Resguardo inicial

linux-7.2.3/net/sctp/Kconfig

@@ -0,0 +1,75 @@
+# SPDX-License-Identifier: GPL-2.0-only
+#
+# SCTP configuration
+#
+
+menuconfig IP_SCTP
+	tristate "The SCTP Protocol"
+	depends on INET
+	select CRYPTO_LIB_SHA1
+	select CRYPTO_LIB_SHA256
+	select CRYPTO_LIB_UTILS
+	select NET_CRC32C
+	select NET_UDP_TUNNEL
+	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. Debug messages are handled by the
+	  kernel's dynamic debugging framework.
+
+	  If in doubt, say N.
+
+if IP_SCTP
+
+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 "Default SCTP cookie authentication method"
+	default SCTP_DEFAULT_COOKIE_HMAC_SHA256
+	help
+	  This option sets the default SCTP cookie authentication method, for
+	  when a method hasn't been explicitly selected via the
+	  net.sctp.cookie_hmac_alg sysctl.
+
+	  If unsure, choose the default (HMAC-SHA256).
+
+config SCTP_DEFAULT_COOKIE_HMAC_SHA256
+	bool "HMAC-SHA256"
+
+config SCTP_DEFAULT_COOKIE_HMAC_NONE
+	bool "None"
+
+endchoice
+
+config INET_SCTP_DIAG
+	depends on INET_DIAG
+	def_tristate INET_DIAG
+
+
+endif # IP_SCTP

linux-7.2.3/net/sctp/Makefile

@@ -0,0 +1,25 @@
+# SPDX-License-Identifier: GPL-2.0
+#
+# Makefile for SCTP support code.
+#
+
+obj-$(CONFIG_IP_SCTP) += sctp.o
+obj-$(CONFIG_INET_SCTP_DIAG) += sctp_diag.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 \
+	  tsnmap.o bind_addr.o socket.o primitive.o \
+	  output.o input.o debug.o stream.o auth.o \
+	  offload.o stream_sched.o stream_sched_prio.o \
+	  stream_sched_rr.o stream_sched_fc.o \
+	  stream_interleave.o
+
+sctp_diag-y := diag.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

linux-7.2.3/net/sctp/bind_addr.c

@@ -0,0 +1,584 @@
+// SPDX-License-Identifier: GPL-2.0-or-later
+/* 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.
+ *
+ * Please send any bug reports or fixes you make to the
+ * email address(es):
+ *    lksctp developers <linux-sctp@vger.kernel.org>
+ *
+ * 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>
+ */
+
+#include <linux/types.h>
+#include <linux/slab.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 net *net, struct sctp_bind_addr *dest,
+			      union sctp_addr *addr, enum sctp_scope 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 net *net, struct sctp_bind_addr *dest,
+			const struct sctp_bind_addr *src,
+			enum sctp_scope 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(net, 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(net, dest, &addr->a,
+						   SCTP_SCOPE_LINK, gfp,
+						   flags);
+			if (error < 0)
+				goto out;
+		}
+	}
+
+	/* If somehow no addresses were found that can be used with this
+	 * scope, it's an error.
+	 */
+	if (list_empty(&dest->address_list))
+		error = -ENETUNREACH;
+
+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, sizeof(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)
+{
+	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, *temp;
+
+	/* Empty the bind address list. */
+	list_for_each_entry_safe(addr, temp, &bp->address_list, list) {
+		list_del_rcu(&addr->list);
+		kfree_rcu(addr, rcu);
+		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);
+}
+
+/* Add an address to the bind address list in the SCTP_bind_addr structure. */
+int sctp_add_bind_addr(struct sctp_bind_addr *bp, union sctp_addr *new,
+		       int new_size, __u8 addr_state, gfp_t gfp)
+{
+	struct sctp_sockaddr_entry *addr;
+
+	/* Add the address to the bind address list.  */
+	addr = kzalloc_obj(*addr, gfp);
+	if (!addr)
+		return -ENOMEM;
+
+	memcpy(&addr->a, new, min_t(size_t, sizeof(*new), new_size));
+
+	/* 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);
+
+	/* 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) {
+		kfree_rcu(addr, rcu);
+		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;
+
+		if (addrs_len < sizeof(*param)) {
+			retval = -EINVAL;
+			goto out_err;
+		}
+		len = ntohs(param->length);
+		if (addrs_len < len) {
+			retval = -EINVAL;
+			goto out_err;
+		}
+
+		af = sctp_get_af_specific(param_type2af(param->type));
+		if (unlikely(!af) ||
+		    !af->from_addr_param(&addr, rawaddr, htons(port), 0)) {
+			retval = -EINVAL;
+			goto out_err;
+		}
+
+		if (sctp_bind_addr_state(bp, &addr) != -1)
+			goto next;
+		retval = sctp_add_bind_addr(bp, &addr, sizeof(addr),
+					    SCTP_ADDR_SRC, gfp);
+		if (retval)
+			/* Can't finish building the list, clean up. */
+			goto out_err;
+
+next:
+		addrs_len -= len;
+		raw_addr_list += len;
+	}
+
+	return retval;
+
+out_err:
+	if (retval)
+		sctp_bind_addr_clean(bp);
+
+	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;
+}
+
+int sctp_bind_addrs_check(struct sctp_sock *sp,
+			  struct sctp_sock *sp2, int cnt2)
+{
+	struct sctp_bind_addr *bp2 = &sp2->ep->base.bind_addr;
+	struct sctp_bind_addr *bp = &sp->ep->base.bind_addr;
+	struct sctp_sockaddr_entry *laddr, *laddr2;
+	bool exist = false;
+	int cnt = 0;
+
+	rcu_read_lock();
+	list_for_each_entry_rcu(laddr, &bp->address_list, list) {
+		list_for_each_entry_rcu(laddr2, &bp2->address_list, list) {
+			if (sp->pf->af->cmp_addr(&laddr->a, &laddr2->a) &&
+			    laddr->valid && laddr2->valid) {
+				exist = true;
+				goto next;
+			}
+		}
+		cnt = 0;
+		break;
+next:
+		cnt++;
+	}
+	rcu_read_unlock();
+
+	return (cnt == cnt2) ? 0 : (exist ? -EEXIST : 1);
+}
+
+/* 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;
+
+	af = sctp_get_af_specific(addr->sa.sa_family);
+	if (unlikely(!af))
+		return -1;
+
+	list_for_each_entry_rcu(laddr, &bp->address_list, list) {
+		if (!laddr->valid)
+			continue;
+		if (af->cmp_addr(&laddr->a, addr))
+			return laddr->state;
+	}
+
+	return -1;
+}
+
+/* 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 = 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 net *net, struct sctp_bind_addr *dest,
+			      union sctp_addr *addr, enum sctp_scope scope,
+			      gfp_t gfp, int flags)
+{
+	int error = 0;
+
+	if (sctp_is_any(NULL, addr)) {
+		error = sctp_copy_local_addr_list(net, dest, scope, gfp, flags);
+	} else if (sctp_in_scope(net, 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_ALLOWED) &&
+		      (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, sizeof(*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(struct net *net, const union sctp_addr *addr,
+		  enum sctp_scope scope)
+{
+	enum sctp_scope 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
+	 * 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 (net->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;
+}
+
+int sctp_is_ep_boundall(struct sock *sk)
+{
+	struct sctp_bind_addr *bp;
+	struct sctp_sockaddr_entry *addr;
+
+	bp = &sctp_sk(sk)->ep->base.bind_addr;
+	if (sctp_list_single_entry(&bp->address_list)) {
+		addr = list_entry(bp->address_list.next,
+				  struct sctp_sockaddr_entry, list);
+		if (sctp_is_any(sk, &addr->a))
+			return 1;
+	}
+	return 0;
+}
+
+/********************************************************************
+ * 3rd Level Abstractions
+ ********************************************************************/
+
+/* What is the scope of 'addr'?  */
+enum sctp_scope 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);
+}

linux-7.2.3/net/sctp/chunk.c

@@ -0,0 +1,354 @@
+// SPDX-License-Identifier: GPL-2.0-or-later
+/* 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.
+ *
+ * Please send any bug reports or fixes you make to the
+ * email address(es):
+ *    lksctp developers <linux-sctp@vger.kernel.org>
+ *
+ * Written or modified by:
+ *    Jon Grimm             <jgrimm@us.ibm.com>
+ *    Sridhar Samudrala     <sri@us.ibm.com>
+ */
+
+#define pr_fmt(fmt) KBUILD_MODNAME ": " fmt
+
+#include <linux/types.h>
+#include <linux/kernel.h>
+#include <linux/net.h>
+#include <linux/inet.h>
+#include <linux/skbuff.h>
+#include <linux/slab.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)
+{
+	refcount_set(&msg->refcnt, 1);
+	msg->send_failed = 0;
+	msg->send_error = 0;
+	msg->can_delay = 1;
+	msg->abandoned = 0;
+	msg->expires_at = 0;
+	INIT_LIST_HEAD(&msg->chunks);
+}
+
+/* Allocate and initialize datamsg. */
+static struct sctp_datamsg *sctp_datamsg_new(gfp_t gfp)
+{
+	struct sctp_datamsg *msg;
+	msg = kmalloc_obj(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 sctp_association *asoc = NULL;
+	struct list_head *pos, *temp;
+	struct sctp_chunk *chunk;
+	struct sctp_ulpevent *ev;
+	int error, sent;
+
+	/* Release all references. */
+	list_for_each_safe(pos, temp, &msg->chunks) {
+		list_del_init(pos);
+		chunk = list_entry(pos, struct sctp_chunk, frag_list);
+
+		if (!msg->send_failed) {
+			sctp_chunk_put(chunk);
+			continue;
+		}
+
+		asoc = chunk->asoc;
+		error = msg->send_error ?: asoc->outqueue.error;
+		sent = chunk->has_tsn ? SCTP_DATA_SENT : SCTP_DATA_UNSENT;
+
+		if (sctp_ulpevent_type_enabled(asoc->subscribe,
+					       SCTP_SEND_FAILED)) {
+			ev = sctp_ulpevent_make_send_failed(asoc, chunk, sent,
+							    error, GFP_ATOMIC);
+			if (ev)
+				asoc->stream.si->enqueue_event(&asoc->ulpq, ev);
+		}
+
+		if (sctp_ulpevent_type_enabled(asoc->subscribe,
+					       SCTP_SEND_FAILED_EVENT)) {
+			ev = sctp_ulpevent_make_send_failed_event(asoc, chunk,
+								  sent, error,
+								  GFP_ATOMIC);
+			if (ev)
+				asoc->stream.si->enqueue_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)
+{
+	refcount_inc(&msg->refcnt);
+}
+
+/* Release a reference. */
+void sctp_datamsg_put(struct sctp_datamsg *msg)
+{
+	if (refcount_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;
+}
+
+
+/* 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 iov_iter *from)
+{
+	size_t len, first_len, max_data, remaining;
+	size_t msg_len = iov_iter_count(from);
+	struct sctp_shared_key *shkey = NULL;
+	struct list_head *pos, *temp;
+	struct sctp_chunk *chunk;
+	struct sctp_datamsg *msg;
+	int err;
+
+	msg = sctp_datamsg_new(GFP_KERNEL);
+	if (!msg)
+		return ERR_PTR(-ENOMEM);
+
+	/* Note: Calculate this outside of the loop, so that all fragments
+	 * have the same expiration.
+	 */
+	if (asoc->peer.prsctp_capable && sinfo->sinfo_timetolive &&
+	    (SCTP_PR_TTL_ENABLED(sinfo->sinfo_flags) ||
+	     !SCTP_PR_POLICY(sinfo->sinfo_flags)))
+		msg->expires_at = jiffies +
+				  msecs_to_jiffies(sinfo->sinfo_timetolive);
+
+	/* This is the biggest possible DATA chunk that can fit into
+	 * the packet
+	 */
+	max_data = asoc->frag_point;
+	if (unlikely(!max_data)) {
+		max_data = sctp_min_frag_point(sctp_sk(asoc->base.sk),
+					       sctp_datachk_len(&asoc->stream));
+		pr_warn_ratelimited("%s: asoc:%p frag_point is zero, forcing max_data to default minimum (%zu)",
+				    __func__, asoc, max_data);
+	}
+
+	/* If the peer requested that we authenticate DATA chunks
+	 * we need to account for bundling of the AUTH chunks along with
+	 * DATA.
+	 */
+	if (sctp_auth_send_cid(SCTP_CID_DATA, asoc)) {
+		const struct sctp_hmac *hmac_desc =
+			sctp_auth_asoc_get_hmac(asoc);
+
+		if (hmac_desc)
+			max_data -= SCTP_PAD4(sizeof(struct sctp_auth_chunk) +
+					      hmac_desc->hmac_len);
+
+		if (sinfo->sinfo_tsn &&
+		    sinfo->sinfo_ssn != asoc->active_key_id) {
+			shkey = sctp_auth_get_shkey(asoc, sinfo->sinfo_ssn);
+			if (!shkey) {
+				err = -EINVAL;
+				goto errout;
+			}
+		} else {
+			shkey = asoc->shkey;
+		}
+	}
+
+	/* Set first_len and then account for possible bundles on first frag */
+	first_len = max_data;
+
+	/* 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_data)
+		first_len -= SCTP_PAD4(sizeof(struct sctp_sack_chunk));
+
+	/* Encourage Cookie-ECHO bundling. */
+	if (asoc->state < SCTP_STATE_COOKIE_ECHOED)
+		first_len -= SCTP_ARBITRARY_COOKIE_ECHO_LEN;
+
+	/* Account for a different sized first fragment */
+	if (msg_len >= first_len) {
+		msg->can_delay = 0;
+		if (msg_len > first_len)
+			SCTP_INC_STATS(asoc->base.net,
+				       SCTP_MIB_FRAGUSRMSGS);
+	} else {
+		/* Which may be the only one... */
+		first_len = msg_len;
+	}
+
+	/* Create chunks for all DATA chunks. */
+	for (remaining = msg_len; remaining; remaining -= len) {
+		u8 frag = SCTP_DATA_MIDDLE_FRAG;
+
+		if (remaining == msg_len) {
+			/* First frag, which may also be the last */
+			frag |= SCTP_DATA_FIRST_FRAG;
+			len = first_len;
+		} else {
+			/* Middle frags */
+			len = max_data;
+		}
+
+		if (len >= remaining) {
+			/* Last frag, which may also be the first */
+			len = remaining;
+			frag |= SCTP_DATA_LAST_FRAG;
+
+			/* The application requests to set the I-bit of the
+			 * last DATA chunk of a user message when providing
+			 * the user message to the SCTP implementation.
+			 */
+			if ((sinfo->sinfo_flags & SCTP_EOF) ||
+			    (sinfo->sinfo_flags & SCTP_SACK_IMMEDIATELY))
+				frag |= SCTP_DATA_SACK_IMM;
+		}
+
+		chunk = asoc->stream.si->make_datafrag(asoc, sinfo, len, frag,
+						       GFP_KERNEL);
+		if (!chunk) {
+			err = -ENOMEM;
+			goto errout;
+		}
+
+		err = sctp_user_addto_chunk(chunk, len, from);
+		if (err < 0)
+			goto errout_chunk_free;
+
+		chunk->shkey = shkey;
+
+		/* Put the chunk->skb back into the form expected by send.  */
+		__skb_pull(chunk->skb, (__u8 *)chunk->chunk_hdr -
+				       chunk->skb->data);
+
+		sctp_datamsg_assign(msg, chunk);
+		list_add_tail(&chunk->frag_list, &msg->chunks);
+	}
+
+	return msg;
+
+errout_chunk_free:
+	sctp_chunk_free(chunk);
+
+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 ERR_PTR(err);
+}
+
+/* Check whether this message has expired. */
+int sctp_chunk_abandoned(struct sctp_chunk *chunk)
+{
+	if (!chunk->asoc->peer.prsctp_capable)
+		return 0;
+
+	if (chunk->msg->abandoned)
+		return 1;
+
+	if (!chunk->has_tsn &&
+	    !(chunk->chunk_hdr->flags & SCTP_DATA_FIRST_FRAG))
+		return 0;
+
+	if (SCTP_PR_TTL_ENABLED(chunk->sinfo.sinfo_flags) &&
+	    time_after(jiffies, chunk->msg->expires_at)) {
+		struct sctp_stream_out *streamout =
+			SCTP_SO(&chunk->asoc->stream,
+				chunk->sinfo.sinfo_stream);
+
+		if (chunk->sent_count) {
+			chunk->asoc->abandoned_sent[SCTP_PR_INDEX(TTL)]++;
+			streamout->ext->abandoned_sent[SCTP_PR_INDEX(TTL)]++;
+		} else {
+			chunk->asoc->abandoned_unsent[SCTP_PR_INDEX(TTL)]++;
+			streamout->ext->abandoned_unsent[SCTP_PR_INDEX(TTL)]++;
+		}
+		chunk->msg->abandoned = 1;
+		return 1;
+	} else if (SCTP_PR_RTX_ENABLED(chunk->sinfo.sinfo_flags) &&
+		   chunk->sent_count > chunk->sinfo.sinfo_timetolive) {
+		struct sctp_stream_out *streamout =
+			SCTP_SO(&chunk->asoc->stream,
+				chunk->sinfo.sinfo_stream);
+
+		chunk->asoc->abandoned_sent[SCTP_PR_INDEX(RTX)]++;
+		streamout->ext->abandoned_sent[SCTP_PR_INDEX(RTX)]++;
+		chunk->msg->abandoned = 1;
+		return 1;
+	} else if (!SCTP_PR_POLICY(chunk->sinfo.sinfo_flags) &&
+		   chunk->msg->expires_at &&
+		   time_after(jiffies, chunk->msg->expires_at)) {
+		chunk->msg->abandoned = 1;
+		return 1;
+	}
+	/* PRIO policy is processed by sendmsg, not here */
+
+	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;
+}

linux-7.2.3/net/sctp/debug.c

@@ -0,0 +1,170 @@
+// SPDX-License-Identifier: GPL-2.0-or-later
+/* 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.
+ *
+ * Please send any bug reports or fixes you make to the
+ * email address(es):
+ *    lksctp developers <linux-sctp@vger.kernel.org>
+ *
+ * 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>
+ */
+
+#include <net/sctp/sctp.h>
+
+/* 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 union sctp_subtype 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";
+
+	case SCTP_CID_RECONF:
+		return "RECONF";
+
+	case SCTP_CID_I_DATA:
+		return "I_DATA";
+
+	case SCTP_CID_I_FWD_TSN:
+		return "I_FWD_TSN";
+
+	default:
+		break;
+	}
+
+	return "unknown chunk";
+}
+
+/* These are printable forms of the states.  */
+const char *const sctp_state_tbl[SCTP_STATE_NUM_STATES] = {
+	"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 union sctp_subtype 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 union sctp_subtype 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_RECONF",
+	"TIMEOUT_PROBE",
+	"TIMEOUT_SACK",
+	"TIMEOUT_AUTOCLOSE",
+};
+
+/* Lookup timer debug name. */
+const char *sctp_tname(const union sctp_subtype id)
+{
+	BUILD_BUG_ON(SCTP_EVENT_TIMEOUT_MAX + 1 != ARRAY_SIZE(sctp_timer_tbl));
+
+	if (id.timeout < ARRAY_SIZE(sctp_timer_tbl))
+		return sctp_timer_tbl[id.timeout];
+	return "unknown_timer";
+}

linux-7.2.3/net/sctp/diag.c

@@ -0,0 +1,541 @@
+// SPDX-License-Identifier: GPL-2.0-or-later
+/* SCTP kernel implementation
+ * (C) Copyright Red Hat Inc. 2017
+ *
+ * This file is part of the SCTP kernel implementation
+ *
+ * These functions implement sctp diag support.
+ *
+ * Please send any bug reports or fixes you make to the
+ * email addresched(es):
+ *    lksctp developers <linux-sctp@vger.kernel.org>
+ *
+ * Written or modified by:
+ *    Xin Long <lucien.xin@gmail.com>
+ */
+
+#include <linux/module.h>
+#include <linux/inet_diag.h>
+#include <linux/sock_diag.h>
+#include <net/sctp/sctp.h>
+
+static void sctp_diag_get_info(struct sock *sk, struct inet_diag_msg *r,
+			       void *info);
+
+/* define some functions to make asoc/ep fill look clean */
+static void inet_diag_msg_sctpasoc_fill(struct inet_diag_msg *r,
+					struct sock *sk,
+					struct sctp_association *asoc)
+{
+	union sctp_addr laddr, paddr;
+	struct dst_entry *dst;
+	struct timer_list *t3_rtx = &asoc->peer.primary_path->T3_rtx_timer;
+
+	laddr = list_entry(asoc->base.bind_addr.address_list.next,
+			   struct sctp_sockaddr_entry, list)->a;
+	paddr = asoc->peer.primary_path->ipaddr;
+	dst = asoc->peer.primary_path->dst;
+
+	r->idiag_family = sk->sk_family;
+	r->id.idiag_sport = htons(asoc->base.bind_addr.port);
+	r->id.idiag_dport = htons(asoc->peer.port);
+	r->id.idiag_if = dst ? dst->dev->ifindex : 0;
+	sock_diag_save_cookie(sk, r->id.idiag_cookie);
+
+#if IS_ENABLED(CONFIG_IPV6)
+	if (sk->sk_family == AF_INET6) {
+		*(struct in6_addr *)r->id.idiag_src = laddr.v6.sin6_addr;
+		*(struct in6_addr *)r->id.idiag_dst = paddr.v6.sin6_addr;
+	} else
+#endif
+	{
+		memset(&r->id.idiag_src, 0, sizeof(r->id.idiag_src));
+		memset(&r->id.idiag_dst, 0, sizeof(r->id.idiag_dst));
+
+		r->id.idiag_src[0] = laddr.v4.sin_addr.s_addr;
+		r->id.idiag_dst[0] = paddr.v4.sin_addr.s_addr;
+	}
+
+	r->idiag_state = asoc->state;
+	if (timer_pending(t3_rtx)) {
+		r->idiag_timer = SCTP_EVENT_TIMEOUT_T3_RTX;
+		r->idiag_retrans = asoc->rtx_data_chunks;
+		r->idiag_expires = jiffies_to_msecs(t3_rtx->expires - jiffies);
+	}
+}
+
+static int inet_diag_msg_sctpladdrs_fill(struct sk_buff *skb,
+					 struct list_head *address_list)
+{
+	struct sctp_sockaddr_entry *laddr;
+	int addrlen = sizeof(struct sockaddr_storage);
+	int addrcnt = 0;
+	struct nlattr *attr;
+	void *info = NULL;
+
+	rcu_read_lock();
+	list_for_each_entry_rcu(laddr, address_list, list)
+		addrcnt++;
+	rcu_read_unlock();
+
+	attr = nla_reserve(skb, INET_DIAG_LOCALS, addrlen * addrcnt);
+	if (!attr)
+		return -EMSGSIZE;
+
+	info = nla_data(attr);
+	rcu_read_lock();
+	list_for_each_entry_rcu(laddr, address_list, list) {
+		memcpy(info, &laddr->a, sizeof(laddr->a));
+		memset(info + sizeof(laddr->a), 0, addrlen - sizeof(laddr->a));
+		info += addrlen;
+
+		if (!--addrcnt)
+			break;
+	}
+	WARN_ON_ONCE(addrcnt);
+	rcu_read_unlock();
+
+	return 0;
+}
+
+static int inet_diag_msg_sctpaddrs_fill(struct sk_buff *skb,
+					struct sctp_association *asoc)
+{
+	int addrlen = sizeof(struct sockaddr_storage);
+	struct sctp_transport *from;
+	struct nlattr *attr;
+	void *info = NULL;
+
+	attr = nla_reserve(skb, INET_DIAG_PEERS,
+			   addrlen * asoc->peer.transport_count);
+	if (!attr)
+		return -EMSGSIZE;
+
+	info = nla_data(attr);
+	list_for_each_entry(from, &asoc->peer.transport_addr_list,
+			    transports) {
+		memcpy(info, &from->ipaddr, sizeof(from->ipaddr));
+		memset(info + sizeof(from->ipaddr), 0,
+		       addrlen - sizeof(from->ipaddr));
+		info += addrlen;
+	}
+
+	return 0;
+}
+
+/* sctp asoc/ep fill*/
+static int inet_sctp_diag_fill(struct sock *sk, struct sctp_association *asoc,
+			       struct sk_buff *skb,
+			       const struct inet_diag_req_v2 *req,
+			       struct user_namespace *user_ns,
+			       int portid, u32 seq, u16 nlmsg_flags,
+			       const struct nlmsghdr *unlh,
+			       bool net_admin)
+{
+	struct sctp_endpoint *ep = sctp_sk(sk)->ep;
+	struct list_head *addr_list;
+	struct inet_diag_msg *r;
+	struct nlmsghdr  *nlh;
+	int ext = req->idiag_ext;
+	struct sctp_infox infox;
+	void *info = NULL;
+
+	nlh = nlmsg_put(skb, portid, seq, unlh->nlmsg_type, sizeof(*r),
+			nlmsg_flags);
+	if (!nlh)
+		return -EMSGSIZE;
+
+	r = nlmsg_data(nlh);
+	BUG_ON(!sk_fullsock(sk));
+
+	r->idiag_timer = 0;
+	r->idiag_retrans = 0;
+	r->idiag_expires = 0;
+	if (asoc) {
+		inet_diag_msg_sctpasoc_fill(r, sk, asoc);
+	} else {
+		inet_diag_msg_common_fill(r, sk);
+		r->idiag_state = sk->sk_state;
+	}
+
+	if (inet_diag_msg_attrs_fill(sk, skb, r, ext, user_ns, net_admin))
+		goto errout;
+
+	if (ext & (1 << (INET_DIAG_SKMEMINFO - 1))) {
+		u32 mem[SK_MEMINFO_VARS];
+		int amt;
+
+		if (asoc && asoc->ep->sndbuf_policy)
+			amt = asoc->sndbuf_used;
+		else
+			amt = sk_wmem_alloc_get(sk);
+		mem[SK_MEMINFO_WMEM_ALLOC] = amt;
+		if (asoc && asoc->ep->rcvbuf_policy)
+			amt = atomic_read(&asoc->rmem_alloc);
+		else
+			amt = sk_rmem_alloc_get(sk);
+		mem[SK_MEMINFO_RMEM_ALLOC] = amt;
+		mem[SK_MEMINFO_RCVBUF] = sk->sk_rcvbuf;
+		mem[SK_MEMINFO_SNDBUF] = sk->sk_sndbuf;
+		mem[SK_MEMINFO_FWD_ALLOC] = sk->sk_forward_alloc;
+		mem[SK_MEMINFO_WMEM_QUEUED] = sk->sk_wmem_queued;
+		mem[SK_MEMINFO_OPTMEM] = atomic_read(&sk->sk_omem_alloc);
+		mem[SK_MEMINFO_BACKLOG] = READ_ONCE(sk->sk_backlog.len);
+		mem[SK_MEMINFO_DROPS] = sk_drops_read(sk);
+
+		if (nla_put(skb, INET_DIAG_SKMEMINFO, sizeof(mem), &mem) < 0)
+			goto errout;
+	}
+
+	if (ext & (1 << (INET_DIAG_INFO - 1))) {
+		struct nlattr *attr;
+
+		attr = nla_reserve_64bit(skb, INET_DIAG_INFO,
+					 sizeof(struct sctp_info),
+					 INET_DIAG_PAD);
+		if (!attr)
+			goto errout;
+
+		info = nla_data(attr);
+	}
+	infox.sctpinfo = (struct sctp_info *)info;
+	infox.asoc = asoc;
+	sctp_diag_get_info(sk, r, &infox);
+
+	addr_list = asoc ? &asoc->base.bind_addr.address_list
+			 : &ep->base.bind_addr.address_list;
+	if (inet_diag_msg_sctpladdrs_fill(skb, addr_list))
+		goto errout;
+
+	if (asoc && (ext & (1 << (INET_DIAG_CONG - 1))))
+		if (nla_put_string(skb, INET_DIAG_CONG, "reno") < 0)
+			goto errout;
+
+	if (asoc && inet_diag_msg_sctpaddrs_fill(skb, asoc))
+		goto errout;
+
+	nlmsg_end(skb, nlh);
+	return 0;
+
+errout:
+	nlmsg_cancel(skb, nlh);
+	return -EMSGSIZE;
+}
+
+/* callback and param */
+struct sctp_comm_param {
+	struct sk_buff *skb;
+	struct netlink_callback *cb;
+	const struct inet_diag_req_v2 *r;
+	const struct nlmsghdr *nlh;
+	bool net_admin;
+};
+
+static size_t inet_assoc_attr_size(struct sock *sk,
+				   struct sctp_association *asoc)
+{
+	int addrlen = sizeof(struct sockaddr_storage);
+	int addrcnt = 0;
+	struct sctp_sockaddr_entry *laddr;
+
+	list_for_each_entry_rcu(laddr, &asoc->base.bind_addr.address_list,
+				list, lockdep_sock_is_held(sk))
+		addrcnt++;
+
+	return	  nla_total_size(sizeof(struct sctp_info))
+		+ nla_total_size(addrlen * asoc->peer.transport_count)
+		+ nla_total_size(addrlen * addrcnt)
+		+ nla_total_size(sizeof(struct inet_diag_msg))
+		+ inet_diag_msg_attrs_size()
+		+ nla_total_size(sizeof(struct inet_diag_meminfo))
+		+ 64;
+}
+
+static int sctp_sock_dump_one(struct sctp_endpoint *ep, struct sctp_transport *tsp, void *p)
+{
+	struct sctp_association *assoc = tsp->asoc;
+	struct sctp_comm_param *commp = p;
+	struct sock *sk = ep->base.sk;
+	const struct inet_diag_req_v2 *req = commp->r;
+	struct sk_buff *skb = commp->skb;
+	struct sk_buff *rep;
+	int err;
+
+	err = sock_diag_check_cookie(sk, req->id.idiag_cookie);
+	if (err)
+		return err;
+
+	lock_sock(sk);
+
+	if (ep != assoc->ep || assoc->base.dead) {
+		err = -ESTALE;
+		goto out_unlock;
+	}
+
+	rep = nlmsg_new(inet_assoc_attr_size(sk, assoc), GFP_KERNEL);
+	if (!rep) {
+		err = -ENOMEM;
+		goto out_unlock;
+	}
+
+	err = inet_sctp_diag_fill(sk, assoc, rep, req, sk_user_ns(NETLINK_CB(skb).sk),
+				  NETLINK_CB(skb).portid, commp->nlh->nlmsg_seq, 0,
+				  commp->nlh, commp->net_admin);
+	if (err < 0) {
+		WARN_ON(err == -EMSGSIZE);
+		goto out;
+	}
+	release_sock(sk);
+
+	return nlmsg_unicast(sock_net(skb->sk)->diag_nlsk, rep, NETLINK_CB(skb).portid);
+
+out:
+	kfree_skb(rep);
+out_unlock:
+	release_sock(sk);
+	return err;
+}
+
+static int sctp_sock_dump(struct sctp_endpoint *ep, struct sctp_transport *tsp, void *p)
+{
+	struct sctp_comm_param *commp = p;
+	struct sock *sk = ep->base.sk;
+	struct sk_buff *skb = commp->skb;
+	struct netlink_callback *cb = commp->cb;
+	const struct inet_diag_req_v2 *r = commp->r;
+	struct sctp_association *assoc;
+	int err = 0;
+
+	lock_sock(sk);
+	if (ep != tsp->asoc->ep)
+		goto release;
+	list_for_each_entry(assoc, &ep->asocs, asocs) {
+		if (cb->args[4] < cb->args[1])
+			goto next;
+
+		if (r->id.idiag_sport != htons(assoc->base.bind_addr.port) &&
+		    r->id.idiag_sport)
+			goto next;
+		if (r->id.idiag_dport != htons(assoc->peer.port) &&
+		    r->id.idiag_dport)
+			goto next;
+
+		if (!cb->args[3] &&
+		    inet_sctp_diag_fill(sk, NULL, skb, r,
+					sk_user_ns(NETLINK_CB(cb->skb).sk),
+					NETLINK_CB(cb->skb).portid,
+					cb->nlh->nlmsg_seq,
+					NLM_F_MULTI, cb->nlh,
+					commp->net_admin) < 0) {
+			err = 1;
+			goto release;
+		}
+		cb->args[3] = 1;
+
+		if (inet_sctp_diag_fill(sk, assoc, skb, r,
+					sk_user_ns(NETLINK_CB(cb->skb).sk),
+					NETLINK_CB(cb->skb).portid,
+					cb->nlh->nlmsg_seq, 0, cb->nlh,
+					commp->net_admin) < 0) {
+			err = 1;
+			goto release;
+		}
+next:
+		cb->args[4]++;
+	}
+	cb->args[1] = 0;
+	cb->args[3] = 0;
+	cb->args[4] = 0;
+release:
+	release_sock(sk);
+	return err;
+}
+
+static int sctp_sock_filter(struct sctp_endpoint *ep, struct sctp_transport *tsp, void *p)
+{
+	struct sctp_comm_param *commp = p;
+	struct sock *sk = ep->base.sk;
+	const struct inet_diag_req_v2 *r = commp->r;
+
+	/* find the ep only once through the transports by this condition */
+	if (!list_is_first(&tsp->asoc->asocs, &ep->asocs))
+		return 0;
+
+	if (r->sdiag_family != AF_UNSPEC && sk->sk_family != r->sdiag_family)
+		return 0;
+
+	return 1;
+}
+
+static int sctp_ep_dump(struct sctp_endpoint *ep, void *p)
+{
+	struct sctp_comm_param *commp = p;
+	struct sock *sk = ep->base.sk;
+	struct sk_buff *skb = commp->skb;
+	struct netlink_callback *cb = commp->cb;
+	const struct inet_diag_req_v2 *r = commp->r;
+	struct inet_sock *inet = inet_sk(sk);
+	int err = 0;
+
+	lock_sock(sk);
+	if (ep->base.dead)
+		goto out;
+
+	/* Skip eps with assocs if non-LISTEN states were requested, since
+	 * they'll be dumped by sctp_sock_dump() during assoc traversal.
+	 */
+	if ((r->idiag_states & ~(TCPF_LISTEN | TCPF_CLOSE)) &&
+	    !list_empty(&ep->asocs))
+		goto out;
+
+	if (r->sdiag_family != AF_UNSPEC &&
+	    sk->sk_family != r->sdiag_family)
+		goto out;
+
+	if (r->id.idiag_sport != inet->inet_sport &&
+	    r->id.idiag_sport)
+		goto out;
+
+	if (r->id.idiag_dport != inet->inet_dport &&
+	    r->id.idiag_dport)
+		goto out;
+
+	err = inet_sctp_diag_fill(sk, NULL, skb, r,
+				  sk_user_ns(NETLINK_CB(cb->skb).sk),
+				  NETLINK_CB(cb->skb).portid,
+				  cb->nlh->nlmsg_seq, NLM_F_MULTI,
+				  cb->nlh, commp->net_admin);
+out:
+	release_sock(sk);
+	return err;
+}
+
+/* define the functions for sctp_diag_handler*/
+static void sctp_diag_get_info(struct sock *sk, struct inet_diag_msg *r,
+			       void *info)
+{
+	struct sctp_infox *infox = (struct sctp_infox *)info;
+
+	if (infox->asoc) {
+		r->idiag_rqueue = atomic_read(&infox->asoc->rmem_alloc);
+		r->idiag_wqueue = infox->asoc->sndbuf_used;
+	} else {
+		r->idiag_rqueue = READ_ONCE(sk->sk_ack_backlog);
+		r->idiag_wqueue = READ_ONCE(sk->sk_max_ack_backlog);
+	}
+	if (infox->sctpinfo)
+		sctp_get_sctp_info(sk, infox->asoc, infox->sctpinfo);
+}
+
+static int sctp_diag_dump_one(struct netlink_callback *cb,
+			      const struct inet_diag_req_v2 *req)
+{
+	struct sk_buff *skb = cb->skb;
+	struct net *net = sock_net(skb->sk);
+	const struct nlmsghdr *nlh = cb->nlh;
+	union sctp_addr laddr, paddr;
+	int dif = req->id.idiag_if;
+	struct sctp_comm_param commp = {
+		.skb = skb,
+		.r = req,
+		.nlh = nlh,
+		.net_admin = netlink_net_capable(skb, CAP_NET_ADMIN),
+	};
+
+	if (req->sdiag_family == AF_INET) {
+		laddr.v4.sin_port = req->id.idiag_sport;
+		laddr.v4.sin_addr.s_addr = req->id.idiag_src[0];
+		laddr.v4.sin_family = AF_INET;
+
+		paddr.v4.sin_port = req->id.idiag_dport;
+		paddr.v4.sin_addr.s_addr = req->id.idiag_dst[0];
+		paddr.v4.sin_family = AF_INET;
+	} else {
+		laddr.v6.sin6_port = req->id.idiag_sport;
+		memcpy(&laddr.v6.sin6_addr, req->id.idiag_src,
+		       sizeof(laddr.v6.sin6_addr));
+		laddr.v6.sin6_family = AF_INET6;
+
+		paddr.v6.sin6_port = req->id.idiag_dport;
+		memcpy(&paddr.v6.sin6_addr, req->id.idiag_dst,
+		       sizeof(paddr.v6.sin6_addr));
+		paddr.v6.sin6_family = AF_INET6;
+	}
+
+	return sctp_transport_lookup_process(sctp_sock_dump_one,
+					     net, &laddr, &paddr, &commp, dif);
+}
+
+static void sctp_diag_dump(struct sk_buff *skb, struct netlink_callback *cb,
+			   const struct inet_diag_req_v2 *r)
+{
+	u32 idiag_states = r->idiag_states;
+	struct net *net = sock_net(skb->sk);
+	struct sctp_comm_param commp = {
+		.skb = skb,
+		.cb = cb,
+		.r = r,
+		.net_admin = netlink_net_capable(cb->skb, CAP_NET_ADMIN),
+	};
+	int pos;
+
+	/* eps hashtable dumps
+	 * args:
+	 * 0 : if it will traversal listen sock
+	 * 1 : to record the sock pos of this time's traversal
+	 */
+	if (cb->args[0] == 0) {
+		if (idiag_states & TCPF_LISTEN) {
+			pos = cb->args[1];
+			if (sctp_for_each_endpoint(sctp_ep_dump, net, &pos,
+						   &commp)) {
+				cb->args[1] = pos;
+				return;
+			}
+		}
+		cb->args[0] = 1;
+		cb->args[1] = 0;
+	}
+
+	if (!(idiag_states & ~(TCPF_LISTEN | TCPF_CLOSE)))
+		return;
+
+	/* asocs by transport hashtable dump
+	 * args:
+	 * 1 : to record the assoc pos of this time's traversal
+	 * 2 : to record the transport pos of this time's traversal
+	 * 3 : to mark if we have dumped the ep info of the current asoc
+	 * 4 : to track position within ep->asocs list in sctp_sock_dump()
+	 */
+	pos = cb->args[2];
+	sctp_transport_traverse_process(sctp_sock_filter, sctp_sock_dump,
+					net, &pos, &commp);
+	cb->args[2] = pos;
+	cb->args[1] = cb->args[4];
+	cb->args[4] = 0;
+}
+
+static const struct inet_diag_handler sctp_diag_handler = {
+	.owner		 = THIS_MODULE,
+	.dump		 = sctp_diag_dump,
+	.dump_one	 = sctp_diag_dump_one,
+	.idiag_get_info  = sctp_diag_get_info,
+	.idiag_type	 = IPPROTO_SCTP,
+	.idiag_info_size = sizeof(struct sctp_info),
+};
+
+static int __init sctp_diag_init(void)
+{
+	return inet_diag_register(&sctp_diag_handler);
+}
+
+static void __exit sctp_diag_exit(void)
+{
+	inet_diag_unregister(&sctp_diag_handler);
+}
+
+module_init(sctp_diag_init);
+module_exit(sctp_diag_exit);
+MODULE_LICENSE("GPL");
+MODULE_DESCRIPTION("SCTP socket monitoring via SOCK_DIAG");
+MODULE_ALIAS_NET_PF_PROTO_TYPE(PF_NETLINK, NETLINK_SOCK_DIAG, 2-132);

linux-7.2.3/net/sctp/endpointola.c

@@ -0,0 +1,423 @@
+// SPDX-License-Identifier: GPL-2.0-or-later
+/* 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.
+ *
+ * Please send any bug reports or fixes you make to the
+ * email address(es):
+ *    lksctp developers <linux-sctp@vger.kernel.org>
+ *
+ * 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>
+ */
+
+#include <linux/types.h>
+#include <linux/slab.h>
+#include <linux/in.h>
+#include <linux/random.h>	/* get_random_bytes() */
+#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);
+
+static void gen_cookie_auth_key(struct hmac_sha256_key *key)
+{
+	u8 raw_key[SCTP_COOKIE_KEY_SIZE];
+
+	get_random_bytes(raw_key, sizeof(raw_key));
+	hmac_sha256_preparekey(key, raw_key, sizeof(raw_key));
+	memzero_explicit(raw_key, sizeof(raw_key));
+}
+
+/*
+ * 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 net *net = sock_net(sk);
+	struct sctp_shared_key *null_key;
+
+	ep->asconf_enable = net->sctp.addip_enable;
+	ep->auth_enable = net->sctp.auth_enable;
+	if (ep->auth_enable) {
+		if (sctp_auth_init(ep, gfp))
+			goto nomem;
+		if (ep->asconf_enable) {
+			sctp_auth_ep_add_chunkid(ep, SCTP_CID_ASCONF);
+			sctp_auth_ep_add_chunkid(ep, SCTP_CID_ASCONF_ACK);
+		}
+	}
+
+	/* Initialize the base structure. */
+	/* What type of endpoint are we?  */
+	ep->base.type = SCTP_EP_TYPE_SOCKET;
+
+	/* Initialize the basic object fields. */
+	refcount_set(&ep->base.refcnt, 1);
+	ep->base.dead = false;
+
+	/* 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);
+
+	/* Create the lists of associations.  */
+	INIT_LIST_HEAD(&ep->asocs);
+
+	/* Use SCTP specific send buffer space queues.  */
+	ep->sndbuf_policy = net->sctp.sndbuf_policy;
+
+	sk->sk_data_ready = sctp_data_ready;
+	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 = net->sctp.rcvbuf_policy;
+
+	/* Generate the cookie authentication key. */
+	gen_cookie_auth_key(&ep->cookie_auth_key);
+
+	/* SCTP-AUTH extensions*/
+	INIT_LIST_HEAD(&ep->endpoint_shared_keys);
+	null_key = sctp_auth_shkey_create(0, gfp);
+	if (!null_key)
+		goto nomem_shkey;
+
+	list_add(&null_key->key_list, &ep->endpoint_shared_keys);
+
+	/* Add the null key to the endpoint shared keys list and
+	 * set the hmcas and chunks pointers.
+	 */
+	ep->prsctp_enable = net->sctp.prsctp_enable;
+	ep->reconf_enable = net->sctp.reconf_enable;
+	ep->ecn_enable = net->sctp.ecn_enable;
+
+	/* Remember who we are attached to.  */
+	ep->base.sk = sk;
+	ep->base.net = sock_net(sk);
+	sock_hold(ep->base.sk);
+
+	return ep;
+
+nomem_shkey:
+	sctp_auth_free(ep);
+nomem:
+	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 = kzalloc_obj(*ep, gfp);
+	if (!ep)
+		goto fail;
+
+	if (!sctp_endpoint_init(ep, sk, gfp))
+		goto fail_init;
+
+	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_acceptq_added(sk);
+}
+
+/* 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 = true;
+
+	inet_sk_set_state(ep->base.sk, 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_rcu(struct rcu_head *head)
+{
+	struct sctp_endpoint *ep = container_of(head, struct sctp_endpoint, rcu);
+	struct sock *sk = ep->base.sk;
+
+	sctp_sk(sk)->ep = NULL;
+	sock_put(sk);
+
+	kfree(ep);
+	SCTP_DBG_OBJCNT_DEC(ep);
+}
+
+static void sctp_endpoint_destroy(struct sctp_endpoint *ep)
+{
+	struct sock *sk;
+
+	if (unlikely(!ep->base.dead)) {
+		WARN(1, "Attempt to destroy undead endpoint %p!\n", ep);
+		return;
+	}
+
+	/* SCTP-AUTH: Free up AUTH related data such as shared keys
+	 * chunks and hmacs arrays that were allocated
+	 */
+	sctp_auth_destroy_keys(&ep->endpoint_shared_keys);
+	sctp_auth_free(ep);
+
+	/* Cleanup. */
+	sctp_inq_free(&ep->base.inqueue);
+	sctp_bind_addr_free(&ep->base.bind_addr);
+
+	memzero_explicit(&ep->cookie_auth_key, sizeof(ep->cookie_auth_key));
+
+	sk = ep->base.sk;
+	/* Remove and free the port */
+	if (sctp_sk(sk)->bind_hash)
+		sctp_put_port(sk);
+
+	call_rcu(&ep->rcu, sctp_endpoint_destroy_rcu);
+}
+
+/* Hold a reference to an endpoint. */
+int sctp_endpoint_hold(struct sctp_endpoint *ep)
+{
+	return refcount_inc_not_zero(&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 (refcount_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,
+					       struct net *net,
+					       const union sctp_addr *laddr,
+					       int dif, int sdif)
+{
+	int bound_dev_if = READ_ONCE(ep->base.sk->sk_bound_dev_if);
+	struct sctp_endpoint *retval = NULL;
+
+	if (net_eq(ep->base.net, net) &&
+	    sctp_sk_bound_dev_eq(net, bound_dev_if, dif, sdif) &&
+	    (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 lookup the transport from hashtable at first, then get association
+ * through t->assoc.
+ */
+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;
+
+	*transport = NULL;
+
+	/* If the local port is not set, there can't be any associations
+	 * on this endpoint.
+	 */
+	if (!ep->base.bind_addr.port)
+		return NULL;
+
+	rcu_read_lock();
+	t = sctp_epaddr_lookup_transport(ep, paddr);
+	if (!t)
+		goto out;
+
+	*transport = t;
+	asoc = t->asoc;
+out:
+	rcu_read_unlock();
+	return asoc;
+}
+
+/* Look for any peeled off association from the endpoint that matches the
+ * given peer address.
+ */
+bool sctp_endpoint_is_peeled_off(struct sctp_endpoint *ep,
+				 const union sctp_addr *paddr)
+{
+	int bound_dev_if = READ_ONCE(ep->base.sk->sk_bound_dev_if);
+	struct sctp_sockaddr_entry *addr;
+	struct net *net = ep->base.net;
+	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(net, &addr->a, paddr,
+					 bound_dev_if, bound_dev_if))
+			return true;
+	}
+
+	return false;
+}
+
+/* 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 net *net;
+	struct sctp_transport *transport;
+	struct sctp_chunk *chunk;
+	struct sctp_inq *inqueue;
+	union sctp_subtype subtype;
+	enum sctp_state state;
+	int error = 0;
+	int first_time = 1;	/* is this the first time through the loop */
+
+	if (ep->base.dead)
+		return;
+
+	asoc = NULL;
+	inqueue = &ep->base.inqueue;
+	sk = ep->base.sk;
+	net = sock_net(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(ep->base.net, SCTP_MIB_INCTRLCHUNKS);
+			if (asoc)
+				asoc->stats.ictrlchunks++;
+		}
+
+		if (chunk->transport)
+			chunk->transport->last_time_heard = ktime_get();
+
+		error = sctp_do_sm(net, 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;
+	}
+}

linux-7.2.3/net/sctp/inqueue.c

@@ -0,0 +1,245 @@
+// SPDX-License-Identifier: GPL-2.0-or-later
+/* 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.
+ *
+ * Please send any bug reports or fixes you make to the
+ * email address(es):
+ *    lksctp developers <linux-sctp@vger.kernel.org>
+ *
+ * Written or modified by:
+ *    La Monte H.P. Yarroll <piggy@acm.org>
+ *    Karl Knutson <karl@athena.chicago.il.us>
+ */
+
+#define pr_fmt(fmt) KBUILD_MODNAME ": " fmt
+
+#include <net/sctp/sctp.h>
+#include <net/sctp/sm.h>
+#include <linux/interrupt.h>
+#include <linux/slab.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);
+}
+
+/* Properly release the chunk which is being worked on. */
+static inline void sctp_inq_chunk_free(struct sctp_chunk *chunk)
+{
+	if (chunk->head_skb)
+		chunk->skb = chunk->head_skb;
+	sctp_chunk_free(chunk);
+}
+
+/* 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_inq_chunk_free(queue->in_progress);
+		queue->in_progress = NULL;
+	}
+}
+
+/* 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);
+	if (chunk->asoc)
+		chunk->asoc->stats.ipackets++;
+	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;
+	struct sctp_chunkhdr *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 = (struct sctp_chunkhdr *)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;
+	struct sctp_chunkhdr *ch = NULL;
+
+	/* The assumption is that we are safe to process the chunks
+	 * at this time.
+	 */
+
+	chunk = queue->in_progress;
+	if (chunk) {
+		/* 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) {
+			if (chunk->head_skb == chunk->skb) {
+				chunk->skb = skb_shinfo(chunk->skb)->frag_list;
+				goto new_skb;
+			}
+			if (chunk->skb->next) {
+				chunk->skb = chunk->skb->next;
+				goto new_skb;
+			}
+
+			sctp_inq_chunk_free(chunk);
+			chunk = queue->in_progress = NULL;
+		} else {
+			/* Nothing to do. Next chunk in the packet, please. */
+			ch = (struct sctp_chunkhdr *)chunk->chunk_end;
+			/* Force chunk->skb->data to chunk->chunk_end.  */
+			skb_pull(chunk->skb, chunk->chunk_end - chunk->skb->data);
+			/* We are guaranteed to pull a SCTP header. */
+		}
+	}
+
+	/* Do we need to take the next packet out of the queue to process? */
+	if (!chunk) {
+		struct list_head *entry;
+
+next_chunk:
+		/* Is the queue empty?  */
+		entry = sctp_list_dequeue(&queue->in_chunk_list);
+		if (!entry)
+			return NULL;
+
+		chunk = list_entry(entry, struct sctp_chunk, list);
+
+		if (skb_is_gso(chunk->skb) && skb_is_gso_sctp(chunk->skb)) {
+			/* GSO-marked skbs but without frags, handle
+			 * them normally
+			 */
+			if (skb_shinfo(chunk->skb)->frag_list)
+				chunk->head_skb = chunk->skb;
+
+			/* skbs with "cover letter" */
+			if (chunk->head_skb && chunk->skb->data_len == chunk->skb->len) {
+				if (WARN_ON(!skb_shinfo(chunk->skb)->frag_list)) {
+					__SCTP_INC_STATS(dev_net(chunk->skb->dev),
+							 SCTP_MIB_IN_PKT_DISCARDS);
+					sctp_chunk_free(chunk);
+					goto next_chunk;
+				}
+				chunk->skb = skb_shinfo(chunk->skb)->frag_list;
+			}
+		}
+
+		if (chunk->asoc)
+			sock_rps_save_rxhash(chunk->asoc->base.sk, chunk->skb);
+
+		queue->in_progress = chunk;
+
+new_skb:
+		/* This is the first chunk in the packet.  */
+		ch = (struct sctp_chunkhdr *)chunk->skb->data;
+		chunk->singleton = 1;
+		chunk->data_accepted = 0;
+		chunk->pdiscard = 0;
+		chunk->auth = 0;
+		chunk->has_asconf = 0;
+		chunk->end_of_packet = 0;
+		if (chunk->head_skb) {
+			struct sctp_input_cb
+				*cb = SCTP_INPUT_CB(chunk->skb),
+				*head_cb = SCTP_INPUT_CB(chunk->head_skb);
+
+			cb->chunk = head_cb->chunk;
+			cb->af = head_cb->af;
+			cb->encap_port = head_cb->encap_port;
+		}
+	}
+
+	chunk->chunk_hdr = ch;
+	chunk->chunk_end = ((__u8 *)ch) + SCTP_PAD4(ntohs(ch->length));
+	skb_pull(chunk->skb, sizeof(*ch));
+	chunk->subh.v = NULL; /* Subheader is no longer valid.  */
+
+	if (chunk->chunk_end + sizeof(*ch) <= skb_tail_pointer(chunk->skb)) {
+		/* This is not a singleton */
+		chunk->singleton = 0;
+	} else if (chunk->chunk_end > skb_tail_pointer(chunk->skb)) {
+		/* Discard inside state machine. */
+		chunk->pdiscard = 1;
+		chunk->chunk_end = skb_tail_pointer(chunk->skb);
+	} 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;
+	}
+
+	pr_debug("+++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);
+}

linux-7.2.3/net/sctp/objcnt.c

@@ -0,0 +1,105 @@
+// SPDX-License-Identifier: GPL-2.0-or-later
+/* 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.
+ *
+ * Please send any bug reports or fixes you make to the
+ * email address(es):
+ *    lksctp developers <linux-sctp@vger.kernel.org>
+ *
+ * Written or modified by:
+ *    Jon Grimm             <jgrimm@us.ibm.com>
+ */
+
+#define pr_fmt(fmt) KBUILD_MODNAME ": " fmt
+
+#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(datamsg);
+SCTP_DBG_OBJCNT(keys);
+
+/* An array to make it easy to pretty print the debug information
+ * to the proc fs.
+ */
+static struct sctp_dbg_objcnt_entry 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(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;
+
+	i = (int)*(loff_t *)v;
+	seq_setwidth(seq, 127);
+	seq_printf(seq, "%s: %d", sctp_dbg_objcnt[i].label,
+				atomic_read(sctp_dbg_objcnt[i].counter));
+	seq_pad(seq, '\n');
+	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,
+};
+
+/* Initialize the objcount in the proc filesystem.  */
+void sctp_dbg_objcnt_init(struct net *net)
+{
+	struct proc_dir_entry *ent;
+
+	ent = proc_create_seq("sctp_dbg_objcnt", 0,
+			  net->sctp.proc_net_sctp, &sctp_objcnt_seq_ops);
+	if (!ent)
+		pr_warn("sctp_dbg_objcnt: Unable to create /proc entry.\n");
+}

linux-7.2.3/net/sctp/offload.c

@@ -0,0 +1,120 @@
+// SPDX-License-Identifier: GPL-2.0-or-later
+/*
+ * sctp_offload - GRO/GSO Offloading for SCTP
+ *
+ * Copyright (C) 2015, Marcelo Ricardo Leitner <marcelo.leitner@gmail.com>
+ */
+
+#define pr_fmt(fmt) KBUILD_MODNAME ": " fmt
+
+#include <linux/kernel.h>
+#include <linux/kprobes.h>
+#include <linux/socket.h>
+#include <linux/sctp.h>
+#include <linux/proc_fs.h>
+#include <linux/vmalloc.h>
+#include <linux/module.h>
+#include <linux/kfifo.h>
+#include <linux/time.h>
+#include <net/net_namespace.h>
+
+#include <linux/skbuff.h>
+#include <net/sctp/sctp.h>
+#include <net/sctp/checksum.h>
+#include <net/protocol.h>
+#include <net/gso.h>
+
+static __le32 sctp_gso_make_checksum(struct sk_buff *skb)
+{
+	skb->ip_summed = CHECKSUM_NONE;
+	skb->csum_not_inet = 0;
+	/* csum and csum_start in GSO CB may be needed to do the UDP
+	 * checksum when it's a UDP tunneling packet.
+	 */
+	SKB_GSO_CB(skb)->csum = (__force __wsum)~0;
+	SKB_GSO_CB(skb)->csum_start = skb_headroom(skb) + skb->len;
+	return sctp_compute_cksum(skb, skb_transport_offset(skb));
+}
+
+static struct sk_buff *sctp_gso_segment(struct sk_buff *skb,
+					netdev_features_t features)
+{
+	struct sk_buff *segs = ERR_PTR(-EINVAL);
+	struct sctphdr *sh;
+
+	if (!skb_is_gso_sctp(skb))
+		goto out;
+
+	sh = sctp_hdr(skb);
+	if (!pskb_may_pull(skb, sizeof(*sh)))
+		goto out;
+
+	__skb_pull(skb, sizeof(*sh));
+
+	if (skb_gso_ok(skb, features | NETIF_F_GSO_ROBUST)) {
+		/* Packet is from an untrusted source, reset gso_segs. */
+		struct skb_shared_info *pinfo = skb_shinfo(skb);
+		struct sk_buff *frag_iter;
+
+		pinfo->gso_segs = 0;
+		if (skb->len != skb->data_len) {
+			/* Means we have chunks in here too */
+			pinfo->gso_segs++;
+		}
+
+		skb_walk_frags(skb, frag_iter)
+			pinfo->gso_segs++;
+
+		segs = NULL;
+		goto out;
+	}
+
+	segs = skb_segment(skb, (features | NETIF_F_HW_CSUM) & ~NETIF_F_SG);
+	if (IS_ERR(segs))
+		goto out;
+
+	/* All that is left is update SCTP CRC if necessary */
+	if (!(features & NETIF_F_SCTP_CRC)) {
+		for (skb = segs; skb; skb = skb->next) {
+			if (skb->ip_summed == CHECKSUM_PARTIAL) {
+				sh = sctp_hdr(skb);
+				sh->checksum = sctp_gso_make_checksum(skb);
+			}
+		}
+	}
+
+out:
+	return segs;
+}
+
+static const struct net_offload sctp_offload = {
+	.callbacks = {
+		.gso_segment = sctp_gso_segment,
+	},
+};
+
+static const struct net_offload sctp6_offload = {
+	.callbacks = {
+		.gso_segment = sctp_gso_segment,
+	},
+};
+
+int __init sctp_offload_init(void)
+{
+	int ret;
+
+	ret = inet_add_offload(&sctp_offload, IPPROTO_SCTP);
+	if (ret)
+		goto out;
+
+	ret = inet6_add_offload(&sctp6_offload, IPPROTO_SCTP);
+	if (ret)
+		goto ipv4;
+
+	return ret;
+
+ipv4:
+	inet_del_offload(&sctp_offload, IPPROTO_SCTP);
+out:
+	return ret;
+}

linux-7.2.3/net/sctp/output.c

@@ -0,0 +1,865 @@
+// SPDX-License-Identifier: GPL-2.0-or-later
+/* 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.
+ *
+ * Please send any bug reports or fixes you make to the
+ * email address(es):
+ *    lksctp developers <linux-sctp@vger.kernel.org>
+ *
+ * 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>
+ */
+
+#define pr_fmt(fmt) KBUILD_MODNAME ": " fmt
+
+#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 <linux/slab.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 enum sctp_xmit __sctp_packet_append_chunk(struct sctp_packet *packet,
+						 struct sctp_chunk *chunk);
+static enum sctp_xmit 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 enum sctp_xmit sctp_packet_will_fit(struct sctp_packet *packet,
+					   struct sctp_chunk *chunk,
+					   u16 chunk_len);
+
+static void sctp_packet_reset(struct sctp_packet *packet)
+{
+	/* sctp_packet_transmit() relies on this to reset size to the
+	 * current overhead after sending packets.
+	 */
+	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.
+ */
+void sctp_packet_config(struct sctp_packet *packet, __u32 vtag,
+			int ecn_capable)
+{
+	struct sctp_transport *tp = packet->transport;
+	struct sctp_association *asoc = tp->asoc;
+	struct sctp_sock *sp = NULL;
+	struct sock *sk;
+
+	pr_debug("%s: packet:%p vtag:0x%x\n", __func__, packet, vtag);
+	packet->vtag = vtag;
+
+	/* do the following jobs only once for a flush schedule */
+	if (!sctp_packet_empty(packet))
+		return;
+
+	/* set packet max_size with pathmtu, then calculate overhead */
+	packet->max_size = tp->pathmtu;
+
+	if (asoc) {
+		sk = asoc->base.sk;
+		sp = sctp_sk(sk);
+	}
+	packet->overhead = sctp_mtu_payload(sp, 0, 0);
+	packet->size = packet->overhead;
+
+	if (!asoc)
+		return;
+
+	/* update dst or transport pathmtu if in need */
+	if (!sctp_transport_dst_check(tp)) {
+		sctp_transport_route(tp, NULL, sp);
+		if (asoc->param_flags & SPP_PMTUD_ENABLE)
+			sctp_assoc_sync_pmtu(asoc);
+	} else if (!sctp_transport_pl_enabled(tp) &&
+		   asoc->param_flags & SPP_PMTUD_ENABLE) {
+		if (!sctp_transport_pmtu_check(tp))
+			sctp_assoc_sync_pmtu(asoc);
+	}
+
+	if (asoc->pmtu_pending) {
+		if (asoc->param_flags & SPP_PMTUD_ENABLE)
+			sctp_assoc_sync_pmtu(asoc);
+		asoc->pmtu_pending = 0;
+	}
+
+	/* If there a is a prepend chunk stick it on the list before
+	 * any other chunks get appended.
+	 */
+	if (ecn_capable) {
+		struct sctp_chunk *chunk = sctp_get_ecne_prepend(asoc);
+
+		if (chunk)
+			sctp_packet_append_chunk(packet, chunk);
+	}
+
+	if (!tp->dst)
+		return;
+
+	/* set packet max_size with gso_max_size if gso is enabled*/
+	rcu_read_lock();
+	if (__sk_dst_get(sk) != tp->dst) {
+		dst_hold(tp->dst);
+		sk_setup_caps(sk, tp->dst);
+	}
+	packet->max_size = sk_can_gso(sk) ? min(READ_ONCE(tp->dst->dev->gso_max_size),
+						GSO_LEGACY_MAX_SIZE)
+					  : asoc->pathmtu;
+	rcu_read_unlock();
+}
+
+/* Initialize the packet structure. */
+void sctp_packet_init(struct sctp_packet *packet,
+		      struct sctp_transport *transport,
+		      __u16 sport, __u16 dport)
+{
+	pr_debug("%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);
+	/* The overhead will be calculated by sctp_packet_config() */
+	packet->overhead = 0;
+	sctp_packet_reset(packet);
+	packet->vtag = 0;
+}
+
+/* Free a packet.  */
+void sctp_packet_free(struct sctp_packet *packet)
+{
+	struct sctp_chunk *chunk, *tmp;
+
+	pr_debug("%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);
+	}
+}
+
+/* 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.
+ */
+enum sctp_xmit sctp_packet_transmit_chunk(struct sctp_packet *packet,
+					  struct sctp_chunk *chunk,
+					  int one_packet, gfp_t gfp)
+{
+	enum sctp_xmit retval;
+
+	pr_debug("%s: packet:%p size:%zu chunk:%p size:%d\n", __func__,
+		 packet, packet->size, chunk, chunk->skb ? chunk->skb->len : -1);
+
+	switch ((retval = (sctp_packet_append_chunk(packet, chunk)))) {
+	case SCTP_XMIT_PMTU_FULL:
+		if (!packet->has_cookie_echo) {
+			int error = 0;
+
+			error = sctp_packet_transmit(packet, gfp);
+			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_DELAY:
+		break;
+	}
+
+	return retval;
+}
+
+/* Try to bundle a pad chunk into a packet with a heartbeat chunk for PLPMTUTD probe */
+static enum sctp_xmit sctp_packet_bundle_pad(struct sctp_packet *pkt, struct sctp_chunk *chunk)
+{
+	struct sctp_transport *t = pkt->transport;
+	struct sctp_chunk *pad;
+	int overhead = 0;
+
+	if (!chunk->pmtu_probe)
+		return SCTP_XMIT_OK;
+
+	/* calculate the Padding Data size for the pad chunk */
+	overhead += sizeof(struct sctphdr) + sizeof(struct sctp_chunkhdr);
+	overhead += sizeof(struct sctp_sender_hb_info) + sizeof(struct sctp_pad_chunk);
+	pad = sctp_make_pad(t->asoc, t->pl.probe_size - overhead);
+	if (!pad)
+		return SCTP_XMIT_DELAY;
+
+	list_add_tail(&pad->list, &pkt->chunk_list);
+	pkt->size += SCTP_PAD4(ntohs(pad->chunk_hdr->length));
+	chunk->transport = t;
+
+	return SCTP_XMIT_OK;
+}
+
+/* Try to bundle an auth chunk into the packet. */
+static enum sctp_xmit sctp_packet_bundle_auth(struct sctp_packet *pkt,
+					      struct sctp_chunk *chunk)
+{
+	struct sctp_association *asoc = pkt->transport->asoc;
+	enum sctp_xmit retval = SCTP_XMIT_OK;
+	struct sctp_chunk *auth;
+
+	/* 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, chunk->shkey->key_id);
+	if (!auth)
+		return retval;
+
+	auth->shkey = chunk->shkey;
+	sctp_auth_shkey_hold(auth->shkey);
+
+	retval = __sctp_packet_append_chunk(pkt, auth);
+
+	if (retval != SCTP_XMIT_OK)
+		sctp_chunk_free(auth);
+
+	return retval;
+}
+
+/* Try to bundle a SACK with the packet. */
+static enum sctp_xmit sctp_packet_bundle_sack(struct sctp_packet *pkt,
+					      struct sctp_chunk *chunk)
+{
+	enum sctp_xmit 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;
+
+			if (pkt->transport->sack_generation !=
+			    pkt->transport->asoc->peer.sack_generation)
+				return retval;
+
+			asoc->a_rwnd = asoc->rwnd;
+			sack = sctp_make_sack(asoc);
+			if (sack) {
+				retval = __sctp_packet_append_chunk(pkt, sack);
+				if (retval != SCTP_XMIT_OK) {
+					sctp_chunk_free(sack);
+					goto out;
+				}
+				SCTP_INC_STATS(asoc->base.net,
+					       SCTP_MIB_OUTCTRLCHUNKS);
+				asoc->stats.octrlchunks++;
+				asoc->peer.sack_needed = 0;
+				if (timer_delete(timer))
+					sctp_association_put(asoc);
+			}
+		}
+	}
+out:
+	return retval;
+}
+
+
+/* Append a chunk to the offered packet reporting back any inability to do
+ * so.
+ */
+static enum sctp_xmit __sctp_packet_append_chunk(struct sctp_packet *packet,
+						 struct sctp_chunk *chunk)
+{
+	__u16 chunk_len = SCTP_PAD4(ntohs(chunk->chunk_hdr->length));
+	enum sctp_xmit retval = SCTP_XMIT_OK;
+
+	/* 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:
+	case SCTP_CID_I_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;
+		/* Mainly used for prsctp RTX policy */
+		chunk->sent_count++;
+		break;
+	case SCTP_CID_COOKIE_ECHO:
+		packet->has_cookie_echo = 1;
+		break;
+
+	case SCTP_CID_SACK:
+		packet->has_sack = 1;
+		if (chunk->asoc)
+			chunk->asoc->stats.osacks++;
+		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;
+}
+
+/* Append a chunk to the offered packet reporting back any inability to do
+ * so.
+ */
+enum sctp_xmit sctp_packet_append_chunk(struct sctp_packet *packet,
+					struct sctp_chunk *chunk)
+{
+	enum sctp_xmit retval = SCTP_XMIT_OK;
+
+	pr_debug("%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;
+
+	retval = __sctp_packet_append_chunk(packet, chunk);
+	if (retval != SCTP_XMIT_OK)
+		goto finish;
+
+	retval = sctp_packet_bundle_pad(packet, chunk);
+
+finish:
+	return retval;
+}
+
+static void sctp_packet_gso_append(struct sk_buff *head, struct sk_buff *skb)
+{
+	if (SCTP_OUTPUT_CB(head)->last == head)
+		skb_shinfo(head)->frag_list = skb;
+	else
+		SCTP_OUTPUT_CB(head)->last->next = skb;
+	SCTP_OUTPUT_CB(head)->last = skb;
+
+	head->truesize += skb->truesize;
+	head->data_len += skb->len;
+	head->len += skb->len;
+	refcount_add(skb->truesize, &head->sk->sk_wmem_alloc);
+
+	__skb_header_release(skb);
+}
+
+static int sctp_packet_pack(struct sctp_packet *packet,
+			    struct sk_buff *head, int gso, gfp_t gfp)
+{
+	struct sctp_transport *tp = packet->transport;
+	struct sctp_auth_chunk *auth = NULL;
+	struct sctp_chunk *chunk, *tmp;
+	int pkt_count = 0, pkt_size;
+	struct sock *sk = head->sk;
+	struct sk_buff *nskb;
+	int auth_len = 0;
+
+	if (gso) {
+		skb_shinfo(head)->gso_type = sk->sk_gso_type;
+		SCTP_OUTPUT_CB(head)->last = head;
+	} else {
+		nskb = head;
+		pkt_size = packet->size;
+		goto merge;
+	}
+
+	do {
+		/* calculate the pkt_size and alloc nskb */
+		pkt_size = packet->overhead;
+		list_for_each_entry_safe(chunk, tmp, &packet->chunk_list,
+					 list) {
+			int padded = SCTP_PAD4(chunk->skb->len);
+
+			if (chunk == packet->auth)
+				auth_len = padded;
+			else if (auth_len + padded + packet->overhead >
+				 tp->pathmtu)
+				return 0;
+			else if (pkt_size + padded > tp->pathmtu)
+				break;
+			pkt_size += padded;
+		}
+		nskb = alloc_skb(pkt_size + MAX_HEADER, gfp);
+		if (!nskb)
+			return 0;
+		skb_reserve(nskb, packet->overhead + MAX_HEADER);
+
+merge:
+		/* merge chunks into nskb and append nskb into head list */
+		pkt_size -= packet->overhead;
+		list_for_each_entry_safe(chunk, tmp, &packet->chunk_list, list) {
+			int padding;
+
+			list_del_init(&chunk->list);
+			if (sctp_chunk_is_data(chunk)) {
+				if (!sctp_chunk_retransmitted(chunk) &&
+				    !tp->rto_pending) {
+					chunk->rtt_in_progress = 1;
+					tp->rto_pending = 1;
+				}
+			}
+
+			padding = SCTP_PAD4(chunk->skb->len) - chunk->skb->len;
+			if (padding)
+				skb_put_zero(chunk->skb, padding);
+
+			if (chunk == packet->auth)
+				auth = (struct sctp_auth_chunk *)
+							skb_tail_pointer(nskb);
+
+			skb_put_data(nskb, chunk->skb->data, chunk->skb->len);
+
+			pr_debug("*** Chunk:%p[%s] %s 0x%x, length:%d, chunk->skb->len:%d, rtt_in_progress:%d\n",
+				 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,
+				 ntohs(chunk->chunk_hdr->length), chunk->skb->len,
+				 chunk->rtt_in_progress);
+
+			pkt_size -= SCTP_PAD4(chunk->skb->len);
+
+			if (!sctp_chunk_is_data(chunk) && chunk != packet->auth)
+				sctp_chunk_free(chunk);
+
+			if (!pkt_size)
+				break;
+		}
+
+		if (auth) {
+			sctp_auth_calculate_hmac(tp->asoc, nskb, auth,
+						 packet->auth->shkey, gfp);
+			/* free auth if no more chunks, or add it back */
+			if (list_empty(&packet->chunk_list))
+				sctp_chunk_free(packet->auth);
+			else
+				list_add(&packet->auth->list,
+					 &packet->chunk_list);
+		}
+
+		if (gso)
+			sctp_packet_gso_append(head, nskb);
+
+		pkt_count++;
+	} while (!list_empty(&packet->chunk_list));
+
+	if (gso) {
+		memset(head->cb, 0, max(sizeof(struct inet_skb_parm),
+					sizeof(struct inet6_skb_parm)));
+		skb_shinfo(head)->gso_segs = pkt_count;
+		skb_shinfo(head)->gso_size = GSO_BY_FRAGS;
+		goto chksum;
+	}
+
+	if (sctp_checksum_disable)
+		return 1;
+
+	if (!(tp->dst->dev->features & NETIF_F_SCTP_CRC) ||
+	    dst_xfrm(tp->dst) || packet->ipfragok || tp->encap_port) {
+		struct sctphdr *sh =
+			(struct sctphdr *)skb_transport_header(head);
+
+		sh->checksum = sctp_compute_cksum(head, 0);
+	} else {
+chksum:
+		head->ip_summed = CHECKSUM_PARTIAL;
+		head->csum_not_inet = 1;
+		head->csum_start = skb_transport_header(head) - head->head;
+		head->csum_offset = offsetof(struct sctphdr, checksum);
+	}
+
+	return pkt_count;
+}
+
+/* All packets are sent to the network through this function from
+ * sctp_outq_tail().
+ *
+ * The return value is always 0 for now.
+ */
+int sctp_packet_transmit(struct sctp_packet *packet, gfp_t gfp)
+{
+	struct sctp_transport *tp = packet->transport;
+	struct sctp_association *asoc = tp->asoc;
+	struct sctp_chunk *chunk, *tmp;
+	int pkt_count, gso = 0;
+	struct sk_buff *head;
+	struct sctphdr *sh;
+	struct sock *sk;
+
+	pr_debug("%s: packet:%p\n", __func__, packet);
+	if (list_empty(&packet->chunk_list))
+		return 0;
+	chunk = list_entry(packet->chunk_list.next, struct sctp_chunk, list);
+	sk = chunk->skb->sk;
+
+	if (packet->size > tp->pathmtu && !packet->ipfragok && !chunk->pmtu_probe) {
+		if (tp->pl.state == SCTP_PL_ERROR) { /* do IP fragmentation if in Error state */
+			packet->ipfragok = 1;
+		} else {
+			if (!sk_can_gso(sk)) { /* check gso */
+				pr_err_once("Trying to GSO but underlying device doesn't support it.");
+				goto out;
+			}
+			gso = 1;
+		}
+	}
+
+	/* alloc head skb */
+	head = alloc_skb((gso ? packet->overhead : packet->size) +
+			 MAX_HEADER, gfp);
+	if (!head)
+		goto out;
+	skb_reserve(head, packet->overhead + MAX_HEADER);
+	skb_set_owner_w(head, sk);
+
+	/* set sctp header */
+	sh = skb_push(head, sizeof(struct sctphdr));
+	skb_reset_transport_header(head);
+	sh->source = htons(packet->source_port);
+	sh->dest = htons(packet->destination_port);
+	sh->vtag = htonl(packet->vtag);
+	sh->checksum = 0;
+
+	/* drop packet if no dst */
+	if (!tp->dst) {
+		IP_INC_STATS(sock_net(sk), IPSTATS_MIB_OUTNOROUTES);
+		kfree_skb(head);
+		goto out;
+	}
+
+	/* pack up chunks */
+	pkt_count = sctp_packet_pack(packet, head, gso, gfp);
+	if (!pkt_count) {
+		kfree_skb(head);
+		goto out;
+	}
+	pr_debug("***sctp_transmit_packet*** skb->len:%d\n", head->len);
+
+	/* start autoclose timer */
+	if (packet->has_data && sctp_state(asoc, ESTABLISHED) &&
+	    asoc->timeouts[SCTP_EVENT_TIMEOUT_AUTOCLOSE]) {
+		struct timer_list *timer =
+			&asoc->timers[SCTP_EVENT_TIMEOUT_AUTOCLOSE];
+		unsigned long timeout =
+			asoc->timeouts[SCTP_EVENT_TIMEOUT_AUTOCLOSE];
+
+		if (!mod_timer(timer, jiffies + timeout))
+			sctp_association_hold(asoc);
+	}
+
+	/* sctp xmit */
+	tp->af_specific->ecn_capable(sk);
+	if (asoc) {
+		asoc->stats.opackets += pkt_count;
+		if (asoc->peer.last_sent_to != tp)
+			asoc->peer.last_sent_to = tp;
+	}
+	head->ignore_df = packet->ipfragok;
+	if (tp->dst_pending_confirm)
+		skb_set_dst_pending_confirm(head, 1);
+	/* neighbour should be confirmed on successful transmission or
+	 * positive error
+	 */
+	if (tp->af_specific->sctp_xmit(head, tp) >= 0 &&
+	    tp->dst_pending_confirm)
+		tp->dst_pending_confirm = 0;
+
+out:
+	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);
+	}
+	sctp_packet_reset(packet);
+	return 0;
+}
+
+/********************************************************************
+ * 2nd Level Abstractions
+ ********************************************************************/
+
+/* This private function check to see if a chunk can be added */
+static enum sctp_xmit sctp_packet_can_append_data(struct sctp_packet *packet,
+						  struct sctp_chunk *chunk)
+{
+	size_t datasize, rwnd, inflight, flight_size;
+	struct sctp_transport *transport = packet->transport;
+	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 && inflight > 0)
+		/* We have (at least) one data chunk in flight,
+		 * so we can't fall back to rule 6.1 B).
+		 */
+		return SCTP_XMIT_RWND_FULL;
+
+	/* 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 &&
+	    flight_size >= transport->cwnd)
+		return SCTP_XMIT_RWND_FULL;
+
+	/* 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 || inflight == 0) &&
+	    !asoc->force_delay)
+		/* Nothing unacked */
+		return SCTP_XMIT_OK;
+
+	if (!sctp_packet_empty(packet))
+		/* Append to packet */
+		return SCTP_XMIT_OK;
+
+	if (!sctp_state(asoc, ESTABLISHED))
+		return SCTP_XMIT_OK;
+
+	/* Check whether this chunk and all the rest of pending data will fit
+	 * or delay in hopes of bundling a full sized packet.
+	 */
+	if (chunk->skb->len + q->out_qlen > transport->pathmtu -
+	    packet->overhead - sctp_datachk_len(&chunk->asoc->stream) - 4)
+		/* Enough data queued to fill a packet */
+		return SCTP_XMIT_OK;
+
+	/* Don't delay large message writes that may have been fragmented */
+	if (!chunk->msg->can_delay)
+		return SCTP_XMIT_OK;
+
+	/* Defer until all data acked or packet full */
+	return SCTP_XMIT_DELAY;
+}
+
+/* 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. */
+	if (datasize < rwnd)
+		rwnd -= datasize;
+	else
+		rwnd = 0;
+
+	asoc->peer.rwnd = rwnd;
+	sctp_chunk_assign_tsn(chunk);
+	asoc->stream.si->assign_number(chunk);
+}
+
+static enum sctp_xmit sctp_packet_will_fit(struct sctp_packet *packet,
+					   struct sctp_chunk *chunk,
+					   u16 chunk_len)
+{
+	enum sctp_xmit retval = SCTP_XMIT_OK;
+	size_t psize, pmtu, maxsize;
+
+	/* Don't bundle in this packet if this chunk's auth key doesn't
+	 * match other chunks already enqueued on this packet. Also,
+	 * don't bundle the chunk with auth key if other chunks in this
+	 * packet don't have auth key.
+	 */
+	if ((packet->auth && chunk->shkey != packet->auth->shkey) ||
+	    (!packet->auth && chunk->shkey &&
+	     chunk->chunk_hdr->type != SCTP_CID_AUTH))
+		return SCTP_XMIT_PMTU_FULL;
+
+	psize = packet->size;
+	if (packet->transport->asoc)
+		pmtu = packet->transport->asoc->pathmtu;
+	else
+		pmtu = packet->transport->pathmtu;
+
+	/* Decide if we need to fragment or resubmit later. */
+	if (psize + chunk_len > pmtu) {
+		/* It's OK to fragment 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 packet doesn't have any data in it yet and data
+		 *	   requires authentication.
+		 */
+		if (sctp_packet_empty(packet) ||
+		    (!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;
+			goto out;
+		}
+
+		/* Similarly, if this chunk was built before a PMTU
+		 * reduction, we have to fragment it at IP level now. So
+		 * if the packet already contains something, we need to
+		 * flush.
+		 */
+		maxsize = pmtu - packet->overhead;
+		if (packet->auth)
+			maxsize -= SCTP_PAD4(packet->auth->skb->len);
+		if (chunk_len > maxsize)
+			retval = SCTP_XMIT_PMTU_FULL;
+
+		/* It is also okay to fragment if the chunk we are
+		 * adding is a control chunk, but only if current packet
+		 * is not a GSO one otherwise it causes fragmentation of
+		 * a large frame. So in this case we allow the
+		 * fragmentation by forcing it to be in a new packet.
+		 */
+		if (!sctp_chunk_is_data(chunk) && packet->has_data)
+			retval = SCTP_XMIT_PMTU_FULL;
+
+		if (psize + chunk_len > packet->max_size)
+			/* Hit GSO/PMTU limit, gotta flush */
+			retval = SCTP_XMIT_PMTU_FULL;
+
+		if (!packet->transport->burst_limited &&
+		    psize + chunk_len > (packet->transport->cwnd >> 1))
+			/* Do not allow a single GSO packet to use more
+			 * than half of cwnd.
+			 */
+			retval = SCTP_XMIT_PMTU_FULL;
+
+		if (packet->transport->burst_limited &&
+		    psize + chunk_len > (packet->transport->burst_limited >> 1))
+			/* Do not allow a single GSO packet to use more
+			 * than half of original cwnd.
+			 */
+			retval = SCTP_XMIT_PMTU_FULL;
+		/* Otherwise it will fit in the GSO packet */
+	}
+
+out:
+	return retval;
+}

linux-7.2.3/net/sctp/primitive.c

@@ -0,0 +1,201 @@
+// SPDX-License-Identifier: GPL-2.0-or-later
+/* 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.
+ *
+ * Please send any bug reports or fixes you make to the
+ * email address(es):
+ *    lksctp developers <linux-sctp@vger.kernel.org>
+ *
+ * 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>
+ */
+
+#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 <linux/gfp.h>
+#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 net *net, struct sctp_association *asoc, \
+			    void *arg) { \
+	int error = 0; \
+	enum sctp_event_type event_type; union sctp_subtype subtype; \
+	enum sctp_state 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(net, 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);
+
+/* RE-CONFIG 5.1 */
+DECLARE_PRIMITIVE(RECONF);

linux-7.2.3/net/sctp/proc.c

@@ -0,0 +1,399 @@
+// SPDX-License-Identifier: GPL-2.0-or-later
+/* SCTP kernel implementation
+ * Copyright (c) 2003 International Business Machines, Corp.
+ *
+ * This file is part of the SCTP kernel implementation
+ *
+ * Please send any bug reports or fixes you make to the
+ * email address(es):
+ *    lksctp developers <linux-sctp@vger.kernel.org>
+ *
+ * Written or modified by:
+ *    Sridhar Samudrala <sri@us.ibm.com>
+ */
+
+#include <linux/types.h>
+#include <linux/seq_file.h>
+#include <linux/init.h>
+#include <linux/export.h>
+#include <net/sctp/sctp.h>
+#include <net/ip.h> /* for snmp_fold_field */
+
+static const 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),
+};
+
+/* Display sctp snmp mib statistics(/proc/net/sctp/snmp). */
+static int sctp_snmp_seq_show(struct seq_file *seq, void *v)
+{
+	unsigned long buff[ARRAY_SIZE(sctp_snmp_list)];
+	const int cnt = ARRAY_SIZE(sctp_snmp_list);
+	struct net *net = seq->private;
+	int i;
+
+	memset(buff, 0, sizeof(buff));
+
+	snmp_get_cpu_field_batch_cnt(buff, sctp_snmp_list, cnt,
+				     net->sctp.sctp_statistics);
+	for (i = 0; i < cnt; i++)
+		seq_printf(seq, "%-32s\t%ld\n", sctp_snmp_list[i].name,
+						buff[i]);
+
+	return 0;
+}
+
+/* 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;
+		if (unlikely(peer == NULL)) {
+			WARN(1, "Association %p with NULL primary path!\n", asoc);
+			return;
+		}
+
+		primary = &peer->saddr;
+	}
+
+	rcu_read_lock();
+	list_for_each_entry_rcu(laddr, &epb->bind_addr.address_list, list) {
+		if (!laddr->valid)
+			continue;
+
+		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);
+	}
+	rcu_read_unlock();
+}
+
+/* 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_rcu(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)
+{
+}
+
+
+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_endpoint *ep;
+	struct sock *sk;
+	int    hash = *(loff_t *)v;
+
+	if (hash >= sctp_ep_hashsize)
+		return -ENOMEM;
+
+	head = &sctp_ep_hashtable[hash];
+	read_lock_bh(&head->lock);
+	sctp_for_each_hentry(ep, &head->chain) {
+		sk = ep->base.sk;
+		if (!net_eq(sock_net(sk), seq_file_net(seq)))
+			continue;
+		seq_printf(seq, "%8pK %8pK %-3d %-3d %-4d %-5d %5u %5llu ", ep, sk,
+			   sctp_sk(sk)->type, sk->sk_state, hash,
+			   ep->base.bind_addr.port,
+			   from_kuid_munged(seq_user_ns(seq), sk_uid(sk)),
+			   sock_i_ino(sk));
+
+		sctp_seq_dump_local_addrs(seq, &ep->base);
+		seq_printf(seq, "\n");
+	}
+	read_unlock_bh(&head->lock);
+
+	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,
+};
+
+struct sctp_ht_iter {
+	struct seq_net_private p;
+	struct rhashtable_iter hti;
+};
+
+static void *sctp_transport_seq_start(struct seq_file *seq, loff_t *pos)
+{
+	struct sctp_ht_iter *iter = seq->private;
+
+	sctp_transport_walk_start(&iter->hti);
+
+	return sctp_transport_get_idx(seq_file_net(seq), &iter->hti, *pos);
+}
+
+static void sctp_transport_seq_stop(struct seq_file *seq, void *v)
+{
+	struct sctp_ht_iter *iter = seq->private;
+
+	if (v && v != SEQ_START_TOKEN) {
+		struct sctp_transport *transport = v;
+
+		sctp_transport_put(transport);
+	}
+
+	sctp_transport_walk_stop(&iter->hti);
+}
+
+static void *sctp_transport_seq_next(struct seq_file *seq, void *v, loff_t *pos)
+{
+	struct sctp_ht_iter *iter = seq->private;
+
+	if (v && v != SEQ_START_TOKEN) {
+		struct sctp_transport *transport = v;
+
+		sctp_transport_put(transport);
+	}
+
+	++*pos;
+
+	return sctp_transport_get_next(seq_file_net(seq), &iter->hti);
+}
+
+/* Display sctp associations (/proc/net/sctp/assocs). */
+static int sctp_assocs_seq_show(struct seq_file *seq, void *v)
+{
+	struct sctp_transport *transport;
+	struct sctp_association *assoc;
+	struct sctp_ep_common *epb;
+	struct sock *sk;
+
+	if (v == SEQ_START_TOKEN) {
+		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 "
+				"wmema wmemq sndbuf rcvbuf\n");
+		return 0;
+	}
+
+	transport = (struct sctp_transport *)v;
+	assoc = transport->asoc;
+	epb = &assoc->base;
+	sk = epb->sk;
+
+	seq_printf(seq,
+		   "%8pK %8pK %-3d %-3d %-2d %-4d "
+		   "%4d %8d %8d %7u %5llu %-5d %5d ",
+		   assoc, sk, sctp_sk(sk)->type, sk->sk_state,
+		   assoc->state, 0,
+		   assoc->assoc_id,
+		   assoc->sndbuf_used,
+		   atomic_read(&assoc->rmem_alloc),
+		   from_kuid_munged(seq_user_ns(seq), sk_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 "
+		   "%8d %8d %8d %8d",
+		assoc->hbinterval, assoc->stream.incnt,
+		assoc->stream.outcnt, assoc->max_retrans,
+		assoc->init_retries, assoc->shutdown_retries,
+		assoc->rtx_data_chunks,
+		refcount_read(&sk->sk_wmem_alloc),
+		READ_ONCE(sk->sk_wmem_queued),
+		sk->sk_sndbuf,
+		sk->sk_rcvbuf);
+	seq_printf(seq, "\n");
+
+	return 0;
+}
+
+static const struct seq_operations sctp_assoc_ops = {
+	.start = sctp_transport_seq_start,
+	.next  = sctp_transport_seq_next,
+	.stop  = sctp_transport_seq_stop,
+	.show  = sctp_assocs_seq_show,
+};
+
+static int sctp_remaddr_seq_show(struct seq_file *seq, void *v)
+{
+	struct sctp_association *assoc;
+	struct sctp_transport *transport, *tsp;
+
+	if (v == SEQ_START_TOKEN) {
+		seq_printf(seq, "ADDR ASSOC_ID HB_ACT RTO MAX_PATH_RTX "
+				"REM_ADDR_RTX START STATE\n");
+		return 0;
+	}
+
+	transport = (struct sctp_transport *)v;
+	assoc = transport->asoc;
+
+	list_for_each_entry_rcu(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_puts(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_puts(seq, "0 ");
+
+		/*
+		 * The current state of this destination. I.e.
+		 * SCTP_ACTIVE, SCTP_INACTIVE, ...
+		 */
+		seq_printf(seq, "%d", tsp->state);
+
+		seq_printf(seq, "\n");
+	}
+
+	return 0;
+}
+
+static const struct seq_operations sctp_remaddr_ops = {
+	.start = sctp_transport_seq_start,
+	.next  = sctp_transport_seq_next,
+	.stop  = sctp_transport_seq_stop,
+	.show  = sctp_remaddr_seq_show,
+};
+
+/* Set up the proc fs entry for the SCTP protocol. */
+int __net_init sctp_proc_init(struct net *net)
+{
+	net->sctp.proc_net_sctp = proc_net_mkdir(net, "sctp", net->proc_net);
+	if (!net->sctp.proc_net_sctp)
+		return -ENOMEM;
+	if (!proc_create_net_single("snmp", 0444, net->sctp.proc_net_sctp,
+			 sctp_snmp_seq_show, NULL))
+		goto cleanup;
+	if (!proc_create_net("eps", 0444, net->sctp.proc_net_sctp,
+			&sctp_eps_ops, sizeof(struct seq_net_private)))
+		goto cleanup;
+	if (!proc_create_net("assocs", 0444, net->sctp.proc_net_sctp,
+			&sctp_assoc_ops, sizeof(struct sctp_ht_iter)))
+		goto cleanup;
+	if (!proc_create_net("remaddr", 0444, net->sctp.proc_net_sctp,
+			&sctp_remaddr_ops, sizeof(struct sctp_ht_iter)))
+		goto cleanup;
+	return 0;
+
+cleanup:
+	remove_proc_subtree("sctp", net->proc_net);
+	net->sctp.proc_net_sctp = NULL;
+	return -ENOMEM;
+}

linux-7.2.3/net/sctp/stream_sched.c

@@ -0,0 +1,280 @@
+// SPDX-License-Identifier: GPL-2.0-or-later
+/* SCTP kernel implementation
+ * (C) Copyright Red Hat Inc. 2017
+ *
+ * This file is part of the SCTP kernel implementation
+ *
+ * These functions manipulate sctp stream queue/scheduling.
+ *
+ * Please send any bug reports or fixes you make to the
+ * email addresched(es):
+ *    lksctp developers <linux-sctp@vger.kernel.org>
+ *
+ * Written or modified by:
+ *    Marcelo Ricardo Leitner <marcelo.leitner@gmail.com>
+ */
+
+#include <linux/list.h>
+#include <net/sctp/sctp.h>
+#include <net/sctp/sm.h>
+#include <net/sctp/stream_sched.h>
+
+/* First Come First Serve (a.k.a. FIFO)
+ * RFC DRAFT ndata Section 3.1
+ */
+static int sctp_sched_fcfs_set(struct sctp_stream *stream, __u16 sid,
+			       __u16 value, gfp_t gfp)
+{
+	return 0;
+}
+
+static int sctp_sched_fcfs_get(struct sctp_stream *stream, __u16 sid,
+			       __u16 *value)
+{
+	*value = 0;
+	return 0;
+}
+
+static int sctp_sched_fcfs_init(struct sctp_stream *stream)
+{
+	return 0;
+}
+
+static int sctp_sched_fcfs_init_sid(struct sctp_stream *stream, __u16 sid,
+				    gfp_t gfp)
+{
+	return 0;
+}
+
+static void sctp_sched_fcfs_free_sid(struct sctp_stream *stream, __u16 sid)
+{
+}
+
+static void sctp_sched_fcfs_enqueue(struct sctp_outq *q,
+				    struct sctp_datamsg *msg)
+{
+}
+
+static struct sctp_chunk *sctp_sched_fcfs_dequeue(struct sctp_outq *q)
+{
+	struct sctp_stream *stream = &q->asoc->stream;
+	struct sctp_chunk *ch = NULL;
+	struct list_head *entry;
+
+	if (list_empty(&q->out_chunk_list))
+		goto out;
+
+	if (stream->out_curr) {
+		ch = list_entry(stream->out_curr->ext->outq.next,
+				struct sctp_chunk, stream_list);
+	} else {
+		entry = q->out_chunk_list.next;
+		ch = list_entry(entry, struct sctp_chunk, list);
+	}
+
+	sctp_sched_dequeue_common(q, ch);
+
+out:
+	return ch;
+}
+
+static void sctp_sched_fcfs_dequeue_done(struct sctp_outq *q,
+					 struct sctp_chunk *chunk)
+{
+}
+
+static void sctp_sched_fcfs_sched_all(struct sctp_stream *stream)
+{
+}
+
+static void sctp_sched_fcfs_unsched_all(struct sctp_stream *stream)
+{
+}
+
+static const struct sctp_sched_ops sctp_sched_fcfs = {
+	.set = sctp_sched_fcfs_set,
+	.get = sctp_sched_fcfs_get,
+	.init = sctp_sched_fcfs_init,
+	.init_sid = sctp_sched_fcfs_init_sid,
+	.free_sid = sctp_sched_fcfs_free_sid,
+	.enqueue = sctp_sched_fcfs_enqueue,
+	.dequeue = sctp_sched_fcfs_dequeue,
+	.dequeue_done = sctp_sched_fcfs_dequeue_done,
+	.sched_all = sctp_sched_fcfs_sched_all,
+	.unsched_all = sctp_sched_fcfs_unsched_all,
+};
+
+static void sctp_sched_ops_fcfs_init(void)
+{
+	sctp_sched_ops_register(SCTP_SS_FCFS, &sctp_sched_fcfs);
+}
+
+/* API to other parts of the stack */
+
+static const struct sctp_sched_ops *sctp_sched_ops[SCTP_SS_MAX + 1];
+
+void sctp_sched_ops_register(enum sctp_sched_type sched,
+			     const struct sctp_sched_ops *sched_ops)
+{
+	sctp_sched_ops[sched] = sched_ops;
+}
+
+void sctp_sched_ops_init(void)
+{
+	sctp_sched_ops_fcfs_init();
+	sctp_sched_ops_prio_init();
+	sctp_sched_ops_rr_init();
+	sctp_sched_ops_fc_init();
+	sctp_sched_ops_wfq_init();
+}
+
+static void sctp_sched_free_sched(struct sctp_stream *stream)
+{
+	const struct sctp_sched_ops *sched = sctp_sched_ops_from_stream(stream);
+	struct sctp_stream_out_ext *soute;
+	int i;
+
+	sched->unsched_all(stream);
+	for (i = 0; i < stream->outcnt; i++) {
+		soute = SCTP_SO(stream, i)->ext;
+		if (!soute)
+			continue;
+		sched->free_sid(stream, i);
+		/* Give the next scheduler a clean slate. */
+		memset_after(soute, 0, outq);
+	}
+}
+
+int sctp_sched_set_sched(struct sctp_association *asoc,
+			 enum sctp_sched_type sched)
+{
+	const struct sctp_sched_ops *old = asoc->outqueue.sched;
+	struct sctp_datamsg *msg = NULL;
+	const struct sctp_sched_ops *n;
+	struct sctp_chunk *ch;
+	int i, ret = 0;
+
+	if (sched > SCTP_SS_MAX)
+		return -EINVAL;
+
+	n = sctp_sched_ops[sched];
+	if (old == n)
+		return ret;
+
+	if (old)
+		sctp_sched_free_sched(&asoc->stream);
+
+	asoc->outqueue.sched = n;
+	n->init(&asoc->stream);
+	for (i = 0; i < asoc->stream.outcnt; i++) {
+		if (!SCTP_SO(&asoc->stream, i)->ext)
+			continue;
+
+		ret = n->init_sid(&asoc->stream, i, GFP_ATOMIC);
+		if (ret)
+			goto err;
+	}
+
+	/* We have to requeue all chunks already queued. */
+	list_for_each_entry(ch, &asoc->outqueue.out_chunk_list, list) {
+		if (ch->msg == msg)
+			continue;
+		msg = ch->msg;
+		n->enqueue(&asoc->outqueue, msg);
+	}
+
+	return ret;
+
+err:
+	sctp_sched_free_sched(&asoc->stream);
+	asoc->outqueue.sched = &sctp_sched_fcfs; /* Always safe */
+
+	return ret;
+}
+
+int sctp_sched_get_sched(struct sctp_association *asoc)
+{
+	int i;
+
+	for (i = 0; i <= SCTP_SS_MAX; i++)
+		if (asoc->outqueue.sched == sctp_sched_ops[i])
+			return i;
+
+	return 0;
+}
+
+int sctp_sched_set_value(struct sctp_association *asoc, __u16 sid,
+			 __u16 value, gfp_t gfp)
+{
+	if (sid >= asoc->stream.outcnt)
+		return -EINVAL;
+
+	if (!SCTP_SO(&asoc->stream, sid)->ext) {
+		int ret;
+
+		ret = sctp_stream_init_ext(&asoc->stream, sid);
+		if (ret)
+			return ret;
+	}
+
+	return asoc->outqueue.sched->set(&asoc->stream, sid, value, gfp);
+}
+
+int sctp_sched_get_value(struct sctp_association *asoc, __u16 sid,
+			 __u16 *value)
+{
+	if (sid >= asoc->stream.outcnt)
+		return -EINVAL;
+
+	if (!SCTP_SO(&asoc->stream, sid)->ext)
+		return 0;
+
+	return asoc->outqueue.sched->get(&asoc->stream, sid, value);
+}
+
+void sctp_sched_dequeue_done(struct sctp_outq *q, struct sctp_chunk *ch)
+{
+	if (!list_is_last(&ch->frag_list, &ch->msg->chunks) &&
+	    !q->asoc->peer.intl_capable) {
+		struct sctp_stream_out *sout;
+		__u16 sid;
+
+		/* datamsg is not finish, so save it as current one,
+		 * in case application switch scheduler or a higher
+		 * priority stream comes in.
+		 */
+		sid = sctp_chunk_stream_no(ch);
+		sout = SCTP_SO(&q->asoc->stream, sid);
+		q->asoc->stream.out_curr = sout;
+		return;
+	}
+
+	q->asoc->stream.out_curr = NULL;
+	q->sched->dequeue_done(q, ch);
+}
+
+/* Auxiliary functions for the schedulers */
+void sctp_sched_dequeue_common(struct sctp_outq *q, struct sctp_chunk *ch)
+{
+	list_del_init(&ch->list);
+	list_del_init(&ch->stream_list);
+	q->out_qlen -= ch->skb->len;
+}
+
+int sctp_sched_init_sid(struct sctp_stream *stream, __u16 sid, gfp_t gfp)
+{
+	const struct sctp_sched_ops *sched = sctp_sched_ops_from_stream(stream);
+	struct sctp_stream_out_ext *ext = SCTP_SO(stream, sid)->ext;
+
+	INIT_LIST_HEAD(&ext->outq);
+	return sched->init_sid(stream, sid, gfp);
+}
+
+const struct sctp_sched_ops *sctp_sched_ops_from_stream(struct sctp_stream *stream)
+{
+	struct sctp_association *asoc;
+
+	asoc = container_of(stream, struct sctp_association, stream);
+
+	return asoc->outqueue.sched;
+}

linux-7.2.3/net/sctp/stream_sched_fc.c

@@ -0,0 +1,225 @@
+// SPDX-License-Identifier: GPL-2.0-or-later
+/* SCTP kernel implementation
+ * (C) Copyright Red Hat Inc. 2022
+ *
+ * This file is part of the SCTP kernel implementation
+ *
+ * These functions manipulate sctp stream queue/scheduling.
+ *
+ * Please send any bug reports or fixes you make to the
+ * email addresched(es):
+ *    lksctp developers <linux-sctp@vger.kernel.org>
+ *
+ * Written or modified by:
+ *    Xin Long <lucien.xin@gmail.com>
+ */
+
+#include <linux/list.h>
+#include <net/sctp/sctp.h>
+#include <net/sctp/sm.h>
+#include <net/sctp/stream_sched.h>
+
+/* Fair Capacity and Weighted Fair Queueing handling
+ * RFC 8260 section 3.5 and 3.6
+ */
+static void sctp_sched_fc_unsched_all(struct sctp_stream *stream);
+
+static int sctp_sched_wfq_set(struct sctp_stream *stream, __u16 sid,
+			      __u16 weight, gfp_t gfp)
+{
+	struct sctp_stream_out_ext *soute = SCTP_SO(stream, sid)->ext;
+
+	if (!weight)
+		return -EINVAL;
+
+	soute->fc_weight = weight;
+	return 0;
+}
+
+static int sctp_sched_wfq_get(struct sctp_stream *stream, __u16 sid,
+			      __u16 *value)
+{
+	struct sctp_stream_out_ext *soute = SCTP_SO(stream, sid)->ext;
+
+	*value = soute->fc_weight;
+	return 0;
+}
+
+static int sctp_sched_fc_set(struct sctp_stream *stream, __u16 sid,
+			     __u16 weight, gfp_t gfp)
+{
+	return 0;
+}
+
+static int sctp_sched_fc_get(struct sctp_stream *stream, __u16 sid,
+			     __u16 *value)
+{
+	return 0;
+}
+
+static int sctp_sched_fc_init(struct sctp_stream *stream)
+{
+	INIT_LIST_HEAD(&stream->fc_list);
+
+	return 0;
+}
+
+static int sctp_sched_fc_init_sid(struct sctp_stream *stream, __u16 sid,
+				  gfp_t gfp)
+{
+	struct sctp_stream_out_ext *soute = SCTP_SO(stream, sid)->ext;
+
+	INIT_LIST_HEAD(&soute->fc_list);
+	soute->fc_length = 0;
+	soute->fc_weight = 1;
+
+	return 0;
+}
+
+static void sctp_sched_fc_free_sid(struct sctp_stream *stream, __u16 sid)
+{
+}
+
+static void sctp_sched_fc_sched(struct sctp_stream *stream,
+				struct sctp_stream_out_ext *soute)
+{
+	struct sctp_stream_out_ext *pos;
+
+	if (!list_empty(&soute->fc_list))
+		return;
+
+	list_for_each_entry(pos, &stream->fc_list, fc_list)
+		if ((__u64)pos->fc_length * soute->fc_weight >=
+		    (__u64)soute->fc_length * pos->fc_weight)
+			break;
+	list_add_tail(&soute->fc_list, &pos->fc_list);
+}
+
+static void sctp_sched_fc_enqueue(struct sctp_outq *q,
+				  struct sctp_datamsg *msg)
+{
+	struct sctp_stream *stream;
+	struct sctp_chunk *ch;
+	__u16 sid;
+
+	ch = list_first_entry(&msg->chunks, struct sctp_chunk, frag_list);
+	sid = sctp_chunk_stream_no(ch);
+	stream = &q->asoc->stream;
+	sctp_sched_fc_sched(stream, SCTP_SO(stream, sid)->ext);
+}
+
+static struct sctp_chunk *sctp_sched_fc_dequeue(struct sctp_outq *q)
+{
+	struct sctp_stream *stream = &q->asoc->stream;
+	struct sctp_stream_out_ext *soute;
+	struct sctp_chunk *ch;
+
+	/* Bail out quickly if queue is empty */
+	if (list_empty(&q->out_chunk_list))
+		return NULL;
+
+	/* Find which chunk is next */
+	if (stream->out_curr)
+		soute = stream->out_curr->ext;
+	else
+		soute = list_entry(stream->fc_list.next, struct sctp_stream_out_ext, fc_list);
+	ch = list_entry(soute->outq.next, struct sctp_chunk, stream_list);
+
+	sctp_sched_dequeue_common(q, ch);
+	return ch;
+}
+
+static void sctp_sched_fc_dequeue_done(struct sctp_outq *q,
+				       struct sctp_chunk *ch)
+{
+	struct sctp_stream *stream = &q->asoc->stream;
+	struct sctp_stream_out_ext *soute, *pos;
+	__u16 sid, i;
+
+	sid = sctp_chunk_stream_no(ch);
+	soute = SCTP_SO(stream, sid)->ext;
+	/* reduce all fc_lengths by U32_MAX / 4 if the current fc_length overflows. */
+	if (soute->fc_length > U32_MAX - ch->skb->len) {
+		for (i = 0; i < stream->outcnt; i++) {
+			pos = SCTP_SO(stream, i)->ext;
+			if (!pos)
+				continue;
+			if (pos->fc_length <= (U32_MAX >> 2)) {
+				pos->fc_length = 0;
+				continue;
+			}
+			pos->fc_length -= (U32_MAX >> 2);
+		}
+	}
+	soute->fc_length += ch->skb->len;
+
+	if (list_empty(&soute->outq)) {
+		list_del_init(&soute->fc_list);
+		return;
+	}
+
+	pos = soute;
+	list_for_each_entry_continue(pos, &stream->fc_list, fc_list)
+		if ((__u64)pos->fc_length * soute->fc_weight >=
+		    (__u64)soute->fc_length * pos->fc_weight)
+			break;
+	list_move_tail(&soute->fc_list, &pos->fc_list);
+}
+
+static void sctp_sched_fc_sched_all(struct sctp_stream *stream)
+{
+	struct sctp_association *asoc;
+	struct sctp_chunk *ch;
+
+	asoc = container_of(stream, struct sctp_association, stream);
+	list_for_each_entry(ch, &asoc->outqueue.out_chunk_list, list) {
+		__u16 sid = sctp_chunk_stream_no(ch);
+
+		if (SCTP_SO(stream, sid)->ext)
+			sctp_sched_fc_sched(stream, SCTP_SO(stream, sid)->ext);
+	}
+}
+
+static void sctp_sched_fc_unsched_all(struct sctp_stream *stream)
+{
+	struct sctp_stream_out_ext *soute, *tmp;
+
+	list_for_each_entry_safe(soute, tmp, &stream->fc_list, fc_list)
+		list_del_init(&soute->fc_list);
+}
+
+static const struct sctp_sched_ops sctp_sched_fc = {
+	.set = sctp_sched_fc_set,
+	.get = sctp_sched_fc_get,
+	.init = sctp_sched_fc_init,
+	.init_sid = sctp_sched_fc_init_sid,
+	.free_sid = sctp_sched_fc_free_sid,
+	.enqueue = sctp_sched_fc_enqueue,
+	.dequeue = sctp_sched_fc_dequeue,
+	.dequeue_done = sctp_sched_fc_dequeue_done,
+	.sched_all = sctp_sched_fc_sched_all,
+	.unsched_all = sctp_sched_fc_unsched_all,
+};
+
+void sctp_sched_ops_fc_init(void)
+{
+	sctp_sched_ops_register(SCTP_SS_FC, &sctp_sched_fc);
+}
+
+static const struct sctp_sched_ops sctp_sched_wfq = {
+	.set = sctp_sched_wfq_set,
+	.get = sctp_sched_wfq_get,
+	.init = sctp_sched_fc_init,
+	.init_sid = sctp_sched_fc_init_sid,
+	.free_sid = sctp_sched_fc_free_sid,
+	.enqueue = sctp_sched_fc_enqueue,
+	.dequeue = sctp_sched_fc_dequeue,
+	.dequeue_done = sctp_sched_fc_dequeue_done,
+	.sched_all = sctp_sched_fc_sched_all,
+	.unsched_all = sctp_sched_fc_unsched_all,
+};
+
+void sctp_sched_ops_wfq_init(void)
+{
+	sctp_sched_ops_register(SCTP_SS_WFQ, &sctp_sched_wfq);
+}

linux-7.2.3/net/sctp/stream_sched_prio.c

@@ -0,0 +1,319 @@
+// SPDX-License-Identifier: GPL-2.0-or-later
+/* SCTP kernel implementation
+ * (C) Copyright Red Hat Inc. 2017
+ *
+ * This file is part of the SCTP kernel implementation
+ *
+ * These functions manipulate sctp stream queue/scheduling.
+ *
+ * Please send any bug reports or fixes you make to the
+ * email addresched(es):
+ *    lksctp developers <linux-sctp@vger.kernel.org>
+ *
+ * Written or modified by:
+ *    Marcelo Ricardo Leitner <marcelo.leitner@gmail.com>
+ */
+
+#include <linux/list.h>
+#include <net/sctp/sctp.h>
+#include <net/sctp/sm.h>
+#include <net/sctp/stream_sched.h>
+
+/* Priority handling
+ * RFC DRAFT ndata section 3.4
+ */
+
+static void sctp_sched_prio_unsched_all(struct sctp_stream *stream);
+
+static struct sctp_stream_priorities *sctp_sched_prio_head_get(struct sctp_stream_priorities *p)
+{
+	p->users++;
+	return p;
+}
+
+static void sctp_sched_prio_head_put(struct sctp_stream_priorities *p)
+{
+	if (p && --p->users == 0)
+		kfree(p);
+}
+
+static struct sctp_stream_priorities *sctp_sched_prio_new_head(
+			struct sctp_stream *stream, int prio, gfp_t gfp)
+{
+	struct sctp_stream_priorities *p;
+
+	p = kmalloc_obj(*p, gfp);
+	if (!p)
+		return NULL;
+
+	INIT_LIST_HEAD(&p->prio_sched);
+	INIT_LIST_HEAD(&p->active);
+	p->next = NULL;
+	p->prio = prio;
+	p->users = 1;
+
+	return p;
+}
+
+static struct sctp_stream_priorities *sctp_sched_prio_get_head(
+			struct sctp_stream *stream, int prio, gfp_t gfp)
+{
+	struct sctp_stream_priorities *p;
+	int i;
+
+	/* Look into scheduled priorities first, as they are sorted and
+	 * we can find it fast IF it's scheduled.
+	 */
+	list_for_each_entry(p, &stream->prio_list, prio_sched) {
+		if (p->prio == prio)
+			return sctp_sched_prio_head_get(p);
+		if (p->prio > prio)
+			break;
+	}
+
+	/* No luck. So we search on all streams now. */
+	for (i = 0; i < stream->outcnt; i++) {
+		if (!SCTP_SO(stream, i)->ext)
+			continue;
+
+		p = SCTP_SO(stream, i)->ext->prio_head;
+		if (!p)
+			/* Means all other streams won't be initialized
+			 * as well.
+			 */
+			break;
+		if (p->prio == prio)
+			return sctp_sched_prio_head_get(p);
+	}
+
+	/* If not even there, allocate a new one. */
+	return sctp_sched_prio_new_head(stream, prio, gfp);
+}
+
+static void sctp_sched_prio_next_stream(struct sctp_stream_priorities *p)
+{
+	struct list_head *pos;
+
+	pos = p->next->prio_list.next;
+	if (pos == &p->active)
+		pos = pos->next;
+	p->next = list_entry(pos, struct sctp_stream_out_ext, prio_list);
+}
+
+static bool sctp_sched_prio_unsched(struct sctp_stream_out_ext *soute)
+{
+	bool scheduled = false;
+
+	if (!list_empty(&soute->prio_list)) {
+		struct sctp_stream_priorities *prio_head = soute->prio_head;
+
+		/* Scheduled */
+		scheduled = true;
+
+		if (prio_head->next == soute)
+			/* Try to move to the next stream */
+			sctp_sched_prio_next_stream(prio_head);
+
+		list_del_init(&soute->prio_list);
+
+		/* Also unsched the priority if this was the last stream */
+		if (list_empty(&prio_head->active)) {
+			list_del_init(&prio_head->prio_sched);
+			/* If there is no stream left, clear next */
+			prio_head->next = NULL;
+		}
+	}
+
+	return scheduled;
+}
+
+static void sctp_sched_prio_sched(struct sctp_stream *stream,
+				  struct sctp_stream_out_ext *soute)
+{
+	struct sctp_stream_priorities *prio, *prio_head;
+
+	prio_head = soute->prio_head;
+
+	/* Nothing to do if already scheduled */
+	if (!list_empty(&soute->prio_list))
+		return;
+
+	/* Schedule the stream. If there is a next, we schedule the new
+	 * one before it, so it's the last in round robin order.
+	 * If there isn't, we also have to schedule the priority.
+	 */
+	if (prio_head->next) {
+		list_add(&soute->prio_list, prio_head->next->prio_list.prev);
+		return;
+	}
+
+	list_add(&soute->prio_list, &prio_head->active);
+	prio_head->next = soute;
+
+	list_for_each_entry(prio, &stream->prio_list, prio_sched) {
+		if (prio->prio > prio_head->prio) {
+			list_add(&prio_head->prio_sched, prio->prio_sched.prev);
+			return;
+		}
+	}
+
+	list_add_tail(&prio_head->prio_sched, &stream->prio_list);
+}
+
+static int sctp_sched_prio_set(struct sctp_stream *stream, __u16 sid,
+			       __u16 prio, gfp_t gfp)
+{
+	struct sctp_stream_out *sout = SCTP_SO(stream, sid);
+	struct sctp_stream_out_ext *soute = sout->ext;
+	struct sctp_stream_priorities *prio_head, *old;
+	bool reschedule = false;
+
+	old = soute->prio_head;
+	if (old && old->prio == prio)
+		return 0;
+
+	prio_head = sctp_sched_prio_get_head(stream, prio, gfp);
+	if (!prio_head)
+		return -ENOMEM;
+
+	reschedule = sctp_sched_prio_unsched(soute);
+	soute->prio_head = prio_head;
+	if (reschedule)
+		sctp_sched_prio_sched(stream, soute);
+
+	sctp_sched_prio_head_put(old);
+	return 0;
+}
+
+static int sctp_sched_prio_get(struct sctp_stream *stream, __u16 sid,
+			       __u16 *value)
+{
+	*value = SCTP_SO(stream, sid)->ext->prio_head->prio;
+	return 0;
+}
+
+static int sctp_sched_prio_init(struct sctp_stream *stream)
+{
+	INIT_LIST_HEAD(&stream->prio_list);
+
+	return 0;
+}
+
+static int sctp_sched_prio_init_sid(struct sctp_stream *stream, __u16 sid,
+				    gfp_t gfp)
+{
+	INIT_LIST_HEAD(&SCTP_SO(stream, sid)->ext->prio_list);
+	return sctp_sched_prio_set(stream, sid, 0, gfp);
+}
+
+static void sctp_sched_prio_free_sid(struct sctp_stream *stream, __u16 sid)
+{
+	sctp_sched_prio_head_put(SCTP_SO(stream, sid)->ext->prio_head);
+	SCTP_SO(stream, sid)->ext->prio_head = NULL;
+}
+
+static void sctp_sched_prio_enqueue(struct sctp_outq *q,
+				    struct sctp_datamsg *msg)
+{
+	struct sctp_stream *stream;
+	struct sctp_chunk *ch;
+	__u16 sid;
+
+	ch = list_first_entry(&msg->chunks, struct sctp_chunk, frag_list);
+	sid = sctp_chunk_stream_no(ch);
+	stream = &q->asoc->stream;
+	sctp_sched_prio_sched(stream, SCTP_SO(stream, sid)->ext);
+}
+
+static struct sctp_chunk *sctp_sched_prio_dequeue(struct sctp_outq *q)
+{
+	struct sctp_stream *stream = &q->asoc->stream;
+	struct sctp_stream_priorities *prio;
+	struct sctp_stream_out_ext *soute;
+	struct sctp_chunk *ch = NULL;
+
+	/* Bail out quickly if queue is empty */
+	if (list_empty(&q->out_chunk_list))
+		goto out;
+
+	/* Find which chunk is next. It's easy, it's either the current
+	 * one or the first chunk on the next active stream.
+	 */
+	if (stream->out_curr) {
+		soute = stream->out_curr->ext;
+	} else {
+		prio = list_entry(stream->prio_list.next,
+				  struct sctp_stream_priorities, prio_sched);
+		soute = prio->next;
+	}
+	ch = list_entry(soute->outq.next, struct sctp_chunk, stream_list);
+	sctp_sched_dequeue_common(q, ch);
+
+out:
+	return ch;
+}
+
+static void sctp_sched_prio_dequeue_done(struct sctp_outq *q,
+					 struct sctp_chunk *ch)
+{
+	struct sctp_stream_priorities *prio;
+	struct sctp_stream_out_ext *soute;
+	__u16 sid;
+
+	/* Last chunk on that msg, move to the next stream on
+	 * this priority.
+	 */
+	sid = sctp_chunk_stream_no(ch);
+	soute = SCTP_SO(&q->asoc->stream, sid)->ext;
+	prio = soute->prio_head;
+
+	sctp_sched_prio_next_stream(prio);
+
+	if (list_empty(&soute->outq))
+		sctp_sched_prio_unsched(soute);
+}
+
+static void sctp_sched_prio_sched_all(struct sctp_stream *stream)
+{
+	struct sctp_association *asoc;
+	struct sctp_stream_out *sout;
+	struct sctp_chunk *ch;
+
+	asoc = container_of(stream, struct sctp_association, stream);
+	list_for_each_entry(ch, &asoc->outqueue.out_chunk_list, list) {
+		__u16 sid;
+
+		sid = sctp_chunk_stream_no(ch);
+		sout = SCTP_SO(stream, sid);
+		if (sout->ext)
+			sctp_sched_prio_sched(stream, sout->ext);
+	}
+}
+
+static void sctp_sched_prio_unsched_all(struct sctp_stream *stream)
+{
+	struct sctp_stream_priorities *p, *tmp;
+	struct sctp_stream_out_ext *soute, *souttmp;
+
+	list_for_each_entry_safe(p, tmp, &stream->prio_list, prio_sched)
+		list_for_each_entry_safe(soute, souttmp, &p->active, prio_list)
+			sctp_sched_prio_unsched(soute);
+}
+
+static const struct sctp_sched_ops sctp_sched_prio = {
+	.set = sctp_sched_prio_set,
+	.get = sctp_sched_prio_get,
+	.init = sctp_sched_prio_init,
+	.init_sid = sctp_sched_prio_init_sid,
+	.free_sid = sctp_sched_prio_free_sid,
+	.enqueue = sctp_sched_prio_enqueue,
+	.dequeue = sctp_sched_prio_dequeue,
+	.dequeue_done = sctp_sched_prio_dequeue_done,
+	.sched_all = sctp_sched_prio_sched_all,
+	.unsched_all = sctp_sched_prio_unsched_all,
+};
+
+void sctp_sched_ops_prio_init(void)
+{
+	sctp_sched_ops_register(SCTP_SS_PRIO, &sctp_sched_prio);
+}

linux-7.2.3/net/sctp/stream_sched_rr.c

@@ -0,0 +1,190 @@
+// SPDX-License-Identifier: GPL-2.0-or-later
+/* SCTP kernel implementation
+ * (C) Copyright Red Hat Inc. 2017
+ *
+ * This file is part of the SCTP kernel implementation
+ *
+ * These functions manipulate sctp stream queue/scheduling.
+ *
+ * Please send any bug reports or fixes you make to the
+ * email addresched(es):
+ *    lksctp developers <linux-sctp@vger.kernel.org>
+ *
+ * Written or modified by:
+ *    Marcelo Ricardo Leitner <marcelo.leitner@gmail.com>
+ */
+
+#include <linux/list.h>
+#include <net/sctp/sctp.h>
+#include <net/sctp/sm.h>
+#include <net/sctp/stream_sched.h>
+
+/* Priority handling
+ * RFC DRAFT ndata section 3.2
+ */
+static void sctp_sched_rr_unsched_all(struct sctp_stream *stream);
+
+static void sctp_sched_rr_next_stream(struct sctp_stream *stream)
+{
+	struct list_head *pos;
+
+	pos = stream->rr_next->rr_list.next;
+	if (pos == &stream->rr_list)
+		pos = pos->next;
+	stream->rr_next = list_entry(pos, struct sctp_stream_out_ext, rr_list);
+}
+
+static void sctp_sched_rr_unsched(struct sctp_stream *stream,
+				  struct sctp_stream_out_ext *soute)
+{
+	if (stream->rr_next == soute)
+		/* Try to move to the next stream */
+		sctp_sched_rr_next_stream(stream);
+
+	list_del_init(&soute->rr_list);
+
+	/* If we have no other stream queued, clear next */
+	if (list_empty(&stream->rr_list))
+		stream->rr_next = NULL;
+}
+
+static void sctp_sched_rr_sched(struct sctp_stream *stream,
+				struct sctp_stream_out_ext *soute)
+{
+	if (!list_empty(&soute->rr_list))
+		/* Already scheduled. */
+		return;
+
+	/* Schedule the stream */
+	list_add_tail(&soute->rr_list, &stream->rr_list);
+
+	if (!stream->rr_next)
+		stream->rr_next = soute;
+}
+
+static int sctp_sched_rr_set(struct sctp_stream *stream, __u16 sid,
+			     __u16 prio, gfp_t gfp)
+{
+	return 0;
+}
+
+static int sctp_sched_rr_get(struct sctp_stream *stream, __u16 sid,
+			     __u16 *value)
+{
+	return 0;
+}
+
+static int sctp_sched_rr_init(struct sctp_stream *stream)
+{
+	INIT_LIST_HEAD(&stream->rr_list);
+	stream->rr_next = NULL;
+
+	return 0;
+}
+
+static int sctp_sched_rr_init_sid(struct sctp_stream *stream, __u16 sid,
+				  gfp_t gfp)
+{
+	INIT_LIST_HEAD(&SCTP_SO(stream, sid)->ext->rr_list);
+
+	return 0;
+}
+
+static void sctp_sched_rr_free_sid(struct sctp_stream *stream, __u16 sid)
+{
+}
+
+static void sctp_sched_rr_enqueue(struct sctp_outq *q,
+				  struct sctp_datamsg *msg)
+{
+	struct sctp_stream *stream;
+	struct sctp_chunk *ch;
+	__u16 sid;
+
+	ch = list_first_entry(&msg->chunks, struct sctp_chunk, frag_list);
+	sid = sctp_chunk_stream_no(ch);
+	stream = &q->asoc->stream;
+	sctp_sched_rr_sched(stream, SCTP_SO(stream, sid)->ext);
+}
+
+static struct sctp_chunk *sctp_sched_rr_dequeue(struct sctp_outq *q)
+{
+	struct sctp_stream *stream = &q->asoc->stream;
+	struct sctp_stream_out_ext *soute;
+	struct sctp_chunk *ch = NULL;
+
+	/* Bail out quickly if queue is empty */
+	if (list_empty(&q->out_chunk_list))
+		goto out;
+
+	/* Find which chunk is next */
+	if (stream->out_curr)
+		soute = stream->out_curr->ext;
+	else
+		soute = stream->rr_next;
+	ch = list_entry(soute->outq.next, struct sctp_chunk, stream_list);
+
+	sctp_sched_dequeue_common(q, ch);
+
+out:
+	return ch;
+}
+
+static void sctp_sched_rr_dequeue_done(struct sctp_outq *q,
+				       struct sctp_chunk *ch)
+{
+	struct sctp_stream_out_ext *soute;
+	__u16 sid;
+
+	/* Last chunk on that msg, move to the next stream */
+	sid = sctp_chunk_stream_no(ch);
+	soute = SCTP_SO(&q->asoc->stream, sid)->ext;
+
+	sctp_sched_rr_next_stream(&q->asoc->stream);
+
+	if (list_empty(&soute->outq))
+		sctp_sched_rr_unsched(&q->asoc->stream, soute);
+}
+
+static void sctp_sched_rr_sched_all(struct sctp_stream *stream)
+{
+	struct sctp_association *asoc;
+	struct sctp_stream_out_ext *soute;
+	struct sctp_chunk *ch;
+
+	asoc = container_of(stream, struct sctp_association, stream);
+	list_for_each_entry(ch, &asoc->outqueue.out_chunk_list, list) {
+		__u16 sid;
+
+		sid = sctp_chunk_stream_no(ch);
+		soute = SCTP_SO(stream, sid)->ext;
+		if (soute)
+			sctp_sched_rr_sched(stream, soute);
+	}
+}
+
+static void sctp_sched_rr_unsched_all(struct sctp_stream *stream)
+{
+	struct sctp_stream_out_ext *soute, *tmp;
+
+	list_for_each_entry_safe(soute, tmp, &stream->rr_list, rr_list)
+		sctp_sched_rr_unsched(stream, soute);
+}
+
+static const struct sctp_sched_ops sctp_sched_rr = {
+	.set = sctp_sched_rr_set,
+	.get = sctp_sched_rr_get,
+	.init = sctp_sched_rr_init,
+	.init_sid = sctp_sched_rr_init_sid,
+	.free_sid = sctp_sched_rr_free_sid,
+	.enqueue = sctp_sched_rr_enqueue,
+	.dequeue = sctp_sched_rr_dequeue,
+	.dequeue_done = sctp_sched_rr_dequeue_done,
+	.sched_all = sctp_sched_rr_sched_all,
+	.unsched_all = sctp_sched_rr_unsched_all,
+};
+
+void sctp_sched_ops_rr_init(void)
+{
+	sctp_sched_ops_register(SCTP_SS_RR, &sctp_sched_rr);
+}

linux-7.2.3/net/sctp/sysctl.c

@@ -0,0 +1,642 @@
+// SPDX-License-Identifier: GPL-2.0-or-later
+/* 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.
+ *
+ * Please send any bug reports or fixes you make to the
+ * email address(es):
+ *    lksctp developers <linux-sctp@vger.kernel.org>
+ *
+ * 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>
+ */
+
+#define pr_fmt(fmt) KBUILD_MODNAME ": " fmt
+
+#include <net/sctp/structs.h>
+#include <net/sctp/sctp.h>
+#include <linux/sysctl.h>
+
+static int timer_max = 86400000; /* ms in one day */
+static int sack_timer_min = 1;
+static int sack_timer_max = 500;
+static int addr_scope_max = SCTP_SCOPE_POLICY_MAX;
+static int rwnd_scale_max = 16;
+static int rto_alpha_min = 0;
+static int rto_beta_min = 0;
+static int rto_alpha_max = 1000;
+static int rto_beta_max = 1000;
+static int pf_expose_max = SCTP_PF_EXPOSE_MAX;
+static int ps_retrans_max = SCTP_PS_RETRANS_MAX;
+static int udp_port_max = 65535;
+
+static unsigned long max_autoclose_min = 0;
+static unsigned long max_autoclose_max =
+	(MAX_SCHEDULE_TIMEOUT / HZ > UINT_MAX)
+	? UINT_MAX : MAX_SCHEDULE_TIMEOUT / HZ;
+
+static int proc_sctp_do_hmac_alg(const struct ctl_table *ctl, int write,
+				 void *buffer, size_t *lenp, loff_t *ppos);
+static int proc_sctp_do_rto_min(const struct ctl_table *ctl, int write,
+				void *buffer, size_t *lenp, loff_t *ppos);
+static int proc_sctp_do_rto_max(const struct ctl_table *ctl, int write, void *buffer,
+				size_t *lenp, loff_t *ppos);
+static int proc_sctp_do_udp_port(const struct ctl_table *ctl, int write, void *buffer,
+				 size_t *lenp, loff_t *ppos);
+static int proc_sctp_do_alpha_beta(const struct ctl_table *ctl, int write,
+				   void *buffer, size_t *lenp, loff_t *ppos);
+static int proc_sctp_do_auth(const struct ctl_table *ctl, int write,
+			     void *buffer, size_t *lenp, loff_t *ppos);
+static int proc_sctp_do_probe_interval(const struct ctl_table *ctl, int write,
+				       void *buffer, size_t *lenp, loff_t *ppos);
+
+static struct ctl_table sctp_table[] = {
+	{
+		.procname	= "sctp_mem",
+		.data		= &sysctl_sctp_mem,
+		.maxlen		= sizeof(sysctl_sctp_mem),
+		.mode		= 0644,
+		.proc_handler	= proc_doulongvec_minmax
+	},
+	{
+		.procname	= "sctp_rmem",
+		.data		= &sysctl_sctp_rmem,
+		.maxlen		= sizeof(sysctl_sctp_rmem),
+		.mode		= 0644,
+		.proc_handler	= proc_dointvec,
+	},
+	{
+		.procname	= "sctp_wmem",
+		.data		= &sysctl_sctp_wmem,
+		.maxlen		= sizeof(sysctl_sctp_wmem),
+		.mode		= 0644,
+		.proc_handler	= proc_dointvec,
+	},
+};
+
+/* The following index defines are used in sctp_sysctl_net_register().
+ * If you add new items to the sctp_net_table, please ensure that
+ * the index values of these defines hold the same meaning indicated by
+ * their macro names when they appear in sctp_net_table.
+ */
+#define SCTP_RTO_MIN_IDX       0
+#define SCTP_RTO_MAX_IDX       1
+#define SCTP_PF_RETRANS_IDX    2
+#define SCTP_PS_RETRANS_IDX    3
+
+static struct ctl_table sctp_net_table[] = {
+	[SCTP_RTO_MIN_IDX] = {
+		.procname	= "rto_min",
+		.data		= &init_net.sctp.rto_min,
+		.maxlen		= sizeof(unsigned int),
+		.mode		= 0644,
+		.proc_handler	= proc_sctp_do_rto_min,
+		.extra1         = SYSCTL_ONE,
+		.extra2         = &init_net.sctp.rto_max
+	},
+	[SCTP_RTO_MAX_IDX] =  {
+		.procname	= "rto_max",
+		.data		= &init_net.sctp.rto_max,
+		.maxlen		= sizeof(unsigned int),
+		.mode		= 0644,
+		.proc_handler	= proc_sctp_do_rto_max,
+		.extra1         = &init_net.sctp.rto_min,
+		.extra2         = &timer_max
+	},
+	[SCTP_PF_RETRANS_IDX] = {
+		.procname	= "pf_retrans",
+		.data		= &init_net.sctp.pf_retrans,
+		.maxlen		= sizeof(int),
+		.mode		= 0644,
+		.proc_handler	= proc_dointvec_minmax,
+		.extra1		= SYSCTL_ZERO,
+		.extra2		= &init_net.sctp.ps_retrans,
+	},
+	[SCTP_PS_RETRANS_IDX] = {
+		.procname	= "ps_retrans",
+		.data		= &init_net.sctp.ps_retrans,
+		.maxlen		= sizeof(int),
+		.mode		= 0644,
+		.proc_handler	= proc_dointvec_minmax,
+		.extra1		= &init_net.sctp.pf_retrans,
+		.extra2		= &ps_retrans_max,
+	},
+	{
+		.procname	= "rto_initial",
+		.data		= &init_net.sctp.rto_initial,
+		.maxlen		= sizeof(unsigned int),
+		.mode		= 0644,
+		.proc_handler	= proc_dointvec_minmax,
+		.extra1         = SYSCTL_ONE,
+		.extra2         = &timer_max
+	},
+	{
+		.procname	= "rto_alpha_exp_divisor",
+		.data		= &init_net.sctp.rto_alpha,
+		.maxlen		= sizeof(int),
+		.mode		= 0644,
+		.proc_handler	= proc_sctp_do_alpha_beta,
+		.extra1		= &rto_alpha_min,
+		.extra2		= &rto_alpha_max,
+	},
+	{
+		.procname	= "rto_beta_exp_divisor",
+		.data		= &init_net.sctp.rto_beta,
+		.maxlen		= sizeof(int),
+		.mode		= 0644,
+		.proc_handler	= proc_sctp_do_alpha_beta,
+		.extra1		= &rto_beta_min,
+		.extra2		= &rto_beta_max,
+	},
+	{
+		.procname	= "max_burst",
+		.data		= &init_net.sctp.max_burst,
+		.maxlen		= sizeof(int),
+		.mode		= 0644,
+		.proc_handler	= proc_dointvec_minmax,
+		.extra1		= SYSCTL_ZERO,
+		.extra2		= SYSCTL_INT_MAX,
+	},
+	{
+		.procname	= "cookie_preserve_enable",
+		.data		= &init_net.sctp.cookie_preserve_enable,
+		.maxlen		= sizeof(int),
+		.mode		= 0644,
+		.proc_handler	= proc_dointvec,
+	},
+	{
+		.procname	= "cookie_hmac_alg",
+		.data		= &init_net.sctp.cookie_auth_enable,
+		.maxlen		= 8,
+		.mode		= 0644,
+		.proc_handler	= proc_sctp_do_hmac_alg,
+	},
+	{
+		.procname	= "valid_cookie_life",
+		.data		= &init_net.sctp.valid_cookie_life,
+		.maxlen		= sizeof(unsigned int),
+		.mode		= 0644,
+		.proc_handler	= proc_dointvec_minmax,
+		.extra1         = SYSCTL_ONE,
+		.extra2         = &timer_max
+	},
+	{
+		.procname	= "sack_timeout",
+		.data		= &init_net.sctp.sack_timeout,
+		.maxlen		= sizeof(int),
+		.mode		= 0644,
+		.proc_handler	= proc_dointvec_minmax,
+		.extra1         = &sack_timer_min,
+		.extra2         = &sack_timer_max,
+	},
+	{
+		.procname	= "hb_interval",
+		.data		= &init_net.sctp.hb_interval,
+		.maxlen		= sizeof(unsigned int),
+		.mode		= 0644,
+		.proc_handler	= proc_dointvec_minmax,
+		.extra1         = SYSCTL_ONE,
+		.extra2         = &timer_max
+	},
+	{
+		.procname	= "association_max_retrans",
+		.data		= &init_net.sctp.max_retrans_association,
+		.maxlen		= sizeof(int),
+		.mode		= 0644,
+		.proc_handler	= proc_dointvec_minmax,
+		.extra1		= SYSCTL_ONE,
+		.extra2		= SYSCTL_INT_MAX,
+	},
+	{
+		.procname	= "path_max_retrans",
+		.data		= &init_net.sctp.max_retrans_path,
+		.maxlen		= sizeof(int),
+		.mode		= 0644,
+		.proc_handler	= proc_dointvec_minmax,
+		.extra1		= SYSCTL_ONE,
+		.extra2		= SYSCTL_INT_MAX,
+	},
+	{
+		.procname	= "max_init_retransmits",
+		.data		= &init_net.sctp.max_retrans_init,
+		.maxlen		= sizeof(int),
+		.mode		= 0644,
+		.proc_handler	= proc_dointvec_minmax,
+		.extra1		= SYSCTL_ONE,
+		.extra2		= SYSCTL_INT_MAX,
+	},
+	{
+		.procname	= "sndbuf_policy",
+		.data		= &init_net.sctp.sndbuf_policy,
+		.maxlen		= sizeof(int),
+		.mode		= 0644,
+		.proc_handler	= proc_dointvec,
+	},
+	{
+		.procname	= "rcvbuf_policy",
+		.data		= &init_net.sctp.rcvbuf_policy,
+		.maxlen		= sizeof(int),
+		.mode		= 0644,
+		.proc_handler	= proc_dointvec,
+	},
+	{
+		.procname	= "default_auto_asconf",
+		.data		= &init_net.sctp.default_auto_asconf,
+		.maxlen		= sizeof(int),
+		.mode		= 0644,
+		.proc_handler	= proc_dointvec,
+	},
+	{
+		.procname	= "addip_enable",
+		.data		= &init_net.sctp.addip_enable,
+		.maxlen		= sizeof(int),
+		.mode		= 0644,
+		.proc_handler	= proc_dointvec,
+	},
+	{
+		.procname	= "addip_noauth_enable",
+		.data		= &init_net.sctp.addip_noauth,
+		.maxlen		= sizeof(int),
+		.mode		= 0644,
+		.proc_handler	= proc_dointvec,
+	},
+	{
+		.procname	= "prsctp_enable",
+		.data		= &init_net.sctp.prsctp_enable,
+		.maxlen		= sizeof(int),
+		.mode		= 0644,
+		.proc_handler	= proc_dointvec,
+	},
+	{
+		.procname	= "reconf_enable",
+		.data		= &init_net.sctp.reconf_enable,
+		.maxlen		= sizeof(int),
+		.mode		= 0644,
+		.proc_handler	= proc_dointvec,
+	},
+	{
+		.procname	= "auth_enable",
+		.data		= &init_net.sctp.auth_enable,
+		.maxlen		= sizeof(int),
+		.mode		= 0644,
+		.proc_handler	= proc_sctp_do_auth,
+	},
+	{
+		.procname	= "intl_enable",
+		.data		= &init_net.sctp.intl_enable,
+		.maxlen		= sizeof(int),
+		.mode		= 0644,
+		.proc_handler	= proc_dointvec,
+	},
+	{
+		.procname	= "ecn_enable",
+		.data		= &init_net.sctp.ecn_enable,
+		.maxlen		= sizeof(int),
+		.mode		= 0644,
+		.proc_handler	= proc_dointvec,
+	},
+	{
+		.procname	= "plpmtud_probe_interval",
+		.data		= &init_net.sctp.probe_interval,
+		.maxlen		= sizeof(int),
+		.mode		= 0644,
+		.proc_handler	= proc_sctp_do_probe_interval,
+	},
+	{
+		.procname	= "udp_port",
+		.data		= &init_net.sctp.udp_port,
+		.maxlen		= sizeof(int),
+		.mode		= 0644,
+		.proc_handler	= proc_sctp_do_udp_port,
+		.extra1		= SYSCTL_ZERO,
+		.extra2		= &udp_port_max,
+	},
+	{
+		.procname	= "encap_port",
+		.data		= &init_net.sctp.encap_port,
+		.maxlen		= sizeof(int),
+		.mode		= 0644,
+		.proc_handler	= proc_dointvec_minmax,
+		.extra1		= SYSCTL_ZERO,
+		.extra2		= &udp_port_max,
+	},
+	{
+		.procname	= "addr_scope_policy",
+		.data		= &init_net.sctp.scope_policy,
+		.maxlen		= sizeof(int),
+		.mode		= 0644,
+		.proc_handler	= proc_dointvec_minmax,
+		.extra1		= SYSCTL_ZERO,
+		.extra2		= &addr_scope_max,
+	},
+	{
+		.procname	= "rwnd_update_shift",
+		.data		= &init_net.sctp.rwnd_upd_shift,
+		.maxlen		= sizeof(int),
+		.mode		= 0644,
+		.proc_handler	= &proc_dointvec_minmax,
+		.extra1		= SYSCTL_ONE,
+		.extra2		= &rwnd_scale_max,
+	},
+	{
+		.procname	= "max_autoclose",
+		.data		= &init_net.sctp.max_autoclose,
+		.maxlen		= sizeof(unsigned long),
+		.mode		= 0644,
+		.proc_handler	= &proc_doulongvec_minmax,
+		.extra1		= &max_autoclose_min,
+		.extra2		= &max_autoclose_max,
+	},
+#ifdef CONFIG_NET_L3_MASTER_DEV
+	{
+		.procname	= "l3mdev_accept",
+		.data		= &init_net.sctp.l3mdev_accept,
+		.maxlen		= sizeof(int),
+		.mode		= 0644,
+		.proc_handler	= proc_dointvec_minmax,
+		.extra1		= SYSCTL_ZERO,
+		.extra2		= SYSCTL_ONE,
+	},
+#endif
+	{
+		.procname	= "pf_enable",
+		.data		= &init_net.sctp.pf_enable,
+		.maxlen		= sizeof(int),
+		.mode		= 0644,
+		.proc_handler	= proc_dointvec,
+	},
+	{
+		.procname	= "pf_expose",
+		.data		= &init_net.sctp.pf_expose,
+		.maxlen		= sizeof(int),
+		.mode		= 0644,
+		.proc_handler	= proc_dointvec_minmax,
+		.extra1		= SYSCTL_ZERO,
+		.extra2		= &pf_expose_max,
+	},
+};
+
+static int proc_sctp_do_hmac_alg(const struct ctl_table *ctl, int write,
+				 void *buffer, size_t *lenp, loff_t *ppos)
+{
+	struct net *net = container_of(ctl->data, struct net,
+				       sctp.cookie_auth_enable);
+	struct ctl_table tbl;
+	char tmp[8] = {0};
+	int ret;
+
+	memset(&tbl, 0, sizeof(struct ctl_table));
+
+	if (write) {
+		tbl.data = tmp;
+		tbl.maxlen = sizeof(tmp) - 1;
+		ret = proc_dostring(&tbl, 1, buffer, lenp, ppos);
+		if (ret)
+			return ret;
+		if (!strcmp(tmp, "sha256")) {
+			net->sctp.cookie_auth_enable = 1;
+			return 0;
+		}
+		if (!strcmp(tmp, "none")) {
+			net->sctp.cookie_auth_enable = 0;
+			return 0;
+		}
+		return -EINVAL;
+	}
+	if (net->sctp.cookie_auth_enable)
+		tbl.data = (char *)"sha256";
+	else
+		tbl.data = (char *)"none";
+	tbl.maxlen = strlen(tbl.data);
+	return proc_dostring(&tbl, 0, buffer, lenp, ppos);
+}
+
+static int proc_sctp_do_rto_min(const struct ctl_table *ctl, int write,
+				void *buffer, size_t *lenp, loff_t *ppos)
+{
+	struct net *net = container_of(ctl->data, struct net, sctp.rto_min);
+	unsigned int min = *(unsigned int *) ctl->extra1;
+	unsigned int max = *(unsigned int *) ctl->extra2;
+	struct ctl_table tbl;
+	int ret, new_value;
+
+	memset(&tbl, 0, sizeof(struct ctl_table));
+	tbl.maxlen = sizeof(unsigned int);
+
+	if (write)
+		tbl.data = &new_value;
+	else
+		tbl.data = &net->sctp.rto_min;
+
+	ret = proc_dointvec(&tbl, write, buffer, lenp, ppos);
+	if (write && ret == 0) {
+		if (new_value > max || new_value < min)
+			return -EINVAL;
+
+		net->sctp.rto_min = new_value;
+	}
+
+	return ret;
+}
+
+static int proc_sctp_do_rto_max(const struct ctl_table *ctl, int write,
+				void *buffer, size_t *lenp, loff_t *ppos)
+{
+	struct net *net = container_of(ctl->data, struct net, sctp.rto_max);
+	unsigned int min = *(unsigned int *) ctl->extra1;
+	unsigned int max = *(unsigned int *) ctl->extra2;
+	struct ctl_table tbl;
+	int ret, new_value;
+
+	memset(&tbl, 0, sizeof(struct ctl_table));
+	tbl.maxlen = sizeof(unsigned int);
+
+	if (write)
+		tbl.data = &new_value;
+	else
+		tbl.data = &net->sctp.rto_max;
+
+	ret = proc_dointvec(&tbl, write, buffer, lenp, ppos);
+	if (write && ret == 0) {
+		if (new_value > max || new_value < min)
+			return -EINVAL;
+
+		net->sctp.rto_max = new_value;
+	}
+
+	return ret;
+}
+
+static int proc_sctp_do_alpha_beta(const struct ctl_table *ctl, int write,
+				   void *buffer, size_t *lenp, loff_t *ppos)
+{
+	if (write)
+		pr_warn_once("Changing rto_alpha or rto_beta may lead to "
+			     "suboptimal rtt/srtt estimations!\n");
+
+	return proc_dointvec_minmax(ctl, write, buffer, lenp, ppos);
+}
+
+static int proc_sctp_do_auth(const struct ctl_table *ctl, int write,
+			     void *buffer, size_t *lenp, loff_t *ppos)
+{
+	struct net *net = container_of(ctl->data, struct net, sctp.auth_enable);
+	struct ctl_table tbl;
+	int new_value, ret;
+
+	memset(&tbl, 0, sizeof(struct ctl_table));
+	tbl.maxlen = sizeof(unsigned int);
+
+	if (write)
+		tbl.data = &new_value;
+	else
+		tbl.data = &net->sctp.auth_enable;
+
+	ret = proc_dointvec(&tbl, write, buffer, lenp, ppos);
+	if (write && ret == 0) {
+		struct sock *sk = net->sctp.ctl_sock;
+
+		net->sctp.auth_enable = new_value;
+		/* Update the value in the control socket */
+		lock_sock(sk);
+		sctp_sk(sk)->ep->auth_enable = new_value;
+		release_sock(sk);
+	}
+
+	return ret;
+}
+
+static DEFINE_MUTEX(sctp_sysctl_mutex);
+
+static int proc_sctp_do_udp_port(const struct ctl_table *ctl, int write,
+				 void *buffer, size_t *lenp, loff_t *ppos)
+{
+	struct net *net = container_of(ctl->data, struct net, sctp.udp_port);
+	unsigned int min = *(unsigned int *)ctl->extra1;
+	unsigned int max = *(unsigned int *)ctl->extra2;
+	struct ctl_table tbl;
+	int ret, new_value;
+
+	memset(&tbl, 0, sizeof(struct ctl_table));
+	tbl.maxlen = sizeof(unsigned int);
+
+	if (write)
+		tbl.data = &new_value;
+	else
+		tbl.data = &net->sctp.udp_port;
+
+	ret = proc_dointvec(&tbl, write, buffer, lenp, ppos);
+	if (write && ret == 0) {
+		struct sock *sk = net->sctp.ctl_sock;
+
+		if (new_value > max || new_value < min)
+			return -EINVAL;
+
+		mutex_lock(&sctp_sysctl_mutex);
+		net->sctp.udp_port = new_value;
+		sctp_udp_sock_stop(net);
+		if (new_value) {
+			ret = sctp_udp_sock_start(net);
+			if (ret)
+				net->sctp.udp_port = 0;
+		}
+
+		/* Update the value in the control socket */
+		lock_sock(sk);
+		sctp_sk(sk)->udp_port = htons(net->sctp.udp_port);
+		release_sock(sk);
+		mutex_unlock(&sctp_sysctl_mutex);
+	}
+
+	return ret;
+}
+
+static int proc_sctp_do_probe_interval(const struct ctl_table *ctl, int write,
+				       void *buffer, size_t *lenp, loff_t *ppos)
+{
+	struct net *net = container_of(ctl->data, struct net,
+				       sctp.probe_interval);
+	struct ctl_table tbl;
+	int ret, new_value;
+
+	memset(&tbl, 0, sizeof(struct ctl_table));
+	tbl.maxlen = sizeof(unsigned int);
+
+	if (write)
+		tbl.data = &new_value;
+	else
+		tbl.data = &net->sctp.probe_interval;
+
+	ret = proc_dointvec(&tbl, write, buffer, lenp, ppos);
+	if (write && ret == 0) {
+		if (new_value && new_value < SCTP_PROBE_TIMER_MIN)
+			return -EINVAL;
+
+		net->sctp.probe_interval = new_value;
+	}
+
+	return ret;
+}
+
+int sctp_sysctl_net_register(struct net *net)
+{
+	size_t table_size = ARRAY_SIZE(sctp_net_table);
+	struct ctl_table *table;
+	int i;
+
+	table = kmemdup(sctp_net_table, sizeof(sctp_net_table), GFP_KERNEL);
+	if (!table)
+		return -ENOMEM;
+
+	for (i = 0; i < table_size; i++)
+		table[i].data += (char *)(&net->sctp) - (char *)&init_net.sctp;
+
+	table[SCTP_RTO_MIN_IDX].extra2 = &net->sctp.rto_max;
+	table[SCTP_RTO_MAX_IDX].extra1 = &net->sctp.rto_min;
+	table[SCTP_PF_RETRANS_IDX].extra2 = &net->sctp.ps_retrans;
+	table[SCTP_PS_RETRANS_IDX].extra1 = &net->sctp.pf_retrans;
+
+	net->sctp.sysctl_header = register_net_sysctl_sz(net, "net/sctp",
+							 table, table_size);
+	if (net->sctp.sysctl_header == NULL) {
+		kfree(table);
+		return -ENOMEM;
+	}
+	return 0;
+}
+
+void sctp_sysctl_net_unregister(struct net *net)
+{
+	struct ctl_table_header *header = net->sctp.sysctl_header;
+	const struct ctl_table *table;
+
+	if (!header)
+		return;
+
+	table = header->ctl_table_arg;
+	unregister_net_sysctl_table(header);
+	kfree(table);
+	net->sctp.sysctl_header = NULL;
+}
+
+static struct ctl_table_header *sctp_sysctl_header;
+
+/* Sysctl registration.  */
+void sctp_sysctl_register(void)
+{
+	sctp_sysctl_header = register_net_sysctl(&init_net, "net/sctp", sctp_table);
+}
+
+/* Sysctl deregistration.  */
+void sctp_sysctl_unregister(void)
+{
+	unregister_net_sysctl_table(sctp_sysctl_header);
+}

linux-7.2.3/net/sctp/transport.c

@@ -0,0 +1,852 @@
+// SPDX-License-Identifier: GPL-2.0-or-later
+/* 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 transport representing
+ * a remote transport address.  For local transport addresses, we just use
+ * union sctp_addr.
+ *
+ * Please send any bug reports or fixes you make to the
+ * email address(es):
+ *    lksctp developers <linux-sctp@vger.kernel.org>
+ *
+ * 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>
+ */
+
+#define pr_fmt(fmt) KBUILD_MODNAME ": " fmt
+
+#include <linux/slab.h>
+#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 void sctp_transport_init(struct net *net,
+				struct sctp_transport *peer,
+				const union sctp_addr *addr,
+				gfp_t gfp)
+{
+	/* Copy in the address.  */
+	peer->af_specific = sctp_get_af_specific(addr->sa.sa_family);
+	memcpy(&peer->ipaddr, addr, peer->af_specific->sockaddr_len);
+	memset(&peer->saddr, 0, sizeof(union sctp_addr));
+
+	peer->sack_generation = 0;
+
+	/* 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(net->sctp.rto_initial);
+
+	peer->last_time_heard = 0;
+	peer->last_time_ecne_reduced = jiffies;
+
+	peer->param_flags = SPP_HB_DISABLE |
+			    SPP_PMTUD_ENABLE |
+			    SPP_SACKDELAY_ENABLE;
+
+	/* Initialize the default path max_retrans.  */
+	peer->pathmaxrxt  = net->sctp.max_retrans_path;
+	peer->pf_retrans  = net->sctp.pf_retrans;
+
+	INIT_LIST_HEAD(&peer->transmitted);
+	INIT_LIST_HEAD(&peer->send_ready);
+	INIT_LIST_HEAD(&peer->transports);
+
+	timer_setup(&peer->T3_rtx_timer, sctp_generate_t3_rtx_event, 0);
+	timer_setup(&peer->hb_timer, sctp_generate_heartbeat_event, 0);
+	timer_setup(&peer->reconf_timer, sctp_generate_reconf_event, 0);
+	timer_setup(&peer->probe_timer, sctp_generate_probe_event, 0);
+	timer_setup(&peer->proto_unreach_timer,
+		    sctp_generate_proto_unreach_event, 0);
+
+	/* Initialize the 64-bit random nonce sent with heartbeat. */
+	get_random_bytes(&peer->hb_nonce, sizeof(peer->hb_nonce));
+
+	refcount_set(&peer->refcnt, 1);
+}
+
+/* Allocate and initialize a new transport.  */
+struct sctp_transport *sctp_transport_new(struct net *net,
+					  const union sctp_addr *addr,
+					  gfp_t gfp)
+{
+	struct sctp_transport *transport;
+
+	transport = kzalloc_obj(*transport, gfp);
+	if (!transport)
+		return NULL;
+
+	sctp_transport_init(net, transport, addr, gfp);
+
+	SCTP_DBG_OBJCNT_INC(transport);
+
+	return transport;
+}
+
+/* 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 (timer_delete(&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 transport is going away.
+	 */
+	if (timer_delete(&transport->T3_rtx_timer))
+		sctp_transport_put(transport);
+
+	if (timer_delete(&transport->reconf_timer))
+		sctp_transport_put(transport);
+
+	if (timer_delete(&transport->probe_timer))
+		sctp_transport_put(transport);
+
+	/* Delete the ICMP proto unreachable timer if it's active. */
+	if (timer_delete(&transport->proto_unreach_timer))
+		sctp_transport_put(transport);
+
+	sctp_transport_put(transport);
+}
+
+static void sctp_transport_destroy_rcu(struct rcu_head *head)
+{
+	struct sctp_transport *transport;
+
+	transport = container_of(head, struct sctp_transport, rcu);
+
+	dst_release(transport->dst);
+	kfree(transport);
+	SCTP_DBG_OBJCNT_DEC(transport);
+}
+
+/* Destroy the transport data structure.
+ * Assumes there are no more users of this structure.
+ */
+static void sctp_transport_destroy(struct sctp_transport *transport)
+{
+	if (unlikely(refcount_read(&transport->refcnt))) {
+		WARN(1, "Attempt to destroy undead transport %p!\n", transport);
+		return;
+	}
+
+	sctp_packet_free(&transport->packet);
+
+	if (transport->asoc)
+		sctp_association_put(transport->asoc);
+
+	call_rcu(&transport->rcu, sctp_transport_destroy_rcu);
+}
+
+/* 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_t3_rtx(struct sctp_transport *transport)
+{
+	/* RFC 2960 6.3.2 Retransmission Timer Rules
+	 *
+	 * R1) Every time a DATA chunk is sent to any address(including a
+	 * retransmission), if the T3-rtx timer of that address is not running
+	 * start it running so that it will expire after the RTO of that
+	 * address.
+	 */
+
+	if (!timer_pending(&transport->T3_rtx_timer))
+		if (!mod_timer(&transport->T3_rtx_timer,
+			       jiffies + transport->rto))
+			sctp_transport_hold(transport);
+}
+
+void sctp_transport_reset_hb_timer(struct sctp_transport *transport)
+{
+	unsigned long expires;
+
+	/* When a data chunk is sent, reset the heartbeat interval.  */
+	expires = jiffies + sctp_transport_timeout(transport);
+	if (!mod_timer(&transport->hb_timer,
+		       expires + get_random_u32_below(transport->rto)))
+		sctp_transport_hold(transport);
+}
+
+void sctp_transport_reset_reconf_timer(struct sctp_transport *transport)
+{
+	if (!timer_pending(&transport->reconf_timer))
+		if (!mod_timer(&transport->reconf_timer,
+			       jiffies + transport->rto))
+			sctp_transport_hold(transport);
+}
+
+void sctp_transport_reset_probe_timer(struct sctp_transport *transport)
+{
+	if (!mod_timer(&transport->probe_timer,
+		       jiffies + transport->probe_interval))
+		sctp_transport_hold(transport);
+}
+
+void sctp_transport_reset_raise_timer(struct sctp_transport *transport)
+{
+	if (!mod_timer(&transport->probe_timer,
+		       jiffies + transport->probe_interval * 30))
+		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 sock *sk)
+{
+	/* If we don't have a fresh route, look one up */
+	if (!transport->dst || READ_ONCE(transport->dst->obsolete)) {
+		sctp_transport_dst_release(transport);
+		transport->af_specific->get_dst(transport, &transport->saddr,
+						&transport->fl, sk);
+	}
+
+	if (transport->param_flags & SPP_PMTUD_DISABLE) {
+		struct sctp_association *asoc = transport->asoc;
+
+		if (!transport->pathmtu && asoc && asoc->pathmtu)
+			transport->pathmtu = asoc->pathmtu;
+		if (transport->pathmtu)
+			return;
+	}
+
+	if (transport->dst)
+		transport->pathmtu = sctp_dst_mtu(transport->dst);
+	else
+		transport->pathmtu = SCTP_DEFAULT_MAXSEGMENT;
+
+	sctp_transport_pl_update(transport);
+}
+
+void sctp_transport_pl_send(struct sctp_transport *t)
+{
+	if (t->pl.probe_count < SCTP_MAX_PROBES)
+		goto out;
+
+	t->pl.probe_count = 0;
+	if (t->pl.state == SCTP_PL_BASE) {
+		if (t->pl.probe_size == SCTP_BASE_PLPMTU) { /* BASE_PLPMTU Confirmation Failed */
+			t->pl.state = SCTP_PL_ERROR; /* Base -> Error */
+
+			t->pl.pmtu = SCTP_BASE_PLPMTU;
+			t->pathmtu = t->pl.pmtu + sctp_transport_pl_hlen(t);
+			sctp_assoc_sync_pmtu(t->asoc);
+		}
+	} else if (t->pl.state == SCTP_PL_SEARCH) {
+		if (t->pl.pmtu == t->pl.probe_size) { /* Black Hole Detected */
+			t->pl.state = SCTP_PL_BASE;  /* Search -> Base */
+			t->pl.probe_size = SCTP_BASE_PLPMTU;
+			t->pl.probe_high = 0;
+
+			t->pl.pmtu = SCTP_BASE_PLPMTU;
+			t->pathmtu = t->pl.pmtu + sctp_transport_pl_hlen(t);
+			sctp_assoc_sync_pmtu(t->asoc);
+		} else { /* Normal probe failure. */
+			t->pl.probe_high = t->pl.probe_size;
+			t->pl.probe_size = t->pl.pmtu;
+		}
+	} else if (t->pl.state == SCTP_PL_COMPLETE) {
+		if (t->pl.pmtu == t->pl.probe_size) { /* Black Hole Detected */
+			t->pl.state = SCTP_PL_BASE;  /* Search Complete -> Base */
+			t->pl.probe_size = SCTP_BASE_PLPMTU;
+
+			t->pl.pmtu = SCTP_BASE_PLPMTU;
+			t->pathmtu = t->pl.pmtu + sctp_transport_pl_hlen(t);
+			sctp_assoc_sync_pmtu(t->asoc);
+		}
+	}
+
+out:
+	pr_debug("%s: PLPMTUD: transport: %p, state: %d, pmtu: %d, size: %d, high: %d\n",
+		 __func__, t, t->pl.state, t->pl.pmtu, t->pl.probe_size, t->pl.probe_high);
+	t->pl.probe_count++;
+}
+
+bool sctp_transport_pl_recv(struct sctp_transport *t)
+{
+	pr_debug("%s: PLPMTUD: transport: %p, state: %d, pmtu: %d, size: %d, high: %d\n",
+		 __func__, t, t->pl.state, t->pl.pmtu, t->pl.probe_size, t->pl.probe_high);
+
+	t->pl.pmtu = t->pl.probe_size;
+	t->pl.probe_count = 0;
+	if (t->pl.state == SCTP_PL_BASE) {
+		t->pl.state = SCTP_PL_SEARCH; /* Base -> Search */
+		t->pl.probe_size += SCTP_PL_BIG_STEP;
+	} else if (t->pl.state == SCTP_PL_ERROR) {
+		t->pl.state = SCTP_PL_SEARCH; /* Error -> Search */
+
+		t->pl.pmtu = t->pl.probe_size;
+		t->pathmtu = t->pl.pmtu + sctp_transport_pl_hlen(t);
+		sctp_assoc_sync_pmtu(t->asoc);
+		t->pl.probe_size += SCTP_PL_BIG_STEP;
+	} else if (t->pl.state == SCTP_PL_SEARCH) {
+		if (!t->pl.probe_high) {
+			if (t->pl.probe_size < SCTP_MAX_PLPMTU) {
+				t->pl.probe_size = min(t->pl.probe_size + SCTP_PL_BIG_STEP,
+						       SCTP_MAX_PLPMTU);
+				return false;
+			}
+			t->pl.probe_high = SCTP_MAX_PLPMTU;
+		}
+		t->pl.probe_size += SCTP_PL_MIN_STEP;
+		if (t->pl.probe_size >= t->pl.probe_high) {
+			t->pl.probe_high = 0;
+			t->pl.state = SCTP_PL_COMPLETE; /* Search -> Search Complete */
+
+			t->pl.probe_size = t->pl.pmtu;
+			t->pathmtu = t->pl.pmtu + sctp_transport_pl_hlen(t);
+			sctp_assoc_sync_pmtu(t->asoc);
+			sctp_transport_reset_raise_timer(t);
+		}
+	} else if (t->pl.state == SCTP_PL_COMPLETE) {
+		/* Raise probe_size again after 30 * interval in Search Complete */
+		t->pl.state = SCTP_PL_SEARCH; /* Search Complete -> Search */
+		t->pl.probe_size = min(t->pl.probe_size + SCTP_PL_MIN_STEP, SCTP_MAX_PLPMTU);
+	}
+
+	return t->pl.state == SCTP_PL_COMPLETE;
+}
+
+static bool sctp_transport_pl_toobig(struct sctp_transport *t, u32 pmtu)
+{
+	pr_debug("%s: PLPMTUD: transport: %p, state: %d, pmtu: %d, size: %d, ptb: %d\n",
+		 __func__, t, t->pl.state, t->pl.pmtu, t->pl.probe_size, pmtu);
+
+	if (pmtu < SCTP_MIN_PLPMTU || pmtu >= t->pl.probe_size)
+		return false;
+
+	if (t->pl.state == SCTP_PL_BASE) {
+		if (pmtu >= SCTP_MIN_PLPMTU && pmtu < SCTP_BASE_PLPMTU) {
+			t->pl.state = SCTP_PL_ERROR; /* Base -> Error */
+
+			t->pl.pmtu = SCTP_BASE_PLPMTU;
+			t->pathmtu = t->pl.pmtu + sctp_transport_pl_hlen(t);
+			return true;
+		}
+	} else if (t->pl.state == SCTP_PL_SEARCH) {
+		if (pmtu >= SCTP_BASE_PLPMTU && pmtu < t->pl.pmtu) {
+			t->pl.state = SCTP_PL_BASE;  /* Search -> Base */
+			t->pl.probe_size = SCTP_BASE_PLPMTU;
+			t->pl.probe_count = 0;
+
+			t->pl.probe_high = 0;
+			t->pl.pmtu = SCTP_BASE_PLPMTU;
+			t->pathmtu = t->pl.pmtu + sctp_transport_pl_hlen(t);
+			return true;
+		} else if (pmtu > t->pl.pmtu && pmtu < t->pl.probe_size) {
+			t->pl.probe_size = pmtu;
+			t->pl.probe_count = 0;
+		}
+	} else if (t->pl.state == SCTP_PL_COMPLETE) {
+		if (pmtu >= SCTP_BASE_PLPMTU && pmtu < t->pl.pmtu) {
+			t->pl.state = SCTP_PL_BASE;  /* Complete -> Base */
+			t->pl.probe_size = SCTP_BASE_PLPMTU;
+			t->pl.probe_count = 0;
+
+			t->pl.probe_high = 0;
+			t->pl.pmtu = SCTP_BASE_PLPMTU;
+			t->pathmtu = t->pl.pmtu + sctp_transport_pl_hlen(t);
+			sctp_transport_reset_probe_timer(t);
+			return true;
+		}
+	}
+
+	return false;
+}
+
+bool sctp_transport_update_pmtu(struct sctp_transport *t, u32 pmtu)
+{
+	struct sock *sk = t->asoc->base.sk;
+	struct dst_entry *dst;
+	bool change = true;
+
+	if (unlikely(pmtu < SCTP_DEFAULT_MINSEGMENT)) {
+		pr_warn_ratelimited("%s: Reported pmtu %d too low, using default minimum of %d\n",
+				    __func__, pmtu, SCTP_DEFAULT_MINSEGMENT);
+		/* Use default minimum segment instead */
+		pmtu = SCTP_DEFAULT_MINSEGMENT;
+	}
+	pmtu = SCTP_TRUNC4(pmtu);
+
+	if (sctp_transport_pl_enabled(t))
+		return sctp_transport_pl_toobig(t, pmtu - sctp_transport_pl_hlen(t));
+
+	dst = sctp_transport_dst_check(t);
+	if (dst) {
+		struct sctp_pf *pf = sctp_get_pf_specific(dst->ops->family);
+		union sctp_addr addr;
+
+		pf->af->from_sk(&addr, sk);
+		pf->to_sk_daddr(&t->ipaddr, sk);
+		dst->ops->update_pmtu(dst, sk, NULL, pmtu, true);
+		pf->to_sk_daddr(&addr, sk);
+
+		dst = sctp_transport_dst_check(t);
+	}
+
+	if (!dst) {
+		t->af_specific->get_dst(t, &t->saddr, &t->fl, sk);
+		dst = t->dst;
+	}
+
+	if (dst) {
+		/* Re-fetch, as under layers may have a higher minimum size */
+		pmtu = sctp_dst_mtu(dst);
+		change = t->pathmtu != pmtu;
+	}
+	t->pathmtu = pmtu;
+
+	return change;
+}
+
+/* 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;
+
+	sctp_transport_dst_release(transport);
+	af->get_dst(transport, saddr, &transport->fl, sctp_opt2sk(opt));
+
+	if (saddr)
+		memcpy(&transport->saddr, saddr, sizeof(union sctp_addr));
+	else
+		af->get_saddr(opt, transport, &transport->fl);
+
+	sctp_transport_pmtu(transport, sctp_opt2sk(opt));
+
+	/* Initialize sk->sk_rcv_saddr, if the transport is the
+	 * association's active path for getsockname().
+	 */
+	if (transport->dst && asoc &&
+	    (!asoc->peer.primary_path || transport == asoc->peer.active_path))
+		opt->pf->to_sk_saddr(&transport->saddr, asoc->base.sk);
+}
+
+/* Hold a reference to a transport.  */
+int sctp_transport_hold(struct sctp_transport *transport)
+{
+	return refcount_inc_not_zero(&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 (refcount_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)
+{
+	if (unlikely(!tp->rto_pending))
+		/* We should not be doing any RTO updates unless rto_pending is set.  */
+		pr_debug("%s: rto_pending not set on transport %p!\n", __func__, tp);
+
+	if (tp->rttvar || tp->srtt) {
+		struct net *net = tp->asoc->base.net;
+		unsigned int rto_beta, rto_alpha;
+		/* 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.
+		 */
+		rto_beta = READ_ONCE(net->sctp.rto_beta);
+		if (rto_beta < 32)
+			tp->rttvar = tp->rttvar - (tp->rttvar >> rto_beta)
+				+ (((__u32)abs((__s64)tp->srtt - (__s64)rtt)) >> rto_beta);
+		rto_alpha = READ_ONCE(net->sctp.rto_alpha);
+		if (rto_alpha < 32)
+			tp->srtt = tp->srtt - (tp->srtt >> rto_alpha)
+				+ (rtt >> 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;
+
+	sctp_max_rto(tp->asoc, tp);
+	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;
+
+	pr_debug("%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)
+{
+	struct sctp_association *asoc = transport->asoc;
+	__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 (asoc->fast_recovery &&
+	    TSN_lte(asoc->fast_recovery_exit, sack_ctsn))
+		asoc->fast_recovery = 0;
+
+	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 (asoc->fast_recovery)
+			return;
+
+		/* The appropriate cwnd increase algorithm is performed
+		 * if, and only if the congestion window is being fully
+		 * utilized.  Note that RFC4960 Errata 3.22 removed the
+		 * other condition on ctsn moving.
+		 */
+		if (flight_size < cwnd)
+			return;
+
+		if (bytes_acked > pmtu)
+			cwnd += pmtu;
+		else
+			cwnd += bytes_acked;
+
+		pr_debug("%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, 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. (updated by RFC4960 Errata 3.22)
+		 *
+		 * When partial_bytes_acked is greater than cwnd and
+		 * before the arrival of the SACK the sender had less
+		 * bytes of data outstanding than cwnd (i.e., before
+		 * arrival of the SACK, flightsize was less than cwnd),
+		 * reset partial_bytes_acked to cwnd. (RFC 4960 Errata
+		 * 3.26)
+		 *
+		 * 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), partial_bytes_acked is reset
+		 * to (partial_bytes_acked - cwnd). Next, cwnd is
+		 * increased by MTU. (RFC 4960 Errata 3.12)
+		 */
+		pba += bytes_acked;
+		if (pba > cwnd && flight_size < cwnd)
+			pba = cwnd;
+		if (pba >= cwnd && flight_size >= cwnd) {
+			pba = pba - cwnd;
+			cwnd += pmtu;
+		}
+
+		pr_debug("%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,
+			       enum sctp_lower_cwnd reason)
+{
+	struct sctp_association *asoc = transport->asoc;
+
+	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*asoc->pathmtu);
+		transport->cwnd = asoc->pathmtu;
+
+		/* T3-rtx also clears fast recovery */
+		asoc->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 (asoc->fast_recovery)
+			return;
+
+		/* Mark Fast recovery */
+		asoc->fast_recovery = 1;
+		asoc->fast_recovery_exit = asoc->next_tsn - 1;
+
+		transport->ssthresh = max(transport->cwnd/2,
+					  4*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*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.
+		 */
+		transport->cwnd = max(transport->cwnd/2,
+					 4*asoc->pathmtu);
+		/* RFC 4960 Errata 3.27.2: also adjust sshthresh */
+		transport->ssthresh = transport->cwnd;
+		break;
+	}
+
+	transport->partial_bytes_acked = 0;
+
+	pr_debug("%s: transport:%p, reason:%d, cwnd:%d, ssthresh:%d\n",
+		 __func__, transport, reason, transport->cwnd,
+		 transport->ssthresh);
+}
+
+/* Apply Max.Burst limit to the congestion window:
+ * 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
+ */
+
+void sctp_transport_burst_limited(struct sctp_transport *t)
+{
+	struct sctp_association *asoc = t->asoc;
+	u32 old_cwnd = t->cwnd;
+	u32 max_burst_bytes;
+
+	if (t->burst_limited || asoc->max_burst == 0)
+		return;
+
+	max_burst_bytes = t->flight_size + (asoc->max_burst * asoc->pathmtu);
+	if (max_burst_bytes < old_cwnd) {
+		t->cwnd = max_burst_bytes;
+		t->burst_limited = old_cwnd;
+	}
+}
+
+/* Restore the old cwnd congestion window, after the burst had it's
+ * desired effect.
+ */
+void sctp_transport_burst_reset(struct sctp_transport *t)
+{
+	if (t->burst_limited) {
+		t->cwnd = t->burst_limited;
+		t->burst_limited = 0;
+	}
+}
+
+/* What is the next timeout value for this transport? */
+unsigned long sctp_transport_timeout(struct sctp_transport *trans)
+{
+	/* RTO + timer slack +/- 50% of RTO */
+	unsigned long timeout = trans->rto >> 1;
+
+	if (trans->state != SCTP_UNCONFIRMED &&
+	    trans->state != SCTP_PF)
+		timeout += trans->hbinterval;
+
+	return max_t(unsigned long, timeout, HZ / 5);
+}
+
+/* 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->burst_limited = 0;
+	t->ssthresh = asoc->peer.i.a_rwnd;
+	t->rto = asoc->rto_initial;
+	sctp_max_rto(asoc, t);
+	t->rtt = 0;
+	t->srtt = 0;
+	t->rttvar = 0;
+
+	/* Reset these additional variables 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;
+
+	/* 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;
+}
+
+/* Schedule retransmission on the given transport */
+void sctp_transport_immediate_rtx(struct sctp_transport *t)
+{
+	/* Stop pending T3_rtx_timer */
+	if (timer_delete(&t->T3_rtx_timer))
+		sctp_transport_put(t);
+
+	sctp_retransmit(&t->asoc->outqueue, t, SCTP_RTXR_T3_RTX);
+	if (!timer_pending(&t->T3_rtx_timer)) {
+		if (!mod_timer(&t->T3_rtx_timer, jiffies + t->rto))
+			sctp_transport_hold(t);
+	}
+}
+
+/* Drop dst */
+void sctp_transport_dst_release(struct sctp_transport *t)
+{
+	dst_release(t->dst);
+	t->dst = NULL;
+	t->dst_pending_confirm = 0;
+}
+
+/* Schedule neighbour confirm */
+void sctp_transport_dst_confirm(struct sctp_transport *t)
+{
+	t->dst_pending_confirm = 1;
+}

linux-7.2.3/net/sctp/tsnmap.c

@@ -0,0 +1,364 @@
+// SPDX-License-Identifier: GPL-2.0-or-later
+/* 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.
+ *
+ * Please send any bug reports or fixes you make to the
+ * email address(es):
+ *    lksctp developers <linux-sctp@vger.kernel.org>
+ *
+ * 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>
+ */
+
+#include <linux/slab.h>
+#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 size);
+
+/* 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
+	 * overflow 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,
+		     struct sctp_transport *trans)
+{
+	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 + 1))
+		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++;
+		if (trans)
+			trans->sack_generation =
+				trans->asoc->peer.sack_generation;
+		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.  */
+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.
+ */
+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;
+
+	pending_data = max_tsn - cum_tsn;
+	gap = max_tsn - base_tsn;
+
+	if (gap == 0 || gap >= map->len)
+		goto out;
+
+	pending_data -= bitmap_weight(map->tsn_map, gap + 1);
+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 = 0, end = 0;
+		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 size)
+{
+	unsigned long *new;
+	unsigned long inc;
+	u16  len;
+
+	if (size > SCTP_TSN_MAP_SIZE)
+		return 0;
+
+	inc = ALIGN((size - 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->cumulative_tsn_ack_point);
+	kfree(map->tsn_map);
+	map->tsn_map = new;
+	map->len = len;
+
+	return 1;
+}