Linux-2.6.12-rc2

Initial git repository build. I'm not bothering with the full history,
even though we have it. We can create a separate "historical" git
archive of that later if we want to, and in the meantime it's about
3.2GB when imported into git - space that would just make the early
git days unnecessarily complicated, when we don't have a lot of good
infrastructure for it.

Let it rip!

net/sctp/Kconfig

@@ -0,0 +1,89 @@
+#
+# SCTP configuration
+#
+
+menu "SCTP Configuration (EXPERIMENTAL)"
+	depends on INET && EXPERIMENTAL
+
+config IP_SCTP
+	tristate "The SCTP Protocol (EXPERIMENTAL)"
+	depends on IPV6 || IPV6=n
+	select CRYPTO if SCTP_HMAC_SHA1 || SCTP_HMAC_MD5
+	select CRYPTO_HMAC if SCTP_HMAC_SHA1 || SCTP_HMAC_MD5
+	select CRYPTO_SHA1 if SCTP_HMAC_SHA1
+	select CRYPTO_MD5 if SCTP_HMAC_MD5
+	---help---
+	  Stream Control Transmission Protocol
+
+	  From RFC 2960 <http://www.ietf.org/rfc/rfc2960.txt>.
+
+	  "SCTP is a reliable transport protocol operating on top of a
+	  connectionless packet network such as IP.  It offers the following
+	  services to its users:
+
+	  -- acknowledged error-free non-duplicated transfer of user data,
+	  -- data fragmentation to conform to discovered path MTU size,
+	  -- sequenced delivery of user messages within multiple streams,
+	  with an option for order-of-arrival delivery of individual user
+	  messages,
+	  -- optional bundling of multiple user messages into a single SCTP
+	  packet, and
+	  -- network-level fault tolerance through supporting of multi-
+	  homing at either or both ends of an association."
+
+	  To compile this protocol support as a module, choose M here: the
+	  module will be called sctp.
+
+	  If in doubt, say N.
+
+config SCTP_DBG_MSG
+	bool "SCTP: Debug messages"
+	depends on IP_SCTP
+	help
+	  If you say Y, this will enable verbose debugging messages. 
+
+	  If unsure, say N.  However, if you are running into problems, use 
+	  this option to gather detailed trace information
+
+config SCTP_DBG_OBJCNT
+	bool "SCTP: Debug object counts"
+	depends on IP_SCTP
+	help
+	  If you say Y, this will enable debugging support for counting the 
+	  type of objects that are currently allocated.  This is useful for 
+	  identifying memory leaks.   If the /proc filesystem is enabled this 
+	  debug information can be viewed by 
+	  'cat /proc/net/sctp/sctp_dbg_objcnt'
+
+	  If unsure, say N
+
+choice
+	prompt "SCTP: Cookie HMAC Algorithm"
+	depends on IP_SCTP
+	default SCTP_HMAC_MD5
+	help
+	  HMAC algorithm to be used during association initialization.  It
+	  is strongly recommended to use HMAC-SHA1 or HMAC-MD5.  See 
+	  configuration for Cryptographic API and enable those algorithms
+          to make usable by SCTP. 
+
+config SCTP_HMAC_NONE
+	bool "None"
+	help 
+	  Choosing this disables the use of an HMAC during association 
+	  establishment.  It is advised to use either HMAC-MD5 or HMAC-SHA1.
+
+config SCTP_HMAC_SHA1
+	bool "HMAC-SHA1"
+	help 
+	  Enable the use of HMAC-SHA1 during association establishment.  It 
+	  is advised to use either HMAC-MD5 or HMAC-SHA1.
+
+config SCTP_HMAC_MD5
+	bool "HMAC-MD5"
+	help
+	  Enable the use of HMAC-MD5 during association establishment.  It is 
+	  advised to use either HMAC-MD5 or HMAC-SHA1.
+
+endchoice
+endmenu

net/sctp/Makefile

@@ -0,0 +1,17 @@
+#
+# Makefile for SCTP support code.
+#
+
+obj-$(CONFIG_IP_SCTP) += sctp.o
+
+sctp-y := sm_statetable.o sm_statefuns.o sm_sideeffect.o \
+	  protocol.o endpointola.o associola.o \
+	  transport.o chunk.o sm_make_chunk.o ulpevent.o \
+	  inqueue.o outqueue.o ulpqueue.o command.o \
+	  tsnmap.o bind_addr.o socket.o primitive.o \
+	  output.o input.o debug.o ssnmap.o proc.o crc32c.o
+
+sctp-$(CONFIG_SCTP_DBG_OBJCNT) += objcnt.o
+sctp-$(CONFIG_SYSCTL) += sysctl.o
+
+sctp-$(subst m,y,$(CONFIG_IPV6))	+= ipv6.o

net/sctp/bind_addr.c

@@ -0,0 +1,417 @@
+/* SCTP kernel reference Implementation
+ * (C) Copyright IBM Corp. 2001, 2003
+ * Copyright (c) Cisco 1999,2000
+ * Copyright (c) Motorola 1999,2000,2001
+ * Copyright (c) La Monte H.P. Yarroll 2001
+ *
+ * This file is part of the SCTP kernel reference implementation.
+ *
+ * A collection class to handle the storage of transport addresses.
+ *
+ * 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 <lksctp-developers@lists.sourceforge.net>
+ *
+ * Or submit a bug report through the following website:
+ *    http://www.sf.net/projects/lksctp
+ *
+ * Written or modified by:
+ *    La Monte H.P. Yarroll <piggy@acm.org>
+ *    Karl Knutson          <karl@athena.chicago.il.us>
+ *    Jon Grimm             <jgrimm@us.ibm.com>
+ *    Daisy Chang           <daisyc@us.ibm.com>
+ *
+ * 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/sched.h>
+#include <linux/in.h>
+#include <net/sock.h>
+#include <net/ipv6.h>
+#include <net/if_inet6.h>
+#include <net/sctp/sctp.h>
+#include <net/sctp/sm.h>
+
+/* Forward declarations for internal helpers. */
+static int sctp_copy_one_addr(struct sctp_bind_addr *, union sctp_addr *,
+			      sctp_scope_t scope, int gfp, int flags);
+static void sctp_bind_addr_clean(struct sctp_bind_addr *);
+
+/* First Level Abstractions. */
+
+/* Copy 'src' to 'dest' taking 'scope' into account.  Omit addresses
+ * in 'src' which have a broader scope than 'scope'.
+ */
+int sctp_bind_addr_copy(struct sctp_bind_addr *dest, 
+			const struct sctp_bind_addr *src,
+			sctp_scope_t scope, int gfp, int flags)
+{
+	struct sctp_sockaddr_entry *addr;
+	struct list_head *pos;
+	int error = 0;
+
+	/* All addresses share the same port.  */
+	dest->port = src->port;
+
+	/* Extract the addresses which are relevant for this scope.  */
+	list_for_each(pos, &src->address_list) {
+		addr = list_entry(pos, struct sctp_sockaddr_entry, list);
+		error = sctp_copy_one_addr(dest, &addr->a, scope,
+					   gfp, flags);
+		if (error < 0)
+			goto out;
+	}
+
+	/* If there are no addresses matching the scope and
+	 * this is global scope, try to get a link scope address, with
+	 * the assumption that we must be sitting behind a NAT.
+	 */
+	if (list_empty(&dest->address_list) && (SCTP_SCOPE_GLOBAL == scope)) {
+		list_for_each(pos, &src->address_list) {
+			addr = list_entry(pos, struct sctp_sockaddr_entry,
+					  list);
+			error = sctp_copy_one_addr(dest, &addr->a,
+						   SCTP_SCOPE_LINK, gfp,
+						   flags);
+			if (error < 0)
+				goto out;
+		}
+	}
+
+out:
+	if (error)
+		sctp_bind_addr_clean(dest);
+
+	return error;
+}
+
+/* Initialize the SCTP_bind_addr structure for either an endpoint or
+ * an association.
+ */
+void sctp_bind_addr_init(struct sctp_bind_addr *bp, __u16 port)
+{
+	bp->malloced = 0;
+
+	INIT_LIST_HEAD(&bp->address_list);
+	bp->port = port;
+}
+
+/* Dispose of the address list. */
+static void sctp_bind_addr_clean(struct sctp_bind_addr *bp)
+{
+	struct sctp_sockaddr_entry *addr;
+	struct list_head *pos, *temp;
+
+	/* Empty the bind address list. */
+	list_for_each_safe(pos, temp, &bp->address_list) {
+		addr = list_entry(pos, struct sctp_sockaddr_entry, list);
+		list_del(pos);
+		kfree(addr);
+		SCTP_DBG_OBJCNT_DEC(addr);
+	}
+}
+
+/* Dispose of an SCTP_bind_addr structure  */
+void sctp_bind_addr_free(struct sctp_bind_addr *bp)
+{
+	/* Empty the bind address list. */
+	sctp_bind_addr_clean(bp);
+
+	if (bp->malloced) {
+		kfree(bp);
+		SCTP_DBG_OBJCNT_DEC(bind_addr);
+	}
+}
+
+/* Add an address to the bind address list in the SCTP_bind_addr structure. */
+int sctp_add_bind_addr(struct sctp_bind_addr *bp, union sctp_addr *new,
+		       int gfp)
+{
+	struct sctp_sockaddr_entry *addr;
+
+	/* Add the address to the bind address list.  */
+	addr = t_new(struct sctp_sockaddr_entry, gfp);
+	if (!addr)
+		return -ENOMEM;
+
+	memcpy(&addr->a, new, sizeof(*new));
+
+	/* Fix up the port if it has not yet been set.
+	 * Both v4 and v6 have the port at the same offset.
+	 */
+	if (!addr->a.v4.sin_port)
+		addr->a.v4.sin_port = bp->port;
+
+	INIT_LIST_HEAD(&addr->list);
+	list_add_tail(&addr->list, &bp->address_list);
+	SCTP_DBG_OBJCNT_INC(addr);
+
+	return 0;
+}
+
+/* Delete an address from the bind address list in the SCTP_bind_addr
+ * structure.
+ */
+int sctp_del_bind_addr(struct sctp_bind_addr *bp, union sctp_addr *del_addr)
+{
+	struct list_head *pos, *temp;
+	struct sctp_sockaddr_entry *addr;
+
+	list_for_each_safe(pos, temp, &bp->address_list) {
+		addr = list_entry(pos, struct sctp_sockaddr_entry, list);
+		if (sctp_cmp_addr_exact(&addr->a, del_addr)) {
+			/* Found the exact match. */
+			list_del(pos);
+			kfree(addr);
+			SCTP_DBG_OBJCNT_DEC(addr);
+
+			return 0;
+		}
+	}
+
+	return -EINVAL;
+}
+
+/* Create a network byte-order representation of all the addresses
+ * formated as SCTP parameters.
+ *
+ * The second argument is the return value for the length.
+ */
+union sctp_params sctp_bind_addrs_to_raw(const struct sctp_bind_addr *bp,
+					 int *addrs_len, int gfp)
+{
+	union sctp_params addrparms;
+	union sctp_params retval;
+	int addrparms_len;
+	union sctp_addr_param rawaddr;
+	int len;
+	struct sctp_sockaddr_entry *addr;
+	struct list_head *pos;
+	struct sctp_af *af;
+
+	addrparms_len = 0;
+	len = 0;
+
+	/* Allocate enough memory at once. */
+	list_for_each(pos, &bp->address_list) {
+		len += sizeof(union sctp_addr_param);
+	}
+
+	/* Don't even bother embedding an address if there
+	 * is only one.
+	 */
+	if (len == sizeof(union sctp_addr_param)) {
+		retval.v = NULL;
+		goto end_raw;
+	}
+
+	retval.v = kmalloc(len, gfp);
+	if (!retval.v)
+		goto end_raw;
+
+	addrparms = retval;
+
+	list_for_each(pos, &bp->address_list) {
+		addr = list_entry(pos, struct sctp_sockaddr_entry, list);
+		af = sctp_get_af_specific(addr->a.v4.sin_family);
+		len = af->to_addr_param(&addr->a, &rawaddr);
+		memcpy(addrparms.v, &rawaddr, len);
+		addrparms.v += len;
+		addrparms_len += len;
+	}
+
+end_raw:
+	*addrs_len = addrparms_len;
+	return retval;
+}
+
+/*
+ * Create an address list out of the raw address list format (IPv4 and IPv6
+ * address parameters).
+ */
+int sctp_raw_to_bind_addrs(struct sctp_bind_addr *bp, __u8 *raw_addr_list,
+			   int addrs_len, __u16 port, int gfp)
+{
+	union sctp_addr_param *rawaddr;
+	struct sctp_paramhdr *param;
+	union sctp_addr addr;
+	int retval = 0;
+	int len;
+	struct sctp_af *af;
+
+	/* Convert the raw address to standard address format */
+	while (addrs_len) {
+		param = (struct sctp_paramhdr *)raw_addr_list;
+		rawaddr = (union sctp_addr_param *)raw_addr_list;
+
+		af = sctp_get_af_specific(param_type2af(param->type));
+		if (unlikely(!af)) {
+			retval = -EINVAL;
+			sctp_bind_addr_clean(bp);
+			break;
+		}
+
+		af->from_addr_param(&addr, rawaddr, port, 0);
+		retval = sctp_add_bind_addr(bp, &addr, gfp);
+		if (retval) {
+			/* Can't finish building the list, clean up. */
+			sctp_bind_addr_clean(bp);
+			break;
+		}
+
+		len = ntohs(param->length);
+		addrs_len -= len;
+		raw_addr_list += len;
+	}
+
+	return retval;
+}
+
+/********************************************************************
+ * 2nd Level Abstractions
+ ********************************************************************/
+
+/* Does this contain a specified address?  Allow wildcarding. */
+int sctp_bind_addr_match(struct sctp_bind_addr *bp, 
+			 const union sctp_addr *addr,
+			 struct sctp_sock *opt)
+{
+	struct sctp_sockaddr_entry *laddr;
+	struct list_head *pos;
+
+	list_for_each(pos, &bp->address_list) {
+		laddr = list_entry(pos, struct sctp_sockaddr_entry, list);
+		if (opt->pf->cmp_addr(&laddr->a, addr, opt))
+ 			return 1;
+	}
+
+	return 0;
+}
+
+/* Find the first address in the bind address list that is not present in
+ * the addrs packed array.
+ */
+union sctp_addr *sctp_find_unmatch_addr(struct sctp_bind_addr	*bp,
+					const union sctp_addr	*addrs,
+					int			addrcnt,
+					struct sctp_sock	*opt)
+{
+	struct sctp_sockaddr_entry	*laddr;
+	union sctp_addr			*addr;
+	void 				*addr_buf;
+	struct sctp_af			*af;
+	struct list_head		*pos;
+	int				i;
+
+	list_for_each(pos, &bp->address_list) {
+		laddr = list_entry(pos, struct sctp_sockaddr_entry, list);
+		
+		addr_buf = (union sctp_addr *)addrs;
+		for (i = 0; i < addrcnt; i++) {
+			addr = (union sctp_addr *)addr_buf;
+			af = sctp_get_af_specific(addr->v4.sin_family);
+			if (!af) 
+				return NULL;
+
+			if (opt->pf->cmp_addr(&laddr->a, addr, opt))
+				break;
+
+			addr_buf += af->sockaddr_len;
+		}
+		if (i == addrcnt)
+			return &laddr->a;
+	}
+
+	return NULL;
+}
+
+/* Copy out addresses from the global local address list. */
+static int sctp_copy_one_addr(struct sctp_bind_addr *dest, 
+			      union sctp_addr *addr,
+			      sctp_scope_t scope, int gfp, int flags)
+{
+	int error = 0;
+
+	if (sctp_is_any(addr)) {
+		error = sctp_copy_local_addr_list(dest, scope, gfp, flags);
+	} else if (sctp_in_scope(addr, scope)) {
+		/* Now that the address is in scope, check to see if
+		 * the address type is supported by local sock as
+		 * well as the remote peer.
+		 */
+		if ((((AF_INET == addr->sa.sa_family) &&
+		      (flags & SCTP_ADDR4_PEERSUPP))) ||
+		    (((AF_INET6 == addr->sa.sa_family) &&
+		      (flags & SCTP_ADDR6_ALLOWED) &&
+		      (flags & SCTP_ADDR6_PEERSUPP))))
+			error = sctp_add_bind_addr(dest, addr, gfp);
+	}
+
+	return error;
+}
+
+/* Is this a wildcard address?  */
+int sctp_is_any(const union sctp_addr *addr)
+{
+	struct sctp_af *af = sctp_get_af_specific(addr->sa.sa_family);
+	if (!af)
+		return 0;
+	return af->is_any(addr);
+}
+
+/* Is 'addr' valid for 'scope'?  */
+int sctp_in_scope(const union sctp_addr *addr, sctp_scope_t scope)
+{
+	sctp_scope_t addr_scope = sctp_scope(addr);
+
+	/* The unusable SCTP addresses will not be considered with
+	 * any defined scopes.
+	 */
+	if (SCTP_SCOPE_UNUSABLE == addr_scope)
+		return 0;
+	/*
+	 * 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.
+	 */
+	if (addr_scope <= scope)
+		return 1;
+
+	return 0;
+}
+
+/********************************************************************
+ * 3rd Level Abstractions
+ ********************************************************************/
+
+/* What is the scope of 'addr'?  */
+sctp_scope_t sctp_scope(const union sctp_addr *addr)
+{
+	struct sctp_af *af;
+
+	af = sctp_get_af_specific(addr->sa.sa_family);
+	if (!af)
+		return SCTP_SCOPE_UNUSABLE;
+
+	return af->scope((union sctp_addr *)addr);
+}

net/sctp/chunk.c

@@ -0,0 +1,309 @@
+/* SCTP kernel reference Implementation
+ * (C) Copyright IBM Corp. 2003, 2004
+ *
+ * This file is part of the SCTP kernel reference Implementation
+ *
+ * This file contains the code relating the the chunk abstraction.
+ *
+ * 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 <lksctp-developers@lists.sourceforge.net>
+ *
+ * Or submit a bug report through the following website:
+ *    http://www.sf.net/projects/lksctp
+ *
+ * Written or modified by:
+ *    Jon Grimm             <jgrimm@us.ibm.com>
+ *    Sridhar Samudrala     <sri@us.ibm.com>
+ *
+ * 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/kernel.h>
+#include <linux/net.h>
+#include <linux/inet.h>
+#include <linux/skbuff.h>
+#include <net/sock.h>
+#include <net/sctp/sctp.h>
+#include <net/sctp/sm.h>
+
+/* This file is mostly in anticipation of future work, but initially
+ * populate with fragment tracking for an outbound message.
+ */
+
+/* Initialize datamsg from memory. */
+static void sctp_datamsg_init(struct sctp_datamsg *msg)
+{
+	atomic_set(&msg->refcnt, 1);
+	msg->send_failed = 0;
+	msg->send_error = 0;
+	msg->can_abandon = 0;
+	msg->expires_at = 0;
+	INIT_LIST_HEAD(&msg->chunks);
+}
+
+/* Allocate and initialize datamsg. */
+SCTP_STATIC struct sctp_datamsg *sctp_datamsg_new(int gfp)
+{
+	struct sctp_datamsg *msg;
+	msg = kmalloc(sizeof(struct sctp_datamsg), gfp);
+	if (msg)
+		sctp_datamsg_init(msg);
+	SCTP_DBG_OBJCNT_INC(datamsg);
+	return msg;
+}
+
+/* Final destructruction of datamsg memory. */
+static void sctp_datamsg_destroy(struct sctp_datamsg *msg)
+{
+	struct list_head *pos, *temp;
+	struct sctp_chunk *chunk;
+	struct sctp_sock *sp;
+	struct sctp_ulpevent *ev;
+	struct sctp_association *asoc = NULL;
+	int error = 0, notify;
+
+	/* If we failed, we may need to notify. */
+	notify = msg->send_failed ? -1 : 0;
+
+	/* Release all references. */
+	list_for_each_safe(pos, temp, &msg->chunks) {
+		list_del_init(pos);
+		chunk = list_entry(pos, struct sctp_chunk, frag_list);
+		/* Check whether we _really_ need to notify. */
+		if (notify < 0) {
+			asoc = chunk->asoc;
+			if (msg->send_error)
+				error = msg->send_error;
+			else
+				error = asoc->outqueue.error;
+
+			sp = sctp_sk(asoc->base.sk);
+			notify = sctp_ulpevent_type_enabled(SCTP_SEND_FAILED,
+							    &sp->subscribe);
+		}
+
+		/* Generate a SEND FAILED event only if enabled. */
+		if (notify > 0) {
+			int sent;
+			if (chunk->has_tsn)
+				sent = SCTP_DATA_SENT;
+			else
+				sent = SCTP_DATA_UNSENT;
+
+			ev = sctp_ulpevent_make_send_failed(asoc, chunk, sent,
+							    error, GFP_ATOMIC);
+			if (ev)
+				sctp_ulpq_tail_event(&asoc->ulpq, ev);
+		}
+
+		sctp_chunk_put(chunk);
+	}
+
+	SCTP_DBG_OBJCNT_DEC(datamsg);
+	kfree(msg);
+}
+
+/* Hold a reference. */
+static void sctp_datamsg_hold(struct sctp_datamsg *msg)
+{
+	atomic_inc(&msg->refcnt);
+}
+
+/* Release a reference. */
+void sctp_datamsg_put(struct sctp_datamsg *msg)
+{
+	if (atomic_dec_and_test(&msg->refcnt))
+		sctp_datamsg_destroy(msg);
+}
+
+/* Free a message.  Really just give up a reference, the
+ * really free happens in sctp_datamsg_destroy().
+ */
+void sctp_datamsg_free(struct sctp_datamsg *msg)
+{
+	sctp_datamsg_put(msg);
+}
+
+/* Hold on to all the fragments until all chunks have been sent. */
+void sctp_datamsg_track(struct sctp_chunk *chunk)
+{
+	sctp_chunk_hold(chunk);
+}
+
+/* Assign a chunk to this datamsg. */
+static void sctp_datamsg_assign(struct sctp_datamsg *msg, struct sctp_chunk *chunk)
+{
+	sctp_datamsg_hold(msg);
+	chunk->msg = msg;
+}
+
+
+/* A data chunk can have a maximum payload of (2^16 - 20).  Break
+ * down any such message into smaller chunks.  Opportunistically, fragment
+ * the chunks down to the current MTU constraints.  We may get refragmented
+ * later if the PMTU changes, but it is _much better_ to fragment immediately
+ * with a reasonable guess than always doing our fragmentation on the
+ * soft-interrupt.
+ */
+struct sctp_datamsg *sctp_datamsg_from_user(struct sctp_association *asoc,
+					    struct sctp_sndrcvinfo *sinfo,
+					    struct msghdr *msgh, int msg_len)
+{
+	int max, whole, i, offset, over, err;
+	int len, first_len;
+	struct sctp_chunk *chunk;
+	struct sctp_datamsg *msg;
+	struct list_head *pos, *temp;
+	__u8 frag;
+
+	msg = sctp_datamsg_new(GFP_KERNEL);
+	if (!msg)
+		return NULL;
+
+	/* Note: Calculate this outside of the loop, so that all fragments
+	 * have the same expiration.
+	 */
+	if (sinfo->sinfo_timetolive) {
+		/* sinfo_timetolive is in milliseconds */
+		msg->expires_at = jiffies +
+				    msecs_to_jiffies(sinfo->sinfo_timetolive);
+		msg->can_abandon = 1;
+		SCTP_DEBUG_PRINTK("%s: msg:%p expires_at: %ld jiffies:%ld\n",
+				  __FUNCTION__, msg, msg->expires_at, jiffies);
+	}
+
+	max = asoc->frag_point;
+
+	whole = 0;
+	first_len = max;
+
+	/* Encourage Cookie-ECHO bundling. */
+	if (asoc->state < SCTP_STATE_COOKIE_ECHOED) {
+		whole = msg_len / (max - SCTP_ARBITRARY_COOKIE_ECHO_LEN);
+
+		/* Account for the DATA to be bundled with the COOKIE-ECHO. */
+		if (whole) {
+			first_len = max - SCTP_ARBITRARY_COOKIE_ECHO_LEN;
+			msg_len -= first_len;
+			whole = 1;
+		}
+	}
+
+	/* How many full sized?  How many bytes leftover? */
+	whole += msg_len / max;
+	over = msg_len % max;
+	offset = 0;
+
+	if ((whole > 1) || (whole && over))
+		SCTP_INC_STATS_USER(SCTP_MIB_FRAGUSRMSGS);
+
+	/* Create chunks for all the full sized DATA chunks. */
+	for (i=0, len=first_len; i < whole; i++) {
+		frag = SCTP_DATA_MIDDLE_FRAG;
+
+		if (0 == i)
+			frag |= SCTP_DATA_FIRST_FRAG;
+
+		if ((i == (whole - 1)) && !over)
+			frag |= SCTP_DATA_LAST_FRAG;
+
+		chunk = sctp_make_datafrag_empty(asoc, sinfo, len, frag, 0);
+
+		if (!chunk)
+			goto errout;
+		err = sctp_user_addto_chunk(chunk, offset, len, msgh->msg_iov);
+		if (err < 0)
+			goto errout;
+
+		offset += len;
+
+		/* Put the chunk->skb back into the form expected by send.  */
+		__skb_pull(chunk->skb, (__u8 *)chunk->chunk_hdr
+			   - (__u8 *)chunk->skb->data);
+
+		sctp_datamsg_assign(msg, chunk);
+		list_add_tail(&chunk->frag_list, &msg->chunks);
+
+		/* The first chunk, the first chunk was likely short
+		 * to allow bundling, so reset to full size.
+		 */
+		if (0 == i)
+			len = max;
+	}
+
+	/* .. now the leftover bytes. */
+	if (over) {
+		if (!whole)
+			frag = SCTP_DATA_NOT_FRAG;
+		else
+			frag = SCTP_DATA_LAST_FRAG;
+
+		chunk = sctp_make_datafrag_empty(asoc, sinfo, over, frag, 0);
+
+		if (!chunk)
+			goto errout;
+
+		err = sctp_user_addto_chunk(chunk, offset, over,msgh->msg_iov);
+
+		/* Put the chunk->skb back into the form expected by send.  */
+		__skb_pull(chunk->skb, (__u8 *)chunk->chunk_hdr
+			   - (__u8 *)chunk->skb->data);
+		if (err < 0)
+			goto errout;
+
+		sctp_datamsg_assign(msg, chunk);
+		list_add_tail(&chunk->frag_list, &msg->chunks);
+	}
+
+	return msg;
+
+errout:
+	list_for_each_safe(pos, temp, &msg->chunks) {
+		list_del_init(pos);
+		chunk = list_entry(pos, struct sctp_chunk, frag_list);
+		sctp_chunk_free(chunk);
+	}
+	sctp_datamsg_free(msg);
+	return NULL;
+}
+
+/* Check whether this message has expired. */
+int sctp_chunk_abandoned(struct sctp_chunk *chunk)
+{
+	struct sctp_datamsg *msg = chunk->msg;
+
+	if (!msg->can_abandon)
+		return 0;
+
+	if (time_after(jiffies, msg->expires_at))
+		return 1;
+
+	return 0;
+}
+
+/* This chunk (and consequently entire message) has failed in its sending. */
+void sctp_chunk_fail(struct sctp_chunk *chunk, int error)
+{
+	chunk->msg->send_failed = 1;
+	chunk->msg->send_error = error;
+}

net/sctp/command.c

@@ -0,0 +1,81 @@
+/* SCTP kernel reference Implementation Copyright (C) 1999-2001
+ * Cisco, Motorola, and IBM
+ * Copyright 2001 La Monte H.P. Yarroll
+ *
+ * This file is part of the SCTP kernel reference Implementation
+ *
+ * These functions manipulate sctp command sequences.
+ *
+ * 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 <lksctp-developers@lists.sourceforge.net>
+ *
+ * Or submit a bug report through the following website:
+ *    http://www.sf.net/projects/lksctp
+ *
+ * Written or modified by:
+ *    La Monte H.P. Yarroll <piggy@acm.org>
+ *    Karl Knutson <karl@athena.chicago.il.us>
+ *
+ * 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 <net/sctp/sctp.h>
+#include <net/sctp/sm.h>
+
+/* Initialize a block of memory as a command sequence. */
+int sctp_init_cmd_seq(sctp_cmd_seq_t *seq)
+{
+	memset(seq, 0, sizeof(sctp_cmd_seq_t));
+	return 1;		/* We always succeed.  */
+}
+
+/* Add a command to a sctp_cmd_seq_t.
+ * Return 0 if the command sequence is full.
+ */
+int sctp_add_cmd(sctp_cmd_seq_t *seq, sctp_verb_t verb, sctp_arg_t obj)
+{
+	if (seq->next_free_slot >= SCTP_MAX_NUM_COMMANDS)
+		goto fail;
+
+	seq->cmds[seq->next_free_slot].verb = verb;
+	seq->cmds[seq->next_free_slot++].obj = obj;
+
+	return 1;
+
+fail:
+	return 0;
+}
+
+/* Return the next command structure in a sctp_cmd_seq.
+ * Returns NULL at the end of the sequence.
+ */
+sctp_cmd_t *sctp_next_cmd(sctp_cmd_seq_t *seq)
+{
+	sctp_cmd_t *retval = NULL;
+
+	if (seq->next_cmd < seq->next_free_slot)
+		retval = &seq->cmds[seq->next_cmd++];
+
+	return retval;
+}
+

net/sctp/crc32c.c

@@ -0,0 +1,220 @@
+/* SCTP kernel reference Implementation
+ * Copyright (c) 1999-2001 Motorola, Inc.
+ * Copyright (c) 2001-2003 International Business Machines, Corp.
+ * 
+ * This file is part of the SCTP kernel reference Implementation
+ * 
+ * SCTP Checksum functions
+ * 
+ * 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 <lksctp-developers@lists.sourceforge.net>
+ * 
+ * Or submit a bug report through the following website:
+ *    http://www.sf.net/projects/lksctp
+ *
+ * Written or modified by: 
+ *    Dinakaran Joseph 
+ *    Jon Grimm <jgrimm@us.ibm.com>
+ *    Sridhar Samudrala <sri@us.ibm.com>
+ * 
+ * Any bugs reported given to us we will try to fix... any fixes shared will
+ * be incorporated into the next SCTP release.
+ */
+
+/* The following code has been taken directly from
+ * draft-ietf-tsvwg-sctpcsum-03.txt
+ *
+ * The code has now been modified specifically for SCTP knowledge.
+ */
+
+#include <linux/types.h>
+#include <net/sctp/sctp.h>
+
+#define CRC32C_POLY 0x1EDC6F41
+#define CRC32C(c,d) (c=(c>>8)^crc_c[(c^(d))&0xFF])
+/* * * * * * * * * * * * * * * * * * * * * * * * * * * * * * * * */
+/* Copyright 2001, D. Otis.  Use this program, code or tables    */
+/* extracted from it, as desired without restriction.            */
+/*                                                               */
+/* 32 Bit Reflected CRC table generation for SCTP.               */
+/* To accommodate serial byte data being shifted out least       */
+/* significant bit first, the table's 32 bit words are reflected */
+/* which flips both byte and bit MS and LS positions.  The CRC   */
+/* is calculated MS bits first from the perspective of the serial*/
+/* stream.  The x^32 term is implied and the x^0 term may also   */
+/* be shown as +1.  The polynomial code used is 0x1EDC6F41.      */
+/* Castagnoli93                                                  */
+/* x^32+x^28+x^27+x^26+x^25+x^23+x^22+x^20+x^19+x^18+x^14+x^13+  */
+/* x^11+x^10+x^9+x^8+x^6+x^0                                     */
+/* Guy Castagnoli Stefan Braeuer and Martin Herrman              */
+/* "Optimization of Cyclic Redundancy-Check Codes                */
+/* with 24 and 32 Parity Bits",                                  */
+/* IEEE Transactions on Communications, Vol.41, No.6, June 1993  */
+/* * * * * * * * * * * * * * * * * * * * * * * * * * * * * * * * */
+static const __u32 crc_c[256] = {
+	0x00000000, 0xF26B8303, 0xE13B70F7, 0x1350F3F4,
+	0xC79A971F, 0x35F1141C, 0x26A1E7E8, 0xD4CA64EB,
+	0x8AD958CF, 0x78B2DBCC, 0x6BE22838, 0x9989AB3B,
+	0x4D43CFD0, 0xBF284CD3, 0xAC78BF27, 0x5E133C24,
+	0x105EC76F, 0xE235446C, 0xF165B798, 0x030E349B,
+	0xD7C45070, 0x25AFD373, 0x36FF2087, 0xC494A384,
+	0x9A879FA0, 0x68EC1CA3, 0x7BBCEF57, 0x89D76C54,
+	0x5D1D08BF, 0xAF768BBC, 0xBC267848, 0x4E4DFB4B,
+	0x20BD8EDE, 0xD2D60DDD, 0xC186FE29, 0x33ED7D2A,
+	0xE72719C1, 0x154C9AC2, 0x061C6936, 0xF477EA35,
+	0xAA64D611, 0x580F5512, 0x4B5FA6E6, 0xB93425E5,
+	0x6DFE410E, 0x9F95C20D, 0x8CC531F9, 0x7EAEB2FA,
+	0x30E349B1, 0xC288CAB2, 0xD1D83946, 0x23B3BA45,
+	0xF779DEAE, 0x05125DAD, 0x1642AE59, 0xE4292D5A,
+	0xBA3A117E, 0x4851927D, 0x5B016189, 0xA96AE28A,
+	0x7DA08661, 0x8FCB0562, 0x9C9BF696, 0x6EF07595,
+	0x417B1DBC, 0xB3109EBF, 0xA0406D4B, 0x522BEE48,
+	0x86E18AA3, 0x748A09A0, 0x67DAFA54, 0x95B17957,
+	0xCBA24573, 0x39C9C670, 0x2A993584, 0xD8F2B687,
+	0x0C38D26C, 0xFE53516F, 0xED03A29B, 0x1F682198,
+	0x5125DAD3, 0xA34E59D0, 0xB01EAA24, 0x42752927,
+	0x96BF4DCC, 0x64D4CECF, 0x77843D3B, 0x85EFBE38,
+	0xDBFC821C, 0x2997011F, 0x3AC7F2EB, 0xC8AC71E8,
+	0x1C661503, 0xEE0D9600, 0xFD5D65F4, 0x0F36E6F7,
+	0x61C69362, 0x93AD1061, 0x80FDE395, 0x72966096,
+	0xA65C047D, 0x5437877E, 0x4767748A, 0xB50CF789,
+	0xEB1FCBAD, 0x197448AE, 0x0A24BB5A, 0xF84F3859,
+	0x2C855CB2, 0xDEEEDFB1, 0xCDBE2C45, 0x3FD5AF46,
+	0x7198540D, 0x83F3D70E, 0x90A324FA, 0x62C8A7F9,
+	0xB602C312, 0x44694011, 0x5739B3E5, 0xA55230E6,
+	0xFB410CC2, 0x092A8FC1, 0x1A7A7C35, 0xE811FF36,
+	0x3CDB9BDD, 0xCEB018DE, 0xDDE0EB2A, 0x2F8B6829,
+	0x82F63B78, 0x709DB87B, 0x63CD4B8F, 0x91A6C88C,
+	0x456CAC67, 0xB7072F64, 0xA457DC90, 0x563C5F93,
+	0x082F63B7, 0xFA44E0B4, 0xE9141340, 0x1B7F9043,
+	0xCFB5F4A8, 0x3DDE77AB, 0x2E8E845F, 0xDCE5075C,
+	0x92A8FC17, 0x60C37F14, 0x73938CE0, 0x81F80FE3,
+	0x55326B08, 0xA759E80B, 0xB4091BFF, 0x466298FC,
+	0x1871A4D8, 0xEA1A27DB, 0xF94AD42F, 0x0B21572C,
+	0xDFEB33C7, 0x2D80B0C4, 0x3ED04330, 0xCCBBC033,
+	0xA24BB5A6, 0x502036A5, 0x4370C551, 0xB11B4652,
+	0x65D122B9, 0x97BAA1BA, 0x84EA524E, 0x7681D14D,
+	0x2892ED69, 0xDAF96E6A, 0xC9A99D9E, 0x3BC21E9D,
+	0xEF087A76, 0x1D63F975, 0x0E330A81, 0xFC588982,
+	0xB21572C9, 0x407EF1CA, 0x532E023E, 0xA145813D,
+	0x758FE5D6, 0x87E466D5, 0x94B49521, 0x66DF1622,
+	0x38CC2A06, 0xCAA7A905, 0xD9F75AF1, 0x2B9CD9F2,
+	0xFF56BD19, 0x0D3D3E1A, 0x1E6DCDEE, 0xEC064EED,
+	0xC38D26C4, 0x31E6A5C7, 0x22B65633, 0xD0DDD530,
+	0x0417B1DB, 0xF67C32D8, 0xE52CC12C, 0x1747422F,
+	0x49547E0B, 0xBB3FFD08, 0xA86F0EFC, 0x5A048DFF,
+	0x8ECEE914, 0x7CA56A17, 0x6FF599E3, 0x9D9E1AE0,
+	0xD3D3E1AB, 0x21B862A8, 0x32E8915C, 0xC083125F,
+	0x144976B4, 0xE622F5B7, 0xF5720643, 0x07198540,
+	0x590AB964, 0xAB613A67, 0xB831C993, 0x4A5A4A90,
+	0x9E902E7B, 0x6CFBAD78, 0x7FAB5E8C, 0x8DC0DD8F,
+	0xE330A81A, 0x115B2B19, 0x020BD8ED, 0xF0605BEE,
+	0x24AA3F05, 0xD6C1BC06, 0xC5914FF2, 0x37FACCF1,
+	0x69E9F0D5, 0x9B8273D6, 0x88D28022, 0x7AB90321,
+	0xAE7367CA, 0x5C18E4C9, 0x4F48173D, 0xBD23943E,
+	0xF36E6F75, 0x0105EC76, 0x12551F82, 0xE03E9C81,
+	0x34F4F86A, 0xC69F7B69, 0xD5CF889D, 0x27A40B9E,
+	0x79B737BA, 0x8BDCB4B9, 0x988C474D, 0x6AE7C44E,
+	0xBE2DA0A5, 0x4C4623A6, 0x5F16D052, 0xAD7D5351,
+};
+     
+__u32 sctp_start_cksum(__u8 *buffer, __u16 length)
+{
+    	__u32 crc32 = ~(__u32) 0;
+	__u32 i;
+
+	/* Optimize this routine to be SCTP specific, knowing how
+	 * to skip the checksum field of the SCTP header.
+	 */
+
+	/* Calculate CRC up to the checksum. */
+	for (i = 0; i < (sizeof(struct sctphdr) - sizeof(__u32)); i++)
+      		CRC32C(crc32, buffer[i]);
+
+	/* Skip checksum field of the header. */
+	for (i = 0; i < sizeof(__u32); i++)
+		CRC32C(crc32, 0);
+
+	/* Calculate the rest of the CRC. */
+	for (i = sizeof(struct sctphdr); i < length ; i++)
+		CRC32C(crc32, buffer[i]);
+
+	return crc32;
+}
+
+__u32 sctp_update_cksum(__u8 *buffer, __u16 length, __u32 crc32)
+{
+	__u32 i;
+
+	for (i = 0; i < length ; i++)
+		CRC32C(crc32, buffer[i]);
+
+	return crc32;
+}
+
+__u32 sctp_update_copy_cksum(__u8 *to, __u8 *from, __u16 length, __u32 crc32)
+{
+	__u32 i;
+	__u32 *_to = (__u32 *)to;
+	__u32 *_from = (__u32 *)from;
+	
+	for (i = 0; i < (length/4); i++) {
+		_to[i] = _from[i];
+		CRC32C(crc32, from[i*4]);
+		CRC32C(crc32, from[i*4+1]);
+		CRC32C(crc32, from[i*4+2]);
+		CRC32C(crc32, from[i*4+3]);	
+	}
+
+	return crc32;
+}
+
+__u32 sctp_end_cksum(__u32 crc32)
+{
+	__u32 result;
+	__u8 byte0, byte1, byte2, byte3;
+
+	result = ~crc32;
+
+	/*  result  now holds the negated polynomial remainder;
+	 *  since the table and algorithm is "reflected" [williams95].
+	 *  That is,  result has the same value as if we mapped the message
+	 *  to a polyomial, computed the host-bit-order polynomial
+	 *  remainder, performed final negation, then did an end-for-end
+	 *  bit-reversal.
+	 *  Note that a 32-bit bit-reversal is identical to four inplace
+	 *  8-bit reversals followed by an end-for-end byteswap.
+	 *  In other words, the bytes of each bit are in the right order,
+	 *  but the bytes have been byteswapped.  So we now do an explicit
+	 *  byteswap.  On a little-endian machine, this byteswap and
+	 *  the final ntohl cancel out and could be elided.
+	 */
+	byte0 = result & 0xff;
+	byte1 = (result>>8) & 0xff;
+	byte2 = (result>>16) & 0xff;
+	byte3 = (result>>24) & 0xff;
+
+	crc32 = ((byte0 << 24) |
+		 (byte1 << 16) |
+		 (byte2 << 8)  |
+		 byte3);
+	return crc32;
+}

net/sctp/debug.c

@@ -0,0 +1,191 @@
+/* SCTP kernel reference Implementation
+ * (C) Copyright IBM Corp. 2001, 2004
+ * Copyright (c) 1999-2000 Cisco, Inc.
+ * Copyright (c) 1999-2001 Motorola, Inc.
+ * Copyright (c) 2001 Intel Corp.
+ * 
+ * This file is part of the SCTP kernel reference Implementation
+ * 
+ * This file is part of the implementation of the add-IP extension,
+ * based on <draft-ietf-tsvwg-addip-sctp-02.txt> June 29, 2001,
+ * for the SCTP kernel reference Implementation.
+ * 
+ * This file converts numerical ID value to alphabetical names for SCTP
+ * terms such as chunk type, parameter time, event type, etc.
+ * 
+ * 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 <lksctp-developers@lists.sourceforge.net>
+ * 
+ * Or submit a bug report through the following website:
+ *    http://www.sf.net/projects/lksctp
+ *
+ * Written or modified by: 
+ *    La Monte H.P. Yarroll <piggy@acm.org>
+ *    Karl Knutson          <karl@athena.chicago.il.us>
+ *    Xingang Guo           <xingang.guo@intel.com>
+ *    Jon Grimm             <jgrimm@us.ibm.com>
+ *    Daisy Chang	    <daisyc@us.ibm.com>
+ *    Sridhar Samudrala	    <sri@us.ibm.com>
+ * 
+ * Any bugs reported given to us we will try to fix... any fixes shared will
+ * be incorporated into the next SCTP release.
+ */
+
+#include <net/sctp/sctp.h>
+
+#if SCTP_DEBUG
+int sctp_debug_flag = 1;	/* Initially enable DEBUG */
+#endif	/* SCTP_DEBUG */
+
+/* These are printable forms of Chunk ID's from section 3.1.  */
+static const char *sctp_cid_tbl[SCTP_NUM_BASE_CHUNK_TYPES] = {
+	"DATA",
+	"INIT",
+	"INIT_ACK",
+	"SACK",
+	"HEARTBEAT",
+	"HEARTBEAT_ACK",
+	"ABORT",
+	"SHUTDOWN",
+	"SHUTDOWN_ACK",
+	"ERROR",
+	"COOKIE_ECHO",
+	"COOKIE_ACK",
+	"ECN_ECNE",
+	"ECN_CWR",
+	"SHUTDOWN_COMPLETE",
+};
+
+/* Lookup "chunk type" debug name. */
+const char *sctp_cname(const sctp_subtype_t cid)
+{
+	if (cid.chunk < 0)
+		return "illegal chunk id";
+	if (cid.chunk <= SCTP_CID_BASE_MAX)
+		return sctp_cid_tbl[cid.chunk];
+	
+	switch (cid.chunk) {
+	case SCTP_CID_ASCONF:
+		return "ASCONF";
+
+	case SCTP_CID_ASCONF_ACK:
+		return "ASCONF_ACK";
+
+	case SCTP_CID_FWD_TSN:
+		return "FWD_TSN";
+
+	default:
+		return "unknown chunk";
+	};
+	return "unknown chunk";
+}
+
+/* These are printable forms of the states.  */
+const char *sctp_state_tbl[SCTP_STATE_NUM_STATES] = {
+	"STATE_EMPTY",
+	"STATE_CLOSED",
+	"STATE_COOKIE_WAIT",
+	"STATE_COOKIE_ECHOED",
+	"STATE_ESTABLISHED",
+	"STATE_SHUTDOWN_PENDING",
+	"STATE_SHUTDOWN_SENT",
+	"STATE_SHUTDOWN_RECEIVED",
+	"STATE_SHUTDOWN_ACK_SENT",
+};
+
+/* Events that could change the state of an association.  */
+const char *sctp_evttype_tbl[] = {
+	"EVENT_T_unknown",
+	"EVENT_T_CHUNK",
+	"EVENT_T_TIMEOUT",
+	"EVENT_T_OTHER",
+	"EVENT_T_PRIMITIVE"
+};
+
+/* Return value of a state function */
+const char *sctp_status_tbl[] = {
+	"DISPOSITION_DISCARD",
+	"DISPOSITION_CONSUME",
+	"DISPOSITION_NOMEM",
+	"DISPOSITION_DELETE_TCB",
+	"DISPOSITION_ABORT",
+	"DISPOSITION_VIOLATION",
+	"DISPOSITION_NOT_IMPL",
+	"DISPOSITION_ERROR",
+	"DISPOSITION_BUG"
+};
+
+/* Printable forms of primitives */
+static const char *sctp_primitive_tbl[SCTP_NUM_PRIMITIVE_TYPES] = {
+	"PRIMITIVE_ASSOCIATE",
+	"PRIMITIVE_SHUTDOWN",
+	"PRIMITIVE_ABORT",
+	"PRIMITIVE_SEND",
+	"PRIMITIVE_REQUESTHEARTBEAT",
+};
+
+/* Lookup primitive debug name. */
+const char *sctp_pname(const sctp_subtype_t id)
+{
+	if (id.primitive < 0)
+		return "illegal primitive";
+	if (id.primitive <= SCTP_EVENT_PRIMITIVE_MAX)
+		return sctp_primitive_tbl[id.primitive];
+	return "unknown_primitive";
+}
+
+static const char *sctp_other_tbl[] = {
+	"NO_PENDING_TSN",
+        "ICMP_PROTO_UNREACH",
+};
+
+/* Lookup "other" debug name. */
+const char *sctp_oname(const sctp_subtype_t id)
+{
+	if (id.other < 0)
+		return "illegal 'other' event";
+	if (id.other <= SCTP_EVENT_OTHER_MAX)
+		return sctp_other_tbl[id.other];
+	return "unknown 'other' event";
+}
+
+static const char *sctp_timer_tbl[] = {
+	"TIMEOUT_NONE",
+	"TIMEOUT_T1_COOKIE",
+	"TIMEOUT_T1_INIT",
+	"TIMEOUT_T2_SHUTDOWN",
+	"TIMEOUT_T3_RTX",
+	"TIMEOUT_T4_RTO",
+	"TIMEOUT_T5_SHUTDOWN_GUARD",
+	"TIMEOUT_HEARTBEAT",
+	"TIMEOUT_SACK",
+	"TIMEOUT_AUTOCLOSE",
+};
+
+/* Lookup timer debug name. */
+const char *sctp_tname(const sctp_subtype_t id)
+{
+	if (id.timeout < 0)
+		return "illegal 'timer' event";
+	if (id.timeout <= SCTP_EVENT_TIMEOUT_MAX)
+		return sctp_timer_tbl[id.timeout];
+	return "unknown_timer";
+}

net/sctp/endpointola.c

@@ -0,0 +1,389 @@
+/* SCTP kernel reference Implementation
+ * Copyright (c) 1999-2000 Cisco, Inc.
+ * Copyright (c) 1999-2001 Motorola, Inc.
+ * Copyright (c) 2001-2002 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
+ *
+ * This abstraction represents an SCTP endpoint.
+ *
+ * This file is part of the implementation of the add-IP extension,
+ * based on <draft-ietf-tsvwg-addip-sctp-02.txt> June 29, 2001,
+ * for the SCTP kernel reference Implementation.
+ *
+ * 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 <lksctp-developers@lists.sourceforge.net>
+ *
+ * Or submit a bug report through the following website:
+ *    http://www.sf.net/projects/lksctp
+ *
+ * Written or modified by:
+ *    La Monte H.P. Yarroll <piggy@acm.org>
+ *    Karl Knutson <karl@athena.chicago.il.us>
+ *    Jon Grimm <jgrimm@austin.ibm.com>
+ *    Daisy Chang <daisyc@us.ibm.com>
+ *    Dajiang Zhang <dajiang.zhang@nokia.com>
+ *
+ * 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/sched.h>
+#include <linux/slab.h>
+#include <linux/in.h>
+#include <linux/random.h>	/* get_random_bytes() */
+#include <linux/crypto.h>
+#include <net/sock.h>
+#include <net/ipv6.h>
+#include <net/sctp/sctp.h>
+#include <net/sctp/sm.h>
+
+/* Forward declarations for internal helpers. */
+static void sctp_endpoint_bh_rcv(struct sctp_endpoint *ep);
+
+/*
+ * Initialize the base fields of the endpoint structure.
+ */
+static struct sctp_endpoint *sctp_endpoint_init(struct sctp_endpoint *ep,
+						struct sock *sk, int gfp)
+{
+	struct sctp_sock *sp = sctp_sk(sk);
+	memset(ep, 0, sizeof(struct sctp_endpoint));
+
+	/* Initialize the base structure. */
+	/* What type of endpoint are we?  */
+	ep->base.type = SCTP_EP_TYPE_SOCKET;
+
+	/* Initialize the basic object fields. */
+	atomic_set(&ep->base.refcnt, 1);
+	ep->base.dead = 0;
+	ep->base.malloced = 1;
+
+	/* Create an input queue.  */
+	sctp_inq_init(&ep->base.inqueue);
+
+	/* Set its top-half handler */
+	sctp_inq_set_th_handler(&ep->base.inqueue,
+				(void (*)(void *))sctp_endpoint_bh_rcv, ep);
+
+	/* Initialize the bind addr area */
+	sctp_bind_addr_init(&ep->base.bind_addr, 0);
+	rwlock_init(&ep->base.addr_lock);
+
+	/* Remember who we are attached to.  */
+	ep->base.sk = sk;
+	sock_hold(ep->base.sk);
+
+	/* Create the lists of associations.  */
+	INIT_LIST_HEAD(&ep->asocs);
+
+	/* Set up the base timeout information.  */
+	ep->timeouts[SCTP_EVENT_TIMEOUT_NONE] = 0;
+	ep->timeouts[SCTP_EVENT_TIMEOUT_T1_COOKIE] =
+		SCTP_DEFAULT_TIMEOUT_T1_COOKIE;
+	ep->timeouts[SCTP_EVENT_TIMEOUT_T1_INIT] =
+		SCTP_DEFAULT_TIMEOUT_T1_INIT;
+	ep->timeouts[SCTP_EVENT_TIMEOUT_T2_SHUTDOWN] =
+		msecs_to_jiffies(sp->rtoinfo.srto_initial);
+	ep->timeouts[SCTP_EVENT_TIMEOUT_T3_RTX] = 0;
+	ep->timeouts[SCTP_EVENT_TIMEOUT_T4_RTO] = 0;
+
+	/* sctpimpguide-05 Section 2.12.2
+	 * If the 'T5-shutdown-guard' timer is used, it SHOULD be set to the
+	 * recommended value of 5 times 'RTO.Max'.
+	 */
+        ep->timeouts[SCTP_EVENT_TIMEOUT_T5_SHUTDOWN_GUARD]
+		= 5 * msecs_to_jiffies(sp->rtoinfo.srto_max);
+
+	ep->timeouts[SCTP_EVENT_TIMEOUT_HEARTBEAT] =
+		SCTP_DEFAULT_TIMEOUT_HEARTBEAT;
+	ep->timeouts[SCTP_EVENT_TIMEOUT_SACK] =
+		SCTP_DEFAULT_TIMEOUT_SACK;
+	ep->timeouts[SCTP_EVENT_TIMEOUT_AUTOCLOSE] =
+		sp->autoclose * HZ;
+
+	/* Use SCTP specific send buffer space queues.  */
+	sk->sk_write_space = sctp_write_space;
+	sock_set_flag(sk, SOCK_USE_WRITE_QUEUE);
+
+	/* Initialize the secret key used with cookie. */
+	get_random_bytes(&ep->secret_key[0], SCTP_SECRET_SIZE);
+	ep->last_key = ep->current_key = 0;
+	ep->key_changed_at = jiffies;
+
+	ep->debug_name = "unnamedEndpoint";
+	return ep;
+}
+
+/* Create a sctp_endpoint with all that boring stuff initialized.
+ * Returns NULL if there isn't enough memory.
+ */
+struct sctp_endpoint *sctp_endpoint_new(struct sock *sk, int gfp)
+{
+	struct sctp_endpoint *ep;
+
+	/* Build a local endpoint. */
+	ep = t_new(struct sctp_endpoint, gfp);
+	if (!ep)
+		goto fail;
+	if (!sctp_endpoint_init(ep, sk, gfp))
+		goto fail_init;
+	ep->base.malloced = 1;
+	SCTP_DBG_OBJCNT_INC(ep);
+	return ep;
+
+fail_init:
+	kfree(ep);
+fail:
+	return NULL;
+}
+
+/* Add an association to an endpoint.  */
+void sctp_endpoint_add_asoc(struct sctp_endpoint *ep,
+			    struct sctp_association *asoc)
+{
+	struct sock *sk = ep->base.sk;
+
+	/* Now just add it to our list of asocs */
+	list_add_tail(&asoc->asocs, &ep->asocs);
+
+	/* Increment the backlog value for a TCP-style listening socket. */
+	if (sctp_style(sk, TCP) && sctp_sstate(sk, LISTENING))
+		sk->sk_ack_backlog++;
+}
+
+/* Free the endpoint structure.  Delay cleanup until
+ * all users have released their reference count on this structure.
+ */
+void sctp_endpoint_free(struct sctp_endpoint *ep)
+{
+	ep->base.dead = 1;
+	sctp_endpoint_put(ep);
+}
+
+/* Final destructor for endpoint.  */
+static void sctp_endpoint_destroy(struct sctp_endpoint *ep)
+{
+	SCTP_ASSERT(ep->base.dead, "Endpoint is not dead", return);
+
+	ep->base.sk->sk_state = SCTP_SS_CLOSED;
+
+	/* Unlink this endpoint, so we can't find it again! */
+	sctp_unhash_endpoint(ep);
+
+	/* Free up the HMAC transform. */
+	if (sctp_sk(ep->base.sk)->hmac)
+		sctp_crypto_free_tfm(sctp_sk(ep->base.sk)->hmac);
+
+	/* Cleanup. */
+	sctp_inq_free(&ep->base.inqueue);
+	sctp_bind_addr_free(&ep->base.bind_addr);
+
+	/* Remove and free the port */
+	if (sctp_sk(ep->base.sk)->bind_hash)
+		sctp_put_port(ep->base.sk);
+
+	/* Give up our hold on the sock. */
+	if (ep->base.sk)
+		sock_put(ep->base.sk);
+
+	/* Finally, free up our memory. */
+	if (ep->base.malloced) {
+		kfree(ep);
+		SCTP_DBG_OBJCNT_DEC(ep);
+	}
+}
+
+/* Hold a reference to an endpoint. */
+void sctp_endpoint_hold(struct sctp_endpoint *ep)
+{
+	atomic_inc(&ep->base.refcnt);
+}
+
+/* Release a reference to an endpoint and clean up if there are
+ * no more references.
+ */
+void sctp_endpoint_put(struct sctp_endpoint *ep)
+{
+	if (atomic_dec_and_test(&ep->base.refcnt))
+		sctp_endpoint_destroy(ep);
+}
+
+/* Is this the endpoint we are looking for?  */
+struct sctp_endpoint *sctp_endpoint_is_match(struct sctp_endpoint *ep,
+					       const union sctp_addr *laddr)
+{
+	struct sctp_endpoint *retval;
+
+	sctp_read_lock(&ep->base.addr_lock);
+	if (ep->base.bind_addr.port == laddr->v4.sin_port) {
+		if (sctp_bind_addr_match(&ep->base.bind_addr, laddr,
+					 sctp_sk(ep->base.sk))) {
+			retval = ep;
+			goto out;
+		}
+	}
+
+	retval = NULL;
+
+out:
+	sctp_read_unlock(&ep->base.addr_lock);
+	return retval;
+}
+
+/* Find the association that goes with this chunk.
+ * We do a linear search of the associations for this endpoint.
+ * We return the matching transport address too.
+ */
+static struct sctp_association *__sctp_endpoint_lookup_assoc(
+	const struct sctp_endpoint *ep,
+	const union sctp_addr *paddr,
+	struct sctp_transport **transport)
+{
+	int rport;
+	struct sctp_association *asoc;
+	struct list_head *pos;
+
+	rport = paddr->v4.sin_port;
+
+	list_for_each(pos, &ep->asocs) {
+		asoc = list_entry(pos, struct sctp_association, asocs);
+		if (rport == asoc->peer.port) {
+			sctp_read_lock(&asoc->base.addr_lock);
+			*transport = sctp_assoc_lookup_paddr(asoc, paddr);
+			sctp_read_unlock(&asoc->base.addr_lock);
+
+			if (*transport)
+				return asoc;
+		}
+	}
+
+	*transport = NULL;
+	return NULL;
+}
+
+/* Lookup association on an endpoint based on a peer address.  BH-safe.  */
+struct sctp_association *sctp_endpoint_lookup_assoc(
+	const struct sctp_endpoint *ep,
+	const union sctp_addr *paddr,
+	struct sctp_transport **transport)
+{
+	struct sctp_association *asoc;
+
+	sctp_local_bh_disable();
+	asoc = __sctp_endpoint_lookup_assoc(ep, paddr, transport);
+	sctp_local_bh_enable();
+
+	return asoc;
+}
+
+/* Look for any peeled off association from the endpoint that matches the
+ * given peer address.
+ */
+int sctp_endpoint_is_peeled_off(struct sctp_endpoint *ep,
+				const union sctp_addr *paddr)
+{
+	struct list_head *pos;
+	struct sctp_sockaddr_entry *addr;
+	struct sctp_bind_addr *bp;
+
+	sctp_read_lock(&ep->base.addr_lock);
+	bp = &ep->base.bind_addr;
+	list_for_each(pos, &bp->address_list) {
+		addr = list_entry(pos, struct sctp_sockaddr_entry, list);
+		if (sctp_has_association(&addr->a, paddr)) {
+			sctp_read_unlock(&ep->base.addr_lock);
+			return 1;
+		}
+	}
+	sctp_read_unlock(&ep->base.addr_lock);
+
+	return 0;
+}
+
+/* Do delayed input processing.  This is scheduled by sctp_rcv().
+ * This may be called on BH or task time.
+ */
+static void sctp_endpoint_bh_rcv(struct sctp_endpoint *ep)
+{
+	struct sctp_association *asoc;
+	struct sock *sk;
+	struct sctp_transport *transport;
+	struct sctp_chunk *chunk;
+	struct sctp_inq *inqueue;
+	sctp_subtype_t subtype;
+	sctp_state_t state;
+	int error = 0;
+
+	if (ep->base.dead)
+		return;
+
+	asoc = NULL;
+	inqueue = &ep->base.inqueue;
+	sk = ep->base.sk;
+
+	while (NULL != (chunk = sctp_inq_pop(inqueue))) {
+		subtype = SCTP_ST_CHUNK(chunk->chunk_hdr->type);
+
+		/* We might have grown an association since last we
+		 * looked, so try again.
+		 *
+		 * This happens when we've just processed our
+		 * COOKIE-ECHO chunk.
+		 */
+		if (NULL == chunk->asoc) {
+			asoc = sctp_endpoint_lookup_assoc(ep,
+							  sctp_source(chunk),
+							  &transport);
+			chunk->asoc = asoc;
+			chunk->transport = transport;
+		}
+
+		state = asoc ? asoc->state : SCTP_STATE_CLOSED;
+
+		/* Remember where the last DATA chunk came from so we
+		 * know where to send the SACK.
+		 */
+		if (asoc && sctp_chunk_is_data(chunk))
+			asoc->peer.last_data_from = chunk->transport;
+		else
+			SCTP_INC_STATS(SCTP_MIB_INCTRLCHUNKS);
+
+		if (chunk->transport)
+			chunk->transport->last_time_heard = jiffies;
+
+		error = sctp_do_sm(SCTP_EVENT_T_CHUNK, subtype, state,
+                                   ep, asoc, chunk, GFP_ATOMIC);
+
+		if (error && chunk)
+			chunk->pdiscard = 1;
+
+		/* Check to see if the endpoint is freed in response to
+		 * the incoming chunk. If so, get out of the while loop.
+		 */
+		if (!sctp_sk(sk)->ep)
+			break;
+	}
+}

net/sctp/input.c

@@ -0,0 +1,913 @@
+/* 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 <lksctp-developers@lists.sourceforge.net>
+ *
+ * Or submit a bug report through the following website:
+ *    http://www.sf.net/projects/lksctp
+ *
+ * Written or modified by:
+ *    La Monte H.P. Yarroll <piggy@acm.org>
+ *    Karl Knutson <karl@athena.chicago.il.us>
+ *    Xingang Guo <xingang.guo@intel.com>
+ *    Jon Grimm <jgrimm@us.ibm.com>
+ *    Hui Huang <hui.huang@nokia.com>
+ *    Daisy Chang <daisyc@us.ibm.com>
+ *    Sridhar Samudrala <sri@us.ibm.com>
+ *    Ardelle Fan <ardelle.fan@intel.com>
+ *
+ * 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);
+
+	/*
+	 * 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) {
+		ep = __sctp_rcv_lookup_endpoint(&dest);
+		if (sctp_rcv_ootb(skb)) {
+			SCTP_INC_STATS_BH(SCTP_MIB_OUTOFBLUES);
+			goto discard_release;
+		}
+	}
+
+	/* Retrieve the common input handling substructure. */
+	rcvr = asoc ? &asoc->base : &ep->base;
+	sk = rcvr->sk;
+
+	if ((sk) && (atomic_read(&sk->sk_rmem_alloc) >= sk->sk_rcvbuf)) {
+		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. */
+	if (asoc) {
+		sock_put(asoc->base.sk);
+		sctp_association_put(asoc);
+	} else {
+		sock_put(ep->base.sk);
+		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;
+	struct sctp_endpoint *ep;
+	struct sctp_association *asoc;
+	struct sctp_transport *transport;
+	struct inet_sock *inet;
+	char *saveip, *savesctp;
+	int err;
+
+	if (skb->len < ((iph->ihl << 2) + 8)) {
+		ICMP_INC_STATS_BH(ICMP_MIB_INERRORS);
+		return;
+	}
+
+	/* Fix up skb to look at the embedded net header. */
+	saveip = skb->nh.raw;
+	savesctp  = skb->h.raw;
+	skb->nh.iph = iph;
+	skb->h.raw = (char *)sh;
+	sk = sctp_err_lookup(AF_INET, skb, sh, &ep, &asoc, &transport);
+	/* Put back, the original pointers. */
+	skb->nh.raw = saveip;
+	skb->h.raw = 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;
+		}
+		else {
+			if (ICMP_PROT_UNREACH == code) {
+				sctp_icmp_proto_unreachable(sk, ep, asoc,
+							    transport);
+				goto out_unlock;
+			}
+		}
+		err = icmp_err_convert[code].errno;
+		break;
+	case ICMP_TIME_EXCEEDED:
+		/* Ignore any time exceeded errors due to fragment reassembly
+		 * timeouts.
+		 */
+		if (ICMP_EXC_FRAGTIME == code)
+			goto out_unlock;
+
+		err = EHOSTUNREACH;
+		break;
+	default:
+		goto out_unlock;
+	}
+
+	inet = inet_sk(sk);
+	if (!sock_owned_by_user(sk) && inet->recverr) {
+		sk->sk_err = err;
+		sk->sk_error_report(sk);
+	} else {  /* Only an error on timeout */
+		sk->sk_err_soft = err;
+	}
+
+out_unlock:
+	sctp_err_finish(sk, ep, asoc);
+}
+
+/*
+ * RFC 2960, 8.4 - Handle "Out of the blue" Packets.
+ *
+ * This function scans all the chunks in the OOTB packet to determine if
+ * the packet should be discarded right away.  If a response might be needed
+ * for this packet, or, if further processing is possible, the packet will
+ * be queued to a proper inqueue for the next phase of handling.
+ *
+ * Output:
+ * Return 0 - If further processing is needed.
+ * Return 1 - If the packet can be discarded right away.
+ */
+int sctp_rcv_ootb(struct sk_buff *skb)
+{
+	sctp_chunkhdr_t *ch;
+	__u8 *ch_end;
+	sctp_errhdr_t *err;
+
+	ch = (sctp_chunkhdr_t *) skb->data;
+	ch_end = ((__u8 *) ch) + WORD_ROUND(ntohs(ch->length));
+
+	/* Scan through all the chunks in the packet.  */
+	while (ch_end > (__u8 *)ch && ch_end < skb->tail) {
+
+		/* RFC 8.4, 2) If the OOTB packet contains an ABORT chunk, the
+		 * receiver MUST silently discard the OOTB packet and take no
+		 * further action.
+		 */
+		if (SCTP_CID_ABORT == ch->type)
+			goto discard;
+
+		/* RFC 8.4, 6) If the packet contains a SHUTDOWN COMPLETE
+		 * chunk, the receiver should silently discard the packet
+		 * and take no further action.
+		 */
+		if (SCTP_CID_SHUTDOWN_COMPLETE == ch->type)
+			goto discard;
+
+		/* RFC 8.4, 7) If the packet contains a "Stale cookie" ERROR
+		 * or a COOKIE ACK the SCTP Packet should be silently
+		 * discarded.
+		 */
+		if (SCTP_CID_COOKIE_ACK == ch->type)
+			goto discard;
+
+		if (SCTP_CID_ERROR == ch->type) {
+			sctp_walk_errors(err, ch) {
+				if (SCTP_ERROR_STALE_COOKIE == err->cause)
+					goto discard;
+			}
+		}
+
+		ch = (sctp_chunkhdr_t *) ch_end;
+	        ch_end = ((__u8 *) ch) + WORD_ROUND(ntohs(ch->length));
+	}
+
+	return 0;
+
+discard:
+	return 1;
+}
+
+/* Insert endpoint into the hash table.  */
+static void __sctp_hash_endpoint(struct sctp_endpoint *ep)
+{
+	struct sctp_ep_common **epp;
+	struct sctp_ep_common *epb;
+	struct sctp_hashbucket *head;
+
+	epb = &ep->base;
+
+	epb->hashent = sctp_ep_hashfn(epb->bind_addr.port);
+	head = &sctp_ep_hashtable[epb->hashent];
+
+	sctp_write_lock(&head->lock);
+	epp = &head->chain;
+	epb->next = *epp;
+	if (epb->next)
+		(*epp)->pprev = &epb->next;
+	*epp = epb;
+	epb->pprev = epp;
+	sctp_write_unlock(&head->lock);
+}
+
+/* Add an endpoint to the hash. Local BH-safe. */
+void sctp_hash_endpoint(struct sctp_endpoint *ep)
+{
+	sctp_local_bh_disable();
+	__sctp_hash_endpoint(ep);
+	sctp_local_bh_enable();
+}
+
+/* Remove endpoint from the hash table.  */
+static void __sctp_unhash_endpoint(struct sctp_endpoint *ep)
+{
+	struct sctp_hashbucket *head;
+	struct sctp_ep_common *epb;
+
+	epb = &ep->base;
+
+	epb->hashent = sctp_ep_hashfn(epb->bind_addr.port);
+
+	head = &sctp_ep_hashtable[epb->hashent];
+
+	sctp_write_lock(&head->lock);
+
+	if (epb->pprev) {
+		if (epb->next)
+			epb->next->pprev = epb->pprev;
+		*epb->pprev = epb->next;
+		epb->pprev = NULL;
+	}
+
+	sctp_write_unlock(&head->lock);
+}
+
+/* Remove endpoint from the hash.  Local BH-safe. */
+void sctp_unhash_endpoint(struct sctp_endpoint *ep)
+{
+	sctp_local_bh_disable();
+	__sctp_unhash_endpoint(ep);
+	sctp_local_bh_enable();
+}
+
+/* Look up an endpoint. */
+static struct sctp_endpoint *__sctp_rcv_lookup_endpoint(const union sctp_addr *laddr)
+{
+	struct sctp_hashbucket *head;
+	struct sctp_ep_common *epb;
+	struct sctp_endpoint *ep;
+	int hash;
+
+	hash = sctp_ep_hashfn(laddr->v4.sin_port);
+	head = &sctp_ep_hashtable[hash];
+	read_lock(&head->lock);
+	for (epb = head->chain; epb; epb = epb->next) {
+		ep = sctp_ep(epb);
+		if (sctp_endpoint_is_match(ep, laddr))
+			goto hit;
+	}
+
+	ep = sctp_sk((sctp_get_ctl_sock()))->ep;
+	epb = &ep->base;
+
+hit:
+	sctp_endpoint_hold(ep);
+	sock_hold(epb->sk);
+	read_unlock(&head->lock);
+	return ep;
+}
+
+/* Insert association into the hash table.  */
+static void __sctp_hash_established(struct sctp_association *asoc)
+{
+	struct sctp_ep_common **epp;
+	struct sctp_ep_common *epb;
+	struct sctp_hashbucket *head;
+
+	epb = &asoc->base;
+
+	/* Calculate which chain this entry will belong to. */
+	epb->hashent = sctp_assoc_hashfn(epb->bind_addr.port, asoc->peer.port);
+
+	head = &sctp_assoc_hashtable[epb->hashent];
+
+	sctp_write_lock(&head->lock);
+	epp = &head->chain;
+	epb->next = *epp;
+	if (epb->next)
+		(*epp)->pprev = &epb->next;
+	*epp = epb;
+	epb->pprev = epp;
+	sctp_write_unlock(&head->lock);
+}
+
+/* Add an association to the hash. Local BH-safe. */
+void sctp_hash_established(struct sctp_association *asoc)
+{
+	sctp_local_bh_disable();
+	__sctp_hash_established(asoc);
+	sctp_local_bh_enable();
+}
+
+/* Remove association from the hash table.  */
+static void __sctp_unhash_established(struct sctp_association *asoc)
+{
+	struct sctp_hashbucket *head;
+	struct sctp_ep_common *epb;
+
+	epb = &asoc->base;
+
+	epb->hashent = sctp_assoc_hashfn(epb->bind_addr.port,
+					 asoc->peer.port);
+
+	head = &sctp_assoc_hashtable[epb->hashent];
+
+	sctp_write_lock(&head->lock);
+
+	if (epb->pprev) {
+		if (epb->next)
+			epb->next->pprev = epb->pprev;
+		*epb->pprev = epb->next;
+		epb->pprev = NULL;
+	}
+
+	sctp_write_unlock(&head->lock);
+}
+
+/* Remove association from the hash table.  Local BH-safe. */
+void sctp_unhash_established(struct sctp_association *asoc)
+{
+	sctp_local_bh_disable();
+	__sctp_unhash_established(asoc);
+	sctp_local_bh_enable();
+}
+
+/* Look up an association. */
+static struct sctp_association *__sctp_lookup_association(
+					const union sctp_addr *local,
+					const union sctp_addr *peer,
+					struct sctp_transport **pt)
+{
+	struct sctp_hashbucket *head;
+	struct sctp_ep_common *epb;
+	struct sctp_association *asoc;
+	struct sctp_transport *transport;
+	int hash;
+
+	/* Optimize here for direct hit, only listening connections can
+	 * have wildcards anyways.
+	 */
+	hash = sctp_assoc_hashfn(local->v4.sin_port, peer->v4.sin_port);
+	head = &sctp_assoc_hashtable[hash];
+	read_lock(&head->lock);
+	for (epb = head->chain; epb; epb = epb->next) {
+		asoc = sctp_assoc(epb);
+		transport = sctp_assoc_is_match(asoc, local, peer);
+		if (transport)
+			goto hit;
+	}
+
+	read_unlock(&head->lock);
+
+	return NULL;
+
+hit:
+	*pt = transport;
+	sctp_association_hold(asoc);
+	sock_hold(epb->sk);
+	read_unlock(&head->lock);
+	return asoc;
+}
+
+/* Look up an association. BH-safe. */
+SCTP_STATIC
+struct sctp_association *sctp_lookup_association(const union sctp_addr *laddr,
+						 const union sctp_addr *paddr,
+					    struct sctp_transport **transportp)
+{
+	struct sctp_association *asoc;
+
+	sctp_local_bh_disable();
+	asoc = __sctp_lookup_association(laddr, paddr, transportp);
+	sctp_local_bh_enable();
+
+	return asoc;
+}
+
+/* Is there an association matching the given local and peer addresses? */
+int sctp_has_association(const union sctp_addr *laddr,
+			 const union sctp_addr *paddr)
+{
+	struct sctp_association *asoc;
+	struct sctp_transport *transport;
+
+	if ((asoc = sctp_lookup_association(laddr, paddr, &transport))) {
+		sock_put(asoc->base.sk);
+		sctp_association_put(asoc);
+		return 1;
+	}
+
+	return 0;
+}
+
+/*
+ * SCTP Implementors Guide, 2.18 Handling of address
+ * parameters within the INIT or INIT-ACK.
+ *
+ * D) When searching for a matching TCB upon reception of an INIT
+ *    or INIT-ACK chunk the receiver SHOULD use not only the
+ *    source address of the packet (containing the INIT or
+ *    INIT-ACK) but the receiver SHOULD also use all valid
+ *    address parameters contained within the chunk.
+ *
+ * 2.18.3 Solution description
+ *
+ * This new text clearly specifies to an implementor the need
+ * to look within the INIT or INIT-ACK. Any implementation that
+ * does not do this, may not be able to establish associations
+ * in certain circumstances.
+ *
+ */
+static struct sctp_association *__sctp_rcv_init_lookup(struct sk_buff *skb,
+	const union sctp_addr *laddr, struct sctp_transport **transportp)
+{
+	struct sctp_association *asoc;
+	union sctp_addr addr;
+	union sctp_addr *paddr = &addr;
+	struct sctphdr *sh = (struct sctphdr *) skb->h.raw;
+	sctp_chunkhdr_t *ch;
+	union sctp_params params;
+	sctp_init_chunk_t *init;
+	struct sctp_transport *transport;
+	struct sctp_af *af;
+
+	ch = (sctp_chunkhdr_t *) skb->data;
+
+	/* If this is INIT/INIT-ACK look inside the chunk too. */
+	switch (ch->type) {
+	case SCTP_CID_INIT:
+	case SCTP_CID_INIT_ACK:
+		break;
+	default:
+		return NULL;
+	}
+
+	/* The code below will attempt to walk the chunk and extract
+	 * parameter information.  Before we do that, we need to verify
+	 * that the chunk length doesn't cause overflow.  Otherwise, we'll
+	 * walk off the end.
+	 */
+	if (WORD_ROUND(ntohs(ch->length)) > skb->len)
+		return NULL;
+
+	/*
+	 * This code will NOT touch anything inside the chunk--it is
+	 * strictly READ-ONLY.
+	 *
+	 * RFC 2960 3  SCTP packet Format
+	 *
+	 * Multiple chunks can be bundled into one SCTP packet up to
+	 * the MTU size, except for the INIT, INIT ACK, and SHUTDOWN
+	 * COMPLETE chunks.  These chunks MUST NOT be bundled with any
+	 * other chunk in a packet.  See Section 6.10 for more details
+	 * on chunk bundling.
+	 */
+
+	/* Find the start of the TLVs and the end of the chunk.  This is
+	 * the region we search for address parameters.
+	 */
+	init = (sctp_init_chunk_t *)skb->data;
+
+	/* Walk the parameters looking for embedded addresses. */
+	sctp_walk_params(params, init, init_hdr.params) {
+
+		/* Note: Ignoring hostname addresses. */
+		af = sctp_get_af_specific(param_type2af(params.p->type));
+		if (!af)
+			continue;
+
+		af->from_addr_param(paddr, params.addr, ntohs(sh->source), 0);
+
+		asoc = __sctp_lookup_association(laddr, paddr, &transport);
+		if (asoc)
+			return asoc;
+	}
+
+	return NULL;
+}
+
+/* Lookup an association for an inbound skb. */
+static struct sctp_association *__sctp_rcv_lookup(struct sk_buff *skb,
+				      const union sctp_addr *paddr,
+				      const union sctp_addr *laddr,
+				      struct sctp_transport **transportp)
+{
+	struct sctp_association *asoc;
+
+	asoc = __sctp_lookup_association(laddr, paddr, transportp);
+
+	/* Further lookup for INIT/INIT-ACK packets.
+	 * SCTP Implementors Guide, 2.18 Handling of address
+	 * parameters within the INIT or INIT-ACK.
+	 */
+	if (!asoc)
+		asoc = __sctp_rcv_init_lookup(skb, laddr, transportp);
+
+	return asoc;
+}

net/sctp/inqueue.c

@@ -0,0 +1,204 @@
+/* SCTP kernel reference Implementation
+ * Copyright (c) 1999-2000 Cisco, Inc.
+ * Copyright (c) 1999-2001 Motorola, Inc.
+ * Copyright (c) 2002 International Business Machines, Corp.
+ * 
+ * This file is part of the SCTP kernel reference Implementation
+ * 
+ * These functions are the methods for accessing the SCTP inqueue.
+ *
+ * An SCTP inqueue is a queue into which you push SCTP packets
+ * (which might be bundles or fragments of chunks) and out of which you
+ * pop SCTP whole chunks.
+ * 
+ * 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 <lksctp-developers@lists.sourceforge.net>
+ * 
+ * Or submit a bug report through the following website:
+ *    http://www.sf.net/projects/lksctp
+ *
+ * Written or modified by: 
+ *    La Monte H.P. Yarroll <piggy@acm.org>
+ *    Karl Knutson <karl@athena.chicago.il.us>
+ * 
+ * Any bugs reported given to us we will try to fix... any fixes shared will
+ * be incorporated into the next SCTP release.
+ */
+
+#include <net/sctp/sctp.h>
+#include <net/sctp/sm.h>
+#include <linux/interrupt.h>
+
+/* Initialize an SCTP inqueue.  */
+void sctp_inq_init(struct sctp_inq *queue)
+{
+	skb_queue_head_init(&queue->in);
+	queue->in_progress = NULL;
+
+	/* Create a task for delivering data.  */
+	INIT_WORK(&queue->immediate, NULL, NULL);
+
+	queue->malloced = 0;
+}
+
+/* Release the memory associated with an SCTP inqueue.  */
+void sctp_inq_free(struct sctp_inq *queue)
+{
+	struct sctp_chunk *chunk;
+
+	/* Empty the queue.  */
+	while ((chunk = (struct sctp_chunk *) skb_dequeue(&queue->in)) != NULL)
+		sctp_chunk_free(chunk);
+
+	/* If there is a packet which is currently being worked on,
+	 * free it as well.
+	 */
+	if (queue->in_progress)
+		sctp_chunk_free(queue->in_progress);
+
+	if (queue->malloced) {
+		/* Dump the master memory segment.  */
+		kfree(queue);
+	}
+}
+
+/* Put a new packet in an SCTP inqueue.
+ * We assume that packet->sctp_hdr is set and in host byte order.
+ */
+void sctp_inq_push(struct sctp_inq *q, struct sctp_chunk *packet)
+{
+	/* Directly call the packet handling routine. */
+
+	/* We are now calling this either from the soft interrupt
+	 * or from the backlog processing.
+	 * Eventually, we should clean up inqueue to not rely
+	 * on the BH related data structures.
+	 */
+	skb_queue_tail(&(q->in), (struct sk_buff *) packet);
+	q->immediate.func(q->immediate.data);
+}
+
+/* Extract a chunk from an SCTP inqueue.
+ *
+ * WARNING:  If you need to put the chunk on another queue, you need to
+ * make a shallow copy (clone) of it.
+ */
+struct sctp_chunk *sctp_inq_pop(struct sctp_inq *queue)
+{
+	struct sctp_chunk *chunk;
+	sctp_chunkhdr_t *ch = NULL;
+
+	/* The assumption is that we are safe to process the chunks
+	 * at this time.
+	 */
+
+	if ((chunk = queue->in_progress)) {
+		/* There is a packet that we have been working on.
+		 * Any post processing work to do before we move on?
+		 */
+		if (chunk->singleton ||
+		    chunk->end_of_packet ||
+		    chunk->pdiscard) {
+			sctp_chunk_free(chunk);
+			chunk = queue->in_progress = NULL;
+		} else {
+			/* Nothing to do. Next chunk in the packet, please. */
+			ch = (sctp_chunkhdr_t *) chunk->chunk_end;
+
+			/* Force chunk->skb->data to chunk->chunk_end.  */
+			skb_pull(chunk->skb,
+				 chunk->chunk_end - chunk->skb->data);
+		}
+	}
+
+	/* Do we need to take the next packet out of the queue to process? */
+	if (!chunk) {
+		/* Is the queue empty?  */
+        	if (skb_queue_empty(&queue->in))
+			return NULL;
+
+		chunk = queue->in_progress =
+			(struct sctp_chunk *) skb_dequeue(&queue->in);
+
+		/* This is the first chunk in the packet.  */
+		chunk->singleton = 1;
+		ch = (sctp_chunkhdr_t *) chunk->skb->data;
+	}
+
+        chunk->chunk_hdr = ch;
+        chunk->chunk_end = ((__u8 *)ch) + WORD_ROUND(ntohs(ch->length));
+	/* In the unlikely case of an IP reassembly, the skb could be
+	 * non-linear. If so, update chunk_end so that it doesn't go past
+	 * the skb->tail.
+	 */
+	if (unlikely(skb_is_nonlinear(chunk->skb))) {
+		if (chunk->chunk_end > chunk->skb->tail)
+			chunk->chunk_end = chunk->skb->tail;
+	}
+	skb_pull(chunk->skb, sizeof(sctp_chunkhdr_t));
+	chunk->subh.v = NULL; /* Subheader is no longer valid.  */
+
+	if (chunk->chunk_end < chunk->skb->tail) {
+		/* This is not a singleton */
+		chunk->singleton = 0;
+	} else if (chunk->chunk_end > chunk->skb->tail) {
+                /* RFC 2960, Section 6.10  Bundling
+		 *
+		 * Partial chunks MUST NOT be placed in an SCTP packet.
+		 * If the receiver detects a partial chunk, it MUST drop
+		 * the chunk.  
+		 *
+		 * Since the end of the chunk is past the end of our buffer
+		 * (which contains the whole packet, we can freely discard
+		 * the whole packet.
+		 */
+		sctp_chunk_free(chunk);
+		chunk = queue->in_progress = NULL;
+
+		return NULL;
+	} else {
+		/* We are at the end of the packet, so mark the chunk
+		 * in case we need to send a SACK.
+		 */
+		chunk->end_of_packet = 1;
+	}
+
+	SCTP_DEBUG_PRINTK("+++sctp_inq_pop+++ chunk %p[%s],"
+			  " length %d, skb->len %d\n",chunk,
+			  sctp_cname(SCTP_ST_CHUNK(chunk->chunk_hdr->type)),
+			  ntohs(chunk->chunk_hdr->length), chunk->skb->len);
+	return chunk;
+}
+
+/* Set a top-half handler.
+ *
+ * Originally, we the top-half handler was scheduled as a BH.  We now
+ * call the handler directly in sctp_inq_push() at a time that
+ * we know we are lock safe.
+ * The intent is that this routine will pull stuff out of the
+ * inqueue and process it.
+ */
+void sctp_inq_set_th_handler(struct sctp_inq *q,
+				 void (*callback)(void *), void *arg)
+{
+	INIT_WORK(&q->immediate, callback, arg);
+}
+

net/sctp/objcnt.c

@@ -0,0 +1,140 @@
+/* SCTP kernel reference Implementation
+ * (C) Copyright IBM Corp. 2001, 2004
+ * 
+ * This file is part of the SCTP kernel reference Implementation
+ * 
+ * Support for memory object debugging.  This allows one to monitor the
+ * object allocations/deallocations for types instrumented for this 
+ * via the proc fs. 
+ * 
+ * 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 <lksctp-developers@lists.sourceforge.net>
+ * 
+ * Or submit a bug report through the following website:
+ *    http://www.sf.net/projects/lksctp
+ *
+ * Written or modified by: 
+ *    Jon Grimm             <jgrimm@us.ibm.com>
+ * 
+ * Any bugs reported given to us we will try to fix... any fixes shared will
+ * be incorporated into the next SCTP release.
+ */
+
+#include <linux/kernel.h>
+#include <net/sctp/sctp.h>
+
+/*
+ * Global counters to count raw object allocation counts.
+ * To add new counters, choose a unique suffix for the variable
+ * name as the helper macros key off this suffix to make
+ * life easier for the programmer.
+ */
+
+SCTP_DBG_OBJCNT(sock);
+SCTP_DBG_OBJCNT(ep);
+SCTP_DBG_OBJCNT(transport);
+SCTP_DBG_OBJCNT(assoc);
+SCTP_DBG_OBJCNT(bind_addr);
+SCTP_DBG_OBJCNT(bind_bucket);
+SCTP_DBG_OBJCNT(chunk);
+SCTP_DBG_OBJCNT(addr);
+SCTP_DBG_OBJCNT(ssnmap);
+SCTP_DBG_OBJCNT(datamsg);
+
+/* An array to make it easy to pretty print the debug information
+ * to the proc fs.
+ */
+static sctp_dbg_objcnt_entry_t sctp_dbg_objcnt[] = {
+	SCTP_DBG_OBJCNT_ENTRY(sock),
+	SCTP_DBG_OBJCNT_ENTRY(ep),
+	SCTP_DBG_OBJCNT_ENTRY(assoc),
+	SCTP_DBG_OBJCNT_ENTRY(transport),
+	SCTP_DBG_OBJCNT_ENTRY(chunk),
+	SCTP_DBG_OBJCNT_ENTRY(bind_addr),
+	SCTP_DBG_OBJCNT_ENTRY(bind_bucket),
+	SCTP_DBG_OBJCNT_ENTRY(addr),
+	SCTP_DBG_OBJCNT_ENTRY(ssnmap),
+	SCTP_DBG_OBJCNT_ENTRY(datamsg),
+};
+
+/* Callback from procfs to read out objcount information.
+ * Walk through the entries in the sctp_dbg_objcnt array, dumping
+ * the raw object counts for each monitored type.
+ *
+ * This code was modified from similar code in route.c
+ */
+static int sctp_dbg_objcnt_read(char *buffer, char **start, off_t offset,
+				int length, int *eof, void *data)
+{
+	int len = 0;
+	off_t pos = 0;
+	int entries;
+	int i;
+	char temp[128];
+
+	/* How many entries? */
+	entries = ARRAY_SIZE(sctp_dbg_objcnt);
+
+	/* Walk the entries and print out the debug information
+	 * for proc fs.
+	 */
+	for (i = 0; i < entries; i++) {
+		pos += 128;
+
+		/* Skip ahead. */
+		if (pos <= offset) {
+			len = 0;
+			continue;
+		}
+		/* Print out each entry. */
+		sprintf(temp, "%s: %d",
+			sctp_dbg_objcnt[i].label,
+			atomic_read(sctp_dbg_objcnt[i].counter));
+
+		sprintf(buffer + len, "%-127s\n", temp);
+		len += 128;
+		if (pos >= offset+length)
+			goto done;
+	}
+
+done:
+	*start = buffer + len - (pos - offset);
+	len = pos - offset;
+	if (len > length)
+		len = length;
+
+  	return len;
+}
+
+/* Initialize the objcount in the proc filesystem.  */
+void sctp_dbg_objcnt_init(void)
+{
+	create_proc_read_entry("sctp_dbg_objcnt", 0, proc_net_sctp,
+			       sctp_dbg_objcnt_read, NULL);
+}
+
+/* Cleanup the objcount entry in the proc filesystem.  */
+void sctp_dbg_objcnt_exit(void)
+{
+	remove_proc_entry("sctp_dbg_objcnt", proc_net_sctp);
+}
+
+

net/sctp/output.c

@@ -0,0 +1,646 @@
+/* SCTP kernel reference Implementation
+ * (C) Copyright IBM Corp. 2001, 2004
+ * Copyright (c) 1999-2000 Cisco, Inc.
+ * Copyright (c) 1999-2001 Motorola, Inc.
+ *
+ * This file is part of the SCTP kernel reference Implementation
+ *
+ * These functions handle output processing.
+ *
+ * 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 <lksctp-developers@lists.sourceforge.net>
+ *
+ * Or submit a bug report through the following website:
+ *    http://www.sf.net/projects/lksctp
+ *
+ * Written or modified by:
+ *    La Monte H.P. Yarroll <piggy@acm.org>
+ *    Karl Knutson          <karl@athena.chicago.il.us>
+ *    Jon Grimm             <jgrimm@austin.ibm.com>
+ *    Sridhar Samudrala     <sri@us.ibm.com>
+ *
+ * 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/kernel.h>
+#include <linux/wait.h>
+#include <linux/time.h>
+#include <linux/ip.h>
+#include <linux/ipv6.h>
+#include <linux/init.h>
+#include <net/inet_ecn.h>
+#include <net/icmp.h>
+
+#ifndef TEST_FRAME
+#include <net/tcp.h>
+#endif /* TEST_FRAME (not defined) */
+
+#include <linux/socket.h> /* for sa_family_t */
+#include <net/sock.h>
+
+#include <net/sctp/sctp.h>
+#include <net/sctp/sm.h>
+
+/* Forward declarations for private helpers. */
+static sctp_xmit_t sctp_packet_append_data(struct sctp_packet *packet,
+					   struct sctp_chunk *chunk);
+
+/* Config a packet.
+ * This appears to be a followup set of initializations.
+ */
+struct sctp_packet *sctp_packet_config(struct sctp_packet *packet,
+				       __u32 vtag, int ecn_capable)
+{
+	struct sctp_chunk *chunk = NULL;
+
+	SCTP_DEBUG_PRINTK("%s: packet:%p vtag:0x%x\n", __FUNCTION__,
+			  packet, vtag);
+
+	packet->vtag = vtag;
+	packet->has_cookie_echo = 0;
+	packet->has_sack = 0;
+	packet->ipfragok = 0;
+
+	if (ecn_capable && sctp_packet_empty(packet)) {
+		chunk = sctp_get_ecne_prepend(packet->transport->asoc);
+
+		/* If there a is a prepend chunk stick it on the list before
+	 	 * any other chunks get appended.
+	 	 */
+		if (chunk)
+			sctp_packet_append_chunk(packet, chunk);
+	}
+
+	return packet;
+}
+
+/* Initialize the packet structure. */
+struct sctp_packet *sctp_packet_init(struct sctp_packet *packet,
+				     struct sctp_transport *transport,
+				     __u16 sport, __u16 dport)
+{
+	struct sctp_association *asoc = transport->asoc;
+	size_t overhead;
+
+	SCTP_DEBUG_PRINTK("%s: packet:%p transport:%p\n", __FUNCTION__,
+			  packet, transport);
+
+	packet->transport = transport;
+	packet->source_port = sport;
+	packet->destination_port = dport;
+	skb_queue_head_init(&packet->chunks);
+	if (asoc) {
+		struct sctp_sock *sp = sctp_sk(asoc->base.sk);	
+		overhead = sp->pf->af->net_header_len; 
+	} else {
+		overhead = sizeof(struct ipv6hdr);
+	}
+	overhead += sizeof(struct sctphdr);
+	packet->overhead = overhead;
+	packet->size = overhead;
+	packet->vtag = 0;
+	packet->has_cookie_echo = 0;
+	packet->has_sack = 0;
+	packet->ipfragok = 0;
+	packet->malloced = 0;
+	return packet;
+}
+
+/* Free a packet.  */
+void sctp_packet_free(struct sctp_packet *packet)
+{
+	struct sctp_chunk *chunk;
+
+	SCTP_DEBUG_PRINTK("%s: packet:%p\n", __FUNCTION__, packet);
+
+        while ((chunk = (struct sctp_chunk *)__skb_dequeue(&packet->chunks)) != NULL)
+		sctp_chunk_free(chunk);
+
+	if (packet->malloced)
+		kfree(packet);
+}
+
+/* This routine tries to append the chunk to the offered packet. If adding
+ * the chunk causes the packet to exceed the path MTU and COOKIE_ECHO chunk
+ * is not present in the packet, it transmits the input packet.
+ * Data can be bundled with a packet containing a COOKIE_ECHO chunk as long
+ * as it can fit in the packet, but any more data that does not fit in this
+ * packet can be sent only after receiving the COOKIE_ACK.
+ */
+sctp_xmit_t sctp_packet_transmit_chunk(struct sctp_packet *packet,
+				       struct sctp_chunk *chunk)
+{
+	sctp_xmit_t retval;
+	int error = 0;
+
+	SCTP_DEBUG_PRINTK("%s: packet:%p chunk:%p\n", __FUNCTION__,
+			  packet, chunk);
+
+	switch ((retval = (sctp_packet_append_chunk(packet, chunk)))) {
+	case SCTP_XMIT_PMTU_FULL:
+		if (!packet->has_cookie_echo) {
+			error = sctp_packet_transmit(packet);
+			if (error < 0)
+				chunk->skb->sk->sk_err = -error;
+
+			/* If we have an empty packet, then we can NOT ever
+			 * return PMTU_FULL.
+			 */
+			retval = sctp_packet_append_chunk(packet, chunk);
+		}
+		break;
+
+	case SCTP_XMIT_RWND_FULL:
+	case SCTP_XMIT_OK:
+	case SCTP_XMIT_NAGLE_DELAY:
+		break;
+	};
+
+	return retval;
+}
+
+/* Try to bundle a SACK with the packet. */
+static sctp_xmit_t sctp_packet_bundle_sack(struct sctp_packet *pkt,
+					   struct sctp_chunk *chunk)
+{
+	sctp_xmit_t retval = SCTP_XMIT_OK;
+
+	/* If sending DATA and haven't aleady bundled a SACK, try to
+	 * bundle one in to the packet.
+	 */
+	if (sctp_chunk_is_data(chunk) && !pkt->has_sack &&
+	    !pkt->has_cookie_echo) {
+		struct sctp_association *asoc;
+		asoc = pkt->transport->asoc;
+
+		if (asoc->a_rwnd > asoc->rwnd) {
+			struct sctp_chunk *sack;
+			asoc->a_rwnd = asoc->rwnd;
+			sack = sctp_make_sack(asoc);
+			if (sack) {
+				struct timer_list *timer;
+				retval = sctp_packet_append_chunk(pkt, sack);
+				asoc->peer.sack_needed = 0;
+				timer = &asoc->timers[SCTP_EVENT_TIMEOUT_SACK];
+				if (timer_pending(timer) && del_timer(timer))
+					sctp_association_put(asoc);
+			}
+		}
+	}
+	return retval;
+}
+
+/* Append a chunk to the offered packet reporting back any inability to do
+ * so.
+ */
+sctp_xmit_t sctp_packet_append_chunk(struct sctp_packet *packet,
+				     struct sctp_chunk *chunk)
+{
+	sctp_xmit_t retval = SCTP_XMIT_OK;
+	__u16 chunk_len = WORD_ROUND(ntohs(chunk->chunk_hdr->length));
+	size_t psize;
+	size_t pmtu;
+	int too_big;
+
+	SCTP_DEBUG_PRINTK("%s: packet:%p chunk:%p\n", __FUNCTION__, packet,
+			  chunk);
+
+	retval = sctp_packet_bundle_sack(packet, chunk);
+	psize = packet->size;
+
+	if (retval != SCTP_XMIT_OK)
+		goto finish;
+
+	pmtu  = ((packet->transport->asoc) ?
+		 (packet->transport->asoc->pmtu) :
+		 (packet->transport->pmtu));
+
+	too_big = (psize + chunk_len > pmtu);
+
+	/* Decide if we need to fragment or resubmit later. */
+	if (too_big) {
+		/* Both control chunks and data chunks with TSNs are
+		 * non-fragmentable.
+		 */
+		if (sctp_packet_empty(packet) || !sctp_chunk_is_data(chunk)) {
+			/* We no longer do re-fragmentation.
+			 * Just fragment at the IP layer, if we
+			 * actually hit this condition
+			 */
+			packet->ipfragok = 1;
+			goto append;
+
+		} else {
+			retval = SCTP_XMIT_PMTU_FULL;
+			goto finish;
+		}
+	}
+
+append:
+	/* We believe that this chunk is OK to add to the packet (as
+	 * long as we have the cwnd for it).
+	 */
+
+	/* DATA is a special case since we must examine both rwnd and cwnd
+	 * before we send DATA.
+	 */
+	if (sctp_chunk_is_data(chunk)) {
+		retval = sctp_packet_append_data(packet, chunk);
+		/* Disallow SACK bundling after DATA. */
+		packet->has_sack = 1;
+		if (SCTP_XMIT_OK != retval)
+			goto finish;
+	} else if (SCTP_CID_COOKIE_ECHO == chunk->chunk_hdr->type)
+		packet->has_cookie_echo = 1;
+	else if (SCTP_CID_SACK == chunk->chunk_hdr->type)
+		packet->has_sack = 1;
+
+	/* It is OK to send this chunk.  */
+	__skb_queue_tail(&packet->chunks, (struct sk_buff *)chunk);
+	packet->size += chunk_len;
+	chunk->transport = packet->transport;
+finish:
+	return retval;
+}
+
+/* All packets are sent to the network through this function from
+ * sctp_outq_tail().
+ *
+ * The return value is a normal kernel error return value.
+ */
+int sctp_packet_transmit(struct sctp_packet *packet)
+{
+	struct sctp_transport *tp = packet->transport;
+	struct sctp_association *asoc = tp->asoc;
+	struct sctphdr *sh;
+	__u32 crc32;
+	struct sk_buff *nskb;
+	struct sctp_chunk *chunk;
+	struct sock *sk;
+	int err = 0;
+	int padding;		/* How much padding do we need?  */
+	__u8 has_data = 0;
+	struct dst_entry *dst;
+
+	SCTP_DEBUG_PRINTK("%s: packet:%p\n", __FUNCTION__, packet);
+
+	/* Do NOT generate a chunkless packet. */
+	chunk = (struct sctp_chunk *)skb_peek(&packet->chunks);
+	if (unlikely(!chunk))
+		return err;
+
+	/* Set up convenience variables... */
+	sk = chunk->skb->sk;
+
+	/* Allocate the new skb.  */
+	nskb = dev_alloc_skb(packet->size);
+	if (!nskb)
+		goto nomem;
+
+	/* Make sure the outbound skb has enough header room reserved. */
+	skb_reserve(nskb, packet->overhead);
+
+	/* Set the owning socket so that we know where to get the
+	 * destination IP address.
+	 */
+	skb_set_owner_w(nskb, sk);
+
+	/* Build the SCTP header.  */
+	sh = (struct sctphdr *)skb_push(nskb, sizeof(struct sctphdr));
+	sh->source = htons(packet->source_port);
+	sh->dest   = htons(packet->destination_port);
+
+	/* From 6.8 Adler-32 Checksum Calculation:
+	 * After the packet is constructed (containing the SCTP common
+	 * header and one or more control or DATA chunks), the
+	 * transmitter shall:
+	 *
+	 * 1) Fill in the proper Verification Tag in the SCTP common
+	 *    header and initialize the checksum field to 0's.
+	 */
+	sh->vtag     = htonl(packet->vtag);
+	sh->checksum = 0;
+
+	/* 2) Calculate the Adler-32 checksum of the whole packet,
+	 *    including the SCTP common header and all the
+	 *    chunks.
+	 *
+	 * Note: Adler-32 is no longer applicable, as has been replaced
+	 * by CRC32-C as described in <draft-ietf-tsvwg-sctpcsum-02.txt>.
+	 */
+	crc32 = sctp_start_cksum((__u8 *)sh, sizeof(struct sctphdr));
+
+	/**
+	 * 6.10 Bundling
+	 *
+	 *    An endpoint bundles chunks by simply including multiple
+	 *    chunks in one outbound SCTP packet.  ...
+	 */
+
+	/**
+	 * 3.2  Chunk Field Descriptions
+	 *
+	 * The total length of a chunk (including Type, Length and
+	 * Value fields) MUST be a multiple of 4 bytes.  If the length
+	 * of the chunk is not a multiple of 4 bytes, the sender MUST
+	 * pad the chunk with all zero bytes and this padding is not
+	 * included in the chunk length field.  The sender should
+	 * never pad with more than 3 bytes.
+	 *
+	 * [This whole comment explains WORD_ROUND() below.]
+	 */
+	SCTP_DEBUG_PRINTK("***sctp_transmit_packet***\n");
+	while ((chunk = (struct sctp_chunk *)__skb_dequeue(&packet->chunks)) != NULL) {
+		if (sctp_chunk_is_data(chunk)) {
+
+			if (!chunk->has_tsn) {
+				sctp_chunk_assign_ssn(chunk);
+				sctp_chunk_assign_tsn(chunk);
+
+			/* 6.3.1 C4) When data is in flight and when allowed
+			 * by rule C5, a new RTT measurement MUST be made each
+			 * round trip.  Furthermore, new RTT measurements
+			 * SHOULD be made no more than once per round-trip
+			 * for a given destination transport address.
+			 */
+
+				if (!tp->rto_pending) {
+					chunk->rtt_in_progress = 1;
+					tp->rto_pending = 1;
+				}
+			} else
+				chunk->resent = 1;
+
+			chunk->sent_at = jiffies;
+			has_data = 1;
+		}
+
+		padding = WORD_ROUND(chunk->skb->len) - chunk->skb->len;
+		if (padding)
+			memset(skb_put(chunk->skb, padding), 0, padding);
+
+		crc32 = sctp_update_copy_cksum(skb_put(nskb, chunk->skb->len),
+					       chunk->skb->data,
+					       chunk->skb->len, crc32);
+
+		SCTP_DEBUG_PRINTK("%s %p[%s] %s 0x%x, %s %d, %s %d, %s %d\n",
+				  "*** Chunk", chunk,
+				  sctp_cname(SCTP_ST_CHUNK(
+					  chunk->chunk_hdr->type)),
+				  chunk->has_tsn ? "TSN" : "No TSN",
+				  chunk->has_tsn ?
+				  ntohl(chunk->subh.data_hdr->tsn) : 0,
+				  "length", ntohs(chunk->chunk_hdr->length),
+				  "chunk->skb->len", chunk->skb->len,
+				  "rtt_in_progress", chunk->rtt_in_progress);
+
+		/*
+		 * If this is a control chunk, this is our last
+		 * reference. Free data chunks after they've been
+		 * acknowledged or have failed.
+		 */
+		if (!sctp_chunk_is_data(chunk))
+    			sctp_chunk_free(chunk);
+	}
+
+	/* Perform final transformation on checksum. */
+	crc32 = sctp_end_cksum(crc32);
+
+	/* 3) Put the resultant value into the checksum field in the
+	 *    common header, and leave the rest of the bits unchanged.
+	 */
+	sh->checksum = htonl(crc32);
+
+	/* IP layer ECN support
+	 * From RFC 2481
+	 *  "The ECN-Capable Transport (ECT) bit would be set by the
+	 *   data sender to indicate that the end-points of the
+	 *   transport protocol are ECN-capable."
+	 *
+	 * Now setting the ECT bit all the time, as it should not cause
+	 * any problems protocol-wise even if our peer ignores it.
+	 *
+	 * Note: The works for IPv6 layer checks this bit too later
+	 * in transmission.  See IP6_ECN_flow_xmit().
+	 */
+	INET_ECN_xmit(nskb->sk);
+
+	/* Set up the IP options.  */
+	/* BUG: not implemented
+	 * For v4 this all lives somewhere in sk->sk_opt...
+	 */
+
+	/* Dump that on IP!  */
+	if (asoc && asoc->peer.last_sent_to != tp) {
+		/* Considering the multiple CPU scenario, this is a
+		 * "correcter" place for last_sent_to.  --xguo
+		 */
+		asoc->peer.last_sent_to = tp;
+	}
+
+	if (has_data) {
+		struct timer_list *timer;
+		unsigned long timeout;
+
+		tp->last_time_used = jiffies;
+
+		/* Restart the AUTOCLOSE timer when sending data. */
+		if (sctp_state(asoc, ESTABLISHED) && asoc->autoclose) {
+			timer = &asoc->timers[SCTP_EVENT_TIMEOUT_AUTOCLOSE];
+			timeout = asoc->timeouts[SCTP_EVENT_TIMEOUT_AUTOCLOSE];
+
+			if (!mod_timer(timer, jiffies + timeout))
+				sctp_association_hold(asoc);
+		}
+	}
+
+	dst = tp->dst;
+	/* The 'obsolete' field of dst is set to 2 when a dst is freed. */
+	if (!dst || (dst->obsolete > 1)) {
+		dst_release(dst);
+		sctp_transport_route(tp, NULL, sctp_sk(sk));
+		sctp_assoc_sync_pmtu(asoc);
+	}
+
+	nskb->dst = dst_clone(tp->dst);
+	if (!nskb->dst)
+		goto no_route;
+
+	SCTP_DEBUG_PRINTK("***sctp_transmit_packet*** skb len %d\n",
+			  nskb->len);
+
+	(*tp->af_specific->sctp_xmit)(nskb, tp, packet->ipfragok);
+
+out:
+	packet->size = packet->overhead;
+	return err;
+no_route:
+	kfree_skb(nskb);
+	IP_INC_STATS_BH(IPSTATS_MIB_OUTNOROUTES);
+
+	/* FIXME: Returning the 'err' will effect all the associations
+	 * associated with a socket, although only one of the paths of the
+	 * association is unreachable.
+	 * The real failure of a transport or association can be passed on
+	 * to the user via notifications. So setting this error may not be
+	 * required.
+	 */
+	 /* err = -EHOSTUNREACH; */
+err:
+	/* Control chunks are unreliable so just drop them.  DATA chunks
+	 * will get resent or dropped later.
+	 */
+
+	while ((chunk = (struct sctp_chunk *)__skb_dequeue(&packet->chunks)) != NULL) {
+		if (!sctp_chunk_is_data(chunk))
+    			sctp_chunk_free(chunk);
+	}
+	goto out;
+nomem:
+	err = -ENOMEM;
+	goto err;
+}
+
+/********************************************************************
+ * 2nd Level Abstractions
+ ********************************************************************/
+
+/* This private function handles the specifics of appending DATA chunks.  */
+static sctp_xmit_t sctp_packet_append_data(struct sctp_packet *packet,
+					   struct sctp_chunk *chunk)
+{
+	sctp_xmit_t retval = SCTP_XMIT_OK;
+	size_t datasize, rwnd, inflight;
+	struct sctp_transport *transport = packet->transport;
+	__u32 max_burst_bytes;
+	struct sctp_association *asoc = transport->asoc;
+	struct sctp_sock *sp = sctp_sk(asoc->base.sk);
+	struct sctp_outq *q = &asoc->outqueue;
+
+	/* RFC 2960 6.1  Transmission of DATA Chunks
+	 *
+	 * A) At any given time, the data sender MUST NOT transmit new data to
+	 * any destination transport address if its peer's rwnd indicates
+	 * that the peer has no buffer space (i.e. rwnd is 0, see Section
+	 * 6.2.1).  However, regardless of the value of rwnd (including if it
+	 * is 0), the data sender can always have one DATA chunk in flight to
+	 * the receiver if allowed by cwnd (see rule B below).  This rule
+	 * allows the sender to probe for a change in rwnd that the sender
+	 * missed due to the SACK having been lost in transit from the data
+	 * receiver to the data sender.
+	 */
+
+	rwnd = asoc->peer.rwnd;
+	inflight = asoc->outqueue.outstanding_bytes;
+
+	datasize = sctp_data_size(chunk);
+
+	if (datasize > rwnd) {
+		if (inflight > 0) {
+			/* We have (at least) one data chunk in flight,
+			 * so we can't fall back to rule 6.1 B).
+			 */
+			retval = SCTP_XMIT_RWND_FULL;
+			goto finish;
+		}
+	}
+
+	/* sctpimpguide-05 2.14.2
+	 * D) When the time comes for the sender to
+	 * transmit new DATA chunks, the protocol parameter Max.Burst MUST
+	 * first be applied to limit how many new DATA chunks may be sent.
+	 * The limit is applied by adjusting cwnd as follows:
+	 * 	if ((flightsize + Max.Burst * MTU) < cwnd)
+	 *		cwnd = flightsize + Max.Burst * MTU
+	 */
+	max_burst_bytes = asoc->max_burst * asoc->pmtu;
+	if ((transport->flight_size + max_burst_bytes) < transport->cwnd) {
+		transport->cwnd = transport->flight_size + max_burst_bytes;
+		SCTP_DEBUG_PRINTK("%s: cwnd limited by max_burst: "
+				  "transport: %p, cwnd: %d, "
+				  "ssthresh: %d, flight_size: %d, "
+				  "pba: %d\n",
+				  __FUNCTION__, transport,
+				  transport->cwnd,
+				  transport->ssthresh,
+				  transport->flight_size,
+				  transport->partial_bytes_acked);
+	}
+
+	/* RFC 2960 6.1  Transmission of DATA Chunks
+	 *
+	 * B) At any given time, the sender MUST NOT transmit new data
+	 * to a given transport address if it has cwnd or more bytes
+	 * of data outstanding to that transport address.
+	 */
+	/* RFC 7.2.4 & the Implementers Guide 2.8.
+	 *
+	 * 3) ...
+	 *    When a Fast Retransmit is being performed the sender SHOULD
+	 *    ignore the value of cwnd and SHOULD NOT delay retransmission.
+	 */
+	if (!chunk->fast_retransmit)
+		if (transport->flight_size >= transport->cwnd) {
+			retval = SCTP_XMIT_RWND_FULL;
+			goto finish;
+		}
+
+	/* Nagle's algorithm to solve small-packet problem:
+	 * Inhibit the sending of new chunks when new outgoing data arrives
+	 * if any previously transmitted data on the connection remains
+	 * unacknowledged.
+	 */
+	if (!sp->nodelay && sctp_packet_empty(packet) &&
+	    q->outstanding_bytes && sctp_state(asoc, ESTABLISHED)) {
+		unsigned len = datasize + q->out_qlen;
+
+		/* Check whether this chunk and all the rest of pending
+		 * data will fit or delay in hopes of bundling a full
+		 * sized packet.
+		 */
+		if (len < asoc->pmtu - packet->overhead) {
+			retval = SCTP_XMIT_NAGLE_DELAY;
+			goto finish;
+		}
+	}
+
+	/* Keep track of how many bytes are in flight over this transport. */
+	transport->flight_size += datasize;
+
+	/* Keep track of how many bytes are in flight to the receiver. */
+	asoc->outqueue.outstanding_bytes += datasize;
+
+	/* Update our view of the receiver's rwnd. */
+	if (datasize < rwnd)
+		rwnd -= datasize;
+	else
+		rwnd = 0;
+
+	asoc->peer.rwnd = rwnd;
+	/* Has been accepted for transmission. */
+	if (!asoc->peer.prsctp_capable)
+		chunk->msg->can_abandon = 0;
+
+finish:
+	return retval;
+}

net/sctp/primitive.c

@@ -0,0 +1,219 @@
+/* SCTP kernel reference Implementation
+ * Copyright (c) 1999-2000 Cisco, Inc.
+ * Copyright (c) 1999-2001 Motorola, Inc.
+ *
+ * This file is part of the SCTP kernel reference Implementation
+ *
+ * These functions implement the SCTP primitive functions from Section 10.
+ *
+ * Note that the descriptions from the specification are USER level
+ * functions--this file is the functions which populate the struct proto
+ * for SCTP which is the BOTTOM of the sockets interface.
+ *
+ * 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 <lksctp-developers@lists.sourceforge.net>
+ *
+ * Or submit a bug report through the following website:
+ *    http://www.sf.net/projects/lksctp
+ *
+ * Written or modified by:
+ *    La Monte H.P. Yarroll <piggy@acm.org>
+ *    Narasimha Budihal     <narasimha@refcode.org>
+ *    Karl Knutson          <karl@athena.chicago.il.us>
+ *    Ardelle Fan	    <ardelle.fan@intel.com>
+ *    Kevin Gao             <kevin.gao@intel.com>
+ *
+ * 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/sock.h>
+#include <net/sctp/sctp.h>
+#include <net/sctp/sm.h>
+
+#define DECLARE_PRIMITIVE(name) \
+/* This is called in the code as sctp_primitive_ ## name.  */ \
+int sctp_primitive_ ## name(struct sctp_association *asoc, \
+			    void *arg) { \
+	int error = 0; \
+	sctp_event_t event_type; sctp_subtype_t subtype; \
+	sctp_state_t state; \
+	struct sctp_endpoint *ep; \
+	\
+	event_type = SCTP_EVENT_T_PRIMITIVE; \
+	subtype = SCTP_ST_PRIMITIVE(SCTP_PRIMITIVE_ ## name); \
+	state = asoc ? asoc->state : SCTP_STATE_CLOSED; \
+	ep = asoc ? asoc->ep : NULL; \
+	\
+	error = sctp_do_sm(event_type, subtype, state, ep, asoc, \
+			   arg, GFP_KERNEL); \
+ 	return error; \
+}
+
+/* 10.1 ULP-to-SCTP
+ * B) Associate
+ *
+ * Format: ASSOCIATE(local SCTP instance name, destination transport addr,
+ *         outbound stream count)
+ * -> association id [,destination transport addr list] [,outbound stream
+ *    count]
+ *
+ * This primitive allows the upper layer to initiate an association to a
+ * specific peer endpoint.
+ *
+ * This version assumes that asoc is fully populated with the initial
+ * parameters.  We then return a traditional kernel indicator of
+ * success or failure.
+ */
+
+/* This is called in the code as sctp_primitive_ASSOCIATE.  */
+
+DECLARE_PRIMITIVE(ASSOCIATE)
+
+/* 10.1 ULP-to-SCTP
+ * C) Shutdown
+ *
+ * Format: SHUTDOWN(association id)
+ * -> result
+ *
+ * Gracefully closes an association. Any locally queued user data
+ * will be delivered to the peer. The association will be terminated only
+ * after the peer acknowledges all the SCTP packets sent.  A success code
+ * will be returned on successful termination of the association. If
+ * attempting to terminate the association results in a failure, an error
+ * code shall be returned.
+ */
+
+DECLARE_PRIMITIVE(SHUTDOWN);
+
+/* 10.1 ULP-to-SCTP
+ * C) Abort
+ *
+ * Format: Abort(association id [, cause code])
+ * -> result
+ *
+ * Ungracefully closes an association. Any locally queued user data
+ * will be discarded and an ABORT chunk is sent to the peer. A success
+ * code will be returned on successful abortion of the association. If
+ * attempting to abort the association results in a failure, an error
+ * code shall be returned.
+ */
+
+DECLARE_PRIMITIVE(ABORT);
+
+/* 10.1 ULP-to-SCTP
+ * E) Send
+ *
+ * Format: SEND(association id, buffer address, byte count [,context]
+ *         [,stream id] [,life time] [,destination transport address]
+ *         [,unorder flag] [,no-bundle flag] [,payload protocol-id] )
+ * -> result
+ *
+ * This is the main method to send user data via SCTP.
+ *
+ * Mandatory attributes:
+ *
+ *  o association id - local handle to the SCTP association
+ *
+ *  o buffer address - the location where the user message to be
+ *    transmitted is stored;
+ *
+ *  o byte count - The size of the user data in number of bytes;
+ *
+ * Optional attributes:
+ *
+ *  o context - an optional 32 bit integer that will be carried in the
+ *    sending failure notification to the ULP if the transportation of
+ *    this User Message fails.
+ *
+ *  o stream id - to indicate which stream to send the data on. If not
+ *    specified, stream 0 will be used.
+ *
+ *  o life time - specifies the life time of the user data. The user data
+ *    will not be sent by SCTP after the life time expires. This
+ *    parameter can be used to avoid efforts to transmit stale
+ *    user messages. SCTP notifies the ULP if the data cannot be
+ *    initiated to transport (i.e. sent to the destination via SCTP's
+ *    send primitive) within the life time variable. However, the
+ *    user data will be transmitted if SCTP has attempted to transmit a
+ *    chunk before the life time expired.
+ *
+ *  o destination transport address - specified as one of the destination
+ *    transport addresses of the peer endpoint to which this packet
+ *    should be sent. Whenever possible, SCTP should use this destination
+ *    transport address for sending the packets, instead of the current
+ *    primary path.
+ *
+ *  o unorder flag - this flag, if present, indicates that the user
+ *    would like the data delivered in an unordered fashion to the peer
+ *    (i.e., the U flag is set to 1 on all DATA chunks carrying this
+ *    message).
+ *
+ *  o no-bundle flag - instructs SCTP not to bundle this user data with
+ *    other outbound DATA chunks. SCTP MAY still bundle even when
+ *    this flag is present, when faced with network congestion.
+ *
+ *  o payload protocol-id - A 32 bit unsigned integer that is to be
+ *    passed to the peer indicating the type of payload protocol data
+ *    being transmitted. This value is passed as opaque data by SCTP.
+ */
+
+DECLARE_PRIMITIVE(SEND);
+
+/* 10.1 ULP-to-SCTP
+ * J) Request Heartbeat
+ *
+ * Format: REQUESTHEARTBEAT(association id, destination transport address)
+ *
+ * -> result
+ *
+ * Instructs the local endpoint to perform a HeartBeat on the specified
+ * destination transport address of the given association. The returned
+ * result should indicate whether the transmission of the HEARTBEAT
+ * chunk to the destination address is successful.
+ *
+ * Mandatory attributes:
+ *
+ * o association id - local handle to the SCTP association
+ *
+ * o destination transport address - the transport address of the
+ *   association on which a heartbeat should be issued.
+ */
+
+DECLARE_PRIMITIVE(REQUESTHEARTBEAT);
+
+/* ADDIP
+* 3.1.1 Address Configuration Change Chunk (ASCONF)
+* 
+* This chunk is used to communicate to the remote endpoint one of the
+* configuration change requests that MUST be acknowledged.  The
+* information carried in the ASCONF Chunk uses the form of a
+* Type-Length-Value (TLV), as described in "3.2.1 Optional/
+* Variable-length Parameter Format" in RFC2960 [5], forall variable
+* parameters.
+*/
+
+DECLARE_PRIMITIVE(ASCONF);

net/sctp/proc.c

@@ -0,0 +1,288 @@
+/* SCTP kernel reference Implementation
+ * Copyright (c) 2003 International Business Machines, Corp.
+ *
+ * This file is part of the SCTP kernel reference Implementation
+ *
+ * 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 <lksctp-developers@lists.sourceforge.net>
+ *
+ * Or submit a bug report through the following website:
+ *    http://www.sf.net/projects/lksctp
+ *
+ * Written or modified by:
+ *    Sridhar Samudrala <sri@us.ibm.com>
+ *
+ * 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/seq_file.h>
+#include <linux/init.h>
+#include <net/sctp/sctp.h>
+
+static struct snmp_mib sctp_snmp_list[] = {
+	SNMP_MIB_ITEM("SctpCurrEstab", SCTP_MIB_CURRESTAB),
+	SNMP_MIB_ITEM("SctpActiveEstabs", SCTP_MIB_ACTIVEESTABS),
+	SNMP_MIB_ITEM("SctpPassiveEstabs", SCTP_MIB_PASSIVEESTABS),
+	SNMP_MIB_ITEM("SctpAborteds", SCTP_MIB_ABORTEDS),
+	SNMP_MIB_ITEM("SctpShutdowns", SCTP_MIB_SHUTDOWNS),
+	SNMP_MIB_ITEM("SctpOutOfBlues", SCTP_MIB_OUTOFBLUES),
+	SNMP_MIB_ITEM("SctpChecksumErrors", SCTP_MIB_CHECKSUMERRORS),
+	SNMP_MIB_ITEM("SctpOutCtrlChunks", SCTP_MIB_OUTCTRLCHUNKS),
+	SNMP_MIB_ITEM("SctpOutOrderChunks", SCTP_MIB_OUTORDERCHUNKS),
+	SNMP_MIB_ITEM("SctpOutUnorderChunks", SCTP_MIB_OUTUNORDERCHUNKS),
+	SNMP_MIB_ITEM("SctpInCtrlChunks", SCTP_MIB_INCTRLCHUNKS),
+	SNMP_MIB_ITEM("SctpInOrderChunks", SCTP_MIB_INORDERCHUNKS),
+	SNMP_MIB_ITEM("SctpInUnorderChunks", SCTP_MIB_INUNORDERCHUNKS),
+	SNMP_MIB_ITEM("SctpFragUsrMsgs", SCTP_MIB_FRAGUSRMSGS),
+	SNMP_MIB_ITEM("SctpReasmUsrMsgs", SCTP_MIB_REASMUSRMSGS),
+	SNMP_MIB_ITEM("SctpOutSCTPPacks", SCTP_MIB_OUTSCTPPACKS),
+	SNMP_MIB_ITEM("SctpInSCTPPacks", SCTP_MIB_INSCTPPACKS),
+};
+
+/* Return the current value of a particular entry in the mib by adding its
+ * per cpu counters.
+ */ 
+static unsigned long
+fold_field(void *mib[], int nr)
+{
+	unsigned long res = 0;
+	int i;
+
+	for (i = 0; i < NR_CPUS; i++) {
+		if (!cpu_possible(i))
+			continue;
+		res +=
+		    *((unsigned long *) (((void *) per_cpu_ptr(mib[0], i)) +
+					 sizeof (unsigned long) * nr));
+		res +=
+		    *((unsigned long *) (((void *) per_cpu_ptr(mib[1], i)) +
+					 sizeof (unsigned long) * nr));
+	}
+	return res;
+}
+
+/* Display sctp snmp mib statistics(/proc/net/sctp/snmp). */
+static int sctp_snmp_seq_show(struct seq_file *seq, void *v)
+{
+	int i;
+
+	for (i = 0; sctp_snmp_list[i].name != NULL; i++)
+		seq_printf(seq, "%-32s\t%ld\n", sctp_snmp_list[i].name,
+			   fold_field((void **)sctp_statistics, 
+				      sctp_snmp_list[i].entry));
+
+	return 0;
+}
+
+/* Initialize the seq file operations for 'snmp' object. */
+static int sctp_snmp_seq_open(struct inode *inode, struct file *file)
+{
+	return single_open(file, sctp_snmp_seq_show, NULL);
+}
+
+static struct file_operations sctp_snmp_seq_fops = {
+	.owner	 = THIS_MODULE,
+	.open	 = sctp_snmp_seq_open,
+	.read	 = seq_read,
+	.llseek	 = seq_lseek,
+	.release = single_release,
+};
+
+/* Set up the proc fs entry for 'snmp' object. */
+int __init sctp_snmp_proc_init(void)
+{
+	struct proc_dir_entry *p;
+
+	p = create_proc_entry("snmp", S_IRUGO, proc_net_sctp);
+	if (!p)
+		return -ENOMEM;
+
+	p->proc_fops = &sctp_snmp_seq_fops;
+
+	return 0;
+}
+
+/* Cleanup the proc fs entry for 'snmp' object. */
+void sctp_snmp_proc_exit(void)
+{
+	remove_proc_entry("snmp", proc_net_sctp);
+}
+
+/* Dump local addresses of an association/endpoint. */
+static void sctp_seq_dump_local_addrs(struct seq_file *seq, struct sctp_ep_common *epb)
+{
+	struct list_head *pos;
+	struct sctp_sockaddr_entry *laddr;
+	union sctp_addr *addr;
+	struct sctp_af *af;
+
+	list_for_each(pos, &epb->bind_addr.address_list) {
+		laddr = list_entry(pos, struct sctp_sockaddr_entry, list);
+		addr = (union sctp_addr *)&laddr->a;
+		af = sctp_get_af_specific(addr->sa.sa_family);
+		af->seq_dump_addr(seq, addr);
+	}
+}
+
+/* Dump remote addresses of an association. */
+static void sctp_seq_dump_remote_addrs(struct seq_file *seq, struct sctp_association *assoc)
+{
+	struct list_head *pos;
+	struct sctp_transport *transport;
+	union sctp_addr *addr;
+	struct sctp_af *af;
+
+	list_for_each(pos, &assoc->peer.transport_addr_list) {
+		transport = list_entry(pos, struct sctp_transport, transports);
+		addr = (union sctp_addr *)&transport->ipaddr;
+		af = sctp_get_af_specific(addr->sa.sa_family);
+		af->seq_dump_addr(seq, addr);
+	}
+}
+
+/* Display sctp endpoints (/proc/net/sctp/eps). */
+static int sctp_eps_seq_show(struct seq_file *seq, void *v)
+{
+	struct sctp_hashbucket *head;
+	struct sctp_ep_common *epb;
+	struct sctp_endpoint *ep;
+	struct sock *sk;
+	int hash;
+
+	seq_printf(seq, " ENDPT     SOCK   STY SST HBKT LPORT LADDRS\n");
+	for (hash = 0; hash < sctp_ep_hashsize; hash++) {
+		head = &sctp_ep_hashtable[hash];
+		read_lock(&head->lock);
+		for (epb = head->chain; epb; epb = epb->next) {
+			ep = sctp_ep(epb);
+			sk = epb->sk;
+			seq_printf(seq, "%8p %8p %-3d %-3d %-4d %-5d ", ep, sk,
+				   sctp_sk(sk)->type, sk->sk_state, hash,
+				   epb->bind_addr.port);
+			sctp_seq_dump_local_addrs(seq, epb);
+			seq_printf(seq, "\n");
+		}
+		read_unlock(&head->lock);
+	}
+
+	return 0;
+}
+
+/* Initialize the seq file operations for 'eps' object. */
+static int sctp_eps_seq_open(struct inode *inode, struct file *file)
+{
+	return single_open(file, sctp_eps_seq_show, NULL);
+}
+
+static struct file_operations sctp_eps_seq_fops = {
+	.open	 = sctp_eps_seq_open,
+	.read	 = seq_read,
+	.llseek	 = seq_lseek,
+	.release = single_release,
+};
+
+/* Set up the proc fs entry for 'eps' object. */
+int __init sctp_eps_proc_init(void)
+{
+	struct proc_dir_entry *p;
+
+	p = create_proc_entry("eps", S_IRUGO, proc_net_sctp);
+	if (!p)
+		return -ENOMEM;
+
+	p->proc_fops = &sctp_eps_seq_fops;
+
+	return 0;
+}
+
+/* Cleanup the proc fs entry for 'eps' object. */
+void sctp_eps_proc_exit(void)
+{
+	remove_proc_entry("eps", proc_net_sctp);
+}
+
+/* Display sctp associations (/proc/net/sctp/assocs). */
+static int sctp_assocs_seq_show(struct seq_file *seq, void *v)
+{
+	struct sctp_hashbucket *head;
+	struct sctp_ep_common *epb;
+	struct sctp_association *assoc;
+	struct sock *sk;
+	int hash;
+
+	seq_printf(seq, " ASSOC     SOCK   STY SST ST HBKT LPORT RPORT "
+			"LADDRS <-> RADDRS\n");
+	for (hash = 0; hash < sctp_assoc_hashsize; hash++) {
+		head = &sctp_assoc_hashtable[hash];
+		read_lock(&head->lock);
+		for (epb = head->chain; epb; epb = epb->next) {
+			assoc = sctp_assoc(epb);
+			sk = epb->sk;
+			seq_printf(seq,
+				   "%8p %8p %-3d %-3d %-2d %-4d %-5d %-5d ",
+				   assoc, sk, sctp_sk(sk)->type, sk->sk_state,
+				   assoc->state, hash, epb->bind_addr.port,
+				   assoc->peer.port);
+			sctp_seq_dump_local_addrs(seq, epb);
+			seq_printf(seq, "<-> ");
+			sctp_seq_dump_remote_addrs(seq, assoc);
+			seq_printf(seq, "\n");
+		}
+		read_unlock(&head->lock);
+	}
+
+	return 0;
+}
+
+/* Initialize the seq file operations for 'assocs' object. */
+static int sctp_assocs_seq_open(struct inode *inode, struct file *file)
+{
+	return single_open(file, sctp_assocs_seq_show, NULL);
+}
+
+static struct file_operations sctp_assocs_seq_fops = {
+	.open	 = sctp_assocs_seq_open,
+	.read	 = seq_read,
+	.llseek	 = seq_lseek,
+	.release = single_release,
+};
+
+/* Set up the proc fs entry for 'assocs' object. */
+int __init sctp_assocs_proc_init(void)
+{
+	struct proc_dir_entry *p;
+
+	p = create_proc_entry("assocs", S_IRUGO, proc_net_sctp);
+	if (!p)
+		return -ENOMEM;
+
+	p->proc_fops = &sctp_assocs_seq_fops;
+
+	return 0;
+}
+
+/* Cleanup the proc fs entry for 'assocs' object. */
+void sctp_assocs_proc_exit(void)
+{
+	remove_proc_entry("assocs", proc_net_sctp);
+}

net/sctp/ssnmap.c

@@ -0,0 +1,131 @@
+/* SCTP kernel reference Implementation
+ * Copyright (c) 2003 International Business Machines, Corp.
+ *
+ * This file is part of the SCTP kernel reference Implementation
+ *
+ * These functions manipulate sctp SSN tracker.
+ *
+ * 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 <lksctp-developers@lists.sourceforge.net>
+ *
+ * Or submit a bug report through the following website:
+ *    http://www.sf.net/projects/lksctp
+ *
+ * Written or modified by:
+ *    Jon Grimm             <jgrimm@us.ibm.com>
+ *
+ * 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 <net/sctp/sctp.h>
+#include <net/sctp/sm.h>
+
+#define MAX_KMALLOC_SIZE	131072
+
+static struct sctp_ssnmap *sctp_ssnmap_init(struct sctp_ssnmap *map, __u16 in,
+					    __u16 out);
+
+/* Storage size needed for map includes 2 headers and then the
+ * specific needs of in or out streams.
+ */
+static inline size_t sctp_ssnmap_size(__u16 in, __u16 out)
+{
+	return sizeof(struct sctp_ssnmap) + (in + out) * sizeof(__u16);
+}
+
+
+/* Create a new sctp_ssnmap.
+ * Allocate room to store at least 'len' contiguous TSNs.
+ */
+struct sctp_ssnmap *sctp_ssnmap_new(__u16 in, __u16 out, int gfp)
+{
+	struct sctp_ssnmap *retval;
+	int size;
+
+	size = sctp_ssnmap_size(in, out);
+	if (size <= MAX_KMALLOC_SIZE)
+		retval = kmalloc(size, gfp);
+	else
+		retval = (struct sctp_ssnmap *)
+			  __get_free_pages(gfp, get_order(size));
+	if (!retval)
+		goto fail;
+
+	if (!sctp_ssnmap_init(retval, in, out))
+		goto fail_map;
+
+	retval->malloced = 1;
+	SCTP_DBG_OBJCNT_INC(ssnmap);
+
+	return retval;
+
+fail_map:
+	if (size <= MAX_KMALLOC_SIZE)
+		kfree(retval);
+	else
+		free_pages((unsigned long)retval, get_order(size));
+fail:
+	return NULL;
+}
+
+
+/* Initialize a block of memory as a ssnmap.  */
+static struct sctp_ssnmap *sctp_ssnmap_init(struct sctp_ssnmap *map, __u16 in,
+					    __u16 out)
+{
+	memset(map, 0x00, sctp_ssnmap_size(in, out));
+
+	/* Start 'in' stream just after the map header. */
+	map->in.ssn = (__u16 *)&map[1];
+	map->in.len = in;
+
+	/* Start 'out' stream just after 'in'. */
+	map->out.ssn = &map->in.ssn[in];
+	map->out.len = out;
+
+	return map;
+}
+
+/* Clear out the ssnmap streams.  */
+void sctp_ssnmap_clear(struct sctp_ssnmap *map)
+{
+	size_t size;
+
+	size = (map->in.len + map->out.len) * sizeof(__u16);
+	memset(map->in.ssn, 0x00, size);
+}
+
+/* Dispose of a ssnmap.  */
+void sctp_ssnmap_free(struct sctp_ssnmap *map)
+{
+	if (map && map->malloced) {
+		int size;
+
+		size = sctp_ssnmap_size(map->in.len, map->out.len);
+		if (size <= MAX_KMALLOC_SIZE)
+			kfree(map);
+		else
+			free_pages((unsigned long)map, get_order(size));
+		SCTP_DBG_OBJCNT_DEC(ssnmap);
+	}
+}

net/sctp/sysctl.c

@@ -0,0 +1,251 @@
+/* SCTP kernel reference Implementation
+ * (C) Copyright IBM Corp. 2002, 2004
+ * Copyright (c) 2002 Intel Corp.
+ *
+ * This file is part of the SCTP kernel reference Implementation
+ *
+ * Sysctl related interfaces for 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 <lksctp-developers@lists.sourceforge.net>
+ *
+ * Or submit a bug report through the following website:
+ *    http://www.sf.net/projects/lksctp
+ *
+ * Written or modified by:
+ *    Mingqin Liu           <liuming@us.ibm.com>
+ *    Jon Grimm             <jgrimm@us.ibm.com>
+ *    Ardelle Fan           <ardelle.fan@intel.com>
+ *    Ryan Layer            <rmlayer@us.ibm.com>
+ *    Sridhar Samudrala     <sri@us.ibm.com>
+ *
+ * Any bugs reported given to us we will try to fix... any fixes shared will
+ * be incorporated into the next SCTP release.
+ */
+
+#include <net/sctp/structs.h>
+#include <linux/sysctl.h>
+
+static ctl_handler sctp_sysctl_jiffies_ms;
+static long rto_timer_min = 1;
+static long rto_timer_max = 86400000; /* One day */
+
+static ctl_table sctp_table[] = {
+	{
+		.ctl_name	= NET_SCTP_RTO_INITIAL,
+		.procname	= "rto_initial",
+		.data		= &sctp_rto_initial,
+		.maxlen		= sizeof(long),
+		.mode		= 0644,
+		.proc_handler	= &proc_doulongvec_ms_jiffies_minmax,
+		.strategy	= &sctp_sysctl_jiffies_ms,
+		.extra1         = &rto_timer_min,
+		.extra2         = &rto_timer_max
+	},
+	{
+		.ctl_name	= NET_SCTP_RTO_MIN,
+		.procname	= "rto_min",
+		.data		= &sctp_rto_min,
+		.maxlen		= sizeof(long),
+		.mode		= 0644,
+		.proc_handler	= &proc_doulongvec_ms_jiffies_minmax,
+		.strategy	= &sctp_sysctl_jiffies_ms,
+		.extra1         = &rto_timer_min,
+		.extra2         = &rto_timer_max
+	},
+	{
+		.ctl_name	= NET_SCTP_RTO_MAX,
+		.procname	= "rto_max",
+		.data		= &sctp_rto_max,
+		.maxlen		= sizeof(long),
+		.mode		= 0644,
+		.proc_handler	= &proc_doulongvec_ms_jiffies_minmax,
+		.strategy	= &sctp_sysctl_jiffies_ms,
+		.extra1         = &rto_timer_min,
+		.extra2         = &rto_timer_max
+	},
+	{
+		.ctl_name	= NET_SCTP_VALID_COOKIE_LIFE,
+		.procname	= "valid_cookie_life",
+		.data		= &sctp_valid_cookie_life,
+		.maxlen		= sizeof(long),
+		.mode		= 0644,
+		.proc_handler	= &proc_doulongvec_ms_jiffies_minmax,
+		.strategy	= &sctp_sysctl_jiffies_ms,
+		.extra1         = &rto_timer_min,
+		.extra2         = &rto_timer_max
+	},
+	{
+		.ctl_name	= NET_SCTP_MAX_BURST,
+		.procname	= "max_burst",
+		.data		= &sctp_max_burst,
+		.maxlen		= sizeof(int),
+		.mode		= 0644,
+		.proc_handler	= &proc_dointvec
+	},
+	{
+		.ctl_name	= NET_SCTP_ASSOCIATION_MAX_RETRANS,
+		.procname	= "association_max_retrans",
+		.data		= &sctp_max_retrans_association,
+		.maxlen		= sizeof(int),
+		.mode		= 0644,
+		.proc_handler	= &proc_dointvec
+	},
+	{
+		.ctl_name	= NET_SCTP_PATH_MAX_RETRANS,
+		.procname	= "path_max_retrans",
+		.data		= &sctp_max_retrans_path,
+		.maxlen		= sizeof(int),
+		.mode		= 0644,
+		.proc_handler	= &proc_dointvec
+	},
+	{
+		.ctl_name	= NET_SCTP_MAX_INIT_RETRANSMITS,
+		.procname	= "max_init_retransmits",
+		.data		= &sctp_max_retrans_init,
+		.maxlen		= sizeof(int),
+		.mode		= 0644,
+		.proc_handler	= &proc_dointvec
+	},
+	{
+		.ctl_name	= NET_SCTP_HB_INTERVAL,
+		.procname	= "hb_interval",
+		.data		= &sctp_hb_interval,
+		.maxlen		= sizeof(long),
+		.mode		= 0644,
+		.proc_handler	= &proc_doulongvec_ms_jiffies_minmax,
+		.strategy	= &sctp_sysctl_jiffies_ms,
+		.extra1         = &rto_timer_min,
+		.extra2         = &rto_timer_max
+	},
+	{
+		.ctl_name	= NET_SCTP_PRESERVE_ENABLE,
+		.procname	= "cookie_preserve_enable",
+		.data		= &sctp_cookie_preserve_enable,
+		.maxlen		= sizeof(long),
+		.mode		= 0644,
+		.proc_handler	= &proc_doulongvec_ms_jiffies_minmax,
+		.strategy	= &sctp_sysctl_jiffies_ms,
+		.extra1         = &rto_timer_min,
+		.extra2         = &rto_timer_max
+	},
+	{
+		.ctl_name	= NET_SCTP_RTO_ALPHA,
+		.procname	= "rto_alpha_exp_divisor",
+		.data		= &sctp_rto_alpha,
+		.maxlen		= sizeof(int),
+		.mode		= 0644,
+		.proc_handler	= &proc_dointvec
+	},
+	{
+		.ctl_name	= NET_SCTP_RTO_BETA,
+		.procname	= "rto_beta_exp_divisor",
+		.data		= &sctp_rto_beta,
+		.maxlen		= sizeof(int),
+		.mode		= 0644,
+		.proc_handler	= &proc_dointvec
+	},
+	{
+		.ctl_name	= NET_SCTP_ADDIP_ENABLE,
+		.procname	= "addip_enable",
+		.data		= &sctp_addip_enable,
+		.maxlen		= sizeof(int),
+		.mode		= 0644,
+		.proc_handler	= &proc_dointvec
+	},
+	{
+		.ctl_name	= NET_SCTP_PRSCTP_ENABLE,
+		.procname	= "prsctp_enable",
+		.data		= &sctp_prsctp_enable,
+		.maxlen		= sizeof(int),
+		.mode		= 0644,
+		.proc_handler	= &proc_dointvec
+	},
+	{ .ctl_name = 0 }
+};
+
+static ctl_table sctp_net_table[] = {
+	{
+		.ctl_name	= NET_SCTP,
+		.procname	= "sctp",
+		.mode		= 0555,
+		.child		= sctp_table
+	},
+	{ .ctl_name = 0 }
+};
+
+static ctl_table sctp_root_table[] = {
+	{
+		.ctl_name	= CTL_NET,
+		.procname	= "net",
+		.mode		= 0555,
+		.child		= sctp_net_table
+	},
+	{ .ctl_name = 0 }
+};
+
+static struct ctl_table_header * sctp_sysctl_header;
+
+/* Sysctl registration.  */
+void sctp_sysctl_register(void)
+{
+	sctp_sysctl_header = register_sysctl_table(sctp_root_table, 0);
+}
+
+/* Sysctl deregistration.  */
+void sctp_sysctl_unregister(void)
+{
+	unregister_sysctl_table(sctp_sysctl_header);
+}
+
+/* Strategy function to convert jiffies to milliseconds.  */
+static int sctp_sysctl_jiffies_ms(ctl_table *table, int __user *name, int nlen,
+		void __user *oldval, size_t __user *oldlenp,
+		void __user *newval, size_t newlen, void **context) {
+
+	if (oldval) {
+		size_t olen;
+
+		if (oldlenp) {
+			if (get_user(olen, oldlenp))
+				return -EFAULT;
+
+			if (olen != sizeof (int))
+				return -EINVAL;
+		}
+		if (put_user((*(int *)(table->data) * 1000) / HZ,
+			(int __user *)oldval) ||
+		    (oldlenp && put_user(sizeof (int), oldlenp)))
+			return -EFAULT;
+	}
+	if (newval && newlen) {
+		int new;
+
+		if (newlen != sizeof (int))
+			return -EINVAL;
+
+		if (get_user(new, (int __user *)newval))
+			return -EFAULT;
+
+		*(int *)(table->data) = (new * HZ) / 1000;
+	}
+	return 1;
+}

net/sctp/transport.c

@@ -0,0 +1,514 @@
+/* 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 La Monte H.P. Yarroll
+ *
+ * This file is part of the SCTP kernel reference Implementation
+ *
+ * This module provides the abstraction for an SCTP tranport representing
+ * a remote transport address.  For local transport addresses, we just use
+ * union sctp_addr.
+ *
+ * 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 <lksctp-developers@lists.sourceforge.net>
+ *
+ * Or submit a bug report through the following website:
+ *    http://www.sf.net/projects/lksctp
+ *
+ * Written or modified by:
+ *    La Monte H.P. Yarroll <piggy@acm.org>
+ *    Karl Knutson          <karl@athena.chicago.il.us>
+ *    Jon Grimm             <jgrimm@us.ibm.com>
+ *    Xingang Guo           <xingang.guo@intel.com>
+ *    Hui Huang             <hui.huang@nokia.com>
+ *    Sridhar Samudrala	    <sri@us.ibm.com>
+ *    Ardelle Fan	    <ardelle.fan@intel.com>
+ *
+ * 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 <net/sctp/sctp.h>
+#include <net/sctp/sm.h>
+
+/* 1st Level Abstractions.  */
+
+/* Initialize a new transport from provided memory.  */
+static struct sctp_transport *sctp_transport_init(struct sctp_transport *peer,
+						  const union sctp_addr *addr,
+						  int gfp)
+{
+	/* Copy in the address.  */
+	peer->ipaddr = *addr;
+	peer->af_specific = sctp_get_af_specific(addr->sa.sa_family);
+	peer->asoc = NULL;
+
+	peer->dst = NULL;
+	memset(&peer->saddr, 0, sizeof(union sctp_addr));
+
+	/* From 6.3.1 RTO Calculation:
+	 *
+	 * C1) Until an RTT measurement has been made for a packet sent to the
+	 * given destination transport address, set RTO to the protocol
+	 * parameter 'RTO.Initial'.
+	 */
+	peer->rtt = 0;
+	peer->rto = sctp_rto_initial;
+	peer->rttvar = 0;
+	peer->srtt = 0;
+	peer->rto_pending = 0;
+
+	peer->last_time_heard = jiffies;
+	peer->last_time_used = jiffies;
+	peer->last_time_ecne_reduced = jiffies;
+
+	peer->active = SCTP_ACTIVE;
+	peer->hb_allowed = 0;
+
+	/* Initialize the default path max_retrans.  */
+	peer->max_retrans = sctp_max_retrans_path;
+	peer->error_count = 0;
+
+	INIT_LIST_HEAD(&peer->transmitted);
+	INIT_LIST_HEAD(&peer->send_ready);
+	INIT_LIST_HEAD(&peer->transports);
+
+	/* Set up the retransmission timer.  */
+	init_timer(&peer->T3_rtx_timer);
+	peer->T3_rtx_timer.function = sctp_generate_t3_rtx_event;
+	peer->T3_rtx_timer.data = (unsigned long)peer;
+
+	/* Set up the heartbeat timer. */
+	init_timer(&peer->hb_timer);
+	peer->hb_interval = SCTP_DEFAULT_TIMEOUT_HEARTBEAT;
+	peer->hb_timer.function = sctp_generate_heartbeat_event;
+	peer->hb_timer.data = (unsigned long)peer;
+
+	atomic_set(&peer->refcnt, 1);
+	peer->dead = 0;
+
+	peer->malloced = 0;
+
+	/* Initialize the state information for SFR-CACC */
+	peer->cacc.changeover_active = 0;
+	peer->cacc.cycling_changeover = 0;
+	peer->cacc.next_tsn_at_change = 0;
+	peer->cacc.cacc_saw_newack = 0;
+
+	return peer;
+}
+
+/* Allocate and initialize a new transport.  */
+struct sctp_transport *sctp_transport_new(const union sctp_addr *addr, int gfp)
+{
+        struct sctp_transport *transport;
+
+        transport = t_new(struct sctp_transport, gfp);
+	if (!transport)
+		goto fail;
+
+	if (!sctp_transport_init(transport, addr, gfp))
+		goto fail_init;
+
+	transport->malloced = 1;
+	SCTP_DBG_OBJCNT_INC(transport);
+
+	return transport;
+
+fail_init:
+	kfree(transport);
+
+fail:
+	return NULL;
+}
+
+/* This transport is no longer needed.  Free up if possible, or
+ * delay until it last reference count.
+ */
+void sctp_transport_free(struct sctp_transport *transport)
+{
+	transport->dead = 1;
+
+	/* Try to delete the heartbeat timer.  */
+	if (del_timer(&transport->hb_timer))
+		sctp_transport_put(transport);
+
+	/* Delete the T3_rtx timer if it's active.
+	 * There is no point in not doing this now and letting
+	 * structure hang around in memory since we know
+	 * the tranport is going away.
+	 */
+	if (timer_pending(&transport->T3_rtx_timer) &&
+	    del_timer(&transport->T3_rtx_timer))
+		sctp_transport_put(transport);
+
+
+	sctp_transport_put(transport);
+}
+
+/* Destroy the transport data structure.
+ * Assumes there are no more users of this structure.
+ */
+static void sctp_transport_destroy(struct sctp_transport *transport)
+{
+	SCTP_ASSERT(transport->dead, "Transport is not dead", return);
+
+	if (transport->asoc)
+		sctp_association_put(transport->asoc);
+
+        sctp_packet_free(&transport->packet);
+
+	dst_release(transport->dst);
+	kfree(transport);
+	SCTP_DBG_OBJCNT_DEC(transport);
+}
+
+/* Start T3_rtx timer if it is not already running and update the heartbeat
+ * timer.  This routine is called every time a DATA chunk is sent.
+ */
+void sctp_transport_reset_timers(struct sctp_transport *transport)
+{
+	/* RFC 2960 6.3.2 Retransmission Timer Rules
+	 *
+	 * R1) Every time a DATA chunk is sent to any address(including a
+	 * retransmission), if the T3-rtx timer of that address is not running
+	 * start it running so that it will expire after the RTO of that
+	 * address.
+	 */
+
+	if (!timer_pending(&transport->T3_rtx_timer))
+		if (!mod_timer(&transport->T3_rtx_timer,
+			       jiffies + transport->rto))
+			sctp_transport_hold(transport);
+
+	/* When a data chunk is sent, reset the heartbeat interval.  */
+	if (!mod_timer(&transport->hb_timer,
+		       sctp_transport_timeout(transport)))
+	    sctp_transport_hold(transport);
+}
+
+/* This transport has been assigned to an association.
+ * Initialize fields from the association or from the sock itself.
+ * Register the reference count in the association.
+ */
+void sctp_transport_set_owner(struct sctp_transport *transport,
+			      struct sctp_association *asoc)
+{
+	transport->asoc = asoc;
+	sctp_association_hold(asoc);
+}
+
+/* Initialize the pmtu of a transport. */
+void sctp_transport_pmtu(struct sctp_transport *transport)
+{
+	struct dst_entry *dst;
+
+	dst = transport->af_specific->get_dst(NULL, &transport->ipaddr, NULL);
+
+	if (dst) {
+		transport->pmtu = dst_mtu(dst);
+		dst_release(dst);
+	} else
+		transport->pmtu = SCTP_DEFAULT_MAXSEGMENT;
+}
+
+/* Caches the dst entry and source address for a transport's destination
+ * address.
+ */
+void sctp_transport_route(struct sctp_transport *transport,
+			  union sctp_addr *saddr, struct sctp_sock *opt)
+{
+	struct sctp_association *asoc = transport->asoc;
+	struct sctp_af *af = transport->af_specific;
+	union sctp_addr *daddr = &transport->ipaddr;
+	struct dst_entry *dst;
+
+	dst = af->get_dst(asoc, daddr, saddr);
+
+	if (saddr)
+		memcpy(&transport->saddr, saddr, sizeof(union sctp_addr));
+	else
+		af->get_saddr(asoc, dst, daddr, &transport->saddr);
+
+	transport->dst = dst;
+	if (dst) {
+		transport->pmtu = dst_mtu(dst);
+
+		/* Initialize sk->sk_rcv_saddr, if the transport is the
+		 * association's active path for getsockname().
+		 */ 
+		if (asoc && (transport == asoc->peer.active_path))
+			af->to_sk_saddr(&transport->saddr, asoc->base.sk);
+	} else
+		transport->pmtu = SCTP_DEFAULT_MAXSEGMENT;
+}
+
+/* Hold a reference to a transport.  */
+void sctp_transport_hold(struct sctp_transport *transport)
+{
+	atomic_inc(&transport->refcnt);
+}
+
+/* Release a reference to a transport and clean up
+ * if there are no more references.
+ */
+void sctp_transport_put(struct sctp_transport *transport)
+{
+	if (atomic_dec_and_test(&transport->refcnt))
+		sctp_transport_destroy(transport);
+}
+
+/* Update transport's RTO based on the newly calculated RTT. */
+void sctp_transport_update_rto(struct sctp_transport *tp, __u32 rtt)
+{
+	/* Check for valid transport.  */
+	SCTP_ASSERT(tp, "NULL transport", return);
+
+	/* We should not be doing any RTO updates unless rto_pending is set.  */
+	SCTP_ASSERT(tp->rto_pending, "rto_pending not set", return);
+
+	if (tp->rttvar || tp->srtt) {
+		/* 6.3.1 C3) When a new RTT measurement R' is made, set
+		 * RTTVAR <- (1 - RTO.Beta) * RTTVAR + RTO.Beta * |SRTT - R'|
+		 * SRTT <- (1 - RTO.Alpha) * SRTT + RTO.Alpha * R'
+		 */
+
+		/* Note:  The above algorithm has been rewritten to
+		 * express rto_beta and rto_alpha as inverse powers
+		 * of two.
+		 * For example, assuming the default value of RTO.Alpha of
+		 * 1/8, rto_alpha would be expressed as 3.
+		 */
+		tp->rttvar = tp->rttvar - (tp->rttvar >> sctp_rto_beta)
+			+ ((abs(tp->srtt - rtt)) >> sctp_rto_beta);
+		tp->srtt = tp->srtt - (tp->srtt >> sctp_rto_alpha)
+			+ (rtt >> sctp_rto_alpha);
+	} else {
+		/* 6.3.1 C2) When the first RTT measurement R is made, set
+		 * SRTT <- R, RTTVAR <- R/2.
+		 */
+		tp->srtt = rtt;
+		tp->rttvar = rtt >> 1;
+	}
+
+	/* 6.3.1 G1) Whenever RTTVAR is computed, if RTTVAR = 0, then
+	 * adjust RTTVAR <- G, where G is the CLOCK GRANULARITY.
+	 */
+	if (tp->rttvar == 0)
+		tp->rttvar = SCTP_CLOCK_GRANULARITY;
+
+	/* 6.3.1 C3) After the computation, update RTO <- SRTT + 4 * RTTVAR. */
+	tp->rto = tp->srtt + (tp->rttvar << 2);
+
+	/* 6.3.1 C6) Whenever RTO is computed, if it is less than RTO.Min
+	 * seconds then it is rounded up to RTO.Min seconds.
+	 */
+	if (tp->rto < tp->asoc->rto_min)
+		tp->rto = tp->asoc->rto_min;
+
+	/* 6.3.1 C7) A maximum value may be placed on RTO provided it is
+	 * at least RTO.max seconds.
+	 */
+	if (tp->rto > tp->asoc->rto_max)
+		tp->rto = tp->asoc->rto_max;
+
+	tp->rtt = rtt;
+
+	/* Reset rto_pending so that a new RTT measurement is started when a
+	 * new data chunk is sent.
+	 */
+	tp->rto_pending = 0;
+
+	SCTP_DEBUG_PRINTK("%s: transport: %p, rtt: %d, srtt: %d "
+			  "rttvar: %d, rto: %d\n", __FUNCTION__,
+			  tp, rtt, tp->srtt, tp->rttvar, tp->rto);
+}
+
+/* This routine updates the transport's cwnd and partial_bytes_acked
+ * parameters based on the bytes acked in the received SACK.
+ */
+void sctp_transport_raise_cwnd(struct sctp_transport *transport,
+			       __u32 sack_ctsn, __u32 bytes_acked)
+{
+	__u32 cwnd, ssthresh, flight_size, pba, pmtu;
+
+	cwnd = transport->cwnd;
+	flight_size = transport->flight_size;
+
+	/* The appropriate cwnd increase algorithm is performed if, and only
+	 * if the cumulative TSN has advanced and the congestion window is
+	 * being fully utilized.
+	 */
+	if ((transport->asoc->ctsn_ack_point >= sack_ctsn) ||
+	    (flight_size < cwnd))
+		return;
+
+	ssthresh = transport->ssthresh;
+	pba = transport->partial_bytes_acked;
+	pmtu = transport->asoc->pmtu;
+
+	if (cwnd <= ssthresh) {
+		/* RFC 2960 7.2.1, sctpimpguide-05 2.14.2 When cwnd is less
+		 * than or equal to ssthresh an SCTP endpoint MUST use the
+		 * slow start algorithm to increase cwnd only if the current
+		 * congestion window is being fully utilized and an incoming
+		 * SACK advances the Cumulative TSN Ack Point. Only when these
+		 * two conditions are met can the cwnd be increased otherwise
+		 * the cwnd MUST not be increased. If these conditions are met
+		 * then cwnd MUST be increased by at most the lesser of
+		 * 1) the total size of the previously outstanding DATA
+		 * chunk(s) acknowledged, and 2) the destination's path MTU.
+		 */
+		if (bytes_acked > pmtu)
+			cwnd += pmtu;
+		else
+			cwnd += bytes_acked;
+		SCTP_DEBUG_PRINTK("%s: SLOW START: transport: %p, "
+				  "bytes_acked: %d, cwnd: %d, ssthresh: %d, "
+				  "flight_size: %d, pba: %d\n",
+				  __FUNCTION__,
+				  transport, bytes_acked, cwnd,
+				  ssthresh, flight_size, pba);
+	} else {
+		/* RFC 2960 7.2.2 Whenever cwnd is greater than ssthresh,
+		 * upon each SACK arrival that advances the Cumulative TSN Ack
+		 * Point, increase partial_bytes_acked by the total number of
+		 * bytes of all new chunks acknowledged in that SACK including
+		 * chunks acknowledged by the new Cumulative TSN Ack and by
+		 * Gap Ack Blocks.
+		 *
+		 * When partial_bytes_acked is equal to or greater than cwnd
+		 * and before the arrival of the SACK the sender had cwnd or
+		 * more bytes of data outstanding (i.e., before arrival of the
+		 * SACK, flightsize was greater than or equal to cwnd),
+		 * increase cwnd by MTU, and reset partial_bytes_acked to
+		 * (partial_bytes_acked - cwnd).
+		 */
+		pba += bytes_acked;
+		if (pba >= cwnd) {
+			cwnd += pmtu;
+			pba = ((cwnd < pba) ? (pba - cwnd) : 0);
+		}
+		SCTP_DEBUG_PRINTK("%s: CONGESTION AVOIDANCE: "
+				  "transport: %p, bytes_acked: %d, cwnd: %d, "
+				  "ssthresh: %d, flight_size: %d, pba: %d\n",
+				  __FUNCTION__,
+				  transport, bytes_acked, cwnd,
+				  ssthresh, flight_size, pba);
+	}
+
+	transport->cwnd = cwnd;
+	transport->partial_bytes_acked = pba;
+}
+
+/* This routine is used to lower the transport's cwnd when congestion is
+ * detected.
+ */
+void sctp_transport_lower_cwnd(struct sctp_transport *transport,
+			       sctp_lower_cwnd_t reason)
+{
+	switch (reason) {
+	case SCTP_LOWER_CWND_T3_RTX:
+		/* RFC 2960 Section 7.2.3, sctpimpguide
+		 * When the T3-rtx timer expires on an address, SCTP should
+		 * perform slow start by:
+		 *      ssthresh = max(cwnd/2, 4*MTU)
+		 *      cwnd = 1*MTU
+		 *      partial_bytes_acked = 0
+		 */
+		transport->ssthresh = max(transport->cwnd/2,
+					  4*transport->asoc->pmtu);
+		transport->cwnd = transport->asoc->pmtu;
+		break;
+
+	case SCTP_LOWER_CWND_FAST_RTX:
+		/* RFC 2960 7.2.4 Adjust the ssthresh and cwnd of the
+		 * destination address(es) to which the missing DATA chunks
+		 * were last sent, according to the formula described in
+		 * Section 7.2.3.
+	 	 *
+	 	 * RFC 2960 7.2.3, sctpimpguide Upon detection of packet
+		 * losses from SACK (see Section 7.2.4), An endpoint
+		 * should do the following:
+		 *      ssthresh = max(cwnd/2, 4*MTU)
+		 *      cwnd = ssthresh
+		 *      partial_bytes_acked = 0
+		 */
+		transport->ssthresh = max(transport->cwnd/2,
+					  4*transport->asoc->pmtu);
+		transport->cwnd = transport->ssthresh;
+		break;
+
+	case SCTP_LOWER_CWND_ECNE:
+		/* RFC 2481 Section 6.1.2.
+		 * If the sender receives an ECN-Echo ACK packet
+		 * then the sender knows that congestion was encountered in the
+		 * network on the path from the sender to the receiver. The
+		 * indication of congestion should be treated just as a
+		 * congestion loss in non-ECN Capable TCP. That is, the TCP
+		 * source halves the congestion window "cwnd" and reduces the
+		 * slow start threshold "ssthresh".
+		 * A critical condition is that TCP does not react to
+		 * congestion indications more than once every window of
+		 * data (or more loosely more than once every round-trip time).
+		 */
+		if ((jiffies - transport->last_time_ecne_reduced) >
+		    transport->rtt) {
+			transport->ssthresh = max(transport->cwnd/2,
+					  	  4*transport->asoc->pmtu);
+			transport->cwnd = transport->ssthresh;
+			transport->last_time_ecne_reduced = jiffies;
+		}
+		break;
+
+	case SCTP_LOWER_CWND_INACTIVE:
+		/* RFC 2960 Section 7.2.1, sctpimpguide
+		 * When the endpoint does not transmit data on a given
+		 * transport address, the cwnd of the transport address
+		 * should be adjusted to max(cwnd/2, 4*MTU) per RTO.
+		 * NOTE: Although the draft recommends that this check needs
+		 * to be done every RTO interval, we do it every hearbeat
+		 * interval.
+		 */
+		if ((jiffies - transport->last_time_used) > transport->rto)
+			transport->cwnd = max(transport->cwnd/2,
+						 4*transport->asoc->pmtu);
+		break;
+	};
+
+	transport->partial_bytes_acked = 0;
+	SCTP_DEBUG_PRINTK("%s: transport: %p reason: %d cwnd: "
+			  "%d ssthresh: %d\n", __FUNCTION__,
+			  transport, reason,
+			  transport->cwnd, transport->ssthresh);
+}
+
+/* What is the next timeout value for this transport? */
+unsigned long sctp_transport_timeout(struct sctp_transport *t)
+{
+	unsigned long timeout;
+	timeout = t->hb_interval + t->rto + sctp_jitter(t->rto);
+	timeout += jiffies;
+	return timeout;
+}

net/sctp/tsnmap.c

@@ -0,0 +1,417 @@
+/* SCTP kernel reference Implementation
+ * (C) Copyright IBM Corp. 2001, 2004
+ * Copyright (c) 1999-2000 Cisco, Inc.
+ * Copyright (c) 1999-2001 Motorola, Inc.
+ * Copyright (c) 2001 Intel Corp.
+ *
+ * This file is part of the SCTP kernel reference Implementation
+ *
+ * These functions manipulate sctp tsn mapping array.
+ *
+ * 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 <lksctp-developers@lists.sourceforge.net>
+ *
+ * Or submit a bug report through the following website:
+ *    http://www.sf.net/projects/lksctp
+ *
+ * Written or modified by:
+ *    La Monte H.P. Yarroll <piggy@acm.org>
+ *    Jon Grimm             <jgrimm@us.ibm.com>
+ *    Karl Knutson          <karl@athena.chicago.il.us>
+ *    Sridhar Samudrala     <sri@us.ibm.com>
+ *
+ * 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 <net/sctp/sctp.h>
+#include <net/sctp/sm.h>
+
+static void sctp_tsnmap_update(struct sctp_tsnmap *map);
+static void sctp_tsnmap_find_gap_ack(__u8 *map, __u16 off,
+				     __u16 len, __u16 base,
+				     int *started, __u16 *start,
+				     int *ended, __u16 *end);
+
+/* Initialize a block of memory as a tsnmap.  */
+struct sctp_tsnmap *sctp_tsnmap_init(struct sctp_tsnmap *map, __u16 len,
+				     __u32 initial_tsn)
+{
+	map->tsn_map = map->raw_map;
+	map->overflow_map = map->tsn_map + len;
+	map->len = len;
+
+	/* Clear out a TSN ack status.  */
+	memset(map->tsn_map, 0x00, map->len + map->len);
+
+	/* Keep track of TSNs represented by tsn_map.  */
+	map->base_tsn = initial_tsn;
+	map->overflow_tsn = initial_tsn + map->len;
+	map->cumulative_tsn_ack_point = initial_tsn - 1;
+	map->max_tsn_seen = map->cumulative_tsn_ack_point;
+	map->malloced = 0;
+	map->num_dup_tsns = 0;
+
+	return map;
+}
+
+/* Test the tracking state of this TSN.
+ * Returns:
+ *   0 if the TSN has not yet been seen
+ *  >0 if the TSN has been seen (duplicate)
+ *  <0 if the TSN is invalid (too large to track)
+ */
+int sctp_tsnmap_check(const struct sctp_tsnmap *map, __u32 tsn)
+{
+	__s32 gap;
+	int dup;
+
+	/* Calculate the index into the mapping arrays.  */
+	gap = tsn - map->base_tsn;
+
+	/* Verify that we can hold this TSN.  */
+	if (gap >= (/* base */ map->len + /* overflow */ map->len)) {
+		dup = -1;
+		goto out;
+	}
+
+	/* Honk if we've already seen this TSN.
+	 * We have three cases:
+	 *	1. The TSN is ancient or belongs to a previous tsn_map.
+	 *	2. The TSN is already marked in the tsn_map.
+	 *	3. The TSN is already marked in the tsn_map_overflow.
+	 */
+	if (gap < 0 ||
+	    (gap < map->len && map->tsn_map[gap]) ||
+	    (gap >= map->len && map->overflow_map[gap - map->len]))
+		dup = 1;
+	else
+		dup = 0;
+
+out:
+	return dup;
+}
+
+
+/* Mark this TSN as seen.  */
+void sctp_tsnmap_mark(struct sctp_tsnmap *map, __u32 tsn)
+{
+	__s32 gap;
+
+	/* Vacuously mark any TSN which precedes the map base or
+	 * exceeds the end of the map.
+	 */
+	if (TSN_lt(tsn, map->base_tsn))
+		return;
+	if (!TSN_lt(tsn, map->base_tsn + map->len + map->len))
+		return;
+
+	/* Bump the max.  */
+	if (TSN_lt(map->max_tsn_seen, tsn))
+		map->max_tsn_seen = tsn;
+
+	/* Assert: TSN is in range.  */
+	gap = tsn - map->base_tsn;
+
+	/* Mark the TSN as received.  */
+	if (gap < map->len)
+		map->tsn_map[gap]++;
+	else
+		map->overflow_map[gap - map->len]++;
+
+	/* Go fixup any internal TSN mapping variables including
+	 * cumulative_tsn_ack_point.
+	 */
+	sctp_tsnmap_update(map);
+}
+
+
+/* Initialize a Gap Ack Block iterator from memory being provided.  */
+SCTP_STATIC void sctp_tsnmap_iter_init(const struct sctp_tsnmap *map,
+				       struct sctp_tsnmap_iter *iter)
+{
+	/* Only start looking one past the Cumulative TSN Ack Point.  */
+	iter->start = map->cumulative_tsn_ack_point + 1;
+}
+
+/* Get the next Gap Ack Blocks. Returns 0 if there was not another block
+ * to get.
+ */
+SCTP_STATIC int sctp_tsnmap_next_gap_ack(const struct sctp_tsnmap *map,
+					 struct sctp_tsnmap_iter *iter,
+					 __u16 *start, __u16 *end)
+{
+	int started, ended;
+	__u16 _start, _end, offset;
+
+	/* We haven't found a gap yet.  */
+	started = ended = 0;
+
+	/* If there are no more gap acks possible, get out fast.  */
+	if (TSN_lte(map->max_tsn_seen, iter->start))
+		return 0;
+
+	/* Search the first mapping array.  */
+	if (iter->start - map->base_tsn < map->len) {
+
+		offset = iter->start - map->base_tsn;
+		sctp_tsnmap_find_gap_ack(map->tsn_map, offset, map->len, 0,
+					 &started, &_start, &ended, &_end);
+	}
+
+	/* Do we need to check the overflow map? */
+	if (!ended) {
+		/* Fix up where we'd like to start searching in the
+		 * overflow map.
+		 */
+		if (iter->start - map->base_tsn < map->len)
+			offset = 0;
+		else
+			offset = iter->start - map->base_tsn - map->len;
+
+		/* Search the overflow map.  */
+		sctp_tsnmap_find_gap_ack(map->overflow_map,
+					 offset,
+					 map->len,
+					 map->len,
+					 &started, &_start,
+					 &ended, &_end);
+	}
+
+	/* The Gap Ack Block happens to end at the end of the
+	 * overflow map.
+	 */
+	if (started && !ended) {
+		ended++;
+		_end = map->len + map->len - 1;
+	}
+
+	/* If we found a Gap Ack Block, return the start and end and
+	 * bump the iterator forward.
+	 */
+	if (ended) {
+		/* Fix up the start and end based on the
+		 * Cumulative TSN Ack offset into the map.
+		 */
+		int gap = map->cumulative_tsn_ack_point -
+			map->base_tsn;
+
+		*start = _start - gap;
+		*end = _end - gap;
+
+		/* Move the iterator forward.  */
+		iter->start = map->cumulative_tsn_ack_point + *end + 1;
+	}
+
+	return ended;
+}
+
+/* Mark this and any lower TSN as seen.  */
+void sctp_tsnmap_skip(struct sctp_tsnmap *map, __u32 tsn)
+{
+	__s32 gap;
+
+	/* Vacuously mark any TSN which precedes the map base or
+	 * exceeds the end of the map.
+	 */
+	if (TSN_lt(tsn, map->base_tsn))
+		return;
+	if (!TSN_lt(tsn, map->base_tsn + map->len + map->len))
+		return;
+
+	/* Bump the max.  */
+	if (TSN_lt(map->max_tsn_seen, tsn))
+		map->max_tsn_seen = tsn;
+
+	/* Assert: TSN is in range.  */
+	gap = tsn - map->base_tsn + 1;
+
+	/* Mark the TSNs as received.  */
+	if (gap <= map->len)
+		memset(map->tsn_map, 0x01, gap);
+	else {
+		memset(map->tsn_map, 0x01, map->len);
+		memset(map->overflow_map, 0x01, (gap - map->len));
+	}
+
+	/* Go fixup any internal TSN mapping variables including
+	 * cumulative_tsn_ack_point.
+	 */
+	sctp_tsnmap_update(map);
+}
+
+/********************************************************************
+ * 2nd Level Abstractions
+ ********************************************************************/
+
+/* This private helper function updates the tsnmap buffers and
+ * the Cumulative TSN Ack Point.
+ */
+static void sctp_tsnmap_update(struct sctp_tsnmap *map)
+{
+	__u32 ctsn;
+
+	ctsn = map->cumulative_tsn_ack_point;
+	do {
+		ctsn++;
+		if (ctsn == map->overflow_tsn) {
+			/* Now tsn_map must have been all '1's,
+			 * so we swap the map and check the overflow table
+			 */
+        		__u8 *tmp = map->tsn_map;
+			memset(tmp, 0, map->len);
+			map->tsn_map = map->overflow_map;
+			map->overflow_map = tmp;
+
+			/* Update the tsn_map boundaries.  */
+			map->base_tsn += map->len;
+			map->overflow_tsn += map->len;
+		}
+	} while (map->tsn_map[ctsn - map->base_tsn]);
+
+	map->cumulative_tsn_ack_point = ctsn - 1; /* Back up one. */
+}
+
+/* How many data chunks  are we missing from our peer?
+ */
+__u16 sctp_tsnmap_pending(struct sctp_tsnmap *map)
+{
+	__u32 cum_tsn = map->cumulative_tsn_ack_point;
+	__u32 max_tsn = map->max_tsn_seen;
+	__u32 base_tsn = map->base_tsn;
+	__u16 pending_data;
+	__s32 gap, start, end, i;
+
+	pending_data = max_tsn - cum_tsn;
+	gap = max_tsn - base_tsn;
+
+	if (gap <= 0 || gap >= (map->len + map->len))
+		goto out;
+
+	start = ((cum_tsn >= base_tsn) ? (cum_tsn - base_tsn + 1) : 0);
+	end = ((gap > map->len ) ? map->len : gap + 1);
+
+	for (i = start; i < end; i++) {
+		if (map->tsn_map[i])
+			pending_data--;
+	}
+
+	if (gap >= map->len) {
+		start = 0;
+		end = gap - map->len + 1;
+		for (i = start; i < end; i++) {
+			if (map->overflow_map[i])
+				pending_data--;
+		}
+	}
+
+out:
+	return pending_data;
+}
+
+/* This is a private helper for finding Gap Ack Blocks.  It searches a
+ * single array for the start and end of a Gap Ack Block.
+ *
+ * The flags "started" and "ended" tell is if we found the beginning
+ * or (respectively) the end of a Gap Ack Block.
+ */
+static void sctp_tsnmap_find_gap_ack(__u8 *map, __u16 off,
+				     __u16 len, __u16 base,
+				     int *started, __u16 *start,
+				     int *ended, __u16 *end)
+{
+	int i = off;
+
+	/* Look through the entire array, but break out
+	 * early if we have found the end of the Gap Ack Block.
+	 */
+
+	/* Also, stop looking past the maximum TSN seen. */
+
+	/* Look for the start. */
+	if (!(*started)) {
+		for (; i < len; i++) {
+			if (map[i]) {
+				(*started)++;
+				*start = base + i;
+				break;
+			}
+		}
+	}
+
+	/* Look for the end.  */
+	if (*started) {
+		/* We have found the start, let's find the
+		 * end.  If we find the end, break out.
+		 */
+		for (; i < len; i++) {
+			if (!map[i]) {
+				(*ended)++;
+				*end = base + i - 1;
+				break;
+			}
+		}
+	}
+}
+
+/* Renege that we have seen a TSN.  */
+void sctp_tsnmap_renege(struct sctp_tsnmap *map, __u32 tsn)
+{
+	__s32 gap;
+
+	if (TSN_lt(tsn, map->base_tsn))
+		return;
+	if (!TSN_lt(tsn, map->base_tsn + map->len + map->len))
+		return;
+
+	/* Assert: TSN is in range.  */
+	gap = tsn - map->base_tsn;
+
+	/* Pretend we never saw the TSN.  */
+	if (gap < map->len)
+		map->tsn_map[gap] = 0;
+	else
+		map->overflow_map[gap - map->len] = 0;
+}
+
+/* How many gap ack blocks do we have recorded? */
+__u16 sctp_tsnmap_num_gabs(struct sctp_tsnmap *map)
+{
+	struct sctp_tsnmap_iter iter;
+	int gabs = 0;
+
+	/* Refresh the gap ack information. */
+	if (sctp_tsnmap_has_gap(map)) {
+		sctp_tsnmap_iter_init(map, &iter);
+		while (sctp_tsnmap_next_gap_ack(map, &iter,
+						&map->gabs[gabs].start,
+						&map->gabs[gabs].end)) {
+
+			map->gabs[gabs].start = htons(map->gabs[gabs].start);
+			map->gabs[gabs].end = htons(map->gabs[gabs].end);
+			gabs++;
+			if (gabs >= SCTP_MAX_GABS)
+				break;
+		}
+	}
+	return gabs;
+}

net/sctp/ulpevent.c

@@ -0,0 +1,942 @@
+/* SCTP kernel reference 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
+ *
+ * These functions manipulate an sctp event.   The struct ulpevent is used
+ * to carry notifications and data to the ULP (sockets).
+ * 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 <lksctp-developers@lists.sourceforge.net>
+ *
+ * Or submit a bug report through the following website:
+ *    http://www.sf.net/projects/lksctp
+ *
+ * Written or modified by:
+ *    Jon Grimm             <jgrimm@us.ibm.com>
+ *    La Monte H.P. Yarroll <piggy@acm.org>
+ *    Ardelle Fan	    <ardelle.fan@intel.com>
+ *    Sridhar Samudrala     <sri@us.ibm.com>
+ *
+ * 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/skbuff.h>
+#include <net/sctp/structs.h>
+#include <net/sctp/sctp.h>
+#include <net/sctp/sm.h>
+
+static void sctp_ulpevent_receive_data(struct sctp_ulpevent *event,
+				       struct sctp_association *asoc);
+static void sctp_ulpevent_release_data(struct sctp_ulpevent *event);
+
+/* Stub skb destructor.  */
+static void sctp_stub_rfree(struct sk_buff *skb)
+{
+/* WARNING:  This function is just a warning not to use the
+ * skb destructor.  If the skb is shared, we may get the destructor
+ * callback on some processor that does not own the sock_lock.  This
+ * was occuring with PACKET socket applications that were monitoring
+ * our skbs.   We can't take the sock_lock, because we can't risk
+ * recursing if we do really own the sock lock.  Instead, do all
+ * of our rwnd manipulation while we own the sock_lock outright.
+ */
+}
+
+/* Initialize an ULP event from an given skb.  */
+SCTP_STATIC void sctp_ulpevent_init(struct sctp_ulpevent *event, int msg_flags)
+{
+	memset(event, 0, sizeof(struct sctp_ulpevent));
+	event->msg_flags = msg_flags;
+}
+
+/* Create a new sctp_ulpevent.  */
+SCTP_STATIC struct sctp_ulpevent *sctp_ulpevent_new(int size, int msg_flags,
+						    int gfp)
+{
+	struct sctp_ulpevent *event;
+	struct sk_buff *skb;
+
+	skb = alloc_skb(size, gfp);
+	if (!skb)
+		goto fail;
+
+	event = sctp_skb2event(skb);
+	sctp_ulpevent_init(event, msg_flags);
+
+	return event;
+
+fail:
+	return NULL;
+}
+
+/* Is this a MSG_NOTIFICATION?  */
+int sctp_ulpevent_is_notification(const struct sctp_ulpevent *event)
+{
+	return MSG_NOTIFICATION == (event->msg_flags & MSG_NOTIFICATION);
+}
+
+/* Hold the association in case the msg_name needs read out of
+ * the association.
+ */
+static inline void sctp_ulpevent_set_owner(struct sctp_ulpevent *event,
+					   const struct sctp_association *asoc)
+{
+	struct sk_buff *skb;
+
+	/* Cast away the const, as we are just wanting to
+	 * bump the reference count.
+	 */
+	sctp_association_hold((struct sctp_association *)asoc);
+	skb = sctp_event2skb(event);
+	skb->sk = asoc->base.sk;
+	event->asoc = (struct sctp_association *)asoc;
+	skb->destructor = sctp_stub_rfree;
+}
+
+/* A simple destructor to give up the reference to the association. */
+static inline void sctp_ulpevent_release_owner(struct sctp_ulpevent *event)
+{
+	sctp_association_put(event->asoc);
+}
+
+/* Create and initialize an SCTP_ASSOC_CHANGE event.
+ *
+ * 5.3.1.1 SCTP_ASSOC_CHANGE
+ *
+ * Communication notifications inform the ULP that an SCTP association
+ * has either begun or ended. The identifier for a new association is
+ * provided by this notification.
+ *
+ * Note: There is no field checking here.  If a field is unused it will be
+ * zero'd out.
+ */
+struct sctp_ulpevent  *sctp_ulpevent_make_assoc_change(
+	const struct sctp_association *asoc,
+	__u16 flags, __u16 state, __u16 error, __u16 outbound,
+	__u16 inbound, int gfp)
+{
+	struct sctp_ulpevent *event;
+	struct sctp_assoc_change *sac;
+	struct sk_buff *skb;
+
+	event = sctp_ulpevent_new(sizeof(struct sctp_assoc_change),
+				  MSG_NOTIFICATION, gfp);
+	if (!event)
+		goto fail;
+	skb = sctp_event2skb(event);
+	sac = (struct sctp_assoc_change *)
+		skb_put(skb, sizeof(struct sctp_assoc_change));
+
+	/* Socket Extensions for SCTP
+	 * 5.3.1.1 SCTP_ASSOC_CHANGE
+	 *
+	 * sac_type:
+	 * It should be SCTP_ASSOC_CHANGE.
+	 */
+	sac->sac_type = SCTP_ASSOC_CHANGE;
+
+	/* Socket Extensions for SCTP
+	 * 5.3.1.1 SCTP_ASSOC_CHANGE
+	 *
+	 * sac_state: 32 bits (signed integer)
+	 * This field holds one of a number of values that communicate the
+	 * event that happened to the association.
+	 */
+	sac->sac_state = state;
+
+	/* Socket Extensions for SCTP
+	 * 5.3.1.1 SCTP_ASSOC_CHANGE
+	 *
+	 * sac_flags: 16 bits (unsigned integer)
+	 * Currently unused.
+	 */
+	sac->sac_flags = 0;
+
+	/* Socket Extensions for SCTP
+	 * 5.3.1.1 SCTP_ASSOC_CHANGE
+	 *
+	 * sac_length: sizeof (__u32)
+	 * This field is the total length of the notification data, including
+	 * the notification header.
+	 */
+	sac->sac_length = sizeof(struct sctp_assoc_change);
+
+	/* Socket Extensions for SCTP
+	 * 5.3.1.1 SCTP_ASSOC_CHANGE
+	 *
+	 * sac_error:  32 bits (signed integer)
+	 *
+	 * If the state was reached due to a error condition (e.g.
+	 * COMMUNICATION_LOST) any relevant error information is available in
+	 * this field. This corresponds to the protocol error codes defined in
+	 * [SCTP].
+	 */
+	sac->sac_error = error;
+
+	/* Socket Extensions for SCTP
+	 * 5.3.1.1 SCTP_ASSOC_CHANGE
+	 *
+	 * sac_outbound_streams:  16 bits (unsigned integer)
+	 * sac_inbound_streams:  16 bits (unsigned integer)
+	 *
+	 * The maximum number of streams allowed in each direction are
+	 * available in sac_outbound_streams and sac_inbound streams.
+	 */
+	sac->sac_outbound_streams = outbound;
+	sac->sac_inbound_streams = inbound;
+
+	/* Socket Extensions for SCTP
+	 * 5.3.1.1 SCTP_ASSOC_CHANGE
+	 *
+	 * sac_assoc_id: sizeof (sctp_assoc_t)
+	 *
+	 * The association id field, holds the identifier for the association.
+	 * All notifications for a given association have the same association
+	 * identifier.  For TCP style socket, this field is ignored.
+	 */
+	sctp_ulpevent_set_owner(event, asoc);
+	sac->sac_assoc_id = sctp_assoc2id(asoc);
+
+	return event;
+
+fail:
+	return NULL;
+}
+
+/* Create and initialize an SCTP_PEER_ADDR_CHANGE event.
+ *
+ * Socket Extensions for SCTP - draft-01
+ * 5.3.1.2 SCTP_PEER_ADDR_CHANGE
+ *
+ * When a destination address on a multi-homed peer encounters a change
+ * an interface details event is sent.
+ */
+struct sctp_ulpevent *sctp_ulpevent_make_peer_addr_change(
+	const struct sctp_association *asoc,
+	const struct sockaddr_storage *aaddr,
+	int flags, int state, int error, int gfp)
+{
+	struct sctp_ulpevent *event;
+	struct sctp_paddr_change  *spc;
+	struct sk_buff *skb;
+
+	event = sctp_ulpevent_new(sizeof(struct sctp_paddr_change),
+				  MSG_NOTIFICATION, gfp);
+	if (!event)
+		goto fail;
+
+	skb = sctp_event2skb(event);
+	spc = (struct sctp_paddr_change *)
+		skb_put(skb, sizeof(struct sctp_paddr_change));
+
+	/* Sockets API Extensions for SCTP
+	 * Section 5.3.1.2 SCTP_PEER_ADDR_CHANGE
+	 *
+	 * spc_type:
+	 *
+	 *    It should be SCTP_PEER_ADDR_CHANGE.
+	 */
+	spc->spc_type = SCTP_PEER_ADDR_CHANGE;
+
+	/* Sockets API Extensions for SCTP
+	 * Section 5.3.1.2 SCTP_PEER_ADDR_CHANGE
+	 *
+	 * spc_length: sizeof (__u32)
+	 *
+	 * This field is the total length of the notification data, including
+	 * the notification header.
+	 */
+	spc->spc_length = sizeof(struct sctp_paddr_change);
+
+	/* Sockets API Extensions for SCTP
+	 * Section 5.3.1.2 SCTP_PEER_ADDR_CHANGE
+	 *
+	 * spc_flags: 16 bits (unsigned integer)
+	 * Currently unused.
+	 */
+	spc->spc_flags = 0;
+
+	/* Sockets API Extensions for SCTP
+	 * Section 5.3.1.2 SCTP_PEER_ADDR_CHANGE
+	 *
+	 * spc_state:  32 bits (signed integer)
+	 *
+	 * This field holds one of a number of values that communicate the
+	 * event that happened to the address.
+	 */
+	spc->spc_state = state;
+
+	/* Sockets API Extensions for SCTP
+	 * Section 5.3.1.2 SCTP_PEER_ADDR_CHANGE
+	 *
+	 * spc_error:  32 bits (signed integer)
+	 *
+	 * If the state was reached due to any error condition (e.g.
+	 * ADDRESS_UNREACHABLE) any relevant error information is available in
+	 * this field.
+	 */
+	spc->spc_error = error;
+
+	/* Socket Extensions for SCTP
+	 * 5.3.1.1 SCTP_ASSOC_CHANGE
+	 *
+	 * spc_assoc_id: sizeof (sctp_assoc_t)
+	 *
+	 * The association id field, holds the identifier for the association.
+	 * All notifications for a given association have the same association
+	 * identifier.  For TCP style socket, this field is ignored.
+	 */
+	sctp_ulpevent_set_owner(event, asoc);
+	spc->spc_assoc_id = sctp_assoc2id(asoc);
+
+	/* Sockets API Extensions for SCTP
+	 * Section 5.3.1.2 SCTP_PEER_ADDR_CHANGE
+	 *
+	 * spc_aaddr: sizeof (struct sockaddr_storage)
+	 *
+	 * The affected address field, holds the remote peer's address that is
+	 * encountering the change of state.
+	 */
+	memcpy(&spc->spc_aaddr, aaddr, sizeof(struct sockaddr_storage));
+
+	/* Map ipv4 address into v4-mapped-on-v6 address.  */
+	sctp_get_pf_specific(asoc->base.sk->sk_family)->addr_v4map(
+					sctp_sk(asoc->base.sk),
+					(union sctp_addr *)&spc->spc_aaddr);
+
+	return event;
+
+fail:
+	return NULL;
+}
+
+/* Create and initialize an SCTP_REMOTE_ERROR notification.
+ *
+ * Note: This assumes that the chunk->skb->data already points to the
+ * operation error payload.
+ *
+ * Socket Extensions for SCTP - draft-01
+ * 5.3.1.3 SCTP_REMOTE_ERROR
+ *
+ * A remote peer may send an Operational Error message to its peer.
+ * This message indicates a variety of error conditions on an
+ * association. The entire error TLV as it appears on the wire is
+ * included in a SCTP_REMOTE_ERROR event.  Please refer to the SCTP
+ * specification [SCTP] and any extensions for a list of possible
+ * error formats.
+ */
+struct sctp_ulpevent *sctp_ulpevent_make_remote_error(
+	const struct sctp_association *asoc, struct sctp_chunk *chunk,
+	__u16 flags, int gfp)
+{
+	struct sctp_ulpevent *event;
+	struct sctp_remote_error *sre;
+	struct sk_buff *skb;
+	sctp_errhdr_t *ch;
+	__u16 cause;
+	int elen;
+
+	ch = (sctp_errhdr_t *)(chunk->skb->data);
+	cause = ch->cause;
+	elen = WORD_ROUND(ntohs(ch->length)) - sizeof(sctp_errhdr_t);
+
+	/* Pull off the ERROR header.  */
+	skb_pull(chunk->skb, sizeof(sctp_errhdr_t));
+
+	/* Copy the skb to a new skb with room for us to prepend
+	 * notification with.
+	 */
+	skb = skb_copy_expand(chunk->skb, sizeof(struct sctp_remote_error),
+			      0, gfp);
+
+	/* Pull off the rest of the cause TLV from the chunk.  */
+	skb_pull(chunk->skb, elen);
+	if (!skb)
+		goto fail;
+
+	/* Embed the event fields inside the cloned skb.  */
+	event = sctp_skb2event(skb);
+	sctp_ulpevent_init(event, MSG_NOTIFICATION);
+
+	sre = (struct sctp_remote_error *)
+		skb_push(skb, sizeof(struct sctp_remote_error));
+
+	/* Trim the buffer to the right length.  */
+	skb_trim(skb, sizeof(struct sctp_remote_error) + elen);
+
+	/* Socket Extensions for SCTP
+	 * 5.3.1.3 SCTP_REMOTE_ERROR
+	 *
+	 * sre_type:
+	 *   It should be SCTP_REMOTE_ERROR.
+	 */
+	sre->sre_type = SCTP_REMOTE_ERROR;
+
+	/*
+	 * Socket Extensions for SCTP
+	 * 5.3.1.3 SCTP_REMOTE_ERROR
+	 *
+	 * sre_flags: 16 bits (unsigned integer)
+	 *   Currently unused.
+	 */
+	sre->sre_flags = 0;
+
+	/* Socket Extensions for SCTP
+	 * 5.3.1.3 SCTP_REMOTE_ERROR
+	 *
+	 * sre_length: sizeof (__u32)
+	 *
+	 * This field is the total length of the notification data,
+	 * including the notification header.
+	 */
+	sre->sre_length = skb->len;
+
+	/* Socket Extensions for SCTP
+	 * 5.3.1.3 SCTP_REMOTE_ERROR
+	 *
+	 * sre_error: 16 bits (unsigned integer)
+	 * This value represents one of the Operational Error causes defined in
+	 * the SCTP specification, in network byte order.
+	 */
+	sre->sre_error = cause;
+
+	/* Socket Extensions for SCTP
+	 * 5.3.1.3 SCTP_REMOTE_ERROR
+	 *
+	 * sre_assoc_id: sizeof (sctp_assoc_t)
+	 *
+	 * The association id field, holds the identifier for the association.
+	 * All notifications for a given association have the same association
+	 * identifier.  For TCP style socket, this field is ignored.
+	 */
+	sctp_ulpevent_set_owner(event, asoc);
+	sre->sre_assoc_id = sctp_assoc2id(asoc);
+
+	return event;
+
+fail:
+	return NULL;
+}
+
+/* Create and initialize a SCTP_SEND_FAILED notification.
+ *
+ * Socket Extensions for SCTP - draft-01
+ * 5.3.1.4 SCTP_SEND_FAILED
+ */
+struct sctp_ulpevent *sctp_ulpevent_make_send_failed(
+	const struct sctp_association *asoc, struct sctp_chunk *chunk,
+	__u16 flags, __u32 error, int gfp)
+{
+	struct sctp_ulpevent *event;
+	struct sctp_send_failed *ssf;
+	struct sk_buff *skb;
+
+	/* Pull off any padding. */
+	int len = ntohs(chunk->chunk_hdr->length);
+
+	/* Make skb with more room so we can prepend notification.  */
+	skb = skb_copy_expand(chunk->skb,
+			      sizeof(struct sctp_send_failed), /* headroom */
+			      0,                               /* tailroom */
+			      gfp);
+	if (!skb)
+		goto fail;
+
+	/* Pull off the common chunk header and DATA header.  */
+	skb_pull(skb, sizeof(struct sctp_data_chunk));
+	len -= sizeof(struct sctp_data_chunk);
+
+	/* Embed the event fields inside the cloned skb.  */
+	event = sctp_skb2event(skb);
+	sctp_ulpevent_init(event, MSG_NOTIFICATION);
+
+	ssf = (struct sctp_send_failed *)
+		skb_push(skb, sizeof(struct sctp_send_failed));
+
+	/* Socket Extensions for SCTP
+	 * 5.3.1.4 SCTP_SEND_FAILED
+	 *
+	 * ssf_type:
+	 * It should be SCTP_SEND_FAILED.
+	 */
+	ssf->ssf_type = SCTP_SEND_FAILED;
+
+	/* Socket Extensions for SCTP
+	 * 5.3.1.4 SCTP_SEND_FAILED
+	 *
+	 * ssf_flags: 16 bits (unsigned integer)
+	 * The flag value will take one of the following values
+	 *
+	 * SCTP_DATA_UNSENT - Indicates that the data was never put on
+	 *                    the wire.
+	 *
+	 * SCTP_DATA_SENT   - Indicates that the data was put on the wire.
+	 *                    Note that this does not necessarily mean that the
+	 *                    data was (or was not) successfully delivered.
+	 */
+	ssf->ssf_flags = flags;
+
+	/* Socket Extensions for SCTP
+	 * 5.3.1.4 SCTP_SEND_FAILED
+	 *
+	 * ssf_length: sizeof (__u32)
+	 * This field is the total length of the notification data, including
+	 * the notification header.
+	 */
+	ssf->ssf_length = sizeof(struct sctp_send_failed) + len;
+	skb_trim(skb, ssf->ssf_length);
+
+	/* Socket Extensions for SCTP
+	 * 5.3.1.4 SCTP_SEND_FAILED
+	 *
+	 * ssf_error: 16 bits (unsigned integer)
+	 * This value represents the reason why the send failed, and if set,
+	 * will be a SCTP protocol error code as defined in [SCTP] section
+	 * 3.3.10.
+	 */
+	ssf->ssf_error = error;
+
+	/* Socket Extensions for SCTP
+	 * 5.3.1.4 SCTP_SEND_FAILED
+	 *
+	 * ssf_info: sizeof (struct sctp_sndrcvinfo)
+	 * The original send information associated with the undelivered
+	 * message.
+	 */
+	memcpy(&ssf->ssf_info, &chunk->sinfo, sizeof(struct sctp_sndrcvinfo));
+
+	/* Per TSVWG discussion with Randy. Allow the application to
+	 * ressemble a fragmented message.
+	 */
+	ssf->ssf_info.sinfo_flags = chunk->chunk_hdr->flags;
+
+	/* Socket Extensions for SCTP
+	 * 5.3.1.4 SCTP_SEND_FAILED
+	 *
+	 * ssf_assoc_id: sizeof (sctp_assoc_t)
+	 * The association id field, sf_assoc_id, holds the identifier for the
+	 * association.  All notifications for a given association have the
+	 * same association identifier.  For TCP style socket, this field is
+	 * ignored.
+	 */
+	sctp_ulpevent_set_owner(event, asoc);
+	ssf->ssf_assoc_id = sctp_assoc2id(asoc);
+	return event;
+
+fail:
+	return NULL;
+}
+
+/* Create and initialize a SCTP_SHUTDOWN_EVENT notification.
+ *
+ * Socket Extensions for SCTP - draft-01
+ * 5.3.1.5 SCTP_SHUTDOWN_EVENT
+ */
+struct sctp_ulpevent *sctp_ulpevent_make_shutdown_event(
+	const struct sctp_association *asoc,
+	__u16 flags, int gfp)
+{
+	struct sctp_ulpevent *event;
+	struct sctp_shutdown_event *sse;
+	struct sk_buff *skb;
+
+	event = sctp_ulpevent_new(sizeof(struct sctp_shutdown_event),
+				  MSG_NOTIFICATION, gfp);
+	if (!event)
+		goto fail;
+
+	skb = sctp_event2skb(event);
+	sse = (struct sctp_shutdown_event *)
+		skb_put(skb, sizeof(struct sctp_shutdown_event));
+
+	/* Socket Extensions for SCTP
+	 * 5.3.1.5 SCTP_SHUTDOWN_EVENT
+	 *
+	 * sse_type
+	 * It should be SCTP_SHUTDOWN_EVENT
+	 */
+	sse->sse_type = SCTP_SHUTDOWN_EVENT;
+
+	/* Socket Extensions for SCTP
+	 * 5.3.1.5 SCTP_SHUTDOWN_EVENT
+	 *
+	 * sse_flags: 16 bits (unsigned integer)
+	 * Currently unused.
+	 */
+	sse->sse_flags = 0;
+
+	/* Socket Extensions for SCTP
+	 * 5.3.1.5 SCTP_SHUTDOWN_EVENT
+	 *
+	 * sse_length: sizeof (__u32)
+	 * This field is the total length of the notification data, including
+	 * the notification header.
+	 */
+	sse->sse_length = sizeof(struct sctp_shutdown_event);
+
+	/* Socket Extensions for SCTP
+	 * 5.3.1.5 SCTP_SHUTDOWN_EVENT
+	 *
+	 * sse_assoc_id: sizeof (sctp_assoc_t)
+	 * The association id field, holds the identifier for the association.
+	 * All notifications for a given association have the same association
+	 * identifier.  For TCP style socket, this field is ignored.
+	 */
+	sctp_ulpevent_set_owner(event, asoc);
+	sse->sse_assoc_id = sctp_assoc2id(asoc);
+
+	return event;
+
+fail:
+	return NULL;
+}
+
+/* Create and initialize a SCTP_ADAPTION_INDICATION notification.
+ *
+ * Socket Extensions for SCTP
+ * 5.3.1.6 SCTP_ADAPTION_INDICATION
+ */
+struct sctp_ulpevent *sctp_ulpevent_make_adaption_indication(
+	const struct sctp_association *asoc, int gfp)
+{
+	struct sctp_ulpevent *event;
+	struct sctp_adaption_event *sai;
+	struct sk_buff *skb;
+
+	event = sctp_ulpevent_new(sizeof(struct sctp_adaption_event),
+				  MSG_NOTIFICATION, gfp);
+	if (!event)
+		goto fail;
+
+	skb = sctp_event2skb(event);
+	sai = (struct sctp_adaption_event *)
+		skb_put(skb, sizeof(struct sctp_adaption_event));
+
+	sai->sai_type = SCTP_ADAPTION_INDICATION;
+	sai->sai_flags = 0;
+	sai->sai_length = sizeof(struct sctp_adaption_event);
+	sai->sai_adaption_ind = asoc->peer.adaption_ind;
+	sctp_ulpevent_set_owner(event, asoc);
+	sai->sai_assoc_id = sctp_assoc2id(asoc);
+
+	return event;
+
+fail:
+	return NULL;
+}
+
+/* A message has been received.  Package this message as a notification
+ * to pass it to the upper layers.  Go ahead and calculate the sndrcvinfo
+ * even if filtered out later.
+ *
+ * Socket Extensions for SCTP
+ * 5.2.2 SCTP Header Information Structure (SCTP_SNDRCV)
+ */
+struct sctp_ulpevent *sctp_ulpevent_make_rcvmsg(struct sctp_association *asoc,
+						struct sctp_chunk *chunk,
+						int gfp)
+{
+	struct sctp_ulpevent *event = NULL;
+	struct sk_buff *skb;
+	size_t padding, len;
+
+	/* Clone the original skb, sharing the data.  */
+	skb = skb_clone(chunk->skb, gfp);
+	if (!skb)
+		goto fail;
+
+	/* First calculate the padding, so we don't inadvertently
+	 * pass up the wrong length to the user.
+	 *
+	 * RFC 2960 - Section 3.2  Chunk Field Descriptions
+	 *
+	 * The total length of a chunk(including Type, Length and Value fields)
+	 * MUST be a multiple of 4 bytes.  If the length of the chunk is not a
+	 * multiple of 4 bytes, the sender MUST pad the chunk with all zero
+	 * bytes and this padding is not included in the chunk length field.
+	 * The sender should never pad with more than 3 bytes.  The receiver
+	 * MUST ignore the padding bytes.
+	 */
+	len = ntohs(chunk->chunk_hdr->length);
+	padding = WORD_ROUND(len) - len;
+
+	/* Fixup cloned skb with just this chunks data.  */
+	skb_trim(skb, chunk->chunk_end - padding - skb->data);
+
+	/* Embed the event fields inside the cloned skb.  */
+	event = sctp_skb2event(skb);
+
+	/* Initialize event with flags 0.  */
+	sctp_ulpevent_init(event, 0);
+
+	sctp_ulpevent_receive_data(event, asoc);
+
+	event->stream = ntohs(chunk->subh.data_hdr->stream);
+	event->ssn = ntohs(chunk->subh.data_hdr->ssn);
+	event->ppid = chunk->subh.data_hdr->ppid;
+	if (chunk->chunk_hdr->flags & SCTP_DATA_UNORDERED) {
+		event->flags |= MSG_UNORDERED;
+		event->cumtsn = sctp_tsnmap_get_ctsn(&asoc->peer.tsn_map);
+	}
+	event->tsn = ntohl(chunk->subh.data_hdr->tsn);
+	event->msg_flags |= chunk->chunk_hdr->flags;
+	event->iif = sctp_chunk_iif(chunk);
+
+fail:
+	return event;
+}
+
+/* Create a partial delivery related event.
+ *
+ * 5.3.1.7 SCTP_PARTIAL_DELIVERY_EVENT
+ *
+ *   When a receiver is engaged in a partial delivery of a
+ *   message this notification will be used to indicate
+ *   various events.
+ */
+struct sctp_ulpevent *sctp_ulpevent_make_pdapi(
+	const struct sctp_association *asoc, __u32 indication, int gfp)
+{
+	struct sctp_ulpevent *event;
+	struct sctp_pdapi_event *pd;
+	struct sk_buff *skb;
+
+	event = sctp_ulpevent_new(sizeof(struct sctp_pdapi_event),
+				  MSG_NOTIFICATION, gfp);
+	if (!event)
+		goto fail;
+
+	skb = sctp_event2skb(event);
+	pd = (struct sctp_pdapi_event *)
+		skb_put(skb, sizeof(struct sctp_pdapi_event));
+
+	/* pdapi_type
+	 *   It should be SCTP_PARTIAL_DELIVERY_EVENT
+	 *
+	 * pdapi_flags: 16 bits (unsigned integer)
+	 *   Currently unused.
+	 */
+	pd->pdapi_type = SCTP_PARTIAL_DELIVERY_EVENT;
+	pd->pdapi_flags = 0;
+
+	/* pdapi_length: 32 bits (unsigned integer)
+	 *
+	 * This field is the total length of the notification data, including
+	 * the notification header.  It will generally be sizeof (struct
+	 * sctp_pdapi_event).
+	 */
+	pd->pdapi_length = sizeof(struct sctp_pdapi_event);
+
+        /*  pdapi_indication: 32 bits (unsigned integer)
+	 *
+	 * This field holds the indication being sent to the application.
+	 */
+	pd->pdapi_indication = indication;
+
+	/*  pdapi_assoc_id: sizeof (sctp_assoc_t)
+	 *
+	 * The association id field, holds the identifier for the association.
+	 */
+	sctp_ulpevent_set_owner(event, asoc);
+	pd->pdapi_assoc_id = sctp_assoc2id(asoc);
+
+	return event;
+fail:
+	return NULL;
+}
+
+/* Return the notification type, assuming this is a notification
+ * event.
+ */
+__u16 sctp_ulpevent_get_notification_type(const struct sctp_ulpevent *event)
+{
+	union sctp_notification *notification;
+	struct sk_buff *skb;
+
+	skb = sctp_event2skb((struct sctp_ulpevent *)event);
+	notification = (union sctp_notification *) skb->data;
+	return notification->sn_header.sn_type;
+}
+
+/* Copy out the sndrcvinfo into a msghdr.  */
+void sctp_ulpevent_read_sndrcvinfo(const struct sctp_ulpevent *event,
+				   struct msghdr *msghdr)
+{
+	struct sctp_sndrcvinfo sinfo;
+
+	if (sctp_ulpevent_is_notification(event))
+		return;
+
+	/* Sockets API Extensions for SCTP
+ 	 * Section 5.2.2 SCTP Header Information Structure (SCTP_SNDRCV)
+ 	 *
+ 	 * sinfo_stream: 16 bits (unsigned integer)
+ 	 *
+ 	 * For recvmsg() the SCTP stack places the message's stream number in
+ 	 * this value.
+ 	*/
+	sinfo.sinfo_stream = event->stream;
+	/* sinfo_ssn: 16 bits (unsigned integer)
+	 *
+	 * For recvmsg() this value contains the stream sequence number that
+	 * the remote endpoint placed in the DATA chunk.  For fragmented
+	 * messages this is the same number for all deliveries of the message
+	 * (if more than one recvmsg() is needed to read the message).
+	 */
+	sinfo.sinfo_ssn = event->ssn;
+	/* sinfo_ppid: 32 bits (unsigned integer)
+	 *
+	 * In recvmsg() this value is
+	 * the same information that was passed by the upper layer in the peer
+	 * application.  Please note that byte order issues are NOT accounted
+	 * for and this information is passed opaquely by the SCTP stack from
+	 * one end to the other.
+	 */
+	sinfo.sinfo_ppid = event->ppid;
+	/* sinfo_flags: 16 bits (unsigned integer)
+	 *
+	 * This field may contain any of the following flags and is composed of
+	 * a bitwise OR of these values.
+	 *
+	 * recvmsg() flags:
+	 *
+	 * MSG_UNORDERED - This flag is present when the message was sent
+	 *                 non-ordered.
+	 */
+	sinfo.sinfo_flags = event->flags;
+	/* sinfo_tsn: 32 bit (unsigned integer)
+	 *
+	 * For the receiving side, this field holds a TSN that was 
+	 * assigned to one of the SCTP Data Chunks.
+	 */
+	sinfo.sinfo_tsn = event->tsn;
+	/* sinfo_cumtsn: 32 bit (unsigned integer)
+	 *
+	 * This field will hold the current cumulative TSN as
+	 * known by the underlying SCTP layer.  Note this field is
+	 * ignored when sending and only valid for a receive
+	 * operation when sinfo_flags are set to MSG_UNORDERED.
+	 */
+	sinfo.sinfo_cumtsn = event->cumtsn;
+	/* sinfo_assoc_id: sizeof (sctp_assoc_t)
+	 *
+	 * The association handle field, sinfo_assoc_id, holds the identifier
+	 * for the association announced in the COMMUNICATION_UP notification.
+	 * All notifications for a given association have the same identifier.
+	 * Ignored for one-to-one style sockets.
+	 */
+	sinfo.sinfo_assoc_id = sctp_assoc2id(event->asoc);
+
+	/* These fields are not used while receiving. */
+	sinfo.sinfo_context = 0;
+	sinfo.sinfo_timetolive = 0;
+
+	put_cmsg(msghdr, IPPROTO_SCTP, SCTP_SNDRCV,
+		 sizeof(struct sctp_sndrcvinfo), (void *)&sinfo);
+}
+
+/* Do accounting for bytes received and hold a reference to the association
+ * for each skb.
+ */
+static void sctp_ulpevent_receive_data(struct sctp_ulpevent *event,
+				       struct sctp_association *asoc)
+{
+	struct sk_buff *skb, *frag;
+
+	skb = sctp_event2skb(event);
+	/* Set the owner and charge rwnd for bytes received.  */
+	sctp_ulpevent_set_owner(event, asoc);
+	sctp_assoc_rwnd_decrease(asoc, skb_headlen(skb));
+
+	if (!skb->data_len)
+		return;
+
+	/* Note:  Not clearing the entire event struct as this is just a
+	 * fragment of the real event.  However, we still need to do rwnd
+	 * accounting.
+	 * In general, the skb passed from IP can have only 1 level of
+	 * fragments. But we allow multiple levels of fragments. 
+	 */
+	for (frag = skb_shinfo(skb)->frag_list; frag; frag = frag->next) {
+		sctp_ulpevent_receive_data(sctp_skb2event(frag), asoc);
+	}
+}
+
+/* Do accounting for bytes just read by user and release the references to
+ * the association.
+ */ 
+static void sctp_ulpevent_release_data(struct sctp_ulpevent *event)
+{
+	struct sk_buff *skb, *frag;
+
+	/* Current stack structures assume that the rcv buffer is
+	 * per socket.   For UDP style sockets this is not true as
+	 * multiple associations may be on a single UDP-style socket.
+	 * Use the local private area of the skb to track the owning
+	 * association.
+	 */
+
+	skb = sctp_event2skb(event);
+	sctp_assoc_rwnd_increase(event->asoc, skb_headlen(skb));
+
+	if (!skb->data_len)
+		goto done;
+
+	/* Don't forget the fragments. */
+	for (frag = skb_shinfo(skb)->frag_list; frag; frag = frag->next) {
+		/* NOTE:  skb_shinfos are recursive. Although IP returns
+		 * skb's with only 1 level of fragments, SCTP reassembly can
+		 * increase the levels.
+		 */
+		sctp_ulpevent_release_data(sctp_skb2event(frag));
+	}
+
+done:
+	sctp_ulpevent_release_owner(event);
+}
+
+/* Free a ulpevent that has an owner.  It includes releasing the reference
+ * to the owner, updating the rwnd in case of a DATA event and freeing the
+ * skb.
+ * See comments in sctp_stub_rfree().
+ */
+void sctp_ulpevent_free(struct sctp_ulpevent *event)
+{
+	if (sctp_ulpevent_is_notification(event))
+		sctp_ulpevent_release_owner(event);
+	else
+		sctp_ulpevent_release_data(event);
+
+	kfree_skb(sctp_event2skb(event));
+}
+
+/* Purge the skb lists holding ulpevents. */
+void sctp_queue_purge_ulpevents(struct sk_buff_head *list)
+{
+	struct sk_buff *skb;
+	while ((skb = skb_dequeue(list)) != NULL)
+		sctp_ulpevent_free(sctp_skb2event(skb));
+}

net/sctp/ulpqueue.c

@@ -0,0 +1,864 @@
+/* SCTP kernel reference 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 abstraction carries sctp events to the ULP (sockets).
+ *
+ * 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 <lksctp-developers@lists.sourceforge.net>
+ *
+ * Or submit a bug report through the following website:
+ *    http://www.sf.net/projects/lksctp
+ *
+ * Written or modified by:
+ *    Jon Grimm             <jgrimm@us.ibm.com>
+ *    La Monte H.P. Yarroll <piggy@acm.org>
+ *    Sridhar Samudrala     <sri@us.ibm.com>
+ *
+ * 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/skbuff.h>
+#include <net/sock.h>
+#include <net/sctp/structs.h>
+#include <net/sctp/sctp.h>
+#include <net/sctp/sm.h>
+
+/* Forward declarations for internal helpers.  */
+static struct sctp_ulpevent * sctp_ulpq_reasm(struct sctp_ulpq *ulpq,
+						struct sctp_ulpevent *);
+static struct sctp_ulpevent * sctp_ulpq_order(struct sctp_ulpq *,
+						struct sctp_ulpevent *);
+
+/* 1st Level Abstractions */
+
+/* Initialize a ULP queue from a block of memory.  */
+struct sctp_ulpq *sctp_ulpq_init(struct sctp_ulpq *ulpq,
+				 struct sctp_association *asoc)
+{
+	memset(ulpq, 0, sizeof(struct sctp_ulpq));
+
+	ulpq->asoc = asoc;
+	skb_queue_head_init(&ulpq->reasm);
+	skb_queue_head_init(&ulpq->lobby);
+	ulpq->pd_mode  = 0;
+	ulpq->malloced = 0;
+
+	return ulpq;
+}
+
+
+/* Flush the reassembly and ordering queues.  */
+static void sctp_ulpq_flush(struct sctp_ulpq *ulpq)
+{
+	struct sk_buff *skb;
+	struct sctp_ulpevent *event;
+
+	while ((skb = __skb_dequeue(&ulpq->lobby)) != NULL) {
+		event = sctp_skb2event(skb);
+		sctp_ulpevent_free(event);
+	}
+
+	while ((skb = __skb_dequeue(&ulpq->reasm)) != NULL) {
+		event = sctp_skb2event(skb);
+		sctp_ulpevent_free(event);
+	}
+
+}
+
+/* Dispose of a ulpqueue.  */
+void sctp_ulpq_free(struct sctp_ulpq *ulpq)
+{
+	sctp_ulpq_flush(ulpq);
+	if (ulpq->malloced)
+		kfree(ulpq);
+}
+
+/* Process an incoming DATA chunk.  */
+int sctp_ulpq_tail_data(struct sctp_ulpq *ulpq, struct sctp_chunk *chunk,
+			int gfp)
+{
+	struct sk_buff_head temp;
+	sctp_data_chunk_t *hdr;
+	struct sctp_ulpevent *event;
+
+	hdr = (sctp_data_chunk_t *) chunk->chunk_hdr;
+
+	/* Create an event from the incoming chunk. */
+	event = sctp_ulpevent_make_rcvmsg(chunk->asoc, chunk, gfp);
+	if (!event)
+		return -ENOMEM;
+
+	/* Do reassembly if needed.  */
+	event = sctp_ulpq_reasm(ulpq, event);
+
+	/* Do ordering if needed.  */
+	if ((event) && (event->msg_flags & MSG_EOR)){
+		/* Create a temporary list to collect chunks on.  */
+		skb_queue_head_init(&temp);
+		__skb_queue_tail(&temp, sctp_event2skb(event));
+
+		event = sctp_ulpq_order(ulpq, event);
+	}
+
+	/* Send event to the ULP.  */
+	if (event)
+		sctp_ulpq_tail_event(ulpq, event);
+
+	return 0;
+}
+
+/* Add a new event for propagation to the ULP.  */
+/* Clear the partial delivery mode for this socket.   Note: This
+ * assumes that no association is currently in partial delivery mode.
+ */
+int sctp_clear_pd(struct sock *sk)
+{
+	struct sctp_sock *sp = sctp_sk(sk);
+
+	sp->pd_mode = 0;
+	if (!skb_queue_empty(&sp->pd_lobby)) {
+		struct list_head *list;
+		sctp_skb_list_tail(&sp->pd_lobby, &sk->sk_receive_queue);
+		list = (struct list_head *)&sctp_sk(sk)->pd_lobby;
+		INIT_LIST_HEAD(list);
+		return 1;
+	}
+	return 0;
+}
+
+/* Clear the pd_mode and restart any pending messages waiting for delivery. */
+static int sctp_ulpq_clear_pd(struct sctp_ulpq *ulpq)
+{
+	ulpq->pd_mode = 0;
+	return sctp_clear_pd(ulpq->asoc->base.sk);
+}
+
+
+
+int sctp_ulpq_tail_event(struct sctp_ulpq *ulpq, struct sctp_ulpevent *event)
+{
+	struct sock *sk = ulpq->asoc->base.sk;
+	struct sk_buff_head *queue;
+	int clear_pd = 0;
+
+	/* If the socket is just going to throw this away, do not
+	 * even try to deliver it.
+	 */
+	if (sock_flag(sk, SOCK_DEAD) || (sk->sk_shutdown & RCV_SHUTDOWN))
+		goto out_free;
+
+	/* Check if the user wishes to receive this event.  */
+	if (!sctp_ulpevent_is_enabled(event, &sctp_sk(sk)->subscribe))
+		goto out_free;
+
+	/* If we are in partial delivery mode, post to the lobby until
+	 * partial delivery is cleared, unless, of course _this_ is
+	 * the association the cause of the partial delivery.
+	 */
+
+	if (!sctp_sk(sk)->pd_mode) {
+		queue = &sk->sk_receive_queue;
+	} else if (ulpq->pd_mode) {
+		if (event->msg_flags & MSG_NOTIFICATION)
+		       	queue = &sctp_sk(sk)->pd_lobby;
+		else {
+			clear_pd = event->msg_flags & MSG_EOR;
+			queue = &sk->sk_receive_queue;
+		}
+	} else
+		queue = &sctp_sk(sk)->pd_lobby;
+
+
+	/* If we are harvesting multiple skbs they will be
+	 * collected on a list.
+	 */
+	if (sctp_event2skb(event)->list)
+		sctp_skb_list_tail(sctp_event2skb(event)->list, queue);
+	else
+		__skb_queue_tail(queue, sctp_event2skb(event));
+
+	/* Did we just complete partial delivery and need to get
+	 * rolling again?  Move pending data to the receive
+	 * queue.
+	 */
+	if (clear_pd)
+		sctp_ulpq_clear_pd(ulpq);
+
+	if (queue == &sk->sk_receive_queue)
+		sk->sk_data_ready(sk, 0);
+	return 1;
+
+out_free:
+	if (sctp_event2skb(event)->list)
+		sctp_queue_purge_ulpevents(sctp_event2skb(event)->list);
+	else
+		sctp_ulpevent_free(event);
+	return 0;
+}
+
+/* 2nd Level Abstractions */
+
+/* Helper function to store chunks that need to be reassembled.  */
+static inline void sctp_ulpq_store_reasm(struct sctp_ulpq *ulpq,
+					 struct sctp_ulpevent *event)
+{
+	struct sk_buff *pos;
+	struct sctp_ulpevent *cevent;
+	__u32 tsn, ctsn;
+
+	tsn = event->tsn;
+
+	/* See if it belongs at the end. */
+	pos = skb_peek_tail(&ulpq->reasm);
+	if (!pos) {
+		__skb_queue_tail(&ulpq->reasm, sctp_event2skb(event));
+		return;
+	}
+
+	/* Short circuit just dropping it at the end. */
+	cevent = sctp_skb2event(pos);
+	ctsn = cevent->tsn;
+	if (TSN_lt(ctsn, tsn)) {
+		__skb_queue_tail(&ulpq->reasm, sctp_event2skb(event));
+		return;
+	}
+
+	/* Find the right place in this list. We store them by TSN.  */
+	skb_queue_walk(&ulpq->reasm, pos) {
+		cevent = sctp_skb2event(pos);
+		ctsn = cevent->tsn;
+
+		if (TSN_lt(tsn, ctsn))
+			break;
+	}
+
+	/* Insert before pos. */
+	__skb_insert(sctp_event2skb(event), pos->prev, pos, &ulpq->reasm);
+
+}
+
+/* Helper function to return an event corresponding to the reassembled
+ * datagram.
+ * This routine creates a re-assembled skb given the first and last skb's
+ * as stored in the reassembly queue. The skb's may be non-linear if the sctp
+ * payload was fragmented on the way and ip had to reassemble them.
+ * We add the rest of skb's to the first skb's fraglist.
+ */
+static struct sctp_ulpevent *sctp_make_reassembled_event(struct sk_buff *f_frag, struct sk_buff *l_frag)
+{
+	struct sk_buff *pos;
+	struct sctp_ulpevent *event;
+	struct sk_buff *pnext, *last;
+	struct sk_buff *list = skb_shinfo(f_frag)->frag_list;
+
+	/* Store the pointer to the 2nd skb */
+	if (f_frag == l_frag)
+		pos = NULL;
+	else
+		pos = f_frag->next;
+
+	/* Get the last skb in the f_frag's frag_list if present. */
+	for (last = list; list; last = list, list = list->next);
+
+	/* Add the list of remaining fragments to the first fragments
+	 * frag_list.
+	 */
+	if (last)
+		last->next = pos;
+	else
+		skb_shinfo(f_frag)->frag_list = pos;
+
+	/* Remove the first fragment from the reassembly queue.  */
+	__skb_unlink(f_frag, f_frag->list);
+	while (pos) {
+
+		pnext = pos->next;
+
+		/* Update the len and data_len fields of the first fragment. */
+		f_frag->len += pos->len;
+		f_frag->data_len += pos->len;
+
+		/* Remove the fragment from the reassembly queue.  */
+		__skb_unlink(pos, pos->list);
+	
+		/* Break if we have reached the last fragment.  */
+		if (pos == l_frag)
+			break;
+		pos->next = pnext;
+		pos = pnext;
+	};
+
+	event = sctp_skb2event(f_frag);
+	SCTP_INC_STATS(SCTP_MIB_REASMUSRMSGS);
+
+	return event;
+}
+
+
+/* Helper function to check if an incoming chunk has filled up the last
+ * missing fragment in a SCTP datagram and return the corresponding event.
+ */
+static inline struct sctp_ulpevent *sctp_ulpq_retrieve_reassembled(struct sctp_ulpq *ulpq)
+{
+	struct sk_buff *pos;
+	struct sctp_ulpevent *cevent;
+	struct sk_buff *first_frag = NULL;
+	__u32 ctsn, next_tsn;
+	struct sctp_ulpevent *retval = NULL;
+
+	/* Initialized to 0 just to avoid compiler warning message.  Will
+	 * never be used with this value. It is referenced only after it
+	 * is set when we find the first fragment of a message.
+	 */
+	next_tsn = 0;
+
+	/* The chunks are held in the reasm queue sorted by TSN.
+	 * Walk through the queue sequentially and look for a sequence of
+	 * fragmented chunks that complete a datagram.
+	 * 'first_frag' and next_tsn are reset when we find a chunk which
+	 * is the first fragment of a datagram. Once these 2 fields are set
+	 * we expect to find the remaining middle fragments and the last
+	 * fragment in order. If not, first_frag is reset to NULL and we
+	 * start the next pass when we find another first fragment.
+	 */
+	skb_queue_walk(&ulpq->reasm, pos) {
+		cevent = sctp_skb2event(pos);
+		ctsn = cevent->tsn;
+
+		switch (cevent->msg_flags & SCTP_DATA_FRAG_MASK) {
+		case SCTP_DATA_FIRST_FRAG:
+			first_frag = pos;
+			next_tsn = ctsn + 1;
+			break;
+
+		case SCTP_DATA_MIDDLE_FRAG:
+			if ((first_frag) && (ctsn == next_tsn))
+				next_tsn++;
+			else
+				first_frag = NULL;
+			break;
+
+		case SCTP_DATA_LAST_FRAG:
+			if (first_frag && (ctsn == next_tsn))
+				goto found;
+			else
+				first_frag = NULL;
+			break;
+		};
+
+	}
+done:
+	return retval;
+found:
+	retval = sctp_make_reassembled_event(first_frag, pos);
+	if (retval)
+		retval->msg_flags |= MSG_EOR;
+	goto done;
+}
+
+/* Retrieve the next set of fragments of a partial message. */
+static inline struct sctp_ulpevent *sctp_ulpq_retrieve_partial(struct sctp_ulpq *ulpq)
+{
+	struct sk_buff *pos, *last_frag, *first_frag;
+	struct sctp_ulpevent *cevent;
+	__u32 ctsn, next_tsn;
+	int is_last;
+	struct sctp_ulpevent *retval;
+
+	/* The chunks are held in the reasm queue sorted by TSN.
+	 * Walk through the queue sequentially and look for the first
+	 * sequence of fragmented chunks.
+	 */
+
+	if (skb_queue_empty(&ulpq->reasm))
+		return NULL;
+
+	last_frag = first_frag = NULL;
+	retval = NULL;
+	next_tsn = 0;
+	is_last = 0;
+
+	skb_queue_walk(&ulpq->reasm, pos) {
+		cevent = sctp_skb2event(pos);
+		ctsn = cevent->tsn;
+
+		switch (cevent->msg_flags & SCTP_DATA_FRAG_MASK) {
+		case SCTP_DATA_MIDDLE_FRAG:
+			if (!first_frag) {
+				first_frag = pos;
+				next_tsn = ctsn + 1;
+				last_frag = pos;
+			} else if (next_tsn == ctsn)
+				next_tsn++;
+			else
+				goto done;
+			break;
+		case SCTP_DATA_LAST_FRAG:
+			if (!first_frag)
+				first_frag = pos;
+			else if (ctsn != next_tsn)
+				goto done;
+			last_frag = pos;
+			is_last = 1;
+			goto done;
+		default:
+			return NULL;
+		};
+	}
+
+	/* We have the reassembled event. There is no need to look
+	 * further.
+	 */
+done:
+	retval = sctp_make_reassembled_event(first_frag, last_frag);
+	if (retval && is_last)
+		retval->msg_flags |= MSG_EOR;
+
+	return retval;
+}
+
+
+/* Helper function to reassemble chunks.  Hold chunks on the reasm queue that
+ * need reassembling.
+ */
+static struct sctp_ulpevent *sctp_ulpq_reasm(struct sctp_ulpq *ulpq,
+						struct sctp_ulpevent *event)
+{
+	struct sctp_ulpevent *retval = NULL;
+
+	/* Check if this is part of a fragmented message.  */
+	if (SCTP_DATA_NOT_FRAG == (event->msg_flags & SCTP_DATA_FRAG_MASK)) {
+		event->msg_flags |= MSG_EOR;
+		return event;
+	}
+
+	sctp_ulpq_store_reasm(ulpq, event);
+	if (!ulpq->pd_mode)
+		retval = sctp_ulpq_retrieve_reassembled(ulpq);
+	else {
+		__u32 ctsn, ctsnap;
+
+		/* Do not even bother unless this is the next tsn to
+		 * be delivered.
+		 */
+		ctsn = event->tsn;
+		ctsnap = sctp_tsnmap_get_ctsn(&ulpq->asoc->peer.tsn_map);
+		if (TSN_lte(ctsn, ctsnap))
+			retval = sctp_ulpq_retrieve_partial(ulpq);
+	}
+
+	return retval;
+}
+
+/* Retrieve the first part (sequential fragments) for partial delivery.  */
+static inline struct sctp_ulpevent *sctp_ulpq_retrieve_first(struct sctp_ulpq *ulpq)
+{
+	struct sk_buff *pos, *last_frag, *first_frag;
+	struct sctp_ulpevent *cevent;
+	__u32 ctsn, next_tsn;
+	struct sctp_ulpevent *retval;
+
+	/* The chunks are held in the reasm queue sorted by TSN.
+	 * Walk through the queue sequentially and look for a sequence of
+	 * fragmented chunks that start a datagram.
+	 */
+
+	if (skb_queue_empty(&ulpq->reasm))
+		return NULL;
+
+	last_frag = first_frag = NULL;
+	retval = NULL;
+	next_tsn = 0;
+
+	skb_queue_walk(&ulpq->reasm, pos) {
+		cevent = sctp_skb2event(pos);
+		ctsn = cevent->tsn;
+
+		switch (cevent->msg_flags & SCTP_DATA_FRAG_MASK) {
+		case SCTP_DATA_FIRST_FRAG:
+			if (!first_frag) {
+				first_frag = pos;
+				next_tsn = ctsn + 1;
+				last_frag = pos;
+			} else
+				goto done;
+			break;
+
+		case SCTP_DATA_MIDDLE_FRAG:
+			if (!first_frag)
+				return NULL;
+			if (ctsn == next_tsn) {
+				next_tsn++;
+				last_frag = pos;
+			} else
+				goto done;
+			break;
+		default:
+			return NULL;
+		};
+	}
+
+	/* We have the reassembled event. There is no need to look
+	 * further.
+	 */
+done:
+	retval = sctp_make_reassembled_event(first_frag, last_frag);
+	return retval;
+}
+
+/* Helper function to gather skbs that have possibly become
+ * ordered by an an incoming chunk.
+ */
+static inline void sctp_ulpq_retrieve_ordered(struct sctp_ulpq *ulpq,
+					      struct sctp_ulpevent *event)
+{
+	struct sk_buff *pos, *tmp;
+	struct sctp_ulpevent *cevent;
+	struct sctp_stream *in;
+	__u16 sid, csid;
+	__u16 ssn, cssn;
+
+	sid = event->stream;
+	ssn = event->ssn;
+	in  = &ulpq->asoc->ssnmap->in;
+
+	/* We are holding the chunks by stream, by SSN.  */
+	sctp_skb_for_each(pos, &ulpq->lobby, tmp) {
+		cevent = (struct sctp_ulpevent *) pos->cb;
+		csid = cevent->stream;
+		cssn = cevent->ssn;
+
+		/* Have we gone too far?  */
+		if (csid > sid)
+			break;
+
+		/* Have we not gone far enough?  */
+		if (csid < sid)
+			continue;
+
+		if (cssn != sctp_ssn_peek(in, sid))
+			break;
+
+		/* Found it, so mark in the ssnmap. */
+		sctp_ssn_next(in, sid);
+
+		__skb_unlink(pos, pos->list);
+
+		/* Attach all gathered skbs to the event.  */
+		__skb_queue_tail(sctp_event2skb(event)->list, pos);
+	}
+}
+
+/* Helper function to store chunks needing ordering.  */
+static inline void sctp_ulpq_store_ordered(struct sctp_ulpq *ulpq,
+					   struct sctp_ulpevent *event)
+{
+	struct sk_buff *pos;
+	struct sctp_ulpevent *cevent;
+	__u16 sid, csid;
+	__u16 ssn, cssn;
+
+	pos = skb_peek_tail(&ulpq->lobby);
+	if (!pos) {
+		__skb_queue_tail(&ulpq->lobby, sctp_event2skb(event));
+		return;
+	}
+
+	sid = event->stream;
+	ssn = event->ssn;
+	
+	cevent = (struct sctp_ulpevent *) pos->cb;
+	csid = cevent->stream;
+	cssn = cevent->ssn;
+	if (sid > csid) {
+		__skb_queue_tail(&ulpq->lobby, sctp_event2skb(event));
+		return;
+	}
+
+	if ((sid == csid) && SSN_lt(cssn, ssn)) {
+		__skb_queue_tail(&ulpq->lobby, sctp_event2skb(event));
+		return;
+	}
+
+	/* Find the right place in this list.  We store them by
+	 * stream ID and then by SSN.
+	 */
+	skb_queue_walk(&ulpq->lobby, pos) {
+		cevent = (struct sctp_ulpevent *) pos->cb;
+		csid = cevent->stream;
+		cssn = cevent->ssn;
+
+		if (csid > sid)
+			break;
+		if (csid == sid && SSN_lt(ssn, cssn))
+			break;
+	}
+
+
+	/* Insert before pos. */
+	__skb_insert(sctp_event2skb(event), pos->prev, pos, &ulpq->lobby);
+
+}
+
+static struct sctp_ulpevent *sctp_ulpq_order(struct sctp_ulpq *ulpq,
+						struct sctp_ulpevent *event)
+{
+	__u16 sid, ssn;
+	struct sctp_stream *in;
+
+	/* Check if this message needs ordering.  */
+	if (SCTP_DATA_UNORDERED & event->msg_flags)
+		return event;
+
+	/* Note: The stream ID must be verified before this routine.  */
+	sid = event->stream;
+	ssn = event->ssn;
+	in  = &ulpq->asoc->ssnmap->in;
+
+	/* Is this the expected SSN for this stream ID?  */
+	if (ssn != sctp_ssn_peek(in, sid)) {
+		/* We've received something out of order, so find where it
+		 * needs to be placed.  We order by stream and then by SSN.
+		 */
+		sctp_ulpq_store_ordered(ulpq, event);
+		return NULL;
+	}
+
+	/* Mark that the next chunk has been found.  */
+	sctp_ssn_next(in, sid);
+
+	/* Go find any other chunks that were waiting for
+	 * ordering.
+	 */
+	sctp_ulpq_retrieve_ordered(ulpq, event);
+
+	return event;
+}
+
+/* Helper function to gather skbs that have possibly become
+ * ordered by forward tsn skipping their dependencies.
+ */
+static inline void sctp_ulpq_reap_ordered(struct sctp_ulpq *ulpq)
+{
+	struct sk_buff *pos, *tmp;
+	struct sctp_ulpevent *cevent;
+	struct sctp_ulpevent *event = NULL;
+	struct sctp_stream *in;
+	struct sk_buff_head temp;
+	__u16 csid, cssn;
+
+	in  = &ulpq->asoc->ssnmap->in;
+
+	/* We are holding the chunks by stream, by SSN.  */
+	sctp_skb_for_each(pos, &ulpq->lobby, tmp) {
+		cevent = (struct sctp_ulpevent *) pos->cb;
+		csid = cevent->stream;
+		cssn = cevent->ssn;
+
+		if (cssn != sctp_ssn_peek(in, csid))
+			break;
+
+		/* Found it, so mark in the ssnmap. */	       
+		sctp_ssn_next(in, csid);
+
+		__skb_unlink(pos, pos->list);
+		if (!event) {						
+			/* Create a temporary list to collect chunks on.  */
+			event = sctp_skb2event(pos);
+			skb_queue_head_init(&temp);
+			__skb_queue_tail(&temp, sctp_event2skb(event));
+		} else {
+			/* Attach all gathered skbs to the event.  */
+			__skb_queue_tail(sctp_event2skb(event)->list, pos);
+		}
+	}
+
+	/* Send event to the ULP.  */
+	if (event)
+		sctp_ulpq_tail_event(ulpq, event);
+}
+
+/* Skip over an SSN. */
+void sctp_ulpq_skip(struct sctp_ulpq *ulpq, __u16 sid, __u16 ssn)
+{
+	struct sctp_stream *in;
+
+	/* Note: The stream ID must be verified before this routine.  */
+	in  = &ulpq->asoc->ssnmap->in;
+
+	/* Is this an old SSN?  If so ignore. */
+	if (SSN_lt(ssn, sctp_ssn_peek(in, sid)))
+		return;
+
+	/* Mark that we are no longer expecting this SSN or lower. */
+	sctp_ssn_skip(in, sid, ssn);
+
+	/* Go find any other chunks that were waiting for
+	 * ordering and deliver them if needed. 
+	 */
+	sctp_ulpq_reap_ordered(ulpq);
+	return;
+}
+
+/* Renege 'needed' bytes from the ordering queue. */
+static __u16 sctp_ulpq_renege_order(struct sctp_ulpq *ulpq, __u16 needed)
+{
+	__u16 freed = 0;
+	__u32 tsn;
+	struct sk_buff *skb;
+	struct sctp_ulpevent *event;
+	struct sctp_tsnmap *tsnmap;
+
+	tsnmap = &ulpq->asoc->peer.tsn_map;
+
+	while ((skb = __skb_dequeue_tail(&ulpq->lobby)) != NULL) {
+		freed += skb_headlen(skb);
+		event = sctp_skb2event(skb);
+		tsn = event->tsn;
+
+		sctp_ulpevent_free(event);
+		sctp_tsnmap_renege(tsnmap, tsn);
+		if (freed >= needed)
+			return freed;
+	}
+
+	return freed;
+}
+
+/* Renege 'needed' bytes from the reassembly queue. */
+static __u16 sctp_ulpq_renege_frags(struct sctp_ulpq *ulpq, __u16 needed)
+{
+	__u16 freed = 0;
+	__u32 tsn;
+	struct sk_buff *skb;
+	struct sctp_ulpevent *event;
+	struct sctp_tsnmap *tsnmap;
+
+	tsnmap = &ulpq->asoc->peer.tsn_map;
+
+	/* Walk backwards through the list, reneges the newest tsns. */
+	while ((skb = __skb_dequeue_tail(&ulpq->reasm)) != NULL) {
+		freed += skb_headlen(skb);
+		event = sctp_skb2event(skb);
+		tsn = event->tsn;
+
+		sctp_ulpevent_free(event);
+		sctp_tsnmap_renege(tsnmap, tsn);
+		if (freed >= needed)
+			return freed;
+	}
+
+	return freed;
+}
+
+/* Partial deliver the first message as there is pressure on rwnd. */
+void sctp_ulpq_partial_delivery(struct sctp_ulpq *ulpq,
+				struct sctp_chunk *chunk, int gfp)
+{
+	struct sctp_ulpevent *event;
+	struct sctp_association *asoc;
+
+	asoc = ulpq->asoc;
+
+	/* Are we already in partial delivery mode?  */
+	if (!sctp_sk(asoc->base.sk)->pd_mode) {
+
+		/* Is partial delivery possible?  */
+		event = sctp_ulpq_retrieve_first(ulpq);
+		/* Send event to the ULP.   */
+		if (event) {
+			sctp_ulpq_tail_event(ulpq, event);
+			sctp_sk(asoc->base.sk)->pd_mode = 1;
+			ulpq->pd_mode = 1;
+			return;
+		}
+	}
+}
+
+/* Renege some packets to make room for an incoming chunk.  */
+void sctp_ulpq_renege(struct sctp_ulpq *ulpq, struct sctp_chunk *chunk,
+		      int gfp)
+{
+	struct sctp_association *asoc;
+	__u16 needed, freed;
+
+	asoc = ulpq->asoc;
+
+	if (chunk) {
+		needed = ntohs(chunk->chunk_hdr->length);
+		needed -= sizeof(sctp_data_chunk_t);
+	} else 
+		needed = SCTP_DEFAULT_MAXWINDOW;
+
+	freed = 0;
+
+	if (skb_queue_empty(&asoc->base.sk->sk_receive_queue)) {
+		freed = sctp_ulpq_renege_order(ulpq, needed);
+		if (freed < needed) {
+			freed += sctp_ulpq_renege_frags(ulpq, needed - freed);
+		}
+	}
+	/* If able to free enough room, accept this chunk. */
+	if (chunk && (freed >= needed)) {
+		__u32 tsn;
+		tsn = ntohl(chunk->subh.data_hdr->tsn);
+		sctp_tsnmap_mark(&asoc->peer.tsn_map, tsn);
+		sctp_ulpq_tail_data(ulpq, chunk, gfp);
+		
+		sctp_ulpq_partial_delivery(ulpq, chunk, gfp);
+	}
+
+	return;
+}
+
+
+
+/* Notify the application if an association is aborted and in
+ * partial delivery mode.  Send up any pending received messages.
+ */
+void sctp_ulpq_abort_pd(struct sctp_ulpq *ulpq, int gfp)
+{
+	struct sctp_ulpevent *ev = NULL;
+	struct sock *sk;
+
+	if (!ulpq->pd_mode)
+		return;
+
+	sk = ulpq->asoc->base.sk;
+	if (sctp_ulpevent_type_enabled(SCTP_PARTIAL_DELIVERY_EVENT,
+				       &sctp_sk(sk)->subscribe))
+		ev = sctp_ulpevent_make_pdapi(ulpq->asoc,
+					      SCTP_PARTIAL_DELIVERY_ABORTED,
+					      gfp);
+	if (ev)
+		__skb_queue_tail(&sk->sk_receive_queue, sctp_event2skb(ev));
+
+	/* If there is data waiting, send it up the socket now. */
+	if (sctp_ulpq_clear_pd(ulpq) || ev)
+		sk->sk_data_ready(sk, 0);
+}