node.h 10.7 KB
Newer Older
1
/*
2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22
 * fs/f2fs/node.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.
 */
/* start node id of a node block dedicated to the given node id */
#define	START_NID(nid) ((nid / NAT_ENTRY_PER_BLOCK) * NAT_ENTRY_PER_BLOCK)

/* node block offset on the NAT area dedicated to the given start node id */
#define	NAT_BLOCK_OFFSET(start_nid) (start_nid / NAT_ENTRY_PER_BLOCK)

/* # of pages to perform readahead before building free nids */
#define FREE_NID_PAGES 4

/* maximum readahead size for node during getting data blocks */
#define MAX_RA_NODE		128

23 24 25
/* control the memory footprint threshold (10MB per 1GB ram) */
#define DEF_RAM_THRESHOLD	10

26 27 28
/* vector size for gang look-up from nat cache that consists of radix tree */
#define NATVEC_SIZE	64

29 30 31
/* return value for read_node_page */
#define LOCKED_PAGE	1

32 33 34 35 36 37 38 39 40 41
/*
 * For node information
 */
struct node_info {
	nid_t nid;		/* node id */
	nid_t ino;		/* inode number of the node's owner */
	block_t	blk_addr;	/* block address of the node */
	unsigned char version;	/* version of the node */
};

42 43
enum {
	IS_CHECKPOINTED,	/* is it checkpointed before? */
44 45
	HAS_FSYNCED_INODE,	/* is the inode fsynced before? */
	HAS_LAST_FSYNC,		/* has the latest node fsync mark? */
46
	IS_DIRTY,		/* this nat entry is dirty? */
47 48
};

49 50
struct nat_entry {
	struct list_head list;	/* for clean or dirty nat list */
51
	unsigned char flag;	/* for node information bits */
52 53 54 55 56 57 58 59 60 61 62 63 64 65
	struct node_info ni;	/* in-memory node information */
};

#define nat_get_nid(nat)		(nat->ni.nid)
#define nat_set_nid(nat, n)		(nat->ni.nid = n)
#define nat_get_blkaddr(nat)		(nat->ni.blk_addr)
#define nat_set_blkaddr(nat, b)		(nat->ni.blk_addr = b)
#define nat_get_ino(nat)		(nat->ni.ino)
#define nat_set_ino(nat, i)		(nat->ni.ino = i)
#define nat_get_version(nat)		(nat->ni.version)
#define nat_set_version(nat, v)		(nat->ni.version = v)

#define inc_node_version(version)	(++version)

66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81
static inline void set_nat_flag(struct nat_entry *ne,
				unsigned int type, bool set)
{
	unsigned char mask = 0x01 << type;
	if (set)
		ne->flag |= mask;
	else
		ne->flag &= ~mask;
}

static inline bool get_nat_flag(struct nat_entry *ne, unsigned int type)
{
	unsigned char mask = 0x01 << type;
	return ne->flag & mask;
}

82 83 84 85 86 87 88 89
static inline void nat_reset_flag(struct nat_entry *ne)
{
	/* these states can be set only after checkpoint was done */
	set_nat_flag(ne, IS_CHECKPOINTED, true);
	set_nat_flag(ne, HAS_FSYNCED_INODE, false);
	set_nat_flag(ne, HAS_LAST_FSYNC, true);
}

90 91 92 93 94 95 96 97
static inline void node_info_from_raw_nat(struct node_info *ni,
						struct f2fs_nat_entry *raw_ne)
{
	ni->ino = le32_to_cpu(raw_ne->ino);
	ni->blk_addr = le32_to_cpu(raw_ne->block_addr);
	ni->version = raw_ne->version;
}

98 99 100 101 102 103 104 105
static inline void raw_nat_from_node_info(struct f2fs_nat_entry *raw_ne,
						struct node_info *ni)
{
	raw_ne->ino = cpu_to_le32(ni->ino);
	raw_ne->block_addr = cpu_to_le32(ni->blk_addr);
	raw_ne->version = ni->version;
}

106
enum mem_type {
107
	FREE_NIDS,	/* indicates the free nid list */
108
	NAT_ENTRIES,	/* indicates the cached nat entry */
109 110
	DIRTY_DENTS,	/* indicates dirty dentry pages */
	INO_ENTRIES,	/* indicates inode entries */
111
	BASE_CHECK,	/* check kernel status */
112 113
};

114
struct nat_entry_set {
115
	struct list_head set_list;	/* link with other nat sets */
116
	struct list_head entry_list;	/* link with dirty nat entries */
117
	nid_t set;			/* set number*/
118 119 120
	unsigned int entry_cnt;		/* the # of nat entries in set */
};

121 122 123 124 125 126 127 128 129 130 131 132 133 134
/*
 * For free nid mangement
 */
enum nid_state {
	NID_NEW,	/* newly added to free nid list */
	NID_ALLOC	/* it is allocated */
};

struct free_nid {
	struct list_head list;	/* for free node id list */
	nid_t nid;		/* node id */
	int state;		/* in use or not: NID_NEW or NID_ALLOC */
};

135
static inline void next_free_nid(struct f2fs_sb_info *sbi, nid_t *nid)
136 137 138 139 140
{
	struct f2fs_nm_info *nm_i = NM_I(sbi);
	struct free_nid *fnid;

	spin_lock(&nm_i->free_nid_list_lock);
141 142
	if (nm_i->fcnt <= 0) {
		spin_unlock(&nm_i->free_nid_list_lock);
143
		return;
144
	}
145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196
	fnid = list_entry(nm_i->free_nid_list.next, struct free_nid, list);
	*nid = fnid->nid;
	spin_unlock(&nm_i->free_nid_list_lock);
}

/*
 * inline functions
 */
static inline void get_nat_bitmap(struct f2fs_sb_info *sbi, void *addr)
{
	struct f2fs_nm_info *nm_i = NM_I(sbi);
	memcpy(addr, nm_i->nat_bitmap, nm_i->bitmap_size);
}

static inline pgoff_t current_nat_addr(struct f2fs_sb_info *sbi, nid_t start)
{
	struct f2fs_nm_info *nm_i = NM_I(sbi);
	pgoff_t block_off;
	pgoff_t block_addr;
	int seg_off;

	block_off = NAT_BLOCK_OFFSET(start);
	seg_off = block_off >> sbi->log_blocks_per_seg;

	block_addr = (pgoff_t)(nm_i->nat_blkaddr +
		(seg_off << sbi->log_blocks_per_seg << 1) +
		(block_off & ((1 << sbi->log_blocks_per_seg) - 1)));

	if (f2fs_test_bit(block_off, nm_i->nat_bitmap))
		block_addr += sbi->blocks_per_seg;

	return block_addr;
}

static inline pgoff_t next_nat_addr(struct f2fs_sb_info *sbi,
						pgoff_t block_addr)
{
	struct f2fs_nm_info *nm_i = NM_I(sbi);

	block_addr -= nm_i->nat_blkaddr;
	if ((block_addr >> sbi->log_blocks_per_seg) % 2)
		block_addr -= sbi->blocks_per_seg;
	else
		block_addr += sbi->blocks_per_seg;

	return block_addr + nm_i->nat_blkaddr;
}

static inline void set_to_next_nat(struct f2fs_nm_info *nm_i, nid_t start_nid)
{
	unsigned int block_off = NAT_BLOCK_OFFSET(start_nid);

197
	f2fs_change_bit(block_off, nm_i->nat_bitmap);
198 199 200 201 202
}

static inline void fill_node_footer(struct page *page, nid_t nid,
				nid_t ino, unsigned int ofs, bool reset)
{
203
	struct f2fs_node *rn = F2FS_NODE(page);
204 205 206 207 208 209 210 211 212
	if (reset)
		memset(rn, 0, sizeof(*rn));
	rn->footer.nid = cpu_to_le32(nid);
	rn->footer.ino = cpu_to_le32(ino);
	rn->footer.flag = cpu_to_le32(ofs << OFFSET_BIT_SHIFT);
}

static inline void copy_node_footer(struct page *dst, struct page *src)
{
213 214
	struct f2fs_node *src_rn = F2FS_NODE(src);
	struct f2fs_node *dst_rn = F2FS_NODE(dst);
215 216 217 218 219
	memcpy(&dst_rn->footer, &src_rn->footer, sizeof(struct node_footer));
}

static inline void fill_node_footer_blkaddr(struct page *page, block_t blkaddr)
{
220
	struct f2fs_checkpoint *ckpt = F2FS_CKPT(F2FS_P_SB(page));
221 222
	struct f2fs_node *rn = F2FS_NODE(page);

223
	rn->footer.cp_ver = ckpt->checkpoint_ver;
224
	rn->footer.next_blkaddr = cpu_to_le32(blkaddr);
225 226 227 228
}

static inline nid_t ino_of_node(struct page *node_page)
{
229
	struct f2fs_node *rn = F2FS_NODE(node_page);
230 231 232 233 234
	return le32_to_cpu(rn->footer.ino);
}

static inline nid_t nid_of_node(struct page *node_page)
{
235
	struct f2fs_node *rn = F2FS_NODE(node_page);
236 237 238 239 240
	return le32_to_cpu(rn->footer.nid);
}

static inline unsigned int ofs_of_node(struct page *node_page)
{
241
	struct f2fs_node *rn = F2FS_NODE(node_page);
242 243 244 245 246 247
	unsigned flag = le32_to_cpu(rn->footer.flag);
	return flag >> OFFSET_BIT_SHIFT;
}

static inline unsigned long long cpver_of_node(struct page *node_page)
{
248
	struct f2fs_node *rn = F2FS_NODE(node_page);
249 250 251 252 253
	return le64_to_cpu(rn->footer.cp_ver);
}

static inline block_t next_blkaddr_of_node(struct page *node_page)
{
254
	struct f2fs_node *rn = F2FS_NODE(node_page);
255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270
	return le32_to_cpu(rn->footer.next_blkaddr);
}

/*
 * f2fs assigns the following node offsets described as (num).
 * N = NIDS_PER_BLOCK
 *
 *  Inode block (0)
 *    |- direct node (1)
 *    |- direct node (2)
 *    |- indirect node (3)
 *    |            `- direct node (4 => 4 + N - 1)
 *    |- indirect node (4 + N)
 *    |            `- direct node (5 + N => 5 + 2N - 1)
 *    `- double indirect node (5 + 2N)
 *                 `- indirect node (6 + 2N)
C
Chao Yu 已提交
271 272 273 274 275 276 277
 *                       `- direct node
 *                 ......
 *                 `- indirect node ((6 + 2N) + x(N + 1))
 *                       `- direct node
 *                 ......
 *                 `- indirect node ((6 + 2N) + (N - 1)(N + 1))
 *                       `- direct node
278 279 280 281
 */
static inline bool IS_DNODE(struct page *node_page)
{
	unsigned int ofs = ofs_of_node(node_page);
282

283
	if (f2fs_has_xattr_block(ofs))
284 285
		return false;

286 287 288 289 290
	if (ofs == 3 || ofs == 4 + NIDS_PER_BLOCK ||
			ofs == 5 + 2 * NIDS_PER_BLOCK)
		return false;
	if (ofs >= 6 + 2 * NIDS_PER_BLOCK) {
		ofs -= 6 + 2 * NIDS_PER_BLOCK;
291
		if (!((long int)ofs % (NIDS_PER_BLOCK + 1)))
292 293 294 295 296 297 298
			return false;
	}
	return true;
}

static inline void set_nid(struct page *p, int off, nid_t nid, bool i)
{
299
	struct f2fs_node *rn = F2FS_NODE(p);
300

301
	f2fs_wait_on_page_writeback(p, NODE);
302 303 304 305 306 307 308 309 310 311

	if (i)
		rn->i.i_nid[off - NODE_DIR1_BLOCK] = cpu_to_le32(nid);
	else
		rn->in.nid[off] = cpu_to_le32(nid);
	set_page_dirty(p);
}

static inline nid_t get_nid(struct page *p, int off, bool i)
{
312 313
	struct f2fs_node *rn = F2FS_NODE(p);

314 315 316 317 318 319 320 321 322 323 324
	if (i)
		return le32_to_cpu(rn->i.i_nid[off - NODE_DIR1_BLOCK]);
	return le32_to_cpu(rn->in.nid[off]);
}

/*
 * Coldness identification:
 *  - Mark cold files in f2fs_inode_info
 *  - Mark cold node blocks in their node footer
 *  - Mark cold data pages in page cache
 */
325
static inline int is_file(struct inode *inode, int type)
326
{
327
	return F2FS_I(inode)->i_advise & type;
328 329
}

330
static inline void set_file(struct inode *inode, int type)
331
{
332
	F2FS_I(inode)->i_advise |= type;
333 334
}

335 336 337 338 339 340 341 342 343 344 345
static inline void clear_file(struct inode *inode, int type)
{
	F2FS_I(inode)->i_advise &= ~type;
}

#define file_is_cold(inode)	is_file(inode, FADVISE_COLD_BIT)
#define file_wrong_pino(inode)	is_file(inode, FADVISE_LOST_PINO_BIT)
#define file_set_cold(inode)	set_file(inode, FADVISE_COLD_BIT)
#define file_lost_pino(inode)	set_file(inode, FADVISE_LOST_PINO_BIT)
#define file_clear_cold(inode)	clear_file(inode, FADVISE_COLD_BIT)
#define file_got_pino(inode)	clear_file(inode, FADVISE_LOST_PINO_BIT)
346

347 348 349 350 351 352 353 354 355 356 357 358 359 360 361
static inline int is_cold_data(struct page *page)
{
	return PageChecked(page);
}

static inline void set_cold_data(struct page *page)
{
	SetPageChecked(page);
}

static inline void clear_cold_data(struct page *page)
{
	ClearPageChecked(page);
}

362
static inline int is_node(struct page *page, int type)
363
{
364
	struct f2fs_node *rn = F2FS_NODE(page);
365
	return le32_to_cpu(rn->footer.flag) & (1 << type);
366 367
}

368 369 370
#define is_cold_node(page)	is_node(page, COLD_BIT_SHIFT)
#define is_fsync_dnode(page)	is_node(page, FSYNC_BIT_SHIFT)
#define is_dent_dnode(page)	is_node(page, DENT_BIT_SHIFT)
371 372 373

static inline void set_cold_node(struct inode *inode, struct page *page)
{
374
	struct f2fs_node *rn = F2FS_NODE(page);
375 376 377 378 379 380 381 382 383
	unsigned int flag = le32_to_cpu(rn->footer.flag);

	if (S_ISDIR(inode->i_mode))
		flag &= ~(0x1 << COLD_BIT_SHIFT);
	else
		flag |= (0x1 << COLD_BIT_SHIFT);
	rn->footer.flag = cpu_to_le32(flag);
}

384
static inline void set_mark(struct page *page, int mark, int type)
385
{
386
	struct f2fs_node *rn = F2FS_NODE(page);
387 388
	unsigned int flag = le32_to_cpu(rn->footer.flag);
	if (mark)
389
		flag |= (0x1 << type);
390
	else
391
		flag &= ~(0x1 << type);
392 393
	rn->footer.flag = cpu_to_le32(flag);
}
394 395
#define set_dentry_mark(page, mark)	set_mark(page, mark, DENT_BIT_SHIFT)
#define set_fsync_mark(page, mark)	set_mark(page, mark, FSYNC_BIT_SHIFT)
新手
引导
客服 返回
顶部