X-Git-Url: http://ftp.safe.ca/?a=blobdiff_plain;f=net%2Fsctp%2Fprotocol.c;h=182749867c72a4c2b629d8675e1ad2de6340a536;hb=b2e75eff5e859d0c294e7405958362b26a423c6e;hp=20883ffd51d95ef3bfef6479fe9c4b0fdf989465;hpb=09ef7fecea40c5e4c0dfe35bed3f0ed8da554cf5;p=safe%2Fjmp%2Flinux-2.6 diff --git a/net/sctp/protocol.c b/net/sctp/protocol.c index 20883ff..1827498 100644 --- a/net/sctp/protocol.c +++ b/net/sctp/protocol.c @@ -1,4 +1,4 @@ -/* SCTP kernel reference Implementation +/* SCTP kernel implementation * (C) Copyright IBM Corp. 2001, 2004 * Copyright (c) 1999-2000 Cisco, Inc. * Copyright (c) 1999-2001 Motorola, Inc. @@ -6,17 +6,17 @@ * Copyright (c) 2001 Nokia, Inc. * Copyright (c) 2001 La Monte H.P. Yarroll * - * This file is part of the SCTP kernel reference Implementation + * This file is part of the SCTP kernel implementation * * Initialization/cleanup for SCTP protocol support. * - * The SCTP reference implementation is free software; + * This SCTP implementation is free software; * you can redistribute it and/or modify it under the terms of * the GNU General Public License as published by * the Free Software Foundation; either version 2, or (at your option) * any later version. * - * The SCTP reference implementation is distributed in the hope that it + * This SCTP implementation is distributed in the hope that it * will be useful, but WITHOUT ANY WARRANTY; without even the implied * ************************ * warranty of MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. @@ -51,6 +51,11 @@ #include #include #include +#include +#include +#include +#include +#include #include #include #include @@ -62,9 +67,12 @@ /* Global data structures. */ struct sctp_globals sctp_globals __read_mostly; -struct proc_dir_entry *proc_net_sctp; DEFINE_SNMP_STAT(struct sctp_mib, sctp_statistics) __read_mostly; +#ifdef CONFIG_PROC_FS +struct proc_dir_entry *proc_net_sctp; +#endif + struct idr sctp_assocs_id; DEFINE_SPINLOCK(sctp_assocs_id_lock); @@ -72,62 +80,88 @@ DEFINE_SPINLOCK(sctp_assocs_id_lock); * the Out-of-the-blue (OOTB) packets. A control sock will be created * for this socket at the initialization time. */ -static struct socket *sctp_ctl_socket; +static struct sock *sctp_ctl_sock; static struct sctp_pf *sctp_pf_inet6_specific; static struct sctp_pf *sctp_pf_inet_specific; static struct sctp_af *sctp_af_v4_specific; static struct sctp_af *sctp_af_v6_specific; -kmem_cache_t *sctp_chunk_cachep __read_mostly; -kmem_cache_t *sctp_bucket_cachep __read_mostly; +struct kmem_cache *sctp_chunk_cachep __read_mostly; +struct kmem_cache *sctp_bucket_cachep __read_mostly; + +int sysctl_sctp_mem[3]; +int sysctl_sctp_rmem[3]; +int sysctl_sctp_wmem[3]; /* Return the address of the control sock. */ struct sock *sctp_get_ctl_sock(void) { - return sctp_ctl_socket->sk; + return sctp_ctl_sock; } /* Set up the proc fs entry for the SCTP protocol. */ static __init int sctp_proc_init(void) { + if (percpu_counter_init(&sctp_sockets_allocated, 0)) + goto out_nomem; +#ifdef CONFIG_PROC_FS if (!proc_net_sctp) { - struct proc_dir_entry *ent; - ent = proc_mkdir("net/sctp", NULL); - if (ent) { - ent->owner = THIS_MODULE; - proc_net_sctp = ent; - } else - goto out_nomem; + proc_net_sctp = proc_mkdir("sctp", init_net.proc_net); + if (!proc_net_sctp) + goto out_free_percpu; } if (sctp_snmp_proc_init()) - goto out_nomem; + goto out_snmp_proc_init; if (sctp_eps_proc_init()) - goto out_nomem; + goto out_eps_proc_init; if (sctp_assocs_proc_init()) - goto out_nomem; + goto out_assocs_proc_init; + if (sctp_remaddr_proc_init()) + goto out_remaddr_proc_init; return 0; +out_remaddr_proc_init: + sctp_assocs_proc_exit(); +out_assocs_proc_init: + sctp_eps_proc_exit(); +out_eps_proc_init: + sctp_snmp_proc_exit(); +out_snmp_proc_init: + if (proc_net_sctp) { + proc_net_sctp = NULL; + remove_proc_entry("sctp", init_net.proc_net); + } +out_free_percpu: + percpu_counter_destroy(&sctp_sockets_allocated); +#else + return 0; +#endif /* CONFIG_PROC_FS */ + out_nomem: return -ENOMEM; } -/* Clean up the proc fs entry for the SCTP protocol. +/* Clean up the proc fs entry for the SCTP protocol. * Note: Do not make this __exit as it is used in the init error * path. */ static void sctp_proc_exit(void) { +#ifdef CONFIG_PROC_FS sctp_snmp_proc_exit(); sctp_eps_proc_exit(); sctp_assocs_proc_exit(); + sctp_remaddr_proc_exit(); if (proc_net_sctp) { proc_net_sctp = NULL; - remove_proc_entry("net/sctp", NULL); + remove_proc_entry("sctp", init_net.proc_net); } +#endif + percpu_counter_destroy(&sctp_sockets_allocated); } /* Private helper to extract ipv4 address and stash them in @@ -150,9 +184,11 @@ static void sctp_v4_copy_addrlist(struct list_head *addrlist, /* Add the address to the local list. */ addr = t_new(struct sctp_sockaddr_entry, GFP_ATOMIC); if (addr) { - addr->a_h.v4.sin_family = AF_INET; - addr->a_h.v4.sin_port = 0; - addr->a_h.v4.sin_addr.s_addr = ifa->ifa_local; + addr->a.v4.sin_family = AF_INET; + addr->a.v4.sin_port = 0; + addr->a.v4.sin_addr.s_addr = ifa->ifa_local; + addr->valid = 1; + INIT_LIST_HEAD(&addr->list); list_add_tail(&addr->list, addrlist); } } @@ -163,33 +199,24 @@ static void sctp_v4_copy_addrlist(struct list_head *addrlist, /* Extract our IP addresses from the system and stash them in the * protocol structure. */ -static void __sctp_get_local_addr_list(void) +static void sctp_get_local_addr_list(void) { struct net_device *dev; struct list_head *pos; struct sctp_af *af; - read_lock(&dev_base_lock); - for (dev = dev_base; dev; dev = dev->next) { + rcu_read_lock(); + for_each_netdev_rcu(&init_net, dev) { __list_for_each(pos, &sctp_address_families) { af = list_entry(pos, struct sctp_af, list); af->copy_addrlist(&sctp_local_addr_list, dev); } } - read_unlock(&dev_base_lock); -} - -static void sctp_get_local_addr_list(void) -{ - unsigned long flags; - - sctp_spin_lock_irqsave(&sctp_local_addr_lock, flags); - __sctp_get_local_addr_list(); - sctp_spin_unlock_irqrestore(&sctp_local_addr_lock, flags); + rcu_read_unlock(); } /* Free the existing local addresses. */ -static void __sctp_free_local_addr_list(void) +static void sctp_free_local_addr_list(void) { struct sctp_sockaddr_entry *addr; struct list_head *pos, *temp; @@ -201,14 +228,11 @@ static void __sctp_free_local_addr_list(void) } } -/* Free the existing local addresses. */ -static void sctp_free_local_addr_list(void) +void sctp_local_addr_free(struct rcu_head *head) { - unsigned long flags; - - sctp_spin_lock_irqsave(&sctp_local_addr_lock, flags); - __sctp_free_local_addr_list(); - sctp_spin_unlock_irqrestore(&sctp_local_addr_lock, flags); + struct sctp_sockaddr_entry *e = container_of(head, + struct sctp_sockaddr_entry, rcu); + kfree(e); } /* Copy the local addresses which are valid for 'scope' into 'bp'. */ @@ -217,24 +241,23 @@ int sctp_copy_local_addr_list(struct sctp_bind_addr *bp, sctp_scope_t scope, { struct sctp_sockaddr_entry *addr; int error = 0; - struct list_head *pos; - unsigned long flags; - sctp_spin_lock_irqsave(&sctp_local_addr_lock, flags); - list_for_each(pos, &sctp_local_addr_list) { - addr = list_entry(pos, struct sctp_sockaddr_entry, list); - if (sctp_in_scope(&addr->a_h, scope)) { + rcu_read_lock(); + list_for_each_entry_rcu(addr, &sctp_local_addr_list, list) { + if (!addr->valid) + continue; + if (sctp_in_scope(&addr->a, scope)) { /* Now that the address is in scope, check to see if * the address type is really supported by the local * sock as well as the remote peer. */ - if ((((AF_INET == addr->a_h.sa.sa_family) && + if ((((AF_INET == addr->a.sa.sa_family) && (copy_flags & SCTP_ADDR4_PEERSUPP))) || - (((AF_INET6 == addr->a_h.sa.sa_family) && + (((AF_INET6 == addr->a.sa.sa_family) && (copy_flags & SCTP_ADDR6_ALLOWED) && (copy_flags & SCTP_ADDR6_PEERSUPP)))) { - error = sctp_add_bind_addr(bp, &addr->a_h, 1, - GFP_ATOMIC); + error = sctp_add_bind_addr(bp, &addr->a, + SCTP_ADDR_SRC, GFP_ATOMIC); if (error) goto end_copy; } @@ -242,7 +265,7 @@ int sctp_copy_local_addr_list(struct sctp_bind_addr *bp, sctp_scope_t scope, } end_copy: - sctp_spin_unlock_irqrestore(&sctp_local_addr_lock, flags); + rcu_read_unlock(); return error; } @@ -251,19 +274,19 @@ static void sctp_v4_from_skb(union sctp_addr *addr, struct sk_buff *skb, int is_saddr) { void *from; - __u16 *port; + __be16 *port; struct sctphdr *sh; port = &addr->v4.sin_port; addr->v4.sin_family = AF_INET; - sh = (struct sctphdr *) skb->h.raw; + sh = sctp_hdr(skb); if (is_saddr) { - *port = ntohs(sh->source); - from = &skb->nh.iph->saddr; + *port = sh->source; + from = &ip_hdr(skb)->saddr; } else { - *port = ntohs(sh->dest); - from = &skb->nh.iph->daddr; + *port = sh->dest; + from = &ip_hdr(skb)->daddr; } memcpy(&addr->v4.sin_addr.s_addr, from, sizeof(struct in_addr)); } @@ -272,26 +295,26 @@ static void sctp_v4_from_skb(union sctp_addr *addr, struct sk_buff *skb, static void sctp_v4_from_sk(union sctp_addr *addr, struct sock *sk) { addr->v4.sin_family = AF_INET; - addr->v4.sin_port = inet_sk(sk)->num; - addr->v4.sin_addr.s_addr = inet_sk(sk)->rcv_saddr; + addr->v4.sin_port = 0; + addr->v4.sin_addr.s_addr = inet_sk(sk)->inet_rcv_saddr; } /* Initialize sk->sk_rcv_saddr from sctp_addr. */ static void sctp_v4_to_sk_saddr(union sctp_addr *addr, struct sock *sk) { - inet_sk(sk)->rcv_saddr = addr->v4.sin_addr.s_addr; + inet_sk(sk)->inet_rcv_saddr = addr->v4.sin_addr.s_addr; } /* Initialize sk->sk_daddr from sctp_addr. */ static void sctp_v4_to_sk_daddr(union sctp_addr *addr, struct sock *sk) { - inet_sk(sk)->daddr = addr->v4.sin_addr.s_addr; + inet_sk(sk)->inet_daddr = addr->v4.sin_addr.s_addr; } /* Initialize a sctp_addr from an address parameter. */ static void sctp_v4_from_addr_param(union sctp_addr *addr, union sctp_addr_param *param, - __u16 port, int iif) + __be16 port, int iif) { addr->v4.sin_family = AF_INET; addr->v4.sin_port = port; @@ -308,14 +331,14 @@ static int sctp_v4_to_addr_param(const union sctp_addr *addr, param->v4.param_hdr.type = SCTP_PARAM_IPV4_ADDRESS; param->v4.param_hdr.length = htons(length); - param->v4.addr.s_addr = addr->v4.sin_addr.s_addr; + param->v4.addr.s_addr = addr->v4.sin_addr.s_addr; return length; } /* Initialize a sctp_addr from a dst_entry. */ static void sctp_v4_dst_saddr(union sctp_addr *saddr, struct dst_entry *dst, - unsigned short port) + __be16 port) { struct rtable *rt = (struct rtable *)dst; saddr->v4.sin_family = AF_INET; @@ -338,17 +361,17 @@ static int sctp_v4_cmp_addr(const union sctp_addr *addr1, } /* Initialize addr struct to INADDR_ANY. */ -static void sctp_v4_inaddr_any(union sctp_addr *addr, unsigned short port) +static void sctp_v4_inaddr_any(union sctp_addr *addr, __be16 port) { addr->v4.sin_family = AF_INET; - addr->v4.sin_addr.s_addr = INADDR_ANY; + addr->v4.sin_addr.s_addr = htonl(INADDR_ANY); addr->v4.sin_port = port; } /* Is this a wildcard address? */ static int sctp_v4_is_any(const union sctp_addr *addr) { - return INADDR_ANY == addr->v4.sin_addr.s_addr; + return htonl(INADDR_ANY) == addr->v4.sin_addr.s_addr; } /* This function checks if the address is a valid address to be used for @@ -362,13 +385,17 @@ static int sctp_v4_addr_valid(union sctp_addr *addr, struct sctp_sock *sp, const struct sk_buff *skb) { + /* IPv4 addresses not allowed */ + if (sp && ipv6_only_sock(sctp_opt2sk(sp))) + return 0; + /* Is this a non-unicast address or a unusable SCTP address? */ - if (IS_IPV4_UNUSABLE_ADDRESS(&addr->v4.sin_addr.s_addr)) + if (IS_IPV4_UNUSABLE_ADDRESS(addr->v4.sin_addr.s_addr)) return 0; - /* Is this a broadcast address? */ - if (skb && ((struct rtable *)skb->dst)->rt_flags & RTCF_BROADCAST) - return 0; + /* Is this a broadcast address? */ + if (skb && skb_rtable(skb)->rt_flags & RTCF_BROADCAST) + return 0; return 1; } @@ -376,15 +403,18 @@ static int sctp_v4_addr_valid(union sctp_addr *addr, /* Should this be available for binding? */ static int sctp_v4_available(union sctp_addr *addr, struct sctp_sock *sp) { - int ret = inet_addr_type(addr->v4.sin_addr.s_addr); + int ret = inet_addr_type(&init_net, addr->v4.sin_addr.s_addr); - if (addr->v4.sin_addr.s_addr != INADDR_ANY && + if (addr->v4.sin_addr.s_addr != htonl(INADDR_ANY) && ret != RTN_LOCAL && !sp->inet.freebind && !sysctl_ip_nonlocal_bind) return 0; + if (ipv6_only_sock(sctp_opt2sk(sp))) + return 0; + return 1; } @@ -401,24 +431,24 @@ static int sctp_v4_available(union sctp_addr *addr, struct sctp_sock *sp) * of requested destination address, sender and receiver * SHOULD include all of its addresses with level greater * than or equal to L. + * + * IPv4 scoping can be controlled through sysctl option + * net.sctp.addr_scope_policy */ static sctp_scope_t sctp_v4_scope(union sctp_addr *addr) { sctp_scope_t retval; - /* Should IPv4 scoping be a sysctl configurable option - * so users can turn it off (default on) for certain - * unconventional networking environments? - */ - /* Check for unusable SCTP addresses. */ - if (IS_IPV4_UNUSABLE_ADDRESS(&addr->v4.sin_addr.s_addr)) { + if (IS_IPV4_UNUSABLE_ADDRESS(addr->v4.sin_addr.s_addr)) { retval = SCTP_SCOPE_UNUSABLE; - } else if (LOOPBACK(addr->v4.sin_addr.s_addr)) { + } else if (ipv4_is_loopback(addr->v4.sin_addr.s_addr)) { retval = SCTP_SCOPE_LOOPBACK; - } else if (IS_IPV4_LINK_ADDRESS(&addr->v4.sin_addr.s_addr)) { + } else if (ipv4_is_linklocal_169(addr->v4.sin_addr.s_addr)) { retval = SCTP_SCOPE_LINK; - } else if (IS_IPV4_PRIVATE_ADDRESS(&addr->v4.sin_addr.s_addr)) { + } else if (ipv4_is_private_10(addr->v4.sin_addr.s_addr) || + ipv4_is_private_172(addr->v4.sin_addr.s_addr) || + ipv4_is_private_192(addr->v4.sin_addr.s_addr)) { retval = SCTP_SCOPE_PRIVATE; } else { retval = SCTP_SCOPE_GLOBAL; @@ -438,27 +468,28 @@ static struct dst_entry *sctp_v4_get_dst(struct sctp_association *asoc, struct rtable *rt; struct flowi fl; struct sctp_bind_addr *bp; - rwlock_t *addr_lock; struct sctp_sockaddr_entry *laddr; - struct list_head *pos; struct dst_entry *dst = NULL; union sctp_addr dst_saddr; memset(&fl, 0x0, sizeof(struct flowi)); fl.fl4_dst = daddr->v4.sin_addr.s_addr; + fl.fl_ip_dport = daddr->v4.sin_port; fl.proto = IPPROTO_SCTP; if (asoc) { fl.fl4_tos = RT_CONN_FLAGS(asoc->base.sk); fl.oif = asoc->base.sk->sk_bound_dev_if; + fl.fl_ip_sport = htons(asoc->base.bind_addr.port); } - if (saddr) + if (saddr) { fl.fl4_src = saddr->v4.sin_addr.s_addr; + fl.fl_ip_sport = saddr->v4.sin_port; + } - SCTP_DEBUG_PRINTK("%s: DST:%u.%u.%u.%u, SRC:%u.%u.%u.%u - ", - __FUNCTION__, NIPQUAD(fl.fl4_dst), - NIPQUAD(fl.fl4_src)); + SCTP_DEBUG_PRINTK("%s: DST:%pI4, SRC:%pI4 - ", + __func__, &fl.fl4_dst, &fl.fl4_src); - if (!ip_route_output_key(&rt, &fl)) { + if (!ip_route_output_key(&init_net, &rt, &fl)) { dst = &rt->u.dst; } @@ -469,23 +500,20 @@ static struct dst_entry *sctp_v4_get_dst(struct sctp_association *asoc, goto out; bp = &asoc->base.bind_addr; - addr_lock = &asoc->base.addr_lock; if (dst) { /* Walk through the bind address list and look for a bind * address that matches the source address of the returned dst. */ - sctp_read_lock(addr_lock); - list_for_each(pos, &bp->address_list) { - laddr = list_entry(pos, struct sctp_sockaddr_entry, - list); - if (!laddr->use_as_src) + sctp_v4_dst_saddr(&dst_saddr, dst, htons(bp->port)); + rcu_read_lock(); + list_for_each_entry_rcu(laddr, &bp->address_list, list) { + if (!laddr->valid || (laddr->state != SCTP_ADDR_SRC)) continue; - sctp_v4_dst_saddr(&dst_saddr, dst, bp->port); - if (sctp_v4_cmp_addr(&dst_saddr, &laddr->a_h)) + if (sctp_v4_cmp_addr(&dst_saddr, &laddr->a)) goto out_unlock; } - sctp_read_unlock(addr_lock); + rcu_read_unlock(); /* None of the bound addresses match the source address of the * dst. So release it. @@ -497,14 +525,15 @@ static struct dst_entry *sctp_v4_get_dst(struct sctp_association *asoc, /* Walk through the bind address list and try to get a dst that * matches a bind address as the source address. */ - sctp_read_lock(addr_lock); - list_for_each(pos, &bp->address_list) { - laddr = list_entry(pos, struct sctp_sockaddr_entry, list); - - if ((laddr->use_as_src) && - (AF_INET == laddr->a_h.sa.sa_family)) { - fl.fl4_src = laddr->a_h.v4.sin_addr.s_addr; - if (!ip_route_output_key(&rt, &fl)) { + rcu_read_lock(); + list_for_each_entry_rcu(laddr, &bp->address_list, list) { + if (!laddr->valid) + continue; + if ((laddr->state == SCTP_ADDR_SRC) && + (AF_INET == laddr->a.sa.sa_family)) { + fl.fl4_src = laddr->a.v4.sin_addr.s_addr; + fl.fl_ip_sport = laddr->a.v4.sin_port; + if (!ip_route_output_key(&init_net, &rt, &fl)) { dst = &rt->u.dst; goto out_unlock; } @@ -512,11 +541,11 @@ static struct dst_entry *sctp_v4_get_dst(struct sctp_association *asoc, } out_unlock: - sctp_read_unlock(addr_lock); + rcu_read_unlock(); out: if (dst) - SCTP_DEBUG_PRINTK("rt_dst:%u.%u.%u.%u, rt_src:%u.%u.%u.%u\n", - NIPQUAD(rt->rt_dst), NIPQUAD(rt->rt_src)); + SCTP_DEBUG_PRINTK("rt_dst:%pI4, rt_src:%pI4\n", + &rt->rt_dst, &rt->rt_src); else SCTP_DEBUG_PRINTK("NO ROUTE\n"); @@ -526,7 +555,8 @@ out: /* For v4, the source address is cached in the route entry(dst). So no need * to cache it separately and hence this is an empty routine. */ -static void sctp_v4_get_saddr(struct sctp_association *asoc, +static void sctp_v4_get_saddr(struct sctp_sock *sk, + struct sctp_association *asoc, struct dst_entry *dst, union sctp_addr *daddr, union sctp_addr *saddr) @@ -538,66 +568,42 @@ static void sctp_v4_get_saddr(struct sctp_association *asoc, if (rt) { saddr->v4.sin_family = AF_INET; - saddr->v4.sin_port = asoc->base.bind_addr.port; - saddr->v4.sin_addr.s_addr = rt->rt_src; + saddr->v4.sin_port = htons(asoc->base.bind_addr.port); + saddr->v4.sin_addr.s_addr = rt->rt_src; } } /* What interface did this skb arrive on? */ static int sctp_v4_skb_iif(const struct sk_buff *skb) { - return ((struct rtable *)skb->dst)->rt_iif; + return skb_rtable(skb)->rt_iif; } /* Was this packet marked by Explicit Congestion Notification? */ static int sctp_v4_is_ce(const struct sk_buff *skb) { - return INET_ECN_is_ce(skb->nh.iph->tos); + return INET_ECN_is_ce(ip_hdr(skb)->tos); } /* Create and initialize a new sk for the socket returned by accept(). */ static struct sock *sctp_v4_create_accept_sk(struct sock *sk, struct sctp_association *asoc) { - struct inet_sock *inet = inet_sk(sk); + struct sock *newsk = sk_alloc(sock_net(sk), PF_INET, GFP_KERNEL, + sk->sk_prot); struct inet_sock *newinet; - struct sock *newsk = sk_alloc(PF_INET, GFP_KERNEL, sk->sk_prot, 1); if (!newsk) goto out; sock_init_data(NULL, newsk); - newsk->sk_type = SOCK_STREAM; - - newsk->sk_no_check = sk->sk_no_check; - newsk->sk_reuse = sk->sk_reuse; - newsk->sk_shutdown = sk->sk_shutdown; - - newsk->sk_destruct = inet_sock_destruct; - newsk->sk_family = PF_INET; - newsk->sk_protocol = IPPROTO_SCTP; - newsk->sk_backlog_rcv = sk->sk_prot->backlog_rcv; + sctp_copy_sock(newsk, sk, asoc); sock_reset_flag(newsk, SOCK_ZAPPED); newinet = inet_sk(newsk); - /* Initialize sk's sport, dport, rcv_saddr and daddr for - * getsockname() and getpeername() - */ - newinet->sport = inet->sport; - newinet->saddr = inet->saddr; - newinet->rcv_saddr = inet->rcv_saddr; - newinet->dport = htons(asoc->peer.port); - newinet->daddr = asoc->peer.primary_addr.v4.sin_addr.s_addr; - newinet->pmtudisc = inet->pmtudisc; - newinet->id = asoc->next_tsn ^ jiffies; - - newinet->uc_ttl = -1; - newinet->mc_loop = 1; - newinet->mc_ttl = 1; - newinet->mc_index = 0; - newinet->mc_list = NULL; + newinet->inet_daddr = asoc->peer.primary_addr.v4.sin_addr.s_addr; sk_refcnt_debug_inc(newsk); @@ -619,21 +625,62 @@ static void sctp_v4_addr_v4map(struct sctp_sock *sp, union sctp_addr *addr) /* Dump the v4 addr to the seq file. */ static void sctp_v4_seq_dump_addr(struct seq_file *seq, union sctp_addr *addr) { - seq_printf(seq, "%d.%d.%d.%d ", NIPQUAD(addr->v4.sin_addr)); + seq_printf(seq, "%pI4 ", &addr->v4.sin_addr); +} + +static void sctp_v4_ecn_capable(struct sock *sk) +{ + INET_ECN_xmit(sk); } /* Event handler for inet address addition/deletion events. - * Basically, whenever there is an event, we re-build our local address list. + * The sctp_local_addr_list needs to be protocted by a spin lock since + * multiple notifiers (say IPv4 and IPv6) may be running at the same + * time and thus corrupt the list. + * The reader side is protected with RCU. */ -int sctp_inetaddr_event(struct notifier_block *this, unsigned long ev, - void *ptr) +static int sctp_inetaddr_event(struct notifier_block *this, unsigned long ev, + void *ptr) { - unsigned long flags; + struct in_ifaddr *ifa = (struct in_ifaddr *)ptr; + struct sctp_sockaddr_entry *addr = NULL; + struct sctp_sockaddr_entry *temp; + int found = 0; - sctp_spin_lock_irqsave(&sctp_local_addr_lock, flags); - __sctp_free_local_addr_list(); - __sctp_get_local_addr_list(); - sctp_spin_unlock_irqrestore(&sctp_local_addr_lock, flags); + if (!net_eq(dev_net(ifa->ifa_dev->dev), &init_net)) + return NOTIFY_DONE; + + switch (ev) { + case NETDEV_UP: + addr = kmalloc(sizeof(struct sctp_sockaddr_entry), GFP_ATOMIC); + if (addr) { + addr->a.v4.sin_family = AF_INET; + addr->a.v4.sin_port = 0; + addr->a.v4.sin_addr.s_addr = ifa->ifa_local; + addr->valid = 1; + spin_lock_bh(&sctp_local_addr_lock); + list_add_tail_rcu(&addr->list, &sctp_local_addr_list); + spin_unlock_bh(&sctp_local_addr_lock); + } + break; + case NETDEV_DOWN: + spin_lock_bh(&sctp_local_addr_lock); + list_for_each_entry_safe(addr, temp, + &sctp_local_addr_list, list) { + if (addr->a.sa.sa_family == AF_INET && + addr->a.v4.sin_addr.s_addr == + ifa->ifa_local) { + found = 1; + addr->valid = 0; + list_del_rcu(&addr->list); + break; + } + } + spin_unlock_bh(&sctp_local_addr_lock); + if (found) + call_rcu(&addr->rcu, sctp_local_addr_free); + break; + } return NOTIFY_DONE; } @@ -645,23 +692,25 @@ int sctp_inetaddr_event(struct notifier_block *this, unsigned long ev, static int sctp_ctl_sock_init(void) { int err; - sa_family_t family; + sa_family_t family = PF_INET; if (sctp_get_pf_specific(PF_INET6)) family = PF_INET6; - else - family = PF_INET; - err = sock_create_kern(family, SOCK_SEQPACKET, IPPROTO_SCTP, - &sctp_ctl_socket); + err = inet_ctl_sock_create(&sctp_ctl_sock, family, + SOCK_SEQPACKET, IPPROTO_SCTP, &init_net); + + /* If IPv6 socket could not be created, try the IPv4 socket */ + if (err < 0 && family == PF_INET6) + err = inet_ctl_sock_create(&sctp_ctl_sock, AF_INET, + SOCK_SEQPACKET, IPPROTO_SCTP, + &init_net); + if (err < 0) { printk(KERN_ERR "SCTP: Failed to create the SCTP control socket.\n"); return err; } - sctp_ctl_socket->sk->sk_allocation = GFP_ATOMIC; - inet_sk(sctp_ctl_socket->sk)->uc_ttl = -1; - return 0; } @@ -735,15 +784,13 @@ static void sctp_inet_event_msgname(struct sctp_ulpevent *event, char *msgname, /* Initialize and copy out a msgname from an inbound skb. */ static void sctp_inet_skb_msgname(struct sk_buff *skb, char *msgname, int *len) { - struct sctphdr *sh; - struct sockaddr_in *sin; - if (msgname) { + struct sctphdr *sh = sctp_hdr(skb); + struct sockaddr_in *sin = (struct sockaddr_in *)msgname; + sctp_inet_msgname(msgname, len); - sin = (struct sockaddr_in *)msgname; - sh = (struct sctphdr *)skb->h.raw; sin->sin_port = sh->source; - sin->sin_addr.s_addr = skb->nh.iph->saddr; + sin->sin_addr.s_addr = ip_hdr(skb)->saddr; } } @@ -762,8 +809,8 @@ static int sctp_inet_cmp_addr(const union sctp_addr *addr1, /* PF_INET only supports AF_INET addresses. */ if (addr1->sa.sa_family != addr2->sa.sa_family) return 0; - if (INADDR_ANY == addr1->v4.sin_addr.s_addr || - INADDR_ANY == addr2->v4.sin_addr.s_addr) + if (htonl(INADDR_ANY) == addr1->v4.sin_addr.s_addr || + htonl(INADDR_ANY) == addr2->v4.sin_addr.s_addr) return 1; if (addr1->v4.sin_addr.s_addr == addr2->v4.sin_addr.s_addr) return 1; @@ -791,7 +838,7 @@ static int sctp_inet_send_verify(struct sctp_sock *opt, union sctp_addr *addr) * chunks. Returns number of addresses supported. */ static int sctp_inet_supported_addrs(const struct sctp_sock *opt, - __u16 *types) + __be16 *types) { types[0] = SCTP_PARAM_IPV4_ADDRESS; return 1; @@ -799,19 +846,23 @@ static int sctp_inet_supported_addrs(const struct sctp_sock *opt, /* Wrapper routine that calls the ip transmit routine. */ static inline int sctp_v4_xmit(struct sk_buff *skb, - struct sctp_transport *transport, int ipfragok) + struct sctp_transport *transport) { - SCTP_DEBUG_PRINTK("%s: skb:%p, len:%d, " - "src:%u.%u.%u.%u, dst:%u.%u.%u.%u\n", - __FUNCTION__, skb, skb->len, - NIPQUAD(((struct rtable *)skb->dst)->rt_src), - NIPQUAD(((struct rtable *)skb->dst)->rt_dst)); + struct inet_sock *inet = inet_sk(skb->sk); + + SCTP_DEBUG_PRINTK("%s: skb:%p, len:%d, src:%pI4, dst:%pI4\n", + __func__, skb, skb->len, + &skb_rtable(skb)->rt_src, + &skb_rtable(skb)->rt_dst); + + inet->pmtudisc = transport->param_flags & SPP_PMTUD_ENABLE ? + IP_PMTUDISC_DO : IP_PMTUDISC_DONT; SCTP_INC_STATS(SCTP_MIB_OUTSCTPPACKS); - return ip_queue_xmit(skb, skb->sk, ipfragok); + return ip_queue_xmit(skb); } -static struct sctp_af sctp_ipv4_specific; +static struct sctp_af sctp_af_inet; static struct sctp_pf sctp_pf_inet = { .event_msgname = sctp_inet_event_msgname, @@ -823,7 +874,7 @@ static struct sctp_pf sctp_pf_inet = { .supported_addrs = sctp_inet_supported_addrs, .create_accept_sk = sctp_v4_create_accept_sk, .addr_v4map = sctp_v4_addr_v4map, - .af = &sctp_ipv4_specific, + .af = &sctp_af_inet }; /* Notifier for inetaddr addition/deletion events. */ @@ -863,7 +914,6 @@ static struct inet_protosw sctp_seqpacket_protosw = { .protocol = IPPROTO_SCTP, .prot = &sctp_prot, .ops = &inet_seqpacket_ops, - .capability = -1, .no_check = 0, .flags = SCTP_PROTOSW_FLAG }; @@ -872,20 +922,19 @@ static struct inet_protosw sctp_stream_protosw = { .protocol = IPPROTO_SCTP, .prot = &sctp_prot, .ops = &inet_seqpacket_ops, - .capability = -1, .no_check = 0, .flags = SCTP_PROTOSW_FLAG }; /* Register with IP layer. */ -static struct net_protocol sctp_protocol = { +static const struct net_protocol sctp_protocol = { .handler = sctp_rcv, .err_handler = sctp_v4_err, .no_policy = 1, }; /* IPv4 address related functions. */ -static struct sctp_af sctp_ipv4_specific = { +static struct sctp_af sctp_af_inet = { .sa_family = AF_INET, .sctp_xmit = sctp_v4_xmit, .setsockopt = ip_setsockopt, @@ -909,6 +958,7 @@ static struct sctp_af sctp_ipv4_specific = { .skb_iif = sctp_v4_skb_iif, .is_ce = sctp_v4_is_ce, .seq_dump_addr = sctp_v4_seq_dump_addr, + .ecn_capable = sctp_v4_ecn_capable, .net_header_len = sizeof(struct iphdr), .sockaddr_len = sizeof(struct sockaddr_in), #ifdef CONFIG_COMPAT @@ -949,24 +999,67 @@ int sctp_register_pf(struct sctp_pf *pf, sa_family_t family) return 1; } -static int __init init_sctp_mibs(void) +static inline int init_sctp_mibs(void) { - sctp_statistics[0] = alloc_percpu(struct sctp_mib); - if (!sctp_statistics[0]) - return -ENOMEM; - sctp_statistics[1] = alloc_percpu(struct sctp_mib); - if (!sctp_statistics[1]) { - free_percpu(sctp_statistics[0]); - return -ENOMEM; - } + return snmp_mib_init((void __percpu **)sctp_statistics, + sizeof(struct sctp_mib)); +} + +static inline void cleanup_sctp_mibs(void) +{ + snmp_mib_free((void __percpu **)sctp_statistics); +} + +static void sctp_v4_pf_init(void) +{ + /* Initialize the SCTP specific PF functions. */ + sctp_register_pf(&sctp_pf_inet, PF_INET); + sctp_register_af(&sctp_af_inet); +} + +static void sctp_v4_pf_exit(void) +{ + list_del(&sctp_af_inet.list); +} + +static int sctp_v4_protosw_init(void) +{ + int rc; + + rc = proto_register(&sctp_prot, 1); + if (rc) + return rc; + + /* Register SCTP(UDP and TCP style) with socket layer. */ + inet_register_protosw(&sctp_seqpacket_protosw); + inet_register_protosw(&sctp_stream_protosw); + return 0; +} +static void sctp_v4_protosw_exit(void) +{ + inet_unregister_protosw(&sctp_stream_protosw); + inet_unregister_protosw(&sctp_seqpacket_protosw); + proto_unregister(&sctp_prot); } -static void cleanup_sctp_mibs(void) +static int sctp_v4_add_protocol(void) { - free_percpu(sctp_statistics[0]); - free_percpu(sctp_statistics[1]); + /* Register notifier for inet address additions/deletions. */ + register_inetaddr_notifier(&sctp_inetaddr_notifier); + + /* Register SCTP with inet layer. */ + if (inet_add_protocol(&sctp_protocol, IPPROTO_SCTP) < 0) + return -EAGAIN; + + return 0; +} + +static void sctp_v4_del_protocol(void) +{ + inet_del_protocol(&sctp_protocol, IPPROTO_SCTP); + unregister_inetaddr_notifier(&sctp_inetaddr_notifier); } /* Initialize the universe into something sensible. */ @@ -975,39 +1068,28 @@ SCTP_STATIC __init int sctp_init(void) int i; int status = -EINVAL; unsigned long goal; + unsigned long limit; + unsigned long nr_pages; + int max_share; int order; /* SCTP_DEBUG sanity check. */ if (!sctp_sanity_check()) goto out; - status = proto_register(&sctp_prot, 1); - if (status) - goto out; - - /* Add SCTP to inet_protos hash table. */ - status = -EAGAIN; - if (inet_add_protocol(&sctp_protocol, IPPROTO_SCTP) < 0) - goto err_add_protocol; - - /* Add SCTP(TCP and UDP style) to inetsw linked list. */ - inet_register_protosw(&sctp_seqpacket_protosw); - inet_register_protosw(&sctp_stream_protosw); - - /* Allocate a cache pools. */ + /* Allocate bind_bucket and chunk caches. */ status = -ENOBUFS; sctp_bucket_cachep = kmem_cache_create("sctp_bind_bucket", sizeof(struct sctp_bind_bucket), 0, SLAB_HWCACHE_ALIGN, - NULL, NULL); - + NULL); if (!sctp_bucket_cachep) - goto err_bucket_cachep; + goto out; sctp_chunk_cachep = kmem_cache_create("sctp_chunk", sizeof(struct sctp_chunk), 0, SLAB_HWCACHE_ALIGN, - NULL, NULL); + NULL); if (!sctp_chunk_cachep) goto err_chunk_cachep; @@ -1024,8 +1106,6 @@ SCTP_STATIC __init int sctp_init(void) /* Initialize object count debugging. */ sctp_dbg_objcnt_init(); - /* Initialize the SCTP specific PF functions. */ - sctp_register_pf(&sctp_pf_inet, PF_INET); /* * 14. Suggested SCTP Protocol Parameter Values */ @@ -1048,7 +1128,7 @@ SCTP_STATIC __init int sctp_init(void) sctp_cookie_preserve_enable = 1; /* Max.Burst - 4 */ - sctp_max_burst = SCTP_MAX_BURST; + sctp_max_burst = SCTP_DEFAULT_MAX_BURST; /* Association.Max.Retrans - 10 attempts * Path.Max.Retrans - 5 attempts (per destination address) @@ -1079,13 +1159,39 @@ SCTP_STATIC __init int sctp_init(void) /* Initialize handle used for association ids. */ idr_init(&sctp_assocs_id); + /* Set the pressure threshold to be a fraction of global memory that + * is up to 1/2 at 256 MB, decreasing toward zero with the amount of + * memory, with a floor of 128 pages. + * Note this initalizes the data in sctpv6_prot too + * Unabashedly stolen from tcp_init + */ + nr_pages = totalram_pages - totalhigh_pages; + limit = min(nr_pages, 1UL<<(28-PAGE_SHIFT)) >> (20-PAGE_SHIFT); + limit = (limit * (nr_pages >> (20-PAGE_SHIFT))) >> (PAGE_SHIFT-11); + limit = max(limit, 128UL); + sysctl_sctp_mem[0] = limit / 4 * 3; + sysctl_sctp_mem[1] = limit; + sysctl_sctp_mem[2] = sysctl_sctp_mem[0] * 2; + + /* Set per-socket limits to no more than 1/128 the pressure threshold*/ + limit = (sysctl_sctp_mem[1]) << (PAGE_SHIFT - 7); + max_share = min(4UL*1024*1024, limit); + + sysctl_sctp_rmem[0] = SK_MEM_QUANTUM; /* give each asoc 1 page min */ + sysctl_sctp_rmem[1] = (1500 *(sizeof(struct sk_buff) + 1)); + sysctl_sctp_rmem[2] = max(sysctl_sctp_rmem[1], max_share); + + sysctl_sctp_wmem[0] = SK_MEM_QUANTUM; + sysctl_sctp_wmem[1] = 16*1024; + sysctl_sctp_wmem[2] = max(64*1024, max_share); + /* Size and allocate the association hash table. * The methodology is similar to that of the tcp hash tables. */ - if (num_physpages >= (128 * 1024)) - goal = num_physpages >> (22 - PAGE_SHIFT); + if (totalram_pages >= (128 * 1024)) + goal = totalram_pages >> (22 - PAGE_SHIFT); else - goal = num_physpages >> (24 - PAGE_SHIFT); + goal = totalram_pages >> (24 - PAGE_SHIFT); for (order = 0; (1UL << order) < goal; order++) ; @@ -1105,7 +1211,7 @@ SCTP_STATIC __init int sctp_init(void) } for (i = 0; i < sctp_assoc_hashsize; i++) { rwlock_init(&sctp_assoc_hashtable[i].lock); - sctp_assoc_hashtable[i].chain = NULL; + INIT_HLIST_HEAD(&sctp_assoc_hashtable[i].chain); } /* Allocate and initialize the endpoint hash table. */ @@ -1119,7 +1225,7 @@ SCTP_STATIC __init int sctp_init(void) } for (i = 0; i < sctp_ep_hashsize; i++) { rwlock_init(&sctp_ep_hashtable[i].lock); - sctp_ep_hashtable[i].chain = NULL; + INIT_HLIST_HEAD(&sctp_ep_hashtable[i].chain); } /* Allocate and initialize the SCTP port hash table. */ @@ -1138,30 +1244,48 @@ SCTP_STATIC __init int sctp_init(void) } for (i = 0; i < sctp_port_hashsize; i++) { spin_lock_init(&sctp_port_hashtable[i].lock); - sctp_port_hashtable[i].chain = NULL; + INIT_HLIST_HEAD(&sctp_port_hashtable[i].chain); } - spin_lock_init(&sctp_port_alloc_lock); - sctp_port_rover = sysctl_local_port_range[0] - 1; - printk(KERN_INFO "SCTP: Hash tables configured " "(established %d bind %d)\n", sctp_assoc_hashsize, sctp_port_hashsize); /* Disable ADDIP by default. */ sctp_addip_enable = 0; + sctp_addip_noauth = 0; /* Enable PR-SCTP by default. */ sctp_prsctp_enable = 1; + /* Disable AUTH by default. */ + sctp_auth_enable = 0; + + /* Set SCOPE policy to enabled */ + sctp_scope_policy = SCTP_SCOPE_POLICY_ENABLE; + + /* Set the default rwnd update threshold */ + sctp_rwnd_upd_shift = SCTP_DEFAULT_RWND_SHIFT; + sctp_sysctl_register(); INIT_LIST_HEAD(&sctp_address_families); - sctp_register_af(&sctp_ipv4_specific); + sctp_v4_pf_init(); + sctp_v6_pf_init(); + + /* Initialize the local address list. */ + INIT_LIST_HEAD(&sctp_local_addr_list); + spin_lock_init(&sctp_local_addr_lock); + sctp_get_local_addr_list(); + + status = sctp_v4_protosw_init(); - status = sctp_v6_init(); if (status) - goto err_v6_init; + goto err_protosw_init; + + status = sctp_v6_protosw_init(); + if (status) + goto err_v6_protosw_init; /* Initialize the control inode/socket for handling OOTB packets. */ if ((status = sctp_ctl_sock_init())) { @@ -1170,24 +1294,31 @@ SCTP_STATIC __init int sctp_init(void) goto err_ctl_sock_init; } - /* Initialize the local address list. */ - INIT_LIST_HEAD(&sctp_local_addr_list); - spin_lock_init(&sctp_local_addr_lock); - - /* Register notifier for inet address additions/deletions. */ - register_inetaddr_notifier(&sctp_inetaddr_notifier); + status = sctp_v4_add_protocol(); + if (status) + goto err_add_protocol; - sctp_get_local_addr_list(); + /* Register SCTP with inet6 layer. */ + status = sctp_v6_add_protocol(); + if (status) + goto err_v6_add_protocol; - __unsafe(THIS_MODULE); status = 0; out: return status; +err_v6_add_protocol: + sctp_v4_del_protocol(); +err_add_protocol: + inet_ctl_sock_destroy(sctp_ctl_sock); err_ctl_sock_init: - sctp_v6_exit(); -err_v6_init: + sctp_v6_protosw_exit(); +err_v6_protosw_init: + sctp_v4_protosw_exit(); +err_protosw_init: + sctp_free_local_addr_list(); + sctp_v4_pf_exit(); + sctp_v6_pf_exit(); sctp_sysctl_unregister(); - list_del(&sctp_ipv4_specific.list); free_pages((unsigned long)sctp_port_hashtable, get_order(sctp_port_hashsize * sizeof(struct sctp_bind_hashbucket))); @@ -1199,19 +1330,13 @@ err_ehash_alloc: sizeof(struct sctp_hashbucket))); err_ahash_alloc: sctp_dbg_objcnt_exit(); -err_init_proc: sctp_proc_exit(); +err_init_proc: cleanup_sctp_mibs(); err_init_mibs: kmem_cache_destroy(sctp_chunk_cachep); err_chunk_cachep: kmem_cache_destroy(sctp_bucket_cachep); -err_bucket_cachep: - inet_del_protocol(&sctp_protocol, IPPROTO_SCTP); - inet_unregister_protosw(&sctp_seqpacket_protosw); - inet_unregister_protosw(&sctp_stream_protosw); -err_add_protocol: - proto_unregister(&sctp_prot); goto out; } @@ -1222,18 +1347,25 @@ SCTP_STATIC __exit void sctp_exit(void) * up all the remaining associations and all that memory. */ - /* Unregister notifier for inet address additions/deletions. */ - unregister_inetaddr_notifier(&sctp_inetaddr_notifier); + /* Unregister with inet6/inet layers. */ + sctp_v6_del_protocol(); + sctp_v4_del_protocol(); + + /* Free the control endpoint. */ + inet_ctl_sock_destroy(sctp_ctl_sock); + + /* Free protosw registrations */ + sctp_v6_protosw_exit(); + sctp_v4_protosw_exit(); /* Free the local address list. */ sctp_free_local_addr_list(); - /* Free the control endpoint. */ - sock_release(sctp_ctl_socket); + /* Unregister with socket layer. */ + sctp_v6_pf_exit(); + sctp_v4_pf_exit(); - sctp_v6_exit(); sctp_sysctl_unregister(); - list_del(&sctp_ipv4_specific.list); free_pages((unsigned long)sctp_assoc_hashtable, get_order(sctp_assoc_hashsize * @@ -1243,17 +1375,14 @@ SCTP_STATIC __exit void sctp_exit(void) get_order(sctp_port_hashsize * sizeof(struct sctp_bind_hashbucket))); - kmem_cache_destroy(sctp_chunk_cachep); - kmem_cache_destroy(sctp_bucket_cachep); - sctp_dbg_objcnt_exit(); sctp_proc_exit(); cleanup_sctp_mibs(); - inet_del_protocol(&sctp_protocol, IPPROTO_SCTP); - inet_unregister_protosw(&sctp_seqpacket_protosw); - inet_unregister_protosw(&sctp_stream_protosw); - proto_unregister(&sctp_prot); + rcu_barrier(); /* Wait for completion of call_rcu()'s */ + + kmem_cache_destroy(sctp_chunk_cachep); + kmem_cache_destroy(sctp_bucket_cachep); } module_init(sctp_init); @@ -1263,6 +1392,9 @@ module_exit(sctp_exit); * __stringify doesn't likes enums, so use IPPROTO_SCTP value (132) directly. */ MODULE_ALIAS("net-pf-" __stringify(PF_INET) "-proto-132"); +MODULE_ALIAS("net-pf-" __stringify(PF_INET6) "-proto-132"); MODULE_AUTHOR("Linux Kernel SCTP developers "); MODULE_DESCRIPTION("Support for the SCTP protocol (RFC2960)"); +module_param_named(no_checksums, sctp_checksum_disable, bool, 0644); +MODULE_PARM_DESC(no_checksums, "Disable checksums computing and verification"); MODULE_LICENSE("GPL");