segment.c 49.8 KB
Newer Older
J
Jaegeuk Kim 已提交
1
/*
J
Jaegeuk Kim 已提交
2 3 4 5 6 7 8 9 10 11 12 13 14
 * fs/f2fs/segment.c
 *
 * Copyright (c) 2012 Samsung Electronics Co., Ltd.
 *             http://www.samsung.com/
 *
 * This program is free software; you can redistribute it and/or modify
 * it under the terms of the GNU General Public License version 2 as
 * published by the Free Software Foundation.
 */
#include <linux/fs.h>
#include <linux/f2fs_fs.h>
#include <linux/bio.h>
#include <linux/blkdev.h>
15
#include <linux/prefetch.h>
J
Jaegeuk Kim 已提交
16
#include <linux/vmalloc.h>
17
#include <linux/swap.h>
J
Jaegeuk Kim 已提交
18 19 20 21

#include "f2fs.h"
#include "segment.h"
#include "node.h"
22
#include <trace/events/f2fs.h>
J
Jaegeuk Kim 已提交
23

24 25
#define __reverse_ffz(x) __reverse_ffs(~(x))

26 27
static struct kmem_cache *discard_entry_slab;

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
/*
 * __reverse_ffs is copied from include/asm-generic/bitops/__ffs.h since
 * MSB and LSB are reversed in a byte by f2fs_set_bit.
 */
static inline unsigned long __reverse_ffs(unsigned long word)
{
	int num = 0;

#if BITS_PER_LONG == 64
	if ((word & 0xffffffff) == 0) {
		num += 32;
		word >>= 32;
	}
#endif
	if ((word & 0xffff) == 0) {
		num += 16;
		word >>= 16;
	}
	if ((word & 0xff) == 0) {
		num += 8;
		word >>= 8;
	}
	if ((word & 0xf0) == 0)
		num += 4;
	else
		word >>= 4;
	if ((word & 0xc) == 0)
		num += 2;
	else
		word >>= 2;
	if ((word & 0x2) == 0)
		num += 1;
	return num;
}

/*
 * __find_rev_next(_zero)_bit is copied from lib/find_next_bit.c becasue
 * f2fs_set_bit makes MSB and LSB reversed in a byte.
 * Example:
 *                             LSB <--> MSB
 *   f2fs_set_bit(0, bitmap) => 0000 0001
 *   f2fs_set_bit(7, bitmap) => 1000 0000
 */
static unsigned long __find_rev_next_bit(const unsigned long *addr,
			unsigned long size, unsigned long offset)
{
	const unsigned long *p = addr + BIT_WORD(offset);
	unsigned long result = offset & ~(BITS_PER_LONG - 1);
	unsigned long tmp;
	unsigned long mask, submask;
	unsigned long quot, rest;

	if (offset >= size)
		return size;

	size -= result;
	offset %= BITS_PER_LONG;
	if (!offset)
		goto aligned;

	tmp = *(p++);
	quot = (offset >> 3) << 3;
	rest = offset & 0x7;
	mask = ~0UL << quot;
	submask = (unsigned char)(0xff << rest) >> rest;
	submask <<= quot;
	mask &= submask;
	tmp &= mask;
	if (size < BITS_PER_LONG)
		goto found_first;
	if (tmp)
		goto found_middle;

	size -= BITS_PER_LONG;
	result += BITS_PER_LONG;
aligned:
	while (size & ~(BITS_PER_LONG-1)) {
		tmp = *(p++);
		if (tmp)
			goto found_middle;
		result += BITS_PER_LONG;
		size -= BITS_PER_LONG;
	}
	if (!size)
		return result;
	tmp = *p;
found_first:
	tmp &= (~0UL >> (BITS_PER_LONG - size));
	if (tmp == 0UL)		/* Are any bits set? */
		return result + size;   /* Nope. */
found_middle:
	return result + __reverse_ffs(tmp);
}

static unsigned long __find_rev_next_zero_bit(const unsigned long *addr,
			unsigned long size, unsigned long offset)
{
	const unsigned long *p = addr + BIT_WORD(offset);
	unsigned long result = offset & ~(BITS_PER_LONG - 1);
	unsigned long tmp;
	unsigned long mask, submask;
	unsigned long quot, rest;

	if (offset >= size)
		return size;

	size -= result;
	offset %= BITS_PER_LONG;
	if (!offset)
		goto aligned;

	tmp = *(p++);
	quot = (offset >> 3) << 3;
	rest = offset & 0x7;
	mask = ~(~0UL << quot);
	submask = (unsigned char)~((unsigned char)(0xff << rest) >> rest);
	submask <<= quot;
	mask += submask;
	tmp |= mask;
	if (size < BITS_PER_LONG)
		goto found_first;
	if (~tmp)
		goto found_middle;

	size -= BITS_PER_LONG;
	result += BITS_PER_LONG;
aligned:
	while (size & ~(BITS_PER_LONG - 1)) {
		tmp = *(p++);
		if (~tmp)
			goto found_middle;
		result += BITS_PER_LONG;
		size -= BITS_PER_LONG;
	}
	if (!size)
		return result;
	tmp = *p;

found_first:
	tmp |= ~0UL << size;
	if (tmp == ~0UL)        /* Are any bits zero? */
		return result + size;   /* Nope. */
found_middle:
	return result + __reverse_ffz(tmp);
}

J
Jaegeuk Kim 已提交
174
/*
J
Jaegeuk Kim 已提交
175 176 177 178 179 180
 * This function balances dirty node and dentry pages.
 * In addition, it controls garbage collection.
 */
void f2fs_balance_fs(struct f2fs_sb_info *sbi)
{
	/*
181 182
	 * We should do GC or end up with checkpoint, if there are so many dirty
	 * dir/node pages without enough free segments.
J
Jaegeuk Kim 已提交
183
	 */
184
	if (has_not_enough_free_secs(sbi, 0)) {
J
Jaegeuk Kim 已提交
185
		mutex_lock(&sbi->gc_mutex);
J
Jaegeuk Kim 已提交
186
		f2fs_gc(sbi);
J
Jaegeuk Kim 已提交
187 188 189
	}
}

190 191 192 193 194 195 196 197
void f2fs_balance_fs_bg(struct f2fs_sb_info *sbi)
{
	/* check the # of cached NAT entries and prefree segments */
	if (try_to_free_nats(sbi, NAT_ENTRY_PER_BLOCK) ||
				excess_prefree_segs(sbi))
		f2fs_sync_fs(sbi->sb, true);
}

J
Jaegeuk Kim 已提交
198 199 200 201 202 203 204 205 206 207 208 209 210 211
static void __locate_dirty_segment(struct f2fs_sb_info *sbi, unsigned int segno,
		enum dirty_type dirty_type)
{
	struct dirty_seglist_info *dirty_i = DIRTY_I(sbi);

	/* need not be added */
	if (IS_CURSEG(sbi, segno))
		return;

	if (!test_and_set_bit(segno, dirty_i->dirty_segmap[dirty_type]))
		dirty_i->nr_dirty[dirty_type]++;

	if (dirty_type == DIRTY) {
		struct seg_entry *sentry = get_seg_entry(sbi, segno);
212
		enum dirty_type t = sentry->type;
213

214 215
		if (!test_and_set_bit(segno, dirty_i->dirty_segmap[t]))
			dirty_i->nr_dirty[t]++;
J
Jaegeuk Kim 已提交
216 217 218 219 220 221 222 223 224 225 226 227
	}
}

static void __remove_dirty_segment(struct f2fs_sb_info *sbi, unsigned int segno,
		enum dirty_type dirty_type)
{
	struct dirty_seglist_info *dirty_i = DIRTY_I(sbi);

	if (test_and_clear_bit(segno, dirty_i->dirty_segmap[dirty_type]))
		dirty_i->nr_dirty[dirty_type]--;

	if (dirty_type == DIRTY) {
228 229 230 231 232
		struct seg_entry *sentry = get_seg_entry(sbi, segno);
		enum dirty_type t = sentry->type;

		if (test_and_clear_bit(segno, dirty_i->dirty_segmap[t]))
			dirty_i->nr_dirty[t]--;
233

234 235 236
		if (get_valid_blocks(sbi, segno, sbi->segs_per_sec) == 0)
			clear_bit(GET_SECNO(sbi, segno),
						dirty_i->victim_secmap);
J
Jaegeuk Kim 已提交
237 238 239
	}
}

J
Jaegeuk Kim 已提交
240
/*
J
Jaegeuk Kim 已提交
241 242 243 244
 * Should not occur error such as -ENOMEM.
 * Adding dirty entry into seglist is not critical operation.
 * If a given segment is one of current working segments, it won't be added.
 */
245
static void locate_dirty_segment(struct f2fs_sb_info *sbi, unsigned int segno)
J
Jaegeuk Kim 已提交
246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269
{
	struct dirty_seglist_info *dirty_i = DIRTY_I(sbi);
	unsigned short valid_blocks;

	if (segno == NULL_SEGNO || IS_CURSEG(sbi, segno))
		return;

	mutex_lock(&dirty_i->seglist_lock);

	valid_blocks = get_valid_blocks(sbi, segno, 0);

	if (valid_blocks == 0) {
		__locate_dirty_segment(sbi, segno, PRE);
		__remove_dirty_segment(sbi, segno, DIRTY);
	} else if (valid_blocks < sbi->blocks_per_seg) {
		__locate_dirty_segment(sbi, segno, DIRTY);
	} else {
		/* Recovery routine with SSR needs this */
		__remove_dirty_segment(sbi, segno, DIRTY);
	}

	mutex_unlock(&dirty_i->seglist_lock);
}

270 271 272
static void f2fs_issue_discard(struct f2fs_sb_info *sbi,
				block_t blkstart, block_t blklen)
{
273 274
	sector_t start = SECTOR_FROM_BLOCK(sbi, blkstart);
	sector_t len = SECTOR_FROM_BLOCK(sbi, blklen);
275
	blkdev_issue_discard(sbi->sb->s_bdev, start, len, GFP_NOFS, 0);
276
	trace_f2fs_issue_discard(sbi->sb, blkstart, blklen);
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
static void add_discard_addrs(struct f2fs_sb_info *sbi,
			unsigned int segno, struct seg_entry *se)
{
	struct list_head *head = &SM_I(sbi)->discard_list;
	struct discard_entry *new;
	int entries = SIT_VBLOCK_MAP_SIZE / sizeof(unsigned long);
	int max_blocks = sbi->blocks_per_seg;
	unsigned long *cur_map = (unsigned long *)se->cur_valid_map;
	unsigned long *ckpt_map = (unsigned long *)se->ckpt_valid_map;
	unsigned long dmap[entries];
	unsigned int start = 0, end = -1;
	int i;

	if (!test_opt(sbi, DISCARD))
		return;

	/* zero block will be discarded through the prefree list */
	if (!se->valid_blocks || se->valid_blocks == max_blocks)
		return;

	/* SIT_VBLOCK_MAP_SIZE should be multiple of sizeof(unsigned long) */
	for (i = 0; i < entries; i++)
		dmap[i] = (cur_map[i] ^ ckpt_map[i]) & ckpt_map[i];

	while (SM_I(sbi)->nr_discards <= SM_I(sbi)->max_discards) {
		start = __find_rev_next_bit(dmap, max_blocks, end + 1);
		if (start >= max_blocks)
			break;

		end = __find_rev_next_zero_bit(dmap, max_blocks, start + 1);

		new = f2fs_kmem_cache_alloc(discard_entry_slab, GFP_NOFS);
		INIT_LIST_HEAD(&new->list);
		new->blkaddr = START_BLOCK(sbi, segno) + start;
		new->len = end - start;

		list_add_tail(&new->list, head);
		SM_I(sbi)->nr_discards += end - start;
	}
}

J
Jaegeuk Kim 已提交
320
/*
J
Jaegeuk Kim 已提交
321 322 323 324 325
 * Should call clear_prefree_segments after checkpoint is done.
 */
static void set_prefree_as_free_segments(struct f2fs_sb_info *sbi)
{
	struct dirty_seglist_info *dirty_i = DIRTY_I(sbi);
326
	unsigned int segno = -1;
J
Jaegeuk Kim 已提交
327 328 329 330 331
	unsigned int total_segs = TOTAL_SEGS(sbi);

	mutex_lock(&dirty_i->seglist_lock);
	while (1) {
		segno = find_next_bit(dirty_i->dirty_segmap[PRE], total_segs,
332
				segno + 1);
J
Jaegeuk Kim 已提交
333 334 335 336 337 338 339 340 341
		if (segno >= total_segs)
			break;
		__set_test_and_free(sbi, segno);
	}
	mutex_unlock(&dirty_i->seglist_lock);
}

void clear_prefree_segments(struct f2fs_sb_info *sbi)
{
342
	struct list_head *head = &(SM_I(sbi)->discard_list);
343
	struct discard_entry *entry, *this;
J
Jaegeuk Kim 已提交
344
	struct dirty_seglist_info *dirty_i = DIRTY_I(sbi);
345
	unsigned long *prefree_map = dirty_i->dirty_segmap[PRE];
J
Jaegeuk Kim 已提交
346
	unsigned int total_segs = TOTAL_SEGS(sbi);
347
	unsigned int start = 0, end = -1;
J
Jaegeuk Kim 已提交
348 349

	mutex_lock(&dirty_i->seglist_lock);
350

J
Jaegeuk Kim 已提交
351
	while (1) {
352 353 354
		int i;
		start = find_next_bit(prefree_map, total_segs, end + 1);
		if (start >= total_segs)
J
Jaegeuk Kim 已提交
355
			break;
356 357 358 359 360 361 362 363 364
		end = find_next_zero_bit(prefree_map, total_segs, start + 1);

		for (i = start; i < end; i++)
			clear_bit(i, prefree_map);

		dirty_i->nr_dirty[PRE] -= end - start;

		if (!test_opt(sbi, DISCARD))
			continue;
J
Jaegeuk Kim 已提交
365

366 367
		f2fs_issue_discard(sbi, START_BLOCK(sbi, start),
				(end - start) << sbi->log_blocks_per_seg);
J
Jaegeuk Kim 已提交
368 369
	}
	mutex_unlock(&dirty_i->seglist_lock);
370 371

	/* send small discards */
372
	list_for_each_entry_safe(entry, this, head, list) {
373
		f2fs_issue_discard(sbi, entry->blkaddr, entry->len);
374 375 376 377
		list_del(&entry->list);
		SM_I(sbi)->nr_discards -= entry->len;
		kmem_cache_free(discard_entry_slab, entry);
	}
J
Jaegeuk Kim 已提交
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
}

static void __mark_sit_entry_dirty(struct f2fs_sb_info *sbi, unsigned int segno)
{
	struct sit_info *sit_i = SIT_I(sbi);
	if (!__test_and_set_bit(segno, sit_i->dirty_sentries_bitmap))
		sit_i->dirty_sentries++;
}

static void __set_sit_entry_type(struct f2fs_sb_info *sbi, int type,
					unsigned int segno, int modified)
{
	struct seg_entry *se = get_seg_entry(sbi, segno);
	se->type = type;
	if (modified)
		__mark_sit_entry_dirty(sbi, segno);
}

static void update_sit_entry(struct f2fs_sb_info *sbi, block_t blkaddr, int del)
{
	struct seg_entry *se;
	unsigned int segno, offset;
	long int new_vblocks;

	segno = GET_SEGNO(sbi, blkaddr);

	se = get_seg_entry(sbi, segno);
	new_vblocks = se->valid_blocks + del;
J
Jaegeuk Kim 已提交
406
	offset = GET_BLKOFF_FROM_SEG0(sbi, blkaddr);
J
Jaegeuk Kim 已提交
407

408
	f2fs_bug_on((new_vblocks >> (sizeof(unsigned short) << 3) ||
J
Jaegeuk Kim 已提交
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
				(new_vblocks > sbi->blocks_per_seg)));

	se->valid_blocks = new_vblocks;
	se->mtime = get_mtime(sbi);
	SIT_I(sbi)->max_mtime = se->mtime;

	/* Update valid block bitmap */
	if (del > 0) {
		if (f2fs_set_bit(offset, se->cur_valid_map))
			BUG();
	} else {
		if (!f2fs_clear_bit(offset, se->cur_valid_map))
			BUG();
	}
	if (!f2fs_test_bit(offset, se->ckpt_valid_map))
		se->ckpt_valid_blocks += del;

	__mark_sit_entry_dirty(sbi, segno);

	/* update total number of valid blocks to be written in ckpt area */
	SIT_I(sbi)->written_valid_blocks += del;

	if (sbi->segs_per_sec > 1)
		get_sec_entry(sbi, segno)->valid_blocks += del;
}

435
void refresh_sit_entry(struct f2fs_sb_info *sbi, block_t old, block_t new)
J
Jaegeuk Kim 已提交
436
{
437 438 439 440 441 442
	update_sit_entry(sbi, new, 1);
	if (GET_SEGNO(sbi, old) != NULL_SEGNO)
		update_sit_entry(sbi, old, -1);

	locate_dirty_segment(sbi, GET_SEGNO(sbi, old));
	locate_dirty_segment(sbi, GET_SEGNO(sbi, new));
J
Jaegeuk Kim 已提交
443 444 445 446 447 448 449
}

void invalidate_blocks(struct f2fs_sb_info *sbi, block_t addr)
{
	unsigned int segno = GET_SEGNO(sbi, addr);
	struct sit_info *sit_i = SIT_I(sbi);

450
	f2fs_bug_on(addr == NULL_ADDR);
J
Jaegeuk Kim 已提交
451 452 453 454 455 456 457 458 459 460 461 462 463 464
	if (addr == NEW_ADDR)
		return;

	/* add it into sit main buffer */
	mutex_lock(&sit_i->sentry_lock);

	update_sit_entry(sbi, addr, -1);

	/* add it into dirty seglist */
	locate_dirty_segment(sbi, segno);

	mutex_unlock(&sit_i->sentry_lock);
}

J
Jaegeuk Kim 已提交
465
/*
J
Jaegeuk Kim 已提交
466 467 468
 * This function should be resided under the curseg_mutex lock
 */
static void __add_sum_entry(struct f2fs_sb_info *sbi, int type,
469
					struct f2fs_summary *sum)
J
Jaegeuk Kim 已提交
470 471 472
{
	struct curseg_info *curseg = CURSEG_I(sbi, type);
	void *addr = curseg->sum_blk;
473
	addr += curseg->next_blkoff * sizeof(struct f2fs_summary);
J
Jaegeuk Kim 已提交
474 475 476
	memcpy(addr, sum, sizeof(struct f2fs_summary));
}

J
Jaegeuk Kim 已提交
477
/*
J
Jaegeuk Kim 已提交
478 479 480 481 482
 * Calculate the number of current summary pages for writing
 */
int npages_for_summary_flush(struct f2fs_sb_info *sbi)
{
	int valid_sum_count = 0;
483
	int i, sum_in_page;
J
Jaegeuk Kim 已提交
484 485 486 487 488 489 490 491

	for (i = CURSEG_HOT_DATA; i <= CURSEG_COLD_DATA; i++) {
		if (sbi->ckpt->alloc_type[i] == SSR)
			valid_sum_count += sbi->blocks_per_seg;
		else
			valid_sum_count += curseg_blkoff(sbi, i);
	}

492 493 494
	sum_in_page = (PAGE_CACHE_SIZE - 2 * SUM_JOURNAL_SIZE -
			SUM_FOOTER_SIZE) / SUMMARY_SIZE;
	if (valid_sum_count <= sum_in_page)
J
Jaegeuk Kim 已提交
495
		return 1;
496 497
	else if ((valid_sum_count - sum_in_page) <=
		(PAGE_CACHE_SIZE - SUM_FOOTER_SIZE) / SUMMARY_SIZE)
J
Jaegeuk Kim 已提交
498 499 500 501
		return 2;
	return 3;
}

J
Jaegeuk Kim 已提交
502
/*
J
Jaegeuk Kim 已提交
503 504 505 506 507 508 509 510 511 512 513 514 515 516 517 518 519
 * Caller should put this summary page
 */
struct page *get_sum_page(struct f2fs_sb_info *sbi, unsigned int segno)
{
	return get_meta_page(sbi, GET_SUM_BLOCK(sbi, segno));
}

static void write_sum_page(struct f2fs_sb_info *sbi,
			struct f2fs_summary_block *sum_blk, block_t blk_addr)
{
	struct page *page = grab_meta_page(sbi, blk_addr);
	void *kaddr = page_address(page);
	memcpy(kaddr, sum_blk, PAGE_CACHE_SIZE);
	set_page_dirty(page);
	f2fs_put_page(page, 1);
}

520 521 522
static int is_next_segment_free(struct f2fs_sb_info *sbi, int type)
{
	struct curseg_info *curseg = CURSEG_I(sbi, type);
523
	unsigned int segno = curseg->segno + 1;
524 525
	struct free_segmap_info *free_i = FREE_I(sbi);

526 527
	if (segno < TOTAL_SEGS(sbi) && segno % sbi->segs_per_sec)
		return !test_bit(segno, free_i->free_segmap);
528 529 530
	return 0;
}

J
Jaegeuk Kim 已提交
531
/*
J
Jaegeuk Kim 已提交
532 533 534 535 536 537 538 539
 * Find a new segment from the free segments bitmap to right order
 * This function should be returned with success, otherwise BUG
 */
static void get_new_segment(struct f2fs_sb_info *sbi,
			unsigned int *newseg, bool new_sec, int dir)
{
	struct free_segmap_info *free_i = FREE_I(sbi);
	unsigned int segno, secno, zoneno;
J
Jaegeuk Kim 已提交
540
	unsigned int total_zones = TOTAL_SECS(sbi) / sbi->secs_per_zone;
J
Jaegeuk Kim 已提交
541 542 543 544 545 546 547 548 549 550 551 552
	unsigned int hint = *newseg / sbi->segs_per_sec;
	unsigned int old_zoneno = GET_ZONENO_FROM_SEGNO(sbi, *newseg);
	unsigned int left_start = hint;
	bool init = true;
	int go_left = 0;
	int i;

	write_lock(&free_i->segmap_lock);

	if (!new_sec && ((*newseg + 1) % sbi->segs_per_sec)) {
		segno = find_next_zero_bit(free_i->free_segmap,
					TOTAL_SEGS(sbi), *newseg + 1);
553 554
		if (segno - *newseg < sbi->segs_per_sec -
					(*newseg % sbi->segs_per_sec))
J
Jaegeuk Kim 已提交
555 556 557
			goto got_it;
	}
find_other_zone:
J
Jaegeuk Kim 已提交
558 559
	secno = find_next_zero_bit(free_i->free_secmap, TOTAL_SECS(sbi), hint);
	if (secno >= TOTAL_SECS(sbi)) {
J
Jaegeuk Kim 已提交
560 561
		if (dir == ALLOC_RIGHT) {
			secno = find_next_zero_bit(free_i->free_secmap,
J
Jaegeuk Kim 已提交
562
							TOTAL_SECS(sbi), 0);
563
			f2fs_bug_on(secno >= TOTAL_SECS(sbi));
J
Jaegeuk Kim 已提交
564 565 566 567 568 569 570 571 572 573 574 575 576 577
		} else {
			go_left = 1;
			left_start = hint - 1;
		}
	}
	if (go_left == 0)
		goto skip_left;

	while (test_bit(left_start, free_i->free_secmap)) {
		if (left_start > 0) {
			left_start--;
			continue;
		}
		left_start = find_next_zero_bit(free_i->free_secmap,
J
Jaegeuk Kim 已提交
578
							TOTAL_SECS(sbi), 0);
579
		f2fs_bug_on(left_start >= TOTAL_SECS(sbi));
J
Jaegeuk Kim 已提交
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
		break;
	}
	secno = left_start;
skip_left:
	hint = secno;
	segno = secno * sbi->segs_per_sec;
	zoneno = secno / sbi->secs_per_zone;

	/* give up on finding another zone */
	if (!init)
		goto got_it;
	if (sbi->secs_per_zone == 1)
		goto got_it;
	if (zoneno == old_zoneno)
		goto got_it;
	if (dir == ALLOC_LEFT) {
		if (!go_left && zoneno + 1 >= total_zones)
			goto got_it;
		if (go_left && zoneno == 0)
			goto got_it;
	}
	for (i = 0; i < NR_CURSEG_TYPE; i++)
		if (CURSEG_I(sbi, i)->zone == zoneno)
			break;

	if (i < NR_CURSEG_TYPE) {
		/* zone is in user, try another */
		if (go_left)
			hint = zoneno * sbi->secs_per_zone - 1;
		else if (zoneno + 1 >= total_zones)
			hint = 0;
		else
			hint = (zoneno + 1) * sbi->secs_per_zone;
		init = false;
		goto find_other_zone;
	}
got_it:
	/* set it as dirty segment in free segmap */
618
	f2fs_bug_on(test_bit(segno, free_i->free_segmap));
J
Jaegeuk Kim 已提交
619 620 621 622 623 624 625 626 627 628 629 630 631 632 633 634 635 636 637 638 639 640 641 642
	__set_inuse(sbi, segno);
	*newseg = segno;
	write_unlock(&free_i->segmap_lock);
}

static void reset_curseg(struct f2fs_sb_info *sbi, int type, int modified)
{
	struct curseg_info *curseg = CURSEG_I(sbi, type);
	struct summary_footer *sum_footer;

	curseg->segno = curseg->next_segno;
	curseg->zone = GET_ZONENO_FROM_SEGNO(sbi, curseg->segno);
	curseg->next_blkoff = 0;
	curseg->next_segno = NULL_SEGNO;

	sum_footer = &(curseg->sum_blk->footer);
	memset(sum_footer, 0, sizeof(struct summary_footer));
	if (IS_DATASEG(type))
		SET_SUM_TYPE(sum_footer, SUM_TYPE_DATA);
	if (IS_NODESEG(type))
		SET_SUM_TYPE(sum_footer, SUM_TYPE_NODE);
	__set_sit_entry_type(sbi, type, curseg->segno, modified);
}

J
Jaegeuk Kim 已提交
643
/*
J
Jaegeuk Kim 已提交
644 645 646 647 648 649 650 651 652 653
 * Allocate a current working segment.
 * This function always allocates a free segment in LFS manner.
 */
static void new_curseg(struct f2fs_sb_info *sbi, int type, bool new_sec)
{
	struct curseg_info *curseg = CURSEG_I(sbi, type);
	unsigned int segno = curseg->segno;
	int dir = ALLOC_LEFT;

	write_sum_page(sbi, curseg->sum_blk,
654
				GET_SUM_BLOCK(sbi, segno));
J
Jaegeuk Kim 已提交
655 656 657 658 659 660 661 662 663 664 665 666 667 668 669 670
	if (type == CURSEG_WARM_DATA || type == CURSEG_COLD_DATA)
		dir = ALLOC_RIGHT;

	if (test_opt(sbi, NOHEAP))
		dir = ALLOC_RIGHT;

	get_new_segment(sbi, &segno, new_sec, dir);
	curseg->next_segno = segno;
	reset_curseg(sbi, type, 1);
	curseg->alloc_type = LFS;
}

static void __next_free_blkoff(struct f2fs_sb_info *sbi,
			struct curseg_info *seg, block_t start)
{
	struct seg_entry *se = get_seg_entry(sbi, seg->segno);
671 672 673 674 675 676 677 678 679 680 681 682
	int entries = SIT_VBLOCK_MAP_SIZE / sizeof(unsigned long);
	unsigned long target_map[entries];
	unsigned long *ckpt_map = (unsigned long *)se->ckpt_valid_map;
	unsigned long *cur_map = (unsigned long *)se->cur_valid_map;
	int i, pos;

	for (i = 0; i < entries; i++)
		target_map[i] = ckpt_map[i] | cur_map[i];

	pos = __find_rev_next_zero_bit(target_map, sbi->blocks_per_seg, start);

	seg->next_blkoff = pos;
J
Jaegeuk Kim 已提交
683 684
}

J
Jaegeuk Kim 已提交
685
/*
J
Jaegeuk Kim 已提交
686 687 688 689 690 691 692 693 694 695 696 697 698
 * If a segment is written by LFS manner, next block offset is just obtained
 * by increasing the current block offset. However, if a segment is written by
 * SSR manner, next block offset obtained by calling __next_free_blkoff
 */
static void __refresh_next_blkoff(struct f2fs_sb_info *sbi,
				struct curseg_info *seg)
{
	if (seg->alloc_type == SSR)
		__next_free_blkoff(sbi, seg, seg->next_blkoff + 1);
	else
		seg->next_blkoff++;
}

J
Jaegeuk Kim 已提交
699
/*
J
Jaegeuk Kim 已提交
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
 * This function always allocates a used segment (from dirty seglist) by SSR
 * manner, so it should recover the existing segment information of valid blocks
 */
static void change_curseg(struct f2fs_sb_info *sbi, int type, bool reuse)
{
	struct dirty_seglist_info *dirty_i = DIRTY_I(sbi);
	struct curseg_info *curseg = CURSEG_I(sbi, type);
	unsigned int new_segno = curseg->next_segno;
	struct f2fs_summary_block *sum_node;
	struct page *sum_page;

	write_sum_page(sbi, curseg->sum_blk,
				GET_SUM_BLOCK(sbi, curseg->segno));
	__set_test_and_inuse(sbi, new_segno);

	mutex_lock(&dirty_i->seglist_lock);
	__remove_dirty_segment(sbi, new_segno, PRE);
	__remove_dirty_segment(sbi, new_segno, DIRTY);
	mutex_unlock(&dirty_i->seglist_lock);

	reset_curseg(sbi, type, 1);
	curseg->alloc_type = SSR;
	__next_free_blkoff(sbi, curseg, 0);

	if (reuse) {
		sum_page = get_sum_page(sbi, new_segno);
		sum_node = (struct f2fs_summary_block *)page_address(sum_page);
		memcpy(curseg->sum_blk, sum_node, SUM_ENTRY_SIZE);
		f2fs_put_page(sum_page, 1);
	}
}

732 733 734 735 736 737 738 739 740 741 742 743 744 745 746 747 748
static int get_ssr_segment(struct f2fs_sb_info *sbi, int type)
{
	struct curseg_info *curseg = CURSEG_I(sbi, type);
	const struct victim_selection *v_ops = DIRTY_I(sbi)->v_ops;

	if (IS_NODESEG(type) || !has_not_enough_free_secs(sbi, 0))
		return v_ops->get_victim(sbi,
				&(curseg)->next_segno, BG_GC, type, SSR);

	/* For data segments, let's do SSR more intensively */
	for (; type >= CURSEG_HOT_DATA; type--)
		if (v_ops->get_victim(sbi, &(curseg)->next_segno,
						BG_GC, type, SSR))
			return 1;
	return 0;
}

J
Jaegeuk Kim 已提交
749 750 751 752 753 754 755 756 757
/*
 * flush out current segment and replace it with new segment
 * This function should be returned with success, otherwise BUG
 */
static void allocate_segment_by_default(struct f2fs_sb_info *sbi,
						int type, bool force)
{
	struct curseg_info *curseg = CURSEG_I(sbi, type);

758
	if (force)
J
Jaegeuk Kim 已提交
759
		new_curseg(sbi, type, true);
760
	else if (type == CURSEG_WARM_NODE)
J
Jaegeuk Kim 已提交
761
		new_curseg(sbi, type, false);
762 763
	else if (curseg->alloc_type == LFS && is_next_segment_free(sbi, type))
		new_curseg(sbi, type, false);
J
Jaegeuk Kim 已提交
764 765 766 767
	else if (need_SSR(sbi) && get_ssr_segment(sbi, type))
		change_curseg(sbi, type, true);
	else
		new_curseg(sbi, type, false);
768 769

	stat_inc_seg_type(sbi, curseg);
J
Jaegeuk Kim 已提交
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
}

void allocate_new_segments(struct f2fs_sb_info *sbi)
{
	struct curseg_info *curseg;
	unsigned int old_curseg;
	int i;

	for (i = CURSEG_HOT_DATA; i <= CURSEG_COLD_DATA; i++) {
		curseg = CURSEG_I(sbi, i);
		old_curseg = curseg->segno;
		SIT_I(sbi)->s_ops->allocate_segment(sbi, i, true);
		locate_dirty_segment(sbi, old_curseg);
	}
}

static const struct segment_allocation default_salloc_ops = {
	.allocate_segment = allocate_segment_by_default,
};

static bool __has_curseg_space(struct f2fs_sb_info *sbi, int type)
{
	struct curseg_info *curseg = CURSEG_I(sbi, type);
	if (curseg->next_blkoff < sbi->blocks_per_seg)
		return true;
	return false;
}

static int __get_segment_type_2(struct page *page, enum page_type p_type)
{
	if (p_type == DATA)
		return CURSEG_HOT_DATA;
	else
		return CURSEG_HOT_NODE;
}

static int __get_segment_type_4(struct page *page, enum page_type p_type)
{
	if (p_type == DATA) {
		struct inode *inode = page->mapping->host;

		if (S_ISDIR(inode->i_mode))
			return CURSEG_HOT_DATA;
		else
			return CURSEG_COLD_DATA;
	} else {
		if (IS_DNODE(page) && !is_cold_node(page))
			return CURSEG_HOT_NODE;
		else
			return CURSEG_COLD_NODE;
	}
}

static int __get_segment_type_6(struct page *page, enum page_type p_type)
{
	if (p_type == DATA) {
		struct inode *inode = page->mapping->host;

		if (S_ISDIR(inode->i_mode))
			return CURSEG_HOT_DATA;
830
		else if (is_cold_data(page) || file_is_cold(inode))
J
Jaegeuk Kim 已提交
831 832 833 834 835 836 837 838 839 840 841 842 843 844 845 846 847 848 849 850 851
			return CURSEG_COLD_DATA;
		else
			return CURSEG_WARM_DATA;
	} else {
		if (IS_DNODE(page))
			return is_cold_node(page) ? CURSEG_WARM_NODE :
						CURSEG_HOT_NODE;
		else
			return CURSEG_COLD_NODE;
	}
}

static int __get_segment_type(struct page *page, enum page_type p_type)
{
	struct f2fs_sb_info *sbi = F2FS_SB(page->mapping->host->i_sb);
	switch (sbi->active_logs) {
	case 2:
		return __get_segment_type_2(page, p_type);
	case 4:
		return __get_segment_type_4(page, p_type);
	}
852
	/* NR_CURSEG_TYPE(6) logs by default */
853
	f2fs_bug_on(sbi->active_logs != NR_CURSEG_TYPE);
854
	return __get_segment_type_6(page, p_type);
J
Jaegeuk Kim 已提交
855 856
}

857 858 859
void allocate_data_block(struct f2fs_sb_info *sbi, struct page *page,
		block_t old_blkaddr, block_t *new_blkaddr,
		struct f2fs_summary *sum, int type)
J
Jaegeuk Kim 已提交
860 861 862 863 864 865 866 867 868 869 870 871 872 873 874 875 876
{
	struct sit_info *sit_i = SIT_I(sbi);
	struct curseg_info *curseg;
	unsigned int old_cursegno;

	curseg = CURSEG_I(sbi, type);

	mutex_lock(&curseg->curseg_mutex);

	*new_blkaddr = NEXT_FREE_BLKADDR(sbi, curseg);
	old_cursegno = curseg->segno;

	/*
	 * __add_sum_entry should be resided under the curseg_mutex
	 * because, this function updates a summary entry in the
	 * current summary block.
	 */
877
	__add_sum_entry(sbi, type, sum);
J
Jaegeuk Kim 已提交
878 879 880

	mutex_lock(&sit_i->sentry_lock);
	__refresh_next_blkoff(sbi, curseg);
881 882

	stat_inc_block_count(sbi, curseg);
J
Jaegeuk Kim 已提交
883

884 885
	if (!__has_curseg_space(sbi, type))
		sit_i->s_ops->allocate_segment(sbi, type, false);
J
Jaegeuk Kim 已提交
886 887 888 889 890 891
	/*
	 * SIT information should be updated before segment allocation,
	 * since SSR needs latest valid block information.
	 */
	refresh_sit_entry(sbi, old_blkaddr, *new_blkaddr);
	locate_dirty_segment(sbi, old_cursegno);
892

J
Jaegeuk Kim 已提交
893 894
	mutex_unlock(&sit_i->sentry_lock);

895
	if (page && IS_NODESEG(type))
J
Jaegeuk Kim 已提交
896 897
		fill_node_footer_blkaddr(page, NEXT_FREE_BLKADDR(sbi, curseg));

898 899 900 901 902 903 904 905 906 907 908
	mutex_unlock(&curseg->curseg_mutex);
}

static void do_write_page(struct f2fs_sb_info *sbi, struct page *page,
			block_t old_blkaddr, block_t *new_blkaddr,
			struct f2fs_summary *sum, struct f2fs_io_info *fio)
{
	int type = __get_segment_type(page, fio->type);

	allocate_data_block(sbi, page, old_blkaddr, new_blkaddr, sum, type);

J
Jaegeuk Kim 已提交
909
	/* writeout dirty page into bdev */
J
Jaegeuk Kim 已提交
910
	f2fs_submit_page_mbio(sbi, page, *new_blkaddr, fio);
J
Jaegeuk Kim 已提交
911 912
}

913
void write_meta_page(struct f2fs_sb_info *sbi, struct page *page)
J
Jaegeuk Kim 已提交
914
{
J
Jaegeuk Kim 已提交
915 916
	struct f2fs_io_info fio = {
		.type = META,
917
		.rw = WRITE_SYNC | REQ_META | REQ_PRIO
J
Jaegeuk Kim 已提交
918 919
	};

J
Jaegeuk Kim 已提交
920
	set_page_writeback(page);
J
Jaegeuk Kim 已提交
921
	f2fs_submit_page_mbio(sbi, page, page->index, &fio);
J
Jaegeuk Kim 已提交
922 923 924
}

void write_node_page(struct f2fs_sb_info *sbi, struct page *page,
925
		struct f2fs_io_info *fio,
J
Jaegeuk Kim 已提交
926 927 928 929
		unsigned int nid, block_t old_blkaddr, block_t *new_blkaddr)
{
	struct f2fs_summary sum;
	set_summary(&sum, nid, 0, 0);
930
	do_write_page(sbi, page, old_blkaddr, new_blkaddr, &sum, fio);
J
Jaegeuk Kim 已提交
931 932
}

J
Jaegeuk Kim 已提交
933 934
void write_data_page(struct page *page, struct dnode_of_data *dn,
		block_t *new_blkaddr, struct f2fs_io_info *fio)
J
Jaegeuk Kim 已提交
935
{
J
Jaegeuk Kim 已提交
936
	struct f2fs_sb_info *sbi = F2FS_SB(dn->inode->i_sb);
J
Jaegeuk Kim 已提交
937 938 939
	struct f2fs_summary sum;
	struct node_info ni;

J
Jaegeuk Kim 已提交
940
	f2fs_bug_on(dn->data_blkaddr == NULL_ADDR);
J
Jaegeuk Kim 已提交
941 942 943
	get_node_info(sbi, dn->nid, &ni);
	set_summary(&sum, dn->nid, dn->ofs_in_node, ni.version);

J
Jaegeuk Kim 已提交
944
	do_write_page(sbi, page, dn->data_blkaddr, new_blkaddr, &sum, fio);
J
Jaegeuk Kim 已提交
945 946
}

C
Chris Fries 已提交
947 948
void rewrite_data_page(struct page *page, block_t old_blkaddr,
					struct f2fs_io_info *fio)
J
Jaegeuk Kim 已提交
949
{
J
Jaegeuk Kim 已提交
950 951 952
	struct inode *inode = page->mapping->host;
	struct f2fs_sb_info *sbi = F2FS_SB(inode->i_sb);
	f2fs_submit_page_mbio(sbi, page, old_blkaddr, fio);
J
Jaegeuk Kim 已提交
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
}

void recover_data_page(struct f2fs_sb_info *sbi,
			struct page *page, struct f2fs_summary *sum,
			block_t old_blkaddr, block_t new_blkaddr)
{
	struct sit_info *sit_i = SIT_I(sbi);
	struct curseg_info *curseg;
	unsigned int segno, old_cursegno;
	struct seg_entry *se;
	int type;

	segno = GET_SEGNO(sbi, new_blkaddr);
	se = get_seg_entry(sbi, segno);
	type = se->type;

	if (se->valid_blocks == 0 && !IS_CURSEG(sbi, segno)) {
		if (old_blkaddr == NULL_ADDR)
			type = CURSEG_COLD_DATA;
		else
			type = CURSEG_WARM_DATA;
	}
	curseg = CURSEG_I(sbi, type);

	mutex_lock(&curseg->curseg_mutex);
	mutex_lock(&sit_i->sentry_lock);

	old_cursegno = curseg->segno;

	/* change the current segment */
	if (segno != curseg->segno) {
		curseg->next_segno = segno;
		change_curseg(sbi, type, true);
	}

J
Jaegeuk Kim 已提交
988
	curseg->next_blkoff = GET_BLKOFF_FROM_SEG0(sbi, new_blkaddr);
989
	__add_sum_entry(sbi, type, sum);
J
Jaegeuk Kim 已提交
990 991 992 993 994 995 996 997 998 999 1000 1001 1002 1003 1004 1005 1006 1007

	refresh_sit_entry(sbi, old_blkaddr, new_blkaddr);
	locate_dirty_segment(sbi, old_cursegno);

	mutex_unlock(&sit_i->sentry_lock);
	mutex_unlock(&curseg->curseg_mutex);
}

void rewrite_node_page(struct f2fs_sb_info *sbi,
			struct page *page, struct f2fs_summary *sum,
			block_t old_blkaddr, block_t new_blkaddr)
{
	struct sit_info *sit_i = SIT_I(sbi);
	int type = CURSEG_WARM_NODE;
	struct curseg_info *curseg;
	unsigned int segno, old_cursegno;
	block_t next_blkaddr = next_blkaddr_of_node(page);
	unsigned int next_segno = GET_SEGNO(sbi, next_blkaddr);
J
Jaegeuk Kim 已提交
1008 1009 1010 1011
	struct f2fs_io_info fio = {
		.type = NODE,
		.rw = WRITE_SYNC,
	};
J
Jaegeuk Kim 已提交
1012 1013 1014 1015 1016 1017 1018 1019 1020 1021 1022 1023 1024 1025

	curseg = CURSEG_I(sbi, type);

	mutex_lock(&curseg->curseg_mutex);
	mutex_lock(&sit_i->sentry_lock);

	segno = GET_SEGNO(sbi, new_blkaddr);
	old_cursegno = curseg->segno;

	/* change the current segment */
	if (segno != curseg->segno) {
		curseg->next_segno = segno;
		change_curseg(sbi, type, true);
	}
J
Jaegeuk Kim 已提交
1026
	curseg->next_blkoff = GET_BLKOFF_FROM_SEG0(sbi, new_blkaddr);
1027
	__add_sum_entry(sbi, type, sum);
J
Jaegeuk Kim 已提交
1028 1029 1030 1031 1032 1033

	/* change the current log to the next block addr in advance */
	if (next_segno != segno) {
		curseg->next_segno = next_segno;
		change_curseg(sbi, type, true);
	}
J
Jaegeuk Kim 已提交
1034
	curseg->next_blkoff = GET_BLKOFF_FROM_SEG0(sbi, next_blkaddr);
J
Jaegeuk Kim 已提交
1035 1036 1037

	/* rewrite node page */
	set_page_writeback(page);
J
Jaegeuk Kim 已提交
1038 1039
	f2fs_submit_page_mbio(sbi, page, new_blkaddr, &fio);
	f2fs_submit_merged_bio(sbi, NODE, WRITE);
J
Jaegeuk Kim 已提交
1040 1041 1042 1043 1044 1045 1046
	refresh_sit_entry(sbi, old_blkaddr, new_blkaddr);
	locate_dirty_segment(sbi, old_cursegno);

	mutex_unlock(&sit_i->sentry_lock);
	mutex_unlock(&curseg->curseg_mutex);
}

1047 1048 1049 1050 1051 1052 1053 1054 1055
static inline bool is_merged_page(struct f2fs_sb_info *sbi,
					struct page *page, enum page_type type)
{
	enum page_type btype = PAGE_TYPE_OF_BIO(type);
	struct f2fs_bio_info *io = &sbi->write_io[btype];
	struct bio_vec *bvec;
	int i;

	down_read(&io->io_rwsem);
1056
	if (!io->bio)
1057 1058
		goto out;

1059
	bio_for_each_segment_all(bvec, io->bio, i) {
1060 1061 1062 1063 1064 1065 1066 1067 1068 1069 1070
		if (page == bvec->bv_page) {
			up_read(&io->io_rwsem);
			return true;
		}
	}

out:
	up_read(&io->io_rwsem);
	return false;
}

1071
void f2fs_wait_on_page_writeback(struct page *page,
1072
				enum page_type type)
1073 1074 1075
{
	struct f2fs_sb_info *sbi = F2FS_SB(page->mapping->host->i_sb);
	if (PageWriteback(page)) {
1076 1077
		if (is_merged_page(sbi, page, type))
			f2fs_submit_merged_bio(sbi, type, WRITE);
1078 1079 1080 1081
		wait_on_page_writeback(page);
	}
}

J
Jaegeuk Kim 已提交
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
static int read_compacted_summaries(struct f2fs_sb_info *sbi)
{
	struct f2fs_checkpoint *ckpt = F2FS_CKPT(sbi);
	struct curseg_info *seg_i;
	unsigned char *kaddr;
	struct page *page;
	block_t start;
	int i, j, offset;

	start = start_sum_block(sbi);

	page = get_meta_page(sbi, start++);
	kaddr = (unsigned char *)page_address(page);

	/* Step 1: restore nat cache */
	seg_i = CURSEG_I(sbi, CURSEG_HOT_DATA);
	memcpy(&seg_i->sum_blk->n_nats, kaddr, SUM_JOURNAL_SIZE);

	/* Step 2: restore sit cache */
	seg_i = CURSEG_I(sbi, CURSEG_COLD_DATA);
	memcpy(&seg_i->sum_blk->n_sits, kaddr + SUM_JOURNAL_SIZE,
						SUM_JOURNAL_SIZE);
	offset = 2 * SUM_JOURNAL_SIZE;

	/* Step 3: restore summary entries */
	for (i = CURSEG_HOT_DATA; i <= CURSEG_COLD_DATA; i++) {
		unsigned short blk_off;
		unsigned int segno;

		seg_i = CURSEG_I(sbi, i);
		segno = le32_to_cpu(ckpt->cur_data_segno[i]);
		blk_off = le16_to_cpu(ckpt->cur_data_blkoff[i]);
		seg_i->next_segno = segno;
		reset_curseg(sbi, i, 0);
		seg_i->alloc_type = ckpt->alloc_type[i];
		seg_i->next_blkoff = blk_off;

		if (seg_i->alloc_type == SSR)
			blk_off = sbi->blocks_per_seg;

		for (j = 0; j < blk_off; j++) {
			struct f2fs_summary *s;
			s = (struct f2fs_summary *)(kaddr + offset);
			seg_i->sum_blk->entries[j] = *s;
			offset += SUMMARY_SIZE;
			if (offset + SUMMARY_SIZE <= PAGE_CACHE_SIZE -
						SUM_FOOTER_SIZE)
				continue;

			f2fs_put_page(page, 1);
			page = NULL;

			page = get_meta_page(sbi, start++);
			kaddr = (unsigned char *)page_address(page);
			offset = 0;
		}
	}
	f2fs_put_page(page, 1);
	return 0;
}

static int read_normal_summaries(struct f2fs_sb_info *sbi, int type)
{
	struct f2fs_checkpoint *ckpt = F2FS_CKPT(sbi);
	struct f2fs_summary_block *sum;
	struct curseg_info *curseg;
	struct page *new;
	unsigned short blk_off;
	unsigned int segno = 0;
	block_t blk_addr = 0;

	/* get segment number and block addr */
	if (IS_DATASEG(type)) {
		segno = le32_to_cpu(ckpt->cur_data_segno[type]);
		blk_off = le16_to_cpu(ckpt->cur_data_blkoff[type -
							CURSEG_HOT_DATA]);
1158
		if (is_set_ckpt_flags(ckpt, CP_UMOUNT_FLAG))
J
Jaegeuk Kim 已提交
1159 1160 1161 1162 1163 1164 1165 1166
			blk_addr = sum_blk_addr(sbi, NR_CURSEG_TYPE, type);
		else
			blk_addr = sum_blk_addr(sbi, NR_CURSEG_DATA_TYPE, type);
	} else {
		segno = le32_to_cpu(ckpt->cur_node_segno[type -
							CURSEG_HOT_NODE]);
		blk_off = le16_to_cpu(ckpt->cur_node_blkoff[type -
							CURSEG_HOT_NODE]);
1167
		if (is_set_ckpt_flags(ckpt, CP_UMOUNT_FLAG))
J
Jaegeuk Kim 已提交
1168 1169 1170 1171 1172 1173 1174 1175 1176 1177
			blk_addr = sum_blk_addr(sbi, NR_CURSEG_NODE_TYPE,
							type - CURSEG_HOT_NODE);
		else
			blk_addr = GET_SUM_BLOCK(sbi, segno);
	}

	new = get_meta_page(sbi, blk_addr);
	sum = (struct f2fs_summary_block *)page_address(new);

	if (IS_NODESEG(type)) {
1178
		if (is_set_ckpt_flags(ckpt, CP_UMOUNT_FLAG)) {
J
Jaegeuk Kim 已提交
1179 1180 1181 1182 1183 1184 1185
			struct f2fs_summary *ns = &sum->entries[0];
			int i;
			for (i = 0; i < sbi->blocks_per_seg; i++, ns++) {
				ns->version = 0;
				ns->ofs_in_node = 0;
			}
		} else {
1186 1187 1188 1189
			int err;

			err = restore_node_summary(sbi, segno, sum);
			if (err) {
J
Jaegeuk Kim 已提交
1190
				f2fs_put_page(new, 1);
1191
				return err;
J
Jaegeuk Kim 已提交
1192 1193 1194 1195 1196 1197 1198 1199 1200 1201 1202 1203 1204 1205 1206 1207 1208 1209 1210 1211
			}
		}
	}

	/* set uncompleted segment to curseg */
	curseg = CURSEG_I(sbi, type);
	mutex_lock(&curseg->curseg_mutex);
	memcpy(curseg->sum_blk, sum, PAGE_CACHE_SIZE);
	curseg->next_segno = segno;
	reset_curseg(sbi, type, 0);
	curseg->alloc_type = ckpt->alloc_type[type];
	curseg->next_blkoff = blk_off;
	mutex_unlock(&curseg->curseg_mutex);
	f2fs_put_page(new, 1);
	return 0;
}

static int restore_curseg_summaries(struct f2fs_sb_info *sbi)
{
	int type = CURSEG_HOT_DATA;
1212
	int err;
J
Jaegeuk Kim 已提交
1213

1214
	if (is_set_ckpt_flags(F2FS_CKPT(sbi), CP_COMPACT_SUM_FLAG)) {
J
Jaegeuk Kim 已提交
1215 1216 1217 1218 1219 1220
		/* restore for compacted data summary */
		if (read_compacted_summaries(sbi))
			return -EINVAL;
		type = CURSEG_HOT_NODE;
	}

1221 1222 1223 1224 1225 1226
	for (; type <= CURSEG_COLD_NODE; type++) {
		err = read_normal_summaries(sbi, type);
		if (err)
			return err;
	}

J
Jaegeuk Kim 已提交
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
	return 0;
}

static void write_compacted_summaries(struct f2fs_sb_info *sbi, block_t blkaddr)
{
	struct page *page;
	unsigned char *kaddr;
	struct f2fs_summary *summary;
	struct curseg_info *seg_i;
	int written_size = 0;
	int i, j;

	page = grab_meta_page(sbi, blkaddr++);
	kaddr = (unsigned char *)page_address(page);

	/* Step 1: write nat cache */
	seg_i = CURSEG_I(sbi, CURSEG_HOT_DATA);
	memcpy(kaddr, &seg_i->sum_blk->n_nats, SUM_JOURNAL_SIZE);
	written_size += SUM_JOURNAL_SIZE;

	/* Step 2: write sit cache */
	seg_i = CURSEG_I(sbi, CURSEG_COLD_DATA);
	memcpy(kaddr + written_size, &seg_i->sum_blk->n_sits,
						SUM_JOURNAL_SIZE);
	written_size += SUM_JOURNAL_SIZE;

	/* Step 3: write summary entries */
	for (i = CURSEG_HOT_DATA; i <= CURSEG_COLD_DATA; i++) {
		unsigned short blkoff;
		seg_i = CURSEG_I(sbi, i);
		if (sbi->ckpt->alloc_type[i] == SSR)
			blkoff = sbi->blocks_per_seg;
		else
			blkoff = curseg_blkoff(sbi, i);

		for (j = 0; j < blkoff; j++) {
			if (!page) {
				page = grab_meta_page(sbi, blkaddr++);
				kaddr = (unsigned char *)page_address(page);
				written_size = 0;
			}
			summary = (struct f2fs_summary *)(kaddr + written_size);
			*summary = seg_i->sum_blk->entries[j];
			written_size += SUMMARY_SIZE;

			if (written_size + SUMMARY_SIZE <= PAGE_CACHE_SIZE -
							SUM_FOOTER_SIZE)
				continue;

1276
			set_page_dirty(page);
J
Jaegeuk Kim 已提交
1277 1278 1279 1280
			f2fs_put_page(page, 1);
			page = NULL;
		}
	}
1281 1282
	if (page) {
		set_page_dirty(page);
J
Jaegeuk Kim 已提交
1283
		f2fs_put_page(page, 1);
1284
	}
J
Jaegeuk Kim 已提交
1285 1286 1287 1288 1289 1290 1291 1292 1293 1294 1295 1296 1297 1298 1299 1300 1301 1302 1303 1304 1305
}

static void write_normal_summaries(struct f2fs_sb_info *sbi,
					block_t blkaddr, int type)
{
	int i, end;
	if (IS_DATASEG(type))
		end = type + NR_CURSEG_DATA_TYPE;
	else
		end = type + NR_CURSEG_NODE_TYPE;

	for (i = type; i < end; i++) {
		struct curseg_info *sum = CURSEG_I(sbi, i);
		mutex_lock(&sum->curseg_mutex);
		write_sum_page(sbi, sum->sum_blk, blkaddr + (i - type));
		mutex_unlock(&sum->curseg_mutex);
	}
}

void write_data_summaries(struct f2fs_sb_info *sbi, block_t start_blk)
{
1306
	if (is_set_ckpt_flags(F2FS_CKPT(sbi), CP_COMPACT_SUM_FLAG))
J
Jaegeuk Kim 已提交
1307 1308 1309 1310 1311 1312 1313
		write_compacted_summaries(sbi, start_blk);
	else
		write_normal_summaries(sbi, start_blk, CURSEG_HOT_DATA);
}

void write_node_summaries(struct f2fs_sb_info *sbi, block_t start_blk)
{
1314
	if (is_set_ckpt_flags(F2FS_CKPT(sbi), CP_UMOUNT_FLAG))
J
Jaegeuk Kim 已提交
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
		write_normal_summaries(sbi, start_blk, CURSEG_HOT_NODE);
}

int lookup_journal_in_cursum(struct f2fs_summary_block *sum, int type,
					unsigned int val, int alloc)
{
	int i;

	if (type == NAT_JOURNAL) {
		for (i = 0; i < nats_in_cursum(sum); i++) {
			if (le32_to_cpu(nid_in_journal(sum, i)) == val)
				return i;
		}
		if (alloc && nats_in_cursum(sum) < NAT_JOURNAL_ENTRIES)
			return update_nats_in_cursum(sum, 1);
	} else if (type == SIT_JOURNAL) {
		for (i = 0; i < sits_in_cursum(sum); i++)
			if (le32_to_cpu(segno_in_journal(sum, i)) == val)
				return i;
		if (alloc && sits_in_cursum(sum) < SIT_JOURNAL_ENTRIES)
			return update_sits_in_cursum(sum, 1);
	}
	return -1;
}

static struct page *get_current_sit_page(struct f2fs_sb_info *sbi,
					unsigned int segno)
{
	struct sit_info *sit_i = SIT_I(sbi);
	unsigned int offset = SIT_BLOCK_OFFSET(sit_i, segno);
	block_t blk_addr = sit_i->sit_base_addr + offset;

	check_seg_range(sbi, segno);

	/* calculate sit block address */
	if (f2fs_test_bit(offset, sit_i->sit_bitmap))
		blk_addr += sit_i->sit_blocks;

	return get_meta_page(sbi, blk_addr);
}

static struct page *get_next_sit_page(struct f2fs_sb_info *sbi,
					unsigned int start)
{
	struct sit_info *sit_i = SIT_I(sbi);
	struct page *src_page, *dst_page;
	pgoff_t src_off, dst_off;
	void *src_addr, *dst_addr;

	src_off = current_sit_addr(sbi, start);
	dst_off = next_sit_addr(sbi, src_off);

	/* get current sit block page without lock */
	src_page = get_meta_page(sbi, src_off);
	dst_page = grab_meta_page(sbi, dst_off);
1370
	f2fs_bug_on(PageDirty(src_page));
J
Jaegeuk Kim 已提交
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

	src_addr = page_address(src_page);
	dst_addr = page_address(dst_page);
	memcpy(dst_addr, src_addr, PAGE_CACHE_SIZE);

	set_page_dirty(dst_page);
	f2fs_put_page(src_page, 1);

	set_to_next_sit(sit_i, start);

	return dst_page;
}

static bool flush_sits_in_journal(struct f2fs_sb_info *sbi)
{
	struct curseg_info *curseg = CURSEG_I(sbi, CURSEG_COLD_DATA);
	struct f2fs_summary_block *sum = curseg->sum_blk;
	int i;

	/*
	 * If the journal area in the current summary is full of sit entries,
	 * all the sit entries will be flushed. Otherwise the sit entries
	 * are not able to replace with newly hot sit entries.
	 */
	if (sits_in_cursum(sum) >= SIT_JOURNAL_ENTRIES) {
		for (i = sits_in_cursum(sum) - 1; i >= 0; i--) {
			unsigned int segno;
			segno = le32_to_cpu(segno_in_journal(sum, i));
			__mark_sit_entry_dirty(sbi, segno);
		}
		update_sits_in_cursum(sum, -sits_in_cursum(sum));
1402
		return true;
J
Jaegeuk Kim 已提交
1403
	}
1404
	return false;
J
Jaegeuk Kim 已提交
1405 1406
}

J
Jaegeuk Kim 已提交
1407
/*
J
Jaegeuk Kim 已提交
1408 1409 1410 1411 1412 1413 1414 1415 1416 1417 1418 1419 1420 1421 1422 1423 1424 1425 1426 1427 1428 1429 1430 1431 1432 1433 1434 1435 1436 1437 1438
 * CP calls this function, which flushes SIT entries including sit_journal,
 * and moves prefree segs to free segs.
 */
void flush_sit_entries(struct f2fs_sb_info *sbi)
{
	struct sit_info *sit_i = SIT_I(sbi);
	unsigned long *bitmap = sit_i->dirty_sentries_bitmap;
	struct curseg_info *curseg = CURSEG_I(sbi, CURSEG_COLD_DATA);
	struct f2fs_summary_block *sum = curseg->sum_blk;
	unsigned long nsegs = TOTAL_SEGS(sbi);
	struct page *page = NULL;
	struct f2fs_sit_block *raw_sit = NULL;
	unsigned int start = 0, end = 0;
	unsigned int segno = -1;
	bool flushed;

	mutex_lock(&curseg->curseg_mutex);
	mutex_lock(&sit_i->sentry_lock);

	/*
	 * "flushed" indicates whether sit entries in journal are flushed
	 * to the SIT area or not.
	 */
	flushed = flush_sits_in_journal(sbi);

	while ((segno = find_next_bit(bitmap, nsegs, segno + 1)) < nsegs) {
		struct seg_entry *se = get_seg_entry(sbi, segno);
		int sit_offset, offset;

		sit_offset = SIT_ENTRY_OFFSET(sit_i, segno);

1439 1440 1441 1442
		/* add discard candidates */
		if (SM_I(sbi)->nr_discards < SM_I(sbi)->max_discards)
			add_discard_addrs(sbi, segno, se);

J
Jaegeuk Kim 已提交
1443 1444 1445 1446 1447 1448 1449 1450 1451 1452 1453 1454 1455 1456 1457 1458 1459 1460 1461 1462 1463 1464 1465 1466 1467 1468 1469 1470 1471 1472 1473 1474 1475 1476 1477 1478 1479 1480 1481 1482 1483 1484 1485 1486 1487 1488 1489 1490 1491 1492 1493 1494 1495 1496 1497 1498 1499 1500 1501 1502 1503 1504 1505 1506 1507 1508 1509 1510 1511 1512 1513 1514 1515 1516 1517
		if (flushed)
			goto to_sit_page;

		offset = lookup_journal_in_cursum(sum, SIT_JOURNAL, segno, 1);
		if (offset >= 0) {
			segno_in_journal(sum, offset) = cpu_to_le32(segno);
			seg_info_to_raw_sit(se, &sit_in_journal(sum, offset));
			goto flush_done;
		}
to_sit_page:
		if (!page || (start > segno) || (segno > end)) {
			if (page) {
				f2fs_put_page(page, 1);
				page = NULL;
			}

			start = START_SEGNO(sit_i, segno);
			end = start + SIT_ENTRY_PER_BLOCK - 1;

			/* read sit block that will be updated */
			page = get_next_sit_page(sbi, start);
			raw_sit = page_address(page);
		}

		/* udpate entry in SIT block */
		seg_info_to_raw_sit(se, &raw_sit->entries[sit_offset]);
flush_done:
		__clear_bit(segno, bitmap);
		sit_i->dirty_sentries--;
	}
	mutex_unlock(&sit_i->sentry_lock);
	mutex_unlock(&curseg->curseg_mutex);

	/* writeout last modified SIT block */
	f2fs_put_page(page, 1);

	set_prefree_as_free_segments(sbi);
}

static int build_sit_info(struct f2fs_sb_info *sbi)
{
	struct f2fs_super_block *raw_super = F2FS_RAW_SUPER(sbi);
	struct f2fs_checkpoint *ckpt = F2FS_CKPT(sbi);
	struct sit_info *sit_i;
	unsigned int sit_segs, start;
	char *src_bitmap, *dst_bitmap;
	unsigned int bitmap_size;

	/* allocate memory for SIT information */
	sit_i = kzalloc(sizeof(struct sit_info), GFP_KERNEL);
	if (!sit_i)
		return -ENOMEM;

	SM_I(sbi)->sit_info = sit_i;

	sit_i->sentries = vzalloc(TOTAL_SEGS(sbi) * sizeof(struct seg_entry));
	if (!sit_i->sentries)
		return -ENOMEM;

	bitmap_size = f2fs_bitmap_size(TOTAL_SEGS(sbi));
	sit_i->dirty_sentries_bitmap = kzalloc(bitmap_size, GFP_KERNEL);
	if (!sit_i->dirty_sentries_bitmap)
		return -ENOMEM;

	for (start = 0; start < TOTAL_SEGS(sbi); start++) {
		sit_i->sentries[start].cur_valid_map
			= kzalloc(SIT_VBLOCK_MAP_SIZE, GFP_KERNEL);
		sit_i->sentries[start].ckpt_valid_map
			= kzalloc(SIT_VBLOCK_MAP_SIZE, GFP_KERNEL);
		if (!sit_i->sentries[start].cur_valid_map
				|| !sit_i->sentries[start].ckpt_valid_map)
			return -ENOMEM;
	}

	if (sbi->segs_per_sec > 1) {
J
Jaegeuk Kim 已提交
1518
		sit_i->sec_entries = vzalloc(TOTAL_SECS(sbi) *
J
Jaegeuk Kim 已提交
1519 1520 1521 1522 1523 1524 1525 1526 1527 1528 1529 1530
					sizeof(struct sec_entry));
		if (!sit_i->sec_entries)
			return -ENOMEM;
	}

	/* get information related with SIT */
	sit_segs = le32_to_cpu(raw_super->segment_count_sit) >> 1;

	/* setup SIT bitmap from ckeckpoint pack */
	bitmap_size = __bitmap_size(sbi, SIT_BITMAP);
	src_bitmap = __bitmap_ptr(sbi, SIT_BITMAP);

A
Alexandru Gheorghiu 已提交
1531
	dst_bitmap = kmemdup(src_bitmap, bitmap_size, GFP_KERNEL);
J
Jaegeuk Kim 已提交
1532 1533 1534 1535 1536 1537 1538 1539 1540 1541 1542 1543 1544 1545 1546 1547 1548 1549 1550 1551 1552 1553 1554 1555 1556 1557 1558 1559 1560 1561 1562 1563 1564 1565 1566 1567 1568
	if (!dst_bitmap)
		return -ENOMEM;

	/* init SIT information */
	sit_i->s_ops = &default_salloc_ops;

	sit_i->sit_base_addr = le32_to_cpu(raw_super->sit_blkaddr);
	sit_i->sit_blocks = sit_segs << sbi->log_blocks_per_seg;
	sit_i->written_valid_blocks = le64_to_cpu(ckpt->valid_block_count);
	sit_i->sit_bitmap = dst_bitmap;
	sit_i->bitmap_size = bitmap_size;
	sit_i->dirty_sentries = 0;
	sit_i->sents_per_block = SIT_ENTRY_PER_BLOCK;
	sit_i->elapsed_time = le64_to_cpu(sbi->ckpt->elapsed_time);
	sit_i->mounted_time = CURRENT_TIME_SEC.tv_sec;
	mutex_init(&sit_i->sentry_lock);
	return 0;
}

static int build_free_segmap(struct f2fs_sb_info *sbi)
{
	struct f2fs_sm_info *sm_info = SM_I(sbi);
	struct free_segmap_info *free_i;
	unsigned int bitmap_size, sec_bitmap_size;

	/* allocate memory for free segmap information */
	free_i = kzalloc(sizeof(struct free_segmap_info), GFP_KERNEL);
	if (!free_i)
		return -ENOMEM;

	SM_I(sbi)->free_info = free_i;

	bitmap_size = f2fs_bitmap_size(TOTAL_SEGS(sbi));
	free_i->free_segmap = kmalloc(bitmap_size, GFP_KERNEL);
	if (!free_i->free_segmap)
		return -ENOMEM;

J
Jaegeuk Kim 已提交
1569
	sec_bitmap_size = f2fs_bitmap_size(TOTAL_SECS(sbi));
J
Jaegeuk Kim 已提交
1570 1571 1572 1573 1574 1575 1576 1577 1578 1579 1580 1581 1582 1583 1584 1585 1586 1587 1588
	free_i->free_secmap = kmalloc(sec_bitmap_size, GFP_KERNEL);
	if (!free_i->free_secmap)
		return -ENOMEM;

	/* set all segments as dirty temporarily */
	memset(free_i->free_segmap, 0xff, bitmap_size);
	memset(free_i->free_secmap, 0xff, sec_bitmap_size);

	/* init free segmap information */
	free_i->start_segno =
		(unsigned int) GET_SEGNO_FROM_SEG0(sbi, sm_info->main_blkaddr);
	free_i->free_segments = 0;
	free_i->free_sections = 0;
	rwlock_init(&free_i->segmap_lock);
	return 0;
}

static int build_curseg(struct f2fs_sb_info *sbi)
{
N
Namjae Jeon 已提交
1589
	struct curseg_info *array;
J
Jaegeuk Kim 已提交
1590 1591 1592 1593 1594 1595 1596 1597 1598 1599 1600 1601 1602 1603 1604 1605 1606 1607 1608 1609 1610 1611 1612 1613
	int i;

	array = kzalloc(sizeof(*array) * NR_CURSEG_TYPE, GFP_KERNEL);
	if (!array)
		return -ENOMEM;

	SM_I(sbi)->curseg_array = array;

	for (i = 0; i < NR_CURSEG_TYPE; i++) {
		mutex_init(&array[i].curseg_mutex);
		array[i].sum_blk = kzalloc(PAGE_CACHE_SIZE, GFP_KERNEL);
		if (!array[i].sum_blk)
			return -ENOMEM;
		array[i].segno = NULL_SEGNO;
		array[i].next_blkoff = 0;
	}
	return restore_curseg_summaries(sbi);
}

static void build_sit_entries(struct f2fs_sb_info *sbi)
{
	struct sit_info *sit_i = SIT_I(sbi);
	struct curseg_info *curseg = CURSEG_I(sbi, CURSEG_COLD_DATA);
	struct f2fs_summary_block *sum = curseg->sum_blk;
1614 1615 1616 1617
	int sit_blk_cnt = SIT_BLK_CNT(sbi);
	unsigned int i, start, end;
	unsigned int readed, start_blk = 0;
	int nrpages = MAX_BIO_BLOCKS(max_hw_blocks(sbi));
J
Jaegeuk Kim 已提交
1618

1619
	do {
1620
		readed = ra_meta_pages(sbi, start_blk, nrpages, META_SIT);
1621 1622 1623 1624 1625 1626 1627 1628 1629 1630 1631 1632

		start = start_blk * sit_i->sents_per_block;
		end = (start_blk + readed) * sit_i->sents_per_block;

		for (; start < end && start < TOTAL_SEGS(sbi); start++) {
			struct seg_entry *se = &sit_i->sentries[start];
			struct f2fs_sit_block *sit_blk;
			struct f2fs_sit_entry sit;
			struct page *page;

			mutex_lock(&curseg->curseg_mutex);
			for (i = 0; i < sits_in_cursum(sum); i++) {
C
Chris Fries 已提交
1633 1634
				if (le32_to_cpu(segno_in_journal(sum, i))
								== start) {
1635 1636 1637 1638
					sit = sit_in_journal(sum, i);
					mutex_unlock(&curseg->curseg_mutex);
					goto got_it;
				}
J
Jaegeuk Kim 已提交
1639
			}
1640 1641 1642 1643 1644 1645
			mutex_unlock(&curseg->curseg_mutex);

			page = get_current_sit_page(sbi, start);
			sit_blk = (struct f2fs_sit_block *)page_address(page);
			sit = sit_blk->entries[SIT_ENTRY_OFFSET(sit_i, start)];
			f2fs_put_page(page, 1);
J
Jaegeuk Kim 已提交
1646
got_it:
1647 1648 1649 1650 1651 1652
			check_block_count(sbi, start, &sit);
			seg_info_from_raw_sit(se, &sit);
			if (sbi->segs_per_sec > 1) {
				struct sec_entry *e = get_sec_entry(sbi, start);
				e->valid_blocks += se->valid_blocks;
			}
J
Jaegeuk Kim 已提交
1653
		}
1654 1655
		start_blk += readed;
	} while (start_blk < sit_blk_cnt);
J
Jaegeuk Kim 已提交
1656 1657 1658 1659 1660 1661 1662 1663 1664 1665 1666 1667 1668 1669 1670 1671 1672 1673 1674 1675 1676 1677 1678 1679
}

static void init_free_segmap(struct f2fs_sb_info *sbi)
{
	unsigned int start;
	int type;

	for (start = 0; start < TOTAL_SEGS(sbi); start++) {
		struct seg_entry *sentry = get_seg_entry(sbi, start);
		if (!sentry->valid_blocks)
			__set_free(sbi, start);
	}

	/* set use the current segments */
	for (type = CURSEG_HOT_DATA; type <= CURSEG_COLD_NODE; type++) {
		struct curseg_info *curseg_t = CURSEG_I(sbi, type);
		__set_test_and_inuse(sbi, curseg_t->segno);
	}
}

static void init_dirty_segmap(struct f2fs_sb_info *sbi)
{
	struct dirty_seglist_info *dirty_i = DIRTY_I(sbi);
	struct free_segmap_info *free_i = FREE_I(sbi);
1680
	unsigned int segno = 0, offset = 0, total_segs = TOTAL_SEGS(sbi);
J
Jaegeuk Kim 已提交
1681 1682
	unsigned short valid_blocks;

1683
	while (1) {
J
Jaegeuk Kim 已提交
1684
		/* find dirty segment based on free segmap */
1685 1686
		segno = find_next_inuse(free_i, total_segs, offset);
		if (segno >= total_segs)
J
Jaegeuk Kim 已提交
1687 1688 1689 1690 1691 1692 1693 1694 1695 1696 1697
			break;
		offset = segno + 1;
		valid_blocks = get_valid_blocks(sbi, segno, 0);
		if (valid_blocks >= sbi->blocks_per_seg || !valid_blocks)
			continue;
		mutex_lock(&dirty_i->seglist_lock);
		__locate_dirty_segment(sbi, segno, DIRTY);
		mutex_unlock(&dirty_i->seglist_lock);
	}
}

1698
static int init_victim_secmap(struct f2fs_sb_info *sbi)
J
Jaegeuk Kim 已提交
1699 1700
{
	struct dirty_seglist_info *dirty_i = DIRTY_I(sbi);
1701
	unsigned int bitmap_size = f2fs_bitmap_size(TOTAL_SECS(sbi));
J
Jaegeuk Kim 已提交
1702

1703 1704
	dirty_i->victim_secmap = kzalloc(bitmap_size, GFP_KERNEL);
	if (!dirty_i->victim_secmap)
J
Jaegeuk Kim 已提交
1705 1706 1707 1708 1709 1710 1711 1712 1713 1714 1715 1716 1717 1718 1719 1720 1721 1722 1723 1724 1725 1726 1727 1728 1729 1730
		return -ENOMEM;
	return 0;
}

static int build_dirty_segmap(struct f2fs_sb_info *sbi)
{
	struct dirty_seglist_info *dirty_i;
	unsigned int bitmap_size, i;

	/* allocate memory for dirty segments list information */
	dirty_i = kzalloc(sizeof(struct dirty_seglist_info), GFP_KERNEL);
	if (!dirty_i)
		return -ENOMEM;

	SM_I(sbi)->dirty_info = dirty_i;
	mutex_init(&dirty_i->seglist_lock);

	bitmap_size = f2fs_bitmap_size(TOTAL_SEGS(sbi));

	for (i = 0; i < NR_DIRTY_TYPE; i++) {
		dirty_i->dirty_segmap[i] = kzalloc(bitmap_size, GFP_KERNEL);
		if (!dirty_i->dirty_segmap[i])
			return -ENOMEM;
	}

	init_dirty_segmap(sbi);
1731
	return init_victim_secmap(sbi);
J
Jaegeuk Kim 已提交
1732 1733
}

J
Jaegeuk Kim 已提交
1734
/*
J
Jaegeuk Kim 已提交
1735 1736 1737 1738 1739 1740 1741 1742 1743 1744 1745 1746 1747 1748 1749 1750 1751 1752 1753 1754 1755 1756 1757 1758 1759 1760 1761 1762 1763 1764 1765
 * Update min, max modified time for cost-benefit GC algorithm
 */
static void init_min_max_mtime(struct f2fs_sb_info *sbi)
{
	struct sit_info *sit_i = SIT_I(sbi);
	unsigned int segno;

	mutex_lock(&sit_i->sentry_lock);

	sit_i->min_mtime = LLONG_MAX;

	for (segno = 0; segno < TOTAL_SEGS(sbi); segno += sbi->segs_per_sec) {
		unsigned int i;
		unsigned long long mtime = 0;

		for (i = 0; i < sbi->segs_per_sec; i++)
			mtime += get_seg_entry(sbi, segno + i)->mtime;

		mtime = div_u64(mtime, sbi->segs_per_sec);

		if (sit_i->min_mtime > mtime)
			sit_i->min_mtime = mtime;
	}
	sit_i->max_mtime = get_mtime(sbi);
	mutex_unlock(&sit_i->sentry_lock);
}

int build_segment_manager(struct f2fs_sb_info *sbi)
{
	struct f2fs_super_block *raw_super = F2FS_RAW_SUPER(sbi);
	struct f2fs_checkpoint *ckpt = F2FS_CKPT(sbi);
N
Namjae Jeon 已提交
1766
	struct f2fs_sm_info *sm_info;
J
Jaegeuk Kim 已提交
1767 1768 1769 1770 1771 1772 1773 1774 1775 1776 1777 1778 1779 1780 1781 1782 1783
	int err;

	sm_info = kzalloc(sizeof(struct f2fs_sm_info), GFP_KERNEL);
	if (!sm_info)
		return -ENOMEM;

	/* init sm info */
	sbi->sm_info = sm_info;
	INIT_LIST_HEAD(&sm_info->wblist_head);
	spin_lock_init(&sm_info->wblist_lock);
	sm_info->seg0_blkaddr = le32_to_cpu(raw_super->segment0_blkaddr);
	sm_info->main_blkaddr = le32_to_cpu(raw_super->main_blkaddr);
	sm_info->segment_count = le32_to_cpu(raw_super->segment_count);
	sm_info->reserved_segments = le32_to_cpu(ckpt->rsvd_segment_count);
	sm_info->ovp_segments = le32_to_cpu(ckpt->overprov_segment_count);
	sm_info->main_segments = le32_to_cpu(raw_super->segment_count_main);
	sm_info->ssa_blkaddr = le32_to_cpu(raw_super->ssa_blkaddr);
1784 1785
	sm_info->rec_prefree_segments = sm_info->main_segments *
					DEF_RECLAIM_PREFREE_SEGMENTS / 100;
1786 1787
	sm_info->ipu_policy = F2FS_IPU_DISABLE;
	sm_info->min_ipu_util = DEF_MIN_IPU_UTIL;
J
Jaegeuk Kim 已提交
1788

1789 1790 1791 1792
	INIT_LIST_HEAD(&sm_info->discard_list);
	sm_info->nr_discards = 0;
	sm_info->max_discards = 0;

J
Jaegeuk Kim 已提交
1793 1794 1795 1796 1797 1798 1799 1800 1801 1802 1803 1804 1805 1806 1807 1808 1809 1810 1811 1812 1813 1814 1815 1816 1817 1818 1819 1820 1821 1822 1823 1824 1825
	err = build_sit_info(sbi);
	if (err)
		return err;
	err = build_free_segmap(sbi);
	if (err)
		return err;
	err = build_curseg(sbi);
	if (err)
		return err;

	/* reinit free segmap based on SIT */
	build_sit_entries(sbi);

	init_free_segmap(sbi);
	err = build_dirty_segmap(sbi);
	if (err)
		return err;

	init_min_max_mtime(sbi);
	return 0;
}

static void discard_dirty_segmap(struct f2fs_sb_info *sbi,
		enum dirty_type dirty_type)
{
	struct dirty_seglist_info *dirty_i = DIRTY_I(sbi);

	mutex_lock(&dirty_i->seglist_lock);
	kfree(dirty_i->dirty_segmap[dirty_type]);
	dirty_i->nr_dirty[dirty_type] = 0;
	mutex_unlock(&dirty_i->seglist_lock);
}

1826
static void destroy_victim_secmap(struct f2fs_sb_info *sbi)
J
Jaegeuk Kim 已提交
1827 1828
{
	struct dirty_seglist_info *dirty_i = DIRTY_I(sbi);
1829
	kfree(dirty_i->victim_secmap);
J
Jaegeuk Kim 已提交
1830 1831 1832 1833 1834 1835 1836 1837 1838 1839 1840 1841 1842 1843
}

static void destroy_dirty_segmap(struct f2fs_sb_info *sbi)
{
	struct dirty_seglist_info *dirty_i = DIRTY_I(sbi);
	int i;

	if (!dirty_i)
		return;

	/* discard pre-free/dirty segments list */
	for (i = 0; i < NR_DIRTY_TYPE; i++)
		discard_dirty_segmap(sbi, i);

1844
	destroy_victim_secmap(sbi);
J
Jaegeuk Kim 已提交
1845 1846 1847 1848 1849 1850 1851 1852 1853 1854 1855 1856 1857 1858 1859 1860 1861 1862 1863 1864 1865 1866 1867 1868 1869 1870 1871 1872 1873 1874 1875 1876 1877 1878 1879 1880 1881 1882 1883 1884 1885 1886 1887 1888 1889 1890 1891 1892 1893 1894 1895 1896 1897 1898
	SM_I(sbi)->dirty_info = NULL;
	kfree(dirty_i);
}

static void destroy_curseg(struct f2fs_sb_info *sbi)
{
	struct curseg_info *array = SM_I(sbi)->curseg_array;
	int i;

	if (!array)
		return;
	SM_I(sbi)->curseg_array = NULL;
	for (i = 0; i < NR_CURSEG_TYPE; i++)
		kfree(array[i].sum_blk);
	kfree(array);
}

static void destroy_free_segmap(struct f2fs_sb_info *sbi)
{
	struct free_segmap_info *free_i = SM_I(sbi)->free_info;
	if (!free_i)
		return;
	SM_I(sbi)->free_info = NULL;
	kfree(free_i->free_segmap);
	kfree(free_i->free_secmap);
	kfree(free_i);
}

static void destroy_sit_info(struct f2fs_sb_info *sbi)
{
	struct sit_info *sit_i = SIT_I(sbi);
	unsigned int start;

	if (!sit_i)
		return;

	if (sit_i->sentries) {
		for (start = 0; start < TOTAL_SEGS(sbi); start++) {
			kfree(sit_i->sentries[start].cur_valid_map);
			kfree(sit_i->sentries[start].ckpt_valid_map);
		}
	}
	vfree(sit_i->sentries);
	vfree(sit_i->sec_entries);
	kfree(sit_i->dirty_sentries_bitmap);

	SM_I(sbi)->sit_info = NULL;
	kfree(sit_i->sit_bitmap);
	kfree(sit_i);
}

void destroy_segment_manager(struct f2fs_sb_info *sbi)
{
	struct f2fs_sm_info *sm_info = SM_I(sbi);
1899 1900
	if (!sm_info)
		return;
J
Jaegeuk Kim 已提交
1901 1902 1903 1904 1905 1906 1907
	destroy_dirty_segmap(sbi);
	destroy_curseg(sbi);
	destroy_free_segmap(sbi);
	destroy_sit_info(sbi);
	sbi->sm_info = NULL;
	kfree(sm_info);
}
1908 1909 1910 1911

int __init create_segment_manager_caches(void)
{
	discard_entry_slab = f2fs_kmem_cache_create("discard_entry",
1912
			sizeof(struct discard_entry));
1913 1914 1915 1916 1917 1918 1919 1920 1921
	if (!discard_entry_slab)
		return -ENOMEM;
	return 0;
}

void destroy_segment_manager_caches(void)
{
	kmem_cache_destroy(discard_entry_slab);
}