summaryrefslogtreecommitdiff
path: root/kernel/softirq.c
blob: 4992853ef53d2e24a652010ddd6568cc36fdb648 (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
// SPDX-License-Identifier: GPL-2.0-only
/*
 *	linux/kernel/softirq.c
 *
 *	Copyright (C) 1992 Linus Torvalds
 *
 *	Rewritten. Old one was good in 2.2, but in 2.3 it was immoral. --ANK (990903)
 */

#define pr_fmt(fmt) KBUILD_MODNAME ": " fmt

#include <linux/export.h>
#include <linux/kernel_stat.h>
#include <linux/interrupt.h>
#include <linux/init.h>
#include <linux/local_lock.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/ftrace.h>
#include <linux/smp.h>
#include <linux/smpboot.h>
#include <linux/tick.h>
#include <linux/irq.h>
#include <linux/wait_bit.h>

#include <asm/softirq_stack.h>

#define CREATE_TRACE_POINTS
#include <trace/events/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
DEFINE_PER_CPU_ALIGNED(irq_cpustat_t, irq_stat);
EXPORT_PER_CPU_SYMBOL(irq_stat);
#endif

static struct softirq_action softirq_vec[NR_SOFTIRQS] __cacheline_aligned_in_smp;

DEFINE_PER_CPU(struct task_struct *, ksoftirqd);

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

/*
 * 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);
}

/*
 * If ksoftirqd is scheduled, we do not want to process pending softirqs
 * right now. Let ksoftirqd handle this at its own rate, to get fairness,
 * unless we're doing some of the synchronous softirqs.
 */
#define SOFTIRQ_NOW_MASK ((1 << HI_SOFTIRQ) | (1 << TASKLET_SOFTIRQ))
static bool ksoftirqd_running(unsigned long pending)
{
	struct task_struct *tsk = __this_cpu_read(ksoftirqd);

	if (pending & SOFTIRQ_NOW_MASK)
		return false;
	return tsk && (tsk->state == TASK_RUNNING) &&
		!__kthread_should_park(tsk);
}

#ifdef CONFIG_TRACE_IRQFLAGS
DEFINE_PER_CPU(int, hardirqs_enabled);
DEFINE_PER_CPU(int, hardirq_context);
EXPORT_PER_CPU_SYMBOL_GPL(hardirqs_enabled);
EXPORT_PER_CPU_SYMBOL_GPL(hardirq_context);
#endif

/*
 * SOFTIRQ_OFFSET usage:
 *
 * On !RT kernels 'count' is the preempt counter, on RT kernels this applies
 * to a per CPU counter and to task::softirqs_disabled_cnt.
 *
 * - count is changed by SOFTIRQ_OFFSET on entering or leaving softirq
 *   processing.
 *
 * - 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.
 */
#ifdef CONFIG_PREEMPT_RT

/*
 * RT accounts for BH disabled sections in task::softirqs_disabled_cnt and
 * also in per CPU softirq_ctrl::cnt. This is necessary to allow tasks in a
 * softirq disabled section to be preempted.
 *
 * The per task counter is used for softirq_count(), in_softirq() and
 * in_serving_softirqs() because these counts are only valid when the task
 * holding softirq_ctrl::lock is running.
 *
 * The per CPU counter prevents pointless wakeups of ksoftirqd in case that
 * the task which is in a softirq disabled section is preempted or blocks.
 */
struct softirq_ctrl {
	local_lock_t	lock;
	int		cnt;
};

static DEFINE_PER_CPU(struct softirq_ctrl, softirq_ctrl) = {
	.lock	= INIT_LOCAL_LOCK(softirq_ctrl.lock),
};

/**
 * local_bh_blocked() - Check for idle whether BH processing is blocked
 *
 * Returns false if the per CPU softirq::cnt is 0 otherwise true.
 *
 * This is invoked from the idle task to guard against false positive
 * softirq pending warnings, which would happen when the task which holds
 * softirq_ctrl::lock was the only running task on the CPU and blocks on
 * some other lock.
 */
bool local_bh_blocked(void)
{
	return __this_cpu_read(softirq_ctrl.cnt) != 0;
}

void __local_bh_disable_ip(unsigned long ip, unsigned int cnt)
{
	unsigned long flags;
	int newcnt;

	WARN_ON_ONCE(in_hardirq());

	/* First entry of a task into a BH disabled section? */
	if (!current->softirq_disable_cnt) {
		if (preemptible()) {
			local_lock(&softirq_ctrl.lock);
			/* Required to meet the RCU bottomhalf requirements. */
			rcu_read_lock();
		} else {
			DEBUG_LOCKS_WARN_ON(this_cpu_read(softirq_ctrl.cnt));
		}
	}

	/*
	 * Track the per CPU softirq disabled state. On RT this is per CPU
	 * state to allow preemption of bottom half disabled sections.
	 */
	newcnt = __this_cpu_add_return(softirq_ctrl.cnt, cnt);
	/*
	 * Reflect the result in the task state to prevent recursion on the
	 * local lock and to make softirq_count() & al work.
	 */
	current->softirq_disable_cnt = newcnt;

	if (IS_ENABLED(CONFIG_TRACE_IRQFLAGS) && newcnt == cnt) {
		raw_local_irq_save(flags);
		lockdep_softirqs_off(ip);
		raw_local_irq_restore(flags);
	}
}
EXPORT_SYMBOL(__local_bh_disable_ip);

static void __local_bh_enable(unsigned int cnt, bool unlock)
{
	unsigned long flags;
	int newcnt;

	DEBUG_LOCKS_WARN_ON(current->softirq_disable_cnt !=
			    this_cpu_read(softirq_ctrl.cnt));

	if (IS_ENABLED(CONFIG_TRACE_IRQFLAGS) && softirq_count() == cnt) {
		raw_local_irq_save(flags);
		lockdep_softirqs_on(_RET_IP_);
		raw_local_irq_restore(flags);
	}

	newcnt = __this_cpu_sub_return(softirq_ctrl.cnt, cnt);
	current->softirq_disable_cnt = newcnt;

	if (!newcnt && unlock) {
		rcu_read_unlock();
		local_unlock(&softirq_ctrl.lock);
	}
}

void __local_bh_enable_ip(unsigned long ip, unsigned int cnt)
{
	bool preempt_on = preemptible();
	unsigned long flags;
	u32 pending;
	int curcnt;

	WARN_ON_ONCE(in_irq());
	lockdep_assert_irqs_enabled();

	local_irq_save(flags);
	curcnt = __this_cpu_read(softirq_ctrl.cnt);

	/*
	 * If this is not reenabling soft interrupts, no point in trying to
	 * run pending ones.
	 */
	if (curcnt != cnt)
		goto out;

	pending = local_softirq_pending();
	if (!pending || ksoftirqd_running(pending))
		goto out;

	/*
	 * If this was called from non preemptible context, wake up the
	 * softirq daemon.
	 */
	if (!preempt_on) {
		wakeup_softirqd();
		goto out;
	}

	/*
	 * Adjust softirq count to SOFTIRQ_OFFSET which makes
	 * in_serving_softirq() become true.
	 */
	cnt = SOFTIRQ_OFFSET;
	__local_bh_enable(cnt, false);
	__do_softirq();

out:
	__local_bh_enable(cnt, preempt_on);
	local_irq_restore(flags);
}
EXPORT_SYMBOL(__local_bh_enable_ip);

/*
 * Invoked from ksoftirqd_run() outside of the interrupt disabled section
 * to acquire the per CPU local lock for reentrancy protection.
 */
static inline void ksoftirqd_run_begin(void)
{
	__local_bh_disable_ip(_RET_IP_, SOFTIRQ_OFFSET);
	local_irq_disable();
}

/* Counterpart to ksoftirqd_run_begin() */
static inline void ksoftirqd_run_end(void)
{
	__local_bh_enable(SOFTIRQ_OFFSET, true);
	WARN_ON_ONCE(in_interrupt());
	local_irq_enable();
}

static inline void softirq_handle_begin(void) { }
static inline void softirq_handle_end(void) { }

static inline bool should_wake_ksoftirqd(void)
{
	return !this_cpu_read(softirq_ctrl.cnt);
}

static inline void invoke_softirq(void)
{
	if (should_wake_ksoftirqd())
		wakeup_softirqd();
}

#else /* CONFIG_PREEMPT_RT */

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

	WARN_ON_ONCE(in_irq());

	raw_local_irq_save(flags);
	/*
	 * The preempt tracer hooks into preempt_count_add 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_add(cnt);
	/*
	 * Were softirqs turned off above:
	 */
	if (softirq_count() == (cnt & SOFTIRQ_MASK))
		lockdep_softirqs_off(ip);
	raw_local_irq_restore(flags);

	if (preempt_count() == cnt) {
#ifdef CONFIG_DEBUG_PREEMPT
		current->preempt_disable_ip = get_lock_parent_ip();
#endif
		trace_preempt_off(CALLER_ADDR0, get_lock_parent_ip());
	}
}
EXPORT_SYMBOL(__local_bh_disable_ip);
#endif /* CONFIG_TRACE_IRQFLAGS */

static void __local_bh_enable(unsigned int cnt)
{
	lockdep_assert_irqs_disabled();

	if (preempt_count() == cnt)
		trace_preempt_on(CALLER_ADDR0, get_lock_parent_ip());

	if (softirq_count() == (cnt & SOFTIRQ_MASK))
		lockdep_softirqs_on(_RET_IP_);

	__preempt_count_sub(cnt);
}

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

void __local_bh_enable_ip(unsigned long ip, unsigned int cnt)
{
	WARN_ON_ONCE(in_irq());
	lockdep_assert_irqs_enabled();
#ifdef CONFIG_TRACE_IRQFLAGS
	local_irq_disable();
#endif
	/*
	 * Are softirqs going to be turned on now:
	 */
	if (softirq_count() == SOFTIRQ_DISABLE_OFFSET)
		lockdep_softirqs_on(ip);
	/*
	 * Keep preemption disabled until we are done with
	 * softirq processing:
	 */
	__preempt_count_sub(cnt - 1);

	if (unlikely(!in_interrupt() && local_softirq_pending())) {
		/*
		 * Run softirq if any pending. And do it in its own stack
		 * as we may be calling this deep in a task call stack already.
		 */
		do_softirq();
	}

	preempt_count_dec();
#ifdef CONFIG_TRACE_IRQFLAGS
	local_irq_enable();
#endif
	preempt_check_resched();
}
EXPORT_SYMBOL(__local_bh_enable_ip);

static inline void softirq_handle_begin(void)
{
	__local_bh_disable_ip(_RET_IP_, SOFTIRQ_OFFSET);
}

static inline void softirq_handle_end(void)
{
	__local_bh_enable(SOFTIRQ_OFFSET);
	WARN_ON_ONCE(in_interrupt());
}

static inline void ksoftirqd_run_begin(void)
{
	local_irq_disable();
}

static inline void ksoftirqd_run_end(void)
{
	local_irq_enable();
}

static inline bool should_wake_ksoftirqd(void)
{
	return true;
}

static inline void invoke_softirq(void)
{
	if (ksoftirqd_running(local_softirq_pending()))
		return;

	if (!force_irqthreads || !__this_cpu_read(ksoftirqd)) {
#ifdef CONFIG_HAVE_IRQ_EXIT_ON_IRQ_STACK
		/*
		 * We can safely execute softirq on the current stack if
		 * it is the irq stack, because it should be near empty
		 * at this stage.
		 */
		__do_softirq();
#else
		/*
		 * Otherwise, irq_exit() is called on the task stack that can
		 * be potentially deep already. So call softirq in its own stack
		 * to prevent from any overrun.
		 */
		do_softirq_own_stack();
#endif
	} else {
		wakeup_softirqd();
	}
}

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

	if (in_interrupt())
		return;

	local_irq_save(flags);

	pending = local_softirq_pending();

	if (pending && !ksoftirqd_running(pending))
		do_softirq_own_stack();

	local_irq_restore(flags);
}

#endif /* !CONFIG_PREEMPT_RT */

/*
 * 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
/*
 * 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 inline bool lockdep_softirq_start(void)
{
	bool in_hardirq = false;

	if (lockdep_hardirq_context()) {
		in_hardirq = true;
		lockdep_hardirq_exit();
	}

	lockdep_softirq_enter();

	return in_hardirq;
}

static inline void lockdep_softirq_end(bool in_hardirq)
{
	lockdep_softirq_exit();

	if (in_hardirq)
		lockdep_hardirq_enter();
}
#else
static inline bool lockdep_softirq_start(void) { return false; }
static inline void lockdep_softirq_end(bool in_hardirq) { }
#endif

asmlinkage __visible void __softirq_entry __do_softirq(void)
{
	unsigned long end = jiffies + MAX_SOFTIRQ_TIME;
	unsigned long old_flags = current->flags;
	int max_restart = MAX_SOFTIRQ_RESTART;
	struct softirq_action *h;
	bool in_hardirq;
	__u32 pending;
	int softirq_bit;

	/*
	 * Mask out PF_MEMALLOC as the 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 swapping.
	 */
	current->flags &= ~PF_MEMALLOC;

	pending = local_softirq_pending();

	softirq_handle_begin();
	in_hardirq = lockdep_softirq_start();
	account_softirq_enter(current);

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

	local_irq_enable();

	h = softirq_vec;

	while ((softirq_bit = ffs(pending))) {
		unsigned int vec_nr;
		int prev_count;

		h += softirq_bit - 1;

		vec_nr = h - softirq_vec;
		prev_count = preempt_count();

		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, preempt_count());
			preempt_count_set(prev_count);
		}
		h++;
		pending >>= softirq_bit;
	}

	if (!IS_ENABLED(CONFIG_PREEMPT_RT) &&
	    __this_cpu_read(ksoftirqd) == current)
		rcu_softirq_qs();

	local_irq_disable();

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

		wakeup_softirqd();
	}

	account_softirq_exit(current);
	lockdep_softirq_end(in_hardirq);
	softirq_handle_end();
	current_restore_flags(old_flags, PF_MEMALLOC);
}

/**
 * irq_enter_rcu - Enter an interrupt context with RCU watching
 */
void irq_enter_rcu(void)
{
	__irq_enter_raw();

	if (is_idle_task(current) && (irq_count() == HARDIRQ_OFFSET))
		tick_irq_enter();

	account_hardirq_enter(current);
}

/**
 * irq_enter - Enter an interrupt context including RCU update
 */
void irq_enter(void)
{
	rcu_irq_enter();
	irq_enter_rcu();
}

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_irq())
			tick_nohz_irq_exit();
	}
#endif
}

static inline void __irq_exit_rcu(void)
{
#ifndef __ARCH_IRQ_EXIT_IRQS_DISABLED
	local_irq_disable();
#else
	lockdep_assert_irqs_disabled();
#endif
	account_hardirq_exit(current);
	preempt_count_sub(HARDIRQ_OFFSET);
	if (!in_interrupt() && local_softirq_pending())
		invoke_softirq();

	tick_irq_exit();
}

/**
 * irq_exit_rcu() - Exit an interrupt context without updating RCU
 *
 * Also processes softirqs if needed and possible.
 */
void irq_exit_rcu(void)
{
	__irq_exit_rcu();
	 /* must be last! */
	lockdep_hardirq_exit();
}

/**
 * irq_exit - Exit an interrupt context, update RCU and lockdep
 *
 * Also processes softirqs if needed and possible.
 */
void irq_exit(void)
{
	__irq_exit_rcu();
	rcu_irq_exit();
	 /* must be last! */
	lockdep_hardirq_exit();
}

/*
 * 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() && should_wake_ksoftirqd())
		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)
{
	lockdep_assert_irqs_disabled();
	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 __tasklet_schedule_common(struct tasklet_struct *t,
				      struct tasklet_head __percpu *headp,
				      unsigned int softirq_nr)
{
	struct tasklet_head *head;
	unsigned long flags;

	local_irq_save(flags);
	head = this_cpu_ptr(headp);
	t->next = NULL;
	*head->tail = t;
	head->tail = &(t->next);
	raise_softirq_irqoff(softirq_nr);
	local_irq_restore(flags);
}

void __tasklet_schedule(struct tasklet_struct *t)
{
	__tasklet_schedule_common(t, &tasklet_vec,
				  TASKLET_SOFTIRQ);
}
EXPORT_SYMBOL(__tasklet_schedule);

void __tasklet_hi_schedule(struct tasklet_struct *t)
{
	__tasklet_schedule_common(t, &tasklet_hi_vec,
				  HI_SOFTIRQ);
}
EXPORT_SYMBOL(__tasklet_hi_schedule);

static bool tasklet_clear_sched(struct tasklet_struct *t)
{
	if (test_and_clear_bit(TASKLET_STATE_SCHED, &t->state)) {
		wake_up_var(&t->state);
		return true;
	}

	WARN_ONCE(1, "tasklet SCHED state not set: %s %pS\n",
		  t->use_callback ? "callback" : "func",
		  t->use_callback ? (void *)t->callback : (void *)t->func);

	return false;
}

static void tasklet_action_common(struct softirq_action *a,
				  struct tasklet_head *tl_head,
				  unsigned int softirq_nr)
{
	struct tasklet_struct *list;

	local_irq_disable();
	list = tl_head->head;
	tl_head->head = NULL;
	tl_head->tail = &tl_head->head;
	local_irq_enable();

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

		list = list->next;

		if (tasklet_trylock(t)) {
			if (!atomic_read(&t->count)) {
				if (tasklet_clear_sched(t)) {
					if (t->use_callback)
						t->callback(t);
					else
						t->func(t->data);
				}
				tasklet_unlock(t);
				continue;
			}
			tasklet_unlock(t);
		}

		local_irq_disable();
		t->next = NULL;
		*tl_head->tail = t;
		tl_head->tail = &t->next;
		__raise_softirq_irqoff(softirq_nr);
		local_irq_enable();
	}
}

static __latent_entropy void tasklet_action(struct softirq_action *a)
{
	tasklet_action_common(a, this_cpu_ptr(&tasklet_vec), TASKLET_SOFTIRQ);
}

static __latent_entropy void tasklet_hi_action(struct softirq_action *a)
{
	tasklet_action_common(a, this_cpu_ptr(&tasklet_hi_vec), HI_SOFTIRQ);
}

void tasklet_setup(struct tasklet_struct *t,
		   void (*callback)(struct tasklet_struct *))
{
	t->next = NULL;
	t->state = 0;
	atomic_set(&t->count, 0);
	t->callback = callback;
	t->use_callback = true;
	t->data = 0;
}
EXPORT_SYMBOL(tasklet_setup);

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->use_callback = false;
	t->data = data;
}
EXPORT_SYMBOL(tasklet_init);

#if defined(CONFIG_SMP) || defined(CONFIG_PREEMPT_RT)
/*
 * Do not use in new code. Waiting for tasklets from atomic contexts is
 * error prone and should be avoided.
 */
void tasklet_unlock_spin_wait(struct tasklet_struct *t)
{
	while (test_bit(TASKLET_STATE_RUN, &(t)->state)) {
		if (IS_ENABLED(CONFIG_PREEMPT_RT)) {
			/*
			 * Prevent a live lock when current preempted soft
			 * interrupt processing or prevents ksoftirqd from
			 * running. If the tasklet runs on a different CPU
			 * then this has no effect other than doing the BH
			 * disable/enable dance for nothing.
			 */
			local_bh_disable();
			local_bh_enable();
		} else {
			cpu_relax();
		}
	}
}
EXPORT_SYMBOL(tasklet_unlock_spin_wait);
#endif

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

	while (test_and_set_bit(TASKLET_STATE_SCHED, &t->state))
		wait_var_event(&t->state, !test_bit(TASKLET_STATE_SCHED, &t->state));

	tasklet_unlock_wait(t);
	tasklet_clear_sched(t);
}
EXPORT_SYMBOL(tasklet_kill);

#if defined(CONFIG_SMP) || defined(CONFIG_PREEMPT_RT)
void tasklet_unlock(struct tasklet_struct *t)
{
	smp_mb__before_atomic();
	clear_bit(TASKLET_STATE_RUN, &t->state);
	smp_mb__after_atomic();
	wake_up_var(&t->state);
}
EXPORT_SYMBOL_GPL(tasklet_unlock);

void tasklet_unlock_wait(struct tasklet_struct *t)
{
	wait_var_event(&t->state, !test_bit(TASKLET_STATE_RUN, &t->state));
}
EXPORT_SYMBOL_GPL(tasklet_unlock_wait);
#endif

void __init softirq_init(void)
{
	int cpu;

	for_each_possible_cpu(cpu) {
		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;
	}

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

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

static void run_ksoftirqd(unsigned int cpu)
{
	ksoftirqd_run_begin();
	if (local_softirq_pending()) {
		/*
		 * We can safely run softirq on inline stack, as we are not deep
		 * in the task stack here.
		 */
		__do_softirq();
		ksoftirqd_run_end();
		cond_resched();
		return;
	}
	ksoftirqd_run_end();
}

#ifdef CONFIG_HOTPLUG_CPU
static int 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();
	return 0;
}
#else
#define takeover_tasklets	NULL
#endif /* CONFIG_HOTPLUG_CPU */

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

static __init int spawn_ksoftirqd(void)
{
	cpuhp_setup_state_nocalls(CPUHP_SOFTIRQ_DEAD, "softirq:dead", NULL,
				  takeover_tasklets);
	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;
}

unsigned int __weak arch_dynirq_lower_bound(unsigned int from)
{
	return from;
}