aboutsummaryrefslogtreecommitdiffstats
path: root/kernel/mutex.c
blob: c4195fa98900b65528bf5ee2229f7eeadfa5c4d7 (plain) (blame)
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
/*
 * kernel/mutex.c
 *
 * Mutexes: blocking mutual exclusion locks
 *
 * Started by Ingo Molnar:
 *
 *  Copyright (C) 2004, 2005, 2006 Red Hat, Inc., Ingo Molnar <mingo@redhat.com>
 *
 * Many thanks to Arjan van de Ven, Thomas Gleixner, Steven Rostedt and
 * David Howells for suggestions and improvements.
 *
 *  - Adaptive spinning for mutexes by Peter Zijlstra. (Ported to mainline
 *    from the -rt tree, where it was originally implemented for rtmutexes
 *    by Steven Rostedt, based on work by Gregory Haskins, Peter Morreale
 *    and Sven Dietrich.
 *
 * Also see Documentation/mutex-design.txt.
 */
#include <linux/mutex.h>
#include <linux/sched.h>
#include <linux/module.h>
#include <linux/spinlock.h>
#include <linux/interrupt.h>
#include <linux/debug_locks.h>

/*
 * In the DEBUG case we are using the "NULL fastpath" for mutexes,
 * which forces all calls into the slowpath:
 */
#ifdef CONFIG_DEBUG_MUTEXES
# include "mutex-debug.h"
# include <asm-generic/mutex-null.h>
#else
# include "mutex.h"
# include <asm/mutex.h>
#endif

void
__mutex_init(struct mutex *lock, const char *name, struct lock_class_key *key)
{
	atomic_set(&lock->count, 1);
	spin_lock_init(&lock->wait_lock);
	INIT_LIST_HEAD(&lock->wait_list);
	mutex_clear_owner(lock);

	debug_mutex_init(lock, name, key);
}

EXPORT_SYMBOL(__mutex_init);

#ifndef CONFIG_DEBUG_LOCK_ALLOC
/*
 * We split the mutex lock/unlock logic into separate fastpath and
 * slowpath functions, to reduce the register pressure on the fastpath.
 * We also put the fastpath first in the kernel image, to make sure the
 * branch is predicted by the CPU as default-untaken.
 */
static __used noinline void __sched
__mutex_lock_slowpath(atomic_t *lock_count);

/**
 * mutex_lock - acquire the mutex
 * @lock: the mutex to be acquired
 *
 * Lock the mutex exclusively for this task. If the mutex is not
 * available right now, it will sleep until it can get it.
 *
 * The mutex must later on be released by the same task that
 * acquired it. Recursive locking is not allowed. The task
 * may not exit without first unlocking the mutex. Also, kernel
 * memory where the mutex resides mutex must not be freed with
 * the mutex still locked. The mutex must first be initialized
 * (or statically defined) before it can be locked. memset()-ing
 * the mutex to 0 is not allowed.
 *
 * ( The CONFIG_DEBUG_MUTEXES .config option turns on debugging
 *   checks that will enforce the restrictions and will also do
 *   deadlock debugging. )
 *
 * This function is similar to (but not equivalent to) down().
 */
void __sched mutex_lock(struct mutex *lock)
{
	might_sleep();
	/*
	 * The locking fastpath is the 1->0 transition from
	 * 'unlocked' into 'locked' state.
	 */
	__mutex_fastpath_lock(&lock->count, __mutex_lock_slowpath);
	mutex_set_owner(lock);
}

EXPORT_SYMBOL(mutex_lock);
#endif

static __used noinline void __sched __mutex_unlock_slowpath(atomic_t *lock_count);

/**
 * mutex_unlock - release the mutex
 * @lock: the mutex to be released
 *
 * Unlock a mutex that has been locked by this task previously.
 *
 * This function must not be used in interrupt context. Unlocking
 * of a not locked mutex is not allowed.
 *
 * This function is similar to (but not equivalent to) up().
 */
void __sched mutex_unlock(struct mutex *lock)
{
	/*
	 * The unlocking fastpath is the 0->1 transition from 'locked'
	 * into 'unlocked' state:
	 */
#ifndef CONFIG_DEBUG_MUTEXES
	/*
	 * When debugging is enabled we must not clear the owner before time,
	 * the slow path will always be taken, and that clears the owner field
	 * after verifying that it was indeed current.
	 */
	mutex_clear_owner(lock);
#endif
	__mutex_fastpath_unlock(&lock->count, __mutex_unlock_slowpath);
}

EXPORT_SYMBOL(mutex_unlock);

/*
 * Lock a mutex (possibly interruptible), slowpath:
 */
static inline int __sched
__mutex_lock_common(struct mutex *lock, long state, unsigned int subclass,
	       	unsigned long ip)
{
	struct task_struct *task = current;
	struct mutex_waiter waiter;
	unsigned long flags;

	preempt_disable();
	mutex_acquire(&lock->dep_map, subclass, 0, ip);

#ifdef CONFIG_MUTEX_SPIN_ON_OWNER
	/*
	 * Optimistic spinning.
	 *
	 * We try to spin for acquisition when we find that there are no
	 * pending waiters and the lock owner is currently running on a
	 * (different) CPU.
	 *
	 * The rationale is that if the lock owner is running, it is likely to
	 * release the lock soon.
	 *
	 * Since this needs the lock owner, and this mutex implementation
	 * doesn't track the owner atomically in the lock field, we need to
	 * track it non-atomically.
	 *
	 * We can't do this for DEBUG_MUTEXES because that relies on wait_lock
	 * to serialize everything.
	 */

	for (;;) {
		struct thread_info *owner;

		/*
		 * If we own the BKL, then don't spin. The owner of
		 * the mutex might be waiting on us to release the BKL.
		 */
		if (unlikely(current->lock_depth >= 0))
			break;

		/*
		 * If there's an owner, wait for it to either
		 * release the lock or go to sleep.
		 */
		owner = ACCESS_ONCE(lock->owner);
		if (owner && !mutex_spin_on_owner(lock, owner))
			break;

		if (atomic_cmpxchg(&lock->count, 1, 0) == 1) {
			lock_acquired(&lock->dep_map, ip);
			mutex_set_owner(lock);
			preempt_enable();
			return 0;
		}

		/*
		 * When there's no owner, we might have preempted between the
		 * owner acquiring the lock and setting the owner field. If
		 * we're an RT task that will live-lock because we won't let
		 * the owner complete.
		 */
		if (!owner && (need_resched() || rt_task(task)))
			break;

		/*
		 * The cpu_relax() call is a compiler barrier which forces
		 * everything in this loop to be re-loaded. We don't need
		 * memory barriers as we'll eventually observe the right
		 * values at the cost of a few extra spins.
		 */
		arch_mutex_cpu_relax();
	}
#endif
	spin_lock_mutex(&lock->wait_lock, flags);

	debug_mutex_lock_common(lock, &waiter);
	debug_mutex_add_waiter(lock, &waiter, task_thread_info(task));

	/* add waiting tasks to the end of the waitqueue (FIFO): */
	list_add_tail(&waiter.list, &lock->wait_list);
	waiter.task = task;

	if (atomic_xchg(&lock->count, -1) == 1)
		goto done;

	lock_contended(&lock->dep_map, ip);

	for (;;) {
		/*
		 * Lets try to take the lock again - this is needed even if
		 * we get here for the first time (shortly after failing to
		 * acquire the lock), to make sure that we get a wakeup once
		 * it's unlocked. Later on, if we sleep, this is the
		 * operation that gives us the lock. We xchg it to -1, so
		 * that when we release the lock, we properly wake up the
		 * other waiters:
		 */
		if (atomic_xchg(&lock->count, -1) == 1)
			break;

		/*
		 * got a signal? (This code gets eliminated in the
		 * TASK_UNINTERRUPTIBLE case.)
		 */
		if (unlikely(signal_pending_state(state, task))) {
			mutex_remove_waiter(lock, &waiter,
					    task_thread_info(task));
			mutex_release(&lock->dep_map, 1, ip);
			spin_unlock_mutex(&lock->wait_lock, flags);

			debug_mutex_free_waiter(&waiter);
			preempt_enable();
			return -EINTR;
		}
		__set_task_state(task, state);

		/* didn't get the lock, go to sleep: */
		spin_unlock_mutex(&lock->wait_lock, flags);
		preempt_enable_no_resched();
		schedule();
		preempt_disable();
		spin_lock_mutex(&lock->wait_lock, flags);
	}

done:
	lock_acquired(&lock->dep_map, ip);
	/* got the lock - rejoice! */
	mutex_remove_waiter(lock, &waiter, current_thread_info());
	mutex_set_owner(lock);

	/* set it to 0 if there are no waiters left: */
	if (likely(list_empty(&lock->wait_list)))
		atomic_set(&lock->count, 0);

	spin_unlock_mutex(&lock->wait_lock, flags);

	debug_mutex_free_waiter(&waiter);
	preempt_enable();

	return 0;
}

#ifdef CONFIG_DEBUG_LOCK_ALLOC
void __sched
mutex_lock_nested(struct mutex *lock, unsigned int subclass)
{
	might_sleep();
	__mutex_lock_common(lock, TASK_UNINTERRUPTIBLE, subclass, _RET_IP_);
}

EXPORT_SYMBOL_GPL(mutex_lock_nested);

int __sched
mutex_lock_killable_nested(struct mutex *lock, unsigned int subclass)
{
	might_sleep();
	return __mutex_lock_common(lock, TASK_KILLABLE, subclass, _RET_IP_);
}
EXPORT_SYMBOL_GPL(mutex_lock_killable_nested);

int __sched
mutex_lock_interruptible_nested(struct mutex *lock, unsigned int subclass)
{
	might_sleep();
	return __mutex_lock_common(lock, TASK_INTERRUPTIBLE,
				   subclass, _RET_IP_);
}

EXPORT_SYMBOL_GPL(mutex_lock_interruptible_nested);
#endif

/*
 * Release the lock, slowpath:
 */
static inline void
__mutex_unlock_common_slowpath(atomic_t *lock_count, int nested)
{
	struct mutex *lock = container_of(lock_count, struct mutex, count);
	unsigned long flags;

	spin_lock_mutex(&lock->wait_lock, flags);
	mutex_release(&lock->dep_map, nested, _RET_IP_);
	debug_mutex_unlock(lock);

	/*
	 * some architectures leave the lock unlocked in the fastpath failure
	 * case, others need to leave it locked. In the later case we have to
	 * unlock it here
	 */
	if (__mutex_slowpath_needs_to_unlock())
		atomic_set(&lock->count, 1);

	if (!list_empty(&lock->wait_list)) {
		/* get the first entry from the wait-list: */
		struct mutex_waiter *waiter =
				list_entry(lock->wait_list.next,
					   struct mutex_waiter, list);

		debug_mutex_wake_waiter(lock, waiter);

		wake_up_process(waiter->task);
	}

	spin_unlock_mutex(&lock->wait_lock, flags);
}

/*
 * Release the lock, slowpath:
 */
static __used noinline void
__mutex_unlock_slowpath(atomic_t *lock_count)
{
	__mutex_unlock_common_slowpath(lock_count, 1);
}

#ifndef CONFIG_DEBUG_LOCK_ALLOC
/*
 * Here come the less common (and hence less performance-critical) APIs:
 * mutex_lock_interruptible() and mutex_trylock().
 */
static noinline int __sched
__mutex_lock_killable_slowpath(atomic_t *lock_count);

static noinline int __sched
__mutex_lock_interruptible_slowpath(atomic_t *lock_count);

/**
 * mutex_lock_interruptible - acquire the mutex, interruptible
 * @lock: the mutex to be acquired
 *
 * Lock the mutex like mutex_lock(), and return 0 if the mutex has
 * been acquired or sleep until the mutex becomes available. If a
 * signal arrives while waiting for the lock then this function
 * returns -EINTR.
 *
 * This function is similar to (but not equivalent to) down_interruptible().
 */
int __sched mutex_lock_interruptible(struct mutex *lock)
{
	int ret;

	might_sleep();
	ret =  __mutex_fastpath_lock_retval
			(&lock->count, __mutex_lock_interruptible_slowpath);
	if (!ret)
		mutex_set_owner(lock);

	return ret;
}

EXPORT_SYMBOL(mutex_lock_interruptible);

int __sched mutex_lock_killable(struct mutex *lock)
{
	int ret;

	might_sleep();
	ret = __mutex_fastpath_lock_retval
			(&lock->count, __mutex_lock_killable_slowpath);
	if (!ret)
		mutex_set_owner(lock);

	return ret;
}
EXPORT_SYMBOL(mutex_lock_killable);

static __used noinline void __sched
__mutex_lock_slowpath(atomic_t *lock_count)
{
	struct mutex *lock = container_of(lock_count, struct mutex, count);

	__mutex_lock_common(lock, TASK_UNINTERRUPTIBLE, 0, _RET_IP_);
}

static noinline int __sched
__mutex_lock_killable_slowpath(atomic_t *lock_count)
{
	struct mutex *lock = container_of(lock_count, struct mutex, count);

	return __mutex_lock_common(lock, TASK_KILLABLE, 0, _RET_IP_);
}

static noinline int __sched
__mutex_lock_interruptible_slowpath(atomic_t *lock_count)
{
	struct mutex *lock = container_of(lock_count, struct mutex, count);

	return __mutex_lock_common(lock, TASK_INTERRUPTIBLE, 0, _RET_IP_);
}
#endif

/*
 * Spinlock based trylock, we take the spinlock and check whether we
 * can get the lock:
 */
static inline int __mutex_trylock_slowpath(atomic_t *lock_count)
{
	struct mutex *lock = container_of(lock_count, struct mutex, count);
	unsigned long flags;
	int prev;

	spin_lock_mutex(&lock->wait_lock, flags);

	prev = atomic_xchg(&lock->count, -1);
	if (likely(prev == 1)) {
		mutex_set_owner(lock);
		mutex_acquire(&lock->dep_map, 0, 1, _RET_IP_);
	}

	/* Set it back to 0 if there are no waiters: */
	if (likely(list_empty(&lock->wait_list)))
		atomic_set(&lock->count, 0);

	spin_unlock_mutex(&lock->wait_lock, flags);

	return prev == 1;
}

/**
 * mutex_trylock - try to acquire the mutex, without waiting
 * @lock: the mutex to be acquired
 *
 * Try to acquire the mutex atomically. Returns 1 if the mutex
 * has been acquired successfully, and 0 on contention.
 *
 * NOTE: this function follows the spin_trylock() convention, so
 * it is negated from the down_trylock() return values! Be careful
 * about this when converting semaphore users to mutexes.
 *
 * This function must not be used in interrupt context. The
 * mutex must be released by the same task that acquired it.
 */
int __sched mutex_trylock(struct mutex *lock)
{
	int ret;

	ret = __mutex_fastpath_trylock(&lock->count, __mutex_trylock_slowpath);
	if (ret)
		mutex_set_owner(lock);

	return ret;
}
EXPORT_SYMBOL(mutex_trylock);

/**
 * atomic_dec_and_mutex_lock - return holding mutex if we dec to 0
 * @cnt: the atomic which we are to dec
 * @lock: the mutex to return holding if we dec to 0
 *
 * return true and hold lock if we dec to 0, return false otherwise
 */
int atomic_dec_and_mutex_lock(atomic_t *cnt, struct mutex *lock)
{
	/* dec if we can't possibly hit 0 */
	if (atomic_add_unless(cnt, -1, 1))
		return 0;
	/* we might hit 0, so take the lock */
	mutex_lock(lock);
	if (!atomic_dec_and_test(cnt)) {
		/* when we actually did the dec, we didn't hit 0 */
		mutex_unlock(lock);
		return 0;
	}
	/* we hit 0, and we hold the lock */
	return 1;
}
EXPORT_SYMBOL(atomic_dec_and_mutex_lock);
id=ac331d158e198d2a91a5b0a3ec4ca9991fdb57af'>ac331d158e19
0ab4dc92278a
61df47c8da1b
0ab4dc92278a


785042f2e275
ac331d158e19

0ab4dc92278a

ac331d158e19
0ab4dc92278a






0ab4dc92278a


0ab4dc92278a

a06a4dc3a082
0ab4dc92278a

a06a4dc3a082





0ab4dc92278a
a06a4dc3a082
0ab4dc92278a



785042f2e275
a06a4dc3a082
879669961b11
a06a4dc3a082

0ab4dc92278a

a06a4dc3a082

0ab4dc92278a
0ab4dc92278a

0ab4dc92278a

1da177e4c3f4
a98f0dd34d94


1da177e4c3f4



1da177e4c3f4
785042f2e275
9d944ef32e83
1da177e4c3f4
60be6b9a41cb
784680336b61
1da177e4c3f4
ccd4b65aef4b
784680336b61
0ab4dc92278a
1da177e4c3f4
8cdd4936c17b
0ab4dc92278a


a98f0dd34d94
a98f0dd34d94
a98f0dd34d94


784680336b61

d0bd587a8096











1da177e4c3f4
d0bd587a8096
a98f0dd34d94
784680336b61
0ab4dc92278a
784680336b61
ccd4b65aef4b
a98f0dd34d94
1da177e4c3f4
785042f2e275


















1da177e4c3f4
17f60a7da150













































































1da177e4c3f4




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
519
520
521
522
523
524
525
526
527
528
529
530
531
532
533
534
535
536
537
538
539
540
541
542
543
544
545
546
547
548
549
550
551
552
553
554
555
556
557
558
559
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
591
592
593
594
595
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
646
647
648
649
650
651
652
653
654
655
656
657
658
659
660
661
662
663
664
665
666
667
668
669
670
671
672
673
674
675
676
677
678
679
680
681



















                                                                         




                           
                       
                             
                       
                       
                          




                            
                           

                           
                        

                        

                                



                                           





                                                              
                                   
 
                     





                                                     





                                                            








                                                     












                                                                

                                                                 




                                                                     

 
   

                                                     

                                                              









                                                                        
                                                     




                                          









                                                                      



                                                          















                                                                                
                                        


                                                                            

                                        



                                             

                                                          
                                                                               
 


                                     
                                
                           
 





                                                       
                         

                   

                                                  


                                                               
                                                    
 





                                                                               










                                                                          







                                                       

                          


                                                                    

                          
     
                                  
                 

 
                                                                      

                          
                                       

                    
 

                                                          








                                                                  

 




                                                  
 



                                                                       




                                                                        
                                  








                                                                                








                                                                             

         
                               



                                    
                                                           
 

                                                                 
                                                  
                  



                                                                   
                                  





                                                                      

                         
                                                       
                      
 


                              
                                 
                           

                                               
                                       
         

 



                                                                               
                                                                      
   
                                                                     




                                                 
                                                                           




                                                      





                                                                              
                                                                        
                                                            


                                        
                                     
 
                          

                    
                                 








                                                                      
                                       







                                         
         
                                                           
                   
 
                                               
 


























                                                                      
                                     


                               
                                              
 
   
                                                                       
                                                          


                                                                             
   
                                                                     

                                  
                                        




                                                



                                                                              
   
                                                          
 

                    


                               
                                  
                                        

                                






                                                                       

                                                                           

                         
 
                                                        


                       










                                                  
 
   
                                                                


                                     
                                            
  
                                                                   


                                                                   
      

                                                                              

                                         
                                                                     






                                                          


                        

   
                                                           

                                                                 





                                                                       
  
                                                                       



                                                                  
      
                                                             
                                                                                

                                                                  

                                

                          
 

   

                                                          
                                                               


                                                                          



                                                                     
   
      
                                                                        
 
                                         
                       
 
                      
                                      
                         
 
                                                     


                                
 
                                   


                                                

                                                                     











                                                                    
                                   
          
                                  
    
                                               
       
                        
                      
 


















                                                                         
 













































































                                                                                                        




                                                              
/*
	kmod, the new module loader (replaces kerneld)
	Kirk Petersen

	Reorganized not to be a daemon by Adam Richter, with guidance
	from Greg Zornetzer.

	Modified to avoid chroot and file sharing problems.
	Mikael Pettersson

	Limit the concurrent number of kmod modprobes to catch loops from
	"modprobe needs a service that is in a module".
	Keith Owens <kaos@ocs.com.au> December 1999

	Unblock all signals when we exec a usermode process.
	Shuu Yamaguchi <shuu@wondernetworkresources.com> December 2000

	call_usermodehelper wait flag, and remove exec_usermodehelper.
	Rusty Russell <rusty@rustcorp.com.au>  Jan 2003
*/
#include <linux/module.h>
#include <linux/sched.h>
#include <linux/syscalls.h>
#include <linux/unistd.h>
#include <linux/kmod.h>
#include <linux/slab.h>
#include <linux/completion.h>
#include <linux/cred.h>
#include <linux/file.h>
#include <linux/fdtable.h>
#include <linux/workqueue.h>
#include <linux/security.h>
#include <linux/mount.h>
#include <linux/kernel.h>
#include <linux/init.h>
#include <linux/resource.h>
#include <linux/notifier.h>
#include <linux/suspend.h>
#include <linux/rwsem.h>
#include <asm/uaccess.h>

#include <trace/events/module.h>

extern int max_threads;

static struct workqueue_struct *khelper_wq;

#define CAP_BSET	(void *)1
#define CAP_PI		(void *)2

static kernel_cap_t usermodehelper_bset = CAP_FULL_SET;
static kernel_cap_t usermodehelper_inheritable = CAP_FULL_SET;
static DEFINE_SPINLOCK(umh_sysctl_lock);
static DECLARE_RWSEM(umhelper_sem);

#ifdef CONFIG_MODULES

/*
	modprobe_path is set via /proc/sys.
*/
char modprobe_path[KMOD_PATH_LEN] = "/sbin/modprobe";

static void free_modprobe_argv(struct subprocess_info *info)
{
	kfree(info->argv[3]); /* check call_modprobe() */
	kfree(info->argv);
}

static int call_modprobe(char *module_name, int wait)
{
	static char *envp[] = {
		"HOME=/",
		"TERM=linux",
		"PATH=/sbin:/usr/sbin:/bin:/usr/bin",
		NULL
	};

	char **argv = kmalloc(sizeof(char *[5]), GFP_KERNEL);
	if (!argv)
		goto out;

	module_name = kstrdup(module_name, GFP_KERNEL);
	if (!module_name)
		goto free_argv;

	argv[0] = modprobe_path;
	argv[1] = "-q";
	argv[2] = "--";
	argv[3] = module_name;	/* check free_modprobe_argv() */
	argv[4] = NULL;

	return call_usermodehelper_fns(modprobe_path, argv, envp,
		wait | UMH_KILLABLE, NULL, free_modprobe_argv, NULL);
free_argv:
	kfree(argv);
out:
	return -ENOMEM;
}

/**
 * __request_module - try to load a kernel module
 * @wait: wait (or not) for the operation to complete
 * @fmt: printf style format string for the name of the module
 * @...: arguments as specified in the format string
 *
 * Load a module using the user mode module loader. The function returns
 * zero on success or a negative errno code on failure. Note that a
 * successful module load does not mean the module did not then unload
 * and exit on an error of its own. Callers must check that the service
 * they requested is now available not blindly invoke it.
 *
 * If module auto-loading support is disabled then this function
 * becomes a no-operation.
 */
int __request_module(bool wait, const char *fmt, ...)
{
	va_list args;
	char module_name[MODULE_NAME_LEN];
	unsigned int max_modprobes;
	int ret;
	static atomic_t kmod_concurrent = ATOMIC_INIT(0);
#define MAX_KMOD_CONCURRENT 50	/* Completely arbitrary value - KAO */
	static int kmod_loop_msg;

	va_start(args, fmt);
	ret = vsnprintf(module_name, MODULE_NAME_LEN, fmt, args);
	va_end(args);
	if (ret >= MODULE_NAME_LEN)
		return -ENAMETOOLONG;

	ret = security_kernel_module_request(module_name);
	if (ret)
		return ret;

	/* If modprobe needs a service that is in a module, we get a recursive
	 * loop.  Limit the number of running kmod threads to max_threads/2 or
	 * MAX_KMOD_CONCURRENT, whichever is the smaller.  A cleaner method
	 * would be to run the parents of this process, counting how many times
	 * kmod was invoked.  That would mean accessing the internals of the
	 * process tables to get the command line, proc_pid_cmdline is static
	 * and it is not worth changing the proc code just to handle this case. 
	 * KAO.
	 *
	 * "trace the ppid" is simple, but will fail if someone's
	 * parent exits.  I think this is as good as it gets. --RR
	 */
	max_modprobes = min(max_threads/2, MAX_KMOD_CONCURRENT);
	atomic_inc(&kmod_concurrent);
	if (atomic_read(&kmod_concurrent) > max_modprobes) {
		/* We may be blaming an innocent here, but unlikely */
		if (kmod_loop_msg < 5) {
			printk(KERN_ERR
			       "request_module: runaway loop modprobe %s\n",
			       module_name);
			kmod_loop_msg++;
		}
		atomic_dec(&kmod_concurrent);
		return -ENOMEM;
	}

	trace_module_request(module_name, wait, _RET_IP_);

	ret = call_modprobe(module_name, wait ? UMH_WAIT_PROC : UMH_WAIT_EXEC);

	atomic_dec(&kmod_concurrent);
	return ret;
}
EXPORT_SYMBOL(__request_module);
#endif /* CONFIG_MODULES */

/*
 * This is the task which runs the usermode application
 */
static int ____call_usermodehelper(void *data)
{
	struct subprocess_info *sub_info = data;
	struct cred *new;
	int retval;

	spin_lock_irq(&current->sighand->siglock);
	flush_signal_handlers(current, 1);
	spin_unlock_irq(&current->sighand->siglock);

	/* We can run anywhere, unlike our parent keventd(). */
	set_cpus_allowed_ptr(current, cpu_all_mask);

	/*
	 * Our parent is keventd, which runs with elevated scheduling priority.
	 * Avoid propagating that into the userspace child.
	 */
	set_user_nice(current, 0);

	retval = -ENOMEM;
	new = prepare_kernel_cred(current);
	if (!new)
		goto fail;

	spin_lock(&umh_sysctl_lock);
	new->cap_bset = cap_intersect(usermodehelper_bset, new->cap_bset);
	new->cap_inheritable = cap_intersect(usermodehelper_inheritable,
					     new->cap_inheritable);
	spin_unlock(&umh_sysctl_lock);

	if (sub_info->init) {
		retval = sub_info->init(sub_info, new);
		if (retval) {
			abort_creds(new);
			goto fail;
		}
	}

	commit_creds(new);

	retval = kernel_execve(sub_info->path,
			       (const char *const *)sub_info->argv,
			       (const char *const *)sub_info->envp);

	/* Exec failed? */
fail:
	sub_info->retval = retval;
	return 0;
}

static void call_usermodehelper_freeinfo(struct subprocess_info *info)
{
	if (info->cleanup)
		(*info->cleanup)(info);
	kfree(info);
}

static void umh_complete(struct subprocess_info *sub_info)
{
	struct completion *comp = xchg(&sub_info->complete, NULL);
	/*
	 * See call_usermodehelper_exec(). If xchg() returns NULL
	 * we own sub_info, the UMH_KILLABLE caller has gone away.
	 */
	if (comp)
		complete(comp);
	else
		call_usermodehelper_freeinfo(sub_info);
}

/* Keventd can't block, but this (a child) can. */
static int wait_for_helper(void *data)
{
	struct subprocess_info *sub_info = data;
	pid_t pid;

	/* If SIGCLD is ignored sys_wait4 won't populate the status. */
	spin_lock_irq(&current->sighand->siglock);
	current->sighand->action[SIGCHLD-1].sa.sa_handler = SIG_DFL;
	spin_unlock_irq(&current->sighand->siglock);

	pid = kernel_thread(____call_usermodehelper, sub_info, SIGCHLD);
	if (pid < 0) {
		sub_info->retval = pid;
	} else {
		int ret = -ECHILD;
		/*
		 * Normally it is bogus to call wait4() from in-kernel because
		 * wait4() wants to write the exit code to a userspace address.
		 * But wait_for_helper() always runs as keventd, and put_user()
		 * to a kernel address works OK for kernel threads, due to their
		 * having an mm_segment_t which spans the entire address space.
		 *
		 * Thus the __user pointer cast is valid here.
		 */
		sys_wait4(pid, (int __user *)&ret, 0, NULL);

		/*
		 * If ret is 0, either ____call_usermodehelper failed and the
		 * real error code is already in sub_info->retval or
		 * sub_info->retval is 0 anyway, so don't mess with it then.
		 */
		if (ret)
			sub_info->retval = ret;
	}

	umh_complete(sub_info);
	return 0;
}

/* This is run by khelper thread  */
static void __call_usermodehelper(struct work_struct *work)
{
	struct subprocess_info *sub_info =
		container_of(work, struct subprocess_info, work);
	int wait = sub_info->wait & ~UMH_KILLABLE;
	pid_t pid;

	/* CLONE_VFORK: wait until the usermode helper has execve'd
	 * successfully We need the data structures to stay around
	 * until that is done.  */
	if (wait == UMH_WAIT_PROC)
		pid = kernel_thread(wait_for_helper, sub_info,
				    CLONE_FS | CLONE_FILES | SIGCHLD);
	else
		pid = kernel_thread(____call_usermodehelper, sub_info,
				    CLONE_VFORK | SIGCHLD);

	switch (wait) {
	case UMH_NO_WAIT:
		call_usermodehelper_freeinfo(sub_info);
		break;

	case UMH_WAIT_PROC:
		if (pid > 0)
			break;
		/* FALLTHROUGH */
	case UMH_WAIT_EXEC:
		if (pid < 0)
			sub_info->retval = pid;
		umh_complete(sub_info);
	}
}

/*
 * If set, call_usermodehelper_exec() will exit immediately returning -EBUSY
 * (used for preventing user land processes from being created after the user
 * land has been frozen during a system-wide hibernation or suspend operation).
 * Should always be manipulated under umhelper_sem acquired for write.
 */
static enum umh_disable_depth usermodehelper_disabled = UMH_DISABLED;

/* Number of helpers running */
static atomic_t running_helpers = ATOMIC_INIT(0);

/*
 * Wait queue head used by usermodehelper_disable() to wait for all running
 * helpers to finish.
 */
static DECLARE_WAIT_QUEUE_HEAD(running_helpers_waitq);

/*
 * Used by usermodehelper_read_lock_wait() to wait for usermodehelper_disabled
 * to become 'false'.
 */
static DECLARE_WAIT_QUEUE_HEAD(usermodehelper_disabled_waitq);

/*
 * Time to wait for running_helpers to become zero before the setting of
 * usermodehelper_disabled in usermodehelper_disable() fails
 */
#define RUNNING_HELPERS_TIMEOUT	(5 * HZ)

int usermodehelper_read_trylock(void)
{
	DEFINE_WAIT(wait);
	int ret = 0;

	down_read(&umhelper_sem);
	for (;;) {
		prepare_to_wait(&usermodehelper_disabled_waitq, &wait,
				TASK_INTERRUPTIBLE);
		if (!usermodehelper_disabled)
			break;

		if (usermodehelper_disabled == UMH_DISABLED)
			ret = -EAGAIN;

		up_read(&umhelper_sem);

		if (ret)
			break;

		schedule();
		try_to_freeze();

		down_read(&umhelper_sem);
	}
	finish_wait(&usermodehelper_disabled_waitq, &wait);
	return ret;
}
EXPORT_SYMBOL_GPL(usermodehelper_read_trylock);

long usermodehelper_read_lock_wait(long timeout)
{
	DEFINE_WAIT(wait);

	if (timeout < 0)
		return -EINVAL;

	down_read(&umhelper_sem);
	for (;;) {
		prepare_to_wait(&usermodehelper_disabled_waitq, &wait,
				TASK_UNINTERRUPTIBLE);
		if (!usermodehelper_disabled)
			break;

		up_read(&umhelper_sem);

		timeout = schedule_timeout(timeout);
		if (!timeout)
			break;

		down_read(&umhelper_sem);
	}
	finish_wait(&usermodehelper_disabled_waitq, &wait);
	return timeout;
}
EXPORT_SYMBOL_GPL(usermodehelper_read_lock_wait);

void usermodehelper_read_unlock(void)
{
	up_read(&umhelper_sem);
}
EXPORT_SYMBOL_GPL(usermodehelper_read_unlock);

/**
 * __usermodehelper_set_disable_depth - Modify usermodehelper_disabled.
 * @depth: New value to assign to usermodehelper_disabled.
 *
 * Change the value of usermodehelper_disabled (under umhelper_sem locked for
 * writing) and wakeup tasks waiting for it to change.
 */
void __usermodehelper_set_disable_depth(enum umh_disable_depth depth)
{
	down_write(&umhelper_sem);
	usermodehelper_disabled = depth;
	wake_up(&usermodehelper_disabled_waitq);
	up_write(&umhelper_sem);
}

/**
 * __usermodehelper_disable - Prevent new helpers from being started.
 * @depth: New value to assign to usermodehelper_disabled.
 *
 * Set usermodehelper_disabled to @depth and wait for running helpers to exit.
 */
int __usermodehelper_disable(enum umh_disable_depth depth)
{
	long retval;

	if (!depth)
		return -EINVAL;

	down_write(&umhelper_sem);
	usermodehelper_disabled = depth;
	up_write(&umhelper_sem);

	/*
	 * From now on call_usermodehelper_exec() won't start any new
	 * helpers, so it is sufficient if running_helpers turns out to
	 * be zero at one point (it may be increased later, but that
	 * doesn't matter).
	 */
	retval = wait_event_timeout(running_helpers_waitq,
					atomic_read(&running_helpers) == 0,
					RUNNING_HELPERS_TIMEOUT);
	if (retval)
		return 0;

	__usermodehelper_set_disable_depth(UMH_ENABLED);
	return -EAGAIN;
}

static void helper_lock(void)
{
	atomic_inc(&running_helpers);
	smp_mb__after_atomic_inc();
}

static void helper_unlock(void)
{
	if (atomic_dec_and_test(&running_helpers))
		wake_up(&running_helpers_waitq);
}

/**
 * call_usermodehelper_setup - prepare to call a usermode helper
 * @path: path to usermode executable
 * @argv: arg vector for process
 * @envp: environment for process
 * @gfp_mask: gfp mask for memory allocation
 *
 * Returns either %NULL on allocation failure, or a subprocess_info
 * structure.  This should be passed to call_usermodehelper_exec to
 * exec the process and free the structure.
 */
static
struct subprocess_info *call_usermodehelper_setup(char *path, char **argv,
						  char **envp, gfp_t gfp_mask)
{
	struct subprocess_info *sub_info;
	sub_info = kzalloc(sizeof(struct subprocess_info), gfp_mask);
	if (!sub_info)
		goto out;

	INIT_WORK(&sub_info->work, __call_usermodehelper);
	sub_info->path = path;
	sub_info->argv = argv;
	sub_info->envp = envp;
  out:
	return sub_info;
}

/**
 * call_usermodehelper_setfns - set a cleanup/init function
 * @info: a subprocess_info returned by call_usermodehelper_setup
 * @cleanup: a cleanup function
 * @init: an init function
 * @data: arbitrary context sensitive data
 *
 * The init function is used to customize the helper process prior to
 * exec.  A non-zero return code causes the process to error out, exit,
 * and return the failure to the calling process
 *
 * The cleanup function is just before ethe subprocess_info is about to
 * be freed.  This can be used for freeing the argv and envp.  The
 * Function must be runnable in either a process context or the
 * context in which call_usermodehelper_exec is called.
 */
static
void call_usermodehelper_setfns(struct subprocess_info *info,
		    int (*init)(struct subprocess_info *info, struct cred *new),
		    void (*cleanup)(struct subprocess_info *info),
		    void *data)
{
	info->cleanup = cleanup;
	info->init = init;
	info->data = data;
}

/**
 * call_usermodehelper_exec - start a usermode application
 * @sub_info: information about the subprocessa
 * @wait: wait for the application to finish and return status.
 *        when -1 don't wait at all, but you get no useful error back when
 *        the program couldn't be exec'ed. This makes it safe to call
 *        from interrupt context.
 *
 * Runs a user-space application.  The application is started
 * asynchronously if wait is not set, and runs as a child of keventd.
 * (ie. it runs with full root capabilities).
 */
static
int call_usermodehelper_exec(struct subprocess_info *sub_info, int wait)
{
	DECLARE_COMPLETION_ONSTACK(done);
	int retval = 0;

	helper_lock();
	if (sub_info->path[0] == '\0')
		goto out;

	if (!khelper_wq || usermodehelper_disabled) {
		retval = -EBUSY;
		goto out;
	}

	sub_info->complete = &done;
	sub_info->wait = wait;

	queue_work(khelper_wq, &sub_info->work);
	if (wait == UMH_NO_WAIT)	/* task has freed sub_info */
		goto unlock;

	if (wait & UMH_KILLABLE) {
		retval = wait_for_completion_killable(&done);
		if (!retval)
			goto wait_done;

		/* umh_complete() will see NULL and free sub_info */
		if (xchg(&sub_info->complete, NULL))
			goto unlock;
		/* fallthrough, umh_complete() was already called */
	}

	wait_for_completion(&done);
wait_done:
	retval = sub_info->retval;
out:
	call_usermodehelper_freeinfo(sub_info);
unlock:
	helper_unlock();
	return retval;
}

int call_usermodehelper_fns(
	char *path, char **argv, char **envp, int wait,
	int (*init)(struct subprocess_info *info, struct cred *new),
	void (*cleanup)(struct subprocess_info *), void *data)
{
	struct subprocess_info *info;
	gfp_t gfp_mask = (wait == UMH_NO_WAIT) ? GFP_ATOMIC : GFP_KERNEL;

	info = call_usermodehelper_setup(path, argv, envp, gfp_mask);

	if (info == NULL)
		return -ENOMEM;

	call_usermodehelper_setfns(info, init, cleanup, data);

	return call_usermodehelper_exec(info, wait);
}
EXPORT_SYMBOL(call_usermodehelper_fns);

static int proc_cap_handler(struct ctl_table *table, int write,
			 void __user *buffer, size_t *lenp, loff_t *ppos)
{
	struct ctl_table t;
	unsigned long cap_array[_KERNEL_CAPABILITY_U32S];
	kernel_cap_t new_cap;
	int err, i;

	if (write && (!capable(CAP_SETPCAP) ||
		      !capable(CAP_SYS_MODULE)))
		return -EPERM;

	/*
	 * convert from the global kernel_cap_t to the ulong array to print to
	 * userspace if this is a read.
	 */
	spin_lock(&umh_sysctl_lock);
	for (i = 0; i < _KERNEL_CAPABILITY_U32S; i++)  {
		if (table->data == CAP_BSET)
			cap_array[i] = usermodehelper_bset.cap[i];
		else if (table->data == CAP_PI)
			cap_array[i] = usermodehelper_inheritable.cap[i];
		else
			BUG();
	}
	spin_unlock(&umh_sysctl_lock);

	t = *table;
	t.data = &cap_array;

	/*
	 * actually read or write and array of ulongs from userspace.  Remember
	 * these are least significant 32 bits first
	 */
	err = proc_doulongvec_minmax(&t, write, buffer, lenp, ppos);
	if (err < 0)
		return err;

	/*
	 * convert from the sysctl array of ulongs to the kernel_cap_t
	 * internal representation
	 */
	for (i = 0; i < _KERNEL_CAPABILITY_U32S; i++)
		new_cap.cap[i] = cap_array[i];

	/*
	 * Drop everything not in the new_cap (but don't add things)
	 */
	spin_lock(&umh_sysctl_lock);
	if (write) {
		if (table->data == CAP_BSET)
			usermodehelper_bset = cap_intersect(usermodehelper_bset, new_cap);
		if (table->data == CAP_PI)
			usermodehelper_inheritable = cap_intersect(usermodehelper_inheritable, new_cap);
	}
	spin_unlock(&umh_sysctl_lock);

	return 0;
}

struct ctl_table usermodehelper_table[] = {
	{
		.procname	= "bset",
		.data		= CAP_BSET,
		.maxlen		= _KERNEL_CAPABILITY_U32S * sizeof(unsigned long),
		.mode		= 0600,
		.proc_handler	= proc_cap_handler,
	},
	{
		.procname	= "inheritable",
		.data		= CAP_PI,
		.maxlen		= _KERNEL_CAPABILITY_U32S * sizeof(unsigned long),
		.mode		= 0600,
		.proc_handler	= proc_cap_handler,
	},
	{ }
};

void __init usermodehelper_init(void)
{
	khelper_wq = create_singlethread_workqueue("khelper");
	BUG_ON(!khelper_wq);
}