diff options
Diffstat (limited to 'net')
41 files changed, 360 insertions, 287 deletions
diff --git a/net/ax25/af_ax25.c b/net/ax25/af_ax25.c index 0906c194a413..9d9a6a3edbd5 100644 --- a/net/ax25/af_ax25.c +++ b/net/ax25/af_ax25.c @@ -2011,16 +2011,17 @@ static void __exit ax25_exit(void) proc_net_remove(&init_net, "ax25_route"); proc_net_remove(&init_net, "ax25"); proc_net_remove(&init_net, "ax25_calls"); - ax25_rt_free(); - ax25_uid_free(); - ax25_dev_free(); - ax25_unregister_sysctl(); unregister_netdevice_notifier(&ax25_dev_notifier); + ax25_unregister_sysctl(); dev_remove_pack(&ax25_packet_type); sock_unregister(PF_AX25); proto_unregister(&ax25_proto); + + ax25_rt_free(); + ax25_uid_free(); + ax25_dev_free(); } module_exit(ax25_exit); diff --git a/net/bridge/br_forward.c b/net/bridge/br_forward.c index 61f65344e711..a2098e3de500 100644 --- a/net/bridge/br_forward.c +++ b/net/bridge/br_forward.c @@ -47,6 +47,7 @@ int br_dev_queue_push_xmit(struct sk_buff *skb) kfree_skb(skb); } else { skb_push(skb, ETH_HLEN); + br_drop_fake_rtable(skb); dev_queue_xmit(skb); } diff --git a/net/bridge/br_multicast.c b/net/bridge/br_multicast.c index 702a1ae9220b..27ca25ed7021 100644 --- a/net/bridge/br_multicast.c +++ b/net/bridge/br_multicast.c @@ -241,7 +241,6 @@ static void br_multicast_group_expired(unsigned long data) hlist_del_rcu(&mp->hlist[mdb->ver]); mdb->size--; - del_timer(&mp->query_timer); call_rcu_bh(&mp->rcu, br_multicast_free_group); out: @@ -271,7 +270,6 @@ static void br_multicast_del_pg(struct net_bridge *br, rcu_assign_pointer(*pp, p->next); hlist_del_init(&p->mglist); del_timer(&p->timer); - del_timer(&p->query_timer); call_rcu_bh(&p->rcu, br_multicast_free_pg); if (!mp->ports && !mp->mglist && @@ -507,74 +505,6 @@ static struct sk_buff *br_multicast_alloc_query(struct net_bridge *br, return NULL; } -static void br_multicast_send_group_query(struct net_bridge_mdb_entry *mp) -{ - struct net_bridge *br = mp->br; - struct sk_buff *skb; - - skb = br_multicast_alloc_query(br, &mp->addr); - if (!skb) - goto timer; - - netif_rx(skb); - -timer: - if (++mp->queries_sent < br->multicast_last_member_count) - mod_timer(&mp->query_timer, - jiffies + br->multicast_last_member_interval); -} - -static void br_multicast_group_query_expired(unsigned long data) -{ - struct net_bridge_mdb_entry *mp = (void *)data; - struct net_bridge *br = mp->br; - - spin_lock(&br->multicast_lock); - if (!netif_running(br->dev) || !mp->mglist || - mp->queries_sent >= br->multicast_last_member_count) - goto out; - - br_multicast_send_group_query(mp); - -out: - spin_unlock(&br->multicast_lock); -} - -static void br_multicast_send_port_group_query(struct net_bridge_port_group *pg) -{ - struct net_bridge_port *port = pg->port; - struct net_bridge *br = port->br; - struct sk_buff *skb; - - skb = br_multicast_alloc_query(br, &pg->addr); - if (!skb) - goto timer; - - br_deliver(port, skb); - -timer: - if (++pg->queries_sent < br->multicast_last_member_count) - mod_timer(&pg->query_timer, - jiffies + br->multicast_last_member_interval); -} - -static void br_multicast_port_group_query_expired(unsigned long data) -{ - struct net_bridge_port_group *pg = (void *)data; - struct net_bridge_port *port = pg->port; - struct net_bridge *br = port->br; - - spin_lock(&br->multicast_lock); - if (!netif_running(br->dev) || hlist_unhashed(&pg->mglist) || - pg->queries_sent >= br->multicast_last_member_count) - goto out; - - br_multicast_send_port_group_query(pg); - -out: - spin_unlock(&br->multicast_lock); -} - static struct net_bridge_mdb_entry *br_multicast_get_group( struct net_bridge *br, struct net_bridge_port *port, struct br_ip *group, int hash) @@ -690,8 +620,6 @@ rehash: mp->addr = *group; setup_timer(&mp->timer, br_multicast_group_expired, (unsigned long)mp); - setup_timer(&mp->query_timer, br_multicast_group_query_expired, - (unsigned long)mp); hlist_add_head_rcu(&mp->hlist[mdb->ver], &mdb->mhash[hash]); mdb->size++; @@ -746,8 +674,6 @@ static int br_multicast_add_group(struct net_bridge *br, hlist_add_head(&p->mglist, &port->mglist); setup_timer(&p->timer, br_multicast_port_group_expired, (unsigned long)p); - setup_timer(&p->query_timer, br_multicast_port_group_query_expired, - (unsigned long)p); rcu_assign_pointer(*pp, p); @@ -1291,9 +1217,6 @@ static void br_multicast_leave_group(struct net_bridge *br, time_after(mp->timer.expires, time) : try_to_del_timer_sync(&mp->timer) >= 0)) { mod_timer(&mp->timer, time); - - mp->queries_sent = 0; - mod_timer(&mp->query_timer, now); } goto out; @@ -1310,9 +1233,6 @@ static void br_multicast_leave_group(struct net_bridge *br, time_after(p->timer.expires, time) : try_to_del_timer_sync(&p->timer) >= 0)) { mod_timer(&p->timer, time); - - p->queries_sent = 0; - mod_timer(&p->query_timer, now); } break; @@ -1681,7 +1601,6 @@ void br_multicast_stop(struct net_bridge *br) hlist_for_each_entry_safe(mp, p, n, &mdb->mhash[i], hlist[ver]) { del_timer(&mp->timer); - del_timer(&mp->query_timer); call_rcu_bh(&mp->rcu, br_multicast_free_group); } } diff --git a/net/bridge/br_netfilter.c b/net/bridge/br_netfilter.c index dec4f3817133..d7f49b63ab0f 100644 --- a/net/bridge/br_netfilter.c +++ b/net/bridge/br_netfilter.c @@ -156,7 +156,7 @@ 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 | DST_NOPEER; + rt->dst.flags = DST_NOXFRM | DST_NOPEER | DST_FAKE_RTABLE; rt->dst.ops = &fake_dst_ops; } @@ -694,11 +694,7 @@ static unsigned int br_nf_local_in(unsigned int hook, struct sk_buff *skb, const struct net_device *out, int (*okfn)(struct sk_buff *)) { - struct rtable *rt = skb_rtable(skb); - - if (rt && rt == bridge_parent_rtable(in)) - skb_dst_drop(skb); - + br_drop_fake_rtable(skb); return NF_ACCEPT; } diff --git a/net/bridge/br_private.h b/net/bridge/br_private.h index 0b67a63ad7a8..e1d882257877 100644 --- a/net/bridge/br_private.h +++ b/net/bridge/br_private.h @@ -82,9 +82,7 @@ struct net_bridge_port_group { struct hlist_node mglist; struct rcu_head rcu; struct timer_list timer; - struct timer_list query_timer; struct br_ip addr; - u32 queries_sent; }; struct net_bridge_mdb_entry @@ -94,10 +92,8 @@ struct net_bridge_mdb_entry struct net_bridge_port_group __rcu *ports; struct rcu_head rcu; struct timer_list timer; - struct timer_list query_timer; struct br_ip addr; bool mglist; - u32 queries_sent; }; struct net_bridge_mdb_htable diff --git a/net/caif/chnl_net.c b/net/caif/chnl_net.c index 20618dd3088b..d09340e1523f 100644 --- a/net/caif/chnl_net.c +++ b/net/caif/chnl_net.c @@ -103,6 +103,7 @@ static int chnl_recv_cb(struct cflayer *layr, struct cfpkt *pkt) skb->protocol = htons(ETH_P_IPV6); break; default: + kfree_skb(skb); priv->netdev->stats.rx_errors++; return -EINVAL; } @@ -220,14 +221,16 @@ static int chnl_net_start_xmit(struct sk_buff *skb, struct net_device *dev) if (skb->len > priv->netdev->mtu) { pr_warn("Size of skb exceeded MTU\n"); + kfree_skb(skb); dev->stats.tx_errors++; - return -ENOSPC; + return NETDEV_TX_OK; } if (!priv->flowenabled) { pr_debug("dropping packets flow off\n"); + kfree_skb(skb); dev->stats.tx_dropped++; - return NETDEV_TX_BUSY; + return NETDEV_TX_OK; } if (priv->conn_req.protocol == CAIFPROTO_DATAGRAM_LOOP) @@ -242,7 +245,7 @@ static int chnl_net_start_xmit(struct sk_buff *skb, struct net_device *dev) result = priv->chnl.dn->transmit(priv->chnl.dn, pkt); if (result) { dev->stats.tx_dropped++; - return result; + return NETDEV_TX_OK; } /* Update statistics. */ diff --git a/net/core/dev.c b/net/core/dev.c index c25d453b2803..9bb8f87c4cda 100644 --- a/net/core/dev.c +++ b/net/core/dev.c @@ -1409,14 +1409,34 @@ EXPORT_SYMBOL(register_netdevice_notifier); * register_netdevice_notifier(). The notifier is unlinked into the * kernel structures and may then be reused. A negative errno code * is returned on a failure. + * + * After unregistering unregister and down device events are synthesized + * for all devices on the device list to the removed notifier to remove + * the need for special case cleanup code. */ int unregister_netdevice_notifier(struct notifier_block *nb) { + struct net_device *dev; + struct net *net; int err; rtnl_lock(); err = raw_notifier_chain_unregister(&netdev_chain, nb); + if (err) + goto unlock; + + for_each_net(net) { + for_each_netdev(net, dev) { + if (dev->flags & IFF_UP) { + nb->notifier_call(nb, NETDEV_GOING_DOWN, dev); + nb->notifier_call(nb, NETDEV_DOWN, dev); + } + nb->notifier_call(nb, NETDEV_UNREGISTER, dev); + nb->notifier_call(nb, NETDEV_UNREGISTER_BATCH, dev); + } + } +unlock: rtnl_unlock(); return err; } diff --git a/net/core/drop_monitor.c b/net/core/drop_monitor.c index 7f36b38e060f..7592943513e3 100644 --- a/net/core/drop_monitor.c +++ b/net/core/drop_monitor.c @@ -42,11 +42,11 @@ static void send_dm_alert(struct work_struct *unused); * netlink alerts */ static int trace_state = TRACE_OFF; -static DEFINE_SPINLOCK(trace_state_lock); +static DEFINE_MUTEX(trace_state_mutex); struct per_cpu_dm_data { struct work_struct dm_alert_work; - struct sk_buff *skb; + struct sk_buff __rcu *skb; atomic_t dm_hit_count; struct timer_list send_timer; }; @@ -73,35 +73,58 @@ static int dm_hit_limit = 64; static int dm_delay = 1; static unsigned long dm_hw_check_delta = 2*HZ; static LIST_HEAD(hw_stats_list); +static int initialized = 0; static void reset_per_cpu_data(struct per_cpu_dm_data *data) { size_t al; struct net_dm_alert_msg *msg; struct nlattr *nla; + struct sk_buff *skb; + struct sk_buff *oskb = rcu_dereference_protected(data->skb, 1); al = sizeof(struct net_dm_alert_msg); al += dm_hit_limit * sizeof(struct net_dm_drop_point); al += sizeof(struct nlattr); - data->skb = genlmsg_new(al, GFP_KERNEL); - genlmsg_put(data->skb, 0, 0, &net_drop_monitor_family, - 0, NET_DM_CMD_ALERT); - nla = nla_reserve(data->skb, NLA_UNSPEC, sizeof(struct net_dm_alert_msg)); - msg = nla_data(nla); - memset(msg, 0, al); - atomic_set(&data->dm_hit_count, dm_hit_limit); + skb = genlmsg_new(al, GFP_KERNEL); + + if (skb) { + genlmsg_put(skb, 0, 0, &net_drop_monitor_family, + 0, NET_DM_CMD_ALERT); + nla = nla_reserve(skb, NLA_UNSPEC, + sizeof(struct net_dm_alert_msg)); + msg = nla_data(nla); + memset(msg, 0, al); + } else if (initialized) + schedule_work_on(smp_processor_id(), &data->dm_alert_work); + + /* + * Don't need to lock this, since we are guaranteed to only + * run this on a single cpu at a time. + * Note also that we only update data->skb if the old and new skb + * pointers don't match. This ensures that we don't continually call + * synchornize_rcu if we repeatedly fail to alloc a new netlink message. + */ + if (skb != oskb) { + rcu_assign_pointer(data->skb, skb); + + synchronize_rcu(); + + atomic_set(&data->dm_hit_count, dm_hit_limit); + } + } static void send_dm_alert(struct work_struct *unused) { struct sk_buff *skb; - struct per_cpu_dm_data *data = &__get_cpu_var(dm_cpu_data); + struct per_cpu_dm_data *data = &get_cpu_var(dm_cpu_data); /* * Grab the skb we're about to send */ - skb = data->skb; + skb = rcu_dereference_protected(data->skb, 1); /* * Replace it with a new one @@ -111,8 +134,10 @@ static void send_dm_alert(struct work_struct *unused) /* * Ship it! */ - genlmsg_multicast(skb, 0, NET_DM_GRP_ALERT, GFP_KERNEL); + if (skb) + genlmsg_multicast(skb, 0, NET_DM_GRP_ALERT, GFP_KERNEL); + put_cpu_var(dm_cpu_data); } /* @@ -123,9 +148,11 @@ static void send_dm_alert(struct work_struct *unused) */ static void sched_send_work(unsigned long unused) { - struct per_cpu_dm_data *data = &__get_cpu_var(dm_cpu_data); + struct per_cpu_dm_data *data = &get_cpu_var(dm_cpu_data); + + schedule_work_on(smp_processor_id(), &data->dm_alert_work); - schedule_work(&data->dm_alert_work); + put_cpu_var(dm_cpu_data); } static void trace_drop_common(struct sk_buff *skb, void *location) @@ -134,9 +161,16 @@ static void trace_drop_common(struct sk_buff *skb, void *location) struct nlmsghdr *nlh; struct nlattr *nla; int i; - struct per_cpu_dm_data *data = &__get_cpu_var(dm_cpu_data); + struct sk_buff *dskb; + struct per_cpu_dm_data *data = &get_cpu_var(dm_cpu_data); + rcu_read_lock(); + dskb = rcu_dereference(data->skb); + + if (!dskb) + goto out; + if (!atomic_add_unless(&data->dm_hit_count, -1, 0)) { /* * we're already at zero, discard this hit @@ -144,12 +178,13 @@ static void trace_drop_common(struct sk_buff *skb, void *location) goto out; } - nlh = (struct nlmsghdr *)data->skb->data; + nlh = (struct nlmsghdr *)dskb->data; nla = genlmsg_data(nlmsg_data(nlh)); msg = nla_data(nla); for (i = 0; i < msg->entries; i++) { if (!memcmp(&location, msg->points[i].pc, sizeof(void *))) { msg->points[i].count++; + atomic_inc(&data->dm_hit_count); goto out; } } @@ -157,7 +192,7 @@ static void trace_drop_common(struct sk_buff *skb, void *location) /* * We need to create a new entry */ - __nla_reserve_nohdr(data->skb, sizeof(struct net_dm_drop_point)); + __nla_reserve_nohdr(dskb, sizeof(struct net_dm_drop_point)); nla->nla_len += NLA_ALIGN(sizeof(struct net_dm_drop_point)); memcpy(msg->points[msg->entries].pc, &location, sizeof(void *)); msg->points[msg->entries].count = 1; @@ -169,6 +204,8 @@ static void trace_drop_common(struct sk_buff *skb, void *location) } out: + rcu_read_unlock(); + put_cpu_var(dm_cpu_data); return; } @@ -213,7 +250,7 @@ static int set_all_monitor_traces(int state) struct dm_hw_stat_delta *new_stat = NULL; struct dm_hw_stat_delta *temp; - spin_lock(&trace_state_lock); + mutex_lock(&trace_state_mutex); if (state == trace_state) { rc = -EAGAIN; @@ -252,7 +289,7 @@ static int set_all_monitor_traces(int state) rc = -EINPROGRESS; out_unlock: - spin_unlock(&trace_state_lock); + mutex_unlock(&trace_state_mutex); return rc; } @@ -295,12 +332,12 @@ static int dropmon_net_event(struct notifier_block *ev_block, new_stat->dev = dev; new_stat->last_rx = jiffies; - spin_lock(&trace_state_lock); + mutex_lock(&trace_state_mutex); list_add_rcu(&new_stat->list, &hw_stats_list); - spin_unlock(&trace_state_lock); + mutex_unlock(&trace_state_mutex); break; case NETDEV_UNREGISTER: - spin_lock(&trace_state_lock); + mutex_lock(&trace_state_mutex); list_for_each_entry_safe(new_stat, tmp, &hw_stats_list, list) { if (new_stat->dev == dev) { new_stat->dev = NULL; @@ -311,7 +348,7 @@ static int dropmon_net_event(struct notifier_block *ev_block, } } } - spin_unlock(&trace_state_lock); + mutex_unlock(&trace_state_mutex); break; } out: @@ -374,6 +411,8 @@ static int __init init_net_drop_monitor(void) data->send_timer.function = sched_send_work; } + initialized = 1; + goto out; out_unreg: diff --git a/net/core/net_namespace.c b/net/core/net_namespace.c index 0e950fda9a0a..31a5ae51a45c 100644 --- a/net/core/net_namespace.c +++ b/net/core/net_namespace.c @@ -83,21 +83,29 @@ assign: static int ops_init(const struct pernet_operations *ops, struct net *net) { - int err; + int err = -ENOMEM; + void *data = NULL; + if (ops->id && ops->size) { - void *data = kzalloc(ops->size, GFP_KERNEL); + data = kzalloc(ops->size, GFP_KERNEL); if (!data) - return -ENOMEM; + goto out; err = net_assign_generic(net, *ops->id, data); - if (err) { - kfree(data); - return err; - } + if (err) + goto cleanup; } + err = 0; if (ops->init) - return ops->init(net); - return 0; + err = ops->init(net); + if (!err) + return 0; + +cleanup: + kfree(data); + +out: + return err; } static void ops_free(const struct pernet_operations *ops, struct net *net) @@ -448,12 +456,7 @@ static void __unregister_pernet_operations(struct pernet_operations *ops) static int __register_pernet_operations(struct list_head *list, struct pernet_operations *ops) { - int err = 0; - err = ops_init(ops, &init_net); - if (err) - ops_free(ops, &init_net); - return err; - + return ops_init(ops, &init_net); } static void __unregister_pernet_operations(struct pernet_operations *ops) diff --git a/net/core/skbuff.c b/net/core/skbuff.c index baf8d281152c..e59840010d45 100644 --- a/net/core/skbuff.c +++ b/net/core/skbuff.c @@ -952,9 +952,11 @@ int pskb_expand_head(struct sk_buff *skb, int nhead, int ntail, goto adjust_others; } - data = kmalloc(size + sizeof(struct skb_shared_info), gfp_mask); + data = kmalloc(size + SKB_DATA_ALIGN(sizeof(struct skb_shared_info)), + gfp_mask); if (!data) goto nodata; + size = SKB_WITH_OVERHEAD(ksize(data)); /* Copy only real data... and, alas, header. This should be * optimized for the cases when header is void. diff --git a/net/ieee802154/6lowpan.c b/net/ieee802154/6lowpan.c index 368515885368..840821b90bcd 100644 --- a/net/ieee802154/6lowpan.c +++ b/net/ieee802154/6lowpan.c @@ -1044,6 +1044,24 @@ static void lowpan_dev_free(struct net_device *dev) free_netdev(dev); } +static struct wpan_phy *lowpan_get_phy(const struct net_device *dev) +{ + struct net_device *real_dev = lowpan_dev_info(dev)->real_dev; + return ieee802154_mlme_ops(real_dev)->get_phy(real_dev); +} + +static u16 lowpan_get_pan_id(const struct net_device *dev) +{ + struct net_device *real_dev = lowpan_dev_info(dev)->real_dev; + return ieee802154_mlme_ops(real_dev)->get_pan_id(real_dev); +} + +static u16 lowpan_get_short_addr(const struct net_device *dev) +{ + struct net_device *real_dev = lowpan_dev_info(dev)->real_dev; + return ieee802154_mlme_ops(real_dev)->get_short_addr(real_dev); +} + static struct header_ops lowpan_header_ops = { .create = lowpan_header_create, }; @@ -1053,6 +1071,12 @@ static const struct net_device_ops lowpan_netdev_ops = { .ndo_set_mac_address = eth_mac_addr, }; +static struct ieee802154_mlme_ops lowpan_mlme = { + .get_pan_id = lowpan_get_pan_id, + .get_phy = lowpan_get_phy, + .get_short_addr = lowpan_get_short_addr, +}; + static void lowpan_setup(struct net_device *dev) { pr_debug("(%s)\n", __func__); @@ -1070,6 +1094,7 @@ static void lowpan_setup(struct net_device *dev) dev->netdev_ops = &lowpan_netdev_ops; dev->header_ops = &lowpan_header_ops; + dev->ml_priv = &lowpan_mlme; dev->destructor = lowpan_dev_free; } @@ -1143,6 +1168,8 @@ static int lowpan_newlink(struct net *src_net, struct net_device *dev, list_add_tail(&entry->list, &lowpan_devices); mutex_unlock(&lowpan_dev_info(dev)->dev_list_mtx); + spin_lock_init(&flist_lock); + register_netdevice(dev); return 0; @@ -1152,11 +1179,20 @@ static void lowpan_dellink(struct net_device *dev, struct list_head *head) { struct lowpan_dev_info *lowpan_dev = lowpan_dev_info(dev); struct net_device *real_dev = lowpan_dev->real_dev; - struct lowpan_dev_record *entry; - struct lowpan_dev_record *tmp; + struct lowpan_dev_record *entry, *tmp; + struct lowpan_fragment *frame, *tframe; ASSERT_RTNL(); + spin_lock(&flist_lock); + list_for_each_entry_safe(frame, tframe, &lowpan_fragments, list) { + del_timer(&frame->timer); + list_del(&frame->list); + dev_kfree_skb(frame->skb); + kfree(frame); + } + spin_unlock(&flist_lock); + mutex_lock(&lowpan_dev_info(dev)->dev_list_mtx); list_for_each_entry_safe(entry, tmp, &lowpan_devices, list) { if (entry->ldev == dev) { diff --git a/net/ipv4/inet_diag.c b/net/ipv4/inet_diag.c index 8d25a1c557eb..8f8db724bfaf 100644 --- a/net/ipv4/inet_diag.c +++ b/net/ipv4/inet_diag.c @@ -141,7 +141,7 @@ int inet_sk_diag_fill(struct sock *sk, struct inet_connection_sock *icsk, goto rtattr_failure; if (icsk == NULL) { - r->idiag_rqueue = r->idiag_wqueue = 0; + handler->idiag_get_info(sk, r, NULL); goto out; } diff --git a/net/ipv4/netfilter/nf_conntrack_l3proto_ipv4.c b/net/ipv4/netfilter/nf_conntrack_l3proto_ipv4.c index de9da21113a1..cf73cc70ed2d 100644 --- a/net/ipv4/netfilter/nf_conntrack_l3proto_ipv4.c +++ b/net/ipv4/netfilter/nf_conntrack_l3proto_ipv4.c @@ -74,16 +74,24 @@ static int ipv4_get_l4proto(const struct sk_buff *skb, unsigned int nhoff, iph = skb_header_pointer(skb, nhoff, sizeof(_iph), &_iph); if (iph == NULL) - return -NF_DROP; + return -NF_ACCEPT; /* Conntrack defragments packets, we might still see fragments * inside ICMP packets though. */ if (iph->frag_off & htons(IP_OFFSET)) - return -NF_DROP; + return -NF_ACCEPT; *dataoff = nhoff + (iph->ihl << 2); *protonum = iph->protocol; + /* Check bogus IP headers */ + if (*dataoff > skb->len) { + pr_debug("nf_conntrack_ipv4: bogus IPv4 packet: " + "nhoff %u, ihl %u, skblen %u\n", + nhoff, iph->ihl << 2, skb->len); + return -NF_ACCEPT; + } + return NF_ACCEPT; } diff --git a/net/ipv4/tcp.c b/net/ipv4/tcp.c index 5d54ed30e821..8bb6adeb62c0 100644 --- a/net/ipv4/tcp.c +++ b/net/ipv4/tcp.c @@ -701,11 +701,12 @@ struct sk_buff *sk_stream_alloc_skb(struct sock *sk, int size, gfp_t gfp) skb = alloc_skb_fclone(size + sk->sk_prot->max_header, gfp); if (skb) { if (sk_wmem_schedule(sk, skb->truesize)) { + skb_reserve(skb, sk->sk_prot->max_header); /* * Make sure that we have exactly size bytes * available to the caller, no more, no less. */ - skb_reserve(skb, skb_tailroom(skb) - size); + skb->avail_size = size; return skb; } __kfree_skb(skb); @@ -995,10 +996,9 @@ new_segment: copy = seglen; /* Where to copy to? */ - if (skb_tailroom(skb) > 0) { + if (skb_availroom(skb) > 0) { /* We have some space in skb head. Superb! */ - if (copy > skb_tailroom(skb)) - copy = skb_tailroom(skb); + copy = min_t(int, copy, skb_availroom(skb)); err = skb_add_data_nocache(sk, skb, from, copy); if (err) goto do_fault; @@ -1452,7 +1452,7 @@ int tcp_recvmsg(struct kiocb *iocb, struct sock *sk, struct msghdr *msg, if ((available < target) && (len > sysctl_tcp_dma_copybreak) && !(flags & MSG_PEEK) && !sysctl_tcp_low_latency && - dma_find_channel(DMA_MEMCPY)) { + net_dma_find_channel()) { preempt_enable_no_resched(); tp->ucopy.pinned_list = dma_pin_iovec_pages(msg->msg_iov, len); @@ -1667,7 +1667,7 @@ do_prequeue: if (!(flags & MSG_TRUNC)) { #ifdef CONFIG_NET_DMA if (!tp->ucopy.dma_chan && tp->ucopy.pinned_list) - tp->ucopy.dma_chan = dma_find_channel(DMA_MEMCPY); + tp->ucopy.dma_chan = net_dma_find_channel(); if (tp->ucopy.dma_chan) { tp->ucopy.dma_cookie = dma_skb_copy_datagram_iovec( @@ -3302,8 +3302,7 @@ void __init tcp_init(void) tcp_init_mem(&init_net); /* Set per-socket limits to no more than 1/128 the pressure threshold */ - limit = nr_free_buffer_pages() << (PAGE_SHIFT - 10); - limit = max(limit, 128UL); + limit = nr_free_buffer_pages() << (PAGE_SHIFT - 7); max_share = min(4UL*1024*1024, limit); sysctl_tcp_wmem[0] = SK_MEM_QUANTUM; diff --git a/net/ipv4/tcp_input.c b/net/ipv4/tcp_input.c index e886e2f7fa8d..d99efd7dfb6c 100644 --- a/net/ipv4/tcp_input.c +++ b/net/ipv4/tcp_input.c @@ -335,6 +335,7 @@ static void tcp_grow_window(struct sock *sk, const struct sk_buff *skb) incr = __tcp_grow_window(sk, skb); if (incr) { + incr = max_t(int, incr, 2 * skb->len); tp->rcv_ssthresh = min(tp->rcv_ssthresh + incr, tp->window_clamp); inet_csk(sk)->icsk_ack.quick |= 1; @@ -474,8 +475,11 @@ static void tcp_rcv_rtt_update(struct tcp_sock *tp, u32 sample, int win_dep) if (!win_dep) { m -= (new_sample >> 3); new_sample += m; - } else if (m < new_sample) - new_sample = m << 3; + } else { + m <<= 3; + if (m < new_sample) + new_sample = m; + } } else { /* No previous measure. */ new_sample = m << 3; @@ -491,7 +495,7 @@ static inline void tcp_rcv_rtt_measure(struct tcp_sock *tp) goto new_measure; if (before(tp->rcv_nxt, tp->rcv_rtt_est.seq)) return; - tcp_rcv_rtt_update(tp, jiffies - tp->rcv_rtt_est.time, 1); + tcp_rcv_rtt_update(tp, tcp_time_stamp - tp->rcv_rtt_est.time, 1); new_measure: tp->rcv_rtt_est.seq = tp->rcv_nxt + tp->rcv_wnd; @@ -2864,11 +2868,14 @@ static inline void tcp_complete_cwr(struct sock *sk) /* Do not moderate cwnd if it's already undone in cwr or recovery. */ if (tp->undo_marker) { - if (inet_csk(sk)->icsk_ca_state == TCP_CA_CWR) + if (inet_csk(sk)->icsk_ca_state == TCP_CA_CWR) { tp->snd_cwnd = min(tp->snd_cwnd, tp->snd_ssthresh); - else /* PRR */ + tp->snd_cwnd_stamp = tcp_time_stamp; + } else if (tp->snd_ssthresh < TCP_INFINITE_SSTHRESH) { + /* PRR algorithm. */ tp->snd_cwnd = tp->snd_ssthresh; - tp->snd_cwnd_stamp = tcp_time_stamp; + tp->snd_cwnd_stamp = tcp_time_stamp; + } } tcp_ca_event(sk, CA_EVENT_COMPLETE_CWR); } @@ -5225,7 +5232,7 @@ static int tcp_dma_try_early_copy(struct sock *sk, struct sk_buff *skb, return 0; if (!tp->ucopy.dma_chan && tp->ucopy.pinned_list) - tp->ucopy.dma_chan = dma_find_channel(DMA_MEMCPY); + tp->ucopy.dma_chan = net_dma_find_channel(); if (tp->ucopy.dma_chan && skb_csum_unnecessary(skb)) { diff --git a/net/ipv4/tcp_ipv4.c b/net/ipv4/tcp_ipv4.c index 3a25cf743f8b..0cb86ceb652f 100644 --- a/net/ipv4/tcp_ipv4.c +++ b/net/ipv4/tcp_ipv4.c @@ -1730,7 +1730,7 @@ process: #ifdef CONFIG_NET_DMA struct tcp_sock *tp = tcp_sk(sk); if (!tp->ucopy.dma_chan && tp->ucopy.pinned_list) - tp->ucopy.dma_chan = dma_find_channel(DMA_MEMCPY); + tp->ucopy.dma_chan = net_dma_find_channel(); if (tp->ucopy.dma_chan) ret = tcp_v4_do_rcv(sk, skb); else diff --git a/net/ipv4/tcp_output.c b/net/ipv4/tcp_output.c index 364784a91939..7ac6423117ad 100644 --- a/net/ipv4/tcp_output.c +++ b/net/ipv4/tcp_output.c @@ -1096,6 +1096,7 @@ static void __pskb_trim_head(struct sk_buff *skb, int len) eat = min_t(int, len, skb_headlen(skb)); if (eat) { __skb_pull(skb, eat); + skb->avail_size -= eat; len -= eat; if (!len) return; @@ -2060,7 +2061,7 @@ static void tcp_retrans_try_collapse(struct sock *sk, struct sk_buff *to, /* Punt if not enough space exists in the first SKB for * the data in the second */ - if (skb->len > skb_tailroom(to)) + if (skb->len > skb_availroom(to)) break; if (after(TCP_SKB_CB(skb)->end_seq, tcp_wnd_end(tp))) diff --git a/net/ipv4/udp_diag.c b/net/ipv4/udp_diag.c index 8a949f19deb6..a7f86a3cd502 100644 --- a/net/ipv4/udp_diag.c +++ b/net/ipv4/udp_diag.c @@ -146,9 +146,17 @@ static int udp_diag_dump_one(struct sk_buff *in_skb, const struct nlmsghdr *nlh, return udp_dump_one(&udp_table, in_skb, nlh, req); } +static void udp_diag_get_info(struct sock *sk, struct inet_diag_msg *r, + void *info) +{ + r->idiag_rqueue = sk_rmem_alloc_get(sk); + r->idiag_wqueue = sk_wmem_alloc_get(sk); +} + static const struct inet_diag_handler udp_diag_handler = { .dump = udp_diag_dump, .dump_one = udp_diag_dump_one, + .idiag_get_info = udp_diag_get_info, .idiag_type = IPPROTO_UDP, }; @@ -167,6 +175,7 @@ static int udplite_diag_dump_one(struct sk_buff *in_skb, const struct nlmsghdr * static const struct inet_diag_handler udplite_diag_handler = { .dump = udplite_diag_dump, .dump_one = udplite_diag_dump_one, + .idiag_get_info = udp_diag_get_info, .idiag_type = IPPROTO_UDPLITE, }; diff --git a/net/ipv6/addrconf.c b/net/ipv6/addrconf.c index 6a3bb6077e19..7d5cb975cc6f 100644 --- a/net/ipv6/addrconf.c +++ b/net/ipv6/addrconf.c @@ -803,8 +803,7 @@ static void ipv6_del_addr(struct inet6_ifaddr *ifp) ip6_del_rt(rt); rt = NULL; } else if (!(rt->rt6i_flags & RTF_EXPIRES)) { - rt->dst.expires = expires; - rt->rt6i_flags |= RTF_EXPIRES; + rt6_set_expires(rt, expires); } } dst_release(&rt->dst); @@ -1887,11 +1886,9 @@ void addrconf_prefix_rcv(struct net_device *dev, u8 *opt, int len, bool sllao) rt = NULL; } else if (addrconf_finite_timeout(rt_expires)) { /* not infinity */ - rt->dst.expires = jiffies + rt_expires; - rt->rt6i_flags |= RTF_EXPIRES; + rt6_set_expires(rt, jiffies + rt_expires); } else { - rt->rt6i_flags &= ~RTF_EXPIRES; - rt->dst.expires = 0; + rt6_clean_expires(rt); } } else if (valid_lft) { clock_t expires = 0; diff --git a/net/ipv6/ip6_fib.c b/net/ipv6/ip6_fib.c index 5b27fbcae346..93717435013e 100644 --- a/net/ipv6/ip6_fib.c +++ b/net/ipv6/ip6_fib.c @@ -673,11 +673,10 @@ static int fib6_add_rt2node(struct fib6_node *fn, struct rt6_info *rt, &rt->rt6i_gateway)) { if (!(iter->rt6i_flags & RTF_EXPIRES)) return -EEXIST; - iter->dst.expires = rt->dst.expires; - if (!(rt->rt6i_flags & RTF_EXPIRES)) { - iter->rt6i_flags &= ~RTF_EXPIRES; - iter->dst.expires = 0; - } + if (!(rt->rt6i_flags & RTF_EXPIRES)) + rt6_clean_expires(iter); + else + rt6_set_expires(iter, rt->dst.expires); return -EEXIST; } } diff --git a/net/ipv6/ndisc.c b/net/ipv6/ndisc.c index 3dcdb81ec3e8..176b469322ac 100644 --- a/net/ipv6/ndisc.c +++ b/net/ipv6/ndisc.c @@ -1264,8 +1264,7 @@ static void ndisc_router_discovery(struct sk_buff *skb) } if (rt) - rt->dst.expires = jiffies + (HZ * lifetime); - + rt6_set_expires(rt, jiffies + (HZ * lifetime)); if (ra_msg->icmph.icmp6_hop_limit) { in6_dev->cnf.hop_limit = ra_msg->icmph.icmp6_hop_limit; if (rt) diff --git a/net/ipv6/netfilter/ip6_tables.c b/net/ipv6/netfilter/ip6_tables.c index 94874b0bdcdc..9d4e15559319 100644 --- a/net/ipv6/netfilter/ip6_tables.c +++ b/net/ipv6/netfilter/ip6_tables.c @@ -78,19 +78,6 @@ EXPORT_SYMBOL_GPL(ip6t_alloc_initial_table); Hence the start of any table is given by get_table() below. */ -/* Check for an extension */ -int -ip6t_ext_hdr(u8 nexthdr) -{ - return (nexthdr == IPPROTO_HOPOPTS) || - (nexthdr == IPPROTO_ROUTING) || - (nexthdr == IPPROTO_FRAGMENT) || - (nexthdr == IPPROTO_ESP) || - (nexthdr == IPPROTO_AH) || - (nexthdr == IPPROTO_NONE) || - (nexthdr == IPPROTO_DSTOPTS); -} - /* Returns whether matches rule or not. */ /* Performance critical - called for every packet */ static inline bool @@ -2366,7 +2353,6 @@ int ipv6_find_hdr(const struct sk_buff *skb, unsigned int *offset, EXPORT_SYMBOL(ip6t_register_table); EXPORT_SYMBOL(ip6t_unregister_table); EXPORT_SYMBOL(ip6t_do_table); -EXPORT_SYMBOL(ip6t_ext_hdr); EXPORT_SYMBOL(ipv6_find_hdr); module_init(ip6_tables_init); diff --git a/net/ipv6/route.c b/net/ipv6/route.c index 3992e26a6039..bc4888d902b2 100644 --- a/net/ipv6/route.c +++ b/net/ipv6/route.c @@ -62,7 +62,7 @@ #include <linux/sysctl.h> #endif -static struct rt6_info *ip6_rt_copy(const struct rt6_info *ort, +static struct rt6_info *ip6_rt_copy(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); @@ -285,6 +285,10 @@ static void ip6_dst_destroy(struct dst_entry *dst) rt->rt6i_idev = NULL; in6_dev_put(idev); } + + if (!(rt->rt6i_flags & RTF_EXPIRES) && dst->from) + dst_release(dst->from); + if (peer) { rt->rt6i_peer = NULL; inet_putpeer(peer); @@ -329,8 +333,17 @@ static void ip6_dst_ifdown(struct dst_entry *dst, struct net_device *dev, static __inline__ int rt6_check_expired(const struct rt6_info *rt) { - return (rt->rt6i_flags & RTF_EXPIRES) && - time_after(jiffies, rt->dst.expires); + struct rt6_info *ort = NULL; + + if (rt->rt6i_flags & RTF_EXPIRES) { + if (time_after(jiffies, rt->dst.expires)) + return 1; + } else if (rt->dst.from) { + ort = (struct rt6_info *) rt->dst.from; + return (ort->rt6i_flags & RTF_EXPIRES) && + time_after(jiffies, ort->dst.expires); + } + return 0; } static inline int rt6_need_strict(const struct in6_addr *daddr) @@ -620,12 +633,11 @@ int rt6_route_rcv(struct net_device *dev, u8 *opt, int len, (rt->rt6i_flags & ~RTF_PREF_MASK) | RTF_PREF(pref); if (rt) { - if (!addrconf_finite_timeout(lifetime)) { - rt->rt6i_flags &= ~RTF_EXPIRES; - } else { - rt->dst.expires = jiffies + HZ * lifetime; - rt->rt6i_flags |= RTF_EXPIRES; - } + if (!addrconf_finite_timeout(lifetime)) + rt6_clean_expires(rt); + else + rt6_set_expires(rt, jiffies + HZ * lifetime); + dst_release(&rt->dst); } return 0; @@ -730,7 +742,7 @@ int ip6_ins_rt(struct rt6_info *rt) return __ip6_ins_rt(rt, &info); } -static struct rt6_info *rt6_alloc_cow(const struct rt6_info *ort, +static struct rt6_info *rt6_alloc_cow(struct rt6_info *ort, const struct in6_addr *daddr, const struct in6_addr *saddr) { @@ -954,10 +966,10 @@ struct dst_entry *ip6_blackhole_route(struct net *net, struct dst_entry *dst_ori rt->rt6i_idev = ort->rt6i_idev; if (rt->rt6i_idev) in6_dev_hold(rt->rt6i_idev); - rt->dst.expires = 0; rt->rt6i_gateway = ort->rt6i_gateway; - rt->rt6i_flags = ort->rt6i_flags & ~RTF_EXPIRES; + rt->rt6i_flags = ort->rt6i_flags; + rt6_clean_expires(rt); rt->rt6i_metric = 0; memcpy(&rt->rt6i_dst, &ort->rt6i_dst, sizeof(struct rt6key)); @@ -1019,10 +1031,9 @@ static void ip6_link_failure(struct sk_buff *skb) rt = (struct rt6_info *) skb_dst(skb); if (rt) { - if (rt->rt6i_flags & RTF_CACHE) { - dst_set_expires(&rt->dst, 0); - rt->rt6i_flags |= RTF_EXPIRES; - } else if (rt->rt6i_node && (rt->rt6i_flags & RTF_DEFAULT)) + if (rt->rt6i_flags & RTF_CACHE) + rt6_update_expires(rt, 0); + else if (rt->rt6i_node && (rt->rt6i_flags & RTF_DEFAULT)) rt->rt6i_node->fn_sernum = -1; } } @@ -1289,9 +1300,12 @@ int ip6_route_add(struct fib6_config *cfg) } rt->dst.obsolete = -1; - rt->dst.expires = (cfg->fc_flags & RTF_EXPIRES) ? - jiffies + clock_t_to_jiffies(cfg->fc_expires) : - 0; + + if (cfg->fc_flags & RTF_EXPIRES) + rt6_set_expires(rt, jiffies + + clock_t_to_jiffies(cfg->fc_expires)); + else + rt6_clean_expires(rt); if (cfg->fc_protocol == RTPROT_UNSPEC) cfg->fc_protocol = RTPROT_BOOT; @@ -1736,8 +1750,8 @@ again: features |= RTAX_FEATURE_ALLFRAG; dst_metric_set(&rt->dst, RTAX_FEATURES, features); } - dst_set_expires(&rt->dst, net->ipv6.sysctl.ip6_rt_mtu_expires); - rt->rt6i_flags |= RTF_MODIFIED|RTF_EXPIRES; + rt6_update_expires(rt, net->ipv6.sysctl.ip6_rt_mtu_expires); + rt->rt6i_flags |= RTF_MODIFIED; goto out; } @@ -1765,9 +1779,8 @@ again: * which is 10 mins. After 10 mins the decreased pmtu is expired * and detecting PMTU increase will be automatically happened. */ - dst_set_expires(&nrt->dst, net->ipv6.sysctl.ip6_rt_mtu_expires); - nrt->rt6i_flags |= RTF_DYNAMIC|RTF_EXPIRES; - + rt6_update_expires(nrt, net->ipv6.sysctl.ip6_rt_mtu_expires); + nrt->rt6i_flags |= RTF_DYNAMIC; ip6_ins_rt(nrt); } out: @@ -1799,7 +1812,7 @@ void rt6_pmtu_discovery(const struct in6_addr *daddr, const struct in6_addr *sad * Misc support functions */ -static struct rt6_info *ip6_rt_copy(const struct rt6_info *ort, +static struct rt6_info *ip6_rt_copy(struct rt6_info *ort, const struct in6_addr *dest) { struct net *net = dev_net(ort->dst.dev); @@ -1819,10 +1832,14 @@ static struct rt6_info *ip6_rt_copy(const struct rt6_info *ort, if (rt->rt6i_idev) in6_dev_hold(rt->rt6i_idev); rt->dst.lastuse = jiffies; - rt->dst.expires = 0; rt->rt6i_gateway = ort->rt6i_gateway; - rt->rt6i_flags = ort->rt6i_flags & ~RTF_EXPIRES; + rt->rt6i_flags = ort->rt6i_flags; + if ((ort->rt6i_flags & (RTF_DEFAULT | RTF_ADDRCONF)) == + (RTF_DEFAULT | RTF_ADDRCONF)) + rt6_set_from(rt, ort); + else + rt6_clean_expires(rt); rt->rt6i_metric = 0; #ifdef CONFIG_IPV6_SUBTREES diff --git a/net/ipv6/tcp_ipv6.c b/net/ipv6/tcp_ipv6.c index 12c6ece67f39..98256cf72f9d 100644 --- a/net/ipv6/tcp_ipv6.c +++ b/net/ipv6/tcp_ipv6.c @@ -1383,6 +1383,10 @@ static struct sock * tcp_v6_syn_recv_sock(struct sock *sk, struct sk_buff *skb, tcp_mtup_init(newsk); tcp_sync_mss(newsk, dst_mtu(dst)); newtp->advmss = dst_metric_advmss(dst); + if (tcp_sk(sk)->rx_opt.user_mss && + tcp_sk(sk)->rx_opt.user_mss < newtp->advmss) + newtp->advmss = tcp_sk(sk)->rx_opt.user_mss; + tcp_initialize_rcv_mss(newsk); if (tcp_rsk(req)->snt_synack) tcp_valid_rtt_meas(newsk, @@ -1645,7 +1649,7 @@ process: #ifdef CONFIG_NET_DMA struct tcp_sock *tp = tcp_sk(sk); if (!tp->ucopy.dma_chan && tp->ucopy.pinned_list) - tp->ucopy.dma_chan = dma_find_channel(DMA_MEMCPY); + tp->ucopy.dma_chan = net_dma_find_channel(); if (tp->ucopy.dma_chan) ret = tcp_v6_do_rcv(sk, skb); else diff --git a/net/key/af_key.c b/net/key/af_key.c index 11dbb2255ccb..7e5d927b576f 100644 --- a/net/key/af_key.c +++ b/net/key/af_key.c @@ -3480,7 +3480,7 @@ static int pfkey_send_migrate(const struct xfrm_selector *sel, u8 dir, u8 type, /* Addresses to be used by KM for negotiation, if ext is available */ if (k != NULL && (set_sadb_kmaddress(skb, k) < 0)) - return -EINVAL; + goto err; /* selector src */ set_sadb_address(skb, sasize_sel, SADB_EXT_ADDRESS_SRC, sel); diff --git a/net/l2tp/l2tp_ip.c b/net/l2tp/l2tp_ip.c index 55670ec3cd0f..585d93ecee2d 100644 --- a/net/l2tp/l2tp_ip.c +++ b/net/l2tp/l2tp_ip.c @@ -232,7 +232,7 @@ static void l2tp_ip_close(struct sock *sk, long timeout) { write_lock_bh(&l2tp_ip_lock); hlist_del_init(&sk->sk_bind_node); - hlist_del_init(&sk->sk_node); + sk_del_node_init(sk); write_unlock_bh(&l2tp_ip_lock); sk_common_release(sk); } @@ -271,7 +271,8 @@ static int l2tp_ip_bind(struct sock *sk, struct sockaddr *uaddr, int addr_len) chk_addr_ret != RTN_MULTICAST && chk_addr_ret != RTN_BROADCAST) goto out; - inet->inet_rcv_saddr = inet->inet_saddr = addr->l2tp_addr.s_addr; + if (addr->l2tp_addr.s_addr) + inet->inet_rcv_saddr = inet->inet_saddr = addr->l2tp_addr.s_addr; if (chk_addr_ret == RTN_MULTICAST || chk_addr_ret == RTN_BROADCAST) inet->inet_saddr = 0; /* Use device */ sk_dst_reset(sk); diff --git a/net/netfilter/ipvs/ip_vs_core.c b/net/netfilter/ipvs/ip_vs_core.c index 2555816e7788..00bdb1d9d690 100644 --- a/net/netfilter/ipvs/ip_vs_core.c +++ b/net/netfilter/ipvs/ip_vs_core.c @@ -1924,6 +1924,7 @@ protocol_fail: control_fail: ip_vs_estimator_net_cleanup(net); estimator_fail: + net->ipvs = NULL; return -ENOMEM; } @@ -1936,6 +1937,7 @@ static void __net_exit __ip_vs_cleanup(struct net *net) ip_vs_control_net_cleanup(net); ip_vs_estimator_net_cleanup(net); IP_VS_DBG(2, "ipvs netns %d released\n", net_ipvs(net)->gen); + net->ipvs = NULL; } static void __net_exit __ip_vs_dev_cleanup(struct net *net) @@ -1993,10 +1995,18 @@ static int __init ip_vs_init(void) goto cleanup_dev; } + ret = ip_vs_register_nl_ioctl(); + if (ret < 0) { + pr_err("can't register netlink/ioctl.\n"); + goto cleanup_hooks; + } + pr_info("ipvs loaded.\n"); return ret; +cleanup_hooks: + nf_unregister_hooks(ip_vs_ops, ARRAY_SIZE(ip_vs_ops)); cleanup_dev: unregister_pernet_device(&ipvs_core_dev_ops); cleanup_sub: @@ -2012,6 +2022,7 @@ exit: static void __exit ip_vs_cleanup(void) { + ip_vs_unregister_nl_ioctl(); nf_unregister_hooks(ip_vs_ops, ARRAY_SIZE(ip_vs_ops)); unregister_pernet_device(&ipvs_core_dev_ops); unregister_pernet_subsys(&ipvs_core_ops); /* free ip_vs struct */ diff --git a/net/netfilter/ipvs/ip_vs_ctl.c b/net/netfilter/ipvs/ip_vs_ctl.c index b3afe189af61..f5589987fc80 100644 --- a/net/netfilter/ipvs/ip_vs_ctl.c +++ b/net/netfilter/ipvs/ip_vs_ctl.c @@ -3680,7 +3680,7 @@ int __net_init ip_vs_control_net_init_sysctl(struct net *net) return 0; } -void __net_init ip_vs_control_net_cleanup_sysctl(struct net *net) +void __net_exit ip_vs_control_net_cleanup_sysctl(struct net *net) { struct netns_ipvs *ipvs = net_ipvs(net); @@ -3692,7 +3692,7 @@ void __net_init ip_vs_control_net_cleanup_sysctl(struct net *net) #else int __net_init ip_vs_control_net_init_sysctl(struct net *net) { return 0; } -void __net_init ip_vs_control_net_cleanup_sysctl(struct net *net) { } +void __net_exit ip_vs_control_net_cleanup_sysctl(struct net *net) { } #endif @@ -3750,21 +3750,10 @@ void __net_exit ip_vs_control_net_cleanup(struct net *net) free_percpu(ipvs->tot_stats.cpustats); } -int __init ip_vs_control_init(void) +int __init ip_vs_register_nl_ioctl(void) { - int idx; int ret; - EnterFunction(2); - - /* Initialize svc_table, ip_vs_svc_fwm_table, rs_table */ - for(idx = 0; idx < IP_VS_SVC_TAB_SIZE; idx++) { - INIT_LIST_HEAD(&ip_vs_svc_table[idx]); - INIT_LIST_HEAD(&ip_vs_svc_fwm_table[idx]); - } - - smp_wmb(); /* Do we really need it now ? */ - ret = nf_register_sockopt(&ip_vs_sockopts); if (ret) { pr_err("cannot register sockopt.\n"); @@ -3776,28 +3765,47 @@ int __init ip_vs_control_init(void) pr_err("cannot register Generic Netlink interface.\n"); goto err_genl; } - - ret = register_netdevice_notifier(&ip_vs_dst_notifier); - if (ret < 0) - goto err_notf; - - LeaveFunction(2); return 0; -err_notf: - ip_vs_genl_unregister(); err_genl: nf_unregister_sockopt(&ip_vs_sockopts); err_sock: return ret; } +void ip_vs_unregister_nl_ioctl(void) +{ + ip_vs_genl_unregister(); + nf_unregister_sockopt(&ip_vs_sockopts); +} + +int __init ip_vs_control_init(void) +{ + int idx; + int ret; + + EnterFunction(2); + + /* Initialize svc_table, ip_vs_svc_fwm_table, rs_table */ + for (idx = 0; idx < IP_VS_SVC_TAB_SIZE; idx++) { + INIT_LIST_HEAD(&ip_vs_svc_table[idx]); + INIT_LIST_HEAD(&ip_vs_svc_fwm_table[idx]); + } + + smp_wmb(); /* Do we really need it now ? */ + + ret = register_netdevice_notifier(&ip_vs_dst_notifier); + if (ret < 0) + return ret; + + LeaveFunction(2); + return 0; +} + void ip_vs_control_cleanup(void) { EnterFunction(2); unregister_netdevice_notifier(&ip_vs_dst_notifier); - ip_vs_genl_unregister(); - nf_unregister_sockopt(&ip_vs_sockopts); LeaveFunction(2); } diff --git a/net/netfilter/ipvs/ip_vs_ftp.c b/net/netfilter/ipvs/ip_vs_ftp.c index 538d74ee4f68..e39f693dd3e4 100644 --- a/net/netfilter/ipvs/ip_vs_ftp.c +++ b/net/netfilter/ipvs/ip_vs_ftp.c @@ -439,6 +439,8 @@ static int __net_init __ip_vs_ftp_init(struct net *net) struct ip_vs_app *app; struct netns_ipvs *ipvs = net_ipvs(net); + if (!ipvs) + return -ENOENT; app = kmemdup(&ip_vs_ftp, sizeof(struct ip_vs_app), GFP_KERNEL); if (!app) return -ENOMEM; diff --git a/net/netfilter/ipvs/ip_vs_lblc.c b/net/netfilter/ipvs/ip_vs_lblc.c index 0f16283fd058..caa43704e55e 100644 --- a/net/netfilter/ipvs/ip_vs_lblc.c +++ b/net/netfilter/ipvs/ip_vs_lblc.c @@ -551,6 +551,9 @@ static int __net_init __ip_vs_lblc_init(struct net *net) { struct netns_ipvs *ipvs = net_ipvs(net); + if (!ipvs) + return -ENOENT; + if (!net_eq(net, &init_net)) { ipvs->lblc_ctl_table = kmemdup(vs_vars_table, sizeof(vs_vars_table), diff --git a/net/netfilter/ipvs/ip_vs_lblcr.c b/net/netfilter/ipvs/ip_vs_lblcr.c index eec797f8cce7..548bf37aa29e 100644 --- a/net/netfilter/ipvs/ip_vs_lblcr.c +++ b/net/netfilter/ipvs/ip_vs_lblcr.c @@ -745,6 +745,9 @@ static int __net_init __ip_vs_lblcr_init(struct net *net) { struct netns_ipvs *ipvs = net_ipvs(net); + if (!ipvs) + return -ENOENT; + if (!net_eq(net, &init_net)) { ipvs->lblcr_ctl_table = kmemdup(vs_vars_table, sizeof(vs_vars_table), diff --git a/net/netfilter/ipvs/ip_vs_proto.c b/net/netfilter/ipvs/ip_vs_proto.c index f843a8833250..ed835e67a07e 100644 --- a/net/netfilter/ipvs/ip_vs_proto.c +++ b/net/netfilter/ipvs/ip_vs_proto.c @@ -59,9 +59,6 @@ static int __used __init register_ip_vs_protocol(struct ip_vs_protocol *pp) return 0; } -#if defined(CONFIG_IP_VS_PROTO_TCP) || defined(CONFIG_IP_VS_PROTO_UDP) || \ - defined(CONFIG_IP_VS_PROTO_SCTP) || defined(CONFIG_IP_VS_PROTO_AH) || \ - defined(CONFIG_IP_VS_PROTO_ESP) /* * register an ipvs protocols netns related data */ @@ -81,12 +78,18 @@ register_ip_vs_proto_netns(struct net *net, struct ip_vs_protocol *pp) ipvs->proto_data_table[hash] = pd; atomic_set(&pd->appcnt, 0); /* Init app counter */ - if (pp->init_netns != NULL) - pp->init_netns(net, pd); + if (pp->init_netns != NULL) { + int ret = pp->init_netns(net, pd); + if (ret) { + /* unlink an free proto data */ + ipvs->proto_data_table[hash] = pd->next; + kfree(pd); + return ret; + } + } return 0; } -#endif /* * unregister an ipvs protocol @@ -316,22 +319,35 @@ ip_vs_tcpudp_debug_packet(int af, struct ip_vs_protocol *pp, */ int __net_init ip_vs_protocol_net_init(struct net *net) { + int i, ret; + static struct ip_vs_protocol *protos[] = { #ifdef CONFIG_IP_VS_PROTO_TCP - register_ip_vs_proto_netns(net, &ip_vs_protocol_tcp); + &ip_vs_protocol_tcp, #endif #ifdef CONFIG_IP_VS_PROTO_UDP - register_ip_vs_proto_netns(net, &ip_vs_protocol_udp); + &ip_vs_protocol_udp, #endif #ifdef CONFIG_IP_VS_PROTO_SCTP - register_ip_vs_proto_netns(net, &ip_vs_protocol_sctp); + &ip_vs_protocol_sctp, #endif #ifdef CONFIG_IP_VS_PROTO_AH - register_ip_vs_proto_netns(net, &ip_vs_protocol_ah); + &ip_vs_protocol_ah, #endif #ifdef CONFIG_IP_VS_PROTO_ESP - register_ip_vs_proto_netns(net, &ip_vs_protocol_esp); + &ip_vs_protocol_esp, #endif + }; + + for (i = 0; i < ARRAY_SIZE(protos); i++) { + ret = register_ip_vs_proto_netns(net, protos[i]); + if (ret < 0) + goto cleanup; + } return 0; + +cleanup: + ip_vs_protocol_net_cleanup(net); + return ret; } void __net_exit ip_vs_protocol_net_cleanup(struct net *net) diff --git a/net/netfilter/ipvs/ip_vs_proto_sctp.c b/net/netfilter/ipvs/ip_vs_proto_sctp.c index 1fbf7a2816f5..9f3fb751c491 100644 --- a/net/netfilter/ipvs/ip_vs_proto_sctp.c +++ b/net/netfilter/ipvs/ip_vs_proto_sctp.c @@ -1090,7 +1090,7 @@ out: * timeouts is netns related now. * --------------------------------------------- */ -static void __ip_vs_sctp_init(struct net *net, struct ip_vs_proto_data *pd) +static int __ip_vs_sctp_init(struct net *net, struct ip_vs_proto_data *pd) { struct netns_ipvs *ipvs = net_ipvs(net); @@ -1098,6 +1098,9 @@ static void __ip_vs_sctp_init(struct net *net, struct ip_vs_proto_data *pd) spin_lock_init(&ipvs->sctp_app_lock); pd->timeout_table = ip_vs_create_timeout_table((int *)sctp_timeouts, sizeof(sctp_timeouts)); + if (!pd->timeout_table) + return -ENOMEM; + return 0; } static void __ip_vs_sctp_exit(struct net *net, struct ip_vs_proto_data *pd) diff --git a/net/netfilter/ipvs/ip_vs_proto_tcp.c b/net/netfilter/ipvs/ip_vs_proto_tcp.c index ef8641f7af83..cd609cc62721 100644 --- a/net/netfilter/ipvs/ip_vs_proto_tcp.c +++ b/net/netfilter/ipvs/ip_vs_proto_tcp.c @@ -677,7 +677,7 @@ void ip_vs_tcp_conn_listen(struct net *net, struct ip_vs_conn *cp) * timeouts is netns related now. * --------------------------------------------- */ -static void __ip_vs_tcp_init(struct net *net, struct ip_vs_proto_data *pd) +static int __ip_vs_tcp_init(struct net *net, struct ip_vs_proto_data *pd) { struct netns_ipvs *ipvs = net_ipvs(net); @@ -685,7 +685,10 @@ static void __ip_vs_tcp_init(struct net *net, struct ip_vs_proto_data *pd) spin_lock_init(&ipvs->tcp_app_lock); pd->timeout_table = ip_vs_create_timeout_table((int *)tcp_timeouts, sizeof(tcp_timeouts)); + if (!pd->timeout_table) + return -ENOMEM; pd->tcp_state_table = tcp_states; + return 0; } static void __ip_vs_tcp_exit(struct net *net, struct ip_vs_proto_data *pd) diff --git a/net/netfilter/ipvs/ip_vs_proto_udp.c b/net/netfilter/ipvs/ip_vs_proto_udp.c index f4b7262896bb..2fedb2dcb3d1 100644 --- a/net/netfilter/ipvs/ip_vs_proto_udp.c +++ b/net/netfilter/ipvs/ip_vs_proto_udp.c @@ -467,7 +467,7 @@ udp_state_transition(struct ip_vs_conn *cp, int direction, cp->timeout = pd->timeout_table[IP_VS_UDP_S_NORMAL]; } -static void __udp_init(struct net *net, struct ip_vs_proto_data *pd) +static int __udp_init(struct net *net, struct ip_vs_proto_data *pd) { struct netns_ipvs *ipvs = net_ipvs(net); @@ -475,6 +475,9 @@ static void __udp_init(struct net *net, struct ip_vs_proto_data *pd) spin_lock_init(&ipvs->udp_app_lock); pd->timeout_table = ip_vs_create_timeout_table((int *)udp_timeouts, sizeof(udp_timeouts)); + if (!pd->timeout_table) + return -ENOMEM; + return 0; } static void __udp_exit(struct net *net, struct ip_vs_proto_data *pd) diff --git a/net/netfilter/nf_conntrack_core.c b/net/netfilter/nf_conntrack_core.c index 3cc4487ac349..729f157a0efa 100644 --- a/net/netfilter/nf_conntrack_core.c +++ b/net/netfilter/nf_conntrack_core.c @@ -1592,7 +1592,7 @@ static int nf_conntrack_init_net(struct net *net) return 0; err_timeout: - nf_conntrack_timeout_fini(net); + nf_conntrack_ecache_fini(net); err_ecache: nf_conntrack_tstamp_fini(net); err_tstamp: diff --git a/net/netfilter/nf_conntrack_proto_tcp.c b/net/netfilter/nf_conntrack_proto_tcp.c index 361eade62a09..0d07a1dcf605 100644 --- a/net/netfilter/nf_conntrack_proto_tcp.c +++ b/net/netfilter/nf_conntrack_proto_tcp.c @@ -584,8 +584,8 @@ static bool tcp_in_window(const struct nf_conn *ct, * Let's try to use the data from the packet. */ sender->td_end = end; - win <<= sender->td_scale; - sender->td_maxwin = (win == 0 ? 1 : win); + swin = win << sender->td_scale; + sender->td_maxwin = (swin == 0 ? 1 : swin); sender->td_maxend = end + sender->td_maxwin; /* * We haven't seen traffic in the other direction yet diff --git a/net/netfilter/xt_CT.c b/net/netfilter/xt_CT.c index 59530e93fa58..3746d8b9a478 100644 --- a/net/netfilter/xt_CT.c +++ b/net/netfilter/xt_CT.c @@ -227,7 +227,7 @@ static int xt_ct_tg_check_v1(const struct xt_tgchk_param *par) } #ifdef CONFIG_NF_CONNTRACK_TIMEOUT - if (info->timeout) { + if (info->timeout[0]) { typeof(nf_ct_timeout_find_get_hook) timeout_find_get; struct nf_conn_timeout *timeout_ext; diff --git a/net/phonet/pn_dev.c b/net/phonet/pn_dev.c index 9b9a85ecc4c7..bf5cf69c820a 100644 --- a/net/phonet/pn_dev.c +++ b/net/phonet/pn_dev.c @@ -331,23 +331,6 @@ static int __net_init phonet_init_net(struct net *net) static void __net_exit phonet_exit_net(struct net *net) { - struct phonet_net *pnn = phonet_pernet(net); - struct net_device *dev; - unsigned i; - - rtnl_lock(); - for_each_netdev(net, dev) - phonet_device_destroy(dev); - - for (i = 0; i < 64; i++) { - dev = pnn->routes.table[i]; - if (dev) { - rtm_phonet_notify(RTM_DELROUTE, dev, i); - dev_put(dev); - } - } - rtnl_unlock(); - proc_net_remove(net, "phonet"); } @@ -361,7 +344,7 @@ static struct pernet_operations phonet_net_ops = { /* Initialize Phonet devices list */ int __init phonet_device_init(void) { - int err = register_pernet_device(&phonet_net_ops); + int err = register_pernet_subsys(&phonet_net_ops); if (err) return err; @@ -377,7 +360,7 @@ void phonet_device_exit(void) { rtnl_unregister_all(PF_PHONET); unregister_netdevice_notifier(&phonet_device_notifier); - unregister_pernet_device(&phonet_net_ops); + unregister_pernet_subsys(&phonet_net_ops); proc_net_remove(&init_net, "pnresource"); } diff --git a/net/sched/sch_gred.c b/net/sched/sch_gred.c index 0b15236be7b6..8179494c269a 100644 --- a/net/sched/sch_gred.c +++ b/net/sched/sch_gred.c @@ -565,11 +565,8 @@ static int gred_dump(struct Qdisc *sch, struct sk_buff *skb) opt.packets = q->packetsin; opt.bytesin = q->bytesin; - if (gred_wred_mode(table)) { - q->vars.qidlestart = - table->tab[table->def]->vars.qidlestart; - q->vars.qavg = table->tab[table->def]->vars.qavg; - } + if (gred_wred_mode(table)) + gred_load_wred_set(table, q); opt.qave = red_calc_qavg(&q->parms, &q->vars, q->vars.qavg); diff --git a/net/sched/sch_netem.c b/net/sched/sch_netem.c index 5da548fa7ae9..ebd22966f748 100644 --- a/net/sched/sch_netem.c +++ b/net/sched/sch_netem.c @@ -408,10 +408,8 @@ static int netem_enqueue(struct sk_buff *skb, struct Qdisc *sch) if (q->corrupt && q->corrupt >= get_crandom(&q->corrupt_cor)) { if (!(skb = skb_unshare(skb, GFP_ATOMIC)) || (skb->ip_summed == CHECKSUM_PARTIAL && - skb_checksum_help(skb))) { - sch->qstats.drops++; - return NET_XMIT_DROP; - } + skb_checksum_help(skb))) + return qdisc_drop(skb, sch); skb->data[net_random() % skb_headlen(skb)] ^= 1<<(net_random() % 8); } |