summaryrefslogtreecommitdiff
path: root/arch/arm64/kvm/vgic/vgic-init.c
blob: c8c3cb812783218e93065d157291d09c7a4a0812 (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
// SPDX-License-Identifier: GPL-2.0-only
/*
 * Copyright (C) 2015, 2016 ARM Ltd.
 */

#include <linux/uaccess.h>
#include <linux/interrupt.h>
#include <linux/cpu.h>
#include <linux/kvm_host.h>
#include <kvm/arm_vgic.h>
#include <asm/kvm_emulate.h>
#include <asm/kvm_mmu.h>
#include "vgic.h"

/*
 * Initialization rules: there are multiple stages to the vgic
 * initialization, both for the distributor and the CPU interfaces.  The basic
 * idea is that even though the VGIC is not functional or not requested from
 * user space, the critical path of the run loop can still call VGIC functions
 * that just won't do anything, without them having to check additional
 * initialization flags to ensure they don't look at uninitialized data
 * structures.
 *
 * Distributor:
 *
 * - kvm_vgic_early_init(): initialization of static data that doesn't
 *   depend on any sizing information or emulation type. No allocation
 *   is allowed there.
 *
 * - vgic_init(): allocation and initialization of the generic data
 *   structures that depend on sizing information (number of CPUs,
 *   number of interrupts). Also initializes the vcpu specific data
 *   structures. Can be executed lazily for GICv2.
 *
 * CPU Interface:
 *
 * - kvm_vgic_vcpu_init(): initialization of static data that
 *   doesn't depend on any sizing information or emulation type. No
 *   allocation is allowed there.
 */

/* EARLY INIT */

/**
 * kvm_vgic_early_init() - Initialize static VGIC VCPU data structures
 * @kvm: The VM whose VGIC districutor should be initialized
 *
 * Only do initialization of static structures that don't require any
 * allocation or sizing information from userspace.  vgic_init() called
 * kvm_vgic_dist_init() which takes care of the rest.
 */
void kvm_vgic_early_init(struct kvm *kvm)
{
	struct vgic_dist *dist = &kvm->arch.vgic;

	INIT_LIST_HEAD(&dist->lpi_list_head);
	INIT_LIST_HEAD(&dist->lpi_translation_cache);
	raw_spin_lock_init(&dist->lpi_list_lock);
}

/* CREATION */

/**
 * kvm_vgic_create: triggered by the instantiation of the VGIC device by
 * user space, either through the legacy KVM_CREATE_IRQCHIP ioctl (v2 only)
 * or through the generic KVM_CREATE_DEVICE API ioctl.
 * irqchip_in_kernel() tells you if this function succeeded or not.
 * @kvm: kvm struct pointer
 * @type: KVM_DEV_TYPE_ARM_VGIC_V[23]
 */
int kvm_vgic_create(struct kvm *kvm, u32 type)
{
	struct kvm_vcpu *vcpu;
	unsigned long i;
	int ret;

	/*
	 * This function is also called by the KVM_CREATE_IRQCHIP handler,
	 * which had no chance yet to check the availability of the GICv2
	 * emulation. So check this here again. KVM_CREATE_DEVICE does
	 * the proper checks already.
	 */
	if (type == KVM_DEV_TYPE_ARM_VGIC_V2 &&
		!kvm_vgic_global_state.can_emulate_gicv2)
		return -ENODEV;

	/* Must be held to avoid race with vCPU creation */
	lockdep_assert_held(&kvm->lock);

	ret = -EBUSY;
	if (!lock_all_vcpus(kvm))
		return ret;

	mutex_lock(&kvm->arch.config_lock);

	if (irqchip_in_kernel(kvm)) {
		ret = -EEXIST;
		goto out_unlock;
	}

	kvm_for_each_vcpu(i, vcpu, kvm) {
		if (vcpu_has_run_once(vcpu))
			goto out_unlock;
	}
	ret = 0;

	if (type == KVM_DEV_TYPE_ARM_VGIC_V2)
		kvm->max_vcpus = VGIC_V2_MAX_CPUS;
	else
		kvm->max_vcpus = VGIC_V3_MAX_CPUS;

	if (atomic_read(&kvm->online_vcpus) > kvm->max_vcpus) {
		ret = -E2BIG;
		goto out_unlock;
	}

	kvm->arch.vgic.in_kernel = true;
	kvm->arch.vgic.vgic_model = type;

	kvm->arch.vgic.vgic_dist_base = VGIC_ADDR_UNDEF;

	if (type == KVM_DEV_TYPE_ARM_VGIC_V2)
		kvm->arch.vgic.vgic_cpu_base = VGIC_ADDR_UNDEF;
	else
		INIT_LIST_HEAD(&kvm->arch.vgic.rd_regions);

out_unlock:
	mutex_unlock(&kvm->arch.config_lock);
	unlock_all_vcpus(kvm);
	return ret;
}

/* INIT/DESTROY */

/**
 * kvm_vgic_dist_init: initialize the dist data structures
 * @kvm: kvm struct pointer
 * @nr_spis: number of spis, frozen by caller
 */
static int kvm_vgic_dist_init(struct kvm *kvm, unsigned int nr_spis)
{
	struct vgic_dist *dist = &kvm->arch.vgic;
	struct kvm_vcpu *vcpu0 = kvm_get_vcpu(kvm, 0);
	int i;

	dist->spis = kcalloc(nr_spis, sizeof(struct vgic_irq), GFP_KERNEL_ACCOUNT);
	if (!dist->spis)
		return  -ENOMEM;

	/*
	 * In the following code we do not take the irq struct lock since
	 * no other action on irq structs can happen while the VGIC is
	 * not initialized yet:
	 * If someone wants to inject an interrupt or does a MMIO access, we
	 * require prior initialization in case of a virtual GICv3 or trigger
	 * initialization when using a virtual GICv2.
	 */
	for (i = 0; i < nr_spis; i++) {
		struct vgic_irq *irq = &dist->spis[i];

		irq->intid = i + VGIC_NR_PRIVATE_IRQS;
		INIT_LIST_HEAD(&irq->ap_list);
		raw_spin_lock_init(&irq->irq_lock);
		irq->vcpu = NULL;
		irq->target_vcpu = vcpu0;
		kref_init(&irq->refcount);
		switch (dist->vgic_model) {
		case KVM_DEV_TYPE_ARM_VGIC_V2:
			irq->targets = 0;
			irq->group = 0;
			break;
		case KVM_DEV_TYPE_ARM_VGIC_V3:
			irq->mpidr = 0;
			irq->group = 1;
			break;
		default:
			kfree(dist->spis);
			dist->spis = NULL;
			return -EINVAL;
		}
	}
	return 0;
}

/**
 * kvm_vgic_vcpu_init() - Initialize static VGIC VCPU data
 * structures and register VCPU-specific KVM iodevs
 *
 * @vcpu: pointer to the VCPU being created and initialized
 *
 * Only do initialization, but do not actually enable the
 * VGIC CPU interface
 */
int kvm_vgic_vcpu_init(struct kvm_vcpu *vcpu)
{
	struct vgic_cpu *vgic_cpu = &vcpu->arch.vgic_cpu;
	struct vgic_dist *dist = &vcpu->kvm->arch.vgic;
	int ret = 0;
	int i;

	vgic_cpu->rd_iodev.base_addr = VGIC_ADDR_UNDEF;

	INIT_LIST_HEAD(&vgic_cpu->ap_list_head);
	raw_spin_lock_init(&vgic_cpu->ap_list_lock);
	atomic_set(&vgic_cpu->vgic_v3.its_vpe.vlpi_count, 0);

	/*
	 * Enable and configure all SGIs to be edge-triggered and
	 * configure all PPIs as level-triggered.
	 */
	for (i = 0; i < VGIC_NR_PRIVATE_IRQS; i++) {
		struct vgic_irq *irq = &vgic_cpu->private_irqs[i];

		INIT_LIST_HEAD(&irq->ap_list);
		raw_spin_lock_init(&irq->irq_lock);
		irq->intid = i;
		irq->vcpu = NULL;
		irq->target_vcpu = vcpu;
		kref_init(&irq->refcount);
		if (vgic_irq_is_sgi(i)) {
			/* SGIs */
			irq->enabled = 1;
			irq->config = VGIC_CONFIG_EDGE;
		} else {
			/* PPIs */
			irq->config = VGIC_CONFIG_LEVEL;
		}
	}

	if (!irqchip_in_kernel(vcpu->kvm))
		return 0;

	/*
	 * If we are creating a VCPU with a GICv3 we must also register the
	 * KVM io device for the redistributor that belongs to this VCPU.
	 */
	if (dist->vgic_model == KVM_DEV_TYPE_ARM_VGIC_V3) {
		mutex_lock(&vcpu->kvm->slots_lock);
		ret = vgic_register_redist_iodev(vcpu);
		mutex_unlock(&vcpu->kvm->slots_lock);
	}
	return ret;
}

static void kvm_vgic_vcpu_enable(struct kvm_vcpu *vcpu)
{
	if (kvm_vgic_global_state.type == VGIC_V2)
		vgic_v2_enable(vcpu);
	else
		vgic_v3_enable(vcpu);
}

/*
 * vgic_init: allocates and initializes dist and vcpu data structures
 * depending on two dimensioning parameters:
 * - the number of spis
 * - the number of vcpus
 * The function is generally called when nr_spis has been explicitly set
 * by the guest through the KVM DEVICE API. If not nr_spis is set to 256.
 * vgic_initialized() returns true when this function has succeeded.
 */
int vgic_init(struct kvm *kvm)
{
	struct vgic_dist *dist = &kvm->arch.vgic;
	struct kvm_vcpu *vcpu;
	int ret = 0, i;
	unsigned long idx;

	lockdep_assert_held(&kvm->arch.config_lock);

	if (vgic_initialized(kvm))
		return 0;

	/* Are we also in the middle of creating a VCPU? */
	if (kvm->created_vcpus != atomic_read(&kvm->online_vcpus))
		return -EBUSY;

	/* freeze the number of spis */
	if (!dist->nr_spis)
		dist->nr_spis = VGIC_NR_IRQS_LEGACY - VGIC_NR_PRIVATE_IRQS;

	ret = kvm_vgic_dist_init(kvm, dist->nr_spis);
	if (ret)
		goto out;

	/* Initialize groups on CPUs created before the VGIC type was known */
	kvm_for_each_vcpu(idx, vcpu, kvm) {
		struct vgic_cpu *vgic_cpu = &vcpu->arch.vgic_cpu;

		for (i = 0; i < VGIC_NR_PRIVATE_IRQS; i++) {
			struct vgic_irq *irq = &vgic_cpu->private_irqs[i];
			switch (dist->vgic_model) {
			case KVM_DEV_TYPE_ARM_VGIC_V3:
				irq->group = 1;
				irq->mpidr = kvm_vcpu_get_mpidr_aff(vcpu);
				break;
			case KVM_DEV_TYPE_ARM_VGIC_V2:
				irq->group = 0;
				irq->targets = 1U << idx;
				break;
			default:
				ret = -EINVAL;
				goto out;
			}
		}
	}

	if (vgic_has_its(kvm))
		vgic_lpi_translation_cache_init(kvm);

	/*
	 * If we have GICv4.1 enabled, unconditionnaly request enable the
	 * v4 support so that we get HW-accelerated vSGIs. Otherwise, only
	 * enable it if we present a virtual ITS to the guest.
	 */
	if (vgic_supports_direct_msis(kvm)) {
		ret = vgic_v4_init(kvm);
		if (ret)
			goto out;
	}

	kvm_for_each_vcpu(idx, vcpu, kvm)
		kvm_vgic_vcpu_enable(vcpu);

	ret = kvm_vgic_setup_default_irq_routing(kvm);
	if (ret)
		goto out;

	vgic_debug_init(kvm);

	/*
	 * If userspace didn't set the GIC implementation revision,
	 * default to the latest and greatest. You know want it.
	 */
	if (!dist->implementation_rev)
		dist->implementation_rev = KVM_VGIC_IMP_REV_LATEST;
	dist->initialized = true;

out:
	return ret;
}

static void kvm_vgic_dist_destroy(struct kvm *kvm)
{
	struct vgic_dist *dist = &kvm->arch.vgic;
	struct vgic_redist_region *rdreg, *next;

	dist->ready = false;
	dist->initialized = false;

	kfree(dist->spis);
	dist->spis = NULL;
	dist->nr_spis = 0;
	dist->vgic_dist_base = VGIC_ADDR_UNDEF;

	if (dist->vgic_model == KVM_DEV_TYPE_ARM_VGIC_V3) {
		list_for_each_entry_safe(rdreg, next, &dist->rd_regions, list)
			vgic_v3_free_redist_region(rdreg);
		INIT_LIST_HEAD(&dist->rd_regions);
	} else {
		dist->vgic_cpu_base = VGIC_ADDR_UNDEF;
	}

	if (vgic_has_its(kvm))
		vgic_lpi_translation_cache_destroy(kvm);

	if (vgic_supports_direct_msis(kvm))
		vgic_v4_teardown(kvm);
}

void kvm_vgic_vcpu_destroy(struct kvm_vcpu *vcpu)
{
	struct vgic_cpu *vgic_cpu = &vcpu->arch.vgic_cpu;

	/*
	 * Retire all pending LPIs on this vcpu anyway as we're
	 * going to destroy it.
	 */
	vgic_flush_pending_lpis(vcpu);

	INIT_LIST_HEAD(&vgic_cpu->ap_list_head);
	vgic_cpu->rd_iodev.base_addr = VGIC_ADDR_UNDEF;
}

static void __kvm_vgic_destroy(struct kvm *kvm)
{
	struct kvm_vcpu *vcpu;
	unsigned long i;

	lockdep_assert_held(&kvm->arch.config_lock);

	vgic_debug_destroy(kvm);

	kvm_for_each_vcpu(i, vcpu, kvm)
		kvm_vgic_vcpu_destroy(vcpu);

	kvm_vgic_dist_destroy(kvm);
}

void kvm_vgic_destroy(struct kvm *kvm)
{
	mutex_lock(&kvm->arch.config_lock);
	__kvm_vgic_destroy(kvm);
	mutex_unlock(&kvm->arch.config_lock);
}

/**
 * vgic_lazy_init: Lazy init is only allowed if the GIC exposed to the guest
 * is a GICv2. A GICv3 must be explicitly initialized by userspace using the
 * KVM_DEV_ARM_VGIC_GRP_CTRL KVM_DEVICE group.
 * @kvm: kvm struct pointer
 */
int vgic_lazy_init(struct kvm *kvm)
{
	int ret = 0;

	if (unlikely(!vgic_initialized(kvm))) {
		/*
		 * We only provide the automatic initialization of the VGIC
		 * for the legacy case of a GICv2. Any other type must
		 * be explicitly initialized once setup with the respective
		 * KVM device call.
		 */
		if (kvm->arch.vgic.vgic_model != KVM_DEV_TYPE_ARM_VGIC_V2)
			return -EBUSY;

		mutex_lock(&kvm->arch.config_lock);
		ret = vgic_init(kvm);
		mutex_unlock(&kvm->arch.config_lock);
	}

	return ret;
}

/* RESOURCE MAPPING */

/**
 * Map the MMIO regions depending on the VGIC model exposed to the guest
 * called on the first VCPU run.
 * Also map the virtual CPU interface into the VM.
 * v2 calls vgic_init() if not already done.
 * v3 and derivatives return an error if the VGIC is not initialized.
 * vgic_ready() returns true if this function has succeeded.
 * @kvm: kvm struct pointer
 */
int kvm_vgic_map_resources(struct kvm *kvm)
{
	struct vgic_dist *dist = &kvm->arch.vgic;
	enum vgic_type type;
	gpa_t dist_base;
	int ret = 0;

	if (likely(vgic_ready(kvm)))
		return 0;

	mutex_lock(&kvm->slots_lock);
	mutex_lock(&kvm->arch.config_lock);
	if (vgic_ready(kvm))
		goto out;

	if (!irqchip_in_kernel(kvm))
		goto out;

	if (dist->vgic_model == KVM_DEV_TYPE_ARM_VGIC_V2) {
		ret = vgic_v2_map_resources(kvm);
		type = VGIC_V2;
	} else {
		ret = vgic_v3_map_resources(kvm);
		type = VGIC_V3;
	}

	if (ret) {
		__kvm_vgic_destroy(kvm);
		goto out;
	}
	dist->ready = true;
	dist_base = dist->vgic_dist_base;
	mutex_unlock(&kvm->arch.config_lock);

	ret = vgic_register_dist_iodev(kvm, dist_base, type);
	if (ret) {
		kvm_err("Unable to register VGIC dist MMIO regions\n");
		kvm_vgic_destroy(kvm);
	}
	mutex_unlock(&kvm->slots_lock);
	return ret;

out:
	mutex_unlock(&kvm->arch.config_lock);
	mutex_unlock(&kvm->slots_lock);
	return ret;
}

/* GENERIC PROBE */

void kvm_vgic_cpu_up(void)
{
	enable_percpu_irq(kvm_vgic_global_state.maint_irq, 0);
}


void kvm_vgic_cpu_down(void)
{
	disable_percpu_irq(kvm_vgic_global_state.maint_irq);
}

static irqreturn_t vgic_maintenance_handler(int irq, void *data)
{
	/*
	 * We cannot rely on the vgic maintenance interrupt to be
	 * delivered synchronously. This means we can only use it to
	 * exit the VM, and we perform the handling of EOIed
	 * interrupts on the exit path (see vgic_fold_lr_state).
	 */
	return IRQ_HANDLED;
}

static struct gic_kvm_info *gic_kvm_info;

void __init vgic_set_kvm_info(const struct gic_kvm_info *info)
{
	BUG_ON(gic_kvm_info != NULL);
	gic_kvm_info = kmalloc(sizeof(*info), GFP_KERNEL);
	if (gic_kvm_info)
		*gic_kvm_info = *info;
}

/**
 * kvm_vgic_init_cpu_hardware - initialize the GIC VE hardware
 *
 * For a specific CPU, initialize the GIC VE hardware.
 */
void kvm_vgic_init_cpu_hardware(void)
{
	BUG_ON(preemptible());

	/*
	 * We want to make sure the list registers start out clear so that we
	 * only have the program the used registers.
	 */
	if (kvm_vgic_global_state.type == VGIC_V2)
		vgic_v2_init_lrs();
	else
		kvm_call_hyp(__vgic_v3_init_lrs);
}

/**
 * kvm_vgic_hyp_init: populates the kvm_vgic_global_state variable
 * according to the host GIC model. Accordingly calls either
 * vgic_v2/v3_probe which registers the KVM_DEVICE that can be
 * instantiated by a guest later on .
 */
int kvm_vgic_hyp_init(void)
{
	bool has_mask;
	int ret;

	if (!gic_kvm_info)
		return -ENODEV;

	has_mask = !gic_kvm_info->no_maint_irq_mask;

	if (has_mask && !gic_kvm_info->maint_irq) {
		kvm_err("No vgic maintenance irq\n");
		return -ENXIO;
	}

	/*
	 * If we get one of these oddball non-GICs, taint the kernel,
	 * as we have no idea of how they *really* behave.
	 */
	if (gic_kvm_info->no_hw_deactivation) {
		kvm_info("Non-architectural vgic, tainting kernel\n");
		add_taint(TAINT_CPU_OUT_OF_SPEC, LOCKDEP_STILL_OK);
		kvm_vgic_global_state.no_hw_deactivation = true;
	}

	switch (gic_kvm_info->type) {
	case GIC_V2:
		ret = vgic_v2_probe(gic_kvm_info);
		break;
	case GIC_V3:
		ret = vgic_v3_probe(gic_kvm_info);
		if (!ret) {
			static_branch_enable(&kvm_vgic_global_state.gicv3_cpuif);
			kvm_info("GIC system register CPU interface enabled\n");
		}
		break;
	default:
		ret = -ENODEV;
	}

	kvm_vgic_global_state.maint_irq = gic_kvm_info->maint_irq;

	kfree(gic_kvm_info);
	gic_kvm_info = NULL;

	if (ret)
		return ret;

	if (!has_mask && !kvm_vgic_global_state.maint_irq)
		return 0;

	ret = request_percpu_irq(kvm_vgic_global_state.maint_irq,
				 vgic_maintenance_handler,
				 "vgic", kvm_get_running_vcpus());
	if (ret) {
		kvm_err("Cannot register interrupt %d\n",
			kvm_vgic_global_state.maint_irq);
		return ret;
	}

	kvm_info("vgic interrupt IRQ%d\n", kvm_vgic_global_state.maint_irq);
	return 0;
}