summaryrefslogtreecommitdiffstats
path: root/arch/x86/hyperv/hv_init.c
blob: 783ed339f3415c09bf83830b0bd854d92e5f31dc (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
// SPDX-License-Identifier: GPL-2.0-only
/*
 * X86 specific Hyper-V initialization code.
 *
 * Copyright (C) 2016, Microsoft, Inc.
 *
 * Author : K. Y. Srinivasan <kys@microsoft.com>
 */

#include <linux/efi.h>
#include <linux/types.h>
#include <linux/bitfield.h>
#include <linux/io.h>
#include <asm/apic.h>
#include <asm/desc.h>
#include <asm/sev.h>
#include <asm/ibt.h>
#include <asm/hypervisor.h>
#include <asm/hyperv-tlfs.h>
#include <asm/mshyperv.h>
#include <asm/idtentry.h>
#include <asm/set_memory.h>
#include <linux/kexec.h>
#include <linux/version.h>
#include <linux/vmalloc.h>
#include <linux/mm.h>
#include <linux/hyperv.h>
#include <linux/slab.h>
#include <linux/kernel.h>
#include <linux/cpuhotplug.h>
#include <linux/syscore_ops.h>
#include <clocksource/hyperv_timer.h>
#include <linux/highmem.h>

int hyperv_init_cpuhp;
u64 hv_current_partition_id = ~0ull;
EXPORT_SYMBOL_GPL(hv_current_partition_id);

void *hv_hypercall_pg;
EXPORT_SYMBOL_GPL(hv_hypercall_pg);

union hv_ghcb * __percpu *hv_ghcb_pg;

/* Storage to save the hypercall page temporarily for hibernation */
static void *hv_hypercall_pg_saved;

struct hv_vp_assist_page **hv_vp_assist_page;
EXPORT_SYMBOL_GPL(hv_vp_assist_page);

static int hyperv_init_ghcb(void)
{
	u64 ghcb_gpa;
	void *ghcb_va;
	void **ghcb_base;

	if (!ms_hyperv.paravisor_present || !hv_isolation_type_snp())
		return 0;

	if (!hv_ghcb_pg)
		return -EINVAL;

	/*
	 * GHCB page is allocated by paravisor. The address
	 * returned by MSR_AMD64_SEV_ES_GHCB is above shared
	 * memory boundary and map it here.
	 */
	rdmsrl(MSR_AMD64_SEV_ES_GHCB, ghcb_gpa);

	/* Mask out vTOM bit. ioremap_cache() maps decrypted */
	ghcb_gpa &= ~ms_hyperv.shared_gpa_boundary;
	ghcb_va = (void *)ioremap_cache(ghcb_gpa, HV_HYP_PAGE_SIZE);
	if (!ghcb_va)
		return -ENOMEM;

	ghcb_base = (void **)this_cpu_ptr(hv_ghcb_pg);
	*ghcb_base = ghcb_va;

	return 0;
}

static int hv_cpu_init(unsigned int cpu)
{
	union hv_vp_assist_msr_contents msr = { 0 };
	struct hv_vp_assist_page **hvp;
	int ret;

	ret = hv_common_cpu_init(cpu);
	if (ret)
		return ret;

	if (!hv_vp_assist_page)
		return 0;

	hvp = &hv_vp_assist_page[cpu];
	if (hv_root_partition) {
		/*
		 * For root partition we get the hypervisor provided VP assist
		 * page, instead of allocating a new page.
		 */
		rdmsrl(HV_X64_MSR_VP_ASSIST_PAGE, msr.as_uint64);
		*hvp = memremap(msr.pfn << HV_X64_MSR_VP_ASSIST_PAGE_ADDRESS_SHIFT,
				PAGE_SIZE, MEMREMAP_WB);
	} else {
		/*
		 * The VP assist page is an "overlay" page (see Hyper-V TLFS's
		 * Section 5.2.1 "GPA Overlay Pages"). Here it must be zeroed
		 * out to make sure we always write the EOI MSR in
		 * hv_apic_eoi_write() *after* the EOI optimization is disabled
		 * in hv_cpu_die(), otherwise a CPU may not be stopped in the
		 * case of CPU offlining and the VM will hang.
		 */
		if (!*hvp) {
			*hvp = __vmalloc(PAGE_SIZE, GFP_KERNEL | __GFP_ZERO);

			/*
			 * Hyper-V should never specify a VM that is a Confidential
			 * VM and also running in the root partition. Root partition
			 * is blocked to run in Confidential VM. So only decrypt assist
			 * page in non-root partition here.
			 */
			if (*hvp && !ms_hyperv.paravisor_present && hv_isolation_type_snp()) {
				WARN_ON_ONCE(set_memory_decrypted((unsigned long)(*hvp), 1));
				memset(*hvp, 0, PAGE_SIZE);
			}
		}

		if (*hvp)
			msr.pfn = vmalloc_to_pfn(*hvp);

	}
	if (!WARN_ON(!(*hvp))) {
		msr.enable = 1;
		wrmsrl(HV_X64_MSR_VP_ASSIST_PAGE, msr.as_uint64);
	}

	return hyperv_init_ghcb();
}

static void (*hv_reenlightenment_cb)(void);

static void hv_reenlightenment_notify(struct work_struct *dummy)
{
	struct hv_tsc_emulation_status emu_status;

	rdmsrl(HV_X64_MSR_TSC_EMULATION_STATUS, *(u64 *)&emu_status);

	/* Don't issue the callback if TSC accesses are not emulated */
	if (hv_reenlightenment_cb && emu_status.inprogress)
		hv_reenlightenment_cb();
}
static DECLARE_DELAYED_WORK(hv_reenlightenment_work, hv_reenlightenment_notify);

void hyperv_stop_tsc_emulation(void)
{
	u64 freq;
	struct hv_tsc_emulation_status emu_status;

	rdmsrl(HV_X64_MSR_TSC_EMULATION_STATUS, *(u64 *)&emu_status);
	emu_status.inprogress = 0;
	wrmsrl(HV_X64_MSR_TSC_EMULATION_STATUS, *(u64 *)&emu_status);

	rdmsrl(HV_X64_MSR_TSC_FREQUENCY, freq);
	tsc_khz = div64_u64(freq, 1000);
}
EXPORT_SYMBOL_GPL(hyperv_stop_tsc_emulation);

static inline bool hv_reenlightenment_available(void)
{
	/*
	 * Check for required features and privileges to make TSC frequency
	 * change notifications work.
	 */
	return ms_hyperv.features & HV_ACCESS_FREQUENCY_MSRS &&
		ms_hyperv.misc_features & HV_FEATURE_FREQUENCY_MSRS_AVAILABLE &&
		ms_hyperv.features & HV_ACCESS_REENLIGHTENMENT;
}

DEFINE_IDTENTRY_SYSVEC(sysvec_hyperv_reenlightenment)
{
	apic_eoi();
	inc_irq_stat(irq_hv_reenlightenment_count);
	schedule_delayed_work(&hv_reenlightenment_work, HZ/10);
}

void set_hv_tscchange_cb(void (*cb)(void))
{
	struct hv_reenlightenment_control re_ctrl = {
		.vector = HYPERV_REENLIGHTENMENT_VECTOR,
		.enabled = 1,
	};
	struct hv_tsc_emulation_control emu_ctrl = {.enabled = 1};

	if (!hv_reenlightenment_available()) {
		pr_warn("Hyper-V: reenlightenment support is unavailable\n");
		return;
	}

	if (!hv_vp_index)
		return;

	hv_reenlightenment_cb = cb;

	/* Make sure callback is registered before we write to MSRs */
	wmb();

	re_ctrl.target_vp = hv_vp_index[get_cpu()];

	wrmsrl(HV_X64_MSR_REENLIGHTENMENT_CONTROL, *((u64 *)&re_ctrl));
	wrmsrl(HV_X64_MSR_TSC_EMULATION_CONTROL, *((u64 *)&emu_ctrl));

	put_cpu();
}
EXPORT_SYMBOL_GPL(set_hv_tscchange_cb);

void clear_hv_tscchange_cb(void)
{
	struct hv_reenlightenment_control re_ctrl;

	if (!hv_reenlightenment_available())
		return;

	rdmsrl(HV_X64_MSR_REENLIGHTENMENT_CONTROL, *(u64 *)&re_ctrl);
	re_ctrl.enabled = 0;
	wrmsrl(HV_X64_MSR_REENLIGHTENMENT_CONTROL, *(u64 *)&re_ctrl);

	hv_reenlightenment_cb = NULL;
}
EXPORT_SYMBOL_GPL(clear_hv_tscchange_cb);

static int hv_cpu_die(unsigned int cpu)
{
	struct hv_reenlightenment_control re_ctrl;
	unsigned int new_cpu;
	void **ghcb_va;

	if (hv_ghcb_pg) {
		ghcb_va = (void **)this_cpu_ptr(hv_ghcb_pg);
		if (*ghcb_va)
			iounmap(*ghcb_va);
		*ghcb_va = NULL;
	}

	hv_common_cpu_die(cpu);

	if (hv_vp_assist_page && hv_vp_assist_page[cpu]) {
		union hv_vp_assist_msr_contents msr = { 0 };
		if (hv_root_partition) {
			/*
			 * For root partition the VP assist page is mapped to
			 * hypervisor provided page, and thus we unmap the
			 * page here and nullify it, so that in future we have
			 * correct page address mapped in hv_cpu_init.
			 */
			memunmap(hv_vp_assist_page[cpu]);
			hv_vp_assist_page[cpu] = NULL;
			rdmsrl(HV_X64_MSR_VP_ASSIST_PAGE, msr.as_uint64);
			msr.enable = 0;
		}
		wrmsrl(HV_X64_MSR_VP_ASSIST_PAGE, msr.as_uint64);
	}

	if (hv_reenlightenment_cb == NULL)
		return 0;

	rdmsrl(HV_X64_MSR_REENLIGHTENMENT_CONTROL, *((u64 *)&re_ctrl));
	if (re_ctrl.target_vp == hv_vp_index[cpu]) {
		/*
		 * Reassign reenlightenment notifications to some other online
		 * CPU or just disable the feature if there are no online CPUs
		 * left (happens on hibernation).
		 */
		new_cpu = cpumask_any_but(cpu_online_mask, cpu);

		if (new_cpu < nr_cpu_ids)
			re_ctrl.target_vp = hv_vp_index[new_cpu];
		else
			re_ctrl.enabled = 0;

		wrmsrl(HV_X64_MSR_REENLIGHTENMENT_CONTROL, *((u64 *)&re_ctrl));
	}

	return 0;
}

static int __init hv_pci_init(void)
{
	int gen2vm = efi_enabled(EFI_BOOT);

	/*
	 * For Generation-2 VM, we exit from pci_arch_init() by returning 0.
	 * The purpose is to suppress the harmless warning:
	 * "PCI: Fatal: No config space access function found"
	 */
	if (gen2vm)
		return 0;

	/* For Generation-1 VM, we'll proceed in pci_arch_init().  */
	return 1;
}

static int hv_suspend(void)
{
	union hv_x64_msr_hypercall_contents hypercall_msr;
	int ret;

	if (hv_root_partition)
		return -EPERM;

	/*
	 * Reset the hypercall page as it is going to be invalidated
	 * across hibernation. Setting hv_hypercall_pg to NULL ensures
	 * that any subsequent hypercall operation fails safely instead of
	 * crashing due to an access of an invalid page. The hypercall page
	 * pointer is restored on resume.
	 */
	hv_hypercall_pg_saved = hv_hypercall_pg;
	hv_hypercall_pg = NULL;

	/* Disable the hypercall page in the hypervisor */
	rdmsrl(HV_X64_MSR_HYPERCALL, hypercall_msr.as_uint64);
	hypercall_msr.enable = 0;
	wrmsrl(HV_X64_MSR_HYPERCALL, hypercall_msr.as_uint64);

	ret = hv_cpu_die(0);
	return ret;
}

static void hv_resume(void)
{
	union hv_x64_msr_hypercall_contents hypercall_msr;
	int ret;

	ret = hv_cpu_init(0);
	WARN_ON(ret);

	/* Re-enable the hypercall page */
	rdmsrl(HV_X64_MSR_HYPERCALL, hypercall_msr.as_uint64);
	hypercall_msr.enable = 1;
	hypercall_msr.guest_physical_address =
		vmalloc_to_pfn(hv_hypercall_pg_saved);
	wrmsrl(HV_X64_MSR_HYPERCALL, hypercall_msr.as_uint64);

	hv_hypercall_pg = hv_hypercall_pg_saved;
	hv_hypercall_pg_saved = NULL;

	/*
	 * Reenlightenment notifications are disabled by hv_cpu_die(0),
	 * reenable them here if hv_reenlightenment_cb was previously set.
	 */
	if (hv_reenlightenment_cb)
		set_hv_tscchange_cb(hv_reenlightenment_cb);
}

/* Note: when the ops are called, only CPU0 is online and IRQs are disabled. */
static struct syscore_ops hv_syscore_ops = {
	.suspend	= hv_suspend,
	.resume		= hv_resume,
};

static void (* __initdata old_setup_percpu_clockev)(void);

static void __init hv_stimer_setup_percpu_clockev(void)
{
	/*
	 * Ignore any errors in setting up stimer clockevents
	 * as we can run with the LAPIC timer as a fallback.
	 */
	(void)hv_stimer_alloc(false);

	/*
	 * Still register the LAPIC timer, because the direct-mode STIMER is
	 * not supported by old versions of Hyper-V. This also allows users
	 * to switch to LAPIC timer via /sys, if they want to.
	 */
	if (old_setup_percpu_clockev)
		old_setup_percpu_clockev();
}

static void __init hv_get_partition_id(void)
{
	struct hv_get_partition_id *output_page;
	u64 status;
	unsigned long flags;

	local_irq_save(flags);
	output_page = *this_cpu_ptr(hyperv_pcpu_output_arg);
	status = hv_do_hypercall(HVCALL_GET_PARTITION_ID, NULL, output_page);
	if (!hv_result_success(status)) {
		/* No point in proceeding if this failed */
		pr_err("Failed to get partition ID: %lld\n", status);
		BUG();
	}
	hv_current_partition_id = output_page->partition_id;
	local_irq_restore(flags);
}

static u8 __init get_vtl(void)
{
	u64 control = HV_HYPERCALL_REP_COMP_1 | HVCALL_GET_VP_REGISTERS;
	struct hv_get_vp_registers_input *input;
	struct hv_get_vp_registers_output *output;
	unsigned long flags;
	u64 ret;

	local_irq_save(flags);
	input = *this_cpu_ptr(hyperv_pcpu_input_arg);
	output = (struct hv_get_vp_registers_output *)input;

	memset(input, 0, struct_size(input, element, 1));
	input->header.partitionid = HV_PARTITION_ID_SELF;
	input->header.vpindex = HV_VP_INDEX_SELF;
	input->header.inputvtl = 0;
	input->element[0].name0 = HV_X64_REGISTER_VSM_VP_STATUS;

	ret = hv_do_hypercall(control, input, output);
	if (hv_result_success(ret)) {
		ret = output->as64.low & HV_X64_VTL_MASK;
	} else {
		pr_err("Failed to get VTL(%lld) and set VTL to zero by default.\n", ret);
		ret = 0;
	}

	local_irq_restore(flags);
	return ret;
}

/*
 * This function is to be invoked early in the boot sequence after the
 * hypervisor has been detected.
 *
 * 1. Setup the hypercall page.
 * 2. Register Hyper-V specific clocksource.
 * 3. Setup Hyper-V specific APIC entry points.
 */
void __init hyperv_init(void)
{
	u64 guest_id;
	union hv_x64_msr_hypercall_contents hypercall_msr;
	int cpuhp;

	if (x86_hyper_type != X86_HYPER_MS_HYPERV)
		return;

	if (hv_common_init())
		return;

	/*
	 * The VP assist page is useless to a TDX guest: the only use we
	 * would have for it is lazy EOI, which can not be used with TDX.
	 */
	if (hv_isolation_type_tdx())
		hv_vp_assist_page = NULL;
	else
		hv_vp_assist_page = kcalloc(num_possible_cpus(),
					    sizeof(*hv_vp_assist_page),
					    GFP_KERNEL);
	if (!hv_vp_assist_page) {
		ms_hyperv.hints &= ~HV_X64_ENLIGHTENED_VMCS_RECOMMENDED;

		if (!hv_isolation_type_tdx())
			goto common_free;
	}

	if (ms_hyperv.paravisor_present && hv_isolation_type_snp()) {
		/* Negotiate GHCB Version. */
		if (!hv_ghcb_negotiate_protocol())
			hv_ghcb_terminate(SEV_TERM_SET_GEN,
					  GHCB_SEV_ES_PROT_UNSUPPORTED);

		hv_ghcb_pg = alloc_percpu(union hv_ghcb *);
		if (!hv_ghcb_pg)
			goto free_vp_assist_page;
	}

	cpuhp = cpuhp_setup_state(CPUHP_AP_HYPERV_ONLINE, "x86/hyperv_init:online",
				  hv_cpu_init, hv_cpu_die);
	if (cpuhp < 0)
		goto free_ghcb_page;

	/*
	 * Setup the hypercall page and enable hypercalls.
	 * 1. Register the guest ID
	 * 2. Enable the hypercall and register the hypercall page
	 *
	 * A TDX VM with no paravisor only uses TDX GHCI rather than hv_hypercall_pg:
	 * when the hypercall input is a page, such a VM must pass a decrypted
	 * page to Hyper-V, e.g. hv_post_message() uses the per-CPU page
	 * hyperv_pcpu_input_arg, which is decrypted if no paravisor is present.
	 *
	 * A TDX VM with the paravisor uses hv_hypercall_pg for most hypercalls,
	 * which are handled by the paravisor and the VM must use an encrypted
	 * input page: in such a VM, the hyperv_pcpu_input_arg is encrypted and
	 * used in the hypercalls, e.g. see hv_mark_gpa_visibility() and
	 * hv_arch_irq_unmask(). Such a VM uses TDX GHCI for two hypercalls:
	 * 1. HVCALL_SIGNAL_EVENT: see vmbus_set_event() and _hv_do_fast_hypercall8().
	 * 2. HVCALL_POST_MESSAGE: the input page must be a decrypted page, i.e.
	 * hv_post_message() in such a VM can't use the encrypted hyperv_pcpu_input_arg;
	 * instead, hv_post_message() uses the post_msg_page, which is decrypted
	 * in such a VM and is only used in such a VM.
	 */
	guest_id = hv_generate_guest_id(LINUX_VERSION_CODE);
	wrmsrl(HV_X64_MSR_GUEST_OS_ID, guest_id);

	/* With the paravisor, the VM must also write the ID via GHCB/GHCI */
	hv_ivm_msr_write(HV_X64_MSR_GUEST_OS_ID, guest_id);

	/* A TDX VM with no paravisor only uses TDX GHCI rather than hv_hypercall_pg */
	if (hv_isolation_type_tdx() && !ms_hyperv.paravisor_present)
		goto skip_hypercall_pg_init;

	hv_hypercall_pg = __vmalloc_node_range(PAGE_SIZE, 1, VMALLOC_START,
			VMALLOC_END, GFP_KERNEL, PAGE_KERNEL_ROX,
			VM_FLUSH_RESET_PERMS, NUMA_NO_NODE,
			__builtin_return_address(0));
	if (hv_hypercall_pg == NULL)
		goto clean_guest_os_id;

	rdmsrl(HV_X64_MSR_HYPERCALL, hypercall_msr.as_uint64);
	hypercall_msr.enable = 1;

	if (hv_root_partition) {
		struct page *pg;
		void *src;

		/*
		 * For the root partition, the hypervisor will set up its
		 * hypercall page. The hypervisor guarantees it will not show
		 * up in the root's address space. The root can't change the
		 * location of the hypercall page.
		 *
		 * Order is important here. We must enable the hypercall page
		 * so it is populated with code, then copy the code to an
		 * executable page.
		 */
		wrmsrl(HV_X64_MSR_HYPERCALL, hypercall_msr.as_uint64);

		pg = vmalloc_to_page(hv_hypercall_pg);
		src = memremap(hypercall_msr.guest_physical_address << PAGE_SHIFT, PAGE_SIZE,
				MEMREMAP_WB);
		BUG_ON(!src);
		memcpy_to_page(pg, 0, src, HV_HYP_PAGE_SIZE);
		memunmap(src);

		hv_remap_tsc_clocksource();
	} else {
		hypercall_msr.guest_physical_address = vmalloc_to_pfn(hv_hypercall_pg);
		wrmsrl(HV_X64_MSR_HYPERCALL, hypercall_msr.as_uint64);
	}

skip_hypercall_pg_init:
	/*
	 * Some versions of Hyper-V that provide IBT in guest VMs have a bug
	 * in that there's no ENDBR64 instruction at the entry to the
	 * hypercall page. Because hypercalls are invoked via an indirect call
	 * to the hypercall page, all hypercall attempts fail when IBT is
	 * enabled, and Linux panics. For such buggy versions, disable IBT.
	 *
	 * Fixed versions of Hyper-V always provide ENDBR64 on the hypercall
	 * page, so if future Linux kernel versions enable IBT for 32-bit
	 * builds, additional hypercall page hackery will be required here
	 * to provide an ENDBR32.
	 */
#ifdef CONFIG_X86_KERNEL_IBT
	if (cpu_feature_enabled(X86_FEATURE_IBT) &&
	    *(u32 *)hv_hypercall_pg != gen_endbr()) {
		setup_clear_cpu_cap(X86_FEATURE_IBT);
		pr_warn("Hyper-V: Disabling IBT because of Hyper-V bug\n");
	}
#endif

	/*
	 * hyperv_init() is called before LAPIC is initialized: see
	 * apic_intr_mode_init() -> x86_platform.apic_post_init() and
	 * apic_bsp_setup() -> setup_local_APIC(). The direct-mode STIMER
	 * depends on LAPIC, so hv_stimer_alloc() should be called from
	 * x86_init.timers.setup_percpu_clockev.
	 */
	old_setup_percpu_clockev = x86_init.timers.setup_percpu_clockev;
	x86_init.timers.setup_percpu_clockev = hv_stimer_setup_percpu_clockev;

	hv_apic_init();

	x86_init.pci.arch_init = hv_pci_init;

	register_syscore_ops(&hv_syscore_ops);

	hyperv_init_cpuhp = cpuhp;

	if (cpuid_ebx(HYPERV_CPUID_FEATURES) & HV_ACCESS_PARTITION_ID)
		hv_get_partition_id();

	BUG_ON(hv_root_partition && hv_current_partition_id == ~0ull);

#ifdef CONFIG_PCI_MSI
	/*
	 * If we're running as root, we want to create our own PCI MSI domain.
	 * We can't set this in hv_pci_init because that would be too late.
	 */
	if (hv_root_partition)
		x86_init.irqs.create_pci_msi_domain = hv_create_pci_msi_domain;
#endif

	/* Query the VMs extended capability once, so that it can be cached. */
	hv_query_ext_cap(0);

	/* Find the VTL */
	if (!ms_hyperv.paravisor_present && hv_isolation_type_snp())
		ms_hyperv.vtl = get_vtl();

	return;

clean_guest_os_id:
	wrmsrl(HV_X64_MSR_GUEST_OS_ID, 0);
	hv_ivm_msr_write(HV_X64_MSR_GUEST_OS_ID, 0);
	cpuhp_remove_state(cpuhp);
free_ghcb_page:
	free_percpu(hv_ghcb_pg);
free_vp_assist_page:
	kfree(hv_vp_assist_page);
	hv_vp_assist_page = NULL;
common_free:
	hv_common_free();
}

/*
 * This routine is called before kexec/kdump, it does the required cleanup.
 */
void hyperv_cleanup(void)
{
	union hv_x64_msr_hypercall_contents hypercall_msr;
	union hv_reference_tsc_msr tsc_msr;

	/* Reset our OS id */
	wrmsrl(HV_X64_MSR_GUEST_OS_ID, 0);
	hv_ivm_msr_write(HV_X64_MSR_GUEST_OS_ID, 0);

	/*
	 * Reset hypercall page reference before reset the page,
	 * let hypercall operations fail safely rather than
	 * panic the kernel for using invalid hypercall page
	 */
	hv_hypercall_pg = NULL;

	/* Reset the hypercall page */
	hypercall_msr.as_uint64 = hv_get_register(HV_X64_MSR_HYPERCALL);
	hypercall_msr.enable = 0;
	hv_set_register(HV_X64_MSR_HYPERCALL, hypercall_msr.as_uint64);

	/* Reset the TSC page */
	tsc_msr.as_uint64 = hv_get_register(HV_X64_MSR_REFERENCE_TSC);
	tsc_msr.enable = 0;
	hv_set_register(HV_X64_MSR_REFERENCE_TSC, tsc_msr.as_uint64);
}

void hyperv_report_panic(struct pt_regs *regs, long err, bool in_die)
{
	static bool panic_reported;
	u64 guest_id;

	if (in_die && !panic_on_oops)
		return;

	/*
	 * We prefer to report panic on 'die' chain as we have proper
	 * registers to report, but if we miss it (e.g. on BUG()) we need
	 * to report it on 'panic'.
	 */
	if (panic_reported)
		return;
	panic_reported = true;

	rdmsrl(HV_X64_MSR_GUEST_OS_ID, guest_id);

	wrmsrl(HV_X64_MSR_CRASH_P0, err);
	wrmsrl(HV_X64_MSR_CRASH_P1, guest_id);
	wrmsrl(HV_X64_MSR_CRASH_P2, regs->ip);
	wrmsrl(HV_X64_MSR_CRASH_P3, regs->ax);
	wrmsrl(HV_X64_MSR_CRASH_P4, regs->sp);

	/*
	 * Let Hyper-V know there is crash data available
	 */
	wrmsrl(HV_X64_MSR_CRASH_CTL, HV_CRASH_CTL_CRASH_NOTIFY);
}
EXPORT_SYMBOL_GPL(hyperv_report_panic);

bool hv_is_hyperv_initialized(void)
{
	union hv_x64_msr_hypercall_contents hypercall_msr;

	/*
	 * Ensure that we're really on Hyper-V, and not a KVM or Xen
	 * emulation of Hyper-V
	 */
	if (x86_hyper_type != X86_HYPER_MS_HYPERV)
		return false;

	/* A TDX VM with no paravisor uses TDX GHCI call rather than hv_hypercall_pg */
	if (hv_isolation_type_tdx() && !ms_hyperv.paravisor_present)
		return true;
	/*
	 * Verify that earlier initialization succeeded by checking
	 * that the hypercall page is setup
	 */
	hypercall_msr.as_uint64 = 0;
	rdmsrl(HV_X64_MSR_HYPERCALL, hypercall_msr.as_uint64);

	return hypercall_msr.enable;
}
EXPORT_SYMBOL_GPL(hv_is_hyperv_initialized);