summaryrefslogtreecommitdiff
path: root/arch/arm64/kvm/hyp/nvhe/hyp-main.c
blob: f43d845f3c4ecdc41c1c661f8bbbb8165678897b (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
// SPDX-License-Identifier: GPL-2.0-only
/*
 * Copyright (C) 2020 - Google Inc
 * Author: Andrew Scull <ascull@google.com>
 */

#include <hyp/adjust_pc.h>

#include <asm/pgtable-types.h>
#include <asm/kvm_asm.h>
#include <asm/kvm_emulate.h>
#include <asm/kvm_host.h>
#include <asm/kvm_hyp.h>
#include <asm/kvm_mmu.h>

#include <nvhe/ffa.h>
#include <nvhe/mem_protect.h>
#include <nvhe/mm.h>
#include <nvhe/pkvm.h>
#include <nvhe/trap_handler.h>

DEFINE_PER_CPU(struct kvm_nvhe_init_params, kvm_init_params);

void __kvm_hyp_host_forward_smc(struct kvm_cpu_context *host_ctxt);

static void __hyp_sve_save_guest(struct kvm_vcpu *vcpu)
{
	__vcpu_sys_reg(vcpu, ZCR_EL1) = read_sysreg_el1(SYS_ZCR);
	/*
	 * On saving/restoring guest sve state, always use the maximum VL for
	 * the guest. The layout of the data when saving the sve state depends
	 * on the VL, so use a consistent (i.e., the maximum) guest VL.
	 */
	sve_cond_update_zcr_vq(vcpu_sve_max_vq(vcpu) - 1, SYS_ZCR_EL2);
	__sve_save_state(vcpu_sve_pffr(vcpu), &vcpu->arch.ctxt.fp_regs.fpsr, true);
	write_sysreg_s(ZCR_ELx_LEN_MASK, SYS_ZCR_EL2);
}

static void __hyp_sve_restore_host(void)
{
	struct cpu_sve_state *sve_state = *host_data_ptr(sve_state);

	/*
	 * On saving/restoring host sve state, always use the maximum VL for
	 * the host. The layout of the data when saving the sve state depends
	 * on the VL, so use a consistent (i.e., the maximum) host VL.
	 *
	 * Setting ZCR_EL2 to ZCR_ELx_LEN_MASK sets the effective length
	 * supported by the system (or limited at EL3).
	 */
	write_sysreg_s(ZCR_ELx_LEN_MASK, SYS_ZCR_EL2);
	__sve_restore_state(sve_state->sve_regs + sve_ffr_offset(kvm_host_sve_max_vl),
			    &sve_state->fpsr,
			    true);
	write_sysreg_el1(sve_state->zcr_el1, SYS_ZCR);
}

static void fpsimd_sve_flush(void)
{
	*host_data_ptr(fp_owner) = FP_STATE_HOST_OWNED;
}

static void fpsimd_sve_sync(struct kvm_vcpu *vcpu)
{
	if (!guest_owns_fp_regs())
		return;

	cpacr_clear_set(0, CPACR_ELx_FPEN | CPACR_ELx_ZEN);
	isb();

	if (vcpu_has_sve(vcpu))
		__hyp_sve_save_guest(vcpu);
	else
		__fpsimd_save_state(&vcpu->arch.ctxt.fp_regs);

	if (system_supports_sve())
		__hyp_sve_restore_host();
	else
		__fpsimd_restore_state(*host_data_ptr(fpsimd_state));

	*host_data_ptr(fp_owner) = FP_STATE_HOST_OWNED;
}

static void flush_hyp_vcpu(struct pkvm_hyp_vcpu *hyp_vcpu)
{
	struct kvm_vcpu *host_vcpu = hyp_vcpu->host_vcpu;

	fpsimd_sve_flush();

	hyp_vcpu->vcpu.arch.ctxt	= host_vcpu->arch.ctxt;

	hyp_vcpu->vcpu.arch.sve_state	= kern_hyp_va(host_vcpu->arch.sve_state);
	/* Limit guest vector length to the maximum supported by the host.  */
	hyp_vcpu->vcpu.arch.sve_max_vl	= min(host_vcpu->arch.sve_max_vl, kvm_host_sve_max_vl);

	hyp_vcpu->vcpu.arch.hw_mmu	= host_vcpu->arch.hw_mmu;

	hyp_vcpu->vcpu.arch.hcr_el2	= host_vcpu->arch.hcr_el2;
	hyp_vcpu->vcpu.arch.mdcr_el2	= host_vcpu->arch.mdcr_el2;

	hyp_vcpu->vcpu.arch.iflags	= host_vcpu->arch.iflags;

	hyp_vcpu->vcpu.arch.debug_ptr	= kern_hyp_va(host_vcpu->arch.debug_ptr);

	hyp_vcpu->vcpu.arch.vsesr_el2	= host_vcpu->arch.vsesr_el2;

	hyp_vcpu->vcpu.arch.vgic_cpu.vgic_v3 = host_vcpu->arch.vgic_cpu.vgic_v3;
}

static void sync_hyp_vcpu(struct pkvm_hyp_vcpu *hyp_vcpu)
{
	struct kvm_vcpu *host_vcpu = hyp_vcpu->host_vcpu;
	struct vgic_v3_cpu_if *hyp_cpu_if = &hyp_vcpu->vcpu.arch.vgic_cpu.vgic_v3;
	struct vgic_v3_cpu_if *host_cpu_if = &host_vcpu->arch.vgic_cpu.vgic_v3;
	unsigned int i;

	fpsimd_sve_sync(&hyp_vcpu->vcpu);

	host_vcpu->arch.ctxt		= hyp_vcpu->vcpu.arch.ctxt;

	host_vcpu->arch.hcr_el2		= hyp_vcpu->vcpu.arch.hcr_el2;

	host_vcpu->arch.fault		= hyp_vcpu->vcpu.arch.fault;

	host_vcpu->arch.iflags		= hyp_vcpu->vcpu.arch.iflags;

	host_cpu_if->vgic_hcr		= hyp_cpu_if->vgic_hcr;
	for (i = 0; i < hyp_cpu_if->used_lrs; ++i)
		host_cpu_if->vgic_lr[i] = hyp_cpu_if->vgic_lr[i];
}

static void handle___kvm_vcpu_run(struct kvm_cpu_context *host_ctxt)
{
	DECLARE_REG(struct kvm_vcpu *, host_vcpu, host_ctxt, 1);
	int ret;

	host_vcpu = kern_hyp_va(host_vcpu);

	if (unlikely(is_protected_kvm_enabled())) {
		struct pkvm_hyp_vcpu *hyp_vcpu;
		struct kvm *host_kvm;

		/*
		 * KVM (and pKVM) doesn't support SME guests for now, and
		 * ensures that SME features aren't enabled in pstate when
		 * loading a vcpu. Therefore, if SME features enabled the host
		 * is misbehaving.
		 */
		if (unlikely(system_supports_sme() && read_sysreg_s(SYS_SVCR))) {
			ret = -EINVAL;
			goto out;
		}

		host_kvm = kern_hyp_va(host_vcpu->kvm);
		hyp_vcpu = pkvm_load_hyp_vcpu(host_kvm->arch.pkvm.handle,
					      host_vcpu->vcpu_idx);
		if (!hyp_vcpu) {
			ret = -EINVAL;
			goto out;
		}

		flush_hyp_vcpu(hyp_vcpu);

		ret = __kvm_vcpu_run(&hyp_vcpu->vcpu);

		sync_hyp_vcpu(hyp_vcpu);
		pkvm_put_hyp_vcpu(hyp_vcpu);
	} else {
		/* The host is fully trusted, run its vCPU directly. */
		ret = __kvm_vcpu_run(host_vcpu);
	}

out:
	cpu_reg(host_ctxt, 1) =  ret;
}

static void handle___kvm_adjust_pc(struct kvm_cpu_context *host_ctxt)
{
	DECLARE_REG(struct kvm_vcpu *, vcpu, host_ctxt, 1);

	__kvm_adjust_pc(kern_hyp_va(vcpu));
}

static void handle___kvm_flush_vm_context(struct kvm_cpu_context *host_ctxt)
{
	__kvm_flush_vm_context();
}

static void handle___kvm_tlb_flush_vmid_ipa(struct kvm_cpu_context *host_ctxt)
{
	DECLARE_REG(struct kvm_s2_mmu *, mmu, host_ctxt, 1);
	DECLARE_REG(phys_addr_t, ipa, host_ctxt, 2);
	DECLARE_REG(int, level, host_ctxt, 3);

	__kvm_tlb_flush_vmid_ipa(kern_hyp_va(mmu), ipa, level);
}

static void handle___kvm_tlb_flush_vmid_ipa_nsh(struct kvm_cpu_context *host_ctxt)
{
	DECLARE_REG(struct kvm_s2_mmu *, mmu, host_ctxt, 1);
	DECLARE_REG(phys_addr_t, ipa, host_ctxt, 2);
	DECLARE_REG(int, level, host_ctxt, 3);

	__kvm_tlb_flush_vmid_ipa_nsh(kern_hyp_va(mmu), ipa, level);
}

static void
handle___kvm_tlb_flush_vmid_range(struct kvm_cpu_context *host_ctxt)
{
	DECLARE_REG(struct kvm_s2_mmu *, mmu, host_ctxt, 1);
	DECLARE_REG(phys_addr_t, start, host_ctxt, 2);
	DECLARE_REG(unsigned long, pages, host_ctxt, 3);

	__kvm_tlb_flush_vmid_range(kern_hyp_va(mmu), start, pages);
}

static void handle___kvm_tlb_flush_vmid(struct kvm_cpu_context *host_ctxt)
{
	DECLARE_REG(struct kvm_s2_mmu *, mmu, host_ctxt, 1);

	__kvm_tlb_flush_vmid(kern_hyp_va(mmu));
}

static void handle___kvm_flush_cpu_context(struct kvm_cpu_context *host_ctxt)
{
	DECLARE_REG(struct kvm_s2_mmu *, mmu, host_ctxt, 1);

	__kvm_flush_cpu_context(kern_hyp_va(mmu));
}

static void handle___kvm_timer_set_cntvoff(struct kvm_cpu_context *host_ctxt)
{
	__kvm_timer_set_cntvoff(cpu_reg(host_ctxt, 1));
}

static void handle___kvm_enable_ssbs(struct kvm_cpu_context *host_ctxt)
{
	u64 tmp;

	tmp = read_sysreg_el2(SYS_SCTLR);
	tmp |= SCTLR_ELx_DSSBS;
	write_sysreg_el2(tmp, SYS_SCTLR);
}

static void handle___vgic_v3_get_gic_config(struct kvm_cpu_context *host_ctxt)
{
	cpu_reg(host_ctxt, 1) = __vgic_v3_get_gic_config();
}

static void handle___vgic_v3_init_lrs(struct kvm_cpu_context *host_ctxt)
{
	__vgic_v3_init_lrs();
}

static void handle___kvm_get_mdcr_el2(struct kvm_cpu_context *host_ctxt)
{
	cpu_reg(host_ctxt, 1) = __kvm_get_mdcr_el2();
}

static void handle___vgic_v3_save_vmcr_aprs(struct kvm_cpu_context *host_ctxt)
{
	DECLARE_REG(struct vgic_v3_cpu_if *, cpu_if, host_ctxt, 1);

	__vgic_v3_save_vmcr_aprs(kern_hyp_va(cpu_if));
}

static void handle___vgic_v3_restore_vmcr_aprs(struct kvm_cpu_context *host_ctxt)
{
	DECLARE_REG(struct vgic_v3_cpu_if *, cpu_if, host_ctxt, 1);

	__vgic_v3_restore_vmcr_aprs(kern_hyp_va(cpu_if));
}

static void handle___pkvm_init(struct kvm_cpu_context *host_ctxt)
{
	DECLARE_REG(phys_addr_t, phys, host_ctxt, 1);
	DECLARE_REG(unsigned long, size, host_ctxt, 2);
	DECLARE_REG(unsigned long, nr_cpus, host_ctxt, 3);
	DECLARE_REG(unsigned long *, per_cpu_base, host_ctxt, 4);
	DECLARE_REG(u32, hyp_va_bits, host_ctxt, 5);

	/*
	 * __pkvm_init() will return only if an error occurred, otherwise it
	 * will tail-call in __pkvm_init_finalise() which will have to deal
	 * with the host context directly.
	 */
	cpu_reg(host_ctxt, 1) = __pkvm_init(phys, size, nr_cpus, per_cpu_base,
					    hyp_va_bits);
}

static void handle___pkvm_cpu_set_vector(struct kvm_cpu_context *host_ctxt)
{
	DECLARE_REG(enum arm64_hyp_spectre_vector, slot, host_ctxt, 1);

	cpu_reg(host_ctxt, 1) = pkvm_cpu_set_vector(slot);
}

static void handle___pkvm_host_share_hyp(struct kvm_cpu_context *host_ctxt)
{
	DECLARE_REG(u64, pfn, host_ctxt, 1);

	cpu_reg(host_ctxt, 1) = __pkvm_host_share_hyp(pfn);
}

static void handle___pkvm_host_unshare_hyp(struct kvm_cpu_context *host_ctxt)
{
	DECLARE_REG(u64, pfn, host_ctxt, 1);

	cpu_reg(host_ctxt, 1) = __pkvm_host_unshare_hyp(pfn);
}

static void handle___pkvm_create_private_mapping(struct kvm_cpu_context *host_ctxt)
{
	DECLARE_REG(phys_addr_t, phys, host_ctxt, 1);
	DECLARE_REG(size_t, size, host_ctxt, 2);
	DECLARE_REG(enum kvm_pgtable_prot, prot, host_ctxt, 3);

	/*
	 * __pkvm_create_private_mapping() populates a pointer with the
	 * hypervisor start address of the allocation.
	 *
	 * However, handle___pkvm_create_private_mapping() hypercall crosses the
	 * EL1/EL2 boundary so the pointer would not be valid in this context.
	 *
	 * Instead pass the allocation address as the return value (or return
	 * ERR_PTR() on failure).
	 */
	unsigned long haddr;
	int err = __pkvm_create_private_mapping(phys, size, prot, &haddr);

	if (err)
		haddr = (unsigned long)ERR_PTR(err);

	cpu_reg(host_ctxt, 1) = haddr;
}

static void handle___pkvm_prot_finalize(struct kvm_cpu_context *host_ctxt)
{
	cpu_reg(host_ctxt, 1) = __pkvm_prot_finalize();
}

static void handle___pkvm_vcpu_init_traps(struct kvm_cpu_context *host_ctxt)
{
	DECLARE_REG(struct kvm_vcpu *, vcpu, host_ctxt, 1);

	__pkvm_vcpu_init_traps(kern_hyp_va(vcpu));
}

static void handle___pkvm_init_vm(struct kvm_cpu_context *host_ctxt)
{
	DECLARE_REG(struct kvm *, host_kvm, host_ctxt, 1);
	DECLARE_REG(unsigned long, vm_hva, host_ctxt, 2);
	DECLARE_REG(unsigned long, pgd_hva, host_ctxt, 3);

	host_kvm = kern_hyp_va(host_kvm);
	cpu_reg(host_ctxt, 1) = __pkvm_init_vm(host_kvm, vm_hva, pgd_hva);
}

static void handle___pkvm_init_vcpu(struct kvm_cpu_context *host_ctxt)
{
	DECLARE_REG(pkvm_handle_t, handle, host_ctxt, 1);
	DECLARE_REG(struct kvm_vcpu *, host_vcpu, host_ctxt, 2);
	DECLARE_REG(unsigned long, vcpu_hva, host_ctxt, 3);

	host_vcpu = kern_hyp_va(host_vcpu);
	cpu_reg(host_ctxt, 1) = __pkvm_init_vcpu(handle, host_vcpu, vcpu_hva);
}

static void handle___pkvm_teardown_vm(struct kvm_cpu_context *host_ctxt)
{
	DECLARE_REG(pkvm_handle_t, handle, host_ctxt, 1);

	cpu_reg(host_ctxt, 1) = __pkvm_teardown_vm(handle);
}

typedef void (*hcall_t)(struct kvm_cpu_context *);

#define HANDLE_FUNC(x)	[__KVM_HOST_SMCCC_FUNC_##x] = (hcall_t)handle_##x

static const hcall_t host_hcall[] = {
	/* ___kvm_hyp_init */
	HANDLE_FUNC(__kvm_get_mdcr_el2),
	HANDLE_FUNC(__pkvm_init),
	HANDLE_FUNC(__pkvm_create_private_mapping),
	HANDLE_FUNC(__pkvm_cpu_set_vector),
	HANDLE_FUNC(__kvm_enable_ssbs),
	HANDLE_FUNC(__vgic_v3_init_lrs),
	HANDLE_FUNC(__vgic_v3_get_gic_config),
	HANDLE_FUNC(__pkvm_prot_finalize),

	HANDLE_FUNC(__pkvm_host_share_hyp),
	HANDLE_FUNC(__pkvm_host_unshare_hyp),
	HANDLE_FUNC(__kvm_adjust_pc),
	HANDLE_FUNC(__kvm_vcpu_run),
	HANDLE_FUNC(__kvm_flush_vm_context),
	HANDLE_FUNC(__kvm_tlb_flush_vmid_ipa),
	HANDLE_FUNC(__kvm_tlb_flush_vmid_ipa_nsh),
	HANDLE_FUNC(__kvm_tlb_flush_vmid),
	HANDLE_FUNC(__kvm_tlb_flush_vmid_range),
	HANDLE_FUNC(__kvm_flush_cpu_context),
	HANDLE_FUNC(__kvm_timer_set_cntvoff),
	HANDLE_FUNC(__vgic_v3_save_vmcr_aprs),
	HANDLE_FUNC(__vgic_v3_restore_vmcr_aprs),
	HANDLE_FUNC(__pkvm_vcpu_init_traps),
	HANDLE_FUNC(__pkvm_init_vm),
	HANDLE_FUNC(__pkvm_init_vcpu),
	HANDLE_FUNC(__pkvm_teardown_vm),
};

static void handle_host_hcall(struct kvm_cpu_context *host_ctxt)
{
	DECLARE_REG(unsigned long, id, host_ctxt, 0);
	unsigned long hcall_min = 0;
	hcall_t hfn;

	/*
	 * If pKVM has been initialised then reject any calls to the
	 * early "privileged" hypercalls. Note that we cannot reject
	 * calls to __pkvm_prot_finalize for two reasons: (1) The static
	 * key used to determine initialisation must be toggled prior to
	 * finalisation and (2) finalisation is performed on a per-CPU
	 * basis. This is all fine, however, since __pkvm_prot_finalize
	 * returns -EPERM after the first call for a given CPU.
	 */
	if (static_branch_unlikely(&kvm_protected_mode_initialized))
		hcall_min = __KVM_HOST_SMCCC_FUNC___pkvm_prot_finalize;

	id &= ~ARM_SMCCC_CALL_HINTS;
	id -= KVM_HOST_SMCCC_ID(0);

	if (unlikely(id < hcall_min || id >= ARRAY_SIZE(host_hcall)))
		goto inval;

	hfn = host_hcall[id];
	if (unlikely(!hfn))
		goto inval;

	cpu_reg(host_ctxt, 0) = SMCCC_RET_SUCCESS;
	hfn(host_ctxt);

	return;
inval:
	cpu_reg(host_ctxt, 0) = SMCCC_RET_NOT_SUPPORTED;
}

static void default_host_smc_handler(struct kvm_cpu_context *host_ctxt)
{
	__kvm_hyp_host_forward_smc(host_ctxt);
}

static void handle_host_smc(struct kvm_cpu_context *host_ctxt)
{
	DECLARE_REG(u64, func_id, host_ctxt, 0);
	bool handled;

	func_id &= ~ARM_SMCCC_CALL_HINTS;

	handled = kvm_host_psci_handler(host_ctxt, func_id);
	if (!handled)
		handled = kvm_host_ffa_handler(host_ctxt, func_id);
	if (!handled)
		default_host_smc_handler(host_ctxt);

	/* SMC was trapped, move ELR past the current PC. */
	kvm_skip_host_instr();
}

void handle_trap(struct kvm_cpu_context *host_ctxt)
{
	u64 esr = read_sysreg_el2(SYS_ESR);

	switch (ESR_ELx_EC(esr)) {
	case ESR_ELx_EC_HVC64:
		handle_host_hcall(host_ctxt);
		break;
	case ESR_ELx_EC_SMC64:
		handle_host_smc(host_ctxt);
		break;
	case ESR_ELx_EC_SVE:
		cpacr_clear_set(0, CPACR_ELx_ZEN);
		isb();
		sve_cond_update_zcr_vq(ZCR_ELx_LEN_MASK, SYS_ZCR_EL2);
		break;
	case ESR_ELx_EC_IABT_LOW:
	case ESR_ELx_EC_DABT_LOW:
		handle_host_mem_abort(host_ctxt);
		break;
	default:
		BUG();
	}
}