input.c

一种在UDP协议中实现了拥赛控制和重传机制的协议

/* SCTP kernel reference 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 reference Implementation
 *
 * These functions handle all input from the IP layer into SCTP.
 *
 * The SCTP reference 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
 * 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>

/* 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);


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

	sh = (struct sctphdr *) skb->h.raw;
	cmp = ntohl(sh->checksum);

	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;
}

/* The free routine for skbuffs that sctp receives */
static void sctp_rfree(struct sk_buff *skb)
{
	atomic_sub(sizeof(struct sctp_chunk),&skb->sk->sk_rmem_alloc);
	sock_rfree(skb);
}

/* The ownership wrapper routine to do receive buffer accounting */
static void sctp_rcv_set_owner_r(struct sk_buff *skb, struct sock *sk)
{
	skb_set_owner_r(skb,sk);
	skb->destructor = sctp_rfree;
	atomic_add(sizeof(struct sctp_chunk),&sk->sk_rmem_alloc);
}

/*
 * 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;
	int ret = 0;

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

	SCTP_INC_STATS_BH(SCTP_MIB_INSCTPPACKS);

	sh = (struct sctphdr *) skb->h.raw;

	/* Pull up the IP and SCTP headers. */
	__skb_pull(skb, skb->h.raw - skb->data);
	if (skb->len < sizeof(struct sctphdr))
		goto discard_it;
	if (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(skb->nh.iph->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) || !af->addr_valid(&dest, NULL))
		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)))
	{
		sock_put(sk);
		if (asoc) {
			sctp_association_put(asoc);
			asoc = NULL;
		} else {
			sctp_endpoint_put(ep);
			ep = NULL;
		}
		sk = sctp_get_ctl_sock();
		ep = sctp_sk(sk)->ep;
		sctp_endpoint_hold(ep);
		sock_hold(sk);
		rcvr = &ep->base;
	}

	if (atomic_read(&sk->sk_rmem_alloc) >= sk->sk_rcvbuf)
		goto discard_release;

	/*
	 * RFC 2960, 8.4 - Handle "Out of the blue" Packets.
	 * An SCTP packet is called an "out of the blue" (OOTB)
	 * 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;
		}
	}

	/* SCTP seems to always need a timestamp right now (FIXME) */
	if (skb->stamp.tv_sec == 0) {
		do_gettimeofday(&skb->stamp);
		sock_enable_timestamp(sk); 
	}

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

	ret = sk_filter(sk, skb, 1);
	if (ret)
                goto discard_release;

	/* Create an SCTP packet structure. */
	chunk = sctp_chunkify(skb, asoc, sk);
	if (!chunk) {
		ret = -ENOMEM;
		goto discard_release;
	}

	sctp_rcv_set_owner_r(skb,sk);

	/* 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))
		sk_add_backlog(sk, (struct sk_buff *) chunk);
	else
		sctp_backlog_rcv(sk, (struct sk_buff *) chunk);

	/* Release the sock and any reference counts we took in the
	 * lookup calls.
	 */
	sctp_bh_unlock_sock(sk);
	if (asoc)
		sctp_association_put(asoc);
	else
		sctp_endpoint_put(ep);
	sock_put(sk);
	return ret;

discard_it:
	kfree_skb(skb);
	return ret;

discard_release:
	/* Release any structures we may be holding. */
	sock_put(sk);
	if (asoc)
		sctp_association_put(asoc);
	else
		sctp_endpoint_put(ep);

	goto discard_it;
}

/* Handle second half of inbound skb processing.  If the sock was busy,
 * we may have need to delay processing until later when the sock is
 * released (on the backlog).   If not busy, we call this routine
 * directly from the bottom half.
 */
int sctp_backlog_rcv(struct sock *sk, struct sk_buff *skb)
{
	struct sctp_chunk *chunk;
	struct sctp_inq *inqueue;

	/* One day chunk will live inside the skb, but for
	 * now this works.
	 */
	chunk = (struct sctp_chunk *) skb;
	inqueue = &chunk->rcvr->inqueue;

	sctp_inq_push(inqueue, chunk);
        return 0;
}

/* Handle icmp frag needed error. */
void sctp_icmp_frag_needed(struct sock *sk, struct sctp_association *asoc,
			   struct sctp_transport *t, __u32 pmtu)
{
	if (unlikely(pmtu < SCTP_DEFAULT_MINSEGMENT)) {
		printk(KERN_WARNING "%s: Reported pmtu %d too low, "
		       "using default minimum of %d\n", __FUNCTION__, pmtu,
		       SCTP_DEFAULT_MINSEGMENT);
		pmtu = SCTP_DEFAULT_MINSEGMENT;
	}

	if (!sock_owned_by_user(sk) && t && (t->pmtu != pmtu)) {
		t->pmtu = pmtu;
		sctp_assoc_sync_pmtu(asoc);
		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_endpoint *ep,
                           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, NULL,
		   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_endpoint **epp,
			     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_endpoint *ep = NULL;
	struct sctp_association *asoc = NULL;
	struct sctp_transport *transport = NULL;

	*app = NULL; *epp = 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) {
		/* If there is no matching association, see if it matches any
		 * endpoint. This may happen for an ICMP error generated in
		 * response to an INIT_ACK.
		 */
		ep = __sctp_rcv_lookup_endpoint(&daddr);
		if (!ep) {
			return NULL;
		}
	}

	if (asoc) {
		sk = asoc->base.sk;

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

	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);

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

out:
	sock_put(sk);
	if (asoc)
		sctp_association_put(asoc);
	if (ep)
		sctp_endpoint_put(ep);
	return NULL;
}

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

/*
 * 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;
	struct sctphdr *sh = (struct sctphdr *)(skb->data + (iph->ihl <<2));
	int type = skb->h.icmph->type;
	int code = skb->h.icmph->code;
	struct sock *sk;