summaryrefslogtreecommitdiffstats
path: root/rtmutex-implement-lock-replacement-functions.patch
blob: 93366a620b41d088cd7c5fcb062f9327dba4b7ae (plain)
1
2
3
4
5
6
7
8
9
10
11
12
13
14
15
16
17
18
19
20
21
22
23
24
25
26
27
28
29
30
31
32
33
34
35
36
37
38
39
40
41
42
43
44
45
46
47
48
49
50
51
52
53
54
55
56
57
58
59
60
61
62
63
64
65
66
67
68
69
70
71
72
73
74
75
76
77
78
79
80
81
82
83
84
85
86
87
88
89
90
91
92
93
94
95
96
97
98
99
100
101
102
103
104
105
106
107
108
109
110
111
112
113
114
115
116
117
118
119
120
121
122
123
124
125
126
127
128
129
130
131
132
133
134
135
136
137
138
139
140
141
142
143
144
145
146
147
148
149
150
151
152
153
154
155
156
157
158
159
160
161
162
163
164
165
166
167
168
169
170
171
172
173
174
175
176
177
178
179
180
181
182
183
184
185
186
187
188
189
190
191
192
193
194
195
196
197
198
199
200
201
202
203
204
205
206
207
208
209
210
211
212
213
214
215
216
217
218
219
220
221
222
223
224
225
226
227
228
229
230
231
232
233
234
235
236
237
238
239
240
241
242
243
244
245
246
247
248
249
250
251
252
253
254
255
256
257
258
259
260
261
262
263
264
265
266
267
268
269
270
271
272
273
274
275
276
277
278
279
280
281
282
283
284
285
286
287
288
289
290
291
292
293
294
295
296
297
298
299
300
301
302
303
304
305
306
307
308
309
310
311
312
313
314
315
316
317
318
319
320
321
322
323
324
325
326
327
328
329
330
331
332
333
334
335
336
337
338
339
340
341
342
343
344
345
346
347
348
349
350
351
352
353
354
355
356
357
358
359
360
361
362
363
364
365
366
367
368
369
370
371
372
373
374
375
376
377
378
379
380
381
382
383
384
385
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
682
683
684
685
686
687
688
689
690
691
692
693
694
695
696
697
698
699
700
701
702
703
704
705
706
707
708
709
710
711
712
713
714
715
716
717
718
719
720
721
722
723
724
725
726
727
728
729
730
731
732
733
734
735
736
737
738
739
740
741
742
743
744
745
746
747
748
749
750
751
752
753
754
755
756
757
758
759
760
761
762
763
764
765
766
767
768
769
770
771
772
773
774
775
776
777
778
779
780
781
782
783
784
785
786
787
788
789
790
791
792
793
794
795
796
797
798
799
800
801
802
803
804
805
806
807
808
809
810
811
812
813
814
815
816
817
818
819
820
821
822
823
824
825
826
827
828
829
830
831
832
833
834
835
836
837
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
872
873
874
875
876
877
878
879
880
881
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
940
941
942
943
944
945
946
947
948
949
950
951
952
953
954
955
956
957
958
959
960
961
962
963
964
965
966
967
968
969
970
971
972
973
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
1011
1012
1013
1014
1015
1016
1017
1018
1019
1020
1021
1022
1023
1024
1025
1026
1027
1028
1029
1030
1031
1032
1033
1034
1035
1036
1037
1038
1039
1040
1041
1042
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
From 32cb8ec402e4f42eeebaf0cc9df7f76597561fcf Mon Sep 17 00:00:00 2001
From: Thomas Gleixner <tglx@linutronix.de>
Date: Sun, 26 Jul 2009 18:27:32 +0200
Subject: [PATCH] rtmutex: implement lock replacement functions

commit 012bf7321ab031b80c527753411bd54217a61ab9 in tip.

Implement the base infrastructure to replace spinlocks for -rt.

Signed-off-by: Thomas Gleixner <tglx@linutronix.de>
Signed-off-by: Paul Gortmaker <paul.gortmaker@windriver.com>
---
 include/linux/rtmutex.h |    2 +
 include/linux/sched.h   |    1 +
 kernel/rtmutex-debug.c  |  107 ++++-------
 kernel/rtmutex.c        |  467 +++++++++++++++++++++++++++++++++++++++++------
 lib/kernel_lock.c       |    2 +-
 5 files changed, 451 insertions(+), 128 deletions(-)

diff --git a/include/linux/rtmutex.h b/include/linux/rtmutex.h
index 8d522ff..fc4b22e 100644
--- a/include/linux/rtmutex.h
+++ b/include/linux/rtmutex.h
@@ -90,6 +90,8 @@ extern void rt_mutex_destroy(struct rt_mutex *lock);
 extern void rt_mutex_lock(struct rt_mutex *lock);
 extern int rt_mutex_lock_interruptible(struct rt_mutex *lock,
 						int detect_deadlock);
+extern int rt_mutex_lock_killable(struct rt_mutex *lock,
+				  int detect_deadlock);
 extern int rt_mutex_timed_lock(struct rt_mutex *lock,
 					struct hrtimer_sleeper *timeout,
 					int detect_deadlock);
diff --git a/include/linux/sched.h b/include/linux/sched.h
index 2ef88d7..8550369 100644
--- a/include/linux/sched.h
+++ b/include/linux/sched.h
@@ -175,6 +175,7 @@ print_cfs_rq(struct seq_file *m, int cpu, struct cfs_rq *cfs_rq)
 {
 }
 #endif
+extern struct semaphore kernel_sem;
 
 /*
  * Task state bitmask. NOTE! These bits are also
diff --git a/kernel/rtmutex-debug.c b/kernel/rtmutex-debug.c
index ddabb54..2381c7a 100644
--- a/kernel/rtmutex-debug.c
+++ b/kernel/rtmutex-debug.c
@@ -29,61 +29,6 @@
 
 #include "rtmutex_common.h"
 
-# define TRACE_WARN_ON(x)			WARN_ON(x)
-# define TRACE_BUG_ON(x)			BUG_ON(x)
-
-# define TRACE_OFF()						\
-do {								\
-	if (rt_trace_on) {					\
-		rt_trace_on = 0;				\
-		console_verbose();				\
-		if (raw_spin_is_locked(&current->pi_lock))	\
-			raw_spin_unlock(&current->pi_lock);	\
-	}							\
-} while (0)
-
-# define TRACE_OFF_NOLOCK()					\
-do {								\
-	if (rt_trace_on) {					\
-		rt_trace_on = 0;				\
-		console_verbose();				\
-	}							\
-} while (0)
-
-# define TRACE_BUG_LOCKED()			\
-do {						\
-	TRACE_OFF();				\
-	BUG();					\
-} while (0)
-
-# define TRACE_WARN_ON_LOCKED(c)		\
-do {						\
-	if (unlikely(c)) {			\
-		TRACE_OFF();			\
-		WARN_ON(1);			\
-	}					\
-} while (0)
-
-# define TRACE_BUG_ON_LOCKED(c)			\
-do {						\
-	if (unlikely(c))			\
-		TRACE_BUG_LOCKED();		\
-} while (0)
-
-#ifdef CONFIG_SMP
-# define SMP_TRACE_BUG_ON_LOCKED(c)	TRACE_BUG_ON_LOCKED(c)
-#else
-# define SMP_TRACE_BUG_ON_LOCKED(c)	do { } while (0)
-#endif
-
-/*
- * deadlock detection flag. We turn it off when we detect
- * the first problem because we dont want to recurse back
- * into the tracing code when doing error printk or
- * executing a BUG():
- */
-static int rt_trace_on = 1;
-
 static void printk_task(struct task_struct *p)
 {
 	if (p)
@@ -111,8 +56,8 @@ static void printk_lock(struct rt_mutex *lock, int print_owner)
 
 void rt_mutex_debug_task_free(struct task_struct *task)
 {
-	WARN_ON(!plist_head_empty(&task->pi_waiters));
-	WARN_ON(task->pi_blocked_on);
+	DEBUG_LOCKS_WARN_ON(!plist_head_empty(&task->pi_waiters));
+	DEBUG_LOCKS_WARN_ON(task->pi_blocked_on);
 }
 
 /*
@@ -125,7 +70,7 @@ void debug_rt_mutex_deadlock(int detect, struct rt_mutex_waiter *act_waiter,
 {
 	struct task_struct *task;
 
-	if (!rt_trace_on || detect || !act_waiter)
+	if (!debug_locks || detect || !act_waiter)
 		return;
 
 	task = rt_mutex_owner(act_waiter->lock);
@@ -139,7 +84,7 @@ void debug_rt_mutex_print_deadlock(struct rt_mutex_waiter *waiter)
 {
 	struct task_struct *task;
 
-	if (!waiter->deadlock_lock || !rt_trace_on)
+	if (!waiter->deadlock_lock || !debug_locks)
 		return;
 
 	rcu_read_lock();
@@ -149,7 +94,8 @@ void debug_rt_mutex_print_deadlock(struct rt_mutex_waiter *waiter)
 		return;
 	}
 
-	TRACE_OFF_NOLOCK();
+	if (!debug_locks_off())
+		return;
 
 	printk("\n============================================\n");
 	printk(  "[ BUG: circular locking deadlock detected! ]\n");
@@ -180,7 +126,6 @@ void debug_rt_mutex_print_deadlock(struct rt_mutex_waiter *waiter)
 
 	printk("[ turning off deadlock detection."
 	       "Please report this trace. ]\n\n");
-	local_irq_disable();
 }
 
 void debug_rt_mutex_lock(struct rt_mutex *lock)
@@ -189,7 +134,8 @@ void debug_rt_mutex_lock(struct rt_mutex *lock)
 
 void debug_rt_mutex_unlock(struct rt_mutex *lock)
 {
-	TRACE_WARN_ON_LOCKED(rt_mutex_owner(lock) != current);
+	if (debug_locks)
+		DEBUG_LOCKS_WARN_ON(rt_mutex_owner(lock) != current);
 }
 
 void
@@ -199,7 +145,7 @@ debug_rt_mutex_proxy_lock(struct rt_mutex *lock, struct task_struct *powner)
 
 void debug_rt_mutex_proxy_unlock(struct rt_mutex *lock)
 {
-	TRACE_WARN_ON_LOCKED(!rt_mutex_owner(lock));
+	DEBUG_LOCKS_WARN_ON(!rt_mutex_owner(lock));
 }
 
 void debug_rt_mutex_init_waiter(struct rt_mutex_waiter *waiter)
@@ -213,9 +159,9 @@ void debug_rt_mutex_init_waiter(struct rt_mutex_waiter *waiter)
 void debug_rt_mutex_free_waiter(struct rt_mutex_waiter *waiter)
 {
 	put_pid(waiter->deadlock_task_pid);
-	TRACE_WARN_ON(!plist_node_empty(&waiter->list_entry));
-	TRACE_WARN_ON(!plist_node_empty(&waiter->pi_list_entry));
-	TRACE_WARN_ON(waiter->task);
+	DEBUG_LOCKS_WARN_ON(!plist_node_empty(&waiter->list_entry));
+	DEBUG_LOCKS_WARN_ON(!plist_node_empty(&waiter->pi_list_entry));
+	DEBUG_LOCKS_WARN_ON(waiter->task);
 	memset(waiter, 0x22, sizeof(*waiter));
 }
 
@@ -231,9 +177,36 @@ void debug_rt_mutex_init(struct rt_mutex *lock, const char *name)
 void
 rt_mutex_deadlock_account_lock(struct rt_mutex *lock, struct task_struct *task)
 {
+#ifdef CONFIG_DEBUG_PREEMPT
+	if (task->lock_count >= MAX_LOCK_STACK) {
+		if (!debug_locks_off())
+			return;
+		printk("BUG: %s/%d: lock count overflow!\n",
+			task->comm, task->pid);
+		dump_stack();
+		return;
+	}
+#ifdef CONFIG_PREEMPT_RT
+	task->owned_lock[task->lock_count] = lock;
+#endif
+	task->lock_count++;
+#endif
 }
 
 void rt_mutex_deadlock_account_unlock(struct task_struct *task)
 {
+#ifdef CONFIG_DEBUG_PREEMPT
+	if (!task->lock_count) {
+		if (!debug_locks_off())
+			return;
+		printk("BUG: %s/%d: lock count underflow!\n",
+			task->comm, task->pid);
+		dump_stack();
+		return;
+	}
+	task->lock_count--;
+#ifdef CONFIG_PREEMPT_RT
+	task->owned_lock[task->lock_count] = NULL;
+#endif
+#endif
 }
-
diff --git a/kernel/rtmutex.c b/kernel/rtmutex.c
index a960481..fe9b2fc 100644
--- a/kernel/rtmutex.c
+++ b/kernel/rtmutex.c
@@ -14,6 +14,7 @@
 #include <linux/module.h>
 #include <linux/sched.h>
 #include <linux/timer.h>
+#include <linux/semaphore.h>
 
 #include "rtmutex_common.h"
 
@@ -97,6 +98,22 @@ static inline void mark_rt_mutex_waiters(struct rt_mutex *lock)
 }
 #endif
 
+int pi_initialized;
+
+/*
+ * we initialize the wait_list runtime. (Could be done build-time and/or
+ * boot-time.)
+ */
+static inline void init_lists(struct rt_mutex *lock)
+{
+	if (unlikely(!lock->wait_list.prio_list.prev)) {
+		plist_head_init_raw(&lock->wait_list, &lock->wait_lock);
+#ifdef CONFIG_DEBUG_RT_MUTEXES
+		pi_initialized++;
+#endif
+	}
+}
+
 /*
  * Calculate task priority from the waiter list priority
  *
@@ -253,13 +270,13 @@ static int rt_mutex_adjust_prio_chain(struct task_struct *task,
 	plist_add(&waiter->list_entry, &lock->wait_list);
 
 	/* Release the task */
-	raw_spin_unlock_irqrestore(&task->pi_lock, flags);
+	raw_spin_unlock(&task->pi_lock);
 	put_task_struct(task);
 
 	/* Grab the next task */
 	task = rt_mutex_owner(lock);
 	get_task_struct(task);
-	raw_spin_lock_irqsave(&task->pi_lock, flags);
+	raw_spin_lock(&task->pi_lock);
 
 	if (waiter == rt_mutex_top_waiter(lock)) {
 		/* Boost the owner */
@@ -277,10 +294,10 @@ static int rt_mutex_adjust_prio_chain(struct task_struct *task,
 		__rt_mutex_adjust_prio(task);
 	}
 
-	raw_spin_unlock_irqrestore(&task->pi_lock, flags);
+	raw_spin_unlock(&task->pi_lock);
 
 	top_waiter = rt_mutex_top_waiter(lock);
-	raw_spin_unlock(&lock->wait_lock);
+	raw_spin_unlock_irqrestore(&lock->wait_lock, flags);
 
 	if (!detect_deadlock && waiter != top_waiter)
 		goto out_put_task;
@@ -305,7 +322,6 @@ static inline int try_to_steal_lock(struct rt_mutex *lock,
 {
 	struct task_struct *pendowner = rt_mutex_owner(lock);
 	struct rt_mutex_waiter *next;
-	unsigned long flags;
 
 	if (!rt_mutex_owner_pending(lock))
 		return 0;
@@ -313,9 +329,9 @@ static inline int try_to_steal_lock(struct rt_mutex *lock,
 	if (pendowner == task)
 		return 1;
 
-	raw_spin_lock_irqsave(&pendowner->pi_lock, flags);
+	raw_spin_lock(&pendowner->pi_lock);
 	if (task->prio >= pendowner->prio) {
-		raw_spin_unlock_irqrestore(&pendowner->pi_lock, flags);
+		raw_spin_unlock(&pendowner->pi_lock);
 		return 0;
 	}
 
@@ -325,7 +341,7 @@ static inline int try_to_steal_lock(struct rt_mutex *lock,
 	 * priority.
 	 */
 	if (likely(!rt_mutex_has_waiters(lock))) {
-		raw_spin_unlock_irqrestore(&pendowner->pi_lock, flags);
+		raw_spin_unlock(&pendowner->pi_lock);
 		return 1;
 	}
 
@@ -333,7 +349,7 @@ static inline int try_to_steal_lock(struct rt_mutex *lock,
 	next = rt_mutex_top_waiter(lock);
 	plist_del(&next->pi_list_entry, &pendowner->pi_waiters);
 	__rt_mutex_adjust_prio(pendowner);
-	raw_spin_unlock_irqrestore(&pendowner->pi_lock, flags);
+	raw_spin_unlock(&pendowner->pi_lock);
 
 	/*
 	 * We are going to steal the lock and a waiter was
@@ -350,10 +366,10 @@ static inline int try_to_steal_lock(struct rt_mutex *lock,
 	 * might be task:
 	 */
 	if (likely(next->task != task)) {
-		raw_spin_lock_irqsave(&task->pi_lock, flags);
+		raw_spin_lock(&task->pi_lock);
 		plist_add(&next->pi_list_entry, &task->pi_waiters);
 		__rt_mutex_adjust_prio(task);
-		raw_spin_unlock_irqrestore(&task->pi_lock, flags);
+		raw_spin_unlock(&task->pi_lock);
 	}
 	return 1;
 }
@@ -413,14 +429,13 @@ static int try_to_take_rt_mutex(struct rt_mutex *lock)
 static int task_blocks_on_rt_mutex(struct rt_mutex *lock,
 				   struct rt_mutex_waiter *waiter,
 				   struct task_struct *task,
-				   int detect_deadlock)
+				   int detect_deadlock, unsigned long flags)
 {
 	struct task_struct *owner = rt_mutex_owner(lock);
 	struct rt_mutex_waiter *top_waiter = waiter;
-	unsigned long flags;
 	int chain_walk = 0, res;
 
-	raw_spin_lock_irqsave(&task->pi_lock, flags);
+	raw_spin_lock(&task->pi_lock);
 	__rt_mutex_adjust_prio(task);
 	waiter->task = task;
 	waiter->lock = lock;
@@ -434,17 +449,17 @@ static int task_blocks_on_rt_mutex(struct rt_mutex *lock,
 
 	task->pi_blocked_on = waiter;
 
-	raw_spin_unlock_irqrestore(&task->pi_lock, flags);
+	raw_spin_unlock(&task->pi_lock);
 
 	if (waiter == rt_mutex_top_waiter(lock)) {
-		raw_spin_lock_irqsave(&owner->pi_lock, flags);
+		raw_spin_lock(&owner->pi_lock);
 		plist_del(&top_waiter->pi_list_entry, &owner->pi_waiters);
 		plist_add(&waiter->pi_list_entry, &owner->pi_waiters);
 
 		__rt_mutex_adjust_prio(owner);
 		if (owner->pi_blocked_on)
 			chain_walk = 1;
-		raw_spin_unlock_irqrestore(&owner->pi_lock, flags);
+		raw_spin_unlock(&owner->pi_lock);
 	}
 	else if (debug_rt_mutex_detect_deadlock(waiter, detect_deadlock))
 		chain_walk = 1;
@@ -459,12 +474,12 @@ static int task_blocks_on_rt_mutex(struct rt_mutex *lock,
 	 */
 	get_task_struct(owner);
 
-	raw_spin_unlock(&lock->wait_lock);
+	raw_spin_unlock_irqrestore(&lock->wait_lock, flags);
 
 	res = rt_mutex_adjust_prio_chain(owner, detect_deadlock, lock, waiter,
 					 task);
 
-	raw_spin_lock(&lock->wait_lock);
+	raw_spin_lock_irq(&lock->wait_lock);
 
 	return res;
 }
@@ -477,13 +492,12 @@ static int task_blocks_on_rt_mutex(struct rt_mutex *lock,
  *
  * Called with lock->wait_lock held.
  */
-static void wakeup_next_waiter(struct rt_mutex *lock)
+static void wakeup_next_waiter(struct rt_mutex *lock, int savestate)
 {
 	struct rt_mutex_waiter *waiter;
 	struct task_struct *pendowner;
-	unsigned long flags;
 
-	raw_spin_lock_irqsave(&current->pi_lock, flags);
+	raw_spin_lock(&current->pi_lock);
 
 	waiter = rt_mutex_top_waiter(lock);
 	plist_del(&waiter->list_entry, &lock->wait_list);
@@ -500,7 +514,7 @@ static void wakeup_next_waiter(struct rt_mutex *lock)
 
 	rt_mutex_set_owner(lock, pendowner, RT_MUTEX_OWNER_PENDING);
 
-	raw_spin_unlock_irqrestore(&current->pi_lock, flags);
+	raw_spin_unlock(&current->pi_lock);
 
 	/*
 	 * Clear the pi_blocked_on variable and enqueue a possible
@@ -509,7 +523,7 @@ static void wakeup_next_waiter(struct rt_mutex *lock)
 	 * waiter with higher priority than pending-owner->normal_prio
 	 * is blocked on the unboosted (pending) owner.
 	 */
-	raw_spin_lock_irqsave(&pendowner->pi_lock, flags);
+	raw_spin_lock(&pendowner->pi_lock);
 
 	WARN_ON(!pendowner->pi_blocked_on);
 	WARN_ON(pendowner->pi_blocked_on != waiter);
@@ -523,9 +537,12 @@ static void wakeup_next_waiter(struct rt_mutex *lock)
 		next = rt_mutex_top_waiter(lock);
 		plist_add(&next->pi_list_entry, &pendowner->pi_waiters);
 	}
-	raw_spin_unlock_irqrestore(&pendowner->pi_lock, flags);
+	raw_spin_unlock(&pendowner->pi_lock);
 
-	wake_up_process(pendowner);
+	if (savestate)
+		wake_up_process_mutex(pendowner);
+	else
+		wake_up_process(pendowner);
 }
 
 /*
@@ -534,22 +551,22 @@ static void wakeup_next_waiter(struct rt_mutex *lock)
  * Must be called with lock->wait_lock held
  */
 static void remove_waiter(struct rt_mutex *lock,
-			  struct rt_mutex_waiter *waiter)
+			  struct rt_mutex_waiter *waiter,
+			  unsigned long flags)
 {
 	int first = (waiter == rt_mutex_top_waiter(lock));
 	struct task_struct *owner = rt_mutex_owner(lock);
-	unsigned long flags;
 	int chain_walk = 0;
 
-	raw_spin_lock_irqsave(&current->pi_lock, flags);
+	raw_spin_lock(&current->pi_lock);
 	plist_del(&waiter->list_entry, &lock->wait_list);
 	waiter->task = NULL;
 	current->pi_blocked_on = NULL;
-	raw_spin_unlock_irqrestore(&current->pi_lock, flags);
+	raw_spin_unlock(&current->pi_lock);
 
 	if (first && owner != current) {
 
-		raw_spin_lock_irqsave(&owner->pi_lock, flags);
+		raw_spin_lock(&owner->pi_lock);
 
 		plist_del(&waiter->pi_list_entry, &owner->pi_waiters);
 
@@ -564,7 +581,7 @@ static void remove_waiter(struct rt_mutex *lock,
 		if (owner->pi_blocked_on)
 			chain_walk = 1;
 
-		raw_spin_unlock_irqrestore(&owner->pi_lock, flags);
+		raw_spin_unlock(&owner->pi_lock);
 	}
 
 	WARN_ON(!plist_node_empty(&waiter->pi_list_entry));
@@ -575,11 +592,11 @@ static void remove_waiter(struct rt_mutex *lock,
 	/* gets dropped in rt_mutex_adjust_prio_chain()! */
 	get_task_struct(owner);
 
-	raw_spin_unlock(&lock->wait_lock);
+	raw_spin_unlock_irqrestore(&lock->wait_lock, flags);
 
 	rt_mutex_adjust_prio_chain(owner, 0, lock, NULL, current);
 
-	raw_spin_lock(&lock->wait_lock);
+	raw_spin_lock_irq(&lock->wait_lock);
 }
 
 /*
@@ -600,18 +617,305 @@ void rt_mutex_adjust_pi(struct task_struct *task)
 		return;
 	}
 
-	raw_spin_unlock_irqrestore(&task->pi_lock, flags);
-
 	/* gets dropped in rt_mutex_adjust_prio_chain()! */
 	get_task_struct(task);
+	raw_spin_unlock_irqrestore(&task->pi_lock, flags);
 	rt_mutex_adjust_prio_chain(task, 0, NULL, NULL, task);
 }
 
+/*
+ * preemptible spin_lock functions:
+ */
+
+#ifdef CONFIG_PREEMPT_RT
+
+static inline void
+rt_spin_lock_fastlock(struct rt_mutex *lock,
+		void  (*slowfn)(struct rt_mutex *lock))
+{
+	might_sleep();
+
+	if (likely(rt_mutex_cmpxchg(lock, NULL, current)))
+		rt_mutex_deadlock_account_lock(lock, current);
+	else
+		slowfn(lock);
+}
+
+static inline void
+rt_spin_lock_fastunlock(struct rt_mutex *lock,
+			void  (*slowfn)(struct rt_mutex *lock))
+{
+	if (likely(rt_mutex_cmpxchg(lock, current, NULL)))
+		rt_mutex_deadlock_account_unlock(current);
+	else
+		slowfn(lock);
+}
+
+/*
+ * Slow path lock function spin_lock style: this variant is very
+ * careful not to miss any non-lock wakeups.
+ *
+ * The wakeup side uses wake_up_process_mutex, which, combined with
+ * the xchg code of this function is a transparent sleep/wakeup
+ * mechanism nested within any existing sleep/wakeup mechanism. This
+ * enables the seemless use of arbitrary (blocking) spinlocks within
+ * sleep/wakeup event loops.
+ */
+static void  noinline __sched
+rt_spin_lock_slowlock(struct rt_mutex *lock)
+{
+	struct rt_mutex_waiter waiter;
+	unsigned long saved_state, state, flags;
+
+	debug_rt_mutex_init_waiter(&waiter);
+	waiter.task = NULL;
+
+	raw_spin_lock_irqsave(&lock->wait_lock, flags);
+	init_lists(lock);
+
+	/* Try to acquire the lock again: */
+	if (try_to_take_rt_mutex(lock)) {
+		raw_spin_unlock_irqrestore(&lock->wait_lock, flags);
+		return;
+	}
+
+	BUG_ON(rt_mutex_owner(lock) == current);
+
+	/*
+	 * Here we save whatever state the task was in originally,
+	 * we'll restore it at the end of the function and we'll take
+	 * any intermediate wakeup into account as well, independently
+	 * of the lock sleep/wakeup mechanism. When we get a real
+	 * wakeup the task->state is TASK_RUNNING and we change
+	 * saved_state accordingly. If we did not get a real wakeup
+	 * then we return with the saved state.
+	 */
+	saved_state = xchg(&current->state, TASK_UNINTERRUPTIBLE);
+
+	for (;;) {
+		int saved_lock_depth = current->lock_depth;
+
+		/* Try to acquire the lock */
+		if (try_to_take_rt_mutex(lock))
+			break;
+		/*
+		 * waiter.task is NULL the first time we come here and
+		 * when we have been woken up by the previous owner
+		 * but the lock got stolen by an higher prio task.
+		 */
+		if (!waiter.task) {
+			task_blocks_on_rt_mutex(lock, &waiter, current, 0,
+						flags);
+			/* Wakeup during boost ? */
+			if (unlikely(!waiter.task))
+				continue;
+		}
+
+		/*
+		 * Prevent schedule() to drop BKL, while waiting for
+		 * the lock ! We restore lock_depth when we come back.
+		 */
+		current->lock_depth = -1;
+		raw_spin_unlock_irqrestore(&lock->wait_lock, flags);
+
+		debug_rt_mutex_print_deadlock(&waiter);
+
+		schedule_rt_mutex(lock);
+
+		raw_spin_lock_irqsave(&lock->wait_lock, flags);
+		current->lock_depth = saved_lock_depth;
+		state = xchg(&current->state, TASK_UNINTERRUPTIBLE);
+		if (unlikely(state == TASK_RUNNING))
+			saved_state = TASK_RUNNING;
+	}
+
+	state = xchg(&current->state, saved_state);
+	if (unlikely(state == TASK_RUNNING))
+		current->state = TASK_RUNNING;
+
+	/*
+	 * Extremely rare case, if we got woken up by a non-mutex wakeup,
+	 * and we managed to steal the lock despite us not being the
+	 * highest-prio waiter (due to SCHED_OTHER changing prio), then we
+	 * can end up with a non-NULL waiter.task:
+	 */
+	if (unlikely(waiter.task))
+		remove_waiter(lock, &waiter, flags);
+	/*
+	 * try_to_take_rt_mutex() sets the waiter bit
+	 * unconditionally. We might have to fix that up:
+	 */
+	fixup_rt_mutex_waiters(lock);
+
+	raw_spin_unlock_irqrestore(&lock->wait_lock, flags);
+
+	debug_rt_mutex_free_waiter(&waiter);
+}
+
+/*
+ * Slow path to release a rt_mutex spin_lock style
+ */
+static void  noinline __sched
+rt_spin_lock_slowunlock(struct rt_mutex *lock)
+{
+	unsigned long flags;
+
+	raw_spin_lock_irqsave(&lock->wait_lock, flags);
+
+	debug_rt_mutex_unlock(lock);
+
+	rt_mutex_deadlock_account_unlock(current);
+
+	if (!rt_mutex_has_waiters(lock)) {
+		lock->owner = NULL;
+		raw_spin_unlock_irqrestore(&lock->wait_lock, flags);
+		return;
+	}
+
+	wakeup_next_waiter(lock, 1);
+
+	raw_spin_unlock_irqrestore(&lock->wait_lock, flags);
+
+	/* Undo pi boosting.when necessary */
+	rt_mutex_adjust_prio(current);
+}
+
+void __lockfunc rt_spin_lock(spinlock_t *lock)
+{
+	rt_spin_lock_fastlock(&lock->lock, rt_spin_lock_slowlock);
+	spin_acquire(&lock->dep_map, 0, 0, _RET_IP_);
+}
+EXPORT_SYMBOL(rt_spin_lock);
+
+void __lockfunc __rt_spin_lock(struct rt_mutex *lock)
+{
+	rt_spin_lock_fastlock(lock, rt_spin_lock_slowlock);
+}
+EXPORT_SYMBOL(__rt_spin_lock);
+
+#ifdef CONFIG_DEBUG_LOCK_ALLOC
+
+void __lockfunc rt_spin_lock_nested(spinlock_t *lock, int subclass)
+{
+	rt_spin_lock_fastlock(&lock->lock, rt_spin_lock_slowlock);
+	spin_acquire(&lock->dep_map, subclass, 0, _RET_IP_);
+}
+EXPORT_SYMBOL(rt_spin_lock_nested);
+
+#endif
+
+void __lockfunc rt_spin_unlock(spinlock_t *lock)
+{
+	/* NOTE: we always pass in '1' for nested, for simplicity */
+	spin_release(&lock->dep_map, 1, _RET_IP_);
+	rt_spin_lock_fastunlock(&lock->lock, rt_spin_lock_slowunlock);
+}
+EXPORT_SYMBOL(rt_spin_unlock);
+
+void __lockfunc __rt_spin_unlock(struct rt_mutex *lock)
+{
+	rt_spin_lock_fastunlock(lock, rt_spin_lock_slowunlock);
+}
+EXPORT_SYMBOL(__rt_spin_unlock);
+
+/*
+ * Wait for the lock to get unlocked: instead of polling for an unlock
+ * (like raw spinlocks do), we lock and unlock, to force the kernel to
+ * schedule if there's contention:
+ */
+void __lockfunc rt_spin_unlock_wait(spinlock_t *lock)
+{
+	spin_lock(lock);
+	spin_unlock(lock);
+}
+EXPORT_SYMBOL(rt_spin_unlock_wait);
+
+int __lockfunc rt_spin_trylock(spinlock_t *lock)
+{
+	int ret = rt_mutex_trylock(&lock->lock);
+
+	if (ret)
+		spin_acquire(&lock->dep_map, 0, 1, _RET_IP_);
+
+	return ret;
+}
+EXPORT_SYMBOL(rt_spin_trylock);
+
+int __lockfunc rt_spin_trylock_irqsave(spinlock_t *lock, unsigned long *flags)
+{
+	int ret;
+
+	*flags = 0;
+	ret = rt_mutex_trylock(&lock->lock);
+	if (ret)
+		spin_acquire(&lock->dep_map, 0, 1, _RET_IP_);
+
+	return ret;
+}
+EXPORT_SYMBOL(rt_spin_trylock_irqsave);
+
+int atomic_dec_and_spin_lock(atomic_t *atomic, spinlock_t *lock)
+{
+	/* Subtract 1 from counter unless that drops it to 0 (ie. it was 1) */
+	if (atomic_add_unless(atomic, -1, 1))
+		return 0;
+	rt_spin_lock(lock);
+	if (atomic_dec_and_test(atomic))
+		return 1;
+	rt_spin_unlock(lock);
+	return 0;
+}
+EXPORT_SYMBOL(atomic_dec_and_spin_lock);
+
+void
+__rt_spin_lock_init(spinlock_t *lock, char *name, struct lock_class_key *key)
+{
+#ifdef CONFIG_DEBUG_LOCK_ALLOC
+	/*
+	 * Make sure we are not reinitializing a held lock:
+	 */
+	debug_check_no_locks_freed((void *)lock, sizeof(*lock));
+	lockdep_init_map(&lock->dep_map, name, key, 0);
+#endif
+	__rt_mutex_init(&lock->lock, name);
+}
+EXPORT_SYMBOL(__rt_spin_lock_init);
+
+#endif
+
+static inline int rt_release_bkl(struct rt_mutex *lock, unsigned long flags)
+{
+	int saved_lock_depth = current->lock_depth;
+
+#ifdef CONFIG_LOCK_KERNEL
+	current->lock_depth = -1;
+	/*
+	 * try_to_take_lock set the waiters, make sure it's
+	 * still correct.
+	 */
+	fixup_rt_mutex_waiters(lock);
+	raw_spin_unlock_irqrestore(&lock->wait_lock, flags);
+
+	up(&kernel_sem);
+
+	raw_spin_lock_irq(&lock->wait_lock);
+#endif
+	return saved_lock_depth;
+}
+
+static inline void rt_reacquire_bkl(int saved_lock_depth)
+{
+#ifdef CONFIG_LOCK_KERNEL
+	down(&kernel_sem);
+	current->lock_depth = saved_lock_depth;
+#endif
+}
+
 /**
  * __rt_mutex_slowlock() - Perform the wait-wake-try-to-take loop
  * @lock:		 the rt_mutex to take
  * @state:		 the state the task should block in (TASK_INTERRUPTIBLE
- * 			 or TASK_UNINTERRUPTIBLE)
+ *			 or TASK_UNINTERRUPTIBLE)
  * @timeout:		 the pre-initialized and started timer, or NULL for none
  * @waiter:		 the pre-initialized rt_mutex_waiter
  * @detect_deadlock:	 passed to task_blocks_on_rt_mutex
@@ -622,7 +926,7 @@ static int __sched
 __rt_mutex_slowlock(struct rt_mutex *lock, int state,
 		    struct hrtimer_sleeper *timeout,
 		    struct rt_mutex_waiter *waiter,
-		    int detect_deadlock)
+		    int detect_deadlock, unsigned long flags)
 {
 	int ret = 0;
 
@@ -652,7 +956,7 @@ __rt_mutex_slowlock(struct rt_mutex *lock, int state,
 		 */
 		if (!waiter->task) {
 			ret = task_blocks_on_rt_mutex(lock, waiter, current,
-						      detect_deadlock);
+						      detect_deadlock, flags);
 			/*
 			 * If we got woken up by the owner then start loop
 			 * all over without going into schedule to try
@@ -672,14 +976,15 @@ __rt_mutex_slowlock(struct rt_mutex *lock, int state,
 				break;
 		}
 
-		raw_spin_unlock(&lock->wait_lock);
+		raw_spin_unlock_irq(&lock->wait_lock);
 
 		debug_rt_mutex_print_deadlock(waiter);
 
 		if (waiter->task)
 			schedule_rt_mutex(lock);
 
-		raw_spin_lock(&lock->wait_lock);
+		raw_spin_lock_irq(&lock->wait_lock);
+
 		set_current_state(state);
 	}
 
@@ -694,20 +999,29 @@ rt_mutex_slowlock(struct rt_mutex *lock, int state,
 		  struct hrtimer_sleeper *timeout,
 		  int detect_deadlock)
 {
+	int ret = 0, saved_lock_depth = -1;
 	struct rt_mutex_waiter waiter;
-	int ret = 0;
+	unsigned long flags;
 
 	debug_rt_mutex_init_waiter(&waiter);
 	waiter.task = NULL;
 
-	raw_spin_lock(&lock->wait_lock);
+	raw_spin_lock_irqsave(&lock->wait_lock, flags);
+	init_lists(lock);
 
 	/* Try to acquire the lock again: */
 	if (try_to_take_rt_mutex(lock)) {
-		raw_spin_unlock(&lock->wait_lock);
+		raw_spin_unlock_irqrestore(&lock->wait_lock, flags);
 		return 0;
 	}
 
+	/*
+	 * We drop the BKL here before we go into the wait loop to avoid a
+	 * possible deadlock in the scheduler.
+	 */
+	if (unlikely(current->lock_depth >= 0))
+		saved_lock_depth = rt_release_bkl(lock, flags);
+
 	set_current_state(state);
 
 	/* Setup the timer, when timeout != NULL */
@@ -718,12 +1032,12 @@ rt_mutex_slowlock(struct rt_mutex *lock, int state,
 	}
 
 	ret = __rt_mutex_slowlock(lock, state, timeout, &waiter,
-				  detect_deadlock);
+				  detect_deadlock, flags);
 
 	set_current_state(TASK_RUNNING);
 
 	if (unlikely(waiter.task))
-		remove_waiter(lock, &waiter);
+		remove_waiter(lock, &waiter, flags);
 
 	/*
 	 * try_to_take_rt_mutex() sets the waiter bit
@@ -731,7 +1045,7 @@ rt_mutex_slowlock(struct rt_mutex *lock, int state,
 	 */
 	fixup_rt_mutex_waiters(lock);
 
-	raw_spin_unlock(&lock->wait_lock);
+	raw_spin_unlock_irqrestore(&lock->wait_lock, flags);
 
 	/* Remove pending timer: */
 	if (unlikely(timeout))
@@ -745,6 +1059,10 @@ rt_mutex_slowlock(struct rt_mutex *lock, int state,
 	if (unlikely(ret))
 		rt_mutex_adjust_prio(current);
 
+	/* Must we reaquire the BKL? */
+	if (unlikely(saved_lock_depth >= 0))
+		rt_reacquire_bkl(saved_lock_depth);
+
 	debug_rt_mutex_free_waiter(&waiter);
 
 	return ret;
@@ -756,12 +1074,15 @@ rt_mutex_slowlock(struct rt_mutex *lock, int state,
 static inline int
 rt_mutex_slowtrylock(struct rt_mutex *lock)
 {
+	unsigned long flags;
 	int ret = 0;
 
-	raw_spin_lock(&lock->wait_lock);
+	raw_spin_lock_irqsave(&lock->wait_lock, flags);
 
 	if (likely(rt_mutex_owner(lock) != current)) {
 
+		init_lists(lock);
+
 		ret = try_to_take_rt_mutex(lock);
 		/*
 		 * try_to_take_rt_mutex() sets the lock waiters
@@ -770,7 +1091,7 @@ rt_mutex_slowtrylock(struct rt_mutex *lock)
 		fixup_rt_mutex_waiters(lock);
 	}
 
-	raw_spin_unlock(&lock->wait_lock);
+	raw_spin_unlock_irqrestore(&lock->wait_lock, flags);
 
 	return ret;
 }
@@ -781,7 +1102,9 @@ rt_mutex_slowtrylock(struct rt_mutex *lock)
 static void __sched
 rt_mutex_slowunlock(struct rt_mutex *lock)
 {
-	raw_spin_lock(&lock->wait_lock);
+	unsigned long flags;
+
+	raw_spin_lock_irqsave(&lock->wait_lock, flags);
 
 	debug_rt_mutex_unlock(lock);
 
@@ -789,13 +1112,13 @@ rt_mutex_slowunlock(struct rt_mutex *lock)
 
 	if (!rt_mutex_has_waiters(lock)) {
 		lock->owner = NULL;
-		raw_spin_unlock(&lock->wait_lock);
+		raw_spin_unlock_irqrestore(&lock->wait_lock, flags);
 		return;
 	}
 
-	wakeup_next_waiter(lock);
+	wakeup_next_waiter(lock, 0);
 
-	raw_spin_unlock(&lock->wait_lock);
+	raw_spin_unlock_irqrestore(&lock->wait_lock, flags);
 
 	/* Undo pi boosting if necessary: */
 	rt_mutex_adjust_prio(current);
@@ -857,6 +1180,27 @@ rt_mutex_fastunlock(struct rt_mutex *lock,
 }
 
 /**
+ * rt_mutex_lock_killable - lock a rt_mutex killable
+ *
+ * @lock: 		the rt_mutex to be locked
+ * @detect_deadlock:	deadlock detection on/off
+ *
+ * Returns:
+ *  0 		on success
+ * -EINTR 	when interrupted by a signal
+ * -EDEADLK	when the lock would deadlock (when deadlock detection is on)
+ */
+int __sched rt_mutex_lock_killable(struct rt_mutex *lock,
+				   int detect_deadlock)
+{
+	might_sleep();
+
+	return rt_mutex_fastlock(lock, TASK_KILLABLE,
+				 detect_deadlock, rt_mutex_slowlock);
+}
+EXPORT_SYMBOL_GPL(rt_mutex_lock_killable);
+
+/**
  * rt_mutex_lock - lock a rt_mutex
  *
  * @lock: the rt_mutex to be locked
@@ -1030,9 +1374,10 @@ int rt_mutex_start_proxy_lock(struct rt_mutex *lock,
 			      struct rt_mutex_waiter *waiter,
 			      struct task_struct *task, int detect_deadlock)
 {
+	unsigned long flags;
 	int ret;
 
-	raw_spin_lock(&lock->wait_lock);
+	raw_spin_lock_irqsave(&lock->wait_lock, flags);
 
 	mark_rt_mutex_waiters(lock);
 
@@ -1045,7 +1390,8 @@ int rt_mutex_start_proxy_lock(struct rt_mutex *lock,
 		return 1;
 	}
 
-	ret = task_blocks_on_rt_mutex(lock, waiter, task, detect_deadlock);
+	ret = task_blocks_on_rt_mutex(lock, waiter, task, detect_deadlock,
+				      flags);
 
 	if (ret && !waiter->task) {
 		/*
@@ -1056,7 +1402,7 @@ int rt_mutex_start_proxy_lock(struct rt_mutex *lock,
 		 */
 		ret = 0;
 	}
-	raw_spin_unlock(&lock->wait_lock);
+	raw_spin_unlock_irqrestore(&lock->wait_lock, flags);
 
 	debug_rt_mutex_print_deadlock(waiter);
 
@@ -1104,19 +1450,20 @@ int rt_mutex_finish_proxy_lock(struct rt_mutex *lock,
 			       struct rt_mutex_waiter *waiter,
 			       int detect_deadlock)
 {
+	unsigned long flags;
 	int ret;
 
-	raw_spin_lock(&lock->wait_lock);
+	raw_spin_lock_irqsave(&lock->wait_lock, flags);
 
 	set_current_state(TASK_INTERRUPTIBLE);
 
 	ret = __rt_mutex_slowlock(lock, TASK_INTERRUPTIBLE, to, waiter,
-				  detect_deadlock);
+				  detect_deadlock, flags);
 
 	set_current_state(TASK_RUNNING);
 
 	if (unlikely(waiter->task))
-		remove_waiter(lock, waiter);
+		remove_waiter(lock, waiter, flags);
 
 	/*
 	 * try_to_take_rt_mutex() sets the waiter bit unconditionally. We might
@@ -1124,7 +1471,7 @@ int rt_mutex_finish_proxy_lock(struct rt_mutex *lock,
 	 */
 	fixup_rt_mutex_waiters(lock);
 
-	raw_spin_unlock(&lock->wait_lock);
+	raw_spin_unlock_irqrestore(&lock->wait_lock, flags);
 
 	/*
 	 * Readjust priority, when we did not get the lock. We might have been
diff --git a/lib/kernel_lock.c b/lib/kernel_lock.c
index 2c9b548..e495acf 100644
--- a/lib/kernel_lock.c
+++ b/lib/kernel_lock.c
@@ -27,7 +27,7 @@
  *
  * Don't use in new code.
  */
-static struct semaphore kernel_sem;
+struct semaphore kernel_sem;
 
 /*
  * Re-acquire the kernel semaphore.
-- 
1.7.0.4