diff options
Diffstat (limited to 'net')
52 files changed, 1611 insertions, 814 deletions
diff --git a/net/core/dev.c b/net/core/dev.c index 32611c8f1219..3daee30a7c82 100644 --- a/net/core/dev.c +++ b/net/core/dev.c @@ -1470,7 +1470,7 @@ static inline void net_timestamp(struct sk_buff *skb) * * return values: * NET_RX_SUCCESS (no congestion) - * NET_RX_DROP (packet was dropped) + * NET_RX_DROP (packet was dropped, but freed) * * dev_forward_skb can be used for injecting an skb from the * start_xmit function of one device into the receive queue @@ -1484,12 +1484,11 @@ int dev_forward_skb(struct net_device *dev, struct sk_buff *skb) { skb_orphan(skb); - if (!(dev->flags & IFF_UP)) - return NET_RX_DROP; - - if (skb->len > (dev->mtu + dev->hard_header_len)) + if (!(dev->flags & IFF_UP) || + (skb->len > (dev->mtu + dev->hard_header_len))) { + kfree_skb(skb); return NET_RX_DROP; - + } skb_set_dev(skb, dev); skb->tstamp.tv64 = 0; skb->pkt_type = PACKET_HOST; diff --git a/net/ipv4/arp.c b/net/ipv4/arp.c index 6e747065c202..80769f1f9fab 100644 --- a/net/ipv4/arp.c +++ b/net/ipv4/arp.c @@ -661,13 +661,13 @@ struct sk_buff *arp_create(int type, int ptype, __be32 dest_ip, #endif #endif -#ifdef CONFIG_FDDI +#if defined(CONFIG_FDDI) || defined(CONFIG_FDDI_MODULE) case ARPHRD_FDDI: arp->ar_hrd = htons(ARPHRD_ETHER); arp->ar_pro = htons(ETH_P_IP); break; #endif -#ifdef CONFIG_TR +#if defined(CONFIG_TR) || defined(CONFIG_TR_MODULE) case ARPHRD_IEEE802_TR: arp->ar_hrd = htons(ARPHRD_IEEE802); arp->ar_pro = htons(ETH_P_IP); @@ -1051,7 +1051,7 @@ static int arp_req_set(struct net *net, struct arpreq *r, return -EINVAL; } switch (dev->type) { -#ifdef CONFIG_FDDI +#if defined(CONFIG_FDDI) || defined(CONFIG_FDDI_MODULE) case ARPHRD_FDDI: /* * According to RFC 1390, FDDI devices should accept ARP diff --git a/net/ipv4/ipmr.c b/net/ipv4/ipmr.c index f3f1c6b5c70c..7a7ee1cc3b5a 100644 --- a/net/ipv4/ipmr.c +++ b/net/ipv4/ipmr.c @@ -998,7 +998,8 @@ ipmr_cache_unresolved(struct mr_table *mrt, vifi_t vifi, struct sk_buff *skb) atomic_inc(&mrt->cache_resolve_queue_len); list_add(&c->list, &mrt->mfc_unres_queue); - mod_timer(&mrt->ipmr_expire_timer, c->mfc_un.unres.expires); + if (atomic_read(&mrt->cache_resolve_queue_len) == 1) + mod_timer(&mrt->ipmr_expire_timer, c->mfc_un.unres.expires); } /* diff --git a/net/ipv4/udp.c b/net/ipv4/udp.c index 4560b291180b..f3e00c5cd1ed 100644 --- a/net/ipv4/udp.c +++ b/net/ipv4/udp.c @@ -1536,6 +1536,9 @@ int __udp4_lib_rcv(struct sk_buff *skb, struct udp_table *udptable, uh = udp_hdr(skb); ulen = ntohs(uh->len); + saddr = ip_hdr(skb)->saddr; + daddr = ip_hdr(skb)->daddr; + if (ulen > skb->len) goto short_packet; @@ -1549,9 +1552,6 @@ int __udp4_lib_rcv(struct sk_buff *skb, struct udp_table *udptable, if (udp4_csum_init(skb, uh, proto)) goto csum_error; - saddr = ip_hdr(skb)->saddr; - daddr = ip_hdr(skb)->daddr; - if (rt->rt_flags & (RTCF_BROADCAST|RTCF_MULTICAST)) return __udp4_lib_mcast_deliver(net, skb, uh, saddr, daddr, udptable); diff --git a/net/ipv6/Kconfig b/net/ipv6/Kconfig index a578096152ab..36d7437ac054 100644 --- a/net/ipv6/Kconfig +++ b/net/ipv6/Kconfig @@ -229,6 +229,20 @@ config IPV6_MROUTE Experimental support for IPv6 multicast forwarding. If unsure, say N. +config IPV6_MROUTE_MULTIPLE_TABLES + bool "IPv6: multicast policy routing" + depends on IPV6_MROUTE + select FIB_RULES + help + Normally, a multicast router runs a userspace daemon and decides + what to do with a multicast packet based on the source and + destination addresses. If you say Y here, the multicast router + will also be able to take interfaces and packet marks into + account and run multiple instances of userspace daemons + simultaneously, each one handling a single table. + + If unsure, say N. + config IPV6_PIMSM_V2 bool "IPv6: PIM-SM version 2 support (EXPERIMENTAL)" depends on IPV6_MROUTE diff --git a/net/ipv6/af_inet6.c b/net/ipv6/af_inet6.c index d2df3144429b..e733942dafe1 100644 --- a/net/ipv6/af_inet6.c +++ b/net/ipv6/af_inet6.c @@ -200,7 +200,7 @@ lookup_protocol: inet_sk(sk)->pinet6 = np = inet6_sk_generic(sk); np->hop_limit = -1; - np->mcast_hops = -1; + np->mcast_hops = IPV6_DEFAULT_MCASTHOPS; np->mc_loop = 1; np->pmtudisc = IPV6_PMTUDISC_WANT; np->ipv6only = net->ipv6.sysctl.bindv6only; diff --git a/net/ipv6/datagram.c b/net/ipv6/datagram.c index 5959230bc6c1..712684687c9a 100644 --- a/net/ipv6/datagram.c +++ b/net/ipv6/datagram.c @@ -222,6 +222,8 @@ void ipv6_icmp_error(struct sock *sk, struct sk_buff *skb, int err, if (!skb) return; + skb->protocol = htons(ETH_P_IPV6); + serr = SKB_EXT_ERR(skb); serr->ee.ee_errno = err; serr->ee.ee_origin = SO_EE_ORIGIN_ICMP6; @@ -255,6 +257,8 @@ void ipv6_local_error(struct sock *sk, int err, struct flowi *fl, u32 info) if (!skb) return; + skb->protocol = htons(ETH_P_IPV6); + skb_put(skb, sizeof(struct ipv6hdr)); skb_reset_network_header(skb); iph = ipv6_hdr(skb); @@ -358,7 +362,7 @@ int ipv6_recv_error(struct sock *sk, struct msghdr *msg, int len) sin->sin6_flowinfo = 0; sin->sin6_port = serr->port; sin->sin6_scope_id = 0; - if (serr->ee.ee_origin == SO_EE_ORIGIN_ICMP6) { + if (skb->protocol == htons(ETH_P_IPV6)) { ipv6_addr_copy(&sin->sin6_addr, (struct in6_addr *)(nh + serr->addr_offset)); if (np->sndflow) @@ -380,7 +384,7 @@ int ipv6_recv_error(struct sock *sk, struct msghdr *msg, int len) sin->sin6_family = AF_INET6; sin->sin6_flowinfo = 0; sin->sin6_scope_id = 0; - if (serr->ee.ee_origin == SO_EE_ORIGIN_ICMP6) { + if (skb->protocol == htons(ETH_P_IPV6)) { ipv6_addr_copy(&sin->sin6_addr, &ipv6_hdr(skb)->saddr); if (np->rxopt.all) datagram_recv_ctl(sk, msg, skb); diff --git a/net/ipv6/ip6_output.c b/net/ipv6/ip6_output.c index 5173acaeb501..cd963f64e27c 100644 --- a/net/ipv6/ip6_output.c +++ b/net/ipv6/ip6_output.c @@ -108,7 +108,7 @@ static int ip6_finish_output2(struct sk_buff *skb) struct inet6_dev *idev = ip6_dst_idev(skb_dst(skb)); if (!(dev->flags & IFF_LOOPBACK) && sk_mc_loop(skb->sk) && - ((mroute6_socket(dev_net(dev)) && + ((mroute6_socket(dev_net(dev), skb) && !(IP6CB(skb)->flags & IP6SKB_FORWARDED)) || ipv6_chk_mcast_addr(dev, &ipv6_hdr(skb)->daddr, &ipv6_hdr(skb)->saddr))) { diff --git a/net/ipv6/ip6mr.c b/net/ipv6/ip6mr.c index e0b530ca394c..163850e22b11 100644 --- a/net/ipv6/ip6mr.c +++ b/net/ipv6/ip6mr.c @@ -42,6 +42,7 @@ #include <linux/if_arp.h> #include <net/checksum.h> #include <net/netlink.h> +#include <net/fib_rules.h> #include <net/ipv6.h> #include <net/ip6_route.h> @@ -51,6 +52,34 @@ #include <linux/netfilter_ipv6.h> #include <net/ip6_checksum.h> +struct mr6_table { + struct list_head list; +#ifdef CONFIG_NET_NS + struct net *net; +#endif + u32 id; + struct sock *mroute6_sk; + struct timer_list ipmr_expire_timer; + struct list_head mfc6_unres_queue; + struct list_head mfc6_cache_array[MFC6_LINES]; + struct mif_device vif6_table[MAXMIFS]; + int maxvif; + atomic_t cache_resolve_queue_len; + int mroute_do_assert; + int mroute_do_pim; +#ifdef CONFIG_IPV6_PIMSM_V2 + int mroute_reg_vif_num; +#endif +}; + +struct ip6mr_rule { + struct fib_rule common; +}; + +struct ip6mr_result { + struct mr6_table *mrt; +}; + /* Big lock, protecting vif table, mrt cache and mroute socket state. Note that the changes are semaphored via rtnl_lock. */ @@ -61,9 +90,7 @@ static DEFINE_RWLOCK(mrt_lock); * Multicast router control variables */ -#define MIF_EXISTS(_net, _idx) ((_net)->ipv6.vif6_table[_idx].dev != NULL) - -static struct mfc6_cache *mfc_unres_queue; /* Queue of unresolved entries */ +#define MIF_EXISTS(_mrt, _idx) ((_mrt)->vif6_table[_idx].dev != NULL) /* Special spinlock for queue of unresolved entries */ static DEFINE_SPINLOCK(mfc_unres_lock); @@ -78,20 +105,233 @@ static DEFINE_SPINLOCK(mfc_unres_lock); static struct kmem_cache *mrt_cachep __read_mostly; -static int ip6_mr_forward(struct sk_buff *skb, struct mfc6_cache *cache); -static int ip6mr_cache_report(struct net *net, struct sk_buff *pkt, +static struct mr6_table *ip6mr_new_table(struct net *net, u32 id); +static void ip6mr_free_table(struct mr6_table *mrt); + +static int ip6_mr_forward(struct net *net, struct mr6_table *mrt, + struct sk_buff *skb, struct mfc6_cache *cache); +static int ip6mr_cache_report(struct mr6_table *mrt, struct sk_buff *pkt, mifi_t mifi, int assert); -static int ip6mr_fill_mroute(struct sk_buff *skb, struct mfc6_cache *c, struct rtmsg *rtm); -static void mroute_clean_tables(struct net *net); +static int __ip6mr_fill_mroute(struct mr6_table *mrt, struct sk_buff *skb, + struct mfc6_cache *c, struct rtmsg *rtm); +static int ip6mr_rtm_dumproute(struct sk_buff *skb, + struct netlink_callback *cb); +static void mroute_clean_tables(struct mr6_table *mrt); +static void ipmr_expire_process(unsigned long arg); + +#ifdef CONFIG_IPV6_MROUTE_MULTIPLE_TABLES +#define ip6mr_for_each_table(mrt, met) \ + list_for_each_entry_rcu(mrt, &net->ipv6.mr6_tables, list) + +static struct mr6_table *ip6mr_get_table(struct net *net, u32 id) +{ + struct mr6_table *mrt; + + ip6mr_for_each_table(mrt, net) { + if (mrt->id == id) + return mrt; + } + return NULL; +} + +static int ip6mr_fib_lookup(struct net *net, struct flowi *flp, + struct mr6_table **mrt) +{ + struct ip6mr_result res; + struct fib_lookup_arg arg = { .result = &res, }; + int err; + + err = fib_rules_lookup(net->ipv6.mr6_rules_ops, flp, 0, &arg); + if (err < 0) + return err; + *mrt = res.mrt; + return 0; +} + +static int ip6mr_rule_action(struct fib_rule *rule, struct flowi *flp, + int flags, struct fib_lookup_arg *arg) +{ + struct ip6mr_result *res = arg->result; + struct mr6_table *mrt; + + switch (rule->action) { + case FR_ACT_TO_TBL: + break; + case FR_ACT_UNREACHABLE: + return -ENETUNREACH; + case FR_ACT_PROHIBIT: + return -EACCES; + case FR_ACT_BLACKHOLE: + default: + return -EINVAL; + } + + mrt = ip6mr_get_table(rule->fr_net, rule->table); + if (mrt == NULL) + return -EAGAIN; + res->mrt = mrt; + return 0; +} + +static int ip6mr_rule_match(struct fib_rule *rule, struct flowi *flp, int flags) +{ + return 1; +} + +static const struct nla_policy ip6mr_rule_policy[FRA_MAX + 1] = { + FRA_GENERIC_POLICY, +}; + +static int ip6mr_rule_configure(struct fib_rule *rule, struct sk_buff *skb, + struct fib_rule_hdr *frh, struct nlattr **tb) +{ + return 0; +} + +static int ip6mr_rule_compare(struct fib_rule *rule, struct fib_rule_hdr *frh, + struct nlattr **tb) +{ + return 1; +} + +static int ip6mr_rule_fill(struct fib_rule *rule, struct sk_buff *skb, + struct fib_rule_hdr *frh) +{ + frh->dst_len = 0; + frh->src_len = 0; + frh->tos = 0; + return 0; +} + +static const struct fib_rules_ops __net_initdata ip6mr_rules_ops_template = { + .family = RTNL_FAMILY_IP6MR, + .rule_size = sizeof(struct ip6mr_rule), + .addr_size = sizeof(struct in6_addr), + .action = ip6mr_rule_action, + .match = ip6mr_rule_match, + .configure = ip6mr_rule_configure, + .compare = ip6mr_rule_compare, + .default_pref = fib_default_rule_pref, + .fill = ip6mr_rule_fill, + .nlgroup = RTNLGRP_IPV6_RULE, + .policy = ip6mr_rule_policy, + .owner = THIS_MODULE, +}; -static struct timer_list ipmr_expire_timer; +static int __net_init ip6mr_rules_init(struct net *net) +{ + struct fib_rules_ops *ops; + struct mr6_table *mrt; + int err; + + ops = fib_rules_register(&ip6mr_rules_ops_template, net); + if (IS_ERR(ops)) + return PTR_ERR(ops); + + INIT_LIST_HEAD(&net->ipv6.mr6_tables); + + mrt = ip6mr_new_table(net, RT6_TABLE_DFLT); + if (mrt == NULL) { + err = -ENOMEM; + goto err1; + } + err = fib_default_rule_add(ops, 0x7fff, RT6_TABLE_DFLT, 0); + if (err < 0) + goto err2; + + net->ipv6.mr6_rules_ops = ops; + return 0; + +err2: + kfree(mrt); +err1: + fib_rules_unregister(ops); + return err; +} + +static void __net_exit ip6mr_rules_exit(struct net *net) +{ + struct mr6_table *mrt, *next; + + list_for_each_entry_safe(mrt, next, &net->ipv6.mr6_tables, list) + ip6mr_free_table(mrt); + fib_rules_unregister(net->ipv6.mr6_rules_ops); +} +#else +#define ip6mr_for_each_table(mrt, net) \ + for (mrt = net->ipv6.mrt6; mrt; mrt = NULL) + +static struct mr6_table *ip6mr_get_table(struct net *net, u32 id) +{ + return net->ipv6.mrt6; +} + +static int ip6mr_fib_lookup(struct net *net, struct flowi *flp, + struct mr6_table **mrt) +{ + *mrt = net->ipv6.mrt6; + return 0; +} + +static int __net_init ip6mr_rules_init(struct net *net) +{ + net->ipv6.mrt6 = ip6mr_new_table(net, RT6_TABLE_DFLT); + return net->ipv6.mrt6 ? 0 : -ENOMEM; +} + +static void __net_exit ip6mr_rules_exit(struct net *net) +{ + ip6mr_free_table(net->ipv6.mrt6); +} +#endif + +static struct mr6_table *ip6mr_new_table(struct net *net, u32 id) +{ + struct mr6_table *mrt; + unsigned int i; + + mrt = ip6mr_get_table(net, id); + if (mrt != NULL) + return mrt; + + mrt = kzalloc(sizeof(*mrt), GFP_KERNEL); + if (mrt == NULL) + return NULL; + mrt->id = id; + write_pnet(&mrt->net, net); + + /* Forwarding cache */ + for (i = 0; i < MFC6_LINES; i++) + INIT_LIST_HEAD(&mrt->mfc6_cache_array[i]); + + INIT_LIST_HEAD(&mrt->mfc6_unres_queue); + + setup_timer(&mrt->ipmr_expire_timer, ipmr_expire_process, + (unsigned long)mrt); + +#ifdef CONFIG_IPV6_PIMSM_V2 + mrt->mroute_reg_vif_num = -1; +#endif +#ifdef CONFIG_IPV6_MROUTE_MULTIPLE_TABLES + list_add_tail_rcu(&mrt->list, &net->ipv6.mr6_tables); +#endif + return mrt; +} + +static void ip6mr_free_table(struct mr6_table *mrt) +{ + del_timer(&mrt->ipmr_expire_timer); + mroute_clean_tables(mrt); + kfree(mrt); +} #ifdef CONFIG_PROC_FS struct ipmr_mfc_iter { struct seq_net_private p; - struct mfc6_cache **cache; + struct mr6_table *mrt; + struct list_head *cache; int ct; }; @@ -99,22 +339,22 @@ struct ipmr_mfc_iter { static struct mfc6_cache *ipmr_mfc_seq_idx(struct net *net, struct ipmr_mfc_iter *it, loff_t pos) { + struct mr6_table *mrt = it->mrt; struct mfc6_cache *mfc; - it->cache = net->ipv6.mfc6_cache_array; read_lock(&mrt_lock); - for (it->ct = 0; it->ct < MFC6_LINES; it->ct++) - for (mfc = net->ipv6.mfc6_cache_array[it->ct]; - mfc; mfc = mfc->next) + for (it->ct = 0; it->ct < MFC6_LINES; it->ct++) { + it->cache = &mrt->mfc6_cache_array[it->ct]; + list_for_each_entry(mfc, it->cache, list) if (pos-- == 0) return mfc; + } read_unlock(&mrt_lock); - it->cache = &mfc_unres_queue; spin_lock_bh(&mfc_unres_lock); - for (mfc = mfc_unres_queue; mfc; mfc = mfc->next) - if (net_eq(mfc6_net(mfc), net) && - pos-- == 0) + it->cache = &mrt->mfc6_unres_queue; + list_for_each_entry(mfc, it->cache, list) + if (pos-- == 0) return mfc; spin_unlock_bh(&mfc_unres_lock); @@ -122,15 +362,13 @@ static struct mfc6_cache *ipmr_mfc_seq_idx(struct net *net, return NULL; } - - - /* * The /proc interfaces to multicast routing /proc/ip6_mr_cache /proc/ip6_mr_vif */ struct ipmr_vif_iter { struct seq_net_private p; + struct mr6_table *mrt; int ct; }; @@ -138,11 +376,13 @@ static struct mif_device *ip6mr_vif_seq_idx(struct net *net, struct ipmr_vif_iter *iter, loff_t pos) { - for (iter->ct = 0; iter->ct < net->ipv6.maxvif; ++iter->ct) { - if (!MIF_EXISTS(net, iter->ct)) + struct mr6_table *mrt = iter->mrt; + + for (iter->ct = 0; iter->ct < mrt->maxvif; ++iter->ct) { + if (!MIF_EXISTS(mrt, iter->ct)) continue; if (pos-- == 0) - return &net->ipv6.vif6_table[iter->ct]; + return &mrt->vif6_table[iter->ct]; } return NULL; } @@ -150,7 +390,15 @@ static struct mif_device *ip6mr_vif_seq_idx(struct net *net, static void *ip6mr_vif_seq_start(struct seq_file *seq, loff_t *pos) __acquires(mrt_lock) { + struct ipmr_vif_iter *iter = seq->private; struct net *net = seq_file_net(seq); + struct mr6_table *mrt; + + mrt = ip6mr_get_table(net, RT6_TABLE_DFLT); + if (mrt == NULL) + return ERR_PTR(-ENOENT); + + iter->mrt = mrt; read_lock(&mrt_lock); return *pos ? ip6mr_vif_seq_idx(net, seq->private, *pos - 1) @@ -161,15 +409,16 @@ static void *ip6mr_vif_seq_next(struct seq_file *seq, void *v, loff_t *pos) { struct ipmr_vif_iter *iter = seq->private; struct net *net = seq_file_net(seq); + struct mr6_table *mrt = iter->mrt; ++*pos; if (v == SEQ_START_TOKEN) return ip6mr_vif_seq_idx(net, iter, 0); - while (++iter->ct < net->ipv6.maxvif) { - if (!MIF_EXISTS(net, iter->ct)) + while (++iter->ct < mrt->maxvif) { + if (!MIF_EXISTS(mrt, iter->ct)) continue; - return &net->ipv6.vif6_table[iter->ct]; + return &mrt->vif6_table[iter->ct]; } return NULL; } @@ -182,7 +431,8 @@ static void ip6mr_vif_seq_stop(struct seq_file *seq, void *v) static int ip6mr_vif_seq_show(struct seq_file *seq, void *v) { - struct net *net = seq_file_net(seq); + struct ipmr_vif_iter *iter = seq->private; + struct mr6_table *mrt = iter->mrt; if (v == SEQ_START_TOKEN) { seq_puts(seq, @@ -193,7 +443,7 @@ static int ip6mr_vif_seq_show(struct seq_file *seq, void *v) seq_printf(seq, "%2td %-10s %8ld %7ld %8ld %7ld %05X\n", - vif - net->ipv6.vif6_table, + vif - mrt->vif6_table, name, vif->bytes_in, vif->pkt_in, vif->bytes_out, vif->pkt_out, vif->flags); @@ -224,8 +474,15 @@ static const struct file_operations ip6mr_vif_fops = { static void *ipmr_mfc_seq_start(struct seq_file *seq, loff_t *pos) { + struct ipmr_mfc_iter *it = seq->private; struct net *net = seq_file_net(seq); + struct mr6_table *mrt; + + mrt = ip6mr_get_table(net, RT6_TABLE_DFLT); + if (mrt == NULL) + return ERR_PTR(-ENOENT); + it->mrt = mrt; return *pos ? ipmr_mfc_seq_idx(net, seq->private, *pos - 1) : SEQ_START_TOKEN; } @@ -235,35 +492,36 @@ static void *ipmr_mfc_seq_next(struct seq_file *seq, void *v, loff_t *pos) struct mfc6_cache *mfc = v; struct ipmr_mfc_iter *it = seq->private; struct net *net = seq_file_net(seq); + struct mr6_table *mrt = it->mrt; ++*pos; if (v == SEQ_START_TOKEN) return ipmr_mfc_seq_idx(net, seq->private, 0); - if (mfc->next) - return mfc->next; + if (mfc->list.next != it->cache) + return list_entry(mfc->list.next, struct mfc6_cache, list); - if (it->cache == &mfc_unres_queue) + if (it->cache == &mrt->mfc6_unres_queue) goto end_of_list; - BUG_ON(it->cache != net->ipv6.mfc6_cache_array); + BUG_ON(it->cache != &mrt->mfc6_cache_array[it->ct]); while (++it->ct < MFC6_LINES) { - mfc = net->ipv6.mfc6_cache_array[it->ct]; - if (mfc) - return mfc; + it->cache = &mrt->mfc6_cache_array[it->ct]; + if (list_empty(it->cache)) + continue; + return list_first_entry(it->cache, struct mfc6_cache, list); } /* exhausted cache_array, show unresolved */ read_unlock(&mrt_lock); - it->cache = &mfc_unres_queue; + it->cache = &mrt->mfc6_unres_queue; it->ct = 0; spin_lock_bh(&mfc_unres_lock); - mfc = mfc_unres_queue; - if (mfc) - return mfc; + if (!list_empty(it->cache)) + return list_first_entry(it->cache, struct mfc6_cache, list); end_of_list: spin_unlock_bh(&mfc_unres_lock); @@ -275,18 +533,17 @@ static void *ipmr_mfc_seq_next(struct seq_file *seq, void *v, loff_t *pos) static void ipmr_mfc_seq_stop(struct seq_file *seq, void *v) { struct ipmr_mfc_iter *it = seq->private; - struct net *net = seq_file_net(seq); + struct mr6_table *mrt = it->mrt; - if (it->cache == &mfc_unres_queue) + if (it->cache == &mrt->mfc6_unres_queue) spin_unlock_bh(&mfc_unres_lock); - else if (it->cache == net->ipv6.mfc6_cache_array) + else if (it->cache == mrt->mfc6_cache_array) read_unlock(&mrt_lock); } static int ipmr_mfc_seq_show(struct seq_file *seq, void *v) { int n; - struct net *net = seq_file_net(seq); if (v == SEQ_START_TOKEN) { seq_puts(seq, @@ -296,19 +553,20 @@ static int ipmr_mfc_seq_show(struct seq_file *seq, void *v) } else { const struct mfc6_cache *mfc = v; const struct ipmr_mfc_iter *it = seq->private; + struct mr6_table *mrt = it->mrt; seq_printf(seq, "%pI6 %pI6 %-3hd", &mfc->mf6c_mcastgrp, &mfc->mf6c_origin, mfc->mf6c_parent); - if (it->cache != &mfc_unres_queue) { + if (it->cache != &mrt->mfc6_unres_queue) { seq_printf(seq, " %8lu %8lu %8lu", mfc->mfc_un.res.pkt, mfc->mfc_un.res.bytes, mfc->mfc_un.res.wrong_if); for (n = mfc->mfc_un.res.minvif; n < mfc->mfc_un.res.maxvif; n++) { - if (MIF_EXISTS(net, n) && + if (MIF_EXISTS(mrt, n) && mfc->mfc_un.res.ttls[n] < 255) seq_printf(seq, " %2d:%-3d", @@ -355,7 +613,12 @@ static int pim6_rcv(struct sk_buff *skb) struct ipv6hdr *encap; struct net_device *reg_dev = NULL; struct net *net = dev_net(skb->dev); - int reg_vif_num = net->ipv6.mroute_reg_vif_num; + struct mr6_table *mrt; + struct flowi fl = { + .iif = skb->dev->ifindex, + .mark = skb->mark, + }; + int reg_vif_num; if (!pskb_may_pull(skb, sizeof(*pim) + sizeof(*encap))) goto drop; @@ -378,9 +641,13 @@ static int pim6_rcv(struct sk_buff *skb) ntohs(encap->payload_len) + sizeof(*pim) > skb->len) goto drop; + if (ip6mr_fib_lookup(net, &fl, &mrt) < 0) + goto drop; + reg_vif_num = mrt->mroute_reg_vif_num; + read_lock(&mrt_lock); if (reg_vif_num >= 0) - reg_dev = net->ipv6.vif6_table[reg_vif_num].dev; + reg_dev = mrt->vif6_table[reg_vif_num].dev; if (reg_dev) dev_hold(reg_dev); read_unlock(&mrt_lock); @@ -417,12 +684,22 @@ static netdev_tx_t reg_vif_xmit(struct sk_buff *skb, struct net_device *dev) { struct net *net = dev_net(dev); + struct mr6_table *mrt; + struct flowi fl = { + .oif = dev->ifindex, + .iif = skb->skb_iif, + .mark = skb->mark, + }; + int err; + + err = ip6mr_fib_lookup(net, &fl, &mrt); + if (err < 0) + return err; read_lock(&mrt_lock); dev->stats.tx_bytes += skb->len; dev->stats.tx_packets++; - ip6mr_cache_report(net, skb, net->ipv6.mroute_reg_vif_num, - MRT6MSG_WHOLEPKT); + ip6mr_cache_report(mrt, skb, mrt->mroute_reg_vif_num, MRT6MSG_WHOLEPKT); read_unlock(&mrt_lock); kfree_skb(skb); return NETDEV_TX_OK; @@ -442,11 +719,17 @@ static void reg_vif_setup(struct net_device *dev) dev->features |= NETIF_F_NETNS_LOCAL; } -static struct net_device *ip6mr_reg_vif(struct net *net) +static struct net_device *ip6mr_reg_vif(struct net *net, struct mr6_table *mrt) { struct net_device *dev; + char name[IFNAMSIZ]; - dev = alloc_netdev(0, "pim6reg", reg_vif_setup); + if (mrt->id == RT6_TABLE_DFLT) + sprintf(name, "pim6reg"); + else + sprintf(name, "pim6reg%u", mrt->id); + + dev = alloc_netdev(0, name, reg_vif_setup); if (dev == NULL) return NULL; @@ -478,15 +761,16 @@ failure: * Delete a VIF entry */ -static int mif6_delete(struct net *net, int vifi, struct list_head *head) +static int mif6_delete(struct mr6_table *mrt, int vifi, struct list_head *head) { struct mif_device *v; struct net_device *dev; struct inet6_dev *in6_dev; - if (vifi < 0 || vifi >= net->ipv6.maxvif) + + if (vifi < 0 || vifi >= mrt->maxvif) return -EADDRNOTAVAIL; - v = &net->ipv6.vif6_table[vifi]; + v = &mrt->vif6_table[vifi]; write_lock_bh(&mrt_lock); dev = v->dev; @@ -498,17 +782,17 @@ static int mif6_delete(struct net *net, int vifi, struct list_head *head) } #ifdef CONFIG_IPV6_PIMSM_V2 - if (vifi == net->ipv6.mroute_reg_vif_num) - net->ipv6.mroute_reg_vif_num = -1; + if (vifi == mrt->mroute_reg_vif_num) + mrt->mroute_reg_vif_num = -1; #endif - if (vifi + 1 == net->ipv6.maxvif) { + if (vifi + 1 == mrt->maxvif) { int tmp; for (tmp = vifi - 1; tmp >= 0; tmp--) { - if (MIF_EXISTS(net, tmp)) + if (MIF_EXISTS(mrt, tmp)) break; } - net->ipv6.maxvif = tmp + 1; + mrt->maxvif = tmp + 1; } write_unlock_bh(&mrt_lock); @@ -528,7 +812,6 @@ static int mif6_delete(struct net *net, int vifi, struct list_head *head) static inline void ip6mr_cache_free(struct mfc6_cache *c) { - release_net(mfc6_net(c)); kmem_cache_free(mrt_cachep, c); } @@ -536,12 +819,12 @@ static inline void ip6mr_cache_free(struct mfc6_cache *c) and reporting error to netlink readers. */ -static void ip6mr_destroy_unres(struct mfc6_cache *c) +static void ip6mr_destroy_unres(struct mr6_table *mrt, struct mfc6_cache *c) { + struct net *net = read_pnet(&mrt->net); struct sk_buff *skb; - struct net *net = mfc6_net(c); - atomic_dec(&net->ipv6.cache_resolve_queue_len); + atomic_dec(&mrt->cache_resolve_queue_len); while((skb = skb_dequeue(&c->mfc_un.unres.unresolved)) != NULL) { if (ipv6_hdr(skb)->version == 0) { @@ -559,60 +842,59 @@ static void ip6mr_destroy_unres(struct mfc6_cache *c) } -/* Single timer process for all the unresolved queue. */ +/* Timer process for all the unresolved queue. */ -static void ipmr_do_expire_process(unsigned long dummy) +static void ipmr_do_expire_process(struct mr6_table *mrt) { unsigned long now = jiffies; unsigned long expires = 10 * HZ; - struct mfc6_cache *c, **cp; + struct mfc6_cache *c, *next; - cp = &mfc_unres_queue; - - while ((c = *cp) != NULL) { + list_for_each_entry_safe(c, next, &mrt->mfc6_unres_queue, list) { if (time_after(c->mfc_un.unres.expires, now)) { /* not yet... */ unsigned long interval = c->mfc_un.unres.expires - now; if (interval < expires) expires = interval; - cp = &c->next; continue; } - *cp = c->next; - ip6mr_destroy_unres(c); + list_del(&c->list); + ip6mr_destroy_unres(mrt, c); } - if (mfc_unres_queue != NULL) - mod_timer(&ipmr_expire_timer, jiffies + expires); + if (!list_empty(&mrt->mfc6_unres_queue)) + mod_timer(&mrt->ipmr_expire_timer, jiffies + expires); } -static void ipmr_expire_process(unsigned long dummy) +static void ipmr_expire_process(unsigned long arg) { + struct mr6_table *mrt = (struct mr6_table *)arg; + if (!spin_trylock(&mfc_unres_lock)) { - mod_timer(&ipmr_expire_timer, jiffies + 1); + mod_timer(&mrt->ipmr_expire_timer, jiffies + 1); return; } - if (mfc_unres_queue != NULL) - ipmr_do_expire_process(dummy); + if (!list_empty(&mrt->mfc6_unres_queue)) + ipmr_do_expire_process(mrt); spin_unlock(&mfc_unres_lock); } /* Fill oifs list. It is called under write locked mrt_lock. */ -static void ip6mr_update_thresholds(struct mfc6_cache *cache, unsigned char *ttls) +static void ip6mr_update_thresholds(struct mr6_table *mrt, struct mfc6_cache *cache, + unsigned char *ttls) { int vifi; - struct net *net = mfc6_net(cache); cache->mfc_un.res.minvif = MAXMIFS; cache->mfc_un.res.maxvif = 0; memset(cache->mfc_un.res.ttls, 255, MAXMIFS); - for (vifi = 0; vifi < net->ipv6.maxvif; vifi++) { - if (MIF_EXISTS(net, vifi) && + for (vifi = 0; vifi < mrt->maxvif; vifi++) { + if (MIF_EXISTS(mrt, vifi) && ttls[vifi] && ttls[vifi] < 255) { cache->mfc_un.res.ttls[vifi] = ttls[vifi]; if (cache->mfc_un.res.minvif > vifi) @@ -623,16 +905,17 @@ static void ip6mr_update_thresholds(struct mfc6_cache *cache, unsigned char *ttl } } -static int mif6_add(struct net *net, struct mif6ctl *vifc, int mrtsock) +static int mif6_add(struct net *net, struct mr6_table *mrt, + struct mif6ctl *vifc, int mrtsock) { int vifi = vifc->mif6c_mifi; - struct mif_device *v = &net->ipv6.vif6_table[vifi]; + struct mif_device *v = &mrt->vif6_table[vifi]; struct net_device *dev; struct inet6_dev *in6_dev; int err; /* Is vif busy ? */ - if (MIF_EXISTS(net, vifi)) + if (MIF_EXISTS(mrt, vifi)) return -EADDRINUSE; switch (vifc->mif6c_flags) { @@ -642,9 +925,9 @@ static int mif6_add(struct net *net, struct mif6ctl *vifc, int mrtsock) * Special Purpose VIF in PIM * All the packets will be sent to the daemon */ - if (net->ipv6.mroute_reg_vif_num >= 0) + if (mrt->mroute_reg_vif_num >= 0) return -EADDRINUSE; - dev = ip6mr_reg_vif(net); + dev = ip6mr_reg_vif(net, mrt); if (!dev) return -ENOBUFS; err = dev_set_allmulti(dev, 1); @@ -694,50 +977,48 @@ static int mif6_add(struct net *net, struct mif6ctl *vifc, int mrtsock) v->dev = dev; #ifdef CONFIG_IPV6_PIMSM_V2 if (v->flags & MIFF_REGISTER) - net->ipv6.mroute_reg_vif_num = vifi; + mrt->mroute_reg_vif_num = vifi; #endif - if (vifi + 1 > net->ipv6.maxvif) - net->ipv6.maxvif = vifi + 1; + if (vifi + 1 > mrt->maxvif) + mrt->maxvif = vifi + 1; write_unlock_bh(&mrt_lock); return 0; } -static struct mfc6_cache *ip6mr_cache_find(struct net *net, +static struct mfc6_cache *ip6mr_cache_find(struct mr6_table *mrt, struct in6_addr *origin, struct in6_addr *mcastgrp) { int line = MFC6_HASH(mcastgrp, origin); struct mfc6_cache *c; - for (c = net->ipv6.mfc6_cache_array[line]; c; c = c->next) { + list_for_each_entry(c, &mrt->mfc6_cache_array[line], list) { if (ipv6_addr_equal(&c->mf6c_origin, origin) && ipv6_addr_equal(&c->mf6c_mcastgrp, mcastgrp)) - break; + return c; } - return c; + return NULL; } /* * Allocate a multicast cache entry */ -static struct mfc6_cache *ip6mr_cache_alloc(struct net *net) +static struct mfc6_cache *ip6mr_cache_alloc(void) { struct mfc6_cache *c = kmem_cache_zalloc(mrt_cachep, GFP_KERNEL); if (c == NULL) return NULL; c->mfc_un.res.minvif = MAXMIFS; - mfc6_net_set(c, net); return c; } -static struct mfc6_cache *ip6mr_cache_alloc_unres(struct net *net) +static struct mfc6_cache *ip6mr_cache_alloc_unres(void) { struct mfc6_cache *c = kmem_cache_zalloc(mrt_cachep, GFP_ATOMIC); if (c == NULL) return NULL; skb_queue_head_init(&c->mfc_un.unres.unresolved); c->mfc_un.unres.expires = jiffies + 10 * HZ; - mfc6_net_set(c, net); return c; } @@ -745,7 +1026,8 @@ static struct mfc6_cache *ip6mr_cache_alloc_unres(struct net *net) * A cache entry has gone into a resolved state from queued */ -static void ip6mr_cache_resolve(struct mfc6_cache *uc, struct mfc6_cache *c) +static void ip6mr_cache_resolve(struct net *net, struct mr6_table *mrt, + struct mfc6_cache *uc, struct mfc6_cache *c) { struct sk_buff *skb; @@ -758,7 +1040,7 @@ static void ip6mr_cache_resolve(struct mfc6_cache *uc, struct mfc6_cache *c) int err; struct nlmsghdr *nlh = (struct nlmsghdr *)skb_pull(skb, sizeof(struct ipv6hdr)); - if (ip6mr_fill_mroute(skb, c, NLMSG_DATA(nlh)) > 0) { + if (__ip6mr_fill_mroute(mrt, skb, c, NLMSG_DATA(nlh)) > 0) { nlh->nlmsg_len = skb_tail_pointer(skb) - (u8 *)nlh; } else { nlh->nlmsg_type = NLMSG_ERROR; @@ -766,9 +1048,9 @@ static void ip6mr_cache_resolve(struct mfc6_cache *uc, struct mfc6_cache *c) skb_trim(skb, nlh->nlmsg_len); ((struct nlmsgerr *)NLMSG_DATA(nlh))->error = -EMSGSIZE; } - err = rtnl_unicast(skb, mfc6_net(uc), NETLINK_CB(skb).pid); + err = rtnl_unicast(skb, net, NETLINK_CB(skb).pid); } else - ip6_mr_forward(skb, c); + ip6_mr_forward(net, mrt, skb, c); } } @@ -779,8 +1061,8 @@ static void ip6mr_cache_resolve(struct mfc6_cache *uc, struct mfc6_cache *c) * Called under mrt_lock. */ -static int ip6mr_cache_report(struct net *net, struct sk_buff *pkt, mifi_t mifi, - int assert) +static int ip6mr_cache_report(struct mr6_table *mrt, struct sk_buff *pkt, + mifi_t mifi, int assert) { struct sk_buff *skb; struct mrt6msg *msg; @@ -816,7 +1098,7 @@ static int ip6mr_cache_report(struct net *net, struct sk_buff *pkt, mifi_t mifi, msg = (struct mrt6msg *)skb_transport_header(skb); msg->im6_mbz = 0; msg->im6_msgtype = MRT6MSG_WHOLEPKT; - msg->im6_mif = net->ipv6.mroute_reg_vif_num; + msg->im6_mif = mrt->mroute_reg_vif_num; msg->im6_pad = 0; ipv6_addr_copy(&msg->im6_src, &ipv6_hdr(pkt)->saddr); ipv6_addr_copy(&msg->im6_dst, &ipv6_hdr(pkt)->daddr); @@ -851,7 +1133,7 @@ static int ip6mr_cache_report(struct net *net, struct sk_buff *pkt, mifi_t mifi, skb->ip_summed = CHECKSUM_UNNECESSARY; } - if (net->ipv6.mroute6_sk == NULL) { + if (mrt->mroute6_sk == NULL) { kfree_skb(skb); return -EINVAL; } @@ -859,7 +1141,7 @@ static int ip6mr_cache_report(struct net *net, struct sk_buff *pkt, mifi_t mifi, /* * Deliver to user space multicast routing algorithms */ - ret = sock_queue_rcv_skb(net->ipv6.mroute6_sk, skb); + ret = sock_queue_rcv_skb(mrt->mroute6_sk, skb); if (ret < 0) { if (net_ratelimit()) printk(KERN_WARNING "mroute6: pending queue full, dropping entries.\n"); @@ -874,26 +1156,28 @@ static int ip6mr_cache_report(struct net *net, struct sk_buff *pkt, mifi_t mifi, */ static int -ip6mr_cache_unresolved(struct net *net, mifi_t mifi, struct sk_buff *skb) +ip6mr_cache_unresolved(struct mr6_table *mrt, mifi_t mifi, struct sk_buff *skb) { + bool found = false; int err; struct mfc6_cache *c; spin_lock_bh(&mfc_unres_lock); - for (c = mfc_unres_queue; c; c = c->next) { - if (net_eq(mfc6_net(c), net) && - ipv6_addr_equal(&c->mf6c_mcastgrp, &ipv6_hdr(skb)->daddr) && - ipv6_addr_equal(&c->mf6c_origin, &ipv6_hdr(skb)->saddr)) + list_for_each_entry(c, &mrt->mfc6_unres_queue, list) { + if (ipv6_addr_equal(&c->mf6c_mcastgrp, &ipv6_hdr(skb)->daddr) && + ipv6_addr_equal(&c->mf6c_origin, &ipv6_hdr(skb)->saddr)) { + found = true; break; + } } - if (c == NULL) { + if (!found) { /* * Create a new entry if allowable */ - if (atomic_read(&net->ipv6.cache_resolve_queue_len) >= 10 || - (c = ip6mr_cache_alloc_unres(net)) == NULL) { + if (atomic_read(&mrt->cache_resolve_queue_len) >= 10 || + (c = ip6mr_cache_alloc_unres()) == NULL) { spin_unlock_bh(&mfc_unres_lock); kfree_skb(skb); @@ -910,7 +1194,7 @@ ip6mr_cache_unresolved(struct net *net, mifi_t mifi, struct sk_buff *skb) /* * Reflect first query at pim6sd */ - err = ip6mr_cache_report(net, skb, mifi, MRT6MSG_NOCACHE); + err = ip6mr_cache_report(mrt, skb, mifi, MRT6MSG_NOCACHE); if (err < 0) { /* If the report failed throw the cache entry out - Brad Parker @@ -922,11 +1206,10 @@ ip6mr_cache_unresolved(struct net *net, mifi_t mifi, struct sk_buff *skb) return err; } - atomic_inc(&net->ipv6.cache_resolve_queue_len); - c->next = mfc_unres_queue; - mfc_unres_queue = c; + atomic_inc(&mrt->cache_resolve_queue_len); + list_add(&c->list, &mrt->mfc6_unres_queue); - ipmr_do_expire_process(1); + ipmr_do_expire_process(mrt); } /* @@ -948,19 +1231,18 @@ ip6mr_cache_unresolved(struct net *net, mifi_t mifi, struct sk_buff *skb) * MFC6 cache manipulation by user space */ -static int ip6mr_mfc_delete(struct net *net, struct mf6cctl *mfc) +static int ip6mr_mfc_delete(struct mr6_table *mrt, struct mf6cctl *mfc) { int line; - struct mfc6_cache *c, **cp; + struct mfc6_cache *c, *next; line = MFC6_HASH(&mfc->mf6cc_mcastgrp.sin6_addr, &mfc->mf6cc_origin.sin6_addr); - for (cp = &net->ipv6.mfc6_cache_array[line]; - (c = *cp) != NULL; cp = &c->next) { + list_for_each_entry_safe(c, next, &mrt->mfc6_cache_array[line], list) { if (ipv6_addr_equal(&c->mf6c_origin, &mfc->mf6cc_origin.sin6_addr) && ipv6_addr_equal(&c->mf6c_mcastgrp, &mfc->mf6cc_mcastgrp.sin6_addr)) { write_lock_bh(&mrt_lock); - *cp = c->next; + list_del(&c->list); write_unlock_bh(&mrt_lock); ip6mr_cache_free(c); @@ -975,6 +1257,7 @@ static int ip6mr_device_event(struct notifier_block *this, { struct net_device *dev = ptr; struct net *net = dev_net(dev); + struct mr6_table *mrt; struct mif_device *v; int ct; LIST_HEAD(list); @@ -982,10 +1265,12 @@ static int ip6mr_device_event(struct notifier_block *this, if (event != NETDEV_UNREGISTER) return NOTIFY_DONE; - v = &net->ipv6.vif6_table[0]; - for (ct = 0; ct < net->ipv6.maxvif; ct++, v++) { - if (v->dev == dev) - mif6_delete(net, ct, &list); + ip6mr_for_each_table(mrt, net) { + v = &mrt->vif6_table[0]; + for (ct = 0; ct < mrt->maxvif; ct++, v++) { + if (v->dev == dev) + mif6_delete(mrt, ct, &list); + } } unregister_netdevice_many(&list); @@ -1002,26 +1287,11 @@ static struct notifier_block ip6_mr_notifier = { static int __net_init ip6mr_net_init(struct net *net) { - int err = 0; - net->ipv6.vif6_table = kcalloc(MAXMIFS, sizeof(struct mif_device), - GFP_KERNEL); - if (!net->ipv6.vif6_table) { - err = -ENOMEM; - goto fail; - } - - /* Forwarding cache */ - net->ipv6.mfc6_cache_array = kcalloc(MFC6_LINES, - sizeof(struct mfc6_cache *), - GFP_KERNEL); - if (!net->ipv6.mfc6_cache_array) { - err = -ENOMEM; - goto fail_mfc6_cache; - } + int err; -#ifdef CONFIG_IPV6_PIMSM_V2 - net->ipv6.mroute_reg_vif_num = -1; -#endif + err = ip6mr_rules_init(net); + if (err < 0) + goto fail; #ifdef CONFIG_PROC_FS err = -ENOMEM; @@ -1030,16 +1300,15 @@ static int __net_init ip6mr_net_init(struct net *net) if (!proc_net_fops_create(net, "ip6_mr_cache", 0, &ip6mr_mfc_fops)) goto proc_cache_fail; #endif + return 0; #ifdef CONFIG_PROC_FS proc_cache_fail: proc_net_remove(net, "ip6_mr_vif"); proc_vif_fail: - kfree(net->ipv6.mfc6_cache_array); + ip6mr_rules_exit(net); #endif -fail_mfc6_cache: - kfree(net->ipv6.vif6_table); fail: return err; } @@ -1050,9 +1319,7 @@ static void __net_exit ip6mr_net_exit(struct net *net) proc_net_remove(net, "ip6_mr_cache"); proc_net_remove(net, "ip6_mr_vif"); #endif - mroute_clean_tables(net); - kfree(net->ipv6.mfc6_cache_array); - kfree(net->ipv6.vif6_table); + ip6mr_rules_exit(net); } static struct pernet_operations ip6mr_net_ops = { @@ -1075,7 +1342,6 @@ int __init ip6_mr_init(void) if (err) goto reg_pernet_fail; - setup_timer(&ipmr_expire_timer, ipmr_expire_process, 0); err = register_netdevice_notifier(&ip6_mr_notifier); if (err) goto reg_notif_fail; @@ -1086,13 +1352,13 @@ int __init ip6_mr_init(void) goto add_proto_fail; } #endif + rtnl_register(RTNL_FAMILY_IP6MR, RTM_GETROUTE, NULL, ip6mr_rtm_dumproute); return 0; #ifdef CONFIG_IPV6_PIMSM_V2 add_proto_fail: unregister_netdevice_notifier(&ip6_mr_notifier); #endif reg_notif_fail: - del_timer(&ipmr_expire_timer); unregister_pernet_subsys(&ip6mr_net_ops); reg_pernet_fail: kmem_cache_destroy(mrt_cachep); @@ -1102,15 +1368,16 @@ reg_pernet_fail: void ip6_mr_cleanup(void) { unregister_netdevice_notifier(&ip6_mr_notifier); - del_timer(&ipmr_expire_timer); unregister_pernet_subsys(&ip6mr_net_ops); kmem_cache_destroy(mrt_cachep); } -static int ip6mr_mfc_add(struct net *net, struct mf6cctl *mfc, int mrtsock) +static int ip6mr_mfc_add(struct net *net, struct mr6_table *mrt, + struct mf6cctl *mfc, int mrtsock) { + bool found = false; int line; - struct mfc6_cache *uc, *c, **cp; + struct mfc6_cache *uc, *c; unsigned char ttls[MAXMIFS]; int i; @@ -1126,17 +1393,18 @@ static int ip6mr_mfc_add(struct net *net, struct mf6cctl *mfc, int mrtsock) line = MFC6_HASH(&mfc->mf6cc_mcastgrp.sin6_addr, &mfc->mf6cc_origin.sin6_addr); - for (cp = &net->ipv6.mfc6_cache_array[line]; - (c = *cp) != NULL; cp = &c->next) { + list_for_each_entry(c, &mrt->mfc6_cache_array[line], list) { if (ipv6_addr_equal(&c->mf6c_origin, &mfc->mf6cc_origin.sin6_addr) && - ipv6_addr_equal(&c->mf6c_mcastgrp, &mfc->mf6cc_mcastgrp.sin6_addr)) + ipv6_addr_equal(&c->mf6c_mcastgrp, &mfc->mf6cc_mcastgrp.sin6_addr)) { + found = true; break; + } } - if (c != NULL) { + if (found) { write_lock_bh(&mrt_lock); c->mf6c_parent = mfc->mf6cc_parent; - ip6mr_update_thresholds(c, ttls); + ip6mr_update_thresholds(mrt, c, ttls); if (!mrtsock) c->mfc_flags |= MFC_STATIC; write_unlock_bh(&mrt_lock); @@ -1146,43 +1414,42 @@ static int ip6mr_mfc_add(struct net *net, struct mf6cctl *mfc, int mrtsock) if (!ipv6_addr_is_multicast(&mfc->mf6cc_mcastgrp.sin6_addr)) return -EINVAL; - c = ip6mr_cache_alloc(net); + c = ip6mr_cache_alloc(); if (c == NULL) return -ENOMEM; c->mf6c_origin = mfc->mf6cc_origin.sin6_addr; c->mf6c_mcastgrp = mfc->mf6cc_mcastgrp.sin6_addr; c->mf6c_parent = mfc->mf6cc_parent; - ip6mr_update_thresholds(c, ttls); + ip6mr_update_thresholds(mrt, c, ttls); if (!mrtsock) c->mfc_flags |= MFC_STATIC; write_lock_bh(&mrt_lock); - c->next = net->ipv6.mfc6_cache_array[line]; - net->ipv6.mfc6_cache_array[line] = c; + list_add(&c->list, &mrt->mfc6_cache_array[line]); write_unlock_bh(&mrt_lock); /* * Check to see if we resolved a queued list. If so we * need to send on the frames and tidy up. */ + found = false; spin_lock_bh(&mfc_unres_lock); - for (cp = &mfc_unres_queue; (uc = *cp) != NULL; - cp = &uc->next) { - if (net_eq(mfc6_net(uc), net) && - ipv6_addr_equal(&uc->mf6c_origin, &c->mf6c_origin) && + list_for_each_entry(uc, &mrt->mfc6_unres_queue, list) { + if (ipv6_addr_equal(&uc->mf6c_origin, &c->mf6c_origin) && ipv6_addr_equal(&uc->mf6c_mcastgrp, &c->mf6c_mcastgrp)) { - *cp = uc->next; - atomic_dec(&net->ipv6.cache_resolve_queue_len); + list_del(&uc->list); + atomic_dec(&mrt->cache_resolve_queue_len); + found = true; break; } } - if (mfc_unres_queue == NULL) - del_timer(&ipmr_expire_timer); + if (list_empty(&mrt->mfc6_unres_queue)) + del_timer(&mrt->ipmr_expire_timer); spin_unlock_bh(&mfc_unres_lock); - if (uc) { - ip6mr_cache_resolve(uc, c); + if (found) { + ip6mr_cache_resolve(net, mrt, uc, c); ip6mr_cache_free(uc); } return 0; @@ -1192,17 +1459,18 @@ static int ip6mr_mfc_add(struct net *net, struct mf6cctl *mfc, int mrtsock) * Close the multicast socket, and clear the vif tables etc */ -static void mroute_clean_tables(struct net *net) +static void mroute_clean_tables(struct mr6_table *mrt) { int i; LIST_HEAD(list); + struct mfc6_cache *c, *next; /* * Shut down all active vif entries */ - for (i = 0; i < net->ipv6.maxvif; i++) { - if (!(net->ipv6.vif6_table[i].flags & VIFF_STATIC)) - mif6_delete(net, i, &list); + for (i = 0; i < mrt->maxvif; i++) { + if (!(mrt->vif6_table[i].flags & VIFF_STATIC)) + mif6_delete(mrt, i, &list); } unregister_netdevice_many(&list); @@ -1210,48 +1478,36 @@ static void mroute_clean_tables(struct net *net) * Wipe the cache */ for (i = 0; i < MFC6_LINES; i++) { - struct mfc6_cache *c, **cp; - - cp = &net->ipv6.mfc6_cache_array[i]; - while ((c = *cp) != NULL) { - if (c->mfc_flags & MFC_STATIC) { - cp = &c->next; + list_for_each_entry_safe(c, next, &mrt->mfc6_cache_array[i], list) { + if (c->mfc_flags & MFC_STATIC) continue; - } write_lock_bh(&mrt_lock); - *cp = c->next; + list_del(&c->list); write_unlock_bh(&mrt_lock); ip6mr_cache_free(c); } } - if (atomic_read(&net->ipv6.cache_resolve_queue_len) != 0) { - struct mfc6_cache *c, **cp; - + if (atomic_read(&mrt->cache_resolve_queue_len) != 0) { spin_lock_bh(&mfc_unres_lock); - cp = &mfc_unres_queue; - while ((c = *cp) != NULL) { - if (!net_eq(mfc6_net(c), net)) { - cp = &c->next; - continue; - } - *cp = c->next; - ip6mr_destroy_unres(c); + list_for_each_entry_safe(c, next, &mrt->mfc6_unres_queue, list) { + list_del(&c->list); + ip6mr_destroy_unres(mrt, c); } spin_unlock_bh(&mfc_unres_lock); } } -static int ip6mr_sk_init(struct sock *sk) +static int ip6mr_sk_init(struct mr6_table *mrt, struct sock *sk) { int err = 0; struct net *net = sock_net(sk); rtnl_lock(); write_lock_bh(&mrt_lock); - if (likely(net->ipv6.mroute6_sk == NULL)) { - net->ipv6.mroute6_sk = sk; + if (likely(mrt->mroute6_sk == NULL)) { + mrt->mroute6_sk = sk; net->ipv6.devconf_all->mc_forwarding++; } else @@ -1265,24 +1521,43 @@ static int ip6mr_sk_init(struct sock *sk) int ip6mr_sk_done(struct sock *sk) { - int err = 0; + int err = -EACCES; struct net *net = sock_net(sk); + struct mr6_table *mrt; rtnl_lock(); - if (sk == net->ipv6.mroute6_sk) { - write_lock_bh(&mrt_lock); - net->ipv6.mroute6_sk = NULL; - net->ipv6.devconf_all->mc_forwarding--; - write_unlock_bh(&mrt_lock); + ip6mr_for_each_table(mrt, net) { + if (sk == mrt->mroute6_sk) { + write_lock_bh(&mrt_lock); + mrt->mroute6_sk = NULL; + net->ipv6.devconf_all->mc_forwarding--; + write_unlock_bh(&mrt_lock); - mroute_clean_tables(net); - } else - err = -EACCES; + mroute_clean_tables(mrt); + err = 0; + break; + } + } rtnl_unlock(); return err; } +struct sock *mroute6_socket(struct net *net, struct sk_buff *skb) +{ + struct mr6_table *mrt; + struct flowi fl = { + .iif = skb->skb_iif, + .oif = skb->dev->ifindex, + .mark = skb->mark, + }; + + if (ip6mr_fib_lookup(net, &fl, &mrt) < 0) + return NULL; + + return mrt->mroute6_sk; +} + /* * Socket options and virtual interface manipulation. The whole * virtual interface system is a complete heap, but unfortunately @@ -1297,9 +1572,14 @@ int ip6_mroute_setsockopt(struct sock *sk, int optname, char __user *optval, uns struct mf6cctl mfc; mifi_t mifi; struct net *net = sock_net(sk); + struct mr6_table *mrt; + + mrt = ip6mr_get_table(net, raw6_sk(sk)->ip6mr_table ? : RT6_TABLE_DFLT); + if (mrt == NULL) + return -ENOENT; if (optname != MRT6_INIT) { - if (sk != net->ipv6.mroute6_sk && !capable(CAP_NET_ADMIN)) + if (sk != mrt->mroute6_sk && !capable(CAP_NET_ADMIN)) return -EACCES; } @@ -1311,7 +1591,7 @@ int ip6_mroute_setsockopt(struct sock *sk, int optname, char __user *optval, uns if (optlen < sizeof(int)) return -EINVAL; - return ip6mr_sk_init(sk); + return ip6mr_sk_init(mrt, sk); case MRT6_DONE: return ip6mr_sk_done(sk); @@ -1324,7 +1604,7 @@ int ip6_mroute_setsockopt(struct sock *sk, int optname, char __user *optval, uns if (vif.mif6c_mifi >= MAXMIFS) return -ENFILE; rtnl_lock(); - ret = mif6_add(net, &vif, sk == net->ipv6.mroute6_sk); + ret = mif6_add(net, mrt, &vif, sk == mrt->mroute6_sk); rtnl_unlock(); return ret; @@ -1334,7 +1614,7 @@ int ip6_mroute_setsockopt(struct sock *sk, int optname, char __user *optval, uns if (copy_from_user(&mifi, optval, sizeof(mifi_t))) return -EFAULT; rtnl_lock(); - ret = mif6_delete(net, mifi, NULL); + ret = mif6_delete(mrt, mifi, NULL); rtnl_unlock(); return ret; @@ -1350,10 +1630,9 @@ int ip6_mroute_setsockopt(struct sock *sk, int optname, char __user *optval, uns return -EFAULT; rtnl_lock(); if (optname == MRT6_DEL_MFC) - ret = ip6mr_mfc_delete(net, &mfc); + ret = ip6mr_mfc_delete(mrt, &mfc); else - ret = ip6mr_mfc_add(net, &mfc, - sk == net->ipv6.mroute6_sk); + ret = ip6mr_mfc_add(net, mrt, &mfc, sk == mrt->mroute6_sk); rtnl_unlock(); return ret; @@ -1365,7 +1644,7 @@ int ip6_mroute_setsockopt(struct sock *sk, int optname, char __user *optval, uns int v; if (get_user(v, (int __user *)optval)) return -EFAULT; - net->ipv6.mroute_do_assert = !!v; + mrt->mroute_do_assert = !!v; return 0; } @@ -1378,15 +1657,36 @@ int ip6_mroute_setsockopt(struct sock *sk, int optname, char __user *optval, uns v = !!v; rtnl_lock(); ret = 0; - if (v != net->ipv6.mroute_do_pim) { - net->ipv6.mroute_do_pim = v; - net->ipv6.mroute_do_assert = v; + if (v != mrt->mroute_do_pim) { + mrt->mroute_do_pim = v; + mrt->mroute_do_assert = v; } rtnl_unlock(); return ret; } #endif +#ifdef CONFIG_IPV6_MROUTE_MULTIPLE_TABLES + case MRT6_TABLE: + { + u32 v; + + if (optlen != sizeof(u32)) + return -EINVAL; + if (get_user(v, (u32 __user *)optval)) + return -EFAULT; + if (sk == mrt->mroute6_sk) + return -EBUSY; + + rtnl_lock(); + ret = 0; + if (!ip6mr_new_table(net, v)) + ret = -ENOMEM; + raw6_sk(sk)->ip6mr_table = v; + rtnl_unlock(); + return ret; + } +#endif /* * Spurious command, or MRT6_VERSION which you cannot * set. @@ -1406,6 +1706,11 @@ int ip6_mroute_getsockopt(struct sock *sk, int optname, char __user *optval, int olr; int val; struct net *net = sock_net(sk); + struct mr6_table *mrt; + + mrt = ip6mr_get_table(net, raw6_sk(sk)->ip6mr_table ? : RT6_TABLE_DFLT); + if (mrt == NULL) + return -ENOENT; switch (optname) { case MRT6_VERSION: @@ -1413,11 +1718,11 @@ int ip6_mroute_getsockopt(struct sock *sk, int optname, char __user *optval, break; #ifdef CONFIG_IPV6_PIMSM_V2 case MRT6_PIM: - val = net->ipv6.mroute_do_pim; + val = mrt->mroute_do_pim; break; #endif case MRT6_ASSERT: - val = net->ipv6.mroute_do_assert; + val = mrt->mroute_do_assert; break; default: return -ENOPROTOOPT; @@ -1448,16 +1753,21 @@ int ip6mr_ioctl(struct sock *sk, int cmd, void __user *arg) struct mif_device *vif; struct mfc6_cache *c; struct net *net = sock_net(sk); + struct mr6_table *mrt; + + mrt = ip6mr_get_table(net, raw6_sk(sk)->ip6mr_table ? : RT6_TABLE_DFLT); + if (mrt == NULL) + return -ENOENT; switch (cmd) { case SIOCGETMIFCNT_IN6: if (copy_from_user(&vr, arg, sizeof(vr))) return -EFAULT; - if (vr.mifi >= net->ipv6.maxvif) + if (vr.mifi >= mrt->maxvif) return -EINVAL; read_lock(&mrt_lock); - vif = &net->ipv6.vif6_table[vr.mifi]; - if (MIF_EXISTS(net, vr.mifi)) { + vif = &mrt->vif6_table[vr.mifi]; + if (MIF_EXISTS(mrt, vr.mifi)) { vr.icount = vif->pkt_in; vr.ocount = vif->pkt_out; vr.ibytes = vif->bytes_in; @@ -1475,7 +1785,7 @@ int ip6mr_ioctl(struct sock *sk, int cmd, void __user *arg) return -EFAULT; read_lock(&mrt_lock); - c = ip6mr_cache_find(net, &sr.src.sin6_addr, &sr.grp.sin6_addr); + c = ip6mr_cache_find(mrt, &sr.src.sin6_addr, &sr.grp.sin6_addr); if (c) { sr.pktcnt = c->mfc_un.res.pkt; sr.bytecnt = c->mfc_un.res.bytes; @@ -1505,11 +1815,11 @@ static inline int ip6mr_forward2_finish(struct sk_buff *skb) * Processing handlers for ip6mr_forward */ -static int ip6mr_forward2(struct sk_buff *skb, struct mfc6_cache *c, int vifi) +static int ip6mr_forward2(struct net *net, struct mr6_table *mrt, + struct sk_buff *skb, struct mfc6_cache *c, int vifi) { struct ipv6hdr *ipv6h; - struct net *net = mfc6_net(c); - struct mif_device *vif = &net->ipv6.vif6_table[vifi]; + struct mif_device *vif = &mrt->vif6_table[vifi]; struct net_device *dev; struct dst_entry *dst; struct flowi fl; @@ -1523,7 +1833,7 @@ static int ip6mr_forward2(struct sk_buff *skb, struct mfc6_cache *c, int vifi) vif->bytes_out += skb->len; vif->dev->stats.tx_bytes += skb->len; vif->dev->stats.tx_packets++; - ip6mr_cache_report(net, skb, vifi, MRT6MSG_WHOLEPKT); + ip6mr_cache_report(mrt, skb, vifi, MRT6MSG_WHOLEPKT); goto out_free; } #endif @@ -1578,22 +1888,22 @@ out_free: return 0; } -static int ip6mr_find_vif(struct net_device *dev) +static int ip6mr_find_vif(struct mr6_table *mrt, struct net_device *dev) { - struct net *net = dev_net(dev); int ct; - for (ct = net->ipv6.maxvif - 1; ct >= 0; ct--) { - if (net->ipv6.vif6_table[ct].dev == dev) + + for (ct = mrt->maxvif - 1; ct >= 0; ct--) { + if (mrt->vif6_table[ct].dev == dev) break; } return ct; } -static int ip6_mr_forward(struct sk_buff *skb, struct mfc6_cache *cache) +static int ip6_mr_forward(struct net *net, struct mr6_table *mrt, + struct sk_buff *skb, struct mfc6_cache *cache) { int psend = -1; int vif, ct; - struct net *net = mfc6_net(cache); vif = cache->mf6c_parent; cache->mfc_un.res.pkt++; @@ -1602,30 +1912,30 @@ static int ip6_mr_forward(struct sk_buff *skb, struct mfc6_cache *cache) /* * Wrong interface: drop packet and (maybe) send PIM assert. */ - if (net->ipv6.vif6_table[vif].dev != skb->dev) { + if (mrt->vif6_table[vif].dev != skb->dev) { int true_vifi; cache->mfc_un.res.wrong_if++; - true_vifi = ip6mr_find_vif(skb->dev); + true_vifi = ip6mr_find_vif(mrt, skb->dev); - if (true_vifi >= 0 && net->ipv6.mroute_do_assert && + if (true_vifi >= 0 && mrt->mroute_do_assert && /* pimsm uses asserts, when switching from RPT to SPT, so that we cannot check that packet arrived on an oif. It is bad, but otherwise we would need to move pretty large chunk of pimd to kernel. Ough... --ANK */ - (net->ipv6.mroute_do_pim || + (mrt->mroute_do_pim || cache->mfc_un.res.ttls[true_vifi] < 255) && time_after(jiffies, cache->mfc_un.res.last_assert + MFC_ASSERT_THRESH)) { cache->mfc_un.res.last_assert = jiffies; - ip6mr_cache_report(net, skb, true_vifi, MRT6MSG_WRONGMIF); + ip6mr_cache_report(mrt, skb, true_vifi, MRT6MSG_WRONGMIF); } goto dont_forward; } - net->ipv6.vif6_table[vif].pkt_in++; - net->ipv6.vif6_table[vif].bytes_in += skb->len; + mrt->vif6_table[vif].pkt_in++; + mrt->vif6_table[vif].bytes_in += skb->len; /* * Forward the frame @@ -1635,13 +1945,13 @@ static int ip6_mr_forward(struct sk_buff *skb, struct mfc6_cache *cache) if (psend != -1) { struct sk_buff *skb2 = skb_clone(skb, GFP_ATOMIC); if (skb2) - ip6mr_forward2(skb2, cache, psend); + ip6mr_forward2(net, mrt, skb2, cache, psend); } psend = ct; } } if (psend != -1) { - ip6mr_forward2(skb, cache, psend); + ip6mr_forward2(net, mrt, skb, cache, psend); return 0; } @@ -1659,9 +1969,19 @@ int ip6_mr_input(struct sk_buff *skb) { struct mfc6_cache *cache; struct net *net = dev_net(skb->dev); + struct mr6_table *mrt; + struct flowi fl = { + .iif = skb->dev->ifindex, + .mark = skb->mark, + }; + int err; + + err = ip6mr_fib_lookup(net, &fl, &mrt); + if (err < 0) + return err; read_lock(&mrt_lock); - cache = ip6mr_cache_find(net, + cache = ip6mr_cache_find(mrt, &ipv6_hdr(skb)->saddr, &ipv6_hdr(skb)->daddr); /* @@ -1670,9 +1990,9 @@ int ip6_mr_input(struct sk_buff *skb) if (cache == NULL) { int vif; - vif = ip6mr_find_vif(skb->dev); + vif = ip6mr_find_vif(mrt, skb->dev); if (vif >= 0) { - int err = ip6mr_cache_unresolved(net, vif, skb); + int err = ip6mr_cache_unresolved(mrt, vif, skb); read_unlock(&mrt_lock); return err; @@ -1682,7 +2002,7 @@ int ip6_mr_input(struct sk_buff *skb) return -ENODEV; } - ip6_mr_forward(skb, cache); + ip6_mr_forward(net, mrt, skb, cache); read_unlock(&mrt_lock); @@ -1690,12 +2010,11 @@ int ip6_mr_input(struct sk_buff *skb) } -static int -ip6mr_fill_mroute(struct sk_buff *skb, struct mfc6_cache *c, struct rtmsg *rtm) +static int __ip6mr_fill_mroute(struct mr6_table *mrt, struct sk_buff *skb, + struct mfc6_cache *c, struct rtmsg *rtm) { int ct; struct rtnexthop *nhp; - struct net *net = mfc6_net(c); u8 *b = skb_tail_pointer(skb); struct rtattr *mp_head; @@ -1703,19 +2022,19 @@ ip6mr_fill_mroute(struct sk_buff *skb, struct mfc6_cache *c, struct rtmsg *rtm) if (c->mf6c_parent > MAXMIFS) return -ENOENT; - if (MIF_EXISTS(net, c->mf6c_parent)) - RTA_PUT(skb, RTA_IIF, 4, &net->ipv6.vif6_table[c->mf6c_parent].dev->ifindex); + if (MIF_EXISTS(mrt, c->mf6c_parent)) + RTA_PUT(skb, RTA_IIF, 4, &mrt->vif6_table[c->mf6c_parent].dev->ifindex); mp_head = (struct rtattr *)skb_put(skb, RTA_LENGTH(0)); for (ct = c->mfc_un.res.minvif; ct < c->mfc_un.res.maxvif; ct++) { - if (MIF_EXISTS(net, ct) && c->mfc_un.res.ttls[ct] < 255) { + if (MIF_EXISTS(mrt, ct) && c->mfc_un.res.ttls[ct] < 255) { if (skb_tailroom(skb) < RTA_ALIGN(RTA_ALIGN(sizeof(*nhp)) + 4)) goto rtattr_failure; nhp = (struct rtnexthop *)skb_put(skb, RTA_ALIGN(sizeof(*nhp))); nhp->rtnh_flags = 0; nhp->rtnh_hops = c->mfc_un.res.ttls[ct]; - nhp->rtnh_ifindex = net->ipv6.vif6_table[ct].dev->ifindex; + nhp->rtnh_ifindex = mrt->vif6_table[ct].dev->ifindex; nhp->rtnh_len = sizeof(*nhp); } } @@ -1733,11 +2052,16 @@ int ip6mr_get_route(struct net *net, struct sk_buff *skb, struct rtmsg *rtm, int nowait) { int err; + struct mr6_table *mrt; struct mfc6_cache *cache; struct rt6_info *rt = (struct rt6_info *)skb_dst(skb); + mrt = ip6mr_get_table(net, RT6_TABLE_DFLT); + if (mrt == NULL) + return -ENOENT; + read_lock(&mrt_lock); - cache = ip6mr_cache_find(net, &rt->rt6i_src.addr, &rt->rt6i_dst.addr); + cache = ip6mr_cache_find(mrt, &rt->rt6i_src.addr, &rt->rt6i_dst.addr); if (!cache) { struct sk_buff *skb2; @@ -1751,7 +2075,7 @@ int ip6mr_get_route(struct net *net, } dev = skb->dev; - if (dev == NULL || (vif = ip6mr_find_vif(dev)) < 0) { + if (dev == NULL || (vif = ip6mr_find_vif(mrt, dev)) < 0) { read_unlock(&mrt_lock); return -ENODEV; } @@ -1780,7 +2104,7 @@ int ip6mr_get_route(struct net *net, ipv6_addr_copy(&iph->saddr, &rt->rt6i_src.addr); ipv6_addr_copy(&iph->daddr, &rt->rt6i_dst.addr); - err = ip6mr_cache_unresolved(net, vif, skb2); + err = ip6mr_cache_unresolved(mrt, vif, skb2); read_unlock(&mrt_lock); return err; @@ -1789,8 +2113,88 @@ int ip6mr_get_route(struct net *net, if (!nowait && (rtm->rtm_flags&RTM_F_NOTIFY)) cache->mfc_flags |= MFC_NOTIFY; - err = ip6mr_fill_mroute(skb, cache, rtm); + err = __ip6mr_fill_mroute(mrt, skb, cache, rtm); read_unlock(&mrt_lock); return err; } +static int ip6mr_fill_mroute(struct mr6_table *mrt, struct sk_buff *skb, + u32 pid, u32 seq, struct mfc6_cache *c) +{ + struct nlmsghdr *nlh; + struct rtmsg *rtm; + + nlh = nlmsg_put(skb, pid, seq, RTM_NEWROUTE, sizeof(*rtm), NLM_F_MULTI); + if (nlh == NULL) + return -EMSGSIZE; + + rtm = nlmsg_data(nlh); + rtm->rtm_family = RTNL_FAMILY_IPMR; + rtm->rtm_dst_len = 128; + rtm->rtm_src_len = 128; + rtm->rtm_tos = 0; + rtm->rtm_table = mrt->id; + NLA_PUT_U32(skb, RTA_TABLE, mrt->id); + rtm->rtm_scope = RT_SCOPE_UNIVERSE; + rtm->rtm_protocol = RTPROT_UNSPEC; + rtm->rtm_flags = 0; + + NLA_PUT(skb, RTA_SRC, 16, &c->mf6c_origin); + NLA_PUT(skb, RTA_DST, 16, &c->mf6c_mcastgrp); + + if (__ip6mr_fill_mroute(mrt, skb, c, rtm) < 0) + goto nla_put_failure; + + return nlmsg_end(skb, nlh); + +nla_put_failure: + nlmsg_cancel(skb, nlh); + return -EMSGSIZE; +} + +static int ip6mr_rtm_dumproute(struct sk_buff *skb, struct netlink_callback *cb) +{ + struct net *net = sock_net(skb->sk); + struct mr6_table *mrt; + struct mfc6_cache *mfc; + unsigned int t = 0, s_t; + unsigned int h = 0, s_h; + unsigned int e = 0, s_e; + + s_t = cb->args[0]; + s_h = cb->args[1]; + s_e = cb->args[2]; + + read_lock(&mrt_lock); + ip6mr_for_each_table(mrt, net) { + if (t < s_t) + goto next_table; + if (t > s_t) + s_h = 0; + for (h = s_h; h < MFC6_LINES; h++) { + list_for_each_entry(mfc, &mrt->mfc6_cache_array[h], list) { + if (e < s_e) + goto next_entry; + if (ip6mr_fill_mroute(mrt, skb, + NETLINK_CB(cb->skb).pid, + cb->nlh->nlmsg_seq, + mfc) < 0) + goto done; +next_entry: + e++; + } + e = s_e = 0; + } + s_h = 0; +next_table: + t++; + } +done: + read_unlock(&mrt_lock); + + cb->args[2] = e; + cb->args[1] = h; + cb->args[0] = t; + + return skb->len; +} diff --git a/net/llc/llc_sap.c b/net/llc/llc_sap.c index a432f0ec051c..94e7fca75b85 100644 --- a/net/llc/llc_sap.c +++ b/net/llc/llc_sap.c @@ -31,7 +31,7 @@ static int llc_mac_header_len(unsigned short devtype) case ARPHRD_ETHER: case ARPHRD_LOOPBACK: return sizeof(struct ethhdr); -#ifdef CONFIG_TR +#if defined(CONFIG_TR) || defined(CONFIG_TR_MODULE) case ARPHRD_IEEE802_TR: return sizeof(struct trh_hdr); #endif diff --git a/net/mac80211/Makefile b/net/mac80211/Makefile index 04420291e7ad..84b48ba8a77e 100644 --- a/net/mac80211/Makefile +++ b/net/mac80211/Makefile @@ -23,7 +23,8 @@ mac80211-y := \ key.o \ util.o \ wme.o \ - event.o + event.o \ + chan.o mac80211-$(CONFIG_MAC80211_LEDS) += led.o mac80211-$(CONFIG_MAC80211_DEBUGFS) += \ diff --git a/net/mac80211/cfg.c b/net/mac80211/cfg.c index ae37270a0633..c7000a6ca379 100644 --- a/net/mac80211/cfg.c +++ b/net/mac80211/cfg.c @@ -1162,15 +1162,39 @@ static int ieee80211_set_txq_params(struct wiphy *wiphy, } static int ieee80211_set_channel(struct wiphy *wiphy, + struct net_device *netdev, struct ieee80211_channel *chan, enum nl80211_channel_type channel_type) { struct ieee80211_local *local = wiphy_priv(wiphy); + struct ieee80211_sub_if_data *sdata = NULL; + + if (netdev) + sdata = IEEE80211_DEV_TO_SUB_IF(netdev); + + switch (ieee80211_get_channel_mode(local, NULL)) { + case CHAN_MODE_HOPPING: + return -EBUSY; + case CHAN_MODE_FIXED: + if (local->oper_channel != chan) + return -EBUSY; + if (!sdata && local->_oper_channel_type == channel_type) + return 0; + break; + case CHAN_MODE_UNDEFINED: + break; + } local->oper_channel = chan; - local->oper_channel_type = channel_type; - return ieee80211_hw_config(local, IEEE80211_CONF_CHANGE_CHANNEL); + if (!ieee80211_set_channel_type(local, sdata, channel_type)) + return -EBUSY; + + ieee80211_hw_config(local, IEEE80211_CONF_CHANGE_CHANNEL); + if (sdata && sdata->vif.type != NL80211_IFTYPE_MONITOR) + ieee80211_bss_info_change_notify(sdata, BSS_CHANGED_HT); + + return 0; } #ifdef CONFIG_PM @@ -1214,6 +1238,20 @@ static int ieee80211_auth(struct wiphy *wiphy, struct net_device *dev, static int ieee80211_assoc(struct wiphy *wiphy, struct net_device *dev, struct cfg80211_assoc_request *req) { + struct ieee80211_local *local = wiphy_priv(wiphy); + struct ieee80211_sub_if_data *sdata = IEEE80211_DEV_TO_SUB_IF(dev); + + switch (ieee80211_get_channel_mode(local, sdata)) { + case CHAN_MODE_HOPPING: + return -EBUSY; + case CHAN_MODE_FIXED: + if (local->oper_channel == req->bss->channel) + break; + return -EBUSY; + case CHAN_MODE_UNDEFINED: + break; + } + return ieee80211_mgd_assoc(IEEE80211_DEV_TO_SUB_IF(dev), req); } @@ -1236,8 +1274,22 @@ static int ieee80211_disassoc(struct wiphy *wiphy, struct net_device *dev, static int ieee80211_join_ibss(struct wiphy *wiphy, struct net_device *dev, struct cfg80211_ibss_params *params) { + struct ieee80211_local *local = wiphy_priv(wiphy); struct ieee80211_sub_if_data *sdata = IEEE80211_DEV_TO_SUB_IF(dev); + switch (ieee80211_get_channel_mode(local, sdata)) { + case CHAN_MODE_HOPPING: + return -EBUSY; + case CHAN_MODE_FIXED: + if (!params->channel_fixed) + return -EBUSY; + if (local->oper_channel == params->channel) + break; + return -EBUSY; + case CHAN_MODE_UNDEFINED: + break; + } + return ieee80211_ibss_join(sdata, params); } @@ -1366,7 +1418,7 @@ int __ieee80211_request_smps(struct ieee80211_sub_if_data *sdata, * association, there's no need to send an action frame. */ if (!sdata->u.mgd.associated || - sdata->local->oper_channel_type == NL80211_CHAN_NO_HT) { + sdata->vif.bss_conf.channel_type == NL80211_CHAN_NO_HT) { mutex_lock(&sdata->local->iflist_mtx); ieee80211_recalc_smps(sdata->local, sdata); mutex_unlock(&sdata->local->iflist_mtx); diff --git a/net/mac80211/chan.c b/net/mac80211/chan.c new file mode 100644 index 000000000000..5d218c530a4e --- /dev/null +++ b/net/mac80211/chan.c @@ -0,0 +1,127 @@ +/* + * mac80211 - channel management + */ + +#include <linux/nl80211.h> +#include "ieee80211_i.h" + +enum ieee80211_chan_mode +__ieee80211_get_channel_mode(struct ieee80211_local *local, + struct ieee80211_sub_if_data *ignore) +{ + struct ieee80211_sub_if_data *sdata; + + WARN_ON(!mutex_is_locked(&local->iflist_mtx)); + + list_for_each_entry(sdata, &local->interfaces, list) { + if (sdata == ignore) + continue; + + if (!ieee80211_sdata_running(sdata)) + continue; + + if (sdata->vif.type == NL80211_IFTYPE_MONITOR) + continue; + + if (sdata->vif.type == NL80211_IFTYPE_STATION && + !sdata->u.mgd.associated) + continue; + + if (sdata->vif.type == NL80211_IFTYPE_ADHOC) { + if (!sdata->u.ibss.ssid_len) + continue; + if (!sdata->u.ibss.fixed_channel) + return CHAN_MODE_HOPPING; + } + + if (sdata->vif.type == NL80211_IFTYPE_AP && + !sdata->u.ap.beacon) + continue; + + return CHAN_MODE_FIXED; + } + + return CHAN_MODE_UNDEFINED; +} + +enum ieee80211_chan_mode +ieee80211_get_channel_mode(struct ieee80211_local *local, + struct ieee80211_sub_if_data *ignore) +{ + enum ieee80211_chan_mode mode; + + mutex_lock(&local->iflist_mtx); + mode = __ieee80211_get_channel_mode(local, ignore); + mutex_unlock(&local->iflist_mtx); + + return mode; +} + +bool ieee80211_set_channel_type(struct ieee80211_local *local, + struct ieee80211_sub_if_data *sdata, + enum nl80211_channel_type chantype) +{ + struct ieee80211_sub_if_data *tmp; + enum nl80211_channel_type superchan = NL80211_CHAN_NO_HT; + bool result; + + mutex_lock(&local->iflist_mtx); + + list_for_each_entry(tmp, &local->interfaces, list) { + if (tmp == sdata) + continue; + + if (!ieee80211_sdata_running(tmp)) + continue; + + switch (tmp->vif.bss_conf.channel_type) { + case NL80211_CHAN_NO_HT: + case NL80211_CHAN_HT20: + superchan = tmp->vif.bss_conf.channel_type; + break; + case NL80211_CHAN_HT40PLUS: + WARN_ON(superchan == NL80211_CHAN_HT40MINUS); + superchan = NL80211_CHAN_HT40PLUS; + break; + case NL80211_CHAN_HT40MINUS: + WARN_ON(superchan == NL80211_CHAN_HT40PLUS); + superchan = NL80211_CHAN_HT40MINUS; + break; + } + } + + switch (superchan) { + case NL80211_CHAN_NO_HT: + case NL80211_CHAN_HT20: + /* + * allow any change that doesn't go to no-HT + * (if it already is no-HT no change is needed) + */ + if (chantype == NL80211_CHAN_NO_HT) + break; + superchan = chantype; + break; + case NL80211_CHAN_HT40PLUS: + case NL80211_CHAN_HT40MINUS: + /* allow smaller bandwidth and same */ + if (chantype == NL80211_CHAN_NO_HT) + break; + if (chantype == NL80211_CHAN_HT20) + break; + if (superchan == chantype) + break; + result = false; + goto out; + } + + local->_oper_channel_type = superchan; + + if (sdata) + sdata->vif.bss_conf.channel_type = chantype; + + result = true; + out: + mutex_unlock(&local->iflist_mtx); + + return result; +} diff --git a/net/mac80211/ibss.c b/net/mac80211/ibss.c index b72ee6435fa3..b2cc1fda6cfd 100644 --- a/net/mac80211/ibss.c +++ b/net/mac80211/ibss.c @@ -103,7 +103,7 @@ static void __ieee80211_sta_join_ibss(struct ieee80211_sub_if_data *sdata, sdata->drop_unencrypted = capability & WLAN_CAPABILITY_PRIVACY ? 1 : 0; local->oper_channel = chan; - local->oper_channel_type = NL80211_CHAN_NO_HT; + WARN_ON(!ieee80211_set_channel_type(local, sdata, NL80211_CHAN_NO_HT)); ieee80211_hw_config(local, IEEE80211_CONF_CHANGE_CHANNEL); sband = local->hw.wiphy->bands[chan->band]; @@ -911,7 +911,8 @@ int ieee80211_ibss_join(struct ieee80211_sub_if_data *sdata, /* fix ourselves to that channel now already */ if (params->channel_fixed) { sdata->local->oper_channel = params->channel; - sdata->local->oper_channel_type = NL80211_CHAN_NO_HT; + WARN_ON(!ieee80211_set_channel_type(sdata->local, sdata, + NL80211_CHAN_NO_HT)); } if (params->ie) { diff --git a/net/mac80211/ieee80211_i.h b/net/mac80211/ieee80211_i.h index cbaf4981e110..7ef7798d04cd 100644 --- a/net/mac80211/ieee80211_i.h +++ b/net/mac80211/ieee80211_i.h @@ -767,7 +767,7 @@ struct ieee80211_local { enum mac80211_scan_state next_scan_state; struct delayed_work scan_work; struct ieee80211_sub_if_data *scan_sdata; - enum nl80211_channel_type oper_channel_type; + enum nl80211_channel_type _oper_channel_type; struct ieee80211_channel *oper_channel, *csa_channel; /* Temporary remain-on-channel for off-channel operations */ @@ -1228,6 +1228,20 @@ int ieee80211_wk_remain_on_channel(struct ieee80211_sub_if_data *sdata, int ieee80211_wk_cancel_remain_on_channel( struct ieee80211_sub_if_data *sdata, u64 cookie); +/* channel management */ +enum ieee80211_chan_mode { + CHAN_MODE_UNDEFINED, + CHAN_MODE_HOPPING, + CHAN_MODE_FIXED, +}; + +enum ieee80211_chan_mode +ieee80211_get_channel_mode(struct ieee80211_local *local, + struct ieee80211_sub_if_data *ignore); +bool ieee80211_set_channel_type(struct ieee80211_local *local, + struct ieee80211_sub_if_data *sdata, + enum nl80211_channel_type chantype); + #ifdef CONFIG_MAC80211_NOINLINE #define debug_noinline noinline #else diff --git a/net/mac80211/main.c b/net/mac80211/main.c index bd632e1ee2c5..22a384dfab65 100644 --- a/net/mac80211/main.c +++ b/net/mac80211/main.c @@ -111,7 +111,7 @@ int ieee80211_hw_config(struct ieee80211_local *local, u32 changed) channel_type = local->tmp_channel_type; } else { chan = local->oper_channel; - channel_type = local->oper_channel_type; + channel_type = local->_oper_channel_type; } if (chan != local->hw.conf.channel || diff --git a/net/mac80211/mlme.c b/net/mac80211/mlme.c index 358226f63b81..3093e46273c3 100644 --- a/net/mac80211/mlme.c +++ b/net/mac80211/mlme.c @@ -137,11 +137,14 @@ static u32 ieee80211_enable_ht(struct ieee80211_sub_if_data *sdata, struct sta_info *sta; u32 changed = 0; u16 ht_opmode; - bool enable_ht = true, ht_changed; + bool enable_ht = true; + enum nl80211_channel_type prev_chantype; enum nl80211_channel_type channel_type = NL80211_CHAN_NO_HT; sband = local->hw.wiphy->bands[local->hw.conf.channel->band]; + prev_chantype = sdata->vif.bss_conf.channel_type; + /* HT is not supported */ if (!sband->ht_cap.ht_supported) enable_ht = false; @@ -172,38 +175,37 @@ static u32 ieee80211_enable_ht(struct ieee80211_sub_if_data *sdata, } } - ht_changed = conf_is_ht(&local->hw.conf) != enable_ht || - channel_type != local->hw.conf.channel_type; - if (local->tmp_channel) local->tmp_channel_type = channel_type; - local->oper_channel_type = channel_type; - if (ht_changed) { - /* channel_type change automatically detected */ - ieee80211_hw_config(local, 0); + if (!ieee80211_set_channel_type(local, sdata, channel_type)) { + /* can only fail due to HT40+/- mismatch */ + channel_type = NL80211_CHAN_HT20; + WARN_ON(!ieee80211_set_channel_type(local, sdata, channel_type)); + } + /* channel_type change automatically detected */ + ieee80211_hw_config(local, 0); + + if (prev_chantype != channel_type) { rcu_read_lock(); sta = sta_info_get(sdata, bssid); if (sta) rate_control_rate_update(local, sband, sta, IEEE80211_RC_HT_CHANGED, - local->oper_channel_type); + channel_type); rcu_read_unlock(); - } - - /* disable HT */ - if (!enable_ht) - return 0; + } ht_opmode = le16_to_cpu(hti->operation_mode); /* if bss configuration changed store the new one */ - if (!sdata->ht_opmode_valid || - sdata->vif.bss_conf.ht_operation_mode != ht_opmode) { + if (sdata->ht_opmode_valid != enable_ht || + sdata->vif.bss_conf.ht_operation_mode != ht_opmode || + prev_chantype != channel_type) { changed |= BSS_CHANGED_HT; sdata->vif.bss_conf.ht_operation_mode = ht_opmode; - sdata->ht_opmode_valid = true; + sdata->ht_opmode_valid = enable_ht; } return changed; @@ -866,7 +868,7 @@ static void ieee80211_set_disassoc(struct ieee80211_sub_if_data *sdata, ieee80211_set_wmm_default(sdata); /* channel(_type) changes are handled by ieee80211_hw_config */ - local->oper_channel_type = NL80211_CHAN_NO_HT; + WARN_ON(!ieee80211_set_channel_type(local, sdata, NL80211_CHAN_NO_HT)); /* on the next assoc, re-program HT parameters */ sdata->ht_opmode_valid = false; @@ -883,8 +885,8 @@ static void ieee80211_set_disassoc(struct ieee80211_sub_if_data *sdata, ieee80211_hw_config(local, config_changed); - /* And the BSSID changed -- not very interesting here */ - changed |= BSS_CHANGED_BSSID; + /* The BSSID (not really interesting) and HT changed */ + changed |= BSS_CHANGED_BSSID | BSS_CHANGED_HT; ieee80211_bss_info_change_notify(sdata, changed); if (remove_sta) @@ -2176,7 +2178,8 @@ int ieee80211_mgd_deauth(struct ieee80211_sub_if_data *sdata, continue; if (wk->type != IEEE80211_WORK_DIRECT_PROBE && - wk->type != IEEE80211_WORK_AUTH) + wk->type != IEEE80211_WORK_AUTH && + wk->type != IEEE80211_WORK_ASSOC) continue; if (memcmp(req->bss->bssid, wk->filter_ta, ETH_ALEN)) @@ -2266,7 +2269,7 @@ int ieee80211_mgd_action(struct ieee80211_sub_if_data *sdata, if ((chan != local->tmp_channel || channel_type != local->tmp_channel_type) && (chan != local->oper_channel || - channel_type != local->oper_channel_type)) + channel_type != local->_oper_channel_type)) return -EBUSY; skb = dev_alloc_skb(local->hw.extra_tx_headroom + len); diff --git a/net/mac80211/tx.c b/net/mac80211/tx.c index f3841f43249e..680bcb7093db 100644 --- a/net/mac80211/tx.c +++ b/net/mac80211/tx.c @@ -2251,8 +2251,9 @@ struct sk_buff *ieee80211_beacon_get_tim(struct ieee80211_hw *hw, info->control.vif = vif; - info->flags |= IEEE80211_TX_CTL_CLEAR_PS_FILT; - info->flags |= IEEE80211_TX_CTL_ASSIGN_SEQ; + info->flags |= IEEE80211_TX_CTL_CLEAR_PS_FILT | + IEEE80211_TX_CTL_ASSIGN_SEQ | + IEEE80211_TX_CTL_FIRST_FRAGMENT; out: rcu_read_unlock(); return skb; diff --git a/net/mac80211/util.c b/net/mac80211/util.c index 2b75b4fb68f4..5b79d552780a 100644 --- a/net/mac80211/util.c +++ b/net/mac80211/util.c @@ -1160,18 +1160,33 @@ int ieee80211_reconfig(struct ieee80211_local *local) /* Finally also reconfigure all the BSS information */ list_for_each_entry(sdata, &local->interfaces, list) { - u32 changed = ~0; + u32 changed; + if (!ieee80211_sdata_running(sdata)) continue; + + /* common change flags for all interface types */ + changed = BSS_CHANGED_ERP_CTS_PROT | + BSS_CHANGED_ERP_PREAMBLE | + BSS_CHANGED_ERP_SLOT | + BSS_CHANGED_HT | + BSS_CHANGED_BASIC_RATES | + BSS_CHANGED_BEACON_INT | + BSS_CHANGED_BSSID | + BSS_CHANGED_CQM; + switch (sdata->vif.type) { case NL80211_IFTYPE_STATION: - /* disable beacon change bits */ - changed &= ~(BSS_CHANGED_BEACON | - BSS_CHANGED_BEACON_ENABLED); - /* fall through */ + changed |= BSS_CHANGED_ASSOC; + ieee80211_bss_info_change_notify(sdata, changed); + break; case NL80211_IFTYPE_ADHOC: + changed |= BSS_CHANGED_IBSS; + /* fall through */ case NL80211_IFTYPE_AP: case NL80211_IFTYPE_MESH_POINT: + changed |= BSS_CHANGED_BEACON | + BSS_CHANGED_BEACON_ENABLED; ieee80211_bss_info_change_notify(sdata, changed); break; case NL80211_IFTYPE_WDS: diff --git a/net/netfilter/Kconfig b/net/netfilter/Kconfig index 673a6c8f0e95..e223f47b8bae 100644 --- a/net/netfilter/Kconfig +++ b/net/netfilter/Kconfig @@ -505,6 +505,7 @@ config NETFILTER_XT_TARGET_RATEEST config NETFILTER_XT_TARGET_TEE tristate '"TEE" - packet cloning to alternate destiantion' depends on NETFILTER_ADVANCED + depends on (IPV6 || IPV6=n) ---help--- This option adds a "TEE" target with which a packet can be cloned and this clone be rerouted to another nexthop. diff --git a/net/sctp/input.c b/net/sctp/input.c index 2a570184e5a9..ea2192444ce6 100644 --- a/net/sctp/input.c +++ b/net/sctp/input.c @@ -440,11 +440,25 @@ void sctp_icmp_proto_unreachable(struct sock *sk, { SCTP_DEBUG_PRINTK("%s\n", __func__); - sctp_do_sm(SCTP_EVENT_T_OTHER, - SCTP_ST_OTHER(SCTP_EVENT_ICMP_PROTO_UNREACH), - asoc->state, asoc->ep, asoc, t, - GFP_ATOMIC); + if (sock_owned_by_user(sk)) { + if (timer_pending(&t->proto_unreach_timer)) + return; + else { + if (!mod_timer(&t->proto_unreach_timer, + jiffies + (HZ/20))) + sctp_association_hold(asoc); + } + + } else { + if (timer_pending(&t->proto_unreach_timer) && + del_timer(&t->proto_unreach_timer)) + sctp_association_put(asoc); + sctp_do_sm(SCTP_EVENT_T_OTHER, + SCTP_ST_OTHER(SCTP_EVENT_ICMP_PROTO_UNREACH), + asoc->state, asoc->ep, asoc, t, + GFP_ATOMIC); + } } /* Common lookup code for icmp/icmpv6 error handler. */ diff --git a/net/sctp/sm_sideeffect.c b/net/sctp/sm_sideeffect.c index 3b7230ef77c2..22e670200449 100644 --- a/net/sctp/sm_sideeffect.c +++ b/net/sctp/sm_sideeffect.c @@ -397,6 +397,41 @@ out_unlock: sctp_transport_put(transport); } +/* Handle the timeout of the ICMP protocol unreachable timer. Trigger + * the correct state machine transition that will close the association. + */ +void sctp_generate_proto_unreach_event(unsigned long data) +{ + struct sctp_transport *transport = (struct sctp_transport *) data; + struct sctp_association *asoc = transport->asoc; + + sctp_bh_lock_sock(asoc->base.sk); + if (sock_owned_by_user(asoc->base.sk)) { + SCTP_DEBUG_PRINTK("%s:Sock is busy.\n", __func__); + + /* Try again later. */ + if (!mod_timer(&transport->proto_unreach_timer, + jiffies + (HZ/20))) + sctp_association_hold(asoc); + goto out_unlock; + } + + /* Is this structure just waiting around for us to actually + * get destroyed? + */ + if (asoc->base.dead) + goto out_unlock; + + sctp_do_sm(SCTP_EVENT_T_OTHER, + SCTP_ST_OTHER(SCTP_EVENT_ICMP_PROTO_UNREACH), + asoc->state, asoc->ep, asoc, transport, GFP_ATOMIC); + +out_unlock: + sctp_bh_unlock_sock(asoc->base.sk); + sctp_association_put(asoc); +} + + /* Inject a SACK Timeout event into the state machine. */ static void sctp_generate_sack_event(unsigned long data) { diff --git a/net/sctp/transport.c b/net/sctp/transport.c index fccf4947aff1..d67501f92ca3 100644 --- a/net/sctp/transport.c +++ b/net/sctp/transport.c @@ -92,6 +92,8 @@ static struct sctp_transport *sctp_transport_init(struct sctp_transport *peer, (unsigned long)peer); setup_timer(&peer->hb_timer, sctp_generate_heartbeat_event, (unsigned long)peer); + setup_timer(&peer->proto_unreach_timer, + sctp_generate_proto_unreach_event, (unsigned long)peer); /* Initialize the 64-bit random nonce sent with heartbeat. */ get_random_bytes(&peer->hb_nonce, sizeof(peer->hb_nonce)); diff --git a/net/sunrpc/auth.c b/net/sunrpc/auth.c index f394fc190a49..95afe79dd9d7 100644 --- a/net/sunrpc/auth.c +++ b/net/sunrpc/auth.c @@ -237,7 +237,7 @@ rpcauth_prune_expired(struct list_head *free, int nr_to_scan) list_for_each_entry_safe(cred, next, &cred_unused, cr_lru) { /* Enforce a 60 second garbage collection moratorium */ - if (time_in_range_open(cred->cr_expire, expired, jiffies) && + if (time_in_range(cred->cr_expire, expired, jiffies) && test_bit(RPCAUTH_CRED_HASHED, &cred->cr_flags) != 0) continue; diff --git a/net/tipc/addr.c b/net/tipc/addr.c index e5207a11edf6..c048543ffbeb 100644 --- a/net/tipc/addr.c +++ b/net/tipc/addr.c @@ -92,3 +92,35 @@ int tipc_addr_node_valid(u32 addr) return (tipc_addr_domain_valid(addr) && tipc_node(addr)); } +int tipc_in_scope(u32 domain, u32 addr) +{ + if (!domain || (domain == addr)) + return 1; + if (domain == (addr & 0xfffff000u)) /* domain <Z.C.0> */ + return 1; + if (domain == (addr & 0xff000000u)) /* domain <Z.0.0> */ + return 1; + return 0; +} + +/** + * tipc_addr_scope - convert message lookup domain to a 2-bit scope value + */ + +int tipc_addr_scope(u32 domain) +{ + if (likely(!domain)) + return TIPC_ZONE_SCOPE; + if (tipc_node(domain)) + return TIPC_NODE_SCOPE; + if (tipc_cluster(domain)) + return TIPC_CLUSTER_SCOPE; + return TIPC_ZONE_SCOPE; +} + +char *tipc_addr_string_fill(char *string, u32 addr) +{ + snprintf(string, 16, "<%u.%u.%u>", + tipc_zone(addr), tipc_cluster(addr), tipc_node(addr)); + return string; +} diff --git a/net/tipc/addr.h b/net/tipc/addr.h index 3ba67e6ce03e..c1cc5724d8cc 100644 --- a/net/tipc/addr.h +++ b/net/tipc/addr.h @@ -67,32 +67,6 @@ static inline int may_route(u32 addr) return(addr ^ tipc_own_addr) >> 11; } -static inline int in_scope(u32 domain, u32 addr) -{ - if (!domain || (domain == addr)) - return 1; - if (domain == (addr & 0xfffff000u)) /* domain <Z.C.0> */ - return 1; - if (domain == (addr & 0xff000000u)) /* domain <Z.0.0> */ - return 1; - return 0; -} - -/** - * addr_scope - convert message lookup domain to equivalent 2-bit scope value - */ - -static inline int addr_scope(u32 domain) -{ - if (likely(!domain)) - return TIPC_ZONE_SCOPE; - if (tipc_node(domain)) - return TIPC_NODE_SCOPE; - if (tipc_cluster(domain)) - return TIPC_CLUSTER_SCOPE; - return TIPC_ZONE_SCOPE; -} - /** * addr_domain - convert 2-bit scope value to equivalent message lookup domain * @@ -110,14 +84,9 @@ static inline int addr_domain(int sc) return tipc_addr(tipc_zone(tipc_own_addr), 0, 0); } -static inline char *addr_string_fill(char *string, u32 addr) -{ - snprintf(string, 16, "<%u.%u.%u>", - tipc_zone(addr), tipc_cluster(addr), tipc_node(addr)); - return string; -} - int tipc_addr_domain_valid(u32); int tipc_addr_node_valid(u32 addr); - +int tipc_in_scope(u32 domain, u32 addr); +int tipc_addr_scope(u32 domain); +char *tipc_addr_string_fill(char *string, u32 addr); #endif diff --git a/net/tipc/bcast.c b/net/tipc/bcast.c index 90a051912c03..a008c6689305 100644 --- a/net/tipc/bcast.c +++ b/net/tipc/bcast.c @@ -119,7 +119,7 @@ static struct bclink *bclink = NULL; static struct link *bcl = NULL; static DEFINE_SPINLOCK(bc_lock); -const char tipc_bclink_name[] = "multicast-link"; +const char tipc_bclink_name[] = "broadcast-link"; static u32 buf_seqno(struct sk_buff *buf) @@ -275,7 +275,7 @@ static void bclink_send_nack(struct tipc_node *n_ptr) buf = buf_acquire(INT_H_SIZE); if (buf) { msg = buf_msg(buf); - msg_init(msg, BCAST_PROTOCOL, STATE_MSG, + tipc_msg_init(msg, BCAST_PROTOCOL, STATE_MSG, INT_H_SIZE, n_ptr->addr); msg_set_mc_netid(msg, tipc_net_id); msg_set_bcast_ack(msg, mod(n_ptr->bclink.last_in)); @@ -822,3 +822,113 @@ void tipc_bclink_stop(void) spin_unlock_bh(&bc_lock); } + +/** + * tipc_nmap_add - add a node to a node map + */ + +void tipc_nmap_add(struct tipc_node_map *nm_ptr, u32 node) +{ + int n = tipc_node(node); + int w = n / WSIZE; + u32 mask = (1 << (n % WSIZE)); + + if ((nm_ptr->map[w] & mask) == 0) { + nm_ptr->count++; + nm_ptr->map[w] |= mask; + } +} + +/** + * tipc_nmap_remove - remove a node from a node map + */ + +void tipc_nmap_remove(struct tipc_node_map *nm_ptr, u32 node) +{ + int n = tipc_node(node); + int w = n / WSIZE; + u32 mask = (1 << (n % WSIZE)); + + if ((nm_ptr->map[w] & mask) != 0) { + nm_ptr->map[w] &= ~mask; + nm_ptr->count--; + } +} + +/** + * tipc_nmap_diff - find differences between node maps + * @nm_a: input node map A + * @nm_b: input node map B + * @nm_diff: output node map A-B (i.e. nodes of A that are not in B) + */ + +void tipc_nmap_diff(struct tipc_node_map *nm_a, struct tipc_node_map *nm_b, + struct tipc_node_map *nm_diff) +{ + int stop = ARRAY_SIZE(nm_a->map); + int w; + int b; + u32 map; + + memset(nm_diff, 0, sizeof(*nm_diff)); + for (w = 0; w < stop; w++) { + map = nm_a->map[w] ^ (nm_a->map[w] & nm_b->map[w]); + nm_diff->map[w] = map; + if (map != 0) { + for (b = 0 ; b < WSIZE; b++) { + if (map & (1 << b)) + nm_diff->count++; + } + } + } +} + +/** + * tipc_port_list_add - add a port to a port list, ensuring no duplicates + */ + +void tipc_port_list_add(struct port_list *pl_ptr, u32 port) +{ + struct port_list *item = pl_ptr; + int i; + int item_sz = PLSIZE; + int cnt = pl_ptr->count; + + for (; ; cnt -= item_sz, item = item->next) { + if (cnt < PLSIZE) + item_sz = cnt; + for (i = 0; i < item_sz; i++) + if (item->ports[i] == port) + return; + if (i < PLSIZE) { + item->ports[i] = port; + pl_ptr->count++; + return; + } + if (!item->next) { + item->next = kmalloc(sizeof(*item), GFP_ATOMIC); + if (!item->next) { + warn("Incomplete multicast delivery, no memory\n"); + return; + } + item->next->next = NULL; + } + } +} + +/** + * tipc_port_list_free - free dynamically created entries in port_list chain + * + */ + +void tipc_port_list_free(struct port_list *pl_ptr) +{ + struct port_list *item; + struct port_list *next; + + for (item = pl_ptr->next; item; item = next) { + next = item->next; + kfree(item); + } +} + diff --git a/net/tipc/bcast.h b/net/tipc/bcast.h index 4c1771e95c99..e8c2b81658c7 100644 --- a/net/tipc/bcast.h +++ b/net/tipc/bcast.h @@ -72,41 +72,11 @@ struct tipc_node; extern const char tipc_bclink_name[]; +void tipc_nmap_add(struct tipc_node_map *nm_ptr, u32 node); +void tipc_nmap_remove(struct tipc_node_map *nm_ptr, u32 node); /** - * nmap_add - add a node to a node map - */ - -static inline void tipc_nmap_add(struct tipc_node_map *nm_ptr, u32 node) -{ - int n = tipc_node(node); - int w = n / WSIZE; - u32 mask = (1 << (n % WSIZE)); - - if ((nm_ptr->map[w] & mask) == 0) { - nm_ptr->count++; - nm_ptr->map[w] |= mask; - } -} - -/** - * nmap_remove - remove a node from a node map - */ - -static inline void tipc_nmap_remove(struct tipc_node_map *nm_ptr, u32 node) -{ - int n = tipc_node(node); - int w = n / WSIZE; - u32 mask = (1 << (n % WSIZE)); - - if ((nm_ptr->map[w] & mask) != 0) { - nm_ptr->map[w] &= ~mask; - nm_ptr->count--; - } -} - -/** - * nmap_equal - test for equality of node maps + * tipc_nmap_equal - test for equality of node maps */ static inline int tipc_nmap_equal(struct tipc_node_map *nm_a, struct tipc_node_map *nm_b) @@ -114,84 +84,11 @@ static inline int tipc_nmap_equal(struct tipc_node_map *nm_a, struct tipc_node_m return !memcmp(nm_a, nm_b, sizeof(*nm_a)); } -/** - * nmap_diff - find differences between node maps - * @nm_a: input node map A - * @nm_b: input node map B - * @nm_diff: output node map A-B (i.e. nodes of A that are not in B) - */ - -static inline void tipc_nmap_diff(struct tipc_node_map *nm_a, struct tipc_node_map *nm_b, - struct tipc_node_map *nm_diff) -{ - int stop = ARRAY_SIZE(nm_a->map); - int w; - int b; - u32 map; - - memset(nm_diff, 0, sizeof(*nm_diff)); - for (w = 0; w < stop; w++) { - map = nm_a->map[w] ^ (nm_a->map[w] & nm_b->map[w]); - nm_diff->map[w] = map; - if (map != 0) { - for (b = 0 ; b < WSIZE; b++) { - if (map & (1 << b)) - nm_diff->count++; - } - } - } -} - -/** - * port_list_add - add a port to a port list, ensuring no duplicates - */ - -static inline void tipc_port_list_add(struct port_list *pl_ptr, u32 port) -{ - struct port_list *item = pl_ptr; - int i; - int item_sz = PLSIZE; - int cnt = pl_ptr->count; - - for (; ; cnt -= item_sz, item = item->next) { - if (cnt < PLSIZE) - item_sz = cnt; - for (i = 0; i < item_sz; i++) - if (item->ports[i] == port) - return; - if (i < PLSIZE) { - item->ports[i] = port; - pl_ptr->count++; - return; - } - if (!item->next) { - item->next = kmalloc(sizeof(*item), GFP_ATOMIC); - if (!item->next) { - warn("Incomplete multicast delivery, no memory\n"); - return; - } - item->next->next = NULL; - } - } -} - -/** - * port_list_free - free dynamically created entries in port_list chain - * - * Note: First item is on stack, so it doesn't need to be released - */ - -static inline void tipc_port_list_free(struct port_list *pl_ptr) -{ - struct port_list *item; - struct port_list *next; - - for (item = pl_ptr->next; item; item = next) { - next = item->next; - kfree(item); - } -} +void tipc_nmap_diff(struct tipc_node_map *nm_a, struct tipc_node_map *nm_b, + struct tipc_node_map *nm_diff); +void tipc_port_list_add(struct port_list *pl_ptr, u32 port); +void tipc_port_list_free(struct port_list *pl_ptr); int tipc_bclink_init(void); void tipc_bclink_stop(void); diff --git a/net/tipc/bearer.c b/net/tipc/bearer.c index 78091375ca12..52ae17b2583e 100644 --- a/net/tipc/bearer.c +++ b/net/tipc/bearer.c @@ -467,6 +467,18 @@ int tipc_bearer_resolve_congestion(struct bearer *b_ptr, struct link *l_ptr) return res; } +/** + * tipc_bearer_congested - determines if bearer is currently congested + */ + +int tipc_bearer_congested(struct bearer *b_ptr, struct link *l_ptr) +{ + if (unlikely(b_ptr->publ.blocked)) + return 1; + if (likely(list_empty(&b_ptr->cong_links))) + return 0; + return !tipc_bearer_resolve_congestion(b_ptr, l_ptr); +} /** * tipc_enable_bearer - enable bearer with the given name @@ -493,7 +505,7 @@ int tipc_enable_bearer(const char *name, u32 bcast_scope, u32 priority) return -EINVAL; } if (!tipc_addr_domain_valid(bcast_scope) || - !in_scope(bcast_scope, tipc_own_addr)) { + !tipc_in_scope(bcast_scope, tipc_own_addr)) { warn("Bearer <%s> rejected, illegal broadcast scope\n", name); return -EINVAL; } @@ -571,7 +583,7 @@ restart: spin_lock_init(&b_ptr->publ.lock); write_unlock_bh(&tipc_net_lock); info("Enabled bearer <%s>, discovery domain %s, priority %u\n", - name, addr_string_fill(addr_string, bcast_scope), priority); + name, tipc_addr_string_fill(addr_string, bcast_scope), priority); return 0; failed: write_unlock_bh(&tipc_net_lock); diff --git a/net/tipc/bearer.h b/net/tipc/bearer.h index 000228e93f9e..a850b389663e 100644 --- a/net/tipc/bearer.h +++ b/net/tipc/bearer.h @@ -125,6 +125,7 @@ void tipc_bearer_remove_dest(struct bearer *b_ptr, u32 dest); void tipc_bearer_schedule(struct bearer *b_ptr, struct link *l_ptr); struct bearer *tipc_bearer_find_interface(const char *if_name); int tipc_bearer_resolve_congestion(struct bearer *b_ptr, struct link *l_ptr); +int tipc_bearer_congested(struct bearer *b_ptr, struct link *l_ptr); int tipc_bearer_init(void); void tipc_bearer_stop(void); void tipc_bearer_lock_push(struct bearer *b_ptr); @@ -154,17 +155,4 @@ static inline int tipc_bearer_send(struct bearer *b_ptr, struct sk_buff *buf, return !b_ptr->media->send_msg(buf, &b_ptr->publ, dest); } -/** - * tipc_bearer_congested - determines if bearer is currently congested - */ - -static inline int tipc_bearer_congested(struct bearer *b_ptr, struct link *l_ptr) -{ - if (unlikely(b_ptr->publ.blocked)) - return 1; - if (likely(list_empty(&b_ptr->cong_links))) - return 0; - return !tipc_bearer_resolve_congestion(b_ptr, l_ptr); -} - -#endif +#endif /* _TIPC_BEARER_H */ diff --git a/net/tipc/cluster.c b/net/tipc/cluster.c index a7eac00cd363..e68f705381bc 100644 --- a/net/tipc/cluster.c +++ b/net/tipc/cluster.c @@ -238,7 +238,7 @@ static struct sk_buff *tipc_cltr_prepare_routing_msg(u32 data_size, u32 dest) if (buf) { msg = buf_msg(buf); memset((char *)msg, 0, size); - msg_init(msg, ROUTE_DISTRIBUTOR, 0, INT_H_SIZE, dest); + tipc_msg_init(msg, ROUTE_DISTRIBUTOR, 0, INT_H_SIZE, dest); } return buf; } diff --git a/net/tipc/config.c b/net/tipc/config.c index ca3544d030c7..961d1b097146 100644 --- a/net/tipc/config.c +++ b/net/tipc/config.c @@ -56,9 +56,6 @@ struct subscr_data { struct manager { u32 user_ref; u32 port_ref; - u32 subscr_ref; - u32 link_subscriptions; - struct list_head link_subscribers; }; static struct manager mng = { 0}; @@ -70,12 +67,6 @@ static int req_tlv_space; /* request message TLV area size */ static int rep_headroom; /* reply message headroom to use */ -void tipc_cfg_link_event(u32 addr, char *name, int up) -{ - /* TIPC DOESN'T HANDLE LINK EVENT SUBSCRIPTIONS AT THE MOMENT */ -} - - struct sk_buff *tipc_cfg_reply_alloc(int payload_size) { struct sk_buff *buf; @@ -130,12 +121,24 @@ struct sk_buff *tipc_cfg_reply_string_type(u16 tlv_type, char *string) } - - #if 0 /* Now obsolete code for handling commands not yet implemented the new way */ +/* + * Some of this code assumed that the manager structure contains two added + * fields: + * u32 link_subscriptions; + * struct list_head link_subscribers; + * which are currently not present. These fields may need to be re-introduced + * if and when support for link subscriptions is added. + */ + +void tipc_cfg_link_event(u32 addr, char *name, int up) +{ + /* TIPC DOESN'T HANDLE LINK EVENT SUBSCRIPTIONS AT THE MOMENT */ +} + int tipc_cfg_cmd(const struct tipc_cmd_msg * msg, char *data, u32 sz, @@ -243,13 +246,48 @@ static void cfg_cmd_event(struct tipc_cmd_msg *msg, default: rv = tipc_cfg_cmd(msg, data, sz, (u32 *)&msg_sect[1].iov_len, orig); } - exit: +exit: rmsg.result_len = htonl(msg_sect[1].iov_len); rmsg.retval = htonl(rv); tipc_cfg_respond(msg_sect, 2u, orig); } #endif +#define MAX_STATS_INFO 2000 + +static struct sk_buff *tipc_show_stats(void) +{ + struct sk_buff *buf; + struct tlv_desc *rep_tlv; + struct print_buf pb; + int str_len; + u32 value; + + if (!TLV_CHECK(req_tlv_area, req_tlv_space, TIPC_TLV_UNSIGNED)) + return tipc_cfg_reply_error_string(TIPC_CFG_TLV_ERROR); + + value = ntohl(*(u32 *)TLV_DATA(req_tlv_area)); + if (value != 0) + return tipc_cfg_reply_error_string("unsupported argument"); + + buf = tipc_cfg_reply_alloc(TLV_SPACE(MAX_STATS_INFO)); + if (buf == NULL) + return NULL; + + rep_tlv = (struct tlv_desc *)buf->data; + tipc_printbuf_init(&pb, (char *)TLV_DATA(rep_tlv), MAX_STATS_INFO); + + tipc_printf(&pb, "TIPC version " TIPC_MOD_VER "\n"); + + /* Use additional tipc_printf()'s to return more info ... */ + + str_len = tipc_printbuf_validate(&pb); + skb_put(buf, TLV_SPACE(str_len)); + TLV_SET(rep_tlv, TIPC_TLV_ULTRA_STRING, NULL, str_len); + + return buf; +} + static struct sk_buff *cfg_enable_bearer(void) { struct tipc_bearer_config *args; @@ -533,6 +571,9 @@ struct sk_buff *tipc_cfg_do_cmd(u32 orig_node, u16 cmd, const void *request_area case TIPC_CMD_DUMP_LOG: rep_tlv_buf = tipc_log_dump(); break; + case TIPC_CMD_SHOW_STATS: + rep_tlv_buf = tipc_show_stats(); + break; case TIPC_CMD_SET_LINK_TOL: case TIPC_CMD_SET_LINK_PRI: case TIPC_CMD_SET_LINK_WINDOW: @@ -667,9 +708,6 @@ int tipc_cfg_init(void) struct tipc_name_seq seq; int res; - memset(&mng, 0, sizeof(mng)); - INIT_LIST_HEAD(&mng.link_subscribers); - res = tipc_attach(&mng.user_ref, NULL, NULL); if (res) goto failed; diff --git a/net/tipc/core.c b/net/tipc/core.c index 4e84c8431f32..696468117985 100644 --- a/net/tipc/core.c +++ b/net/tipc/core.c @@ -49,8 +49,6 @@ #include "config.h" -#define TIPC_MOD_VER "2.0.0" - #ifndef CONFIG_TIPC_ZONES #define CONFIG_TIPC_ZONES 3 #endif @@ -104,6 +102,30 @@ int tipc_get_mode(void) } /** + * buf_acquire - creates a TIPC message buffer + * @size: message size (including TIPC header) + * + * Returns a new buffer with data pointers set to the specified size. + * + * NOTE: Headroom is reserved to allow prepending of a data link header. + * There may also be unrequested tailroom present at the buffer's end. + */ + +struct sk_buff *buf_acquire(u32 size) +{ + struct sk_buff *skb; + unsigned int buf_size = (BUF_HEADROOM + size + 3) & ~3u; + + skb = alloc_skb_fclone(buf_size, GFP_ATOMIC); + if (skb) { + skb_reserve(skb, BUF_HEADROOM); + skb_put(skb, size); + skb->next = NULL; + } + return skb; +} + +/** * tipc_core_stop_net - shut down TIPC networking sub-systems */ diff --git a/net/tipc/core.h b/net/tipc/core.h index c58a1d16563a..188799017abd 100644 --- a/net/tipc/core.h +++ b/net/tipc/core.h @@ -59,6 +59,9 @@ #include <linux/slab.h> #include <linux/vmalloc.h> + +#define TIPC_MOD_VER "2.0.0" + /* * TIPC sanity test macros */ @@ -325,29 +328,7 @@ static inline struct tipc_msg *buf_msg(struct sk_buff *skb) return (struct tipc_msg *)skb->data; } -/** - * buf_acquire - creates a TIPC message buffer - * @size: message size (including TIPC header) - * - * Returns a new buffer with data pointers set to the specified size. - * - * NOTE: Headroom is reserved to allow prepending of a data link header. - * There may also be unrequested tailroom present at the buffer's end. - */ - -static inline struct sk_buff *buf_acquire(u32 size) -{ - struct sk_buff *skb; - unsigned int buf_size = (BUF_HEADROOM + size + 3) & ~3u; - - skb = alloc_skb_fclone(buf_size, GFP_ATOMIC); - if (skb) { - skb_reserve(skb, BUF_HEADROOM); - skb_put(skb, size); - skb->next = NULL; - } - return skb; -} +extern struct sk_buff *buf_acquire(u32 size); /** * buf_discard - frees a TIPC message buffer diff --git a/net/tipc/discover.c b/net/tipc/discover.c index 74b7d1e28aec..fc1fcf5e6b53 100644 --- a/net/tipc/discover.c +++ b/net/tipc/discover.c @@ -120,7 +120,7 @@ static struct sk_buff *tipc_disc_init_msg(u32 type, if (buf) { msg = buf_msg(buf); - msg_init(msg, LINK_CONFIG, type, DSC_H_SIZE, dest_domain); + tipc_msg_init(msg, LINK_CONFIG, type, DSC_H_SIZE, dest_domain); msg_set_non_seq(msg, 1); msg_set_req_links(msg, req_links); msg_set_dest_domain(msg, dest_domain); @@ -144,7 +144,7 @@ static void disc_dupl_alert(struct bearer *b_ptr, u32 node_addr, char media_addr_str[64]; struct print_buf pb; - addr_string_fill(node_addr_str, node_addr); + tipc_addr_string_fill(node_addr_str, node_addr); tipc_printbuf_init(&pb, media_addr_str, sizeof(media_addr_str)); tipc_media_addr_printf(&pb, media_addr); tipc_printbuf_validate(&pb); @@ -183,7 +183,7 @@ void tipc_disc_recv_msg(struct sk_buff *buf, struct bearer *b_ptr) disc_dupl_alert(b_ptr, tipc_own_addr, &media_addr); return; } - if (!in_scope(dest, tipc_own_addr)) + if (!tipc_in_scope(dest, tipc_own_addr)) return; if (is_slave(tipc_own_addr) && is_slave(orig)) return; @@ -224,7 +224,7 @@ void tipc_disc_recv_msg(struct sk_buff *buf, struct bearer *b_ptr) memcpy(addr, &media_addr, sizeof(*addr)); tipc_link_reset(link); } - link_fully_up = (link->state == WORKING_WORKING); + link_fully_up = link_working_working(link); spin_unlock_bh(&n_ptr->lock); if ((type == DSC_RESP_MSG) || link_fully_up) return; diff --git a/net/tipc/link.c b/net/tipc/link.c index c76e82e5f982..a3616b99529b 100644 --- a/net/tipc/link.c +++ b/net/tipc/link.c @@ -202,41 +202,6 @@ static unsigned int align(unsigned int i) return (i + 3) & ~3u; } -static int link_working_working(struct link *l_ptr) -{ - return (l_ptr->state == WORKING_WORKING); -} - -static int link_working_unknown(struct link *l_ptr) -{ - return (l_ptr->state == WORKING_UNKNOWN); -} - -static int link_reset_unknown(struct link *l_ptr) -{ - return (l_ptr->state == RESET_UNKNOWN); -} - -static int link_reset_reset(struct link *l_ptr) -{ - return (l_ptr->state == RESET_RESET); -} - -static int link_blocked(struct link *l_ptr) -{ - return (l_ptr->exp_msg_count || l_ptr->blocked); -} - -static int link_congested(struct link *l_ptr) -{ - return (l_ptr->out_queue_size >= l_ptr->queue_limit[0]); -} - -static u32 link_max_pkt(struct link *l_ptr) -{ - return l_ptr->max_pkt; -} - static void link_init_max_pkt(struct link *l_ptr) { u32 max_pkt; @@ -468,7 +433,7 @@ struct link *tipc_link_create(struct bearer *b_ptr, const u32 peer, l_ptr->pmsg = (struct tipc_msg *)&l_ptr->proto_msg; msg = l_ptr->pmsg; - msg_init(msg, LINK_PROTOCOL, RESET_MSG, INT_H_SIZE, l_ptr->addr); + tipc_msg_init(msg, LINK_PROTOCOL, RESET_MSG, INT_H_SIZE, l_ptr->addr); msg_set_size(msg, sizeof(l_ptr->proto_msg)); msg_set_session(msg, (tipc_random & 0xffff)); msg_set_bearer_id(msg, b_ptr->identity); @@ -561,9 +526,8 @@ static int link_schedule_port(struct link *l_ptr, u32 origport, u32 sz) goto exit; if (!list_empty(&p_ptr->wait_list)) goto exit; - p_ptr->congested_link = l_ptr; p_ptr->publ.congested = 1; - p_ptr->waiting_pkts = 1 + ((sz - 1) / link_max_pkt(l_ptr)); + p_ptr->waiting_pkts = 1 + ((sz - 1) / l_ptr->max_pkt); list_add_tail(&p_ptr->wait_list, &l_ptr->waiting_ports); l_ptr->stats.link_congs++; exit: @@ -592,7 +556,6 @@ void tipc_link_wakeup_ports(struct link *l_ptr, int all) if (win <= 0) break; list_del_init(&p_ptr->wait_list); - p_ptr->congested_link = NULL; spin_lock_bh(p_ptr->publ.lock); p_ptr->publ.congested = 0; p_ptr->wakeup(&p_ptr->publ); @@ -1017,7 +980,7 @@ static int link_bundle_buf(struct link *l_ptr, return 0; if (skb_tailroom(bundler) < (pad + size)) return 0; - if (link_max_pkt(l_ptr) < (to_pos + size)) + if (l_ptr->max_pkt < (to_pos + size)) return 0; skb_put(bundler, pad + size); @@ -1062,9 +1025,9 @@ int tipc_link_send_buf(struct link *l_ptr, struct sk_buff *buf) u32 size = msg_size(msg); u32 dsz = msg_data_sz(msg); u32 queue_size = l_ptr->out_queue_size; - u32 imp = msg_tot_importance(msg); + u32 imp = tipc_msg_tot_importance(msg); u32 queue_limit = l_ptr->queue_limit[imp]; - u32 max_packet = link_max_pkt(l_ptr); + u32 max_packet = l_ptr->max_pkt; msg_set_prevnode(msg, tipc_own_addr); /* If routed message */ @@ -1127,7 +1090,7 @@ int tipc_link_send_buf(struct link *l_ptr, struct sk_buff *buf) struct tipc_msg bundler_hdr; if (bundler) { - msg_init(&bundler_hdr, MSG_BUNDLER, OPEN_MSG, + tipc_msg_init(&bundler_hdr, MSG_BUNDLER, OPEN_MSG, INT_H_SIZE, l_ptr->addr); skb_copy_to_linear_data(bundler, &bundler_hdr, INT_H_SIZE); @@ -1195,7 +1158,7 @@ static int link_send_buf_fast(struct link *l_ptr, struct sk_buff *buf, int res = msg_data_sz(msg); if (likely(!link_congested(l_ptr))) { - if (likely(msg_size(msg) <= link_max_pkt(l_ptr))) { + if (likely(msg_size(msg) <= l_ptr->max_pkt)) { if (likely(list_empty(&l_ptr->b_ptr->cong_links))) { link_add_to_outqueue(l_ptr, buf, msg); if (likely(tipc_bearer_send(l_ptr->b_ptr, buf, @@ -1212,7 +1175,7 @@ static int link_send_buf_fast(struct link *l_ptr, struct sk_buff *buf, } } else - *used_max_pkt = link_max_pkt(l_ptr); + *used_max_pkt = l_ptr->max_pkt; } return tipc_link_send_buf(l_ptr, buf); /* All other cases */ } @@ -1280,7 +1243,7 @@ again: * (Must not hold any locks while building message.) */ - res = msg_build(hdr, msg_sect, num_sect, sender->publ.max_pkt, + res = tipc_msg_build(hdr, msg_sect, num_sect, sender->publ.max_pkt, !sender->user_port, &buf); read_lock_bh(&tipc_net_lock); @@ -1319,7 +1282,7 @@ exit: * then re-try fast path or fragment the message */ - sender->publ.max_pkt = link_max_pkt(l_ptr); + sender->publ.max_pkt = l_ptr->max_pkt; tipc_node_unlock(node); read_unlock_bh(&tipc_net_lock); @@ -1391,7 +1354,7 @@ again: /* Prepare reusable fragment header: */ msg_dbg(hdr, ">FRAGMENTING>"); - msg_init(&fragm_hdr, MSG_FRAGMENTER, FIRST_FRAGMENT, + tipc_msg_init(&fragm_hdr, MSG_FRAGMENTER, FIRST_FRAGMENT, INT_H_SIZE, msg_destnode(hdr)); msg_set_link_selector(&fragm_hdr, sender->publ.ref); msg_set_size(&fragm_hdr, max_pkt); @@ -1482,8 +1445,8 @@ error: tipc_node_unlock(node); goto reject; } - if (link_max_pkt(l_ptr) < max_pkt) { - sender->publ.max_pkt = link_max_pkt(l_ptr); + if (l_ptr->max_pkt < max_pkt) { + sender->publ.max_pkt = l_ptr->max_pkt; tipc_node_unlock(node); for (; buf_chain; buf_chain = buf) { buf = buf_chain->next; @@ -1650,7 +1613,7 @@ static void link_reset_all(unsigned long addr) tipc_node_lock(n_ptr); warn("Resetting all links to %s\n", - addr_string_fill(addr_string, n_ptr->addr)); + tipc_addr_string_fill(addr_string, n_ptr->addr)); for (i = 0; i < MAX_BEARERS; i++) { if (n_ptr->links[i]) { @@ -1692,7 +1655,7 @@ static void link_retransmit_failure(struct link *l_ptr, struct sk_buff *buf) n_ptr = l_ptr->owner->next; tipc_node_lock(n_ptr); - addr_string_fill(addr_string, n_ptr->addr); + tipc_addr_string_fill(addr_string, n_ptr->addr); tipc_printf(TIPC_OUTPUT, "Multicast link info for %s\n", addr_string); tipc_printf(TIPC_OUTPUT, "Supported: %d, ", n_ptr->bclink.supported); tipc_printf(TIPC_OUTPUT, "Acked: %u\n", n_ptr->bclink.acked); @@ -2435,7 +2398,7 @@ void tipc_link_changeover(struct link *l_ptr) return; } - msg_init(&tunnel_hdr, CHANGEOVER_PROTOCOL, + tipc_msg_init(&tunnel_hdr, CHANGEOVER_PROTOCOL, ORIGINAL_MSG, INT_H_SIZE, l_ptr->addr); msg_set_bearer_id(&tunnel_hdr, l_ptr->peer_bearer_id); msg_set_msgcnt(&tunnel_hdr, msgcount); @@ -2490,7 +2453,7 @@ void tipc_link_send_duplicate(struct link *l_ptr, struct link *tunnel) struct sk_buff *iter; struct tipc_msg tunnel_hdr; - msg_init(&tunnel_hdr, CHANGEOVER_PROTOCOL, + tipc_msg_init(&tunnel_hdr, CHANGEOVER_PROTOCOL, DUPLICATE_MSG, INT_H_SIZE, l_ptr->addr); msg_set_msgcnt(&tunnel_hdr, l_ptr->out_queue_size); msg_set_bearer_id(&tunnel_hdr, l_ptr->peer_bearer_id); @@ -2681,7 +2644,7 @@ int tipc_link_send_long_buf(struct link *l_ptr, struct sk_buff *buf) u32 dsz = msg_data_sz(inmsg); unchar *crs = buf->data; u32 rest = insize; - u32 pack_sz = link_max_pkt(l_ptr); + u32 pack_sz = l_ptr->max_pkt; u32 fragm_sz = pack_sz - INT_H_SIZE; u32 fragm_no = 1; u32 destaddr; @@ -2696,7 +2659,7 @@ int tipc_link_send_long_buf(struct link *l_ptr, struct sk_buff *buf) /* Prepare reusable fragment header: */ - msg_init(&fragm_hdr, MSG_FRAGMENTER, FIRST_FRAGMENT, + tipc_msg_init(&fragm_hdr, MSG_FRAGMENTER, FIRST_FRAGMENT, INT_H_SIZE, destaddr); msg_set_link_selector(&fragm_hdr, msg_link_selector(inmsg)); msg_set_long_msgno(&fragm_hdr, mod(l_ptr->long_msg_seq_no++)); @@ -3127,7 +3090,7 @@ static int tipc_link_stats(const char *name, char *buf, const u32 buf_size) tipc_printf(&pb, "Link <%s>\n" " %s MTU:%u Priority:%u Tolerance:%u ms" " Window:%u packets\n", - l_ptr->name, status, link_max_pkt(l_ptr), + l_ptr->name, status, l_ptr->max_pkt, l_ptr->priority, l_ptr->tolerance, l_ptr->queue_limit[0]); tipc_printf(&pb, " RX packets:%u fragments:%u/%u bundles:%u/%u\n", l_ptr->next_in_no - l_ptr->stats.recv_info, @@ -3272,7 +3235,7 @@ u32 tipc_link_get_max_pkt(u32 dest, u32 selector) tipc_node_lock(n_ptr); l_ptr = n_ptr->active_links[selector & 1]; if (l_ptr) - res = link_max_pkt(l_ptr); + res = l_ptr->max_pkt; tipc_node_unlock(n_ptr); } read_unlock_bh(&tipc_net_lock); @@ -3330,9 +3293,7 @@ static void link_print(struct link *l_ptr, struct print_buf *buf, if (l_ptr->next_out) tipc_printf(buf, "%u..", msg_seqno(buf_msg(l_ptr->next_out))); - tipc_printf(buf, "%u]", - msg_seqno(buf_msg - (l_ptr->last_out)), l_ptr->out_queue_size); + tipc_printf(buf, "%u]", msg_seqno(buf_msg(l_ptr->last_out))); if ((mod(msg_seqno(buf_msg(l_ptr->last_out)) - msg_seqno(buf_msg(l_ptr->first_out))) != (l_ptr->out_queue_size - 1)) || diff --git a/net/tipc/link.h b/net/tipc/link.h index 6a51e38ad25c..2e5385c47d30 100644 --- a/net/tipc/link.h +++ b/net/tipc/link.h @@ -292,4 +292,39 @@ static inline u32 lesser(u32 left, u32 right) return less_eq(left, right) ? left : right; } + +/* + * Link status checking routines + */ + +static inline int link_working_working(struct link *l_ptr) +{ + return (l_ptr->state == WORKING_WORKING); +} + +static inline int link_working_unknown(struct link *l_ptr) +{ + return (l_ptr->state == WORKING_UNKNOWN); +} + +static inline int link_reset_unknown(struct link *l_ptr) +{ + return (l_ptr->state == RESET_UNKNOWN); +} + +static inline int link_reset_reset(struct link *l_ptr) +{ + return (l_ptr->state == RESET_RESET); +} + +static inline int link_blocked(struct link *l_ptr) +{ + return (l_ptr->exp_msg_count || l_ptr->blocked); +} + +static inline int link_congested(struct link *l_ptr) +{ + return (l_ptr->out_queue_size >= l_ptr->queue_limit[0]); +} + #endif diff --git a/net/tipc/msg.c b/net/tipc/msg.c index 73dcd00d674e..381063817b41 100644 --- a/net/tipc/msg.c +++ b/net/tipc/msg.c @@ -40,6 +40,100 @@ #include "msg.h" #include "bearer.h" +u32 tipc_msg_tot_importance(struct tipc_msg *m) +{ + if (likely(msg_isdata(m))) { + if (likely(msg_orignode(m) == tipc_own_addr)) + return msg_importance(m); + return msg_importance(m) + 4; + } + if ((msg_user(m) == MSG_FRAGMENTER) && + (msg_type(m) == FIRST_FRAGMENT)) + return msg_importance(msg_get_wrapped(m)); + return msg_importance(m); +} + + +void tipc_msg_init(struct tipc_msg *m, u32 user, u32 type, + u32 hsize, u32 destnode) +{ + memset(m, 0, hsize); + msg_set_version(m); + msg_set_user(m, user); + msg_set_hdr_sz(m, hsize); + msg_set_size(m, hsize); + msg_set_prevnode(m, tipc_own_addr); + msg_set_type(m, type); + if (!msg_short(m)) { + msg_set_orignode(m, tipc_own_addr); + msg_set_destnode(m, destnode); + } +} + +/** + * tipc_msg_calc_data_size - determine total data size for message + */ + +int tipc_msg_calc_data_size(struct iovec const *msg_sect, u32 num_sect) +{ + int dsz = 0; + int i; + + for (i = 0; i < num_sect; i++) + dsz += msg_sect[i].iov_len; + return dsz; +} + +/** + * tipc_msg_build - create message using specified header and data + * + * Note: Caller must not hold any locks in case copy_from_user() is interrupted! + * + * Returns message data size or errno + */ + +int tipc_msg_build(struct tipc_msg *hdr, + struct iovec const *msg_sect, u32 num_sect, + int max_size, int usrmem, struct sk_buff** buf) +{ + int dsz, sz, hsz, pos, res, cnt; + + dsz = tipc_msg_calc_data_size(msg_sect, num_sect); + if (unlikely(dsz > TIPC_MAX_USER_MSG_SIZE)) { + *buf = NULL; + return -EINVAL; + } + + pos = hsz = msg_hdr_sz(hdr); + sz = hsz + dsz; + msg_set_size(hdr, sz); + if (unlikely(sz > max_size)) { + *buf = NULL; + return dsz; + } + + *buf = buf_acquire(sz); + if (!(*buf)) + return -ENOMEM; + skb_copy_to_linear_data(*buf, hdr, hsz); + for (res = 1, cnt = 0; res && (cnt < num_sect); cnt++) { + if (likely(usrmem)) + res = !copy_from_user((*buf)->data + pos, + msg_sect[cnt].iov_base, + msg_sect[cnt].iov_len); + else + skb_copy_to_linear_data_offset(*buf, pos, + msg_sect[cnt].iov_base, + msg_sect[cnt].iov_len); + pos += msg_sect[cnt].iov_len; + } + if (likely(res)) + return dsz; + + buf_discard(*buf); + *buf = NULL; + return -EFAULT; +} #ifdef CONFIG_TIPC_DEBUG diff --git a/net/tipc/msg.h b/net/tipc/msg.h index 7ee6ae238147..995d2da35b01 100644 --- a/net/tipc/msg.h +++ b/net/tipc/msg.h @@ -708,100 +708,13 @@ static inline void msg_set_dataoctet(struct tipc_msg *m, u32 pos) #define DSC_REQ_MSG 0 #define DSC_RESP_MSG 1 -static inline u32 msg_tot_importance(struct tipc_msg *m) -{ - if (likely(msg_isdata(m))) { - if (likely(msg_orignode(m) == tipc_own_addr)) - return msg_importance(m); - return msg_importance(m) + 4; - } - if ((msg_user(m) == MSG_FRAGMENTER) && - (msg_type(m) == FIRST_FRAGMENT)) - return msg_importance(msg_get_wrapped(m)); - return msg_importance(m); -} - - -static inline void msg_init(struct tipc_msg *m, u32 user, u32 type, - u32 hsize, u32 destnode) -{ - memset(m, 0, hsize); - msg_set_version(m); - msg_set_user(m, user); - msg_set_hdr_sz(m, hsize); - msg_set_size(m, hsize); - msg_set_prevnode(m, tipc_own_addr); - msg_set_type(m, type); - if (!msg_short(m)) { - msg_set_orignode(m, tipc_own_addr); - msg_set_destnode(m, destnode); - } -} - -/** - * msg_calc_data_size - determine total data size for message - */ - -static inline int msg_calc_data_size(struct iovec const *msg_sect, u32 num_sect) -{ - int dsz = 0; - int i; - - for (i = 0; i < num_sect; i++) - dsz += msg_sect[i].iov_len; - return dsz; -} - -/** - * msg_build - create message using specified header and data - * - * Note: Caller must not hold any locks in case copy_from_user() is interrupted! - * - * Returns message data size or errno - */ - -static inline int msg_build(struct tipc_msg *hdr, +u32 tipc_msg_tot_importance(struct tipc_msg *m); +void tipc_msg_init(struct tipc_msg *m, u32 user, u32 type, + u32 hsize, u32 destnode); +int tipc_msg_calc_data_size(struct iovec const *msg_sect, u32 num_sect); +int tipc_msg_build(struct tipc_msg *hdr, struct iovec const *msg_sect, u32 num_sect, - int max_size, int usrmem, struct sk_buff** buf) -{ - int dsz, sz, hsz, pos, res, cnt; - - dsz = msg_calc_data_size(msg_sect, num_sect); - if (unlikely(dsz > TIPC_MAX_USER_MSG_SIZE)) { - *buf = NULL; - return -EINVAL; - } - - pos = hsz = msg_hdr_sz(hdr); - sz = hsz + dsz; - msg_set_size(hdr, sz); - if (unlikely(sz > max_size)) { - *buf = NULL; - return dsz; - } - - *buf = buf_acquire(sz); - if (!(*buf)) - return -ENOMEM; - skb_copy_to_linear_data(*buf, hdr, hsz); - for (res = 1, cnt = 0; res && (cnt < num_sect); cnt++) { - if (likely(usrmem)) - res = !copy_from_user((*buf)->data + pos, - msg_sect[cnt].iov_base, - msg_sect[cnt].iov_len); - else - skb_copy_to_linear_data_offset(*buf, pos, - msg_sect[cnt].iov_base, - msg_sect[cnt].iov_len); - pos += msg_sect[cnt].iov_len; - } - if (likely(res)) - return dsz; - - buf_discard(*buf); - *buf = NULL; - return -EFAULT; -} + int max_size, int usrmem, struct sk_buff** buf); static inline void msg_set_media_addr(struct tipc_msg *m, struct tipc_media_addr *a) { diff --git a/net/tipc/name_distr.c b/net/tipc/name_distr.c index 10a69894e2fd..6ac3c543250b 100644 --- a/net/tipc/name_distr.c +++ b/net/tipc/name_distr.c @@ -103,7 +103,7 @@ static struct sk_buff *named_prepare_buf(u32 type, u32 size, u32 dest) if (buf != NULL) { msg = buf_msg(buf); - msg_init(msg, NAME_DISTRIBUTOR, type, LONG_H_SIZE, dest); + tipc_msg_init(msg, NAME_DISTRIBUTOR, type, LONG_H_SIZE, dest); msg_set_size(msg, LONG_H_SIZE + size); } return buf; diff --git a/net/tipc/name_table.c b/net/tipc/name_table.c index acab41a48d67..8ba79620db3f 100644 --- a/net/tipc/name_table.c +++ b/net/tipc/name_table.c @@ -627,7 +627,7 @@ u32 tipc_nametbl_translate(u32 type, u32 instance, u32 *destnode) struct name_seq *seq; u32 ref; - if (!in_scope(*destnode, tipc_own_addr)) + if (!tipc_in_scope(*destnode, tipc_own_addr)) return 0; read_lock_bh(&tipc_nametbl_lock); diff --git a/net/tipc/net.c b/net/tipc/net.c index d7cd1e064a80..f61b7694138b 100644 --- a/net/tipc/net.c +++ b/net/tipc/net.c @@ -219,7 +219,7 @@ void tipc_net_route_msg(struct sk_buff *buf) /* Handle message for this node */ dnode = msg_short(msg) ? tipc_own_addr : msg_destnode(msg); - if (in_scope(dnode, tipc_own_addr)) { + if (tipc_in_scope(dnode, tipc_own_addr)) { if (msg_isdata(msg)) { if (msg_mcast(msg)) tipc_port_recv_mcast(buf, NULL); @@ -277,7 +277,7 @@ int tipc_net_start(u32 addr) info("Started in network mode\n"); info("Own node address %s, network identity %u\n", - addr_string_fill(addr_string, tipc_own_addr), tipc_net_id); + tipc_addr_string_fill(addr_string, tipc_own_addr), tipc_net_id); return 0; } diff --git a/net/tipc/node.c b/net/tipc/node.c index 17cc394f424f..b634942caba5 100644 --- a/net/tipc/node.c +++ b/net/tipc/node.c @@ -268,7 +268,7 @@ struct tipc_node *tipc_node_attach_link(struct link *l_ptr) if (n_ptr->link_cnt >= 2) { err("Attempt to create third link to %s\n", - addr_string_fill(addr_string, n_ptr->addr)); + tipc_addr_string_fill(addr_string, n_ptr->addr)); return NULL; } @@ -280,7 +280,7 @@ struct tipc_node *tipc_node_attach_link(struct link *l_ptr) } err("Attempt to establish second link on <%s> to %s\n", l_ptr->b_ptr->publ.name, - addr_string_fill(addr_string, l_ptr->addr)); + tipc_addr_string_fill(addr_string, l_ptr->addr)); } return NULL; } @@ -439,7 +439,7 @@ static void node_lost_contact(struct tipc_node *n_ptr) return; info("Lost contact with %s\n", - addr_string_fill(addr_string, n_ptr->addr)); + tipc_addr_string_fill(addr_string, n_ptr->addr)); /* Abort link changeover */ for (i = 0; i < MAX_BEARERS; i++) { @@ -602,7 +602,7 @@ u32 tipc_available_nodes(const u32 domain) read_lock_bh(&tipc_net_lock); for (n_ptr = tipc_nodes; n_ptr; n_ptr = n_ptr->next) { - if (!in_scope(domain, n_ptr->addr)) + if (!tipc_in_scope(domain, n_ptr->addr)) continue; if (tipc_node_is_up(n_ptr)) cnt++; @@ -651,7 +651,7 @@ struct sk_buff *tipc_node_get_nodes(const void *req_tlv_area, int req_tlv_space) /* Add TLVs for all nodes in scope */ for (n_ptr = tipc_nodes; n_ptr; n_ptr = n_ptr->next) { - if (!in_scope(domain, n_ptr->addr)) + if (!tipc_in_scope(domain, n_ptr->addr)) continue; node_info.addr = htonl(n_ptr->addr); node_info.up = htonl(tipc_node_is_up(n_ptr)); @@ -711,7 +711,7 @@ struct sk_buff *tipc_node_get_links(const void *req_tlv_area, int req_tlv_space) for (n_ptr = tipc_nodes; n_ptr; n_ptr = n_ptr->next) { u32 i; - if (!in_scope(domain, n_ptr->addr)) + if (!tipc_in_scope(domain, n_ptr->addr)) continue; tipc_node_lock(n_ptr); for (i = 0; i < MAX_BEARERS; i++) { diff --git a/net/tipc/port.c b/net/tipc/port.c index e70d27ea6578..0737680e9266 100644 --- a/net/tipc/port.c +++ b/net/tipc/port.c @@ -116,7 +116,7 @@ int tipc_multicast(u32 ref, struct tipc_name_seq const *seq, u32 domain, msg_set_namelower(hdr, seq->lower); msg_set_nameupper(hdr, seq->upper); msg_set_hdr_sz(hdr, MCAST_H_SIZE); - res = msg_build(hdr, msg_sect, num_sect, MAX_MSG_SIZE, + res = tipc_msg_build(hdr, msg_sect, num_sect, MAX_MSG_SIZE, !oport->user_port, &buf); if (unlikely(!buf)) return res; @@ -241,13 +241,12 @@ struct tipc_port *tipc_createport_raw(void *usr_handle, p_ptr->publ.max_pkt = MAX_PKT_DEFAULT; p_ptr->publ.ref = ref; msg = &p_ptr->publ.phdr; - msg_init(msg, importance, TIPC_NAMED_MSG, LONG_H_SIZE, 0); + tipc_msg_init(msg, importance, TIPC_NAMED_MSG, LONG_H_SIZE, 0); msg_set_origport(msg, ref); p_ptr->last_in_seqno = 41; p_ptr->sent = 1; INIT_LIST_HEAD(&p_ptr->wait_list); INIT_LIST_HEAD(&p_ptr->subscription.nodesub_list); - p_ptr->congested_link = NULL; p_ptr->dispatcher = dispatcher; p_ptr->wakeup = wakeup; p_ptr->user_port = NULL; @@ -396,7 +395,7 @@ static struct sk_buff *port_build_proto_msg(u32 destport, u32 destnode, buf = buf_acquire(LONG_H_SIZE); if (buf) { msg = buf_msg(buf); - msg_init(msg, usr, type, LONG_H_SIZE, destnode); + tipc_msg_init(msg, usr, type, LONG_H_SIZE, destnode); msg_set_errcode(msg, err); msg_set_destport(msg, destport); msg_set_origport(msg, origport); @@ -440,7 +439,7 @@ int tipc_reject_msg(struct sk_buff *buf, u32 err) return data_sz; } rmsg = buf_msg(rbuf); - msg_init(rmsg, imp, msg_type(msg), hdr_sz, msg_orignode(msg)); + tipc_msg_init(rmsg, imp, msg_type(msg), hdr_sz, msg_orignode(msg)); msg_set_errcode(rmsg, err); msg_set_destport(rmsg, msg_origport(msg)); msg_set_origport(rmsg, msg_destport(msg)); @@ -481,7 +480,7 @@ int tipc_port_reject_sections(struct port *p_ptr, struct tipc_msg *hdr, struct sk_buff *buf; int res; - res = msg_build(hdr, msg_sect, num_sect, MAX_MSG_SIZE, + res = tipc_msg_build(hdr, msg_sect, num_sect, MAX_MSG_SIZE, !p_ptr->user_port, &buf); if (!buf) return res; @@ -1344,7 +1343,7 @@ int tipc_port_recv_sections(struct port *sender, unsigned int num_sect, struct sk_buff *buf; int res; - res = msg_build(&sender->publ.phdr, msg_sect, num_sect, + res = tipc_msg_build(&sender->publ.phdr, msg_sect, num_sect, MAX_MSG_SIZE, !sender->user_port, &buf); if (likely(buf)) tipc_port_recv_msg(buf); @@ -1384,7 +1383,7 @@ int tipc_send(u32 ref, unsigned int num_sect, struct iovec const *msg_sect) if (port_unreliable(p_ptr)) { p_ptr->publ.congested = 0; /* Just calculate msg length and return */ - return msg_calc_data_size(msg_sect, num_sect); + return tipc_msg_calc_data_size(msg_sect, num_sect); } return -ELINKCONG; } @@ -1453,7 +1452,7 @@ int tipc_forward2name(u32 ref, struct port *p_ptr; struct tipc_msg *msg; u32 destnode = domain; - u32 destport = 0; + u32 destport; int res; p_ptr = tipc_port_deref(ref); @@ -1467,7 +1466,7 @@ int tipc_forward2name(u32 ref, msg_set_hdr_sz(msg, LONG_H_SIZE); msg_set_nametype(msg, name->type); msg_set_nameinst(msg, name->instance); - msg_set_lookup_scope(msg, addr_scope(domain)); + msg_set_lookup_scope(msg, tipc_addr_scope(domain)); if (importance <= TIPC_CRITICAL_IMPORTANCE) msg_set_importance(msg,importance); destport = tipc_nametbl_translate(name->type, name->instance, &destnode); @@ -1484,7 +1483,7 @@ int tipc_forward2name(u32 ref, return res; if (port_unreliable(p_ptr)) { /* Just calculate msg length and return */ - return msg_calc_data_size(msg_sect, num_sect); + return tipc_msg_calc_data_size(msg_sect, num_sect); } return -ELINKCONG; } @@ -1525,7 +1524,7 @@ int tipc_forward_buf2name(u32 ref, struct port *p_ptr; struct tipc_msg *msg; u32 destnode = domain; - u32 destport = 0; + u32 destport; int res; p_ptr = (struct port *)tipc_ref_deref(ref); @@ -1540,7 +1539,7 @@ int tipc_forward_buf2name(u32 ref, msg_set_origport(msg, orig->ref); msg_set_nametype(msg, name->type); msg_set_nameinst(msg, name->instance); - msg_set_lookup_scope(msg, addr_scope(domain)); + msg_set_lookup_scope(msg, tipc_addr_scope(domain)); msg_set_hdr_sz(msg, LONG_H_SIZE); msg_set_size(msg, LONG_H_SIZE + dsz); destport = tipc_nametbl_translate(name->type, name->instance, &destnode); @@ -1620,7 +1619,7 @@ int tipc_forward2port(u32 ref, return res; if (port_unreliable(p_ptr)) { /* Just calculate msg length and return */ - return msg_calc_data_size(msg_sect, num_sect); + return tipc_msg_calc_data_size(msg_sect, num_sect); } return -ELINKCONG; } diff --git a/net/tipc/port.h b/net/tipc/port.h index ff31ee4a1dc3..8d1652aab298 100644 --- a/net/tipc/port.h +++ b/net/tipc/port.h @@ -75,7 +75,6 @@ struct user_port { * @wakeup: ptr to routine to call when port is no longer congested * @user_port: ptr to user port associated with port (if any) * @wait_list: adjacent ports in list of ports waiting on link congestion - * @congested_link: ptr to congested link port is waiting on * @waiting_pkts: * @sent: * @acked: @@ -95,7 +94,6 @@ struct port { void (*wakeup)(struct tipc_port *); struct user_port *user_port; struct list_head wait_list; - struct link *congested_link; u32 waiting_pkts; u32 sent; u32 acked; diff --git a/net/wireless/chan.c b/net/wireless/chan.c index bf1737fc9a7e..d92d088026bf 100644 --- a/net/wireless/chan.c +++ b/net/wireless/chan.c @@ -10,38 +10,6 @@ #include "core.h" struct ieee80211_channel * -rdev_fixed_channel(struct cfg80211_registered_device *rdev, - struct wireless_dev *for_wdev) -{ - struct wireless_dev *wdev; - struct ieee80211_channel *result = NULL; - - WARN_ON(!mutex_is_locked(&rdev->devlist_mtx)); - - list_for_each_entry(wdev, &rdev->netdev_list, list) { - if (wdev == for_wdev) - continue; - - /* - * Lock manually to tell lockdep about allowed - * nesting here if for_wdev->mtx is held already. - * This is ok as it's all under the rdev devlist - * mutex and as such can only be done once at any - * given time. - */ - mutex_lock_nested(&wdev->mtx, SINGLE_DEPTH_NESTING); - if (wdev->current_bss) - result = wdev->current_bss->pub.channel; - wdev_unlock(wdev); - - if (result) - break; - } - - return result; -} - -struct ieee80211_channel * rdev_freq_to_chan(struct cfg80211_registered_device *rdev, int freq, enum nl80211_channel_type channel_type) { @@ -75,15 +43,22 @@ rdev_freq_to_chan(struct cfg80211_registered_device *rdev, return chan; } -int rdev_set_freq(struct cfg80211_registered_device *rdev, - struct wireless_dev *for_wdev, - int freq, enum nl80211_channel_type channel_type) +int cfg80211_set_freq(struct cfg80211_registered_device *rdev, + struct wireless_dev *wdev, int freq, + enum nl80211_channel_type channel_type) { struct ieee80211_channel *chan; int result; - if (rdev_fixed_channel(rdev, for_wdev)) - return -EBUSY; + if (wdev->iftype == NL80211_IFTYPE_MONITOR) + wdev = NULL; + + if (wdev) { + ASSERT_WDEV_LOCK(wdev); + + if (!netif_running(wdev->netdev)) + return -ENETDOWN; + } if (!rdev->ops->set_channel) return -EOPNOTSUPP; @@ -92,11 +67,14 @@ int rdev_set_freq(struct cfg80211_registered_device *rdev, if (!chan) return -EINVAL; - result = rdev->ops->set_channel(&rdev->wiphy, chan, channel_type); + result = rdev->ops->set_channel(&rdev->wiphy, + wdev ? wdev->netdev : NULL, + chan, channel_type); if (result) return result; - rdev->channel = chan; + if (wdev) + wdev->channel = chan; return 0; } diff --git a/net/wireless/core.h b/net/wireless/core.h index b2234b436ead..ae930acf75e9 100644 --- a/net/wireless/core.h +++ b/net/wireless/core.h @@ -70,9 +70,6 @@ struct cfg80211_registered_device { struct work_struct conn_work; struct work_struct event_work; - /* current channel */ - struct ieee80211_channel *channel; - /* must be last because of the way we do wiphy_priv(), * and it should at least be aligned to NETDEV_ALIGN */ struct wiphy wiphy __attribute__((__aligned__(NETDEV_ALIGN))); @@ -388,14 +385,11 @@ int cfg80211_change_iface(struct cfg80211_registered_device *rdev, void cfg80211_process_rdev_events(struct cfg80211_registered_device *rdev); struct ieee80211_channel * -rdev_fixed_channel(struct cfg80211_registered_device *rdev, - struct wireless_dev *for_wdev); -struct ieee80211_channel * rdev_freq_to_chan(struct cfg80211_registered_device *rdev, int freq, enum nl80211_channel_type channel_type); -int rdev_set_freq(struct cfg80211_registered_device *rdev, - struct wireless_dev *for_wdev, - int freq, enum nl80211_channel_type channel_type); +int cfg80211_set_freq(struct cfg80211_registered_device *rdev, + struct wireless_dev *wdev, int freq, + enum nl80211_channel_type channel_type); u16 cfg80211_calculate_bitrate(struct rate_info *rate); diff --git a/net/wireless/ibss.c b/net/wireless/ibss.c index 6a5acf750174..adcabba02e20 100644 --- a/net/wireless/ibss.c +++ b/net/wireless/ibss.c @@ -81,15 +81,10 @@ int __cfg80211_join_ibss(struct cfg80211_registered_device *rdev, struct cfg80211_cached_keys *connkeys) { struct wireless_dev *wdev = dev->ieee80211_ptr; - struct ieee80211_channel *chan; int err; ASSERT_WDEV_LOCK(wdev); - chan = rdev_fixed_channel(rdev, wdev); - if (chan && chan != params->channel) - return -EBUSY; - if (wdev->ssid_len) return -EALREADY; diff --git a/net/wireless/nl80211.c b/net/wireless/nl80211.c index 01da83ddcff7..aaa1aad566cd 100644 --- a/net/wireless/nl80211.c +++ b/net/wireless/nl80211.c @@ -589,6 +589,7 @@ static int nl80211_send_wiphy(struct sk_buff *msg, u32 pid, u32 seq, int flags, i++; NLA_PUT_U32(msg, i, NL80211_CMD_SET_WIPHY_NETNS); } + CMD(set_channel, SET_CHANNEL); #undef CMD @@ -689,10 +690,90 @@ static int parse_txq_params(struct nlattr *tb[], return 0; } +static bool nl80211_can_set_dev_channel(struct wireless_dev *wdev) +{ + /* + * You can only set the channel explicitly for AP, mesh + * and WDS type interfaces; all others have their channel + * managed via their respective "establish a connection" + * command (connect, join, ...) + * + * Monitors are special as they are normally slaved to + * whatever else is going on, so they behave as though + * you tried setting the wiphy channel itself. + */ + return !wdev || + wdev->iftype == NL80211_IFTYPE_AP || + wdev->iftype == NL80211_IFTYPE_WDS || + wdev->iftype == NL80211_IFTYPE_MESH_POINT || + wdev->iftype == NL80211_IFTYPE_MONITOR; +} + +static int __nl80211_set_channel(struct cfg80211_registered_device *rdev, + struct wireless_dev *wdev, + struct genl_info *info) +{ + enum nl80211_channel_type channel_type = NL80211_CHAN_NO_HT; + u32 freq; + int result; + + if (!info->attrs[NL80211_ATTR_WIPHY_FREQ]) + return -EINVAL; + + if (!nl80211_can_set_dev_channel(wdev)) + return -EOPNOTSUPP; + + if (info->attrs[NL80211_ATTR_WIPHY_CHANNEL_TYPE]) { + channel_type = nla_get_u32(info->attrs[ + NL80211_ATTR_WIPHY_CHANNEL_TYPE]); + if (channel_type != NL80211_CHAN_NO_HT && + channel_type != NL80211_CHAN_HT20 && + channel_type != NL80211_CHAN_HT40PLUS && + channel_type != NL80211_CHAN_HT40MINUS) + return -EINVAL; + } + + freq = nla_get_u32(info->attrs[NL80211_ATTR_WIPHY_FREQ]); + + mutex_lock(&rdev->devlist_mtx); + if (wdev) { + wdev_lock(wdev); + result = cfg80211_set_freq(rdev, wdev, freq, channel_type); + wdev_unlock(wdev); + } else { + result = cfg80211_set_freq(rdev, NULL, freq, channel_type); + } + mutex_unlock(&rdev->devlist_mtx); + + return result; +} + +static int nl80211_set_channel(struct sk_buff *skb, struct genl_info *info) +{ + struct cfg80211_registered_device *rdev; + struct net_device *netdev; + int result; + + rtnl_lock(); + + result = get_rdev_dev_by_info_ifindex(info, &rdev, &netdev); + if (result) + goto unlock; + + result = __nl80211_set_channel(rdev, netdev->ieee80211_ptr, info); + + unlock: + rtnl_unlock(); + + return result; +} + static int nl80211_set_wiphy(struct sk_buff *skb, struct genl_info *info) { struct cfg80211_registered_device *rdev; - int result = 0, rem_txq_params = 0; + struct net_device *netdev = NULL; + struct wireless_dev *wdev; + int result, rem_txq_params = 0; struct nlattr *nl_txq_params; u32 changed; u8 retry_short = 0, retry_long = 0; @@ -701,16 +782,50 @@ static int nl80211_set_wiphy(struct sk_buff *skb, struct genl_info *info) rtnl_lock(); + /* + * Try to find the wiphy and netdev. Normally this + * function shouldn't need the netdev, but this is + * done for backward compatibility -- previously + * setting the channel was done per wiphy, but now + * it is per netdev. Previous userland like hostapd + * also passed a netdev to set_wiphy, so that it is + * possible to let that go to the right netdev! + */ mutex_lock(&cfg80211_mutex); - rdev = __cfg80211_rdev_from_info(info); - if (IS_ERR(rdev)) { - mutex_unlock(&cfg80211_mutex); - result = PTR_ERR(rdev); - goto unlock; + if (info->attrs[NL80211_ATTR_IFINDEX]) { + int ifindex = nla_get_u32(info->attrs[NL80211_ATTR_IFINDEX]); + + netdev = dev_get_by_index(genl_info_net(info), ifindex); + if (netdev && netdev->ieee80211_ptr) { + rdev = wiphy_to_dev(netdev->ieee80211_ptr->wiphy); + mutex_lock(&rdev->mtx); + } else + netdev = NULL; } - mutex_lock(&rdev->mtx); + if (!netdev) { + rdev = __cfg80211_rdev_from_info(info); + if (IS_ERR(rdev)) { + mutex_unlock(&cfg80211_mutex); + result = PTR_ERR(rdev); + goto unlock; + } + wdev = NULL; + netdev = NULL; + result = 0; + + mutex_lock(&rdev->mtx); + } else if (netif_running(netdev) && + nl80211_can_set_dev_channel(netdev->ieee80211_ptr)) + wdev = netdev->ieee80211_ptr; + else + wdev = NULL; + + /* + * end workaround code, by now the rdev is available + * and locked, and wdev may or may not be NULL. + */ if (info->attrs[NL80211_ATTR_WIPHY_NAME]) result = cfg80211_dev_rename( @@ -749,26 +864,7 @@ static int nl80211_set_wiphy(struct sk_buff *skb, struct genl_info *info) } if (info->attrs[NL80211_ATTR_WIPHY_FREQ]) { - enum nl80211_channel_type channel_type = NL80211_CHAN_NO_HT; - u32 freq; - - result = -EINVAL; - - if (info->attrs[NL80211_ATTR_WIPHY_CHANNEL_TYPE]) { - channel_type = nla_get_u32(info->attrs[ - NL80211_ATTR_WIPHY_CHANNEL_TYPE]); - if (channel_type != NL80211_CHAN_NO_HT && - channel_type != NL80211_CHAN_HT20 && - channel_type != NL80211_CHAN_HT40PLUS && - channel_type != NL80211_CHAN_HT40MINUS) - goto bad_res; - } - - freq = nla_get_u32(info->attrs[NL80211_ATTR_WIPHY_FREQ]); - - mutex_lock(&rdev->devlist_mtx); - result = rdev_set_freq(rdev, NULL, freq, channel_type); - mutex_unlock(&rdev->devlist_mtx); + result = __nl80211_set_channel(rdev, wdev, info); if (result) goto bad_res; } @@ -865,6 +961,8 @@ static int nl80211_set_wiphy(struct sk_buff *skb, struct genl_info *info) bad_res: mutex_unlock(&rdev->mtx); + if (netdev) + dev_put(netdev); unlock: rtnl_unlock(); return result; @@ -3562,9 +3660,8 @@ static int nl80211_associate(struct sk_buff *skb, struct genl_info *info) { struct cfg80211_registered_device *rdev; struct net_device *dev; - struct wireless_dev *wdev; struct cfg80211_crypto_settings crypto; - struct ieee80211_channel *chan, *fixedchan; + struct ieee80211_channel *chan; const u8 *bssid, *ssid, *ie = NULL, *prev_bssid = NULL; int err, ssid_len, ie_len = 0; bool use_mfp = false; @@ -3607,16 +3704,6 @@ static int nl80211_associate(struct sk_buff *skb, struct genl_info *info) goto out; } - mutex_lock(&rdev->devlist_mtx); - wdev = dev->ieee80211_ptr; - fixedchan = rdev_fixed_channel(rdev, wdev); - if (fixedchan && chan != fixedchan) { - err = -EBUSY; - mutex_unlock(&rdev->devlist_mtx); - goto out; - } - mutex_unlock(&rdev->devlist_mtx); - ssid = nla_data(info->attrs[NL80211_ATTR_SSID]); ssid_len = nla_len(info->attrs[NL80211_ATTR_SSID]); @@ -5186,6 +5273,12 @@ static struct genl_ops nl80211_ops[] = { .policy = nl80211_policy, .flags = GENL_ADMIN_PERM, }, + { + .cmd = NL80211_CMD_SET_CHANNEL, + .doit = nl80211_set_channel, + .policy = nl80211_policy, + .flags = GENL_ADMIN_PERM, + }, }; static struct genl_multicast_group nl80211_mlme_mcgrp = { diff --git a/net/wireless/sme.c b/net/wireless/sme.c index 8ddf5ae0dd03..72222f0074db 100644 --- a/net/wireless/sme.c +++ b/net/wireless/sme.c @@ -741,7 +741,6 @@ int __cfg80211_connect(struct cfg80211_registered_device *rdev, const u8 *prev_bssid) { struct wireless_dev *wdev = dev->ieee80211_ptr; - struct ieee80211_channel *chan; struct cfg80211_bss *bss = NULL; int err; @@ -750,10 +749,6 @@ int __cfg80211_connect(struct cfg80211_registered_device *rdev, if (wdev->sme_state != CFG80211_SME_IDLE) return -EALREADY; - chan = rdev_fixed_channel(rdev, wdev); - if (chan && chan != connect->channel) - return -EBUSY; - if (WARN_ON(wdev->connect_keys)) { kfree(wdev->connect_keys); wdev->connect_keys = NULL; diff --git a/net/wireless/wext-compat.c b/net/wireless/wext-compat.c index a60a2773b497..96342993cf93 100644 --- a/net/wireless/wext-compat.c +++ b/net/wireless/wext-compat.c @@ -782,16 +782,22 @@ int cfg80211_wext_siwfreq(struct net_device *dev, return cfg80211_mgd_wext_siwfreq(dev, info, wextfreq, extra); case NL80211_IFTYPE_ADHOC: return cfg80211_ibss_wext_siwfreq(dev, info, wextfreq, extra); - default: + case NL80211_IFTYPE_MONITOR: + case NL80211_IFTYPE_WDS: + case NL80211_IFTYPE_MESH_POINT: freq = cfg80211_wext_freq(wdev->wiphy, wextfreq); if (freq < 0) return freq; if (freq == 0) return -EINVAL; + wdev_lock(wdev); mutex_lock(&rdev->devlist_mtx); - err = rdev_set_freq(rdev, NULL, freq, NL80211_CHAN_NO_HT); + err = cfg80211_set_freq(rdev, wdev, freq, NL80211_CHAN_NO_HT); mutex_unlock(&rdev->devlist_mtx); + wdev_unlock(wdev); return err; + default: + return -EOPNOTSUPP; } } EXPORT_SYMBOL_GPL(cfg80211_wext_siwfreq); @@ -801,7 +807,6 @@ int cfg80211_wext_giwfreq(struct net_device *dev, struct iw_freq *freq, char *extra) { struct wireless_dev *wdev = dev->ieee80211_ptr; - struct cfg80211_registered_device *rdev = wiphy_to_dev(wdev->wiphy); switch (wdev->iftype) { case NL80211_IFTYPE_STATION: @@ -809,9 +814,9 @@ int cfg80211_wext_giwfreq(struct net_device *dev, case NL80211_IFTYPE_ADHOC: return cfg80211_ibss_wext_giwfreq(dev, info, freq, extra); default: - if (!rdev->channel) + if (!wdev->channel) return -EINVAL; - freq->m = rdev->channel->center_freq; + freq->m = wdev->channel->center_freq; freq->e = 6; return 0; } diff --git a/net/wireless/wext-sme.c b/net/wireless/wext-sme.c index d5c6140f4cb8..9818198add8a 100644 --- a/net/wireless/wext-sme.c +++ b/net/wireless/wext-sme.c @@ -108,7 +108,7 @@ int cfg80211_mgd_wext_siwfreq(struct net_device *dev, /* SSID is not set, we just want to switch channel */ if (chan && !wdev->wext.connect.ssid_len) { - err = rdev_set_freq(rdev, wdev, freq, NL80211_CHAN_NO_HT); + err = cfg80211_set_freq(rdev, wdev, freq, NL80211_CHAN_NO_HT); goto out; } |
