locks.c 57.3 KB
Newer Older
L
Linus Torvalds 已提交
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
/*
 *  linux/fs/locks.c
 *
 *  Provide support for fcntl()'s F_GETLK, F_SETLK, and F_SETLKW calls.
 *  Doug Evans (dje@spiff.uucp), August 07, 1992
 *
 *  Deadlock detection added.
 *  FIXME: one thing isn't handled yet:
 *	- mandatory locks (requires lots of changes elsewhere)
 *  Kelly Carmichael (kelly@[142.24.8.65]), September 17, 1994.
 *
 *  Miscellaneous edits, and a total rewrite of posix_lock_file() code.
 *  Kai Petzke (wpp@marie.physik.tu-berlin.de), 1994
 *  
 *  Converted file_lock_table to a linked list from an array, which eliminates
 *  the limits on how many active file locks are open.
 *  Chad Page (pageone@netcom.com), November 27, 1994
 * 
 *  Removed dependency on file descriptors. dup()'ed file descriptors now
 *  get the same locks as the original file descriptors, and a close() on
 *  any file descriptor removes ALL the locks on the file for the current
 *  process. Since locks still depend on the process id, locks are inherited
 *  after an exec() but not after a fork(). This agrees with POSIX, and both
 *  BSD and SVR4 practice.
 *  Andy Walker (andy@lysaker.kvaerner.no), February 14, 1995
 *
 *  Scrapped free list which is redundant now that we allocate locks
 *  dynamically with kmalloc()/kfree().
 *  Andy Walker (andy@lysaker.kvaerner.no), February 21, 1995
 *
 *  Implemented two lock personalities - FL_FLOCK and FL_POSIX.
 *
 *  FL_POSIX locks are created with calls to fcntl() and lockf() through the
 *  fcntl() system call. They have the semantics described above.
 *
 *  FL_FLOCK locks are created with calls to flock(), through the flock()
 *  system call, which is new. Old C libraries implement flock() via fcntl()
 *  and will continue to use the old, broken implementation.
 *
 *  FL_FLOCK locks follow the 4.4 BSD flock() semantics. They are associated
 *  with a file pointer (filp). As a result they can be shared by a parent
 *  process and its children after a fork(). They are removed when the last
 *  file descriptor referring to the file pointer is closed (unless explicitly
 *  unlocked). 
 *
 *  FL_FLOCK locks never deadlock, an existing lock is always removed before
 *  upgrading from shared to exclusive (or vice versa). When this happens
 *  any processes blocked by the current lock are woken up and allowed to
 *  run before the new lock is applied.
 *  Andy Walker (andy@lysaker.kvaerner.no), June 09, 1995
 *
 *  Removed some race conditions in flock_lock_file(), marked other possible
 *  races. Just grep for FIXME to see them. 
 *  Dmitry Gorodchanin (pgmdsg@ibi.com), February 09, 1996.
 *
 *  Addressed Dmitry's concerns. Deadlock checking no longer recursive.
 *  Lock allocation changed to GFP_ATOMIC as we can't afford to sleep
 *  once we've checked for blocking and deadlocking.
 *  Andy Walker (andy@lysaker.kvaerner.no), April 03, 1996.
 *
 *  Initial implementation of mandatory locks. SunOS turned out to be
 *  a rotten model, so I implemented the "obvious" semantics.
 *  See 'Documentation/mandatory.txt' for details.
 *  Andy Walker (andy@lysaker.kvaerner.no), April 06, 1996.
 *
 *  Don't allow mandatory locks on mmap()'ed files. Added simple functions to
 *  check if a file has mandatory locks, used by mmap(), open() and creat() to
 *  see if system call should be rejected. Ref. HP-UX/SunOS/Solaris Reference
 *  Manual, Section 2.
 *  Andy Walker (andy@lysaker.kvaerner.no), April 09, 1996.
 *
 *  Tidied up block list handling. Added '/proc/locks' interface.
 *  Andy Walker (andy@lysaker.kvaerner.no), April 24, 1996.
 *
 *  Fixed deadlock condition for pathological code that mixes calls to
 *  flock() and fcntl().
 *  Andy Walker (andy@lysaker.kvaerner.no), April 29, 1996.
 *
 *  Allow only one type of locking scheme (FL_POSIX or FL_FLOCK) to be in use
 *  for a given file at a time. Changed the CONFIG_LOCK_MANDATORY scheme to
 *  guarantee sensible behaviour in the case where file system modules might
 *  be compiled with different options than the kernel itself.
 *  Andy Walker (andy@lysaker.kvaerner.no), May 15, 1996.
 *
 *  Added a couple of missing wake_up() calls. Thanks to Thomas Meckel
 *  (Thomas.Meckel@mni.fh-giessen.de) for spotting this.
 *  Andy Walker (andy@lysaker.kvaerner.no), May 15, 1996.
 *
 *  Changed FL_POSIX locks to use the block list in the same way as FL_FLOCK
 *  locks. Changed process synchronisation to avoid dereferencing locks that
 *  have already been freed.
 *  Andy Walker (andy@lysaker.kvaerner.no), Sep 21, 1996.
 *
 *  Made the block list a circular list to minimise searching in the list.
 *  Andy Walker (andy@lysaker.kvaerner.no), Sep 25, 1996.
 *
 *  Made mandatory locking a mount option. Default is not to allow mandatory
 *  locking.
 *  Andy Walker (andy@lysaker.kvaerner.no), Oct 04, 1996.
 *
 *  Some adaptations for NFS support.
 *  Olaf Kirch (okir@monad.swb.de), Dec 1996,
 *
 *  Fixed /proc/locks interface so that we can't overrun the buffer we are handed.
 *  Andy Walker (andy@lysaker.kvaerner.no), May 12, 1997.
 *
 *  Use slab allocator instead of kmalloc/kfree.
 *  Use generic list implementation from <linux/list.h>.
 *  Sped up posix_locks_deadlock by only considering blocked locks.
 *  Matthew Wilcox <willy@debian.org>, March, 2000.
 *
 *  Leases and LOCK_MAND
 *  Matthew Wilcox <willy@debian.org>, June, 2000.
 *  Stephen Rothwell <sfr@canb.auug.org.au>, June, 2000.
 */

#include <linux/capability.h>
#include <linux/file.h>
#include <linux/fs.h>
#include <linux/init.h>
#include <linux/module.h>
#include <linux/security.h>
#include <linux/slab.h>
#include <linux/smp_lock.h>
#include <linux/syscalls.h>
#include <linux/time.h>
127
#include <linux/rcupdate.h>
128
#include <linux/pid_namespace.h>
L
Linus Torvalds 已提交
129 130 131 132 133 134 135 136 137 138 139 140 141

#include <asm/uaccess.h>

#define IS_POSIX(fl)	(fl->fl_flags & FL_POSIX)
#define IS_FLOCK(fl)	(fl->fl_flags & FL_FLOCK)
#define IS_LEASE(fl)	(fl->fl_flags & FL_LEASE)

int leases_enable = 1;
int lease_break_time = 45;

#define for_each_lock(inode, lockp) \
	for (lockp = &inode->i_flock; *lockp != NULL; lockp = &(*lockp)->fl_next)

142
static LIST_HEAD(file_lock_list);
L
Linus Torvalds 已提交
143 144
static LIST_HEAD(blocked_list);

145
static struct kmem_cache *filelock_cache __read_mostly;
L
Linus Torvalds 已提交
146 147 148 149

/* Allocate an empty lock structure. */
static struct file_lock *locks_alloc_lock(void)
{
150
	return kmem_cache_alloc(filelock_cache, GFP_KERNEL);
L
Linus Torvalds 已提交
151 152
}

153 154 155 156 157 158 159 160 161 162 163 164 165 166 167
static void locks_release_private(struct file_lock *fl)
{
	if (fl->fl_ops) {
		if (fl->fl_ops->fl_release_private)
			fl->fl_ops->fl_release_private(fl);
		fl->fl_ops = NULL;
	}
	if (fl->fl_lmops) {
		if (fl->fl_lmops->fl_release_private)
			fl->fl_lmops->fl_release_private(fl);
		fl->fl_lmops = NULL;
	}

}

L
Linus Torvalds 已提交
168
/* Free a lock which is not in use. */
169
static void locks_free_lock(struct file_lock *fl)
L
Linus Torvalds 已提交
170
{
M
Miklos Szeredi 已提交
171 172 173
	BUG_ON(waitqueue_active(&fl->fl_wait));
	BUG_ON(!list_empty(&fl->fl_block));
	BUG_ON(!list_empty(&fl->fl_link));
L
Linus Torvalds 已提交
174

175
	locks_release_private(fl);
L
Linus Torvalds 已提交
176 177 178 179 180 181 182 183 184 185 186 187
	kmem_cache_free(filelock_cache, fl);
}

void locks_init_lock(struct file_lock *fl)
{
	INIT_LIST_HEAD(&fl->fl_link);
	INIT_LIST_HEAD(&fl->fl_block);
	init_waitqueue_head(&fl->fl_wait);
	fl->fl_next = NULL;
	fl->fl_fasync = NULL;
	fl->fl_owner = NULL;
	fl->fl_pid = 0;
188
	fl->fl_nspid = NULL;
L
Linus Torvalds 已提交
189 190 191 192 193 194 195 196 197 198 199 200 201 202
	fl->fl_file = NULL;
	fl->fl_flags = 0;
	fl->fl_type = 0;
	fl->fl_start = fl->fl_end = 0;
	fl->fl_ops = NULL;
	fl->fl_lmops = NULL;
}

EXPORT_SYMBOL(locks_init_lock);

/*
 * Initialises the fields of the file lock which are invariant for
 * free file_locks.
 */
203
static void init_once(struct kmem_cache *cache, void *foo)
L
Linus Torvalds 已提交
204 205 206 207 208 209
{
	struct file_lock *lock = (struct file_lock *) foo;

	locks_init_lock(lock);
}

210 211 212 213 214 215 216 217 218 219 220 221 222 223
static void locks_copy_private(struct file_lock *new, struct file_lock *fl)
{
	if (fl->fl_ops) {
		if (fl->fl_ops->fl_copy_lock)
			fl->fl_ops->fl_copy_lock(new, fl);
		new->fl_ops = fl->fl_ops;
	}
	if (fl->fl_lmops) {
		if (fl->fl_lmops->fl_copy_lock)
			fl->fl_lmops->fl_copy_lock(new, fl);
		new->fl_lmops = fl->fl_lmops;
	}
}

L
Linus Torvalds 已提交
224 225 226
/*
 * Initialize a new lock from an existing file_lock structure.
 */
227
void __locks_copy_lock(struct file_lock *new, const struct file_lock *fl)
L
Linus Torvalds 已提交
228 229 230
{
	new->fl_owner = fl->fl_owner;
	new->fl_pid = fl->fl_pid;
231
	new->fl_file = NULL;
L
Linus Torvalds 已提交
232 233 234 235
	new->fl_flags = fl->fl_flags;
	new->fl_type = fl->fl_type;
	new->fl_start = fl->fl_start;
	new->fl_end = fl->fl_end;
236 237 238
	new->fl_ops = NULL;
	new->fl_lmops = NULL;
}
239
EXPORT_SYMBOL(__locks_copy_lock);
240 241 242 243 244 245 246

void locks_copy_lock(struct file_lock *new, struct file_lock *fl)
{
	locks_release_private(new);

	__locks_copy_lock(new, fl);
	new->fl_file = fl->fl_file;
L
Linus Torvalds 已提交
247 248
	new->fl_ops = fl->fl_ops;
	new->fl_lmops = fl->fl_lmops;
249 250

	locks_copy_private(new, fl);
L
Linus Torvalds 已提交
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
}

EXPORT_SYMBOL(locks_copy_lock);

static inline int flock_translate_cmd(int cmd) {
	if (cmd & LOCK_MAND)
		return cmd & (LOCK_MAND | LOCK_RW);
	switch (cmd) {
	case LOCK_SH:
		return F_RDLCK;
	case LOCK_EX:
		return F_WRLCK;
	case LOCK_UN:
		return F_UNLCK;
	}
	return -EINVAL;
}

/* Fill in a file_lock structure with an appropriate FLOCK lock. */
static int flock_make_lock(struct file *filp, struct file_lock **lock,
		unsigned int cmd)
{
	struct file_lock *fl;
	int type = flock_translate_cmd(cmd);
	if (type < 0)
		return type;
	
	fl = locks_alloc_lock();
	if (fl == NULL)
		return -ENOMEM;

	fl->fl_file = filp;
	fl->fl_pid = current->tgid;
	fl->fl_flags = FL_FLOCK;
	fl->fl_type = type;
	fl->fl_end = OFFSET_MAX;
	
	*lock = fl;
	return 0;
}

static int assign_type(struct file_lock *fl, int type)
{
	switch (type) {
	case F_RDLCK:
	case F_WRLCK:
	case F_UNLCK:
		fl->fl_type = type;
		break;
	default:
		return -EINVAL;
	}
	return 0;
}

/* Verify a "struct flock" and copy it to a "struct file_lock" as a POSIX
 * style lock.
 */
static int flock_to_posix_lock(struct file *filp, struct file_lock *fl,
			       struct flock *l)
{
	off_t start, end;

	switch (l->l_whence) {
315
	case SEEK_SET:
L
Linus Torvalds 已提交
316 317
		start = 0;
		break;
318
	case SEEK_CUR:
L
Linus Torvalds 已提交
319 320
		start = filp->f_pos;
		break;
321
	case SEEK_END:
322
		start = i_size_read(filp->f_path.dentry->d_inode);
L
Linus Torvalds 已提交
323 324 325 326 327 328 329 330
		break;
	default:
		return -EINVAL;
	}

	/* POSIX-1996 leaves the case l->l_len < 0 undefined;
	   POSIX-2001 defines it. */
	start += l->l_start;
331 332 333 334 335 336 337
	if (start < 0)
		return -EINVAL;
	fl->fl_end = OFFSET_MAX;
	if (l->l_len > 0) {
		end = start + l->l_len - 1;
		fl->fl_end = end;
	} else if (l->l_len < 0) {
L
Linus Torvalds 已提交
338
		end = start - 1;
339
		fl->fl_end = end;
L
Linus Torvalds 已提交
340
		start += l->l_len;
341 342
		if (start < 0)
			return -EINVAL;
L
Linus Torvalds 已提交
343 344
	}
	fl->fl_start = start;	/* we record the absolute position */
345 346
	if (fl->fl_end < fl->fl_start)
		return -EOVERFLOW;
L
Linus Torvalds 已提交
347 348 349 350 351 352 353 354 355 356 357 358 359 360 361 362 363 364
	
	fl->fl_owner = current->files;
	fl->fl_pid = current->tgid;
	fl->fl_file = filp;
	fl->fl_flags = FL_POSIX;
	fl->fl_ops = NULL;
	fl->fl_lmops = NULL;

	return assign_type(fl, l->l_type);
}

#if BITS_PER_LONG == 32
static int flock64_to_posix_lock(struct file *filp, struct file_lock *fl,
				 struct flock64 *l)
{
	loff_t start;

	switch (l->l_whence) {
365
	case SEEK_SET:
L
Linus Torvalds 已提交
366 367
		start = 0;
		break;
368
	case SEEK_CUR:
L
Linus Torvalds 已提交
369 370
		start = filp->f_pos;
		break;
371
	case SEEK_END:
372
		start = i_size_read(filp->f_path.dentry->d_inode);
L
Linus Torvalds 已提交
373 374 375 376 377
		break;
	default:
		return -EINVAL;
	}

378 379
	start += l->l_start;
	if (start < 0)
L
Linus Torvalds 已提交
380
		return -EINVAL;
381 382 383 384 385 386 387 388 389
	fl->fl_end = OFFSET_MAX;
	if (l->l_len > 0) {
		fl->fl_end = start + l->l_len - 1;
	} else if (l->l_len < 0) {
		fl->fl_end = start - 1;
		start += l->l_len;
		if (start < 0)
			return -EINVAL;
	}
L
Linus Torvalds 已提交
390
	fl->fl_start = start;	/* we record the absolute position */
391 392
	if (fl->fl_end < fl->fl_start)
		return -EOVERFLOW;
L
Linus Torvalds 已提交
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
	
	fl->fl_owner = current->files;
	fl->fl_pid = current->tgid;
	fl->fl_file = filp;
	fl->fl_flags = FL_POSIX;
	fl->fl_ops = NULL;
	fl->fl_lmops = NULL;

	switch (l->l_type) {
	case F_RDLCK:
	case F_WRLCK:
	case F_UNLCK:
		fl->fl_type = l->l_type;
		break;
	default:
		return -EINVAL;
	}

	return (0);
}
#endif

/* default lease lock manager operations */
static void lease_break_callback(struct file_lock *fl)
{
	kill_fasync(&fl->fl_fasync, SIGIO, POLL_MSG);
}

static void lease_release_private_callback(struct file_lock *fl)
{
	if (!fl->fl_file)
		return;

	f_delown(fl->fl_file);
	fl->fl_file->f_owner.signum = 0;
}

A
Adrian Bunk 已提交
430
static int lease_mylease_callback(struct file_lock *fl, struct file_lock *try)
L
Linus Torvalds 已提交
431 432 433 434
{
	return fl->fl_file == try->fl_file;
}

A
Adrian Bunk 已提交
435
static struct lock_manager_operations lease_manager_ops = {
L
Linus Torvalds 已提交
436 437 438 439 440 441 442 443 444 445 446
	.fl_break = lease_break_callback,
	.fl_release_private = lease_release_private_callback,
	.fl_mylease = lease_mylease_callback,
	.fl_change = lease_modify,
};

/*
 * Initialize a lease, use the default lock manager operations
 */
static int lease_init(struct file *filp, int type, struct file_lock *fl)
 {
447 448 449
	if (assign_type(fl, type) != 0)
		return -EINVAL;

L
Linus Torvalds 已提交
450 451 452 453 454 455 456 457 458 459 460 461 462
	fl->fl_owner = current->files;
	fl->fl_pid = current->tgid;

	fl->fl_file = filp;
	fl->fl_flags = FL_LEASE;
	fl->fl_start = 0;
	fl->fl_end = OFFSET_MAX;
	fl->fl_ops = NULL;
	fl->fl_lmops = &lease_manager_ops;
	return 0;
}

/* Allocate a file_lock initialised to this type of lease */
J
J. Bruce Fields 已提交
463
static struct file_lock *lease_alloc(struct file *filp, int type)
L
Linus Torvalds 已提交
464 465
{
	struct file_lock *fl = locks_alloc_lock();
466
	int error = -ENOMEM;
L
Linus Torvalds 已提交
467 468

	if (fl == NULL)
J
J. Bruce Fields 已提交
469
		return ERR_PTR(error);
L
Linus Torvalds 已提交
470 471

	error = lease_init(filp, type, fl);
472 473
	if (error) {
		locks_free_lock(fl);
J
J. Bruce Fields 已提交
474
		return ERR_PTR(error);
475
	}
J
J. Bruce Fields 已提交
476
	return fl;
L
Linus Torvalds 已提交
477 478 479 480 481 482 483 484 485 486 487 488 489
}

/* Check if two locks overlap each other.
 */
static inline int locks_overlap(struct file_lock *fl1, struct file_lock *fl2)
{
	return ((fl1->fl_end >= fl2->fl_start) &&
		(fl2->fl_end >= fl1->fl_start));
}

/*
 * Check whether two locks have the same owner.
 */
490
static int posix_same_owner(struct file_lock *fl1, struct file_lock *fl2)
L
Linus Torvalds 已提交
491 492 493 494 495 496 497 498 499 500
{
	if (fl1->fl_lmops && fl1->fl_lmops->fl_compare_owner)
		return fl2->fl_lmops == fl1->fl_lmops &&
			fl1->fl_lmops->fl_compare_owner(fl1, fl2);
	return fl1->fl_owner == fl2->fl_owner;
}

/* Remove waiter from blocker's block list.
 * When blocker ends up pointing to itself then the list is empty.
 */
501
static void __locks_delete_block(struct file_lock *waiter)
L
Linus Torvalds 已提交
502 503 504 505 506 507 508 509 510 511 512 513 514 515 516 517 518 519 520 521 522 523 524
{
	list_del_init(&waiter->fl_block);
	list_del_init(&waiter->fl_link);
	waiter->fl_next = NULL;
}

/*
 */
static void locks_delete_block(struct file_lock *waiter)
{
	lock_kernel();
	__locks_delete_block(waiter);
	unlock_kernel();
}

/* Insert waiter into blocker's block list.
 * We use a circular list so that processes can be easily woken up in
 * the order they blocked. The documentation doesn't require this but
 * it seems like the reasonable thing to do.
 */
static void locks_insert_block(struct file_lock *blocker, 
			       struct file_lock *waiter)
{
525
	BUG_ON(!list_empty(&waiter->fl_block));
L
Linus Torvalds 已提交
526 527 528 529 530 531 532 533 534 535 536 537 538
	list_add_tail(&waiter->fl_block, &blocker->fl_block);
	waiter->fl_next = blocker;
	if (IS_POSIX(blocker))
		list_add(&waiter->fl_link, &blocked_list);
}

/* Wake up processes blocked waiting for blocker.
 * If told to wait then schedule the processes until the block list
 * is empty, otherwise empty the block list ourselves.
 */
static void locks_wake_up_blocks(struct file_lock *blocker)
{
	while (!list_empty(&blocker->fl_block)) {
539 540 541
		struct file_lock *waiter;

		waiter = list_first_entry(&blocker->fl_block,
L
Linus Torvalds 已提交
542 543 544 545 546 547 548 549 550 551 552 553 554 555 556 557
				struct file_lock, fl_block);
		__locks_delete_block(waiter);
		if (waiter->fl_lmops && waiter->fl_lmops->fl_notify)
			waiter->fl_lmops->fl_notify(waiter);
		else
			wake_up(&waiter->fl_wait);
	}
}

/* Insert file lock fl into an inode's lock list at the position indicated
 * by pos. At the same time add the lock to the global file lock list.
 */
static void locks_insert_lock(struct file_lock **pos, struct file_lock *fl)
{
	list_add(&fl->fl_link, &file_lock_list);

558 559
	fl->fl_nspid = get_pid(task_tgid(current));

L
Linus Torvalds 已提交
560 561 562 563 564 565 566 567 568 569 570 571 572 573 574 575 576 577 578 579 580 581 582 583 584 585 586 587 588 589 590
	/* insert into file's list */
	fl->fl_next = *pos;
	*pos = fl;

	if (fl->fl_ops && fl->fl_ops->fl_insert)
		fl->fl_ops->fl_insert(fl);
}

/*
 * Delete a lock and then free it.
 * Wake up processes that are blocked waiting for this lock,
 * notify the FS that the lock has been cleared and
 * finally free the lock.
 */
static void locks_delete_lock(struct file_lock **thisfl_p)
{
	struct file_lock *fl = *thisfl_p;

	*thisfl_p = fl->fl_next;
	fl->fl_next = NULL;
	list_del_init(&fl->fl_link);

	fasync_helper(0, fl->fl_file, 0, &fl->fl_fasync);
	if (fl->fl_fasync != NULL) {
		printk(KERN_ERR "locks_delete_lock: fasync == %p\n", fl->fl_fasync);
		fl->fl_fasync = NULL;
	}

	if (fl->fl_ops && fl->fl_ops->fl_remove)
		fl->fl_ops->fl_remove(fl);

591 592 593 594 595
	if (fl->fl_nspid) {
		put_pid(fl->fl_nspid);
		fl->fl_nspid = NULL;
	}

L
Linus Torvalds 已提交
596 597 598 599 600 601 602 603 604 605 606 607 608 609 610 611 612 613 614 615 616 617 618 619 620 621 622 623 624 625 626 627 628 629 630 631 632 633 634 635 636 637 638 639 640 641 642 643 644 645
	locks_wake_up_blocks(fl);
	locks_free_lock(fl);
}

/* Determine if lock sys_fl blocks lock caller_fl. Common functionality
 * checks for shared/exclusive status of overlapping locks.
 */
static int locks_conflict(struct file_lock *caller_fl, struct file_lock *sys_fl)
{
	if (sys_fl->fl_type == F_WRLCK)
		return 1;
	if (caller_fl->fl_type == F_WRLCK)
		return 1;
	return 0;
}

/* Determine if lock sys_fl blocks lock caller_fl. POSIX specific
 * checking before calling the locks_conflict().
 */
static int posix_locks_conflict(struct file_lock *caller_fl, struct file_lock *sys_fl)
{
	/* POSIX locks owned by the same process do not conflict with
	 * each other.
	 */
	if (!IS_POSIX(sys_fl) || posix_same_owner(caller_fl, sys_fl))
		return (0);

	/* Check whether they overlap */
	if (!locks_overlap(caller_fl, sys_fl))
		return 0;

	return (locks_conflict(caller_fl, sys_fl));
}

/* Determine if lock sys_fl blocks lock caller_fl. FLOCK specific
 * checking before calling the locks_conflict().
 */
static int flock_locks_conflict(struct file_lock *caller_fl, struct file_lock *sys_fl)
{
	/* FLOCK locks referring to the same filp do not conflict with
	 * each other.
	 */
	if (!IS_FLOCK(sys_fl) || (caller_fl->fl_file == sys_fl->fl_file))
		return (0);
	if ((caller_fl->fl_type & LOCK_MAND) || (sys_fl->fl_type & LOCK_MAND))
		return 0;

	return (locks_conflict(caller_fl, sys_fl));
}

646
void
647
posix_test_lock(struct file *filp, struct file_lock *fl)
L
Linus Torvalds 已提交
648 649 650 651
{
	struct file_lock *cfl;

	lock_kernel();
652
	for (cfl = filp->f_path.dentry->d_inode->i_flock; cfl; cfl = cfl->fl_next) {
L
Linus Torvalds 已提交
653 654
		if (!IS_POSIX(cfl))
			continue;
655
		if (posix_locks_conflict(fl, cfl))
L
Linus Torvalds 已提交
656 657
			break;
	}
658
	if (cfl) {
659
		__locks_copy_lock(fl, cfl);
660
		if (cfl->fl_nspid)
661
			fl->fl_pid = pid_vnr(cfl->fl_nspid);
662
	} else
663
		fl->fl_type = F_UNLCK;
L
Linus Torvalds 已提交
664
	unlock_kernel();
665
	return;
L
Linus Torvalds 已提交
666 667 668
}
EXPORT_SYMBOL(posix_test_lock);

669 670 671 672 673
/*
 * Deadlock detection:
 *
 * We attempt to detect deadlocks that are due purely to posix file
 * locks.
L
Linus Torvalds 已提交
674
 *
675 676 677 678 679 680 681
 * We assume that a task can be waiting for at most one lock at a time.
 * So for any acquired lock, the process holding that lock may be
 * waiting on at most one other lock.  That lock in turns may be held by
 * someone waiting for at most one other lock.  Given a requested lock
 * caller_fl which is about to wait for a conflicting lock block_fl, we
 * follow this chain of waiters to ensure we are not about to create a
 * cycle.
L
Linus Torvalds 已提交
682
 *
683 684 685
 * Since we do this before we ever put a process to sleep on a lock, we
 * are ensured that there is never a cycle; that is what guarantees that
 * the while() loop in posix_locks_deadlock() eventually completes.
686
 *
687 688 689 690 691
 * Note: the above assumption may not be true when handling lock
 * requests from a broken NFS client. It may also fail in the presence
 * of tasks (such as posix threads) sharing the same open file table.
 *
 * To handle those cases, we just bail out after a few iterations.
L
Linus Torvalds 已提交
692
 */
693 694 695

#define MAX_DEADLK_ITERATIONS 10

696 697 698 699 700 701 702 703 704 705 706 707
/* Find a lock that the owner of the given block_fl is blocking on. */
static struct file_lock *what_owner_is_waiting_for(struct file_lock *block_fl)
{
	struct file_lock *fl;

	list_for_each_entry(fl, &blocked_list, fl_link) {
		if (posix_same_owner(fl, block_fl))
			return fl->fl_next;
	}
	return NULL;
}

708
static int posix_locks_deadlock(struct file_lock *caller_fl,
L
Linus Torvalds 已提交
709 710
				struct file_lock *block_fl)
{
711
	int i = 0;
L
Linus Torvalds 已提交
712

713 714 715 716 717
	while ((block_fl = what_owner_is_waiting_for(block_fl))) {
		if (i++ > MAX_DEADLK_ITERATIONS)
			return 0;
		if (posix_same_owner(caller_fl, block_fl))
			return 1;
L
Linus Torvalds 已提交
718 719 720 721 722
	}
	return 0;
}

/* Try to create a FLOCK lock on filp. We always insert new FLOCK locks
723
 * after any leases, but before any posix locks.
724 725 726 727
 *
 * Note that if called with an FL_EXISTS argument, the caller may determine
 * whether or not a lock was successfully freed by testing the return
 * value for -ENOENT.
L
Linus Torvalds 已提交
728
 */
729
static int flock_lock_file(struct file *filp, struct file_lock *request)
L
Linus Torvalds 已提交
730
{
731
	struct file_lock *new_fl = NULL;
L
Linus Torvalds 已提交
732
	struct file_lock **before;
733
	struct inode * inode = filp->f_path.dentry->d_inode;
L
Linus Torvalds 已提交
734 735 736 737
	int error = 0;
	int found = 0;

	lock_kernel();
738 739
	if (request->fl_flags & FL_ACCESS)
		goto find_conflict;
740 741 742 743 744 745 746 747 748

	if (request->fl_type != F_UNLCK) {
		error = -ENOMEM;
		new_fl = locks_alloc_lock();
		if (new_fl == NULL)
			goto out;
		error = 0;
	}

L
Linus Torvalds 已提交
749 750 751 752 753 754 755 756
	for_each_lock(inode, before) {
		struct file_lock *fl = *before;
		if (IS_POSIX(fl))
			break;
		if (IS_LEASE(fl))
			continue;
		if (filp != fl->fl_file)
			continue;
757
		if (request->fl_type == fl->fl_type)
L
Linus Torvalds 已提交
758 759 760 761 762 763
			goto out;
		found = 1;
		locks_delete_lock(before);
		break;
	}

764 765 766
	if (request->fl_type == F_UNLCK) {
		if ((request->fl_flags & FL_EXISTS) && !found)
			error = -ENOENT;
767
		goto out;
768
	}
L
Linus Torvalds 已提交
769 770 771 772 773 774 775 776

	/*
	 * If a higher-priority process was blocked on the old file lock,
	 * give it the opportunity to lock the file.
	 */
	if (found)
		cond_resched();

777
find_conflict:
L
Linus Torvalds 已提交
778 779 780 781 782 783
	for_each_lock(inode, before) {
		struct file_lock *fl = *before;
		if (IS_POSIX(fl))
			break;
		if (IS_LEASE(fl))
			continue;
784
		if (!flock_locks_conflict(request, fl))
L
Linus Torvalds 已提交
785 786
			continue;
		error = -EAGAIN;
787 788
		if (request->fl_flags & FL_SLEEP)
			locks_insert_block(fl, request);
L
Linus Torvalds 已提交
789 790
		goto out;
	}
791 792
	if (request->fl_flags & FL_ACCESS)
		goto out;
793
	locks_copy_lock(new_fl, request);
P
Pavel Emelyanov 已提交
794
	locks_insert_lock(before, new_fl);
795
	new_fl = NULL;
796
	error = 0;
L
Linus Torvalds 已提交
797 798 799

out:
	unlock_kernel();
800 801
	if (new_fl)
		locks_free_lock(new_fl);
L
Linus Torvalds 已提交
802 803 804
	return error;
}

805
static int __posix_lock_file(struct inode *inode, struct file_lock *request, struct file_lock *conflock)
L
Linus Torvalds 已提交
806 807
{
	struct file_lock *fl;
808 809
	struct file_lock *new_fl = NULL;
	struct file_lock *new_fl2 = NULL;
L
Linus Torvalds 已提交
810 811 812 813 814 815 816 817
	struct file_lock *left = NULL;
	struct file_lock *right = NULL;
	struct file_lock **before;
	int error, added = 0;

	/*
	 * We may need two file_lock structures for this operation,
	 * so we get them in advance to avoid races.
818 819
	 *
	 * In some cases we can be sure, that no new locks will be needed
L
Linus Torvalds 已提交
820
	 */
821 822 823 824 825 826
	if (!(request->fl_flags & FL_ACCESS) &&
	    (request->fl_type != F_UNLCK ||
	     request->fl_start != 0 || request->fl_end != OFFSET_MAX)) {
		new_fl = locks_alloc_lock();
		new_fl2 = locks_alloc_lock();
	}
L
Linus Torvalds 已提交
827 828 829 830

	lock_kernel();
	if (request->fl_type != F_UNLCK) {
		for_each_lock(inode, before) {
831
			fl = *before;
L
Linus Torvalds 已提交
832 833 834 835
			if (!IS_POSIX(fl))
				continue;
			if (!posix_locks_conflict(request, fl))
				continue;
836
			if (conflock)
837
				__locks_copy_lock(conflock, fl);
L
Linus Torvalds 已提交
838 839 840 841 842 843 844 845 846 847 848 849 850 851 852 853 854 855 856 857 858 859 860 861 862 863 864 865 866 867 868 869 870 871
			error = -EAGAIN;
			if (!(request->fl_flags & FL_SLEEP))
				goto out;
			error = -EDEADLK;
			if (posix_locks_deadlock(request, fl))
				goto out;
			error = -EAGAIN;
			locks_insert_block(fl, request);
			goto out;
  		}
  	}

	/* If we're just looking for a conflict, we're done. */
	error = 0;
	if (request->fl_flags & FL_ACCESS)
		goto out;

	/*
	 * Find the first old lock with the same owner as the new lock.
	 */
	
	before = &inode->i_flock;

	/* First skip locks owned by other processes.  */
	while ((fl = *before) && (!IS_POSIX(fl) ||
				  !posix_same_owner(request, fl))) {
		before = &fl->fl_next;
	}

	/* Process locks with this owner.  */
	while ((fl = *before) && posix_same_owner(request, fl)) {
		/* Detect adjacent or overlapping regions (if same lock type)
		 */
		if (request->fl_type == fl->fl_type) {
O
Olaf Kirch 已提交
872 873 874 875
			/* In all comparisons of start vs end, use
			 * "start - 1" rather than "end + 1". If end
			 * is OFFSET_MAX, end + 1 will become negative.
			 */
L
Linus Torvalds 已提交
876 877 878 879 880
			if (fl->fl_end < request->fl_start - 1)
				goto next_lock;
			/* If the next lock in the list has entirely bigger
			 * addresses than the new one, insert the lock here.
			 */
O
Olaf Kirch 已提交
881
			if (fl->fl_start - 1 > request->fl_end)
L
Linus Torvalds 已提交
882 883 884 885 886 887 888 889 890 891 892 893 894 895 896 897 898 899 900 901 902 903 904 905 906 907 908 909 910 911 912 913 914 915 916 917 918 919 920 921 922 923 924 925 926 927 928 929 930 931 932 933 934 935 936 937 938 939
				break;

			/* If we come here, the new and old lock are of the
			 * same type and adjacent or overlapping. Make one
			 * lock yielding from the lower start address of both
			 * locks to the higher end address.
			 */
			if (fl->fl_start > request->fl_start)
				fl->fl_start = request->fl_start;
			else
				request->fl_start = fl->fl_start;
			if (fl->fl_end < request->fl_end)
				fl->fl_end = request->fl_end;
			else
				request->fl_end = fl->fl_end;
			if (added) {
				locks_delete_lock(before);
				continue;
			}
			request = fl;
			added = 1;
		}
		else {
			/* Processing for different lock types is a bit
			 * more complex.
			 */
			if (fl->fl_end < request->fl_start)
				goto next_lock;
			if (fl->fl_start > request->fl_end)
				break;
			if (request->fl_type == F_UNLCK)
				added = 1;
			if (fl->fl_start < request->fl_start)
				left = fl;
			/* If the next lock in the list has a higher end
			 * address than the new one, insert the new one here.
			 */
			if (fl->fl_end > request->fl_end) {
				right = fl;
				break;
			}
			if (fl->fl_start >= request->fl_start) {
				/* The new lock completely replaces an old
				 * one (This may happen several times).
				 */
				if (added) {
					locks_delete_lock(before);
					continue;
				}
				/* Replace the old lock with the new one.
				 * Wake up anybody waiting for the old one,
				 * as the change in lock type might satisfy
				 * their needs.
				 */
				locks_wake_up_blocks(fl);
				fl->fl_start = request->fl_start;
				fl->fl_end = request->fl_end;
				fl->fl_type = request->fl_type;
940 941
				locks_release_private(fl);
				locks_copy_private(fl, request);
L
Linus Torvalds 已提交
942 943 944 945 946 947 948 949 950 951
				request = fl;
				added = 1;
			}
		}
		/* Go on to next lock.
		 */
	next_lock:
		before = &fl->fl_next;
	}

952 953 954 955 956 957 958 959 960 961
	/*
	 * The above code only modifies existing locks in case of
	 * merging or replacing.  If new lock(s) need to be inserted
	 * all modifications are done bellow this, so it's safe yet to
	 * bail out.
	 */
	error = -ENOLCK; /* "no luck" */
	if (right && left == right && !new_fl2)
		goto out;

L
Linus Torvalds 已提交
962 963
	error = 0;
	if (!added) {
964 965 966
		if (request->fl_type == F_UNLCK) {
			if (request->fl_flags & FL_EXISTS)
				error = -ENOENT;
L
Linus Torvalds 已提交
967
			goto out;
968
		}
969 970 971 972 973

		if (!new_fl) {
			error = -ENOLCK;
			goto out;
		}
L
Linus Torvalds 已提交
974 975 976 977 978 979 980 981 982 983 984 985 986 987 988 989 990 991 992 993 994 995 996 997 998 999 1000 1001 1002 1003 1004 1005 1006 1007 1008 1009 1010
		locks_copy_lock(new_fl, request);
		locks_insert_lock(before, new_fl);
		new_fl = NULL;
	}
	if (right) {
		if (left == right) {
			/* The new lock breaks the old one in two pieces,
			 * so we have to use the second new lock.
			 */
			left = new_fl2;
			new_fl2 = NULL;
			locks_copy_lock(left, right);
			locks_insert_lock(before, left);
		}
		right->fl_start = request->fl_end + 1;
		locks_wake_up_blocks(right);
	}
	if (left) {
		left->fl_end = request->fl_start - 1;
		locks_wake_up_blocks(left);
	}
 out:
	unlock_kernel();
	/*
	 * Free any unused locks.
	 */
	if (new_fl)
		locks_free_lock(new_fl);
	if (new_fl2)
		locks_free_lock(new_fl2);
	return error;
}

/**
 * posix_lock_file - Apply a POSIX-style lock to a file
 * @filp: The file to apply the lock to
 * @fl: The lock to be applied
1011
 * @conflock: Place to return a copy of the conflicting lock, if found.
L
Linus Torvalds 已提交
1012 1013 1014 1015
 *
 * Add a POSIX style lock to a file.
 * We merge adjacent & overlapping locks whenever possible.
 * POSIX locks are sorted by owner task, then by starting address
1016 1017 1018 1019
 *
 * Note that if called with an FL_EXISTS argument, the caller may determine
 * whether or not a lock was successfully freed by testing the return
 * value for -ENOENT.
L
Linus Torvalds 已提交
1020
 */
1021
int posix_lock_file(struct file *filp, struct file_lock *fl,
1022 1023
			struct file_lock *conflock)
{
1024
	return __posix_lock_file(filp->f_path.dentry->d_inode, fl, conflock);
L
Linus Torvalds 已提交
1025
}
1026
EXPORT_SYMBOL(posix_lock_file);
L
Linus Torvalds 已提交
1027 1028 1029 1030 1031 1032 1033 1034 1035 1036 1037 1038 1039 1040 1041

/**
 * posix_lock_file_wait - Apply a POSIX-style lock to a file
 * @filp: The file to apply the lock to
 * @fl: The lock to be applied
 *
 * Add a POSIX style lock to a file.
 * We merge adjacent & overlapping locks whenever possible.
 * POSIX locks are sorted by owner task, then by starting address
 */
int posix_lock_file_wait(struct file *filp, struct file_lock *fl)
{
	int error;
	might_sleep ();
	for (;;) {
1042
		error = posix_lock_file(filp, fl, NULL);
L
Linus Torvalds 已提交
1043 1044 1045 1046 1047 1048 1049 1050 1051 1052 1053 1054 1055 1056 1057 1058 1059 1060 1061 1062 1063 1064 1065 1066 1067 1068 1069 1070 1071 1072 1073 1074 1075 1076 1077 1078 1079 1080 1081 1082 1083 1084 1085 1086 1087 1088 1089 1090 1091 1092 1093 1094 1095 1096 1097 1098 1099 1100 1101 1102 1103 1104 1105 1106 1107 1108 1109 1110 1111 1112 1113
		if ((error != -EAGAIN) || !(fl->fl_flags & FL_SLEEP))
			break;
		error = wait_event_interruptible(fl->fl_wait, !fl->fl_next);
		if (!error)
			continue;

		locks_delete_block(fl);
		break;
	}
	return error;
}
EXPORT_SYMBOL(posix_lock_file_wait);

/**
 * locks_mandatory_locked - Check for an active lock
 * @inode: the file to check
 *
 * Searches the inode's list of locks to find any POSIX locks which conflict.
 * This function is called from locks_verify_locked() only.
 */
int locks_mandatory_locked(struct inode *inode)
{
	fl_owner_t owner = current->files;
	struct file_lock *fl;

	/*
	 * Search the lock list for this inode for any POSIX locks.
	 */
	lock_kernel();
	for (fl = inode->i_flock; fl != NULL; fl = fl->fl_next) {
		if (!IS_POSIX(fl))
			continue;
		if (fl->fl_owner != owner)
			break;
	}
	unlock_kernel();
	return fl ? -EAGAIN : 0;
}

/**
 * locks_mandatory_area - Check for a conflicting lock
 * @read_write: %FLOCK_VERIFY_WRITE for exclusive access, %FLOCK_VERIFY_READ
 *		for shared
 * @inode:      the file to check
 * @filp:       how the file was opened (if it was)
 * @offset:     start of area to check
 * @count:      length of area to check
 *
 * Searches the inode's list of locks to find any POSIX locks which conflict.
 * This function is called from rw_verify_area() and
 * locks_verify_truncate().
 */
int locks_mandatory_area(int read_write, struct inode *inode,
			 struct file *filp, loff_t offset,
			 size_t count)
{
	struct file_lock fl;
	int error;

	locks_init_lock(&fl);
	fl.fl_owner = current->files;
	fl.fl_pid = current->tgid;
	fl.fl_file = filp;
	fl.fl_flags = FL_POSIX | FL_ACCESS;
	if (filp && !(filp->f_flags & O_NONBLOCK))
		fl.fl_flags |= FL_SLEEP;
	fl.fl_type = (read_write == FLOCK_VERIFY_WRITE) ? F_WRLCK : F_RDLCK;
	fl.fl_start = offset;
	fl.fl_end = offset + count - 1;

	for (;;) {
1114
		error = __posix_lock_file(inode, &fl, NULL);
L
Linus Torvalds 已提交
1115 1116 1117 1118 1119 1120 1121 1122 1123 1124
		if (error != -EAGAIN)
			break;
		if (!(fl.fl_flags & FL_SLEEP))
			break;
		error = wait_event_interruptible(fl.fl_wait, !fl.fl_next);
		if (!error) {
			/*
			 * If we've been sleeping someone might have
			 * changed the permissions behind our back.
			 */
1125
			if (__mandatory_lock(inode))
L
Linus Torvalds 已提交
1126 1127 1128 1129 1130 1131 1132 1133 1134 1135 1136 1137 1138 1139 1140 1141 1142 1143 1144 1145 1146 1147 1148 1149 1150 1151 1152 1153 1154 1155 1156 1157 1158 1159 1160 1161 1162 1163 1164 1165 1166 1167 1168 1169 1170 1171 1172 1173 1174 1175 1176
				continue;
		}

		locks_delete_block(&fl);
		break;
	}

	return error;
}

EXPORT_SYMBOL(locks_mandatory_area);

/* We already had a lease on this file; just change its type */
int lease_modify(struct file_lock **before, int arg)
{
	struct file_lock *fl = *before;
	int error = assign_type(fl, arg);

	if (error)
		return error;
	locks_wake_up_blocks(fl);
	if (arg == F_UNLCK)
		locks_delete_lock(before);
	return 0;
}

EXPORT_SYMBOL(lease_modify);

static void time_out_leases(struct inode *inode)
{
	struct file_lock **before;
	struct file_lock *fl;

	before = &inode->i_flock;
	while ((fl = *before) && IS_LEASE(fl) && (fl->fl_type & F_INPROGRESS)) {
		if ((fl->fl_break_time == 0)
				|| time_before(jiffies, fl->fl_break_time)) {
			before = &fl->fl_next;
			continue;
		}
		lease_modify(before, fl->fl_type & ~F_INPROGRESS);
		if (fl == *before)	/* lease_modify may have freed fl */
			before = &fl->fl_next;
	}
}

/**
 *	__break_lease	-	revoke all outstanding leases on file
 *	@inode: the inode of the file to return
 *	@mode: the open mode (read or write)
 *
1177 1178 1179
 *	break_lease (inlined for speed) has checked there already is at least
 *	some kind of lock (maybe a lease) on this file.  Leases are broken on
 *	a call to open() or truncate().  This function can sleep unless you
L
Linus Torvalds 已提交
1180 1181 1182 1183 1184 1185 1186 1187 1188 1189
 *	specified %O_NONBLOCK to your open().
 */
int __break_lease(struct inode *inode, unsigned int mode)
{
	int error = 0, future;
	struct file_lock *new_fl, *flock;
	struct file_lock *fl;
	unsigned long break_time;
	int i_have_this_lease = 0;

J
J. Bruce Fields 已提交
1190
	new_fl = lease_alloc(NULL, mode & FMODE_WRITE ? F_WRLCK : F_RDLCK);
L
Linus Torvalds 已提交
1191 1192 1193 1194 1195 1196 1197 1198 1199 1200 1201 1202 1203 1204 1205 1206 1207 1208 1209 1210 1211 1212 1213 1214 1215 1216 1217

	lock_kernel();

	time_out_leases(inode);

	flock = inode->i_flock;
	if ((flock == NULL) || !IS_LEASE(flock))
		goto out;

	for (fl = flock; fl && IS_LEASE(fl); fl = fl->fl_next)
		if (fl->fl_owner == current->files)
			i_have_this_lease = 1;

	if (mode & FMODE_WRITE) {
		/* If we want write access, we have to revoke any lease. */
		future = F_UNLCK | F_INPROGRESS;
	} else if (flock->fl_type & F_INPROGRESS) {
		/* If the lease is already being broken, we just leave it */
		future = flock->fl_type;
	} else if (flock->fl_type & F_WRLCK) {
		/* Downgrade the exclusive lease to a read-only lease. */
		future = F_RDLCK | F_INPROGRESS;
	} else {
		/* the existing lease was read-only, so we can read too. */
		goto out;
	}

J
J. Bruce Fields 已提交
1218 1219 1220
	if (IS_ERR(new_fl) && !i_have_this_lease
			&& ((mode & O_NONBLOCK) == 0)) {
		error = PTR_ERR(new_fl);
L
Linus Torvalds 已提交
1221 1222 1223 1224 1225 1226 1227 1228 1229 1230 1231 1232 1233 1234 1235 1236 1237 1238 1239 1240 1241 1242 1243 1244 1245 1246 1247 1248 1249 1250 1251
		goto out;
	}

	break_time = 0;
	if (lease_break_time > 0) {
		break_time = jiffies + lease_break_time * HZ;
		if (break_time == 0)
			break_time++;	/* so that 0 means no break time */
	}

	for (fl = flock; fl && IS_LEASE(fl); fl = fl->fl_next) {
		if (fl->fl_type != future) {
			fl->fl_type = future;
			fl->fl_break_time = break_time;
			/* lease must have lmops break callback */
			fl->fl_lmops->fl_break(fl);
		}
	}

	if (i_have_this_lease || (mode & O_NONBLOCK)) {
		error = -EWOULDBLOCK;
		goto out;
	}

restart:
	break_time = flock->fl_break_time;
	if (break_time != 0) {
		break_time -= jiffies;
		if (break_time == 0)
			break_time++;
	}
1252 1253 1254 1255
	locks_insert_block(flock, new_fl);
	error = wait_event_interruptible_timeout(new_fl->fl_wait,
						!new_fl->fl_next, break_time);
	__locks_delete_block(new_fl);
L
Linus Torvalds 已提交
1256 1257 1258 1259 1260 1261 1262 1263 1264 1265 1266 1267 1268 1269
	if (error >= 0) {
		if (error == 0)
			time_out_leases(inode);
		/* Wait for the next lease that has not been broken yet */
		for (flock = inode->i_flock; flock && IS_LEASE(flock);
				flock = flock->fl_next) {
			if (flock->fl_type & F_INPROGRESS)
				goto restart;
		}
		error = 0;
	}

out:
	unlock_kernel();
J
J. Bruce Fields 已提交
1270
	if (!IS_ERR(new_fl))
L
Linus Torvalds 已提交
1271 1272 1273 1274 1275 1276 1277
		locks_free_lock(new_fl);
	return error;
}

EXPORT_SYMBOL(__break_lease);

/**
1278
 *	lease_get_mtime - get the last modified time of an inode
L
Linus Torvalds 已提交
1279 1280 1281 1282 1283
 *	@inode: the inode
 *      @time:  pointer to a timespec which will contain the last modified time
 *
 * This is to force NFS clients to flush their caches for files with
 * exclusive leases.  The justification is that if someone has an
1284
 * exclusive lease, then they could be modifying it.
L
Linus Torvalds 已提交
1285 1286 1287 1288 1289 1290 1291 1292 1293 1294 1295 1296 1297 1298 1299 1300 1301 1302 1303 1304 1305 1306 1307 1308 1309 1310 1311 1312 1313 1314 1315 1316 1317 1318 1319 1320 1321 1322 1323 1324 1325
 */
void lease_get_mtime(struct inode *inode, struct timespec *time)
{
	struct file_lock *flock = inode->i_flock;
	if (flock && IS_LEASE(flock) && (flock->fl_type & F_WRLCK))
		*time = current_fs_time(inode->i_sb);
	else
		*time = inode->i_mtime;
}

EXPORT_SYMBOL(lease_get_mtime);

/**
 *	fcntl_getlease - Enquire what lease is currently active
 *	@filp: the file
 *
 *	The value returned by this function will be one of
 *	(if no lease break is pending):
 *
 *	%F_RDLCK to indicate a shared lease is held.
 *
 *	%F_WRLCK to indicate an exclusive lease is held.
 *
 *	%F_UNLCK to indicate no lease is held.
 *
 *	(if a lease break is pending):
 *
 *	%F_RDLCK to indicate an exclusive lease needs to be
 *		changed to a shared lease (or removed).
 *
 *	%F_UNLCK to indicate the lease needs to be removed.
 *
 *	XXX: sfr & willy disagree over whether F_INPROGRESS
 *	should be returned to userspace.
 */
int fcntl_getlease(struct file *filp)
{
	struct file_lock *fl;
	int type = F_UNLCK;

	lock_kernel();
1326 1327
	time_out_leases(filp->f_path.dentry->d_inode);
	for (fl = filp->f_path.dentry->d_inode->i_flock; fl && IS_LEASE(fl);
L
Linus Torvalds 已提交
1328 1329 1330 1331 1332 1333 1334 1335 1336 1337 1338
			fl = fl->fl_next) {
		if (fl->fl_file == filp) {
			type = fl->fl_type & ~F_INPROGRESS;
			break;
		}
	}
	unlock_kernel();
	return type;
}

/**
1339
 *	generic_setlease	-	sets a lease on an open file
L
Linus Torvalds 已提交
1340 1341 1342 1343 1344 1345 1346 1347 1348
 *	@filp: file pointer
 *	@arg: type of lease to obtain
 *	@flp: input - file_lock to use, output - file_lock inserted
 *
 *	The (input) flp->fl_lmops->fl_break function is required
 *	by break_lease().
 *
 *	Called with kernel lock held.
 */
1349
int generic_setlease(struct file *filp, long arg, struct file_lock **flp)
L
Linus Torvalds 已提交
1350
{
1351
	struct file_lock *fl, **before, **my_before = NULL, *lease;
1352
	struct file_lock *new_fl = NULL;
1353
	struct dentry *dentry = filp->f_path.dentry;
L
Linus Torvalds 已提交
1354 1355 1356
	struct inode *inode = dentry->d_inode;
	int error, rdlease_count = 0, wrlease_count = 0;

1357 1358 1359 1360 1361 1362 1363 1364
	if ((current->fsuid != inode->i_uid) && !capable(CAP_LEASE))
		return -EACCES;
	if (!S_ISREG(inode->i_mode))
		return -EINVAL;
	error = security_file_lock(filp, arg);
	if (error)
		return error;

L
Linus Torvalds 已提交
1365 1366
	time_out_leases(inode);

1367
	BUG_ON(!(*flp)->fl_lmops->fl_break);
L
Linus Torvalds 已提交
1368

1369 1370
	lease = *flp;

1371
	if (arg != F_UNLCK) {
1372 1373 1374 1375 1376
		error = -ENOMEM;
		new_fl = locks_alloc_lock();
		if (new_fl == NULL)
			goto out;

1377 1378 1379 1380 1381 1382 1383 1384
		error = -EAGAIN;
		if ((arg == F_RDLCK) && (atomic_read(&inode->i_writecount) > 0))
			goto out;
		if ((arg == F_WRLCK)
		    && ((atomic_read(&dentry->d_count) > 1)
			|| (atomic_read(&inode->i_count) > 1)))
			goto out;
	}
1385

L
Linus Torvalds 已提交
1386 1387 1388 1389 1390 1391 1392 1393 1394 1395 1396 1397 1398 1399 1400 1401 1402 1403 1404 1405 1406 1407 1408 1409
	/*
	 * At this point, we know that if there is an exclusive
	 * lease on this file, then we hold it on this filp
	 * (otherwise our open of this file would have blocked).
	 * And if we are trying to acquire an exclusive lease,
	 * then the file is not open by anyone (including us)
	 * except for this filp.
	 */
	for (before = &inode->i_flock;
			((fl = *before) != NULL) && IS_LEASE(fl);
			before = &fl->fl_next) {
		if (lease->fl_lmops->fl_mylease(fl, lease))
			my_before = before;
		else if (fl->fl_type == (F_INPROGRESS | F_UNLCK))
			/*
			 * Someone is in the process of opening this
			 * file for writing so we may not take an
			 * exclusive lease on it.
			 */
			wrlease_count++;
		else
			rdlease_count++;
	}

1410
	error = -EAGAIN;
L
Linus Torvalds 已提交
1411 1412 1413 1414 1415
	if ((arg == F_RDLCK && (wrlease_count > 0)) ||
	    (arg == F_WRLCK && ((rdlease_count + wrlease_count) > 0)))
		goto out;

	if (my_before != NULL) {
1416
		*flp = *my_before;
L
Linus Torvalds 已提交
1417 1418 1419 1420 1421 1422 1423 1424 1425 1426 1427 1428
		error = lease->fl_lmops->fl_change(my_before, arg);
		goto out;
	}

	error = 0;
	if (arg == F_UNLCK)
		goto out;

	error = -EINVAL;
	if (!leases_enable)
		goto out;

1429 1430
	locks_copy_lock(new_fl, lease);
	locks_insert_lock(before, new_fl);
L
Linus Torvalds 已提交
1431

1432 1433
	*flp = new_fl;
	return 0;
L
Linus Torvalds 已提交
1434 1435

out:
1436 1437
	if (new_fl != NULL)
		locks_free_lock(new_fl);
L
Linus Torvalds 已提交
1438 1439
	return error;
}
1440
EXPORT_SYMBOL(generic_setlease);
L
Linus Torvalds 已提交
1441 1442

 /**
1443
 *	vfs_setlease        -       sets a lease on an open file
L
Linus Torvalds 已提交
1444 1445 1446 1447 1448
 *	@filp: file pointer
 *	@arg: type of lease to obtain
 *	@lease: file_lock to use
 *
 *	Call this to establish a lease on the file.
1449 1450 1451 1452 1453 1454 1455 1456 1457 1458 1459 1460 1461 1462 1463 1464 1465 1466
 *	The (*lease)->fl_lmops->fl_break operation must be set; if not,
 *	break_lease will oops!
 *
 *	This will call the filesystem's setlease file method, if
 *	defined.  Note that there is no getlease method; instead, the
 *	filesystem setlease method should call back to setlease() to
 *	add a lease to the inode's lease list, where fcntl_getlease() can
 *	find it.  Since fcntl_getlease() only reports whether the current
 *	task holds a lease, a cluster filesystem need only do this for
 *	leases held by processes on this node.
 *
 *	There is also no break_lease method; filesystems that
 *	handle their own leases shoud break leases themselves from the
 *	filesystem's open, create, and (on truncate) setattr methods.
 *
 *	Warning: the only current setlease methods exist only to disable
 *	leases in certain cases.  More vfs changes may be required to
 *	allow a full filesystem lease implementation.
L
Linus Torvalds 已提交
1467 1468
 */

1469
int vfs_setlease(struct file *filp, long arg, struct file_lock **lease)
L
Linus Torvalds 已提交
1470 1471 1472 1473
{
	int error;

	lock_kernel();
1474 1475 1476
	if (filp->f_op && filp->f_op->setlease)
		error = filp->f_op->setlease(filp, arg, lease);
	else
1477
		error = generic_setlease(filp, arg, lease);
L
Linus Torvalds 已提交
1478 1479 1480 1481
	unlock_kernel();

	return error;
}
1482
EXPORT_SYMBOL_GPL(vfs_setlease);
L
Linus Torvalds 已提交
1483 1484 1485 1486 1487 1488 1489 1490 1491 1492 1493 1494 1495 1496

/**
 *	fcntl_setlease	-	sets a lease on an open file
 *	@fd: open file descriptor
 *	@filp: file pointer
 *	@arg: type of lease to obtain
 *
 *	Call this fcntl to establish a lease on the file.
 *	Note that you also need to call %F_SETSIG to
 *	receive a signal when the lease is broken.
 */
int fcntl_setlease(unsigned int fd, struct file *filp, long arg)
{
	struct file_lock fl, *flp = &fl;
1497
	struct inode *inode = filp->f_path.dentry->d_inode;
L
Linus Torvalds 已提交
1498 1499 1500 1501 1502 1503 1504 1505 1506
	int error;

	locks_init_lock(&fl);
	error = lease_init(filp, arg, &fl);
	if (error)
		return error;

	lock_kernel();

1507
	error = vfs_setlease(filp, arg, &flp);
1508
	if (error || arg == F_UNLCK)
L
Linus Torvalds 已提交
1509 1510 1511 1512
		goto out_unlock;

	error = fasync_helper(fd, filp, 1, &flp->fl_fasync);
	if (error < 0) {
1513
		/* remove lease just inserted by setlease */
L
Linus Torvalds 已提交
1514
		flp->fl_type = F_UNLCK | F_INPROGRESS;
1515
		flp->fl_break_time = jiffies - 10;
L
Linus Torvalds 已提交
1516 1517 1518 1519
		time_out_leases(inode);
		goto out_unlock;
	}

1520
	error = __f_setown(filp, task_pid(current), PIDTYPE_PID, 0);
L
Linus Torvalds 已提交
1521 1522 1523 1524 1525 1526 1527 1528 1529 1530 1531 1532 1533 1534 1535 1536 1537 1538 1539 1540 1541 1542 1543 1544 1545 1546 1547 1548 1549 1550 1551 1552 1553 1554 1555 1556 1557 1558 1559 1560 1561 1562 1563 1564 1565 1566 1567 1568 1569 1570 1571 1572 1573 1574 1575 1576 1577 1578 1579 1580 1581 1582 1583 1584 1585 1586 1587 1588 1589 1590 1591 1592 1593 1594 1595 1596 1597 1598 1599 1600 1601 1602 1603 1604 1605 1606 1607 1608
out_unlock:
	unlock_kernel();
	return error;
}

/**
 * flock_lock_file_wait - Apply a FLOCK-style lock to a file
 * @filp: The file to apply the lock to
 * @fl: The lock to be applied
 *
 * Add a FLOCK style lock to a file.
 */
int flock_lock_file_wait(struct file *filp, struct file_lock *fl)
{
	int error;
	might_sleep();
	for (;;) {
		error = flock_lock_file(filp, fl);
		if ((error != -EAGAIN) || !(fl->fl_flags & FL_SLEEP))
			break;
		error = wait_event_interruptible(fl->fl_wait, !fl->fl_next);
		if (!error)
			continue;

		locks_delete_block(fl);
		break;
	}
	return error;
}

EXPORT_SYMBOL(flock_lock_file_wait);

/**
 *	sys_flock: - flock() system call.
 *	@fd: the file descriptor to lock.
 *	@cmd: the type of lock to apply.
 *
 *	Apply a %FL_FLOCK style lock to an open file descriptor.
 *	The @cmd can be one of
 *
 *	%LOCK_SH -- a shared lock.
 *
 *	%LOCK_EX -- an exclusive lock.
 *
 *	%LOCK_UN -- remove an existing lock.
 *
 *	%LOCK_MAND -- a `mandatory' flock.  This exists to emulate Windows Share Modes.
 *
 *	%LOCK_MAND can be combined with %LOCK_READ or %LOCK_WRITE to allow other
 *	processes read and write access respectively.
 */
asmlinkage long sys_flock(unsigned int fd, unsigned int cmd)
{
	struct file *filp;
	struct file_lock *lock;
	int can_sleep, unlock;
	int error;

	error = -EBADF;
	filp = fget(fd);
	if (!filp)
		goto out;

	can_sleep = !(cmd & LOCK_NB);
	cmd &= ~LOCK_NB;
	unlock = (cmd == LOCK_UN);

	if (!unlock && !(cmd & LOCK_MAND) && !(filp->f_mode & 3))
		goto out_putf;

	error = flock_make_lock(filp, &lock, cmd);
	if (error)
		goto out_putf;
	if (can_sleep)
		lock->fl_flags |= FL_SLEEP;

	error = security_file_lock(filp, cmd);
	if (error)
		goto out_free;

	if (filp->f_op && filp->f_op->flock)
		error = filp->f_op->flock(filp,
					  (can_sleep) ? F_SETLKW : F_SETLK,
					  lock);
	else
		error = flock_lock_file_wait(filp, lock);

 out_free:
1609
	locks_free_lock(lock);
L
Linus Torvalds 已提交
1610 1611 1612 1613 1614 1615 1616

 out_putf:
	fput(filp);
 out:
	return error;
}

1617 1618 1619
/**
 * vfs_test_lock - test file byte range lock
 * @filp: The file to test lock for
1620
 * @fl: The lock to test; also used to hold result
1621 1622 1623 1624 1625 1626 1627 1628 1629 1630 1631 1632 1633
 *
 * Returns -ERRNO on failure.  Indicates presence of conflicting lock by
 * setting conf->fl_type to something other than F_UNLCK.
 */
int vfs_test_lock(struct file *filp, struct file_lock *fl)
{
	if (filp->f_op && filp->f_op->lock)
		return filp->f_op->lock(filp, F_GETLK, fl);
	posix_test_lock(filp, fl);
	return 0;
}
EXPORT_SYMBOL_GPL(vfs_test_lock);

1634 1635 1636 1637 1638 1639 1640 1641 1642 1643 1644 1645 1646 1647 1648 1649 1650
static int posix_lock_to_flock(struct flock *flock, struct file_lock *fl)
{
	flock->l_pid = fl->fl_pid;
#if BITS_PER_LONG == 32
	/*
	 * Make sure we can represent the posix lock via
	 * legacy 32bit flock.
	 */
	if (fl->fl_start > OFFT_OFFSET_MAX)
		return -EOVERFLOW;
	if (fl->fl_end != OFFSET_MAX && fl->fl_end > OFFT_OFFSET_MAX)
		return -EOVERFLOW;
#endif
	flock->l_start = fl->fl_start;
	flock->l_len = fl->fl_end == OFFSET_MAX ? 0 :
		fl->fl_end - fl->fl_start + 1;
	flock->l_whence = 0;
1651
	flock->l_type = fl->fl_type;
1652 1653 1654 1655 1656 1657 1658 1659 1660 1661 1662 1663 1664 1665 1666
	return 0;
}

#if BITS_PER_LONG == 32
static void posix_lock_to_flock64(struct flock64 *flock, struct file_lock *fl)
{
	flock->l_pid = fl->fl_pid;
	flock->l_start = fl->fl_start;
	flock->l_len = fl->fl_end == OFFSET_MAX ? 0 :
		fl->fl_end - fl->fl_start + 1;
	flock->l_whence = 0;
	flock->l_type = fl->fl_type;
}
#endif

L
Linus Torvalds 已提交
1667 1668 1669 1670 1671
/* Report the first existing lock that would conflict with l.
 * This implements the F_GETLK command of fcntl().
 */
int fcntl_getlk(struct file *filp, struct flock __user *l)
{
1672
	struct file_lock file_lock;
L
Linus Torvalds 已提交
1673 1674 1675 1676 1677 1678 1679 1680 1681 1682 1683 1684 1685 1686
	struct flock flock;
	int error;

	error = -EFAULT;
	if (copy_from_user(&flock, l, sizeof(flock)))
		goto out;
	error = -EINVAL;
	if ((flock.l_type != F_RDLCK) && (flock.l_type != F_WRLCK))
		goto out;

	error = flock_to_posix_lock(filp, &file_lock, &flock);
	if (error)
		goto out;

1687 1688 1689
	error = vfs_test_lock(filp, &file_lock);
	if (error)
		goto out;
L
Linus Torvalds 已提交
1690
 
1691 1692 1693
	flock.l_type = file_lock.fl_type;
	if (file_lock.fl_type != F_UNLCK) {
		error = posix_lock_to_flock(&flock, &file_lock);
1694
		if (error)
L
Linus Torvalds 已提交
1695 1696 1697 1698 1699 1700 1701 1702 1703
			goto out;
	}
	error = -EFAULT;
	if (!copy_to_user(l, &flock, sizeof(flock)))
		error = 0;
out:
	return error;
}

1704 1705 1706 1707 1708
/**
 * vfs_lock_file - file byte range lock
 * @filp: The file to apply the lock to
 * @cmd: type of locking operation (F_SETLK, F_GETLK, etc.)
 * @fl: The lock to be applied
1709 1710 1711 1712 1713 1714 1715 1716
 * @conf: Place to return a copy of the conflicting lock, if found.
 *
 * A caller that doesn't care about the conflicting lock may pass NULL
 * as the final argument.
 *
 * If the filesystem defines a private ->lock() method, then @conf will
 * be left unchanged; so a caller that cares should initialize it to
 * some acceptable default.
1717 1718 1719 1720 1721 1722 1723 1724 1725 1726 1727 1728 1729 1730 1731 1732 1733 1734 1735
 *
 * To avoid blocking kernel daemons, such as lockd, that need to acquire POSIX
 * locks, the ->lock() interface may return asynchronously, before the lock has
 * been granted or denied by the underlying filesystem, if (and only if)
 * fl_grant is set. Callers expecting ->lock() to return asynchronously
 * will only use F_SETLK, not F_SETLKW; they will set FL_SLEEP if (and only if)
 * the request is for a blocking lock. When ->lock() does return asynchronously,
 * it must return -EINPROGRESS, and call ->fl_grant() when the lock
 * request completes.
 * If the request is for non-blocking lock the file system should return
 * -EINPROGRESS then try to get the lock and call the callback routine with
 * the result. If the request timed out the callback routine will return a
 * nonzero return code and the file system should release the lock. The file
 * system is also responsible to keep a corresponding posix lock when it
 * grants a lock so the VFS can find out which locks are locally held and do
 * the correct lock cleanup when required.
 * The underlying filesystem must not drop the kernel lock or call
 * ->fl_grant() before returning to the caller with a -EINPROGRESS
 * return code.
1736
 */
1737
int vfs_lock_file(struct file *filp, unsigned int cmd, struct file_lock *fl, struct file_lock *conf)
1738 1739 1740 1741
{
	if (filp->f_op && filp->f_op->lock)
		return filp->f_op->lock(filp, cmd, fl);
	else
1742
		return posix_lock_file(filp, fl, conf);
1743 1744 1745
}
EXPORT_SYMBOL_GPL(vfs_lock_file);

L
Linus Torvalds 已提交
1746 1747 1748
/* Apply the lock described by l to an open file descriptor.
 * This implements both the F_SETLK and F_SETLKW commands of fcntl().
 */
1749 1750
int fcntl_setlk(unsigned int fd, struct file *filp, unsigned int cmd,
		struct flock __user *l)
L
Linus Torvalds 已提交
1751 1752 1753 1754 1755 1756 1757 1758 1759 1760 1761 1762 1763 1764 1765 1766
{
	struct file_lock *file_lock = locks_alloc_lock();
	struct flock flock;
	struct inode *inode;
	int error;

	if (file_lock == NULL)
		return -ENOLCK;

	/*
	 * This might block, so we do it before checking the inode.
	 */
	error = -EFAULT;
	if (copy_from_user(&flock, l, sizeof(flock)))
		goto out;

1767
	inode = filp->f_path.dentry->d_inode;
L
Linus Torvalds 已提交
1768 1769 1770 1771

	/* Don't allow mandatory locks on files that may be memory mapped
	 * and shared.
	 */
1772
	if (mandatory_lock(inode) && mapping_writably_mapped(filp->f_mapping)) {
L
Linus Torvalds 已提交
1773 1774 1775 1776
		error = -EAGAIN;
		goto out;
	}

1777
again:
L
Linus Torvalds 已提交
1778 1779 1780 1781 1782 1783 1784 1785 1786 1787 1788 1789 1790 1791 1792 1793 1794 1795 1796 1797 1798 1799 1800 1801 1802 1803 1804 1805
	error = flock_to_posix_lock(filp, file_lock, &flock);
	if (error)
		goto out;
	if (cmd == F_SETLKW) {
		file_lock->fl_flags |= FL_SLEEP;
	}
	
	error = -EBADF;
	switch (flock.l_type) {
	case F_RDLCK:
		if (!(filp->f_mode & FMODE_READ))
			goto out;
		break;
	case F_WRLCK:
		if (!(filp->f_mode & FMODE_WRITE))
			goto out;
		break;
	case F_UNLCK:
		break;
	default:
		error = -EINVAL;
		goto out;
	}

	error = security_file_lock(filp, file_lock->fl_type);
	if (error)
		goto out;

1806 1807 1808 1809 1810 1811 1812 1813 1814 1815 1816
	if (filp->f_op && filp->f_op->lock != NULL)
		error = filp->f_op->lock(filp, cmd, file_lock);
	else {
		for (;;) {
			error = posix_lock_file(filp, file_lock, NULL);
			if (error != -EAGAIN || cmd == F_SETLK)
				break;
			error = wait_event_interruptible(file_lock->fl_wait,
					!file_lock->fl_next);
			if (!error)
				continue;
1817

1818 1819 1820
			locks_delete_block(file_lock);
			break;
		}
1821
	}
L
Linus Torvalds 已提交
1822

1823 1824 1825 1826 1827 1828 1829
	/*
	 * Attempt to detect a close/fcntl race and recover by
	 * releasing the lock that was just acquired.
	 */
	if (!error && fcheck(fd) != filp && flock.l_type != F_UNLCK) {
		flock.l_type = F_UNLCK;
		goto again;
L
Linus Torvalds 已提交
1830 1831
	}

1832
out:
L
Linus Torvalds 已提交
1833 1834 1835 1836 1837 1838 1839 1840 1841 1842
	locks_free_lock(file_lock);
	return error;
}

#if BITS_PER_LONG == 32
/* Report the first existing lock that would conflict with l.
 * This implements the F_GETLK command of fcntl().
 */
int fcntl_getlk64(struct file *filp, struct flock64 __user *l)
{
1843
	struct file_lock file_lock;
L
Linus Torvalds 已提交
1844 1845 1846 1847 1848 1849 1850 1851 1852 1853 1854 1855 1856 1857
	struct flock64 flock;
	int error;

	error = -EFAULT;
	if (copy_from_user(&flock, l, sizeof(flock)))
		goto out;
	error = -EINVAL;
	if ((flock.l_type != F_RDLCK) && (flock.l_type != F_WRLCK))
		goto out;

	error = flock64_to_posix_lock(filp, &file_lock, &flock);
	if (error)
		goto out;

1858 1859 1860 1861
	error = vfs_test_lock(filp, &file_lock);
	if (error)
		goto out;

1862 1863 1864 1865
	flock.l_type = file_lock.fl_type;
	if (file_lock.fl_type != F_UNLCK)
		posix_lock_to_flock64(&flock, &file_lock);

L
Linus Torvalds 已提交
1866 1867 1868 1869 1870 1871 1872 1873 1874 1875 1876
	error = -EFAULT;
	if (!copy_to_user(l, &flock, sizeof(flock)))
		error = 0;
  
out:
	return error;
}

/* Apply the lock described by l to an open file descriptor.
 * This implements both the F_SETLK and F_SETLKW commands of fcntl().
 */
1877 1878
int fcntl_setlk64(unsigned int fd, struct file *filp, unsigned int cmd,
		struct flock64 __user *l)
L
Linus Torvalds 已提交
1879 1880 1881 1882 1883 1884 1885 1886 1887 1888 1889 1890 1891 1892 1893 1894
{
	struct file_lock *file_lock = locks_alloc_lock();
	struct flock64 flock;
	struct inode *inode;
	int error;

	if (file_lock == NULL)
		return -ENOLCK;

	/*
	 * This might block, so we do it before checking the inode.
	 */
	error = -EFAULT;
	if (copy_from_user(&flock, l, sizeof(flock)))
		goto out;

1895
	inode = filp->f_path.dentry->d_inode;
L
Linus Torvalds 已提交
1896 1897 1898 1899

	/* Don't allow mandatory locks on files that may be memory mapped
	 * and shared.
	 */
1900
	if (mandatory_lock(inode) && mapping_writably_mapped(filp->f_mapping)) {
L
Linus Torvalds 已提交
1901 1902 1903 1904
		error = -EAGAIN;
		goto out;
	}

1905
again:
L
Linus Torvalds 已提交
1906 1907 1908 1909 1910 1911 1912 1913 1914 1915 1916 1917 1918 1919 1920 1921 1922 1923 1924 1925 1926 1927 1928 1929 1930 1931 1932 1933
	error = flock64_to_posix_lock(filp, file_lock, &flock);
	if (error)
		goto out;
	if (cmd == F_SETLKW64) {
		file_lock->fl_flags |= FL_SLEEP;
	}
	
	error = -EBADF;
	switch (flock.l_type) {
	case F_RDLCK:
		if (!(filp->f_mode & FMODE_READ))
			goto out;
		break;
	case F_WRLCK:
		if (!(filp->f_mode & FMODE_WRITE))
			goto out;
		break;
	case F_UNLCK:
		break;
	default:
		error = -EINVAL;
		goto out;
	}

	error = security_file_lock(filp, file_lock->fl_type);
	if (error)
		goto out;

1934 1935 1936 1937 1938 1939 1940 1941 1942 1943 1944
	if (filp->f_op && filp->f_op->lock != NULL)
		error = filp->f_op->lock(filp, cmd, file_lock);
	else {
		for (;;) {
			error = posix_lock_file(filp, file_lock, NULL);
			if (error != -EAGAIN || cmd == F_SETLK64)
				break;
			error = wait_event_interruptible(file_lock->fl_wait,
					!file_lock->fl_next);
			if (!error)
				continue;
1945

1946 1947 1948
			locks_delete_block(file_lock);
			break;
		}
1949
	}
L
Linus Torvalds 已提交
1950

1951 1952 1953 1954 1955 1956 1957
	/*
	 * Attempt to detect a close/fcntl race and recover by
	 * releasing the lock that was just acquired.
	 */
	if (!error && fcheck(fd) != filp && flock.l_type != F_UNLCK) {
		flock.l_type = F_UNLCK;
		goto again;
L
Linus Torvalds 已提交
1958 1959 1960 1961 1962 1963 1964 1965 1966 1967 1968 1969 1970 1971 1972
	}

out:
	locks_free_lock(file_lock);
	return error;
}
#endif /* BITS_PER_LONG == 32 */

/*
 * This function is called when the file is being removed
 * from the task's fd array.  POSIX locks belonging to this task
 * are deleted at this time.
 */
void locks_remove_posix(struct file *filp, fl_owner_t owner)
{
1973
	struct file_lock lock;
L
Linus Torvalds 已提交
1974 1975 1976 1977 1978 1979

	/*
	 * If there are no locks held on this file, we don't need to call
	 * posix_lock_file().  Another process could be setting a lock on this
	 * file at the same time, but we wouldn't remove that lock anyway.
	 */
1980
	if (!filp->f_path.dentry->d_inode->i_flock)
L
Linus Torvalds 已提交
1981 1982 1983
		return;

	lock.fl_type = F_UNLCK;
1984
	lock.fl_flags = FL_POSIX | FL_CLOSE;
L
Linus Torvalds 已提交
1985 1986 1987 1988 1989 1990 1991 1992
	lock.fl_start = 0;
	lock.fl_end = OFFSET_MAX;
	lock.fl_owner = owner;
	lock.fl_pid = current->tgid;
	lock.fl_file = filp;
	lock.fl_ops = NULL;
	lock.fl_lmops = NULL;

1993
	vfs_lock_file(filp, F_SETLK, &lock, NULL);
L
Linus Torvalds 已提交
1994 1995 1996 1997 1998 1999 2000 2001 2002 2003 2004 2005

	if (lock.fl_ops && lock.fl_ops->fl_release_private)
		lock.fl_ops->fl_release_private(&lock);
}

EXPORT_SYMBOL(locks_remove_posix);

/*
 * This function is called on the last close of an open file.
 */
void locks_remove_flock(struct file *filp)
{
2006
	struct inode * inode = filp->f_path.dentry->d_inode;
L
Linus Torvalds 已提交
2007 2008 2009 2010 2011 2012 2013 2014 2015 2016 2017 2018 2019 2020 2021
	struct file_lock *fl;
	struct file_lock **before;

	if (!inode->i_flock)
		return;

	if (filp->f_op && filp->f_op->flock) {
		struct file_lock fl = {
			.fl_pid = current->tgid,
			.fl_file = filp,
			.fl_flags = FL_FLOCK,
			.fl_type = F_UNLCK,
			.fl_end = OFFSET_MAX,
		};
		filp->f_op->flock(filp, F_SETLKW, &fl);
2022 2023
		if (fl.fl_ops && fl.fl_ops->fl_release_private)
			fl.fl_ops->fl_release_private(&fl);
L
Linus Torvalds 已提交
2024 2025 2026 2027 2028 2029 2030
	}

	lock_kernel();
	before = &inode->i_flock;

	while ((fl = *before) != NULL) {
		if (fl->fl_file == filp) {
2031
			if (IS_FLOCK(fl)) {
L
Linus Torvalds 已提交
2032 2033 2034 2035 2036 2037 2038 2039 2040 2041 2042 2043 2044 2045 2046 2047 2048 2049 2050 2051 2052 2053
				locks_delete_lock(before);
				continue;
			}
			if (IS_LEASE(fl)) {
				lease_modify(before, F_UNLCK);
				continue;
			}
			/* What? */
			BUG();
 		}
		before = &fl->fl_next;
	}
	unlock_kernel();
}

/**
 *	posix_unblock_lock - stop waiting for a file lock
 *      @filp:   how the file was opened
 *	@waiter: the lock which was waiting
 *
 *	lockd needs to block waiting for locks.
 */
J
J. Bruce Fields 已提交
2054
int
L
Linus Torvalds 已提交
2055 2056
posix_unblock_lock(struct file *filp, struct file_lock *waiter)
{
J
J. Bruce Fields 已提交
2057 2058
	int status = 0;

L
Linus Torvalds 已提交
2059
	lock_kernel();
2060
	if (waiter->fl_next)
L
Linus Torvalds 已提交
2061
		__locks_delete_block(waiter);
J
J. Bruce Fields 已提交
2062 2063
	else
		status = -ENOENT;
2064
	unlock_kernel();
J
J. Bruce Fields 已提交
2065
	return status;
L
Linus Torvalds 已提交
2066 2067 2068 2069
}

EXPORT_SYMBOL(posix_unblock_lock);

M
Marc Eshel 已提交
2070 2071 2072 2073 2074 2075 2076 2077 2078 2079 2080 2081 2082 2083 2084 2085
/**
 * vfs_cancel_lock - file byte range unblock lock
 * @filp: The file to apply the unblock to
 * @fl: The lock to be unblocked
 *
 * Used by lock managers to cancel blocked requests
 */
int vfs_cancel_lock(struct file *filp, struct file_lock *fl)
{
	if (filp->f_op && filp->f_op->lock)
		return filp->f_op->lock(filp, F_CANCELLK, fl);
	return 0;
}

EXPORT_SYMBOL_GPL(vfs_cancel_lock);

2086 2087 2088 2089 2090
#ifdef CONFIG_PROC_FS
#include <linux/seq_file.h>

static void lock_get_status(struct seq_file *f, struct file_lock *fl,
							int id, char *pfx)
L
Linus Torvalds 已提交
2091 2092
{
	struct inode *inode = NULL;
2093 2094 2095
	unsigned int fl_pid;

	if (fl->fl_nspid)
2096
		fl_pid = pid_vnr(fl->fl_nspid);
2097 2098
	else
		fl_pid = fl->fl_pid;
L
Linus Torvalds 已提交
2099 2100

	if (fl->fl_file != NULL)
2101
		inode = fl->fl_file->f_path.dentry->d_inode;
L
Linus Torvalds 已提交
2102

2103
	seq_printf(f, "%d:%s ", id, pfx);
L
Linus Torvalds 已提交
2104
	if (IS_POSIX(fl)) {
2105
		seq_printf(f, "%6s %s ",
L
Linus Torvalds 已提交
2106 2107
			     (fl->fl_flags & FL_ACCESS) ? "ACCESS" : "POSIX ",
			     (inode == NULL) ? "*NOINODE*" :
2108
			     mandatory_lock(inode) ? "MANDATORY" : "ADVISORY ");
L
Linus Torvalds 已提交
2109 2110
	} else if (IS_FLOCK(fl)) {
		if (fl->fl_type & LOCK_MAND) {
2111
			seq_printf(f, "FLOCK  MSNFS     ");
L
Linus Torvalds 已提交
2112
		} else {
2113
			seq_printf(f, "FLOCK  ADVISORY  ");
L
Linus Torvalds 已提交
2114 2115
		}
	} else if (IS_LEASE(fl)) {
2116
		seq_printf(f, "LEASE  ");
L
Linus Torvalds 已提交
2117
		if (fl->fl_type & F_INPROGRESS)
2118
			seq_printf(f, "BREAKING  ");
L
Linus Torvalds 已提交
2119
		else if (fl->fl_file)
2120
			seq_printf(f, "ACTIVE    ");
L
Linus Torvalds 已提交
2121
		else
2122
			seq_printf(f, "BREAKER   ");
L
Linus Torvalds 已提交
2123
	} else {
2124
		seq_printf(f, "UNKNOWN UNKNOWN  ");
L
Linus Torvalds 已提交
2125 2126
	}
	if (fl->fl_type & LOCK_MAND) {
2127
		seq_printf(f, "%s ",
L
Linus Torvalds 已提交
2128 2129 2130 2131
			       (fl->fl_type & LOCK_READ)
			       ? (fl->fl_type & LOCK_WRITE) ? "RW   " : "READ "
			       : (fl->fl_type & LOCK_WRITE) ? "WRITE" : "NONE ");
	} else {
2132
		seq_printf(f, "%s ",
L
Linus Torvalds 已提交
2133 2134 2135 2136 2137 2138
			       (fl->fl_type & F_INPROGRESS)
			       ? (fl->fl_type & F_UNLCK) ? "UNLCK" : "READ "
			       : (fl->fl_type & F_WRLCK) ? "WRITE" : "READ ");
	}
	if (inode) {
#ifdef WE_CAN_BREAK_LSLK_NOW
2139
		seq_printf(f, "%d %s:%ld ", fl_pid,
L
Linus Torvalds 已提交
2140 2141 2142
				inode->i_sb->s_id, inode->i_ino);
#else
		/* userspace relies on this representation of dev_t ;-( */
2143
		seq_printf(f, "%d %02x:%02x:%ld ", fl_pid,
L
Linus Torvalds 已提交
2144 2145 2146 2147
				MAJOR(inode->i_sb->s_dev),
				MINOR(inode->i_sb->s_dev), inode->i_ino);
#endif
	} else {
2148
		seq_printf(f, "%d <none>:0 ", fl_pid);
L
Linus Torvalds 已提交
2149 2150 2151
	}
	if (IS_POSIX(fl)) {
		if (fl->fl_end == OFFSET_MAX)
2152
			seq_printf(f, "%Ld EOF\n", fl->fl_start);
L
Linus Torvalds 已提交
2153
		else
2154
			seq_printf(f, "%Ld %Ld\n", fl->fl_start, fl->fl_end);
L
Linus Torvalds 已提交
2155
	} else {
2156
		seq_printf(f, "0 EOF\n");
L
Linus Torvalds 已提交
2157 2158 2159
	}
}

2160
static int locks_show(struct seq_file *f, void *v)
L
Linus Torvalds 已提交
2161
{
2162
	struct file_lock *fl, *bfl;
L
Linus Torvalds 已提交
2163

2164
	fl = list_entry(v, struct file_lock, fl_link);
L
Linus Torvalds 已提交
2165

2166
	lock_get_status(f, fl, (long)f->private, "");
L
Linus Torvalds 已提交
2167

2168 2169
	list_for_each_entry(bfl, &fl->fl_block, fl_block)
		lock_get_status(f, bfl, (long)f->private, " ->");
2170

2171 2172 2173
	f->private++;
	return 0;
}
L
Linus Torvalds 已提交
2174

2175 2176 2177 2178 2179 2180
static void *locks_start(struct seq_file *f, loff_t *pos)
{
	lock_kernel();
	f->private = (void *)1;
	return seq_list_start(&file_lock_list, *pos);
}
L
Linus Torvalds 已提交
2181

2182 2183 2184 2185
static void *locks_next(struct seq_file *f, void *v, loff_t *pos)
{
	return seq_list_next(v, &file_lock_list, pos);
}
L
Linus Torvalds 已提交
2186

2187 2188
static void locks_stop(struct seq_file *f, void *v)
{
L
Linus Torvalds 已提交
2189 2190 2191
	unlock_kernel();
}

2192 2193 2194 2195 2196 2197 2198 2199
struct seq_operations locks_seq_operations = {
	.start	= locks_start,
	.next	= locks_next,
	.stop	= locks_stop,
	.show	= locks_show,
};
#endif

L
Linus Torvalds 已提交
2200 2201 2202 2203 2204 2205 2206 2207 2208 2209 2210 2211 2212 2213 2214 2215 2216 2217 2218 2219 2220 2221 2222 2223 2224 2225 2226 2227 2228 2229 2230 2231 2232 2233 2234 2235 2236 2237 2238 2239 2240 2241 2242 2243 2244 2245 2246 2247 2248 2249 2250 2251 2252 2253 2254 2255 2256 2257 2258 2259 2260 2261 2262 2263 2264 2265 2266 2267 2268 2269 2270 2271 2272 2273 2274 2275 2276 2277 2278 2279 2280 2281
/**
 *	lock_may_read - checks that the region is free of locks
 *	@inode: the inode that is being read
 *	@start: the first byte to read
 *	@len: the number of bytes to read
 *
 *	Emulates Windows locking requirements.  Whole-file
 *	mandatory locks (share modes) can prohibit a read and
 *	byte-range POSIX locks can prohibit a read if they overlap.
 *
 *	N.B. this function is only ever called
 *	from knfsd and ownership of locks is never checked.
 */
int lock_may_read(struct inode *inode, loff_t start, unsigned long len)
{
	struct file_lock *fl;
	int result = 1;
	lock_kernel();
	for (fl = inode->i_flock; fl != NULL; fl = fl->fl_next) {
		if (IS_POSIX(fl)) {
			if (fl->fl_type == F_RDLCK)
				continue;
			if ((fl->fl_end < start) || (fl->fl_start > (start + len)))
				continue;
		} else if (IS_FLOCK(fl)) {
			if (!(fl->fl_type & LOCK_MAND))
				continue;
			if (fl->fl_type & LOCK_READ)
				continue;
		} else
			continue;
		result = 0;
		break;
	}
	unlock_kernel();
	return result;
}

EXPORT_SYMBOL(lock_may_read);

/**
 *	lock_may_write - checks that the region is free of locks
 *	@inode: the inode that is being written
 *	@start: the first byte to write
 *	@len: the number of bytes to write
 *
 *	Emulates Windows locking requirements.  Whole-file
 *	mandatory locks (share modes) can prohibit a write and
 *	byte-range POSIX locks can prohibit a write if they overlap.
 *
 *	N.B. this function is only ever called
 *	from knfsd and ownership of locks is never checked.
 */
int lock_may_write(struct inode *inode, loff_t start, unsigned long len)
{
	struct file_lock *fl;
	int result = 1;
	lock_kernel();
	for (fl = inode->i_flock; fl != NULL; fl = fl->fl_next) {
		if (IS_POSIX(fl)) {
			if ((fl->fl_end < start) || (fl->fl_start > (start + len)))
				continue;
		} else if (IS_FLOCK(fl)) {
			if (!(fl->fl_type & LOCK_MAND))
				continue;
			if (fl->fl_type & LOCK_WRITE)
				continue;
		} else
			continue;
		result = 0;
		break;
	}
	unlock_kernel();
	return result;
}

EXPORT_SYMBOL(lock_may_write);

static int __init filelock_init(void)
{
	filelock_cache = kmem_cache_create("file_lock_cache",
			sizeof(struct file_lock), 0, SLAB_PANIC,
2282
			init_once);
L
Linus Torvalds 已提交
2283 2284 2285 2286
	return 0;
}

core_initcall(filelock_init);