aboutsummaryrefslogtreecommitdiffstats
path: root/net/unix/af_unix.c
diff options
context:
space:
mode:
Diffstat (limited to 'net/unix/af_unix.c')
0 files changed, 0 insertions, 0 deletions
generated by cgit v1.2.2 (git 2.25.0) at 2025-07-12 01:27:27 -0400
2'>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 1283 1284 1285 1286 1287 1288 1289 1290 1291 1292 1293 1294 1295 1296 1297 1298 1299 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 1331 1332 1333 1334 1335 1336 1337 1338 1339 1340 1341 1342 1343 1344 1345 1346 1347 1348 1349 1350 1351 1352 1353 1354 1355 1356 1357 1358 1359 1360 1361 1362 1363 1364 1365 1366 1367 1368 1369 1370 1371 1372 1373 1374 1375 1376 1377 1378 1379 1380 1381 1382 1383 1384 1385 1386 1387 1388 1389 1390 1391 1392 1393 1394 1395 1396 1397 1398 1399 1400 1401 1402 1403 1404 1405 1406 1407 1408 1409 1410 1411 1412 1413 1414 1415 1416 1417 1418 1419 1420 1421 1422 1423 1424 1425 1426 1427 1428 
/*
 * fs/direct-io.c
 *
 * Copyright (C) 2002, Linus Torvalds.
 *
 * O_DIRECT
 *
 * 04Jul2002	Andrew Morton
 *		Initial version
 * 11Sep2002	janetinc@us.ibm.com
 * 		added readv/writev support.
 * 29Oct2002	Andrew Morton
 *		rewrote bio_add_page() support.
 * 30Oct2002	pbadari@us.ibm.com
 *		added support for non-aligned IO.
 * 06Nov2002	pbadari@us.ibm.com
 *		added asynchronous IO support.
 * 21Jul2003	nathans@sgi.com
 *		added IO completion notifier.
 */

#include <linux/kernel.h>
#include <linux/module.h>
#include <linux/types.h>
#include <linux/fs.h>
#include <linux/mm.h>
#include <linux/slab.h>
#include <linux/highmem.h>
#include <linux/pagemap.h>
#include <linux/task_io_accounting_ops.h>
#include <linux/bio.h>
#include <linux/wait.h>
#include <linux/err.h>
#include <linux/blkdev.h>
#include <linux/buffer_head.h>
#include <linux/rwsem.h>
#include <linux/uio.h>
#include <linux/atomic.h>
#include <linux/prefetch.h>

/*
 * How many user pages to map in one call to get_user_pages().  This determines
 * the size of a structure in the slab cache
 */
#define DIO_PAGES	64

/*
 * Flags for dio_complete()
 */
#define DIO_COMPLETE_ASYNC		0x01	/* This is async IO */
#define DIO_COMPLETE_INVALIDATE		0x02	/* Can invalidate pages */

/*
 * This code generally works in units of "dio_blocks".  A dio_block is
 * somewhere between the hard sector size and the filesystem block size.  it
 * is determined on a per-invocation basis.   When talking to the filesystem
 * we need to convert dio_blocks to fs_blocks by scaling the dio_block quantity
 * down by dio->blkfactor.  Similarly, fs-blocksize quantities are converted
 * to bio_block quantities by shifting left by blkfactor.
 *
 * If blkfactor is zero then the user's request was aligned to the filesystem's
 * blocksize.
 */

/* dio_state only used in the submission path */

struct dio_submit {
	struct bio *bio;		/* bio under assembly */
	unsigned blkbits;		/* doesn't change */
	unsigned blkfactor;		/* When we're using an alignment which
					   is finer than the filesystem's soft
					   blocksize, this specifies how much
					   finer.  blkfactor=2 means 1/4-block
					   alignment.  Does not change */
	unsigned start_zero_done;	/* flag: sub-blocksize zeroing has
					   been performed at the start of a
					   write */
	int pages_in_io;		/* approximate total IO pages */
	sector_t block_in_file;		/* Current offset into the underlying
					   file in dio_block units. */
	unsigned blocks_available;	/* At block_in_file.  changes */
	int reap_counter;		/* rate limit reaping */
	sector_t final_block_in_request;/* doesn't change */
	int boundary;			/* prev block is at a boundary */
	get_block_t *get_block;		/* block mapping function */
	dio_submit_t *submit_io;	/* IO submition function */

	loff_t logical_offset_in_bio;	/* current first logical block in bio */
	sector_t final_block_in_bio;	/* current final block in bio + 1 */
	sector_t next_block_for_io;	/* next block to be put under IO,
					   in dio_blocks units */

	/*
	 * Deferred addition of a page to the dio.  These variables are
	 * private to dio_send_cur_page(), submit_page_section() and
	 * dio_bio_add_page().
	 */
	struct page *cur_page;		/* The page */
	unsigned cur_page_offset;	/* Offset into it, in bytes */
	unsigned cur_page_len;		/* Nr of bytes at cur_page_offset */
	sector_t cur_page_block;	/* Where it starts */
	loff_t cur_page_fs_offset;	/* Offset in file */

	struct iov_iter *iter;
	/*
	 * Page queue.  These variables belong to dio_refill_pages() and
	 * dio_get_page().
	 */
	unsigned head;			/* next page to process */
	unsigned tail;			/* last valid page + 1 */
	size_t from, to;
};

/* dio_state communicated between submission path and end_io */
struct dio {
	int flags;			/* doesn't change */
	int op;
	int op_flags;
	blk_qc_t bio_cookie;
	struct gendisk *bio_disk;
	struct inode *inode;
	loff_t i_size;			/* i_size when submitted */
	dio_iodone_t *end_io;		/* IO completion function */

	void *private;			/* copy from map_bh.b_private */

	/* BIO completion state */
	spinlock_t bio_lock;		/* protects BIO fields below */
	int page_errors;		/* errno from get_user_pages() */
	int is_async;			/* is IO async ? */
	bool defer_completion;		/* defer AIO completion to workqueue? */
	bool should_dirty;		/* if pages should be dirtied */
	int io_error;			/* IO error in completion path */
	unsigned long refcount;		/* direct_io_worker() and bios */
	struct bio *bio_list;		/* singly linked via bi_private */
	struct task_struct *waiter;	/* waiting task (NULL if none) */

	/* AIO related stuff */
	struct kiocb *iocb;		/* kiocb */
	ssize_t result;                 /* IO result */

	/*
	 * pages[] (and any fields placed after it) are not zeroed out at
	 * allocation time.  Don't add new fields after pages[] unless you
	 * wish that they not be zeroed.
	 */
	union {
		struct page *pages[DIO_PAGES];	/* page buffer */
		struct work_struct complete_work;/* deferred AIO completion */
	};
} ____cacheline_aligned_in_smp;

static struct kmem_cache *dio_cache __read_mostly;

/*
 * How many pages are in the queue?
 */
static inline unsigned dio_pages_present(struct dio_submit *sdio)
{
	return sdio->tail - sdio->head;
}

/*
 * Go grab and pin some userspace pages.   Typically we'll get 64 at a time.
 */
static inline int dio_refill_pages(struct dio *dio, struct dio_submit *sdio)
{
	ssize_t ret;

	ret = iov_iter_get_pages(sdio->iter, dio->pages, LONG_MAX, DIO_PAGES,
				&sdio->from);

	if (ret < 0 && sdio->blocks_available && (dio->op == REQ_OP_WRITE)) {
		struct page *page = ZERO_PAGE(0);
		/*
		 * A memory fault, but the filesystem has some outstanding
		 * mapped blocks.  We need to use those blocks up to avoid
		 * leaking stale data in the file.
		 */
		if (dio->page_errors == 0)
			dio->page_errors = ret;
		get_page(page);
		dio->pages[0] = page;
		sdio->head = 0;
		sdio->tail = 1;
		sdio->from = 0;
		sdio->to = PAGE_SIZE;
		return 0;
	}

	if (ret >= 0) {
		iov_iter_advance(sdio->iter, ret);
		ret += sdio->from;
		sdio->head = 0;
		sdio->tail = (ret + PAGE_SIZE - 1) / PAGE_SIZE;
		sdio->to = ((ret - 1) & (PAGE_SIZE - 1)) + 1;
		return 0;
	}
	return ret;	
}

/*
 * Get another userspace page.  Returns an ERR_PTR on error.  Pages are
 * buffered inside the dio so that we can call get_user_pages() against a
 * decent number of pages, less frequently.  To provide nicer use of the
 * L1 cache.
 */
static inline struct page *dio_get_page(struct dio *dio,
					struct dio_submit *sdio)
{
	if (dio_pages_present(sdio) == 0) {
		int ret;

		ret = dio_refill_pages(dio, sdio);
		if (ret)
			return ERR_PTR(ret);
		BUG_ON(dio_pages_present(sdio) == 0);
	}
	return dio->pages[sdio->head];
}

/*
 * Warn about a page cache invalidation failure during a direct io write.
 */
void dio_warn_stale_pagecache(struct file *filp)
{
	static DEFINE_RATELIMIT_STATE(_rs, 86400 * HZ, DEFAULT_RATELIMIT_BURST);
	char pathname[128];
	struct inode *inode = file_inode(filp);
	char *path;

	errseq_set(&inode->i_mapping->wb_err, -EIO);
	if (__ratelimit(&_rs)) {
		path = file_path(filp, pathname, sizeof(pathname));
		if (IS_ERR(path))
			path = "(unknown)";
		pr_crit("Page cache invalidation failure on direct I/O.  Possible data corruption due to collision with buffered I/O!\n");
		pr_crit("File: %s PID: %d Comm: %.20s\n", path, current->pid,
			current->comm);
	}
}

/**
 * dio_complete() - called when all DIO BIO I/O has been completed
 * @offset: the byte offset in the file of the completed operation
 *
 * This drops i_dio_count, lets interested parties know that a DIO operation
 * has completed, and calculates the resulting return code for the operation.
 *
 * It lets the filesystem know if it registered an interest earlier via
 * get_block.  Pass the private field of the map buffer_head so that
 * filesystems can use it to hold additional state between get_block calls and
 * dio_complete.
 */
static ssize_t dio_complete(struct dio *dio, ssize_t ret, unsigned int flags)
{
	loff_t offset = dio->iocb->ki_pos;
	ssize_t transferred = 0;
	int err;

	/*
	 * AIO submission can race with bio completion to get here while
	 * expecting to have the last io completed by bio completion.
	 * In that case -EIOCBQUEUED is in fact not an error we want
	 * to preserve through this call.
	 */
	if (ret == -EIOCBQUEUED)
		ret = 0;

	if (dio->result) {
		transferred = dio->result;

		/* Check for short read case */
		if ((dio->op == REQ_OP_READ) &&
		    ((offset + transferred) > dio->i_size))
			transferred = dio->i_size - offset;
		/* ignore EFAULT if some IO has been done */
		if (unlikely(ret == -EFAULT) && transferred)
			ret = 0;
	}

	if (ret == 0)
		ret = dio->page_errors;
	if (ret == 0)
		ret = dio->io_error;
	if (ret == 0)
		ret = transferred;

	if (dio->end_io) {
		// XXX: ki_pos??
		err = dio->end_io(dio->iocb, offset, ret, dio->private);
		if (err)
			ret = err;
	}

	/*
	 * Try again to invalidate clean pages which might have been cached by
	 * non-direct readahead, or faulted in by get_user_pages() if the source
	 * of the write was an mmap'ed region of the file we're writing.  Either
	 * one is a pretty crazy thing to do, so we don't support it 100%.  If
	 * this invalidation fails, tough, the write still worked...
	 *
	 * And this page cache invalidation has to be after dio->end_io(), as
	 * some filesystems convert unwritten extents to real allocations in
	 * end_io() when necessary, otherwise a racing buffer read would cache
	 * zeros from unwritten extents.
	 */
	if (flags & DIO_COMPLETE_INVALIDATE &&
	    ret > 0 && dio->op == REQ_OP_WRITE &&
	    dio->inode->i_mapping->nrpages) {
		err = invalidate_inode_pages2_range(dio->inode->i_mapping,
					offset >> PAGE_SHIFT,
					(offset + ret - 1) >> PAGE_SHIFT);
		if (err)
			dio_warn_stale_pagecache(dio->iocb->ki_filp);
	}

	inode_dio_end(dio->inode);

	if (flags & DIO_COMPLETE_ASYNC) {
		/*
		 * generic_write_sync expects ki_pos to have been updated
		 * already, but the submission path only does this for
		 * synchronous I/O.
		 */
		dio->iocb->ki_pos += transferred;

		if (dio->op == REQ_OP_WRITE)
			ret = generic_write_sync(dio->iocb,  transferred);
		dio->iocb->ki_complete(dio->iocb, ret, 0);
	}

	kmem_cache_free(dio_cache, dio);
	return ret;
}

static void dio_aio_complete_work(struct work_struct *work)
{
	struct dio *dio = container_of(work, struct dio, complete_work);

	dio_complete(dio, 0, DIO_COMPLETE_ASYNC | DIO_COMPLETE_INVALIDATE);
}

static blk_status_t dio_bio_complete(struct dio *dio, struct bio *bio);

/*
 * Asynchronous IO callback. 
 */
static void dio_bio_end_aio(struct bio *bio)
{
	struct dio *dio = bio->bi_private;
	unsigned long remaining;
	unsigned long flags;
	bool defer_completion = false;

	/* cleanup the bio */
	dio_bio_complete(dio, bio);

	spin_lock_irqsave(&dio->bio_lock, flags);
	remaining = --dio->refcount;
	if (remaining == 1 && dio->waiter)
		wake_up_process(dio->waiter);
	spin_unlock_irqrestore(&dio->bio_lock, flags);

	if (remaining == 0) {
		/*
		 * Defer completion when defer_completion is set or
		 * when the inode has pages mapped and this is AIO write.
		 * We need to invalidate those pages because there is a
		 * chance they contain stale data in the case buffered IO
		 * went in between AIO submission and completion into the
		 * same region.
		 */
		if (dio->result)
			defer_completion = dio->defer_completion ||
					   (dio->op == REQ_OP_WRITE &&
					    dio->inode->i_mapping->nrpages);
		if (defer_completion) {
			INIT_WORK(&dio->complete_work, dio_aio_complete_work);
			queue_work(dio->inode->i_sb->s_dio_done_wq,
				   &dio->complete_work);
		} else {
			dio_complete(dio, 0, DIO_COMPLETE_ASYNC);
		}
	}
}

/*
 * The BIO completion handler simply queues the BIO up for the process-context
 * handler.
 *
 * During I/O bi_private points at the dio.  After I/O, bi_private is used to
 * implement a singly-linked list of completed BIOs, at dio->bio_list.
 */
static void dio_bio_end_io(struct bio *bio)
{
	struct dio *dio = bio->bi_private;
	unsigned long flags;

	spin_lock_irqsave(&dio->bio_lock, flags);
	bio->bi_private = dio->bio_list;
	dio->bio_list = bio;
	if (--dio->refcount == 1 && dio->waiter)
		wake_up_process(dio->waiter);
	spin_unlock_irqrestore(&dio->bio_lock, flags);
}

/**
 * dio_end_io - handle the end io action for the given bio
 * @bio: The direct io bio thats being completed
 *
 * This is meant to be called by any filesystem that uses their own dio_submit_t
 * so that the DIO specific endio actions are dealt with after the filesystem
 * has done it's completion work.
 */
void dio_end_io(struct bio *bio)
{
	struct dio *dio = bio->bi_private;

	if (dio->is_async)
		dio_bio_end_aio(bio);
	else
		dio_bio_end_io(bio);
}
EXPORT_SYMBOL_GPL(dio_end_io);

static inline void
dio_bio_alloc(struct dio *dio, struct dio_submit *sdio,
	      struct block_device *bdev,
	      sector_t first_sector, int nr_vecs)
{