summaryrefslogtreecommitdiffstats
path: root/include/sys/zfs_znode.h
blob: a0200684e3460ac133ec1ded275b99c0d5a42f51 (plain)
1
2
3
4
5
6
7
8
9
10
11
12
13
14
15
16
17
18
19
20
21
22
23
24
25
26
27
28
29
30
31
32
33
34
35
36
37
38
39
40
41
42
43
44
45
46
47
48
49
50
51
52
53
54
55
56
57
58
59
60
61
62
63
64
65
66
67
68
69
70
71
72
73
74
75
76
77
78
79
80
81
82
83
84
85
86
87
88
89
90
91
92
93
94
95
96
97
98
99
100
101
102
103
104
105
106
107
108
109
110
111
112
113
114
115
116
117
118
119
120
121
122
123
124
125
126
127
128
129
130
131
132
133
134
135
136
137
138
139
140
141
142
143
144
145
146
147
148
149
150
151
152
153
154
155
156
157
158
159
160
161
162
163
164
165
166
167
168
169
170
171
172
173
174
175
176
177
178
179
180
181
182
183
184
185
186
187
188
189
190
191
192
193
194
195
196
197
198
199
200
201
202
203
204
205
206
207
208
209
210
211
212
213
214
215
216
217
218
219
220
221
222
223
224
225
226
227
228
229
230
231
232
233
234
235
236
237
238
239
240
241
242
243
244
245
246
247
248
249
250
251
252
253
254
255
256
257
258
259
260
261
262
263
264
265
266
267
268
269
270
271
272
273
274
275
276
277
278
279
280
281
282
283
284
285
286
287
288
289
290
291
292
293
294
295
296
297
298
299
300
301
302
303
304
305
306
307
308
309
310
311
312
313
314
315
316
317
318
319
320
321
322
323
324
325
326
327
328
329
330
331
332
333
334
335
336
337
338
339
340
341
342
343
344
345
346
347
348
349
350
351
352
353
354
355
356
357
358
359
360
361
362
363
364
365
366
367
368
369
370
371
372
373
374
375
376
377
378
379
380
381
382
383
384
385
/*
 * CDDL HEADER START
 *
 * The contents of this file are subject to the terms of the
 * Common Development and Distribution License (the "License").
 * You may not use this file except in compliance with the License.
 *
 * You can obtain a copy of the license at usr/src/OPENSOLARIS.LICENSE
 * or http://www.opensolaris.org/os/licensing.
 * See the License for the specific language governing permissions
 * and limitations under the License.
 *
 * When distributing Covered Code, include this CDDL HEADER in each
 * file and include the License file at usr/src/OPENSOLARIS.LICENSE.
 * If applicable, add the following below this CDDL HEADER, with the
 * fields enclosed by brackets "[]" replaced with your own identifying
 * information: Portions Copyright [yyyy] [name of copyright owner]
 *
 * CDDL HEADER END
 */
/*
 * Copyright (c) 2005, 2010, Oracle and/or its affiliates. All rights reserved.
 * Copyright (c) 2012 by Delphix. All rights reserved.
 */

#ifndef	_SYS_FS_ZFS_ZNODE_H
#define	_SYS_FS_ZFS_ZNODE_H

#ifdef _KERNEL
#include <sys/isa_defs.h>
#include <sys/types32.h>
#include <sys/attr.h>
#include <sys/list.h>
#include <sys/dmu.h>
#include <sys/sa.h>
#include <sys/zfs_vfsops.h>
#include <sys/rrwlock.h>
#include <sys/zfs_sa.h>
#include <sys/zfs_stat.h>
#endif
#include <sys/zfs_acl.h>
#include <sys/zil.h>

#ifdef	__cplusplus
extern "C" {
#endif

/*
 * Additional file level attributes, that are stored
 * in the upper half of zp_flags
 */
#define	ZFS_READONLY		0x0000000100000000ull
#define	ZFS_HIDDEN		0x0000000200000000ull
#define	ZFS_SYSTEM		0x0000000400000000ull
#define	ZFS_ARCHIVE		0x0000000800000000ull
#define	ZFS_IMMUTABLE		0x0000001000000000ull
#define	ZFS_NOUNLINK		0x0000002000000000ull
#define	ZFS_APPENDONLY		0x0000004000000000ull
#define	ZFS_NODUMP		0x0000008000000000ull
#define	ZFS_OPAQUE		0x0000010000000000ull
#define	ZFS_AV_QUARANTINED	0x0000020000000000ull
#define	ZFS_AV_MODIFIED		0x0000040000000000ull
#define	ZFS_REPARSE		0x0000080000000000ull
#define	ZFS_OFFLINE		0x0000100000000000ull
#define	ZFS_SPARSE		0x0000200000000000ull

#define	ZFS_ATTR_SET(zp, attr, value, pflags, tx) \
{ \
	if (value) \
		pflags |= attr; \
	else \
		pflags &= ~attr; \
	VERIFY(0 == sa_update(zp->z_sa_hdl, SA_ZPL_FLAGS(ZTOZSB(zp)), \
	    &pflags, sizeof (pflags), tx)); \
}

/*
 * Define special zfs pflags
 */
#define	ZFS_XATTR		0x1		/* is an extended attribute */
#define	ZFS_INHERIT_ACE		0x2		/* ace has inheritable ACEs */
#define	ZFS_ACL_TRIVIAL		0x4		/* files ACL is trivial */
#define	ZFS_ACL_OBJ_ACE		0x8		/* ACL has CMPLX Object ACE */
#define	ZFS_ACL_PROTECTED	0x10		/* ACL protected */
#define	ZFS_ACL_DEFAULTED	0x20		/* ACL should be defaulted */
#define	ZFS_ACL_AUTO_INHERIT	0x40		/* ACL should be inherited */
#define	ZFS_BONUS_SCANSTAMP	0x80		/* Scanstamp in bonus area */
#define	ZFS_NO_EXECS_DENIED	0x100		/* exec was given to everyone */

#define	SA_ZPL_ATIME(z)		z->z_attr_table[ZPL_ATIME]
#define	SA_ZPL_MTIME(z)		z->z_attr_table[ZPL_MTIME]
#define	SA_ZPL_CTIME(z)		z->z_attr_table[ZPL_CTIME]
#define	SA_ZPL_CRTIME(z)	z->z_attr_table[ZPL_CRTIME]
#define	SA_ZPL_GEN(z)		z->z_attr_table[ZPL_GEN]
#define	SA_ZPL_DACL_ACES(z)	z->z_attr_table[ZPL_DACL_ACES]
#define	SA_ZPL_XATTR(z)		z->z_attr_table[ZPL_XATTR]
#define	SA_ZPL_SYMLINK(z)	z->z_attr_table[ZPL_SYMLINK]
#define	SA_ZPL_RDEV(z)		z->z_attr_table[ZPL_RDEV]
#define	SA_ZPL_SCANSTAMP(z)	z->z_attr_table[ZPL_SCANSTAMP]
#define	SA_ZPL_UID(z)		z->z_attr_table[ZPL_UID]
#define	SA_ZPL_GID(z)		z->z_attr_table[ZPL_GID]
#define	SA_ZPL_PARENT(z)	z->z_attr_table[ZPL_PARENT]
#define	SA_ZPL_LINKS(z)		z->z_attr_table[ZPL_LINKS]
#define	SA_ZPL_MODE(z)		z->z_attr_table[ZPL_MODE]
#define	SA_ZPL_DACL_COUNT(z)	z->z_attr_table[ZPL_DACL_COUNT]
#define	SA_ZPL_FLAGS(z)		z->z_attr_table[ZPL_FLAGS]
#define	SA_ZPL_SIZE(z)		z->z_attr_table[ZPL_SIZE]
#define	SA_ZPL_ZNODE_ACL(z)	z->z_attr_table[ZPL_ZNODE_ACL]
#define	SA_ZPL_DXATTR(z)	z->z_attr_table[ZPL_DXATTR]
#define	SA_ZPL_PAD(z)		z->z_attr_table[ZPL_PAD]

/*
 * Is ID ephemeral?
 */
#define	IS_EPHEMERAL(x)		(x > MAXUID)

/*
 * Should we use FUIDs?
 */
#define	USE_FUIDS(version, os)	(version >= ZPL_VERSION_FUID && \
    spa_version(dmu_objset_spa(os)) >= SPA_VERSION_FUID)
#define	USE_SA(version, os) (version >= ZPL_VERSION_SA && \
    spa_version(dmu_objset_spa(os)) >= SPA_VERSION_SA)

#define	MASTER_NODE_OBJ	1

/*
 * Special attributes for master node.
 * "userquota@" and "groupquota@" are also valid (from
 * zfs_userquota_prop_prefixes[]).
 */
#define	ZFS_FSID		"FSID"
#define	ZFS_UNLINKED_SET	"DELETE_QUEUE"
#define	ZFS_ROOT_OBJ		"ROOT"
#define	ZPL_VERSION_STR		"VERSION"
#define	ZFS_FUID_TABLES		"FUID"
#define	ZFS_SHARES_DIR		"SHARES"
#define	ZFS_SA_ATTRS		"SA_ATTRS"

#define	ZFS_MAX_BLOCKSIZE	(SPA_MAXBLOCKSIZE)

/*
 * Path component length
 *
 * The generic fs code uses MAXNAMELEN to represent
 * what the largest component length is.  Unfortunately,
 * this length includes the terminating NULL.  ZFS needs
 * to tell the users via pathconf() and statvfs() what the
 * true maximum length of a component is, excluding the NULL.
 */
#define	ZFS_MAXNAMELEN	(MAXNAMELEN - 1)

/*
 * Convert mode bits (zp_mode) to BSD-style DT_* values for storing in
 * the directory entries.  On Linux systems this value is already
 * defined correctly as part of the /usr/include/dirent.h header file.
 */
#ifndef IFTODT
#define	IFTODT(mode) (((mode) & S_IFMT) >> 12)
#endif

/*
 * The directory entry has the type (currently unused on Solaris) in the
 * top 4 bits, and the object number in the low 48 bits.  The "middle"
 * 12 bits are unused.
 */
#define	ZFS_DIRENT_TYPE(de) BF64_GET(de, 60, 4)
#define	ZFS_DIRENT_OBJ(de) BF64_GET(de, 0, 48)

/*
 * Directory entry locks control access to directory entries.
 * They are used to protect creates, deletes, and renames.
 * Each directory znode has a mutex and a list of locked names.
 */
#ifdef _KERNEL
typedef struct zfs_dirlock {
	char		*dl_name;	/* directory entry being locked */
	uint32_t	dl_sharecnt;	/* 0 if exclusive, > 0 if shared */
	uint8_t		dl_namelock;	/* 1 if z_name_lock is NOT held */
	uint16_t	dl_namesize;	/* set if dl_name was allocated */
	kcondvar_t	dl_cv;		/* wait for entry to be unlocked */
	struct znode	*dl_dzp;	/* directory znode */
	struct zfs_dirlock *dl_next;	/* next in z_dirlocks list */
} zfs_dirlock_t;

typedef struct znode {
	uint64_t	z_id;		/* object ID for this znode */
	kmutex_t	z_lock;		/* znode modification lock */
	krwlock_t	z_parent_lock;	/* parent lock for directories */
	krwlock_t	z_name_lock;	/* "master" lock for dirent locks */
	zfs_dirlock_t	*z_dirlocks;	/* directory entry lock list */
	kmutex_t	z_range_lock;	/* protects changes to z_range_avl */
	avl_tree_t	z_range_avl;	/* avl tree of file range locks */
	uint8_t		z_unlinked;	/* file has been unlinked */
	uint8_t		z_atime_dirty;	/* atime needs to be synced */
	uint8_t		z_zn_prefetch;	/* Prefetch znodes? */
	uint8_t		z_moved;	/* Has this znode been moved? */
	uint_t		z_blksz;	/* block size in bytes */
	uint_t		z_seq;		/* modification sequence number */
	uint64_t	z_mapcnt;	/* number of pages mapped to file */
	uint64_t	z_gen;		/* generation (cached) */
	uint64_t	z_size;		/* file size (cached) */
	uint64_t	z_atime[2];	/* atime (cached) */
	uint64_t	z_links;	/* file links (cached) */
	uint64_t	z_pflags;	/* pflags (cached) */
	uint64_t	z_uid;		/* uid fuid (cached) */
	uint64_t	z_gid;		/* gid fuid (cached) */
	uint32_t	z_sync_cnt;	/* synchronous open count */
	mode_t		z_mode;		/* mode (cached) */
	kmutex_t	z_acl_lock;	/* acl data lock */
	zfs_acl_t	*z_acl_cached;	/* cached acl */
	krwlock_t	z_xattr_lock;	/* xattr data lock */
	nvlist_t	*z_xattr_cached; /* cached xattrs */
	struct znode	*z_xattr_parent; /* xattr parent znode */
	list_node_t	z_link_node;	/* all znodes in fs link */
	sa_handle_t	*z_sa_hdl;	/* handle to sa data */
	boolean_t	z_is_sa;	/* are we native sa? */
	boolean_t	z_is_zvol;	/* are we used by the zvol */
	boolean_t	z_is_mapped;	/* are we mmap'ed */
	boolean_t	z_is_ctldir;	/* are we .zfs entry */
	boolean_t	z_is_stale;	/* are we stale due to rollback? */
	struct inode	z_inode;	/* generic vfs inode */
} znode_t;


/*
 * Range locking rules
 * --------------------
 * 1. When truncating a file (zfs_create, zfs_setattr, zfs_space) the whole
 *    file range needs to be locked as RL_WRITER. Only then can the pages be
 *    freed etc and zp_size reset. zp_size must be set within range lock.
 * 2. For writes and punching holes (zfs_write & zfs_space) just the range
 *    being written or freed needs to be locked as RL_WRITER.
 *    Multiple writes at the end of the file must coordinate zp_size updates
 *    to ensure data isn't lost. A compare and swap loop is currently used
 *    to ensure the file size is at least the offset last written.
 * 3. For reads (zfs_read, zfs_get_data & zfs_putapage) just the range being
 *    read needs to be locked as RL_READER. A check against zp_size can then
 *    be made for reading beyond end of file.
 */

/*
 * Convert between znode pointers and inode pointers
 */
#define	ZTOI(znode)	(&((znode)->z_inode))
#define	ITOZ(inode)	(container_of((inode), znode_t, z_inode))
#define	ZTOZSB(znode)	((zfs_sb_t *)(ZTOI(znode)->i_sb->s_fs_info))
#define	ITOZSB(inode)	((zfs_sb_t *)((inode)->i_sb->s_fs_info))

#define	S_ISDEV(mode)	(S_ISCHR(mode) || S_ISBLK(mode) || S_ISFIFO(mode))

/* Called on entry to each ZFS vnode and vfs operation  */
#define	ZFS_ENTER(zsb) \
	{ \
		rrw_enter_read(&(zsb)->z_teardown_lock, FTAG); \
		if ((zsb)->z_unmounted) { \
			ZFS_EXIT(zsb); \
			return (EIO); \
		} \
	}

/* Must be called before exiting the vop */
#define	ZFS_EXIT(zsb) \
	{ \
		rrw_exit(&(zsb)->z_teardown_lock, FTAG); \
		tsd_exit(); \
	}

/* Verifies the znode is valid */
#define	ZFS_VERIFY_ZP(zp) \
	if ((zp)->z_sa_hdl == NULL) { \
		ZFS_EXIT(ZTOZSB(zp)); \
		return (EIO); \
	}

/*
 * Macros for dealing with dmu_buf_hold
 */
#define	ZFS_OBJ_HASH(obj_num)	((obj_num) & (ZFS_OBJ_MTX_SZ - 1))
#define	ZFS_OBJ_MUTEX(zsb, obj_num)	\
	(&(zsb)->z_hold_mtx[ZFS_OBJ_HASH(obj_num)])
#define	ZFS_OBJ_HOLD_ENTER(zsb, obj_num) \
	mutex_enter(ZFS_OBJ_MUTEX((zsb), (obj_num)))
#define	ZFS_OBJ_HOLD_TRYENTER(zsb, obj_num) \
	mutex_tryenter(ZFS_OBJ_MUTEX((zsb), (obj_num)))
#define	ZFS_OBJ_HOLD_EXIT(zsb, obj_num) \
	mutex_exit(ZFS_OBJ_MUTEX((zsb), (obj_num)))
#define	ZFS_OBJ_HOLD_OWNED(zsb, obj_num) \
	mutex_owned(ZFS_OBJ_MUTEX((zsb), (obj_num)))

/* Encode ZFS stored time values from a struct timespec */
#define	ZFS_TIME_ENCODE(tp, stmp)		\
{						\
	(stmp)[0] = (uint64_t)(tp)->tv_sec;	\
	(stmp)[1] = (uint64_t)(tp)->tv_nsec;	\
}

/* Decode ZFS stored time values to a struct timespec */
#define	ZFS_TIME_DECODE(tp, stmp)		\
{						\
	(tp)->tv_sec = (time_t)(stmp)[0];		\
	(tp)->tv_nsec = (long)(stmp)[1];		\
}

/*
 * Timestamp defines
 */
#define	ACCESSED		(ATTR_ATIME)
#define	STATE_CHANGED		(ATTR_CTIME)
#define	CONTENT_MODIFIED	(ATTR_MTIME | ATTR_CTIME)

#define	ZFS_ACCESSTIME_STAMP(zsb, zp) \
	if ((zsb)->z_atime && !(zfs_is_readonly(zsb))) \
		zfs_tstamp_update_setup(zp, ACCESSED, NULL, NULL, B_FALSE);

extern int	zfs_init_fs(zfs_sb_t *, znode_t **);
extern void	zfs_set_dataprop(objset_t *);
extern void	zfs_create_fs(objset_t *os, cred_t *cr, nvlist_t *,
    dmu_tx_t *tx);
extern void	zfs_tstamp_update_setup(znode_t *, uint_t, uint64_t [2],
    uint64_t [2], boolean_t);
extern void	zfs_grow_blocksize(znode_t *, uint64_t, dmu_tx_t *);
extern int	zfs_freesp(znode_t *, uint64_t, uint64_t, int, boolean_t);
extern void	zfs_znode_init(void);
extern void	zfs_znode_fini(void);
extern int	zfs_zget(zfs_sb_t *, uint64_t, znode_t **);
extern int	zfs_rezget(znode_t *);
extern void	zfs_zinactive(znode_t *);
extern void	zfs_znode_delete(znode_t *, dmu_tx_t *);
extern void	zfs_remove_op_tables(void);
extern int	zfs_create_op_tables(void);
extern int	zfs_sync(struct super_block *, int, cred_t *);
extern dev_t	zfs_cmpldev(uint64_t);
extern int	zfs_get_zplprop(objset_t *os, zfs_prop_t prop, uint64_t *value);
extern int	zfs_get_stats(objset_t *os, nvlist_t *nv);
extern void	zfs_znode_dmu_fini(znode_t *);
extern int	zfs_inode_alloc(struct super_block *, struct inode **ip);
extern void	zfs_inode_destroy(struct inode *);
extern void	zfs_inode_update(znode_t *);

extern void zfs_log_create(zilog_t *zilog, dmu_tx_t *tx, uint64_t txtype,
    znode_t *dzp, znode_t *zp, char *name, vsecattr_t *, zfs_fuid_info_t *,
    vattr_t *vap);
extern int zfs_log_create_txtype(zil_create_t, vsecattr_t *vsecp,
    vattr_t *vap);
extern void zfs_log_remove(zilog_t *zilog, dmu_tx_t *tx, uint64_t txtype,
    znode_t *dzp, char *name, uint64_t foid);
#define	ZFS_NO_OBJECT	0	/* no object id */
extern void zfs_log_link(zilog_t *zilog, dmu_tx_t *tx, uint64_t txtype,
    znode_t *dzp, znode_t *zp, char *name);
extern void zfs_log_symlink(zilog_t *zilog, dmu_tx_t *tx, uint64_t txtype,
    znode_t *dzp, znode_t *zp, char *name, char *link);
extern void zfs_log_rename(zilog_t *zilog, dmu_tx_t *tx, uint64_t txtype,
    znode_t *sdzp, char *sname, znode_t *tdzp, char *dname, znode_t *szp);
extern void zfs_log_write(zilog_t *zilog, dmu_tx_t *tx, int txtype,
    znode_t *zp, offset_t off, ssize_t len, int ioflag,
    zil_callback_t callback, void *callback_data);
extern void zfs_log_truncate(zilog_t *zilog, dmu_tx_t *tx, int txtype,
    znode_t *zp, uint64_t off, uint64_t len);
extern void zfs_log_setattr(zilog_t *zilog, dmu_tx_t *tx, int txtype,
    znode_t *zp, vattr_t *vap, uint_t mask_applied, zfs_fuid_info_t *fuidp);
extern void zfs_log_acl(zilog_t *zilog, dmu_tx_t *tx, znode_t *zp,
    vsecattr_t *vsecp, zfs_fuid_info_t *fuidp);
extern void zfs_xvattr_set(znode_t *zp, xvattr_t *xvap, dmu_tx_t *tx);
extern void zfs_upgrade(zfs_sb_t *zsb, dmu_tx_t *tx);
extern int zfs_create_share_dir(zfs_sb_t *zsb, dmu_tx_t *tx);

#if defined(HAVE_UIO_RW)
extern caddr_t zfs_map_page(page_t *, enum seg_rw);
extern void zfs_unmap_page(page_t *, caddr_t);
#endif /* HAVE_UIO_RW */

extern zil_get_data_t zfs_get_data;
extern zil_replay_func_t zfs_replay_vector[TX_MAX_TYPE];
extern int zfsfstype;

#endif /* _KERNEL */

extern int zfs_obj_to_path(objset_t *osp, uint64_t obj, char *buf, int len);

#ifdef	__cplusplus
}
#endif

#endif	/* _SYS_FS_ZFS_ZNODE_H */