summaryrefslogtreecommitdiff
path: root/arch/um/kernel/irq.c
blob: 6b7f3827d6e4add1993315c220bf96217bfb8986 (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
/*
 * Copyright (C) 2017 - Cambridge Greys Ltd
 * Copyright (C) 2011 - 2014 Cisco Systems Inc
 * Copyright (C) 2000 - 2007 Jeff Dike (jdike@{addtoit,linux.intel}.com)
 * Licensed under the GPL
 * Derived (i.e. mostly copied) from arch/i386/kernel/irq.c:
 *	Copyright (C) 1992, 1998 Linus Torvalds, Ingo Molnar
 */

#include <linux/cpumask.h>
#include <linux/hardirq.h>
#include <linux/interrupt.h>
#include <linux/kernel_stat.h>
#include <linux/module.h>
#include <linux/sched.h>
#include <linux/seq_file.h>
#include <linux/slab.h>
#include <as-layout.h>
#include <kern_util.h>
#include <os.h>
#include <irq_user.h>


/* When epoll triggers we do not know why it did so
 * we can also have different IRQs for read and write.
 * This is why we keep a small irq_fd array for each fd -
 * one entry per IRQ type
 */

struct irq_entry {
	struct irq_entry *next;
	int fd;
	struct irq_fd *irq_array[MAX_IRQ_TYPE + 1];
};

static struct irq_entry *active_fds;

static DEFINE_SPINLOCK(irq_lock);

static void irq_io_loop(struct irq_fd *irq, struct uml_pt_regs *regs)
{
/*
 * irq->active guards against reentry
 * irq->pending accumulates pending requests
 * if pending is raised the irq_handler is re-run
 * until pending is cleared
 */
	if (irq->active) {
		irq->active = false;
		do {
			irq->pending = false;
			do_IRQ(irq->irq, regs);
		} while (irq->pending && (!irq->purge));
		if (!irq->purge)
			irq->active = true;
	} else {
		irq->pending = true;
	}
}

void sigio_handler(int sig, struct siginfo *unused_si, struct uml_pt_regs *regs)
{
	struct irq_entry *irq_entry;
	struct irq_fd *irq;

	int n, i, j;

	while (1) {
		/* This is now lockless - epoll keeps back-referencesto the irqs
		 * which have trigger it so there is no need to walk the irq
		 * list and lock it every time. We avoid locking by turning off
		 * IO for a specific fd by executing os_del_epoll_fd(fd) before
		 * we do any changes to the actual data structures
		 */
		n = os_waiting_for_events_epoll();

		if (n <= 0) {
			if (n == -EINTR)
				continue;
			else
				break;
		}

		for (i = 0; i < n ; i++) {
			/* Epoll back reference is the entry with 3 irq_fd
			 * leaves - one for each irq type.
			 */
			irq_entry = (struct irq_entry *)
				os_epoll_get_data_pointer(i);
			for (j = 0; j < MAX_IRQ_TYPE ; j++) {
				irq = irq_entry->irq_array[j];
				if (irq == NULL)
					continue;
				if (os_epoll_triggered(i, irq->events) > 0)
					irq_io_loop(irq, regs);
				if (irq->purge) {
					irq_entry->irq_array[j] = NULL;
					kfree(irq);
				}
			}
		}
	}
}

static int assign_epoll_events_to_irq(struct irq_entry *irq_entry)
{
	int i;
	int events = 0;
	struct irq_fd *irq;

	for (i = 0; i < MAX_IRQ_TYPE ; i++) {
		irq = irq_entry->irq_array[i];
		if (irq != NULL)
			events = irq->events | events;
	}
	if (events > 0) {
	/* os_add_epoll will call os_mod_epoll if this already exists */
		return os_add_epoll_fd(events, irq_entry->fd, irq_entry);
	}
	/* No events - delete */
	return os_del_epoll_fd(irq_entry->fd);
}



static int activate_fd(int irq, int fd, int type, void *dev_id)
{
	struct irq_fd *new_fd;
	struct irq_entry *irq_entry;
	int i, err, events;
	unsigned long flags;

	err = os_set_fd_async(fd);
	if (err < 0)
		goto out;

	spin_lock_irqsave(&irq_lock, flags);

	/* Check if we have an entry for this fd */

	err = -EBUSY;
	for (irq_entry = active_fds;
		irq_entry != NULL; irq_entry = irq_entry->next) {
		if (irq_entry->fd == fd)
			break;
	}

	if (irq_entry == NULL) {
		/* This needs to be atomic as it may be called from an
		 * IRQ context.
		 */
		irq_entry = kmalloc(sizeof(struct irq_entry), GFP_ATOMIC);
		if (irq_entry == NULL) {
			printk(KERN_ERR
				"Failed to allocate new IRQ entry\n");
			goto out_unlock;
		}
		irq_entry->fd = fd;
		for (i = 0; i < MAX_IRQ_TYPE; i++)
			irq_entry->irq_array[i] = NULL;
		irq_entry->next = active_fds;
		active_fds = irq_entry;
	}

	/* Check if we are trying to re-register an interrupt for a
	 * particular fd
	 */

	if (irq_entry->irq_array[type] != NULL) {
		printk(KERN_ERR
			"Trying to reregister IRQ %d FD %d TYPE %d ID %p\n",
			irq, fd, type, dev_id
		);
		goto out_unlock;
	} else {
		/* New entry for this fd */

		err = -ENOMEM;
		new_fd = kmalloc(sizeof(struct irq_fd), GFP_ATOMIC);
		if (new_fd == NULL)
			goto out_unlock;

		events = os_event_mask(type);

		*new_fd = ((struct irq_fd) {
			.id		= dev_id,
			.irq		= irq,
			.type		= type,
			.events		= events,
			.active		= true,
			.pending	= false,
			.purge		= false
		});
		/* Turn off any IO on this fd - allows us to
		 * avoid locking the IRQ loop
		 */
		os_del_epoll_fd(irq_entry->fd);
		irq_entry->irq_array[type] = new_fd;
	}

	/* Turn back IO on with the correct (new) IO event mask */
	assign_epoll_events_to_irq(irq_entry);
	spin_unlock_irqrestore(&irq_lock, flags);
	maybe_sigio_broken(fd, (type != IRQ_NONE));

	return 0;
out_unlock:
	spin_unlock_irqrestore(&irq_lock, flags);
out:
	return err;
}

/*
 * Walk the IRQ list and dispose of any unused entries.
 * Should be done under irq_lock.
 */

static void garbage_collect_irq_entries(void)
{
	int i;
	bool reap;
	struct irq_entry *walk;
	struct irq_entry *previous = NULL;
	struct irq_entry *to_free;

	if (active_fds == NULL)
		return;
	walk = active_fds;
	while (walk != NULL) {
		reap = true;
		for (i = 0; i < MAX_IRQ_TYPE ; i++) {
			if (walk->irq_array[i] != NULL) {
				reap = false;
				break;
			}
		}
		if (reap) {
			if (previous == NULL)
				active_fds = walk->next;
			else
				previous->next = walk->next;
			to_free = walk;
		} else {
			to_free = NULL;
		}
		walk = walk->next;
		if (to_free != NULL)
			kfree(to_free);
	}
}

/*
 * Walk the IRQ list and get the descriptor for our FD
 */

static struct irq_entry *get_irq_entry_by_fd(int fd)
{
	struct irq_entry *walk = active_fds;

	while (walk != NULL) {
		if (walk->fd == fd)
			return walk;
		walk = walk->next;
	}
	return NULL;
}


/*
 * Walk the IRQ list and dispose of an entry for a specific
 * device, fd and number. Note - if sharing an IRQ for read
 * and writefor the same FD it will be disposed in either case.
 * If this behaviour is undesirable use different IRQ ids.
 */

#define IGNORE_IRQ 1
#define IGNORE_DEV (1<<1)

static void do_free_by_irq_and_dev(
	struct irq_entry *irq_entry,
	unsigned int irq,
	void *dev,
	int flags
)
{
	int i;
	struct irq_fd *to_free;

	for (i = 0; i < MAX_IRQ_TYPE ; i++) {
		if (irq_entry->irq_array[i] != NULL) {
			if (
			((flags & IGNORE_IRQ) ||
				(irq_entry->irq_array[i]->irq == irq)) &&
			((flags & IGNORE_DEV) ||
				(irq_entry->irq_array[i]->id == dev))
			) {
				/* Turn off any IO on this fd - allows us to
				 * avoid locking the IRQ loop
				 */
				os_del_epoll_fd(irq_entry->fd);
				to_free = irq_entry->irq_array[i];
				irq_entry->irq_array[i] = NULL;
				assign_epoll_events_to_irq(irq_entry);
				if (to_free->active)
					to_free->purge = true;
				else
					kfree(to_free);
			}
		}
	}
}

void free_irq_by_fd(int fd)
{
	struct irq_entry *to_free;
	unsigned long flags;

	spin_lock_irqsave(&irq_lock, flags);
	to_free = get_irq_entry_by_fd(fd);
	if (to_free != NULL) {
		do_free_by_irq_and_dev(
			to_free,
			-1,
			NULL,
			IGNORE_IRQ | IGNORE_DEV
		);
	}
	garbage_collect_irq_entries();
	spin_unlock_irqrestore(&irq_lock, flags);
}
EXPORT_SYMBOL(free_irq_by_fd);

static void free_irq_by_irq_and_dev(unsigned int irq, void *dev)
{
	struct irq_entry *to_free;
	unsigned long flags;

	spin_lock_irqsave(&irq_lock, flags);
	to_free = active_fds;
	while (to_free != NULL) {
		do_free_by_irq_and_dev(
			to_free,
			irq,
			dev,
			0
		);
		to_free = to_free->next;
	}
	garbage_collect_irq_entries();
	spin_unlock_irqrestore(&irq_lock, flags);
}


void reactivate_fd(int fd, int irqnum)
{
	/** NOP - we do auto-EOI now **/
}

void deactivate_fd(int fd, int irqnum)
{
	struct irq_entry *to_free;
	unsigned long flags;

	os_del_epoll_fd(fd);
	spin_lock_irqsave(&irq_lock, flags);
	to_free = get_irq_entry_by_fd(fd);
	if (to_free != NULL) {
		do_free_by_irq_and_dev(
			to_free,
			irqnum,
			NULL,
			IGNORE_DEV
		);
	}
	garbage_collect_irq_entries();
	spin_unlock_irqrestore(&irq_lock, flags);
	ignore_sigio_fd(fd);
}
EXPORT_SYMBOL(deactivate_fd);

/*
 * Called just before shutdown in order to provide a clean exec
 * environment in case the system is rebooting.  No locking because
 * that would cause a pointless shutdown hang if something hadn't
 * released the lock.
 */
int deactivate_all_fds(void)
{
	unsigned long flags;
	struct irq_entry *to_free;

	spin_lock_irqsave(&irq_lock, flags);
	/* Stop IO. The IRQ loop has no lock so this is our
	 * only way of making sure we are safe to dispose
	 * of all IRQ handlers
	 */
	os_set_ioignore();
	to_free = active_fds;
	while (to_free != NULL) {
		do_free_by_irq_and_dev(
			to_free,
			-1,
			NULL,
			IGNORE_IRQ | IGNORE_DEV
		);
		to_free = to_free->next;
	}
	garbage_collect_irq_entries();
	spin_unlock_irqrestore(&irq_lock, flags);
	os_close_epoll_fd();
	return 0;
}

/*
 * do_IRQ handles all normal device IRQs (the special
 * SMP cross-CPU interrupts have their own specific
 * handlers).
 */
unsigned int do_IRQ(int irq, struct uml_pt_regs *regs)
{
	struct pt_regs *old_regs = set_irq_regs((struct pt_regs *)regs);
	irq_enter();
	generic_handle_irq(irq);
	irq_exit();
	set_irq_regs(old_regs);
	return 1;
}

void um_free_irq(unsigned int irq, void *dev)
{
	free_irq_by_irq_and_dev(irq, dev);
	free_irq(irq, dev);
}
EXPORT_SYMBOL(um_free_irq);

int um_request_irq(unsigned int irq, int fd, int type,
		   irq_handler_t handler,
		   unsigned long irqflags, const char * devname,
		   void *dev_id)
{
	int err;

	if (fd != -1) {
		err = activate_fd(irq, fd, type, dev_id);
		if (err)
			return err;
	}

	return request_irq(irq, handler, irqflags, devname, dev_id);
}

EXPORT_SYMBOL(um_request_irq);
EXPORT_SYMBOL(reactivate_fd);

/*
 * irq_chip must define at least enable/disable and ack when
 * the edge handler is used.
 */
static void dummy(struct irq_data *d)
{
}

/* This is used for everything else than the timer. */
static struct irq_chip normal_irq_type = {
	.name = "SIGIO",
	.irq_disable = dummy,
	.irq_enable = dummy,
	.irq_ack = dummy,
	.irq_mask = dummy,
	.irq_unmask = dummy,
};

static struct irq_chip SIGVTALRM_irq_type = {
	.name = "SIGVTALRM",
	.irq_disable = dummy,
	.irq_enable = dummy,
	.irq_ack = dummy,
	.irq_mask = dummy,
	.irq_unmask = dummy,
};

void __init init_IRQ(void)
{
	int i;

	irq_set_chip_and_handler(TIMER_IRQ, &SIGVTALRM_irq_type, handle_edge_irq);


	for (i = 1; i < NR_IRQS; i++)
		irq_set_chip_and_handler(i, &normal_irq_type, handle_edge_irq);
	/* Initialize EPOLL Loop */
	os_setup_epoll();
}

/*
 * IRQ stack entry and exit:
 *
 * Unlike i386, UML doesn't receive IRQs on the normal kernel stack
 * and switch over to the IRQ stack after some preparation.  We use
 * sigaltstack to receive signals on a separate stack from the start.
 * These two functions make sure the rest of the kernel won't be too
 * upset by being on a different stack.  The IRQ stack has a
 * thread_info structure at the bottom so that current et al continue
 * to work.
 *
 * to_irq_stack copies the current task's thread_info to the IRQ stack
 * thread_info and sets the tasks's stack to point to the IRQ stack.
 *
 * from_irq_stack copies the thread_info struct back (flags may have
 * been modified) and resets the task's stack pointer.
 *
 * Tricky bits -
 *
 * What happens when two signals race each other?  UML doesn't block
 * signals with sigprocmask, SA_DEFER, or sa_mask, so a second signal
 * could arrive while a previous one is still setting up the
 * thread_info.
 *
 * There are three cases -
 *     The first interrupt on the stack - sets up the thread_info and
 * handles the interrupt
 *     A nested interrupt interrupting the copying of the thread_info -
 * can't handle the interrupt, as the stack is in an unknown state
 *     A nested interrupt not interrupting the copying of the
 * thread_info - doesn't do any setup, just handles the interrupt
 *
 * The first job is to figure out whether we interrupted stack setup.
 * This is done by xchging the signal mask with thread_info->pending.
 * If the value that comes back is zero, then there is no setup in
 * progress, and the interrupt can be handled.  If the value is
 * non-zero, then there is stack setup in progress.  In order to have
 * the interrupt handled, we leave our signal in the mask, and it will
 * be handled by the upper handler after it has set up the stack.
 *
 * Next is to figure out whether we are the outer handler or a nested
 * one.  As part of setting up the stack, thread_info->real_thread is
 * set to non-NULL (and is reset to NULL on exit).  This is the
 * nesting indicator.  If it is non-NULL, then the stack is already
 * set up and the handler can run.
 */

static unsigned long pending_mask;

unsigned long to_irq_stack(unsigned long *mask_out)
{
	struct thread_info *ti;
	unsigned long mask, old;
	int nested;

	mask = xchg(&pending_mask, *mask_out);
	if (mask != 0) {
		/*
		 * If any interrupts come in at this point, we want to
		 * make sure that their bits aren't lost by our
		 * putting our bit in.  So, this loop accumulates bits
		 * until xchg returns the same value that we put in.
		 * When that happens, there were no new interrupts,
		 * and pending_mask contains a bit for each interrupt
		 * that came in.
		 */
		old = *mask_out;
		do {
			old |= mask;
			mask = xchg(&pending_mask, old);
		} while (mask != old);
		return 1;
	}

	ti = current_thread_info();
	nested = (ti->real_thread != NULL);
	if (!nested) {
		struct task_struct *task;
		struct thread_info *tti;

		task = cpu_tasks[ti->cpu].task;
		tti = task_thread_info(task);

		*ti = *tti;
		ti->real_thread = tti;
		task->stack = ti;
	}

	mask = xchg(&pending_mask, 0);
	*mask_out |= mask | nested;
	return 0;
}

unsigned long from_irq_stack(int nested)
{
	struct thread_info *ti, *to;
	unsigned long mask;

	ti = current_thread_info();

	pending_mask = 1;

	to = ti->real_thread;
	current->stack = to;
	ti->real_thread = NULL;
	*to = *ti;

	mask = xchg(&pending_mask, 0);
	return mask & ~1;
}