summaryrefslogtreecommitdiff
path: root/kernel/softirq.c
blob: 869290835b5bb67de92fb598cd6d39fb918f03db (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
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
1114
1115
1116
1117
1118
1119
1120
1121
1122
1123
1124
1125
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
1177
1178
1179
1180
1181
1182
1183
1184
1185
1186
1187
1188
1189
1190
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
1218
1219
1220
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
1252
1253
1254
1255
1256
1257
1258
1259
1260
1261
1262
1263
1264
1265
1266
1267
1268
1269
1270
1271
1272
1273
1274
1275
1276
1277
1278
1279
1280
1281
/*
 *	linux/kernel/softirq.c
 *
 *	Copyright (C) 1992 Linus Torvalds
 *
 *	Distribute under GPLv2.
 *
 *	Rewritten. Old one was good in 2.2, but in 2.3 it was immoral. --ANK (990903)
 *
 *	Remote softirq infrastructure is by Jens Axboe.
 */

#include <linux/export.h>
#include <linux/kernel_stat.h>
#include <linux/interrupt.h>
#include <linux/init.h>
#include <linux/mm.h>
#include <linux/notifier.h>
#include <linux/percpu.h>
#include <linux/cpu.h>
#include <linux/freezer.h>
#include <linux/kthread.h>
#include <linux/rcupdate.h>
#include <linux/delay.h>
#include <linux/ftrace.h>
#include <linux/smp.h>
#include <linux/smpboot.h>
#include <linux/tick.h>
#include <linux/locallock.h>

#define CREATE_TRACE_POINTS
#include <trace/events/irq.h>

#include <asm/irq.h>
/*
   - No shared variables, all the data are CPU local.
   - If a softirq needs serialization, let it serialize itself
     by its own spinlocks.
   - Even if softirq is serialized, only local cpu is marked for
     execution. Hence, we get something sort of weak cpu binding.
     Though it is still not clear, will it result in better locality
     or will not.

   Examples:
   - NET RX softirq. It is multithreaded and does not require
     any global serialization.
   - NET TX softirq. It kicks software netdevice queues, hence
     it is logically serialized per device, but this serialization
     is invisible to common code.
   - Tasklets: serialized wrt itself.
 */

#ifndef __ARCH_IRQ_STAT
irq_cpustat_t irq_stat[NR_CPUS] ____cacheline_aligned;
EXPORT_SYMBOL(irq_stat);
#endif

static struct softirq_action softirq_vec[NR_SOFTIRQS] __cacheline_aligned_in_smp;

DEFINE_PER_CPU(struct task_struct *, ksoftirqd);

char *softirq_to_name[NR_SOFTIRQS] = {
	"HI", "TIMER", "NET_TX", "NET_RX", "BLOCK", "BLOCK_IOPOLL",
	"TASKLET", "SCHED", "HRTIMER", "RCU"
};

#ifdef CONFIG_NO_HZ_COMMON
# ifdef CONFIG_PREEMPT_RT_FULL
/*
 * On preempt-rt a softirq might be blocked on a lock. There might be
 * no other runnable task on this CPU because the lock owner runs on
 * some other CPU. So we have to go into idle with the pending bit
 * set. Therefor we need to check this otherwise we warn about false
 * positives which confuses users and defeats the whole purpose of
 * this test.
 *
 * This code is called with interrupts disabled.
 */
void softirq_check_pending_idle(void)
{
	static int rate_limit;
	u32 warnpending = 0, pending;

	if (rate_limit >= 10)
		return;

	pending = local_softirq_pending() & SOFTIRQ_STOP_IDLE_MASK;
	if (pending) {
		struct task_struct *tsk;

		tsk = __get_cpu_var(ksoftirqd);
		/*
		 * The wakeup code in rtmutex.c wakes up the task
		 * _before_ it sets pi_blocked_on to NULL under
		 * tsk->pi_lock. So we need to check for both: state
		 * and pi_blocked_on.
		 */
		raw_spin_lock(&tsk->pi_lock);

		if (!tsk->pi_blocked_on && !(tsk->state == TASK_RUNNING))
			warnpending = 1;

		raw_spin_unlock(&tsk->pi_lock);
	}

	if (warnpending) {
		printk(KERN_ERR "NOHZ: local_softirq_pending %02x\n",
		       pending);
		rate_limit++;
	}
}
# else
/*
 * On !PREEMPT_RT we just printk rate limited:
 */
void softirq_check_pending_idle(void)
{
	static int rate_limit;

	if (rate_limit < 10 &&
			(local_softirq_pending() & SOFTIRQ_STOP_IDLE_MASK)) {
		printk(KERN_ERR "NOHZ: local_softirq_pending %02x\n",
		       local_softirq_pending());
		rate_limit++;
	}
}
# endif
#endif

/*
 * we cannot loop indefinitely here to avoid userspace starvation,
 * but we also don't want to introduce a worst case 1/HZ latency
 * to the pending events, so lets the scheduler to balance
 * the softirq load for us.
 */
static void wakeup_softirqd(void)
{
	/* Interrupts are disabled: no need to stop preemption */
	struct task_struct *tsk = __this_cpu_read(ksoftirqd);

	if (tsk && tsk->state != TASK_RUNNING)
		wake_up_process(tsk);
}

static void handle_pending_softirqs(u32 pending, int cpu, int need_rcu_bh_qs)
{
	struct softirq_action *h = softirq_vec;
	unsigned int prev_count = preempt_count();

	local_irq_enable();
	for (; pending; h++, pending >>= 1) {
		unsigned int vec_nr = h - softirq_vec;

		if (!(pending & 1))
			continue;

		kstat_incr_softirqs_this_cpu(vec_nr);
		trace_softirq_entry(vec_nr);
		h->action(h);
		trace_softirq_exit(vec_nr);
		if (unlikely(prev_count != preempt_count())) {
			pr_err(
"huh, entered softirq %u %s %p with preempt_count %08x exited with %08x?\n",
			       vec_nr, softirq_to_name[vec_nr], h->action,
			       prev_count, (unsigned int) preempt_count());
			preempt_count() = prev_count;
		}
		if (need_rcu_bh_qs)
			rcu_bh_qs(cpu);
	}
	local_irq_disable();
}

#ifndef CONFIG_PREEMPT_RT_FULL
/*
 * preempt_count and SOFTIRQ_OFFSET usage:
 * - preempt_count is changed by SOFTIRQ_OFFSET on entering or leaving
 *   softirq processing.
 * - preempt_count is changed by SOFTIRQ_DISABLE_OFFSET (= 2 * SOFTIRQ_OFFSET)
 *   on local_bh_disable or local_bh_enable.
 * This lets us distinguish between whether we are currently processing
 * softirq and whether we just have bh disabled.
 */

/*
 * This one is for softirq.c-internal use,
 * where hardirqs are disabled legitimately:
 */
#ifdef CONFIG_TRACE_IRQFLAGS
static void __local_bh_disable(unsigned long ip, unsigned int cnt)
{
	unsigned long flags;

	WARN_ON_ONCE(in_irq());

	raw_local_irq_save(flags);
	/*
	 * The preempt tracer hooks into add_preempt_count and will break
	 * lockdep because it calls back into lockdep after SOFTIRQ_OFFSET
	 * is set and before current->softirq_enabled is cleared.
	 * We must manually increment preempt_count here and manually
	 * call the trace_preempt_off later.
	 */
	preempt_count() += cnt;
	/*
	 * Were softirqs turned off above:
	 */
	if (softirq_count() == cnt)
		trace_softirqs_off(ip);
	raw_local_irq_restore(flags);

	if (preempt_count() == cnt)
		trace_preempt_off(CALLER_ADDR0, get_parent_ip(CALLER_ADDR1));
}
#else /* !CONFIG_TRACE_IRQFLAGS */
static inline void __local_bh_disable(unsigned long ip, unsigned int cnt)
{
	add_preempt_count(cnt);
	barrier();
}
#endif /* CONFIG_TRACE_IRQFLAGS */

void local_bh_disable(void)
{
	__local_bh_disable(_RET_IP_, SOFTIRQ_DISABLE_OFFSET);
}

EXPORT_SYMBOL(local_bh_disable);

static void __local_bh_enable(unsigned int cnt)
{
	WARN_ON_ONCE(in_irq());
	WARN_ON_ONCE(!irqs_disabled());

	if (softirq_count() == cnt)
		trace_softirqs_on(_RET_IP_);
	sub_preempt_count(cnt);
}

/*
 * Special-case - softirqs can safely be enabled in
 * cond_resched_softirq(), or by __do_softirq(),
 * without processing still-pending softirqs:
 */
void _local_bh_enable(void)
{
	__local_bh_enable(SOFTIRQ_DISABLE_OFFSET);
}

EXPORT_SYMBOL(_local_bh_enable);

static inline void _local_bh_enable_ip(unsigned long ip)
{
	WARN_ON_ONCE(in_irq() || irqs_disabled());
#ifdef CONFIG_TRACE_IRQFLAGS
	local_irq_disable();
#endif
	/*
	 * Are softirqs going to be turned on now:
	 */
	if (softirq_count() == SOFTIRQ_DISABLE_OFFSET)
		trace_softirqs_on(ip);
	/*
	 * Keep preemption disabled until we are done with
	 * softirq processing:
 	 */
	sub_preempt_count(SOFTIRQ_DISABLE_OFFSET - 1);

	if (unlikely(!in_interrupt() && local_softirq_pending()))
		do_softirq();

	dec_preempt_count();
#ifdef CONFIG_TRACE_IRQFLAGS
	local_irq_enable();
#endif
	preempt_check_resched();
}

void local_bh_enable(void)
{
	_local_bh_enable_ip(_RET_IP_);
}
EXPORT_SYMBOL(local_bh_enable);

void local_bh_enable_ip(unsigned long ip)
{
	_local_bh_enable_ip(ip);
}
EXPORT_SYMBOL(local_bh_enable_ip);

/*
 * We restart softirq processing for at most MAX_SOFTIRQ_RESTART times,
 * but break the loop if need_resched() is set or after 2 ms.
 * The MAX_SOFTIRQ_TIME provides a nice upper bound in most cases, but in
 * certain cases, such as stop_machine(), jiffies may cease to
 * increment and so we need the MAX_SOFTIRQ_RESTART limit as
 * well to make sure we eventually return from this method.
 *
 * These limits have been established via experimentation.
 * The two things to balance is latency against fairness -
 * we want to handle softirqs as soon as possible, but they
 * should not be able to lock up the box.
 */
#define MAX_SOFTIRQ_TIME  msecs_to_jiffies(2)
#define MAX_SOFTIRQ_RESTART 10

#ifdef CONFIG_TRACE_IRQFLAGS
/*
 * Convoluted means of passing __do_softirq() a message through the various
 * architecture execute_on_stack() bits.
 *
 * When we run softirqs from irq_exit() and thus on the hardirq stack we need
 * to keep the lockdep irq context tracking as tight as possible in order to
 * not miss-qualify lock contexts and miss possible deadlocks.
 */
static DEFINE_PER_CPU(int, softirq_from_hardirq);

static inline void lockdep_softirq_from_hardirq(void)
{
	this_cpu_write(softirq_from_hardirq, 1);
}

static inline void lockdep_softirq_start(void)
{
	if (this_cpu_read(softirq_from_hardirq))
		trace_hardirq_exit();
	lockdep_softirq_enter();
}

static inline void lockdep_softirq_end(void)
{
	lockdep_softirq_exit();
	if (this_cpu_read(softirq_from_hardirq)) {
		this_cpu_write(softirq_from_hardirq, 0);
		trace_hardirq_enter();
	}
}

#else
static inline void lockdep_softirq_from_hardirq(void) { }
static inline void lockdep_softirq_start(void) { }
static inline void lockdep_softirq_end(void) { }
#endif

asmlinkage void __do_softirq(void)
{
	unsigned long end = jiffies + MAX_SOFTIRQ_TIME;
	unsigned long old_flags = current->flags;
	int max_restart = MAX_SOFTIRQ_RESTART;
	__u32 pending;
	int cpu;

	/*
	 * Mask out PF_MEMALLOC s current task context is borrowed for the
	 * softirq. A softirq handled such as network RX might set PF_MEMALLOC
	 * again if the socket is related to swap
	 */
	current->flags &= ~PF_MEMALLOC;

	pending = local_softirq_pending();
	account_irq_enter_time(current);

	__local_bh_disable(_RET_IP_, SOFTIRQ_OFFSET);
	lockdep_softirq_start();

	cpu = smp_processor_id();
restart:
	/* Reset the pending bitmask before enabling irqs */
	set_softirq_pending(0);

	handle_pending_softirqs(pending, cpu, 1);

	pending = local_softirq_pending();
	if (pending) {
		if (time_before(jiffies, end) && !need_resched() &&
		    --max_restart)
			goto restart;

		wakeup_softirqd();
	}

	lockdep_softirq_end();
	account_irq_exit_time(current);
	__local_bh_enable(SOFTIRQ_OFFSET);
	tsk_restore_flags(current, old_flags, PF_MEMALLOC);
}

#ifndef __ARCH_HAS_DO_SOFTIRQ

asmlinkage void do_softirq(void)
{
	__u32 pending;
	unsigned long flags;

	if (in_interrupt())
		return;

	local_irq_save(flags);

	pending = local_softirq_pending();

	if (pending)
		__do_softirq();

	local_irq_restore(flags);
}

#endif

static inline void local_bh_disable_nort(void) { local_bh_disable(); }
static inline void _local_bh_enable_nort(void) { _local_bh_enable(); }
static void ksoftirqd_set_sched_params(unsigned int cpu) { }
static void ksoftirqd_clr_sched_params(unsigned int cpu, bool online) { }

#else /* !PREEMPT_RT_FULL */

/*
 * On RT we serialize softirq execution with a cpu local lock
 */
static DEFINE_LOCAL_IRQ_LOCK(local_softirq_lock);
static DEFINE_PER_CPU(struct task_struct *, local_softirq_runner);

static void __do_softirq_common(int need_rcu_bh_qs);

void __do_softirq(void)
{
	__do_softirq_common(0);
}

void __init softirq_early_init(void)
{
	local_irq_lock_init(local_softirq_lock);
}

void local_bh_disable(void)
{
	migrate_disable();
	current->softirq_nestcnt++;
}
EXPORT_SYMBOL(local_bh_disable);

void local_bh_enable(void)
{
	if (WARN_ON(current->softirq_nestcnt == 0))
		return;

	if ((current->softirq_nestcnt == 1) &&
	    local_softirq_pending() &&
	    local_trylock(local_softirq_lock)) {

		local_irq_disable();
		if (local_softirq_pending())
			__do_softirq();
		local_irq_enable();
		local_unlock(local_softirq_lock);
		WARN_ON(current->softirq_nestcnt != 1);
	}
	current->softirq_nestcnt--;
	migrate_enable();
}
EXPORT_SYMBOL(local_bh_enable);

void local_bh_enable_ip(unsigned long ip)
{
	local_bh_enable();
}
EXPORT_SYMBOL(local_bh_enable_ip);

void _local_bh_enable(void)
{
	current->softirq_nestcnt--;
	migrate_enable();
}
EXPORT_SYMBOL(_local_bh_enable);

/* For tracing */
int notrace __in_softirq(void)
{
	if (__get_cpu_var(local_softirq_lock).owner == current)
		return __get_cpu_var(local_softirq_lock).nestcnt;
	return 0;
}

int in_serving_softirq(void)
{
	int res;

	preempt_disable();
	res = __get_cpu_var(local_softirq_runner) == current;
	preempt_enable();
	return res;
}
EXPORT_SYMBOL(in_serving_softirq);

/*
 * Called with bh and local interrupts disabled. For full RT cpu must
 * be pinned.
 */
static void __do_softirq_common(int need_rcu_bh_qs)
{
	u32 pending = local_softirq_pending();
	int cpu = smp_processor_id();

	current->softirq_nestcnt++;

	/* Reset the pending bitmask before enabling irqs */
	set_softirq_pending(0);

	__get_cpu_var(local_softirq_runner) = current;

	lockdep_softirq_enter();

	handle_pending_softirqs(pending, cpu, need_rcu_bh_qs);

	pending = local_softirq_pending();
	if (pending)
		wakeup_softirqd();

	lockdep_softirq_exit();
	__get_cpu_var(local_softirq_runner) = NULL;

	current->softirq_nestcnt--;
}

static int __thread_do_softirq(int cpu)
{
	/*
	 * Prevent the current cpu from going offline.
	 * pin_current_cpu() can reenable preemption and block on the
	 * hotplug mutex. When it returns, the current cpu is
	 * pinned. It might be the wrong one, but the offline check
	 * below catches that.
	 */
	pin_current_cpu();
	/*
	 * If called from ksoftirqd (cpu >= 0) we need to check
	 * whether we are on the wrong cpu due to cpu offlining. If
	 * called via thread_do_softirq() no action required.
	 */
	if (cpu >= 0 && cpu_is_offline(cpu)) {
		unpin_current_cpu();
		return -1;
	}
	preempt_enable();
	local_lock(local_softirq_lock);
	local_irq_disable();
	/*
	 * We cannot switch stacks on RT as we want to be able to
	 * schedule!
	 */
	if (local_softirq_pending())
		__do_softirq_common(cpu >= 0);
	local_unlock(local_softirq_lock);
	unpin_current_cpu();
	preempt_disable();
	local_irq_enable();
	return 0;
}

/*
 * Called from netif_rx_ni(). Preemption enabled.
 */
void thread_do_softirq(void)
{
	if (!in_serving_softirq()) {
		preempt_disable();
		__thread_do_softirq(-1);
		preempt_enable();
	}
}

static int ksoftirqd_do_softirq(int cpu)
{
	return __thread_do_softirq(cpu);
}

static inline void local_bh_disable_nort(void) { }
static inline void _local_bh_enable_nort(void) { }

static inline void ksoftirqd_set_sched_params(unsigned int cpu)
{
	struct sched_param param = { .sched_priority = 1 };

	sched_setscheduler(current, SCHED_FIFO, &param);
}

static inline void ksoftirqd_clr_sched_params(unsigned int cpu, bool online)
{
	struct sched_param param = { .sched_priority = 0 };

	sched_setscheduler(current, SCHED_NORMAL, &param);
}

#endif /* PREEMPT_RT_FULL */
/*
 * Enter an interrupt context.
 */
void irq_enter(void)
{
	int cpu = smp_processor_id();

	rcu_irq_enter();
	if (is_idle_task(current) && !in_interrupt()) {
		/*
		 * Prevent raise_softirq from needlessly waking up ksoftirqd
		 * here, as softirq will be serviced on return from interrupt.
		 */
		local_bh_disable_nort();
		tick_check_idle(cpu);
		_local_bh_enable_nort();
	}

	__irq_enter();
}

static inline void invoke_softirq(void)
{
#ifndef CONFIG_PREEMPT_RT_FULL
	if (!force_irqthreads) {
		lockdep_softirq_from_hardirq();
		/*
		 * We can safely execute softirq on the current stack if
		 * it is the irq stack, because it should be near empty
		 * at this stage. But we have no way to know if the arch
		 * calls irq_exit() on the irq stack. So call softirq
		 * in its own stack to prevent from any overrun on top
		 * of a potentially deep task stack.
		 */
		do_softirq();
	} else {
		wakeup_softirqd();
	}
#else
	wakeup_softirqd();
#endif
}

static inline void tick_irq_exit(void)
{
#ifdef CONFIG_NO_HZ_COMMON
	int cpu = smp_processor_id();

	/* Make sure that timer wheel updates are propagated */
	if ((idle_cpu(cpu) && !need_resched()) || tick_nohz_full_cpu(cpu)) {
		if (!in_interrupt())
			tick_nohz_irq_exit();
	}
#endif
}

/*
 * Exit an interrupt context. Process softirqs if needed and possible:
 */
void irq_exit(void)
{
#ifndef __ARCH_IRQ_EXIT_IRQS_DISABLED
	local_irq_disable();
#else
	WARN_ON_ONCE(!irqs_disabled());
#endif

	account_irq_exit_time(current);
	sub_preempt_count(HARDIRQ_OFFSET);
	if (!in_interrupt() && local_softirq_pending())
		invoke_softirq();

	tick_irq_exit();
	rcu_irq_exit();
	trace_hardirq_exit(); /* must be last! */
}

/*
 * This function must run with irqs disabled!
 */
inline void raise_softirq_irqoff(unsigned int nr)
{
	__raise_softirq_irqoff(nr);

	/*
	 * If we're in an interrupt or softirq, we're done
	 * (this also catches softirq-disabled code). We will
	 * actually run the softirq once we return from
	 * the irq or softirq.
	 *
	 * Otherwise we wake up ksoftirqd to make sure we
	 * schedule the softirq soon.
	 */
	if (!in_interrupt())
		wakeup_softirqd();
}

void raise_softirq(unsigned int nr)
{
	unsigned long flags;

	local_irq_save(flags);
	raise_softirq_irqoff(nr);
	local_irq_restore(flags);
}

void __raise_softirq_irqoff(unsigned int nr)
{
	trace_softirq_raise(nr);
	or_softirq_pending(1UL << nr);
}

void open_softirq(int nr, void (*action)(struct softirq_action *))
{
	softirq_vec[nr].action = action;
}

/*
 * Tasklets
 */
struct tasklet_head
{
	struct tasklet_struct *head;
	struct tasklet_struct **tail;
};

static DEFINE_PER_CPU(struct tasklet_head, tasklet_vec);
static DEFINE_PER_CPU(struct tasklet_head, tasklet_hi_vec);

static void inline
__tasklet_common_schedule(struct tasklet_struct *t, struct tasklet_head *head, unsigned int nr)
{
	if (tasklet_trylock(t)) {
again:
		/* We may have been preempted before tasklet_trylock
		 * and __tasklet_action may have already run.
		 * So double check the sched bit while the takslet
		 * is locked before adding it to the list.
		 */
		if (test_bit(TASKLET_STATE_SCHED, &t->state)) {
			t->next = NULL;
			*head->tail = t;
			head->tail = &(t->next);
			raise_softirq_irqoff(nr);
			tasklet_unlock(t);
		} else {
			/* This is subtle. If we hit the corner case above
			 * It is possible that we get preempted right here,
			 * and another task has successfully called
			 * tasklet_schedule(), then this function, and
			 * failed on the trylock. Thus we must be sure
			 * before releasing the tasklet lock, that the
			 * SCHED_BIT is clear. Otherwise the tasklet
			 * may get its SCHED_BIT set, but not added to the
			 * list
			 */
			if (!tasklet_tryunlock(t))
				goto again;
		}
	}
}

void __tasklet_schedule(struct tasklet_struct *t)
{
	unsigned long flags;

	local_irq_save(flags);
	__tasklet_common_schedule(t, &__get_cpu_var(tasklet_vec), TASKLET_SOFTIRQ);
	local_irq_restore(flags);
}

EXPORT_SYMBOL(__tasklet_schedule);

void __tasklet_hi_schedule(struct tasklet_struct *t)
{
	unsigned long flags;

	local_irq_save(flags);
	__tasklet_common_schedule(t, &__get_cpu_var(tasklet_hi_vec), HI_SOFTIRQ);
	local_irq_restore(flags);
}

EXPORT_SYMBOL(__tasklet_hi_schedule);

void __tasklet_hi_schedule_first(struct tasklet_struct *t)
{
	__tasklet_hi_schedule(t);
}

EXPORT_SYMBOL(__tasklet_hi_schedule_first);

void  tasklet_enable(struct tasklet_struct *t)
{
	if (!atomic_dec_and_test(&t->count))
		return;
	if (test_and_clear_bit(TASKLET_STATE_PENDING, &t->state))
		tasklet_schedule(t);
}

EXPORT_SYMBOL(tasklet_enable);

void  tasklet_hi_enable(struct tasklet_struct *t)
{
	if (!atomic_dec_and_test(&t->count))
		return;
	if (test_and_clear_bit(TASKLET_STATE_PENDING, &t->state))
		tasklet_hi_schedule(t);
}

EXPORT_SYMBOL(tasklet_hi_enable);

static void
__tasklet_action(struct softirq_action *a, struct tasklet_struct *list)
{
	int loops = 1000000;

	while (list) {
		struct tasklet_struct *t = list;

		list = list->next;

		/*
		 * Should always succeed - after a tasklist got on the
		 * list (after getting the SCHED bit set from 0 to 1),
		 * nothing but the tasklet softirq it got queued to can
		 * lock it:
		 */
		if (!tasklet_trylock(t)) {
			WARN_ON(1);
			continue;
		}

		t->next = NULL;

		/*
		 * If we cannot handle the tasklet because it's disabled,
		 * mark it as pending. tasklet_enable() will later
		 * re-schedule the tasklet.
		 */
		if (unlikely(atomic_read(&t->count))) {
out_disabled:
			/* implicit unlock: */
			wmb();
			t->state = TASKLET_STATEF_PENDING;
			continue;
		}

		/*
		 * After this point on the tasklet might be rescheduled
		 * on another CPU, but it can only be added to another
		 * CPU's tasklet list if we unlock the tasklet (which we
		 * dont do yet).
		 */
		if (!test_and_clear_bit(TASKLET_STATE_SCHED, &t->state))
			WARN_ON(1);

again:
		t->func(t->data);

		/*
		 * Try to unlock the tasklet. We must use cmpxchg, because
		 * another CPU might have scheduled or disabled the tasklet.
		 * We only allow the STATE_RUN -> 0 transition here.
		 */
		while (!tasklet_tryunlock(t)) {
			/*
			 * If it got disabled meanwhile, bail out:
			 */
			if (atomic_read(&t->count))
				goto out_disabled;
			/*
			 * If it got scheduled meanwhile, re-execute
			 * the tasklet function:
			 */
			if (test_and_clear_bit(TASKLET_STATE_SCHED, &t->state))
				goto again;
			if (!--loops) {
				printk("hm, tasklet state: %08lx\n", t->state);
				WARN_ON(1);
				tasklet_unlock(t);
				break;
			}
		}
	}
}

static void tasklet_action(struct softirq_action *a)
{
	struct tasklet_struct *list;

	local_irq_disable();
	list = __get_cpu_var(tasklet_vec).head;
	__get_cpu_var(tasklet_vec).head = NULL;
	__get_cpu_var(tasklet_vec).tail = &__get_cpu_var(tasklet_vec).head;
	local_irq_enable();

	__tasklet_action(a, list);
}

static void tasklet_hi_action(struct softirq_action *a)
{
	struct tasklet_struct *list;

	local_irq_disable();
	list = __this_cpu_read(tasklet_hi_vec.head);
	__this_cpu_write(tasklet_hi_vec.head, NULL);
	__this_cpu_write(tasklet_hi_vec.tail, &__get_cpu_var(tasklet_hi_vec).head);
	local_irq_enable();

	__tasklet_action(a, list);
}


void tasklet_init(struct tasklet_struct *t,
		  void (*func)(unsigned long), unsigned long data)
{
	t->next = NULL;
	t->state = 0;
	atomic_set(&t->count, 0);
	t->func = func;
	t->data = data;
}

EXPORT_SYMBOL(tasklet_init);

void tasklet_kill(struct tasklet_struct *t)
{
	if (in_interrupt())
		printk("Attempt to kill tasklet from interrupt\n");

	while (test_and_set_bit(TASKLET_STATE_SCHED, &t->state)) {
		do {
			msleep(1);
		} while (test_bit(TASKLET_STATE_SCHED, &t->state));
	}
	tasklet_unlock_wait(t);
	clear_bit(TASKLET_STATE_SCHED, &t->state);
}

EXPORT_SYMBOL(tasklet_kill);

/*
 * tasklet_hrtimer
 */

/*
 * The trampoline is called when the hrtimer expires. It schedules a tasklet
 * to run __tasklet_hrtimer_trampoline() which in turn will call the intended
 * hrtimer callback, but from softirq context.
 */
static enum hrtimer_restart __hrtimer_tasklet_trampoline(struct hrtimer *timer)
{
	struct tasklet_hrtimer *ttimer =
		container_of(timer, struct tasklet_hrtimer, timer);

	tasklet_hi_schedule(&ttimer->tasklet);
	return HRTIMER_NORESTART;
}

/*
 * Helper function which calls the hrtimer callback from
 * tasklet/softirq context
 */
static void __tasklet_hrtimer_trampoline(unsigned long data)
{
	struct tasklet_hrtimer *ttimer = (void *)data;
	enum hrtimer_restart restart;

	restart = ttimer->function(&ttimer->timer);
	if (restart != HRTIMER_NORESTART)
		hrtimer_restart(&ttimer->timer);
}

/**
 * tasklet_hrtimer_init - Init a tasklet/hrtimer combo for softirq callbacks
 * @ttimer:	 tasklet_hrtimer which is initialized
 * @function:	 hrtimer callback function which gets called from softirq context
 * @which_clock: clock id (CLOCK_MONOTONIC/CLOCK_REALTIME)
 * @mode:	 hrtimer mode (HRTIMER_MODE_ABS/HRTIMER_MODE_REL)
 */
void tasklet_hrtimer_init(struct tasklet_hrtimer *ttimer,
			  enum hrtimer_restart (*function)(struct hrtimer *),
			  clockid_t which_clock, enum hrtimer_mode mode)
{
	hrtimer_init(&ttimer->timer, which_clock, mode);
	ttimer->timer.function = __hrtimer_tasklet_trampoline;
	tasklet_init(&ttimer->tasklet, __tasklet_hrtimer_trampoline,
		     (unsigned long)ttimer);
	ttimer->function = function;
}
EXPORT_SYMBOL_GPL(tasklet_hrtimer_init);

/*
 * Remote softirq bits
 */

DEFINE_PER_CPU(struct list_head [NR_SOFTIRQS], softirq_work_list);
EXPORT_PER_CPU_SYMBOL(softirq_work_list);

static void __local_trigger(struct call_single_data *cp, int softirq)
{
	struct list_head *head = &__get_cpu_var(softirq_work_list[softirq]);

	list_add_tail(&cp->list, head);

	/* Trigger the softirq only if the list was previously empty.  */
	if (head->next == &cp->list)
		raise_softirq_irqoff(softirq);
}

#ifdef CONFIG_USE_GENERIC_SMP_HELPERS
static void remote_softirq_receive(void *data)
{
	struct call_single_data *cp = data;
	unsigned long flags;
	int softirq;

	softirq = *(int *)cp->info;
	local_irq_save(flags);
	__local_trigger(cp, softirq);
	local_irq_restore(flags);
}

static int __try_remote_softirq(struct call_single_data *cp, int cpu, int softirq)
{
	if (cpu_online(cpu)) {
		cp->func = remote_softirq_receive;
		cp->info = &softirq;
		cp->flags = 0;

		__smp_call_function_single(cpu, cp, 0);
		return 0;
	}
	return 1;
}
#else /* CONFIG_USE_GENERIC_SMP_HELPERS */
static int __try_remote_softirq(struct call_single_data *cp, int cpu, int softirq)
{
	return 1;
}
#endif

/**
 * __send_remote_softirq - try to schedule softirq work on a remote cpu
 * @cp: private SMP call function data area
 * @cpu: the remote cpu
 * @this_cpu: the currently executing cpu
 * @softirq: the softirq for the work
 *
 * Attempt to schedule softirq work on a remote cpu.  If this cannot be
 * done, the work is instead queued up on the local cpu.
 *
 * Interrupts must be disabled.
 */
void __send_remote_softirq(struct call_single_data *cp, int cpu, int this_cpu, int softirq)
{
	if (cpu == this_cpu || __try_remote_softirq(cp, cpu, softirq))
		__local_trigger(cp, softirq);
}
EXPORT_SYMBOL(__send_remote_softirq);

/**
 * send_remote_softirq - try to schedule softirq work on a remote cpu
 * @cp: private SMP call function data area
 * @cpu: the remote cpu
 * @softirq: the softirq for the work
 *
 * Like __send_remote_softirq except that disabling interrupts and
 * computing the current cpu is done for the caller.
 */
void send_remote_softirq(struct call_single_data *cp, int cpu, int softirq)
{
	unsigned long flags;
	int this_cpu;

	local_irq_save(flags);
	this_cpu = smp_processor_id();
	__send_remote_softirq(cp, cpu, this_cpu, softirq);
	local_irq_restore(flags);
}
EXPORT_SYMBOL(send_remote_softirq);

static int remote_softirq_cpu_notify(struct notifier_block *self,
					       unsigned long action, void *hcpu)
{
	/*
	 * If a CPU goes away, splice its entries to the current CPU
	 * and trigger a run of the softirq
	 */
	if (action == CPU_DEAD || action == CPU_DEAD_FROZEN) {
		int cpu = (unsigned long) hcpu;
		int i;

		local_irq_disable();
		for (i = 0; i < NR_SOFTIRQS; i++) {
			struct list_head *head = &per_cpu(softirq_work_list[i], cpu);
			struct list_head *local_head;

			if (list_empty(head))
				continue;

			local_head = &__get_cpu_var(softirq_work_list[i]);
			list_splice_init(head, local_head);
			raise_softirq_irqoff(i);
		}
		local_irq_enable();
	}

	return NOTIFY_OK;
}

static struct notifier_block remote_softirq_cpu_notifier = {
	.notifier_call	= remote_softirq_cpu_notify,
};

void __init softirq_init(void)
{
	int cpu;

	for_each_possible_cpu(cpu) {
		int i;

		per_cpu(tasklet_vec, cpu).tail =
			&per_cpu(tasklet_vec, cpu).head;
		per_cpu(tasklet_hi_vec, cpu).tail =
			&per_cpu(tasklet_hi_vec, cpu).head;
		for (i = 0; i < NR_SOFTIRQS; i++)
			INIT_LIST_HEAD(&per_cpu(softirq_work_list[i], cpu));
	}

	register_hotcpu_notifier(&remote_softirq_cpu_notifier);

	open_softirq(TASKLET_SOFTIRQ, tasklet_action);
	open_softirq(HI_SOFTIRQ, tasklet_hi_action);
}

#if defined(CONFIG_SMP) || defined(CONFIG_PREEMPT_RT_FULL)
void tasklet_unlock_wait(struct tasklet_struct *t)
{
	while (test_bit(TASKLET_STATE_RUN, &(t)->state)) {
		/*
		 * Hack for now to avoid this busy-loop:
		 */
#ifdef CONFIG_PREEMPT_RT_FULL
		msleep(1);
#else
		barrier();
#endif
	}
}
EXPORT_SYMBOL(tasklet_unlock_wait);
#endif

static int ksoftirqd_should_run(unsigned int cpu)
{
	return local_softirq_pending();
}

static void run_ksoftirqd(unsigned int cpu)
{
	local_irq_disable();
	if (local_softirq_pending()) {
		__do_softirq();
		rcu_note_context_switch(cpu);
		local_irq_enable();
		cond_resched();
		return;
	}
	local_irq_enable();
}

#ifdef CONFIG_HOTPLUG_CPU
/*
 * tasklet_kill_immediate is called to remove a tasklet which can already be
 * scheduled for execution on @cpu.
 *
 * Unlike tasklet_kill, this function removes the tasklet
 * _immediately_, even if the tasklet is in TASKLET_STATE_SCHED state.
 *
 * When this function is called, @cpu must be in the CPU_DEAD state.
 */
void tasklet_kill_immediate(struct tasklet_struct *t, unsigned int cpu)
{
	struct tasklet_struct **i;

	BUG_ON(cpu_online(cpu));
	BUG_ON(test_bit(TASKLET_STATE_RUN, &t->state));

	if (!test_bit(TASKLET_STATE_SCHED, &t->state))
		return;

	/* CPU is dead, so no lock needed. */
	for (i = &per_cpu(tasklet_vec, cpu).head; *i; i = &(*i)->next) {
		if (*i == t) {
			*i = t->next;
			/* If this was the tail element, move the tail ptr */
			if (*i == NULL)
				per_cpu(tasklet_vec, cpu).tail = i;
			return;
		}
	}
	BUG();
}

static void takeover_tasklets(unsigned int cpu)
{
	/* CPU is dead, so no lock needed. */
	local_irq_disable();

	/* Find end, append list for that CPU. */
	if (&per_cpu(tasklet_vec, cpu).head != per_cpu(tasklet_vec, cpu).tail) {
		*__this_cpu_read(tasklet_vec.tail) = per_cpu(tasklet_vec, cpu).head;
		this_cpu_write(tasklet_vec.tail, per_cpu(tasklet_vec, cpu).tail);
		per_cpu(tasklet_vec, cpu).head = NULL;
		per_cpu(tasklet_vec, cpu).tail = &per_cpu(tasklet_vec, cpu).head;
	}
	raise_softirq_irqoff(TASKLET_SOFTIRQ);

	if (&per_cpu(tasklet_hi_vec, cpu).head != per_cpu(tasklet_hi_vec, cpu).tail) {
		*__this_cpu_read(tasklet_hi_vec.tail) = per_cpu(tasklet_hi_vec, cpu).head;
		__this_cpu_write(tasklet_hi_vec.tail, per_cpu(tasklet_hi_vec, cpu).tail);
		per_cpu(tasklet_hi_vec, cpu).head = NULL;
		per_cpu(tasklet_hi_vec, cpu).tail = &per_cpu(tasklet_hi_vec, cpu).head;
	}
	raise_softirq_irqoff(HI_SOFTIRQ);

	local_irq_enable();
}
#endif /* CONFIG_HOTPLUG_CPU */

static int cpu_callback(struct notifier_block *nfb,
				  unsigned long action,
				  void *hcpu)
{
	switch (action) {
#ifdef CONFIG_HOTPLUG_CPU
	case CPU_DEAD:
	case CPU_DEAD_FROZEN:
		takeover_tasklets((unsigned long)hcpu);
		break;
#endif /* CONFIG_HOTPLUG_CPU */
	}
	return NOTIFY_OK;
}

static struct notifier_block cpu_nfb = {
	.notifier_call = cpu_callback
};

static struct smp_hotplug_thread softirq_threads = {
	.store			= &ksoftirqd,
	.setup			= ksoftirqd_set_sched_params,
	.cleanup		= ksoftirqd_clr_sched_params,
	.thread_should_run	= ksoftirqd_should_run,
	.thread_fn		= run_ksoftirqd,
	.thread_comm		= "ksoftirqd/%u",
};

static __init int spawn_ksoftirqd(void)
{
	register_cpu_notifier(&cpu_nfb);

	BUG_ON(smpboot_register_percpu_thread(&softirq_threads));

	return 0;
}
early_initcall(spawn_ksoftirqd);

/*
 * [ These __weak aliases are kept in a separate compilation unit, so that
 *   GCC does not inline them incorrectly. ]
 */

int __init __weak early_irq_init(void)
{
	return 0;
}

int __init __weak arch_probe_nr_irqs(void)
{
	return NR_IRQS_LEGACY;
}

int __init __weak arch_early_irq_init(void)
{
	return 0;
}