100644 --- a/net/netlink/af_netlink.c +++ b/net/netlink/af_netlink.c @@ -2050,7 +2050,7 @@ static const struct proto_ops netlink_ops = { .sendpage = sock_no_sendpage, }; -static struct net_proto_family netlink_family_ops = { +static const struct net_proto_family netlink_family_ops = { .family = PF_NETLINK, .create = netlink_create, .owner = THIS_MODULE, /* for consistency 8) */ diff --git a/net/netlink/genetlink.c b/net/netlink/genetlink.c index 44ff3f3810f..d07ecda0a92 100644 --- a/net/netlink/genetlink.c +++ b/net/netlink/genetlink.c @@ -97,25 +97,17 @@ static struct genl_ops *genl_get_cmd(u8 cmd, struct genl_family *family) */ static inline u16 genl_generate_id(void) { - static u16 id_gen_idx; - int overflowed = 0; + static u16 id_gen_idx = GENL_MIN_ID; + int i; - do { - if (id_gen_idx == 0) + for (i = 0; i <= GENL_MAX_ID - GENL_MIN_ID; i++) { + if (!genl_family_find_byid(id_gen_idx)) + return id_gen_idx; + if (++id_gen_idx > GENL_MAX_ID) id_gen_idx = GENL_MIN_ID; + } - if (++id_gen_idx > GENL_MAX_ID) { - if (!overflowed) { - overflowed = 1; - id_gen_idx = 0; - continue; - } else - return 0; - } - - } while (genl_family_find_byid(id_gen_idx)); - - return id_gen_idx; + return 0; } static struct genl_multicast_group notify_grp; @@ -374,11 +366,6 @@ int genl_register_family(struct genl_family *family) goto errout_locked; } - if (genl_family_find_byid(family->id)) { - err = -EEXIST; - goto errout_locked; - } - if (family->id == GENL_ID_GENERATE) { u16 newid = genl_generate_id(); @@ -388,6 +375,9 @@ int genl_register_family(struct genl_family *family) } family->id = newid; + } else if (genl_family_find_byid(family->id)) { + err = -EEXIST; + goto errout_locked; } if (family->maxattr) { diff --git a/net/netrom/af_netrom.c b/net/netrom/af_netrom.c index 7a834952f67..281fa597cae 100644 --- a/net/netrom/af_netrom.c +++ b/net/netrom/af_netrom.c @@ -1372,7 +1372,7 @@ static const struct file_operations nr_info_fops = { }; #endif /* CONFIG_PROC_FS */ -static struct net_proto_family nr_family_ops = { +static const struct net_proto_family nr_family_ops = { .family = PF_NETROM, .create = nr_create, .owner = THIS_MODULE, diff --git a/net/packet/af_packet.c b/net/packet/af_packet.c index 48b18dad676..95ef64e4189 100644 --- a/net/packet/af_packet.c +++ b/net/packet/af_packet.c @@ -79,6 +79,7 @@ #include <linux/module.h> #include <linux/init.h> #include <linux/mutex.h> +#include <linux/if_vlan.h> #ifdef CONFIG_INET #include <net/inet_common.h> @@ -188,7 +189,6 @@ struct packet_sock { struct packet_ring_buffer tx_ring; int copy_thresh; #endif - struct packet_type prot_hook; spinlock_t bind_lock; struct mutex pg_vec_lock; unsigned int running:1, /* prot_hook is attached*/ @@ -204,6 +204,7 @@ struct packet_sock { unsigned int tp_reserve; unsigned int tp_loss:1; #endif + struct packet_type prot_hook ____cacheline_aligned_in_smp; }; struct packet_skb_cb { @@ -490,6 +491,7 @@ static int packet_sendmsg_spkt(struct kiocb *iocb, struct socket *sock, skb->protocol = proto; skb->dev = dev; skb->priority = sk->sk_priority; + skb->mark = sk->sk_mark; if (err) goto out_free; @@ -626,15 +628,14 @@ static int packet_rcv(struct sk_buff *skb, struct net_device *dev, spin_lock(&sk->sk_receive_queue.lock); po->stats.tp_packets++; + skb->dropcount = atomic_read(&sk->sk_drops); __skb_queue_tail(&sk->sk_receive_queue, skb); spin_unlock(&sk->sk_receive_queue.lock); sk->sk_data_ready(sk, skb->len); return 0; drop_n_acct: - spin_lock(&sk->sk_receive_queue.lock); - po->stats.tp_drops++; - spin_unlock(&sk->sk_receive_queue.lock); + po->stats.tp_drops = atomic_inc_return(&sk->sk_drops); drop_n_restore: if (skb_head != skb->data && skb_shared(skb)) { @@ -766,7 +767,7 @@ static int tpacket_rcv(struct sk_buff *skb, struct net_device *dev, getnstimeofday(&ts); h.h2->tp_sec = ts.tv_sec; h.h2->tp_nsec = ts.tv_nsec; - h.h2->tp_vlan_tci = skb->vlan_tci; + h.h2->tp_vlan_tci = vlan_tx_tag_get(skb); hdrlen = sizeof(*h.h2); break; default: @@ -856,6 +857,7 @@ static int tpacket_fill_skb(struct packet_sock *po, struct sk_buff *skb, skb->protocol = proto; skb->dev = dev; skb->priority = po->sk.sk_priority; + skb->mark = po->sk.sk_mark; skb_shinfo(skb)->destructor_arg = ph.raw; switch (po->tp_version) { @@ -1122,6 +1124,7 @@ static int packet_snd(struct socket *sock, skb->protocol = proto; skb->dev = dev; skb->priority = sk->sk_priority; + skb->mark = sk->sk_mark; /* * Now send it @@ -1472,7 +1475,7 @@ static int packet_recvmsg(struct kiocb *iocb, struct socket *sock, if (err) goto out_free; - sock_recv_timestamp(msg, sk, skb); + sock_recv_ts_and_drops(msg, sk, skb); if (msg->msg_name) memcpy(msg->msg_name, &PACKET_SKB_CB(skb)->sa, @@ -1488,7 +1491,7 @@ static int packet_recvmsg(struct kiocb *iocb, struct socket *sock, aux.tp_snaplen = skb->len; aux.tp_mac = 0; aux.tp_net = skb_network_offset(skb); - aux.tp_vlan_tci = skb->vlan_tci; + aux.tp_vlan_tci = vlan_tx_tag_get(skb); put_cmsg(msg, SOL_PACKET, PACKET_AUXDATA, sizeof(aux), &aux); } @@ -1659,11 +1662,9 @@ static int packet_mc_drop(struct sock *sk, struct packet_mreq_max *mreq) if (--ml->count == 0) { struct net_device *dev; *mlp = ml->next; - dev = dev_get_by_index(sock_net(sk), ml->ifindex); - if (dev) { + dev = __dev_get_by_index(sock_net(sk), ml->ifindex); + if (dev) packet_dev_mc(dev, ml, -1); - dev_put(dev); - } kfree(ml); } rtnl_unlock(); @@ -1687,11 +1688,9 @@ static void packet_flush_mclist(struct sock *sk) struct net_device *dev; po->mclist = ml->next; - dev = dev_get_by_index(sock_net(sk), ml->ifindex); - if (dev != NULL) { + dev = __dev_get_by_index(sock_net(sk), ml->ifindex); + if (dev != NULL) packet_dev_mc(dev, ml, -1); - dev_put(dev); - } kfree(ml); } rtnl_unlock(); @@ -2081,7 +2080,7 @@ static void packet_mm_close(struct vm_area_struct *vma) atomic_dec(&pkt_sk(sk)->mapped); } -static struct vm_operations_struct packet_mmap_ops = { +static const struct vm_operations_struct packet_mmap_ops = { .open = packet_mm_open, .close = packet_mm_close, }; @@ -2360,7 +2359,7 @@ static const struct proto_ops packet_ops = { .sendpage = sock_no_sendpage, }; -static struct net_proto_family packet_family_ops = { +static const struct net_proto_family packet_family_ops = { .family = PF_PACKET, .create = packet_create, .owner = THIS_MODULE, diff --git a/net/phonet/af_phonet.c b/net/phonet/af_phonet.c index f60c0c2aacb..66737aa995e 100644 --- a/net/phonet/af_phonet.c +++ b/net/phonet/af_phonet.c @@ -118,7 +118,7 @@ out: return err; } -static struct net_proto_family phonet_proto_family = { +static const struct net_proto_family phonet_proto_family = { .family = PF_PHONET, .create = pn_socket_create, .owner = THIS_MODULE, @@ -190,9 +190,8 @@ static int pn_send(struct sk_buff *skb, struct net_device *dev, skb->priority = 0; skb->dev = dev; - if (pn_addr(src) == pn_addr(dst)) { + if (skb->pkt_type == PACKET_LOOPBACK) { skb_reset_mac_header(skb); - skb->pkt_type = PACKET_LOOPBACK; skb_orphan(skb); if (irq) netif_rx(skb); @@ -222,6 +221,9 @@ static int pn_raw_send(const void *data, int len, struct net_device *dev, if (skb == NULL) return -ENOMEM; + if (phonet_address_lookup(dev_net(dev), pn_addr(dst)) == 0) + skb->pkt_type = PACKET_LOOPBACK; + skb_reserve(skb, MAX_PHONET_HEADER); __skb_put(skb, len); skb_copy_to_linear_data(skb, data, len); @@ -235,6 +237,7 @@ static int pn_raw_send(const void *data, int len, struct net_device *dev, int pn_skb_send(struct sock *sk, struct sk_buff *skb, const struct sockaddr_pn *target) { + struct net *net = sock_net(sk); struct net_device *dev; struct pn_sock *pn = pn_sk(sk); int err; @@ -243,9 +246,13 @@ int pn_skb_send(struct sock *sk, struct sk_buff *skb, err = -EHOSTUNREACH; if (sk->sk_bound_dev_if) - dev = dev_get_by_index(sock_net(sk), sk->sk_bound_dev_if); - else - dev = phonet_device_get(sock_net(sk)); + dev = dev_get_by_index(net, sk->sk_bound_dev_if); + else if (phonet_address_lookup(net, daddr) == 0) { + dev = phonet_device_get(net); + skb->pkt_type = PACKET_LOOPBACK; + } else + dev = phonet_route_output(net, daddr); + if (!dev || !(dev->flags & IFF_UP)) goto drop; @@ -369,6 +376,12 @@ static int phonet_rcv(struct sk_buff *skb, struct net_device *dev, pn_skb_get_dst_sockaddr(skb, &sa); + /* check if this is broadcasted */ + if (pn_sockaddr_get_addr(&sa) == PNADDR_BROADCAST) { + pn_deliver_sock_broadcast(net, skb); + goto out; + } + /* check if we are the destination */ if (phonet_address_lookup(net, pn_sockaddr_get_addr(&sa)) == 0) { /* Phonet packet input */ @@ -381,6 +394,38 @@ static int phonet_rcv(struct sk_buff *skb, struct net_device *dev, send_obj_unreachable(skb); send_reset_indications(skb); } + } else if (unlikely(skb->pkt_type == PACKET_LOOPBACK)) + goto out; /* Race between address deletion and loopback */ + else { + /* Phonet packet routing */ + struct net_device *out_dev; + + out_dev = phonet_route_output(net, pn_sockaddr_get_addr(&sa)); + if (!out_dev) { + LIMIT_NETDEBUG(KERN_WARNING"No Phonet route to %02X\n", + pn_sockaddr_get_addr(&sa)); + goto out; + } + + __skb_push(skb, sizeof(struct phonethdr)); + skb->dev = out_dev; + if (out_dev == dev) { + LIMIT_NETDEBUG(KERN_ERR"Phonet loop to %02X on %s\n", + pn_sockaddr_get_addr(&sa), dev->name); + goto out_dev; + } + /* Some drivers (e.g. TUN) do not allocate HW header space */ + if (skb_cow_head(skb, out_dev->hard_header_len)) + goto out_dev; + + if (dev_hard_header(skb, out_dev, ETH_P_PHONET, NULL, NULL, + skb->len) < 0) + goto out_dev; + dev_queue_xmit(skb); + dev_put(out_dev); + return NET_RX_SUCCESS; +out_dev: + dev_put(out_dev); } out: diff --git a/net/phonet/datagram.c b/net/phonet/datagram.c index ef5c75c372e..67f072e94d0 100644 --- a/net/phonet/datagram.c +++ b/net/phonet/datagram.c @@ -159,11 +159,9 @@ out_nofree: static int pn_backlog_rcv(struct sock *sk, struct sk_buff *skb) { int err = sock_queue_rcv_skb(sk, skb); - if (err < 0) { + + if (err < 0) kfree_skb(skb); - if (err == -ENOMEM) - atomic_inc(&sk->sk_drops); - } return err ? NET_RX_DROP : NET_RX_SUCCESS; } diff --git a/net/phonet/pep.c b/net/phonet/pep.c index 5f32d217535..cbaa1d67d77 100644 --- a/net/phonet/pep.c +++ b/net/phonet/pep.c @@ -360,8 +360,6 @@ static int pipe_do_rcv(struct sock *sk, struct sk_buff *skb) err = sock_queue_rcv_skb(sk, skb); if (!err) return 0; - if (err == -ENOMEM) - atomic_inc(&sk->sk_drops); break; } diff --git a/net/phonet/pn_dev.c b/net/phonet/pn_dev.c index 5f42f30dd16..6d64fda1afc 100644 --- a/net/phonet/pn_dev.c +++ b/net/phonet/pn_dev.c @@ -33,8 +33,14 @@ #include <net/netns/generic.h> #include <net/phonet/pn_dev.h> +struct phonet_routes { + spinlock_t lock; + struct net_device *table[64]; +}; + struct phonet_net { struct phonet_device_list pndevs; + struct phonet_routes routes; }; int phonet_net_id; @@ -154,10 +160,11 @@ int phonet_address_del(struct net_device *dev, u8 addr) } /* Gets a source address toward a destination, through a interface. */ -u8 phonet_address_get(struct net_device *dev, u8 addr) +u8 phonet_address_get(struct net_device *dev, u8 daddr) { struct phonet_device_list *pndevs = phonet_device_list(dev_net(dev)); struct phonet_device *pnd; + u8 saddr; spin_lock_bh(&pndevs->lock); pnd = __phonet_get(dev); @@ -165,12 +172,26 @@ u8 phonet_address_get(struct net_device *dev, u8 addr) BUG_ON(bitmap_empty(pnd->addrs, 64)); /* Use same source address as destination, if possible */ - if (!test_bit(addr >> 2, pnd->addrs)) - addr = find_first_bit(pnd->addrs, 64) << 2; + if (test_bit(daddr >> 2, pnd->addrs)) + saddr = daddr; + else + saddr = find_first_bit(pnd->addrs, 64) << 2; } else - addr = PN_NO_ADDR; + saddr = PN_NO_ADDR; spin_unlock_bh(&pndevs->lock); - return addr; + + if (saddr == PN_NO_ADDR) { + /* Fallback to another device */ + struct net_device *def_dev; + + def_dev = phonet_device_get(dev_net(dev)); + if (def_dev) { + if (def_dev != dev) + saddr = phonet_address_get(def_dev, daddr); + dev_put(def_dev); + } + } + return saddr; } int phonet_address_lookup(struct net *net, u8 addr) @@ -219,6 +240,27 @@ static int phonet_device_autoconf(struct net_device *dev) return 0; } +static void phonet_route_autodel(struct net_device *dev) +{ + struct phonet_net *pnn = net_generic(dev_net(dev), phonet_net_id); + unsigned i; + DECLARE_BITMAP(deleted, 64); + + /* Remove left-over Phonet routes */ + bitmap_zero(deleted, 64); + spin_lock_bh(&pnn->routes.lock); + for (i = 0; i < 64; i++) + if (dev == pnn->routes.table[i]) { + set_bit(i, deleted); + pnn->routes.table[i] = NULL; + dev_put(dev); + } + spin_unlock_bh(&pnn->routes.lock); + for (i = find_first_bit(deleted, 64); i < 64; + i = find_next_bit(deleted, 64, i + 1)) + rtm_phonet_notify(RTM_DELROUTE, dev, i); +} + /* notify Phonet of device events */ static int phonet_device_notify(struct notifier_block *me, unsigned long what, void *arg) @@ -232,6 +274,7 @@ static int phonet_device_notify(struct notifier_block *me, unsigned long what, break; case NETDEV_UNREGISTER: phonet_device_destroy(dev); + phonet_route_autodel(dev); break; } return 0; @@ -246,7 +289,7 @@ static struct notifier_block phonet_device_notifier = { /* Per-namespace Phonet devices handling */ static int phonet_init_net(struct net *net) { - struct phonet_net *pnn = kmalloc(sizeof(*pnn), GFP_KERNEL); + struct phonet_net *pnn = kzalloc(sizeof(*pnn), GFP_KERNEL); if (!pnn) return -ENOMEM; @@ -257,6 +300,7 @@ static int phonet_init_net(struct net *net) INIT_LIST_HEAD(&pnn->pndevs.list); spin_lock_init(&pnn->pndevs.lock); + spin_lock_init(&pnn->routes.lock); net_assign_generic(net, phonet_net_id, pnn); return 0; } @@ -265,10 +309,19 @@ static void phonet_exit_net(struct net *net) { struct phonet_net *pnn = net_generic(net, phonet_net_id); struct net_device *dev; + unsigned i; rtnl_lock(); for_each_netdev(net, dev) phonet_device_destroy(dev); + + for (i = 0; i < 64; i++) { + dev = pnn->routes.table[i]; + if (dev) { + rtm_phonet_notify(RTM_DELROUTE, dev, i); + dev_put(dev); + } + } rtnl_unlock(); proc_net_remove(net, "phonet"); @@ -300,3 +353,69 @@ void phonet_device_exit(void) unregister_netdevice_notifier(&phonet_device_notifier); unregister_pernet_gen_device(phonet_net_id, &phonet_net_ops); } + +int phonet_route_add(struct net_device *dev, u8 daddr) +{ + struct phonet_net *pnn = net_generic(dev_net(dev), phonet_net_id); + struct phonet_routes *routes = &pnn->routes; + int err = -EEXIST; + + daddr = daddr >> 2; + spin_lock_bh(&routes->lock); + if (routes->table[daddr] == NULL) { + routes->table[daddr] = dev; + dev_hold(dev); + err = 0; + } + spin_unlock_bh(&routes->lock); + return err; +} + +int phonet_route_del(struct net_device *dev, u8 daddr) +{ + struct phonet_net *pnn = net_generic(dev_net(dev), phonet_net_id); + struct phonet_routes *routes = &pnn->routes; + int err = -ENOENT; + + daddr = daddr >> 2; + spin_lock_bh(&routes->lock); + if (dev == routes->table[daddr]) { + routes->table[daddr] = NULL; + dev_put(dev); + err = 0; + } + spin_unlock_bh(&routes->lock); + return err; +} + +struct net_device *phonet_route_get(struct net *net, u8 daddr) +{ + struct phonet_net *pnn = net_generic(net, phonet_net_id); + struct phonet_routes *routes = &pnn->routes; + struct net_device *dev; + + ASSERT_RTNL(); /* no need to hold the device */ + + daddr >>= 2; + spin_lock_bh(&routes->lock); + dev = routes->table[daddr]; + spin_unlock_bh(&routes->lock); + return dev; +} + +struct net_device *phonet_route_output(struct net *net, u8 daddr) +{ + struct phonet_net *pnn = net_generic(net, phonet_net_id); + struct phonet_routes *routes = &pnn->routes; + struct net_device *dev; + + spin_lock_bh(&routes->lock); + dev = routes->table[daddr >> 2]; + if (dev) + dev_hold(dev); + spin_unlock_bh(&routes->lock); + + if (!dev) + dev = phonet_device_get(net); /* Default route */ + return dev; +} diff --git a/net/phonet/pn_netlink.c b/net/phonet/pn_netlink.c index d21fd357661..d8f5d3fb9ee 100644 --- a/net/phonet/pn_netlink.c +++ b/net/phonet/pn_netlink.c @@ -29,6 +29,8 @@ #include <net/sock.h> #include <net/phonet/pn_dev.h> +/* Device address handling */ + static int fill_addr(struct sk_buff *skb, struct net_device *dev, u8 addr, u32 pid, u32 seq, int event); @@ -160,6 +162,131 @@ out: return skb->len; } +/* Routes handling */ + +static int fill_route(struct sk_buff *skb, struct net_device *dev, u8 dst, + u32 pid, u32 seq, int event) +{ + struct rtmsg *rtm; + struct nlmsghdr *nlh; + + nlh = nlmsg_put(skb, pid, seq, event, sizeof(*rtm), 0); + if (nlh == NULL) + return -EMSGSIZE; + + rtm = nlmsg_data(nlh); + rtm->rtm_family = AF_PHONET; + rtm->rtm_dst_len = 6; + rtm->rtm_src_len = 0; + rtm->rtm_tos = 0; + rtm->rtm_table = RT_TABLE_MAIN; + rtm->rtm_protocol = RTPROT_STATIC; + rtm->rtm_scope = RT_SCOPE_UNIVERSE; + rtm->rtm_type = RTN_UNICAST; + rtm->rtm_flags = 0; + NLA_PUT_U8(skb, RTA_DST, dst); + NLA_PUT_U32(skb, RTA_OIF, dev->ifindex); + return nlmsg_end(skb, nlh); + +nla_put_failure: + nlmsg_cancel(skb, nlh); + return -EMSGSIZE; +} + +void rtm_phonet_notify(int event, struct net_device *dev, u8 dst) +{ + struct sk_buff *skb; + int err = -ENOBUFS; + + skb = nlmsg_new(NLMSG_ALIGN(sizeof(struct ifaddrmsg)) + + nla_total_size(1) + nla_total_size(4), GFP_KERNEL); + if (skb == NULL) + goto errout; + err = fill_route(skb, dev, dst, 0, 0, event); + if (err < 0) { + WARN_ON(err == -EMSGSIZE); + kfree_skb(skb); + goto errout; + } + rtnl_notify(skb, dev_net(dev), 0, + RTNLGRP_PHONET_ROUTE, NULL, GFP_KERNEL); + return; +errout: + if (err < 0) + rtnl_set_sk_err(dev_net(dev), RTNLGRP_PHONET_ROUTE, err); +} + +static const struct nla_policy rtm_phonet_policy[RTA_MAX+1] = { + [RTA_DST] = { .type = NLA_U8 }, + [RTA_OIF] = { .type = NLA_U32 }, +}; + +static int route_doit(struct sk_buff *skb, struct nlmsghdr *nlh, void *attr) +{ + struct net *net = sock_net(skb->sk); + struct nlattr *tb[RTA_MAX+1]; + struct net_device *dev; + struct rtmsg *rtm; + int err; + u8 dst; + + if (!capable(CAP_SYS_ADMIN)) + return -EPERM; + + ASSERT_RTNL(); + + err = nlmsg_parse(nlh, sizeof(*rtm), tb, RTA_MAX, rtm_phonet_policy); + if (err < 0) + return err; + + rtm = nlmsg_data(nlh); + if (rtm->rtm_table != RT_TABLE_MAIN || rtm->rtm_type != RTN_UNICAST) + return -EINVAL; + if (tb[RTA_DST] == NULL || tb[RTA_OIF] == NULL) + return -EINVAL; + dst = nla_get_u8(tb[RTA_DST]); + if (dst & 3) /* Phonet addresses only have 6 high-order bits */ + return -EINVAL; + + dev = __dev_get_by_index(net, nla_get_u32(tb[RTA_OIF])); + if (dev == NULL) + return -ENODEV; + + if (nlh->nlmsg_type == RTM_NEWROUTE) + err = phonet_route_add(dev, dst); + else + err = phonet_route_del(dev, dst); + if (!err) + rtm_phonet_notify(nlh->nlmsg_type, dev, dst); + return err; +} + +static int route_dumpit(struct sk_buff *skb, struct netlink_callback *cb) +{ + struct net *net = sock_net(skb->sk); + u8 addr, addr_idx = 0, addr_start_idx = cb->args[0]; + + for (addr = 0; addr < 64; addr++) { + struct net_device *dev; + + dev = phonet_route_get(net, addr << 2); + if (!dev) + continue; + + if (addr_idx++ < addr_start_idx) + continue; + if (fill_route(skb, dev, addr << 2, NETLINK_CB(cb->skb).pid, + cb->nlh->nlmsg_seq, RTM_NEWROUTE)) + goto out; + } + +out: + cb->args[0] = addr_idx; + cb->args[1] = 0; + + return skb->len; +} + int __init phonet_netlink_register(void) { int err = __rtnl_register(PF_PHONET, RTM_NEWADDR, addr_doit, NULL); @@ -169,5 +296,8 @@ int __init phonet_netlink_register(void) /* Further __rtnl_register() cannot fail */ __rtnl_register(PF_PHONET, RTM_DELADDR, addr_doit, NULL); __rtnl_register(PF_PHONET, RTM_GETADDR, NULL, getaddr_dumpit); + __rtnl_register(PF_PHONET, RTM_NEWROUTE, route_doit, NULL); + __rtnl_register(PF_PHONET, RTM_DELROUTE, route_doit, NULL); + __rtnl_register(PF_PHONET, RTM_GETROUTE, NULL, route_dumpit); return 0; } diff --git a/net/phonet/socket.c b/net/phonet/socket.c index aa5b5a972bf..0412beb59a0 100644 --- a/net/phonet/socket.c +++ b/net/phonet/socket.c @@ -94,7 +94,30 @@ struct sock *pn_find_sock_by_sa(struct net *net, const struct sockaddr_pn *spn) spin_unlock_bh(&pnsocks.lock); return rval; +} + +/* Deliver a broadcast packet (only in bottom-half) */ +void pn_deliver_sock_broadcast(struct net *net, struct sk_buff *skb) +{ + struct hlist_node *node; + struct sock *sknode; + + spin_lock(&pnsocks.lock); + sk_for_each(sknode, node, &pnsocks.hlist) { + struct sk_buff *clone; + if (!net_eq(sock_net(sknode), net)) + continue; + if (!sock_flag(sknode, SOCK_BROADCAST)) + continue; + + clone = skb_clone(skb, GFP_ATOMIC); + if (clone) { + sock_hold(sknode); + sk_receive_skb(sknode, clone, 0); + } + } + spin_unlock(&pnsocks.lock); } void pn_sock_hash(struct sock *sk) diff --git a/net/rds/af_rds.c b/net/rds/af_rds.c index 98e05382fd3..a202e5b3607 100644 --- a/net/rds/af_rds.c +++ b/net/rds/af_rds.c @@ -431,7 +431,7 @@ void rds_sock_put(struct rds_sock *rs) sock_put(rds_rs_to_sk(rs)); } -static struct net_proto_family rds_family_ops = { +static const struct net_proto_family rds_family_ops = { .family = AF_RDS, .create = rds_create, .owner = THIS_MODULE, diff --git a/net/rds/tcp_listen.c b/net/rds/tcp_listen.c index 24b743eb0b1..45474a43686 100644 --- a/net/rds/tcp_listen.c +++ b/net/rds/tcp_listen.c @@ -67,11 +67,11 @@ static int rds_tcp_accept_one(struct socket *sock) inet = inet_sk(new_sock->sk); rdsdebug("accepted tcp %u.%u.%u.%u:%u -> %u.%u.%u.%u:%u\n", - NIPQUAD(inet->saddr), ntohs(inet->sport), - NIPQUAD(inet->daddr), ntohs(inet->dport)); + NIPQUAD(inet->inet_saddr), ntohs(inet->inet_sport), + NIPQUAD(inet->inet_daddr), ntohs(inet->inet_dport)); - conn = rds_conn_create(inet->saddr, inet->daddr, &rds_tcp_transport, - GFP_KERNEL); + conn = rds_conn_create(inet->inet_saddr, inet->inet_daddr, + &rds_tcp_transport, GFP_KERNEL); if (IS_ERR(conn)) { ret = PTR_ERR(conn); goto out; diff --git a/net/rfkill/core.c b/net/rfkill/core.c index dbeaf298382..ba2efb960c6 100644 --- a/net/rfkill/core.c +++ b/net/rfkill/core.c @@ -27,6 +27,7 @@ #include <linux/list.h> #include <linux/mutex.h> #include <linux/rfkill.h> +#include <linux/sched.h> #include <linux/spinlock.h> #include <linux/miscdevice.h> #include <linux/wait.h> diff --git a/net/rose/af_rose.c b/net/rose/af_rose.c index 502cce76621..c17734c2ce8 100644 --- a/net/rose/af_rose.c +++ b/net/rose/af_rose.c @@ -1509,7 +1509,7 @@ static const struct file_operations rose_info_fops = { }; #endif /* CONFIG_PROC_FS */ -static struct net_proto_family rose_family_ops = { +static const struct net_proto_family rose_family_ops = { .family = PF_ROSE, .create = rose_create, .owner = THIS_MODULE, diff --git a/net/rxrpc/af_rxrpc.c b/net/rxrpc/af_rxrpc.c index a86afceaa94..6817c9781ef 100644 --- a/net/rxrpc/af_rxrpc.c +++ b/net/rxrpc/af_rxrpc.c @@ -777,7 +777,7 @@ static struct proto rxrpc_proto = { .max_header = sizeof(struct rxrpc_header), }; -static struct net_proto_family rxrpc_family_ops = { +static const struct net_proto_family rxrpc_family_ops = { .family = PF_RXRPC, .create = rxrpc_create, .owner = THIS_MODULE, diff --git a/net/rxrpc/ar-recvmsg.c b/net/rxrpc/ar-recvmsg.c index a39bf97f883..60c2b94e6b5 100644 --- a/net/rxrpc/ar-recvmsg.c +++ b/net/rxrpc/ar-recvmsg.c @@ -146,7 +146,7 @@ int rxrpc_recvmsg(struct kiocb *iocb, struct socket *sock, memcpy(msg->msg_name, &call->conn->trans->peer->srx, sizeof(call->conn->trans->peer->srx)); - sock_recv_timestamp(msg, &rx->sk, skb); + sock_recv_ts_and_drops(msg, &rx->sk, skb); } /* receive the message */ diff --git a/net/sched/act_api.c b/net/sched/act_api.c index 2dfb3e7a040..ca2e1fd2bf6 100644 --- a/net/sched/act_api.c +++ b/net/sched/act_api.c @@ -618,7 +618,8 @@ int tcf_action_copy_stats(struct sk_buff *skb, struct tc_action *a, goto errout; if (gnet_stats_copy_basic(&d, &h->tcf_bstats) < 0 || - gnet_stats_copy_rate_est(&d, &h->tcf_rate_est) < 0 || + gnet_stats_copy_rate_est(&d, &h->tcf_bstats, + &h->tcf_rate_est) < 0 || gnet_stats_copy_queue(&d, &h->tcf_qstats) < 0) goto errout; diff --git a/net/sched/act_skbedit.c b/net/sched/act_skbedit.c index 4ab916b8074..e9607fe55b5 100644 --- a/net/sched/act_skbedit.c +++ b/net/sched/act_skbedit.c @@ -54,6 +54,8 @@ static int tcf_skbedit(struct sk_buff *skb, struct tc_action *a, if (d->flags & SKBEDIT_F_QUEUE_MAPPING && skb->dev->real_num_tx_queues > d->queue_mapping) skb_set_queue_mapping(skb, d->queue_mapping); + if (d->flags & SKBEDIT_F_MARK) + skb->mark = d->mark; spin_unlock(&d->tcf_lock); return d->tcf_action; @@ -63,6 +65,7 @@ static const struct nla_policy skbedit_policy[TCA_SKBEDIT_MAX + 1] = { [TCA_SKBEDIT_PARMS] = { .len = sizeof(struct tc_skbedit) }, [TCA_SKBEDIT_PRIORITY] = { .len = sizeof(u32) }, [TCA_SKBEDIT_QUEUE_MAPPING] = { .len = sizeof(u16) }, + [TCA_SKBEDIT_MARK] = { .len = sizeof(u32) }, }; static int tcf_skbedit_init(struct nlattr *nla, struct nlattr *est, @@ -72,7 +75,7 @@ static int tcf_skbedit_init(struct nlattr *nla, struct nlattr *est, struct tc_skbedit *parm; struct tcf_skbedit *d; struct tcf_common *pc; - u32 flags = 0, *priority = NULL; + u32 flags = 0, *priority = NULL, *mark = NULL; u16 *queue_mapping = NULL; int ret = 0, err; @@ -95,6 +98,12 @@ static int tcf_skbedit_init(struct nlattr *nla, struct nlattr *est, flags |= SKBEDIT_F_QUEUE_MAPPING; queue_mapping = nla_data(tb[TCA_SKBEDIT_QUEUE_MAPPING]); } + + if (tb[TCA_SKBEDIT_MARK] != NULL) { + flags |= SKBEDIT_F_MARK; + mark = nla_data(tb[TCA_SKBEDIT_MARK]); + } + if (!flags) return -EINVAL; @@ -124,6 +133,9 @@ static int tcf_skbedit_init(struct nlattr *nla, struct nlattr *est, d->priority = *priority; if (flags & SKBEDIT_F_QUEUE_MAPPING) d->queue_mapping = *queue_mapping; + if (flags & SKBEDIT_F_MARK) + d->mark = *mark; + d->tcf_action = parm->action; spin_unlock_bh(&d->tcf_lock); @@ -161,6 +173,9 @@ static inline int tcf_skbedit_dump(struct sk_buff *skb, struct tc_action *a, if (d->flags & SKBEDIT_F_QUEUE_MAPPING) NLA_PUT(skb, TCA_SKBEDIT_QUEUE_MAPPING, sizeof(d->queue_mapping), &d->queue_mapping); + if (d->flags & SKBEDIT_F_MARK) + NLA_PUT(skb, TCA_SKBEDIT_MARK, sizeof(d->mark), + &d->mark); t.install = jiffies_to_clock_t(jiffies - d->tcf_tm.install); t.lastuse = jiffies_to_clock_t(jiffies - d->tcf_tm.lastuse); t.expires = jiffies_to_clock_t(d->tcf_tm.expires); diff --git a/net/sched/sch_api.c b/net/sched/sch_api.c index 903e4188b6c..1acfd29cc82 100644 --- a/net/sched/sch_api.c +++ b/net/sched/sch_api.c @@ -1179,7 +1179,7 @@ static int tc_fill_qdisc(struct sk_buff *skb, struct Qdisc *q, u32 clid, goto nla_put_failure; if (gnet_stats_copy_basic(&d, &q->bstats) < 0 || - gnet_stats_copy_rate_est(&d, &q->rate_est) < 0 || + gnet_stats_copy_rate_est(&d, &q->bstats, &q->rate_est) < 0 || gnet_stats_copy_queue(&d, &q->qstats) < 0) goto nla_put_failure; diff --git a/net/sched/sch_cbq.c b/net/sched/sch_cbq.c index 5b132c47326..3846d65bc03 100644 --- a/net/sched/sch_cbq.c +++ b/net/sched/sch_cbq.c @@ -1609,7 +1609,7 @@ cbq_dump_class_stats(struct Qdisc *sch, unsigned long arg, cl->xstats.undertime = cl->undertime - q->now; if (gnet_stats_copy_basic(d, &cl->bstats) < 0 || - gnet_stats_copy_rate_est(d, &cl->rate_est) < 0 || + gnet_stats_copy_rate_est(d, &cl->bstats, &cl->rate_est) < 0 || gnet_stats_copy_queue(d, &cl->qstats) < 0) return -1; diff --git a/net/sched/sch_drr.c b/net/sched/sch_drr.c index 5a888af7e5d..a65604f8f2b 100644 --- a/net/sched/sch_drr.c +++ b/net/sched/sch_drr.c @@ -280,7 +280,7 @@ static int drr_dump_class_stats(struct Qdisc *sch, unsigned long arg, } if (gnet_stats_copy_basic(d, &cl->bstats) < 0 || - gnet_stats_copy_rate_est(d, &cl->rate_est) < 0 || + gnet_stats_copy_rate_est(d, &cl->bstats, &cl->rate_est) < 0 || gnet_stats_copy_queue(d, &cl->qdisc->qstats) < 0) return -1; diff --git a/net/sched/sch_hfsc.c b/net/sched/sch_hfsc.c index 2c5c76be18f..b38b39c6075 100644 --- a/net/sched/sch_hfsc.c +++ b/net/sched/sch_hfsc.c @@ -1375,7 +1375,7 @@ hfsc_dump_class_stats(struct Qdisc *sch, unsigned long arg, xstats.rtwork = cl->cl_cumul; if (gnet_stats_copy_basic(d, &cl->bstats) < 0 || - gnet_stats_copy_rate_est(d, &cl->rate_est) < 0 || + gnet_stats_copy_rate_est(d, &cl->bstats, &cl->rate_est) < 0 || gnet_stats_copy_queue(d, &cl->qstats) < 0) return -1; diff --git a/net/sched/sch_htb.c b/net/sched/sch_htb.c index 85acab9dc6f..2e38d1abd83 100644 --- a/net/sched/sch_htb.c +++ b/net/sched/sch_htb.c @@ -1105,7 +1105,7 @@ htb_dump_class_stats(struct Qdisc *sch, unsigned long arg, struct gnet_dump *d) cl->xstats.ctokens = cl->ctokens; if (gnet_stats_copy_basic(d, &cl->bstats) < 0 || - gnet_stats_copy_rate_est(d, &cl->rate_est) < 0 || + gnet_stats_copy_rate_est(d, NULL, &cl->rate_est) < 0 || gnet_stats_copy_queue(d, &cl->qstats) < 0) return -1; diff --git a/net/sctp/protocol.c b/net/sctp/protocol.c index 612dc878e05..d9f4cc2c786 100644 --- a/net/sctp/protocol.c +++ b/net/sctp/protocol.c @@ -296,19 +296,19 @@ static void sctp_v4_from_sk(union sctp_addr *addr, struct sock *sk) { addr->v4.sin_family = AF_INET; addr->v4.sin_port = 0; - addr->v4.sin_addr.s_addr = inet_sk(sk)->rcv_saddr; + addr->v4.sin_addr.s_addr = inet_sk(sk)->inet_rcv_saddr; } /* Initialize sk->sk_rcv_saddr from sctp_addr. */ static void sctp_v4_to_sk_saddr(union sctp_addr *addr, struct sock *sk) { - inet_sk(sk)->rcv_saddr = addr->v4.sin_addr.s_addr; + inet_sk(sk)->inet_rcv_saddr = addr->v4.sin_addr.s_addr; } /* Initialize sk->sk_daddr from sctp_addr. */ static void sctp_v4_to_sk_daddr(union sctp_addr *addr, struct sock *sk) { - inet_sk(sk)->daddr = addr->v4.sin_addr.s_addr; + inet_sk(sk)->inet_daddr = addr->v4.sin_addr.s_addr; } /* Initialize a sctp_addr from an address parameter. */ @@ -598,7 +598,7 @@ static struct sock *sctp_v4_create_accept_sk(struct sock *sk, newinet = inet_sk(newsk); - newinet->daddr = asoc->peer.primary_addr.v4.sin_addr.s_addr; + newinet->inet_daddr = asoc->peer.primary_addr.v4.sin_addr.s_addr; sk_refcnt_debug_inc(newsk); diff --git a/net/sctp/socket.c b/net/sctp/socket.c index c8d05758661..4085db99033 100644 --- a/net/sctp/socket.c +++ b/net/sctp/socket.c @@ -394,7 +394,7 @@ SCTP_STATIC int sctp_do_bind(struct sock *sk, union sctp_addr *addr, int len) /* Refresh ephemeral port. */ if (!bp->port) - bp->port = inet_sk(sk)->num; + bp->port = inet_sk(sk)->inet_num; /* Add the address to the bind address list. * Use GFP_ATOMIC since BHs will be disabled. @@ -403,7 +403,7 @@ SCTP_STATIC int sctp_do_bind(struct sock *sk, union sctp_addr *addr, int len) /* Copy back into socket for getsockname() use. */ if (!ret) { - inet_sk(sk)->sport = htons(inet_sk(sk)->num); + inet_sk(sk)->inet_sport = htons(inet_sk(sk)->inet_num); af->to_sk_saddr(addr, sk); } @@ -1115,7 +1115,7 @@ static int __sctp_connect(struct sock* sk, } /* Initialize sk's dport and daddr for getpeername() */ - inet_sk(sk)->dport = htons(asoc->peer.port); + inet_sk(sk)->inet_dport = htons(asoc->peer.port); af = sctp_get_af_specific(sa_addr->sa.sa_family); af->to_sk_daddr(sa_addr, sk); sk->sk_err = 0; @@ -1958,7 +1958,7 @@ SCTP_STATIC int sctp_recvmsg(struct kiocb *iocb, struct sock *sk, if (err) goto out_free; - sock_recv_timestamp(msg, sk, skb); + sock_recv_ts_and_drops(msg, sk, skb); if (sctp_ulpevent_is_notification(event)) { msg->msg_flags |= MSG_NOTIFICATION; sp->pf->event_msgname(event, msg->msg_name, addr_len); @@ -5851,7 +5851,7 @@ pp_not_found: */ success: if (!sctp_sk(sk)->bind_hash) { - inet_sk(sk)->num = snum; + inet_sk(sk)->inet_num = snum; sk_add_bind_node(sk, &pp->owner); sctp_sk(sk)->bind_hash = pp; } @@ -5923,7 +5923,7 @@ SCTP_STATIC int sctp_listen_start(struct sock *sk, int backlog) if (sctp_autobind(sk)) return -EAGAIN; } else { - if (sctp_get_port(sk, inet_sk(sk)->num)) { + if (sctp_get_port(sk, inet_sk(sk)->inet_num)) { sk->sk_state = SCTP_SS_CLOSED; return -EADDRINUSE; } @@ -6094,14 +6094,14 @@ static void sctp_bucket_destroy(struct sctp_bind_bucket *pp) static inline void __sctp_put_port(struct sock *sk) { struct sctp_bind_hashbucket *head = - &sctp_port_hashtable[sctp_phashfn(inet_sk(sk)->num)]; + &sctp_port_hashtable[sctp_phashfn(inet_sk(sk)->inet_num)]; struct sctp_bind_bucket *pp; sctp_spin_lock(&head->lock); pp = sctp_sk(sk)->bind_hash; __sk_del_bind_node(sk); sctp_sk(sk)->bind_hash = NULL; - inet_sk(sk)->num = 0; + inet_sk(sk)->inet_num = 0; sctp_bucket_destroy(pp); sctp_spin_unlock(&head->lock); } @@ -6128,7 +6128,7 @@ static int sctp_autobind(struct sock *sk) /* Initialize a local sockaddr structure to INADDR_ANY. */ af = sctp_sk(sk)->pf->af; - port = htons(inet_sk(sk)->num); + port = htons(inet_sk(sk)->inet_num); af->inaddr_any(&autoaddr, port); return sctp_do_bind(sk, &autoaddr, af->sockaddr_len); @@ -6697,12 +6697,12 @@ void sctp_copy_sock(struct sock *newsk, struct sock *sk, /* Initialize sk's sport, dport, rcv_saddr and daddr for * getsockname() and getpeername() */ - newinet->sport = inet->sport; - newinet->saddr = inet->saddr; - newinet->rcv_saddr = inet->rcv_saddr; - newinet->dport = htons(asoc->peer.port); + newinet->inet_sport = inet->inet_sport; + newinet->inet_saddr = inet->inet_saddr; + newinet->inet_rcv_saddr = inet->inet_rcv_saddr; + newinet->inet_dport = htons(asoc->peer.port); newinet->pmtudisc = inet->pmtudisc; - newinet->id = asoc->next_tsn ^ jiffies; + newinet->inet_id = asoc->next_tsn ^ jiffies; newinet->uc_ttl = inet->uc_ttl; newinet->mc_loop = 1; @@ -6741,13 +6741,13 @@ static void sctp_sock_migrate(struct sock *oldsk, struct sock *newsk, newsp->hmac = NULL; /* Hook this new socket in to the bind_hash list. */ - head = &sctp_port_hashtable[sctp_phashfn(inet_sk(oldsk)->num)]; + head = &sctp_port_hashtable[sctp_phashfn(inet_sk(oldsk)->inet_num)]; sctp_local_bh_disable(); sctp_spin_lock(&head->lock); pp = sctp_sk(oldsk)->bind_hash; sk_add_bind_node(newsk, &pp->owner); sctp_sk(newsk)->bind_hash = pp; - inet_sk(newsk)->num = inet_sk(oldsk)->num; + inet_sk(newsk)->inet_num = inet_sk(oldsk)->inet_num; sctp_spin_unlock(&head->lock); sctp_local_bh_enable(); diff --git a/net/socket.c b/net/socket.c index 75655365b5f..9dff31c9b79 100644 --- a/net/socket.c +++ b/net/socket.c @@ -668,10 +668,24 @@ void __sock_recv_timestamp(struct msghdr *msg, struct sock *sk, EXPORT_SYMBOL_GPL(__sock_recv_timestamp); -static inline int __sock_recvmsg(struct kiocb *iocb, struct socket *sock, - struct msghdr *msg, size_t size, int flags) +inline void sock_recv_drops(struct msghdr *msg, struct sock *sk, struct sk_buff *skb) +{ + if (sock_flag(sk, SOCK_RXQ_OVFL) && skb && skb->dropcount) + put_cmsg(msg, SOL_SOCKET, SO_RXQ_OVFL, + sizeof(__u32), &skb->dropcount); +} + +void sock_recv_ts_and_drops(struct msghdr *msg, struct sock *sk, + struct sk_buff *skb) +{ + sock_recv_timestamp(msg, sk, skb); + sock_recv_drops(msg, sk, skb); +} +EXPORT_SYMBOL_GPL(sock_recv_ts_and_drops); + +static inline int __sock_recvmsg_nosec(struct kiocb *iocb, struct socket *sock, + struct msghdr *msg, size_t size, int flags) { - int err; struct sock_iocb *si = kiocb_to_siocb(iocb); si->sock = sock; @@ -680,13 +694,17 @@ static inline int __sock_recvmsg(struct kiocb *iocb, struct socket *sock, si->size = size; si->flags = flags; - err = security_socket_recvmsg(sock, msg, size, flags); - if (err) - return err; - return sock->ops->recvmsg(iocb, sock, msg, size, flags); } +static inline int __sock_recvmsg(struct kiocb *iocb, struct socket *sock, + struct msghdr *msg, size_t size, int flags) +{ + int err = security_socket_recvmsg(sock, msg, size, flags); + + return err ?: __sock_recvmsg_nosec(iocb, sock, msg, size, flags); +} + int sock_recvmsg(struct socket *sock, struct msghdr *msg, size_t size, int flags) { @@ -702,6 +720,21 @@ int sock_recvmsg(struct socket *sock, struct msghdr *msg, return ret; } +static int sock_recvmsg_nosec(struct socket *sock, struct msghdr *msg, + size_t size, int flags) +{ + struct kiocb iocb; + struct sock_iocb siocb; + int ret; + + init_sync_kiocb(&iocb, NULL); + iocb.private = &siocb; + ret = __sock_recvmsg_nosec(&iocb, sock, msg, size, flags); + if (-EIOCBQUEUED == ret) + ret = wait_on_sync_kiocb(&iocb); + return ret; +} + int kernel_recvmsg(struct socket *sock, struct msghdr *msg, struct kvec *vec, size_t num, size_t size, int flags) { @@ -905,11 +938,11 @@ static long sock_ioctl(struct file *file, unsigned cmd, unsigned long arg) if (cmd >= SIOCDEVPRIVATE && cmd <= (SIOCDEVPRIVATE + 15)) { err = dev_ioctl(net, cmd, argp); } else -#ifdef CONFIG_WIRELESS_EXT +#ifdef CONFIG_WEXT_CORE if (cmd >= SIOCIWFIRST && cmd <= SIOCIWLAST) { err = dev_ioctl(net, cmd, argp); } else -#endif /* CONFIG_WIRELESS_EXT */ +#endif switch (cmd) { case FIOSETOWN: case SIOCSPGRP: @@ -1100,11 +1133,14 @@ static int sock_fasync(int fd, struct file *filp, int on) fna->fa_next = sock->fasync_list; write_lock_bh(&sk->sk_callback_lock); sock->fasync_list = fna; + sock_set_flag(sk, SOCK_FASYNC); write_unlock_bh(&sk->sk_callback_lock); } else { if (fa != NULL) { write_lock_bh(&sk->sk_callback_lock); *prev = fa->fa_next; + if (!sock->fasync_list) + sock_reset_flag(sk, SOCK_FASYNC); write_unlock_bh(&sk->sk_callback_lock); kfree(fa); } @@ -1965,22 +2001,15 @@ out: return err; } -/* - * BSD recvmsg interface - */ - -SYSCALL_DEFINE3(recvmsg, int, fd, struct msghdr __user *, msg, - unsigned int, flags) +static int __sys_recvmsg(struct socket *sock, struct msghdr __user *msg, + struct msghdr *msg_sys, unsigned flags, int nosec) { struct compat_msghdr __user *msg_compat = (struct compat_msghdr __user *)msg; - struct socket *sock; struct iovec iovstack[UIO_FASTIOV]; struct iovec *iov = iovstack; - struct msghdr msg_sys; unsigned long cmsg_ptr; int err, iov_size, total_len, len; - int fput_needed; /* kernel mode address */ struct sockaddr_storage addr; @@ -1990,27 +2019,23 @@ SYSCALL_DEFINE3(recvmsg, int, fd, struct msghdr __user *, msg, int __user *uaddr_len; if (MSG_CMSG_COMPAT & flags) { - if (get_compat_msghdr(&msg_sys, msg_compat)) + if (get_compat_msghdr(msg_sys, msg_compat)) return -EFAULT; } - else if (copy_from_user(&msg_sys, msg, sizeof(struct msghdr))) + else if (copy_from_user(msg_sys, msg, sizeof(struct msghdr))) return -EFAULT; - sock = sockfd_lookup_light(fd, &err, &fput_needed); - if (!sock) - goto out; - err = -EMSGSIZE; - if (msg_sys.msg_iovlen > UIO_MAXIOV) - goto out_put; + if (msg_sys->msg_iovlen > UIO_MAXIOV) + goto out; /* Check whether to allocate the iovec area */ err = -ENOMEM; - iov_size = msg_sys.msg_iovlen * sizeof(struct iovec); - if (msg_sys.msg_iovlen > UIO_FASTIOV) { + iov_size = msg_sys->msg_iovlen * sizeof(struct iovec); + if (msg_sys->msg_iovlen > UIO_FASTIOV) { iov = sock_kmalloc(sock->sk, iov_size, GFP_KERNEL); if (!iov) - goto out_put; + goto out; } /* @@ -2018,46 +2043,47 @@ SYSCALL_DEFINE3(recvmsg, int, fd, struct msghdr __user *, msg, * kernel msghdr to use the kernel address space) */ - uaddr = (__force void __user *)msg_sys.msg_name; + uaddr = (__force void __user *)msg_sys->msg_name; uaddr_len = COMPAT_NAMELEN(msg); if (MSG_CMSG_COMPAT & flags) { - err = verify_compat_iovec(&msg_sys, iov, + err = verify_compat_iovec(msg_sys, iov, (struct sockaddr *)&addr, VERIFY_WRITE); } else - err = verify_iovec(&msg_sys, iov, + err = verify_iovec(msg_sys, iov, (struct sockaddr *)&addr, VERIFY_WRITE); if (err < 0) goto out_freeiov; total_len = err; - cmsg_ptr = (unsigned long)msg_sys.msg_control; - msg_sys.msg_flags = flags & (MSG_CMSG_CLOEXEC|MSG_CMSG_COMPAT); + cmsg_ptr = (unsigned long)msg_sys->msg_control; + msg_sys->msg_flags = flags & (MSG_CMSG_CLOEXEC|MSG_CMSG_COMPAT); if (sock->file->f_flags & O_NONBLOCK) flags |= MSG_DONTWAIT; - err = sock_recvmsg(sock, &msg_sys, total_len, flags); + err = (nosec ? sock_recvmsg_nosec : sock_recvmsg)(sock, msg_sys, + total_len, flags); if (err < 0) goto out_freeiov; len = err; if (uaddr != NULL) { err = move_addr_to_user((struct sockaddr *)&addr, - msg_sys.msg_namelen, uaddr, + msg_sys->msg_namelen, uaddr, uaddr_len); if (err < 0) goto out_freeiov; } - err = __put_user((msg_sys.msg_flags & ~MSG_CMSG_COMPAT), + err = __put_user((msg_sys->msg_flags & ~MSG_CMSG_COMPAT), COMPAT_FLAGS(msg)); if (err) goto out_freeiov; if (MSG_CMSG_COMPAT & flags) - err = __put_user((unsigned long)msg_sys.msg_control - cmsg_ptr, + err = __put_user((unsigned long)msg_sys->msg_control - cmsg_ptr, &msg_compat->msg_controllen); else - err = __put_user((unsigned long)msg_sys.msg_control - cmsg_ptr, + err = __put_user((unsigned long)msg_sys->msg_control - cmsg_ptr, &msg->msg_controllen); if (err) goto out_freeiov; @@ -2066,21 +2092,150 @@ SYSCALL_DEFINE3(recvmsg, int, fd, struct msghdr __user *, msg, out_freeiov: if (iov != iovstack) sock_kfree_s(sock->sk, iov, iov_size); -out_put: +out: + return err; +} + +/* + * BSD recvmsg interface + */ + +SYSCALL_DEFINE3(recvmsg, int, fd, struct msghdr __user *, msg, + unsigned int, flags) +{ + int fput_needed, err; + struct msghdr msg_sys; + struct socket *sock = sockfd_lookup_light(fd, &err, &fput_needed); + + if (!sock) + goto out; + + err = __sys_recvmsg(sock, msg, &msg_sys, flags, 0); + fput_light(sock->file, fput_needed); out: return err; } -#ifdef __ARCH_WANT_SYS_SOCKETCALL +/* + * Linux recvmmsg interface + */ + +int __sys_recvmmsg(int fd, struct mmsghdr __user *mmsg, unsigned int vlen, + unsigned int flags, struct timespec *timeout) +{ + int fput_needed, err, datagrams; + struct socket *sock; + struct mmsghdr __user *entry; + struct msghdr msg_sys; + struct timespec end_time; + + if (timeout && + poll_select_set_timeout(&end_time, timeout->tv_sec, + timeout->tv_nsec)) + return -EINVAL; + + datagrams = 0; + + sock = sockfd_lookup_light(fd, &err, &fput_needed); + if (!sock) + return err; + + err = sock_error(sock->sk); + if (err) + goto out_put; + + entry = mmsg; + + while (datagrams < vlen) { + /* + * No need to ask LSM for more than the first datagram. + */ + err = __sys_recvmsg(sock, (struct msghdr __user *)entry, + &msg_sys, flags, datagrams); + if (err < 0) + break; + err = put_user(err, &entry->msg_len); + if (err) + break; + ++entry; + ++datagrams; + + if (timeout) { + ktime_get_ts(timeout); + *timeout = timespec_sub(end_time, *timeout); + if (timeout->tv_sec < 0) { + timeout->tv_sec = timeout->tv_nsec = 0; + break; + } + + /* Timeout, return less than vlen datagrams */ + if (timeout->tv_nsec == 0 && timeout->tv_sec == 0) + break; + } + + /* Out of band data, return right away */ + if (msg_sys.msg_flags & MSG_OOB) + break; + } + +out_put: + fput_light(sock->file, fput_needed); + + if (err == 0) + return datagrams; + + if (datagrams != 0) { + /* + * We may return less entries than requested (vlen) if the + * sock is non block and there aren't enough datagrams... + */ + if (err != -EAGAIN) { + /* + * ... or if recvmsg returns an error after we + * received some datagrams, where we record the + * error to return on the next call or if the + * app asks about it using getsockopt(SO_ERROR). + */ + sock->sk->sk_err = -err; + } + return datagrams; + } + + return err; +} + +SYSCALL_DEFINE5(recvmmsg, int, fd, struct mmsghdr __user *, mmsg, + unsigned int, vlen, unsigned int, flags, + struct timespec __user *, timeout) +{ + int datagrams; + struct timespec timeout_sys; + + if (!timeout) + return __sys_recvmmsg(fd, mmsg, vlen, flags, NULL); + + if (copy_from_user(&timeout_sys, timeout, sizeof(timeout_sys))) + return -EFAULT; + + datagrams = __sys_recvmmsg(fd, mmsg, vlen, flags, &timeout_sys); + + if (datagrams > 0 && + copy_to_user(timeout, &timeout_sys, sizeof(timeout_sys))) + datagrams = -EFAULT; + + return datagrams; +} + +#ifdef __ARCH_WANT_SYS_SOCKETCALL /* Argument list sizes for sys_socketcall */ #define AL(x) ((x) * sizeof(unsigned long)) -static const unsigned char nargs[19]={ +static const unsigned char nargs[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 @@ -2100,7 +2255,7 @@ SYSCALL_DEFINE2(socketcall, int, call, unsigned long __user *, args) int err; unsigned int len; - if (call < 1 || call > SYS_ACCEPT4) + if (call < 1 || call > SYS_RECVMMSG) return -EINVAL; len = nargs[call]; @@ -2178,6 +2333,10 @@ SYSCALL_DEFINE2(socketcall, int, call, unsigned long __user *, args) case SYS_RECVMSG: err = sys_recvmsg(a0, (struct msghdr __user *)a1, a[2]); break; + case SYS_RECVMMSG: + err = sys_recvmmsg(a0, (struct mmsghdr __user *)a1, a[2], a[3], + (struct timespec __user *)a[4]); + break; case SYS_ACCEPT4: err = sys_accept4(a0, (struct sockaddr __user *)a1, (int __user *)a[2], a[3]); diff --git a/net/sunrpc/svcauth_unix.c b/net/sunrpc/svcauth_unix.c index 117f68a8aa4..f4c7ff3a53e 100644 --- a/net/sunrpc/svcauth_unix.c +++ b/net/sunrpc/svcauth_unix.c @@ -686,8 +686,7 @@ svcauth_unix_set_client(struct svc_rqst *rqstp) case AF_INET: sin = svc_addr_in(rqstp); sin6 = &sin6_storage; - ipv6_addr_set(&sin6->sin6_addr, 0, 0, - htonl(0x0000FFFF), sin->sin_addr.s_addr); + ipv6_addr_set_v4mapped(sin->sin_addr.s_addr, &sin6->sin6_addr); break; case AF_INET6: sin6 = svc_addr_in6(rqstp); diff --git a/net/sunrpc/svcsock.c b/net/sunrpc/svcsock.c index ccc5e83cae5..c2a17876def 100644 --- a/net/sunrpc/svcsock.c +++ b/net/sunrpc/svcsock.c @@ -272,14 +272,14 @@ static int svc_one_sock_name(struct svc_sock *svsk, char *buf, int remaining) case PF_INET: len = snprintf(buf, remaining, "ipv4 %s %pI4 %d\n", proto_name, - &inet_sk(sk)->rcv_saddr, - inet_sk(sk)->num); + &inet_sk(sk)->inet_rcv_saddr, + inet_sk(sk)->inet_num); break; case PF_INET6: len = snprintf(buf, remaining, "ipv6 %s %pI6 %d\n", proto_name, &inet6_sk(sk)->rcv_saddr, - inet_sk(sk)->num); + inet_sk(sk)->inet_num); break; default: len = snprintf(buf, remaining, "*unknown-%d*\n", @@ -1311,7 +1311,7 @@ static struct svc_sock *svc_setup_socket(struct svc_serv *serv, /* Register socket with portmapper */ if (*errp >= 0 && pmap_register) *errp = svc_register(serv, inet->sk_family, inet->sk_protocol, - ntohs(inet_sk(inet)->sport)); + ntohs(inet_sk(inet)->inet_sport)); if (*errp < 0) { kfree(svsk); diff --git a/net/unix/af_unix.c b/net/unix/af_unix.c index fc820cd7545..3291902f0b8 100644 --- a/net/unix/af_unix.c +++ b/net/unix/af_unix.c @@ -2216,7 +2216,7 @@ static const struct file_operations unix_seq_fops = { #endif -static struct net_proto_family unix_family_ops = { +static const struct net_proto_family unix_family_ops = { .family = PF_UNIX, .create = unix_create, .owner = THIS_MODULE, diff --git a/net/wireless/Kconfig b/net/wireless/Kconfig index abf7ca3f9ff..614bdcec1c8 100644 --- a/net/wireless/Kconfig +++ b/net/wireless/Kconfig @@ -1,3 +1,21 @@ +config WIRELESS_EXT + bool + +config WEXT_CORE + def_bool y + depends on CFG80211_WEXT || WIRELESS_EXT + +config WEXT_PROC + def_bool y + depends on PROC_FS + depends on WEXT_CORE + +config WEXT_SPY + bool + +config WEXT_PRIV + bool + config CFG80211 tristate "cfg80211 - wireless configuration API" depends on RFKILL || !RFKILL @@ -56,6 +74,12 @@ config CFG80211_REG_DEBUG If unsure, say N. +config CFG80211_DEFAULT_PS_VALUE + int + default 1 if CFG80211_DEFAULT_PS + default 0 + depends on CFG80211 + config CFG80211_DEFAULT_PS bool "enable powersave by default" depends on CFG80211 @@ -67,14 +91,10 @@ config CFG80211_DEFAULT_PS applications instead -- they need to register their network latency requirement, see Documentation/power/pm_qos_interface.txt. -config CFG80211_DEFAULT_PS_VALUE - int - default 1 if CFG80211_DEFAULT_PS - default 0 - config CFG80211_DEBUGFS bool "cfg80211 DebugFS entries" - depends on CFG80211 && DEBUG_FS + depends on CFG80211 + depends on DEBUG_FS ---help--- You can enable this if you want to debugfs entries for cfg80211. @@ -83,6 +103,7 @@ config CFG80211_DEBUGFS config WIRELESS_OLD_REGULATORY bool "Old wireless static regulatory definitions" default n + depends on CFG80211 ---help--- This option enables the old static regulatory information and uses it within the new framework. This option is available @@ -94,20 +115,19 @@ config WIRELESS_OLD_REGULATORY Say N and if you say Y, please tell us why. The default is N. -config WIRELESS_EXT - bool "Wireless extensions" +config CFG80211_WEXT + bool "cfg80211 wireless extensions compatibility" + depends on CFG80211 + select WEXT_CORE default y - ---help--- - This option enables the legacy wireless extensions - (wireless network interface configuration via ioctls.) - - Say Y unless you've upgraded all your userspace to use - nl80211 instead of wireless extensions. + help + Enable this option if you need old userspace for wireless + extensions with cfg80211-based drivers. config WIRELESS_EXT_SYSFS bool "Wireless extensions sysfs files" default y - depends on WIRELESS_EXT && SYSFS + depends on WEXT_CORE && SYSFS help This option enables the deprecated wireless statistics files in /sys/class/net/*/wireless/. The same information diff --git a/net/wireless/Makefile b/net/wireless/Makefile index 3ecaa917997..f07c8dc7aab 100644 --- a/net/wireless/Makefile +++ b/net/wireless/Makefile @@ -1,13 +1,17 @@ -obj-$(CONFIG_WIRELESS_EXT) += wext.o obj-$(CONFIG_CFG80211) += cfg80211.o obj-$(CONFIG_LIB80211) += lib80211.o obj-$(CONFIG_LIB80211_CRYPT_WEP) += lib80211_crypt_wep.o obj-$(CONFIG_LIB80211_CRYPT_CCMP) += lib80211_crypt_ccmp.o obj-$(CONFIG_LIB80211_CRYPT_TKIP) += lib80211_crypt_tkip.o +obj-$(CONFIG_WEXT_CORE) += wext-core.o +obj-$(CONFIG_WEXT_PROC) += wext-proc.o +obj-$(CONFIG_WEXT_SPY) += wext-spy.o +obj-$(CONFIG_WEXT_PRIV) += wext-priv.o + cfg80211-y += core.o sysfs.o radiotap.o util.o reg.o scan.o nl80211.o -cfg80211-y += mlme.o ibss.o sme.o chan.o +cfg80211-y += mlme.o ibss.o sme.o chan.o ethtool.o cfg80211-$(CONFIG_CFG80211_DEBUGFS) += debugfs.o -cfg80211-$(CONFIG_WIRELESS_EXT) += wext-compat.o wext-sme.o +cfg80211-$(CONFIG_CFG80211_WEXT) += wext-compat.o wext-sme.o ccflags-y += -D__CHECK_ENDIAN__ diff --git a/net/wireless/core.c b/net/wireless/core.c index 45b2be3274d..07252967be9 100644 --- a/net/wireless/core.c +++ b/net/wireless/core.c @@ -21,6 +21,7 @@ #include "sysfs.h" #include "debugfs.h" #include "wext-compat.h" +#include "ethtool.h" /* name for sysfs, %d is appended */ #define PHY_NAME "phy" @@ -358,6 +359,10 @@ struct wiphy *wiphy_new(const struct cfg80211_ops *ops, int sizeof_priv) INIT_LIST_HEAD(&rdev->bss_list); INIT_WORK(&rdev->scan_done_wk, __cfg80211_scan_done); +#ifdef CONFIG_CFG80211_WEXT + rdev->wiphy.wext = &cfg80211_wext_handler; +#endif + device_initialize(&rdev->wiphy.dev); rdev->wiphy.dev.class = &ieee80211_class; rdev->wiphy.dev.platform_data = rdev; @@ -625,6 +630,10 @@ static void wdev_cleanup_work(struct work_struct *work) dev_put(wdev->netdev); } +static struct device_type wiphy_type = { + .name = "wlan", +}; + static int cfg80211_netdev_notifier_call(struct notifier_block * nb, unsigned long state, void *ndev) @@ -641,6 +650,9 @@ static int cfg80211_netdev_notifier_call(struct notifier_block * nb, WARN_ON(wdev->iftype == NL80211_IFTYPE_UNSPECIFIED); switch (state) { + case NETDEV_POST_INIT: + SET_NETDEV_DEVTYPE(dev, &wiphy_type); + break; case NETDEV_REGISTER: /* * NB: cannot take rdev->mtx here because this may be @@ -665,9 +677,7 @@ static int cfg80211_netdev_notifier_call(struct notifier_block * nb, wdev->netdev = dev; wdev->sme_state = CFG80211_SME_IDLE; mutex_unlock(&rdev->devlist_mtx); -#ifdef CONFIG_WIRELESS_EXT - if (!dev->wireless_handlers) - dev->wireless_handlers = &cfg80211_wext_handler; +#ifdef CONFIG_CFG80211_WEXT wdev->wext.default_key = -1; wdev->wext.default_mgmt_key = -1; wdev->wext.connect.auth_type = NL80211_AUTHTYPE_AUTOMATIC; @@ -681,6 +691,8 @@ static int cfg80211_netdev_notifier_call(struct notifier_block * nb, wdev->wext.ps = false; } #endif + if (!dev->ethtool_ops) + dev->ethtool_ops = &cfg80211_ethtool_ops; break; case NETDEV_GOING_DOWN: switch (wdev->iftype) { @@ -689,7 +701,7 @@ static int cfg80211_netdev_notifier_call(struct notifier_block * nb, break; case NL80211_IFTYPE_STATION: wdev_lock(wdev); -#ifdef CONFIG_WIRELESS_EXT +#ifdef CONFIG_CFG80211_WEXT kfree(wdev->wext.ie); wdev->wext.ie = NULL; wdev->wext.ie_len = 0; @@ -721,7 +733,7 @@ static int cfg80211_netdev_notifier_call(struct notifier_block * nb, mutex_unlock(&rdev->devlist_mtx); dev_put(dev); } -#ifdef CONFIG_WIRELESS_EXT +#ifdef CONFIG_CFG80211_WEXT cfg80211_lock_rdev(rdev); mutex_lock(&rdev->devlist_mtx); wdev_lock(wdev); @@ -759,7 +771,7 @@ static int cfg80211_netdev_notifier_call(struct notifier_block * nb, sysfs_remove_link(&dev->dev.kobj, "phy80211"); list_del_init(&wdev->list); rdev->devlist_generation++; -#ifdef CONFIG_WIRELESS_EXT +#ifdef CONFIG_CFG80211_WEXT kfree(wdev->wext.keys); #endif } diff --git a/net/wireless/ethtool.c b/net/wireless/ethtool.c new file mode 100644 index 00000000000..ca4c825be93 --- /dev/null +++ b/net/wireless/ethtool.c @@ -0,0 +1,45 @@ +#include <linux/utsname.h> +#include <net/cfg80211.h> +#include "ethtool.h" + +static void cfg80211_get_drvinfo(struct net_device *dev, + struct ethtool_drvinfo *info) +{ + struct wireless_dev *wdev = dev->ieee80211_ptr; + + strlcpy(info->driver, wiphy_dev(wdev->wiphy)->driver->name, + sizeof(info->driver)); + + strlcpy(info->version, init_utsname()->release, sizeof(info->version)); + + if (wdev->wiphy->fw_version[0]) + strncpy(info->fw_version, wdev->wiphy->fw_version, + sizeof(info->fw_version)); + else + strncpy(info->fw_version, "N/A", sizeof(info->fw_version)); + + strlcpy(info->bus_info, dev_name(wiphy_dev(wdev->wiphy)), + sizeof(info->bus_info)); +} + +static int cfg80211_get_regs_len(struct net_device *dev) +{ + /* For now, return 0... */ + return 0; +} + +static void cfg80211_get_regs(struct net_device *dev, struct ethtool_regs *regs, + void *data) +{ + struct wireless_dev *wdev = dev->ieee80211_ptr; + + regs->version = wdev->wiphy->hw_version; + regs->len = 0; +} + +const struct ethtool_ops cfg80211_ethtool_ops = { + .get_drvinfo = cfg80211_get_drvinfo, + .get_regs_len = cfg80211_get_regs_len, + .get_regs = cfg80211_get_regs, + .get_link = ethtool_op_get_link, +}; diff --git a/net/wireless/ethtool.h b/net/wireless/ethtool.h new file mode 100644 index 00000000000..695ecad20bd --- /dev/null +++ b/net/wireless/ethtool.h @@ -0,0 +1,6 @@ +#ifndef __CFG80211_ETHTOOL__ +#define __CFG80211_ETHTOOL__ + +extern const struct ethtool_ops cfg80211_ethtool_ops; + +#endif /* __CFG80211_ETHTOOL__ */ diff --git a/net/wireless/ibss.c b/net/wireless/ibss.c index c8833891197..39b6d92e282 100644 --- a/net/wireless/ibss.c +++ b/net/wireless/ibss.c @@ -15,7 +15,7 @@ void __cfg80211_ibss_joined(struct net_device *dev, const u8 *bssid) { struct wireless_dev *wdev = dev->ieee80211_ptr; struct cfg80211_bss *bss; -#ifdef CONFIG_WIRELESS_EXT +#ifdef CONFIG_CFG80211_WEXT union iwreq_data wrqu; #endif @@ -44,7 +44,7 @@ void __cfg80211_ibss_joined(struct net_device *dev, const u8 *bssid) nl80211_send_ibss_bssid(wiphy_to_dev(wdev->wiphy), dev, bssid, GFP_KERNEL); -#ifdef CONFIG_WIRELESS_EXT +#ifdef CONFIG_CFG80211_WEXT memset(&wrqu, 0, sizeof(wrqu)); memcpy(wrqu.ap_addr.sa_data, bssid, ETH_ALEN); wireless_send_event(dev, SIOCGIWAP, &wrqu, NULL); @@ -96,7 +96,7 @@ int __cfg80211_join_ibss(struct cfg80211_registered_device *rdev, kfree(wdev->connect_keys); wdev->connect_keys = connkeys; -#ifdef CONFIG_WIRELESS_EXT +#ifdef CONFIG_CFG80211_WEXT wdev->wext.ibss.channel = params->channel; #endif err = rdev->ops->join_ibss(&rdev->wiphy, dev, params); @@ -154,7 +154,7 @@ static void __cfg80211_clear_ibss(struct net_device *dev, bool nowext) wdev->current_bss = NULL; wdev->ssid_len = 0; -#ifdef CONFIG_WIRELESS_EXT +#ifdef CONFIG_CFG80211_WEXT if (!nowext) wdev->wext.ibss.ssid_len = 0; #endif @@ -203,7 +203,7 @@ int cfg80211_leave_ibss(struct cfg80211_registered_device *rdev, return err; } -#ifdef CONFIG_WIRELESS_EXT +#ifdef CONFIG_CFG80211_WEXT int cfg80211_ibss_wext_join(struct cfg80211_registered_device *rdev, struct wireless_dev *wdev) { diff --git a/net/wireless/mlme.c b/net/wireless/mlme.c index 0a6b7a0eca6..83c2a288dc6 100644 --- a/net/wireless/mlme.c +++ b/net/wireless/mlme.c @@ -130,7 +130,7 @@ void cfg80211_send_rx_assoc(struct net_device *dev, const u8 *buf, size_t len) } EXPORT_SYMBOL(cfg80211_send_rx_assoc); -static void __cfg80211_send_deauth(struct net_device *dev, +void __cfg80211_send_deauth(struct net_device *dev, const u8 *buf, size_t len) { struct wireless_dev *wdev = dev->ieee80211_ptr; @@ -139,7 +139,6 @@ static void __cfg80211_send_deauth(struct net_device *dev, struct ieee80211_mgmt *mgmt = (struct ieee80211_mgmt *)buf; const u8 *bssid = mgmt->bssid; int i; - bool done = false; ASSERT_WDEV_LOCK(wdev); @@ -147,7 +146,6 @@ static void __cfg80211_send_deauth(struct net_device *dev, if (wdev->current_bss && memcmp(wdev->current_bss->pub.bssid, bssid, ETH_ALEN) == 0) { - done = true; cfg80211_unhold_bss(wdev->current_bss); cfg80211_put_bss(&wdev->current_bss->pub); wdev->current_bss = NULL; @@ -157,7 +155,6 @@ static void __cfg80211_send_deauth(struct net_device *dev, cfg80211_unhold_bss(wdev->auth_bsses[i]); cfg80211_put_bss(&wdev->auth_bsses[i]->pub); wdev->auth_bsses[i] = NULL; - done = true; break; } if (wdev->authtry_bsses[i] && @@ -165,13 +162,10 @@ static void __cfg80211_send_deauth(struct net_device *dev, cfg80211_unhold_bss(wdev->authtry_bsses[i]); cfg80211_put_bss(&wdev->authtry_bsses[i]->pub); wdev->authtry_bsses[i] = NULL; - done = true; break; } } - WARN_ON(!done); - if (wdev->sme_state == CFG80211_SME_CONNECTED) { u16 reason_code; bool from_ap; @@ -186,27 +180,19 @@ static void __cfg80211_send_deauth(struct net_device *dev, false, NULL); } } +EXPORT_SYMBOL(__cfg80211_send_deauth); - -void cfg80211_send_deauth(struct net_device *dev, const u8 *buf, size_t len, - void *cookie) +void cfg80211_send_deauth(struct net_device *dev, const u8 *buf, size_t len) { struct wireless_dev *wdev = dev->ieee80211_ptr; - BUG_ON(cookie && wdev != cookie); - - if (cookie) { - /* called within callback */ - __cfg80211_send_deauth(dev, buf, len); - } else { - wdev_lock(wdev); - __cfg80211_send_deauth(dev, buf, len); - wdev_unlock(wdev); - } + wdev_lock(wdev); + __cfg80211_send_deauth(dev, buf, len); + wdev_unlock(wdev); } EXPORT_SYMBOL(cfg80211_send_deauth); -static void __cfg80211_send_disassoc(struct net_device *dev, +void __cfg80211_send_disassoc(struct net_device *dev, const u8 *buf, size_t len) { struct wireless_dev *wdev = dev->ieee80211_ptr; @@ -247,22 +233,15 @@ static void __cfg80211_send_disassoc(struct net_device *dev, from_ap = memcmp(mgmt->sa, dev->dev_addr, ETH_ALEN) != 0; __cfg80211_disconnected(dev, NULL, 0, reason_code, from_ap); } +EXPORT_SYMBOL(__cfg80211_send_disassoc); -void cfg80211_send_disassoc(struct net_device *dev, const u8 *buf, size_t len, - void *cookie) +void cfg80211_send_disassoc(struct net_device *dev, const u8 *buf, size_t len) { struct wireless_dev *wdev = dev->ieee80211_ptr; - BUG_ON(cookie && wdev != cookie); - - if (cookie) { - /* called within callback */ - __cfg80211_send_disassoc(dev, buf, len); - } else { - wdev_lock(wdev); - __cfg80211_send_disassoc(dev, buf, len); - wdev_unlock(wdev); - } + wdev_lock(wdev); + __cfg80211_send_disassoc(dev, buf, len); + wdev_unlock(wdev); } EXPORT_SYMBOL(cfg80211_send_disassoc); @@ -340,7 +319,7 @@ void cfg80211_michael_mic_failure(struct net_device *dev, const u8 *addr, { struct wiphy *wiphy = dev->ieee80211_ptr->wiphy; struct cfg80211_registered_device *rdev = wiphy_to_dev(wiphy); -#ifdef CONFIG_WIRELESS_EXT +#ifdef CONFIG_CFG80211_WEXT union iwreq_data wrqu; char *buf = kmalloc(128, gfp); diff --git a/net/wireless/nl80211.c b/net/wireless/nl80211.c index ca3c92a0a14..f48394126bf 100644 --- a/net/wireless/nl80211.c +++ b/net/wireless/nl80211.c @@ -1264,7 +1264,7 @@ static int nl80211_set_key(struct sk_buff *skb, struct genl_info *info) if (!err) err = func(&rdev->wiphy, dev, key.idx); -#ifdef CONFIG_WIRELESS_EXT +#ifdef CONFIG_CFG80211_WEXT if (!err) { if (func == rdev->ops->set_default_key) dev->ieee80211_ptr->wext.default_key = key.idx; @@ -1365,7 +1365,7 @@ static int nl80211_del_key(struct sk_buff *skb, struct genl_info *info) if (!err) err = rdev->ops->del_key(&rdev->wiphy, dev, key.idx, mac_addr); -#ifdef CONFIG_WIRELESS_EXT +#ifdef CONFIG_CFG80211_WEXT if (!err) { if (key.idx == dev->ieee80211_ptr->wext.default_key) dev->ieee80211_ptr->wext.default_key = -1; @@ -3105,6 +3105,8 @@ static int nl80211_send_bss(struct sk_buff *msg, u32 pid, u32 seq, int flags, NLA_PUT_U16(msg, NL80211_BSS_BEACON_INTERVAL, res->beacon_interval); NLA_PUT_U16(msg, NL80211_BSS_CAPABILITY, res->capability); NLA_PUT_U32(msg, NL80211_BSS_FREQUENCY, res->channel->center_freq); + NLA_PUT_U32(msg, NL80211_BSS_SEEN_MS_AGO, + jiffies_to_msecs(jiffies - intbss->ts)); switch (rdev->wiphy.signal_type) { case CFG80211_SIGNAL_TYPE_MBM: diff --git a/net/wireless/scan.c b/net/wireless/scan.c index e5f92ee758f..2e8c515f3c5 100644 --- a/net/wireless/scan.c +++ b/net/wireless/scan.c @@ -22,7 +22,7 @@ void ___cfg80211_scan_done(struct cfg80211_registered_device *rdev, bool leak) { struct cfg80211_scan_request *request; struct net_device *dev; -#ifdef CONFIG_WIRELESS_EXT +#ifdef CONFIG_CFG80211_WEXT union iwreq_data wrqu; #endif @@ -47,7 +47,7 @@ void ___cfg80211_scan_done(struct cfg80211_registered_device *rdev, bool leak) else nl80211_send_scan_done(rdev, dev); -#ifdef CONFIG_WIRELESS_EXT +#ifdef CONFIG_CFG80211_WEXT if (!request->aborted) { memset(&wrqu, 0, sizeof(wrqu)); @@ -592,7 +592,7 @@ void cfg80211_unlink_bss(struct wiphy *wiphy, struct cfg80211_bss *pub) } EXPORT_SYMBOL(cfg80211_unlink_bss); -#ifdef CONFIG_WIRELESS_EXT +#ifdef CONFIG_CFG80211_WEXT int cfg80211_wext_siwscan(struct net_device *dev, struct iw_request_info *info, union iwreq_data *wrqu, char *extra) diff --git a/net/wireless/sme.c b/net/wireless/sme.c index ece378d531e..98a3b7efac4 100644 --- a/net/wireless/sme.c +++ b/net/wireless/sme.c @@ -362,7 +362,7 @@ void __cfg80211_connect_result(struct net_device *dev, const u8 *bssid, { struct wireless_dev *wdev = dev->ieee80211_ptr; u8 *country_ie; -#ifdef CONFIG_WIRELESS_EXT +#ifdef CONFIG_CFG80211_WEXT union iwreq_data wrqu; #endif @@ -379,7 +379,7 @@ void __cfg80211_connect_result(struct net_device *dev, const u8 *bssid, resp_ie, resp_ie_len, status, GFP_KERNEL); -#ifdef CONFIG_WIRELESS_EXT +#ifdef CONFIG_CFG80211_WEXT if (wextev) { if (req_ie && status == WLAN_STATUS_SUCCESS) { memset(&wrqu, 0, sizeof(wrqu)); @@ -494,7 +494,7 @@ void __cfg80211_roamed(struct wireless_dev *wdev, const u8 *bssid, const u8 *resp_ie, size_t resp_ie_len) { struct cfg80211_bss *bss; -#ifdef CONFIG_WIRELESS_EXT +#ifdef CONFIG_CFG80211_WEXT union iwreq_data wrqu; #endif @@ -529,7 +529,7 @@ void __cfg80211_roamed(struct wireless_dev *wdev, const u8 *bssid, req_ie, req_ie_len, resp_ie, resp_ie_len, GFP_KERNEL); -#ifdef CONFIG_WIRELESS_EXT +#ifdef CONFIG_CFG80211_WEXT if (req_ie) { memset(&wrqu, 0, sizeof(wrqu)); wrqu.data.length = req_ie_len; @@ -590,7 +590,7 @@ void __cfg80211_disconnected(struct net_device *dev, const u8 *ie, struct wireless_dev *wdev = dev->ieee80211_ptr; struct cfg80211_registered_device *rdev = wiphy_to_dev(wdev->wiphy); int i; -#ifdef CONFIG_WIRELESS_EXT +#ifdef CONFIG_CFG80211_WEXT union iwreq_data wrqu; #endif @@ -648,7 +648,7 @@ void __cfg80211_disconnected(struct net_device *dev, const u8 *ie, for (i = 0; i < 6; i++) rdev->ops->del_key(wdev->wiphy, dev, i, NULL); -#ifdef CONFIG_WIRELESS_EXT +#ifdef CONFIG_CFG80211_WEXT memset(&wrqu, 0, sizeof(wrqu)); wrqu.ap_addr.sa_family = ARPHRD_ETHER; wireless_send_event(dev, SIOCGIWAP, &wrqu, NULL); diff --git a/net/wireless/wext.c b/net/wireless/wext-core.c index 60fe57761ca..a4e5ddc8d4f 100644 --- a/net/wireless/wext.c +++ b/net/wireless/wext-core.c @@ -1,112 +1,28 @@ /* - * This file implement the Wireless Extensions APIs. + * This file implement the Wireless Extensions core API. * * Authors : Jean Tourrilhes - HPL - <jt@hpl.hp.com> * Copyright (c) 1997-2007 Jean Tourrilhes, All Rights Reserved. + * Copyright 2009 Johannes Berg <johannes@sipsolutions.net> * * (As all part of the Linux kernel, this file is GPL) */ - -/************************** DOCUMENTATION **************************/ -/* - * API definition : - * -------------- - * See <linux/wireless.h> for details of the APIs and the rest. - * - * History : - * ------- - * - * v1 - 5.12.01 - Jean II - * o Created this file. - * - * v2 - 13.12.01 - Jean II - * o Move /proc/net/wireless stuff from net/core/dev.c to here - * o Make Wireless Extension IOCTLs go through here - * o Added iw_handler handling ;-) - * o Added standard ioctl description - * o Initial dumb commit strategy based on orinoco.c - * - * v3 - 19.12.01 - Jean II - * o Make sure we don't go out of standard_ioctl[] in ioctl_standard_call - * o Add event dispatcher function - * o Add event description - * o Propagate events as rtnetlink IFLA_WIRELESS option - * o Generate event on selected SET requests - * - * v4 - 18.04.02 - Jean II - * o Fix stupid off by one in iw_ioctl_description : IW_ESSID_MAX_SIZE + 1 - * - * v5 - 21.06.02 - Jean II - * o Add IW_PRIV_TYPE_ADDR in priv_type_size (+cleanup) - * o Reshuffle IW_HEADER_TYPE_XXX to map IW_PRIV_TYPE_XXX changes - * o Add IWEVCUSTOM for driver specific event/scanning token - * o Turn on WE_STRICT_WRITE by default + kernel warning - * o Fix WE_STRICT_WRITE in ioctl_export_private() (32 => iw_num) - * o Fix off-by-one in test (extra_size <= IFNAMSIZ) - * - * v6 - 9.01.03 - Jean II - * o Add common spy support : iw_handler_set_spy(), wireless_spy_update() - * o Add enhanced spy support : iw_handler_set_thrspy() and event. - * o Add WIRELESS_EXT version display in /proc/net/wireless - * - * v6 - 18.06.04 - Jean II - * o Change get_spydata() method for added safety - * o Remove spy #ifdef, they are always on -> cleaner code - * o Allow any size GET request if user specifies length > max - * and if request has IW_DESCR_FLAG_NOMAX flag or is SIOCGIWPRIV - * o Start migrating get_wireless_stats to struct iw_handler_def - * o Add wmb() in iw_handler_set_spy() for non-coherent archs/cpus - * Based on patch from Pavel Roskin <proski@gnu.org> : - * o Fix kernel data leak to user space in private handler handling - * - * v7 - 18.3.05 - Jean II - * o Remove (struct iw_point *)->pointer from events and streams - * o Remove spy_offset from struct iw_handler_def - * o Start deprecating dev->get_wireless_stats, output a warning - * o If IW_QUAL_DBM is set, show dBm values in /proc/net/wireless - * o Don't lose INVALID/DBM flags when clearing UPDATED flags (iwstats) - * - * v8 - 17.02.06 - Jean II - * o RtNetlink requests support (SET/GET) - * - * v8b - 03.08.06 - Herbert Xu - * o Fix Wireless Event locking issues. - * - * v9 - 14.3.06 - Jean II - * o Change length in ESSID and NICK to strlen() instead of strlen()+1 - * o Make standard_ioctl_num and standard_event_num unsigned - * o Remove (struct net_device *)->get_wireless_stats() - * - * v10 - 16.3.07 - Jean II - * o Prevent leaking of kernel space in stream on 64 bits. - */ - -/***************************** INCLUDES *****************************/ - -#include <linux/module.h> -#include <linux/types.h> /* off_t */ -#include <linux/netdevice.h> /* struct ifreq, dev_get_by_name() */ -#include <linux/proc_fs.h> -#include <linux/rtnetlink.h> /* rtnetlink stuff */ -#include <linux/seq_file.h> -#include <linux/init.h> /* for __init */ -#include <linux/if_arp.h> /* ARPHRD_ETHER */ -#include <linux/etherdevice.h> /* compare_ether_addr */ -#include <linux/interrupt.h> -#include <net/net_namespace.h> - -#include <linux/wireless.h> /* Pretty obvious */ -#include <net/iw_handler.h> /* New driver API */ +#include <linux/kernel.h> +#include <linux/netdevice.h> +#include <linux/rtnetlink.h> +#include <linux/wireless.h> +#include <linux/uaccess.h> +#include <net/cfg80211.h> +#include <net/iw_handler.h> #include <net/netlink.h> #include <net/wext.h> +#include <net/net_namespace.h> + +typedef int (*wext_ioctl_func)(struct net_device *, struct iwreq *, + unsigned int, struct iw_request_info *, + iw_handler); -#include <asm/uaccess.h> /* copy_to_user() */ -/************************* GLOBAL VARIABLES *************************/ -/* - * You should not use global variables, because of re-entrancy. - * On our case, it's only const, so it's OK... - */ /* * Meta-data about all the standard Wireless Extension request we * know about. @@ -390,18 +306,6 @@ static const struct iw_ioctl_description standard_event[] = { }; static const unsigned standard_event_num = ARRAY_SIZE(standard_event); -/* Size (in bytes) of the various private data types */ -static const char iw_priv_type_size[] = { - 0, /* IW_PRIV_TYPE_NONE */ - 1, /* IW_PRIV_TYPE_BYTE */ - 1, /* IW_PRIV_TYPE_CHAR */ - 0, /* Not defined */ - sizeof(__u32), /* IW_PRIV_TYPE_INT */ - sizeof(struct iw_freq), /* IW_PRIV_TYPE_FLOAT */ - sizeof(struct sockaddr), /* IW_PRIV_TYPE_ADDR */ - 0, /* Not defined */ -}; - /* Size (in bytes) of various events */ static const int event_type_size[] = { IW_EV_LCP_LEN, /* IW_HEADER_TYPE_NULL */ @@ -433,323 +337,346 @@ static const int compat_event_type_size[] = { }; #endif -/************************ COMMON SUBROUTINES ************************/ -/* - * Stuff that may be used in various place or doesn't fit in one - * of the section below. - */ - -/* ---------------------------------------------------------------- */ -/* - * Return the driver handler associated with a specific Wireless Extension. - */ -static iw_handler get_handler(struct net_device *dev, unsigned int cmd) -{ - /* Don't "optimise" the following variable, it will crash */ - unsigned int index; /* *MUST* be unsigned */ - /* Check if we have some wireless handlers defined */ - if (dev->wireless_handlers == NULL) - return NULL; - - /* Try as a standard command */ - index = cmd - SIOCIWFIRST; - if (index < dev->wireless_handlers->num_standard) - return dev->wireless_handlers->standard[index]; - - /* Try as a private command */ - index = cmd - SIOCIWFIRSTPRIV; - if (index < dev->wireless_handlers->num_private) - return dev->wireless_handlers->private[index]; +/* IW event code */ - /* Not found */ - return NULL; -} - -/* ---------------------------------------------------------------- */ -/* - * Get statistics out of the driver - */ -struct iw_statistics *get_wireless_stats(struct net_device *dev) +static int __net_init wext_pernet_init(struct net *net) { - /* New location */ - if ((dev->wireless_handlers != NULL) && - (dev->wireless_handlers->get_wireless_stats != NULL)) - return dev->wireless_handlers->get_wireless_stats(dev); - - /* Not found */ - return NULL; + skb_queue_head_init(&net->wext_nlevents); + return 0; } -/* ---------------------------------------------------------------- */ -/* - * Call the commit handler in the driver - * (if exist and if conditions are right) - * - * Note : our current commit strategy is currently pretty dumb, - * but we will be able to improve on that... - * The goal is to try to agreagate as many changes as possible - * before doing the commit. Drivers that will define a commit handler - * are usually those that need a reset after changing parameters, so - * we want to minimise the number of reset. - * A cool idea is to use a timer : at each "set" command, we re-set the - * timer, when the timer eventually fires, we call the driver. - * Hopefully, more on that later. - * - * Also, I'm waiting to see how many people will complain about the - * netif_running(dev) test. I'm open on that one... - * Hopefully, the driver will remember to do a commit in "open()" ;-) - */ -static int call_commit_handler(struct net_device *dev) +static void __net_exit wext_pernet_exit(struct net *net) { - if ((netif_running(dev)) && - (dev->wireless_handlers->standard[0] != NULL)) - /* Call the commit handler on the driver */ - return dev->wireless_handlers->standard[0](dev, NULL, - NULL, NULL); - else - return 0; /* Command completed successfully */ + skb_queue_purge(&net->wext_nlevents); } -/* ---------------------------------------------------------------- */ -/* - * Calculate size of private arguments - */ -static int get_priv_size(__u16 args) -{ - int num = args & IW_PRIV_SIZE_MASK; - int type = (args & IW_PRIV_TYPE_MASK) >> 12; +static struct pernet_operations wext_pernet_ops = { + .init = wext_pernet_init, + .exit = wext_pernet_exit, +}; - return num * iw_priv_type_size[type]; +static int __init wireless_nlevent_init(void) +{ + return register_pernet_subsys(&wext_pernet_ops); } -/* ---------------------------------------------------------------- */ -/* - * Re-calculate the size of private arguments - */ -static int adjust_priv_size(__u16 args, struct iw_point *iwp) +subsys_initcall(wireless_nlevent_init); + +/* Process events generated by the wireless layer or the driver. */ +static void wireless_nlevent_process(struct work_struct *work) { - int num = iwp->length; - int max = args & IW_PRIV_SIZE_MASK; - int type = (args & IW_PRIV_TYPE_MASK) >> 12; + struct sk_buff *skb; + struct net *net; - /* Make sure the driver doesn't goof up */ - if (max < num) - num = max; + rtnl_lock(); + + for_each_net(net) { + while ((skb = skb_dequeue(&net->wext_nlevents))) + rtnl_notify(skb, net, 0, RTNLGRP_LINK, NULL, + GFP_KERNEL); + } - return num * iw_priv_type_size[type]; + rtnl_unlock(); } -/* ---------------------------------------------------------------- */ -/* - * Standard Wireless Handler : get wireless stats - * Allow programatic access to /proc/net/wireless even if /proc - * doesn't exist... Also more efficient... - */ -static int iw_handler_get_iwstats(struct net_device * dev, - struct iw_request_info * info, - union iwreq_data * wrqu, - char * extra) +static DECLARE_WORK(wireless_nlevent_work, wireless_nlevent_process); + +static struct nlmsghdr *rtnetlink_ifinfo_prep(struct net_device *dev, + struct sk_buff *skb) { - /* Get stats from the driver */ - struct iw_statistics *stats; + struct ifinfomsg *r; + struct nlmsghdr *nlh; - stats = get_wireless_stats(dev); - if (stats) { - /* Copy statistics to extra */ - memcpy(extra, stats, sizeof(struct iw_statistics)); - wrqu->data.length = sizeof(struct iw_statistics); + nlh = nlmsg_put(skb, 0, 0, RTM_NEWLINK, sizeof(*r), 0); + if (!nlh) + return NULL; - /* Check if we need to clear the updated flag */ - if (wrqu->data.flags != 0) - stats->qual.updated &= ~IW_QUAL_ALL_UPDATED; - return 0; - } else - return -EOPNOTSUPP; + r = nlmsg_data(nlh); + r->ifi_family = AF_UNSPEC; + r->__ifi_pad = 0; + r->ifi_type = dev->type; + r->ifi_index = dev->ifindex; + r->ifi_flags = dev_get_flags(dev); + r->ifi_change = 0; /* Wireless changes don't affect those flags */ + + NLA_PUT_STRING(skb, IFLA_IFNAME, dev->name); + + return nlh; + nla_put_failure: + nlmsg_cancel(skb, nlh); + return NULL; } -/* ---------------------------------------------------------------- */ + /* - * Standard Wireless Handler : get iwpriv definitions - * Export the driver private handler definition - * They will be picked up by tools like iwpriv... + * Main event dispatcher. Called from other parts and drivers. + * Send the event on the appropriate channels. + * May be called from interrupt context. */ -static int iw_handler_get_private(struct net_device * dev, - struct iw_request_info * info, - union iwreq_data * wrqu, - char * extra) +void wireless_send_event(struct net_device * dev, + unsigned int cmd, + union iwreq_data * wrqu, + const char * extra) { - /* Check if the driver has something to export */ - if ((dev->wireless_handlers->num_private_args == 0) || - (dev->wireless_handlers->private_args == NULL)) - return -EOPNOTSUPP; + const struct iw_ioctl_description * descr = NULL; + int extra_len = 0; + struct iw_event *event; /* Mallocated whole event */ + int event_len; /* Its size */ + int hdr_len; /* Size of the event header */ + int wrqu_off = 0; /* Offset in wrqu */ + /* Don't "optimise" the following variable, it will crash */ + unsigned cmd_index; /* *MUST* be unsigned */ + struct sk_buff *skb; + struct nlmsghdr *nlh; + struct nlattr *nla; +#ifdef CONFIG_COMPAT + struct __compat_iw_event *compat_event; + struct compat_iw_point compat_wrqu; + struct sk_buff *compskb; +#endif - /* Check if there is enough buffer up there */ - if (wrqu->data.length < dev->wireless_handlers->num_private_args) { - /* User space can't know in advance how large the buffer - * needs to be. Give it a hint, so that we can support - * any size buffer we want somewhat efficiently... */ - wrqu->data.length = dev->wireless_handlers->num_private_args; - return -E2BIG; + /* + * Nothing in the kernel sends scan events with data, be safe. + * This is necessary because we cannot fix up scan event data + * for compat, due to being contained in 'extra', but normally + * applications are required to retrieve the scan data anyway + * and no data is included in the event, this codifies that + * practice. + */ + if (WARN_ON(cmd == SIOCGIWSCAN && extra)) + extra = NULL; + + /* Get the description of the Event */ + if (cmd <= SIOCIWLAST) { + cmd_index = cmd - SIOCIWFIRST; + if (cmd_index < standard_ioctl_num) + descr = &(standard_ioctl[cmd_index]); + } else { + cmd_index = cmd - IWEVFIRST; + if (cmd_index < standard_event_num) + descr = &(standard_event[cmd_index]); + } + /* Don't accept unknown events */ + if (descr == NULL) { + /* Note : we don't return an error to the driver, because + * the driver would not know what to do about it. It can't + * return an error to the user, because the event is not + * initiated by a user request. + * The best the driver could do is to log an error message. + * We will do it ourselves instead... + */ + printk(KERN_ERR "%s (WE) : Invalid/Unknown Wireless Event (0x%04X)\n", + dev->name, cmd); + return; } - /* Set the number of available ioctls. */ - wrqu->data.length = dev->wireless_handlers->num_private_args; + /* Check extra parameters and set extra_len */ + if (descr->header_type == IW_HEADER_TYPE_POINT) { + /* Check if number of token fits within bounds */ + if (wrqu->data.length > descr->max_tokens) { + printk(KERN_ERR "%s (WE) : Wireless Event too big (%d)\n", dev->name, wrqu->data.length); + return; + } + if (wrqu->data.length < descr->min_tokens) { + printk(KERN_ERR "%s (WE) : Wireless Event too small (%d)\n", dev->name, wrqu->data.length); + return; + } + /* Calculate extra_len - extra is NULL for restricted events */ + if (extra != NULL) + extra_len = wrqu->data.length * descr->token_size; + /* Always at an offset in wrqu */ + wrqu_off = IW_EV_POINT_OFF; + } - /* Copy structure to the user buffer. */ - memcpy(extra, dev->wireless_handlers->private_args, - sizeof(struct iw_priv_args) * wrqu->data.length); + /* Total length of the event */ + hdr_len = event_type_size[descr->header_type]; + event_len = hdr_len + extra_len; - return 0; -} + /* + * The problem for 64/32 bit. + * + * On 64-bit, a regular event is laid out as follows: + * | 0 | 1 | 2 | 3 | 4 | 5 | 6 | 7 | + * | event.len | event.cmd | p a d d i n g | + * | wrqu data ... (with the correct size) | + * + * This padding exists because we manipulate event->u, + * and 'event' is not packed. + * + * An iw_point event is laid out like this instead: + * | 0 | 1 | 2 | 3 | 4 | 5 | 6 | 7 | + * | event.len | event.cmd | p a d d i n g | + * | iwpnt.len | iwpnt.flg | p a d d i n g | + * | extra data ... + * + * The second padding exists because struct iw_point is extended, + * but this depends on the platform... + * + * On 32-bit, all the padding shouldn't be there. + */ + skb = nlmsg_new(NLMSG_DEFAULT_SIZE, GFP_ATOMIC); + if (!skb) + return; -/******************** /proc/net/wireless SUPPORT ********************/ -/* - * The /proc/net/wireless file is a human readable user-space interface - * exporting various wireless specific statistics from the wireless devices. - * This is the most popular part of the Wireless Extensions ;-) - * - * This interface is a pure clone of /proc/net/dev (in net/core/dev.c). - * The content of the file is basically the content of "struct iw_statistics". - */ + /* Send via the RtNetlink event channel */ + nlh = rtnetlink_ifinfo_prep(dev, skb); + if (WARN_ON(!nlh)) { + kfree_skb(skb); + return; + } -#ifdef CONFIG_PROC_FS + /* Add the wireless events in the netlink packet */ + nla = nla_reserve(skb, IFLA_WIRELESS, event_len); + if (!nla) { + kfree_skb(skb); + return; + } + event = nla_data(nla); -/* ---------------------------------------------------------------- */ -/* - * Print one entry (line) of /proc/net/wireless - */ -static void wireless_seq_printf_stats(struct seq_file *seq, - struct net_device *dev) -{ - /* Get stats from the driver */ - struct iw_statistics *stats = get_wireless_stats(dev); - static struct iw_statistics nullstats = {}; + /* Fill event - first clear to avoid data leaking */ + memset(event, 0, hdr_len); + event->len = event_len; + event->cmd = cmd; + memcpy(&event->u, ((char *) wrqu) + wrqu_off, hdr_len - IW_EV_LCP_LEN); + if (extra_len) + memcpy(((char *) event) + hdr_len, extra, extra_len); - /* show device if it's wireless regardless of current stats */ - if (!stats && dev->wireless_handlers) - stats = &nullstats; + nlmsg_end(skb, nlh); +#ifdef CONFIG_COMPAT + hdr_len = compat_event_type_size[descr->header_type]; + event_len = hdr_len + extra_len; - if (stats) { - seq_printf(seq, "%6s: %04x %3d%c %3d%c %3d%c %6d %6d %6d " - "%6d %6d %6d\n", - dev->name, stats->status, stats->qual.qual, - stats->qual.updated & IW_QUAL_QUAL_UPDATED - ? '.' : ' ', - ((__s32) stats->qual.level) - - ((stats->qual.updated & IW_QUAL_DBM) ? 0x100 : 0), - stats->qual.updated & IW_QUAL_LEVEL_UPDATED - ? '.' : ' ', - ((__s32) stats->qual.noise) - - ((stats->qual.updated & IW_QUAL_DBM) ? 0x100 : 0), - stats->qual.updated & IW_QUAL_NOISE_UPDATED - ? '.' : ' ', - stats->discard.nwid, stats->discard.code, - stats->discard.fragment, stats->discard.retries, - stats->discard.misc, stats->miss.beacon); - - if (stats != &nullstats) - stats->qual.updated &= ~IW_QUAL_ALL_UPDATED; + compskb = nlmsg_new(NLMSG_DEFAULT_SIZE, GFP_ATOMIC); + if (!compskb) { + kfree_skb(skb); + return; } -} -/* ---------------------------------------------------------------- */ -/* - * Print info for /proc/net/wireless (print all entries) - */ -static int wireless_dev_seq_show(struct seq_file *seq, void *v) -{ - might_sleep(); - - if (v == SEQ_START_TOKEN) - seq_printf(seq, "Inter-| sta-| Quality | Discarded " - "packets | Missed | WE\n" - " face | tus | link level noise | nwid " - "crypt frag retry misc | beacon | %d\n", - WIRELESS_EXT); - else - wireless_seq_printf_stats(seq, v); - return 0; + /* Send via the RtNetlink event channel */ + nlh = rtnetlink_ifinfo_prep(dev, compskb); + if (WARN_ON(!nlh)) { + kfree_skb(skb); + kfree_skb(compskb); + return; + } + + /* Add the wireless events in the netlink packet */ + nla = nla_reserve(compskb, IFLA_WIRELESS, event_len); + if (!nla) { + kfree_skb(skb); + kfree_skb(compskb); + return; + } + compat_event = nla_data(nla); + + compat_event->len = event_len; + compat_event->cmd = cmd; + if (descr->header_type == IW_HEADER_TYPE_POINT) { + compat_wrqu.length = wrqu->data.length; + compat_wrqu.flags = wrqu->data.flags; + memcpy(&compat_event->pointer, + ((char *) &compat_wrqu) + IW_EV_COMPAT_POINT_OFF, + hdr_len - IW_EV_COMPAT_LCP_LEN); + if (extra_len) + memcpy(((char *) compat_event) + hdr_len, + extra, extra_len); + } else { + /* extra_len must be zero, so no if (extra) needed */ + memcpy(&compat_event->pointer, wrqu, + hdr_len - IW_EV_COMPAT_LCP_LEN); + } + + nlmsg_end(compskb, nlh); + + skb_shinfo(skb)->frag_list = compskb; +#endif + skb_queue_tail(&dev_net(dev)->wext_nlevents, skb); + schedule_work(&wireless_nlevent_work); } +EXPORT_SYMBOL(wireless_send_event); + + + +/* IW handlers */ -static void *wireless_dev_seq_start(struct seq_file *seq, loff_t *pos) +struct iw_statistics *get_wireless_stats(struct net_device *dev) { - struct net *net = seq_file_net(seq); - loff_t off; - struct net_device *dev; +#ifdef CONFIG_WIRELESS_EXT + if ((dev->wireless_handlers != NULL) && + (dev->wireless_handlers->get_wireless_stats != NULL)) + return dev->wireless_handlers->get_wireless_stats(dev); +#endif - rtnl_lock(); - if (!*pos) - return SEQ_START_TOKEN; +#ifdef CONFIG_CFG80211_WEXT + if (dev->ieee80211_ptr && dev->ieee80211_ptr && + dev->ieee80211_ptr->wiphy && + dev->ieee80211_ptr->wiphy->wext && + dev->ieee80211_ptr->wiphy->wext->get_wireless_stats) + return dev->ieee80211_ptr->wiphy->wext->get_wireless_stats(dev); +#endif - off = 1; - for_each_netdev(net, dev) - if (off++ == *pos) - return dev; + /* not found */ return NULL; } -static void *wireless_dev_seq_next(struct seq_file *seq, void *v, loff_t *pos) +static int iw_handler_get_iwstats(struct net_device * dev, + struct iw_request_info * info, + union iwreq_data * wrqu, + char * extra) { - struct net *net = seq_file_net(seq); + /* Get stats from the driver */ + struct iw_statistics *stats; - ++*pos; + stats = get_wireless_stats(dev); + if (stats) { + /* Copy statistics to extra */ + memcpy(extra, stats, sizeof(struct iw_statistics)); + wrqu->data.length = sizeof(struct iw_statistics); - return v == SEQ_START_TOKEN ? - first_net_device(net) : next_net_device(v); + /* Check if we need to clear the updated flag */ + if (wrqu->data.flags != 0) + stats->qual.updated &= ~IW_QUAL_ALL_UPDATED; + return 0; + } else + return -EOPNOTSUPP; } -static void wireless_dev_seq_stop(struct seq_file *seq, void *v) +static iw_handler get_handler(struct net_device *dev, unsigned int cmd) { - rtnl_unlock(); -} - -static const struct seq_operations wireless_seq_ops = { - .start = wireless_dev_seq_start, - .next = wireless_dev_seq_next, - .stop = wireless_dev_seq_stop, - .show = wireless_dev_seq_show, -}; + /* Don't "optimise" the following variable, it will crash */ + unsigned int index; /* *MUST* be unsigned */ + const struct iw_handler_def *handlers = NULL; -static int seq_open_wireless(struct inode *inode, struct file *file) -{ - return seq_open_net(inode, file, &wireless_seq_ops, - sizeof(struct seq_net_private)); -} +#ifdef CONFIG_CFG80211_WEXT + if (dev->ieee80211_ptr && dev->ieee80211_ptr->wiphy) + handlers = dev->ieee80211_ptr->wiphy->wext; +#endif +#ifdef CONFIG_WIRELESS_EXT + if (dev->wireless_handlers) + handlers = dev->wireless_handlers; +#endif -static const struct file_operations wireless_seq_fops = { - .owner = THIS_MODULE, - .open = seq_open_wireless, - .read = seq_read, - .llseek = seq_lseek, - .release = seq_release_net, -}; + if (!handlers) + return NULL; -int wext_proc_init(struct net *net) -{ - /* Create /proc/net/wireless entry */ - if (!proc_net_fops_create(net, "wireless", S_IRUGO, &wireless_seq_fops)) - return -ENOMEM; + /* Try as a standard command */ + index = cmd - SIOCIWFIRST; + if (index < handlers->num_standard) + return handlers->standard[index]; - return 0; -} +#ifdef CONFIG_WEXT_PRIV + /* Try as a private command */ + index = cmd - SIOCIWFIRSTPRIV; + if (index < handlers->num_private) + return handlers->private[index]; +#endif -void wext_proc_exit(struct net *net) -{ - proc_net_remove(net, "wireless"); + /* Not found */ + return NULL; } -#endif /* CONFIG_PROC_FS */ -/************************** IOCTL SUPPORT **************************/ -/* - * The original user space API to configure all those Wireless Extensions - * is through IOCTLs. - * In there, we check if we need to call the new driver API (iw_handler) - * or just call the driver ioctl handler. - */ - -/* ---------------------------------------------------------------- */ static int ioctl_standard_iw_point(struct iw_point *iwp, unsigned int cmd, const struct iw_ioctl_description *descr, iw_handler handler, struct net_device *dev, @@ -893,188 +820,39 @@ out: } /* - * Wrapper to call a standard Wireless Extension handler. - * We do various checks and also take care of moving data between - * user space and kernel space. - */ -static int ioctl_standard_call(struct net_device * dev, - struct iwreq *iwr, - unsigned int cmd, - struct iw_request_info *info, - iw_handler handler) -{ - const struct iw_ioctl_description * descr; - int ret = -EINVAL; - - /* Get the description of the IOCTL */ - if ((cmd - SIOCIWFIRST) >= standard_ioctl_num) - return -EOPNOTSUPP; - descr = &(standard_ioctl[cmd - SIOCIWFIRST]); - - /* Check if we have a pointer to user space data or not */ - if (descr->header_type != IW_HEADER_TYPE_POINT) { - - /* No extra arguments. Trivial to handle */ - ret = handler(dev, info, &(iwr->u), NULL); - - /* Generate an event to notify listeners of the change */ - if ((descr->flags & IW_DESCR_FLAG_EVENT) && - ((ret == 0) || (ret == -EIWCOMMIT))) - wireless_send_event(dev, cmd, &(iwr->u), NULL); - } else { - ret = ioctl_standard_iw_point(&iwr->u.data, cmd, descr, - handler, dev, info); - } - - /* Call commit handler if needed and defined */ - if (ret == -EIWCOMMIT) - ret = call_commit_handler(dev); - - /* Here, we will generate the appropriate event if needed */ - - return ret; -} - -/* ---------------------------------------------------------------- */ -/* - * Wrapper to call a private Wireless Extension handler. - * We do various checks and also take care of moving data between - * user space and kernel space. - * It's not as nice and slimline as the standard wrapper. The cause - * is struct iw_priv_args, which was not really designed for the - * job we are going here. + * Call the commit handler in the driver + * (if exist and if conditions are right) + * + * Note : our current commit strategy is currently pretty dumb, + * but we will be able to improve on that... + * The goal is to try to agreagate as many changes as possible + * before doing the commit. Drivers that will define a commit handler + * are usually those that need a reset after changing parameters, so + * we want to minimise the number of reset. + * A cool idea is to use a timer : at each "set" command, we re-set the + * timer, when the timer eventually fires, we call the driver. + * Hopefully, more on that later. * - * IMPORTANT : This function prevent to set and get data on the same - * IOCTL and enforce the SET/GET convention. Not doing it would be - * far too hairy... - * If you need to set and get data at the same time, please don't use - * a iw_handler but process it in your ioctl handler (i.e. use the - * old driver API). + * Also, I'm waiting to see how many people will complain about the + * netif_running(dev) test. I'm open on that one... + * Hopefully, the driver will remember to do a commit in "open()" ;-) */ -static int get_priv_descr_and_size(struct net_device *dev, unsigned int cmd, - const struct iw_priv_args **descrp) -{ - const struct iw_priv_args *descr; - int i, extra_size; - - descr = NULL; - for (i = 0; i < dev->wireless_handlers->num_private_args; i++) { - if (cmd == dev->wireless_handlers->private_args[i].cmd) { - descr = &dev->wireless_handlers->private_args[i]; - break; - } - } - - extra_size = 0; - if (descr) { - if (IW_IS_SET(cmd)) { - int offset = 0; /* For sub-ioctls */ - /* Check for sub-ioctl handler */ - if (descr->name[0] == '\0') - /* Reserve one int for sub-ioctl index */ - offset = sizeof(__u32); - - /* Size of set arguments */ - extra_size = get_priv_size(descr->set_args); - - /* Does it fits in iwr ? */ - if ((descr->set_args & IW_PRIV_SIZE_FIXED) && - ((extra_size + offset) <= IFNAMSIZ)) - extra_size = 0; - } else { - /* Size of get arguments */ - extra_size = get_priv_size(descr->get_args); - - /* Does it fits in iwr ? */ - if ((descr->get_args & IW_PRIV_SIZE_FIXED) && - (extra_size <= IFNAMSIZ)) - extra_size = 0; - } - } - *descrp = descr; - return extra_size; -} - -static int ioctl_private_iw_point(struct iw_point *iwp, unsigned int cmd, - const struct iw_priv_args *descr, - iw_handler handler, struct net_device *dev, - struct iw_request_info *info, int extra_size) -{ - char *extra; - int err; - - /* Check what user space is giving us */ - if (IW_IS_SET(cmd)) { - if (!iwp->pointer && iwp->length != 0) - return -EFAULT; - - if (iwp->length > (descr->set_args & IW_PRIV_SIZE_MASK)) - return -E2BIG; - } else if (!iwp->pointer) - return -EFAULT; - - extra = kmalloc(extra_size, GFP_KERNEL); - if (!extra) - return -ENOMEM; - - /* If it is a SET, get all the extra data in here */ - if (IW_IS_SET(cmd) && (iwp->length != 0)) { - if (copy_from_user(extra, iwp->pointer, extra_size)) { - err = -EFAULT; - goto out; - } - } - - /* Call the handler */ - err = handler(dev, info, (union iwreq_data *) iwp, extra); - - /* If we have something to return to the user */ - if (!err && IW_IS_GET(cmd)) { - /* Adjust for the actual length if it's variable, - * avoid leaking kernel bits outside. - */ - if (!(descr->get_args & IW_PRIV_SIZE_FIXED)) - extra_size = adjust_priv_size(descr->get_args, iwp); - - if (copy_to_user(iwp->pointer, extra, extra_size)) - err = -EFAULT; - } - -out: - kfree(extra); - return err; -} - -static int ioctl_private_call(struct net_device *dev, struct iwreq *iwr, - unsigned int cmd, struct iw_request_info *info, - iw_handler handler) +int call_commit_handler(struct net_device *dev) { - int extra_size = 0, ret = -EINVAL; - const struct iw_priv_args *descr; - - extra_size = get_priv_descr_and_size(dev, cmd, &descr); - - /* Check if we have a pointer to user space data or not. */ - if (extra_size == 0) { - /* No extra arguments. Trivial to handle */ - ret = handler(dev, info, &(iwr->u), (char *) &(iwr->u)); - } else { - ret = ioctl_private_iw_point(&iwr->u.data, cmd, descr, - handler, dev, info, extra_size); - } - - /* Call commit handler if needed and defined */ - if (ret == -EIWCOMMIT) - ret = call_commit_handler(dev); - - return ret; +#ifdef CONFIG_WIRELESS_EXT + if ((netif_running(dev)) && + (dev->wireless_handlers->standard[0] != NULL)) + /* Call the commit handler on the driver */ + return dev->wireless_handlers->standard[0](dev, NULL, + NULL, NULL); + else + return 0; /* Command completed successfully */ +#else + /* cfg80211 has no commit */ + return 0; +#endif } -/* ---------------------------------------------------------------- */ -typedef int (*wext_ioctl_func)(struct net_device *, struct iwreq *, - unsigned int, struct iw_request_info *, - iw_handler); - /* * Main IOCTl dispatcher. * Check the type of IOCTL and call the appropriate wrapper... @@ -1103,9 +881,11 @@ static int wireless_process_ioctl(struct net *net, struct ifreq *ifr, return standard(dev, iwr, cmd, info, &iw_handler_get_iwstats); +#ifdef CONFIG_WEXT_PRIV if (cmd == SIOCGIWPRIV && dev->wireless_handlers) return standard(dev, iwr, cmd, info, - &iw_handler_get_private); + iw_handler_get_private); +#endif /* Basic check */ if (!netif_device_present(dev)) @@ -1117,7 +897,7 @@ static int wireless_process_ioctl(struct net *net, struct ifreq *ifr, /* Standard and private are not the same */ if (cmd < SIOCIWFIRSTPRIV) return standard(dev, iwr, cmd, info, handler); - else + else if (private) return private(dev, iwr, cmd, info, handler); } /* Old driver API : call driver ioctl handler */ @@ -1157,6 +937,50 @@ static int wext_ioctl_dispatch(struct net *net, struct ifreq *ifr, return ret; } +/* + * Wrapper to call a standard Wireless Extension handler. + * We do various checks and also take care of moving data between + * user space and kernel space. + */ +static int ioctl_standard_call(struct net_device * dev, + struct iwreq *iwr, + unsigned int cmd, + struct iw_request_info *info, + iw_handler handler) +{ + const struct iw_ioctl_description * descr; + int ret = -EINVAL; + + /* Get the description of the IOCTL */ + if ((cmd - SIOCIWFIRST) >= standard_ioctl_num) + return -EOPNOTSUPP; + descr = &(standard_ioctl[cmd - SIOCIWFIRST]); + + /* Check if we have a pointer to user space data or not */ + if (descr->header_type != IW_HEADER_TYPE_POINT) { + + /* No extra arguments. Trivial to handle */ + ret = handler(dev, info, &(iwr->u), NULL); + + /* Generate an event to notify listeners of the change */ + if ((descr->flags & IW_DESCR_FLAG_EVENT) && + ((ret == 0) || (ret == -EIWCOMMIT))) + wireless_send_event(dev, cmd, &(iwr->u), NULL); + } else { + ret = ioctl_standard_iw_point(&iwr->u.data, cmd, descr, + handler, dev, info); + } + + /* Call commit handler if needed and defined */ + if (ret == -EIWCOMMIT) + ret = call_commit_handler(dev); + + /* Here, we will generate the appropriate event if needed */ + + return ret; +} + + int wext_handle_ioctl(struct net *net, struct ifreq *ifr, unsigned int cmd, void __user *arg) { @@ -1205,43 +1029,6 @@ static int compat_standard_call(struct net_device *dev, return err; } -static int compat_private_call(struct net_device *dev, struct iwreq *iwr, - unsigned int cmd, struct iw_request_info *info, - iw_handler handler) -{ - const struct iw_priv_args *descr; - int ret, extra_size; - - extra_size = get_priv_descr_and_size(dev, cmd, &descr); - - /* Check if we have a pointer to user space data or not. */ - if (extra_size == 0) { - /* No extra arguments. Trivial to handle */ - ret = handler(dev, info, &(iwr->u), (char *) &(iwr->u)); - } else { - struct compat_iw_point *iwp_compat; - struct iw_point iwp; - - iwp_compat = (struct compat_iw_point *) &iwr->u.data; - iwp.pointer = compat_ptr(iwp_compat->pointer); - iwp.length = iwp_compat->length; - iwp.flags = iwp_compat->flags; - - ret = ioctl_private_iw_point(&iwp, cmd, descr, - handler, dev, info, extra_size); - - iwp_compat->pointer = ptr_to_compat(iwp.pointer); - iwp_compat->length = iwp.length; - iwp_compat->flags = iwp.flags; - } - - /* Call commit handler if needed and defined */ - if (ret == -EIWCOMMIT) - ret = call_commit_handler(dev); - - return ret; -} - int compat_wext_handle_ioctl(struct net *net, unsigned int cmd, unsigned long arg) { @@ -1274,502 +1061,3 @@ int compat_wext_handle_ioctl(struct net *net, unsigned int cmd, return ret; } #endif - -static int __net_init wext_pernet_init(struct net *net) -{ - skb_queue_head_init(&net->wext_nlevents); - return 0; -} - -static void __net_exit wext_pernet_exit(struct net *net) -{ - skb_queue_purge(&net->wext_nlevents); -} - -static struct pernet_operations wext_pernet_ops = { - .init = wext_pernet_init, - .exit = wext_pernet_exit, -}; - -static int __init wireless_nlevent_init(void) -{ - return register_pernet_subsys(&wext_pernet_ops); -} - -subsys_initcall(wireless_nlevent_init); - -/* Process events generated by the wireless layer or the driver. */ -static void wireless_nlevent_process(struct work_struct *work) -{ - struct sk_buff *skb; - struct net *net; - - rtnl_lock(); - - for_each_net(net) { - while ((skb = skb_dequeue(&net->wext_nlevents))) - rtnl_notify(skb, net, 0, RTNLGRP_LINK, NULL, - GFP_KERNEL); - } - - rtnl_unlock(); -} - -static DECLARE_WORK(wireless_nlevent_work, wireless_nlevent_process); - -static struct nlmsghdr *rtnetlink_ifinfo_prep(struct net_device *dev, - struct sk_buff *skb) -{ - struct ifinfomsg *r; - struct nlmsghdr *nlh; - - nlh = nlmsg_put(skb, 0, 0, RTM_NEWLINK, sizeof(*r), 0); - if (!nlh) - return NULL; - - r = nlmsg_data(nlh); - r->ifi_family = AF_UNSPEC; - r->__ifi_pad = 0; - r->ifi_type = dev->type; - r->ifi_index = dev->ifindex; - r->ifi_flags = dev_get_flags(dev); - r->ifi_change = 0; /* Wireless changes don't affect those flags */ - - NLA_PUT_STRING(skb, IFLA_IFNAME, dev->name); - - return nlh; - nla_put_failure: - nlmsg_cancel(skb, nlh); - return NULL; -} - - -/* - * Main event dispatcher. Called from other parts and drivers. - * Send the event on the appropriate channels. - * May be called from interrupt context. - */ -void wireless_send_event(struct net_device * dev, - unsigned int cmd, - union iwreq_data * wrqu, - const char * extra) -{ - const struct iw_ioctl_description * descr = NULL; - int extra_len = 0; - struct iw_event *event; /* Mallocated whole event */ - int event_len; /* Its size */ - int hdr_len; /* Size of the event header */ - int wrqu_off = 0; /* Offset in wrqu */ - /* Don't "optimise" the following variable, it will crash */ - unsigned cmd_index; /* *MUST* be unsigned */ - struct sk_buff *skb; - struct nlmsghdr *nlh; - struct nlattr *nla; -#ifdef CONFIG_COMPAT - struct __compat_iw_event *compat_event; - struct compat_iw_point compat_wrqu; - struct sk_buff *compskb; -#endif - - /* - * Nothing in the kernel sends scan events with data, be safe. - * This is necessary because we cannot fix up scan event data - * for compat, due to being contained in 'extra', but normally - * applications are required to retrieve the scan data anyway - * and no data is included in the event, this codifies that - * practice. - */ - if (WARN_ON(cmd == SIOCGIWSCAN && extra)) - extra = NULL; - - /* Get the description of the Event */ - if (cmd <= SIOCIWLAST) { - cmd_index = cmd - SIOCIWFIRST; - if (cmd_index < standard_ioctl_num) - descr = &(standard_ioctl[cmd_index]); - } else { - cmd_index = cmd - IWEVFIRST; - if (cmd_index < standard_event_num) - descr = &(standard_event[cmd_index]); - } - /* Don't accept unknown events */ - if (descr == NULL) { - /* Note : we don't return an error to the driver, because - * the driver would not know what to do about it. It can't - * return an error to the user, because the event is not - * initiated by a user request. - * The best the driver could do is to log an error message. - * We will do it ourselves instead... - */ - printk(KERN_ERR "%s (WE) : Invalid/Unknown Wireless Event (0x%04X)\n", - dev->name, cmd); - return; - } - - /* Check extra parameters and set extra_len */ - if (descr->header_type == IW_HEADER_TYPE_POINT) { - /* Check if number of token fits within bounds */ - if (wrqu->data.length > descr->max_tokens) { - printk(KERN_ERR "%s (WE) : Wireless Event too big (%d)\n", dev->name, wrqu->data.length); - return; - } - if (wrqu->data.length < descr->min_tokens) { - printk(KERN_ERR "%s (WE) : Wireless Event too small (%d)\n", dev->name, wrqu->data.length); - return; - } - /* Calculate extra_len - extra is NULL for restricted events */ - if (extra != NULL) - extra_len = wrqu->data.length * descr->token_size; - /* Always at an offset in wrqu */ - wrqu_off = IW_EV_POINT_OFF; - } - - /* Total length of the event */ - hdr_len = event_type_size[descr->header_type]; - event_len = hdr_len + extra_len; - - /* - * The problem for 64/32 bit. - * - * On 64-bit, a regular event is laid out as follows: - * | 0 | 1 | 2 | 3 | 4 | 5 | 6 | 7 | - * | event.len | event.cmd | p a d d i n g | - * | wrqu data ... (with the correct size) | - * - * This padding exists because we manipulate event->u, - * and 'event' is not packed. - * - * An iw_point event is laid out like this instead: - * | 0 | 1 | 2 | 3 | 4 | 5 | 6 | 7 | - * | event.len | event.cmd | p a d d i n g | - * | iwpnt.len | iwpnt.flg | p a d d i n g | - * | extra data ... - * - * The second padding exists because struct iw_point is extended, - * but this depends on the platform... - * - * On 32-bit, all the padding shouldn't be there. - */ - - skb = nlmsg_new(NLMSG_DEFAULT_SIZE, GFP_ATOMIC); - if (!skb) - return; - - /* Send via the RtNetlink event channel */ - nlh = rtnetlink_ifinfo_prep(dev, skb); - if (WARN_ON(!nlh)) { - kfree_skb(skb); - return; - } - - /* Add the wireless events in the netlink packet */ - nla = nla_reserve(skb, IFLA_WIRELESS, event_len); - if (!nla) { - kfree_skb(skb); - return; - } - event = nla_data(nla); - - /* Fill event - first clear to avoid data leaking */ - memset(event, 0, hdr_len); - event->len = event_len; - event->cmd = cmd; - memcpy(&event->u, ((char *) wrqu) + wrqu_off, hdr_len - IW_EV_LCP_LEN); - if (extra_len) - memcpy(((char *) event) + hdr_len, extra, extra_len); - - nlmsg_end(skb, nlh); -#ifdef CONFIG_COMPAT - hdr_len = compat_event_type_size[descr->header_type]; - event_len = hdr_len + extra_len; - - compskb = nlmsg_new(NLMSG_DEFAULT_SIZE, GFP_ATOMIC); - if (!compskb) { - kfree_skb(skb); - return; - } - - /* Send via the RtNetlink event channel */ - nlh = rtnetlink_ifinfo_prep(dev, compskb); - if (WARN_ON(!nlh)) { - kfree_skb(skb); - kfree_skb(compskb); - return; - } - - /* Add the wireless events in the netlink packet */ - nla = nla_reserve(compskb, IFLA_WIRELESS, event_len); - if (!nla) { - kfree_skb(skb); - kfree_skb(compskb); - return; - } - compat_event = nla_data(nla); - - compat_event->len = event_len; - compat_event->cmd = cmd; - if (descr->header_type == IW_HEADER_TYPE_POINT) { - compat_wrqu.length = wrqu->data.length; - compat_wrqu.flags = wrqu->data.flags; - memcpy(&compat_event->pointer, - ((char *) &compat_wrqu) + IW_EV_COMPAT_POINT_OFF, - hdr_len - IW_EV_COMPAT_LCP_LEN); - if (extra_len) - memcpy(((char *) compat_event) + hdr_len, - extra, extra_len); - } else { - /* extra_len must be zero, so no if (extra) needed */ - memcpy(&compat_event->pointer, wrqu, - hdr_len - IW_EV_COMPAT_LCP_LEN); - } - - nlmsg_end(compskb, nlh); - - skb_shinfo(skb)->frag_list = compskb; -#endif - skb_queue_tail(&dev_net(dev)->wext_nlevents, skb); - schedule_work(&wireless_nlevent_work); -} -EXPORT_SYMBOL(wireless_send_event); - -/********************** ENHANCED IWSPY SUPPORT **********************/ -/* - * In the old days, the driver was handling spy support all by itself. - * Now, the driver can delegate this task to Wireless Extensions. - * It needs to use those standard spy iw_handler in struct iw_handler_def, - * push data to us via wireless_spy_update() and include struct iw_spy_data - * in its private part (and export it in net_device->wireless_data->spy_data). - * One of the main advantage of centralising spy support here is that - * it becomes much easier to improve and extend it without having to touch - * the drivers. One example is the addition of the Spy-Threshold events. - */ - -/* ---------------------------------------------------------------- */ -/* - * Return the pointer to the spy data in the driver. - * Because this is called on the Rx path via wireless_spy_update(), - * we want it to be efficient... - */ -static inline struct iw_spy_data *get_spydata(struct net_device *dev) -{ - /* This is the new way */ - if (dev->wireless_data) - return dev->wireless_data->spy_data; - return NULL; -} - -/*------------------------------------------------------------------*/ -/* - * Standard Wireless Handler : set Spy List - */ -int iw_handler_set_spy(struct net_device * dev, - struct iw_request_info * info, - union iwreq_data * wrqu, - char * extra) -{ - struct iw_spy_data * spydata = get_spydata(dev); - struct sockaddr * address = (struct sockaddr *) extra; - - /* Make sure driver is not buggy or using the old API */ - if (!spydata) - return -EOPNOTSUPP; - - /* Disable spy collection while we copy the addresses. - * While we copy addresses, any call to wireless_spy_update() - * will NOP. This is OK, as anyway the addresses are changing. */ - spydata->spy_number = 0; - - /* We want to operate without locking, because wireless_spy_update() - * most likely will happen in the interrupt handler, and therefore - * have its own locking constraints and needs performance. - * The rtnl_lock() make sure we don't race with the other iw_handlers. - * This make sure wireless_spy_update() "see" that the spy list - * is temporarily disabled. */ - smp_wmb(); - - /* Are there are addresses to copy? */ - if (wrqu->data.length > 0) { - int i; - - /* Copy addresses */ - for (i = 0; i < wrqu->data.length; i++) - memcpy(spydata->spy_address[i], address[i].sa_data, - ETH_ALEN); - /* Reset stats */ - memset(spydata->spy_stat, 0, - sizeof(struct iw_quality) * IW_MAX_SPY); - } - - /* Make sure above is updated before re-enabling */ - smp_wmb(); - - /* Enable addresses */ - spydata->spy_number = wrqu->data.length; - - return 0; -} -EXPORT_SYMBOL(iw_handler_set_spy); - -/*------------------------------------------------------------------*/ -/* - * Standard Wireless Handler : get Spy List - */ -int iw_handler_get_spy(struct net_device * dev, - struct iw_request_info * info, - union iwreq_data * wrqu, - char * extra) -{ - struct iw_spy_data * spydata = get_spydata(dev); - struct sockaddr * address = (struct sockaddr *) extra; - int i; - - /* Make sure driver is not buggy or using the old API */ - if (!spydata) - return -EOPNOTSUPP; - - wrqu->data.length = spydata->spy_number; - - /* Copy addresses. */ - for (i = 0; i < spydata->spy_number; i++) { - memcpy(address[i].sa_data, spydata->spy_address[i], ETH_ALEN); - address[i].sa_family = AF_UNIX; - } - /* Copy stats to the user buffer (just after). */ - if (spydata->spy_number > 0) - memcpy(extra + (sizeof(struct sockaddr) *spydata->spy_number), - spydata->spy_stat, - sizeof(struct iw_quality) * spydata->spy_number); - /* Reset updated flags. */ - for (i = 0; i < spydata->spy_number; i++) - spydata->spy_stat[i].updated &= ~IW_QUAL_ALL_UPDATED; - return 0; -} -EXPORT_SYMBOL(iw_handler_get_spy); - -/*------------------------------------------------------------------*/ -/* - * Standard Wireless Handler : set spy threshold - */ -int iw_handler_set_thrspy(struct net_device * dev, - struct iw_request_info *info, - union iwreq_data * wrqu, - char * extra) -{ - struct iw_spy_data * spydata = get_spydata(dev); - struct iw_thrspy * threshold = (struct iw_thrspy *) extra; - - /* Make sure driver is not buggy or using the old API */ - if (!spydata) - return -EOPNOTSUPP; - - /* Just do it */ - memcpy(&(spydata->spy_thr_low), &(threshold->low), - 2 * sizeof(struct iw_quality)); - - /* Clear flag */ - memset(spydata->spy_thr_under, '\0', sizeof(spydata->spy_thr_under)); - - return 0; -} -EXPORT_SYMBOL(iw_handler_set_thrspy); - -/*------------------------------------------------------------------*/ -/* - * Standard Wireless Handler : get spy threshold - */ -int iw_handler_get_thrspy(struct net_device * dev, - struct iw_request_info *info, - union iwreq_data * wrqu, - char * extra) -{ - struct iw_spy_data * spydata = get_spydata(dev); - struct iw_thrspy * threshold = (struct iw_thrspy *) extra; - - /* Make sure driver is not buggy or using the old API */ - if (!spydata) - return -EOPNOTSUPP; - - /* Just do it */ - memcpy(&(threshold->low), &(spydata->spy_thr_low), - 2 * sizeof(struct iw_quality)); - - return 0; -} -EXPORT_SYMBOL(iw_handler_get_thrspy); - -/*------------------------------------------------------------------*/ -/* - * Prepare and send a Spy Threshold event - */ -static void iw_send_thrspy_event(struct net_device * dev, - struct iw_spy_data * spydata, - unsigned char * address, - struct iw_quality * wstats) -{ - union iwreq_data wrqu; - struct iw_thrspy threshold; - - /* Init */ - wrqu.data.length = 1; - wrqu.data.flags = 0; - /* Copy address */ - memcpy(threshold.addr.sa_data, address, ETH_ALEN); - threshold.addr.sa_family = ARPHRD_ETHER; - /* Copy stats */ - memcpy(&(threshold.qual), wstats, sizeof(struct iw_quality)); - /* Copy also thresholds */ - memcpy(&(threshold.low), &(spydata->spy_thr_low), - 2 * sizeof(struct iw_quality)); - - /* Send event to user space */ - wireless_send_event(dev, SIOCGIWTHRSPY, &wrqu, (char *) &threshold); -} - -/* ---------------------------------------------------------------- */ -/* - * Call for the driver to update the spy data. - * For now, the spy data is a simple array. As the size of the array is - * small, this is good enough. If we wanted to support larger number of - * spy addresses, we should use something more efficient... - */ -void wireless_spy_update(struct net_device * dev, - unsigned char * address, - struct iw_quality * wstats) -{ - struct iw_spy_data * spydata = get_spydata(dev); - int i; - int match = -1; - - /* Make sure driver is not buggy or using the old API */ - if (!spydata) - return; - - /* Update all records that match */ - for (i = 0; i < spydata->spy_number; i++) - if (!compare_ether_addr(address, spydata->spy_address[i])) { - memcpy(&(spydata->spy_stat[i]), wstats, - sizeof(struct iw_quality)); - match = i; - } - - /* Generate an event if we cross the spy threshold. - * To avoid event storms, we have a simple hysteresis : we generate - * event only when we go under the low threshold or above the - * high threshold. */ - if (match >= 0) { - if (spydata->spy_thr_under[match]) { - if (wstats->level > spydata->spy_thr_high.level) { - spydata->spy_thr_under[match] = 0; - iw_send_thrspy_event(dev, spydata, - address, wstats); - } - } else { - if (wstats->level < spydata->spy_thr_low.level) { - spydata->spy_thr_under[match] = 1; - iw_send_thrspy_event(dev, spydata, - address, wstats); - } - } - } -} -EXPORT_SYMBOL(wireless_spy_update); diff --git a/net/wireless/wext-priv.c b/net/wireless/wext-priv.c new file mode 100644 index 00000000000..a3c2277de9e --- /dev/null +++ b/net/wireless/wext-priv.c @@ -0,0 +1,248 @@ +/* + * This file implement the Wireless Extensions priv API. + * + * Authors : Jean Tourrilhes - HPL - <jt@hpl.hp.com> + * Copyright (c) 1997-2007 Jean Tourrilhes, All Rights Reserved. + * Copyright 2009 Johannes Berg <johannes@sipsolutions.net> + * + * (As all part of the Linux kernel, this file is GPL) + */ +#include <linux/wireless.h> +#include <linux/netdevice.h> +#include <net/iw_handler.h> +#include <net/wext.h> + +int iw_handler_get_private(struct net_device * dev, + struct iw_request_info * info, + union iwreq_data * wrqu, + char * extra) +{ + /* Check if the driver has something to export */ + if ((dev->wireless_handlers->num_private_args == 0) || + (dev->wireless_handlers->private_args == NULL)) + return -EOPNOTSUPP; + + /* Check if there is enough buffer up there */ + if (wrqu->data.length < dev->wireless_handlers->num_private_args) { + /* User space can't know in advance how large the buffer + * needs to be. Give it a hint, so that we can support + * any size buffer we want somewhat efficiently... */ + wrqu->data.length = dev->wireless_handlers->num_private_args; + return -E2BIG; + } + + /* Set the number of available ioctls. */ + wrqu->data.length = dev->wireless_handlers->num_private_args; + + /* Copy structure to the user buffer. */ + memcpy(extra, dev->wireless_handlers->private_args, + sizeof(struct iw_priv_args) * wrqu->data.length); + + return 0; +} + +/* Size (in bytes) of the various private data types */ +static const char iw_priv_type_size[] = { + 0, /* IW_PRIV_TYPE_NONE */ + 1, /* IW_PRIV_TYPE_BYTE */ + 1, /* IW_PRIV_TYPE_CHAR */ + 0, /* Not defined */ + sizeof(__u32), /* IW_PRIV_TYPE_INT */ + sizeof(struct iw_freq), /* IW_PRIV_TYPE_FLOAT */ + sizeof(struct sockaddr), /* IW_PRIV_TYPE_ADDR */ + 0, /* Not defined */ +}; + +static int get_priv_size(__u16 args) +{ + int num = args & IW_PRIV_SIZE_MASK; + int type = (args & IW_PRIV_TYPE_MASK) >> 12; + + return num * iw_priv_type_size[type]; +} + +static int adjust_priv_size(__u16 args, struct iw_point *iwp) +{ + int num = iwp->length; + int max = args & IW_PRIV_SIZE_MASK; + int type = (args & IW_PRIV_TYPE_MASK) >> 12; + + /* Make sure the driver doesn't goof up */ + if (max < num) + num = max; + + return num * iw_priv_type_size[type]; +} + +/* + * Wrapper to call a private Wireless Extension handler. + * We do various checks and also take care of moving data between + * user space and kernel space. + * It's not as nice and slimline as the standard wrapper. The cause + * is struct iw_priv_args, which was not really designed for the + * job we are going here. + * + * IMPORTANT : This function prevent to set and get data on the same + * IOCTL and enforce the SET/GET convention. Not doing it would be + * far too hairy... + * If you need to set and get data at the same time, please don't use + * a iw_handler but process it in your ioctl handler (i.e. use the + * old driver API). + */ +static int get_priv_descr_and_size(struct net_device *dev, unsigned int cmd, + const struct iw_priv_args **descrp) +{ + const struct iw_priv_args *descr; + int i, extra_size; + + descr = NULL; + for (i = 0; i < dev->wireless_handlers->num_private_args; i++) { + if (cmd == dev->wireless_handlers->private_args[i].cmd) { + descr = &dev->wireless_handlers->private_args[i]; + break; + } + } + + extra_size = 0; + if (descr) { + if (IW_IS_SET(cmd)) { + int offset = 0; /* For sub-ioctls */ + /* Check for sub-ioctl handler */ + if (descr->name[0] == '\0') + /* Reserve one int for sub-ioctl index */ + offset = sizeof(__u32); + + /* Size of set arguments */ + extra_size = get_priv_size(descr->set_args); + + /* Does it fits in iwr ? */ + if ((descr->set_args & IW_PRIV_SIZE_FIXED) && + ((extra_size + offset) <= IFNAMSIZ)) + extra_size = 0; + } else { + /* Size of get arguments */ + extra_size = get_priv_size(descr->get_args); + + /* Does it fits in iwr ? */ + if ((descr->get_args & IW_PRIV_SIZE_FIXED) && + (extra_size <= IFNAMSIZ)) + extra_size = 0; + } + } + *descrp = descr; + return extra_size; +} + +static int ioctl_private_iw_point(struct iw_point *iwp, unsigned int cmd, + const struct iw_priv_args *descr, + iw_handler handler, struct net_device *dev, + struct iw_request_info *info, int extra_size) +{ + char *extra; + int err; + + /* Check what user space is giving us */ + if (IW_IS_SET(cmd)) { + if (!iwp->pointer && iwp->length != 0) + return -EFAULT; + + if (iwp->length > (descr->set_args & IW_PRIV_SIZE_MASK)) + return -E2BIG; + } else if (!iwp->pointer) + return -EFAULT; + + extra = kmalloc(extra_size, GFP_KERNEL); + if (!extra) + return -ENOMEM; + + /* If it is a SET, get all the extra data in here */ + if (IW_IS_SET(cmd) && (iwp->length != 0)) { + if (copy_from_user(extra, iwp->pointer, extra_size)) { + err = -EFAULT; + goto out; + } + } + + /* Call the handler */ + err = handler(dev, info, (union iwreq_data *) iwp, extra); + + /* If we have something to return to the user */ + if (!err && IW_IS_GET(cmd)) { + /* Adjust for the actual length if it's variable, + * avoid leaking kernel bits outside. + */ + if (!(descr->get_args & IW_PRIV_SIZE_FIXED)) + extra_size = adjust_priv_size(descr->get_args, iwp); + + if (copy_to_user(iwp->pointer, extra, extra_size)) + err = -EFAULT; + } + +out: + kfree(extra); + return err; +} + +int ioctl_private_call(struct net_device *dev, struct iwreq *iwr, + unsigned int cmd, struct iw_request_info *info, + iw_handler handler) +{ + int extra_size = 0, ret = -EINVAL; + const struct iw_priv_args *descr; + + extra_size = get_priv_descr_and_size(dev, cmd, &descr); + + /* Check if we have a pointer to user space data or not. */ + if (extra_size == 0) { + /* No extra arguments. Trivial to handle */ + ret = handler(dev, info, &(iwr->u), (char *) &(iwr->u)); + } else { + ret = ioctl_private_iw_point(&iwr->u.data, cmd, descr, + handler, dev, info, extra_size); + } + + /* Call commit handler if needed and defined */ + if (ret == -EIWCOMMIT) + ret = call_commit_handler(dev); + + return ret; +} + +#ifdef CONFIG_COMPAT +int compat_private_call(struct net_device *dev, struct iwreq *iwr, + unsigned int cmd, struct iw_request_info *info, + iw_handler handler) +{ + const struct iw_priv_args *descr; + int ret, extra_size; + + extra_size = get_priv_descr_and_size(dev, cmd, &descr); + + /* Check if we have a pointer to user space data or not. */ + if (extra_size == 0) { + /* No extra arguments. Trivial to handle */ + ret = handler(dev, info, &(iwr->u), (char *) &(iwr->u)); + } else { + struct compat_iw_point *iwp_compat; + struct iw_point iwp; + + iwp_compat = (struct compat_iw_point *) &iwr->u.data; + iwp.pointer = compat_ptr(iwp_compat->pointer); + iwp.length = iwp_compat->length; + iwp.flags = iwp_compat->flags; + + ret = ioctl_private_iw_point(&iwp, cmd, descr, + handler, dev, info, extra_size); + + iwp_compat->pointer = ptr_to_compat(iwp.pointer); + iwp_compat->length = iwp.length; + iwp_compat->flags = iwp.flags; + } + + /* Call commit handler if needed and defined */ + if (ret == -EIWCOMMIT) + ret = call_commit_handler(dev); + + return ret; +} +#endif diff --git a/net/wireless/wext-proc.c b/net/wireless/wext-proc.c new file mode 100644 index 00000000000..273a7f77c83 --- /dev/null +++ b/net/wireless/wext-proc.c @@ -0,0 +1,155 @@ +/* + * This file implement the Wireless Extensions proc API. + * + * Authors : Jean Tourrilhes - HPL - <jt@hpl.hp.com> + * Copyright (c) 1997-2007 Jean Tourrilhes, All Rights Reserved. + * + * (As all part of the Linux kernel, this file is GPL) + */ + +/* + * The /proc/net/wireless file is a human readable user-space interface + * exporting various wireless specific statistics from the wireless devices. + * This is the most popular part of the Wireless Extensions ;-) + * + * This interface is a pure clone of /proc/net/dev (in net/core/dev.c). + * The content of the file is basically the content of "struct iw_statistics". + */ + +#include <linux/module.h> +#include <linux/proc_fs.h> +#include <linux/seq_file.h> +#include <linux/wireless.h> +#include <linux/netdevice.h> +#include <linux/rtnetlink.h> +#include <net/iw_handler.h> +#include <net/wext.h> + + +static void wireless_seq_printf_stats(struct seq_file *seq, + struct net_device *dev) +{ + /* Get stats from the driver */ + struct iw_statistics *stats = get_wireless_stats(dev); + static struct iw_statistics nullstats = {}; + + /* show device if it's wireless regardless of current stats */ + if (!stats) { +#ifdef CONFIG_WIRELESS_EXT + if (dev->wireless_handlers) + stats = &nullstats; +#endif +#ifdef CONFIG_CFG80211 + if (dev->ieee80211_ptr) + stats = &nullstats; +#endif + } + + if (stats) { + seq_printf(seq, "%6s: %04x %3d%c %3d%c %3d%c %6d %6d %6d " + "%6d %6d %6d\n", + dev->name, stats->status, stats->qual.qual, + stats->qual.updated & IW_QUAL_QUAL_UPDATED + ? '.' : ' ', + ((__s32) stats->qual.level) - + ((stats->qual.updated & IW_QUAL_DBM) ? 0x100 : 0), + stats->qual.updated & IW_QUAL_LEVEL_UPDATED + ? '.' : ' ', + ((__s32) stats->qual.noise) - + ((stats->qual.updated & IW_QUAL_DBM) ? 0x100 : 0), + stats->qual.updated & IW_QUAL_NOISE_UPDATED + ? '.' : ' ', + stats->discard.nwid, stats->discard.code, + stats->discard.fragment, stats->discard.retries, + stats->discard.misc, stats->miss.beacon); + + if (stats != &nullstats) + stats->qual.updated &= ~IW_QUAL_ALL_UPDATED; + } +} + +/* ---------------------------------------------------------------- */ +/* + * Print info for /proc/net/wireless (print all entries) + */ +static int wireless_dev_seq_show(struct seq_file *seq, void *v) +{ + might_sleep(); + + if (v == SEQ_START_TOKEN) + seq_printf(seq, "Inter-| sta-| Quality | Discarded " + "packets | Missed | WE\n" + " face | tus | link level noise | nwid " + "crypt frag retry misc | beacon | %d\n", + WIRELESS_EXT); + else + wireless_seq_printf_stats(seq, v); + return 0; +} + +static void *wireless_dev_seq_start(struct seq_file *seq, loff_t *pos) +{ + struct net *net = seq_file_net(seq); + loff_t off; + struct net_device *dev; + + rtnl_lock(); + if (!*pos) + return SEQ_START_TOKEN; + + off = 1; + for_each_netdev(net, dev) + if (off++ == *pos) + return dev; + return NULL; +} + +static void *wireless_dev_seq_next(struct seq_file *seq, void *v, loff_t *pos) +{ + struct net *net = seq_file_net(seq); + + ++*pos; + + return v == SEQ_START_TOKEN ? + first_net_device(net) : next_net_device(v); +} + +static void wireless_dev_seq_stop(struct seq_file *seq, void *v) +{ + rtnl_unlock(); +} + +static const struct seq_operations wireless_seq_ops = { + .start = wireless_dev_seq_start, + .next = wireless_dev_seq_next, + .stop = wireless_dev_seq_stop, + .show = wireless_dev_seq_show, +}; + +static int seq_open_wireless(struct inode *inode, struct file *file) +{ + return seq_open_net(inode, file, &wireless_seq_ops, + sizeof(struct seq_net_private)); +} + +static const struct file_operations wireless_seq_fops = { + .owner = THIS_MODULE, + .open = seq_open_wireless, + .read = seq_read, + .llseek = seq_lseek, + .release = seq_release_net, +}; + +int wext_proc_init(struct net *net) +{ + /* Create /proc/net/wireless entry */ + if (!proc_net_fops_create(net, "wireless", S_IRUGO, &wireless_seq_fops)) + return -ENOMEM; + + return 0; +} + +void wext_proc_exit(struct net *net) +{ + proc_net_remove(net, "wireless"); +} diff --git a/net/wireless/wext-spy.c b/net/wireless/wext-spy.c new file mode 100644 index 00000000000..6dcfe65a2d1 --- /dev/null +++ b/net/wireless/wext-spy.c @@ -0,0 +1,231 @@ +/* + * This file implement the Wireless Extensions spy API. + * + * Authors : Jean Tourrilhes - HPL - <jt@hpl.hp.com> + * Copyright (c) 1997-2007 Jean Tourrilhes, All Rights Reserved. + * + * (As all part of the Linux kernel, this file is GPL) + */ + +#include <linux/wireless.h> +#include <linux/netdevice.h> +#include <linux/etherdevice.h> +#include <net/iw_handler.h> +#include <net/arp.h> +#include <net/wext.h> + +static inline struct iw_spy_data *get_spydata(struct net_device *dev) +{ + /* This is the new way */ + if (dev->wireless_data) + return dev->wireless_data->spy_data; + return NULL; +} + +int iw_handler_set_spy(struct net_device * dev, + struct iw_request_info * info, + union iwreq_data * wrqu, + char * extra) +{ + struct iw_spy_data * spydata = get_spydata(dev); + struct sockaddr * address = (struct sockaddr *) extra; + + /* Make sure driver is not buggy or using the old API */ + if (!spydata) + return -EOPNOTSUPP; + + /* Disable spy collection while we copy the addresses. + * While we copy addresses, any call to wireless_spy_update() + * will NOP. This is OK, as anyway the addresses are changing. */ + spydata->spy_number = 0; + + /* We want to operate without locking, because wireless_spy_update() + * most likely will happen in the interrupt handler, and therefore + * have its own locking constraints and needs performance. + * The rtnl_lock() make sure we don't race with the other iw_handlers. + * This make sure wireless_spy_update() "see" that the spy list + * is temporarily disabled. */ + smp_wmb(); + + /* Are there are addresses to copy? */ + if (wrqu->data.length > 0) { + int i; + + /* Copy addresses */ + for (i = 0; i < wrqu->data.length; i++) + memcpy(spydata->spy_address[i], address[i].sa_data, + ETH_ALEN); + /* Reset stats */ + memset(spydata->spy_stat, 0, + sizeof(struct iw_quality) * IW_MAX_SPY); + } + + /* Make sure above is updated before re-enabling */ + smp_wmb(); + + /* Enable addresses */ + spydata->spy_number = wrqu->data.length; + + return 0; +} +EXPORT_SYMBOL(iw_handler_set_spy); + +int iw_handler_get_spy(struct net_device * dev, + struct iw_request_info * info, + union iwreq_data * wrqu, + char * extra) +{ + struct iw_spy_data * spydata = get_spydata(dev); + struct sockaddr * address = (struct sockaddr *) extra; + int i; + + /* Make sure driver is not buggy or using the old API */ + if (!spydata) + return -EOPNOTSUPP; + + wrqu->data.length = spydata->spy_number; + + /* Copy addresses. */ + for (i = 0; i < spydata->spy_number; i++) { + memcpy(address[i].sa_data, spydata->spy_address[i], ETH_ALEN); + address[i].sa_family = AF_UNIX; + } + /* Copy stats to the user buffer (just after). */ + if (spydata->spy_number > 0) + memcpy(extra + (sizeof(struct sockaddr) *spydata->spy_number), + spydata->spy_stat, + sizeof(struct iw_quality) * spydata->spy_number); + /* Reset updated flags. */ + for (i = 0; i < spydata->spy_number; i++) + spydata->spy_stat[i].updated &= ~IW_QUAL_ALL_UPDATED; + return 0; +} +EXPORT_SYMBOL(iw_handler_get_spy); + +/*------------------------------------------------------------------*/ +/* + * Standard Wireless Handler : set spy threshold + */ +int iw_handler_set_thrspy(struct net_device * dev, + struct iw_request_info *info, + union iwreq_data * wrqu, + char * extra) +{ + struct iw_spy_data * spydata = get_spydata(dev); + struct iw_thrspy * threshold = (struct iw_thrspy *) extra; + + /* Make sure driver is not buggy or using the old API */ + if (!spydata) + return -EOPNOTSUPP; + + /* Just do it */ + memcpy(&(spydata->spy_thr_low), &(threshold->low), + 2 * sizeof(struct iw_quality)); + + /* Clear flag */ + memset(spydata->spy_thr_under, '\0', sizeof(spydata->spy_thr_under)); + + return 0; +} +EXPORT_SYMBOL(iw_handler_set_thrspy); + +/*------------------------------------------------------------------*/ +/* + * Standard Wireless Handler : get spy threshold + */ +int iw_handler_get_thrspy(struct net_device * dev, + struct iw_request_info *info, + union iwreq_data * wrqu, + char * extra) +{ + struct iw_spy_data * spydata = get_spydata(dev); + struct iw_thrspy * threshold = (struct iw_thrspy *) extra; + + /* Make sure driver is not buggy or using the old API */ + if (!spydata) + return -EOPNOTSUPP; + + /* Just do it */ + memcpy(&(threshold->low), &(spydata->spy_thr_low), + 2 * sizeof(struct iw_quality)); + + return 0; +} +EXPORT_SYMBOL(iw_handler_get_thrspy); + +/*------------------------------------------------------------------*/ +/* + * Prepare and send a Spy Threshold event + */ +static void iw_send_thrspy_event(struct net_device * dev, + struct iw_spy_data * spydata, + unsigned char * address, + struct iw_quality * wstats) +{ + union iwreq_data wrqu; + struct iw_thrspy threshold; + + /* Init */ + wrqu.data.length = 1; + wrqu.data.flags = 0; + /* Copy address */ + memcpy(threshold.addr.sa_data, address, ETH_ALEN); + threshold.addr.sa_family = ARPHRD_ETHER; + /* Copy stats */ + memcpy(&(threshold.qual), wstats, sizeof(struct iw_quality)); + /* Copy also thresholds */ + memcpy(&(threshold.low), &(spydata->spy_thr_low), + 2 * sizeof(struct iw_quality)); + + /* Send event to user space */ + wireless_send_event(dev, SIOCGIWTHRSPY, &wrqu, (char *) &threshold); +} + +/* ---------------------------------------------------------------- */ +/* + * Call for the driver to update the spy data. + * For now, the spy data is a simple array. As the size of the array is + * small, this is good enough. If we wanted to support larger number of + * spy addresses, we should use something more efficient... + */ +void wireless_spy_update(struct net_device * dev, + unsigned char * address, + struct iw_quality * wstats) +{ + struct iw_spy_data * spydata = get_spydata(dev); + int i; + int match = -1; + + /* Make sure driver is not buggy or using the old API */ + if (!spydata) + return; + + /* Update all records that match */ + for (i = 0; i < spydata->spy_number; i++) + if (!compare_ether_addr(address, spydata->spy_address[i])) { + memcpy(&(spydata->spy_stat[i]), wstats, + sizeof(struct iw_quality)); + match = i; + } + + /* Generate an event if we cross the spy threshold. + * To avoid event storms, we have a simple hysteresis : we generate + * event only when we go under the low threshold or above the + * high threshold. */ + if (match >= 0) { + if (spydata->spy_thr_under[match]) { + if (wstats->level > spydata->spy_thr_high.level) { + spydata->spy_thr_under[match] = 0; + iw_send_thrspy_event(dev, spydata, + address, wstats); + } + } else { + if (wstats->level < spydata->spy_thr_low.level) { + spydata->spy_thr_under[match] = 1; + iw_send_thrspy_event(dev, spydata, + address, wstats); + } + } + } +} +EXPORT_SYMBOL(wireless_spy_update); diff --git a/net/x25/af_x25.c b/net/x25/af_x25.c index 7fa9c7ad3d3..e19d811788a 100644 --- a/net/x25/af_x25.c +++ b/net/x25/af_x25.c @@ -1363,7 +1363,7 @@ static int x25_ioctl(struct socket *sock, unsigned int cmd, unsigned long arg) facilities.throughput > 0xDD) break; if (facilities.reverse && - (facilities.reverse | 0x81)!= 0x81) + (facilities.reverse & 0x81) != 0x81) break; x25->facilities = facilities; rc = 0; @@ -1476,7 +1476,7 @@ static int x25_ioctl(struct socket *sock, unsigned int cmd, unsigned long arg) return rc; } -static struct net_proto_family x25_family_ops = { +static const struct net_proto_family x25_family_ops = { .family = AF_X25, .create = x25_create, .owner = THIS_MODULE, diff --git a/net/x25/x25_in.c b/net/x25/x25_in.c index 7d7c3abf38b..96d92278354 100644 --- a/net/x25/x25_in.c +++ b/net/x25/x25_in.c @@ -114,7 +114,7 @@ static int x25_state1_machine(struct sock *sk, struct sk_buff *skb, int frametyp /* * Copy any Call User Data. */ - if (skb->len >= 0) { + if (skb->len > 0) { skb_copy_from_linear_data(skb, x25->calluserdata.cuddata, skb->len); diff --git a/net/x25/x25_route.c b/net/x25/x25_route.c index 2c999ccf504..66961ea28c9 100644 --- a/net/x25/x25_route.c +++ b/net/x25/x25_route.c @@ -190,7 +190,7 @@ int x25_route_ioctl(unsigned int cmd, void __user *arg) goto out; rc = -EINVAL; - if (rt.sigdigits < 0 || rt.sigdigits > 15) + if (rt.sigdigits > 15) goto out; dev = x25_dev_get(rt.device); diff --git a/net/xfrm/xfrm_algo.c b/net/xfrm/xfrm_algo.c index faf54c6bf96..b39341072aa 100644 --- a/net/xfrm/xfrm_algo.c +++ b/net/xfrm/xfrm_algo.c @@ -689,84 +689,6 @@ int xfrm_count_enc_supported(void) } EXPORT_SYMBOL_GPL(xfrm_count_enc_supported); -/* Move to common area: it is shared with AH. */ - -int skb_icv_walk(const struct sk_buff *skb, struct hash_desc *desc, - int offset, int len, icv_update_fn_t icv_update) -{ - int start = skb_headlen(skb); - int i, copy = start - offset; - struct sk_buff *frag_iter; - struct scatterlist sg; - int err; - - /* Checksum header. */ - if (copy > 0) { - if (copy > len) - copy = len; - - sg_init_one(&sg, skb->data + offset, copy); - - err = icv_update(desc, &sg, copy); - if (unlikely(err)) - return err; - - if ((len -= copy) == 0) - return 0; - offset += copy; - } - - for (i = 0; i < skb_shinfo(skb)->nr_frags; i++) { - int end; - - WARN_ON(start > offset + len); - - end = start + skb_shinfo(skb)->frags[i].size; - if ((copy = end - offset) > 0) { - skb_frag_t *frag = &skb_shinfo(skb)->frags[i]; - - if (copy > len) - copy = len; - - sg_init_table(&sg, 1); - sg_set_page(&sg, frag->page, copy, - frag->page_offset + offset-start); - - err = icv_update(desc, &sg, copy); - if (unlikely(err)) - return err; - - if (!(len -= copy)) - return 0; - offset += copy; - } - start = end; - } - - skb_walk_frags(skb, frag_iter) { - int end; - - WARN_ON(start > offset + len); - - end = start + frag_iter->len; - if ((copy = end - offset) > 0) { - if (copy > len) - copy = len; - err = skb_icv_walk(frag_iter, desc, offset-start, - copy, icv_update); - if (unlikely(err)) - return err; - if ((len -= copy) == 0) - return 0; - offset += copy; - } - start = end; - } - BUG_ON(len); - return 0; -} -EXPORT_SYMBOL_GPL(skb_icv_walk); - #if defined(CONFIG_INET_ESP) || defined(CONFIG_INET_ESP_MODULE) || defined(CONFIG_INET6_ESP) || defined(CONFIG_INET6_ESP_MODULE) void *pskb_put(struct sk_buff *skb, struct sk_buff *tail, int len) |