input.c

在linux环境下的流控制传输协议（sctp）的源代码

/* SCTP kernel implementation
 * Copyright (c) 1999-2000 Cisco, Inc.
 * Copyright (c) 1999-2001 Motorola, Inc.
 * Copyright (c) 2001-2003 International Business Machines, Corp.
 * 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
 *
 * These functions handle all input from the IP layer into SCTP.
 *
 * 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]>
 *    Xingang Guo <[e-mail]>
 *    Jon Grimm <[e-mail]>
 *    Hui Huang <[e-mail]>
 *    Daisy Chang <[e-mail]>
 *    Sridhar Samudrala <[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/types.h>
#include <linux/list.h> /* For struct list_head */
#include <linux/socket.h>
#include <linux/ip.h>
#include <linux/time.h> /* For struct timeval */
#include <net/ip.h>
#include <net/icmp.h>
#include <net/snmp.h>
#include <net/sock.h>
#include <net/xfrm.h>
#include <net/sctp/sctp.h>
#include <net/sctp/sm.h>
#include <net/sctp/checksum.h>

/* Forward declarations for internal helpers. */
static int sctp_rcv_ootb(struct sk_buff *);
static struct sctp_association *__sctp_rcv_lookup(struct sk_buff *skb,
				      const union sctp_addr *laddr,
				      const union sctp_addr *paddr,
				      struct sctp_transport **transportp);
static struct sctp_endpoint *__sctp_rcv_lookup_endpoint(const union sctp_addr *laddr);
static struct sctp_association *__sctp_lookup_association(
					const union sctp_addr *local,
					const union sctp_addr *peer,
					struct sctp_transport **pt);

static void sctp_add_backlog(struct sock *sk, struct sk_buff *skb);


/* Calculate the SCTP checksum of an SCTP packet.  */
static inline int sctp_rcv_checksum(struct sk_buff *skb)
{
	struct sk_buff *list = skb_shinfo(skb)->frag_list;
	struct sctphdr *sh = sctp_hdr(skb);
	__u32 cmp = ntohl(sh->checksum);
	__u32 val = sctp_start_cksum((__u8 *)sh, skb_headlen(skb));

	for (; list; list = list->next)
		val = sctp_update_cksum((__u8 *)list->data, skb_headlen(list),
					val);

	val = sctp_end_cksum(val);

	if (val != cmp) {
		/* CRC failure, dump it. */
		SCTP_INC_STATS_BH(SCTP_MIB_CHECKSUMERRORS);
		return -1;
	}
	return 0;
}

struct sctp_input_cb {
	union {
		struct inet_skb_parm	h4;
#if defined(CONFIG_IPV6) || defined (CONFIG_IPV6_MODULE)
		struct inet6_skb_parm	h6;
#endif
	} header;
	struct sctp_chunk *chunk;
};
#define SCTP_INPUT_CB(__skb)	((struct sctp_input_cb *)&((__skb)->cb[0]))

/*
 * This is the routine which IP calls when receiving an SCTP packet.
 */
int sctp_rcv(struct sk_buff *skb)
{
	struct sock *sk;
	struct sctp_association *asoc;
	struct sctp_endpoint *ep = NULL;
	struct sctp_ep_common *rcvr;
	struct sctp_transport *transport = NULL;
	struct sctp_chunk *chunk;
	struct sctphdr *sh;
	union sctp_addr src;
	union sctp_addr dest;
	int family;
	struct sctp_af *af;

	if (skb->pkt_type!=PACKET_HOST)
		goto discard_it;

	SCTP_INC_STATS_BH(SCTP_MIB_INSCTPPACKS);

	if (skb_linearize(skb))
		goto discard_it;

	sh = sctp_hdr(skb);

	/* Pull up the IP and SCTP headers. */
	__skb_pull(skb, skb_transport_offset(skb));
	if (skb->len < sizeof(struct sctphdr))
		goto discard_it;
	if (!skb_csum_unnecessary(skb) && sctp_rcv_checksum(skb) < 0)
		goto discard_it;

	skb_pull(skb, sizeof(struct sctphdr));

	/* Make sure we at least have chunk headers worth of data left. */
	if (skb->len < sizeof(struct sctp_chunkhdr))
		goto discard_it;

	family = ipver2af(ip_hdr(skb)->version);
	af = sctp_get_af_specific(family);
	if (unlikely(!af))
		goto discard_it;

	/* Initialize local addresses for lookups. */
	af->from_skb(&src, skb, 1);
	af->from_skb(&dest, skb, 0);

	/* If the packet is to or from a non-unicast address,
	 * silently discard the packet.
	 *
	 * This is not clearly defined in the RFC except in section
	 * 8.4 - OOTB handling.  However, based on the book "Stream Control
	 * Transmission Protocol" 2.1, "It is important to note that the
	 * IP address of an SCTP transport address must be a routable
	 * unicast address.  In other words, IP multicast addresses and
	 * IP broadcast addresses cannot be used in an SCTP transport
	 * address."
	 */
	if (!af->addr_valid(&src, NULL, skb) ||
	    !af->addr_valid(&dest, NULL, skb))
		goto discard_it;

	asoc = __sctp_rcv_lookup(skb, &src, &dest, &transport);

	if (!asoc)
		ep = __sctp_rcv_lookup_endpoint(&dest);

	/* Retrieve the common input handling substructure. */
	rcvr = asoc ? &asoc->base : &ep->base;
	sk = rcvr->sk;

	/*
	 * If a frame arrives on an interface and the receiving socket is
	 * bound to another interface, via SO_BINDTODEVICE, treat it as OOTB
	 */
	if (sk->sk_bound_dev_if && (sk->sk_bound_dev_if != af->skb_iif(skb)))
	{
		if (asoc) {
			sctp_association_put(asoc);
			asoc = NULL;
		} else {
			sctp_endpoint_put(ep);
			ep = NULL;
		}
		sk = sctp_get_ctl_sock();
		ep = sctp_sk(sk)->ep;
		sctp_endpoint_hold(ep);
		rcvr = &ep->base;
	}

	/*
	 * RFC 2960, 8.4 - Handle "Out of the blue" Packets.
	 * An SCTP packet is called an "out of the blue" (OOTB)
	 * packet if it is correctly formed, i.e., passed the
	 * receiver's checksum check, but the receiver is not
	 * able to identify the association to which this
	 * packet belongs.
	 */
	if (!asoc) {
		if (sctp_rcv_ootb(skb)) {
			SCTP_INC_STATS_BH(SCTP_MIB_OUTOFBLUES);
			goto discard_release;
		}
	}

	if (!xfrm_policy_check(sk, XFRM_POLICY_IN, skb, family))
		goto discard_release;
	nf_reset(skb);

	if (sk_filter(sk, skb))
		goto discard_release;

	/* Create an SCTP packet structure. */
	chunk = sctp_chunkify(skb, asoc, sk);
	if (!chunk)
		goto discard_release;
	SCTP_INPUT_CB(skb)->chunk = chunk;

	/* Remember what endpoint is to handle this packet. */
	chunk->rcvr = rcvr;

	/* Remember the SCTP header. */
	chunk->sctp_hdr = sh;

	/* Set the source and destination addresses of the incoming chunk.  */
	sctp_init_addrs(chunk, &src, &dest);

	/* Remember where we came from.  */
	chunk->transport = transport;

	/* Acquire access to the sock lock. Note: We are safe from other
	 * bottom halves on this lock, but a user may be in the lock too,
	 * so check if it is busy.
	 */
	sctp_bh_lock_sock(sk);

	if (sock_owned_by_user(sk)) {
		SCTP_INC_STATS_BH(SCTP_MIB_IN_PKT_BACKLOG);
		sctp_add_backlog(sk, skb);
	} else {
		SCTP_INC_STATS_BH(SCTP_MIB_IN_PKT_SOFTIRQ);
		sctp_inq_push(&chunk->rcvr->inqueue, chunk);
	}

	sctp_bh_unlock_sock(sk);

	/* Release the asoc/ep ref we took in the lookup calls. */
	if (asoc)
		sctp_association_put(asoc);
	else
		sctp_endpoint_put(ep);

	return 0;

discard_it:
	SCTP_INC_STATS_BH(SCTP_MIB_IN_PKT_DISCARDS);
	kfree_skb(skb);
	return 0;

discard_release:
	/* Release the asoc/ep ref we took in the lookup calls. */
	if (asoc)
		sctp_association_put(asoc);
	else
		sctp_endpoint_put(ep);

	goto discard_it;
}

/* Process the backlog queue of the socket.  Every skb on
 * the backlog holds a ref on an association or endpoint.
 * We hold this ref throughout the state machine to make
 * sure that the structure we need is still around.
 */
int sctp_backlog_rcv(struct sock *sk, struct sk_buff *skb)
{
	struct sctp_chunk *chunk = SCTP_INPUT_CB(skb)->chunk;
	struct sctp_inq *inqueue = &chunk->rcvr->inqueue;
	struct sctp_ep_common *rcvr = NULL;
	int backloged = 0;

	rcvr = chunk->rcvr;

	/* If the rcvr is dead then the association or endpoint
	 * has been deleted and we can safely drop the chunk
	 * and refs that we are holding.
	 */
	if (rcvr->dead) {
		sctp_chunk_free(chunk);
		goto done;
	}

	if (unlikely(rcvr->sk != sk)) {
		/* In this case, the association moved from one socket to
		 * another.  We are currently sitting on the backlog of the
		 * old socket, so we need to move.
		 * However, since we are here in the process context we
		 * need to take make sure that the user doesn't own
		 * the new socket when we process the packet.
		 * If the new socket is user-owned, queue the chunk to the
		 * backlog of the new socket without dropping any refs.
		 * Otherwise, we can safely push the chunk on the inqueue.
		 */

		sk = rcvr->sk;
		sctp_bh_lock_sock(sk);

		if (sock_owned_by_user(sk)) {
			sk_add_backlog(sk, skb);
			backloged = 1;
		} else
			sctp_inq_push(inqueue, chunk);

		sctp_bh_unlock_sock(sk);

		/* If the chunk was backloged again, don't drop refs */
		if (backloged)
			return 0;
	} else {
		sctp_inq_push(inqueue, chunk);
	}

done:
	/* Release the refs we took in sctp_add_backlog */
	if (SCTP_EP_TYPE_ASSOCIATION == rcvr->type)
		sctp_association_put(sctp_assoc(rcvr));
	else if (SCTP_EP_TYPE_SOCKET == rcvr->type)
		sctp_endpoint_put(sctp_ep(rcvr));
	else
		BUG();

	return 0;
}

static void sctp_add_backlog(struct sock *sk, struct sk_buff *skb)
{
	struct sctp_chunk *chunk = SCTP_INPUT_CB(skb)->chunk;
	struct sctp_ep_common *rcvr = chunk->rcvr;

	/* Hold the assoc/ep while hanging on the backlog queue.
	 * This way, we know structures we need will not disappear from us
	 */
	if (SCTP_EP_TYPE_ASSOCIATION == rcvr->type)
		sctp_association_hold(sctp_assoc(rcvr));
	else if (SCTP_EP_TYPE_SOCKET == rcvr->type)
		sctp_endpoint_hold(sctp_ep(rcvr));
	else
		BUG();

	sk_add_backlog(sk, skb);
}

/* Handle icmp frag needed error. */
void sctp_icmp_frag_needed(struct sock *sk, struct sctp_association *asoc,
			   struct sctp_transport *t, __u32 pmtu)
{
	if (!t || (t->pathmtu == pmtu))
		return;

	if (sock_owned_by_user(sk)) {
		asoc->pmtu_pending = 1;
		t->pmtu_pending = 1;
		return;
	}

	if (t->param_flags & SPP_PMTUD_ENABLE) {
		/* Update transports view of the MTU */
		sctp_transport_update_pmtu(t, pmtu);

		/* Update association pmtu. */
		sctp_assoc_sync_pmtu(asoc);
	}

	/* Retransmit with the new pmtu setting.
	 * Normally, if PMTU discovery is disabled, an ICMP Fragmentation
	 * Needed will never be sent, but if a message was sent before
	 * PMTU discovery was disabled that was larger than the PMTU, it
	 * would not be fragmented, so it must be re-transmitted fragmented.
	 */
	sctp_retransmit(&asoc->outqueue, t, SCTP_RTXR_PMTUD);
}

/*
 * SCTP Implementer's Guide, 2.37 ICMP handling procedures
 *
 * ICMP8) If the ICMP code is a "Unrecognized next header type encountered"
 *        or a "Protocol Unreachable" treat this message as an abort
 *        with the T bit set.
 *
 * This function sends an event to the state machine, which will abort the
 * association.
 *
 */
void sctp_icmp_proto_unreachable(struct sock *sk,
			   struct sctp_association *asoc,
			   struct sctp_transport *t)
{
	SCTP_DEBUG_PRINTK("%s\n",  __FUNCTION__);

	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. */
struct sock *sctp_err_lookup(int family, struct sk_buff *skb,
			     struct sctphdr *sctphdr,
			     struct sctp_association **app,
			     struct sctp_transport **tpp)
{
	union sctp_addr saddr;
	union sctp_addr daddr;
	struct sctp_af *af;
	struct sock *sk = NULL;
	struct sctp_association *asoc;
	struct sctp_transport *transport = NULL;

	*app = NULL; *tpp = NULL;

	af = sctp_get_af_specific(family);
	if (unlikely(!af)) {
		return NULL;
	}

	/* Initialize local addresses for lookups. */
	af->from_skb(&saddr, skb, 1);
	af->from_skb(&daddr, skb, 0);

	/* Look for an association that matches the incoming ICMP error
	 * packet.
	 */
	asoc = __sctp_lookup_association(&saddr, &daddr, &transport);
	if (!asoc)
		return NULL;

	sk = asoc->base.sk;

	if (ntohl(sctphdr->vtag) != asoc->c.peer_vtag) {
		ICMP_INC_STATS_BH(ICMP_MIB_INERRORS);
		goto out;
	}

	sctp_bh_lock_sock(sk);

	/* If too many ICMPs get dropped on busy
	 * servers this needs to be solved differently.
	 */
	if (sock_owned_by_user(sk))
		NET_INC_STATS_BH(LINUX_MIB_LOCKDROPPEDICMPS);

	*app = asoc;
	*tpp = transport;
	return sk;

out:
	if (asoc)
		sctp_association_put(asoc);
	return NULL;
}

/* Common cleanup code for icmp/icmpv6 error handler. */
void sctp_err_finish(struct sock *sk, struct sctp_association *asoc)
{
	sctp_bh_unlock_sock(sk);
	if (asoc)
		sctp_association_put(asoc);
}

/*
 * This routine is called by the ICMP module when it gets some
 * sort of error condition.  If err < 0 then the socket should
 * be closed and the error returned to the user.  If err > 0
 * it's just the icmp type << 8 | icmp code.  After adjustment
 * header points to the first 8 bytes of the sctp header.  We need
 * to find the appropriate port.
 *
 * The locking strategy used here is very "optimistic". When
 * someone else accesses the socket the ICMP is just dropped
 * and for some paths there is no check at all.
 * A more general error queue to queue errors for later handling
 * is probably better.
 *
 */
void sctp_v4_err(struct sk_buff *skb, __u32 info)
{
	struct iphdr *iph = (struct iphdr *)skb->data;
	const int ihlen = iph->ihl * 4;
	const int type = icmp_hdr(skb)->type;
	const int code = icmp_hdr(skb)->code;
	struct sock *sk;
	struct sctp_association *asoc = NULL;
	struct sctp_transport *transport;
	struct inet_sock *inet;
	sk_buff_data_t saveip, savesctp;
	int err;

	if (skb->len < ihlen + 8) {
		ICMP_INC_STATS_BH(ICMP_MIB_INERRORS);
		return;
	}

	/* Fix up skb to look at the embedded net header. */
	saveip = skb->network_header;
	savesctp = skb->transport_header;
	skb_reset_network_header(skb);
	skb_set_transport_header(skb, ihlen);
	sk = sctp_err_lookup(AF_INET, skb, sctp_hdr(skb), &asoc, &transport);
	/* Put back, the original values. */
	skb->network_header = saveip;
	skb->transport_header = savesctp;
	if (!sk) {
		ICMP_INC_STATS_BH(ICMP_MIB_INERRORS);
		return;
	}
	/* Warning:  The sock lock is held.  Remember to call
	 * sctp_err_finish!
	 */

	switch (type) {
	case ICMP_PARAMETERPROB:
		err = EPROTO;
		break;
	case ICMP_DEST_UNREACH:
		if (code > NR_ICMP_UNREACH)
			goto out_unlock;

		/* PMTU discovery (RFC1191) */
		if (ICMP_FRAG_NEEDED == code) {
			sctp_icmp_frag_needed(sk, asoc, transport, info);
			goto out_unlock;
		}