summaryrefslogtreecommitdiffstats
path: root/kernel/irq/handle.c
blob: fc27d76e83ef5f3c45c0eeb2554acb9e81f21af9 (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
/*
 * linux/kernel/irq/handle.c
 *
 * Copyright (C) 1992, 1998-2006 Linus Torvalds, Ingo Molnar
 * Copyright (C) 2005-2006, Thomas Gleixner, Russell King
 *
 * This file contains the core interrupt handling code.
 *
 * Detailed information is available in Documentation/DocBook/genericirq
 *
 */

#include <linux/irq.h>
#include <linux/sched.h>
#include <linux/slab.h>
#include <linux/module.h>
#include <linux/random.h>
#include <linux/interrupt.h>
#include <linux/kernel_stat.h>
#include <linux/rculist.h>
#include <linux/hash.h>
#include <linux/radix-tree.h>
#include <trace/events/irq.h>

#include "internals.h"

/*
 * lockdep: we want to handle all irq_desc locks as a single lock-class:
 */
struct lock_class_key irq_desc_lock_class;

/**
 * handle_bad_irq - handle spurious and unhandled irqs
 * @irq:       the interrupt number
 * @desc:      description of the interrupt
 *
 * Handles spurious and unhandled IRQ's. It also prints a debugmessage.
 */
void handle_bad_irq(unsigned int irq, struct irq_desc *desc)
{
	print_irq_desc(irq, desc);
	kstat_incr_irqs_this_cpu(irq, desc);
	ack_bad_irq(irq);
}

#if defined(CONFIG_SMP) && defined(CONFIG_GENERIC_HARDIRQS)
static void __init init_irq_default_affinity(void)
{
	alloc_cpumask_var(&irq_default_affinity, GFP_NOWAIT);
	cpumask_setall(irq_default_affinity);
}
#else
static void __init init_irq_default_affinity(void)
{
}
#endif

/*
 * Linux has a controller-independent interrupt architecture.
 * Every controller has a 'controller-template', that is used
 * by the main code to do the right thing. Each driver-visible
 * interrupt source is transparently wired to the appropriate
 * controller. Thus drivers need not be aware of the
 * interrupt-controller.
 *
 * The code is designed to be easily extended with new/different
 * interrupt controllers, without having to do assembly magic or
 * having to touch the generic code.
 *
 * Controller mappings for all interrupt sources:
 */
int nr_irqs = NR_IRQS;
EXPORT_SYMBOL_GPL(nr_irqs);

#ifdef CONFIG_SPARSE_IRQ

static struct irq_desc irq_desc_init = {
	.status		= IRQ_DISABLED,
	.handle_irq	= handle_bad_irq,
	.depth		= 1,
	.lock		= __RAW_SPIN_LOCK_UNLOCKED(irq_desc_init.lock),
};

void __ref init_kstat_irqs(struct irq_desc *desc, int node, int nr)
{
	void *ptr;

	ptr = kzalloc_node(nr * sizeof(*desc->kstat_irqs),
			   GFP_ATOMIC, node);

	/*
	 * don't overwite if can not get new one
	 * init_copy_kstat_irqs() could still use old one
	 */
	if (ptr) {
		printk(KERN_DEBUG "  alloc kstat_irqs on node %d\n", node);
		desc->kstat_irqs = ptr;
	}
}

static void init_one_irq_desc(int irq, struct irq_desc *desc, int node)
{
	memcpy(desc, &irq_desc_init, sizeof(struct irq_desc));

	raw_spin_lock_init(&desc->lock);
	desc->irq_data.irq = irq;
#ifdef CONFIG_SMP
	desc->irq_data.node = node;
#endif
	lockdep_set_class(&desc->lock, &irq_desc_lock_class);
	init_kstat_irqs(desc, node, nr_cpu_ids);
	if (!desc->kstat_irqs) {
		printk(KERN_ERR "can not alloc kstat_irqs\n");
		BUG_ON(1);
	}
	if (!alloc_desc_masks(desc, node, false)) {
		printk(KERN_ERR "can not alloc irq_desc cpumasks\n");
		BUG_ON(1);
	}
	init_desc_masks(desc);
	arch_init_chip_data(desc, node);
}

/*
 * Protect the sparse_irqs:
 */
DEFINE_RAW_SPINLOCK(sparse_irq_lock);

static RADIX_TREE(irq_desc_tree, GFP_ATOMIC);

static void set_irq_desc(unsigned int irq, struct irq_desc *desc)
{
	radix_tree_insert(&irq_desc_tree, irq, desc);
}

struct irq_desc *irq_to_desc(unsigned int irq)
{
	return radix_tree_lookup(&irq_desc_tree, irq);
}

void replace_irq_desc(unsigned int irq, struct irq_desc *desc)
{
	void **ptr;

	ptr = radix_tree_lookup_slot(&irq_desc_tree, irq);
	if (ptr)
		radix_tree_replace_slot(ptr, desc);
}

static struct irq_desc irq_desc_legacy[NR_IRQS_LEGACY] __cacheline_aligned_in_smp = {
	[0 ... NR_IRQS_LEGACY-1] = {
		.status		= IRQ_DISABLED,
		.handle_irq	= handle_bad_irq,
		.depth		= 1,
		.lock		= __RAW_SPIN_LOCK_UNLOCKED(irq_desc_init.lock),
	}
};

static unsigned int *kstat_irqs_legacy;

int __init early_irq_init(void)
{
	struct irq_desc *desc;
	int legacy_count;
	int node;
	int i;

	init_irq_default_affinity();

	 /* initialize nr_irqs based on nr_cpu_ids */
	arch_probe_nr_irqs();
	printk(KERN_INFO "NR_IRQS:%d nr_irqs:%d\n", NR_IRQS, nr_irqs);

	desc = irq_desc_legacy;
	legacy_count = ARRAY_SIZE(irq_desc_legacy);
	node = first_online_node;

	/* allocate based on nr_cpu_ids */
	kstat_irqs_legacy = kzalloc_node(NR_IRQS_LEGACY * nr_cpu_ids *
					  sizeof(int), GFP_NOWAIT, node);

	irq_desc_init.irq_data.chip = &no_irq_chip;

	for (i = 0; i < legacy_count; i++) {
		desc[i].irq_data.irq = i;
		desc[i].irq_data.chip = &no_irq_chip;
#ifdef CONFIG_SMP
		desc[i].irq_data.node = node;
#endif
		desc[i].kstat_irqs = kstat_irqs_legacy + i * nr_cpu_ids;
		lockdep_set_class(&desc[i].lock, &irq_desc_lock_class);
		alloc_desc_masks(&desc[i], node, true);
		init_desc_masks(&desc[i]);
		set_irq_desc(i, &desc[i]);
	}

	return arch_early_irq_init();
}

struct irq_desc * __ref irq_to_desc_alloc_node(unsigned int irq, int node)
{
	struct irq_desc *desc;
	unsigned long flags;

	if (irq >= nr_irqs) {
		WARN(1, "irq (%d) >= nr_irqs (%d) in irq_to_desc_alloc\n",
			irq, nr_irqs);
		return NULL;
	}

	desc = irq_to_desc(irq);
	if (desc)
		return desc;

	raw_spin_lock_irqsave(&sparse_irq_lock, flags);

	/* We have to check it to avoid races with another CPU */
	desc = irq_to_desc(irq);
	if (desc)
		goto out_unlock;

	desc = kzalloc_node(sizeof(*desc), GFP_ATOMIC, node);

	printk(KERN_DEBUG "  alloc irq_desc for %d on node %d\n", irq, node);
	if (!desc) {
		printk(KERN_ERR "can not alloc irq_desc\n");
		BUG_ON(1);
	}
	init_one_irq_desc(irq, desc, node);

	set_irq_desc(irq, desc);

out_unlock:
	raw_spin_unlock_irqrestore(&sparse_irq_lock, flags);

	return desc;
}

#else /* !CONFIG_SPARSE_IRQ */

struct irq_desc irq_desc[NR_IRQS] __cacheline_aligned_in_smp = {
	[0 ... NR_IRQS-1] = {
		.status		= IRQ_DISABLED,
		.handle_irq	= handle_bad_irq,
		.depth		= 1,
		.lock		= __RAW_SPIN_LOCK_UNLOCKED(irq_desc->lock),
	}
};

static unsigned int kstat_irqs_all[NR_IRQS][NR_CPUS];
int __init early_irq_init(void)
{
	struct irq_desc *desc;
	int count;
	int i;

	init_irq_default_affinity();

	printk(KERN_INFO "NR_IRQS:%d\n", NR_IRQS);

	desc = irq_desc;
	count = ARRAY_SIZE(irq_desc);

	for (i = 0; i < count; i++) {
		desc[i].irq_data.irq = i;
		desc[i].irq_data.chip = &no_irq_chip;
		alloc_desc_masks(&desc[i], 0, true);
		init_desc_masks(&desc[i]);
		desc[i].kstat_irqs = kstat_irqs_all[i];
	}
	return arch_early_irq_init();
}

struct irq_desc *irq_to_desc(unsigned int irq)
{
	return (irq < NR_IRQS) ? irq_desc + irq : NULL;
}

struct irq_desc *irq_to_desc_alloc_node(unsigned int irq, int node)
{
	return irq_to_desc(irq);
}
#endif /* !CONFIG_SPARSE_IRQ */

void clear_kstat_irqs(struct irq_desc *desc)
{
	memset(desc->kstat_irqs, 0, nr_cpu_ids * sizeof(*(desc->kstat_irqs)));
}

/*
 * What should we do if we get a hw irq event on an illegal vector?
 * Each architecture has to answer this themself.
 */
static void ack_bad(unsigned int irq)
{
	struct irq_desc *desc = irq_to_desc(irq);

	print_irq_desc(irq, desc);
	ack_bad_irq(irq);
}

/*
 * NOP functions
 */
static void noop(unsigned int irq)
{
}

static unsigned int noop_ret(unsigned int irq)
{
	return 0;
}

/*
 * Generic no controller implementation
 */
struct irq_chip no_irq_chip = {
	.name		= "none",
	.startup	= noop_ret,
	.shutdown	= noop,
	.enable		= noop,
	.disable	= noop,
	.ack		= ack_bad,
	.end		= noop,
};

/*
 * Generic dummy implementation which can be used for
 * real dumb interrupt sources
 */
struct irq_chip dummy_irq_chip = {
	.name		= "dummy",
	.startup	= noop_ret,
	.shutdown	= noop,
	.enable		= noop,
	.disable	= noop,
	.ack		= noop,
	.mask		= noop,
	.unmask		= noop,
	.end		= noop,
};

/*
 * Special, empty irq handler:
 */
irqreturn_t no_action(int cpl, void *dev_id)
{
	return IRQ_NONE;
}

static void warn_no_thread(unsigned int irq, struct irqaction *action)
{
	if (test_and_set_bit(IRQTF_WARNED, &action->thread_flags))
		return;

	printk(KERN_WARNING "IRQ %d device %s returned IRQ_WAKE_THREAD "
	       "but no thread function available.", irq, action->name);
}

/**
 * handle_IRQ_event - irq action chain handler
 * @irq:	the interrupt number
 * @action:	the interrupt action chain for this irq
 *
 * Handles the action chain of an irq event
 */
irqreturn_t handle_IRQ_event(unsigned int irq, struct irqaction *action)
{
	irqreturn_t ret, retval = IRQ_NONE;
	unsigned int status = 0;

	do {
		trace_irq_handler_entry(irq, action);
		ret = action->handler(irq, action->dev_id);
		trace_irq_handler_exit(irq, action, ret);

		switch (ret) {
		case IRQ_WAKE_THREAD:
			/*
			 * Set result to handled so the spurious check
			 * does not trigger.
			 */
			ret = IRQ_HANDLED;

			/*
			 * Catch drivers which return WAKE_THREAD but
			 * did not set up a thread function
			 */
			if (unlikely(!action->thread_fn)) {
				warn_no_thread(irq, action);
				break;
			}

			/*
			 * Wake up the handler thread for this
			 * action. In case the thread crashed and was
			 * killed we just pretend that we handled the
			 * interrupt. The hardirq handler above has
			 * disabled the device interrupt, so no irq
			 * storm is lurking.
			 */
			if (likely(!test_bit(IRQTF_DIED,
					     &action->thread_flags))) {
				set_bit(IRQTF_RUNTHREAD, &action->thread_flags);
				wake_up_process(action->thread);
			}

			/* Fall through to add to randomness */
		case IRQ_HANDLED:
			status |= action->flags;
			break;

		default:
			break;
		}

		retval |= ret;
		action = action->next;
	} while (action);

	if (status & IRQF_SAMPLE_RANDOM)
		add_interrupt_randomness(irq);
	local_irq_disable();

	return retval;
}

#ifndef CONFIG_GENERIC_HARDIRQS_NO__DO_IRQ

#ifdef CONFIG_ENABLE_WARN_DEPRECATED
# warning __do_IRQ is deprecated. Please convert to proper flow handlers
#endif

/**
 * __do_IRQ - original all in one highlevel IRQ handler
 * @irq:	the interrupt number
 *
 * __do_IRQ handles all normal device IRQ's (the special
 * SMP cross-CPU interrupts have their own specific
 * handlers).
 *
 * This is the original x86 implementation which is used for every
 * interrupt type.
 */
unsigned int __do_IRQ(unsigned int irq)
{
	struct irq_desc *desc = irq_to_desc(irq);
	struct irqaction *action;
	unsigned int status;

	kstat_incr_irqs_this_cpu(irq, desc);

	if (CHECK_IRQ_PER_CPU(desc->status)) {
		irqreturn_t action_ret;

		/*
		 * No locking required for CPU-local interrupts:
		 */
		if (desc->irq_data.chip->ack)
			desc->irq_data.chip->ack(irq);
		if (likely(!(desc->status & IRQ_DISABLED))) {
			action_ret = handle_IRQ_event(irq, desc->action);
			if (!noirqdebug)
				note_interrupt(irq, desc, action_ret);
		}
		desc->irq_data.chip->end(irq);
		return 1;
	}

	raw_spin_lock(&desc->lock);
	if (desc->irq_data.chip->ack)
		desc->irq_data.chip->ack(irq);
	/*
	 * REPLAY is when Linux resends an IRQ that was dropped earlier
	 * WAITING is used by probe to mark irqs that are being tested
	 */
	status = desc->status & ~(IRQ_REPLAY | IRQ_WAITING);
	status |= IRQ_PENDING; /* we _want_ to handle it */

	/*
	 * If the IRQ is disabled for whatever reason, we cannot
	 * use the action we have.
	 */
	action = NULL;
	if (likely(!(status & (IRQ_DISABLED | IRQ_INPROGRESS)))) {
		action = desc->action;
		status &= ~IRQ_PENDING; /* we commit to handling */
		status |= IRQ_INPROGRESS; /* we are handling it */
	}
	desc->status = status;

	/*
	 * If there is no IRQ handler or it was disabled, exit early.
	 * Since we set PENDING, if another processor is handling
	 * a different instance of this same irq, the other processor
	 * will take care of it.
	 */
	if (unlikely(!action))
		goto out;

	/*
	 * Edge triggered interrupts need to remember
	 * pending events.
	 * This applies to any hw interrupts that allow a second
	 * instance of the same irq to arrive while we are in do_IRQ
	 * or in the handler. But the code here only handles the _second_
	 * instance of the irq, not the third or fourth. So it is mostly
	 * useful for irq hardware that does not mask cleanly in an
	 * SMP environment.
	 */
	for (;;) {
		irqreturn_t action_ret;

		raw_spin_unlock(&desc->lock);

		action_ret = handle_IRQ_event(irq, action);
		if (!noirqdebug)
			note_interrupt(irq, desc, action_ret);

		raw_spin_lock(&desc->lock);
		if (likely(!(desc->status & IRQ_PENDING)))
			break;
		desc->status &= ~IRQ_PENDING;
	}
	desc->status &= ~IRQ_INPROGRESS;

out:
	/*
	 * The ->end() handler has to deal with interrupts which got
	 * disabled while the handler was running.
	 */
	desc->irq_data.chip->end(irq);
	raw_spin_unlock(&desc->lock);

	return 1;
}
#endif

void early_init_irq_lock_class(void)
{
	struct irq_desc *desc;
	int i;

	for_each_irq_desc(i, desc) {
		lockdep_set_class(&desc->lock, &irq_desc_lock_class);
	}
}

unsigned int kstat_irqs_cpu(unsigned int irq, int cpu)
{
	struct irq_desc *desc = irq_to_desc(irq);
	return desc ? desc->kstat_irqs[cpu] : 0;
}
EXPORT_SYMBOL(kstat_irqs_cpu);