summaryrefslogtreecommitdiffstats
path: root/arch/x86/kernel/kvm.c
blob: 9663ba31347c20141e4d1806731f2e8512239c52 (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
865
866
867
868
869
870
871
872
873
874
875
876
877
878
879
880
881
882
883
884
885
886
887
888
889
890
891
892
893
894
895
896
897
898
899
900
901
902
903
904
905
906
907
908
909
910
911
912
913
914
915
916
917
918
919
920
921
922
923
924
925
926
927
928
929
930
931
932
933
934
935
936
937
938
939
940
941
942
943
944
945
946
947
948
949
950
951
952
953
954
955
956
957
958
959
// SPDX-License-Identifier: GPL-2.0-or-later
/*
 * KVM paravirt_ops implementation
 *
 * Copyright (C) 2007, Red Hat, Inc., Ingo Molnar <mingo@redhat.com>
 * Copyright IBM Corporation, 2007
 *   Authors: Anthony Liguori <aliguori@us.ibm.com>
 */

#define pr_fmt(fmt) "kvm-guest: " fmt

#include <linux/context_tracking.h>
#include <linux/init.h>
#include <linux/irq.h>
#include <linux/kernel.h>
#include <linux/kvm_para.h>
#include <linux/cpu.h>
#include <linux/mm.h>
#include <linux/highmem.h>
#include <linux/hardirq.h>
#include <linux/notifier.h>
#include <linux/reboot.h>
#include <linux/hash.h>
#include <linux/sched.h>
#include <linux/slab.h>
#include <linux/kprobes.h>
#include <linux/nmi.h>
#include <linux/swait.h>
#include <asm/timer.h>
#include <asm/cpu.h>
#include <asm/traps.h>
#include <asm/desc.h>
#include <asm/tlbflush.h>
#include <asm/apic.h>
#include <asm/apicdef.h>
#include <asm/hypervisor.h>
#include <asm/tlb.h>
#include <asm/cpuidle_haltpoll.h>

DEFINE_STATIC_KEY_FALSE(kvm_async_pf_enabled);

static int kvmapf = 1;

static int __init parse_no_kvmapf(char *arg)
{
        kvmapf = 0;
        return 0;
}

early_param("no-kvmapf", parse_no_kvmapf);

static int steal_acc = 1;
static int __init parse_no_stealacc(char *arg)
{
        steal_acc = 0;
        return 0;
}

early_param("no-steal-acc", parse_no_stealacc);

static DEFINE_PER_CPU_DECRYPTED(struct kvm_vcpu_pv_apf_data, apf_reason) __aligned(64);
DEFINE_PER_CPU_DECRYPTED(struct kvm_steal_time, steal_time) __aligned(64) __visible;
static int has_steal_clock = 0;

/*
 * No need for any "IO delay" on KVM
 */
static void kvm_io_delay(void)
{
}

#define KVM_TASK_SLEEP_HASHBITS 8
#define KVM_TASK_SLEEP_HASHSIZE (1<<KVM_TASK_SLEEP_HASHBITS)

struct kvm_task_sleep_node {
	struct hlist_node link;
	struct swait_queue_head wq;
	u32 token;
	int cpu;
};

static struct kvm_task_sleep_head {
	raw_spinlock_t lock;
	struct hlist_head list;
} async_pf_sleepers[KVM_TASK_SLEEP_HASHSIZE];

static struct kvm_task_sleep_node *_find_apf_task(struct kvm_task_sleep_head *b,
						  u32 token)
{
	struct hlist_node *p;

	hlist_for_each(p, &b->list) {
		struct kvm_task_sleep_node *n =
			hlist_entry(p, typeof(*n), link);
		if (n->token == token)
			return n;
	}

	return NULL;
}

static bool kvm_async_pf_queue_task(u32 token, struct kvm_task_sleep_node *n)
{
	u32 key = hash_32(token, KVM_TASK_SLEEP_HASHBITS);
	struct kvm_task_sleep_head *b = &async_pf_sleepers[key];
	struct kvm_task_sleep_node *e;

	raw_spin_lock(&b->lock);
	e = _find_apf_task(b, token);
	if (e) {
		/* dummy entry exist -> wake up was delivered ahead of PF */
		hlist_del(&e->link);
		raw_spin_unlock(&b->lock);
		kfree(e);
		return false;
	}

	n->token = token;
	n->cpu = smp_processor_id();
	init_swait_queue_head(&n->wq);
	hlist_add_head(&n->link, &b->list);
	raw_spin_unlock(&b->lock);
	return true;
}

/*
 * kvm_async_pf_task_wait_schedule - Wait for pagefault to be handled
 * @token:	Token to identify the sleep node entry
 *
 * Invoked from the async pagefault handling code or from the VM exit page
 * fault handler. In both cases RCU is watching.
 */
void kvm_async_pf_task_wait_schedule(u32 token)
{
	struct kvm_task_sleep_node n;
	DECLARE_SWAITQUEUE(wait);

	lockdep_assert_irqs_disabled();

	if (!kvm_async_pf_queue_task(token, &n))
		return;

	for (;;) {
		prepare_to_swait_exclusive(&n.wq, &wait, TASK_UNINTERRUPTIBLE);
		if (hlist_unhashed(&n.link))
			break;

		local_irq_enable();
		schedule();
		local_irq_disable();
	}
	finish_swait(&n.wq, &wait);
}
EXPORT_SYMBOL_GPL(kvm_async_pf_task_wait_schedule);

static void apf_task_wake_one(struct kvm_task_sleep_node *n)
{
	hlist_del_init(&n->link);
	if (swq_has_sleeper(&n->wq))
		swake_up_one(&n->wq);
}

static void apf_task_wake_all(void)
{
	int i;

	for (i = 0; i < KVM_TASK_SLEEP_HASHSIZE; i++) {
		struct kvm_task_sleep_head *b = &async_pf_sleepers[i];
		struct kvm_task_sleep_node *n;
		struct hlist_node *p, *next;

		raw_spin_lock(&b->lock);
		hlist_for_each_safe(p, next, &b->list) {
			n = hlist_entry(p, typeof(*n), link);
			if (n->cpu == smp_processor_id())
				apf_task_wake_one(n);
		}
		raw_spin_unlock(&b->lock);
	}
}

void kvm_async_pf_task_wake(u32 token)
{
	u32 key = hash_32(token, KVM_TASK_SLEEP_HASHBITS);
	struct kvm_task_sleep_head *b = &async_pf_sleepers[key];
	struct kvm_task_sleep_node *n;

	if (token == ~0) {
		apf_task_wake_all();
		return;
	}

again:
	raw_spin_lock(&b->lock);
	n = _find_apf_task(b, token);
	if (!n) {
		/*
		 * async PF was not yet handled.
		 * Add dummy entry for the token.
		 */
		n = kzalloc(sizeof(*n), GFP_ATOMIC);
		if (!n) {
			/*
			 * Allocation failed! Busy wait while other cpu
			 * handles async PF.
			 */
			raw_spin_unlock(&b->lock);
			cpu_relax();
			goto again;
		}
		n->token = token;
		n->cpu = smp_processor_id();
		init_swait_queue_head(&n->wq);
		hlist_add_head(&n->link, &b->list);
	} else {
		apf_task_wake_one(n);
	}
	raw_spin_unlock(&b->lock);
	return;
}
EXPORT_SYMBOL_GPL(kvm_async_pf_task_wake);

noinstr u32 kvm_read_and_reset_apf_flags(void)
{
	u32 flags = 0;

	if (__this_cpu_read(apf_reason.enabled)) {
		flags = __this_cpu_read(apf_reason.flags);
		__this_cpu_write(apf_reason.flags, 0);
	}

	return flags;
}
EXPORT_SYMBOL_GPL(kvm_read_and_reset_apf_flags);

noinstr bool __kvm_handle_async_pf(struct pt_regs *regs, u32 token)
{
	u32 flags = kvm_read_and_reset_apf_flags();
	irqentry_state_t state;

	if (!flags)
		return false;

	state = irqentry_enter(regs);
	instrumentation_begin();

	/*
	 * If the host managed to inject an async #PF into an interrupt
	 * disabled region, then die hard as this is not going to end well
	 * and the host side is seriously broken.
	 */
	if (unlikely(!(regs->flags & X86_EFLAGS_IF)))
		panic("Host injected async #PF in interrupt disabled region\n");

	if (flags & KVM_PV_REASON_PAGE_NOT_PRESENT) {
		if (unlikely(!(user_mode(regs))))
			panic("Host injected async #PF in kernel mode\n");
		/* Page is swapped out by the host. */
		kvm_async_pf_task_wait_schedule(token);
	} else {
		WARN_ONCE(1, "Unexpected async PF flags: %x\n", flags);
	}

	instrumentation_end();
	irqentry_exit(regs, state);
	return true;
}

DEFINE_IDTENTRY_SYSVEC(sysvec_kvm_asyncpf_interrupt)
{
	struct pt_regs *old_regs = set_irq_regs(regs);
	u32 token;

	ack_APIC_irq();

	inc_irq_stat(irq_hv_callback_count);

	if (__this_cpu_read(apf_reason.enabled)) {
		token = __this_cpu_read(apf_reason.token);
		kvm_async_pf_task_wake(token);
		__this_cpu_write(apf_reason.token, 0);
		wrmsrl(MSR_KVM_ASYNC_PF_ACK, 1);
	}

	set_irq_regs(old_regs);
}

static void __init paravirt_ops_setup(void)
{
	pv_info.name = "KVM";

	if (kvm_para_has_feature(KVM_FEATURE_NOP_IO_DELAY))
		pv_ops.cpu.io_delay = kvm_io_delay;

#ifdef CONFIG_X86_IO_APIC
	no_timer_check = 1;
#endif
}

static void kvm_register_steal_time(void)
{
	int cpu = smp_processor_id();
	struct kvm_steal_time *st = &per_cpu(steal_time, cpu);

	if (!has_steal_clock)
		return;

	wrmsrl(MSR_KVM_STEAL_TIME, (slow_virt_to_phys(st) | KVM_MSR_ENABLED));
	pr_info("stealtime: cpu %d, msr %llx\n", cpu,
		(unsigned long long) slow_virt_to_phys(st));
}

static DEFINE_PER_CPU_DECRYPTED(unsigned long, kvm_apic_eoi) = KVM_PV_EOI_DISABLED;

static notrace void kvm_guest_apic_eoi_write(u32 reg, u32 val)
{
	/**
	 * This relies on __test_and_clear_bit to modify the memory
	 * in a way that is atomic with respect to the local CPU.
	 * The hypervisor only accesses this memory from the local CPU so
	 * there's no need for lock or memory barriers.
	 * An optimization barrier is implied in apic write.
	 */
	if (__test_and_clear_bit(KVM_PV_EOI_BIT, this_cpu_ptr(&kvm_apic_eoi)))
		return;
	apic->native_eoi_write(APIC_EOI, APIC_EOI_ACK);
}

static void kvm_guest_cpu_init(void)
{
	if (kvm_para_has_feature(KVM_FEATURE_ASYNC_PF_INT) && kvmapf) {
		u64 pa = slow_virt_to_phys(this_cpu_ptr(&apf_reason));

		WARN_ON_ONCE(!static_branch_likely(&kvm_async_pf_enabled));

		pa = slow_virt_to_phys(this_cpu_ptr(&apf_reason));
		pa |= KVM_ASYNC_PF_ENABLED | KVM_ASYNC_PF_DELIVERY_AS_INT;

		if (kvm_para_has_feature(KVM_FEATURE_ASYNC_PF_VMEXIT))
			pa |= KVM_ASYNC_PF_DELIVERY_AS_PF_VMEXIT;

		wrmsrl(MSR_KVM_ASYNC_PF_INT, HYPERVISOR_CALLBACK_VECTOR);

		wrmsrl(MSR_KVM_ASYNC_PF_EN, pa);
		__this_cpu_write(apf_reason.enabled, 1);
		pr_info("KVM setup async PF for cpu %d\n", smp_processor_id());
	}

	if (kvm_para_has_feature(KVM_FEATURE_PV_EOI)) {
		unsigned long pa;

		/* Size alignment is implied but just to make it explicit. */
		BUILD_BUG_ON(__alignof__(kvm_apic_eoi) < 4);
		__this_cpu_write(kvm_apic_eoi, 0);
		pa = slow_virt_to_phys(this_cpu_ptr(&kvm_apic_eoi))
			| KVM_MSR_ENABLED;
		wrmsrl(MSR_KVM_PV_EOI_EN, pa);
	}

	if (has_steal_clock)
		kvm_register_steal_time();
}

static void kvm_pv_disable_apf(void)
{
	if (!__this_cpu_read(apf_reason.enabled))
		return;

	wrmsrl(MSR_KVM_ASYNC_PF_EN, 0);
	__this_cpu_write(apf_reason.enabled, 0);

	pr_info("Unregister pv shared memory for cpu %d\n", smp_processor_id());
}

static void kvm_pv_guest_cpu_reboot(void *unused)
{
	/*
	 * We disable PV EOI before we load a new kernel by kexec,
	 * since MSR_KVM_PV_EOI_EN stores a pointer into old kernel's memory.
	 * New kernel can re-enable when it boots.
	 */
	if (kvm_para_has_feature(KVM_FEATURE_PV_EOI))
		wrmsrl(MSR_KVM_PV_EOI_EN, 0);
	kvm_pv_disable_apf();
	kvm_disable_steal_time();
}

static int kvm_pv_reboot_notify(struct notifier_block *nb,
				unsigned long code, void *unused)
{
	if (code == SYS_RESTART)
		on_each_cpu(kvm_pv_guest_cpu_reboot, NULL, 1);
	return NOTIFY_DONE;
}

static struct notifier_block kvm_pv_reboot_nb = {
	.notifier_call = kvm_pv_reboot_notify,
};

static u64 kvm_steal_clock(int cpu)
{
	u64 steal;
	struct kvm_steal_time *src;
	int version;

	src = &per_cpu(steal_time, cpu);
	do {
		version = src->version;
		virt_rmb();
		steal = src->steal;
		virt_rmb();
	} while ((version & 1) || (version != src->version));

	return steal;
}

void kvm_disable_steal_time(void)
{
	if (!has_steal_clock)
		return;

	wrmsr(MSR_KVM_STEAL_TIME, 0, 0);
}

static inline void __set_percpu_decrypted(void *ptr, unsigned long size)
{
	early_set_memory_decrypted((unsigned long) ptr, size);
}

/*
 * Iterate through all possible CPUs and map the memory region pointed
 * by apf_reason, steal_time and kvm_apic_eoi as decrypted at once.
 *
 * Note: we iterate through all possible CPUs to ensure that CPUs
 * hotplugged will have their per-cpu variable already mapped as
 * decrypted.
 */
static void __init sev_map_percpu_data(void)
{
	int cpu;

	if (!sev_active())
		return;

	for_each_possible_cpu(cpu) {
		__set_percpu_decrypted(&per_cpu(apf_reason, cpu), sizeof(apf_reason));
		__set_percpu_decrypted(&per_cpu(steal_time, cpu), sizeof(steal_time));
		__set_percpu_decrypted(&per_cpu(kvm_apic_eoi, cpu), sizeof(kvm_apic_eoi));
	}
}

static bool pv_tlb_flush_supported(void)
{
	return (kvm_para_has_feature(KVM_FEATURE_PV_TLB_FLUSH) &&
		!kvm_para_has_hint(KVM_HINTS_REALTIME) &&
		kvm_para_has_feature(KVM_FEATURE_STEAL_TIME));
}

static DEFINE_PER_CPU(cpumask_var_t, __pv_cpu_mask);

#ifdef CONFIG_SMP

static bool pv_ipi_supported(void)
{
	return kvm_para_has_feature(KVM_FEATURE_PV_SEND_IPI);
}

static bool pv_sched_yield_supported(void)
{
	return (kvm_para_has_feature(KVM_FEATURE_PV_SCHED_YIELD) &&
		!kvm_para_has_hint(KVM_HINTS_REALTIME) &&
	    kvm_para_has_feature(KVM_FEATURE_STEAL_TIME));
}

#define KVM_IPI_CLUSTER_SIZE	(2 * BITS_PER_LONG)

static void __send_ipi_mask(const struct cpumask *mask, int vector)
{
	unsigned long flags;
	int cpu, apic_id, icr;
	int min = 0, max = 0;
#ifdef CONFIG_X86_64
	__uint128_t ipi_bitmap = 0;
#else
	u64 ipi_bitmap = 0;
#endif
	long ret;

	if (cpumask_empty(mask))
		return;

	local_irq_save(flags);

	switch (vector) {
	default:
		icr = APIC_DM_FIXED | vector;
		break;
	case NMI_VECTOR:
		icr = APIC_DM_NMI;
		break;
	}

	for_each_cpu(cpu, mask) {
		apic_id = per_cpu(x86_cpu_to_apicid, cpu);
		if (!ipi_bitmap) {
			min = max = apic_id;
		} else if (apic_id < min && max - apic_id < KVM_IPI_CLUSTER_SIZE) {
			ipi_bitmap <<= min - apic_id;
			min = apic_id;
		} else if (apic_id < min + KVM_IPI_CLUSTER_SIZE) {
			max = apic_id < max ? max : apic_id;
		} else {
			ret = kvm_hypercall4(KVM_HC_SEND_IPI, (unsigned long)ipi_bitmap,
				(unsigned long)(ipi_bitmap >> BITS_PER_LONG), min, icr);
			WARN_ONCE(ret < 0, "kvm-guest: failed to send PV IPI: %ld",
				  ret);
			min = max = apic_id;
			ipi_bitmap = 0;
		}
		__set_bit(apic_id - min, (unsigned long *)&ipi_bitmap);
	}

	if (ipi_bitmap) {
		ret = kvm_hypercall4(KVM_HC_SEND_IPI, (unsigned long)ipi_bitmap,
			(unsigned long)(ipi_bitmap >> BITS_PER_LONG), min, icr);
		WARN_ONCE(ret < 0, "kvm-guest: failed to send PV IPI: %ld",
			  ret);
	}

	local_irq_restore(flags);
}

static void kvm_send_ipi_mask(const struct cpumask *mask, int vector)
{
	__send_ipi_mask(mask, vector);
}

static void kvm_send_ipi_mask_allbutself(const struct cpumask *mask, int vector)
{
	unsigned int this_cpu = smp_processor_id();
	struct cpumask *new_mask = this_cpu_cpumask_var_ptr(__pv_cpu_mask);
	const struct cpumask *local_mask;

	cpumask_copy(new_mask, mask);
	cpumask_clear_cpu(this_cpu, new_mask);
	local_mask = new_mask;
	__send_ipi_mask(local_mask, vector);
}

/*
 * Set the IPI entry points
 */
static void kvm_setup_pv_ipi(void)
{
	apic->send_IPI_mask = kvm_send_ipi_mask;
	apic->send_IPI_mask_allbutself = kvm_send_ipi_mask_allbutself;
	pr_info("setup PV IPIs\n");
}

static void kvm_smp_send_call_func_ipi(const struct cpumask *mask)
{
	int cpu;

	native_send_call_func_ipi(mask);

	/* Make sure other vCPUs get a chance to run if they need to. */
	for_each_cpu(cpu, mask) {
		if (vcpu_is_preempted(cpu)) {
			kvm_hypercall1(KVM_HC_SCHED_YIELD, per_cpu(x86_cpu_to_apicid, cpu));
			break;
		}
	}
}

static void __init kvm_smp_prepare_boot_cpu(void)
{
	/*
	 * Map the per-cpu variables as decrypted before kvm_guest_cpu_init()
	 * shares the guest physical address with the hypervisor.
	 */
	sev_map_percpu_data();

	kvm_guest_cpu_init();
	native_smp_prepare_boot_cpu();
	kvm_spinlock_init();
}

static void kvm_guest_cpu_offline(void)
{
	kvm_disable_steal_time();
	if (kvm_para_has_feature(KVM_FEATURE_PV_EOI))
		wrmsrl(MSR_KVM_PV_EOI_EN, 0);
	kvm_pv_disable_apf();
	apf_task_wake_all();
}

static int kvm_cpu_online(unsigned int cpu)
{
	local_irq_disable();
	kvm_guest_cpu_init();
	local_irq_enable();
	return 0;
}

static int kvm_cpu_down_prepare(unsigned int cpu)
{
	local_irq_disable();
	kvm_guest_cpu_offline();
	local_irq_enable();
	return 0;
}
#endif

static void kvm_flush_tlb_others(const struct cpumask *cpumask,
			const struct flush_tlb_info *info)
{
	u8 state;
	int cpu;
	struct kvm_steal_time *src;
	struct cpumask *flushmask = this_cpu_cpumask_var_ptr(__pv_cpu_mask);

	cpumask_copy(flushmask, cpumask);
	/*
	 * We have to call flush only on online vCPUs. And
	 * queue flush_on_enter for pre-empted vCPUs
	 */
	for_each_cpu(cpu, flushmask) {
		src = &per_cpu(steal_time, cpu);
		state = READ_ONCE(src->preempted);
		if ((state & KVM_VCPU_PREEMPTED)) {
			if (try_cmpxchg(&src->preempted, &state,
					state | KVM_VCPU_FLUSH_TLB))
				__cpumask_clear_cpu(cpu, flushmask);
		}
	}

	native_flush_tlb_others(flushmask, info);
}

static void __init kvm_guest_init(void)
{
	int i;

	paravirt_ops_setup();
	register_reboot_notifier(&kvm_pv_reboot_nb);
	for (i = 0; i < KVM_TASK_SLEEP_HASHSIZE; i++)
		raw_spin_lock_init(&async_pf_sleepers[i].lock);

	if (kvm_para_has_feature(KVM_FEATURE_STEAL_TIME)) {
		has_steal_clock = 1;
		pv_ops.time.steal_clock = kvm_steal_clock;
	}

	if (pv_tlb_flush_supported()) {
		pv_ops.mmu.flush_tlb_others = kvm_flush_tlb_others;
		pv_ops.mmu.tlb_remove_table = tlb_remove_table;
		pr_info("KVM setup pv remote TLB flush\n");
	}

	if (kvm_para_has_feature(KVM_FEATURE_PV_EOI))
		apic_set_eoi_write(kvm_guest_apic_eoi_write);

	if (kvm_para_has_feature(KVM_FEATURE_ASYNC_PF_INT) && kvmapf) {
		static_branch_enable(&kvm_async_pf_enabled);
		alloc_intr_gate(HYPERVISOR_CALLBACK_VECTOR, asm_sysvec_kvm_asyncpf_interrupt);
	}

#ifdef CONFIG_SMP
	smp_ops.smp_prepare_boot_cpu = kvm_smp_prepare_boot_cpu;
	if (pv_sched_yield_supported()) {
		smp_ops.send_call_func_ipi = kvm_smp_send_call_func_ipi;
		pr_info("setup PV sched yield\n");
	}
	if (cpuhp_setup_state_nocalls(CPUHP_AP_ONLINE_DYN, "x86/kvm:online",
				      kvm_cpu_online, kvm_cpu_down_prepare) < 0)
		pr_err("failed to install cpu hotplug callbacks\n");
#else
	sev_map_percpu_data();
	kvm_guest_cpu_init();
#endif

	/*
	 * Hard lockup detection is enabled by default. Disable it, as guests
	 * can get false positives too easily, for example if the host is
	 * overcommitted.
	 */
	hardlockup_detector_disable();
}

static noinline uint32_t __kvm_cpuid_base(void)
{
	if (boot_cpu_data.cpuid_level < 0)
		return 0;	/* So we don't blow up on old processors */

	if (boot_cpu_has(X86_FEATURE_HYPERVISOR))
		return hypervisor_cpuid_base("KVMKVMKVM\0\0\0", 0);

	return 0;
}

static inline uint32_t kvm_cpuid_base(void)
{
	static int kvm_cpuid_base = -1;

	if (kvm_cpuid_base == -1)
		kvm_cpuid_base = __kvm_cpuid_base();

	return kvm_cpuid_base;
}

bool kvm_para_available(void)
{
	return kvm_cpuid_base() != 0;
}
EXPORT_SYMBOL_GPL(kvm_para_available);

unsigned int kvm_arch_para_features(void)
{
	return cpuid_eax(kvm_cpuid_base() | KVM_CPUID_FEATURES);
}

unsigned int kvm_arch_para_hints(void)
{
	return cpuid_edx(kvm_cpuid_base() | KVM_CPUID_FEATURES);
}
EXPORT_SYMBOL_GPL(kvm_arch_para_hints);

static uint32_t __init kvm_detect(void)
{
	return kvm_cpuid_base();
}

static void __init kvm_apic_init(void)
{
#if defined(CONFIG_SMP)
	if (pv_ipi_supported())
		kvm_setup_pv_ipi();
#endif
}

static void __init kvm_init_platform(void)
{
	kvmclock_init();
	x86_platform.apic_post_init = kvm_apic_init;
}

const __initconst struct hypervisor_x86 x86_hyper_kvm = {
	.name			= "KVM",
	.detect			= kvm_detect,
	.type			= X86_HYPER_KVM,
	.init.guest_late_init	= kvm_guest_init,
	.init.x2apic_available	= kvm_para_available,
	.init.init_platform	= kvm_init_platform,
};

static __init int activate_jump_labels(void)
{
	if (has_steal_clock) {
		static_key_slow_inc(&paravirt_steal_enabled);
		if (steal_acc)
			static_key_slow_inc(&paravirt_steal_rq_enabled);
	}

	return 0;
}
arch_initcall(activate_jump_labels);

static __init int kvm_alloc_cpumask(void)
{
	int cpu;
	bool alloc = false;

	if (!kvm_para_available() || nopv)
		return 0;

	if (pv_tlb_flush_supported())
		alloc = true;

#if defined(CONFIG_SMP)
	if (pv_ipi_supported())
		alloc = true;
#endif

	if (alloc)
		for_each_possible_cpu(cpu) {
			zalloc_cpumask_var_node(per_cpu_ptr(&__pv_cpu_mask, cpu),
				GFP_KERNEL, cpu_to_node(cpu));
		}

	return 0;
}
arch_initcall(kvm_alloc_cpumask);

#ifdef CONFIG_PARAVIRT_SPINLOCKS

/* Kick a cpu by its apicid. Used to wake up a halted vcpu */
static void kvm_kick_cpu(int cpu)
{
	int apicid;
	unsigned long flags = 0;

	apicid = per_cpu(x86_cpu_to_apicid, cpu);
	kvm_hypercall2(KVM_HC_KICK_CPU, flags, apicid);
}

#include <asm/qspinlock.h>

static void kvm_wait(u8 *ptr, u8 val)
{
	unsigned long flags;

	if (in_nmi())
		return;

	local_irq_save(flags);

	if (READ_ONCE(*ptr) != val)
		goto out;

	/*
	 * halt until it's our turn and kicked. Note that we do safe halt
	 * for irq enabled case to avoid hang when lock info is overwritten
	 * in irq spinlock slowpath and no spurious interrupt occur to save us.
	 */
	if (arch_irqs_disabled_flags(flags))
		halt();
	else
		safe_halt();

out:
	local_irq_restore(flags);
}

#ifdef CONFIG_X86_32
__visible bool __kvm_vcpu_is_preempted(long cpu)
{
	struct kvm_steal_time *src = &per_cpu(steal_time, cpu);

	return !!(src->preempted & KVM_VCPU_PREEMPTED);
}
PV_CALLEE_SAVE_REGS_THUNK(__kvm_vcpu_is_preempted);

#else

#include <asm/asm-offsets.h>

extern bool __raw_callee_save___kvm_vcpu_is_preempted(long);

/*
 * Hand-optimize version for x86-64 to avoid 8 64-bit register saving and
 * restoring to/from the stack.
 */
asm(
".pushsection .text;"
".global __raw_callee_save___kvm_vcpu_is_preempted;"
".type __raw_callee_save___kvm_vcpu_is_preempted, @function;"
"__raw_callee_save___kvm_vcpu_is_preempted:"
"movq	__per_cpu_offset(,%rdi,8), %rax;"
"cmpb	$0, " __stringify(KVM_STEAL_TIME_preempted) "+steal_time(%rax);"
"setne	%al;"
"ret;"
".size __raw_callee_save___kvm_vcpu_is_preempted, .-__raw_callee_save___kvm_vcpu_is_preempted;"
".popsection");

#endif

/*
 * Setup pv_lock_ops to exploit KVM_FEATURE_PV_UNHALT if present.
 */
void __init kvm_spinlock_init(void)
{
	/*
	 * In case host doesn't support KVM_FEATURE_PV_UNHALT there is still an
	 * advantage of keeping virt_spin_lock_key enabled: virt_spin_lock() is
	 * preferred over native qspinlock when vCPU is preempted.
	 */
	if (!kvm_para_has_feature(KVM_FEATURE_PV_UNHALT)) {
		pr_info("PV spinlocks disabled, no host support\n");
		return;
	}

	/*
	 * Disable PV spinlocks and use native qspinlock when dedicated pCPUs
	 * are available.
	 */
	if (kvm_para_has_hint(KVM_HINTS_REALTIME)) {
		pr_info("PV spinlocks disabled with KVM_HINTS_REALTIME hints\n");
		goto out;
	}

	if (num_possible_cpus() == 1) {
		pr_info("PV spinlocks disabled, single CPU\n");
		goto out;
	}

	if (nopvspin) {
		pr_info("PV spinlocks disabled, forced by \"nopvspin\" parameter\n");
		goto out;
	}

	pr_info("PV spinlocks enabled\n");

	__pv_init_lock_hash();
	pv_ops.lock.queued_spin_lock_slowpath = __pv_queued_spin_lock_slowpath;
	pv_ops.lock.queued_spin_unlock =
		PV_CALLEE_SAVE(__pv_queued_spin_unlock);
	pv_ops.lock.wait = kvm_wait;
	pv_ops.lock.kick = kvm_kick_cpu;

	if (kvm_para_has_feature(KVM_FEATURE_STEAL_TIME)) {
		pv_ops.lock.vcpu_is_preempted =
			PV_CALLEE_SAVE(__kvm_vcpu_is_preempted);
	}
	/*
	 * When PV spinlock is enabled which is preferred over
	 * virt_spin_lock(), virt_spin_lock_key's value is meaningless.
	 * Just disable it anyway.
	 */
out:
	static_branch_disable(&virt_spin_lock_key);
}

#endif	/* CONFIG_PARAVIRT_SPINLOCKS */

#ifdef CONFIG_ARCH_CPUIDLE_HALTPOLL

static void kvm_disable_host_haltpoll(void *i)
{
	wrmsrl(MSR_KVM_POLL_CONTROL, 0);
}

static void kvm_enable_host_haltpoll(void *i)
{
	wrmsrl(MSR_KVM_POLL_CONTROL, 1);
}

void arch_haltpoll_enable(unsigned int cpu)
{
	if (!kvm_para_has_feature(KVM_FEATURE_POLL_CONTROL)) {
		pr_err_once("host does not support poll control\n");
		pr_err_once("host upgrade recommended\n");
		return;
	}

	/* Enable guest halt poll disables host halt poll */
	smp_call_function_single(cpu, kvm_disable_host_haltpoll, NULL, 1);
}
EXPORT_SYMBOL_GPL(arch_haltpoll_enable);

void arch_haltpoll_disable(unsigned int cpu)
{
	if (!kvm_para_has_feature(KVM_FEATURE_POLL_CONTROL))
		return;

	/* Enable guest halt poll disables host halt poll */
	smp_call_function_single(cpu, kvm_enable_host_haltpoll, NULL, 1);
}
EXPORT_SYMBOL_GPL(arch_haltpoll_disable);
#endif