sufile.c 24.6 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
/*
 * sufile.c - NILFS segment usage file.
 *
 * Copyright (C) 2006-2008 Nippon Telegraph and Telephone Corporation.
 *
 * This program is free software; you can redistribute it and/or modify
 * it under the terms of the GNU General Public License as published by
 * the Free Software Foundation; either version 2 of the License, or
 * (at your option) any later version.
 *
 * This program is distributed in the hope that it will be useful,
 * but WITHOUT ANY WARRANTY; without even the implied warranty of
 * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
 * GNU General Public License for more details.
 *
 * You should have received a copy of the GNU General Public License
 * along with this program; if not, write to the Free Software
 * Foundation, Inc., 51 Franklin St, Fifth Floor, Boston, MA  02110-1301  USA
 *
 * Written by Koji Sato <koji@osrg.net>.
 * Revised by Ryusuke Konishi <ryusuke@osrg.net>.
 */

#include <linux/kernel.h>
#include <linux/fs.h>
#include <linux/string.h>
#include <linux/buffer_head.h>
#include <linux/errno.h>
#include <linux/nilfs2_fs.h>
#include "mdt.h"
#include "sufile.h"

/**
 * struct nilfs_sufile_info - on-memory private data of sufile
 * @mi: on-memory private data of metadata file
 * @ncleansegs: number of clean segments
 * @allocmin: lower limit of allocatable segment range
 * @allocmax: upper limit of allocatable segment range
 */
struct nilfs_sufile_info {
	struct nilfs_mdt_info mi;
	unsigned long ncleansegs;/* number of clean segments */
	__u64 allocmin;		/* lower limit of allocatable segment range */
	__u64 allocmax;		/* upper limit of allocatable segment range */
};

static inline struct nilfs_sufile_info *NILFS_SUI(struct inode *sufile)
{
	return (struct nilfs_sufile_info *)NILFS_MDT(sufile);
}

static inline unsigned long
nilfs_sufile_segment_usages_per_block(const struct inode *sufile)
{
	return NILFS_MDT(sufile)->mi_entries_per_block;
}

static unsigned long
nilfs_sufile_get_blkoff(const struct inode *sufile, __u64 segnum)
{
	__u64 t = segnum + NILFS_MDT(sufile)->mi_first_entry_offset;
	do_div(t, nilfs_sufile_segment_usages_per_block(sufile));
	return (unsigned long)t;
}

static unsigned long
nilfs_sufile_get_offset(const struct inode *sufile, __u64 segnum)
{
	__u64 t = segnum + NILFS_MDT(sufile)->mi_first_entry_offset;
	return do_div(t, nilfs_sufile_segment_usages_per_block(sufile));
}

static unsigned long
nilfs_sufile_segment_usages_in_block(const struct inode *sufile, __u64 curr,
				     __u64 max)
{
	return min_t(unsigned long,
		     nilfs_sufile_segment_usages_per_block(sufile) -
		     nilfs_sufile_get_offset(sufile, curr),
		     max - curr + 1);
}

static struct nilfs_segment_usage *
nilfs_sufile_block_get_segment_usage(const struct inode *sufile, __u64 segnum,
				     struct buffer_head *bh, void *kaddr)
{
	return kaddr + bh_offset(bh) +
		nilfs_sufile_get_offset(sufile, segnum) *
		NILFS_MDT(sufile)->mi_entry_size;
}

static inline int nilfs_sufile_get_header_block(struct inode *sufile,
						struct buffer_head **bhp)
{
	return nilfs_mdt_get_block(sufile, 0, 0, NULL, bhp);
}

static inline int
nilfs_sufile_get_segment_usage_block(struct inode *sufile, __u64 segnum,
				     int create, struct buffer_head **bhp)
{
	return nilfs_mdt_get_block(sufile,
				   nilfs_sufile_get_blkoff(sufile, segnum),
				   create, NULL, bhp);
}

static int nilfs_sufile_delete_segment_usage_block(struct inode *sufile,
						   __u64 segnum)
{
	return nilfs_mdt_delete_block(sufile,
				      nilfs_sufile_get_blkoff(sufile, segnum));
}

static void nilfs_sufile_mod_counter(struct buffer_head *header_bh,
				     u64 ncleanadd, u64 ndirtyadd)
{
	struct nilfs_sufile_header *header;
	void *kaddr;

	kaddr = kmap_atomic(header_bh->b_page);
	header = kaddr + bh_offset(header_bh);
	le64_add_cpu(&header->sh_ncleansegs, ncleanadd);
	le64_add_cpu(&header->sh_ndirtysegs, ndirtyadd);
	kunmap_atomic(kaddr);

	mark_buffer_dirty(header_bh);
}

/**
 * nilfs_sufile_get_ncleansegs - return the number of clean segments
 * @sufile: inode of segment usage file
 */
unsigned long nilfs_sufile_get_ncleansegs(struct inode *sufile)
{
	return NILFS_SUI(sufile)->ncleansegs;
}

/**
 * nilfs_sufile_updatev - modify multiple segment usages at a time
 * @sufile: inode of segment usage file
 * @segnumv: array of segment numbers
 * @nsegs: size of @segnumv array
 * @create: creation flag
 * @ndone: place to store number of modified segments on @segnumv
 * @dofunc: primitive operation for the update
 *
 * Description: nilfs_sufile_updatev() repeatedly calls @dofunc
 * against the given array of segments.  The @dofunc is called with
 * buffers of a header block and the sufile block in which the target
 * segment usage entry is contained.  If @ndone is given, the number
 * of successfully modified segments from the head is stored in the
 * place @ndone points to.
 *
 * Return Value: On success, zero is returned.  On error, one of the
 * following negative error codes is returned.
 *
 * %-EIO - I/O error.
 *
 * %-ENOMEM - Insufficient amount of memory available.
 *
 * %-ENOENT - Given segment usage is in hole block (may be returned if
 *            @create is zero)
 *
 * %-EINVAL - Invalid segment usage number
 */
int nilfs_sufile_updatev(struct inode *sufile, __u64 *segnumv, size_t nsegs,
			 int create, size_t *ndone,
			 void (*dofunc)(struct inode *, __u64,
					struct buffer_head *,
					struct buffer_head *))
{
	struct buffer_head *header_bh, *bh;
	unsigned long blkoff, prev_blkoff;
	__u64 *seg;
	size_t nerr = 0, n = 0;
	int ret = 0;

	if (unlikely(nsegs == 0))
		goto out;

	down_write(&NILFS_MDT(sufile)->mi_sem);
	for (seg = segnumv; seg < segnumv + nsegs; seg++) {
		if (unlikely(*seg >= nilfs_sufile_get_nsegments(sufile))) {
			printk(KERN_WARNING
			       "%s: invalid segment number: %llu\n", __func__,
			       (unsigned long long)*seg);
			nerr++;
		}
	}
	if (nerr > 0) {
		ret = -EINVAL;
		goto out_sem;
	}

	ret = nilfs_sufile_get_header_block(sufile, &header_bh);
	if (ret < 0)
		goto out_sem;

	seg = segnumv;
	blkoff = nilfs_sufile_get_blkoff(sufile, *seg);
	ret = nilfs_mdt_get_block(sufile, blkoff, create, NULL, &bh);
	if (ret < 0)
		goto out_header;

	for (;;) {
		dofunc(sufile, *seg, header_bh, bh);

		if (++seg >= segnumv + nsegs)
			break;
		prev_blkoff = blkoff;
		blkoff = nilfs_sufile_get_blkoff(sufile, *seg);
		if (blkoff == prev_blkoff)
			continue;

		/* get different block */
		brelse(bh);
		ret = nilfs_mdt_get_block(sufile, blkoff, create, NULL, &bh);
		if (unlikely(ret < 0))
			goto out_header;
	}
	brelse(bh);

 out_header:
	n = seg - segnumv;
	brelse(header_bh);
 out_sem:
	up_write(&NILFS_MDT(sufile)->mi_sem);
 out:
	if (ndone)
		*ndone = n;
	return ret;
}

int nilfs_sufile_update(struct inode *sufile, __u64 segnum, int create,
			void (*dofunc)(struct inode *, __u64,
				       struct buffer_head *,
				       struct buffer_head *))
{
	struct buffer_head *header_bh, *bh;
	int ret;

	if (unlikely(segnum >= nilfs_sufile_get_nsegments(sufile))) {
		printk(KERN_WARNING "%s: invalid segment number: %llu\n",
		       __func__, (unsigned long long)segnum);
		return -EINVAL;
	}
	down_write(&NILFS_MDT(sufile)->mi_sem);

	ret = nilfs_sufile_get_header_block(sufile, &header_bh);
	if (ret < 0)
		goto out_sem;

	ret = nilfs_sufile_get_segment_usage_block(sufile, segnum, create, &bh);
	if (!ret) {
		dofunc(sufile, segnum, header_bh, bh);
		brelse(bh);
	}
	brelse(header_bh);

 out_sem:
	up_write(&NILFS_MDT(sufile)->mi_sem);
	return ret;
}

/**
 * nilfs_sufile_set_alloc_range - limit range of segment to be allocated
 * @sufile: inode of segment usage file
 * @start: minimum segment number of allocatable region (inclusive)
 * @end: maximum segment number of allocatable region (inclusive)
 *
 * Return Value: On success, 0 is returned.  On error, one of the
 * following negative error codes is returned.
 *
 * %-ERANGE - invalid segment region
 */
int nilfs_sufile_set_alloc_range(struct inode *sufile, __u64 start, __u64 end)
{
	struct nilfs_sufile_info *sui = NILFS_SUI(sufile);
	__u64 nsegs;
	int ret = -ERANGE;

	down_write(&NILFS_MDT(sufile)->mi_sem);
	nsegs = nilfs_sufile_get_nsegments(sufile);

	if (start <= end && end < nsegs) {
		sui->allocmin = start;
		sui->allocmax = end;
		ret = 0;
	}
	up_write(&NILFS_MDT(sufile)->mi_sem);
	return ret;
}

/**
 * nilfs_sufile_alloc - allocate a segment
 * @sufile: inode of segment usage file
 * @segnump: pointer to segment number
 *
 * Description: nilfs_sufile_alloc() allocates a clean segment.
 *
 * Return Value: On success, 0 is returned and the segment number of the
 * allocated segment is stored in the place pointed by @segnump. On error, one
 * of the following negative error codes is returned.
 *
 * %-EIO - I/O error.
 *
 * %-ENOMEM - Insufficient amount of memory available.
 *
 * %-ENOSPC - No clean segment left.
 */
int nilfs_sufile_alloc(struct inode *sufile, __u64 *segnump)
{
	struct buffer_head *header_bh, *su_bh;
	struct nilfs_sufile_header *header;
	struct nilfs_segment_usage *su;
	struct nilfs_sufile_info *sui = NILFS_SUI(sufile);
	size_t susz = NILFS_MDT(sufile)->mi_entry_size;
	__u64 segnum, maxsegnum, last_alloc;
	void *kaddr;
	unsigned long nsegments, ncleansegs, nsus, cnt;
	int ret, j;

	down_write(&NILFS_MDT(sufile)->mi_sem);

	ret = nilfs_sufile_get_header_block(sufile, &header_bh);
	if (ret < 0)
		goto out_sem;
	kaddr = kmap_atomic(header_bh->b_page);
	header = kaddr + bh_offset(header_bh);
	ncleansegs = le64_to_cpu(header->sh_ncleansegs);
	last_alloc = le64_to_cpu(header->sh_last_alloc);
	kunmap_atomic(kaddr);

	nsegments = nilfs_sufile_get_nsegments(sufile);
	maxsegnum = sui->allocmax;
	segnum = last_alloc + 1;
	if (segnum < sui->allocmin || segnum > sui->allocmax)
		segnum = sui->allocmin;

	for (cnt = 0; cnt < nsegments; cnt += nsus) {
		if (segnum > maxsegnum) {
			if (cnt < sui->allocmax - sui->allocmin + 1) {
				/*
				 * wrap around in the limited region.
				 * if allocation started from
				 * sui->allocmin, this never happens.
				 */
				segnum = sui->allocmin;
				maxsegnum = last_alloc;
			} else if (segnum > sui->allocmin &&
				   sui->allocmax + 1 < nsegments) {
				segnum = sui->allocmax + 1;
				maxsegnum = nsegments - 1;
			} else if (sui->allocmin > 0)  {
				segnum = 0;
				maxsegnum = sui->allocmin - 1;
			} else {
				break; /* never happens */
			}
		}
		ret = nilfs_sufile_get_segment_usage_block(sufile, segnum, 1,
							   &su_bh);
		if (ret < 0)
			goto out_header;
		kaddr = kmap_atomic(su_bh->b_page);
		su = nilfs_sufile_block_get_segment_usage(
			sufile, segnum, su_bh, kaddr);

		nsus = nilfs_sufile_segment_usages_in_block(
			sufile, segnum, maxsegnum);
		for (j = 0; j < nsus; j++, su = (void *)su + susz, segnum++) {
			if (!nilfs_segment_usage_clean(su))
				continue;
			/* found a clean segment */
			nilfs_segment_usage_set_dirty(su);
			kunmap_atomic(kaddr);

			kaddr = kmap_atomic(header_bh->b_page);
			header = kaddr + bh_offset(header_bh);
			le64_add_cpu(&header->sh_ncleansegs, -1);
			le64_add_cpu(&header->sh_ndirtysegs, 1);
			header->sh_last_alloc = cpu_to_le64(segnum);
			kunmap_atomic(kaddr);

			sui->ncleansegs--;
			mark_buffer_dirty(header_bh);
			mark_buffer_dirty(su_bh);
			nilfs_mdt_mark_dirty(sufile);
			brelse(su_bh);
			*segnump = segnum;
			goto out_header;
		}

		kunmap_atomic(kaddr);
		brelse(su_bh);
	}

	/* no segments left */
	ret = -ENOSPC;

 out_header:
	brelse(header_bh);

 out_sem:
	up_write(&NILFS_MDT(sufile)->mi_sem);
	return ret;
}

void nilfs_sufile_do_cancel_free(struct inode *sufile, __u64 segnum,
				 struct buffer_head *header_bh,
				 struct buffer_head *su_bh)
{
	struct nilfs_segment_usage *su;
	void *kaddr;

	kaddr = kmap_atomic(su_bh->b_page);
	su = nilfs_sufile_block_get_segment_usage(sufile, segnum, su_bh, kaddr);
	if (unlikely(!nilfs_segment_usage_clean(su))) {
		printk(KERN_WARNING "%s: segment %llu must be clean\n",
		       __func__, (unsigned long long)segnum);
		kunmap_atomic(kaddr);
		return;
	}
	nilfs_segment_usage_set_dirty(su);
	kunmap_atomic(kaddr);

	nilfs_sufile_mod_counter(header_bh, -1, 1);
	NILFS_SUI(sufile)->ncleansegs--;

	mark_buffer_dirty(su_bh);
	nilfs_mdt_mark_dirty(sufile);
}

void nilfs_sufile_do_scrap(struct inode *sufile, __u64 segnum,
			   struct buffer_head *header_bh,
			   struct buffer_head *su_bh)
{
	struct nilfs_segment_usage *su;
	void *kaddr;
	int clean, dirty;

	kaddr = kmap_atomic(su_bh->b_page);
	su = nilfs_sufile_block_get_segment_usage(sufile, segnum, su_bh, kaddr);
	if (su->su_flags == cpu_to_le32(1UL << NILFS_SEGMENT_USAGE_DIRTY) &&
	    su->su_nblocks == cpu_to_le32(0)) {
		kunmap_atomic(kaddr);
		return;
	}
	clean = nilfs_segment_usage_clean(su);
	dirty = nilfs_segment_usage_dirty(su);

	/* make the segment garbage */
	su->su_lastmod = cpu_to_le64(0);
	su->su_nblocks = cpu_to_le32(0);
	su->su_flags = cpu_to_le32(1UL << NILFS_SEGMENT_USAGE_DIRTY);
	kunmap_atomic(kaddr);

	nilfs_sufile_mod_counter(header_bh, clean ? (u64)-1 : 0, dirty ? 0 : 1);
	NILFS_SUI(sufile)->ncleansegs -= clean;

	mark_buffer_dirty(su_bh);
	nilfs_mdt_mark_dirty(sufile);
}

void nilfs_sufile_do_free(struct inode *sufile, __u64 segnum,
			  struct buffer_head *header_bh,
			  struct buffer_head *su_bh)
{
	struct nilfs_segment_usage *su;
	void *kaddr;
	int sudirty;

	kaddr = kmap_atomic(su_bh->b_page);
	su = nilfs_sufile_block_get_segment_usage(sufile, segnum, su_bh, kaddr);
	if (nilfs_segment_usage_clean(su)) {
		printk(KERN_WARNING "%s: segment %llu is already clean\n",
		       __func__, (unsigned long long)segnum);
		kunmap_atomic(kaddr);
		return;
	}
	WARN_ON(nilfs_segment_usage_error(su));
	WARN_ON(!nilfs_segment_usage_dirty(su));

	sudirty = nilfs_segment_usage_dirty(su);
	nilfs_segment_usage_set_clean(su);
	kunmap_atomic(kaddr);
	mark_buffer_dirty(su_bh);

	nilfs_sufile_mod_counter(header_bh, 1, sudirty ? (u64)-1 : 0);
	NILFS_SUI(sufile)->ncleansegs++;

	nilfs_mdt_mark_dirty(sufile);
}

/**
 * nilfs_sufile_mark_dirty - mark the buffer having a segment usage dirty
 * @sufile: inode of segment usage file
 * @segnum: segment number
 */
int nilfs_sufile_mark_dirty(struct inode *sufile, __u64 segnum)
{
	struct buffer_head *bh;
	int ret;

	ret = nilfs_sufile_get_segment_usage_block(sufile, segnum, 0, &bh);
	if (!ret) {
		mark_buffer_dirty(bh);
		nilfs_mdt_mark_dirty(sufile);
		brelse(bh);
	}
	return ret;
}

/**
 * nilfs_sufile_set_segment_usage - set usage of a segment
 * @sufile: inode of segment usage file
 * @segnum: segment number
 * @nblocks: number of live blocks in the segment
 * @modtime: modification time (option)
 */
int nilfs_sufile_set_segment_usage(struct inode *sufile, __u64 segnum,
				   unsigned long nblocks, time_t modtime)
{
	struct buffer_head *bh;
	struct nilfs_segment_usage *su;
	void *kaddr;
	int ret;

	down_write(&NILFS_MDT(sufile)->mi_sem);
	ret = nilfs_sufile_get_segment_usage_block(sufile, segnum, 0, &bh);
	if (ret < 0)
		goto out_sem;

	kaddr = kmap_atomic(bh->b_page);
	su = nilfs_sufile_block_get_segment_usage(sufile, segnum, bh, kaddr);
	WARN_ON(nilfs_segment_usage_error(su));
	if (modtime)
		su->su_lastmod = cpu_to_le64(modtime);
	su->su_nblocks = cpu_to_le32(nblocks);
	kunmap_atomic(kaddr);

	mark_buffer_dirty(bh);
	nilfs_mdt_mark_dirty(sufile);
	brelse(bh);

 out_sem:
	up_write(&NILFS_MDT(sufile)->mi_sem);
	return ret;
}

/**
 * nilfs_sufile_get_stat - get segment usage statistics
 * @sufile: inode of segment usage file
 * @stat: pointer to a structure of segment usage statistics
 *
 * Description: nilfs_sufile_get_stat() returns information about segment
 * usage.
 *
 * Return Value: On success, 0 is returned, and segment usage information is
 * stored in the place pointed by @stat. On error, one of the following
 * negative error codes is returned.
 *
 * %-EIO - I/O error.
 *
 * %-ENOMEM - Insufficient amount of memory available.
 */
int nilfs_sufile_get_stat(struct inode *sufile, struct nilfs_sustat *sustat)
{
	struct buffer_head *header_bh;
	struct nilfs_sufile_header *header;
	struct the_nilfs *nilfs = sufile->i_sb->s_fs_info;
	void *kaddr;
	int ret;

	down_read(&NILFS_MDT(sufile)->mi_sem);

	ret = nilfs_sufile_get_header_block(sufile, &header_bh);
	if (ret < 0)
		goto out_sem;

	kaddr = kmap_atomic(header_bh->b_page);
	header = kaddr + bh_offset(header_bh);
	sustat->ss_nsegs = nilfs_sufile_get_nsegments(sufile);
	sustat->ss_ncleansegs = le64_to_cpu(header->sh_ncleansegs);
	sustat->ss_ndirtysegs = le64_to_cpu(header->sh_ndirtysegs);
	sustat->ss_ctime = nilfs->ns_ctime;
	sustat->ss_nongc_ctime = nilfs->ns_nongc_ctime;
	spin_lock(&nilfs->ns_last_segment_lock);
	sustat->ss_prot_seq = nilfs->ns_prot_seq;
	spin_unlock(&nilfs->ns_last_segment_lock);
	kunmap_atomic(kaddr);
	brelse(header_bh);

 out_sem:
	up_read(&NILFS_MDT(sufile)->mi_sem);
	return ret;
}

void nilfs_sufile_do_set_error(struct inode *sufile, __u64 segnum,
			       struct buffer_head *header_bh,
			       struct buffer_head *su_bh)
{
	struct nilfs_segment_usage *su;
	void *kaddr;
	int suclean;

	kaddr = kmap_atomic(su_bh->b_page);
	su = nilfs_sufile_block_get_segment_usage(sufile, segnum, su_bh, kaddr);
	if (nilfs_segment_usage_error(su)) {
		kunmap_atomic(kaddr);
		return;
	}
	suclean = nilfs_segment_usage_clean(su);
	nilfs_segment_usage_set_error(su);
	kunmap_atomic(kaddr);

	if (suclean) {
		nilfs_sufile_mod_counter(header_bh, -1, 0);
		NILFS_SUI(sufile)->ncleansegs--;
	}
	mark_buffer_dirty(su_bh);
	nilfs_mdt_mark_dirty(sufile);
}

/**
  * nilfs_sufile_truncate_range - truncate range of segment array
  * @sufile: inode of segment usage file
  * @start: start segment number (inclusive)
  * @end: end segment number (inclusive)
  *
  * Return Value: On success, 0 is returned.  On error, one of the
  * following negative error codes is returned.
  *
  * %-EIO - I/O error.
  *
  * %-ENOMEM - Insufficient amount of memory available.
  *
  * %-EINVAL - Invalid number of segments specified
  *
  * %-EBUSY - Dirty or active segments are present in the range
  */
static int nilfs_sufile_truncate_range(struct inode *sufile,
				       __u64 start, __u64 end)
{
	struct the_nilfs *nilfs = sufile->i_sb->s_fs_info;
	struct buffer_head *header_bh;
	struct buffer_head *su_bh;
	struct nilfs_segment_usage *su, *su2;
	size_t susz = NILFS_MDT(sufile)->mi_entry_size;
	unsigned long segusages_per_block;
	unsigned long nsegs, ncleaned;
	__u64 segnum;
	void *kaddr;
	ssize_t n, nc;
	int ret;
	int j;

	nsegs = nilfs_sufile_get_nsegments(sufile);

	ret = -EINVAL;
	if (start > end || start >= nsegs)
		goto out;

	ret = nilfs_sufile_get_header_block(sufile, &header_bh);
	if (ret < 0)
		goto out;

	segusages_per_block = nilfs_sufile_segment_usages_per_block(sufile);
	ncleaned = 0;

	for (segnum = start; segnum <= end; segnum += n) {
		n = min_t(unsigned long,
			  segusages_per_block -
				  nilfs_sufile_get_offset(sufile, segnum),
			  end - segnum + 1);
		ret = nilfs_sufile_get_segment_usage_block(sufile, segnum, 0,
							   &su_bh);
		if (ret < 0) {
			if (ret != -ENOENT)
				goto out_header;
			/* hole */
			continue;
		}
		kaddr = kmap_atomic(su_bh->b_page);
		su = nilfs_sufile_block_get_segment_usage(
			sufile, segnum, su_bh, kaddr);
		su2 = su;
		for (j = 0; j < n; j++, su = (void *)su + susz) {
			if ((le32_to_cpu(su->su_flags) &
			     ~(1UL << NILFS_SEGMENT_USAGE_ERROR)) ||
			    nilfs_segment_is_active(nilfs, segnum + j)) {
				ret = -EBUSY;
				kunmap_atomic(kaddr);
				brelse(su_bh);
				goto out_header;
			}
		}
		nc = 0;
		for (su = su2, j = 0; j < n; j++, su = (void *)su + susz) {
			if (nilfs_segment_usage_error(su)) {
				nilfs_segment_usage_set_clean(su);
				nc++;
			}
		}
		kunmap_atomic(kaddr);
		if (nc > 0) {
			mark_buffer_dirty(su_bh);
			ncleaned += nc;
		}
		brelse(su_bh);

		if (n == segusages_per_block) {
			/* make hole */
			nilfs_sufile_delete_segment_usage_block(sufile, segnum);
		}
	}
	ret = 0;

out_header:
	if (ncleaned > 0) {
		NILFS_SUI(sufile)->ncleansegs += ncleaned;
		nilfs_sufile_mod_counter(header_bh, ncleaned, 0);
		nilfs_mdt_mark_dirty(sufile);
	}
	brelse(header_bh);
out:
	return ret;
}

/**
 * nilfs_sufile_resize - resize segment array
 * @sufile: inode of segment usage file
 * @newnsegs: new number of segments
 *
 * Return Value: On success, 0 is returned.  On error, one of the
 * following negative error codes is returned.
 *
 * %-EIO - I/O error.
 *
 * %-ENOMEM - Insufficient amount of memory available.
 *
 * %-ENOSPC - Enough free space is not left for shrinking
 *
 * %-EBUSY - Dirty or active segments exist in the region to be truncated
 */
int nilfs_sufile_resize(struct inode *sufile, __u64 newnsegs)
{
	struct the_nilfs *nilfs = sufile->i_sb->s_fs_info;
	struct buffer_head *header_bh;
	struct nilfs_sufile_header *header;
	struct nilfs_sufile_info *sui = NILFS_SUI(sufile);
	void *kaddr;
	unsigned long nsegs, nrsvsegs;
	int ret = 0;

	down_write(&NILFS_MDT(sufile)->mi_sem);

	nsegs = nilfs_sufile_get_nsegments(sufile);
	if (nsegs == newnsegs)
		goto out;

	ret = -ENOSPC;
	nrsvsegs = nilfs_nrsvsegs(nilfs, newnsegs);
	if (newnsegs < nsegs && nsegs - newnsegs + nrsvsegs > sui->ncleansegs)
		goto out;

	ret = nilfs_sufile_get_header_block(sufile, &header_bh);
	if (ret < 0)
		goto out;

	if (newnsegs > nsegs) {
		sui->ncleansegs += newnsegs - nsegs;
	} else /* newnsegs < nsegs */ {
		ret = nilfs_sufile_truncate_range(sufile, newnsegs, nsegs - 1);
		if (ret < 0)
			goto out_header;

		sui->ncleansegs -= nsegs - newnsegs;
	}

	kaddr = kmap_atomic(header_bh->b_page);
	header = kaddr + bh_offset(header_bh);
	header->sh_ncleansegs = cpu_to_le64(sui->ncleansegs);
	kunmap_atomic(kaddr);

	mark_buffer_dirty(header_bh);
	nilfs_mdt_mark_dirty(sufile);
	nilfs_set_nsegments(nilfs, newnsegs);

out_header:
	brelse(header_bh);
out:
	up_write(&NILFS_MDT(sufile)->mi_sem);
	return ret;
}

/**
 * nilfs_sufile_get_suinfo -
 * @sufile: inode of segment usage file
 * @segnum: segment number to start looking
 * @buf: array of suinfo
 * @sisz: byte size of suinfo
 * @nsi: size of suinfo array
 *
 * Description:
 *
 * Return Value: On success, 0 is returned and .... On error, one of the
 * following negative error codes is returned.
 *
 * %-EIO - I/O error.
 *
 * %-ENOMEM - Insufficient amount of memory available.
 */
ssize_t nilfs_sufile_get_suinfo(struct inode *sufile, __u64 segnum, void *buf,
				unsigned sisz, size_t nsi)
{
	struct buffer_head *su_bh;
	struct nilfs_segment_usage *su;
	struct nilfs_suinfo *si = buf;
	size_t susz = NILFS_MDT(sufile)->mi_entry_size;
	struct the_nilfs *nilfs = sufile->i_sb->s_fs_info;
	void *kaddr;
	unsigned long nsegs, segusages_per_block;
	ssize_t n;
	int ret, i, j;

	down_read(&NILFS_MDT(sufile)->mi_sem);

	segusages_per_block = nilfs_sufile_segment_usages_per_block(sufile);
	nsegs = min_t(unsigned long,
		      nilfs_sufile_get_nsegments(sufile) - segnum,
		      nsi);
	for (i = 0; i < nsegs; i += n, segnum += n) {
		n = min_t(unsigned long,
			  segusages_per_block -
				  nilfs_sufile_get_offset(sufile, segnum),
			  nsegs - i);
		ret = nilfs_sufile_get_segment_usage_block(sufile, segnum, 0,
							   &su_bh);
		if (ret < 0) {
			if (ret != -ENOENT)
				goto out;
			/* hole */
			memset(si, 0, sisz * n);
			si = (void *)si + sisz * n;
			continue;
		}

		kaddr = kmap_atomic(su_bh->b_page);
		su = nilfs_sufile_block_get_segment_usage(
			sufile, segnum, su_bh, kaddr);
		for (j = 0; j < n;
		     j++, su = (void *)su + susz, si = (void *)si + sisz) {
			si->sui_lastmod = le64_to_cpu(su->su_lastmod);
			si->sui_nblocks = le32_to_cpu(su->su_nblocks);
			si->sui_flags = le32_to_cpu(su->su_flags) &
				~(1UL << NILFS_SEGMENT_USAGE_ACTIVE);
			if (nilfs_segment_is_active(nilfs, segnum + j))
				si->sui_flags |=
					(1UL << NILFS_SEGMENT_USAGE_ACTIVE);
		}
		kunmap_atomic(kaddr);
		brelse(su_bh);
	}
	ret = nsegs;

 out:
	up_read(&NILFS_MDT(sufile)->mi_sem);
	return ret;
}

/**
 * nilfs_sufile_read - read or get sufile inode
 * @sb: super block instance
 * @susize: size of a segment usage entry
 * @raw_inode: on-disk sufile inode
 * @inodep: buffer to store the inode
 */
int nilfs_sufile_read(struct super_block *sb, size_t susize,
		      struct nilfs_inode *raw_inode, struct inode **inodep)
{
	struct inode *sufile;
	struct nilfs_sufile_info *sui;
	struct buffer_head *header_bh;
	struct nilfs_sufile_header *header;
	void *kaddr;
	int err;

	sufile = nilfs_iget_locked(sb, NULL, NILFS_SUFILE_INO);
	if (unlikely(!sufile))
		return -ENOMEM;
	if (!(sufile->i_state & I_NEW))
		goto out;

	err = nilfs_mdt_init(sufile, NILFS_MDT_GFP, sizeof(*sui));
	if (err)
		goto failed;

	nilfs_mdt_set_entry_size(sufile, susize,
				 sizeof(struct nilfs_sufile_header));

	err = nilfs_read_inode_common(sufile, raw_inode);
	if (err)
		goto failed;

	err = nilfs_sufile_get_header_block(sufile, &header_bh);
	if (err)
		goto failed;

	sui = NILFS_SUI(sufile);
	kaddr = kmap_atomic(header_bh->b_page);
	header = kaddr + bh_offset(header_bh);
	sui->ncleansegs = le64_to_cpu(header->sh_ncleansegs);
	kunmap_atomic(kaddr);
	brelse(header_bh);

	sui->allocmax = nilfs_sufile_get_nsegments(sufile) - 1;
	sui->allocmin = 0;

	unlock_new_inode(sufile);
 out:
	*inodep = sufile;
	return 0;
 failed:
	iget_failed(sufile);
	return err;
}