segment.h 22.6 KB
Newer Older
J
Jaegeuk Kim 已提交
1
/*
2 3 4 5 6 7 8 9 10
 * fs/f2fs/segment.h
 *
 * 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.
 */
11
#include <linux/blkdev.h>
12
#include <linux/backing-dev.h>
13

14 15
/* constant macro */
#define NULL_SEGNO			((unsigned int)(~0))
16
#define NULL_SECNO			((unsigned int)(~0))
17

18
#define DEF_RECLAIM_PREFREE_SEGMENTS	5	/* 5% over total segments */
J
Jaegeuk Kim 已提交
19
#define DEF_MAX_RECLAIM_PREFREE_SEGMENTS	4096	/* 8GB in maximum */
20

J
Jaegeuk Kim 已提交
21 22
#define F2FS_MIN_SEGMENTS	9 /* SB + 2 (CP + SIT + NAT) + SSA + MAIN */

N
Namjae Jeon 已提交
23
/* L: Logical segment # in volume, R: Relative segment # in main area */
24 25 26
#define GET_L2R_SEGNO(free_i, segno)	(segno - free_i->start_segno)
#define GET_R2L_SEGNO(free_i, segno)	(segno + free_i->start_segno)

27 28
#define IS_DATASEG(t)	(t <= CURSEG_COLD_DATA)
#define IS_NODESEG(t)	(t >= CURSEG_HOT_NODE)
29

30 31 32 33 34 35 36
#define IS_CURSEG(sbi, seg)						\
	((seg == CURSEG_I(sbi, CURSEG_HOT_DATA)->segno) ||	\
	 (seg == CURSEG_I(sbi, CURSEG_WARM_DATA)->segno) ||	\
	 (seg == CURSEG_I(sbi, CURSEG_COLD_DATA)->segno) ||	\
	 (seg == CURSEG_I(sbi, CURSEG_HOT_NODE)->segno) ||	\
	 (seg == CURSEG_I(sbi, CURSEG_WARM_NODE)->segno) ||	\
	 (seg == CURSEG_I(sbi, CURSEG_COLD_NODE)->segno))
37 38 39 40 41 42 43 44 45 46 47 48 49 50 51

#define IS_CURSEC(sbi, secno)						\
	((secno == CURSEG_I(sbi, CURSEG_HOT_DATA)->segno /		\
	  sbi->segs_per_sec) ||	\
	 (secno == CURSEG_I(sbi, CURSEG_WARM_DATA)->segno /		\
	  sbi->segs_per_sec) ||	\
	 (secno == CURSEG_I(sbi, CURSEG_COLD_DATA)->segno /		\
	  sbi->segs_per_sec) ||	\
	 (secno == CURSEG_I(sbi, CURSEG_HOT_NODE)->segno /		\
	  sbi->segs_per_sec) ||	\
	 (secno == CURSEG_I(sbi, CURSEG_WARM_NODE)->segno /		\
	  sbi->segs_per_sec) ||	\
	 (secno == CURSEG_I(sbi, CURSEG_COLD_NODE)->segno /		\
	  sbi->segs_per_sec))	\

52 53 54 55 56 57 58 59 60 61
#define MAIN_BLKADDR(sbi)	(SM_I(sbi)->main_blkaddr)
#define SEG0_BLKADDR(sbi)	(SM_I(sbi)->seg0_blkaddr)

#define MAIN_SEGS(sbi)	(SM_I(sbi)->main_segments)
#define MAIN_SECS(sbi)	(sbi->total_sections)

#define TOTAL_SEGS(sbi)	(SM_I(sbi)->segment_count)
#define TOTAL_BLKS(sbi)	(TOTAL_SEGS(sbi) << sbi->log_blocks_per_seg)

#define MAX_BLKADDR(sbi)	(SEG0_BLKADDR(sbi) + TOTAL_BLKS(sbi))
62
#define SEGMENT_SIZE(sbi)	(1ULL << (sbi->log_blocksize +		\
63 64 65
					sbi->log_blocks_per_seg))

#define START_BLOCK(sbi, segno)	(SEG0_BLKADDR(sbi) +			\
66
	 (GET_R2L_SEGNO(FREE_I(sbi), segno) << sbi->log_blocks_per_seg))
67

68 69 70
#define NEXT_FREE_BLKADDR(sbi, curseg)					\
	(START_BLOCK(sbi, curseg->segno) + curseg->next_blkoff)

71
#define GET_SEGOFF_FROM_SEG0(sbi, blk_addr)	((blk_addr) - SEG0_BLKADDR(sbi))
72 73
#define GET_SEGNO_FROM_SEG0(sbi, blk_addr)				\
	(GET_SEGOFF_FROM_SEG0(sbi, blk_addr) >> sbi->log_blocks_per_seg)
J
Jaegeuk Kim 已提交
74 75 76
#define GET_BLKOFF_FROM_SEG0(sbi, blk_addr)				\
	(GET_SEGOFF_FROM_SEG0(sbi, blk_addr) & (sbi->blocks_per_seg - 1))

77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93
#define GET_SEGNO(sbi, blk_addr)					\
	(((blk_addr == NULL_ADDR) || (blk_addr == NEW_ADDR)) ?		\
	NULL_SEGNO : GET_L2R_SEGNO(FREE_I(sbi),			\
		GET_SEGNO_FROM_SEG0(sbi, blk_addr)))
#define GET_SECNO(sbi, segno)					\
	((segno) / sbi->segs_per_sec)
#define GET_ZONENO_FROM_SEGNO(sbi, segno)				\
	((segno / sbi->segs_per_sec) / sbi->secs_per_zone)

#define GET_SUM_BLOCK(sbi, segno)				\
	((sbi->sm_info->ssa_blkaddr) + segno)

#define GET_SUM_TYPE(footer) ((footer)->entry_type)
#define SET_SUM_TYPE(footer, type) ((footer)->entry_type = type)

#define SIT_ENTRY_OFFSET(sit_i, segno)					\
	(segno % sit_i->sents_per_block)
94
#define SIT_BLOCK_OFFSET(segno)					\
95
	(segno / SIT_ENTRY_PER_BLOCK)
96 97
#define	START_SEGNO(segno)		\
	(SIT_BLOCK_OFFSET(segno) * SIT_ENTRY_PER_BLOCK)
98
#define SIT_BLK_CNT(sbi)			\
99
	((MAIN_SEGS(sbi) + SIT_ENTRY_PER_BLOCK - 1) / SIT_ENTRY_PER_BLOCK)
100 101 102
#define f2fs_bitmap_size(nr)			\
	(BITS_TO_LONGS(nr) * sizeof(unsigned long))

C
Chao Yu 已提交
103 104 105 106
#define SECTOR_FROM_BLOCK(blk_addr)					\
	(((sector_t)blk_addr) << F2FS_LOG_SECTORS_PER_BLOCK)
#define SECTOR_TO_BLOCK(sectors)					\
	(sectors >> F2FS_LOG_SECTORS_PER_BLOCK)
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
/*
 * indicate a block allocation direction: RIGHT and LEFT.
 * RIGHT means allocating new sections towards the end of volume.
 * LEFT means the opposite direction.
 */
enum {
	ALLOC_RIGHT = 0,
	ALLOC_LEFT
};

/*
 * In the victim_sel_policy->alloc_mode, there are two block allocation modes.
 * LFS writes data sequentially with cleaning operations.
 * SSR (Slack Space Recycle) reuses obsolete space without cleaning operations.
 */
enum {
	LFS = 0,
	SSR
};

/*
 * In the victim_sel_policy->gc_mode, there are two gc, aka cleaning, modes.
 * GC_CB is based on cost-benefit algorithm.
 * GC_GREEDY is based on greedy algorithm.
 */
enum {
	GC_CB = 0,
	GC_GREEDY
};

/*
 * BG_GC means the background cleaning job.
 * FG_GC means the on-demand cleaning job.
141
 * FORCE_FG_GC means on-demand cleaning job in background.
142 143 144
 */
enum {
	BG_GC = 0,
145 146
	FG_GC,
	FORCE_FG_GC,
147 148 149 150 151 152 153
};

/* for a function parameter to select a victim segment */
struct victim_sel_policy {
	int alloc_mode;			/* LFS or SSR */
	int gc_mode;			/* GC_CB or GC_GREEDY */
	unsigned long *dirty_segmap;	/* dirty segment bitmap */
154
	unsigned int max_search;	/* maximum # of segments to search */
155 156 157 158 159 160 161
	unsigned int offset;		/* last scanned bitmap offset */
	unsigned int ofs_unit;		/* bitmap search unit */
	unsigned int min_cost;		/* minimum cost */
	unsigned int min_segno;		/* segment # having min. cost */
};

struct seg_entry {
C
Chao Yu 已提交
162 163 164 165
	unsigned int type:6;		/* segment type like CURSEG_XXX_TYPE */
	unsigned int valid_blocks:10;	/* # of valid blocks */
	unsigned int ckpt_valid_blocks:10;	/* # of valid blocks last cp */
	unsigned int padding:6;		/* padding */
166
	unsigned char *cur_valid_map;	/* validity bitmap of blocks */
C
Chao Yu 已提交
167 168 169
#ifdef CONFIG_F2FS_CHECK_FS
	unsigned char *cur_valid_map_mir;	/* mirror of current valid bitmap */
#endif
170 171 172 173
	/*
	 * # of valid blocks and the validity bitmap stored in the the last
	 * checkpoint pack. This information is used by the SSR mode.
	 */
C
Chao Yu 已提交
174
	unsigned char *ckpt_valid_map;	/* validity bitmap of blocks last cp */
175
	unsigned char *discard_map;
176 177 178 179 180 181 182 183 184 185 186
	unsigned long long mtime;	/* modification time of the segment */
};

struct sec_entry {
	unsigned int valid_blocks;	/* # of valid blocks in a section */
};

struct segment_allocation {
	void (*allocate_segment)(struct f2fs_sb_info *, int, bool);
};

C
Chao Yu 已提交
187 188 189 190
/*
 * this value is set in page as a private data which indicate that
 * the page is atomically written, and it is in inmem_pages list.
 */
191
#define ATOMIC_WRITTEN_PAGE		((unsigned long)-1)
192
#define DUMMY_WRITTEN_PAGE		((unsigned long)-2)
C
Chao Yu 已提交
193 194 195

#define IS_ATOMIC_WRITTEN_PAGE(page)			\
		(page_private(page) == (unsigned long)ATOMIC_WRITTEN_PAGE)
196 197
#define IS_DUMMY_WRITTEN_PAGE(page)			\
		(page_private(page) == (unsigned long)DUMMY_WRITTEN_PAGE)
C
Chao Yu 已提交
198

J
Jaegeuk Kim 已提交
199 200 201
struct inmem_pages {
	struct list_head list;
	struct page *page;
202
	block_t old_addr;		/* for revoking when fail to commit */
J
Jaegeuk Kim 已提交
203 204
};

205 206 207 208 209 210 211 212 213
struct sit_info {
	const struct segment_allocation *s_ops;

	block_t sit_base_addr;		/* start block address of SIT area */
	block_t sit_blocks;		/* # of blocks used by SIT area */
	block_t written_valid_blocks;	/* # of valid blocks in main area */
	char *sit_bitmap;		/* SIT bitmap pointer */
	unsigned int bitmap_size;	/* SIT bitmap size */

J
Jaegeuk Kim 已提交
214
	unsigned long *tmp_map;			/* bitmap for temporal use */
215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232
	unsigned long *dirty_sentries_bitmap;	/* bitmap for dirty sentries */
	unsigned int dirty_sentries;		/* # of dirty sentries */
	unsigned int sents_per_block;		/* # of SIT entries per block */
	struct mutex sentry_lock;		/* to protect SIT cache */
	struct seg_entry *sentries;		/* SIT segment-level cache */
	struct sec_entry *sec_entries;		/* SIT section-level cache */

	/* for cost-benefit algorithm in cleaning procedure */
	unsigned long long elapsed_time;	/* elapsed time after mount */
	unsigned long long mounted_time;	/* mount time */
	unsigned long long min_mtime;		/* min. modification time */
	unsigned long long max_mtime;		/* max. modification time */
};

struct free_segmap_info {
	unsigned int start_segno;	/* start segment number logically */
	unsigned int free_segments;	/* # of free segments */
	unsigned int free_sections;	/* # of free sections */
233
	spinlock_t segmap_lock;		/* free segmap lock */
234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255
	unsigned long *free_segmap;	/* free segment bitmap */
	unsigned long *free_secmap;	/* free section bitmap */
};

/* Notice: The order of dirty type is same with CURSEG_XXX in f2fs.h */
enum dirty_type {
	DIRTY_HOT_DATA,		/* dirty segments assigned as hot data logs */
	DIRTY_WARM_DATA,	/* dirty segments assigned as warm data logs */
	DIRTY_COLD_DATA,	/* dirty segments assigned as cold data logs */
	DIRTY_HOT_NODE,		/* dirty segments assigned as hot node logs */
	DIRTY_WARM_NODE,	/* dirty segments assigned as warm node logs */
	DIRTY_COLD_NODE,	/* dirty segments assigned as cold node logs */
	DIRTY,			/* to count # of dirty segments */
	PRE,			/* to count # of entirely obsolete segments */
	NR_DIRTY_TYPE
};

struct dirty_seglist_info {
	const struct victim_selection *v_ops;	/* victim selction operation */
	unsigned long *dirty_segmap[NR_DIRTY_TYPE];
	struct mutex seglist_lock;		/* lock for segment bitmaps */
	int nr_dirty[NR_DIRTY_TYPE];		/* # of dirty segments */
256
	unsigned long *victim_secmap;		/* background GC victims */
257 258 259 260 261 262 263 264 265 266 267 268
};

/* victim selection function for cleaning and SSR */
struct victim_selection {
	int (*get_victim)(struct f2fs_sb_info *, unsigned int *,
							int, int, char);
};

/* for active log information */
struct curseg_info {
	struct mutex curseg_mutex;		/* lock for consistency */
	struct f2fs_summary_block *sum_blk;	/* cached summary block */
269 270
	struct rw_semaphore journal_rwsem;	/* protect journal area */
	struct f2fs_journal *journal;		/* cached journal info */
271 272 273 274 275 276 277
	unsigned char alloc_type;		/* current allocation type */
	unsigned int segno;			/* current segment number */
	unsigned short next_blkoff;		/* next block offset to write */
	unsigned int zone;			/* current zone number */
	unsigned int next_segno;		/* preallocated segment */
};

278 279 280 281 282 283
struct sit_entry_set {
	struct list_head set_list;	/* link with all sit sets */
	unsigned int start_segno;	/* start segno of sits in set */
	unsigned int entry_cnt;		/* the # of sit entries in set */
};

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
/*
 * inline functions
 */
static inline struct curseg_info *CURSEG_I(struct f2fs_sb_info *sbi, int type)
{
	return (struct curseg_info *)(SM_I(sbi)->curseg_array + type);
}

static inline struct seg_entry *get_seg_entry(struct f2fs_sb_info *sbi,
						unsigned int segno)
{
	struct sit_info *sit_i = SIT_I(sbi);
	return &sit_i->sentries[segno];
}

static inline struct sec_entry *get_sec_entry(struct f2fs_sb_info *sbi,
						unsigned int segno)
{
	struct sit_info *sit_i = SIT_I(sbi);
	return &sit_i->sec_entries[GET_SECNO(sbi, segno)];
}

static inline unsigned int get_valid_blocks(struct f2fs_sb_info *sbi,
				unsigned int segno, int section)
{
	/*
	 * In order to get # of valid blocks in a section instantly from many
	 * segments, f2fs manages two counting structures separately.
	 */
	if (section > 1)
		return get_sec_entry(sbi, segno)->valid_blocks;
	else
		return get_seg_entry(sbi, segno)->valid_blocks;
}

static inline void seg_info_from_raw_sit(struct seg_entry *se,
					struct f2fs_sit_entry *rs)
{
	se->valid_blocks = GET_SIT_VBLOCKS(rs);
	se->ckpt_valid_blocks = GET_SIT_VBLOCKS(rs);
	memcpy(se->cur_valid_map, rs->valid_map, SIT_VBLOCK_MAP_SIZE);
	memcpy(se->ckpt_valid_map, rs->valid_map, SIT_VBLOCK_MAP_SIZE);
C
Chao Yu 已提交
326 327 328
#ifdef CONFIG_F2FS_CHECK_FS
	memcpy(se->cur_valid_map_mir, rs->valid_map, SIT_VBLOCK_MAP_SIZE);
#endif
329 330 331 332 333 334 335 336 337 338 339 340 341 342 343 344 345 346 347 348
	se->type = GET_SIT_TYPE(rs);
	se->mtime = le64_to_cpu(rs->mtime);
}

static inline void seg_info_to_raw_sit(struct seg_entry *se,
					struct f2fs_sit_entry *rs)
{
	unsigned short raw_vblocks = (se->type << SIT_VBLOCKS_SHIFT) |
					se->valid_blocks;
	rs->vblocks = cpu_to_le16(raw_vblocks);
	memcpy(rs->valid_map, se->cur_valid_map, SIT_VBLOCK_MAP_SIZE);
	memcpy(se->ckpt_valid_map, rs->valid_map, SIT_VBLOCK_MAP_SIZE);
	se->ckpt_valid_blocks = se->valid_blocks;
	rs->mtime = cpu_to_le64(se->mtime);
}

static inline unsigned int find_next_inuse(struct free_segmap_info *free_i,
		unsigned int max, unsigned int segno)
{
	unsigned int ret;
349
	spin_lock(&free_i->segmap_lock);
350
	ret = find_next_bit(free_i->free_segmap, max, segno);
351
	spin_unlock(&free_i->segmap_lock);
352 353 354 355 356 357 358 359 360 361
	return ret;
}

static inline void __set_free(struct f2fs_sb_info *sbi, unsigned int segno)
{
	struct free_segmap_info *free_i = FREE_I(sbi);
	unsigned int secno = segno / sbi->segs_per_sec;
	unsigned int start_segno = secno * sbi->segs_per_sec;
	unsigned int next;

362
	spin_lock(&free_i->segmap_lock);
363 364 365
	clear_bit(segno, free_i->free_segmap);
	free_i->free_segments++;

366 367
	next = find_next_bit(free_i->free_segmap,
			start_segno + sbi->segs_per_sec, start_segno);
368 369 370 371
	if (next >= start_segno + sbi->segs_per_sec) {
		clear_bit(secno, free_i->free_secmap);
		free_i->free_sections++;
	}
372
	spin_unlock(&free_i->segmap_lock);
373 374 375 376 377 378 379 380 381 382 383 384 385 386 387 388 389 390 391 392 393
}

static inline void __set_inuse(struct f2fs_sb_info *sbi,
		unsigned int segno)
{
	struct free_segmap_info *free_i = FREE_I(sbi);
	unsigned int secno = segno / sbi->segs_per_sec;
	set_bit(segno, free_i->free_segmap);
	free_i->free_segments--;
	if (!test_and_set_bit(secno, free_i->free_secmap))
		free_i->free_sections--;
}

static inline void __set_test_and_free(struct f2fs_sb_info *sbi,
		unsigned int segno)
{
	struct free_segmap_info *free_i = FREE_I(sbi);
	unsigned int secno = segno / sbi->segs_per_sec;
	unsigned int start_segno = secno * sbi->segs_per_sec;
	unsigned int next;

394
	spin_lock(&free_i->segmap_lock);
395 396 397
	if (test_and_clear_bit(segno, free_i->free_segmap)) {
		free_i->free_segments++;

398 399
		next = find_next_bit(free_i->free_segmap,
				start_segno + sbi->segs_per_sec, start_segno);
400 401 402 403 404
		if (next >= start_segno + sbi->segs_per_sec) {
			if (test_and_clear_bit(secno, free_i->free_secmap))
				free_i->free_sections++;
		}
	}
405
	spin_unlock(&free_i->segmap_lock);
406 407 408 409 410 411 412
}

static inline void __set_test_and_inuse(struct f2fs_sb_info *sbi,
		unsigned int segno)
{
	struct free_segmap_info *free_i = FREE_I(sbi);
	unsigned int secno = segno / sbi->segs_per_sec;
413
	spin_lock(&free_i->segmap_lock);
414 415 416 417 418
	if (!test_and_set_bit(segno, free_i->free_segmap)) {
		free_i->free_segments--;
		if (!test_and_set_bit(secno, free_i->free_secmap))
			free_i->free_sections--;
	}
419
	spin_unlock(&free_i->segmap_lock);
420 421 422 423 424 425 426 427 428 429 430
}

static inline void get_sit_bitmap(struct f2fs_sb_info *sbi,
		void *dst_addr)
{
	struct sit_info *sit_i = SIT_I(sbi);
	memcpy(dst_addr, sit_i->sit_bitmap, sit_i->bitmap_size);
}

static inline block_t written_block_count(struct f2fs_sb_info *sbi)
{
431
	return SIT_I(sbi)->written_valid_blocks;
432 433 434 435
}

static inline unsigned int free_segments(struct f2fs_sb_info *sbi)
{
436
	return FREE_I(sbi)->free_segments;
437 438 439 440 441 442 443 444 445
}

static inline int reserved_segments(struct f2fs_sb_info *sbi)
{
	return SM_I(sbi)->reserved_segments;
}

static inline unsigned int free_sections(struct f2fs_sb_info *sbi)
{
446
	return FREE_I(sbi)->free_sections;
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
}

static inline unsigned int prefree_segments(struct f2fs_sb_info *sbi)
{
	return DIRTY_I(sbi)->nr_dirty[PRE];
}

static inline unsigned int dirty_segments(struct f2fs_sb_info *sbi)
{
	return DIRTY_I(sbi)->nr_dirty[DIRTY_HOT_DATA] +
		DIRTY_I(sbi)->nr_dirty[DIRTY_WARM_DATA] +
		DIRTY_I(sbi)->nr_dirty[DIRTY_COLD_DATA] +
		DIRTY_I(sbi)->nr_dirty[DIRTY_HOT_NODE] +
		DIRTY_I(sbi)->nr_dirty[DIRTY_WARM_NODE] +
		DIRTY_I(sbi)->nr_dirty[DIRTY_COLD_NODE];
}

static inline int overprovision_segments(struct f2fs_sb_info *sbi)
{
	return SM_I(sbi)->ovp_segments;
}

static inline int overprovision_sections(struct f2fs_sb_info *sbi)
{
	return ((unsigned int) overprovision_segments(sbi)) / sbi->segs_per_sec;
}

static inline int reserved_sections(struct f2fs_sb_info *sbi)
{
	return ((unsigned int) reserved_segments(sbi)) / sbi->segs_per_sec;
}

static inline bool need_SSR(struct f2fs_sb_info *sbi)
{
481 482
	int node_secs = get_blocktype_secs(sbi, F2FS_DIRTY_NODES);
	int dent_secs = get_blocktype_secs(sbi, F2FS_DIRTY_DENTS);
483
	int imeta_secs = get_blocktype_secs(sbi, F2FS_DIRTY_IMETA);
484 485 486 487

	if (test_opt(sbi, LFS))
		return false;

488
	return free_sections(sbi) <= (node_secs + 2 * dent_secs + imeta_secs +
489
						reserved_sections(sbi) + 1);
490 491
}

492 493
static inline bool has_not_enough_free_secs(struct f2fs_sb_info *sbi,
					int freed, int needed)
494
{
495 496
	int node_secs = get_blocktype_secs(sbi, F2FS_DIRTY_NODES);
	int dent_secs = get_blocktype_secs(sbi, F2FS_DIRTY_DENTS);
497
	int imeta_secs = get_blocktype_secs(sbi, F2FS_DIRTY_IMETA);
498

499
	if (unlikely(is_sbi_flag_set(sbi, SBI_POR_DOING)))
500 501
		return false;

502
	return (free_sections(sbi) + freed) <=
503 504
		(node_secs + 2 * dent_secs + imeta_secs +
		reserved_sections(sbi) + needed);
505 506
}

507 508
static inline bool excess_prefree_segs(struct f2fs_sb_info *sbi)
{
C
Chris Fries 已提交
509
	return prefree_segments(sbi) > SM_I(sbi)->rec_prefree_segments;
510 511
}

512 513
static inline int utilization(struct f2fs_sb_info *sbi)
{
C
Chris Fries 已提交
514 515
	return div_u64((u64)valid_user_blocks(sbi) * 100,
					sbi->user_block_count);
516 517 518 519
}

/*
 * Sometimes f2fs may be better to drop out-of-place update policy.
520 521 522 523 524 525 526
 * And, users can control the policy through sysfs entries.
 * There are five policies with triggering conditions as follows.
 * F2FS_IPU_FORCE - all the time,
 * F2FS_IPU_SSR - if SSR mode is activated,
 * F2FS_IPU_UTIL - if FS utilization is over threashold,
 * F2FS_IPU_SSR_UTIL - if SSR mode is activated and FS utilization is over
 *                     threashold,
527 528 529
 * F2FS_IPU_FSYNC - activated in fsync path only for high performance flash
 *                     storages. IPU will be triggered only if the # of dirty
 *                     pages over min_fsync_blocks.
530
 * F2FS_IPUT_DISABLE - disable IPU. (=default option)
531
 */
532
#define DEF_MIN_IPU_UTIL	70
533
#define DEF_MIN_FSYNC_BLOCKS	8
534 535 536 537 538 539

enum {
	F2FS_IPU_FORCE,
	F2FS_IPU_SSR,
	F2FS_IPU_UTIL,
	F2FS_IPU_SSR_UTIL,
540
	F2FS_IPU_FSYNC,
541 542
};

543 544
static inline bool need_inplace_update(struct inode *inode)
{
545
	struct f2fs_sb_info *sbi = F2FS_I_SB(inode);
546
	unsigned int policy = SM_I(sbi)->ipu_policy;
547 548

	/* IPU can be done only for the user data */
J
Jaegeuk Kim 已提交
549
	if (S_ISDIR(inode->i_mode) || f2fs_is_atomic_file(inode))
550
		return false;
551

552 553 554
	if (test_opt(sbi, LFS))
		return false;

555
	if (policy & (0x1 << F2FS_IPU_FORCE))
556
		return true;
557 558 559 560 561 562 563 564 565 566 567
	if (policy & (0x1 << F2FS_IPU_SSR) && need_SSR(sbi))
		return true;
	if (policy & (0x1 << F2FS_IPU_UTIL) &&
			utilization(sbi) > SM_I(sbi)->min_ipu_util)
		return true;
	if (policy & (0x1 << F2FS_IPU_SSR_UTIL) && need_SSR(sbi) &&
			utilization(sbi) > SM_I(sbi)->min_ipu_util)
		return true;

	/* this is only set during fdatasync */
	if (policy & (0x1 << F2FS_IPU_FSYNC) &&
568
			is_inode_flag_set(inode, FI_NEED_IPU))
569 570
		return true;

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
	return false;
}

static inline unsigned int curseg_segno(struct f2fs_sb_info *sbi,
		int type)
{
	struct curseg_info *curseg = CURSEG_I(sbi, type);
	return curseg->segno;
}

static inline unsigned char curseg_alloc_type(struct f2fs_sb_info *sbi,
		int type)
{
	struct curseg_info *curseg = CURSEG_I(sbi, type);
	return curseg->alloc_type;
}

static inline unsigned short curseg_blkoff(struct f2fs_sb_info *sbi, int type)
{
	struct curseg_info *curseg = CURSEG_I(sbi, type);
	return curseg->next_blkoff;
}

static inline void check_seg_range(struct f2fs_sb_info *sbi, unsigned int segno)
{
596
	f2fs_bug_on(sbi, segno > TOTAL_SEGS(sbi) - 1);
597 598 599 600
}

static inline void verify_block_addr(struct f2fs_sb_info *sbi, block_t blk_addr)
{
601 602
	BUG_ON(blk_addr < SEG0_BLKADDR(sbi)
			|| blk_addr >= MAX_BLKADDR(sbi));
603 604 605
}

/*
A
arter97 已提交
606
 * Summary block is always treated as an invalid block
607 608 609 610
 */
static inline void check_block_count(struct f2fs_sb_info *sbi,
		int segno, struct f2fs_sit_entry *raw_sit)
{
J
Jaegeuk Kim 已提交
611
#ifdef CONFIG_F2FS_CHECK_FS
612
	bool is_valid  = test_bit_le(0, raw_sit->valid_map) ? true : false;
613
	int valid_blocks = 0;
614
	int cur_pos = 0, next_pos;
615 616

	/* check bitmap with valid block count */
617 618 619 620 621 622 623 624 625 626 627 628 629
	do {
		if (is_valid) {
			next_pos = find_next_zero_bit_le(&raw_sit->valid_map,
					sbi->blocks_per_seg,
					cur_pos);
			valid_blocks += next_pos - cur_pos;
		} else
			next_pos = find_next_bit_le(&raw_sit->valid_map,
					sbi->blocks_per_seg,
					cur_pos);
		cur_pos = next_pos;
		is_valid = !is_valid;
	} while (cur_pos < sbi->blocks_per_seg);
630
	BUG_ON(GET_SIT_VBLOCKS(raw_sit) != valid_blocks);
631
#endif
J
Jaegeuk Kim 已提交
632 633 634
	/* check segment usage, and check boundary of a given segment number */
	f2fs_bug_on(sbi, GET_SIT_VBLOCKS(raw_sit) > sbi->blocks_per_seg
					|| segno > TOTAL_SEGS(sbi) - 1);
635
}
636 637 638 639 640

static inline pgoff_t current_sit_addr(struct f2fs_sb_info *sbi,
						unsigned int start)
{
	struct sit_info *sit_i = SIT_I(sbi);
641
	unsigned int offset = SIT_BLOCK_OFFSET(start);
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
	block_t blk_addr = sit_i->sit_base_addr + offset;

	check_seg_range(sbi, start);

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

	return blk_addr;
}

static inline pgoff_t next_sit_addr(struct f2fs_sb_info *sbi,
						pgoff_t block_addr)
{
	struct sit_info *sit_i = SIT_I(sbi);
	block_addr -= sit_i->sit_base_addr;
	if (block_addr < sit_i->sit_blocks)
		block_addr += sit_i->sit_blocks;
	else
		block_addr -= sit_i->sit_blocks;

	return block_addr + sit_i->sit_base_addr;
}

static inline void set_to_next_sit(struct sit_info *sit_i, unsigned int start)
{
668
	unsigned int block_off = SIT_BLOCK_OFFSET(start);
669

670
	f2fs_change_bit(block_off, sit_i->sit_bitmap);
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
}

static inline unsigned long long get_mtime(struct f2fs_sb_info *sbi)
{
	struct sit_info *sit_i = SIT_I(sbi);
	return sit_i->elapsed_time + CURRENT_TIME_SEC.tv_sec -
						sit_i->mounted_time;
}

static inline void set_summary(struct f2fs_summary *sum, nid_t nid,
			unsigned int ofs_in_node, unsigned char version)
{
	sum->nid = cpu_to_le32(nid);
	sum->ofs_in_node = cpu_to_le16(ofs_in_node);
	sum->version = version;
}

static inline block_t start_sum_block(struct f2fs_sb_info *sbi)
{
	return __start_cp_addr(sbi) +
		le32_to_cpu(F2FS_CKPT(sbi)->cp_pack_start_sum);
}

static inline block_t sum_blk_addr(struct f2fs_sb_info *sbi, int base, int type)
{
	return __start_cp_addr(sbi) +
		le32_to_cpu(F2FS_CKPT(sbi)->cp_pack_total_block_count)
				- (base + 1) + type;
}
700 701 702 703 704 705 706

static inline bool sec_usage_check(struct f2fs_sb_info *sbi, unsigned int secno)
{
	if (IS_CURSEC(sbi, secno) || (sbi->cur_victim_sec == secno))
		return true;
	return false;
}
707

708 709 710 711 712 713 714 715 716
/*
 * It is very important to gather dirty pages and write at once, so that we can
 * submit a big bio without interfering other data writes.
 * By default, 512 pages for directory data,
 * 512 pages (2MB) * 3 for three types of nodes, and
 * max_bio_blocks for meta are set.
 */
static inline int nr_pages_to_skip(struct f2fs_sb_info *sbi, int type)
{
717
	if (sbi->sb->s_bdi->wb.dirty_exceeded)
718 719
		return 0;

720 721 722
	if (type == DATA)
		return sbi->blocks_per_seg;
	else if (type == NODE)
723
		return 8 * sbi->blocks_per_seg;
724
	else if (type == META)
725
		return 8 * BIO_MAX_PAGES;
726 727 728
	else
		return 0;
}
729 730 731 732 733 734 735 736 737 738 739 740 741

/*
 * When writing pages, it'd better align nr_to_write for segment size.
 */
static inline long nr_pages_to_write(struct f2fs_sb_info *sbi, int type,
					struct writeback_control *wbc)
{
	long nr_to_write, desired;

	if (wbc->sync_mode != WB_SYNC_NONE)
		return 0;

	nr_to_write = wbc->nr_to_write;
742
	desired = BIO_MAX_PAGES;
743
	if (type == NODE)
744
		desired <<= 1;
745 746 747 748

	wbc->nr_to_write = desired;
	return desired - nr_to_write;
}