add idl4k kernel firmware version 1.13.0.105

kernel/net/sctp/Kconfig

@@ -0,0 +1,88 @@
+#
+# SCTP configuration
+#
+
+menuconfig IP_SCTP
+	tristate "The SCTP Protocol (EXPERIMENTAL)"
+	depends on INET && EXPERIMENTAL
+	depends on IPV6 || IPV6=n
+	select CRYPTO
+	select CRYPTO_HMAC
+	select CRYPTO_SHA1
+	select CRYPTO_MD5 if SCTP_HMAC_MD5
+	select LIBCRC32C
+	---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.
+
+if IP_SCTP
+
+config SCTP_DBG_MSG
+	bool "SCTP: Debug messages"
+	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 PROC_FS
+	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. This debug information can be viewed by
+	  'cat /proc/net/sctp/sctp_dbg_objcnt'
+
+	  If unsure, say N
+
+choice
+	prompt "SCTP: Cookie HMAC Algorithm"
+	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
+
+endif # IP_SCTP

kernel/net/sctp/Makefile

@@ -0,0 +1,18 @@
+#
+# Makefile for SCTP support code.
+#
+
+obj-$(CONFIG_IP_SCTP) += sctp.o
+
+sctp-y := sm_statetable.o sm_statefuns.o sm_sideeffect.o \
+	  protocol.o endpointola.o associola.o \
+	  transport.o chunk.o sm_make_chunk.o ulpevent.o \
+	  inqueue.o outqueue.o ulpqueue.o command.o \
+	  tsnmap.o bind_addr.o socket.o primitive.o \
+	  output.o input.o debug.o ssnmap.o auth.o
+
+sctp-$(CONFIG_SCTP_DBG_OBJCNT) += objcnt.o
+sctp-$(CONFIG_PROC_FS) += proc.o
+sctp-$(CONFIG_SYSCTL) += sysctl.o
+
+sctp-$(subst m,y,$(CONFIG_IPV6))	+= ipv6.o

kernel/net/sctp/auth.c

@@ -0,0 +1,949 @@
+/* SCTP kernel implementation
+ * (C) Copyright 2007 Hewlett-Packard Development Company, L.P.
+ *
+ * This file is part of the SCTP kernel implementation
+ *
+ * This SCTP implementation is free software;
+ * you can redistribute it and/or modify it under the terms of
+ * the GNU General Public License as published by
+ * the Free Software Foundation; either version 2, or (at your option)
+ * any later version.
+ *
+ * This SCTP implementation is distributed in the hope that it
+ * will be useful, but WITHOUT ANY WARRANTY; without even the implied
+ *                 ************************
+ * warranty of MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.
+ * See the GNU General Public License for more details.
+ *
+ * You should have received a copy of the GNU General Public License
+ * along with GNU CC; see the file COPYING.  If not, write to
+ * the Free Software Foundation, 59 Temple Place - Suite 330,
+ * Boston, MA 02111-1307, USA.
+ *
+ * Please send any bug reports or fixes you make to the
+ * email address(es):
+ *    lksctp developers <lksctp-developers@lists.sourceforge.net>
+ *
+ * Or submit a bug report through the following website:
+ *    http://www.sf.net/projects/lksctp
+ *
+ * Written or modified by:
+ *   Vlad Yasevich     <vladislav.yasevich@hp.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/crypto.h>
+#include <linux/scatterlist.h>
+#include <net/sctp/sctp.h>
+#include <net/sctp/auth.h>
+
+static struct sctp_hmac sctp_hmac_list[SCTP_AUTH_NUM_HMACS] = {
+	{
+		/* id 0 is reserved.  as all 0 */
+		.hmac_id = SCTP_AUTH_HMAC_ID_RESERVED_0,
+	},
+	{
+		.hmac_id = SCTP_AUTH_HMAC_ID_SHA1,
+		.hmac_name="hmac(sha1)",
+		.hmac_len = SCTP_SHA1_SIG_SIZE,
+	},
+	{
+		/* id 2 is reserved as well */
+		.hmac_id = SCTP_AUTH_HMAC_ID_RESERVED_2,
+	},
+#if defined (CONFIG_CRYPTO_SHA256) || defined (CONFIG_CRYPTO_SHA256_MODULE)
+	{
+		.hmac_id = SCTP_AUTH_HMAC_ID_SHA256,
+		.hmac_name="hmac(sha256)",
+		.hmac_len = SCTP_SHA256_SIG_SIZE,
+	}
+#endif
+};
+
+
+void sctp_auth_key_put(struct sctp_auth_bytes *key)
+{
+	if (!key)
+		return;
+
+	if (atomic_dec_and_test(&key->refcnt)) {
+		kfree(key);
+		SCTP_DBG_OBJCNT_DEC(keys);
+	}
+}
+
+/* Create a new key structure of a given length */
+static struct sctp_auth_bytes *sctp_auth_create_key(__u32 key_len, gfp_t gfp)
+{
+	struct sctp_auth_bytes *key;
+
+	/* Verify that we are not going to overflow INT_MAX */
+	if ((INT_MAX - key_len) < sizeof(struct sctp_auth_bytes))
+		return NULL;
+
+	/* Allocate the shared key */
+	key = kmalloc(sizeof(struct sctp_auth_bytes) + key_len, gfp);
+	if (!key)
+		return NULL;
+
+	key->len = key_len;
+	atomic_set(&key->refcnt, 1);
+	SCTP_DBG_OBJCNT_INC(keys);
+
+	return key;
+}
+
+/* Create a new shared key container with a give key id */
+struct sctp_shared_key *sctp_auth_shkey_create(__u16 key_id, gfp_t gfp)
+{
+	struct sctp_shared_key *new;
+
+	/* Allocate the shared key container */
+	new = kzalloc(sizeof(struct sctp_shared_key), gfp);
+	if (!new)
+		return NULL;
+
+	INIT_LIST_HEAD(&new->key_list);
+	new->key_id = key_id;
+
+	return new;
+}
+
+/* Free the shared key stucture */
+static void sctp_auth_shkey_free(struct sctp_shared_key *sh_key)
+{
+	BUG_ON(!list_empty(&sh_key->key_list));
+	sctp_auth_key_put(sh_key->key);
+	sh_key->key = NULL;
+	kfree(sh_key);
+}
+
+/* Destory the entire key list.  This is done during the
+ * associon and endpoint free process.
+ */
+void sctp_auth_destroy_keys(struct list_head *keys)
+{
+	struct sctp_shared_key *ep_key;
+	struct sctp_shared_key *tmp;
+
+	if (list_empty(keys))
+		return;
+
+	key_for_each_safe(ep_key, tmp, keys) {
+		list_del_init(&ep_key->key_list);
+		sctp_auth_shkey_free(ep_key);
+	}
+}
+
+/* Compare two byte vectors as numbers.  Return values
+ * are:
+ * 	  0 - vectors are equal
+ * 	< 0 - vector 1 is smaller than vector2
+ * 	> 0 - vector 1 is greater than vector2
+ *
+ * Algorithm is:
+ * 	This is performed by selecting the numerically smaller key vector...
+ *	If the key vectors are equal as numbers but differ in length ...
+ *	the shorter vector is considered smaller
+ *
+ * Examples (with small values):
+ * 	000123456789 > 123456789 (first number is longer)
+ * 	000123456789 < 234567891 (second number is larger numerically)
+ * 	123456789 > 2345678 	 (first number is both larger & longer)
+ */
+static int sctp_auth_compare_vectors(struct sctp_auth_bytes *vector1,
+			      struct sctp_auth_bytes *vector2)
+{
+	int diff;
+	int i;
+	const __u8 *longer;
+
+	diff = vector1->len - vector2->len;
+	if (diff) {
+		longer = (diff > 0) ? vector1->data : vector2->data;
+
+		/* Check to see if the longer number is
+		 * lead-zero padded.  If it is not, it
+		 * is automatically larger numerically.
+		 */
+		for (i = 0; i < abs(diff); i++ ) {
+			if (longer[i] != 0)
+				return diff;
+		}
+	}
+
+	/* lengths are the same, compare numbers */
+	return memcmp(vector1->data, vector2->data, vector1->len);
+}
+
+/*
+ * Create a key vector as described in SCTP-AUTH, Section 6.1
+ *    The RANDOM parameter, the CHUNKS parameter and the HMAC-ALGO
+ *    parameter sent by each endpoint are concatenated as byte vectors.
+ *    These parameters include the parameter type, parameter length, and
+ *    the parameter value, but padding is omitted; all padding MUST be
+ *    removed from this concatenation before proceeding with further
+ *    computation of keys.  Parameters which were not sent are simply
+ *    omitted from the concatenation process.  The resulting two vectors
+ *    are called the two key vectors.
+ */
+static struct sctp_auth_bytes *sctp_auth_make_key_vector(
+			sctp_random_param_t *random,
+			sctp_chunks_param_t *chunks,
+			sctp_hmac_algo_param_t *hmacs,
+			gfp_t gfp)
+{
+	struct sctp_auth_bytes *new;
+	__u32	len;
+	__u32	offset = 0;
+
+	len = ntohs(random->param_hdr.length) + ntohs(hmacs->param_hdr.length);
+        if (chunks)
+		len += ntohs(chunks->param_hdr.length);
+
+	new = kmalloc(sizeof(struct sctp_auth_bytes) + len, gfp);
+	if (!new)
+		return NULL;
+
+	new->len = len;
+
+	memcpy(new->data, random, ntohs(random->param_hdr.length));
+	offset += ntohs(random->param_hdr.length);
+
+	if (chunks) {
+		memcpy(new->data + offset, chunks,
+			ntohs(chunks->param_hdr.length));
+		offset += ntohs(chunks->param_hdr.length);
+	}
+
+	memcpy(new->data + offset, hmacs, ntohs(hmacs->param_hdr.length));
+
+	return new;
+}
+
+
+/* Make a key vector based on our local parameters */
+static struct sctp_auth_bytes *sctp_auth_make_local_vector(
+				    const struct sctp_association *asoc,
+				    gfp_t gfp)
+{
+	return sctp_auth_make_key_vector(
+				    (sctp_random_param_t*)asoc->c.auth_random,
+				    (sctp_chunks_param_t*)asoc->c.auth_chunks,
+				    (sctp_hmac_algo_param_t*)asoc->c.auth_hmacs,
+				    gfp);
+}
+
+/* Make a key vector based on peer's parameters */
+static struct sctp_auth_bytes *sctp_auth_make_peer_vector(
+				    const struct sctp_association *asoc,
+				    gfp_t gfp)
+{
+	return sctp_auth_make_key_vector(asoc->peer.peer_random,
+					 asoc->peer.peer_chunks,
+					 asoc->peer.peer_hmacs,
+					 gfp);
+}
+
+
+/* Set the value of the association shared key base on the parameters
+ * given.  The algorithm is:
+ *    From the endpoint pair shared keys and the key vectors the
+ *    association shared keys are computed.  This is performed by selecting
+ *    the numerically smaller key vector and concatenating it to the
+ *    endpoint pair shared key, and then concatenating the numerically
+ *    larger key vector to that.  The result of the concatenation is the
+ *    association shared key.
+ */
+static struct sctp_auth_bytes *sctp_auth_asoc_set_secret(
+			struct sctp_shared_key *ep_key,
+			struct sctp_auth_bytes *first_vector,
+			struct sctp_auth_bytes *last_vector,
+			gfp_t gfp)
+{
+	struct sctp_auth_bytes *secret;
+	__u32 offset = 0;
+	__u32 auth_len;
+
+	auth_len = first_vector->len + last_vector->len;
+	if (ep_key->key)
+		auth_len += ep_key->key->len;
+
+	secret = sctp_auth_create_key(auth_len, gfp);
+	if (!secret)
+		return NULL;
+
+	if (ep_key->key) {
+		memcpy(secret->data, ep_key->key->data, ep_key->key->len);
+		offset += ep_key->key->len;
+	}
+
+	memcpy(secret->data + offset, first_vector->data, first_vector->len);
+	offset += first_vector->len;
+
+	memcpy(secret->data + offset, last_vector->data, last_vector->len);
+
+	return secret;
+}
+
+/* Create an association shared key.  Follow the algorithm
+ * described in SCTP-AUTH, Section 6.1
+ */
+static struct sctp_auth_bytes *sctp_auth_asoc_create_secret(
+				 const struct sctp_association *asoc,
+				 struct sctp_shared_key *ep_key,
+				 gfp_t gfp)
+{
+	struct sctp_auth_bytes *local_key_vector;
+	struct sctp_auth_bytes *peer_key_vector;
+	struct sctp_auth_bytes	*first_vector,
+				*last_vector;
+	struct sctp_auth_bytes	*secret = NULL;
+	int	cmp;
+
+
+	/* Now we need to build the key vectors
+	 * SCTP-AUTH , Section 6.1
+	 *    The RANDOM parameter, the CHUNKS parameter and the HMAC-ALGO
+	 *    parameter sent by each endpoint are concatenated as byte vectors.
+	 *    These parameters include the parameter type, parameter length, and
+	 *    the parameter value, but padding is omitted; all padding MUST be
+	 *    removed from this concatenation before proceeding with further
+	 *    computation of keys.  Parameters which were not sent are simply
+	 *    omitted from the concatenation process.  The resulting two vectors
+	 *    are called the two key vectors.
+	 */
+
+	local_key_vector = sctp_auth_make_local_vector(asoc, gfp);
+	peer_key_vector = sctp_auth_make_peer_vector(asoc, gfp);
+
+	if (!peer_key_vector || !local_key_vector)
+		goto out;
+
+	/* Figure out the order in wich the key_vectors will be
+	 * added to the endpoint shared key.
+	 * SCTP-AUTH, Section 6.1:
+	 *   This is performed by selecting the numerically smaller key
+	 *   vector and concatenating it to the endpoint pair shared
+	 *   key, and then concatenating the numerically larger key
+	 *   vector to that.  If the key vectors are equal as numbers
+	 *   but differ in length, then the concatenation order is the
+	 *   endpoint shared key, followed by the shorter key vector,
+	 *   followed by the longer key vector.  Otherwise, the key
+	 *   vectors are identical, and may be concatenated to the
+	 *   endpoint pair key in any order.
+	 */
+	cmp = sctp_auth_compare_vectors(local_key_vector,
+					peer_key_vector);
+	if (cmp < 0) {
+		first_vector = local_key_vector;
+		last_vector = peer_key_vector;
+	} else {
+		first_vector = peer_key_vector;
+		last_vector = local_key_vector;
+	}
+
+	secret = sctp_auth_asoc_set_secret(ep_key, first_vector, last_vector,
+					    gfp);
+out:
+	kfree(local_key_vector);
+	kfree(peer_key_vector);
+
+	return secret;
+}
+
+/*
+ * Populate the association overlay list with the list
+ * from the endpoint.
+ */
+int sctp_auth_asoc_copy_shkeys(const struct sctp_endpoint *ep,
+				struct sctp_association *asoc,
+				gfp_t gfp)
+{
+	struct sctp_shared_key *sh_key;
+	struct sctp_shared_key *new;
+
+	BUG_ON(!list_empty(&asoc->endpoint_shared_keys));
+
+	key_for_each(sh_key, &ep->endpoint_shared_keys) {
+		new = sctp_auth_shkey_create(sh_key->key_id, gfp);
+		if (!new)
+			goto nomem;
+
+		new->key = sh_key->key;
+		sctp_auth_key_hold(new->key);
+		list_add(&new->key_list, &asoc->endpoint_shared_keys);
+	}
+
+	return 0;
+
+nomem:
+	sctp_auth_destroy_keys(&asoc->endpoint_shared_keys);
+	return -ENOMEM;
+}
+
+
+/* Public interface to creat the association shared key.
+ * See code above for the algorithm.
+ */
+int sctp_auth_asoc_init_active_key(struct sctp_association *asoc, gfp_t gfp)
+{
+	struct sctp_auth_bytes	*secret;
+	struct sctp_shared_key *ep_key;
+
+	/* If we don't support AUTH, or peer is not capable
+	 * we don't need to do anything.
+	 */
+	if (!sctp_auth_enable || !asoc->peer.auth_capable)
+		return 0;
+
+	/* If the key_id is non-zero and we couldn't find an
+	 * endpoint pair shared key, we can't compute the
+	 * secret.
+	 * For key_id 0, endpoint pair shared key is a NULL key.
+	 */
+	ep_key = sctp_auth_get_shkey(asoc, asoc->active_key_id);
+	BUG_ON(!ep_key);
+
+	secret = sctp_auth_asoc_create_secret(asoc, ep_key, gfp);
+	if (!secret)
+		return -ENOMEM;
+
+	sctp_auth_key_put(asoc->asoc_shared_key);
+	asoc->asoc_shared_key = secret;
+
+	return 0;
+}
+
+
+/* Find the endpoint pair shared key based on the key_id */
+struct sctp_shared_key *sctp_auth_get_shkey(
+				const struct sctp_association *asoc,
+				__u16 key_id)
+{
+	struct sctp_shared_key *key;
+
+	/* First search associations set of endpoint pair shared keys */
+	key_for_each(key, &asoc->endpoint_shared_keys) {
+		if (key->key_id == key_id)
+			return key;
+	}
+
+	return NULL;
+}
+
+/*
+ * Initialize all the possible digest transforms that we can use.  Right now
+ * now, the supported digests are SHA1 and SHA256.  We do this here once
+ * because of the restrictiong that transforms may only be allocated in
+ * user context.  This forces us to pre-allocated all possible transforms
+ * at the endpoint init time.
+ */
+int sctp_auth_init_hmacs(struct sctp_endpoint *ep, gfp_t gfp)
+{
+	struct crypto_hash *tfm = NULL;
+	__u16   id;
+
+	/* if the transforms are already allocted, we are done */
+	if (!sctp_auth_enable) {
+		ep->auth_hmacs = NULL;
+		return 0;
+	}
+
+	if (ep->auth_hmacs)
+		return 0;
+
+	/* Allocated the array of pointers to transorms */
+	ep->auth_hmacs = kzalloc(
+			    sizeof(struct crypto_hash *) * SCTP_AUTH_NUM_HMACS,
+			    gfp);
+	if (!ep->auth_hmacs)
+		return -ENOMEM;
+
+	for (id = 0; id < SCTP_AUTH_NUM_HMACS; id++) {
+
+		/* See is we support the id.  Supported IDs have name and
+		 * length fields set, so that we can allocated and use
+		 * them.  We can safely just check for name, for without the
+		 * name, we can't allocate the TFM.
+		 */
+		if (!sctp_hmac_list[id].hmac_name)
+			continue;
+
+		/* If this TFM has been allocated, we are all set */
+		if (ep->auth_hmacs[id])
+			continue;
+
+		/* Allocate the ID */
+		tfm = crypto_alloc_hash(sctp_hmac_list[id].hmac_name, 0,
+					CRYPTO_ALG_ASYNC);
+		if (IS_ERR(tfm))
+			goto out_err;
+
+		ep->auth_hmacs[id] = tfm;
+	}
+
+	return 0;
+
+out_err:
+	/* Clean up any successful allocations */
+	sctp_auth_destroy_hmacs(ep->auth_hmacs);
+	return -ENOMEM;
+}
+
+/* Destroy the hmac tfm array */
+void sctp_auth_destroy_hmacs(struct crypto_hash *auth_hmacs[])
+{
+	int i;
+
+	if (!auth_hmacs)
+		return;
+
+	for (i = 0; i < SCTP_AUTH_NUM_HMACS; i++)
+	{
+		if (auth_hmacs[i])
+			crypto_free_hash(auth_hmacs[i]);
+	}
+	kfree(auth_hmacs);
+}
+
+
+struct sctp_hmac *sctp_auth_get_hmac(__u16 hmac_id)
+{
+	return &sctp_hmac_list[hmac_id];
+}
+
+/* Get an hmac description information that we can use to build
+ * the AUTH chunk
+ */
+struct sctp_hmac *sctp_auth_asoc_get_hmac(const struct sctp_association *asoc)
+{
+	struct sctp_hmac_algo_param *hmacs;
+	__u16 n_elt;
+	__u16 id = 0;
+	int i;
+
+	/* If we have a default entry, use it */
+	if (asoc->default_hmac_id)
+		return &sctp_hmac_list[asoc->default_hmac_id];
+
+	/* Since we do not have a default entry, find the first entry
+	 * we support and return that.  Do not cache that id.
+	 */
+	hmacs = asoc->peer.peer_hmacs;
+	if (!hmacs)
+		return NULL;
+
+	n_elt = (ntohs(hmacs->param_hdr.length) - sizeof(sctp_paramhdr_t)) >> 1;
+	for (i = 0; i < n_elt; i++) {
+		id = ntohs(hmacs->hmac_ids[i]);
+
+		/* Check the id is in the supported range */
+		if (id > SCTP_AUTH_HMAC_ID_MAX) {
+			id = 0;
+			continue;
+		}
+
+		/* See is we support the id.  Supported IDs have name and
+		 * length fields set, so that we can allocated and use
+		 * them.  We can safely just check for name, for without the
+		 * name, we can't allocate the TFM.
+		 */
+		if (!sctp_hmac_list[id].hmac_name) {
+			id = 0;
+			continue;
+		}
+
+		break;
+	}
+
+	if (id == 0)
+		return NULL;
+
+	return &sctp_hmac_list[id];
+}
+
+static int __sctp_auth_find_hmacid(__be16 *hmacs, int n_elts, __be16 hmac_id)
+{
+	int  found = 0;
+	int  i;
+
+	for (i = 0; i < n_elts; i++) {
+		if (hmac_id == hmacs[i]) {
+			found = 1;
+			break;
+		}
+	}
+
+	return found;
+}
+
+/* See if the HMAC_ID is one that we claim as supported */
+int sctp_auth_asoc_verify_hmac_id(const struct sctp_association *asoc,
+				    __be16 hmac_id)
+{
+	struct sctp_hmac_algo_param *hmacs;
+	__u16 n_elt;
+
+	if (!asoc)
+		return 0;
+
+	hmacs = (struct sctp_hmac_algo_param *)asoc->c.auth_hmacs;
+	n_elt = (ntohs(hmacs->param_hdr.length) - sizeof(sctp_paramhdr_t)) >> 1;
+
+	return __sctp_auth_find_hmacid(hmacs->hmac_ids, n_elt, hmac_id);
+}
+
+
+/* Cache the default HMAC id.  This to follow this text from SCTP-AUTH:
+ * Section 6.1:
+ *   The receiver of a HMAC-ALGO parameter SHOULD use the first listed
+ *   algorithm it supports.
+ */
+void sctp_auth_asoc_set_default_hmac(struct sctp_association *asoc,
+				     struct sctp_hmac_algo_param *hmacs)
+{
+	struct sctp_endpoint *ep;
+	__u16   id;
+	int	i;
+	int	n_params;
+
+	/* if the default id is already set, use it */
+	if (asoc->default_hmac_id)
+		return;
+
+	n_params = (ntohs(hmacs->param_hdr.length)
+				- sizeof(sctp_paramhdr_t)) >> 1;
+	ep = asoc->ep;
+	for (i = 0; i < n_params; i++) {
+		id = ntohs(hmacs->hmac_ids[i]);
+
+		/* Check the id is in the supported range */
+		if (id > SCTP_AUTH_HMAC_ID_MAX)
+			continue;
+
+		/* If this TFM has been allocated, use this id */
+		if (ep->auth_hmacs[id]) {
+			asoc->default_hmac_id = id;
+			break;
+		}
+	}
+}
+
+
+/* Check to see if the given chunk is supposed to be authenticated */
+static int __sctp_auth_cid(sctp_cid_t chunk, struct sctp_chunks_param *param)
+{
+	unsigned short len;
+	int found = 0;
+	int i;
+
+	if (!param || param->param_hdr.length == 0)
+		return 0;
+
+	len = ntohs(param->param_hdr.length) - sizeof(sctp_paramhdr_t);
+
+	/* SCTP-AUTH, Section 3.2
+	 *    The chunk types for INIT, INIT-ACK, SHUTDOWN-COMPLETE and AUTH
+	 *    chunks MUST NOT be listed in the CHUNKS parameter.  However, if
+	 *    a CHUNKS parameter is received then the types for INIT, INIT-ACK,
+	 *    SHUTDOWN-COMPLETE and AUTH chunks MUST be ignored.
+	 */
+	for (i = 0; !found && i < len; i++) {
+		switch (param->chunks[i]) {
+		    case SCTP_CID_INIT:
+		    case SCTP_CID_INIT_ACK:
+		    case SCTP_CID_SHUTDOWN_COMPLETE:
+		    case SCTP_CID_AUTH:
+			break;
+
+		    default:
+			if (param->chunks[i] == chunk)
+			    found = 1;
+			break;
+		}
+	}
+
+	return found;
+}
+
+/* Check if peer requested that this chunk is authenticated */
+int sctp_auth_send_cid(sctp_cid_t chunk, const struct sctp_association *asoc)
+{
+	if (!sctp_auth_enable || !asoc || !asoc->peer.auth_capable)
+		return 0;
+
+	return __sctp_auth_cid(chunk, asoc->peer.peer_chunks);
+}
+
+/* Check if we requested that peer authenticate this chunk. */
+int sctp_auth_recv_cid(sctp_cid_t chunk, const struct sctp_association *asoc)
+{
+	if (!sctp_auth_enable || !asoc)
+		return 0;
+
+	return __sctp_auth_cid(chunk,
+			      (struct sctp_chunks_param *)asoc->c.auth_chunks);
+}
+
+/* SCTP-AUTH: Section 6.2:
+ *    The sender MUST calculate the MAC as described in RFC2104 [2] using
+ *    the hash function H as described by the MAC Identifier and the shared
+ *    association key K based on the endpoint pair shared key described by
+ *    the shared key identifier.  The 'data' used for the computation of
+ *    the AUTH-chunk is given by the AUTH chunk with its HMAC field set to
+ *    zero (as shown in Figure 6) followed by all chunks that are placed
+ *    after the AUTH chunk in the SCTP packet.
+ */
+void sctp_auth_calculate_hmac(const struct sctp_association *asoc,
+			      struct sk_buff *skb,
+			      struct sctp_auth_chunk *auth,
+			      gfp_t gfp)
+{
+	struct scatterlist sg;
+	struct hash_desc desc;
+	struct sctp_auth_bytes *asoc_key;
+	__u16 key_id, hmac_id;
+	__u8 *digest;
+	unsigned char *end;
+	int free_key = 0;
+
+	/* Extract the info we need:
+	 * - hmac id
+	 * - key id
+	 */
+	key_id = ntohs(auth->auth_hdr.shkey_id);
+	hmac_id = ntohs(auth->auth_hdr.hmac_id);
+
+	if (key_id == asoc->active_key_id)
+		asoc_key = asoc->asoc_shared_key;
+	else {
+		struct sctp_shared_key *ep_key;
+
+		ep_key = sctp_auth_get_shkey(asoc, key_id);
+		if (!ep_key)
+			return;
+
+		asoc_key = sctp_auth_asoc_create_secret(asoc, ep_key, gfp);
+		if (!asoc_key)
+			return;
+
+		free_key = 1;
+	}
+
+	/* set up scatter list */
+	end = skb_tail_pointer(skb);
+	sg_init_one(&sg, auth, end - (unsigned char *)auth);
+
+	desc.tfm = asoc->ep->auth_hmacs[hmac_id];
+	desc.flags = 0;
+
+	digest = auth->auth_hdr.hmac;
+	if (crypto_hash_setkey(desc.tfm, &asoc_key->data[0], asoc_key->len))
+		goto free;
+
+	crypto_hash_digest(&desc, &sg, sg.length, digest);
+
+free:
+	if (free_key)
+		sctp_auth_key_put(asoc_key);
+}
+
+/* API Helpers */
+
+/* Add a chunk to the endpoint authenticated chunk list */
+int sctp_auth_ep_add_chunkid(struct sctp_endpoint *ep, __u8 chunk_id)
+{
+	struct sctp_chunks_param *p = ep->auth_chunk_list;
+	__u16 nchunks;
+	__u16 param_len;
+
+	/* If this chunk is already specified, we are done */
+	if (__sctp_auth_cid(chunk_id, p))
+		return 0;
+
+	/* Check if we can add this chunk to the array */
+	param_len = ntohs(p->param_hdr.length);
+	nchunks = param_len - sizeof(sctp_paramhdr_t);
+	if (nchunks == SCTP_NUM_CHUNK_TYPES)
+		return -EINVAL;
+
+	p->chunks[nchunks] = chunk_id;
+	p->param_hdr.length = htons(param_len + 1);
+	return 0;
+}
+
+/* Add hmac identifires to the endpoint list of supported hmac ids */
+int sctp_auth_ep_set_hmacs(struct sctp_endpoint *ep,
+			   struct sctp_hmacalgo *hmacs)
+{
+	int has_sha1 = 0;
+	__u16 id;
+	int i;
+
+	/* Scan the list looking for unsupported id.  Also make sure that
+	 * SHA1 is specified.
+	 */
+	for (i = 0; i < hmacs->shmac_num_idents; i++) {
+		id = hmacs->shmac_idents[i];
+
+		if (id > SCTP_AUTH_HMAC_ID_MAX)
+			return -EOPNOTSUPP;
+
+		if (SCTP_AUTH_HMAC_ID_SHA1 == id)
+			has_sha1 = 1;
+
+		if (!sctp_hmac_list[id].hmac_name)
+			return -EOPNOTSUPP;
+	}
+
+	if (!has_sha1)
+		return -EINVAL;
+
+	memcpy(ep->auth_hmacs_list->hmac_ids, &hmacs->shmac_idents[0],
+		hmacs->shmac_num_idents * sizeof(__u16));
+	ep->auth_hmacs_list->param_hdr.length = htons(sizeof(sctp_paramhdr_t) +
+				hmacs->shmac_num_idents * sizeof(__u16));
+	return 0;
+}
+
+/* Set a new shared key on either endpoint or association.  If the
+ * the key with a same ID already exists, replace the key (remove the
+ * old key and add a new one).
+ */
+int sctp_auth_set_key(struct sctp_endpoint *ep,
+		      struct sctp_association *asoc,
+		      struct sctp_authkey *auth_key)
+{
+	struct sctp_shared_key *cur_key = NULL;
+	struct sctp_auth_bytes *key;
+	struct list_head *sh_keys;
+	int replace = 0;
+
+	/* Try to find the given key id to see if
+	 * we are doing a replace, or adding a new key
+	 */
+	if (asoc)
+		sh_keys = &asoc->endpoint_shared_keys;
+	else
+		sh_keys = &ep->endpoint_shared_keys;
+
+	key_for_each(cur_key, sh_keys) {
+		if (cur_key->key_id == auth_key->sca_keynumber) {
+			replace = 1;
+			break;
+		}
+	}
+
+	/* If we are not replacing a key id, we need to allocate
+	 * a shared key.
+	 */
+	if (!replace) {
+		cur_key = sctp_auth_shkey_create(auth_key->sca_keynumber,
+						 GFP_KERNEL);
+		if (!cur_key)
+			return -ENOMEM;
+	}
+
+	/* Create a new key data based on the info passed in */
+	key = sctp_auth_create_key(auth_key->sca_keylength, GFP_KERNEL);
+	if (!key)
+		goto nomem;
+
+	memcpy(key->data, &auth_key->sca_key[0], auth_key->sca_keylength);
+
+	/* If we are replacing, remove the old keys data from the
+	 * key id.  If we are adding new key id, add it to the
+	 * list.
+	 */
+	if (replace)
+		sctp_auth_key_put(cur_key->key);
+	else
+		list_add(&cur_key->key_list, sh_keys);
+
+	cur_key->key = key;
+	sctp_auth_key_hold(key);
+
+	return 0;
+nomem:
+	if (!replace)
+		sctp_auth_shkey_free(cur_key);
+
+	return -ENOMEM;
+}
+
+int sctp_auth_set_active_key(struct sctp_endpoint *ep,
+			     struct sctp_association *asoc,
+			     __u16  key_id)
+{
+	struct sctp_shared_key *key;
+	struct list_head *sh_keys;
+	int found = 0;
+
+	/* The key identifier MUST correst to an existing key */
+	if (asoc)
+		sh_keys = &asoc->endpoint_shared_keys;
+	else
+		sh_keys = &ep->endpoint_shared_keys;
+
+	key_for_each(key, sh_keys) {
+		if (key->key_id == key_id) {
+			found = 1;
+			break;
+		}
+	}
+
+	if (!found)
+		return -EINVAL;
+
+	if (asoc) {
+		asoc->active_key_id = key_id;
+		sctp_auth_asoc_init_active_key(asoc, GFP_KERNEL);
+	} else
+		ep->active_key_id = key_id;
+
+	return 0;
+}
+
+int sctp_auth_del_key_id(struct sctp_endpoint *ep,
+			 struct sctp_association *asoc,
+			 __u16  key_id)
+{
+	struct sctp_shared_key *key;
+	struct list_head *sh_keys;
+	int found = 0;
+
+	/* The key identifier MUST NOT be the current active key
+	 * The key identifier MUST correst to an existing key
+	 */
+	if (asoc) {
+		if (asoc->active_key_id == key_id)
+			return -EINVAL;
+
+		sh_keys = &asoc->endpoint_shared_keys;
+	} else {
+		if (ep->active_key_id == key_id)
+			return -EINVAL;
+
+		sh_keys = &ep->endpoint_shared_keys;
+	}
+
+	key_for_each(key, sh_keys) {
+		if (key->key_id == key_id) {
+			found = 1;
+			break;
+		}
+	}
+
+	if (!found)
+		return -EINVAL;
+
+	/* Delete the shared key */
+	list_del_init(&key->key_list);
+	sctp_auth_shkey_free(key);
+
+	return 0;
+}

kernel/net/sctp/bind_addr.c

@@ -0,0 +1,553 @@
+/* SCTP kernel 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 implementation.
+ *
+ * A collection class to handle the storage of transport addresses.
+ *
+ * This SCTP implementation is free software;
+ * you can redistribute it and/or modify it under the terms of
+ * the GNU General Public License as published by
+ * the Free Software Foundation; either version 2, or (at your option)
+ * any later version.
+ *
+ * This SCTP implementation is distributed in the hope that it
+ * will be useful, but WITHOUT ANY WARRANTY; without even the implied
+ *                 ************************
+ * warranty of MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.
+ * See the GNU General Public License for more details.
+ *
+ * You should have received a copy of the GNU General Public License
+ * along with GNU CC; see the file COPYING.  If not, write to
+ * the Free Software Foundation, 59 Temple Place - Suite 330,
+ * Boston, MA 02111-1307, USA.
+ *
+ * Please send any bug reports or fixes you make to the
+ * email address(es):
+ *    lksctp developers <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/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, gfp_t 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, gfp_t gfp,
+			int flags)
+{
+	struct sctp_sockaddr_entry *addr;
+	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_entry(addr, &src->address_list, 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_entry(addr, &src->address_list, 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;
+}
+
+/* Exactly duplicate the address lists.  This is necessary when doing
+ * peer-offs and accepts.  We don't want to put all the current system
+ * addresses into the endpoint.  That's useless.  But we do want duplicat
+ * the list of bound addresses that the older endpoint used.
+ */
+int sctp_bind_addr_dup(struct sctp_bind_addr *dest,
+			const struct sctp_bind_addr *src,
+			gfp_t gfp)
+{
+	struct sctp_sockaddr_entry *addr;
+	int error = 0;
+
+	/* All addresses share the same port.  */
+	dest->port = src->port;
+
+	list_for_each_entry(addr, &src->address_list, list) {
+		error = sctp_add_bind_addr(dest, &addr->a, 1, gfp);
+		if (error < 0)
+			break;
+	}
+
+	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,
+		       __u8 addr_state, gfp_t 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 = htons(bp->port);
+
+	addr->state = addr_state;
+	addr->valid = 1;
+
+	INIT_LIST_HEAD(&addr->list);
+	INIT_RCU_HEAD(&addr->rcu);
+
+	/* We always hold a socket lock when calling this function,
+	 * and that acts as a writer synchronizing lock.
+	 */
+	list_add_tail_rcu(&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 sctp_sockaddr_entry *addr, *temp;
+	int found = 0;
+
+	/* We hold the socket lock when calling this function,
+	 * and that acts as a writer synchronizing lock.
+	 */
+	list_for_each_entry_safe(addr, temp, &bp->address_list, list) {
+		if (sctp_cmp_addr_exact(&addr->a, del_addr)) {
+			/* Found the exact match. */
+			found = 1;
+			addr->valid = 0;
+			list_del_rcu(&addr->list);
+			break;
+		}
+	}
+
+	if (found) {
+		call_rcu(&addr->rcu, sctp_local_addr_free);
+		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,
+					 gfp_t 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_entry(addr, &bp->address_list, 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, gfp_t 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, htons(port), 0);
+		retval = sctp_add_bind_addr(bp, &addr, SCTP_ADDR_SRC, 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;
+	int match = 0;
+
+	rcu_read_lock();
+	list_for_each_entry_rcu(laddr, &bp->address_list, list) {
+		if (!laddr->valid)
+			continue;
+		if (opt->pf->cmp_addr(&laddr->a, addr, opt)) {
+			match = 1;
+			break;
+		}
+	}
+	rcu_read_unlock();
+
+	return match;
+}
+
+/* Does the address 'addr' conflict with any addresses in
+ * the bp.
+ */
+int sctp_bind_addr_conflict(struct sctp_bind_addr *bp,
+			    const union sctp_addr *addr,
+			    struct sctp_sock *bp_sp,
+			    struct sctp_sock *addr_sp)
+{
+	struct sctp_sockaddr_entry *laddr;
+	int conflict = 0;
+	struct sctp_sock *sp;
+
+	/* Pick the IPv6 socket as the basis of comparison
+	 * since it's usually a superset of the IPv4.
+	 * If there is no IPv6 socket, then default to bind_addr.
+	 */
+	if (sctp_opt2sk(bp_sp)->sk_family == AF_INET6)
+		sp = bp_sp;
+	else if (sctp_opt2sk(addr_sp)->sk_family == AF_INET6)
+		sp = addr_sp;
+	else
+		sp = bp_sp;
+
+	rcu_read_lock();
+	list_for_each_entry_rcu(laddr, &bp->address_list, list) {
+		if (!laddr->valid)
+			continue;
+
+		conflict = sp->pf->cmp_addr(&laddr->a, addr, sp);
+		if (conflict)
+			break;
+	}
+	rcu_read_unlock();
+
+	return conflict;
+}
+
+/* Get the state of the entry in the bind_addr_list */
+int sctp_bind_addr_state(const struct sctp_bind_addr *bp,
+			 const union sctp_addr *addr)
+{
+	struct sctp_sockaddr_entry *laddr;
+	struct sctp_af *af;
+	int state = -1;
+
+	af = sctp_get_af_specific(addr->sa.sa_family);
+	if (unlikely(!af))
+		return state;
+
+	rcu_read_lock();
+	list_for_each_entry_rcu(laddr, &bp->address_list, list) {
+		if (!laddr->valid)
+			continue;
+		if (af->cmp_addr(&laddr->a, addr)) {
+			state = laddr->state;
+			break;
+		}
+	}
+	rcu_read_unlock();
+
+	return state;
+}
+
+/* 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;
+	int				i;
+
+	/* This is only called sctp_send_asconf_del_ip() and we hold
+	 * the socket lock in that code patch, so that address list
+	 * can't change.
+	 */
+	list_for_each_entry(laddr, &bp->address_list, 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)
+				break;
+
+			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, gfp_t gfp,
+			      int flags)
+{
+	int error = 0;
+
+	if (sctp_is_any(NULL, 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, SCTP_ADDR_SRC,
+						    gfp);
+	}
+
+	return error;
+}
+
+/* Is this a wildcard address?  */
+int sctp_is_any(struct sock *sk, const union sctp_addr *addr)
+{
+	unsigned short fam = 0;
+	struct sctp_af *af;
+
+	/* Try to get the right address family */
+	if (addr->sa.sa_family != AF_UNSPEC)
+		fam = addr->sa.sa_family;
+	else if (sk)
+		fam = sk->sk_family;
+
+	af = sctp_get_af_specific(fam);
+	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.
+	 *
+	 * Address scoping can be selectively controlled via sysctl
+	 * option
+	 */
+	switch (sctp_scope_policy) {
+	case SCTP_SCOPE_POLICY_DISABLE:
+		return 1;
+	case SCTP_SCOPE_POLICY_ENABLE:
+		if (addr_scope <= scope)
+			return 1;
+		break;
+	case SCTP_SCOPE_POLICY_PRIVATE:
+		if (addr_scope <= scope || SCTP_SCOPE_PRIVATE == addr_scope)
+			return 1;
+		break;
+	case SCTP_SCOPE_POLICY_LINK:
+		if (addr_scope <= scope || SCTP_SCOPE_LINK == addr_scope)
+			return 1;
+		break;
+	default:
+		break;
+	}
+
+	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);
+}

kernel/net/sctp/chunk.c

@@ -0,0 +1,348 @@
+/* SCTP kernel implementation
+ * (C) Copyright IBM Corp. 2003, 2004
+ *
+ * This file is part of the SCTP kernel implementation
+ *
+ * This file contains the code relating the chunk abstraction.
+ *
+ * This SCTP implementation is free software;
+ * you can redistribute it and/or modify it under the terms of
+ * the GNU General Public License as published by
+ * the Free Software Foundation; either version 2, or (at your option)
+ * any later version.
+ *
+ * This SCTP implementation is distributed in the hope that it
+ * will be useful, but WITHOUT ANY WARRANTY; without even the implied
+ *                 ************************
+ * warranty of MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.
+ * See the GNU General Public License for more details.
+ *
+ * You should have received a copy of the GNU General Public License
+ * along with GNU CC; see the file COPYING.  If not, write to
+ * the Free Software Foundation, 59 Temple Place - Suite 330,
+ * Boston, MA 02111-1307, USA.
+ *
+ * Please send any bug reports or fixes you make to the
+ * email address(es):
+ *    lksctp developers <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);
+	msg->msg_size = 0;
+}
+
+/* Allocate and initialize datamsg. */
+SCTP_STATIC struct sctp_datamsg *sctp_datamsg_new(gfp_t 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;
+}
+
+void sctp_datamsg_free(struct sctp_datamsg *msg)
+{
+	struct sctp_chunk *chunk;
+
+	/* This doesn't have to be a _safe vairant because
+	 * sctp_chunk_free() only drops the refs.
+	 */
+	list_for_each_entry(chunk, &msg->chunks, frag_list)
+		sctp_chunk_free(chunk);
+
+	sctp_datamsg_put(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);
+}
+
+/* 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;
+	msg->msg_size += chunk->skb->len;
+}
+
+
+/* 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;
+	int max_data;
+	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",
+				  __func__, msg, msg->expires_at, jiffies);
+	}
+
+	/* This is the biggest possible DATA chunk that can fit into
+	 * the packet
+	 */
+	max_data = asoc->pathmtu -
+		sctp_sk(asoc->base.sk)->pf->af->net_header_len -
+		sizeof(struct sctphdr) - sizeof(struct sctp_data_chunk);
+
+	max = asoc->frag_point;
+	/* If the the peer requested that we authenticate DATA chunks
+	 * we need to accound for bundling of the AUTH chunks along with
+	 * DATA.
+	 */
+	if (sctp_auth_send_cid(SCTP_CID_DATA, asoc)) {
+		struct sctp_hmac *hmac_desc = sctp_auth_asoc_get_hmac(asoc);
+
+		if (hmac_desc)
+			max_data -= WORD_ROUND(sizeof(sctp_auth_chunk_t) +
+					    hmac_desc->hmac_len);
+	}
+
+	/* Now, check if we need to reduce our max */
+	if (max > max_data)
+		max = max_data;
+
+	whole = 0;
+	first_len = max;
+
+	/* Check to see if we have a pending SACK and try to let it be bundled
+	 * with this message.  Do this if we don't have any data queued already.
+	 * To check that, look at out_qlen and retransmit list.
+	 * NOTE: we will not reduce to account for SACK, if the message would
+	 * not have been fragmented.
+	 */
+	if (timer_pending(&asoc->timers[SCTP_EVENT_TIMEOUT_SACK]) &&
+	    asoc->outqueue.out_qlen == 0 &&
+	    list_empty(&asoc->outqueue.retransmit) &&
+	    msg_len > max)
+		max_data -= WORD_ROUND(sizeof(sctp_sack_chunk_t));
+
+	/* Encourage Cookie-ECHO bundling. */
+	if (asoc->state < SCTP_STATE_COOKIE_ECHOED)
+		max_data -= SCTP_ARBITRARY_COOKIE_ECHO_LEN;
+
+	/* Now that we adjusted completely, reset first_len */
+	if (first_len > max_data)
+		first_len = max_data;
+
+	/* Account for a different sized first fragment */
+	if (msg_len >= first_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_put(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;
+}

kernel/net/sctp/command.c

@@ -0,0 +1,75 @@
+/* SCTP kernel implementation Copyright (C) 1999-2001
+ * Cisco, Motorola, and IBM
+ * Copyright 2001 La Monte H.P. Yarroll
+ *
+ * This file is part of the SCTP kernel implementation
+ *
+ * These functions manipulate sctp command sequences.
+ *
+ * This SCTP implementation is free software;
+ * you can redistribute it and/or modify it under the terms of
+ * the GNU General Public License as published by
+ * the Free Software Foundation; either version 2, or (at your option)
+ * any later version.
+ *
+ * This SCTP implementation is distributed in the hope that it
+ * will be useful, but WITHOUT ANY WARRANTY; without even the implied
+ *                 ************************
+ * warranty of MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.
+ * See the GNU General Public License for more details.
+ *
+ * You should have received a copy of the GNU General Public License
+ * along with GNU CC; see the file COPYING.  If not, write to
+ * the Free Software Foundation, 59 Temple Place - Suite 330,
+ * Boston, MA 02111-1307, USA.
+ *
+ * Please send any bug reports or fixes you make to the
+ * email address(es):
+ *    lksctp developers <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.
+ */
+void sctp_add_cmd_sf(sctp_cmd_seq_t *seq, sctp_verb_t verb, sctp_arg_t obj)
+{
+	BUG_ON(seq->next_free_slot >= SCTP_MAX_NUM_COMMANDS);
+
+	seq->cmds[seq->next_free_slot].verb = verb;
+	seq->cmds[seq->next_free_slot++].obj = obj;
+}
+
+/* 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;
+}
+

kernel/net/sctp/debug.c

@@ -0,0 +1,184 @@
+/* SCTP kernel implementation
+ * (C) Copyright IBM Corp. 2001, 2004
+ * Copyright (c) 1999-2000 Cisco, Inc.
+ * Copyright (c) 1999-2001 Motorola, Inc.
+ * Copyright (c) 2001 Intel Corp.
+ *
+ * This file is part of the SCTP kernel implementation
+ *
+ * This file converts numerical ID value to alphabetical names for SCTP
+ * terms such as chunk type, parameter time, event type, etc.
+ *
+ * This SCTP implementation is free software;
+ * you can redistribute it and/or modify it under the terms of
+ * the GNU General Public License as published by
+ * the Free Software Foundation; either version 2, or (at your option)
+ * any later version.
+ *
+ * This SCTP implementation is distributed in the hope that it
+ * will be useful, but WITHOUT ANY WARRANTY; without even the implied
+ *                 ************************
+ * warranty of MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.
+ * See the GNU General Public License for more details.
+ *
+ * You should have received a copy of the GNU General Public License
+ * along with GNU CC; see the file COPYING.  If not, write to
+ * the Free Software Foundation, 59 Temple Place - Suite 330,
+ * Boston, MA 02111-1307, USA.
+ *
+ * Please send any bug reports or fixes you make to the
+ * email address(es):
+ *    lksctp developers <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 *const 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 <= 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";
+
+	case SCTP_CID_AUTH:
+		return "AUTH";
+
+	default:
+		break;
+	}
+
+	return "unknown chunk";
+}
+
+/* These are printable forms of the states.  */
+const char *const 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 *const 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 *const 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 *const sctp_primitive_tbl[SCTP_NUM_PRIMITIVE_TYPES] = {
+	"PRIMITIVE_ASSOCIATE",
+	"PRIMITIVE_SHUTDOWN",
+	"PRIMITIVE_ABORT",
+	"PRIMITIVE_SEND",
+	"PRIMITIVE_REQUESTHEARTBEAT",
+	"PRIMITIVE_ASCONF",
+};
+
+/* Lookup primitive debug name. */
+const char *sctp_pname(const sctp_subtype_t id)
+{
+	if (id.primitive <= SCTP_EVENT_PRIMITIVE_MAX)
+		return sctp_primitive_tbl[id.primitive];
+	return "unknown_primitive";
+}
+
+static const char *const 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 <= SCTP_EVENT_OTHER_MAX)
+		return sctp_other_tbl[id.other];
+	return "unknown 'other' event";
+}
+
+static const char *const 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 <= SCTP_EVENT_TIMEOUT_MAX)
+		return sctp_timer_tbl[id.timeout];
+	return "unknown_timer";
+}

kernel/net/sctp/endpointola.c

@@ -0,0 +1,490 @@
+/* SCTP kernel 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 implementation
+ *
+ * This abstraction represents an SCTP endpoint.
+ *
+ * The SCTP implementation is free software;
+ * you can redistribute it and/or modify it under the terms of
+ * the GNU General Public License as published by
+ * the Free Software Foundation; either version 2, or (at your option)
+ * any later version.
+ *
+ * The SCTP 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/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 work_struct *work);
+
+/*
+ * Initialize the base fields of the endpoint structure.
+ */
+static struct sctp_endpoint *sctp_endpoint_init(struct sctp_endpoint *ep,
+						struct sock *sk,
+						gfp_t gfp)
+{
+	struct sctp_hmac_algo_param *auth_hmacs = NULL;
+	struct sctp_chunks_param *auth_chunks = NULL;
+	struct sctp_shared_key *null_key;
+	int err;
+
+	memset(ep, 0, sizeof(struct sctp_endpoint));
+
+	ep->digest = kzalloc(SCTP_SIGNATURE_SIZE, gfp);
+	if (!ep->digest)
+		return NULL;
+
+	if (sctp_auth_enable) {
+		/* Allocate space for HMACS and CHUNKS authentication
+		 * variables.  There are arrays that we encode directly
+		 * into parameters to make the rest of the operations easier.
+		 */
+		auth_hmacs = kzalloc(sizeof(sctp_hmac_algo_param_t) +
+				sizeof(__u16) * SCTP_AUTH_NUM_HMACS, gfp);
+		if (!auth_hmacs)
+			goto nomem;
+
+		auth_chunks = kzalloc(sizeof(sctp_chunks_param_t) +
+					SCTP_NUM_CHUNK_TYPES, gfp);
+		if (!auth_chunks)
+			goto nomem;
+
+		/* Initialize the HMACS parameter.
+		 * SCTP-AUTH: Section 3.3
+		 *    Every endpoint supporting SCTP chunk authentication MUST
+		 *    support the HMAC based on the SHA-1 algorithm.
+		 */
+		auth_hmacs->param_hdr.type = SCTP_PARAM_HMAC_ALGO;
+		auth_hmacs->param_hdr.length =
+					htons(sizeof(sctp_paramhdr_t) + 2);
+		auth_hmacs->hmac_ids[0] = htons(SCTP_AUTH_HMAC_ID_SHA1);
+
+		/* Initialize the CHUNKS parameter */
+		auth_chunks->param_hdr.type = SCTP_PARAM_CHUNKS;
+		auth_chunks->param_hdr.length = htons(sizeof(sctp_paramhdr_t));
+
+		/* If the Add-IP functionality is enabled, we must
+		 * authenticate, ASCONF and ASCONF-ACK chunks
+		 */
+		if (sctp_addip_enable) {
+			auth_chunks->chunks[0] = SCTP_CID_ASCONF;
+			auth_chunks->chunks[1] = SCTP_CID_ASCONF_ACK;
+			auth_chunks->param_hdr.length =
+					htons(sizeof(sctp_paramhdr_t) + 2);
+		}
+	}
+
+	/* 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, sctp_endpoint_bh_rcv);
+
+	/* Initialize the bind addr area */
+	sctp_bind_addr_init(&ep->base.bind_addr, 0);
+
+	/* 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);
+
+	/* Use SCTP specific send buffer space queues.  */
+	ep->sndbuf_policy = sctp_sndbuf_policy;
+
+	sk->sk_write_space = sctp_write_space;
+	sock_set_flag(sk, SOCK_USE_WRITE_QUEUE);
+
+	/* Get the receive buffer policy for this endpoint */
+	ep->rcvbuf_policy = sctp_rcvbuf_policy;
+
+	/* 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;
+
+	/* SCTP-AUTH extensions*/
+	INIT_LIST_HEAD(&ep->endpoint_shared_keys);
+	null_key = sctp_auth_shkey_create(0, GFP_KERNEL);
+	if (!null_key)
+		goto nomem;
+
+	list_add(&null_key->key_list, &ep->endpoint_shared_keys);
+
+	/* Allocate and initialize transorms arrays for suported HMACs. */
+	err = sctp_auth_init_hmacs(ep, gfp);
+	if (err)
+		goto nomem_hmacs;
+
+	/* Add the null key to the endpoint shared keys list and
+	 * set the hmcas and chunks pointers.
+	 */
+	ep->auth_hmacs_list = auth_hmacs;
+	ep->auth_chunk_list = auth_chunks;
+
+	return ep;
+
+nomem_hmacs:
+	sctp_auth_destroy_keys(&ep->endpoint_shared_keys);
+nomem:
+	/* Free all allocations */
+	kfree(auth_hmacs);
+	kfree(auth_chunks);
+	kfree(ep->digest);
+	return NULL;
+
+}
+
+/* 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, gfp_t 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;
+
+	/* If this is a temporary association, don't bother
+	 * since we'll be removing it shortly and don't
+	 * want anyone to find it anyway.
+	 */
+	if (asoc->temp)
+		return;
+
+	/* 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;
+
+	ep->base.sk->sk_state = SCTP_SS_CLOSED;
+
+	/* Unlink this endpoint, so we can't find it again! */
+	sctp_unhash_endpoint(ep);
+
+	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);
+
+	/* Free up the HMAC transform. */
+	crypto_free_hash(sctp_sk(ep->base.sk)->hmac);
+
+	/* Free the digest buffer */
+	kfree(ep->digest);
+
+	/* SCTP-AUTH: Free up AUTH releated data such as shared keys
+	 * chunks and hmacs arrays that were allocated
+	 */
+	sctp_auth_destroy_keys(&ep->endpoint_shared_keys);
+	kfree(ep->auth_hmacs_list);
+	kfree(ep->auth_chunk_list);
+
+	/* AUTH - Free any allocated HMAC transform containers */
+	sctp_auth_destroy_hmacs(ep->auth_hmacs);
+
+	/* 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 = NULL;
+
+	if (htons(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;
+	}
+
+	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)
+{
+	struct sctp_association *asoc = NULL;
+	struct sctp_transport *t = NULL;
+	struct sctp_hashbucket *head;
+	struct sctp_ep_common *epb;
+	struct hlist_node *node;
+	int hash;
+	int rport;
+
+	*transport = NULL;
+	rport = ntohs(paddr->v4.sin_port);
+
+	hash = sctp_assoc_hashfn(ep->base.bind_addr.port, rport);
+	head = &sctp_assoc_hashtable[hash];
+	read_lock(&head->lock);
+	sctp_for_each_hentry(epb, node, &head->chain) {
+		asoc = sctp_assoc(epb);
+		if (asoc->ep != ep || rport != asoc->peer.port)
+			goto next;
+
+		t = sctp_assoc_lookup_paddr(asoc, paddr);
+		if (t) {
+			*transport = t;
+			break;
+		}
+next:
+		asoc = NULL;
+	}
+	read_unlock(&head->lock);
+	return asoc;
+}
+
+/* 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 sctp_sockaddr_entry *addr;
+	struct sctp_bind_addr *bp;
+
+	bp = &ep->base.bind_addr;
+	/* This function is called with the socket lock held,
+	 * so the address_list can not change.
+	 */
+	list_for_each_entry(addr, &bp->address_list, list) {
+		if (sctp_has_association(&addr->a, paddr))
+			return 1;
+	}
+
+	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 work_struct *work)
+{
+	struct sctp_endpoint *ep =
+		container_of(work, struct sctp_endpoint,
+			     base.inqueue.immediate);
+	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;
+	int first_time = 1;	/* is this the first time through the looop */
+
+	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);
+
+		/* If the first chunk in the packet is AUTH, do special
+		 * processing specified in Section 6.3 of SCTP-AUTH spec
+		 */
+		if (first_time && (subtype.chunk == SCTP_CID_AUTH)) {
+			struct sctp_chunkhdr *next_hdr;
+
+			next_hdr = sctp_inq_peek(inqueue);
+			if (!next_hdr)
+				goto normal;
+
+			/* If the next chunk is COOKIE-ECHO, skip the AUTH
+			 * chunk while saving a pointer to it so we can do
+			 * Authentication later (during cookie-echo
+			 * processing).
+			 */
+			if (next_hdr->type == SCTP_CID_COOKIE_ECHO) {
+				chunk->auth_chunk = skb_clone(chunk->skb,
+								GFP_ATOMIC);
+				chunk->auth = 1;
+				continue;
+			}
+		}
+normal:
+		/* 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;
+		if (sctp_auth_recv_cid(subtype.chunk, asoc) && !chunk->auth)
+			continue;
+
+		/* 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;
+
+		if (first_time)
+			first_time = 0;
+	}
+}

kernel/net/sctp/inqueue.c

@@ -0,0 +1,243 @@
+/* SCTP kernel 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 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.
+ *
+ * This SCTP implementation is free software;
+ * you can redistribute it and/or modify it under the terms of
+ * the GNU General Public License as published by
+ * the Free Software Foundation; either version 2, or (at your option)
+ * any later version.
+ *
+ * This SCTP implementation is distributed in the hope that it
+ * will be useful, but WITHOUT ANY WARRANTY; without even the implied
+ *                 ************************
+ * warranty of MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.
+ * See the GNU General Public License for more details.
+ *
+ * You should have received a copy of the GNU General Public License
+ * along with GNU CC; see the file COPYING.  If not, write to
+ * the Free Software Foundation, 59 Temple Place - Suite 330,
+ * Boston, MA 02111-1307, USA.
+ *
+ * Please send any bug reports or fixes you make to the
+ * email address(es):
+ *    lksctp developers <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)
+{
+	INIT_LIST_HEAD(&queue->in_chunk_list);
+	queue->in_progress = NULL;
+
+	/* Create a task for delivering data.  */
+	INIT_WORK(&queue->immediate, NULL);
+
+	queue->malloced = 0;
+}
+
+/* Release the memory associated with an SCTP inqueue.  */
+void sctp_inq_free(struct sctp_inq *queue)
+{
+	struct sctp_chunk *chunk, *tmp;
+
+	/* Empty the queue.  */
+	list_for_each_entry_safe(chunk, tmp, &queue->in_chunk_list, list) {
+		list_del_init(&chunk->list);
+		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);
+		queue->in_progress = NULL;
+	}
+
+	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 *chunk)
+{
+	/* Directly call the packet handling routine. */
+	if (chunk->rcvr->dead) {
+		sctp_chunk_free(chunk);
+		return;
+	}
+
+	/* 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.
+	 */
+	list_add_tail(&chunk->list, &q->in_chunk_list);
+	q->immediate.func(&q->immediate);
+}
+
+/* Peek at the next chunk on the inqeue. */
+struct sctp_chunkhdr *sctp_inq_peek(struct sctp_inq *queue)
+{
+	struct sctp_chunk *chunk;
+	sctp_chunkhdr_t *ch = NULL;
+
+	chunk = queue->in_progress;
+	/* If there is no more chunks in this packet, say so */
+	if (chunk->singleton ||
+	    chunk->end_of_packet ||
+	    chunk->pdiscard)
+		    return NULL;
+
+	ch = (sctp_chunkhdr_t *)chunk->chunk_end;
+
+	return ch;
+}
+
+
+/* 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);
+
+			/* Verify that we have at least chunk headers
+			 * worth of buffer left.
+			 */
+			if (skb_headlen(chunk->skb) < sizeof(sctp_chunkhdr_t)) {
+				sctp_chunk_free(chunk);
+				chunk = queue->in_progress = NULL;
+			}
+		}
+	}
+
+	/* Do we need to take the next packet out of the queue to process? */
+	if (!chunk) {
+		struct list_head *entry;
+
+		/* Is the queue empty?  */
+		if (list_empty(&queue->in_chunk_list))
+			return NULL;
+
+		entry = queue->in_chunk_list.next;
+		chunk = queue->in_progress =
+			list_entry(entry, struct sctp_chunk, list);
+		list_del_init(entry);
+
+		/* This is the first chunk in the packet.  */
+		chunk->singleton = 1;
+		ch = (sctp_chunkhdr_t *) chunk->skb->data;
+		chunk->data_accepted = 0;
+	}
+
+	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 > skb_tail_pointer(chunk->skb))
+			chunk->chunk_end = skb_tail_pointer(chunk->skb);
+	}
+	skb_pull(chunk->skb, sizeof(sctp_chunkhdr_t));
+	chunk->subh.v = NULL; /* Subheader is no longer valid.  */
+
+	if (chunk->chunk_end < skb_tail_pointer(chunk->skb)) {
+		/* This is not a singleton */
+		chunk->singleton = 0;
+	} else if (chunk->chunk_end > skb_tail_pointer(chunk->skb)) {
+		/* 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, work_func_t callback)
+{
+	INIT_WORK(&q->immediate, callback);
+}
+

kernel/net/sctp/objcnt.c

@@ -0,0 +1,147 @@
+/* SCTP kernel implementation
+ * (C) Copyright IBM Corp. 2001, 2004
+ *
+ * This file is part of the SCTP kernel implementation
+ *
+ * Support for memory object debugging.  This allows one to monitor the
+ * object allocations/deallocations for types instrumented for this
+ * via the proc fs.
+ *
+ * This SCTP implementation is free software;
+ * you can redistribute it and/or modify it under the terms of
+ * the GNU General Public License as published by
+ * the Free Software Foundation; either version 2, or (at your option)
+ * any later version.
+ *
+ * This SCTP implementation is distributed in the hope that it
+ * will be useful, but WITHOUT ANY WARRANTY; without even the implied
+ *                 ************************
+ * warranty of MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.
+ * See the GNU General Public License for more details.
+ *
+ * You should have received a copy of the GNU General Public License
+ * along with GNU CC; see the file COPYING.  If not, write to
+ * the Free Software Foundation, 59 Temple Place - Suite 330,
+ * Boston, MA 02111-1307, USA.
+ *
+ * Please send any bug reports or fixes you make to the
+ * email address(es):
+ *    lksctp developers <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);
+SCTP_DBG_OBJCNT(keys);
+
+/* 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),
+	SCTP_DBG_OBJCNT_ENTRY(keys),
+};
+
+/* 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.
+ */
+static int sctp_objcnt_seq_show(struct seq_file *seq, void *v)
+{
+	int i, len;
+
+	i = (int)*(loff_t *)v;
+	seq_printf(seq, "%s: %d%n", sctp_dbg_objcnt[i].label,
+				atomic_read(sctp_dbg_objcnt[i].counter), &len);
+	seq_printf(seq, "%*s\n", 127 - len, "");
+	return 0;
+}
+
+static void *sctp_objcnt_seq_start(struct seq_file *seq, loff_t *pos)
+{
+	return (*pos >= ARRAY_SIZE(sctp_dbg_objcnt)) ? NULL : (void *)pos;
+}
+
+static void sctp_objcnt_seq_stop(struct seq_file *seq, void *v)
+{
+}
+
+static void * sctp_objcnt_seq_next(struct seq_file *seq, void *v, loff_t *pos)
+{
+	++*pos;
+	return (*pos >= ARRAY_SIZE(sctp_dbg_objcnt)) ? NULL : (void *)pos;
+}
+
+static const struct seq_operations sctp_objcnt_seq_ops = {
+	.start = sctp_objcnt_seq_start,
+	.next  = sctp_objcnt_seq_next,
+	.stop  = sctp_objcnt_seq_stop,
+	.show  = sctp_objcnt_seq_show,
+};
+
+static int sctp_objcnt_seq_open(struct inode *inode, struct file *file)
+{
+	return seq_open(file, &sctp_objcnt_seq_ops);
+}
+
+static const struct file_operations sctp_objcnt_ops = {
+	.open	 = sctp_objcnt_seq_open,
+	.read	 = seq_read,
+	.llseek	 = seq_lseek,
+	.release = seq_release,
+};
+
+/* Initialize the objcount in the proc filesystem.  */
+void sctp_dbg_objcnt_init(void)
+{
+	struct proc_dir_entry *ent;
+
+	ent = proc_create("sctp_dbg_objcnt", 0,
+			  proc_net_sctp, &sctp_objcnt_ops);
+	if (!ent)
+		printk(KERN_WARNING
+			"sctp_dbg_objcnt: Unable to create /proc entry.\n");
+}
+
+/* Cleanup the objcount entry in the proc filesystem.  */
+void sctp_dbg_objcnt_exit(void)
+{
+	remove_proc_entry("sctp_dbg_objcnt", proc_net_sctp);
+}
+
+

kernel/net/sctp/output.c

@@ -0,0 +1,790 @@
+/* SCTP kernel 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 implementation
+ *
+ * These functions handle output processing.
+ *
+ * This SCTP implementation is free software;
+ * you can redistribute it and/or modify it under the terms of
+ * the GNU General Public License as published by
+ * the Free Software Foundation; either version 2, or (at your option)
+ * any later version.
+ *
+ * This SCTP implementation is distributed in the hope that it
+ * will be useful, but WITHOUT ANY WARRANTY; without even the implied
+ *                 ************************
+ * warranty of MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.
+ * See the GNU General Public License for more details.
+ *
+ * You should have received a copy of the GNU General Public License
+ * along with GNU CC; see the file COPYING.  If not, write to
+ * the Free Software Foundation, 59 Temple Place - Suite 330,
+ * Boston, MA 02111-1307, USA.
+ *
+ * Please send any bug reports or fixes you make to the
+ * email address(es):
+ *    lksctp developers <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/ip.h>
+#include <net/icmp.h>
+#include <net/net_namespace.h>
+
+#include <linux/socket.h> /* for sa_family_t */
+#include <net/sock.h>
+
+#include <net/sctp/sctp.h>
+#include <net/sctp/sm.h>
+#include <net/sctp/checksum.h>
+
+/* Forward declarations for private helpers. */
+static sctp_xmit_t sctp_packet_can_append_data(struct sctp_packet *packet,
+					   struct sctp_chunk *chunk);
+static void sctp_packet_append_data(struct sctp_packet *packet,
+					   struct sctp_chunk *chunk);
+static sctp_xmit_t sctp_packet_will_fit(struct sctp_packet *packet,
+					struct sctp_chunk *chunk,
+					u16 chunk_len);
+
+static void sctp_packet_reset(struct sctp_packet *packet)
+{
+	packet->size = packet->overhead;
+	packet->has_cookie_echo = 0;
+	packet->has_sack = 0;
+	packet->has_data = 0;
+	packet->has_auth = 0;
+	packet->ipfragok = 0;
+	packet->auth = NULL;
+}
+
+/* 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", __func__,
+			  packet, vtag);
+
+	packet->vtag = vtag;
+
+	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", __func__,
+			  packet, transport);
+
+	packet->transport = transport;
+	packet->source_port = sport;
+	packet->destination_port = dport;
+	INIT_LIST_HEAD(&packet->chunk_list);
+	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;
+	sctp_packet_reset(packet);
+	packet->vtag = 0;
+	packet->malloced = 0;
+	return packet;
+}
+
+/* Free a packet.  */
+void sctp_packet_free(struct sctp_packet *packet)
+{
+	struct sctp_chunk *chunk, *tmp;
+
+	SCTP_DEBUG_PRINTK("%s: packet:%p\n", __func__, packet);
+
+	list_for_each_entry_safe(chunk, tmp, &packet->chunk_list, list) {
+		list_del_init(&chunk->list);
+		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,
+				       int one_packet)
+{
+	sctp_xmit_t retval;
+	int error = 0;
+
+	SCTP_DEBUG_PRINTK("%s: packet:%p chunk:%p\n", __func__,
+			  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.
+			 */
+			if (!one_packet)
+				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 an auth chunk into the packet. */
+static sctp_xmit_t sctp_packet_bundle_auth(struct sctp_packet *pkt,
+					   struct sctp_chunk *chunk)
+{
+	struct sctp_association *asoc = pkt->transport->asoc;
+	struct sctp_chunk *auth;
+	sctp_xmit_t retval = SCTP_XMIT_OK;
+
+	/* if we don't have an association, we can't do authentication */
+	if (!asoc)
+		return retval;
+
+	/* See if this is an auth chunk we are bundling or if
+	 * auth is already bundled.
+	 */
+	if (chunk->chunk_hdr->type == SCTP_CID_AUTH || pkt->has_auth)
+		return retval;
+
+	/* if the peer did not request this chunk to be authenticated,
+	 * don't do it
+	 */
+	if (!chunk->auth)
+		return retval;
+
+	auth = sctp_make_auth(asoc);
+	if (!auth)
+		return retval;
+
+	retval = sctp_packet_append_chunk(pkt, auth);
+
+	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;
+		struct timer_list *timer;
+		asoc = pkt->transport->asoc;
+		timer = &asoc->timers[SCTP_EVENT_TIMEOUT_SACK];
+
+		/* If the SACK timer is running, we have a pending SACK */
+		if (timer_pending(timer)) {
+			struct sctp_chunk *sack;
+			asoc->a_rwnd = asoc->rwnd;
+			sack = sctp_make_sack(asoc);
+			if (sack) {
+				retval = sctp_packet_append_chunk(pkt, sack);
+				asoc->peer.sack_needed = 0;
+				if (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));
+
+	SCTP_DEBUG_PRINTK("%s: packet:%p chunk:%p\n", __func__, packet,
+			  chunk);
+
+	/* Data chunks are special.  Before seeing what else we can
+	 * bundle into this packet, check to see if we are allowed to
+	 * send this DATA.
+	 */
+	if (sctp_chunk_is_data(chunk)) {
+		retval = sctp_packet_can_append_data(packet, chunk);
+		if (retval != SCTP_XMIT_OK)
+			goto finish;
+	}
+
+	/* Try to bundle AUTH chunk */
+	retval = sctp_packet_bundle_auth(packet, chunk);
+	if (retval != SCTP_XMIT_OK)
+		goto finish;
+
+	/* Try to bundle SACK chunk */
+	retval = sctp_packet_bundle_sack(packet, chunk);
+	if (retval != SCTP_XMIT_OK)
+		goto finish;
+
+	/* Check to see if this chunk will fit into the packet */
+	retval = sctp_packet_will_fit(packet, chunk, chunk_len);
+	if (retval != SCTP_XMIT_OK)
+		goto finish;
+
+	/* We believe that this chunk is OK to add to the packet */
+	switch (chunk->chunk_hdr->type) {
+	    case SCTP_CID_DATA:
+		/* Account for the data being in the packet */
+		sctp_packet_append_data(packet, chunk);
+		/* Disallow SACK bundling after DATA. */
+		packet->has_sack = 1;
+		/* Disallow AUTH bundling after DATA */
+		packet->has_auth = 1;
+		/* Let it be knows that packet has DATA in it */
+		packet->has_data = 1;
+		/* timestamp the chunk for rtx purposes */
+		chunk->sent_at = jiffies;
+		break;
+	    case SCTP_CID_COOKIE_ECHO:
+		packet->has_cookie_echo = 1;
+		break;
+
+	    case SCTP_CID_SACK:
+		packet->has_sack = 1;
+		break;
+
+	    case SCTP_CID_AUTH:
+		packet->has_auth = 1;
+		packet->auth = chunk;
+		break;
+	}
+
+	/* It is OK to send this chunk.  */
+	list_add_tail(&chunk->list, &packet->chunk_list);
+	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;
+	struct sk_buff *nskb;
+	struct sctp_chunk *chunk, *tmp;
+	struct sock *sk;
+	int err = 0;
+	int padding;		/* How much padding do we need?  */
+	__u8 has_data = 0;
+	struct dst_entry *dst = tp->dst;
+	unsigned char *auth = NULL;	/* pointer to auth in skb data */
+	__u32 cksum_buf_len = sizeof(struct sctphdr);
+
+	SCTP_DEBUG_PRINTK("%s: packet:%p\n", __func__, packet);
+
+	/* Do NOT generate a chunkless packet. */
+	if (list_empty(&packet->chunk_list))
+		return err;
+
+	/* Set up convenience variables... */
+	chunk = list_entry(packet->chunk_list.next, struct sctp_chunk, list);
+	sk = chunk->skb->sk;
+
+	/* Allocate the new skb.  */
+	nskb = alloc_skb(packet->size + LL_MAX_HEADER, GFP_ATOMIC);
+	if (!nskb)
+		goto nomem;
+
+	/* Make sure the outbound skb has enough header room reserved. */
+	skb_reserve(nskb, packet->overhead + LL_MAX_HEADER);
+
+	/* Set the owning socket so that we know where to get the
+	 * destination IP address.
+	 */
+	skb_set_owner_w(nskb, sk);
+
+	/* 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));
+		if (asoc && (asoc->param_flags & SPP_PMTUD_ENABLE)) {
+			sctp_assoc_sync_pmtu(asoc);
+		}
+	}
+	dst = dst_clone(tp->dst);
+	skb_dst_set(nskb, dst);
+	if (!dst)
+		goto no_route;
+
+	/* Build the SCTP header.  */
+	sh = (struct sctphdr *)skb_push(nskb, sizeof(struct sctphdr));
+	skb_reset_transport_header(nskb);
+	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;
+
+	/**
+	 * 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");
+	list_for_each_entry_safe(chunk, tmp, &packet->chunk_list, list) {
+		list_del_init(&chunk->list);
+		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;
+
+			has_data = 1;
+		}
+
+		padding = WORD_ROUND(chunk->skb->len) - chunk->skb->len;
+		if (padding)
+			memset(skb_put(chunk->skb, padding), 0, padding);
+
+		/* if this is the auth chunk that we are adding,
+		 * store pointer where it will be added and put
+		 * the auth into the packet.
+		 */
+		if (chunk == packet->auth)
+			auth = skb_tail_pointer(nskb);
+
+		cksum_buf_len += chunk->skb->len;
+		memcpy(skb_put(nskb, chunk->skb->len),
+			       chunk->skb->data, chunk->skb->len);
+
+		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);
+	}
+
+	/* SCTP-AUTH, Section 6.2
+	 *    The sender MUST calculate the MAC as described in RFC2104 [2]
+	 *    using the hash function H as described by the MAC Identifier and
+	 *    the shared association key K based on the endpoint pair shared key
+	 *    described by the shared key identifier.  The 'data' used for the
+	 *    computation of the AUTH-chunk is given by the AUTH chunk with its
+	 *    HMAC field set to zero (as shown in Figure 6) followed by all
+	 *    chunks that are placed after the AUTH chunk in the SCTP packet.
+	 */
+	if (auth)
+		sctp_auth_calculate_hmac(asoc, nskb,
+					(struct sctp_auth_chunk *)auth,
+					GFP_ATOMIC);
+
+	/* 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>.
+	 */
+	if (!sctp_checksum_disable &&
+	    !(dst->dev->features & (NETIF_F_NO_CSUM | NETIF_F_SCTP_CSUM))) {
+		__u32 crc32 = sctp_start_cksum((__u8 *)sh, cksum_buf_len);
+
+		/* 3) Put the resultant value into the checksum field in the
+		 *    common header, and leave the rest of the bits unchanged.
+		 */
+		sh->checksum = sctp_end_cksum(crc32);
+	} else {
+		if (dst->dev->features & NETIF_F_SCTP_CSUM) {
+			/* no need to seed psuedo checksum for SCTP */
+			nskb->ip_summed = CHECKSUM_PARTIAL;
+			nskb->csum_start = (skb_transport_header(nskb) -
+			                    nskb->head);
+			nskb->csum_offset = offsetof(struct sctphdr, checksum);
+		} else {
+			nskb->ip_summed = CHECKSUM_UNNECESSARY;
+		}
+	}
+
+	/* 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().
+	 */
+	(*tp->af_specific->ecn_capable)(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);
+		}
+	}
+
+	SCTP_DEBUG_PRINTK("***sctp_transmit_packet*** skb len %d\n",
+			  nskb->len);
+
+	nskb->local_df = packet->ipfragok;
+	(*tp->af_specific->sctp_xmit)(nskb, tp);
+
+out:
+	sctp_packet_reset(packet);
+	return err;
+no_route:
+	kfree_skb(nskb);
+	IP_INC_STATS_BH(&init_net, 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.
+	 */
+
+	list_for_each_entry_safe(chunk, tmp, &packet->chunk_list, list) {
+		list_del_init(&chunk->list);
+		if (!sctp_chunk_is_data(chunk))
+			sctp_chunk_free(chunk);
+	}
+	goto out;
+nomem:
+	err = -ENOMEM;
+	goto err;
+}
+
+/********************************************************************
+ * 2nd Level Abstractions
+ ********************************************************************/
+
+/* This private function check to see if a chunk can be added */
+static sctp_xmit_t sctp_packet_can_append_data(struct sctp_packet *packet,
+					   struct sctp_chunk *chunk)
+{
+	sctp_xmit_t retval = SCTP_XMIT_OK;
+	size_t datasize, rwnd, inflight, flight_size;
+	struct sctp_transport *transport = packet->transport;
+	__u32 max_burst_bytes;
+	struct sctp_association *asoc = transport->asoc;
+	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 = q->outstanding_bytes;
+	flight_size = transport->flight_size;
+
+	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->pathmtu;
+	if ((flight_size + max_burst_bytes) < transport->cwnd) {
+		transport->cwnd = 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",
+				  __func__, 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 != SCTP_NEED_FRTX)
+		if (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 (!sctp_sk(asoc->base.sk)->nodelay && sctp_packet_empty(packet) &&
+	    inflight && sctp_state(asoc, ESTABLISHED)) {
+		unsigned max = transport->pathmtu - packet->overhead;
+		unsigned len = chunk->skb->len + 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.
+		 * Don't delay large message writes that may have been
+		 * fragmeneted into small peices.
+		 */
+		if ((len < max) && (chunk->msg->msg_size < max)) {
+			retval = SCTP_XMIT_NAGLE_DELAY;
+			goto finish;
+		}
+	}
+
+finish:
+	return retval;
+}
+
+/* This private function does management things when adding DATA chunk */
+static void sctp_packet_append_data(struct sctp_packet *packet,
+				struct sctp_chunk *chunk)
+{
+	struct sctp_transport *transport = packet->transport;
+	size_t datasize = sctp_data_size(chunk);
+	struct sctp_association *asoc = transport->asoc;
+	u32 rwnd = asoc->peer.rwnd;
+
+	/* 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. Include sk_buff overhead
+	 * while updating peer.rwnd so that it reduces the chances of a
+	 * receiver running out of receive buffer space even when receive
+	 * window is still open. This can happen when a sender is sending
+	 * sending small messages.
+	 */
+	datasize += sizeof(struct sk_buff);
+	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;
+}
+
+static sctp_xmit_t sctp_packet_will_fit(struct sctp_packet *packet,
+					struct sctp_chunk *chunk,
+					u16 chunk_len)
+{
+	size_t psize;
+	size_t pmtu;
+	int too_big;
+	sctp_xmit_t retval = SCTP_XMIT_OK;
+
+	psize = packet->size;
+	pmtu  = ((packet->transport->asoc) ?
+		(packet->transport->asoc->pathmtu) :
+		(packet->transport->pathmtu));
+
+	too_big = (psize + chunk_len > pmtu);
+
+	/* Decide if we need to fragment or resubmit later. */
+	if (too_big) {
+		/* It's OK to fragmet at IP level if any one of the following
+		 * is true:
+		 * 	1. The packet is empty (meaning this chunk is greater
+		 * 	   the MTU)
+		 * 	2. The chunk we are adding is a control chunk
+		 * 	3. The packet doesn't have any data in it yet and data
+		 * 	requires authentication.
+		 */
+		if (sctp_packet_empty(packet) || !sctp_chunk_is_data(chunk) ||
+		    (!packet->has_data && chunk->auth)) {
+			/* We no longer do re-fragmentation.
+			 * Just fragment at the IP layer, if we
+			 * actually hit this condition
+			 */
+			packet->ipfragok = 1;
+		} else {
+			retval = SCTP_XMIT_PMTU_FULL;
+		}
+	}
+
+	return retval;
+}

kernel/net/sctp/primitive.c

@@ -0,0 +1,219 @@
+/* SCTP kernel implementation
+ * Copyright (c) 1999-2000 Cisco, Inc.
+ * Copyright (c) 1999-2001 Motorola, Inc.
+ *
+ * This file is part of the SCTP kernel 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.
+ *
+ * This SCTP implementation is free software;
+ * you can redistribute it and/or modify it under the terms of
+ * the GNU General Public License as published by
+ * the Free Software Foundation; either version 2, or (at your option)
+ * any later version.
+ *
+ * This SCTP implementation is distributed in the hope that it
+ * will be useful, but WITHOUT ANY WARRANTY; without even the implied
+ *                 ************************
+ * warranty of MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.
+ * See the GNU General Public License for more details.
+ *
+ * You should have received a copy of the GNU General Public License
+ * along with GNU CC; see the file COPYING.  If not, write to
+ * the Free Software Foundation, 59 Temple Place - Suite 330,
+ * Boston, MA 02111-1307, USA.
+ *
+ * Please send any bug reports or fixes you make to the
+ * email address(es):
+ *    lksctp developers <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);

kernel/net/sctp/proc.c

@@ -0,0 +1,519 @@
+/* SCTP kernel implementation
+ * Copyright (c) 2003 International Business Machines, Corp.
+ *
+ * This file is part of the SCTP kernel implementation
+ *
+ * This SCTP implementation is free software;
+ * you can redistribute it and/or modify it under the terms of
+ * the GNU General Public License as published by
+ * the Free Software Foundation; either version 2, or (at your option)
+ * any later version.
+ *
+ * This SCTP implementation is distributed in the hope that it
+ * will be useful, but WITHOUT ANY WARRANTY; without even the implied
+ *                 ************************
+ * warranty of MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.
+ * See the GNU General Public License for more details.
+ *
+ * You should have received a copy of the GNU General Public License
+ * along with GNU CC; see the file COPYING.  If not, write to
+ * the Free Software Foundation, 59 Temple Place - Suite 330,
+ * Boston, MA 02111-1307, USA.
+ *
+ * Please send any bug reports or fixes you make to the
+ * email address(es):
+ *    lksctp developers <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>
+#include <net/ip.h> /* for snmp_fold_field */
+
+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),
+	SNMP_MIB_ITEM("SctpT1InitExpireds", SCTP_MIB_T1_INIT_EXPIREDS),
+	SNMP_MIB_ITEM("SctpT1CookieExpireds", SCTP_MIB_T1_COOKIE_EXPIREDS),
+	SNMP_MIB_ITEM("SctpT2ShutdownExpireds", SCTP_MIB_T2_SHUTDOWN_EXPIREDS),
+	SNMP_MIB_ITEM("SctpT3RtxExpireds", SCTP_MIB_T3_RTX_EXPIREDS),
+	SNMP_MIB_ITEM("SctpT4RtoExpireds", SCTP_MIB_T4_RTO_EXPIREDS),
+	SNMP_MIB_ITEM("SctpT5ShutdownGuardExpireds", SCTP_MIB_T5_SHUTDOWN_GUARD_EXPIREDS),
+	SNMP_MIB_ITEM("SctpDelaySackExpireds", SCTP_MIB_DELAY_SACK_EXPIREDS),
+	SNMP_MIB_ITEM("SctpAutocloseExpireds", SCTP_MIB_AUTOCLOSE_EXPIREDS),
+	SNMP_MIB_ITEM("SctpT3Retransmits", SCTP_MIB_T3_RETRANSMITS),
+	SNMP_MIB_ITEM("SctpPmtudRetransmits", SCTP_MIB_PMTUD_RETRANSMITS),
+	SNMP_MIB_ITEM("SctpFastRetransmits", SCTP_MIB_FAST_RETRANSMITS),
+	SNMP_MIB_ITEM("SctpInPktSoftirq", SCTP_MIB_IN_PKT_SOFTIRQ),
+	SNMP_MIB_ITEM("SctpInPktBacklog", SCTP_MIB_IN_PKT_BACKLOG),
+	SNMP_MIB_ITEM("SctpInPktDiscards", SCTP_MIB_IN_PKT_DISCARDS),
+	SNMP_MIB_ITEM("SctpInDataChunkDiscards", SCTP_MIB_IN_DATA_CHUNK_DISCARDS),
+	SNMP_MIB_SENTINEL
+};
+
+/* 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,
+			   snmp_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 const 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 = proc_create("snmp", S_IRUGO, proc_net_sctp, &sctp_snmp_seq_fops);
+	if (!p)
+		return -ENOMEM;
+
+	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 sctp_association *asoc;
+	struct sctp_sockaddr_entry *laddr;
+	struct sctp_transport *peer;
+	union sctp_addr *addr, *primary = NULL;
+	struct sctp_af *af;
+
+	if (epb->type == SCTP_EP_TYPE_ASSOCIATION) {
+	    asoc = sctp_assoc(epb);
+	    peer = asoc->peer.primary_path;
+	    primary = &peer->saddr;
+	}
+
+	list_for_each_entry(laddr, &epb->bind_addr.address_list, list) {
+		addr = &laddr->a;
+		af = sctp_get_af_specific(addr->sa.sa_family);
+		if (primary && af->cmp_addr(addr, primary)) {
+			seq_printf(seq, "*");
+		}
+		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 sctp_transport *transport;
+	union sctp_addr *addr, *primary;
+	struct sctp_af *af;
+
+	primary = &assoc->peer.primary_addr;
+	list_for_each_entry(transport, &assoc->peer.transport_addr_list,
+			transports) {
+		addr = &transport->ipaddr;
+		af = sctp_get_af_specific(addr->sa.sa_family);
+		if (af->cmp_addr(addr, primary)) {
+			seq_printf(seq, "*");
+		}
+		af->seq_dump_addr(seq, addr);
+	}
+}
+
+static void * sctp_eps_seq_start(struct seq_file *seq, loff_t *pos)
+{
+	if (*pos >= sctp_ep_hashsize)
+		return NULL;
+
+	if (*pos < 0)
+		*pos = 0;
+
+	if (*pos == 0)
+		seq_printf(seq, " ENDPT     SOCK   STY SST HBKT LPORT   UID INODE LADDRS\n");
+
+	return (void *)pos;
+}
+
+static void sctp_eps_seq_stop(struct seq_file *seq, void *v)
+{
+	return;
+}
+
+
+static void * sctp_eps_seq_next(struct seq_file *seq, void *v, loff_t *pos)
+{
+	if (++*pos >= sctp_ep_hashsize)
+		return NULL;
+
+	return pos;
+}
+
+
+/* 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;
+	struct hlist_node *node;
+	int    hash = *(loff_t *)v;
+
+	if (hash >= sctp_ep_hashsize)
+		return -ENOMEM;
+
+	head = &sctp_ep_hashtable[hash];
+	sctp_local_bh_disable();
+	read_lock(&head->lock);
+	sctp_for_each_hentry(epb, node, &head->chain) {
+		ep = sctp_ep(epb);
+		sk = epb->sk;
+		seq_printf(seq, "%8p %8p %-3d %-3d %-4d %-5d %5d %5lu ", ep, sk,
+			   sctp_sk(sk)->type, sk->sk_state, hash,
+			   epb->bind_addr.port,
+			   sock_i_uid(sk), sock_i_ino(sk));
+
+		sctp_seq_dump_local_addrs(seq, epb);
+		seq_printf(seq, "\n");
+	}
+	read_unlock(&head->lock);
+	sctp_local_bh_enable();
+
+	return 0;
+}
+
+static const struct seq_operations sctp_eps_ops = {
+	.start = sctp_eps_seq_start,
+	.next  = sctp_eps_seq_next,
+	.stop  = sctp_eps_seq_stop,
+	.show  = sctp_eps_seq_show,
+};
+
+
+/* Initialize the seq file operations for 'eps' object. */
+static int sctp_eps_seq_open(struct inode *inode, struct file *file)
+{
+	return seq_open(file, &sctp_eps_ops);
+}
+
+static const struct file_operations sctp_eps_seq_fops = {
+	.open	 = sctp_eps_seq_open,
+	.read	 = seq_read,
+	.llseek	 = seq_lseek,
+	.release = seq_release,
+};
+
+/* Set up the proc fs entry for 'eps' object. */
+int __init sctp_eps_proc_init(void)
+{
+	struct proc_dir_entry *p;
+
+	p = proc_create("eps", S_IRUGO, proc_net_sctp, &sctp_eps_seq_fops);
+	if (!p)
+		return -ENOMEM;
+
+	return 0;
+}
+
+/* Cleanup the proc fs entry for 'eps' object. */
+void sctp_eps_proc_exit(void)
+{
+	remove_proc_entry("eps", proc_net_sctp);
+}
+
+
+static void * sctp_assocs_seq_start(struct seq_file *seq, loff_t *pos)
+{
+	if (*pos >= sctp_assoc_hashsize)
+		return NULL;
+
+	if (*pos < 0)
+		*pos = 0;
+
+	if (*pos == 0)
+		seq_printf(seq, " ASSOC     SOCK   STY SST ST HBKT "
+				"ASSOC-ID TX_QUEUE RX_QUEUE UID INODE LPORT "
+				"RPORT LADDRS <-> RADDRS "
+				"HBINT INS OUTS MAXRT T1X T2X RTXC\n");
+
+	return (void *)pos;
+}
+
+static void sctp_assocs_seq_stop(struct seq_file *seq, void *v)
+{
+	return;
+}
+
+
+static void * sctp_assocs_seq_next(struct seq_file *seq, void *v, loff_t *pos)
+{
+	if (++*pos >= sctp_assoc_hashsize)
+		return NULL;
+
+	return pos;
+}
+
+/* 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;
+	struct hlist_node *node;
+	int    hash = *(loff_t *)v;
+
+	if (hash >= sctp_assoc_hashsize)
+		return -ENOMEM;
+
+	head = &sctp_assoc_hashtable[hash];
+	sctp_local_bh_disable();
+	read_lock(&head->lock);
+	sctp_for_each_hentry(epb, node, &head->chain) {
+		assoc = sctp_assoc(epb);
+		sk = epb->sk;
+		seq_printf(seq,
+			   "%8p %8p %-3d %-3d %-2d %-4d "
+			   "%4d %8d %8d %7d %5lu %-5d %5d ",
+			   assoc, sk, sctp_sk(sk)->type, sk->sk_state,
+			   assoc->state, hash,
+			   assoc->assoc_id,
+			   assoc->sndbuf_used,
+			   atomic_read(&assoc->rmem_alloc),
+			   sock_i_uid(sk), sock_i_ino(sk),
+			   epb->bind_addr.port,
+			   assoc->peer.port);
+		seq_printf(seq, " ");
+		sctp_seq_dump_local_addrs(seq, epb);
+		seq_printf(seq, "<-> ");
+		sctp_seq_dump_remote_addrs(seq, assoc);
+		seq_printf(seq, "\t%8lu %5d %5d %4d %4d %4d %8d ",
+			assoc->hbinterval, assoc->c.sinit_max_instreams,
+			assoc->c.sinit_num_ostreams, assoc->max_retrans,
+			assoc->init_retries, assoc->shutdown_retries,
+			assoc->rtx_data_chunks);
+		seq_printf(seq, "\n");
+	}
+	read_unlock(&head->lock);
+	sctp_local_bh_enable();
+
+	return 0;
+}
+
+static const struct seq_operations sctp_assoc_ops = {
+	.start = sctp_assocs_seq_start,
+	.next  = sctp_assocs_seq_next,
+	.stop  = sctp_assocs_seq_stop,
+	.show  = sctp_assocs_seq_show,
+};
+
+/* Initialize the seq file operations for 'assocs' object. */
+static int sctp_assocs_seq_open(struct inode *inode, struct file *file)
+{
+	return seq_open(file, &sctp_assoc_ops);
+}
+
+static const struct file_operations sctp_assocs_seq_fops = {
+	.open	 = sctp_assocs_seq_open,
+	.read	 = seq_read,
+	.llseek	 = seq_lseek,
+	.release = seq_release,
+};
+
+/* Set up the proc fs entry for 'assocs' object. */
+int __init sctp_assocs_proc_init(void)
+{
+	struct proc_dir_entry *p;
+
+	p = proc_create("assocs", S_IRUGO, proc_net_sctp,
+			&sctp_assocs_seq_fops);
+	if (!p)
+		return -ENOMEM;
+
+	return 0;
+}
+
+/* Cleanup the proc fs entry for 'assocs' object. */
+void sctp_assocs_proc_exit(void)
+{
+	remove_proc_entry("assocs", proc_net_sctp);
+}
+
+static void *sctp_remaddr_seq_start(struct seq_file *seq, loff_t *pos)
+{
+	if (*pos >= sctp_assoc_hashsize)
+		return NULL;
+
+	if (*pos < 0)
+		*pos = 0;
+
+	if (*pos == 0)
+		seq_printf(seq, "ADDR ASSOC_ID HB_ACT RTO MAX_PATH_RTX "
+				"REM_ADDR_RTX  START\n");
+
+	return (void *)pos;
+}
+
+static void *sctp_remaddr_seq_next(struct seq_file *seq, void *v, loff_t *pos)
+{
+	if (++*pos >= sctp_assoc_hashsize)
+		return NULL;
+
+	return pos;
+}
+
+static void sctp_remaddr_seq_stop(struct seq_file *seq, void *v)
+{
+	return;
+}
+
+static int sctp_remaddr_seq_show(struct seq_file *seq, void *v)
+{
+	struct sctp_hashbucket *head;
+	struct sctp_ep_common *epb;
+	struct sctp_association *assoc;
+	struct hlist_node *node;
+	struct sctp_transport *tsp;
+	int    hash = *(loff_t *)v;
+
+	if (hash >= sctp_assoc_hashsize)
+		return -ENOMEM;
+
+	head = &sctp_assoc_hashtable[hash];
+	sctp_local_bh_disable();
+	read_lock(&head->lock);
+	sctp_for_each_hentry(epb, node, &head->chain) {
+		assoc = sctp_assoc(epb);
+		list_for_each_entry(tsp, &assoc->peer.transport_addr_list,
+					transports) {
+			/*
+			 * The remote address (ADDR)
+			 */
+			tsp->af_specific->seq_dump_addr(seq, &tsp->ipaddr);
+			seq_printf(seq, " ");
+
+			/*
+			 * The association ID (ASSOC_ID)
+			 */
+			seq_printf(seq, "%d ", tsp->asoc->assoc_id);
+
+			/*
+			 * If the Heartbeat is active (HB_ACT)
+			 * Note: 1 = Active, 0 = Inactive
+			 */
+			seq_printf(seq, "%d ", timer_pending(&tsp->hb_timer));
+
+			/*
+			 * Retransmit time out (RTO)
+			 */
+			seq_printf(seq, "%lu ", tsp->rto);
+
+			/*
+			 * Maximum path retransmit count (PATH_MAX_RTX)
+			 */
+			seq_printf(seq, "%d ", tsp->pathmaxrxt);
+
+			/*
+			 * remote address retransmit count (REM_ADDR_RTX)
+			 * Note: We don't have a way to tally this at the moment
+			 * so lets just leave it as zero for the moment
+			 */
+			seq_printf(seq, "0 ");
+
+			/*
+			 * remote address start time (START).  This is also not
+			 * currently implemented, but we can record it with a
+			 * jiffies marker in a subsequent patch
+			 */
+			seq_printf(seq, "0");
+
+			seq_printf(seq, "\n");
+		}
+	}
+
+	read_unlock(&head->lock);
+	sctp_local_bh_enable();
+
+	return 0;
+
+}
+
+static const struct seq_operations sctp_remaddr_ops = {
+	.start = sctp_remaddr_seq_start,
+	.next  = sctp_remaddr_seq_next,
+	.stop  = sctp_remaddr_seq_stop,
+	.show  = sctp_remaddr_seq_show,
+};
+
+/* Cleanup the proc fs entry for 'remaddr' object. */
+void sctp_remaddr_proc_exit(void)
+{
+	remove_proc_entry("remaddr", proc_net_sctp);
+}
+
+static int sctp_remaddr_seq_open(struct inode *inode, struct file *file)
+{
+	return seq_open(file, &sctp_remaddr_ops);
+}
+
+static const struct file_operations sctp_remaddr_seq_fops = {
+	.open = sctp_remaddr_seq_open,
+	.read = seq_read,
+	.llseek = seq_lseek,
+	.release = seq_release,
+};
+
+int __init sctp_remaddr_proc_init(void)
+{
+	struct proc_dir_entry *p;
+
+	p = proc_create("remaddr", S_IRUGO, proc_net_sctp, &sctp_remaddr_seq_fops);
+	if (!p)
+		return -ENOMEM;
+	return 0;
+}

kernel/net/sctp/ssnmap.c

@@ -0,0 +1,132 @@
+/* SCTP kernel implementation
+ * Copyright (c) 2003 International Business Machines, Corp.
+ *
+ * This file is part of the SCTP kernel implementation
+ *
+ * These functions manipulate sctp SSN tracker.
+ *
+ * This SCTP implementation is free software;
+ * you can redistribute it and/or modify it under the terms of
+ * the GNU General Public License as published by
+ * the Free Software Foundation; either version 2, or (at your option)
+ * any later version.
+ *
+ * This SCTP implementation is distributed in the hope that it
+ * will be useful, but WITHOUT ANY WARRANTY; without even the implied
+ *                 ************************
+ * warranty of MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.
+ * See the GNU General Public License for more details.
+ *
+ * You should have received a copy of the GNU General Public License
+ * along with GNU CC; see the file COPYING.  If not, write to
+ * the Free Software Foundation, 59 Temple Place - Suite 330,
+ * Boston, MA 02111-1307, USA.
+ *
+ * Please send any bug reports or fixes you make to the
+ * email address(es):
+ *    lksctp developers <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,
+				    gfp_t 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);
+	}
+}

kernel/net/sctp/sysctl.c

@@ -0,0 +1,308 @@
+/* SCTP kernel implementation
+ * (C) Copyright IBM Corp. 2002, 2004
+ * Copyright (c) 2002 Intel Corp.
+ *
+ * This file is part of the SCTP kernel implementation
+ *
+ * Sysctl related interfaces for SCTP.
+ *
+ * This SCTP implementation is free software;
+ * you can redistribute it and/or modify it under the terms of
+ * the GNU General Public License as published by
+ * the Free Software Foundation; either version 2, or (at your option)
+ * any later version.
+ *
+ * This SCTP implementation is distributed in the hope that it
+ * will be useful, but WITHOUT ANY WARRANTY; without even the implied
+ *                 ************************
+ * warranty of MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.
+ * See the GNU General Public License for more details.
+ *
+ * You should have received a copy of the GNU General Public License
+ * along with GNU CC; see the file COPYING.  If not, write to
+ * the Free Software Foundation, 59 Temple Place - Suite 330,
+ * Boston, MA 02111-1307, USA.
+ *
+ * Please send any bug reports or fixes you make to the
+ * email address(es):
+ *    lksctp developers <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 <net/sctp/sctp.h>
+#include <linux/sysctl.h>
+
+static int zero = 0;
+static int one = 1;
+static int timer_max = 86400000; /* ms in one day */
+static int int_max = INT_MAX;
+static int sack_timer_min = 1;
+static int sack_timer_max = 500;
+static int addr_scope_max = 3; /* check sctp_scope_policy_t in include/net/sctp/constants.h for max entries */
+
+extern int sysctl_sctp_mem[3];
+extern int sysctl_sctp_rmem[3];
+extern int sysctl_sctp_wmem[3];
+
+static ctl_table sctp_table[] = {
+	{
+		.ctl_name	= NET_SCTP_RTO_INITIAL,
+		.procname	= "rto_initial",
+		.data		= &sctp_rto_initial,
+		.maxlen		= sizeof(unsigned int),
+		.mode		= 0644,
+		.proc_handler	= proc_dointvec_minmax,
+		.strategy	= sysctl_intvec,
+		.extra1         = &one,
+		.extra2         = &timer_max
+	},
+	{
+		.ctl_name	= NET_SCTP_RTO_MIN,
+		.procname	= "rto_min",
+		.data		= &sctp_rto_min,
+		.maxlen		= sizeof(unsigned int),
+		.mode		= 0644,
+		.proc_handler	= proc_dointvec_minmax,
+		.strategy	= sysctl_intvec,
+		.extra1         = &one,
+		.extra2         = &timer_max
+	},
+	{
+		.ctl_name	= NET_SCTP_RTO_MAX,
+		.procname	= "rto_max",
+		.data		= &sctp_rto_max,
+		.maxlen		= sizeof(unsigned int),
+		.mode		= 0644,
+		.proc_handler	= proc_dointvec_minmax,
+		.strategy	= sysctl_intvec,
+		.extra1         = &one,
+		.extra2         = &timer_max
+	},
+	{
+		.ctl_name	= NET_SCTP_VALID_COOKIE_LIFE,
+		.procname	= "valid_cookie_life",
+		.data		= &sctp_valid_cookie_life,
+		.maxlen		= sizeof(unsigned int),
+		.mode		= 0644,
+		.proc_handler	= proc_dointvec_minmax,
+		.strategy	= sysctl_intvec,
+		.extra1         = &one,
+		.extra2         = &timer_max
+	},
+	{
+		.ctl_name	= NET_SCTP_MAX_BURST,
+		.procname	= "max_burst",
+		.data		= &sctp_max_burst,
+		.maxlen		= sizeof(int),
+		.mode		= 0644,
+		.proc_handler	= proc_dointvec_minmax,
+		.strategy	= sysctl_intvec,
+		.extra1		= &zero,
+		.extra2		= &int_max
+	},
+	{
+		.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_minmax,
+		.strategy	= sysctl_intvec,
+		.extra1		= &one,
+		.extra2		= &int_max
+	},
+	{
+		.ctl_name	= NET_SCTP_SNDBUF_POLICY,
+		.procname	= "sndbuf_policy",
+		.data		= &sctp_sndbuf_policy,
+		.maxlen		= sizeof(int),
+		.mode		= 0644,
+		.proc_handler	= proc_dointvec,
+		.strategy	= sysctl_intvec
+	},
+	{
+		.ctl_name	= NET_SCTP_RCVBUF_POLICY,
+		.procname	= "rcvbuf_policy",
+		.data		= &sctp_rcvbuf_policy,
+		.maxlen		= sizeof(int),
+		.mode		= 0644,
+		.proc_handler	= proc_dointvec,
+		.strategy	= sysctl_intvec
+	},
+	{
+		.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_minmax,
+		.strategy	= sysctl_intvec,
+		.extra1		= &one,
+		.extra2		= &int_max
+	},
+	{
+		.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_minmax,
+		.strategy	= sysctl_intvec,
+		.extra1		= &one,
+		.extra2		= &int_max
+	},
+	{
+		.ctl_name	= NET_SCTP_HB_INTERVAL,
+		.procname	= "hb_interval",
+		.data		= &sctp_hb_interval,
+		.maxlen		= sizeof(unsigned int),
+		.mode		= 0644,
+		.proc_handler	= proc_dointvec_minmax,
+		.strategy	= sysctl_intvec,
+		.extra1         = &one,
+		.extra2         = &timer_max
+	},
+	{
+		.ctl_name	= NET_SCTP_PRESERVE_ENABLE,
+		.procname	= "cookie_preserve_enable",
+		.data		= &sctp_cookie_preserve_enable,
+		.maxlen		= sizeof(int),
+		.mode		= 0644,
+		.proc_handler	= proc_dointvec,
+		.strategy	= sysctl_intvec
+	},
+	{
+		.ctl_name	= NET_SCTP_RTO_ALPHA,
+		.procname	= "rto_alpha_exp_divisor",
+		.data		= &sctp_rto_alpha,
+		.maxlen		= sizeof(int),
+		.mode		= 0444,
+		.proc_handler	= proc_dointvec,
+		.strategy	= sysctl_intvec
+	},
+	{
+		.ctl_name	= NET_SCTP_RTO_BETA,
+		.procname	= "rto_beta_exp_divisor",
+		.data		= &sctp_rto_beta,
+		.maxlen		= sizeof(int),
+		.mode		= 0444,
+		.proc_handler	= proc_dointvec,
+		.strategy	= sysctl_intvec
+	},
+	{
+		.ctl_name	= NET_SCTP_ADDIP_ENABLE,
+		.procname	= "addip_enable",
+		.data		= &sctp_addip_enable,
+		.maxlen		= sizeof(int),
+		.mode		= 0644,
+		.proc_handler	= proc_dointvec,
+		.strategy	= sysctl_intvec
+	},
+	{
+		.ctl_name	= NET_SCTP_PRSCTP_ENABLE,
+		.procname	= "prsctp_enable",
+		.data		= &sctp_prsctp_enable,
+		.maxlen		= sizeof(int),
+		.mode		= 0644,
+		.proc_handler	= proc_dointvec,
+		.strategy	= sysctl_intvec
+	},
+	{
+		.ctl_name	= NET_SCTP_SACK_TIMEOUT,
+		.procname	= "sack_timeout",
+		.data		= &sctp_sack_timeout,
+		.maxlen		= sizeof(int),
+		.mode		= 0644,
+		.proc_handler	= proc_dointvec_minmax,
+		.strategy	= sysctl_intvec,
+		.extra1         = &sack_timer_min,
+		.extra2         = &sack_timer_max,
+	},
+	{
+		.ctl_name	= CTL_UNNUMBERED,
+		.procname	= "sctp_mem",
+		.data		= &sysctl_sctp_mem,
+		.maxlen		= sizeof(sysctl_sctp_mem),
+		.mode		= 0644,
+		.proc_handler	= proc_dointvec,
+	},
+	{
+		.ctl_name	= CTL_UNNUMBERED,
+		.procname	= "sctp_rmem",
+		.data		= &sysctl_sctp_rmem,
+		.maxlen		= sizeof(sysctl_sctp_rmem),
+		.mode		= 0644,
+		.proc_handler	= proc_dointvec,
+	},
+	{
+		.ctl_name	= CTL_UNNUMBERED,
+		.procname	= "sctp_wmem",
+		.data		= &sysctl_sctp_wmem,
+		.maxlen		= sizeof(sysctl_sctp_wmem),
+		.mode		= 0644,
+		.proc_handler	= proc_dointvec,
+	},
+	{
+		.ctl_name	= CTL_UNNUMBERED,
+		.procname	= "auth_enable",
+		.data		= &sctp_auth_enable,
+		.maxlen		= sizeof(int),
+		.mode		= 0644,
+		.proc_handler	= proc_dointvec,
+		.strategy	= sysctl_intvec
+	},
+	{
+		.ctl_name	= CTL_UNNUMBERED,
+		.procname	= "addip_noauth_enable",
+		.data		= &sctp_addip_noauth,
+		.maxlen		= sizeof(int),
+		.mode		= 0644,
+		.proc_handler	= proc_dointvec,
+		.strategy	= sysctl_intvec
+	},
+	{
+		.ctl_name	= CTL_UNNUMBERED,
+		.procname	= "addr_scope_policy",
+		.data		= &sctp_scope_policy,
+		.maxlen		= sizeof(int),
+		.mode		= 0644,
+		.proc_handler	= &proc_dointvec_minmax,
+		.strategy	= &sysctl_intvec,
+		.extra1		= &zero,
+		.extra2		= &addr_scope_max,
+	},
+	{ .ctl_name = 0 }
+};
+
+static struct ctl_path sctp_path[] = {
+	{ .procname = "net", .ctl_name = CTL_NET, },
+	{ .procname = "sctp", .ctl_name = NET_SCTP, },
+	{ }
+};
+
+static struct ctl_table_header * sctp_sysctl_header;
+
+/* Sysctl registration.  */
+void sctp_sysctl_register(void)
+{
+	sctp_sysctl_header = register_sysctl_paths(sctp_path, sctp_table);
+}
+
+/* Sysctl deregistration.  */
+void sctp_sysctl_unregister(void)
+{
+	unregister_sysctl_table(sctp_sysctl_header);
+}

kernel/net/sctp/transport.c

@@ -0,0 +1,626 @@
+/* SCTP kernel implementation
+ * Copyright (c) 1999-2000 Cisco, Inc.
+ * Copyright (c) 1999-2001 Motorola, Inc.
+ * Copyright (c) 2001-2003 International Business Machines Corp.
+ * Copyright (c) 2001 Intel Corp.
+ * Copyright (c) 2001 La Monte H.P. Yarroll
+ *
+ * This file is part of the SCTP kernel 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.
+ *
+ * This SCTP implementation is free software;
+ * you can redistribute it and/or modify it under the terms of
+ * the GNU General Public License as published by
+ * the Free Software Foundation; either version 2, or (at your option)
+ * any later version.
+ *
+ * This SCTP implementation is distributed in the hope that it
+ * will be useful, but WITHOUT ANY WARRANTY; without even the implied
+ *                 ************************
+ * warranty of MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.
+ * See the GNU General Public License for more details.
+ *
+ * You should have received a copy of the GNU General Public License
+ * along with GNU CC; see the file COPYING.  If not, write to
+ * the Free Software Foundation, 59 Temple Place - Suite 330,
+ * Boston, MA 02111-1307, USA.
+ *
+ * Please send any bug reports or fixes you make to the
+ * email address(es):
+ *    lksctp developers <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 <linux/random.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,
+						  gfp_t 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->rto = msecs_to_jiffies(sctp_rto_initial);
+	peer->rtt = 0;
+	peer->rttvar = 0;
+	peer->srtt = 0;
+	peer->rto_pending = 0;
+	peer->hb_sent = 0;
+	peer->fast_recovery = 0;
+
+	peer->last_time_heard = jiffies;
+	peer->last_time_used = jiffies;
+	peer->last_time_ecne_reduced = jiffies;
+
+	peer->init_sent_count = 0;
+
+	peer->param_flags = SPP_HB_DISABLE |
+			    SPP_PMTUD_ENABLE |
+			    SPP_SACKDELAY_ENABLE;
+	peer->hbinterval  = 0;
+
+	/* Initialize the default path max_retrans.  */
+	peer->pathmaxrxt  = sctp_max_retrans_path;
+	peer->error_count = 0;
+
+	INIT_LIST_HEAD(&peer->transmitted);
+	INIT_LIST_HEAD(&peer->send_ready);
+	INIT_LIST_HEAD(&peer->transports);
+
+	peer->T3_rtx_timer.expires = 0;
+	peer->hb_timer.expires = 0;
+
+	setup_timer(&peer->T3_rtx_timer, sctp_generate_t3_rtx_event,
+			(unsigned long)peer);
+	setup_timer(&peer->hb_timer, sctp_generate_heartbeat_event,
+			(unsigned long)peer);
+	setup_timer(&peer->proto_unreach_timer,
+		    sctp_generate_proto_unreach_event, (unsigned long)peer);
+
+	/* Initialize the 64-bit random nonce sent with heartbeat. */
+	get_random_bytes(&peer->hb_nonce, sizeof(peer->hb_nonce));
+
+	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,
+					  gfp_t 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, int force)
+{
+	/* 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 (force || !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->pathmtu = dst_mtu(dst);
+		dst_release(dst);
+	} else
+		transport->pathmtu = SCTP_DEFAULT_MAXSEGMENT;
+}
+
+/* this is a complete rip-off from __sk_dst_check
+ * the cookie is always 0 since this is how it's used in the
+ * pmtu code
+ */
+static struct dst_entry *sctp_transport_dst_check(struct sctp_transport *t)
+{
+	struct dst_entry *dst = t->dst;
+
+	if (dst && dst->obsolete && dst->ops->check(dst, 0) == NULL) {
+		dst_release(t->dst);
+		t->dst = NULL;
+		return NULL;
+	}
+
+	return dst;
+}
+
+void sctp_transport_update_pmtu(struct sctp_transport *t, u32 pmtu)
+{
+	struct dst_entry *dst;
+
+	if (unlikely(pmtu < SCTP_DEFAULT_MINSEGMENT)) {
+		printk(KERN_WARNING "%s: Reported pmtu %d too low, "
+		       "using default minimum of %d\n",
+		       __func__, pmtu,
+		       SCTP_DEFAULT_MINSEGMENT);
+		/* Use default minimum segment size and disable
+		 * pmtu discovery on this transport.
+		 */
+		t->pathmtu = SCTP_DEFAULT_MINSEGMENT;
+	} else {
+		t->pathmtu = pmtu;
+	}
+
+	dst = sctp_transport_dst_check(t);
+	if (dst)
+		dst->ops->update_pmtu(dst, pmtu);
+}
+
+/* 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(opt, asoc, dst, daddr, &transport->saddr);
+
+	transport->dst = dst;
+	if ((transport->param_flags & SPP_PMTUD_DISABLE) && transport->pathmtu) {
+		return;
+	}
+	if (dst) {
+		transport->pathmtu = dst_mtu(dst);
+
+		/* Initialize sk->sk_rcv_saddr, if the transport is the
+		 * association's active path for getsockname().
+		 */
+		if (asoc && (!asoc->peer.primary_path ||
+				(transport == asoc->peer.active_path)))
+			opt->pf->af->to_sk_saddr(&transport->saddr,
+						 asoc->base.sk);
+	} else
+		transport->pathmtu = 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: %ld\n", __func__,
+			  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;
+
+	/* See if we need to exit Fast Recovery first */
+	if (transport->fast_recovery &&
+	    TSN_lte(transport->fast_recovery_exit, sack_ctsn))
+		transport->fast_recovery = 0;
+
+	/* The appropriate cwnd increase algorithm is performed if, and only
+	 * if the cumulative TSN whould advanced and the congestion window is
+	 * being fully utilized.
+	 */
+	if (TSN_lte(sack_ctsn, transport->asoc->ctsn_ack_point) ||
+	    (flight_size < cwnd))
+		return;
+
+	ssthresh = transport->ssthresh;
+	pba = transport->partial_bytes_acked;
+	pmtu = transport->asoc->pathmtu;
+
+	if (cwnd <= ssthresh) {
+		/* RFC 4960 7.2.1
+		 * o  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, an incoming SACK advances the Cumulative TSN
+		 *    Ack Point, and the data sender is not in Fast Recovery.
+		 *    Only when these three 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.  This upper bound protects
+		 *    against the ACK-Splitting attack outlined in [SAVAGE99].
+		 */
+		if (transport->fast_recovery)
+			return;
+
+		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",
+				  __func__,
+				  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",
+				  __func__,
+				  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->pathmtu);
+		transport->cwnd = transport->asoc->pathmtu;
+
+		/* T3-rtx also clears fast recovery on the transport */
+		transport->fast_recovery = 0;
+		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
+		 */
+		if (transport->fast_recovery)
+			return;
+
+		/* Mark Fast recovery */
+		transport->fast_recovery = 1;
+		transport->fast_recovery_exit = transport->asoc->next_tsn - 1;
+
+		transport->ssthresh = max(transport->cwnd/2,
+					  4*transport->asoc->pathmtu);
+		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 (time_after(jiffies, transport->last_time_ecne_reduced +
+					transport->rtt)) {
+			transport->ssthresh = max(transport->cwnd/2,
+						  4*transport->asoc->pathmtu);
+			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 (time_after(jiffies, transport->last_time_used +
+					transport->rto))
+			transport->cwnd = max(transport->cwnd/2,
+						 4*transport->asoc->pathmtu);
+		break;
+	}
+
+	transport->partial_bytes_acked = 0;
+	SCTP_DEBUG_PRINTK("%s: transport: %p reason: %d cwnd: "
+			  "%d ssthresh: %d\n", __func__,
+			  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->rto + sctp_jitter(t->rto);
+	if (t->state != SCTP_UNCONFIRMED)
+		timeout += t->hbinterval;
+	timeout += jiffies;
+	return timeout;
+}
+
+/* Reset transport variables to their initial values */
+void sctp_transport_reset(struct sctp_transport *t)
+{
+	struct sctp_association *asoc = t->asoc;
+
+	/* RFC 2960 (bis), Section 5.2.4
+	 * All the congestion control parameters (e.g., cwnd, ssthresh)
+	 * related to this peer MUST be reset to their initial values
+	 * (see Section 6.2.1)
+	 */
+	t->cwnd = min(4*asoc->pathmtu, max_t(__u32, 2*asoc->pathmtu, 4380));
+	t->ssthresh = asoc->peer.i.a_rwnd;
+	t->rto = asoc->rto_initial;
+	t->rtt = 0;
+	t->srtt = 0;
+	t->rttvar = 0;
+
+	/* Reset these additional varibles so that we have a clean
+	 * slate.
+	 */
+	t->partial_bytes_acked = 0;
+	t->flight_size = 0;
+	t->error_count = 0;
+	t->rto_pending = 0;
+	t->hb_sent = 0;
+	t->fast_recovery = 0;
+
+	/* Initialize the state information for SFR-CACC */
+	t->cacc.changeover_active = 0;
+	t->cacc.cycling_changeover = 0;
+	t->cacc.next_tsn_at_change = 0;
+	t->cacc.cacc_saw_newack = 0;
+}

kernel/net/sctp/tsnmap.c

@@ -0,0 +1,384 @@
+/* SCTP kernel implementation
+ * (C) Copyright IBM Corp. 2001, 2004
+ * Copyright (c) 1999-2000 Cisco, Inc.
+ * Copyright (c) 1999-2001 Motorola, Inc.
+ * Copyright (c) 2001 Intel Corp.
+ *
+ * This file is part of the SCTP kernel implementation
+ *
+ * These functions manipulate sctp tsn mapping array.
+ *
+ * This SCTP implementation is free software;
+ * you can redistribute it and/or modify it under the terms of
+ * the GNU General Public License as published by
+ * the Free Software Foundation; either version 2, or (at your option)
+ * any later version.
+ *
+ * This SCTP implementation is distributed in the hope that it
+ * will be useful, but WITHOUT ANY WARRANTY; without even the implied
+ *                 ************************
+ * warranty of MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.
+ * See the GNU General Public License for more details.
+ *
+ * You should have received a copy of the GNU General Public License
+ * along with GNU CC; see the file COPYING.  If not, write to
+ * the Free Software Foundation, 59 Temple Place - Suite 330,
+ * Boston, MA 02111-1307, USA.
+ *
+ * Please send any bug reports or fixes you make to the
+ * email address(es):
+ *    lksctp developers <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 <linux/bitmap.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(unsigned long *map, __u16 off,
+				     __u16 len, __u16 *start, __u16 *end);
+static int sctp_tsnmap_grow(struct sctp_tsnmap *map, u16 gap);
+
+/* Initialize a block of memory as a tsnmap.  */
+struct sctp_tsnmap *sctp_tsnmap_init(struct sctp_tsnmap *map, __u16 len,
+				     __u32 initial_tsn, gfp_t gfp)
+{
+	if (!map->tsn_map) {
+		map->tsn_map = kzalloc(len>>3, gfp);
+		if (map->tsn_map == NULL)
+			return NULL;
+
+		map->len = len;
+	} else {
+		bitmap_zero(map->tsn_map, map->len);
+	}
+
+	/* Keep track of TSNs represented by tsn_map.  */
+	map->base_tsn = initial_tsn;
+	map->cumulative_tsn_ack_point = initial_tsn - 1;
+	map->max_tsn_seen = map->cumulative_tsn_ack_point;
+	map->num_dup_tsns = 0;
+
+	return map;
+}
+
+void sctp_tsnmap_free(struct sctp_tsnmap *map)
+{
+	map->len = 0;
+	kfree(map->tsn_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)
+{
+	u32 gap;
+
+	/* Check to see if this is an old TSN */
+	if (TSN_lte(tsn, map->cumulative_tsn_ack_point))
+		return 1;
+
+	/* Verify that we can hold this TSN and that it will not
+	 * overlfow our map
+	 */
+	if (!TSN_lt(tsn, map->base_tsn + SCTP_TSN_MAP_SIZE))
+		return -1;
+
+	/* Calculate the index into the mapping arrays.  */
+	gap = tsn - map->base_tsn;
+
+	/* Check to see if TSN has already been recorded.  */
+	if (gap < map->len && test_bit(gap, map->tsn_map))
+		return 1;
+	else
+		return 0;
+}
+
+
+/* Mark this TSN as seen.  */
+int sctp_tsnmap_mark(struct sctp_tsnmap *map, __u32 tsn)
+{
+	u16 gap;
+
+	if (TSN_lt(tsn, map->base_tsn))
+		return 0;
+
+	gap = tsn - map->base_tsn;
+
+	if (gap >= map->len && !sctp_tsnmap_grow(map, gap))
+		return -ENOMEM;
+
+	if (!sctp_tsnmap_has_gap(map) && gap == 0) {
+		/* In this case the map has no gaps and the tsn we are
+		 * recording is the next expected tsn.  We don't touch
+		 * the map but simply bump the values.
+		 */
+		map->max_tsn_seen++;
+		map->cumulative_tsn_ack_point++;
+		map->base_tsn++;
+	} else {
+		/* Either we already have a gap, or about to record a gap, so
+		 * have work to do.
+		 *
+		 * Bump the max.
+		 */
+		if (TSN_lt(map->max_tsn_seen, tsn))
+			map->max_tsn_seen = tsn;
+
+		/* Mark the TSN as received.  */
+		set_bit(gap, map->tsn_map);
+
+		/* Go fixup any internal TSN mapping variables including
+		 * cumulative_tsn_ack_point.
+		 */
+		sctp_tsnmap_update(map);
+	}
+
+	return 0;
+}
+
+
+/* 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 ended = 0;
+	__u16 start_ = 0, end_ = 0, offset;
+
+	/* If there are no more gap acks possible, get out fast.  */
+	if (TSN_lte(map->max_tsn_seen, iter->start))
+		return 0;
+
+	offset = iter->start - map->base_tsn;
+	sctp_tsnmap_find_gap_ack(map->tsn_map, offset, map->len,
+				 &start_, &end_);
+
+	/* The Gap Ack Block happens to end at the end of the map. */
+	if (start_ && !end_)
+		end_ = map->len - 1;
+
+	/* If we found a Gap Ack Block, return the start and end and
+	 * bump the iterator forward.
+	 */
+	if (end_) {
+		/* Fix up the start and end based on the
+		 * Cumulative TSN Ack which is always 1 behind base.
+		 */
+		*start = start_ + 1;
+		*end = end_ + 1;
+
+		/* Move the iterator forward.  */
+		iter->start = map->cumulative_tsn_ack_point + *end + 1;
+		ended = 1;
+	}
+
+	return ended;
+}
+
+/* Mark this and any lower TSN as seen.  */
+void sctp_tsnmap_skip(struct sctp_tsnmap *map, __u32 tsn)
+{
+	u32 gap;
+
+	if (TSN_lt(tsn, map->base_tsn))
+		return;
+	if (!TSN_lt(tsn, map->base_tsn + SCTP_TSN_MAP_SIZE))
+		return;
+
+	/* Bump the max.  */
+	if (TSN_lt(map->max_tsn_seen, tsn))
+		map->max_tsn_seen = tsn;
+
+	gap = tsn - map->base_tsn + 1;
+
+	map->base_tsn += gap;
+	map->cumulative_tsn_ack_point += gap;
+	if (gap >= map->len) {
+		/* If our gap is larger then the map size, just
+		 * zero out the map.
+		 */
+		bitmap_zero(map->tsn_map, map->len);
+	} else {
+		/* If the gap is smaller than the map size,
+		 * shift the map by 'gap' bits and update further.
+		 */
+		bitmap_shift_right(map->tsn_map, map->tsn_map, gap, map->len);
+		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)
+{
+	u16 len;
+	unsigned long zero_bit;
+
+
+	len = map->max_tsn_seen - map->cumulative_tsn_ack_point;
+	zero_bit = find_first_zero_bit(map->tsn_map, len);
+	if (!zero_bit)
+		return;		/* The first 0-bit is bit 0.  nothing to do */
+
+	map->base_tsn += zero_bit;
+	map->cumulative_tsn_ack_point += zero_bit;
+
+	bitmap_shift_right(map->tsn_map, map->tsn_map, zero_bit, map->len);
+}
+
+/* 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;
+	u32 gap, i;
+
+	pending_data = max_tsn - cum_tsn;
+	gap = max_tsn - base_tsn;
+
+	if (gap == 0 || gap >= map->len)
+		goto out;
+
+	for (i = 0; i < gap+1; i++) {
+		if (test_bit(i, map->tsn_map))
+			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(unsigned long *map, __u16 off,
+				     __u16 len, __u16 *start, __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. */
+	i = find_next_bit(map, len, off);
+	if (i < len)
+		*start = i;
+
+	/* Look for the end.  */
+	if (*start) {
+		/* We have found the start, let's find the
+		 * end.  If we find the end, break out.
+		 */
+		i = find_next_zero_bit(map, len, i);
+		if (i < len)
+			*end = i - 1;
+	}
+}
+
+/* Renege that we have seen a TSN.  */
+void sctp_tsnmap_renege(struct sctp_tsnmap *map, __u32 tsn)
+{
+	u32 gap;
+
+	if (TSN_lt(tsn, map->base_tsn))
+		return;
+	/* Assert: TSN is in range.  */
+	if (!TSN_lt(tsn, map->base_tsn + map->len))
+		return;
+
+	gap = tsn - map->base_tsn;
+
+	/* Pretend we never saw the TSN.  */
+	clear_bit(gap, map->tsn_map);
+}
+
+/* How many gap ack blocks do we have recorded? */
+__u16 sctp_tsnmap_num_gabs(struct sctp_tsnmap *map,
+			   struct sctp_gap_ack_block *gabs)
+{
+	struct sctp_tsnmap_iter iter;
+	int ngaps = 0;
+
+	/* Refresh the gap ack information. */
+	if (sctp_tsnmap_has_gap(map)) {
+		__u16 start, end;
+		sctp_tsnmap_iter_init(map, &iter);
+		while (sctp_tsnmap_next_gap_ack(map, &iter,
+						&start,
+						&end)) {
+
+			gabs[ngaps].start = htons(start);
+			gabs[ngaps].end = htons(end);
+			ngaps++;
+			if (ngaps >= SCTP_MAX_GABS)
+				break;
+		}
+	}
+	return ngaps;
+}
+
+static int sctp_tsnmap_grow(struct sctp_tsnmap *map, u16 gap)
+{
+	unsigned long *new;
+	unsigned long inc;
+	u16  len;
+
+	if (gap >= SCTP_TSN_MAP_SIZE)
+		return 0;
+
+	inc = ALIGN((gap - map->len),BITS_PER_LONG) + SCTP_TSN_MAP_INCREMENT;
+	len = min_t(u16, map->len + inc, SCTP_TSN_MAP_SIZE);
+
+	new = kzalloc(len>>3, GFP_ATOMIC);
+	if (!new)
+		return 0;
+
+	bitmap_copy(new, map->tsn_map, map->max_tsn_seen - map->base_tsn);
+	kfree(map->tsn_map);
+	map->tsn_map = new;
+	map->len = len;
+
+	return 1;
+}