summaryrefslogtreecommitdiffstats
path: root/arch/arm64/kvm/reset.c
blob: 2202b710d44c9dc001d6dd4c0eb186754b03e975 (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
// SPDX-License-Identifier: GPL-2.0-only
/*
 * Copyright (C) 2012,2013 - ARM Ltd
 * Author: Marc Zyngier <marc.zyngier@arm.com>
 *
 * Derived from arch/arm/kvm/reset.c
 * Copyright (C) 2012 - Virtual Open Systems and Columbia University
 * Author: Christoffer Dall <c.dall@virtualopensystems.com>
 */

#include <linux/errno.h>
#include <linux/kernel.h>
#include <linux/kvm_host.h>
#include <linux/kvm.h>
#include <linux/hw_breakpoint.h>
#include <linux/slab.h>
#include <linux/string.h>
#include <linux/types.h>

#include <kvm/arm_arch_timer.h>

#include <asm/cpufeature.h>
#include <asm/cputype.h>
#include <asm/fpsimd.h>
#include <asm/ptrace.h>
#include <asm/kvm_arm.h>
#include <asm/kvm_asm.h>
#include <asm/kvm_coproc.h>
#include <asm/kvm_emulate.h>
#include <asm/kvm_mmu.h>
#include <asm/virt.h>

/* Maximum phys_shift supported for any VM on this host */
static u32 kvm_ipa_limit;

/*
 * ARMv8 Reset Values
 */
#define VCPU_RESET_PSTATE_EL1	(PSR_MODE_EL1h | PSR_A_BIT | PSR_I_BIT | \
				 PSR_F_BIT | PSR_D_BIT)

#define VCPU_RESET_PSTATE_SVC	(PSR_AA32_MODE_SVC | PSR_AA32_A_BIT | \
				 PSR_AA32_I_BIT | PSR_AA32_F_BIT)

static bool system_has_full_ptr_auth(void)
{
	return system_supports_address_auth() && system_supports_generic_auth();
}

/**
 * kvm_arch_vm_ioctl_check_extension
 *
 * We currently assume that the number of HW registers is uniform
 * across all CPUs (see cpuinfo_sanity_check).
 */
int kvm_arch_vm_ioctl_check_extension(struct kvm *kvm, long ext)
{
	int r;

	switch (ext) {
	case KVM_CAP_ARM_EL1_32BIT:
		r = cpus_have_const_cap(ARM64_HAS_32BIT_EL1);
		break;
	case KVM_CAP_GUEST_DEBUG_HW_BPS:
		r = get_num_brps();
		break;
	case KVM_CAP_GUEST_DEBUG_HW_WPS:
		r = get_num_wrps();
		break;
	case KVM_CAP_ARM_PMU_V3:
		r = kvm_arm_support_pmu_v3();
		break;
	case KVM_CAP_ARM_INJECT_SERROR_ESR:
		r = cpus_have_const_cap(ARM64_HAS_RAS_EXTN);
		break;
	case KVM_CAP_SET_GUEST_DEBUG:
	case KVM_CAP_VCPU_ATTRIBUTES:
		r = 1;
		break;
	case KVM_CAP_ARM_VM_IPA_SIZE:
		r = kvm_ipa_limit;
		break;
	case KVM_CAP_ARM_SVE:
		r = system_supports_sve();
		break;
	case KVM_CAP_ARM_PTRAUTH_ADDRESS:
	case KVM_CAP_ARM_PTRAUTH_GENERIC:
		r = system_has_full_ptr_auth();
		break;
	default:
		r = 0;
	}

	return r;
}

unsigned int kvm_sve_max_vl;

int kvm_arm_init_sve(void)
{
	if (system_supports_sve()) {
		kvm_sve_max_vl = sve_max_virtualisable_vl;

		/*
		 * The get_sve_reg()/set_sve_reg() ioctl interface will need
		 * to be extended with multiple register slice support in
		 * order to support vector lengths greater than
		 * SVE_VL_ARCH_MAX:
		 */
		if (WARN_ON(kvm_sve_max_vl > SVE_VL_ARCH_MAX))
			kvm_sve_max_vl = SVE_VL_ARCH_MAX;

		/*
		 * Don't even try to make use of vector lengths that
		 * aren't available on all CPUs, for now:
		 */
		if (kvm_sve_max_vl < sve_max_vl)
			pr_warn("KVM: SVE vector length for guests limited to %u bytes\n",
				kvm_sve_max_vl);
	}

	return 0;
}

static int kvm_vcpu_enable_sve(struct kvm_vcpu *vcpu)
{
	if (!system_supports_sve())
		return -EINVAL;

	/* Verify that KVM startup enforced this when SVE was detected: */
	if (WARN_ON(!has_vhe()))
		return -EINVAL;

	vcpu->arch.sve_max_vl = kvm_sve_max_vl;

	/*
	 * Userspace can still customize the vector lengths by writing
	 * KVM_REG_ARM64_SVE_VLS.  Allocation is deferred until
	 * kvm_arm_vcpu_finalize(), which freezes the configuration.
	 */
	vcpu->arch.flags |= KVM_ARM64_GUEST_HAS_SVE;

	return 0;
}

/*
 * Finalize vcpu's maximum SVE vector length, allocating
 * vcpu->arch.sve_state as necessary.
 */
static int kvm_vcpu_finalize_sve(struct kvm_vcpu *vcpu)
{
	void *buf;
	unsigned int vl;

	vl = vcpu->arch.sve_max_vl;

	/*
	 * Responsibility for these properties is shared between
	 * kvm_arm_init_arch_resources(), kvm_vcpu_enable_sve() and
	 * set_sve_vls().  Double-check here just to be sure:
	 */
	if (WARN_ON(!sve_vl_valid(vl) || vl > sve_max_virtualisable_vl ||
		    vl > SVE_VL_ARCH_MAX))
		return -EIO;

	buf = kzalloc(SVE_SIG_REGS_SIZE(sve_vq_from_vl(vl)), GFP_KERNEL);
	if (!buf)
		return -ENOMEM;

	vcpu->arch.sve_state = buf;
	vcpu->arch.flags |= KVM_ARM64_VCPU_SVE_FINALIZED;
	return 0;
}

int kvm_arm_vcpu_finalize(struct kvm_vcpu *vcpu, int feature)
{
	switch (feature) {
	case KVM_ARM_VCPU_SVE:
		if (!vcpu_has_sve(vcpu))
			return -EINVAL;

		if (kvm_arm_vcpu_sve_finalized(vcpu))
			return -EPERM;

		return kvm_vcpu_finalize_sve(vcpu);
	}

	return -EINVAL;
}

bool kvm_arm_vcpu_is_finalized(struct kvm_vcpu *vcpu)
{
	if (vcpu_has_sve(vcpu) && !kvm_arm_vcpu_sve_finalized(vcpu))
		return false;

	return true;
}

void kvm_arm_vcpu_destroy(struct kvm_vcpu *vcpu)
{
	kfree(vcpu->arch.sve_state);
}

static void kvm_vcpu_reset_sve(struct kvm_vcpu *vcpu)
{
	if (vcpu_has_sve(vcpu))
		memset(vcpu->arch.sve_state, 0, vcpu_sve_state_size(vcpu));
}

static int kvm_vcpu_enable_ptrauth(struct kvm_vcpu *vcpu)
{
	/*
	 * For now make sure that both address/generic pointer authentication
	 * features are requested by the userspace together and the system
	 * supports these capabilities.
	 */
	if (!test_bit(KVM_ARM_VCPU_PTRAUTH_ADDRESS, vcpu->arch.features) ||
	    !test_bit(KVM_ARM_VCPU_PTRAUTH_GENERIC, vcpu->arch.features) ||
	    !system_has_full_ptr_auth())
		return -EINVAL;

	vcpu->arch.flags |= KVM_ARM64_GUEST_HAS_PTRAUTH;
	return 0;
}

/**
 * kvm_reset_vcpu - sets core registers and sys_regs to reset value
 * @vcpu: The VCPU pointer
 *
 * This function finds the right table above and sets the registers on
 * the virtual CPU struct to their architecturally defined reset
 * values, except for registers whose reset is deferred until
 * kvm_arm_vcpu_finalize().
 *
 * Note: This function can be called from two paths: The KVM_ARM_VCPU_INIT
 * ioctl or as part of handling a request issued by another VCPU in the PSCI
 * handling code.  In the first case, the VCPU will not be loaded, and in the
 * second case the VCPU will be loaded.  Because this function operates purely
 * on the memory-backed values of system registers, we want to do a full put if
 * we were loaded (handling a request) and load the values back at the end of
 * the function.  Otherwise we leave the state alone.  In both cases, we
 * disable preemption around the vcpu reset as we would otherwise race with
 * preempt notifiers which also call put/load.
 */
int kvm_reset_vcpu(struct kvm_vcpu *vcpu)
{
	int ret;
	bool loaded;
	u32 pstate;

	/* Reset PMU outside of the non-preemptible section */
	kvm_pmu_vcpu_reset(vcpu);

	preempt_disable();
	loaded = (vcpu->cpu != -1);
	if (loaded)
		kvm_arch_vcpu_put(vcpu);

	if (!kvm_arm_vcpu_sve_finalized(vcpu)) {
		if (test_bit(KVM_ARM_VCPU_SVE, vcpu->arch.features)) {
			ret = kvm_vcpu_enable_sve(vcpu);
			if (ret)
				goto out;
		}
	} else {
		kvm_vcpu_reset_sve(vcpu);
	}

	if (test_bit(KVM_ARM_VCPU_PTRAUTH_ADDRESS, vcpu->arch.features) ||
	    test_bit(KVM_ARM_VCPU_PTRAUTH_GENERIC, vcpu->arch.features)) {
		if (kvm_vcpu_enable_ptrauth(vcpu)) {
			ret = -EINVAL;
			goto out;
		}
	}

	switch (vcpu->arch.target) {
	default:
		if (test_bit(KVM_ARM_VCPU_EL1_32BIT, vcpu->arch.features)) {
			if (!cpus_have_const_cap(ARM64_HAS_32BIT_EL1)) {
				ret = -EINVAL;
				goto out;
			}
			pstate = VCPU_RESET_PSTATE_SVC;
		} else {
			pstate = VCPU_RESET_PSTATE_EL1;
		}

		break;
	}

	/* Reset core registers */
	memset(vcpu_gp_regs(vcpu), 0, sizeof(*vcpu_gp_regs(vcpu)));
	vcpu_gp_regs(vcpu)->pstate = pstate;

	/* Reset system registers */
	kvm_reset_sys_regs(vcpu);

	/*
	 * Additional reset state handling that PSCI may have imposed on us.
	 * Must be done after all the sys_reg reset.
	 */
	if (vcpu->arch.reset_state.reset) {
		unsigned long target_pc = vcpu->arch.reset_state.pc;

		/* Gracefully handle Thumb2 entry point */
		if (vcpu_mode_is_32bit(vcpu) && (target_pc & 1)) {
			target_pc &= ~1UL;
			vcpu_set_thumb(vcpu);
		}

		/* Propagate caller endianness */
		if (vcpu->arch.reset_state.be)
			kvm_vcpu_set_be(vcpu);

		*vcpu_pc(vcpu) = target_pc;
		vcpu_set_reg(vcpu, 0, vcpu->arch.reset_state.r0);

		vcpu->arch.reset_state.reset = false;
	}

	/* Default workaround setup is enabled (if supported) */
	if (kvm_arm_have_ssbd() == KVM_SSBD_KERNEL)
		vcpu->arch.workaround_flags |= VCPU_WORKAROUND_2_FLAG;

	/* Reset timer */
	ret = kvm_timer_vcpu_reset(vcpu);
out:
	if (loaded)
		kvm_arch_vcpu_load(vcpu, smp_processor_id());
	preempt_enable();
	return ret;
}

u32 get_kvm_ipa_limit(void)
{
	return kvm_ipa_limit;
}

int kvm_set_ipa_limit(void)
{
	unsigned int parange, tgran_2;
	u64 mmfr0;

	mmfr0 = read_sanitised_ftr_reg(SYS_ID_AA64MMFR0_EL1);
	parange = cpuid_feature_extract_unsigned_field(mmfr0,
				ID_AA64MMFR0_PARANGE_SHIFT);

	/*
	 * Check with ARMv8.5-GTG that our PAGE_SIZE is supported at
	 * Stage-2. If not, things will stop very quickly.
	 */
	switch (PAGE_SIZE) {
	default:
	case SZ_4K:
		tgran_2 = ID_AA64MMFR0_TGRAN4_2_SHIFT;
		break;
	case SZ_16K:
		tgran_2 = ID_AA64MMFR0_TGRAN16_2_SHIFT;
		break;
	case SZ_64K:
		tgran_2 = ID_AA64MMFR0_TGRAN64_2_SHIFT;
		break;
	}

	switch (cpuid_feature_extract_unsigned_field(mmfr0, tgran_2)) {
	default:
	case 1:
		kvm_err("PAGE_SIZE not supported at Stage-2, giving up\n");
		return -EINVAL;
	case 0:
		kvm_debug("PAGE_SIZE supported at Stage-2 (default)\n");
		break;
	case 2:
		kvm_debug("PAGE_SIZE supported at Stage-2 (advertised)\n");
		break;
	}

	kvm_ipa_limit = id_aa64mmfr0_parange_to_phys_shift(parange);
	WARN(kvm_ipa_limit < KVM_PHYS_SHIFT,
	     "KVM IPA Size Limit (%d bits) is smaller than default size\n",
	     kvm_ipa_limit);
	kvm_info("IPA Size Limit: %d bits\n", kvm_ipa_limit);

	return 0;
}

/*
 * Configure the VTCR_EL2 for this VM. The VTCR value is common
 * across all the physical CPUs on the system. We use system wide
 * sanitised values to fill in different fields, except for Hardware
 * Management of Access Flags. HA Flag is set unconditionally on
 * all CPUs, as it is safe to run with or without the feature and
 * the bit is RES0 on CPUs that don't support it.
 */
int kvm_arm_setup_stage2(struct kvm *kvm, unsigned long type)
{
	u64 vtcr = VTCR_EL2_FLAGS, mmfr0;
	u32 parange, phys_shift;
	u8 lvls;

	if (type & ~KVM_VM_TYPE_ARM_IPA_SIZE_MASK)
		return -EINVAL;

	phys_shift = KVM_VM_TYPE_ARM_IPA_SIZE(type);
	if (phys_shift) {
		if (phys_shift > kvm_ipa_limit ||
		    phys_shift < 32)
			return -EINVAL;
	} else {
		phys_shift = KVM_PHYS_SHIFT;
	}

	mmfr0 = read_sanitised_ftr_reg(SYS_ID_AA64MMFR0_EL1);
	parange = cpuid_feature_extract_unsigned_field(mmfr0,
				ID_AA64MMFR0_PARANGE_SHIFT);
	if (parange > ID_AA64MMFR0_PARANGE_MAX)
		parange = ID_AA64MMFR0_PARANGE_MAX;
	vtcr |= parange << VTCR_EL2_PS_SHIFT;

	vtcr |= VTCR_EL2_T0SZ(phys_shift);
	/*
	 * Use a minimum 2 level page table to prevent splitting
	 * host PMD huge pages at stage2.
	 */
	lvls = stage2_pgtable_levels(phys_shift);
	if (lvls < 2)
		lvls = 2;
	vtcr |= VTCR_EL2_LVLS_TO_SL0(lvls);

	/*
	 * Enable the Hardware Access Flag management, unconditionally
	 * on all CPUs. The features is RES0 on CPUs without the support
	 * and must be ignored by the CPUs.
	 */
	vtcr |= VTCR_EL2_HA;

	/* Set the vmid bits */
	vtcr |= (kvm_get_vmid_bits() == 16) ?
		VTCR_EL2_VS_16BIT :
		VTCR_EL2_VS_8BIT;
	kvm->arch.vtcr = vtcr;
	return 0;
}