socket.c

在linux环境下的流控制传输协议（sctp）的源代码

 * op        Operation to perform (add or remove, see the flags of
 *           sctp_bindx)
 *
 * Returns 0 if ok, <0 errno code on error.
 */
SCTP_STATIC int sctp_setsockopt_bindx(struct sock* sk,
				      struct sockaddr __user *addrs,
				      int addrs_size, int op)
{
	struct sockaddr *kaddrs;
	int err;
	int addrcnt = 0;
	int walk_size = 0;
	struct sockaddr *sa_addr;
	void *addr_buf;
	struct sctp_af *af;

	SCTP_DEBUG_PRINTK("sctp_setsocktopt_bindx: sk %p addrs %p"
			  " addrs_size %d opt %d\n", sk, addrs, addrs_size, op);

	if (unlikely(addrs_size <= 0))
		return -EINVAL;

	/* Check the user passed a healthy pointer.  */
	if (unlikely(!access_ok(VERIFY_READ, addrs, addrs_size)))
		return -EFAULT;

	/* Alloc space for the address array in kernel memory.  */
	kaddrs = kmalloc(addrs_size, GFP_KERNEL);
	if (unlikely(!kaddrs))
		return -ENOMEM;

	if (__copy_from_user(kaddrs, addrs, addrs_size)) {
		kfree(kaddrs);
		return -EFAULT;
	}

	/* Walk through the addrs buffer and count the number of addresses. */
	addr_buf = kaddrs;
	while (walk_size < addrs_size) {
		sa_addr = (struct sockaddr *)addr_buf;
		af = sctp_get_af_specific(sa_addr->sa_family);

		/* If the address family is not supported or if this address
		 * causes the address buffer to overflow return EINVAL.
		 */
		if (!af || (walk_size + af->sockaddr_len) > addrs_size) {
			kfree(kaddrs);
			return -EINVAL;
		}
		addrcnt++;
		addr_buf += af->sockaddr_len;
		walk_size += af->sockaddr_len;
	}

	/* Do the work. */
	switch (op) {
	case SCTP_BINDX_ADD_ADDR:
		err = sctp_bindx_add(sk, kaddrs, addrcnt);
		if (err)
			goto out;
		err = sctp_send_asconf_add_ip(sk, kaddrs, addrcnt);
		break;

	case SCTP_BINDX_REM_ADDR:
		err = sctp_bindx_rem(sk, kaddrs, addrcnt);
		if (err)
			goto out;
		err = sctp_send_asconf_del_ip(sk, kaddrs, addrcnt);
		break;

	default:
		err = -EINVAL;
		break;
	}

out:
	kfree(kaddrs);

	return err;
}

/* __sctp_connect(struct sock* sk, struct sockaddr *kaddrs, int addrs_size)
 *
 * Common routine for handling connect() and sctp_connectx().
 * Connect will come in with just a single address.
 */
static int __sctp_connect(struct sock* sk,
			  struct sockaddr *kaddrs,
			  int addrs_size)
{
	struct sctp_sock *sp;
	struct sctp_endpoint *ep;
	struct sctp_association *asoc = NULL;
	struct sctp_association *asoc2;
	struct sctp_transport *transport;
	union sctp_addr to;
	struct sctp_af *af;
	sctp_scope_t scope;
	long timeo;
	int err = 0;
	int addrcnt = 0;
	int walk_size = 0;
	union sctp_addr *sa_addr = NULL;
	void *addr_buf;
	unsigned short port;
	unsigned int f_flags = 0;

	sp = sctp_sk(sk);
	ep = sp->ep;

	/* connect() cannot be done on a socket that is already in ESTABLISHED
	 * state - UDP-style peeled off socket or a TCP-style socket that
	 * is already connected.
	 * It cannot be done even on a TCP-style listening socket.
	 */
	if (sctp_sstate(sk, ESTABLISHED) ||
	    (sctp_style(sk, TCP) && sctp_sstate(sk, LISTENING))) {
		err = -EISCONN;
		goto out_free;
	}

	/* Walk through the addrs buffer and count the number of addresses. */
	addr_buf = kaddrs;
	while (walk_size < addrs_size) {
		sa_addr = (union sctp_addr *)addr_buf;
		af = sctp_get_af_specific(sa_addr->sa.sa_family);
		port = ntohs(sa_addr->v4.sin_port);

		/* If the address family is not supported or if this address
		 * causes the address buffer to overflow return EINVAL.
		 */
		if (!af || (walk_size + af->sockaddr_len) > addrs_size) {
			err = -EINVAL;
			goto out_free;
		}

		/* Save current address so we can work with it */
		memcpy(&to, sa_addr, af->sockaddr_len);

		err = sctp_verify_addr(sk, &to, af->sockaddr_len);
		if (err)
			goto out_free;

		/* Make sure the destination port is correctly set
		 * in all addresses.
		 */
		if (asoc && asoc->peer.port && asoc->peer.port != port)
			goto out_free;


		/* Check if there already is a matching association on the
		 * endpoint (other than the one created here).
		 */
		asoc2 = sctp_endpoint_lookup_assoc(ep, &to, &transport);
		if (asoc2 && asoc2 != asoc) {
			if (asoc2->state >= SCTP_STATE_ESTABLISHED)
				err = -EISCONN;
			else
				err = -EALREADY;
			goto out_free;
		}

		/* If we could not find a matching association on the endpoint,
		 * make sure that there is no peeled-off association matching
		 * the peer address even on another socket.
		 */
		if (sctp_endpoint_is_peeled_off(ep, &to)) {
			err = -EADDRNOTAVAIL;
			goto out_free;
		}

		if (!asoc) {
			/* If a bind() or sctp_bindx() is not called prior to
			 * an sctp_connectx() call, the system picks an
			 * ephemeral port and will choose an address set
			 * equivalent to binding with a wildcard address.
			 */
			if (!ep->base.bind_addr.port) {
				if (sctp_autobind(sk)) {
					err = -EAGAIN;
					goto out_free;
				}
			} else {
				/*
				 * If an unprivileged user inherits a 1-many
				 * style socket with open associations on a
				 * privileged port, it MAY be permitted to
				 * accept new associations, but it SHOULD NOT
				 * be permitted to open new associations.
				 */
				if (ep->base.bind_addr.port < PROT_SOCK &&
				    !capable(CAP_NET_BIND_SERVICE)) {
					err = -EACCES;
					goto out_free;
				}
			}

			scope = sctp_scope(&to);
			asoc = sctp_association_new(ep, sk, scope, GFP_KERNEL);
			if (!asoc) {
				err = -ENOMEM;
				goto out_free;
			}
		}

		/* Prime the peer's transport structures.  */
		transport = sctp_assoc_add_peer(asoc, &to, GFP_KERNEL,
						SCTP_UNKNOWN);
		if (!transport) {
			err = -ENOMEM;
			goto out_free;
		}

		addrcnt++;
		addr_buf += af->sockaddr_len;
		walk_size += af->sockaddr_len;
	}

	err = sctp_assoc_set_bind_addr_from_ep(asoc, GFP_KERNEL);
	if (err < 0) {
		goto out_free;
	}

	err = sctp_primitive_ASSOCIATE(asoc, NULL);
	if (err < 0) {
		goto out_free;
	}

	/* Initialize sk's dport and daddr for getpeername() */
	inet_sk(sk)->dport = htons(asoc->peer.port);
	af = sctp_get_af_specific(sa_addr->sa.sa_family);
	af->to_sk_daddr(sa_addr, sk);
	sk->sk_err = 0;

	/* in-kernel sockets don't generally have a file allocated to them
	 * if all they do is call sock_create_kern().
	 */
	if (sk->sk_socket->file)
		f_flags = sk->sk_socket->file->f_flags;

	timeo = sock_sndtimeo(sk, f_flags & O_NONBLOCK);

	err = sctp_wait_for_connect(asoc, &timeo);

	/* Don't free association on exit. */
	asoc = NULL;

out_free:

	SCTP_DEBUG_PRINTK("About to exit __sctp_connect() free asoc: %p"
			  " kaddrs: %p err: %d\n",
			  asoc, kaddrs, err);
	if (asoc)
		sctp_association_free(asoc);
	return err;
}

/* Helper for tunneling sctp_connectx() requests through sctp_setsockopt()
 *
 * API 8.9
 * int sctp_connectx(int sd, struct sockaddr *addrs, int addrcnt);
 *
 * If sd is an IPv4 socket, the addresses passed must be IPv4 addresses.
 * If the sd is an IPv6 socket, the addresses passed can either be IPv4
 * or IPv6 addresses.
 *
 * A single address may be specified as INADDR_ANY or IN6ADDR_ANY, see
 * Section 3.1.2 for this usage.
 *
 * addrs is a pointer to an array of one or more socket addresses. Each
 * address is contained in its appropriate structure (i.e. struct
 * sockaddr_in or struct sockaddr_in6) the family of the address type
 * must be used to distengish the address length (note that this
 * representation is termed a "packed array" of addresses). The caller
 * specifies the number of addresses in the array with addrcnt.
 *
 * On success, sctp_connectx() returns 0. On failure, sctp_connectx() returns
 * -1, and sets errno to the appropriate error code.
 *
 * For SCTP, the port given in each socket address must be the same, or
 * sctp_connectx() will fail, setting errno to EINVAL.
 *
 * An application can use sctp_connectx to initiate an association with
 * an endpoint that is multi-homed.  Much like sctp_bindx() this call
 * allows a caller to specify multiple addresses at which a peer can be
 * reached.  The way the SCTP stack uses the list of addresses to set up
 * the association is implementation dependant.  This function only
 * specifies that the stack will try to make use of all the addresses in
 * the list when needed.
 *
 * Note that the list of addresses passed in is only used for setting up
 * the association.  It does not necessarily equal the set of addresses
 * the peer uses for the resulting association.  If the caller wants to
 * find out the set of peer addresses, it must use sctp_getpaddrs() to
 * retrieve them after the association has been set up.
 *
 * Basically do nothing but copying the addresses from user to kernel
 * land and invoking either sctp_connectx(). This is used for tunneling
 * the sctp_connectx() request through sctp_setsockopt() from userspace.
 *
 * We don't use copy_from_user() for optimization: we first do the
 * sanity checks (buffer size -fast- and access check-healthy
 * pointer); if all of those succeed, then we can alloc the memory
 * (expensive operation) needed to copy the data to kernel. Then we do
 * the copying without checking the user space area
 * (__copy_from_user()).
 *
 * On exit there is no need to do sockfd_put(), sys_setsockopt() does
 * it.
 *
 * sk        The sk of the socket
 * addrs     The pointer to the addresses in user land
 * addrssize Size of the addrs buffer
 *
 * Returns 0 if ok, <0 errno code on error.
 */
SCTP_STATIC int sctp_setsockopt_connectx(struct sock* sk,
				      struct sockaddr __user *addrs,
				      int addrs_size)
{
	int err = 0;
	struct sockaddr *kaddrs;

	SCTP_DEBUG_PRINTK("%s - sk %p addrs %p addrs_size %d\n",
			  __FUNCTION__, sk, addrs, addrs_size);

	if (unlikely(addrs_size <= 0))
		return -EINVAL;

	/* Check the user passed a healthy pointer.  */
	if (unlikely(!access_ok(VERIFY_READ, addrs, addrs_size)))
		return -EFAULT;

	/* Alloc space for the address array in kernel memory.  */
	kaddrs = kmalloc(addrs_size, GFP_KERNEL);
	if (unlikely(!kaddrs))
		return -ENOMEM;

	if (__copy_from_user(kaddrs, addrs, addrs_size)) {
		err = -EFAULT;
	} else {
		err = __sctp_connect(sk, kaddrs, addrs_size);
	}

	kfree(kaddrs);
	return err;
}

/* API 3.1.4 close() - UDP Style Syntax
 * Applications use close() to perform graceful shutdown (as described in
 * Section 10.1 of [SCTP]) on ALL the associations currently represented
 * by a UDP-style socket.
 *
 * The syntax is
 *
 *   ret = close(int sd);
 *
 *   sd      - the socket descriptor of the associations to be closed.
 *
 * To gracefully shutdown a specific association represented by the
 * UDP-style socket, an application should use the sendmsg() call,
 * passing no user data, but including the appropriate flag in the
 * ancillary data (see Section xxxx).
 *
 * If sd in the close() call is a branched-off socket representing only
 * one association, the shutdown is performed on that association only.
 *
 * 4.1.6 close() - TCP Style Syntax
 *
 * Applications use close() to gracefully close down an association.
 *
 * The syntax is:
 *
 *    int close(int sd);
 *
 *      sd      - the socket descriptor of the association to be closed.
 *
 * After an application calls close() on a socket descriptor, no further
 * socket operations will succeed on that descriptor.
 *
 * API 7.1.4 SO_LINGER
 *
 * An application using the TCP-style socket can use this option to
 * perform the SCTP ABORT primitive.  The linger option structure is:
 *
 *  struct  linger {
 *     int     l_onoff;                // option on/off
 *     int     l_linger;               // linger time
 * };
 *
 * To enable the option, set l_onoff to 1.  If the l_linger value is set
 * to 0, calling close() is the same as the ABORT primitive.  If the
 * value is set to a negative value, the setsockopt() call will return
 * an error.  If the value is set to a positive value linger_time, the
 * close() can be blocked for at most linger_time ms.  If the graceful
 * shutdown phase does not finish during this period, close() will
 * return but the graceful shutdown phase continues in the system.
 */
SCTP_STATIC void sctp_close(struct sock *sk, long timeout)
{
	struct sctp_endpoint *ep;
	struct sctp_association *asoc;
	struct list_head *pos, *temp;

	SCTP_DEBUG_PRINTK("sctp_close(sk: 0x%p, timeout:%ld)\n", sk, timeout);

	sctp_lock_sock(sk);
	sk->sk_shutdown = SHUTDOWN_MASK;

	ep = sctp_sk(sk)->ep;

	/* Walk all associations on an endpoint.  */
	list_for_each_safe(pos, temp, &ep->asocs) {
		asoc = list_entry(pos, struct sctp_association, asocs);

		if (sctp_style(sk, TCP)) {
			/* A closed association can still be in the list if
			 * it belongs to a TCP-style listening socket that is
			 * not yet accepted. If so, free it. If not, send an
			 * ABORT or SHUTDOWN based on the linger options.
			 */
			if (sctp_state(asoc, CLOSED)) {
				sctp_unhash_established(asoc);
				sctp_association_free(asoc);
				continue;
			}
		}

		if (sock_flag(sk, SOCK_LINGER) && !sk->sk_lingertime) {
			struct sctp_chunk *chunk;

			chunk = sctp_make_abort_user(asoc, NULL, 0);
			if (chunk)
				sctp_primitive_ABORT(asoc, chunk);
		} else
			sctp_primitive_SHUTDOWN(asoc, NULL);