pipe.c 27.8 KB
1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 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 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 321 322 323 324 325 326 327 328 329 330 331 332 333 334 335 336 337 338 339 340 341 342 343 344 345 346 347 348 349 350 351 352 353 354 355 356 357 358 359 360 361 362 363 364 365 366 367 368 369 370 371 372 373 374 375 376 377 378 379 380 381 382 383 384 385 386 387 388 389 390 391 392 393 394 395 396 397 398 399 400 401 402 403 404 405 406 407 408 409 410 411 412 413 414 415 416 417 418 419 420 421 422 423 424 425 426 427 428 429 430 431 432 433 434 435 436 437 438 439 440 441 442 443 444 445 446 447 448 449 450 451 452 453 454 455 456 457 458 459 460 461 462 463 464 465 466 467 468 469 470 471 472 473 474 475 476 477 478 479 480 481 482 483 484 485 486 487 488 489 490 491 492 493 494 495 496 497 498 499 500 501 502 503 504 505 506 507 508 509 510 511 512 513 514 515 516 517 518 519 520 521 522 523 524 525 526 527 528 529 530 531 532 533 534 535 536 537 538 539 540 541 542 543 544 545 546 547 548 549 550 551 552 553 554 555 556 557 558 559 560 561 562 563 564 565 566 567 568 569 570 571 572 573 574 575 576 577 578 579 580 581 582 583 584 585 586 587 588 589 590 591 592 593 594 595 596 597 598 599 600 601 602 603 604 605 606 607 608 609 610 611 612 613 614 615 616 617 618 619 620 621 622 623 624 625 626 627 628 629 630 631 632 633 634 635 636 637 638 639 640 641 642 643 644 645 646 647 648 649 650 651 652 653 654 655 656 657 658 659 660 661 662 663 664 665 666 667 668 669 670 671 672 673 674 675 676 677 678 679 680 681 682 683 684 685 686 687 688 689 690 691 692 693 694 695 696 697 698 699 700 701 702 703 704 705 706 707 708 709 710 711 712 713 714 715 716 717 718 719 720 721 722 723 724 725 726 727 728 729 730 731 732 733 734 735 736 737 738 739 740 741 742 743 744 745 746 747 748 749 750 751 752 753 754 755 756 757 758 759 760 761 762 763 764 765 766 767 768 769 770 771 772 773 774 775 776 777 778 779 780 781 782 783 784 785 786 787 788 789 790 791 792 793 794 795 796 797 798 799 800 801 802 803 804 805 806 807 808 809 810 811 812 813 814 815 816 817 818 819 820 821 822 823 824 825 826 827 828 829 830 831 832 833 834 835 836 837 838 839 840 841 842 843 844 845 846 847 848 849 850 851 852 853 854 855 856 857 858 859 860 861 862 863 864 865 866 867 868 869 870 871 872 873 874 875 876 877 878 879 880 881 882 883 884 885 886 887 888 889 890 891 892 893 894 895 896 897 898 899 900 901 902 903 904 905 906 907 908 909 910 911 912 913 914 915 916 917 918 919 920 921 922 923 924 925 926 927 928 929 930 931 932 933 934 935 936 937 938 939 940 941 942 943 944 945 946 947 948 949 950 951 952 953 954 955 956 957 958 959 960 961 962 963 964 965 966 967 968 969 970 971 972 973 974 975 976 977 978 979 980 981 982 983 984 985 986 987 988 989 990 991 992 993 994 995 996 997 998 999 1000 1001 1002 1003 1004 1005 1006 1007 1008 1009 1010 1011 1012 1013 1014 1015 1016 1017 1018 1019 1020 1021 1022 1023 1024 1025 1026 1027 1028 1029 1030 1031 1032 1033 1034 1035 1036 1037 1038 1039 1040 1041 1042 1043 1044 1045 1046 1047 1048 1049 1050 1051 1052 1053 1054 1055 1056 1057 1058 1059 1060 1061 1062 1063 1064 1065 1066 1067 1068 1069 1070 1071 1072 1073 1074 1075 1076 1077 1078 1079 1080 1081 1082 1083 1084 1085 1086 1087 1088 1089 1090 1091 1092 1093 1094 1095 1096 1097 1098 1099 1100 1101 1102 1103 1104 1105 1106 1107 1108 1109 1110 1111 1112 1113 1114 1115 1116 1117 1118 1119 1120 1121 1122 1123 1124 1125 1126 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 1157 1158 1159 1160 1161 1162 1163 1164 1165 1166 1167 1168 1169 1170 1171 1172 1173 1174 1175 1176 1177 1178 1179 1180 1181 1182 1183 1184 1185 1186 1187 1188 1189 1190 1191 1192 1193 1194 1195 1196 1197 1198 1199 1200 1201 1202 1203 1204 1205 1206 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 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
/*
 *  linux/fs/pipe.c
 *
 *  Copyright (C) 1991, 1992, 1999  Linus Torvalds
 */

#include <linux/mm.h>
#include <linux/file.h>
#include <linux/poll.h>
#include <linux/slab.h>
#include <linux/module.h>
#include <linux/init.h>
#include <linux/fs.h>
#include <linux/log2.h>
#include <linux/mount.h>
#include <linux/pipe_fs_i.h>
#include <linux/uio.h>
#include <linux/highmem.h>
#include <linux/pagemap.h>
#include <linux/audit.h>
#include <linux/syscalls.h>
#include <linux/fcntl.h>

#include <asm/uaccess.h>
#include <asm/ioctls.h>

/*
 * The max size that a non-root user is allowed to grow the pipe. Can
 * be set by root in /proc/sys/fs/pipe-max-size
 */
unsigned int pipe_max_size = 1048576;

/*
 * Minimum pipe size, as required by POSIX
 */
unsigned int pipe_min_size = PAGE_SIZE;

/*
 * We use a start+len construction, which provides full use of the 
 * allocated memory.
 * -- Florian Coosmann (FGC)
 * 
 * Reads with count = 0 should always return 0.
 * -- Julian Bradfield 1999-06-07.
 *
 * FIFOs and Pipes now generate SIGIO for both readers and writers.
 * -- Jeremy Elson <jelson@circlemud.org> 2001-08-16
 *
 * pipe_read & write cleanup
 * -- Manfred Spraul <manfred@colorfullife.com> 2002-05-09
 */

static void pipe_lock_nested(struct pipe_inode_info *pipe, int subclass)
{
	if (pipe->inode)
		mutex_lock_nested(&pipe->inode->i_mutex, subclass);
}

void pipe_lock(struct pipe_inode_info *pipe)
{
	/*
	 * pipe_lock() nests non-pipe inode locks (for writing to a file)
	 */
	pipe_lock_nested(pipe, I_MUTEX_PARENT);
}
EXPORT_SYMBOL(pipe_lock);

void pipe_unlock(struct pipe_inode_info *pipe)
{
	if (pipe->inode)
		mutex_unlock(&pipe->inode->i_mutex);
}
EXPORT_SYMBOL(pipe_unlock);

void pipe_double_lock(struct pipe_inode_info *pipe1,
		      struct pipe_inode_info *pipe2)
{
	BUG_ON(pipe1 == pipe2);

	if (pipe1 < pipe2) {
		pipe_lock_nested(pipe1, I_MUTEX_PARENT);
		pipe_lock_nested(pipe2, I_MUTEX_CHILD);
	} else {
		pipe_lock_nested(pipe2, I_MUTEX_PARENT);
		pipe_lock_nested(pipe1, I_MUTEX_CHILD);
	}
}

/* Drop the inode semaphore and wait for a pipe event, atomically */
void pipe_wait(struct pipe_inode_info *pipe)
{
	DEFINE_WAIT(wait);

	/*
	 * Pipes are system-local resources, so sleeping on them
	 * is considered a noninteractive wait:
	 */
	prepare_to_wait(&pipe->wait, &wait, TASK_INTERRUPTIBLE);
	pipe_unlock(pipe);
	schedule();
	finish_wait(&pipe->wait, &wait);
	pipe_lock(pipe);
}

static int
pipe_iov_copy_from_user(void *to, struct iovec *iov, unsigned long len,
			int atomic)
{
	unsigned long copy;

	while (len > 0) {
		while (!iov->iov_len)
			iov++;
		copy = min_t(unsigned long, len, iov->iov_len);

		if (atomic) {
			if (__copy_from_user_inatomic(to, iov->iov_base, copy))
				return -EFAULT;
		} else {
			if (copy_from_user(to, iov->iov_base, copy))
				return -EFAULT;
		}
		to += copy;
		len -= copy;
		iov->iov_base += copy;
		iov->iov_len -= copy;
	}
	return 0;
}

static int
pipe_iov_copy_to_user(struct iovec *iov, const void *from, unsigned long len,
		      int atomic)
{
	unsigned long copy;

	while (len > 0) {
		while (!iov->iov_len)
			iov++;
		copy = min_t(unsigned long, len, iov->iov_len);

		if (atomic) {
			if (__copy_to_user_inatomic(iov->iov_base, from, copy))
				return -EFAULT;
		} else {
			if (copy_to_user(iov->iov_base, from, copy))
				return -EFAULT;
		}
		from += copy;
		len -= copy;
		iov->iov_base += copy;
		iov->iov_len -= copy;
	}
	return 0;
}

/*
 * Attempt to pre-fault in the user memory, so we can use atomic copies.
 * Returns the number of bytes not faulted in.
 */
static int iov_fault_in_pages_write(struct iovec *iov, unsigned long len)
{
	while (!iov->iov_len)
		iov++;

	while (len > 0) {
		unsigned long this_len;

		this_len = min_t(unsigned long, len, iov->iov_len);
		if (fault_in_pages_writeable(iov->iov_base, this_len))
			break;

		len -= this_len;
		iov++;
	}

	return len;
}

/*
 * Pre-fault in the user memory, so we can use atomic copies.
 */
static void iov_fault_in_pages_read(struct iovec *iov, unsigned long len)
{
	while (!iov->iov_len)
		iov++;

	while (len > 0) {
		unsigned long this_len;

		this_len = min_t(unsigned long, len, iov->iov_len);
		fault_in_pages_readable(iov->iov_base, this_len);
		len -= this_len;
		iov++;
	}
}

static void anon_pipe_buf_release(struct pipe_inode_info *pipe,
				  struct pipe_buffer *buf)
{
	struct page *page = buf->page;

	/*
	 * If nobody else uses this page, and we don't already have a
	 * temporary page, let's keep track of it as a one-deep
	 * allocation cache. (Otherwise just release our reference to it)
	 */
	if (page_count(page) == 1 && !pipe->tmp_page)
		pipe->tmp_page = page;
	else
		page_cache_release(page);
}

/**
 * generic_pipe_buf_map - virtually map a pipe buffer
 * @pipe:	the pipe that the buffer belongs to
 * @buf:	the buffer that should be mapped
 * @atomic:	whether to use an atomic map
 *
 * Description:
 *	This function returns a kernel virtual address mapping for the
 *	pipe_buffer passed in @buf. If @atomic is set, an atomic map is provided
 *	and the caller has to be careful not to fault before calling
 *	the unmap function.
 *
 *	Note that this function occupies KM_USER0 if @atomic != 0.
 */
void *generic_pipe_buf_map(struct pipe_inode_info *pipe,
			   struct pipe_buffer *buf, int atomic)
{
	if (atomic) {
		buf->flags |= PIPE_BUF_FLAG_ATOMIC;
		return kmap_atomic(buf->page, KM_USER0);
	}

	return kmap(buf->page);
}
EXPORT_SYMBOL(generic_pipe_buf_map);

/**
 * generic_pipe_buf_unmap - unmap a previously mapped pipe buffer
 * @pipe:	the pipe that the buffer belongs to
 * @buf:	the buffer that should be unmapped
 * @map_data:	the data that the mapping function returned
 *
 * Description:
 *	This function undoes the mapping that ->map() provided.
 */
void generic_pipe_buf_unmap(struct pipe_inode_info *pipe,
			    struct pipe_buffer *buf, void *map_data)
{
	if (buf->flags & PIPE_BUF_FLAG_ATOMIC) {
		buf->flags &= ~PIPE_BUF_FLAG_ATOMIC;
		kunmap_atomic(map_data, KM_USER0);
	} else
		kunmap(buf->page);
}
EXPORT_SYMBOL(generic_pipe_buf_unmap);

/**
 * generic_pipe_buf_steal - attempt to take ownership of a &pipe_buffer
 * @pipe:	the pipe that the buffer belongs to
 * @buf:	the buffer to attempt to steal
 *
 * Description:
 *	This function attempts to steal the &struct page attached to
 *	@buf. If successful, this function returns 0 and returns with
 *	the page locked. The caller may then reuse the page for whatever
 *	he wishes; the typical use is insertion into a different file
 *	page cache.
 */
int generic_pipe_buf_steal(struct pipe_inode_info *pipe,
			   struct pipe_buffer *buf)
{
	struct page *page = buf->page;

	/*
	 * A reference of one is golden, that means that the owner of this
	 * page is the only one holding a reference to it. lock the page
	 * and return OK.
	 */
	if (page_count(page) == 1) {
		lock_page(page);
		return 0;
	}

	return 1;
}
EXPORT_SYMBOL(generic_pipe_buf_steal);

/**
 * generic_pipe_buf_get - get a reference to a &struct pipe_buffer
 * @pipe:	the pipe that the buffer belongs to
 * @buf:	the buffer to get a reference to
 *
 * Description:
 *	This function grabs an extra reference to @buf. It's used in
 *	in the tee() system call, when we duplicate the buffers in one
 *	pipe into another.
 */
void generic_pipe_buf_get(struct pipe_inode_info *pipe, struct pipe_buffer *buf)
{
	page_cache_get(buf->page);
}
EXPORT_SYMBOL(generic_pipe_buf_get);

/**
 * generic_pipe_buf_confirm - verify contents of the pipe buffer
 * @info:	the pipe that the buffer belongs to
 * @buf:	the buffer to confirm
 *
 * Description:
 *	This function does nothing, because the generic pipe code uses
 *	pages that are always good when inserted into the pipe.
 */
int generic_pipe_buf_confirm(struct pipe_inode_info *info,
			     struct pipe_buffer *buf)
{
	return 0;
}
EXPORT_SYMBOL(generic_pipe_buf_confirm);

/**
 * generic_pipe_buf_release - put a reference to a &struct pipe_buffer
 * @pipe:	the pipe that the buffer belongs to
 * @buf:	the buffer to put a reference to
 *
 * Description:
 *	This function releases a reference to @buf.
 */
void generic_pipe_buf_release(struct pipe_inode_info *pipe,
			      struct pipe_buffer *buf)
{
	page_cache_release(buf->page);
}
EXPORT_SYMBOL(generic_pipe_buf_release);

static const struct pipe_buf_operations anon_pipe_buf_ops = {
	.can_merge = 1,
	.map = generic_pipe_buf_map,
	.unmap = generic_pipe_buf_unmap,
	.confirm = generic_pipe_buf_confirm,
	.release = anon_pipe_buf_release,
	.steal = generic_pipe_buf_steal,
	.get = generic_pipe_buf_get,
};

static ssize_t
pipe_read(struct kiocb *iocb, const struct iovec *_iov,
	   unsigned long nr_segs, loff_t pos)
{
	struct file *filp = iocb->ki_filp;
	struct inode *inode = filp->f_path.dentry->d_inode;
	struct pipe_inode_info *pipe;
	int do_wakeup;
	ssize_t ret;
	struct iovec *iov = (struct iovec *)_iov;
	size_t total_len;

	total_len = iov_length(iov, nr_segs);
	/* Null read succeeds. */
	if (unlikely(total_len == 0))
		return 0;

	do_wakeup = 0;
	ret = 0;
	mutex_lock(&inode->i_mutex);
	pipe = inode->i_pipe;
	for (;;) {
		int bufs = pipe->nrbufs;
		if (bufs) {
			int curbuf = pipe->curbuf;
			struct pipe_buffer *buf = pipe->bufs + curbuf;
			const struct pipe_buf_operations *ops = buf->ops;
			void *addr;
			size_t chars = buf->len;
			int error, atomic;

			if (chars > total_len)
				chars = total_len;

			error = ops->confirm(pipe, buf);
			if (error) {
				if (!ret)
					error = ret;
				break;
			}

			atomic = !iov_fault_in_pages_write(iov, chars);
redo:
			addr = ops->map(pipe, buf, atomic);
			error = pipe_iov_copy_to_user(iov, addr + buf->offset, chars, atomic);
			ops->unmap(pipe, buf, addr);
			if (unlikely(error)) {
				/*
				 * Just retry with the slow path if we failed.
				 */
				if (atomic) {
					atomic = 0;
					goto redo;
				}
				if (!ret)
					ret = error;
				break;
			}
			ret += chars;
			buf->offset += chars;
			buf->len -= chars;
			if (!buf->len) {
				buf->ops = NULL;
				ops->release(pipe, buf);
				curbuf = (curbuf + 1) & (pipe->buffers - 1);
				pipe->curbuf = curbuf;
				pipe->nrbufs = --bufs;
				do_wakeup = 1;
			}
			total_len -= chars;
			if (!total_len)
				break;	/* common path: read succeeded */
		}
		if (bufs)	/* More to do? */
			continue;
		if (!pipe->writers)
			break;
		if (!pipe->waiting_writers) {
			/* syscall merging: Usually we must not sleep
			 * if O_NONBLOCK is set, or if we got some data.
			 * But if a writer sleeps in kernel space, then
			 * we can wait for that data without violating POSIX.
			 */
			if (ret)
				break;
			if (filp->f_flags & O_NONBLOCK) {
				ret = -EAGAIN;
				break;
			}
		}
		if (signal_pending(current)) {
			if (!ret)
				ret = -ERESTARTSYS;
			break;
		}
		if (do_wakeup) {
			wake_up_interruptible_sync(&pipe->wait);
 			kill_fasync(&pipe->fasync_writers, SIGIO, POLL_OUT);
		}
		pipe_wait(pipe);
	}
	mutex_unlock(&inode->i_mutex);

	/* Signal writers asynchronously that there is more room. */
	if (do_wakeup) {
		wake_up_interruptible_sync(&pipe->wait);
		kill_fasync(&pipe->fasync_writers, SIGIO, POLL_OUT);
	}
	if (ret > 0)
		file_accessed(filp);
	return ret;
}

static ssize_t
pipe_write(struct kiocb *iocb, const struct iovec *_iov,
	    unsigned long nr_segs, loff_t ppos)
{
	struct file *filp = iocb->ki_filp;
	struct inode *inode = filp->f_path.dentry->d_inode;
	struct pipe_inode_info *pipe;
	ssize_t ret;
	int do_wakeup;
	struct iovec *iov = (struct iovec *)_iov;
	size_t total_len;
	ssize_t chars;

	total_len = iov_length(iov, nr_segs);
	/* Null write succeeds. */
	if (unlikely(total_len == 0))
		return 0;

	do_wakeup = 0;
	ret = 0;
	mutex_lock(&inode->i_mutex);
	pipe = inode->i_pipe;

	if (!pipe->readers) {
		send_sig(SIGPIPE, current, 0);
		ret = -EPIPE;
		goto out;
	}

	/* We try to merge small writes */
	chars = total_len & (PAGE_SIZE-1); /* size of the last buffer */
	if (pipe->nrbufs && chars != 0) {
		int lastbuf = (pipe->curbuf + pipe->nrbufs - 1) &
							(pipe->buffers - 1);
		struct pipe_buffer *buf = pipe->bufs + lastbuf;
		const struct pipe_buf_operations *ops = buf->ops;
		int offset = buf->offset + buf->len;

		if (ops->can_merge && offset + chars <= PAGE_SIZE) {
			int error, atomic = 1;
			void *addr;

			error = ops->confirm(pipe, buf);
			if (error)
				goto out;

			iov_fault_in_pages_read(iov, chars);
redo1:
			addr = ops->map(pipe, buf, atomic);
			error = pipe_iov_copy_from_user(offset + addr, iov,
							chars, atomic);
			ops->unmap(pipe, buf, addr);
			ret = error;
			do_wakeup = 1;
			if (error) {
				if (atomic) {
					atomic = 0;
					goto redo1;
				}
				goto out;
			}
			buf->len += chars;
			total_len -= chars;
			ret = chars;
			if (!total_len)
				goto out;
		}
	}

	for (;;) {
		int bufs;

		if (!pipe->readers) {
			send_sig(SIGPIPE, current, 0);
			if (!ret)
				ret = -EPIPE;
			break;
		}
		bufs = pipe->nrbufs;
		if (bufs < pipe->buffers) {
			int newbuf = (pipe->curbuf + bufs) & (pipe->buffers-1);
			struct pipe_buffer *buf = pipe->bufs + newbuf;
			struct page *page = pipe->tmp_page;
			char *src;
			int error, atomic = 1;

			if (!page) {
				page = alloc_page(GFP_HIGHUSER);
				if (unlikely(!page)) {
					ret = ret ? : -ENOMEM;
					break;
				}
				pipe->tmp_page = page;
			}
			/* Always wake up, even if the copy fails. Otherwise
			 * we lock up (O_NONBLOCK-)readers that sleep due to
			 * syscall merging.
			 * FIXME! Is this really true?
			 */
			do_wakeup = 1;
			chars = PAGE_SIZE;
			if (chars > total_len)
				chars = total_len;

			iov_fault_in_pages_read(iov, chars);
redo2:
			if (atomic)
				src = kmap_atomic(page, KM_USER0);
			else
				src = kmap(page);

			error = pipe_iov_copy_from_user(src, iov, chars,
							atomic);
			if (atomic)
				kunmap_atomic(src, KM_USER0);
			else
				kunmap(page);

			if (unlikely(error)) {
				if (atomic) {
					atomic = 0;
					goto redo2;
				}
				if (!ret)
					ret = error;
				break;
			}
			ret += chars;

			/* Insert it into the buffer array */
			buf->page = page;
			buf->ops = &anon_pipe_buf_ops;
			buf->offset = 0;
			buf->len = chars;
			pipe->nrbufs = ++bufs;
			pipe->tmp_page = NULL;

			total_len -= chars;
			if (!total_len)
				break;
		}
		if (bufs < pipe->buffers)
			continue;
		if (filp->f_flags & O_NONBLOCK) {
			if (!ret)
				ret = -EAGAIN;
			break;
		}
		if (signal_pending(current)) {
			if (!ret)
				ret = -ERESTARTSYS;
			break;
		}
		if (do_wakeup) {
			wake_up_interruptible_sync(&pipe->wait);
			kill_fasync(&pipe->fasync_readers, SIGIO, POLL_IN);
			do_wakeup = 0;
		}
		pipe->waiting_writers++;
		pipe_wait(pipe);
		pipe->waiting_writers--;
	}
out:
	mutex_unlock(&inode->i_mutex);
	if (do_wakeup) {
		wake_up_interruptible_sync(&pipe->wait);
		kill_fasync(&pipe->fasync_readers, SIGIO, POLL_IN);
	}
	if (ret > 0)
		file_update_time(filp);
	return ret;
}

static ssize_t
bad_pipe_r(struct file *filp, char __user *buf, size_t count, loff_t *ppos)
{
	return -EBADF;
}

static ssize_t
bad_pipe_w(struct file *filp, const char __user *buf, size_t count,
	   loff_t *ppos)
{
	return -EBADF;
}

static long pipe_ioctl(struct file *filp, unsigned int cmd, unsigned long arg)
{
	struct inode *inode = filp->f_path.dentry->d_inode;
	struct pipe_inode_info *pipe;
	int count, buf, nrbufs;

	switch (cmd) {
		case FIONREAD:
			mutex_lock(&inode->i_mutex);
			pipe = inode->i_pipe;
			count = 0;
			buf = pipe->curbuf;
			nrbufs = pipe->nrbufs;
			while (--nrbufs >= 0) {
				count += pipe->bufs[buf].len;
				buf = (buf+1) & (pipe->buffers - 1);
			}
			mutex_unlock(&inode->i_mutex);

			return put_user(count, (int __user *)arg);
		default:
			return -EINVAL;
	}
}

/* No kernel lock held - fine */
static unsigned int
pipe_poll(struct file *filp, poll_table *wait)
{
	unsigned int mask;
	struct inode *inode = filp->f_path.dentry->d_inode;
	struct pipe_inode_info *pipe = inode->i_pipe;
	int nrbufs;

	poll_wait(filp, &pipe->wait, wait);

	/* Reading only -- no need for acquiring the semaphore.  */
	nrbufs = pipe->nrbufs;
	mask = 0;
	if (filp->f_mode & FMODE_READ) {
		mask = (nrbufs > 0) ? POLLIN | POLLRDNORM : 0;
		if (!pipe->writers && filp->f_version != pipe->w_counter)
			mask |= POLLHUP;
	}

	if (filp->f_mode & FMODE_WRITE) {
		mask |= (nrbufs < pipe->buffers) ? POLLOUT | POLLWRNORM : 0;
		/*
		 * Most Unices do not set POLLERR for FIFOs but on Linux they
		 * behave exactly like pipes for poll().
		 */
		if (!pipe->readers)
			mask |= POLLERR;
	}

	return mask;
}

static int
pipe_release(struct inode *inode, int decr, int decw)
{
	struct pipe_inode_info *pipe;

	mutex_lock(&inode->i_mutex);
	pipe = inode->i_pipe;
	pipe->readers -= decr;
	pipe->writers -= decw;

	if (!pipe->readers && !pipe->writers) {
		free_pipe_info(inode);
	} else {
		wake_up_interruptible_sync(&pipe->wait);
		kill_fasync(&pipe->fasync_readers, SIGIO, POLL_IN);
		kill_fasync(&pipe->fasync_writers, SIGIO, POLL_OUT);
	}
	mutex_unlock(&inode->i_mutex);

	return 0;
}

static int
pipe_read_fasync(int fd, struct file *filp, int on)
{
	struct inode *inode = filp->f_path.dentry->d_inode;
	int retval;

	mutex_lock(&inode->i_mutex);
	retval = fasync_helper(fd, filp, on, &inode->i_pipe->fasync_readers);
	mutex_unlock(&inode->i_mutex);

	return retval;
}


static int
pipe_write_fasync(int fd, struct file *filp, int on)
{
	struct inode *inode = filp->f_path.dentry->d_inode;
	int retval;

	mutex_lock(&inode->i_mutex);
	retval = fasync_helper(fd, filp, on, &inode->i_pipe->fasync_writers);
	mutex_unlock(&inode->i_mutex);

	return retval;
}


static int
pipe_rdwr_fasync(int fd, struct file *filp, int on)
{
	struct inode *inode = filp->f_path.dentry->d_inode;
	struct pipe_inode_info *pipe = inode->i_pipe;
	int retval;

	mutex_lock(&inode->i_mutex);
	retval = fasync_helper(fd, filp, on, &pipe->fasync_readers);
	if (retval >= 0) {
		retval = fasync_helper(fd, filp, on, &pipe->fasync_writers);
		if (retval < 0) /* this can happen only if on == T */
			fasync_helper(-1, filp, 0, &pipe->fasync_readers);
	}
	mutex_unlock(&inode->i_mutex);
	return retval;
}


static int
pipe_read_release(struct inode *inode, struct file *filp)
{
	return pipe_release(inode, 1, 0);
}

static int
pipe_write_release(struct inode *inode, struct file *filp)
{
	return pipe_release(inode, 0, 1);
}

static int
pipe_rdwr_release(struct inode *inode, struct file *filp)
{
	int decr, decw;

	decr = (filp->f_mode & FMODE_READ) != 0;
	decw = (filp->f_mode & FMODE_WRITE) != 0;
	return pipe_release(inode, decr, decw);
}

static int
pipe_read_open(struct inode *inode, struct file *filp)
{
	int ret = -ENOENT;

	mutex_lock(&inode->i_mutex);

	if (inode->i_pipe) {
		ret = 0;
		inode->i_pipe->readers++;
	}

	mutex_unlock(&inode->i_mutex);

	return ret;
}

static int
pipe_write_open(struct inode *inode, struct file *filp)
{
	int ret = -ENOENT;

	mutex_lock(&inode->i_mutex);

	if (inode->i_pipe) {
		ret = 0;
		inode->i_pipe->writers++;
	}

	mutex_unlock(&inode->i_mutex);

	return ret;
}

static int
pipe_rdwr_open(struct inode *inode, struct file *filp)
{
	int ret = -ENOENT;

	mutex_lock(&inode->i_mutex);

	if (inode->i_pipe) {
		ret = 0;
		if (filp->f_mode & FMODE_READ)
			inode->i_pipe->readers++;
		if (filp->f_mode & FMODE_WRITE)
			inode->i_pipe->writers++;
	}

	mutex_unlock(&inode->i_mutex);

	return ret;
}

/*
 * The file_operations structs are not static because they
 * are also used in linux/fs/fifo.c to do operations on FIFOs.
 *
 * Pipes reuse fifos' file_operations structs.
 */
const struct file_operations read_pipefifo_fops = {
	.llseek		= no_llseek,
	.read		= do_sync_read,
	.aio_read	= pipe_read,
	.write		= bad_pipe_w,
	.poll		= pipe_poll,
	.unlocked_ioctl	= pipe_ioctl,
	.open		= pipe_read_open,
	.release	= pipe_read_release,
	.fasync		= pipe_read_fasync,
};

const struct file_operations write_pipefifo_fops = {
	.llseek		= no_llseek,
	.read		= bad_pipe_r,
	.write		= do_sync_write,
	.aio_write	= pipe_write,
	.poll		= pipe_poll,
	.unlocked_ioctl	= pipe_ioctl,
	.open		= pipe_write_open,
	.release	= pipe_write_release,
	.fasync		= pipe_write_fasync,
};

const struct file_operations rdwr_pipefifo_fops = {
	.llseek		= no_llseek,
	.read		= do_sync_read,
	.aio_read	= pipe_read,
	.write		= do_sync_write,
	.aio_write	= pipe_write,
	.poll		= pipe_poll,
	.unlocked_ioctl	= pipe_ioctl,
	.open		= pipe_rdwr_open,
	.release	= pipe_rdwr_release,
	.fasync		= pipe_rdwr_fasync,
};

struct pipe_inode_info * alloc_pipe_info(struct inode *inode)
{
	struct pipe_inode_info *pipe;

	pipe = kzalloc(sizeof(struct pipe_inode_info), GFP_KERNEL);
	if (pipe) {
		pipe->bufs = kzalloc(sizeof(struct pipe_buffer) * PIPE_DEF_BUFFERS, GFP_KERNEL);
		if (pipe->bufs) {
			init_waitqueue_head(&pipe->wait);
			pipe->r_counter = pipe->w_counter = 1;
			pipe->inode = inode;
			pipe->buffers = PIPE_DEF_BUFFERS;
			return pipe;
		}
		kfree(pipe);
	}

	return NULL;
}

void __free_pipe_info(struct pipe_inode_info *pipe)
{
	int i;

	for (i = 0; i < pipe->buffers; i++) {
		struct pipe_buffer *buf = pipe->bufs + i;
		if (buf->ops)
			buf->ops->release(pipe, buf);
	}
	if (pipe->tmp_page)
		__free_page(pipe->tmp_page);
	kfree(pipe->bufs);
	kfree(pipe);
}

void free_pipe_info(struct inode *inode)
{
	__free_pipe_info(inode->i_pipe);
	inode->i_pipe = NULL;
}

static struct vfsmount *pipe_mnt __read_mostly;

/*
 * pipefs_dname() is called from d_path().
 */
static char *pipefs_dname(struct dentry *dentry, char *buffer, int buflen)
{
	return dynamic_dname(dentry, buffer, buflen, "pipe:[%lu]",
				dentry->d_inode->i_ino);
}

static const struct dentry_operations pipefs_dentry_operations = {
	.d_dname	= pipefs_dname,
};

static struct inode * get_pipe_inode(void)
{
	struct inode *inode = new_inode(pipe_mnt->mnt_sb);
	struct pipe_inode_info *pipe;

	if (!inode)
		goto fail_inode;

	pipe = alloc_pipe_info(inode);
	if (!pipe)
		goto fail_iput;
	inode->i_pipe = pipe;

	pipe->readers = pipe->writers = 1;
	inode->i_fop = &rdwr_pipefifo_fops;

	/*
	 * Mark the inode dirty from the very beginning,
	 * that way it will never be moved to the dirty
	 * list because "mark_inode_dirty()" will think
	 * that it already _is_ on the dirty list.
	 */
	inode->i_state = I_DIRTY;
	inode->i_mode = S_IFIFO | S_IRUSR | S_IWUSR;
	inode->i_uid = current_fsuid();
	inode->i_gid = current_fsgid();
	inode->i_atime = inode->i_mtime = inode->i_ctime = CURRENT_TIME;

	return inode;

fail_iput:
	iput(inode);

fail_inode:
	return NULL;
}

struct file *create_write_pipe(int flags)
{
	int err;
	struct inode *inode;
	struct file *f;
	struct path path;
	struct qstr name = { .name = "" };

	err = -ENFILE;
	inode = get_pipe_inode();
	if (!inode)
		goto err;

	err = -ENOMEM;
	path.dentry = d_alloc(pipe_mnt->mnt_sb->s_root, &name);
	if (!path.dentry)
		goto err_inode;
	path.mnt = mntget(pipe_mnt);

	path.dentry->d_op = &pipefs_dentry_operations;
	d_instantiate(path.dentry, inode);

	err = -ENFILE;
	f = alloc_file(&path, FMODE_WRITE, &write_pipefifo_fops);
	if (!f)
		goto err_dentry;
	f->f_mapping = inode->i_mapping;

	f->f_flags = O_WRONLY | (flags & O_NONBLOCK);
	f->f_version = 0;

	return f;

 err_dentry:
	free_pipe_info(inode);
	path_put(&path);
	return ERR_PTR(err);

 err_inode:
	free_pipe_info(inode);
	iput(inode);
 err:
	return ERR_PTR(err);
}

void free_write_pipe(struct file *f)
{
	free_pipe_info(f->f_dentry->d_inode);
	path_put(&f->f_path);
	put_filp(f);
}

struct file *create_read_pipe(struct file *wrf, int flags)
{
	/* Grab pipe from the writer */
	struct file *f = alloc_file(&wrf->f_path, FMODE_READ,
				    &read_pipefifo_fops);
	if (!f)
		return ERR_PTR(-ENFILE);

	path_get(&wrf->f_path);
	f->f_flags = O_RDONLY | (flags & O_NONBLOCK);

	return f;
}

int do_pipe_flags(int *fd, int flags)
{
	struct file *fw, *fr;
	int error;
	int fdw, fdr;

	if (flags & ~(O_CLOEXEC | O_NONBLOCK))
		return -EINVAL;

	fw = create_write_pipe(flags);
	if (IS_ERR(fw))
		return PTR_ERR(fw);
	fr = create_read_pipe(fw, flags);
	error = PTR_ERR(fr);
	if (IS_ERR(fr))
		goto err_write_pipe;

	error = get_unused_fd_flags(flags);
	if (error < 0)
		goto err_read_pipe;
	fdr = error;

	error = get_unused_fd_flags(flags);
	if (error < 0)
		goto err_fdr;
	fdw = error;

	audit_fd_pair(fdr, fdw);
	fd_install(fdr, fr);
	fd_install(fdw, fw);
	fd[0] = fdr;
	fd[1] = fdw;

	return 0;

 err_fdr:
	put_unused_fd(fdr);
 err_read_pipe:
	path_put(&fr->f_path);
	put_filp(fr);
 err_write_pipe:
	free_write_pipe(fw);
	return error;
}

/*
 * sys_pipe() is the normal C calling standard for creating
 * a pipe. It's not the way Unix traditionally does this, though.
 */
SYSCALL_DEFINE2(pipe2, int __user *, fildes, int, flags)
{
	int fd[2];
	int error;

	error = do_pipe_flags(fd, flags);
	if (!error) {
		if (copy_to_user(fildes, fd, sizeof(fd))) {
			sys_close(fd[0]);
			sys_close(fd[1]);
			error = -EFAULT;
		}
	}
	return error;
}

SYSCALL_DEFINE1(pipe, int __user *, fildes)
{
	return sys_pipe2(fildes, 0);
}

/*
 * Allocate a new array of pipe buffers and copy the info over. Returns the
 * pipe size if successful, or return -ERROR on error.
 */
static long pipe_set_size(struct pipe_inode_info *pipe, unsigned long nr_pages)
{
	struct pipe_buffer *bufs;

	/*
	 * We can shrink the pipe, if arg >= pipe->nrbufs. Since we don't
	 * expect a lot of shrink+grow operations, just free and allocate
	 * again like we would do for growing. If the pipe currently
	 * contains more buffers than arg, then return busy.
	 */
	if (nr_pages < pipe->nrbufs)
		return -EBUSY;

	bufs = kcalloc(nr_pages, sizeof(struct pipe_buffer), GFP_KERNEL);
	if (unlikely(!bufs))
		return -ENOMEM;

	/*
	 * The pipe array wraps around, so just start the new one at zero
	 * and adjust the indexes.
	 */
	if (pipe->nrbufs) {
		unsigned int tail;
		unsigned int head;

		tail = pipe->curbuf + pipe->nrbufs;
		if (tail < pipe->buffers)
			tail = 0;
		else
			tail &= (pipe->buffers - 1);

		head = pipe->nrbufs - tail;
		if (head)
			memcpy(bufs, pipe->bufs + pipe->curbuf, head * sizeof(struct pipe_buffer));
		if (tail)
			memcpy(bufs + head, pipe->bufs, tail * sizeof(struct pipe_buffer));
	}

	pipe->curbuf = 0;
	kfree(pipe->bufs);
	pipe->bufs = bufs;
	pipe->buffers = nr_pages;
	return nr_pages * PAGE_SIZE;
}

/*
 * Currently we rely on the pipe array holding a power-of-2 number
 * of pages.
 */
static inline unsigned int round_pipe_size(unsigned int size)
{
	unsigned long nr_pages;

	nr_pages = (size + PAGE_SIZE - 1) >> PAGE_SHIFT;
	return roundup_pow_of_two(nr_pages) << PAGE_SHIFT;
}

/*
 * This should work even if CONFIG_PROC_FS isn't set, as proc_dointvec_minmax
 * will return an error.
 */
int pipe_proc_fn(struct ctl_table *table, int write, void __user *buf,
		 size_t *lenp, loff_t *ppos)
{
	int ret;

	ret = proc_dointvec_minmax(table, write, buf, lenp, ppos);
	if (ret < 0 || !write)
		return ret;

	pipe_max_size = round_pipe_size(pipe_max_size);
	return ret;
}

long pipe_fcntl(struct file *file, unsigned int cmd, unsigned long arg)
{
	struct pipe_inode_info *pipe;
	long ret;

	pipe = file->f_path.dentry->d_inode->i_pipe;
	if (!pipe)
		return -EBADF;

	mutex_lock(&pipe->inode->i_mutex);

	switch (cmd) {
	case F_SETPIPE_SZ: {
		unsigned int size, nr_pages;

		size = round_pipe_size(arg);
		nr_pages = size >> PAGE_SHIFT;

		ret = -EINVAL;
		if (!nr_pages)
			goto out;

		if (!capable(CAP_SYS_RESOURCE) && size > pipe_max_size) {
			ret = -EPERM;
			goto out;
		}
		ret = pipe_set_size(pipe, nr_pages);
		break;
		}
	case F_GETPIPE_SZ:
		ret = pipe->buffers * PAGE_SIZE;
		break;
	default:
		ret = -EINVAL;
		break;
	}

out:
	mutex_unlock(&pipe->inode->i_mutex);
	return ret;
}

/*
 * pipefs should _never_ be mounted by userland - too much of security hassle,
 * no real gain from having the whole whorehouse mounted. So we don't need
 * any operations on the root directory. However, we need a non-trivial
 * d_name - pipe: will go nicely and kill the special-casing in procfs.
 */
static int pipefs_get_sb(struct file_system_type *fs_type,
			 int flags, const char *dev_name, void *data,
			 struct vfsmount *mnt)
{
	return get_sb_pseudo(fs_type, "pipe:", NULL, PIPEFS_MAGIC, mnt);
}

static struct file_system_type pipe_fs_type = {
	.name		= "pipefs",
	.get_sb		= pipefs_get_sb,
	.kill_sb	= kill_anon_super,
};

static int __init init_pipe_fs(void)
{
	int err = register_filesystem(&pipe_fs_type);

	if (!err) {
		pipe_mnt = kern_mount(&pipe_fs_type);
		if (IS_ERR(pipe_mnt)) {
			err = PTR_ERR(pipe_mnt);
			unregister_filesystem(&pipe_fs_type);
		}
	}
	return err;
}

static void __exit exit_pipe_fs(void)
{
	unregister_filesystem(&pipe_fs_type);
	mntput(pipe_mnt);
}

fs_initcall(init_pipe_fs);
module_exit(exit_pipe_fs);