summaryrefslogtreecommitdiff
path: root/kvm_irq_comm.c
blob: aa2ef74e6de7a9a6c981b856c17f810e1cfbc9f6 (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
/*
 * irq_comm.c: Common API for in kernel interrupt controller
 * Copyright (c) 2007, Intel Corporation.
 *
 * This program is free software; you can redistribute it and/or modify it
 * under the terms and conditions of the GNU General Public License,
 * version 2, as published by the Free Software Foundation.
 *
 * This program is distributed in the hope it will be useful, but WITHOUT
 * ANY WARRANTY; without even the implied warranty of MERCHANTABILITY or
 * FITNESS FOR A PARTICULAR PURPOSE.  See the GNU General Public License for
 * more details.
 *
 * You should have received a copy of the GNU General Public License along with
 * this program; if not, write to the Free Software Foundation, Inc., 59 Temple
 * Place - Suite 330, Boston, MA 02111-1307 USA.
 * Authors:
 *   Yaozu (Eddie) Dong <Eddie.dong@intel.com>
 *
 */

#include <sys/sysmacros.h>

/*
 * XXX Need proper header files!
 */
#include "bitops.h"
#include "msr.h"
#include "irqflags.h"
#include "kvm_msidef.h"
#include "kvm_host.h"
#include "kvm_x86host.h"
#include "kvm_iodev.h"
#include "kvm.h"
#include "apicdef.h"
#include "kvm_lapic.h"
#include "kvm_ioapic.h"
#include "kvm_irq.h"

extern long find_first_zero_bit(const unsigned long *, unsigned long);
extern int kvm_pic_set_irq(void *, int, int);
extern int irqchip_in_kernel(struct kvm *kvm);

static int
kvm_irq_line_state(unsigned long *irq_state, int irq_source_id, int level)
{
	/* Logical OR for level trig interrupt */
	if (level) {
		set_bit(irq_source_id, irq_state);
	} else {
		clear_bit(irq_source_id, irq_state);
	}

	return (!!(*irq_state));
}

static int
kvm_set_pic_irq(struct kvm_kernel_irq_routing_entry *e,
    struct kvm *kvm, int irq_source_id, int level)
{
#ifdef CONFIG_X86
	struct kvm_pic *pic = pic_irqchip(kvm);
	level = kvm_irq_line_state(&pic->irq_states[e->irqchip.pin],
	    irq_source_id, level);
	return (kvm_pic_set_irq(pic, e->irqchip.pin, level));
#else
	return (-1);
#endif
}

static int
kvm_set_ioapic_irq(struct kvm_kernel_irq_routing_entry *e,
    struct kvm *kvm, int irq_source_id, int level)
{
	struct kvm_ioapic *ioapic = kvm->arch.vioapic;
	level = kvm_irq_line_state(&ioapic->irq_states[e->irqchip.pin],
	    irq_source_id, level);

	return (kvm_ioapic_set_irq(ioapic, e->irqchip.pin, level));
}

static int
kvm_is_dm_lowest_prio(struct kvm_lapic_irq *irq)
{
#ifdef CONFIG_IA64
	return (irq->delivery_mode ==
		(IOSAPIC_LOWEST_PRIORITY << IOSAPIC_DELIVERY_SHIFT));
#else
	return (irq->delivery_mode == APIC_DM_LOWEST);
#endif
}

int
kvm_irq_delivery_to_apic(struct kvm *kvm, struct kvm_lapic *src,
    struct kvm_lapic_irq *irq)
{
	int i, r = -1;
	struct kvm_vcpu *vcpu, *lowest = NULL;

	if (irq->dest_mode == 0 && irq->dest_id == 0xff &&
	    kvm_is_dm_lowest_prio(irq))
		cmn_err(CE_NOTE, "kvm: apic: phys broadcast and lowest prio\n");

	kvm_for_each_vcpu(i, vcpu, kvm) {
		if (!kvm_apic_present(vcpu))
			continue;

		if (!kvm_apic_match_dest(vcpu, src, irq->shorthand,
		    irq->dest_id, irq->dest_mode))
			continue;

		if (!kvm_is_dm_lowest_prio(irq)) {
			if (r < 0)
				r = 0;
			r += kvm_apic_set_irq(vcpu, irq);
		} else {
			if (!lowest)
				lowest = vcpu;
			else if (kvm_apic_compare_prio(vcpu, lowest) < 0)
				lowest = vcpu;
		}
	}
	if (lowest)
		r = kvm_apic_set_irq(lowest, irq);

	return (r);
}

static int
kvm_set_msi(struct kvm_kernel_irq_routing_entry *e, struct kvm *kvm,
    int irq_source_id, int level)
{
	struct kvm_lapic_irq irq;

	if (!level)
		return (-1);

	KVM_TRACE2(msi__set__irq, uintptr_t, e->msi.address_lo,
	    uintptr_t, e->msi.data);

	irq.dest_id = (e->msi.address_lo & MSI_ADDR_DEST_ID_MASK) >>
	    MSI_ADDR_DEST_ID_SHIFT;
	irq.vector = (e->msi.data & MSI_DATA_VECTOR_MASK) >>
	    MSI_DATA_VECTOR_SHIFT;
	irq.dest_mode = (1 << MSI_ADDR_DEST_MODE_SHIFT) & e->msi.address_lo;
	irq.trig_mode = (1 << MSI_DATA_TRIGGER_SHIFT) & e->msi.data;
	irq.delivery_mode = e->msi.data & 0x700;
	irq.level = 1;
	irq.shorthand = 0;

	/* TODO Deal with RH bit of MSI message address */
	return (kvm_irq_delivery_to_apic(kvm, NULL, &irq));
}

/*
 * Return value:
 *  < 0   Interrupt was ignored (masked or not delivered for other reasons)
 *  = 0   Interrupt was coalesced (previous irq is still pending)
 *  > 0   Number of CPUs interrupt was delivered to
 */
int
kvm_set_irq(struct kvm *kvm, int irq_source_id, uint32_t irq, int level)
{
	struct kvm_kernel_irq_routing_entry *e, irq_set[KVM_NR_IRQCHIPS];
	int ret = -1, i = 0;
	struct kvm_irq_routing_table *irq_rt;

	/*
	 * Not possible to detect if the guest uses the PIC or the
	 * IOAPIC.  So set the bit in both. The guest will ignore
	 * writes to the unused one.
	 */
#ifdef XXX
	rcu_read_lock();
	irq_rt = rcu_dereference(kvm->irq_routing);
#else
	XXX_KVM_SYNC_PROBE;
	irq_rt = kvm->irq_routing;
#endif
	if (irq < irq_rt->nr_rt_entries) {
		for (e = list_head(&irq_rt->map[irq]); e != NULL;
		    e = list_next(&irq_rt->map[irq], e)) {
			irq_set[i++] = *e;
		}
	}
#ifdef XXX
	rcu_read_unlock();
#else
	XXX_KVM_SYNC_PROBE;
#endif

	while (i--) {
		int r;
		r = irq_set[i].set(&irq_set[i], kvm, irq_source_id, level);
		if (r < 0)
			continue;

		ret = r + ((ret < 0) ? 0 : ret);
	}

	return (ret);
}

void
kvm_notify_acked_irq(struct kvm *kvm, unsigned irqchip, unsigned pin)
{
	struct kvm_irq_ack_notifier *kian;
	struct hlist_node *n;
	int gsi;

	KVM_TRACE2(ack__irq, unsigned int, irqchip, unsigned int, pin);

#ifdef XXX
	rcu_read_lock();

	gsi = rcu_dereference(kvm->irq_routing)->chip[irqchip][pin];
#else
	XXX_KVM_SYNC_PROBE;
#endif
	gsi = (kvm->irq_routing)->chip[irqchip][pin];

	if (gsi != -1) {
		for (kian = list_head(&kvm->irq_ack_notifier_list);
		    kian != NULL;
		    kian = list_next(&kvm->irq_ack_notifier_list, kian)) {
			if (kian->gsi == gsi)
				kian->irq_acked(kian);
		}
	}
#ifdef XXX
	rcu_read_unlock();
#else
	XXX_KVM_SYNC_PROBE;
#endif
}

void
kvm_register_irq_ack_notifier(struct kvm *kvm,
    struct kvm_irq_ack_notifier *kian)
{
	mutex_enter(&kvm->irq_lock);
	list_insert_head(&kvm->irq_ack_notifier_list, kian);
	mutex_exit(&kvm->irq_lock);
}

void
kvm_unregister_irq_ack_notifier(struct kvm *kvm,
    struct kvm_irq_ack_notifier *kian)
{
	mutex_enter(&kvm->irq_lock);
	list_remove(&kvm->irq_ack_notifier_list, kian);
	mutex_exit(&kvm->irq_lock);
}

int
kvm_request_irq_source_id(struct kvm *kvm)
{
	unsigned long *bitmap = &kvm->arch.irq_sources_bitmap;
	int irq_source_id;

	mutex_enter(&kvm->irq_lock);
	irq_source_id = find_first_zero_bit(bitmap, 64);

	if (irq_source_id >= 64) {
		irq_source_id = -EFAULT;
		goto unlock;
	}

	ASSERT(irq_source_id != KVM_USERSPACE_IRQ_SOURCE_ID);
	set_bit(irq_source_id, bitmap);
unlock:
	mutex_exit(&kvm->irq_lock);

	return (irq_source_id);
}

void
kvm_free_irq_source_id(struct kvm *kvm, int irq_source_id)
{
	int i;

	ASSERT(irq_source_id != KVM_USERSPACE_IRQ_SOURCE_ID);

	mutex_enter(&kvm->irq_lock);
	if (irq_source_id < 0 ||
	    irq_source_id >= BITS_PER_LONG) {
#ifdef XXX
		printk(KERN_ERR "kvm: IRQ source ID out of range!\n");
#else
		XXX_KVM_PROBE;
#endif
		goto unlock;
	}
	clear_bit(irq_source_id, &kvm->arch.irq_sources_bitmap);
	if (!irqchip_in_kernel(kvm))
		goto unlock;

	for (i = 0; i < KVM_IOAPIC_NUM_PINS; i++) {
		clear_bit(irq_source_id, &kvm->arch.vioapic->irq_states[i]);
		if (i >= 16)
			continue;
#ifdef CONFIG_X86
		clear_bit(irq_source_id, &pic_irqchip(kvm)->irq_states[i]);
#endif
	}
unlock:
	mutex_exit(&kvm->irq_lock);
}

void
kvm_register_irq_mask_notifier(struct kvm *kvm, int irq,
    struct kvm_irq_mask_notifier *kimn)
{
	mutex_enter(&kvm->irq_lock);
	kimn->irq = irq;
	list_insert_head(&kvm->mask_notifier_list, kimn);
	mutex_exit(&kvm->irq_lock);
}

void
kvm_unregister_irq_mask_notifier(struct kvm *kvm, int irq,
    struct kvm_irq_mask_notifier *kimn)
{
	mutex_enter(&kvm->irq_lock);
	list_remove(&kvm->mask_notifier_list, kimn);
	mutex_exit(&kvm->irq_lock);
}

void
kvm_fire_mask_notifiers(struct kvm *kvm, int irq, int mask)
{
	struct kvm_irq_mask_notifier *kimn;

#ifdef XXX
	rcu_read_lock();
#else
	XXX_KVM_SYNC_PROBE;
#endif

	for (kimn = list_head(&kvm->mask_notifier_list); kimn != NULL;
	    kimn = list_next(&kvm->mask_notifier_list, kimn)) {
		if (kimn->irq == irq)
			kimn->func(kimn, mask);
	}

#ifdef XXX
	rcu_read_unlock();
#else
	XXX_KVM_SYNC_PROBE;
#endif
}

static int
setup_routing_entry(struct kvm_irq_routing_table *rt,
    struct kvm_kernel_irq_routing_entry *e,
    const struct kvm_irq_routing_entry *ue)
{
	int r = -EINVAL;
	int delta;
	unsigned max_pin;
	struct kvm_kernel_irq_routing_entry *ei;

	/*
	 * Do not allow GSI to be mapped to the same irqchip more than once.
	 * Allow only one to one mapping between GSI and MSI.
	 */
	for (ei = list_head(&rt->map[ue->gsi]); ei != NULL;
	    ei = list_next(&rt->map[ue->gsi], ei)) {
		if (ei->type == KVM_IRQ_ROUTING_MSI ||
		    ue->u.irqchip.irqchip == ei->irqchip.irqchip)
			return (r);
	}

	e->gsi = ue->gsi;
	e->type = ue->type;
	switch (ue->type) {
	case KVM_IRQ_ROUTING_IRQCHIP:
		delta = 0;
		switch (ue->u.irqchip.irqchip) {
		case KVM_IRQCHIP_PIC_MASTER:
			e->set = kvm_set_pic_irq;
			max_pin = 16;
			break;
		case KVM_IRQCHIP_PIC_SLAVE:
			e->set = kvm_set_pic_irq;
			max_pin = 16;
			delta = 8;
			break;
		case KVM_IRQCHIP_IOAPIC:
			max_pin = KVM_IOAPIC_NUM_PINS;
			e->set = kvm_set_ioapic_irq;
			break;
		default:
			goto out;
		}
		e->irqchip.irqchip = ue->u.irqchip.irqchip;
		e->irqchip.pin = ue->u.irqchip.pin + delta;
		if (e->irqchip.pin >= max_pin)
			goto out;
		rt->chip[ue->u.irqchip.irqchip][e->irqchip.pin] = ue->gsi;
		break;
	case KVM_IRQ_ROUTING_MSI:
		e->set = kvm_set_msi;
		e->msi.address_lo = ue->u.msi.address_lo;
		e->msi.address_hi = ue->u.msi.address_hi;
		e->msi.data = ue->u.msi.data;
		break;
	default:
		goto out;
	}

	list_insert_head(&rt->map[e->gsi], e);
	r = 0;
out:
	return (r);
}

int
kvm_set_irq_routing(struct kvm *kvm, const struct kvm_irq_routing_entry *ue,
    unsigned nr, unsigned flags)
{
	struct kvm_irq_routing_table *new, *old;
	uint32_t i, j, nr_rt_entries = 0;
	size_t sz = sizeof (struct kvm_kernel_irq_routing_entry);
	int r;

	for (i = 0; i < nr; ++i) {
		if (ue[i].gsi >= KVM_MAX_IRQ_ROUTES)
			return (-EINVAL);
		nr_rt_entries = MAX(nr_rt_entries, ue[i].gsi);
	}

	nr_rt_entries += 1;

#ifdef XXX
	new = kmem_zalloc(sizeof (*new) + (nr_rt_entries * sizeof (list_t)) +
	    (nr * sz), KM_SLEEP);

	new->rt_entries = (void *)&new->map[nr_rt_entries];
#else
	XXX_KVM_PROBE;
	new = kmem_zalloc(sizeof (*new), KM_SLEEP);

	for (i = 0; i < KVM_MAX_IRQ_ROUTES; i++) {
		list_create(&new->map[i], sz,
		    offsetof(struct kvm_kernel_irq_routing_entry, link));
	}

	new->rt_entries = kmem_zalloc(sz * nr, KM_SLEEP);

#endif

	new->nr_rt_entries = nr_rt_entries;
	for (i = 0; i < 3; i++)
		for (j = 0; j < KVM_IOAPIC_NUM_PINS; j++)
			new->chip[i][j] = -1;

	for (i = 0; i < nr; ++i) {
		r = -EINVAL;
		if (ue->flags)
			goto out;
		r = setup_routing_entry(new,
		    (struct kvm_kernel_irq_routing_entry *)
		    ((caddr_t)new->rt_entries + (i * sz)), ue);

		if (r)
			goto out;
		++ue;
	}

	mutex_enter(&kvm->irq_lock);
	old = kvm->irq_routing;
#ifdef XXX
	rcu_assign_pointer(kvm->irq_routing, new);
#else
	XXX_KVM_SYNC_PROBE;
	kvm->irq_routing = new;
#endif
	mutex_exit(&kvm->irq_lock);
#ifdef XXX
	synchronize_rcu();
#else
	XXX_KVM_SYNC_PROBE;
#endif

	new = old;
	r = 0;

out:
	if (new) {
		if (new->rt_entries != NULL)
			kmem_free(new->rt_entries, sz * nr);

		kmem_free(new, sizeof (*new));
	}
	return (r);
}

#define	IOAPIC_ROUTING_ENTRY(irq)				\
	{							\
		.gsi = irq,					\
		.type = KVM_IRQ_ROUTING_IRQCHIP,		\
		.u.irqchip.irqchip = KVM_IRQCHIP_IOAPIC,	\
		.u.irqchip.pin = (irq)				\
	}

#define	ROUTING_ENTRY1(irq) IOAPIC_ROUTING_ENTRY(irq)

#ifdef CONFIG_X86
#define	PIC_ROUTING_ENTRY(irq)					\
	{							\
		.gsi = irq,					\
		.type = KVM_IRQ_ROUTING_IRQCHIP,		\
		.u.irqchip.irqchip = SELECT_PIC(irq),		\
		.u.irqchip.pin = (irq) % 8			\
	}

#define	ROUTING_ENTRY2(irq) \
	IOAPIC_ROUTING_ENTRY(irq), PIC_ROUTING_ENTRY(irq)
#else
#define	ROUTING_ENTRY2(irq) \
	IOAPIC_ROUTING_ENTRY(irq)
#endif

static const struct kvm_irq_routing_entry default_routing[] = {
	ROUTING_ENTRY2(0), ROUTING_ENTRY2(1),
	ROUTING_ENTRY2(2), ROUTING_ENTRY2(3),
	ROUTING_ENTRY2(4), ROUTING_ENTRY2(5),
	ROUTING_ENTRY2(6), ROUTING_ENTRY2(7),
	ROUTING_ENTRY2(8), ROUTING_ENTRY2(9),
	ROUTING_ENTRY2(10), ROUTING_ENTRY2(11),
	ROUTING_ENTRY2(12), ROUTING_ENTRY2(13),
	ROUTING_ENTRY2(14), ROUTING_ENTRY2(15),
	ROUTING_ENTRY1(16), ROUTING_ENTRY1(17),
	ROUTING_ENTRY1(18), ROUTING_ENTRY1(19),
	ROUTING_ENTRY1(20), ROUTING_ENTRY1(21),
	ROUTING_ENTRY1(22), ROUTING_ENTRY1(23),
#ifdef CONFIG_IA64
	ROUTING_ENTRY1(24), ROUTING_ENTRY1(25),
	ROUTING_ENTRY1(26), ROUTING_ENTRY1(27),
	ROUTING_ENTRY1(28), ROUTING_ENTRY1(29),
	ROUTING_ENTRY1(30), ROUTING_ENTRY1(31),
	ROUTING_ENTRY1(32), ROUTING_ENTRY1(33),
	ROUTING_ENTRY1(34), ROUTING_ENTRY1(35),
	ROUTING_ENTRY1(36), ROUTING_ENTRY1(37),
	ROUTING_ENTRY1(38), ROUTING_ENTRY1(39),
	ROUTING_ENTRY1(40), ROUTING_ENTRY1(41),
	ROUTING_ENTRY1(42), ROUTING_ENTRY1(43),
	ROUTING_ENTRY1(44), ROUTING_ENTRY1(45),
	ROUTING_ENTRY1(46), ROUTING_ENTRY1(47),
#endif
};

int
kvm_setup_default_irq_routing(struct kvm *kvm)
{
	return (kvm_set_irq_routing(kvm, default_routing,
	    ARRAY_SIZE(default_routing), 0));
}