diff options
Diffstat (limited to 'net')
92 files changed, 2078 insertions, 1828 deletions
diff --git a/net/appletalk/ddp.c b/net/appletalk/ddp.c index b1a4290..abe3801 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/pvc.c b/net/atm/pvc.c index d4c0245..a6e1fdb 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 f90d143..8193542 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 f454607..f05306f 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 8cfb5a8..1f6e49c 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; diff --git a/net/bluetooth/bnep/sock.c b/net/bluetooth/bnep/sock.c index e857628..0a2c546 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 16b0fad..de7c804 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 75302a9..e7395f2 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 37c9d7d..4beb6a7 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 555d9da..4b66bd5 100644 --- a/net/bluetooth/l2cap.c +++ b/net/bluetooth/l2cap.c @@ -3916,7 +3916,7 @@ 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 8a20aaf..c707865 100644 --- a/net/bluetooth/rfcomm/sock.c +++ b/net/bluetooth/rfcomm/sock.c @@ -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 77f4153..694a655 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 07a0777..1a99c4e 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/can/af_can.c b/net/can/af_can.c index 6068321..3f2eb27 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/core/dev.c b/net/core/dev.c index b8f74cf..510ff20 100644 --- a/net/core/dev.c +++ b/net/core/dev.c @@ -4836,6 +4836,12 @@ 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; @@ -5483,7 +5489,7 @@ 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; diff --git a/net/core/ethtool.c b/net/core/ethtool.c index 4c12ddb..d8aee58 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/gen_stats.c b/net/core/gen_stats.c index 8569310..393b1d8 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 427ded8..753c420 100644 --- a/net/core/net-sysfs.c +++ b/net/core/net-sysfs.c @@ -130,6 +130,44 @@ 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->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->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 +297,8 @@ 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 +543,13 @@ 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 86acdba..1da0e03 100644 --- a/net/core/pktgen.c +++ b/net/core/pktgen.c @@ -3441,12 +3441,14 @@ 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: @@ -3468,6 +3470,7 @@ 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/dccp/ccids/ccid2.c b/net/dccp/ccids/ccid2.c index e8cf99e..a47a8c9 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 326ac90..1ec6a30 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 34dcc79..bcd7632 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 e5a2441..0326357 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/ipv6.c b/net/dccp/ipv6.c index e48ca5d..a2afb55 100644 --- a/net/dccp/ipv6.c +++ b/net/dccp/ipv6.c @@ -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->daddr, &newnp->daddr); - ipv6_addr_set(&newnp->saddr, 0, 0, htonl(0x0000FFFF), - newinet->saddr); + ipv6_addr_set_v4mapped(newinet->saddr, &newnp->saddr); ipv6_addr_copy(&newnp->rcv_saddr, &newnp->saddr); @@ -971,10 +969,8 @@ static int dccp_v6_connect(struct sock *sk, struct sockaddr *uaddr, 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->saddr, &np->saddr); + ipv6_addr_set_v4mapped(inet->rcv_saddr, &np->rcv_saddr); } return err; diff --git a/net/dccp/probe.c b/net/dccp/probe.c index 37731da..5e6ec8b 100644 --- a/net/dccp/probe.c +++ b/net/dccp/probe.c @@ -75,22 +75,20 @@ 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); + hc = 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", + if (hc) + 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->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), diff --git a/net/decnet/af_decnet.c b/net/decnet/af_decnet.c index 7a58c87..4d30606 100644 --- a/net/decnet/af_decnet.c +++ b/net/decnet/af_decnet.c @@ -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 0e0254f..5e9426a1 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 cd949d5..309348f 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/ipv4/af_inet.c b/net/ipv4/af_inet.c index 57737b8..1deff48 100644 --- a/net/ipv4/af_inet.c +++ b/net/ipv4/af_inet.c @@ -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, diff --git a/net/ipv4/cipso_ipv4.c b/net/ipv4/cipso_ipv4.c index 039cc1f..1e029dc 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/fib_frontend.c b/net/ipv4/fib_frontend.c index e2f9505..f73dbed 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 ecd3945..14972017b 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 92d9d97..835262c 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 291bdf5..af5d897 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 5bc13fe..84adb57 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 4351ca2..9139e8f 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 : diff --git a/net/ipv4/ip_gre.c b/net/ipv4/ip_gre.c index 41ada99..89ff9d5b 100644 --- a/net/ipv4/ip_gre.c +++ b/net/ipv4/ip_gre.c @@ -662,7 +662,8 @@ 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 +811,7 @@ 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; } diff --git a/net/ipv4/ipip.c b/net/ipv4/ipip.c index 08ccd34..6a55392 100644 --- a/net/ipv4/ipip.c +++ b/net/ipv4/ipip.c @@ -390,7 +390,8 @@ 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 +479,7 @@ 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; } diff --git a/net/ipv4/ipmr.c b/net/ipv4/ipmr.c index 630a56d..c757f0b 100644 --- a/net/ipv4/ipmr.c +++ b/net/ipv4/ipmr.c @@ -469,8 +469,18 @@ 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); diff --git a/net/ipv4/syncookies.c b/net/ipv4/syncookies.c index a6e0e07..5ec678a 100644 --- a/net/ipv4/syncookies.c +++ b/net/ipv4/syncookies.c @@ -333,7 +333,8 @@ 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), diff --git a/net/ipv4/udp.c b/net/ipv4/udp.c index 6ec6a8a..194bcdc 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); @@ -204,9 +207,10 @@ 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: @@ -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; @@ -1013,8 +1017,8 @@ 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)) { @@ -1169,7 +1173,7 @@ 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); @@ -1609,9 +1613,14 @@ 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)) @@ -1636,7 +1645,7 @@ 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); } @@ -1656,7 +1665,7 @@ 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; } @@ -1678,7 +1687,7 @@ 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); } @@ -1738,7 +1747,7 @@ static void udp4_format_sock(struct sock *sp, struct seq_file *f, __u16 destp = ntohs(inet->dport); __u16 srcp = ntohs(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), @@ -1804,11 +1813,43 @@ 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); } @@ -1818,7 +1859,7 @@ 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 95248d7..470c504 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 ead6c7a..a578096 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 1fd0a3d..bdcee69 100644 --- a/net/ipv6/addrconf.c +++ b/net/ipv6/addrconf.c @@ -4353,6 +4353,14 @@ 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 e127a32..9421651 100644 --- a/net/ipv6/af_inet6.c +++ b/net/ipv6/af_inet6.c @@ -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, @@ -654,6 +654,7 @@ 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.mark = sk->sk_mark; fl.fl_ip_dport = inet->dport; fl.fl_ip_sport = inet->sport; security_sk_classify_flow(sk, &fl); diff --git a/net/ipv6/datagram.c b/net/ipv6/datagram.c index e2bdc6d..dbfec71 100644 --- a/net/ipv6/datagram.c +++ b/net/ipv6/datagram.c @@ -98,17 +98,14 @@ ipv4_connected: if (err) goto out; - ipv6_addr_set(&np->daddr, 0, 0, htonl(0x0000ffff), inet->daddr); + ipv6_addr_set_v4mapped(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->saddr, &np->saddr); + + if (ipv6_addr_any(&np->rcv_saddr)) + ipv6_addr_set_v4mapped(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; } @@ -147,6 +144,7 @@ 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.mark = sk->sk_mark; fl.fl_ip_dport = inet->dport; fl.fl_ip_sport = inet->sport; @@ -329,9 +327,8 @@ 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 +348,8 @@ 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 cc4797d..a9f4a21b 100644 --- a/net/ipv6/inet6_connection_sock.c +++ b/net/ipv6/inet6_connection_sock.c @@ -194,6 +194,7 @@ 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.mark = sk->sk_mark; fl.fl_ip_sport = inet->sport; fl.fl_ip_dport = inet->dport; security_sk_classify_flow(sk, &fl); diff --git a/net/ipv6/ipv6_sockglue.c b/net/ipv6/ipv6_sockglue.c index 14f54eb..dc0f736 100644 --- a/net/ipv6/ipv6_sockglue.c +++ b/net/ipv6/ipv6_sockglue.c @@ -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; diff --git a/net/ipv6/ndisc.c b/net/ipv6/ndisc.c index f74e4e2..3507cfe 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/route.c b/net/ipv6/route.c index d6fe764..df9432a 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 dbd19a7..6955654 100644 --- a/net/ipv6/sit.c +++ b/net/ipv6/sit.c @@ -161,6 +161,21 @@ static void ipip6_tunnel_link(struct sit_net *sitn, struct ip_tunnel *t) write_unlock_bh(&ipip6_lock); } +static void ipip6_tunnel_clone_6rd(struct ip_tunnel *t, struct sit_net *sitn) +{ +#ifdef CONFIG_IPV6_SIT_6RD + 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, struct ip_tunnel_parm *parms, int create) { @@ -213,6 +228,8 @@ static struct ip_tunnel * ipip6_tunnel_locate(struct net *net, dev_hold(dev); + ipip6_tunnel_clone_6rd(t, sitn); + ipip6_tunnel_link(sitn, nt); return nt; @@ -532,17 +549,41 @@ out: 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(tunnel->ip6rd.prefix.s6_addr32[pbw0]) << pbi0) >> + tunnel->ip6rd.relay_prefixlen; + + pbi1 = pbi0 - tunnel->ip6rd.relay_prefixlen; + if (pbi1 > 0) + d |= ntohl(tunnel->ip6rd.prefix.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 +596,8 @@ 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 +637,7 @@ 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 +730,7 @@ 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 +827,15 @@ 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 +846,25 @@ 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 +985,51 @@ 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; + relay_prefix = ip6rd.relay_prefix & + htonl(0xffffffffUL << + (32 - ip6rd.relay_prefixlen)); + 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(t, sitn); + + err = 0; + break; +#endif + default: err = -EINVAL; } diff --git a/net/ipv6/syncookies.c b/net/ipv6/syncookies.c index 6b6ae91..cbe55e5 100644 --- a/net/ipv6/syncookies.c +++ b/net/ipv6/syncookies.c @@ -252,6 +252,7 @@ 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; security_req_classify_flow(req, &fl); diff --git a/net/ipv6/tcp_ipv6.c b/net/ipv6/tcp_ipv6.c index 21d100b..4517630 100644 --- a/net/ipv6/tcp_ipv6.c +++ b/net/ipv6/tcp_ipv6.c @@ -226,10 +226,8 @@ 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->saddr, &np->saddr); + ipv6_addr_set_v4mapped(inet->rcv_saddr, &np->rcv_saddr); } return err; @@ -243,6 +241,7 @@ 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; @@ -383,6 +382,7 @@ 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.mark = sk->sk_mark; fl.fl_ip_dport = inet->dport; fl.fl_ip_sport = inet->sport; security_skb_classify_flow(skb, &fl); @@ -477,6 +477,7 @@ 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); @@ -1290,11 +1291,9 @@ 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->daddr, &newnp->daddr); - ipv6_addr_set(&newnp->saddr, 0, 0, htonl(0x0000FFFF), - newinet->saddr); + ipv6_addr_set_v4mapped(newinet->saddr, &newnp->saddr); ipv6_addr_copy(&newnp->rcv_saddr, &newnp->saddr); @@ -1345,6 +1344,7 @@ 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); diff --git a/net/ipv6/udp.c b/net/ipv6/udp.c index 3a60f12..ff778c1 100644 --- a/net/ipv6/udp.c +++ b/net/ipv6/udp.c @@ -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; @@ -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); @@ -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); @@ -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)); @@ -1195,7 +1197,7 @@ static void udp6_sock_seq_show(struct seq_file *seq, struct sock *sp, int bucket destp = ntohs(inet->dport); srcp = ntohs(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/ipx/af_ipx.c b/net/ipx/af_ipx.c index 66c7a20..6481ee4 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 dd35641..9429e40 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 bada1b9..004134b 100644 --- a/net/iucv/af_iucv.c +++ b/net/iucv/af_iucv.c @@ -1715,7 +1715,7 @@ 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 4e98193..c078ae6 100644 --- a/net/key/af_key.c +++ b/net/key/af_key.c @@ -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 7aa4fd1..4866b4f 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 b8295cb..87aff1d 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); + } } /* @@ -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/netlink/af_netlink.c b/net/netlink/af_netlink.c index 19e9800..0cd2d88 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/netrom/af_netrom.c b/net/netrom/af_netrom.c index 7a83495..281fa59 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 1238949..70073a0 100644 --- a/net/packet/af_packet.c +++ b/net/packet/af_packet.c @@ -490,6 +490,7 @@ 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; @@ -524,6 +525,31 @@ static inline unsigned int run_filter(struct sk_buff *skb, struct sock *sk, } /* + * If we've lost frames since the last time we queued one to the + * sk_receive_queue, we need to record it here. + * This must be called under the protection of the socket lock + * to prevent racing with other softirqs and user space + */ +static inline void record_packet_gap(struct sk_buff *skb, + struct packet_sock *po) +{ + /* + * We overload the mark field here, since we're about + * to enqueue to a receive queue and no body else will + * use this field at this point + */ + skb->mark = po->stats.tp_gap; + po->stats.tp_gap = 0; + return; + +} + +static inline __u32 check_packet_gap(struct sk_buff *skb) +{ + return skb->mark; +} + +/* This function makes lazy skb cloning in hope that most of packets are discarded by BPF. @@ -626,6 +652,7 @@ static int packet_rcv(struct sk_buff *skb, struct net_device *dev, spin_lock(&sk->sk_receive_queue.lock); po->stats.tp_packets++; + record_packet_gap(skb, po); __skb_queue_tail(&sk->sk_receive_queue, skb); spin_unlock(&sk->sk_receive_queue.lock); sk->sk_data_ready(sk, skb->len); @@ -634,6 +661,7 @@ static int packet_rcv(struct sk_buff *skb, struct net_device *dev, drop_n_acct: spin_lock(&sk->sk_receive_queue.lock); po->stats.tp_drops++; + po->stats.tp_gap++; spin_unlock(&sk->sk_receive_queue.lock); drop_n_restore: @@ -811,6 +839,7 @@ drop: ring_is_full: po->stats.tp_drops++; + po->stats.tp_gap++; spin_unlock(&sk->sk_receive_queue.lock); sk->sk_data_ready(sk, 0); @@ -856,6 +885,7 @@ 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) { @@ -1125,6 +1155,7 @@ 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 @@ -1418,6 +1449,7 @@ static int packet_recvmsg(struct kiocb *iocb, struct socket *sock, struct sk_buff *skb; int copied, err; struct sockaddr_ll *sll; + __u32 gap; err = -EINVAL; if (flags & ~(MSG_PEEK|MSG_DONTWAIT|MSG_TRUNC|MSG_CMSG_COMPAT)) @@ -1496,6 +1528,10 @@ static int packet_recvmsg(struct kiocb *iocb, struct socket *sock, put_cmsg(msg, SOL_PACKET, PACKET_AUXDATA, sizeof(aux), &aux); } + gap = check_packet_gap(skb); + if (gap) + put_cmsg(msg, SOL_PACKET, PACKET_GAPDATA, sizeof(__u32), &gap); + /* * Free or return the buffer as appropriate. Again this * hides all the races and re-entrancy issues from us. @@ -2084,7 +2120,7 @@ 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, }; @@ -2363,7 +2399,7 @@ 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 f60c0c2..c711d58 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, diff --git a/net/rds/af_rds.c b/net/rds/af_rds.c index 98e0538..a202e5b 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/rfkill/core.c b/net/rfkill/core.c index dbeaf29..ba2efb9 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 502cce7..c17734c 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 a86afce..6817c97 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/sched/act_api.c b/net/sched/act_api.c index 2dfb3e7..ca2e1fd 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/sch_api.c b/net/sched/sch_api.c index 903e418..1acfd29 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 5b132c4..3846d65 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 5a888af..a65604f 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 2c5c76b..b38b39c 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 85acab9..2e38d1a 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/socket.c b/net/socket.c index 7565536..954f338 100644 --- a/net/socket.c +++ b/net/socket.c @@ -905,11 +905,11 @@ 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 +1100,14 @@ 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); } diff --git a/net/sunrpc/svcauth_unix.c b/net/sunrpc/svcauth_unix.c index 117f68a..f4c7ff3 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/unix/af_unix.c b/net/unix/af_unix.c index 51ab497..0f133c5 100644 --- a/net/unix/af_unix.c +++ b/net/unix/af_unix.c @@ -2214,7 +2214,7 @@ 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 abf7ca3..614bdce 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 3ecaa91..f07c8dc 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 45b2be3..0725296 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 0000000..ca4c825 --- /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 0000000..695ecad --- /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 c883389..39b6d92 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 79d2eec..ceb2c14 100644 --- a/net/wireless/mlme.c +++ b/net/wireless/mlme.c @@ -331,7 +331,7 @@ 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 ca3c92a..f483941 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 e5f92ee..2e8c515 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 93c3ed3..d362415 100644 --- a/net/wireless/sme.c +++ b/net/wireless/sme.c @@ -345,7 +345,7 @@ 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 @@ -362,7 +362,7 @@ 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)); @@ -477,7 +477,7 @@ 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 @@ -512,7 +512,7 @@ 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; @@ -573,7 +573,7 @@ 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 @@ -631,7 +631,7 @@ 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 60fe5776..a4e5ddc 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 0000000..a3c2277 --- /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 0000000..273a7f7 --- /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 0000000..6dcfe65 --- /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 7fa9c7a..ebbfe6b 100644 --- a/net/x25/af_x25.c +++ b/net/x25/af_x25.c @@ -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, |
