protocol.c

在linux环境下的流控制传输协议（sctp）的源代码

/* SCTP kernel implementation
 * (C) Copyright IBM Corp. 2001, 2004
 * Copyright (c) 1999-2000 Cisco, Inc.
 * Copyright (c) 1999-2001 Motorola, Inc.
 * Copyright (c) 2001 Intel Corp.
 * Copyright (c) 2001 Nokia, Inc.
 * Copyright (c) 2001 La Monte H.P. Yarroll
 *
 * This file is part of the SCTP kernel implementation
 *
 * Initialization/cleanup for SCTP protocol support.
 *
 * 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.
 *
 * 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.
 * See the GNU General Public License for more details.
 *
 * You should have received a copy of the GNU General Public License
 * along with GNU CC; see the file COPYING.  If not, write to
 * the Free Software Foundation, 59 Temple Place - Suite 330,
 * Boston, MA 02111-1307, USA.
 *
 * Please send any bug reports or fixes you make to the
 * email address(es):
 *    lksctp developers <[e-mail]>
 *
 * Or submit a bug report through the following website:
 *    http://www.sf.net/projects/lksctp
 *
 * Written or modified by:
 *    La Monte H.P. Yarroll <[e-mail]>
 *    Karl Knutson <[e-mail]>
 *    Jon Grimm <[e-mail]>
 *    Sridhar Samudrala <[e-mail]>
 *    Daisy Chang <[e-mail]>
 *    Ardelle Fan <[e-mail]>
 *
 * Any bugs reported given to us we will try to fix... any fixes shared will
 * be incorporated into the next SCTP release.
 */

#include <linux/module.h>
#include <linux/init.h>
#include <linux/netdevice.h>
#include <linux/inetdevice.h>
#include <linux/seq_file.h>
#include <linux/bootmem.h>
#include <net/net_namespace.h>
#include <net/protocol.h>
#include <net/ip.h>
#include <net/ipv6.h>
#include <net/route.h>
#include <net/sctp/sctp.h>
#include <net/addrconf.h>
#include <net/inet_common.h>
#include <net/inet_ecn.h>

/* 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;

struct idr sctp_assocs_id;
DEFINE_SPINLOCK(sctp_assocs_id_lock);

/* This is the global socket data structure used for responding to
 * 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 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;

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;
}

/* Set up the proc fs entry for the SCTP protocol. */
static __init int sctp_proc_init(void)
{
	if (!proc_net_sctp) {
		struct proc_dir_entry *ent;
		ent = proc_mkdir("sctp", init_net.proc_net);
		if (ent) {
			ent->owner = THIS_MODULE;
			proc_net_sctp = ent;
		} else
			goto out_nomem;
	}

	if (sctp_snmp_proc_init())
		goto out_nomem;
	if (sctp_eps_proc_init())
		goto out_nomem;
	if (sctp_assocs_proc_init())
		goto out_nomem;

	return 0;

out_nomem:
	return -ENOMEM;
}

/* 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)
{
	sctp_snmp_proc_exit();
	sctp_eps_proc_exit();
	sctp_assocs_proc_exit();

	if (proc_net_sctp) {
		proc_net_sctp = NULL;
		remove_proc_entry("sctp", init_net.proc_net);
	}
}

/* Private helper to extract ipv4 address and stash them in
 * the protocol structure.
 */
static void sctp_v4_copy_addrlist(struct list_head *addrlist,
				  struct net_device *dev)
{
	struct in_device *in_dev;
	struct in_ifaddr *ifa;
	struct sctp_sockaddr_entry *addr;

	rcu_read_lock();
	if ((in_dev = __in_dev_get_rcu(dev)) == NULL) {
		rcu_read_unlock();
		return;
	}

	for (ifa = in_dev->ifa_list; ifa; ifa = ifa->ifa_next) {
		/* Add the address to the local list.  */
		addr = t_new(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;
			INIT_LIST_HEAD(&addr->list);
			INIT_RCU_HEAD(&addr->rcu);
			list_add_tail(&addr->list, addrlist);
		}
	}

	rcu_read_unlock();
}

/* Extract our IP addresses from the system and stash them in the
 * protocol structure.
 */
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_each_netdev(&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);
}

/* Free the existing local addresses.  */
static void sctp_free_local_addr_list(void)
{
	struct sctp_sockaddr_entry *addr;
	struct list_head *pos, *temp;

	list_for_each_safe(pos, temp, &sctp_local_addr_list) {
		addr = list_entry(pos, struct sctp_sockaddr_entry, list);
		list_del(pos);
		kfree(addr);
	}
}

void sctp_local_addr_free(struct rcu_head *head)
{
	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'.  */
int sctp_copy_local_addr_list(struct sctp_bind_addr *bp, sctp_scope_t scope,
			      gfp_t gfp, int copy_flags)
{
	struct sctp_sockaddr_entry *addr;
	int error = 0;

	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.sa.sa_family) &&
			      (copy_flags & SCTP_ADDR4_PEERSUPP))) ||
			    (((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,
						    SCTP_ADDR_SRC, GFP_ATOMIC);
				if (error)
					goto end_copy;
			}
		}
	}

end_copy:
	rcu_read_unlock();
	return error;
}

/* Initialize a sctp_addr from in incoming skb.  */
static void sctp_v4_from_skb(union sctp_addr *addr, struct sk_buff *skb,
			     int is_saddr)
{
	void *from;
	__be16 *port;
	struct sctphdr *sh;

	port = &addr->v4.sin_port;
	addr->v4.sin_family = AF_INET;

	sh = sctp_hdr(skb);
	if (is_saddr) {
		*port  = sh->source;
		from = &ip_hdr(skb)->saddr;
	} else {
		*port = sh->dest;
		from = &ip_hdr(skb)->daddr;
	}
	memcpy(&addr->v4.sin_addr.s_addr, from, sizeof(struct in_addr));
}

/* Initialize an sctp_addr from a socket. */
static void sctp_v4_from_sk(union sctp_addr *addr, struct sock *sk)
{
	addr->v4.sin_family = AF_INET;
	addr->v4.sin_port = 0;
	addr->v4.sin_addr.s_addr = inet_sk(sk)->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;
}

/* 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;
}

/* Initialize a sctp_addr from an address parameter. */
static void sctp_v4_from_addr_param(union sctp_addr *addr,
				    union sctp_addr_param *param,
				    __be16 port, int iif)
{
	addr->v4.sin_family = AF_INET;
	addr->v4.sin_port = port;
	addr->v4.sin_addr.s_addr = param->v4.addr.s_addr;
}

/* Initialize an address parameter from a sctp_addr and return the length
 * of the address parameter.
 */
static int sctp_v4_to_addr_param(const union sctp_addr *addr,
				 union sctp_addr_param *param)
{
	int length = sizeof(sctp_ipv4addr_param_t);

	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;

	return length;
}

/* Initialize a sctp_addr from a dst_entry. */
static void sctp_v4_dst_saddr(union sctp_addr *saddr, struct dst_entry *dst,
			      __be16 port)
{
	struct rtable *rt = (struct rtable *)dst;
	saddr->v4.sin_family = AF_INET;
	saddr->v4.sin_port = port;
	saddr->v4.sin_addr.s_addr = rt->rt_src;
}

/* Compare two addresses exactly. */
static int sctp_v4_cmp_addr(const union sctp_addr *addr1,
			    const union sctp_addr *addr2)
{
	if (addr1->sa.sa_family != addr2->sa.sa_family)
		return 0;
	if (addr1->v4.sin_port != addr2->v4.sin_port)
		return 0;
	if (addr1->v4.sin_addr.s_addr != addr2->v4.sin_addr.s_addr)
		return 0;

	return 1;
}

/* Initialize addr struct to INADDR_ANY. */
static void sctp_v4_inaddr_any(union sctp_addr *addr, __be16 port)
{
	addr->v4.sin_family = AF_INET;
	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 htonl(INADDR_ANY) == addr->v4.sin_addr.s_addr;
}

/* This function checks if the address is a valid address to be used for
 * SCTP binding.
 *
 * Output:
 * Return 0 - If the address is a non-unicast or an illegal address.
 * Return 1 - If the address is a unicast.
 */
static int sctp_v4_addr_valid(union sctp_addr *addr,
			      struct sctp_sock *sp,
			      const struct sk_buff *skb)
{
	/* Is this a non-unicast address or a unusable SCTP address? */
	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;

	return 1;
}

/* Should this be available for binding?   */
static int sctp_v4_available(union sctp_addr *addr, struct sctp_sock *sp)
{
	int ret = inet_addr_type(&init_net, addr->v4.sin_addr.s_addr);


	if (addr->v4.sin_addr.s_addr != htonl(INADDR_ANY) &&
	   ret != RTN_LOCAL &&
	   !sp->inet.freebind &&
	   !sysctl_ip_nonlocal_bind)
		return 0;

	return 1;
}

/* Checking the loopback, private and other address scopes as defined in
 * RFC 1918.   The IPv4 scoping is based on the draft for SCTP IPv4
 * scoping <draft-stewart-tsvwg-sctp-ipv4-00.txt>.
 *
 * Level 0 - unusable SCTP addresses
 * Level 1 - loopback address
 * Level 2 - link-local addresses
 * Level 3 - private addresses.
 * Level 4 - global addresses
 * For INIT and INIT-ACK address list, let L be the level of
 * of requested destination address, sender and receiver
 * SHOULD include all of its addresses with level greater
 * than or equal to L.
 */
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)) {
		retval =  SCTP_SCOPE_UNUSABLE;
	} else if (ipv4_is_loopback(addr->v4.sin_addr.s_addr)) {
		retval = SCTP_SCOPE_LOOPBACK;
	} else if (ipv4_is_linklocal_169(addr->v4.sin_addr.s_addr)) {
		retval = SCTP_SCOPE_LINK;
	} 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;
	}

	return retval;
}

/* Returns a valid dst cache entry for the given source and destination ip
 * addresses. If an association is passed, trys to get a dst entry with a
 * source address that matches an address in the bind address list.
 */
static struct dst_entry *sctp_v4_get_dst(struct sctp_association *asoc,
					 union sctp_addr *daddr,
					 union sctp_addr *saddr)
{
	struct rtable *rt;
	struct flowi fl;
	struct sctp_bind_addr *bp;
	struct sctp_sockaddr_entry *laddr;
	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.proto = IPPROTO_SCTP;
	if (asoc) {
		fl.fl4_tos = RT_CONN_FLAGS(asoc->base.sk);
		fl.oif = asoc->base.sk->sk_bound_dev_if;
	}
	if (saddr)
		fl.fl4_src = saddr->v4.sin_addr.s_addr;

	SCTP_DEBUG_PRINTK("%s: DST:%u.%u.%u.%u, SRC:%u.%u.%u.%u - ",
			  __FUNCTION__, NIPQUAD(fl.fl4_dst),
			  NIPQUAD(fl.fl4_src));

	if (!ip_route_output_key(&init_net, &rt, &fl)) {
		dst = &rt->u.dst;
	}