summaryrefslogtreecommitdiffstats
path: root/arch/arm64/kvm/handle_exit.c
blob: 617ae6dea5d5bcf01c8c72cec5f16c684151905c (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
// 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/handle_exit.c:
 * Copyright (C) 2012 - Virtual Open Systems and Columbia University
 * Author: Christoffer Dall <c.dall@virtualopensystems.com>
 */

#include <linux/kvm.h>
#include <linux/kvm_host.h>

#include <asm/esr.h>
#include <asm/exception.h>
#include <asm/kvm_asm.h>
#include <asm/kvm_emulate.h>
#include <asm/kvm_mmu.h>
#include <asm/kvm_nested.h>
#include <asm/debug-monitors.h>
#include <asm/stacktrace/nvhe.h>
#include <asm/traps.h>

#include <kvm/arm_hypercalls.h>

#define CREATE_TRACE_POINTS
#include "trace_handle_exit.h"

typedef int (*exit_handle_fn)(struct kvm_vcpu *);

static void kvm_handle_guest_serror(struct kvm_vcpu *vcpu, u64 esr)
{
	if (!arm64_is_ras_serror(esr) || arm64_is_fatal_ras_serror(NULL, esr))
		kvm_inject_vabt(vcpu);
}

static int handle_hvc(struct kvm_vcpu *vcpu)
{
	trace_kvm_hvc_arm64(*vcpu_pc(vcpu), vcpu_get_reg(vcpu, 0),
			    kvm_vcpu_hvc_get_imm(vcpu));
	vcpu->stat.hvc_exit_stat++;

	/* Forward hvc instructions to the virtual EL2 if the guest has EL2. */
	if (vcpu_has_nv(vcpu)) {
		if (vcpu_read_sys_reg(vcpu, HCR_EL2) & HCR_HCD)
			kvm_inject_undefined(vcpu);
		else
			kvm_inject_nested_sync(vcpu, kvm_vcpu_get_esr(vcpu));

		return 1;
	}

	return kvm_smccc_call_handler(vcpu);
}

static int handle_smc(struct kvm_vcpu *vcpu)
{
	/*
	 * "If an SMC instruction executed at Non-secure EL1 is
	 * trapped to EL2 because HCR_EL2.TSC is 1, the exception is a
	 * Trap exception, not a Secure Monitor Call exception [...]"
	 *
	 * We need to advance the PC after the trap, as it would
	 * otherwise return to the same address. Furthermore, pre-incrementing
	 * the PC before potentially exiting to userspace maintains the same
	 * abstraction for both SMCs and HVCs.
	 */
	kvm_incr_pc(vcpu);

	/*
	 * SMCs with a nonzero immediate are reserved according to DEN0028E 2.9
	 * "SMC and HVC immediate value".
	 */
	if (kvm_vcpu_hvc_get_imm(vcpu)) {
		vcpu_set_reg(vcpu, 0, ~0UL);
		return 1;
	}

	/*
	 * If imm is zero then it is likely an SMCCC call.
	 *
	 * Note that on ARMv8.3, even if EL3 is not implemented, SMC executed
	 * at Non-secure EL1 is trapped to EL2 if HCR_EL2.TSC==1, rather than
	 * being treated as UNDEFINED.
	 */
	return kvm_smccc_call_handler(vcpu);
}

/*
 * Guest access to FP/ASIMD registers are routed to this handler only
 * when the system doesn't support FP/ASIMD.
 */
static int handle_no_fpsimd(struct kvm_vcpu *vcpu)
{
	kvm_inject_undefined(vcpu);
	return 1;
}

/**
 * kvm_handle_wfx - handle a wait-for-interrupts or wait-for-event
 *		    instruction executed by a guest
 *
 * @vcpu:	the vcpu pointer
 *
 * WFE[T]: Yield the CPU and come back to this vcpu when the scheduler
 * decides to.
 * WFI: Simply call kvm_vcpu_halt(), which will halt execution of
 * world-switches and schedule other host processes until there is an
 * incoming IRQ or FIQ to the VM.
 * WFIT: Same as WFI, with a timed wakeup implemented as a background timer
 *
 * WF{I,E}T can immediately return if the deadline has already expired.
 */
static int kvm_handle_wfx(struct kvm_vcpu *vcpu)
{
	u64 esr = kvm_vcpu_get_esr(vcpu);

	if (esr & ESR_ELx_WFx_ISS_WFE) {
		trace_kvm_wfx_arm64(*vcpu_pc(vcpu), true);
		vcpu->stat.wfe_exit_stat++;
	} else {
		trace_kvm_wfx_arm64(*vcpu_pc(vcpu), false);
		vcpu->stat.wfi_exit_stat++;
	}

	if (esr & ESR_ELx_WFx_ISS_WFxT) {
		if (esr & ESR_ELx_WFx_ISS_RV) {
			u64 val, now;

			now = kvm_arm_timer_get_reg(vcpu, KVM_REG_ARM_TIMER_CNT);
			val = vcpu_get_reg(vcpu, kvm_vcpu_sys_get_rt(vcpu));

			if (now >= val)
				goto out;
		} else {
			/* Treat WFxT as WFx if RN is invalid */
			esr &= ~ESR_ELx_WFx_ISS_WFxT;
		}
	}

	if (esr & ESR_ELx_WFx_ISS_WFE) {
		kvm_vcpu_on_spin(vcpu, vcpu_mode_priv(vcpu));
	} else {
		if (esr & ESR_ELx_WFx_ISS_WFxT)
			vcpu_set_flag(vcpu, IN_WFIT);

		kvm_vcpu_wfi(vcpu);
	}
out:
	kvm_incr_pc(vcpu);

	return 1;
}

/**
 * kvm_handle_guest_debug - handle a debug exception instruction
 *
 * @vcpu:	the vcpu pointer
 *
 * We route all debug exceptions through the same handler. If both the
 * guest and host are using the same debug facilities it will be up to
 * userspace to re-inject the correct exception for guest delivery.
 *
 * @return: 0 (while setting vcpu->run->exit_reason)
 */
static int kvm_handle_guest_debug(struct kvm_vcpu *vcpu)
{
	struct kvm_run *run = vcpu->run;
	u64 esr = kvm_vcpu_get_esr(vcpu);

	run->exit_reason = KVM_EXIT_DEBUG;
	run->debug.arch.hsr = lower_32_bits(esr);
	run->debug.arch.hsr_high = upper_32_bits(esr);
	run->flags = KVM_DEBUG_ARCH_HSR_HIGH_VALID;

	switch (ESR_ELx_EC(esr)) {
	case ESR_ELx_EC_WATCHPT_LOW:
		run->debug.arch.far = vcpu->arch.fault.far_el2;
		break;
	case ESR_ELx_EC_SOFTSTP_LOW:
		vcpu_clear_flag(vcpu, DBG_SS_ACTIVE_PENDING);
		break;
	}

	return 0;
}

static int kvm_handle_unknown_ec(struct kvm_vcpu *vcpu)
{
	u64 esr = kvm_vcpu_get_esr(vcpu);

	kvm_pr_unimpl("Unknown exception class: esr: %#016llx -- %s\n",
		      esr, esr_get_class_string(esr));

	kvm_inject_undefined(vcpu);
	return 1;
}

/*
 * Guest access to SVE registers should be routed to this handler only
 * when the system doesn't support SVE.
 */
static int handle_sve(struct kvm_vcpu *vcpu)
{
	kvm_inject_undefined(vcpu);
	return 1;
}

/*
 * Guest usage of a ptrauth instruction (which the guest EL1 did not turn into
 * a NOP). If we get here, it is that we didn't fixup ptrauth on exit, and all
 * that we can do is give the guest an UNDEF.
 */
static int kvm_handle_ptrauth(struct kvm_vcpu *vcpu)
{
	kvm_inject_undefined(vcpu);
	return 1;
}

static int kvm_handle_eret(struct kvm_vcpu *vcpu)
{
	if (kvm_vcpu_get_esr(vcpu) & ESR_ELx_ERET_ISS_ERET)
		return kvm_handle_ptrauth(vcpu);

	/*
	 * If we got here, two possibilities:
	 *
	 * - the guest is in EL2, and we need to fully emulate ERET
	 *
	 * - the guest is in EL1, and we need to reinject the
         *   exception into the L1 hypervisor.
	 *
	 * If KVM ever traps ERET for its own use, we'll have to
	 * revisit this.
	 */
	if (is_hyp_ctxt(vcpu))
		kvm_emulate_nested_eret(vcpu);
	else
		kvm_inject_nested_sync(vcpu, kvm_vcpu_get_esr(vcpu));

	return 1;
}

static int handle_svc(struct kvm_vcpu *vcpu)
{
	/*
	 * So far, SVC traps only for NV via HFGITR_EL2. A SVC from a
	 * 32bit guest would be caught by vpcu_mode_is_bad_32bit(), so
	 * we should only have to deal with a 64 bit exception.
	 */
	kvm_inject_nested_sync(vcpu, kvm_vcpu_get_esr(vcpu));
	return 1;
}

static exit_handle_fn arm_exit_handlers[] = {
	[0 ... ESR_ELx_EC_MAX]	= kvm_handle_unknown_ec,
	[ESR_ELx_EC_WFx]	= kvm_handle_wfx,
	[ESR_ELx_EC_CP15_32]	= kvm_handle_cp15_32,
	[ESR_ELx_EC_CP15_64]	= kvm_handle_cp15_64,
	[ESR_ELx_EC_CP14_MR]	= kvm_handle_cp14_32,
	[ESR_ELx_EC_CP14_LS]	= kvm_handle_cp14_load_store,
	[ESR_ELx_EC_CP10_ID]	= kvm_handle_cp10_id,
	[ESR_ELx_EC_CP14_64]	= kvm_handle_cp14_64,
	[ESR_ELx_EC_HVC32]	= handle_hvc,
	[ESR_ELx_EC_SMC32]	= handle_smc,
	[ESR_ELx_EC_HVC64]	= handle_hvc,
	[ESR_ELx_EC_SMC64]	= handle_smc,
	[ESR_ELx_EC_SVC64]	= handle_svc,
	[ESR_ELx_EC_SYS64]	= kvm_handle_sys_reg,
	[ESR_ELx_EC_SVE]	= handle_sve,
	[ESR_ELx_EC_ERET]	= kvm_handle_eret,
	[ESR_ELx_EC_IABT_LOW]	= kvm_handle_guest_abort,
	[ESR_ELx_EC_DABT_LOW]	= kvm_handle_guest_abort,
	[ESR_ELx_EC_SOFTSTP_LOW]= kvm_handle_guest_debug,
	[ESR_ELx_EC_WATCHPT_LOW]= kvm_handle_guest_debug,
	[ESR_ELx_EC_BREAKPT_LOW]= kvm_handle_guest_debug,
	[ESR_ELx_EC_BKPT32]	= kvm_handle_guest_debug,
	[ESR_ELx_EC_BRK64]	= kvm_handle_guest_debug,
	[ESR_ELx_EC_FP_ASIMD]	= handle_no_fpsimd,
	[ESR_ELx_EC_PAC]	= kvm_handle_ptrauth,
};

static exit_handle_fn kvm_get_exit_handler(struct kvm_vcpu *vcpu)
{
	u64 esr = kvm_vcpu_get_esr(vcpu);
	u8 esr_ec = ESR_ELx_EC(esr);

	return arm_exit_handlers[esr_ec];
}

/*
 * We may be single-stepping an emulated instruction. If the emulation
 * has been completed in the kernel, we can return to userspace with a
 * KVM_EXIT_DEBUG, otherwise userspace needs to complete its
 * emulation first.
 */
static int handle_trap_exceptions(struct kvm_vcpu *vcpu)
{
	int handled;

	/*
	 * See ARM ARM B1.14.1: "Hyp traps on instructions
	 * that fail their condition code check"
	 */
	if (!kvm_condition_valid(vcpu)) {
		kvm_incr_pc(vcpu);
		handled = 1;
	} else {
		exit_handle_fn exit_handler;

		exit_handler = kvm_get_exit_handler(vcpu);
		handled = exit_handler(vcpu);
	}

	return handled;
}

/*
 * Return > 0 to return to guest, < 0 on error, 0 (and set exit_reason) on
 * proper exit to userspace.
 */
int handle_exit(struct kvm_vcpu *vcpu, int exception_index)
{
	struct kvm_run *run = vcpu->run;

	if (ARM_SERROR_PENDING(exception_index)) {
		/*
		 * The SError is handled by handle_exit_early(). If the guest
		 * survives it will re-execute the original instruction.
		 */
		return 1;
	}

	exception_index = ARM_EXCEPTION_CODE(exception_index);

	switch (exception_index) {
	case ARM_EXCEPTION_IRQ:
		return 1;
	case ARM_EXCEPTION_EL1_SERROR:
		return 1;
	case ARM_EXCEPTION_TRAP:
		return handle_trap_exceptions(vcpu);
	case ARM_EXCEPTION_HYP_GONE:
		/*
		 * EL2 has been reset to the hyp-stub. This happens when a guest
		 * is pre-emptied by kvm_reboot()'s shutdown call.
		 */
		run->exit_reason = KVM_EXIT_FAIL_ENTRY;
		return 0;
	case ARM_EXCEPTION_IL:
		/*
		 * We attempted an illegal exception return.  Guest state must
		 * have been corrupted somehow.  Give up.
		 */
		run->exit_reason = KVM_EXIT_FAIL_ENTRY;
		return -EINVAL;
	default:
		kvm_pr_unimpl("Unsupported exception type: %d",
			      exception_index);
		run->exit_reason = KVM_EXIT_INTERNAL_ERROR;
		return 0;
	}
}

/* For exit types that need handling before we can be preempted */
void handle_exit_early(struct kvm_vcpu *vcpu, int exception_index)
{
	if (ARM_SERROR_PENDING(exception_index)) {
		if (this_cpu_has_cap(ARM64_HAS_RAS_EXTN)) {
			u64 disr = kvm_vcpu_get_disr(vcpu);

			kvm_handle_guest_serror(vcpu, disr_to_esr(disr));
		} else {
			kvm_inject_vabt(vcpu);
		}

		return;
	}

	exception_index = ARM_EXCEPTION_CODE(exception_index);

	if (exception_index == ARM_EXCEPTION_EL1_SERROR)
		kvm_handle_guest_serror(vcpu, kvm_vcpu_get_esr(vcpu));
}

void __noreturn __cold nvhe_hyp_panic_handler(u64 esr, u64 spsr,
					      u64 elr_virt, u64 elr_phys,
					      u64 par, uintptr_t vcpu,
					      u64 far, u64 hpfar) {
	u64 elr_in_kimg = __phys_to_kimg(elr_phys);
	u64 hyp_offset = elr_in_kimg - kaslr_offset() - elr_virt;
	u64 mode = spsr & PSR_MODE_MASK;
	u64 panic_addr = elr_virt + hyp_offset;

	if (mode != PSR_MODE_EL2t && mode != PSR_MODE_EL2h) {
		kvm_err("Invalid host exception to nVHE hyp!\n");
	} else if (ESR_ELx_EC(esr) == ESR_ELx_EC_BRK64 &&
		   (esr & ESR_ELx_BRK64_ISS_COMMENT_MASK) == BUG_BRK_IMM) {
		const char *file = NULL;
		unsigned int line = 0;

		/* All hyp bugs, including warnings, are treated as fatal. */
		if (!is_protected_kvm_enabled() ||
		    IS_ENABLED(CONFIG_NVHE_EL2_DEBUG)) {
			struct bug_entry *bug = find_bug(elr_in_kimg);

			if (bug)
				bug_get_file_line(bug, &file, &line);
		}

		if (file)
			kvm_err("nVHE hyp BUG at: %s:%u!\n", file, line);
		else
			kvm_err("nVHE hyp BUG at: [<%016llx>] %pB!\n", panic_addr,
					(void *)(panic_addr + kaslr_offset()));
	} else {
		kvm_err("nVHE hyp panic at: [<%016llx>] %pB!\n", panic_addr,
				(void *)(panic_addr + kaslr_offset()));
	}

	/* Dump the nVHE hypervisor backtrace */
	kvm_nvhe_dump_backtrace(hyp_offset);

	/*
	 * Hyp has panicked and we're going to handle that by panicking the
	 * kernel. The kernel offset will be revealed in the panic so we're
	 * also safe to reveal the hyp offset as a debugging aid for translating
	 * hyp VAs to vmlinux addresses.
	 */
	kvm_err("Hyp Offset: 0x%llx\n", hyp_offset);

	panic("HYP panic:\nPS:%08llx PC:%016llx ESR:%016llx\nFAR:%016llx HPFAR:%016llx PAR:%016llx\nVCPU:%016lx\n",
	      spsr, elr_virt, esr, far, hpfar, par, vcpu);
}