af_iucv.c 37.3 KB
Newer Older
1 2 3 4 5 6 7 8 9 10
/*
 *  linux/net/iucv/af_iucv.c
 *
 *  IUCV protocol stack for Linux on zSeries
 *
 *  Copyright 2006 IBM Corporation
 *
 *  Author(s):	Jennifer Hunt <jenhunt@us.ibm.com>
 */

11 12 13
#define KMSG_COMPONENT "af_iucv"
#define pr_fmt(fmt) KMSG_COMPONENT ": " fmt

14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31
#include <linux/module.h>
#include <linux/types.h>
#include <linux/list.h>
#include <linux/errno.h>
#include <linux/kernel.h>
#include <linux/sched.h>
#include <linux/slab.h>
#include <linux/skbuff.h>
#include <linux/init.h>
#include <linux/poll.h>
#include <net/sock.h>
#include <asm/ebcdic.h>
#include <asm/cpcmd.h>
#include <linux/kmod.h>

#include <net/iucv/iucv.h>
#include <net/iucv/af_iucv.h>

32
#define VERSION "1.1"
33 34 35 36 37 38 39 40 41 42 43

static char iucv_userid[80];

static struct proto_ops iucv_sock_ops;

static struct proto iucv_proto = {
	.name		= "AF_IUCV",
	.owner		= THIS_MODULE,
	.obj_size	= sizeof(struct iucv_sock),
};

44 45 46 47
/* special AF_IUCV IPRM messages */
static const u8 iprm_shutdown[8] =
	{0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x01};

48 49 50 51 52 53 54 55
#define TRGCLS_SIZE	(sizeof(((struct iucv_message *)0)->class))

/* macros to set/get socket control buffer at correct offset */
#define CB_TAG(skb)	((skb)->cb)		/* iucv message tag */
#define CB_TAG_LEN	(sizeof(((struct iucv_message *) 0)->tag))
#define CB_TRGCLS(skb)	((skb)->cb + CB_TAG_LEN) /* iucv msg target class */
#define CB_TRGCLS_LEN	(TRGCLS_SIZE)

56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87
#define __iucv_sock_wait(sk, condition, timeo, ret)			\
do {									\
	DEFINE_WAIT(__wait);						\
	long __timeo = timeo;						\
	ret = 0;							\
	while (!(condition)) {						\
		prepare_to_wait(sk->sk_sleep, &__wait, TASK_INTERRUPTIBLE); \
		if (!__timeo) {						\
			ret = -EAGAIN;					\
			break;						\
		}							\
		if (signal_pending(current)) {				\
			ret = sock_intr_errno(__timeo);			\
			break;						\
		}							\
		release_sock(sk);					\
		__timeo = schedule_timeout(__timeo);			\
		lock_sock(sk);						\
		ret = sock_error(sk);					\
		if (ret)						\
			break;						\
	}								\
	finish_wait(sk->sk_sleep, &__wait);				\
} while (0)

#define iucv_sock_wait(sk, condition, timeo)				\
({									\
	int __ret = 0;							\
	if (!(condition))						\
		__iucv_sock_wait(sk, condition, timeo, __ret);		\
	__ret;								\
})
88

89 90 91
static void iucv_sock_kill(struct sock *sk);
static void iucv_sock_close(struct sock *sk);

92 93 94 95
/* Call Back functions */
static void iucv_callback_rx(struct iucv_path *, struct iucv_message *);
static void iucv_callback_txdone(struct iucv_path *, struct iucv_message *);
static void iucv_callback_connack(struct iucv_path *, u8 ipuser[16]);
96 97
static int iucv_callback_connreq(struct iucv_path *, u8 ipvmid[8],
				 u8 ipuser[16]);
98
static void iucv_callback_connrej(struct iucv_path *, u8 ipuser[16]);
99
static void iucv_callback_shutdown(struct iucv_path *, u8 ipuser[16]);
100 101

static struct iucv_sock_list iucv_sk_list = {
102
	.lock = __RW_LOCK_UNLOCKED(iucv_sk_list.lock),
103 104 105 106 107 108 109 110
	.autobind_name = ATOMIC_INIT(0)
};

static struct iucv_handler af_iucv_handler = {
	.path_pending	  = iucv_callback_connreq,
	.path_complete	  = iucv_callback_connack,
	.path_severed	  = iucv_callback_connrej,
	.message_pending  = iucv_callback_rx,
111 112
	.message_complete = iucv_callback_txdone,
	.path_quiesced	  = iucv_callback_shutdown,
113 114 115 116 117 118 119 120 121 122 123 124
};

static inline void high_nmcpy(unsigned char *dst, char *src)
{
       memcpy(dst, src, 8);
}

static inline void low_nmcpy(unsigned char *dst, char *src)
{
       memcpy(&dst[8], src, 8);
}

125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155
/**
 * iucv_msg_length() - Returns the length of an iucv message.
 * @msg:	Pointer to struct iucv_message, MUST NOT be NULL
 *
 * The function returns the length of the specified iucv message @msg of data
 * stored in a buffer and of data stored in the parameter list (PRMDATA).
 *
 * For IUCV_IPRMDATA, AF_IUCV uses the following convention to transport socket
 * data:
 *	PRMDATA[0..6]	socket data (max 7 bytes);
 *	PRMDATA[7]	socket data length value (len is 0xff - PRMDATA[7])
 *
 * The socket data length is computed by substracting the socket data length
 * value from 0xFF.
 * If the socket data len is greater 7, then PRMDATA can be used for special
 * notifications (see iucv_sock_shutdown); and further,
 * if the socket data len is > 7, the function returns 8.
 *
 * Use this function to allocate socket buffers to store iucv message data.
 */
static inline size_t iucv_msg_length(struct iucv_message *msg)
{
	size_t datalen;

	if (msg->flags & IUCV_IPRMDATA) {
		datalen = 0xff - msg->rmmsg[7];
		return (datalen < 8) ? datalen : 8;
	}
	return msg->length;
}

156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197
/**
 * iucv_sock_in_state() - check for specific states
 * @sk:		sock structure
 * @state:	first iucv sk state
 * @state:	second iucv sk state
 *
 * Returns true if the socket in either in the first or second state.
 */
static int iucv_sock_in_state(struct sock *sk, int state, int state2)
{
	return (sk->sk_state == state || sk->sk_state == state2);
}

/**
 * iucv_below_msglim() - function to check if messages can be sent
 * @sk:		sock structure
 *
 * Returns true if the send queue length is lower than the message limit.
 * Always returns true if the socket is not connected (no iucv path for
 * checking the message limit).
 */
static inline int iucv_below_msglim(struct sock *sk)
{
	struct iucv_sock *iucv = iucv_sk(sk);

	if (sk->sk_state != IUCV_CONNECTED)
		return 1;
	return (skb_queue_len(&iucv->send_skb_q) < iucv->path->msglim);
}

/**
 * iucv_sock_wake_msglim() - Wake up thread waiting on msg limit
 */
static void iucv_sock_wake_msglim(struct sock *sk)
{
	read_lock(&sk->sk_callback_lock);
	if (sk->sk_sleep && waitqueue_active(sk->sk_sleep))
		wake_up_interruptible_all(sk->sk_sleep);
	sk_wake_async(sk, SOCK_WAKE_SPACE, POLL_OUT);
	read_unlock(&sk->sk_callback_lock);
}

198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266
/* Timers */
static void iucv_sock_timeout(unsigned long arg)
{
	struct sock *sk = (struct sock *)arg;

	bh_lock_sock(sk);
	sk->sk_err = ETIMEDOUT;
	sk->sk_state_change(sk);
	bh_unlock_sock(sk);

	iucv_sock_kill(sk);
	sock_put(sk);
}

static void iucv_sock_clear_timer(struct sock *sk)
{
	sk_stop_timer(sk, &sk->sk_timer);
}

static struct sock *__iucv_get_sock_by_name(char *nm)
{
	struct sock *sk;
	struct hlist_node *node;

	sk_for_each(sk, node, &iucv_sk_list.head)
		if (!memcmp(&iucv_sk(sk)->src_name, nm, 8))
			return sk;

	return NULL;
}

static void iucv_sock_destruct(struct sock *sk)
{
	skb_queue_purge(&sk->sk_receive_queue);
	skb_queue_purge(&sk->sk_write_queue);
}

/* Cleanup Listen */
static void iucv_sock_cleanup_listen(struct sock *parent)
{
	struct sock *sk;

	/* Close non-accepted connections */
	while ((sk = iucv_accept_dequeue(parent, NULL))) {
		iucv_sock_close(sk);
		iucv_sock_kill(sk);
	}

	parent->sk_state = IUCV_CLOSED;
	sock_set_flag(parent, SOCK_ZAPPED);
}

/* Kill socket */
static void iucv_sock_kill(struct sock *sk)
{
	if (!sock_flag(sk, SOCK_ZAPPED) || sk->sk_socket)
		return;

	iucv_sock_unlink(&iucv_sk_list, sk);
	sock_set_flag(sk, SOCK_DEAD);
	sock_put(sk);
}

/* Close an IUCV socket */
static void iucv_sock_close(struct sock *sk)
{
	unsigned char user_data[16];
	struct iucv_sock *iucv = iucv_sk(sk);
	int err;
267
	unsigned long timeo;
268 269 270 271

	iucv_sock_clear_timer(sk);
	lock_sock(sk);

272
	switch (sk->sk_state) {
273 274 275 276 277 278 279
	case IUCV_LISTEN:
		iucv_sock_cleanup_listen(sk);
		break;

	case IUCV_CONNECTED:
	case IUCV_DISCONN:
		err = 0;
280 281 282 283

		sk->sk_state = IUCV_CLOSING;
		sk->sk_state_change(sk);

284
		if (!skb_queue_empty(&iucv->send_skb_q)) {
285 286 287 288
			if (sock_flag(sk, SOCK_LINGER) && sk->sk_lingertime)
				timeo = sk->sk_lingertime;
			else
				timeo = IUCV_DISCONN_TIMEOUT;
289 290 291
			err = iucv_sock_wait(sk,
					iucv_sock_in_state(sk, IUCV_CLOSED, 0),
					timeo);
292 293
		}

294
	case IUCV_CLOSING:   /* fall through */
295 296 297
		sk->sk_state = IUCV_CLOSED;
		sk->sk_state_change(sk);

298 299 300 301 302 303 304 305 306 307 308 309 310
		if (iucv->path) {
			low_nmcpy(user_data, iucv->src_name);
			high_nmcpy(user_data, iucv->dst_name);
			ASCEBC(user_data, sizeof(user_data));
			err = iucv_path_sever(iucv->path, user_data);
			iucv_path_free(iucv->path);
			iucv->path = NULL;
		}

		sk->sk_err = ECONNRESET;
		sk->sk_state_change(sk);

		skb_queue_purge(&iucv->send_skb_q);
311
		skb_queue_purge(&iucv->backlog_skb_q);
312 313 314 315 316 317 318

		sock_set_flag(sk, SOCK_ZAPPED);
		break;

	default:
		sock_set_flag(sk, SOCK_ZAPPED);
		break;
319
	}
320 321 322 323 324 325 326 327 328 329 330 331 332 333 334

	release_sock(sk);
	iucv_sock_kill(sk);
}

static void iucv_sock_init(struct sock *sk, struct sock *parent)
{
	if (parent)
		sk->sk_type = parent->sk_type;
}

static struct sock *iucv_sock_alloc(struct socket *sock, int proto, gfp_t prio)
{
	struct sock *sk;

335
	sk = sk_alloc(&init_net, PF_IUCV, prio, &iucv_proto);
336 337 338 339 340
	if (!sk)
		return NULL;

	sock_init_data(sock, sk);
	INIT_LIST_HEAD(&iucv_sk(sk)->accept_q);
341
	spin_lock_init(&iucv_sk(sk)->accept_q_lock);
342
	skb_queue_head_init(&iucv_sk(sk)->send_skb_q);
343 344
	INIT_LIST_HEAD(&iucv_sk(sk)->message_q.list);
	spin_lock_init(&iucv_sk(sk)->message_q.lock);
345
	skb_queue_head_init(&iucv_sk(sk)->backlog_skb_q);
346
	iucv_sk(sk)->send_tag = 0;
347
	iucv_sk(sk)->flags = 0;
348
	iucv_sk(sk)->msglimit = IUCV_QUEUELEN_DEFAULT;
349 350
	iucv_sk(sk)->path = NULL;
	memset(&iucv_sk(sk)->src_user_id , 0, 32);
351 352 353 354 355 356 357 358 359 360

	sk->sk_destruct = iucv_sock_destruct;
	sk->sk_sndtimeo = IUCV_CONN_TIMEOUT;
	sk->sk_allocation = GFP_DMA;

	sock_reset_flag(sk, SOCK_ZAPPED);

	sk->sk_protocol = proto;
	sk->sk_state	= IUCV_OPEN;

361
	setup_timer(&sk->sk_timer, iucv_sock_timeout, (unsigned long)sk);
362 363 364 365 366 367

	iucv_sock_link(&iucv_sk_list, sk);
	return sk;
}

/* Create an IUCV socket */
368
static int iucv_sock_create(struct net *net, struct socket *sock, int protocol)
369 370 371
{
	struct sock *sk;

372 373
	if (protocol && protocol != PF_IUCV)
		return -EPROTONOSUPPORT;
374 375

	sock->state = SS_UNCONNECTED;
376 377 378 379 380 381 382 383 384 385 386 387

	switch (sock->type) {
	case SOCK_STREAM:
		sock->ops = &iucv_sock_ops;
		break;
	case SOCK_SEQPACKET:
		/* currently, proto ops can handle both sk types */
		sock->ops = &iucv_sock_ops;
		break;
	default:
		return -ESOCKTNOSUPPORT;
	}
388 389 390 391 392 393 394 395 396 397 398 399 400 401 402 403 404 405 406 407 408 409 410 411 412 413

	sk = iucv_sock_alloc(sock, protocol, GFP_KERNEL);
	if (!sk)
		return -ENOMEM;

	iucv_sock_init(sk, NULL);

	return 0;
}

void iucv_sock_link(struct iucv_sock_list *l, struct sock *sk)
{
	write_lock_bh(&l->lock);
	sk_add_node(sk, &l->head);
	write_unlock_bh(&l->lock);
}

void iucv_sock_unlink(struct iucv_sock_list *l, struct sock *sk)
{
	write_lock_bh(&l->lock);
	sk_del_node_init(sk);
	write_unlock_bh(&l->lock);
}

void iucv_accept_enqueue(struct sock *parent, struct sock *sk)
{
414 415 416
	unsigned long flags;
	struct iucv_sock *par = iucv_sk(parent);

417
	sock_hold(sk);
418 419 420
	spin_lock_irqsave(&par->accept_q_lock, flags);
	list_add_tail(&iucv_sk(sk)->accept_q, &par->accept_q);
	spin_unlock_irqrestore(&par->accept_q_lock, flags);
421 422 423 424 425 426
	iucv_sk(sk)->parent = parent;
	parent->sk_ack_backlog++;
}

void iucv_accept_unlink(struct sock *sk)
{
427 428 429 430
	unsigned long flags;
	struct iucv_sock *par = iucv_sk(iucv_sk(sk)->parent);

	spin_lock_irqsave(&par->accept_q_lock, flags);
431
	list_del_init(&iucv_sk(sk)->accept_q);
432
	spin_unlock_irqrestore(&par->accept_q_lock, flags);
433 434 435 436 437 438 439 440 441 442
	iucv_sk(sk)->parent->sk_ack_backlog--;
	iucv_sk(sk)->parent = NULL;
	sock_put(sk);
}

struct sock *iucv_accept_dequeue(struct sock *parent, struct socket *newsock)
{
	struct iucv_sock *isk, *n;
	struct sock *sk;

443
	list_for_each_entry_safe(isk, n, &iucv_sk(parent)->accept_q, accept_q) {
444 445 446 447 448
		sk = (struct sock *) isk;
		lock_sock(sk);

		if (sk->sk_state == IUCV_CLOSED) {
			iucv_accept_unlink(sk);
449
			release_sock(sk);
450 451 452 453 454 455 456 457 458 459 460 461 462 463 464 465 466 467 468 469 470 471 472 473 474 475 476 477 478 479 480 481 482 483 484 485 486 487 488 489 490 491 492 493 494 495 496 497 498 499 500 501 502 503 504 505 506 507 508 509 510 511 512 513 514 515 516 517 518 519 520 521 522 523 524 525 526 527 528 529 530 531 532 533 534 535 536 537 538 539 540 541 542 543 544 545 546 547 548 549 550 551 552 553 554 555 556 557 558 559 560 561 562 563 564
			continue;
		}

		if (sk->sk_state == IUCV_CONNECTED ||
		    sk->sk_state == IUCV_SEVERED ||
		    !newsock) {
			iucv_accept_unlink(sk);
			if (newsock)
				sock_graft(sk, newsock);

			if (sk->sk_state == IUCV_SEVERED)
				sk->sk_state = IUCV_DISCONN;

			release_sock(sk);
			return sk;
		}

		release_sock(sk);
	}
	return NULL;
}

/* Bind an unbound socket */
static int iucv_sock_bind(struct socket *sock, struct sockaddr *addr,
			  int addr_len)
{
	struct sockaddr_iucv *sa = (struct sockaddr_iucv *) addr;
	struct sock *sk = sock->sk;
	struct iucv_sock *iucv;
	int err;

	/* Verify the input sockaddr */
	if (!addr || addr->sa_family != AF_IUCV)
		return -EINVAL;

	lock_sock(sk);
	if (sk->sk_state != IUCV_OPEN) {
		err = -EBADFD;
		goto done;
	}

	write_lock_bh(&iucv_sk_list.lock);

	iucv = iucv_sk(sk);
	if (__iucv_get_sock_by_name(sa->siucv_name)) {
		err = -EADDRINUSE;
		goto done_unlock;
	}
	if (iucv->path) {
		err = 0;
		goto done_unlock;
	}

	/* Bind the socket */
	memcpy(iucv->src_name, sa->siucv_name, 8);

	/* Copy the user id */
	memcpy(iucv->src_user_id, iucv_userid, 8);
	sk->sk_state = IUCV_BOUND;
	err = 0;

done_unlock:
	/* Release the socket list lock */
	write_unlock_bh(&iucv_sk_list.lock);
done:
	release_sock(sk);
	return err;
}

/* Automatically bind an unbound socket */
static int iucv_sock_autobind(struct sock *sk)
{
	struct iucv_sock *iucv = iucv_sk(sk);
	char query_buffer[80];
	char name[12];
	int err = 0;

	/* Set the userid and name */
	cpcmd("QUERY USERID", query_buffer, sizeof(query_buffer), &err);
	if (unlikely(err))
		return -EPROTO;

	memcpy(iucv->src_user_id, query_buffer, 8);

	write_lock_bh(&iucv_sk_list.lock);

	sprintf(name, "%08x", atomic_inc_return(&iucv_sk_list.autobind_name));
	while (__iucv_get_sock_by_name(name)) {
		sprintf(name, "%08x",
			atomic_inc_return(&iucv_sk_list.autobind_name));
	}

	write_unlock_bh(&iucv_sk_list.lock);

	memcpy(&iucv->src_name, name, 8);

	return err;
}

/* Connect an unconnected socket */
static int iucv_sock_connect(struct socket *sock, struct sockaddr *addr,
			     int alen, int flags)
{
	struct sockaddr_iucv *sa = (struct sockaddr_iucv *) addr;
	struct sock *sk = sock->sk;
	struct iucv_sock *iucv;
	unsigned char user_data[16];
	int err;

	if (addr->sa_family != AF_IUCV || alen < sizeof(struct sockaddr_iucv))
		return -EINVAL;

	if (sk->sk_state != IUCV_OPEN && sk->sk_state != IUCV_BOUND)
		return -EBADFD;

565
	if (sk->sk_type != SOCK_STREAM && sk->sk_type != SOCK_SEQPACKET)
566 567 568 569 570 571 572 573 574 575 576 577 578 579 580 581 582 583 584 585
		return -EINVAL;

	if (sk->sk_state == IUCV_OPEN) {
		err = iucv_sock_autobind(sk);
		if (unlikely(err))
			return err;
	}

	lock_sock(sk);

	/* Set the destination information */
	memcpy(iucv_sk(sk)->dst_user_id, sa->siucv_user_id, 8);
	memcpy(iucv_sk(sk)->dst_name, sa->siucv_name, 8);

	high_nmcpy(user_data, sa->siucv_name);
	low_nmcpy(user_data, iucv_sk(sk)->src_name);
	ASCEBC(user_data, sizeof(user_data));

	iucv = iucv_sk(sk);
	/* Create path. */
586
	iucv->path = iucv_path_alloc(iucv->msglimit,
587
				     IUCV_IPRMDATA, GFP_KERNEL);
588 589 590 591
	if (!iucv->path) {
		err = -ENOMEM;
		goto done;
	}
592 593 594 595 596
	err = iucv_path_connect(iucv->path, &af_iucv_handler,
				sa->siucv_user_id, NULL, user_data, sk);
	if (err) {
		iucv_path_free(iucv->path);
		iucv->path = NULL;
597 598 599 600 601 602 603 604 605 606 607 608 609 610 611
		switch (err) {
		case 0x0b:	/* Target communicator is not logged on */
			err = -ENETUNREACH;
			break;
		case 0x0d:	/* Max connections for this guest exceeded */
		case 0x0e:	/* Max connections for target guest exceeded */
			err = -EAGAIN;
			break;
		case 0x0f:	/* Missing IUCV authorization */
			err = -EACCES;
			break;
		default:
			err = -ECONNREFUSED;
			break;
		}
612 613 614 615
		goto done;
	}

	if (sk->sk_state != IUCV_CONNECTED) {
616 617 618
		err = iucv_sock_wait(sk, iucv_sock_in_state(sk, IUCV_CONNECTED,
							    IUCV_DISCONN),
				     sock_sndtimeo(sk, flags & O_NONBLOCK));
619 620 621
	}

	if (sk->sk_state == IUCV_DISCONN) {
622
		err = -ECONNREFUSED;
623
	}
624 625 626 627 628 629 630

	if (err) {
		iucv_path_sever(iucv->path, NULL);
		iucv_path_free(iucv->path);
		iucv->path = NULL;
	}

631 632 633 634 635 636 637 638 639 640 641 642 643 644
done:
	release_sock(sk);
	return err;
}

/* Move a socket into listening state. */
static int iucv_sock_listen(struct socket *sock, int backlog)
{
	struct sock *sk = sock->sk;
	int err;

	lock_sock(sk);

	err = -EINVAL;
645 646 647 648
	if (sk->sk_state != IUCV_BOUND)
		goto done;

	if (sock->type != SOCK_STREAM && sock->type != SOCK_SEQPACKET)
649 650 651 652 653 654 655 656 657 658 659 660 661 662 663 664 665 666 667 668 669
		goto done;

	sk->sk_max_ack_backlog = backlog;
	sk->sk_ack_backlog = 0;
	sk->sk_state = IUCV_LISTEN;
	err = 0;

done:
	release_sock(sk);
	return err;
}

/* Accept a pending connection */
static int iucv_sock_accept(struct socket *sock, struct socket *newsock,
			    int flags)
{
	DECLARE_WAITQUEUE(wait, current);
	struct sock *sk = sock->sk, *nsk;
	long timeo;
	int err = 0;

670
	lock_sock_nested(sk, SINGLE_DEPTH_NESTING);
671 672 673 674 675 676 677 678 679 680

	if (sk->sk_state != IUCV_LISTEN) {
		err = -EBADFD;
		goto done;
	}

	timeo = sock_rcvtimeo(sk, flags & O_NONBLOCK);

	/* Wait for an incoming connection */
	add_wait_queue_exclusive(sk->sk_sleep, &wait);
681
	while (!(nsk = iucv_accept_dequeue(sk, newsock))) {
682 683 684 685 686 687 688 689
		set_current_state(TASK_INTERRUPTIBLE);
		if (!timeo) {
			err = -EAGAIN;
			break;
		}

		release_sock(sk);
		timeo = schedule_timeout(timeo);
690
		lock_sock_nested(sk, SINGLE_DEPTH_NESTING);
691 692 693 694 695 696 697 698 699 700 701 702 703 704 705 706 707 708 709 710 711 712 713 714 715 716 717 718 719 720 721 722 723 724 725 726 727 728 729 730 731 732 733 734 735 736 737 738

		if (sk->sk_state != IUCV_LISTEN) {
			err = -EBADFD;
			break;
		}

		if (signal_pending(current)) {
			err = sock_intr_errno(timeo);
			break;
		}
	}

	set_current_state(TASK_RUNNING);
	remove_wait_queue(sk->sk_sleep, &wait);

	if (err)
		goto done;

	newsock->state = SS_CONNECTED;

done:
	release_sock(sk);
	return err;
}

static int iucv_sock_getname(struct socket *sock, struct sockaddr *addr,
			     int *len, int peer)
{
	struct sockaddr_iucv *siucv = (struct sockaddr_iucv *) addr;
	struct sock *sk = sock->sk;

	addr->sa_family = AF_IUCV;
	*len = sizeof(struct sockaddr_iucv);

	if (peer) {
		memcpy(siucv->siucv_user_id, iucv_sk(sk)->dst_user_id, 8);
		memcpy(siucv->siucv_name, &iucv_sk(sk)->dst_name, 8);
	} else {
		memcpy(siucv->siucv_user_id, iucv_sk(sk)->src_user_id, 8);
		memcpy(siucv->siucv_name, iucv_sk(sk)->src_name, 8);
	}
	memset(&siucv->siucv_port, 0, sizeof(siucv->siucv_port));
	memset(&siucv->siucv_addr, 0, sizeof(siucv->siucv_addr));
	memset(siucv->siucv_nodeid, 0, sizeof(siucv->siucv_nodeid));

	return 0;
}

739 740 741 742 743 744 745 746 747 748 749 750 751 752 753 754 755 756 757 758 759 760 761 762
/**
 * iucv_send_iprm() - Send socket data in parameter list of an iucv message.
 * @path:	IUCV path
 * @msg:	Pointer to a struct iucv_message
 * @skb:	The socket data to send, skb->len MUST BE <= 7
 *
 * Send the socket data in the parameter list in the iucv message
 * (IUCV_IPRMDATA). The socket data is stored at index 0 to 6 in the parameter
 * list and the socket data len at index 7 (last byte).
 * See also iucv_msg_length().
 *
 * Returns the error code from the iucv_message_send() call.
 */
static int iucv_send_iprm(struct iucv_path *path, struct iucv_message *msg,
			  struct sk_buff *skb)
{
	u8 prmdata[8];

	memcpy(prmdata, (void *) skb->data, skb->len);
	prmdata[7] = 0xff - (u8) skb->len;
	return iucv_message_send(path, msg, IUCV_IPRMDATA, 0,
				 (void *) prmdata, 8);
}

763 764 765 766 767 768 769
static int iucv_sock_sendmsg(struct kiocb *iocb, struct socket *sock,
			     struct msghdr *msg, size_t len)
{
	struct sock *sk = sock->sk;
	struct iucv_sock *iucv = iucv_sk(sk);
	struct sk_buff *skb;
	struct iucv_message txmsg;
770 771
	struct cmsghdr *cmsg;
	int cmsg_done;
772
	long timeo;
773 774
	char user_id[9];
	char appl_id[9];
775
	int err;
776
	int noblock = msg->msg_flags & MSG_DONTWAIT;
777 778 779 780 781 782 783 784

	err = sock_error(sk);
	if (err)
		return err;

	if (msg->msg_flags & MSG_OOB)
		return -EOPNOTSUPP;

785 786 787 788
	/* SOCK_SEQPACKET: we do not support segmented records */
	if (sk->sk_type == SOCK_SEQPACKET && !(msg->msg_flags & MSG_EOR))
		return -EOPNOTSUPP;

789 790 791 792 793 794 795
	lock_sock(sk);

	if (sk->sk_shutdown & SEND_SHUTDOWN) {
		err = -EPIPE;
		goto out;
	}

796 797 798 799 800
	/* Return if the socket is not in connected state */
	if (sk->sk_state != IUCV_CONNECTED) {
		err = -ENOTCONN;
		goto out;
	}
801

802 803 804
	/* initialize defaults */
	cmsg_done   = 0;	/* check for duplicate headers */
	txmsg.class = 0;
805

806 807 808
	/* iterate over control messages */
	for (cmsg = CMSG_FIRSTHDR(msg); cmsg;
		cmsg = CMSG_NXTHDR(msg, cmsg)) {
809

810 811 812 813
		if (!CMSG_OK(msg, cmsg)) {
			err = -EINVAL;
			goto out;
		}
814

815 816
		if (cmsg->cmsg_level != SOL_IUCV)
			continue;
817

818 819 820 821 822
		if (cmsg->cmsg_type & cmsg_done) {
			err = -EINVAL;
			goto out;
		}
		cmsg_done |= cmsg->cmsg_type;
823

824 825 826
		switch (cmsg->cmsg_type) {
		case SCM_IUCV_TRGCLS:
			if (cmsg->cmsg_len != CMSG_LEN(TRGCLS_SIZE)) {
827 828 829 830
				err = -EINVAL;
				goto out;
			}

831 832 833
			/* set iucv message target class */
			memcpy(&txmsg.class,
				(void *) CMSG_DATA(cmsg), TRGCLS_SIZE);
834

835 836 837 838 839 840
			break;

		default:
			err = -EINVAL;
			goto out;
			break;
841
		}
842
	}
843

844 845 846 847
	/* allocate one skb for each iucv message:
	 * this is fine for SOCK_SEQPACKET (unless we want to support
	 * segmented records using the MSG_EOR flag), but
	 * for SOCK_STREAM we might want to improve it in future */
848
	skb = sock_alloc_send_skb(sk, len, noblock, &err);
849 850 851 852 853 854
	if (!skb)
		goto out;
	if (memcpy_fromiovec(skb_put(skb, len), msg->msg_iov, len)) {
		err = -EFAULT;
		goto fail;
	}
855

856 857 858 859 860 861 862 863 864 865 866 867
	/* wait if outstanding messages for iucv path has reached */
	timeo = sock_sndtimeo(sk, noblock);
	err = iucv_sock_wait(sk, iucv_below_msglim(sk), timeo);
	if (err)
		goto fail;

	/* return -ECONNRESET if the socket is no longer connected */
	if (sk->sk_state != IUCV_CONNECTED) {
		err = -ECONNRESET;
		goto fail;
	}

868 869 870 871
	/* increment and save iucv message tag for msg_completion cbk */
	txmsg.tag = iucv->send_tag++;
	memcpy(CB_TAG(skb), &txmsg.tag, CB_TAG_LEN);
	skb_queue_tail(&iucv->send_skb_q, skb);
872

873 874 875
	if (((iucv->path->flags & IUCV_IPRMDATA) & iucv->flags)
	      && skb->len <= 7) {
		err = iucv_send_iprm(iucv->path, &txmsg, skb);
876

877 878 879 880 881 882 883 884 885 886 887
		/* on success: there is no message_complete callback
		 * for an IPRMDATA msg; remove skb from send queue */
		if (err == 0) {
			skb_unlink(skb, &iucv->send_skb_q);
			kfree_skb(skb);
		}

		/* this error should never happen since the
		 * IUCV_IPRMDATA path flag is set... sever path */
		if (err == 0x15) {
			iucv_path_sever(iucv->path, NULL);
888 889 890 891
			skb_unlink(skb, &iucv->send_skb_q);
			err = -EPIPE;
			goto fail;
		}
892 893 894 895 896 897 898 899 900 901 902 903
	} else
		err = iucv_message_send(iucv->path, &txmsg, 0, 0,
					(void *) skb->data, skb->len);
	if (err) {
		if (err == 3) {
			user_id[8] = 0;
			memcpy(user_id, iucv->dst_user_id, 8);
			appl_id[8] = 0;
			memcpy(appl_id, iucv->dst_name, 8);
			pr_err("Application %s on z/VM guest %s"
				" exceeds message limit\n",
				appl_id, user_id);
904 905 906
			err = -EAGAIN;
		} else
			err = -EPIPE;
907 908
		skb_unlink(skb, &iucv->send_skb_q);
		goto fail;
909 910 911 912 913 914 915 916 917 918 919 920
	}

	release_sock(sk);
	return len;

fail:
	kfree_skb(skb);
out:
	release_sock(sk);
	return err;
}

921 922 923 924 925 926 927 928 929 930 931 932 933 934 935 936
static int iucv_fragment_skb(struct sock *sk, struct sk_buff *skb, int len)
{
	int dataleft, size, copied = 0;
	struct sk_buff *nskb;

	dataleft = len;
	while (dataleft) {
		if (dataleft >= sk->sk_rcvbuf / 4)
			size = sk->sk_rcvbuf / 4;
		else
			size = dataleft;

		nskb = alloc_skb(size, GFP_ATOMIC | GFP_DMA);
		if (!nskb)
			return -ENOMEM;

937 938 939 940
		/* copy target class to control buffer of new skb */
		memcpy(CB_TRGCLS(nskb), CB_TRGCLS(skb), CB_TRGCLS_LEN);

		/* copy data fragment */
941 942 943 944 945 946 947 948 949 950 951 952 953 954 955 956 957 958 959
		memcpy(nskb->data, skb->data + copied, size);
		copied += size;
		dataleft -= size;

		skb_reset_transport_header(nskb);
		skb_reset_network_header(nskb);
		nskb->len = size;

		skb_queue_tail(&iucv_sk(sk)->backlog_skb_q, nskb);
	}

	return 0;
}

static void iucv_process_message(struct sock *sk, struct sk_buff *skb,
				 struct iucv_path *path,
				 struct iucv_message *msg)
{
	int rc;
960 961 962
	unsigned int len;

	len = iucv_msg_length(msg);
963

964 965 966 967
	/* store msg target class in the second 4 bytes of skb ctrl buffer */
	/* Note: the first 4 bytes are reserved for msg tag */
	memcpy(CB_TRGCLS(skb), &msg->class, CB_TRGCLS_LEN);

968 969 970 971 972 973
	/* check for special IPRM messages (e.g. iucv_sock_shutdown) */
	if ((msg->flags & IUCV_IPRMDATA) && len > 7) {
		if (memcmp(msg->rmmsg, iprm_shutdown, 8) == 0) {
			skb->data = NULL;
			skb->len = 0;
		}
974
	} else {
975 976
		rc = iucv_message_receive(path, msg, msg->flags & IUCV_IPRMDATA,
					  skb->data, len, NULL);
977 978 979 980
		if (rc) {
			kfree_skb(skb);
			return;
		}
981 982 983 984 985
		/* we need to fragment iucv messages for SOCK_STREAM only;
		 * for SOCK_SEQPACKET, it is only relevant if we support
		 * record segmentation using MSG_EOR (see also recvmsg()) */
		if (sk->sk_type == SOCK_STREAM &&
		    skb->truesize >= sk->sk_rcvbuf / 4) {
986
			rc = iucv_fragment_skb(sk, skb, len);
987 988 989 990 991 992 993 994 995 996
			kfree_skb(skb);
			skb = NULL;
			if (rc) {
				iucv_path_sever(path, NULL);
				return;
			}
			skb = skb_dequeue(&iucv_sk(sk)->backlog_skb_q);
		} else {
			skb_reset_transport_header(skb);
			skb_reset_network_header(skb);
997
			skb->len = len;
998 999 1000 1001 1002 1003 1004 1005 1006 1007 1008 1009 1010 1011
		}
	}

	if (sock_queue_rcv_skb(sk, skb))
		skb_queue_head(&iucv_sk(sk)->backlog_skb_q, skb);
}

static void iucv_process_message_q(struct sock *sk)
{
	struct iucv_sock *iucv = iucv_sk(sk);
	struct sk_buff *skb;
	struct sock_msg_q *p, *n;

	list_for_each_entry_safe(p, n, &iucv->message_q.list, list) {
1012
		skb = alloc_skb(iucv_msg_length(&p->msg), GFP_ATOMIC | GFP_DMA);
1013 1014 1015 1016 1017 1018 1019 1020 1021 1022
		if (!skb)
			break;
		iucv_process_message(sk, skb, p->path, &p->msg);
		list_del(&p->list);
		kfree(p);
		if (!skb_queue_empty(&iucv->backlog_skb_q))
			break;
	}
}

1023 1024 1025 1026 1027
static int iucv_sock_recvmsg(struct kiocb *iocb, struct socket *sock,
			     struct msghdr *msg, size_t len, int flags)
{
	int noblock = flags & MSG_DONTWAIT;
	struct sock *sk = sock->sk;
1028
	struct iucv_sock *iucv = iucv_sk(sk);
1029
	unsigned int copied, rlen;
1030
	struct sk_buff *skb, *rskb, *cskb;
1031 1032
	int err = 0;

1033
	if ((sk->sk_state == IUCV_DISCONN || sk->sk_state == IUCV_SEVERED) &&
1034 1035 1036
	    skb_queue_empty(&iucv->backlog_skb_q) &&
	    skb_queue_empty(&sk->sk_receive_queue) &&
	    list_empty(&iucv->message_q.list))
1037 1038
		return 0;

1039 1040 1041
	if (flags & (MSG_OOB))
		return -EOPNOTSUPP;

1042 1043
	/* receive/dequeue next skb:
	 * the function understands MSG_PEEK and, thus, does not dequeue skb */
1044 1045 1046 1047 1048 1049 1050
	skb = skb_recv_datagram(sk, flags, noblock, &err);
	if (!skb) {
		if (sk->sk_shutdown & RCV_SHUTDOWN)
			return 0;
		return err;
	}

1051 1052
	rlen   = skb->len;		/* real length of skb */
	copied = min_t(unsigned int, rlen, len);
1053

1054 1055
	cskb = skb;
	if (memcpy_toiovec(msg->msg_iov, cskb->data, copied)) {
1056 1057 1058
		if (!(flags & MSG_PEEK))
			skb_queue_head(&sk->sk_receive_queue, skb);
		return -EFAULT;
1059 1060
	}

1061 1062 1063 1064 1065 1066 1067
	/* SOCK_SEQPACKET: set MSG_TRUNC if recv buf size is too small */
	if (sk->sk_type == SOCK_SEQPACKET) {
		if (copied < rlen)
			msg->msg_flags |= MSG_TRUNC;
		/* each iucv message contains a complete record */
		msg->msg_flags |= MSG_EOR;
	}
1068

1069 1070 1071 1072 1073 1074 1075 1076 1077 1078 1079
	/* create control message to store iucv msg target class:
	 * get the trgcls from the control buffer of the skb due to
	 * fragmentation of original iucv message. */
	err = put_cmsg(msg, SOL_IUCV, SCM_IUCV_TRGCLS,
			CB_TRGCLS_LEN, CB_TRGCLS(skb));
	if (err) {
		if (!(flags & MSG_PEEK))
			skb_queue_head(&sk->sk_receive_queue, skb);
		return err;
	}

1080 1081 1082
	/* Mark read part of skb as used */
	if (!(flags & MSG_PEEK)) {

1083 1084 1085 1086 1087 1088 1089
		/* SOCK_STREAM: re-queue skb if it contains unreceived data */
		if (sk->sk_type == SOCK_STREAM) {
			skb_pull(skb, copied);
			if (skb->len) {
				skb_queue_head(&sk->sk_receive_queue, skb);
				goto done;
			}
1090 1091 1092
		}

		kfree_skb(skb);
1093 1094

		/* Queue backlog skbs */
1095
		rskb = skb_dequeue(&iucv->backlog_skb_q);
1096
		while (rskb) {
1097
			if (sock_queue_rcv_skb(sk, rskb)) {
1098
				skb_queue_head(&iucv->backlog_skb_q,
1099 1100 1101
						rskb);
				break;
			} else {
1102
				rskb = skb_dequeue(&iucv->backlog_skb_q);
1103 1104
			}
		}
1105 1106 1107 1108 1109 1110
		if (skb_queue_empty(&iucv->backlog_skb_q)) {
			spin_lock_bh(&iucv->message_q.lock);
			if (!list_empty(&iucv->message_q.list))
				iucv_process_message_q(sk);
			spin_unlock_bh(&iucv->message_q.lock);
		}
1111
	}
1112 1113

done:
1114 1115 1116 1117 1118
	/* SOCK_SEQPACKET: return real length if MSG_TRUNC is set */
	if (sk->sk_type == SOCK_SEQPACKET && (flags & MSG_TRUNC))
		copied = rlen;

	return copied;
1119 1120 1121 1122 1123 1124 1125
}

static inline unsigned int iucv_accept_poll(struct sock *parent)
{
	struct iucv_sock *isk, *n;
	struct sock *sk;

1126
	list_for_each_entry_safe(isk, n, &iucv_sk(parent)->accept_q, accept_q) {
1127 1128 1129 1130 1131 1132 1133 1134 1135 1136 1137 1138 1139 1140 1141 1142 1143 1144 1145 1146 1147 1148 1149 1150 1151 1152 1153 1154 1155 1156
		sk = (struct sock *) isk;

		if (sk->sk_state == IUCV_CONNECTED)
			return POLLIN | POLLRDNORM;
	}

	return 0;
}

unsigned int iucv_sock_poll(struct file *file, struct socket *sock,
			    poll_table *wait)
{
	struct sock *sk = sock->sk;
	unsigned int mask = 0;

	poll_wait(file, sk->sk_sleep, wait);

	if (sk->sk_state == IUCV_LISTEN)
		return iucv_accept_poll(sk);

	if (sk->sk_err || !skb_queue_empty(&sk->sk_error_queue))
		mask |= POLLERR;

	if (sk->sk_shutdown & RCV_SHUTDOWN)
		mask |= POLLRDHUP;

	if (sk->sk_shutdown == SHUTDOWN_MASK)
		mask |= POLLHUP;

	if (!skb_queue_empty(&sk->sk_receive_queue) ||
1157
	    (sk->sk_shutdown & RCV_SHUTDOWN))
1158 1159 1160 1161 1162
		mask |= POLLIN | POLLRDNORM;

	if (sk->sk_state == IUCV_CLOSED)
		mask |= POLLHUP;

1163 1164 1165
	if (sk->sk_state == IUCV_DISCONN || sk->sk_state == IUCV_SEVERED)
		mask |= POLLIN;

1166 1167 1168 1169 1170 1171 1172 1173 1174 1175 1176 1177 1178 1179 1180 1181 1182 1183 1184 1185 1186
	if (sock_writeable(sk))
		mask |= POLLOUT | POLLWRNORM | POLLWRBAND;
	else
		set_bit(SOCK_ASYNC_NOSPACE, &sk->sk_socket->flags);

	return mask;
}

static int iucv_sock_shutdown(struct socket *sock, int how)
{
	struct sock *sk = sock->sk;
	struct iucv_sock *iucv = iucv_sk(sk);
	struct iucv_message txmsg;
	int err = 0;

	how++;

	if ((how & ~SHUTDOWN_MASK) || !how)
		return -EINVAL;

	lock_sock(sk);
1187
	switch (sk->sk_state) {
1188 1189 1190
	case IUCV_DISCONN:
	case IUCV_CLOSING:
	case IUCV_SEVERED:
1191 1192 1193 1194 1195 1196 1197 1198 1199 1200 1201 1202 1203
	case IUCV_CLOSED:
		err = -ENOTCONN;
		goto fail;

	default:
		sk->sk_shutdown |= how;
		break;
	}

	if (how == SEND_SHUTDOWN || how == SHUTDOWN_MASK) {
		txmsg.class = 0;
		txmsg.tag = 0;
		err = iucv_message_send(iucv->path, &txmsg, IUCV_IPRMDATA, 0,
1204
					(void *) iprm_shutdown, 8);
1205
		if (err) {
1206
			switch (err) {
1207 1208 1209 1210 1211 1212 1213 1214 1215 1216 1217 1218 1219 1220 1221 1222 1223 1224 1225 1226 1227 1228 1229 1230 1231 1232 1233 1234 1235 1236 1237 1238 1239 1240 1241 1242 1243 1244 1245 1246 1247 1248 1249 1250 1251 1252 1253 1254 1255 1256 1257
			case 1:
				err = -ENOTCONN;
				break;
			case 2:
				err = -ECONNRESET;
				break;
			default:
				err = -ENOTCONN;
				break;
			}
		}
	}

	if (how == RCV_SHUTDOWN || how == SHUTDOWN_MASK) {
		err = iucv_path_quiesce(iucv_sk(sk)->path, NULL);
		if (err)
			err = -ENOTCONN;

		skb_queue_purge(&sk->sk_receive_queue);
	}

	/* Wake up anyone sleeping in poll */
	sk->sk_state_change(sk);

fail:
	release_sock(sk);
	return err;
}

static int iucv_sock_release(struct socket *sock)
{
	struct sock *sk = sock->sk;
	int err = 0;

	if (!sk)
		return 0;

	iucv_sock_close(sk);

	/* Unregister with IUCV base support */
	if (iucv_sk(sk)->path) {
		iucv_path_sever(iucv_sk(sk)->path, NULL);
		iucv_path_free(iucv_sk(sk)->path);
		iucv_sk(sk)->path = NULL;
	}

	sock_orphan(sk);
	iucv_sock_kill(sk);
	return err;
}

1258 1259 1260 1261 1262 1263 1264 1265 1266 1267 1268 1269 1270 1271 1272 1273 1274 1275 1276 1277 1278 1279 1280 1281 1282 1283 1284 1285
/* getsockopt and setsockopt */
static int iucv_sock_setsockopt(struct socket *sock, int level, int optname,
				char __user *optval, int optlen)
{
	struct sock *sk = sock->sk;
	struct iucv_sock *iucv = iucv_sk(sk);
	int val;
	int rc;

	if (level != SOL_IUCV)
		return -ENOPROTOOPT;

	if (optlen < sizeof(int))
		return -EINVAL;

	if (get_user(val, (int __user *) optval))
		return -EFAULT;

	rc = 0;

	lock_sock(sk);
	switch (optname) {
	case SO_IPRMDATA_MSG:
		if (val)
			iucv->flags |= IUCV_IPRMDATA;
		else
			iucv->flags &= ~IUCV_IPRMDATA;
		break;
1286 1287 1288 1289 1290 1291 1292 1293 1294 1295 1296 1297 1298 1299
	case SO_MSGLIMIT:
		switch (sk->sk_state) {
		case IUCV_OPEN:
		case IUCV_BOUND:
			if (val < 1 || val > (u16)(~0))
				rc = -EINVAL;
			else
				iucv->msglimit = val;
			break;
		default:
			rc = -EINVAL;
			break;
		}
		break;
1300 1301 1302 1303 1304 1305 1306 1307 1308 1309 1310 1311 1312 1313 1314 1315 1316 1317 1318 1319 1320 1321 1322 1323 1324 1325 1326 1327 1328 1329 1330
	default:
		rc = -ENOPROTOOPT;
		break;
	}
	release_sock(sk);

	return rc;
}

static int iucv_sock_getsockopt(struct socket *sock, int level, int optname,
				char __user *optval, int __user *optlen)
{
	struct sock *sk = sock->sk;
	struct iucv_sock *iucv = iucv_sk(sk);
	int val, len;

	if (level != SOL_IUCV)
		return -ENOPROTOOPT;

	if (get_user(len, optlen))
		return -EFAULT;

	if (len < 0)
		return -EINVAL;

	len = min_t(unsigned int, len, sizeof(int));

	switch (optname) {
	case SO_IPRMDATA_MSG:
		val = (iucv->flags & IUCV_IPRMDATA) ? 1 : 0;
		break;
1331 1332 1333 1334 1335 1336
	case SO_MSGLIMIT:
		lock_sock(sk);
		val = (iucv->path != NULL) ? iucv->path->msglim	/* connected */
					   : iucv->msglimit;	/* default */
		release_sock(sk);
		break;
1337 1338 1339 1340 1341 1342 1343 1344 1345 1346 1347 1348 1349
	default:
		return -ENOPROTOOPT;
	}

	if (put_user(len, optlen))
		return -EFAULT;
	if (copy_to_user(optval, &val, len))
		return -EFAULT;

	return 0;
}


1350 1351 1352 1353 1354 1355 1356 1357 1358 1359 1360 1361 1362 1363 1364 1365 1366
/* Callback wrappers - called from iucv base support */
static int iucv_callback_connreq(struct iucv_path *path,
				 u8 ipvmid[8], u8 ipuser[16])
{
	unsigned char user_data[16];
	unsigned char nuser_data[16];
	unsigned char src_name[8];
	struct hlist_node *node;
	struct sock *sk, *nsk;
	struct iucv_sock *iucv, *niucv;
	int err;

	memcpy(src_name, ipuser, 8);
	EBCASC(src_name, 8);
	/* Find out if this path belongs to af_iucv. */
	read_lock(&iucv_sk_list.lock);
	iucv = NULL;
1367
	sk = NULL;
1368 1369 1370 1371 1372 1373 1374 1375 1376 1377 1378 1379 1380 1381 1382 1383 1384 1385 1386 1387 1388 1389 1390
	sk_for_each(sk, node, &iucv_sk_list.head)
		if (sk->sk_state == IUCV_LISTEN &&
		    !memcmp(&iucv_sk(sk)->src_name, src_name, 8)) {
			/*
			 * Found a listening socket with
			 * src_name == ipuser[0-7].
			 */
			iucv = iucv_sk(sk);
			break;
		}
	read_unlock(&iucv_sk_list.lock);
	if (!iucv)
		/* No socket found, not one of our paths. */
		return -EINVAL;

	bh_lock_sock(sk);

	/* Check if parent socket is listening */
	low_nmcpy(user_data, iucv->src_name);
	high_nmcpy(user_data, iucv->dst_name);
	ASCEBC(user_data, sizeof(user_data));
	if (sk->sk_state != IUCV_LISTEN) {
		err = iucv_path_sever(path, user_data);
1391
		iucv_path_free(path);
1392 1393 1394 1395 1396 1397
		goto fail;
	}

	/* Check for backlog size */
	if (sk_acceptq_is_full(sk)) {
		err = iucv_path_sever(path, user_data);
1398
		iucv_path_free(path);
1399 1400 1401 1402
		goto fail;
	}

	/* Create the new socket */
1403
	nsk = iucv_sock_alloc(NULL, sk->sk_type, GFP_ATOMIC);
1404
	if (!nsk) {
1405
		err = iucv_path_sever(path, user_data);
1406
		iucv_path_free(path);
1407 1408 1409 1410 1411 1412 1413 1414 1415 1416 1417 1418 1419 1420 1421 1422 1423 1424 1425
		goto fail;
	}

	niucv = iucv_sk(nsk);
	iucv_sock_init(nsk, sk);

	/* Set the new iucv_sock */
	memcpy(niucv->dst_name, ipuser + 8, 8);
	EBCASC(niucv->dst_name, 8);
	memcpy(niucv->dst_user_id, ipvmid, 8);
	memcpy(niucv->src_name, iucv->src_name, 8);
	memcpy(niucv->src_user_id, iucv->src_user_id, 8);
	niucv->path = path;

	/* Call iucv_accept */
	high_nmcpy(nuser_data, ipuser + 8);
	memcpy(nuser_data + 8, niucv->src_name, 8);
	ASCEBC(nuser_data + 8, 8);

1426 1427 1428
	/* set message limit for path based on msglimit of accepting socket */
	niucv->msglimit = iucv->msglimit;
	path->msglim = iucv->msglimit;
1429
	err = iucv_path_accept(path, &af_iucv_handler, nuser_data, nsk);
1430
	if (err) {
1431
		err = iucv_path_sever(path, user_data);
1432 1433
		iucv_path_free(path);
		iucv_sock_kill(nsk);
1434 1435 1436 1437 1438 1439 1440 1441 1442 1443 1444 1445 1446 1447 1448 1449 1450 1451 1452 1453 1454 1455 1456 1457 1458
		goto fail;
	}

	iucv_accept_enqueue(sk, nsk);

	/* Wake up accept */
	nsk->sk_state = IUCV_CONNECTED;
	sk->sk_data_ready(sk, 1);
	err = 0;
fail:
	bh_unlock_sock(sk);
	return 0;
}

static void iucv_callback_connack(struct iucv_path *path, u8 ipuser[16])
{
	struct sock *sk = path->private;

	sk->sk_state = IUCV_CONNECTED;
	sk->sk_state_change(sk);
}

static void iucv_callback_rx(struct iucv_path *path, struct iucv_message *msg)
{
	struct sock *sk = path->private;
1459
	struct iucv_sock *iucv = iucv_sk(sk);
1460 1461 1462
	struct sk_buff *skb;
	struct sock_msg_q *save_msg;
	int len;
1463

1464 1465
	if (sk->sk_shutdown & RCV_SHUTDOWN) {
		iucv_message_reject(path, msg);
1466
		return;
1467
	}
1468

1469
	spin_lock(&iucv->message_q.lock);
1470

1471 1472 1473 1474 1475
	if (!list_empty(&iucv->message_q.list) ||
	    !skb_queue_empty(&iucv->backlog_skb_q))
		goto save_message;

	len = atomic_read(&sk->sk_rmem_alloc);
1476
	len += iucv_msg_length(msg) + sizeof(struct sk_buff);
1477 1478 1479
	if (len > sk->sk_rcvbuf)
		goto save_message;

1480
	skb = alloc_skb(iucv_msg_length(msg), GFP_ATOMIC | GFP_DMA);
1481 1482
	if (!skb)
		goto save_message;
1483

1484
	iucv_process_message(sk, skb, path, msg);
1485
	goto out_unlock;
1486

1487 1488
save_message:
	save_msg = kzalloc(sizeof(struct sock_msg_q), GFP_ATOMIC | GFP_DMA);
1489 1490
	if (!save_msg)
		return;
1491 1492
	save_msg->path = path;
	save_msg->msg = *msg;
1493

1494
	list_add_tail(&save_msg->list, &iucv->message_q.list);
1495 1496

out_unlock:
1497
	spin_unlock(&iucv->message_q.lock);
1498 1499 1500 1501 1502 1503
}

static void iucv_callback_txdone(struct iucv_path *path,
				 struct iucv_message *msg)
{
	struct sock *sk = path->private;
1504
	struct sk_buff *this = NULL;
1505 1506 1507 1508
	struct sk_buff_head *list = &iucv_sk(sk)->send_skb_q;
	struct sk_buff *list_skb = list->next;
	unsigned long flags;

1509
	if (!skb_queue_empty(list)) {
1510 1511
		spin_lock_irqsave(&list->lock, flags);

1512
		while (list_skb != (struct sk_buff *)list) {
1513
			if (!memcmp(&msg->tag, CB_TAG(list_skb), CB_TAG_LEN)) {
1514 1515 1516
				this = list_skb;
				break;
			}
1517
			list_skb = list_skb->next;
1518 1519 1520
		}
		if (this)
			__skb_unlink(this, list);
1521 1522

		spin_unlock_irqrestore(&list->lock, flags);
1523

1524 1525 1526 1527 1528
		if (this) {
			kfree_skb(this);
			/* wake up any process waiting for sending */
			iucv_sock_wake_msglim(sk);
		}
1529
	}
1530
	BUG_ON(!this);
1531

1532
	if (sk->sk_state == IUCV_CLOSING) {
1533 1534 1535 1536 1537
		if (skb_queue_empty(&iucv_sk(sk)->send_skb_q)) {
			sk->sk_state = IUCV_CLOSED;
			sk->sk_state_change(sk);
		}
	}
1538 1539 1540 1541 1542 1543 1544 1545 1546 1547 1548 1549 1550 1551 1552

}

static void iucv_callback_connrej(struct iucv_path *path, u8 ipuser[16])
{
	struct sock *sk = path->private;

	if (!list_empty(&iucv_sk(sk)->accept_q))
		sk->sk_state = IUCV_SEVERED;
	else
		sk->sk_state = IUCV_DISCONN;

	sk->sk_state_change(sk);
}

1553 1554 1555 1556 1557 1558 1559 1560 1561 1562 1563 1564 1565 1566 1567
/* called if the other communication side shuts down its RECV direction;
 * in turn, the callback sets SEND_SHUTDOWN to disable sending of data.
 */
static void iucv_callback_shutdown(struct iucv_path *path, u8 ipuser[16])
{
	struct sock *sk = path->private;

	bh_lock_sock(sk);
	if (sk->sk_state != IUCV_CLOSED) {
		sk->sk_shutdown |= SEND_SHUTDOWN;
		sk->sk_state_change(sk);
	}
	bh_unlock_sock(sk);
}

1568 1569 1570 1571 1572 1573 1574 1575 1576 1577 1578 1579 1580 1581 1582 1583
static struct proto_ops iucv_sock_ops = {
	.family		= PF_IUCV,
	.owner		= THIS_MODULE,
	.release	= iucv_sock_release,
	.bind		= iucv_sock_bind,
	.connect	= iucv_sock_connect,
	.listen		= iucv_sock_listen,
	.accept		= iucv_sock_accept,
	.getname	= iucv_sock_getname,
	.sendmsg	= iucv_sock_sendmsg,
	.recvmsg	= iucv_sock_recvmsg,
	.poll		= iucv_sock_poll,
	.ioctl		= sock_no_ioctl,
	.mmap		= sock_no_mmap,
	.socketpair	= sock_no_socketpair,
	.shutdown	= iucv_sock_shutdown,
1584 1585
	.setsockopt	= iucv_sock_setsockopt,
	.getsockopt	= iucv_sock_getsockopt,
1586 1587 1588 1589 1590 1591 1592 1593
};

static struct net_proto_family iucv_sock_family_ops = {
	.family	= AF_IUCV,
	.owner	= THIS_MODULE,
	.create	= iucv_sock_create,
};

1594
static int __init afiucv_init(void)
1595 1596 1597 1598
{
	int err;

	if (!MACHINE_IS_VM) {
1599 1600
		pr_err("The af_iucv module cannot be loaded"
		       " without z/VM\n");
1601 1602 1603 1604 1605
		err = -EPROTONOSUPPORT;
		goto out;
	}
	cpcmd("QUERY USERID", iucv_userid, sizeof(iucv_userid), &err);
	if (unlikely(err)) {
1606
		WARN_ON(err);
1607 1608 1609 1610 1611 1612 1613 1614 1615 1616 1617 1618 1619 1620 1621 1622 1623 1624 1625 1626 1627 1628 1629 1630 1631 1632 1633 1634 1635 1636 1637 1638 1639 1640 1641 1642 1643 1644
		err = -EPROTONOSUPPORT;
		goto out;
	}

	err = iucv_register(&af_iucv_handler, 0);
	if (err)
		goto out;
	err = proto_register(&iucv_proto, 0);
	if (err)
		goto out_iucv;
	err = sock_register(&iucv_sock_family_ops);
	if (err)
		goto out_proto;
	return 0;

out_proto:
	proto_unregister(&iucv_proto);
out_iucv:
	iucv_unregister(&af_iucv_handler, 0);
out:
	return err;
}

static void __exit afiucv_exit(void)
{
	sock_unregister(PF_IUCV);
	proto_unregister(&iucv_proto);
	iucv_unregister(&af_iucv_handler, 0);
}

module_init(afiucv_init);
module_exit(afiucv_exit);

MODULE_AUTHOR("Jennifer Hunt <jenhunt@us.ibm.com>");
MODULE_DESCRIPTION("IUCV Sockets ver " VERSION);
MODULE_VERSION(VERSION);
MODULE_LICENSE("GPL");
MODULE_ALIAS_NETPROTO(PF_IUCV);