summaryrefslogtreecommitdiff
path: root/arch/arm64/kvm/hyp/switch.c
blob: 925086b46136f3cefd629ce28a9995a21bf38b71 (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
616
617
618
619
620
621
622
623
624
625
626
627
628
629
630
631
632
633
634
635
636
637
638
639
640
641
642
643
644
645
646
647
648
649
650
651
652
653
654
655
656
657
658
659
660
661
662
663
664
665
666
667
668
669
670
671
672
673
674
675
676
677
678
679
680
681
682
683
684
685
686
687
688
689
690
691
692
693
694
695
696
697
698
699
700
701
702
703
704
705
706
707
708
709
710
711
712
713
714
715
716
717
718
719
720
721
722
723
724
725
726
727
728
729
730
731
732
733
734
735
736
737
738
739
740
741
742
743
744
745
746
747
748
749
750
751
752
753
754
755
756
757
758
759
760
761
762
763
764
765
766
767
768
769
770
771
772
773
774
775
776
777
778
779
780
781
782
783
784
785
786
787
788
789
790
791
792
793
794
795
796
797
798
799
800
801
802
803
804
805
806
807
808
809
810
811
812
813
814
815
816
817
818
819
820
821
822
823
824
825
826
827
828
829
830
831
832
833
834
835
836
837
838
839
840
841
842
843
844
845
846
847
848
849
850
851
852
853
854
855
856
857
858
859
860
861
862
863
864
// SPDX-License-Identifier: GPL-2.0-only
/*
 * Copyright (C) 2015 - ARM Ltd
 * Author: Marc Zyngier <marc.zyngier@arm.com>
 */

#include <linux/arm-smccc.h>
#include <linux/kvm_host.h>
#include <linux/types.h>
#include <linux/jump_label.h>
#include <uapi/linux/psci.h>

#include <kvm/arm_psci.h>

#include <asm/barrier.h>
#include <asm/cpufeature.h>
#include <asm/kprobes.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 <asm/fpsimd.h>
#include <asm/debug-monitors.h>
#include <asm/processor.h>
#include <asm/thread_info.h>

/* Check whether the FP regs were dirtied while in the host-side run loop: */
static bool __hyp_text update_fp_enabled(struct kvm_vcpu *vcpu)
{
	/*
	 * When the system doesn't support FP/SIMD, we cannot rely on
	 * the _TIF_FOREIGN_FPSTATE flag. However, we always inject an
	 * abort on the very first access to FP and thus we should never
	 * see KVM_ARM64_FP_ENABLED. For added safety, make sure we always
	 * trap the accesses.
	 */
	if (!system_supports_fpsimd() ||
	    vcpu->arch.host_thread_info->flags & _TIF_FOREIGN_FPSTATE)
		vcpu->arch.flags &= ~(KVM_ARM64_FP_ENABLED |
				      KVM_ARM64_FP_HOST);

	return !!(vcpu->arch.flags & KVM_ARM64_FP_ENABLED);
}

/* Save the 32-bit only FPSIMD system register state */
static void __hyp_text __fpsimd_save_fpexc32(struct kvm_vcpu *vcpu)
{
	if (!vcpu_el1_is_32bit(vcpu))
		return;

	vcpu->arch.ctxt.sys_regs[FPEXC32_EL2] = read_sysreg(fpexc32_el2);
}

static void __hyp_text __activate_traps_fpsimd32(struct kvm_vcpu *vcpu)
{
	/*
	 * We are about to set CPTR_EL2.TFP to trap all floating point
	 * register accesses to EL2, however, the ARM ARM clearly states that
	 * traps are only taken to EL2 if the operation would not otherwise
	 * trap to EL1.  Therefore, always make sure that for 32-bit guests,
	 * we set FPEXC.EN to prevent traps to EL1, when setting the TFP bit.
	 * If FP/ASIMD is not implemented, FPEXC is UNDEFINED and any access to
	 * it will cause an exception.
	 */
	if (vcpu_el1_is_32bit(vcpu) && system_supports_fpsimd()) {
		write_sysreg(1 << 30, fpexc32_el2);
		isb();
	}
}

static void __hyp_text __activate_traps_common(struct kvm_vcpu *vcpu)
{
	/* Trap on AArch32 cp15 c15 (impdef sysregs) accesses (EL1 or EL0) */
	write_sysreg(1 << 15, hstr_el2);

	/*
	 * Make sure we trap PMU access from EL0 to EL2. Also sanitize
	 * PMSELR_EL0 to make sure it never contains the cycle
	 * counter, which could make a PMXEVCNTR_EL0 access UNDEF at
	 * EL1 instead of being trapped to EL2.
	 */
	write_sysreg(0, pmselr_el0);
	write_sysreg(ARMV8_PMU_USERENR_MASK, pmuserenr_el0);
	write_sysreg(vcpu->arch.mdcr_el2, mdcr_el2);
}

static void __hyp_text __deactivate_traps_common(void)
{
	write_sysreg(0, hstr_el2);
	write_sysreg(0, pmuserenr_el0);
}

static void activate_traps_vhe(struct kvm_vcpu *vcpu)
{
	u64 val;

	val = read_sysreg(cpacr_el1);
	val |= CPACR_EL1_TTA;
	val &= ~CPACR_EL1_ZEN;
	if (update_fp_enabled(vcpu)) {
		if (vcpu_has_sve(vcpu))
			val |= CPACR_EL1_ZEN;
	} else {
		val &= ~CPACR_EL1_FPEN;
		__activate_traps_fpsimd32(vcpu);
	}

	write_sysreg(val, cpacr_el1);

	write_sysreg(kvm_get_hyp_vector(), vbar_el1);
}
NOKPROBE_SYMBOL(activate_traps_vhe);

static void __hyp_text __activate_traps_nvhe(struct kvm_vcpu *vcpu)
{
	u64 val;

	__activate_traps_common(vcpu);

	val = CPTR_EL2_DEFAULT;
	val |= CPTR_EL2_TTA | CPTR_EL2_TZ;
	if (!update_fp_enabled(vcpu)) {
		val |= CPTR_EL2_TFP;
		__activate_traps_fpsimd32(vcpu);
	}

	write_sysreg(val, cptr_el2);

	if (cpus_have_const_cap(ARM64_WORKAROUND_SPECULATIVE_AT_NVHE)) {
		struct kvm_cpu_context *ctxt = &vcpu->arch.ctxt;

		isb();
		/*
		 * At this stage, and thanks to the above isb(), S2 is
		 * configured and enabled. We can now restore the guest's S1
		 * configuration: SCTLR, and only then TCR.
		 */
		write_sysreg_el1(ctxt->sys_regs[SCTLR_EL1],	SYS_SCTLR);
		isb();
		write_sysreg_el1(ctxt->sys_regs[TCR_EL1],	SYS_TCR);
	}
}

static void __hyp_text __activate_traps(struct kvm_vcpu *vcpu)
{
	u64 hcr = vcpu->arch.hcr_el2;

	if (cpus_have_const_cap(ARM64_WORKAROUND_CAVIUM_TX2_219_TVM))
		hcr |= HCR_TVM;

	write_sysreg(hcr, hcr_el2);

	if (cpus_have_const_cap(ARM64_HAS_RAS_EXTN) && (hcr & HCR_VSE))
		write_sysreg_s(vcpu->arch.vsesr_el2, SYS_VSESR_EL2);

	if (has_vhe())
		activate_traps_vhe(vcpu);
	else
		__activate_traps_nvhe(vcpu);
}

static void deactivate_traps_vhe(void)
{
	extern char vectors[];	/* kernel exception vectors */
	write_sysreg(HCR_HOST_VHE_FLAGS, hcr_el2);

	/*
	 * ARM errata 1165522 and 1530923 require the actual execution of the
	 * above before we can switch to the EL2/EL0 translation regime used by
	 * the host.
	 */
	asm(ALTERNATIVE("nop", "isb", ARM64_WORKAROUND_SPECULATIVE_AT_VHE));

	write_sysreg(CPACR_EL1_DEFAULT, cpacr_el1);
	write_sysreg(vectors, vbar_el1);
}
NOKPROBE_SYMBOL(deactivate_traps_vhe);

static void __hyp_text __deactivate_traps_nvhe(void)
{
	u64 mdcr_el2 = read_sysreg(mdcr_el2);

	if (cpus_have_const_cap(ARM64_WORKAROUND_SPECULATIVE_AT_NVHE)) {
		u64 val;

		/*
		 * Set the TCR and SCTLR registers in the exact opposite
		 * sequence as __activate_traps_nvhe (first prevent walks,
		 * then force the MMU on). A generous sprinkling of isb()
		 * ensure that things happen in this exact order.
		 */
		val = read_sysreg_el1(SYS_TCR);
		write_sysreg_el1(val | TCR_EPD1_MASK | TCR_EPD0_MASK, SYS_TCR);
		isb();
		val = read_sysreg_el1(SYS_SCTLR);
		write_sysreg_el1(val | SCTLR_ELx_M, SYS_SCTLR);
		isb();
	}

	__deactivate_traps_common();

	mdcr_el2 &= MDCR_EL2_HPMN_MASK;
	mdcr_el2 |= MDCR_EL2_E2PB_MASK << MDCR_EL2_E2PB_SHIFT;

	write_sysreg(mdcr_el2, mdcr_el2);
	write_sysreg(HCR_HOST_NVHE_FLAGS, hcr_el2);
	write_sysreg(CPTR_EL2_DEFAULT, cptr_el2);
}

static void __hyp_text __deactivate_traps(struct kvm_vcpu *vcpu)
{
	/*
	 * If we pended a virtual abort, preserve it until it gets
	 * cleared. See D1.14.3 (Virtual Interrupts) for details, but
	 * the crucial bit is "On taking a vSError interrupt,
	 * HCR_EL2.VSE is cleared to 0."
	 */
	if (vcpu->arch.hcr_el2 & HCR_VSE) {
		vcpu->arch.hcr_el2 &= ~HCR_VSE;
		vcpu->arch.hcr_el2 |= read_sysreg(hcr_el2) & HCR_VSE;
	}

	if (has_vhe())
		deactivate_traps_vhe();
	else
		__deactivate_traps_nvhe();
}

void activate_traps_vhe_load(struct kvm_vcpu *vcpu)
{
	__activate_traps_common(vcpu);
}

void deactivate_traps_vhe_put(void)
{
	u64 mdcr_el2 = read_sysreg(mdcr_el2);

	mdcr_el2 &= MDCR_EL2_HPMN_MASK |
		    MDCR_EL2_E2PB_MASK << MDCR_EL2_E2PB_SHIFT |
		    MDCR_EL2_TPMS;

	write_sysreg(mdcr_el2, mdcr_el2);

	__deactivate_traps_common();
}

static void __hyp_text __activate_vm(struct kvm *kvm)
{
	__load_guest_stage2(kvm);
}

static void __hyp_text __deactivate_vm(struct kvm_vcpu *vcpu)
{
	write_sysreg(0, vttbr_el2);
}

/* Save VGICv3 state on non-VHE systems */
static void __hyp_text __hyp_vgic_save_state(struct kvm_vcpu *vcpu)
{
	if (static_branch_unlikely(&kvm_vgic_global_state.gicv3_cpuif)) {
		__vgic_v3_save_state(vcpu);
		__vgic_v3_deactivate_traps(vcpu);
	}
}

/* Restore VGICv3 state on non_VEH systems */
static void __hyp_text __hyp_vgic_restore_state(struct kvm_vcpu *vcpu)
{
	if (static_branch_unlikely(&kvm_vgic_global_state.gicv3_cpuif)) {
		__vgic_v3_activate_traps(vcpu);
		__vgic_v3_restore_state(vcpu);
	}
}

static bool __hyp_text __translate_far_to_hpfar(u64 far, u64 *hpfar)
{
	u64 par, tmp;

	/*
	 * Resolve the IPA the hard way using the guest VA.
	 *
	 * Stage-1 translation already validated the memory access
	 * rights. As such, we can use the EL1 translation regime, and
	 * don't have to distinguish between EL0 and EL1 access.
	 *
	 * We do need to save/restore PAR_EL1 though, as we haven't
	 * saved the guest context yet, and we may return early...
	 */
	par = read_sysreg(par_el1);
	asm volatile("at s1e1r, %0" : : "r" (far));
	isb();

	tmp = read_sysreg(par_el1);
	write_sysreg(par, par_el1);

	if (unlikely(tmp & SYS_PAR_EL1_F))
		return false; /* Translation failed, back to guest */

	/* Convert PAR to HPFAR format */
	*hpfar = PAR_TO_HPFAR(tmp);
	return true;
}

static bool __hyp_text __populate_fault_info(struct kvm_vcpu *vcpu)
{
	u8 ec;
	u64 esr;
	u64 hpfar, far;

	esr = vcpu->arch.fault.esr_el2;
	ec = ESR_ELx_EC(esr);

	if (ec != ESR_ELx_EC_DABT_LOW && ec != ESR_ELx_EC_IABT_LOW)
		return true;

	far = read_sysreg_el2(SYS_FAR);

	/*
	 * The HPFAR can be invalid if the stage 2 fault did not
	 * happen during a stage 1 page table walk (the ESR_EL2.S1PTW
	 * bit is clear) and one of the two following cases are true:
	 *   1. The fault was due to a permission fault
	 *   2. The processor carries errata 834220
	 *
	 * Therefore, for all non S1PTW faults where we either have a
	 * permission fault or the errata workaround is enabled, we
	 * resolve the IPA using the AT instruction.
	 */
	if (!(esr & ESR_ELx_S1PTW) &&
	    (cpus_have_const_cap(ARM64_WORKAROUND_834220) ||
	     (esr & ESR_ELx_FSC_TYPE) == FSC_PERM)) {
		if (!__translate_far_to_hpfar(far, &hpfar))
			return false;
	} else {
		hpfar = read_sysreg(hpfar_el2);
	}

	vcpu->arch.fault.far_el2 = far;
	vcpu->arch.fault.hpfar_el2 = hpfar;
	return true;
}

/* Check for an FPSIMD/SVE trap and handle as appropriate */
static bool __hyp_text __hyp_handle_fpsimd(struct kvm_vcpu *vcpu)
{
	bool vhe, sve_guest, sve_host;
	u8 hsr_ec;

	if (!system_supports_fpsimd())
		return false;

	if (system_supports_sve()) {
		sve_guest = vcpu_has_sve(vcpu);
		sve_host = vcpu->arch.flags & KVM_ARM64_HOST_SVE_IN_USE;
		vhe = true;
	} else {
		sve_guest = false;
		sve_host = false;
		vhe = has_vhe();
	}

	hsr_ec = kvm_vcpu_trap_get_class(vcpu);
	if (hsr_ec != ESR_ELx_EC_FP_ASIMD &&
	    hsr_ec != ESR_ELx_EC_SVE)
		return false;

	/* Don't handle SVE traps for non-SVE vcpus here: */
	if (!sve_guest)
		if (hsr_ec != ESR_ELx_EC_FP_ASIMD)
			return false;

	/* Valid trap.  Switch the context: */

	if (vhe) {
		u64 reg = read_sysreg(cpacr_el1) | CPACR_EL1_FPEN;

		if (sve_guest)
			reg |= CPACR_EL1_ZEN;

		write_sysreg(reg, cpacr_el1);
	} else {
		write_sysreg(read_sysreg(cptr_el2) & ~(u64)CPTR_EL2_TFP,
			     cptr_el2);
	}

	isb();

	if (vcpu->arch.flags & KVM_ARM64_FP_HOST) {
		/*
		 * In the SVE case, VHE is assumed: it is enforced by
		 * Kconfig and kvm_arch_init().
		 */
		if (sve_host) {
			struct thread_struct *thread = container_of(
				vcpu->arch.host_fpsimd_state,
				struct thread_struct, uw.fpsimd_state);

			sve_save_state(sve_pffr(thread),
				       &vcpu->arch.host_fpsimd_state->fpsr);
		} else {
			__fpsimd_save_state(vcpu->arch.host_fpsimd_state);
		}

		vcpu->arch.flags &= ~KVM_ARM64_FP_HOST;
	}

	if (sve_guest) {
		sve_load_state(vcpu_sve_pffr(vcpu),
			       &vcpu->arch.ctxt.gp_regs.fp_regs.fpsr,
			       sve_vq_from_vl(vcpu->arch.sve_max_vl) - 1);
		write_sysreg_s(vcpu->arch.ctxt.sys_regs[ZCR_EL1], SYS_ZCR_EL12);
	} else {
		__fpsimd_restore_state(&vcpu->arch.ctxt.gp_regs.fp_regs);
	}

	/* Skip restoring fpexc32 for AArch64 guests */
	if (!(read_sysreg(hcr_el2) & HCR_RW))
		write_sysreg(vcpu->arch.ctxt.sys_regs[FPEXC32_EL2],
			     fpexc32_el2);

	vcpu->arch.flags |= KVM_ARM64_FP_ENABLED;

	return true;
}

static bool __hyp_text handle_tx2_tvm(struct kvm_vcpu *vcpu)
{
	u32 sysreg = esr_sys64_to_sysreg(kvm_vcpu_get_hsr(vcpu));
	int rt = kvm_vcpu_sys_get_rt(vcpu);
	u64 val = vcpu_get_reg(vcpu, rt);

	/*
	 * The normal sysreg handling code expects to see the traps,
	 * let's not do anything here.
	 */
	if (vcpu->arch.hcr_el2 & HCR_TVM)
		return false;

	switch (sysreg) {
	case SYS_SCTLR_EL1:
		write_sysreg_el1(val, SYS_SCTLR);
		break;
	case SYS_TTBR0_EL1:
		write_sysreg_el1(val, SYS_TTBR0);
		break;
	case SYS_TTBR1_EL1:
		write_sysreg_el1(val, SYS_TTBR1);
		break;
	case SYS_TCR_EL1:
		write_sysreg_el1(val, SYS_TCR);
		break;
	case SYS_ESR_EL1:
		write_sysreg_el1(val, SYS_ESR);
		break;
	case SYS_FAR_EL1:
		write_sysreg_el1(val, SYS_FAR);
		break;
	case SYS_AFSR0_EL1:
		write_sysreg_el1(val, SYS_AFSR0);
		break;
	case SYS_AFSR1_EL1:
		write_sysreg_el1(val, SYS_AFSR1);
		break;
	case SYS_MAIR_EL1:
		write_sysreg_el1(val, SYS_MAIR);
		break;
	case SYS_AMAIR_EL1:
		write_sysreg_el1(val, SYS_AMAIR);
		break;
	case SYS_CONTEXTIDR_EL1:
		write_sysreg_el1(val, SYS_CONTEXTIDR);
		break;
	default:
		return false;
	}

	__kvm_skip_instr(vcpu);
	return true;
}

/*
 * Return true when we were able to fixup the guest exit and should return to
 * the guest, false when we should restore the host state and return to the
 * main run loop.
 */
static bool __hyp_text fixup_guest_exit(struct kvm_vcpu *vcpu, u64 *exit_code)
{
	if (ARM_EXCEPTION_CODE(*exit_code) != ARM_EXCEPTION_IRQ)
		vcpu->arch.fault.esr_el2 = read_sysreg_el2(SYS_ESR);

	/*
	 * We're using the raw exception code in order to only process
	 * the trap if no SError is pending. We will come back to the
	 * same PC once the SError has been injected, and replay the
	 * trapping instruction.
	 */
	if (*exit_code != ARM_EXCEPTION_TRAP)
		goto exit;

	if (cpus_have_const_cap(ARM64_WORKAROUND_CAVIUM_TX2_219_TVM) &&
	    kvm_vcpu_trap_get_class(vcpu) == ESR_ELx_EC_SYS64 &&
	    handle_tx2_tvm(vcpu))
		return true;

	/*
	 * We trap the first access to the FP/SIMD to save the host context
	 * and restore the guest context lazily.
	 * If FP/SIMD is not implemented, handle the trap and inject an
	 * undefined instruction exception to the guest.
	 * Similarly for trapped SVE accesses.
	 */
	if (__hyp_handle_fpsimd(vcpu))
		return true;

	if (!__populate_fault_info(vcpu))
		return true;

	if (static_branch_unlikely(&vgic_v2_cpuif_trap)) {
		bool valid;

		valid = kvm_vcpu_trap_get_class(vcpu) == ESR_ELx_EC_DABT_LOW &&
			kvm_vcpu_trap_get_fault_type(vcpu) == FSC_FAULT &&
			kvm_vcpu_dabt_isvalid(vcpu) &&
			!kvm_vcpu_dabt_isextabt(vcpu) &&
			!kvm_vcpu_dabt_iss1tw(vcpu);

		if (valid) {
			int ret = __vgic_v2_perform_cpuif_access(vcpu);

			if (ret == 1)
				return true;

			/* Promote an illegal access to an SError.*/
			if (ret == -1)
				*exit_code = ARM_EXCEPTION_EL1_SERROR;

			goto exit;
		}
	}

	if (static_branch_unlikely(&vgic_v3_cpuif_trap) &&
	    (kvm_vcpu_trap_get_class(vcpu) == ESR_ELx_EC_SYS64 ||
	     kvm_vcpu_trap_get_class(vcpu) == ESR_ELx_EC_CP15_32)) {
		int ret = __vgic_v3_perform_cpuif_access(vcpu);

		if (ret == 1)
			return true;
	}

exit:
	/* Return to the host kernel and handle the exit */
	return false;
}

static inline bool __hyp_text __needs_ssbd_off(struct kvm_vcpu *vcpu)
{
	if (!cpus_have_const_cap(ARM64_SSBD))
		return false;

	return !(vcpu->arch.workaround_flags & VCPU_WORKAROUND_2_FLAG);
}

static void __hyp_text __set_guest_arch_workaround_state(struct kvm_vcpu *vcpu)
{
#ifdef CONFIG_ARM64_SSBD
	/*
	 * The host runs with the workaround always present. If the
	 * guest wants it disabled, so be it...
	 */
	if (__needs_ssbd_off(vcpu) &&
	    __hyp_this_cpu_read(arm64_ssbd_callback_required))
		arm_smccc_1_1_smc(ARM_SMCCC_ARCH_WORKAROUND_2, 0, NULL);
#endif
}

static void __hyp_text __set_host_arch_workaround_state(struct kvm_vcpu *vcpu)
{
#ifdef CONFIG_ARM64_SSBD
	/*
	 * If the guest has disabled the workaround, bring it back on.
	 */
	if (__needs_ssbd_off(vcpu) &&
	    __hyp_this_cpu_read(arm64_ssbd_callback_required))
		arm_smccc_1_1_smc(ARM_SMCCC_ARCH_WORKAROUND_2, 1, NULL);
#endif
}

/**
 * Disable host events, enable guest events
 */
static bool __hyp_text __pmu_switch_to_guest(struct kvm_cpu_context *host_ctxt)
{
	struct kvm_host_data *host;
	struct kvm_pmu_events *pmu;

	host = container_of(host_ctxt, struct kvm_host_data, host_ctxt);
	pmu = &host->pmu_events;

	if (pmu->events_host)
		write_sysreg(pmu->events_host, pmcntenclr_el0);

	if (pmu->events_guest)
		write_sysreg(pmu->events_guest, pmcntenset_el0);

	return (pmu->events_host || pmu->events_guest);
}

/**
 * Disable guest events, enable host events
 */
static void __hyp_text __pmu_switch_to_host(struct kvm_cpu_context *host_ctxt)
{
	struct kvm_host_data *host;
	struct kvm_pmu_events *pmu;

	host = container_of(host_ctxt, struct kvm_host_data, host_ctxt);
	pmu = &host->pmu_events;

	if (pmu->events_guest)
		write_sysreg(pmu->events_guest, pmcntenclr_el0);

	if (pmu->events_host)
		write_sysreg(pmu->events_host, pmcntenset_el0);
}

/* Switch to the guest for VHE systems running in EL2 */
static int __kvm_vcpu_run_vhe(struct kvm_vcpu *vcpu)
{
	struct kvm_cpu_context *host_ctxt;
	struct kvm_cpu_context *guest_ctxt;
	u64 exit_code;

	host_ctxt = vcpu->arch.host_cpu_context;
	host_ctxt->__hyp_running_vcpu = vcpu;
	guest_ctxt = &vcpu->arch.ctxt;

	sysreg_save_host_state_vhe(host_ctxt);

	/*
	 * ARM erratum 1165522 requires us to configure both stage 1 and
	 * stage 2 translation for the guest context before we clear
	 * HCR_EL2.TGE.
	 *
	 * We have already configured the guest's stage 1 translation in
	 * kvm_vcpu_load_sysregs above.  We must now call __activate_vm
	 * before __activate_traps, because __activate_vm configures
	 * stage 2 translation, and __activate_traps clear HCR_EL2.TGE
	 * (among other things).
	 */
	__activate_vm(vcpu->kvm);
	__activate_traps(vcpu);

	sysreg_restore_guest_state_vhe(guest_ctxt);
	__debug_switch_to_guest(vcpu);

	__set_guest_arch_workaround_state(vcpu);

	do {
		/* Jump in the fire! */
		exit_code = __guest_enter(vcpu, host_ctxt);

		/* And we're baaack! */
	} while (fixup_guest_exit(vcpu, &exit_code));

	__set_host_arch_workaround_state(vcpu);

	sysreg_save_guest_state_vhe(guest_ctxt);

	__deactivate_traps(vcpu);

	sysreg_restore_host_state_vhe(host_ctxt);

	if (vcpu->arch.flags & KVM_ARM64_FP_ENABLED)
		__fpsimd_save_fpexc32(vcpu);

	__debug_switch_to_host(vcpu);

	return exit_code;
}
NOKPROBE_SYMBOL(__kvm_vcpu_run_vhe);

int kvm_vcpu_run_vhe(struct kvm_vcpu *vcpu)
{
	int ret;

	local_daif_mask();

	/*
	 * Having IRQs masked via PMR when entering the guest means the GIC
	 * will not signal the CPU of interrupts of lower priority, and the
	 * only way to get out will be via guest exceptions.
	 * Naturally, we want to avoid this.
	 *
	 * local_daif_mask() already sets GIC_PRIO_PSR_I_SET, we just need a
	 * dsb to ensure the redistributor is forwards EL2 IRQs to the CPU.
	 */
	pmr_sync();

	ret = __kvm_vcpu_run_vhe(vcpu);

	/*
	 * local_daif_restore() takes care to properly restore PSTATE.DAIF
	 * and the GIC PMR if the host is using IRQ priorities.
	 */
	local_daif_restore(DAIF_PROCCTX_NOIRQ);

	/*
	 * When we exit from the guest we change a number of CPU configuration
	 * parameters, such as traps.  Make sure these changes take effect
	 * before running the host or additional guests.
	 */
	isb();

	return ret;
}

/* Switch to the guest for legacy non-VHE systems */
int __hyp_text __kvm_vcpu_run_nvhe(struct kvm_vcpu *vcpu)
{
	struct kvm_cpu_context *host_ctxt;
	struct kvm_cpu_context *guest_ctxt;
	bool pmu_switch_needed;
	u64 exit_code;

	/*
	 * Having IRQs masked via PMR when entering the guest means the GIC
	 * will not signal the CPU of interrupts of lower priority, and the
	 * only way to get out will be via guest exceptions.
	 * Naturally, we want to avoid this.
	 */
	if (system_uses_irq_prio_masking()) {
		gic_write_pmr(GIC_PRIO_IRQON | GIC_PRIO_PSR_I_SET);
		pmr_sync();
	}

	vcpu = kern_hyp_va(vcpu);

	host_ctxt = kern_hyp_va(vcpu->arch.host_cpu_context);
	host_ctxt->__hyp_running_vcpu = vcpu;
	guest_ctxt = &vcpu->arch.ctxt;

	pmu_switch_needed = __pmu_switch_to_guest(host_ctxt);

	__sysreg_save_state_nvhe(host_ctxt);

	/*
	 * We must restore the 32-bit state before the sysregs, thanks
	 * to erratum #852523 (Cortex-A57) or #853709 (Cortex-A72).
	 *
	 * Also, and in order to be able to deal with erratum #1319537 (A57)
	 * and #1319367 (A72), we must ensure that all VM-related sysreg are
	 * restored before we enable S2 translation.
	 */
	__sysreg32_restore_state(vcpu);
	__sysreg_restore_state_nvhe(guest_ctxt);

	__activate_vm(kern_hyp_va(vcpu->kvm));
	__activate_traps(vcpu);

	__hyp_vgic_restore_state(vcpu);
	__timer_enable_traps(vcpu);

	__debug_switch_to_guest(vcpu);

	__set_guest_arch_workaround_state(vcpu);

	do {
		/* Jump in the fire! */
		exit_code = __guest_enter(vcpu, host_ctxt);

		/* And we're baaack! */
	} while (fixup_guest_exit(vcpu, &exit_code));

	__set_host_arch_workaround_state(vcpu);

	__sysreg_save_state_nvhe(guest_ctxt);
	__sysreg32_save_state(vcpu);
	__timer_disable_traps(vcpu);
	__hyp_vgic_save_state(vcpu);

	__deactivate_traps(vcpu);
	__deactivate_vm(vcpu);

	__sysreg_restore_state_nvhe(host_ctxt);

	if (vcpu->arch.flags & KVM_ARM64_FP_ENABLED)
		__fpsimd_save_fpexc32(vcpu);

	/*
	 * This must come after restoring the host sysregs, since a non-VHE
	 * system may enable SPE here and make use of the TTBRs.
	 */
	__debug_switch_to_host(vcpu);

	if (pmu_switch_needed)
		__pmu_switch_to_host(host_ctxt);

	/* Returning to host will clear PSR.I, remask PMR if needed */
	if (system_uses_irq_prio_masking())
		gic_write_pmr(GIC_PRIO_IRQOFF);

	return exit_code;
}

static const char __hyp_panic_string[] = "HYP panic:\nPS:%08llx PC:%016llx ESR:%08llx\nFAR:%016llx HPFAR:%016llx PAR:%016llx\nVCPU:%p\n";

static void __hyp_text __hyp_call_panic_nvhe(u64 spsr, u64 elr, u64 par,
					     struct kvm_cpu_context *__host_ctxt)
{
	struct kvm_vcpu *vcpu;
	unsigned long str_va;

	vcpu = __host_ctxt->__hyp_running_vcpu;

	if (read_sysreg(vttbr_el2)) {
		__timer_disable_traps(vcpu);
		__deactivate_traps(vcpu);
		__deactivate_vm(vcpu);
		__sysreg_restore_state_nvhe(__host_ctxt);
	}

	/*
	 * Force the panic string to be loaded from the literal pool,
	 * making sure it is a kernel address and not a PC-relative
	 * reference.
	 */
	asm volatile("ldr %0, =__hyp_panic_string" : "=r" (str_va));

	__hyp_do_panic(str_va,
		       spsr, elr,
		       read_sysreg(esr_el2), read_sysreg_el2(SYS_FAR),
		       read_sysreg(hpfar_el2), par, vcpu);
}

static void __hyp_call_panic_vhe(u64 spsr, u64 elr, u64 par,
				 struct kvm_cpu_context *host_ctxt)
{
	struct kvm_vcpu *vcpu;
	vcpu = host_ctxt->__hyp_running_vcpu;

	__deactivate_traps(vcpu);
	sysreg_restore_host_state_vhe(host_ctxt);

	panic(__hyp_panic_string,
	      spsr,  elr,
	      read_sysreg_el2(SYS_ESR),   read_sysreg_el2(SYS_FAR),
	      read_sysreg(hpfar_el2), par, vcpu);
}
NOKPROBE_SYMBOL(__hyp_call_panic_vhe);

void __hyp_text __noreturn hyp_panic(struct kvm_cpu_context *host_ctxt)
{
	u64 spsr = read_sysreg_el2(SYS_SPSR);
	u64 elr = read_sysreg_el2(SYS_ELR);
	u64 par = read_sysreg(par_el1);

	if (!has_vhe())
		__hyp_call_panic_nvhe(spsr, elr, par, host_ctxt);
	else
		__hyp_call_panic_vhe(spsr, elr, par, host_ctxt);

	unreachable();
}