summaryrefslogtreecommitdiff
path: root/arch/powerpc/kernel/irq.c
blob: 85c48911938a7cba9ad23405948f80fcae943f8a (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
/*
 *  Derived from arch/i386/kernel/irq.c
 *    Copyright (C) 1992 Linus Torvalds
 *  Adapted from arch/i386 by Gary Thomas
 *    Copyright (C) 1995-1996 Gary Thomas (gdt@linuxppc.org)
 *  Updated and modified by Cort Dougan <cort@fsmlabs.com>
 *    Copyright (C) 1996-2001 Cort Dougan
 *  Adapted for Power Macintosh by Paul Mackerras
 *    Copyright (C) 1996 Paul Mackerras (paulus@cs.anu.edu.au)
 *
 * This program is free software; you can redistribute it and/or
 * modify it under the terms of the GNU General Public License
 * as published by the Free Software Foundation; either version
 * 2 of the License, or (at your option) any later version.
 *
 * This file contains the code used by various IRQ handling routines:
 * asking for different IRQ's should be done through these routines
 * instead of just grabbing them. Thus setups with different IRQ numbers
 * shouldn't result in any weird surprises, and installing new handlers
 * should be easier.
 *
 * The MPC8xx has an interrupt mask in the SIU.  If a bit is set, the
 * interrupt is _enabled_.  As expected, IRQ0 is bit 0 in the 32-bit
 * mask register (of which only 16 are defined), hence the weird shifting
 * and complement of the cached_irq_mask.  I want to be able to stuff
 * this right into the SIU SMASK register.
 * Many of the prep/chrp functions are conditional compiled on CONFIG_PPC_8xx
 * to reduce code space and undefined function references.
 */

#undef DEBUG

#include <linux/export.h>
#include <linux/threads.h>
#include <linux/kernel_stat.h>
#include <linux/signal.h>
#include <linux/sched.h>
#include <linux/ptrace.h>
#include <linux/ioport.h>
#include <linux/interrupt.h>
#include <linux/timex.h>
#include <linux/init.h>
#include <linux/slab.h>
#include <linux/delay.h>
#include <linux/irq.h>
#include <linux/seq_file.h>
#include <linux/cpumask.h>
#include <linux/profile.h>
#include <linux/bitops.h>
#include <linux/list.h>
#include <linux/radix-tree.h>
#include <linux/mutex.h>
#include <linux/pci.h>
#include <linux/debugfs.h>
#include <linux/of.h>
#include <linux/of_irq.h>

#include <linux/uaccess.h>
#include <asm/io.h>
#include <asm/pgtable.h>
#include <asm/irq.h>
#include <asm/cache.h>
#include <asm/prom.h>
#include <asm/ptrace.h>
#include <asm/machdep.h>
#include <asm/udbg.h>
#include <asm/smp.h>
#include <asm/livepatch.h>
#include <asm/asm-prototypes.h>
#include <asm/hw_irq.h>

#ifdef CONFIG_PPC64
#include <asm/paca.h>
#include <asm/firmware.h>
#include <asm/lv1call.h>
#endif
#define CREATE_TRACE_POINTS
#include <asm/trace.h>
#include <asm/cpu_has_feature.h>

DEFINE_PER_CPU_SHARED_ALIGNED(irq_cpustat_t, irq_stat);
EXPORT_PER_CPU_SYMBOL(irq_stat);

int __irq_offset_value;

#ifdef CONFIG_PPC32
EXPORT_SYMBOL(__irq_offset_value);
atomic_t ppc_n_lost_interrupts;

#ifdef CONFIG_TAU_INT
extern int tau_initialized;
u32 tau_interrupts(unsigned long cpu);
#endif
#endif /* CONFIG_PPC32 */

#ifdef CONFIG_PPC64

int distribute_irqs = 1;

static inline notrace unsigned long get_irq_happened(void)
{
	unsigned long happened;

	__asm__ __volatile__("lbz %0,%1(13)"
	: "=r" (happened) : "i" (offsetof(struct paca_struct, irq_happened)));

	return happened;
}

static inline notrace int decrementer_check_overflow(void)
{
 	u64 now = get_tb_or_rtc();
	u64 *next_tb = this_cpu_ptr(&decrementers_next_tb);
 
	return now >= *next_tb;
}

/* This is called whenever we are re-enabling interrupts
 * and returns either 0 (nothing to do) or 500/900/280/a00/e80 if
 * there's an EE, DEC or DBELL to generate.
 *
 * This is called in two contexts: From arch_local_irq_restore()
 * before soft-enabling interrupts, and from the exception exit
 * path when returning from an interrupt from a soft-disabled to
 * a soft enabled context. In both case we have interrupts hard
 * disabled.
 *
 * We take care of only clearing the bits we handled in the
 * PACA irq_happened field since we can only re-emit one at a
 * time and we don't want to "lose" one.
 */
notrace unsigned int __check_irq_replay(void)
{
	/*
	 * We use local_paca rather than get_paca() to avoid all
	 * the debug_smp_processor_id() business in this low level
	 * function
	 */
	unsigned char happened = local_paca->irq_happened;

	/*
	 * We are responding to the next interrupt, so interrupt-off
	 * latencies should be reset here.
	 */
	trace_hardirqs_on();
	trace_hardirqs_off();

	/*
	 * We are always hard disabled here, but PACA_IRQ_HARD_DIS may
	 * not be set, which means interrupts have only just been hard
	 * disabled as part of the local_irq_restore or interrupt return
	 * code. In that case, skip the decrementr check becaus it's
	 * expensive to read the TB.
	 *
	 * HARD_DIS then gets cleared here, but it's reconciled later.
	 * Either local_irq_disable will replay the interrupt and that
	 * will reconcile state like other hard interrupts. Or interrupt
	 * retur will replay the interrupt and in that case it sets
	 * PACA_IRQ_HARD_DIS by hand (see comments in entry_64.S).
	 */
	if (happened & PACA_IRQ_HARD_DIS) {
		local_paca->irq_happened &= ~PACA_IRQ_HARD_DIS;

		/*
		 * We may have missed a decrementer interrupt if hard disabled.
		 * Check the decrementer register in case we had a rollover
		 * while hard disabled.
		 */
		if (!(happened & PACA_IRQ_DEC)) {
			if (decrementer_check_overflow()) {
				local_paca->irq_happened |= PACA_IRQ_DEC;
				happened |= PACA_IRQ_DEC;
			}
		}
	}

	/*
	 * Force the delivery of pending soft-disabled interrupts on PS3.
	 * Any HV call will have this side effect.
	 */
	if (firmware_has_feature(FW_FEATURE_PS3_LV1)) {
		u64 tmp, tmp2;
		lv1_get_version_info(&tmp, &tmp2);
	}

	/*
	 * Check if an hypervisor Maintenance interrupt happened.
	 * This is a higher priority interrupt than the others, so
	 * replay it first.
	 */
	if (happened & PACA_IRQ_HMI) {
		local_paca->irq_happened &= ~PACA_IRQ_HMI;
		return 0xe60;
	}

	if (happened & PACA_IRQ_DEC) {
		local_paca->irq_happened &= ~PACA_IRQ_DEC;
		return 0x900;
	}

	if (happened & PACA_IRQ_PMI) {
		local_paca->irq_happened &= ~PACA_IRQ_PMI;
		return 0xf00;
	}

	if (happened & PACA_IRQ_EE) {
		local_paca->irq_happened &= ~PACA_IRQ_EE;
		return 0x500;
	}

#ifdef CONFIG_PPC_BOOK3E
	/*
	 * Check if an EPR external interrupt happened this bit is typically
	 * set if we need to handle another "edge" interrupt from within the
	 * MPIC "EPR" handler.
	 */
	if (happened & PACA_IRQ_EE_EDGE) {
		local_paca->irq_happened &= ~PACA_IRQ_EE_EDGE;
		return 0x500;
	}

	if (happened & PACA_IRQ_DBELL) {
		local_paca->irq_happened &= ~PACA_IRQ_DBELL;
		return 0x280;
	}
#else
	if (happened & PACA_IRQ_DBELL) {
		local_paca->irq_happened &= ~PACA_IRQ_DBELL;
		return 0xa00;
	}
#endif /* CONFIG_PPC_BOOK3E */

	/* There should be nothing left ! */
	BUG_ON(local_paca->irq_happened != 0);

	return 0;
}

notrace void arch_local_irq_restore(unsigned long mask)
{
	unsigned char irq_happened;
	unsigned int replay;

	/* Write the new soft-enabled value */
	irq_soft_mask_set(mask);
	if (mask)
		return;

	/*
	 * From this point onward, we can take interrupts, preempt,
	 * etc... unless we got hard-disabled. We check if an event
	 * happened. If none happened, we know we can just return.
	 *
	 * We may have preempted before the check below, in which case
	 * we are checking the "new" CPU instead of the old one. This
	 * is only a problem if an event happened on the "old" CPU.
	 *
	 * External interrupt events will have caused interrupts to
	 * be hard-disabled, so there is no problem, we
	 * cannot have preempted.
	 */
	irq_happened = get_irq_happened();
	if (!irq_happened) {
		/*
		 * FIXME. Here we'd like to be able to do:
		 *
		 * #ifdef CONFIG_PPC_IRQ_SOFT_MASK_DEBUG
		 *   WARN_ON(!(mfmsr() & MSR_EE));
		 * #endif
		 *
		 * But currently it hits in a few paths, we should fix those and
		 * enable the warning.
		 */
		return;
	}

	/*
	 * We need to hard disable to get a trusted value from
	 * __check_irq_replay(). We also need to soft-disable
	 * again to avoid warnings in there due to the use of
	 * per-cpu variables.
	 */
	if (!(irq_happened & PACA_IRQ_HARD_DIS)) {
#ifdef CONFIG_PPC_IRQ_SOFT_MASK_DEBUG
		WARN_ON(!(mfmsr() & MSR_EE));
#endif
		__hard_irq_disable();
#ifdef CONFIG_PPC_IRQ_SOFT_MASK_DEBUG
	} else {
		/*
		 * We should already be hard disabled here. We had bugs
		 * where that wasn't the case so let's dbl check it and
		 * warn if we are wrong. Only do that when IRQ tracing
		 * is enabled as mfmsr() can be costly.
		 */
		if (WARN_ON(mfmsr() & MSR_EE))
			__hard_irq_disable();
#endif
	}

	irq_soft_mask_set(IRQS_ALL_DISABLED);
	trace_hardirqs_off();

	/*
	 * Check if anything needs to be re-emitted. We haven't
	 * soft-enabled yet to avoid warnings in decrementer_check_overflow
	 * accessing per-cpu variables
	 */
	replay = __check_irq_replay();

	/* We can soft-enable now */
	trace_hardirqs_on();
	irq_soft_mask_set(IRQS_ENABLED);

	/*
	 * And replay if we have to. This will return with interrupts
	 * hard-enabled.
	 */
	if (replay) {
		__replay_interrupt(replay);
		return;
	}

	/* Finally, let's ensure we are hard enabled */
	__hard_irq_enable();
}
EXPORT_SYMBOL(arch_local_irq_restore);

/*
 * This is specifically called by assembly code to re-enable interrupts
 * if they are currently disabled. This is typically called before
 * schedule() or do_signal() when returning to userspace. We do it
 * in C to avoid the burden of dealing with lockdep etc...
 *
 * NOTE: This is called with interrupts hard disabled but not marked
 * as such in paca->irq_happened, so we need to resync this.
 */
void notrace restore_interrupts(void)
{
	if (irqs_disabled()) {
		local_paca->irq_happened |= PACA_IRQ_HARD_DIS;
		local_irq_enable();
	} else
		__hard_irq_enable();
}

/*
 * This is a helper to use when about to go into idle low-power
 * when the latter has the side effect of re-enabling interrupts
 * (such as calling H_CEDE under pHyp).
 *
 * You call this function with interrupts soft-disabled (this is
 * already the case when ppc_md.power_save is called). The function
 * will return whether to enter power save or just return.
 *
 * In the former case, it will have notified lockdep of interrupts
 * being re-enabled and generally sanitized the lazy irq state,
 * and in the latter case it will leave with interrupts hard
 * disabled and marked as such, so the local_irq_enable() call
 * in arch_cpu_idle() will properly re-enable everything.
 */
bool prep_irq_for_idle(void)
{
	/*
	 * First we need to hard disable to ensure no interrupt
	 * occurs before we effectively enter the low power state
	 */
	__hard_irq_disable();
	local_paca->irq_happened |= PACA_IRQ_HARD_DIS;

	/*
	 * If anything happened while we were soft-disabled,
	 * we return now and do not enter the low power state.
	 */
	if (lazy_irq_pending())
		return false;

	/* Tell lockdep we are about to re-enable */
	trace_hardirqs_on();

	/*
	 * Mark interrupts as soft-enabled and clear the
	 * PACA_IRQ_HARD_DIS from the pending mask since we
	 * are about to hard enable as well as a side effect
	 * of entering the low power state.
	 */
	local_paca->irq_happened &= ~PACA_IRQ_HARD_DIS;
	irq_soft_mask_set(IRQS_ENABLED);

	/* Tell the caller to enter the low power state */
	return true;
}

#ifdef CONFIG_PPC_BOOK3S
/*
 * This is for idle sequences that return with IRQs off, but the
 * idle state itself wakes on interrupt. Tell the irq tracer that
 * IRQs are enabled for the duration of idle so it does not get long
 * off times. Must be paired with fini_irq_for_idle_irqsoff.
 */
bool prep_irq_for_idle_irqsoff(void)
{
	WARN_ON(!irqs_disabled());

	/*
	 * First we need to hard disable to ensure no interrupt
	 * occurs before we effectively enter the low power state
	 */
	__hard_irq_disable();
	local_paca->irq_happened |= PACA_IRQ_HARD_DIS;

	/*
	 * If anything happened while we were soft-disabled,
	 * we return now and do not enter the low power state.
	 */
	if (lazy_irq_pending())
		return false;

	/* Tell lockdep we are about to re-enable */
	trace_hardirqs_on();

	return true;
}

/*
 * Take the SRR1 wakeup reason, index into this table to find the
 * appropriate irq_happened bit.
 *
 * Sytem reset exceptions taken in idle state also come through here,
 * but they are NMI interrupts so do not need to wait for IRQs to be
 * restored, and should be taken as early as practical. These are marked
 * with 0xff in the table. The Power ISA specifies 0100b as the system
 * reset interrupt reason.
 */
#define IRQ_SYSTEM_RESET	0xff

static const u8 srr1_to_lazyirq[0x10] = {
	0, 0, 0,
	PACA_IRQ_DBELL,
	IRQ_SYSTEM_RESET,
	PACA_IRQ_DBELL,
	PACA_IRQ_DEC,
	0,
	PACA_IRQ_EE,
	PACA_IRQ_EE,
	PACA_IRQ_HMI,
	0, 0, 0, 0, 0 };

void replay_system_reset(void)
{
	struct pt_regs regs;

	ppc_save_regs(&regs);
	regs.trap = 0x100;
	get_paca()->in_nmi = 1;
	system_reset_exception(&regs);
	get_paca()->in_nmi = 0;
}
EXPORT_SYMBOL_GPL(replay_system_reset);

void irq_set_pending_from_srr1(unsigned long srr1)
{
	unsigned int idx = (srr1 & SRR1_WAKEMASK_P8) >> 18;
	u8 reason = srr1_to_lazyirq[idx];

	/*
	 * Take the system reset now, which is immediately after registers
	 * are restored from idle. It's an NMI, so interrupts need not be
	 * re-enabled before it is taken.
	 */
	if (unlikely(reason == IRQ_SYSTEM_RESET)) {
		replay_system_reset();
		return;
	}

	/*
	 * The 0 index (SRR1[42:45]=b0000) must always evaluate to 0,
	 * so this can be called unconditionally with the SRR1 wake
	 * reason as returned by the idle code, which uses 0 to mean no
	 * interrupt.
	 *
	 * If a future CPU was to designate this as an interrupt reason,
	 * then a new index for no interrupt must be assigned.
	 */
	local_paca->irq_happened |= reason;
}
#endif /* CONFIG_PPC_BOOK3S */

/*
 * Force a replay of the external interrupt handler on this CPU.
 */
void force_external_irq_replay(void)
{
	/*
	 * This must only be called with interrupts soft-disabled,
	 * the replay will happen when re-enabling.
	 */
	WARN_ON(!arch_irqs_disabled());

	/*
	 * Interrupts must always be hard disabled before irq_happened is
	 * modified (to prevent lost update in case of interrupt between
	 * load and store).
	 */
	__hard_irq_disable();
	local_paca->irq_happened |= PACA_IRQ_HARD_DIS;

	/* Indicate in the PACA that we have an interrupt to replay */
	local_paca->irq_happened |= PACA_IRQ_EE;
}

#endif /* CONFIG_PPC64 */

int arch_show_interrupts(struct seq_file *p, int prec)
{
	int j;

#if defined(CONFIG_PPC32) && defined(CONFIG_TAU_INT)
	if (tau_initialized) {
		seq_printf(p, "%*s: ", prec, "TAU");
		for_each_online_cpu(j)
			seq_printf(p, "%10u ", tau_interrupts(j));
		seq_puts(p, "  PowerPC             Thermal Assist (cpu temp)\n");
	}
#endif /* CONFIG_PPC32 && CONFIG_TAU_INT */

	seq_printf(p, "%*s: ", prec, "LOC");
	for_each_online_cpu(j)
		seq_printf(p, "%10u ", per_cpu(irq_stat, j).timer_irqs_event);
        seq_printf(p, "  Local timer interrupts for timer event device\n");

	seq_printf(p, "%*s: ", prec, "BCT");
	for_each_online_cpu(j)
		seq_printf(p, "%10u ", per_cpu(irq_stat, j).broadcast_irqs_event);
	seq_printf(p, "  Broadcast timer interrupts for timer event device\n");

	seq_printf(p, "%*s: ", prec, "LOC");
	for_each_online_cpu(j)
		seq_printf(p, "%10u ", per_cpu(irq_stat, j).timer_irqs_others);
        seq_printf(p, "  Local timer interrupts for others\n");

	seq_printf(p, "%*s: ", prec, "SPU");
	for_each_online_cpu(j)
		seq_printf(p, "%10u ", per_cpu(irq_stat, j).spurious_irqs);
	seq_printf(p, "  Spurious interrupts\n");

	seq_printf(p, "%*s: ", prec, "PMI");
	for_each_online_cpu(j)
		seq_printf(p, "%10u ", per_cpu(irq_stat, j).pmu_irqs);
	seq_printf(p, "  Performance monitoring interrupts\n");

	seq_printf(p, "%*s: ", prec, "MCE");
	for_each_online_cpu(j)
		seq_printf(p, "%10u ", per_cpu(irq_stat, j).mce_exceptions);
	seq_printf(p, "  Machine check exceptions\n");

	if (cpu_has_feature(CPU_FTR_HVMODE)) {
		seq_printf(p, "%*s: ", prec, "HMI");
		for_each_online_cpu(j)
			seq_printf(p, "%10u ",
					per_cpu(irq_stat, j).hmi_exceptions);
		seq_printf(p, "  Hypervisor Maintenance Interrupts\n");
	}

	seq_printf(p, "%*s: ", prec, "NMI");
	for_each_online_cpu(j)
		seq_printf(p, "%10u ", per_cpu(irq_stat, j).sreset_irqs);
	seq_printf(p, "  System Reset interrupts\n");

#ifdef CONFIG_PPC_WATCHDOG
	seq_printf(p, "%*s: ", prec, "WDG");
	for_each_online_cpu(j)
		seq_printf(p, "%10u ", per_cpu(irq_stat, j).soft_nmi_irqs);
	seq_printf(p, "  Watchdog soft-NMI interrupts\n");
#endif

#ifdef CONFIG_PPC_DOORBELL
	if (cpu_has_feature(CPU_FTR_DBELL)) {
		seq_printf(p, "%*s: ", prec, "DBL");
		for_each_online_cpu(j)
			seq_printf(p, "%10u ", per_cpu(irq_stat, j).doorbell_irqs);
		seq_printf(p, "  Doorbell interrupts\n");
	}
#endif

	return 0;
}

/*
 * /proc/stat helpers
 */
u64 arch_irq_stat_cpu(unsigned int cpu)
{
	u64 sum = per_cpu(irq_stat, cpu).timer_irqs_event;

	sum += per_cpu(irq_stat, cpu).broadcast_irqs_event;
	sum += per_cpu(irq_stat, cpu).pmu_irqs;
	sum += per_cpu(irq_stat, cpu).mce_exceptions;
	sum += per_cpu(irq_stat, cpu).spurious_irqs;
	sum += per_cpu(irq_stat, cpu).timer_irqs_others;
	sum += per_cpu(irq_stat, cpu).hmi_exceptions;
	sum += per_cpu(irq_stat, cpu).sreset_irqs;
#ifdef CONFIG_PPC_WATCHDOG
	sum += per_cpu(irq_stat, cpu).soft_nmi_irqs;
#endif
#ifdef CONFIG_PPC_DOORBELL
	sum += per_cpu(irq_stat, cpu).doorbell_irqs;
#endif

	return sum;
}

static inline void check_stack_overflow(void)
{
#ifdef CONFIG_DEBUG_STACKOVERFLOW
	long sp;

	sp = current_stack_pointer() & (THREAD_SIZE-1);

	/* check for stack overflow: is there less than 2KB free? */
	if (unlikely(sp < (sizeof(struct thread_info) + 2048))) {
		pr_err("do_IRQ: stack overflow: %ld\n",
			sp - sizeof(struct thread_info));
		dump_stack();
	}
#endif
}

void __do_irq(struct pt_regs *regs)
{
	unsigned int irq;

	irq_enter();

	trace_irq_entry(regs);

	check_stack_overflow();

	/*
	 * Query the platform PIC for the interrupt & ack it.
	 *
	 * This will typically lower the interrupt line to the CPU
	 */
	irq = ppc_md.get_irq();

	/* We can hard enable interrupts now to allow perf interrupts */
	may_hard_irq_enable();

	/* And finally process it */
	if (unlikely(!irq))
		__this_cpu_inc(irq_stat.spurious_irqs);
	else
		generic_handle_irq(irq);

	trace_irq_exit(regs);

	irq_exit();
}

void do_IRQ(struct pt_regs *regs)
{
	struct pt_regs *old_regs = set_irq_regs(regs);
	struct thread_info *curtp, *irqtp, *sirqtp;

	/* Switch to the irq stack to handle this */
	curtp = (void *)(current_stack_pointer() & ~(THREAD_SIZE - 1));
	irqtp = hardirq_ctx[raw_smp_processor_id()];
	sirqtp = softirq_ctx[raw_smp_processor_id()];

	/* Already there ? */
	if (unlikely(curtp == irqtp || curtp == sirqtp)) {
		__do_irq(regs);
		set_irq_regs(old_regs);
		return;
	}
	/* Switch stack and call */
	call_do_irq(regs, irqtp);

	set_irq_regs(old_regs);
}

void __init init_IRQ(void)
{
	if (ppc_md.init_IRQ)
		ppc_md.init_IRQ();
}

#if defined(CONFIG_BOOKE) || defined(CONFIG_40x)
struct thread_info   *critirq_ctx[NR_CPUS] __read_mostly;
struct thread_info    *dbgirq_ctx[NR_CPUS] __read_mostly;
struct thread_info *mcheckirq_ctx[NR_CPUS] __read_mostly;
#endif

struct thread_info *softirq_ctx[NR_CPUS] __read_mostly;
struct thread_info *hardirq_ctx[NR_CPUS] __read_mostly;

void do_softirq_own_stack(void)
{
	struct thread_info *irqtp;

	irqtp = softirq_ctx[smp_processor_id()];
	call_do_softirq(irqtp);
}

irq_hw_number_t virq_to_hw(unsigned int virq)
{
	struct irq_data *irq_data = irq_get_irq_data(virq);
	return WARN_ON(!irq_data) ? 0 : irq_data->hwirq;
}
EXPORT_SYMBOL_GPL(virq_to_hw);

#ifdef CONFIG_SMP
int irq_choose_cpu(const struct cpumask *mask)
{
	int cpuid;

	if (cpumask_equal(mask, cpu_online_mask)) {
		static int irq_rover;
		static DEFINE_RAW_SPINLOCK(irq_rover_lock);
		unsigned long flags;

		/* Round-robin distribution... */
do_round_robin:
		raw_spin_lock_irqsave(&irq_rover_lock, flags);

		irq_rover = cpumask_next(irq_rover, cpu_online_mask);
		if (irq_rover >= nr_cpu_ids)
			irq_rover = cpumask_first(cpu_online_mask);

		cpuid = irq_rover;

		raw_spin_unlock_irqrestore(&irq_rover_lock, flags);
	} else {
		cpuid = cpumask_first_and(mask, cpu_online_mask);
		if (cpuid >= nr_cpu_ids)
			goto do_round_robin;
	}

	return get_hard_smp_processor_id(cpuid);
}
#else
int irq_choose_cpu(const struct cpumask *mask)
{
	return hard_smp_processor_id();
}
#endif

#ifdef CONFIG_PPC64
static int __init setup_noirqdistrib(char *str)
{
	distribute_irqs = 0;
	return 1;
}

__setup("noirqdistrib", setup_noirqdistrib);
#endif /* CONFIG_PPC64 */