diff options
Diffstat (limited to 'net')
-rw-r--r-- | net/core/dev.c | 1 | ||||
-rw-r--r-- | net/core/ethtool.c | 2 | ||||
-rw-r--r-- | net/core/net-sysfs.c | 17 | ||||
-rw-r--r-- | net/ipv4/af_inet.c | 1 | ||||
-rw-r--r-- | net/ipv4/icmp.c | 9 | ||||
-rw-r--r-- | net/ipv4/multipath_drr.c | 2 | ||||
-rw-r--r-- | net/ipv4/multipath_random.c | 2 | ||||
-rw-r--r-- | net/ipv4/multipath_rr.c | 2 | ||||
-rw-r--r-- | net/ipv4/multipath_wrandom.c | 2 | ||||
-rw-r--r-- | net/ipv4/netfilter/ip_conntrack_standalone.c | 1 | ||||
-rw-r--r-- | net/ipv4/netfilter/ipt_recent.c | 10 | ||||
-rw-r--r-- | net/ipv4/sysctl_net_ipv4.c | 9 | ||||
-rw-r--r-- | net/ipv4/tcp.c | 2 | ||||
-rw-r--r-- | net/ipv6/addrconf.c | 1 | ||||
-rw-r--r-- | net/ipv6/icmp.c | 14 | ||||
-rw-r--r-- | net/ipv6/ip6_tunnel.c | 1 | ||||
-rw-r--r-- | net/sched/Kconfig | 2 | ||||
-rw-r--r-- | net/sched/act_api.c | 2 | ||||
-rw-r--r-- | net/sched/cls_basic.c | 3 | ||||
-rw-r--r-- | net/sched/em_meta.c | 295 | ||||
-rw-r--r-- | net/sctp/input.c | 49 | ||||
-rw-r--r-- | net/sctp/ipv6.c | 36 | ||||
-rw-r--r-- | net/sctp/proc.c | 194 | ||||
-rw-r--r-- | net/sctp/protocol.c | 7 | ||||
-rw-r--r-- | net/sctp/socket.c | 12 |
25 files changed, 554 insertions, 122 deletions
diff --git a/net/core/dev.c b/net/core/dev.c index f15a3ff..ab93577 100644 --- a/net/core/dev.c +++ b/net/core/dev.c @@ -1744,6 +1744,7 @@ static int process_backlog(struct net_device *backlog_dev, int *budget) struct softnet_data *queue = &__get_cpu_var(softnet_data); unsigned long start_time = jiffies; + backlog_dev->weight = weight_p; for (;;) { struct sk_buff *skb; struct net_device *dev; diff --git a/net/core/ethtool.c b/net/core/ethtool.c index 8ec4848..a3eeb88 100644 --- a/net/core/ethtool.c +++ b/net/core/ethtool.c @@ -356,7 +356,7 @@ static int ethtool_set_coalesce(struct net_device *dev, void __user *useraddr) { struct ethtool_coalesce coalesce; - if (!dev->ethtool_ops->get_coalesce) + if (!dev->ethtool_ops->set_coalesce) return -EOPNOTSUPP; if (copy_from_user(&coalesce, useraddr, sizeof(coalesce))) diff --git a/net/core/net-sysfs.c b/net/core/net-sysfs.c index 910eb4c..e2137f3 100644 --- a/net/core/net-sysfs.c +++ b/net/core/net-sysfs.c @@ -185,6 +185,22 @@ static ssize_t store_tx_queue_len(struct class_device *dev, const char *buf, siz static CLASS_DEVICE_ATTR(tx_queue_len, S_IRUGO | S_IWUSR, show_tx_queue_len, store_tx_queue_len); +NETDEVICE_SHOW(weight, fmt_dec); + +static int change_weight(struct net_device *net, unsigned long new_weight) +{ + net->weight = new_weight; + return 0; +} + +static ssize_t store_weight(struct class_device *dev, const char *buf, size_t len) +{ + return netdev_store(dev, buf, len, change_weight); +} + +static CLASS_DEVICE_ATTR(weight, S_IRUGO | S_IWUSR, show_weight, + store_weight); + static struct class_device_attribute *net_class_attributes[] = { &class_device_attr_ifindex, @@ -194,6 +210,7 @@ static struct class_device_attribute *net_class_attributes[] = { &class_device_attr_features, &class_device_attr_mtu, &class_device_attr_flags, + &class_device_attr_weight, &class_device_attr_type, &class_device_attr_address, &class_device_attr_broadcast, diff --git a/net/ipv4/af_inet.c b/net/ipv4/af_inet.c index b3cb49c..03942f1 100644 --- a/net/ipv4/af_inet.c +++ b/net/ipv4/af_inet.c @@ -1181,6 +1181,7 @@ EXPORT_SYMBOL(inet_stream_connect); EXPORT_SYMBOL(inet_stream_ops); EXPORT_SYMBOL(inet_unregister_protosw); EXPORT_SYMBOL(net_statistics); +EXPORT_SYMBOL(sysctl_ip_nonlocal_bind); #ifdef INET_REFCNT_DEBUG EXPORT_SYMBOL(inet_sock_nr); diff --git a/net/ipv4/icmp.c b/net/ipv4/icmp.c index 85bf0d3..cb75948 100644 --- a/net/ipv4/icmp.c +++ b/net/ipv4/icmp.c @@ -207,6 +207,7 @@ int sysctl_icmp_ignore_bogus_error_responses; int sysctl_icmp_ratelimit = 1 * HZ; int sysctl_icmp_ratemask = 0x1818; +int sysctl_icmp_errors_use_inbound_ifaddr; /* * ICMP control array. This specifies what to do with each ICMP. @@ -511,8 +512,12 @@ void icmp_send(struct sk_buff *skb_in, int type, int code, u32 info) */ saddr = iph->daddr; - if (!(rt->rt_flags & RTCF_LOCAL)) - saddr = 0; + if (!(rt->rt_flags & RTCF_LOCAL)) { + if (sysctl_icmp_errors_use_inbound_ifaddr) + saddr = inet_select_addr(skb_in->dev, 0, RT_SCOPE_LINK); + else + saddr = 0; + } tos = icmp_pointers[type].error ? ((iph->tos & IPTOS_TOS_MASK) | IPTOS_PREC_INTERNETCONTROL) : diff --git a/net/ipv4/multipath_drr.c b/net/ipv4/multipath_drr.c index cf2e6bc..c9cf872 100644 --- a/net/ipv4/multipath_drr.c +++ b/net/ipv4/multipath_drr.c @@ -31,6 +31,7 @@ #include <linux/igmp.h> #include <linux/proc_fs.h> #include <linux/seq_file.h> +#include <linux/module.h> #include <linux/mroute.h> #include <linux/init.h> #include <net/ip.h> @@ -247,3 +248,4 @@ static void __exit drr_exit(void) module_init(drr_init); module_exit(drr_exit); +MODULE_LICENSE("GPL"); diff --git a/net/ipv4/multipath_random.c b/net/ipv4/multipath_random.c index 805a16e..5249dbe 100644 --- a/net/ipv4/multipath_random.c +++ b/net/ipv4/multipath_random.c @@ -31,6 +31,7 @@ #include <linux/igmp.h> #include <linux/proc_fs.h> #include <linux/seq_file.h> +#include <linux/module.h> #include <linux/mroute.h> #include <linux/init.h> #include <net/ip.h> @@ -126,3 +127,4 @@ static void __exit random_exit(void) module_init(random_init); module_exit(random_exit); +MODULE_LICENSE("GPL"); diff --git a/net/ipv4/multipath_rr.c b/net/ipv4/multipath_rr.c index 061b6b2..b6cd287 100644 --- a/net/ipv4/multipath_rr.c +++ b/net/ipv4/multipath_rr.c @@ -31,6 +31,7 @@ #include <linux/igmp.h> #include <linux/proc_fs.h> #include <linux/seq_file.h> +#include <linux/module.h> #include <linux/mroute.h> #include <linux/init.h> #include <net/ip.h> @@ -93,3 +94,4 @@ static void __exit rr_exit(void) module_init(rr_init); module_exit(rr_exit); +MODULE_LICENSE("GPL"); diff --git a/net/ipv4/multipath_wrandom.c b/net/ipv4/multipath_wrandom.c index c3d2ca1..bd7d75b 100644 --- a/net/ipv4/multipath_wrandom.c +++ b/net/ipv4/multipath_wrandom.c @@ -31,6 +31,7 @@ #include <linux/igmp.h> #include <linux/proc_fs.h> #include <linux/seq_file.h> +#include <linux/module.h> #include <linux/mroute.h> #include <linux/init.h> #include <net/ip.h> @@ -342,3 +343,4 @@ static void __exit wrandom_exit(void) module_init(wrandom_init); module_exit(wrandom_exit); +MODULE_LICENSE("GPL"); diff --git a/net/ipv4/netfilter/ip_conntrack_standalone.c b/net/ipv4/netfilter/ip_conntrack_standalone.c index 46ca45f..bc59f7b 100644 --- a/net/ipv4/netfilter/ip_conntrack_standalone.c +++ b/net/ipv4/netfilter/ip_conntrack_standalone.c @@ -256,6 +256,7 @@ static void *exp_seq_next(struct seq_file *s, void *v, loff_t *pos) { struct list_head *e = v; + ++*pos; e = e->next; if (e == &ip_conntrack_expect_list) diff --git a/net/ipv4/netfilter/ipt_recent.c b/net/ipv4/netfilter/ipt_recent.c index 25ab9fa..2d44b07 100644 --- a/net/ipv4/netfilter/ipt_recent.c +++ b/net/ipv4/netfilter/ipt_recent.c @@ -223,7 +223,7 @@ static int ip_recent_ctrl(struct file *file, const char __user *input, unsigned curr_table->table[count].last_seen = 0; curr_table->table[count].addr = 0; curr_table->table[count].ttl = 0; - memset(curr_table->table[count].last_pkts,0,ip_pkt_list_tot*sizeof(u_int32_t)); + memset(curr_table->table[count].last_pkts,0,ip_pkt_list_tot*sizeof(unsigned long)); curr_table->table[count].oldest_pkt = 0; curr_table->table[count].time_pos = 0; curr_table->time_info[count].position = count; @@ -502,7 +502,7 @@ match(const struct sk_buff *skb, location = time_info[curr_table->time_pos].position; hash_table[r_list[location].hash_entry] = -1; hash_table[hash_result] = location; - memset(r_list[location].last_pkts,0,ip_pkt_list_tot*sizeof(u_int32_t)); + memset(r_list[location].last_pkts,0,ip_pkt_list_tot*sizeof(unsigned long)); r_list[location].time_pos = curr_table->time_pos; r_list[location].addr = addr; r_list[location].ttl = ttl; @@ -631,7 +631,7 @@ match(const struct sk_buff *skb, r_list[location].last_seen = 0; r_list[location].addr = 0; r_list[location].ttl = 0; - memset(r_list[location].last_pkts,0,ip_pkt_list_tot*sizeof(u_int32_t)); + memset(r_list[location].last_pkts,0,ip_pkt_list_tot*sizeof(unsigned long)); r_list[location].oldest_pkt = 0; ans = !info->invert; } @@ -734,10 +734,10 @@ checkentry(const char *tablename, memset(curr_table->table,0,sizeof(struct recent_ip_list)*ip_list_tot); #ifdef DEBUG if(debug) printk(KERN_INFO RECENT_NAME ": checkentry: Allocating %d for pkt_list.\n", - sizeof(u_int32_t)*ip_pkt_list_tot*ip_list_tot); + sizeof(unsigned long)*ip_pkt_list_tot*ip_list_tot); #endif - hold = vmalloc(sizeof(u_int32_t)*ip_pkt_list_tot*ip_list_tot); + hold = vmalloc(sizeof(unsigned long)*ip_pkt_list_tot*ip_list_tot); #ifdef DEBUG if(debug) printk(KERN_INFO RECENT_NAME ": checkentry: After pkt_list allocation.\n"); #endif diff --git a/net/ipv4/sysctl_net_ipv4.c b/net/ipv4/sysctl_net_ipv4.c index 3aafb29..23068bd 100644 --- a/net/ipv4/sysctl_net_ipv4.c +++ b/net/ipv4/sysctl_net_ipv4.c @@ -23,6 +23,7 @@ extern int sysctl_ip_nonlocal_bind; extern int sysctl_icmp_echo_ignore_all; extern int sysctl_icmp_echo_ignore_broadcasts; extern int sysctl_icmp_ignore_bogus_error_responses; +extern int sysctl_icmp_errors_use_inbound_ifaddr; /* From ip_fragment.c */ extern int sysctl_ipfrag_low_thresh; @@ -396,6 +397,14 @@ ctl_table ipv4_table[] = { .proc_handler = &proc_dointvec }, { + .ctl_name = NET_IPV4_ICMP_ERRORS_USE_INBOUND_IFADDR, + .procname = "icmp_errors_use_inbound_ifaddr", + .data = &sysctl_icmp_errors_use_inbound_ifaddr, + .maxlen = sizeof(int), + .mode = 0644, + .proc_handler = &proc_dointvec + }, + { .ctl_name = NET_IPV4_ROUTE, .procname = "route", .maxlen = 0, diff --git a/net/ipv4/tcp.c b/net/ipv4/tcp.c index a037baf..0d9a4fd 100644 --- a/net/ipv4/tcp.c +++ b/net/ipv4/tcp.c @@ -2338,7 +2338,7 @@ void __init tcp_init(void) (tcp_bhash_size * sizeof(struct tcp_bind_hashbucket)); order++) ; - if (order > 4) { + if (order >= 4) { sysctl_local_port_range[0] = 32768; sysctl_local_port_range[1] = 61000; sysctl_tcp_max_tw_buckets = 180000; diff --git a/net/ipv6/addrconf.c b/net/ipv6/addrconf.c index 7744a25..2720899 100644 --- a/net/ipv6/addrconf.c +++ b/net/ipv6/addrconf.c @@ -372,6 +372,7 @@ static struct inet6_dev * ipv6_add_dev(struct net_device *dev) ndev->regen_timer.data = (unsigned long) ndev; if ((dev->flags&IFF_LOOPBACK) || dev->type == ARPHRD_TUNNEL || + dev->type == ARPHRD_NONE || dev->type == ARPHRD_SIT) { printk(KERN_INFO "Disabled Privacy Extensions on device %p(%s)\n", diff --git a/net/ipv6/icmp.c b/net/ipv6/icmp.c index 8e0f569..ff3ec98 100644 --- a/net/ipv6/icmp.c +++ b/net/ipv6/icmp.c @@ -277,8 +277,8 @@ void icmpv6_send(struct sk_buff *skb, int type, int code, __u32 info, { struct inet6_dev *idev = NULL; struct ipv6hdr *hdr = skb->nh.ipv6h; - struct sock *sk = icmpv6_socket->sk; - struct ipv6_pinfo *np = inet6_sk(sk); + struct sock *sk; + struct ipv6_pinfo *np; struct in6_addr *saddr = NULL; struct dst_entry *dst; struct icmp6hdr tmp_hdr; @@ -358,6 +358,9 @@ void icmpv6_send(struct sk_buff *skb, int type, int code, __u32 info, if (icmpv6_xmit_lock()) return; + sk = icmpv6_socket->sk; + np = inet6_sk(sk); + if (!icmpv6_xrlim_allow(sk, type, &fl)) goto out; @@ -423,9 +426,9 @@ out: static void icmpv6_echo_reply(struct sk_buff *skb) { - struct sock *sk = icmpv6_socket->sk; + struct sock *sk; struct inet6_dev *idev; - struct ipv6_pinfo *np = inet6_sk(sk); + struct ipv6_pinfo *np; struct in6_addr *saddr = NULL; struct icmp6hdr *icmph = (struct icmp6hdr *) skb->h.raw; struct icmp6hdr tmp_hdr; @@ -454,6 +457,9 @@ static void icmpv6_echo_reply(struct sk_buff *skb) if (icmpv6_xmit_lock()) return; + sk = icmpv6_socket->sk; + np = inet6_sk(sk); + if (!fl.oif && ipv6_addr_is_multicast(&fl.fl6_dst)) fl.oif = np->mcast_oif; diff --git a/net/ipv6/ip6_tunnel.c b/net/ipv6/ip6_tunnel.c index 3b1c9fa..ba3b0c2 100644 --- a/net/ipv6/ip6_tunnel.c +++ b/net/ipv6/ip6_tunnel.c @@ -882,6 +882,7 @@ ip6ip6_tnl_change(struct ip6_tnl *t, struct ip6_tnl_parm *p) t->parms.hop_limit = p->hop_limit; t->parms.encap_limit = p->encap_limit; t->parms.flowinfo = p->flowinfo; + t->parms.link = p->link; ip6ip6_tnl_link_config(t); return 0; } diff --git a/net/sched/Kconfig b/net/sched/Kconfig index b094118..b22c9be 100644 --- a/net/sched/Kconfig +++ b/net/sched/Kconfig @@ -405,7 +405,7 @@ config NET_EMATCH_STACK ---help--- Size of the local stack variable used while evaluating the tree of ematches. Limits the depth of the tree, i.e. the number of - encapsulated precedences. Every level requires 4 bytes of addtional + encapsulated precedences. Every level requires 4 bytes of additional stack space. config NET_EMATCH_CMP diff --git a/net/sched/act_api.c b/net/sched/act_api.c index cafcb08..914c85f 100644 --- a/net/sched/act_api.c +++ b/net/sched/act_api.c @@ -881,7 +881,7 @@ static int __init tc_action_init(void) link_p[RTM_GETACTION-RTM_BASE].dumpit = tc_dump_action; } - printk("TC classifier action (bugs to netdev@oss.sgi.com cc " + printk("TC classifier action (bugs to netdev@vger.kernel.org cc " "hadi@cyberus.ca)\n"); return 0; } diff --git a/net/sched/cls_basic.c b/net/sched/cls_basic.c index 0d2d441..dfb300b 100644 --- a/net/sched/cls_basic.c +++ b/net/sched/cls_basic.c @@ -261,6 +261,9 @@ static int basic_dump(struct tcf_proto *tp, unsigned long fh, rta = (struct rtattr *) b; RTA_PUT(skb, TCA_OPTIONS, 0, NULL); + if (f->res.classid) + RTA_PUT(skb, TCA_BASIC_CLASSID, sizeof(u32), &f->res.classid); + if (tcf_exts_dump(skb, &f->exts, &basic_ext_map) < 0 || tcf_em_tree_dump(skb, &f->ematches, TCA_BASIC_EMATCHES) < 0) goto rtattr_failure; diff --git a/net/sched/em_meta.c b/net/sched/em_meta.c index f1eeaf6..48bb23c 100644 --- a/net/sched/em_meta.c +++ b/net/sched/em_meta.c @@ -32,7 +32,7 @@ * +-----------+ +-----------+ * | | * ---> meta_ops[INT][INDEV](...) | - * | | + * | | * ----------- | * V V * +-----------+ +-----------+ @@ -70,6 +70,7 @@ #include <net/dst.h> #include <net/route.h> #include <net/pkt_cls.h> +#include <net/sock.h> struct meta_obj { @@ -284,6 +285,214 @@ META_COLLECTOR(int_rtiif) } /************************************************************************** + * Socket Attributes + **************************************************************************/ + +#define SKIP_NONLOCAL(skb) \ + if (unlikely(skb->sk == NULL)) { \ + *err = -1; \ + return; \ + } + +META_COLLECTOR(int_sk_family) +{ + SKIP_NONLOCAL(skb); + dst->value = skb->sk->sk_family; +} + +META_COLLECTOR(int_sk_state) +{ + SKIP_NONLOCAL(skb); + dst->value = skb->sk->sk_state; +} + +META_COLLECTOR(int_sk_reuse) +{ + SKIP_NONLOCAL(skb); + dst->value = skb->sk->sk_reuse; +} + +META_COLLECTOR(int_sk_bound_if) +{ + SKIP_NONLOCAL(skb); + /* No error if bound_dev_if is 0, legal userspace check */ + dst->value = skb->sk->sk_bound_dev_if; +} + +META_COLLECTOR(var_sk_bound_if) +{ + SKIP_NONLOCAL(skb); + + if (skb->sk->sk_bound_dev_if == 0) { + dst->value = (unsigned long) "any"; + dst->len = 3; + } else { + struct net_device *dev; + + dev = dev_get_by_index(skb->sk->sk_bound_dev_if); + *err = var_dev(dev, dst); + if (dev) + dev_put(dev); + } +} + +META_COLLECTOR(int_sk_refcnt) +{ + SKIP_NONLOCAL(skb); + dst->value = atomic_read(&skb->sk->sk_refcnt); +} + +META_COLLECTOR(int_sk_rcvbuf) +{ + SKIP_NONLOCAL(skb); + dst->value = skb->sk->sk_rcvbuf; +} + +META_COLLECTOR(int_sk_shutdown) +{ + SKIP_NONLOCAL(skb); + dst->value = skb->sk->sk_shutdown; +} + +META_COLLECTOR(int_sk_proto) +{ + SKIP_NONLOCAL(skb); + dst->value = skb->sk->sk_protocol; +} + +META_COLLECTOR(int_sk_type) +{ + SKIP_NONLOCAL(skb); + dst->value = skb->sk->sk_type; +} + +META_COLLECTOR(int_sk_rmem_alloc) +{ + SKIP_NONLOCAL(skb); + dst->value = atomic_read(&skb->sk->sk_rmem_alloc); +} + +META_COLLECTOR(int_sk_wmem_alloc) +{ + SKIP_NONLOCAL(skb); + dst->value = atomic_read(&skb->sk->sk_wmem_alloc); +} + +META_COLLECTOR(int_sk_omem_alloc) +{ + SKIP_NONLOCAL(skb); + dst->value = atomic_read(&skb->sk->sk_omem_alloc); +} + +META_COLLECTOR(int_sk_rcv_qlen) +{ + SKIP_NONLOCAL(skb); + dst->value = skb->sk->sk_receive_queue.qlen; +} + +META_COLLECTOR(int_sk_snd_qlen) +{ + SKIP_NONLOCAL(skb); + dst->value = skb->sk->sk_write_queue.qlen; +} + +META_COLLECTOR(int_sk_wmem_queued) +{ + SKIP_NONLOCAL(skb); + dst->value = skb->sk->sk_wmem_queued; +} + +META_COLLECTOR(int_sk_fwd_alloc) +{ + SKIP_NONLOCAL(skb); + dst->value = skb->sk->sk_forward_alloc; +} + +META_COLLECTOR(int_sk_sndbuf) +{ + SKIP_NONLOCAL(skb); + dst->value = skb->sk->sk_sndbuf; +} + +META_COLLECTOR(int_sk_alloc) +{ + SKIP_NONLOCAL(skb); + dst->value = skb->sk->sk_allocation; +} + +META_COLLECTOR(int_sk_route_caps) +{ + SKIP_NONLOCAL(skb); + dst->value = skb->sk->sk_route_caps; +} + +META_COLLECTOR(int_sk_hashent) +{ + SKIP_NONLOCAL(skb); + dst->value = skb->sk->sk_hashent; +} + +META_COLLECTOR(int_sk_lingertime) +{ + SKIP_NONLOCAL(skb); + dst->value = skb->sk->sk_lingertime / HZ; +} + +META_COLLECTOR(int_sk_err_qlen) +{ + SKIP_NONLOCAL(skb); + dst->value = skb->sk->sk_error_queue.qlen; +} + +META_COLLECTOR(int_sk_ack_bl) +{ + SKIP_NONLOCAL(skb); + dst->value = skb->sk->sk_ack_backlog; +} + +META_COLLECTOR(int_sk_max_ack_bl) +{ + SKIP_NONLOCAL(skb); + dst->value = skb->sk->sk_max_ack_backlog; +} + +META_COLLECTOR(int_sk_prio) +{ + SKIP_NONLOCAL(skb); + dst->value = skb->sk->sk_priority; +} + +META_COLLECTOR(int_sk_rcvlowat) +{ + SKIP_NONLOCAL(skb); + dst->value = skb->sk->sk_rcvlowat; +} + +META_COLLECTOR(int_sk_rcvtimeo) +{ + SKIP_NONLOCAL(skb); + dst->value = skb->sk->sk_rcvtimeo / HZ; +} + +META_COLLECTOR(int_sk_sndtimeo) +{ + SKIP_NONLOCAL(skb); + dst->value = skb->sk->sk_sndtimeo / HZ; +} + +META_COLLECTOR(int_sk_sendmsg_off) +{ + SKIP_NONLOCAL(skb); + dst->value = skb->sk->sk_sndmsg_off; +} + +META_COLLECTOR(int_sk_write_pend) +{ + SKIP_NONLOCAL(skb); + dst->value = skb->sk->sk_write_pending; +} + +/************************************************************************** * Meta value collectors assignment table **************************************************************************/ @@ -293,41 +502,75 @@ struct meta_ops struct meta_value *, struct meta_obj *, int *); }; +#define META_ID(name) TCF_META_ID_##name +#define META_FUNC(name) { .get = meta_##name } + /* Meta value operations table listing all meta value collectors and * assigns them to a type and meta id. */ static struct meta_ops __meta_ops[TCF_META_TYPE_MAX+1][TCF_META_ID_MAX+1] = { [TCF_META_TYPE_VAR] = { - [TCF_META_ID_DEV] = { .get = meta_var_dev }, - [TCF_META_ID_INDEV] = { .get = meta_var_indev }, - [TCF_META_ID_REALDEV] = { .get = meta_var_realdev } + [META_ID(DEV)] = META_FUNC(var_dev), + [META_ID(INDEV)] = META_FUNC(var_indev), + [META_ID(REALDEV)] = META_FUNC(var_realdev), + [META_ID(SK_BOUND_IF)] = META_FUNC(var_sk_bound_if), }, [TCF_META_TYPE_INT] = { - [TCF_META_ID_RANDOM] = { .get = meta_int_random }, - [TCF_META_ID_LOADAVG_0] = { .get = meta_int_loadavg_0 }, - [TCF_META_ID_LOADAVG_1] = { .get = meta_int_loadavg_1 }, - [TCF_META_ID_LOADAVG_2] = { .get = meta_int_loadavg_2 }, - [TCF_META_ID_DEV] = { .get = meta_int_dev }, - [TCF_META_ID_INDEV] = { .get = meta_int_indev }, - [TCF_META_ID_REALDEV] = { .get = meta_int_realdev }, - [TCF_META_ID_PRIORITY] = { .get = meta_int_priority }, - [TCF_META_ID_PROTOCOL] = { .get = meta_int_protocol }, - [TCF_META_ID_SECURITY] = { .get = meta_int_security }, - [TCF_META_ID_PKTTYPE] = { .get = meta_int_pkttype }, - [TCF_META_ID_PKTLEN] = { .get = meta_int_pktlen }, - [TCF_META_ID_DATALEN] = { .get = meta_int_datalen }, - [TCF_META_ID_MACLEN] = { .get = meta_int_maclen }, + [META_ID(RANDOM)] = META_FUNC(int_random), + [META_ID(LOADAVG_0)] = META_FUNC(int_loadavg_0), + [META_ID(LOADAVG_1)] = META_FUNC(int_loadavg_1), + [META_ID(LOADAVG_2)] = META_FUNC(int_loadavg_2), + [META_ID(DEV)] = META_FUNC(int_dev), + [META_ID(INDEV)] = META_FUNC(int_indev), + [META_ID(REALDEV)] = META_FUNC(int_realdev), + [META_ID(PRIORITY)] = META_FUNC(int_priority), + [META_ID(PROTOCOL)] = META_FUNC(int_protocol), + [META_ID(SECURITY)] = META_FUNC(int_security), + [META_ID(PKTTYPE)] = META_FUNC(int_pkttype), + [META_ID(PKTLEN)] = META_FUNC(int_pktlen), + [META_ID(DATALEN)] = META_FUNC(int_datalen), + [META_ID(MACLEN)] = META_FUNC(int_maclen), #ifdef CONFIG_NETFILTER - [TCF_META_ID_NFMARK] = { .get = meta_int_nfmark }, + [META_ID(NFMARK)] = META_FUNC(int_nfmark), #endif - [TCF_META_ID_TCINDEX] = { .get = meta_int_tcindex }, + [META_ID(TCINDEX)] = META_FUNC(int_tcindex), #ifdef CONFIG_NET_CLS_ACT - [TCF_META_ID_TCVERDICT] = { .get = meta_int_tcverd }, - [TCF_META_ID_TCCLASSID] = { .get = meta_int_tcclassid }, + [META_ID(TCVERDICT)] = META_FUNC(int_tcverd), + [META_ID(TCCLASSID)] = META_FUNC(int_tcclassid), #endif #ifdef CONFIG_NET_CLS_ROUTE - [TCF_META_ID_RTCLASSID] = { .get = meta_int_rtclassid }, + [META_ID(RTCLASSID)] = META_FUNC(int_rtclassid), #endif - [TCF_META_ID_RTIIF] = { .get = meta_int_rtiif } + [META_ID(RTIIF)] = META_FUNC(int_rtiif), + [META_ID(SK_FAMILY)] = META_FUNC(int_sk_family), + [META_ID(SK_STATE)] = META_FUNC(int_sk_state), + [META_ID(SK_REUSE)] = META_FUNC(int_sk_reuse), + [META_ID(SK_BOUND_IF)] = META_FUNC(int_sk_bound_if), + [META_ID(SK_REFCNT)] = META_FUNC(int_sk_refcnt), + [META_ID(SK_RCVBUF)] = META_FUNC(int_sk_rcvbuf), + [META_ID(SK_SNDBUF)] = META_FUNC(int_sk_sndbuf), + [META_ID(SK_SHUTDOWN)] = META_FUNC(int_sk_shutdown), + [META_ID(SK_PROTO)] = META_FUNC(int_sk_proto), + [META_ID(SK_TYPE)] = META_FUNC(int_sk_type), + [META_ID(SK_RMEM_ALLOC)] = META_FUNC(int_sk_rmem_alloc), + [META_ID(SK_WMEM_ALLOC)] = META_FUNC(int_sk_wmem_alloc), + [META_ID(SK_OMEM_ALLOC)] = META_FUNC(int_sk_omem_alloc), + [META_ID(SK_WMEM_QUEUED)] = META_FUNC(int_sk_wmem_queued), + [META_ID(SK_RCV_QLEN)] = META_FUNC(int_sk_rcv_qlen), + [META_ID(SK_SND_QLEN)] = META_FUNC(int_sk_snd_qlen), + [META_ID(SK_ERR_QLEN)] = META_FUNC(int_sk_err_qlen), + [META_ID(SK_FORWARD_ALLOCS)] = META_FUNC(int_sk_fwd_alloc), + [META_ID(SK_ALLOCS)] = META_FUNC(int_sk_alloc), + [META_ID(SK_ROUTE_CAPS)] = META_FUNC(int_sk_route_caps), + [META_ID(SK_HASHENT)] = META_FUNC(int_sk_hashent), + [META_ID(SK_LINGERTIME)] = META_FUNC(int_sk_lingertime), + [META_ID(SK_ACK_BACKLOG)] = META_FUNC(int_sk_ack_bl), + [META_ID(SK_MAX_ACK_BACKLOG)] = META_FUNC(int_sk_max_ack_bl), + [META_ID(SK_PRIO)] = META_FUNC(int_sk_prio), + [META_ID(SK_RCVLOWAT)] = META_FUNC(int_sk_rcvlowat), + [META_ID(SK_RCVTIMEO)] = META_FUNC(int_sk_rcvtimeo), + [META_ID(SK_SNDTIMEO)] = META_FUNC(int_sk_sndtimeo), + [META_ID(SK_SENDMSG_OFF)] = META_FUNC(int_sk_sendmsg_off), + [META_ID(SK_WRITE_PENDING)] = META_FUNC(int_sk_write_pend), } }; @@ -396,9 +639,9 @@ static int meta_int_compare(struct meta_obj *a, struct meta_obj *b) /* Let gcc optimize it, the unlikely is not really based on * some numbers but jump free code for mismatches seems * more logical. */ - if (unlikely(a == b)) + if (unlikely(a->value == b->value)) return 0; - else if (a < b) + else if (a->value < b->value) return -1; else return 1; diff --git a/net/sctp/input.c b/net/sctp/input.c index b719a77..fffc880 100644 --- a/net/sctp/input.c +++ b/net/sctp/input.c @@ -178,6 +178,37 @@ int sctp_rcv(struct sk_buff *skb) asoc = __sctp_rcv_lookup(skb, &src, &dest, &transport); + if (!asoc) + ep = __sctp_rcv_lookup_endpoint(&dest); + + /* Retrieve the common input handling substructure. */ + rcvr = asoc ? &asoc->base : &ep->base; + sk = rcvr->sk; + + /* + * If a frame arrives on an interface and the receiving socket is + * bound to another interface, via SO_BINDTODEVICE, treat it as OOTB + */ + if (sk->sk_bound_dev_if && (sk->sk_bound_dev_if != af->skb_iif(skb))) + { + sock_put(sk); + if (asoc) { + sctp_association_put(asoc); + asoc = NULL; + } else { + sctp_endpoint_put(ep); + ep = NULL; + } + sk = sctp_get_ctl_sock(); + ep = sctp_sk(sk)->ep; + sctp_endpoint_hold(ep); + sock_hold(sk); + rcvr = &ep->base; + } + + if (atomic_read(&sk->sk_rmem_alloc) >= sk->sk_rcvbuf) + goto discard_release; + /* * RFC 2960, 8.4 - Handle "Out of the blue" Packets. * An SCTP packet is called an "out of the blue" (OOTB) @@ -187,22 +218,12 @@ int sctp_rcv(struct sk_buff *skb) * packet belongs. */ if (!asoc) { - ep = __sctp_rcv_lookup_endpoint(&dest); if (sctp_rcv_ootb(skb)) { SCTP_INC_STATS_BH(SCTP_MIB_OUTOFBLUES); goto discard_release; } } - /* Retrieve the common input handling substructure. */ - rcvr = asoc ? &asoc->base : &ep->base; - sk = rcvr->sk; - - if ((sk) && (atomic_read(&sk->sk_rmem_alloc) >= sk->sk_rcvbuf)) { - goto discard_release; - } - - /* SCTP seems to always need a timestamp right now (FIXME) */ if (skb->stamp.tv_sec == 0) { do_gettimeofday(&skb->stamp); @@ -265,13 +286,11 @@ discard_it: discard_release: /* Release any structures we may be holding. */ - if (asoc) { - sock_put(asoc->base.sk); + sock_put(sk); + if (asoc) sctp_association_put(asoc); - } else { - sock_put(ep->base.sk); + else sctp_endpoint_put(ep); - } goto discard_it; } diff --git a/net/sctp/ipv6.c b/net/sctp/ipv6.c index c9d9ea0..c7e42d1 100644 --- a/net/sctp/ipv6.c +++ b/net/sctp/ipv6.c @@ -812,26 +812,23 @@ static int sctp_inet6_bind_verify(struct sctp_sock *opt, union sctp_addr *addr) if (addr->sa.sa_family != AF_INET6) af = sctp_get_af_specific(addr->sa.sa_family); else { - struct sock *sk; int type = ipv6_addr_type(&addr->v6.sin6_addr); - sk = sctp_opt2sk(opt); + struct net_device *dev; + if (type & IPV6_ADDR_LINKLOCAL) { - /* Note: Behavior similar to af_inet6.c: - * 1) Overrides previous bound_dev_if - * 2) Destructive even if bind isn't successful. - */ - - if (addr->v6.sin6_scope_id) - sk->sk_bound_dev_if = addr->v6.sin6_scope_id; - if (!sk->sk_bound_dev_if) + if (!addr->v6.sin6_scope_id) + return 0; + dev = dev_get_by_index(addr->v6.sin6_scope_id); + if (!dev) return 0; + dev_put(dev); } af = opt->pf->af; } return af->available(addr, opt); } -/* Verify that the provided sockaddr looks bindable. Common verification, +/* Verify that the provided sockaddr looks sendable. Common verification, * has already been taken care of. */ static int sctp_inet6_send_verify(struct sctp_sock *opt, union sctp_addr *addr) @@ -842,19 +839,16 @@ static int sctp_inet6_send_verify(struct sctp_sock *opt, union sctp_addr *addr) if (addr->sa.sa_family != AF_INET6) af = sctp_get_af_specific(addr->sa.sa_family); else { - struct sock *sk; int type = ipv6_addr_type(&addr->v6.sin6_addr); - sk = sctp_opt2sk(opt); + struct net_device *dev; + if (type & IPV6_ADDR_LINKLOCAL) { - /* Note: Behavior similar to af_inet6.c: - * 1) Overrides previous bound_dev_if - * 2) Destructive even if bind isn't successful. - */ - - if (addr->v6.sin6_scope_id) - sk->sk_bound_dev_if = addr->v6.sin6_scope_id; - if (!sk->sk_bound_dev_if) + if (!addr->v6.sin6_scope_id) + return 0; + dev = dev_get_by_index(addr->v6.sin6_scope_id); + if (!dev) return 0; + dev_put(dev); } af = opt->pf->af; } diff --git a/net/sctp/proc.c b/net/sctp/proc.c index e42fd8c..98d49ec 100644 --- a/net/sctp/proc.c +++ b/net/sctp/proc.c @@ -132,14 +132,25 @@ void sctp_snmp_proc_exit(void) static void sctp_seq_dump_local_addrs(struct seq_file *seq, struct sctp_ep_common *epb) { struct list_head *pos; + struct sctp_association *asoc; struct sctp_sockaddr_entry *laddr; - union sctp_addr *addr; + struct sctp_transport *peer; + union sctp_addr *addr, *primary = NULL; struct sctp_af *af; + if (epb->type == SCTP_EP_TYPE_ASSOCIATION) { + asoc = sctp_assoc(epb); + peer = asoc->peer.primary_path; + primary = &peer->saddr; + } + list_for_each(pos, &epb->bind_addr.address_list) { laddr = list_entry(pos, struct sctp_sockaddr_entry, list); addr = (union sctp_addr *)&laddr->a; af = sctp_get_af_specific(addr->sa.sa_family); + if (primary && af->cmp_addr(addr, primary)) { + seq_printf(seq, "*"); + } af->seq_dump_addr(seq, addr); } } @@ -149,17 +160,54 @@ static void sctp_seq_dump_remote_addrs(struct seq_file *seq, struct sctp_associa { struct list_head *pos; struct sctp_transport *transport; - union sctp_addr *addr; + union sctp_addr *addr, *primary; struct sctp_af *af; + primary = &(assoc->peer.primary_addr); list_for_each(pos, &assoc->peer.transport_addr_list) { transport = list_entry(pos, struct sctp_transport, transports); addr = (union sctp_addr *)&transport->ipaddr; af = sctp_get_af_specific(addr->sa.sa_family); + if (af->cmp_addr(addr, primary)) { + seq_printf(seq, "*"); + } af->seq_dump_addr(seq, addr); } } +static void * sctp_eps_seq_start(struct seq_file *seq, loff_t *pos) +{ + if (*pos > sctp_ep_hashsize) + return NULL; + + if (*pos < 0) + *pos = 0; + + if (*pos == 0) + seq_printf(seq, " ENDPT SOCK STY SST HBKT LPORT UID INODE LADDRS\n"); + + ++*pos; + + return (void *)pos; +} + +static void sctp_eps_seq_stop(struct seq_file *seq, void *v) +{ + return; +} + + +static void * sctp_eps_seq_next(struct seq_file *seq, void *v, loff_t *pos) +{ + if (*pos > sctp_ep_hashsize) + return NULL; + + ++*pos; + + return pos; +} + + /* Display sctp endpoints (/proc/net/sctp/eps). */ static int sctp_eps_seq_show(struct seq_file *seq, void *v) { @@ -167,38 +215,50 @@ static int sctp_eps_seq_show(struct seq_file *seq, void *v) struct sctp_ep_common *epb; struct sctp_endpoint *ep; struct sock *sk; - int hash; - - seq_printf(seq, " ENDPT SOCK STY SST HBKT LPORT LADDRS\n"); - for (hash = 0; hash < sctp_ep_hashsize; hash++) { - head = &sctp_ep_hashtable[hash]; - read_lock(&head->lock); - for (epb = head->chain; epb; epb = epb->next) { - ep = sctp_ep(epb); - sk = epb->sk; - seq_printf(seq, "%8p %8p %-3d %-3d %-4d %-5d ", ep, sk, - sctp_sk(sk)->type, sk->sk_state, hash, - epb->bind_addr.port); - sctp_seq_dump_local_addrs(seq, epb); - seq_printf(seq, "\n"); - } - read_unlock(&head->lock); + int hash = *(int *)v; + + if (hash > sctp_ep_hashsize) + return -ENOMEM; + + head = &sctp_ep_hashtable[hash-1]; + sctp_local_bh_disable(); + read_lock(&head->lock); + for (epb = head->chain; epb; epb = epb->next) { + ep = sctp_ep(epb); + sk = epb->sk; + seq_printf(seq, "%8p %8p %-3d %-3d %-4d %-5d %5d %5lu ", ep, sk, + sctp_sk(sk)->type, sk->sk_state, hash-1, + epb->bind_addr.port, + sock_i_uid(sk), sock_i_ino(sk)); + + sctp_seq_dump_local_addrs(seq, epb); + seq_printf(seq, "\n"); } + read_unlock(&head->lock); + sctp_local_bh_enable(); return 0; } +static struct seq_operations sctp_eps_ops = { + .start = sctp_eps_seq_start, + .next = sctp_eps_seq_next, + .stop = sctp_eps_seq_stop, + .show = sctp_eps_seq_show, +}; + + /* Initialize the seq file operations for 'eps' object. */ static int sctp_eps_seq_open(struct inode *inode, struct file *file) { - return single_open(file, sctp_eps_seq_show, NULL); + return seq_open(file, &sctp_eps_ops); } static struct file_operations sctp_eps_seq_fops = { .open = sctp_eps_seq_open, .read = seq_read, .llseek = seq_lseek, - .release = single_release, + .release = seq_release, }; /* Set up the proc fs entry for 'eps' object. */ @@ -221,6 +281,40 @@ void sctp_eps_proc_exit(void) remove_proc_entry("eps", proc_net_sctp); } + +static void * sctp_assocs_seq_start(struct seq_file *seq, loff_t *pos) +{ + if (*pos > sctp_assoc_hashsize) + return NULL; + + if (*pos < 0) + *pos = 0; + + if (*pos == 0) + seq_printf(seq, " ASSOC SOCK STY SST ST HBKT ASSOC-ID TX_QUEUE RX_QUEUE UID INODE LPORT " + "RPORT LADDRS <-> RADDRS\n"); + + ++*pos; + + return (void *)pos; +} + +static void sctp_assocs_seq_stop(struct seq_file *seq, void *v) +{ + return; +} + + +static void * sctp_assocs_seq_next(struct seq_file *seq, void *v, loff_t *pos) +{ + if (*pos > sctp_assoc_hashsize) + return NULL; + + ++*pos; + + return pos; +} + /* Display sctp associations (/proc/net/sctp/assocs). */ static int sctp_assocs_seq_show(struct seq_file *seq, void *v) { @@ -228,43 +322,57 @@ static int sctp_assocs_seq_show(struct seq_file *seq, void *v) struct sctp_ep_common *epb; struct sctp_association *assoc; struct sock *sk; - int hash; - - seq_printf(seq, " ASSOC SOCK STY SST ST HBKT LPORT RPORT " - "LADDRS <-> RADDRS\n"); - for (hash = 0; hash < sctp_assoc_hashsize; hash++) { - head = &sctp_assoc_hashtable[hash]; - read_lock(&head->lock); - for (epb = head->chain; epb; epb = epb->next) { - assoc = sctp_assoc(epb); - sk = epb->sk; - seq_printf(seq, - "%8p %8p %-3d %-3d %-2d %-4d %-5d %-5d ", - assoc, sk, sctp_sk(sk)->type, sk->sk_state, - assoc->state, hash, epb->bind_addr.port, - assoc->peer.port); - sctp_seq_dump_local_addrs(seq, epb); - seq_printf(seq, "<-> "); - sctp_seq_dump_remote_addrs(seq, assoc); - seq_printf(seq, "\n"); - } - read_unlock(&head->lock); + int hash = *(int *)v; + + if (hash > sctp_assoc_hashsize) + return -ENOMEM; + + head = &sctp_assoc_hashtable[hash-1]; + sctp_local_bh_disable(); + read_lock(&head->lock); + for (epb = head->chain; epb; epb = epb->next) { + assoc = sctp_assoc(epb); + sk = epb->sk; + seq_printf(seq, + "%8p %8p %-3d %-3d %-2d %-4d %4d %8d %8d %7d %5lu %-5d %5d ", + assoc, sk, sctp_sk(sk)->type, sk->sk_state, + assoc->state, hash-1, assoc->assoc_id, + (sk->sk_rcvbuf - assoc->rwnd), + assoc->sndbuf_used, + sock_i_uid(sk), sock_i_ino(sk), + epb->bind_addr.port, + assoc->peer.port); + + seq_printf(seq, " "); + sctp_seq_dump_local_addrs(seq, epb); + seq_printf(seq, "<-> "); + sctp_seq_dump_remote_addrs(seq, assoc); + seq_printf(seq, "\n"); } + read_unlock(&head->lock); + sctp_local_bh_enable(); return 0; } +static struct seq_operations sctp_assoc_ops = { + .start = sctp_assocs_seq_start, + .next = sctp_assocs_seq_next, + .stop = sctp_assocs_seq_stop, + .show = sctp_assocs_seq_show, +}; + /* Initialize the seq file operations for 'assocs' object. */ static int sctp_assocs_seq_open(struct inode *inode, struct file *file) { - return single_open(file, sctp_assocs_seq_show, NULL); + return seq_open(file, &sctp_assoc_ops); } static struct file_operations sctp_assocs_seq_fops = { .open = sctp_assocs_seq_open, .read = seq_read, .llseek = seq_lseek, - .release = single_release, + .release = seq_release, }; /* Set up the proc fs entry for 'assocs' object. */ diff --git a/net/sctp/protocol.c b/net/sctp/protocol.c index 2e1f9c3..5135e1a 100644 --- a/net/sctp/protocol.c +++ b/net/sctp/protocol.c @@ -378,10 +378,13 @@ static int sctp_v4_available(union sctp_addr *addr, struct sctp_sock *sp) { int ret = inet_addr_type(addr->v4.sin_addr.s_addr); - /* FIXME: ip_nonlocal_bind sysctl support. */ - if (addr->v4.sin_addr.s_addr != INADDR_ANY && ret != RTN_LOCAL) + if (addr->v4.sin_addr.s_addr != INADDR_ANY && + ret != RTN_LOCAL && + !sp->inet.freebind && + !sysctl_ip_nonlocal_bind) return 0; + return 1; } diff --git a/net/sctp/socket.c b/net/sctp/socket.c index 0b338ec..2a3c0e0 100644 --- a/net/sctp/socket.c +++ b/net/sctp/socket.c @@ -4686,6 +4686,7 @@ static void sctp_sock_migrate(struct sock *oldsk, struct sock *newsk, struct sctp_endpoint *newep = newsp->ep; struct sk_buff *skb, *tmp; struct sctp_ulpevent *event; + int flags = 0; /* Migrate socket buffer sizes and all the socket level options to the * new socket. @@ -4707,6 +4708,17 @@ static void sctp_sock_migrate(struct sock *oldsk, struct sock *newsk, sctp_sk(newsk)->bind_hash = pp; inet_sk(newsk)->num = inet_sk(oldsk)->num; + /* Copy the bind_addr list from the original endpoint to the new + * endpoint so that we can handle restarts properly + */ + if (assoc->peer.ipv4_address) + flags |= SCTP_ADDR4_PEERSUPP; + if (assoc->peer.ipv6_address) + flags |= SCTP_ADDR6_PEERSUPP; + sctp_bind_addr_copy(&newsp->ep->base.bind_addr, + &oldsp->ep->base.bind_addr, + SCTP_SCOPE_GLOBAL, GFP_KERNEL, flags); + /* Move any messages in the old socket's receive queue that are for the * peeled off association to the new socket's receive queue. */ |