summaryrefslogtreecommitdiff
path: root/arch/x86/kvm/irq_comm.c
blob: 6825cd36d13b7c2af164ca9c09e51cbf58109040 (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
/*
 * 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>
 *
 * Copyright 2010 Red Hat, Inc. and/or its affiliates.
 */

#include <linux/kvm_host.h>
#include <linux/slab.h>
#include <linux/export.h>
#include <linux/rculist.h>

#include <trace/events/kvm.h>

#include <asm/msidef.h>

#include "irq.h"

#include "ioapic.h"

#include "lapic.h"

#include "hyperv.h"
#include "x86.h"

static int kvm_set_pic_irq(struct kvm_kernel_irq_routing_entry *e,
			   struct kvm *kvm, int irq_source_id, int level,
			   bool line_status)
{
	struct kvm_pic *pic = pic_irqchip(kvm);
	return kvm_pic_set_irq(pic, e->irqchip.pin, irq_source_id, level);
}

static int kvm_set_ioapic_irq(struct kvm_kernel_irq_routing_entry *e,
			      struct kvm *kvm, int irq_source_id, int level,
			      bool line_status)
{
	struct kvm_ioapic *ioapic = kvm->arch.vioapic;
	return kvm_ioapic_set_irq(ioapic, e->irqchip.pin, irq_source_id, level,
				line_status);
}

int kvm_irq_delivery_to_apic(struct kvm *kvm, struct kvm_lapic *src,
		struct kvm_lapic_irq *irq, struct dest_map *dest_map)
{
	int i, r = -1;
	struct kvm_vcpu *vcpu, *lowest = NULL;
	unsigned long dest_vcpu_bitmap[BITS_TO_LONGS(KVM_MAX_VCPUS)];
	unsigned int dest_vcpus = 0;

	if (irq->dest_mode == 0 && irq->dest_id == 0xff &&
			kvm_lowest_prio_delivery(irq)) {
		printk(KERN_INFO "kvm: apic: phys broadcast and lowest prio\n");
		irq->delivery_mode = APIC_DM_FIXED;
	}

	if (kvm_irq_delivery_to_apic_fast(kvm, src, irq, &r, dest_map))
		return r;

	memset(dest_vcpu_bitmap, 0, sizeof(dest_vcpu_bitmap));

	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_lowest_prio_delivery(irq)) {
			if (r < 0)
				r = 0;
			r += kvm_apic_set_irq(vcpu, irq, dest_map);
		} else if (kvm_lapic_enabled(vcpu)) {
			if (!kvm_vector_hashing_enabled()) {
				if (!lowest)
					lowest = vcpu;
				else if (kvm_apic_compare_prio(vcpu, lowest) < 0)
					lowest = vcpu;
			} else {
				__set_bit(i, dest_vcpu_bitmap);
				dest_vcpus++;
			}
		}
	}

	if (dest_vcpus != 0) {
		int idx = kvm_vector_to_index(irq->vector, dest_vcpus,
					dest_vcpu_bitmap, KVM_MAX_VCPUS);

		lowest = kvm_get_vcpu(kvm, idx);
	}

	if (lowest)
		r = kvm_apic_set_irq(lowest, irq, dest_map);

	return r;
}

void kvm_set_msi_irq(struct kvm *kvm, struct kvm_kernel_irq_routing_entry *e,
		     struct kvm_lapic_irq *irq)
{
	trace_kvm_msi_set_irq(e->msi.address_lo | (kvm->arch.x2apic_format ?
	                                     (u64)e->msi.address_hi << 32 : 0),
	                      e->msi.data);

	irq->dest_id = (e->msi.address_lo &
			MSI_ADDR_DEST_ID_MASK) >> MSI_ADDR_DEST_ID_SHIFT;
	if (kvm->arch.x2apic_format)
		irq->dest_id |= MSI_ADDR_EXT_DEST_ID(e->msi.address_hi);
	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->msi_redir_hint = ((e->msi.address_lo
		& MSI_ADDR_REDIRECTION_LOWPRI) > 0);
	irq->level = 1;
	irq->shorthand = 0;
}
EXPORT_SYMBOL_GPL(kvm_set_msi_irq);

static inline bool kvm_msi_route_invalid(struct kvm *kvm,
		struct kvm_kernel_irq_routing_entry *e)
{
	return kvm->arch.x2apic_format && (e->msi.address_hi & 0xff);
}

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

	if (kvm_msi_route_invalid(kvm, e))
		return -EINVAL;

	if (!level)
		return -1;

	kvm_set_msi_irq(kvm, e, &irq);

	return kvm_irq_delivery_to_apic(kvm, NULL, &irq, NULL);
}


static int kvm_hv_set_sint(struct kvm_kernel_irq_routing_entry *e,
		    struct kvm *kvm, int irq_source_id, int level,
		    bool line_status)
{
	if (!level)
		return -1;

	return kvm_hv_synic_set_irq(kvm, e->hv_sint.vcpu, e->hv_sint.sint);
}

int kvm_arch_set_irq_inatomic(struct kvm_kernel_irq_routing_entry *e,
			      struct kvm *kvm, int irq_source_id, int level,
			      bool line_status)
{
	struct kvm_lapic_irq irq;
	int r;

	switch (e->type) {
	case KVM_IRQ_ROUTING_HV_SINT:
		return kvm_hv_set_sint(e, kvm, irq_source_id, level,
				       line_status);

	case KVM_IRQ_ROUTING_MSI:
		if (kvm_msi_route_invalid(kvm, e))
			return -EINVAL;

		kvm_set_msi_irq(kvm, e, &irq);

		if (kvm_irq_delivery_to_apic_fast(kvm, NULL, &irq, &r, NULL))
			return r;
		break;

	default:
		break;
	}

	return -EWOULDBLOCK;
}

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

	mutex_lock(&kvm->irq_lock);
	irq_source_id = find_first_zero_bit(bitmap, BITS_PER_LONG);

	if (irq_source_id >= BITS_PER_LONG) {
		printk(KERN_WARNING "kvm: exhaust allocatable IRQ sources!\n");
		irq_source_id = -EFAULT;
		goto unlock;
	}

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

	return irq_source_id;
}

void kvm_free_irq_source_id(struct kvm *kvm, int irq_source_id)
{
	ASSERT(irq_source_id != KVM_USERSPACE_IRQ_SOURCE_ID);
	ASSERT(irq_source_id != KVM_IRQFD_RESAMPLE_IRQ_SOURCE_ID);

	mutex_lock(&kvm->irq_lock);
	if (irq_source_id < 0 ||
	    irq_source_id >= BITS_PER_LONG) {
		printk(KERN_ERR "kvm: IRQ source ID out of range!\n");
		goto unlock;
	}
	clear_bit(irq_source_id, &kvm->arch.irq_sources_bitmap);
	if (!ioapic_in_kernel(kvm))
		goto unlock;

	kvm_ioapic_clear_all(kvm->arch.vioapic, irq_source_id);
	kvm_pic_clear_all(pic_irqchip(kvm), irq_source_id);
unlock:
	mutex_unlock(&kvm->irq_lock);
}

void kvm_register_irq_mask_notifier(struct kvm *kvm, int irq,
				    struct kvm_irq_mask_notifier *kimn)
{
	mutex_lock(&kvm->irq_lock);
	kimn->irq = irq;
	hlist_add_head_rcu(&kimn->link, &kvm->arch.mask_notifier_list);
	mutex_unlock(&kvm->irq_lock);
}

void kvm_unregister_irq_mask_notifier(struct kvm *kvm, int irq,
				      struct kvm_irq_mask_notifier *kimn)
{
	mutex_lock(&kvm->irq_lock);
	hlist_del_rcu(&kimn->link);
	mutex_unlock(&kvm->irq_lock);
	synchronize_srcu(&kvm->irq_srcu);
}

void kvm_fire_mask_notifiers(struct kvm *kvm, unsigned irqchip, unsigned pin,
			     bool mask)
{
	struct kvm_irq_mask_notifier *kimn;
	int idx, gsi;

	idx = srcu_read_lock(&kvm->irq_srcu);
	gsi = kvm_irq_map_chip_pin(kvm, irqchip, pin);
	if (gsi != -1)
		hlist_for_each_entry_rcu(kimn, &kvm->arch.mask_notifier_list, link)
			if (kimn->irq == gsi)
				kimn->func(kimn, mask);
	srcu_read_unlock(&kvm->irq_srcu, idx);
}

int kvm_set_routing_entry(struct kvm *kvm,
			  struct kvm_kernel_irq_routing_entry *e,
			  const struct kvm_irq_routing_entry *ue)
{
	int r = -EINVAL;
	int delta;
	unsigned max_pin;

	switch (ue->type) {
	case KVM_IRQ_ROUTING_IRQCHIP:
		delta = 0;
		switch (ue->u.irqchip.irqchip) {
		case KVM_IRQCHIP_PIC_SLAVE:
			delta = 8;
			/* fall through */
		case KVM_IRQCHIP_PIC_MASTER:
			if (!pic_in_kernel(kvm))
				goto out;

			e->set = kvm_set_pic_irq;
			max_pin = PIC_NUM_PINS;
			break;
		case KVM_IRQCHIP_IOAPIC:
			if (!ioapic_in_kernel(kvm))
				goto out;

			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;
		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;

		if (kvm_msi_route_invalid(kvm, e))
			goto out;
		break;
	case KVM_IRQ_ROUTING_HV_SINT:
		e->set = kvm_hv_set_sint;
		e->hv_sint.vcpu = ue->u.hv_sint.vcpu;
		e->hv_sint.sint = ue->u.hv_sint.sint;
		break;
	default:
		goto out;
	}

	r = 0;
out:
	return r;
}

bool kvm_intr_is_single_vcpu(struct kvm *kvm, struct kvm_lapic_irq *irq,
			     struct kvm_vcpu **dest_vcpu)
{
	int i, r = 0;
	struct kvm_vcpu *vcpu;

	if (kvm_intr_is_single_vcpu_fast(kvm, irq, dest_vcpu))
		return true;

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

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

		if (++r == 2)
			return false;

		*dest_vcpu = vcpu;
	}

	return r == 1;
}
EXPORT_SYMBOL_GPL(kvm_intr_is_single_vcpu);

#define IOAPIC_ROUTING_ENTRY(irq) \
	{ .gsi = irq, .type = KVM_IRQ_ROUTING_IRQCHIP,	\
	  .u.irqchip = { .irqchip = KVM_IRQCHIP_IOAPIC, .pin = (irq) } }
#define ROUTING_ENTRY1(irq) IOAPIC_ROUTING_ENTRY(irq)

#define PIC_ROUTING_ENTRY(irq) \
	{ .gsi = irq, .type = KVM_IRQ_ROUTING_IRQCHIP,	\
	  .u.irqchip = { .irqchip = SELECT_PIC(irq), .pin = (irq) % 8 } }
#define ROUTING_ENTRY2(irq) \
	IOAPIC_ROUTING_ENTRY(irq), PIC_ROUTING_ENTRY(irq)

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),
};

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

static const struct kvm_irq_routing_entry empty_routing[] = {};

int kvm_setup_empty_irq_routing(struct kvm *kvm)
{
	return kvm_set_irq_routing(kvm, empty_routing, 0, 0);
}

void kvm_arch_post_irq_routing_update(struct kvm *kvm)
{
	if (!irqchip_split(kvm))
		return;
	kvm_make_scan_ioapic_request(kvm);
}

void kvm_scan_ioapic_routes(struct kvm_vcpu *vcpu,
			    ulong *ioapic_handled_vectors)
{
	struct kvm *kvm = vcpu->kvm;
	struct kvm_kernel_irq_routing_entry *entry;
	struct kvm_irq_routing_table *table;
	u32 i, nr_ioapic_pins;
	int idx;

	idx = srcu_read_lock(&kvm->irq_srcu);
	table = srcu_dereference(kvm->irq_routing, &kvm->irq_srcu);
	nr_ioapic_pins = min_t(u32, table->nr_rt_entries,
			       kvm->arch.nr_reserved_ioapic_pins);
	for (i = 0; i < nr_ioapic_pins; ++i) {
		hlist_for_each_entry(entry, &table->map[i], link) {
			struct kvm_lapic_irq irq;

			if (entry->type != KVM_IRQ_ROUTING_MSI)
				continue;

			kvm_set_msi_irq(vcpu->kvm, entry, &irq);

			if (irq.level && kvm_apic_match_dest(vcpu, NULL, 0,
						irq.dest_id, irq.dest_mode))
				__set_bit(irq.vector, ioapic_handled_vectors);
		}
	}
	srcu_read_unlock(&kvm->irq_srcu, idx);
}

void kvm_arch_irq_routing_update(struct kvm *kvm)
{
	kvm_hv_irq_routing_update(kvm);
}