diff options
Diffstat (limited to 'net')
93 files changed, 865 insertions, 457 deletions
diff --git a/net/batman-adv/translation-table.c b/net/batman-adv/translation-table.c index c7aafc7c5ed..5f09a578d49 100644 --- a/net/batman-adv/translation-table.c +++ b/net/batman-adv/translation-table.c @@ -245,9 +245,11 @@ void tt_local_add(struct net_device *soft_iface, const uint8_t *addr, if (tt_global_entry) { /* This node is probably going to update its tt table */ tt_global_entry->orig_node->tt_poss_change = true; - /* The global entry has to be marked as PENDING and has to be + /* The global entry has to be marked as ROAMING and has to be * kept for consistency purpose */ - tt_global_entry->flags |= TT_CLIENT_PENDING; + tt_global_entry->flags |= TT_CLIENT_ROAM; + tt_global_entry->roam_at = jiffies; + send_roam_adv(bat_priv, tt_global_entry->addr, tt_global_entry->orig_node); } @@ -694,6 +696,7 @@ void tt_global_del(struct bat_priv *bat_priv, const char *message, bool roaming) { struct tt_global_entry *tt_global_entry = NULL; + struct tt_local_entry *tt_local_entry = NULL; tt_global_entry = tt_global_hash_find(bat_priv, addr); if (!tt_global_entry) @@ -701,15 +704,29 @@ void tt_global_del(struct bat_priv *bat_priv, if (tt_global_entry->orig_node == orig_node) { if (roaming) { - tt_global_entry->flags |= TT_CLIENT_ROAM; - tt_global_entry->roam_at = jiffies; - goto out; + /* if we are deleting a global entry due to a roam + * event, there are two possibilities: + * 1) the client roamed from node A to node B => we mark + * it with TT_CLIENT_ROAM, we start a timer and we + * wait for node B to claim it. In case of timeout + * the entry is purged. + * 2) the client roamed to us => we can directly delete + * the global entry, since it is useless now. */ + tt_local_entry = tt_local_hash_find(bat_priv, + tt_global_entry->addr); + if (!tt_local_entry) { + tt_global_entry->flags |= TT_CLIENT_ROAM; + tt_global_entry->roam_at = jiffies; + goto out; + } } _tt_global_del(bat_priv, tt_global_entry, message); } out: if (tt_global_entry) tt_global_entry_free_ref(tt_global_entry); + if (tt_local_entry) + tt_local_entry_free_ref(tt_local_entry); } void tt_global_del_orig(struct bat_priv *bat_priv, diff --git a/net/bluetooth/bnep/core.c b/net/bluetooth/bnep/core.c index 91bcd3a961e..1eea8208b2c 100644 --- a/net/bluetooth/bnep/core.c +++ b/net/bluetooth/bnep/core.c @@ -79,17 +79,12 @@ static struct bnep_session *__bnep_get_session(u8 *dst) static void __bnep_link_session(struct bnep_session *s) { - /* It's safe to call __module_get() here because sessions are added - by the socket layer which has to hold the reference to this module. - */ - __module_get(THIS_MODULE); list_add(&s->list, &bnep_session_list); } static void __bnep_unlink_session(struct bnep_session *s) { list_del(&s->list); - module_put(THIS_MODULE); } static int bnep_send(struct bnep_session *s, void *data, size_t len) @@ -530,6 +525,7 @@ static int bnep_session(void *arg) up_write(&bnep_session_sem); free_netdev(dev); + module_put_and_exit(0); return 0; } @@ -616,9 +612,11 @@ int bnep_add_connection(struct bnep_connadd_req *req, struct socket *sock) __bnep_link_session(s); + __module_get(THIS_MODULE); s->task = kthread_run(bnep_session, s, "kbnepd %s", dev->name); if (IS_ERR(s->task)) { /* Session thread start failed, gotta cleanup. */ + module_put(THIS_MODULE); unregister_netdev(dev); __bnep_unlink_session(s); err = PTR_ERR(s->task); diff --git a/net/bluetooth/cmtp/core.c b/net/bluetooth/cmtp/core.c index 7d00ddf9e9d..5a6e634f7fc 100644 --- a/net/bluetooth/cmtp/core.c +++ b/net/bluetooth/cmtp/core.c @@ -67,14 +67,12 @@ static struct cmtp_session *__cmtp_get_session(bdaddr_t *bdaddr) static void __cmtp_link_session(struct cmtp_session *session) { - __module_get(THIS_MODULE); list_add(&session->list, &cmtp_session_list); } static void __cmtp_unlink_session(struct cmtp_session *session) { list_del(&session->list); - module_put(THIS_MODULE); } static void __cmtp_copy_session(struct cmtp_session *session, struct cmtp_conninfo *ci) @@ -327,6 +325,7 @@ static int cmtp_session(void *arg) up_write(&cmtp_session_sem); kfree(session); + module_put_and_exit(0); return 0; } @@ -376,9 +375,11 @@ int cmtp_add_connection(struct cmtp_connadd_req *req, struct socket *sock) __cmtp_link_session(session); + __module_get(THIS_MODULE); session->task = kthread_run(cmtp_session, session, "kcmtpd_ctr_%d", session->num); if (IS_ERR(session->task)) { + module_put(THIS_MODULE); err = PTR_ERR(session->task); goto unlink; } diff --git a/net/bluetooth/hci_event.c b/net/bluetooth/hci_event.c index d7d96b6b1f0..643a41b76e2 100644 --- a/net/bluetooth/hci_event.c +++ b/net/bluetooth/hci_event.c @@ -545,7 +545,7 @@ static void hci_setup(struct hci_dev *hdev) { hci_setup_event_mask(hdev); - if (hdev->lmp_ver > 1) + if (hdev->hci_ver > 1) hci_send_cmd(hdev, HCI_OP_READ_LOCAL_COMMANDS, 0, NULL); if (hdev->features[6] & LMP_SIMPLE_PAIR) { diff --git a/net/bluetooth/l2cap_core.c b/net/bluetooth/l2cap_core.c index 8cd12917733..17b5b1cd965 100644 --- a/net/bluetooth/l2cap_core.c +++ b/net/bluetooth/l2cap_core.c @@ -251,7 +251,7 @@ static void l2cap_chan_timeout(unsigned long arg) if (sock_owned_by_user(sk)) { /* sk is owned by user. Try again later */ - __set_chan_timer(chan, HZ / 5); + __set_chan_timer(chan, L2CAP_DISC_TIMEOUT); bh_unlock_sock(sk); chan_put(chan); return; @@ -2152,7 +2152,7 @@ static int l2cap_parse_conf_rsp(struct l2cap_chan *chan, void *rsp, int len, voi void *ptr = req->data; int type, olen; unsigned long val; - struct l2cap_conf_rfc rfc; + struct l2cap_conf_rfc rfc = { .mode = L2CAP_MODE_BASIC }; BT_DBG("chan %p, rsp %p, len %d, req %p", chan, rsp, len, data); @@ -2271,6 +2271,16 @@ static void l2cap_conf_rfc_get(struct l2cap_chan *chan, void *rsp, int len) } } + /* Use sane default values in case a misbehaving remote device + * did not send an RFC option. + */ + rfc.mode = chan->mode; + rfc.retrans_timeout = cpu_to_le16(L2CAP_DEFAULT_RETRANS_TO); + rfc.monitor_timeout = cpu_to_le16(L2CAP_DEFAULT_MONITOR_TO); + rfc.max_pdu_size = cpu_to_le16(chan->imtu); + + BT_ERR("Expected RFC option was not found, using defaults"); + done: switch (rfc.mode) { case L2CAP_MODE_ERTM: @@ -2488,7 +2498,7 @@ static inline int l2cap_connect_rsp(struct l2cap_conn *conn, struct l2cap_cmd_hd if (sock_owned_by_user(sk)) { l2cap_state_change(chan, BT_DISCONN); __clear_chan_timer(chan); - __set_chan_timer(chan, HZ / 5); + __set_chan_timer(chan, L2CAP_DISC_TIMEOUT); break; } @@ -2661,7 +2671,7 @@ static inline int l2cap_config_rsp(struct l2cap_conn *conn, struct l2cap_cmd_hdr default: sk->sk_err = ECONNRESET; - __set_chan_timer(chan, HZ * 5); + __set_chan_timer(chan, L2CAP_DISC_REJ_TIMEOUT); l2cap_send_disconn_req(conn, chan, ECONNRESET); goto done; } @@ -2718,7 +2728,7 @@ static inline int l2cap_disconnect_req(struct l2cap_conn *conn, struct l2cap_cmd if (sock_owned_by_user(sk)) { l2cap_state_change(chan, BT_DISCONN); __clear_chan_timer(chan); - __set_chan_timer(chan, HZ / 5); + __set_chan_timer(chan, L2CAP_DISC_TIMEOUT); bh_unlock_sock(sk); return 0; } @@ -2752,7 +2762,7 @@ static inline int l2cap_disconnect_rsp(struct l2cap_conn *conn, struct l2cap_cmd if (sock_owned_by_user(sk)) { l2cap_state_change(chan,BT_DISCONN); __clear_chan_timer(chan); - __set_chan_timer(chan, HZ / 5); + __set_chan_timer(chan, L2CAP_DISC_TIMEOUT); bh_unlock_sock(sk); return 0; } @@ -3998,7 +4008,7 @@ static inline void l2cap_check_encryption(struct l2cap_chan *chan, u8 encrypt) if (encrypt == 0x00) { if (chan->sec_level == BT_SECURITY_MEDIUM) { __clear_chan_timer(chan); - __set_chan_timer(chan, HZ * 5); + __set_chan_timer(chan, L2CAP_ENC_TIMEOUT); } else if (chan->sec_level == BT_SECURITY_HIGH) l2cap_chan_close(chan, ECONNREFUSED); } else { @@ -4066,7 +4076,7 @@ static int l2cap_security_cfm(struct hci_conn *hcon, u8 status, u8 encrypt) L2CAP_CONN_REQ, sizeof(req), &req); } else { __clear_chan_timer(chan); - __set_chan_timer(chan, HZ / 10); + __set_chan_timer(chan, L2CAP_DISC_TIMEOUT); } } else if (chan->state == BT_CONNECT2) { struct l2cap_conn_rsp rsp; @@ -4086,7 +4096,7 @@ static int l2cap_security_cfm(struct hci_conn *hcon, u8 status, u8 encrypt) } } else { l2cap_state_change(chan, BT_DISCONN); - __set_chan_timer(chan, HZ / 10); + __set_chan_timer(chan, L2CAP_DISC_TIMEOUT); res = L2CAP_CR_SEC_BLOCK; stat = L2CAP_CS_NO_INFO; } diff --git a/net/bluetooth/rfcomm/core.c b/net/bluetooth/rfcomm/core.c index 4e32e18211f..2d28dfe9838 100644 --- a/net/bluetooth/rfcomm/core.c +++ b/net/bluetooth/rfcomm/core.c @@ -1146,6 +1146,7 @@ static int rfcomm_recv_ua(struct rfcomm_session *s, u8 dlci) if (list_empty(&s->dlcs)) { s->state = BT_DISCONN; rfcomm_send_disc(s, 0); + rfcomm_session_clear_timer(s); } break; diff --git a/net/bridge/br_multicast.c b/net/bridge/br_multicast.c index 995cbe0ac0b..a5f4e576980 100644 --- a/net/bridge/br_multicast.c +++ b/net/bridge/br_multicast.c @@ -1501,6 +1501,8 @@ static int br_multicast_ipv6_rcv(struct net_bridge *br, __skb_pull(skb2, offset); skb_reset_transport_header(skb2); + skb_postpull_rcsum(skb2, skb_network_header(skb2), + skb_network_header_len(skb2)); icmp6_type = icmp6_hdr(skb2)->icmp6_type; @@ -1770,7 +1772,7 @@ int br_multicast_toggle(struct net_bridge *br, unsigned long val) int err = 0; struct net_bridge_mdb_htable *mdb; - spin_lock(&br->multicast_lock); + spin_lock_bh(&br->multicast_lock); if (br->multicast_disabled == !val) goto unlock; @@ -1806,7 +1808,7 @@ rollback: } unlock: - spin_unlock(&br->multicast_lock); + spin_unlock_bh(&br->multicast_lock); return err; } diff --git a/net/bridge/br_netfilter.c b/net/bridge/br_netfilter.c index d6ec3720c77..fa8b8f76358 100644 --- a/net/bridge/br_netfilter.c +++ b/net/bridge/br_netfilter.c @@ -114,12 +114,18 @@ static struct neighbour *fake_neigh_lookup(const struct dst_entry *dst, const vo return NULL; } +static unsigned int fake_mtu(const struct dst_entry *dst) +{ + return dst->dev->mtu; +} + static struct dst_ops fake_dst_ops = { .family = AF_INET, .protocol = cpu_to_be16(ETH_P_IP), .update_pmtu = fake_update_pmtu, .cow_metrics = fake_cow_metrics, .neigh_lookup = fake_neigh_lookup, + .mtu = fake_mtu, }; /* @@ -141,7 +147,7 @@ void br_netfilter_rtable_init(struct net_bridge *br) rt->dst.dev = br->dev; rt->dst.path = &rt->dst; dst_init_metrics(&rt->dst, br_dst_default_metrics, true); - rt->dst.flags = DST_NOXFRM; + rt->dst.flags = DST_NOXFRM | DST_NOPEER; rt->dst.ops = &fake_dst_ops; } diff --git a/net/bridge/br_netlink.c b/net/bridge/br_netlink.c index e5f9ece3c9a..a1daf8227ed 100644 --- a/net/bridge/br_netlink.c +++ b/net/bridge/br_netlink.c @@ -18,6 +18,7 @@ #include <net/sock.h> #include "br_private.h" +#include "br_private_stp.h" static inline size_t br_nlmsg_size(void) { @@ -188,6 +189,11 @@ static int br_rtm_setlink(struct sk_buff *skb, struct nlmsghdr *nlh, void *arg) p->state = new_state; br_log_state(p); + + spin_lock_bh(&p->br->lock); + br_port_state_selection(p->br); + spin_unlock_bh(&p->br->lock); + br_ifinfo_notify(RTM_NEWLINK, p); return 0; diff --git a/net/bridge/br_stp.c b/net/bridge/br_stp.c index ad0a3f7cf6c..dd147d78a58 100644 --- a/net/bridge/br_stp.c +++ b/net/bridge/br_stp.c @@ -399,25 +399,24 @@ void br_port_state_selection(struct net_bridge *br) struct net_bridge_port *p; unsigned int liveports = 0; - /* Don't change port states if userspace is handling STP */ - if (br->stp_enabled == BR_USER_STP) - return; - list_for_each_entry(p, &br->port_list, list) { if (p->state == BR_STATE_DISABLED) continue; - if (p->port_no == br->root_port) { - p->config_pending = 0; - p->topology_change_ack = 0; - br_make_forwarding(p); - } else if (br_is_designated_port(p)) { - del_timer(&p->message_age_timer); - br_make_forwarding(p); - } else { - p->config_pending = 0; - p->topology_change_ack = 0; - br_make_blocking(p); + /* Don't change port states if userspace is handling STP */ + if (br->stp_enabled != BR_USER_STP) { + if (p->port_no == br->root_port) { + p->config_pending = 0; + p->topology_change_ack = 0; + br_make_forwarding(p); + } else if (br_is_designated_port(p)) { + del_timer(&p->message_age_timer); + br_make_forwarding(p); + } else { + p->config_pending = 0; + p->topology_change_ack = 0; + br_make_blocking(p); + } } if (p->state == BR_STATE_FORWARDING) diff --git a/net/caif/cffrml.c b/net/caif/cffrml.c index f39921171d0..d3ca87bf23b 100644 --- a/net/caif/cffrml.c +++ b/net/caif/cffrml.c @@ -136,20 +136,21 @@ static int cffrml_receive(struct cflayer *layr, struct cfpkt *pkt) static int cffrml_transmit(struct cflayer *layr, struct cfpkt *pkt) { - int tmp; u16 chks; u16 len; + __le16 data; + struct cffrml *this = container_obj(layr); if (this->dofcs) { chks = cfpkt_iterate(pkt, cffrml_checksum, 0xffff); - tmp = cpu_to_le16(chks); - cfpkt_add_trail(pkt, &tmp, 2); + data = cpu_to_le16(chks); + cfpkt_add_trail(pkt, &data, 2); } else { cfpkt_pad_trail(pkt, 2); } len = cfpkt_getlen(pkt); - tmp = cpu_to_le16(len); - cfpkt_add_head(pkt, &tmp, 2); + data = cpu_to_le16(len); + cfpkt_add_head(pkt, &data, 2); cfpkt_info(pkt)->hdr_len += 2; if (cfpkt_erroneous(pkt)) { pr_err("Packet is erroneous!\n"); diff --git a/net/ceph/crush/mapper.c b/net/ceph/crush/mapper.c index 42599e31dca..3a94eae7abe 100644 --- a/net/ceph/crush/mapper.c +++ b/net/ceph/crush/mapper.c @@ -477,7 +477,6 @@ int crush_do_rule(struct crush_map *map, int i, j; int numrep; int firstn; - int rc = -1; BUG_ON(ruleno >= map->max_rules); @@ -491,23 +490,18 @@ int crush_do_rule(struct crush_map *map, * that this may or may not correspond to the specific types * referenced by the crush rule. */ - if (force >= 0) { - if (force >= map->max_devices || - map->device_parents[force] == 0) { - /*dprintk("CRUSH: forcefed device dne\n");*/ - rc = -1; /* force fed device dne */ - goto out; - } - if (!is_out(map, weight, force, x)) { - while (1) { - force_context[++force_pos] = force; - if (force >= 0) - force = map->device_parents[force]; - else - force = map->bucket_parents[-1-force]; - if (force == 0) - break; - } + if (force >= 0 && + force < map->max_devices && + map->device_parents[force] != 0 && + !is_out(map, weight, force, x)) { + while (1) { + force_context[++force_pos] = force; + if (force >= 0) + force = map->device_parents[force]; + else + force = map->bucket_parents[-1-force]; + if (force == 0) + break; } } @@ -600,10 +594,7 @@ int crush_do_rule(struct crush_map *map, BUG_ON(1); } } - rc = result_len; - -out: - return rc; + return result_len; } diff --git a/net/ceph/osd_client.c b/net/ceph/osd_client.c index 733e46008b8..f4f3f58f523 100644 --- a/net/ceph/osd_client.c +++ b/net/ceph/osd_client.c @@ -244,7 +244,7 @@ struct ceph_osd_request *ceph_osdc_alloc_request(struct ceph_osd_client *osdc, ceph_pagelist_init(req->r_trail); } /* create request message; allow space for oid */ - msg_size += 40; + msg_size += MAX_OBJ_NAME_SIZE; if (snapc) msg_size += sizeof(u64) * snapc->num_snaps; if (use_mempool) diff --git a/net/core/dev.c b/net/core/dev.c index 6ba50a1e404..5a13edfc9f7 100644 --- a/net/core/dev.c +++ b/net/core/dev.c @@ -1396,7 +1396,7 @@ rollback: for_each_net(net) { for_each_netdev(net, dev) { if (dev == last) - break; + goto outroll; if (dev->flags & IFF_UP) { nb->notifier_call(nb, NETDEV_GOING_DOWN, dev); @@ -1407,6 +1407,7 @@ rollback: } } +outroll: raw_notifier_chain_unregister(&netdev_chain, nb); goto unlock; } @@ -4282,6 +4283,12 @@ static int dev_seq_open(struct inode *inode, struct file *file) sizeof(struct dev_iter_state)); } +int dev_seq_open_ops(struct inode *inode, struct file *file, + const struct seq_operations *ops) +{ + return seq_open_net(inode, file, ops, sizeof(struct dev_iter_state)); +} + static const struct file_operations dev_seq_fops = { .owner = THIS_MODULE, .open = dev_seq_open, diff --git a/net/core/dev_addr_lists.c b/net/core/dev_addr_lists.c index 277faef9148..febba516db6 100644 --- a/net/core/dev_addr_lists.c +++ b/net/core/dev_addr_lists.c @@ -696,8 +696,7 @@ static const struct seq_operations dev_mc_seq_ops = { static int dev_mc_seq_open(struct inode *inode, struct file *file) { - return seq_open_net(inode, file, &dev_mc_seq_ops, - sizeof(struct seq_net_private)); + return dev_seq_open_ops(inode, file, &dev_mc_seq_ops); } static const struct file_operations dev_mc_seq_fops = { diff --git a/net/core/flow.c b/net/core/flow.c index 8ae42de9c79..e318c7e9804 100644 --- a/net/core/flow.c +++ b/net/core/flow.c @@ -358,6 +358,18 @@ void flow_cache_flush(void) put_online_cpus(); } +static void flow_cache_flush_task(struct work_struct *work) +{ + flow_cache_flush(); +} + +static DECLARE_WORK(flow_cache_flush_work, flow_cache_flush_task); + +void flow_cache_flush_deferred(void) +{ + schedule_work(&flow_cache_flush_work); +} + static int __cpuinit flow_cache_cpu_prepare(struct flow_cache *fc, int cpu) { struct flow_cache_percpu *fcp = per_cpu_ptr(fc->percpu, cpu); diff --git a/net/core/neighbour.c b/net/core/neighbour.c index 039d51e6c28..5ac07d31fbc 100644 --- a/net/core/neighbour.c +++ b/net/core/neighbour.c @@ -2397,7 +2397,10 @@ static struct pneigh_entry *pneigh_get_next(struct seq_file *seq, struct net *net = seq_file_net(seq); struct neigh_table *tbl = state->tbl; - pn = pn->next; + do { + pn = pn->next; + } while (pn && !net_eq(pneigh_net(pn), net)); + while (!pn) { if (++state->bucket > PNEIGH_HASHMASK) break; diff --git a/net/core/net-sysfs.c b/net/core/net-sysfs.c index c71c434a4c0..385aefe5364 100644 --- a/net/core/net-sysfs.c +++ b/net/core/net-sysfs.c @@ -665,11 +665,14 @@ static ssize_t store_rps_dev_flow_table_cnt(struct netdev_rx_queue *queue, if (count) { int i; - if (count > 1<<30) { + if (count > INT_MAX) + return -EINVAL; + count = roundup_pow_of_two(count); + if (count > (ULONG_MAX - sizeof(struct rps_dev_flow_table)) + / sizeof(struct rps_dev_flow)) { /* Enforce a limit to prevent overflow */ return -EINVAL; } - count = roundup_pow_of_two(count); table = vmalloc(RPS_DEV_FLOW_TABLE_SIZE(count)); if (!table) return -ENOMEM; diff --git a/net/core/request_sock.c b/net/core/request_sock.c index 182236b2510..9b570a6a33c 100644 --- a/net/core/request_sock.c +++ b/net/core/request_sock.c @@ -26,10 +26,11 @@ * but then some measure against one socket starving all other sockets * would be needed. * - * It was 128 by default. Experiments with real servers show, that + * The minimum value of it is 128. Experiments with real servers show that * it is absolutely not enough even at 100conn/sec. 256 cures most - * of problems. This value is adjusted to 128 for very small machines - * (<=32Mb of memory) and to 1024 on normal or better ones (>=256Mb). + * of problems. + * This value is adjusted to 128 for low memory machines, + * and it will increase in proportion to the memory of machine. * Note : Dont forget somaxconn that may limit backlog too. */ int sysctl_max_syn_backlog = 256; diff --git a/net/core/secure_seq.c b/net/core/secure_seq.c index 025233de25f..925991ae6f5 100644 --- a/net/core/secure_seq.c +++ b/net/core/secure_seq.c @@ -19,6 +19,7 @@ static int __init net_secret_init(void) } late_initcall(net_secret_init); +#ifdef CONFIG_INET static u32 seq_scale(u32 seq) { /* @@ -33,6 +34,7 @@ static u32 seq_scale(u32 seq) */ return seq + (ktime_to_ns(ktime_get_real()) >> 6); } +#endif #if defined(CONFIG_IPV6) || defined(CONFIG_IPV6_MODULE) __u32 secure_tcpv6_sequence_number(const __be32 *saddr, const __be32 *daddr, diff --git a/net/core/skbuff.c b/net/core/skbuff.c index 18a3cebb753..3c30ee4a571 100644 --- a/net/core/skbuff.c +++ b/net/core/skbuff.c @@ -2230,7 +2230,7 @@ static int skb_prepare_for_shift(struct sk_buff *skb) * @shiftlen: shift up to this many bytes * * Attempts to shift up to shiftlen worth of bytes, which may be less than - * the length of the skb, from tgt to skb. Returns number bytes shifted. + * the length of the skb, from skb to tgt. Returns number bytes shifted. * It's up to caller to free skb if everything was shifted. * * If @tgt runs out of frags, the whole operation is aborted. diff --git a/net/core/sock.c b/net/core/sock.c index 4ed7b1d12f5..b23f174ab84 100644 --- a/net/core/sock.c +++ b/net/core/sock.c @@ -288,11 +288,7 @@ int sock_queue_rcv_skb(struct sock *sk, struct sk_buff *skb) unsigned long flags; struct sk_buff_head *list = &sk->sk_receive_queue; - /* Cast sk->rcvbuf to unsigned... It's pointless, but reduces - number of warnings when compiling with -W --ANK - */ - if (atomic_read(&sk->sk_rmem_alloc) + skb->truesize >= - (unsigned)sk->sk_rcvbuf) { + if (atomic_read(&sk->sk_rmem_alloc) >= sk->sk_rcvbuf) { atomic_inc(&sk->sk_drops); trace_sock_rcvqueue_full(sk, skb); return -ENOMEM; diff --git a/net/dccp/ipv4.c b/net/dccp/ipv4.c index 90a919afbed..3f4e5414c8e 100644 --- a/net/dccp/ipv4.c +++ b/net/dccp/ipv4.c @@ -111,6 +111,7 @@ int dccp_v4_connect(struct sock *sk, struct sockaddr *uaddr, int addr_len) rt = ip_route_newports(fl4, rt, orig_sport, orig_dport, inet->inet_sport, inet->inet_dport, sk); if (IS_ERR(rt)) { + err = PTR_ERR(rt); rt = NULL; goto failure; } diff --git a/net/decnet/dn_route.c b/net/decnet/dn_route.c index a77d16158eb..94f4ec03666 100644 --- a/net/decnet/dn_route.c +++ b/net/decnet/dn_route.c @@ -112,7 +112,7 @@ static unsigned long dn_rt_deadline; static int dn_dst_gc(struct dst_ops *ops); static struct dst_entry *dn_dst_check(struct dst_entry *, __u32); static unsigned int dn_dst_default_advmss(const struct dst_entry *dst); -static unsigned int dn_dst_default_mtu(const struct dst_entry *dst); +static unsigned int dn_dst_mtu(const struct dst_entry *dst); static void dn_dst_destroy(struct dst_entry *); static struct dst_entry *dn_dst_negative_advice(struct dst_entry *); static void dn_dst_link_failure(struct sk_buff *); @@ -135,7 +135,7 @@ static struct dst_ops dn_dst_ops = { .gc = dn_dst_gc, .check = dn_dst_check, .default_advmss = dn_dst_default_advmss, - .default_mtu = dn_dst_default_mtu, + .mtu = dn_dst_mtu, .cow_metrics = dst_cow_metrics_generic, .destroy = dn_dst_destroy, .negative_advice = dn_dst_negative_advice, @@ -825,9 +825,11 @@ static unsigned int dn_dst_default_advmss(const struct dst_entry *dst) return dn_mss_from_pmtu(dst->dev, dst_mtu(dst)); } -static unsigned int dn_dst_default_mtu(const struct dst_entry *dst) +static unsigned int dn_dst_mtu(const struct dst_entry *dst) { - return dst->dev->mtu; + unsigned int mtu = dst_metric_raw(dst, RTAX_MTU); + + return mtu ? : dst->dev->mtu; } static struct neighbour *dn_dst_neigh_lookup(const struct dst_entry *dst, const void *daddr) diff --git a/net/decnet/dn_timer.c b/net/decnet/dn_timer.c index 67f691bd4ac..d9c150cc59a 100644 --- a/net/decnet/dn_timer.c +++ b/net/decnet/dn_timer.c @@ -36,16 +36,13 @@ static void dn_slow_timer(unsigned long arg); void dn_start_slow_timer(struct sock *sk) { - sk->sk_timer.expires = jiffies + SLOW_INTERVAL; - sk->sk_timer.function = dn_slow_timer; - sk->sk_timer.data = (unsigned long)sk; - - add_timer(&sk->sk_timer); + setup_timer(&sk->sk_timer, dn_slow_timer, (unsigned long)sk); + sk_reset_timer(sk, &sk->sk_timer, jiffies + SLOW_INTERVAL); } void dn_stop_slow_timer(struct sock *sk) { - del_timer(&sk->sk_timer); + sk_stop_timer(sk, &sk->sk_timer); } static void dn_slow_timer(unsigned long arg) @@ -53,12 +50,10 @@ static void dn_slow_timer(unsigned long arg) struct sock *sk = (struct sock *)arg; struct dn_scp *scp = DN_SK(sk); - sock_hold(sk); bh_lock_sock(sk); if (sock_owned_by_user(sk)) { - sk->sk_timer.expires = jiffies + HZ / 10; - add_timer(&sk->sk_timer); + sk_reset_timer(sk, &sk->sk_timer, jiffies + HZ / 10); goto out; } @@ -100,9 +95,7 @@ static void dn_slow_timer(unsigned long arg) scp->keepalive_fxn(sk); } - sk->sk_timer.expires = jiffies + SLOW_INTERVAL; - - add_timer(&sk->sk_timer); + sk_reset_timer(sk, &sk->sk_timer, jiffies + SLOW_INTERVAL); out: bh_unlock_sock(sk); sock_put(sk); diff --git a/net/ipv4/ah4.c b/net/ipv4/ah4.c index c1f4154552f..36d14406261 100644 --- a/net/ipv4/ah4.c +++ b/net/ipv4/ah4.c @@ -136,8 +136,6 @@ static void ah_output_done(struct crypto_async_request *base, int err) memcpy(top_iph+1, iph+1, top_iph->ihl*4 - sizeof(struct iphdr)); } - err = ah->nexthdr; - kfree(AH_SKB_CB(skb)->tmp); xfrm_output_resume(skb, err); } @@ -264,12 +262,12 @@ static void ah_input_done(struct crypto_async_request *base, int err) if (err) goto out; + err = ah->nexthdr; + skb->network_header += ah_hlen; memcpy(skb_network_header(skb), work_iph, ihl); __skb_pull(skb, ah_hlen + ihl); skb_set_transport_header(skb, -ihl); - - err = ah->nexthdr; out: kfree(AH_SKB_CB(skb)->tmp); xfrm_input_resume(skb, err); @@ -371,8 +369,6 @@ static int ah_input(struct xfrm_state *x, struct sk_buff *skb) if (err == -EINPROGRESS) goto out; - if (err == -EBUSY) - err = NET_XMIT_DROP; goto out_free; } diff --git a/net/ipv4/devinet.c b/net/ipv4/devinet.c index c6b5092f29a..65f01dc4756 100644 --- a/net/ipv4/devinet.c +++ b/net/ipv4/devinet.c @@ -1490,7 +1490,9 @@ static int devinet_conf_proc(ctl_table *ctl, int write, void __user *buffer, size_t *lenp, loff_t *ppos) { + int old_value = *(int *)ctl->data; int ret = proc_dointvec(ctl, write, buffer, lenp, ppos); + int new_value = *(int *)ctl->data; if (write) { struct ipv4_devconf *cnf = ctl->extra1; @@ -1501,6 +1503,9 @@ static int devinet_conf_proc(ctl_table *ctl, int write, if (cnf == net->ipv4.devconf_dflt) devinet_copy_dflt_conf(net, i); + if (i == IPV4_DEVCONF_ACCEPT_LOCAL - 1) + if ((new_value == 0) && (old_value != 0)) + rt_cache_flush(net, 0); } return ret; diff --git a/net/ipv4/igmp.c b/net/ipv4/igmp.c index c7472eff2d5..b2ca095cb9d 100644 --- a/net/ipv4/igmp.c +++ b/net/ipv4/igmp.c @@ -1716,7 +1716,8 @@ static int ip_mc_add_src(struct in_device *in_dev, __be32 *pmca, int sfmode, if (err) { int j; - pmc->sfcount[sfmode]--; + if (!delta) + pmc->sfcount[sfmode]--; for (j=0; j<i; j++) (void) ip_mc_del1_src(pmc, sfmode, &psfsrc[j]); } else if (isexclude != (pmc->sfcount[MCAST_EXCLUDE] != 0)) { diff --git a/net/ipv4/inet_diag.c b/net/ipv4/inet_diag.c index f5e2bdaef94..ccee270a9b6 100644 --- a/net/ipv4/inet_diag.c +++ b/net/ipv4/inet_diag.c @@ -108,9 +108,6 @@ static int inet_csk_diag_fill(struct sock *sk, icsk->icsk_ca_ops->name); } - if ((ext & (1 << (INET_DIAG_TOS - 1))) && (sk->sk_family != AF_INET6)) - RTA_PUT_U8(skb, INET_DIAG_TOS, inet->tos); - r->idiag_family = sk->sk_family; r->idiag_state = sk->sk_state; r->idiag_timer = 0; @@ -125,16 +122,23 @@ static int inet_csk_diag_fill(struct sock *sk, r->id.idiag_src[0] = inet->inet_rcv_saddr; r->id.idiag_dst[0] = inet->inet_daddr; + /* IPv6 dual-stack sockets use inet->tos for IPv4 connections, + * hence this needs to be included regardless of socket family. + */ + if (ext & (1 << (INET_DIAG_TOS - 1))) + RTA_PUT_U8(skb, INET_DIAG_TOS, inet->tos); + #if defined(CONFIG_IPV6) || defined (CONFIG_IPV6_MODULE) if (r->idiag_family == AF_INET6) { const struct ipv6_pinfo *np = inet6_sk(sk); + if (ext & (1 << (INET_DIAG_TCLASS - 1))) + RTA_PUT_U8(skb, INET_DIAG_TCLASS, np->tclass); + ipv6_addr_copy((struct in6_addr *)r->id.idiag_src, &np->rcv_saddr); ipv6_addr_copy((struct in6_addr *)r->id.idiag_dst, &np->daddr); - if (ext & (1 << (INET_DIAG_TOS - 1))) - RTA_PUT_U8(skb, INET_DIAG_TOS, np->tclass); } #endif diff --git a/net/ipv4/ip_forward.c b/net/ipv4/ip_forward.c index 3b34d1c8627..29a07b6c716 100644 --- a/net/ipv4/ip_forward.c +++ b/net/ipv4/ip_forward.c @@ -84,7 +84,7 @@ int ip_forward(struct sk_buff *skb) rt = skb_rtable(skb); - if (opt->is_strictroute && ip_hdr(skb)->daddr != rt->rt_gateway) + if (opt->is_strictroute && opt->nexthop != rt->rt_gateway) goto sr_failed; if (unlikely(skb->len > dst_mtu(&rt->dst) && !skb_is_gso(skb) && diff --git a/net/ipv4/ip_options.c b/net/ipv4/ip_options.c index ec93335901d..1e60f767907 100644 --- a/net/ipv4/ip_options.c +++ b/net/ipv4/ip_options.c @@ -568,12 +568,13 @@ void ip_forward_options(struct sk_buff *skb) ) { if (srrptr + 3 > srrspace) break; - if (memcmp(&ip_hdr(skb)->daddr, &optptr[srrptr-1], 4) == 0) + if (memcmp(&opt->nexthop, &optptr[srrptr-1], 4) == 0) break; } if (srrptr + 3 <= srrspace) { opt->is_changed = 1; ip_rt_get_source(&optptr[srrptr-1], skb, rt); + ip_hdr(skb)->daddr = opt->nexthop; optptr[2] = srrptr+4; } else if (net_ratelimit()) printk(KERN_CRIT "ip_forward(): Argh! Destination lost!\n"); @@ -640,6 +641,7 @@ int ip_options_rcv_srr(struct sk_buff *skb) } if (srrptr <= srrspace) { opt->srr_is_hit = 1; + opt->nexthop = nexthop; opt->is_changed = 1; } return 0; diff --git a/net/ipv4/ipconfig.c b/net/ipv4/ipconfig.c index 0da2afc97f3..99ec116bef1 100644 --- a/net/ipv4/ipconfig.c +++ b/net/ipv4/ipconfig.c @@ -253,6 +253,10 @@ static int __init ic_open_devs(void) } } + /* no point in waiting if we could not bring up at least one device */ + if (!ic_first_dev) + goto have_carrier; + /* wait for a carrier on at least one device */ start = jiffies; while (jiffies - start < msecs_to_jiffies(CONF_CARRIER_TIMEOUT)) { diff --git a/net/ipv4/ipip.c b/net/ipv4/ipip.c index 065effd8349..0b2e7329abd 100644 --- a/net/ipv4/ipip.c +++ b/net/ipv4/ipip.c @@ -285,6 +285,8 @@ static struct ip_tunnel * ipip_tunnel_locate(struct net *net, if (register_netdevice(dev) < 0) goto failed_free; + strcpy(nt->parms.name, dev->name); + dev_hold(dev); ipip_tunnel_link(ipn, nt); return nt; @@ -759,7 +761,6 @@ static int ipip_tunnel_init(struct net_device *dev) struct ip_tunnel *tunnel = netdev_priv(dev); tunnel->dev = dev; - strcpy(tunnel->parms.name, dev->name); memcpy(dev->dev_addr, &tunnel->parms.iph.saddr, 4); memcpy(dev->broadcast, &tunnel->parms.iph.daddr, 4); @@ -825,6 +826,7 @@ static void ipip_destroy_tunnels(struct ipip_net *ipn, struct list_head *head) static int __net_init ipip_init_net(struct net *net) { struct ipip_net *ipn = net_generic(net, ipip_net_id); + struct ip_tunnel *t; int err; ipn->tunnels[0] = ipn->tunnels_wc; @@ -848,6 +850,9 @@ static int __net_init ipip_init_net(struct net *net) if ((err = register_netdev(ipn->fb_tunnel_dev))) goto err_reg_dev; + t = netdev_priv(ipn->fb_tunnel_dev); + + strcpy(t->parms.name, ipn->fb_tunnel_dev->name); return 0; err_reg_dev: diff --git a/net/ipv4/netfilter.c b/net/ipv4/netfilter.c index 9899619ab9b..4f47e064e26 100644 --- a/net/ipv4/netfilter.c +++ b/net/ipv4/netfilter.c @@ -64,7 +64,8 @@ int ip_route_me_harder(struct sk_buff *skb, unsigned addr_type) /* Change in oif may mean change in hh_len. */ hh_len = skb_dst(skb)->dev->hard_header_len; if (skb_headroom(skb) < hh_len && - pskb_expand_head(skb, hh_len - skb_headroom(skb), 0, GFP_ATOMIC)) + pskb_expand_head(skb, HH_DATA_ALIGN(hh_len - skb_headroom(skb)), + 0, GFP_ATOMIC)) return -1; return 0; diff --git a/net/ipv4/netfilter/Kconfig b/net/ipv4/netfilter/Kconfig index 1dfc18a03fd..f19f2182894 100644 --- a/net/ipv4/netfilter/Kconfig +++ b/net/ipv4/netfilter/Kconfig @@ -325,7 +325,6 @@ config IP_NF_TARGET_TTL # raw + specific targets config IP_NF_RAW tristate 'raw table support (required for NOTRACK/TRACE)' - depends on NETFILTER_ADVANCED help This option adds a `raw' table to iptables. This table is the very first in the netfilter framework and hooks in at the PREROUTING diff --git a/net/ipv4/ping.c b/net/ipv4/ping.c index a06f73fdb3c..43d4c3b2236 100644 --- a/net/ipv4/ping.c +++ b/net/ipv4/ping.c @@ -339,7 +339,6 @@ void ping_err(struct sk_buff *skb, u32 info) sk = ping_v4_lookup(net, iph->daddr, iph->saddr, ntohs(icmph->un.echo.id), skb->dev->ifindex); if (sk == NULL) { - ICMP_INC_STATS_BH(net, ICMP_MIB_INERRORS); pr_debug("no socket, dropping\n"); return; /* No socket for error */ } @@ -679,7 +678,6 @@ static int ping_queue_rcv_skb(struct sock *sk, struct sk_buff *skb) pr_debug("ping_queue_rcv_skb(sk=%p,sk->num=%d,skb=%p)\n", inet_sk(sk), inet_sk(sk)->inet_num, skb); if (sock_queue_rcv_skb(sk, skb) < 0) { - ICMP_INC_STATS_BH(sock_net(sk), ICMP_MIB_INERRORS); kfree_skb(skb); pr_debug("ping_queue_rcv_skb -> failed\n"); return -1; diff --git a/net/ipv4/route.c b/net/ipv4/route.c index 155138d8ec8..94cdbc55ca7 100644 --- a/net/ipv4/route.c +++ b/net/ipv4/route.c @@ -91,6 +91,7 @@ #include <linux/rcupdate.h> #include <linux/times.h> #include <linux/slab.h> +#include <linux/prefetch.h> #include <net/dst.h> #include <net/net_namespace.h> #include <net/protocol.h> @@ -112,7 +113,7 @@ #include <net/secure_seq.h> #define RT_FL_TOS(oldflp4) \ - ((u32)(oldflp4->flowi4_tos & (IPTOS_RT_MASK | RTO_ONLINK))) + ((oldflp4)->flowi4_tos & (IPTOS_RT_MASK | RTO_ONLINK)) #define IP_MAX_MTU 0xFFF0 @@ -120,6 +121,7 @@ static int ip_rt_max_size; static int ip_rt_gc_timeout __read_mostly = RT_GC_TIMEOUT; +static int ip_rt_gc_interval __read_mostly = 60 * HZ; static int ip_rt_gc_min_interval __read_mostly = HZ / 2; static int ip_rt_redirect_number __read_mostly = 9; static int ip_rt_redirect_load __read_mostly = HZ / 50; @@ -131,6 +133,10 @@ static int ip_rt_mtu_expires __read_mostly = 10 * 60 * HZ; static int ip_rt_min_pmtu __read_mostly = 512 + 20 + 20; static int ip_rt_min_advmss __read_mostly = 256; static int rt_chain_length_max __read_mostly = 20; +static int redirect_genid; + +static struct delayed_work expires_work; +static unsigned long expires_ljiffies; /* * Interface to generic destination cache. @@ -138,7 +144,7 @@ static int rt_chain_length_max __read_mostly = 20; static struct dst_entry *ipv4_dst_check(struct dst_entry *dst, u32 cookie); static unsigned int ipv4_default_advmss(const struct dst_entry *dst); -static unsigned int ipv4_default_mtu(const struct dst_entry *dst); +static unsigned int ipv4_mtu(const struct dst_entry *dst); static void ipv4_dst_destroy(struct dst_entry *dst); static struct dst_entry *ipv4_negative_advice(struct dst_entry *dst); static void ipv4_link_failure(struct sk_buff *skb); @@ -193,7 +199,7 @@ static struct dst_ops ipv4_dst_ops = { .gc = rt_garbage_collect, .check = ipv4_dst_check, .default_advmss = ipv4_default_advmss, - .default_mtu = ipv4_default_mtu, + .mtu = ipv4_mtu, .cow_metrics = ipv4_cow_metrics, .destroy = ipv4_dst_destroy, .ifdown = ipv4_dst_ifdown, @@ -416,9 +422,13 @@ static int rt_cache_seq_show(struct seq_file *seq, void *v) else { struct rtable *r = v; struct neighbour *n; - int len; + int len, HHUptod; + rcu_read_lock(); n = dst_get_neighbour(&r->dst); + HHUptod = (n && (n->nud_state & NUD_CONNECTED)) ? 1 : 0; + rcu_read_unlock(); + seq_printf(seq, "%s\t%08X\t%08X\t%8X\t%d\t%u\t%d\t" "%08X\t%d\t%u\t%u\t%02X\t%d\t%1d\t%08X%n", r->dst.dev ? r->dst.dev->name : "*", @@ -432,7 +442,7 @@ static int rt_cache_seq_show(struct seq_file *seq, void *v) dst_metric(&r->dst, RTAX_RTTVAR)), r->rt_key_tos, -1, - (n && (n->nud_state & NUD_CONNECTED)) ? 1 : 0, + HHUptod, r->rt_spec_dst, &len); seq_printf(seq, "%*s\n", 127 - len, ""); @@ -825,6 +835,97 @@ static int has_noalias(const struct rtable *head, const struct rtable *rth) return ONE; } +static void rt_check_expire(void) +{ + static unsigned int rover; + unsigned int i = rover, goal; + struct rtable *rth; + struct rtable __rcu **rthp; + unsigned long samples = 0; + unsigned long sum = 0, sum2 = 0; + unsigned long delta; + u64 mult; + + delta = jiffies - expires_ljiffies; + expires_ljiffies = jiffies; + mult = ((u64)delta) << rt_hash_log; + if (ip_rt_gc_timeout > 1) + do_div(mult, ip_rt_gc_timeout); + goal = (unsigned int)mult; + if (goal > rt_hash_mask) + goal = rt_hash_mask + 1; + for (; goal > 0; goal--) { + unsigned long tmo = ip_rt_gc_timeout; + unsigned long length; + + i = (i + 1) & rt_hash_mask; + rthp = &rt_hash_table[i].chain; + + if (need_resched()) + cond_resched(); + + samples++; + + if (rcu_dereference_raw(*rthp) == NULL) + continue; + length = 0; + spin_lock_bh(rt_hash_lock_addr(i)); + while ((rth = rcu_dereference_protected(*rthp, + lockdep_is_held(rt_hash_lock_addr(i)))) != NULL) { + prefetch(rth->dst.rt_next); + if (rt_is_expired(rth)) { + *rthp = rth->dst.rt_next; + rt_free(rth); + continue; + } + if (rth->dst.expires) { + /* Entry is expired even if it is in use */ + if (time_before_eq(jiffies, rth->dst.expires)) { +nofree: + tmo >>= 1; + rthp = &rth->dst.rt_next; + /* + * We only count entries on + * a chain with equal hash inputs once + * so that entries for different QOS + * levels, and other non-hash input + * attributes don't unfairly skew + * the length computation + */ + length += has_noalias(rt_hash_table[i].chain, rth); + continue; + } + } else if (!rt_may_expire(rth, tmo, ip_rt_gc_timeout)) + goto nofree; + + /* Cleanup aged off entries. */ + *rthp = rth->dst.rt_next; + rt_free(rth); + } + spin_unlock_bh(rt_hash_lock_addr(i)); + sum += length; + sum2 += length*length; + } + if (samples) { + unsigned long avg = sum / samples; + unsigned long sd = int_sqrt(sum2 / samples - avg*avg); + rt_chain_length_max = max_t(unsigned long, + ip_rt_gc_elasticity, + (avg + 4*sd) >> FRACT_BITS); + } + rover = i; +} + +/* + * rt_worker_func() is run in process context. + * we call rt_check_expire() to scan part of the hash table + */ +static void rt_worker_func(struct work_struct *work) +{ + rt_check_expire(); + schedule_delayed_work(&expires_work, ip_rt_gc_interval); +} + /* * Perturbation of rt_genid by a small quantity [1..256] * Using 8 bits of shuffling ensure we can call rt_cache_invalidate() @@ -837,6 +938,7 @@ static void rt_cache_invalidate(struct net *net) get_random_bytes(&shuffle, sizeof(shuffle)); atomic_add(shuffle + 1U, &net->ipv4.rt_genid); + redirect_genid++; } /* @@ -1265,7 +1367,7 @@ void __ip_select_ident(struct iphdr *iph, struct dst_entry *dst, int more) { struct rtable *rt = (struct rtable *) dst; - if (rt) { + if (rt && !(rt->dst.flags & DST_NOPEER)) { if (rt->peer == NULL) rt_bind_peer(rt, rt->rt_dst, 1); @@ -1276,7 +1378,7 @@ void __ip_select_ident(struct iphdr *iph, struct dst_entry *dst, int more) iph->id = htons(inet_getid(rt->peer, more)); return; } - } else + } else if (!rt) printk(KERN_DEBUG "rt_bind_peer(0) @%p\n", __builtin_return_address(0)); @@ -1304,16 +1406,40 @@ static void rt_del(unsigned hash, struct rtable *rt) spin_unlock_bh(rt_hash_lock_addr(hash)); } +static void check_peer_redir(struct dst_entry *dst, struct inet_peer *peer) +{ + struct rtable *rt = (struct rtable *) dst; + __be32 orig_gw = rt->rt_gateway; + struct neighbour *n, *old_n; + + dst_confirm(&rt->dst); + + rt->rt_gateway = peer->redirect_learned.a4; + + n = ipv4_neigh_lookup(&rt->dst, &rt->rt_gateway); + if (IS_ERR(n)) { + rt->rt_gateway = orig_gw; + return; + } + old_n = xchg(&rt->dst._neighbour, n); + if (old_n) + neigh_release(old_n); + if (!(n->nud_state & NUD_VALID)) { + neigh_event_send(n, NULL); + } else { + rt->rt_flags |= RTCF_REDIRECTED; + call_netevent_notifiers(NETEVENT_NEIGH_UPDATE, n); + } +} + /* called in rcu_read_lock() section */ void ip_rt_redirect(__be32 old_gw, __be32 daddr, __be32 new_gw, __be32 saddr, struct net_device *dev) { int s, i; struct in_device *in_dev = __in_dev_get_rcu(dev); - struct rtable *rt; __be32 skeys[2] = { saddr, 0 }; int ikeys[2] = { dev->ifindex, 0 }; - struct flowi4 fl4; struct inet_peer *peer; struct net *net; @@ -1336,33 +1462,44 @@ void ip_rt_redirect(__be32 old_gw, __be32 daddr, __be32 new_gw, goto reject_redirect; } - memset(&fl4, 0, sizeof(fl4)); - fl4.daddr = daddr; for (s = 0; s < 2; s++) { for (i = 0; i < 2; i++) { - fl4.flowi4_oif = ikeys[i]; - fl4.saddr = skeys[s]; - rt = __ip_route_output_key(net, &fl4); - if (IS_ERR(rt)) - continue; - - if (rt->dst.error || rt->dst.dev != dev || - rt->rt_gateway != old_gw) { - ip_rt_put(rt); - continue; - } - - if (!rt->peer) - rt_bind_peer(rt, rt->rt_dst, 1); + unsigned int hash; + struct rtable __rcu **rthp; + struct rtable *rt; + + hash = rt_hash(daddr, skeys[s], ikeys[i], rt_genid(net)); + + rthp = &rt_hash_table[hash].chain; + + while ((rt = rcu_dereference(*rthp)) != NULL) { + rthp = &rt->dst.rt_next; + + if (rt->rt_key_dst != daddr || + rt->rt_key_src != skeys[s] || + rt->rt_oif != ikeys[i] || + rt_is_input_route(rt) || + rt_is_expired(rt) || + !net_eq(dev_net(rt->dst.dev), net) || + rt->dst.error || + rt->dst.dev != dev || + rt->rt_gateway != old_gw) + continue; - peer = rt->peer; - if (peer) { - peer->redirect_learned.a4 = new_gw; - atomic_inc(&__rt_peer_genid); + if (!rt->peer) + rt_bind_peer(rt, rt->rt_dst, 1); + + peer = rt->peer; + if (peer) { + if (peer->redirect_learned.a4 != new_gw || + peer->redirect_genid != redirect_genid) { + peer->redirect_learned.a4 = new_gw; + peer->redirect_genid = redirect_genid; + atomic_inc(&__rt_peer_genid); + } + check_peer_redir(&rt->dst, peer); + } } - - ip_rt_put(rt); - return; } } return; @@ -1649,40 +1786,9 @@ static void ip_rt_update_pmtu(struct dst_entry *dst, u32 mtu) } } -static int check_peer_redir(struct dst_entry *dst, struct inet_peer *peer) -{ - struct rtable *rt = (struct rtable *) dst; - __be32 orig_gw = rt->rt_gateway; - struct neighbour *n, *old_n; - - dst_confirm(&rt->dst); - - rt->rt_gateway = peer->redirect_learned.a4; - n = ipv4_neigh_lookup(&rt->dst, &rt->rt_gateway); - if (IS_ERR(n)) - return PTR_ERR(n); - old_n = xchg(&rt->dst._neighbour, n); - if (old_n) - neigh_release(old_n); - if (!n || !(n->nud_state & NUD_VALID)) { - if (n) - neigh_event_send(n, NULL); - rt->rt_gateway = orig_gw; - return -EAGAIN; - } else { - rt->rt_flags |= RTCF_REDIRECTED; - call_netevent_notifiers(NETEVENT_NEIGH_UPDATE, n); - } - return 0; -} - -static struct dst_entry *ipv4_dst_check(struct dst_entry *dst, u32 cookie) +static void ipv4_validate_peer(struct rtable *rt) { - struct rtable *rt = (struct rtable *) dst; - - if (rt_is_expired(rt)) - return NULL; if (rt->rt_peer_genid != rt_peer_genid()) { struct inet_peer *peer; @@ -1691,17 +1797,26 @@ static struct dst_entry *ipv4_dst_check(struct dst_entry *dst, u32 cookie) peer = rt->peer; if (peer) { - check_peer_pmtu(dst, peer); + check_peer_pmtu(&rt->dst, peer); + if (peer->redirect_genid != redirect_genid) + peer->redirect_learned.a4 = 0; if (peer->redirect_learned.a4 && - peer->redirect_learned.a4 != rt->rt_gateway) { - if (check_peer_redir(dst, peer)) - return NULL; - } + peer->redirect_learned.a4 != rt->rt_gateway) + check_peer_redir(&rt->dst, peer); } rt->rt_peer_genid = rt_peer_genid(); } +} + +static struct dst_entry *ipv4_dst_check(struct dst_entry *dst, u32 cookie) +{ + struct rtable *rt = (struct rtable *) dst; + + if (rt_is_expired(rt)) + return NULL; + ipv4_validate_peer(rt); return dst; } @@ -1806,12 +1921,17 @@ static unsigned int ipv4_default_advmss(const struct dst_entry *dst) return advmss; } -static unsigned int ipv4_default_mtu(const struct dst_entry *dst) +static unsigned int ipv4_mtu(const struct dst_entry *dst) { - unsigned int mtu = dst->dev->mtu; + const struct rtable *rt = (const struct rtable *) dst; + unsigned int mtu = dst_metric_raw(dst, RTAX_MTU); + + if (mtu && rt_is_output_route(rt)) + return mtu; + + mtu = dst->dev->mtu; if (unlikely(dst_metric_locked(dst, RTAX_MTU))) { - const struct rtable *rt = (const struct rtable *) dst; if (rt->rt_gateway != rt->rt_dst && mtu > 576) mtu = 576; @@ -1844,6 +1964,8 @@ static void rt_init_metrics(struct rtable *rt, const struct flowi4 *fl4, dst_init_metrics(&rt->dst, peer->metrics, false); check_peer_pmtu(&rt->dst, peer); + if (peer->redirect_genid != redirect_genid) + peer->redirect_learned.a4 = 0; if (peer->redirect_learned.a4 && peer->redirect_learned.a4 != rt->rt_gateway) { rt->rt_gateway = peer->redirect_learned.a4; @@ -2349,6 +2471,7 @@ int ip_route_input_common(struct sk_buff *skb, __be32 daddr, __be32 saddr, rth->rt_mark == skb->mark && net_eq(dev_net(rth->dst.dev), net) && !rt_is_expired(rth)) { + ipv4_validate_peer(rth); if (noref) { dst_use_noref(&rth->dst, jiffies); skb_dst_set_noref(skb, &rth->dst); @@ -2407,11 +2530,11 @@ EXPORT_SYMBOL(ip_route_input_common); static struct rtable *__mkroute_output(const struct fib_result *res, const struct flowi4 *fl4, __be32 orig_daddr, __be32 orig_saddr, - int orig_oif, struct net_device *dev_out, + int orig_oif, __u8 orig_rtos, + struct net_device *dev_out, unsigned int flags) { struct fib_info *fi = res->fi; - u32 tos = RT_FL_TOS(fl4); struct in_device *in_dev; u16 type = res->type; struct rtable *rth; @@ -2462,7 +2585,7 @@ static struct rtable *__mkroute_output(const struct fib_result *res, rth->rt_genid = rt_genid(dev_net(dev_out)); rth->rt_flags = flags; rth->rt_type = type; - rth->rt_key_tos = tos; + rth->rt_key_tos = orig_rtos; rth->rt_dst = fl4->daddr; rth->rt_src = fl4->saddr; rth->rt_route_iif = 0; @@ -2512,7 +2635,7 @@ static struct rtable *__mkroute_output(const struct fib_result *res, static struct rtable *ip_route_output_slow(struct net *net, struct flowi4 *fl4) { struct net_device *dev_out = NULL; - u32 tos = RT_FL_TOS(fl4); + __u8 tos = RT_FL_TOS(fl4); unsigned int flags = 0; struct fib_result res; struct rtable *rth; @@ -2688,7 +2811,7 @@ static struct rtable *ip_route_output_slow(struct net *net, struct flowi4 *fl4) make_route: rth = __mkroute_output(&res, fl4, orig_daddr, orig_saddr, orig_oif, - dev_out, flags); + tos, dev_out, flags); if (!IS_ERR(rth)) { unsigned int hash; @@ -2724,6 +2847,7 @@ struct rtable *__ip_route_output_key(struct net *net, struct flowi4 *flp4) (IPTOS_RT_MASK | RTO_ONLINK)) && net_eq(dev_net(rth->dst.dev), net) && !rt_is_expired(rth)) { + ipv4_validate_peer(rth); dst_use(&rth->dst, jiffies); RT_CACHE_STAT_INC(out_hit); rcu_read_unlock_bh(); @@ -2747,9 +2871,11 @@ static struct dst_entry *ipv4_blackhole_dst_check(struct dst_entry *dst, u32 coo return NULL; } -static unsigned int ipv4_blackhole_default_mtu(const struct dst_entry *dst) +static unsigned int ipv4_blackhole_mtu(const struct dst_entry *dst) { - return 0; + unsigned int mtu = dst_metric_raw(dst, RTAX_MTU); + + return mtu ? : dst->dev->mtu; } static void ipv4_rt_blackhole_update_pmtu(struct dst_entry *dst, u32 mtu) @@ -2767,7 +2893,7 @@ static struct dst_ops ipv4_dst_blackhole_ops = { .protocol = cpu_to_be16(ETH_P_IP), .destroy = ipv4_dst_destroy, .check = ipv4_blackhole_dst_check, - .default_mtu = ipv4_blackhole_default_mtu, + .mtu = ipv4_blackhole_mtu, .default_advmss = ipv4_default_advmss, .update_pmtu = ipv4_rt_blackhole_update_pmtu, .cow_metrics = ipv4_rt_blackhole_cow_metrics, @@ -2845,7 +2971,7 @@ static int rt_fill_info(struct net *net, struct rtable *rt = skb_rtable(skb); struct rtmsg *r; struct nlmsghdr *nlh; - long expires = 0; + unsigned long expires = 0; const struct inet_peer *peer = rt->peer; u32 id = 0, ts = 0, tsage = 0, error; @@ -2902,8 +3028,12 @@ static int rt_fill_info(struct net *net, tsage = get_seconds() - peer->tcp_ts_stamp; } expires = ACCESS_ONCE(peer->pmtu_expires); - if (expires) - expires -= jiffies; + if (expires) { + if (time_before(jiffies, expires)) + expires -= jiffies; + else + expires = 0; + } } if (rt_is_input_route(rt)) { @@ -3145,6 +3275,13 @@ static ctl_table ipv4_route_table[] = { .proc_handler = proc_dointvec_jiffies, }, { + .procname = "gc_interval", + .data = &ip_rt_gc_interval, + .maxlen = sizeof(int), + .mode = 0644, + .proc_handler = proc_dointvec_jiffies, + }, + { .procname = "redirect_load", .data = &ip_rt_redirect_load, .maxlen = sizeof(int), @@ -3354,6 +3491,11 @@ int __init ip_rt_init(void) devinet_init(); ip_fib_init(); + INIT_DELAYED_WORK_DEFERRABLE(&expires_work, rt_worker_func); + expires_ljiffies = jiffies; + schedule_delayed_work(&expires_work, + net_random() % ip_rt_gc_interval + ip_rt_gc_interval); + if (ip_rt_proc_init()) printk(KERN_ERR "Unable to create route proc files\n"); #ifdef CONFIG_XFRM diff --git a/net/ipv4/tcp_ipv4.c b/net/ipv4/tcp_ipv4.c index a7443159c40..a9db4b1a221 100644 --- a/net/ipv4/tcp_ipv4.c +++ b/net/ipv4/tcp_ipv4.c @@ -1510,6 +1510,7 @@ exit: NET_INC_STATS_BH(sock_net(sk), LINUX_MIB_LISTENDROPS); return NULL; put_and_exit: + tcp_clear_xmit_timers(newsk); bh_unlock_sock(newsk); sock_put(newsk); goto exit; diff --git a/net/ipv4/tcp_output.c b/net/ipv4/tcp_output.c index 980b98f6288..63170e29754 100644 --- a/net/ipv4/tcp_output.c +++ b/net/ipv4/tcp_output.c @@ -1382,7 +1382,7 @@ static inline int tcp_minshall_check(const struct tcp_sock *tp) /* Return 0, if packet can be sent now without violation Nagle's rules: * 1. It is full sized. * 2. Or it contains FIN. (already checked by caller) - * 3. Or TCP_NODELAY was set. + * 3. Or TCP_CORK is not set, and TCP_NODELAY is set. * 4. Or TCP_CORK is not set, and all sent packets are ACKed. * With Minshall's modification: all sent small packets are ACKed. */ diff --git a/net/ipv4/udp.c b/net/ipv4/udp.c index ab0966df1e2..5a65eeac1d2 100644 --- a/net/ipv4/udp.c +++ b/net/ipv4/udp.c @@ -1164,7 +1164,7 @@ int udp_recvmsg(struct kiocb *iocb, struct sock *sk, struct msghdr *msg, struct inet_sock *inet = inet_sk(sk); struct sockaddr_in *sin = (struct sockaddr_in *)msg->msg_name; struct sk_buff *skb; - unsigned int ulen; + unsigned int ulen, copied; int peeked; int err; int is_udplite = IS_UDPLITE(sk); @@ -1186,9 +1186,10 @@ try_again: goto out; ulen = skb->len - sizeof(struct udphdr); - if (len > ulen) - len = ulen; - else if (len < ulen) + copied = len; + if (copied > ulen) + copied = ulen; + else if (copied < ulen) msg->msg_flags |= MSG_TRUNC; /* @@ -1197,14 +1198,14 @@ try_again: * coverage checksum (UDP-Lite), do it before the copy. */ - if (len < ulen || UDP_SKB_CB(skb)->partial_cov) { + if (copied < ulen || UDP_SKB_CB(skb)->partial_cov) { if (udp_lib_checksum_complete(skb)) goto csum_copy_err; } if (skb_csum_unnecessary(skb)) err = skb_copy_datagram_iovec(skb, sizeof(struct udphdr), - msg->msg_iov, len); + msg->msg_iov, copied); else { err = skb_copy_and_csum_datagram_iovec(skb, sizeof(struct udphdr), @@ -1233,7 +1234,7 @@ try_again: if (inet->cmsg_flags) ip_cmsg_recv(msg, skb); - err = len; + err = copied; if (flags & MSG_TRUNC) err = ulen; diff --git a/net/ipv6/addrconf.c b/net/ipv6/addrconf.c index cf88df82e2c..36806def8cf 100644 --- a/net/ipv6/addrconf.c +++ b/net/ipv6/addrconf.c @@ -1805,7 +1805,8 @@ static struct inet6_dev *addrconf_add_dev(struct net_device *dev) return ERR_PTR(-EACCES); /* Add default multicast route */ - addrconf_add_mroute(dev); + if (!(dev->flags & IFF_LOOPBACK)) + addrconf_add_mroute(dev); /* Add link local route */ addrconf_add_lroute(dev); diff --git a/net/ipv6/ah6.c b/net/ipv6/ah6.c index 2195ae65192..4c0f894d084 100644 --- a/net/ipv6/ah6.c +++ b/net/ipv6/ah6.c @@ -324,8 +324,6 @@ static void ah6_output_done(struct crypto_async_request *base, int err) #endif } - err = ah->nexthdr; - kfree(AH_SKB_CB(skb)->tmp); xfrm_output_resume(skb, err); } @@ -466,12 +464,12 @@ static void ah6_input_done(struct crypto_async_request *base, int err) if (err) goto out; + err = ah->nexthdr; + skb->network_header += ah_hlen; memcpy(skb_network_header(skb), work_iph, hdr_len); __skb_pull(skb, ah_hlen + hdr_len); skb_set_transport_header(skb, -hdr_len); - - err = ah->nexthdr; out: kfree(AH_SKB_CB(skb)->tmp); xfrm_input_resume(skb, err); @@ -583,8 +581,6 @@ static int ah6_input(struct xfrm_state *x, struct sk_buff *skb) if (err == -EINPROGRESS) goto out; - if (err == -EBUSY) - err = NET_XMIT_DROP; goto out_free; } diff --git a/net/ipv6/inet6_connection_sock.c b/net/ipv6/inet6_connection_sock.c index fee46d5a2f1..1567fb12039 100644 --- a/net/ipv6/inet6_connection_sock.c +++ b/net/ipv6/inet6_connection_sock.c @@ -85,7 +85,7 @@ struct dst_entry *inet6_csk_route_req(struct sock *sk, * request_sock (formerly open request) hash tables. */ static u32 inet6_synq_hash(const struct in6_addr *raddr, const __be16 rport, - const u32 rnd, const u16 synq_hsize) + const u32 rnd, const u32 synq_hsize) { u32 c; diff --git a/net/ipv6/ip6_input.c b/net/ipv6/ip6_input.c index 027c7ff6f1e..a46c64eb0a6 100644 --- a/net/ipv6/ip6_input.c +++ b/net/ipv6/ip6_input.c @@ -111,6 +111,14 @@ int ipv6_rcv(struct sk_buff *skb, struct net_device *dev, struct packet_type *pt ipv6_addr_loopback(&hdr->daddr)) goto err; + /* + * RFC4291 2.7 + * Multicast addresses must not be used as source addresses in IPv6 + * packets or appear in any Routing header. + */ + if (ipv6_addr_is_multicast(&hdr->saddr)) + goto err; + skb->transport_header = skb->network_header + sizeof(*hdr); IP6CB(skb)->nhoff = offsetof(struct ipv6hdr, nexthdr); diff --git a/net/ipv6/ip6_output.c b/net/ipv6/ip6_output.c index 84d0bd5cac9..ec562713db9 100644 --- a/net/ipv6/ip6_output.c +++ b/net/ipv6/ip6_output.c @@ -603,7 +603,7 @@ void ipv6_select_ident(struct frag_hdr *fhdr, struct rt6_info *rt) static atomic_t ipv6_fragmentation_id; int old, new; - if (rt) { + if (rt && !(rt->dst.flags & DST_NOPEER)) { struct inet_peer *peer; if (!rt->rt6i_peer) diff --git a/net/ipv6/ip6_tunnel.c b/net/ipv6/ip6_tunnel.c index bdc15c9003d..4e2e9ff67ef 100644 --- a/net/ipv6/ip6_tunnel.c +++ b/net/ipv6/ip6_tunnel.c @@ -289,6 +289,8 @@ static struct ip6_tnl *ip6_tnl_create(struct net *net, struct ip6_tnl_parm *p) if ((err = register_netdevice(dev)) < 0) goto failed_free; + strcpy(t->parms.name, dev->name); + dev_hold(dev); ip6_tnl_link(ip6n, t); return t; @@ -1407,7 +1409,6 @@ ip6_tnl_dev_init_gen(struct net_device *dev) struct ip6_tnl *t = netdev_priv(dev); t->dev = dev; - strcpy(t->parms.name, dev->name); dev->tstats = alloc_percpu(struct pcpu_tstats); if (!dev->tstats) return -ENOMEM; @@ -1487,6 +1488,7 @@ static void __net_exit ip6_tnl_destroy_tunnels(struct ip6_tnl_net *ip6n) static int __net_init ip6_tnl_init_net(struct net *net) { struct ip6_tnl_net *ip6n = net_generic(net, ip6_tnl_net_id); + struct ip6_tnl *t = NULL; int err; ip6n->tnls[0] = ip6n->tnls_wc; @@ -1507,6 +1509,10 @@ static int __net_init ip6_tnl_init_net(struct net *net) err = register_netdev(ip6n->fb_tnl_dev); if (err < 0) goto err_register; + + t = netdev_priv(ip6n->fb_tnl_dev); + + strcpy(t->parms.name, ip6n->fb_tnl_dev->name); return 0; err_register: diff --git a/net/ipv6/ipv6_sockglue.c b/net/ipv6/ipv6_sockglue.c index c99e3ee9781..26cb08c84b7 100644 --- a/net/ipv6/ipv6_sockglue.c +++ b/net/ipv6/ipv6_sockglue.c @@ -503,7 +503,7 @@ done: goto e_inval; if (val > 255 || val < -1) goto e_inval; - np->mcast_hops = val; + np->mcast_hops = (val == -1 ? IPV6_DEFAULT_MCASTHOPS : val); retv = 0; break; diff --git a/net/ipv6/ndisc.c b/net/ipv6/ndisc.c index 44e5b7f2a6c..0cb78d7ddaf 100644 --- a/net/ipv6/ndisc.c +++ b/net/ipv6/ndisc.c @@ -1571,7 +1571,7 @@ void ndisc_send_redirect(struct sk_buff *skb, struct neighbour *neigh, } if (!rt->rt6i_peer) rt6_bind_peer(rt, 1); - if (inet_peer_xrlim_allow(rt->rt6i_peer, 1*HZ)) + if (!inet_peer_xrlim_allow(rt->rt6i_peer, 1*HZ)) goto release; if (dev->addr_len) { diff --git a/net/ipv6/netfilter/Kconfig b/net/ipv6/netfilter/Kconfig index 448464844a2..f792b34cbe9 100644 --- a/net/ipv6/netfilter/Kconfig +++ b/net/ipv6/netfilter/Kconfig @@ -186,7 +186,6 @@ config IP6_NF_MANGLE config IP6_NF_RAW tristate 'raw table support (required for TRACE)' - depends on NETFILTER_ADVANCED help This option adds a `raw' table to ip6tables. This table is the very first in the netfilter framework and hooks in at the PREROUTING diff --git a/net/ipv6/route.c b/net/ipv6/route.c index 8473016bba4..b582a0a0f1c 100644 --- a/net/ipv6/route.c +++ b/net/ipv6/route.c @@ -77,7 +77,7 @@ static struct rt6_info *ip6_rt_copy(const struct rt6_info *ort, const struct in6_addr *dest); static struct dst_entry *ip6_dst_check(struct dst_entry *dst, u32 cookie); static unsigned int ip6_default_advmss(const struct dst_entry *dst); -static unsigned int ip6_default_mtu(const struct dst_entry *dst); +static unsigned int ip6_mtu(const struct dst_entry *dst); static struct dst_entry *ip6_negative_advice(struct dst_entry *); static void ip6_dst_destroy(struct dst_entry *); static void ip6_dst_ifdown(struct dst_entry *, @@ -144,7 +144,7 @@ static struct dst_ops ip6_dst_ops_template = { .gc_thresh = 1024, .check = ip6_dst_check, .default_advmss = ip6_default_advmss, - .default_mtu = ip6_default_mtu, + .mtu = ip6_mtu, .cow_metrics = ipv6_cow_metrics, .destroy = ip6_dst_destroy, .ifdown = ip6_dst_ifdown, @@ -155,9 +155,11 @@ static struct dst_ops ip6_dst_ops_template = { .neigh_lookup = ip6_neigh_lookup, }; -static unsigned int ip6_blackhole_default_mtu(const struct dst_entry *dst) +static unsigned int ip6_blackhole_mtu(const struct dst_entry *dst) { - return 0; + unsigned int mtu = dst_metric_raw(dst, RTAX_MTU); + + return mtu ? : dst->dev->mtu; } static void ip6_rt_blackhole_update_pmtu(struct dst_entry *dst, u32 mtu) @@ -175,7 +177,7 @@ static struct dst_ops ip6_dst_blackhole_ops = { .protocol = cpu_to_be16(ETH_P_IPV6), .destroy = ip6_dst_destroy, .check = ip6_dst_check, - .default_mtu = ip6_blackhole_default_mtu, + .mtu = ip6_blackhole_mtu, .default_advmss = ip6_default_advmss, .update_pmtu = ip6_rt_blackhole_update_pmtu, .cow_metrics = ip6_rt_blackhole_cow_metrics, @@ -726,7 +728,7 @@ static struct rt6_info *rt6_alloc_cow(const struct rt6_info *ort, int attempts = !in_softirq(); if (!(rt->rt6i_flags&RTF_GATEWAY)) { - if (rt->rt6i_dst.plen != 128 && + if (ort->rt6i_dst.plen != 128 && ipv6_addr_equal(&ort->rt6i_dst.addr, daddr)) rt->rt6i_flags |= RTF_ANYCAST; ipv6_addr_copy(&rt->rt6i_gateway, daddr); @@ -1041,10 +1043,15 @@ static unsigned int ip6_default_advmss(const struct dst_entry *dst) return mtu; } -static unsigned int ip6_default_mtu(const struct dst_entry *dst) +static unsigned int ip6_mtu(const struct dst_entry *dst) { - unsigned int mtu = IPV6_MIN_MTU; struct inet6_dev *idev; + unsigned int mtu = dst_metric_raw(dst, RTAX_MTU); + + if (mtu) + return mtu; + + mtu = IPV6_MIN_MTU; rcu_read_lock(); idev = __in6_dev_get(dst->dev); diff --git a/net/ipv6/sit.c b/net/ipv6/sit.c index a7a18602a04..96f3623618e 100644 --- a/net/ipv6/sit.c +++ b/net/ipv6/sit.c @@ -263,6 +263,8 @@ static struct ip_tunnel *ipip6_tunnel_locate(struct net *net, if (register_netdevice(dev) < 0) goto failed_free; + strcpy(nt->parms.name, dev->name); + dev_hold(dev); ipip6_tunnel_link(sitn, nt); @@ -1144,7 +1146,6 @@ static int ipip6_tunnel_init(struct net_device *dev) struct ip_tunnel *tunnel = netdev_priv(dev); tunnel->dev = dev; - strcpy(tunnel->parms.name, dev->name); memcpy(dev->dev_addr, &tunnel->parms.iph.saddr, 4); memcpy(dev->broadcast, &tunnel->parms.iph.daddr, 4); @@ -1207,6 +1208,7 @@ static void __net_exit sit_destroy_tunnels(struct sit_net *sitn, struct list_hea static int __net_init sit_init_net(struct net *net) { struct sit_net *sitn = net_generic(net, sit_net_id); + struct ip_tunnel *t; int err; sitn->tunnels[0] = sitn->tunnels_wc; @@ -1231,6 +1233,9 @@ static int __net_init sit_init_net(struct net *net) if ((err = register_netdev(sitn->fb_tunnel_dev))) goto err_reg_dev; + t = netdev_priv(sitn->fb_tunnel_dev); + + strcpy(t->parms.name, sitn->fb_tunnel_dev->name); return 0; err_reg_dev: diff --git a/net/ipv6/tcp_ipv6.c b/net/ipv6/tcp_ipv6.c index 36131d122a6..2dea4bb7b54 100644 --- a/net/ipv6/tcp_ipv6.c +++ b/net/ipv6/tcp_ipv6.c @@ -1255,6 +1255,13 @@ static int tcp_v6_conn_request(struct sock *sk, struct sk_buff *skb) if (!want_cookie || tmp_opt.tstamp_ok) TCP_ECN_create_request(req, tcp_hdr(skb)); + treq->iif = sk->sk_bound_dev_if; + + /* So that link locals have meaning */ + if (!sk->sk_bound_dev_if && + ipv6_addr_type(&treq->rmt_addr) & IPV6_ADDR_LINKLOCAL) + treq->iif = inet6_iif(skb); + if (!isn) { struct inet_peer *peer = NULL; @@ -1264,12 +1271,6 @@ static int tcp_v6_conn_request(struct sock *sk, struct sk_buff *skb) atomic_inc(&skb->users); treq->pktopts = skb; } - treq->iif = sk->sk_bound_dev_if; - - /* So that link locals have meaning */ - if (!sk->sk_bound_dev_if && - ipv6_addr_type(&treq->rmt_addr) & IPV6_ADDR_LINKLOCAL) - treq->iif = inet6_iif(skb); if (want_cookie) { isn = cookie_v6_init_sequence(sk, skb, &req->mss); diff --git a/net/ipv6/udp.c b/net/ipv6/udp.c index 846f4757eb8..8c254191518 100644 --- a/net/ipv6/udp.c +++ b/net/ipv6/udp.c @@ -340,7 +340,7 @@ int udpv6_recvmsg(struct kiocb *iocb, struct sock *sk, struct ipv6_pinfo *np = inet6_sk(sk); struct inet_sock *inet = inet_sk(sk); struct sk_buff *skb; - unsigned int ulen; + unsigned int ulen, copied; int peeked; int err; int is_udplite = IS_UDPLITE(sk); @@ -363,9 +363,10 @@ try_again: goto out; ulen = skb->len - sizeof(struct udphdr); - if (len > ulen) - len = ulen; - else if (len < ulen) + copied = len; + if (copied > ulen) + copied = ulen; + else if (copied < ulen) msg->msg_flags |= MSG_TRUNC; is_udp4 = (skb->protocol == htons(ETH_P_IP)); @@ -376,14 +377,14 @@ try_again: * coverage checksum (UDP-Lite), do it before the copy. */ - if (len < ulen || UDP_SKB_CB(skb)->partial_cov) { + if (copied < ulen || UDP_SKB_CB(skb)->partial_cov) { if (udp_lib_checksum_complete(skb)) goto csum_copy_err; } if (skb_csum_unnecessary(skb)) err = skb_copy_datagram_iovec(skb, sizeof(struct udphdr), - msg->msg_iov,len); + msg->msg_iov, copied ); else { err = skb_copy_and_csum_datagram_iovec(skb, sizeof(struct udphdr), msg->msg_iov); if (err == -EINVAL) @@ -432,7 +433,7 @@ try_again: datagram_recv_ctl(sk, msg, skb); } - err = len; + err = copied; if (flags & MSG_TRUNC) err = ulen; diff --git a/net/l2tp/l2tp_core.c b/net/l2tp/l2tp_core.c index bf8d50c6793..89ff8c67943 100644 --- a/net/l2tp/l2tp_core.c +++ b/net/l2tp/l2tp_core.c @@ -756,9 +756,6 @@ static int l2tp_udp_recv_core(struct l2tp_tunnel *tunnel, struct sk_buff *skb, goto error; } - /* Point to L2TP header */ - optr = ptr = skb->data; - /* Trace packet contents, if enabled */ if (tunnel->debug & L2TP_MSG_DATA) { length = min(32u, skb->len); @@ -769,12 +766,15 @@ static int l2tp_udp_recv_core(struct l2tp_tunnel *tunnel, struct sk_buff *skb, offset = 0; do { - printk(" %02X", ptr[offset]); + printk(" %02X", skb->data[offset]); } while (++offset < length); printk("\n"); } + /* Point to L2TP header */ + optr = ptr = skb->data; + /* Get L2TP header flags */ hdrflags = ntohs(*(__be16 *) ptr); @@ -1072,7 +1072,7 @@ int l2tp_xmit_skb(struct l2tp_session *session, struct sk_buff *skb, int hdr_len /* Get routing info from the tunnel socket */ skb_dst_drop(skb); - skb_dst_set(skb, dst_clone(__sk_dst_get(sk))); + skb_dst_set(skb, dst_clone(__sk_dst_check(sk, 0))); inet = inet_sk(sk); fl = &inet->cork.fl; diff --git a/net/llc/af_llc.c b/net/llc/af_llc.c index dfd3a648a55..a18e6c3d36e 100644 --- a/net/llc/af_llc.c +++ b/net/llc/af_llc.c @@ -833,15 +833,15 @@ static int llc_ui_recvmsg(struct kiocb *iocb, struct socket *sock, copied += used; len -= used; + /* For non stream protcols we get one packet per recvmsg call */ + if (sk->sk_type != SOCK_STREAM) + goto copy_uaddr; + if (!(flags & MSG_PEEK)) { sk_eat_skb(sk, skb, 0); *seq = 0; } - /* For non stream protcols we get one packet per recvmsg call */ - if (sk->sk_type != SOCK_STREAM) - goto copy_uaddr; - /* Partial read */ if (used + offset < skb->len) continue; @@ -857,6 +857,12 @@ copy_uaddr: } if (llc_sk(sk)->cmsg_flags) llc_cmsg_rcv(msg, skb); + + if (!(flags & MSG_PEEK)) { + sk_eat_skb(sk, skb, 0); + *seq = 0; + } + goto out; } diff --git a/net/mac80211/agg-tx.c b/net/mac80211/agg-tx.c index b3f65520e7a..2e4b961648d 100644 --- a/net/mac80211/agg-tx.c +++ b/net/mac80211/agg-tx.c @@ -161,6 +161,12 @@ int ___ieee80211_stop_tx_ba_session(struct sta_info *sta, u16 tid, return -ENOENT; } + /* if we're already stopping ignore any new requests to stop */ + if (test_bit(HT_AGG_STATE_STOPPING, &tid_tx->state)) { + spin_unlock_bh(&sta->lock); + return -EALREADY; + } + if (test_bit(HT_AGG_STATE_WANT_START, &tid_tx->state)) { /* not even started yet! */ ieee80211_assign_tid_tx(sta, tid, NULL); @@ -169,6 +175,8 @@ int ___ieee80211_stop_tx_ba_session(struct sta_info *sta, u16 tid, return 0; } + set_bit(HT_AGG_STATE_STOPPING, &tid_tx->state); + spin_unlock_bh(&sta->lock); #ifdef CONFIG_MAC80211_HT_DEBUG @@ -176,8 +184,6 @@ int ___ieee80211_stop_tx_ba_session(struct sta_info *sta, u16 tid, sta->sta.addr, tid); #endif /* CONFIG_MAC80211_HT_DEBUG */ - set_bit(HT_AGG_STATE_STOPPING, &tid_tx->state); - del_timer_sync(&tid_tx->addba_resp_timer); /* @@ -187,6 +193,20 @@ int ___ieee80211_stop_tx_ba_session(struct sta_info *sta, u16 tid, */ clear_bit(HT_AGG_STATE_OPERATIONAL, &tid_tx->state); + /* + * There might be a few packets being processed right now (on + * another CPU) that have already gotten past the aggregation + * check when it was still OPERATIONAL and consequently have + * IEEE80211_TX_CTL_AMPDU set. In that case, this code might + * call into the driver at the same time or even before the + * TX paths calls into it, which could confuse the driver. + * + * Wait for all currently running TX paths to finish before + * telling the driver. New packets will not go through since + * the aggregation session is no longer OPERATIONAL. + */ + synchronize_net(); + tid_tx->stop_initiator = initiator; tid_tx->tx_stop = tx; @@ -283,6 +303,38 @@ ieee80211_wake_queue_agg(struct ieee80211_local *local, int tid) __release(agg_queue); } +/* + * splice packets from the STA's pending to the local pending, + * requires a call to ieee80211_agg_splice_finish later + */ +static void __acquires(agg_queue) +ieee80211_agg_splice_packets(struct ieee80211_local *local, + struct tid_ampdu_tx *tid_tx, u16 tid) +{ + int queue = ieee80211_ac_from_tid(tid); + unsigned long flags; + + ieee80211_stop_queue_agg(local, tid); + + if (WARN(!tid_tx, "TID %d gone but expected when splicing aggregates" + " from the pending queue\n", tid)) + return; + + if (!skb_queue_empty(&tid_tx->pending)) { + spin_lock_irqsave(&local->queue_stop_reason_lock, flags); + /* copy over remaining packets */ + skb_queue_splice_tail_init(&tid_tx->pending, + &local->pending[queue]); + spin_unlock_irqrestore(&local->queue_stop_reason_lock, flags); + } +} + +static void __releases(agg_queue) +ieee80211_agg_splice_finish(struct ieee80211_local *local, u16 tid) +{ + ieee80211_wake_queue_agg(local, tid); +} + void ieee80211_tx_ba_session_handle_start(struct sta_info *sta, int tid) { struct tid_ampdu_tx *tid_tx; @@ -294,19 +346,17 @@ void ieee80211_tx_ba_session_handle_start(struct sta_info *sta, int tid) tid_tx = rcu_dereference_protected_tid_tx(sta, tid); /* - * While we're asking the driver about the aggregation, - * stop the AC queue so that we don't have to worry - * about frames that came in while we were doing that, - * which would require us to put them to the AC pending - * afterwards which just makes the code more complex. + * Start queuing up packets for this aggregation session. + * We're going to release them once the driver is OK with + * that. */ - ieee80211_stop_queue_agg(local, tid); - clear_bit(HT_AGG_STATE_WANT_START, &tid_tx->state); /* - * make sure no packets are being processed to get - * valid starting sequence number + * Make sure no packets are being processed. This ensures that + * we have a valid starting sequence number and that in-flight + * packets have been flushed out and no packets for this TID + * will go into the driver during the ampdu_action call. */ synchronize_net(); @@ -320,17 +370,15 @@ void ieee80211_tx_ba_session_handle_start(struct sta_info *sta, int tid) " tid %d\n", tid); #endif spin_lock_bh(&sta->lock); + ieee80211_agg_splice_packets(local, tid_tx, tid); ieee80211_assign_tid_tx(sta, tid, NULL); + ieee80211_agg_splice_finish(local, tid); spin_unlock_bh(&sta->lock); - ieee80211_wake_queue_agg(local, tid); kfree_rcu(tid_tx, rcu_head); return; } - /* we can take packets again now */ - ieee80211_wake_queue_agg(local, tid); - /* activate the timer for the recipient's addBA response */ mod_timer(&tid_tx->addba_resp_timer, jiffies + ADDBA_RESP_INTERVAL); #ifdef CONFIG_MAC80211_HT_DEBUG @@ -446,38 +494,6 @@ int ieee80211_start_tx_ba_session(struct ieee80211_sta *pubsta, u16 tid, } EXPORT_SYMBOL(ieee80211_start_tx_ba_session); -/* - * splice packets from the STA's pending to the local pending, - * requires a call to ieee80211_agg_splice_finish later - */ -static void __acquires(agg_queue) -ieee80211_agg_splice_packets(struct ieee80211_local *local, - struct tid_ampdu_tx *tid_tx, u16 tid) -{ - int queue = ieee80211_ac_from_tid(tid); - unsigned long flags; - - ieee80211_stop_queue_agg(local, tid); - - if (WARN(!tid_tx, "TID %d gone but expected when splicing aggregates" - " from the pending queue\n", tid)) - return; - - if (!skb_queue_empty(&tid_tx->pending)) { - spin_lock_irqsave(&local->queue_stop_reason_lock, flags); - /* copy over remaining packets */ - skb_queue_splice_tail_init(&tid_tx->pending, - &local->pending[queue]); - spin_unlock_irqrestore(&local->queue_stop_reason_lock, flags); - } -} - -static void __releases(agg_queue) -ieee80211_agg_splice_finish(struct ieee80211_local *local, u16 tid) -{ - ieee80211_wake_queue_agg(local, tid); -} - static void ieee80211_agg_tx_operational(struct ieee80211_local *local, struct sta_info *sta, u16 tid) { @@ -757,11 +773,27 @@ void ieee80211_process_addba_resp(struct ieee80211_local *local, goto out; } - del_timer(&tid_tx->addba_resp_timer); + del_timer_sync(&tid_tx->addba_resp_timer); #ifdef CONFIG_MAC80211_HT_DEBUG printk(KERN_DEBUG "switched off addBA timer for tid %d\n", tid); #endif + + /* + * addba_resp_timer may have fired before we got here, and + * caused WANT_STOP to be set. If the stop then was already + * processed further, STOPPING might be set. + */ + if (test_bit(HT_AGG_STATE_WANT_STOP, &tid_tx->state) || + test_bit(HT_AGG_STATE_STOPPING, &tid_tx->state)) { +#ifdef CONFIG_MAC80211_HT_DEBUG + printk(KERN_DEBUG + "got addBA resp for tid %d but we already gave up\n", + tid); +#endif + goto out; + } + /* * IEEE 802.11-2007 7.3.1.14: * In an ADDBA Response frame, when the Status Code field diff --git a/net/mac80211/debugfs_sta.c b/net/mac80211/debugfs_sta.c index c5f341798c1..3110cbdc501 100644 --- a/net/mac80211/debugfs_sta.c +++ b/net/mac80211/debugfs_sta.c @@ -274,9 +274,9 @@ static ssize_t sta_ht_capa_read(struct file *file, char __user *userbuf, PRINT_HT_CAP((htc->cap & BIT(10)), "HT Delayed Block Ack"); - PRINT_HT_CAP((htc->cap & BIT(11)), "Max AMSDU length: " - "3839 bytes"); PRINT_HT_CAP(!(htc->cap & BIT(11)), "Max AMSDU length: " + "3839 bytes"); + PRINT_HT_CAP((htc->cap & BIT(11)), "Max AMSDU length: " "7935 bytes"); /* diff --git a/net/mac80211/main.c b/net/mac80211/main.c index d999bf3b84e..cae443563ec 100644 --- a/net/mac80211/main.c +++ b/net/mac80211/main.c @@ -757,6 +757,12 @@ int ieee80211_register_hw(struct ieee80211_hw *hw) if (!local->int_scan_req) return -ENOMEM; + for (band = 0; band < IEEE80211_NUM_BANDS; band++) { + if (!local->hw.wiphy->bands[band]) + continue; + local->int_scan_req->rates[band] = (u32) -1; + } + /* if low-level driver supports AP, we also support VLAN */ if (local->hw.wiphy->interface_modes & BIT(NL80211_IFTYPE_AP)) { hw->wiphy->interface_modes |= BIT(NL80211_IFTYPE_AP_VLAN); diff --git a/net/mac80211/mlme.c b/net/mac80211/mlme.c index 72c8bea81a6..b1b1bb368f7 100644 --- a/net/mac80211/mlme.c +++ b/net/mac80211/mlme.c @@ -1487,6 +1487,7 @@ static bool ieee80211_assoc_success(struct ieee80211_work *wk, int i, j, err; bool have_higher_than_11mbit = false; u16 ap_ht_cap_flags; + int min_rate = INT_MAX, min_rate_index = -1; /* AssocResp and ReassocResp have identical structure */ @@ -1553,6 +1554,10 @@ static bool ieee80211_assoc_success(struct ieee80211_work *wk, rates |= BIT(j); if (is_basic) basic_rates |= BIT(j); + if (rate < min_rate) { + min_rate = rate; + min_rate_index = j; + } break; } } @@ -1570,11 +1575,25 @@ static bool ieee80211_assoc_success(struct ieee80211_work *wk, rates |= BIT(j); if (is_basic) basic_rates |= BIT(j); + if (rate < min_rate) { + min_rate = rate; + min_rate_index = j; + } break; } } } + /* + * some buggy APs don't advertise basic_rates. use the lowest + * supported rate instead. + */ + if (unlikely(!basic_rates) && min_rate_index >= 0) { + printk(KERN_DEBUG "%s: No basic rates in AssocResp. " + "Using min supported rate instead.\n", sdata->name); + basic_rates = BIT(min_rate_index); + } + sta->sta.supp_rates[wk->chan->band] = rates; sdata->vif.bss_conf.basic_rates = basic_rates; @@ -2269,6 +2288,7 @@ void ieee80211_sta_quiesce(struct ieee80211_sub_if_data *sdata) cancel_work_sync(&ifmgd->request_smps_work); + cancel_work_sync(&ifmgd->monitor_work); cancel_work_sync(&ifmgd->beacon_connection_loss_work); if (del_timer_sync(&ifmgd->timer)) set_bit(TMR_RUNNING_TIMER, &ifmgd->timers_running); @@ -2277,7 +2297,6 @@ void ieee80211_sta_quiesce(struct ieee80211_sub_if_data *sdata) if (del_timer_sync(&ifmgd->chswitch_timer)) set_bit(TMR_RUNNING_CHANSW, &ifmgd->timers_running); - cancel_work_sync(&ifmgd->monitor_work); /* these will just be re-established on connection */ del_timer_sync(&ifmgd->conn_mon_timer); del_timer_sync(&ifmgd->bcn_mon_timer); diff --git a/net/mac80211/rx.c b/net/mac80211/rx.c index bb53726cb04..fb123e2e081 100644 --- a/net/mac80211/rx.c +++ b/net/mac80211/rx.c @@ -141,8 +141,9 @@ ieee80211_add_rx_radiotap_header(struct ieee80211_local *local, pos++; /* IEEE80211_RADIOTAP_RATE */ - if (status->flag & RX_FLAG_HT) { + if (!rate || status->flag & RX_FLAG_HT) { /* + * Without rate information don't add it. If we have, * MCS information is a separate field in radiotap, * added below. The byte here is needed as padding * for the channel though, so initialise it to 0. @@ -163,12 +164,14 @@ ieee80211_add_rx_radiotap_header(struct ieee80211_local *local, else if (status->flag & RX_FLAG_HT) put_unaligned_le16(IEEE80211_CHAN_DYN | IEEE80211_CHAN_2GHZ, pos); - else if (rate->flags & IEEE80211_RATE_ERP_G) + else if (rate && rate->flags & IEEE80211_RATE_ERP_G) put_unaligned_le16(IEEE80211_CHAN_OFDM | IEEE80211_CHAN_2GHZ, pos); - else + else if (rate) put_unaligned_le16(IEEE80211_CHAN_CCK | IEEE80211_CHAN_2GHZ, pos); + else + put_unaligned_le16(IEEE80211_CHAN_2GHZ, pos); pos += 2; /* IEEE80211_RADIOTAP_DBM_ANTSIGNAL */ diff --git a/net/mac80211/sta_info.c b/net/mac80211/sta_info.c index ce962d2c878..8eaa746ec7a 100644 --- a/net/mac80211/sta_info.c +++ b/net/mac80211/sta_info.c @@ -1354,12 +1354,12 @@ ieee80211_sta_ps_deliver_response(struct sta_info *sta, * Use MoreData flag to indicate whether there are * more buffered frames for this STA */ - if (!more_data) - hdr->frame_control &= - cpu_to_le16(~IEEE80211_FCTL_MOREDATA); - else + if (more_data || !skb_queue_empty(&frames)) hdr->frame_control |= cpu_to_le16(IEEE80211_FCTL_MOREDATA); + else + hdr->frame_control &= + cpu_to_le16(~IEEE80211_FCTL_MOREDATA); if (ieee80211_is_data_qos(hdr->frame_control) || ieee80211_is_qos_nullfunc(hdr->frame_control)) diff --git a/net/mac80211/status.c b/net/mac80211/status.c index 80de436eae2..16518f38611 100644 --- a/net/mac80211/status.c +++ b/net/mac80211/status.c @@ -260,7 +260,7 @@ static void ieee80211_add_tx_radiotap_header(struct ieee80211_supported_band struct ieee80211_hdr *hdr = (struct ieee80211_hdr *) skb->data; struct ieee80211_radiotap_header *rthdr; unsigned char *pos; - __le16 txflags; + u16 txflags; rthdr = (struct ieee80211_radiotap_header *) skb_push(skb, rtap_len); @@ -290,13 +290,13 @@ static void ieee80211_add_tx_radiotap_header(struct ieee80211_supported_band txflags = 0; if (!(info->flags & IEEE80211_TX_STAT_ACK) && !is_multicast_ether_addr(hdr->addr1)) - txflags |= cpu_to_le16(IEEE80211_RADIOTAP_F_TX_FAIL); + txflags |= IEEE80211_RADIOTAP_F_TX_FAIL; if ((info->status.rates[0].flags & IEEE80211_TX_RC_USE_RTS_CTS) || (info->status.rates[0].flags & IEEE80211_TX_RC_USE_CTS_PROTECT)) - txflags |= cpu_to_le16(IEEE80211_RADIOTAP_F_TX_CTS); + txflags |= IEEE80211_RADIOTAP_F_TX_CTS; else if (info->status.rates[0].flags & IEEE80211_TX_RC_USE_RTS_CTS) - txflags |= cpu_to_le16(IEEE80211_RADIOTAP_F_TX_RTS); + txflags |= IEEE80211_RADIOTAP_F_TX_RTS; put_unaligned_le16(txflags, pos); pos += 2; diff --git a/net/mac80211/util.c b/net/mac80211/util.c index 51e256c5fb7..d5230ecc784 100644 --- a/net/mac80211/util.c +++ b/net/mac80211/util.c @@ -881,6 +881,8 @@ struct sk_buff *ieee80211_build_probe_req(struct ieee80211_sub_if_data *sdata, skb = ieee80211_probereq_get(&local->hw, &sdata->vif, ssid, ssid_len, buf, buf_len); + if (!skb) + goto out; if (dst) { mgmt = (struct ieee80211_mgmt *) skb->data; @@ -889,6 +891,8 @@ struct sk_buff *ieee80211_build_probe_req(struct ieee80211_sub_if_data *sdata, } IEEE80211_SKB_CB(skb)->flags |= IEEE80211_TX_INTFL_DONT_ENCRYPT; + + out: kfree(buf); return skb; @@ -1035,7 +1039,6 @@ int ieee80211_reconfig(struct ieee80211_local *local) struct ieee80211_sub_if_data, u.ap); - memset(&sta->sta.drv_priv, 0, hw->sta_data_size); WARN_ON(drv_sta_add(local, sdata, &sta->sta)); } } diff --git a/net/netfilter/Kconfig b/net/netfilter/Kconfig index 8260b13d93c..d5597b759ba 100644 --- a/net/netfilter/Kconfig +++ b/net/netfilter/Kconfig @@ -201,7 +201,6 @@ config NF_CONNTRACK_BROADCAST config NF_CONNTRACK_NETBIOS_NS tristate "NetBIOS name service protocol support" - depends on NETFILTER_ADVANCED select NF_CONNTRACK_BROADCAST help NetBIOS name service requests are sent as broadcast messages from an @@ -542,7 +541,6 @@ config NETFILTER_XT_TARGET_NOTRACK tristate '"NOTRACK" target support' depends on IP_NF_RAW || IP6_NF_RAW depends on NF_CONNTRACK - depends on NETFILTER_ADVANCED help The NOTRACK target allows a select rule to specify which packets *not* to enter the conntrack/NAT diff --git a/net/netfilter/ipset/ip_set_hash_ipport.c b/net/netfilter/ipset/ip_set_hash_ipport.c index 6ee10f5d59b..37d667e3f6f 100644 --- a/net/netfilter/ipset/ip_set_hash_ipport.c +++ b/net/netfilter/ipset/ip_set_hash_ipport.c @@ -158,7 +158,7 @@ hash_ipport4_uadt(struct ip_set *set, struct nlattr *tb[], const struct ip_set_hash *h = set->data; ipset_adtfn adtfn = set->variant->adt[adt]; struct hash_ipport4_elem data = { }; - u32 ip, ip_to, p = 0, port, port_to; + u32 ip, ip_to = 0, p = 0, port, port_to; u32 timeout = h->timeout; bool with_ports = false; int ret; diff --git a/net/netfilter/ipset/ip_set_hash_ipportip.c b/net/netfilter/ipset/ip_set_hash_ipportip.c index fb90e344e90..e69e2718fbe 100644 --- a/net/netfilter/ipset/ip_set_hash_ipportip.c +++ b/net/netfilter/ipset/ip_set_hash_ipportip.c @@ -162,7 +162,7 @@ hash_ipportip4_uadt(struct ip_set *set, struct nlattr *tb[], const struct ip_set_hash *h = set->data; ipset_adtfn adtfn = set->variant->adt[adt]; struct hash_ipportip4_elem data = { }; - u32 ip, ip_to, p = 0, port, port_to; + u32 ip, ip_to = 0, p = 0, port, port_to; u32 timeout = h->timeout; bool with_ports = false; int ret; diff --git a/net/netfilter/ipset/ip_set_hash_ipportnet.c b/net/netfilter/ipset/ip_set_hash_ipportnet.c index deb3e3dfa5f..64199b4e93c 100644 --- a/net/netfilter/ipset/ip_set_hash_ipportnet.c +++ b/net/netfilter/ipset/ip_set_hash_ipportnet.c @@ -184,7 +184,7 @@ hash_ipportnet4_uadt(struct ip_set *set, struct nlattr *tb[], const struct ip_set_hash *h = set->data; ipset_adtfn adtfn = set->variant->adt[adt]; struct hash_ipportnet4_elem data = { .cidr = HOST_MASK }; - u32 ip, ip_to, p = 0, port, port_to; + u32 ip, ip_to = 0, p = 0, port, port_to; u32 ip2_from = 0, ip2_to, ip2_last, ip2; u32 timeout = h->timeout; bool with_ports = false; diff --git a/net/netfilter/nf_conntrack_ecache.c b/net/netfilter/nf_conntrack_ecache.c index 6b368be937c..b62c4148b92 100644 --- a/net/netfilter/nf_conntrack_ecache.c +++ b/net/netfilter/nf_conntrack_ecache.c @@ -27,22 +27,17 @@ static DEFINE_MUTEX(nf_ct_ecache_mutex); -struct nf_ct_event_notifier __rcu *nf_conntrack_event_cb __read_mostly; -EXPORT_SYMBOL_GPL(nf_conntrack_event_cb); - -struct nf_exp_event_notifier __rcu *nf_expect_event_cb __read_mostly; -EXPORT_SYMBOL_GPL(nf_expect_event_cb); - /* deliver cached events and clear cache entry - must be called with locally * disabled softirqs */ void nf_ct_deliver_cached_events(struct nf_conn *ct) { + struct net *net = nf_ct_net(ct); unsigned long events; struct nf_ct_event_notifier *notify; struct nf_conntrack_ecache *e; rcu_read_lock(); - notify = rcu_dereference(nf_conntrack_event_cb); + notify = rcu_dereference(net->ct.nf_conntrack_event_cb); if (notify == NULL) goto out_unlock; @@ -83,19 +78,20 @@ out_unlock: } EXPORT_SYMBOL_GPL(nf_ct_deliver_cached_events); -int nf_conntrack_register_notifier(struct nf_ct_event_notifier *new) +int nf_conntrack_register_notifier(struct net *net, + struct nf_ct_event_notifier *new) { int ret = 0; struct nf_ct_event_notifier *notify; mutex_lock(&nf_ct_ecache_mutex); - notify = rcu_dereference_protected(nf_conntrack_event_cb, + notify = rcu_dereference_protected(net->ct.nf_conntrack_event_cb, lockdep_is_held(&nf_ct_ecache_mutex)); if (notify != NULL) { ret = -EBUSY; goto out_unlock; } - RCU_INIT_POINTER(nf_conntrack_event_cb, new); + RCU_INIT_POINTER(net->ct.nf_conntrack_event_cb, new); mutex_unlock(&nf_ct_ecache_mutex); return ret; @@ -105,32 +101,34 @@ out_unlock: } EXPORT_SYMBOL_GPL(nf_conntrack_register_notifier); -void nf_conntrack_unregister_notifier(struct nf_ct_event_notifier *new) +void nf_conntrack_unregister_notifier(struct net *net, + struct nf_ct_event_notifier *new) { struct nf_ct_event_notifier *notify; mutex_lock(&nf_ct_ecache_mutex); - notify = rcu_dereference_protected(nf_conntrack_event_cb, + notify = rcu_dereference_protected(net->ct.nf_conntrack_event_cb, lockdep_is_held(&nf_ct_ecache_mutex)); BUG_ON(notify != new); - RCU_INIT_POINTER(nf_conntrack_event_cb, NULL); + RCU_INIT_POINTER(net->ct.nf_conntrack_event_cb, NULL); mutex_unlock(&nf_ct_ecache_mutex); } EXPORT_SYMBOL_GPL(nf_conntrack_unregister_notifier); -int nf_ct_expect_register_notifier(struct nf_exp_event_notifier *new) +int nf_ct_expect_register_notifier(struct net *net, + struct nf_exp_event_notifier *new) { int ret = 0; struct nf_exp_event_notifier *notify; mutex_lock(&nf_ct_ecache_mutex); - notify = rcu_dereference_protected(nf_expect_event_cb, + notify = rcu_dereference_protected(net->ct.nf_expect_event_cb, lockdep_is_held(&nf_ct_ecache_mutex)); if (notify != NULL) { ret = -EBUSY; goto out_unlock; } - RCU_INIT_POINTER(nf_expect_event_cb, new); + RCU_INIT_POINTER(net->ct.nf_expect_event_cb, new); mutex_unlock(&nf_ct_ecache_mutex); return ret; @@ -140,15 +138,16 @@ out_unlock: } EXPORT_SYMBOL_GPL(nf_ct_expect_register_notifier); -void nf_ct_expect_unregister_notifier(struct nf_exp_event_notifier *new) +void nf_ct_expect_unregister_notifier(struct net *net, + struct nf_exp_event_notifier *new) { struct nf_exp_event_notifier *notify; mutex_lock(&nf_ct_ecache_mutex); - notify = rcu_dereference_protected(nf_expect_event_cb, + notify = rcu_dereference_protected(net->ct.nf_expect_event_cb, lockdep_is_held(&nf_ct_ecache_mutex)); BUG_ON(notify != new); - RCU_INIT_POINTER(nf_expect_event_cb, NULL); + RCU_INIT_POINTER(net->ct.nf_expect_event_cb, NULL); mutex_unlock(&nf_ct_ecache_mutex); } EXPORT_SYMBOL_GPL(nf_ct_expect_unregister_notifier); diff --git a/net/netfilter/nf_conntrack_netlink.c b/net/netfilter/nf_conntrack_netlink.c index e58aa9b1fe8..ef21b221f03 100644 --- a/net/netfilter/nf_conntrack_netlink.c +++ b/net/netfilter/nf_conntrack_netlink.c @@ -4,7 +4,7 @@ * (C) 2001 by Jay Schulist <jschlst@samba.org> * (C) 2002-2006 by Harald Welte <laforge@gnumonks.org> * (C) 2003 by Patrick Mchardy <kaber@trash.net> - * (C) 2005-2008 by Pablo Neira Ayuso <pablo@netfilter.org> + * (C) 2005-2011 by Pablo Neira Ayuso <pablo@netfilter.org> * * Initial connection tracking via netlink development funded and * generally made possible by Network Robots, Inc. (www.networkrobots.com) @@ -2163,6 +2163,54 @@ MODULE_ALIAS("ip_conntrack_netlink"); MODULE_ALIAS_NFNL_SUBSYS(NFNL_SUBSYS_CTNETLINK); MODULE_ALIAS_NFNL_SUBSYS(NFNL_SUBSYS_CTNETLINK_EXP); +static int __net_init ctnetlink_net_init(struct net *net) +{ +#ifdef CONFIG_NF_CONNTRACK_EVENTS + int ret; + + ret = nf_conntrack_register_notifier(net, &ctnl_notifier); + if (ret < 0) { + pr_err("ctnetlink_init: cannot register notifier.\n"); + goto err_out; + } + + ret = nf_ct_expect_register_notifier(net, &ctnl_notifier_exp); + if (ret < 0) { + pr_err("ctnetlink_init: cannot expect register notifier.\n"); + goto err_unreg_notifier; + } +#endif + return 0; + +#ifdef CONFIG_NF_CONNTRACK_EVENTS +err_unreg_notifier: + nf_conntrack_unregister_notifier(net, &ctnl_notifier); +err_out: + return ret; +#endif +} + +static void ctnetlink_net_exit(struct net *net) +{ +#ifdef CONFIG_NF_CONNTRACK_EVENTS + nf_ct_expect_unregister_notifier(net, &ctnl_notifier_exp); + nf_conntrack_unregister_notifier(net, &ctnl_notifier); +#endif +} + +static void __net_exit ctnetlink_net_exit_batch(struct list_head *net_exit_list) +{ + struct net *net; + + list_for_each_entry(net, net_exit_list, exit_list) + ctnetlink_net_exit(net); +} + +static struct pernet_operations ctnetlink_net_ops = { + .init = ctnetlink_net_init, + .exit_batch = ctnetlink_net_exit_batch, +}; + static int __init ctnetlink_init(void) { int ret; @@ -2180,28 +2228,15 @@ static int __init ctnetlink_init(void) goto err_unreg_subsys; } -#ifdef CONFIG_NF_CONNTRACK_EVENTS - ret = nf_conntrack_register_notifier(&ctnl_notifier); - if (ret < 0) { - pr_err("ctnetlink_init: cannot register notifier.\n"); + if (register_pernet_subsys(&ctnetlink_net_ops)) { + pr_err("ctnetlink_init: cannot register pernet operations\n"); goto err_unreg_exp_subsys; } - ret = nf_ct_expect_register_notifier(&ctnl_notifier_exp); - if (ret < 0) { - pr_err("ctnetlink_init: cannot expect register notifier.\n"); - goto err_unreg_notifier; - } -#endif - return 0; -#ifdef CONFIG_NF_CONNTRACK_EVENTS -err_unreg_notifier: - nf_conntrack_unregister_notifier(&ctnl_notifier); err_unreg_exp_subsys: nfnetlink_subsys_unregister(&ctnl_exp_subsys); -#endif err_unreg_subsys: nfnetlink_subsys_unregister(&ctnl_subsys); err_out: @@ -2213,11 +2248,7 @@ static void __exit ctnetlink_exit(void) pr_info("ctnetlink: unregistering from nfnetlink.\n"); nf_ct_remove_userspace_expectations(); -#ifdef CONFIG_NF_CONNTRACK_EVENTS - nf_ct_expect_unregister_notifier(&ctnl_notifier_exp); - nf_conntrack_unregister_notifier(&ctnl_notifier); -#endif - + unregister_pernet_subsys(&ctnetlink_net_ops); nfnetlink_subsys_unregister(&ctnl_exp_subsys); nfnetlink_subsys_unregister(&ctnl_subsys); } diff --git a/net/netfilter/xt_connbytes.c b/net/netfilter/xt_connbytes.c index 5b138506690..9ddf1c3bfb3 100644 --- a/net/netfilter/xt_connbytes.c +++ b/net/netfilter/xt_connbytes.c @@ -87,10 +87,10 @@ connbytes_mt(const struct sk_buff *skb, struct xt_action_param *par) break; } - if (sinfo->count.to) + if (sinfo->count.to >= sinfo->count.from) return what <= sinfo->count.to && what >= sinfo->count.from; - else - return what >= sinfo->count.from; + else /* inverted */ + return what < sinfo->count.to || what > sinfo->count.from; } static int connbytes_mt_check(const struct xt_mtchk_param *par) diff --git a/net/netlabel/netlabel_kapi.c b/net/netlabel/netlabel_kapi.c index 9c24de10a65..824f184f7a9 100644 --- a/net/netlabel/netlabel_kapi.c +++ b/net/netlabel/netlabel_kapi.c @@ -111,8 +111,6 @@ int netlbl_cfg_unlbl_map_add(const char *domain, struct netlbl_domaddr_map *addrmap = NULL; struct netlbl_domaddr4_map *map4 = NULL; struct netlbl_domaddr6_map *map6 = NULL; - const struct in_addr *addr4, *mask4; - const struct in6_addr *addr6, *mask6; entry = kzalloc(sizeof(*entry), GFP_ATOMIC); if (entry == NULL) @@ -133,9 +131,9 @@ int netlbl_cfg_unlbl_map_add(const char *domain, INIT_LIST_HEAD(&addrmap->list6); switch (family) { - case AF_INET: - addr4 = addr; - mask4 = mask; + case AF_INET: { + const struct in_addr *addr4 = addr; + const struct in_addr *mask4 = mask; map4 = kzalloc(sizeof(*map4), GFP_ATOMIC); if (map4 == NULL) goto cfg_unlbl_map_add_failure; @@ -148,9 +146,11 @@ int netlbl_cfg_unlbl_map_add(const char *domain, if (ret_val != 0) goto cfg_unlbl_map_add_failure; break; - case AF_INET6: - addr6 = addr; - mask6 = mask; + } +#if defined(CONFIG_IPV6) || defined(CONFIG_IPV6_MODULE) + case AF_INET6: { + const struct in6_addr *addr6 = addr; + const struct in6_addr *mask6 = mask; map6 = kzalloc(sizeof(*map6), GFP_ATOMIC); if (map6 == NULL) goto cfg_unlbl_map_add_failure; @@ -162,11 +162,13 @@ int netlbl_cfg_unlbl_map_add(const char *domain, map6->list.addr.s6_addr32[3] &= mask6->s6_addr32[3]; ipv6_addr_copy(&map6->list.mask, mask6); map6->list.valid = 1; - ret_val = netlbl_af4list_add(&map4->list, - &addrmap->list4); + ret_val = netlbl_af6list_add(&map6->list, + &addrmap->list6); if (ret_val != 0) goto cfg_unlbl_map_add_failure; break; + } +#endif /* IPv6 */ default: goto cfg_unlbl_map_add_failure; break; @@ -225,9 +227,11 @@ int netlbl_cfg_unlbl_static_add(struct net *net, case AF_INET: addr_len = sizeof(struct in_addr); break; +#if defined(CONFIG_IPV6) || defined(CONFIG_IPV6_MODULE) case AF_INET6: addr_len = sizeof(struct in6_addr); break; +#endif /* IPv6 */ default: return -EPFNOSUPPORT; } @@ -266,9 +270,11 @@ int netlbl_cfg_unlbl_static_del(struct net *net, case AF_INET: addr_len = sizeof(struct in_addr); break; +#if defined(CONFIG_IPV6) || defined(CONFIG_IPV6_MODULE) case AF_INET6: addr_len = sizeof(struct in6_addr); break; +#endif /* IPv6 */ default: return -EPFNOSUPPORT; } diff --git a/net/nfc/nci/core.c b/net/nfc/nci/core.c index 3925c657876..ea66034499c 100644 --- a/net/nfc/nci/core.c +++ b/net/nfc/nci/core.c @@ -69,7 +69,7 @@ static int __nci_request(struct nci_dev *ndev, __u32 timeout) { int rc = 0; - unsigned long completion_rc; + long completion_rc; ndev->req_status = NCI_REQ_PEND; diff --git a/net/packet/af_packet.c b/net/packet/af_packet.c index 82a6f34d39d..3891702b81d 100644 --- a/net/packet/af_packet.c +++ b/net/packet/af_packet.c @@ -1630,8 +1630,7 @@ static int packet_rcv(struct sk_buff *skb, struct net_device *dev, if (snaplen > res) snaplen = res; - if (atomic_read(&sk->sk_rmem_alloc) + skb->truesize >= - (unsigned)sk->sk_rcvbuf) + if (atomic_read(&sk->sk_rmem_alloc) >= sk->sk_rcvbuf) goto drop_n_acct; if (skb_shared(skb)) { @@ -1762,8 +1761,7 @@ static int tpacket_rcv(struct sk_buff *skb, struct net_device *dev, if (po->tp_version <= TPACKET_V2) { if (macoff + snaplen > po->rx_ring.frame_size) { if (po->copy_thresh && - atomic_read(&sk->sk_rmem_alloc) + skb->truesize - < (unsigned)sk->sk_rcvbuf) { + atomic_read(&sk->sk_rmem_alloc) < sk->sk_rcvbuf) { if (skb_shared(skb)) { copy_skb = skb_clone(skb, GFP_ATOMIC); } else { diff --git a/net/rds/Kconfig b/net/rds/Kconfig index 4cf6dc7910e..ec753b3ae72 100644 --- a/net/rds/Kconfig +++ b/net/rds/Kconfig @@ -9,7 +9,6 @@ config RDS config RDS_RDMA tristate "RDS over Infiniband and iWARP" - select LLIST depends on RDS && INFINIBAND && INFINIBAND_ADDR_TRANS ---help--- Allow RDS to use Infiniband and iWARP as a transport. diff --git a/net/sched/sch_gred.c b/net/sched/sch_gred.c index b9493a09a87..6cd8ddfb512 100644 --- a/net/sched/sch_gred.c +++ b/net/sched/sch_gred.c @@ -385,7 +385,7 @@ static inline int gred_change_vq(struct Qdisc *sch, int dp, struct gred_sched_data *q; if (table->tab[dp] == NULL) { - table->tab[dp] = kzalloc(sizeof(*q), GFP_KERNEL); + table->tab[dp] = kzalloc(sizeof(*q), GFP_ATOMIC); if (table->tab[dp] == NULL) return -ENOMEM; } diff --git a/net/sched/sch_mqprio.c b/net/sched/sch_mqprio.c index f88256cbacb..28de4309233 100644 --- a/net/sched/sch_mqprio.c +++ b/net/sched/sch_mqprio.c @@ -107,7 +107,7 @@ static int mqprio_init(struct Qdisc *sch, struct nlattr *opt) if (!netif_is_multiqueue(dev)) return -EOPNOTSUPP; - if (nla_len(opt) < sizeof(*qopt)) + if (!opt || nla_len(opt) < sizeof(*qopt)) return -EINVAL; qopt = nla_data(opt); diff --git a/net/sched/sch_red.c b/net/sched/sch_red.c index 6649463da1b..d617161f8dd 100644 --- a/net/sched/sch_red.c +++ b/net/sched/sch_red.c @@ -209,8 +209,8 @@ static int red_change(struct Qdisc *sch, struct nlattr *opt) ctl->Plog, ctl->Scell_log, nla_data(tb[TCA_RED_STAB])); - if (skb_queue_empty(&sch->q)) - red_end_of_idle_period(&q->parms); + if (!q->qdisc->q.qlen) + red_start_of_idle_period(&q->parms); sch_tree_unlock(sch); return 0; diff --git a/net/sched/sch_teql.c b/net/sched/sch_teql.c index a3b7120fcc7..4f4c52c0eeb 100644 --- a/net/sched/sch_teql.c +++ b/net/sched/sch_teql.c @@ -225,11 +225,11 @@ static int teql_qdisc_init(struct Qdisc *sch, struct nlattr *opt) static int -__teql_resolve(struct sk_buff *skb, struct sk_buff *skb_res, struct net_device *dev) +__teql_resolve(struct sk_buff *skb, struct sk_buff *skb_res, + struct net_device *dev, struct netdev_queue *txq, + struct neighbour *mn) { - struct netdev_queue *dev_queue = netdev_get_tx_queue(dev, 0); - struct teql_sched_data *q = qdisc_priv(dev_queue->qdisc); - struct neighbour *mn = dst_get_neighbour(skb_dst(skb)); + struct teql_sched_data *q = qdisc_priv(txq->qdisc); struct neighbour *n = q->ncache; if (mn->tbl == NULL) @@ -262,17 +262,26 @@ __teql_resolve(struct sk_buff *skb, struct sk_buff *skb_res, struct net_device * } static inline int teql_resolve(struct sk_buff *skb, - struct sk_buff *skb_res, struct net_device *dev) + struct sk_buff *skb_res, + struct net_device *dev, + struct netdev_queue *txq) { - struct netdev_queue *txq = netdev_get_tx_queue(dev, 0); + struct dst_entry *dst = skb_dst(skb); + struct neighbour *mn; + int res; + if (txq->qdisc == &noop_qdisc) return -ENODEV; - if (dev->header_ops == NULL || - skb_dst(skb) == NULL || - dst_get_neighbour(skb_dst(skb)) == NULL) + if (!dev->header_ops || !dst) return 0; - return __teql_resolve(skb, skb_res, dev); + + rcu_read_lock(); + mn = dst_get_neighbour(dst); + res = mn ? __teql_resolve(skb, skb_res, dev, txq, mn) : 0; + rcu_read_unlock(); + + return res; } static netdev_tx_t teql_master_xmit(struct sk_buff *skb, struct net_device *dev) @@ -307,7 +316,7 @@ restart: continue; } - switch (teql_resolve(skb, skb_res, slave)) { + switch (teql_resolve(skb, skb_res, slave, slave_txq)) { case 0: if (__netif_tx_trylock(slave_txq)) { unsigned int length = qdisc_pkt_len(skb); diff --git a/net/sctp/associola.c b/net/sctp/associola.c index 152b5b3c3ff..acd2edbc073 100644 --- a/net/sctp/associola.c +++ b/net/sctp/associola.c @@ -173,7 +173,7 @@ static struct sctp_association *sctp_association_init(struct sctp_association *a asoc->timeouts[SCTP_EVENT_TIMEOUT_HEARTBEAT] = 0; asoc->timeouts[SCTP_EVENT_TIMEOUT_SACK] = asoc->sackdelay; asoc->timeouts[SCTP_EVENT_TIMEOUT_AUTOCLOSE] = - (unsigned long)sp->autoclose * HZ; + min_t(unsigned long, sp->autoclose, sctp_max_autoclose) * HZ; /* Initializes the timers */ for (i = SCTP_EVENT_TIMEOUT_NONE; i < SCTP_NUM_TIMEOUT_TYPES; ++i) diff --git a/net/sctp/auth.c b/net/sctp/auth.c index 865e68fef21..bf812048cf6 100644 --- a/net/sctp/auth.c +++ b/net/sctp/auth.c @@ -82,7 +82,7 @@ static struct sctp_auth_bytes *sctp_auth_create_key(__u32 key_len, gfp_t gfp) struct sctp_auth_bytes *key; /* Verify that we are not going to overflow INT_MAX */ - if ((INT_MAX - key_len) < sizeof(struct sctp_auth_bytes)) + if (key_len > (INT_MAX - sizeof(struct sctp_auth_bytes))) return NULL; /* Allocate the shared key */ diff --git a/net/sctp/output.c b/net/sctp/output.c index 08b3cead650..817174eb5f4 100644 --- a/net/sctp/output.c +++ b/net/sctp/output.c @@ -697,13 +697,7 @@ static void sctp_packet_append_data(struct sctp_packet *packet, /* Keep track of how many bytes are in flight to the receiver. */ asoc->outqueue.outstanding_bytes += datasize; - /* Update our view of the receiver's rwnd. Include sk_buff overhead - * while updating peer.rwnd so that it reduces the chances of a - * receiver running out of receive buffer space even when receive - * window is still open. This can happen when a sender is sending - * sending small messages. - */ - datasize += sizeof(struct sk_buff); + /* Update our view of the receiver's rwnd. */ if (datasize < rwnd) rwnd -= datasize; else diff --git a/net/sctp/outqueue.c b/net/sctp/outqueue.c index 14c2b06028f..cfeb1d4a1ee 100644 --- a/net/sctp/outqueue.c +++ b/net/sctp/outqueue.c @@ -411,8 +411,7 @@ void sctp_retransmit_mark(struct sctp_outq *q, chunk->transport->flight_size -= sctp_data_size(chunk); q->outstanding_bytes -= sctp_data_size(chunk); - q->asoc->peer.rwnd += (sctp_data_size(chunk) + - sizeof(struct sk_buff)); + q->asoc->peer.rwnd += sctp_data_size(chunk); } continue; } @@ -432,8 +431,7 @@ void sctp_retransmit_mark(struct sctp_outq *q, * (Section 7.2.4)), add the data size of those * chunks to the rwnd. */ - q->asoc->peer.rwnd += (sctp_data_size(chunk) + - sizeof(struct sk_buff)); + q->asoc->peer.rwnd += sctp_data_size(chunk); q->outstanding_bytes -= sctp_data_size(chunk); if (chunk->transport) transport->flight_size -= sctp_data_size(chunk); diff --git a/net/sctp/protocol.c b/net/sctp/protocol.c index 61b9fca5a17..6f6ad868683 100644 --- a/net/sctp/protocol.c +++ b/net/sctp/protocol.c @@ -1285,6 +1285,9 @@ SCTP_STATIC __init int sctp_init(void) sctp_max_instreams = SCTP_DEFAULT_INSTREAMS; sctp_max_outstreams = SCTP_DEFAULT_OUTSTREAMS; + /* Initialize maximum autoclose timeout. */ + sctp_max_autoclose = INT_MAX / HZ; + /* Initialize handle used for association ids. */ idr_init(&sctp_assocs_id); diff --git a/net/sctp/socket.c b/net/sctp/socket.c index 13bf5fcdbff..54a7cd2fdd7 100644 --- a/net/sctp/socket.c +++ b/net/sctp/socket.c @@ -2200,8 +2200,6 @@ static int sctp_setsockopt_autoclose(struct sock *sk, char __user *optval, return -EINVAL; if (copy_from_user(&sp->autoclose, optval, optlen)) return -EFAULT; - /* make sure it won't exceed MAX_SCHEDULE_TIMEOUT */ - sp->autoclose = min_t(long, sp->autoclose, MAX_SCHEDULE_TIMEOUT / HZ); return 0; } diff --git a/net/sctp/sysctl.c b/net/sctp/sysctl.c index 6b3952961b8..60ffbd067ff 100644 --- a/net/sctp/sysctl.c +++ b/net/sctp/sysctl.c @@ -53,6 +53,10 @@ static int sack_timer_min = 1; static int sack_timer_max = 500; static int addr_scope_max = 3; /* check sctp_scope_policy_t in include/net/sctp/constants.h for max entries */ static int rwnd_scale_max = 16; +static unsigned long max_autoclose_min = 0; +static unsigned long max_autoclose_max = + (MAX_SCHEDULE_TIMEOUT / HZ > UINT_MAX) + ? UINT_MAX : MAX_SCHEDULE_TIMEOUT / HZ; extern long sysctl_sctp_mem[3]; extern int sysctl_sctp_rmem[3]; @@ -258,6 +262,15 @@ static ctl_table sctp_table[] = { .extra1 = &one, .extra2 = &rwnd_scale_max, }, + { + .procname = "max_autoclose", + .data = &sctp_max_autoclose, + .maxlen = sizeof(unsigned long), + .mode = 0644, + .proc_handler = &proc_doulongvec_minmax, + .extra1 = &max_autoclose_min, + .extra2 = &max_autoclose_max, + }, { /* sentinel */ } }; diff --git a/net/sunrpc/sched.c b/net/sunrpc/sched.c index d12ffa54581..00a1a2acd58 100644 --- a/net/sunrpc/sched.c +++ b/net/sunrpc/sched.c @@ -590,6 +590,27 @@ void rpc_prepare_task(struct rpc_task *task) task->tk_ops->rpc_call_prepare(task, task->tk_calldata); } +static void +rpc_init_task_statistics(struct rpc_task *task) +{ + /* Initialize retry counters */ + task->tk_garb_retry = 2; + task->tk_cred_retry = 2; + task->tk_rebind_retry = 2; + + /* starting timestamp */ + task->tk_start = ktime_get(); +} + +static void +rpc_reset_task_statistics(struct rpc_task *task) +{ + task->tk_timeouts = 0; + task->tk_flags &= ~(RPC_CALL_MAJORSEEN|RPC_TASK_KILLED|RPC_TASK_SENT); + + rpc_init_task_statistics(task); +} + /* * Helper that calls task->tk_ops->rpc_call_done if it exists */ @@ -602,6 +623,7 @@ void rpc_exit_task(struct rpc_task *task) WARN_ON(RPC_ASSASSINATED(task)); /* Always release the RPC slot and buffer memory */ xprt_release(task); + rpc_reset_task_statistics(task); } } } @@ -804,11 +826,6 @@ static void rpc_init_task(struct rpc_task *task, const struct rpc_task_setup *ta task->tk_calldata = task_setup_data->callback_data; INIT_LIST_HEAD(&task->tk_task); - /* Initialize retry counters */ - task->tk_garb_retry = 2; - task->tk_cred_retry = 2; - task->tk_rebind_retry = 2; - task->tk_priority = task_setup_data->priority - RPC_PRIORITY_LOW; task->tk_owner = current->tgid; @@ -818,8 +835,7 @@ static void rpc_init_task(struct rpc_task *task, const struct rpc_task_setup *ta if (task->tk_ops->rpc_call_prepare != NULL) task->tk_action = rpc_prepare_task; - /* starting timestamp */ - task->tk_start = ktime_get(); + rpc_init_task_statistics(task); dprintk("RPC: new task initialized, procpid %u\n", task_pid_nr(current)); diff --git a/net/sunrpc/xprt.c b/net/sunrpc/xprt.c index f4385e45a5f..c64c0ef519b 100644 --- a/net/sunrpc/xprt.c +++ b/net/sunrpc/xprt.c @@ -995,13 +995,11 @@ out_init_req: static void xprt_free_slot(struct rpc_xprt *xprt, struct rpc_rqst *req) { - if (xprt_dynamic_free_slot(xprt, req)) - return; - - memset(req, 0, sizeof(*req)); /* mark unused */ - spin_lock(&xprt->reserve_lock); - list_add(&req->rq_list, &xprt->free); + if (!xprt_dynamic_free_slot(xprt, req)) { + memset(req, 0, sizeof(*req)); /* mark unused */ + list_add(&req->rq_list, &xprt->free); + } rpc_wake_up_next(&xprt->backlog); spin_unlock(&xprt->reserve_lock); } diff --git a/net/sunrpc/xprtsock.c b/net/sunrpc/xprtsock.c index d7f97ef2659..55472c48825 100644 --- a/net/sunrpc/xprtsock.c +++ b/net/sunrpc/xprtsock.c @@ -496,7 +496,7 @@ static int xs_nospace(struct rpc_task *task) struct rpc_rqst *req = task->tk_rqstp; struct rpc_xprt *xprt = req->rq_xprt; struct sock_xprt *transport = container_of(xprt, struct sock_xprt, xprt); - int ret = 0; + int ret = -EAGAIN; dprintk("RPC: %5u xmit incomplete (%u left of %u)\n", task->tk_pid, req->rq_slen - req->rq_bytes_sent, @@ -508,7 +508,6 @@ static int xs_nospace(struct rpc_task *task) /* Don't race with disconnect */ if (xprt_connected(xprt)) { if (test_bit(SOCK_ASYNC_NOSPACE, &transport->sock->flags)) { - ret = -EAGAIN; /* * Notify TCP that we're limited by the application * window size @@ -2530,8 +2529,10 @@ static struct rpc_xprt *xs_setup_xprt(struct xprt_create *args, int err; err = xs_init_anyaddr(args->dstaddr->sa_family, (struct sockaddr *)&new->srcaddr); - if (err != 0) + if (err != 0) { + xprt_free(xprt); return ERR_PTR(err); + } } return xprt; diff --git a/net/unix/af_unix.c b/net/unix/af_unix.c index 466fbcc5cf7..b595a3d8679 100644 --- a/net/unix/af_unix.c +++ b/net/unix/af_unix.c @@ -1957,6 +1957,7 @@ static int unix_stream_recvmsg(struct kiocb *iocb, struct socket *sock, if ((UNIXCB(skb).pid != siocb->scm->pid) || (UNIXCB(skb).cred != siocb->scm->cred)) { skb_queue_head(&sk->sk_receive_queue, skb); + sk->sk_data_ready(sk, skb->len); break; } } else { @@ -1974,6 +1975,7 @@ static int unix_stream_recvmsg(struct kiocb *iocb, struct socket *sock, chunk = min_t(unsigned int, skb->len, size); if (memcpy_toiovec(msg->msg_iov, skb->data, chunk)) { skb_queue_head(&sk->sk_receive_queue, skb); + sk->sk_data_ready(sk, skb->len); if (copied == 0) copied = -EFAULT; break; @@ -1991,6 +1993,7 @@ static int unix_stream_recvmsg(struct kiocb *iocb, struct socket *sock, /* put the skb back if we didn't use it up.. */ if (skb->len) { skb_queue_head(&sk->sk_receive_queue, skb); + sk->sk_data_ready(sk, skb->len); break; } @@ -2006,6 +2009,7 @@ static int unix_stream_recvmsg(struct kiocb *iocb, struct socket *sock, /* put message back and return */ skb_queue_head(&sk->sk_receive_queue, skb); + sk->sk_data_ready(sk, skb->len); break; } } while (size); diff --git a/net/wireless/nl80211.c b/net/wireless/nl80211.c index 48260c2d092..ffafda5022c 100644 --- a/net/wireless/nl80211.c +++ b/net/wireless/nl80211.c @@ -89,8 +89,8 @@ static const struct nla_policy nl80211_policy[NL80211_ATTR_MAX+1] = { [NL80211_ATTR_IFINDEX] = { .type = NLA_U32 }, [NL80211_ATTR_IFNAME] = { .type = NLA_NUL_STRING, .len = IFNAMSIZ-1 }, - [NL80211_ATTR_MAC] = { .type = NLA_BINARY, .len = ETH_ALEN }, - [NL80211_ATTR_PREV_BSSID] = { .type = NLA_BINARY, .len = ETH_ALEN }, + [NL80211_ATTR_MAC] = { .len = ETH_ALEN }, + [NL80211_ATTR_PREV_BSSID] = { .len = ETH_ALEN }, [NL80211_ATTR_KEY] = { .type = NLA_NESTED, }, [NL80211_ATTR_KEY_DATA] = { .type = NLA_BINARY, @@ -132,8 +132,7 @@ static const struct nla_policy nl80211_policy[NL80211_ATTR_MAX+1] = { [NL80211_ATTR_MESH_CONFIG] = { .type = NLA_NESTED }, [NL80211_ATTR_SUPPORT_MESH_AUTH] = { .type = NLA_FLAG }, - [NL80211_ATTR_HT_CAPABILITY] = { .type = NLA_BINARY, - .len = NL80211_HT_CAPABILITY_LEN }, + [NL80211_ATTR_HT_CAPABILITY] = { .len = NL80211_HT_CAPABILITY_LEN }, [NL80211_ATTR_MGMT_SUBTYPE] = { .type = NLA_U8 }, [NL80211_ATTR_IE] = { .type = NLA_BINARY, @@ -1253,6 +1252,12 @@ static int nl80211_set_wiphy(struct sk_buff *skb, struct genl_info *info) goto bad_res; } + if (netdev->ieee80211_ptr->iftype != NL80211_IFTYPE_AP && + netdev->ieee80211_ptr->iftype != NL80211_IFTYPE_P2P_GO) { + result = -EINVAL; + goto bad_res; + } + nla_for_each_nested(nl_txq_params, info->attrs[NL80211_ATTR_WIPHY_TXQ_PARAMS], rem_txq_params) { diff --git a/net/wireless/reg.c b/net/wireless/reg.c index 6acba9d18cc..3302c56f60d 100644 --- a/net/wireless/reg.c +++ b/net/wireless/reg.c @@ -57,8 +57,17 @@ #define REG_DBG_PRINT(args...) #endif +static struct regulatory_request core_request_world = { + .initiator = NL80211_REGDOM_SET_BY_CORE, + .alpha2[0] = '0', + .alpha2[1] = '0', + .intersect = false, + .processed = true, + .country_ie_env = ENVIRON_ANY, +}; + /* Receipt of information from last regulatory request */ -static struct regulatory_request *last_request; +static struct regulatory_request *last_request = &core_request_world; /* To trigger userspace events */ static struct platform_device *reg_pdev; @@ -150,7 +159,7 @@ static char user_alpha2[2]; module_param(ieee80211_regdom, charp, 0444); MODULE_PARM_DESC(ieee80211_regdom, "IEEE 802.11 regulatory domain code"); -static void reset_regdomains(void) +static void reset_regdomains(bool full_reset) { /* avoid freeing static information or freeing something twice */ if (cfg80211_regdomain == cfg80211_world_regdom) @@ -165,6 +174,13 @@ static void reset_regdomains(void) cfg80211_world_regdom = &world_regdom; cfg80211_regdomain = NULL; + + if (!full_reset) + return; + + if (last_request != &core_request_world) + kfree(last_request); + last_request = &core_request_world; } /* @@ -175,7 +191,7 @@ static void update_world_regdomain(const struct ieee80211_regdomain *rd) { BUG_ON(!last_request); - reset_regdomains(); + reset_regdomains(false); cfg80211_world_regdom = rd; cfg80211_regdomain = rd; @@ -1407,7 +1423,8 @@ static int __regulatory_hint(struct wiphy *wiphy, } new_request: - kfree(last_request); + if (last_request != &core_request_world) + kfree(last_request); last_request = pending_request; last_request->intersect = intersect; @@ -1577,9 +1594,6 @@ static int regulatory_hint_core(const char *alpha2) { struct regulatory_request *request; - kfree(last_request); - last_request = NULL; - request = kzalloc(sizeof(struct regulatory_request), GFP_KERNEL); if (!request) @@ -1777,7 +1791,7 @@ static void restore_regulatory_settings(bool reset_user) mutex_lock(&cfg80211_mutex); mutex_lock(®_mutex); - reset_regdomains(); + reset_regdomains(true); restore_alpha2(alpha2, reset_user); /* @@ -2037,12 +2051,18 @@ static int __set_regdom(const struct ieee80211_regdomain *rd) } request_wiphy = wiphy_idx_to_wiphy(last_request->wiphy_idx); + if (!request_wiphy && + (last_request->initiator == NL80211_REGDOM_SET_BY_DRIVER || + last_request->initiator == NL80211_REGDOM_SET_BY_COUNTRY_IE)) { + schedule_delayed_work(®_timeout, 0); + return -ENODEV; + } if (!last_request->intersect) { int r; if (last_request->initiator != NL80211_REGDOM_SET_BY_DRIVER) { - reset_regdomains(); + reset_regdomains(false); cfg80211_regdomain = rd; return 0; } @@ -2063,7 +2083,7 @@ static int __set_regdom(const struct ieee80211_regdomain *rd) if (r) return r; - reset_regdomains(); + reset_regdomains(false); cfg80211_regdomain = rd; return 0; } @@ -2088,7 +2108,7 @@ static int __set_regdom(const struct ieee80211_regdomain *rd) rd = NULL; - reset_regdomains(); + reset_regdomains(false); cfg80211_regdomain = intersected_rd; return 0; @@ -2108,7 +2128,7 @@ static int __set_regdom(const struct ieee80211_regdomain *rd) kfree(rd); rd = NULL; - reset_regdomains(); + reset_regdomains(false); cfg80211_regdomain = intersected_rd; return 0; @@ -2261,9 +2281,9 @@ void /* __init_or_exit */ regulatory_exit(void) mutex_lock(&cfg80211_mutex); mutex_lock(®_mutex); - reset_regdomains(); + reset_regdomains(true); - kfree(last_request); + dev_set_uevent_suppress(®_pdev->dev, true); platform_device_unregister(reg_pdev); diff --git a/net/wireless/scan.c b/net/wireless/scan.c index 0fb14241040..dc23b31594e 100644 --- a/net/wireless/scan.c +++ b/net/wireless/scan.c @@ -259,17 +259,20 @@ static int cmp_ies(u8 num, u8 *ies1, size_t len1, u8 *ies2, size_t len2) { const u8 *ie1 = cfg80211_find_ie(num, ies1, len1); const u8 *ie2 = cfg80211_find_ie(num, ies2, len2); - int r; + /* equal if both missing */ if (!ie1 && !ie2) return 0; - if (!ie1 || !ie2) + /* sort missing IE before (left of) present IE */ + if (!ie1) return -1; + if (!ie2) + return 1; - r = memcmp(ie1 + 2, ie2 + 2, min(ie1[1], ie2[1])); - if (r == 0 && ie1[1] != ie2[1]) + /* sort by length first, then by contents */ + if (ie1[1] != ie2[1]) return ie2[1] - ie1[1]; - return r; + return memcmp(ie1 + 2, ie2 + 2, ie1[1]); } static bool is_bss(struct cfg80211_bss *a, diff --git a/net/xfrm/xfrm_policy.c b/net/xfrm/xfrm_policy.c index 552df27dcf5..9049a5caeb2 100644 --- a/net/xfrm/xfrm_policy.c +++ b/net/xfrm/xfrm_policy.c @@ -2276,8 +2276,6 @@ static void __xfrm_garbage_collect(struct net *net) { struct dst_entry *head, *next; - flow_cache_flush(); - spin_lock_bh(&xfrm_policy_sk_bundle_lock); head = xfrm_policy_sk_bundles; xfrm_policy_sk_bundles = NULL; @@ -2290,6 +2288,18 @@ static void __xfrm_garbage_collect(struct net *net) } } +static void xfrm_garbage_collect(struct net *net) +{ + flow_cache_flush(); + __xfrm_garbage_collect(net); +} + +static void xfrm_garbage_collect_deferred(struct net *net) +{ + flow_cache_flush_deferred(); + __xfrm_garbage_collect(net); +} + static void xfrm_init_pmtu(struct dst_entry *dst) { do { @@ -2382,9 +2392,11 @@ static unsigned int xfrm_default_advmss(const struct dst_entry *dst) return dst_metric_advmss(dst->path); } -static unsigned int xfrm_default_mtu(const struct dst_entry *dst) +static unsigned int xfrm_mtu(const struct dst_entry *dst) { - return dst_mtu(dst->path); + unsigned int mtu = dst_metric_raw(dst, RTAX_MTU); + + return mtu ? : dst_mtu(dst->path); } static struct neighbour *xfrm_neigh_lookup(const struct dst_entry *dst, const void *daddr) @@ -2411,8 +2423,8 @@ int xfrm_policy_register_afinfo(struct xfrm_policy_afinfo *afinfo) dst_ops->check = xfrm_dst_check; if (likely(dst_ops->default_advmss == NULL)) dst_ops->default_advmss = xfrm_default_advmss; - if (likely(dst_ops->default_mtu == NULL)) - dst_ops->default_mtu = xfrm_default_mtu; + if (likely(dst_ops->mtu == NULL)) + dst_ops->mtu = xfrm_mtu; if (likely(dst_ops->negative_advice == NULL)) dst_ops->negative_advice = xfrm_negative_advice; if (likely(dst_ops->link_failure == NULL)) @@ -2420,7 +2432,7 @@ int xfrm_policy_register_afinfo(struct xfrm_policy_afinfo *afinfo) if (likely(dst_ops->neigh_lookup == NULL)) dst_ops->neigh_lookup = xfrm_neigh_lookup; if (likely(afinfo->garbage_collect == NULL)) - afinfo->garbage_collect = __xfrm_garbage_collect; + afinfo->garbage_collect = xfrm_garbage_collect_deferred; xfrm_policy_afinfo[afinfo->family] = afinfo; } write_unlock_bh(&xfrm_policy_afinfo_lock); @@ -2514,7 +2526,7 @@ static int xfrm_dev_event(struct notifier_block *this, unsigned long event, void switch (event) { case NETDEV_DOWN: - __xfrm_garbage_collect(dev_net(dev)); + xfrm_garbage_collect(dev_net(dev)); } return NOTIFY_DONE; } |