Loading...
  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
386
387
388
389
390
391
392
393
394
395
396
397
398
399
400
401
402
403
404
405
406
407
408
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
435
436
437
438
439
440
441
442
443
444
445
446
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
481
482
483
484
485
486
487
488
489
490
491
492
493
494
495
496
497
498
499
500
501
502
503
504
505
506
507
508
509
510
511
512
513
514
515
516
517
518
/*
 * Copyright (c) 2000-2018 Apple Inc. All rights reserved.
 *
 * @APPLE_OSREFERENCE_LICENSE_HEADER_START@
 *
 * This file contains Original Code and/or Modifications of Original Code
 * as defined in and that are subject to the Apple Public Source License
 * Version 2.0 (the 'License'). You may not use this file except in
 * compliance with the License. The rights granted to you under the License
 * may not be used to create, or enable the creation or redistribution of,
 * unlawful or unlicensed copies of an Apple operating system, or to
 * circumvent, violate, or enable the circumvention or violation of, any
 * terms of an Apple operating system software license agreement.
 *
 * Please obtain a copy of the License at
 * http://www.opensource.apple.com/apsl/ and read it before using this file.
 *
 * The Original Code and all software distributed under the License are
 * distributed on an 'AS IS' basis, WITHOUT WARRANTY OF ANY KIND, EITHER
 * EXPRESS OR IMPLIED, AND APPLE HEREBY DISCLAIMS ALL SUCH WARRANTIES,
 * INCLUDING WITHOUT LIMITATION, ANY WARRANTIES OF MERCHANTABILITY,
 * FITNESS FOR A PARTICULAR PURPOSE, QUIET ENJOYMENT OR NON-INFRINGEMENT.
 * Please see the License for the specific language governing rights and
 * limitations under the License.
 *
 * @APPLE_OSREFERENCE_LICENSE_HEADER_END@
 */
/* Copyright (c) 1995 NeXT Computer, Inc. All Rights Reserved */
/*
 * Copyright (c) 1989, 1991, 1993
 *	The Regents of the University of California.  All rights reserved.
 *
 * Redistribution and use in source and binary forms, with or without
 * modification, are permitted provided that the following conditions
 * are met:
 * 1. Redistributions of source code must retain the above copyright
 *    notice, this list of conditions and the following disclaimer.
 * 2. Redistributions in binary form must reproduce the above copyright
 *    notice, this list of conditions and the following disclaimer in the
 *    documentation and/or other materials provided with the distribution.
 * 3. All advertising materials mentioning features or use of this software
 *    must display the following acknowledgement:
 *	This product includes software developed by the University of
 *	California, Berkeley and its contributors.
 * 4. Neither the name of the University nor the names of its contributors
 *    may be used to endorse or promote products derived from this software
 *    without specific prior written permission.
 *
 * THIS SOFTWARE IS PROVIDED BY THE REGENTS AND CONTRIBUTORS ``AS IS'' AND
 * ANY EXPRESS OR IMPLIED WARRANTIES, INCLUDING, BUT NOT LIMITED TO, THE
 * IMPLIED WARRANTIES OF MERCHANTABILITY AND FITNESS FOR A PARTICULAR PURPOSE
 * ARE DISCLAIMED.  IN NO EVENT SHALL THE REGENTS OR CONTRIBUTORS BE LIABLE
 * FOR ANY DIRECT, INDIRECT, INCIDENTAL, SPECIAL, EXEMPLARY, OR CONSEQUENTIAL
 * DAMAGES (INCLUDING, BUT NOT LIMITED TO, PROCUREMENT OF SUBSTITUTE GOODS
 * OR SERVICES; LOSS OF USE, DATA, OR PROFITS; OR BUSINESS INTERRUPTION)
 * HOWEVER CAUSED AND ON ANY THEORY OF LIABILITY, WHETHER IN CONTRACT, STRICT
 * LIABILITY, OR TORT (INCLUDING NEGLIGENCE OR OTHERWISE) ARISING IN ANY WAY
 * OUT OF THE USE OF THIS SOFTWARE, EVEN IF ADVISED OF THE POSSIBILITY OF
 * SUCH DAMAGE.
 *
 *	@(#)mount.h	8.21 (Berkeley) 5/20/95
 */
/*
 * NOTICE: This file was modified by McAfee Research in 2004 to introduce
 * support for mandatory and extensible security protections.  This notice
 * is included in support of clause 2.2 (b) of the Apple Public License,
 * Version 2.0.
 */

#ifndef _SYS_MOUNT_INTERNAL_H_
#define _SYS_MOUNT_INTERNAL_H_

#include <sys/appleapiopts.h>
#ifndef KERNEL
#include <sys/ucred.h>
#else
#include <sys/kernel_types.h>
#include <sys/namei.h>
#endif
#include <sys/queue.h>
#include <sys/lock.h>
#include <net/radix.h>
#include <sys/socket.h>         /* XXX for AF_MAX */
#include <sys/vfs_context.h>            /* XXX for AF_MAX */
#include <sys/mount.h>
#include <sys/cdefs.h>
#include <sys/sysctl.h>

struct label;

#if defined(__i386__) || defined(__x86_64__)
typedef uint64_t  pending_io_t;
#define INCR_PENDING_IO(a, b) OSAddAtomic64((int64_t)(a), (int64_t *)&(b));
#else
typedef uint32_t  pending_io_t;
#define INCR_PENDING_IO(a, b) OSAddAtomic((int32_t)(a), (int32_t *)&(b));
#endif


/*
 * Structure per mounted file system.  Each mounted file system has an
 * array of operations and an instance record.  The file systems are
 * put on a doubly linked list.
 */
TAILQ_HEAD(vnodelst, vnode);

struct mount {
	TAILQ_ENTRY(mount)      mnt_list;                   /* mount list */
	int32_t                 mnt_count;                  /* reference on the mount */
	lck_mtx_t               mnt_mlock;                  /* mutex that protects mount point */
	const struct vfsops     * XNU_PTRAUTH_SIGNED_PTR("mount.vfsops") mnt_op;        /* operations on fs */
	struct vfstable         * XNU_PTRAUTH_SIGNED_PTR("mount.mnt_vtable") mnt_vtable;        /* configuration info */
	struct vnode            * XNU_PTRAUTH_SIGNED_PTR("mount.mnt_vnodecovered") mnt_vnodecovered;    /* vnode we mounted on */
	struct vnodelst         mnt_vnodelist;              /* list of vnodes this mount */
	struct vnodelst         mnt_workerqueue;            /* list of vnodes this mount */
	struct vnodelst         mnt_newvnodes;              /* list of vnodes this mount */
	uint32_t                mnt_flag;                   /* flags */
	uint32_t                mnt_kern_flag;              /* kernel only flags.  NOTE: See mnt_supl_kern_flags below! */
	uint32_t                mnt_compound_ops;           /* Available compound operations */
	uint32_t                mnt_lflag;                  /* mount life cycle flags */
	uint32_t                mnt_maxsymlinklen;          /* max size of short symlink */
	struct vfsstatfs        mnt_vfsstat;                /* cache of filesystem stats */
	qaddr_t                 mnt_data;                   /* private data */
	/* Cached values of the IO constraints for the device */
	uint32_t                mnt_maxreadcnt;             /* Max. byte count for read */
	uint32_t                mnt_maxwritecnt;            /* Max. byte count for write */
	uint32_t                mnt_segreadcnt;             /* Max. segment count for read */
	uint32_t                mnt_segwritecnt;            /* Max. segment count for write */
	uint32_t                mnt_maxsegreadsize;         /* Max. segment read size  */
	uint32_t                mnt_maxsegwritesize;        /* Max. segment write size */
	uint32_t                mnt_alignmentmask;          /* Mask of bits that aren't addressable via DMA */
	uint32_t                mnt_devblocksize;           /* the underlying device block size */
	uint32_t                mnt_ioqueue_depth;          /* the maxiumum number of commands a device can accept */
	uint32_t                mnt_ioscale;                /* scale the various throttles/limits imposed on the amount of I/O in flight */
	uint32_t                mnt_ioflags;                /* flags for  underlying device */
	uint32_t                mnt_minsaturationbytecount; /* if non-zero, mininum amount of writes (in bytes) needed to max out throughput */
	pending_io_t            mnt_pending_write_size __attribute__((aligned(sizeof(pending_io_t))));  /* byte count of pending writes */
	pending_io_t            mnt_pending_read_size  __attribute__((aligned(sizeof(pending_io_t))));  /* byte count of pending reads */
	struct timeval          mnt_last_write_issued_timestamp;
	struct timeval          mnt_last_write_completed_timestamp;
	int64_t                 mnt_max_swappin_available;

	lck_rw_t                mnt_rwlock;                 /* mutex readwrite lock */
	lck_mtx_t               mnt_renamelock;             /* mutex that serializes renames that change shape of tree */
	vnode_t                 mnt_devvp;                  /* the device mounted on for local file systems */
	uint32_t                mnt_devbsdunit;             /* the BSD unit number of the device */
	uint64_t                mnt_throttle_mask;          /* the throttle mask of what devices will be affected by I/O from this mnt */
	void                    *mnt_throttle_info;         /* used by the throttle code */
	int32_t                 mnt_crossref;               /* refernces to cover lookups  crossing into mp */
	int32_t                 mnt_iterref;                /* refernces to cover iterations; drained makes it -ve  */
#if CONFIG_TRIGGERS
	int32_t                 mnt_numtriggers;            /* num of trigger vnodes for this mount */
	vfs_trigger_callback_t  *mnt_triggercallback;
	void                    *mnt_triggerdata;
#endif
	/* XXX 3762912 hack to support HFS filesystem 'owner' */
	uid_t                   mnt_fsowner;
	gid_t                   mnt_fsgroup;

	struct label            *mnt_mntlabel;              /* MAC mount label */

	/*
	 * cache the rootvp of the last mount point
	 * in the chain in the mount struct pointed
	 * to by the vnode sitting in '/'
	 * this cache is used to shortcircuit the
	 * mount chain traversal and allows us
	 * to traverse to the true underlying rootvp
	 * in 1 easy step inside of 'cache_lookup_path'
	 *
	 * make sure to validate against the cached vid
	 * in case the rootvp gets stolen away since
	 * we don't take an explicit long term reference
	 * on it when we mount it
	 */
	vnode_t                 mnt_realrootvp;
	uint32_t                mnt_realrootvp_vid;
	/*
	 * bumped each time a mount or unmount
	 * occurs... its used to invalidate
	 * 'mnt_realrootvp' from the cache
	 */
	uint32_t                mnt_generation;
	/*
	 * if 'MNTK_AUTH_CACHE_TIMEOUT' is
	 * set, then 'mnt_authcache_ttl' is
	 * the time-to-live for the per-vnode authentication cache
	 * on this mount... if zero, no cache is maintained...
	 * if 'MNTK_AUTH_CACHE_TIMEOUT' isn't set, its the
	 * time-to-live for the cached lookup right for
	 * volumes marked 'MNTK_AUTH_OPAQUE'.
	 */
	int                     mnt_authcache_ttl;
	char                    fstypename_override[MFSTYPENAMELEN];

	uint32_t                mnt_iobufinuse;

	void                    *mnt_disk_conditioner_info;

	lck_mtx_t               mnt_iter_lock;              /* mutex that protects iteration of vnodes */

	uint64_t                mnt_mount_id;               /* system-wide unique mount ID */
	uint32_t                mnt_supl_kern_flag;         /* Supplemental kernel-only mount flags */
};

/*
 * default number of seconds to keep cached lookup
 * rights valid on mounts marked MNTK_AUTH_OPAQUE
 */
#define CACHED_LOOKUP_RIGHT_TTL         2

/*
 * ioflags
 */
#define MNT_IOFLAGS_FUA_SUPPORTED       0x00000001
#define MNT_IOFLAGS_UNMAP_SUPPORTED     0x00000002
#define MNT_IOFLAGS_IOSCHED_SUPPORTED   0x00000004
#define MNT_IOFLAGS_CSUNMAP_SUPPORTED   0x00000008
#define MNT_IOFLAGS_SWAPPIN_SUPPORTED   0x00000010
#define MNT_IOFLAGS_FUSION_DRIVE        0x00000020
#define MNT_IOFLAGS_PERIPHERAL_DRIVE    0x00000040 /* External: Attached directly to the system (USB,TBT,FW,etc.) */

/*
 * ioqueue depth for devices that don't report one
 */
#define MNT_DEFAULT_IOQUEUE_DEPTH       32

/*
 * mnt_ioscale value for the given ioqueue depth
 */
#define MNT_IOSCALE(ioqueue_depth)      ((ioqueue_depth + (MNT_DEFAULT_IOQUEUE_DEPTH - 1)) / MNT_DEFAULT_IOQUEUE_DEPTH)

/* mount point to which dead vps point to */
extern struct mount * const dead_mountp;

/*
 * Internal filesystem control flags stored in mnt_kern_flag.
 *
 * MNTK_UNMOUNT locks the mount entry so that name lookup cannot proceed
 * past the mount point.  This keeps the subtree stable during mounts
 * and unmounts.
 *
 * Note:	We are counting down on new bit assignments.  This is
 *		because the bits here were broken out from the high bits
 *		of the mount flags.
 */
#define MNTK_SYSTEM             0x00000040      /* Volume associated with system volume (do not allow unmount) */
#define MNTK_NOSWAP             0x00000080      /* swap files cannot be used on this mount */
#define MNTK_SWAP_MOUNT         0x00000100      /* we are swapping to this mount */
#define MNTK_DENY_READDIREXT    0x00000200      /* Deny Extended-style readdir's for this volume */
#define MNTK_PERMIT_UNMOUNT     0x00000400      /* Allow (non-forced) unmounts by UIDs other than the one that mounted the volume */
#define MNTK_TYPENAME_OVERRIDE  0x00000800      /* override the fstypename for statfs() */
#define MNTK_KERNEL_MOUNT       0x00001000      /* mount came from kernel side */
#ifdef CONFIG_IMGSRC_ACCESS
#define MNTK_HAS_MOVED          0x00002000
#endif /* CONFIG_IMGSRC_ACCESS */
#define MNTK_BACKS_ROOT         0x00004000      /* mount contains a disk image backing the root filesystem - therefore it mustn't be unmounted */
#define MNTK_AUTH_CACHE_TTL     0x00008000      /* rights cache has TTL - TTL of 0 disables cache */
#define MNTK_PATH_FROM_ID       0x00010000      /* mounted file system supports id-to-path lookups */
#define MNTK_UNMOUNT_PREFLIGHT  0x00020000      /* mounted file system wants preflight check during unmount */
#define MNTK_NAMED_STREAMS      0x00040000      /* mounted file system supports Named Streams VNOPs */
#define MNTK_EXTENDED_ATTRS     0x00080000      /* mounted file system supports Extended Attributes VNOPs */
#define MNTK_LOCK_LOCAL         0x00100000      /* advisory locking is done above the VFS itself */
#define MNTK_VIRTUALDEV         0x00200000      /* mounted on a virtual device i.e. a disk image */
#define MNTK_ROOTDEV            0x00400000      /* this filesystem resides on the same device as the root - appears unused as of 2020 */
#define MNTK_SSD                0x00800000      /* underlying device is of the solid state variety */
#define MNTK_UNMOUNT            0x01000000      /* unmount in progress */
#define MNTK_MWAIT              0x02000000      /* waiting for unmount to finish - appears unused as of 2020 */
#define MNTK_WANTRDWR           0x04000000      /* upgrade to read/write requested */
#define MNTK_SYSTEMDATA         0x08000000      /* volume is a Data volume tightly linked with System root volume. Firmlinks, etc */
#define MNTK_DIR_HARDLINKS      0x10000000      /* mounted file system supports directory hard links */
#define MNTK_AUTH_OPAQUE        0x20000000      /* authorisation decisions are not made locally */
#define MNTK_AUTH_OPAQUE_ACCESS 0x40000000      /* VNOP_ACCESS is reliable for remote auth */
#define MNTK_EXTENDED_SECURITY  0x80000000      /* extended security supported */


/*
 * Internal supplemental FS control flags stored in mnt_supl_kern_flag
 *
 * NOTE: The 32 bits in the above-mentioned 32bit flag word (mnt_kern_flag) have been
 * exhausted, so this is intended as a supplement.
 */
#define MNTK_SUPL_BASESYSTEM    0x00000001


/*
 * Mount Lifecycle Flags (stored in mnt_lflag)
 */
#define MNT_LNOTRESP            0x00000001      /* mount not responding */
#define MNT_LUNMOUNT            0x00000002      /* mount in unmount */
#define MNT_LFORCE              0x00000004      /* mount in forced unmount */
#define MNT_LDRAIN              0x00000008      /* mount in drain */
#define MNT_LITER               0x00000010      /* mount in iteration */
#define MNT_LNEWVN              0x00000020      /* mount has new vnodes created */
#define MNT_LWAIT               0x00000040      /* wait for unmount op */
#define MNT_LMOUNT              0x00000080      /* not finished mounting */
#define MNT_LDEAD               0x00000100      /* mount already unmounted*/
#define MNT_LNOSUB              0x00000200      /* submount - no recursion */

/*
 * Filesystem configuration information. One of these exists for each
 * type of filesystem supported by the kernel. These are searched at
 * mount time to identify the requested filesystem.
 */
struct vfstable {
	const struct vfsops *vfc_vfsops;/* filesystem operations vector */
	char        vfc_name[MFSNAMELEN];   /* filesystem type name */
	int         vfc_typenum;            /* historic filesystem type number */
	int         vfc_refcount;           /* number mounted of this type */
	int         vfc_flags;              /* permanent flags */
	int         (*vfc_mountroot)(mount_t, vnode_t, vfs_context_t);      /* if != NULL, routine to mount root */
	struct      vfstable *vfc_next;     /* next in list */
	int32_t     vfc_reserved1;
	int32_t     vfc_reserved2;
	int         vfc_vfsflags;           /* for optional types */
	void       *vfc_descptr;            /* desc table allocated address */
	uint32_t    vfc_descsize;           /* number of elements in desc table */
	struct sysctl_oid       *vfc_sysctl;    /* dynamically registered sysctl node */
};

/* vfc_vfsflags: */
#define VFC_VFSLOCALARGS        0x002
#define VFC_VFSGENERICARGS      0x004
#define VFC_VFSNATIVEXATTR      0x010
#define VFC_VFSCANMOUNTROOT 0x020
#define VFC_VFSPREFLIGHT        0x040
#define VFC_VFSREADDIR_EXTENDED 0x080
#define VFC_VFS64BITREADY       0x100
#define VFC_VFSNOMACLABEL       0x1000
#define VFC_VFSVNOP_PAGEINV2    0x2000
#define VFC_VFSVNOP_PAGEOUTV2   0x4000
#define VFC_VFSVNOP_NOUPDATEID_RENAME   0x8000
#define VFC_VFSVNOP_SECLUDE_RENAME      0x10000

extern int maxvfstypenum;               /* highest defined filesystem type */
extern struct vfstable  *vfsconf;       /* head of list of filesystem types */
extern const int maxvfsslots;           /* Maximum statically allocated slots available to be used */
extern int numused_vfsslots;    /* number of statically allocated slots already used */
extern int numregistered_fses;  /* number of total registered filesystems */

/* the following two are xnu private */
struct vfstable *       vfstable_add(struct     vfstable *);
int     vfstable_del(struct vfstable *);


struct vfsmount_args {
	union {
		struct {
			char * mnt_fspec;
			void * mnt_fsdata;
		} mnt_localfs_args;
		struct {
			void *  mnt_fsdata;             /* FS specific */
		} mnt_remotefs_args;
	} mountfs_args;
};


/*
 * LP64 *user* version of statfs structure.
 * NOTE - must be kept in sync with struct statfs in mount.h
 */
struct user64_statfs {
	short           f_otype;                /* TEMPORARY SHADOW COPY OF f_type */
	short           f_oflags;               /* TEMPORARY SHADOW COPY OF f_flags */
	user64_long_t   f_bsize;                /* fundamental file system block size */
	user64_long_t   f_iosize;               /* optimal transfer block size */
	user64_long_t   f_blocks;               /* total data blocks in file system */
	user64_long_t   f_bfree;                /* free blocks in fs */
	user64_long_t   f_bavail;               /* free blocks avail to non-superuser */
	user64_long_t   f_files;                /* total file nodes in file system */
	user64_long_t   f_ffree;                /* free file nodes in fs */
	fsid_t          f_fsid;                 /* file system id */
	uid_t           f_owner;                /* user that mounted the filesystem */
	short           f_reserved1;            /* spare for later */
	short           f_type;                 /* type of filesystem */
	user64_long_t   f_flags;                /* copy of mount exported flags */
	user64_long_t   f_reserved2[2];         /* reserved for future use */
	char            f_fstypename[MFSNAMELEN]; /* fs type name */
	char            f_mntonname[MNAMELEN];  /* directory on which mounted */
	char            f_mntfromname[MNAMELEN];/* mounted filesystem */
	char            f_reserved3;    /* For alignment */
	user64_long_t   f_reserved4[4]; /* For future use */
};

/*
 * ILP32 *user* version of statfs structure.
 * NOTE - must be kept in sync with struct statfs in mount.h
 */
struct user32_statfs {
	short           f_otype;                /* TEMPORARY SHADOW COPY OF f_type */
	short           f_oflags;               /* TEMPORARY SHADOW COPY OF f_flags */
	user32_long_t   f_bsize;                /* fundamental file system block size */
	user32_long_t   f_iosize;               /* optimal transfer block size */
	user32_long_t   f_blocks;               /* total data blocks in file system */
	user32_long_t   f_bfree;                /* free blocks in fs */
	user32_long_t   f_bavail;               /* free blocks avail to non-superuser */
	user32_long_t   f_files;                /* total file nodes in file system */
	user32_long_t   f_ffree;                /* free file nodes in fs */
	fsid_t          f_fsid;                 /* file system id */
	uid_t           f_owner;                /* user that mounted the filesystem */
	short           f_reserved1;    /* spare for later */
	short           f_type;                 /* type of filesystem */
	user32_long_t       f_flags;            /* copy of mount exported flags */
	user32_long_t f_reserved2[2];   /* reserved for future use */
	char            f_fstypename[MFSNAMELEN]; /* fs type name */
	char            f_mntonname[MNAMELEN];  /* directory on which mounted */
	char            f_mntfromname[MNAMELEN];/* mounted filesystem */
	char            f_reserved3;    /* For alignment */
	user32_long_t   f_reserved4[4]; /* For future use */
};

/*
 * throttle I/Os are affected only by normal I/Os happening on the same spindle.  Currently we use a 64-bit integer to
 * represent what devices are affected, so we can handle at most 64 different spindles.  Since
 * throttled I/O is usually useful in non-server environment only, this number is enough in most cases.
 */
#define LOWPRI_MAX_NUM_DEV 64

__BEGIN_DECLS

extern uint32_t mount_generation;
extern TAILQ_HEAD(mntlist, mount) mountlist;
void mount_list_lock(void);
void mount_list_unlock(void);
void mount_lock_init(mount_t);
void mount_lock_destroy(mount_t);
void mount_lock(mount_t);
void mount_lock_spin(mount_t);
void mount_unlock(mount_t);
void mount_iterate_lock(mount_t);
void mount_iterate_unlock(mount_t);
void mount_lock_renames(mount_t);
void mount_unlock_renames(mount_t);
void mount_ref(mount_t, int);
void mount_drop(mount_t, int);
int  mount_refdrain(mount_t);

/* vfs_rootmountalloc should be kept as a private api */
errno_t vfs_rootmountalloc(const char *, const char *, mount_t *mpp);

int vfs_mount_recovery(void);

typedef uint32_t vfs_switch_root_flags_t;
#define VFSSR_VIRTUALDEV_PROHIBITED     0x01 /* Not allowed to pivot into virtual devices (disk images).
	                                      * This is really just because we don't have a great way to find
	                                      * the filesystem that backs the image in order to set
	                                      * MNTK_BACKS_ROOT on it, which would prevent even forced-unmounts.
	                                      * Also, lots of disk images are backed by userspace processes,
	                                      * which also seems like a bad idea for the root filesystem. */

int vfs_switch_root(const char *, const char *, vfs_switch_root_flags_t);

int     vfs_mountroot(void);
void    vfs_unmountall(int only_non_system);
int     safedounmount(struct mount *, int, vfs_context_t);
int     dounmount(struct mount *, int, int, vfs_context_t);
void    dounmount_submounts(struct mount *, int, vfs_context_t);

/* xnu internal api */
void  mount_dropcrossref(mount_t, vnode_t, int);
mount_t mount_lookupby_volfsid(int, int);
mount_t mount_list_lookupby_fsid(fsid_t *, int, int);
int  mount_list_add(mount_t);
void mount_list_remove(mount_t);
int  mount_iterref(mount_t, int);
int  mount_isdrained(mount_t, int);
void mount_iterdrop(mount_t);
void mount_iterdrain(mount_t);
void mount_iterreset(mount_t);

/* These flags are used as flag bits in the `internal_flags` argument to mount_common */
/* Private NFS spi */
#define KERNEL_MOUNT_NOAUTH             0x01 /* Don't check the UID of the directory we are mounting on */
#define KERNEL_MOUNT_PERMIT_UNMOUNT     0x02 /* Allow (non-forced) unmounts by users other the one who mounted the volume */
/* used by snapshot mounting SPI */
#define KERNEL_MOUNT_SNAPSHOT           0x04 /* Mounting a snapshot */
#define KERNEL_MOUNT_DATAVOL            0x08 /* mount the data volume */
#define KERNEL_MOUNT_VMVOL              0x10 /* mount the VM volume */
#define KERNEL_MOUNT_PREBOOTVOL         0x20 /* mount the Preboot volume */
#define KERNEL_MOUNT_RECOVERYVOL        0x40 /* mount the Recovery volume */
#define KERNEL_MOUNT_BASESYSTEMROOT     0x80 /* mount a base root volume "instead of" the full root volume (only used during bsd_init) */
#define KERNEL_MOUNT_DEVFS             0x100 /* kernel startup mount of devfs */
#define KERNEL_MOUNT_FMOUNT            0x200 /* is fmount() system call */
#define KERNEL_MOUNT_KMOUNT            0x400 /* is kernel_mount() call */

/* mask for checking if any of the "mount volume by role" flags are set */
#define KERNEL_MOUNT_VOLBYROLE_MASK (KERNEL_MOUNT_DATAVOL | KERNEL_MOUNT_VMVOL | KERNEL_MOUNT_PREBOOTVOL | KERNEL_MOUNT_RECOVERYVOL)

/* mask for sanitizing inputs to kernel_mount() */
#define KERNEL_MOUNT_SANITIZE_MASK (~(KERNEL_MOUNT_FMOUNT))

/*
 * NOTE: kernel_mount() does not force MNT_NOSUID, MNT_NOEXEC, or MNT_NODEC for non-privileged
 * mounting credentials, as the mount(2) system call does.
 */
int kernel_mount(const char *, vnode_t, vnode_t, const char *, void *, size_t, int, uint32_t, vfs_context_t);

/* Throttled I/O API.  KPI/SPI is in systm.h. */

int  throttle_get_io_policy(struct uthread **ut);
int  throttle_get_passive_io_policy(struct uthread **ut);
void *throttle_info_update_by_mount(mount_t mp);
void rethrottle_thread(uthread_t ut);


/* throttled I/O helper function */
/* convert the lowest bit to a device index */
extern int num_trailing_0(uint64_t n);

/* sync lock */
extern int sync_timeout_seconds;

extern zone_t mount_zone;

__END_DECLS

#endif /* !_SYS_MOUNT_INTERNAL_H_ */