aboutsummaryrefslogtreecommitdiffstats
path: root/kernel/workqueue_internal.h
diff options
context:
space:
mode:
Diffstat (limited to 'kernel/workqueue_internal.h')
0 files changed, 0 insertions, 0 deletions
generated by cgit v1.2.2 (git 2.25.0) at 2026-04-09 05:29:40 -0400
n227' href='#n227'>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 
/*
 * fs/fs-writeback.c
 *
 * Copyright (C) 2002, Linus Torvalds.
 *
 * Contains all the functions related to writing back and waiting
 * upon dirty inodes against superblocks, and writing back dirty
 * pages against inodes.  ie: data writeback.  Writeout of the
 * inode itself is not handled here.
 *
 * 10Apr2002	Andrew Morton
 *		Split out of fs/inode.c
 *		Additions for address_space-based writeback
 */

#include <linux/kernel.h>
#include <linux/module.h>
#include <linux/spinlock.h>
#include <linux/slab.h>
#include <linux/sched.h>
#include <linux/fs.h>
#include <linux/mm.h>
#include <linux/kthread.h>
#include <linux/freezer.h>
#include <linux/writeback.h>
#include <linux/blkdev.h>
#include <linux/backing-dev.h>
#include <linux/buffer_head.h>
#include <linux/tracepoint.h>
#include "internal.h"

/*
 * Passed into wb_writeback(), essentially a subset of writeback_control
 */
struct wb_writeback_work {
	long nr_pages;
	struct super_block *sb;
	enum writeback_sync_modes sync_mode;
	unsigned int for_kupdate:1;
	unsigned int range_cyclic:1;
	unsigned int for_background:1;

	struct list_head list;		/* pending work list */
	struct completion *done;	/* set if the caller waits */
};

/*
 * Include the creation of the trace points after defining the
 * wb_writeback_work structure so that the definition remains local to this
 * file.
 */
#define CREATE_TRACE_POINTS
#include <trace/events/writeback.h>

/*
 * We don't actually have pdflush, but this one is exported though /proc...
 */
int nr_pdflush_threads;

/**
 * writeback_in_progress - determine whether there is writeback in progress
 * @bdi: the device's backing_dev_info structure.
 *
 * Determine whether there is writeback waiting to be handled against a
 * backing device.
 */
int writeback_in_progress(struct backing_dev_info *bdi)
{
	return test_bit(BDI_writeback_running, &bdi->state);
}

static inline struct backing_dev_info *inode_to_bdi(struct inode *inode)
{
	struct super_block *sb = inode->i_sb;

	if (strcmp(sb->s_type->name, "bdev") == 0)
		return inode->i_mapping->backing_dev_info;

	return sb->s_bdi;
}

static inline struct inode *wb_inode(struct list_head *head)
{
	return list_entry(head, struct inode, i_wb_list);
}

static void bdi_queue_work(struct backing_dev_info *bdi,
		struct wb_writeback_work *work)
{
	trace_writeback_queue(bdi, work);

	spin_lock_bh(&bdi->wb_lock);
	list_add_tail(&work->list, &bdi->work_list);
	if (bdi->wb.task) {
		wake_up_process(bdi->wb.task);
	} else {
		/*
		 * The bdi thread isn't there, wake up the forker thread which
		 * will create and run it.
		 */
		trace_writeback_nothread(bdi, work);
		wake_up_process(default_backing_dev_info.wb.task);
	}
	spin_unlock_bh(&bdi->wb_lock);
}

static void
__bdi_start_writeback(struct backing_dev_info *bdi, long nr_pages,
		bool range_cyclic, bool for_background)
{
	struct wb_writeback_work *work;

	/*
	 * This is WB_SYNC_NONE writeback, so if allocation fails just
	 * wakeup the thread for old dirty data writeback
	 */
	work = kzalloc(sizeof(*work), GFP_ATOMIC);
	if (!work) {
		if (bdi->wb.task) {
			trace_writeback_nowork(bdi);
			wake_up_process(bdi->wb.task);
		}
		return;
	}

	work->sync_mode	= WB_SYNC_NONE;
	work->nr_pages	= nr_pages;
	work->range_cyclic = range_cyclic;
	work->for_background = for_background;

	bdi_queue_work(bdi, work);
}

/**
 * bdi_start_writeback - start writeback
 * @bdi: the backing device to write from
 * @nr_pages: the number of pages to write
 *
 * Description:
 *   This does WB_SYNC_NONE opportunistic writeback. The IO is only
 *   started when this function returns, we make no guarentees on
 *   completion. Caller need not hold sb s_umount semaphore.
 *
 */
void bdi_start_writeback(struct backing_dev_info *bdi, long nr_pages)
{
	__bdi_start_writeback(bdi, nr_pages, true, false);
}

/**
 * bdi_start_background_writeback - start background writeback
 * @bdi: the backing device to write from
 *
 * Description:
 *   This does WB_SYNC_NONE background writeback. The IO is only
 *   started when this function returns, we make no guarentees on
 *   completion. Caller need not hold sb s_umount semaphore.
 */
void bdi_start_background_writeback(struct backing_dev_info *bdi)
{
	__bdi_start_writeback(bdi, LONG_MAX, true, true);
}

/*
 * Redirty an inode: set its when-it-was dirtied timestamp and move it to the
 * furthest end of its superblock's dirty-inode list.
 *
 * Before stamping the inode's ->dirtied_when, we check to see whether it is
 * already the most-recently-dirtied inode on the b_dirty list.  If that is
 * the case then the inode must have been redirtied while it was being written
 * out and we don't reset its dirtied_when.
 */
static void redirty_tail(struct inode *inode)
{
	struct bdi_writeback *wb = &inode_to_bdi(inode)->wb;

	if (!list_empty(&wb->b_dirty)) {
		struct inode *tail;

		tail = wb_inode(wb->b_dirty.next);
		if (time_before(inode->dirtied_when, tail->dirtied_when))
			inode->dirtied_when = jiffies;
	}
	list_move(&inode->i_wb_list, &wb->b_dirty);
}

/*
 * requeue inode for re-scanning after bdi->b_io list is exhausted.
 */
static void requeue_io(struct inode *inode)
{
	struct bdi_writeback *wb = &inode_to_bdi(inode)->wb;

	list_move(&inode->i_wb_list, &wb->b_more_io);
}

static void inode_sync_complete(struct inode *inode)
{
	/*
	 * Prevent speculative execution through spin_unlock(&inode_lock);
	 */
	smp_mb();
	wake_up_bit(&inode->i_state, __I_SYNC);
}

static bool inode_dirtied_after(struct inode *inode, unsigned long t)
{
	bool ret = time_after(inode->dirtied_when, t);
#ifndef CONFIG_64BIT
	/*
	 * For inodes being constantly redirtied, dirtied_when can get stuck.
	 * It _appears_ to be in the future, but is actually in distant past.
	 * This test is necessary to prevent such wrapped-around relative times
	 * from permanently stopping the whole bdi writeback.
	 */
	ret = ret && time_before_eq(inode->dirtied_when, jiffies);
#endif
	return ret;
}

/*
 * Move expired dirty inodes from @delaying_queue to @dispatch_queue.
 */
static void move_expired_inodes(struct list_head *delaying_queue,
			       struct list_head *dispatch_queue,
				unsigned long *older_than_this)
{
	LIST_HEAD(tmp);
	struct list_head *pos, *node;
	struct super_block *sb = NULL;
	struct inode *inode;
	int do_sb_sort = 0;

	while (!list_empty(delaying_queue)) {
		inode = wb_inode(delaying_queue->prev);
		if (older_than_this &&
		    inode_dirtied_after(inode, *older_than_this))
			break;
		if (sb && sb != inode->i_sb)
			do_sb_sort = 1;
		sb = inode->i_sb;
		list_move(&inode->i_wb_list, &tmp);
	}

	/* just one sb in list, splice to dispatch_queue and we're done */
	if (!do_sb_sort) {
		list_splice(&tmp, dispatch_queue);
		return;
	}

	/* Move inodes from one superblock together */
	while (!list_empty(&tmp)) {
		sb = wb_inode(tmp.prev)->i_sb;
		list_for_each_prev_safe(pos, node, &tmp) {
			inode = wb_inode(pos);
			if (inode->i_sb == sb)
				list_move(&inode->i_wb_list, dispatch_queue);
		}
	}
}

/*
 * Queue all expired dirty inodes for io, eldest first.
 * Before
 *         newly dirtied     b_dirty    b_io    b_more_io
 *         =============>    gf         edc     BA
 * After
 *         newly dirtied     b_dirty    b_io    b_more_io
 *         =============>    g          fBAedc
 *                                           |
 *                                           +--> dequeue for IO
 */
static void queue_io(struct bdi_writeback *wb, unsigned long *older_than_this)
{
	list_splice_init(&wb->b_more_io, &wb->b_io);
	move_expired_inodes(&wb->b_dirty, &wb->b_io, older_than_this);
}

static int write_inode(struct inode *inode, struct writeback_control *wbc)
{
	if (inode->i_sb->s_op->write_inode && !is_bad_inode(inode))
		return inode->i_sb->s_op->write_inode(inode, wbc);
	return 0;
}

/*
 * Wait for writeback on an inode to complete.
 */
static void inode_wait_for_writeback(struct inode *inode)
{
	DEFINE_WAIT_BIT(wq, &inode->i_state, __I_SYNC);
	wait_queue_head_t *wqh;

	wqh = bit_waitqueue(&inode->i_state, __I_SYNC);
	 while (inode->i_state & I_SYNC) {
		spin_unlock(&inode_lock);
		__wait_on_bit(wqh, &wq, inode_wait, TASK_UNINTERRUPTIBLE);
		spin_lock(&inode_lock);
	}
}

/*
 * Write out an inode's dirty pages.  Called under inode_lock.  Either the
 * caller has ref on the inode (either via __iget or via syscall against an fd)
 * or the inode has I_WILL_FREE set (via generic_forget_inode)
 *
 * If `wait' is set, wait on the writeout.
 *
 * The whole writeout design is quite complex and fragile.  We want to avoid
 * starvation of particular inodes when others are being redirtied, prevent
 * livelocks, etc.
 *
 * Called under inode_lock.
 */
static int
writeback_single_inode(struct inode *inode, struct writeback_control *wbc)
{
	struct address_space *mapping = inode->i_mapping;
	unsigned dirty;
	int ret;

	if (!atomic_read(&inode->i_count))
		WARN_ON(!(inode->i_state & (I_WILL_FREE|I_FREEING)));
	else
		WARN_ON(inode->i_state & I_WILL_FREE);

	if (inode->i_state & I_SYNC) {
		/*
		 * If this inode is locked for writeback and we are not doing
		 * writeback-for-data-integrity, move it to b_more_io so that
		 * writeback can proceed with the other inodes on s_io.
		 *
		 * We'll have another go at writing back this inode when we
		 * completed a full scan of b_io.
		 */
		if (wbc->sync_mode != WB_SYNC_ALL) {
			requeue_io(inode);
			return 0;
		}

		/*
		 * It's a data-integrity sync.  We must wait.
		 */
		inode_wait_for_writeback(inode);
	}

	BUG_ON(inode->i_state & I_SYNC);

	/* Set I_SYNC, reset I_DIRTY_PAGES */
	inode->i_state |= I_SYNC;
	inode->i_state &= ~I_DIRTY_PAGES;
	spin_unlock(&inode_lock);

	ret = do_writepages(mapping, wbc);