path: root/fs/f2fs/segment.h

/*
 * 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.
 */
#include <linux/blkdev.h>
#include <linux/backing-dev.h>

/* constant macro */
#define NULL_SEGNO			((unsigned int)(~0))
#define NULL_SECNO			((unsigned int)(~0))

#define DEF_RECLAIM_PREFREE_SEGMENTS	5	/* 5% over total segments */

/* L: Logical segment # in volume, R: Relative segment # in main area */
#define GET_L2R_SEGNO(free_i, segno)	(segno - free_i->start_segno)
#define GET_R2L_SEGNO(free_i, segno)	(segno + free_i->start_segno)

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

#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))

#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))	\

#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))
#define SEGMENT_SIZE(sbi)	(1ULL << (sbi->log_blocksize +		\
					sbi->log_blocks_per_seg))

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

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

#define GET_SEGOFF_FROM_SEG0(sbi, blk_addr)	((blk_addr) - SEG0_BLKADDR(sbi))
#define GET_SEGNO_FROM_SEG0(sbi, blk_addr)				\
	(GET_SEGOFF_FROM_SEG0(sbi, blk_addr) >> sbi->log_blocks_per_seg)
#define GET_BLKOFF_FROM_SEG0(sbi, blk_addr)				\
	(GET_SEGOFF_FROM_SEG0(sbi, blk_addr) & (sbi->blocks_per_seg - 1))

#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)
#define SIT_BLOCK_OFFSET(segno)					\
	(segno / SIT_ENTRY_PER_BLOCK)
#define	START_SEGNO(segno)		\
	(SIT_BLOCK_OFFSET(segno) * SIT_ENTRY_PER_BLOCK)
#define SIT_BLK_CNT(sbi)			\
	((MAIN_SEGS(sbi) + SIT_ENTRY_PER_BLOCK - 1) / SIT_ENTRY_PER_BLOCK)
#define f2fs_bitmap_size(nr)			\
	(BITS_TO_LONGS(nr) * sizeof(unsigned long))

#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)
#define MAX_BIO_BLOCKS(sbi)						\
	((int)min((int)max_hw_blocks(sbi), BIO_MAX_PAGES))

/*
 * 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.
 * FORCE_FG_GC means on-demand cleaning job in background.
 */
enum {
	BG_GC = 0,
	FG_GC,
	FORCE_FG_GC,
};

/* 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 */
	unsigned int max_search;	/* maximum # of segments to search */
	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 {
	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 */
	unsigned char *cur_valid_map;	/* validity bitmap of blocks */
	/*
	 * # of valid blocks and the validity bitmap stored in the the last
	 * checkpoint pack. This information is used by the SSR mode.
	 */
	unsigned char *ckpt_valid_map;	/* validity bitmap of blocks last cp */
	unsigned char *discard_map;
	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);
};

/*
 * 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.
 */
#define ATOMIC_WRITTEN_PAGE		((unsigned long)-1)

#define IS_ATOMIC_WRITTEN_PAGE(page)			\
		(page_private(page) == (unsigned long)ATOMIC_WRITTEN_PAGE)

struct inmem_pages {
	struct list_head list;
	struct page *page;
	block_t old_addr;		/* for revoking when fail to commit */
};

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 */

	unsigned long *tmp_map;			/* bitmap for temporal use */
	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 */
	spinlock_t segmap_lock;		/* free segmap lock */
	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 */
	unsigned long *victim_secmap;		/* background GC victims */
};

/* 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 */
	struct rw_semaphore journal_rwsem;	/* protect journal area */
	struct f2fs_journal *journal;		/* cached journal info */
	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 */
};

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 */
};

/*
 * inline functions
 */
static inline struct curseg_info *CURSEG_I(struct f2fs_sb_info *sbi, int type)
{
	return (struct curseg_info<